diff options
1139 files changed, 25563 insertions, 15862 deletions
diff --git a/Documentation/ABI/testing/sysfs-block-rssd b/Documentation/ABI/testing/sysfs-block-rssd index 679ce3543122..beef30c046b0 100644 --- a/Documentation/ABI/testing/sysfs-block-rssd +++ b/Documentation/ABI/testing/sysfs-block-rssd @@ -1,26 +1,5 @@ -What: /sys/block/rssd*/registers -Date: March 2012 -KernelVersion: 3.3 -Contact: Asai Thambi S P <asamymuthupa@micron.com> -Description: This is a read-only file. Dumps below driver information and - hardware registers. - - S ACTive - - Command Issue - - Completed - - PORT IRQ STAT - - HOST IRQ STAT - - Allocated - - Commands in Q - What: /sys/block/rssd*/status Date: April 2012 KernelVersion: 3.4 Contact: Asai Thambi S P <asamymuthupa@micron.com> Description: This is a read-only file. Indicates the status of the device. - -What: /sys/block/rssd*/flags -Date: May 2012 -KernelVersion: 3.5 -Contact: Asai Thambi S P <asamymuthupa@micron.com> -Description: This is a read-only file. Dumps the flags in port and driver - data structure diff --git a/Documentation/ABI/testing/sysfs-class-mtd b/Documentation/ABI/testing/sysfs-class-mtd index db1ad7e34fc3..938ef71e2035 100644 --- a/Documentation/ABI/testing/sysfs-class-mtd +++ b/Documentation/ABI/testing/sysfs-class-mtd @@ -142,13 +142,14 @@ KernelVersion: 3.4 Contact: linux-mtd@lists.infradead.org Description: This allows the user to examine and adjust the criteria by which - mtd returns -EUCLEAN from mtd_read(). If the maximum number of - bit errors that were corrected on any single region comprising - an ecc step (as reported by the driver) equals or exceeds this - value, -EUCLEAN is returned. Otherwise, absent an error, 0 is - returned. Higher layers (e.g., UBI) use this return code as an - indication that an erase block may be degrading and should be - scrutinized as a candidate for being marked as bad. + mtd returns -EUCLEAN from mtd_read() and mtd_read_oob(). If the + maximum number of bit errors that were corrected on any single + region comprising an ecc step (as reported by the driver) equals + or exceeds this value, -EUCLEAN is returned. Otherwise, absent + an error, 0 is returned. Higher layers (e.g., UBI) use this + return code as an indication that an erase block may be + degrading and should be scrutinized as a candidate for being + marked as bad. The initial value may be specified by the flash device driver. If not, then the default value is ecc_strength. @@ -167,7 +168,7 @@ Description: block degradation, but high enough to avoid the consequences of a persistent return value of -EUCLEAN on devices where sticky bitflips occur. Note that if bitflip_threshold exceeds - ecc_strength, -EUCLEAN is never returned by mtd_read(). + ecc_strength, -EUCLEAN is never returned by the read operations. Conversely, if bitflip_threshold is zero, -EUCLEAN is always returned, absent a hard error. diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power index 31725ffeeb3a..217772615d02 100644 --- a/Documentation/ABI/testing/sysfs-power +++ b/Documentation/ABI/testing/sysfs-power @@ -231,3 +231,16 @@ Description: Reads from this file return a string consisting of the names of wakeup sources created with the help of /sys/power/wake_lock that are inactive at the moment, separated with spaces. + +What: /sys/power/pm_print_times +Date: May 2012 +Contact: Sameer Nanda <snanda@chromium.org> +Description: + The /sys/power/pm_print_times file allows user space to + control whether the time taken by devices to suspend and + resume is printed. These prints are useful for hunting down + devices that take too long to suspend or resume. + + Writing a "1" enables this printing while writing a "0" + disables it. The default value is "0". Reading from this file + will display the current value. diff --git a/Documentation/DocBook/media/v4l/controls.xml b/Documentation/DocBook/media/v4l/controls.xml index 676bc46f9c52..cda0dfb6769a 100644 --- a/Documentation/DocBook/media/v4l/controls.xml +++ b/Documentation/DocBook/media/v4l/controls.xml @@ -3988,7 +3988,7 @@ interface and may change in the future.</para> from RGB to Y'CbCr color space. </entry> </row> - <row id = "v4l2-jpeg-chroma-subsampling"> + <row> <entrytbl spanname="descr" cols="2"> <tbody valign="top"> <row> diff --git a/Documentation/DocBook/media/v4l/vidioc-g-ext-ctrls.xml b/Documentation/DocBook/media/v4l/vidioc-g-ext-ctrls.xml index e3d5afcdafbb..0a4b90fcf2da 100644 --- a/Documentation/DocBook/media/v4l/vidioc-g-ext-ctrls.xml +++ b/Documentation/DocBook/media/v4l/vidioc-g-ext-ctrls.xml @@ -284,13 +284,6 @@ These controls are described in <xref processing controls. These controls are described in <xref linkend="image-process-controls" />.</entry> </row> - <row> - <entry><constant>V4L2_CTRL_CLASS_JPEG</constant></entry> - <entry>0x9d0000</entry> - <entry>The class containing JPEG compression controls. -These controls are described in <xref - linkend="jpeg-controls" />.</entry> - </row> </tbody> </tgroup> </table> diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt index 5c8d74968090..fc103d7a0474 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.txt @@ -162,9 +162,9 @@ over a rather long period of time, but improvements are always welcome! when publicizing a pointer to a structure that can be traversed by an RCU read-side critical section. -5. If call_rcu(), or a related primitive such as call_rcu_bh() or - call_rcu_sched(), is used, the callback function must be - written to be called from softirq context. In particular, +5. If call_rcu(), or a related primitive such as call_rcu_bh(), + call_rcu_sched(), or call_srcu() is used, the callback function + must be written to be called from softirq context. In particular, it cannot block. 6. Since synchronize_rcu() can block, it cannot be called from @@ -202,11 +202,12 @@ over a rather long period of time, but improvements are always welcome! updater uses call_rcu_sched() or synchronize_sched(), then the corresponding readers must disable preemption, possibly by calling rcu_read_lock_sched() and rcu_read_unlock_sched(). - If the updater uses synchronize_srcu(), the the corresponding - readers must use srcu_read_lock() and srcu_read_unlock(), - and with the same srcu_struct. The rules for the expedited - primitives are the same as for their non-expedited counterparts. - Mixing things up will result in confusion and broken kernels. + If the updater uses synchronize_srcu() or call_srcu(), + the the corresponding readers must use srcu_read_lock() and + srcu_read_unlock(), and with the same srcu_struct. The rules for + the expedited primitives are the same as for their non-expedited + counterparts. Mixing things up will result in confusion and + broken kernels. One exception to this rule: rcu_read_lock() and rcu_read_unlock() may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh() @@ -333,14 +334,14 @@ over a rather long period of time, but improvements are always welcome! victim CPU from ever going offline.) 14. SRCU (srcu_read_lock(), srcu_read_unlock(), srcu_dereference(), - synchronize_srcu(), and synchronize_srcu_expedited()) may only - be invoked from process context. Unlike other forms of RCU, it - -is- permissible to block in an SRCU read-side critical section - (demarked by srcu_read_lock() and srcu_read_unlock()), hence the - "SRCU": "sleepable RCU". Please note that if you don't need - to sleep in read-side critical sections, you should be using - RCU rather than SRCU, because RCU is almost always faster and - easier to use than is SRCU. + synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu()) + may only be invoked from process context. Unlike other forms of + RCU, it -is- permissible to block in an SRCU read-side critical + section (demarked by srcu_read_lock() and srcu_read_unlock()), + hence the "SRCU": "sleepable RCU". Please note that if you + don't need to sleep in read-side critical sections, you should be + using RCU rather than SRCU, because RCU is almost always faster + and easier to use than is SRCU. If you need to enter your read-side critical section in a hardirq or exception handler, and then exit that same read-side @@ -353,8 +354,8 @@ over a rather long period of time, but improvements are always welcome! cleanup_srcu_struct(). These are passed a "struct srcu_struct" that defines the scope of a given SRCU domain. Once initialized, the srcu_struct is passed to srcu_read_lock(), srcu_read_unlock() - synchronize_srcu(), and synchronize_srcu_expedited(). A given - synchronize_srcu() waits only for SRCU read-side critical + synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu(). + A given synchronize_srcu() waits only for SRCU read-side critical sections governed by srcu_read_lock() and srcu_read_unlock() calls that have been passed the same srcu_struct. This property is what makes sleeping read-side critical sections tolerable -- @@ -374,7 +375,7 @@ over a rather long period of time, but improvements are always welcome! requiring SRCU's read-side deadlock immunity or low read-side realtime latency. - Note that, rcu_assign_pointer() relates to SRCU just as they do + Note that, rcu_assign_pointer() relates to SRCU just as it does to other forms of RCU. 15. The whole point of call_rcu(), synchronize_rcu(), and friends diff --git a/Documentation/RCU/rcubarrier.txt b/Documentation/RCU/rcubarrier.txt index e439a0edee22..38428c125135 100644 --- a/Documentation/RCU/rcubarrier.txt +++ b/Documentation/RCU/rcubarrier.txt @@ -79,8 +79,6 @@ complete. Pseudo-code using rcu_barrier() is as follows: 2. Execute rcu_barrier(). 3. Allow the module to be unloaded. -Quick Quiz #1: Why is there no srcu_barrier()? - The rcutorture module makes use of rcu_barrier in its exit function as follows: @@ -162,7 +160,7 @@ for any pre-existing callbacks to complete. Then lines 55-62 print status and do operation-specific cleanup, and then return, permitting the module-unload operation to be completed. -Quick Quiz #2: Is there any other situation where rcu_barrier() might +Quick Quiz #1: Is there any other situation where rcu_barrier() might be required? Your module might have additional complications. For example, if your @@ -242,7 +240,7 @@ reaches zero, as follows: 4 complete(&rcu_barrier_completion); 5 } -Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes +Quick Quiz #2: What happens if CPU 0's rcu_barrier_func() executes immediately (thus incrementing rcu_barrier_cpu_count to the value one), but the other CPU's rcu_barrier_func() invocations are delayed for a full grace period? Couldn't this result in @@ -259,12 +257,7 @@ so that your module may be safely unloaded. Answers to Quick Quizzes -Quick Quiz #1: Why is there no srcu_barrier()? - -Answer: Since there is no call_srcu(), there can be no outstanding SRCU - callbacks. Therefore, there is no need to wait for them. - -Quick Quiz #2: Is there any other situation where rcu_barrier() might +Quick Quiz #1: Is there any other situation where rcu_barrier() might be required? Answer: Interestingly enough, rcu_barrier() was not originally @@ -278,7 +271,7 @@ Answer: Interestingly enough, rcu_barrier() was not originally implementing rcutorture, and found that rcu_barrier() solves this problem as well. -Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes +Quick Quiz #2: What happens if CPU 0's rcu_barrier_func() executes immediately (thus incrementing rcu_barrier_cpu_count to the value one), but the other CPU's rcu_barrier_func() invocations are delayed for a full grace period? Couldn't this result in diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt index 4ddf3913fd8c..7dce8a17eac2 100644 --- a/Documentation/RCU/torture.txt +++ b/Documentation/RCU/torture.txt @@ -174,11 +174,20 @@ torture_type The type of RCU to test, with string values as follows: and synchronize_rcu_bh_expedited(). "srcu": srcu_read_lock(), srcu_read_unlock() and + call_srcu(). + + "srcu_sync": srcu_read_lock(), srcu_read_unlock() and synchronize_srcu(). "srcu_expedited": srcu_read_lock(), srcu_read_unlock() and synchronize_srcu_expedited(). + "srcu_raw": srcu_read_lock_raw(), srcu_read_unlock_raw(), + and call_srcu(). + + "srcu_raw_sync": srcu_read_lock_raw(), srcu_read_unlock_raw(), + and synchronize_srcu(). + "sched": preempt_disable(), preempt_enable(), and call_rcu_sched(). diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt index 6bbe8dcdc3da..69ee188515e7 100644 --- a/Documentation/RCU/whatisRCU.txt +++ b/Documentation/RCU/whatisRCU.txt @@ -833,9 +833,9 @@ sched: Critical sections Grace period Barrier SRCU: Critical sections Grace period Barrier - srcu_read_lock synchronize_srcu N/A - srcu_read_unlock synchronize_srcu_expedited - srcu_read_lock_raw + srcu_read_lock synchronize_srcu srcu_barrier + srcu_read_unlock call_srcu + srcu_read_lock_raw synchronize_srcu_expedited srcu_read_unlock_raw srcu_dereference diff --git a/Documentation/device-mapper/verity.txt b/Documentation/device-mapper/verity.txt index 32e48797a14f..9884681535ee 100644 --- a/Documentation/device-mapper/verity.txt +++ b/Documentation/device-mapper/verity.txt @@ -7,39 +7,39 @@ This target is read-only. Construction Parameters ======================= - <version> <dev> <hash_dev> <hash_start> + <version> <dev> <hash_dev> <data_block_size> <hash_block_size> <num_data_blocks> <hash_start_block> <algorithm> <digest> <salt> <version> - This is the version number of the on-disk format. + This is the type of the on-disk hash format. 0 is the original format used in the Chromium OS. - The salt is appended when hashing, digests are stored continuously and - the rest of the block is padded with zeros. + The salt is appended when hashing, digests are stored continuously and + the rest of the block is padded with zeros. 1 is the current format that should be used for new devices. - The salt is prepended when hashing and each digest is - padded with zeros to the power of two. + The salt is prepended when hashing and each digest is + padded with zeros to the power of two. <dev> - This is the device containing the data the integrity of which needs to be + This is the device containing data, the integrity of which needs to be checked. It may be specified as a path, like /dev/sdaX, or a device number, <major>:<minor>. <hash_dev> - This is the device that that supplies the hash tree data. It may be + This is the device that supplies the hash tree data. It may be specified similarly to the device path and may be the same device. If the - same device is used, the hash_start should be outside of the dm-verity - configured device size. + same device is used, the hash_start should be outside the configured + dm-verity device. <data_block_size> - The block size on a data device. Each block corresponds to one digest on - the hash device. + The block size on a data device in bytes. + Each block corresponds to one digest on the hash device. <hash_block_size> - The size of a hash block. + The size of a hash block in bytes. <num_data_blocks> The number of data blocks on the data device. Additional blocks are @@ -65,7 +65,7 @@ Construction Parameters Theory of operation =================== -dm-verity is meant to be setup as part of a verified boot path. This +dm-verity is meant to be set up as part of a verified boot path. This may be anything ranging from a boot using tboot or trustedgrub to just booting from a known-good device (like a USB drive or CD). @@ -73,20 +73,20 @@ When a dm-verity device is configured, it is expected that the caller has been authenticated in some way (cryptographic signatures, etc). After instantiation, all hashes will be verified on-demand during disk access. If they cannot be verified up to the root node of the -tree, the root hash, then the I/O will fail. This should identify +tree, the root hash, then the I/O will fail. This should detect tampering with any data on the device and the hash data. Cryptographic hashes are used to assert the integrity of the device on a -per-block basis. This allows for a lightweight hash computation on first read -into the page cache. Block hashes are stored linearly-aligned to the nearest -block the size of a page. +per-block basis. This allows for a lightweight hash computation on first read +into the page cache. Block hashes are stored linearly, aligned to the nearest +block size. Hash Tree --------- Each node in the tree is a cryptographic hash. If it is a leaf node, the hash -is of some block data on disk. If it is an intermediary node, then the hash is -of a number of child nodes. +of some data block on disk is calculated. If it is an intermediary node, +the hash of a number of child nodes is calculated. Each entry in the tree is a collection of neighboring nodes that fit in one block. The number is determined based on block_size and the size of the @@ -110,63 +110,23 @@ alg = sha256, num_blocks = 32768, block_size = 4096 On-disk format ============== -Below is the recommended on-disk format. The verity kernel code does not -read the on-disk header. It only reads the hash blocks which directly -follow the header. It is expected that a user-space tool will verify the -integrity of the verity_header and then call dmsetup with the correct -parameters. Alternatively, the header can be omitted and the dmsetup -parameters can be passed via the kernel command-line in a rooted chain -of trust where the command-line is verified. +The verity kernel code does not read the verity metadata on-disk header. +It only reads the hash blocks which directly follow the header. +It is expected that a user-space tool will verify the integrity of the +verity header. -The on-disk format is especially useful in cases where the hash blocks -are on a separate partition. The magic number allows easy identification -of the partition contents. Alternatively, the hash blocks can be stored -in the same partition as the data to be verified. In such a configuration -the filesystem on the partition would be sized a little smaller than -the full-partition, leaving room for the hash blocks. - -struct superblock { - uint8_t signature[8] - "verity\0\0"; - - uint8_t version; - 1 - current format - - uint8_t data_block_bits; - log2(data block size) - - uint8_t hash_block_bits; - log2(hash block size) - - uint8_t pad1[1]; - zero padding - - uint16_t salt_size; - big-endian salt size - - uint8_t pad2[2]; - zero padding - - uint32_t data_blocks_hi; - big-endian high 32 bits of the 64-bit number of data blocks - - uint32_t data_blocks_lo; - big-endian low 32 bits of the 64-bit number of data blocks - - uint8_t algorithm[16]; - cryptographic algorithm - - uint8_t salt[384]; - salt (the salt size is specified above) - - uint8_t pad3[88]; - zero padding to 512-byte boundary -} +Alternatively, the header can be omitted and the dmsetup parameters can +be passed via the kernel command-line in a rooted chain of trust where +the command-line is verified. Directly following the header (and with sector number padded to the next hash block boundary) are the hash blocks which are stored a depth at a time (starting from the root), sorted in order of increasing index. +The full specification of kernel parameters and on-disk metadata format +is available at the cryptsetup project's wiki page + http://code.google.com/p/cryptsetup/wiki/DMVerity + Status ====== V (for Valid) is returned if every check performed so far was valid. @@ -174,21 +134,22 @@ If any check failed, C (for Corruption) is returned. Example ======= - -Setup a device: - dmsetup create vroot --table \ - "0 2097152 "\ - "verity 1 /dev/sda1 /dev/sda2 4096 4096 2097152 1 "\ +Set up a device: + # dmsetup create vroot --readonly --table \ + "0 2097152 verity 1 /dev/sda1 /dev/sda2 4096 4096 262144 1 sha256 "\ "4392712ba01368efdf14b05c76f9e4df0d53664630b5d48632ed17a137f39076 "\ "1234000000000000000000000000000000000000000000000000000000000000" A command line tool veritysetup is available to compute or verify -the hash tree or activate the kernel driver. This is available from -the LVM2 upstream repository and may be supplied as a package called -device-mapper-verity-tools: - git://sources.redhat.com/git/lvm2 - http://sourceware.org/git/?p=lvm2.git - http://sourceware.org/cgi-bin/cvsweb.cgi/LVM2/verity?cvsroot=lvm2 - -veritysetup -a vroot /dev/sda1 /dev/sda2 \ - 4392712ba01368efdf14b05c76f9e4df0d53664630b5d48632ed17a137f39076 +the hash tree or activate the kernel device. This is available from +the cryptsetup upstream repository http://code.google.com/p/cryptsetup/ +(as a libcryptsetup extension). + +Create hash on the device: + # veritysetup format /dev/sda1 /dev/sda2 + ... + Root hash: 4392712ba01368efdf14b05c76f9e4df0d53664630b5d48632ed17a137f39076 + +Activate the device: + # veritysetup create vroot /dev/sda1 /dev/sda2 \ + 4392712ba01368efdf14b05c76f9e4df0d53664630b5d48632ed17a137f39076 diff --git a/Documentation/devicetree/bindings/input/fsl-mma8450.txt b/Documentation/devicetree/bindings/input/fsl-mma8450.txt index a00c94ccbdee..0b96e5737d3a 100644 --- a/Documentation/devicetree/bindings/input/fsl-mma8450.txt +++ b/Documentation/devicetree/bindings/input/fsl-mma8450.txt @@ -2,6 +2,7 @@ Required properties: - compatible : "fsl,mma8450". +- reg: the I2C address of MMA8450 Example: diff --git a/Documentation/devicetree/bindings/mfd/mc13xxx.txt b/Documentation/devicetree/bindings/mfd/mc13xxx.txt index 19f6af47a792..baf07987ae68 100644 --- a/Documentation/devicetree/bindings/mfd/mc13xxx.txt +++ b/Documentation/devicetree/bindings/mfd/mc13xxx.txt @@ -46,8 +46,8 @@ Examples: ecspi@70010000 { /* ECSPI1 */ fsl,spi-num-chipselects = <2>; - cs-gpios = <&gpio3 24 0>, /* GPIO4_24 */ - <&gpio3 25 0>; /* GPIO4_25 */ + cs-gpios = <&gpio4 24 0>, /* GPIO4_24 */ + <&gpio4 25 0>; /* GPIO4_25 */ status = "okay"; pmic: mc13892@0 { diff --git a/Documentation/devicetree/bindings/mfd/tps65910.txt b/Documentation/devicetree/bindings/mfd/tps65910.txt index 645f5eaadb3f..d2802d4717bc 100644 --- a/Documentation/devicetree/bindings/mfd/tps65910.txt +++ b/Documentation/devicetree/bindings/mfd/tps65910.txt @@ -17,18 +17,46 @@ Required properties: device need to be present. The definition for each of these nodes is defined using the standard binding for regulators found at Documentation/devicetree/bindings/regulator/regulator.txt. + The regulator is matched with the regulator-compatible. - The valid names for regulators are: + The valid regulator-compatible values are: tps65910: vrtc, vio, vdd1, vdd2, vdd3, vdig1, vdig2, vpll, vdac, vaux1, vaux2, vaux33, vmmc tps65911: vrtc, vio, vdd1, vdd3, vddctrl, ldo1, ldo2, ldo3, ldo4, ldo5, ldo6, ldo7, ldo8 +- xxx-supply: Input voltage supply regulator. + These entries are require if regulators are enabled for a device. Missing of these + properties can cause the regulator registration fails. + If some of input supply is powered through battery or always-on supply then + also it is require to have these parameters with proper node handle of always + on power supply. + tps65910: + vcc1-supply: VDD1 input. + vcc2-supply: VDD2 input. + vcc3-supply: VAUX33 and VMMC input. + vcc4-supply: VAUX1 and VAUX2 input. + vcc5-supply: VPLL and VDAC input. + vcc6-supply: VDIG1 and VDIG2 input. + vcc7-supply: VRTC input. + vccio-supply: VIO input. + tps65911: + vcc1-supply: VDD1 input. + vcc2-supply: VDD2 input. + vcc3-supply: LDO6, LDO7 and LDO8 input. + vcc4-supply: LDO5 input. + vcc5-supply: LDO3 and LDO4 input. + vcc6-supply: LDO1 and LDO2 input. + vcc7-supply: VRTC input. + vccio-supply: VIO input. + Optional properties: - ti,vmbch-threshold: (tps65911) main battery charged threshold comparator. (see VMBCH_VSEL in TPS65910 datasheet) - ti,vmbch2-threshold: (tps65911) main battery discharged threshold comparator. (see VMBCH_VSEL in TPS65910 datasheet) +- ti,en-ck32k-xtal: enable external 32-kHz crystal oscillator (see CK32K_CTRL + in TPS6591X datasheet) - ti,en-gpio-sleep: enable sleep control for gpios There should be 9 entries here, one for each gpio. @@ -56,74 +84,110 @@ Example: ti,en-gpio-sleep = <0 0 1 0 0 0 0 0 0>; + vcc1-supply = <®_parent>; + vcc2-supply = <&some_reg>; + vcc3-supply = <...>; + vcc4-supply = <...>; + vcc5-supply = <...>; + vcc6-supply = <...>; + vcc7-supply = <...>; + vccio-supply = <...>; + regulators { - vdd1_reg: vdd1 { + #address-cells = <1>; + #size-cells = <0>; + + vdd1_reg: regulator@0 { + regulator-compatible = "vdd1"; + reg = <0>; regulator-min-microvolt = < 600000>; regulator-max-microvolt = <1500000>; regulator-always-on; regulator-boot-on; ti,regulator-ext-sleep-control = <0>; }; - vdd2_reg: vdd2 { + vdd2_reg: regulator@1 { + regulator-compatible = "vdd2"; + reg = <1>; regulator-min-microvolt = < 600000>; regulator-max-microvolt = <1500000>; regulator-always-on; regulator-boot-on; ti,regulator-ext-sleep-control = <4>; }; - vddctrl_reg: vddctrl { + vddctrl_reg: regulator@2 { + regulator-compatible = "vddctrl"; + reg = <2>; regulator-min-microvolt = < 600000>; regulator-max-microvolt = <1400000>; regulator-always-on; regulator-boot-on; ti,regulator-ext-sleep-control = <0>; }; - vio_reg: vio { + vio_reg: regulator@3 { + regulator-compatible = "vio"; + reg = <3>; regulator-min-microvolt = <1500000>; regulator-max-microvolt = <1800000>; regulator-always-on; regulator-boot-on; ti,regulator-ext-sleep-control = <1>; }; - ldo1_reg: ldo1 { + ldo1_reg: regulator@4 { + regulator-compatible = "ldo1"; + reg = <4>; regulator-min-microvolt = <1000000>; regulator-max-microvolt = <3300000>; ti,regulator-ext-sleep-control = <0>; }; - ldo2_reg: ldo2 { + ldo2_reg: regulator@5 { + regulator-compatible = "ldo2"; + reg = <5>; regulator-min-microvolt = <1050000>; regulator-max-microvolt = <1050000>; ti,regulator-ext-sleep-control = <0>; }; - ldo3_reg: ldo3 { + ldo3_reg: regulator@6 { + regulator-compatible = "ldo3"; + reg = <6>; regulator-min-microvolt = <1000000>; regulator-max-microvolt = <3300000>; ti,regulator-ext-sleep-control = <0>; }; - ldo4_reg: ldo4 { + ldo4_reg: regulator@7 { + regulator-compatible = "ldo4"; + reg = <7>; regulator-min-microvolt = <1000000>; regulator-max-microvolt = <3300000>; regulator-always-on; ti,regulator-ext-sleep-control = <0>; }; - ldo5_reg: ldo5 { + ldo5_reg: regulator@8 { + regulator-compatible = "ldo5"; + reg = <8>; regulator-min-microvolt = <1000000>; regulator-max-microvolt = <3300000>; ti,regulator-ext-sleep-control = <0>; }; - ldo6_reg: ldo6 { + ldo6_reg: regulator@9 { + regulator-compatible = "ldo6"; + reg = <9>; regulator-min-microvolt = <1200000>; regulator-max-microvolt = <1200000>; ti,regulator-ext-sleep-control = <0>; }; - ldo7_reg: ldo7 { + ldo7_reg: regulator@10 { + regulator-compatible = "ldo7"; + reg = <10>; regulator-min-microvolt = <1200000>; regulator-max-microvolt = <1200000>; regulator-always-on; regulator-boot-on; ti,regulator-ext-sleep-control = <1>; }; - ldo8_reg: ldo8 { + ldo8_reg: regulator@11 { + regulator-compatible = "ldo8"; + reg = <11>; regulator-min-microvolt = <1000000>; regulator-max-microvolt = <3300000>; regulator-always-on; diff --git a/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt index 0d93b4b0e0e3..bd9be0b5bc20 100644 --- a/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt +++ b/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt @@ -3,21 +3,22 @@ The Enhanced Secure Digital Host Controller provides an interface for MMC, SD, and SDIO types of memory cards. +This file documents differences between the core properties described +by mmc.txt and the properties used by the sdhci-esdhc driver. + Required properties: - - compatible : should be - "fsl,<chip>-esdhc", "fsl,esdhc" - - reg : should contain eSDHC registers location and length. - - interrupts : should contain eSDHC interrupt. - interrupt-parent : interrupt source phandle. - clock-frequency : specifies eSDHC base clock frequency. - - sdhci,wp-inverted : (optional) specifies that eSDHC controller - reports inverted write-protect state; New devices should use - the generic "wp-inverted" property. - - sdhci,1-bit-only : (optional) specifies that a controller can - only handle 1-bit data transfers. New devices should use the - generic "bus-width = <1>" property. - - sdhci,auto-cmd12: (optional) specifies that a controller can - only handle auto CMD12. + +Optional properties: + - sdhci,wp-inverted : specifies that eSDHC controller reports + inverted write-protect state; New devices should use the generic + "wp-inverted" property. + - sdhci,1-bit-only : specifies that a controller can only handle + 1-bit data transfers. New devices should use the generic + "bus-width = <1>" property. + - sdhci,auto-cmd12: specifies that a controller can only handle auto + CMD12. Example: diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt index c7e404b3ef05..70cd49b1caa8 100644 --- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt +++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt @@ -3,17 +3,15 @@ The Enhanced Secure Digital Host Controller on Freescale i.MX family provides an interface for MMC, SD, and SDIO types of memory cards. +This file documents differences between the core properties described +by mmc.txt and the properties used by the sdhci-esdhc-imx driver. + Required properties: - compatible : Should be "fsl,<chip>-esdhc" -- reg : Should contain eSDHC registers location and length -- interrupts : Should contain eSDHC interrupt Optional properties: -- non-removable : Indicate the card is wired to host permanently - fsl,cd-internal : Indicate to use controller internal card detection - fsl,wp-internal : Indicate to use controller internal write protection -- cd-gpios : Specify GPIOs for card detection -- wp-gpios : Specify GPIOs for write protection Examples: @@ -29,6 +27,6 @@ esdhc@70008000 { compatible = "fsl,imx51-esdhc"; reg = <0x70008000 0x4000>; interrupts = <2>; - cd-gpios = <&gpio0 6 0>; /* GPIO1_6 */ - wp-gpios = <&gpio0 5 0>; /* GPIO1_5 */ + cd-gpios = <&gpio1 6 0>; /* GPIO1_6 */ + wp-gpios = <&gpio1 5 0>; /* GPIO1_5 */ }; diff --git a/Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt b/Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt index d64aea5a4203..0e5e2ec4001d 100644 --- a/Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt +++ b/Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt @@ -1,8 +1,9 @@ MMC/SD/SDIO slot directly connected to a SPI bus +This file documents differences between the core properties described +by mmc.txt and the properties used by the mmc_spi driver. + Required properties: -- compatible : should be "mmc-spi-slot". -- reg : should specify SPI address (chip-select number). - spi-max-frequency : maximum frequency for this device (Hz). - voltage-ranges : two cells are required, first cell specifies minimum slot voltage (mV), second cell specifies maximum slot voltage (mV). @@ -11,8 +12,7 @@ Required properties: Optional properties: - gpios : may specify GPIOs in this order: Card-Detect GPIO, Write-Protect GPIO. Note that this does not follow the - binding from mmc.txt, for historic reasons. -- interrupts : the interrupt of a card detect interrupt. + binding from mmc.txt, for historical reasons. - interrupt-parent : the phandle for the interrupt controller that services interrupts for this device. diff --git a/Documentation/devicetree/bindings/mmc/mmc.txt b/Documentation/devicetree/bindings/mmc/mmc.txt index 6e70dcde0a71..8a6811f4a02f 100644 --- a/Documentation/devicetree/bindings/mmc/mmc.txt +++ b/Documentation/devicetree/bindings/mmc/mmc.txt @@ -2,13 +2,17 @@ These properties are common to multiple MMC host controllers. Any host that requires the respective functionality should implement them using these definitions. +Interpreted by the OF core: +- reg: Registers location and length. +- interrupts: Interrupts used by the MMC controller. + Required properties: - bus-width: Number of data lines, can be <1>, <4>, or <8> Optional properties: -- cd-gpios : Specify GPIOs for card detection, see gpio binding -- wp-gpios : Specify GPIOs for write protection, see gpio binding -- cd-inverted: when present, polarity on the wp gpio line is inverted +- cd-gpios: Specify GPIOs for card detection, see gpio binding +- wp-gpios: Specify GPIOs for write protection, see gpio binding +- cd-inverted: when present, polarity on the cd gpio line is inverted - wp-inverted: when present, polarity on the wp gpio line is inverted - non-removable: non-removable slot (like eMMC) - max-frequency: maximum operating clock frequency diff --git a/Documentation/devicetree/bindings/mmc/mmci.txt b/Documentation/devicetree/bindings/mmc/mmci.txt index 14a81d526118..2b584cae352a 100644 --- a/Documentation/devicetree/bindings/mmc/mmci.txt +++ b/Documentation/devicetree/bindings/mmc/mmci.txt @@ -1,19 +1,15 @@ * ARM PrimeCell MultiMedia Card Interface (MMCI) PL180/1 -The ARM PrimeCell MMCI PL180 and PL181 provides and interface for +The ARM PrimeCell MMCI PL180 and PL181 provides an interface for reading and writing to MultiMedia and SD cards alike. +This file documents differences between the core properties described +by mmc.txt and the properties used by the mmci driver. + Required properties: - compatible : contains "arm,pl18x", "arm,primecell". -- reg : contains pl18x registers and length. -- interrupts : contains the device IRQ(s). - arm,primecell-periphid : contains the PrimeCell Peripheral ID. Optional properties: -- wp-gpios : contains any write protect (ro) gpios -- cd-gpios : contains any card detection gpios -- cd-inverted : indicates whether the cd gpio is inverted -- max-frequency : contains the maximum operating frequency -- bus-width : number of data lines, can be <1>, <4>, or <8> - mmc-cap-mmc-highspeed : indicates whether MMC is high speed capable - mmc-cap-sd-highspeed : indicates whether SD is high speed capable diff --git a/Documentation/devicetree/bindings/mmc/mxs-mmc.txt b/Documentation/devicetree/bindings/mmc/mxs-mmc.txt index 14d870a9e3db..54949f6faede 100644 --- a/Documentation/devicetree/bindings/mmc/mxs-mmc.txt +++ b/Documentation/devicetree/bindings/mmc/mxs-mmc.txt @@ -3,16 +3,14 @@ The Freescale MXS Synchronous Serial Ports (SSP) can act as a MMC controller to support MMC, SD, and SDIO types of memory cards. +This file documents differences between the core properties in mmc.txt +and the properties used by the mxsmmc driver. + Required properties: - compatible: Should be "fsl,<chip>-mmc". The supported chips include imx23 and imx28. -- reg: Should contain registers location and length - interrupts: Should contain ERROR and DMA interrupts - fsl,ssp-dma-channel: APBH DMA channel for the SSP -- bus-width: Number of data lines, can be <1>, <4>, or <8> - -Optional properties: -- wp-gpios: Specify GPIOs for write protection Examples: diff --git a/Documentation/devicetree/bindings/mmc/nvidia-sdhci.txt b/Documentation/devicetree/bindings/mmc/nvidia-sdhci.txt index f77c3031607f..c6d7b11db9eb 100644 --- a/Documentation/devicetree/bindings/mmc/nvidia-sdhci.txt +++ b/Documentation/devicetree/bindings/mmc/nvidia-sdhci.txt @@ -3,15 +3,13 @@ This controller on Tegra family SoCs provides an interface for MMC, SD, and SDIO types of memory cards. +This file documents differences between the core properties described +by mmc.txt and the properties used by the sdhci-tegra driver. + Required properties: - compatible : Should be "nvidia,<chip>-sdhci" -- reg : Should contain SD/MMC registers location and length -- interrupts : Should contain SD/MMC interrupt -- bus-width : Number of data lines, can be <1>, <4>, or <8> Optional properties: -- cd-gpios : Specify GPIOs for card detection -- wp-gpios : Specify GPIOs for write protection - power-gpios : Specify GPIOs for power control Example: diff --git a/Documentation/devicetree/bindings/mmc/sdhci-pxa.txt b/Documentation/devicetree/bindings/mmc/sdhci-pxa.txt new file mode 100644 index 000000000000..dbe98a3c183a --- /dev/null +++ b/Documentation/devicetree/bindings/mmc/sdhci-pxa.txt @@ -0,0 +1,21 @@ +* Marvell sdhci-pxa v2/v3 controller + +This file documents differences between the core properties in mmc.txt +and the properties used by the sdhci-pxav2 and sdhci-pxav3 drivers. + +Required properties: +- compatible: Should be "mrvl,pxav2-mmc" or "mrvl,pxav3-mmc". + +Optional properties: +- mrvl,clk-delay-cycles: Specify a number of cycles to delay for tuning. + +Example: + +sdhci@d4280800 { + compatible = "mrvl,pxav3-mmc"; + reg = <0xd4280800 0x800>; + bus-width = <8>; + interrupts = <27>; + non-removable; + mrvl,clk-delay-cycles = <31>; +}; diff --git a/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt b/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt index 8a53958c9a9f..be76a23b34c4 100644 --- a/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt +++ b/Documentation/devicetree/bindings/mmc/ti-omap-hsmmc.txt @@ -3,21 +3,20 @@ The Highspeed MMC Host Controller on TI OMAP family provides an interface for MMC, SD, and SDIO types of memory cards. +This file documents differences between the core properties described +by mmc.txt and the properties used by the omap_hsmmc driver. + Required properties: - compatible: Should be "ti,omap2-hsmmc", for OMAP2 controllers Should be "ti,omap3-hsmmc", for OMAP3 controllers Should be "ti,omap4-hsmmc", for OMAP4 controllers - ti,hwmods: Must be "mmc<n>", n is controller instance starting 1 -- reg : should contain hsmmc registers location and length Optional properties: ti,dual-volt: boolean, supports dual voltage cards <supply-name>-supply: phandle to the regulator device tree node "supply-name" examples are "vmmc", "vmmc_aux" etc -bus-width: Number of data lines, default assumed is 1 if the property is missing. -cd-gpios: GPIOs for card detection -wp-gpios: GPIOs for write protection ti,non-removable: non-removable slot (like eMMC) ti,needs-special-reset: Requires a special softreset sequence diff --git a/Documentation/devicetree/bindings/net/fsl-fec.txt b/Documentation/devicetree/bindings/net/fsl-fec.txt index 7ab9e1a2d8be..4616fc28ee86 100644 --- a/Documentation/devicetree/bindings/net/fsl-fec.txt +++ b/Documentation/devicetree/bindings/net/fsl-fec.txt @@ -19,6 +19,6 @@ ethernet@83fec000 { reg = <0x83fec000 0x4000>; interrupts = <87>; phy-mode = "mii"; - phy-reset-gpios = <&gpio1 14 0>; /* GPIO2_14 */ + phy-reset-gpios = <&gpio2 14 0>; /* GPIO2_14 */ local-mac-address = [00 04 9F 01 1B B9]; }; diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx6q-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx6q-pinctrl.txt index 82b43f915857..a4119f6422d9 100644 --- a/Documentation/devicetree/bindings/pinctrl/fsl,imx6q-pinctrl.txt +++ b/Documentation/devicetree/bindings/pinctrl/fsl,imx6q-pinctrl.txt @@ -1626,3 +1626,5 @@ MX6Q_PAD_SD2_DAT3__PCIE_CTRL_MUX_11 1587 MX6Q_PAD_SD2_DAT3__GPIO_1_12 1588 MX6Q_PAD_SD2_DAT3__SJC_DONE 1589 MX6Q_PAD_SD2_DAT3__ANATOP_TESTO_3 1590 +MX6Q_PAD_ENET_RX_ER__ANATOP_USBOTG_ID 1591 +MX6Q_PAD_GPIO_1__ANATOP_USBOTG_ID 1592 diff --git a/Documentation/devicetree/bindings/regulator/fixed-regulator.txt b/Documentation/devicetree/bindings/regulator/fixed-regulator.txt index 2f5b6b1ba15f..4fae41d54798 100644 --- a/Documentation/devicetree/bindings/regulator/fixed-regulator.txt +++ b/Documentation/devicetree/bindings/regulator/fixed-regulator.txt @@ -10,6 +10,7 @@ Optional properties: If this property is missing, the default assumed is Active low. - gpio-open-drain: GPIO is open drain type. If this property is missing then default assumption is false. +-vin-supply: Input supply name. Any property defined as part of the core regulator binding, defined in regulator.txt, can also be used. @@ -29,4 +30,5 @@ Example: enable-active-high; regulator-boot-on; gpio-open-drain; + vin-supply = <&parent_reg>; }; diff --git a/Documentation/devicetree/bindings/regulator/regulator.txt b/Documentation/devicetree/bindings/regulator/regulator.txt index 5b7a408acdaa..66ece3f87bbc 100644 --- a/Documentation/devicetree/bindings/regulator/regulator.txt +++ b/Documentation/devicetree/bindings/regulator/regulator.txt @@ -10,6 +10,11 @@ Optional properties: - regulator-always-on: boolean, regulator should never be disabled - regulator-boot-on: bootloader/firmware enabled regulator - <name>-supply: phandle to the parent supply/regulator node +- regulator-ramp-delay: ramp delay for regulator(in uV/uS) +- regulator-compatible: If a regulator chip contains multiple + regulators, and if the chip's binding contains a child node that + describes each regulator, then this property indicates which regulator + this child node is intended to configure. Example: diff --git a/Documentation/devicetree/bindings/regulator/tps65217.txt b/Documentation/devicetree/bindings/regulator/tps65217.txt new file mode 100644 index 000000000000..0487e9675ba0 --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/tps65217.txt @@ -0,0 +1,91 @@ +TPS65217 family of regulators + +Required properties: +- compatible: "ti,tps65217" +- reg: I2C slave address +- regulators: list of regulators provided by this controller, must be named + after their hardware counterparts: dcdc[1-3] and ldo[1-4] +- regulators: This is the list of child nodes that specify the regulator + initialization data for defined regulators. Not all regulators for the given + device need to be present. The definition for each of these nodes is defined + using the standard binding for regulators found at + Documentation/devicetree/bindings/regulator/regulator.txt. + + The valid names for regulators are: + tps65217: dcdc1, dcdc2, dcdc3, ldo1, ldo2, ldo3 and ldo4 + +Each regulator is defined using the standard binding for regulators. + +Example: + + tps: tps@24 { + compatible = "ti,tps65217"; + + regulators { + #address-cells = <1>; + #size-cells = <0>; + + dcdc1_reg: regulator@0 { + reg = <0>; + regulator-compatible = "dcdc1"; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; + regulator-always-on; + }; + + dcdc2_reg: regulator@1 { + reg = <1>; + regulator-compatible = "dcdc2"; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + + dcdc3_reg: regulator@2 { + reg = <2>; + regulator-compatible = "dcdc3"; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <1500000>; + regulator-boot-on; + regulator-always-on; + }; + + ldo1_reg: regulator@3 { + reg = <3>; + regulator-compatible = "ldo1"; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + + ldo2_reg: regulator@4 { + reg = <4>; + regulator-compatible = "ldo2"; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + + ldo3_reg: regulator@5 { + reg = <5>; + regulator-compatible = "ldo3"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + + ldo4_reg: regulator@6 { + reg = <6>; + regulator-compatible = "ldo4"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/regulator/tps6586x.txt b/Documentation/devicetree/bindings/regulator/tps6586x.txt index 0fcabaa3baa3..d156e1b5db12 100644 --- a/Documentation/devicetree/bindings/regulator/tps6586x.txt +++ b/Documentation/devicetree/bindings/regulator/tps6586x.txt @@ -6,8 +6,17 @@ Required properties: - interrupts: the interrupt outputs of the controller - #gpio-cells: number of cells to describe a GPIO - gpio-controller: mark the device as a GPIO controller -- regulators: list of regulators provided by this controller, must be named - after their hardware counterparts: sm[0-2], ldo[0-9] and ldo_rtc +- regulators: list of regulators provided by this controller, must have + property "regulator-compatible" to match their hardware counterparts: + sm[0-2], ldo[0-9] and ldo_rtc +- sm0-supply: The input supply for the SM0. +- sm1-supply: The input supply for the SM1. +- sm2-supply: The input supply for the SM2. +- vinldo01-supply: The input supply for the LDO1 and LDO2 +- vinldo23-supply: The input supply for the LDO2 and LDO3 +- vinldo4-supply: The input supply for the LDO4 +- vinldo678-supply: The input supply for the LDO6, LDO7 and LDO8 +- vinldo9-supply: The input supply for the LDO9 Each regulator is defined using the standard binding for regulators. @@ -21,75 +30,113 @@ Example: #gpio-cells = <2>; gpio-controller; + sm0-supply = <&some_reg>; + sm1-supply = <&some_reg>; + sm2-supply = <&some_reg>; + vinldo01-supply = <...>; + vinldo23-supply = <...>; + vinldo4-supply = <...>; + vinldo678-supply = <...>; + vinldo9-supply = <...>; + regulators { - sm0_reg: sm0 { + #address-cells = <1>; + #size-cells = <0>; + + sm0_reg: regulator@0 { + reg = <0>; + regulator-compatible = "sm0"; regulator-min-microvolt = < 725000>; regulator-max-microvolt = <1500000>; regulator-boot-on; regulator-always-on; }; - sm1_reg: sm1 { + sm1_reg: regulator@1 { + reg = <1>; + regulator-compatible = "sm1"; regulator-min-microvolt = < 725000>; regulator-max-microvolt = <1500000>; regulator-boot-on; regulator-always-on; }; - sm2_reg: sm2 { + sm2_reg: regulator@2 { + reg = <2>; + regulator-compatible = "sm2"; regulator-min-microvolt = <3000000>; regulator-max-microvolt = <4550000>; regulator-boot-on; regulator-always-on; }; - ldo0_reg: ldo0 { + ldo0_reg: regulator@3 { + reg = <3>; + regulator-compatible = "ldo0"; regulator-name = "PCIE CLK"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; }; - ldo1_reg: ldo1 { + ldo1_reg: regulator@4 { + reg = <4>; + regulator-compatible = "ldo1"; regulator-min-microvolt = < 725000>; regulator-max-microvolt = <1500000>; }; - ldo2_reg: ldo2 { + ldo2_reg: regulator@5 { + reg = <5>; + regulator-compatible = "ldo2"; regulator-min-microvolt = < 725000>; regulator-max-microvolt = <1500000>; }; - ldo3_reg: ldo3 { + ldo3_reg: regulator@6 { + reg = <6>; + regulator-compatible = "ldo3"; regulator-min-microvolt = <1250000>; regulator-max-microvolt = <3300000>; }; - ldo4_reg: ldo4 { + ldo4_reg: regulator@7 { + reg = <7>; + regulator-compatible = "ldo4"; regulator-min-microvolt = <1700000>; regulator-max-microvolt = <2475000>; }; - ldo5_reg: ldo5 { + ldo5_reg: regulator@8 { + reg = <8>; + regulator-compatible = "ldo5"; regulator-min-microvolt = <1250000>; regulator-max-microvolt = <3300000>; }; - ldo6_reg: ldo6 { + ldo6_reg: regulator@9 { + reg = <9>; + regulator-compatible = "ldo6"; regulator-min-microvolt = <1250000>; regulator-max-microvolt = <3300000>; }; - ldo7_reg: ldo7 { + ldo7_reg: regulator@10 { + reg = <10>; + regulator-compatible = "ldo7"; regulator-min-microvolt = <1250000>; regulator-max-microvolt = <3300000>; }; - ldo8_reg: ldo8 { + ldo8_reg: regulator@11 { + reg = <11>; + regulator-compatible = "ldo8"; regulator-min-microvolt = <1250000>; regulator-max-microvolt = <3300000>; }; - ldo9_reg: ldo9 { + ldo9_reg: regulator@12 { + reg = <12>; + regulator-compatible = "ldo9"; regulator-min-microvolt = <1250000>; regulator-max-microvolt = <3300000>; }; diff --git a/Documentation/devicetree/bindings/regulator/twl-regulator.txt b/Documentation/devicetree/bindings/regulator/twl-regulator.txt index 0c3395d55ac1..658749b90b97 100644 --- a/Documentation/devicetree/bindings/regulator/twl-regulator.txt +++ b/Documentation/devicetree/bindings/regulator/twl-regulator.txt @@ -15,7 +15,6 @@ For twl6030 regulators/LDOs - "ti,twl6030-vusb" for VUSB LDO - "ti,twl6030-v1v8" for V1V8 LDO - "ti,twl6030-v2v1" for V2V1 LDO - - "ti,twl6030-clk32kg" for CLK32KG RESOURCE - "ti,twl6030-vdd1" for VDD1 SMPS - "ti,twl6030-vdd2" for VDD2 SMPS - "ti,twl6030-vdd3" for VDD3 SMPS diff --git a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt index 9841057d112b..4256a6df9b79 100644 --- a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt +++ b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt @@ -17,6 +17,6 @@ ecspi@70010000 { reg = <0x70010000 0x4000>; interrupts = <36>; fsl,spi-num-chipselects = <2>; - cs-gpios = <&gpio3 24 0>, /* GPIO4_24 */ - <&gpio3 25 0>; /* GPIO4_25 */ + cs-gpios = <&gpio3 24 0>, /* GPIO3_24 */ + <&gpio3 25 0>; /* GPIO3_25 */ }; diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index 6eab91747a86..db4d3af3643c 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -3,6 +3,7 @@ Device tree binding vendor prefix registry. Keep list in alphabetical order. This isn't an exhaustive list, but you should add new prefixes to it before using them to avoid name-space collisions. +ad Avionic Design GmbH adi Analog Devices, Inc. amcc Applied Micro Circuits Corporation (APM, formally AMCC) apm Applied Micro Circuits Corporation (APM) diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 8e2da1e06e3b..e0cce2a5f820 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -9,7 +9,7 @@ be able to use diff(1). --------------------------- dentry_operations -------------------------- prototypes: - int (*d_revalidate)(struct dentry *, struct nameidata *); + int (*d_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, const struct inode *, struct qstr *); int (*d_compare)(const struct dentry *, const struct inode *, @@ -37,9 +37,8 @@ d_manage: no no yes (ref-walk) maybe --------------------------- inode_operations --------------------------- prototypes: - int (*create) (struct inode *,struct dentry *,umode_t, struct nameidata *); - struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameid -ata *); + int (*create) (struct inode *,struct dentry *,umode_t, bool); + struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct inode *,struct dentry *,const char *); @@ -62,6 +61,9 @@ ata *); int (*removexattr) (struct dentry *, const char *); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); void (*update_time)(struct inode *, struct timespec *, int); + int (*atomic_open)(struct inode *, struct dentry *, + struct file *, unsigned open_flag, + umode_t create_mode, int *opened); locking rules: all may block @@ -89,6 +91,7 @@ listxattr: no removexattr: yes fiemap: no update_time: no +atomic_open: yes Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on victim. diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index 8c91d1057d9a..2bef2b3843d1 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -355,12 +355,10 @@ protects *all* the dcache state of a given dentry. via rcu-walk path walk (basically, if the file can have had a path name in the vfs namespace). - i_dentry and i_rcu share storage in a union, and the vfs expects -i_dentry to be reinitialized before it is freed, so an: - - INIT_LIST_HEAD(&inode->i_dentry); - -must be done in the RCU callback. + Even though i_dentry and i_rcu share storage in a union, we will +initialize the former in inode_init_always(), so just leave it alone in +the callback. It used to be necessary to clean it there, but not anymore +(starting at 3.2). -- [recommended] @@ -433,3 +431,14 @@ release it yourself. d_alloc_root() is gone, along with a lot of bugs caused by code misusing it. Replacement: d_make_root(inode). The difference is, d_make_root() drops the reference to inode if dentry allocation fails. + +-- +[mandatory] + The witch is dead! Well, 2/3 of it, anyway. ->d_revalidate() and +->lookup() do *not* take struct nameidata anymore; just the flags. +-- +[mandatory] + ->create() doesn't take struct nameidata *; unlike the previous +two, it gets "is it an O_EXCL or equivalent?" boolean argument. Note that +local filesystems can ignore tha argument - they are guaranteed that the +object doesn't exist. It's remote/distributed ones that might care... diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index efd23f481704..aa754e01464e 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -341,8 +341,8 @@ This describes how the VFS can manipulate an inode in your filesystem. As of kernel 2.6.22, the following members are defined: struct inode_operations { - int (*create) (struct inode *,struct dentry *, umode_t, struct nameidata *); - struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *); + int (*create) (struct inode *,struct dentry *, umode_t, bool); + struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct inode *,struct dentry *,const char *); @@ -364,6 +364,9 @@ struct inode_operations { ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*removexattr) (struct dentry *, const char *); void (*update_time)(struct inode *, struct timespec *, int); + int (*atomic_open)(struct inode *, struct dentry *, + struct file *, unsigned open_flag, + umode_t create_mode, int *opened); }; Again, all methods are called without any locks being held, unless @@ -476,6 +479,14 @@ otherwise noted. an inode. If this is not defined the VFS will update the inode itself and call mark_inode_dirty_sync. + atomic_open: called on the last component of an open. Using this optional + method the filesystem can look up, possibly create and open the file in + one atomic operation. If it cannot perform this (e.g. the file type + turned out to be wrong) it may signal this by returning 1 instead of + usual 0 or -ve . This method is only called if the last + component is negative or needs lookup. Cached positive dentries are + still handled by f_op->open(). + The Address Space Object ======================== @@ -891,7 +902,7 @@ the VFS uses a default. As of kernel 2.6.22, the following members are defined: struct dentry_operations { - int (*d_revalidate)(struct dentry *, struct nameidata *); + int (*d_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, const struct inode *, struct qstr *); int (*d_compare)(const struct dentry *, const struct inode *, @@ -910,11 +921,11 @@ struct dentry_operations { dcache. Most filesystems leave this as NULL, because all their dentries in the dcache are valid - d_revalidate may be called in rcu-walk mode (nd->flags & LOOKUP_RCU). + d_revalidate may be called in rcu-walk mode (flags & LOOKUP_RCU). If in rcu-walk mode, the filesystem must revalidate the dentry without blocking or storing to the dentry, d_parent and d_inode should not be - used without care (because they can go NULL), instead nd->inode should - be used. + used without care (because they can change and, in d_inode case, even + become NULL under us). If a situation is encountered that rcu-walk cannot handle, return -ECHILD and it will be called again in ref-walk mode. diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt index 506c7390c2b9..13f1aa09b938 100644 --- a/Documentation/kdump/kdump.txt +++ b/Documentation/kdump/kdump.txt @@ -86,7 +86,7 @@ There is also a gitweb interface available at http://www.kernel.org/git/?p=utils/kernel/kexec/kexec-tools.git More information about kexec-tools can be found at -http://www.kernel.org/pub/linux/utils/kernel/kexec/README.html +http://horms.net/projects/kexec/ 3) Unpack the tarball with the tar command, as follows: diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index a92c5ebf373e..12783fa833c3 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2367,6 +2367,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Set maximum number of finished RCU callbacks to process in one batch. + rcutree.fanout_leaf= [KNL,BOOT] + Increase the number of CPUs assigned to each + leaf rcu_node structure. Useful for very large + systems. + rcutree.qhimark= [KNL,BOOT] Set threshold of queued RCU callbacks over which batch limiting is disabled. diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt index 872815cd41d3..504dfe4d52eb 100644 --- a/Documentation/power/devices.txt +++ b/Documentation/power/devices.txt @@ -583,9 +583,10 @@ for the given device during all power transitions, instead of the respective subsystem-level callbacks. Specifically, if a device's pm_domain pointer is not NULL, the ->suspend() callback from the object pointed to by it will be executed instead of its subsystem's (e.g. bus type's) ->suspend() callback and -anlogously for all of the remaining callbacks. In other words, power management -domain callbacks, if defined for the given device, always take precedence over -the callbacks provided by the device's subsystem (e.g. bus type). +analogously for all of the remaining callbacks. In other words, power +management domain callbacks, if defined for the given device, always take +precedence over the callbacks provided by the device's subsystem (e.g. bus +type). The support for device power management domains is only relevant to platforms needing to use the same device driver power management callbacks in many @@ -598,7 +599,7 @@ it into account in any way. Device Low Power (suspend) States --------------------------------- Device low-power states aren't standard. One device might only handle -"on" and "off, while another might support a dozen different versions of +"on" and "off", while another might support a dozen different versions of "on" (how many engines are active?), plus a state that gets back to "on" faster than from a full "off". diff --git a/Documentation/power/swsusp.txt b/Documentation/power/swsusp.txt index ac190cf1963e..92341b84250d 100644 --- a/Documentation/power/swsusp.txt +++ b/Documentation/power/swsusp.txt @@ -33,6 +33,11 @@ echo shutdown > /sys/power/disk; echo disk > /sys/power/state echo platform > /sys/power/disk; echo disk > /sys/power/state +. If you would like to write hibernation image to swap and then suspend +to RAM (provided your platform supports it), you can try + +echo suspend > /sys/power/disk; echo disk > /sys/power/state + . If you have SATA disks, you'll need recent kernels with SATA suspend support. For suspend and resume to work, make sure your disk drivers are built into kernel -- not modules. [There's way to make diff --git a/Documentation/prctl/no_new_privs.txt b/Documentation/prctl/no_new_privs.txt new file mode 100644 index 000000000000..f7be84fba910 --- /dev/null +++ b/Documentation/prctl/no_new_privs.txt @@ -0,0 +1,57 @@ +The execve system call can grant a newly-started program privileges that +its parent did not have. The most obvious examples are setuid/setgid +programs and file capabilities. To prevent the parent program from +gaining these privileges as well, the kernel and user code must be +careful to prevent the parent from doing anything that could subvert the +child. For example: + + - The dynamic loader handles LD_* environment variables differently if + a program is setuid. + + - chroot is disallowed to unprivileged processes, since it would allow + /etc/passwd to be replaced from the point of view of a process that + inherited chroot. + + - The exec code has special handling for ptrace. + +These are all ad-hoc fixes. The no_new_privs bit (since Linux 3.5) is a +new, generic mechanism to make it safe for a process to modify its +execution environment in a manner that persists across execve. Any task +can set no_new_privs. Once the bit is set, it is inherited across fork, +clone, and execve and cannot be unset. With no_new_privs set, execve +promises not to grant the privilege to do anything that could not have +been done without the execve call. For example, the setuid and setgid +bits will no longer change the uid or gid; file capabilities will not +add to the permitted set, and LSMs will not relax constraints after +execve. + +To set no_new_privs, use prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0). + +Be careful, though: LSMs might also not tighten constraints on exec +in no_new_privs mode. (This means that setting up a general-purpose +service launcher to set no_new_privs before execing daemons may +interfere with LSM-based sandboxing.) + +Note that no_new_privs does not prevent privilege changes that do not +involve execve. An appropriately privileged task can still call +setuid(2) and receive SCM_RIGHTS datagrams. + +There are two main use cases for no_new_privs so far: + + - Filters installed for the seccomp mode 2 sandbox persist across + execve and can change the behavior of newly-executed programs. + Unprivileged users are therefore only allowed to install such filters + if no_new_privs is set. + + - By itself, no_new_privs can be used to reduce the attack surface + available to an unprivileged user. If everything running with a + given uid has no_new_privs set, then that uid will be unable to + escalate its privileges by directly attacking setuid, setgid, and + fcap-using binaries; it will need to compromise something without the + no_new_privs bit set first. + +In the future, other potentially dangerous kernel features could become +available to unprivileged tasks if no_new_privs is set. In principle, +several options to unshare(2) and clone(2) would be safe when +no_new_privs is set, and no_new_privs + chroot is considerable less +dangerous than chroot by itself. diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 930126698a0f..2c9948379469 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1930,6 +1930,23 @@ The "pte_enc" field provides a value that can OR'ed into the hash PTE's RPN field (ie, it needs to be shifted left by 12 to OR it into the hash PTE second double word). +4.75 KVM_IRQFD + +Capability: KVM_CAP_IRQFD +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_irqfd (in) +Returns: 0 on success, -1 on error + +Allows setting an eventfd to directly trigger a guest interrupt. +kvm_irqfd.fd specifies the file descriptor to use as the eventfd and +kvm_irqfd.gsi specifies the irqchip pin toggled by this event. When +an event is tiggered on the eventfd, an interrupt is injected into +the guest using the specified gsi pin. The irqfd is removed using +the KVM_IRQFD_FLAG_DEASSIGN flag, specifying both kvm_irqfd.fd +and kvm_irqfd.gsi. + + 5. The kvm_run structure ------------------------ diff --git a/MAINTAINERS b/MAINTAINERS index eb22272b2116..fe643e7b9df6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3433,13 +3433,14 @@ S: Supported F: drivers/idle/i7300_idle.c IEEE 802.15.4 SUBSYSTEM +M: Alexander Smirnov <alex.bluesman.smirnov@gmail.com> M: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> -M: Sergey Lapin <slapin@ossfans.org> L: linux-zigbee-devel@lists.sourceforge.net (moderated for non-subscribers) W: http://apps.sourceforge.net/trac/linux-zigbee T: git git://git.kernel.org/pub/scm/linux/kernel/git/lowpan/lowpan.git S: Maintained F: net/ieee802154/ +F: net/mac802154/ F: drivers/ieee802154/ IIO SUBSYSTEM AND DRIVERS @@ -4654,8 +4655,8 @@ L: netfilter@vger.kernel.org L: coreteam@netfilter.org W: http://www.netfilter.org/ W: http://www.iptables.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-2.6.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next-2.6.git +T: git git://1984.lsi.us.es/nf +T: git git://1984.lsi.us.es/nf-next S: Supported F: include/linux/netfilter* F: include/linux/netfilter/ @@ -4857,6 +4858,7 @@ M: Kevin Hilman <khilman@ti.com> L: linux-omap@vger.kernel.org S: Maintained F: arch/arm/*omap*/*pm* +F: drivers/cpufreq/omap-cpufreq.c OMAP POWERDOMAIN/CLOCKDOMAIN SOC ADAPTATION LAYER SUPPORT M: Rajendra Nayak <rnayak@ti.com> @@ -5563,7 +5565,7 @@ F: Documentation/networking/LICENSE.qla3xxx F: drivers/net/ethernet/qlogic/qla3xxx.* QLOGIC QLCNIC (1/10)Gb ETHERNET DRIVER -M: Anirban Chakraborty <anirban.chakraborty@qlogic.com> +M: Jitendra Kalsaria <jitendra.kalsaria@qlogic.com> M: Sony Chacko <sony.chacko@qlogic.com> M: linux-driver@qlogic.com L: netdev@vger.kernel.org @@ -5571,7 +5573,6 @@ S: Supported F: drivers/net/ethernet/qlogic/qlcnic/ QLOGIC QLGE 10Gb ETHERNET DRIVER -M: Anirban Chakraborty <anirban.chakraborty@qlogic.com> M: Jitendra Kalsaria <jitendra.kalsaria@qlogic.com> M: Ron Mercer <ron.mercer@qlogic.com> M: linux-driver@qlogic.com @@ -5909,7 +5910,7 @@ M: Ingo Molnar <mingo@redhat.com> M: Peter Zijlstra <peterz@infradead.org> T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched/core S: Maintained -F: kernel/sched* +F: kernel/sched/ F: include/linux/sched.h SCORE ARCHITECTURE @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = NAME = Saber-toothed Squirrel # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/db8500.dtsi b/arch/arm/boot/dts/db8500.dtsi index 4ad5160018cb..ec2be92b270d 100644 --- a/arch/arm/boot/dts/db8500.dtsi +++ b/arch/arm/boot/dts/db8500.dtsi @@ -206,62 +206,74 @@ // DB8500_REGULATOR_VAPE db8500_vape_reg: db8500_vape { + regulator-compatible = "db8500_vape"; regulator-name = "db8500-vape"; regulator-always-on; }; // DB8500_REGULATOR_VARM db8500_varm_reg: db8500_varm { + regulator-compatible = "db8500_varm"; regulator-name = "db8500-varm"; }; // DB8500_REGULATOR_VMODEM db8500_vmodem_reg: db8500_vmodem { + regulator-compatible = "db8500_vmodem"; regulator-name = "db8500-vmodem"; }; // DB8500_REGULATOR_VPLL db8500_vpll_reg: db8500_vpll { + regulator-compatible = "db8500_vpll"; regulator-name = "db8500-vpll"; }; // DB8500_REGULATOR_VSMPS1 db8500_vsmps1_reg: db8500_vsmps1 { + regulator-compatible = "db8500_vsmps1"; regulator-name = "db8500-vsmps1"; }; // DB8500_REGULATOR_VSMPS2 db8500_vsmps2_reg: db8500_vsmps2 { + regulator-compatible = "db8500_vsmps2"; regulator-name = "db8500-vsmps2"; }; // DB8500_REGULATOR_VSMPS3 db8500_vsmps3_reg: db8500_vsmps3 { + regulator-compatible = "db8500_vsmps3"; regulator-name = "db8500-vsmps3"; }; // DB8500_REGULATOR_VRF1 db8500_vrf1_reg: db8500_vrf1 { + regulator-compatible = "db8500_vrf1"; regulator-name = "db8500-vrf1"; }; // DB8500_REGULATOR_SWITCH_SVAMMDSP db8500_sva_mmdsp_reg: db8500_sva_mmdsp { + regulator-compatible = "db8500_sva_mmdsp"; regulator-name = "db8500-sva-mmdsp"; }; // DB8500_REGULATOR_SWITCH_SVAMMDSPRET db8500_sva_mmdsp_ret_reg: db8500_sva_mmdsp_ret { + regulator-compatible = "db8500_sva_mmdsp_ret"; regulator-name = "db8500-sva-mmdsp-ret"; }; // DB8500_REGULATOR_SWITCH_SVAPIPE db8500_sva_pipe_reg: db8500_sva_pipe { + regulator-compatible = "db8500_sva_pipe"; regulator-name = "db8500_sva_pipe"; }; // DB8500_REGULATOR_SWITCH_SIAMMDSP db8500_sia_mmdsp_reg: db8500_sia_mmdsp { + regulator-compatible = "db8500_sia_mmdsp"; regulator-name = "db8500_sia_mmdsp"; }; @@ -272,38 +284,45 @@ // DB8500_REGULATOR_SWITCH_SIAPIPE db8500_sia_pipe_reg: db8500_sia_pipe { + regulator-compatible = "db8500_sia_pipe"; regulator-name = "db8500-sia-pipe"; }; // DB8500_REGULATOR_SWITCH_SGA db8500_sga_reg: db8500_sga { + regulator-compatible = "db8500_sga"; regulator-name = "db8500-sga"; vin-supply = <&db8500_vape_reg>; }; // DB8500_REGULATOR_SWITCH_B2R2_MCDE db8500_b2r2_mcde_reg: db8500_b2r2_mcde { + regulator-compatible = "db8500_b2r2_mcde"; regulator-name = "db8500-b2r2-mcde"; vin-supply = <&db8500_vape_reg>; }; // DB8500_REGULATOR_SWITCH_ESRAM12 db8500_esram12_reg: db8500_esram12 { + regulator-compatible = "db8500_esram12"; regulator-name = "db8500-esram12"; }; // DB8500_REGULATOR_SWITCH_ESRAM12RET db8500_esram12_ret_reg: db8500_esram12_ret { + regulator-compatible = "db8500_esram12_ret"; regulator-name = "db8500-esram12-ret"; }; // DB8500_REGULATOR_SWITCH_ESRAM34 db8500_esram34_reg: db8500_esram34 { + regulator-compatible = "db8500_esram34"; regulator-name = "db8500-esram34"; }; // DB8500_REGULATOR_SWITCH_ESRAM34RET db8500_esram34_ret_reg: db8500_esram34_ret { + regulator-compatible = "db8500_esram34_ret"; regulator-name = "db8500-esram34-ret"; }; }; @@ -318,6 +337,7 @@ // supplies to the display/camera ab8500_ldo_aux1_reg: ab8500_ldo_aux1 { + regulator-compatible = "ab8500_ldo_aux1"; regulator-name = "V-DISPLAY"; regulator-min-microvolt = <2500000>; regulator-max-microvolt = <2900000>; @@ -328,6 +348,7 @@ // supplies to the on-board eMMC ab8500_ldo_aux2_reg: ab8500_ldo_aux2 { + regulator-compatible = "ab8500_ldo_aux2"; regulator-name = "V-eMMC1"; regulator-min-microvolt = <1100000>; regulator-max-microvolt = <3300000>; @@ -335,6 +356,7 @@ // supply for VAUX3; SDcard slots ab8500_ldo_aux3_reg: ab8500_ldo_aux3 { + regulator-compatible = "ab8500_ldo_aux3"; regulator-name = "V-MMC-SD"; regulator-min-microvolt = <1100000>; regulator-max-microvolt = <3300000>; @@ -342,41 +364,49 @@ // supply for v-intcore12; VINTCORE12 LDO ab8500_ldo_initcore_reg: ab8500_ldo_initcore { + regulator-compatible = "ab8500_ldo_initcore"; regulator-name = "V-INTCORE"; }; // supply for tvout; gpadc; TVOUT LDO ab8500_ldo_tvout_reg: ab8500_ldo_tvout { + regulator-compatible = "ab8500_ldo_tvout"; regulator-name = "V-TVOUT"; }; // supply for ab8500-usb; USB LDO ab8500_ldo_usb_reg: ab8500_ldo_usb { + regulator-compatible = "ab8500_ldo_usb"; regulator-name = "dummy"; }; // supply for ab8500-vaudio; VAUDIO LDO ab8500_ldo_audio_reg: ab8500_ldo_audio { + regulator-compatible = "ab8500_ldo_audio"; regulator-name = "V-AUD"; }; // supply for v-anamic1 VAMic1-LDO ab8500_ldo_anamic1_reg: ab8500_ldo_anamic1 { + regulator-compatible = "ab8500_ldo_anamic1"; regulator-name = "V-AMIC1"; }; // supply for v-amic2; VAMIC2 LDO; reuse constants for AMIC1 ab8500_ldo_amamic2_reg: ab8500_ldo_amamic2 { + regulator-compatible = "ab8500_ldo_amamic2"; regulator-name = "V-AMIC2"; }; // supply for v-dmic; VDMIC LDO ab8500_ldo_dmic_reg: ab8500_ldo_dmic { + regulator-compatible = "ab8500_ldo_dmic"; regulator-name = "V-DMIC"; }; // supply for U8500 CSI/DSI; VANA LDO ab8500_ldo_ana_reg: ab8500_ldo_ana { + regulator-compatible = "ab8500_ldo_ana"; regulator-name = "V-CSI/DSI"; }; }; diff --git a/arch/arm/boot/dts/spear13xx.dtsi b/arch/arm/boot/dts/spear13xx.dtsi index 10dcec7e7321..f7b84aced654 100644 --- a/arch/arm/boot/dts/spear13xx.dtsi +++ b/arch/arm/boot/dts/spear13xx.dtsi @@ -43,8 +43,8 @@ pmu { compatible = "arm,cortex-a9-pmu"; - interrupts = <0 8 0x04 - 0 9 0x04>; + interrupts = <0 6 0x04 + 0 7 0x04>; }; L2: l2-cache { @@ -119,8 +119,8 @@ gmac0: eth@e2000000 { compatible = "st,spear600-gmac"; reg = <0xe2000000 0x8000>; - interrupts = <0 23 0x4 - 0 24 0x4>; + interrupts = <0 33 0x4 + 0 34 0x4>; interrupt-names = "macirq", "eth_wake_irq"; status = "disabled"; }; @@ -202,6 +202,7 @@ kbd@e0300000 { compatible = "st,spear300-kbd"; reg = <0xe0300000 0x1000>; + interrupts = <0 52 0x4>; status = "disabled"; }; @@ -224,7 +225,7 @@ serial@e0000000 { compatible = "arm,pl011", "arm,primecell"; reg = <0xe0000000 0x1000>; - interrupts = <0 36 0x4>; + interrupts = <0 35 0x4>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/spear320-evb.dts b/arch/arm/boot/dts/spear320-evb.dts index c13fd1f3b09f..e4e912f95024 100644 --- a/arch/arm/boot/dts/spear320-evb.dts +++ b/arch/arm/boot/dts/spear320-evb.dts @@ -15,8 +15,8 @@ /include/ "spear320.dtsi" / { - model = "ST SPEAr300 Evaluation Board"; - compatible = "st,spear300-evb", "st,spear300"; + model = "ST SPEAr320 Evaluation Board"; + compatible = "st,spear320-evb", "st,spear320"; #address-cells = <1>; #size-cells = <1>; @@ -26,7 +26,7 @@ ahb { pinmux@b3000000 { - st,pinmux-mode = <3>; + st,pinmux-mode = <4>; pinctrl-names = "default"; pinctrl-0 = <&state_default>; diff --git a/arch/arm/boot/dts/spear600.dtsi b/arch/arm/boot/dts/spear600.dtsi index 089f0a42c50e..a3c36e47d7ef 100644 --- a/arch/arm/boot/dts/spear600.dtsi +++ b/arch/arm/boot/dts/spear600.dtsi @@ -181,6 +181,7 @@ timer@f0000000 { compatible = "st,spear-timer"; reg = <0xf0000000 0x400>; + interrupt-parent = <&vic0>; interrupts = <16>; }; }; diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index f3087cb0ab08..d3c29b377af9 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -176,7 +176,6 @@ CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_DEVICEFS=y CONFIG_USB_SUSPEND=y CONFIG_USB_MON=y -CONFIG_USB_EHCI_HCD=y CONFIG_USB_WDM=y CONFIG_USB_STORAGE=y CONFIG_USB_LIBUSUAL=y diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 68374ba6a943..c79f61faa3a5 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -243,7 +243,7 @@ typedef struct { #define ATOMIC64_INIT(i) { (i) } -static inline u64 atomic64_read(atomic64_t *v) +static inline u64 atomic64_read(const atomic64_t *v) { u64 result; diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h index 3d2220498abc..6ddbe446425e 100644 --- a/arch/arm/include/asm/domain.h +++ b/arch/arm/include/asm/domain.h @@ -60,13 +60,13 @@ #ifndef __ASSEMBLY__ #ifdef CONFIG_CPU_USE_DOMAINS -#define set_domain(x) \ - do { \ - __asm__ __volatile__( \ - "mcr p15, 0, %0, c3, c0 @ set domain" \ - : : "r" (x)); \ - isb(); \ - } while (0) +static inline void set_domain(unsigned val) +{ + asm volatile( + "mcr p15, 0, %0, c3, c0 @ set domain" + : : "r" (val)); + isb(); +} #define modify_domain(dom,type) \ do { \ @@ -78,8 +78,8 @@ } while (0) #else -#define set_domain(x) do { } while (0) -#define modify_domain(dom,type) do { } while (0) +static inline void set_domain(unsigned val) { } +static inline void modify_domain(unsigned dom, unsigned type) { } #endif /* diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h index b79f8e97f775..af7b0bda3355 100644 --- a/arch/arm/include/asm/thread_info.h +++ b/arch/arm/include/asm/thread_info.h @@ -148,7 +148,6 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ #define TIF_SYSCALL_TRACE 8 #define TIF_SYSCALL_AUDIT 9 -#define TIF_SYSCALL_RESTARTSYS 10 #define TIF_POLLING_NRFLAG 16 #define TIF_USING_IWMMXT 17 #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ @@ -164,11 +163,9 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_USING_IWMMXT (1 << TIF_USING_IWMMXT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) -#define _TIF_SYSCALL_RESTARTSYS (1 << TIF_SYSCALL_RESTARTSYS) /* Checks for any syscall work in entry-common.S */ -#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ - _TIF_SYSCALL_RESTARTSYS) +#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT) /* * Change these and you break ASM code in entry-common.S diff --git a/arch/arm/kernel/kprobes-test-arm.c b/arch/arm/kernel/kprobes-test-arm.c index ba32b393b3f0..38c1a3b103a0 100644 --- a/arch/arm/kernel/kprobes-test-arm.c +++ b/arch/arm/kernel/kprobes-test-arm.c @@ -187,8 +187,8 @@ void kprobe_arm_test_cases(void) TEST_BF_R ("mov pc, r",0,2f,"") TEST_BF_RR("mov pc, r",0,2f,", asl r",1,0,"") TEST_BB( "sub pc, pc, #1b-2b+8") -#if __LINUX_ARM_ARCH__ >= 6 - TEST_BB( "sub pc, pc, #1b-2b+8-2") /* UNPREDICTABLE before ARMv6 */ +#if __LINUX_ARM_ARCH__ == 6 && !defined(CONFIG_CPU_V7) + TEST_BB( "sub pc, pc, #1b-2b+8-2") /* UNPREDICTABLE before and after ARMv6 */ #endif TEST_BB_R( "sub pc, pc, r",14, 1f-2f+8,"") TEST_BB_R( "rsb pc, r",14,1f-2f+8,", pc") diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 186c8cb982c5..a02eada3aa5d 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -503,7 +503,7 @@ __hw_perf_event_init(struct perf_event *event) event_requires_mode_exclusion(&event->attr)) { pr_debug("ARM performance counters do not support " "mode exclusion\n"); - return -EPERM; + return -EOPNOTSUPP; } /* diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index 5700a7ae7f0b..14e38261cd31 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -25,7 +25,6 @@ #include <linux/regset.h> #include <linux/audit.h> #include <linux/tracehook.h> -#include <linux/unistd.h> #include <asm/pgtable.h> #include <asm/traps.h> @@ -918,8 +917,6 @@ asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno) audit_syscall_entry(AUDIT_ARCH_ARM, scno, regs->ARM_r0, regs->ARM_r1, regs->ARM_r2, regs->ARM_r3); - if (why == 0 && test_and_clear_thread_flag(TIF_SYSCALL_RESTARTSYS)) - scno = __NR_restart_syscall - __NR_SYSCALL_BASE; if (!test_thread_flag(TIF_SYSCALL_TRACE)) return scno; diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index fd2392a17ac1..536c5d6b340b 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -27,6 +27,7 @@ */ #define SWI_SYS_SIGRETURN (0xef000000|(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE)) #define SWI_SYS_RT_SIGRETURN (0xef000000|(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE)) +#define SWI_SYS_RESTART (0xef000000|__NR_restart_syscall|__NR_OABI_SYSCALL_BASE) /* * With EABI, the syscall number has to be loaded into r7. @@ -47,6 +48,18 @@ const unsigned long sigreturn_codes[7] = { }; /* + * Either we support OABI only, or we have EABI with the OABI + * compat layer enabled. In the later case we don't know if + * user space is EABI or not, and if not we must not clobber r7. + * Always using the OABI syscall solves that issue and works for + * all those cases. + */ +const unsigned long syscall_restart_code[2] = { + SWI_SYS_RESTART, /* swi __NR_restart_syscall */ + 0xe49df004, /* ldr pc, [sp], #4 */ +}; + +/* * atomically swap in the new signal mask, and wait for a signal. */ asmlinkage int sys_sigsuspend(int restart, unsigned long oldmask, old_sigset_t mask) @@ -592,10 +605,12 @@ static void do_signal(struct pt_regs *regs, int syscall) case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: - case -ERESTART_RESTARTBLOCK: regs->ARM_r0 = regs->ARM_ORIG_r0; regs->ARM_pc = restart_addr; break; + case -ERESTART_RESTARTBLOCK: + regs->ARM_r0 = -EINTR; + break; } } @@ -611,14 +626,12 @@ static void do_signal(struct pt_regs *regs, int syscall) * debugger has chosen to restart at a different PC. */ if (regs->ARM_pc == restart_addr) { - if (retval == -ERESTARTNOHAND || - retval == -ERESTART_RESTARTBLOCK + if (retval == -ERESTARTNOHAND || (retval == -ERESTARTSYS && !(ka.sa.sa_flags & SA_RESTART))) { regs->ARM_r0 = -EINTR; regs->ARM_pc = continue_addr; } - clear_thread_flag(TIF_SYSCALL_RESTARTSYS); } handle_signal(signr, &ka, &info, regs); @@ -632,8 +645,29 @@ static void do_signal(struct pt_regs *regs, int syscall) * ignore the restart. */ if (retval == -ERESTART_RESTARTBLOCK - && regs->ARM_pc == restart_addr) - set_thread_flag(TIF_SYSCALL_RESTARTSYS); + && regs->ARM_pc == continue_addr) { + if (thumb_mode(regs)) { + regs->ARM_r7 = __NR_restart_syscall - __NR_SYSCALL_BASE; + regs->ARM_pc -= 2; + } else { +#if defined(CONFIG_AEABI) && !defined(CONFIG_OABI_COMPAT) + regs->ARM_r7 = __NR_restart_syscall; + regs->ARM_pc -= 4; +#else + u32 __user *usp; + + regs->ARM_sp -= 4; + usp = (u32 __user *)regs->ARM_sp; + + if (put_user(regs->ARM_pc, usp) == 0) { + regs->ARM_pc = KERN_RESTART_CODE; + } else { + regs->ARM_sp += 4; + force_sigsegv(0, current); + } +#endif + } + } } restore_saved_sigmask(); diff --git a/arch/arm/kernel/signal.h b/arch/arm/kernel/signal.h index 5ff067b7c752..6fcfe8398aa4 100644 --- a/arch/arm/kernel/signal.h +++ b/arch/arm/kernel/signal.h @@ -8,5 +8,7 @@ * published by the Free Software Foundation. */ #define KERN_SIGRETURN_CODE (CONFIG_VECTORS_BASE + 0x00000500) +#define KERN_RESTART_CODE (KERN_SIGRETURN_CODE + sizeof(sigreturn_codes)) extern const unsigned long sigreturn_codes[7]; +extern const unsigned long syscall_restart_code[2]; diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 4928d89758f4..3647170e9a16 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -820,6 +820,8 @@ void __init early_trap_init(void *vectors_base) */ memcpy((void *)(vectors + KERN_SIGRETURN_CODE - CONFIG_VECTORS_BASE), sigreturn_codes, sizeof(sigreturn_codes)); + memcpy((void *)(vectors + KERN_RESTART_CODE - CONFIG_VECTORS_BASE), + syscall_restart_code, sizeof(syscall_restart_code)); flush_icache_range(vectors, vectors + PAGE_SIZE); modify_domain(DOMAIN_USER, DOMAIN_CLIENT); diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 43a31fb06318..36ff15bbfdd4 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -183,7 +183,9 @@ SECTIONS } #endif +#ifdef CONFIG_SMP PERCPU_SECTION(L1_CACHE_BYTES) +#endif #ifdef CONFIG_XIP_KERNEL __data_loc = ALIGN(4); /* location in binary */ diff --git a/arch/arm/mach-dove/include/mach/bridge-regs.h b/arch/arm/mach-dove/include/mach/bridge-regs.h index 226949dc4ac0..f953bb54aa9d 100644 --- a/arch/arm/mach-dove/include/mach/bridge-regs.h +++ b/arch/arm/mach-dove/include/mach/bridge-regs.h @@ -50,5 +50,6 @@ #define POWER_MANAGEMENT (BRIDGE_VIRT_BASE | 0x011c) #define TIMER_VIRT_BASE (BRIDGE_VIRT_BASE | 0x0300) +#define TIMER_PHYS_BASE (BRIDGE_PHYS_BASE | 0x0300) #endif diff --git a/arch/arm/mach-dove/include/mach/dove.h b/arch/arm/mach-dove/include/mach/dove.h index ad1165d488c1..d52b0ef313b7 100644 --- a/arch/arm/mach-dove/include/mach/dove.h +++ b/arch/arm/mach-dove/include/mach/dove.h @@ -78,6 +78,7 @@ /* North-South Bridge */ #define BRIDGE_VIRT_BASE (DOVE_SB_REGS_VIRT_BASE | 0x20000) +#define BRIDGE_PHYS_BASE (DOVE_SB_REGS_PHYS_BASE | 0x20000) /* Cryptographic Engine */ #define DOVE_CRYPT_PHYS_BASE (DOVE_SB_REGS_PHYS_BASE | 0x30000) diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c index e9fafcf163de..373c3c00d24c 100644 --- a/arch/arm/mach-exynos/pm_domains.c +++ b/arch/arm/mach-exynos/pm_domains.c @@ -119,7 +119,9 @@ static __init void exynos_pm_add_dev_to_genpd(struct platform_device *pdev, struct exynos_pm_domain *pd) { if (pdev->dev.bus) { - if (pm_genpd_add_device(&pd->pd, &pdev->dev)) + if (!pm_genpd_add_device(&pd->pd, &pdev->dev)) + pm_genpd_dev_need_restore(&pdev->dev, true); + else pr_info("%s: error in adding %s device to %s power" "domain\n", __func__, dev_name(&pdev->dev), pd->name); @@ -151,9 +153,12 @@ static __init int exynos4_pm_init_power_domain(void) if (of_have_populated_dt()) return exynos_pm_dt_parse_domains(); - for (idx = 0; idx < ARRAY_SIZE(exynos4_pm_domains); idx++) - pm_genpd_init(&exynos4_pm_domains[idx]->pd, NULL, - exynos4_pm_domains[idx]->is_off); + for (idx = 0; idx < ARRAY_SIZE(exynos4_pm_domains); idx++) { + struct exynos_pm_domain *pd = exynos4_pm_domains[idx]; + int on = __raw_readl(pd->base + 0x4) & S5P_INT_LOCAL_PWR_EN; + + pm_genpd_init(&pd->pd, NULL, !on); + } #ifdef CONFIG_S5P_DEV_FIMD0 exynos_pm_add_dev_to_genpd(&s5p_device_fimd0, &exynos4_pd_lcd0); diff --git a/arch/arm/mach-imx/clk-imx35.c b/arch/arm/mach-imx/clk-imx35.c index 920a8cc42726..c6422fb10bae 100644 --- a/arch/arm/mach-imx/clk-imx35.c +++ b/arch/arm/mach-imx/clk-imx35.c @@ -201,7 +201,6 @@ int __init mx35_clocks_init() pr_err("i.MX35 clk %d: register failed with %ld\n", i, PTR_ERR(clk[i])); - clk_register_clkdev(clk[pata_gate], NULL, "pata_imx"); clk_register_clkdev(clk[can1_gate], NULL, "flexcan.0"); clk_register_clkdev(clk[can2_gate], NULL, "flexcan.1"); @@ -264,6 +263,14 @@ int __init mx35_clocks_init() clk_prepare_enable(clk[iim_gate]); clk_prepare_enable(clk[emi_gate]); + /* + * SCC is needed to boot via mmc after a watchdog reset. The clock code + * before conversion to common clk also enabled UART1 (which isn't + * handled here and not needed for mmc) and IIM (which is enabled + * unconditionally above). + */ + clk_prepare_enable(clk[scc_gate]); + imx_print_silicon_rev("i.MX35", mx35_revision()); #ifdef CONFIG_MXC_USE_EPIT diff --git a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c index f76edb96a48a..ba09552fe5fe 100644 --- a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c +++ b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c @@ -38,7 +38,7 @@ #include <asm/mach-types.h> #include <asm/mach/arch.h> #include <asm/mach/time.h> -#include <asm/system.h> +#include <asm/system_info.h> #include <mach/common.h> #include <mach/iomux-mx27.h> diff --git a/arch/arm/mach-mmp/include/mach/gpio-pxa.h b/arch/arm/mach-mmp/include/mach/gpio-pxa.h deleted file mode 100644 index 0e135a599f3e..000000000000 --- a/arch/arm/mach-mmp/include/mach/gpio-pxa.h +++ /dev/null @@ -1,29 +0,0 @@ -#ifndef __ASM_MACH_GPIO_PXA_H -#define __ASM_MACH_GPIO_PXA_H - -#include <mach/addr-map.h> -#include <mach/cputype.h> -#include <mach/irqs.h> - -#define GPIO_REGS_VIRT (APB_VIRT_BASE + 0x19000) - -#define BANK_OFF(n) (((n) < 3) ? (n) << 2 : 0x100 + (((n) - 3) << 2)) -#define GPIO_REG(x) (*(volatile u32 *)(GPIO_REGS_VIRT + (x))) - -#define gpio_to_bank(gpio) ((gpio) >> 5) - -/* NOTE: these macros are defined here to make optimization of - * gpio_{get,set}_value() to work when 'gpio' is a constant. - * Usage of these macros otherwise is no longer recommended, - * use generic GPIO API whenever possible. - */ -#define GPIO_bit(gpio) (1 << ((gpio) & 0x1f)) - -#define GPLR(x) GPIO_REG(BANK_OFF(gpio_to_bank(x)) + 0x00) -#define GPDR(x) GPIO_REG(BANK_OFF(gpio_to_bank(x)) + 0x0c) -#define GPSR(x) GPIO_REG(BANK_OFF(gpio_to_bank(x)) + 0x18) -#define GPCR(x) GPIO_REG(BANK_OFF(gpio_to_bank(x)) + 0x24) - -#include <plat/gpio-pxa.h> - -#endif /* __ASM_MACH_GPIO_PXA_H */ diff --git a/arch/arm/mach-mv78xx0/include/mach/bridge-regs.h b/arch/arm/mach-mv78xx0/include/mach/bridge-regs.h index c64dbb96dbad..eb187e0e059b 100644 --- a/arch/arm/mach-mv78xx0/include/mach/bridge-regs.h +++ b/arch/arm/mach-mv78xx0/include/mach/bridge-regs.h @@ -31,5 +31,6 @@ #define IRQ_MASK_HIGH_OFF 0x0014 #define TIMER_VIRT_BASE (BRIDGE_VIRT_BASE | 0x0300) +#define TIMER_PHYS_BASE (BRIDGE_PHYS_BASE | 0x0300) #endif diff --git a/arch/arm/mach-mv78xx0/include/mach/mv78xx0.h b/arch/arm/mach-mv78xx0/include/mach/mv78xx0.h index 3674497162e3..e807c4c52a0b 100644 --- a/arch/arm/mach-mv78xx0/include/mach/mv78xx0.h +++ b/arch/arm/mach-mv78xx0/include/mach/mv78xx0.h @@ -42,6 +42,7 @@ #define MV78XX0_CORE0_REGS_PHYS_BASE 0xf1020000 #define MV78XX0_CORE1_REGS_PHYS_BASE 0xf1024000 #define MV78XX0_CORE_REGS_VIRT_BASE 0xfe400000 +#define MV78XX0_CORE_REGS_PHYS_BASE 0xfe400000 #define MV78XX0_CORE_REGS_SIZE SZ_16K #define MV78XX0_PCIE_IO_PHYS_BASE(i) (0xf0800000 + ((i) << 20)) @@ -59,6 +60,7 @@ * Core-specific peripheral registers. */ #define BRIDGE_VIRT_BASE (MV78XX0_CORE_REGS_VIRT_BASE) +#define BRIDGE_PHYS_BASE (MV78XX0_CORE_REGS_PHYS_BASE) /* * Register Map diff --git a/arch/arm/mach-mxs/mach-apx4devkit.c b/arch/arm/mach-mxs/mach-apx4devkit.c index 5e90b9dcdef8..f5f061757deb 100644 --- a/arch/arm/mach-mxs/mach-apx4devkit.c +++ b/arch/arm/mach-mxs/mach-apx4devkit.c @@ -205,6 +205,16 @@ static int apx4devkit_phy_fixup(struct phy_device *phy) return 0; } +static void __init apx4devkit_fec_phy_clk_enable(void) +{ + struct clk *clk; + + /* Enable fec phy clock */ + clk = clk_get_sys("enet_out", NULL); + if (!IS_ERR(clk)) + clk_prepare_enable(clk); +} + static void __init apx4devkit_init(void) { mx28_soc_init(); @@ -225,6 +235,7 @@ static void __init apx4devkit_init(void) phy_register_fixup_for_uid(PHY_ID_KS8051, MICREL_PHY_ID_MASK, apx4devkit_phy_fixup); + apx4devkit_fec_phy_clk_enable(); mx28_add_fec(0, &mx28_fec_pdata); mx28_add_mxs_mmc(0, &apx4devkit_mmc_pdata); diff --git a/arch/arm/mach-omap2/board-overo.c b/arch/arm/mach-omap2/board-overo.c index 8fa2fc3a4c3c..779734d8ba37 100644 --- a/arch/arm/mach-omap2/board-overo.c +++ b/arch/arm/mach-omap2/board-overo.c @@ -494,8 +494,8 @@ static void __init overo_init(void) regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies)); omap3_mux_init(board_mux, OMAP_PACKAGE_CBB); - omap_hsmmc_init(mmc); overo_i2c_init(); + omap_hsmmc_init(mmc); omap_display_init(&overo_dss_data); omap_serial_init(); omap_sdrc_init(mt46h32m32lf6_sdrc_params, diff --git a/arch/arm/mach-omap2/clockdomain.h b/arch/arm/mach-omap2/clockdomain.h index f7b58609bad8..6227e9505c2d 100644 --- a/arch/arm/mach-omap2/clockdomain.h +++ b/arch/arm/mach-omap2/clockdomain.h @@ -31,12 +31,16 @@ * * CLKDM_NO_AUTODEPS: Prevent "autodeps" from being added/removed from this * clockdomain. (Currently, this applies to OMAP3 clockdomains only.) + * CLKDM_ACTIVE_WITH_MPU: The PRCM guarantees that this clockdomain is + * active whenever the MPU is active. True for interconnects and + * the WKUP clockdomains. */ #define CLKDM_CAN_FORCE_SLEEP (1 << 0) #define CLKDM_CAN_FORCE_WAKEUP (1 << 1) #define CLKDM_CAN_ENABLE_AUTO (1 << 2) #define CLKDM_CAN_DISABLE_AUTO (1 << 3) #define CLKDM_NO_AUTODEPS (1 << 4) +#define CLKDM_ACTIVE_WITH_MPU (1 << 5) #define CLKDM_CAN_HWSUP (CLKDM_CAN_ENABLE_AUTO | CLKDM_CAN_DISABLE_AUTO) #define CLKDM_CAN_SWSUP (CLKDM_CAN_FORCE_SLEEP | CLKDM_CAN_FORCE_WAKEUP) diff --git a/arch/arm/mach-omap2/clockdomains2xxx_3xxx_data.c b/arch/arm/mach-omap2/clockdomains2xxx_3xxx_data.c index 839145e1cfbe..4972219653ce 100644 --- a/arch/arm/mach-omap2/clockdomains2xxx_3xxx_data.c +++ b/arch/arm/mach-omap2/clockdomains2xxx_3xxx_data.c @@ -88,4 +88,5 @@ struct clockdomain wkup_common_clkdm = { .name = "wkup_clkdm", .pwrdm = { .name = "wkup_pwrdm" }, .dep_bit = OMAP_EN_WKUP_SHIFT, + .flags = CLKDM_ACTIVE_WITH_MPU, }; diff --git a/arch/arm/mach-omap2/clockdomains44xx_data.c b/arch/arm/mach-omap2/clockdomains44xx_data.c index c53425847493..7f2133abe7d3 100644 --- a/arch/arm/mach-omap2/clockdomains44xx_data.c +++ b/arch/arm/mach-omap2/clockdomains44xx_data.c @@ -381,7 +381,7 @@ static struct clockdomain l4_wkup_44xx_clkdm = { .cm_inst = OMAP4430_PRM_WKUP_CM_INST, .clkdm_offs = OMAP4430_PRM_WKUP_CM_WKUP_CDOFFS, .dep_bit = OMAP4430_L4WKUP_STATDEP_SHIFT, - .flags = CLKDM_CAN_HWSUP, + .flags = CLKDM_CAN_HWSUP | CLKDM_ACTIVE_WITH_MPU, }; static struct clockdomain emu_sys_44xx_clkdm = { diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 773193670ea2..2d710f50fca2 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -1124,15 +1124,18 @@ static struct omap_hwmod_addr_space * __init _find_mpu_rt_addr_space(struct omap * _enable_sysc - try to bring a module out of idle via OCP_SYSCONFIG * @oh: struct omap_hwmod * * - * If module is marked as SWSUP_SIDLE, force the module out of slave - * idle; otherwise, configure it for smart-idle. If module is marked - * as SWSUP_MSUSPEND, force the module out of master standby; - * otherwise, configure it for smart-standby. No return value. + * Ensure that the OCP_SYSCONFIG register for the IP block represented + * by @oh is set to indicate to the PRCM that the IP block is active. + * Usually this means placing the module into smart-idle mode and + * smart-standby, but if there is a bug in the automatic idle handling + * for the IP block, it may need to be placed into the force-idle or + * no-idle variants of these modes. No return value. */ static void _enable_sysc(struct omap_hwmod *oh) { u8 idlemode, sf; u32 v; + bool clkdm_act; if (!oh->class->sysc) return; @@ -1141,8 +1144,16 @@ static void _enable_sysc(struct omap_hwmod *oh) sf = oh->class->sysc->sysc_flags; if (sf & SYSC_HAS_SIDLEMODE) { - idlemode = (oh->flags & HWMOD_SWSUP_SIDLE) ? - HWMOD_IDLEMODE_NO : HWMOD_IDLEMODE_SMART; + clkdm_act = ((oh->clkdm && + oh->clkdm->flags & CLKDM_ACTIVE_WITH_MPU) || + (oh->_clk && oh->_clk->clkdm && + oh->_clk->clkdm->flags & CLKDM_ACTIVE_WITH_MPU)); + if (clkdm_act && !(oh->class->sysc->idlemodes & + (SIDLE_SMART | SIDLE_SMART_WKUP))) + idlemode = HWMOD_IDLEMODE_FORCE; + else + idlemode = (oh->flags & HWMOD_SWSUP_SIDLE) ? + HWMOD_IDLEMODE_NO : HWMOD_IDLEMODE_SMART; _set_slave_idlemode(oh, idlemode, &v); } @@ -1208,8 +1219,13 @@ static void _idle_sysc(struct omap_hwmod *oh) sf = oh->class->sysc->sysc_flags; if (sf & SYSC_HAS_SIDLEMODE) { - idlemode = (oh->flags & HWMOD_SWSUP_SIDLE) ? - HWMOD_IDLEMODE_FORCE : HWMOD_IDLEMODE_SMART; + /* XXX What about HWMOD_IDLEMODE_SMART_WKUP? */ + if (oh->flags & HWMOD_SWSUP_SIDLE || + !(oh->class->sysc->idlemodes & + (SIDLE_SMART | SIDLE_SMART_WKUP))) + idlemode = HWMOD_IDLEMODE_FORCE; + else + idlemode = HWMOD_IDLEMODE_SMART; _set_slave_idlemode(oh, idlemode, &v); } diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c index f30e861ce6d9..b7bcba5221ba 100644 --- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c @@ -1928,7 +1928,7 @@ static struct omap_hwmod_dma_info omap44xx_mcbsp1_sdma_reqs[] = { static struct omap_hwmod_opt_clk mcbsp1_opt_clks[] = { { .role = "pad_fck", .clk = "pad_clks_ck" }, - { .role = "prcm_clk", .clk = "mcbsp1_sync_mux_ck" }, + { .role = "prcm_fck", .clk = "mcbsp1_sync_mux_ck" }, }; static struct omap_hwmod omap44xx_mcbsp1_hwmod = { @@ -1963,7 +1963,7 @@ static struct omap_hwmod_dma_info omap44xx_mcbsp2_sdma_reqs[] = { static struct omap_hwmod_opt_clk mcbsp2_opt_clks[] = { { .role = "pad_fck", .clk = "pad_clks_ck" }, - { .role = "prcm_clk", .clk = "mcbsp2_sync_mux_ck" }, + { .role = "prcm_fck", .clk = "mcbsp2_sync_mux_ck" }, }; static struct omap_hwmod omap44xx_mcbsp2_hwmod = { @@ -1998,7 +1998,7 @@ static struct omap_hwmod_dma_info omap44xx_mcbsp3_sdma_reqs[] = { static struct omap_hwmod_opt_clk mcbsp3_opt_clks[] = { { .role = "pad_fck", .clk = "pad_clks_ck" }, - { .role = "prcm_clk", .clk = "mcbsp3_sync_mux_ck" }, + { .role = "prcm_fck", .clk = "mcbsp3_sync_mux_ck" }, }; static struct omap_hwmod omap44xx_mcbsp3_hwmod = { @@ -2033,7 +2033,7 @@ static struct omap_hwmod_dma_info omap44xx_mcbsp4_sdma_reqs[] = { static struct omap_hwmod_opt_clk mcbsp4_opt_clks[] = { { .role = "pad_fck", .clk = "pad_clks_ck" }, - { .role = "prcm_clk", .clk = "mcbsp4_sync_mux_ck" }, + { .role = "prcm_fck", .clk = "mcbsp4_sync_mux_ck" }, }; static struct omap_hwmod omap44xx_mcbsp4_hwmod = { @@ -3864,7 +3864,7 @@ static struct omap_hwmod_ocp_if omap44xx_l4_cfg__l3_main_2 = { }; /* usb_host_fs -> l3_main_2 */ -static struct omap_hwmod_ocp_if omap44xx_usb_host_fs__l3_main_2 = { +static struct omap_hwmod_ocp_if __maybe_unused omap44xx_usb_host_fs__l3_main_2 = { .master = &omap44xx_usb_host_fs_hwmod, .slave = &omap44xx_l3_main_2_hwmod, .clk = "l3_div_ck", @@ -3922,7 +3922,7 @@ static struct omap_hwmod_ocp_if omap44xx_l4_cfg__l3_main_3 = { }; /* aess -> l4_abe */ -static struct omap_hwmod_ocp_if omap44xx_aess__l4_abe = { +static struct omap_hwmod_ocp_if __maybe_unused omap44xx_aess__l4_abe = { .master = &omap44xx_aess_hwmod, .slave = &omap44xx_l4_abe_hwmod, .clk = "ocp_abe_iclk", @@ -4013,7 +4013,7 @@ static struct omap_hwmod_addr_space omap44xx_aess_addrs[] = { }; /* l4_abe -> aess */ -static struct omap_hwmod_ocp_if omap44xx_l4_abe__aess = { +static struct omap_hwmod_ocp_if __maybe_unused omap44xx_l4_abe__aess = { .master = &omap44xx_l4_abe_hwmod, .slave = &omap44xx_aess_hwmod, .clk = "ocp_abe_iclk", @@ -4031,7 +4031,7 @@ static struct omap_hwmod_addr_space omap44xx_aess_dma_addrs[] = { }; /* l4_abe -> aess (dma) */ -static struct omap_hwmod_ocp_if omap44xx_l4_abe__aess_dma = { +static struct omap_hwmod_ocp_if __maybe_unused omap44xx_l4_abe__aess_dma = { .master = &omap44xx_l4_abe_hwmod, .slave = &omap44xx_aess_hwmod, .clk = "ocp_abe_iclk", @@ -5857,7 +5857,7 @@ static struct omap_hwmod_addr_space omap44xx_usb_host_fs_addrs[] = { }; /* l4_cfg -> usb_host_fs */ -static struct omap_hwmod_ocp_if omap44xx_l4_cfg__usb_host_fs = { +static struct omap_hwmod_ocp_if __maybe_unused omap44xx_l4_cfg__usb_host_fs = { .master = &omap44xx_l4_cfg_hwmod, .slave = &omap44xx_usb_host_fs_hwmod, .clk = "l4_div_ck", @@ -6014,13 +6014,13 @@ static struct omap_hwmod_ocp_if *omap44xx_hwmod_ocp_ifs[] __initdata = { &omap44xx_iva__l3_main_2, &omap44xx_l3_main_1__l3_main_2, &omap44xx_l4_cfg__l3_main_2, - &omap44xx_usb_host_fs__l3_main_2, + /* &omap44xx_usb_host_fs__l3_main_2, */ &omap44xx_usb_host_hs__l3_main_2, &omap44xx_usb_otg_hs__l3_main_2, &omap44xx_l3_main_1__l3_main_3, &omap44xx_l3_main_2__l3_main_3, &omap44xx_l4_cfg__l3_main_3, - &omap44xx_aess__l4_abe, + /* &omap44xx_aess__l4_abe, */ &omap44xx_dsp__l4_abe, &omap44xx_l3_main_1__l4_abe, &omap44xx_mpu__l4_abe, @@ -6029,8 +6029,8 @@ static struct omap_hwmod_ocp_if *omap44xx_hwmod_ocp_ifs[] __initdata = { &omap44xx_l4_cfg__l4_wkup, &omap44xx_mpu__mpu_private, &omap44xx_l4_cfg__ocp_wp_noc, - &omap44xx_l4_abe__aess, - &omap44xx_l4_abe__aess_dma, + /* &omap44xx_l4_abe__aess, */ + /* &omap44xx_l4_abe__aess_dma, */ &omap44xx_l3_main_2__c2c, &omap44xx_l4_wkup__counter_32k, &omap44xx_l4_cfg__ctrl_module_core, @@ -6136,7 +6136,7 @@ static struct omap_hwmod_ocp_if *omap44xx_hwmod_ocp_ifs[] __initdata = { &omap44xx_l4_per__uart2, &omap44xx_l4_per__uart3, &omap44xx_l4_per__uart4, - &omap44xx_l4_cfg__usb_host_fs, + /* &omap44xx_l4_cfg__usb_host_fs, */ &omap44xx_l4_cfg__usb_host_hs, &omap44xx_l4_cfg__usb_otg_hs, &omap44xx_l4_cfg__usb_tll_hs, diff --git a/arch/arm/mach-omap2/twl-common.c b/arch/arm/mach-omap2/twl-common.c index afafd83c84c0..3882f3c7608c 100644 --- a/arch/arm/mach-omap2/twl-common.c +++ b/arch/arm/mach-omap2/twl-common.c @@ -32,6 +32,7 @@ #include "twl-common.h" #include "pm.h" #include "voltage.h" +#include "mux.h" static struct i2c_board_info __initdata pmic_i2c_board_info = { .addr = 0x48, @@ -79,6 +80,7 @@ void __init omap4_pmic_init(const char *pmic_type, struct twl6040_platform_data *twl6040_data, int twl6040_irq) { /* PMIC part*/ + omap_mux_init_signal("sys_nirq1", OMAP_PIN_INPUT_PULLUP | OMAP_PIN_OFF_WAKEUPENABLE); strncpy(omap4_i2c1_board_info[0].type, pmic_type, sizeof(omap4_i2c1_board_info[0].type)); omap4_i2c1_board_info[0].irq = OMAP44XX_IRQ_SYS_1N; diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c index d09da6a746b8..d3de84b0dcbe 100644 --- a/arch/arm/mach-pxa/hx4700.c +++ b/arch/arm/mach-pxa/hx4700.c @@ -127,7 +127,11 @@ static unsigned long hx4700_pin_config[] __initdata = { GPIO19_SSP2_SCLK, GPIO86_SSP2_RXD, GPIO87_SSP2_TXD, - GPIO88_GPIO, + GPIO88_GPIO | MFP_LPM_DRIVE_HIGH, /* TSC2046_CS */ + + /* BQ24022 Regulator */ + GPIO72_GPIO | MFP_LPM_KEEP_OUTPUT, /* BQ24022_nCHARGE_EN */ + GPIO96_GPIO | MFP_LPM_KEEP_OUTPUT, /* BQ24022_ISET2 */ /* HX4700 specific input GPIOs */ GPIO12_GPIO | WAKEUP_ON_EDGE_RISE, /* ASIC3_IRQ */ @@ -135,6 +139,10 @@ static unsigned long hx4700_pin_config[] __initdata = { GPIO14_GPIO, /* nWLAN_IRQ */ /* HX4700 specific output GPIOs */ + GPIO61_GPIO | MFP_LPM_DRIVE_HIGH, /* W3220_nRESET */ + GPIO71_GPIO | MFP_LPM_DRIVE_HIGH, /* ASIC3_nRESET */ + GPIO81_GPIO | MFP_LPM_DRIVE_HIGH, /* CPU_GP_nRESET */ + GPIO116_GPIO | MFP_LPM_DRIVE_HIGH, /* CPU_HW_nRESET */ GPIO102_GPIO | MFP_LPM_DRIVE_LOW, /* SYNAPTICS_POWER_ON */ GPIO10_GPIO, /* GSM_IRQ */ @@ -872,14 +880,19 @@ static struct gpio global_gpios[] = { { GPIO110_HX4700_LCD_LVDD_3V3_ON, GPIOF_OUT_INIT_HIGH, "LCD_LVDD" }, { GPIO111_HX4700_LCD_AVDD_3V3_ON, GPIOF_OUT_INIT_HIGH, "LCD_AVDD" }, { GPIO32_HX4700_RS232_ON, GPIOF_OUT_INIT_HIGH, "RS232_ON" }, + { GPIO61_HX4700_W3220_nRESET, GPIOF_OUT_INIT_HIGH, "W3220_nRESET" }, { GPIO71_HX4700_ASIC3_nRESET, GPIOF_OUT_INIT_HIGH, "ASIC3_nRESET" }, + { GPIO81_HX4700_CPU_GP_nRESET, GPIOF_OUT_INIT_HIGH, "CPU_GP_nRESET" }, { GPIO82_HX4700_EUART_RESET, GPIOF_OUT_INIT_HIGH, "EUART_RESET" }, + { GPIO116_HX4700_CPU_HW_nRESET, GPIOF_OUT_INIT_HIGH, "CPU_HW_nRESET" }, }; static void __init hx4700_init(void) { int ret; + PCFR = PCFR_GPR_EN | PCFR_OPDE; + pxa2xx_mfp_config(ARRAY_AND_SIZE(hx4700_pin_config)); gpio_set_wake(GPIO12_HX4700_ASIC3_IRQ, 1); ret = gpio_request_array(ARRAY_AND_SIZE(global_gpios)); diff --git a/arch/arm/mach-s3c24xx/clock-s3c2440.c b/arch/arm/mach-s3c24xx/clock-s3c2440.c index 414364eb426c..cb2883d553b5 100644 --- a/arch/arm/mach-s3c24xx/clock-s3c2440.c +++ b/arch/arm/mach-s3c24xx/clock-s3c2440.c @@ -106,7 +106,7 @@ static struct clk s3c2440_clk_cam_upll = { static struct clk s3c2440_clk_ac97 = { .name = "ac97", .enable = s3c2410_clkcon_enable, - .ctrlbit = S3C2440_CLKCON_CAMERA, + .ctrlbit = S3C2440_CLKCON_AC97, }; static unsigned long s3c2440_fclk_n_getrate(struct clk *clk) diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c index e859fcdb3d58..fde0d23121dc 100644 --- a/arch/arm/mach-shmobile/platsmp.c +++ b/arch/arm/mach-shmobile/platsmp.c @@ -22,8 +22,13 @@ #include <mach/common.h> #include <mach/emev2.h> +#ifdef CONFIG_ARCH_SH73A0 #define is_sh73a0() (machine_is_ag5evm() || machine_is_kota2() || \ of_machine_is_compatible("renesas,sh73a0")) +#else +#define is_sh73a0() (0) +#endif + #define is_r8a7779() machine_is_marzen() #ifdef CONFIG_ARCH_EMEV2 diff --git a/arch/arm/mach-spear3xx/spear3xx.c b/arch/arm/mach-spear3xx/spear3xx.c index 0f41bd1c47c3..66db5f13af84 100644 --- a/arch/arm/mach-spear3xx/spear3xx.c +++ b/arch/arm/mach-spear3xx/spear3xx.c @@ -87,7 +87,7 @@ void __init spear3xx_map_io(void) static void __init spear3xx_timer_init(void) { - char pclk_name[] = "pll3_48m_clk"; + char pclk_name[] = "pll3_clk"; struct clk *gpt_clk, *pclk; spear3xx_clk_init(); diff --git a/arch/arm/mach-spear6xx/spear6xx.c b/arch/arm/mach-spear6xx/spear6xx.c index 2e2e3596583e..9af67d003c62 100644 --- a/arch/arm/mach-spear6xx/spear6xx.c +++ b/arch/arm/mach-spear6xx/spear6xx.c @@ -423,7 +423,7 @@ void __init spear6xx_map_io(void) static void __init spear6xx_timer_init(void) { - char pclk_name[] = "pll3_48m_clk"; + char pclk_name[] = "pll3_clk"; struct clk *gpt_clk, *pclk; spear6xx_clk_init(); diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c index 1509a3cb5833..4fd93f5c49ec 100644 --- a/arch/arm/mach-ux500/board-mop500.c +++ b/arch/arm/mach-ux500/board-mop500.c @@ -625,11 +625,6 @@ static struct platform_device *snowball_platform_devs[] __initdata = { &ab8500_device, }; -static struct platform_device *snowball_of_platform_devs[] __initdata = { - &snowball_led_dev, - &snowball_key_dev, -}; - static void __init mop500_init_machine(void) { struct device *parent = NULL; @@ -769,6 +764,11 @@ MACHINE_END #ifdef CONFIG_MACH_UX500_DT +static struct platform_device *snowball_of_platform_devs[] __initdata = { + &snowball_led_dev, + &snowball_key_dev, +}; + struct of_dev_auxdata u8500_auxdata_lookup[] __initdata = { /* Requires DMA and call-back bindings. */ OF_DEV_AUXDATA("arm,pl011", 0x80120000, "uart0", &uart0_plat), @@ -786,6 +786,8 @@ struct of_dev_auxdata u8500_auxdata_lookup[] __initdata = { OF_DEV_AUXDATA("st,nomadik-gpio", 0x8011e000, "gpio.6", NULL), OF_DEV_AUXDATA("st,nomadik-gpio", 0x8011e080, "gpio.7", NULL), OF_DEV_AUXDATA("st,nomadik-gpio", 0xa03fe000, "gpio.8", NULL), + /* Requires device name bindings. */ + OF_DEV_AUXDATA("stericsson,nmk_pinctrl", 0, "pinctrl-db8500", NULL), {}, }; diff --git a/arch/arm/mach-ux500/timer.c b/arch/arm/mach-ux500/timer.c index 741e71feca78..66e7f00884ab 100644 --- a/arch/arm/mach-ux500/timer.c +++ b/arch/arm/mach-ux500/timer.c @@ -63,8 +63,10 @@ static void __init ux500_timer_init(void) /* TODO: Once MTU has been DT:ed place code above into else. */ if (of_have_populated_dt()) { +#ifdef CONFIG_OF np = of_find_matching_node(NULL, prcmu_timer_of_match); if (!np) +#endif goto dt_fail; tmp_base = of_iomap(np, 0); diff --git a/arch/arm/mach-versatile/pci.c b/arch/arm/mach-versatile/pci.c index bec933b04ef0..e95bf84cc837 100644 --- a/arch/arm/mach-versatile/pci.c +++ b/arch/arm/mach-versatile/pci.c @@ -339,7 +339,6 @@ void __init pci_versatile_preinit(void) static int __init versatile_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { int irq; - int devslot = PCI_SLOT(dev->devfn); /* slot, pin, irq * 24 1 27 diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 4044abcf6f9d..655878bcc96d 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1091,7 +1091,7 @@ error: while (--i) if (pages[i]) __free_pages(pages[i], 0); - if (array_size < PAGE_SIZE) + if (array_size <= PAGE_SIZE) kfree(pages); else vfree(pages); @@ -1106,7 +1106,7 @@ static int __iommu_free_buffer(struct device *dev, struct page **pages, size_t s for (i = 0; i < count; i++) if (pages[i]) __free_pages(pages[i], 0); - if (array_size < PAGE_SIZE) + if (array_size <= PAGE_SIZE) kfree(pages); else vfree(pages); diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index c471436c7952..2e8a1efdf7b8 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -64,7 +64,7 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page #ifdef CONFIG_ZONE_DMA extern phys_addr_t arm_dma_limit; #else -#define arm_dma_limit ((u32)~0) +#define arm_dma_limit ((phys_addr_t)~0) #endif extern phys_addr_t arm_lowmem_limit; diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index e5dad60b558b..cf4528d51774 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -791,6 +791,79 @@ void __init iotable_init(struct map_desc *io_desc, int nr) } } +#ifndef CONFIG_ARM_LPAE + +/* + * The Linux PMD is made of two consecutive section entries covering 2MB + * (see definition in include/asm/pgtable-2level.h). However a call to + * create_mapping() may optimize static mappings by using individual + * 1MB section mappings. This leaves the actual PMD potentially half + * initialized if the top or bottom section entry isn't used, leaving it + * open to problems if a subsequent ioremap() or vmalloc() tries to use + * the virtual space left free by that unused section entry. + * + * Let's avoid the issue by inserting dummy vm entries covering the unused + * PMD halves once the static mappings are in place. + */ + +static void __init pmd_empty_section_gap(unsigned long addr) +{ + struct vm_struct *vm; + + vm = early_alloc_aligned(sizeof(*vm), __alignof__(*vm)); + vm->addr = (void *)addr; + vm->size = SECTION_SIZE; + vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING; + vm->caller = pmd_empty_section_gap; + vm_area_add_early(vm); +} + +static void __init fill_pmd_gaps(void) +{ + struct vm_struct *vm; + unsigned long addr, next = 0; + pmd_t *pmd; + + /* we're still single threaded hence no lock needed here */ + for (vm = vmlist; vm; vm = vm->next) { + if (!(vm->flags & VM_ARM_STATIC_MAPPING)) + continue; + addr = (unsigned long)vm->addr; + if (addr < next) + continue; + + /* + * Check if this vm starts on an odd section boundary. + * If so and the first section entry for this PMD is free + * then we block the corresponding virtual address. + */ + if ((addr & ~PMD_MASK) == SECTION_SIZE) { + pmd = pmd_off_k(addr); + if (pmd_none(*pmd)) + pmd_empty_section_gap(addr & PMD_MASK); + } + + /* + * Then check if this vm ends on an odd section boundary. + * If so and the second section entry for this PMD is empty + * then we block the corresponding virtual address. + */ + addr += vm->size; + if ((addr & ~PMD_MASK) == SECTION_SIZE) { + pmd = pmd_off_k(addr) + 1; + if (pmd_none(*pmd)) + pmd_empty_section_gap(addr); + } + + /* no need to look at any vm entry until we hit the next PMD */ + next = (addr + PMD_SIZE - 1) & PMD_MASK; + } +} + +#else +#define fill_pmd_gaps() do { } while (0) +#endif + static void * __initdata vmalloc_min = (void *)(VMALLOC_END - (240 << 20) - VMALLOC_OFFSET); @@ -1072,6 +1145,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc) */ if (mdesc->map_io) mdesc->map_io(); + fill_pmd_gaps(); /* * Finally flush the caches and tlb to ensure that we're in a diff --git a/arch/arm/plat-samsung/adc.c b/arch/arm/plat-samsung/adc.c index 33ecd0c9f0c3..b1e05ccff3ac 100644 --- a/arch/arm/plat-samsung/adc.c +++ b/arch/arm/plat-samsung/adc.c @@ -157,11 +157,13 @@ int s3c_adc_start(struct s3c_adc_client *client, return -EINVAL; } - if (client->is_ts && adc->ts_pend) - return -EAGAIN; - spin_lock_irqsave(&adc->lock, flags); + if (client->is_ts && adc->ts_pend) { + spin_unlock_irqrestore(&adc->lock, flags); + return -EAGAIN; + } + client->channel = channel; client->nr_samples = nr_samples; diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c index 1d214cb9d770..6303974c2ee0 100644 --- a/arch/arm/plat-samsung/devs.c +++ b/arch/arm/plat-samsung/devs.c @@ -126,7 +126,8 @@ struct platform_device s3c_device_adc = { #ifdef CONFIG_CPU_S3C2440 static struct resource s3c_camif_resource[] = { [0] = DEFINE_RES_MEM(S3C2440_PA_CAMIF, S3C2440_SZ_CAMIF), - [1] = DEFINE_RES_IRQ(IRQ_CAM), + [1] = DEFINE_RES_IRQ(IRQ_S3C2440_CAM_C), + [2] = DEFINE_RES_IRQ(IRQ_S3C2440_CAM_P), }; struct platform_device s3c_device_camif = { diff --git a/arch/arm/plat-samsung/s5p-clock.c b/arch/arm/plat-samsung/s5p-clock.c index 031a61899bef..48a159911037 100644 --- a/arch/arm/plat-samsung/s5p-clock.c +++ b/arch/arm/plat-samsung/s5p-clock.c @@ -37,6 +37,7 @@ struct clk clk_ext_xtal_mux = { struct clk clk_xusbxti = { .name = "xusbxti", .id = -1, + .rate = 24000000, }; struct clk s5p_clk_27m = { diff --git a/arch/h8300/include/asm/pgtable.h b/arch/h8300/include/asm/pgtable.h index a09230a08e02..62ef17676b40 100644 --- a/arch/h8300/include/asm/pgtable.h +++ b/arch/h8300/include/asm/pgtable.h @@ -70,4 +70,7 @@ extern int is_in_rom(unsigned long); #define VMALLOC_END 0xffffffff #define arch_enter_lazy_cpu_mode() do {} while (0) + +#include <asm-generic/pgtable.h> + #endif /* _H8300_PGTABLE_H */ diff --git a/arch/h8300/include/asm/uaccess.h b/arch/h8300/include/asm/uaccess.h index 356068cd0879..8725d1ad4272 100644 --- a/arch/h8300/include/asm/uaccess.h +++ b/arch/h8300/include/asm/uaccess.h @@ -100,7 +100,6 @@ extern int __put_user_bad(void); break; \ default: \ __gu_err = __get_user_bad(); \ - __gu_val = 0; \ break; \ } \ (x) = __gu_val; \ @@ -159,4 +158,6 @@ clear_user(void *to, unsigned long n) return 0; } +#define __clear_user clear_user + #endif /* _H8300_UACCESS_H */ diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c index fca10378701b..5adaadaf9218 100644 --- a/arch/h8300/kernel/signal.c +++ b/arch/h8300/kernel/signal.c @@ -447,7 +447,7 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ -statis void do_signal(struct pt_regs *regs) +static void do_signal(struct pt_regs *regs) { siginfo_t info; int signr; diff --git a/arch/h8300/kernel/time.c b/arch/h8300/kernel/time.c index 32263a138aa6..e0f74191d553 100644 --- a/arch/h8300/kernel/time.c +++ b/arch/h8300/kernel/time.c @@ -27,6 +27,7 @@ #include <linux/profile.h> #include <asm/io.h> +#include <asm/irq_regs.h> #include <asm/timer.h> #define TICK_SIZE (tick_nsec / 1000) diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c index f7264621e58d..149fbefc1a4d 100644 --- a/arch/hexagon/kernel/smp.c +++ b/arch/hexagon/kernel/smp.c @@ -180,9 +180,7 @@ void __cpuinit start_secondary(void) notify_cpu_starting(cpu); - ipi_call_lock(); set_cpu_online(cpu, true); - ipi_call_unlock(); local_irq_enable(); diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index 1113b8aba07f..963d2db53bfa 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -382,7 +382,6 @@ smp_callin (void) set_numa_node(cpu_to_node_map[cpuid]); set_numa_mem(local_memory_node(cpu_to_node_map[cpuid])); - ipi_call_lock_irq(); spin_lock(&vector_lock); /* Setup the per cpu irq handling data structures */ __setup_vector_irq(cpuid); @@ -390,7 +389,6 @@ smp_callin (void) set_cpu_online(cpuid, true); per_cpu(cpu_state, cpuid) = CPU_ONLINE; spin_unlock(&vector_lock); - ipi_call_unlock_irq(); smp_setup_percpu_timer(); diff --git a/arch/m32r/boot/compressed/Makefile b/arch/m32r/boot/compressed/Makefile index 177716b1d613..01729c2979ba 100644 --- a/arch/m32r/boot/compressed/Makefile +++ b/arch/m32r/boot/compressed/Makefile @@ -43,9 +43,9 @@ endif OBJCOPYFLAGS += -R .empty_zero_page -suffix_$(CONFIG_KERNEL_GZIP) = gz -suffix_$(CONFIG_KERNEL_BZIP2) = bz2 -suffix_$(CONFIG_KERNEL_LZMA) = lzma +suffix-$(CONFIG_KERNEL_GZIP) = gz +suffix-$(CONFIG_KERNEL_BZIP2) = bz2 +suffix-$(CONFIG_KERNEL_LZMA) = lzma $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y) FORCE $(call if_changed,ld) diff --git a/arch/m32r/boot/compressed/misc.c b/arch/m32r/boot/compressed/misc.c index 370d60881977..28a09529f206 100644 --- a/arch/m32r/boot/compressed/misc.c +++ b/arch/m32r/boot/compressed/misc.c @@ -28,7 +28,7 @@ static unsigned long free_mem_ptr; static unsigned long free_mem_end_ptr; #ifdef CONFIG_KERNEL_BZIP2 -static void *memset(void *s, int c, size_t n) +void *memset(void *s, int c, size_t n) { char *ss = s; @@ -39,6 +39,16 @@ static void *memset(void *s, int c, size_t n) #endif #ifdef CONFIG_KERNEL_GZIP +void *memcpy(void *dest, const void *src, size_t n) +{ + char *d = dest; + const char *s = src; + while (n--) + *d++ = *s++; + + return dest; +} + #define BOOT_HEAP_SIZE 0x10000 #include "../../../../lib/decompress_inflate.c" #endif diff --git a/arch/m32r/include/asm/ptrace.h b/arch/m32r/include/asm/ptrace.h index 527527584dd0..4313aa62b51b 100644 --- a/arch/m32r/include/asm/ptrace.h +++ b/arch/m32r/include/asm/ptrace.h @@ -113,9 +113,6 @@ struct pt_regs { #define PTRACE_OLDSETOPTIONS 21 -/* options set using PTRACE_SETOPTIONS */ -#define PTRACE_O_TRACESYSGOOD 0x00000001 - #ifdef __KERNEL__ #include <asm/m32r.h> /* M32R_PSW_BSM, M32R_PSW_BPM */ diff --git a/arch/m32r/include/asm/smp.h b/arch/m32r/include/asm/smp.h index cf7829a61551..c689b828dfe2 100644 --- a/arch/m32r/include/asm/smp.h +++ b/arch/m32r/include/asm/smp.h @@ -79,11 +79,6 @@ static __inline__ int cpu_number_map(int cpu) return cpu; } -static __inline__ unsigned int num_booting_cpus(void) -{ - return cpumask_weight(&cpu_callout_map); -} - extern void smp_send_timer(void); extern unsigned long send_IPI_mask_phys(const cpumask_t*, int, int); diff --git a/arch/m32r/kernel/ptrace.c b/arch/m32r/kernel/ptrace.c index 4c03361537aa..51f5e9aa4901 100644 --- a/arch/m32r/kernel/ptrace.c +++ b/arch/m32r/kernel/ptrace.c @@ -591,17 +591,16 @@ void user_enable_single_step(struct task_struct *child) if (access_process_vm(child, pc&~3, &insn, sizeof(insn), 0) != sizeof(insn)) - return -EIO; + return; compute_next_pc(insn, pc, &next_pc, child); if (next_pc & 0x80000000) - return -EIO; + return; if (embed_debug_trap(child, next_pc)) - return -EIO; + return; invalidate_cache(); - return 0; } void user_disable_single_step(struct task_struct *child) diff --git a/arch/m32r/kernel/signal.c b/arch/m32r/kernel/signal.c index f3fb2c029cfc..d0f60b97bbc5 100644 --- a/arch/m32r/kernel/signal.c +++ b/arch/m32r/kernel/signal.c @@ -286,7 +286,7 @@ handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, case -ERESTARTNOINTR: regs->r0 = regs->orig_r0; if (prev_insn(regs) < 0) - return -EFAULT; + return; } } diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 09ab87ee6fef..b3e10fdd3898 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -288,6 +288,7 @@ config MIPS_MALTA select SYS_HAS_CPU_MIPS32_R1 select SYS_HAS_CPU_MIPS32_R2 select SYS_HAS_CPU_MIPS64_R1 + select SYS_HAS_CPU_MIPS64_R2 select SYS_HAS_CPU_NEVADA select SYS_HAS_CPU_RM7000 select SYS_HAS_EARLY_PRINTK @@ -1423,6 +1424,7 @@ config CPU_SB1 config CPU_CAVIUM_OCTEON bool "Cavium Octeon processor" depends on SYS_HAS_CPU_CAVIUM_OCTEON + select ARCH_SPARSEMEM_ENABLE select CPU_HAS_PREFETCH select CPU_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_SMP diff --git a/arch/mips/bcm47xx/Kconfig b/arch/mips/bcm47xx/Kconfig index 6210b8d84109..b311be45a720 100644 --- a/arch/mips/bcm47xx/Kconfig +++ b/arch/mips/bcm47xx/Kconfig @@ -21,6 +21,7 @@ config BCM47XX_BCMA select BCMA select BCMA_HOST_SOC select BCMA_DRIVER_MIPS + select BCMA_HOST_PCI if PCI select BCMA_DRIVER_PCI_HOSTMODE if PCI default y help diff --git a/arch/mips/bcm63xx/dev-pcmcia.c b/arch/mips/bcm63xx/dev-pcmcia.c index de4d917fd54d..a551bab5ecb9 100644 --- a/arch/mips/bcm63xx/dev-pcmcia.c +++ b/arch/mips/bcm63xx/dev-pcmcia.c @@ -79,11 +79,11 @@ static int __init config_pcmcia_cs(unsigned int cs, return ret; } -static const __initdata struct { +static const struct { unsigned int cs; unsigned int base; unsigned int size; -} pcmcia_cs[3] = { +} pcmcia_cs[3] __initconst = { { .cs = MPI_CS_PCMCIA_COMMON, .base = BCM_PCMCIA_COMMON_BASE_PA, diff --git a/arch/mips/cavium-octeon/Kconfig b/arch/mips/cavium-octeon/Kconfig index f9e275a50d98..2f4f6d5e05b6 100644 --- a/arch/mips/cavium-octeon/Kconfig +++ b/arch/mips/cavium-octeon/Kconfig @@ -82,10 +82,6 @@ config CAVIUM_OCTEON_LOCK_L2_MEMCPY help Lock the kernel's implementation of memcpy() into L2. -config ARCH_SPARSEMEM_ENABLE - def_bool y - select SPARSEMEM_STATIC - config IOMMU_HELPER bool diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 4b93048044eb..ee1fb9f7f517 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -185,7 +185,6 @@ static void __cpuinit octeon_init_secondary(void) octeon_init_cvmcount(); octeon_irq_setup_secondary(); - raw_local_irq_enable(); } /** @@ -233,6 +232,7 @@ static void octeon_smp_finish(void) /* to generate the first CPU timer interrupt */ write_c0_compare(read_c0_count() + mips_hpt_frequency / HZ); + local_irq_enable(); } /** diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h index 2e1ad4c652b7..82ad35ce2b45 100644 --- a/arch/mips/include/asm/bitops.h +++ b/arch/mips/include/asm/bitops.h @@ -17,7 +17,6 @@ #include <linux/irqflags.h> #include <linux/types.h> #include <asm/barrier.h> -#include <asm/bug.h> #include <asm/byteorder.h> /* sigh ... */ #include <asm/cpu-features.h> #include <asm/sgidefs.h> diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index 285a41fa0b18..eee10dc07ac1 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -8,6 +8,7 @@ #ifndef __ASM_CMPXCHG_H #define __ASM_CMPXCHG_H +#include <linux/bug.h> #include <linux/irqflags.h> #include <asm/war.h> diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h index f9fa2a479dd0..95e40c1e8ed1 100644 --- a/arch/mips/include/asm/cpu.h +++ b/arch/mips/include/asm/cpu.h @@ -94,6 +94,7 @@ #define PRID_IMP_24KE 0x9600 #define PRID_IMP_74K 0x9700 #define PRID_IMP_1004K 0x9900 +#define PRID_IMP_M14KC 0x9c00 /* * These are the PRID's for when 23:16 == PRID_COMP_SIBYTE @@ -260,12 +261,12 @@ enum cpu_type_enum { */ CPU_4KC, CPU_4KEC, CPU_4KSC, CPU_24K, CPU_34K, CPU_1004K, CPU_74K, CPU_ALCHEMY, CPU_PR4450, CPU_BMIPS32, CPU_BMIPS3300, CPU_BMIPS4350, - CPU_BMIPS4380, CPU_BMIPS5000, CPU_JZRISC, + CPU_BMIPS4380, CPU_BMIPS5000, CPU_JZRISC, CPU_M14KC, /* * MIPS64 class processors */ - CPU_5KC, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2, + CPU_5KC, CPU_5KE, CPU_20KC, CPU_25KF, CPU_SB1, CPU_SB1A, CPU_LOONGSON2, CPU_CAVIUM_OCTEON, CPU_CAVIUM_OCTEON_PLUS, CPU_CAVIUM_OCTEON2, CPU_XLR, CPU_XLP, @@ -288,7 +289,7 @@ enum cpu_type_enum { #define MIPS_CPU_ISA_M64R2 0x00000100 #define MIPS_CPU_ISA_32BIT (MIPS_CPU_ISA_I | MIPS_CPU_ISA_II | \ - MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2 ) + MIPS_CPU_ISA_M32R1 | MIPS_CPU_ISA_M32R2) #define MIPS_CPU_ISA_64BIT (MIPS_CPU_ISA_III | MIPS_CPU_ISA_IV | \ MIPS_CPU_ISA_V | MIPS_CPU_ISA_M64R1 | MIPS_CPU_ISA_M64R2) diff --git a/arch/mips/include/asm/gic.h b/arch/mips/include/asm/gic.h index 86548da650e7..991b659e2548 100644 --- a/arch/mips/include/asm/gic.h +++ b/arch/mips/include/asm/gic.h @@ -206,7 +206,7 @@ #define GIC_VPE_EIC_SHADOW_SET_BASE 0x0100 #define GIC_VPE_EIC_SS(intr) \ - (GIC_EIC_SHADOW_SET_BASE + (4 * intr)) + (GIC_VPE_EIC_SHADOW_SET_BASE + (4 * intr)) #define GIC_VPE_EIC_VEC_BASE 0x0800 #define GIC_VPE_EIC_VEC(intr) \ @@ -330,6 +330,17 @@ struct gic_intr_map { #define GIC_FLAG_TRANSPARENT 0x02 }; +/* + * This is only used in EIC mode. This helps to figure out which + * shared interrupts we need to process when we get a vector interrupt. + */ +#define GIC_MAX_SHARED_INTR 0x5 +struct gic_shared_intr_map { + unsigned int num_shared_intr; + unsigned int intr_list[GIC_MAX_SHARED_INTR]; + unsigned int local_intr_mask; +}; + extern void gic_init(unsigned long gic_base_addr, unsigned long gic_addrspace_size, struct gic_intr_map *intrmap, unsigned int intrmap_size, unsigned int irqbase); @@ -338,5 +349,7 @@ extern unsigned int gic_get_int(void); extern void gic_send_ipi(unsigned int intr); extern unsigned int plat_ipi_call_int_xlate(unsigned int); extern unsigned int plat_ipi_resched_int_xlate(unsigned int); +extern void gic_bind_eic_interrupt(int irq, int set); +extern unsigned int gic_get_timer_pending(void); #endif /* _ASM_GICREGS_H */ diff --git a/arch/mips/include/asm/inst.h b/arch/mips/include/asm/inst.h index 7ebfc392e58d..ab84064283db 100644 --- a/arch/mips/include/asm/inst.h +++ b/arch/mips/include/asm/inst.h @@ -251,7 +251,7 @@ struct f_format { /* FPU register format */ unsigned int func : 6; }; -struct ma_format { /* FPU multipy and add format (MIPS IV) */ +struct ma_format { /* FPU multiply and add format (MIPS IV) */ unsigned int opcode : 6; unsigned int fr : 5; unsigned int ft : 5; @@ -324,7 +324,7 @@ struct f_format { /* FPU register format */ unsigned int opcode : 6; }; -struct ma_format { /* FPU multipy and add format (MIPS IV) */ +struct ma_format { /* FPU multiply and add format (MIPS IV) */ unsigned int fmt : 2; unsigned int func : 4; unsigned int fd : 5; diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index a58f22998a86..29d9c23c20c7 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -17,6 +17,7 @@ #include <linux/types.h> #include <asm/addrspace.h> +#include <asm/bug.h> #include <asm/byteorder.h> #include <asm/cpu.h> #include <asm/cpu-features.h> diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index fb698dc09bc9..78dbb8a86da2 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -136,6 +136,7 @@ extern void free_irqno(unsigned int irq); * IE7. Since R2 their number has to be read from the c0_intctl register. */ #define CP0_LEGACY_COMPARE_IRQ 7 +#define CP0_LEGACY_PERFCNT_IRQ 7 extern int cp0_compare_irq; extern int cp0_compare_irq_shift; diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h index 94d4faad29a1..fdcd78ca1b03 100644 --- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h +++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h @@ -99,7 +99,7 @@ #define CKCTL_6368_USBH_CLK_EN (1 << 15) #define CKCTL_6368_DISABLE_GLESS_EN (1 << 16) #define CKCTL_6368_NAND_CLK_EN (1 << 17) -#define CKCTL_6368_IPSEC_CLK_EN (1 << 17) +#define CKCTL_6368_IPSEC_CLK_EN (1 << 18) #define CKCTL_6368_ALL_SAFE_EN (CKCTL_6368_SWPKT_USB_EN | \ CKCTL_6368_SWPKT_SAR_EN | \ diff --git a/arch/mips/include/asm/mips-boards/maltaint.h b/arch/mips/include/asm/mips-boards/maltaint.h index d11aa02a956a..5447d9fc4219 100644 --- a/arch/mips/include/asm/mips-boards/maltaint.h +++ b/arch/mips/include/asm/mips-boards/maltaint.h @@ -86,6 +86,16 @@ #define GIC_CPU_INT4 4 /* . */ #define GIC_CPU_INT5 5 /* Core Interrupt 5 */ +/* MALTA GIC local interrupts */ +#define GIC_INT_TMR (GIC_CPU_INT5) +#define GIC_INT_PERFCTR (GIC_CPU_INT5) + +/* GIC constants */ +/* Add 2 to convert non-eic hw int # to eic vector # */ +#define GIC_CPU_TO_VEC_OFFSET (2) +/* If we map an intr to pin X, GIC will actually generate vector X+1 */ +#define GIC_PIN_TO_VEC_OFFSET (1) + #define GIC_EXT_INTR(x) x /* External Interrupts used for IPI */ diff --git a/arch/mips/include/asm/mipsmtregs.h b/arch/mips/include/asm/mipsmtregs.h index c9420aa97e32..e71ff4c317f2 100644 --- a/arch/mips/include/asm/mipsmtregs.h +++ b/arch/mips/include/asm/mipsmtregs.h @@ -48,7 +48,7 @@ #define CP0_VPECONF0 $1, 2 #define CP0_VPECONF1 $1, 3 #define CP0_YQMASK $1, 4 -#define CP0_VPESCHEDULE $1, 5 +#define CP0_VPESCHEDULE $1, 5 #define CP0_VPESCHEFBK $1, 6 #define CP0_TCSTATUS $2, 1 #define CP0_TCBIND $2, 2 diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h index 5d33621b5658..4f8ddba8c360 100644 --- a/arch/mips/include/asm/switch_to.h +++ b/arch/mips/include/asm/switch_to.h @@ -22,7 +22,7 @@ struct task_struct; * switch_to(n) should switch tasks to task nr n, first * checking that n isn't the current task, in which case it does nothing. */ -extern asmlinkage void *resume(void *last, void *next, void *next_ti); +extern asmlinkage void *resume(void *last, void *next, void *next_ti, u32 __usedfpu); extern unsigned int ll_bit; extern struct task_struct *ll_task; @@ -66,11 +66,13 @@ do { \ #define switch_to(prev, next, last) \ do { \ + u32 __usedfpu; \ __mips_mt_fpaff_switch_to(prev); \ if (cpu_has_dsp) \ __save_dsp(prev); \ __clear_software_ll_bit(); \ - (last) = resume(prev, next, task_thread_info(next)); \ + __usedfpu = test_and_clear_tsk_thread_flag(prev, TIF_USEDFPU); \ + (last) = resume(prev, next, task_thread_info(next), __usedfpu); \ } while (0) #define finish_arch_switch(prev) \ diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h index e2eca7d10598..ca97e0ecb64b 100644 --- a/arch/mips/include/asm/thread_info.h +++ b/arch/mips/include/asm/thread_info.h @@ -60,6 +60,8 @@ struct thread_info { register struct thread_info *__current_thread_info __asm__("$28"); #define current_thread_info() __current_thread_info +#endif /* !__ASSEMBLY__ */ + /* thread information allocation */ #if defined(CONFIG_PAGE_SIZE_4KB) && defined(CONFIG_32BIT) #define THREAD_SIZE_ORDER (1) @@ -85,8 +87,6 @@ register struct thread_info *__current_thread_info __asm__("$28"); #define STACK_WARN (THREAD_SIZE / 8) -#endif /* !__ASSEMBLY__ */ - #define PREEMPT_ACTIVE 0x10000000 /* diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 6ae7ce4ac63e..f4630e1082ab 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -4,7 +4,7 @@ * Copyright (C) xxxx the Anonymous * Copyright (C) 1994 - 2006 Ralf Baechle * Copyright (C) 2003, 2004 Maciej W. Rozycki - * Copyright (C) 2001, 2004 MIPS Inc. + * Copyright (C) 2001, 2004, 2011, 2012 MIPS Technologies, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -199,6 +199,7 @@ void __init check_wait(void) cpu_wait = rm7k_wait_irqoff; break; + case CPU_M14KC: case CPU_24K: case CPU_34K: case CPU_1004K: @@ -810,6 +811,10 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu) c->cputype = CPU_5KC; __cpu_name[cpu] = "MIPS 5Kc"; break; + case PRID_IMP_5KE: + c->cputype = CPU_5KE; + __cpu_name[cpu] = "MIPS 5KE"; + break; case PRID_IMP_20KC: c->cputype = CPU_20KC; __cpu_name[cpu] = "MIPS 20Kc"; @@ -831,6 +836,10 @@ static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu) c->cputype = CPU_74K; __cpu_name[cpu] = "MIPS 74Kc"; break; + case PRID_IMP_M14KC: + c->cputype = CPU_M14KC; + __cpu_name[cpu] = "MIPS M14Kc"; + break; case PRID_IMP_1004K: c->cputype = CPU_1004K; __cpu_name[cpu] = "MIPS 1004Kc"; diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c index 57ba13edb03a..3fc1691110dc 100644 --- a/arch/mips/kernel/mips_ksyms.c +++ b/arch/mips/kernel/mips_ksyms.c @@ -5,7 +5,7 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (C) 1996, 97, 98, 99, 2000, 01, 03, 04, 05 by Ralf Baechle + * Copyright (C) 1996, 97, 98, 99, 2000, 01, 03, 04, 05, 12 by Ralf Baechle * Copyright (C) 1999, 2000, 01 Silicon Graphics, Inc. */ #include <linux/interrupt.h> @@ -35,6 +35,12 @@ EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(kernel_thread); /* + * Functions that operate on entire pages. Mostly used by memory management. + */ +EXPORT_SYMBOL(clear_page); +EXPORT_SYMBOL(copy_page); + +/* * Userspace access stuff. */ EXPORT_SYMBOL(__copy_user); diff --git a/arch/mips/kernel/octeon_switch.S b/arch/mips/kernel/octeon_switch.S index ce89c8061708..0441f54b2a6a 100644 --- a/arch/mips/kernel/octeon_switch.S +++ b/arch/mips/kernel/octeon_switch.S @@ -31,7 +31,7 @@ /* * task_struct *resume(task_struct *prev, task_struct *next, - * struct thread_info *next_ti) + * struct thread_info *next_ti, int usedfpu) */ .align 7 LEAF(resume) diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index f29099b104c4..eb5e394a4650 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -162,11 +162,6 @@ static unsigned int counters_total_to_per_cpu(unsigned int counters) return counters >> vpe_shift(); } -static unsigned int counters_per_cpu_to_total(unsigned int counters) -{ - return counters << vpe_shift(); -} - #else /* !CONFIG_MIPS_MT_SMP */ #define vpe_id() 0 diff --git a/arch/mips/kernel/r2300_switch.S b/arch/mips/kernel/r2300_switch.S index 293898391e67..9c51be5a163a 100644 --- a/arch/mips/kernel/r2300_switch.S +++ b/arch/mips/kernel/r2300_switch.S @@ -43,7 +43,7 @@ /* * task_struct *resume(task_struct *prev, task_struct *next, - * struct thread_info *next_ti) ) + * struct thread_info *next_ti, int usedfpu) */ LEAF(resume) mfc0 t1, CP0_STATUS @@ -51,18 +51,9 @@ LEAF(resume) cpu_save_nonscratch a0 sw ra, THREAD_REG31(a0) - /* - * check if we need to save FPU registers - */ - lw t3, TASK_THREAD_INFO(a0) - lw t0, TI_FLAGS(t3) - li t1, _TIF_USEDFPU - and t2, t0, t1 - beqz t2, 1f - nor t1, zero, t1 + beqz a3, 1f - and t0, t0, t1 - sw t0, TI_FLAGS(t3) + PTR_L t3, TASK_THREAD_INFO(a0) /* * clear saved user stack CU1 bit diff --git a/arch/mips/kernel/r4k_switch.S b/arch/mips/kernel/r4k_switch.S index 9414f9354469..42d2a3938420 100644 --- a/arch/mips/kernel/r4k_switch.S +++ b/arch/mips/kernel/r4k_switch.S @@ -41,7 +41,7 @@ /* * task_struct *resume(task_struct *prev, task_struct *next, - * struct thread_info *next_ti) + * struct thread_info *next_ti, int usedfpu) */ .align 5 LEAF(resume) @@ -53,16 +53,10 @@ /* * check if we need to save FPU registers */ - PTR_L t3, TASK_THREAD_INFO(a0) - LONG_L t0, TI_FLAGS(t3) - li t1, _TIF_USEDFPU - and t2, t0, t1 - beqz t2, 1f - nor t1, zero, t1 - and t0, t0, t1 - LONG_S t0, TI_FLAGS(t3) + beqz a3, 1f + PTR_L t3, TASK_THREAD_INFO(a0) /* * clear saved user stack CU1 bit */ diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 3046e2986006..8e393b8443f7 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -15,7 +15,6 @@ #include <linux/smp.h> #include <linux/interrupt.h> #include <linux/spinlock.h> -#include <linux/init.h> #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/reboot.h> @@ -197,13 +196,6 @@ static void bmips_init_secondary(void) write_c0_brcm_action(ACTION_CLR_IPI(smp_processor_id(), 0)); #endif - - /* make sure there won't be a timer interrupt for a little while */ - write_c0_compare(read_c0_count() + mips_hpt_frequency / HZ); - - irq_enable_hazard(); - set_c0_status(IE_SW0 | IE_SW1 | IE_IRQ1 | IE_IRQ5 | ST0_IE); - irq_enable_hazard(); } /* @@ -212,6 +204,13 @@ static void bmips_init_secondary(void) static void bmips_smp_finish(void) { pr_info("SMP: CPU%d is running\n", smp_processor_id()); + + /* make sure there won't be a timer interrupt for a little while */ + write_c0_compare(read_c0_count() + mips_hpt_frequency / HZ); + + irq_enable_hazard(); + set_c0_status(IE_SW0 | IE_SW1 | IE_IRQ1 | IE_IRQ5 | ST0_IE); + irq_enable_hazard(); } /* diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 48650c818040..1268392f1d27 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -122,13 +122,21 @@ asmlinkage __cpuinit void start_secondary(void) notify_cpu_starting(cpu); - mp_ops->smp_finish(); + set_cpu_online(cpu, true); + set_cpu_sibling_map(cpu); cpu_set(cpu, cpu_callin_map); synchronise_count_slave(); + /* + * irq will be enabled in ->smp_finish(), enabling it too early + * is dangerous. + */ + WARN_ON_ONCE(!irqs_disabled()); + mp_ops->smp_finish(); + cpu_idle(); } @@ -196,8 +204,6 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle) while (!cpu_isset(cpu, cpu_callin_map)) udelay(100); - set_cpu_online(cpu, true); - return 0; } diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c index f5dd38f1d015..15b5f3cfd20c 100644 --- a/arch/mips/kernel/smtc.c +++ b/arch/mips/kernel/smtc.c @@ -322,7 +322,7 @@ int __init smtc_build_cpu_map(int start_cpu_slot) /* * Common setup before any secondaries are started - * Make sure all CPU's are in a sensible state before we boot any of the + * Make sure all CPUs are in a sensible state before we boot any of the * secondaries. * * For MIPS MT "SMTC" operation, we set up all TCs, spread as evenly @@ -340,12 +340,12 @@ static void smtc_tc_setup(int vpe, int tc, int cpu) /* * TCContext gets an offset from the base of the IPIQ array * to be used in low-level code to detect the presence of - * an active IPI queue + * an active IPI queue. */ write_tc_c0_tccontext((sizeof(struct smtc_ipi_q) * cpu) << 16); /* Bind tc to vpe */ write_tc_c0_tcbind(vpe); - /* In general, all TCs should have the same cpu_data indications */ + /* In general, all TCs should have the same cpu_data indications. */ memcpy(&cpu_data[cpu], &cpu_data[0], sizeof(struct cpuinfo_mips)); /* For 34Kf, start with TC/CPU 0 as sole owner of single FPU context */ if (cpu_data[0].cputype == CPU_34K || @@ -358,8 +358,8 @@ static void smtc_tc_setup(int vpe, int tc, int cpu) } /* - * Tweak to get Count registes in as close a sync as possible. - * Value seems good for 34K-class cores. + * Tweak to get Count registes in as close a sync as possible. The + * value seems good for 34K-class cores. */ #define CP0_SKEW 8 @@ -615,7 +615,6 @@ void __cpuinit smtc_boot_secondary(int cpu, struct task_struct *idle) void smtc_init_secondary(void) { - local_irq_enable(); } void smtc_smp_finish(void) @@ -631,6 +630,8 @@ void smtc_smp_finish(void) if (cpu > 0 && (cpu_data[cpu].vpe_id != cpu_data[cpu - 1].vpe_id)) write_c0_compare(read_c0_count() + mips_hpt_frequency/HZ); + local_irq_enable(); + printk("TC %d going on-line as CPU %d\n", cpu_data[smp_processor_id()].tc_id, smp_processor_id()); } diff --git a/arch/mips/kernel/sync-r4k.c b/arch/mips/kernel/sync-r4k.c index 99f913c8d7a6..842d55e411fd 100644 --- a/arch/mips/kernel/sync-r4k.c +++ b/arch/mips/kernel/sync-r4k.c @@ -111,7 +111,6 @@ void __cpuinit synchronise_count_master(void) void __cpuinit synchronise_count_slave(void) { int i; - unsigned long flags; unsigned int initcount; int ncpus; @@ -123,8 +122,6 @@ void __cpuinit synchronise_count_slave(void) return; #endif - local_irq_save(flags); - /* * Not every cpu is online at the time this gets called, * so we first wait for the master to say everyone is ready @@ -154,7 +151,5 @@ void __cpuinit synchronise_count_slave(void) } /* Arrange for an interrupt in a short while */ write_c0_compare(read_c0_count() + COUNTON); - - local_irq_restore(flags); } #undef NR_LOOPS diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 2d0c2a277f52..c3c293543703 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -132,6 +132,9 @@ static void show_backtrace(struct task_struct *task, const struct pt_regs *regs) unsigned long ra = regs->regs[31]; unsigned long pc = regs->cp0_epc; + if (!task) + task = current; + if (raw_show_trace || !__kernel_text_address(pc)) { show_raw_backtrace(sp); return; @@ -1249,6 +1252,7 @@ static inline void parity_protection_init(void) break; case CPU_5KC: + case CPU_5KE: write_c0_ecc(0x80000000); back_to_back_c0_hazard(); /* Set the PE bit (bit 31) in the c0_errctl register. */ @@ -1498,6 +1502,7 @@ extern void flush_tlb_handlers(void); * Timer interrupt */ int cp0_compare_irq; +EXPORT_SYMBOL_GPL(cp0_compare_irq); int cp0_compare_irq_shift; /* @@ -1597,7 +1602,7 @@ void __cpuinit per_cpu_trap_init(bool is_boot_cpu) cp0_perfcount_irq = -1; } else { cp0_compare_irq = CP0_LEGACY_COMPARE_IRQ; - cp0_compare_irq_shift = cp0_compare_irq; + cp0_compare_irq_shift = CP0_LEGACY_PERFCNT_IRQ; cp0_perfcount_irq = -1; } diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index 924da5eb7031..df243a64f430 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -1,5 +1,6 @@ #include <asm/asm-offsets.h> #include <asm/page.h> +#include <asm/thread_info.h> #include <asm-generic/vmlinux.lds.h> #undef mips @@ -72,7 +73,7 @@ SECTIONS .data : { /* Data */ . = . + DATAOFFSET; /* for CONFIG_MAPPED_KERNEL */ - INIT_TASK_DATA(PAGE_SIZE) + INIT_TASK_DATA(THREAD_SIZE) NOSAVE_DATA CACHELINE_ALIGNED_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT) READ_MOSTLY_DATA(1 << CONFIG_MIPS_L1_CACHE_SHIFT) diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile index 4aa20280613e..fd6203f14f1f 100644 --- a/arch/mips/mm/Makefile +++ b/arch/mips/mm/Makefile @@ -3,8 +3,8 @@ # obj-y += cache.o dma-default.o extable.o fault.o \ - gup.o init.o mmap.o page.o tlbex.o \ - tlbex-fault.o uasm.o + gup.o init.o mmap.o page.o page-funcs.o \ + tlbex.o tlbex-fault.o uasm.o obj-$(CONFIG_32BIT) += ioremap.o pgtable-32.o obj-$(CONFIG_64BIT) += pgtable-64.o diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 5109be96d98d..f092c265dc63 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -977,7 +977,7 @@ static void __cpuinit probe_pcache(void) c->icache.linesz = 2 << lsize; else c->icache.linesz = lsize; - c->icache.sets = 64 << ((config1 >> 22) & 7); + c->icache.sets = 32 << (((config1 >> 22) + 1) & 7); c->icache.ways = 1 + ((config1 >> 16) & 7); icache_size = c->icache.sets * @@ -997,7 +997,7 @@ static void __cpuinit probe_pcache(void) c->dcache.linesz = 2 << lsize; else c->dcache.linesz= lsize; - c->dcache.sets = 64 << ((config1 >> 13) & 7); + c->dcache.sets = 32 << (((config1 >> 13) + 1) & 7); c->dcache.ways = 1 + ((config1 >> 7) & 7); dcache_size = c->dcache.sets * @@ -1051,6 +1051,7 @@ static void __cpuinit probe_pcache(void) case CPU_R14000: break; + case CPU_M14KC: case CPU_24K: case CPU_34K: case CPU_74K: diff --git a/arch/mips/mm/page-funcs.S b/arch/mips/mm/page-funcs.S new file mode 100644 index 000000000000..48a6b38ff13e --- /dev/null +++ b/arch/mips/mm/page-funcs.S @@ -0,0 +1,50 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Micro-assembler generated clear_page/copy_page functions. + * + * Copyright (C) 2012 MIPS Technologies, Inc. + * Copyright (C) 2012 Ralf Baechle <ralf@linux-mips.org> + */ +#include <asm/asm.h> +#include <asm/regdef.h> + +#ifdef CONFIG_SIBYTE_DMA_PAGEOPS +#define cpu_clear_page_function_name clear_page_cpu +#define cpu_copy_page_function_name copy_page_cpu +#else +#define cpu_clear_page_function_name clear_page +#define cpu_copy_page_function_name copy_page +#endif + +/* + * Maximum sizes: + * + * R4000 128 bytes S-cache: 0x058 bytes + * R4600 v1.7: 0x05c bytes + * R4600 v2.0: 0x060 bytes + * With prefetching, 16 word strides 0x120 bytes + */ +EXPORT(__clear_page_start) +LEAF(cpu_clear_page_function_name) +1: j 1b /* Dummy, will be replaced. */ + .space 288 +END(cpu_clear_page_function_name) +EXPORT(__clear_page_end) + +/* + * Maximum sizes: + * + * R4000 128 bytes S-cache: 0x11c bytes + * R4600 v1.7: 0x080 bytes + * R4600 v2.0: 0x07c bytes + * With prefetching, 16 word strides 0x540 bytes + */ +EXPORT(__copy_page_start) +LEAF(cpu_copy_page_function_name) +1: j 1b /* Dummy, will be replaced. */ + .space 1344 +END(cpu_copy_page_function_name) +EXPORT(__copy_page_end) diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c index cc0b626858b3..98f530e18216 100644 --- a/arch/mips/mm/page.c +++ b/arch/mips/mm/page.c @@ -6,6 +6,7 @@ * Copyright (C) 2003, 04, 05 Ralf Baechle (ralf@linux-mips.org) * Copyright (C) 2007 Maciej W. Rozycki * Copyright (C) 2008 Thiemo Seufer + * Copyright (C) 2012 MIPS Technologies, Inc. */ #include <linux/init.h> #include <linux/kernel.h> @@ -71,45 +72,6 @@ static struct uasm_reloc __cpuinitdata relocs[5]; #define cpu_is_r4600_v1_x() ((read_c0_prid() & 0xfffffff0) == 0x00002010) #define cpu_is_r4600_v2_x() ((read_c0_prid() & 0xfffffff0) == 0x00002020) -/* - * Maximum sizes: - * - * R4000 128 bytes S-cache: 0x058 bytes - * R4600 v1.7: 0x05c bytes - * R4600 v2.0: 0x060 bytes - * With prefetching, 16 word strides 0x120 bytes - */ - -static u32 clear_page_array[0x120 / 4]; - -#ifdef CONFIG_SIBYTE_DMA_PAGEOPS -void clear_page_cpu(void *page) __attribute__((alias("clear_page_array"))); -#else -void clear_page(void *page) __attribute__((alias("clear_page_array"))); -#endif - -EXPORT_SYMBOL(clear_page); - -/* - * Maximum sizes: - * - * R4000 128 bytes S-cache: 0x11c bytes - * R4600 v1.7: 0x080 bytes - * R4600 v2.0: 0x07c bytes - * With prefetching, 16 word strides 0x540 bytes - */ -static u32 copy_page_array[0x540 / 4]; - -#ifdef CONFIG_SIBYTE_DMA_PAGEOPS -void -copy_page_cpu(void *to, void *from) __attribute__((alias("copy_page_array"))); -#else -void copy_page(void *to, void *from) __attribute__((alias("copy_page_array"))); -#endif - -EXPORT_SYMBOL(copy_page); - - static int pref_bias_clear_store __cpuinitdata; static int pref_bias_copy_load __cpuinitdata; static int pref_bias_copy_store __cpuinitdata; @@ -282,10 +244,15 @@ static inline void __cpuinit build_clear_pref(u32 **buf, int off) } } +extern u32 __clear_page_start; +extern u32 __clear_page_end; +extern u32 __copy_page_start; +extern u32 __copy_page_end; + void __cpuinit build_clear_page(void) { int off; - u32 *buf = (u32 *)&clear_page_array; + u32 *buf = &__clear_page_start; struct uasm_label *l = labels; struct uasm_reloc *r = relocs; int i; @@ -356,17 +323,17 @@ void __cpuinit build_clear_page(void) uasm_i_jr(&buf, RA); uasm_i_nop(&buf); - BUG_ON(buf > clear_page_array + ARRAY_SIZE(clear_page_array)); + BUG_ON(buf > &__clear_page_end); uasm_resolve_relocs(relocs, labels); pr_debug("Synthesized clear page handler (%u instructions).\n", - (u32)(buf - clear_page_array)); + (u32)(buf - &__clear_page_start)); pr_debug("\t.set push\n"); pr_debug("\t.set noreorder\n"); - for (i = 0; i < (buf - clear_page_array); i++) - pr_debug("\t.word 0x%08x\n", clear_page_array[i]); + for (i = 0; i < (buf - &__clear_page_start); i++) + pr_debug("\t.word 0x%08x\n", (&__clear_page_start)[i]); pr_debug("\t.set pop\n"); } @@ -427,7 +394,7 @@ static inline void build_copy_store_pref(u32 **buf, int off) void __cpuinit build_copy_page(void) { int off; - u32 *buf = (u32 *)©_page_array; + u32 *buf = &__copy_page_start; struct uasm_label *l = labels; struct uasm_reloc *r = relocs; int i; @@ -595,21 +562,23 @@ void __cpuinit build_copy_page(void) uasm_i_jr(&buf, RA); uasm_i_nop(&buf); - BUG_ON(buf > copy_page_array + ARRAY_SIZE(copy_page_array)); + BUG_ON(buf > &__copy_page_end); uasm_resolve_relocs(relocs, labels); pr_debug("Synthesized copy page handler (%u instructions).\n", - (u32)(buf - copy_page_array)); + (u32)(buf - &__copy_page_start)); pr_debug("\t.set push\n"); pr_debug("\t.set noreorder\n"); - for (i = 0; i < (buf - copy_page_array); i++) - pr_debug("\t.word 0x%08x\n", copy_page_array[i]); + for (i = 0; i < (buf - &__copy_page_start); i++) + pr_debug("\t.word 0x%08x\n", (&__copy_page_start)[i]); pr_debug("\t.set pop\n"); } #ifdef CONFIG_SIBYTE_DMA_PAGEOPS +extern void clear_page_cpu(void *page); +extern void copy_page_cpu(void *to, void *from); /* * Pad descriptors to cacheline, since each is exclusively owned by a diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 0bc485b3cd60..03eb0ef91580 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -9,6 +9,7 @@ * Copyright (C) 2005, 2007, 2008, 2009 Maciej W. Rozycki * Copyright (C) 2006 Ralf Baechle (ralf@linux-mips.org) * Copyright (C) 2008, 2009 Cavium Networks, Inc. + * Copyright (C) 2011 MIPS Technologies, Inc. * * ... and the days got worse and worse and now you see * I've gone completly out of my mind. @@ -494,6 +495,7 @@ static void __cpuinit build_tlb_write_entry(u32 **p, struct uasm_label **l, case CPU_R14000: case CPU_4KC: case CPU_4KEC: + case CPU_M14KC: case CPU_SB1: case CPU_SB1A: case CPU_4KSC: diff --git a/arch/mips/mti-malta/malta-pci.c b/arch/mips/mti-malta/malta-pci.c index bf80921f2f56..284dea54faf5 100644 --- a/arch/mips/mti-malta/malta-pci.c +++ b/arch/mips/mti-malta/malta-pci.c @@ -241,8 +241,9 @@ void __init mips_pcibios_init(void) return; } - if (controller->io_resource->start < 0x00001000UL) /* FIXME */ - controller->io_resource->start = 0x00001000UL; + /* Change start address to avoid conflicts with ACPI and SMB devices */ + if (controller->io_resource->start < 0x00002000UL) + controller->io_resource->start = 0x00002000UL; iomem_resource.end &= 0xfffffffffULL; /* 64 GB */ ioport_resource.end = controller->io_resource->end; @@ -253,7 +254,7 @@ void __init mips_pcibios_init(void) } /* Enable PCI 2.1 compatibility in PIIX4 */ -static void __init quirk_dlcsetup(struct pci_dev *dev) +static void __devinit quirk_dlcsetup(struct pci_dev *dev) { u8 odlc, ndlc; (void) pci_read_config_byte(dev, 0x82, &odlc); diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c index b7f37d4982fa..2e28f653f66d 100644 --- a/arch/mips/mti-malta/malta-setup.c +++ b/arch/mips/mti-malta/malta-setup.c @@ -111,7 +111,7 @@ static void __init pci_clock_check(void) unsigned int __iomem *jmpr_p = (unsigned int *) ioremap(MALTA_JMPRS_REG, sizeof(unsigned int)); int jmpr = (__raw_readl(jmpr_p) >> 2) & 0x07; - static const int pciclocks[] __initdata = { + static const int pciclocks[] __initconst = { 33, 20, 25, 30, 12, 16, 37, 10 }; int pciclock = pciclocks[jmpr]; diff --git a/arch/mips/netlogic/xlp/setup.c b/arch/mips/netlogic/xlp/setup.c index acb677a1227c..b3df7c2aad1e 100644 --- a/arch/mips/netlogic/xlp/setup.c +++ b/arch/mips/netlogic/xlp/setup.c @@ -82,8 +82,10 @@ void __init prom_free_prom_memory(void) void xlp_mmu_init(void) { + /* enable extended TLB and Large Fixed TLB */ write_c0_config6(read_c0_config6() | 0x24); - current_cpu_data.tlbsize = ((read_c0_config6() >> 16) & 0xffff) + 1; + + /* set page mask of Fixed TLB in config7 */ write_c0_config7(PM_DEFAULT_MASK >> (13 + (ffz(PM_DEFAULT_MASK >> 13) / 2))); } @@ -100,6 +102,10 @@ void __init prom_init(void) nlm_common_ebase = read_c0_ebase() & (~((1 << 12) - 1)); #ifdef CONFIG_SMP nlm_wakeup_secondary_cpus(0xffffffff); + + /* update TLB size after waking up threads */ + current_cpu_data.tlbsize = ((read_c0_config6() >> 16) & 0xffff) + 1; + register_smp_ops(&nlm_smp_ops); #endif } diff --git a/arch/mips/oprofile/common.c b/arch/mips/oprofile/common.c index d1f2d4c52d42..b6e378211a2c 100644 --- a/arch/mips/oprofile/common.c +++ b/arch/mips/oprofile/common.c @@ -78,6 +78,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) switch (current_cpu_type()) { case CPU_5KC: + case CPU_M14KC: case CPU_20KC: case CPU_24K: case CPU_25KF: diff --git a/arch/mips/oprofile/op_model_mipsxx.c b/arch/mips/oprofile/op_model_mipsxx.c index baba3bcaa3c2..4d80a856048d 100644 --- a/arch/mips/oprofile/op_model_mipsxx.c +++ b/arch/mips/oprofile/op_model_mipsxx.c @@ -322,6 +322,10 @@ static int __init mipsxx_init(void) op_model_mipsxx_ops.num_counters = counters; switch (current_cpu_type()) { + case CPU_M14KC: + op_model_mipsxx_ops.cpu_type = "mips/M14Kc"; + break; + case CPU_20KC: op_model_mipsxx_ops.cpu_type = "mips/20K"; break; diff --git a/arch/mips/pci/fixup-fuloong2e.c b/arch/mips/pci/fixup-fuloong2e.c index d5d4c018fb04..0857ab8c3919 100644 --- a/arch/mips/pci/fixup-fuloong2e.c +++ b/arch/mips/pci/fixup-fuloong2e.c @@ -48,7 +48,7 @@ int pcibios_plat_dev_init(struct pci_dev *dev) return 0; } -static void __init loongson2e_nec_fixup(struct pci_dev *pdev) +static void __devinit loongson2e_nec_fixup(struct pci_dev *pdev) { unsigned int val; @@ -60,7 +60,7 @@ static void __init loongson2e_nec_fixup(struct pci_dev *pdev) pci_write_config_dword(pdev, 0xe4, 1 << 5); } -static void __init loongson2e_686b_func0_fixup(struct pci_dev *pdev) +static void __devinit loongson2e_686b_func0_fixup(struct pci_dev *pdev) { unsigned char c; @@ -135,7 +135,7 @@ static void __init loongson2e_686b_func0_fixup(struct pci_dev *pdev) printk(KERN_INFO"via686b fix: ISA bridge done\n"); } -static void __init loongson2e_686b_func1_fixup(struct pci_dev *pdev) +static void __devinit loongson2e_686b_func1_fixup(struct pci_dev *pdev) { printk(KERN_INFO"via686b fix: IDE\n"); @@ -168,19 +168,19 @@ static void __init loongson2e_686b_func1_fixup(struct pci_dev *pdev) printk(KERN_INFO"via686b fix: IDE done\n"); } -static void __init loongson2e_686b_func2_fixup(struct pci_dev *pdev) +static void __devinit loongson2e_686b_func2_fixup(struct pci_dev *pdev) { /* irq routing */ pci_write_config_byte(pdev, PCI_INTERRUPT_LINE, 10); } -static void __init loongson2e_686b_func3_fixup(struct pci_dev *pdev) +static void __devinit loongson2e_686b_func3_fixup(struct pci_dev *pdev) { /* irq routing */ pci_write_config_byte(pdev, PCI_INTERRUPT_LINE, 11); } -static void __init loongson2e_686b_func5_fixup(struct pci_dev *pdev) +static void __devinit loongson2e_686b_func5_fixup(struct pci_dev *pdev) { unsigned int val; unsigned char c; diff --git a/arch/mips/pci/fixup-lemote2f.c b/arch/mips/pci/fixup-lemote2f.c index 4b9768d5d729..a7b917dcf604 100644 --- a/arch/mips/pci/fixup-lemote2f.c +++ b/arch/mips/pci/fixup-lemote2f.c @@ -96,21 +96,21 @@ int pcibios_plat_dev_init(struct pci_dev *dev) } /* CS5536 SPEC. fixup */ -static void __init loongson_cs5536_isa_fixup(struct pci_dev *pdev) +static void __devinit loongson_cs5536_isa_fixup(struct pci_dev *pdev) { /* the uart1 and uart2 interrupt in PIC is enabled as default */ pci_write_config_dword(pdev, PCI_UART1_INT_REG, 1); pci_write_config_dword(pdev, PCI_UART2_INT_REG, 1); } -static void __init loongson_cs5536_ide_fixup(struct pci_dev *pdev) +static void __devinit loongson_cs5536_ide_fixup(struct pci_dev *pdev) { /* setting the mutex pin as IDE function */ pci_write_config_dword(pdev, PCI_IDE_CFG_REG, CS5536_IDE_FLASH_SIGNATURE); } -static void __init loongson_cs5536_acc_fixup(struct pci_dev *pdev) +static void __devinit loongson_cs5536_acc_fixup(struct pci_dev *pdev) { /* enable the AUDIO interrupt in PIC */ pci_write_config_dword(pdev, PCI_ACC_INT_REG, 1); @@ -118,14 +118,14 @@ static void __init loongson_cs5536_acc_fixup(struct pci_dev *pdev) pci_write_config_byte(pdev, PCI_LATENCY_TIMER, 0xc0); } -static void __init loongson_cs5536_ohci_fixup(struct pci_dev *pdev) +static void __devinit loongson_cs5536_ohci_fixup(struct pci_dev *pdev) { /* enable the OHCI interrupt in PIC */ /* THE OHCI, EHCI, UDC, OTG are shared with interrupt in PIC */ pci_write_config_dword(pdev, PCI_OHCI_INT_REG, 1); } -static void __init loongson_cs5536_ehci_fixup(struct pci_dev *pdev) +static void __devinit loongson_cs5536_ehci_fixup(struct pci_dev *pdev) { u32 hi, lo; @@ -137,7 +137,7 @@ static void __init loongson_cs5536_ehci_fixup(struct pci_dev *pdev) pci_write_config_dword(pdev, PCI_EHCI_FLADJ_REG, 0x2000); } -static void __init loongson_nec_fixup(struct pci_dev *pdev) +static void __devinit loongson_nec_fixup(struct pci_dev *pdev) { unsigned int val; diff --git a/arch/mips/pci/fixup-malta.c b/arch/mips/pci/fixup-malta.c index 0f48498bc231..70073c98ed32 100644 --- a/arch/mips/pci/fixup-malta.c +++ b/arch/mips/pci/fixup-malta.c @@ -49,10 +49,10 @@ int pcibios_plat_dev_init(struct pci_dev *dev) return 0; } -static void __init malta_piix_func0_fixup(struct pci_dev *pdev) +static void __devinit malta_piix_func0_fixup(struct pci_dev *pdev) { unsigned char reg_val; - static int piixirqmap[16] __initdata = { /* PIIX PIRQC[A:D] irq mappings */ + static int piixirqmap[16] __devinitdata = { /* PIIX PIRQC[A:D] irq mappings */ 0, 0, 0, 3, 4, 5, 6, 7, 0, 9, 10, 11, @@ -83,7 +83,7 @@ static void __init malta_piix_func0_fixup(struct pci_dev *pdev) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371AB_0, malta_piix_func0_fixup); -static void __init malta_piix_func1_fixup(struct pci_dev *pdev) +static void __devinit malta_piix_func1_fixup(struct pci_dev *pdev) { unsigned char reg_val; diff --git a/arch/mips/pci/fixup-mpc30x.c b/arch/mips/pci/fixup-mpc30x.c index e08f49cb6875..8e4f8288eca2 100644 --- a/arch/mips/pci/fixup-mpc30x.c +++ b/arch/mips/pci/fixup-mpc30x.c @@ -22,13 +22,13 @@ #include <asm/vr41xx/mpc30x.h> -static const int internal_func_irqs[] __initdata = { +static const int internal_func_irqs[] __initconst = { VRC4173_CASCADE_IRQ, VRC4173_AC97_IRQ, VRC4173_USB_IRQ, }; -static const int irq_tab_mpc30x[] __initdata = { +static const int irq_tab_mpc30x[] __initconst = { [12] = VRC4173_PCMCIA1_IRQ, [13] = VRC4173_PCMCIA2_IRQ, [29] = MQ200_IRQ, diff --git a/arch/mips/pci/fixup-sb1250.c b/arch/mips/pci/fixup-sb1250.c index f0bb9146e6c0..d02900a72916 100644 --- a/arch/mips/pci/fixup-sb1250.c +++ b/arch/mips/pci/fixup-sb1250.c @@ -15,7 +15,7 @@ * Set the BCM1250, etc. PCI host bridge's TRDY timeout * to the finite max. */ -static void __init quirk_sb1250_pci(struct pci_dev *dev) +static void __devinit quirk_sb1250_pci(struct pci_dev *dev) { pci_write_config_byte(dev, 0x40, 0xff); } @@ -25,7 +25,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_PCI, /* * The BCM1250, etc. PCI/HT bridge reports as a host bridge. */ -static void __init quirk_sb1250_ht(struct pci_dev *dev) +static void __devinit quirk_sb1250_ht(struct pci_dev *dev) { dev->class = PCI_CLASS_BRIDGE_PCI << 8; } @@ -35,7 +35,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_HT, /* * Set the SP1011 HT/PCI bridge's TRDY timeout to the finite max. */ -static void __init quirk_sp1011(struct pci_dev *dev) +static void __devinit quirk_sp1011(struct pci_dev *dev) { pci_write_config_byte(dev, 0x64, 0xff); } diff --git a/arch/mips/pci/ops-tx4927.c b/arch/mips/pci/ops-tx4927.c index a1e7e6d80c8c..bc13e29d2bb3 100644 --- a/arch/mips/pci/ops-tx4927.c +++ b/arch/mips/pci/ops-tx4927.c @@ -495,7 +495,7 @@ irqreturn_t tx4927_pcierr_interrupt(int irq, void *dev_id) } #ifdef CONFIG_TOSHIBA_FPCIB0 -static void __init tx4927_quirk_slc90e66_bridge(struct pci_dev *dev) +static void __devinit tx4927_quirk_slc90e66_bridge(struct pci_dev *dev) { struct tx4927_pcic_reg __iomem *pcicptr = pci_bus_to_pcicptr(dev->bus); diff --git a/arch/mips/pci/pci-ip27.c b/arch/mips/pci/pci-ip27.c index 0fbe4c0c170a..fdc24440294c 100644 --- a/arch/mips/pci/pci-ip27.c +++ b/arch/mips/pci/pci-ip27.c @@ -212,7 +212,7 @@ static inline void pci_enable_swapping(struct pci_dev *dev) bridge->b_widget.w_tflush; /* Flush */ } -static void __init pci_fixup_ioc3(struct pci_dev *d) +static void __devinit pci_fixup_ioc3(struct pci_dev *d) { pci_disable_swapping(d); } diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c index ea453532a33c..075d87acd12a 100644 --- a/arch/mips/pci/pci-lantiq.c +++ b/arch/mips/pci/pci-lantiq.c @@ -129,7 +129,7 @@ static int __devinit ltq_pci_startup(struct platform_device *pdev) /* setup reset gpio used by pci */ reset_gpio = of_get_named_gpio(node, "gpio-reset", 0); - if (reset_gpio > 0) + if (gpio_is_valid(reset_gpio)) devm_gpio_request(&pdev->dev, reset_gpio, "pci-reset"); /* enable auto-switching between PCI and EBU */ @@ -192,7 +192,7 @@ static int __devinit ltq_pci_startup(struct platform_device *pdev) ltq_ebu_w32(ltq_ebu_r32(LTQ_EBU_PCC_IEN) | 0x10, LTQ_EBU_PCC_IEN); /* toggle reset pin */ - if (reset_gpio > 0) { + if (gpio_is_valid(reset_gpio)) { __gpio_set_value(reset_gpio, 0); wmb(); mdelay(1); diff --git a/arch/mips/pci/pci-xlr.c b/arch/mips/pci/pci-xlr.c index 1644805a6730..172af1cd5867 100644 --- a/arch/mips/pci/pci-xlr.c +++ b/arch/mips/pci/pci-xlr.c @@ -41,6 +41,7 @@ #include <linux/irq.h> #include <linux/irqdesc.h> #include <linux/console.h> +#include <linux/pci_regs.h> #include <asm/io.h> @@ -156,35 +157,55 @@ struct pci_controller nlm_pci_controller = { .io_offset = 0x00000000UL, }; +/* + * The top level PCIe links on the XLS PCIe controller appear as + * bridges. Given a device, this function finds which link it is + * on. + */ +static struct pci_dev *xls_get_pcie_link(const struct pci_dev *dev) +{ + struct pci_bus *bus, *p; + + /* Find the bridge on bus 0 */ + bus = dev->bus; + for (p = bus->parent; p && p->number != 0; p = p->parent) + bus = p; + + return p ? bus->self : NULL; +} + static int get_irq_vector(const struct pci_dev *dev) { + struct pci_dev *lnk; + if (!nlm_chip_is_xls()) - return PIC_PCIX_IRQ; /* for XLR just one IRQ*/ + return PIC_PCIX_IRQ; /* for XLR just one IRQ */ /* * For XLS PCIe, there is an IRQ per Link, find out which * link the device is on to assign interrupts - */ - if (dev->bus->self == NULL) + */ + lnk = xls_get_pcie_link(dev); + if (lnk == NULL) return 0; - switch (dev->bus->self->devfn) { - case 0x0: + switch (PCI_SLOT(lnk->devfn)) { + case 0: return PIC_PCIE_LINK0_IRQ; - case 0x8: + case 1: return PIC_PCIE_LINK1_IRQ; - case 0x10: + case 2: if (nlm_chip_is_xls_b()) return PIC_PCIE_XLSB0_LINK2_IRQ; else return PIC_PCIE_LINK2_IRQ; - case 0x18: + case 3: if (nlm_chip_is_xls_b()) return PIC_PCIE_XLSB0_LINK3_IRQ; else return PIC_PCIE_LINK3_IRQ; } - WARN(1, "Unexpected devfn %d\n", dev->bus->self->devfn); + WARN(1, "Unexpected devfn %d\n", lnk->devfn); return 0; } @@ -202,7 +223,27 @@ void arch_teardown_msi_irq(unsigned int irq) int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc) { struct msi_msg msg; + struct pci_dev *lnk; int irq, ret; + u16 val; + + /* MSI not supported on XLR */ + if (!nlm_chip_is_xls()) + return 1; + + /* + * Enable MSI on the XLS PCIe controller bridge which was disabled + * at enumeration, the bridge MSI capability is at 0x50 + */ + lnk = xls_get_pcie_link(dev); + if (lnk == NULL) + return 1; + + pci_read_config_word(lnk, 0x50 + PCI_MSI_FLAGS, &val); + if ((val & PCI_MSI_FLAGS_ENABLE) == 0) { + val |= PCI_MSI_FLAGS_ENABLE; + pci_write_config_word(lnk, 0x50 + PCI_MSI_FLAGS, val); + } irq = get_irq_vector(dev); if (irq <= 0) @@ -327,7 +368,7 @@ static int __init pcibios_init(void) } } else { /* XLR PCI controller ACK */ - irq_set_handler_data(PIC_PCIE_XLSB0_LINK3_IRQ, xlr_pci_ack); + irq_set_handler_data(PIC_PCIX_IRQ, xlr_pci_ack); } return 0; diff --git a/arch/mips/pmc-sierra/yosemite/smp.c b/arch/mips/pmc-sierra/yosemite/smp.c index b71fae231049..5edab2bc6fc0 100644 --- a/arch/mips/pmc-sierra/yosemite/smp.c +++ b/arch/mips/pmc-sierra/yosemite/smp.c @@ -115,11 +115,11 @@ static void yos_send_ipi_mask(const struct cpumask *mask, unsigned int action) */ static void __cpuinit yos_init_secondary(void) { - set_c0_status(ST0_CO | ST0_IE | ST0_IM); } static void __cpuinit yos_smp_finish(void) { + set_c0_status(ST0_CO | ST0_IM | ST0_IE); } /* Hook for after all CPUs are online */ diff --git a/arch/mips/powertv/asic/asic-calliope.c b/arch/mips/powertv/asic/asic-calliope.c index 0a170e0ffeaa..7773f3d956b0 100644 --- a/arch/mips/powertv/asic/asic-calliope.c +++ b/arch/mips/powertv/asic/asic-calliope.c @@ -28,7 +28,7 @@ #define CALLIOPE_ADDR(x) (CALLIOPE_IO_BASE + (x)) -const struct register_map calliope_register_map __initdata = { +const struct register_map calliope_register_map __initconst = { .eic_slow0_strt_add = {.phys = CALLIOPE_ADDR(0x800000)}, .eic_cfg_bits = {.phys = CALLIOPE_ADDR(0x800038)}, .eic_ready_status = {.phys = CALLIOPE_ADDR(0x80004c)}, diff --git a/arch/mips/powertv/asic/asic-cronus.c b/arch/mips/powertv/asic/asic-cronus.c index bbc0c122be5e..da076db7b7ed 100644 --- a/arch/mips/powertv/asic/asic-cronus.c +++ b/arch/mips/powertv/asic/asic-cronus.c @@ -28,7 +28,7 @@ #define CRONUS_ADDR(x) (CRONUS_IO_BASE + (x)) -const struct register_map cronus_register_map __initdata = { +const struct register_map cronus_register_map __initconst = { .eic_slow0_strt_add = {.phys = CRONUS_ADDR(0x000000)}, .eic_cfg_bits = {.phys = CRONUS_ADDR(0x000038)}, .eic_ready_status = {.phys = CRONUS_ADDR(0x00004C)}, diff --git a/arch/mips/powertv/asic/asic-gaia.c b/arch/mips/powertv/asic/asic-gaia.c index 91dda682752c..47683b370e74 100644 --- a/arch/mips/powertv/asic/asic-gaia.c +++ b/arch/mips/powertv/asic/asic-gaia.c @@ -23,7 +23,7 @@ #include <linux/init.h> #include <asm/mach-powertv/asic.h> -const struct register_map gaia_register_map __initdata = { +const struct register_map gaia_register_map __initconst = { .eic_slow0_strt_add = {.phys = GAIA_IO_BASE + 0x000000}, .eic_cfg_bits = {.phys = GAIA_IO_BASE + 0x000038}, .eic_ready_status = {.phys = GAIA_IO_BASE + 0x00004C}, diff --git a/arch/mips/powertv/asic/asic-zeus.c b/arch/mips/powertv/asic/asic-zeus.c index 4a05bb096476..6ff4b10f09da 100644 --- a/arch/mips/powertv/asic/asic-zeus.c +++ b/arch/mips/powertv/asic/asic-zeus.c @@ -28,7 +28,7 @@ #define ZEUS_ADDR(x) (ZEUS_IO_BASE + (x)) -const struct register_map zeus_register_map __initdata = { +const struct register_map zeus_register_map __initconst = { .eic_slow0_strt_add = {.phys = ZEUS_ADDR(0x000000)}, .eic_cfg_bits = {.phys = ZEUS_ADDR(0x000038)}, .eic_ready_status = {.phys = ZEUS_ADDR(0x00004c)}, diff --git a/arch/mips/txx9/generic/pci.c b/arch/mips/txx9/generic/pci.c index 682efb0c108d..64eb71b15280 100644 --- a/arch/mips/txx9/generic/pci.c +++ b/arch/mips/txx9/generic/pci.c @@ -269,7 +269,7 @@ txx9_i8259_irq_setup(int irq) return err; } -static void __init quirk_slc90e66_bridge(struct pci_dev *dev) +static void __devinit quirk_slc90e66_bridge(struct pci_dev *dev) { int irq; /* PCI/ISA Bridge interrupt */ u8 reg_64; diff --git a/arch/mn10300/include/asm/ptrace.h b/arch/mn10300/include/asm/ptrace.h index 55b79ef10028..44251b974f1d 100644 --- a/arch/mn10300/include/asm/ptrace.h +++ b/arch/mn10300/include/asm/ptrace.h @@ -81,9 +81,6 @@ struct pt_regs { #define PTRACE_GETFPREGS 14 #define PTRACE_SETFPREGS 15 -/* options set using PTRACE_SETOPTIONS */ -#define PTRACE_O_TRACESYSGOOD 0x00000001 - #ifdef __KERNEL__ #define user_mode(regs) (((regs)->epsw & EPSW_nSL) == EPSW_nSL) diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h index 08251d6f6b11..ac519bbd42ff 100644 --- a/arch/mn10300/include/asm/thread_info.h +++ b/arch/mn10300/include/asm/thread_info.h @@ -123,7 +123,7 @@ static inline unsigned long current_stack_pointer(void) } #ifndef CONFIG_KGDB -void arch_release_thread_info(struct thread_info *ti) +void arch_release_thread_info(struct thread_info *ti); #endif #define get_thread_info(ti) get_task_struct((ti)->task) #define put_thread_info(ti) put_task_struct((ti)->task) diff --git a/arch/mn10300/include/asm/timex.h b/arch/mn10300/include/asm/timex.h index bd4e90dfe6c2..f8e66425cbf8 100644 --- a/arch/mn10300/include/asm/timex.h +++ b/arch/mn10300/include/asm/timex.h @@ -11,7 +11,6 @@ #ifndef _ASM_TIMEX_H #define _ASM_TIMEX_H -#include <asm/hardirq.h> #include <unit/timex.h> #define TICK_SIZE (tick_nsec / 1000) @@ -30,16 +29,6 @@ static inline cycles_t get_cycles(void) extern int init_clockevents(void); extern int init_clocksource(void); -static inline void setup_jiffies_interrupt(int irq, - struct irqaction *action) -{ - u16 tmp; - setup_irq(irq, action); - set_intr_level(irq, NUM2GxICR_LEVEL(CONFIG_TIMER_IRQ_LEVEL)); - GxICR(irq) |= GxICR_ENABLE | GxICR_DETECT | GxICR_REQUEST; - tmp = GxICR(irq); -} - #endif /* __KERNEL__ */ #endif /* _ASM_TIMEX_H */ diff --git a/arch/mn10300/kernel/cevt-mn10300.c b/arch/mn10300/kernel/cevt-mn10300.c index 69cae0260786..ccce35e3e179 100644 --- a/arch/mn10300/kernel/cevt-mn10300.c +++ b/arch/mn10300/kernel/cevt-mn10300.c @@ -70,6 +70,16 @@ static void event_handler(struct clock_event_device *dev) { } +static inline void setup_jiffies_interrupt(int irq, + struct irqaction *action) +{ + u16 tmp; + setup_irq(irq, action); + set_intr_level(irq, NUM2GxICR_LEVEL(CONFIG_TIMER_IRQ_LEVEL)); + GxICR(irq) |= GxICR_ENABLE | GxICR_DETECT | GxICR_REQUEST; + tmp = GxICR(irq); +} + int __init init_clockevents(void) { struct clock_event_device *cd; diff --git a/arch/mn10300/kernel/internal.h b/arch/mn10300/kernel/internal.h index a5ac755dd69f..2df440105a80 100644 --- a/arch/mn10300/kernel/internal.h +++ b/arch/mn10300/kernel/internal.h @@ -9,6 +9,8 @@ * 2 of the Licence, or (at your option) any later version. */ +#include <linux/irqreturn.h> + struct clocksource; struct clock_event_device; diff --git a/arch/mn10300/kernel/irq.c b/arch/mn10300/kernel/irq.c index 2381df83bd00..35932a8de8b8 100644 --- a/arch/mn10300/kernel/irq.c +++ b/arch/mn10300/kernel/irq.c @@ -170,9 +170,9 @@ mn10300_cpupic_setaffinity(struct irq_data *d, const struct cpumask *mask, case SC1TXIRQ: #ifdef CONFIG_MN10300_TTYSM1_TIMER12 case TM12IRQ: -#elif CONFIG_MN10300_TTYSM1_TIMER9 +#elif defined(CONFIG_MN10300_TTYSM1_TIMER9) case TM9IRQ: -#elif CONFIG_MN10300_TTYSM1_TIMER3 +#elif defined(CONFIG_MN10300_TTYSM1_TIMER3) case TM3IRQ: #endif /* CONFIG_MN10300_TTYSM1_TIMER12 */ #endif /* CONFIG_MN10300_TTYSM1 */ diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c index 6ab0bee2a54f..4d584ae29ae1 100644 --- a/arch/mn10300/kernel/signal.c +++ b/arch/mn10300/kernel/signal.c @@ -459,10 +459,11 @@ static int handle_signal(int sig, else ret = setup_frame(sig, ka, oldset, regs); if (ret) - return; + return ret; signal_delivered(sig, info, ka, regs, - test_thread_flag(TIF_SINGLESTEP)); + test_thread_flag(TIF_SINGLESTEP)); + return 0; } /* diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c index 090d35d36973..e62c223e4c45 100644 --- a/arch/mn10300/kernel/smp.c +++ b/arch/mn10300/kernel/smp.c @@ -876,9 +876,7 @@ static void __init smp_online(void) notify_cpu_starting(cpu); - ipi_call_lock(); set_cpu_online(cpu, true); - ipi_call_unlock(); local_irq_enable(); } diff --git a/arch/mn10300/kernel/traps.c b/arch/mn10300/kernel/traps.c index 94a9c6d53e1b..b900e5afa0ae 100644 --- a/arch/mn10300/kernel/traps.c +++ b/arch/mn10300/kernel/traps.c @@ -26,6 +26,7 @@ #include <linux/kdebug.h> #include <linux/bug.h> #include <linux/irq.h> +#include <linux/export.h> #include <asm/processor.h> #include <linux/uaccess.h> #include <asm/io.h> diff --git a/arch/mn10300/mm/dma-alloc.c b/arch/mn10300/mm/dma-alloc.c index 159acb02cfd4..e244ebe637e1 100644 --- a/arch/mn10300/mm/dma-alloc.c +++ b/arch/mn10300/mm/dma-alloc.c @@ -15,6 +15,7 @@ #include <linux/string.h> #include <linux/pci.h> #include <linux/gfp.h> +#include <linux/export.h> #include <asm/io.h> static unsigned long pci_sram_allocated = 0xbc000000; diff --git a/arch/mn10300/unit-asb2303/include/unit/timex.h b/arch/mn10300/unit-asb2303/include/unit/timex.h index cc18fe7d8b90..c37f9832cf17 100644 --- a/arch/mn10300/unit-asb2303/include/unit/timex.h +++ b/arch/mn10300/unit-asb2303/include/unit/timex.h @@ -11,10 +11,6 @@ #ifndef _ASM_UNIT_TIMEX_H #define _ASM_UNIT_TIMEX_H -#ifndef __ASSEMBLY__ -#include <linux/irq.h> -#endif /* __ASSEMBLY__ */ - #include <asm/timer-regs.h> #include <unit/clock.h> #include <asm/param.h> diff --git a/arch/mn10300/unit-asb2303/smc91111.c b/arch/mn10300/unit-asb2303/smc91111.c index 43c246439413..53677694b165 100644 --- a/arch/mn10300/unit-asb2303/smc91111.c +++ b/arch/mn10300/unit-asb2303/smc91111.c @@ -15,6 +15,7 @@ #include <linux/platform_device.h> #include <asm/io.h> +#include <asm/irq.h> #include <asm/timex.h> #include <asm/processor.h> #include <asm/intctl-regs.h> diff --git a/arch/mn10300/unit-asb2305/include/unit/timex.h b/arch/mn10300/unit-asb2305/include/unit/timex.h index 758af30d1a16..4cefc224f448 100644 --- a/arch/mn10300/unit-asb2305/include/unit/timex.h +++ b/arch/mn10300/unit-asb2305/include/unit/timex.h @@ -11,10 +11,6 @@ #ifndef _ASM_UNIT_TIMEX_H #define _ASM_UNIT_TIMEX_H -#ifndef __ASSEMBLY__ -#include <linux/irq.h> -#endif /* __ASSEMBLY__ */ - #include <asm/timer-regs.h> #include <unit/clock.h> #include <asm/param.h> diff --git a/arch/mn10300/unit-asb2305/unit-init.c b/arch/mn10300/unit-asb2305/unit-init.c index e1becd6b7571..bc4adfaf815c 100644 --- a/arch/mn10300/unit-asb2305/unit-init.c +++ b/arch/mn10300/unit-asb2305/unit-init.c @@ -13,6 +13,7 @@ #include <linux/init.h> #include <linux/pci.h> #include <asm/io.h> +#include <asm/irq.h> #include <asm/setup.h> #include <asm/processor.h> #include <asm/intctl-regs.h> diff --git a/arch/mn10300/unit-asb2364/include/unit/timex.h b/arch/mn10300/unit-asb2364/include/unit/timex.h index ddb7ed010706..42f32db75087 100644 --- a/arch/mn10300/unit-asb2364/include/unit/timex.h +++ b/arch/mn10300/unit-asb2364/include/unit/timex.h @@ -11,10 +11,6 @@ #ifndef _ASM_UNIT_TIMEX_H #define _ASM_UNIT_TIMEX_H -#ifndef __ASSEMBLY__ -#include <linux/irq.h> -#endif /* __ASSEMBLY__ */ - #include <asm/timer-regs.h> #include <unit/clock.h> #include <asm/param.h> diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index a47828d31fe6..6266730efd61 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -300,9 +300,7 @@ smp_cpu_init(int cpunum) notify_cpu_starting(cpunum); - ipi_call_lock(); set_cpu_online(cpunum, true); - ipi_call_unlock(); /* Initialise the idle task for this CPU */ atomic_inc(&init_mm.mm_count); diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 6eb75b80488c..0554ab062bdc 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -86,8 +86,8 @@ static inline bool arch_irqs_disabled(void) } #ifdef CONFIG_PPC_BOOK3E -#define __hard_irq_enable() asm volatile("wrteei 1" : : : "memory"); -#define __hard_irq_disable() asm volatile("wrteei 0" : : : "memory"); +#define __hard_irq_enable() asm volatile("wrteei 1" : : : "memory") +#define __hard_irq_disable() asm volatile("wrteei 0" : : : "memory") #else #define __hard_irq_enable() __mtmsrd(local_paca->kernel_msr | MSR_EE, 1) #define __hard_irq_disable() __mtmsrd(local_paca->kernel_msr, 1) @@ -125,6 +125,8 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs) return !regs->softe; } +extern bool prep_irq_for_idle(void); + #else /* CONFIG_PPC64 */ #define SET_MSR_EE(x) mtmsr(x) diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 1b415027ec0e..1f017bb7a7ce 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -229,7 +229,7 @@ notrace void arch_local_irq_restore(unsigned long en) */ if (unlikely(irq_happened != PACA_IRQ_HARD_DIS)) __hard_irq_disable(); -#ifdef CONFIG_TRACE_IRQFLAG +#ifdef CONFIG_TRACE_IRQFLAGS else { /* * We should already be hard disabled here. We had bugs @@ -286,6 +286,52 @@ void notrace restore_interrupts(void) __hard_irq_enable(); } +/* + * This is a helper to use when about to go into idle low-power + * when the latter has the side effect of re-enabling interrupts + * (such as calling H_CEDE under pHyp). + * + * You call this function with interrupts soft-disabled (this is + * already the case when ppc_md.power_save is called). The function + * will return whether to enter power save or just return. + * + * In the former case, it will have notified lockdep of interrupts + * being re-enabled and generally sanitized the lazy irq state, + * and in the latter case it will leave with interrupts hard + * disabled and marked as such, so the local_irq_enable() call + * in cpu_idle() will properly re-enable everything. + */ +bool prep_irq_for_idle(void) +{ + /* + * First we need to hard disable to ensure no interrupt + * occurs before we effectively enter the low power state + */ + hard_irq_disable(); + + /* + * If anything happened while we were soft-disabled, + * we return now and do not enter the low power state. + */ + if (lazy_irq_pending()) + return false; + + /* Tell lockdep we are about to re-enable */ + trace_hardirqs_on(); + + /* + * Mark interrupts as soft-enabled and clear the + * PACA_IRQ_HARD_DIS from the pending mask since we + * are about to hard enable as well as a side effect + * of entering the low power state. + */ + local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; + local_paca->soft_enabled = 1; + + /* Tell the caller to enter the low power state */ + return true; +} + #endif /* CONFIG_PPC64 */ int arch_show_interrupts(struct seq_file *p, int prec) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index e4cb34322de4..e1417c42155c 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -571,7 +571,6 @@ void __devinit start_secondary(void *unused) if (system_state == SYSTEM_RUNNING) vdso_data->processorCount++; #endif - ipi_call_lock(); notify_cpu_starting(cpu); set_cpu_online(cpu, true); /* Update sibling maps */ @@ -601,7 +600,6 @@ void __devinit start_secondary(void *unused) of_node_put(np); } of_node_put(l2_cache); - ipi_call_unlock(); local_irq_enable(); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index a84aafce2a12..a1044f43becd 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -810,7 +810,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201) lwz r3,VCORE_NAPPING_THREADS(r5) lwz r4,VCPU_PTID(r9) li r0,1 - sldi r0,r0,r4 + sld r0,r0,r4 andc. r3,r3,r0 /* no sense IPI'ing ourselves */ beq 43f mulli r4,r4,PACA_SIZE /* get paca for thread 0 */ diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index 3ff9013d6e79..ee02b30878ed 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -241,6 +241,7 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) case H_PUT_TCE: return kvmppc_h_pr_put_tce(vcpu); case H_CEDE: + vcpu->arch.shared->msr |= MSR_EE; kvm_vcpu_block(vcpu); clear_bit(KVM_REQ_UNHALT, &vcpu->requests); vcpu->stat.halt_wakeup++; diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 6e8f677f5646..1e95556dc692 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -639,7 +639,7 @@ static void __init parse_drconf_memory(struct device_node *memory) unsigned int n, rc, ranges, is_kexec_kdump = 0; unsigned long lmb_size, base, size, sz; int nid; - struct assoc_arrays aa; + struct assoc_arrays aa = { .arrays = NULL }; n = of_get_drconf_memory(memory, &dm); if (!n) diff --git a/arch/powerpc/platforms/cell/pervasive.c b/arch/powerpc/platforms/cell/pervasive.c index efdacc829576..d17e98bc0c10 100644 --- a/arch/powerpc/platforms/cell/pervasive.c +++ b/arch/powerpc/platforms/cell/pervasive.c @@ -42,11 +42,9 @@ static void cbe_power_save(void) { unsigned long ctrl, thread_switch_control; - /* - * We need to hard disable interrupts, the local_irq_enable() done by - * our caller upon return will hard re-enable. - */ - hard_irq_disable(); + /* Ensure our interrupt state is properly tracked */ + if (!prep_irq_for_idle()) + return; ctrl = mfspr(SPRN_CTRLF); @@ -81,6 +79,9 @@ static void cbe_power_save(void) */ ctrl &= ~(CTRL_RUNLATCH | CTRL_TE); mtspr(SPRN_CTRLT, ctrl); + + /* Re-enable interrupts in MSR */ + __hard_irq_enable(); } static int cbe_system_reset_exception(struct pt_regs *regs) diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 66519d263da7..d544d7816df3 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -317,28 +317,23 @@ out: return ret; } -static int spufs_context_open(struct dentry *dentry, struct vfsmount *mnt) +static int spufs_context_open(struct path *path) { int ret; struct file *filp; ret = get_unused_fd(); - if (ret < 0) { - dput(dentry); - mntput(mnt); - goto out; - } + if (ret < 0) + return ret; - filp = dentry_open(dentry, mnt, O_RDONLY, current_cred()); + filp = dentry_open(path, O_RDONLY, current_cred()); if (IS_ERR(filp)) { put_unused_fd(ret); - ret = PTR_ERR(filp); - goto out; + return PTR_ERR(filp); } filp->f_op = &spufs_context_fops; fd_install(ret, filp); -out: return ret; } @@ -453,6 +448,7 @@ spufs_create_context(struct inode *inode, struct dentry *dentry, int affinity; struct spu_gang *gang; struct spu_context *neighbor; + struct path path = {.mnt = mnt, .dentry = dentry}; ret = -EPERM; if ((flags & SPU_CREATE_NOSCHED) && @@ -495,11 +491,7 @@ spufs_create_context(struct inode *inode, struct dentry *dentry, put_spu_context(neighbor); } - /* - * get references for dget and mntget, will be released - * in error path of *_open(). - */ - ret = spufs_context_open(dget(dentry), mntget(mnt)); + ret = spufs_context_open(&path); if (ret < 0) { WARN_ON(spufs_rmdir(inode, dentry)); if (affinity) @@ -556,28 +548,27 @@ out: return ret; } -static int spufs_gang_open(struct dentry *dentry, struct vfsmount *mnt) +static int spufs_gang_open(struct path *path) { int ret; struct file *filp; ret = get_unused_fd(); - if (ret < 0) { - dput(dentry); - mntput(mnt); - goto out; - } + if (ret < 0) + return ret; - filp = dentry_open(dentry, mnt, O_RDONLY, current_cred()); + /* + * get references for dget and mntget, will be released + * in error path of *_open(). + */ + filp = dentry_open(path, O_RDONLY, current_cred()); if (IS_ERR(filp)) { put_unused_fd(ret); - ret = PTR_ERR(filp); - goto out; + return PTR_ERR(filp); } filp->f_op = &simple_dir_operations; fd_install(ret, filp); -out: return ret; } @@ -585,17 +576,14 @@ static int spufs_create_gang(struct inode *inode, struct dentry *dentry, struct vfsmount *mnt, umode_t mode) { + struct path path = {.mnt = mnt, .dentry = dentry}; int ret; ret = spufs_mkgang(inode, dentry, mode & S_IRWXUGO); if (ret) goto out; - /* - * get references for dget and mntget, will be released - * in error path of *_open(). - */ - ret = spufs_gang_open(dget(dentry), mntget(mnt)); + ret = spufs_gang_open(&path); if (ret < 0) { int err = simple_rmdir(inode, dentry); WARN_ON(err); diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c index e61483e8e960..c71be66bd5dc 100644 --- a/arch/powerpc/platforms/pseries/processor_idle.c +++ b/arch/powerpc/platforms/pseries/processor_idle.c @@ -99,15 +99,18 @@ out: static void check_and_cede_processor(void) { /* - * Interrupts are soft-disabled at this point, - * but not hard disabled. So an interrupt might have - * occurred before entering NAP, and would be potentially - * lost (edge events, decrementer events, etc...) unless - * we first hard disable then check. + * Ensure our interrupt state is properly tracked, + * also checks if no interrupt has occurred while we + * were soft-disabled */ - hard_irq_disable(); - if (!lazy_irq_pending()) + if (prep_irq_for_idle()) { cede_processor(); +#ifdef CONFIG_TRACE_IRQFLAGS + /* Ensure that H_CEDE returns with IRQs on */ + if (WARN_ON(!(mfmsr() & MSR_EE))) + __hard_irq_enable(); +#endif + } } static int dedicated_cede_loop(struct cpuidle_device *dev, diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 0f3ab06d2222..eab3492a45c5 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -971,7 +971,7 @@ static int cpu_cmd(void) /* print cpus waiting or in xmon */ printf("cpus stopped:"); count = 0; - for (cpu = 0; cpu < NR_CPUS; ++cpu) { + for_each_possible_cpu(cpu) { if (cpumask_test_cpu(cpu, &cpus_in_xmon)) { if (count == 0) printf(" %x", cpu); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 15cca26ccb6c..8dca9c248ac7 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -717,9 +717,7 @@ static void __cpuinit smp_start_secondary(void *cpuvoid) init_cpu_vtimer(); pfault_init(); notify_cpu_starting(smp_processor_id()); - ipi_call_lock(); set_cpu_online(smp_processor_id(), true); - ipi_call_unlock(); local_irq_enable(); /* cpu_idle will call schedule for us */ cpu_idle(); diff --git a/arch/sh/include/asm/io_noioport.h b/arch/sh/include/asm/io_noioport.h index e136d28d1d2e..4d48f1436a63 100644 --- a/arch/sh/include/asm/io_noioport.h +++ b/arch/sh/include/asm/io_noioport.h @@ -19,9 +19,20 @@ static inline u32 inl(unsigned long addr) return -1; } -#define outb(x, y) BUG() -#define outw(x, y) BUG() -#define outl(x, y) BUG() +static inline void outb(unsigned char x, unsigned long port) +{ + BUG(); +} + +static inline void outw(unsigned short x, unsigned long port) +{ + BUG(); +} + +static inline void outl(unsigned int x, unsigned long port) +{ + BUG(); +} #define inb_p(addr) inb(addr) #define inw_p(addr) inw(addr) diff --git a/arch/sh/kernel/cpu/sh3/serial-sh7720.c b/arch/sh/kernel/cpu/sh3/serial-sh7720.c index 8832c526cdf9..c4a0336660dd 100644 --- a/arch/sh/kernel/cpu/sh3/serial-sh7720.c +++ b/arch/sh/kernel/cpu/sh3/serial-sh7720.c @@ -2,7 +2,7 @@ #include <linux/serial_core.h> #include <linux/io.h> #include <cpu/serial.h> -#include <asm/gpio.h> +#include <cpu/gpio.h> static void sh7720_sci_init_pins(struct uart_port *port, unsigned int cflag) { diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index f591598d92f6..781bcb10b8bd 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -103,8 +103,6 @@ void __cpuinit smp_callin(void) if (cheetah_pcache_forced_on) cheetah_enable_pcache(); - local_irq_enable(); - callin_flag = 1; __asm__ __volatile__("membar #Sync\n\t" "flush %%g6" : : : "memory"); @@ -124,9 +122,8 @@ void __cpuinit smp_callin(void) while (!cpumask_test_cpu(cpuid, &smp_commenced_mask)) rmb(); - ipi_call_lock_irq(); set_cpu_online(cpuid, true); - ipi_call_unlock_irq(); + local_irq_enable(); /* idle thread is expected to have preempt disabled */ preempt_disable(); @@ -1308,9 +1305,7 @@ int __cpu_disable(void) mdelay(1); local_irq_disable(); - ipi_call_lock(); set_cpu_online(cpu, false); - ipi_call_unlock(); cpu_map_rebuild(); diff --git a/arch/tile/kernel/backtrace.c b/arch/tile/kernel/backtrace.c index 9092ce8aa6b4..f8b74ca83b92 100644 --- a/arch/tile/kernel/backtrace.c +++ b/arch/tile/kernel/backtrace.c @@ -14,6 +14,7 @@ #include <linux/kernel.h> #include <linux/string.h> +#include <asm/byteorder.h> #include <asm/backtrace.h> #include <asm/tile-desc.h> #include <arch/abi.h> @@ -336,8 +337,12 @@ static void find_caller_pc_and_caller_sp(CallerLocation *location, bytes_to_prefetch / sizeof(tile_bundle_bits); } - /* Decode the next bundle. */ - bundle.bits = prefetched_bundles[next_bundle++]; + /* + * Decode the next bundle. + * TILE always stores instruction bundles in little-endian + * mode, even when the chip is running in big-endian mode. + */ + bundle.bits = le64_to_cpu(prefetched_bundles[next_bundle++]); bundle.num_insns = parse_insn_tile(bundle.bits, pc, bundle.insns); num_info_ops = bt_get_info_ops(&bundle, info_operands); diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c index 84873fbe8f27..e686c5ac90be 100644 --- a/arch/tile/kernel/smpboot.c +++ b/arch/tile/kernel/smpboot.c @@ -198,17 +198,7 @@ void __cpuinit online_secondary(void) notify_cpu_starting(smp_processor_id()); - /* - * We need to hold call_lock, so there is no inconsistency - * between the time smp_call_function() determines number of - * IPI recipients, and the time when the determination is made - * for which cpus receive the IPI. Holding this - * lock helps us to not include this cpu in a currently in progress - * smp_call_function(). - */ - ipi_call_lock(); set_cpu_online(smp_processor_id(), 1); - ipi_call_unlock(); __get_cpu_var(cpu_state) = CPU_ONLINE; /* Set up tile-specific state for this cpu. */ diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 88e466b159dc..43b39d61b538 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -705,7 +705,6 @@ static void stack_proc(void *arg) struct task_struct *from = current, *to = arg; to->thread.saved_task = from; - rcu_switch_from(from); switch_to(from, to, from); } diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 1f2521434554..b0c5276861ec 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -49,6 +49,9 @@ else KBUILD_AFLAGS += -m64 KBUILD_CFLAGS += -m64 + # Use -mpreferred-stack-boundary=3 if supported. + KBUILD_CFLAGS += $(call cc-option,-mno-sse -mpreferred-stack-boundary=3) + # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu) cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8) cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 49331bedc158..70780689599a 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -75,23 +75,54 @@ static inline int alternatives_text_reserved(void *start, void *end) } #endif /* CONFIG_SMP */ +#define OLDINSTR(oldinstr) "661:\n\t" oldinstr "\n662:\n" + +#define b_replacement(number) "663"#number +#define e_replacement(number) "664"#number + +#define alt_slen "662b-661b" +#define alt_rlen(number) e_replacement(number)"f-"b_replacement(number)"f" + +#define ALTINSTR_ENTRY(feature, number) \ + " .long 661b - .\n" /* label */ \ + " .long " b_replacement(number)"f - .\n" /* new instruction */ \ + " .word " __stringify(feature) "\n" /* feature bit */ \ + " .byte " alt_slen "\n" /* source len */ \ + " .byte " alt_rlen(number) "\n" /* replacement len */ + +#define DISCARD_ENTRY(number) /* rlen <= slen */ \ + " .byte 0xff + (" alt_rlen(number) ") - (" alt_slen ")\n" + +#define ALTINSTR_REPLACEMENT(newinstr, feature, number) /* replacement */ \ + b_replacement(number)":\n\t" newinstr "\n" e_replacement(number) ":\n\t" + /* alternative assembly primitive: */ #define ALTERNATIVE(oldinstr, newinstr, feature) \ - \ - "661:\n\t" oldinstr "\n662:\n" \ - ".section .altinstructions,\"a\"\n" \ - " .long 661b - .\n" /* label */ \ - " .long 663f - .\n" /* new instruction */ \ - " .word " __stringify(feature) "\n" /* feature bit */ \ - " .byte 662b-661b\n" /* sourcelen */ \ - " .byte 664f-663f\n" /* replacementlen */ \ - ".previous\n" \ - ".section .discard,\"aw\",@progbits\n" \ - " .byte 0xff + (664f-663f) - (662b-661b)\n" /* rlen <= slen */ \ - ".previous\n" \ - ".section .altinstr_replacement, \"ax\"\n" \ - "663:\n\t" newinstr "\n664:\n" /* replacement */ \ - ".previous" + OLDINSTR(oldinstr) \ + ".section .altinstructions,\"a\"\n" \ + ALTINSTR_ENTRY(feature, 1) \ + ".previous\n" \ + ".section .discard,\"aw\",@progbits\n" \ + DISCARD_ENTRY(1) \ + ".previous\n" \ + ".section .altinstr_replacement, \"ax\"\n" \ + ALTINSTR_REPLACEMENT(newinstr, feature, 1) \ + ".previous" + +#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\ + OLDINSTR(oldinstr) \ + ".section .altinstructions,\"a\"\n" \ + ALTINSTR_ENTRY(feature1, 1) \ + ALTINSTR_ENTRY(feature2, 2) \ + ".previous\n" \ + ".section .discard,\"aw\",@progbits\n" \ + DISCARD_ENTRY(1) \ + DISCARD_ENTRY(2) \ + ".previous\n" \ + ".section .altinstr_replacement, \"ax\"\n" \ + ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \ + ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \ + ".previous" /* * This must be included *after* the definition of ALTERNATIVE due to @@ -140,6 +171,19 @@ static inline int alternatives_text_reserved(void *start, void *end) : output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input) /* + * Like alternative_call, but there are two features and respective functions. + * If CPU has feature2, function2 is used. + * Otherwise, if CPU has feature1, function1 is used. + * Otherwise, old function is used. + */ +#define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \ + output, input...) \ + asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\ + "call %P[new2]", feature2) \ + : output : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ + [new2] "i" (newfunc2), ## input) + +/* * use this macro(s) if you need more than one output parameter * in alternative_io */ diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 49ad773f4b9f..b3341e9cd8fd 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -26,10 +26,31 @@ struct amd_l3_cache { u8 subcaches[4]; }; +struct threshold_block { + unsigned int block; + unsigned int bank; + unsigned int cpu; + u32 address; + u16 interrupt_enable; + bool interrupt_capable; + u16 threshold_limit; + struct kobject kobj; + struct list_head miscj; +}; + +struct threshold_bank { + struct kobject *kobj; + struct threshold_block *blocks; + + /* initialized to the number of CPUs on the node sharing this bank */ + atomic_t cpus; +}; + struct amd_northbridge { struct pci_dev *misc; struct pci_dev *link; struct amd_l3_cache l3_cache; + struct threshold_bank *bank4; }; struct amd_northbridge_info { diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index eaff4790ed96..88093c1d44fd 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -306,7 +306,8 @@ struct apic { unsigned long (*check_apicid_used)(physid_mask_t *map, int apicid); unsigned long (*check_apicid_present)(int apicid); - void (*vector_allocation_domain)(int cpu, struct cpumask *retmask); + void (*vector_allocation_domain)(int cpu, struct cpumask *retmask, + const struct cpumask *mask); void (*init_apic_ldr)(void); void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap); @@ -331,9 +332,9 @@ struct apic { unsigned long (*set_apic_id)(unsigned int id); unsigned long apic_id_mask; - unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask); - unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask, - const struct cpumask *andmask); + int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask, + const struct cpumask *andmask, + unsigned int *apicid); /* ipi */ void (*send_IPI_mask)(const struct cpumask *mask, int vector); @@ -537,6 +538,11 @@ static inline const struct cpumask *default_target_cpus(void) #endif } +static inline const struct cpumask *online_target_cpus(void) +{ + return cpu_online_mask; +} + DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid); @@ -586,21 +592,50 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb) #endif -static inline unsigned int -default_cpu_mask_to_apicid(const struct cpumask *cpumask) +static inline int +flat_cpu_mask_to_apicid_and(const struct cpumask *cpumask, + const struct cpumask *andmask, + unsigned int *apicid) { - return cpumask_bits(cpumask)[0] & APIC_ALL_CPUS; + unsigned long cpu_mask = cpumask_bits(cpumask)[0] & + cpumask_bits(andmask)[0] & + cpumask_bits(cpu_online_mask)[0] & + APIC_ALL_CPUS; + + if (likely(cpu_mask)) { + *apicid = (unsigned int)cpu_mask; + return 0; + } else { + return -EINVAL; + } } -static inline unsigned int +extern int default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) + const struct cpumask *andmask, + unsigned int *apicid); + +static inline void +flat_vector_allocation_domain(int cpu, struct cpumask *retmask, + const struct cpumask *mask) { - unsigned long mask1 = cpumask_bits(cpumask)[0]; - unsigned long mask2 = cpumask_bits(andmask)[0]; - unsigned long mask3 = cpumask_bits(cpu_online_mask)[0]; + /* Careful. Some cpus do not strictly honor the set of cpus + * specified in the interrupt destination when using lowest + * priority interrupt delivery mode. + * + * In particular there was a hyperthreading cpu observed to + * deliver interrupts to the wrong hyperthread when only one + * hyperthread was specified in the interrupt desitination. + */ + cpumask_clear(retmask); + cpumask_bits(retmask)[0] = APIC_ALL_CPUS; +} - return (unsigned int)(mask1 & mask2 & mask3); +static inline void +default_vector_allocation_domain(int cpu, struct cpumask *retmask, + const struct cpumask *mask) +{ + cpumask_copy(retmask, cpumask_of(cpu)); } static inline unsigned long default_check_apicid_used(physid_mask_t *map, int apicid) diff --git a/arch/x86/include/asm/emergency-restart.h b/arch/x86/include/asm/emergency-restart.h index cc70c1c78ca4..75ce3f47d204 100644 --- a/arch/x86/include/asm/emergency-restart.h +++ b/arch/x86/include/asm/emergency-restart.h @@ -4,9 +4,7 @@ enum reboot_type { BOOT_TRIPLE = 't', BOOT_KBD = 'k', -#ifdef CONFIG_X86_32 BOOT_BIOS = 'b', -#endif BOOT_ACPI = 'a', BOOT_EFI = 'e', BOOT_CF9 = 'p', diff --git a/arch/x86/include/asm/floppy.h b/arch/x86/include/asm/floppy.h index dbe82a5c5eac..d3d74698dce9 100644 --- a/arch/x86/include/asm/floppy.h +++ b/arch/x86/include/asm/floppy.h @@ -99,7 +99,7 @@ static irqreturn_t floppy_hardint(int irq, void *dev_id) virtual_dma_residue += virtual_dma_count; virtual_dma_count = 0; #ifdef TRACE_FLPY_INT - printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n", + printk(KERN_DEBUG "count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n", virtual_dma_count, virtual_dma_residue, calls, bytes, dma_wait); calls = 0; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index db7c1f2709a2..2da88c0cda14 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -313,8 +313,8 @@ struct kvm_pmu { u64 counter_bitmask[2]; u64 global_ctrl_mask; u8 version; - struct kvm_pmc gp_counters[X86_PMC_MAX_GENERIC]; - struct kvm_pmc fixed_counters[X86_PMC_MAX_FIXED]; + struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC]; + struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED]; struct irq_work irq_work; u64 reprogram_pmi; }; diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 084ef95274cd..813ed103f45e 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -115,8 +115,8 @@ notrace static inline int native_write_msr_safe(unsigned int msr, extern unsigned long long native_read_tsc(void); -extern int native_rdmsr_safe_regs(u32 regs[8]); -extern int native_wrmsr_safe_regs(u32 regs[8]); +extern int rdmsr_safe_regs(u32 regs[8]); +extern int wrmsr_safe_regs(u32 regs[8]); static __always_inline unsigned long long __native_read_tsc(void) { @@ -187,43 +187,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) return err; } -static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) -{ - u32 gprs[8] = { 0 }; - int err; - - gprs[1] = msr; - gprs[7] = 0x9c5a203a; - - err = native_rdmsr_safe_regs(gprs); - - *p = gprs[0] | ((u64)gprs[2] << 32); - - return err; -} - -static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val) -{ - u32 gprs[8] = { 0 }; - - gprs[0] = (u32)val; - gprs[1] = msr; - gprs[2] = val >> 32; - gprs[7] = 0x9c5a203a; - - return native_wrmsr_safe_regs(gprs); -} - -static inline int rdmsr_safe_regs(u32 regs[8]) -{ - return native_rdmsr_safe_regs(regs); -} - -static inline int wrmsr_safe_regs(u32 regs[8]) -{ - return native_wrmsr_safe_regs(regs); -} - #define rdtscl(low) \ ((low) = (u32)__native_read_tsc()) @@ -237,6 +200,8 @@ do { \ (high) = (u32)(_l >> 32); \ } while (0) +#define rdpmcl(counter, val) ((val) = native_read_pmc(counter)) + #define rdtscp(low, high, aux) \ do { \ unsigned long long _val = native_read_tscp(&(aux)); \ @@ -248,8 +213,7 @@ do { \ #endif /* !CONFIG_PARAVIRT */ - -#define checking_wrmsrl(msr, val) wrmsr_safe((msr), (u32)(val), \ +#define wrmsrl_safe(msr, val) wrmsr_safe((msr), (u32)(val), \ (u32)((val) >> 32)) #define write_tsc(val1, val2) wrmsr(MSR_IA32_TSC, (val1), (val2)) diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index dc580c42851c..c0fa356e90de 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -44,28 +44,14 @@ struct nmiaction { const char *name; }; -#define register_nmi_handler(t, fn, fg, n) \ +#define register_nmi_handler(t, fn, fg, n, init...) \ ({ \ - static struct nmiaction fn##_na = { \ + static struct nmiaction init fn##_na = { \ .handler = (fn), \ .name = (n), \ .flags = (fg), \ }; \ - __register_nmi_handler((t), &fn##_na); \ -}) - -/* - * For special handlers that register/unregister in the - * init section only. This should be considered rare. - */ -#define register_nmi_handler_initonly(t, fn, fg, n) \ -({ \ - static struct nmiaction fn##_na __initdata = { \ - .handler = (fn), \ - .name = (n), \ - .flags = (fg), \ - }; \ - __register_nmi_handler((t), &fn##_na); \ + __register_nmi_handler((t), &fn##_na); \ }) int __register_nmi_handler(unsigned int, struct nmiaction *); diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 6cbbabf52707..0b47ddb6f00b 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -128,21 +128,11 @@ static inline u64 paravirt_read_msr(unsigned msr, int *err) return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err); } -static inline int paravirt_rdmsr_regs(u32 *regs) -{ - return PVOP_CALL1(int, pv_cpu_ops.rdmsr_regs, regs); -} - static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high) { return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high); } -static inline int paravirt_wrmsr_regs(u32 *regs) -{ - return PVOP_CALL1(int, pv_cpu_ops.wrmsr_regs, regs); -} - /* These should all do BUG_ON(_err), but our headers are too tangled. */ #define rdmsr(msr, val1, val2) \ do { \ @@ -176,9 +166,6 @@ do { \ _err; \ }) -#define rdmsr_safe_regs(regs) paravirt_rdmsr_regs(regs) -#define wrmsr_safe_regs(regs) paravirt_wrmsr_regs(regs) - static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) { int err; @@ -186,32 +173,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) *p = paravirt_read_msr(msr, &err); return err; } -static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) -{ - u32 gprs[8] = { 0 }; - int err; - - gprs[1] = msr; - gprs[7] = 0x9c5a203a; - - err = paravirt_rdmsr_regs(gprs); - - *p = gprs[0] | ((u64)gprs[2] << 32); - - return err; -} - -static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val) -{ - u32 gprs[8] = { 0 }; - - gprs[0] = (u32)val; - gprs[1] = msr; - gprs[2] = val >> 32; - gprs[7] = 0x9c5a203a; - - return paravirt_wrmsr_regs(gprs); -} static inline u64 paravirt_read_tsc(void) { @@ -252,6 +213,8 @@ do { \ high = _l >> 32; \ } while (0) +#define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter)) + static inline unsigned long long paravirt_rdtscp(unsigned int *aux) { return PVOP_CALL1(u64, pv_cpu_ops.read_tscp, aux); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 8e8b9a4987ee..8613cbb7ba41 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -153,9 +153,7 @@ struct pv_cpu_ops { /* MSR, PMC and TSR operations. err = 0/-EFAULT. wrmsr returns 0/-EFAULT. */ u64 (*read_msr)(unsigned int msr, int *err); - int (*rdmsr_regs)(u32 *regs); int (*write_msr)(unsigned int msr, unsigned low, unsigned high); - int (*wrmsr_regs)(u32 *regs); u64 (*read_tsc)(void); u64 (*read_pmc)(int counter); diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index b3a531746026..5ad24a89b19b 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -7,9 +7,13 @@ #undef DEBUG #ifdef DEBUG -#define DBG(x...) printk(x) +#define DBG(fmt, ...) printk(fmt, ##__VA_ARGS__) #else -#define DBG(x...) +#define DBG(fmt, ...) \ +do { \ + if (0) \ + printk(fmt, ##__VA_ARGS__); \ +} while (0) #endif #define PCI_PROBE_BIOS 0x0001 diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 588f52ea810e..c78f14a0df00 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -5,11 +5,10 @@ * Performance event hw details: */ -#define X86_PMC_MAX_GENERIC 32 -#define X86_PMC_MAX_FIXED 3 +#define INTEL_PMC_MAX_GENERIC 32 +#define INTEL_PMC_MAX_FIXED 3 +#define INTEL_PMC_IDX_FIXED 32 -#define X86_PMC_IDX_GENERIC 0 -#define X86_PMC_IDX_FIXED 32 #define X86_PMC_IDX_MAX 64 #define MSR_ARCH_PERFMON_PERFCTR0 0xc1 @@ -48,8 +47,7 @@ (X86_RAW_EVENT_MASK | \ AMD64_EVENTSEL_EVENT) #define AMD64_NUM_COUNTERS 4 -#define AMD64_NUM_COUNTERS_F15H 6 -#define AMD64_NUM_COUNTERS_MAX AMD64_NUM_COUNTERS_F15H +#define AMD64_NUM_COUNTERS_CORE 6 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8) @@ -121,16 +119,16 @@ struct x86_pmu_capability { /* Instr_Retired.Any: */ #define MSR_ARCH_PERFMON_FIXED_CTR0 0x309 -#define X86_PMC_IDX_FIXED_INSTRUCTIONS (X86_PMC_IDX_FIXED + 0) +#define INTEL_PMC_IDX_FIXED_INSTRUCTIONS (INTEL_PMC_IDX_FIXED + 0) /* CPU_CLK_Unhalted.Core: */ #define MSR_ARCH_PERFMON_FIXED_CTR1 0x30a -#define X86_PMC_IDX_FIXED_CPU_CYCLES (X86_PMC_IDX_FIXED + 1) +#define INTEL_PMC_IDX_FIXED_CPU_CYCLES (INTEL_PMC_IDX_FIXED + 1) /* CPU_CLK_Unhalted.Ref: */ #define MSR_ARCH_PERFMON_FIXED_CTR2 0x30b -#define X86_PMC_IDX_FIXED_REF_CYCLES (X86_PMC_IDX_FIXED + 2) -#define X86_PMC_MSK_FIXED_REF_CYCLES (1ULL << X86_PMC_IDX_FIXED_REF_CYCLES) +#define INTEL_PMC_IDX_FIXED_REF_CYCLES (INTEL_PMC_IDX_FIXED + 2) +#define INTEL_PMC_MSK_FIXED_REF_CYCLES (1ULL << INTEL_PMC_IDX_FIXED_REF_CYCLES) /* * We model BTS tracing as another fixed-mode PMC. @@ -139,7 +137,7 @@ struct x86_pmu_capability { * values are used by actual fixed events and higher values are used * to indicate other overflow conditions in the PERF_GLOBAL_STATUS msr. */ -#define X86_PMC_IDX_FIXED_BTS (X86_PMC_IDX_FIXED + 16) +#define INTEL_PMC_IDX_FIXED_BTS (INTEL_PMC_IDX_FIXED + 16) /* * IBS cpuid feature detection @@ -234,6 +232,7 @@ struct perf_guest_switch_msr { extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr); extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap); +extern void perf_check_microcode(void); #else static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr) { @@ -247,6 +246,7 @@ static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap) } static inline void perf_events_lapic_init(void) { } +static inline void perf_check_microcode(void) { } #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index 98391db840c6..f2b489cf1602 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -2,9 +2,9 @@ #define _ASM_X86_PGTABLE_2LEVEL_H #define pte_ERROR(e) \ - printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low) + pr_err("%s:%d: bad pte %08lx\n", __FILE__, __LINE__, (e).pte_low) #define pgd_ERROR(e) \ - printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) + pr_err("%s:%d: bad pgd %08lx\n", __FILE__, __LINE__, pgd_val(e)) /* * Certain architectures need to do special things when PTEs diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index cb00ccc7d571..4cc9f2b7cdc3 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -9,13 +9,13 @@ */ #define pte_ERROR(e) \ - printk("%s:%d: bad pte %p(%08lx%08lx).\n", \ + pr_err("%s:%d: bad pte %p(%08lx%08lx)\n", \ __FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low) #define pmd_ERROR(e) \ - printk("%s:%d: bad pmd %p(%016Lx).\n", \ + pr_err("%s:%d: bad pmd %p(%016Lx)\n", \ __FILE__, __LINE__, &(e), pmd_val(e)) #define pgd_ERROR(e) \ - printk("%s:%d: bad pgd %p(%016Lx).\n", \ + pr_err("%s:%d: bad pgd %p(%016Lx)\n", \ __FILE__, __LINE__, &(e), pgd_val(e)) /* Rules for using set_pte: the pte being assigned *must* be diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 975f709e09ae..8251be02301e 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -26,16 +26,16 @@ extern pgd_t init_level4_pgt[]; extern void paging_init(void); #define pte_ERROR(e) \ - printk("%s:%d: bad pte %p(%016lx).\n", \ + pr_err("%s:%d: bad pte %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pte_val(e)) #define pmd_ERROR(e) \ - printk("%s:%d: bad pmd %p(%016lx).\n", \ + pr_err("%s:%d: bad pmd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pmd_val(e)) #define pud_ERROR(e) \ - printk("%s:%d: bad pud %p(%016lx).\n", \ + pr_err("%s:%d: bad pud %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pud_val(e)) #define pgd_ERROR(e) \ - printk("%s:%d: bad pgd %p(%016lx).\n", \ + pr_err("%s:%d: bad pgd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pgd_val(e)) struct mm_struct; diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index fce3f4ae5bd6..fe1ec5bcd846 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -21,8 +21,9 @@ struct real_mode_header { u32 wakeup_header; #endif /* APM/BIOS reboot */ -#ifdef CONFIG_X86_32 u32 machine_real_restart_asm; +#ifdef CONFIG_X86_64 + u32 machine_real_restart_seg; #endif }; diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index 92f297069e87..a82c4f1b4d83 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -18,8 +18,8 @@ extern struct machine_ops machine_ops; void native_machine_crash_shutdown(struct pt_regs *regs); void native_machine_shutdown(void); -void machine_real_restart(unsigned int type); -/* These must match dispatch_table in reboot_32.S */ +void __noreturn machine_real_restart(unsigned int type); +/* These must match dispatch in arch/x86/realmore/rm/reboot.S */ #define MRR_BIOS 0 #define MRR_APM 1 diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index f48394513c37..2ffa95dc2333 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -169,11 +169,6 @@ void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle); void smp_store_cpu_info(int id); #define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu) -/* We don't mark CPUs online until __cpu_up(), so we need another measure */ -static inline int num_booting_cpus(void) -{ - return cpumask_weight(cpu_callout_mask); -} #else /* !CONFIG_SMP */ #define wbinvd_on_cpu(cpu) wbinvd() static inline int wbinvd_on_all_cpus(void) diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 8e796fbbf9c6..d8def8b3dba0 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -17,6 +17,8 @@ /* Handles exceptions in both to and from, but doesn't do access_ok */ __must_check unsigned long +copy_user_enhanced_fast_string(void *to, const void *from, unsigned len); +__must_check unsigned long copy_user_generic_string(void *to, const void *from, unsigned len); __must_check unsigned long copy_user_generic_unrolled(void *to, const void *from, unsigned len); @@ -26,9 +28,16 @@ copy_user_generic(void *to, const void *from, unsigned len) { unsigned ret; - alternative_call(copy_user_generic_unrolled, + /* + * If CPU has ERMS feature, use copy_user_enhanced_fast_string. + * Otherwise, if CPU has rep_good feature, use copy_user_generic_string. + * Otherwise, use copy_user_generic_unrolled. + */ + alternative_call_2(copy_user_generic_unrolled, copy_user_generic_string, X86_FEATURE_REP_GOOD, + copy_user_enhanced_fast_string, + X86_FEATURE_ERMS, ASM_OUTPUT2("=a" (ret), "=D" (to), "=S" (from), "=d" (len)), "1" (to), "2" (from), "3" (len) diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h index 1e9bed14f7ae..f3971bbcd1de 100644 --- a/arch/x86/include/asm/uprobes.h +++ b/arch/x86/include/asm/uprobes.h @@ -48,7 +48,7 @@ struct arch_uprobe_task { #endif }; -extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm); +extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr); extern int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs); extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs); extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk); diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index 6149b476d9df..a06983cdc125 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -140,6 +140,9 @@ #define IPI_RESET_LIMIT 1 /* after this # consecutive successes, bump up the throttle if it was lowered */ #define COMPLETE_THRESHOLD 5 +/* after this # of giveups (fall back to kernel IPI's) disable the use of + the BAU for a period of time */ +#define GIVEUP_LIMIT 100 #define UV_LB_SUBNODEID 0x10 @@ -166,7 +169,6 @@ #define FLUSH_RETRY_TIMEOUT 2 #define FLUSH_GIVEUP 3 #define FLUSH_COMPLETE 4 -#define FLUSH_RETRY_BUSYBUG 5 /* * tuning the action when the numalink network is extremely delayed @@ -175,7 +177,7 @@ microseconds */ #define CONGESTED_REPS 10 /* long delays averaged over this many broadcasts */ -#define CONGESTED_PERIOD 30 /* time for the bau to be +#define DISABLED_PERIOD 10 /* time for the bau to be disabled, in seconds */ /* see msg_type: */ #define MSG_NOOP 0 @@ -520,6 +522,12 @@ struct ptc_stats { unsigned long s_uv2_wars; /* uv2 workaround, perm. busy */ unsigned long s_uv2_wars_hw; /* uv2 workaround, hiwater */ unsigned long s_uv2_war_waits; /* uv2 workaround, long waits */ + unsigned long s_overipilimit; /* over the ipi reset limit */ + unsigned long s_giveuplimit; /* disables, over giveup limit*/ + unsigned long s_enters; /* entries to the driver */ + unsigned long s_ipifordisabled; /* fall back to IPI; disabled */ + unsigned long s_plugged; /* plugged by h/w bug*/ + unsigned long s_congested; /* giveup on long wait */ /* destination statistics */ unsigned long d_alltlb; /* times all tlb's on this cpu were flushed */ @@ -586,8 +594,8 @@ struct bau_control { int timeout_tries; int ipi_attempts; int conseccompletes; - int baudisabled; - int set_bau_off; + short nobau; + short baudisabled; short cpu; short osnode; short uvhub_cpu; @@ -596,14 +604,16 @@ struct bau_control { short cpus_in_socket; short cpus_in_uvhub; short partition_base_pnode; - short using_desc; /* an index, like uvhub_cpu */ - unsigned int inuse_map; + short busy; /* all were busy (war) */ unsigned short message_number; unsigned short uvhub_quiesce; short socket_acknowledge_count[DEST_Q_SIZE]; cycles_t send_message; + cycles_t period_end; + cycles_t period_time; spinlock_t uvhub_lock; spinlock_t queue_lock; + spinlock_t disable_lock; /* tunables */ int max_concurr; int max_concurr_const; @@ -614,9 +624,9 @@ struct bau_control { int complete_threshold; int cong_response_us; int cong_reps; - int cong_period; - unsigned long clocks_per_100_usec; - cycles_t period_time; + cycles_t disabled_period; + int period_giveups; + int giveup_limit; long period_requests; struct hub_and_pnode *thp; }; diff --git a/arch/x86/include/asm/x2apic.h b/arch/x86/include/asm/x2apic.h index 92e54abf89e0..f90f0a587c66 100644 --- a/arch/x86/include/asm/x2apic.h +++ b/arch/x86/include/asm/x2apic.h @@ -9,15 +9,6 @@ #include <asm/ipi.h> #include <linux/cpumask.h> -/* - * Need to use more than cpu 0, because we need more vectors - * when MSI-X are used. - */ -static const struct cpumask *x2apic_target_cpus(void) -{ - return cpu_online_mask; -} - static int x2apic_apic_id_valid(int apicid) { return 1; @@ -28,15 +19,6 @@ static int x2apic_apic_id_registered(void) return 1; } -/* - * For now each logical cpu is in its own vector allocation domain. - */ -static void x2apic_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - cpumask_clear(retmask); - cpumask_set_cpu(cpu, retmask); -} - static void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest) { diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index c090af10ac7d..38155f667144 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -156,7 +156,6 @@ struct x86_cpuinit_ops { /** * struct x86_platform_ops - platform specific runtime functions * @calibrate_tsc: calibrate TSC - * @wallclock_init: init the wallclock device * @get_wallclock: get time from HW clock like RTC etc. * @set_wallclock: set time back to HW clock * @is_untracked_pat_range exclude from PAT logic @@ -164,10 +163,10 @@ struct x86_cpuinit_ops { * @i8042_detect pre-detect if i8042 controller exists * @save_sched_clock_state: save state for sched_clock() on suspend * @restore_sched_clock_state: restore state for sched_clock() on resume + * @apic_post_init: adjust apic if neeeded */ struct x86_platform_ops { unsigned long (*calibrate_tsc)(void); - void (*wallclock_init)(void); unsigned long (*get_wallclock)(void); int (*set_wallclock)(unsigned long nowtime); void (*iommu_shutdown)(void); @@ -177,6 +176,7 @@ struct x86_platform_ops { int (*i8042_detect)(void); void (*save_sched_clock_state)(void); void (*restore_sched_clock_state)(void); + void (*apic_post_init)(void); }; struct pci_dev; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 1f84794f0759..931280ff8299 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1,3 +1,5 @@ +#define pr_fmt(fmt) "SMP alternatives: " fmt + #include <linux/module.h> #include <linux/sched.h> #include <linux/mutex.h> @@ -63,8 +65,11 @@ static int __init setup_noreplace_paravirt(char *str) __setup("noreplace-paravirt", setup_noreplace_paravirt); #endif -#define DPRINTK(fmt, args...) if (debug_alternative) \ - printk(KERN_DEBUG fmt, args) +#define DPRINTK(fmt, ...) \ +do { \ + if (debug_alternative) \ + printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ +} while (0) /* * Each GENERIC_NOPX is of X bytes, and defined as an array of bytes @@ -428,7 +433,7 @@ void alternatives_smp_switch(int smp) * If this still occurs then you should see a hang * or crash shortly after this line: */ - printk("lockdep: fixing up alternatives.\n"); + pr_info("lockdep: fixing up alternatives\n"); #endif if (noreplace_smp || smp_alt_once || skip_smp_alternatives) @@ -444,14 +449,14 @@ void alternatives_smp_switch(int smp) if (smp == smp_mode) { /* nothing */ } else if (smp) { - printk(KERN_INFO "SMP alternatives: switching to SMP code\n"); + pr_info("switching to SMP code\n"); clear_cpu_cap(&boot_cpu_data, X86_FEATURE_UP); clear_cpu_cap(&cpu_data(0), X86_FEATURE_UP); list_for_each_entry(mod, &smp_alt_modules, next) alternatives_smp_lock(mod->locks, mod->locks_end, mod->text, mod->text_end); } else { - printk(KERN_INFO "SMP alternatives: switching to UP code\n"); + pr_info("switching to UP code\n"); set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP); set_cpu_cap(&cpu_data(0), X86_FEATURE_UP); list_for_each_entry(mod, &smp_alt_modules, next) @@ -546,7 +551,7 @@ void __init alternative_instructions(void) #ifdef CONFIG_SMP if (smp_alt_once) { if (1 == num_possible_cpus()) { - printk(KERN_INFO "SMP alternatives: switching to UP code\n"); + pr_info("switching to UP code\n"); set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP); set_cpu_cap(&cpu_data(0), X86_FEATURE_UP); @@ -664,7 +669,7 @@ static int __kprobes stop_machine_text_poke(void *data) struct text_poke_param *p; int i; - if (atomic_dec_and_test(&stop_machine_first)) { + if (atomic_xchg(&stop_machine_first, 0)) { for (i = 0; i < tpp->nparams; i++) { p = &tpp->params[i]; text_poke(p->addr, p->opcode, p->len); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index be16854591cc..aadf3359e2a7 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -2,6 +2,9 @@ * Shared support code for AMD K8 northbridges and derivates. * Copyright 2006 Andi Kleen, SUSE Labs. Subject to GPLv2. */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/types.h> #include <linux/slab.h> #include <linux/init.h> @@ -16,6 +19,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) }, {} }; EXPORT_SYMBOL(amd_nb_misc_ids); @@ -258,7 +262,7 @@ void amd_flush_garts(void) } spin_unlock_irqrestore(&gart_lock, flags); if (!flushed) - printk("nothing to flush?\n"); + pr_notice("nothing to flush?\n"); } EXPORT_SYMBOL_GPL(amd_flush_garts); @@ -269,11 +273,10 @@ static __init int init_amd_nbs(void) err = amd_cache_northbridges(); if (err < 0) - printk(KERN_NOTICE "AMD NB: Cannot enumerate AMD northbridges.\n"); + pr_notice("Cannot enumerate AMD northbridges\n"); if (amd_cache_gart() < 0) - printk(KERN_NOTICE "AMD NB: Cannot initialize GART flush words, " - "GART support disabled.\n"); + pr_notice("Cannot initialize GART flush words, GART support disabled\n"); return err; } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 39a222e094af..c421512ca5eb 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2123,6 +2123,25 @@ void default_init_apic_ldr(void) apic_write(APIC_LDR, val); } +int default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, + const struct cpumask *andmask, + unsigned int *apicid) +{ + unsigned int cpu; + + for_each_cpu_and(cpu, cpumask, andmask) { + if (cpumask_test_cpu(cpu, cpu_online_mask)) + break; + } + + if (likely(cpu < nr_cpu_ids)) { + *apicid = per_cpu(x86_cpu_to_apicid, cpu); + return 0; + } + + return -EINVAL; +} + /* * Power management */ diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 0e881c46e8c8..00c77cf78e9e 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -36,25 +36,6 @@ static int flat_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return 1; } -static const struct cpumask *flat_target_cpus(void) -{ - return cpu_online_mask; -} - -static void flat_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - /* Careful. Some cpus do not strictly honor the set of cpus - * specified in the interrupt destination when using lowest - * priority interrupt delivery mode. - * - * In particular there was a hyperthreading cpu observed to - * deliver interrupts to the wrong hyperthread when only one - * hyperthread was specified in the interrupt desitination. - */ - cpumask_clear(retmask); - cpumask_bits(retmask)[0] = APIC_ALL_CPUS; -} - /* * Set up the logical destination ID. * @@ -92,7 +73,7 @@ static void flat_send_IPI_mask(const struct cpumask *cpumask, int vector) } static void - flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) +flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) { unsigned long mask = cpumask_bits(cpumask)[0]; int cpu = smp_processor_id(); @@ -186,7 +167,7 @@ static struct apic apic_flat = { .irq_delivery_mode = dest_LowestPrio, .irq_dest_mode = 1, /* logical */ - .target_cpus = flat_target_cpus, + .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = NULL, @@ -210,8 +191,7 @@ static struct apic apic_flat = { .set_apic_id = set_apic_id, .apic_id_mask = 0xFFu << 24, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, .send_IPI_mask = flat_send_IPI_mask, .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself, @@ -262,17 +242,6 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return 0; } -static const struct cpumask *physflat_target_cpus(void) -{ - return cpu_online_mask; -} - -static void physflat_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - cpumask_clear(retmask); - cpumask_set_cpu(cpu, retmask); -} - static void physflat_send_IPI_mask(const struct cpumask *cpumask, int vector) { default_send_IPI_mask_sequence_phys(cpumask, vector); @@ -294,38 +263,6 @@ static void physflat_send_IPI_all(int vector) physflat_send_IPI_mask(cpu_online_mask, vector); } -static unsigned int physflat_cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - int cpu; - - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - cpu = cpumask_first(cpumask); - if ((unsigned)cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_apicid, cpu); - else - return BAD_APICID; -} - -static unsigned int -physflat_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - int cpu; - - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - for_each_cpu_and(cpu, cpumask, andmask) { - if (cpumask_test_cpu(cpu, cpu_online_mask)) - break; - } - return per_cpu(x86_cpu_to_apicid, cpu); -} - static int physflat_probe(void) { if (apic == &apic_physflat || num_possible_cpus() > 8) @@ -345,13 +282,13 @@ static struct apic apic_physflat = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = physflat_target_cpus, + .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, .check_apicid_present = NULL, - .vector_allocation_domain = physflat_vector_allocation_domain, + .vector_allocation_domain = default_vector_allocation_domain, /* not needed, but shouldn't hurt: */ .init_apic_ldr = flat_init_apic_ldr, @@ -370,8 +307,7 @@ static struct apic apic_physflat = { .set_apic_id = set_apic_id, .apic_id_mask = 0xFFu << 24, - .cpu_mask_to_apicid = physflat_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = physflat_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, .send_IPI_mask = physflat_send_IPI_mask, .send_IPI_mask_allbutself = physflat_send_IPI_mask_allbutself, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index a6e4c6e06c08..e145f28b4099 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -100,12 +100,12 @@ static unsigned long noop_check_apicid_present(int bit) return physid_isset(bit, phys_cpu_present_map); } -static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask) +static void noop_vector_allocation_domain(int cpu, struct cpumask *retmask, + const struct cpumask *mask) { if (cpu != 0) pr_warning("APIC: Vector allocated for non-BSP cpu\n"); - cpumask_clear(retmask); - cpumask_set_cpu(cpu, retmask); + cpumask_copy(retmask, cpumask_of(cpu)); } static u32 noop_apic_read(u32 reg) @@ -159,8 +159,7 @@ struct apic apic_noop = { .set_apic_id = NULL, .apic_id_mask = 0x0F << 24, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, .send_IPI_mask = noop_send_IPI_mask, .send_IPI_mask_allbutself = noop_send_IPI_mask_allbutself, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 6ec6d5d297c3..bc552cff2578 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -72,17 +72,6 @@ static int numachip_phys_pkg_id(int initial_apic_id, int index_msb) return initial_apic_id >> index_msb; } -static const struct cpumask *numachip_target_cpus(void) -{ - return cpu_online_mask; -} - -static void numachip_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - cpumask_clear(retmask); - cpumask_set_cpu(cpu, retmask); -} - static int __cpuinit numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip) { union numachip_csr_g3_ext_irq_gen int_gen; @@ -157,38 +146,6 @@ static void numachip_send_IPI_self(int vector) __default_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL); } -static unsigned int numachip_cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - int cpu; - - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - cpu = cpumask_first(cpumask); - if (likely((unsigned)cpu < nr_cpu_ids)) - return per_cpu(x86_cpu_to_apicid, cpu); - - return BAD_APICID; -} - -static unsigned int -numachip_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - int cpu; - - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - for_each_cpu_and(cpu, cpumask, andmask) { - if (cpumask_test_cpu(cpu, cpu_online_mask)) - break; - } - return per_cpu(x86_cpu_to_apicid, cpu); -} - static int __init numachip_probe(void) { return apic == &apic_numachip; @@ -253,13 +210,13 @@ static struct apic apic_numachip __refconst = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = numachip_target_cpus, + .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, .check_apicid_present = NULL, - .vector_allocation_domain = numachip_vector_allocation_domain, + .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = flat_init_apic_ldr, .ioapic_phys_id_map = NULL, @@ -277,8 +234,7 @@ static struct apic apic_numachip __refconst = { .set_apic_id = set_apic_id, .apic_id_mask = 0xffU << 24, - .cpu_mask_to_apicid = numachip_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = numachip_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, .send_IPI_mask = numachip_send_IPI_mask, .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 31fbdbfbf960..d50e3640d5ae 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -26,15 +26,6 @@ static int bigsmp_apic_id_registered(void) return 1; } -static const struct cpumask *bigsmp_target_cpus(void) -{ -#ifdef CONFIG_SMP - return cpu_online_mask; -#else - return cpumask_of(0); -#endif -} - static unsigned long bigsmp_check_apicid_used(physid_mask_t *map, int apicid) { return 0; @@ -105,32 +96,6 @@ static int bigsmp_check_phys_apicid_present(int phys_apicid) return 1; } -/* As we are using single CPU as destination, pick only one CPU here */ -static unsigned int bigsmp_cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - int cpu = cpumask_first(cpumask); - - if (cpu < nr_cpu_ids) - return cpu_physical_id(cpu); - return BAD_APICID; -} - -static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - int cpu; - - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - for_each_cpu_and(cpu, cpumask, andmask) { - if (cpumask_test_cpu(cpu, cpu_online_mask)) - return cpu_physical_id(cpu); - } - return BAD_APICID; -} - static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) { return cpuid_apic >> index_msb; @@ -177,12 +142,6 @@ static const struct dmi_system_id bigsmp_dmi_table[] = { { } /* NULL entry stops DMI scanning */ }; -static void bigsmp_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - cpumask_clear(retmask); - cpumask_set_cpu(cpu, retmask); -} - static int probe_bigsmp(void) { if (def_to_bigsmp) @@ -205,13 +164,13 @@ static struct apic apic_bigsmp = { /* phys delivery to target CPU: */ .irq_dest_mode = 0, - .target_cpus = bigsmp_target_cpus, + .target_cpus = default_target_cpus, .disable_esr = 1, .dest_logical = 0, .check_apicid_used = bigsmp_check_apicid_used, .check_apicid_present = bigsmp_check_apicid_present, - .vector_allocation_domain = bigsmp_vector_allocation_domain, + .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = bigsmp_init_apic_ldr, .ioapic_phys_id_map = bigsmp_ioapic_phys_id_map, @@ -229,8 +188,7 @@ static struct apic apic_bigsmp = { .set_apic_id = NULL, .apic_id_mask = 0xFF << 24, - .cpu_mask_to_apicid = bigsmp_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = bigsmp_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, .send_IPI_mask = bigsmp_send_IPI_mask, .send_IPI_mask_allbutself = NULL, diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index db4ab1be3c79..0874799a98c6 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -394,21 +394,6 @@ static void es7000_enable_apic_mode(void) WARN(1, "Command failed, status = %x\n", mip_status); } -static void es7000_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - /* Careful. Some cpus do not strictly honor the set of cpus - * specified in the interrupt destination when using lowest - * priority interrupt delivery mode. - * - * In particular there was a hyperthreading cpu observed to - * deliver interrupts to the wrong hyperthread when only one - * hyperthread was specified in the interrupt desitination. - */ - cpumask_clear(retmask); - cpumask_bits(retmask)[0] = APIC_ALL_CPUS; -} - - static void es7000_wait_for_init_deassert(atomic_t *deassert) { while (!atomic_read(deassert)) @@ -540,45 +525,49 @@ static int es7000_check_phys_apicid_present(int cpu_physical_apicid) return 1; } -static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask) +static inline int +es7000_cpu_mask_to_apicid(const struct cpumask *cpumask, unsigned int *dest_id) { unsigned int round = 0; - int cpu, uninitialized_var(apicid); + unsigned int cpu, uninitialized_var(apicid); /* * The cpus in the mask must all be on the apic cluster. */ - for_each_cpu(cpu, cpumask) { + for_each_cpu_and(cpu, cpumask, cpu_online_mask) { int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { WARN(1, "Not a valid mask!"); - return BAD_APICID; + return -EINVAL; } - apicid = new_apicid; + apicid |= new_apicid; round++; } - return apicid; + if (!round) + return -EINVAL; + *dest_id = apicid; + return 0; } -static unsigned int +static int es7000_cpu_mask_to_apicid_and(const struct cpumask *inmask, - const struct cpumask *andmask) + const struct cpumask *andmask, + unsigned int *apicid) { - int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0); cpumask_var_t cpumask; + *apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0); if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC)) - return apicid; + return 0; cpumask_and(cpumask, inmask, andmask); - cpumask_and(cpumask, cpumask, cpu_online_mask); - apicid = es7000_cpu_mask_to_apicid(cpumask); + es7000_cpu_mask_to_apicid(cpumask, apicid); free_cpumask_var(cpumask); - return apicid; + return 0; } static int es7000_phys_pkg_id(int cpuid_apic, int index_msb) @@ -638,7 +627,7 @@ static struct apic __refdata apic_es7000_cluster = { .check_apicid_used = es7000_check_apicid_used, .check_apicid_present = es7000_check_apicid_present, - .vector_allocation_domain = es7000_vector_allocation_domain, + .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = es7000_init_apic_ldr_cluster, .ioapic_phys_id_map = es7000_ioapic_phys_id_map, @@ -656,7 +645,6 @@ static struct apic __refdata apic_es7000_cluster = { .set_apic_id = NULL, .apic_id_mask = 0xFF << 24, - .cpu_mask_to_apicid = es7000_cpu_mask_to_apicid, .cpu_mask_to_apicid_and = es7000_cpu_mask_to_apicid_and, .send_IPI_mask = es7000_send_IPI_mask, @@ -705,7 +693,7 @@ static struct apic __refdata apic_es7000 = { .check_apicid_used = es7000_check_apicid_used, .check_apicid_present = es7000_check_apicid_present, - .vector_allocation_domain = es7000_vector_allocation_domain, + .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = es7000_init_apic_ldr, .ioapic_phys_id_map = es7000_ioapic_phys_id_map, @@ -723,7 +711,6 @@ static struct apic __refdata apic_es7000 = { .set_apic_id = NULL, .apic_id_mask = 0xFF << 24, - .cpu_mask_to_apicid = es7000_cpu_mask_to_apicid, .cpu_mask_to_apicid_and = es7000_cpu_mask_to_apicid_and, .send_IPI_mask = es7000_send_IPI_mask, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 5f0ff597437c..406eee784684 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -448,8 +448,8 @@ static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pi entry = alloc_irq_pin_list(node); if (!entry) { - printk(KERN_ERR "can not alloc irq_pin_list (%d,%d,%d)\n", - node, apic, pin); + pr_err("can not alloc irq_pin_list (%d,%d,%d)\n", + node, apic, pin); return -ENOMEM; } entry->apic = apic; @@ -661,7 +661,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) ioapic_mask_entry(apic, pin); entry = ioapic_read_entry(apic, pin); if (entry.irr) - printk(KERN_ERR "Unable to reset IRR for apic: %d, pin :%d\n", + pr_err("Unable to reset IRR for apic: %d, pin :%d\n", mpc_ioapic_id(apic), pin); } @@ -895,7 +895,7 @@ static int irq_polarity(int idx) } case 2: /* reserved */ { - printk(KERN_WARNING "broken BIOS!!\n"); + pr_warn("broken BIOS!!\n"); polarity = 1; break; } @@ -906,7 +906,7 @@ static int irq_polarity(int idx) } default: /* invalid */ { - printk(KERN_WARNING "broken BIOS!!\n"); + pr_warn("broken BIOS!!\n"); polarity = 1; break; } @@ -948,7 +948,7 @@ static int irq_trigger(int idx) } default: { - printk(KERN_WARNING "broken BIOS!!\n"); + pr_warn("broken BIOS!!\n"); trigger = 1; break; } @@ -962,7 +962,7 @@ static int irq_trigger(int idx) } case 2: /* reserved */ { - printk(KERN_WARNING "broken BIOS!!\n"); + pr_warn("broken BIOS!!\n"); trigger = 1; break; } @@ -973,7 +973,7 @@ static int irq_trigger(int idx) } default: /* invalid */ { - printk(KERN_WARNING "broken BIOS!!\n"); + pr_warn("broken BIOS!!\n"); trigger = 0; break; } @@ -991,7 +991,7 @@ static int pin_2_irq(int idx, int apic, int pin) * Debugging check, we are in big trouble if this message pops up! */ if (mp_irqs[idx].dstirq != pin) - printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n"); + pr_err("broken BIOS or MPTABLE parser, ayiee!!\n"); if (test_bit(bus, mp_bus_not_pci)) { irq = mp_irqs[idx].srcbusirq; @@ -1112,8 +1112,7 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) * 0x80, because int 0x80 is hm, kind of importantish. ;) */ static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; - static int current_offset = VECTOR_OFFSET_START % 8; - unsigned int old_vector; + static int current_offset = VECTOR_OFFSET_START % 16; int cpu, err; cpumask_var_t tmp_mask; @@ -1123,35 +1122,45 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC)) return -ENOMEM; - old_vector = cfg->vector; - if (old_vector) { - cpumask_and(tmp_mask, mask, cpu_online_mask); - cpumask_and(tmp_mask, cfg->domain, tmp_mask); - if (!cpumask_empty(tmp_mask)) { - free_cpumask_var(tmp_mask); - return 0; - } - } - /* Only try and allocate irqs on cpus that are present */ err = -ENOSPC; - for_each_cpu_and(cpu, mask, cpu_online_mask) { - int new_cpu; - int vector, offset; + cpumask_clear(cfg->old_domain); + cpu = cpumask_first_and(mask, cpu_online_mask); + while (cpu < nr_cpu_ids) { + int new_cpu, vector, offset; - apic->vector_allocation_domain(cpu, tmp_mask); + apic->vector_allocation_domain(cpu, tmp_mask, mask); + + if (cpumask_subset(tmp_mask, cfg->domain)) { + err = 0; + if (cpumask_equal(tmp_mask, cfg->domain)) + break; + /* + * New cpumask using the vector is a proper subset of + * the current in use mask. So cleanup the vector + * allocation for the members that are not used anymore. + */ + cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask); + cfg->move_in_progress = 1; + cpumask_and(cfg->domain, cfg->domain, tmp_mask); + break; + } vector = current_vector; offset = current_offset; next: - vector += 8; + vector += 16; if (vector >= first_system_vector) { - /* If out of vectors on large boxen, must share them. */ - offset = (offset + 1) % 8; + offset = (offset + 1) % 16; vector = FIRST_EXTERNAL_VECTOR + offset; } - if (unlikely(current_vector == vector)) + + if (unlikely(current_vector == vector)) { + cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask); + cpumask_andnot(tmp_mask, mask, cfg->old_domain); + cpu = cpumask_first_and(tmp_mask, cpu_online_mask); continue; + } if (test_bit(vector, used_vectors)) goto next; @@ -1162,7 +1171,7 @@ next: /* Found one! */ current_vector = vector; current_offset = offset; - if (old_vector) { + if (cfg->vector) { cfg->move_in_progress = 1; cpumask_copy(cfg->old_domain, cfg->domain); } @@ -1346,18 +1355,18 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, if (!IO_APIC_IRQ(irq)) return; - /* - * For legacy irqs, cfg->domain starts with cpu 0 for legacy - * controllers like 8259. Now that IO-APIC can handle this irq, update - * the cfg->domain. - */ - if (irq < legacy_pic->nr_legacy_irqs && cpumask_test_cpu(0, cfg->domain)) - apic->vector_allocation_domain(0, cfg->domain); if (assign_irq_vector(irq, cfg, apic->target_cpus())) return; - dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus()); + if (apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus(), + &dest)) { + pr_warn("Failed to obtain apicid for ioapic %d, pin %d\n", + mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); + __clear_irq_vector(irq, cfg); + + return; + } apic_printk(APIC_VERBOSE,KERN_DEBUG "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> " @@ -1366,7 +1375,7 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, cfg->vector, irq, attr->trigger, attr->polarity, dest); if (setup_ioapic_entry(irq, &entry, dest, cfg->vector, attr)) { - pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n", + pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n", mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); __clear_irq_vector(irq, cfg); @@ -1469,9 +1478,10 @@ void setup_IO_APIC_irq_extra(u32 gsi) * Set up the timer pin, possibly with the 8259A-master behind. */ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, - unsigned int pin, int vector) + unsigned int pin, int vector) { struct IO_APIC_route_entry entry; + unsigned int dest; if (irq_remapping_enabled) return; @@ -1482,9 +1492,13 @@ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, * We use logical delivery to get the timer IRQ * to the first CPU. */ + if (unlikely(apic->cpu_mask_to_apicid_and(apic->target_cpus(), + apic->target_cpus(), &dest))) + dest = BAD_APICID; + entry.dest_mode = apic->irq_dest_mode; entry.mask = 0; /* don't mask IRQ for edge */ - entry.dest = apic->cpu_mask_to_apicid(apic->target_cpus()); + entry.dest = dest; entry.delivery_mode = apic->irq_delivery_mode; entry.polarity = 0; entry.trigger = 0; @@ -1521,7 +1535,6 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx) reg_03.raw = io_apic_read(ioapic_idx, 3); raw_spin_unlock_irqrestore(&ioapic_lock, flags); - printk("\n"); printk(KERN_DEBUG "IO APIC #%d......\n", mpc_ioapic_id(ioapic_idx)); printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw); printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID); @@ -1578,7 +1591,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx) i, ir_entry->index ); - printk("%1d %1d %1d %1d %1d " + pr_cont("%1d %1d %1d %1d %1d " "%1d %1d %X %02X\n", ir_entry->format, ir_entry->mask, @@ -1598,7 +1611,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx) i, entry.dest ); - printk("%1d %1d %1d %1d %1d " + pr_cont("%1d %1d %1d %1d %1d " "%1d %1d %02X\n", entry.mask, entry.trigger, @@ -1651,8 +1664,8 @@ __apicdebuginit(void) print_IO_APICs(void) continue; printk(KERN_DEBUG "IRQ%d ", irq); for_each_irq_pin(entry, cfg->irq_2_pin) - printk("-> %d:%d", entry->apic, entry->pin); - printk("\n"); + pr_cont("-> %d:%d", entry->apic, entry->pin); + pr_cont("\n"); } printk(KERN_INFO ".................................... done.\n"); @@ -1665,9 +1678,9 @@ __apicdebuginit(void) print_APIC_field(int base) printk(KERN_DEBUG); for (i = 0; i < 8; i++) - printk(KERN_CONT "%08x", apic_read(base + i*0x10)); + pr_cont("%08x", apic_read(base + i*0x10)); - printk(KERN_CONT "\n"); + pr_cont("\n"); } __apicdebuginit(void) print_local_APIC(void *dummy) @@ -1769,7 +1782,7 @@ __apicdebuginit(void) print_local_APIC(void *dummy) printk(KERN_DEBUG "... APIC EILVT%d: %08x\n", i, v); } } - printk("\n"); + pr_cont("\n"); } __apicdebuginit(void) print_local_APICs(int maxcpu) @@ -2065,7 +2078,7 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void) reg_00.raw = io_apic_read(ioapic_idx, 0); raw_spin_unlock_irqrestore(&ioapic_lock, flags); if (reg_00.bits.ID != mpc_ioapic_id(ioapic_idx)) - printk("could not set ID!\n"); + pr_cont("could not set ID!\n"); else apic_printk(APIC_VERBOSE, " ok.\n"); } @@ -2210,71 +2223,6 @@ void send_cleanup_vector(struct irq_cfg *cfg) cfg->move_in_progress = 0; } -static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg) -{ - int apic, pin; - struct irq_pin_list *entry; - u8 vector = cfg->vector; - - for_each_irq_pin(entry, cfg->irq_2_pin) { - unsigned int reg; - - apic = entry->apic; - pin = entry->pin; - /* - * With interrupt-remapping, destination information comes - * from interrupt-remapping table entry. - */ - if (!irq_remapped(cfg)) - io_apic_write(apic, 0x11 + pin*2, dest); - reg = io_apic_read(apic, 0x10 + pin*2); - reg &= ~IO_APIC_REDIR_VECTOR_MASK; - reg |= vector; - io_apic_modify(apic, 0x10 + pin*2, reg); - } -} - -/* - * Either sets data->affinity to a valid value, and returns - * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and - * leaves data->affinity untouched. - */ -int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, - unsigned int *dest_id) -{ - struct irq_cfg *cfg = data->chip_data; - - if (!cpumask_intersects(mask, cpu_online_mask)) - return -1; - - if (assign_irq_vector(data->irq, data->chip_data, mask)) - return -1; - - cpumask_copy(data->affinity, mask); - - *dest_id = apic->cpu_mask_to_apicid_and(mask, cfg->domain); - return 0; -} - -static int -ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, - bool force) -{ - unsigned int dest, irq = data->irq; - unsigned long flags; - int ret; - - raw_spin_lock_irqsave(&ioapic_lock, flags); - ret = __ioapic_set_affinity(data, mask, &dest); - if (!ret) { - /* Only the high 8 bits are valid. */ - dest = SET_APIC_LOGICAL_ID(dest); - __target_IO_APIC_irq(irq, dest, data->chip_data); - } - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - return ret; -} - asmlinkage void smp_irq_move_cleanup_interrupt(void) { unsigned vector, me; @@ -2362,6 +2310,87 @@ void irq_force_complete_move(int irq) static inline void irq_complete_move(struct irq_cfg *cfg) { } #endif +static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg) +{ + int apic, pin; + struct irq_pin_list *entry; + u8 vector = cfg->vector; + + for_each_irq_pin(entry, cfg->irq_2_pin) { + unsigned int reg; + + apic = entry->apic; + pin = entry->pin; + /* + * With interrupt-remapping, destination information comes + * from interrupt-remapping table entry. + */ + if (!irq_remapped(cfg)) + io_apic_write(apic, 0x11 + pin*2, dest); + reg = io_apic_read(apic, 0x10 + pin*2); + reg &= ~IO_APIC_REDIR_VECTOR_MASK; + reg |= vector; + io_apic_modify(apic, 0x10 + pin*2, reg); + } +} + +/* + * Either sets data->affinity to a valid value, and returns + * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and + * leaves data->affinity untouched. + */ +int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, + unsigned int *dest_id) +{ + struct irq_cfg *cfg = data->chip_data; + unsigned int irq = data->irq; + int err; + + if (!config_enabled(CONFIG_SMP)) + return -1; + + if (!cpumask_intersects(mask, cpu_online_mask)) + return -EINVAL; + + err = assign_irq_vector(irq, cfg, mask); + if (err) + return err; + + err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id); + if (err) { + if (assign_irq_vector(irq, cfg, data->affinity)) + pr_err("Failed to recover vector for irq %d\n", irq); + return err; + } + + cpumask_copy(data->affinity, mask); + + return 0; +} + +static int +ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, + bool force) +{ + unsigned int dest, irq = data->irq; + unsigned long flags; + int ret; + + if (!config_enabled(CONFIG_SMP)) + return -1; + + raw_spin_lock_irqsave(&ioapic_lock, flags); + ret = __ioapic_set_affinity(data, mask, &dest); + if (!ret) { + /* Only the high 8 bits are valid. */ + dest = SET_APIC_LOGICAL_ID(dest); + __target_IO_APIC_irq(irq, dest, data->chip_data); + ret = IRQ_SET_MASK_OK_NOCOPY; + } + raw_spin_unlock_irqrestore(&ioapic_lock, flags); + return ret; +} + static void ack_apic_edge(struct irq_data *data) { irq_complete_move(data->chip_data); @@ -2541,9 +2570,7 @@ static void irq_remap_modify_chip_defaults(struct irq_chip *chip) chip->irq_ack = ir_ack_apic_edge; chip->irq_eoi = ir_ack_apic_level; -#ifdef CONFIG_SMP chip->irq_set_affinity = set_remapped_irq_affinity; -#endif } #endif /* CONFIG_IRQ_REMAP */ @@ -2554,9 +2581,7 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_unmask = unmask_ioapic_irq, .irq_ack = ack_apic_edge, .irq_eoi = ack_apic_level, -#ifdef CONFIG_SMP .irq_set_affinity = ioapic_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; @@ -3038,7 +3063,10 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, if (err) return err; - dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus()); + err = apic->cpu_mask_to_apicid_and(cfg->domain, + apic->target_cpus(), &dest); + if (err) + return err; if (irq_remapped(cfg)) { compose_remapped_msi_msg(pdev, irq, dest, msg, hpet_id); @@ -3072,7 +3100,6 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, return err; } -#ifdef CONFIG_SMP static int msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -3092,9 +3119,8 @@ msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) __write_msi_msg(data->msi_desc, &msg); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } -#endif /* CONFIG_SMP */ /* * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, @@ -3105,9 +3131,7 @@ static struct irq_chip msi_chip = { .irq_unmask = unmask_msi_irq, .irq_mask = mask_msi_irq, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = msi_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; @@ -3192,7 +3216,6 @@ void native_teardown_msi_irq(unsigned int irq) } #ifdef CONFIG_DMAR_TABLE -#ifdef CONFIG_SMP static int dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) @@ -3214,19 +3237,15 @@ dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, dmar_msi_write(irq, &msg); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } -#endif /* CONFIG_SMP */ - static struct irq_chip dmar_msi_type = { .name = "DMAR_MSI", .irq_unmask = dmar_msi_unmask, .irq_mask = dmar_msi_mask, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = dmar_msi_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; @@ -3247,7 +3266,6 @@ int arch_setup_dmar_msi(unsigned int irq) #ifdef CONFIG_HPET_TIMER -#ifdef CONFIG_SMP static int hpet_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -3267,19 +3285,15 @@ static int hpet_msi_set_affinity(struct irq_data *data, hpet_msi_write(data->handler_data, &msg); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } -#endif /* CONFIG_SMP */ - static struct irq_chip hpet_msi_type = { .name = "HPET_MSI", .irq_unmask = hpet_msi_unmask, .irq_mask = hpet_msi_mask, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = hpet_msi_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; @@ -3314,8 +3328,6 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id) */ #ifdef CONFIG_HT_IRQ -#ifdef CONFIG_SMP - static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector) { struct ht_irq_msg msg; @@ -3340,25 +3352,23 @@ ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) return -1; target_ht_irq(data->irq, dest, cfg->vector); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } -#endif - static struct irq_chip ht_irq_chip = { .name = "PCI-HT", .irq_mask = mask_ht_irq, .irq_unmask = unmask_ht_irq, .irq_ack = ack_apic_edge, -#ifdef CONFIG_SMP .irq_set_affinity = ht_set_affinity, -#endif .irq_retrigger = ioapic_retrigger_irq, }; int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) { struct irq_cfg *cfg; + struct ht_irq_msg msg; + unsigned dest; int err; if (disable_apic) @@ -3366,36 +3376,37 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) cfg = irq_cfg(irq); err = assign_irq_vector(irq, cfg, apic->target_cpus()); - if (!err) { - struct ht_irq_msg msg; - unsigned dest; + if (err) + return err; + + err = apic->cpu_mask_to_apicid_and(cfg->domain, + apic->target_cpus(), &dest); + if (err) + return err; - dest = apic->cpu_mask_to_apicid_and(cfg->domain, - apic->target_cpus()); + msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest); - msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest); + msg.address_lo = + HT_IRQ_LOW_BASE | + HT_IRQ_LOW_DEST_ID(dest) | + HT_IRQ_LOW_VECTOR(cfg->vector) | + ((apic->irq_dest_mode == 0) ? + HT_IRQ_LOW_DM_PHYSICAL : + HT_IRQ_LOW_DM_LOGICAL) | + HT_IRQ_LOW_RQEOI_EDGE | + ((apic->irq_delivery_mode != dest_LowestPrio) ? + HT_IRQ_LOW_MT_FIXED : + HT_IRQ_LOW_MT_ARBITRATED) | + HT_IRQ_LOW_IRQ_MASKED; - msg.address_lo = - HT_IRQ_LOW_BASE | - HT_IRQ_LOW_DEST_ID(dest) | - HT_IRQ_LOW_VECTOR(cfg->vector) | - ((apic->irq_dest_mode == 0) ? - HT_IRQ_LOW_DM_PHYSICAL : - HT_IRQ_LOW_DM_LOGICAL) | - HT_IRQ_LOW_RQEOI_EDGE | - ((apic->irq_delivery_mode != dest_LowestPrio) ? - HT_IRQ_LOW_MT_FIXED : - HT_IRQ_LOW_MT_ARBITRATED) | - HT_IRQ_LOW_IRQ_MASKED; + write_ht_irq_msg(irq, &msg); - write_ht_irq_msg(irq, &msg); + irq_set_chip_and_handler_name(irq, &ht_irq_chip, + handle_edge_irq, "edge"); - irq_set_chip_and_handler_name(irq, &ht_irq_chip, - handle_edge_irq, "edge"); + dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq); - dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq); - } - return err; + return 0; } #endif /* CONFIG_HT_IRQ */ @@ -3563,7 +3574,8 @@ static int __init io_apic_get_unique_id(int ioapic, int apic_id) /* Sanity check */ if (reg_00.bits.ID != apic_id) { - printk("IOAPIC[%d]: Unable to change apic_id!\n", ioapic); + pr_err("IOAPIC[%d]: Unable to change apic_id!\n", + ioapic); return -1; } } diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index f00a68cca37a..d661ee95cabf 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -406,16 +406,13 @@ static inline int numaq_check_phys_apicid_present(int phys_apicid) * We use physical apicids here, not logical, so just return the default * physical broadcast to stop people from breaking us */ -static unsigned int numaq_cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - return 0x0F; -} - -static inline unsigned int +static int numaq_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) + const struct cpumask *andmask, + unsigned int *apicid) { - return 0x0F; + *apicid = 0x0F; + return 0; } /* No NUMA-Q box has a HT CPU, but it can't hurt to use the default code. */ @@ -441,20 +438,6 @@ static int probe_numaq(void) return found_numaq; } -static void numaq_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - /* Careful. Some cpus do not strictly honor the set of cpus - * specified in the interrupt destination when using lowest - * priority interrupt delivery mode. - * - * In particular there was a hyperthreading cpu observed to - * deliver interrupts to the wrong hyperthread when only one - * hyperthread was specified in the interrupt desitination. - */ - cpumask_clear(retmask); - cpumask_bits(retmask)[0] = APIC_ALL_CPUS; -} - static void numaq_setup_portio_remap(void) { int num_quads = num_online_nodes(); @@ -491,7 +474,7 @@ static struct apic __refdata apic_numaq = { .check_apicid_used = numaq_check_apicid_used, .check_apicid_present = numaq_check_apicid_present, - .vector_allocation_domain = numaq_vector_allocation_domain, + .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = numaq_init_apic_ldr, .ioapic_phys_id_map = numaq_ioapic_phys_id_map, @@ -509,7 +492,6 @@ static struct apic __refdata apic_numaq = { .set_apic_id = NULL, .apic_id_mask = 0x0F << 24, - .cpu_mask_to_apicid = numaq_cpu_mask_to_apicid, .cpu_mask_to_apicid_and = numaq_cpu_mask_to_apicid_and, .send_IPI_mask = numaq_send_IPI_mask, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 1b291da09e60..eb35ef9ee63f 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -66,21 +66,6 @@ static void setup_apic_flat_routing(void) #endif } -static void default_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - /* - * Careful. Some cpus do not strictly honor the set of cpus - * specified in the interrupt destination when using lowest - * priority interrupt delivery mode. - * - * In particular there was a hyperthreading cpu observed to - * deliver interrupts to the wrong hyperthread when only one - * hyperthread was specified in the interrupt desitination. - */ - cpumask_clear(retmask); - cpumask_bits(retmask)[0] = APIC_ALL_CPUS; -} - /* should be called last. */ static int probe_default(void) { @@ -105,7 +90,7 @@ static struct apic apic_default = { .check_apicid_used = default_check_apicid_used, .check_apicid_present = default_check_apicid_present, - .vector_allocation_domain = default_vector_allocation_domain, + .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = default_init_apic_ldr, .ioapic_phys_id_map = default_ioapic_phys_id_map, @@ -123,8 +108,7 @@ static struct apic apic_default = { .set_apic_id = NULL, .apic_id_mask = 0x0F << 24, - .cpu_mask_to_apicid = default_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, .send_IPI_mask = default_send_IPI_mask_logical, .send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_logical, @@ -208,6 +192,9 @@ void __init default_setup_apic_routing(void) if (apic->setup_apic_routing) apic->setup_apic_routing(); + + if (x86_platform.apic_post_init) + x86_platform.apic_post_init(); } void __init generic_apic_probe(void) diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index 3fe986698929..1793dba7a741 100644 --- a/arch/x86/kernel/apic/probe_64.c +++ b/arch/x86/kernel/apic/probe_64.c @@ -23,11 +23,6 @@ #include <asm/ipi.h> #include <asm/setup.h> -static int apicid_phys_pkg_id(int initial_apic_id, int index_msb) -{ - return hard_smp_processor_id() >> index_msb; -} - /* * Check the APIC IDs in bios_cpu_apicid and choose the APIC mode. */ @@ -48,10 +43,8 @@ void __init default_setup_apic_routing(void) } } - if (is_vsmp_box()) { - /* need to update phys_pkg_id */ - apic->phys_pkg_id = apicid_phys_pkg_id; - } + if (x86_platform.apic_post_init) + x86_platform.apic_post_init(); } /* Same for both flat and physical. */ diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index 659897c00755..77c95c0e1bf7 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -26,6 +26,8 @@ * */ +#define pr_fmt(fmt) "summit: %s: " fmt, __func__ + #include <linux/mm.h> #include <linux/init.h> #include <asm/io.h> @@ -235,8 +237,8 @@ static int summit_apic_id_registered(void) static void summit_setup_apic_routing(void) { - printk("Enabling APIC mode: Summit. Using %d I/O APICs\n", - nr_ioapics); + pr_info("Enabling APIC mode: Summit. Using %d I/O APICs\n", + nr_ioapics); } static int summit_cpu_present_to_apicid(int mps_cpu) @@ -263,43 +265,48 @@ static int summit_check_phys_apicid_present(int physical_apicid) return 1; } -static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask) +static inline int +summit_cpu_mask_to_apicid(const struct cpumask *cpumask, unsigned int *dest_id) { unsigned int round = 0; - int cpu, apicid = 0; + unsigned int cpu, apicid = 0; /* * The cpus in the mask must all be on the apic cluster. */ - for_each_cpu(cpu, cpumask) { + for_each_cpu_and(cpu, cpumask, cpu_online_mask) { int new_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); if (round && APIC_CLUSTER(apicid) != APIC_CLUSTER(new_apicid)) { - printk("%s: Not a valid mask!\n", __func__); - return BAD_APICID; + pr_err("Not a valid mask!\n"); + return -EINVAL; } apicid |= new_apicid; round++; } - return apicid; + if (!round) + return -EINVAL; + *dest_id = apicid; + return 0; } -static unsigned int summit_cpu_mask_to_apicid_and(const struct cpumask *inmask, - const struct cpumask *andmask) +static int +summit_cpu_mask_to_apicid_and(const struct cpumask *inmask, + const struct cpumask *andmask, + unsigned int *apicid) { - int apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0); cpumask_var_t cpumask; + *apicid = early_per_cpu(x86_cpu_to_logical_apicid, 0); if (!alloc_cpumask_var(&cpumask, GFP_ATOMIC)) - return apicid; + return 0; cpumask_and(cpumask, inmask, andmask); - cpumask_and(cpumask, cpumask, cpu_online_mask); - apicid = summit_cpu_mask_to_apicid(cpumask); + summit_cpu_mask_to_apicid(cpumask, apicid); free_cpumask_var(cpumask); - return apicid; + return 0; } /* @@ -320,20 +327,6 @@ static int probe_summit(void) return 0; } -static void summit_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - /* Careful. Some cpus do not strictly honor the set of cpus - * specified in the interrupt destination when using lowest - * priority interrupt delivery mode. - * - * In particular there was a hyperthreading cpu observed to - * deliver interrupts to the wrong hyperthread when only one - * hyperthread was specified in the interrupt desitination. - */ - cpumask_clear(retmask); - cpumask_bits(retmask)[0] = APIC_ALL_CPUS; -} - #ifdef CONFIG_X86_SUMMIT_NUMA static struct rio_table_hdr *rio_table_hdr; static struct scal_detail *scal_devs[MAX_NUMNODES]; @@ -355,7 +348,7 @@ static int setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) } } if (i == rio_table_hdr->num_rio_dev) { - printk(KERN_ERR "%s: Couldn't find owner Cyclone for Winnipeg!\n", __func__); + pr_err("Couldn't find owner Cyclone for Winnipeg!\n"); return last_bus; } @@ -366,7 +359,7 @@ static int setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) } } if (i == rio_table_hdr->num_scal_dev) { - printk(KERN_ERR "%s: Couldn't find owner Twister for Cyclone!\n", __func__); + pr_err("Couldn't find owner Twister for Cyclone!\n"); return last_bus; } @@ -396,7 +389,7 @@ static int setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) num_buses = 9; break; default: - printk(KERN_INFO "%s: Unsupported Winnipeg type!\n", __func__); + pr_info("Unsupported Winnipeg type!\n"); return last_bus; } @@ -411,13 +404,15 @@ static int build_detail_arrays(void) int i, scal_detail_size, rio_detail_size; if (rio_table_hdr->num_scal_dev > MAX_NUMNODES) { - printk(KERN_WARNING "%s: MAX_NUMNODES too low! Defined as %d, but system has %d nodes.\n", __func__, MAX_NUMNODES, rio_table_hdr->num_scal_dev); + pr_warn("MAX_NUMNODES too low! Defined as %d, but system has %d nodes\n", + MAX_NUMNODES, rio_table_hdr->num_scal_dev); return 0; } switch (rio_table_hdr->version) { default: - printk(KERN_WARNING "%s: Invalid Rio Grande Table Version: %d\n", __func__, rio_table_hdr->version); + pr_warn("Invalid Rio Grande Table Version: %d\n", + rio_table_hdr->version); return 0; case 2: scal_detail_size = 11; @@ -462,7 +457,7 @@ void setup_summit(void) offset = *((unsigned short *)(ptr + offset)); } if (!rio_table_hdr) { - printk(KERN_ERR "%s: Unable to locate Rio Grande Table in EBDA - bailing!\n", __func__); + pr_err("Unable to locate Rio Grande Table in EBDA - bailing!\n"); return; } @@ -509,7 +504,7 @@ static struct apic apic_summit = { .check_apicid_used = summit_check_apicid_used, .check_apicid_present = summit_check_apicid_present, - .vector_allocation_domain = summit_vector_allocation_domain, + .vector_allocation_domain = flat_vector_allocation_domain, .init_apic_ldr = summit_init_apic_ldr, .ioapic_phys_id_map = summit_ioapic_phys_id_map, @@ -527,7 +522,6 @@ static struct apic apic_summit = { .set_apic_id = NULL, .apic_id_mask = 0xFF << 24, - .cpu_mask_to_apicid = summit_cpu_mask_to_apicid, .cpu_mask_to_apicid_and = summit_cpu_mask_to_apicid_and, .send_IPI_mask = summit_send_IPI_mask, diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index ff35cff0e1a7..c88baa4ff0e5 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -81,7 +81,7 @@ static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector) } static void - x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector) +x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector) { __x2apic_send_IPI_mask(mask, vector, APIC_DEST_ALLBUT); } @@ -96,36 +96,37 @@ static void x2apic_send_IPI_all(int vector) __x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLINC); } -static unsigned int x2apic_cpu_mask_to_apicid(const struct cpumask *cpumask) +static int +x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, + const struct cpumask *andmask, + unsigned int *apicid) { - /* - * We're using fixed IRQ delivery, can only return one logical APIC ID. - * May as well be the first. - */ - int cpu = cpumask_first(cpumask); + u32 dest = 0; + u16 cluster; + int i; - if ((unsigned)cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_logical_apicid, cpu); - else - return BAD_APICID; -} + for_each_cpu_and(i, cpumask, andmask) { + if (!cpumask_test_cpu(i, cpu_online_mask)) + continue; + dest = per_cpu(x86_cpu_to_logical_apicid, i); + cluster = x2apic_cluster(i); + break; + } -static unsigned int -x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - int cpu; + if (!dest) + return -EINVAL; - /* - * We're using fixed IRQ delivery, can only return one logical APIC ID. - * May as well be the first. - */ - for_each_cpu_and(cpu, cpumask, andmask) { - if (cpumask_test_cpu(cpu, cpu_online_mask)) - break; + for_each_cpu_and(i, cpumask, andmask) { + if (!cpumask_test_cpu(i, cpu_online_mask)) + continue; + if (cluster != x2apic_cluster(i)) + continue; + dest |= per_cpu(x86_cpu_to_logical_apicid, i); } - return per_cpu(x86_cpu_to_logical_apicid, cpu); + *apicid = dest; + + return 0; } static void init_x2apic_ldr(void) @@ -208,6 +209,32 @@ static int x2apic_cluster_probe(void) return 0; } +static const struct cpumask *x2apic_cluster_target_cpus(void) +{ + return cpu_all_mask; +} + +/* + * Each x2apic cluster is an allocation domain. + */ +static void cluster_vector_allocation_domain(int cpu, struct cpumask *retmask, + const struct cpumask *mask) +{ + /* + * To minimize vector pressure, default case of boot, device bringup + * etc will use a single cpu for the interrupt destination. + * + * On explicit migration requests coming from irqbalance etc, + * interrupts will be routed to the x2apic cluster (cluster-id + * derived from the first cpu in the mask) members specified + * in the mask. + */ + if (mask == x2apic_cluster_target_cpus()) + cpumask_copy(retmask, cpumask_of(cpu)); + else + cpumask_and(retmask, mask, per_cpu(cpus_in_cluster, cpu)); +} + static struct apic apic_x2apic_cluster = { .name = "cluster x2apic", @@ -219,13 +246,13 @@ static struct apic apic_x2apic_cluster = { .irq_delivery_mode = dest_LowestPrio, .irq_dest_mode = 1, /* logical */ - .target_cpus = x2apic_target_cpus, + .target_cpus = x2apic_cluster_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = NULL, .check_apicid_present = NULL, - .vector_allocation_domain = x2apic_vector_allocation_domain, + .vector_allocation_domain = cluster_vector_allocation_domain, .init_apic_ldr = init_x2apic_ldr, .ioapic_phys_id_map = NULL, @@ -243,7 +270,6 @@ static struct apic apic_x2apic_cluster = { .set_apic_id = x2apic_set_apic_id, .apic_id_mask = 0xFFFFFFFFu, - .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid, .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and, .send_IPI_mask = x2apic_send_IPI_mask, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index c17e982db275..e03a1e180e81 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -76,38 +76,6 @@ static void x2apic_send_IPI_all(int vector) __x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLINC); } -static unsigned int x2apic_cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - int cpu = cpumask_first(cpumask); - - if ((unsigned)cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_apicid, cpu); - else - return BAD_APICID; -} - -static unsigned int -x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - int cpu; - - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - for_each_cpu_and(cpu, cpumask, andmask) { - if (cpumask_test_cpu(cpu, cpu_online_mask)) - break; - } - - return per_cpu(x86_cpu_to_apicid, cpu); -} - static void init_x2apic_ldr(void) { } @@ -131,13 +99,13 @@ static struct apic apic_x2apic_phys = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = x2apic_target_cpus, + .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = 0, .check_apicid_used = NULL, .check_apicid_present = NULL, - .vector_allocation_domain = x2apic_vector_allocation_domain, + .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = init_x2apic_ldr, .ioapic_phys_id_map = NULL, @@ -155,8 +123,7 @@ static struct apic apic_x2apic_phys = { .set_apic_id = x2apic_set_apic_id, .apic_id_mask = 0xFFFFFFFFu, - .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, .send_IPI_mask = x2apic_send_IPI_mask, .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index c6d03f7a4401..8cfade9510a4 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -185,17 +185,6 @@ EXPORT_SYMBOL_GPL(uv_possible_blades); unsigned long sn_rtc_cycles_per_second; EXPORT_SYMBOL(sn_rtc_cycles_per_second); -static const struct cpumask *uv_target_cpus(void) -{ - return cpu_online_mask; -} - -static void uv_vector_allocation_domain(int cpu, struct cpumask *retmask) -{ - cpumask_clear(retmask); - cpumask_set_cpu(cpu, retmask); -} - static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) { #ifdef CONFIG_SMP @@ -280,25 +269,12 @@ static void uv_init_apic_ldr(void) { } -static unsigned int uv_cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - int cpu = cpumask_first(cpumask); - - if ((unsigned)cpu < nr_cpu_ids) - return per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits; - else - return BAD_APICID; -} - -static unsigned int +static int uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) + const struct cpumask *andmask, + unsigned int *apicid) { - int cpu; + int unsigned cpu; /* * We're using fixed IRQ delivery, can only return one phys APIC ID. @@ -308,7 +284,13 @@ uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask, if (cpumask_test_cpu(cpu, cpu_online_mask)) break; } - return per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits; + + if (likely(cpu < nr_cpu_ids)) { + *apicid = per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits; + return 0; + } + + return -EINVAL; } static unsigned int x2apic_get_apic_id(unsigned long x) @@ -362,13 +344,13 @@ static struct apic __refdata apic_x2apic_uv_x = { .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 0, /* physical */ - .target_cpus = uv_target_cpus, + .target_cpus = online_target_cpus, .disable_esr = 0, .dest_logical = APIC_DEST_LOGICAL, .check_apicid_used = NULL, .check_apicid_present = NULL, - .vector_allocation_domain = uv_vector_allocation_domain, + .vector_allocation_domain = default_vector_allocation_domain, .init_apic_ldr = uv_init_apic_ldr, .ioapic_phys_id_map = NULL, @@ -386,7 +368,6 @@ static struct apic __refdata apic_x2apic_uv_x = { .set_apic_id = set_apic_id, .apic_id_mask = 0xFFFFFFFFu, - .cpu_mask_to_apicid = uv_cpu_mask_to_apicid, .cpu_mask_to_apicid_and = uv_cpu_mask_to_apicid_and, .send_IPI_mask = uv_send_IPI_mask, diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 07b0c0db466c..d65464e43503 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -201,6 +201,8 @@ * http://www.microsoft.com/whdc/archive/amp_12.mspx] */ +#define pr_fmt(fmt) "apm: " fmt + #include <linux/module.h> #include <linux/poll.h> @@ -485,11 +487,11 @@ static void apm_error(char *str, int err) if (error_table[i].key == err) break; if (i < ERROR_COUNT) - printk(KERN_NOTICE "apm: %s: %s\n", str, error_table[i].msg); + pr_notice("%s: %s\n", str, error_table[i].msg); else if (err < 0) - printk(KERN_NOTICE "apm: %s: linux error code %i\n", str, err); + pr_notice("%s: linux error code %i\n", str, err); else - printk(KERN_NOTICE "apm: %s: unknown error code %#2.2x\n", + pr_notice("%s: unknown error code %#2.2x\n", str, err); } @@ -1184,7 +1186,7 @@ static void queue_event(apm_event_t event, struct apm_user *sender) static int notified; if (notified++ == 0) - printk(KERN_ERR "apm: an event queue overflowed\n"); + pr_err("an event queue overflowed\n"); if (++as->event_tail >= APM_MAX_EVENTS) as->event_tail = 0; } @@ -1447,7 +1449,7 @@ static void apm_mainloop(void) static int check_apm_user(struct apm_user *as, const char *func) { if (as == NULL || as->magic != APM_BIOS_MAGIC) { - printk(KERN_ERR "apm: %s passed bad filp\n", func); + pr_err("%s passed bad filp\n", func); return 1; } return 0; @@ -1586,7 +1588,7 @@ static int do_release(struct inode *inode, struct file *filp) as1 = as1->next) ; if (as1 == NULL) - printk(KERN_ERR "apm: filp not in user list\n"); + pr_err("filp not in user list\n"); else as1->next = as->next; } @@ -1600,11 +1602,9 @@ static int do_open(struct inode *inode, struct file *filp) struct apm_user *as; as = kmalloc(sizeof(*as), GFP_KERNEL); - if (as == NULL) { - printk(KERN_ERR "apm: cannot allocate struct of size %d bytes\n", - sizeof(*as)); + if (as == NULL) return -ENOMEM; - } + as->magic = APM_BIOS_MAGIC; as->event_tail = as->event_head = 0; as->suspends_pending = as->standbys_pending = 0; @@ -2313,16 +2313,16 @@ static int __init apm_init(void) } if (apm_info.disabled) { - printk(KERN_NOTICE "apm: disabled on user request.\n"); + pr_notice("disabled on user request.\n"); return -ENODEV; } if ((num_online_cpus() > 1) && !power_off && !smp) { - printk(KERN_NOTICE "apm: disabled - APM is not SMP safe.\n"); + pr_notice("disabled - APM is not SMP safe.\n"); apm_info.disabled = 1; return -ENODEV; } if (!acpi_disabled) { - printk(KERN_NOTICE "apm: overridden by ACPI.\n"); + pr_notice("overridden by ACPI.\n"); apm_info.disabled = 1; return -ENODEV; } @@ -2356,8 +2356,7 @@ static int __init apm_init(void) kapmd_task = kthread_create(apm, NULL, "kapmd"); if (IS_ERR(kapmd_task)) { - printk(KERN_ERR "apm: disabled - Unable to start kernel " - "thread.\n"); + pr_err("disabled - Unable to start kernel thread\n"); err = PTR_ERR(kapmd_task); kapmd_task = NULL; remove_proc_entry("apm", NULL); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 6ab6aa2fdfdd..bac4c3804cc7 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -32,7 +32,9 @@ obj-$(CONFIG_PERF_EVENTS) += perf_event.o ifdef CONFIG_PERF_EVENTS obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_p4.o perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_p4.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o endif obj-$(CONFIG_X86_MCE) += mcheck/ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 146bb6218eec..9d92e19039f0 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -19,6 +19,39 @@ #include "cpu.h" +static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) +{ + struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + u32 gprs[8] = { 0 }; + int err; + + WARN_ONCE((c->x86 != 0xf), "%s should only be used on K8!\n", __func__); + + gprs[1] = msr; + gprs[7] = 0x9c5a203a; + + err = rdmsr_safe_regs(gprs); + + *p = gprs[0] | ((u64)gprs[2] << 32); + + return err; +} + +static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val) +{ + struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + u32 gprs[8] = { 0 }; + + WARN_ONCE((c->x86 != 0xf), "%s should only be used on K8!\n", __func__); + + gprs[0] = (u32)val; + gprs[1] = msr; + gprs[2] = val >> 32; + gprs[7] = 0x9c5a203a; + + return wrmsr_safe_regs(gprs); +} + #ifdef CONFIG_X86_32 /* * B step AMD K6 before B 9730xxxx have hardware bugs that can cause @@ -586,9 +619,9 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) !cpu_has(c, X86_FEATURE_TOPOEXT)) { u64 val; - if (!rdmsrl_amd_safe(0xc0011005, &val)) { + if (!rdmsrl_safe(0xc0011005, &val)) { val |= 1ULL << 54; - wrmsrl_amd_safe(0xc0011005, val); + wrmsrl_safe(0xc0011005, val); rdmsrl(0xc0011005, val); if (val & (1ULL << 54)) { set_cpu_cap(c, X86_FEATURE_TOPOEXT); @@ -679,7 +712,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) err = rdmsrl_safe(MSR_AMD64_MCx_MASK(4), &mask); if (err == 0) { mask |= (1 << 10); - checking_wrmsrl(MSR_AMD64_MCx_MASK(4), mask); + wrmsrl_safe(MSR_AMD64_MCx_MASK(4), mask); } } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 46674fbb62ba..c97bb7b5a9f8 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -55,8 +55,8 @@ static void __init check_fpu(void) if (!boot_cpu_data.hard_math) { #ifndef CONFIG_MATH_EMULATION - printk(KERN_EMERG "No coprocessor found and no math emulation present.\n"); - printk(KERN_EMERG "Giving up.\n"); + pr_emerg("No coprocessor found and no math emulation present\n"); + pr_emerg("Giving up\n"); for (;;) ; #endif return; @@ -86,7 +86,7 @@ static void __init check_fpu(void) boot_cpu_data.fdiv_bug = fdiv_bug; if (boot_cpu_data.fdiv_bug) - printk(KERN_WARNING "Hmm, FPU with FDIV bug.\n"); + pr_warn("Hmm, FPU with FDIV bug\n"); } static void __init check_hlt(void) @@ -94,16 +94,16 @@ static void __init check_hlt(void) if (boot_cpu_data.x86 >= 5 || paravirt_enabled()) return; - printk(KERN_INFO "Checking 'hlt' instruction... "); + pr_info("Checking 'hlt' instruction... "); if (!boot_cpu_data.hlt_works_ok) { - printk("disabled\n"); + pr_cont("disabled\n"); return; } halt(); halt(); halt(); halt(); - printk(KERN_CONT "OK.\n"); + pr_cont("OK\n"); } /* @@ -116,7 +116,7 @@ static void __init check_popad(void) #ifndef CONFIG_X86_POPAD_OK int res, inp = (int) &res; - printk(KERN_INFO "Checking for popad bug... "); + pr_info("Checking for popad bug... "); __asm__ __volatile__( "movl $12345678,%%eax; movl $0,%%edi; pusha; popa; movl (%%edx,%%edi),%%ecx " : "=&a" (res) @@ -127,9 +127,9 @@ static void __init check_popad(void) * CPU hard. Too bad. */ if (res != 12345678) - printk(KERN_CONT "Buggy.\n"); + pr_cont("Buggy\n"); else - printk(KERN_CONT "OK.\n"); + pr_cont("OK\n"); #endif } @@ -161,7 +161,7 @@ void __init check_bugs(void) { identify_boot_cpu(); #ifndef CONFIG_SMP - printk(KERN_INFO "CPU: "); + pr_info("CPU: "); print_cpu_info(&boot_cpu_data); #endif check_config(); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 6b9333b429ba..5bbc082c47ad 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -947,7 +947,7 @@ static void __cpuinit __print_cpu_msr(void) index_max = msr_range_array[i].max; for (index = index_min; index < index_max; index++) { - if (rdmsrl_amd_safe(index, &val)) + if (rdmsrl_safe(index, &val)) continue; printk(KERN_INFO " MSR%08x: %016llx\n", index, val); } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index da27c5d2168a..9473e8772fd1 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -7,6 +7,9 @@ * Copyright 2008 Intel Corporation * Author: Andi Kleen */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/thread_info.h> #include <linux/capability.h> #include <linux/miscdevice.h> @@ -210,7 +213,7 @@ static void drain_mcelog_buffer(void) cpu_relax(); if (!m->finished && retries >= 4) { - pr_err("MCE: skipping error being logged currently!\n"); + pr_err("skipping error being logged currently!\n"); break; } } @@ -1167,8 +1170,9 @@ int memory_failure(unsigned long pfn, int vector, int flags) { /* mce_severity() should not hand us an ACTION_REQUIRED error */ BUG_ON(flags & MF_ACTION_REQUIRED); - printk(KERN_ERR "Uncorrected memory error in page 0x%lx ignored\n" - "Rebuild kernel with CONFIG_MEMORY_FAILURE=y for smarter handling\n", pfn); + pr_err("Uncorrected memory error in page 0x%lx ignored\n" + "Rebuild kernel with CONFIG_MEMORY_FAILURE=y for smarter handling\n", + pfn); return 0; } @@ -1186,6 +1190,7 @@ void mce_notify_process(void) { unsigned long pfn; struct mce_info *mi = mce_find_info(); + int flags = MF_ACTION_REQUIRED; if (!mi) mce_panic("Lost physical address for unconsumed uncorrectable error", NULL, NULL); @@ -1200,8 +1205,9 @@ void mce_notify_process(void) * doomed. We still need to mark the page as poisoned and alert any * other users of the page. */ - if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0 || - mi->restartable == 0) { + if (!mi->restartable) + flags |= MF_MUST_KILL; + if (memory_failure(pfn, MCE_VECTOR, flags) < 0) { pr_err("Memory error not recovered"); force_sig(SIGBUS, current); } @@ -1358,11 +1364,10 @@ static int __cpuinit __mcheck_cpu_cap_init(void) b = cap & MCG_BANKCNT_MASK; if (!banks) - printk(KERN_INFO "mce: CPU supports %d MCE banks\n", b); + pr_info("CPU supports %d MCE banks\n", b); if (b > MAX_NR_BANKS) { - printk(KERN_WARNING - "MCE: Using only %u machine check banks out of %u\n", + pr_warn("Using only %u machine check banks out of %u\n", MAX_NR_BANKS, b); b = MAX_NR_BANKS; } @@ -1419,7 +1424,7 @@ static void __mcheck_cpu_init_generic(void) static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) { if (c->x86_vendor == X86_VENDOR_UNKNOWN) { - pr_info("MCE: unknown CPU type - not enabling MCE support.\n"); + pr_info("unknown CPU type - not enabling MCE support\n"); return -EOPNOTSUPP; } @@ -1574,7 +1579,7 @@ static void __mcheck_cpu_init_timer(void) /* Handle unconfigured int18 (should never happen) */ static void unexpected_machine_check(struct pt_regs *regs, long error_code) { - printk(KERN_ERR "CPU#%d: Unexpected int18 (Machine Check).\n", + pr_err("CPU#%d: Unexpected int18 (Machine Check)\n", smp_processor_id()); } @@ -1893,8 +1898,7 @@ static int __init mcheck_enable(char *str) get_option(&str, &monarch_timeout); } } else { - printk(KERN_INFO "mce argument %s ignored. Please use /sys\n", - str); + pr_info("mce argument %s ignored. Please use /sys\n", str); return 0; } return 1; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index f4873a64f46d..671b95a2ffb5 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -1,15 +1,17 @@ /* - * (c) 2005, 2006 Advanced Micro Devices, Inc. + * (c) 2005-2012 Advanced Micro Devices, Inc. * Your use of this code is subject to the terms and conditions of the * GNU general public license version 2. See "COPYING" or * http://www.gnu.org/licenses/gpl.html * * Written by Jacob Shin - AMD, Inc. * - * Support : jacob.shin@amd.com + * Support: borislav.petkov@amd.com * * April 2006 * - added support for AMD Family 0x10 processors + * May 2012 + * - major scrubbing * * All MC4_MISCi registers are shared between multi-cores */ @@ -25,6 +27,7 @@ #include <linux/cpu.h> #include <linux/smp.h> +#include <asm/amd_nb.h> #include <asm/apic.h> #include <asm/idle.h> #include <asm/mce.h> @@ -45,23 +48,15 @@ #define MASK_BLKPTR_LO 0xFF000000 #define MCG_XBLK_ADDR 0xC0000400 -struct threshold_block { - unsigned int block; - unsigned int bank; - unsigned int cpu; - u32 address; - u16 interrupt_enable; - bool interrupt_capable; - u16 threshold_limit; - struct kobject kobj; - struct list_head miscj; +static const char * const th_names[] = { + "load_store", + "insn_fetch", + "combined_unit", + "", + "northbridge", + "execution_unit", }; -struct threshold_bank { - struct kobject *kobj; - struct threshold_block *blocks; - cpumask_var_t cpus; -}; static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks); static unsigned char shared_bank[NR_BANKS] = { @@ -84,6 +79,26 @@ struct thresh_restart { u16 old_limit; }; +static const char * const bank4_names(struct threshold_block *b) +{ + switch (b->address) { + /* MSR4_MISC0 */ + case 0x00000413: + return "dram"; + + case 0xc0000408: + return "ht_links"; + + case 0xc0000409: + return "l3_cache"; + + default: + WARN(1, "Funny MSR: 0x%08x\n", b->address); + return ""; + } +}; + + static bool lvt_interrupt_supported(unsigned int bank, u32 msr_high_bits) { /* @@ -224,8 +239,6 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) if (!block) per_cpu(bank_map, cpu) |= (1 << bank); - if (shared_bank[bank] && c->cpu_core_id) - break; memset(&b, 0, sizeof(b)); b.cpu = cpu; @@ -326,7 +339,7 @@ struct threshold_attr { #define SHOW_FIELDS(name) \ static ssize_t show_ ## name(struct threshold_block *b, char *buf) \ { \ - return sprintf(buf, "%lx\n", (unsigned long) b->name); \ + return sprintf(buf, "%lu\n", (unsigned long) b->name); \ } SHOW_FIELDS(interrupt_enable) SHOW_FIELDS(threshold_limit) @@ -377,38 +390,21 @@ store_threshold_limit(struct threshold_block *b, const char *buf, size_t size) return size; } -struct threshold_block_cross_cpu { - struct threshold_block *tb; - long retval; -}; - -static void local_error_count_handler(void *_tbcc) -{ - struct threshold_block_cross_cpu *tbcc = _tbcc; - struct threshold_block *b = tbcc->tb; - u32 low, high; - - rdmsr(b->address, low, high); - tbcc->retval = (high & 0xFFF) - (THRESHOLD_MAX - b->threshold_limit); -} - static ssize_t show_error_count(struct threshold_block *b, char *buf) { - struct threshold_block_cross_cpu tbcc = { .tb = b, }; + u32 lo, hi; - smp_call_function_single(b->cpu, local_error_count_handler, &tbcc, 1); - return sprintf(buf, "%lx\n", tbcc.retval); -} + rdmsr_on_cpu(b->cpu, b->address, &lo, &hi); -static ssize_t store_error_count(struct threshold_block *b, - const char *buf, size_t count) -{ - struct thresh_restart tr = { .b = b, .reset = 1, .old_limit = 0 }; - - smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1); - return 1; + return sprintf(buf, "%u\n", ((hi & THRESHOLD_MAX) - + (THRESHOLD_MAX - b->threshold_limit))); } +static struct threshold_attr error_count = { + .attr = {.name = __stringify(error_count), .mode = 0444 }, + .show = show_error_count, +}; + #define RW_ATTR(val) \ static struct threshold_attr val = { \ .attr = {.name = __stringify(val), .mode = 0644 }, \ @@ -418,7 +414,6 @@ static struct threshold_attr val = { \ RW_ATTR(interrupt_enable); RW_ATTR(threshold_limit); -RW_ATTR(error_count); static struct attribute *default_attrs[] = { &threshold_limit.attr, @@ -517,7 +512,7 @@ static __cpuinit int allocate_threshold_blocks(unsigned int cpu, err = kobject_init_and_add(&b->kobj, &threshold_ktype, per_cpu(threshold_banks, cpu)[bank]->kobj, - "misc%i", block); + (bank == 4 ? bank4_names(b) : th_names[bank])); if (err) goto out_free; recurse: @@ -548,98 +543,91 @@ out_free: return err; } -static __cpuinit long -local_allocate_threshold_blocks(int cpu, unsigned int bank) +static __cpuinit int __threshold_add_blocks(struct threshold_bank *b) { - return allocate_threshold_blocks(cpu, bank, 0, - MSR_IA32_MC0_MISC + bank * 4); + struct list_head *head = &b->blocks->miscj; + struct threshold_block *pos = NULL; + struct threshold_block *tmp = NULL; + int err = 0; + + err = kobject_add(&b->blocks->kobj, b->kobj, b->blocks->kobj.name); + if (err) + return err; + + list_for_each_entry_safe(pos, tmp, head, miscj) { + + err = kobject_add(&pos->kobj, b->kobj, pos->kobj.name); + if (err) { + list_for_each_entry_safe_reverse(pos, tmp, head, miscj) + kobject_del(&pos->kobj); + + return err; + } + } + return err; } -/* symlinks sibling shared banks to first core. first core owns dir/files. */ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) { - int i, err = 0; - struct threshold_bank *b = NULL; struct device *dev = per_cpu(mce_device, cpu); - char name[32]; - - sprintf(name, "threshold_bank%i", bank); + struct amd_northbridge *nb = NULL; + struct threshold_bank *b = NULL; + const char *name = th_names[bank]; + int err = 0; -#ifdef CONFIG_SMP - if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */ - i = cpumask_first(cpu_llc_shared_mask(cpu)); + if (shared_bank[bank]) { - /* first core not up yet */ - if (cpu_data(i).cpu_core_id) - goto out; + nb = node_to_amd_nb(amd_get_nb_id(cpu)); + WARN_ON(!nb); - /* already linked */ - if (per_cpu(threshold_banks, cpu)[bank]) - goto out; + /* threshold descriptor already initialized on this node? */ + if (nb->bank4) { + /* yes, use it */ + b = nb->bank4; + err = kobject_add(b->kobj, &dev->kobj, name); + if (err) + goto out; - b = per_cpu(threshold_banks, i)[bank]; + per_cpu(threshold_banks, cpu)[bank] = b; + atomic_inc(&b->cpus); - if (!b) - goto out; + err = __threshold_add_blocks(b); - err = sysfs_create_link(&dev->kobj, b->kobj, name); - if (err) goto out; - - cpumask_copy(b->cpus, cpu_llc_shared_mask(cpu)); - per_cpu(threshold_banks, cpu)[bank] = b; - - goto out; + } } -#endif b = kzalloc(sizeof(struct threshold_bank), GFP_KERNEL); if (!b) { err = -ENOMEM; goto out; } - if (!zalloc_cpumask_var(&b->cpus, GFP_KERNEL)) { - kfree(b); - err = -ENOMEM; - goto out; - } b->kobj = kobject_create_and_add(name, &dev->kobj); - if (!b->kobj) + if (!b->kobj) { + err = -EINVAL; goto out_free; - -#ifndef CONFIG_SMP - cpumask_setall(b->cpus); -#else - cpumask_set_cpu(cpu, b->cpus); -#endif + } per_cpu(threshold_banks, cpu)[bank] = b; - err = local_allocate_threshold_blocks(cpu, bank); - if (err) - goto out_free; - - for_each_cpu(i, b->cpus) { - if (i == cpu) - continue; + if (shared_bank[bank]) { + atomic_set(&b->cpus, 1); - dev = per_cpu(mce_device, i); - if (dev) - err = sysfs_create_link(&dev->kobj,b->kobj, name); - if (err) - goto out; - - per_cpu(threshold_banks, i)[bank] = b; + /* nb is already initialized, see above */ + WARN_ON(nb->bank4); + nb->bank4 = b; } - goto out; + err = allocate_threshold_blocks(cpu, bank, 0, + MSR_IA32_MC0_MISC + bank * 4); + if (!err) + goto out; -out_free: - per_cpu(threshold_banks, cpu)[bank] = NULL; - free_cpumask_var(b->cpus); + out_free: kfree(b); -out: + + out: return err; } @@ -660,12 +648,6 @@ static __cpuinit int threshold_create_device(unsigned int cpu) return err; } -/* - * let's be hotplug friendly. - * in case of multiple core processors, the first core always takes ownership - * of shared sysfs dir/files, and rest of the cores will be symlinked to it. - */ - static void deallocate_threshold_block(unsigned int cpu, unsigned int bank) { @@ -686,41 +668,42 @@ static void deallocate_threshold_block(unsigned int cpu, per_cpu(threshold_banks, cpu)[bank]->blocks = NULL; } +static void __threshold_remove_blocks(struct threshold_bank *b) +{ + struct threshold_block *pos = NULL; + struct threshold_block *tmp = NULL; + + kobject_del(b->kobj); + + list_for_each_entry_safe(pos, tmp, &b->blocks->miscj, miscj) + kobject_del(&pos->kobj); +} + static void threshold_remove_bank(unsigned int cpu, int bank) { + struct amd_northbridge *nb; struct threshold_bank *b; - struct device *dev; - char name[32]; - int i = 0; b = per_cpu(threshold_banks, cpu)[bank]; if (!b) return; + if (!b->blocks) goto free_out; - sprintf(name, "threshold_bank%i", bank); - -#ifdef CONFIG_SMP - /* sibling symlink */ - if (shared_bank[bank] && b->blocks->cpu != cpu) { - dev = per_cpu(mce_device, cpu); - sysfs_remove_link(&dev->kobj, name); - per_cpu(threshold_banks, cpu)[bank] = NULL; - - return; - } -#endif - - /* remove all sibling symlinks before unregistering */ - for_each_cpu(i, b->cpus) { - if (i == cpu) - continue; - - dev = per_cpu(mce_device, i); - if (dev) - sysfs_remove_link(&dev->kobj, name); - per_cpu(threshold_banks, i)[bank] = NULL; + if (shared_bank[bank]) { + if (!atomic_dec_and_test(&b->cpus)) { + __threshold_remove_blocks(b); + per_cpu(threshold_banks, cpu)[bank] = NULL; + return; + } else { + /* + * the last CPU on this node using the shared bank is + * going away, remove that bank now. + */ + nb = node_to_amd_nb(amd_get_nb_id(cpu)); + nb->bank4 = NULL; + } } deallocate_threshold_block(cpu, bank); @@ -728,7 +711,6 @@ static void threshold_remove_bank(unsigned int cpu, int bank) free_out: kobject_del(b->kobj); kobject_put(b->kobj); - free_cpumask_var(b->cpus); kfree(b); per_cpu(threshold_banks, cpu)[bank] = NULL; } diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index bdda2e6c673b..35ffda5d0727 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -258,11 +258,11 @@ range_to_mtrr(unsigned int reg, unsigned long range_startk, /* Compute the maximum size with which we can make a range: */ if (range_startk) - max_align = ffs(range_startk) - 1; + max_align = __ffs(range_startk); else - max_align = 32; + max_align = BITS_PER_LONG - 1; - align = fls(range_sizek) - 1; + align = __fls(range_sizek); if (align > max_align) align = max_align; diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 75772ae6c65f..e9fe907cd249 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -361,11 +361,7 @@ static void __init print_mtrr_state(void) } pr_debug("MTRR variable ranges %sabled:\n", mtrr_state.enabled & 2 ? "en" : "dis"); - if (size_or_mask & 0xffffffffUL) - high_width = ffs(size_or_mask & 0xffffffffUL) - 1; - else - high_width = ffs(size_or_mask>>32) + 32 - 1; - high_width = (high_width - (32 - PAGE_SHIFT) + 3) / 4; + high_width = (__ffs64(size_or_mask) - (32 - PAGE_SHIFT) + 3) / 4; for (i = 0; i < num_var_ranges; ++i) { if (mtrr_state.var_ranges[i].mask_lo & (1 << 11)) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index c4706cf9c011..29557aa06dda 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -35,17 +35,6 @@ #include "perf_event.h" -#if 0 -#undef wrmsrl -#define wrmsrl(msr, val) \ -do { \ - trace_printk("wrmsrl(%lx, %lx)\n", (unsigned long)(msr),\ - (unsigned long)(val)); \ - native_write_msr((msr), (u32)((u64)(val)), \ - (u32)((u64)(val) >> 32)); \ -} while (0) -#endif - struct x86_pmu x86_pmu __read_mostly; DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { @@ -74,7 +63,7 @@ u64 x86_perf_event_update(struct perf_event *event) int idx = hwc->idx; s64 delta; - if (idx == X86_PMC_IDX_FIXED_BTS) + if (idx == INTEL_PMC_IDX_FIXED_BTS) return 0; /* @@ -86,7 +75,7 @@ u64 x86_perf_event_update(struct perf_event *event) */ again: prev_raw_count = local64_read(&hwc->prev_count); - rdmsrl(hwc->event_base, new_raw_count); + rdpmcl(hwc->event_base_rdpmc, new_raw_count); if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) @@ -189,7 +178,7 @@ static void release_pmc_hardware(void) {} static bool check_hw_exists(void) { - u64 val, val_new = 0; + u64 val, val_new = ~0; int i, reg, ret = 0; /* @@ -222,8 +211,9 @@ static bool check_hw_exists(void) * that don't trap on the MSR access and always return 0s. */ val = 0xabcdUL; - ret = checking_wrmsrl(x86_pmu_event_addr(0), val); - ret |= rdmsrl_safe(x86_pmu_event_addr(0), &val_new); + reg = x86_pmu_event_addr(0); + ret = wrmsrl_safe(reg, val); + ret |= rdmsrl_safe(reg, &val_new); if (ret || val != val_new) goto msr_fail; @@ -240,6 +230,7 @@ bios_fail: msr_fail: printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n"); + printk(KERN_ERR "Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new); return false; } @@ -388,7 +379,7 @@ int x86_pmu_hw_config(struct perf_event *event) int precise = 0; /* Support for constant skid */ - if (x86_pmu.pebs_active) { + if (x86_pmu.pebs_active && !x86_pmu.pebs_broken) { precise++; /* Support for IP fixup */ @@ -637,8 +628,8 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) c = sched->constraints[sched->state.event]; /* Prefer fixed purpose counters */ - if (x86_pmu.num_counters_fixed) { - idx = X86_PMC_IDX_FIXED; + if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) { + idx = INTEL_PMC_IDX_FIXED; for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) { if (!__test_and_set_bit(idx, sched->state.used)) goto done; @@ -646,7 +637,7 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) } /* Grab the first unused counter starting with idx */ idx = sched->state.counter; - for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_FIXED) { + for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) { if (!__test_and_set_bit(idx, sched->state.used)) goto done; } @@ -704,8 +695,8 @@ static bool perf_sched_next_event(struct perf_sched *sched) /* * Assign a counter for each event. */ -static int perf_assign_events(struct event_constraint **constraints, int n, - int wmin, int wmax, int *assign) +int perf_assign_events(struct event_constraint **constraints, int n, + int wmin, int wmax, int *assign) { struct perf_sched sched; @@ -824,15 +815,17 @@ static inline void x86_assign_hw_event(struct perf_event *event, hwc->last_cpu = smp_processor_id(); hwc->last_tag = ++cpuc->tags[i]; - if (hwc->idx == X86_PMC_IDX_FIXED_BTS) { + if (hwc->idx == INTEL_PMC_IDX_FIXED_BTS) { hwc->config_base = 0; hwc->event_base = 0; - } else if (hwc->idx >= X86_PMC_IDX_FIXED) { + } else if (hwc->idx >= INTEL_PMC_IDX_FIXED) { hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL; - hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - X86_PMC_IDX_FIXED); + hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - INTEL_PMC_IDX_FIXED); + hwc->event_base_rdpmc = (hwc->idx - INTEL_PMC_IDX_FIXED) | 1<<30; } else { hwc->config_base = x86_pmu_config_addr(hwc->idx); hwc->event_base = x86_pmu_event_addr(hwc->idx); + hwc->event_base_rdpmc = hwc->idx; } } @@ -930,7 +923,7 @@ int x86_perf_event_set_period(struct perf_event *event) s64 period = hwc->sample_period; int ret = 0, idx = hwc->idx; - if (idx == X86_PMC_IDX_FIXED_BTS) + if (idx == INTEL_PMC_IDX_FIXED_BTS) return 0; /* @@ -1316,7 +1309,6 @@ static struct attribute_group x86_pmu_format_group = { static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; - struct event_constraint *c; int err; pr_info("Performance Events: "); @@ -1347,21 +1339,8 @@ static int __init init_hw_perf_events(void) for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next) quirk->func(); - if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) { - WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!", - x86_pmu.num_counters, X86_PMC_MAX_GENERIC); - x86_pmu.num_counters = X86_PMC_MAX_GENERIC; - } - x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1; - - if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) { - WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!", - x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED); - x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED; - } - - x86_pmu.intel_ctrl |= - ((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED; + if (!x86_pmu.intel_ctrl) + x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1; perf_events_lapic_init(); register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI"); @@ -1370,22 +1349,6 @@ static int __init init_hw_perf_events(void) __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1, 0, x86_pmu.num_counters, 0); - if (x86_pmu.event_constraints) { - /* - * event on fixed counter2 (REF_CYCLES) only works on this - * counter, so do not extend mask to generic counters - */ - for_each_event_constraint(c, x86_pmu.event_constraints) { - if (c->cmask != X86_RAW_EVENT_MASK - || c->idxmsk64 == X86_PMC_MSK_FIXED_REF_CYCLES) { - continue; - } - - c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; - c->weight += x86_pmu.num_counters; - } - } - x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ x86_pmu_format_group.attrs = x86_pmu.format_attrs; @@ -1620,8 +1583,8 @@ static int x86_pmu_event_idx(struct perf_event *event) if (!x86_pmu.attr_rdpmc) return 0; - if (x86_pmu.num_counters_fixed && idx >= X86_PMC_IDX_FIXED) { - idx -= X86_PMC_IDX_FIXED; + if (x86_pmu.num_counters_fixed && idx >= INTEL_PMC_IDX_FIXED) { + idx -= INTEL_PMC_IDX_FIXED; idx |= 1 << 30; } @@ -1649,7 +1612,12 @@ static ssize_t set_attr_rdpmc(struct device *cdev, struct device_attribute *attr, const char *buf, size_t count) { - unsigned long val = simple_strtoul(buf, NULL, 0); + unsigned long val; + ssize_t ret; + + ret = kstrtoul(buf, 0, &val); + if (ret) + return ret; if (!!val != !!x86_pmu.attr_rdpmc) { x86_pmu.attr_rdpmc = !!val; @@ -1682,13 +1650,20 @@ static void x86_pmu_flush_branch_stack(void) x86_pmu.flush_branch_stack(); } +void perf_check_microcode(void) +{ + if (x86_pmu.check_microcode) + x86_pmu.check_microcode(); +} +EXPORT_SYMBOL_GPL(perf_check_microcode); + static struct pmu pmu = { .pmu_enable = x86_pmu_enable, .pmu_disable = x86_pmu_disable, - .attr_groups = x86_pmu_attr_groups, + .attr_groups = x86_pmu_attr_groups, - .event_init = x86_pmu_event_init, + .event_init = x86_pmu_event_init, .add = x86_pmu_add, .del = x86_pmu_del, @@ -1696,11 +1671,11 @@ static struct pmu pmu = { .stop = x86_pmu_stop, .read = x86_pmu_read, - .start_txn = x86_pmu_start_txn, - .cancel_txn = x86_pmu_cancel_txn, - .commit_txn = x86_pmu_commit_txn, + .start_txn = x86_pmu_start_txn, + .cancel_txn = x86_pmu_cancel_txn, + .commit_txn = x86_pmu_commit_txn, - .event_idx = x86_pmu_event_idx, + .event_idx = x86_pmu_event_idx, .flush_branch_stack = x86_pmu_flush_branch_stack, }; @@ -1863,7 +1838,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs) else misc |= PERF_RECORD_MISC_GUEST_KERNEL; } else { - if (user_mode(regs)) + if (!kernel_ip(regs->ip)) misc |= PERF_RECORD_MISC_USER; else misc |= PERF_RECORD_MISC_KERNEL; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 7241e2fc3c17..a15df4be151f 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -14,6 +14,18 @@ #include <linux/perf_event.h> +#if 0 +#undef wrmsrl +#define wrmsrl(msr, val) \ +do { \ + unsigned int _msr = (msr); \ + u64 _val = (val); \ + trace_printk("wrmsrl(%x, %Lx)\n", (unsigned int)(_msr), \ + (unsigned long long)(_val)); \ + native_write_msr((_msr), (u32)(_val), (u32)(_val >> 32)); \ +} while (0) +#endif + /* * | NHM/WSM | SNB | * register ------------------------------- @@ -57,7 +69,7 @@ struct amd_nb { }; /* The maximal number of PEBS events: */ -#define MAX_PEBS_EVENTS 4 +#define MAX_PEBS_EVENTS 8 /* * A debug store configuration. @@ -349,6 +361,8 @@ struct x86_pmu { void (*cpu_starting)(int cpu); void (*cpu_dying)(int cpu); void (*cpu_dead)(int cpu); + + void (*check_microcode)(void); void (*flush_branch_stack)(void); /* @@ -360,12 +374,16 @@ struct x86_pmu { /* * Intel DebugStore bits */ - int bts, pebs; - int bts_active, pebs_active; + int bts :1, + bts_active :1, + pebs :1, + pebs_active :1, + pebs_broken :1; int pebs_record_size; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); + int max_pebs_events; /* * Intel LBR @@ -468,6 +486,8 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, void x86_pmu_enable_all(int added); +int perf_assign_events(struct event_constraint **constraints, int n, + int wmin, int wmax, int *assign); int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign); void x86_pmu_stop(struct perf_event *event, int flags); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 11a4eb9131d5..4528ae7b6ec4 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -366,7 +366,7 @@ static void amd_pmu_cpu_starting(int cpu) cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY; - if (boot_cpu_data.x86_max_cores < 2 || boot_cpu_data.x86 == 0x15) + if (boot_cpu_data.x86_max_cores < 2) return; nb_id = amd_get_nb_id(cpu); @@ -422,35 +422,6 @@ static struct attribute *amd_format_attr[] = { NULL, }; -static __initconst const struct x86_pmu amd_pmu = { - .name = "AMD", - .handle_irq = x86_pmu_handle_irq, - .disable_all = x86_pmu_disable_all, - .enable_all = x86_pmu_enable_all, - .enable = x86_pmu_enable_event, - .disable = x86_pmu_disable_event, - .hw_config = amd_pmu_hw_config, - .schedule_events = x86_schedule_events, - .eventsel = MSR_K7_EVNTSEL0, - .perfctr = MSR_K7_PERFCTR0, - .event_map = amd_pmu_event_map, - .max_events = ARRAY_SIZE(amd_perfmon_event_map), - .num_counters = AMD64_NUM_COUNTERS, - .cntval_bits = 48, - .cntval_mask = (1ULL << 48) - 1, - .apic = 1, - /* use highest bit to detect overflow */ - .max_period = (1ULL << 47) - 1, - .get_event_constraints = amd_get_event_constraints, - .put_event_constraints = amd_put_event_constraints, - - .format_attrs = amd_format_attr, - - .cpu_prepare = amd_pmu_cpu_prepare, - .cpu_starting = amd_pmu_cpu_starting, - .cpu_dead = amd_pmu_cpu_dead, -}; - /* AMD Family 15h */ #define AMD_EVENT_TYPE_MASK 0x000000F0ULL @@ -597,8 +568,8 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev } } -static __initconst const struct x86_pmu amd_pmu_f15h = { - .name = "AMD Family 15h", +static __initconst const struct x86_pmu amd_pmu = { + .name = "AMD", .handle_irq = x86_pmu_handle_irq, .disable_all = x86_pmu_disable_all, .enable_all = x86_pmu_enable_all, @@ -606,50 +577,68 @@ static __initconst const struct x86_pmu amd_pmu_f15h = { .disable = x86_pmu_disable_event, .hw_config = amd_pmu_hw_config, .schedule_events = x86_schedule_events, - .eventsel = MSR_F15H_PERF_CTL, - .perfctr = MSR_F15H_PERF_CTR, + .eventsel = MSR_K7_EVNTSEL0, + .perfctr = MSR_K7_PERFCTR0, .event_map = amd_pmu_event_map, .max_events = ARRAY_SIZE(amd_perfmon_event_map), - .num_counters = AMD64_NUM_COUNTERS_F15H, + .num_counters = AMD64_NUM_COUNTERS, .cntval_bits = 48, .cntval_mask = (1ULL << 48) - 1, .apic = 1, /* use highest bit to detect overflow */ .max_period = (1ULL << 47) - 1, - .get_event_constraints = amd_get_event_constraints_f15h, - /* nortbridge counters not yet implemented: */ -#if 0 + .get_event_constraints = amd_get_event_constraints, .put_event_constraints = amd_put_event_constraints, + .format_attrs = amd_format_attr, + .cpu_prepare = amd_pmu_cpu_prepare, - .cpu_dead = amd_pmu_cpu_dead, -#endif .cpu_starting = amd_pmu_cpu_starting, - .format_attrs = amd_format_attr, + .cpu_dead = amd_pmu_cpu_dead, }; +static int setup_event_constraints(void) +{ + if (boot_cpu_data.x86 >= 0x15) + x86_pmu.get_event_constraints = amd_get_event_constraints_f15h; + return 0; +} + +static int setup_perfctr_core(void) +{ + if (!cpu_has_perfctr_core) { + WARN(x86_pmu.get_event_constraints == amd_get_event_constraints_f15h, + KERN_ERR "Odd, counter constraints enabled but no core perfctrs detected!"); + return -ENODEV; + } + + WARN(x86_pmu.get_event_constraints == amd_get_event_constraints, + KERN_ERR "hw perf events core counters need constraints handler!"); + + /* + * If core performance counter extensions exists, we must use + * MSR_F15H_PERF_CTL/MSR_F15H_PERF_CTR msrs. See also + * x86_pmu_addr_offset(). + */ + x86_pmu.eventsel = MSR_F15H_PERF_CTL; + x86_pmu.perfctr = MSR_F15H_PERF_CTR; + x86_pmu.num_counters = AMD64_NUM_COUNTERS_CORE; + + printk(KERN_INFO "perf: AMD core performance counters detected\n"); + + return 0; +} + __init int amd_pmu_init(void) { /* Performance-monitoring supported from K7 and later: */ if (boot_cpu_data.x86 < 6) return -ENODEV; - /* - * If core performance counter extensions exists, it must be - * family 15h, otherwise fail. See x86_pmu_addr_offset(). - */ - switch (boot_cpu_data.x86) { - case 0x15: - if (!cpu_has_perfctr_core) - return -ENODEV; - x86_pmu = amd_pmu_f15h; - break; - default: - if (cpu_has_perfctr_core) - return -ENODEV; - x86_pmu = amd_pmu; - break; - } + x86_pmu = amd_pmu; + + setup_event_constraints(); + setup_perfctr_core(); /* Events are common for all AMDs */ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 187c294bc658..7a8b9d0abcaa 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -5,6 +5,8 @@ * among events on a single PMU. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/stddef.h> #include <linux/types.h> #include <linux/init.h> @@ -21,14 +23,14 @@ */ static u64 intel_perfmon_event_map[PERF_COUNT_HW_MAX] __read_mostly = { - [PERF_COUNT_HW_CPU_CYCLES] = 0x003c, - [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, - [PERF_COUNT_HW_CACHE_REFERENCES] = 0x4f2e, - [PERF_COUNT_HW_CACHE_MISSES] = 0x412e, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, - [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, - [PERF_COUNT_HW_BUS_CYCLES] = 0x013c, - [PERF_COUNT_HW_REF_CPU_CYCLES] = 0x0300, /* pseudo-encoding */ + [PERF_COUNT_HW_CPU_CYCLES] = 0x003c, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x4f2e, + [PERF_COUNT_HW_CACHE_MISSES] = 0x412e, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, + [PERF_COUNT_HW_BUS_CYCLES] = 0x013c, + [PERF_COUNT_HW_REF_CPU_CYCLES] = 0x0300, /* pseudo-encoding */ }; static struct event_constraint intel_core_event_constraints[] __read_mostly = @@ -747,7 +749,7 @@ static void intel_pmu_disable_all(void) wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0); - if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) + if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) intel_pmu_disable_bts(); intel_pmu_pebs_disable_all(); @@ -763,9 +765,9 @@ static void intel_pmu_enable_all(int added) wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask); - if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) { + if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) { struct perf_event *event = - cpuc->events[X86_PMC_IDX_FIXED_BTS]; + cpuc->events[INTEL_PMC_IDX_FIXED_BTS]; if (WARN_ON_ONCE(!event)) return; @@ -871,7 +873,7 @@ static inline void intel_pmu_ack_status(u64 ack) static void intel_pmu_disable_fixed(struct hw_perf_event *hwc) { - int idx = hwc->idx - X86_PMC_IDX_FIXED; + int idx = hwc->idx - INTEL_PMC_IDX_FIXED; u64 ctrl_val, mask; mask = 0xfULL << (idx * 4); @@ -886,7 +888,7 @@ static void intel_pmu_disable_event(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) { + if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) { intel_pmu_disable_bts(); intel_pmu_drain_bts_buffer(); return; @@ -915,7 +917,7 @@ static void intel_pmu_disable_event(struct perf_event *event) static void intel_pmu_enable_fixed(struct hw_perf_event *hwc) { - int idx = hwc->idx - X86_PMC_IDX_FIXED; + int idx = hwc->idx - INTEL_PMC_IDX_FIXED; u64 ctrl_val, bits, mask; /* @@ -949,7 +951,7 @@ static void intel_pmu_enable_event(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) { + if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) { if (!__this_cpu_read(cpu_hw_events.enabled)) return; @@ -1000,14 +1002,14 @@ static void intel_pmu_reset(void) local_irq_save(flags); - printk("clearing PMU state on CPU#%d\n", smp_processor_id()); + pr_info("clearing PMU state on CPU#%d\n", smp_processor_id()); for (idx = 0; idx < x86_pmu.num_counters; idx++) { - checking_wrmsrl(x86_pmu_config_addr(idx), 0ull); - checking_wrmsrl(x86_pmu_event_addr(idx), 0ull); + wrmsrl_safe(x86_pmu_config_addr(idx), 0ull); + wrmsrl_safe(x86_pmu_event_addr(idx), 0ull); } for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) - checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull); + wrmsrl_safe(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull); if (ds) ds->bts_index = ds->bts_buffer_base; @@ -1707,16 +1709,61 @@ static __init void intel_clovertown_quirk(void) * But taken together it might just make sense to not enable PEBS on * these chips. */ - printk(KERN_WARNING "PEBS disabled due to CPU errata.\n"); + pr_warn("PEBS disabled due to CPU errata\n"); x86_pmu.pebs = 0; x86_pmu.pebs_constraints = NULL; } +static int intel_snb_pebs_broken(int cpu) +{ + u32 rev = UINT_MAX; /* default to broken for unknown models */ + + switch (cpu_data(cpu).x86_model) { + case 42: /* SNB */ + rev = 0x28; + break; + + case 45: /* SNB-EP */ + switch (cpu_data(cpu).x86_mask) { + case 6: rev = 0x618; break; + case 7: rev = 0x70c; break; + } + } + + return (cpu_data(cpu).microcode < rev); +} + +static void intel_snb_check_microcode(void) +{ + int pebs_broken = 0; + int cpu; + + get_online_cpus(); + for_each_online_cpu(cpu) { + if ((pebs_broken = intel_snb_pebs_broken(cpu))) + break; + } + put_online_cpus(); + + if (pebs_broken == x86_pmu.pebs_broken) + return; + + /* + * Serialized by the microcode lock.. + */ + if (x86_pmu.pebs_broken) { + pr_info("PEBS enabled due to microcode update\n"); + x86_pmu.pebs_broken = 0; + } else { + pr_info("PEBS disabled due to CPU errata, please upgrade microcode\n"); + x86_pmu.pebs_broken = 1; + } +} + static __init void intel_sandybridge_quirk(void) { - printk(KERN_WARNING "PEBS disabled due to CPU errata.\n"); - x86_pmu.pebs = 0; - x86_pmu.pebs_constraints = NULL; + x86_pmu.check_microcode = intel_snb_check_microcode; + intel_snb_check_microcode(); } static const struct { int id; char *name; } intel_arch_events_map[] __initconst = { @@ -1736,8 +1783,8 @@ static __init void intel_arch_events_quirk(void) /* disable event that reported as not presend by cpuid */ for_each_set_bit(bit, x86_pmu.events_mask, ARRAY_SIZE(intel_arch_events_map)) { intel_perfmon_event_map[intel_arch_events_map[bit].id] = 0; - printk(KERN_WARNING "CPUID marked event: \'%s\' unavailable\n", - intel_arch_events_map[bit].name); + pr_warn("CPUID marked event: \'%s\' unavailable\n", + intel_arch_events_map[bit].name); } } @@ -1756,7 +1803,7 @@ static __init void intel_nehalem_quirk(void) intel_perfmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x7f89; ebx.split.no_branch_misses_retired = 0; x86_pmu.events_maskl = ebx.full; - printk(KERN_INFO "CPU erratum AAJ80 worked around\n"); + pr_info("CPU erratum AAJ80 worked around\n"); } } @@ -1765,6 +1812,7 @@ __init int intel_pmu_init(void) union cpuid10_edx edx; union cpuid10_eax eax; union cpuid10_ebx ebx; + struct event_constraint *c; unsigned int unused; int version; @@ -1800,6 +1848,8 @@ __init int intel_pmu_init(void) x86_pmu.events_maskl = ebx.full; x86_pmu.events_mask_len = eax.split.mask_length; + x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters); + /* * Quirk: v2 perfmon does not report fixed-purpose events, so * assume at least 3 events: @@ -1951,5 +2001,37 @@ __init int intel_pmu_init(void) } } + if (x86_pmu.num_counters > INTEL_PMC_MAX_GENERIC) { + WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!", + x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC); + x86_pmu.num_counters = INTEL_PMC_MAX_GENERIC; + } + x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1; + + if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED) { + WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!", + x86_pmu.num_counters_fixed, INTEL_PMC_MAX_FIXED); + x86_pmu.num_counters_fixed = INTEL_PMC_MAX_FIXED; + } + + x86_pmu.intel_ctrl |= + ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED; + + if (x86_pmu.event_constraints) { + /* + * event on fixed counter2 (REF_CYCLES) only works on this + * counter, so do not extend mask to generic counters + */ + for_each_event_constraint(c, x86_pmu.event_constraints) { + if (c->cmask != X86_RAW_EVENT_MASK + || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) { + continue; + } + + c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; + c->weight += x86_pmu.num_counters; + } + } + return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 35e2192df9f4..629ae0b7ad90 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -248,7 +248,7 @@ void reserve_ds_buffers(void) */ struct event_constraint bts_constraint = - EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0); + EVENT_CONSTRAINT(0, 1ULL << INTEL_PMC_IDX_FIXED_BTS, 0); void intel_pmu_enable_bts(u64 config) { @@ -295,7 +295,7 @@ int intel_pmu_drain_bts_buffer(void) u64 to; u64 flags; }; - struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS]; + struct perf_event *event = cpuc->events[INTEL_PMC_IDX_FIXED_BTS]; struct bts_record *at, *top; struct perf_output_handle handle; struct perf_event_header header; @@ -620,7 +620,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) * Should not happen, we program the threshold at 1 and do not * set a reset value. */ - WARN_ON_ONCE(n > 1); + WARN_ONCE(n > 1, "bad leftover pebs %d\n", n); at += n - 1; __intel_pmu_pebs_event(event, iregs, at); @@ -651,10 +651,10 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * Should not happen, we program the threshold at 1 and do not * set a reset value. */ - WARN_ON_ONCE(n > MAX_PEBS_EVENTS); + WARN_ONCE(n > x86_pmu.max_pebs_events, "Unexpected number of pebs records %d\n", n); for ( ; at < top; at++) { - for_each_set_bit(bit, (unsigned long *)&at->status, MAX_PEBS_EVENTS) { + for_each_set_bit(bit, (unsigned long *)&at->status, x86_pmu.max_pebs_events) { event = cpuc->events[bit]; if (!test_bit(bit, cpuc->active_mask)) continue; @@ -670,7 +670,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) break; } - if (!event || bit >= MAX_PEBS_EVENTS) + if (!event || bit >= x86_pmu.max_pebs_events) continue; __intel_pmu_pebs_event(event, iregs, at); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c new file mode 100644 index 000000000000..19faffc60886 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -0,0 +1,1850 @@ +#include "perf_event_intel_uncore.h" + +static struct intel_uncore_type *empty_uncore[] = { NULL, }; +static struct intel_uncore_type **msr_uncores = empty_uncore; +static struct intel_uncore_type **pci_uncores = empty_uncore; +/* pci bus to socket mapping */ +static int pcibus_to_physid[256] = { [0 ... 255] = -1, }; + +static DEFINE_RAW_SPINLOCK(uncore_box_lock); + +/* mask of cpus that collect uncore events */ +static cpumask_t uncore_cpu_mask; + +/* constraint for the fixed counter */ +static struct event_constraint constraint_fixed = + EVENT_CONSTRAINT(~0ULL, 1 << UNCORE_PMC_IDX_FIXED, ~0ULL); +static struct event_constraint constraint_empty = + EVENT_CONSTRAINT(0, 0, 0); + +DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); +DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); +DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); +DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28"); +DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28"); +DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); +DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); +DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); +DEFINE_UNCORE_FORMAT_ATTR(filter_brand0, filter_brand0, "config1:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(filter_brand1, filter_brand1, "config1:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(filter_brand2, filter_brand2, "config1:16-23"); +DEFINE_UNCORE_FORMAT_ATTR(filter_brand3, filter_brand3, "config1:24-31"); + +/* Sandy Bridge-EP uncore support */ +static struct intel_uncore_type snbep_uncore_cbox; +static struct intel_uncore_type snbep_uncore_pcu; + +static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); + u32 config; + + pci_read_config_dword(pdev, box_ctl, &config); + config |= SNBEP_PMON_BOX_CTL_FRZ; + pci_write_config_dword(pdev, box_ctl, config); +} + +static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); + u32 config; + + pci_read_config_dword(pdev, box_ctl, &config); + config &= ~SNBEP_PMON_BOX_CTL_FRZ; + pci_write_config_dword(pdev, box_ctl, config); +} + +static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, hwc->config_base, hwc->config | + SNBEP_PMON_CTL_EN); +} + +static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, hwc->config_base, hwc->config); +} + +static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + u64 count; + + pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count); + pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1); + return count; +} + +static void snbep_uncore_pci_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, + SNBEP_PMON_BOX_CTL_INT); +} + +static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box) +{ + u64 config; + unsigned msr; + + msr = uncore_msr_box_ctl(box); + if (msr) { + rdmsrl(msr, config); + config |= SNBEP_PMON_BOX_CTL_FRZ; + wrmsrl(msr, config); + return; + } +} + +static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + u64 config; + unsigned msr; + + msr = uncore_msr_box_ctl(box); + if (msr) { + rdmsrl(msr, config); + config &= ~SNBEP_PMON_BOX_CTL_FRZ; + wrmsrl(msr, config); + return; + } +} + +static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (reg1->idx != EXTRA_REG_NONE) + wrmsrl(reg1->reg, reg1->config); + + wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + wrmsrl(hwc->config_base, hwc->config); +} + +static u64 snbep_uncore_msr_read_counter(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + u64 count; + + rdmsrl(hwc->event_base, count); + return count; +} + +static void snbep_uncore_msr_init_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + if (msr) + wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT); +} + +static struct event_constraint * +snbep_uncore_get_constraint(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct intel_uncore_extra_reg *er; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + unsigned long flags; + bool ok = false; + + if (reg1->idx == EXTRA_REG_NONE || (box->phys_id >= 0 && reg1->alloc)) + return NULL; + + er = &box->shared_regs[reg1->idx]; + raw_spin_lock_irqsave(&er->lock, flags); + if (!atomic_read(&er->ref) || er->config1 == reg1->config) { + atomic_inc(&er->ref); + er->config1 = reg1->config; + ok = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + if (ok) { + if (box->phys_id >= 0) + reg1->alloc = 1; + return NULL; + } + return &constraint_empty; +} + +static void snbep_uncore_put_constraint(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct intel_uncore_extra_reg *er; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + + if (box->phys_id < 0 || !reg1->alloc) + return; + + er = &box->shared_regs[reg1->idx]; + atomic_dec(&er->ref); + reg1->alloc = 0; +} + +static int snbep_uncore_hw_config(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (box->pmu->type == &snbep_uncore_cbox) { + reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + + SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & + SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK; + } else if (box->pmu->type == &snbep_uncore_pcu) { + reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER; + reg1->config = event->attr.config1 & + SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK; + } else { + return 0; + } + reg1->idx = 0; + return 0; +} + +static struct attribute *snbep_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute *snbep_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + NULL, +}; + +static struct attribute *snbep_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid.attr, + &format_attr_filter_nid.attr, + &format_attr_filter_state.attr, + &format_attr_filter_opc.attr, + NULL, +}; + +static struct attribute *snbep_uncore_pcu_formats_attr[] = { + &format_attr_event.attr, + &format_attr_occ_sel.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge.attr, + &format_attr_filter_brand0.attr, + &format_attr_filter_brand1.attr, + &format_attr_filter_brand2.attr, + &format_attr_filter_brand3.attr, + NULL, +}; + +static struct uncore_event_desc snbep_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"), + INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"), + { /* end: all zeroes */ }, +}; + +static struct uncore_event_desc snbep_uncore_qpi_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"), + INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"), + INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x02,umask=0x08"), + INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x03,umask=0x04"), + { /* end: all zeroes */ }, +}; + +static struct attribute_group snbep_uncore_format_group = { + .name = "format", + .attrs = snbep_uncore_formats_attr, +}; + +static struct attribute_group snbep_uncore_ubox_format_group = { + .name = "format", + .attrs = snbep_uncore_ubox_formats_attr, +}; + +static struct attribute_group snbep_uncore_cbox_format_group = { + .name = "format", + .attrs = snbep_uncore_cbox_formats_attr, +}; + +static struct attribute_group snbep_uncore_pcu_format_group = { + .name = "format", + .attrs = snbep_uncore_pcu_formats_attr, +}; + +static struct intel_uncore_ops snbep_uncore_msr_ops = { + .init_box = snbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = snbep_uncore_msr_enable_event, + .read_counter = snbep_uncore_msr_read_counter, + .get_constraint = snbep_uncore_get_constraint, + .put_constraint = snbep_uncore_put_constraint, + .hw_config = snbep_uncore_hw_config, +}; + +static struct intel_uncore_ops snbep_uncore_pci_ops = { + .init_box = snbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = snbep_uncore_pci_disable_event, + .enable_event = snbep_uncore_pci_enable_event, + .read_counter = snbep_uncore_pci_read_counter, +}; + +static struct event_constraint snbep_uncore_cbox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x1), + UNCORE_EVENT_CONSTRAINT(0x02, 0x3), + UNCORE_EVENT_CONSTRAINT(0x04, 0x3), + UNCORE_EVENT_CONSTRAINT(0x05, 0x3), + UNCORE_EVENT_CONSTRAINT(0x07, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x12, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x3), + UNCORE_EVENT_CONSTRAINT(0x1b, 0xc), + UNCORE_EVENT_CONSTRAINT(0x1c, 0xc), + UNCORE_EVENT_CONSTRAINT(0x1d, 0xc), + UNCORE_EVENT_CONSTRAINT(0x1e, 0xc), + EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x31, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x35, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + UNCORE_EVENT_CONSTRAINT(0x3b, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct event_constraint snbep_uncore_r2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x12, 0x1), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x24, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct event_constraint snbep_uncore_r3qpi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x12, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x20, 0x3), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x22, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x24, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x30, 0x3), + UNCORE_EVENT_CONSTRAINT(0x31, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x3), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type snbep_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = SNBEP_U_MSR_PMON_CTR0, + .event_ctl = SNBEP_U_MSR_PMON_CTL0, + .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &snbep_uncore_msr_ops, + .format_group = &snbep_uncore_ubox_format_group, +}; + +static struct intel_uncore_type snbep_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 44, + .event_ctl = SNBEP_C0_MSR_PMON_CTL0, + .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, + .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = SNBEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = snbep_uncore_cbox_constraints, + .ops = &snbep_uncore_msr_ops, + .format_group = &snbep_uncore_cbox_format_group, +}; + +static struct intel_uncore_type snbep_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, + .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, + .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_msr_ops, + .format_group = &snbep_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *snbep_msr_uncores[] = { + &snbep_uncore_ubox, + &snbep_uncore_cbox, + &snbep_uncore_pcu, + NULL, +}; + +#define SNBEP_UNCORE_PCI_COMMON_INIT() \ + .perf_ctr = SNBEP_PCI_PMON_CTR0, \ + .event_ctl = SNBEP_PCI_PMON_CTL0, \ + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, \ + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ + .ops = &snbep_uncore_pci_ops, \ + .format_group = &snbep_uncore_format_group + +static struct intel_uncore_type snbep_uncore_ha = { + .name = "ha", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type snbep_uncore_imc = { + .name = "imc", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + .event_descs = snbep_uncore_imc_events, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type snbep_uncore_qpi = { + .name = "qpi", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_descs = snbep_uncore_qpi_events, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + + +static struct intel_uncore_type snbep_uncore_r2pcie = { + .name = "r2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r2pcie_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type snbep_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 3, + .num_boxes = 2, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r3qpi_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type *snbep_pci_uncores[] = { + &snbep_uncore_ha, + &snbep_uncore_imc, + &snbep_uncore_qpi, + &snbep_uncore_r2pcie, + &snbep_uncore_r3qpi, + NULL, +}; + +static DEFINE_PCI_DEVICE_TABLE(snbep_uncore_pci_ids) = { + { /* Home Agent */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA), + .driver_data = (unsigned long)&snbep_uncore_ha, + }, + { /* MC Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0), + .driver_data = (unsigned long)&snbep_uncore_imc, + }, + { /* MC Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1), + .driver_data = (unsigned long)&snbep_uncore_imc, + }, + { /* MC Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2), + .driver_data = (unsigned long)&snbep_uncore_imc, + }, + { /* MC Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3), + .driver_data = (unsigned long)&snbep_uncore_imc, + }, + { /* QPI Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0), + .driver_data = (unsigned long)&snbep_uncore_qpi, + }, + { /* QPI Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1), + .driver_data = (unsigned long)&snbep_uncore_qpi, + }, + { /* P2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE), + .driver_data = (unsigned long)&snbep_uncore_r2pcie, + }, + { /* R3QPI Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0), + .driver_data = (unsigned long)&snbep_uncore_r3qpi, + }, + { /* R3QPI Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1), + .driver_data = (unsigned long)&snbep_uncore_r3qpi, + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver snbep_uncore_pci_driver = { + .name = "snbep_uncore", + .id_table = snbep_uncore_pci_ids, +}; + +/* + * build pci bus to socket mapping + */ +static void snbep_pci2phy_map_init(void) +{ + struct pci_dev *ubox_dev = NULL; + int i, bus, nodeid; + u32 config; + + while (1) { + /* find the UBOX device */ + ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_JAKETOWN_UBOX, + ubox_dev); + if (!ubox_dev) + break; + bus = ubox_dev->bus->number; + /* get the Node ID of the local register */ + pci_read_config_dword(ubox_dev, 0x40, &config); + nodeid = config; + /* get the Node ID mapping */ + pci_read_config_dword(ubox_dev, 0x54, &config); + /* + * every three bits in the Node ID mapping register maps + * to a particular node. + */ + for (i = 0; i < 8; i++) { + if (nodeid == ((config >> (3 * i)) & 0x7)) { + pcibus_to_physid[bus] = i; + break; + } + } + }; + return; +} +/* end of Sandy Bridge-EP uncore support */ + + +/* Sandy Bridge uncore support */ +static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx < UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); + else + wrmsrl(hwc->config_base, SNB_UNC_CTL_EN); +} + +static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + wrmsrl(event->hw.config_base, 0); +} + +static u64 snb_uncore_msr_read_counter(struct intel_uncore_box *box, + struct perf_event *event) +{ + u64 count; + rdmsrl(event->hw.event_base, count); + return count; +} + +static void snb_uncore_msr_init_box(struct intel_uncore_box *box) +{ + if (box->pmu->pmu_idx == 0) { + wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, + SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL); + } +} + +static struct attribute *snb_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_cmask5.attr, + NULL, +}; + +static struct attribute_group snb_uncore_format_group = { + .name = "format", + .attrs = snb_uncore_formats_attr, +}; + +static struct intel_uncore_ops snb_uncore_msr_ops = { + .init_box = snb_uncore_msr_init_box, + .disable_event = snb_uncore_msr_disable_event, + .enable_event = snb_uncore_msr_enable_event, + .read_counter = snb_uncore_msr_read_counter, +}; + +static struct event_constraint snb_uncore_cbox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x80, 0x1), + UNCORE_EVENT_CONSTRAINT(0x83, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type snb_uncore_cbox = { + .name = "cbox", + .num_counters = 2, + .num_boxes = 4, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = SNB_UNC_CBO_0_PER_CTR0, + .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0, + .fixed_ctr = SNB_UNC_FIXED_CTR, + .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL, + .single_fixed = 1, + .event_mask = SNB_UNC_RAW_EVENT_MASK, + .msr_offset = SNB_UNC_CBO_MSR_OFFSET, + .constraints = snb_uncore_cbox_constraints, + .ops = &snb_uncore_msr_ops, + .format_group = &snb_uncore_format_group, +}; + +static struct intel_uncore_type *snb_msr_uncores[] = { + &snb_uncore_cbox, + NULL, +}; +/* end of Sandy Bridge uncore support */ + +/* Nehalem uncore support */ +static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box) +{ + wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0); +} + +static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, + NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC); +} + +static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx < UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); + else + wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN); +} + +static struct attribute *nhm_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_cmask8.attr, + NULL, +}; + +static struct attribute_group nhm_uncore_format_group = { + .name = "format", + .attrs = nhm_uncore_formats_attr, +}; + +static struct uncore_event_desc nhm_uncore_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any, "event=0x2f,umask=0x0f"), + INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any, "event=0x2c,umask=0x0f"), + INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads, "event=0x20,umask=0x01"), + INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes, "event=0x20,umask=0x02"), + INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads, "event=0x20,umask=0x04"), + INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"), + INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads, "event=0x20,umask=0x10"), + INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes, "event=0x20,umask=0x20"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_ops nhm_uncore_msr_ops = { + .disable_box = nhm_uncore_msr_disable_box, + .enable_box = nhm_uncore_msr_enable_box, + .disable_event = snb_uncore_msr_disable_event, + .enable_event = nhm_uncore_msr_enable_event, + .read_counter = snb_uncore_msr_read_counter, +}; + +static struct intel_uncore_type nhm_uncore = { + .name = "", + .num_counters = 8, + .num_boxes = 1, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .event_ctl = NHM_UNC_PERFEVTSEL0, + .perf_ctr = NHM_UNC_UNCORE_PMC0, + .fixed_ctr = NHM_UNC_FIXED_CTR, + .fixed_ctl = NHM_UNC_FIXED_CTR_CTRL, + .event_mask = NHM_UNC_RAW_EVENT_MASK, + .event_descs = nhm_uncore_events, + .ops = &nhm_uncore_msr_ops, + .format_group = &nhm_uncore_format_group, +}; + +static struct intel_uncore_type *nhm_msr_uncores[] = { + &nhm_uncore, + NULL, +}; +/* end of Nehalem uncore support */ + +static void uncore_assign_hw_event(struct intel_uncore_box *box, + struct perf_event *event, int idx) +{ + struct hw_perf_event *hwc = &event->hw; + + hwc->idx = idx; + hwc->last_tag = ++box->tags[idx]; + + if (hwc->idx == UNCORE_PMC_IDX_FIXED) { + hwc->event_base = uncore_fixed_ctr(box); + hwc->config_base = uncore_fixed_ctl(box); + return; + } + + hwc->config_base = uncore_event_ctl(box, hwc->idx); + hwc->event_base = uncore_perf_ctr(box, hwc->idx); +} + +static void uncore_perf_event_update(struct intel_uncore_box *box, + struct perf_event *event) +{ + u64 prev_count, new_count, delta; + int shift; + + if (event->hw.idx >= UNCORE_PMC_IDX_FIXED) + shift = 64 - uncore_fixed_ctr_bits(box); + else + shift = 64 - uncore_perf_ctr_bits(box); + + /* the hrtimer might modify the previous event value */ +again: + prev_count = local64_read(&event->hw.prev_count); + new_count = uncore_read_counter(box, event); + if (local64_xchg(&event->hw.prev_count, new_count) != prev_count) + goto again; + + delta = (new_count << shift) - (prev_count << shift); + delta >>= shift; + + local64_add(delta, &event->count); +} + +/* + * The overflow interrupt is unavailable for SandyBridge-EP, is broken + * for SandyBridge. So we use hrtimer to periodically poll the counter + * to avoid overflow. + */ +static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer) +{ + struct intel_uncore_box *box; + unsigned long flags; + int bit; + + box = container_of(hrtimer, struct intel_uncore_box, hrtimer); + if (!box->n_active || box->cpu != smp_processor_id()) + return HRTIMER_NORESTART; + /* + * disable local interrupt to prevent uncore_pmu_event_start/stop + * to interrupt the update process + */ + local_irq_save(flags); + + for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX) + uncore_perf_event_update(box, box->events[bit]); + + local_irq_restore(flags); + + hrtimer_forward_now(hrtimer, ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL)); + return HRTIMER_RESTART; +} + +static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box) +{ + __hrtimer_start_range_ns(&box->hrtimer, + ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL), 0, + HRTIMER_MODE_REL_PINNED, 0); +} + +static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box) +{ + hrtimer_cancel(&box->hrtimer); +} + +static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box) +{ + hrtimer_init(&box->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + box->hrtimer.function = uncore_pmu_hrtimer; +} + +struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, + int cpu) +{ + struct intel_uncore_box *box; + int i, size; + + size = sizeof(*box) + type->num_shared_regs * + sizeof(struct intel_uncore_extra_reg); + + box = kmalloc_node(size, GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu)); + if (!box) + return NULL; + + for (i = 0; i < type->num_shared_regs; i++) + raw_spin_lock_init(&box->shared_regs[i].lock); + + uncore_pmu_init_hrtimer(box); + atomic_set(&box->refcnt, 1); + box->cpu = -1; + box->phys_id = -1; + + return box; +} + +static struct intel_uncore_box * +uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) +{ + static struct intel_uncore_box *box; + + box = *per_cpu_ptr(pmu->box, cpu); + if (box) + return box; + + raw_spin_lock(&uncore_box_lock); + list_for_each_entry(box, &pmu->box_list, list) { + if (box->phys_id == topology_physical_package_id(cpu)) { + atomic_inc(&box->refcnt); + *per_cpu_ptr(pmu->box, cpu) = box; + break; + } + } + raw_spin_unlock(&uncore_box_lock); + + return *per_cpu_ptr(pmu->box, cpu); +} + +static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) +{ + return container_of(event->pmu, struct intel_uncore_pmu, pmu); +} + +static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) +{ + /* + * perf core schedules event on the basis of cpu, uncore events are + * collected by one of the cpus inside a physical package. + */ + return uncore_pmu_to_box(uncore_event_to_pmu(event), + smp_processor_id()); +} + +static int uncore_collect_events(struct intel_uncore_box *box, + struct perf_event *leader, bool dogrp) +{ + struct perf_event *event; + int n, max_count; + + max_count = box->pmu->type->num_counters; + if (box->pmu->type->fixed_ctl) + max_count++; + + if (box->n_events >= max_count) + return -EINVAL; + + n = box->n_events; + box->event_list[n] = leader; + n++; + if (!dogrp) + return n; + + list_for_each_entry(event, &leader->sibling_list, group_entry) { + if (event->state <= PERF_EVENT_STATE_OFF) + continue; + + if (n >= max_count) + return -EINVAL; + + box->event_list[n] = event; + n++; + } + return n; +} + +static struct event_constraint * +uncore_get_event_constraint(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct intel_uncore_type *type = box->pmu->type; + struct event_constraint *c; + + if (type->ops->get_constraint) { + c = type->ops->get_constraint(box, event); + if (c) + return c; + } + + if (event->hw.config == ~0ULL) + return &constraint_fixed; + + if (type->constraints) { + for_each_event_constraint(c, type->constraints) { + if ((event->hw.config & c->cmask) == c->code) + return c; + } + } + + return &type->unconstrainted; +} + +static void uncore_put_event_constraint(struct intel_uncore_box *box, + struct perf_event *event) +{ + if (box->pmu->type->ops->put_constraint) + box->pmu->type->ops->put_constraint(box, event); +} + +static int uncore_assign_events(struct intel_uncore_box *box, + int assign[], int n) +{ + unsigned long used_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)]; + struct event_constraint *c, *constraints[UNCORE_PMC_IDX_MAX]; + int i, wmin, wmax, ret = 0; + struct hw_perf_event *hwc; + + bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX); + + for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) { + c = uncore_get_event_constraint(box, box->event_list[i]); + constraints[i] = c; + wmin = min(wmin, c->weight); + wmax = max(wmax, c->weight); + } + + /* fastpath, try to reuse previous register */ + for (i = 0; i < n; i++) { + hwc = &box->event_list[i]->hw; + c = constraints[i]; + + /* never assigned */ + if (hwc->idx == -1) + break; + + /* constraint still honored */ + if (!test_bit(hwc->idx, c->idxmsk)) + break; + + /* not already used */ + if (test_bit(hwc->idx, used_mask)) + break; + + __set_bit(hwc->idx, used_mask); + if (assign) + assign[i] = hwc->idx; + } + /* slow path */ + if (i != n) + ret = perf_assign_events(constraints, n, wmin, wmax, assign); + + if (!assign || ret) { + for (i = 0; i < n; i++) + uncore_put_event_constraint(box, box->event_list[i]); + } + return ret ? -EINVAL : 0; +} + +static void uncore_pmu_event_start(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + int idx = event->hw.idx; + + if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + return; + + if (WARN_ON_ONCE(idx == -1 || idx >= UNCORE_PMC_IDX_MAX)) + return; + + event->hw.state = 0; + box->events[idx] = event; + box->n_active++; + __set_bit(idx, box->active_mask); + + local64_set(&event->hw.prev_count, uncore_read_counter(box, event)); + uncore_enable_event(box, event); + + if (box->n_active == 1) { + uncore_enable_box(box); + uncore_pmu_start_hrtimer(box); + } +} + +static void uncore_pmu_event_stop(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + + if (__test_and_clear_bit(hwc->idx, box->active_mask)) { + uncore_disable_event(box, event); + box->n_active--; + box->events[hwc->idx] = NULL; + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + + if (box->n_active == 0) { + uncore_disable_box(box); + uncore_pmu_cancel_hrtimer(box); + } + } + + if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + /* + * Drain the remaining delta count out of a event + * that we are disabling: + */ + uncore_perf_event_update(box, event); + hwc->state |= PERF_HES_UPTODATE; + } +} + +static int uncore_pmu_event_add(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + int assign[UNCORE_PMC_IDX_MAX]; + int i, n, ret; + + if (!box) + return -ENODEV; + + ret = n = uncore_collect_events(box, event, false); + if (ret < 0) + return ret; + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + if (!(flags & PERF_EF_START)) + hwc->state |= PERF_HES_ARCH; + + ret = uncore_assign_events(box, assign, n); + if (ret) + return ret; + + /* save events moving to new counters */ + for (i = 0; i < box->n_events; i++) { + event = box->event_list[i]; + hwc = &event->hw; + + if (hwc->idx == assign[i] && + hwc->last_tag == box->tags[assign[i]]) + continue; + /* + * Ensure we don't accidentally enable a stopped + * counter simply because we rescheduled. + */ + if (hwc->state & PERF_HES_STOPPED) + hwc->state |= PERF_HES_ARCH; + + uncore_pmu_event_stop(event, PERF_EF_UPDATE); + } + + /* reprogram moved events into new counters */ + for (i = 0; i < n; i++) { + event = box->event_list[i]; + hwc = &event->hw; + + if (hwc->idx != assign[i] || + hwc->last_tag != box->tags[assign[i]]) + uncore_assign_hw_event(box, event, assign[i]); + else if (i < box->n_events) + continue; + + if (hwc->state & PERF_HES_ARCH) + continue; + + uncore_pmu_event_start(event, 0); + } + box->n_events = n; + + return 0; +} + +static void uncore_pmu_event_del(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + int i; + + uncore_pmu_event_stop(event, PERF_EF_UPDATE); + + for (i = 0; i < box->n_events; i++) { + if (event == box->event_list[i]) { + uncore_put_event_constraint(box, event); + + while (++i < box->n_events) + box->event_list[i - 1] = box->event_list[i]; + + --box->n_events; + break; + } + } + + event->hw.idx = -1; + event->hw.last_tag = ~0ULL; +} + +static void uncore_pmu_event_read(struct perf_event *event) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + uncore_perf_event_update(box, event); +} + +/* + * validation ensures the group can be loaded onto the + * PMU if it was the only group available. + */ +static int uncore_validate_group(struct intel_uncore_pmu *pmu, + struct perf_event *event) +{ + struct perf_event *leader = event->group_leader; + struct intel_uncore_box *fake_box; + int ret = -EINVAL, n; + + fake_box = uncore_alloc_box(pmu->type, smp_processor_id()); + if (!fake_box) + return -ENOMEM; + + fake_box->pmu = pmu; + /* + * the event is not yet connected with its + * siblings therefore we must first collect + * existing siblings, then add the new event + * before we can simulate the scheduling + */ + n = uncore_collect_events(fake_box, leader, true); + if (n < 0) + goto out; + + fake_box->n_events = n; + n = uncore_collect_events(fake_box, event, false); + if (n < 0) + goto out; + + fake_box->n_events = n; + + ret = uncore_assign_events(fake_box, NULL, n); +out: + kfree(fake_box); + return ret; +} + +int uncore_pmu_event_init(struct perf_event *event) +{ + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + struct hw_perf_event *hwc = &event->hw; + int ret; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + pmu = uncore_event_to_pmu(event); + /* no device found for this pmu */ + if (pmu->func_id < 0) + return -ENOENT; + + /* + * Uncore PMU does measure at all privilege level all the time. + * So it doesn't make sense to specify any exclude bits. + */ + if (event->attr.exclude_user || event->attr.exclude_kernel || + event->attr.exclude_hv || event->attr.exclude_idle) + return -EINVAL; + + /* Sampling not supported yet */ + if (hwc->sample_period) + return -EINVAL; + + /* + * Place all uncore events for a particular physical package + * onto a single cpu + */ + if (event->cpu < 0) + return -EINVAL; + box = uncore_pmu_to_box(pmu, event->cpu); + if (!box || box->cpu < 0) + return -EINVAL; + event->cpu = box->cpu; + + event->hw.idx = -1; + event->hw.last_tag = ~0ULL; + event->hw.extra_reg.idx = EXTRA_REG_NONE; + + if (event->attr.config == UNCORE_FIXED_EVENT) { + /* no fixed counter */ + if (!pmu->type->fixed_ctl) + return -EINVAL; + /* + * if there is only one fixed counter, only the first pmu + * can access the fixed counter + */ + if (pmu->type->single_fixed && pmu->pmu_idx > 0) + return -EINVAL; + hwc->config = ~0ULL; + } else { + hwc->config = event->attr.config & pmu->type->event_mask; + if (pmu->type->ops->hw_config) { + ret = pmu->type->ops->hw_config(box, event); + if (ret) + return ret; + } + } + + if (event->group_leader != event) + ret = uncore_validate_group(pmu, event); + else + ret = 0; + + return ret; +} + +static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu) +{ + int ret; + + pmu->pmu = (struct pmu) { + .attr_groups = pmu->type->attr_groups, + .task_ctx_nr = perf_invalid_context, + .event_init = uncore_pmu_event_init, + .add = uncore_pmu_event_add, + .del = uncore_pmu_event_del, + .start = uncore_pmu_event_start, + .stop = uncore_pmu_event_stop, + .read = uncore_pmu_event_read, + }; + + if (pmu->type->num_boxes == 1) { + if (strlen(pmu->type->name) > 0) + sprintf(pmu->name, "uncore_%s", pmu->type->name); + else + sprintf(pmu->name, "uncore"); + } else { + sprintf(pmu->name, "uncore_%s_%d", pmu->type->name, + pmu->pmu_idx); + } + + ret = perf_pmu_register(&pmu->pmu, pmu->name, -1); + return ret; +} + +static void __init uncore_type_exit(struct intel_uncore_type *type) +{ + int i; + + for (i = 0; i < type->num_boxes; i++) + free_percpu(type->pmus[i].box); + kfree(type->pmus); + type->pmus = NULL; + kfree(type->attr_groups[1]); + type->attr_groups[1] = NULL; +} + +static void uncore_types_exit(struct intel_uncore_type **types) +{ + int i; + for (i = 0; types[i]; i++) + uncore_type_exit(types[i]); +} + +static int __init uncore_type_init(struct intel_uncore_type *type) +{ + struct intel_uncore_pmu *pmus; + struct attribute_group *events_group; + struct attribute **attrs; + int i, j; + + pmus = kzalloc(sizeof(*pmus) * type->num_boxes, GFP_KERNEL); + if (!pmus) + return -ENOMEM; + + type->unconstrainted = (struct event_constraint) + __EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1, + 0, type->num_counters, 0); + + for (i = 0; i < type->num_boxes; i++) { + pmus[i].func_id = -1; + pmus[i].pmu_idx = i; + pmus[i].type = type; + INIT_LIST_HEAD(&pmus[i].box_list); + pmus[i].box = alloc_percpu(struct intel_uncore_box *); + if (!pmus[i].box) + goto fail; + } + + if (type->event_descs) { + i = 0; + while (type->event_descs[i].attr.attr.name) + i++; + + events_group = kzalloc(sizeof(struct attribute *) * (i + 1) + + sizeof(*events_group), GFP_KERNEL); + if (!events_group) + goto fail; + + attrs = (struct attribute **)(events_group + 1); + events_group->name = "events"; + events_group->attrs = attrs; + + for (j = 0; j < i; j++) + attrs[j] = &type->event_descs[j].attr.attr; + + type->attr_groups[1] = events_group; + } + + type->pmus = pmus; + return 0; +fail: + uncore_type_exit(type); + return -ENOMEM; +} + +static int __init uncore_types_init(struct intel_uncore_type **types) +{ + int i, ret; + + for (i = 0; types[i]; i++) { + ret = uncore_type_init(types[i]); + if (ret) + goto fail; + } + return 0; +fail: + while (--i >= 0) + uncore_type_exit(types[i]); + return ret; +} + +static struct pci_driver *uncore_pci_driver; +static bool pcidrv_registered; + +/* + * add a pci uncore device + */ +static int __devinit uncore_pci_add(struct intel_uncore_type *type, + struct pci_dev *pdev) +{ + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, phys_id; + + phys_id = pcibus_to_physid[pdev->bus->number]; + if (phys_id < 0) + return -ENODEV; + + box = uncore_alloc_box(type, 0); + if (!box) + return -ENOMEM; + + /* + * for performance monitoring unit with multiple boxes, + * each box has a different function id. + */ + for (i = 0; i < type->num_boxes; i++) { + pmu = &type->pmus[i]; + if (pmu->func_id == pdev->devfn) + break; + if (pmu->func_id < 0) { + pmu->func_id = pdev->devfn; + break; + } + pmu = NULL; + } + + if (!pmu) { + kfree(box); + return -EINVAL; + } + + box->phys_id = phys_id; + box->pci_dev = pdev; + box->pmu = pmu; + uncore_box_init(box); + pci_set_drvdata(pdev, box); + + raw_spin_lock(&uncore_box_lock); + list_add_tail(&box->list, &pmu->box_list); + raw_spin_unlock(&uncore_box_lock); + + return 0; +} + +static void uncore_pci_remove(struct pci_dev *pdev) +{ + struct intel_uncore_box *box = pci_get_drvdata(pdev); + struct intel_uncore_pmu *pmu = box->pmu; + int cpu, phys_id = pcibus_to_physid[pdev->bus->number]; + + if (WARN_ON_ONCE(phys_id != box->phys_id)) + return; + + raw_spin_lock(&uncore_box_lock); + list_del(&box->list); + raw_spin_unlock(&uncore_box_lock); + + for_each_possible_cpu(cpu) { + if (*per_cpu_ptr(pmu->box, cpu) == box) { + *per_cpu_ptr(pmu->box, cpu) = NULL; + atomic_dec(&box->refcnt); + } + } + + WARN_ON_ONCE(atomic_read(&box->refcnt) != 1); + kfree(box); +} + +static int __devinit uncore_pci_probe(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + struct intel_uncore_type *type; + + type = (struct intel_uncore_type *)id->driver_data; + return uncore_pci_add(type, pdev); +} + +static int __init uncore_pci_init(void) +{ + int ret; + + switch (boot_cpu_data.x86_model) { + case 45: /* Sandy Bridge-EP */ + pci_uncores = snbep_pci_uncores; + uncore_pci_driver = &snbep_uncore_pci_driver; + snbep_pci2phy_map_init(); + break; + default: + return 0; + } + + ret = uncore_types_init(pci_uncores); + if (ret) + return ret; + + uncore_pci_driver->probe = uncore_pci_probe; + uncore_pci_driver->remove = uncore_pci_remove; + + ret = pci_register_driver(uncore_pci_driver); + if (ret == 0) + pcidrv_registered = true; + else + uncore_types_exit(pci_uncores); + + return ret; +} + +static void __init uncore_pci_exit(void) +{ + if (pcidrv_registered) { + pcidrv_registered = false; + pci_unregister_driver(uncore_pci_driver); + uncore_types_exit(pci_uncores); + } +} + +static void __cpuinit uncore_cpu_dying(int cpu) +{ + struct intel_uncore_type *type; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, j; + + for (i = 0; msr_uncores[i]; i++) { + type = msr_uncores[i]; + for (j = 0; j < type->num_boxes; j++) { + pmu = &type->pmus[j]; + box = *per_cpu_ptr(pmu->box, cpu); + *per_cpu_ptr(pmu->box, cpu) = NULL; + if (box && atomic_dec_and_test(&box->refcnt)) + kfree(box); + } + } +} + +static int __cpuinit uncore_cpu_starting(int cpu) +{ + struct intel_uncore_type *type; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box, *exist; + int i, j, k, phys_id; + + phys_id = topology_physical_package_id(cpu); + + for (i = 0; msr_uncores[i]; i++) { + type = msr_uncores[i]; + for (j = 0; j < type->num_boxes; j++) { + pmu = &type->pmus[j]; + box = *per_cpu_ptr(pmu->box, cpu); + /* called by uncore_cpu_init? */ + if (box && box->phys_id >= 0) { + uncore_box_init(box); + continue; + } + + for_each_online_cpu(k) { + exist = *per_cpu_ptr(pmu->box, k); + if (exist && exist->phys_id == phys_id) { + atomic_inc(&exist->refcnt); + *per_cpu_ptr(pmu->box, cpu) = exist; + kfree(box); + box = NULL; + break; + } + } + + if (box) { + box->phys_id = phys_id; + uncore_box_init(box); + } + } + } + return 0; +} + +static int __cpuinit uncore_cpu_prepare(int cpu, int phys_id) +{ + struct intel_uncore_type *type; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, j; + + for (i = 0; msr_uncores[i]; i++) { + type = msr_uncores[i]; + for (j = 0; j < type->num_boxes; j++) { + pmu = &type->pmus[j]; + if (pmu->func_id < 0) + pmu->func_id = j; + + box = uncore_alloc_box(type, cpu); + if (!box) + return -ENOMEM; + + box->pmu = pmu; + box->phys_id = phys_id; + *per_cpu_ptr(pmu->box, cpu) = box; + } + } + return 0; +} + +static void __cpuinit uncore_change_context(struct intel_uncore_type **uncores, + int old_cpu, int new_cpu) +{ + struct intel_uncore_type *type; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, j; + + for (i = 0; uncores[i]; i++) { + type = uncores[i]; + for (j = 0; j < type->num_boxes; j++) { + pmu = &type->pmus[j]; + if (old_cpu < 0) + box = uncore_pmu_to_box(pmu, new_cpu); + else + box = uncore_pmu_to_box(pmu, old_cpu); + if (!box) + continue; + + if (old_cpu < 0) { + WARN_ON_ONCE(box->cpu != -1); + box->cpu = new_cpu; + continue; + } + + WARN_ON_ONCE(box->cpu != old_cpu); + if (new_cpu >= 0) { + uncore_pmu_cancel_hrtimer(box); + perf_pmu_migrate_context(&pmu->pmu, + old_cpu, new_cpu); + box->cpu = new_cpu; + } else { + box->cpu = -1; + } + } + } +} + +static void __cpuinit uncore_event_exit_cpu(int cpu) +{ + int i, phys_id, target; + + /* if exiting cpu is used for collecting uncore events */ + if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask)) + return; + + /* find a new cpu to collect uncore events */ + phys_id = topology_physical_package_id(cpu); + target = -1; + for_each_online_cpu(i) { + if (i == cpu) + continue; + if (phys_id == topology_physical_package_id(i)) { + target = i; + break; + } + } + + /* migrate uncore events to the new cpu */ + if (target >= 0) + cpumask_set_cpu(target, &uncore_cpu_mask); + + uncore_change_context(msr_uncores, cpu, target); + uncore_change_context(pci_uncores, cpu, target); +} + +static void __cpuinit uncore_event_init_cpu(int cpu) +{ + int i, phys_id; + + phys_id = topology_physical_package_id(cpu); + for_each_cpu(i, &uncore_cpu_mask) { + if (phys_id == topology_physical_package_id(i)) + return; + } + + cpumask_set_cpu(cpu, &uncore_cpu_mask); + + uncore_change_context(msr_uncores, -1, cpu); + uncore_change_context(pci_uncores, -1, cpu); +} + +static int __cpuinit uncore_cpu_notifier(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + /* allocate/free data structure for uncore box */ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + uncore_cpu_prepare(cpu, -1); + break; + case CPU_STARTING: + uncore_cpu_starting(cpu); + break; + case CPU_UP_CANCELED: + case CPU_DYING: + uncore_cpu_dying(cpu); + break; + default: + break; + } + + /* select the cpu that collects uncore events */ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_FAILED: + case CPU_STARTING: + uncore_event_init_cpu(cpu); + break; + case CPU_DOWN_PREPARE: + uncore_event_exit_cpu(cpu); + break; + default: + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block uncore_cpu_nb __cpuinitdata = { + .notifier_call = uncore_cpu_notifier, + /* + * to migrate uncore events, our notifier should be executed + * before perf core's notifier. + */ + .priority = CPU_PRI_PERF + 1, +}; + +static void __init uncore_cpu_setup(void *dummy) +{ + uncore_cpu_starting(smp_processor_id()); +} + +static int __init uncore_cpu_init(void) +{ + int ret, cpu, max_cores; + + max_cores = boot_cpu_data.x86_max_cores; + switch (boot_cpu_data.x86_model) { + case 26: /* Nehalem */ + case 30: + case 37: /* Westmere */ + case 44: + msr_uncores = nhm_msr_uncores; + break; + case 42: /* Sandy Bridge */ + if (snb_uncore_cbox.num_boxes > max_cores) + snb_uncore_cbox.num_boxes = max_cores; + msr_uncores = snb_msr_uncores; + break; + case 45: /* Sandy Birdge-EP */ + if (snbep_uncore_cbox.num_boxes > max_cores) + snbep_uncore_cbox.num_boxes = max_cores; + msr_uncores = snbep_msr_uncores; + break; + default: + return 0; + } + + ret = uncore_types_init(msr_uncores); + if (ret) + return ret; + + get_online_cpus(); + + for_each_online_cpu(cpu) { + int i, phys_id = topology_physical_package_id(cpu); + + for_each_cpu(i, &uncore_cpu_mask) { + if (phys_id == topology_physical_package_id(i)) { + phys_id = -1; + break; + } + } + if (phys_id < 0) + continue; + + uncore_cpu_prepare(cpu, phys_id); + uncore_event_init_cpu(cpu); + } + on_each_cpu(uncore_cpu_setup, NULL, 1); + + register_cpu_notifier(&uncore_cpu_nb); + + put_online_cpus(); + + return 0; +} + +static int __init uncore_pmus_register(void) +{ + struct intel_uncore_pmu *pmu; + struct intel_uncore_type *type; + int i, j; + + for (i = 0; msr_uncores[i]; i++) { + type = msr_uncores[i]; + for (j = 0; j < type->num_boxes; j++) { + pmu = &type->pmus[j]; + uncore_pmu_register(pmu); + } + } + + for (i = 0; pci_uncores[i]; i++) { + type = pci_uncores[i]; + for (j = 0; j < type->num_boxes; j++) { + pmu = &type->pmus[j]; + uncore_pmu_register(pmu); + } + } + + return 0; +} + +static int __init intel_uncore_init(void) +{ + int ret; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return -ENODEV; + + ret = uncore_pci_init(); + if (ret) + goto fail; + ret = uncore_cpu_init(); + if (ret) { + uncore_pci_exit(); + goto fail; + } + + uncore_pmus_register(); + return 0; +fail: + return ret; +} +device_initcall(intel_uncore_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h new file mode 100644 index 000000000000..b13e9ea81def --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -0,0 +1,424 @@ +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/pci.h> +#include <linux/perf_event.h> +#include "perf_event.h" + +#define UNCORE_PMU_NAME_LEN 32 +#define UNCORE_BOX_HASH_SIZE 8 + +#define UNCORE_PMU_HRTIMER_INTERVAL (60 * NSEC_PER_SEC) + +#define UNCORE_FIXED_EVENT 0xff +#define UNCORE_PMC_IDX_MAX_GENERIC 8 +#define UNCORE_PMC_IDX_FIXED UNCORE_PMC_IDX_MAX_GENERIC +#define UNCORE_PMC_IDX_MAX (UNCORE_PMC_IDX_FIXED + 1) + +#define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) + +/* SNB event control */ +#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff +#define SNB_UNC_CTL_UMASK_MASK 0x0000ff00 +#define SNB_UNC_CTL_EDGE_DET (1 << 18) +#define SNB_UNC_CTL_EN (1 << 22) +#define SNB_UNC_CTL_INVERT (1 << 23) +#define SNB_UNC_CTL_CMASK_MASK 0x1f000000 +#define NHM_UNC_CTL_CMASK_MASK 0xff000000 +#define NHM_UNC_FIXED_CTR_CTL_EN (1 << 0) + +#define SNB_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ + SNB_UNC_CTL_UMASK_MASK | \ + SNB_UNC_CTL_EDGE_DET | \ + SNB_UNC_CTL_INVERT | \ + SNB_UNC_CTL_CMASK_MASK) + +#define NHM_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ + SNB_UNC_CTL_UMASK_MASK | \ + SNB_UNC_CTL_EDGE_DET | \ + SNB_UNC_CTL_INVERT | \ + NHM_UNC_CTL_CMASK_MASK) + +/* SNB global control register */ +#define SNB_UNC_PERF_GLOBAL_CTL 0x391 +#define SNB_UNC_FIXED_CTR_CTRL 0x394 +#define SNB_UNC_FIXED_CTR 0x395 + +/* SNB uncore global control */ +#define SNB_UNC_GLOBAL_CTL_CORE_ALL ((1 << 4) - 1) +#define SNB_UNC_GLOBAL_CTL_EN (1 << 29) + +/* SNB Cbo register */ +#define SNB_UNC_CBO_0_PERFEVTSEL0 0x700 +#define SNB_UNC_CBO_0_PER_CTR0 0x706 +#define SNB_UNC_CBO_MSR_OFFSET 0x10 + +/* NHM global control register */ +#define NHM_UNC_PERF_GLOBAL_CTL 0x391 +#define NHM_UNC_FIXED_CTR 0x394 +#define NHM_UNC_FIXED_CTR_CTRL 0x395 + +/* NHM uncore global control */ +#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL ((1ULL << 8) - 1) +#define NHM_UNC_GLOBAL_CTL_EN_FC (1ULL << 32) + +/* NHM uncore register */ +#define NHM_UNC_PERFEVTSEL0 0x3c0 +#define NHM_UNC_UNCORE_PMC0 0x3b0 + +/* SNB-EP Box level control */ +#define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0) +#define SNBEP_PMON_BOX_CTL_RST_CTRS (1 << 1) +#define SNBEP_PMON_BOX_CTL_FRZ (1 << 8) +#define SNBEP_PMON_BOX_CTL_FRZ_EN (1 << 16) +#define SNBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ + SNBEP_PMON_BOX_CTL_RST_CTRS | \ + SNBEP_PMON_BOX_CTL_FRZ_EN) +/* SNB-EP event control */ +#define SNBEP_PMON_CTL_EV_SEL_MASK 0x000000ff +#define SNBEP_PMON_CTL_UMASK_MASK 0x0000ff00 +#define SNBEP_PMON_CTL_RST (1 << 17) +#define SNBEP_PMON_CTL_EDGE_DET (1 << 18) +#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21) /* only for QPI */ +#define SNBEP_PMON_CTL_EN (1 << 22) +#define SNBEP_PMON_CTL_INVERT (1 << 23) +#define SNBEP_PMON_CTL_TRESH_MASK 0xff000000 +#define SNBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_INVERT | \ + SNBEP_PMON_CTL_TRESH_MASK) + +/* SNB-EP Ubox event control */ +#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK 0x1f000000 +#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_INVERT | \ + SNBEP_U_MSR_PMON_CTL_TRESH_MASK) + +#define SNBEP_CBO_PMON_CTL_TID_EN (1 << 19) +#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) + +/* SNB-EP PCU event control */ +#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK 0x0000c000 +#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK 0x1f000000 +#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT (1 << 30) +#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET (1 << 31) +#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) + +/* SNB-EP pci control register */ +#define SNBEP_PCI_PMON_BOX_CTL 0xf4 +#define SNBEP_PCI_PMON_CTL0 0xd8 +/* SNB-EP pci counter register */ +#define SNBEP_PCI_PMON_CTR0 0xa0 + +/* SNB-EP home agent register */ +#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0 0x40 +#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1 0x44 +#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH 0x48 +/* SNB-EP memory controller register */ +#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL 0xf0 +#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR 0xd0 +/* SNB-EP QPI register */ +#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0 0x228 +#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1 0x22c +#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0 0x238 +#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1 0x23c + +/* SNB-EP Ubox register */ +#define SNBEP_U_MSR_PMON_CTR0 0xc16 +#define SNBEP_U_MSR_PMON_CTL0 0xc10 + +#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL 0xc08 +#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR 0xc09 + +/* SNB-EP Cbo register */ +#define SNBEP_C0_MSR_PMON_CTR0 0xd16 +#define SNBEP_C0_MSR_PMON_CTL0 0xd10 +#define SNBEP_C0_MSR_PMON_BOX_CTL 0xd04 +#define SNBEP_C0_MSR_PMON_BOX_FILTER 0xd14 +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK 0xfffffc1f +#define SNBEP_CBO_MSR_OFFSET 0x20 + +/* SNB-EP PCU register */ +#define SNBEP_PCU_MSR_PMON_CTR0 0xc36 +#define SNBEP_PCU_MSR_PMON_CTL0 0xc30 +#define SNBEP_PCU_MSR_PMON_BOX_CTL 0xc24 +#define SNBEP_PCU_MSR_PMON_BOX_FILTER 0xc34 +#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK 0xffffffff +#define SNBEP_PCU_MSR_CORE_C3_CTR 0x3fc +#define SNBEP_PCU_MSR_CORE_C6_CTR 0x3fd + +struct intel_uncore_ops; +struct intel_uncore_pmu; +struct intel_uncore_box; +struct uncore_event_desc; + +struct intel_uncore_type { + const char *name; + int num_counters; + int num_boxes; + int perf_ctr_bits; + int fixed_ctr_bits; + unsigned perf_ctr; + unsigned event_ctl; + unsigned event_mask; + unsigned fixed_ctr; + unsigned fixed_ctl; + unsigned box_ctl; + unsigned msr_offset; + unsigned num_shared_regs:8; + unsigned single_fixed:1; + struct event_constraint unconstrainted; + struct event_constraint *constraints; + struct intel_uncore_pmu *pmus; + struct intel_uncore_ops *ops; + struct uncore_event_desc *event_descs; + const struct attribute_group *attr_groups[3]; +}; + +#define format_group attr_groups[0] + +struct intel_uncore_ops { + void (*init_box)(struct intel_uncore_box *); + void (*disable_box)(struct intel_uncore_box *); + void (*enable_box)(struct intel_uncore_box *); + void (*disable_event)(struct intel_uncore_box *, struct perf_event *); + void (*enable_event)(struct intel_uncore_box *, struct perf_event *); + u64 (*read_counter)(struct intel_uncore_box *, struct perf_event *); + int (*hw_config)(struct intel_uncore_box *, struct perf_event *); + struct event_constraint *(*get_constraint)(struct intel_uncore_box *, + struct perf_event *); + void (*put_constraint)(struct intel_uncore_box *, struct perf_event *); +}; + +struct intel_uncore_pmu { + struct pmu pmu; + char name[UNCORE_PMU_NAME_LEN]; + int pmu_idx; + int func_id; + struct intel_uncore_type *type; + struct intel_uncore_box ** __percpu box; + struct list_head box_list; +}; + +struct intel_uncore_extra_reg { + raw_spinlock_t lock; + u64 config1; + atomic_t ref; +}; + +struct intel_uncore_box { + int phys_id; + int n_active; /* number of active events */ + int n_events; + int cpu; /* cpu to collect events */ + unsigned long flags; + atomic_t refcnt; + struct perf_event *events[UNCORE_PMC_IDX_MAX]; + struct perf_event *event_list[UNCORE_PMC_IDX_MAX]; + unsigned long active_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)]; + u64 tags[UNCORE_PMC_IDX_MAX]; + struct pci_dev *pci_dev; + struct intel_uncore_pmu *pmu; + struct hrtimer hrtimer; + struct list_head list; + struct intel_uncore_extra_reg shared_regs[0]; +}; + +#define UNCORE_BOX_FLAG_INITIATED 0 + +struct uncore_event_desc { + struct kobj_attribute attr; + const char *config; +}; + +#define INTEL_UNCORE_EVENT_DESC(_name, _config) \ +{ \ + .attr = __ATTR(_name, 0444, uncore_event_show, NULL), \ + .config = _config, \ +} + +#define DEFINE_UNCORE_FORMAT_ATTR(_var, _name, _format) \ +static ssize_t __uncore_##_var##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + char *page) \ +{ \ + BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ + return sprintf(page, _format "\n"); \ +} \ +static struct kobj_attribute format_attr_##_var = \ + __ATTR(_name, 0444, __uncore_##_var##_show, NULL) + + +static ssize_t uncore_event_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct uncore_event_desc *event = + container_of(attr, struct uncore_event_desc, attr); + return sprintf(buf, "%s", event->config); +} + +static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box) +{ + return box->pmu->type->box_ctl; +} + +static inline unsigned uncore_pci_fixed_ctl(struct intel_uncore_box *box) +{ + return box->pmu->type->fixed_ctl; +} + +static inline unsigned uncore_pci_fixed_ctr(struct intel_uncore_box *box) +{ + return box->pmu->type->fixed_ctr; +} + +static inline +unsigned uncore_pci_event_ctl(struct intel_uncore_box *box, int idx) +{ + return idx * 4 + box->pmu->type->event_ctl; +} + +static inline +unsigned uncore_pci_perf_ctr(struct intel_uncore_box *box, int idx) +{ + return idx * 8 + box->pmu->type->perf_ctr; +} + +static inline +unsigned uncore_msr_box_ctl(struct intel_uncore_box *box) +{ + if (!box->pmu->type->box_ctl) + return 0; + return box->pmu->type->box_ctl + + box->pmu->type->msr_offset * box->pmu->pmu_idx; +} + +static inline +unsigned uncore_msr_fixed_ctl(struct intel_uncore_box *box) +{ + if (!box->pmu->type->fixed_ctl) + return 0; + return box->pmu->type->fixed_ctl + + box->pmu->type->msr_offset * box->pmu->pmu_idx; +} + +static inline +unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box) +{ + return box->pmu->type->fixed_ctr + + box->pmu->type->msr_offset * box->pmu->pmu_idx; +} + +static inline +unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx) +{ + return idx + box->pmu->type->event_ctl + + box->pmu->type->msr_offset * box->pmu->pmu_idx; +} + +static inline +unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx) +{ + return idx + box->pmu->type->perf_ctr + + box->pmu->type->msr_offset * box->pmu->pmu_idx; +} + +static inline +unsigned uncore_fixed_ctl(struct intel_uncore_box *box) +{ + if (box->pci_dev) + return uncore_pci_fixed_ctl(box); + else + return uncore_msr_fixed_ctl(box); +} + +static inline +unsigned uncore_fixed_ctr(struct intel_uncore_box *box) +{ + if (box->pci_dev) + return uncore_pci_fixed_ctr(box); + else + return uncore_msr_fixed_ctr(box); +} + +static inline +unsigned uncore_event_ctl(struct intel_uncore_box *box, int idx) +{ + if (box->pci_dev) + return uncore_pci_event_ctl(box, idx); + else + return uncore_msr_event_ctl(box, idx); +} + +static inline +unsigned uncore_perf_ctr(struct intel_uncore_box *box, int idx) +{ + if (box->pci_dev) + return uncore_pci_perf_ctr(box, idx); + else + return uncore_msr_perf_ctr(box, idx); +} + +static inline int uncore_perf_ctr_bits(struct intel_uncore_box *box) +{ + return box->pmu->type->perf_ctr_bits; +} + +static inline int uncore_fixed_ctr_bits(struct intel_uncore_box *box) +{ + return box->pmu->type->fixed_ctr_bits; +} + +static inline int uncore_num_counters(struct intel_uncore_box *box) +{ + return box->pmu->type->num_counters; +} + +static inline void uncore_disable_box(struct intel_uncore_box *box) +{ + if (box->pmu->type->ops->disable_box) + box->pmu->type->ops->disable_box(box); +} + +static inline void uncore_enable_box(struct intel_uncore_box *box) +{ + if (box->pmu->type->ops->enable_box) + box->pmu->type->ops->enable_box(box); +} + +static inline void uncore_disable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + box->pmu->type->ops->disable_event(box, event); +} + +static inline void uncore_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + box->pmu->type->ops->enable_event(box, event); +} + +static inline u64 uncore_read_counter(struct intel_uncore_box *box, + struct perf_event *event) +{ + return box->pmu->type->ops->read_counter(box, event); +} + +static inline void uncore_box_init(struct intel_uncore_box *box) +{ + if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { + if (box->pmu->type->ops->init_box) + box->pmu->type->ops->init_box(box); + } +} diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index 47124a73dd73..92c7e39a079f 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -895,8 +895,8 @@ static void p4_pmu_disable_pebs(void) * So at moment let leave metrics turned on forever -- it's * ok for now but need to be revisited! * - * (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)0); - * (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)0); + * (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, (u64)0); + * (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, (u64)0); */ } @@ -909,7 +909,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event) * state we need to clear P4_CCCR_OVF, otherwise interrupt get * asserted again and again */ - (void)checking_wrmsrl(hwc->config_base, + (void)wrmsrl_safe(hwc->config_base, (u64)(p4_config_unpack_cccr(hwc->config)) & ~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED); } @@ -943,8 +943,8 @@ static void p4_pmu_enable_pebs(u64 config) bind = &p4_pebs_bind_map[idx]; - (void)checking_wrmsrl(MSR_IA32_PEBS_ENABLE, (u64)bind->metric_pebs); - (void)checking_wrmsrl(MSR_P4_PEBS_MATRIX_VERT, (u64)bind->metric_vert); + (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, (u64)bind->metric_pebs); + (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, (u64)bind->metric_vert); } static void p4_pmu_enable_event(struct perf_event *event) @@ -978,8 +978,8 @@ static void p4_pmu_enable_event(struct perf_event *event) */ p4_pmu_enable_pebs(hwc->config); - (void)checking_wrmsrl(escr_addr, escr_conf); - (void)checking_wrmsrl(hwc->config_base, + (void)wrmsrl_safe(escr_addr, escr_conf); + (void)wrmsrl_safe(hwc->config_base, (cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE); } @@ -1325,7 +1325,7 @@ __init int p4_pmu_init(void) unsigned int low, high; /* If we get stripped -- indexing fails */ - BUILD_BUG_ON(ARCH_P4_MAX_CCCR > X86_PMC_MAX_GENERIC); + BUILD_BUG_ON(ARCH_P4_MAX_CCCR > INTEL_PMC_MAX_GENERIC); rdmsr(MSR_IA32_MISC_ENABLE, low, high); if (!(low & (1 << 7))) { diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index 32bcfc7dd230..e4dd0f7a0453 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -71,7 +71,7 @@ p6_pmu_disable_event(struct perf_event *event) if (cpuc->enabled) val |= ARCH_PERFMON_EVENTSEL_ENABLE; - (void)checking_wrmsrl(hwc->config_base, val); + (void)wrmsrl_safe(hwc->config_base, val); } static void p6_pmu_enable_event(struct perf_event *event) @@ -84,7 +84,7 @@ static void p6_pmu_enable_event(struct perf_event *event) if (cpuc->enabled) val |= ARCH_PERFMON_EVENTSEL_ENABLE; - (void)checking_wrmsrl(hwc->config_base, val); + (void)wrmsrl_safe(hwc->config_base, val); } PMU_FORMAT_ATTR(event, "config:0-7" ); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 571246d81edf..ae42418bc50f 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -27,8 +27,8 @@ static int die_counter; void printk_address(unsigned long address, int reliable) { - printk(" [<%p>] %s%pB\n", (void *) address, - reliable ? "" : "? ", (void *) address); + pr_cont(" [<%p>] %s%pB\n", + (void *)address, reliable ? "" : "? ", (void *)address); } #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -271,6 +271,7 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err) current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP) return 1; + print_modules(); show_regs(regs); #ifdef CONFIG_X86_32 if (user_mode_vm(regs)) { diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index e0b1d783daab..1038a417ea53 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -73,11 +73,11 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, if (kstack_end(stack)) break; if (i && ((i % STACKSLOTS_PER_LINE) == 0)) - printk(KERN_CONT "\n"); - printk(KERN_CONT " %08lx", *stack++); + pr_cont("\n"); + pr_cont(" %08lx", *stack++); touch_nmi_watchdog(); } - printk(KERN_CONT "\n"); + pr_cont("\n"); show_trace_log_lvl(task, regs, sp, bp, log_lvl); } @@ -86,12 +86,11 @@ void show_regs(struct pt_regs *regs) { int i; - print_modules(); __show_regs(regs, !user_mode_vm(regs)); - printk(KERN_EMERG "Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)\n", - TASK_COMM_LEN, current->comm, task_pid_nr(current), - current_thread_info(), current, task_thread_info(current)); + pr_emerg("Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)\n", + TASK_COMM_LEN, current->comm, task_pid_nr(current), + current_thread_info(), current, task_thread_info(current)); /* * When in-kernel, we also print out the stack and code at the * time of the fault.. @@ -102,10 +101,10 @@ void show_regs(struct pt_regs *regs) unsigned char c; u8 *ip; - printk(KERN_EMERG "Stack:\n"); + pr_emerg("Stack:\n"); show_stack_log_lvl(NULL, regs, ®s->sp, 0, KERN_EMERG); - printk(KERN_EMERG "Code: "); + pr_emerg("Code:"); ip = (u8 *)regs->ip - code_prologue; if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { @@ -116,16 +115,16 @@ void show_regs(struct pt_regs *regs) for (i = 0; i < code_len; i++, ip++) { if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { - printk(KERN_CONT " Bad EIP value."); + pr_cont(" Bad EIP value."); break; } if (ip == (u8 *)regs->ip) - printk(KERN_CONT "<%02x> ", c); + pr_cont(" <%02x>", c); else - printk(KERN_CONT "%02x ", c); + pr_cont(" %02x", c); } } - printk(KERN_CONT "\n"); + pr_cont("\n"); } int is_valid_bugaddr(unsigned long ip) diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 791b76122aa8..b653675d5288 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -228,20 +228,20 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, if (stack >= irq_stack && stack <= irq_stack_end) { if (stack == irq_stack_end) { stack = (unsigned long *) (irq_stack_end[-1]); - printk(KERN_CONT " <EOI> "); + pr_cont(" <EOI> "); } } else { if (((long) stack & (THREAD_SIZE-1)) == 0) break; } if (i && ((i % STACKSLOTS_PER_LINE) == 0)) - printk(KERN_CONT "\n"); - printk(KERN_CONT " %016lx", *stack++); + pr_cont("\n"); + pr_cont(" %016lx", *stack++); touch_nmi_watchdog(); } preempt_enable(); - printk(KERN_CONT "\n"); + pr_cont("\n"); show_trace_log_lvl(task, regs, sp, bp, log_lvl); } @@ -254,10 +254,9 @@ void show_regs(struct pt_regs *regs) sp = regs->sp; printk("CPU %d ", cpu); - print_modules(); __show_regs(regs, 1); - printk("Process %s (pid: %d, threadinfo %p, task %p)\n", - cur->comm, cur->pid, task_thread_info(cur), cur); + printk(KERN_DEFAULT "Process %s (pid: %d, threadinfo %p, task %p)\n", + cur->comm, cur->pid, task_thread_info(cur), cur); /* * When in-kernel, we also print out the stack and code at the @@ -284,16 +283,16 @@ void show_regs(struct pt_regs *regs) for (i = 0; i < code_len; i++, ip++) { if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { - printk(KERN_CONT " Bad RIP value."); + pr_cont(" Bad RIP value."); break; } if (ip == (u8 *)regs->ip) - printk(KERN_CONT "<%02x> ", c); + pr_cont("<%02x> ", c); else - printk(KERN_CONT "%02x ", c); + pr_cont("%02x ", c); } } - printk(KERN_CONT "\n"); + pr_cont("\n"); } int is_valid_bugaddr(unsigned long ip) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 7d65133b51be..111f6bbd8b38 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1758,10 +1758,30 @@ end_repeat_nmi: */ call save_paranoid DEFAULT_FRAME 0 + + /* + * Save off the CR2 register. If we take a page fault in the NMI then + * it could corrupt the CR2 value. If the NMI preempts a page fault + * handler before it was able to read the CR2 register, and then the + * NMI itself takes a page fault, the page fault that was preempted + * will read the information from the NMI page fault and not the + * origin fault. Save it off and restore it if it changes. + * Use the r12 callee-saved register. + */ + movq %cr2, %r12 + /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ movq %rsp,%rdi movq $-1,%rsi call do_nmi + + /* Did the NMI take a page fault? Restore cr2 if it did */ + movq %cr2, %rcx + cmpq %rcx, %r12 + je 1f + movq %r12, %cr2 +1: + testl %ebx,%ebx /* swapgs needed? */ jnz nmi_restore nmi_swapgs: diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 3dafc6003b7c..1f5f1d5d2a02 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -294,9 +294,9 @@ void fixup_irqs(void) raw_spin_unlock(&desc->lock); if (break_affinity && set_affinity) - printk("Broke affinity for irq %i\n", irq); + pr_notice("Broke affinity for irq %i\n", irq); else if (!set_affinity) - printk("Cannot set affinity for irq %i\n", irq); + pr_notice("Cannot set affinity for irq %i\n", irq); } /* diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index fbdfc6917180..4873e62db6a1 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -87,6 +87,7 @@ #include <asm/microcode.h> #include <asm/processor.h> #include <asm/cpu_device_id.h> +#include <asm/perf_event.h> MODULE_DESCRIPTION("Microcode Update Driver"); MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>"); @@ -277,7 +278,6 @@ static int reload_for_cpu(int cpu) struct ucode_cpu_info *uci = ucode_cpu_info + cpu; int err = 0; - mutex_lock(µcode_mutex); if (uci->valid) { enum ucode_state ustate; @@ -288,7 +288,6 @@ static int reload_for_cpu(int cpu) if (ustate == UCODE_ERROR) err = -EINVAL; } - mutex_unlock(µcode_mutex); return err; } @@ -298,19 +297,31 @@ static ssize_t reload_store(struct device *dev, const char *buf, size_t size) { unsigned long val; - int cpu = dev->id; - ssize_t ret = 0; + int cpu; + ssize_t ret = 0, tmp_ret; ret = kstrtoul(buf, 0, &val); if (ret) return ret; - if (val == 1) { - get_online_cpus(); - if (cpu_online(cpu)) - ret = reload_for_cpu(cpu); - put_online_cpus(); + if (val != 1) + return size; + + get_online_cpus(); + mutex_lock(µcode_mutex); + for_each_online_cpu(cpu) { + tmp_ret = reload_for_cpu(cpu); + if (tmp_ret != 0) + pr_warn("Error reloading microcode on CPU %d\n", cpu); + + /* save retval of the first encountered reload error */ + if (!ret) + ret = tmp_ret; } + if (!ret) + perf_check_microcode(); + mutex_unlock(µcode_mutex); + put_online_cpus(); if (!ret) ret = size; @@ -339,7 +350,6 @@ static DEVICE_ATTR(version, 0400, version_show, NULL); static DEVICE_ATTR(processor_flags, 0400, pf_show, NULL); static struct attribute *mc_default_attrs[] = { - &dev_attr_reload.attr, &dev_attr_version.attr, &dev_attr_processor_flags.attr, NULL @@ -504,7 +514,7 @@ static struct notifier_block __refdata mc_cpu_notifier = { #ifdef MODULE /* Autoload on Intel and AMD systems */ -static const struct x86_cpu_id microcode_id[] = { +static const struct x86_cpu_id __initconst microcode_id[] = { #ifdef CONFIG_MICROCODE_INTEL { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, }, #endif @@ -516,6 +526,16 @@ static const struct x86_cpu_id microcode_id[] = { MODULE_DEVICE_TABLE(x86cpu, microcode_id); #endif +static struct attribute *cpu_root_microcode_attrs[] = { + &dev_attr_reload.attr, + NULL +}; + +static struct attribute_group cpu_root_microcode_group = { + .name = "microcode", + .attrs = cpu_root_microcode_attrs, +}; + static int __init microcode_init(void) { struct cpuinfo_x86 *c = &cpu_data(0); @@ -540,16 +560,25 @@ static int __init microcode_init(void) mutex_lock(µcode_mutex); error = subsys_interface_register(&mc_cpu_interface); - + if (!error) + perf_check_microcode(); mutex_unlock(µcode_mutex); put_online_cpus(); if (error) goto out_pdev; + error = sysfs_create_group(&cpu_subsys.dev_root->kobj, + &cpu_root_microcode_group); + + if (error) { + pr_err("Error creating microcode group!\n"); + goto out_driver; + } + error = microcode_dev_init(); if (error) - goto out_driver; + goto out_ucode_group; register_syscore_ops(&mc_syscore_ops); register_hotcpu_notifier(&mc_cpu_notifier); @@ -559,7 +588,11 @@ static int __init microcode_init(void) return 0; -out_driver: + out_ucode_group: + sysfs_remove_group(&cpu_subsys.dev_root->kobj, + &cpu_root_microcode_group); + + out_driver: get_online_cpus(); mutex_lock(µcode_mutex); @@ -568,7 +601,7 @@ out_driver: mutex_unlock(µcode_mutex); put_online_cpus(); -out_pdev: + out_pdev: platform_device_unregister(microcode_pdev); return error; @@ -584,6 +617,9 @@ static void __exit microcode_exit(void) unregister_hotcpu_notifier(&mc_cpu_notifier); unregister_syscore_ops(&mc_syscore_ops); + sysfs_remove_group(&cpu_subsys.dev_root->kobj, + &cpu_root_microcode_group); + get_online_cpus(); mutex_lock(µcode_mutex); diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index f21fd94ac897..202494d2ec6e 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -15,6 +15,9 @@ along with this program; if not, write to the Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/moduleloader.h> #include <linux/elf.h> #include <linux/vmalloc.h> @@ -30,9 +33,14 @@ #include <asm/pgtable.h> #if 0 -#define DEBUGP printk +#define DEBUGP(fmt, ...) \ + printk(KERN_DEBUG fmt, ##__VA_ARGS__) #else -#define DEBUGP(fmt...) +#define DEBUGP(fmt, ...) \ +do { \ + if (0) \ + printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ +} while (0) #endif void *module_alloc(unsigned long size) @@ -56,8 +64,8 @@ int apply_relocate(Elf32_Shdr *sechdrs, Elf32_Sym *sym; uint32_t *location; - DEBUGP("Applying relocate section %u to %u\n", relsec, - sechdrs[relsec].sh_info); + DEBUGP("Applying relocate section %u to %u\n", + relsec, sechdrs[relsec].sh_info); for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { /* This is where to make the change */ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr @@ -77,7 +85,7 @@ int apply_relocate(Elf32_Shdr *sechdrs, *location += sym->st_value - (uint32_t)location; break; default: - printk(KERN_ERR "module %s: Unknown relocation: %u\n", + pr_err("%s: Unknown relocation: %u\n", me->name, ELF32_R_TYPE(rel[i].r_info)); return -ENOEXEC; } @@ -97,8 +105,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, void *loc; u64 val; - DEBUGP("Applying relocate section %u to %u\n", relsec, - sechdrs[relsec].sh_info); + DEBUGP("Applying relocate section %u to %u\n", + relsec, sechdrs[relsec].sh_info); for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { /* This is where to make the change */ loc = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr @@ -110,8 +118,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, + ELF64_R_SYM(rel[i].r_info); DEBUGP("type %d st_value %Lx r_addend %Lx loc %Lx\n", - (int)ELF64_R_TYPE(rel[i].r_info), - sym->st_value, rel[i].r_addend, (u64)loc); + (int)ELF64_R_TYPE(rel[i].r_info), + sym->st_value, rel[i].r_addend, (u64)loc); val = sym->st_value + rel[i].r_addend; @@ -140,7 +148,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, #endif break; default: - printk(KERN_ERR "module %s: Unknown rela relocation: %llu\n", + pr_err("%s: Unknown rela relocation: %llu\n", me->name, ELF64_R_TYPE(rel[i].r_info)); return -ENOEXEC; } @@ -148,9 +156,9 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, return 0; overflow: - printk(KERN_ERR "overflow in relocation type %d val %Lx\n", + pr_err("overflow in relocation type %d val %Lx\n", (int)ELF64_R_TYPE(rel[i].r_info), val); - printk(KERN_ERR "`%s' likely not compiled with -mcmodel=kernel\n", + pr_err("`%s' likely not compiled with -mcmodel=kernel\n", me->name); return -ENOEXEC; } diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index a0b2f84457be..f84f5c57de35 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -365,8 +365,9 @@ static __kprobes void default_do_nmi(struct pt_regs *regs) #ifdef CONFIG_X86_32 /* * For i386, NMIs use the same stack as the kernel, and we can - * add a workaround to the iret problem in C. Simply have 3 states - * the NMI can be in. + * add a workaround to the iret problem in C (preventing nested + * NMIs if an NMI takes a trap). Simply have 3 states the NMI + * can be in: * * 1) not running * 2) executing @@ -383,32 +384,50 @@ static __kprobes void default_do_nmi(struct pt_regs *regs) * If an NMI hits a breakpoint that executes an iret, another * NMI can preempt it. We do not want to allow this new NMI * to run, but we want to execute it when the first one finishes. - * We set the state to "latched", and the first NMI will perform - * an cmpxchg on the state, and if it doesn't successfully - * reset the state to "not running" it will restart the next - * NMI. + * We set the state to "latched", and the exit of the first NMI will + * perform a dec_return, if the result is zero (NOT_RUNNING), then + * it will simply exit the NMI handler. If not, the dec_return + * would have set the state to NMI_EXECUTING (what we want it to + * be when we are running). In this case, we simply jump back + * to rerun the NMI handler again, and restart the 'latched' NMI. + * + * No trap (breakpoint or page fault) should be hit before nmi_restart, + * thus there is no race between the first check of state for NOT_RUNNING + * and setting it to NMI_EXECUTING. The HW will prevent nested NMIs + * at this point. + * + * In case the NMI takes a page fault, we need to save off the CR2 + * because the NMI could have preempted another page fault and corrupt + * the CR2 that is about to be read. As nested NMIs must be restarted + * and they can not take breakpoints or page faults, the update of the + * CR2 must be done before converting the nmi state back to NOT_RUNNING. + * Otherwise, there would be a race of another nested NMI coming in + * after setting state to NOT_RUNNING but before updating the nmi_cr2. */ enum nmi_states { - NMI_NOT_RUNNING, + NMI_NOT_RUNNING = 0, NMI_EXECUTING, NMI_LATCHED, }; static DEFINE_PER_CPU(enum nmi_states, nmi_state); +static DEFINE_PER_CPU(unsigned long, nmi_cr2); #define nmi_nesting_preprocess(regs) \ do { \ - if (__get_cpu_var(nmi_state) != NMI_NOT_RUNNING) { \ - __get_cpu_var(nmi_state) = NMI_LATCHED; \ + if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { \ + this_cpu_write(nmi_state, NMI_LATCHED); \ return; \ } \ - nmi_restart: \ - __get_cpu_var(nmi_state) = NMI_EXECUTING; \ - } while (0) + this_cpu_write(nmi_state, NMI_EXECUTING); \ + this_cpu_write(nmi_cr2, read_cr2()); \ + } while (0); \ + nmi_restart: #define nmi_nesting_postprocess() \ do { \ - if (cmpxchg(&__get_cpu_var(nmi_state), \ - NMI_EXECUTING, NMI_NOT_RUNNING) != NMI_EXECUTING) \ + if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) \ + write_cr2(this_cpu_read(nmi_cr2)); \ + if (this_cpu_dec_return(nmi_state)) \ goto nmi_restart; \ } while (0) #else /* x86_64 */ diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c index 149b8d9c6ad4..6d9582ec0324 100644 --- a/arch/x86/kernel/nmi_selftest.c +++ b/arch/x86/kernel/nmi_selftest.c @@ -42,7 +42,8 @@ static int __init nmi_unk_cb(unsigned int val, struct pt_regs *regs) static void __init init_nmi_testsuite(void) { /* trap all the unknown NMIs we may generate */ - register_nmi_handler_initonly(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk"); + register_nmi_handler(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk", + __initdata); } static void __init cleanup_nmi_testsuite(void) @@ -64,8 +65,8 @@ static void __init test_nmi_ipi(struct cpumask *mask) { unsigned long timeout; - if (register_nmi_handler_initonly(NMI_LOCAL, test_nmi_ipi_callback, - NMI_FLAG_FIRST, "nmi_selftest")) { + if (register_nmi_handler(NMI_LOCAL, test_nmi_ipi_callback, + NMI_FLAG_FIRST, "nmi_selftest", __initdata)) { nmi_fail = FAILURE; return; } diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 9ce885996fd7..17fff18a1031 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -352,9 +352,7 @@ struct pv_cpu_ops pv_cpu_ops = { #endif .wbinvd = native_wbinvd, .read_msr = native_read_msr_safe, - .rdmsr_regs = native_rdmsr_safe_regs, .write_msr = native_write_msr_safe, - .wrmsr_regs = native_wrmsr_safe_regs, .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, .read_tscp = native_read_tscp, diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index b72838bae64a..299d49302e7d 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -22,6 +22,8 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#define pr_fmt(fmt) "Calgary: " fmt + #include <linux/kernel.h> #include <linux/init.h> #include <linux/types.h> @@ -245,7 +247,7 @@ static unsigned long iommu_range_alloc(struct device *dev, offset = iommu_area_alloc(tbl->it_map, tbl->it_size, 0, npages, 0, boundary_size, 0); if (offset == ~0UL) { - printk(KERN_WARNING "Calgary: IOMMU full.\n"); + pr_warn("IOMMU full\n"); spin_unlock_irqrestore(&tbl->it_lock, flags); if (panic_on_overflow) panic("Calgary: fix the allocator.\n"); @@ -271,8 +273,8 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, entry = iommu_range_alloc(dev, tbl, npages); if (unlikely(entry == DMA_ERROR_CODE)) { - printk(KERN_WARNING "Calgary: failed to allocate %u pages in " - "iommu %p\n", npages, tbl); + pr_warn("failed to allocate %u pages in iommu %p\n", + npages, tbl); return DMA_ERROR_CODE; } @@ -561,8 +563,7 @@ static void calgary_tce_cache_blast(struct iommu_table *tbl) i++; } while ((val & 0xff) != 0xff && i < 100); if (i == 100) - printk(KERN_WARNING "Calgary: PCI bus not quiesced, " - "continuing anyway\n"); + pr_warn("PCI bus not quiesced, continuing anyway\n"); /* invalidate TCE cache */ target = calgary_reg(bbar, tar_offset(tbl->it_busno)); @@ -604,8 +605,7 @@ begin: i++; } while ((val64 & 0xff) != 0xff && i < 100); if (i == 100) - printk(KERN_WARNING "CalIOC2: PCI bus not quiesced, " - "continuing anyway\n"); + pr_warn("CalIOC2: PCI bus not quiesced, continuing anyway\n"); /* 3. poll Page Migration DEBUG for SoftStopFault */ target = calgary_reg(bbar, phb_offset(bus) | PHB_PAGE_MIG_DEBUG); @@ -617,8 +617,7 @@ begin: if (++count < 100) goto begin; else { - printk(KERN_WARNING "CalIOC2: too many SoftStopFaults, " - "aborting TCE cache flush sequence!\n"); + pr_warn("CalIOC2: too many SoftStopFaults, aborting TCE cache flush sequence!\n"); return; /* pray for the best */ } } @@ -840,8 +839,8 @@ static void calgary_dump_error_regs(struct iommu_table *tbl) plssr = be32_to_cpu(readl(target)); /* If no error, the agent ID in the CSR is not valid */ - printk(KERN_EMERG "Calgary: DMA error on Calgary PHB 0x%x, " - "0x%08x@CSR 0x%08x@PLSSR\n", tbl->it_busno, csr, plssr); + pr_emerg("DMA error on Calgary PHB 0x%x, 0x%08x@CSR 0x%08x@PLSSR\n", + tbl->it_busno, csr, plssr); } static void calioc2_dump_error_regs(struct iommu_table *tbl) @@ -867,22 +866,21 @@ static void calioc2_dump_error_regs(struct iommu_table *tbl) target = calgary_reg(bbar, phboff | 0x800); mck = be32_to_cpu(readl(target)); - printk(KERN_EMERG "Calgary: DMA error on CalIOC2 PHB 0x%x\n", - tbl->it_busno); + pr_emerg("DMA error on CalIOC2 PHB 0x%x\n", tbl->it_busno); - printk(KERN_EMERG "Calgary: 0x%08x@CSR 0x%08x@PLSSR 0x%08x@CSMR 0x%08x@MCK\n", - csr, plssr, csmr, mck); + pr_emerg("0x%08x@CSR 0x%08x@PLSSR 0x%08x@CSMR 0x%08x@MCK\n", + csr, plssr, csmr, mck); /* dump rest of error regs */ - printk(KERN_EMERG "Calgary: "); + pr_emerg(""); for (i = 0; i < ARRAY_SIZE(errregs); i++) { /* err regs are at 0x810 - 0x870 */ erroff = (0x810 + (i * 0x10)); target = calgary_reg(bbar, phboff | erroff); errregs[i] = be32_to_cpu(readl(target)); - printk("0x%08x@0x%lx ", errregs[i], erroff); + pr_cont("0x%08x@0x%lx ", errregs[i], erroff); } - printk("\n"); + pr_cont("\n"); /* root complex status */ target = calgary_reg(bbar, phboff | PHB_ROOT_COMPLEX_STATUS); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 735279e54e59..ef6a8456f719 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -1,3 +1,5 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/errno.h> #include <linux/kernel.h> #include <linux/mm.h> @@ -145,16 +147,14 @@ void show_regs_common(void) /* Board Name is optional */ board = dmi_get_system_info(DMI_BOARD_NAME); - printk(KERN_CONT "\n"); - printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s", - current->pid, current->comm, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - printk(KERN_CONT " %s %s", vendor, product); - if (board) - printk(KERN_CONT "/%s", board); - printk(KERN_CONT "\n"); + printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s %s %s%s%s\n", + current->pid, current->comm, print_tainted(), + init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version, + vendor, product, + board ? "/" : "", + board ? board : ""); } void flush_thread(void) @@ -645,7 +645,7 @@ static void amd_e400_idle(void) amd_e400_c1e_detected = true; if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) mark_tsc_unstable("TSC halt in AMD C1E"); - printk(KERN_INFO "System has AMD C1E enabled\n"); + pr_info("System has AMD C1E enabled\n"); } } @@ -659,8 +659,7 @@ static void amd_e400_idle(void) */ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, &cpu); - printk(KERN_INFO "Switch to broadcast mode on CPU%d\n", - cpu); + pr_info("Switch to broadcast mode on CPU%d\n", cpu); } clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu); @@ -681,8 +680,7 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP if (pm_idle == poll_idle && smp_num_siblings > 1) { - printk_once(KERN_WARNING "WARNING: polling idle and HT enabled," - " performance may degrade.\n"); + pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n"); } #endif if (pm_idle) @@ -692,11 +690,11 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) /* * One CPU supports mwait => All CPUs supports mwait */ - printk(KERN_INFO "using mwait in idle threads.\n"); + pr_info("using mwait in idle threads\n"); pm_idle = mwait_idle; } else if (cpu_has_amd_erratum(amd_erratum_400)) { /* E400: APIC timer interrupt does not wake up CPU from C1e */ - printk(KERN_INFO "using AMD E400 aware idle routine\n"); + pr_info("using AMD E400 aware idle routine\n"); pm_idle = amd_e400_idle; } else pm_idle = default_idle; @@ -715,7 +713,7 @@ static int __init idle_setup(char *str) return -EINVAL; if (!strcmp(str, "poll")) { - printk("using polling idle threads.\n"); + pr_info("using polling idle threads\n"); pm_idle = poll_idle; boot_option_idle_override = IDLE_POLL; } else if (!strcmp(str, "mwait")) { diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 61cdf7fdf099..0a980c9d7cb8 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -117,10 +117,10 @@ void release_thread(struct task_struct *dead_task) { if (dead_task->mm) { if (dead_task->mm->context.size) { - printk("WARNING: dead process %8s still has LDT? <%p/%d>\n", - dead_task->comm, - dead_task->mm->context.ldt, - dead_task->mm->context.size); + pr_warn("WARNING: dead process %8s still has LDT? <%p/%d>\n", + dead_task->comm, + dead_task->mm->context.ldt, + dead_task->mm->context.size); BUG(); } } @@ -466,7 +466,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) task->thread.gs = addr; if (doit) { load_gs_index(0); - ret = checking_wrmsrl(MSR_KERNEL_GS_BASE, addr); + ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr); } } put_cpu(); @@ -494,7 +494,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) /* set the selector to 0 to not confuse __switch_to */ loadsegment(fs, 0); - ret = checking_wrmsrl(MSR_FS_BASE, addr); + ret = wrmsrl_safe(MSR_FS_BASE, addr); } } put_cpu(); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 5de92f1abd76..52190a938b4a 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -1,3 +1,5 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/reboot.h> #include <linux/init.h> @@ -20,14 +22,12 @@ #include <asm/virtext.h> #include <asm/cpu.h> #include <asm/nmi.h> +#include <asm/smp.h> -#ifdef CONFIG_X86_32 -# include <linux/ctype.h> -# include <linux/mc146818rtc.h> -# include <asm/realmode.h> -#else -# include <asm/x86_init.h> -#endif +#include <linux/ctype.h> +#include <linux/mc146818rtc.h> +#include <asm/realmode.h> +#include <asm/x86_init.h> /* * Power off function, if any @@ -49,7 +49,7 @@ int reboot_force; */ static int reboot_default = 1; -#if defined(CONFIG_X86_32) && defined(CONFIG_SMP) +#ifdef CONFIG_SMP static int reboot_cpu = -1; #endif @@ -67,8 +67,8 @@ bool port_cf9_safe = false; * reboot=b[ios] | s[mp] | t[riple] | k[bd] | e[fi] [, [w]arm | [c]old] | p[ci] * warm Don't set the cold reboot flag * cold Set the cold reboot flag - * bios Reboot by jumping through the BIOS (only for X86_32) - * smp Reboot by executing reset on BSP or other CPU (only for X86_32) + * bios Reboot by jumping through the BIOS + * smp Reboot by executing reset on BSP or other CPU * triple Force a triple fault (init) * kbd Use the keyboard controller. cold reset (default) * acpi Use the RESET_REG in the FADT @@ -95,7 +95,6 @@ static int __init reboot_setup(char *str) reboot_mode = 0; break; -#ifdef CONFIG_X86_32 #ifdef CONFIG_SMP case 's': if (isdigit(*(str+1))) { @@ -112,7 +111,6 @@ static int __init reboot_setup(char *str) #endif /* CONFIG_SMP */ case 'b': -#endif case 'a': case 'k': case 't': @@ -138,7 +136,6 @@ static int __init reboot_setup(char *str) __setup("reboot=", reboot_setup); -#ifdef CONFIG_X86_32 /* * Reboot options and system auto-detection code provided by * Dell Inc. so their systems "just work". :-) @@ -152,16 +149,14 @@ static int __init set_bios_reboot(const struct dmi_system_id *d) { if (reboot_type != BOOT_BIOS) { reboot_type = BOOT_BIOS; - printk(KERN_INFO "%s series board detected. Selecting BIOS-method for reboots.\n", d->ident); + pr_info("%s series board detected. Selecting %s-method for reboots.\n", + "BIOS", d->ident); } return 0; } -void machine_real_restart(unsigned int type) +void __noreturn machine_real_restart(unsigned int type) { - void (*restart_lowmem)(unsigned int) = (void (*)(unsigned int)) - real_mode_header->machine_real_restart_asm; - local_irq_disable(); /* @@ -181,25 +176,28 @@ void machine_real_restart(unsigned int type) /* * Switch back to the initial page table. */ +#ifdef CONFIG_X86_32 load_cr3(initial_page_table); - - /* - * Write 0x1234 to absolute memory location 0x472. The BIOS reads - * this on booting to tell it to "Bypass memory test (also warm - * boot)". This seems like a fairly standard thing that gets set by - * REBOOT.COM programs, and the previous reset routine did this - * too. */ - *((unsigned short *)0x472) = reboot_mode; +#else + write_cr3(real_mode_header->trampoline_pgd); +#endif /* Jump to the identity-mapped low memory code */ - restart_lowmem(type); +#ifdef CONFIG_X86_32 + asm volatile("jmpl *%0" : : + "rm" (real_mode_header->machine_real_restart_asm), + "a" (type)); +#else + asm volatile("ljmpl *%0" : : + "m" (real_mode_header->machine_real_restart_asm), + "D" (type)); +#endif + unreachable(); } #ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(machine_real_restart); #endif -#endif /* CONFIG_X86_32 */ - /* * Some Apple MacBook and MacBookPro's needs reboot=p to be able to reboot */ @@ -207,8 +205,8 @@ static int __init set_pci_reboot(const struct dmi_system_id *d) { if (reboot_type != BOOT_CF9) { reboot_type = BOOT_CF9; - printk(KERN_INFO "%s series board detected. " - "Selecting PCI-method for reboots.\n", d->ident); + pr_info("%s series board detected. Selecting %s-method for reboots.\n", + "PCI", d->ident); } return 0; } @@ -217,17 +215,16 @@ static int __init set_kbd_reboot(const struct dmi_system_id *d) { if (reboot_type != BOOT_KBD) { reboot_type = BOOT_KBD; - printk(KERN_INFO "%s series board detected. Selecting KBD-method for reboot.\n", d->ident); + pr_info("%s series board detected. Selecting %s-method for reboot.\n", + "KBD", d->ident); } return 0; } /* - * This is a single dmi_table handling all reboot quirks. Note that - * REBOOT_BIOS is only available for 32bit + * This is a single dmi_table handling all reboot quirks. */ static struct dmi_system_id __initdata reboot_dmi_table[] = { -#ifdef CONFIG_X86_32 { /* Handle problems with rebooting on Dell E520's */ .callback = set_bios_reboot, .ident = "Dell E520", @@ -377,7 +374,6 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "P4S800"), }, }, -#endif /* CONFIG_X86_32 */ { /* Handle reboot issue on Acer Aspire one */ .callback = set_kbd_reboot, @@ -584,13 +580,11 @@ static void native_machine_emergency_restart(void) reboot_type = BOOT_KBD; break; -#ifdef CONFIG_X86_32 case BOOT_BIOS: machine_real_restart(MRR_BIOS); reboot_type = BOOT_KBD; break; -#endif case BOOT_ACPI: acpi_reboot(); @@ -632,12 +626,10 @@ void native_machine_shutdown(void) /* The boot cpu is always logical cpu 0 */ int reboot_cpu_id = 0; -#ifdef CONFIG_X86_32 /* See if there has been given a command line override */ if ((reboot_cpu != -1) && (reboot_cpu < nr_cpu_ids) && cpu_online(reboot_cpu)) reboot_cpu_id = reboot_cpu; -#endif /* Make certain the cpu I'm about to reboot on is online */ if (!cpu_online(reboot_cpu_id)) @@ -678,7 +670,7 @@ static void __machine_emergency_restart(int emergency) static void native_machine_restart(char *__unused) { - printk("machine restart\n"); + pr_notice("machine restart\n"); if (!reboot_force) machine_shutdown(); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 16be6dc14db1..f4b9b80e1b95 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1031,8 +1031,6 @@ void __init setup_arch(char **cmdline_p) x86_init.timers.wallclock_init(); - x86_platform.wallclock_init(); - mcheck_init(); arch_init_ideal_nops(); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 21af737053aa..b280908a376e 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -6,6 +6,9 @@ * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes * 2000-2002 x86-64 support by Andi Kleen */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/sched.h> #include <linux/mm.h> #include <linux/smp.h> @@ -814,7 +817,7 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where) me->comm, me->pid, where, frame, regs->ip, regs->sp, regs->orig_ax); print_vma_addr(" in ", regs->ip); - printk(KERN_CONT "\n"); + pr_cont("\n"); } force_sig(SIGSEGV, me); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 7bd8a0823654..c1a310fb8309 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1,4 +1,4 @@ -/* + /* * x86 SMP booting functions * * (c) 1995 Alan Cox, Building #3 <alan@lxorguk.ukuu.org.uk> @@ -39,6 +39,8 @@ * Glauber Costa : i386 and x86_64 integration */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/init.h> #include <linux/smp.h> #include <linux/module.h> @@ -184,7 +186,7 @@ static void __cpuinit smp_callin(void) * boards) */ - pr_debug("CALLIN, before setup_local_APIC().\n"); + pr_debug("CALLIN, before setup_local_APIC()\n"); if (apic->smp_callin_clear_local_apic) apic->smp_callin_clear_local_apic(); setup_local_APIC(); @@ -255,22 +257,13 @@ notrace static void __cpuinit start_secondary(void *unused) check_tsc_sync_target(); /* - * We need to hold call_lock, so there is no inconsistency - * between the time smp_call_function() determines number of - * IPI recipients, and the time when the determination is made - * for which cpus receive the IPI. Holding this - * lock helps us to not include this cpu in a currently in progress - * smp_call_function(). - * * We need to hold vector_lock so there the set of online cpus * does not change while we are assigning vectors to cpus. Holding * this lock ensures we don't half assign or remove an irq from a cpu. */ - ipi_call_lock(); lock_vector_lock(); set_cpu_online(smp_processor_id(), true); unlock_vector_lock(); - ipi_call_unlock(); per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; x86_platform.nmi_init(); @@ -432,17 +425,16 @@ static void impress_friends(void) /* * Allow the user to impress friends. */ - pr_debug("Before bogomips.\n"); + pr_debug("Before bogomips\n"); for_each_possible_cpu(cpu) if (cpumask_test_cpu(cpu, cpu_callout_mask)) bogosum += cpu_data(cpu).loops_per_jiffy; - printk(KERN_INFO - "Total of %d processors activated (%lu.%02lu BogoMIPS).\n", + pr_info("Total of %d processors activated (%lu.%02lu BogoMIPS)\n", num_online_cpus(), bogosum/(500000/HZ), (bogosum/(5000/HZ))%100); - pr_debug("Before bogocount - setting activated=1.\n"); + pr_debug("Before bogocount - setting activated=1\n"); } void __inquire_remote_apic(int apicid) @@ -452,18 +444,17 @@ void __inquire_remote_apic(int apicid) int timeout; u32 status; - printk(KERN_INFO "Inquiring remote APIC 0x%x...\n", apicid); + pr_info("Inquiring remote APIC 0x%x...\n", apicid); for (i = 0; i < ARRAY_SIZE(regs); i++) { - printk(KERN_INFO "... APIC 0x%x %s: ", apicid, names[i]); + pr_info("... APIC 0x%x %s: ", apicid, names[i]); /* * Wait for idle. */ status = safe_apic_wait_icr_idle(); if (status) - printk(KERN_CONT - "a previous APIC delivery may have failed\n"); + pr_cont("a previous APIC delivery may have failed\n"); apic_icr_write(APIC_DM_REMRD | regs[i], apicid); @@ -476,10 +467,10 @@ void __inquire_remote_apic(int apicid) switch (status) { case APIC_ICR_RR_VALID: status = apic_read(APIC_RRR); - printk(KERN_CONT "%08x\n", status); + pr_cont("%08x\n", status); break; default: - printk(KERN_CONT "failed\n"); + pr_cont("failed\n"); } } } @@ -513,12 +504,12 @@ wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip) apic_write(APIC_ESR, 0); accept_status = (apic_read(APIC_ESR) & 0xEF); } - pr_debug("NMI sent.\n"); + pr_debug("NMI sent\n"); if (send_status) - printk(KERN_ERR "APIC never delivered???\n"); + pr_err("APIC never delivered???\n"); if (accept_status) - printk(KERN_ERR "APIC delivery error (%lx).\n", accept_status); + pr_err("APIC delivery error (%lx)\n", accept_status); return (send_status | accept_status); } @@ -540,7 +531,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) apic_read(APIC_ESR); } - pr_debug("Asserting INIT.\n"); + pr_debug("Asserting INIT\n"); /* * Turn INIT on target chip @@ -556,7 +547,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) mdelay(10); - pr_debug("Deasserting INIT.\n"); + pr_debug("Deasserting INIT\n"); /* Target chip */ /* Send IPI */ @@ -589,14 +580,14 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) /* * Run STARTUP IPI loop. */ - pr_debug("#startup loops: %d.\n", num_starts); + pr_debug("#startup loops: %d\n", num_starts); for (j = 1; j <= num_starts; j++) { - pr_debug("Sending STARTUP #%d.\n", j); + pr_debug("Sending STARTUP #%d\n", j); if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ apic_write(APIC_ESR, 0); apic_read(APIC_ESR); - pr_debug("After apic_write.\n"); + pr_debug("After apic_write\n"); /* * STARTUP IPI @@ -613,7 +604,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) */ udelay(300); - pr_debug("Startup point 1.\n"); + pr_debug("Startup point 1\n"); pr_debug("Waiting for send to finish...\n"); send_status = safe_apic_wait_icr_idle(); @@ -628,12 +619,12 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) if (send_status || accept_status) break; } - pr_debug("After Startup.\n"); + pr_debug("After Startup\n"); if (send_status) - printk(KERN_ERR "APIC never delivered???\n"); + pr_err("APIC never delivered???\n"); if (accept_status) - printk(KERN_ERR "APIC delivery error (%lx).\n", accept_status); + pr_err("APIC delivery error (%lx)\n", accept_status); return (send_status | accept_status); } @@ -647,11 +638,11 @@ static void __cpuinit announce_cpu(int cpu, int apicid) if (system_state == SYSTEM_BOOTING) { if (node != current_node) { if (current_node > (-1)) - pr_cont(" Ok.\n"); + pr_cont(" OK\n"); current_node = node; pr_info("Booting Node %3d, Processors ", node); } - pr_cont(" #%d%s", cpu, cpu == (nr_cpu_ids - 1) ? " Ok.\n" : ""); + pr_cont(" #%d%s", cpu, cpu == (nr_cpu_ids - 1) ? " OK\n" : ""); return; } else pr_info("Booting Node %d Processor %d APIC 0x%x\n", @@ -731,9 +722,9 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) /* * allow APs to start initializing. */ - pr_debug("Before Callout %d.\n", cpu); + pr_debug("Before Callout %d\n", cpu); cpumask_set_cpu(cpu, cpu_callout_mask); - pr_debug("After Callout %d.\n", cpu); + pr_debug("After Callout %d\n", cpu); /* * Wait 5s total for a response @@ -761,7 +752,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) pr_err("CPU%d: Stuck ??\n", cpu); else /* trampoline code not run */ - pr_err("CPU%d: Not responding.\n", cpu); + pr_err("CPU%d: Not responding\n", cpu); if (apic->inquire_remote_apic) apic->inquire_remote_apic(apicid); } @@ -806,7 +797,7 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle) if (apicid == BAD_APICID || apicid == boot_cpu_physical_apicid || !physid_isset(apicid, phys_cpu_present_map) || !apic->apic_id_valid(apicid)) { - printk(KERN_ERR "%s: bad cpu %d\n", __func__, cpu); + pr_err("%s: bad cpu %d\n", __func__, cpu); return -EINVAL; } @@ -887,9 +878,8 @@ static int __init smp_sanity_check(unsigned max_cpus) unsigned int cpu; unsigned nr; - printk(KERN_WARNING - "More than 8 CPUs detected - skipping them.\n" - "Use CONFIG_X86_BIGSMP.\n"); + pr_warn("More than 8 CPUs detected - skipping them\n" + "Use CONFIG_X86_BIGSMP\n"); nr = 0; for_each_present_cpu(cpu) { @@ -910,8 +900,7 @@ static int __init smp_sanity_check(unsigned max_cpus) #endif if (!physid_isset(hard_smp_processor_id(), phys_cpu_present_map)) { - printk(KERN_WARNING - "weird, boot CPU (#%d) not listed by the BIOS.\n", + pr_warn("weird, boot CPU (#%d) not listed by the BIOS\n", hard_smp_processor_id()); physid_set(hard_smp_processor_id(), phys_cpu_present_map); @@ -923,11 +912,10 @@ static int __init smp_sanity_check(unsigned max_cpus) */ if (!smp_found_config && !acpi_lapic) { preempt_enable(); - printk(KERN_NOTICE "SMP motherboard not detected.\n"); + pr_notice("SMP motherboard not detected\n"); disable_smp(); if (APIC_init_uniprocessor()) - printk(KERN_NOTICE "Local APIC not detected." - " Using dummy APIC emulation.\n"); + pr_notice("Local APIC not detected. Using dummy APIC emulation.\n"); return -1; } @@ -936,9 +924,8 @@ static int __init smp_sanity_check(unsigned max_cpus) * CPU too, but we do it for the sake of robustness anyway. */ if (!apic->check_phys_apicid_present(boot_cpu_physical_apicid)) { - printk(KERN_NOTICE - "weird, boot CPU (#%d) not listed by the BIOS.\n", - boot_cpu_physical_apicid); + pr_notice("weird, boot CPU (#%d) not listed by the BIOS\n", + boot_cpu_physical_apicid); physid_set(hard_smp_processor_id(), phys_cpu_present_map); } preempt_enable(); @@ -951,8 +938,7 @@ static int __init smp_sanity_check(unsigned max_cpus) if (!disable_apic) { pr_err("BIOS bug, local APIC #%d not detected!...\n", boot_cpu_physical_apicid); - pr_err("... forcing use of dummy APIC emulation." - "(tell your hw vendor)\n"); + pr_err("... forcing use of dummy APIC emulation (tell your hw vendor)\n"); } smpboot_clear_io_apic(); disable_ioapic_support(); @@ -965,7 +951,7 @@ static int __init smp_sanity_check(unsigned max_cpus) * If SMP should be disabled, then really disable it! */ if (!max_cpus) { - printk(KERN_INFO "SMP mode deactivated.\n"); + pr_info("SMP mode deactivated\n"); smpboot_clear_io_apic(); connect_bsp_APIC(); @@ -1017,7 +1003,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) if (smp_sanity_check(max_cpus) < 0) { - printk(KERN_INFO "SMP disabled\n"); + pr_info("SMP disabled\n"); disable_smp(); goto out; } @@ -1055,7 +1041,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) * Set up local APIC timer on boot CPU. */ - printk(KERN_INFO "CPU%d: ", 0); + pr_info("CPU%d: ", 0); print_cpu_info(&cpu_data(0)); x86_init.timers.setup_percpu_clockev(); @@ -1105,7 +1091,7 @@ void __init native_smp_prepare_boot_cpu(void) void __init native_smp_cpus_done(unsigned int max_cpus) { - pr_debug("Boot done.\n"); + pr_debug("Boot done\n"); nmi_selftest(); impress_friends(); @@ -1166,8 +1152,7 @@ __init void prefill_possible_map(void) /* nr_cpu_ids could be reduced via nr_cpus= */ if (possible > nr_cpu_ids) { - printk(KERN_WARNING - "%d Processors exceeds NR_CPUS limit of %d\n", + pr_warn("%d Processors exceeds NR_CPUS limit of %d\n", possible, nr_cpu_ids); possible = nr_cpu_ids; } @@ -1176,13 +1161,12 @@ __init void prefill_possible_map(void) if (!setup_max_cpus) #endif if (possible > i) { - printk(KERN_WARNING - "%d Processors exceeds max_cpus limit of %u\n", + pr_warn("%d Processors exceeds max_cpus limit of %u\n", possible, setup_max_cpus); possible = i; } - printk(KERN_INFO "SMP: Allowing %d CPUs, %d hotplug CPUs\n", + pr_info("Allowing %d CPUs, %d hotplug CPUs\n", possible, max_t(int, possible - num_processors, 0)); for (i = 0; i < possible; i++) diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 05b31d92f69c..b481341c9369 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -9,6 +9,9 @@ /* * Handle hardware traps and faults. */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/interrupt.h> #include <linux/kallsyms.h> #include <linux/spinlock.h> @@ -143,12 +146,11 @@ trap_signal: #ifdef CONFIG_X86_64 if (show_unhandled_signals && unhandled_signal(tsk, signr) && printk_ratelimit()) { - printk(KERN_INFO - "%s[%d] trap %s ip:%lx sp:%lx error:%lx", - tsk->comm, tsk->pid, str, - regs->ip, regs->sp, error_code); + pr_info("%s[%d] trap %s ip:%lx sp:%lx error:%lx", + tsk->comm, tsk->pid, str, + regs->ip, regs->sp, error_code); print_vma_addr(" in ", regs->ip); - printk("\n"); + pr_cont("\n"); } #endif @@ -269,12 +271,11 @@ do_general_protection(struct pt_regs *regs, long error_code) if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && printk_ratelimit()) { - printk(KERN_INFO - "%s[%d] general protection ip:%lx sp:%lx error:%lx", + pr_info("%s[%d] general protection ip:%lx sp:%lx error:%lx", tsk->comm, task_pid_nr(tsk), regs->ip, regs->sp, error_code); print_vma_addr(" in ", regs->ip); - printk("\n"); + pr_cont("\n"); } force_sig(SIGSEGV, tsk); @@ -570,7 +571,7 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) conditional_sti(regs); #if 0 /* No need to warn about this any longer. */ - printk(KERN_INFO "Ignoring P6 Local APIC Spurious Interrupt Bug...\n"); + pr_info("Ignoring P6 Local APIC Spurious Interrupt Bug...\n"); #endif } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index fc0a147e3727..cfa5d4f7ca56 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1,3 +1,5 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/sched.h> #include <linux/init.h> @@ -84,8 +86,7 @@ EXPORT_SYMBOL_GPL(check_tsc_unstable); #ifdef CONFIG_X86_TSC int __init notsc_setup(char *str) { - printk(KERN_WARNING "notsc: Kernel compiled with CONFIG_X86_TSC, " - "cannot disable TSC completely.\n"); + pr_warn("Kernel compiled with CONFIG_X86_TSC, cannot disable TSC completely\n"); tsc_disabled = 1; return 1; } @@ -373,7 +374,7 @@ static unsigned long quick_pit_calibrate(void) goto success; } } - printk("Fast TSC calibration failed\n"); + pr_err("Fast TSC calibration failed\n"); return 0; success: @@ -392,7 +393,7 @@ success: */ delta *= PIT_TICK_RATE; do_div(delta, i*256*1000); - printk("Fast TSC calibration using PIT\n"); + pr_info("Fast TSC calibration using PIT\n"); return delta; } @@ -487,9 +488,8 @@ unsigned long native_calibrate_tsc(void) * use the reference value, as it is more precise. */ if (delta >= 90 && delta <= 110) { - printk(KERN_INFO - "TSC: PIT calibration matches %s. %d loops\n", - hpet ? "HPET" : "PMTIMER", i + 1); + pr_info("PIT calibration matches %s. %d loops\n", + hpet ? "HPET" : "PMTIMER", i + 1); return tsc_ref_min; } @@ -511,38 +511,36 @@ unsigned long native_calibrate_tsc(void) */ if (tsc_pit_min == ULONG_MAX) { /* PIT gave no useful value */ - printk(KERN_WARNING "TSC: Unable to calibrate against PIT\n"); + pr_warn("Unable to calibrate against PIT\n"); /* We don't have an alternative source, disable TSC */ if (!hpet && !ref1 && !ref2) { - printk("TSC: No reference (HPET/PMTIMER) available\n"); + pr_notice("No reference (HPET/PMTIMER) available\n"); return 0; } /* The alternative source failed as well, disable TSC */ if (tsc_ref_min == ULONG_MAX) { - printk(KERN_WARNING "TSC: HPET/PMTIMER calibration " - "failed.\n"); + pr_warn("HPET/PMTIMER calibration failed\n"); return 0; } /* Use the alternative source */ - printk(KERN_INFO "TSC: using %s reference calibration\n", - hpet ? "HPET" : "PMTIMER"); + pr_info("using %s reference calibration\n", + hpet ? "HPET" : "PMTIMER"); return tsc_ref_min; } /* We don't have an alternative source, use the PIT calibration value */ if (!hpet && !ref1 && !ref2) { - printk(KERN_INFO "TSC: Using PIT calibration value\n"); + pr_info("Using PIT calibration value\n"); return tsc_pit_min; } /* The alternative source failed, use the PIT calibration value */ if (tsc_ref_min == ULONG_MAX) { - printk(KERN_WARNING "TSC: HPET/PMTIMER calibration failed. " - "Using PIT calibration\n"); + pr_warn("HPET/PMTIMER calibration failed. Using PIT calibration.\n"); return tsc_pit_min; } @@ -551,9 +549,9 @@ unsigned long native_calibrate_tsc(void) * the PIT value as we know that there are PMTIMERs around * running at double speed. At least we let the user know: */ - printk(KERN_WARNING "TSC: PIT calibration deviates from %s: %lu %lu.\n", - hpet ? "HPET" : "PMTIMER", tsc_pit_min, tsc_ref_min); - printk(KERN_INFO "TSC: Using PIT calibration value\n"); + pr_warn("PIT calibration deviates from %s: %lu %lu\n", + hpet ? "HPET" : "PMTIMER", tsc_pit_min, tsc_ref_min); + pr_info("Using PIT calibration value\n"); return tsc_pit_min; } @@ -785,7 +783,7 @@ void mark_tsc_unstable(char *reason) tsc_unstable = 1; sched_clock_stable = 0; disable_sched_clock_irqtime(); - printk(KERN_INFO "Marking TSC unstable due to %s\n", reason); + pr_info("Marking TSC unstable due to %s\n", reason); /* Change only the rating, when not registered */ if (clocksource_tsc.mult) clocksource_mark_unstable(&clocksource_tsc); @@ -912,9 +910,9 @@ static void tsc_refine_calibration_work(struct work_struct *work) goto out; tsc_khz = freq; - printk(KERN_INFO "Refined TSC clocksource calibration: " - "%lu.%03lu MHz.\n", (unsigned long)tsc_khz / 1000, - (unsigned long)tsc_khz % 1000); + pr_info("Refined TSC clocksource calibration: %lu.%03lu MHz\n", + (unsigned long)tsc_khz / 1000, + (unsigned long)tsc_khz % 1000); out: clocksource_register_khz(&clocksource_tsc, tsc_khz); @@ -970,9 +968,9 @@ void __init tsc_init(void) return; } - printk("Detected %lu.%03lu MHz processor.\n", - (unsigned long)cpu_khz / 1000, - (unsigned long)cpu_khz % 1000); + pr_info("Detected %lu.%03lu MHz processor\n", + (unsigned long)cpu_khz / 1000, + (unsigned long)cpu_khz % 1000); /* * Secondary CPUs do not run through tsc_init(), so set up diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index dc4e910a7d96..36fd42091fa7 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -409,9 +409,10 @@ static int validate_insn_bits(struct arch_uprobe *auprobe, struct mm_struct *mm, * arch_uprobe_analyze_insn - instruction analysis including validity and fixups. * @mm: the probed address space. * @arch_uprobe: the probepoint information. + * @addr: virtual address at which to install the probepoint * Return 0 on success or a -ve number on error. */ -int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm) +int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long addr) { int ret; struct insn insn; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 255f58ae71e8..54abcc0baf23 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -28,6 +28,8 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/capability.h> #include <linux/errno.h> #include <linux/interrupt.h> @@ -137,14 +139,14 @@ struct pt_regs *save_v86_state(struct kernel_vm86_regs *regs) local_irq_enable(); if (!current->thread.vm86_info) { - printk("no vm86_info: BAD\n"); + pr_alert("no vm86_info: BAD\n"); do_exit(SIGSEGV); } set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | current->thread.v86mask); tmp = copy_vm86_regs_to_user(¤t->thread.vm86_info->regs, regs); tmp += put_user(current->thread.screen_bitmap, ¤t->thread.vm86_info->screen_bitmap); if (tmp) { - printk("vm86: could not access userspace vm86_info\n"); + pr_alert("could not access userspace vm86_info\n"); do_exit(SIGSEGV); } diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index 8eeb55a551b4..992f890283e9 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -16,6 +16,7 @@ #include <linux/pci_ids.h> #include <linux/pci_regs.h> #include <linux/smp.h> +#include <linux/irq.h> #include <asm/apic.h> #include <asm/pci-direct.h> @@ -95,6 +96,18 @@ static void __init set_vsmp_pv_ops(void) ctl = readl(address + 4); printk(KERN_INFO "vSMP CTL: capabilities:0x%08x control:0x%08x\n", cap, ctl); + + /* If possible, let the vSMP foundation route the interrupt optimally */ +#ifdef CONFIG_SMP + if (cap & ctl & BIT(8)) { + ctl &= ~BIT(8); +#ifdef CONFIG_PROC_FS + /* Don't let users change irq affinity via procfs */ + no_irq_affinity = 1; +#endif + } +#endif + if (cap & ctl & (1 << 4)) { /* Setup irq ops and turn on vSMP IRQ fastpath handling */ pv_irq_ops.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable); @@ -102,12 +115,11 @@ static void __init set_vsmp_pv_ops(void) pv_irq_ops.save_fl = PV_CALLEE_SAVE(vsmp_save_fl); pv_irq_ops.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl); pv_init_ops.patch = vsmp_patch; - ctl &= ~(1 << 4); - writel(ctl, address + 4); - ctl = readl(address + 4); - printk(KERN_INFO "vSMP CTL: control set to:0x%08x\n", ctl); } + writel(ctl, address + 4); + ctl = readl(address + 4); + pr_info("vSMP CTL: control set to:0x%08x\n", ctl); early_iounmap(address, 8); } @@ -187,12 +199,36 @@ static void __init vsmp_cap_cpus(void) #endif } +static int apicid_phys_pkg_id(int initial_apic_id, int index_msb) +{ + return hard_smp_processor_id() >> index_msb; +} + +/* + * In vSMP, all cpus should be capable of handling interrupts, regardless of + * the APIC used. + */ +static void fill_vector_allocation_domain(int cpu, struct cpumask *retmask, + const struct cpumask *mask) +{ + cpumask_setall(retmask); +} + +static void vsmp_apic_post_init(void) +{ + /* need to update phys_pkg_id */ + apic->phys_pkg_id = apicid_phys_pkg_id; + apic->vector_allocation_domain = fill_vector_allocation_domain; +} + void __init vsmp_init(void) { detect_vsmp_box(); if (!is_vsmp_box()) return; + x86_platform.apic_post_init = vsmp_apic_post_init; + vsmp_cap_cpus(); set_vsmp_pv_ops(); diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 7515cf0e1805..8d141b309046 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -18,6 +18,8 @@ * use the vDSO. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/time.h> #include <linux/init.h> #include <linux/kernel.h> @@ -111,18 +113,13 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, const char *message) { - static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); - struct task_struct *tsk; - - if (!show_unhandled_signals || !__ratelimit(&rs)) + if (!show_unhandled_signals) return; - tsk = current; - - printk("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", - level, tsk->comm, task_pid_nr(tsk), - message, regs->ip, regs->cs, - regs->sp, regs->ax, regs->si, regs->di); + pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", + level, current->comm, task_pid_nr(current), + message, regs->ip, regs->cs, + regs->sp, regs->ax, regs->si, regs->di); } static int addr_to_vsyscall_nr(unsigned long addr) @@ -139,6 +136,19 @@ static int addr_to_vsyscall_nr(unsigned long addr) return nr; } +#ifdef CONFIG_SECCOMP +static int vsyscall_seccomp(struct task_struct *tsk, int syscall_nr) +{ + if (!seccomp_mode(&tsk->seccomp)) + return 0; + task_pt_regs(tsk)->orig_ax = syscall_nr; + task_pt_regs(tsk)->ax = syscall_nr; + return __secure_computing(syscall_nr); +} +#else +#define vsyscall_seccomp(_tsk, _nr) 0 +#endif + static bool write_ok_or_segv(unsigned long ptr, size_t size) { /* @@ -174,6 +184,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) int vsyscall_nr; int prev_sig_on_uaccess_error; long ret; + int skip; /* * No point in checking CS -- the only way to get here is a user mode @@ -205,9 +216,6 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) } tsk = current; - if (seccomp_mode(&tsk->seccomp)) - do_exit(SIGKILL); - /* * With a real vsyscall, page faults cause SIGSEGV. We want to * preserve that behavior to make writing exploits harder. @@ -222,8 +230,13 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) * address 0". */ ret = -EFAULT; + skip = 0; switch (vsyscall_nr) { case 0: + skip = vsyscall_seccomp(tsk, __NR_gettimeofday); + if (skip) + break; + if (!write_ok_or_segv(regs->di, sizeof(struct timeval)) || !write_ok_or_segv(regs->si, sizeof(struct timezone))) break; @@ -234,6 +247,10 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) break; case 1: + skip = vsyscall_seccomp(tsk, __NR_time); + if (skip) + break; + if (!write_ok_or_segv(regs->di, sizeof(time_t))) break; @@ -241,6 +258,10 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) break; case 2: + skip = vsyscall_seccomp(tsk, __NR_getcpu); + if (skip) + break; + if (!write_ok_or_segv(regs->di, sizeof(unsigned)) || !write_ok_or_segv(regs->si, sizeof(unsigned))) break; @@ -253,6 +274,12 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) current_thread_info()->sig_on_uaccess_error = prev_sig_on_uaccess_error; + if (skip) { + if ((long)regs->ax <= 0L) /* seccomp errno emulation */ + goto do_ret; + goto done; /* seccomp trace/trap */ + } + if (ret == -EFAULT) { /* Bad news -- userspace fed a bad pointer to a vsyscall. */ warn_bad_vsyscall(KERN_INFO, regs, @@ -271,10 +298,11 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) regs->ax = ret; +do_ret: /* Emulate a ret instruction. */ regs->ip = caller; regs->sp += 8; - +done: return true; sigsegv: diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 9796c2f3d074..6020f6f5927c 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -28,6 +28,7 @@ EXPORT_SYMBOL(__put_user_8); EXPORT_SYMBOL(copy_user_generic_string); EXPORT_SYMBOL(copy_user_generic_unrolled); +EXPORT_SYMBOL(copy_user_enhanced_fast_string); EXPORT_SYMBOL(__copy_user_nocache); EXPORT_SYMBOL(_copy_from_user); EXPORT_SYMBOL(_copy_to_user); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 35c5e543f550..9f3167e891ef 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -29,7 +29,6 @@ void __init x86_init_uint_noop(unsigned int unused) { } void __init x86_init_pgd_noop(pgd_t *unused) { } int __init iommu_init_noop(void) { return 0; } void iommu_shutdown_noop(void) { } -void wallclock_init_noop(void) { } /* * The platform setup functions are preset with the default functions @@ -101,7 +100,6 @@ static int default_i8042_detect(void) { return 1; }; struct x86_platform_ops x86_platform = { .calibrate_tsc = native_calibrate_tsc, - .wallclock_init = wallclock_init_noop, .get_wallclock = mach_get_cmos_time, .set_wallclock = mach_set_rtc_mmss, .iommu_shutdown = iommu_shutdown_noop, diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index bd18149b2b0f..3d3e20709119 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -3,6 +3,9 @@ * * Author: Suresh Siddha <suresh.b.siddha@intel.com> */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/bootmem.h> #include <linux/compat.h> #include <asm/i387.h> @@ -162,7 +165,7 @@ int save_i387_xstate(void __user *buf) BUG_ON(sig_xstate_size < xstate_size); if ((unsigned long)buf % 64) - printk("save_i387_xstate: bad fpstate %p\n", buf); + pr_err("%s: bad fpstate %p\n", __func__, buf); if (!used_math()) return 0; @@ -422,7 +425,7 @@ static void __init xstate_enable_boot_cpu(void) pcntxt_mask = eax + ((u64)edx << 32); if ((pcntxt_mask & XSTATE_FPSSE) != XSTATE_FPSSE) { - printk(KERN_ERR "FP/SSE not shown under xsave features 0x%llx\n", + pr_err("FP/SSE not shown under xsave features 0x%llx\n", pcntxt_mask); BUG(); } @@ -445,9 +448,8 @@ static void __init xstate_enable_boot_cpu(void) setup_xstate_init(); - printk(KERN_INFO "xsave/xrstor: enabled xstate_bv 0x%llx, " - "cntxt size 0x%x\n", - pcntxt_mask, xstate_size); + pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x\n", + pcntxt_mask, xstate_size); } /* diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index be3cea4407ff..57e168e27b5b 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3934,6 +3934,9 @@ static void kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm, { struct kvm_mmu_page *page; + if (list_empty(&kvm->arch.active_mmu_pages)) + return; + page = container_of(kvm->arch.active_mmu_pages.prev, struct kvm_mmu_page, link); kvm_mmu_prepare_zap_page(kvm, page, invalid_list); diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 2e88438ffd83..9b7ec1150ab0 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -80,10 +80,10 @@ static inline struct kvm_pmc *get_fixed_pmc_idx(struct kvm_pmu *pmu, int idx) static struct kvm_pmc *global_idx_to_pmc(struct kvm_pmu *pmu, int idx) { - if (idx < X86_PMC_IDX_FIXED) + if (idx < INTEL_PMC_IDX_FIXED) return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + idx, MSR_P6_EVNTSEL0); else - return get_fixed_pmc_idx(pmu, idx - X86_PMC_IDX_FIXED); + return get_fixed_pmc_idx(pmu, idx - INTEL_PMC_IDX_FIXED); } void kvm_deliver_pmi(struct kvm_vcpu *vcpu) @@ -291,7 +291,7 @@ static void reprogram_idx(struct kvm_pmu *pmu, int idx) if (pmc_is_gp(pmc)) reprogram_gp_counter(pmc, pmc->eventsel); else { - int fidx = idx - X86_PMC_IDX_FIXED; + int fidx = idx - INTEL_PMC_IDX_FIXED; reprogram_fixed_counter(pmc, fixed_en_pmi(pmu->fixed_ctr_ctrl, fidx), fidx); } @@ -452,7 +452,7 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu) return; pmu->nr_arch_gp_counters = min((int)(entry->eax >> 8) & 0xff, - X86_PMC_MAX_GENERIC); + INTEL_PMC_MAX_GENERIC); pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << ((entry->eax >> 16) & 0xff)) - 1; bitmap_len = (entry->eax >> 24) & 0xff; @@ -462,13 +462,13 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu) pmu->nr_arch_fixed_counters = 0; } else { pmu->nr_arch_fixed_counters = min((int)(entry->edx & 0x1f), - X86_PMC_MAX_FIXED); + INTEL_PMC_MAX_FIXED); pmu->counter_bitmask[KVM_PMC_FIXED] = ((u64)1 << ((entry->edx >> 5) & 0xff)) - 1; } pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) | - (((1ull << pmu->nr_arch_fixed_counters) - 1) << X86_PMC_IDX_FIXED); + (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED); pmu->global_ctrl_mask = ~pmu->global_ctrl; } @@ -478,15 +478,15 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) struct kvm_pmu *pmu = &vcpu->arch.pmu; memset(pmu, 0, sizeof(*pmu)); - for (i = 0; i < X86_PMC_MAX_GENERIC; i++) { + for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { pmu->gp_counters[i].type = KVM_PMC_GP; pmu->gp_counters[i].vcpu = vcpu; pmu->gp_counters[i].idx = i; } - for (i = 0; i < X86_PMC_MAX_FIXED; i++) { + for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) { pmu->fixed_counters[i].type = KVM_PMC_FIXED; pmu->fixed_counters[i].vcpu = vcpu; - pmu->fixed_counters[i].idx = i + X86_PMC_IDX_FIXED; + pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; } init_irq_work(&pmu->irq_work, trigger_pmi); kvm_pmu_cpuid_update(vcpu); @@ -498,13 +498,13 @@ void kvm_pmu_reset(struct kvm_vcpu *vcpu) int i; irq_work_sync(&pmu->irq_work); - for (i = 0; i < X86_PMC_MAX_GENERIC; i++) { + for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { struct kvm_pmc *pmc = &pmu->gp_counters[i]; stop_counter(pmc); pmc->counter = pmc->eventsel = 0; } - for (i = 0; i < X86_PMC_MAX_FIXED; i++) + for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) stop_counter(&pmu->fixed_counters[i]); pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 911d2641f14c..62d02e3c3ed6 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -710,16 +710,6 @@ TRACE_EVENT(kvm_skinit, __entry->rip, __entry->slb) ); -#define __print_insn(insn, ilen) ({ \ - int i; \ - const char *ret = p->buffer + p->len; \ - \ - for (i = 0; i < ilen; ++i) \ - trace_seq_printf(p, " %02x", insn[i]); \ - trace_seq_printf(p, "%c", 0); \ - ret; \ - }) - #define KVM_EMUL_INSN_F_CR0_PE (1 << 0) #define KVM_EMUL_INSN_F_EFL_VM (1 << 1) #define KVM_EMUL_INSN_F_CS_D (1 << 2) @@ -786,7 +776,7 @@ TRACE_EVENT(kvm_emulate_insn, TP_printk("%x:%llx:%s (%s)%s", __entry->csbase, __entry->rip, - __print_insn(__entry->insn, __entry->len), + __print_hex(__entry->insn, __entry->len), __print_symbolic(__entry->flags, kvm_trace_symbol_emul_flags), __entry->failed ? " failed" : "" diff --git a/arch/x86/lib/msr-reg-export.c b/arch/x86/lib/msr-reg-export.c index a311cc59b65d..8d6ef78b5d01 100644 --- a/arch/x86/lib/msr-reg-export.c +++ b/arch/x86/lib/msr-reg-export.c @@ -1,5 +1,5 @@ #include <linux/module.h> #include <asm/msr.h> -EXPORT_SYMBOL(native_rdmsr_safe_regs); -EXPORT_SYMBOL(native_wrmsr_safe_regs); +EXPORT_SYMBOL(rdmsr_safe_regs); +EXPORT_SYMBOL(wrmsr_safe_regs); diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S index 69fa10623f21..f6d13eefad10 100644 --- a/arch/x86/lib/msr-reg.S +++ b/arch/x86/lib/msr-reg.S @@ -6,13 +6,13 @@ #ifdef CONFIG_X86_64 /* - * int native_{rdmsr,wrmsr}_safe_regs(u32 gprs[8]); + * int {rdmsr,wrmsr}_safe_regs(u32 gprs[8]); * * reg layout: u32 gprs[eax, ecx, edx, ebx, esp, ebp, esi, edi] * */ .macro op_safe_regs op -ENTRY(native_\op\()_safe_regs) +ENTRY(\op\()_safe_regs) CFI_STARTPROC pushq_cfi %rbx pushq_cfi %rbp @@ -45,13 +45,13 @@ ENTRY(native_\op\()_safe_regs) _ASM_EXTABLE(1b, 3b) CFI_ENDPROC -ENDPROC(native_\op\()_safe_regs) +ENDPROC(\op\()_safe_regs) .endm #else /* X86_32 */ .macro op_safe_regs op -ENTRY(native_\op\()_safe_regs) +ENTRY(\op\()_safe_regs) CFI_STARTPROC pushl_cfi %ebx pushl_cfi %ebp @@ -92,7 +92,7 @@ ENTRY(native_\op\()_safe_regs) _ASM_EXTABLE(1b, 3b) CFI_ENDPROC -ENDPROC(native_\op\()_safe_regs) +ENDPROC(\op\()_safe_regs) .endm #endif diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index bc4e9d84157f..e0e6990723e9 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -385,7 +385,7 @@ void free_initmem(void) } #ifdef CONFIG_BLK_DEV_INITRD -void free_initrd_mem(unsigned long start, unsigned long end) +void __init free_initrd_mem(unsigned long start, unsigned long end) { /* * end could be not aligned, and We can not align that, diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c index 303f08637826..b2b94438ff05 100644 --- a/arch/x86/oprofile/op_model_amd.c +++ b/arch/x86/oprofile/op_model_amd.c @@ -312,7 +312,7 @@ static int op_amd_fill_in_addresses(struct op_msrs * const msrs) goto fail; } /* both registers must be reserved */ - if (num_counters == AMD64_NUM_COUNTERS_F15H) { + if (num_counters == AMD64_NUM_COUNTERS_CORE) { msrs->counters[i].addr = MSR_F15H_PERF_CTR + (i << 1); msrs->controls[i].addr = MSR_F15H_PERF_CTL + (i << 1); } else { @@ -514,7 +514,7 @@ static int op_amd_init(struct oprofile_operations *ops) ops->create_files = setup_ibs_files; if (boot_cpu_data.x86 == 0x15) { - num_counters = AMD64_NUM_COUNTERS_F15H; + num_counters = AMD64_NUM_COUNTERS_CORE; } else { num_counters = AMD64_NUM_COUNTERS; } diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c index 23e5b9d7977b..599be499fdf7 100644 --- a/arch/x86/platform/olpc/olpc-xo15-sci.c +++ b/arch/x86/platform/olpc/olpc-xo15-sci.c @@ -203,7 +203,7 @@ static int xo15_sci_remove(struct acpi_device *device, int type) return 0; } -static int xo15_sci_resume(struct acpi_device *device) +static int xo15_sci_resume(struct device *dev) { /* Enable all EC events */ olpc_ec_mask_write(EC_SCI_SRC_ALL); @@ -215,6 +215,8 @@ static int xo15_sci_resume(struct acpi_device *device) return 0; } +static SIMPLE_DEV_PM_OPS(xo15_sci_pm, NULL, xo15_sci_resume); + static const struct acpi_device_id xo15_sci_device_ids[] = { {"XO15EC", 0}, {"", 0}, @@ -227,8 +229,8 @@ static struct acpi_driver xo15_sci_drv = { .ops = { .add = xo15_sci_add, .remove = xo15_sci_remove, - .resume = xo15_sci_resume, }, + .drv.pm = &xo15_sci_pm, }; static int __init xo15_sci_init(void) diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 59880afa851f..71b5d5a07d7b 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1,7 +1,7 @@ /* * SGI UltraViolet TLB flush routines. * - * (c) 2008-2011 Cliff Wickman <cpw@sgi.com>, SGI. + * (c) 2008-2012 Cliff Wickman <cpw@sgi.com>, SGI. * * This code is released under the GNU General Public License version 2 or * later. @@ -38,8 +38,7 @@ static int timeout_base_ns[] = { static int timeout_us; static int nobau; -static int baudisabled; -static spinlock_t disable_lock; +static int nobau_perm; static cycles_t congested_cycles; /* tunables: */ @@ -47,12 +46,13 @@ static int max_concurr = MAX_BAU_CONCURRENT; static int max_concurr_const = MAX_BAU_CONCURRENT; static int plugged_delay = PLUGGED_DELAY; static int plugsb4reset = PLUGSB4RESET; +static int giveup_limit = GIVEUP_LIMIT; static int timeoutsb4reset = TIMEOUTSB4RESET; static int ipi_reset_limit = IPI_RESET_LIMIT; static int complete_threshold = COMPLETE_THRESHOLD; static int congested_respns_us = CONGESTED_RESPONSE_US; static int congested_reps = CONGESTED_REPS; -static int congested_period = CONGESTED_PERIOD; +static int disabled_period = DISABLED_PERIOD; static struct tunables tunables[] = { {&max_concurr, MAX_BAU_CONCURRENT}, /* must be [0] */ @@ -63,7 +63,8 @@ static struct tunables tunables[] = { {&complete_threshold, COMPLETE_THRESHOLD}, {&congested_respns_us, CONGESTED_RESPONSE_US}, {&congested_reps, CONGESTED_REPS}, - {&congested_period, CONGESTED_PERIOD} + {&disabled_period, DISABLED_PERIOD}, + {&giveup_limit, GIVEUP_LIMIT} }; static struct dentry *tunables_dir; @@ -120,6 +121,40 @@ static DEFINE_PER_CPU(struct ptc_stats, ptcstats); static DEFINE_PER_CPU(struct bau_control, bau_control); static DEFINE_PER_CPU(cpumask_var_t, uv_flush_tlb_mask); +static void +set_bau_on(void) +{ + int cpu; + struct bau_control *bcp; + + if (nobau_perm) { + pr_info("BAU not initialized; cannot be turned on\n"); + return; + } + nobau = 0; + for_each_present_cpu(cpu) { + bcp = &per_cpu(bau_control, cpu); + bcp->nobau = 0; + } + pr_info("BAU turned on\n"); + return; +} + +static void +set_bau_off(void) +{ + int cpu; + struct bau_control *bcp; + + nobau = 1; + for_each_present_cpu(cpu) { + bcp = &per_cpu(bau_control, cpu); + bcp->nobau = 1; + } + pr_info("BAU turned off\n"); + return; +} + /* * Determine the first node on a uvhub. 'Nodes' are used for kernel * memory allocation. @@ -278,7 +313,7 @@ static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp, * Both sockets dump their completed count total into * the message's count. */ - smaster->socket_acknowledge_count[mdp->msg_slot] = 0; + *sp = 0; asp = (struct atomic_short *)&msg->acknowledge_count; msg_ack_count = atom_asr(socket_ack_count, asp); @@ -491,16 +526,15 @@ static int uv1_wait_completion(struct bau_desc *bau_desc, } /* - * UV2 has an extra bit of status in the ACTIVATION_STATUS_2 register. + * UV2 could have an extra bit of status in the ACTIVATION_STATUS_2 register. + * But not currently used. */ static unsigned long uv2_read_status(unsigned long offset, int rshft, int desc) { unsigned long descriptor_status; - unsigned long descriptor_status2; - descriptor_status = ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK); - descriptor_status2 = (read_mmr_uv2_status() >> desc) & 0x1UL; - descriptor_status = (descriptor_status << 1) | descriptor_status2; + descriptor_status = + ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK) << 1; return descriptor_status; } @@ -531,87 +565,11 @@ int normal_busy(struct bau_control *bcp) */ int handle_uv2_busy(struct bau_control *bcp) { - int busy_one = bcp->using_desc; - int normal = bcp->uvhub_cpu; - int selected = -1; - int i; - unsigned long descriptor_status; - unsigned long status; - int mmr_offset; - struct bau_desc *bau_desc_old; - struct bau_desc *bau_desc_new; - struct bau_control *hmaster = bcp->uvhub_master; struct ptc_stats *stat = bcp->statp; - cycles_t ttm; stat->s_uv2_wars++; - spin_lock(&hmaster->uvhub_lock); - /* try for the original first */ - if (busy_one != normal) { - if (!normal_busy(bcp)) - selected = normal; - } - if (selected < 0) { - /* can't use the normal, select an alternate */ - mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1; - descriptor_status = read_lmmr(mmr_offset); - - /* scan available descriptors 32-63 */ - for (i = 0; i < UV_CPUS_PER_AS; i++) { - if ((hmaster->inuse_map & (1 << i)) == 0) { - status = ((descriptor_status >> - (i * UV_ACT_STATUS_SIZE)) & - UV_ACT_STATUS_MASK) << 1; - if (status != UV2H_DESC_BUSY) { - selected = i + UV_CPUS_PER_AS; - break; - } - } - } - } - - if (busy_one != normal) - /* mark the busy alternate as not in-use */ - hmaster->inuse_map &= ~(1 << (busy_one - UV_CPUS_PER_AS)); - - if (selected >= 0) { - /* switch to the selected descriptor */ - if (selected != normal) { - /* set the selected alternate as in-use */ - hmaster->inuse_map |= - (1 << (selected - UV_CPUS_PER_AS)); - if (selected > stat->s_uv2_wars_hw) - stat->s_uv2_wars_hw = selected; - } - bau_desc_old = bcp->descriptor_base; - bau_desc_old += (ITEMS_PER_DESC * busy_one); - bcp->using_desc = selected; - bau_desc_new = bcp->descriptor_base; - bau_desc_new += (ITEMS_PER_DESC * selected); - *bau_desc_new = *bau_desc_old; - } else { - /* - * All are busy. Wait for the normal one for this cpu to - * free up. - */ - stat->s_uv2_war_waits++; - spin_unlock(&hmaster->uvhub_lock); - ttm = get_cycles(); - do { - cpu_relax(); - } while (normal_busy(bcp)); - spin_lock(&hmaster->uvhub_lock); - /* switch to the original descriptor */ - bcp->using_desc = normal; - bau_desc_old = bcp->descriptor_base; - bau_desc_old += (ITEMS_PER_DESC * bcp->using_desc); - bcp->using_desc = (ITEMS_PER_DESC * normal); - bau_desc_new = bcp->descriptor_base; - bau_desc_new += (ITEMS_PER_DESC * normal); - *bau_desc_new = *bau_desc_old; /* copy the entire descriptor */ - } - spin_unlock(&hmaster->uvhub_lock); - return FLUSH_RETRY_BUSYBUG; + bcp->busy = 1; + return FLUSH_GIVEUP; } static int uv2_wait_completion(struct bau_desc *bau_desc, @@ -620,7 +578,7 @@ static int uv2_wait_completion(struct bau_desc *bau_desc, { unsigned long descriptor_stat; cycles_t ttm; - int desc = bcp->using_desc; + int desc = bcp->uvhub_cpu; long busy_reps = 0; struct ptc_stats *stat = bcp->statp; @@ -628,24 +586,38 @@ static int uv2_wait_completion(struct bau_desc *bau_desc, /* spin on the status MMR, waiting for it to go idle */ while (descriptor_stat != UV2H_DESC_IDLE) { - /* - * Our software ack messages may be blocked because - * there are no swack resources available. As long - * as none of them has timed out hardware will NACK - * our message and its state will stay IDLE. - */ - if ((descriptor_stat == UV2H_DESC_SOURCE_TIMEOUT) || - (descriptor_stat == UV2H_DESC_DEST_PUT_ERR)) { + if ((descriptor_stat == UV2H_DESC_SOURCE_TIMEOUT)) { + /* + * A h/w bug on the destination side may + * have prevented the message being marked + * pending, thus it doesn't get replied to + * and gets continually nacked until it times + * out with a SOURCE_TIMEOUT. + */ stat->s_stimeout++; return FLUSH_GIVEUP; - } else if (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) { - stat->s_strongnacks++; - bcp->conseccompletes = 0; - return FLUSH_GIVEUP; } else if (descriptor_stat == UV2H_DESC_DEST_TIMEOUT) { + ttm = get_cycles(); + + /* + * Our retries may be blocked by all destination + * swack resources being consumed, and a timeout + * pending. In that case hardware returns the + * ERROR that looks like a destination timeout. + * Without using the extended status we have to + * deduce from the short time that this was a + * strong nack. + */ + if (cycles_2_us(ttm - bcp->send_message) < timeout_us) { + bcp->conseccompletes = 0; + stat->s_plugged++; + /* FLUSH_RETRY_PLUGGED causes hang on boot */ + return FLUSH_GIVEUP; + } stat->s_dtimeout++; bcp->conseccompletes = 0; - return FLUSH_RETRY_TIMEOUT; + /* FLUSH_RETRY_TIMEOUT causes hang on boot */ + return FLUSH_GIVEUP; } else { busy_reps++; if (busy_reps > 1000000) { @@ -653,9 +625,8 @@ static int uv2_wait_completion(struct bau_desc *bau_desc, busy_reps = 0; ttm = get_cycles(); if ((ttm - bcp->send_message) > - (bcp->clocks_per_100_usec)) { + bcp->timeout_interval) return handle_uv2_busy(bcp); - } } /* * descriptor_stat is still BUSY @@ -679,7 +650,7 @@ static int wait_completion(struct bau_desc *bau_desc, { int right_shift; unsigned long mmr_offset; - int desc = bcp->using_desc; + int desc = bcp->uvhub_cpu; if (desc < UV_CPUS_PER_AS) { mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0; @@ -758,33 +729,31 @@ static void destination_timeout(struct bau_desc *bau_desc, } /* - * Completions are taking a very long time due to a congested numalink - * network. + * Stop all cpus on a uvhub from using the BAU for a period of time. + * This is reversed by check_enable. */ -static void disable_for_congestion(struct bau_control *bcp, - struct ptc_stats *stat) +static void disable_for_period(struct bau_control *bcp, struct ptc_stats *stat) { - /* let only one cpu do this disabling */ - spin_lock(&disable_lock); - - if (!baudisabled && bcp->period_requests && - ((bcp->period_time / bcp->period_requests) > congested_cycles)) { - int tcpu; - struct bau_control *tbcp; - /* it becomes this cpu's job to turn on the use of the - BAU again */ - baudisabled = 1; - bcp->set_bau_off = 1; - bcp->set_bau_on_time = get_cycles(); - bcp->set_bau_on_time += sec_2_cycles(bcp->cong_period); + int tcpu; + struct bau_control *tbcp; + struct bau_control *hmaster; + cycles_t tm1; + + hmaster = bcp->uvhub_master; + spin_lock(&hmaster->disable_lock); + if (!bcp->baudisabled) { stat->s_bau_disabled++; + tm1 = get_cycles(); for_each_present_cpu(tcpu) { tbcp = &per_cpu(bau_control, tcpu); - tbcp->baudisabled = 1; + if (tbcp->uvhub_master == hmaster) { + tbcp->baudisabled = 1; + tbcp->set_bau_on_time = + tm1 + bcp->disabled_period; + } } } - - spin_unlock(&disable_lock); + spin_unlock(&hmaster->disable_lock); } static void count_max_concurr(int stat, struct bau_control *bcp, @@ -815,16 +784,30 @@ static void record_send_stats(cycles_t time1, cycles_t time2, bcp->period_requests++; bcp->period_time += elapsed; if ((elapsed > congested_cycles) && - (bcp->period_requests > bcp->cong_reps)) - disable_for_congestion(bcp, stat); + (bcp->period_requests > bcp->cong_reps) && + ((bcp->period_time / bcp->period_requests) > + congested_cycles)) { + stat->s_congested++; + disable_for_period(bcp, stat); + } } } else stat->s_requestor--; if (completion_status == FLUSH_COMPLETE && try > 1) stat->s_retriesok++; - else if (completion_status == FLUSH_GIVEUP) + else if (completion_status == FLUSH_GIVEUP) { stat->s_giveup++; + if (get_cycles() > bcp->period_end) + bcp->period_giveups = 0; + bcp->period_giveups++; + if (bcp->period_giveups == 1) + bcp->period_end = get_cycles() + bcp->disabled_period; + if (bcp->period_giveups > bcp->giveup_limit) { + disable_for_period(bcp, stat); + stat->s_giveuplimit++; + } + } } /* @@ -868,7 +851,8 @@ static void handle_cmplt(int completion_status, struct bau_desc *bau_desc, * Returns 1 if it gives up entirely and the original cpu mask is to be * returned to the kernel. */ -int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp) +int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp, + struct bau_desc *bau_desc) { int seq_number = 0; int completion_stat = 0; @@ -881,24 +865,23 @@ int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp) struct bau_control *hmaster = bcp->uvhub_master; struct uv1_bau_msg_header *uv1_hdr = NULL; struct uv2_bau_msg_header *uv2_hdr = NULL; - struct bau_desc *bau_desc; - if (bcp->uvhub_version == 1) + if (bcp->uvhub_version == 1) { + uv1 = 1; uv1_throttle(hmaster, stat); + } while (hmaster->uvhub_quiesce) cpu_relax(); time1 = get_cycles(); + if (uv1) + uv1_hdr = &bau_desc->header.uv1_hdr; + else + uv2_hdr = &bau_desc->header.uv2_hdr; + do { - bau_desc = bcp->descriptor_base; - bau_desc += (ITEMS_PER_DESC * bcp->using_desc); - if (bcp->uvhub_version == 1) { - uv1 = 1; - uv1_hdr = &bau_desc->header.uv1_hdr; - } else - uv2_hdr = &bau_desc->header.uv2_hdr; - if ((try == 0) || (completion_stat == FLUSH_RETRY_BUSYBUG)) { + if (try == 0) { if (uv1) uv1_hdr->msg_type = MSG_REGULAR; else @@ -916,25 +899,24 @@ int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp) uv1_hdr->sequence = seq_number; else uv2_hdr->sequence = seq_number; - index = (1UL << AS_PUSH_SHIFT) | bcp->using_desc; + index = (1UL << AS_PUSH_SHIFT) | bcp->uvhub_cpu; bcp->send_message = get_cycles(); write_mmr_activation(index); try++; completion_stat = wait_completion(bau_desc, bcp, try); - /* UV2: wait_completion() may change the bcp->using_desc */ handle_cmplt(completion_stat, bau_desc, bcp, hmaster, stat); if (bcp->ipi_attempts >= bcp->ipi_reset_limit) { bcp->ipi_attempts = 0; + stat->s_overipilimit++; completion_stat = FLUSH_GIVEUP; break; } cpu_relax(); } while ((completion_stat == FLUSH_RETRY_PLUGGED) || - (completion_stat == FLUSH_RETRY_BUSYBUG) || (completion_stat == FLUSH_RETRY_TIMEOUT)); time2 = get_cycles(); @@ -955,28 +937,33 @@ int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp) } /* - * The BAU is disabled. When the disabled time period has expired, the cpu - * that disabled it must re-enable it. - * Return 0 if it is re-enabled for all cpus. + * The BAU is disabled for this uvhub. When the disabled time period has + * expired re-enable it. + * Return 0 if it is re-enabled for all cpus on this uvhub. */ static int check_enable(struct bau_control *bcp, struct ptc_stats *stat) { int tcpu; struct bau_control *tbcp; + struct bau_control *hmaster; - if (bcp->set_bau_off) { - if (get_cycles() >= bcp->set_bau_on_time) { - stat->s_bau_reenabled++; - baudisabled = 0; - for_each_present_cpu(tcpu) { - tbcp = &per_cpu(bau_control, tcpu); + hmaster = bcp->uvhub_master; + spin_lock(&hmaster->disable_lock); + if (bcp->baudisabled && (get_cycles() >= bcp->set_bau_on_time)) { + stat->s_bau_reenabled++; + for_each_present_cpu(tcpu) { + tbcp = &per_cpu(bau_control, tcpu); + if (tbcp->uvhub_master == hmaster) { tbcp->baudisabled = 0; tbcp->period_requests = 0; tbcp->period_time = 0; + tbcp->period_giveups = 0; } - return 0; } + spin_unlock(&hmaster->disable_lock); + return 0; } + spin_unlock(&hmaster->disable_lock); return -1; } @@ -1078,18 +1065,32 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct cpumask *flush_mask; struct ptc_stats *stat; struct bau_control *bcp; - - /* kernel was booted 'nobau' */ - if (nobau) - return cpumask; + unsigned long descriptor_status; + unsigned long status; bcp = &per_cpu(bau_control, cpu); stat = bcp->statp; + stat->s_enters++; + + if (bcp->nobau) + return cpumask; + + if (bcp->busy) { + descriptor_status = + read_lmmr(UVH_LB_BAU_SB_ACTIVATION_STATUS_0); + status = ((descriptor_status >> (bcp->uvhub_cpu * + UV_ACT_STATUS_SIZE)) & UV_ACT_STATUS_MASK) << 1; + if (status == UV2H_DESC_BUSY) + return cpumask; + bcp->busy = 0; + } /* bau was disabled due to slow response */ if (bcp->baudisabled) { - if (check_enable(bcp, stat)) + if (check_enable(bcp, stat)) { + stat->s_ipifordisabled++; return cpumask; + } } /* @@ -1105,7 +1106,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, stat->s_ntargself++; bau_desc = bcp->descriptor_base; - bau_desc += (ITEMS_PER_DESC * bcp->using_desc); + bau_desc += (ITEMS_PER_DESC * bcp->uvhub_cpu); bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE); if (set_distrib_bits(flush_mask, bcp, bau_desc, &locals, &remotes)) return NULL; @@ -1118,25 +1119,27 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, * uv_flush_send_and_wait returns 0 if all cpu's were messaged, * or 1 if it gave up and the original cpumask should be returned. */ - if (!uv_flush_send_and_wait(flush_mask, bcp)) + if (!uv_flush_send_and_wait(flush_mask, bcp, bau_desc)) return NULL; else return cpumask; } /* - * Search the message queue for any 'other' message with the same software - * acknowledge resource bit vector. + * Search the message queue for any 'other' unprocessed message with the + * same software acknowledge resource bit vector as the 'msg' message. */ struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg, - struct bau_control *bcp, unsigned char swack_vec) + struct bau_control *bcp) { struct bau_pq_entry *msg_next = msg + 1; + unsigned char swack_vec = msg->swack_vec; if (msg_next > bcp->queue_last) msg_next = bcp->queue_first; - while ((msg_next->swack_vec != 0) && (msg_next != msg)) { - if (msg_next->swack_vec == swack_vec) + while (msg_next != msg) { + if ((msg_next->canceled == 0) && (msg_next->replied_to == 0) && + (msg_next->swack_vec == swack_vec)) return msg_next; msg_next++; if (msg_next > bcp->queue_last) @@ -1165,32 +1168,30 @@ void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp) * This message was assigned a swack resource, but no * reserved acknowlegment is pending. * The bug has prevented this message from setting the MMR. - * And no other message has used the same sw_ack resource. - * Do the requested shootdown but do not reply to the msg. - * (the 0 means make no acknowledge) */ - bau_process_message(mdp, bcp, 0); - return; - } - - /* - * Some message has set the MMR 'pending' bit; it might have been - * another message. Look for that message. - */ - other_msg = find_another_by_swack(msg, bcp, msg->swack_vec); - if (other_msg) { - /* There is another. Do not ack the current one. */ - bau_process_message(mdp, bcp, 0); /* - * Let the natural processing of that message acknowledge - * it. Don't get the processing of sw_ack's out of order. + * Some message has set the MMR 'pending' bit; it might have + * been another message. Look for that message. */ - return; + other_msg = find_another_by_swack(msg, bcp); + if (other_msg) { + /* + * There is another. Process this one but do not + * ack it. + */ + bau_process_message(mdp, bcp, 0); + /* + * Let the natural processing of that other message + * acknowledge it. Don't get the processing of sw_ack's + * out of order. + */ + return; + } } /* - * There is no other message using this sw_ack, so it is safe to - * acknowledge it. + * Either the MMR shows this one pending a reply or there is no + * other message using this sw_ack, so it is safe to acknowledge it. */ bau_process_message(mdp, bcp, 1); @@ -1295,7 +1296,8 @@ static void __init enable_timeouts(void) */ mmr_image |= (1L << SOFTACK_MSHIFT); if (is_uv2_hub()) { - mmr_image |= (1L << UV2_EXT_SHFT); + /* hw bug workaround; do not use extended status */ + mmr_image &= ~(1L << UV2_EXT_SHFT); } write_mmr_misc_control(pnode, mmr_image); } @@ -1338,29 +1340,34 @@ static inline unsigned long long usec_2_cycles(unsigned long microsec) static int ptc_seq_show(struct seq_file *file, void *data) { struct ptc_stats *stat; + struct bau_control *bcp; int cpu; cpu = *(loff_t *)data; if (!cpu) { seq_printf(file, - "# cpu sent stime self locals remotes ncpus localhub "); + "# cpu bauoff sent stime self locals remotes ncpus localhub "); seq_printf(file, "remotehub numuvhubs numuvhubs16 numuvhubs8 "); seq_printf(file, - "numuvhubs4 numuvhubs2 numuvhubs1 dto snacks retries rok "); + "numuvhubs4 numuvhubs2 numuvhubs1 dto snacks retries "); + seq_printf(file, + "rok resetp resett giveup sto bz throt disable "); seq_printf(file, - "resetp resett giveup sto bz throt swack recv rtime "); + "enable wars warshw warwaits enters ipidis plugged "); seq_printf(file, - "all one mult none retry canc nocan reset rcan "); + "ipiover glim cong swack recv rtime all one mult "); seq_printf(file, - "disable enable wars warshw warwaits\n"); + "none retry canc nocan reset rcan\n"); } if (cpu < num_possible_cpus() && cpu_online(cpu)) { - stat = &per_cpu(ptcstats, cpu); + bcp = &per_cpu(bau_control, cpu); + stat = bcp->statp; /* source side statistics */ seq_printf(file, - "cpu %d %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ", - cpu, stat->s_requestor, cycles_2_us(stat->s_time), + "cpu %d %d %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ", + cpu, bcp->nobau, stat->s_requestor, + cycles_2_us(stat->s_time), stat->s_ntargself, stat->s_ntarglocals, stat->s_ntargremotes, stat->s_ntargcpu, stat->s_ntarglocaluvhub, stat->s_ntargremoteuvhub, @@ -1374,20 +1381,23 @@ static int ptc_seq_show(struct seq_file *file, void *data) stat->s_resets_plug, stat->s_resets_timeout, stat->s_giveup, stat->s_stimeout, stat->s_busy, stat->s_throttles); + seq_printf(file, "%ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ", + stat->s_bau_disabled, stat->s_bau_reenabled, + stat->s_uv2_wars, stat->s_uv2_wars_hw, + stat->s_uv2_war_waits, stat->s_enters, + stat->s_ipifordisabled, stat->s_plugged, + stat->s_overipilimit, stat->s_giveuplimit, + stat->s_congested); /* destination side statistics */ seq_printf(file, - "%lx %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ", + "%lx %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld\n", read_gmmr_sw_ack(uv_cpu_to_pnode(cpu)), stat->d_requestee, cycles_2_us(stat->d_time), stat->d_alltlb, stat->d_onetlb, stat->d_multmsg, stat->d_nomsg, stat->d_retries, stat->d_canceled, stat->d_nocanceled, stat->d_resets, stat->d_rcanceled); - seq_printf(file, "%ld %ld %ld %ld %ld\n", - stat->s_bau_disabled, stat->s_bau_reenabled, - stat->s_uv2_wars, stat->s_uv2_wars_hw, - stat->s_uv2_war_waits); } return 0; } @@ -1401,13 +1411,14 @@ static ssize_t tunables_read(struct file *file, char __user *userbuf, char *buf; int ret; - buf = kasprintf(GFP_KERNEL, "%s %s %s\n%d %d %d %d %d %d %d %d %d\n", - "max_concur plugged_delay plugsb4reset", - "timeoutsb4reset ipi_reset_limit complete_threshold", - "congested_response_us congested_reps congested_period", + buf = kasprintf(GFP_KERNEL, "%s %s %s\n%d %d %d %d %d %d %d %d %d %d\n", + "max_concur plugged_delay plugsb4reset timeoutsb4reset", + "ipi_reset_limit complete_threshold congested_response_us", + "congested_reps disabled_period giveup_limit", max_concurr, plugged_delay, plugsb4reset, timeoutsb4reset, ipi_reset_limit, complete_threshold, - congested_respns_us, congested_reps, congested_period); + congested_respns_us, congested_reps, disabled_period, + giveup_limit); if (!buf) return -ENOMEM; @@ -1438,6 +1449,14 @@ static ssize_t ptc_proc_write(struct file *file, const char __user *user, return -EFAULT; optstr[count - 1] = '\0'; + if (!strcmp(optstr, "on")) { + set_bau_on(); + return count; + } else if (!strcmp(optstr, "off")) { + set_bau_off(); + return count; + } + if (strict_strtol(optstr, 10, &input_arg) < 0) { printk(KERN_DEBUG "%s is invalid\n", optstr); return -EINVAL; @@ -1570,7 +1589,8 @@ static ssize_t tunables_write(struct file *file, const char __user *user, bcp->complete_threshold = complete_threshold; bcp->cong_response_us = congested_respns_us; bcp->cong_reps = congested_reps; - bcp->cong_period = congested_period; + bcp->disabled_period = sec_2_cycles(disabled_period); + bcp->giveup_limit = giveup_limit; } return count; } @@ -1699,6 +1719,10 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode) * fairness chaining multilevel count replied_to */ } else { + /* + * BIOS uses legacy mode, but UV2 hardware always + * uses native mode for selective broadcasts. + */ uv2_hdr = &bd2->header.uv2_hdr; uv2_hdr->swack_flag = 1; uv2_hdr->base_dest_nasid = @@ -1811,8 +1835,8 @@ static int calculate_destination_timeout(void) index = (mmr_image >> BAU_URGENCY_7_SHIFT) & BAU_URGENCY_7_MASK; mmr_image = uv_read_local_mmr(UVH_TRANSACTION_TIMEOUT); mult2 = (mmr_image >> BAU_TRANS_SHIFT) & BAU_TRANS_MASK; - base = timeout_base_ns[index]; - ts_ns = base * mult1 * mult2; + ts_ns = timeout_base_ns[index]; + ts_ns *= (mult1 * mult2); ret = ts_ns / 1000; } else { /* 4 bits 0/1 for 10/80us base, 3 bits of multiplier */ @@ -1836,6 +1860,8 @@ static void __init init_per_cpu_tunables(void) for_each_present_cpu(cpu) { bcp = &per_cpu(bau_control, cpu); bcp->baudisabled = 0; + if (nobau) + bcp->nobau = 1; bcp->statp = &per_cpu(ptcstats, cpu); /* time interval to catch a hardware stay-busy bug */ bcp->timeout_interval = usec_2_cycles(2*timeout_us); @@ -1848,10 +1874,11 @@ static void __init init_per_cpu_tunables(void) bcp->complete_threshold = complete_threshold; bcp->cong_response_us = congested_respns_us; bcp->cong_reps = congested_reps; - bcp->cong_period = congested_period; - bcp->clocks_per_100_usec = usec_2_cycles(100); + bcp->disabled_period = sec_2_cycles(disabled_period); + bcp->giveup_limit = giveup_limit; spin_lock_init(&bcp->queue_lock); spin_lock_init(&bcp->uvhub_lock); + spin_lock_init(&bcp->disable_lock); } } @@ -1972,7 +1999,6 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp, } bcp->uvhub_master = *hmasterp; bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->blade_processor_id; - bcp->using_desc = bcp->uvhub_cpu; if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) { printk(KERN_EMERG "%d cpus per uvhub invalid\n", bcp->uvhub_cpu); @@ -2069,16 +2095,12 @@ static int __init uv_bau_init(void) if (!is_uv_system()) return 0; - if (nobau) - return 0; - for_each_possible_cpu(cur_cpu) { mask = &per_cpu(uv_flush_tlb_mask, cur_cpu); zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cur_cpu)); } nuvhubs = uv_num_possible_blades(); - spin_lock_init(&disable_lock); congested_cycles = usec_2_cycles(congested_respns_us); uv_base_pnode = 0x7fffffff; @@ -2091,7 +2113,8 @@ static int __init uv_bau_init(void) enable_timeouts(); if (init_per_cpu(nuvhubs, uv_base_pnode)) { - nobau = 1; + set_bau_off(); + nobau_perm = 1; return 0; } diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index f25c2765a5c9..acf7752da952 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -135,6 +135,7 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, unsigned long mmr_value; struct uv_IO_APIC_route_entry *entry; int mmr_pnode, err; + unsigned int dest; BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long)); @@ -143,6 +144,10 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, if (err != 0) return err; + err = apic->cpu_mask_to_apicid_and(eligible_cpu, eligible_cpu, &dest); + if (err != 0) + return err; + if (limit == UV_AFFINITY_CPU) irq_set_status_flags(irq, IRQ_NO_BALANCING); else @@ -159,7 +164,7 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, entry->polarity = 0; entry->trigger = 0; entry->mask = 0; - entry->dest = apic->cpu_mask_to_apicid(eligible_cpu); + entry->dest = dest; mmr_pnode = uv_blade_to_pnode(mmr_blade); uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); @@ -222,7 +227,7 @@ uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask, if (cfg->move_in_progress) send_cleanup_vector(cfg); - return 0; + return IRQ_SET_MASK_OK_NOCOPY; } /* diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index 5b84a2d30888..b2d534cab25f 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -22,7 +22,7 @@ wakeup-objs += video-bios.o realmode-y += header.o realmode-y += trampoline_$(BITS).o realmode-y += stack.o -realmode-$(CONFIG_X86_32) += reboot_32.o +realmode-y += reboot.o realmode-$(CONFIG_ACPI_SLEEP) += $(wakeup-objs) targets += $(realmode-y) diff --git a/arch/x86/realmode/rm/header.S b/arch/x86/realmode/rm/header.S index fadf48378ada..a28221d94e69 100644 --- a/arch/x86/realmode/rm/header.S +++ b/arch/x86/realmode/rm/header.S @@ -6,6 +6,7 @@ #include <linux/linkage.h> #include <asm/page_types.h> +#include <asm/segment.h> #include "realmode.h" @@ -28,8 +29,9 @@ GLOBAL(real_mode_header) .long pa_wakeup_header #endif /* APM/BIOS reboot */ -#ifdef CONFIG_X86_32 .long pa_machine_real_restart_asm +#ifdef CONFIG_X86_64 + .long __KERNEL32_CS #endif END(real_mode_header) diff --git a/arch/x86/realmode/rm/reboot_32.S b/arch/x86/realmode/rm/reboot.S index 114044876b3d..f932ea61d1c8 100644 --- a/arch/x86/realmode/rm/reboot_32.S +++ b/arch/x86/realmode/rm/reboot.S @@ -2,6 +2,8 @@ #include <linux/init.h> #include <asm/segment.h> #include <asm/page_types.h> +#include <asm/processor-flags.h> +#include <asm/msr-index.h> #include "realmode.h" /* @@ -12,13 +14,35 @@ * doesn't work with at least one type of 486 motherboard. It is easy * to stop this code working; hence the copious comments. * - * This code is called with the restart type (0 = BIOS, 1 = APM) in %eax. + * This code is called with the restart type (0 = BIOS, 1 = APM) in + * the primary argument register (%eax for 32 bit, %edi for 64 bit). */ .section ".text32", "ax" .code32 - - .balign 16 ENTRY(machine_real_restart_asm) + +#ifdef CONFIG_X86_64 + /* Switch to trampoline GDT as it is guaranteed < 4 GiB */ + movl $__KERNEL_DS, %eax + movl %eax, %ds + lgdtl pa_tr_gdt + + /* Disable paging to drop us out of long mode */ + movl %cr0, %eax + andl $~X86_CR0_PG, %eax + movl %eax, %cr0 + ljmpl $__KERNEL32_CS, $pa_machine_real_restart_paging_off + +GLOBAL(machine_real_restart_paging_off) + xorl %eax, %eax + xorl %edx, %edx + movl $MSR_EFER, %ecx + wrmsr + + movl %edi, %eax + +#endif /* CONFIG_X86_64 */ + /* Set up the IDT for real mode. */ lidtl pa_machine_real_restart_idt diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 66e6d9359826..0faad646f5fd 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -205,9 +205,9 @@ void syscall32_cpu_init(void) { /* Load these always in case some future AMD CPU supports SYSENTER from compat mode too. */ - checking_wrmsrl(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); - checking_wrmsrl(MSR_IA32_SYSENTER_ESP, 0ULL); - checking_wrmsrl(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); + wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); + wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); wrmsrl(MSR_CSTAR, ia32_cstar_target); } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index ff962d4b821e..ed7d54985d0c 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1124,9 +1124,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .wbinvd = native_wbinvd, .read_msr = native_read_msr_safe, - .rdmsr_regs = native_rdmsr_safe_regs, .write_msr = xen_write_msr_safe, - .wrmsr_regs = native_wrmsr_safe_regs, .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index afb250d22a6b..f58dca7a6e52 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -80,9 +80,7 @@ static void __cpuinit cpu_bringup(void) notify_cpu_starting(cpu); - ipi_call_lock(); set_cpu_online(cpu, true); - ipi_call_unlock(); this_cpu_write(cpu_state, CPU_ONLINE); diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 9b306e550e3f..2c8d6a3d250a 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -277,7 +277,7 @@ void xtensa_elf_core_copy_regs (xtensa_gregset_t *elfregs, struct pt_regs *regs) /* Don't leak any random bits. */ - memset(elfregs, 0, sizeof (elfregs)); + memset(elfregs, 0, sizeof(*elfregs)); /* Note: PS.EXCM is not set while user task is running; its * being set in regs->ps is for exception handling convenience. diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 02cf6335e9bd..e7dee617358e 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -125,12 +125,8 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q) blkg->pd[i] = pd; pd->blkg = blkg; - } - - /* invoke per-policy init */ - for (i = 0; i < BLKCG_MAX_POLS; i++) { - struct blkcg_policy *pol = blkcg_policy[i]; + /* invoke per-policy init */ if (blkcg_policy_enabled(blkg->q, pol)) pol->pd_init_fn(blkg); } @@ -245,10 +241,9 @@ EXPORT_SYMBOL_GPL(blkg_lookup_create); static void blkg_destroy(struct blkcg_gq *blkg) { - struct request_queue *q = blkg->q; struct blkcg *blkcg = blkg->blkcg; - lockdep_assert_held(q->queue_lock); + lockdep_assert_held(blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); /* Something wrong if we are trying to remove same group twice */ diff --git a/block/blk-core.c b/block/blk-core.c index 3c923a7aeb56..93eb3e4f88ce 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -361,9 +361,10 @@ EXPORT_SYMBOL(blk_put_queue); */ void blk_drain_queue(struct request_queue *q, bool drain_all) { + int i; + while (true) { bool drain = false; - int i; spin_lock_irq(q->queue_lock); @@ -408,6 +409,18 @@ void blk_drain_queue(struct request_queue *q, bool drain_all) break; msleep(10); } + + /* + * With queue marked dead, any woken up waiter will fail the + * allocation path, so the wakeup chaining is lost and we're + * left with hung waiters. We need to wake up those waiters. + */ + if (q->request_fn) { + spin_lock_irq(q->queue_lock); + for (i = 0; i < ARRAY_SIZE(q->rq.wait); i++) + wake_up_all(&q->rq.wait[i]); + spin_unlock_irq(q->queue_lock); + } } /** @@ -467,7 +480,6 @@ void blk_cleanup_queue(struct request_queue *q) /* mark @q DEAD, no new request or merges will be allowed afterwards */ mutex_lock(&q->sysfs_lock); queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q); - spin_lock_irq(lock); /* @@ -485,10 +497,6 @@ void blk_cleanup_queue(struct request_queue *q) queue_flag_set(QUEUE_FLAG_NOMERGES, q); queue_flag_set(QUEUE_FLAG_NOXMERGES, q); queue_flag_set(QUEUE_FLAG_DEAD, q); - - if (q->queue_lock != &q->__queue_lock) - q->queue_lock = &q->__queue_lock; - spin_unlock_irq(lock); mutex_unlock(&q->sysfs_lock); @@ -499,6 +507,11 @@ void blk_cleanup_queue(struct request_queue *q) del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer); blk_sync_queue(q); + spin_lock_irq(lock); + if (q->queue_lock != &q->__queue_lock) + q->queue_lock = &q->__queue_lock; + spin_unlock_irq(lock); + /* @q is and will stay empty, shutdown and put */ blk_put_queue(q); } diff --git a/block/blk-timeout.c b/block/blk-timeout.c index 780354888958..6e4744cbfb56 100644 --- a/block/blk-timeout.c +++ b/block/blk-timeout.c @@ -197,44 +197,3 @@ void blk_add_timer(struct request *req) mod_timer(&q->timeout, expiry); } -/** - * blk_abort_queue -- Abort all request on given queue - * @queue: pointer to queue - * - */ -void blk_abort_queue(struct request_queue *q) -{ - unsigned long flags; - struct request *rq, *tmp; - LIST_HEAD(list); - - /* - * Not a request based block device, nothing to abort - */ - if (!q->request_fn) - return; - - spin_lock_irqsave(q->queue_lock, flags); - - elv_abort_queue(q); - - /* - * Splice entries to local list, to avoid deadlocking if entries - * get readded to the timeout list by error handling - */ - list_splice_init(&q->timeout_list, &list); - - list_for_each_entry_safe(rq, tmp, &list, timeout_list) - blk_abort_request(rq); - - /* - * Occasionally, blk_abort_request() will return without - * deleting the element from the list. Make sure we add those back - * instead of leaving them on the local stack list. - */ - list_splice(&list, &q->timeout_list); - - spin_unlock_irqrestore(q->queue_lock, flags); - -} -EXPORT_SYMBOL_GPL(blk_abort_queue); diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 673c977cc2bf..fb52df9744f5 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -17,8 +17,6 @@ #include "blk.h" #include "blk-cgroup.h" -static struct blkcg_policy blkcg_policy_cfq __maybe_unused; - /* * tunables */ @@ -418,11 +416,6 @@ static inline struct cfq_group *pd_to_cfqg(struct blkg_policy_data *pd) return pd ? container_of(pd, struct cfq_group, pd) : NULL; } -static inline struct cfq_group *blkg_to_cfqg(struct blkcg_gq *blkg) -{ - return pd_to_cfqg(blkg_to_pd(blkg, &blkcg_policy_cfq)); -} - static inline struct blkcg_gq *cfqg_to_blkg(struct cfq_group *cfqg) { return pd_to_blkg(&cfqg->pd); @@ -572,6 +565,13 @@ static inline void cfqg_stats_update_avg_queue_size(struct cfq_group *cfqg) { } #ifdef CONFIG_CFQ_GROUP_IOSCHED +static struct blkcg_policy blkcg_policy_cfq; + +static inline struct cfq_group *blkg_to_cfqg(struct blkcg_gq *blkg) +{ + return pd_to_cfqg(blkg_to_pd(blkg, &blkcg_policy_cfq)); +} + static inline void cfqg_get(struct cfq_group *cfqg) { return blkg_get(cfqg_to_blkg(cfqg)); @@ -3951,10 +3951,11 @@ static void cfq_exit_queue(struct elevator_queue *e) cfq_shutdown_timer_wq(cfqd); -#ifndef CONFIG_CFQ_GROUP_IOSCHED +#ifdef CONFIG_CFQ_GROUP_IOSCHED + blkcg_deactivate_policy(q, &blkcg_policy_cfq); +#else kfree(cfqd->root_group); #endif - blkcg_deactivate_policy(q, &blkcg_policy_cfq); kfree(cfqd); } @@ -4194,14 +4195,15 @@ static int __init cfq_init(void) #ifdef CONFIG_CFQ_GROUP_IOSCHED if (!cfq_group_idle) cfq_group_idle = 1; -#else - cfq_group_idle = 0; -#endif ret = blkcg_policy_register(&blkcg_policy_cfq); if (ret) return ret; +#else + cfq_group_idle = 0; +#endif + ret = -ENOMEM; cfq_pool = KMEM_CACHE(cfq_queue, 0); if (!cfq_pool) goto err_pol_unreg; @@ -4215,13 +4217,17 @@ static int __init cfq_init(void) err_free_pool: kmem_cache_destroy(cfq_pool); err_pol_unreg: +#ifdef CONFIG_CFQ_GROUP_IOSCHED blkcg_policy_unregister(&blkcg_policy_cfq); +#endif return ret; } static void __exit cfq_exit(void) { +#ifdef CONFIG_CFQ_GROUP_IOSCHED blkcg_policy_unregister(&blkcg_policy_cfq); +#endif elv_unregister(&iosched_cfq); kmem_cache_destroy(cfq_pool); } diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 260fa80ef575..9a87daa6f4fb 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -721,11 +721,14 @@ int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd) break; } + if (capable(CAP_SYS_RAWIO)) + return 0; + /* In particular, rule out all resets and host-specific ioctls. */ printk_ratelimited(KERN_WARNING "%s: sending ioctl %x to a partition!\n", current->comm, cmd); - return capable(CAP_SYS_RAWIO) ? 0 : -ENOIOCTLCMD; + return -ENOIOCTLCMD; } EXPORT_SYMBOL(scsi_verify_blk_ioctl); diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c index 6512b20aeccd..ff9f6bd48301 100644 --- a/drivers/acpi/ac.c +++ b/drivers/acpi/ac.c @@ -61,7 +61,6 @@ static int acpi_ac_open_fs(struct inode *inode, struct file *file); static int acpi_ac_add(struct acpi_device *device); static int acpi_ac_remove(struct acpi_device *device, int type); -static int acpi_ac_resume(struct acpi_device *device); static void acpi_ac_notify(struct acpi_device *device, u32 event); static const struct acpi_device_id ac_device_ids[] = { @@ -70,6 +69,9 @@ static const struct acpi_device_id ac_device_ids[] = { }; MODULE_DEVICE_TABLE(acpi, ac_device_ids); +static int acpi_ac_resume(struct device *dev); +static SIMPLE_DEV_PM_OPS(acpi_ac_pm, NULL, acpi_ac_resume); + static struct acpi_driver acpi_ac_driver = { .name = "ac", .class = ACPI_AC_CLASS, @@ -78,9 +80,9 @@ static struct acpi_driver acpi_ac_driver = { .ops = { .add = acpi_ac_add, .remove = acpi_ac_remove, - .resume = acpi_ac_resume, .notify = acpi_ac_notify, }, + .drv.pm = &acpi_ac_pm, }; struct acpi_ac { @@ -309,13 +311,18 @@ static int acpi_ac_add(struct acpi_device *device) return result; } -static int acpi_ac_resume(struct acpi_device *device) +static int acpi_ac_resume(struct device *dev) { struct acpi_ac *ac; unsigned old_state; - if (!device || !acpi_driver_data(device)) + + if (!dev) return -EINVAL; - ac = acpi_driver_data(device); + + ac = acpi_driver_data(to_acpi_device(dev)); + if (!ac) + return -EINVAL; + old_state = ac->state; if (acpi_ac_get_state(ac)) return 0; diff --git a/drivers/acpi/acpica/hwsleep.c b/drivers/acpi/acpica/hwsleep.c index 0ed85cac3231..615996a36bed 100644 --- a/drivers/acpi/acpica/hwsleep.c +++ b/drivers/acpi/acpica/hwsleep.c @@ -95,18 +95,6 @@ acpi_status acpi_hw_legacy_sleep(u8 sleep_state, u8 flags) return_ACPI_STATUS(status); } - if (sleep_state != ACPI_STATE_S5) { - /* - * Disable BM arbitration. This feature is contained within an - * optional register (PM2 Control), so ignore a BAD_ADDRESS - * exception. - */ - status = acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 1); - if (ACPI_FAILURE(status) && (status != AE_BAD_ADDRESS)) { - return_ACPI_STATUS(status); - } - } - /* * 1) Disable/Clear all GPEs * 2) Enable all wakeup GPEs @@ -364,16 +352,6 @@ acpi_status acpi_hw_legacy_wake(u8 sleep_state, u8 flags) [ACPI_EVENT_POWER_BUTTON]. status_register_id, ACPI_CLEAR_STATUS); - /* - * Enable BM arbitration. This feature is contained within an - * optional register (PM2 Control), so ignore a BAD_ADDRESS - * exception. - */ - status = acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 0); - if (ACPI_FAILURE(status) && (status != AE_BAD_ADDRESS)) { - return_ACPI_STATUS(status); - } - acpi_hw_execute_sleep_method(METHOD_PATHNAME__SST, ACPI_SST_WORKING); return_ACPI_STATUS(status); } diff --git a/drivers/acpi/acpica/nspredef.c b/drivers/acpi/acpica/nspredef.c index 23ce09686418..fe6626035495 100644 --- a/drivers/acpi/acpica/nspredef.c +++ b/drivers/acpi/acpica/nspredef.c @@ -638,7 +638,7 @@ acpi_ns_check_package(struct acpi_predefined_data *data, /* Create the new outer package and populate it */ status = - acpi_ns_wrap_with_package(data, *elements, + acpi_ns_wrap_with_package(data, return_object, return_object_ptr); if (ACPI_FAILURE(status)) { return (status); diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index 7dd3f9fb9f3f..023f9c8534d0 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -1044,17 +1044,24 @@ static int acpi_battery_remove(struct acpi_device *device, int type) } /* this is needed to learn about changes made in suspended state */ -static int acpi_battery_resume(struct acpi_device *device) +static int acpi_battery_resume(struct device *dev) { struct acpi_battery *battery; - if (!device) + + if (!dev) return -EINVAL; - battery = acpi_driver_data(device); + + battery = acpi_driver_data(to_acpi_device(dev)); + if (!battery) + return -EINVAL; + battery->update_time = 0; acpi_battery_update(battery); return 0; } +static SIMPLE_DEV_PM_OPS(acpi_battery_pm, NULL, acpi_battery_resume); + static struct acpi_driver acpi_battery_driver = { .name = "battery", .class = ACPI_BATTERY_CLASS, @@ -1062,10 +1069,10 @@ static struct acpi_driver acpi_battery_driver = { .flags = ACPI_DRIVER_ALL_NOTIFY_EVENTS, .ops = { .add = acpi_battery_add, - .resume = acpi_battery_resume, .remove = acpi_battery_remove, .notify = acpi_battery_notify, }, + .drv.pm = &acpi_battery_pm, }; static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie) diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index d27d072472f9..79d4c22f7a6d 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -76,19 +76,21 @@ MODULE_DEVICE_TABLE(acpi, button_device_ids); static int acpi_button_add(struct acpi_device *device); static int acpi_button_remove(struct acpi_device *device, int type); -static int acpi_button_resume(struct acpi_device *device); static void acpi_button_notify(struct acpi_device *device, u32 event); +static int acpi_button_resume(struct device *dev); +static SIMPLE_DEV_PM_OPS(acpi_button_pm, NULL, acpi_button_resume); + static struct acpi_driver acpi_button_driver = { .name = "button", .class = ACPI_BUTTON_CLASS, .ids = button_device_ids, .ops = { .add = acpi_button_add, - .resume = acpi_button_resume, .remove = acpi_button_remove, .notify = acpi_button_notify, }, + .drv.pm = &acpi_button_pm, }; struct acpi_button { @@ -308,8 +310,9 @@ static void acpi_button_notify(struct acpi_device *device, u32 event) } } -static int acpi_button_resume(struct acpi_device *device) +static int acpi_button_resume(struct device *dev) { + struct acpi_device *device = to_acpi_device(dev); struct acpi_button *button = acpi_driver_data(device); if (button->type == ACPI_BUTTON_TYPE_LID) diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c index 0f0356ca1a9e..669d9ee80d16 100644 --- a/drivers/acpi/fan.c +++ b/drivers/acpi/fan.c @@ -46,8 +46,6 @@ MODULE_LICENSE("GPL"); static int acpi_fan_add(struct acpi_device *device); static int acpi_fan_remove(struct acpi_device *device, int type); -static int acpi_fan_suspend(struct acpi_device *device, pm_message_t state); -static int acpi_fan_resume(struct acpi_device *device); static const struct acpi_device_id fan_device_ids[] = { {"PNP0C0B", 0}, @@ -55,6 +53,10 @@ static const struct acpi_device_id fan_device_ids[] = { }; MODULE_DEVICE_TABLE(acpi, fan_device_ids); +static int acpi_fan_suspend(struct device *dev); +static int acpi_fan_resume(struct device *dev); +static SIMPLE_DEV_PM_OPS(acpi_fan_pm, acpi_fan_suspend, acpi_fan_resume); + static struct acpi_driver acpi_fan_driver = { .name = "fan", .class = ACPI_FAN_CLASS, @@ -62,9 +64,8 @@ static struct acpi_driver acpi_fan_driver = { .ops = { .add = acpi_fan_add, .remove = acpi_fan_remove, - .suspend = acpi_fan_suspend, - .resume = acpi_fan_resume, }, + .drv.pm = &acpi_fan_pm, }; /* thermal cooling device callbacks */ @@ -183,24 +184,24 @@ static int acpi_fan_remove(struct acpi_device *device, int type) return 0; } -static int acpi_fan_suspend(struct acpi_device *device, pm_message_t state) +static int acpi_fan_suspend(struct device *dev) { - if (!device) + if (!dev) return -EINVAL; - acpi_bus_set_power(device->handle, ACPI_STATE_D0); + acpi_bus_set_power(to_acpi_device(dev)->handle, ACPI_STATE_D0); return AE_OK; } -static int acpi_fan_resume(struct acpi_device *device) +static int acpi_fan_resume(struct device *dev) { int result; - if (!device) + if (!dev) return -EINVAL; - result = acpi_bus_update_power(device->handle, NULL); + result = acpi_bus_update_power(to_acpi_device(dev)->handle, NULL); if (result) printk(KERN_ERR PREFIX "Error updating fan power state\n"); diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index dd6d6a3c6780..894d45c6bc67 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -60,7 +60,6 @@ ACPI_MODULE_NAME("power"); static int acpi_power_add(struct acpi_device *device); static int acpi_power_remove(struct acpi_device *device, int type); -static int acpi_power_resume(struct acpi_device *device); static const struct acpi_device_id power_device_ids[] = { {ACPI_POWER_HID, 0}, @@ -68,6 +67,9 @@ static const struct acpi_device_id power_device_ids[] = { }; MODULE_DEVICE_TABLE(acpi, power_device_ids); +static int acpi_power_resume(struct device *dev); +static SIMPLE_DEV_PM_OPS(acpi_power_pm, NULL, acpi_power_resume); + static struct acpi_driver acpi_power_driver = { .name = "power", .class = ACPI_POWER_CLASS, @@ -75,8 +77,8 @@ static struct acpi_driver acpi_power_driver = { .ops = { .add = acpi_power_add, .remove = acpi_power_remove, - .resume = acpi_power_resume, }, + .drv.pm = &acpi_power_pm, }; /* @@ -771,14 +773,16 @@ static int acpi_power_remove(struct acpi_device *device, int type) return 0; } -static int acpi_power_resume(struct acpi_device *device) +static int acpi_power_resume(struct device *dev) { int result = 0, state; + struct acpi_device *device; struct acpi_power_resource *resource; - if (!device) + if (!dev) return -EINVAL; + device = to_acpi_device(dev); resource = acpi_driver_data(device); if (!resource) return -EINVAL; diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index c850de4c9a14..eff722278ff5 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -189,10 +189,12 @@ int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id) * Processor (CPU3, 0x03, 0x00000410, 0x06) {} * } * - * Ignores apic_id and always return 0 for CPU0's handle. + * Ignores apic_id and always returns 0 for the processor + * handle with acpi id 0 if nr_cpu_ids is 1. + * This should be the case if SMP tables are not found. * Return -1 for other CPU's handle. */ - if (acpi_id == 0) + if (nr_cpu_ids <= 1 && acpi_id == 0) return acpi_id; else return apic_id; diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c index 0734086537b8..7048b97853e0 100644 --- a/drivers/acpi/processor_driver.c +++ b/drivers/acpi/processor_driver.c @@ -93,6 +93,9 @@ static const struct acpi_device_id processor_device_ids[] = { }; MODULE_DEVICE_TABLE(acpi, processor_device_ids); +static SIMPLE_DEV_PM_OPS(acpi_processor_pm, + acpi_processor_suspend, acpi_processor_resume); + static struct acpi_driver acpi_processor_driver = { .name = "processor", .class = ACPI_PROCESSOR_CLASS, @@ -100,10 +103,9 @@ static struct acpi_driver acpi_processor_driver = { .ops = { .add = acpi_processor_add, .remove = acpi_processor_remove, - .suspend = acpi_processor_suspend, - .resume = acpi_processor_resume, .notify = acpi_processor_notify, }, + .drv.pm = &acpi_processor_pm, }; #define INSTALL_NOTIFY_HANDLER 1 @@ -427,18 +429,11 @@ static int acpi_cpu_soft_notify(struct notifier_block *nfb, * Initialize missing things */ if (pr->flags.need_hotplug_init) { - struct cpuidle_driver *idle_driver = - cpuidle_get_driver(); - printk(KERN_INFO "Will online and init hotplugged " "CPU: %d\n", pr->id); WARN(acpi_processor_start(pr), "Failed to start CPU:" " %d\n", pr->id); pr->flags.need_hotplug_init = 0; - if (idle_driver && !strcmp(idle_driver->name, - "intel_idle")) { - intel_idle_cpu_init(pr->id); - } /* Normal CPU soft online event */ } else { acpi_processor_ppc_has_changed(pr, 0); diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 47a8caa89dbe..e589c1985248 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -221,10 +221,6 @@ static void lapic_timer_state_broadcast(struct acpi_processor *pr, #endif -/* - * Suspend / resume control - */ -static int acpi_idle_suspend; static u32 saved_bm_rld; static void acpi_idle_bm_rld_save(void) @@ -241,23 +237,15 @@ static void acpi_idle_bm_rld_restore(void) acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, saved_bm_rld); } -int acpi_processor_suspend(struct acpi_device * device, pm_message_t state) +int acpi_processor_suspend(struct device *dev) { - if (acpi_idle_suspend == 1) - return 0; - acpi_idle_bm_rld_save(); - acpi_idle_suspend = 1; return 0; } -int acpi_processor_resume(struct acpi_device * device) +int acpi_processor_resume(struct device *dev) { - if (acpi_idle_suspend == 0) - return 0; - acpi_idle_bm_rld_restore(); - acpi_idle_suspend = 0; return 0; } @@ -595,7 +583,6 @@ static void acpi_processor_power_verify_c3(struct acpi_processor *pr, */ cx->valid = 1; - cx->latency_ticks = cx->latency; /* * On older chipsets, BM_RLD needs to be set * in order for Bus Master activity to wake the @@ -628,7 +615,6 @@ static int acpi_processor_power_verify(struct acpi_processor *pr) if (!cx->address) break; cx->valid = 1; - cx->latency_ticks = cx->latency; /* Normalize latency */ break; case ACPI_STATE_C3: @@ -763,11 +749,6 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev, local_irq_disable(); - if (acpi_idle_suspend) { - local_irq_enable(); - cpu_relax(); - return -EBUSY; - } lapic_timer_state_broadcast(pr, cx, 1); kt1 = ktime_get_real(); @@ -779,7 +760,6 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev, dev->last_residency = (int)idle_time; local_irq_enable(); - cx->usage++; lapic_timer_state_broadcast(pr, cx, 0); return index; @@ -838,11 +818,6 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev, local_irq_disable(); - if (acpi_idle_suspend) { - local_irq_enable(); - cpu_relax(); - return -EBUSY; - } if (cx->entry_method != ACPI_CSTATE_FFH) { current_thread_info()->status &= ~TS_POLLING; @@ -887,10 +862,7 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev, if (cx->entry_method != ACPI_CSTATE_FFH) current_thread_info()->status |= TS_POLLING; - cx->usage++; - lapic_timer_state_broadcast(pr, cx, 0); - cx->time += idle_time; return index; } @@ -928,8 +900,7 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev, drv, drv->safe_state_index); } else { local_irq_disable(); - if (!acpi_idle_suspend) - acpi_safe_halt(); + acpi_safe_halt(); local_irq_enable(); return -EBUSY; } @@ -937,11 +908,6 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev, local_irq_disable(); - if (acpi_idle_suspend) { - local_irq_enable(); - cpu_relax(); - return -EBUSY; - } if (cx->entry_method != ACPI_CSTATE_FFH) { current_thread_info()->status &= ~TS_POLLING; @@ -1014,10 +980,7 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev, if (cx->entry_method != ACPI_CSTATE_FFH) current_thread_info()->status |= TS_POLLING; - cx->usage++; - lapic_timer_state_broadcast(pr, cx, 0); - cx->time += idle_time; return index; } diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c index 6e36d0c0057c..c0b9aa5faf4c 100644 --- a/drivers/acpi/sbs.c +++ b/drivers/acpi/sbs.c @@ -988,16 +988,18 @@ static void acpi_sbs_rmdirs(void) #endif } -static int acpi_sbs_resume(struct acpi_device *device) +static int acpi_sbs_resume(struct device *dev) { struct acpi_sbs *sbs; - if (!device) + if (!dev) return -EINVAL; - sbs = device->driver_data; + sbs = to_acpi_device(dev)->driver_data; acpi_sbs_callback(sbs); return 0; } +static SIMPLE_DEV_PM_OPS(acpi_sbs_pm, NULL, acpi_sbs_resume); + static struct acpi_driver acpi_sbs_driver = { .name = "sbs", .class = ACPI_SBS_CLASS, @@ -1005,8 +1007,8 @@ static struct acpi_driver acpi_sbs_driver = { .ops = { .add = acpi_sbs_add, .remove = acpi_sbs_remove, - .resume = acpi_sbs_resume, }, + .drv.pm = &acpi_sbs_pm, }; static int __init acpi_sbs_init(void) diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index c8a1f3b68110..fdda49336560 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -290,26 +290,6 @@ static void acpi_device_release(struct device *dev) kfree(acpi_dev); } -static int acpi_device_suspend(struct device *dev, pm_message_t state) -{ - struct acpi_device *acpi_dev = to_acpi_device(dev); - struct acpi_driver *acpi_drv = acpi_dev->driver; - - if (acpi_drv && acpi_drv->ops.suspend) - return acpi_drv->ops.suspend(acpi_dev, state); - return 0; -} - -static int acpi_device_resume(struct device *dev) -{ - struct acpi_device *acpi_dev = to_acpi_device(dev); - struct acpi_driver *acpi_drv = acpi_dev->driver; - - if (acpi_drv && acpi_drv->ops.resume) - return acpi_drv->ops.resume(acpi_dev); - return 0; -} - static int acpi_bus_match(struct device *dev, struct device_driver *drv) { struct acpi_device *acpi_dev = to_acpi_device(dev); @@ -441,8 +421,6 @@ static int acpi_device_remove(struct device * dev) struct bus_type acpi_bus_type = { .name = "acpi", - .suspend = acpi_device_suspend, - .resume = acpi_device_resume, .match = acpi_bus_match, .probe = acpi_device_probe, .remove = acpi_device_remove, diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index 7dbebea1ec31..21dd4c268aef 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -98,7 +98,6 @@ MODULE_PARM_DESC(psv, "Disable or override all passive trip points."); static int acpi_thermal_add(struct acpi_device *device); static int acpi_thermal_remove(struct acpi_device *device, int type); -static int acpi_thermal_resume(struct acpi_device *device); static void acpi_thermal_notify(struct acpi_device *device, u32 event); static const struct acpi_device_id thermal_device_ids[] = { @@ -107,6 +106,9 @@ static const struct acpi_device_id thermal_device_ids[] = { }; MODULE_DEVICE_TABLE(acpi, thermal_device_ids); +static int acpi_thermal_resume(struct device *dev); +static SIMPLE_DEV_PM_OPS(acpi_thermal_pm, NULL, acpi_thermal_resume); + static struct acpi_driver acpi_thermal_driver = { .name = "thermal", .class = ACPI_THERMAL_CLASS, @@ -114,9 +116,9 @@ static struct acpi_driver acpi_thermal_driver = { .ops = { .add = acpi_thermal_add, .remove = acpi_thermal_remove, - .resume = acpi_thermal_resume, .notify = acpi_thermal_notify, }, + .drv.pm = &acpi_thermal_pm, }; struct acpi_thermal_state { @@ -1041,16 +1043,17 @@ static int acpi_thermal_remove(struct acpi_device *device, int type) return 0; } -static int acpi_thermal_resume(struct acpi_device *device) +static int acpi_thermal_resume(struct device *dev) { - struct acpi_thermal *tz = NULL; + struct acpi_thermal *tz; int i, j, power_state, result; - - if (!device || !acpi_driver_data(device)) + if (!dev) return -EINVAL; - tz = acpi_driver_data(device); + tz = acpi_driver_data(to_acpi_device(dev)); + if (!tz) + return -EINVAL; for (i = 0; i < ACPI_THERMAL_MAX_ACTIVE; i++) { if (!(&tz->trips.active[i])) diff --git a/drivers/base/dd.c b/drivers/base/dd.c index dcb8a6e48692..4b01ab3d2c24 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -24,6 +24,7 @@ #include <linux/wait.h> #include <linux/async.h> #include <linux/pm_runtime.h> +#include <scsi/scsi_scan.h> #include "base.h" #include "power/power.h" @@ -332,6 +333,7 @@ void wait_for_device_probe(void) /* wait for the known devices to complete their probing */ wait_event(probe_waitqueue, atomic_read(&probe_count) == 0); async_synchronize_full(); + scsi_complete_async_scans(); } EXPORT_SYMBOL_GPL(wait_for_device_probe); diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index 765c3a28077a..d91a3a0b2325 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -227,33 +227,24 @@ static int handle_create(const char *nodename, umode_t mode, struct device *dev) static int dev_rmdir(const char *name) { - struct nameidata nd; + struct path parent; struct dentry *dentry; int err; - err = kern_path_parent(name, &nd); - if (err) - return err; - - mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); - dentry = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len); - if (!IS_ERR(dentry)) { - if (dentry->d_inode) { - if (dentry->d_inode->i_private == &thread) - err = vfs_rmdir(nd.path.dentry->d_inode, - dentry); - else - err = -EPERM; - } else { - err = -ENOENT; - } - dput(dentry); + dentry = kern_path_locked(name, &parent); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + if (dentry->d_inode) { + if (dentry->d_inode->i_private == &thread) + err = vfs_rmdir(parent.dentry->d_inode, dentry); + else + err = -EPERM; } else { - err = PTR_ERR(dentry); + err = -ENOENT; } - - mutex_unlock(&nd.path.dentry->d_inode->i_mutex); - path_put(&nd.path); + dput(dentry); + mutex_unlock(&parent.dentry->d_inode->i_mutex); + path_put(&parent); return err; } @@ -305,50 +296,43 @@ static int dev_mynode(struct device *dev, struct inode *inode, struct kstat *sta static int handle_remove(const char *nodename, struct device *dev) { - struct nameidata nd; + struct path parent; struct dentry *dentry; - struct kstat stat; int deleted = 1; int err; - err = kern_path_parent(nodename, &nd); - if (err) - return err; + dentry = kern_path_locked(nodename, &parent); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); - mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); - dentry = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len); - if (!IS_ERR(dentry)) { - if (dentry->d_inode) { - err = vfs_getattr(nd.path.mnt, dentry, &stat); - if (!err && dev_mynode(dev, dentry->d_inode, &stat)) { - struct iattr newattrs; - /* - * before unlinking this node, reset permissions - * of possible references like hardlinks - */ - newattrs.ia_uid = 0; - newattrs.ia_gid = 0; - newattrs.ia_mode = stat.mode & ~0777; - newattrs.ia_valid = - ATTR_UID|ATTR_GID|ATTR_MODE; - mutex_lock(&dentry->d_inode->i_mutex); - notify_change(dentry, &newattrs); - mutex_unlock(&dentry->d_inode->i_mutex); - err = vfs_unlink(nd.path.dentry->d_inode, - dentry); - if (!err || err == -ENOENT) - deleted = 1; - } - } else { - err = -ENOENT; + if (dentry->d_inode) { + struct kstat stat; + err = vfs_getattr(parent.mnt, dentry, &stat); + if (!err && dev_mynode(dev, dentry->d_inode, &stat)) { + struct iattr newattrs; + /* + * before unlinking this node, reset permissions + * of possible references like hardlinks + */ + newattrs.ia_uid = 0; + newattrs.ia_gid = 0; + newattrs.ia_mode = stat.mode & ~0777; + newattrs.ia_valid = + ATTR_UID|ATTR_GID|ATTR_MODE; + mutex_lock(&dentry->d_inode->i_mutex); + notify_change(dentry, &newattrs); + mutex_unlock(&dentry->d_inode->i_mutex); + err = vfs_unlink(parent.dentry->d_inode, dentry); + if (!err || err == -ENOENT) + deleted = 1; } - dput(dentry); } else { - err = PTR_ERR(dentry); + err = -ENOENT; } - mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + dput(dentry); + mutex_unlock(&parent.dentry->d_inode->i_mutex); - path_put(&nd.path); + path_put(&parent); if (deleted && strchr(nodename, '/')) delete_path(nodename); return err; diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 83aa694a8efe..ba3487c9835b 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -75,19 +75,6 @@ static int genpd_start_dev(struct generic_pm_domain *genpd, struct device *dev) start_latency_ns, "start"); } -static int genpd_save_dev(struct generic_pm_domain *genpd, struct device *dev) -{ - return GENPD_DEV_TIMED_CALLBACK(genpd, int, save_state, dev, - save_state_latency_ns, "state save"); -} - -static int genpd_restore_dev(struct generic_pm_domain *genpd, struct device *dev) -{ - return GENPD_DEV_TIMED_CALLBACK(genpd, int, restore_state, dev, - restore_state_latency_ns, - "state restore"); -} - static bool genpd_sd_counter_dec(struct generic_pm_domain *genpd) { bool ret = false; @@ -139,6 +126,19 @@ static void genpd_set_active(struct generic_pm_domain *genpd) genpd->status = GPD_STATE_ACTIVE; } +static void genpd_recalc_cpu_exit_latency(struct generic_pm_domain *genpd) +{ + s64 usecs64; + + if (!genpd->cpu_data) + return; + + usecs64 = genpd->power_on_latency_ns; + do_div(usecs64, NSEC_PER_USEC); + usecs64 += genpd->cpu_data->saved_exit_latency; + genpd->cpu_data->idle_state->exit_latency = usecs64; +} + /** * __pm_genpd_poweron - Restore power to a given PM domain and its masters. * @genpd: PM domain to power up. @@ -146,7 +146,7 @@ static void genpd_set_active(struct generic_pm_domain *genpd) * Restore power to @genpd and all of its masters so that it is possible to * resume a device belonging to it. */ -int __pm_genpd_poweron(struct generic_pm_domain *genpd) +static int __pm_genpd_poweron(struct generic_pm_domain *genpd) __releases(&genpd->lock) __acquires(&genpd->lock) { struct gpd_link *link; @@ -176,6 +176,13 @@ int __pm_genpd_poweron(struct generic_pm_domain *genpd) return 0; } + if (genpd->cpu_data) { + cpuidle_pause_and_lock(); + genpd->cpu_data->idle_state->disabled = true; + cpuidle_resume_and_unlock(); + goto out; + } + /* * The list is guaranteed not to change while the loop below is being * executed, unless one of the masters' .power_on() callbacks fiddles @@ -215,6 +222,7 @@ int __pm_genpd_poweron(struct generic_pm_domain *genpd) if (elapsed_ns > genpd->power_on_latency_ns) { genpd->power_on_latency_ns = elapsed_ns; genpd->max_off_time_changed = true; + genpd_recalc_cpu_exit_latency(genpd); if (genpd->name) pr_warning("%s: Power-on latency exceeded, " "new value %lld ns\n", genpd->name, @@ -222,6 +230,7 @@ int __pm_genpd_poweron(struct generic_pm_domain *genpd) } } + out: genpd_set_active(genpd); return 0; @@ -251,6 +260,19 @@ int pm_genpd_poweron(struct generic_pm_domain *genpd) #ifdef CONFIG_PM_RUNTIME +static int genpd_save_dev(struct generic_pm_domain *genpd, struct device *dev) +{ + return GENPD_DEV_TIMED_CALLBACK(genpd, int, save_state, dev, + save_state_latency_ns, "state save"); +} + +static int genpd_restore_dev(struct generic_pm_domain *genpd, struct device *dev) +{ + return GENPD_DEV_TIMED_CALLBACK(genpd, int, restore_state, dev, + restore_state_latency_ns, + "state restore"); +} + static int genpd_dev_pm_qos_notifier(struct notifier_block *nb, unsigned long val, void *ptr) { @@ -275,7 +297,7 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb, pdd = dev->power.subsys_data ? dev->power.subsys_data->domain_data : NULL; - if (pdd) { + if (pdd && pdd->dev) { to_gpd_data(pdd)->td.constraint_changed = true; genpd = dev_to_genpd(dev); } else { @@ -339,19 +361,16 @@ static void __pm_genpd_restore_device(struct pm_domain_data *pdd, { struct generic_pm_domain_data *gpd_data = to_gpd_data(pdd); struct device *dev = pdd->dev; + bool need_restore = gpd_data->need_restore; - if (!gpd_data->need_restore) - return; - + gpd_data->need_restore = false; mutex_unlock(&genpd->lock); genpd_start_dev(genpd, dev); - genpd_restore_dev(genpd, dev); - genpd_stop_dev(genpd, dev); + if (need_restore) + genpd_restore_dev(genpd, dev); mutex_lock(&genpd->lock); - - gpd_data->need_restore = false; } /** @@ -458,6 +477,21 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd) } } + if (genpd->cpu_data) { + /* + * If cpu_data is set, cpuidle should turn the domain off when + * the CPU in it is idle. In that case we don't decrement the + * subdomain counts of the master domains, so that power is not + * removed from the current domain prematurely as a result of + * cutting off the masters' power. + */ + genpd->status = GPD_STATE_POWER_OFF; + cpuidle_pause_and_lock(); + genpd->cpu_data->idle_state->disabled = false; + cpuidle_resume_and_unlock(); + goto out; + } + if (genpd->power_off) { ktime_t time_start; s64 elapsed_ns; @@ -595,7 +629,7 @@ static int pm_genpd_runtime_resume(struct device *dev) /* If power.irq_safe, the PM domain is never powered off. */ if (dev->power.irq_safe) - goto out; + return genpd_start_dev(genpd, dev); mutex_lock(&genpd->lock); ret = __pm_genpd_poweron(genpd); @@ -628,9 +662,6 @@ static int pm_genpd_runtime_resume(struct device *dev) wake_up_all(&genpd->status_wait_queue); mutex_unlock(&genpd->lock); - out: - genpd_start_dev(genpd, dev); - return 0; } @@ -1235,6 +1266,27 @@ static void pm_genpd_complete(struct device *dev) #endif /* CONFIG_PM_SLEEP */ +static struct generic_pm_domain_data *__pm_genpd_alloc_dev_data(struct device *dev) +{ + struct generic_pm_domain_data *gpd_data; + + gpd_data = kzalloc(sizeof(*gpd_data), GFP_KERNEL); + if (!gpd_data) + return NULL; + + mutex_init(&gpd_data->lock); + gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier; + dev_pm_qos_add_notifier(dev, &gpd_data->nb); + return gpd_data; +} + +static void __pm_genpd_free_dev_data(struct device *dev, + struct generic_pm_domain_data *gpd_data) +{ + dev_pm_qos_remove_notifier(dev, &gpd_data->nb); + kfree(gpd_data); +} + /** * __pm_genpd_add_device - Add a device to an I/O PM domain. * @genpd: PM domain to add the device to. @@ -1244,7 +1296,7 @@ static void pm_genpd_complete(struct device *dev) int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, struct gpd_timing_data *td) { - struct generic_pm_domain_data *gpd_data; + struct generic_pm_domain_data *gpd_data_new, *gpd_data = NULL; struct pm_domain_data *pdd; int ret = 0; @@ -1253,14 +1305,10 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev)) return -EINVAL; - gpd_data = kzalloc(sizeof(*gpd_data), GFP_KERNEL); - if (!gpd_data) + gpd_data_new = __pm_genpd_alloc_dev_data(dev); + if (!gpd_data_new) return -ENOMEM; - mutex_init(&gpd_data->lock); - gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier; - dev_pm_qos_add_notifier(dev, &gpd_data->nb); - genpd_acquire_lock(genpd); if (genpd->prepared_count > 0) { @@ -1274,35 +1322,42 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, goto out; } + ret = dev_pm_get_subsys_data(dev); + if (ret) + goto out; + genpd->device_count++; genpd->max_off_time_changed = true; - dev_pm_get_subsys_data(dev); - - mutex_lock(&gpd_data->lock); spin_lock_irq(&dev->power.lock); + dev->pm_domain = &genpd->domain; - dev->power.subsys_data->domain_data = &gpd_data->base; - gpd_data->base.dev = dev; - list_add_tail(&gpd_data->base.list_node, &genpd->dev_list); - gpd_data->need_restore = genpd->status == GPD_STATE_POWER_OFF; + if (dev->power.subsys_data->domain_data) { + gpd_data = to_gpd_data(dev->power.subsys_data->domain_data); + } else { + gpd_data = gpd_data_new; + dev->power.subsys_data->domain_data = &gpd_data->base; + } + gpd_data->refcount++; if (td) gpd_data->td = *td; + spin_unlock_irq(&dev->power.lock); + + mutex_lock(&gpd_data->lock); + gpd_data->base.dev = dev; + list_add_tail(&gpd_data->base.list_node, &genpd->dev_list); + gpd_data->need_restore = genpd->status == GPD_STATE_POWER_OFF; gpd_data->td.constraint_changed = true; gpd_data->td.effective_constraint_ns = -1; - spin_unlock_irq(&dev->power.lock); mutex_unlock(&gpd_data->lock); - genpd_release_lock(genpd); - - return 0; - out: genpd_release_lock(genpd); - dev_pm_qos_remove_notifier(dev, &gpd_data->nb); - kfree(gpd_data); + if (gpd_data != gpd_data_new) + __pm_genpd_free_dev_data(dev, gpd_data_new); + return ret; } @@ -1348,6 +1403,7 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, { struct generic_pm_domain_data *gpd_data; struct pm_domain_data *pdd; + bool remove = false; int ret = 0; dev_dbg(dev, "%s()\n", __func__); @@ -1368,22 +1424,28 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, genpd->max_off_time_changed = true; spin_lock_irq(&dev->power.lock); + dev->pm_domain = NULL; pdd = dev->power.subsys_data->domain_data; list_del_init(&pdd->list_node); - dev->power.subsys_data->domain_data = NULL; + gpd_data = to_gpd_data(pdd); + if (--gpd_data->refcount == 0) { + dev->power.subsys_data->domain_data = NULL; + remove = true; + } + spin_unlock_irq(&dev->power.lock); - gpd_data = to_gpd_data(pdd); mutex_lock(&gpd_data->lock); pdd->dev = NULL; mutex_unlock(&gpd_data->lock); genpd_release_lock(genpd); - dev_pm_qos_remove_notifier(dev, &gpd_data->nb); - kfree(gpd_data); dev_pm_put_subsys_data(dev); + if (remove) + __pm_genpd_free_dev_data(dev, gpd_data); + return 0; out: @@ -1541,33 +1603,52 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, * @dev: Device to add the callbacks to. * @ops: Set of callbacks to add. * @td: Timing data to add to the device along with the callbacks (optional). + * + * Every call to this routine should be balanced with a call to + * __pm_genpd_remove_callbacks() and they must not be nested. */ int pm_genpd_add_callbacks(struct device *dev, struct gpd_dev_ops *ops, struct gpd_timing_data *td) { - struct pm_domain_data *pdd; + struct generic_pm_domain_data *gpd_data_new, *gpd_data = NULL; int ret = 0; - if (!(dev && dev->power.subsys_data && ops)) + if (!(dev && ops)) return -EINVAL; + gpd_data_new = __pm_genpd_alloc_dev_data(dev); + if (!gpd_data_new) + return -ENOMEM; + pm_runtime_disable(dev); device_pm_lock(); - pdd = dev->power.subsys_data->domain_data; - if (pdd) { - struct generic_pm_domain_data *gpd_data = to_gpd_data(pdd); + ret = dev_pm_get_subsys_data(dev); + if (ret) + goto out; - gpd_data->ops = *ops; - if (td) - gpd_data->td = *td; + spin_lock_irq(&dev->power.lock); + + if (dev->power.subsys_data->domain_data) { + gpd_data = to_gpd_data(dev->power.subsys_data->domain_data); } else { - ret = -EINVAL; + gpd_data = gpd_data_new; + dev->power.subsys_data->domain_data = &gpd_data->base; } + gpd_data->refcount++; + gpd_data->ops = *ops; + if (td) + gpd_data->td = *td; + + spin_unlock_irq(&dev->power.lock); + out: device_pm_unlock(); pm_runtime_enable(dev); + if (gpd_data != gpd_data_new) + __pm_genpd_free_dev_data(dev, gpd_data_new); + return ret; } EXPORT_SYMBOL_GPL(pm_genpd_add_callbacks); @@ -1576,10 +1657,13 @@ EXPORT_SYMBOL_GPL(pm_genpd_add_callbacks); * __pm_genpd_remove_callbacks - Remove PM domain callbacks from a given device. * @dev: Device to remove the callbacks from. * @clear_td: If set, clear the device's timing data too. + * + * This routine can only be called after pm_genpd_add_callbacks(). */ int __pm_genpd_remove_callbacks(struct device *dev, bool clear_td) { - struct pm_domain_data *pdd; + struct generic_pm_domain_data *gpd_data = NULL; + bool remove = false; int ret = 0; if (!(dev && dev->power.subsys_data)) @@ -1588,24 +1672,118 @@ int __pm_genpd_remove_callbacks(struct device *dev, bool clear_td) pm_runtime_disable(dev); device_pm_lock(); - pdd = dev->power.subsys_data->domain_data; - if (pdd) { - struct generic_pm_domain_data *gpd_data = to_gpd_data(pdd); + spin_lock_irq(&dev->power.lock); - gpd_data->ops = (struct gpd_dev_ops){ 0 }; + if (dev->power.subsys_data->domain_data) { + gpd_data = to_gpd_data(dev->power.subsys_data->domain_data); + gpd_data->ops = (struct gpd_dev_ops){ NULL }; if (clear_td) gpd_data->td = (struct gpd_timing_data){ 0 }; + + if (--gpd_data->refcount == 0) { + dev->power.subsys_data->domain_data = NULL; + remove = true; + } } else { ret = -EINVAL; } + spin_unlock_irq(&dev->power.lock); + device_pm_unlock(); pm_runtime_enable(dev); - return ret; + if (ret) + return ret; + + dev_pm_put_subsys_data(dev); + if (remove) + __pm_genpd_free_dev_data(dev, gpd_data); + + return 0; } EXPORT_SYMBOL_GPL(__pm_genpd_remove_callbacks); +int genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state) +{ + struct cpuidle_driver *cpuidle_drv; + struct gpd_cpu_data *cpu_data; + struct cpuidle_state *idle_state; + int ret = 0; + + if (IS_ERR_OR_NULL(genpd) || state < 0) + return -EINVAL; + + genpd_acquire_lock(genpd); + + if (genpd->cpu_data) { + ret = -EEXIST; + goto out; + } + cpu_data = kzalloc(sizeof(*cpu_data), GFP_KERNEL); + if (!cpu_data) { + ret = -ENOMEM; + goto out; + } + cpuidle_drv = cpuidle_driver_ref(); + if (!cpuidle_drv) { + ret = -ENODEV; + goto out; + } + if (cpuidle_drv->state_count <= state) { + ret = -EINVAL; + goto err; + } + idle_state = &cpuidle_drv->states[state]; + if (!idle_state->disabled) { + ret = -EAGAIN; + goto err; + } + cpu_data->idle_state = idle_state; + cpu_data->saved_exit_latency = idle_state->exit_latency; + genpd->cpu_data = cpu_data; + genpd_recalc_cpu_exit_latency(genpd); + + out: + genpd_release_lock(genpd); + return ret; + + err: + cpuidle_driver_unref(); + goto out; +} + +int genpd_detach_cpuidle(struct generic_pm_domain *genpd) +{ + struct gpd_cpu_data *cpu_data; + struct cpuidle_state *idle_state; + int ret = 0; + + if (IS_ERR_OR_NULL(genpd)) + return -EINVAL; + + genpd_acquire_lock(genpd); + + cpu_data = genpd->cpu_data; + if (!cpu_data) { + ret = -ENODEV; + goto out; + } + idle_state = cpu_data->idle_state; + if (!idle_state->disabled) { + ret = -EAGAIN; + goto out; + } + idle_state->exit_latency = cpu_data->saved_exit_latency; + cpuidle_driver_unref(); + genpd->cpu_data = NULL; + kfree(cpu_data); + + out: + genpd_release_lock(genpd); + return ret; +} + /* Default device callbacks for generic PM domains. */ /** @@ -1615,16 +1793,24 @@ EXPORT_SYMBOL_GPL(__pm_genpd_remove_callbacks); static int pm_genpd_default_save_state(struct device *dev) { int (*cb)(struct device *__dev); - struct device_driver *drv = dev->driver; cb = dev_gpd_data(dev)->ops.save_state; if (cb) return cb(dev); - if (drv && drv->pm && drv->pm->runtime_suspend) - return drv->pm->runtime_suspend(dev); + if (dev->type && dev->type->pm) + cb = dev->type->pm->runtime_suspend; + else if (dev->class && dev->class->pm) + cb = dev->class->pm->runtime_suspend; + else if (dev->bus && dev->bus->pm) + cb = dev->bus->pm->runtime_suspend; + else + cb = NULL; - return 0; + if (!cb && dev->driver && dev->driver->pm) + cb = dev->driver->pm->runtime_suspend; + + return cb ? cb(dev) : 0; } /** @@ -1634,16 +1820,24 @@ static int pm_genpd_default_save_state(struct device *dev) static int pm_genpd_default_restore_state(struct device *dev) { int (*cb)(struct device *__dev); - struct device_driver *drv = dev->driver; cb = dev_gpd_data(dev)->ops.restore_state; if (cb) return cb(dev); - if (drv && drv->pm && drv->pm->runtime_resume) - return drv->pm->runtime_resume(dev); + if (dev->type && dev->type->pm) + cb = dev->type->pm->runtime_resume; + else if (dev->class && dev->class->pm) + cb = dev->class->pm->runtime_resume; + else if (dev->bus && dev->bus->pm) + cb = dev->bus->pm->runtime_resume; + else + cb = NULL; - return 0; + if (!cb && dev->driver && dev->driver->pm) + cb = dev->driver->pm->runtime_resume; + + return cb ? cb(dev) : 0; } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 9cb845e49334..0113adc310dc 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -28,7 +28,7 @@ #include <linux/sched.h> #include <linux/async.h> #include <linux/suspend.h> - +#include <linux/cpuidle.h> #include "../base.h" #include "power.h" @@ -45,10 +45,10 @@ typedef int (*pm_callback_t)(struct device *); */ LIST_HEAD(dpm_list); -LIST_HEAD(dpm_prepared_list); -LIST_HEAD(dpm_suspended_list); -LIST_HEAD(dpm_late_early_list); -LIST_HEAD(dpm_noirq_list); +static LIST_HEAD(dpm_prepared_list); +static LIST_HEAD(dpm_suspended_list); +static LIST_HEAD(dpm_late_early_list); +static LIST_HEAD(dpm_noirq_list); struct suspend_stats suspend_stats; static DEFINE_MUTEX(dpm_list_mtx); @@ -166,7 +166,7 @@ static ktime_t initcall_debug_start(struct device *dev) { ktime_t calltime = ktime_set(0, 0); - if (initcall_debug) { + if (pm_print_times_enabled) { pr_info("calling %s+ @ %i, parent: %s\n", dev_name(dev), task_pid_nr(current), dev->parent ? dev_name(dev->parent) : "none"); @@ -181,7 +181,7 @@ static void initcall_debug_report(struct device *dev, ktime_t calltime, { ktime_t delta, rettime; - if (initcall_debug) { + if (pm_print_times_enabled) { rettime = ktime_get(); delta = ktime_sub(rettime, calltime); pr_info("call %s+ returned %d after %Ld usecs\n", dev_name(dev), @@ -467,6 +467,7 @@ static void dpm_resume_noirq(pm_message_t state) mutex_unlock(&dpm_list_mtx); dpm_show_time(starttime, state, "noirq"); resume_device_irqs(); + cpuidle_resume(); } /** @@ -867,6 +868,7 @@ static int dpm_suspend_noirq(pm_message_t state) ktime_t starttime = ktime_get(); int error = 0; + cpuidle_pause(); suspend_device_irqs(); mutex_lock(&dpm_list_mtx); while (!list_empty(&dpm_late_early_list)) { @@ -989,8 +991,16 @@ static int dpm_suspend_late(pm_message_t state) int dpm_suspend_end(pm_message_t state) { int error = dpm_suspend_late(state); + if (error) + return error; + + error = dpm_suspend_noirq(state); + if (error) { + dpm_resume_early(state); + return error; + } - return error ? : dpm_suspend_noirq(state); + return 0; } EXPORT_SYMBOL_GPL(dpm_suspend_end); diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c index fd849a2c4fa8..74a67e0019a2 100644 --- a/drivers/base/power/qos.c +++ b/drivers/base/power/qos.c @@ -462,7 +462,7 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_add_ancestor_request); static void __dev_pm_qos_drop_user_request(struct device *dev) { dev_pm_qos_remove_request(dev->power.pq_req); - dev->power.pq_req = 0; + dev->power.pq_req = NULL; } /** diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index 48be2ad4dd2c..b91dc6f1e914 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -474,6 +474,8 @@ static DEVICE_ATTR(runtime_enabled, 0444, rtpm_enabled_show, NULL); #endif +#ifdef CONFIG_PM_SLEEP + static ssize_t async_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -500,6 +502,8 @@ static ssize_t async_store(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR(async, 0644, async_show, async_store); + +#endif #endif /* CONFIG_PM_ADVANCED_DEBUG */ static struct attribute *power_attrs[] = { diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index b986b8660b0c..80f9ab9c3aa4 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -95,6 +95,9 @@ struct regmap { /* if set, converts bulk rw to single rw */ bool use_single_rw; + + struct rb_root range_tree; + void *selector_work_buf; /* Scratch buffer used for selector */ }; struct regcache_ops { @@ -115,6 +118,20 @@ bool regmap_precious(struct regmap *map, unsigned int reg); int _regmap_write(struct regmap *map, unsigned int reg, unsigned int val); +struct regmap_range_node { + struct rb_node node; + + unsigned int range_min; + unsigned int range_max; + + unsigned int selector_reg; + unsigned int selector_mask; + int selector_shift; + + unsigned int window_start; + unsigned int window_len; +}; + #ifdef CONFIG_DEBUG_FS extern void regmap_debugfs_initcall(void); extern void regmap_debugfs_init(struct regmap *map, const char *name); diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index 4fac4b9be88f..a89734621e51 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -24,14 +24,18 @@ struct regmap_irq_chip_data { struct mutex lock; struct regmap *map; - struct regmap_irq_chip *chip; + const struct regmap_irq_chip *chip; int irq_base; struct irq_domain *domain; + int irq; + int wake_count; + unsigned int *status_buf; unsigned int *mask_buf; unsigned int *mask_buf_def; + unsigned int *wake_buf; unsigned int irq_reg_stride; }; @@ -71,6 +75,16 @@ static void regmap_irq_sync_unlock(struct irq_data *data) d->chip->mask_base + (i * map->reg_stride)); } + /* If we've changed our wakeup count propagate it to the parent */ + if (d->wake_count < 0) + for (i = d->wake_count; i < 0; i++) + irq_set_irq_wake(d->irq, 0); + else if (d->wake_count > 0) + for (i = 0; i < d->wake_count; i++) + irq_set_irq_wake(d->irq, 1); + + d->wake_count = 0; + mutex_unlock(&d->lock); } @@ -92,18 +106,41 @@ static void regmap_irq_disable(struct irq_data *data) d->mask_buf[irq_data->reg_offset / map->reg_stride] |= irq_data->mask; } +static int regmap_irq_set_wake(struct irq_data *data, unsigned int on) +{ + struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data); + struct regmap *map = d->map; + const struct regmap_irq *irq_data = irq_to_regmap_irq(d, data->hwirq); + + if (!d->chip->wake_base) + return -EINVAL; + + if (on) { + d->wake_buf[irq_data->reg_offset / map->reg_stride] + &= ~irq_data->mask; + d->wake_count++; + } else { + d->wake_buf[irq_data->reg_offset / map->reg_stride] + |= irq_data->mask; + d->wake_count--; + } + + return 0; +} + static struct irq_chip regmap_irq_chip = { .name = "regmap", .irq_bus_lock = regmap_irq_lock, .irq_bus_sync_unlock = regmap_irq_sync_unlock, .irq_disable = regmap_irq_disable, .irq_enable = regmap_irq_enable, + .irq_set_wake = regmap_irq_set_wake, }; static irqreturn_t regmap_irq_thread(int irq, void *d) { struct regmap_irq_chip_data *data = d; - struct regmap_irq_chip *chip = data->chip; + const struct regmap_irq_chip *chip = data->chip; struct regmap *map = data->map; int ret, i; bool handled = false; @@ -195,7 +232,7 @@ static struct irq_domain_ops regmap_domain_ops = { * register values used by the IRQ controller over suspend and resume. */ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, - int irq_base, struct regmap_irq_chip *chip, + int irq_base, const struct regmap_irq_chip *chip, struct regmap_irq_chip_data **data) { struct regmap_irq_chip_data *d; @@ -240,6 +277,14 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, if (!d->mask_buf_def) goto err_alloc; + if (chip->wake_base) { + d->wake_buf = kzalloc(sizeof(unsigned int) * chip->num_regs, + GFP_KERNEL); + if (!d->wake_buf) + goto err_alloc; + } + + d->irq = irq; d->map = map; d->chip = chip; d->irq_base = irq_base; @@ -294,6 +339,7 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, err_domain: /* Should really dispose of the domain but... */ err_alloc: + kfree(d->wake_buf); kfree(d->mask_buf_def); kfree(d->mask_buf); kfree(d->status_buf); @@ -315,6 +361,7 @@ void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *d) free_irq(irq, d); /* We should unmap the domain but... */ + kfree(d->wake_buf); kfree(d->mask_buf_def); kfree(d->mask_buf); kfree(d->status_buf); @@ -346,6 +393,10 @@ EXPORT_SYMBOL_GPL(regmap_irq_chip_get_base); */ int regmap_irq_get_virq(struct regmap_irq_chip_data *data, int irq) { + /* Handle holes in the IRQ list */ + if (!data->chip->irqs[irq].mask) + return -EINVAL; + return irq_create_mapping(data->domain, irq); } EXPORT_SYMBOL_GPL(regmap_irq_get_virq); diff --git a/drivers/base/regmap/regmap-mmio.c b/drivers/base/regmap/regmap-mmio.c index febd6de6c8ac..f05fc74dd84a 100644 --- a/drivers/base/regmap/regmap-mmio.c +++ b/drivers/base/regmap/regmap-mmio.c @@ -37,7 +37,7 @@ static int regmap_mmio_gather_write(void *context, BUG_ON(reg_size != 4); - offset = be32_to_cpup(reg); + offset = *(u32 *)reg; while (val_size) { switch (ctx->val_bytes) { @@ -45,14 +45,14 @@ static int regmap_mmio_gather_write(void *context, writeb(*(u8 *)val, ctx->regs + offset); break; case 2: - writew(be16_to_cpup(val), ctx->regs + offset); + writew(*(u16 *)val, ctx->regs + offset); break; case 4: - writel(be32_to_cpup(val), ctx->regs + offset); + writel(*(u32 *)val, ctx->regs + offset); break; #ifdef CONFIG_64BIT case 8: - writeq(be64_to_cpup(val), ctx->regs + offset); + writeq(*(u64 *)val, ctx->regs + offset); break; #endif default: @@ -83,7 +83,7 @@ static int regmap_mmio_read(void *context, BUG_ON(reg_size != 4); - offset = be32_to_cpup(reg); + offset = *(u32 *)reg; while (val_size) { switch (ctx->val_bytes) { @@ -91,14 +91,14 @@ static int regmap_mmio_read(void *context, *(u8 *)val = readb(ctx->regs + offset); break; case 2: - *(u16 *)val = cpu_to_be16(readw(ctx->regs + offset)); + *(u16 *)val = readw(ctx->regs + offset); break; case 4: - *(u32 *)val = cpu_to_be32(readl(ctx->regs + offset)); + *(u32 *)val = readl(ctx->regs + offset); break; #ifdef CONFIG_64BIT case 8: - *(u64 *)val = cpu_to_be32(readq(ctx->regs + offset)); + *(u64 *)val = readq(ctx->regs + offset); break; #endif default: @@ -124,9 +124,11 @@ static struct regmap_bus regmap_mmio = { .gather_write = regmap_mmio_gather_write, .read = regmap_mmio_read, .free_context = regmap_mmio_free_context, + .reg_format_endian_default = REGMAP_ENDIAN_NATIVE, + .val_format_endian_default = REGMAP_ENDIAN_NATIVE, }; -struct regmap_mmio_context *regmap_mmio_gen_context(void __iomem *regs, +static struct regmap_mmio_context *regmap_mmio_gen_context(void __iomem *regs, const struct regmap_config *config) { struct regmap_mmio_context *ctx; @@ -162,7 +164,15 @@ struct regmap_mmio_context *regmap_mmio_gen_context(void __iomem *regs, if (config->reg_stride < min_stride) return ERR_PTR(-EINVAL); - ctx = kzalloc(GFP_KERNEL, sizeof(*ctx)); + switch (config->reg_format_endian) { + case REGMAP_ENDIAN_DEFAULT: + case REGMAP_ENDIAN_NATIVE: + break; + default: + return ERR_PTR(-EINVAL); + } + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return ERR_PTR(-ENOMEM); diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index c89aa01fb1de..c241ae2f2f10 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -15,12 +15,25 @@ #include <linux/export.h> #include <linux/mutex.h> #include <linux/err.h> +#include <linux/rbtree.h> #define CREATE_TRACE_POINTS #include <trace/events/regmap.h> #include "internal.h" +/* + * Sometimes for failures during very early init the trace + * infrastructure isn't available early enough to be used. For this + * sort of problem defining LOG_DEVICE will add printks for basic + * register I/O on a specific device. + */ +#undef LOG_DEVICE + +static int _regmap_update_bits(struct regmap *map, unsigned int reg, + unsigned int mask, unsigned int val, + bool *change); + bool regmap_writeable(struct regmap *map, unsigned int reg) { if (map->max_register && reg > map->max_register) @@ -119,13 +132,19 @@ static void regmap_format_8(void *buf, unsigned int val, unsigned int shift) b[0] = val << shift; } -static void regmap_format_16(void *buf, unsigned int val, unsigned int shift) +static void regmap_format_16_be(void *buf, unsigned int val, unsigned int shift) { __be16 *b = buf; b[0] = cpu_to_be16(val << shift); } +static void regmap_format_16_native(void *buf, unsigned int val, + unsigned int shift) +{ + *(u16 *)buf = val << shift; +} + static void regmap_format_24(void *buf, unsigned int val, unsigned int shift) { u8 *b = buf; @@ -137,13 +156,19 @@ static void regmap_format_24(void *buf, unsigned int val, unsigned int shift) b[2] = val; } -static void regmap_format_32(void *buf, unsigned int val, unsigned int shift) +static void regmap_format_32_be(void *buf, unsigned int val, unsigned int shift) { __be32 *b = buf; b[0] = cpu_to_be32(val << shift); } +static void regmap_format_32_native(void *buf, unsigned int val, + unsigned int shift) +{ + *(u32 *)buf = val << shift; +} + static unsigned int regmap_parse_8(void *buf) { u8 *b = buf; @@ -151,7 +176,7 @@ static unsigned int regmap_parse_8(void *buf) return b[0]; } -static unsigned int regmap_parse_16(void *buf) +static unsigned int regmap_parse_16_be(void *buf) { __be16 *b = buf; @@ -160,6 +185,11 @@ static unsigned int regmap_parse_16(void *buf) return b[0]; } +static unsigned int regmap_parse_16_native(void *buf) +{ + return *(u16 *)buf; +} + static unsigned int regmap_parse_24(void *buf) { u8 *b = buf; @@ -170,7 +200,7 @@ static unsigned int regmap_parse_24(void *buf) return ret; } -static unsigned int regmap_parse_32(void *buf) +static unsigned int regmap_parse_32_be(void *buf) { __be32 *b = buf; @@ -179,6 +209,11 @@ static unsigned int regmap_parse_32(void *buf) return b[0]; } +static unsigned int regmap_parse_32_native(void *buf) +{ + return *(u32 *)buf; +} + static void regmap_lock_mutex(struct regmap *map) { mutex_lock(&map->mutex); @@ -208,6 +243,67 @@ static void dev_get_regmap_release(struct device *dev, void *res) */ } +static bool _regmap_range_add(struct regmap *map, + struct regmap_range_node *data) +{ + struct rb_root *root = &map->range_tree; + struct rb_node **new = &(root->rb_node), *parent = NULL; + + while (*new) { + struct regmap_range_node *this = + container_of(*new, struct regmap_range_node, node); + + parent = *new; + if (data->range_max < this->range_min) + new = &((*new)->rb_left); + else if (data->range_min > this->range_max) + new = &((*new)->rb_right); + else + return false; + } + + rb_link_node(&data->node, parent, new); + rb_insert_color(&data->node, root); + + return true; +} + +static struct regmap_range_node *_regmap_range_lookup(struct regmap *map, + unsigned int reg) +{ + struct rb_node *node = map->range_tree.rb_node; + + while (node) { + struct regmap_range_node *this = + container_of(node, struct regmap_range_node, node); + + if (reg < this->range_min) + node = node->rb_left; + else if (reg > this->range_max) + node = node->rb_right; + else + return this; + } + + return NULL; +} + +static void regmap_range_exit(struct regmap *map) +{ + struct rb_node *next; + struct regmap_range_node *range_node; + + next = rb_first(&map->range_tree); + while (next) { + range_node = rb_entry(next, struct regmap_range_node, node); + next = rb_next(&range_node->node); + rb_erase(&range_node->node, &map->range_tree); + kfree(range_node); + } + + kfree(map->selector_work_buf); +} + /** * regmap_init(): Initialise register map * @@ -227,6 +323,8 @@ struct regmap *regmap_init(struct device *dev, { struct regmap *map, **m; int ret = -EINVAL; + enum regmap_endian reg_endian, val_endian; + int i, j; if (!bus || !config) goto err; @@ -275,6 +373,18 @@ struct regmap *regmap_init(struct device *dev, map->read_flag_mask = bus->read_flag_mask; } + reg_endian = config->reg_format_endian; + if (reg_endian == REGMAP_ENDIAN_DEFAULT) + reg_endian = bus->reg_format_endian_default; + if (reg_endian == REGMAP_ENDIAN_DEFAULT) + reg_endian = REGMAP_ENDIAN_BIG; + + val_endian = config->val_format_endian; + if (val_endian == REGMAP_ENDIAN_DEFAULT) + val_endian = bus->val_format_endian_default; + if (val_endian == REGMAP_ENDIAN_DEFAULT) + val_endian = REGMAP_ENDIAN_BIG; + switch (config->reg_bits + map->reg_shift) { case 2: switch (config->val_bits) { @@ -321,11 +431,29 @@ struct regmap *regmap_init(struct device *dev, break; case 16: - map->format.format_reg = regmap_format_16; + switch (reg_endian) { + case REGMAP_ENDIAN_BIG: + map->format.format_reg = regmap_format_16_be; + break; + case REGMAP_ENDIAN_NATIVE: + map->format.format_reg = regmap_format_16_native; + break; + default: + goto err_map; + } break; case 32: - map->format.format_reg = regmap_format_32; + switch (reg_endian) { + case REGMAP_ENDIAN_BIG: + map->format.format_reg = regmap_format_32_be; + break; + case REGMAP_ENDIAN_NATIVE: + map->format.format_reg = regmap_format_32_native; + break; + default: + goto err_map; + } break; default: @@ -338,21 +466,47 @@ struct regmap *regmap_init(struct device *dev, map->format.parse_val = regmap_parse_8; break; case 16: - map->format.format_val = regmap_format_16; - map->format.parse_val = regmap_parse_16; + switch (val_endian) { + case REGMAP_ENDIAN_BIG: + map->format.format_val = regmap_format_16_be; + map->format.parse_val = regmap_parse_16_be; + break; + case REGMAP_ENDIAN_NATIVE: + map->format.format_val = regmap_format_16_native; + map->format.parse_val = regmap_parse_16_native; + break; + default: + goto err_map; + } break; case 24: + if (val_endian != REGMAP_ENDIAN_BIG) + goto err_map; map->format.format_val = regmap_format_24; map->format.parse_val = regmap_parse_24; break; case 32: - map->format.format_val = regmap_format_32; - map->format.parse_val = regmap_parse_32; + switch (val_endian) { + case REGMAP_ENDIAN_BIG: + map->format.format_val = regmap_format_32_be; + map->format.parse_val = regmap_parse_32_be; + break; + case REGMAP_ENDIAN_NATIVE: + map->format.format_val = regmap_format_32_native; + map->format.parse_val = regmap_parse_32_native; + break; + default: + goto err_map; + } break; } - if (map->format.format_write) + if (map->format.format_write) { + if ((reg_endian != REGMAP_ENDIAN_BIG) || + (val_endian != REGMAP_ENDIAN_BIG)) + goto err_map; map->use_single_rw = true; + } if (!map->format.format_write && !(map->format.format_reg && map->format.format_val)) @@ -364,27 +518,88 @@ struct regmap *regmap_init(struct device *dev, goto err_map; } - regmap_debugfs_init(map, config->name); + map->range_tree = RB_ROOT; + for (i = 0; i < config->n_ranges; i++) { + const struct regmap_range_cfg *range_cfg = &config->ranges[i]; + struct regmap_range_node *new; + + /* Sanity check */ + if (range_cfg->range_max < range_cfg->range_min || + range_cfg->range_max > map->max_register || + range_cfg->selector_reg > map->max_register || + range_cfg->window_len == 0) + goto err_range; + + /* Make sure, that this register range has no selector + or data window within its boundary */ + for (j = 0; j < config->n_ranges; j++) { + unsigned sel_reg = config->ranges[j].selector_reg; + unsigned win_min = config->ranges[j].window_start; + unsigned win_max = win_min + + config->ranges[j].window_len - 1; + + if (range_cfg->range_min <= sel_reg && + sel_reg <= range_cfg->range_max) { + goto err_range; + } + + if (!(win_max < range_cfg->range_min || + win_min > range_cfg->range_max)) { + goto err_range; + } + } + + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (new == NULL) { + ret = -ENOMEM; + goto err_range; + } + + new->range_min = range_cfg->range_min; + new->range_max = range_cfg->range_max; + new->selector_reg = range_cfg->selector_reg; + new->selector_mask = range_cfg->selector_mask; + new->selector_shift = range_cfg->selector_shift; + new->window_start = range_cfg->window_start; + new->window_len = range_cfg->window_len; + + if (_regmap_range_add(map, new) == false) { + kfree(new); + goto err_range; + } + + if (map->selector_work_buf == NULL) { + map->selector_work_buf = + kzalloc(map->format.buf_size, GFP_KERNEL); + if (map->selector_work_buf == NULL) { + ret = -ENOMEM; + goto err_range; + } + } + } ret = regcache_init(map, config); if (ret < 0) - goto err_debugfs; + goto err_range; + + regmap_debugfs_init(map, config->name); /* Add a devres resource for dev_get_regmap() */ m = devres_alloc(dev_get_regmap_release, sizeof(*m), GFP_KERNEL); if (!m) { ret = -ENOMEM; - goto err_cache; + goto err_debugfs; } *m = map; devres_add(dev, m); return map; -err_cache: - regcache_exit(map); err_debugfs: regmap_debugfs_exit(map); + regcache_exit(map); +err_range: + regmap_range_exit(map); kfree(map->work_buf); err_map: kfree(map); @@ -481,6 +696,7 @@ void regmap_exit(struct regmap *map) { regcache_exit(map); regmap_debugfs_exit(map); + regmap_range_exit(map); if (map->bus->free_context) map->bus->free_context(map->bus_context); kfree(map->work_buf); @@ -526,6 +742,57 @@ struct regmap *dev_get_regmap(struct device *dev, const char *name) } EXPORT_SYMBOL_GPL(dev_get_regmap); +static int _regmap_select_page(struct regmap *map, unsigned int *reg, + unsigned int val_num) +{ + struct regmap_range_node *range; + void *orig_work_buf; + unsigned int win_offset; + unsigned int win_page; + bool page_chg; + int ret; + + range = _regmap_range_lookup(map, *reg); + if (range) { + win_offset = (*reg - range->range_min) % range->window_len; + win_page = (*reg - range->range_min) / range->window_len; + + if (val_num > 1) { + /* Bulk write shouldn't cross range boundary */ + if (*reg + val_num - 1 > range->range_max) + return -EINVAL; + + /* ... or single page boundary */ + if (val_num > range->window_len - win_offset) + return -EINVAL; + } + + /* It is possible to have selector register inside data window. + In that case, selector register is located on every page and + it needs no page switching, when accessed alone. */ + if (val_num > 1 || + range->window_start + win_offset != range->selector_reg) { + /* Use separate work_buf during page switching */ + orig_work_buf = map->work_buf; + map->work_buf = map->selector_work_buf; + + ret = _regmap_update_bits(map, range->selector_reg, + range->selector_mask, + win_page << range->selector_shift, + &page_chg); + + map->work_buf = orig_work_buf; + + if (ret < 0) + return ret; + } + + *reg = range->window_start + win_offset; + } + + return 0; +} + static int _regmap_raw_write(struct regmap *map, unsigned int reg, const void *val, size_t val_len) { @@ -563,6 +830,10 @@ static int _regmap_raw_write(struct regmap *map, unsigned int reg, } } + ret = _regmap_select_page(map, ®, val_len / map->format.val_bytes); + if (ret < 0) + return ret; + map->format.format_reg(map->work_buf, reg, map->reg_shift); u8[0] |= map->write_flag_mask; @@ -623,9 +894,18 @@ int _regmap_write(struct regmap *map, unsigned int reg, } } +#ifdef LOG_DEVICE + if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0) + dev_info(map->dev, "%x <= %x\n", reg, val); +#endif + trace_regmap_reg_write(map->dev, reg, val); if (map->format.format_write) { + ret = _regmap_select_page(map, ®, 1); + if (ret < 0) + return ret; + map->format.format_write(map, reg, val); trace_regmap_hw_write_start(map->dev, reg, 1); @@ -783,6 +1063,10 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, u8 *u8 = map->work_buf; int ret; + ret = _regmap_select_page(map, ®, val_len / map->format.val_bytes); + if (ret < 0) + return ret; + map->format.format_reg(map->work_buf, reg, map->reg_shift); /* @@ -826,6 +1110,12 @@ static int _regmap_read(struct regmap *map, unsigned int reg, ret = _regmap_raw_read(map, reg, map->work_buf, map->format.val_bytes); if (ret == 0) { *val = map->format.parse_val(map->work_buf); + +#ifdef LOG_DEVICE + if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0) + dev_info(map->dev, "%x => %x\n", reg, *val); +#endif + trace_regmap_reg_read(map->dev, reg, *val); } @@ -982,11 +1272,9 @@ static int _regmap_update_bits(struct regmap *map, unsigned int reg, int ret; unsigned int tmp, orig; - map->lock(map); - ret = _regmap_read(map, reg, &orig); if (ret != 0) - goto out; + return ret; tmp = orig & ~mask; tmp |= val & mask; @@ -998,9 +1286,6 @@ static int _regmap_update_bits(struct regmap *map, unsigned int reg, *change = false; } -out: - map->unlock(map); - return ret; } @@ -1018,7 +1303,13 @@ int regmap_update_bits(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val) { bool change; - return _regmap_update_bits(map, reg, mask, val, &change); + int ret; + + map->lock(map); + ret = _regmap_update_bits(map, reg, mask, val, &change); + map->unlock(map); + + return ret; } EXPORT_SYMBOL_GPL(regmap_update_bits); @@ -1038,7 +1329,12 @@ int regmap_update_bits_check(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, bool *change) { - return _regmap_update_bits(map, reg, mask, val, change); + int ret; + + map->lock(map); + ret = _regmap_update_bits(map, reg, mask, val, change); + map->unlock(map); + return ret; } EXPORT_SYMBOL_GPL(regmap_update_bits_check); diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index b5c5ff53cb57..fcb956bb4b4c 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -1475,10 +1475,17 @@ void _drbd_bm_set_bits(struct drbd_conf *mdev, const unsigned long s, const unsi first_word = 0; spin_lock_irq(&b->bm_lock); } - /* last page (respectively only page, for first page == last page) */ last_word = MLPP(el >> LN2_BPL); - bm_set_full_words_within_one_page(mdev->bitmap, last_page, first_word, last_word); + + /* consider bitmap->bm_bits = 32768, bitmap->bm_number_of_pages = 1. (or multiples). + * ==> e = 32767, el = 32768, last_page = 2, + * and now last_word = 0. + * We do not want to touch last_page in this case, + * as we did not allocate it, it is not present in bitmap->bm_pages. + */ + if (last_word) + bm_set_full_words_within_one_page(mdev->bitmap, last_page, first_word, last_word); /* possibly trailing bits. * example: (e & 63) == 63, el will be e+1. diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 9c5c84946b05..8e93a6ac9bb6 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -472,12 +472,17 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what, req->rq_state |= RQ_LOCAL_COMPLETED; req->rq_state &= ~RQ_LOCAL_PENDING; - D_ASSERT(!(req->rq_state & RQ_NET_MASK)); + if (req->rq_state & RQ_LOCAL_ABORTED) { + _req_may_be_done(req, m); + break; + } __drbd_chk_io_error(mdev, false); goto_queue_for_net_read: + D_ASSERT(!(req->rq_state & RQ_NET_MASK)); + /* no point in retrying if there is no good remote data, * or we have no connection. */ if (mdev->state.pdsk != D_UP_TO_DATE) { @@ -765,6 +770,40 @@ static int drbd_may_do_local_read(struct drbd_conf *mdev, sector_t sector, int s return 0 == drbd_bm_count_bits(mdev, sbnr, ebnr); } +static void maybe_pull_ahead(struct drbd_conf *mdev) +{ + int congested = 0; + + /* If I don't even have good local storage, we can not reasonably try + * to pull ahead of the peer. We also need the local reference to make + * sure mdev->act_log is there. + * Note: caller has to make sure that net_conf is there. + */ + if (!get_ldev_if_state(mdev, D_UP_TO_DATE)) + return; + + if (mdev->net_conf->cong_fill && + atomic_read(&mdev->ap_in_flight) >= mdev->net_conf->cong_fill) { + dev_info(DEV, "Congestion-fill threshold reached\n"); + congested = 1; + } + + if (mdev->act_log->used >= mdev->net_conf->cong_extents) { + dev_info(DEV, "Congestion-extents threshold reached\n"); + congested = 1; + } + + if (congested) { + queue_barrier(mdev); /* last barrier, after mirrored writes */ + + if (mdev->net_conf->on_congestion == OC_PULL_AHEAD) + _drbd_set_state(_NS(mdev, conn, C_AHEAD), 0, NULL); + else /*mdev->net_conf->on_congestion == OC_DISCONNECT */ + _drbd_set_state(_NS(mdev, conn, C_DISCONNECTING), 0, NULL); + } + put_ldev(mdev); +} + static int drbd_make_request_common(struct drbd_conf *mdev, struct bio *bio, unsigned long start_time) { const int rw = bio_rw(bio); @@ -972,29 +1011,8 @@ allocate_barrier: _req_mod(req, queue_for_send_oos); if (remote && - mdev->net_conf->on_congestion != OC_BLOCK && mdev->agreed_pro_version >= 96) { - int congested = 0; - - if (mdev->net_conf->cong_fill && - atomic_read(&mdev->ap_in_flight) >= mdev->net_conf->cong_fill) { - dev_info(DEV, "Congestion-fill threshold reached\n"); - congested = 1; - } - - if (mdev->act_log->used >= mdev->net_conf->cong_extents) { - dev_info(DEV, "Congestion-extents threshold reached\n"); - congested = 1; - } - - if (congested) { - queue_barrier(mdev); /* last barrier, after mirrored writes */ - - if (mdev->net_conf->on_congestion == OC_PULL_AHEAD) - _drbd_set_state(_NS(mdev, conn, C_AHEAD), 0, NULL); - else /*mdev->net_conf->on_congestion == OC_DISCONNECT */ - _drbd_set_state(_NS(mdev, conn, C_DISCONNECTING), 0, NULL); - } - } + mdev->net_conf->on_congestion != OC_BLOCK && mdev->agreed_pro_version >= 96) + maybe_pull_ahead(mdev); spin_unlock_irq(&mdev->req_lock); kfree(b); /* if someone else has beaten us to it... */ diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index cce7df367b79..553f43a90953 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -671,6 +671,7 @@ static void __reschedule_timeout(int drive, const char *message) if (drive == current_reqD) drive = current_drive; + __cancel_delayed_work(&fd_timeout); if (drive < 0 || drive >= N_DRIVE) { delay = 20UL * HZ; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index bbca966f8f66..3bba65510d23 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1597,14 +1597,12 @@ static int loop_add(struct loop_device **l, int i) struct gendisk *disk; int err; + err = -ENOMEM; lo = kzalloc(sizeof(*lo), GFP_KERNEL); - if (!lo) { - err = -ENOMEM; + if (!lo) goto out; - } - err = idr_pre_get(&loop_index_idr, GFP_KERNEL); - if (err < 0) + if (!idr_pre_get(&loop_index_idr, GFP_KERNEL)) goto out_free_dev; if (i >= 0) { diff --git a/drivers/block/mg_disk.c b/drivers/block/mg_disk.c index 76fa3deaee84..1788f491e0fb 100644 --- a/drivers/block/mg_disk.c +++ b/drivers/block/mg_disk.c @@ -780,9 +780,9 @@ static const struct block_device_operations mg_disk_ops = { .getgeo = mg_getgeo }; -static int mg_suspend(struct platform_device *plat_dev, pm_message_t state) +static int mg_suspend(struct device *dev) { - struct mg_drv_data *prv_data = plat_dev->dev.platform_data; + struct mg_drv_data *prv_data = dev->platform_data; struct mg_host *host = prv_data->host; if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD)) @@ -804,9 +804,9 @@ static int mg_suspend(struct platform_device *plat_dev, pm_message_t state) return 0; } -static int mg_resume(struct platform_device *plat_dev) +static int mg_resume(struct device *dev) { - struct mg_drv_data *prv_data = plat_dev->dev.platform_data; + struct mg_drv_data *prv_data = dev->platform_data; struct mg_host *host = prv_data->host; if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD)) @@ -825,6 +825,8 @@ static int mg_resume(struct platform_device *plat_dev) return 0; } +static SIMPLE_DEV_PM_OPS(mg_pm, mg_suspend, mg_resume); + static int mg_probe(struct platform_device *plat_dev) { struct mg_host *host; @@ -1074,11 +1076,10 @@ static int mg_remove(struct platform_device *plat_dev) static struct platform_driver mg_disk_driver = { .probe = mg_probe, .remove = mg_remove, - .suspend = mg_suspend, - .resume = mg_resume, .driver = { .name = MG_DEV_NAME, .owner = THIS_MODULE, + .pm = &mg_pm, } }; diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 264bc77dcb91..a8fddeb3d638 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -37,6 +37,7 @@ #include <linux/kthread.h> #include <../drivers/ata/ahci.h> #include <linux/export.h> +#include <linux/debugfs.h> #include "mtip32xx.h" #define HW_CMD_SLOT_SZ (MTIP_MAX_COMMAND_SLOTS * 32) @@ -85,6 +86,7 @@ static int instance; * allocated in mtip_init(). */ static int mtip_major; +static struct dentry *dfs_parent; static DEFINE_SPINLOCK(rssd_index_lock); static DEFINE_IDA(rssd_index_ida); @@ -2546,7 +2548,7 @@ static struct scatterlist *mtip_hw_get_scatterlist(struct driver_data *dd, } /* - * Sysfs register/status dump. + * Sysfs status dump. * * @dev Pointer to the device structure, passed by the kernrel. * @attr Pointer to the device_attribute structure passed by the kernel. @@ -2555,45 +2557,68 @@ static struct scatterlist *mtip_hw_get_scatterlist(struct driver_data *dd, * return value * The size, in bytes, of the data copied into buf. */ -static ssize_t mtip_hw_show_registers(struct device *dev, +static ssize_t mtip_hw_show_status(struct device *dev, struct device_attribute *attr, char *buf) { - u32 group_allocated; struct driver_data *dd = dev_to_disk(dev)->private_data; int size = 0; + + if (test_bit(MTIP_DDF_OVER_TEMP_BIT, &dd->dd_flag)) + size += sprintf(buf, "%s", "thermal_shutdown\n"); + else if (test_bit(MTIP_DDF_WRITE_PROTECT_BIT, &dd->dd_flag)) + size += sprintf(buf, "%s", "write_protect\n"); + else + size += sprintf(buf, "%s", "online\n"); + + return size; +} + +static DEVICE_ATTR(status, S_IRUGO, mtip_hw_show_status, NULL); + +static ssize_t mtip_hw_read_registers(struct file *f, char __user *ubuf, + size_t len, loff_t *offset) +{ + struct driver_data *dd = (struct driver_data *)f->private_data; + char buf[MTIP_DFS_MAX_BUF_SIZE]; + u32 group_allocated; + int size = *offset; int n; - size += sprintf(&buf[size], "Hardware\n--------\n"); - size += sprintf(&buf[size], "S ACTive : [ 0x"); + if (!len || size) + return 0; + + if (size < 0) + return -EINVAL; + + size += sprintf(&buf[size], "H/ S ACTive : [ 0x"); for (n = dd->slot_groups-1; n >= 0; n--) size += sprintf(&buf[size], "%08X ", readl(dd->port->s_active[n])); size += sprintf(&buf[size], "]\n"); - size += sprintf(&buf[size], "Command Issue : [ 0x"); + size += sprintf(&buf[size], "H/ Command Issue : [ 0x"); for (n = dd->slot_groups-1; n >= 0; n--) size += sprintf(&buf[size], "%08X ", readl(dd->port->cmd_issue[n])); size += sprintf(&buf[size], "]\n"); - size += sprintf(&buf[size], "Completed : [ 0x"); + size += sprintf(&buf[size], "H/ Completed : [ 0x"); for (n = dd->slot_groups-1; n >= 0; n--) size += sprintf(&buf[size], "%08X ", readl(dd->port->completed[n])); size += sprintf(&buf[size], "]\n"); - size += sprintf(&buf[size], "PORT IRQ STAT : [ 0x%08X ]\n", + size += sprintf(&buf[size], "H/ PORT IRQ STAT : [ 0x%08X ]\n", readl(dd->port->mmio + PORT_IRQ_STAT)); - size += sprintf(&buf[size], "HOST IRQ STAT : [ 0x%08X ]\n", + size += sprintf(&buf[size], "H/ HOST IRQ STAT : [ 0x%08X ]\n", readl(dd->mmio + HOST_IRQ_STAT)); size += sprintf(&buf[size], "\n"); - size += sprintf(&buf[size], "Local\n-----\n"); - size += sprintf(&buf[size], "Allocated : [ 0x"); + size += sprintf(&buf[size], "L/ Allocated : [ 0x"); for (n = dd->slot_groups-1; n >= 0; n--) { if (sizeof(long) > sizeof(u32)) @@ -2605,7 +2630,7 @@ static ssize_t mtip_hw_show_registers(struct device *dev, } size += sprintf(&buf[size], "]\n"); - size += sprintf(&buf[size], "Commands in Q: [ 0x"); + size += sprintf(&buf[size], "L/ Commands in Q : [ 0x"); for (n = dd->slot_groups-1; n >= 0; n--) { if (sizeof(long) > sizeof(u32)) @@ -2617,44 +2642,53 @@ static ssize_t mtip_hw_show_registers(struct device *dev, } size += sprintf(&buf[size], "]\n"); - return size; + *offset = size <= len ? size : len; + size = copy_to_user(ubuf, buf, *offset); + if (size) + return -EFAULT; + + return *offset; } -static ssize_t mtip_hw_show_status(struct device *dev, - struct device_attribute *attr, - char *buf) +static ssize_t mtip_hw_read_flags(struct file *f, char __user *ubuf, + size_t len, loff_t *offset) { - struct driver_data *dd = dev_to_disk(dev)->private_data; - int size = 0; + struct driver_data *dd = (struct driver_data *)f->private_data; + char buf[MTIP_DFS_MAX_BUF_SIZE]; + int size = *offset; - if (test_bit(MTIP_DDF_OVER_TEMP_BIT, &dd->dd_flag)) - size += sprintf(buf, "%s", "thermal_shutdown\n"); - else if (test_bit(MTIP_DDF_WRITE_PROTECT_BIT, &dd->dd_flag)) - size += sprintf(buf, "%s", "write_protect\n"); - else - size += sprintf(buf, "%s", "online\n"); - - return size; -} + if (!len || size) + return 0; -static ssize_t mtip_hw_show_flags(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct driver_data *dd = dev_to_disk(dev)->private_data; - int size = 0; + if (size < 0) + return -EINVAL; - size += sprintf(&buf[size], "Flag in port struct : [ %08lX ]\n", + size += sprintf(&buf[size], "Flag-port : [ %08lX ]\n", dd->port->flags); - size += sprintf(&buf[size], "Flag in dd struct : [ %08lX ]\n", + size += sprintf(&buf[size], "Flag-dd : [ %08lX ]\n", dd->dd_flag); - return size; + *offset = size <= len ? size : len; + size = copy_to_user(ubuf, buf, *offset); + if (size) + return -EFAULT; + + return *offset; } -static DEVICE_ATTR(registers, S_IRUGO, mtip_hw_show_registers, NULL); -static DEVICE_ATTR(status, S_IRUGO, mtip_hw_show_status, NULL); -static DEVICE_ATTR(flags, S_IRUGO, mtip_hw_show_flags, NULL); +static const struct file_operations mtip_regs_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = mtip_hw_read_registers, + .llseek = no_llseek, +}; + +static const struct file_operations mtip_flags_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = mtip_hw_read_flags, + .llseek = no_llseek, +}; /* * Create the sysfs related attributes. @@ -2671,15 +2705,9 @@ static int mtip_hw_sysfs_init(struct driver_data *dd, struct kobject *kobj) if (!kobj || !dd) return -EINVAL; - if (sysfs_create_file(kobj, &dev_attr_registers.attr)) - dev_warn(&dd->pdev->dev, - "Error creating 'registers' sysfs entry\n"); if (sysfs_create_file(kobj, &dev_attr_status.attr)) dev_warn(&dd->pdev->dev, "Error creating 'status' sysfs entry\n"); - if (sysfs_create_file(kobj, &dev_attr_flags.attr)) - dev_warn(&dd->pdev->dev, - "Error creating 'flags' sysfs entry\n"); return 0; } @@ -2698,13 +2726,39 @@ static int mtip_hw_sysfs_exit(struct driver_data *dd, struct kobject *kobj) if (!kobj || !dd) return -EINVAL; - sysfs_remove_file(kobj, &dev_attr_registers.attr); sysfs_remove_file(kobj, &dev_attr_status.attr); - sysfs_remove_file(kobj, &dev_attr_flags.attr); return 0; } +static int mtip_hw_debugfs_init(struct driver_data *dd) +{ + if (!dfs_parent) + return -1; + + dd->dfs_node = debugfs_create_dir(dd->disk->disk_name, dfs_parent); + if (IS_ERR_OR_NULL(dd->dfs_node)) { + dev_warn(&dd->pdev->dev, + "Error creating node %s under debugfs\n", + dd->disk->disk_name); + dd->dfs_node = NULL; + return -1; + } + + debugfs_create_file("flags", S_IRUGO, dd->dfs_node, dd, + &mtip_flags_fops); + debugfs_create_file("registers", S_IRUGO, dd->dfs_node, dd, + &mtip_regs_fops); + + return 0; +} + +static void mtip_hw_debugfs_exit(struct driver_data *dd) +{ + debugfs_remove_recursive(dd->dfs_node); +} + + /* * Perform any init/resume time hardware setup * @@ -3730,6 +3784,7 @@ skip_create_disk: mtip_hw_sysfs_init(dd, kobj); kobject_put(kobj); } + mtip_hw_debugfs_init(dd); if (dd->mtip_svc_handler) { set_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag); @@ -3755,6 +3810,8 @@ start_service_thread: return rv; kthread_run_error: + mtip_hw_debugfs_exit(dd); + /* Delete our gendisk. This also removes the device from /dev */ del_gendisk(dd->disk); @@ -3805,6 +3862,7 @@ static int mtip_block_remove(struct driver_data *dd) kobject_put(kobj); } } + mtip_hw_debugfs_exit(dd); /* * Delete our gendisk structure. This also removes the device @@ -4152,10 +4210,20 @@ static int __init mtip_init(void) } mtip_major = error; + if (!dfs_parent) { + dfs_parent = debugfs_create_dir("rssd", NULL); + if (IS_ERR_OR_NULL(dfs_parent)) { + printk(KERN_WARNING "Error creating debugfs parent\n"); + dfs_parent = NULL; + } + } + /* Register our PCI operations. */ error = pci_register_driver(&mtip_pci_driver); - if (error) + if (error) { + debugfs_remove(dfs_parent); unregister_blkdev(mtip_major, MTIP_DRV_NAME); + } return error; } @@ -4172,6 +4240,8 @@ static int __init mtip_init(void) */ static void __exit mtip_exit(void) { + debugfs_remove_recursive(dfs_parent); + /* Release the allocated major block device number. */ unregister_blkdev(mtip_major, MTIP_DRV_NAME); diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h index b2c88da26b2a..f51fc23d17bb 100644 --- a/drivers/block/mtip32xx/mtip32xx.h +++ b/drivers/block/mtip32xx/mtip32xx.h @@ -26,7 +26,6 @@ #include <linux/ata.h> #include <linux/interrupt.h> #include <linux/genhd.h> -#include <linux/version.h> /* Offset of Subsystem Device ID in pci confoguration space */ #define PCI_SUBSYSTEM_DEVICEID 0x2E @@ -111,6 +110,8 @@ #define dbg_printk(format, arg...) #endif +#define MTIP_DFS_MAX_BUF_SIZE 1024 + #define __force_bit2int (unsigned int __force) enum { @@ -447,6 +448,8 @@ struct driver_data { unsigned long dd_flag; /* NOTE: use atomic bit operations on this */ struct task_struct *mtip_svc_handler; /* task_struct of svc thd */ + + struct dentry *dfs_node; }; #endif diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 65665c9c42c6..8f428a8ab003 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -499,7 +499,7 @@ static int rbd_header_from_disk(struct rbd_image_header *header, / sizeof (*ondisk)) return -EINVAL; header->snapc = kmalloc(sizeof(struct ceph_snap_context) + - snap_count * sizeof (*ondisk), + snap_count * sizeof(u64), gfp_flags); if (!header->snapc) return -ENOMEM; @@ -977,7 +977,7 @@ static void rbd_req_cb(struct ceph_osd_request *req, struct ceph_msg *msg) op = (void *)(replyhead + 1); rc = le32_to_cpu(replyhead->result); bytes = le64_to_cpu(op->extent.length); - read_op = (le32_to_cpu(op->op) == CEPH_OSD_OP_READ); + read_op = (le16_to_cpu(op->op) == CEPH_OSD_OP_READ); dout("rbd_req_cb bytes=%lld readop=%d rc=%d\n", bytes, read_op, rc); diff --git a/drivers/block/umem.c b/drivers/block/umem.c index aa2712060bfb..9a72277a31df 100644 --- a/drivers/block/umem.c +++ b/drivers/block/umem.c @@ -513,6 +513,44 @@ static void process_page(unsigned long data) } } +struct mm_plug_cb { + struct blk_plug_cb cb; + struct cardinfo *card; +}; + +static void mm_unplug(struct blk_plug_cb *cb) +{ + struct mm_plug_cb *mmcb = container_of(cb, struct mm_plug_cb, cb); + + spin_lock_irq(&mmcb->card->lock); + activate(mmcb->card); + spin_unlock_irq(&mmcb->card->lock); + kfree(mmcb); +} + +static int mm_check_plugged(struct cardinfo *card) +{ + struct blk_plug *plug = current->plug; + struct mm_plug_cb *mmcb; + + if (!plug) + return 0; + + list_for_each_entry(mmcb, &plug->cb_list, cb.list) { + if (mmcb->cb.callback == mm_unplug && mmcb->card == card) + return 1; + } + /* Not currently on the callback list */ + mmcb = kmalloc(sizeof(*mmcb), GFP_ATOMIC); + if (!mmcb) + return 0; + + mmcb->card = card; + mmcb->cb.callback = mm_unplug; + list_add(&mmcb->cb.list, &plug->cb_list); + return 1; +} + static void mm_make_request(struct request_queue *q, struct bio *bio) { struct cardinfo *card = q->queuedata; @@ -523,6 +561,8 @@ static void mm_make_request(struct request_queue *q, struct bio *bio) *card->biotail = bio; bio->bi_next = NULL; card->biotail = &bio->bi_next; + if (bio->bi_rw & REQ_SYNC || !mm_check_plugged(card)) + activate(card); spin_unlock_irq(&card->lock); return; diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index 773cf27dc23f..9ad3b5ec1dc1 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -257,6 +257,7 @@ static inline void blkif_get_x86_32_req(struct blkif_request *dst, break; case BLKIF_OP_DISCARD: dst->u.discard.flag = src->u.discard.flag; + dst->u.discard.id = src->u.discard.id; dst->u.discard.sector_number = src->u.discard.sector_number; dst->u.discard.nr_sectors = src->u.discard.nr_sectors; break; @@ -287,6 +288,7 @@ static inline void blkif_get_x86_64_req(struct blkif_request *dst, break; case BLKIF_OP_DISCARD: dst->u.discard.flag = src->u.discard.flag; + dst->u.discard.id = src->u.discard.id; dst->u.discard.sector_number = src->u.discard.sector_number; dst->u.discard.nr_sectors = src->u.discard.nr_sectors; break; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 60eed4bdd2e4..e4fb3374dcd2 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -141,14 +141,36 @@ static int get_id_from_freelist(struct blkfront_info *info) return free; } -static void add_id_to_freelist(struct blkfront_info *info, +static int add_id_to_freelist(struct blkfront_info *info, unsigned long id) { + if (info->shadow[id].req.u.rw.id != id) + return -EINVAL; + if (info->shadow[id].request == NULL) + return -EINVAL; info->shadow[id].req.u.rw.id = info->shadow_free; info->shadow[id].request = NULL; info->shadow_free = id; + return 0; } +static const char *op_name(int op) +{ + static const char *const names[] = { + [BLKIF_OP_READ] = "read", + [BLKIF_OP_WRITE] = "write", + [BLKIF_OP_WRITE_BARRIER] = "barrier", + [BLKIF_OP_FLUSH_DISKCACHE] = "flush", + [BLKIF_OP_DISCARD] = "discard" }; + + if (op < 0 || op >= ARRAY_SIZE(names)) + return "unknown"; + + if (!names[op]) + return "reserved"; + + return names[op]; +} static int xlbd_reserve_minors(unsigned int minor, unsigned int nr) { unsigned int end = minor + nr; @@ -746,20 +768,36 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) bret = RING_GET_RESPONSE(&info->ring, i); id = bret->id; + /* + * The backend has messed up and given us an id that we would + * never have given to it (we stamp it up to BLK_RING_SIZE - + * look in get_id_from_freelist. + */ + if (id >= BLK_RING_SIZE) { + WARN(1, "%s: response to %s has incorrect id (%ld)\n", + info->gd->disk_name, op_name(bret->operation), id); + /* We can't safely get the 'struct request' as + * the id is busted. */ + continue; + } req = info->shadow[id].request; if (bret->operation != BLKIF_OP_DISCARD) blkif_completion(&info->shadow[id]); - add_id_to_freelist(info, id); + if (add_id_to_freelist(info, id)) { + WARN(1, "%s: response to %s (id %ld) couldn't be recycled!\n", + info->gd->disk_name, op_name(bret->operation), id); + continue; + } error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO; switch (bret->operation) { case BLKIF_OP_DISCARD: if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) { struct request_queue *rq = info->rq; - printk(KERN_WARNING "blkfront: %s: discard op failed\n", - info->gd->disk_name); + printk(KERN_WARNING "blkfront: %s: %s op failed\n", + info->gd->disk_name, op_name(bret->operation)); error = -EOPNOTSUPP; info->feature_discard = 0; info->feature_secdiscard = 0; @@ -771,18 +809,14 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) case BLKIF_OP_FLUSH_DISKCACHE: case BLKIF_OP_WRITE_BARRIER: if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) { - printk(KERN_WARNING "blkfront: %s: write %s op failed\n", - info->flush_op == BLKIF_OP_WRITE_BARRIER ? - "barrier" : "flush disk cache", - info->gd->disk_name); + printk(KERN_WARNING "blkfront: %s: %s op failed\n", + info->gd->disk_name, op_name(bret->operation)); error = -EOPNOTSUPP; } if (unlikely(bret->status == BLKIF_RSP_ERROR && info->shadow[id].req.u.rw.nr_segments == 0)) { - printk(KERN_WARNING "blkfront: %s: empty write %s op failed\n", - info->flush_op == BLKIF_OP_WRITE_BARRIER ? - "barrier" : "flush disk cache", - info->gd->disk_name); + printk(KERN_WARNING "blkfront: %s: empty %s op failed\n", + info->gd->disk_name, op_name(bret->operation)); error = -EOPNOTSUPP; } if (unlikely(error)) { diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c index 1412565c01af..d706bd0e9e80 100644 --- a/drivers/char/hw_random/omap-rng.c +++ b/drivers/char/hw_random/omap-rng.c @@ -162,22 +162,24 @@ static int __exit omap_rng_remove(struct platform_device *pdev) #ifdef CONFIG_PM -static int omap_rng_suspend(struct platform_device *pdev, pm_message_t message) +static int omap_rng_suspend(struct device *dev) { omap_rng_write_reg(RNG_MASK_REG, 0x0); return 0; } -static int omap_rng_resume(struct platform_device *pdev) +static int omap_rng_resume(struct device *dev) { omap_rng_write_reg(RNG_MASK_REG, 0x1); return 0; } +static SIMPLE_DEV_PM_OPS(omap_rng_pm, omap_rng_suspend, omap_rng_resume); +#define OMAP_RNG_PM (&omap_rng_pm) + #else -#define omap_rng_suspend NULL -#define omap_rng_resume NULL +#define OMAP_RNG_PM NULL #endif @@ -188,11 +190,10 @@ static struct platform_driver omap_rng_driver = { .driver = { .name = "omap_rng", .owner = THIS_MODULE, + .pm = OMAP_RNG_PM, }, .probe = omap_rng_probe, .remove = __exit_p(omap_rng_remove), - .suspend = omap_rng_suspend, - .resume = omap_rng_resume }; static int __init omap_rng_init(void) diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 1e638fff40ea..83f85cf7fb1b 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -2503,18 +2503,6 @@ static void __devexit ipmi_pci_remove(struct pci_dev *pdev) cleanup_one_si(info); } -#ifdef CONFIG_PM -static int ipmi_pci_suspend(struct pci_dev *pdev, pm_message_t state) -{ - return 0; -} - -static int ipmi_pci_resume(struct pci_dev *pdev) -{ - return 0; -} -#endif - static struct pci_device_id ipmi_pci_devices[] = { { PCI_DEVICE(PCI_HP_VENDOR_ID, PCI_MMC_DEVICE_ID) }, { PCI_DEVICE_CLASS(PCI_ERMC_CLASSCODE, PCI_ERMC_CLASSCODE_MASK) }, @@ -2527,10 +2515,6 @@ static struct pci_driver ipmi_pci_driver = { .id_table = ipmi_pci_devices, .probe = ipmi_pci_probe, .remove = __devexit_p(ipmi_pci_remove), -#ifdef CONFIG_PM - .suspend = ipmi_pci_suspend, - .resume = ipmi_pci_resume, -#endif }; #endif /* CONFIG_PCI */ diff --git a/drivers/char/sonypi.c b/drivers/char/sonypi.c index 45713f0e7d61..f87780502b41 100644 --- a/drivers/char/sonypi.c +++ b/drivers/char/sonypi.c @@ -1459,7 +1459,7 @@ static int __devexit sonypi_remove(struct platform_device *dev) #ifdef CONFIG_PM static int old_camera_power; -static int sonypi_suspend(struct platform_device *dev, pm_message_t state) +static int sonypi_suspend(struct device *dev) { old_camera_power = sonypi_device.camera_power; sonypi_disable(); @@ -1467,14 +1467,16 @@ static int sonypi_suspend(struct platform_device *dev, pm_message_t state) return 0; } -static int sonypi_resume(struct platform_device *dev) +static int sonypi_resume(struct device *dev) { sonypi_enable(old_camera_power); return 0; } + +static SIMPLE_DEV_PM_OPS(sonypi_pm, sonypi_suspend, sonypi_resume); +#define SONYPI_PM (&sonypi_pm) #else -#define sonypi_suspend NULL -#define sonypi_resume NULL +#define SONYPI_PM NULL #endif static void sonypi_shutdown(struct platform_device *dev) @@ -1486,12 +1488,11 @@ static struct platform_driver sonypi_driver = { .driver = { .name = "sonypi", .owner = THIS_MODULE, + .pm = SONYPI_PM, }, .probe = sonypi_probe, .remove = __devexit_p(sonypi_remove), .shutdown = sonypi_shutdown, - .suspend = sonypi_suspend, - .resume = sonypi_resume, }; static struct platform_device *sonypi_platform_device; diff --git a/drivers/char/tpm/tpm.c b/drivers/char/tpm/tpm.c index ad7c7320dd1b..ae43ac55fc1e 100644 --- a/drivers/char/tpm/tpm.c +++ b/drivers/char/tpm/tpm.c @@ -1274,7 +1274,7 @@ static struct tpm_input_header savestate_header = { * We are about to suspend. Save the TPM state * so that it can be restored. */ -int tpm_pm_suspend(struct device *dev, pm_message_t pm_state) +int tpm_pm_suspend(struct device *dev) { struct tpm_chip *chip = dev_get_drvdata(dev); struct tpm_cmd_t cmd; diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index b1c5280ac159..917f727e6740 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -299,7 +299,7 @@ extern ssize_t tpm_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t tpm_read(struct file *, char __user *, size_t, loff_t *); extern void tpm_remove_hardware(struct device *); -extern int tpm_pm_suspend(struct device *, pm_message_t); +extern int tpm_pm_suspend(struct device *); extern int tpm_pm_resume(struct device *); extern int wait_for_tpm_stat(struct tpm_chip *, u8, unsigned long, wait_queue_head_t *); diff --git a/drivers/char/tpm/tpm_atmel.c b/drivers/char/tpm/tpm_atmel.c index c64a1bc65349..678d57019dc4 100644 --- a/drivers/char/tpm/tpm_atmel.c +++ b/drivers/char/tpm/tpm_atmel.c @@ -168,22 +168,14 @@ static void atml_plat_remove(void) } } -static int tpm_atml_suspend(struct platform_device *dev, pm_message_t msg) -{ - return tpm_pm_suspend(&dev->dev, msg); -} +static SIMPLE_DEV_PM_OPS(tpm_atml_pm, tpm_pm_suspend, tpm_pm_resume); -static int tpm_atml_resume(struct platform_device *dev) -{ - return tpm_pm_resume(&dev->dev); -} static struct platform_driver atml_drv = { .driver = { .name = "tpm_atmel", .owner = THIS_MODULE, + .pm = &tpm_atml_pm, }, - .suspend = tpm_atml_suspend, - .resume = tpm_atml_resume, }; static int __init init_atmel(void) diff --git a/drivers/char/tpm/tpm_nsc.c b/drivers/char/tpm/tpm_nsc.c index 4d2464871ada..640c9a427b59 100644 --- a/drivers/char/tpm/tpm_nsc.c +++ b/drivers/char/tpm/tpm_nsc.c @@ -274,22 +274,13 @@ static void tpm_nsc_remove(struct device *dev) } } -static int tpm_nsc_suspend(struct platform_device *dev, pm_message_t msg) -{ - return tpm_pm_suspend(&dev->dev, msg); -} - -static int tpm_nsc_resume(struct platform_device *dev) -{ - return tpm_pm_resume(&dev->dev); -} +static SIMPLE_DEV_PM_OPS(tpm_nsc_pm, tpm_pm_suspend, tpm_pm_resume); static struct platform_driver nsc_drv = { - .suspend = tpm_nsc_suspend, - .resume = tpm_nsc_resume, .driver = { .name = "tpm_nsc", .owner = THIS_MODULE, + .pm = &tpm_nsc_pm, }, }; diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index d2a70cae76df..89682fa8801e 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -750,7 +750,7 @@ static int __devinit tpm_tis_pnp_init(struct pnp_dev *pnp_dev, static int tpm_tis_pnp_suspend(struct pnp_dev *dev, pm_message_t msg) { - return tpm_pm_suspend(&dev->dev, msg); + return tpm_pm_suspend(&dev->dev); } static int tpm_tis_pnp_resume(struct pnp_dev *dev) @@ -806,27 +806,25 @@ module_param_string(hid, tpm_pnp_tbl[TIS_HID_USR_IDX].id, sizeof(tpm_pnp_tbl[TIS_HID_USR_IDX].id), 0444); MODULE_PARM_DESC(hid, "Set additional specific HID for this driver to probe"); #endif -static int tpm_tis_suspend(struct platform_device *dev, pm_message_t msg) -{ - return tpm_pm_suspend(&dev->dev, msg); -} -static int tpm_tis_resume(struct platform_device *dev) +static int tpm_tis_resume(struct device *dev) { - struct tpm_chip *chip = dev_get_drvdata(&dev->dev); + struct tpm_chip *chip = dev_get_drvdata(dev); if (chip->vendor.irq) tpm_tis_reenable_interrupts(chip); - return tpm_pm_resume(&dev->dev); + return tpm_pm_resume(dev); } + +static SIMPLE_DEV_PM_OPS(tpm_tis_pm, tpm_pm_suspend, tpm_tis_resume); + static struct platform_driver tis_drv = { .driver = { .name = "tpm_tis", .owner = THIS_MODULE, + .pm = &tpm_tis_pm, }, - .suspend = tpm_tis_suspend, - .resume = tpm_tis_resume, }; static struct platform_device *pdev; diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index dcbe05616090..9a1eb0cfa95f 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1067,26 +1067,24 @@ static int __clk_set_parent(struct clk *clk, struct clk *parent) old_parent = clk->parent; - /* find index of new parent clock using cached parent ptrs */ - if (clk->parents) - for (i = 0; i < clk->num_parents; i++) - if (clk->parents[i] == parent) - break; - else + if (!clk->parents) clk->parents = kzalloc((sizeof(struct clk*) * clk->num_parents), GFP_KERNEL); /* - * find index of new parent clock using string name comparison - * also try to cache the parent to avoid future calls to __clk_lookup + * find index of new parent clock using cached parent ptrs, + * or if not yet cached, use string name comparison and cache + * them now to avoid future calls to __clk_lookup. */ - if (i == clk->num_parents) - for (i = 0; i < clk->num_parents; i++) - if (!strcmp(clk->parent_names[i], parent->name)) { - if (clk->parents) - clk->parents[i] = __clk_lookup(parent->name); - break; - } + for (i = 0; i < clk->num_parents; i++) { + if (clk->parents && clk->parents[i] == parent) + break; + else if (!strcmp(clk->parent_names[i], parent->name)) { + if (clk->parents) + clk->parents[i] = __clk_lookup(parent->name); + break; + } + } if (i == clk->num_parents) { pr_debug("%s: clock %s is not a possible parent of clock %s\n", diff --git a/drivers/clk/spear/spear1310_clock.c b/drivers/clk/spear/spear1310_clock.c index 8f05652d53e6..0fcec2aae19c 100644 --- a/drivers/clk/spear/spear1310_clock.c +++ b/drivers/clk/spear/spear1310_clock.c @@ -345,31 +345,30 @@ static struct frac_rate_tbl gen_rtbl[] = { /* clock parents */ static const char *vco_parents[] = { "osc_24m_clk", "osc_25m_clk", }; static const char *gpt_parents[] = { "osc_24m_clk", "apb_clk", }; -static const char *uart0_parents[] = { "pll5_clk", "uart_synth_gate_clk", }; -static const char *c3_parents[] = { "pll5_clk", "c3_synth_gate_clk", }; -static const char *gmac_phy_input_parents[] = { "gmii_125m_pad_clk", "pll2_clk", +static const char *uart0_parents[] = { "pll5_clk", "uart_syn_gclk", }; +static const char *c3_parents[] = { "pll5_clk", "c3_syn_gclk", }; +static const char *gmac_phy_input_parents[] = { "gmii_pad_clk", "pll2_clk", "osc_25m_clk", }; -static const char *gmac_phy_parents[] = { "gmac_phy_input_mux_clk", - "gmac_phy_synth_gate_clk", }; +static const char *gmac_phy_parents[] = { "phy_input_mclk", "phy_syn_gclk", }; static const char *clcd_synth_parents[] = { "vco1div4_clk", "pll2_clk", }; -static const char *clcd_pixel_parents[] = { "pll5_clk", "clcd_synth_clk", }; +static const char *clcd_pixel_parents[] = { "pll5_clk", "clcd_syn_clk", }; static const char *i2s_src_parents[] = { "vco1div2_clk", "none", "pll3_clk", "i2s_src_pad_clk", }; -static const char *i2s_ref_parents[] = { "i2s_src_mux_clk", "i2s_prs1_clk", }; +static const char *i2s_ref_parents[] = { "i2s_src_mclk", "i2s_prs1_clk", }; static const char *gen_synth0_1_parents[] = { "vco1div4_clk", "vco3div2_clk", "pll3_clk", }; static const char *gen_synth2_3_parents[] = { "vco1div4_clk", "vco3div2_clk", "pll2_clk", }; static const char *rmii_phy_parents[] = { "ras_tx50_clk", "none", - "ras_pll2_clk", "ras_synth0_clk", }; + "ras_pll2_clk", "ras_syn0_clk", }; static const char *smii_rgmii_phy_parents[] = { "none", "ras_tx125_clk", - "ras_pll2_clk", "ras_synth0_clk", }; -static const char *uart_parents[] = { "ras_apb_clk", "gen_synth3_clk", }; -static const char *i2c_parents[] = { "ras_apb_clk", "gen_synth1_clk", }; -static const char *ssp1_parents[] = { "ras_apb_clk", "gen_synth1_clk", + "ras_pll2_clk", "ras_syn0_clk", }; +static const char *uart_parents[] = { "ras_apb_clk", "gen_syn3_clk", }; +static const char *i2c_parents[] = { "ras_apb_clk", "gen_syn1_clk", }; +static const char *ssp1_parents[] = { "ras_apb_clk", "gen_syn1_clk", "ras_plclk0_clk", }; -static const char *pci_parents[] = { "ras_pll3_clk", "gen_synth2_clk", }; -static const char *tdm_parents[] = { "ras_pll3_clk", "gen_synth1_clk", }; +static const char *pci_parents[] = { "ras_pll3_clk", "gen_syn2_clk", }; +static const char *tdm_parents[] = { "ras_pll3_clk", "gen_syn1_clk", }; void __init spear1310_clk_init(void) { @@ -390,9 +389,9 @@ void __init spear1310_clk_init(void) 25000000); clk_register_clkdev(clk, "osc_25m_clk", NULL); - clk = clk_register_fixed_rate(NULL, "gmii_125m_pad_clk", NULL, - CLK_IS_ROOT, 125000000); - clk_register_clkdev(clk, "gmii_125m_pad_clk", NULL); + clk = clk_register_fixed_rate(NULL, "gmii_pad_clk", NULL, CLK_IS_ROOT, + 125000000); + clk_register_clkdev(clk, "gmii_pad_clk", NULL); clk = clk_register_fixed_rate(NULL, "i2s_src_pad_clk", NULL, CLK_IS_ROOT, 12288000); @@ -406,34 +405,34 @@ void __init spear1310_clk_init(void) /* clock derived from 24 or 25 MHz osc clk */ /* vco-pll */ - clk = clk_register_mux(NULL, "vco1_mux_clk", vco_parents, + clk = clk_register_mux(NULL, "vco1_mclk", vco_parents, ARRAY_SIZE(vco_parents), 0, SPEAR1310_PLL_CFG, SPEAR1310_PLL1_CLK_SHIFT, SPEAR1310_PLL_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "vco1_mux_clk", NULL); - clk = clk_register_vco_pll("vco1_clk", "pll1_clk", NULL, "vco1_mux_clk", + clk_register_clkdev(clk, "vco1_mclk", NULL); + clk = clk_register_vco_pll("vco1_clk", "pll1_clk", NULL, "vco1_mclk", 0, SPEAR1310_PLL1_CTR, SPEAR1310_PLL1_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), &_lock, &clk1, NULL); clk_register_clkdev(clk, "vco1_clk", NULL); clk_register_clkdev(clk1, "pll1_clk", NULL); - clk = clk_register_mux(NULL, "vco2_mux_clk", vco_parents, + clk = clk_register_mux(NULL, "vco2_mclk", vco_parents, ARRAY_SIZE(vco_parents), 0, SPEAR1310_PLL_CFG, SPEAR1310_PLL2_CLK_SHIFT, SPEAR1310_PLL_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "vco2_mux_clk", NULL); - clk = clk_register_vco_pll("vco2_clk", "pll2_clk", NULL, "vco2_mux_clk", + clk_register_clkdev(clk, "vco2_mclk", NULL); + clk = clk_register_vco_pll("vco2_clk", "pll2_clk", NULL, "vco2_mclk", 0, SPEAR1310_PLL2_CTR, SPEAR1310_PLL2_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), &_lock, &clk1, NULL); clk_register_clkdev(clk, "vco2_clk", NULL); clk_register_clkdev(clk1, "pll2_clk", NULL); - clk = clk_register_mux(NULL, "vco3_mux_clk", vco_parents, + clk = clk_register_mux(NULL, "vco3_mclk", vco_parents, ARRAY_SIZE(vco_parents), 0, SPEAR1310_PLL_CFG, SPEAR1310_PLL3_CLK_SHIFT, SPEAR1310_PLL_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "vco3_mux_clk", NULL); - clk = clk_register_vco_pll("vco3_clk", "pll3_clk", NULL, "vco3_mux_clk", + clk_register_clkdev(clk, "vco3_mclk", NULL); + clk = clk_register_vco_pll("vco3_clk", "pll3_clk", NULL, "vco3_mclk", 0, SPEAR1310_PLL3_CTR, SPEAR1310_PLL3_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), &_lock, &clk1, NULL); clk_register_clkdev(clk, "vco3_clk", NULL); @@ -473,7 +472,7 @@ void __init spear1310_clk_init(void) /* peripherals */ clk_register_fixed_factor(NULL, "thermal_clk", "osc_24m_clk", 0, 1, 128); - clk = clk_register_gate(NULL, "thermal_gate_clk", "thermal_clk", 0, + clk = clk_register_gate(NULL, "thermal_gclk", "thermal_clk", 0, SPEAR1310_PERIP2_CLK_ENB, SPEAR1310_THSENS_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spear_thermal"); @@ -500,177 +499,176 @@ void __init spear1310_clk_init(void) clk_register_clkdev(clk, "apb_clk", NULL); /* gpt clocks */ - clk = clk_register_mux(NULL, "gpt0_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt0_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_GPT0_CLK_SHIFT, SPEAR1310_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt0_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt0_clk", "gpt0_mux_clk", 0, + clk_register_clkdev(clk, "gpt0_mclk", NULL); + clk = clk_register_gate(NULL, "gpt0_clk", "gpt0_mclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_GPT0_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt0"); - clk = clk_register_mux(NULL, "gpt1_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt1_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_GPT1_CLK_SHIFT, SPEAR1310_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt1_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mux_clk", 0, + clk_register_clkdev(clk, "gpt1_mclk", NULL); + clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_GPT1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt1"); - clk = clk_register_mux(NULL, "gpt2_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt2_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_GPT2_CLK_SHIFT, SPEAR1310_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt2_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mux_clk", 0, + clk_register_clkdev(clk, "gpt2_mclk", NULL); + clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mclk", 0, SPEAR1310_PERIP2_CLK_ENB, SPEAR1310_GPT2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt2"); - clk = clk_register_mux(NULL, "gpt3_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt3_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_GPT3_CLK_SHIFT, SPEAR1310_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt3_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt3_clk", "gpt3_mux_clk", 0, + clk_register_clkdev(clk, "gpt3_mclk", NULL); + clk = clk_register_gate(NULL, "gpt3_clk", "gpt3_mclk", 0, SPEAR1310_PERIP2_CLK_ENB, SPEAR1310_GPT3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt3"); /* others */ - clk = clk_register_aux("uart_synth_clk", "uart_synth_gate_clk", - "vco1div2_clk", 0, SPEAR1310_UART_CLK_SYNT, NULL, - aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "uart_synth_clk", NULL); - clk_register_clkdev(clk1, "uart_synth_gate_clk", NULL); + clk = clk_register_aux("uart_syn_clk", "uart_syn_gclk", "vco1div2_clk", + 0, SPEAR1310_UART_CLK_SYNT, NULL, aux_rtbl, + ARRAY_SIZE(aux_rtbl), &_lock, &clk1); + clk_register_clkdev(clk, "uart_syn_clk", NULL); + clk_register_clkdev(clk1, "uart_syn_gclk", NULL); - clk = clk_register_mux(NULL, "uart0_mux_clk", uart0_parents, + clk = clk_register_mux(NULL, "uart0_mclk", uart0_parents, ARRAY_SIZE(uart0_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_UART_CLK_SHIFT, SPEAR1310_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart0_mux_clk", NULL); + clk_register_clkdev(clk, "uart0_mclk", NULL); - clk = clk_register_gate(NULL, "uart0_clk", "uart0_mux_clk", 0, + clk = clk_register_gate(NULL, "uart0_clk", "uart0_mclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_UART_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "e0000000.serial"); - clk = clk_register_aux("sdhci_synth_clk", "sdhci_synth_gate_clk", + clk = clk_register_aux("sdhci_syn_clk", "sdhci_syn_gclk", "vco1div2_clk", 0, SPEAR1310_SDHCI_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "sdhci_synth_clk", NULL); - clk_register_clkdev(clk1, "sdhci_synth_gate_clk", NULL); + clk_register_clkdev(clk, "sdhci_syn_clk", NULL); + clk_register_clkdev(clk1, "sdhci_syn_gclk", NULL); - clk = clk_register_gate(NULL, "sdhci_clk", "sdhci_synth_gate_clk", 0, + clk = clk_register_gate(NULL, "sdhci_clk", "sdhci_syn_gclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_SDHCI_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "b3000000.sdhci"); - clk = clk_register_aux("cfxd_synth_clk", "cfxd_synth_gate_clk", - "vco1div2_clk", 0, SPEAR1310_CFXD_CLK_SYNT, NULL, - aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "cfxd_synth_clk", NULL); - clk_register_clkdev(clk1, "cfxd_synth_gate_clk", NULL); + clk = clk_register_aux("cfxd_syn_clk", "cfxd_syn_gclk", "vco1div2_clk", + 0, SPEAR1310_CFXD_CLK_SYNT, NULL, aux_rtbl, + ARRAY_SIZE(aux_rtbl), &_lock, &clk1); + clk_register_clkdev(clk, "cfxd_syn_clk", NULL); + clk_register_clkdev(clk1, "cfxd_syn_gclk", NULL); - clk = clk_register_gate(NULL, "cfxd_clk", "cfxd_synth_gate_clk", 0, + clk = clk_register_gate(NULL, "cfxd_clk", "cfxd_syn_gclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_CFXD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "b2800000.cf"); clk_register_clkdev(clk, NULL, "arasan_xd"); - clk = clk_register_aux("c3_synth_clk", "c3_synth_gate_clk", - "vco1div2_clk", 0, SPEAR1310_C3_CLK_SYNT, NULL, - aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "c3_synth_clk", NULL); - clk_register_clkdev(clk1, "c3_synth_gate_clk", NULL); + clk = clk_register_aux("c3_syn_clk", "c3_syn_gclk", "vco1div2_clk", + 0, SPEAR1310_C3_CLK_SYNT, NULL, aux_rtbl, + ARRAY_SIZE(aux_rtbl), &_lock, &clk1); + clk_register_clkdev(clk, "c3_syn_clk", NULL); + clk_register_clkdev(clk1, "c3_syn_gclk", NULL); - clk = clk_register_mux(NULL, "c3_mux_clk", c3_parents, + clk = clk_register_mux(NULL, "c3_mclk", c3_parents, ARRAY_SIZE(c3_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_C3_CLK_SHIFT, SPEAR1310_C3_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "c3_mux_clk", NULL); + clk_register_clkdev(clk, "c3_mclk", NULL); - clk = clk_register_gate(NULL, "c3_clk", "c3_mux_clk", 0, + clk = clk_register_gate(NULL, "c3_clk", "c3_mclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_C3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "c3"); /* gmac */ - clk = clk_register_mux(NULL, "gmac_phy_input_mux_clk", - gmac_phy_input_parents, + clk = clk_register_mux(NULL, "phy_input_mclk", gmac_phy_input_parents, ARRAY_SIZE(gmac_phy_input_parents), 0, SPEAR1310_GMAC_CLK_CFG, SPEAR1310_GMAC_PHY_INPUT_CLK_SHIFT, SPEAR1310_GMAC_PHY_INPUT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gmac_phy_input_mux_clk", NULL); + clk_register_clkdev(clk, "phy_input_mclk", NULL); - clk = clk_register_aux("gmac_phy_synth_clk", "gmac_phy_synth_gate_clk", - "gmac_phy_input_mux_clk", 0, SPEAR1310_GMAC_CLK_SYNT, - NULL, gmac_rtbl, ARRAY_SIZE(gmac_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "gmac_phy_synth_clk", NULL); - clk_register_clkdev(clk1, "gmac_phy_synth_gate_clk", NULL); + clk = clk_register_aux("phy_syn_clk", "phy_syn_gclk", "phy_input_mclk", + 0, SPEAR1310_GMAC_CLK_SYNT, NULL, gmac_rtbl, + ARRAY_SIZE(gmac_rtbl), &_lock, &clk1); + clk_register_clkdev(clk, "phy_syn_clk", NULL); + clk_register_clkdev(clk1, "phy_syn_gclk", NULL); - clk = clk_register_mux(NULL, "gmac_phy_mux_clk", gmac_phy_parents, + clk = clk_register_mux(NULL, "phy_mclk", gmac_phy_parents, ARRAY_SIZE(gmac_phy_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_GMAC_PHY_CLK_SHIFT, SPEAR1310_GMAC_PHY_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, NULL, "stmmacphy.0"); /* clcd */ - clk = clk_register_mux(NULL, "clcd_synth_mux_clk", clcd_synth_parents, + clk = clk_register_mux(NULL, "clcd_syn_mclk", clcd_synth_parents, ARRAY_SIZE(clcd_synth_parents), 0, SPEAR1310_CLCD_CLK_SYNT, SPEAR1310_CLCD_SYNT_CLK_SHIFT, SPEAR1310_CLCD_SYNT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "clcd_synth_mux_clk", NULL); + clk_register_clkdev(clk, "clcd_syn_mclk", NULL); - clk = clk_register_frac("clcd_synth_clk", "clcd_synth_mux_clk", 0, + clk = clk_register_frac("clcd_syn_clk", "clcd_syn_mclk", 0, SPEAR1310_CLCD_CLK_SYNT, clcd_rtbl, ARRAY_SIZE(clcd_rtbl), &_lock); - clk_register_clkdev(clk, "clcd_synth_clk", NULL); + clk_register_clkdev(clk, "clcd_syn_clk", NULL); - clk = clk_register_mux(NULL, "clcd_pixel_mux_clk", clcd_pixel_parents, + clk = clk_register_mux(NULL, "clcd_pixel_mclk", clcd_pixel_parents, ARRAY_SIZE(clcd_pixel_parents), 0, SPEAR1310_PERIP_CLK_CFG, SPEAR1310_CLCD_CLK_SHIFT, SPEAR1310_CLCD_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, "clcd_pixel_clk", NULL); - clk = clk_register_gate(NULL, "clcd_clk", "clcd_pixel_mux_clk", 0, + clk = clk_register_gate(NULL, "clcd_clk", "clcd_pixel_mclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_CLCD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, "clcd_clk", NULL); /* i2s */ - clk = clk_register_mux(NULL, "i2s_src_mux_clk", i2s_src_parents, + clk = clk_register_mux(NULL, "i2s_src_mclk", i2s_src_parents, ARRAY_SIZE(i2s_src_parents), 0, SPEAR1310_I2S_CLK_CFG, SPEAR1310_I2S_SRC_CLK_SHIFT, SPEAR1310_I2S_SRC_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, "i2s_src_clk", NULL); - clk = clk_register_aux("i2s_prs1_clk", NULL, "i2s_src_mux_clk", 0, + clk = clk_register_aux("i2s_prs1_clk", NULL, "i2s_src_mclk", 0, SPEAR1310_I2S_CLK_CFG, &i2s_prs1_masks, i2s_prs1_rtbl, ARRAY_SIZE(i2s_prs1_rtbl), &_lock, NULL); clk_register_clkdev(clk, "i2s_prs1_clk", NULL); - clk = clk_register_mux(NULL, "i2s_ref_mux_clk", i2s_ref_parents, + clk = clk_register_mux(NULL, "i2s_ref_mclk", i2s_ref_parents, ARRAY_SIZE(i2s_ref_parents), 0, SPEAR1310_I2S_CLK_CFG, SPEAR1310_I2S_REF_SHIFT, SPEAR1310_I2S_REF_SEL_MASK, 0, &_lock); clk_register_clkdev(clk, "i2s_ref_clk", NULL); - clk = clk_register_gate(NULL, "i2s_ref_pad_clk", "i2s_ref_mux_clk", 0, + clk = clk_register_gate(NULL, "i2s_ref_pad_clk", "i2s_ref_mclk", 0, SPEAR1310_PERIP2_CLK_ENB, SPEAR1310_I2S_REF_PAD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, "i2s_ref_pad_clk", NULL); - clk = clk_register_aux("i2s_sclk_clk", "i2s_sclk_gate_clk", + clk = clk_register_aux("i2s_sclk_clk", "i2s_sclk_gclk", "i2s_ref_pad_clk", 0, SPEAR1310_I2S_CLK_CFG, &i2s_sclk_masks, i2s_sclk_rtbl, ARRAY_SIZE(i2s_sclk_rtbl), &_lock, &clk1); clk_register_clkdev(clk, "i2s_sclk_clk", NULL); - clk_register_clkdev(clk1, "i2s_sclk_gate_clk", NULL); + clk_register_clkdev(clk1, "i2s_sclk_gclk", NULL); /* clock derived from ahb clk */ clk = clk_register_gate(NULL, "i2c0_clk", "ahb_clk", 0, @@ -747,13 +745,13 @@ void __init spear1310_clk_init(void) &_lock); clk_register_clkdev(clk, "sysram1_clk", NULL); - clk = clk_register_aux("adc_synth_clk", "adc_synth_gate_clk", "ahb_clk", + clk = clk_register_aux("adc_syn_clk", "adc_syn_gclk", "ahb_clk", 0, SPEAR1310_ADC_CLK_SYNT, NULL, adc_rtbl, ARRAY_SIZE(adc_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "adc_synth_clk", NULL); - clk_register_clkdev(clk1, "adc_synth_gate_clk", NULL); + clk_register_clkdev(clk, "adc_syn_clk", NULL); + clk_register_clkdev(clk1, "adc_syn_gclk", NULL); - clk = clk_register_gate(NULL, "adc_clk", "adc_synth_gate_clk", 0, + clk = clk_register_gate(NULL, "adc_clk", "adc_syn_gclk", 0, SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_ADC_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "adc_clk"); @@ -790,37 +788,37 @@ void __init spear1310_clk_init(void) clk_register_clkdev(clk, NULL, "e0300000.kbd"); /* RAS clks */ - clk = clk_register_mux(NULL, "gen_synth0_1_mux_clk", - gen_synth0_1_parents, ARRAY_SIZE(gen_synth0_1_parents), - 0, SPEAR1310_PLL_CFG, SPEAR1310_RAS_SYNT0_1_CLK_SHIFT, + clk = clk_register_mux(NULL, "gen_syn0_1_mclk", gen_synth0_1_parents, + ARRAY_SIZE(gen_synth0_1_parents), 0, SPEAR1310_PLL_CFG, + SPEAR1310_RAS_SYNT0_1_CLK_SHIFT, SPEAR1310_RAS_SYNT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gen_synth0_1_clk", NULL); + clk_register_clkdev(clk, "gen_syn0_1_clk", NULL); - clk = clk_register_mux(NULL, "gen_synth2_3_mux_clk", - gen_synth2_3_parents, ARRAY_SIZE(gen_synth2_3_parents), - 0, SPEAR1310_PLL_CFG, SPEAR1310_RAS_SYNT2_3_CLK_SHIFT, + clk = clk_register_mux(NULL, "gen_syn2_3_mclk", gen_synth2_3_parents, + ARRAY_SIZE(gen_synth2_3_parents), 0, SPEAR1310_PLL_CFG, + SPEAR1310_RAS_SYNT2_3_CLK_SHIFT, SPEAR1310_RAS_SYNT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gen_synth2_3_clk", NULL); + clk_register_clkdev(clk, "gen_syn2_3_clk", NULL); - clk = clk_register_frac("gen_synth0_clk", "gen_synth0_1_clk", 0, + clk = clk_register_frac("gen_syn0_clk", "gen_syn0_1_clk", 0, SPEAR1310_RAS_CLK_SYNT0, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth0_clk", NULL); + clk_register_clkdev(clk, "gen_syn0_clk", NULL); - clk = clk_register_frac("gen_synth1_clk", "gen_synth0_1_clk", 0, + clk = clk_register_frac("gen_syn1_clk", "gen_syn0_1_clk", 0, SPEAR1310_RAS_CLK_SYNT1, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth1_clk", NULL); + clk_register_clkdev(clk, "gen_syn1_clk", NULL); - clk = clk_register_frac("gen_synth2_clk", "gen_synth2_3_clk", 0, + clk = clk_register_frac("gen_syn2_clk", "gen_syn2_3_clk", 0, SPEAR1310_RAS_CLK_SYNT2, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth2_clk", NULL); + clk_register_clkdev(clk, "gen_syn2_clk", NULL); - clk = clk_register_frac("gen_synth3_clk", "gen_synth2_3_clk", 0, + clk = clk_register_frac("gen_syn3_clk", "gen_syn2_3_clk", 0, SPEAR1310_RAS_CLK_SYNT3, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth3_clk", NULL); + clk_register_clkdev(clk, "gen_syn3_clk", NULL); clk = clk_register_gate(NULL, "ras_osc_24m_clk", "osc_24m_clk", 0, SPEAR1310_RAS_CLK_ENB, SPEAR1310_OSC_24M_CLK_ENB, 0, @@ -847,7 +845,7 @@ void __init spear1310_clk_init(void) &_lock); clk_register_clkdev(clk, "ras_pll3_clk", NULL); - clk = clk_register_gate(NULL, "ras_tx125_clk", "gmii_125m_pad_clk", 0, + clk = clk_register_gate(NULL, "ras_tx125_clk", "gmii_pad_clk", 0, SPEAR1310_RAS_CLK_ENB, SPEAR1310_C125M_PAD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, "ras_tx125_clk", NULL); @@ -912,7 +910,7 @@ void __init spear1310_clk_init(void) &_lock); clk_register_clkdev(clk, NULL, "5c700000.eth"); - clk = clk_register_mux(NULL, "smii_rgmii_phy_mux_clk", + clk = clk_register_mux(NULL, "smii_rgmii_phy_mclk", smii_rgmii_phy_parents, ARRAY_SIZE(smii_rgmii_phy_parents), 0, SPEAR1310_RAS_CTRL_REG1, @@ -922,184 +920,184 @@ void __init spear1310_clk_init(void) clk_register_clkdev(clk, NULL, "stmmacphy.2"); clk_register_clkdev(clk, NULL, "stmmacphy.4"); - clk = clk_register_mux(NULL, "rmii_phy_mux_clk", rmii_phy_parents, + clk = clk_register_mux(NULL, "rmii_phy_mclk", rmii_phy_parents, ARRAY_SIZE(rmii_phy_parents), 0, SPEAR1310_RAS_CTRL_REG1, SPEAR1310_RMII_PHY_CLK_SHIFT, SPEAR1310_PHY_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, NULL, "stmmacphy.3"); - clk = clk_register_mux(NULL, "uart1_mux_clk", uart_parents, + clk = clk_register_mux(NULL, "uart1_mclk", uart_parents, ARRAY_SIZE(uart_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_UART1_CLK_SHIFT, SPEAR1310_RAS_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart1_mux_clk", NULL); + clk_register_clkdev(clk, "uart1_mclk", NULL); - clk = clk_register_gate(NULL, "uart1_clk", "uart1_mux_clk", 0, + clk = clk_register_gate(NULL, "uart1_clk", "uart1_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_UART1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5c800000.serial"); - clk = clk_register_mux(NULL, "uart2_mux_clk", uart_parents, + clk = clk_register_mux(NULL, "uart2_mclk", uart_parents, ARRAY_SIZE(uart_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_UART2_CLK_SHIFT, SPEAR1310_RAS_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart2_mux_clk", NULL); + clk_register_clkdev(clk, "uart2_mclk", NULL); - clk = clk_register_gate(NULL, "uart2_clk", "uart2_mux_clk", 0, + clk = clk_register_gate(NULL, "uart2_clk", "uart2_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_UART2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5c900000.serial"); - clk = clk_register_mux(NULL, "uart3_mux_clk", uart_parents, + clk = clk_register_mux(NULL, "uart3_mclk", uart_parents, ARRAY_SIZE(uart_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_UART3_CLK_SHIFT, SPEAR1310_RAS_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart3_mux_clk", NULL); + clk_register_clkdev(clk, "uart3_mclk", NULL); - clk = clk_register_gate(NULL, "uart3_clk", "uart3_mux_clk", 0, + clk = clk_register_gate(NULL, "uart3_clk", "uart3_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_UART3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5ca00000.serial"); - clk = clk_register_mux(NULL, "uart4_mux_clk", uart_parents, + clk = clk_register_mux(NULL, "uart4_mclk", uart_parents, ARRAY_SIZE(uart_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_UART4_CLK_SHIFT, SPEAR1310_RAS_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart4_mux_clk", NULL); + clk_register_clkdev(clk, "uart4_mclk", NULL); - clk = clk_register_gate(NULL, "uart4_clk", "uart4_mux_clk", 0, + clk = clk_register_gate(NULL, "uart4_clk", "uart4_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_UART4_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5cb00000.serial"); - clk = clk_register_mux(NULL, "uart5_mux_clk", uart_parents, + clk = clk_register_mux(NULL, "uart5_mclk", uart_parents, ARRAY_SIZE(uart_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_UART5_CLK_SHIFT, SPEAR1310_RAS_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart5_mux_clk", NULL); + clk_register_clkdev(clk, "uart5_mclk", NULL); - clk = clk_register_gate(NULL, "uart5_clk", "uart5_mux_clk", 0, + clk = clk_register_gate(NULL, "uart5_clk", "uart5_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_UART5_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5cc00000.serial"); - clk = clk_register_mux(NULL, "i2c1_mux_clk", i2c_parents, + clk = clk_register_mux(NULL, "i2c1_mclk", i2c_parents, ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C1_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "i2c1_mux_clk", NULL); + clk_register_clkdev(clk, "i2c1_mclk", NULL); - clk = clk_register_gate(NULL, "i2c1_clk", "i2c1_mux_clk", 0, + clk = clk_register_gate(NULL, "i2c1_clk", "i2c1_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_I2C1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5cd00000.i2c"); - clk = clk_register_mux(NULL, "i2c2_mux_clk", i2c_parents, + clk = clk_register_mux(NULL, "i2c2_mclk", i2c_parents, ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C2_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "i2c2_mux_clk", NULL); + clk_register_clkdev(clk, "i2c2_mclk", NULL); - clk = clk_register_gate(NULL, "i2c2_clk", "i2c2_mux_clk", 0, + clk = clk_register_gate(NULL, "i2c2_clk", "i2c2_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_I2C2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5ce00000.i2c"); - clk = clk_register_mux(NULL, "i2c3_mux_clk", i2c_parents, + clk = clk_register_mux(NULL, "i2c3_mclk", i2c_parents, ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C3_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "i2c3_mux_clk", NULL); + clk_register_clkdev(clk, "i2c3_mclk", NULL); - clk = clk_register_gate(NULL, "i2c3_clk", "i2c3_mux_clk", 0, + clk = clk_register_gate(NULL, "i2c3_clk", "i2c3_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_I2C3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5cf00000.i2c"); - clk = clk_register_mux(NULL, "i2c4_mux_clk", i2c_parents, + clk = clk_register_mux(NULL, "i2c4_mclk", i2c_parents, ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C4_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "i2c4_mux_clk", NULL); + clk_register_clkdev(clk, "i2c4_mclk", NULL); - clk = clk_register_gate(NULL, "i2c4_clk", "i2c4_mux_clk", 0, + clk = clk_register_gate(NULL, "i2c4_clk", "i2c4_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_I2C4_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5d000000.i2c"); - clk = clk_register_mux(NULL, "i2c5_mux_clk", i2c_parents, + clk = clk_register_mux(NULL, "i2c5_mclk", i2c_parents, ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C5_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "i2c5_mux_clk", NULL); + clk_register_clkdev(clk, "i2c5_mclk", NULL); - clk = clk_register_gate(NULL, "i2c5_clk", "i2c5_mux_clk", 0, + clk = clk_register_gate(NULL, "i2c5_clk", "i2c5_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_I2C5_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5d100000.i2c"); - clk = clk_register_mux(NULL, "i2c6_mux_clk", i2c_parents, + clk = clk_register_mux(NULL, "i2c6_mclk", i2c_parents, ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C6_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "i2c6_mux_clk", NULL); + clk_register_clkdev(clk, "i2c6_mclk", NULL); - clk = clk_register_gate(NULL, "i2c6_clk", "i2c6_mux_clk", 0, + clk = clk_register_gate(NULL, "i2c6_clk", "i2c6_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_I2C6_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5d200000.i2c"); - clk = clk_register_mux(NULL, "i2c7_mux_clk", i2c_parents, + clk = clk_register_mux(NULL, "i2c7_mclk", i2c_parents, ARRAY_SIZE(i2c_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_I2C7_CLK_SHIFT, SPEAR1310_I2C_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "i2c7_mux_clk", NULL); + clk_register_clkdev(clk, "i2c7_mclk", NULL); - clk = clk_register_gate(NULL, "i2c7_clk", "i2c7_mux_clk", 0, + clk = clk_register_gate(NULL, "i2c7_clk", "i2c7_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_I2C7_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5d300000.i2c"); - clk = clk_register_mux(NULL, "ssp1_mux_clk", ssp1_parents, + clk = clk_register_mux(NULL, "ssp1_mclk", ssp1_parents, ARRAY_SIZE(ssp1_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_SSP1_CLK_SHIFT, SPEAR1310_SSP1_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "ssp1_mux_clk", NULL); + clk_register_clkdev(clk, "ssp1_mclk", NULL); - clk = clk_register_gate(NULL, "ssp1_clk", "ssp1_mux_clk", 0, + clk = clk_register_gate(NULL, "ssp1_clk", "ssp1_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_SSP1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "5d400000.spi"); - clk = clk_register_mux(NULL, "pci_mux_clk", pci_parents, + clk = clk_register_mux(NULL, "pci_mclk", pci_parents, ARRAY_SIZE(pci_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_PCI_CLK_SHIFT, SPEAR1310_PCI_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "pci_mux_clk", NULL); + clk_register_clkdev(clk, "pci_mclk", NULL); - clk = clk_register_gate(NULL, "pci_clk", "pci_mux_clk", 0, + clk = clk_register_gate(NULL, "pci_clk", "pci_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_PCI_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "pci"); - clk = clk_register_mux(NULL, "tdm1_mux_clk", tdm_parents, + clk = clk_register_mux(NULL, "tdm1_mclk", tdm_parents, ARRAY_SIZE(tdm_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_TDM1_CLK_SHIFT, SPEAR1310_TDM_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "tdm1_mux_clk", NULL); + clk_register_clkdev(clk, "tdm1_mclk", NULL); - clk = clk_register_gate(NULL, "tdm1_clk", "tdm1_mux_clk", 0, + clk = clk_register_gate(NULL, "tdm1_clk", "tdm1_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_TDM1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "tdm_hdlc.0"); - clk = clk_register_mux(NULL, "tdm2_mux_clk", tdm_parents, + clk = clk_register_mux(NULL, "tdm2_mclk", tdm_parents, ARRAY_SIZE(tdm_parents), 0, SPEAR1310_RAS_CTRL_REG0, SPEAR1310_TDM2_CLK_SHIFT, SPEAR1310_TDM_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "tdm2_mux_clk", NULL); + clk_register_clkdev(clk, "tdm2_mclk", NULL); - clk = clk_register_gate(NULL, "tdm2_clk", "tdm2_mux_clk", 0, + clk = clk_register_gate(NULL, "tdm2_clk", "tdm2_mclk", 0, SPEAR1310_RAS_SW_CLK_CTRL, SPEAR1310_TDM2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "tdm_hdlc.1"); diff --git a/drivers/clk/spear/spear1340_clock.c b/drivers/clk/spear/spear1340_clock.c index e3ea72162236..2352cee7f645 100644 --- a/drivers/clk/spear/spear1340_clock.c +++ b/drivers/clk/spear/spear1340_clock.c @@ -369,27 +369,25 @@ static struct frac_rate_tbl gen_rtbl[] = { /* clock parents */ static const char *vco_parents[] = { "osc_24m_clk", "osc_25m_clk", }; -static const char *sys_parents[] = { "none", "pll1_clk", "none", "none", - "sys_synth_clk", "none", "pll2_clk", "pll3_clk", }; -static const char *ahb_parents[] = { "cpu_div3_clk", "amba_synth_clk", }; +static const char *sys_parents[] = { "pll1_clk", "pll1_clk", "pll1_clk", + "pll1_clk", "sys_synth_clk", "sys_synth_clk", "pll2_clk", "pll3_clk", }; +static const char *ahb_parents[] = { "cpu_div3_clk", "amba_syn_clk", }; static const char *gpt_parents[] = { "osc_24m_clk", "apb_clk", }; static const char *uart0_parents[] = { "pll5_clk", "osc_24m_clk", - "uart0_synth_gate_clk", }; + "uart0_syn_gclk", }; static const char *uart1_parents[] = { "pll5_clk", "osc_24m_clk", - "uart1_synth_gate_clk", }; -static const char *c3_parents[] = { "pll5_clk", "c3_synth_gate_clk", }; -static const char *gmac_phy_input_parents[] = { "gmii_125m_pad_clk", "pll2_clk", + "uart1_syn_gclk", }; +static const char *c3_parents[] = { "pll5_clk", "c3_syn_gclk", }; +static const char *gmac_phy_input_parents[] = { "gmii_pad_clk", "pll2_clk", "osc_25m_clk", }; -static const char *gmac_phy_parents[] = { "gmac_phy_input_mux_clk", - "gmac_phy_synth_gate_clk", }; +static const char *gmac_phy_parents[] = { "phy_input_mclk", "phy_syn_gclk", }; static const char *clcd_synth_parents[] = { "vco1div4_clk", "pll2_clk", }; -static const char *clcd_pixel_parents[] = { "pll5_clk", "clcd_synth_clk", }; +static const char *clcd_pixel_parents[] = { "pll5_clk", "clcd_syn_clk", }; static const char *i2s_src_parents[] = { "vco1div2_clk", "pll2_clk", "pll3_clk", "i2s_src_pad_clk", }; -static const char *i2s_ref_parents[] = { "i2s_src_mux_clk", "i2s_prs1_clk", }; -static const char *spdif_out_parents[] = { "i2s_src_pad_clk", "gen_synth2_clk", -}; -static const char *spdif_in_parents[] = { "pll2_clk", "gen_synth3_clk", }; +static const char *i2s_ref_parents[] = { "i2s_src_mclk", "i2s_prs1_clk", }; +static const char *spdif_out_parents[] = { "i2s_src_pad_clk", "gen_syn2_clk", }; +static const char *spdif_in_parents[] = { "pll2_clk", "gen_syn3_clk", }; static const char *gen_synth0_1_parents[] = { "vco1div4_clk", "vco3div2_clk", "pll3_clk", }; @@ -415,9 +413,9 @@ void __init spear1340_clk_init(void) 25000000); clk_register_clkdev(clk, "osc_25m_clk", NULL); - clk = clk_register_fixed_rate(NULL, "gmii_125m_pad_clk", NULL, - CLK_IS_ROOT, 125000000); - clk_register_clkdev(clk, "gmii_125m_pad_clk", NULL); + clk = clk_register_fixed_rate(NULL, "gmii_pad_clk", NULL, CLK_IS_ROOT, + 125000000); + clk_register_clkdev(clk, "gmii_pad_clk", NULL); clk = clk_register_fixed_rate(NULL, "i2s_src_pad_clk", NULL, CLK_IS_ROOT, 12288000); @@ -431,35 +429,35 @@ void __init spear1340_clk_init(void) /* clock derived from 24 or 25 MHz osc clk */ /* vco-pll */ - clk = clk_register_mux(NULL, "vco1_mux_clk", vco_parents, + clk = clk_register_mux(NULL, "vco1_mclk", vco_parents, ARRAY_SIZE(vco_parents), 0, SPEAR1340_PLL_CFG, SPEAR1340_PLL1_CLK_SHIFT, SPEAR1340_PLL_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "vco1_mux_clk", NULL); - clk = clk_register_vco_pll("vco1_clk", "pll1_clk", NULL, "vco1_mux_clk", - 0, SPEAR1340_PLL1_CTR, SPEAR1340_PLL1_FRQ, pll_rtbl, + clk_register_clkdev(clk, "vco1_mclk", NULL); + clk = clk_register_vco_pll("vco1_clk", "pll1_clk", NULL, "vco1_mclk", 0, + SPEAR1340_PLL1_CTR, SPEAR1340_PLL1_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), &_lock, &clk1, NULL); clk_register_clkdev(clk, "vco1_clk", NULL); clk_register_clkdev(clk1, "pll1_clk", NULL); - clk = clk_register_mux(NULL, "vco2_mux_clk", vco_parents, + clk = clk_register_mux(NULL, "vco2_mclk", vco_parents, ARRAY_SIZE(vco_parents), 0, SPEAR1340_PLL_CFG, SPEAR1340_PLL2_CLK_SHIFT, SPEAR1340_PLL_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "vco2_mux_clk", NULL); - clk = clk_register_vco_pll("vco2_clk", "pll2_clk", NULL, "vco2_mux_clk", - 0, SPEAR1340_PLL2_CTR, SPEAR1340_PLL2_FRQ, pll_rtbl, + clk_register_clkdev(clk, "vco2_mclk", NULL); + clk = clk_register_vco_pll("vco2_clk", "pll2_clk", NULL, "vco2_mclk", 0, + SPEAR1340_PLL2_CTR, SPEAR1340_PLL2_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), &_lock, &clk1, NULL); clk_register_clkdev(clk, "vco2_clk", NULL); clk_register_clkdev(clk1, "pll2_clk", NULL); - clk = clk_register_mux(NULL, "vco3_mux_clk", vco_parents, + clk = clk_register_mux(NULL, "vco3_mclk", vco_parents, ARRAY_SIZE(vco_parents), 0, SPEAR1340_PLL_CFG, SPEAR1340_PLL3_CLK_SHIFT, SPEAR1340_PLL_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "vco3_mux_clk", NULL); - clk = clk_register_vco_pll("vco3_clk", "pll3_clk", NULL, "vco3_mux_clk", - 0, SPEAR1340_PLL3_CTR, SPEAR1340_PLL3_FRQ, pll_rtbl, + clk_register_clkdev(clk, "vco3_mclk", NULL); + clk = clk_register_vco_pll("vco3_clk", "pll3_clk", NULL, "vco3_mclk", 0, + SPEAR1340_PLL3_CTR, SPEAR1340_PLL3_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), &_lock, &clk1, NULL); clk_register_clkdev(clk, "vco3_clk", NULL); clk_register_clkdev(clk1, "pll3_clk", NULL); @@ -498,7 +496,7 @@ void __init spear1340_clk_init(void) /* peripherals */ clk_register_fixed_factor(NULL, "thermal_clk", "osc_24m_clk", 0, 1, 128); - clk = clk_register_gate(NULL, "thermal_gate_clk", "thermal_clk", 0, + clk = clk_register_gate(NULL, "thermal_gclk", "thermal_clk", 0, SPEAR1340_PERIP2_CLK_ENB, SPEAR1340_THSENS_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spear_thermal"); @@ -509,23 +507,23 @@ void __init spear1340_clk_init(void) clk_register_clkdev(clk, "ddr_clk", NULL); /* clock derived from pll1 clk */ - clk = clk_register_frac("sys_synth_clk", "vco1div2_clk", 0, + clk = clk_register_frac("sys_syn_clk", "vco1div2_clk", 0, SPEAR1340_SYS_CLK_SYNT, sys_synth_rtbl, ARRAY_SIZE(sys_synth_rtbl), &_lock); - clk_register_clkdev(clk, "sys_synth_clk", NULL); + clk_register_clkdev(clk, "sys_syn_clk", NULL); - clk = clk_register_frac("amba_synth_clk", "vco1div2_clk", 0, + clk = clk_register_frac("amba_syn_clk", "vco1div2_clk", 0, SPEAR1340_AMBA_CLK_SYNT, amba_synth_rtbl, ARRAY_SIZE(amba_synth_rtbl), &_lock); - clk_register_clkdev(clk, "amba_synth_clk", NULL); + clk_register_clkdev(clk, "amba_syn_clk", NULL); - clk = clk_register_mux(NULL, "sys_mux_clk", sys_parents, + clk = clk_register_mux(NULL, "sys_mclk", sys_parents, ARRAY_SIZE(sys_parents), 0, SPEAR1340_SYS_CLK_CTRL, SPEAR1340_SCLK_SRC_SEL_SHIFT, SPEAR1340_SCLK_SRC_SEL_MASK, 0, &_lock); clk_register_clkdev(clk, "sys_clk", NULL); - clk = clk_register_fixed_factor(NULL, "cpu_clk", "sys_mux_clk", 0, 1, + clk = clk_register_fixed_factor(NULL, "cpu_clk", "sys_mclk", 0, 1, 2); clk_register_clkdev(clk, "cpu_clk", NULL); @@ -548,194 +546,193 @@ void __init spear1340_clk_init(void) clk_register_clkdev(clk, "apb_clk", NULL); /* gpt clocks */ - clk = clk_register_mux(NULL, "gpt0_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt0_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_GPT0_CLK_SHIFT, SPEAR1340_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt0_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt0_clk", "gpt0_mux_clk", 0, + clk_register_clkdev(clk, "gpt0_mclk", NULL); + clk = clk_register_gate(NULL, "gpt0_clk", "gpt0_mclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_GPT0_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt0"); - clk = clk_register_mux(NULL, "gpt1_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt1_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_GPT1_CLK_SHIFT, SPEAR1340_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt1_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mux_clk", 0, + clk_register_clkdev(clk, "gpt1_mclk", NULL); + clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_GPT1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt1"); - clk = clk_register_mux(NULL, "gpt2_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt2_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_GPT2_CLK_SHIFT, SPEAR1340_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt2_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mux_clk", 0, + clk_register_clkdev(clk, "gpt2_mclk", NULL); + clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mclk", 0, SPEAR1340_PERIP2_CLK_ENB, SPEAR1340_GPT2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt2"); - clk = clk_register_mux(NULL, "gpt3_mux_clk", gpt_parents, + clk = clk_register_mux(NULL, "gpt3_mclk", gpt_parents, ARRAY_SIZE(gpt_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_GPT3_CLK_SHIFT, SPEAR1340_GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt3_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt3_clk", "gpt3_mux_clk", 0, + clk_register_clkdev(clk, "gpt3_mclk", NULL); + clk = clk_register_gate(NULL, "gpt3_clk", "gpt3_mclk", 0, SPEAR1340_PERIP2_CLK_ENB, SPEAR1340_GPT3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt3"); /* others */ - clk = clk_register_aux("uart0_synth_clk", "uart0_synth_gate_clk", + clk = clk_register_aux("uart0_syn_clk", "uart0_syn_gclk", "vco1div2_clk", 0, SPEAR1340_UART0_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "uart0_synth_clk", NULL); - clk_register_clkdev(clk1, "uart0_synth_gate_clk", NULL); + clk_register_clkdev(clk, "uart0_syn_clk", NULL); + clk_register_clkdev(clk1, "uart0_syn_gclk", NULL); - clk = clk_register_mux(NULL, "uart0_mux_clk", uart0_parents, + clk = clk_register_mux(NULL, "uart0_mclk", uart0_parents, ARRAY_SIZE(uart0_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_UART0_CLK_SHIFT, SPEAR1340_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart0_mux_clk", NULL); + clk_register_clkdev(clk, "uart0_mclk", NULL); - clk = clk_register_gate(NULL, "uart0_clk", "uart0_mux_clk", 0, + clk = clk_register_gate(NULL, "uart0_clk", "uart0_mclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_UART0_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "e0000000.serial"); - clk = clk_register_aux("uart1_synth_clk", "uart1_synth_gate_clk", + clk = clk_register_aux("uart1_syn_clk", "uart1_syn_gclk", "vco1div2_clk", 0, SPEAR1340_UART1_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "uart1_synth_clk", NULL); - clk_register_clkdev(clk1, "uart1_synth_gate_clk", NULL); + clk_register_clkdev(clk, "uart1_syn_clk", NULL); + clk_register_clkdev(clk1, "uart1_syn_gclk", NULL); - clk = clk_register_mux(NULL, "uart1_mux_clk", uart1_parents, + clk = clk_register_mux(NULL, "uart1_mclk", uart1_parents, ARRAY_SIZE(uart1_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_UART1_CLK_SHIFT, SPEAR1340_UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart1_mux_clk", NULL); + clk_register_clkdev(clk, "uart1_mclk", NULL); - clk = clk_register_gate(NULL, "uart1_clk", "uart1_mux_clk", 0, - SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_UART1_CLK_ENB, 0, + clk = clk_register_gate(NULL, "uart1_clk", "uart1_mclk", 0, + SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_UART1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "b4100000.serial"); - clk = clk_register_aux("sdhci_synth_clk", "sdhci_synth_gate_clk", + clk = clk_register_aux("sdhci_syn_clk", "sdhci_syn_gclk", "vco1div2_clk", 0, SPEAR1340_SDHCI_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "sdhci_synth_clk", NULL); - clk_register_clkdev(clk1, "sdhci_synth_gate_clk", NULL); + clk_register_clkdev(clk, "sdhci_syn_clk", NULL); + clk_register_clkdev(clk1, "sdhci_syn_gclk", NULL); - clk = clk_register_gate(NULL, "sdhci_clk", "sdhci_synth_gate_clk", 0, + clk = clk_register_gate(NULL, "sdhci_clk", "sdhci_syn_gclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_SDHCI_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "b3000000.sdhci"); - clk = clk_register_aux("cfxd_synth_clk", "cfxd_synth_gate_clk", - "vco1div2_clk", 0, SPEAR1340_CFXD_CLK_SYNT, NULL, - aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "cfxd_synth_clk", NULL); - clk_register_clkdev(clk1, "cfxd_synth_gate_clk", NULL); + clk = clk_register_aux("cfxd_syn_clk", "cfxd_syn_gclk", "vco1div2_clk", + 0, SPEAR1340_CFXD_CLK_SYNT, NULL, aux_rtbl, + ARRAY_SIZE(aux_rtbl), &_lock, &clk1); + clk_register_clkdev(clk, "cfxd_syn_clk", NULL); + clk_register_clkdev(clk1, "cfxd_syn_gclk", NULL); - clk = clk_register_gate(NULL, "cfxd_clk", "cfxd_synth_gate_clk", 0, + clk = clk_register_gate(NULL, "cfxd_clk", "cfxd_syn_gclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_CFXD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "b2800000.cf"); clk_register_clkdev(clk, NULL, "arasan_xd"); - clk = clk_register_aux("c3_synth_clk", "c3_synth_gate_clk", - "vco1div2_clk", 0, SPEAR1340_C3_CLK_SYNT, NULL, - aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "c3_synth_clk", NULL); - clk_register_clkdev(clk1, "c3_synth_gate_clk", NULL); + clk = clk_register_aux("c3_syn_clk", "c3_syn_gclk", "vco1div2_clk", 0, + SPEAR1340_C3_CLK_SYNT, NULL, aux_rtbl, + ARRAY_SIZE(aux_rtbl), &_lock, &clk1); + clk_register_clkdev(clk, "c3_syn_clk", NULL); + clk_register_clkdev(clk1, "c3_syn_gclk", NULL); - clk = clk_register_mux(NULL, "c3_mux_clk", c3_parents, + clk = clk_register_mux(NULL, "c3_mclk", c3_parents, ARRAY_SIZE(c3_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_C3_CLK_SHIFT, SPEAR1340_C3_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "c3_mux_clk", NULL); + clk_register_clkdev(clk, "c3_mclk", NULL); - clk = clk_register_gate(NULL, "c3_clk", "c3_mux_clk", 0, + clk = clk_register_gate(NULL, "c3_clk", "c3_mclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_C3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "c3"); /* gmac */ - clk = clk_register_mux(NULL, "gmac_phy_input_mux_clk", - gmac_phy_input_parents, + clk = clk_register_mux(NULL, "phy_input_mclk", gmac_phy_input_parents, ARRAY_SIZE(gmac_phy_input_parents), 0, SPEAR1340_GMAC_CLK_CFG, SPEAR1340_GMAC_PHY_INPUT_CLK_SHIFT, SPEAR1340_GMAC_PHY_INPUT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gmac_phy_input_mux_clk", NULL); + clk_register_clkdev(clk, "phy_input_mclk", NULL); - clk = clk_register_aux("gmac_phy_synth_clk", "gmac_phy_synth_gate_clk", - "gmac_phy_input_mux_clk", 0, SPEAR1340_GMAC_CLK_SYNT, - NULL, gmac_rtbl, ARRAY_SIZE(gmac_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "gmac_phy_synth_clk", NULL); - clk_register_clkdev(clk1, "gmac_phy_synth_gate_clk", NULL); + clk = clk_register_aux("phy_syn_clk", "phy_syn_gclk", "phy_input_mclk", + 0, SPEAR1340_GMAC_CLK_SYNT, NULL, gmac_rtbl, + ARRAY_SIZE(gmac_rtbl), &_lock, &clk1); + clk_register_clkdev(clk, "phy_syn_clk", NULL); + clk_register_clkdev(clk1, "phy_syn_gclk", NULL); - clk = clk_register_mux(NULL, "gmac_phy_mux_clk", gmac_phy_parents, + clk = clk_register_mux(NULL, "phy_mclk", gmac_phy_parents, ARRAY_SIZE(gmac_phy_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_GMAC_PHY_CLK_SHIFT, SPEAR1340_GMAC_PHY_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, NULL, "stmmacphy.0"); /* clcd */ - clk = clk_register_mux(NULL, "clcd_synth_mux_clk", clcd_synth_parents, + clk = clk_register_mux(NULL, "clcd_syn_mclk", clcd_synth_parents, ARRAY_SIZE(clcd_synth_parents), 0, SPEAR1340_CLCD_CLK_SYNT, SPEAR1340_CLCD_SYNT_CLK_SHIFT, SPEAR1340_CLCD_SYNT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "clcd_synth_mux_clk", NULL); + clk_register_clkdev(clk, "clcd_syn_mclk", NULL); - clk = clk_register_frac("clcd_synth_clk", "clcd_synth_mux_clk", 0, + clk = clk_register_frac("clcd_syn_clk", "clcd_syn_mclk", 0, SPEAR1340_CLCD_CLK_SYNT, clcd_rtbl, ARRAY_SIZE(clcd_rtbl), &_lock); - clk_register_clkdev(clk, "clcd_synth_clk", NULL); + clk_register_clkdev(clk, "clcd_syn_clk", NULL); - clk = clk_register_mux(NULL, "clcd_pixel_mux_clk", clcd_pixel_parents, + clk = clk_register_mux(NULL, "clcd_pixel_mclk", clcd_pixel_parents, ARRAY_SIZE(clcd_pixel_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_CLCD_CLK_SHIFT, SPEAR1340_CLCD_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, "clcd_pixel_clk", NULL); - clk = clk_register_gate(NULL, "clcd_clk", "clcd_pixel_mux_clk", 0, + clk = clk_register_gate(NULL, "clcd_clk", "clcd_pixel_mclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_CLCD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, "clcd_clk", NULL); /* i2s */ - clk = clk_register_mux(NULL, "i2s_src_mux_clk", i2s_src_parents, + clk = clk_register_mux(NULL, "i2s_src_mclk", i2s_src_parents, ARRAY_SIZE(i2s_src_parents), 0, SPEAR1340_I2S_CLK_CFG, SPEAR1340_I2S_SRC_CLK_SHIFT, SPEAR1340_I2S_SRC_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, "i2s_src_clk", NULL); - clk = clk_register_aux("i2s_prs1_clk", NULL, "i2s_src_mux_clk", 0, + clk = clk_register_aux("i2s_prs1_clk", NULL, "i2s_src_mclk", 0, SPEAR1340_I2S_CLK_CFG, &i2s_prs1_masks, i2s_prs1_rtbl, ARRAY_SIZE(i2s_prs1_rtbl), &_lock, NULL); clk_register_clkdev(clk, "i2s_prs1_clk", NULL); - clk = clk_register_mux(NULL, "i2s_ref_mux_clk", i2s_ref_parents, + clk = clk_register_mux(NULL, "i2s_ref_mclk", i2s_ref_parents, ARRAY_SIZE(i2s_ref_parents), 0, SPEAR1340_I2S_CLK_CFG, SPEAR1340_I2S_REF_SHIFT, SPEAR1340_I2S_REF_SEL_MASK, 0, &_lock); clk_register_clkdev(clk, "i2s_ref_clk", NULL); - clk = clk_register_gate(NULL, "i2s_ref_pad_clk", "i2s_ref_mux_clk", 0, + clk = clk_register_gate(NULL, "i2s_ref_pad_clk", "i2s_ref_mclk", 0, SPEAR1340_PERIP2_CLK_ENB, SPEAR1340_I2S_REF_PAD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, "i2s_ref_pad_clk", NULL); - clk = clk_register_aux("i2s_sclk_clk", "i2s_sclk_gate_clk", - "i2s_ref_mux_clk", 0, SPEAR1340_I2S_CLK_CFG, - &i2s_sclk_masks, i2s_sclk_rtbl, - ARRAY_SIZE(i2s_sclk_rtbl), &_lock, &clk1); + clk = clk_register_aux("i2s_sclk_clk", "i2s_sclk_gclk", "i2s_ref_mclk", + 0, SPEAR1340_I2S_CLK_CFG, &i2s_sclk_masks, + i2s_sclk_rtbl, ARRAY_SIZE(i2s_sclk_rtbl), &_lock, + &clk1); clk_register_clkdev(clk, "i2s_sclk_clk", NULL); - clk_register_clkdev(clk1, "i2s_sclk_gate_clk", NULL); + clk_register_clkdev(clk1, "i2s_sclk_gclk", NULL); /* clock derived from ahb clk */ clk = clk_register_gate(NULL, "i2c0_clk", "ahb_clk", 0, @@ -744,7 +741,7 @@ void __init spear1340_clk_init(void) clk_register_clkdev(clk, NULL, "e0280000.i2c"); clk = clk_register_gate(NULL, "i2c1_clk", "ahb_clk", 0, - SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_I2C1_CLK_ENB, 0, + SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_I2C1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "b4000000.i2c"); @@ -800,13 +797,13 @@ void __init spear1340_clk_init(void) &_lock); clk_register_clkdev(clk, "sysram1_clk", NULL); - clk = clk_register_aux("adc_synth_clk", "adc_synth_gate_clk", "ahb_clk", + clk = clk_register_aux("adc_syn_clk", "adc_syn_gclk", "ahb_clk", 0, SPEAR1340_ADC_CLK_SYNT, NULL, adc_rtbl, ARRAY_SIZE(adc_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "adc_synth_clk", NULL); - clk_register_clkdev(clk1, "adc_synth_gate_clk", NULL); + clk_register_clkdev(clk, "adc_syn_clk", NULL); + clk_register_clkdev(clk1, "adc_syn_gclk", NULL); - clk = clk_register_gate(NULL, "adc_clk", "adc_synth_gate_clk", 0, + clk = clk_register_gate(NULL, "adc_clk", "adc_syn_gclk", 0, SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_ADC_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "adc_clk"); @@ -843,39 +840,39 @@ void __init spear1340_clk_init(void) clk_register_clkdev(clk, NULL, "e0300000.kbd"); /* RAS clks */ - clk = clk_register_mux(NULL, "gen_synth0_1_mux_clk", - gen_synth0_1_parents, ARRAY_SIZE(gen_synth0_1_parents), - 0, SPEAR1340_PLL_CFG, SPEAR1340_GEN_SYNT0_1_CLK_SHIFT, + clk = clk_register_mux(NULL, "gen_syn0_1_mclk", gen_synth0_1_parents, + ARRAY_SIZE(gen_synth0_1_parents), 0, SPEAR1340_PLL_CFG, + SPEAR1340_GEN_SYNT0_1_CLK_SHIFT, SPEAR1340_GEN_SYNT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gen_synth0_1_clk", NULL); + clk_register_clkdev(clk, "gen_syn0_1_clk", NULL); - clk = clk_register_mux(NULL, "gen_synth2_3_mux_clk", - gen_synth2_3_parents, ARRAY_SIZE(gen_synth2_3_parents), - 0, SPEAR1340_PLL_CFG, SPEAR1340_GEN_SYNT2_3_CLK_SHIFT, + clk = clk_register_mux(NULL, "gen_syn2_3_mclk", gen_synth2_3_parents, + ARRAY_SIZE(gen_synth2_3_parents), 0, SPEAR1340_PLL_CFG, + SPEAR1340_GEN_SYNT2_3_CLK_SHIFT, SPEAR1340_GEN_SYNT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gen_synth2_3_clk", NULL); + clk_register_clkdev(clk, "gen_syn2_3_clk", NULL); - clk = clk_register_frac("gen_synth0_clk", "gen_synth0_1_clk", 0, + clk = clk_register_frac("gen_syn0_clk", "gen_syn0_1_clk", 0, SPEAR1340_GEN_CLK_SYNT0, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth0_clk", NULL); + clk_register_clkdev(clk, "gen_syn0_clk", NULL); - clk = clk_register_frac("gen_synth1_clk", "gen_synth0_1_clk", 0, + clk = clk_register_frac("gen_syn1_clk", "gen_syn0_1_clk", 0, SPEAR1340_GEN_CLK_SYNT1, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth1_clk", NULL); + clk_register_clkdev(clk, "gen_syn1_clk", NULL); - clk = clk_register_frac("gen_synth2_clk", "gen_synth2_3_clk", 0, + clk = clk_register_frac("gen_syn2_clk", "gen_syn2_3_clk", 0, SPEAR1340_GEN_CLK_SYNT2, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth2_clk", NULL); + clk_register_clkdev(clk, "gen_syn2_clk", NULL); - clk = clk_register_frac("gen_synth3_clk", "gen_synth2_3_clk", 0, + clk = clk_register_frac("gen_syn3_clk", "gen_syn2_3_clk", 0, SPEAR1340_GEN_CLK_SYNT3, gen_rtbl, ARRAY_SIZE(gen_rtbl), &_lock); - clk_register_clkdev(clk, "gen_synth3_clk", NULL); + clk_register_clkdev(clk, "gen_syn3_clk", NULL); - clk = clk_register_gate(NULL, "mali_clk", "gen_synth3_clk", 0, + clk = clk_register_gate(NULL, "mali_clk", "gen_syn3_clk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_MALI_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "mali"); @@ -890,74 +887,74 @@ void __init spear1340_clk_init(void) &_lock); clk_register_clkdev(clk, NULL, "spear_cec.1"); - clk = clk_register_mux(NULL, "spdif_out_mux_clk", spdif_out_parents, + clk = clk_register_mux(NULL, "spdif_out_mclk", spdif_out_parents, ARRAY_SIZE(spdif_out_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_SPDIF_OUT_CLK_SHIFT, SPEAR1340_SPDIF_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "spdif_out_mux_clk", NULL); + clk_register_clkdev(clk, "spdif_out_mclk", NULL); - clk = clk_register_gate(NULL, "spdif_out_clk", "spdif_out_mux_clk", 0, + clk = clk_register_gate(NULL, "spdif_out_clk", "spdif_out_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_SPDIF_OUT_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spdif-out"); - clk = clk_register_mux(NULL, "spdif_in_mux_clk", spdif_in_parents, + clk = clk_register_mux(NULL, "spdif_in_mclk", spdif_in_parents, ARRAY_SIZE(spdif_in_parents), 0, SPEAR1340_PERIP_CLK_CFG, SPEAR1340_SPDIF_IN_CLK_SHIFT, SPEAR1340_SPDIF_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "spdif_in_mux_clk", NULL); + clk_register_clkdev(clk, "spdif_in_mclk", NULL); - clk = clk_register_gate(NULL, "spdif_in_clk", "spdif_in_mux_clk", 0, + clk = clk_register_gate(NULL, "spdif_in_clk", "spdif_in_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_SPDIF_IN_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spdif-in"); - clk = clk_register_gate(NULL, "acp_clk", "acp_mux_clk", 0, + clk = clk_register_gate(NULL, "acp_clk", "acp_mclk", 0, SPEAR1340_PERIP2_CLK_ENB, SPEAR1340_ACP_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "acp_clk"); - clk = clk_register_gate(NULL, "plgpio_clk", "plgpio_mux_clk", 0, + clk = clk_register_gate(NULL, "plgpio_clk", "plgpio_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_PLGPIO_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "plgpio"); - clk = clk_register_gate(NULL, "video_dec_clk", "video_dec_mux_clk", 0, + clk = clk_register_gate(NULL, "video_dec_clk", "video_dec_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_VIDEO_DEC_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "video_dec"); - clk = clk_register_gate(NULL, "video_enc_clk", "video_enc_mux_clk", 0, + clk = clk_register_gate(NULL, "video_enc_clk", "video_enc_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_VIDEO_ENC_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "video_enc"); - clk = clk_register_gate(NULL, "video_in_clk", "video_in_mux_clk", 0, + clk = clk_register_gate(NULL, "video_in_clk", "video_in_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_VIDEO_IN_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spear_vip"); - clk = clk_register_gate(NULL, "cam0_clk", "cam0_mux_clk", 0, + clk = clk_register_gate(NULL, "cam0_clk", "cam0_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_CAM0_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spear_camif.0"); - clk = clk_register_gate(NULL, "cam1_clk", "cam1_mux_clk", 0, + clk = clk_register_gate(NULL, "cam1_clk", "cam1_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_CAM1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spear_camif.1"); - clk = clk_register_gate(NULL, "cam2_clk", "cam2_mux_clk", 0, + clk = clk_register_gate(NULL, "cam2_clk", "cam2_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_CAM2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spear_camif.2"); - clk = clk_register_gate(NULL, "cam3_clk", "cam3_mux_clk", 0, + clk = clk_register_gate(NULL, "cam3_clk", "cam3_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_CAM3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "spear_camif.3"); - clk = clk_register_gate(NULL, "pwm_clk", "pwm_mux_clk", 0, + clk = clk_register_gate(NULL, "pwm_clk", "pwm_mclk", 0, SPEAR1340_PERIP3_CLK_ENB, SPEAR1340_PWM_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "pwm"); diff --git a/drivers/clk/spear/spear3xx_clock.c b/drivers/clk/spear/spear3xx_clock.c index 01dd6daff2a1..c3157454bb3f 100644 --- a/drivers/clk/spear/spear3xx_clock.c +++ b/drivers/clk/spear/spear3xx_clock.c @@ -122,12 +122,12 @@ static struct gpt_rate_tbl gpt_rtbl[] = { }; /* clock parents */ -static const char *uart0_parents[] = { "pll3_48m_clk", "uart_synth_gate_clk", }; -static const char *firda_parents[] = { "pll3_48m_clk", "firda_synth_gate_clk", +static const char *uart0_parents[] = { "pll3_clk", "uart_syn_gclk", }; +static const char *firda_parents[] = { "pll3_clk", "firda_syn_gclk", }; -static const char *gpt0_parents[] = { "pll3_48m_clk", "gpt0_synth_clk", }; -static const char *gpt1_parents[] = { "pll3_48m_clk", "gpt1_synth_clk", }; -static const char *gpt2_parents[] = { "pll3_48m_clk", "gpt2_synth_clk", }; +static const char *gpt0_parents[] = { "pll3_clk", "gpt0_syn_clk", }; +static const char *gpt1_parents[] = { "pll3_clk", "gpt1_syn_clk", }; +static const char *gpt2_parents[] = { "pll3_clk", "gpt2_syn_clk", }; static const char *gen2_3_parents[] = { "pll1_clk", "pll2_clk", }; static const char *ddr_parents[] = { "ahb_clk", "ahbmult2_clk", "none", "pll2_clk", }; @@ -137,7 +137,7 @@ static void __init spear300_clk_init(void) { struct clk *clk; - clk = clk_register_fixed_factor(NULL, "clcd_clk", "ras_pll3_48m_clk", 0, + clk = clk_register_fixed_factor(NULL, "clcd_clk", "ras_pll3_clk", 0, 1, 1); clk_register_clkdev(clk, NULL, "60000000.clcd"); @@ -219,15 +219,11 @@ static void __init spear310_clk_init(void) #define SPEAR320_UARTX_PCLK_VAL_SYNTH1 0x0 #define SPEAR320_UARTX_PCLK_VAL_APB 0x1 -static const char *i2s_ref_parents[] = { "ras_pll2_clk", - "ras_gen2_synth_gate_clk", }; -static const char *sdhci_parents[] = { "ras_pll3_48m_clk", - "ras_gen3_synth_gate_clk", -}; +static const char *i2s_ref_parents[] = { "ras_pll2_clk", "ras_syn2_gclk", }; +static const char *sdhci_parents[] = { "ras_pll3_clk", "ras_syn3_gclk", }; static const char *smii0_parents[] = { "smii_125m_pad", "ras_pll2_clk", - "ras_gen0_synth_gate_clk", }; -static const char *uartx_parents[] = { "ras_gen1_synth_gate_clk", "ras_apb_clk", -}; + "ras_syn0_gclk", }; +static const char *uartx_parents[] = { "ras_syn1_gclk", "ras_apb_clk", }; static void __init spear320_clk_init(void) { @@ -237,7 +233,7 @@ static void __init spear320_clk_init(void) CLK_IS_ROOT, 125000000); clk_register_clkdev(clk, "smii_125m_pad", NULL); - clk = clk_register_fixed_factor(NULL, "clcd_clk", "ras_pll3_48m_clk", 0, + clk = clk_register_fixed_factor(NULL, "clcd_clk", "ras_pll3_clk", 0, 1, 1); clk_register_clkdev(clk, NULL, "90000000.clcd"); @@ -363,9 +359,9 @@ void __init spear3xx_clk_init(void) clk_register_clkdev(clk, NULL, "fc900000.rtc"); /* clock derived from 24 MHz osc clk */ - clk = clk_register_fixed_rate(NULL, "pll3_48m_clk", "osc_24m_clk", 0, + clk = clk_register_fixed_rate(NULL, "pll3_clk", "osc_24m_clk", 0, 48000000); - clk_register_clkdev(clk, "pll3_48m_clk", NULL); + clk_register_clkdev(clk, "pll3_clk", NULL); clk = clk_register_fixed_factor(NULL, "wdt_clk", "osc_24m_clk", 0, 1, 1); @@ -392,98 +388,98 @@ void __init spear3xx_clk_init(void) HCLK_RATIO_MASK, 0, &_lock); clk_register_clkdev(clk, "ahb_clk", NULL); - clk = clk_register_aux("uart_synth_clk", "uart_synth_gate_clk", - "pll1_clk", 0, UART_CLK_SYNT, NULL, aux_rtbl, - ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "uart_synth_clk", NULL); - clk_register_clkdev(clk1, "uart_synth_gate_clk", NULL); + clk = clk_register_aux("uart_syn_clk", "uart_syn_gclk", "pll1_clk", 0, + UART_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), + &_lock, &clk1); + clk_register_clkdev(clk, "uart_syn_clk", NULL); + clk_register_clkdev(clk1, "uart_syn_gclk", NULL); - clk = clk_register_mux(NULL, "uart0_mux_clk", uart0_parents, + clk = clk_register_mux(NULL, "uart0_mclk", uart0_parents, ARRAY_SIZE(uart0_parents), 0, PERIP_CLK_CFG, UART_CLK_SHIFT, UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart0_mux_clk", NULL); + clk_register_clkdev(clk, "uart0_mclk", NULL); - clk = clk_register_gate(NULL, "uart0", "uart0_mux_clk", 0, - PERIP1_CLK_ENB, UART_CLK_ENB, 0, &_lock); + clk = clk_register_gate(NULL, "uart0", "uart0_mclk", 0, PERIP1_CLK_ENB, + UART_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "d0000000.serial"); - clk = clk_register_aux("firda_synth_clk", "firda_synth_gate_clk", - "pll1_clk", 0, FIRDA_CLK_SYNT, NULL, aux_rtbl, - ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "firda_synth_clk", NULL); - clk_register_clkdev(clk1, "firda_synth_gate_clk", NULL); + clk = clk_register_aux("firda_syn_clk", "firda_syn_gclk", "pll1_clk", 0, + FIRDA_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), + &_lock, &clk1); + clk_register_clkdev(clk, "firda_syn_clk", NULL); + clk_register_clkdev(clk1, "firda_syn_gclk", NULL); - clk = clk_register_mux(NULL, "firda_mux_clk", firda_parents, + clk = clk_register_mux(NULL, "firda_mclk", firda_parents, ARRAY_SIZE(firda_parents), 0, PERIP_CLK_CFG, FIRDA_CLK_SHIFT, FIRDA_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "firda_mux_clk", NULL); + clk_register_clkdev(clk, "firda_mclk", NULL); - clk = clk_register_gate(NULL, "firda_clk", "firda_mux_clk", 0, + clk = clk_register_gate(NULL, "firda_clk", "firda_mclk", 0, PERIP1_CLK_ENB, FIRDA_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "firda"); /* gpt clocks */ - clk_register_gpt("gpt0_synth_clk", "pll1_clk", 0, PRSC0_CLK_CFG, - gpt_rtbl, ARRAY_SIZE(gpt_rtbl), &_lock); + clk_register_gpt("gpt0_syn_clk", "pll1_clk", 0, PRSC0_CLK_CFG, gpt_rtbl, + ARRAY_SIZE(gpt_rtbl), &_lock); clk = clk_register_mux(NULL, "gpt0_clk", gpt0_parents, ARRAY_SIZE(gpt0_parents), 0, PERIP_CLK_CFG, GPT0_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt0"); - clk_register_gpt("gpt1_synth_clk", "pll1_clk", 0, PRSC1_CLK_CFG, - gpt_rtbl, ARRAY_SIZE(gpt_rtbl), &_lock); - clk = clk_register_mux(NULL, "gpt1_mux_clk", gpt1_parents, + clk_register_gpt("gpt1_syn_clk", "pll1_clk", 0, PRSC1_CLK_CFG, gpt_rtbl, + ARRAY_SIZE(gpt_rtbl), &_lock); + clk = clk_register_mux(NULL, "gpt1_mclk", gpt1_parents, ARRAY_SIZE(gpt1_parents), 0, PERIP_CLK_CFG, GPT1_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt1_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mux_clk", 0, + clk_register_clkdev(clk, "gpt1_mclk", NULL); + clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mclk", 0, PERIP1_CLK_ENB, GPT1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt1"); - clk_register_gpt("gpt2_synth_clk", "pll1_clk", 0, PRSC2_CLK_CFG, - gpt_rtbl, ARRAY_SIZE(gpt_rtbl), &_lock); - clk = clk_register_mux(NULL, "gpt2_mux_clk", gpt2_parents, + clk_register_gpt("gpt2_syn_clk", "pll1_clk", 0, PRSC2_CLK_CFG, gpt_rtbl, + ARRAY_SIZE(gpt_rtbl), &_lock); + clk = clk_register_mux(NULL, "gpt2_mclk", gpt2_parents, ARRAY_SIZE(gpt2_parents), 0, PERIP_CLK_CFG, GPT2_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt2_mux_clk", NULL); - clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mux_clk", 0, + clk_register_clkdev(clk, "gpt2_mclk", NULL); + clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mclk", 0, PERIP1_CLK_ENB, GPT2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt2"); /* general synths clocks */ - clk = clk_register_aux("gen0_synth_clk", "gen0_synth_gate_clk", - "pll1_clk", 0, GEN0_CLK_SYNT, NULL, aux_rtbl, - ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "gen0_synth_clk", NULL); - clk_register_clkdev(clk1, "gen0_synth_gate_clk", NULL); - - clk = clk_register_aux("gen1_synth_clk", "gen1_synth_gate_clk", - "pll1_clk", 0, GEN1_CLK_SYNT, NULL, aux_rtbl, - ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "gen1_synth_clk", NULL); - clk_register_clkdev(clk1, "gen1_synth_gate_clk", NULL); - - clk = clk_register_mux(NULL, "gen2_3_parent_clk", gen2_3_parents, + clk = clk_register_aux("gen0_syn_clk", "gen0_syn_gclk", "pll1_clk", + 0, GEN0_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), + &_lock, &clk1); + clk_register_clkdev(clk, "gen0_syn_clk", NULL); + clk_register_clkdev(clk1, "gen0_syn_gclk", NULL); + + clk = clk_register_aux("gen1_syn_clk", "gen1_syn_gclk", "pll1_clk", + 0, GEN1_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), + &_lock, &clk1); + clk_register_clkdev(clk, "gen1_syn_clk", NULL); + clk_register_clkdev(clk1, "gen1_syn_gclk", NULL); + + clk = clk_register_mux(NULL, "gen2_3_par_clk", gen2_3_parents, ARRAY_SIZE(gen2_3_parents), 0, CORE_CLK_CFG, GEN_SYNTH2_3_CLK_SHIFT, GEN_SYNTH2_3_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gen2_3_parent_clk", NULL); + clk_register_clkdev(clk, "gen2_3_par_clk", NULL); - clk = clk_register_aux("gen2_synth_clk", "gen2_synth_gate_clk", - "gen2_3_parent_clk", 0, GEN2_CLK_SYNT, NULL, aux_rtbl, + clk = clk_register_aux("gen2_syn_clk", "gen2_syn_gclk", + "gen2_3_par_clk", 0, GEN2_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "gen2_synth_clk", NULL); - clk_register_clkdev(clk1, "gen2_synth_gate_clk", NULL); + clk_register_clkdev(clk, "gen2_syn_clk", NULL); + clk_register_clkdev(clk1, "gen2_syn_gclk", NULL); - clk = clk_register_aux("gen3_synth_clk", "gen3_synth_gate_clk", - "gen2_3_parent_clk", 0, GEN3_CLK_SYNT, NULL, aux_rtbl, + clk = clk_register_aux("gen3_syn_clk", "gen3_syn_gclk", + "gen2_3_par_clk", 0, GEN3_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "gen3_synth_clk", NULL); - clk_register_clkdev(clk1, "gen3_synth_gate_clk", NULL); + clk_register_clkdev(clk, "gen3_syn_clk", NULL); + clk_register_clkdev(clk1, "gen3_syn_gclk", NULL); /* clock derived from pll3 clk */ - clk = clk_register_gate(NULL, "usbh_clk", "pll3_48m_clk", 0, - PERIP1_CLK_ENB, USBH_CLK_ENB, 0, &_lock); + clk = clk_register_gate(NULL, "usbh_clk", "pll3_clk", 0, PERIP1_CLK_ENB, + USBH_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, "usbh_clk", NULL); clk = clk_register_fixed_factor(NULL, "usbh.0_clk", "usbh_clk", 0, 1, @@ -494,8 +490,8 @@ void __init spear3xx_clk_init(void) 1); clk_register_clkdev(clk, "usbh.1_clk", NULL); - clk = clk_register_gate(NULL, "usbd_clk", "pll3_48m_clk", 0, - PERIP1_CLK_ENB, USBD_CLK_ENB, 0, &_lock); + clk = clk_register_gate(NULL, "usbd_clk", "pll3_clk", 0, PERIP1_CLK_ENB, + USBD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "designware_udc"); /* clock derived from ahb clk */ @@ -579,29 +575,25 @@ void __init spear3xx_clk_init(void) RAS_CLK_ENB, RAS_PLL2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, "ras_pll2_clk", NULL); - clk = clk_register_gate(NULL, "ras_pll3_48m_clk", "pll3_48m_clk", 0, + clk = clk_register_gate(NULL, "ras_pll3_clk", "pll3_clk", 0, RAS_CLK_ENB, RAS_48M_CLK_ENB, 0, &_lock); - clk_register_clkdev(clk, "ras_pll3_48m_clk", NULL); - - clk = clk_register_gate(NULL, "ras_gen0_synth_gate_clk", - "gen0_synth_gate_clk", 0, RAS_CLK_ENB, - RAS_SYNT0_CLK_ENB, 0, &_lock); - clk_register_clkdev(clk, "ras_gen0_synth_gate_clk", NULL); - - clk = clk_register_gate(NULL, "ras_gen1_synth_gate_clk", - "gen1_synth_gate_clk", 0, RAS_CLK_ENB, - RAS_SYNT1_CLK_ENB, 0, &_lock); - clk_register_clkdev(clk, "ras_gen1_synth_gate_clk", NULL); - - clk = clk_register_gate(NULL, "ras_gen2_synth_gate_clk", - "gen2_synth_gate_clk", 0, RAS_CLK_ENB, - RAS_SYNT2_CLK_ENB, 0, &_lock); - clk_register_clkdev(clk, "ras_gen2_synth_gate_clk", NULL); - - clk = clk_register_gate(NULL, "ras_gen3_synth_gate_clk", - "gen3_synth_gate_clk", 0, RAS_CLK_ENB, - RAS_SYNT3_CLK_ENB, 0, &_lock); - clk_register_clkdev(clk, "ras_gen3_synth_gate_clk", NULL); + clk_register_clkdev(clk, "ras_pll3_clk", NULL); + + clk = clk_register_gate(NULL, "ras_syn0_gclk", "gen0_syn_gclk", 0, + RAS_CLK_ENB, RAS_SYNT0_CLK_ENB, 0, &_lock); + clk_register_clkdev(clk, "ras_syn0_gclk", NULL); + + clk = clk_register_gate(NULL, "ras_syn1_gclk", "gen1_syn_gclk", 0, + RAS_CLK_ENB, RAS_SYNT1_CLK_ENB, 0, &_lock); + clk_register_clkdev(clk, "ras_syn1_gclk", NULL); + + clk = clk_register_gate(NULL, "ras_syn2_gclk", "gen2_syn_gclk", 0, + RAS_CLK_ENB, RAS_SYNT2_CLK_ENB, 0, &_lock); + clk_register_clkdev(clk, "ras_syn2_gclk", NULL); + + clk = clk_register_gate(NULL, "ras_syn3_gclk", "gen3_syn_gclk", 0, + RAS_CLK_ENB, RAS_SYNT3_CLK_ENB, 0, &_lock); + clk_register_clkdev(clk, "ras_syn3_gclk", NULL); if (of_machine_is_compatible("st,spear300")) spear300_clk_init(); diff --git a/drivers/clk/spear/spear6xx_clock.c b/drivers/clk/spear/spear6xx_clock.c index 61026ae564ab..a98d0866f541 100644 --- a/drivers/clk/spear/spear6xx_clock.c +++ b/drivers/clk/spear/spear6xx_clock.c @@ -97,13 +97,12 @@ static struct aux_rate_tbl aux_rtbl[] = { {.xscale = 1, .yscale = 2, .eq = 1}, /* 166 MHz */ }; -static const char *clcd_parents[] = { "pll3_48m_clk", "clcd_synth_gate_clk", }; -static const char *firda_parents[] = { "pll3_48m_clk", "firda_synth_gate_clk", -}; -static const char *uart_parents[] = { "pll3_48m_clk", "uart_synth_gate_clk", }; -static const char *gpt0_1_parents[] = { "pll3_48m_clk", "gpt0_1_synth_clk", }; -static const char *gpt2_parents[] = { "pll3_48m_clk", "gpt2_synth_clk", }; -static const char *gpt3_parents[] = { "pll3_48m_clk", "gpt3_synth_clk", }; +static const char *clcd_parents[] = { "pll3_clk", "clcd_syn_gclk", }; +static const char *firda_parents[] = { "pll3_clk", "firda_syn_gclk", }; +static const char *uart_parents[] = { "pll3_clk", "uart_syn_gclk", }; +static const char *gpt0_1_parents[] = { "pll3_clk", "gpt0_1_syn_clk", }; +static const char *gpt2_parents[] = { "pll3_clk", "gpt2_syn_clk", }; +static const char *gpt3_parents[] = { "pll3_clk", "gpt3_syn_clk", }; static const char *ddr_parents[] = { "ahb_clk", "ahbmult2_clk", "none", "pll2_clk", }; @@ -136,9 +135,9 @@ void __init spear6xx_clk_init(void) clk_register_clkdev(clk, NULL, "rtc-spear"); /* clock derived from 30 MHz osc clk */ - clk = clk_register_fixed_rate(NULL, "pll3_48m_clk", "osc_24m_clk", 0, + clk = clk_register_fixed_rate(NULL, "pll3_clk", "osc_24m_clk", 0, 48000000); - clk_register_clkdev(clk, "pll3_48m_clk", NULL); + clk_register_clkdev(clk, "pll3_clk", NULL); clk = clk_register_vco_pll("vco1_clk", "pll1_clk", NULL, "osc_30m_clk", 0, PLL1_CTR, PLL1_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), @@ -146,9 +145,9 @@ void __init spear6xx_clk_init(void) clk_register_clkdev(clk, "vco1_clk", NULL); clk_register_clkdev(clk1, "pll1_clk", NULL); - clk = clk_register_vco_pll("vco2_clk", "pll2_clk", NULL, - "osc_30m_clk", 0, PLL2_CTR, PLL2_FRQ, pll_rtbl, - ARRAY_SIZE(pll_rtbl), &_lock, &clk1, NULL); + clk = clk_register_vco_pll("vco2_clk", "pll2_clk", NULL, "osc_30m_clk", + 0, PLL2_CTR, PLL2_FRQ, pll_rtbl, ARRAY_SIZE(pll_rtbl), + &_lock, &clk1, NULL); clk_register_clkdev(clk, "vco2_clk", NULL); clk_register_clkdev(clk1, "pll2_clk", NULL); @@ -165,111 +164,111 @@ void __init spear6xx_clk_init(void) HCLK_RATIO_MASK, 0, &_lock); clk_register_clkdev(clk, "ahb_clk", NULL); - clk = clk_register_aux("uart_synth_clk", "uart_synth_gate_clk", - "pll1_clk", 0, UART_CLK_SYNT, NULL, aux_rtbl, - ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "uart_synth_clk", NULL); - clk_register_clkdev(clk1, "uart_synth_gate_clk", NULL); + clk = clk_register_aux("uart_syn_clk", "uart_syn_gclk", "pll1_clk", 0, + UART_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), + &_lock, &clk1); + clk_register_clkdev(clk, "uart_syn_clk", NULL); + clk_register_clkdev(clk1, "uart_syn_gclk", NULL); - clk = clk_register_mux(NULL, "uart_mux_clk", uart_parents, + clk = clk_register_mux(NULL, "uart_mclk", uart_parents, ARRAY_SIZE(uart_parents), 0, PERIP_CLK_CFG, UART_CLK_SHIFT, UART_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "uart_mux_clk", NULL); + clk_register_clkdev(clk, "uart_mclk", NULL); - clk = clk_register_gate(NULL, "uart0", "uart_mux_clk", 0, - PERIP1_CLK_ENB, UART0_CLK_ENB, 0, &_lock); + clk = clk_register_gate(NULL, "uart0", "uart_mclk", 0, PERIP1_CLK_ENB, + UART0_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "d0000000.serial"); - clk = clk_register_gate(NULL, "uart1", "uart_mux_clk", 0, - PERIP1_CLK_ENB, UART1_CLK_ENB, 0, &_lock); + clk = clk_register_gate(NULL, "uart1", "uart_mclk", 0, PERIP1_CLK_ENB, + UART1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "d0080000.serial"); - clk = clk_register_aux("firda_synth_clk", "firda_synth_gate_clk", - "pll1_clk", 0, FIRDA_CLK_SYNT, NULL, aux_rtbl, - ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "firda_synth_clk", NULL); - clk_register_clkdev(clk1, "firda_synth_gate_clk", NULL); + clk = clk_register_aux("firda_syn_clk", "firda_syn_gclk", "pll1_clk", + 0, FIRDA_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), + &_lock, &clk1); + clk_register_clkdev(clk, "firda_syn_clk", NULL); + clk_register_clkdev(clk1, "firda_syn_gclk", NULL); - clk = clk_register_mux(NULL, "firda_mux_clk", firda_parents, + clk = clk_register_mux(NULL, "firda_mclk", firda_parents, ARRAY_SIZE(firda_parents), 0, PERIP_CLK_CFG, FIRDA_CLK_SHIFT, FIRDA_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "firda_mux_clk", NULL); + clk_register_clkdev(clk, "firda_mclk", NULL); - clk = clk_register_gate(NULL, "firda_clk", "firda_mux_clk", 0, + clk = clk_register_gate(NULL, "firda_clk", "firda_mclk", 0, PERIP1_CLK_ENB, FIRDA_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "firda"); - clk = clk_register_aux("clcd_synth_clk", "clcd_synth_gate_clk", - "pll1_clk", 0, CLCD_CLK_SYNT, NULL, aux_rtbl, - ARRAY_SIZE(aux_rtbl), &_lock, &clk1); - clk_register_clkdev(clk, "clcd_synth_clk", NULL); - clk_register_clkdev(clk1, "clcd_synth_gate_clk", NULL); + clk = clk_register_aux("clcd_syn_clk", "clcd_syn_gclk", "pll1_clk", + 0, CLCD_CLK_SYNT, NULL, aux_rtbl, ARRAY_SIZE(aux_rtbl), + &_lock, &clk1); + clk_register_clkdev(clk, "clcd_syn_clk", NULL); + clk_register_clkdev(clk1, "clcd_syn_gclk", NULL); - clk = clk_register_mux(NULL, "clcd_mux_clk", clcd_parents, + clk = clk_register_mux(NULL, "clcd_mclk", clcd_parents, ARRAY_SIZE(clcd_parents), 0, PERIP_CLK_CFG, CLCD_CLK_SHIFT, CLCD_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "clcd_mux_clk", NULL); + clk_register_clkdev(clk, "clcd_mclk", NULL); - clk = clk_register_gate(NULL, "clcd_clk", "clcd_mux_clk", 0, + clk = clk_register_gate(NULL, "clcd_clk", "clcd_mclk", 0, PERIP1_CLK_ENB, CLCD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "clcd"); /* gpt clocks */ - clk = clk_register_gpt("gpt0_1_synth_clk", "pll1_clk", 0, PRSC0_CLK_CFG, + clk = clk_register_gpt("gpt0_1_syn_clk", "pll1_clk", 0, PRSC0_CLK_CFG, gpt_rtbl, ARRAY_SIZE(gpt_rtbl), &_lock); - clk_register_clkdev(clk, "gpt0_1_synth_clk", NULL); + clk_register_clkdev(clk, "gpt0_1_syn_clk", NULL); - clk = clk_register_mux(NULL, "gpt0_mux_clk", gpt0_1_parents, + clk = clk_register_mux(NULL, "gpt0_mclk", gpt0_1_parents, ARRAY_SIZE(gpt0_1_parents), 0, PERIP_CLK_CFG, GPT0_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt0"); - clk = clk_register_mux(NULL, "gpt1_mux_clk", gpt0_1_parents, + clk = clk_register_mux(NULL, "gpt1_mclk", gpt0_1_parents, ARRAY_SIZE(gpt0_1_parents), 0, PERIP_CLK_CFG, GPT1_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt1_mux_clk", NULL); + clk_register_clkdev(clk, "gpt1_mclk", NULL); - clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mux_clk", 0, + clk = clk_register_gate(NULL, "gpt1_clk", "gpt1_mclk", 0, PERIP1_CLK_ENB, GPT1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt1"); - clk = clk_register_gpt("gpt2_synth_clk", "pll1_clk", 0, PRSC1_CLK_CFG, + clk = clk_register_gpt("gpt2_syn_clk", "pll1_clk", 0, PRSC1_CLK_CFG, gpt_rtbl, ARRAY_SIZE(gpt_rtbl), &_lock); - clk_register_clkdev(clk, "gpt2_synth_clk", NULL); + clk_register_clkdev(clk, "gpt2_syn_clk", NULL); - clk = clk_register_mux(NULL, "gpt2_mux_clk", gpt2_parents, + clk = clk_register_mux(NULL, "gpt2_mclk", gpt2_parents, ARRAY_SIZE(gpt2_parents), 0, PERIP_CLK_CFG, GPT2_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt2_mux_clk", NULL); + clk_register_clkdev(clk, "gpt2_mclk", NULL); - clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mux_clk", 0, + clk = clk_register_gate(NULL, "gpt2_clk", "gpt2_mclk", 0, PERIP1_CLK_ENB, GPT2_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt2"); - clk = clk_register_gpt("gpt3_synth_clk", "pll1_clk", 0, PRSC2_CLK_CFG, + clk = clk_register_gpt("gpt3_syn_clk", "pll1_clk", 0, PRSC2_CLK_CFG, gpt_rtbl, ARRAY_SIZE(gpt_rtbl), &_lock); - clk_register_clkdev(clk, "gpt3_synth_clk", NULL); + clk_register_clkdev(clk, "gpt3_syn_clk", NULL); - clk = clk_register_mux(NULL, "gpt3_mux_clk", gpt3_parents, + clk = clk_register_mux(NULL, "gpt3_mclk", gpt3_parents, ARRAY_SIZE(gpt3_parents), 0, PERIP_CLK_CFG, GPT3_CLK_SHIFT, GPT_CLK_MASK, 0, &_lock); - clk_register_clkdev(clk, "gpt3_mux_clk", NULL); + clk_register_clkdev(clk, "gpt3_mclk", NULL); - clk = clk_register_gate(NULL, "gpt3_clk", "gpt3_mux_clk", 0, + clk = clk_register_gate(NULL, "gpt3_clk", "gpt3_mclk", 0, PERIP1_CLK_ENB, GPT3_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "gpt3"); /* clock derived from pll3 clk */ - clk = clk_register_gate(NULL, "usbh0_clk", "pll3_48m_clk", 0, + clk = clk_register_gate(NULL, "usbh0_clk", "pll3_clk", 0, PERIP1_CLK_ENB, USBH0_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "usbh.0_clk"); - clk = clk_register_gate(NULL, "usbh1_clk", "pll3_48m_clk", 0, + clk = clk_register_gate(NULL, "usbh1_clk", "pll3_clk", 0, PERIP1_CLK_ENB, USBH1_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "usbh.1_clk"); - clk = clk_register_gate(NULL, "usbd_clk", "pll3_48m_clk", 0, - PERIP1_CLK_ENB, USBD_CLK_ENB, 0, &_lock); + clk = clk_register_gate(NULL, "usbd_clk", "pll3_clk", 0, PERIP1_CLK_ENB, + USBD_CLK_ENB, 0, &_lock); clk_register_clkdev(clk, NULL, "designware_udc"); /* clock derived from ahb clk */ @@ -278,9 +277,8 @@ void __init spear6xx_clk_init(void) clk_register_clkdev(clk, "ahbmult2_clk", NULL); clk = clk_register_mux(NULL, "ddr_clk", ddr_parents, - ARRAY_SIZE(ddr_parents), - 0, PLL_CLK_CFG, MCTR_CLK_SHIFT, MCTR_CLK_MASK, 0, - &_lock); + ARRAY_SIZE(ddr_parents), 0, PLL_CLK_CFG, MCTR_CLK_SHIFT, + MCTR_CLK_MASK, 0, &_lock); clk_register_clkdev(clk, "ddr_clk", NULL); clk = clk_register_divider(NULL, "apb_clk", "ahb_clk", diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 7f2f149ae40f..fb8a5279c5d8 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -138,7 +138,7 @@ void disable_cpufreq(void) static LIST_HEAD(cpufreq_governor_list); static DEFINE_MUTEX(cpufreq_governor_mutex); -struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu) +static struct cpufreq_policy *__cpufreq_cpu_get(unsigned int cpu, bool sysfs) { struct cpufreq_policy *data; unsigned long flags; @@ -162,7 +162,7 @@ struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu) if (!data) goto err_out_put_module; - if (!kobject_get(&data->kobj)) + if (!sysfs && !kobject_get(&data->kobj)) goto err_out_put_module; spin_unlock_irqrestore(&cpufreq_driver_lock, flags); @@ -175,16 +175,35 @@ err_out_unlock: err_out: return NULL; } + +struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu) +{ + return __cpufreq_cpu_get(cpu, false); +} EXPORT_SYMBOL_GPL(cpufreq_cpu_get); +static struct cpufreq_policy *cpufreq_cpu_get_sysfs(unsigned int cpu) +{ + return __cpufreq_cpu_get(cpu, true); +} -void cpufreq_cpu_put(struct cpufreq_policy *data) +static void __cpufreq_cpu_put(struct cpufreq_policy *data, bool sysfs) { - kobject_put(&data->kobj); + if (!sysfs) + kobject_put(&data->kobj); module_put(cpufreq_driver->owner); } + +void cpufreq_cpu_put(struct cpufreq_policy *data) +{ + __cpufreq_cpu_put(data, false); +} EXPORT_SYMBOL_GPL(cpufreq_cpu_put); +static void cpufreq_cpu_put_sysfs(struct cpufreq_policy *data) +{ + __cpufreq_cpu_put(data, true); +} /********************************************************************* * EXTERNALLY AFFECTING FREQUENCY CHANGES * @@ -617,7 +636,7 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf) struct cpufreq_policy *policy = to_policy(kobj); struct freq_attr *fattr = to_attr(attr); ssize_t ret = -EINVAL; - policy = cpufreq_cpu_get(policy->cpu); + policy = cpufreq_cpu_get_sysfs(policy->cpu); if (!policy) goto no_policy; @@ -631,7 +650,7 @@ static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf) unlock_policy_rwsem_read(policy->cpu); fail: - cpufreq_cpu_put(policy); + cpufreq_cpu_put_sysfs(policy); no_policy: return ret; } @@ -642,7 +661,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, struct cpufreq_policy *policy = to_policy(kobj); struct freq_attr *fattr = to_attr(attr); ssize_t ret = -EINVAL; - policy = cpufreq_cpu_get(policy->cpu); + policy = cpufreq_cpu_get_sysfs(policy->cpu); if (!policy) goto no_policy; @@ -656,7 +675,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr, unlock_policy_rwsem_write(policy->cpu); fail: - cpufreq_cpu_put(policy); + cpufreq_cpu_put_sysfs(policy); no_policy: return ret; } diff --git a/drivers/cpufreq/exynos-cpufreq.c b/drivers/cpufreq/exynos-cpufreq.c index b243a7ee01f6..af2d81e10f71 100644 --- a/drivers/cpufreq/exynos-cpufreq.c +++ b/drivers/cpufreq/exynos-cpufreq.c @@ -62,8 +62,18 @@ static int exynos_target(struct cpufreq_policy *policy, goto out; } - if (cpufreq_frequency_table_target(policy, freq_table, - freqs.old, relation, &old_index)) { + /* + * The policy max have been changed so that we cannot get proper + * old_index with cpufreq_frequency_table_target(). Thus, ignore + * policy and get the index from the raw freqeuncy table. + */ + for (old_index = 0; + freq_table[old_index].frequency != CPUFREQ_TABLE_END; + old_index++) + if (freq_table[old_index].frequency == freqs.old) + break; + + if (freq_table[old_index].frequency == CPUFREQ_TABLE_END) { ret = -EINVAL; goto out; } diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index d90519cec880..d6a533e68e0f 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -201,6 +201,22 @@ void cpuidle_resume_and_unlock(void) EXPORT_SYMBOL_GPL(cpuidle_resume_and_unlock); +/* Currently used in suspend/resume path to suspend cpuidle */ +void cpuidle_pause(void) +{ + mutex_lock(&cpuidle_lock); + cpuidle_uninstall_idle_handler(); + mutex_unlock(&cpuidle_lock); +} + +/* Currently used in suspend/resume path to resume cpuidle */ +void cpuidle_resume(void) +{ + mutex_lock(&cpuidle_lock); + cpuidle_install_idle_handler(); + mutex_unlock(&cpuidle_lock); +} + /** * cpuidle_wrap_enter - performs timekeeping and irqen around enter function * @dev: pointer to a valid cpuidle_device object @@ -265,7 +281,7 @@ static void poll_idle_init(struct cpuidle_driver *drv) state->power_usage = -1; state->flags = 0; state->enter = poll_idle; - state->disable = 0; + state->disabled = false; } #else static void poll_idle_init(struct cpuidle_driver *drv) {} diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index 40cd3f3024df..58bf3b1ac9c4 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -16,6 +16,7 @@ static struct cpuidle_driver *cpuidle_curr_driver; DEFINE_SPINLOCK(cpuidle_driver_lock); +int cpuidle_driver_refcount; static void __cpuidle_register_driver(struct cpuidle_driver *drv) { @@ -89,8 +90,34 @@ void cpuidle_unregister_driver(struct cpuidle_driver *drv) } spin_lock(&cpuidle_driver_lock); - cpuidle_curr_driver = NULL; + + if (!WARN_ON(cpuidle_driver_refcount > 0)) + cpuidle_curr_driver = NULL; + spin_unlock(&cpuidle_driver_lock); } EXPORT_SYMBOL_GPL(cpuidle_unregister_driver); + +struct cpuidle_driver *cpuidle_driver_ref(void) +{ + struct cpuidle_driver *drv; + + spin_lock(&cpuidle_driver_lock); + + drv = cpuidle_curr_driver; + cpuidle_driver_refcount++; + + spin_unlock(&cpuidle_driver_lock); + return drv; +} + +void cpuidle_driver_unref(void) +{ + spin_lock(&cpuidle_driver_lock); + + if (!WARN_ON(cpuidle_driver_refcount <= 0)) + cpuidle_driver_refcount--; + + spin_unlock(&cpuidle_driver_lock); +} diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 06335756ea14..5b1f2c372c1f 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -281,7 +281,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) * unless the timer is happening really really soon. */ if (data->expected_us > 5 && - drv->states[CPUIDLE_DRIVER_STATE_START].disable == 0) + !drv->states[CPUIDLE_DRIVER_STATE_START].disabled && + dev->states_usage[CPUIDLE_DRIVER_STATE_START].disable == 0) data->last_state_idx = CPUIDLE_DRIVER_STATE_START; /* @@ -290,8 +291,9 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) */ for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) { struct cpuidle_state *s = &drv->states[i]; + struct cpuidle_state_usage *su = &dev->states_usage[i]; - if (s->disable) + if (s->disabled || su->disable) continue; if (s->target_residency > data->predicted_us) continue; diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index 88032b4dc6d2..5f809e337b89 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -217,7 +217,8 @@ struct cpuidle_state_attr { struct attribute attr; ssize_t (*show)(struct cpuidle_state *, \ struct cpuidle_state_usage *, char *); - ssize_t (*store)(struct cpuidle_state *, const char *, size_t); + ssize_t (*store)(struct cpuidle_state *, \ + struct cpuidle_state_usage *, const char *, size_t); }; #define define_one_state_ro(_name, show) \ @@ -233,21 +234,22 @@ static ssize_t show_state_##_name(struct cpuidle_state *state, \ return sprintf(buf, "%u\n", state->_name);\ } -#define define_store_state_function(_name) \ +#define define_store_state_ull_function(_name) \ static ssize_t store_state_##_name(struct cpuidle_state *state, \ + struct cpuidle_state_usage *state_usage, \ const char *buf, size_t size) \ { \ - long value; \ + unsigned long long value; \ int err; \ if (!capable(CAP_SYS_ADMIN)) \ return -EPERM; \ - err = kstrtol(buf, 0, &value); \ + err = kstrtoull(buf, 0, &value); \ if (err) \ return err; \ if (value) \ - state->disable = 1; \ + state_usage->_name = 1; \ else \ - state->disable = 0; \ + state_usage->_name = 0; \ return size; \ } @@ -273,8 +275,8 @@ define_show_state_ull_function(usage) define_show_state_ull_function(time) define_show_state_str_function(name) define_show_state_str_function(desc) -define_show_state_function(disable) -define_store_state_function(disable) +define_show_state_ull_function(disable) +define_store_state_ull_function(disable) define_one_state_ro(name, show_state_name); define_one_state_ro(desc, show_state_desc); @@ -318,10 +320,11 @@ static ssize_t cpuidle_state_store(struct kobject *kobj, { int ret = -EIO; struct cpuidle_state *state = kobj_to_state(kobj); + struct cpuidle_state_usage *state_usage = kobj_to_state_usage(kobj); struct cpuidle_state_attr *cattr = attr_to_stateattr(attr); if (cattr->store) - ret = cattr->store(state, buf, size); + ret = cattr->store(state, state_usage, buf, size); return ret; } diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c index 7cac12793a4b..1c307e1b840c 100644 --- a/drivers/crypto/ux500/cryp/cryp_core.c +++ b/drivers/crypto/ux500/cryp/cryp_core.c @@ -1661,27 +1661,26 @@ static void ux500_cryp_shutdown(struct platform_device *pdev) } -static int ux500_cryp_suspend(struct platform_device *pdev, pm_message_t state) +static int ux500_cryp_suspend(struct device *dev) { int ret; + struct platform_device *pdev = to_platform_device(dev); struct cryp_device_data *device_data; struct resource *res_irq; struct cryp_ctx *temp_ctx = NULL; - dev_dbg(&pdev->dev, "[%s]", __func__); + dev_dbg(dev, "[%s]", __func__); /* Handle state? */ device_data = platform_get_drvdata(pdev); if (!device_data) { - dev_err(&pdev->dev, "[%s]: platform_get_drvdata() failed!", - __func__); + dev_err(dev, "[%s]: platform_get_drvdata() failed!", __func__); return -ENOMEM; } res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); if (!res_irq) - dev_err(&pdev->dev, "[%s]: IORESOURCE_IRQ, unavailable", - __func__); + dev_err(dev, "[%s]: IORESOURCE_IRQ, unavailable", __func__); else disable_irq(res_irq->start); @@ -1692,32 +1691,32 @@ static int ux500_cryp_suspend(struct platform_device *pdev, pm_message_t state) if (device_data->current_ctx == ++temp_ctx) { if (down_interruptible(&driver_data.device_allocation)) - dev_dbg(&pdev->dev, "[%s]: down_interruptible() " - "failed", __func__); - ret = cryp_disable_power(&pdev->dev, device_data, false); + dev_dbg(dev, "[%s]: down_interruptible() failed", + __func__); + ret = cryp_disable_power(dev, device_data, false); } else - ret = cryp_disable_power(&pdev->dev, device_data, true); + ret = cryp_disable_power(dev, device_data, true); if (ret) - dev_err(&pdev->dev, "[%s]: cryp_disable_power()", __func__); + dev_err(dev, "[%s]: cryp_disable_power()", __func__); return ret; } -static int ux500_cryp_resume(struct platform_device *pdev) +static int ux500_cryp_resume(struct device *dev) { int ret = 0; + struct platform_device *pdev = to_platform_device(dev); struct cryp_device_data *device_data; struct resource *res_irq; struct cryp_ctx *temp_ctx = NULL; - dev_dbg(&pdev->dev, "[%s]", __func__); + dev_dbg(dev, "[%s]", __func__); device_data = platform_get_drvdata(pdev); if (!device_data) { - dev_err(&pdev->dev, "[%s]: platform_get_drvdata() failed!", - __func__); + dev_err(dev, "[%s]: platform_get_drvdata() failed!", __func__); return -ENOMEM; } @@ -1730,11 +1729,10 @@ static int ux500_cryp_resume(struct platform_device *pdev) if (!device_data->current_ctx) up(&driver_data.device_allocation); else - ret = cryp_enable_power(&pdev->dev, device_data, true); + ret = cryp_enable_power(dev, device_data, true); if (ret) - dev_err(&pdev->dev, "[%s]: cryp_enable_power() failed!", - __func__); + dev_err(dev, "[%s]: cryp_enable_power() failed!", __func__); else { res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); if (res_irq) @@ -1744,15 +1742,16 @@ static int ux500_cryp_resume(struct platform_device *pdev) return ret; } +static SIMPLE_DEV_PM_OPS(ux500_cryp_pm, ux500_cryp_suspend, ux500_cryp_resume); + static struct platform_driver cryp_driver = { .probe = ux500_cryp_probe, .remove = ux500_cryp_remove, .shutdown = ux500_cryp_shutdown, - .suspend = ux500_cryp_suspend, - .resume = ux500_cryp_resume, .driver = { .owner = THIS_MODULE, .name = "cryp1" + .pm = &ux500_cryp_pm, } }; diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c index 6dbb9ec709a3..08d5032cb564 100644 --- a/drivers/crypto/ux500/hash/hash_core.c +++ b/drivers/crypto/ux500/hash/hash_core.c @@ -1894,19 +1894,17 @@ static void ux500_hash_shutdown(struct platform_device *pdev) /** * ux500_hash_suspend - Function that suspends the hash device. - * @pdev: The platform device. - * @state: - + * @dev: Device to suspend. */ -static int ux500_hash_suspend(struct platform_device *pdev, pm_message_t state) +static int ux500_hash_suspend(struct device *dev) { int ret; struct hash_device_data *device_data; struct hash_ctx *temp_ctx = NULL; - device_data = platform_get_drvdata(pdev); + device_data = dev_get_drvdata(dev); if (!device_data) { - dev_err(&pdev->dev, "[%s] platform_get_drvdata() failed!", - __func__); + dev_err(dev, "[%s] platform_get_drvdata() failed!", __func__); return -ENOMEM; } @@ -1917,33 +1915,32 @@ static int ux500_hash_suspend(struct platform_device *pdev, pm_message_t state) if (device_data->current_ctx == ++temp_ctx) { if (down_interruptible(&driver_data.device_allocation)) - dev_dbg(&pdev->dev, "[%s]: down_interruptible() " - "failed", __func__); + dev_dbg(dev, "[%s]: down_interruptible() failed", + __func__); ret = hash_disable_power(device_data, false); } else ret = hash_disable_power(device_data, true); if (ret) - dev_err(&pdev->dev, "[%s]: hash_disable_power()", __func__); + dev_err(dev, "[%s]: hash_disable_power()", __func__); return ret; } /** * ux500_hash_resume - Function that resume the hash device. - * @pdev: The platform device. + * @dev: Device to resume. */ -static int ux500_hash_resume(struct platform_device *pdev) +static int ux500_hash_resume(struct device *dev) { int ret = 0; struct hash_device_data *device_data; struct hash_ctx *temp_ctx = NULL; - device_data = platform_get_drvdata(pdev); + device_data = dev_get_drvdata(dev); if (!device_data) { - dev_err(&pdev->dev, "[%s] platform_get_drvdata() failed!", - __func__); + dev_err(dev, "[%s] platform_get_drvdata() failed!", __func__); return -ENOMEM; } @@ -1958,21 +1955,21 @@ static int ux500_hash_resume(struct platform_device *pdev) ret = hash_enable_power(device_data, true); if (ret) - dev_err(&pdev->dev, "[%s]: hash_enable_power() failed!", - __func__); + dev_err(dev, "[%s]: hash_enable_power() failed!", __func__); return ret; } +static SIMPLE_DEV_PM_OPS(ux500_hash_pm, ux500_hash_suspend, ux500_hash_resume); + static struct platform_driver hash_driver = { .probe = ux500_hash_probe, .remove = ux500_hash_remove, .shutdown = ux500_hash_shutdown, - .suspend = ux500_hash_suspend, - .resume = ux500_hash_resume, .driver = { .owner = THIS_MODULE, .name = "hash1", + .pm = &ux500_hash_pm, } }; diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index c4067d0141f7..542f0c04b695 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -136,7 +136,7 @@ config GPIO_MPC8XXX config GPIO_MSM_V1 tristate "Qualcomm MSM GPIO v1" - depends on GPIOLIB && ARCH_MSM + depends on GPIOLIB && ARCH_MSM && (ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50) help Say yes here to support the GPIO interface on ARM v6 based Qualcomm MSM chips. Most of the pins on the MSM can be diff --git a/drivers/gpio/devres.c b/drivers/gpio/devres.c index 9e9947cb86a3..1077754f8289 100644 --- a/drivers/gpio/devres.c +++ b/drivers/gpio/devres.c @@ -98,6 +98,7 @@ int devm_gpio_request_one(struct device *dev, unsigned gpio, return 0; } +EXPORT_SYMBOL(devm_gpio_request_one); /** * devm_gpio_free - free an interrupt diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c index c337143b18f8..c89c4c1e668d 100644 --- a/drivers/gpio/gpio-mxc.c +++ b/drivers/gpio/gpio-mxc.c @@ -398,10 +398,12 @@ static int __devinit mxc_gpio_probe(struct platform_device *pdev) writel(~0, port->base + GPIO_ISR); if (mxc_gpio_hwtype == IMX21_GPIO) { - /* setup one handler for all GPIO interrupts */ - if (pdev->id == 0) - irq_set_chained_handler(port->irq, - mx2_gpio_irq_handler); + /* + * Setup one handler for all GPIO interrupts. Actually setting + * the handler is needed only once, but doing it for every port + * is more robust and easier. + */ + irq_set_chained_handler(port->irq, mx2_gpio_irq_handler); } else { /* setup one handler for each entry */ irq_set_chained_handler(port->irq, mx3_gpio_irq_handler); diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index c4ed1722734c..4fbc208c32cf 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -174,12 +174,22 @@ static inline void _gpio_dbck_enable(struct gpio_bank *bank) if (bank->dbck_enable_mask && !bank->dbck_enabled) { clk_enable(bank->dbck); bank->dbck_enabled = true; + + __raw_writel(bank->dbck_enable_mask, + bank->base + bank->regs->debounce_en); } } static inline void _gpio_dbck_disable(struct gpio_bank *bank) { if (bank->dbck_enable_mask && bank->dbck_enabled) { + /* + * Disable debounce before cutting it's clock. If debounce is + * enabled but the clock is not, GPIO module seems to be unable + * to detect events and generate interrupts at least on OMAP3. + */ + __raw_writel(0, bank->base + bank->regs->debounce_en); + clk_disable(bank->dbck); bank->dbck_enabled = false; } @@ -1081,7 +1091,6 @@ static int __devinit omap_gpio_probe(struct platform_device *pdev) bank->is_mpuio = pdata->is_mpuio; bank->non_wakeup_gpios = pdata->non_wakeup_gpios; bank->loses_context = pdata->loses_context; - bank->get_context_loss_count = pdata->get_context_loss_count; bank->regs = pdata->regs; #ifdef CONFIG_OF_GPIO bank->chip.of_node = of_node_get(node); @@ -1135,6 +1144,9 @@ static int __devinit omap_gpio_probe(struct platform_device *pdev) omap_gpio_chip_init(bank); omap_gpio_show_rev(bank); + if (bank->loses_context) + bank->get_context_loss_count = pdata->get_context_loss_count; + pm_runtime_put(bank->dev); list_add_tail(&bank->node, &omap_gpio_list); diff --git a/drivers/gpio/gpio-sta2x11.c b/drivers/gpio/gpio-sta2x11.c index 38416be8ba11..6064fb376e11 100644 --- a/drivers/gpio/gpio-sta2x11.c +++ b/drivers/gpio/gpio-sta2x11.c @@ -383,8 +383,9 @@ static int __devinit gsta_probe(struct platform_device *dev) } spin_lock_init(&chip->lock); gsta_gpio_setup(chip); - for (i = 0; i < GSTA_NR_GPIO; i++) - gsta_set_config(chip, i, gpio_pdata->pinconfig[i]); + if (gpio_pdata) + for (i = 0; i < GSTA_NR_GPIO; i++) + gsta_set_config(chip, i, gpio_pdata->pinconfig[i]); /* 384 was used in previous code: be compatible for other drivers */ err = irq_alloc_descs(-1, 384, GSTA_NR_GPIO, NUMA_NO_NODE); diff --git a/drivers/gpio/gpio-tps65910.c b/drivers/gpio/gpio-tps65910.c index c1ad2884f2ed..11f29c82253c 100644 --- a/drivers/gpio/gpio-tps65910.c +++ b/drivers/gpio/gpio-tps65910.c @@ -149,6 +149,9 @@ static int __devinit tps65910_gpio_probe(struct platform_device *pdev) tps65910_gpio->gpio_chip.set = tps65910_gpio_set; tps65910_gpio->gpio_chip.get = tps65910_gpio_get; tps65910_gpio->gpio_chip.dev = &pdev->dev; +#ifdef CONFIG_OF_GPIO + tps65910_gpio->gpio_chip.of_node = tps65910->dev->of_node; +#endif if (pdata && pdata->gpio_base) tps65910_gpio->gpio_chip.base = pdata->gpio_base; else diff --git a/drivers/gpio/gpio-wm8994.c b/drivers/gpio/gpio-wm8994.c index 92ea5350dfe9..aa61ad2fcaaa 100644 --- a/drivers/gpio/gpio-wm8994.c +++ b/drivers/gpio/gpio-wm8994.c @@ -89,8 +89,11 @@ static int wm8994_gpio_direction_out(struct gpio_chip *chip, struct wm8994_gpio *wm8994_gpio = to_wm8994_gpio(chip); struct wm8994 *wm8994 = wm8994_gpio->wm8994; + if (value) + value = WM8994_GPN_LVL; + return wm8994_set_bits(wm8994, WM8994_GPIO_1 + offset, - WM8994_GPN_DIR, 0); + WM8994_GPN_DIR | WM8994_GPN_LVL, value); } static void wm8994_gpio_set(struct gpio_chip *chip, unsigned offset, int value) diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 5873e481e5d2..a8743c399e83 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -1039,6 +1039,24 @@ mode_in_range(const struct drm_display_mode *mode, struct edid *edid, return true; } +static bool valid_inferred_mode(const struct drm_connector *connector, + const struct drm_display_mode *mode) +{ + struct drm_display_mode *m; + bool ok = false; + + list_for_each_entry(m, &connector->probed_modes, head) { + if (mode->hdisplay == m->hdisplay && + mode->vdisplay == m->vdisplay && + drm_mode_vrefresh(mode) == drm_mode_vrefresh(m)) + return false; /* duplicated */ + if (mode->hdisplay <= m->hdisplay && + mode->vdisplay <= m->vdisplay) + ok = true; + } + return ok; +} + static int drm_dmt_modes_for_range(struct drm_connector *connector, struct edid *edid, struct detailed_timing *timing) @@ -1048,7 +1066,8 @@ drm_dmt_modes_for_range(struct drm_connector *connector, struct edid *edid, struct drm_device *dev = connector->dev; for (i = 0; i < drm_num_dmt_modes; i++) { - if (mode_in_range(drm_dmt_modes + i, edid, timing)) { + if (mode_in_range(drm_dmt_modes + i, edid, timing) && + valid_inferred_mode(connector, drm_dmt_modes + i)) { newmode = drm_mode_duplicate(dev, &drm_dmt_modes[i]); if (newmode) { drm_mode_probed_add(connector, newmode); @@ -1088,7 +1107,8 @@ drm_gtf_modes_for_range(struct drm_connector *connector, struct edid *edid, return modes; fixup_mode_1366x768(newmode); - if (!mode_in_range(newmode, edid, timing)) { + if (!mode_in_range(newmode, edid, timing) || + !valid_inferred_mode(connector, newmode)) { drm_mode_destroy(dev, newmode); continue; } @@ -1116,7 +1136,8 @@ drm_cvt_modes_for_range(struct drm_connector *connector, struct edid *edid, return modes; fixup_mode_1366x768(newmode); - if (!mode_in_range(newmode, edid, timing)) { + if (!mode_in_range(newmode, edid, timing) || + !valid_inferred_mode(connector, newmode)) { drm_mode_destroy(dev, newmode); continue; } diff --git a/drivers/gpu/drm/gma500/cdv_device.c b/drivers/gpu/drm/gma500/cdv_device.c index 9764045428ce..b7e7b49d8f62 100644 --- a/drivers/gpu/drm/gma500/cdv_device.c +++ b/drivers/gpu/drm/gma500/cdv_device.c @@ -78,21 +78,6 @@ static int cdv_backlight_combination_mode(struct drm_device *dev) return REG_READ(BLC_PWM_CTL2) & PWM_LEGACY_MODE; } -static int cdv_get_brightness(struct backlight_device *bd) -{ - struct drm_device *dev = bl_get_data(bd); - u32 val = REG_READ(BLC_PWM_CTL) & BACKLIGHT_DUTY_CYCLE_MASK; - - if (cdv_backlight_combination_mode(dev)) { - u8 lbpc; - - val &= ~1; - pci_read_config_byte(dev->pdev, 0xF4, &lbpc); - val *= lbpc; - } - return val; -} - static u32 cdv_get_max_backlight(struct drm_device *dev) { u32 max = REG_READ(BLC_PWM_CTL); @@ -110,6 +95,22 @@ static u32 cdv_get_max_backlight(struct drm_device *dev) return max; } +static int cdv_get_brightness(struct backlight_device *bd) +{ + struct drm_device *dev = bl_get_data(bd); + u32 val = REG_READ(BLC_PWM_CTL) & BACKLIGHT_DUTY_CYCLE_MASK; + + if (cdv_backlight_combination_mode(dev)) { + u8 lbpc; + + val &= ~1; + pci_read_config_byte(dev->pdev, 0xF4, &lbpc); + val *= lbpc; + } + return (val * 100)/cdv_get_max_backlight(dev); + +} + static int cdv_set_brightness(struct backlight_device *bd) { struct drm_device *dev = bl_get_data(bd); @@ -120,6 +121,9 @@ static int cdv_set_brightness(struct backlight_device *bd) if (level < 1) level = 1; + level *= cdv_get_max_backlight(dev); + level /= 100; + if (cdv_backlight_combination_mode(dev)) { u32 max = cdv_get_max_backlight(dev); u8 lbpc; @@ -157,7 +161,6 @@ static int cdv_backlight_init(struct drm_device *dev) cdv_backlight_device->props.brightness = cdv_get_brightness(cdv_backlight_device); - cdv_backlight_device->props.max_brightness = cdv_get_max_backlight(dev); backlight_update_status(cdv_backlight_device); dev_priv->backlight_device = cdv_backlight_device; return 0; diff --git a/drivers/gpu/drm/gma500/opregion.c b/drivers/gpu/drm/gma500/opregion.c index 4f186eca3a30..c430bd424681 100644 --- a/drivers/gpu/drm/gma500/opregion.c +++ b/drivers/gpu/drm/gma500/opregion.c @@ -144,6 +144,8 @@ struct opregion_asle { #define ASLE_CBLV_VALID (1<<31) +static struct psb_intel_opregion *system_opregion; + static u32 asle_set_backlight(struct drm_device *dev, u32 bclp) { struct drm_psb_private *dev_priv = dev->dev_private; @@ -205,7 +207,7 @@ void psb_intel_opregion_enable_asle(struct drm_device *dev) struct drm_psb_private *dev_priv = dev->dev_private; struct opregion_asle *asle = dev_priv->opregion.asle; - if (asle) { + if (asle && system_opregion ) { /* Don't do this on Medfield or other non PC like devices, they use the bit for something different altogether */ psb_enable_pipestat(dev_priv, 0, PIPE_LEGACY_BLC_EVENT_ENABLE); @@ -221,7 +223,6 @@ void psb_intel_opregion_enable_asle(struct drm_device *dev) #define ACPI_EV_LID (1<<1) #define ACPI_EV_DOCK (1<<2) -static struct psb_intel_opregion *system_opregion; static int psb_intel_opregion_video_event(struct notifier_block *nb, unsigned long val, void *data) @@ -266,9 +267,6 @@ void psb_intel_opregion_init(struct drm_device *dev) system_opregion = opregion; register_acpi_notifier(&psb_intel_opregion_notifier); } - - if (opregion->asle) - psb_intel_opregion_enable_asle(dev); } void psb_intel_opregion_fini(struct drm_device *dev) diff --git a/drivers/gpu/drm/gma500/opregion.h b/drivers/gpu/drm/gma500/opregion.h index 72dc6b921265..4a90f8b0e16c 100644 --- a/drivers/gpu/drm/gma500/opregion.h +++ b/drivers/gpu/drm/gma500/opregion.h @@ -27,6 +27,7 @@ extern void psb_intel_opregion_asle_intr(struct drm_device *dev); extern void psb_intel_opregion_init(struct drm_device *dev); extern void psb_intel_opregion_fini(struct drm_device *dev); extern int psb_intel_opregion_setup(struct drm_device *dev); +extern void psb_intel_opregion_enable_asle(struct drm_device *dev); #else @@ -46,4 +47,8 @@ extern inline int psb_intel_opregion_setup(struct drm_device *dev) { return 0; } + +extern inline void psb_intel_opregion_enable_asle(struct drm_device *dev) +{ +} #endif diff --git a/drivers/gpu/drm/gma500/psb_device.c b/drivers/gpu/drm/gma500/psb_device.c index eff039bf92d4..5971bc82b765 100644 --- a/drivers/gpu/drm/gma500/psb_device.c +++ b/drivers/gpu/drm/gma500/psb_device.c @@ -144,6 +144,10 @@ static int psb_backlight_init(struct drm_device *dev) psb_backlight_device->props.max_brightness = 100; backlight_update_status(psb_backlight_device); dev_priv->backlight_device = psb_backlight_device; + + /* This must occur after the backlight is properly initialised */ + psb_lid_timer_init(dev_priv); + return 0; } @@ -354,13 +358,6 @@ static int psb_chip_setup(struct drm_device *dev) return 0; } -/* Not exactly an erratum more an irritation */ -static void psb_chip_errata(struct drm_device *dev) -{ - struct drm_psb_private *dev_priv = dev->dev_private; - psb_lid_timer_init(dev_priv); -} - static void psb_chip_teardown(struct drm_device *dev) { struct drm_psb_private *dev_priv = dev->dev_private; @@ -379,7 +376,6 @@ const struct psb_ops psb_chip_ops = { .sgx_offset = PSB_SGX_OFFSET, .chip_setup = psb_chip_setup, .chip_teardown = psb_chip_teardown, - .errata = psb_chip_errata, .crtc_helper = &psb_intel_helper_funcs, .crtc_funcs = &psb_intel_crtc_funcs, diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index caba6e08693c..a8858a907f47 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -374,6 +374,7 @@ static int psb_driver_load(struct drm_device *dev, unsigned long chipset) if (ret) return ret; + psb_intel_opregion_enable_asle(dev); #if 0 /*enable runtime pm at last*/ pm_runtime_enable(&dev->pdev->dev); diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index f94792626b94..36822b924eb1 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -1401,6 +1401,27 @@ i915_mtrr_setup(struct drm_i915_private *dev_priv, unsigned long base, } } +static void i915_kick_out_firmware_fb(struct drm_i915_private *dev_priv) +{ + struct apertures_struct *ap; + struct pci_dev *pdev = dev_priv->dev->pdev; + bool primary; + + ap = alloc_apertures(1); + if (!ap) + return; + + ap->ranges[0].base = dev_priv->dev->agp->base; + ap->ranges[0].size = + dev_priv->mm.gtt->gtt_mappable_entries << PAGE_SHIFT; + primary = + pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW; + + remove_conflicting_framebuffers(ap, "inteldrmfb", primary); + + kfree(ap); +} + /** * i915_driver_load - setup chip and create an initial config * @dev: DRM device @@ -1446,6 +1467,15 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) goto free_priv; } + dev_priv->mm.gtt = intel_gtt_get(); + if (!dev_priv->mm.gtt) { + DRM_ERROR("Failed to initialize GTT\n"); + ret = -ENODEV; + goto put_bridge; + } + + i915_kick_out_firmware_fb(dev_priv); + pci_set_master(dev->pdev); /* overlay on gen2 is broken and can't address above 1G */ @@ -1471,13 +1501,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) goto put_bridge; } - dev_priv->mm.gtt = intel_gtt_get(); - if (!dev_priv->mm.gtt) { - DRM_ERROR("Failed to initialize GTT\n"); - ret = -ENODEV; - goto out_rmmap; - } - aperture_size = dev_priv->mm.gtt->gtt_mappable_entries << PAGE_SHIFT; dev_priv->mm.gtt_mapping = diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c index 59d44937dd9f..84b648a7ddd8 100644 --- a/drivers/gpu/drm/radeon/radeon_gart.c +++ b/drivers/gpu/drm/radeon/radeon_gart.c @@ -289,8 +289,9 @@ int radeon_vm_manager_init(struct radeon_device *rdev) rdev->vm_manager.enabled = false; /* mark first vm as always in use, it's the system one */ + /* allocate enough for 2 full VM pts */ r = radeon_sa_bo_manager_init(rdev, &rdev->vm_manager.sa_manager, - rdev->vm_manager.max_pfn * 8, + rdev->vm_manager.max_pfn * 8 * 2, RADEON_GEM_DOMAIN_VRAM); if (r) { dev_err(rdev->dev, "failed to allocate vm bo (%dKB)\n", @@ -633,7 +634,15 @@ int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm) mutex_init(&vm->mutex); INIT_LIST_HEAD(&vm->list); INIT_LIST_HEAD(&vm->va); - vm->last_pfn = 0; + /* SI requires equal sized PTs for all VMs, so always set + * last_pfn to max_pfn. cayman allows variable sized + * pts so we can grow then as needed. Once we switch + * to two level pts we can unify this again. + */ + if (rdev->family >= CHIP_TAHITI) + vm->last_pfn = rdev->vm_manager.max_pfn; + else + vm->last_pfn = 0; /* map the ib pool buffer at 0 in virtual address space, set * read only */ diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index f28bd4b7ef98..21ec9f5653ce 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -292,6 +292,7 @@ int radeon_gem_mmap_ioctl(struct drm_device *dev, void *data, int radeon_gem_busy_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) { + struct radeon_device *rdev = dev->dev_private; struct drm_radeon_gem_busy *args = data; struct drm_gem_object *gobj; struct radeon_bo *robj; @@ -317,13 +318,14 @@ int radeon_gem_busy_ioctl(struct drm_device *dev, void *data, break; } drm_gem_object_unreference_unlocked(gobj); - r = radeon_gem_handle_lockup(robj->rdev, r); + r = radeon_gem_handle_lockup(rdev, r); return r; } int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) { + struct radeon_device *rdev = dev->dev_private; struct drm_radeon_gem_wait_idle *args = data; struct drm_gem_object *gobj; struct radeon_bo *robj; @@ -336,10 +338,10 @@ int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data, robj = gem_to_radeon_bo(gobj); r = radeon_bo_wait(robj, NULL, false); /* callback hw specific functions if any */ - if (robj->rdev->asic->ioctl_wait_idle) - robj->rdev->asic->ioctl_wait_idle(robj->rdev, robj); + if (rdev->asic->ioctl_wait_idle) + robj->rdev->asic->ioctl_wait_idle(rdev, robj); drm_gem_object_unreference_unlocked(gobj); - r = radeon_gem_handle_lockup(robj->rdev, r); + r = radeon_gem_handle_lockup(rdev, r); return r; } diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index c7b61f16ecfd..0b0279291a73 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -2365,12 +2365,12 @@ int si_pcie_gart_enable(struct radeon_device *rdev) WREG32(0x15DC, 0); /* empty context1-15 */ - /* FIXME start with 1G, once using 2 level pt switch to full + /* FIXME start with 4G, once using 2 level pt switch to full * vm size space */ /* set vm size, must be a multiple of 4 */ WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0); - WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, (1 << 30) / RADEON_GPU_PAGE_SIZE); + WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn); for (i = 1; i < 16; i++) { if (i < 8) WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2), diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index bef04c192768..3fda8c87f02c 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -386,6 +386,7 @@ config HID_MULTITOUCH - Unitec Panels - XAT optical touch panels - Xiroku optical touch panels + - Zytronic touch panels If unsure, say N. diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index fa10f847f7db..585344b6d338 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -517,6 +517,12 @@ static const struct hid_device_id apple_devices[] = { .driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS), .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_ANSI), + .driver_data = APPLE_HAS_FN }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_ISO), + .driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_JIS), + .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI), .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO), diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 6ac0286b5375..4c87276c8ddb 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1503,6 +1503,9 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_ANSI) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_ISO) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_JIS) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_ANSI) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_ISO) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_JIS) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS) }, @@ -1995,6 +1998,7 @@ static const struct hid_device_id hid_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MCT) }, { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_HYBRID) }, { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_HEATCONTROL) }, + { HID_USB_DEVICE(USB_VENDOR_ID_MADCATZ, USB_DEVICE_ID_MADCATZ_BEATPAD) }, { HID_USB_DEVICE(USB_VENDOR_ID_MCC, USB_DEVICE_ID_MCC_PMD1024LS) }, { HID_USB_DEVICE(USB_VENDOR_ID_MCC, USB_DEVICE_ID_MCC_PMD1208LS) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_PICKIT1) }, @@ -2089,6 +2093,9 @@ static const struct hid_device_id hid_mouse_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_ANSI) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_ISO) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING6A_JIS) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_ANSI) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_ISO) }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7_JIS) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) }, { } diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index d1cdd2d28409..32039235cfee 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -125,6 +125,9 @@ #define USB_DEVICE_ID_APPLE_WELLSPRING6_ANSI 0x024c #define USB_DEVICE_ID_APPLE_WELLSPRING6_ISO 0x024d #define USB_DEVICE_ID_APPLE_WELLSPRING6_JIS 0x024e +#define USB_DEVICE_ID_APPLE_WELLSPRING7_ANSI 0x0262 +#define USB_DEVICE_ID_APPLE_WELLSPRING7_ISO 0x0263 +#define USB_DEVICE_ID_APPLE_WELLSPRING7_JIS 0x0264 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI 0x0239 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO 0x023a #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS 0x023b @@ -518,6 +521,9 @@ #define USB_DEVICE_ID_CRYSTALTOUCH 0x0006 #define USB_DEVICE_ID_CRYSTALTOUCH_DUAL 0x0007 +#define USB_VENDOR_ID_MADCATZ 0x0738 +#define USB_DEVICE_ID_MADCATZ_BEATPAD 0x4540 + #define USB_VENDOR_ID_MCC 0x09db #define USB_DEVICE_ID_MCC_PMD1024LS 0x0076 #define USB_DEVICE_ID_MCC_PMD1208LS 0x007a @@ -653,6 +659,9 @@ #define USB_DEVICE_ID_SAMSUNG_IR_REMOTE 0x0001 #define USB_DEVICE_ID_SAMSUNG_WIRELESS_KBD_MOUSE 0x0600 +#define USB_VENDOR_ID_SENNHEISER 0x1395 +#define USB_DEVICE_ID_SENNHEISER_BTD500USB 0x002c + #define USB_VENDOR_ID_SIGMA_MICRO 0x1c4f #define USB_DEVICE_ID_SIGMA_MICRO_KEYBOARD 0x0002 @@ -802,6 +811,9 @@ #define USB_VENDOR_ID_ZYDACRON 0x13EC #define USB_DEVICE_ID_ZYDACRON_REMOTE_CONTROL 0x0006 +#define USB_VENDOR_ID_ZYTRONIC 0x14c8 +#define USB_DEVICE_ID_ZYTRONIC_ZXY100 0x0005 + #define USB_VENDOR_ID_PRIMAX 0x0461 #define USB_DEVICE_ID_PRIMAX_KEYBOARD 0x4e05 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 132b0019365e..5301006f6c15 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -301,6 +301,9 @@ static const struct hid_device_id hid_battery_quirks[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI), HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, + USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI), + HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE }, {} }; diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 6e3332a99976..76479246d4ee 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1048,6 +1048,11 @@ static const struct hid_device_id mt_devices[] = { MT_USB_DEVICE(USB_VENDOR_ID_XIROKU, USB_DEVICE_ID_XIROKU_CSR2) }, + /* Zytronic panels */ + { .driver_data = MT_CLS_SERIAL, + MT_USB_DEVICE(USB_VENDOR_ID_ZYTRONIC, + USB_DEVICE_ID_ZYTRONIC_ZXY100) }, + /* Generic MT device */ { HID_DEVICE(HID_BUS_ANY, HID_GROUP_MULTITOUCH, HID_ANY_ID, HID_ANY_ID) }, { } diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index 0597ee604f6e..903eef3d3e10 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -76,6 +76,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_PRODIGE, USB_DEVICE_ID_PRODIGE_CORDLESS, HID_QUIRK_NOGET }, { USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_PIXART_IMAGING_INC_OPTICAL_TOUCH_SCREEN, HID_QUIRK_NOGET }, { USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3008, HID_QUIRK_NOGET }, + { USB_VENDOR_ID_SENNHEISER, USB_DEVICE_ID_SENNHEISER_BTD500USB, HID_QUIRK_NOGET }, { USB_VENDOR_ID_SUN, USB_DEVICE_ID_RARITAN_KVM_DONGLE, HID_QUIRK_NOGET }, { USB_VENDOR_ID_SYMBOL, USB_DEVICE_ID_SYMBOL_SCANNER_1, HID_QUIRK_NOGET }, { USB_VENDOR_ID_SYMBOL, USB_DEVICE_ID_SYMBOL_SCANNER_2, HID_QUIRK_NOGET }, diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c index 34ad5a27a7e9..e3fcf8146834 100644 --- a/drivers/hwmon/acpi_power_meter.c +++ b/drivers/hwmon/acpi_power_meter.c @@ -929,20 +929,25 @@ static int acpi_power_meter_remove(struct acpi_device *device, int type) return 0; } -static int acpi_power_meter_resume(struct acpi_device *device) +static int acpi_power_meter_resume(struct device *dev) { struct acpi_power_meter_resource *resource; - if (!device || !acpi_driver_data(device)) + if (!dev) + return -EINVAL; + + resource = acpi_driver_data(to_acpi_device(dev)); + if (!resource) return -EINVAL; - resource = acpi_driver_data(device); free_capabilities(resource); read_capabilities(resource); return 0; } +static SIMPLE_DEV_PM_OPS(acpi_power_meter_pm, NULL, acpi_power_meter_resume); + static struct acpi_driver acpi_power_meter_driver = { .name = "power_meter", .class = ACPI_POWER_METER_CLASS, @@ -950,9 +955,9 @@ static struct acpi_driver acpi_power_meter_driver = { .ops = { .add = acpi_power_meter_add, .remove = acpi_power_meter_remove, - .resume = acpi_power_meter_resume, .notify = acpi_power_meter_notify, }, + .drv.pm = &acpi_power_meter_pm, }; /* Module init/exit routines */ diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c index e7701d99f8e8..f1de3979181f 100644 --- a/drivers/hwmon/it87.c +++ b/drivers/hwmon/it87.c @@ -2341,7 +2341,7 @@ static void __devinit it87_init_device(struct platform_device *pdev) /* Start monitoring */ it87_write_value(data, IT87_REG_CONFIG, - (it87_read_value(data, IT87_REG_CONFIG) & 0x36) + (it87_read_value(data, IT87_REG_CONFIG) & 0x3e) | (update_vbat ? 0x41 : 0x01)); } diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index 7356b5ec8f67..f2fe8078633b 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -33,9 +33,6 @@ static bool force; module_param(force, bool, 0444); MODULE_PARM_DESC(force, "force loading on processors with erratum 319"); -/* PCI-IDs for Northbridge devices not used anywhere else */ -#define PCI_DEVICE_ID_AMD_15H_M10H_NB_F3 0x1403 - /* CPUID function 0x80000001, ebx */ #define CPUID_PKGTYPE_MASK 0xf0000000 #define CPUID_PKGTYPE_F 0x00000000 @@ -213,7 +210,7 @@ static DEFINE_PCI_DEVICE_TABLE(k10temp_id_table) = { { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_11H_NB_MISC) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) }, - { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M10H_NB_F3) }, + { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) }, {} }; MODULE_DEVICE_TABLE(pci, k10temp_id_table); diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c index 61c9cf15fa52..1201a15784c3 100644 --- a/drivers/hwspinlock/hwspinlock_core.c +++ b/drivers/hwspinlock/hwspinlock_core.c @@ -345,7 +345,7 @@ int hwspin_lock_register(struct hwspinlock_device *bank, struct device *dev, spin_lock_init(&hwlock->lock); hwlock->bank = bank; - ret = hwspin_lock_register_single(hwlock, i); + ret = hwspin_lock_register_single(hwlock, base_id + i); if (ret) goto reg_failed; } @@ -354,7 +354,7 @@ int hwspin_lock_register(struct hwspinlock_device *bank, struct device *dev, reg_failed: while (--i >= 0) - hwspin_lock_unregister_single(i); + hwspin_lock_unregister_single(base_id + i); return ret; } EXPORT_SYMBOL_GPL(hwspin_lock_register); diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index d0f59c3f87ef..fe95d5464a02 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -96,6 +96,7 @@ static const struct idle_cpu *icpu; static struct cpuidle_device __percpu *intel_idle_cpuidle_devices; static int intel_idle(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index); +static int intel_idle_cpu_init(int cpu); static struct cpuidle_state *cpuidle_state_table; @@ -302,22 +303,35 @@ static void __setup_broadcast_timer(void *arg) clockevents_notify(reason, &cpu); } -static int setup_broadcast_cpuhp_notify(struct notifier_block *n, - unsigned long action, void *hcpu) +static int cpu_hotplug_notify(struct notifier_block *n, + unsigned long action, void *hcpu) { int hotcpu = (unsigned long)hcpu; + struct cpuidle_device *dev; switch (action & 0xf) { case CPU_ONLINE: - smp_call_function_single(hotcpu, __setup_broadcast_timer, - (void *)true, 1); + + if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE) + smp_call_function_single(hotcpu, __setup_broadcast_timer, + (void *)true, 1); + + /* + * Some systems can hotplug a cpu at runtime after + * the kernel has booted, we have to initialize the + * driver in this case + */ + dev = per_cpu_ptr(intel_idle_cpuidle_devices, hotcpu); + if (!dev->registered) + intel_idle_cpu_init(hotcpu); + break; } return NOTIFY_OK; } -static struct notifier_block setup_broadcast_notifier = { - .notifier_call = setup_broadcast_cpuhp_notify, +static struct notifier_block cpu_hotplug_notifier = { + .notifier_call = cpu_hotplug_notify, }; static void auto_demotion_disable(void *dummy) @@ -405,10 +419,10 @@ static int intel_idle_probe(void) if (boot_cpu_has(X86_FEATURE_ARAT)) /* Always Reliable APIC Timer */ lapic_timer_reliable_states = LAPIC_TIMER_ALWAYS_RELIABLE; - else { + else on_each_cpu(__setup_broadcast_timer, (void *)true, 1); - register_cpu_notifier(&setup_broadcast_notifier); - } + + register_cpu_notifier(&cpu_hotplug_notifier); pr_debug(PREFIX "v" INTEL_IDLE_VERSION " model 0x%X\n", boot_cpu_data.x86_model); @@ -494,7 +508,7 @@ static int intel_idle_cpuidle_driver_init(void) * allocate, initialize, register cpuidle_devices * @cpu: cpu/core to initialize */ -int intel_idle_cpu_init(int cpu) +static int intel_idle_cpu_init(int cpu) { int cstate; struct cpuidle_device *dev; @@ -539,7 +553,6 @@ int intel_idle_cpu_init(int cpu) return 0; } -EXPORT_SYMBOL_GPL(intel_idle_cpu_init); static int __init intel_idle_init(void) { @@ -581,10 +594,10 @@ static void __exit intel_idle_exit(void) intel_idle_cpuidle_devices_uninit(); cpuidle_unregister_driver(&intel_idle_driver); - if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE) { + + if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE) on_each_cpu(__setup_broadcast_timer, (void *)false, 1); - unregister_cpu_notifier(&setup_broadcast_notifier); - } + unregister_cpu_notifier(&cpu_hotplug_notifier); return; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 5c1bc995e560..f10221f40803 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -123,7 +123,7 @@ static void ipoib_ud_skb_put_frags(struct ipoib_dev_priv *priv, skb_frag_size_set(frag, size); skb->data_len += size; - skb->truesize += size; + skb->truesize += PAGE_SIZE; } else skb_put(skb, length); @@ -156,14 +156,18 @@ static struct sk_buff *ipoib_alloc_rx_skb(struct net_device *dev, int id) struct ipoib_dev_priv *priv = netdev_priv(dev); struct sk_buff *skb; int buf_size; + int tailroom; u64 *mapping; - if (ipoib_ud_need_sg(priv->max_ib_mtu)) + if (ipoib_ud_need_sg(priv->max_ib_mtu)) { buf_size = IPOIB_UD_HEAD_SIZE; - else + tailroom = 128; /* reserve some tailroom for IP/TCP headers */ + } else { buf_size = IPOIB_UD_BUF_SIZE(priv->max_ib_mtu); + tailroom = 0; + } - skb = dev_alloc_skb(buf_size + 4); + skb = dev_alloc_skb(buf_size + tailroom + 4); if (unlikely(!skb)) return NULL; diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 5f6b7f63cdef..7a0ce8d42887 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -1377,10 +1377,14 @@ static int srpt_abort_cmd(struct srpt_send_ioctx *ioctx) break; case SRPT_STATE_NEED_DATA: /* DMA_TO_DEVICE (write) - RDMA read error. */ + + /* XXX(hch): this is a horrible layering violation.. */ spin_lock_irqsave(&ioctx->cmd.t_state_lock, flags); ioctx->cmd.transport_state |= CMD_T_LUN_STOP; + ioctx->cmd.transport_state &= ~CMD_T_ACTIVE; spin_unlock_irqrestore(&ioctx->cmd.t_state_lock, flags); - transport_generic_handle_data(&ioctx->cmd); + + complete(&ioctx->cmd.transport_lun_stop_comp); break; case SRPT_STATE_CMD_RSP_SENT: /* @@ -1463,9 +1467,10 @@ static void srpt_handle_send_comp(struct srpt_rdma_ch *ch, /** * srpt_handle_rdma_comp() - Process an IB RDMA completion notification. * - * Note: transport_generic_handle_data() is asynchronous so unmapping the - * data that has been transferred via IB RDMA must be postponed until the - * check_stop_free() callback. + * XXX: what is now target_execute_cmd used to be asynchronous, and unmapping + * the data that has been transferred via IB RDMA had to be postponed until the + * check_stop_free() callback. None of this is nessecary anymore and needs to + * be cleaned up. */ static void srpt_handle_rdma_comp(struct srpt_rdma_ch *ch, struct srpt_send_ioctx *ioctx, @@ -1477,7 +1482,7 @@ static void srpt_handle_rdma_comp(struct srpt_rdma_ch *ch, if (opcode == SRPT_RDMA_READ_LAST) { if (srpt_test_and_set_cmd_state(ioctx, SRPT_STATE_NEED_DATA, SRPT_STATE_DATA_IN)) - transport_generic_handle_data(&ioctx->cmd); + target_execute_cmd(&ioctx->cmd); else printk(KERN_ERR "%s[%d]: wrong state = %d\n", __func__, __LINE__, srpt_get_cmd_state(ioctx)); diff --git a/drivers/input/joystick/as5011.c b/drivers/input/joystick/as5011.c index 57d19d4e0a2d..c96653b58867 100644 --- a/drivers/input/joystick/as5011.c +++ b/drivers/input/joystick/as5011.c @@ -282,7 +282,8 @@ static int __devinit as5011_probe(struct i2c_client *client, error = request_threaded_irq(as5011->button_irq, NULL, as5011_button_interrupt, - IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING, + IRQF_TRIGGER_RISING | + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, "as5011_button", as5011); if (error < 0) { dev_err(&client->dev, @@ -296,7 +297,7 @@ static int __devinit as5011_probe(struct i2c_client *client, error = request_threaded_irq(as5011->axis_irq, NULL, as5011_axis_interrupt, - plat_data->axis_irqflags, + plat_data->axis_irqflags | IRQF_ONESHOT, "as5011_joystick", as5011); if (error) { dev_err(&client->dev, diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index ee16fb67b7ae..83811e45d633 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -142,6 +142,7 @@ static const struct xpad_device { { 0x0c12, 0x880a, "Pelican Eclipse PL-2023", 0, XTYPE_XBOX }, { 0x0c12, 0x8810, "Zeroplus Xbox Controller", 0, XTYPE_XBOX }, { 0x0c12, 0x9902, "HAMA VibraX - *FAULTY HARDWARE*", 0, XTYPE_XBOX }, + { 0x0d2f, 0x0002, "Andamiro Pump It Up pad", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX }, { 0x0e4c, 0x1097, "Radica Gamester Controller", 0, XTYPE_XBOX }, { 0x0e4c, 0x2390, "Radica Games Jtech Controller", 0, XTYPE_XBOX }, { 0x0e6f, 0x0003, "Logic3 Freebird wireless Controller", 0, XTYPE_XBOX }, @@ -164,6 +165,7 @@ static const struct xpad_device { { 0x1bad, 0x0003, "Harmonix Rock Band Drumkit", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 }, { 0x0f0d, 0x0016, "Hori Real Arcade Pro.EX", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, { 0x0f0d, 0x000d, "Hori Fighting Stick EX2", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, + { 0x1689, 0xfd00, "Razer Onza Tournament Edition", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 }, { 0xffff, 0xffff, "Chinese-made Xbox Controller", 0, XTYPE_XBOX }, { 0x0000, 0x0000, "Generic X-Box pad", 0, XTYPE_UNKNOWN } }; @@ -238,12 +240,14 @@ static struct usb_device_id xpad_table [] = { XPAD_XBOX360_VENDOR(0x045e), /* Microsoft X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x046d), /* Logitech X-Box 360 style controllers */ XPAD_XBOX360_VENDOR(0x0738), /* Mad Catz X-Box 360 controllers */ + { USB_DEVICE(0x0738, 0x4540) }, /* Mad Catz Beat Pad */ XPAD_XBOX360_VENDOR(0x0e6f), /* 0x0e6f X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x12ab), /* X-Box 360 dance pads */ XPAD_XBOX360_VENDOR(0x1430), /* RedOctane X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x146b), /* BigBen Interactive Controllers */ XPAD_XBOX360_VENDOR(0x1bad), /* Harminix Rock Band Guitar and Drums */ - XPAD_XBOX360_VENDOR(0x0f0d), /* Hori Controllers */ + XPAD_XBOX360_VENDOR(0x0f0d), /* Hori Controllers */ + XPAD_XBOX360_VENDOR(0x1689), /* Razer Onza */ { } }; diff --git a/drivers/input/keyboard/mcs_touchkey.c b/drivers/input/keyboard/mcs_touchkey.c index 64a0ca4c92f3..0d77f6c84950 100644 --- a/drivers/input/keyboard/mcs_touchkey.c +++ b/drivers/input/keyboard/mcs_touchkey.c @@ -178,7 +178,8 @@ static int __devinit mcs_touchkey_probe(struct i2c_client *client, } error = request_threaded_irq(client->irq, NULL, mcs_touchkey_interrupt, - IRQF_TRIGGER_FALLING, client->dev.driver->name, data); + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + client->dev.driver->name, data); if (error) { dev_err(&client->dev, "Failed to register interrupt\n"); goto err_free_mem; diff --git a/drivers/input/keyboard/mpr121_touchkey.c b/drivers/input/keyboard/mpr121_touchkey.c index caa218a51b5a..7613f1cac951 100644 --- a/drivers/input/keyboard/mpr121_touchkey.c +++ b/drivers/input/keyboard/mpr121_touchkey.c @@ -248,7 +248,7 @@ static int __devinit mpr_touchkey_probe(struct i2c_client *client, error = request_threaded_irq(client->irq, NULL, mpr_touchkey_interrupt, - IRQF_TRIGGER_FALLING, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, client->dev.driver->name, mpr121); if (error) { dev_err(&client->dev, "Failed to register interrupt\n"); diff --git a/drivers/input/keyboard/qt1070.c b/drivers/input/keyboard/qt1070.c index 0b7b2f891752..ca68f2992d72 100644 --- a/drivers/input/keyboard/qt1070.c +++ b/drivers/input/keyboard/qt1070.c @@ -201,7 +201,8 @@ static int __devinit qt1070_probe(struct i2c_client *client, msleep(QT1070_RESET_TIME); err = request_threaded_irq(client->irq, NULL, qt1070_interrupt, - IRQF_TRIGGER_NONE, client->dev.driver->name, data); + IRQF_TRIGGER_NONE | IRQF_ONESHOT, + client->dev.driver->name, data); if (err) { dev_err(&client->dev, "fail to request irq\n"); goto err_free_mem; diff --git a/drivers/input/keyboard/tca6416-keypad.c b/drivers/input/keyboard/tca6416-keypad.c index 3afea3f89718..c355cdde8d22 100644 --- a/drivers/input/keyboard/tca6416-keypad.c +++ b/drivers/input/keyboard/tca6416-keypad.c @@ -278,7 +278,8 @@ static int __devinit tca6416_keypad_probe(struct i2c_client *client, error = request_threaded_irq(chip->irqnum, NULL, tca6416_keys_isr, - IRQF_TRIGGER_FALLING, + IRQF_TRIGGER_FALLING | + IRQF_ONESHOT, "tca6416-keypad", chip); if (error) { dev_dbg(&client->dev, diff --git a/drivers/input/keyboard/tca8418_keypad.c b/drivers/input/keyboard/tca8418_keypad.c index 5f87b28b3192..893869b29ed9 100644 --- a/drivers/input/keyboard/tca8418_keypad.c +++ b/drivers/input/keyboard/tca8418_keypad.c @@ -360,7 +360,7 @@ static int __devinit tca8418_keypad_probe(struct i2c_client *client, client->irq = gpio_to_irq(client->irq); error = request_threaded_irq(client->irq, NULL, tca8418_irq_handler, - IRQF_TRIGGER_FALLING, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, client->name, keypad_data); if (error) { dev_dbg(&client->dev, diff --git a/drivers/input/keyboard/tnetv107x-keypad.c b/drivers/input/keyboard/tnetv107x-keypad.c index a4a445fb7020..4c34f21fbe2d 100644 --- a/drivers/input/keyboard/tnetv107x-keypad.c +++ b/drivers/input/keyboard/tnetv107x-keypad.c @@ -227,15 +227,15 @@ static int __devinit keypad_probe(struct platform_device *pdev) goto error_clk; } - error = request_threaded_irq(kp->irq_press, NULL, keypad_irq, 0, - dev_name(dev), kp); + error = request_threaded_irq(kp->irq_press, NULL, keypad_irq, + IRQF_ONESHOT, dev_name(dev), kp); if (error < 0) { dev_err(kp->dev, "Could not allocate keypad press key irq\n"); goto error_irq_press; } - error = request_threaded_irq(kp->irq_release, NULL, keypad_irq, 0, - dev_name(dev), kp); + error = request_threaded_irq(kp->irq_release, NULL, keypad_irq, + IRQF_ONESHOT, dev_name(dev), kp); if (error < 0) { dev_err(kp->dev, "Could not allocate keypad release key irq\n"); goto error_irq_release; diff --git a/drivers/input/misc/ad714x.c b/drivers/input/misc/ad714x.c index 0ac75bbad4d6..2e5d5e1de647 100644 --- a/drivers/input/misc/ad714x.c +++ b/drivers/input/misc/ad714x.c @@ -972,6 +972,7 @@ struct ad714x_chip *ad714x_probe(struct device *dev, u16 bus_type, int irq, struct ad714x_platform_data *plat_data = dev->platform_data; struct ad714x_chip *ad714x; void *drv_mem; + unsigned long irqflags; struct ad714x_button_drv *bt_drv; struct ad714x_slider_drv *sd_drv; @@ -1162,10 +1163,11 @@ struct ad714x_chip *ad714x_probe(struct device *dev, u16 bus_type, int irq, alloc_idx++; } + irqflags = plat_data->irqflags ?: IRQF_TRIGGER_FALLING; + irqflags |= IRQF_ONESHOT; + error = request_threaded_irq(ad714x->irq, NULL, ad714x_interrupt_thread, - plat_data->irqflags ? - plat_data->irqflags : IRQF_TRIGGER_FALLING, - "ad714x_captouch", ad714x); + irqflags, "ad714x_captouch", ad714x); if (error) { dev_err(dev, "can't allocate irq %d\n", ad714x->irq); goto err_unreg_dev; diff --git a/drivers/input/misc/dm355evm_keys.c b/drivers/input/misc/dm355evm_keys.c index 35083c6836c3..c1313d8535c3 100644 --- a/drivers/input/misc/dm355evm_keys.c +++ b/drivers/input/misc/dm355evm_keys.c @@ -213,7 +213,8 @@ static int __devinit dm355evm_keys_probe(struct platform_device *pdev) /* REVISIT: flush the event queue? */ status = request_threaded_irq(keys->irq, NULL, dm355evm_keys_irq, - IRQF_TRIGGER_FALLING, dev_name(&pdev->dev), keys); + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + dev_name(&pdev->dev), keys); if (status < 0) goto fail2; diff --git a/drivers/input/mouse/bcm5974.c b/drivers/input/mouse/bcm5974.c index 2cf681d98c0d..d528c23e194f 100644 --- a/drivers/input/mouse/bcm5974.c +++ b/drivers/input/mouse/bcm5974.c @@ -79,6 +79,10 @@ #define USB_DEVICE_ID_APPLE_WELLSPRING5A_ANSI 0x0252 #define USB_DEVICE_ID_APPLE_WELLSPRING5A_ISO 0x0253 #define USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS 0x0254 +/* MacbookPro10,1 (unibody, June 2012) */ +#define USB_DEVICE_ID_APPLE_WELLSPRING7_ANSI 0x0262 +#define USB_DEVICE_ID_APPLE_WELLSPRING7_ISO 0x0263 +#define USB_DEVICE_ID_APPLE_WELLSPRING7_JIS 0x0264 #define BCM5974_DEVICE(prod) { \ .match_flags = (USB_DEVICE_ID_MATCH_DEVICE | \ @@ -128,6 +132,10 @@ static const struct usb_device_id bcm5974_table[] = { BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING5A_ANSI), BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING5A_ISO), BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS), + /* MacbookPro10,1 */ + BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING7_ANSI), + BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING7_ISO), + BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING7_JIS), /* Terminating entry */ {} }; @@ -354,6 +362,18 @@ static const struct bcm5974_config bcm5974_config_table[] = { { DIM_X, DIM_X / SN_COORD, -4620, 5140 }, { DIM_Y, DIM_Y / SN_COORD, -150, 6600 } }, + { + USB_DEVICE_ID_APPLE_WELLSPRING7_ANSI, + USB_DEVICE_ID_APPLE_WELLSPRING7_ISO, + USB_DEVICE_ID_APPLE_WELLSPRING7_JIS, + HAS_INTEGRATED_BUTTON, + 0x84, sizeof(struct bt_data), + 0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS, + { DIM_PRESSURE, DIM_PRESSURE / SN_PRESSURE, 0, 300 }, + { DIM_WIDTH, DIM_WIDTH / SN_WIDTH, 0, 2048 }, + { DIM_X, DIM_X / SN_COORD, -4750, 5280 }, + { DIM_Y, DIM_Y / SN_COORD, -150, 6730 } + }, {} }; diff --git a/drivers/input/tablet/wacom_sys.c b/drivers/input/tablet/wacom_sys.c index cad5602d3ce4..8b31473a81fe 100644 --- a/drivers/input/tablet/wacom_sys.c +++ b/drivers/input/tablet/wacom_sys.c @@ -216,7 +216,7 @@ static void wacom_retrieve_report_data(struct usb_interface *intf, rep_data[0] = 12; result = wacom_get_report(intf, WAC_HID_FEATURE_REPORT, - rep_data[0], &rep_data, 2, + rep_data[0], rep_data, 2, WAC_MSG_RETRIES); if (result >= 0 && rep_data[1] > 2) @@ -401,7 +401,9 @@ static int wacom_parse_hid(struct usb_interface *intf, break; case HID_USAGE_CONTACTMAX: - wacom_retrieve_report_data(intf, features); + /* leave touch_max as is if predefined */ + if (!features->touch_max) + wacom_retrieve_report_data(intf, features); i++; break; } diff --git a/drivers/input/touchscreen/ad7879.c b/drivers/input/touchscreen/ad7879.c index e2482b40da51..bd4eb4277697 100644 --- a/drivers/input/touchscreen/ad7879.c +++ b/drivers/input/touchscreen/ad7879.c @@ -597,7 +597,7 @@ struct ad7879 *ad7879_probe(struct device *dev, u8 devid, unsigned int irq, AD7879_TMR(ts->pen_down_acc_interval); err = request_threaded_irq(ts->irq, NULL, ad7879_irq, - IRQF_TRIGGER_FALLING, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, dev_name(dev), ts); if (err) { dev_err(dev, "irq %d busy?\n", ts->irq); diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c index 42e645062c20..25fd0561a17d 100644 --- a/drivers/input/touchscreen/atmel_mxt_ts.c +++ b/drivers/input/touchscreen/atmel_mxt_ts.c @@ -1149,7 +1149,8 @@ static int __devinit mxt_probe(struct i2c_client *client, goto err_free_object; error = request_threaded_irq(client->irq, NULL, mxt_interrupt, - pdata->irqflags, client->dev.driver->name, data); + pdata->irqflags | IRQF_ONESHOT, + client->dev.driver->name, data); if (error) { dev_err(&client->dev, "Failed to register interrupt\n"); goto err_free_object; diff --git a/drivers/input/touchscreen/bu21013_ts.c b/drivers/input/touchscreen/bu21013_ts.c index f2d03c06c2da..5c487d23f11c 100644 --- a/drivers/input/touchscreen/bu21013_ts.c +++ b/drivers/input/touchscreen/bu21013_ts.c @@ -509,7 +509,8 @@ static int __devinit bu21013_probe(struct i2c_client *client, input_set_drvdata(in_dev, bu21013_data); error = request_threaded_irq(pdata->irq, NULL, bu21013_gpio_irq, - IRQF_TRIGGER_FALLING | IRQF_SHARED, + IRQF_TRIGGER_FALLING | IRQF_SHARED | + IRQF_ONESHOT, DRIVER_TP, bu21013_data); if (error) { dev_err(&client->dev, "request irq %d failed\n", pdata->irq); diff --git a/drivers/input/touchscreen/cy8ctmg110_ts.c b/drivers/input/touchscreen/cy8ctmg110_ts.c index 237753ad1031..464f1bf4b61d 100644 --- a/drivers/input/touchscreen/cy8ctmg110_ts.c +++ b/drivers/input/touchscreen/cy8ctmg110_ts.c @@ -251,7 +251,8 @@ static int __devinit cy8ctmg110_probe(struct i2c_client *client, } err = request_threaded_irq(client->irq, NULL, cy8ctmg110_irq_thread, - IRQF_TRIGGER_RISING, "touch_reset_key", ts); + IRQF_TRIGGER_RISING | IRQF_ONESHOT, + "touch_reset_key", ts); if (err < 0) { dev_err(&client->dev, "irq %d busy? error %d\n", client->irq, err); diff --git a/drivers/input/touchscreen/intel-mid-touch.c b/drivers/input/touchscreen/intel-mid-touch.c index 3cd7a837f82b..cf299377fc49 100644 --- a/drivers/input/touchscreen/intel-mid-touch.c +++ b/drivers/input/touchscreen/intel-mid-touch.c @@ -620,7 +620,7 @@ static int __devinit mrstouch_probe(struct platform_device *pdev) MRST_PRESSURE_MIN, MRST_PRESSURE_MAX, 0, 0); err = request_threaded_irq(tsdev->irq, NULL, mrstouch_pendet_irq, - 0, "mrstouch", tsdev); + IRQF_ONESHOT, "mrstouch", tsdev); if (err) { dev_err(tsdev->dev, "unable to allocate irq\n"); goto err_free_mem; diff --git a/drivers/input/touchscreen/pixcir_i2c_ts.c b/drivers/input/touchscreen/pixcir_i2c_ts.c index 72f6ba3a4709..953b4c105cad 100644 --- a/drivers/input/touchscreen/pixcir_i2c_ts.c +++ b/drivers/input/touchscreen/pixcir_i2c_ts.c @@ -165,7 +165,7 @@ static int __devinit pixcir_i2c_ts_probe(struct i2c_client *client, input_set_drvdata(input, tsdata); error = request_threaded_irq(client->irq, NULL, pixcir_ts_isr, - IRQF_TRIGGER_FALLING, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, client->name, tsdata); if (error) { dev_err(&client->dev, "Unable to request touchscreen IRQ.\n"); diff --git a/drivers/input/touchscreen/tnetv107x-ts.c b/drivers/input/touchscreen/tnetv107x-ts.c index 7e7488097359..368d2c6cf780 100644 --- a/drivers/input/touchscreen/tnetv107x-ts.c +++ b/drivers/input/touchscreen/tnetv107x-ts.c @@ -297,7 +297,7 @@ static int __devinit tsc_probe(struct platform_device *pdev) goto error_clk; } - error = request_threaded_irq(ts->tsc_irq, NULL, tsc_irq, 0, + error = request_threaded_irq(ts->tsc_irq, NULL, tsc_irq, IRQF_ONESHOT, dev_name(dev), ts); if (error < 0) { dev_err(ts->dev, "Could not allocate ts irq\n"); diff --git a/drivers/input/touchscreen/tsc2005.c b/drivers/input/touchscreen/tsc2005.c index b6adeaee9cc5..5ce3fa8ce646 100644 --- a/drivers/input/touchscreen/tsc2005.c +++ b/drivers/input/touchscreen/tsc2005.c @@ -650,7 +650,8 @@ static int __devinit tsc2005_probe(struct spi_device *spi) tsc2005_stop_scan(ts); error = request_threaded_irq(spi->irq, NULL, tsc2005_irq_thread, - IRQF_TRIGGER_RISING, "tsc2005", ts); + IRQF_TRIGGER_RISING | IRQF_ONESHOT, + "tsc2005", ts); if (error) { dev_err(&spi->dev, "Failed to request irq, err: %d\n", error); goto err_free_mem; diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index a2e418cba0ff..625626391f2d 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -83,6 +83,8 @@ static struct iommu_ops amd_iommu_ops; static ATOMIC_NOTIFIER_HEAD(ppr_notifier); int amd_iommu_max_glx_val = -1; +static struct dma_map_ops amd_iommu_dma_ops; + /* * general struct to manage commands send to an IOMMU */ @@ -402,7 +404,7 @@ static void amd_iommu_stats_init(void) return; de_fflush = debugfs_create_bool("fullflush", 0444, stats_dir, - (u32 *)&amd_iommu_unmap_flush); + &amd_iommu_unmap_flush); amd_iommu_stats_add(&compl_wait); amd_iommu_stats_add(&cnt_map_single); @@ -2267,6 +2269,13 @@ static int device_change_notifier(struct notifier_block *nb, list_add_tail(&dma_domain->list, &iommu_pd_list); spin_unlock_irqrestore(&iommu_pd_list_lock, flags); + dev_data = get_dev_data(dev); + + if (!dev_data->passthrough) + dev->archdata.dma_ops = &amd_iommu_dma_ops; + else + dev->archdata.dma_ops = &nommu_dma_ops; + break; case BUS_NOTIFY_DEL_DEVICE: diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 542024ba6dba..a33612f3206f 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -129,7 +129,7 @@ u16 amd_iommu_last_bdf; /* largest PCI device id we have to handle */ LIST_HEAD(amd_iommu_unity_map); /* a list of required unity mappings we find in ACPI */ -bool amd_iommu_unmap_flush; /* if true, flush on every unmap */ +u32 amd_iommu_unmap_flush; /* if true, flush on every unmap */ LIST_HEAD(amd_iommu_list); /* list of all AMD IOMMUs in the system */ @@ -1641,6 +1641,8 @@ static int __init amd_iommu_init(void) amd_iommu_init_api(); + x86_platform.iommu_shutdown = disable_iommus; + if (iommu_pass_through) goto out; @@ -1649,8 +1651,6 @@ static int __init amd_iommu_init(void) else printk(KERN_INFO "AMD-Vi: Lazy IO/TLB flushing enabled\n"); - x86_platform.iommu_shutdown = disable_iommus; - out: return ret; diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index 24355559a2ad..c1b1d489817e 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -652,7 +652,7 @@ extern unsigned long *amd_iommu_pd_alloc_bitmap; * If true, the addresses will be flushed on unmap time, not when * they are reused */ -extern bool amd_iommu_unmap_flush; +extern u32 amd_iommu_unmap_flush; /* Smallest number of PASIDs supported by any IOMMU in the system */ extern u32 amd_iommu_max_pasids; diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 3a74e4410fc0..86e2f4a62b9a 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -26,6 +26,8 @@ * These routines are used by both DMA-remapping and Interrupt-remapping */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt /* has to precede printk.h */ + #include <linux/pci.h> #include <linux/dmar.h> #include <linux/iova.h> @@ -39,8 +41,6 @@ #include <asm/irq_remapping.h> #include <asm/iommu_table.h> -#define PREFIX "DMAR: " - /* No locks are needed as DMA remapping hardware unit * list is constructed at boot time and hotplug of * these units are not supported by the architecture. @@ -83,16 +83,12 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope, * ignore it */ if (!bus) { - printk(KERN_WARNING - PREFIX "Device scope bus [%d] not found\n", - scope->bus); + pr_warn("Device scope bus [%d] not found\n", scope->bus); break; } pdev = pci_get_slot(bus, PCI_DEVFN(path->dev, path->fn)); if (!pdev) { - printk(KERN_WARNING PREFIX - "Device scope device [%04x:%02x:%02x.%02x] not found\n", - segment, bus->number, path->dev, path->fn); + /* warning will be printed below */ break; } path ++; @@ -100,9 +96,8 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope, bus = pdev->subordinate; } if (!pdev) { - printk(KERN_WARNING PREFIX - "Device scope device [%04x:%02x:%02x.%02x] not found\n", - segment, scope->bus, path->dev, path->fn); + pr_warn("Device scope device [%04x:%02x:%02x.%02x] not found\n", + segment, scope->bus, path->dev, path->fn); *dev = NULL; return 0; } @@ -110,9 +105,8 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope, pdev->subordinate) || (scope->entry_type == \ ACPI_DMAR_SCOPE_TYPE_BRIDGE && !pdev->subordinate)) { pci_dev_put(pdev); - printk(KERN_WARNING PREFIX - "Device scope type does not match for %s\n", - pci_name(pdev)); + pr_warn("Device scope type does not match for %s\n", + pci_name(pdev)); return -EINVAL; } *dev = pdev; @@ -134,8 +128,7 @@ int __init dmar_parse_dev_scope(void *start, void *end, int *cnt, scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE) (*cnt)++; else if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_IOAPIC) { - printk(KERN_WARNING PREFIX - "Unsupported device scope\n"); + pr_warn("Unsupported device scope\n"); } start += scope->length; } @@ -261,25 +254,23 @@ dmar_table_print_dmar_entry(struct acpi_dmar_header *header) case ACPI_DMAR_TYPE_HARDWARE_UNIT: drhd = container_of(header, struct acpi_dmar_hardware_unit, header); - printk (KERN_INFO PREFIX - "DRHD base: %#016Lx flags: %#x\n", + pr_info("DRHD base: %#016Lx flags: %#x\n", (unsigned long long)drhd->address, drhd->flags); break; case ACPI_DMAR_TYPE_RESERVED_MEMORY: rmrr = container_of(header, struct acpi_dmar_reserved_memory, header); - printk (KERN_INFO PREFIX - "RMRR base: %#016Lx end: %#016Lx\n", + pr_info("RMRR base: %#016Lx end: %#016Lx\n", (unsigned long long)rmrr->base_address, (unsigned long long)rmrr->end_address); break; case ACPI_DMAR_TYPE_ATSR: atsr = container_of(header, struct acpi_dmar_atsr, header); - printk(KERN_INFO PREFIX "ATSR flags: %#x\n", atsr->flags); + pr_info("ATSR flags: %#x\n", atsr->flags); break; case ACPI_DMAR_HARDWARE_AFFINITY: rhsa = container_of(header, struct acpi_dmar_rhsa, header); - printk(KERN_INFO PREFIX "RHSA base: %#016Lx proximity domain: %#x\n", + pr_info("RHSA base: %#016Lx proximity domain: %#x\n", (unsigned long long)rhsa->base_address, rhsa->proximity_domain); break; @@ -299,7 +290,7 @@ static int __init dmar_table_detect(void) &dmar_tbl_size); if (ACPI_SUCCESS(status) && !dmar_tbl) { - printk (KERN_WARNING PREFIX "Unable to map DMAR\n"); + pr_warn("Unable to map DMAR\n"); status = AE_NOT_FOUND; } @@ -333,20 +324,18 @@ parse_dmar_table(void) return -ENODEV; if (dmar->width < PAGE_SHIFT - 1) { - printk(KERN_WARNING PREFIX "Invalid DMAR haw\n"); + pr_warn("Invalid DMAR haw\n"); return -EINVAL; } - printk (KERN_INFO PREFIX "Host address width %d\n", - dmar->width + 1); + pr_info("Host address width %d\n", dmar->width + 1); entry_header = (struct acpi_dmar_header *)(dmar + 1); while (((unsigned long)entry_header) < (((unsigned long)dmar) + dmar_tbl->length)) { /* Avoid looping forever on bad ACPI tables */ if (entry_header->length == 0) { - printk(KERN_WARNING PREFIX - "Invalid 0-length structure\n"); + pr_warn("Invalid 0-length structure\n"); ret = -EINVAL; break; } @@ -369,8 +358,7 @@ parse_dmar_table(void) #endif break; default: - printk(KERN_WARNING PREFIX - "Unknown DMAR structure type %d\n", + pr_warn("Unknown DMAR structure type %d\n", entry_header->type); ret = 0; /* for forward compatibility */ break; @@ -469,12 +457,12 @@ int __init dmar_table_init(void) ret = parse_dmar_table(); if (ret) { if (ret != -ENODEV) - printk(KERN_INFO PREFIX "parse DMAR table failure.\n"); + pr_info("parse DMAR table failure.\n"); return ret; } if (list_empty(&dmar_drhd_units)) { - printk(KERN_INFO PREFIX "No DMAR devices found\n"); + pr_info("No DMAR devices found\n"); return -ENODEV; } @@ -506,8 +494,7 @@ int __init check_zero_address(void) (((unsigned long)dmar) + dmar_tbl->length)) { /* Avoid looping forever on bad ACPI tables */ if (entry_header->length == 0) { - printk(KERN_WARNING PREFIX - "Invalid 0-length structure\n"); + pr_warn("Invalid 0-length structure\n"); return 0; } @@ -558,8 +545,7 @@ int __init detect_intel_iommu(void) if (ret && irq_remapping_enabled && cpu_has_x2apic && dmar->flags & 0x1) - printk(KERN_INFO - "Queued invalidation will be enabled to support x2apic and Intr-remapping.\n"); + pr_info("Queued invalidation will be enabled to support x2apic and Intr-remapping.\n"); if (ret && !no_iommu && !iommu_detected && !dmar_disabled) { iommu_detected = 1; @@ -579,14 +565,89 @@ int __init detect_intel_iommu(void) } +static void unmap_iommu(struct intel_iommu *iommu) +{ + iounmap(iommu->reg); + release_mem_region(iommu->reg_phys, iommu->reg_size); +} + +/** + * map_iommu: map the iommu's registers + * @iommu: the iommu to map + * @phys_addr: the physical address of the base resgister + * + * Memory map the iommu's registers. Start w/ a single page, and + * possibly expand if that turns out to be insufficent. + */ +static int map_iommu(struct intel_iommu *iommu, u64 phys_addr) +{ + int map_size, err=0; + + iommu->reg_phys = phys_addr; + iommu->reg_size = VTD_PAGE_SIZE; + + if (!request_mem_region(iommu->reg_phys, iommu->reg_size, iommu->name)) { + pr_err("IOMMU: can't reserve memory\n"); + err = -EBUSY; + goto out; + } + + iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size); + if (!iommu->reg) { + pr_err("IOMMU: can't map the region\n"); + err = -ENOMEM; + goto release; + } + + iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG); + iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG); + + if (iommu->cap == (uint64_t)-1 && iommu->ecap == (uint64_t)-1) { + err = -EINVAL; + warn_invalid_dmar(phys_addr, " returns all ones"); + goto unmap; + } + + /* the registers might be more than one page */ + map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap), + cap_max_fault_reg_offset(iommu->cap)); + map_size = VTD_PAGE_ALIGN(map_size); + if (map_size > iommu->reg_size) { + iounmap(iommu->reg); + release_mem_region(iommu->reg_phys, iommu->reg_size); + iommu->reg_size = map_size; + if (!request_mem_region(iommu->reg_phys, iommu->reg_size, + iommu->name)) { + pr_err("IOMMU: can't reserve memory\n"); + err = -EBUSY; + goto out; + } + iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size); + if (!iommu->reg) { + pr_err("IOMMU: can't map the region\n"); + err = -ENOMEM; + goto release; + } + } + err = 0; + goto out; + +unmap: + iounmap(iommu->reg); +release: + release_mem_region(iommu->reg_phys, iommu->reg_size); +out: + return err; +} + int alloc_iommu(struct dmar_drhd_unit *drhd) { struct intel_iommu *iommu; - int map_size; u32 ver; static int iommu_allocated = 0; int agaw = 0; int msagaw = 0; + int err; if (!drhd->reg_base_addr) { warn_invalid_dmar(0, ""); @@ -600,30 +661,22 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) iommu->seq_id = iommu_allocated++; sprintf (iommu->name, "dmar%d", iommu->seq_id); - iommu->reg = ioremap(drhd->reg_base_addr, VTD_PAGE_SIZE); - if (!iommu->reg) { - printk(KERN_ERR "IOMMU: can't map the region\n"); + err = map_iommu(iommu, drhd->reg_base_addr); + if (err) { + pr_err("IOMMU: failed to map %s\n", iommu->name); goto error; } - iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG); - iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG); - - if (iommu->cap == (uint64_t)-1 && iommu->ecap == (uint64_t)-1) { - warn_invalid_dmar(drhd->reg_base_addr, " returns all ones"); - goto err_unmap; - } + err = -EINVAL; agaw = iommu_calculate_agaw(iommu); if (agaw < 0) { - printk(KERN_ERR - "Cannot get a valid agaw for iommu (seq_id = %d)\n", - iommu->seq_id); + pr_err("Cannot get a valid agaw for iommu (seq_id = %d)\n", + iommu->seq_id); goto err_unmap; } msagaw = iommu_calculate_max_sagaw(iommu); if (msagaw < 0) { - printk(KERN_ERR - "Cannot get a valid max agaw for iommu (seq_id = %d)\n", + pr_err("Cannot get a valid max agaw for iommu (seq_id = %d)\n", iommu->seq_id); goto err_unmap; } @@ -632,19 +685,6 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) iommu->node = -1; - /* the registers might be more than one page */ - map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap), - cap_max_fault_reg_offset(iommu->cap)); - map_size = VTD_PAGE_ALIGN(map_size); - if (map_size > VTD_PAGE_SIZE) { - iounmap(iommu->reg); - iommu->reg = ioremap(drhd->reg_base_addr, map_size); - if (!iommu->reg) { - printk(KERN_ERR "IOMMU: can't map the region\n"); - goto error; - } - } - ver = readl(iommu->reg + DMAR_VER_REG); pr_info("IOMMU %d: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n", iommu->seq_id, @@ -659,10 +699,10 @@ int alloc_iommu(struct dmar_drhd_unit *drhd) return 0; err_unmap: - iounmap(iommu->reg); + unmap_iommu(iommu); error: kfree(iommu); - return -1; + return err; } void free_iommu(struct intel_iommu *iommu) @@ -673,7 +713,8 @@ void free_iommu(struct intel_iommu *iommu) free_dmar_iommu(iommu); if (iommu->reg) - iounmap(iommu->reg); + unmap_iommu(iommu); + kfree(iommu); } @@ -710,7 +751,7 @@ static int qi_check_fault(struct intel_iommu *iommu, int index) if (fault & DMA_FSTS_IQE) { head = readl(iommu->reg + DMAR_IQH_REG); if ((head >> DMAR_IQ_SHIFT) == index) { - printk(KERN_ERR "VT-d detected invalid descriptor: " + pr_err("VT-d detected invalid descriptor: " "low=%llx, high=%llx\n", (unsigned long long)qi->desc[index].low, (unsigned long long)qi->desc[index].high); @@ -1129,15 +1170,14 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type, reason = dmar_get_fault_reason(fault_reason, &fault_type); if (fault_type == INTR_REMAP) - printk(KERN_ERR "INTR-REMAP: Request device [[%02x:%02x.%d] " + pr_err("INTR-REMAP: Request device [[%02x:%02x.%d] " "fault index %llx\n" "INTR-REMAP:[fault reason %02d] %s\n", (source_id >> 8), PCI_SLOT(source_id & 0xFF), PCI_FUNC(source_id & 0xFF), addr >> 48, fault_reason, reason); else - printk(KERN_ERR - "DMAR:[%s] Request device [%02x:%02x.%d] " + pr_err("DMAR:[%s] Request device [%02x:%02x.%d] " "fault addr %llx \n" "DMAR:[fault reason %02d] %s\n", (type ? "DMA Read" : "DMA Write"), @@ -1157,8 +1197,7 @@ irqreturn_t dmar_fault(int irq, void *dev_id) raw_spin_lock_irqsave(&iommu->register_lock, flag); fault_status = readl(iommu->reg + DMAR_FSTS_REG); if (fault_status) - printk(KERN_ERR "DRHD: handling fault status reg %x\n", - fault_status); + pr_err("DRHD: handling fault status reg %x\n", fault_status); /* TBD: ignore advanced fault log currently */ if (!(fault_status & DMA_FSTS_PPF)) @@ -1224,7 +1263,7 @@ int dmar_set_interrupt(struct intel_iommu *iommu) irq = create_irq(); if (!irq) { - printk(KERN_ERR "IOMMU: no free vectors\n"); + pr_err("IOMMU: no free vectors\n"); return -EINVAL; } @@ -1241,7 +1280,7 @@ int dmar_set_interrupt(struct intel_iommu *iommu) ret = request_irq(irq, dmar_fault, IRQF_NO_THREAD, iommu->name, iommu); if (ret) - printk(KERN_ERR "IOMMU: can't request irq\n"); + pr_err("IOMMU: can't request irq\n"); return ret; } @@ -1258,8 +1297,7 @@ int __init enable_drhd_fault_handling(void) ret = dmar_set_interrupt(iommu); if (ret) { - printk(KERN_ERR "DRHD %Lx: failed to enable fault, " - " interrupt, ret %d\n", + pr_err("DRHD %Lx: failed to enable fault, interrupt, ret %d\n", (unsigned long long)drhd->reg_base_addr, ret); return -1; } diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 6d347064b8b0..e0b18f3ae9a8 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -902,7 +902,6 @@ static int intel_setup_ioapic_entry(int irq, return 0; } -#ifdef CONFIG_SMP /* * Migrate the IO-APIC irq in the presence of intr-remapping. * @@ -924,6 +923,10 @@ intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, struct irq_cfg *cfg = data->chip_data; unsigned int dest, irq = data->irq; struct irte irte; + int err; + + if (!config_enabled(CONFIG_SMP)) + return -EINVAL; if (!cpumask_intersects(mask, cpu_online_mask)) return -EINVAL; @@ -931,10 +934,16 @@ intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, if (get_irte(irq, &irte)) return -EBUSY; - if (assign_irq_vector(irq, cfg, mask)) - return -EBUSY; + err = assign_irq_vector(irq, cfg, mask); + if (err) + return err; - dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask); + err = apic->cpu_mask_to_apicid_and(cfg->domain, mask, &dest); + if (err) { + if (assign_irq_vector(irq, cfg, data->affinity)) + pr_err("Failed to recover vector for irq %d\n", irq); + return err; + } irte.vector = cfg->vector; irte.dest_id = IRTE_DEST(dest); @@ -956,7 +965,6 @@ intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, cpumask_copy(data->affinity, mask); return 0; } -#endif static void intel_compose_msi_msg(struct pci_dev *pdev, unsigned int irq, unsigned int dest, @@ -1058,9 +1066,7 @@ struct irq_remap_ops intel_irq_remap_ops = { .reenable = reenable_irq_remapping, .enable_faulting = enable_drhd_fault_handling, .setup_ioapic_entry = intel_setup_ioapic_entry, -#ifdef CONFIG_SMP .set_affinity = intel_ioapic_set_affinity, -#endif .free_irq = free_irte, .compose_msi_msg = intel_compose_msi_msg, .msi_alloc_irq = intel_msi_alloc_irq, diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c index 40cda8e98d87..1d29b1c66e72 100644 --- a/drivers/iommu/irq_remapping.c +++ b/drivers/iommu/irq_remapping.c @@ -111,16 +111,15 @@ int setup_ioapic_remapped_entry(int irq, vector, attr); } -#ifdef CONFIG_SMP int set_remapped_irq_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { - if (!remap_ops || !remap_ops->set_affinity) + if (!config_enabled(CONFIG_SMP) || !remap_ops || + !remap_ops->set_affinity) return 0; return remap_ops->set_affinity(data, mask, force); } -#endif void free_remapped_irq(int irq) { diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h index be9d72950c51..b12974cc1dfe 100644 --- a/drivers/iommu/irq_remapping.h +++ b/drivers/iommu/irq_remapping.h @@ -59,11 +59,9 @@ struct irq_remap_ops { unsigned int, int, struct io_apic_irq_attr *); -#ifdef CONFIG_SMP /* Set the CPU affinity of a remapped interrupt */ int (*set_affinity)(struct irq_data *data, const struct cpumask *mask, bool force); -#endif /* Free an IRQ */ int (*free_irq)(int); diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index ecd679043d77..3f3d09d560ea 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -550,13 +550,13 @@ static int alloc_pdir(struct smmu_as *as) return 0; as->pte_count = devm_kzalloc(smmu->dev, - sizeof(as->pte_count[0]) * SMMU_PDIR_COUNT, GFP_KERNEL); + sizeof(as->pte_count[0]) * SMMU_PDIR_COUNT, GFP_ATOMIC); if (!as->pte_count) { dev_err(smmu->dev, "failed to allocate smmu_device PTE cunters\n"); return -ENOMEM; } - as->pdir_page = alloc_page(GFP_KERNEL | __GFP_DMA); + as->pdir_page = alloc_page(GFP_ATOMIC | __GFP_DMA); if (!as->pdir_page) { dev_err(smmu->dev, "failed to allocate smmu_device page directory\n"); diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c index 1a0ae4445ff2..5f21f629b7ae 100644 --- a/drivers/isdn/mISDN/stack.c +++ b/drivers/isdn/mISDN/stack.c @@ -135,8 +135,8 @@ send_layer2(struct mISDNstack *st, struct sk_buff *skb) skb = NULL; else if (*debug & DEBUG_SEND_ERR) printk(KERN_DEBUG - "%s ch%d mgr prim(%x) addr(%x) err %d\n", - __func__, ch->nr, hh->prim, ch->addr, ret); + "%s mgr prim(%x) err %d\n", + __func__, hh->prim, ret); } out: mutex_unlock(&st->lmutex); diff --git a/drivers/leds/ledtrig-heartbeat.c b/drivers/leds/ledtrig-heartbeat.c index 41dc76db4311..a019fbb70880 100644 --- a/drivers/leds/ledtrig-heartbeat.c +++ b/drivers/leds/ledtrig-heartbeat.c @@ -21,6 +21,8 @@ #include <linux/reboot.h> #include "leds.h" +static int panic_heartbeats; + struct heartbeat_trig_data { unsigned int phase; unsigned int period; @@ -34,6 +36,11 @@ static void led_heartbeat_function(unsigned long data) unsigned long brightness = LED_OFF; unsigned long delay = 0; + if (unlikely(panic_heartbeats)) { + led_set_brightness(led_cdev, LED_OFF); + return; + } + /* acts like an actual heart beat -- ie thump-thump-pause... */ switch (heartbeat_data->phase) { case 0: @@ -111,12 +118,19 @@ static int heartbeat_reboot_notifier(struct notifier_block *nb, return NOTIFY_DONE; } +static int heartbeat_panic_notifier(struct notifier_block *nb, + unsigned long code, void *unused) +{ + panic_heartbeats = 1; + return NOTIFY_DONE; +} + static struct notifier_block heartbeat_reboot_nb = { .notifier_call = heartbeat_reboot_notifier, }; static struct notifier_block heartbeat_panic_nb = { - .notifier_call = heartbeat_reboot_notifier, + .notifier_call = heartbeat_panic_notifier, }; static int __init heartbeat_trig_init(void) diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index d039de8322f0..b58b7a33914a 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -1084,6 +1084,7 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->split_io = dm_rh_get_region_size(ms->rh); ti->num_flush_requests = 1; ti->num_discard_requests = 1; + ti->discard_zeroes_data_unsupported = 1; ms->kmirrord_wq = alloc_workqueue("kmirrord", WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0); @@ -1214,7 +1215,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, * We need to dec pending if this was a write. */ if (rw == WRITE) { - if (!(bio->bi_rw & REQ_FLUSH)) + if (!(bio->bi_rw & (REQ_FLUSH | REQ_DISCARD))) dm_rh_dec(ms->rh, map_context->ll); return error; } diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c index 7771ed212182..69732e03eb34 100644 --- a/drivers/md/dm-region-hash.c +++ b/drivers/md/dm-region-hash.c @@ -404,6 +404,9 @@ void dm_rh_mark_nosync(struct dm_region_hash *rh, struct bio *bio) return; } + if (bio->bi_rw & REQ_DISCARD) + return; + /* We must inform the log that the sync count has changed. */ log->type->set_region_sync(log, region, 0); @@ -524,7 +527,7 @@ void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios) struct bio *bio; for (bio = bios->head; bio; bio = bio->bi_next) { - if (bio->bi_rw & REQ_FLUSH) + if (bio->bi_rw & (REQ_FLUSH | REQ_DISCARD)) continue; rh_inc(rh, dm_rh_bio_to_region(rh, bio)); } diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 37fdaf81bd1f..68694da0d21d 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -1245,7 +1245,10 @@ static void process_discard(struct thin_c *tc, struct bio *bio) cell_release_singleton(cell, bio); cell_release_singleton(cell2, bio); - remap_and_issue(tc, bio, lookup_result.block); + if ((!lookup_result.shared) && pool->pf.discard_passdown) + remap_and_issue(tc, bio, lookup_result.block); + else + bio_endio(bio, 0); } break; @@ -2292,6 +2295,13 @@ static int process_reserve_metadata_snap_mesg(unsigned argc, char **argv, struct if (r) return r; + r = dm_pool_commit_metadata(pool->pmd); + if (r) { + DMERR("%s: dm_pool_commit_metadata() failed, error = %d", + __func__, r); + return r; + } + r = dm_pool_reserve_metadata_snap(pool->pmd); if (r) DMWARN("reserve_metadata_snap message failed."); @@ -2621,6 +2631,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) if (tc->pool->pf.discard_enabled) { ti->discards_supported = 1; ti->num_discard_requests = 1; + ti->discard_zeroes_data_unsupported = 1; } dm_put(pool_md); diff --git a/drivers/md/md.c b/drivers/md/md.c index 1c2f9048e1ae..d5ab4493c8be 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2931,6 +2931,7 @@ offset_store(struct md_rdev *rdev, const char *buf, size_t len) * can be sane */ return -EBUSY; rdev->data_offset = offset; + rdev->new_data_offset = offset; return len; } @@ -3926,8 +3927,8 @@ array_state_show(struct mddev *mddev, char *page) return sprintf(page, "%s\n", array_states[st]); } -static int do_md_stop(struct mddev * mddev, int ro, int is_open); -static int md_set_readonly(struct mddev * mddev, int is_open); +static int do_md_stop(struct mddev * mddev, int ro, struct block_device *bdev); +static int md_set_readonly(struct mddev * mddev, struct block_device *bdev); static int do_md_run(struct mddev * mddev); static int restart_array(struct mddev *mddev); @@ -3943,14 +3944,14 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len) /* stopping an active array */ if (atomic_read(&mddev->openers) > 0) return -EBUSY; - err = do_md_stop(mddev, 0, 0); + err = do_md_stop(mddev, 0, NULL); break; case inactive: /* stopping an active array */ if (mddev->pers) { if (atomic_read(&mddev->openers) > 0) return -EBUSY; - err = do_md_stop(mddev, 2, 0); + err = do_md_stop(mddev, 2, NULL); } else err = 0; /* already inactive */ break; @@ -3958,7 +3959,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len) break; /* not supported yet */ case readonly: if (mddev->pers) - err = md_set_readonly(mddev, 0); + err = md_set_readonly(mddev, NULL); else { mddev->ro = 1; set_disk_ro(mddev->gendisk, 1); @@ -3968,7 +3969,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len) case read_auto: if (mddev->pers) { if (mddev->ro == 0) - err = md_set_readonly(mddev, 0); + err = md_set_readonly(mddev, NULL); else if (mddev->ro == 1) err = restart_array(mddev); if (err == 0) { @@ -5351,15 +5352,17 @@ void md_stop(struct mddev *mddev) } EXPORT_SYMBOL_GPL(md_stop); -static int md_set_readonly(struct mddev *mddev, int is_open) +static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) { int err = 0; mutex_lock(&mddev->open_mutex); - if (atomic_read(&mddev->openers) > is_open) { + if (atomic_read(&mddev->openers) > !!bdev) { printk("md: %s still in use.\n",mdname(mddev)); err = -EBUSY; goto out; } + if (bdev) + sync_blockdev(bdev); if (mddev->pers) { __md_stop_writes(mddev); @@ -5381,18 +5384,26 @@ out: * 0 - completely stop and dis-assemble array * 2 - stop but do not disassemble array */ -static int do_md_stop(struct mddev * mddev, int mode, int is_open) +static int do_md_stop(struct mddev * mddev, int mode, + struct block_device *bdev) { struct gendisk *disk = mddev->gendisk; struct md_rdev *rdev; mutex_lock(&mddev->open_mutex); - if (atomic_read(&mddev->openers) > is_open || + if (atomic_read(&mddev->openers) > !!bdev || mddev->sysfs_active) { printk("md: %s still in use.\n",mdname(mddev)); mutex_unlock(&mddev->open_mutex); return -EBUSY; } + if (bdev) + /* It is possible IO was issued on some other + * open file which was closed before we took ->open_mutex. + * As that was not the last close __blkdev_put will not + * have called sync_blockdev, so we must. + */ + sync_blockdev(bdev); if (mddev->pers) { if (mddev->ro) @@ -5466,7 +5477,7 @@ static void autorun_array(struct mddev *mddev) err = do_md_run(mddev); if (err) { printk(KERN_WARNING "md: do_md_run() returned %d\n", err); - do_md_stop(mddev, 0, 0); + do_md_stop(mddev, 0, NULL); } } @@ -5784,8 +5795,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info) super_types[mddev->major_version]. validate_super(mddev, rdev); if ((info->state & (1<<MD_DISK_SYNC)) && - (!test_bit(In_sync, &rdev->flags) || - rdev->raid_disk != info->raid_disk)) { + rdev->raid_disk != info->raid_disk) { /* This was a hot-add request, but events doesn't * match, so reject it. */ @@ -6482,11 +6492,11 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, goto done_unlock; case STOP_ARRAY: - err = do_md_stop(mddev, 0, 1); + err = do_md_stop(mddev, 0, bdev); goto done_unlock; case STOP_ARRAY_RO: - err = md_set_readonly(mddev, 1); + err = md_set_readonly(mddev, bdev); goto done_unlock; case BLKROSET: @@ -6751,7 +6761,7 @@ struct md_thread *md_register_thread(void (*run) (struct mddev *), struct mddev thread->tsk = kthread_run(md_thread, thread, "%s_%s", mdname(thread->mddev), - name ?: mddev->pers->name); + name); if (IS_ERR(thread->tsk)) { kfree(thread); return NULL; @@ -7298,6 +7308,7 @@ void md_do_sync(struct mddev *mddev) int skipped = 0; struct md_rdev *rdev; char *desc; + struct blk_plug plug; /* just incase thread restarts... */ if (test_bit(MD_RECOVERY_DONE, &mddev->recovery)) @@ -7447,6 +7458,7 @@ void md_do_sync(struct mddev *mddev) } mddev->curr_resync_completed = j; + blk_start_plug(&plug); while (j < max_sectors) { sector_t sectors; @@ -7552,6 +7564,7 @@ void md_do_sync(struct mddev *mddev) * this also signals 'finished resyncing' to md_stop */ out: + blk_finish_plug(&plug); wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active)); /* tell personality that we are finished */ diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 9339e67fcc79..61a1833ebaf3 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -474,7 +474,8 @@ static int multipath_run (struct mddev *mddev) } { - mddev->thread = md_register_thread(multipathd, mddev, NULL); + mddev->thread = md_register_thread(multipathd, mddev, + "multipath"); if (!mddev->thread) { printk(KERN_ERR "multipath: couldn't allocate thread" " for %s\n", mdname(mddev)); diff --git a/drivers/md/persistent-data/dm-space-map-checker.c b/drivers/md/persistent-data/dm-space-map-checker.c index 50ed53bf4aa2..fc90c11620ad 100644 --- a/drivers/md/persistent-data/dm-space-map-checker.c +++ b/drivers/md/persistent-data/dm-space-map-checker.c @@ -8,6 +8,7 @@ #include <linux/device-mapper.h> #include <linux/export.h> +#include <linux/vmalloc.h> #ifdef CONFIG_DM_DEBUG_SPACE_MAPS @@ -89,13 +90,23 @@ static int ca_create(struct count_array *ca, struct dm_space_map *sm) ca->nr = nr_blocks; ca->nr_free = nr_blocks; - ca->counts = kzalloc(sizeof(*ca->counts) * nr_blocks, GFP_KERNEL); - if (!ca->counts) - return -ENOMEM; + + if (!nr_blocks) + ca->counts = NULL; + else { + ca->counts = vzalloc(sizeof(*ca->counts) * nr_blocks); + if (!ca->counts) + return -ENOMEM; + } return 0; } +static void ca_destroy(struct count_array *ca) +{ + vfree(ca->counts); +} + static int ca_load(struct count_array *ca, struct dm_space_map *sm) { int r; @@ -126,12 +137,14 @@ static int ca_load(struct count_array *ca, struct dm_space_map *sm) static int ca_extend(struct count_array *ca, dm_block_t extra_blocks) { dm_block_t nr_blocks = ca->nr + extra_blocks; - uint32_t *counts = kzalloc(sizeof(*counts) * nr_blocks, GFP_KERNEL); + uint32_t *counts = vzalloc(sizeof(*counts) * nr_blocks); if (!counts) return -ENOMEM; - memcpy(counts, ca->counts, sizeof(*counts) * ca->nr); - kfree(ca->counts); + if (ca->counts) { + memcpy(counts, ca->counts, sizeof(*counts) * ca->nr); + ca_destroy(ca); + } ca->nr = nr_blocks; ca->nr_free += extra_blocks; ca->counts = counts; @@ -151,11 +164,6 @@ static int ca_commit(struct count_array *old, struct count_array *new) return 0; } -static void ca_destroy(struct count_array *ca) -{ - kfree(ca->counts); -} - /*----------------------------------------------------------------*/ struct sm_checker { @@ -343,25 +351,25 @@ struct dm_space_map *dm_sm_checker_create(struct dm_space_map *sm) int r; struct sm_checker *smc; - if (!sm) - return NULL; + if (IS_ERR_OR_NULL(sm)) + return ERR_PTR(-EINVAL); smc = kmalloc(sizeof(*smc), GFP_KERNEL); if (!smc) - return NULL; + return ERR_PTR(-ENOMEM); memcpy(&smc->sm, &ops_, sizeof(smc->sm)); r = ca_create(&smc->old_counts, sm); if (r) { kfree(smc); - return NULL; + return ERR_PTR(r); } r = ca_create(&smc->counts, sm); if (r) { ca_destroy(&smc->old_counts); kfree(smc); - return NULL; + return ERR_PTR(r); } smc->real_sm = sm; @@ -371,7 +379,7 @@ struct dm_space_map *dm_sm_checker_create(struct dm_space_map *sm) ca_destroy(&smc->counts); ca_destroy(&smc->old_counts); kfree(smc); - return NULL; + return ERR_PTR(r); } r = ca_commit(&smc->old_counts, &smc->counts); @@ -379,7 +387,7 @@ struct dm_space_map *dm_sm_checker_create(struct dm_space_map *sm) ca_destroy(&smc->counts); ca_destroy(&smc->old_counts); kfree(smc); - return NULL; + return ERR_PTR(r); } return &smc->sm; @@ -391,25 +399,25 @@ struct dm_space_map *dm_sm_checker_create_fresh(struct dm_space_map *sm) int r; struct sm_checker *smc; - if (!sm) - return NULL; + if (IS_ERR_OR_NULL(sm)) + return ERR_PTR(-EINVAL); smc = kmalloc(sizeof(*smc), GFP_KERNEL); if (!smc) - return NULL; + return ERR_PTR(-ENOMEM); memcpy(&smc->sm, &ops_, sizeof(smc->sm)); r = ca_create(&smc->old_counts, sm); if (r) { kfree(smc); - return NULL; + return ERR_PTR(r); } r = ca_create(&smc->counts, sm); if (r) { ca_destroy(&smc->old_counts); kfree(smc); - return NULL; + return ERR_PTR(r); } smc->real_sm = sm; diff --git a/drivers/md/persistent-data/dm-space-map-disk.c b/drivers/md/persistent-data/dm-space-map-disk.c index fc469ba9f627..3d0ed5332883 100644 --- a/drivers/md/persistent-data/dm-space-map-disk.c +++ b/drivers/md/persistent-data/dm-space-map-disk.c @@ -290,7 +290,16 @@ struct dm_space_map *dm_sm_disk_create(struct dm_transaction_manager *tm, dm_block_t nr_blocks) { struct dm_space_map *sm = dm_sm_disk_create_real(tm, nr_blocks); - return dm_sm_checker_create_fresh(sm); + struct dm_space_map *smc; + + if (IS_ERR_OR_NULL(sm)) + return sm; + + smc = dm_sm_checker_create_fresh(sm); + if (IS_ERR(smc)) + dm_sm_destroy(sm); + + return smc; } EXPORT_SYMBOL_GPL(dm_sm_disk_create); diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c index 400fe144c0cd..e5604b32d91f 100644 --- a/drivers/md/persistent-data/dm-transaction-manager.c +++ b/drivers/md/persistent-data/dm-transaction-manager.c @@ -138,6 +138,9 @@ EXPORT_SYMBOL_GPL(dm_tm_create_non_blocking_clone); void dm_tm_destroy(struct dm_transaction_manager *tm) { + if (!tm->is_clone) + wipe_shadow_table(tm); + kfree(tm); } EXPORT_SYMBOL_GPL(dm_tm_destroy); @@ -344,8 +347,10 @@ static int dm_tm_create_internal(struct dm_block_manager *bm, } *sm = dm_sm_checker_create(inner); - if (!*sm) + if (IS_ERR(*sm)) { + r = PTR_ERR(*sm); goto bad2; + } } else { r = dm_bm_write_lock(dm_tm_get_bm(*tm), sb_location, @@ -364,8 +369,10 @@ static int dm_tm_create_internal(struct dm_block_manager *bm, } *sm = dm_sm_checker_create(inner); - if (!*sm) + if (IS_ERR(*sm)) { + r = PTR_ERR(*sm); goto bad2; + } } return 0; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index a9c7981ddd24..cacd008d6864 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -517,8 +517,8 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect int bad_sectors; int disk = start_disk + i; - if (disk >= conf->raid_disks) - disk -= conf->raid_disks; + if (disk >= conf->raid_disks * 2) + disk -= conf->raid_disks * 2; rdev = rcu_dereference(conf->mirrors[disk].rdev); if (r1_bio->bios[disk] == IO_BLOCKED @@ -883,7 +883,6 @@ static void make_request(struct mddev *mddev, struct bio * bio) const unsigned long do_sync = (bio->bi_rw & REQ_SYNC); const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA)); struct md_rdev *blocked_rdev; - int plugged; int first_clone; int sectors_handled; int max_sectors; @@ -1034,7 +1033,6 @@ read_again: * the bad blocks. Each set of writes gets it's own r1bio * with a set of bios attached. */ - plugged = mddev_check_plugged(mddev); disks = conf->raid_disks * 2; retry_write: @@ -1191,6 +1189,8 @@ read_again: bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); + if (!mddev_check_plugged(mddev)) + md_wakeup_thread(mddev->thread); } /* Mustn't call r1_bio_write_done before this next test, * as it could result in the bio being freed. @@ -1213,9 +1213,6 @@ read_again: /* In case raid1d snuck in to freeze_array */ wake_up(&conf->wait_barrier); - - if (do_sync || !bitmap || !plugged) - md_wakeup_thread(mddev->thread); } static void status(struct seq_file *seq, struct mddev *mddev) @@ -1821,8 +1818,14 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) if (atomic_dec_and_test(&r1_bio->remaining)) { /* if we're here, all write(s) have completed, so clean up */ - md_done_sync(mddev, r1_bio->sectors, 1); - put_buf(r1_bio); + int s = r1_bio->sectors; + if (test_bit(R1BIO_MadeGood, &r1_bio->state) || + test_bit(R1BIO_WriteError, &r1_bio->state)) + reschedule_retry(r1_bio); + else { + put_buf(r1_bio); + md_done_sync(mddev, s, 1); + } } } @@ -2488,9 +2491,10 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp */ if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) { atomic_set(&r1_bio->remaining, read_targets); - for (i = 0; i < conf->raid_disks * 2; i++) { + for (i = 0; i < conf->raid_disks * 2 && read_targets; i++) { bio = r1_bio->bios[i]; if (bio->bi_end_io == end_sync_read) { + read_targets--; md_sync_acct(bio->bi_bdev, nr_sectors); generic_make_request(bio); } @@ -2621,7 +2625,7 @@ static struct r1conf *setup_conf(struct mddev *mddev) goto abort; } err = -ENOMEM; - conf->thread = md_register_thread(raid1d, mddev, NULL); + conf->thread = md_register_thread(raid1d, mddev, "raid1"); if (!conf->thread) { printk(KERN_ERR "md/raid1:%s: couldn't allocate thread\n", diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 99ae6068e456..8da6282254c3 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1039,7 +1039,6 @@ static void make_request(struct mddev *mddev, struct bio * bio) const unsigned long do_fua = (bio->bi_rw & REQ_FUA); unsigned long flags; struct md_rdev *blocked_rdev; - int plugged; int sectors_handled; int max_sectors; int sectors; @@ -1239,7 +1238,6 @@ read_again: * of r10_bios is recored in bio->bi_phys_segments just as with * the read case. */ - plugged = mddev_check_plugged(mddev); r10_bio->read_slot = -1; /* make sure repl_bio gets freed */ raid10_find_phys(conf, r10_bio); @@ -1396,6 +1394,8 @@ retry_write: bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); + if (!mddev_check_plugged(mddev)) + md_wakeup_thread(mddev->thread); if (!r10_bio->devs[i].repl_bio) continue; @@ -1423,6 +1423,8 @@ retry_write: bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); + if (!mddev_check_plugged(mddev)) + md_wakeup_thread(mddev->thread); } /* Don't remove the bias on 'remaining' (one_write_done) until @@ -1448,9 +1450,6 @@ retry_write: /* In case raid10d snuck in to freeze_array */ wake_up(&conf->wait_barrier); - - if (do_sync || !mddev->bitmap || !plugged) - md_wakeup_thread(mddev->thread); } static void status(struct seq_file *seq, struct mddev *mddev) @@ -2310,7 +2309,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 if (r10_sync_page_io(rdev, r10_bio->devs[sl].addr + sect, - s<<9, conf->tmppage, WRITE) + s, conf->tmppage, WRITE) == 0) { /* Well, this device is dead */ printk(KERN_NOTICE @@ -2349,7 +2348,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10 switch (r10_sync_page_io(rdev, r10_bio->devs[sl].addr + sect, - s<<9, conf->tmppage, + s, conf->tmppage, READ)) { case 0: /* Well, this device is dead */ @@ -2512,7 +2511,7 @@ read_more: slot = r10_bio->read_slot; printk_ratelimited( KERN_ERR - "md/raid10:%s: %s: redirecting" + "md/raid10:%s: %s: redirecting " "sector %llu to another mirror\n", mdname(mddev), bdevname(rdev->bdev, b), @@ -2661,7 +2660,8 @@ static void raid10d(struct mddev *mddev) blk_start_plug(&plug); for (;;) { - flush_pending_writes(conf); + if (atomic_read(&mddev->plug_cnt) == 0) + flush_pending_writes(conf); spin_lock_irqsave(&conf->device_lock, flags); if (list_empty(head)) { @@ -2890,6 +2890,12 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, /* want to reconstruct this device */ rb2 = r10_bio; sect = raid10_find_virt(conf, sector_nr, i); + if (sect >= mddev->resync_max_sectors) { + /* last stripe is not complete - don't + * try to recover this sector. + */ + continue; + } /* Unless we are doing a full sync, or a replacement * we only need to recover the block if it is set in * the bitmap @@ -3421,7 +3427,7 @@ static struct r10conf *setup_conf(struct mddev *mddev) spin_lock_init(&conf->resync_lock); init_waitqueue_head(&conf->wait_barrier); - conf->thread = md_register_thread(raid10d, mddev, NULL); + conf->thread = md_register_thread(raid10d, mddev, "raid10"); if (!conf->thread) goto out; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index d26767246d26..04348d76bb30 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -196,12 +196,14 @@ static void __release_stripe(struct r5conf *conf, struct stripe_head *sh) BUG_ON(!list_empty(&sh->lru)); BUG_ON(atomic_read(&conf->active_stripes)==0); if (test_bit(STRIPE_HANDLE, &sh->state)) { - if (test_bit(STRIPE_DELAYED, &sh->state)) + if (test_bit(STRIPE_DELAYED, &sh->state) && + !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) list_add_tail(&sh->lru, &conf->delayed_list); else if (test_bit(STRIPE_BIT_DELAY, &sh->state) && sh->bm_seq - conf->seq_write > 0) list_add_tail(&sh->lru, &conf->bitmap_list); else { + clear_bit(STRIPE_DELAYED, &sh->state); clear_bit(STRIPE_BIT_DELAY, &sh->state); list_add_tail(&sh->lru, &conf->handle_list); } @@ -606,6 +608,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) * a chance*/ md_check_recovery(conf->mddev); } + /* + * Because md_wait_for_blocked_rdev + * will dec nr_pending, we must + * increment it first. + */ + atomic_inc(&rdev->nr_pending); md_wait_for_blocked_rdev(rdev, conf->mddev); } else { /* Acknowledged bad block - skip the write */ @@ -1737,6 +1745,7 @@ static void raid5_end_read_request(struct bio * bi, int error) } else { const char *bdn = bdevname(rdev->bdev, b); int retry = 0; + int set_bad = 0; clear_bit(R5_UPTODATE, &sh->dev[i].flags); atomic_inc(&rdev->read_errors); @@ -1748,7 +1757,8 @@ static void raid5_end_read_request(struct bio * bi, int error) mdname(conf->mddev), (unsigned long long)s, bdn); - else if (conf->mddev->degraded >= conf->max_degraded) + else if (conf->mddev->degraded >= conf->max_degraded) { + set_bad = 1; printk_ratelimited( KERN_WARNING "md/raid:%s: read error not correctable " @@ -1756,8 +1766,9 @@ static void raid5_end_read_request(struct bio * bi, int error) mdname(conf->mddev), (unsigned long long)s, bdn); - else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) + } else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) { /* Oh, no!!! */ + set_bad = 1; printk_ratelimited( KERN_WARNING "md/raid:%s: read error NOT corrected!! " @@ -1765,7 +1776,7 @@ static void raid5_end_read_request(struct bio * bi, int error) mdname(conf->mddev), (unsigned long long)s, bdn); - else if (atomic_read(&rdev->read_errors) + } else if (atomic_read(&rdev->read_errors) > conf->max_nr_stripes) printk(KERN_WARNING "md/raid:%s: Too many read errors, failing device %s.\n", @@ -1777,7 +1788,11 @@ static void raid5_end_read_request(struct bio * bi, int error) else { clear_bit(R5_ReadError, &sh->dev[i].flags); clear_bit(R5_ReWrite, &sh->dev[i].flags); - md_error(conf->mddev, rdev); + if (!(set_bad + && test_bit(In_sync, &rdev->flags) + && rdev_set_badblocks( + rdev, sh->sector, STRIPE_SECTORS, 0))) + md_error(conf->mddev, rdev); } } rdev_dec_pending(rdev, conf->mddev); @@ -3582,8 +3597,18 @@ static void handle_stripe(struct stripe_head *sh) finish: /* wait for this device to become unblocked */ - if (conf->mddev->external && unlikely(s.blocked_rdev)) - md_wait_for_blocked_rdev(s.blocked_rdev, conf->mddev); + if (unlikely(s.blocked_rdev)) { + if (conf->mddev->external) + md_wait_for_blocked_rdev(s.blocked_rdev, + conf->mddev); + else + /* Internal metadata will immediately + * be written by raid5d, so we don't + * need to wait here. + */ + rdev_dec_pending(s.blocked_rdev, + conf->mddev); + } if (s.handle_bad_blocks) for (i = disks; i--; ) { @@ -3881,8 +3906,6 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) raid_bio->bi_next = (void*)rdev; align_bi->bi_bdev = rdev->bdev; align_bi->bi_flags &= ~(1 << BIO_SEG_VALID); - /* No reshape active, so we can trust rdev->data_offset */ - align_bi->bi_sector += rdev->data_offset; if (!bio_fits_rdev(align_bi) || is_badblock(rdev, align_bi->bi_sector, align_bi->bi_size>>9, @@ -3893,6 +3916,9 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) return 0; } + /* No reshape active, so we can trust rdev->data_offset */ + align_bi->bi_sector += rdev->data_offset; + spin_lock_irq(&conf->device_lock); wait_event_lock_irq(conf->wait_for_stripe, conf->quiesce == 0, @@ -3971,7 +3997,6 @@ static void make_request(struct mddev *mddev, struct bio * bi) struct stripe_head *sh; const int rw = bio_data_dir(bi); int remaining; - int plugged; if (unlikely(bi->bi_rw & REQ_FLUSH)) { md_flush_request(mddev, bi); @@ -3990,7 +4015,6 @@ static void make_request(struct mddev *mddev, struct bio * bi) bi->bi_next = NULL; bi->bi_phys_segments = 1; /* over-loaded to count active stripes */ - plugged = mddev_check_plugged(mddev); for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) { DEFINE_WAIT(w); int previous; @@ -4092,6 +4116,7 @@ static void make_request(struct mddev *mddev, struct bio * bi) if ((bi->bi_rw & REQ_SYNC) && !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) atomic_inc(&conf->preread_active_stripes); + mddev_check_plugged(mddev); release_stripe(sh); } else { /* cannot get stripe for read-ahead, just give-up */ @@ -4099,10 +4124,7 @@ static void make_request(struct mddev *mddev, struct bio * bi) finish_wait(&conf->wait_for_overlap, &w); break; } - } - if (!plugged) - md_wakeup_thread(mddev->thread); spin_lock_irq(&conf->device_lock); remaining = raid5_dec_bi_phys_segments(bi); @@ -4823,6 +4845,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) int raid_disk, memory, max_disks; struct md_rdev *rdev; struct disk_info *disk; + char pers_name[6]; if (mddev->new_level != 5 && mddev->new_level != 4 @@ -4946,7 +4969,8 @@ static struct r5conf *setup_conf(struct mddev *mddev) printk(KERN_INFO "md/raid:%s: allocated %dkB\n", mdname(mddev), memory); - conf->thread = md_register_thread(raid5d, mddev, NULL); + sprintf(pers_name, "raid%d", mddev->new_level); + conf->thread = md_register_thread(raid5d, mddev, pers_name); if (!conf->thread) { printk(KERN_ERR "md/raid:%s: couldn't allocate thread.\n", @@ -5465,10 +5489,9 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (rdev->saved_raid_disk >= 0 && rdev->saved_raid_disk >= first && conf->disks[rdev->saved_raid_disk].rdev == NULL) - disk = rdev->saved_raid_disk; - else - disk = first; - for ( ; disk <= last ; disk++) { + first = rdev->saved_raid_disk; + + for (disk = first; disk <= last; disk++) { p = conf->disks + disk; if (p->rdev == NULL) { clear_bit(In_sync, &rdev->flags); @@ -5477,8 +5500,11 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (rdev->saved_raid_disk != disk) conf->fullsync = 1; rcu_assign_pointer(p->rdev, rdev); - break; + goto out; } + } + for (disk = first; disk <= last; disk++) { + p = conf->disks + disk; if (test_bit(WantReplacement, &p->rdev->flags) && p->replacement == NULL) { clear_bit(In_sync, &rdev->flags); @@ -5490,6 +5516,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) break; } } +out: print_raid5_conf(conf); return err; } diff --git a/drivers/media/dvb/dvb-core/dvbdev.c b/drivers/media/dvb/dvb-core/dvbdev.c index 00a67326c193..39eab73b01ae 100644 --- a/drivers/media/dvb/dvb-core/dvbdev.c +++ b/drivers/media/dvb/dvb-core/dvbdev.c @@ -243,6 +243,7 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, if (minor == MAX_DVB_MINORS) { kfree(dvbdevfops); kfree(dvbdev); + up_write(&minor_rwsem); mutex_unlock(&dvbdev_register_lock); return -EINVAL; } diff --git a/drivers/media/rc/winbond-cir.c b/drivers/media/rc/winbond-cir.c index 342c2c8c1ddf..54ee34872d14 100644 --- a/drivers/media/rc/winbond-cir.c +++ b/drivers/media/rc/winbond-cir.c @@ -232,7 +232,7 @@ MODULE_PARM_DESC(invert, "Invert the signal from the IR receiver"); static bool txandrx; /* default = 0 */ module_param(txandrx, bool, 0444); -MODULE_PARM_DESC(invert, "Allow simultaneous TX and RX"); +MODULE_PARM_DESC(txandrx, "Allow simultaneous TX and RX"); static unsigned int wake_sc = 0x800F040C; module_param(wake_sc, uint, 0644); @@ -1032,6 +1032,8 @@ wbcir_probe(struct pnp_dev *device, const struct pnp_device_id *dev_id) data->dev->tx_ir = wbcir_tx; data->dev->priv = data; data->dev->dev.parent = &device->dev; + data->dev->timeout = MS_TO_NS(100); + data->dev->allowed_protos = RC_TYPE_ALL; if (!request_region(data->wbase, WAKEUP_IOMEM_LEN, DRVNAME)) { dev_err(dev, "Region 0x%lx-0x%lx already in use!\n", diff --git a/drivers/media/video/cx231xx/cx231xx-audio.c b/drivers/media/video/cx231xx/cx231xx-audio.c index 068f78dc5d13..b4c99c7270cf 100644 --- a/drivers/media/video/cx231xx/cx231xx-audio.c +++ b/drivers/media/video/cx231xx/cx231xx-audio.c @@ -307,7 +307,7 @@ static int cx231xx_init_audio_isoc(struct cx231xx *dev) urb->context = dev; urb->pipe = usb_rcvisocpipe(dev->udev, dev->adev.end_point_addr); - urb->transfer_flags = URB_ISO_ASAP | URB_NO_TRANSFER_DMA_MAP; + urb->transfer_flags = URB_ISO_ASAP; urb->transfer_buffer = dev->adev.transfer_buffer[i]; urb->interval = 1; urb->complete = cx231xx_audio_isocirq; @@ -368,7 +368,7 @@ static int cx231xx_init_audio_bulk(struct cx231xx *dev) urb->context = dev; urb->pipe = usb_rcvbulkpipe(dev->udev, dev->adev.end_point_addr); - urb->transfer_flags = URB_NO_TRANSFER_DMA_MAP; + urb->transfer_flags = 0; urb->transfer_buffer = dev->adev.transfer_buffer[i]; urb->complete = cx231xx_audio_bulkirq; urb->transfer_buffer_length = sb_size; diff --git a/drivers/media/video/cx231xx/cx231xx-vbi.c b/drivers/media/video/cx231xx/cx231xx-vbi.c index 3d15314e1f88..ac7db52f404f 100644 --- a/drivers/media/video/cx231xx/cx231xx-vbi.c +++ b/drivers/media/video/cx231xx/cx231xx-vbi.c @@ -448,7 +448,7 @@ int cx231xx_init_vbi_isoc(struct cx231xx *dev, int max_packets, return -ENOMEM; } dev->vbi_mode.bulk_ctl.urb[i] = urb; - urb->transfer_flags = URB_NO_TRANSFER_DMA_MAP; + urb->transfer_flags = 0; dev->vbi_mode.bulk_ctl.transfer_buffer[i] = kzalloc(sb_size, GFP_KERNEL); diff --git a/drivers/media/video/cx23885/cx23885-cards.c b/drivers/media/video/cx23885/cx23885-cards.c index 13739e002a63..080e11157e5f 100644 --- a/drivers/media/video/cx23885/cx23885-cards.c +++ b/drivers/media/video/cx23885/cx23885-cards.c @@ -127,22 +127,37 @@ struct cx23885_board cx23885_boards[] = { }, [CX23885_BOARD_HAUPPAUGE_HVR1250] = { .name = "Hauppauge WinTV-HVR1250", + .porta = CX23885_ANALOG_VIDEO, .portc = CX23885_MPEG_DVB, +#ifdef MT2131_NO_ANALOG_SUPPORT_YET + .tuner_type = TUNER_PHILIPS_TDA8290, + .tuner_addr = 0x42, /* 0x84 >> 1 */ + .tuner_bus = 1, +#endif + .force_bff = 1, .input = {{ +#ifdef MT2131_NO_ANALOG_SUPPORT_YET .type = CX23885_VMUX_TELEVISION, - .vmux = 0, + .vmux = CX25840_VIN7_CH3 | + CX25840_VIN5_CH2 | + CX25840_VIN2_CH1, + .amux = CX25840_AUDIO8, .gpio0 = 0xff00, }, { - .type = CX23885_VMUX_DEBUG, - .vmux = 0, - .gpio0 = 0xff01, - }, { +#endif .type = CX23885_VMUX_COMPOSITE1, - .vmux = 1, + .vmux = CX25840_VIN7_CH3 | + CX25840_VIN4_CH2 | + CX25840_VIN6_CH1, + .amux = CX25840_AUDIO7, .gpio0 = 0xff02, }, { .type = CX23885_VMUX_SVIDEO, - .vmux = 2, + .vmux = CX25840_VIN7_CH3 | + CX25840_VIN4_CH2 | + CX25840_VIN8_CH1 | + CX25840_SVIDEO_ON, + .amux = CX25840_AUDIO7, .gpio0 = 0xff02, } }, }, @@ -267,7 +282,55 @@ struct cx23885_board cx23885_boards[] = { }, [CX23885_BOARD_HAUPPAUGE_HVR1255] = { .name = "Hauppauge WinTV-HVR1255", + .porta = CX23885_ANALOG_VIDEO, + .portc = CX23885_MPEG_DVB, + .tuner_type = TUNER_ABSENT, + .tuner_addr = 0x42, /* 0x84 >> 1 */ + .force_bff = 1, + .input = {{ + .type = CX23885_VMUX_TELEVISION, + .vmux = CX25840_VIN7_CH3 | + CX25840_VIN5_CH2 | + CX25840_VIN2_CH1 | + CX25840_DIF_ON, + .amux = CX25840_AUDIO8, + }, { + .type = CX23885_VMUX_COMPOSITE1, + .vmux = CX25840_VIN7_CH3 | + CX25840_VIN4_CH2 | + CX25840_VIN6_CH1, + .amux = CX25840_AUDIO7, + }, { + .type = CX23885_VMUX_SVIDEO, + .vmux = CX25840_VIN7_CH3 | + CX25840_VIN4_CH2 | + CX25840_VIN8_CH1 | + CX25840_SVIDEO_ON, + .amux = CX25840_AUDIO7, + } }, + }, + [CX23885_BOARD_HAUPPAUGE_HVR1255_22111] = { + .name = "Hauppauge WinTV-HVR1255", + .porta = CX23885_ANALOG_VIDEO, .portc = CX23885_MPEG_DVB, + .tuner_type = TUNER_ABSENT, + .tuner_addr = 0x42, /* 0x84 >> 1 */ + .force_bff = 1, + .input = {{ + .type = CX23885_VMUX_TELEVISION, + .vmux = CX25840_VIN7_CH3 | + CX25840_VIN5_CH2 | + CX25840_VIN2_CH1 | + CX25840_DIF_ON, + .amux = CX25840_AUDIO8, + }, { + .type = CX23885_VMUX_SVIDEO, + .vmux = CX25840_VIN7_CH3 | + CX25840_VIN4_CH2 | + CX25840_VIN8_CH1 | + CX25840_SVIDEO_ON, + .amux = CX25840_AUDIO7, + } }, }, [CX23885_BOARD_HAUPPAUGE_HVR1210] = { .name = "Hauppauge WinTV-HVR1210", @@ -624,7 +687,7 @@ struct cx23885_subid cx23885_subids[] = { }, { .subvendor = 0x0070, .subdevice = 0x2259, - .card = CX23885_BOARD_HAUPPAUGE_HVR1255, + .card = CX23885_BOARD_HAUPPAUGE_HVR1255_22111, }, { .subvendor = 0x0070, .subdevice = 0x2291, @@ -900,7 +963,7 @@ int cx23885_tuner_callback(void *priv, int component, int command, int arg) struct cx23885_dev *dev = port->dev; u32 bitmask = 0; - if (command == XC2028_RESET_CLK) + if ((command == XC2028_RESET_CLK) || (command == XC2028_I2C_FLUSH)) return 0; if (command != 0) { @@ -1130,6 +1193,7 @@ void cx23885_gpio_setup(struct cx23885_dev *dev) case CX23885_BOARD_HAUPPAUGE_HVR1270: case CX23885_BOARD_HAUPPAUGE_HVR1275: case CX23885_BOARD_HAUPPAUGE_HVR1255: + case CX23885_BOARD_HAUPPAUGE_HVR1255_22111: case CX23885_BOARD_HAUPPAUGE_HVR1210: /* GPIO-5 RF Control: 0 = RF1 Terrestrial, 1 = RF2 Cable */ /* GPIO-6 I2C Gate which can isolate the demod from the bus */ @@ -1267,6 +1331,7 @@ int cx23885_ir_init(struct cx23885_dev *dev) case CX23885_BOARD_HAUPPAUGE_HVR1400: case CX23885_BOARD_HAUPPAUGE_HVR1275: case CX23885_BOARD_HAUPPAUGE_HVR1255: + case CX23885_BOARD_HAUPPAUGE_HVR1255_22111: case CX23885_BOARD_HAUPPAUGE_HVR1210: /* FIXME: Implement me */ break; @@ -1424,6 +1489,7 @@ void cx23885_card_setup(struct cx23885_dev *dev) case CX23885_BOARD_HAUPPAUGE_HVR1270: case CX23885_BOARD_HAUPPAUGE_HVR1275: case CX23885_BOARD_HAUPPAUGE_HVR1255: + case CX23885_BOARD_HAUPPAUGE_HVR1255_22111: case CX23885_BOARD_HAUPPAUGE_HVR1210: case CX23885_BOARD_HAUPPAUGE_HVR1850: case CX23885_BOARD_HAUPPAUGE_HVR1290: @@ -1511,6 +1577,7 @@ void cx23885_card_setup(struct cx23885_dev *dev) case CX23885_BOARD_HAUPPAUGE_HVR1270: case CX23885_BOARD_HAUPPAUGE_HVR1275: case CX23885_BOARD_HAUPPAUGE_HVR1255: + case CX23885_BOARD_HAUPPAUGE_HVR1255_22111: case CX23885_BOARD_HAUPPAUGE_HVR1210: case CX23885_BOARD_COMPRO_VIDEOMATE_E800: case CX23885_BOARD_HAUPPAUGE_HVR1290: @@ -1526,10 +1593,10 @@ void cx23885_card_setup(struct cx23885_dev *dev) */ switch (dev->board) { case CX23885_BOARD_TEVII_S470: - case CX23885_BOARD_HAUPPAUGE_HVR1250: /* Currently only enabled for the integrated IR controller */ if (!enable_885_ir) break; + case CX23885_BOARD_HAUPPAUGE_HVR1250: case CX23885_BOARD_HAUPPAUGE_HVR1800: case CX23885_BOARD_HAUPPAUGE_HVR1800lp: case CX23885_BOARD_HAUPPAUGE_HVR1700: @@ -1539,6 +1606,8 @@ void cx23885_card_setup(struct cx23885_dev *dev) case CX23885_BOARD_NETUP_DUAL_DVBS2_CI: case CX23885_BOARD_NETUP_DUAL_DVB_T_C_CI_RF: case CX23885_BOARD_COMPRO_VIDEOMATE_E800: + case CX23885_BOARD_HAUPPAUGE_HVR1255: + case CX23885_BOARD_HAUPPAUGE_HVR1255_22111: case CX23885_BOARD_HAUPPAUGE_HVR1270: case CX23885_BOARD_HAUPPAUGE_HVR1850: case CX23885_BOARD_MYGICA_X8506: diff --git a/drivers/media/video/cx23885/cx23885-dvb.c b/drivers/media/video/cx23885/cx23885-dvb.c index a80a92c47455..cd542684ba02 100644 --- a/drivers/media/video/cx23885/cx23885-dvb.c +++ b/drivers/media/video/cx23885/cx23885-dvb.c @@ -712,6 +712,7 @@ static int dvb_register(struct cx23885_tsport *port) } break; case CX23885_BOARD_HAUPPAUGE_HVR1255: + case CX23885_BOARD_HAUPPAUGE_HVR1255_22111: i2c_bus = &dev->i2c_bus[0]; fe0->dvb.frontend = dvb_attach(s5h1411_attach, &hcw_s5h1411_config, @@ -721,6 +722,11 @@ static int dvb_register(struct cx23885_tsport *port) 0x60, &dev->i2c_bus[1].i2c_adap, &hauppauge_tda18271_config); } + + tda18271_attach(&dev->ts1.analog_fe, + 0x60, &dev->i2c_bus[1].i2c_adap, + &hauppauge_tda18271_config); + break; case CX23885_BOARD_HAUPPAUGE_HVR1800: i2c_bus = &dev->i2c_bus[0]; diff --git a/drivers/media/video/cx23885/cx23885-video.c b/drivers/media/video/cx23885/cx23885-video.c index c654bdc7ccb2..22f8e7fbd665 100644 --- a/drivers/media/video/cx23885/cx23885-video.c +++ b/drivers/media/video/cx23885/cx23885-video.c @@ -505,6 +505,9 @@ static int cx23885_video_mux(struct cx23885_dev *dev, unsigned int input) if ((dev->board == CX23885_BOARD_HAUPPAUGE_HVR1800) || (dev->board == CX23885_BOARD_MPX885) || + (dev->board == CX23885_BOARD_HAUPPAUGE_HVR1250) || + (dev->board == CX23885_BOARD_HAUPPAUGE_HVR1255) || + (dev->board == CX23885_BOARD_HAUPPAUGE_HVR1255_22111) || (dev->board == CX23885_BOARD_HAUPPAUGE_HVR1850)) { /* Configure audio routing */ v4l2_subdev_call(dev->sd_cx25840, audio, s_routing, @@ -1578,7 +1581,9 @@ static int cx23885_set_freq_via_ops(struct cx23885_dev *dev, fe = vfe->dvb.frontend; - if (dev->board == CX23885_BOARD_HAUPPAUGE_HVR1850) + if ((dev->board == CX23885_BOARD_HAUPPAUGE_HVR1850) || + (dev->board == CX23885_BOARD_HAUPPAUGE_HVR1255) || + (dev->board == CX23885_BOARD_HAUPPAUGE_HVR1255_22111)) fe = &dev->ts1.analog_fe; if (fe && fe->ops.tuner_ops.set_analog_params) { @@ -1608,6 +1613,8 @@ int cx23885_set_frequency(struct file *file, void *priv, int ret; switch (dev->board) { + case CX23885_BOARD_HAUPPAUGE_HVR1255: + case CX23885_BOARD_HAUPPAUGE_HVR1255_22111: case CX23885_BOARD_HAUPPAUGE_HVR1850: ret = cx23885_set_freq_via_ops(dev, f); break; diff --git a/drivers/media/video/cx23885/cx23885.h b/drivers/media/video/cx23885/cx23885.h index d884784a1c85..13c37ec07ae7 100644 --- a/drivers/media/video/cx23885/cx23885.h +++ b/drivers/media/video/cx23885/cx23885.h @@ -90,6 +90,7 @@ #define CX23885_BOARD_MYGICA_X8507 33 #define CX23885_BOARD_TERRATEC_CINERGY_T_PCIE_DUAL 34 #define CX23885_BOARD_TEVII_S471 35 +#define CX23885_BOARD_HAUPPAUGE_HVR1255_22111 36 #define GPIO_0 0x00000001 #define GPIO_1 0x00000002 diff --git a/drivers/media/video/cx25821/cx25821-core.c b/drivers/media/video/cx25821/cx25821-core.c index 83c1aa6b2e6c..f11f6f07e915 100644 --- a/drivers/media/video/cx25821/cx25821-core.c +++ b/drivers/media/video/cx25821/cx25821-core.c @@ -904,9 +904,6 @@ static int cx25821_dev_setup(struct cx25821_dev *dev) list_add_tail(&dev->devlist, &cx25821_devlist); mutex_unlock(&cx25821_devlist_mutex); - strcpy(cx25821_boards[UNKNOWN_BOARD].name, "unknown"); - strcpy(cx25821_boards[CX25821_BOARD].name, "cx25821"); - if (dev->pci->device != 0x8210) { pr_info("%s(): Exiting. Incorrect Hardware device = 0x%02x\n", __func__, dev->pci->device); diff --git a/drivers/media/video/cx25821/cx25821.h b/drivers/media/video/cx25821/cx25821.h index b9aa801b00a7..029f2934a6d8 100644 --- a/drivers/media/video/cx25821/cx25821.h +++ b/drivers/media/video/cx25821/cx25821.h @@ -187,7 +187,7 @@ enum port { }; struct cx25821_board { - char *name; + const char *name; enum port porta; enum port portb; enum port portc; diff --git a/drivers/media/video/cx25840/cx25840-core.c b/drivers/media/video/cx25840/cx25840-core.c index fc1ff69cffd0..d8eac3e30a7e 100644 --- a/drivers/media/video/cx25840/cx25840-core.c +++ b/drivers/media/video/cx25840/cx25840-core.c @@ -84,7 +84,7 @@ MODULE_PARM_DESC(debug, "Debugging messages [0=Off (default) 1=On]"); /* ----------------------------------------------------------------------- */ -static void cx23885_std_setup(struct i2c_client *client); +static void cx23888_std_setup(struct i2c_client *client); int cx25840_write(struct i2c_client *client, u16 addr, u8 value) { @@ -638,10 +638,13 @@ static void cx23885_initialize(struct i2c_client *client) finish_wait(&state->fw_wait, &wait); destroy_workqueue(q); - /* Call the cx23885 specific std setup func, we no longer rely on + /* Call the cx23888 specific std setup func, we no longer rely on * the generic cx24840 func. */ - cx23885_std_setup(client); + if (is_cx23888(state)) + cx23888_std_setup(client); + else + cx25840_std_setup(client); /* (re)set input */ set_input(client, state->vid_input, state->aud_input); @@ -1103,9 +1106,23 @@ static int set_input(struct i2c_client *client, enum cx25840_video_input vid_inp cx25840_write4(client, 0x410, 0xffff0dbf); cx25840_write4(client, 0x414, 0x00137d03); - cx25840_write4(client, 0x418, 0x01008080); + + /* on the 887, 0x418 is HSCALE_CTRL, on the 888 it is + CHROMA_CTRL */ + if (is_cx23888(state)) + cx25840_write4(client, 0x418, 0x01008080); + else + cx25840_write4(client, 0x418, 0x01000000); + cx25840_write4(client, 0x41c, 0x00000000); - cx25840_write4(client, 0x420, 0x001c3e0f); + + /* on the 887, 0x420 is CHROMA_CTRL, on the 888 it is + CRUSH_CTRL */ + if (is_cx23888(state)) + cx25840_write4(client, 0x420, 0x001c3e0f); + else + cx25840_write4(client, 0x420, 0x001c8282); + cx25840_write4(client, 0x42c, 0x42600000); cx25840_write4(client, 0x430, 0x0000039b); cx25840_write4(client, 0x438, 0x00000000); @@ -1233,7 +1250,7 @@ static int set_input(struct i2c_client *client, enum cx25840_video_input vid_inp cx25840_write4(client, 0x8d0, 0x1f063870); } - if (is_cx2388x(state)) { + if (is_cx23888(state)) { /* HVR1850 */ /* AUD_IO_CTRL - I2S Input, Parallel1*/ /* - Channel 1 src - Parallel1 (Merlin out) */ @@ -1298,8 +1315,8 @@ static int set_v4lstd(struct i2c_client *client) } cx25840_and_or(client, 0x400, ~0xf, fmt); cx25840_and_or(client, 0x403, ~0x3, pal_m); - if (is_cx2388x(state)) - cx23885_std_setup(client); + if (is_cx23888(state)) + cx23888_std_setup(client); else cx25840_std_setup(client); if (!is_cx2583x(state)) @@ -1312,6 +1329,7 @@ static int set_v4lstd(struct i2c_client *client) static int cx25840_s_ctrl(struct v4l2_ctrl *ctrl) { struct v4l2_subdev *sd = to_sd(ctrl); + struct cx25840_state *state = to_state(sd); struct i2c_client *client = v4l2_get_subdevdata(sd); switch (ctrl->id) { @@ -1324,12 +1342,20 @@ static int cx25840_s_ctrl(struct v4l2_ctrl *ctrl) break; case V4L2_CID_SATURATION: - cx25840_write(client, 0x420, ctrl->val << 1); - cx25840_write(client, 0x421, ctrl->val << 1); + if (is_cx23888(state)) { + cx25840_write(client, 0x418, ctrl->val << 1); + cx25840_write(client, 0x419, ctrl->val << 1); + } else { + cx25840_write(client, 0x420, ctrl->val << 1); + cx25840_write(client, 0x421, ctrl->val << 1); + } break; case V4L2_CID_HUE: - cx25840_write(client, 0x422, ctrl->val); + if (is_cx23888(state)) + cx25840_write(client, 0x41a, ctrl->val); + else + cx25840_write(client, 0x422, ctrl->val); break; default: @@ -1354,11 +1380,21 @@ static int cx25840_s_mbus_fmt(struct v4l2_subdev *sd, struct v4l2_mbus_framefmt fmt->field = V4L2_FIELD_INTERLACED; fmt->colorspace = V4L2_COLORSPACE_SMPTE170M; - Vsrc = (cx25840_read(client, 0x476) & 0x3f) << 4; - Vsrc |= (cx25840_read(client, 0x475) & 0xf0) >> 4; + if (is_cx23888(state)) { + Vsrc = (cx25840_read(client, 0x42a) & 0x3f) << 4; + Vsrc |= (cx25840_read(client, 0x429) & 0xf0) >> 4; + } else { + Vsrc = (cx25840_read(client, 0x476) & 0x3f) << 4; + Vsrc |= (cx25840_read(client, 0x475) & 0xf0) >> 4; + } - Hsrc = (cx25840_read(client, 0x472) & 0x3f) << 4; - Hsrc |= (cx25840_read(client, 0x471) & 0xf0) >> 4; + if (is_cx23888(state)) { + Hsrc = (cx25840_read(client, 0x426) & 0x3f) << 4; + Hsrc |= (cx25840_read(client, 0x425) & 0xf0) >> 4; + } else { + Hsrc = (cx25840_read(client, 0x472) & 0x3f) << 4; + Hsrc |= (cx25840_read(client, 0x471) & 0xf0) >> 4; + } Vlines = fmt->height + (is_50Hz ? 4 : 7); @@ -1782,8 +1818,8 @@ static int cx25840_s_video_routing(struct v4l2_subdev *sd, struct cx25840_state *state = to_state(sd); struct i2c_client *client = v4l2_get_subdevdata(sd); - if (is_cx2388x(state)) - cx23885_std_setup(client); + if (is_cx23888(state)) + cx23888_std_setup(client); return set_input(client, input, state->aud_input); } @@ -1794,8 +1830,8 @@ static int cx25840_s_audio_routing(struct v4l2_subdev *sd, struct cx25840_state *state = to_state(sd); struct i2c_client *client = v4l2_get_subdevdata(sd); - if (is_cx2388x(state)) - cx23885_std_setup(client); + if (is_cx23888(state)) + cx23888_std_setup(client); return set_input(client, state->vid_input, input); } @@ -4939,7 +4975,7 @@ void cx23885_dif_setup(struct i2c_client *client, u32 ifHz) } } -static void cx23885_std_setup(struct i2c_client *client) +static void cx23888_std_setup(struct i2c_client *client) { struct cx25840_state *state = to_state(i2c_get_clientdata(client)); v4l2_std_id std = state->std; diff --git a/drivers/media/video/em28xx/em28xx-cards.c b/drivers/media/video/em28xx/em28xx-cards.c index 92da7c28b6f0..862c6575c557 100644 --- a/drivers/media/video/em28xx/em28xx-cards.c +++ b/drivers/media/video/em28xx/em28xx-cards.c @@ -2893,7 +2893,7 @@ static void request_module_async(struct work_struct *work) if (dev->board.has_dvb) request_module("em28xx-dvb"); - if (dev->board.has_ir_i2c && !disable_ir) + if (dev->board.ir_codes && !disable_ir) request_module("em28xx-rc"); } diff --git a/drivers/media/video/gspca/sn9c20x.c b/drivers/media/video/gspca/sn9c20x.c index 6c31e46a1fd2..b9c6f17eabb2 100644 --- a/drivers/media/video/gspca/sn9c20x.c +++ b/drivers/media/video/gspca/sn9c20x.c @@ -2070,10 +2070,13 @@ static int sd_start(struct gspca_dev *gspca_dev) set_gamma(gspca_dev, v4l2_ctrl_g_ctrl(sd->gamma)); set_redblue(gspca_dev, v4l2_ctrl_g_ctrl(sd->blue), v4l2_ctrl_g_ctrl(sd->red)); - set_gain(gspca_dev, v4l2_ctrl_g_ctrl(sd->gain)); - set_exposure(gspca_dev, v4l2_ctrl_g_ctrl(sd->exposure)); - set_hvflip(gspca_dev, v4l2_ctrl_g_ctrl(sd->hflip), - v4l2_ctrl_g_ctrl(sd->vflip)); + if (sd->gain) + set_gain(gspca_dev, v4l2_ctrl_g_ctrl(sd->gain)); + if (sd->exposure) + set_exposure(gspca_dev, v4l2_ctrl_g_ctrl(sd->exposure)); + if (sd->hflip) + set_hvflip(gspca_dev, v4l2_ctrl_g_ctrl(sd->hflip), + v4l2_ctrl_g_ctrl(sd->vflip)); reg_w1(gspca_dev, 0x1007, 0x20); reg_w1(gspca_dev, 0x1061, 0x03); @@ -2176,7 +2179,7 @@ static void sd_dqcallback(struct gspca_dev *gspca_dev) struct sd *sd = (struct sd *) gspca_dev; int avg_lum; - if (!v4l2_ctrl_g_ctrl(sd->autogain)) + if (sd->autogain == NULL || !v4l2_ctrl_g_ctrl(sd->autogain)) return; avg_lum = atomic_read(&sd->avg_lum); diff --git a/drivers/media/video/mx2_camera.c b/drivers/media/video/mx2_camera.c index 41f9a254b245..637bde8aca28 100644 --- a/drivers/media/video/mx2_camera.c +++ b/drivers/media/video/mx2_camera.c @@ -83,6 +83,7 @@ #define CSICR1_INV_DATA (1 << 3) #define CSICR1_INV_PCLK (1 << 2) #define CSICR1_REDGE (1 << 1) +#define CSICR1_FMT_MASK (CSICR1_PACK_DIR | CSICR1_SWAP16_EN) #define SHIFT_STATFF_LEVEL 22 #define SHIFT_RXFF_LEVEL 19 @@ -230,6 +231,7 @@ struct mx2_prp_cfg { u32 src_pixel; u32 ch1_pixel; u32 irq_flags; + u32 csicr1; }; /* prp resizing parameters */ @@ -330,6 +332,7 @@ static struct mx2_fmt_cfg mx27_emma_prp_table[] = { .ch1_pixel = 0x2ca00565, /* RGB565 */ .irq_flags = PRP_INTR_RDERR | PRP_INTR_CH1WERR | PRP_INTR_CH1FC | PRP_INTR_LBOVF, + .csicr1 = 0, } }, { @@ -343,6 +346,21 @@ static struct mx2_fmt_cfg mx27_emma_prp_table[] = { .irq_flags = PRP_INTR_RDERR | PRP_INTR_CH2WERR | PRP_INTR_CH2FC | PRP_INTR_LBOVF | PRP_INTR_CH2OVF, + .csicr1 = CSICR1_PACK_DIR, + } + }, + { + .in_fmt = V4L2_MBUS_FMT_UYVY8_2X8, + .out_fmt = V4L2_PIX_FMT_YUV420, + .cfg = { + .channel = 2, + .in_fmt = PRP_CNTL_DATA_IN_YUV422, + .out_fmt = PRP_CNTL_CH2_OUT_YUV420, + .src_pixel = 0x22000888, /* YUV422 (YUYV) */ + .irq_flags = PRP_INTR_RDERR | PRP_INTR_CH2WERR | + PRP_INTR_CH2FC | PRP_INTR_LBOVF | + PRP_INTR_CH2OVF, + .csicr1 = CSICR1_SWAP16_EN, } }, }; @@ -1015,14 +1033,14 @@ static int mx2_camera_set_bus_param(struct soc_camera_device *icd) return ret; } + csicr1 = (csicr1 & ~CSICR1_FMT_MASK) | pcdev->emma_prp->cfg.csicr1; + if (common_flags & V4L2_MBUS_PCLK_SAMPLE_RISING) csicr1 |= CSICR1_REDGE; if (common_flags & V4L2_MBUS_VSYNC_ACTIVE_HIGH) csicr1 |= CSICR1_SOF_POL; if (common_flags & V4L2_MBUS_HSYNC_ACTIVE_HIGH) csicr1 |= CSICR1_HSYNC_POL; - if (pcdev->platform_flags & MX2_CAMERA_SWAP16) - csicr1 |= CSICR1_SWAP16_EN; if (pcdev->platform_flags & MX2_CAMERA_EXT_VSYNC) csicr1 |= CSICR1_EXT_VSYNC; if (pcdev->platform_flags & MX2_CAMERA_CCIR) @@ -1033,8 +1051,6 @@ static int mx2_camera_set_bus_param(struct soc_camera_device *icd) csicr1 |= CSICR1_GCLK_MODE; if (pcdev->platform_flags & MX2_CAMERA_INV_DATA) csicr1 |= CSICR1_INV_DATA; - if (pcdev->platform_flags & MX2_CAMERA_PACK_DIR_MSB) - csicr1 |= CSICR1_PACK_DIR; pcdev->csicr1 = csicr1; @@ -1109,7 +1125,8 @@ static int mx2_camera_get_formats(struct soc_camera_device *icd, return 0; } - if (code == V4L2_MBUS_FMT_YUYV8_2X8) { + if (code == V4L2_MBUS_FMT_YUYV8_2X8 || + code == V4L2_MBUS_FMT_UYVY8_2X8) { formats++; if (xlate) { /* diff --git a/drivers/media/video/omap3isp/isppreview.c b/drivers/media/video/omap3isp/isppreview.c index 8a4935ecc655..dd91da26f1b0 100644 --- a/drivers/media/video/omap3isp/isppreview.c +++ b/drivers/media/video/omap3isp/isppreview.c @@ -888,12 +888,12 @@ static const struct preview_update update_attrs[] = { preview_config_contrast, NULL, offsetof(struct prev_params, contrast), - 0, true, + 0, 0, true, }, /* OMAP3ISP_PREV_BRIGHTNESS */ { preview_config_brightness, NULL, offsetof(struct prev_params, brightness), - 0, true, + 0, 0, true, }, }; @@ -1102,7 +1102,7 @@ static void preview_config_input_size(struct isp_prev_device *prev, u32 active) unsigned int elv = prev->crop.top + prev->crop.height - 1; u32 features; - if (format->code == V4L2_MBUS_FMT_Y10_1X10) { + if (format->code != V4L2_MBUS_FMT_Y10_1X10) { sph -= 2; eph += 2; slv -= 2; diff --git a/drivers/media/video/pms.c b/drivers/media/video/pms.c index c370c2d87c17..b4c679b3fb0f 100644 --- a/drivers/media/video/pms.c +++ b/drivers/media/video/pms.c @@ -26,6 +26,7 @@ #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/slab.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/mutex.h> diff --git a/drivers/media/video/s5p-fimc/fimc-capture.c b/drivers/media/video/s5p-fimc/fimc-capture.c index 354574591908..725812aa0c30 100644 --- a/drivers/media/video/s5p-fimc/fimc-capture.c +++ b/drivers/media/video/s5p-fimc/fimc-capture.c @@ -350,7 +350,8 @@ static int queue_setup(struct vb2_queue *vq, const struct v4l2_format *pfmt, if (pixm) sizes[i] = max(size, pixm->plane_fmt[i].sizeimage); else - sizes[i] = size; + sizes[i] = max_t(u32, size, frame->payload[i]); + allocators[i] = ctx->fimc_dev->alloc_ctx; } @@ -479,37 +480,39 @@ static int fimc_capture_set_default_format(struct fimc_dev *fimc); static int fimc_capture_open(struct file *file) { struct fimc_dev *fimc = video_drvdata(file); - int ret = v4l2_fh_open(file); - - if (ret) - return ret; + int ret; dbg("pid: %d, state: 0x%lx", task_pid_nr(current), fimc->state); - /* Return if the corresponding video mem2mem node is already opened. */ if (fimc_m2m_active(fimc)) return -EBUSY; set_bit(ST_CAPT_BUSY, &fimc->state); - pm_runtime_get_sync(&fimc->pdev->dev); + ret = pm_runtime_get_sync(&fimc->pdev->dev); + if (ret < 0) + return ret; - if (++fimc->vid_cap.refcnt == 1) { - ret = fimc_pipeline_initialize(&fimc->pipeline, - &fimc->vid_cap.vfd->entity, true); - if (ret < 0) { - dev_err(&fimc->pdev->dev, - "Video pipeline initialization failed\n"); - pm_runtime_put_sync(&fimc->pdev->dev); - fimc->vid_cap.refcnt--; - v4l2_fh_release(file); - clear_bit(ST_CAPT_BUSY, &fimc->state); - return ret; - } - ret = fimc_capture_ctrls_create(fimc); + ret = v4l2_fh_open(file); + if (ret) + return ret; - if (!ret && !fimc->vid_cap.user_subdev_api) - ret = fimc_capture_set_default_format(fimc); + if (++fimc->vid_cap.refcnt != 1) + return 0; + + ret = fimc_pipeline_initialize(&fimc->pipeline, + &fimc->vid_cap.vfd->entity, true); + if (ret < 0) { + clear_bit(ST_CAPT_BUSY, &fimc->state); + pm_runtime_put_sync(&fimc->pdev->dev); + fimc->vid_cap.refcnt--; + v4l2_fh_release(file); + return ret; } + ret = fimc_capture_ctrls_create(fimc); + + if (!ret && !fimc->vid_cap.user_subdev_api) + ret = fimc_capture_set_default_format(fimc); + return ret; } @@ -818,9 +821,6 @@ static int fimc_cap_g_fmt_mplane(struct file *file, void *fh, struct fimc_dev *fimc = video_drvdata(file); struct fimc_ctx *ctx = fimc->vid_cap.ctx; - if (f->type != V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) - return -EINVAL; - return fimc_fill_format(&ctx->d_frame, f); } @@ -833,9 +833,6 @@ static int fimc_cap_try_fmt_mplane(struct file *file, void *fh, struct v4l2_mbus_framefmt mf; struct fimc_fmt *ffmt = NULL; - if (f->type != V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) - return -EINVAL; - if (pix->pixelformat == V4L2_PIX_FMT_JPEG) { fimc_capture_try_format(ctx, &pix->width, &pix->height, NULL, &pix->pixelformat, @@ -887,8 +884,6 @@ static int fimc_capture_set_format(struct fimc_dev *fimc, struct v4l2_format *f) struct fimc_fmt *s_fmt = NULL; int ret, i; - if (f->type != V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) - return -EINVAL; if (vb2_is_busy(&fimc->vid_cap.vbq)) return -EBUSY; @@ -924,10 +919,10 @@ static int fimc_capture_set_format(struct fimc_dev *fimc, struct v4l2_format *f) pix->width = mf->width; pix->height = mf->height; } + fimc_adjust_mplane_format(ff->fmt, pix->width, pix->height, pix); for (i = 0; i < ff->fmt->colplanes; i++) - ff->payload[i] = - (pix->width * pix->height * ff->fmt->depth[i]) / 8; + ff->payload[i] = pix->plane_fmt[i].sizeimage; set_frame_bounds(ff, pix->width, pix->height); /* Reset the composition rectangle if not yet configured */ @@ -1045,18 +1040,22 @@ static int fimc_cap_streamon(struct file *file, void *priv, { struct fimc_dev *fimc = video_drvdata(file); struct fimc_pipeline *p = &fimc->pipeline; + struct v4l2_subdev *sd = p->subdevs[IDX_SENSOR]; int ret; if (fimc_capture_active(fimc)) return -EBUSY; - media_entity_pipeline_start(&p->subdevs[IDX_SENSOR]->entity, - p->m_pipeline); + ret = media_entity_pipeline_start(&sd->entity, p->m_pipeline); + if (ret < 0) + return ret; if (fimc->vid_cap.user_subdev_api) { ret = fimc_pipeline_validate(fimc); - if (ret) + if (ret < 0) { + media_entity_pipeline_stop(&sd->entity); return ret; + } } return vb2_streamon(&fimc->vid_cap.vbq, type); } diff --git a/drivers/media/video/s5p-fimc/fimc-core.c b/drivers/media/video/s5p-fimc/fimc-core.c index 92fc5a20fb76..a4646ca1d56f 100644 --- a/drivers/media/video/s5p-fimc/fimc-core.c +++ b/drivers/media/video/s5p-fimc/fimc-core.c @@ -153,7 +153,7 @@ static struct fimc_fmt fimc_formats[] = { .colplanes = 2, .flags = FMT_FLAGS_M2M, }, { - .name = "YUV 4:2:0 non-contiguous 2-planar, Y/CbCr", + .name = "YUV 4:2:0 non-contig. 2p, Y/CbCr", .fourcc = V4L2_PIX_FMT_NV12M, .color = FIMC_FMT_YCBCR420, .depth = { 8, 4 }, @@ -161,7 +161,7 @@ static struct fimc_fmt fimc_formats[] = { .colplanes = 2, .flags = FMT_FLAGS_M2M, }, { - .name = "YUV 4:2:0 non-contiguous 3-planar, Y/Cb/Cr", + .name = "YUV 4:2:0 non-contig. 3p, Y/Cb/Cr", .fourcc = V4L2_PIX_FMT_YUV420M, .color = FIMC_FMT_YCBCR420, .depth = { 8, 2, 2 }, @@ -169,7 +169,7 @@ static struct fimc_fmt fimc_formats[] = { .colplanes = 3, .flags = FMT_FLAGS_M2M, }, { - .name = "YUV 4:2:0 non-contiguous 2-planar, Y/CbCr, tiled", + .name = "YUV 4:2:0 non-contig. 2p, tiled", .fourcc = V4L2_PIX_FMT_NV12MT, .color = FIMC_FMT_YCBCR420, .depth = { 8, 4 }, @@ -641,7 +641,7 @@ void fimc_ctrls_activate(struct fimc_ctx *ctx, bool active) if (!ctrls->ready) return; - mutex_lock(&ctrls->handler.lock); + mutex_lock(ctrls->handler.lock); v4l2_ctrl_activate(ctrls->rotate, active); v4l2_ctrl_activate(ctrls->hflip, active); v4l2_ctrl_activate(ctrls->vflip, active); @@ -660,7 +660,7 @@ void fimc_ctrls_activate(struct fimc_ctx *ctx, bool active) ctx->hflip = 0; ctx->vflip = 0; } - mutex_unlock(&ctrls->handler.lock); + mutex_unlock(ctrls->handler.lock); } /* Update maximum value of the alpha color control */ @@ -741,8 +741,8 @@ void fimc_adjust_mplane_format(struct fimc_fmt *fmt, u32 width, u32 height, pix->width = width; for (i = 0; i < pix->num_planes; ++i) { - u32 bpl = pix->plane_fmt[i].bytesperline; - u32 *sizeimage = &pix->plane_fmt[i].sizeimage; + struct v4l2_plane_pix_format *plane_fmt = &pix->plane_fmt[i]; + u32 bpl = plane_fmt->bytesperline; if (fmt->colplanes > 1 && (bpl == 0 || bpl < pix->width)) bpl = pix->width; /* Planar */ @@ -754,8 +754,9 @@ void fimc_adjust_mplane_format(struct fimc_fmt *fmt, u32 width, u32 height, if (i == 0) /* Same bytesperline for each plane. */ bytesperline = bpl; - pix->plane_fmt[i].bytesperline = bytesperline; - *sizeimage = (pix->width * pix->height * fmt->depth[i]) / 8; + plane_fmt->bytesperline = bytesperline; + plane_fmt->sizeimage = max((pix->width * pix->height * + fmt->depth[i]) / 8, plane_fmt->sizeimage); } } diff --git a/drivers/media/video/s5p-fimc/fimc-lite.c b/drivers/media/video/s5p-fimc/fimc-lite.c index 400d701aef04..74ff310db30c 100644 --- a/drivers/media/video/s5p-fimc/fimc-lite.c +++ b/drivers/media/video/s5p-fimc/fimc-lite.c @@ -451,34 +451,44 @@ static void fimc_lite_clear_event_counters(struct fimc_lite *fimc) static int fimc_lite_open(struct file *file) { struct fimc_lite *fimc = video_drvdata(file); - int ret = v4l2_fh_open(file); + int ret; - if (ret) - return ret; + if (mutex_lock_interruptible(&fimc->lock)) + return -ERESTARTSYS; set_bit(ST_FLITE_IN_USE, &fimc->state); - pm_runtime_get_sync(&fimc->pdev->dev); + ret = pm_runtime_get_sync(&fimc->pdev->dev); + if (ret < 0) + goto done; - if (++fimc->ref_count != 1 || fimc->out_path != FIMC_IO_DMA) - return ret; + ret = v4l2_fh_open(file); + if (ret < 0) + goto done; - ret = fimc_pipeline_initialize(&fimc->pipeline, &fimc->vfd->entity, - true); - if (ret < 0) { - v4l2_err(fimc->vfd, "Video pipeline initialization failed\n"); - pm_runtime_put_sync(&fimc->pdev->dev); - fimc->ref_count--; - v4l2_fh_release(file); - clear_bit(ST_FLITE_IN_USE, &fimc->state); - } + if (++fimc->ref_count == 1 && fimc->out_path == FIMC_IO_DMA) { + ret = fimc_pipeline_initialize(&fimc->pipeline, + &fimc->vfd->entity, true); + if (ret < 0) { + pm_runtime_put_sync(&fimc->pdev->dev); + fimc->ref_count--; + v4l2_fh_release(file); + clear_bit(ST_FLITE_IN_USE, &fimc->state); + } - fimc_lite_clear_event_counters(fimc); + fimc_lite_clear_event_counters(fimc); + } +done: + mutex_unlock(&fimc->lock); return ret; } static int fimc_lite_close(struct file *file) { struct fimc_lite *fimc = video_drvdata(file); + int ret; + + if (mutex_lock_interruptible(&fimc->lock)) + return -ERESTARTSYS; if (--fimc->ref_count == 0 && fimc->out_path == FIMC_IO_DMA) { clear_bit(ST_FLITE_IN_USE, &fimc->state); @@ -492,20 +502,39 @@ static int fimc_lite_close(struct file *file) if (fimc->ref_count == 0) vb2_queue_release(&fimc->vb_queue); - return v4l2_fh_release(file); + ret = v4l2_fh_release(file); + + mutex_unlock(&fimc->lock); + return ret; } static unsigned int fimc_lite_poll(struct file *file, struct poll_table_struct *wait) { struct fimc_lite *fimc = video_drvdata(file); - return vb2_poll(&fimc->vb_queue, file, wait); + int ret; + + if (mutex_lock_interruptible(&fimc->lock)) + return POLL_ERR; + + ret = vb2_poll(&fimc->vb_queue, file, wait); + mutex_unlock(&fimc->lock); + + return ret; } static int fimc_lite_mmap(struct file *file, struct vm_area_struct *vma) { struct fimc_lite *fimc = video_drvdata(file); - return vb2_mmap(&fimc->vb_queue, vma); + int ret; + + if (mutex_lock_interruptible(&fimc->lock)) + return -ERESTARTSYS; + + ret = vb2_mmap(&fimc->vb_queue, vma); + mutex_unlock(&fimc->lock); + + return ret; } static const struct v4l2_file_operations fimc_lite_fops = { @@ -762,7 +791,9 @@ static int fimc_lite_streamon(struct file *file, void *priv, if (fimc_lite_active(fimc)) return -EBUSY; - media_entity_pipeline_start(&sensor->entity, p->m_pipeline); + ret = media_entity_pipeline_start(&sensor->entity, p->m_pipeline); + if (ret < 0) + return ret; ret = fimc_pipeline_validate(fimc); if (ret) { @@ -1508,7 +1539,7 @@ static int fimc_lite_suspend(struct device *dev) return 0; ret = fimc_lite_stop_capture(fimc, suspend); - if (ret) + if (ret < 0 || !fimc_lite_active(fimc)) return ret; return fimc_pipeline_shutdown(&fimc->pipeline); diff --git a/drivers/media/video/s5p-fimc/fimc-mdevice.c b/drivers/media/video/s5p-fimc/fimc-mdevice.c index 6753c45631b8..52cef4865423 100644 --- a/drivers/media/video/s5p-fimc/fimc-mdevice.c +++ b/drivers/media/video/s5p-fimc/fimc-mdevice.c @@ -193,9 +193,13 @@ int __fimc_pipeline_shutdown(struct fimc_pipeline *p) int fimc_pipeline_shutdown(struct fimc_pipeline *p) { - struct media_entity *me = &p->subdevs[IDX_SENSOR]->entity; + struct media_entity *me; int ret; + if (!p || !p->subdevs[IDX_SENSOR]) + return -EINVAL; + + me = &p->subdevs[IDX_SENSOR]->entity; mutex_lock(&me->parent->graph_mutex); ret = __fimc_pipeline_shutdown(p); mutex_unlock(&me->parent->graph_mutex); @@ -498,12 +502,12 @@ static void fimc_md_unregister_entities(struct fimc_md *fmd) * @source: the source entity to create links to all fimc entities from * @sensor: sensor subdev linked to FIMC[fimc_id] entity, may be null * @pad: the source entity pad index - * @fimc_id: index of the fimc device for which link should be enabled + * @link_mask: bitmask of the fimc devices for which link should be enabled */ static int __fimc_md_create_fimc_sink_links(struct fimc_md *fmd, struct media_entity *source, struct v4l2_subdev *sensor, - int pad, int fimc_id) + int pad, int link_mask) { struct fimc_sensor_info *s_info; struct media_entity *sink; @@ -520,7 +524,7 @@ static int __fimc_md_create_fimc_sink_links(struct fimc_md *fmd, if (!fmd->fimc[i]->variant->has_cam_if) continue; - flags = (i == fimc_id) ? MEDIA_LNK_FL_ENABLED : 0; + flags = ((1 << i) & link_mask) ? MEDIA_LNK_FL_ENABLED : 0; sink = &fmd->fimc[i]->vid_cap.subdev.entity; ret = media_entity_create_link(source, pad, sink, @@ -552,7 +556,10 @@ static int __fimc_md_create_fimc_sink_links(struct fimc_md *fmd, if (!fmd->fimc_lite[i]) continue; - flags = (i == fimc_id) ? MEDIA_LNK_FL_ENABLED : 0; + if (link_mask & (1 << (i + FIMC_MAX_DEVS))) + flags = MEDIA_LNK_FL_ENABLED; + else + flags = 0; sink = &fmd->fimc_lite[i]->subdev.entity; ret = media_entity_create_link(source, pad, sink, @@ -614,9 +621,8 @@ static int fimc_md_create_links(struct fimc_md *fmd) struct s5p_fimc_isp_info *pdata; struct fimc_sensor_info *s_info; struct media_entity *source, *sink; - int i, pad, fimc_id = 0; - int ret = 0; - u32 flags; + int i, pad, fimc_id = 0, ret = 0; + u32 flags, link_mask = 0; for (i = 0; i < fmd->num_sensors; i++) { if (fmd->sensor[i].subdev == NULL) @@ -668,19 +674,20 @@ static int fimc_md_create_links(struct fimc_md *fmd) if (source == NULL) continue; + link_mask = 1 << fimc_id++; ret = __fimc_md_create_fimc_sink_links(fmd, source, sensor, - pad, fimc_id++); + pad, link_mask); } - fimc_id = 0; for (i = 0; i < ARRAY_SIZE(fmd->csis); i++) { if (fmd->csis[i].sd == NULL) continue; source = &fmd->csis[i].sd->entity; pad = CSIS_PAD_SOURCE; + link_mask = 1 << fimc_id++; ret = __fimc_md_create_fimc_sink_links(fmd, source, NULL, - pad, fimc_id++); + pad, link_mask); } /* Create immutable links between each FIMC's subdev and video node */ @@ -734,8 +741,8 @@ static void fimc_md_put_clocks(struct fimc_md *fmd) } static int __fimc_md_set_camclk(struct fimc_md *fmd, - struct fimc_sensor_info *s_info, - bool on) + struct fimc_sensor_info *s_info, + bool on) { struct s5p_fimc_isp_info *pdata = s_info->pdata; struct fimc_camclk_info *camclk; @@ -744,12 +751,10 @@ static int __fimc_md_set_camclk(struct fimc_md *fmd, if (WARN_ON(pdata->clk_id >= FIMC_MAX_CAMCLKS) || fmd == NULL) return -EINVAL; - if (s_info->clk_on == on) - return 0; camclk = &fmd->camclk[pdata->clk_id]; - dbg("camclk %d, f: %lu, clk: %p, on: %d", - pdata->clk_id, pdata->clk_frequency, camclk, on); + dbg("camclk %d, f: %lu, use_count: %d, on: %d", + pdata->clk_id, pdata->clk_frequency, camclk->use_count, on); if (on) { if (camclk->use_count > 0 && @@ -760,11 +765,9 @@ static int __fimc_md_set_camclk(struct fimc_md *fmd, clk_set_rate(camclk->clock, pdata->clk_frequency); camclk->frequency = pdata->clk_frequency; ret = clk_enable(camclk->clock); + dbg("Enabled camclk %d: f: %lu", pdata->clk_id, + clk_get_rate(camclk->clock)); } - s_info->clk_on = 1; - dbg("Enabled camclk %d: f: %lu", pdata->clk_id, - clk_get_rate(camclk->clock)); - return ret; } @@ -773,7 +776,6 @@ static int __fimc_md_set_camclk(struct fimc_md *fmd, if (--camclk->use_count == 0) { clk_disable(camclk->clock); - s_info->clk_on = 0; dbg("Disabled camclk %d", pdata->clk_id); } return ret; @@ -789,8 +791,6 @@ static int __fimc_md_set_camclk(struct fimc_md *fmd, * devices to which sensors can be attached, either directly or through * the MIPI CSI receiver. The clock is allowed here to be used by * multiple sensors concurrently if they use same frequency. - * The per sensor subdev clk_on attribute helps to synchronize accesses - * to the sclk_cam clocks from the video and media device nodes. * This function should only be called when the graph mutex is held. */ int fimc_md_set_camclk(struct v4l2_subdev *sd, bool on) diff --git a/drivers/media/video/s5p-fimc/fimc-mdevice.h b/drivers/media/video/s5p-fimc/fimc-mdevice.h index 3b8a3492a176..1f5dbaff5442 100644 --- a/drivers/media/video/s5p-fimc/fimc-mdevice.h +++ b/drivers/media/video/s5p-fimc/fimc-mdevice.h @@ -47,7 +47,6 @@ struct fimc_camclk_info { * @pdata: sensor's atrributes passed as media device's platform data * @subdev: image sensor v4l2 subdev * @host: fimc device the sensor is currently linked to - * @clk_on: sclk_cam clock's state associated with this subdev * * This data structure applies to image sensor and the writeback subdevs. */ @@ -55,7 +54,6 @@ struct fimc_sensor_info { struct s5p_fimc_isp_info *pdata; struct v4l2_subdev *subdev; struct fimc_dev *host; - bool clk_on; }; /** diff --git a/drivers/media/video/s5p-mfc/s5p_mfc_dec.c b/drivers/media/video/s5p-mfc/s5p_mfc_dec.c index 4dd32fc8fd82..feea867f318c 100644 --- a/drivers/media/video/s5p-mfc/s5p_mfc_dec.c +++ b/drivers/media/video/s5p-mfc/s5p_mfc_dec.c @@ -996,6 +996,7 @@ int s5p_mfc_dec_ctrls_setup(struct s5p_mfc_ctx *ctx) for (i = 0; i < NUM_CTRLS; i++) { if (IS_MFC51_PRIV(controls[i].id)) { + memset(&cfg, 0, sizeof(struct v4l2_ctrl_config)); cfg.ops = &s5p_mfc_dec_ctrl_ops; cfg.id = controls[i].id; cfg.min = controls[i].minimum; diff --git a/drivers/media/video/s5p-mfc/s5p_mfc_enc.c b/drivers/media/video/s5p-mfc/s5p_mfc_enc.c index 03d83340e7fb..158b78989b89 100644 --- a/drivers/media/video/s5p-mfc/s5p_mfc_enc.c +++ b/drivers/media/video/s5p-mfc/s5p_mfc_enc.c @@ -1773,6 +1773,7 @@ int s5p_mfc_enc_ctrls_setup(struct s5p_mfc_ctx *ctx) } for (i = 0; i < NUM_CTRLS; i++) { if (IS_MFC51_PRIV(controls[i].id)) { + memset(&cfg, 0, sizeof(struct v4l2_ctrl_config)); cfg.ops = &s5p_mfc_enc_ctrl_ops; cfg.id = controls[i].id; cfg.min = controls[i].minimum; diff --git a/drivers/media/video/smiapp/smiapp-core.c b/drivers/media/video/smiapp/smiapp-core.c index e8c93c89265a..9cf5bda35fbe 100644 --- a/drivers/media/video/smiapp/smiapp-core.c +++ b/drivers/media/video/smiapp/smiapp-core.c @@ -31,6 +31,7 @@ #include <linux/device.h> #include <linux/gpio.h> #include <linux/module.h> +#include <linux/slab.h> #include <linux/regulator/consumer.h> #include <linux/slab.h> #include <linux/v4l2-mediabus.h> diff --git a/drivers/media/video/v4l2-dev.c b/drivers/media/video/v4l2-dev.c index 83dbb2ddff10..0cbada18f6f5 100644 --- a/drivers/media/video/v4l2-dev.c +++ b/drivers/media/video/v4l2-dev.c @@ -681,6 +681,7 @@ static void determine_valid_ioctls(struct video_device *vdev) SET_VALID_IOCTL(ops, VIDIOC_G_DV_TIMINGS, vidioc_g_dv_timings); SET_VALID_IOCTL(ops, VIDIOC_ENUM_DV_TIMINGS, vidioc_enum_dv_timings); SET_VALID_IOCTL(ops, VIDIOC_QUERY_DV_TIMINGS, vidioc_query_dv_timings); + SET_VALID_IOCTL(ops, VIDIOC_DV_TIMINGS_CAP, vidioc_dv_timings_cap); /* yes, really vidioc_subscribe_event */ SET_VALID_IOCTL(ops, VIDIOC_DQEVENT, vidioc_subscribe_event); SET_VALID_IOCTL(ops, VIDIOC_SUBSCRIBE_EVENT, vidioc_subscribe_event); diff --git a/drivers/media/video/zoran/zoran.h b/drivers/media/video/zoran/zoran.h index d7166afc255e..ca2754a3cd63 100644 --- a/drivers/media/video/zoran/zoran.h +++ b/drivers/media/video/zoran/zoran.h @@ -172,8 +172,10 @@ struct zoran_jpg_settings { struct v4l2_jpegcompression jpg_comp; /* JPEG-specific capture settings */ }; +struct zoran_fh; + struct zoran_mapping { - struct file *file; + struct zoran_fh *fh; int count; }; diff --git a/drivers/media/video/zoran/zoran_driver.c b/drivers/media/video/zoran/zoran_driver.c index c57310931810..c6ccdeb6d8d6 100644 --- a/drivers/media/video/zoran/zoran_driver.c +++ b/drivers/media/video/zoran/zoran_driver.c @@ -2811,7 +2811,7 @@ static void zoran_vm_close (struct vm_area_struct *vma) { struct zoran_mapping *map = vma->vm_private_data; - struct zoran_fh *fh = map->file->private_data; + struct zoran_fh *fh = map->fh; struct zoran *zr = fh->zr; int i; @@ -2938,7 +2938,7 @@ zoran_mmap (struct file *file, res = -ENOMEM; goto mmap_unlock_and_return; } - map->file = file; + map->fh = fh; map->count = 1; vma->vm_ops = &zoran_vm_ops; diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index e129c820df7d..92144ed1ad46 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -286,6 +286,7 @@ config TWL6040_CORE depends on I2C=y && GENERIC_HARDIRQS select MFD_CORE select REGMAP_I2C + select IRQ_DOMAIN default n help Say yes here if you want support for Texas Instruments TWL6040 audio diff --git a/drivers/mfd/ab5500-core.h b/drivers/mfd/ab5500-core.h deleted file mode 100644 index 63b30b17e4f3..000000000000 --- a/drivers/mfd/ab5500-core.h +++ /dev/null @@ -1,87 +0,0 @@ -/* - * Copyright (C) 2011 ST-Ericsson - * License terms: GNU General Public License (GPL) version 2 - * Shared definitions and data structures for the AB5500 MFD driver - */ - -/* Read/write operation values. */ -#define AB5500_PERM_RD (0x01) -#define AB5500_PERM_WR (0x02) - -/* Read/write permissions. */ -#define AB5500_PERM_RO (AB5500_PERM_RD) -#define AB5500_PERM_RW (AB5500_PERM_RD | AB5500_PERM_WR) - -#define AB5500_MASK_BASE (0x60) -#define AB5500_MASK_END (0x79) -#define AB5500_CHIP_ID (0x20) - -/** - * struct ab5500_reg_range - * @first: the first address of the range - * @last: the last address of the range - * @perm: access permissions for the range - */ -struct ab5500_reg_range { - u8 first; - u8 last; - u8 perm; -}; - -/** - * struct ab5500_i2c_ranges - * @count: the number of ranges in the list - * @range: the list of register ranges - */ -struct ab5500_i2c_ranges { - u8 nranges; - u8 bankid; - const struct ab5500_reg_range *range; -}; - -/** - * struct ab5500_i2c_banks - * @count: the number of ranges in the list - * @range: the list of register ranges - */ -struct ab5500_i2c_banks { - u8 nbanks; - const struct ab5500_i2c_ranges *bank; -}; - -/** - * struct ab5500_bank - * @slave_addr: I2C slave_addr found in AB5500 specification - * @name: Documentation name of the bank. For reference - */ -struct ab5500_bank { - u8 slave_addr; - const char *name; -}; - -static const struct ab5500_bank bankinfo[AB5500_NUM_BANKS] = { - [AB5500_BANK_VIT_IO_I2C_CLK_TST_OTP] = { - AB5500_ADDR_VIT_IO_I2C_CLK_TST_OTP, "VIT_IO_I2C_CLK_TST_OTP"}, - [AB5500_BANK_VDDDIG_IO_I2C_CLK_TST] = { - AB5500_ADDR_VDDDIG_IO_I2C_CLK_TST, "VDDDIG_IO_I2C_CLK_TST"}, - [AB5500_BANK_VDENC] = {AB5500_ADDR_VDENC, "VDENC"}, - [AB5500_BANK_SIM_USBSIM] = {AB5500_ADDR_SIM_USBSIM, "SIM_USBSIM"}, - [AB5500_BANK_LED] = {AB5500_ADDR_LED, "LED"}, - [AB5500_BANK_ADC] = {AB5500_ADDR_ADC, "ADC"}, - [AB5500_BANK_RTC] = {AB5500_ADDR_RTC, "RTC"}, - [AB5500_BANK_STARTUP] = {AB5500_ADDR_STARTUP, "STARTUP"}, - [AB5500_BANK_DBI_ECI] = {AB5500_ADDR_DBI_ECI, "DBI-ECI"}, - [AB5500_BANK_CHG] = {AB5500_ADDR_CHG, "CHG"}, - [AB5500_BANK_FG_BATTCOM_ACC] = { - AB5500_ADDR_FG_BATTCOM_ACC, "FG_BATCOM_ACC"}, - [AB5500_BANK_USB] = {AB5500_ADDR_USB, "USB"}, - [AB5500_BANK_IT] = {AB5500_ADDR_IT, "IT"}, - [AB5500_BANK_VIBRA] = {AB5500_ADDR_VIBRA, "VIBRA"}, - [AB5500_BANK_AUDIO_HEADSETUSB] = { - AB5500_ADDR_AUDIO_HEADSETUSB, "AUDIO_HEADSETUSB"}, -}; - -int ab5500_get_register_interruptible_raw(struct ab5500 *ab, u8 bank, u8 reg, - u8 *value); -int ab5500_mask_and_set_register_interruptible_raw(struct ab5500 *ab, u8 bank, - u8 reg, u8 bitmask, u8 bitvalues); diff --git a/drivers/mfd/mc13xxx-spi.c b/drivers/mfd/mc13xxx-spi.c index 3fcdab3eb8eb..03df422feb76 100644 --- a/drivers/mfd/mc13xxx-spi.c +++ b/drivers/mfd/mc13xxx-spi.c @@ -49,10 +49,72 @@ static struct regmap_config mc13xxx_regmap_spi_config = { .reg_bits = 7, .pad_bits = 1, .val_bits = 24, + .write_flag_mask = 0x80, .max_register = MC13XXX_NUMREGS, .cache_type = REGCACHE_NONE, + .use_single_rw = 1, +}; + +static int mc13xxx_spi_read(void *context, const void *reg, size_t reg_size, + void *val, size_t val_size) +{ + unsigned char w[4] = { *((unsigned char *) reg), 0, 0, 0}; + unsigned char r[4]; + unsigned char *p = val; + struct device *dev = context; + struct spi_device *spi = to_spi_device(dev); + struct spi_transfer t = { + .tx_buf = w, + .rx_buf = r, + .len = 4, + }; + + struct spi_message m; + int ret; + + if (val_size != 3 || reg_size != 1) + return -ENOTSUPP; + + spi_message_init(&m); + spi_message_add_tail(&t, &m); + ret = spi_sync(spi, &m); + + memcpy(p, &r[1], 3); + + return ret; +} + +static int mc13xxx_spi_write(void *context, const void *data, size_t count) +{ + struct device *dev = context; + struct spi_device *spi = to_spi_device(dev); + + if (count != 4) + return -ENOTSUPP; + + return spi_write(spi, data, count); +} + +/* + * We cannot use regmap-spi generic bus implementation here. + * The MC13783 chip will get corrupted if CS signal is deasserted + * and on i.Mx31 SoC (the target SoC for MC13783 PMIC) the SPI controller + * has the following errata (DSPhl22960): + * "The CSPI negates SS when the FIFO becomes empty with + * SSCTL= 0. Software cannot guarantee that the FIFO will not + * drain because of higher priority interrupts and the + * non-realtime characteristics of the operating system. As a + * result, the SS will negate before all of the data has been + * transferred to/from the peripheral." + * We workaround this by accessing the SPI controller with a + * single transfert. + */ + +static struct regmap_bus regmap_mc13xxx_bus = { + .write = mc13xxx_spi_write, + .read = mc13xxx_spi_read, }; static int mc13xxx_spi_probe(struct spi_device *spi) @@ -73,12 +135,13 @@ static int mc13xxx_spi_probe(struct spi_device *spi) dev_set_drvdata(&spi->dev, mc13xxx); spi->mode = SPI_MODE_0 | SPI_CS_HIGH; - spi->bits_per_word = 32; mc13xxx->dev = &spi->dev; mutex_init(&mc13xxx->lock); - mc13xxx->regmap = regmap_init_spi(spi, &mc13xxx_regmap_spi_config); + mc13xxx->regmap = regmap_init(&spi->dev, ®map_mc13xxx_bus, &spi->dev, + &mc13xxx_regmap_spi_config); + if (IS_ERR(mc13xxx->regmap)) { ret = PTR_ERR(mc13xxx->regmap); dev_err(mc13xxx->dev, "Failed to initialize register map: %d\n", diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c index 7e96bb229724..41088ecbb2a9 100644 --- a/drivers/mfd/omap-usb-host.c +++ b/drivers/mfd/omap-usb-host.c @@ -25,6 +25,7 @@ #include <linux/clk.h> #include <linux/dma-mapping.h> #include <linux/spinlock.h> +#include <linux/gpio.h> #include <plat/cpu.h> #include <plat/usb.h> #include <linux/pm_runtime.h> @@ -500,8 +501,21 @@ static void omap_usbhs_init(struct device *dev) dev_dbg(dev, "starting TI HSUSB Controller\n"); pm_runtime_get_sync(dev); - spin_lock_irqsave(&omap->lock, flags); + if (pdata->ehci_data->phy_reset) { + if (gpio_is_valid(pdata->ehci_data->reset_gpio_port[0])) + gpio_request_one(pdata->ehci_data->reset_gpio_port[0], + GPIOF_OUT_INIT_LOW, "USB1 PHY reset"); + + if (gpio_is_valid(pdata->ehci_data->reset_gpio_port[1])) + gpio_request_one(pdata->ehci_data->reset_gpio_port[1], + GPIOF_OUT_INIT_LOW, "USB2 PHY reset"); + + /* Hold the PHY in RESET for enough time till DIR is high */ + udelay(10); + } + + spin_lock_irqsave(&omap->lock, flags); omap->usbhs_rev = usbhs_read(omap->uhh_base, OMAP_UHH_REVISION); dev_dbg(dev, "OMAP UHH_REVISION 0x%x\n", omap->usbhs_rev); @@ -581,9 +595,39 @@ static void omap_usbhs_init(struct device *dev) } spin_unlock_irqrestore(&omap->lock, flags); + + if (pdata->ehci_data->phy_reset) { + /* Hold the PHY in RESET for enough time till + * PHY is settled and ready + */ + udelay(10); + + if (gpio_is_valid(pdata->ehci_data->reset_gpio_port[0])) + gpio_set_value_cansleep + (pdata->ehci_data->reset_gpio_port[0], 1); + + if (gpio_is_valid(pdata->ehci_data->reset_gpio_port[1])) + gpio_set_value_cansleep + (pdata->ehci_data->reset_gpio_port[1], 1); + } + pm_runtime_put_sync(dev); } +static void omap_usbhs_deinit(struct device *dev) +{ + struct usbhs_hcd_omap *omap = dev_get_drvdata(dev); + struct usbhs_omap_platform_data *pdata = &omap->platdata; + + if (pdata->ehci_data->phy_reset) { + if (gpio_is_valid(pdata->ehci_data->reset_gpio_port[0])) + gpio_free(pdata->ehci_data->reset_gpio_port[0]); + + if (gpio_is_valid(pdata->ehci_data->reset_gpio_port[1])) + gpio_free(pdata->ehci_data->reset_gpio_port[1]); + } +} + /** * usbhs_omap_probe - initialize TI-based HCDs @@ -767,6 +811,7 @@ static int __devinit usbhs_omap_probe(struct platform_device *pdev) goto end_probe; err_alloc: + omap_usbhs_deinit(&pdev->dev); iounmap(omap->tll_base); err_tll: @@ -818,6 +863,7 @@ static int __devexit usbhs_omap_remove(struct platform_device *pdev) { struct usbhs_hcd_omap *omap = platform_get_drvdata(pdev); + omap_usbhs_deinit(&pdev->dev); iounmap(omap->tll_base); iounmap(omap->uhh_base); clk_put(omap->init_60m_fclk); diff --git a/drivers/mfd/palmas.c b/drivers/mfd/palmas.c index 00c0aba7eba0..c4a69f193a1d 100644 --- a/drivers/mfd/palmas.c +++ b/drivers/mfd/palmas.c @@ -356,7 +356,14 @@ static int __devinit palmas_i2c_probe(struct i2c_client *i2c, } } - ret = regmap_add_irq_chip(palmas->regmap[1], palmas->irq, + /* Change IRQ into clear on read mode for efficiency */ + slave = PALMAS_BASE_TO_SLAVE(PALMAS_INTERRUPT_BASE); + addr = PALMAS_BASE_TO_REG(PALMAS_INTERRUPT_BASE, PALMAS_INT_CTRL); + reg = PALMAS_INT_CTRL_INT_CLEAR; + + regmap_write(palmas->regmap[slave], addr, reg); + + ret = regmap_add_irq_chip(palmas->regmap[slave], palmas->irq, IRQF_ONESHOT | IRQF_TRIGGER_LOW, -1, &palmas_irq_chip, &palmas->irq_data); if (ret < 0) @@ -441,6 +448,9 @@ static int __devinit palmas_i2c_probe(struct i2c_client *i2c, goto err; } + children[PALMAS_PMIC_ID].platform_data = pdata->pmic_pdata; + children[PALMAS_PMIC_ID].pdata_size = sizeof(*pdata->pmic_pdata); + ret = mfd_add_devices(palmas->dev, -1, children, ARRAY_SIZE(palmas_children), NULL, regmap_irq_chip_get_base(palmas->irq_data)); @@ -472,6 +482,7 @@ static const struct i2c_device_id palmas_i2c_id[] = { { "twl6035", }, { "twl6037", }, { "tps65913", }, + { /* end */ } }; MODULE_DEVICE_TABLE(i2c, palmas_i2c_id); diff --git a/drivers/mfd/tps65217.c b/drivers/mfd/tps65217.c index db194e433c08..61c097a98f5d 100644 --- a/drivers/mfd/tps65217.c +++ b/drivers/mfd/tps65217.c @@ -24,6 +24,7 @@ #include <linux/slab.h> #include <linux/regmap.h> #include <linux/err.h> +#include <linux/regulator/of_regulator.h> #include <linux/mfd/core.h> #include <linux/mfd/tps65217.h> @@ -132,6 +133,61 @@ int tps65217_clear_bits(struct tps65217 *tps, unsigned int reg, } EXPORT_SYMBOL_GPL(tps65217_clear_bits); +#ifdef CONFIG_OF +static struct of_regulator_match reg_matches[] = { + { .name = "dcdc1", .driver_data = (void *)TPS65217_DCDC_1 }, + { .name = "dcdc2", .driver_data = (void *)TPS65217_DCDC_2 }, + { .name = "dcdc3", .driver_data = (void *)TPS65217_DCDC_3 }, + { .name = "ldo1", .driver_data = (void *)TPS65217_LDO_1 }, + { .name = "ldo2", .driver_data = (void *)TPS65217_LDO_2 }, + { .name = "ldo3", .driver_data = (void *)TPS65217_LDO_3 }, + { .name = "ldo4", .driver_data = (void *)TPS65217_LDO_4 }, +}; + +static struct tps65217_board *tps65217_parse_dt(struct i2c_client *client) +{ + struct device_node *node = client->dev.of_node; + struct tps65217_board *pdata; + struct device_node *regs; + int count = ARRAY_SIZE(reg_matches); + int ret, i; + + regs = of_find_node_by_name(node, "regulators"); + if (!regs) + return NULL; + + ret = of_regulator_match(&client->dev, regs, reg_matches, count); + of_node_put(regs); + if ((ret < 0) || (ret > count)) + return NULL; + + count = ret; + pdata = devm_kzalloc(&client->dev, count * sizeof(*pdata), GFP_KERNEL); + if (!pdata) + return NULL; + + for (i = 0; i < count; i++) { + if (!reg_matches[i].init_data || !reg_matches[i].of_node) + continue; + + pdata->tps65217_init_data[i] = reg_matches[i].init_data; + pdata->of_node[i] = reg_matches[i].of_node; + } + + return pdata; +} + +static struct of_device_id tps65217_of_match[] = { + { .compatible = "ti,tps65217", }, + { }, +}; +#else +static struct tps65217_board *tps65217_parse_dt(struct i2c_client *client) +{ + return NULL; +} +#endif + static struct regmap_config tps65217_regmap_config = { .reg_bits = 8, .val_bits = 8, @@ -141,10 +197,14 @@ static int __devinit tps65217_probe(struct i2c_client *client, const struct i2c_device_id *ids) { struct tps65217 *tps; + struct regulator_init_data *reg_data; struct tps65217_board *pdata = client->dev.platform_data; int i, ret; unsigned int version; + if (!pdata && client->dev.of_node) + pdata = tps65217_parse_dt(client); + tps = devm_kzalloc(&client->dev, sizeof(*tps), GFP_KERNEL); if (!tps) return -ENOMEM; @@ -182,8 +242,9 @@ static int __devinit tps65217_probe(struct i2c_client *client, } pdev->dev.parent = tps->dev; - platform_device_add_data(pdev, &pdata->tps65217_init_data[i], - sizeof(pdata->tps65217_init_data[i])); + pdev->dev.of_node = pdata->of_node[i]; + reg_data = pdata->tps65217_init_data[i]; + platform_device_add_data(pdev, reg_data, sizeof(*reg_data)); tps->regulator_pdev[i] = pdev; platform_device_add(pdev); @@ -212,6 +273,8 @@ MODULE_DEVICE_TABLE(i2c, tps65217_id_table); static struct i2c_driver tps65217_driver = { .driver = { .name = "tps65217", + .owner = THIS_MODULE, + .of_match_table = of_match_ptr(tps65217_of_match), }, .id_table = tps65217_id_table, .probe = tps65217_probe, diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index 7de13891e49e..783fcd7365bc 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -1147,7 +1147,7 @@ static int mei_pci_resume(struct device *device) err = request_threaded_irq(pdev->irq, NULL, mei_interrupt_thread_handler, - 0, mei_driver_name, dev); + IRQF_ONESHOT, mei_driver_name, dev); else err = request_threaded_irq(pdev->irq, mei_interrupt_quick_handler, diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c index 17bbacb1b4b1..87b251ab6ec5 100644 --- a/drivers/misc/sgi-xp/xpc_uv.c +++ b/drivers/misc/sgi-xp/xpc_uv.c @@ -452,9 +452,9 @@ xpc_handle_activate_mq_msg_uv(struct xpc_partition *part, if (msg->activate_gru_mq_desc_gpa != part_uv->activate_gru_mq_desc_gpa) { - spin_lock_irqsave(&part_uv->flags_lock, irq_flags); + spin_lock(&part_uv->flags_lock); part_uv->flags &= ~XPC_P_CACHED_ACTIVATE_GRU_MQ_DESC_UV; - spin_unlock_irqrestore(&part_uv->flags_lock, irq_flags); + spin_unlock(&part_uv->flags_lock); part_uv->activate_gru_mq_desc_gpa = msg->activate_gru_mq_desc_gpa; } diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 276d21ce6bc1..f1c84decb192 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -850,9 +850,7 @@ out: goto retry; if (!err) mmc_blk_reset_success(md, type); - spin_lock_irq(&md->lock); - __blk_end_request(req, err, blk_rq_bytes(req)); - spin_unlock_irq(&md->lock); + blk_end_request(req, err, blk_rq_bytes(req)); return err ? 0 : 1; } @@ -934,9 +932,7 @@ out_retry: if (!err) mmc_blk_reset_success(md, type); out: - spin_lock_irq(&md->lock); - __blk_end_request(req, err, blk_rq_bytes(req)); - spin_unlock_irq(&md->lock); + blk_end_request(req, err, blk_rq_bytes(req)); return err ? 0 : 1; } @@ -951,9 +947,7 @@ static int mmc_blk_issue_flush(struct mmc_queue *mq, struct request *req) if (ret) ret = -EIO; - spin_lock_irq(&md->lock); - __blk_end_request_all(req, ret); - spin_unlock_irq(&md->lock); + blk_end_request_all(req, ret); return ret ? 0 : 1; } @@ -1252,14 +1246,10 @@ static int mmc_blk_cmd_err(struct mmc_blk_data *md, struct mmc_card *card, blocks = mmc_sd_num_wr_blocks(card); if (blocks != (u32)-1) { - spin_lock_irq(&md->lock); - ret = __blk_end_request(req, 0, blocks << 9); - spin_unlock_irq(&md->lock); + ret = blk_end_request(req, 0, blocks << 9); } } else { - spin_lock_irq(&md->lock); - ret = __blk_end_request(req, 0, brq->data.bytes_xfered); - spin_unlock_irq(&md->lock); + ret = blk_end_request(req, 0, brq->data.bytes_xfered); } return ret; } @@ -1311,10 +1301,8 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) * A block was successfully transferred. */ mmc_blk_reset_success(md, type); - spin_lock_irq(&md->lock); - ret = __blk_end_request(req, 0, + ret = blk_end_request(req, 0, brq->data.bytes_xfered); - spin_unlock_irq(&md->lock); /* * If the blk_end_request function returns non-zero even * though all data has been transferred and no errors @@ -1364,10 +1352,8 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) * time, so we only reach here after trying to * read a single sector. */ - spin_lock_irq(&md->lock); - ret = __blk_end_request(req, -EIO, + ret = blk_end_request(req, -EIO, brq->data.blksz); - spin_unlock_irq(&md->lock); if (!ret) goto start_new_req; break; @@ -1388,12 +1374,10 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) return 1; cmd_abort: - spin_lock_irq(&md->lock); if (mmc_card_removed(card)) req->cmd_flags |= REQ_QUIET; while (ret) - ret = __blk_end_request(req, -EIO, blk_rq_cur_bytes(req)); - spin_unlock_irq(&md->lock); + ret = blk_end_request(req, -EIO, blk_rq_cur_bytes(req)); start_new_req: if (rqc) { @@ -1417,9 +1401,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req) ret = mmc_blk_part_switch(card, md); if (ret) { if (req) { - spin_lock_irq(&md->lock); - __blk_end_request_all(req, -EIO); - spin_unlock_irq(&md->lock); + blk_end_request_all(req, -EIO); } ret = 0; goto out; diff --git a/drivers/mmc/core/Makefile b/drivers/mmc/core/Makefile index dca4428380f1..38ed210ce2f3 100644 --- a/drivers/mmc/core/Makefile +++ b/drivers/mmc/core/Makefile @@ -7,6 +7,6 @@ mmc_core-y := core.o bus.o host.o \ mmc.o mmc_ops.o sd.o sd_ops.o \ sdio.o sdio_ops.o sdio_bus.o \ sdio_cis.o sdio_io.o sdio_irq.o \ - quirks.o cd-gpio.o + quirks.o slot-gpio.o mmc_core-$(CONFIG_DEBUG_FS) += debugfs.o diff --git a/drivers/mmc/core/cd-gpio.c b/drivers/mmc/core/cd-gpio.c deleted file mode 100644 index f13e38deceac..000000000000 --- a/drivers/mmc/core/cd-gpio.c +++ /dev/null @@ -1,83 +0,0 @@ -/* - * Generic GPIO card-detect helper - * - * Copyright (C) 2011, Guennadi Liakhovetski <g.liakhovetski@gmx.de> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/err.h> -#include <linux/gpio.h> -#include <linux/interrupt.h> -#include <linux/jiffies.h> -#include <linux/mmc/cd-gpio.h> -#include <linux/mmc/host.h> -#include <linux/module.h> -#include <linux/slab.h> - -struct mmc_cd_gpio { - unsigned int gpio; - char label[0]; -}; - -static irqreturn_t mmc_cd_gpio_irqt(int irq, void *dev_id) -{ - /* Schedule a card detection after a debounce timeout */ - mmc_detect_change(dev_id, msecs_to_jiffies(100)); - return IRQ_HANDLED; -} - -int mmc_cd_gpio_request(struct mmc_host *host, unsigned int gpio) -{ - size_t len = strlen(dev_name(host->parent)) + 4; - struct mmc_cd_gpio *cd; - int irq = gpio_to_irq(gpio); - int ret; - - if (irq < 0) - return irq; - - cd = kmalloc(sizeof(*cd) + len, GFP_KERNEL); - if (!cd) - return -ENOMEM; - - snprintf(cd->label, len, "%s cd", dev_name(host->parent)); - - ret = gpio_request_one(gpio, GPIOF_DIR_IN, cd->label); - if (ret < 0) - goto egpioreq; - - ret = request_threaded_irq(irq, NULL, mmc_cd_gpio_irqt, - IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING, - cd->label, host); - if (ret < 0) - goto eirqreq; - - cd->gpio = gpio; - host->hotplug.irq = irq; - host->hotplug.handler_priv = cd; - - return 0; - -eirqreq: - gpio_free(gpio); -egpioreq: - kfree(cd); - return ret; -} -EXPORT_SYMBOL(mmc_cd_gpio_request); - -void mmc_cd_gpio_free(struct mmc_host *host) -{ - struct mmc_cd_gpio *cd = host->hotplug.handler_priv; - - if (!cd) - return; - - free_irq(host->hotplug.irq, host); - gpio_free(cd->gpio); - kfree(cd); -} -EXPORT_SYMBOL(mmc_cd_gpio_free); diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 0b6141d29dbd..8ac5246e2ab2 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -404,6 +404,7 @@ int mmc_interrupt_hpi(struct mmc_card *card) { int err; u32 status; + unsigned long prg_wait; BUG_ON(!card); @@ -419,30 +420,38 @@ int mmc_interrupt_hpi(struct mmc_card *card) goto out; } - /* - * If the card status is in PRG-state, we can send the HPI command. - */ - if (R1_CURRENT_STATE(status) == R1_STATE_PRG) { - do { - /* - * We don't know when the HPI command will finish - * processing, so we need to resend HPI until out - * of prg-state, and keep checking the card status - * with SEND_STATUS. If a timeout error occurs when - * sending the HPI command, we are already out of - * prg-state. - */ - err = mmc_send_hpi_cmd(card, &status); - if (err) - pr_debug("%s: abort HPI (%d error)\n", - mmc_hostname(card->host), err); + switch (R1_CURRENT_STATE(status)) { + case R1_STATE_IDLE: + case R1_STATE_READY: + case R1_STATE_STBY: + /* + * In idle states, HPI is not needed and the caller + * can issue the next intended command immediately + */ + goto out; + case R1_STATE_PRG: + break; + default: + /* In all other states, it's illegal to issue HPI */ + pr_debug("%s: HPI cannot be sent. Card state=%d\n", + mmc_hostname(card->host), R1_CURRENT_STATE(status)); + err = -EINVAL; + goto out; + } - err = mmc_send_status(card, &status); - if (err) - break; - } while (R1_CURRENT_STATE(status) == R1_STATE_PRG); - } else - pr_debug("%s: Left prg-state\n", mmc_hostname(card->host)); + err = mmc_send_hpi_cmd(card, &status); + if (err) + goto out; + + prg_wait = jiffies + msecs_to_jiffies(card->ext_csd.out_of_int_time); + do { + err = mmc_send_status(card, &status); + + if (!err && R1_CURRENT_STATE(status) == R1_STATE_TRAN) + break; + if (time_after(jiffies, prg_wait)) + err = -ETIMEDOUT; + } while (!err); out: mmc_release_host(card->host); @@ -941,7 +950,7 @@ int mmc_regulator_get_ocrmask(struct regulator *supply) return result; } -EXPORT_SYMBOL(mmc_regulator_get_ocrmask); +EXPORT_SYMBOL_GPL(mmc_regulator_get_ocrmask); /** * mmc_regulator_set_ocr - set regulator to match host->ios voltage @@ -1011,7 +1020,30 @@ int mmc_regulator_set_ocr(struct mmc_host *mmc, "could not set regulator OCR (%d)\n", result); return result; } -EXPORT_SYMBOL(mmc_regulator_set_ocr); +EXPORT_SYMBOL_GPL(mmc_regulator_set_ocr); + +int mmc_regulator_get_supply(struct mmc_host *mmc) +{ + struct device *dev = mmc_dev(mmc); + struct regulator *supply; + int ret; + + supply = devm_regulator_get(dev, "vmmc"); + mmc->supply.vmmc = supply; + mmc->supply.vqmmc = devm_regulator_get(dev, "vqmmc"); + + if (IS_ERR(supply)) + return PTR_ERR(supply); + + ret = mmc_regulator_get_ocrmask(supply); + if (ret > 0) + mmc->ocr_avail = ret; + else + dev_warn(mmc_dev(mmc), "Failed getting OCR mask: %d\n", ret); + + return 0; +} +EXPORT_SYMBOL_GPL(mmc_regulator_get_supply); #endif /* CONFIG_REGULATOR */ @@ -1180,6 +1212,9 @@ static void mmc_power_up(struct mmc_host *host) host->ios.timing = MMC_TIMING_LEGACY; mmc_set_ios(host); + /* Set signal voltage to 3.3V */ + mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_330, false); + /* * This delay should be sufficient to allow the power supply * to reach the minimum voltage. @@ -1931,9 +1966,6 @@ static int mmc_rescan_try_freq(struct mmc_host *host, unsigned freq) */ mmc_hw_reset_for_init(host); - /* Initialization should be done at 3.3 V I/O voltage. */ - mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_330, 0); - /* * sdio_reset sends CMD52 to reset card. Since we do not know * if the card is being re-initialized, just send it. CMD52 @@ -2075,6 +2107,7 @@ void mmc_rescan(struct work_struct *work) void mmc_start_host(struct mmc_host *host) { host->f_init = max(freqs[0], host->f_min); + host->rescan_disable = 0; mmc_power_up(host); mmc_detect_change(host, 0); } @@ -2088,6 +2121,7 @@ void mmc_stop_host(struct mmc_host *host) spin_unlock_irqrestore(&host->lock, flags); #endif + host->rescan_disable = 1; cancel_delayed_work_sync(&host->detect); mmc_flush_scheduled_work(); diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index 91c84c7a1829..597f189b4427 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -32,6 +32,7 @@ static void mmc_host_classdev_release(struct device *dev) { struct mmc_host *host = cls_dev_to_mmc_host(dev); + mutex_destroy(&host->slot.lock); kfree(host); } @@ -312,6 +313,8 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) if (!host) return NULL; + /* scanning will be enabled when we're ready */ + host->rescan_disable = 1; spin_lock(&mmc_host_lock); err = idr_get_new(&mmc_host_idr, host, &host->index); spin_unlock(&mmc_host_lock); @@ -327,6 +330,9 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) mmc_host_clk_init(host); + mutex_init(&host->slot.lock); + host->slot.cd_irq = -EINVAL; + spin_lock_init(&host->lock); init_waitqueue_head(&host->wq); INIT_DELAYED_WORK(&host->detect, mmc_rescan); diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 258b203397aa..396b25891bb9 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -717,10 +717,6 @@ static int mmc_select_powerclass(struct mmc_card *card, card->ext_csd.generic_cmd6_time); } - if (err) - pr_err("%s: power class selection for ext_csd_bus_width %d" - " failed\n", mmc_hostname(card->host), bus_width); - return err; } @@ -822,9 +818,6 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr, if (!mmc_host_is_spi(host)) mmc_set_bus_mode(host, MMC_BUSMODE_OPENDRAIN); - /* Initialization should be done at 3.3 V I/O voltage. */ - mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_330, 0); - /* * Since we're changing the OCR value, we seem to * need to tell some cards to go back to the idle @@ -1104,7 +1097,9 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr, EXT_CSD_BUS_WIDTH_8 : EXT_CSD_BUS_WIDTH_4; err = mmc_select_powerclass(card, ext_csd_bits, ext_csd); if (err) - goto err; + pr_warning("%s: power class selection to bus width %d" + " failed\n", mmc_hostname(card->host), + 1 << bus_width); } /* @@ -1136,7 +1131,10 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr, err = mmc_select_powerclass(card, ext_csd_bits[idx][0], ext_csd); if (err) - goto err; + pr_warning("%s: power class selection to " + "bus width %d failed\n", + mmc_hostname(card->host), + 1 << bus_width); err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_BUS_WIDTH, @@ -1164,7 +1162,10 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr, err = mmc_select_powerclass(card, ext_csd_bits[idx][1], ext_csd); if (err) - goto err; + pr_warning("%s: power class selection to " + "bus width %d ddr %d failed\n", + mmc_hostname(card->host), + 1 << bus_width, ddr); err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_BUS_WIDTH, diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c index 69370f494e05..0ed2cc5f35b6 100644 --- a/drivers/mmc/core/mmc_ops.c +++ b/drivers/mmc/core/mmc_ops.c @@ -569,7 +569,6 @@ int mmc_send_hpi_cmd(struct mmc_card *card, u32 *status) cmd.opcode = opcode; cmd.arg = card->rca << 16 | 1; - cmd.cmd_timeout_ms = card->ext_csd.out_of_int_time; err = mmc_wait_for_cmd(card->host, &cmd, 0); if (err) { diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index b2b43f624b9e..74972c241dff 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -244,7 +244,7 @@ static int mmc_read_ssr(struct mmc_card *card) * bitfield positions accordingly. */ au = UNSTUFF_BITS(ssr, 428 - 384, 4); - if (au > 0 || au <= 9) { + if (au > 0 && au <= 9) { card->ssr.au = 1 << (au + 4); es = UNSTUFF_BITS(ssr, 408 - 384, 16); et = UNSTUFF_BITS(ssr, 402 - 384, 6); @@ -290,8 +290,12 @@ static int mmc_read_switch(struct mmc_card *card) return -ENOMEM; } - /* Find out the supported Bus Speed Modes. */ - err = mmc_sd_switch(card, 0, 0, 1, status); + /* + * Find out the card's support bits with a mode 0 operation. + * The argument does not matter, as the support bits do not + * change with the arguments. + */ + err = mmc_sd_switch(card, 0, 0, 0, status); if (err) { /* * If the host or the card can't do the switch, @@ -312,46 +316,8 @@ static int mmc_read_switch(struct mmc_card *card) if (card->scr.sda_spec3) { card->sw_caps.sd3_bus_mode = status[13]; - - /* Find out Driver Strengths supported by the card */ - err = mmc_sd_switch(card, 0, 2, 1, status); - if (err) { - /* - * If the host or the card can't do the switch, - * fail more gracefully. - */ - if (err != -EINVAL && err != -ENOSYS && err != -EFAULT) - goto out; - - pr_warning("%s: problem reading " - "Driver Strength.\n", - mmc_hostname(card->host)); - err = 0; - - goto out; - } - + /* Driver Strengths supported by the card */ card->sw_caps.sd3_drv_type = status[9]; - - /* Find out Current Limits supported by the card */ - err = mmc_sd_switch(card, 0, 3, 1, status); - if (err) { - /* - * If the host or the card can't do the switch, - * fail more gracefully. - */ - if (err != -EINVAL && err != -ENOSYS && err != -EFAULT) - goto out; - - pr_warning("%s: problem reading " - "Current Limit.\n", - mmc_hostname(card->host)); - err = 0; - - goto out; - } - - card->sw_caps.sd3_curr_limit = status[7]; } out: @@ -551,60 +517,80 @@ static int sd_set_bus_speed_mode(struct mmc_card *card, u8 *status) return 0; } +/* Get host's max current setting at its current voltage */ +static u32 sd_get_host_max_current(struct mmc_host *host) +{ + u32 voltage, max_current; + + voltage = 1 << host->ios.vdd; + switch (voltage) { + case MMC_VDD_165_195: + max_current = host->max_current_180; + break; + case MMC_VDD_29_30: + case MMC_VDD_30_31: + max_current = host->max_current_300; + break; + case MMC_VDD_32_33: + case MMC_VDD_33_34: + max_current = host->max_current_330; + break; + default: + max_current = 0; + } + + return max_current; +} + static int sd_set_current_limit(struct mmc_card *card, u8 *status) { - int current_limit = 0; + int current_limit = SD_SET_CURRENT_NO_CHANGE; int err; + u32 max_current; /* * Current limit switch is only defined for SDR50, SDR104, and DDR50 - * bus speed modes. For other bus speed modes, we set the default - * current limit of 200mA. + * bus speed modes. For other bus speed modes, we do not change the + * current limit. */ - if ((card->sd_bus_speed == UHS_SDR50_BUS_SPEED) || - (card->sd_bus_speed == UHS_SDR104_BUS_SPEED) || - (card->sd_bus_speed == UHS_DDR50_BUS_SPEED)) { - if (card->host->caps & MMC_CAP_MAX_CURRENT_800) { - if (card->sw_caps.sd3_curr_limit & SD_MAX_CURRENT_800) - current_limit = SD_SET_CURRENT_LIMIT_800; - else if (card->sw_caps.sd3_curr_limit & - SD_MAX_CURRENT_600) - current_limit = SD_SET_CURRENT_LIMIT_600; - else if (card->sw_caps.sd3_curr_limit & - SD_MAX_CURRENT_400) - current_limit = SD_SET_CURRENT_LIMIT_400; - else if (card->sw_caps.sd3_curr_limit & - SD_MAX_CURRENT_200) - current_limit = SD_SET_CURRENT_LIMIT_200; - } else if (card->host->caps & MMC_CAP_MAX_CURRENT_600) { - if (card->sw_caps.sd3_curr_limit & SD_MAX_CURRENT_600) - current_limit = SD_SET_CURRENT_LIMIT_600; - else if (card->sw_caps.sd3_curr_limit & - SD_MAX_CURRENT_400) - current_limit = SD_SET_CURRENT_LIMIT_400; - else if (card->sw_caps.sd3_curr_limit & - SD_MAX_CURRENT_200) - current_limit = SD_SET_CURRENT_LIMIT_200; - } else if (card->host->caps & MMC_CAP_MAX_CURRENT_400) { - if (card->sw_caps.sd3_curr_limit & SD_MAX_CURRENT_400) - current_limit = SD_SET_CURRENT_LIMIT_400; - else if (card->sw_caps.sd3_curr_limit & - SD_MAX_CURRENT_200) - current_limit = SD_SET_CURRENT_LIMIT_200; - } else if (card->host->caps & MMC_CAP_MAX_CURRENT_200) { - if (card->sw_caps.sd3_curr_limit & SD_MAX_CURRENT_200) - current_limit = SD_SET_CURRENT_LIMIT_200; - } - } else + if ((card->sd_bus_speed != UHS_SDR50_BUS_SPEED) && + (card->sd_bus_speed != UHS_SDR104_BUS_SPEED) && + (card->sd_bus_speed != UHS_DDR50_BUS_SPEED)) + return 0; + + /* + * Host has different current capabilities when operating at + * different voltages, so find out its max current first. + */ + max_current = sd_get_host_max_current(card->host); + + /* + * We only check host's capability here, if we set a limit that is + * higher than the card's maximum current, the card will be using its + * maximum current, e.g. if the card's maximum current is 300ma, and + * when we set current limit to 200ma, the card will draw 200ma, and + * when we set current limit to 400/600/800ma, the card will draw its + * maximum 300ma from the host. + */ + if (max_current >= 800) + current_limit = SD_SET_CURRENT_LIMIT_800; + else if (max_current >= 600) + current_limit = SD_SET_CURRENT_LIMIT_600; + else if (max_current >= 400) + current_limit = SD_SET_CURRENT_LIMIT_400; + else if (max_current >= 200) current_limit = SD_SET_CURRENT_LIMIT_200; - err = mmc_sd_switch(card, 1, 3, current_limit, status); - if (err) - return err; + if (current_limit != SD_SET_CURRENT_NO_CHANGE) { + err = mmc_sd_switch(card, 1, 3, current_limit, status); + if (err) + return err; - if (((status[15] >> 4) & 0x0F) != current_limit) - pr_warning("%s: Problem setting current limit!\n", - mmc_hostname(card->host)); + if (((status[15] >> 4) & 0x0F) != current_limit) + pr_warning("%s: Problem setting current limit!\n", + mmc_hostname(card->host)); + + } return 0; } @@ -726,6 +712,7 @@ struct device_type sd_type = { int mmc_sd_get_cid(struct mmc_host *host, u32 ocr, u32 *cid, u32 *rocr) { int err; + u32 max_current; /* * Since we're changing the OCR value, we seem to @@ -753,9 +740,12 @@ int mmc_sd_get_cid(struct mmc_host *host, u32 ocr, u32 *cid, u32 *rocr) MMC_CAP_UHS_SDR50 | MMC_CAP_UHS_SDR104 | MMC_CAP_UHS_DDR50)) ocr |= SD_OCR_S18R; - /* If the host can supply more than 150mA, XPC should be set to 1. */ - if (host->caps & (MMC_CAP_SET_XPC_330 | MMC_CAP_SET_XPC_300 | - MMC_CAP_SET_XPC_180)) + /* + * If the host can supply more than 150mA at current voltage, + * XPC should be set to 1. + */ + max_current = sd_get_host_max_current(host); + if (max_current > 150) ocr |= SD_OCR_XPC; try_again: @@ -911,9 +901,6 @@ static int mmc_sd_init_card(struct mmc_host *host, u32 ocr, BUG_ON(!host); WARN_ON(!host->claimed); - /* The initialization should be done at 3.3 V I/O voltage. */ - mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_330, 0); - err = mmc_sd_get_cid(host, ocr, cid, &rocr); if (err) return err; diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c index 41c5fd8848f4..d4619e2ec030 100644 --- a/drivers/mmc/core/sdio.c +++ b/drivers/mmc/core/sdio.c @@ -591,9 +591,6 @@ static int mmc_sdio_init_card(struct mmc_host *host, u32 ocr, * Inform the card of the voltage */ if (!powered_resume) { - /* The initialization should be done at 3.3 V I/O voltage. */ - mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_330, 0); - err = mmc_send_io_op_cond(host, host->ocr, &ocr); if (err) goto err; @@ -1006,10 +1003,6 @@ static int mmc_sdio_power_restore(struct mmc_host *host) * restore the correct voltage setting of the card. */ - /* The initialization should be done at 3.3 V I/O voltage. */ - if (!mmc_card_keep_power(host)) - mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_330, 0); - sdio_reset(host); mmc_go_idle(host); mmc_send_if_cond(host, host->ocr_avail); diff --git a/drivers/mmc/core/sdio_cis.c b/drivers/mmc/core/sdio_cis.c index f1c7ed8f4d85..8e94e555b788 100644 --- a/drivers/mmc/core/sdio_cis.c +++ b/drivers/mmc/core/sdio_cis.c @@ -313,7 +313,7 @@ static int sdio_read_cis(struct mmc_card *card, struct sdio_func *func) if (ret == -ENOENT) { /* warn about unknown tuples */ - pr_warning("%s: queuing unknown" + pr_warn_ratelimited("%s: queuing unknown" " CIS tuple 0x%02x (%u bytes)\n", mmc_hostname(card->host), tpl_code, tpl_link); diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c new file mode 100644 index 000000000000..058242916cef --- /dev/null +++ b/drivers/mmc/core/slot-gpio.c @@ -0,0 +1,188 @@ +/* + * Generic GPIO card-detect helper + * + * Copyright (C) 2011, Guennadi Liakhovetski <g.liakhovetski@gmx.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/err.h> +#include <linux/gpio.h> +#include <linux/interrupt.h> +#include <linux/jiffies.h> +#include <linux/mmc/host.h> +#include <linux/mmc/slot-gpio.h> +#include <linux/module.h> +#include <linux/slab.h> + +struct mmc_gpio { + int ro_gpio; + int cd_gpio; + char *ro_label; + char cd_label[0]; +}; + +static irqreturn_t mmc_gpio_cd_irqt(int irq, void *dev_id) +{ + /* Schedule a card detection after a debounce timeout */ + mmc_detect_change(dev_id, msecs_to_jiffies(100)); + return IRQ_HANDLED; +} + +static int mmc_gpio_alloc(struct mmc_host *host) +{ + size_t len = strlen(dev_name(host->parent)) + 4; + struct mmc_gpio *ctx; + + mutex_lock(&host->slot.lock); + + ctx = host->slot.handler_priv; + if (!ctx) { + /* + * devm_kzalloc() can be called after device_initialize(), even + * before device_add(), i.e., between mmc_alloc_host() and + * mmc_add_host() + */ + ctx = devm_kzalloc(&host->class_dev, sizeof(*ctx) + 2 * len, + GFP_KERNEL); + if (ctx) { + ctx->ro_label = ctx->cd_label + len; + snprintf(ctx->cd_label, len, "%s cd", dev_name(host->parent)); + snprintf(ctx->ro_label, len, "%s ro", dev_name(host->parent)); + ctx->cd_gpio = -EINVAL; + ctx->ro_gpio = -EINVAL; + host->slot.handler_priv = ctx; + } + } + + mutex_unlock(&host->slot.lock); + + return ctx ? 0 : -ENOMEM; +} + +int mmc_gpio_get_ro(struct mmc_host *host) +{ + struct mmc_gpio *ctx = host->slot.handler_priv; + + if (!ctx || !gpio_is_valid(ctx->ro_gpio)) + return -ENOSYS; + + return !gpio_get_value_cansleep(ctx->ro_gpio) ^ + !!(host->caps2 & MMC_CAP2_RO_ACTIVE_HIGH); +} +EXPORT_SYMBOL(mmc_gpio_get_ro); + +int mmc_gpio_get_cd(struct mmc_host *host) +{ + struct mmc_gpio *ctx = host->slot.handler_priv; + + if (!ctx || !gpio_is_valid(ctx->cd_gpio)) + return -ENOSYS; + + return !gpio_get_value_cansleep(ctx->cd_gpio) ^ + !!(host->caps2 & MMC_CAP2_CD_ACTIVE_HIGH); +} +EXPORT_SYMBOL(mmc_gpio_get_cd); + +int mmc_gpio_request_ro(struct mmc_host *host, unsigned int gpio) +{ + struct mmc_gpio *ctx; + int ret; + + if (!gpio_is_valid(gpio)) + return -EINVAL; + + ret = mmc_gpio_alloc(host); + if (ret < 0) + return ret; + + ctx = host->slot.handler_priv; + + return gpio_request_one(gpio, GPIOF_DIR_IN, ctx->ro_label); +} +EXPORT_SYMBOL(mmc_gpio_request_ro); + +int mmc_gpio_request_cd(struct mmc_host *host, unsigned int gpio) +{ + struct mmc_gpio *ctx; + int irq = gpio_to_irq(gpio); + int ret; + + ret = mmc_gpio_alloc(host); + if (ret < 0) + return ret; + + ctx = host->slot.handler_priv; + + ret = gpio_request_one(gpio, GPIOF_DIR_IN, ctx->cd_label); + if (ret < 0) + /* + * don't bother freeing memory. It might still get used by other + * slot functions, in any case it will be freed, when the device + * is destroyed. + */ + return ret; + + /* + * Even if gpio_to_irq() returns a valid IRQ number, the platform might + * still prefer to poll, e.g., because that IRQ number is already used + * by another unit and cannot be shared. + */ + if (irq >= 0 && host->caps & MMC_CAP_NEEDS_POLL) + irq = -EINVAL; + + if (irq >= 0) { + ret = request_threaded_irq(irq, NULL, mmc_gpio_cd_irqt, + IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + ctx->cd_label, host); + if (ret < 0) + irq = ret; + } + + host->slot.cd_irq = irq; + + if (irq < 0) + host->caps |= MMC_CAP_NEEDS_POLL; + + ctx->cd_gpio = gpio; + + return 0; +} +EXPORT_SYMBOL(mmc_gpio_request_cd); + +void mmc_gpio_free_ro(struct mmc_host *host) +{ + struct mmc_gpio *ctx = host->slot.handler_priv; + int gpio; + + if (!ctx || !gpio_is_valid(ctx->ro_gpio)) + return; + + gpio = ctx->ro_gpio; + ctx->ro_gpio = -EINVAL; + + gpio_free(gpio); +} +EXPORT_SYMBOL(mmc_gpio_free_ro); + +void mmc_gpio_free_cd(struct mmc_host *host) +{ + struct mmc_gpio *ctx = host->slot.handler_priv; + int gpio; + + if (!ctx || !gpio_is_valid(ctx->cd_gpio)) + return; + + if (host->slot.cd_irq >= 0) { + free_irq(host->slot.cd_irq, host); + host->slot.cd_irq = -EINVAL; + } + + gpio = ctx->cd_gpio; + ctx->cd_gpio = -EINVAL; + + gpio_free(gpio); +} +EXPORT_SYMBOL(mmc_gpio_free_cd); diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c index f2c115e06438..322412cec4ee 100644 --- a/drivers/mmc/host/atmel-mci.c +++ b/drivers/mmc/host/atmel-mci.c @@ -391,11 +391,17 @@ static int atmci_regs_show(struct seq_file *s, void *v) clk_disable(host->mck); spin_unlock_bh(&host->lock); - seq_printf(s, "MR:\t0x%08x%s%s CLKDIV=%u\n", + seq_printf(s, "MR:\t0x%08x%s%s ", buf[ATMCI_MR / 4], buf[ATMCI_MR / 4] & ATMCI_MR_RDPROOF ? " RDPROOF" : "", - buf[ATMCI_MR / 4] & ATMCI_MR_WRPROOF ? " WRPROOF" : "", - buf[ATMCI_MR / 4] & 0xff); + buf[ATMCI_MR / 4] & ATMCI_MR_WRPROOF ? " WRPROOF" : ""); + if (host->caps.has_odd_clk_div) + seq_printf(s, "{CLKDIV,CLKODD}=%u\n", + ((buf[ATMCI_MR / 4] & 0xff) << 1) + | ((buf[ATMCI_MR / 4] >> 16) & 1)); + else + seq_printf(s, "CLKDIV=%u\n", + (buf[ATMCI_MR / 4] & 0xff)); seq_printf(s, "DTOR:\t0x%08x\n", buf[ATMCI_DTOR / 4]); seq_printf(s, "SDCR:\t0x%08x\n", buf[ATMCI_SDCR / 4]); seq_printf(s, "ARGR:\t0x%08x\n", buf[ATMCI_ARGR / 4]); @@ -1685,7 +1691,6 @@ static void atmci_tasklet_func(unsigned long priv) dev_dbg(&host->pdev->dev, "FSM: cmd ready\n"); host->cmd = NULL; - host->data = NULL; data->bytes_xfered = data->blocks * data->blksz; data->error = 0; atmci_command_complete(host, mrq->stop); @@ -1699,6 +1704,7 @@ static void atmci_tasklet_func(unsigned long priv) atmci_writel(host, ATMCI_IER, ATMCI_NOTBUSY); state = STATE_WAITING_NOTBUSY; } + host->data = NULL; break; case STATE_END_REQUEST: diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index 1ca5e72ceb65..72dc3cde646d 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -405,11 +405,23 @@ static void dw_mci_idmac_start_dma(struct dw_mci *host, unsigned int sg_len) static int dw_mci_idmac_init(struct dw_mci *host) { struct idmac_desc *p; - int i; + int i, dma_support; /* Number of descriptors in the ring buffer */ host->ring_size = PAGE_SIZE / sizeof(struct idmac_desc); + /* Check if Hardware Configuration Register has support for DMA */ + dma_support = (mci_readl(host, HCON) >> 16) & 0x3; + + if (!dma_support || dma_support > 2) { + dev_err(&host->dev, + "Host Controller does not support IDMA Tx.\n"); + host->dma_ops = NULL; + return -ENODEV; + } + + dev_info(&host->dev, "Using internal DMA controller.\n"); + /* Forward link the descriptor list */ for (i = 0, p = host->sg_cpu; i < host->ring_size - 1; i++, p++) p->des3 = host->sg_dma + (sizeof(struct idmac_desc) * (i + 1)); @@ -1876,7 +1888,6 @@ static void dw_mci_init_dma(struct dw_mci *host) /* Determine which DMA interface to use */ #ifdef CONFIG_MMC_DW_IDMAC host->dma_ops = &dw_mci_idmac_ops; - dev_info(&host->dev, "Using internal DMA controller.\n"); #endif if (!host->dma_ops) @@ -2175,7 +2186,7 @@ int dw_mci_resume(struct dw_mci *host) return ret; } - if (host->dma_ops->init) + if (host->use_dma && host->dma_ops->init) host->dma_ops->init(host); /* Restore the old value at FIFOTH register */ diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c index 277161d279b8..a51f9309ffbb 100644 --- a/drivers/mmc/host/mxs-mmc.c +++ b/drivers/mmc/host/mxs-mmc.c @@ -164,16 +164,23 @@ struct mxs_mmc_host { spinlock_t lock; int sdio_irq_en; int wp_gpio; + bool wp_inverted; }; static int mxs_mmc_get_ro(struct mmc_host *mmc) { struct mxs_mmc_host *host = mmc_priv(mmc); + int ret; if (!gpio_is_valid(host->wp_gpio)) return -EINVAL; - return gpio_get_value(host->wp_gpio); + ret = gpio_get_value(host->wp_gpio); + + if (host->wp_inverted) + ret = !ret; + + return ret; } static int mxs_mmc_get_cd(struct mmc_host *mmc) @@ -707,6 +714,8 @@ static int mxs_mmc_probe(struct platform_device *pdev) struct pinctrl *pinctrl; int ret = 0, irq_err, irq_dma; dma_cap_mask_t mask; + struct regulator *reg_vmmc; + enum of_gpio_flags flags; iores = platform_get_resource(pdev, IORESOURCE_MEM, 0); dmares = platform_get_resource(pdev, IORESOURCE_DMA, 0); @@ -747,6 +756,16 @@ static int mxs_mmc_probe(struct platform_device *pdev) host->mmc = mmc; host->sdio_irq_en = 0; + reg_vmmc = devm_regulator_get(&pdev->dev, "vmmc"); + if (!IS_ERR(reg_vmmc)) { + ret = regulator_enable(reg_vmmc); + if (ret) { + dev_err(&pdev->dev, + "Failed to enable vmmc regulator: %d\n", ret); + goto out_mmc_free; + } + } + pinctrl = devm_pinctrl_get_select_default(&pdev->dev); if (IS_ERR(pinctrl)) { ret = PTR_ERR(pinctrl); @@ -785,7 +804,10 @@ static int mxs_mmc_probe(struct platform_device *pdev) mmc->caps |= MMC_CAP_4_BIT_DATA; else if (bus_width == 8) mmc->caps |= MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA; - host->wp_gpio = of_get_named_gpio(np, "wp-gpios", 0); + host->wp_gpio = of_get_named_gpio_flags(np, "wp-gpios", 0, + &flags); + if (flags & OF_GPIO_ACTIVE_LOW) + host->wp_inverted = 1; } else { if (pdata->flags & SLOTF_8_BIT_CAPABLE) mmc->caps |= MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA; diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 389a3eedfc24..bc28627af66b 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -1089,7 +1089,7 @@ static int omap_hsmmc_switch_opcond(struct omap_hsmmc_host *host, int vdd) /* Disable the clocks */ pm_runtime_put_sync(host->dev); if (host->dbclk) - clk_disable(host->dbclk); + clk_disable_unprepare(host->dbclk); /* Turn the power off */ ret = mmc_slot(host).set_power(host->dev, host->slot_id, 0, 0); @@ -1100,7 +1100,7 @@ static int omap_hsmmc_switch_opcond(struct omap_hsmmc_host *host, int vdd) vdd); pm_runtime_get_sync(host->dev); if (host->dbclk) - clk_enable(host->dbclk); + clk_prepare_enable(host->dbclk); if (ret != 0) goto err; @@ -1899,7 +1899,7 @@ static int __devinit omap_hsmmc_probe(struct platform_device *pdev) if (IS_ERR(host->dbclk)) { dev_warn(mmc_dev(host->mmc), "Failed to get debounce clk\n"); host->dbclk = NULL; - } else if (clk_enable(host->dbclk) != 0) { + } else if (clk_prepare_enable(host->dbclk) != 0) { dev_warn(mmc_dev(host->mmc), "Failed to enable debounce clk\n"); clk_put(host->dbclk); host->dbclk = NULL; @@ -1931,6 +1931,7 @@ static int __devinit omap_hsmmc_probe(struct platform_device *pdev) res = platform_get_resource_byname(pdev, IORESOURCE_DMA, "tx"); if (!res) { dev_err(mmc_dev(host->mmc), "cannot get DMA TX channel\n"); + ret = -ENXIO; goto err_irq; } host->dma_line_tx = res->start; @@ -1938,6 +1939,7 @@ static int __devinit omap_hsmmc_probe(struct platform_device *pdev) res = platform_get_resource_byname(pdev, IORESOURCE_DMA, "rx"); if (!res) { dev_err(mmc_dev(host->mmc), "cannot get DMA RX channel\n"); + ret = -ENXIO; goto err_irq; } host->dma_line_rx = res->start; @@ -2023,7 +2025,7 @@ err_irq: pm_runtime_disable(host->dev); clk_put(host->fclk); if (host->dbclk) { - clk_disable(host->dbclk); + clk_disable_unprepare(host->dbclk); clk_put(host->dbclk); } err1: @@ -2058,7 +2060,7 @@ static int __devexit omap_hsmmc_remove(struct platform_device *pdev) pm_runtime_disable(host->dev); clk_put(host->fclk); if (host->dbclk) { - clk_disable(host->dbclk); + clk_disable_unprepare(host->dbclk); clk_put(host->dbclk); } @@ -2116,7 +2118,7 @@ static int omap_hsmmc_suspend(struct device *dev) } if (host->dbclk) - clk_disable(host->dbclk); + clk_disable_unprepare(host->dbclk); err: pm_runtime_put_sync(host->dev); return ret; @@ -2137,7 +2139,7 @@ static int omap_hsmmc_resume(struct device *dev) pm_runtime_get_sync(host->dev); if (host->dbclk) - clk_enable(host->dbclk); + clk_prepare_enable(host->dbclk); if (!(host->mmc->pm_flags & MMC_PM_KEEP_POWER)) omap_hsmmc_conf_bus_power(host); diff --git a/drivers/mmc/host/s3cmci.c b/drivers/mmc/host/s3cmci.c index c3622a69f432..bd5a5cce122c 100644 --- a/drivers/mmc/host/s3cmci.c +++ b/drivers/mmc/host/s3cmci.c @@ -26,7 +26,6 @@ #include <mach/dma.h> #include <mach/regs-sdi.h> -#include <mach/regs-gpio.h> #include <plat/mci.h> @@ -1237,12 +1236,9 @@ static void s3cmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) switch (ios->power_mode) { case MMC_POWER_ON: case MMC_POWER_UP: - s3c2410_gpio_cfgpin(S3C2410_GPE(5), S3C2410_GPE5_SDCLK); - s3c2410_gpio_cfgpin(S3C2410_GPE(6), S3C2410_GPE6_SDCMD); - s3c2410_gpio_cfgpin(S3C2410_GPE(7), S3C2410_GPE7_SDDAT0); - s3c2410_gpio_cfgpin(S3C2410_GPE(8), S3C2410_GPE8_SDDAT1); - s3c2410_gpio_cfgpin(S3C2410_GPE(9), S3C2410_GPE9_SDDAT2); - s3c2410_gpio_cfgpin(S3C2410_GPE(10), S3C2410_GPE10_SDDAT3); + /* Configure GPE5...GPE10 pins in SD mode */ + s3c_gpio_cfgall_range(S3C2410_GPE(5), 6, S3C_GPIO_SFN(2), + S3C_GPIO_PULL_NONE); if (host->pdata->set_power) host->pdata->set_power(ios->power_mode, ios->vdd); diff --git a/drivers/mmc/host/sdhci-dove.c b/drivers/mmc/host/sdhci-dove.c index 177f697b5835..a6e53a1ebb08 100644 --- a/drivers/mmc/host/sdhci-dove.c +++ b/drivers/mmc/host/sdhci-dove.c @@ -20,11 +20,17 @@ */ #include <linux/io.h> +#include <linux/clk.h> +#include <linux/err.h> #include <linux/module.h> #include <linux/mmc/host.h> #include "sdhci-pltfm.h" +struct sdhci_dove_priv { + struct clk *clk; +}; + static u16 sdhci_dove_readw(struct sdhci_host *host, int reg) { u16 ret; @@ -66,16 +72,57 @@ static struct sdhci_pltfm_data sdhci_dove_pdata = { .quirks = SDHCI_QUIRK_NO_SIMULT_VDD_AND_POWER | SDHCI_QUIRK_NO_BUSY_IRQ | SDHCI_QUIRK_BROKEN_TIMEOUT_VAL | - SDHCI_QUIRK_FORCE_DMA, + SDHCI_QUIRK_FORCE_DMA | + SDHCI_QUIRK_NO_HISPD_BIT, }; static int __devinit sdhci_dove_probe(struct platform_device *pdev) { - return sdhci_pltfm_register(pdev, &sdhci_dove_pdata); + struct sdhci_host *host; + struct sdhci_pltfm_host *pltfm_host; + struct sdhci_dove_priv *priv; + int ret; + + ret = sdhci_pltfm_register(pdev, &sdhci_dove_pdata); + if (ret) + goto sdhci_dove_register_fail; + + priv = devm_kzalloc(&pdev->dev, sizeof(struct sdhci_dove_priv), + GFP_KERNEL); + if (!priv) { + dev_err(&pdev->dev, "unable to allocate private data"); + ret = -ENOMEM; + goto sdhci_dove_allocate_fail; + } + + host = platform_get_drvdata(pdev); + pltfm_host = sdhci_priv(host); + pltfm_host->priv = priv; + + priv->clk = clk_get(&pdev->dev, NULL); + if (!IS_ERR(priv->clk)) + clk_prepare_enable(priv->clk); + return 0; + +sdhci_dove_allocate_fail: + sdhci_pltfm_unregister(pdev); +sdhci_dove_register_fail: + return ret; } static int __devexit sdhci_dove_remove(struct platform_device *pdev) { + struct sdhci_host *host = platform_get_drvdata(pdev); + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_dove_priv *priv = pltfm_host->priv; + + if (priv->clk) { + if (!IS_ERR(priv->clk)) { + clk_disable_unprepare(priv->clk); + clk_put(priv->clk); + } + devm_kfree(&pdev->dev, priv->clk); + } return sdhci_pltfm_unregister(pdev); } diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index ebbe984e5d00..e23f8134591c 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -299,6 +299,8 @@ static void esdhc_writew_le(struct sdhci_host *host, u16 val, int reg) static void esdhc_writeb_le(struct sdhci_host *host, u8 val, int reg) { + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct pltfm_imx_data *imx_data = pltfm_host->priv; u32 new_val; switch (reg) { @@ -315,8 +317,11 @@ static void esdhc_writeb_le(struct sdhci_host *host, u8 val, int reg) SDHCI_CTRL_D3CD); /* ensure the endianess */ new_val |= ESDHC_HOST_CONTROL_LE; - /* DMA mode bits are shifted */ - new_val |= (val & SDHCI_CTRL_DMA_MASK) << 5; + /* bits 8&9 are reserved on mx25 */ + if (!is_imx25_esdhc(imx_data)) { + /* DMA mode bits are shifted */ + new_val |= (val & SDHCI_CTRL_DMA_MASK) << 5; + } esdhc_clrset_le(host, 0xffff, new_val, reg); return; diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c index 69ef0beae104..504da715a41a 100644 --- a/drivers/mmc/host/sdhci-pci.c +++ b/drivers/mmc/host/sdhci-pci.c @@ -157,6 +157,7 @@ static const struct sdhci_pci_fixes sdhci_ene_714 = { static const struct sdhci_pci_fixes sdhci_cafe = { .quirks = SDHCI_QUIRK_NO_SIMULT_VDD_AND_POWER | SDHCI_QUIRK_NO_BUSY_IRQ | + SDHCI_QUIRK_BROKEN_CARD_DETECTION | SDHCI_QUIRK_BROKEN_TIMEOUT_VAL, }; diff --git a/drivers/mmc/host/sdhci-pxav2.c b/drivers/mmc/host/sdhci-pxav2.c index dbb75bfbcffb..b6ee8857e226 100644 --- a/drivers/mmc/host/sdhci-pxav2.c +++ b/drivers/mmc/host/sdhci-pxav2.c @@ -28,6 +28,9 @@ #include <linux/mmc/host.h> #include <linux/platform_data/pxa_sdhci.h> #include <linux/slab.h> +#include <linux/of.h> +#include <linux/of_device.h> + #include "sdhci.h" #include "sdhci-pltfm.h" @@ -121,6 +124,48 @@ static struct sdhci_ops pxav2_sdhci_ops = { .platform_8bit_width = pxav2_mmc_set_width, }; +#ifdef CONFIG_OF +static const struct of_device_id sdhci_pxav2_of_match[] = { + { + .compatible = "mrvl,pxav2-mmc", + }, + {}, +}; +MODULE_DEVICE_TABLE(of, sdhci_pxav2_of_match); + +static struct sdhci_pxa_platdata *pxav2_get_mmc_pdata(struct device *dev) +{ + struct sdhci_pxa_platdata *pdata; + struct device_node *np = dev->of_node; + u32 bus_width; + u32 clk_delay_cycles; + + pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); + if (!pdata) + return NULL; + + if (of_find_property(np, "non-removable", NULL)) + pdata->flags |= PXA_FLAG_CARD_PERMANENT; + + of_property_read_u32(np, "bus-width", &bus_width); + if (bus_width == 8) + pdata->flags |= PXA_FLAG_SD_8_BIT_CAPABLE_SLOT; + + of_property_read_u32(np, "mrvl,clk-delay-cycles", &clk_delay_cycles); + if (clk_delay_cycles > 0) { + pdata->clk_delay_sel = 1; + pdata->clk_delay_cycles = clk_delay_cycles; + } + + return pdata; +} +#else +static inline struct sdhci_pxa_platdata *pxav2_get_mmc_pdata(struct device *dev) +{ + return NULL; +} +#endif + static int __devinit sdhci_pxav2_probe(struct platform_device *pdev) { struct sdhci_pltfm_host *pltfm_host; @@ -128,6 +173,8 @@ static int __devinit sdhci_pxav2_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct sdhci_host *host = NULL; struct sdhci_pxa *pxa = NULL; + const struct of_device_id *match; + int ret; struct clk *clk; @@ -156,6 +203,10 @@ static int __devinit sdhci_pxav2_probe(struct platform_device *pdev) | SDHCI_QUIRK_BROKEN_TIMEOUT_VAL | SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN; + match = of_match_device(of_match_ptr(sdhci_pxav2_of_match), &pdev->dev); + if (match) { + pdata = pxav2_get_mmc_pdata(dev); + } if (pdata) { if (pdata->flags & PXA_FLAG_CARD_PERMANENT) { /* on-chip device */ @@ -218,6 +269,9 @@ static struct platform_driver sdhci_pxav2_driver = { .driver = { .name = "sdhci-pxav2", .owner = THIS_MODULE, +#ifdef CONFIG_OF + .of_match_table = sdhci_pxav2_of_match, +#endif .pm = SDHCI_PLTFM_PMOPS, }, .probe = sdhci_pxav2_probe, diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c index f29695683556..07fe3834fe0b 100644 --- a/drivers/mmc/host/sdhci-pxav3.c +++ b/drivers/mmc/host/sdhci-pxav3.c @@ -28,6 +28,9 @@ #include <linux/slab.h> #include <linux/delay.h> #include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> + #include "sdhci.h" #include "sdhci-pltfm.h" @@ -164,6 +167,46 @@ static struct sdhci_ops pxav3_sdhci_ops = { .platform_send_init_74_clocks = pxav3_gen_init_74_clocks, }; +#ifdef CONFIG_OF +static const struct of_device_id sdhci_pxav3_of_match[] = { + { + .compatible = "mrvl,pxav3-mmc", + }, + {}, +}; +MODULE_DEVICE_TABLE(of, sdhci_pxav3_of_match); + +static struct sdhci_pxa_platdata *pxav3_get_mmc_pdata(struct device *dev) +{ + struct sdhci_pxa_platdata *pdata; + struct device_node *np = dev->of_node; + u32 bus_width; + u32 clk_delay_cycles; + + pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); + if (!pdata) + return NULL; + + if (of_find_property(np, "non-removable", NULL)) + pdata->flags |= PXA_FLAG_CARD_PERMANENT; + + of_property_read_u32(np, "bus-width", &bus_width); + if (bus_width == 8) + pdata->flags |= PXA_FLAG_SD_8_BIT_CAPABLE_SLOT; + + of_property_read_u32(np, "mrvl,clk-delay-cycles", &clk_delay_cycles); + if (clk_delay_cycles > 0) + pdata->clk_delay_cycles = clk_delay_cycles; + + return pdata; +} +#else +static inline struct sdhci_pxa_platdata *pxav3_get_mmc_pdata(struct device *dev) +{ + return NULL; +} +#endif + static int __devinit sdhci_pxav3_probe(struct platform_device *pdev) { struct sdhci_pltfm_host *pltfm_host; @@ -171,6 +214,8 @@ static int __devinit sdhci_pxav3_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct sdhci_host *host = NULL; struct sdhci_pxa *pxa = NULL; + const struct of_device_id *match; + int ret; struct clk *clk; @@ -202,6 +247,10 @@ static int __devinit sdhci_pxav3_probe(struct platform_device *pdev) /* enable 1/8V DDR capable */ host->mmc->caps |= MMC_CAP_1_8V_DDR; + match = of_match_device(of_match_ptr(sdhci_pxav3_of_match), &pdev->dev); + if (match) + pdata = pxav3_get_mmc_pdata(dev); + if (pdata) { if (pdata->flags & PXA_FLAG_CARD_PERMANENT) { /* on-chip device */ @@ -263,6 +312,9 @@ static int __devexit sdhci_pxav3_remove(struct platform_device *pdev) static struct platform_driver sdhci_pxav3_driver = { .driver = { .name = "sdhci-pxav3", +#ifdef CONFIG_OF + .of_match_table = sdhci_pxav3_of_match, +#endif .owner = THIS_MODULE, .pm = SDHCI_PLTFM_PMOPS, }, diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index f4b8b4db3a9a..9a11dc39921c 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -27,6 +27,7 @@ #include <linux/mmc/mmc.h> #include <linux/mmc/host.h> +#include <linux/mmc/card.h> #include "sdhci.h" @@ -244,6 +245,19 @@ static void sdhci_init(struct sdhci_host *host, int soft) static void sdhci_reinit(struct sdhci_host *host) { sdhci_init(host, 0); + /* + * Retuning stuffs are affected by different cards inserted and only + * applicable to UHS-I cards. So reset these fields to their initial + * value when card is removed. + */ + if (host->flags & SDHCI_USING_RETUNING_TIMER) { + host->flags &= ~SDHCI_USING_RETUNING_TIMER; + + del_timer_sync(&host->tuning_timer); + host->flags &= ~SDHCI_NEEDS_RETUNING; + host->mmc->max_blk_count = + (host->quirks & SDHCI_QUIRK_NO_MULTIBLOCK) ? 1 : 65535; + } sdhci_enable_card_detection(host); } @@ -1245,6 +1259,7 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq) struct sdhci_host *host; bool present; unsigned long flags; + u32 tuning_opcode; host = mmc_priv(mmc); @@ -1292,8 +1307,12 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq) */ if ((host->flags & SDHCI_NEEDS_RETUNING) && !(present_state & (SDHCI_DOING_WRITE | SDHCI_DOING_READ))) { + /* eMMC uses cmd21 while sd and sdio use cmd19 */ + tuning_opcode = mmc->card->type == MMC_TYPE_MMC ? + MMC_SEND_TUNING_BLOCK_HS200 : + MMC_SEND_TUNING_BLOCK; spin_unlock_irqrestore(&host->lock, flags); - sdhci_execute_tuning(mmc, mrq->cmd->opcode); + sdhci_execute_tuning(mmc, tuning_opcode); spin_lock_irqsave(&host->lock, flags); /* Restore original mmc_request structure */ @@ -1663,11 +1682,15 @@ static int sdhci_do_start_signal_voltage_switch(struct sdhci_host *host, pwr = sdhci_readb(host, SDHCI_POWER_CONTROL); pwr &= ~SDHCI_POWER_ON; sdhci_writeb(host, pwr, SDHCI_POWER_CONTROL); + if (host->vmmc) + regulator_disable(host->vmmc); /* Wait for 1ms as per the spec */ usleep_range(1000, 1500); pwr |= SDHCI_POWER_ON; sdhci_writeb(host, pwr, SDHCI_POWER_CONTROL); + if (host->vmmc) + regulator_enable(host->vmmc); pr_info(DRIVER_NAME ": Switching to 1.8V signalling " "voltage failed, retrying with S18R set to 0\n"); @@ -1855,6 +1878,7 @@ out: */ if (!(host->flags & SDHCI_NEEDS_RETUNING) && host->tuning_count && (host->tuning_mode == SDHCI_TUNING_MODE_1)) { + host->flags |= SDHCI_USING_RETUNING_TIMER; mod_timer(&host->tuning_timer, jiffies + host->tuning_count * HZ); /* Tuning mode 1 limits the maximum data length to 4MB */ @@ -1872,10 +1896,10 @@ out: * try tuning again at a later time, when the re-tuning timer expires. * So for these controllers, we return 0. Since there might be other * controllers who do not have this capability, we return error for - * them. + * them. SDHCI_USING_RETUNING_TIMER means the host is currently using + * a retuning timer to do the retuning for the card. */ - if (err && host->tuning_count && - host->tuning_mode == SDHCI_TUNING_MODE_1) + if (err && (host->flags & SDHCI_USING_RETUNING_TIMER)) err = 0; sdhci_clear_set_irqs(host, SDHCI_INT_DATA_AVAIL, ier); @@ -2382,7 +2406,6 @@ out: int sdhci_suspend_host(struct sdhci_host *host) { int ret; - bool has_tuning_timer; if (host->ops->platform_suspend) host->ops->platform_suspend(host); @@ -2390,16 +2413,14 @@ int sdhci_suspend_host(struct sdhci_host *host) sdhci_disable_card_detection(host); /* Disable tuning since we are suspending */ - has_tuning_timer = host->version >= SDHCI_SPEC_300 && - host->tuning_count && host->tuning_mode == SDHCI_TUNING_MODE_1; - if (has_tuning_timer) { + if (host->flags & SDHCI_USING_RETUNING_TIMER) { del_timer_sync(&host->tuning_timer); host->flags &= ~SDHCI_NEEDS_RETUNING; } ret = mmc_suspend_host(host->mmc); if (ret) { - if (has_tuning_timer) { + if (host->flags & SDHCI_USING_RETUNING_TIMER) { host->flags |= SDHCI_NEEDS_RETUNING; mod_timer(&host->tuning_timer, jiffies + host->tuning_count * HZ); @@ -2450,8 +2471,7 @@ int sdhci_resume_host(struct sdhci_host *host) host->ops->platform_resume(host); /* Set the re-tuning expiration flag */ - if ((host->version >= SDHCI_SPEC_300) && host->tuning_count && - (host->tuning_mode == SDHCI_TUNING_MODE_1)) + if (host->flags & SDHCI_USING_RETUNING_TIMER) host->flags |= SDHCI_NEEDS_RETUNING; return ret; @@ -2490,8 +2510,7 @@ int sdhci_runtime_suspend_host(struct sdhci_host *host) int ret = 0; /* Disable tuning since we are suspending */ - if (host->version >= SDHCI_SPEC_300 && - host->tuning_mode == SDHCI_TUNING_MODE_1) { + if (host->flags & SDHCI_USING_RETUNING_TIMER) { del_timer_sync(&host->tuning_timer); host->flags &= ~SDHCI_NEEDS_RETUNING; } @@ -2532,8 +2551,7 @@ int sdhci_runtime_resume_host(struct sdhci_host *host) sdhci_do_enable_preset_value(host, true); /* Set the re-tuning expiration flag */ - if ((host->version >= SDHCI_SPEC_300) && host->tuning_count && - (host->tuning_mode == SDHCI_TUNING_MODE_1)) + if (host->flags & SDHCI_USING_RETUNING_TIMER) host->flags |= SDHCI_NEEDS_RETUNING; spin_lock_irqsave(&host->lock, flags); @@ -2584,7 +2602,7 @@ EXPORT_SYMBOL_GPL(sdhci_alloc_host); int sdhci_add_host(struct sdhci_host *host) { struct mmc_host *mmc; - u32 caps[2]; + u32 caps[2] = {0, 0}; u32 max_current_caps; unsigned int ocr_avail; int ret; @@ -2614,8 +2632,10 @@ int sdhci_add_host(struct sdhci_host *host) caps[0] = (host->quirks & SDHCI_QUIRK_MISSING_CAPS) ? host->caps : sdhci_readl(host, SDHCI_CAPABILITIES); - caps[1] = (host->version >= SDHCI_SPEC_300) ? - sdhci_readl(host, SDHCI_CAPABILITIES_1) : 0; + if (host->version >= SDHCI_SPEC_300) + caps[1] = (host->quirks & SDHCI_QUIRK_MISSING_CAPS) ? + host->caps1 : + sdhci_readl(host, SDHCI_CAPABILITIES_1); if (host->quirks & SDHCI_QUIRK_FORCE_DMA) host->flags |= SDHCI_USE_SDMA; @@ -2779,7 +2799,7 @@ int sdhci_add_host(struct sdhci_host *host) mmc->caps |= MMC_CAP_SD_HIGHSPEED | MMC_CAP_MMC_HIGHSPEED; if ((host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) && - mmc_card_is_removable(mmc)) + !(host->mmc->caps & MMC_CAP_NONREMOVABLE)) mmc->caps |= MMC_CAP_NEEDS_POLL; /* Any UHS-I mode in caps implies SDR12 and SDR25 support. */ @@ -2837,6 +2857,30 @@ int sdhci_add_host(struct sdhci_host *host) SDHCI_RETUNING_MODE_SHIFT; ocr_avail = 0; + + host->vmmc = regulator_get(mmc_dev(mmc), "vmmc"); + if (IS_ERR(host->vmmc)) { + pr_info("%s: no vmmc regulator found\n", mmc_hostname(mmc)); + host->vmmc = NULL; + } + +#ifdef CONFIG_REGULATOR + if (host->vmmc) { + ret = regulator_is_supported_voltage(host->vmmc, 3300000, + 3300000); + if ((ret <= 0) || (!(caps[0] & SDHCI_CAN_VDD_330))) + caps[0] &= ~SDHCI_CAN_VDD_330; + ret = regulator_is_supported_voltage(host->vmmc, 3000000, + 3000000); + if ((ret <= 0) || (!(caps[0] & SDHCI_CAN_VDD_300))) + caps[0] &= ~SDHCI_CAN_VDD_300; + ret = regulator_is_supported_voltage(host->vmmc, 1800000, + 1800000); + if ((ret <= 0) || (!(caps[0] & SDHCI_CAN_VDD_180))) + caps[0] &= ~SDHCI_CAN_VDD_180; + } +#endif /* CONFIG_REGULATOR */ + /* * According to SD Host Controller spec v3.00, if the Host System * can afford more than 150mA, Host Driver should set XPC to 1. Also @@ -2845,55 +2889,45 @@ int sdhci_add_host(struct sdhci_host *host) * value. */ max_current_caps = sdhci_readl(host, SDHCI_MAX_CURRENT); + if (!max_current_caps && host->vmmc) { + u32 curr = regulator_get_current_limit(host->vmmc); + if (curr > 0) { + + /* convert to SDHCI_MAX_CURRENT format */ + curr = curr/1000; /* convert to mA */ + curr = curr/SDHCI_MAX_CURRENT_MULTIPLIER; + + curr = min_t(u32, curr, SDHCI_MAX_CURRENT_LIMIT); + max_current_caps = + (curr << SDHCI_MAX_CURRENT_330_SHIFT) | + (curr << SDHCI_MAX_CURRENT_300_SHIFT) | + (curr << SDHCI_MAX_CURRENT_180_SHIFT); + } + } if (caps[0] & SDHCI_CAN_VDD_330) { - int max_current_330; - ocr_avail |= MMC_VDD_32_33 | MMC_VDD_33_34; - max_current_330 = ((max_current_caps & + mmc->max_current_330 = ((max_current_caps & SDHCI_MAX_CURRENT_330_MASK) >> SDHCI_MAX_CURRENT_330_SHIFT) * SDHCI_MAX_CURRENT_MULTIPLIER; - - if (max_current_330 > 150) - mmc->caps |= MMC_CAP_SET_XPC_330; } if (caps[0] & SDHCI_CAN_VDD_300) { - int max_current_300; - ocr_avail |= MMC_VDD_29_30 | MMC_VDD_30_31; - max_current_300 = ((max_current_caps & + mmc->max_current_300 = ((max_current_caps & SDHCI_MAX_CURRENT_300_MASK) >> SDHCI_MAX_CURRENT_300_SHIFT) * SDHCI_MAX_CURRENT_MULTIPLIER; - - if (max_current_300 > 150) - mmc->caps |= MMC_CAP_SET_XPC_300; } if (caps[0] & SDHCI_CAN_VDD_180) { - int max_current_180; - ocr_avail |= MMC_VDD_165_195; - max_current_180 = ((max_current_caps & + mmc->max_current_180 = ((max_current_caps & SDHCI_MAX_CURRENT_180_MASK) >> SDHCI_MAX_CURRENT_180_SHIFT) * SDHCI_MAX_CURRENT_MULTIPLIER; - - if (max_current_180 > 150) - mmc->caps |= MMC_CAP_SET_XPC_180; - - /* Maximum current capabilities of the host at 1.8V */ - if (max_current_180 >= 800) - mmc->caps |= MMC_CAP_MAX_CURRENT_800; - else if (max_current_180 >= 600) - mmc->caps |= MMC_CAP_MAX_CURRENT_600; - else if (max_current_180 >= 400) - mmc->caps |= MMC_CAP_MAX_CURRENT_400; - else - mmc->caps |= MMC_CAP_MAX_CURRENT_200; } mmc->ocr_avail = ocr_avail; @@ -2992,13 +3026,10 @@ int sdhci_add_host(struct sdhci_host *host) ret = request_irq(host->irq, sdhci_irq, IRQF_SHARED, mmc_hostname(mmc), host); - if (ret) + if (ret) { + pr_err("%s: Failed to request IRQ %d: %d\n", + mmc_hostname(mmc), host->irq, ret); goto untasklet; - - host->vmmc = regulator_get(mmc_dev(mmc), "vmmc"); - if (IS_ERR(host->vmmc)) { - pr_info("%s: no vmmc regulator found\n", mmc_hostname(mmc)); - host->vmmc = NULL; } sdhci_init(host, 0); @@ -3016,8 +3047,11 @@ int sdhci_add_host(struct sdhci_host *host) host->led.brightness_set = sdhci_led_control; ret = led_classdev_register(mmc_dev(mmc), &host->led); - if (ret) + if (ret) { + pr_err("%s: Failed to register LED device: %d\n", + mmc_hostname(mmc), ret); goto reset; + } #endif mmiowb(); @@ -3081,8 +3115,6 @@ void sdhci_remove_host(struct sdhci_host *host, int dead) free_irq(host->irq, host); del_timer_sync(&host->timer); - if (host->version >= SDHCI_SPEC_300) - del_timer_sync(&host->tuning_timer); tasklet_kill(&host->card_tasklet); tasklet_kill(&host->finish_tasklet); diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h index f761f23d2a28..97653ea8942b 100644 --- a/drivers/mmc/host/sdhci.h +++ b/drivers/mmc/host/sdhci.h @@ -205,6 +205,7 @@ #define SDHCI_CAPABILITIES_1 0x44 #define SDHCI_MAX_CURRENT 0x48 +#define SDHCI_MAX_CURRENT_LIMIT 0xFF #define SDHCI_MAX_CURRENT_330_MASK 0x0000FF #define SDHCI_MAX_CURRENT_330_SHIFT 0 #define SDHCI_MAX_CURRENT_300_MASK 0x00FF00 diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c index 724b35e85a26..b2af7136cd27 100644 --- a/drivers/mmc/host/sh_mmcif.c +++ b/drivers/mmc/host/sh_mmcif.c @@ -54,6 +54,8 @@ #include <linux/mmc/mmc.h> #include <linux/mmc/sdio.h> #include <linux/mmc/sh_mmcif.h> +#include <linux/mmc/slot-gpio.h> +#include <linux/mod_devicetable.h> #include <linux/pagemap.h> #include <linux/platform_device.h> #include <linux/pm_qos.h> @@ -384,6 +386,9 @@ static void sh_mmcif_request_dma(struct sh_mmcif_host *host, struct sh_dmae_slave *tx, *rx; host->dma_active = false; + if (!pdata) + return; + /* We can only either use DMA for both Tx and Rx or not use it at all */ if (pdata->dma) { dev_warn(&host->pd->dev, @@ -444,13 +449,14 @@ static void sh_mmcif_release_dma(struct sh_mmcif_host *host) static void sh_mmcif_clock_control(struct sh_mmcif_host *host, unsigned int clk) { struct sh_mmcif_plat_data *p = host->pd->dev.platform_data; + bool sup_pclk = p ? p->sup_pclk : false; sh_mmcif_bitclr(host, MMCIF_CE_CLK_CTRL, CLK_ENABLE); sh_mmcif_bitclr(host, MMCIF_CE_CLK_CTRL, CLK_CLEAR); if (!clk) return; - if (p->sup_pclk && clk == host->clk) + if (sup_pclk && clk == host->clk) sh_mmcif_bitset(host, MMCIF_CE_CLK_CTRL, CLK_SUP_PCLK); else sh_mmcif_bitset(host, MMCIF_CE_CLK_CTRL, CLK_CLEAR & @@ -892,21 +898,15 @@ static void sh_mmcif_request(struct mmc_host *mmc, struct mmc_request *mrq) switch (mrq->cmd->opcode) { /* MMCIF does not support SD/SDIO command */ - case SD_IO_SEND_OP_COND: + case MMC_SLEEP_AWAKE: /* = SD_IO_SEND_OP_COND (5) */ + case MMC_SEND_EXT_CSD: /* = SD_SEND_IF_COND (8) */ + if ((mrq->cmd->flags & MMC_CMD_MASK) != MMC_CMD_BCR) + break; case MMC_APP_CMD: host->state = STATE_IDLE; mrq->cmd->error = -ETIMEDOUT; mmc_request_done(mmc, mrq); return; - case MMC_SEND_EXT_CSD: /* = SD_SEND_IF_COND (8) */ - if (!mrq->data) { - /* send_if_cond cmd (not support) */ - host->state = STATE_IDLE; - mrq->cmd->error = -ETIMEDOUT; - mmc_request_done(mmc, mrq); - return; - } - break; default: break; } @@ -916,10 +916,35 @@ static void sh_mmcif_request(struct mmc_host *mmc, struct mmc_request *mrq) sh_mmcif_start_cmd(host, mrq); } +static int sh_mmcif_clk_update(struct sh_mmcif_host *host) +{ + int ret = clk_enable(host->hclk); + + if (!ret) { + host->clk = clk_get_rate(host->hclk); + host->mmc->f_max = host->clk / 2; + host->mmc->f_min = host->clk / 512; + } + + return ret; +} + +static void sh_mmcif_set_power(struct sh_mmcif_host *host, struct mmc_ios *ios) +{ + struct sh_mmcif_plat_data *pd = host->pd->dev.platform_data; + struct mmc_host *mmc = host->mmc; + + if (pd && pd->set_pwr) + pd->set_pwr(host->pd, ios->power_mode != MMC_POWER_OFF); + if (!IS_ERR(mmc->supply.vmmc)) + /* Errors ignored... */ + mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, + ios->power_mode ? ios->vdd : 0); +} + static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) { struct sh_mmcif_host *host = mmc_priv(mmc); - struct sh_mmcif_plat_data *p = host->pd->dev.platform_data; unsigned long flags; spin_lock_irqsave(&host->lock, flags); @@ -937,6 +962,7 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) sh_mmcif_request_dma(host, host->pd->dev.platform_data); host->card_present = true; } + sh_mmcif_set_power(host, ios); } else if (ios->power_mode == MMC_POWER_OFF || !ios->clock) { /* clock stop */ sh_mmcif_clock_control(host, 0); @@ -948,9 +974,10 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) } if (host->power) { pm_runtime_put(&host->pd->dev); + clk_disable(host->hclk); host->power = false; - if (p->down_pwr && ios->power_mode == MMC_POWER_OFF) - p->down_pwr(host->pd); + if (ios->power_mode == MMC_POWER_OFF) + sh_mmcif_set_power(host, ios); } host->state = STATE_IDLE; return; @@ -958,8 +985,7 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) if (ios->clock) { if (!host->power) { - if (p->set_pwr) - p->set_pwr(host->pd, ios->power_mode); + sh_mmcif_clk_update(host); pm_runtime_get_sync(&host->pd->dev); host->power = true; sh_mmcif_sync_reset(host); @@ -975,8 +1001,12 @@ static int sh_mmcif_get_cd(struct mmc_host *mmc) { struct sh_mmcif_host *host = mmc_priv(mmc); struct sh_mmcif_plat_data *p = host->pd->dev.platform_data; + int ret = mmc_gpio_get_cd(mmc); + + if (ret >= 0) + return ret; - if (!p->get_cd) + if (!p || !p->get_cd) return -ENOSYS; else return p->get_cd(host->pd); @@ -1242,12 +1272,28 @@ static void mmcif_timeout_work(struct work_struct *work) mmc_request_done(host->mmc, mrq); } +static void sh_mmcif_init_ocr(struct sh_mmcif_host *host) +{ + struct sh_mmcif_plat_data *pd = host->pd->dev.platform_data; + struct mmc_host *mmc = host->mmc; + + mmc_regulator_get_supply(mmc); + + if (!pd) + return; + + if (!mmc->ocr_avail) + mmc->ocr_avail = pd->ocr; + else if (pd->ocr) + dev_warn(mmc_dev(mmc), "Platform OCR mask is ignored\n"); +} + static int __devinit sh_mmcif_probe(struct platform_device *pdev) { int ret = 0, irq[2]; struct mmc_host *mmc; struct sh_mmcif_host *host; - struct sh_mmcif_plat_data *pd; + struct sh_mmcif_plat_data *pd = pdev->dev.platform_data; struct resource *res; void __iomem *reg; char clk_name[8]; @@ -1268,42 +1314,26 @@ static int __devinit sh_mmcif_probe(struct platform_device *pdev) dev_err(&pdev->dev, "ioremap error.\n"); return -ENOMEM; } - pd = pdev->dev.platform_data; - if (!pd) { - dev_err(&pdev->dev, "sh_mmcif plat data error.\n"); - ret = -ENXIO; - goto clean_up; - } + mmc = mmc_alloc_host(sizeof(struct sh_mmcif_host), &pdev->dev); if (!mmc) { ret = -ENOMEM; - goto clean_up; + goto ealloch; } host = mmc_priv(mmc); host->mmc = mmc; host->addr = reg; host->timeout = 1000; - snprintf(clk_name, sizeof(clk_name), "mmc%d", pdev->id); - host->hclk = clk_get(&pdev->dev, clk_name); - if (IS_ERR(host->hclk)) { - dev_err(&pdev->dev, "cannot get clock \"%s\"\n", clk_name); - ret = PTR_ERR(host->hclk); - goto clean_up1; - } - clk_enable(host->hclk); - host->clk = clk_get_rate(host->hclk); host->pd = pdev; spin_lock_init(&host->lock); mmc->ops = &sh_mmcif_ops; - mmc->f_max = host->clk / 2; - mmc->f_min = host->clk / 512; - if (pd->ocr) - mmc->ocr_avail = pd->ocr; + sh_mmcif_init_ocr(host); + mmc->caps = MMC_CAP_MMC_HIGHSPEED; - if (pd->caps) + if (pd && pd->caps) mmc->caps |= pd->caps; mmc->max_segs = 32; mmc->max_blk_size = 512; @@ -1311,34 +1341,52 @@ static int __devinit sh_mmcif_probe(struct platform_device *pdev) mmc->max_blk_count = mmc->max_req_size / mmc->max_blk_size; mmc->max_seg_size = mmc->max_req_size; - sh_mmcif_sync_reset(host); platform_set_drvdata(pdev, host); pm_runtime_enable(&pdev->dev); host->power = false; + snprintf(clk_name, sizeof(clk_name), "mmc%d", pdev->id); + host->hclk = clk_get(&pdev->dev, clk_name); + if (IS_ERR(host->hclk)) { + ret = PTR_ERR(host->hclk); + dev_err(&pdev->dev, "cannot get clock \"%s\": %d\n", clk_name, ret); + goto eclkget; + } + ret = sh_mmcif_clk_update(host); + if (ret < 0) + goto eclkupdate; + ret = pm_runtime_resume(&pdev->dev); if (ret < 0) - goto clean_up2; + goto eresume; INIT_DELAYED_WORK(&host->timeout_work, mmcif_timeout_work); + sh_mmcif_sync_reset(host); sh_mmcif_writel(host->addr, MMCIF_CE_INT_MASK, MASK_ALL); ret = request_threaded_irq(irq[0], sh_mmcif_intr, sh_mmcif_irqt, 0, "sh_mmc:error", host); if (ret) { dev_err(&pdev->dev, "request_irq error (sh_mmc:error)\n"); - goto clean_up3; + goto ereqirq0; } ret = request_threaded_irq(irq[1], sh_mmcif_intr, sh_mmcif_irqt, 0, "sh_mmc:int", host); if (ret) { dev_err(&pdev->dev, "request_irq error (sh_mmc:int)\n"); - goto clean_up4; + goto ereqirq1; + } + + if (pd && pd->use_cd_gpio) { + ret = mmc_gpio_request_cd(mmc, pd->cd_gpio); + if (ret < 0) + goto erqcd; } + clk_disable(host->hclk); ret = mmc_add_host(mmc); if (ret < 0) - goto clean_up5; + goto emmcaddh; dev_pm_qos_expose_latency_limit(&pdev->dev, 100); @@ -1347,33 +1395,42 @@ static int __devinit sh_mmcif_probe(struct platform_device *pdev) sh_mmcif_readl(host->addr, MMCIF_CE_VERSION) & 0x0000ffff); return ret; -clean_up5: +emmcaddh: + if (pd && pd->use_cd_gpio) + mmc_gpio_free_cd(mmc); +erqcd: free_irq(irq[1], host); -clean_up4: +ereqirq1: free_irq(irq[0], host); -clean_up3: +ereqirq0: pm_runtime_suspend(&pdev->dev); -clean_up2: - pm_runtime_disable(&pdev->dev); +eresume: clk_disable(host->hclk); -clean_up1: +eclkupdate: + clk_put(host->hclk); +eclkget: + pm_runtime_disable(&pdev->dev); mmc_free_host(mmc); -clean_up: - if (reg) - iounmap(reg); +ealloch: + iounmap(reg); return ret; } static int __devexit sh_mmcif_remove(struct platform_device *pdev) { struct sh_mmcif_host *host = platform_get_drvdata(pdev); + struct sh_mmcif_plat_data *pd = pdev->dev.platform_data; int irq[2]; host->dying = true; + clk_enable(host->hclk); pm_runtime_get_sync(&pdev->dev); dev_pm_qos_hide_latency_limit(&pdev->dev); + if (pd && pd->use_cd_gpio) + mmc_gpio_free_cd(host->mmc); + mmc_remove_host(host->mmc); sh_mmcif_writel(host->addr, MMCIF_CE_INT_MASK, MASK_ALL); @@ -1395,9 +1452,9 @@ static int __devexit sh_mmcif_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); - clk_disable(host->hclk); mmc_free_host(host->mmc); pm_runtime_put_sync(&pdev->dev); + clk_disable(host->hclk); pm_runtime_disable(&pdev->dev); return 0; @@ -1406,24 +1463,18 @@ static int __devexit sh_mmcif_remove(struct platform_device *pdev) #ifdef CONFIG_PM static int sh_mmcif_suspend(struct device *dev) { - struct platform_device *pdev = to_platform_device(dev); - struct sh_mmcif_host *host = platform_get_drvdata(pdev); + struct sh_mmcif_host *host = dev_get_drvdata(dev); int ret = mmc_suspend_host(host->mmc); - if (!ret) { + if (!ret) sh_mmcif_writel(host->addr, MMCIF_CE_INT_MASK, MASK_ALL); - clk_disable(host->hclk); - } return ret; } static int sh_mmcif_resume(struct device *dev) { - struct platform_device *pdev = to_platform_device(dev); - struct sh_mmcif_host *host = platform_get_drvdata(pdev); - - clk_enable(host->hclk); + struct sh_mmcif_host *host = dev_get_drvdata(dev); return mmc_resume_host(host->mmc); } @@ -1432,6 +1483,12 @@ static int sh_mmcif_resume(struct device *dev) #define sh_mmcif_resume NULL #endif /* CONFIG_PM */ +static const struct of_device_id mmcif_of_match[] = { + { .compatible = "renesas,sh-mmcif" }, + { } +}; +MODULE_DEVICE_TABLE(of, mmcif_of_match); + static const struct dev_pm_ops sh_mmcif_dev_pm_ops = { .suspend = sh_mmcif_suspend, .resume = sh_mmcif_resume, @@ -1443,6 +1500,8 @@ static struct platform_driver sh_mmcif_driver = { .driver = { .name = DRIVER_NAME, .pm = &sh_mmcif_dev_pm_ops, + .owner = THIS_MODULE, + .of_match_table = mmcif_of_match, }, }; diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c index 934b68e9efc3..a842939e4655 100644 --- a/drivers/mmc/host/sh_mobile_sdhi.c +++ b/drivers/mmc/host/sh_mobile_sdhi.c @@ -21,6 +21,7 @@ #include <linux/kernel.h> #include <linux/clk.h> #include <linux/slab.h> +#include <linux/mod_devicetable.h> #include <linux/module.h> #include <linux/platform_device.h> #include <linux/mmc/host.h> @@ -39,22 +40,39 @@ struct sh_mobile_sdhi { struct tmio_mmc_dma dma_priv; }; +static int sh_mobile_sdhi_clk_enable(struct platform_device *pdev, unsigned int *f) +{ + struct mmc_host *mmc = dev_get_drvdata(&pdev->dev); + struct tmio_mmc_host *host = mmc_priv(mmc); + struct sh_mobile_sdhi *priv = container_of(host->pdata, struct sh_mobile_sdhi, mmc_data); + int ret = clk_enable(priv->clk); + if (ret < 0) + return ret; + + *f = clk_get_rate(priv->clk); + return 0; +} + +static void sh_mobile_sdhi_clk_disable(struct platform_device *pdev) +{ + struct mmc_host *mmc = dev_get_drvdata(&pdev->dev); + struct tmio_mmc_host *host = mmc_priv(mmc); + struct sh_mobile_sdhi *priv = container_of(host->pdata, struct sh_mobile_sdhi, mmc_data); + clk_disable(priv->clk); +} + static void sh_mobile_sdhi_set_pwr(struct platform_device *pdev, int state) { struct sh_mobile_sdhi_info *p = pdev->dev.platform_data; - if (p && p->set_pwr) - p->set_pwr(pdev, state); + p->set_pwr(pdev, state); } static int sh_mobile_sdhi_get_cd(struct platform_device *pdev) { struct sh_mobile_sdhi_info *p = pdev->dev.platform_data; - if (p && p->get_cd) - return p->get_cd(pdev); - else - return -ENOSYS; + return p->get_cd(pdev); } static int sh_mobile_sdhi_wait_idle(struct tmio_mmc_host *host) @@ -116,12 +134,14 @@ static int __devinit sh_mobile_sdhi_probe(struct platform_device *pdev) } mmc_data = &priv->mmc_data; - p->pdata = mmc_data; - if (p->init) { - ret = p->init(pdev, &sdhi_ops); - if (ret) - goto einit; + if (p) { + p->pdata = mmc_data; + if (p->init) { + ret = p->init(pdev, &sdhi_ops); + if (ret) + goto einit; + } } snprintf(clk_name, sizeof(clk_name), "sdhi%d", pdev->id); @@ -132,9 +152,8 @@ static int __devinit sh_mobile_sdhi_probe(struct platform_device *pdev) goto eclkget; } - mmc_data->hclk = clk_get_rate(priv->clk); - mmc_data->set_pwr = sh_mobile_sdhi_set_pwr; - mmc_data->get_cd = sh_mobile_sdhi_get_cd; + mmc_data->clk_enable = sh_mobile_sdhi_clk_enable; + mmc_data->clk_disable = sh_mobile_sdhi_clk_disable; mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED; if (p) { mmc_data->flags = p->tmio_flags; @@ -142,7 +161,12 @@ static int __devinit sh_mobile_sdhi_probe(struct platform_device *pdev) mmc_data->write16_hook = sh_mobile_sdhi_write16_hook; mmc_data->ocr_mask = p->tmio_ocr_mask; mmc_data->capabilities |= p->tmio_caps; + mmc_data->capabilities2 |= p->tmio_caps2; mmc_data->cd_gpio = p->cd_gpio; + if (p->set_pwr) + mmc_data->set_pwr = sh_mobile_sdhi_set_pwr; + if (p->get_cd) + mmc_data->get_cd = sh_mobile_sdhi_get_cd; if (p->dma_slave_tx > 0 && p->dma_slave_rx > 0) { priv->param_tx.slave_id = p->dma_slave_tx; @@ -248,7 +272,7 @@ eirq_card_detect: eprobe: clk_put(priv->clk); eclkget: - if (p->cleanup) + if (p && p->cleanup) p->cleanup(pdev); einit: kfree(priv); @@ -263,7 +287,8 @@ static int sh_mobile_sdhi_remove(struct platform_device *pdev) struct sh_mobile_sdhi_info *p = pdev->dev.platform_data; int i = 0, irq; - p->pdata = NULL; + if (p) + p->pdata = NULL; tmio_mmc_host_remove(host); @@ -276,7 +301,7 @@ static int sh_mobile_sdhi_remove(struct platform_device *pdev) clk_put(priv->clk); - if (p->cleanup) + if (p && p->cleanup) p->cleanup(pdev); kfree(priv); @@ -291,11 +316,18 @@ static const struct dev_pm_ops tmio_mmc_dev_pm_ops = { .runtime_resume = tmio_mmc_host_runtime_resume, }; +static const struct of_device_id sh_mobile_sdhi_of_match[] = { + { .compatible = "renesas,shmobile-sdhi" }, + { } +}; +MODULE_DEVICE_TABLE(of, sh_mobile_sdhi_of_match); + static struct platform_driver sh_mobile_sdhi_driver = { .driver = { .name = "sh_mobile_sdhi", .owner = THIS_MODULE, .pm = &tmio_mmc_dev_pm_ops, + .of_match_table = sh_mobile_sdhi_of_match, }, .probe = sh_mobile_sdhi_probe, .remove = __devexit_p(sh_mobile_sdhi_remove), diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c index 9a7996ade58e..0d8a9bbe30be 100644 --- a/drivers/mmc/host/tmio_mmc_pio.c +++ b/drivers/mmc/host/tmio_mmc_pio.c @@ -34,8 +34,9 @@ #include <linux/io.h> #include <linux/irq.h> #include <linux/mfd/tmio.h> -#include <linux/mmc/cd-gpio.h> #include <linux/mmc/host.h> +#include <linux/mmc/mmc.h> +#include <linux/mmc/slot-gpio.h> #include <linux/mmc/tmio.h> #include <linux/module.h> #include <linux/pagemap.h> @@ -305,8 +306,8 @@ static int tmio_mmc_start_command(struct tmio_mmc_host *host, struct mmc_command int c = cmd->opcode; u32 irq_mask = TMIO_MASK_CMD; - /* Command 12 is handled by hardware */ - if (cmd->opcode == 12 && !cmd->arg) { + /* CMD12 is handled by hardware */ + if (cmd->opcode == MMC_STOP_TRANSMISSION && !cmd->arg) { sd_ctrl_write16(host, CTL_STOP_INTERNAL_ACTION, 0x001); return 0; } @@ -449,7 +450,7 @@ void tmio_mmc_do_data_irq(struct tmio_mmc_host *host) } if (stop) { - if (stop->opcode == 12 && !stop->arg) + if (stop->opcode == MMC_STOP_TRANSMISSION && !stop->arg) sd_ctrl_write16(host, CTL_STOP_INTERNAL_ACTION, 0x000); else BUG(); @@ -751,6 +752,34 @@ fail: mmc_request_done(mmc, mrq); } +static int tmio_mmc_clk_update(struct mmc_host *mmc) +{ + struct tmio_mmc_host *host = mmc_priv(mmc); + struct tmio_mmc_data *pdata = host->pdata; + int ret; + + if (!pdata->clk_enable) + return -ENOTSUPP; + + ret = pdata->clk_enable(host->pdev, &mmc->f_max); + if (!ret) + mmc->f_min = mmc->f_max / 512; + + return ret; +} + +static void tmio_mmc_set_power(struct tmio_mmc_host *host, struct mmc_ios *ios) +{ + struct mmc_host *mmc = host->mmc; + + if (host->set_pwr) + host->set_pwr(host->pdev, ios->power_mode != MMC_POWER_OFF); + if (!IS_ERR(mmc->supply.vmmc)) + /* Errors ignored... */ + mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, + ios->power_mode ? ios->vdd : 0); +} + /* Set MMC clock / power. * Note: This controller uses a simple divider scheme therefore it cannot * run a MMC card at full speed (20MHz). The max clock is 24MHz on SD, but as @@ -797,32 +826,37 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) */ if (ios->power_mode == MMC_POWER_ON && ios->clock) { if (!host->power) { + tmio_mmc_clk_update(mmc); pm_runtime_get_sync(dev); host->power = true; } tmio_mmc_set_clock(host, ios->clock); /* power up SD bus */ - if (host->set_pwr) - host->set_pwr(host->pdev, 1); + tmio_mmc_set_power(host, ios); /* start bus clock */ tmio_mmc_clk_start(host); } else if (ios->power_mode != MMC_POWER_UP) { - if (host->set_pwr && ios->power_mode == MMC_POWER_OFF) - host->set_pwr(host->pdev, 0); + if (ios->power_mode == MMC_POWER_OFF) + tmio_mmc_set_power(host, ios); if (host->power) { + struct tmio_mmc_data *pdata = host->pdata; + tmio_mmc_clk_stop(host); host->power = false; pm_runtime_put(dev); + if (pdata->clk_disable) + pdata->clk_disable(host->pdev); } - tmio_mmc_clk_stop(host); } - switch (ios->bus_width) { - case MMC_BUS_WIDTH_1: - sd_ctrl_write16(host, CTL_SD_MEM_CARD_OPT, 0x80e0); - break; - case MMC_BUS_WIDTH_4: - sd_ctrl_write16(host, CTL_SD_MEM_CARD_OPT, 0x00e0); - break; + if (host->power) { + switch (ios->bus_width) { + case MMC_BUS_WIDTH_1: + sd_ctrl_write16(host, CTL_SD_MEM_CARD_OPT, 0x80e0); + break; + case MMC_BUS_WIDTH_4: + sd_ctrl_write16(host, CTL_SD_MEM_CARD_OPT, 0x00e0); + break; + } } /* Let things settle. delay taken from winCE driver */ @@ -841,6 +875,9 @@ static int tmio_mmc_get_ro(struct mmc_host *mmc) { struct tmio_mmc_host *host = mmc_priv(mmc); struct tmio_mmc_data *pdata = host->pdata; + int ret = mmc_gpio_get_ro(mmc); + if (ret >= 0) + return ret; return !((pdata->flags & TMIO_MMC_WRPROTECT_DISABLE) || (sd_ctrl_read32(host, CTL_STATUS) & TMIO_STAT_WRPROTECT)); @@ -850,6 +887,9 @@ static int tmio_mmc_get_cd(struct mmc_host *mmc) { struct tmio_mmc_host *host = mmc_priv(mmc); struct tmio_mmc_data *pdata = host->pdata; + int ret = mmc_gpio_get_cd(mmc); + if (ret >= 0) + return ret; if (!pdata->get_cd) return -ENOSYS; @@ -865,6 +905,19 @@ static const struct mmc_host_ops tmio_mmc_ops = { .enable_sdio_irq = tmio_mmc_enable_sdio_irq, }; +static void tmio_mmc_init_ocr(struct tmio_mmc_host *host) +{ + struct tmio_mmc_data *pdata = host->pdata; + struct mmc_host *mmc = host->mmc; + + mmc_regulator_get_supply(mmc); + + if (!mmc->ocr_avail) + mmc->ocr_avail = pdata->ocr_mask ? : MMC_VDD_32_33 | MMC_VDD_33_34; + else if (pdata->ocr_mask) + dev_warn(mmc_dev(mmc), "Platform OCR mask is ignored\n"); +} + int __devinit tmio_mmc_host_probe(struct tmio_mmc_host **host, struct platform_device *pdev, struct tmio_mmc_data *pdata) @@ -904,18 +957,14 @@ int __devinit tmio_mmc_host_probe(struct tmio_mmc_host **host, mmc->ops = &tmio_mmc_ops; mmc->caps = MMC_CAP_4_BIT_DATA | pdata->capabilities; - mmc->f_max = pdata->hclk; - mmc->f_min = mmc->f_max / 512; + mmc->caps2 = pdata->capabilities2; mmc->max_segs = 32; mmc->max_blk_size = 512; mmc->max_blk_count = (PAGE_CACHE_SIZE / mmc->max_blk_size) * mmc->max_segs; mmc->max_req_size = mmc->max_blk_size * mmc->max_blk_count; mmc->max_seg_size = mmc->max_req_size; - if (pdata->ocr_mask) - mmc->ocr_avail = pdata->ocr_mask; - else - mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34; + tmio_mmc_init_ocr(_host); _host->native_hotplug = !(pdata->flags & TMIO_MMC_USE_GPIO_CD || mmc->caps & MMC_CAP_NEEDS_POLL || @@ -927,6 +976,11 @@ int __devinit tmio_mmc_host_probe(struct tmio_mmc_host **host, if (ret < 0) goto pm_disable; + if (tmio_mmc_clk_update(mmc) < 0) { + mmc->f_max = pdata->hclk; + mmc->f_min = mmc->f_max / 512; + } + /* * There are 4 different scenarios for the card detection: * 1) an external gpio irq handles the cd (best for power savings) @@ -937,7 +991,6 @@ int __devinit tmio_mmc_host_probe(struct tmio_mmc_host **host, * While we increment the runtime PM counter for all scenarios when * the mmc core activates us by calling an appropriate set_ios(), we * must additionally ensure that in case 2) the tmio mmc hardware stays - * additionally ensure that in case 2) the tmio mmc hardware stays * powered on during runtime for the card detection to work. */ if (_host->native_hotplug) @@ -948,6 +1001,17 @@ int __devinit tmio_mmc_host_probe(struct tmio_mmc_host **host, _host->sdcard_irq_mask = sd_ctrl_read32(_host, CTL_IRQ_MASK); tmio_mmc_disable_mmc_irqs(_host, TMIO_MASK_ALL); + + /* Unmask the IRQs we want to know about */ + if (!_host->chan_rx) + irq_mask |= TMIO_MASK_READOP; + if (!_host->chan_tx) + irq_mask |= TMIO_MASK_WRITEOP; + if (!_host->native_hotplug) + irq_mask &= ~(TMIO_STAT_CARD_REMOVE | TMIO_STAT_CARD_INSERT); + + _host->sdcard_irq_mask &= ~irq_mask; + if (pdata->flags & TMIO_MMC_SDIO_IRQ) tmio_mmc_enable_sdio_irq(mmc, 0); @@ -961,22 +1025,18 @@ int __devinit tmio_mmc_host_probe(struct tmio_mmc_host **host, /* See if we also get DMA */ tmio_mmc_request_dma(_host, pdata); - mmc_add_host(mmc); + ret = mmc_add_host(mmc); + if (pdata->clk_disable) + pdata->clk_disable(pdev); + if (ret < 0) { + tmio_mmc_host_remove(_host); + return ret; + } dev_pm_qos_expose_latency_limit(&pdev->dev, 100); - /* Unmask the IRQs we want to know about */ - if (!_host->chan_rx) - irq_mask |= TMIO_MASK_READOP; - if (!_host->chan_tx) - irq_mask |= TMIO_MASK_WRITEOP; - if (!_host->native_hotplug) - irq_mask &= ~(TMIO_STAT_CARD_REMOVE | TMIO_STAT_CARD_INSERT); - - tmio_mmc_enable_mmc_irqs(_host, irq_mask); - if (pdata->flags & TMIO_MMC_USE_GPIO_CD) { - ret = mmc_cd_gpio_request(mmc, pdata->cd_gpio); + ret = mmc_gpio_request_cd(mmc, pdata->cd_gpio); if (ret < 0) { tmio_mmc_host_remove(_host); return ret; @@ -1008,7 +1068,7 @@ void tmio_mmc_host_remove(struct tmio_mmc_host *host) * This means we can miss a card-eject, but this is anyway * possible, because of delayed processing of hotplug events. */ - mmc_cd_gpio_free(mmc); + mmc_gpio_free_cd(mmc); if (!host->native_hotplug) pm_runtime_get_sync(&pdev->dev); diff --git a/drivers/mtd/mtdsuper.c b/drivers/mtd/mtdsuper.c index a90bfe79916d..334da5f583c0 100644 --- a/drivers/mtd/mtdsuper.c +++ b/drivers/mtd/mtdsuper.c @@ -63,7 +63,7 @@ static struct dentry *mount_mtd_aux(struct file_system_type *fs_type, int flags, struct super_block *sb; int ret; - sb = sget(fs_type, get_sb_mtd_compare, get_sb_mtd_set, mtd); + sb = sget(fs_type, get_sb_mtd_compare, get_sb_mtd_set, flags, mtd); if (IS_ERR(sb)) goto out_error; @@ -74,8 +74,6 @@ static struct dentry *mount_mtd_aux(struct file_system_type *fs_type, int flags, pr_debug("MTDSB: New superblock for device %d (\"%s\")\n", mtd->index, mtd->name); - sb->s_flags = flags; - ret = fill_super(sb, data, flags & MS_SILENT ? 1 : 0); if (ret < 0) { deactivate_locked_super(sb); diff --git a/drivers/mtd/nand/cafe_nand.c b/drivers/mtd/nand/cafe_nand.c index 41371ba1a811..f3f6cfedd69e 100644 --- a/drivers/mtd/nand/cafe_nand.c +++ b/drivers/mtd/nand/cafe_nand.c @@ -102,7 +102,7 @@ static const char *part_probes[] = { "cmdlinepart", "RedBoot", NULL }; static int cafe_device_ready(struct mtd_info *mtd) { struct cafe_priv *cafe = mtd->priv; - int result = !!(cafe_readl(cafe, NAND_STATUS) | 0x40000000); + int result = !!(cafe_readl(cafe, NAND_STATUS) & 0x40000000); uint32_t irqs = cafe_readl(cafe, NAND_IRQ); cafe_writel(cafe, irqs, NAND_IRQ); diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c index a05b7b444d4f..a6cad5caba78 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c @@ -920,12 +920,12 @@ static int gpmi_ecc_read_page(struct mtd_info *mtd, struct nand_chip *chip, */ memset(chip->oob_poi, ~0, mtd->oobsize); chip->oob_poi[0] = ((uint8_t *) auxiliary_virt)[0]; - - read_page_swap_end(this, buf, mtd->writesize, - this->payload_virt, this->payload_phys, - nfc_geo->payload_size, - payload_virt, payload_phys); } + + read_page_swap_end(this, buf, mtd->writesize, + this->payload_virt, this->payload_phys, + nfc_geo->payload_size, + payload_virt, payload_phys); exit_nfc: return ret; } diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c index c58e6a93f445..6acc790c2fbb 100644 --- a/drivers/mtd/nand/mxc_nand.c +++ b/drivers/mtd/nand/mxc_nand.c @@ -273,6 +273,26 @@ static struct nand_ecclayout nandv2_hw_eccoob_4k = { static const char *part_probes[] = { "RedBoot", "cmdlinepart", "ofpart", NULL }; +static void memcpy32_fromio(void *trg, const void __iomem *src, size_t size) +{ + int i; + u32 *t = trg; + const __iomem u32 *s = src; + + for (i = 0; i < (size >> 2); i++) + *t++ = __raw_readl(s++); +} + +static void memcpy32_toio(void __iomem *trg, const void *src, int size) +{ + int i; + u32 __iomem *t = trg; + const u32 *s = src; + + for (i = 0; i < (size >> 2); i++) + __raw_writel(*s++, t++); +} + static int check_int_v3(struct mxc_nand_host *host) { uint32_t tmp; @@ -519,7 +539,7 @@ static void send_read_id_v3(struct mxc_nand_host *host) wait_op_done(host, true); - memcpy_fromio(host->data_buf, host->main_area0, 16); + memcpy32_fromio(host->data_buf, host->main_area0, 16); } /* Request the NANDFC to perform a read of the NAND device ID. */ @@ -535,7 +555,7 @@ static void send_read_id_v1_v2(struct mxc_nand_host *host) /* Wait for operation to complete */ wait_op_done(host, true); - memcpy_fromio(host->data_buf, host->main_area0, 16); + memcpy32_fromio(host->data_buf, host->main_area0, 16); if (this->options & NAND_BUSWIDTH_16) { /* compress the ID info */ @@ -797,16 +817,16 @@ static void copy_spare(struct mtd_info *mtd, bool bfrom) if (bfrom) { for (i = 0; i < n - 1; i++) - memcpy_fromio(d + i * j, s + i * t, j); + memcpy32_fromio(d + i * j, s + i * t, j); /* the last section */ - memcpy_fromio(d + i * j, s + i * t, mtd->oobsize - i * j); + memcpy32_fromio(d + i * j, s + i * t, mtd->oobsize - i * j); } else { for (i = 0; i < n - 1; i++) - memcpy_toio(&s[i * t], &d[i * j], j); + memcpy32_toio(&s[i * t], &d[i * j], j); /* the last section */ - memcpy_toio(&s[i * t], &d[i * j], mtd->oobsize - i * j); + memcpy32_toio(&s[i * t], &d[i * j], mtd->oobsize - i * j); } } @@ -1070,7 +1090,8 @@ static void mxc_nand_command(struct mtd_info *mtd, unsigned command, host->devtype_data->send_page(mtd, NFC_OUTPUT); - memcpy_fromio(host->data_buf, host->main_area0, mtd->writesize); + memcpy32_fromio(host->data_buf, host->main_area0, + mtd->writesize); copy_spare(mtd, true); break; @@ -1086,7 +1107,7 @@ static void mxc_nand_command(struct mtd_info *mtd, unsigned command, break; case NAND_CMD_PAGEPROG: - memcpy_toio(host->main_area0, host->data_buf, mtd->writesize); + memcpy32_toio(host->main_area0, host->data_buf, mtd->writesize); copy_spare(mtd, false); host->devtype_data->send_page(mtd, NFC_INPUT); host->devtype_data->send_cmd(host, command, true); diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index d47586cf64ce..a11253a0fcab 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -3501,6 +3501,13 @@ int nand_scan_tail(struct mtd_info *mtd) /* propagate ecc info to mtd_info */ mtd->ecclayout = chip->ecc.layout; mtd->ecc_strength = chip->ecc.strength; + /* + * Initialize bitflip_threshold to its default prior scan_bbt() call. + * scan_bbt() might invoke mtd_read(), thus bitflip_threshold must be + * properly set. + */ + if (!mtd->bitflip_threshold) + mtd->bitflip_threshold = mtd->ecc_strength; /* Check, if we should skip the bad block table scan */ if (chip->options & NAND_SKIP_BBTSCAN) diff --git a/drivers/mtd/nand/nandsim.c b/drivers/mtd/nand/nandsim.c index 6cc8fbfabb8e..cf0cd3146817 100644 --- a/drivers/mtd/nand/nandsim.c +++ b/drivers/mtd/nand/nandsim.c @@ -28,7 +28,7 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/vmalloc.h> -#include <asm/div64.h> +#include <linux/math64.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/string.h> @@ -546,12 +546,6 @@ static char *get_partition_name(int i) return kstrdup(buf, GFP_KERNEL); } -static uint64_t divide(uint64_t n, uint32_t d) -{ - do_div(n, d); - return n; -} - /* * Initialize the nandsim structure. * @@ -580,7 +574,7 @@ static int init_nandsim(struct mtd_info *mtd) ns->geom.oobsz = mtd->oobsize; ns->geom.secsz = mtd->erasesize; ns->geom.pgszoob = ns->geom.pgsz + ns->geom.oobsz; - ns->geom.pgnum = divide(ns->geom.totsz, ns->geom.pgsz); + ns->geom.pgnum = div_u64(ns->geom.totsz, ns->geom.pgsz); ns->geom.totszoob = ns->geom.totsz + (uint64_t)ns->geom.pgnum * ns->geom.oobsz; ns->geom.secshift = ffs(ns->geom.secsz) - 1; ns->geom.pgshift = chip->page_shift; @@ -921,7 +915,7 @@ static int setup_wear_reporting(struct mtd_info *mtd) if (!rptwear) return 0; - wear_eb_count = divide(mtd->size, mtd->erasesize); + wear_eb_count = div_u64(mtd->size, mtd->erasesize); mem = wear_eb_count * sizeof(unsigned long); if (mem / sizeof(unsigned long) != wear_eb_count) { NS_ERR("Too many erase blocks for wear reporting\n"); diff --git a/drivers/mtd/ubi/Kconfig b/drivers/mtd/ubi/Kconfig index 738ee8dc16cd..ea4b95b5451c 100644 --- a/drivers/mtd/ubi/Kconfig +++ b/drivers/mtd/ubi/Kconfig @@ -29,7 +29,7 @@ config MTD_UBI_WL_THRESHOLD config MTD_UBI_BEB_RESERVE int "Percentage of reserved eraseblocks for bad eraseblocks handling" - default 1 + default 2 range 0 25 help If the MTD device admits of bad eraseblocks (e.g. NAND flash), UBI diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c index acec85deb6af..fb5567878181 100644 --- a/drivers/mtd/ubi/cdev.c +++ b/drivers/mtd/ubi/cdev.c @@ -1026,7 +1026,7 @@ static long ctrl_cdev_ioctl(struct file *file, unsigned int cmd, { int ubi_num; - dbg_gen("dettach MTD device"); + dbg_gen("detach MTD device"); err = get_user(ubi_num, (__user int32_t *)argp); if (err) { err = -EFAULT; diff --git a/drivers/mtd/ubi/misc.c b/drivers/mtd/ubi/misc.c index f6a7d7ac4b98..8bbfb444b895 100644 --- a/drivers/mtd/ubi/misc.c +++ b/drivers/mtd/ubi/misc.c @@ -92,7 +92,30 @@ int ubi_check_volume(struct ubi_device *ubi, int vol_id) } /** - * ubi_calculate_rsvd_pool - calculate how many PEBs must be reserved for bad + * ubi_update_reserved - update bad eraseblock handling accounting data. + * @ubi: UBI device description object + * + * This function calculates the gap between current number of PEBs reserved for + * bad eraseblock handling and the required level of PEBs that must be + * reserved, and if necessary, reserves more PEBs to fill that gap, according + * to availability. Should be called with ubi->volumes_lock held. + */ +void ubi_update_reserved(struct ubi_device *ubi) +{ + int need = ubi->beb_rsvd_level - ubi->beb_rsvd_pebs; + + if (need <= 0 || ubi->avail_pebs == 0) + return; + + need = min_t(int, need, ubi->avail_pebs); + ubi->avail_pebs -= need; + ubi->rsvd_pebs += need; + ubi->beb_rsvd_pebs += need; + ubi_msg("reserved more %d PEBs for bad PEB handling", need); +} + +/** + * ubi_calculate_reserved - calculate how many PEBs must be reserved for bad * eraseblock handling. * @ubi: UBI device description object */ diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h index a1a81c9ea8ce..84f66e3fa05d 100644 --- a/drivers/mtd/ubi/ubi.h +++ b/drivers/mtd/ubi/ubi.h @@ -647,6 +647,7 @@ int ubi_more_leb_change_data(struct ubi_device *ubi, struct ubi_volume *vol, int ubi_calc_data_len(const struct ubi_device *ubi, const void *buf, int length); int ubi_check_volume(struct ubi_device *ubi, int vol_id); +void ubi_update_reserved(struct ubi_device *ubi); void ubi_calculate_reserved(struct ubi_device *ubi); int ubi_check_pattern(const void *buf, uint8_t patt, int size); diff --git a/drivers/mtd/ubi/vmt.c b/drivers/mtd/ubi/vmt.c index 0669cff8ac3c..9169e58c262e 100644 --- a/drivers/mtd/ubi/vmt.c +++ b/drivers/mtd/ubi/vmt.c @@ -443,15 +443,7 @@ int ubi_remove_volume(struct ubi_volume_desc *desc, int no_vtbl) spin_lock(&ubi->volumes_lock); ubi->rsvd_pebs -= reserved_pebs; ubi->avail_pebs += reserved_pebs; - i = ubi->beb_rsvd_level - ubi->beb_rsvd_pebs; - if (i > 0) { - i = ubi->avail_pebs >= i ? i : ubi->avail_pebs; - ubi->avail_pebs -= i; - ubi->rsvd_pebs += i; - ubi->beb_rsvd_pebs += i; - if (i > 0) - ubi_msg("reserve more %d PEBs", i); - } + ubi_update_reserved(ubi); ubi->vol_count -= 1; spin_unlock(&ubi->volumes_lock); @@ -558,15 +550,7 @@ int ubi_resize_volume(struct ubi_volume_desc *desc, int reserved_pebs) spin_lock(&ubi->volumes_lock); ubi->rsvd_pebs += pebs; ubi->avail_pebs -= pebs; - pebs = ubi->beb_rsvd_level - ubi->beb_rsvd_pebs; - if (pebs > 0) { - pebs = ubi->avail_pebs >= pebs ? pebs : ubi->avail_pebs; - ubi->avail_pebs -= pebs; - ubi->rsvd_pebs += pebs; - ubi->beb_rsvd_pebs += pebs; - if (pebs > 0) - ubi_msg("reserve more %d PEBs", pebs); - } + ubi_update_reserved(ubi); for (i = 0; i < reserved_pebs; i++) new_mapping[i] = vol->eba_tbl[i]; kfree(vol->eba_tbl); diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index 3680aa251dea..2cf084eb9d52 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -6,7 +6,7 @@ #include "bonding.h" #include "bond_alb.h" -#ifdef CONFIG_DEBUG_FS +#if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_NET_NS) #include <linux/debugfs.h> #include <linux/seq_file.h> diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b9c2ae62166d..2ee76993f052 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3227,6 +3227,12 @@ static int bond_master_netdev_event(unsigned long event, switch (event) { case NETDEV_CHANGENAME: return bond_event_changename(event_bond); + case NETDEV_UNREGISTER: + bond_remove_proc_entry(event_bond); + break; + case NETDEV_REGISTER: + bond_create_proc_entry(event_bond); + break; default: break; } @@ -4411,8 +4417,6 @@ static void bond_uninit(struct net_device *bond_dev) bond_work_cancel_all(bond); - bond_remove_proc_entry(bond); - bond_debug_unregister(bond); __hw_addr_flush(&bond->mc_list); @@ -4814,7 +4818,6 @@ static int bond_init(struct net_device *bond_dev) bond_set_lockdep_class(bond_dev); - bond_create_proc_entry(bond); list_add_tail(&bond->bond_list, &bn->dev_list); bond_prepare_sysfs_group(bond); diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 9cc15701101b..1f78b63d5efe 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -261,7 +261,6 @@ static void atl1c_check_link_status(struct atl1c_adapter *adapter) if ((phy_data & BMSR_LSTATUS) == 0) { /* link down */ netif_carrier_off(netdev); - netif_stop_queue(netdev); hw->hibernate = true; if (atl1c_reset_mac(hw) != 0) if (netif_msg_hw(adapter)) diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 46b8b7d81633..d09c6b583d17 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -656,7 +656,7 @@ static int b44_alloc_rx_skb(struct b44 *bp, int src_idx, u32 dest_idx_unmasked) dma_unmap_single(bp->sdev->dma_dev, mapping, RX_PKT_BUF_SZ, DMA_FROM_DEVICE); dev_kfree_skb_any(skb); - skb = __netdev_alloc_skb(bp->dev, RX_PKT_BUF_SZ, GFP_ATOMIC|GFP_DMA); + skb = alloc_skb(RX_PKT_BUF_SZ, GFP_ATOMIC | GFP_DMA); if (skb == NULL) return -ENOMEM; mapping = dma_map_single(bp->sdev->dma_dev, skb->data, @@ -967,7 +967,7 @@ static netdev_tx_t b44_start_xmit(struct sk_buff *skb, struct net_device *dev) dma_unmap_single(bp->sdev->dma_dev, mapping, len, DMA_TO_DEVICE); - bounce_skb = __netdev_alloc_skb(dev, len, GFP_ATOMIC | GFP_DMA); + bounce_skb = alloc_skb(len, GFP_ATOMIC | GFP_DMA); if (!bounce_skb) goto err_out; diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index ac7b74488531..1fa4927a45b1 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -5372,7 +5372,7 @@ bnx2_free_tx_skbs(struct bnx2 *bp) int k, last; if (skb == NULL) { - j++; + j = NEXT_TX_BD(j); continue; } @@ -5384,8 +5384,8 @@ bnx2_free_tx_skbs(struct bnx2 *bp) tx_buf->skb = NULL; last = tx_buf->nr_frags; - j++; - for (k = 0; k < last; k++, j++) { + j = NEXT_TX_BD(j); + for (k = 0; k < last; k++, j = NEXT_TX_BD(j)) { tx_buf = &txr->tx_buf_ring[TX_RING_IDX(j)]; dma_unmap_page(&bp->pdev->dev, dma_unmap_addr(tx_buf, mapping), diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index c95e7b5e2b85..2c89d17cbb29 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -534,7 +534,8 @@ int cnic_unregister_driver(int ulp_type) } if (atomic_read(&ulp_ops->ref_count) != 0) - netdev_warn(dev->netdev, "Failed waiting for ref count to go to zero\n"); + pr_warn("%s: Failed waiting for ref count to go to zero\n", + __func__); return 0; out_unlock: @@ -1053,12 +1054,13 @@ static int cnic_init_uio(struct cnic_dev *dev) uinfo = &udev->cnic_uinfo; - uinfo->mem[0].addr = dev->netdev->base_addr; + uinfo->mem[0].addr = pci_resource_start(dev->pcidev, 0); uinfo->mem[0].internal_addr = dev->regview; - uinfo->mem[0].size = dev->netdev->mem_end - dev->netdev->mem_start; uinfo->mem[0].memtype = UIO_MEM_PHYS; if (test_bit(CNIC_F_BNX2_CLASS, &dev->flags)) { + uinfo->mem[0].size = MB_GET_CID_ADDR(TX_TSS_CID + + TX_MAX_TSS_RINGS + 1); uinfo->mem[1].addr = (unsigned long) cp->status_blk.gen & PAGE_MASK; if (cp->ethdev->drv_state & CNIC_DRV_STATE_USING_MSIX) @@ -1068,6 +1070,8 @@ static int cnic_init_uio(struct cnic_dev *dev) uinfo->name = "bnx2_cnic"; } else if (test_bit(CNIC_F_BNX2X_CLASS, &dev->flags)) { + uinfo->mem[0].size = pci_resource_len(dev->pcidev, 0); + uinfo->mem[1].addr = (unsigned long) cp->bnx2x_def_status_blk & PAGE_MASK; uinfo->mem[1].size = sizeof(*cp->bnx2x_def_status_blk); diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 0741aded9eb0..ab1d80ff0791 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1804,18 +1804,16 @@ void gfar_configure_coalescing(struct gfar_private *priv, if (priv->mode == MQ_MG_MODE) { baddr = ®s->txic0; for_each_set_bit(i, &tx_mask, priv->num_tx_queues) { - if (likely(priv->tx_queue[i]->txcoalescing)) { - gfar_write(baddr + i, 0); + gfar_write(baddr + i, 0); + if (likely(priv->tx_queue[i]->txcoalescing)) gfar_write(baddr + i, priv->tx_queue[i]->txic); - } } baddr = ®s->rxic0; for_each_set_bit(i, &rx_mask, priv->num_rx_queues) { - if (likely(priv->rx_queue[i]->rxcoalescing)) { - gfar_write(baddr + i, 0); + gfar_write(baddr + i, 0); + if (likely(priv->rx_queue[i]->rxcoalescing)) gfar_write(baddr + i, priv->rx_queue[i]->rxic); - } } } } @@ -2065,10 +2063,9 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } - /* Steal sock reference for processing TX time stamps */ - swap(skb_new->sk, skb->sk); - swap(skb_new->destructor, skb->destructor); - kfree_skb(skb); + if (skb->sk) + skb_set_owner_w(skb_new, skb->sk); + consume_skb(skb); skb = skb_new; } diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index 36db4df09aed..1f063dcd8f85 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -1572,6 +1572,9 @@ static s32 e1000_check_for_serdes_link_82571(struct e1000_hw *hw) ctrl = er32(CTRL); status = er32(STATUS); rxcw = er32(RXCW); + /* SYNCH bit and IV bit are sticky */ + udelay(10); + rxcw = er32(RXCW); if ((rxcw & E1000_RXCW_SYNCH) && !(rxcw & E1000_RXCW_IV)) { diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index 351a4097b2ba..76edbc1be33b 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -103,6 +103,7 @@ #define E1000_RXD_ERR_SEQ 0x04 /* Sequence Error */ #define E1000_RXD_ERR_CXE 0x10 /* Carrier Extension Error */ #define E1000_RXD_ERR_TCPE 0x20 /* TCP/UDP Checksum Error */ +#define E1000_RXD_ERR_IPE 0x40 /* IP Checksum Error */ #define E1000_RXD_ERR_RXE 0x80 /* Rx Data Error */ #define E1000_RXD_SPC_VLAN_MASK 0x0FFF /* VLAN ID is in lower 12 bits */ diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 238ab2f8a5e7..e3a7b07df629 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -325,24 +325,46 @@ static inline void __ew32flash(struct e1000_hw *hw, unsigned long reg, u32 val) **/ static bool e1000_phy_is_accessible_pchlan(struct e1000_hw *hw) { - u16 phy_reg; - u32 phy_id; + u16 phy_reg = 0; + u32 phy_id = 0; + s32 ret_val; + u16 retry_count; + + for (retry_count = 0; retry_count < 2; retry_count++) { + ret_val = e1e_rphy_locked(hw, PHY_ID1, &phy_reg); + if (ret_val || (phy_reg == 0xFFFF)) + continue; + phy_id = (u32)(phy_reg << 16); - e1e_rphy_locked(hw, PHY_ID1, &phy_reg); - phy_id = (u32)(phy_reg << 16); - e1e_rphy_locked(hw, PHY_ID2, &phy_reg); - phy_id |= (u32)(phy_reg & PHY_REVISION_MASK); + ret_val = e1e_rphy_locked(hw, PHY_ID2, &phy_reg); + if (ret_val || (phy_reg == 0xFFFF)) { + phy_id = 0; + continue; + } + phy_id |= (u32)(phy_reg & PHY_REVISION_MASK); + break; + } if (hw->phy.id) { if (hw->phy.id == phy_id) return true; - } else { - if ((phy_id != 0) && (phy_id != PHY_REVISION_MASK)) - hw->phy.id = phy_id; + } else if (phy_id) { + hw->phy.id = phy_id; + hw->phy.revision = (u32)(phy_reg & ~PHY_REVISION_MASK); return true; } - return false; + /* + * In case the PHY needs to be in mdio slow mode, + * set slow mode and try to get the PHY id again. + */ + hw->phy.ops.release(hw); + ret_val = e1000_set_mdio_slow_mode_hv(hw); + if (!ret_val) + ret_val = e1000e_get_phy_id(hw); + hw->phy.ops.acquire(hw); + + return !ret_val; } /** diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 31d37a2b5ba8..623e30b9964d 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -496,7 +496,7 @@ static void e1000_receive_skb(struct e1000_adapter *adapter, * @sk_buff: socket buffer with received data **/ static void e1000_rx_checksum(struct e1000_adapter *adapter, u32 status_err, - __le16 csum, struct sk_buff *skb) + struct sk_buff *skb) { u16 status = (u16)status_err; u8 errors = (u8)(status_err >> 24); @@ -511,8 +511,8 @@ static void e1000_rx_checksum(struct e1000_adapter *adapter, u32 status_err, if (status & E1000_RXD_STAT_IXSM) return; - /* TCP/UDP checksum error bit is set */ - if (errors & E1000_RXD_ERR_TCPE) { + /* TCP/UDP checksum error bit or IP checksum error bit is set */ + if (errors & (E1000_RXD_ERR_TCPE | E1000_RXD_ERR_IPE)) { /* let the stack verify checksum errors */ adapter->hw_csum_err++; return; @@ -523,19 +523,7 @@ static void e1000_rx_checksum(struct e1000_adapter *adapter, u32 status_err, return; /* It must be a TCP or UDP packet with a valid checksum */ - if (status & E1000_RXD_STAT_TCPCS) { - /* TCP checksum is good */ - skb->ip_summed = CHECKSUM_UNNECESSARY; - } else { - /* - * IP fragment with UDP payload - * Hardware complements the payload checksum, so we undo it - * and then put the value in host order for further stack use. - */ - __sum16 sum = (__force __sum16)swab16((__force u16)csum); - skb->csum = csum_unfold(~sum); - skb->ip_summed = CHECKSUM_COMPLETE; - } + skb->ip_summed = CHECKSUM_UNNECESSARY; adapter->hw_csum_good++; } @@ -954,8 +942,7 @@ static bool e1000_clean_rx_irq(struct e1000_ring *rx_ring, int *work_done, skb_put(skb, length); /* Receive Checksum Offload */ - e1000_rx_checksum(adapter, staterr, - rx_desc->wb.lower.hi_dword.csum_ip.csum, skb); + e1000_rx_checksum(adapter, staterr, skb); e1000_rx_hash(netdev, rx_desc->wb.lower.hi_dword.rss, skb); @@ -1341,8 +1328,7 @@ copydone: total_rx_bytes += skb->len; total_rx_packets++; - e1000_rx_checksum(adapter, staterr, - rx_desc->wb.lower.hi_dword.csum_ip.csum, skb); + e1000_rx_checksum(adapter, staterr, skb); e1000_rx_hash(netdev, rx_desc->wb.lower.hi_dword.rss, skb); @@ -1512,9 +1498,8 @@ static bool e1000_clean_jumbo_rx_irq(struct e1000_ring *rx_ring, int *work_done, } } - /* Receive Checksum Offload XXX recompute due to CRC strip? */ - e1000_rx_checksum(adapter, staterr, - rx_desc->wb.lower.hi_dword.csum_ip.csum, skb); + /* Receive Checksum Offload */ + e1000_rx_checksum(adapter, staterr, skb); e1000_rx_hash(netdev, rx_desc->wb.lower.hi_dword.rss, skb); @@ -3098,19 +3083,10 @@ static void e1000_configure_rx(struct e1000_adapter *adapter) /* Enable Receive Checksum Offload for TCP and UDP */ rxcsum = er32(RXCSUM); - if (adapter->netdev->features & NETIF_F_RXCSUM) { + if (adapter->netdev->features & NETIF_F_RXCSUM) rxcsum |= E1000_RXCSUM_TUOFL; - - /* - * IPv4 payload checksum for UDP fragments must be - * used in conjunction with packet-split. - */ - if (adapter->rx_ps_pages) - rxcsum |= E1000_RXCSUM_IPPCSE; - } else { + else rxcsum &= ~E1000_RXCSUM_TUOFL; - /* no need to clear IPPCSE as it defaults to 0 */ - } ew32(RXCSUM, rxcsum); if (adapter->hw.mac.type == e1000_pch2lan) { @@ -5241,22 +5217,10 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; /* Jumbo frame support */ - if (max_frame > ETH_FRAME_LEN + ETH_FCS_LEN) { - if (!(adapter->flags & FLAG_HAS_JUMBO_FRAMES)) { - e_err("Jumbo Frames not supported.\n"); - return -EINVAL; - } - - /* - * IP payload checksum (enabled with jumbos/packet-split when - * Rx checksum is enabled) and generation of RSS hash is - * mutually exclusive in the hardware. - */ - if ((netdev->features & NETIF_F_RXCSUM) && - (netdev->features & NETIF_F_RXHASH)) { - e_err("Jumbo frames cannot be enabled when both receive checksum offload and receive hashing are enabled. Disable one of the receive offload features before enabling jumbos.\n"); - return -EINVAL; - } + if ((max_frame > ETH_FRAME_LEN + ETH_FCS_LEN) && + !(adapter->flags & FLAG_HAS_JUMBO_FRAMES)) { + e_err("Jumbo Frames not supported.\n"); + return -EINVAL; } /* Supported frame sizes */ @@ -6030,17 +5994,6 @@ static int e1000_set_features(struct net_device *netdev, NETIF_F_RXALL))) return 0; - /* - * IP payload checksum (enabled with jumbos/packet-split when Rx - * checksum is enabled) and generation of RSS hash is mutually - * exclusive in the hardware. - */ - if (adapter->rx_ps_pages && - (features & NETIF_F_RXCSUM) && (features & NETIF_F_RXHASH)) { - e_err("Enabling both receive checksum offload and receive hashing is not possible with jumbo frames. Disable jumbos or enable only one of the receive offload features.\n"); - return -EINVAL; - } - if (changed & NETIF_F_RXFCS) { if (features & NETIF_F_RXFCS) { adapter->flags2 &= ~FLAG2_CRC_STRIPPING; diff --git a/drivers/net/ethernet/intel/igbvf/ethtool.c b/drivers/net/ethernet/intel/igbvf/ethtool.c index 8ce67064b9c5..90eef07943f4 100644 --- a/drivers/net/ethernet/intel/igbvf/ethtool.c +++ b/drivers/net/ethernet/intel/igbvf/ethtool.c @@ -357,21 +357,28 @@ static int igbvf_set_coalesce(struct net_device *netdev, struct igbvf_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - if ((ec->rx_coalesce_usecs > IGBVF_MAX_ITR_USECS) || - ((ec->rx_coalesce_usecs > 3) && - (ec->rx_coalesce_usecs < IGBVF_MIN_ITR_USECS)) || - (ec->rx_coalesce_usecs == 2)) - return -EINVAL; - - /* convert to rate of irq's per second */ - if (ec->rx_coalesce_usecs && ec->rx_coalesce_usecs <= 3) { + if ((ec->rx_coalesce_usecs >= IGBVF_MIN_ITR_USECS) && + (ec->rx_coalesce_usecs <= IGBVF_MAX_ITR_USECS)) { + adapter->current_itr = ec->rx_coalesce_usecs << 2; + adapter->requested_itr = 1000000000 / + (adapter->current_itr * 256); + } else if ((ec->rx_coalesce_usecs == 3) || + (ec->rx_coalesce_usecs == 2)) { adapter->current_itr = IGBVF_START_ITR; adapter->requested_itr = ec->rx_coalesce_usecs; - } else { - adapter->current_itr = ec->rx_coalesce_usecs << 2; + } else if (ec->rx_coalesce_usecs == 0) { + /* + * The user's desire is to turn off interrupt throttling + * altogether, but due to HW limitations, we can't do that. + * Instead we set a very small value in EITR, which would + * allow ~967k interrupts per second, but allow the adapter's + * internal clocking to still function properly. + */ + adapter->current_itr = 4; adapter->requested_itr = 1000000000 / (adapter->current_itr * 256); - } + } else + return -EINVAL; writel(adapter->current_itr, hw->hw_addr + adapter->rx_ring->itr_register); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 18ca3bcadf0c..e242104ab471 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6647,6 +6647,11 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) return -EINVAL; } + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + e_err(drv, "Enable failed, SR-IOV enabled\n"); + return -EINVAL; + } + /* Hardware supports up to 8 traffic classes */ if (tc > adapter->dcb_cfg.num_tcs.pg_tcs || (hw->mac.type == ixgbe_mac_82598EB && diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index f69ec4288b10..41e32257a4e8 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -201,6 +201,9 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_adapter *adapter, unsigned int i, eop, count = 0; unsigned int total_bytes = 0, total_packets = 0; + if (test_bit(__IXGBEVF_DOWN, &adapter->state)) + return true; + i = tx_ring->next_to_clean; eop = tx_ring->tx_buffer_info[i].next_to_watch; eop_desc = IXGBE_TX_DESC_ADV(*tx_ring, eop); @@ -969,8 +972,6 @@ static irqreturn_t ixgbevf_msix_clean_tx(int irq, void *data) r_idx = find_first_bit(q_vector->txr_idx, adapter->num_tx_queues); for (i = 0; i < q_vector->txr_count; i++) { tx_ring = &(adapter->tx_ring[r_idx]); - tx_ring->total_bytes = 0; - tx_ring->total_packets = 0; ixgbevf_clean_tx_irq(adapter, tx_ring); r_idx = find_next_bit(q_vector->txr_idx, adapter->num_tx_queues, r_idx + 1); @@ -994,16 +995,6 @@ static irqreturn_t ixgbevf_msix_clean_rx(int irq, void *data) struct ixgbe_hw *hw = &adapter->hw; struct ixgbevf_ring *rx_ring; int r_idx; - int i; - - r_idx = find_first_bit(q_vector->rxr_idx, adapter->num_rx_queues); - for (i = 0; i < q_vector->rxr_count; i++) { - rx_ring = &(adapter->rx_ring[r_idx]); - rx_ring->total_bytes = 0; - rx_ring->total_packets = 0; - r_idx = find_next_bit(q_vector->rxr_idx, adapter->num_rx_queues, - r_idx + 1); - } if (!q_vector->rxr_count) return IRQ_HANDLED; diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c index fb8377da1687..4b785e10f2ed 100644 --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c @@ -51,7 +51,7 @@ static unsigned int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des3 = desc->des2 + BUF_SIZE_4KiB; priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum); - + wmb(); entry = (++priv->cur_tx) % txsize; desc = priv->dma_tx + entry; @@ -59,6 +59,7 @@ static unsigned int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) len, DMA_TO_DEVICE); desc->des3 = desc->des2 + BUF_SIZE_4KiB; priv->hw->desc->prepare_tx_desc(desc, 0, len, csum); + wmb(); priv->hw->desc->set_tx_owner(desc); priv->tx_skbuff[entry] = NULL; } else { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 51b3b68528ee..ea3003edde18 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1212,6 +1212,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) priv->hw->desc->prepare_tx_desc(desc, 0, len, csum_insertion); wmb(); priv->hw->desc->set_tx_owner(desc); + wmb(); } /* Interrupt on completition only for the latest segment */ @@ -1227,6 +1228,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) /* To avoid raise condition */ priv->hw->desc->set_tx_owner(first); + wmb(); priv->cur_tx++; @@ -1290,6 +1292,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv) } wmb(); priv->hw->desc->set_rx_owner(p + entry); + wmb(); } } diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c index d614c374ed9d..3b5c4571b55e 100644 --- a/drivers/net/ethernet/ti/davinci_cpdma.c +++ b/drivers/net/ethernet/ti/davinci_cpdma.c @@ -15,6 +15,7 @@ #include <linux/kernel.h> #include <linux/spinlock.h> #include <linux/device.h> +#include <linux/module.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/dma-mapping.h> diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c index 39ea0674dcde..5c120189ec86 100644 --- a/drivers/net/phy/mdio-mux.c +++ b/drivers/net/phy/mdio-mux.c @@ -46,7 +46,13 @@ static int mdio_mux_read(struct mii_bus *bus, int phy_id, int regnum) struct mdio_mux_parent_bus *pb = cb->parent; int r; - mutex_lock(&pb->mii_bus->mdio_lock); + /* In theory multiple mdio_mux could be stacked, thus creating + * more than a single level of nesting. But in practice, + * SINGLE_DEPTH_NESTING will cover the vast majority of use + * cases. We use it, instead of trying to handle the general + * case. + */ + mutex_lock_nested(&pb->mii_bus->mdio_lock, SINGLE_DEPTH_NESTING); r = pb->switch_fn(pb->current_child, cb->bus_number, pb->switch_data); if (r) goto out; @@ -71,7 +77,7 @@ static int mdio_mux_write(struct mii_bus *bus, int phy_id, int r; - mutex_lock(&pb->mii_bus->mdio_lock); + mutex_lock_nested(&pb->mii_bus->mdio_lock, SINGLE_DEPTH_NESTING); r = pb->switch_fn(pb->current_child, cb->bus_number, pb->switch_data); if (r) goto out; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 3767a1225860..a051cedd64bd 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -197,6 +197,10 @@ err: static int qmi_wwan_cdc_wdm_manage_power(struct usb_interface *intf, int on) { struct usbnet *dev = usb_get_intfdata(intf); + + /* can be called while disconnecting */ + if (!dev) + return 0; return qmi_wwan_manage_power(dev, on); } @@ -342,6 +346,15 @@ static const struct driver_info qmi_wwan_force_int1 = { .data = BIT(1), /* interface whitelist bitmap */ }; +static const struct driver_info qmi_wwan_force_int2 = { + .description = "Qualcomm WWAN/QMI device", + .flags = FLAG_WWAN, + .bind = qmi_wwan_bind_shared, + .unbind = qmi_wwan_unbind_shared, + .manage_power = qmi_wwan_manage_power, + .data = BIT(2), /* interface whitelist bitmap */ +}; + static const struct driver_info qmi_wwan_force_int3 = { .description = "Qualcomm WWAN/QMI device", .flags = FLAG_WWAN, @@ -494,6 +507,15 @@ static const struct usb_device_id products[] = { .bInterfaceProtocol = 0xff, .driver_info = (unsigned long)&qmi_wwan_force_int4, }, + { /* ZTE MF60 */ + .match_flags = USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x19d2, + .idProduct = 0x1402, + .bInterfaceClass = 0xff, + .bInterfaceSubClass = 0xff, + .bInterfaceProtocol = 0xff, + .driver_info = (unsigned long)&qmi_wwan_force_int2, + }, { /* Sierra Wireless MC77xx in QMI mode */ .match_flags = USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_INT_INFO, .idVendor = 0x1199, diff --git a/drivers/net/wireless/ath/ath.h b/drivers/net/wireless/ath/ath.h index c54b7d37bff1..420d69b2674c 100644 --- a/drivers/net/wireless/ath/ath.h +++ b/drivers/net/wireless/ath/ath.h @@ -143,6 +143,7 @@ struct ath_common { u32 keymax; DECLARE_BITMAP(keymap, ATH_KEYMAX); DECLARE_BITMAP(tkip_keymap, ATH_KEYMAX); + DECLARE_BITMAP(ccmp_keymap, ATH_KEYMAX); enum ath_crypt_caps crypt_caps; unsigned int clockrate; diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index 1c68e564f503..995ca8e1302e 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -622,7 +622,7 @@ static int __ath9k_hw_init(struct ath_hw *ah) if (NR_CPUS > 1 && ah->config.serialize_regmode == SER_REG_MODE_AUTO) { if (ah->hw_version.macVersion == AR_SREV_VERSION_5416_PCI || - ((AR_SREV_9160(ah) || AR_SREV_9280(ah)) && + ((AR_SREV_9160(ah) || AR_SREV_9280(ah) || AR_SREV_9287(ah)) && !ah->is_pciexpress)) { ah->config.serialize_regmode = SER_REG_MODE_ON; diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c index e1fcc68124dc..0735aeb3b26c 100644 --- a/drivers/net/wireless/ath/ath9k/recv.c +++ b/drivers/net/wireless/ath/ath9k/recv.c @@ -695,9 +695,9 @@ static bool ath_edma_get_buffers(struct ath_softc *sc, __skb_unlink(skb, &rx_edma->rx_fifo); list_add_tail(&bf->list, &sc->rx.rxbuf); ath_rx_edma_buf_link(sc, qtype); - } else { - bf = NULL; } + + bf = NULL; } *dest = bf; @@ -822,7 +822,8 @@ static bool ath9k_rx_accept(struct ath_common *common, * descriptor does contain a valid key index. This has been observed * mostly with CCMP encryption. */ - if (rx_stats->rs_keyix == ATH9K_RXKEYIX_INVALID) + if (rx_stats->rs_keyix == ATH9K_RXKEYIX_INVALID || + !test_bit(rx_stats->rs_keyix, common->ccmp_keymap)) rx_stats->rs_status &= ~ATH9K_RXERR_KEYMISS; if (!rx_stats->rs_datalen) { diff --git a/drivers/net/wireless/ath/key.c b/drivers/net/wireless/ath/key.c index 0e81904956cf..5c54aa43ca2d 100644 --- a/drivers/net/wireless/ath/key.c +++ b/drivers/net/wireless/ath/key.c @@ -556,6 +556,9 @@ int ath_key_config(struct ath_common *common, return -EIO; set_bit(idx, common->keymap); + if (key->cipher == WLAN_CIPHER_SUITE_CCMP) + set_bit(idx, common->ccmp_keymap); + if (key->cipher == WLAN_CIPHER_SUITE_TKIP) { set_bit(idx + 64, common->keymap); set_bit(idx, common->tkip_keymap); @@ -582,6 +585,7 @@ void ath_key_delete(struct ath_common *common, struct ieee80211_key_conf *key) return; clear_bit(key->hw_key_idx, common->keymap); + clear_bit(key->hw_key_idx, common->ccmp_keymap); if (key->cipher != WLAN_CIPHER_SUITE_TKIP) return; diff --git a/drivers/net/wireless/b43legacy/dma.c b/drivers/net/wireless/b43legacy/dma.c index f1f8bd09bd87..c8baf020c20f 100644 --- a/drivers/net/wireless/b43legacy/dma.c +++ b/drivers/net/wireless/b43legacy/dma.c @@ -1072,7 +1072,7 @@ static int dma_tx_fragment(struct b43legacy_dmaring *ring, meta->dmaaddr = map_descbuffer(ring, skb->data, skb->len, 1); /* create a bounce buffer in zone_dma on mapping failure. */ if (b43legacy_dma_mapping_error(ring, meta->dmaaddr, skb->len, 1)) { - bounce_skb = __dev_alloc_skb(skb->len, GFP_ATOMIC | GFP_DMA); + bounce_skb = alloc_skb(skb->len, GFP_ATOMIC | GFP_DMA); if (!bounce_skb) { ring->current_slot = old_top_slot; ring->used_slots = old_used_slots; diff --git a/drivers/net/wireless/iwlegacy/4965-mac.c b/drivers/net/wireless/iwlegacy/4965-mac.c index 509301a5e7e2..ff5d689e13f3 100644 --- a/drivers/net/wireless/iwlegacy/4965-mac.c +++ b/drivers/net/wireless/iwlegacy/4965-mac.c @@ -3405,7 +3405,7 @@ il4965_remove_dynamic_key(struct il_priv *il, return 0; } - if (il->stations[sta_id].sta.key.key_offset == WEP_INVALID_OFFSET) { + if (il->stations[sta_id].sta.key.key_flags & STA_KEY_FLG_INVALID) { IL_WARN("Removing wrong key %d 0x%x\n", keyconf->keyidx, key_flags); spin_unlock_irqrestore(&il->sta_lock, flags); @@ -3420,7 +3420,7 @@ il4965_remove_dynamic_key(struct il_priv *il, memset(&il->stations[sta_id].sta.key, 0, sizeof(struct il4965_keyinfo)); il->stations[sta_id].sta.key.key_flags = STA_KEY_FLG_NO_ENC | STA_KEY_FLG_INVALID; - il->stations[sta_id].sta.key.key_offset = WEP_INVALID_OFFSET; + il->stations[sta_id].sta.key.key_offset = keyconf->hw_key_idx; il->stations[sta_id].sta.sta.modify_mask = STA_MODIFY_KEY_MASK; il->stations[sta_id].sta.mode = STA_CONTROL_MODIFY_MSK; diff --git a/drivers/net/wireless/iwlegacy/common.c b/drivers/net/wireless/iwlegacy/common.c index cbf2dc18341f..5d4807c2b56d 100644 --- a/drivers/net/wireless/iwlegacy/common.c +++ b/drivers/net/wireless/iwlegacy/common.c @@ -4767,14 +4767,12 @@ il_bg_watchdog(unsigned long data) return; /* monitor and check for other stuck queues */ - if (il_is_any_associated(il)) { - for (cnt = 0; cnt < il->hw_params.max_txq_num; cnt++) { - /* skip as we already checked the command queue */ - if (cnt == il->cmd_queue) - continue; - if (il_check_stuck_queue(il, cnt)) - return; - } + for (cnt = 0; cnt < il->hw_params.max_txq_num; cnt++) { + /* skip as we already checked the command queue */ + if (cnt == il->cmd_queue) + continue; + if (il_check_stuck_queue(il, cnt)) + return; } mod_timer(&il->watchdog, diff --git a/drivers/net/wireless/iwlwifi/iwl-mac80211.c b/drivers/net/wireless/iwlwifi/iwl-mac80211.c index 3ee23134c02b..013680332f07 100644 --- a/drivers/net/wireless/iwlwifi/iwl-mac80211.c +++ b/drivers/net/wireless/iwlwifi/iwl-mac80211.c @@ -796,6 +796,18 @@ int iwlagn_mac_sta_state(struct ieee80211_hw *hw, switch (op) { case ADD: ret = iwlagn_mac_sta_add(hw, vif, sta); + if (ret) + break; + /* + * Clear the in-progress flag, the AP station entry was added + * but we'll initialize LQ only when we've associated (which + * would also clear the in-progress flag). This is necessary + * in case we never initialize LQ because association fails. + */ + spin_lock_bh(&priv->sta_lock); + priv->stations[iwl_sta_id(sta)].used &= + ~IWL_STA_UCODE_INPROGRESS; + spin_unlock_bh(&priv->sta_lock); break; case REMOVE: ret = iwlagn_mac_sta_remove(hw, vif, sta); diff --git a/drivers/net/wireless/mwifiex/11n_rxreorder.c b/drivers/net/wireless/mwifiex/11n_rxreorder.c index 9c44088054dd..900ee129e825 100644 --- a/drivers/net/wireless/mwifiex/11n_rxreorder.c +++ b/drivers/net/wireless/mwifiex/11n_rxreorder.c @@ -256,7 +256,8 @@ mwifiex_11n_create_rx_reorder_tbl(struct mwifiex_private *priv, u8 *ta, else last_seq = priv->rx_seq[tid]; - if (last_seq >= new_node->start_win) + if (last_seq != MWIFIEX_DEF_11N_RX_SEQ_NUM && + last_seq >= new_node->start_win) new_node->start_win = last_seq + 1; new_node->win_size = win_size; @@ -596,5 +597,5 @@ void mwifiex_11n_cleanup_reorder_tbl(struct mwifiex_private *priv) spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags); INIT_LIST_HEAD(&priv->rx_reorder_tbl_ptr); - memset(priv->rx_seq, 0, sizeof(priv->rx_seq)); + mwifiex_reset_11n_rx_seq_num(priv); } diff --git a/drivers/net/wireless/mwifiex/11n_rxreorder.h b/drivers/net/wireless/mwifiex/11n_rxreorder.h index f1bffebabc60..6c9815a0f5d8 100644 --- a/drivers/net/wireless/mwifiex/11n_rxreorder.h +++ b/drivers/net/wireless/mwifiex/11n_rxreorder.h @@ -37,6 +37,13 @@ #define ADDBA_RSP_STATUS_ACCEPT 0 +#define MWIFIEX_DEF_11N_RX_SEQ_NUM 0xffff + +static inline void mwifiex_reset_11n_rx_seq_num(struct mwifiex_private *priv) +{ + memset(priv->rx_seq, 0xff, sizeof(priv->rx_seq)); +} + int mwifiex_11n_rx_reorder_pkt(struct mwifiex_private *, u16 seqNum, u16 tid, u8 *ta, diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c index ce61b6fae1c9..5c7fd185373c 100644 --- a/drivers/net/wireless/mwifiex/cfg80211.c +++ b/drivers/net/wireless/mwifiex/cfg80211.c @@ -958,6 +958,7 @@ static int mwifiex_cfg80211_start_ap(struct wiphy *wiphy, case NL80211_HIDDEN_SSID_ZERO_CONTENTS: /* firmware doesn't support this type of hidden SSID */ default: + kfree(bss_cfg); return -EINVAL; } diff --git a/drivers/net/wireless/mwifiex/ie.c b/drivers/net/wireless/mwifiex/ie.c index ceb82cd749cc..383820a52beb 100644 --- a/drivers/net/wireless/mwifiex/ie.c +++ b/drivers/net/wireless/mwifiex/ie.c @@ -213,6 +213,7 @@ mwifiex_update_uap_custom_ie(struct mwifiex_private *priv, /* save assoc resp ie index after auto-indexing */ *assoc_idx = *((u16 *)pos); + kfree(ap_custom_ie); return ret; } diff --git a/drivers/net/wireless/mwifiex/sdio.c b/drivers/net/wireless/mwifiex/sdio.c index e0377473282f..fc8a9bfa1248 100644 --- a/drivers/net/wireless/mwifiex/sdio.c +++ b/drivers/net/wireless/mwifiex/sdio.c @@ -978,10 +978,10 @@ static int mwifiex_decode_rx_packet(struct mwifiex_adapter *adapter, dev_dbg(adapter->dev, "info: --- Rx: Event ---\n"); adapter->event_cause = *(u32 *) skb->data; - skb_pull(skb, MWIFIEX_EVENT_HEADER_LEN); - if ((skb->len > 0) && (skb->len < MAX_EVENT_SIZE)) - memcpy(adapter->event_body, skb->data, skb->len); + memcpy(adapter->event_body, + skb->data + MWIFIEX_EVENT_HEADER_LEN, + skb->len); /* event cause has been saved to adapter->event_cause */ adapter->event_received = true; diff --git a/drivers/net/wireless/mwifiex/sta_event.c b/drivers/net/wireless/mwifiex/sta_event.c index 4ace5a3dcd23..11e731f3581c 100644 --- a/drivers/net/wireless/mwifiex/sta_event.c +++ b/drivers/net/wireless/mwifiex/sta_event.c @@ -406,9 +406,9 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv) break; case EVENT_UAP_STA_ASSOC: - skb_pull(adapter->event_skb, MWIFIEX_UAP_EVENT_EXTRA_HEADER); memset(&sinfo, 0, sizeof(sinfo)); - event = (struct mwifiex_assoc_event *)adapter->event_skb->data; + event = (struct mwifiex_assoc_event *) + (adapter->event_body + MWIFIEX_UAP_EVENT_EXTRA_HEADER); if (le16_to_cpu(event->type) == TLV_TYPE_UAP_MGMT_FRAME) { len = -1; @@ -433,9 +433,8 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv) GFP_KERNEL); break; case EVENT_UAP_STA_DEAUTH: - skb_pull(adapter->event_skb, MWIFIEX_UAP_EVENT_EXTRA_HEADER); - cfg80211_del_sta(priv->netdev, adapter->event_skb->data, - GFP_KERNEL); + cfg80211_del_sta(priv->netdev, adapter->event_body + + MWIFIEX_UAP_EVENT_EXTRA_HEADER, GFP_KERNEL); break; case EVENT_UAP_BSS_IDLE: priv->media_connected = false; diff --git a/drivers/net/wireless/mwifiex/usb.c b/drivers/net/wireless/mwifiex/usb.c index 49ebf20c56eb..22a5916564b8 100644 --- a/drivers/net/wireless/mwifiex/usb.c +++ b/drivers/net/wireless/mwifiex/usb.c @@ -49,6 +49,7 @@ static int mwifiex_usb_recv(struct mwifiex_adapter *adapter, struct device *dev = adapter->dev; u32 recv_type; __le32 tmp; + int ret; if (adapter->hs_activated) mwifiex_process_hs_config(adapter); @@ -69,16 +70,19 @@ static int mwifiex_usb_recv(struct mwifiex_adapter *adapter, case MWIFIEX_USB_TYPE_CMD: if (skb->len > MWIFIEX_SIZE_OF_CMD_BUFFER) { dev_err(dev, "CMD: skb->len too large\n"); - return -1; + ret = -1; + goto exit_restore_skb; } else if (!adapter->curr_cmd) { dev_dbg(dev, "CMD: no curr_cmd\n"); if (adapter->ps_state == PS_STATE_SLEEP_CFM) { mwifiex_process_sleep_confirm_resp( adapter, skb->data, skb->len); - return 0; + ret = 0; + goto exit_restore_skb; } - return -1; + ret = -1; + goto exit_restore_skb; } adapter->curr_cmd->resp_skb = skb; @@ -87,20 +91,22 @@ static int mwifiex_usb_recv(struct mwifiex_adapter *adapter, case MWIFIEX_USB_TYPE_EVENT: if (skb->len < sizeof(u32)) { dev_err(dev, "EVENT: skb->len too small\n"); - return -1; + ret = -1; + goto exit_restore_skb; } skb_copy_from_linear_data(skb, &tmp, sizeof(u32)); adapter->event_cause = le32_to_cpu(tmp); - skb_pull(skb, sizeof(u32)); dev_dbg(dev, "event_cause %#x\n", adapter->event_cause); if (skb->len > MAX_EVENT_SIZE) { dev_err(dev, "EVENT: event body too large\n"); - return -1; + ret = -1; + goto exit_restore_skb; } - skb_copy_from_linear_data(skb, adapter->event_body, - skb->len); + memcpy(adapter->event_body, skb->data + + MWIFIEX_EVENT_HEADER_LEN, skb->len); + adapter->event_received = true; adapter->event_skb = skb; break; @@ -124,6 +130,12 @@ static int mwifiex_usb_recv(struct mwifiex_adapter *adapter, } return -EINPROGRESS; + +exit_restore_skb: + /* The buffer will be reused for further cmds/events */ + skb_push(skb, INTF_HEADER_LEN); + + return ret; } static void mwifiex_usb_rx_complete(struct urb *urb) diff --git a/drivers/net/wireless/mwifiex/wmm.c b/drivers/net/wireless/mwifiex/wmm.c index f3fc65515857..3fa4d4176993 100644 --- a/drivers/net/wireless/mwifiex/wmm.c +++ b/drivers/net/wireless/mwifiex/wmm.c @@ -404,6 +404,8 @@ mwifiex_wmm_init(struct mwifiex_adapter *adapter) priv->add_ba_param.tx_win_size = MWIFIEX_AMPDU_DEF_TXWINSIZE; priv->add_ba_param.rx_win_size = MWIFIEX_AMPDU_DEF_RXWINSIZE; + mwifiex_reset_11n_rx_seq_num(priv); + atomic_set(&priv->wmm.tx_pkts_queued, 0); atomic_set(&priv->wmm.highest_queued_prio, HIGH_PRIO_TID); } @@ -1221,6 +1223,7 @@ mwifiex_dequeue_tx_packet(struct mwifiex_adapter *adapter) if (!ptr->is_11n_enabled || mwifiex_is_ba_stream_setup(priv, ptr, tid) || + priv->wps.session_enable || ((priv->sec_info.wpa_enabled || priv->sec_info.wpa2_enabled) && !priv->wpa_is_gtk_set)) { diff --git a/drivers/net/wireless/rt2x00/rt2x00usb.c b/drivers/net/wireless/rt2x00/rt2x00usb.c index d357d1ed92f6..74ecc33fdd90 100644 --- a/drivers/net/wireless/rt2x00/rt2x00usb.c +++ b/drivers/net/wireless/rt2x00/rt2x00usb.c @@ -436,8 +436,8 @@ void rt2x00usb_kick_queue(struct data_queue *queue) case QID_RX: if (!rt2x00queue_full(queue)) rt2x00queue_for_each_entry(queue, - Q_INDEX_DONE, Q_INDEX, + Q_INDEX_DONE, NULL, rt2x00usb_kick_rx_entry); break; diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c index d228358e6a40..9970c2b1b199 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c +++ b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c @@ -301,9 +301,11 @@ static struct usb_device_id rtl8192c_usb_ids[] = { {RTL_USB_DEVICE(0x07b8, 0x8188, rtl92cu_hal_cfg)}, /*Abocom - Abocom*/ {RTL_USB_DEVICE(0x07b8, 0x8189, rtl92cu_hal_cfg)}, /*Funai - Abocom*/ {RTL_USB_DEVICE(0x0846, 0x9041, rtl92cu_hal_cfg)}, /*NetGear WNA1000M*/ + {RTL_USB_DEVICE(0x0bda, 0x5088, rtl92cu_hal_cfg)}, /*Thinkware-CC&C*/ {RTL_USB_DEVICE(0x0df6, 0x0052, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/ {RTL_USB_DEVICE(0x0df6, 0x005c, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/ {RTL_USB_DEVICE(0x0eb0, 0x9071, rtl92cu_hal_cfg)}, /*NO Brand - Etop*/ + {RTL_USB_DEVICE(0x4856, 0x0091, rtl92cu_hal_cfg)}, /*NetweeN - Feixun*/ /* HP - Lite-On ,8188CUS Slim Combo */ {RTL_USB_DEVICE(0x103c, 0x1629, rtl92cu_hal_cfg)}, {RTL_USB_DEVICE(0x13d3, 0x3357, rtl92cu_hal_cfg)}, /* AzureWave */ @@ -346,6 +348,7 @@ static struct usb_device_id rtl8192c_usb_ids[] = { {RTL_USB_DEVICE(0x07b8, 0x8178, rtl92cu_hal_cfg)}, /*Funai -Abocom*/ {RTL_USB_DEVICE(0x0846, 0x9021, rtl92cu_hal_cfg)}, /*Netgear-Sercomm*/ {RTL_USB_DEVICE(0x0b05, 0x17ab, rtl92cu_hal_cfg)}, /*ASUS-Edimax*/ + {RTL_USB_DEVICE(0x0bda, 0x8186, rtl92cu_hal_cfg)}, /*Realtek 92CE-VAU*/ {RTL_USB_DEVICE(0x0df6, 0x0061, rtl92cu_hal_cfg)}, /*Sitecom-Edimax*/ {RTL_USB_DEVICE(0x0e66, 0x0019, rtl92cu_hal_cfg)}, /*Hawking-Edimax*/ {RTL_USB_DEVICE(0x2001, 0x3307, rtl92cu_hal_cfg)}, /*D-Link-Cameo*/ diff --git a/drivers/net/wireless/ti/wlcore/Kconfig b/drivers/net/wireless/ti/wlcore/Kconfig index 54156b0b5c2d..d7b907e67170 100644 --- a/drivers/net/wireless/ti/wlcore/Kconfig +++ b/drivers/net/wireless/ti/wlcore/Kconfig @@ -1,7 +1,6 @@ config WLCORE tristate "TI wlcore support" depends on WL_TI && GENERIC_HARDIRQS && MAC80211 - depends on INET select FW_LOADER ---help--- This module contains the main code for TI WLAN chips. It abstracts diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 343ad29e211c..e44f8c2d239d 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -317,10 +317,9 @@ static const struct of_dev_auxdata *of_dev_lookup(const struct of_dev_auxdata *l for(; lookup->compatible != NULL; lookup++) { if (!of_device_is_compatible(np, lookup->compatible)) continue; - if (of_address_to_resource(np, 0, &res)) - continue; - if (res.start != lookup->phys_addr) - continue; + if (!of_address_to_resource(np, 0, &res)) + if (res.start != lookup->phys_addr) + continue; pr_debug("%s: devname=%s\n", np->full_name, lookup->name); return lookup; } @@ -462,4 +461,5 @@ int of_platform_populate(struct device_node *root, of_node_put(root); return rc; } +EXPORT_SYMBOL_GPL(of_platform_populate); #endif /* CONFIG_OF_ADDRESS */ diff --git a/drivers/oprofile/oprofile_perf.c b/drivers/oprofile/oprofile_perf.c index efc4b7f308cf..f3cfa0b9adfa 100644 --- a/drivers/oprofile/oprofile_perf.c +++ b/drivers/oprofile/oprofile_perf.c @@ -1,5 +1,6 @@ /* * Copyright 2010 ARM Ltd. + * Copyright 2012 Advanced Micro Devices, Inc., Robert Richter * * Perf-events backend for OProfile. */ @@ -25,7 +26,7 @@ static int oprofile_perf_enabled; static DEFINE_MUTEX(oprofile_perf_mutex); static struct op_counter_config *counter_config; -static struct perf_event **perf_events[NR_CPUS]; +static DEFINE_PER_CPU(struct perf_event **, perf_events); static int num_counters; /* @@ -38,7 +39,7 @@ static void op_overflow_handler(struct perf_event *event, u32 cpu = smp_processor_id(); for (id = 0; id < num_counters; ++id) - if (perf_events[cpu][id] == event) + if (per_cpu(perf_events, cpu)[id] == event) break; if (id != num_counters) @@ -74,7 +75,7 @@ static int op_create_counter(int cpu, int event) { struct perf_event *pevent; - if (!counter_config[event].enabled || perf_events[cpu][event]) + if (!counter_config[event].enabled || per_cpu(perf_events, cpu)[event]) return 0; pevent = perf_event_create_kernel_counter(&counter_config[event].attr, @@ -91,18 +92,18 @@ static int op_create_counter(int cpu, int event) return -EBUSY; } - perf_events[cpu][event] = pevent; + per_cpu(perf_events, cpu)[event] = pevent; return 0; } static void op_destroy_counter(int cpu, int event) { - struct perf_event *pevent = perf_events[cpu][event]; + struct perf_event *pevent = per_cpu(perf_events, cpu)[event]; if (pevent) { perf_event_release_kernel(pevent); - perf_events[cpu][event] = NULL; + per_cpu(perf_events, cpu)[event] = NULL; } } @@ -257,12 +258,12 @@ void oprofile_perf_exit(void) for_each_possible_cpu(cpu) { for (id = 0; id < num_counters; ++id) { - event = perf_events[cpu][id]; + event = per_cpu(perf_events, cpu)[id]; if (event) perf_event_release_kernel(event); } - kfree(perf_events[cpu]); + kfree(per_cpu(perf_events, cpu)); } kfree(counter_config); @@ -277,8 +278,6 @@ int __init oprofile_perf_init(struct oprofile_operations *ops) if (ret) return ret; - memset(&perf_events, 0, sizeof(perf_events)); - num_counters = perf_num_counters(); if (num_counters <= 0) { pr_info("oprofile: no performance counters\n"); @@ -298,9 +297,9 @@ int __init oprofile_perf_init(struct oprofile_operations *ops) } for_each_possible_cpu(cpu) { - perf_events[cpu] = kcalloc(num_counters, + per_cpu(perf_events, cpu) = kcalloc(num_counters, sizeof(struct perf_event *), GFP_KERNEL); - if (!perf_events[cpu]) { + if (!per_cpu(perf_events, cpu)) { pr_info("oprofile: failed to allocate %d perf events " "for cpu %d\n", num_counters, cpu); ret = -ENOMEM; diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index bf0cee629b60..099f46cd8e87 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -748,6 +748,18 @@ static int pci_pm_suspend_noirq(struct device *dev) pci_pm_set_unknown_state(pci_dev); + /* + * Some BIOSes from ASUS have a bug: If a USB EHCI host controller's + * PCI COMMAND register isn't 0, the BIOS assumes that the controller + * hasn't been quiesced and tries to turn it off. If the controller + * is already in D3, this can hang or cause memory corruption. + * + * Since the value of the COMMAND register doesn't matter once the + * device has been suspended, we can safely set it to 0 here. + */ + if (pci_dev->class == PCI_CLASS_SERIAL_USB_EHCI) + pci_write_config_word(pci_dev, PCI_COMMAND, 0); + return 0; } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 77cb54a65cde..447e83472c01 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1744,11 +1744,6 @@ int pci_prepare_to_sleep(struct pci_dev *dev) if (target_state == PCI_POWER_ERROR) return -EIO; - /* Some devices mustn't be in D3 during system sleep */ - if (target_state == PCI_D3hot && - (dev->dev_flags & PCI_DEV_FLAGS_NO_D3_DURING_SLEEP)) - return 0; - pci_enable_wake(dev, target_state, device_may_wakeup(&dev->dev)); error = pci_set_power_state(dev, target_state); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 194b243a2817..2a7521677541 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -2929,32 +2929,6 @@ static void __devinit disable_igfx_irq(struct pci_dev *dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0102, disable_igfx_irq); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x010a, disable_igfx_irq); -/* - * The Intel 6 Series/C200 Series chipset's EHCI controllers on many - * ASUS motherboards will cause memory corruption or a system crash - * if they are in D3 while the system is put into S3 sleep. - */ -static void __devinit asus_ehci_no_d3(struct pci_dev *dev) -{ - const char *sys_info; - static const char good_Asus_board[] = "P8Z68-V"; - - if (dev->dev_flags & PCI_DEV_FLAGS_NO_D3_DURING_SLEEP) - return; - if (dev->subsystem_vendor != PCI_VENDOR_ID_ASUSTEK) - return; - sys_info = dmi_get_system_info(DMI_BOARD_NAME); - if (sys_info && memcmp(sys_info, good_Asus_board, - sizeof(good_Asus_board) - 1) == 0) - return; - - dev_info(&dev->dev, "broken D3 during system sleep on ASUS\n"); - dev->dev_flags |= PCI_DEV_FLAGS_NO_D3_DURING_SLEEP; - device_set_wakeup_capable(&dev->dev, false); -} -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1c26, asus_ehci_no_d3); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1c2d, asus_ehci_no_d3); - static void pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f, struct pci_fixup *end) { diff --git a/drivers/pinctrl/pinctrl-imx.c b/drivers/pinctrl/pinctrl-imx.c index dd6d93aa5334..90c837f469a6 100644 --- a/drivers/pinctrl/pinctrl-imx.c +++ b/drivers/pinctrl/pinctrl-imx.c @@ -474,7 +474,9 @@ static int __devinit imx_pinctrl_parse_groups(struct device_node *np, grp->configs[j] = config & ~IMX_PAD_SION; } +#ifdef DEBUG IMX_PMX_DUMP(info, grp->pins, grp->mux_mode, grp->configs, grp->npins); +#endif return 0; } diff --git a/drivers/pinctrl/pinctrl-imx6q.c b/drivers/pinctrl/pinctrl-imx6q.c index 7737d4d71a3c..e9bf71fbedca 100644 --- a/drivers/pinctrl/pinctrl-imx6q.c +++ b/drivers/pinctrl/pinctrl-imx6q.c @@ -1950,6 +1950,8 @@ static struct imx_pin_reg imx6q_pin_regs[] = { IMX_PIN_REG(MX6Q_PAD_SD2_DAT3, 0x0744, 0x035C, 5, 0x0000, 0), /* MX6Q_PAD_SD2_DAT3__GPIO_1_12 */ IMX_PIN_REG(MX6Q_PAD_SD2_DAT3, 0x0744, 0x035C, 6, 0x0000, 0), /* MX6Q_PAD_SD2_DAT3__SJC_DONE */ IMX_PIN_REG(MX6Q_PAD_SD2_DAT3, 0x0744, 0x035C, 7, 0x0000, 0), /* MX6Q_PAD_SD2_DAT3__ANATOP_TESTO_3 */ + IMX_PIN_REG(MX6Q_PAD_ENET_RX_ER, 0x04EC, 0x01D8, 0, 0x0000, 0), /* MX6Q_PAD_ENET_RX_ER__ANATOP_USBOTG_ID */ + IMX_PIN_REG(MX6Q_PAD_GPIO_1, 0x05F4, 0x0224, 3, 0x0000, 0), /* MX6Q_PAD_GPIO_1__ANATOP_USBOTG_ID */ }; /* Pad names for the pinmux subsystem */ diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index ce875dc365e5..c8f40c9c0428 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -1877,8 +1877,7 @@ static int acer_platform_remove(struct platform_device *device) return 0; } -static int acer_platform_suspend(struct platform_device *dev, -pm_message_t state) +static int acer_suspend(struct device *dev) { u32 value; struct acer_data *data = &interface->data; @@ -1900,7 +1899,7 @@ pm_message_t state) return 0; } -static int acer_platform_resume(struct platform_device *device) +static int acer_resume(struct device *dev) { struct acer_data *data = &interface->data; @@ -1916,6 +1915,8 @@ static int acer_platform_resume(struct platform_device *device) return 0; } +static SIMPLE_DEV_PM_OPS(acer_pm, acer_suspend, acer_resume); + static void acer_platform_shutdown(struct platform_device *device) { struct acer_data *data = &interface->data; @@ -1931,11 +1932,10 @@ static struct platform_driver acer_platform_driver = { .driver = { .name = "acer-wmi", .owner = THIS_MODULE, + .pm = &acer_pm, }, .probe = acer_platform_probe, .remove = acer_platform_remove, - .suspend = acer_platform_suspend, - .resume = acer_platform_resume, .shutdown = acer_platform_shutdown, }; diff --git a/drivers/platform/x86/classmate-laptop.c b/drivers/platform/x86/classmate-laptop.c index 94f93b621d7b..e2230a2b2f8e 100644 --- a/drivers/platform/x86/classmate-laptop.c +++ b/drivers/platform/x86/classmate-laptop.c @@ -362,15 +362,18 @@ static int cmpc_tablet_remove(struct acpi_device *acpi, int type) return cmpc_remove_acpi_notify_device(acpi); } -static int cmpc_tablet_resume(struct acpi_device *acpi) +static int cmpc_tablet_resume(struct device *dev) { - struct input_dev *inputdev = dev_get_drvdata(&acpi->dev); + struct input_dev *inputdev = dev_get_drvdata(dev); + unsigned long long val = 0; - if (ACPI_SUCCESS(cmpc_get_tablet(acpi->handle, &val))) + if (ACPI_SUCCESS(cmpc_get_tablet(to_acpi_device(dev)->handle, &val))) input_report_switch(inputdev, SW_TABLET_MODE, !val); return 0; } +static SIMPLE_DEV_PM_OPS(cmpc_tablet_pm, NULL, cmpc_tablet_resume); + static const struct acpi_device_id cmpc_tablet_device_ids[] = { {CMPC_TABLET_HID, 0}, {"", 0} @@ -384,9 +387,9 @@ static struct acpi_driver cmpc_tablet_acpi_driver = { .ops = { .add = cmpc_tablet_add, .remove = cmpc_tablet_remove, - .resume = cmpc_tablet_resume, .notify = cmpc_tablet_handler, - } + }, + .drv.pm = &cmpc_tablet_pm, }; diff --git a/drivers/platform/x86/fujitsu-tablet.c b/drivers/platform/x86/fujitsu-tablet.c index da267eae8ba8..d2e41735a47b 100644 --- a/drivers/platform/x86/fujitsu-tablet.c +++ b/drivers/platform/x86/fujitsu-tablet.c @@ -440,12 +440,14 @@ static int __devexit acpi_fujitsu_remove(struct acpi_device *adev, int type) return 0; } -static int acpi_fujitsu_resume(struct acpi_device *adev) +static int acpi_fujitsu_resume(struct device *dev) { fujitsu_reset(); return 0; } +static SIMPLE_DEV_PM_OPS(acpi_fujitsu_pm, NULL, acpi_fujitsu_resume); + static struct acpi_driver acpi_fujitsu_driver = { .name = MODULENAME, .class = "hotkey", @@ -453,8 +455,8 @@ static struct acpi_driver acpi_fujitsu_driver = { .ops = { .add = acpi_fujitsu_add, .remove = acpi_fujitsu_remove, - .resume = acpi_fujitsu_resume, - } + }, + .drv.pm = &acpi_fujitsu_pm, }; static int __init fujitsu_module_init(void) diff --git a/drivers/platform/x86/hdaps.c b/drivers/platform/x86/hdaps.c index 24a3ae065f1b..d9ab6f64dcec 100644 --- a/drivers/platform/x86/hdaps.c +++ b/drivers/platform/x86/hdaps.c @@ -305,17 +305,19 @@ static int hdaps_probe(struct platform_device *dev) return 0; } -static int hdaps_resume(struct platform_device *dev) +static int hdaps_resume(struct device *dev) { return hdaps_device_init(); } +static SIMPLE_DEV_PM_OPS(hdaps_pm, NULL, hdaps_resume); + static struct platform_driver hdaps_driver = { .probe = hdaps_probe, - .resume = hdaps_resume, .driver = { .name = "hdaps", .owner = THIS_MODULE, + .pm = &hdaps_pm, }, }; diff --git a/drivers/platform/x86/hp_accel.c b/drivers/platform/x86/hp_accel.c index 22b2dfa73148..f4d91154ad67 100644 --- a/drivers/platform/x86/hp_accel.c +++ b/drivers/platform/x86/hp_accel.c @@ -353,20 +353,22 @@ static int lis3lv02d_remove(struct acpi_device *device, int type) #ifdef CONFIG_PM -static int lis3lv02d_suspend(struct acpi_device *device, pm_message_t state) +static int lis3lv02d_suspend(struct device *dev) { /* make sure the device is off when we suspend */ lis3lv02d_poweroff(&lis3_dev); return 0; } -static int lis3lv02d_resume(struct acpi_device *device) +static int lis3lv02d_resume(struct device *dev) { return lis3lv02d_poweron(&lis3_dev); } + +static SIMPLE_DEV_PM_OPS(hp_accel_pm, lis3lv02d_suspend, lis3lv02d_resume); +#define HP_ACCEL_PM (&hp_accel_pm) #else -#define lis3lv02d_suspend NULL -#define lis3lv02d_resume NULL +#define HP_ACCEL_PM NULL #endif /* For the HP MDPS aka 3D Driveguard */ @@ -377,9 +379,8 @@ static struct acpi_driver lis3lv02d_driver = { .ops = { .add = lis3lv02d_add, .remove = lis3lv02d_remove, - .suspend = lis3lv02d_suspend, - .resume = lis3lv02d_resume, - } + }, + .drv.pm = HP_ACCEL_PM, }; static int __init lis3lv02d_init_module(void) diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 4f20f8dd3d7c..17f6dfd8dbfb 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -694,10 +694,10 @@ MODULE_DEVICE_TABLE(acpi, ideapad_device_ids); static int __devinit ideapad_acpi_add(struct acpi_device *adevice) { int ret, i; - unsigned long cfg; + int cfg; struct ideapad_private *priv; - if (read_method_int(adevice->handle, "_CFG", (int *)&cfg)) + if (read_method_int(adevice->handle, "_CFG", &cfg)) return -ENODEV; priv = kzalloc(sizeof(*priv), GFP_KERNEL); @@ -721,7 +721,7 @@ static int __devinit ideapad_acpi_add(struct acpi_device *adevice) goto input_failed; for (i = 0; i < IDEAPAD_RFKILL_DEV_NUM; i++) { - if (test_bit(ideapad_rfk_data[i].cfgbit, &cfg)) + if (test_bit(ideapad_rfk_data[i].cfgbit, &priv->cfg)) ideapad_register_rfkill(adevice, i); else priv->rfk[i] = NULL; diff --git a/drivers/platform/x86/intel_ips.c b/drivers/platform/x86/intel_ips.c index 0ffdb3cde2bb..5051aa970e0a 100644 --- a/drivers/platform/x86/intel_ips.c +++ b/drivers/platform/x86/intel_ips.c @@ -72,6 +72,7 @@ #include <linux/string.h> #include <linux/tick.h> #include <linux/timer.h> +#include <linux/dmi.h> #include <drm/i915_drm.h> #include <asm/msr.h> #include <asm/processor.h> @@ -1485,6 +1486,24 @@ static DEFINE_PCI_DEVICE_TABLE(ips_id_table) = { MODULE_DEVICE_TABLE(pci, ips_id_table); +static int ips_blacklist_callback(const struct dmi_system_id *id) +{ + pr_info("Blacklisted intel_ips for %s\n", id->ident); + return 1; +} + +static const struct dmi_system_id ips_blacklist[] = { + { + .callback = ips_blacklist_callback, + .ident = "HP ProBook", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook"), + }, + }, + { } /* terminating entry */ +}; + static int ips_probe(struct pci_dev *dev, const struct pci_device_id *id) { u64 platform_info; @@ -1494,6 +1513,9 @@ static int ips_probe(struct pci_dev *dev, const struct pci_device_id *id) u16 htshi, trc, trc_required_mask; u8 tse; + if (dmi_check_system(ips_blacklist)) + return -ENODEV; + ips = kzalloc(sizeof(struct ips_driver), GFP_KERNEL); if (!ips) return -ENOMEM; @@ -1697,21 +1719,6 @@ static void ips_remove(struct pci_dev *dev) dev_dbg(&dev->dev, "IPS driver removed\n"); } -#ifdef CONFIG_PM -static int ips_suspend(struct pci_dev *dev, pm_message_t state) -{ - return 0; -} - -static int ips_resume(struct pci_dev *dev) -{ - return 0; -} -#else -#define ips_suspend NULL -#define ips_resume NULL -#endif /* CONFIG_PM */ - static void ips_shutdown(struct pci_dev *dev) { } @@ -1721,8 +1728,6 @@ static struct pci_driver ips_pci_driver = { .id_table = ips_id_table, .probe = ips_probe, .remove = ips_remove, - .suspend = ips_suspend, - .resume = ips_resume, .shutdown = ips_shutdown, }; diff --git a/drivers/platform/x86/intel_mid_thermal.c b/drivers/platform/x86/intel_mid_thermal.c index 5ae9cd9c7e6e..ea7422f6fa03 100644 --- a/drivers/platform/x86/intel_mid_thermal.c +++ b/drivers/platform/x86/intel_mid_thermal.c @@ -418,23 +418,23 @@ static struct thermal_device_info *initialize_sensor(int index) /** * mid_thermal_resume - resume routine - * @pdev: platform device structure + * @dev: device structure * * mid thermal resume: re-initializes the adc. Can sleep. */ -static int mid_thermal_resume(struct platform_device *pdev) +static int mid_thermal_resume(struct device *dev) { - return mid_initialize_adc(&pdev->dev); + return mid_initialize_adc(dev); } /** * mid_thermal_suspend - suspend routine - * @pdev: platform device structure + * @dev: device structure * * mid thermal suspend implements the suspend functionality * by stopping the ADC. Can sleep. */ -static int mid_thermal_suspend(struct platform_device *pdev, pm_message_t mesg) +static int mid_thermal_suspend(struct device *dev) { /* * This just stops the ADC and does not disable it. @@ -444,6 +444,9 @@ static int mid_thermal_suspend(struct platform_device *pdev, pm_message_t mesg) return configure_adc(0); } +static SIMPLE_DEV_PM_OPS(mid_thermal_pm, + mid_thermal_suspend, mid_thermal_resume); + /** * read_curr_temp - reads the current temperature and stores in temp * @temp: holds the current temperature value after reading @@ -557,10 +560,9 @@ static struct platform_driver mid_thermal_driver = { .driver = { .name = DRIVER_NAME, .owner = THIS_MODULE, + .pm = &mid_thermal_pm, }, .probe = mid_thermal_probe, - .suspend = mid_thermal_suspend, - .resume = mid_thermal_resume, .remove = __devexit_p(mid_thermal_remove), .id_table = therm_id_table, }; diff --git a/drivers/platform/x86/msi-laptop.c b/drivers/platform/x86/msi-laptop.c index bb5132128b33..f64441844317 100644 --- a/drivers/platform/x86/msi-laptop.c +++ b/drivers/platform/x86/msi-laptop.c @@ -85,7 +85,8 @@ #define MSI_STANDARD_EC_TOUCHPAD_ADDRESS 0xe4 #define MSI_STANDARD_EC_TOUCHPAD_MASK (1 << 4) -static int msi_laptop_resume(struct platform_device *device); +static int msi_laptop_resume(struct device *device); +static SIMPLE_DEV_PM_OPS(msi_laptop_pm, NULL, msi_laptop_resume); #define MSI_STANDARD_EC_DEVICES_EXISTS_ADDRESS 0x2f @@ -437,8 +438,8 @@ static struct platform_driver msipf_driver = { .driver = { .name = "msi-laptop-pf", .owner = THIS_MODULE, + .pm = &msi_laptop_pm, }, - .resume = msi_laptop_resume, }; static struct platform_device *msipf_device; @@ -752,7 +753,7 @@ err_bluetooth: return retval; } -static int msi_laptop_resume(struct platform_device *device) +static int msi_laptop_resume(struct device *device) { u8 data; int result; diff --git a/drivers/platform/x86/panasonic-laptop.c b/drivers/platform/x86/panasonic-laptop.c index ffff8b4b4949..24480074bcf0 100644 --- a/drivers/platform/x86/panasonic-laptop.c +++ b/drivers/platform/x86/panasonic-laptop.c @@ -177,7 +177,6 @@ enum SINF_BITS { SINF_NUM_BATTERIES = 0, static int acpi_pcc_hotkey_add(struct acpi_device *device); static int acpi_pcc_hotkey_remove(struct acpi_device *device, int type); -static int acpi_pcc_hotkey_resume(struct acpi_device *device); static void acpi_pcc_hotkey_notify(struct acpi_device *device, u32 event); static const struct acpi_device_id pcc_device_ids[] = { @@ -189,6 +188,9 @@ static const struct acpi_device_id pcc_device_ids[] = { }; MODULE_DEVICE_TABLE(acpi, pcc_device_ids); +static int acpi_pcc_hotkey_resume(struct device *dev); +static SIMPLE_DEV_PM_OPS(acpi_pcc_hotkey_pm, NULL, acpi_pcc_hotkey_resume); + static struct acpi_driver acpi_pcc_driver = { .name = ACPI_PCC_DRIVER_NAME, .class = ACPI_PCC_CLASS, @@ -196,9 +198,9 @@ static struct acpi_driver acpi_pcc_driver = { .ops = { .add = acpi_pcc_hotkey_add, .remove = acpi_pcc_hotkey_remove, - .resume = acpi_pcc_hotkey_resume, .notify = acpi_pcc_hotkey_notify, }, + .drv.pm = &acpi_pcc_hotkey_pm, }; static const struct key_entry panasonic_keymap[] = { @@ -538,11 +540,15 @@ static void acpi_pcc_destroy_input(struct pcc_acpi *pcc) /* kernel module interface */ -static int acpi_pcc_hotkey_resume(struct acpi_device *device) +static int acpi_pcc_hotkey_resume(struct device *dev) { - struct pcc_acpi *pcc = acpi_driver_data(device); + struct pcc_acpi *pcc; + + if (!dev) + return -EINVAL; - if (device == NULL || pcc == NULL) + pcc = acpi_driver_data(to_acpi_device(dev)); + if (!pcc) return -EINVAL; ACPI_DEBUG_PRINT((ACPI_DB_ERROR, "Sticky mode restore: %d\n", diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c index 210d4ae547c2..9363969ad07a 100644 --- a/drivers/platform/x86/sony-laptop.c +++ b/drivers/platform/x86/sony-laptop.c @@ -973,7 +973,7 @@ static ssize_t sony_nc_sysfs_store(struct device *dev, struct device_attribute *attr, const char *buffer, size_t count) { - unsigned long value = 0; + int value; int ret = 0; struct sony_nc_value *item = container_of(attr, struct sony_nc_value, devattr); @@ -984,7 +984,7 @@ static ssize_t sony_nc_sysfs_store(struct device *dev, if (count > 31) return -EINVAL; - if (kstrtoul(buffer, 10, &value)) + if (kstrtoint(buffer, 10, &value)) return -EINVAL; if (item->validate) @@ -994,7 +994,7 @@ static ssize_t sony_nc_sysfs_store(struct device *dev, return value; ret = sony_nc_int_call(sony_nc_acpi_handle, *item->acpiset, - (int *)&value, NULL); + &value, NULL); if (ret < 0) return -EIO; @@ -1010,6 +1010,7 @@ static ssize_t sony_nc_sysfs_store(struct device *dev, struct sony_backlight_props { struct backlight_device *dev; int handle; + int cmd_base; u8 offset; u8 maxlvl; }; @@ -1037,7 +1038,7 @@ static int sony_nc_get_brightness_ng(struct backlight_device *bd) struct sony_backlight_props *sdev = (struct sony_backlight_props *)bl_get_data(bd); - sony_call_snc_handle(sdev->handle, 0x0200, &result); + sony_call_snc_handle(sdev->handle, sdev->cmd_base + 0x100, &result); return (result & 0xff) - sdev->offset; } @@ -1049,7 +1050,8 @@ static int sony_nc_update_status_ng(struct backlight_device *bd) (struct sony_backlight_props *)bl_get_data(bd); value = bd->props.brightness + sdev->offset; - if (sony_call_snc_handle(sdev->handle, 0x0100 | (value << 16), &result)) + if (sony_call_snc_handle(sdev->handle, sdev->cmd_base | (value << 0x10), + &result)) return -EIO; return value; @@ -1172,6 +1174,11 @@ static int sony_nc_hotkeys_decode(u32 event, unsigned int handle) /* * ACPI callbacks */ +enum event_types { + HOTKEY = 1, + KILLSWITCH, + GFX_SWITCH +}; static void sony_nc_notify(struct acpi_device *device, u32 event) { u32 real_ev = event; @@ -1196,7 +1203,7 @@ static void sony_nc_notify(struct acpi_device *device, u32 event) /* hotkey event */ case 0x0100: case 0x0127: - ev_type = 1; + ev_type = HOTKEY; real_ev = sony_nc_hotkeys_decode(event, handle); if (real_ev > 0) @@ -1216,7 +1223,7 @@ static void sony_nc_notify(struct acpi_device *device, u32 event) * update the rfkill device status when the * switch is moved. */ - ev_type = 2; + ev_type = KILLSWITCH; sony_call_snc_handle(handle, 0x0100, &result); real_ev = result & 0x03; @@ -1226,6 +1233,24 @@ static void sony_nc_notify(struct acpi_device *device, u32 event) break; + case 0x0128: + case 0x0146: + /* Hybrid GFX switching */ + sony_call_snc_handle(handle, 0x0000, &result); + dprintk("GFX switch event received (reason: %s)\n", + (result & 0x01) ? + "switch change" : "unknown"); + + /* verify the switch state + * 1: discrete GFX + * 0: integrated GFX + */ + sony_call_snc_handle(handle, 0x0100, &result); + + ev_type = GFX_SWITCH; + real_ev = result & 0xff; + break; + default: dprintk("Unknown event 0x%x for handle 0x%x\n", event, handle); @@ -1238,7 +1263,7 @@ static void sony_nc_notify(struct acpi_device *device, u32 event) } else { /* old style event */ - ev_type = 1; + ev_type = HOTKEY; sony_laptop_report_input_event(real_ev); } @@ -1452,7 +1477,7 @@ static void sony_nc_function_resume(void) &result); } -static int sony_nc_resume(struct acpi_device *device) +static int sony_nc_resume(struct device *dev) { struct sony_nc_value *item; acpi_handle handle; @@ -1484,6 +1509,8 @@ static int sony_nc_resume(struct acpi_device *device) return 0; } +static SIMPLE_DEV_PM_OPS(sony_nc_pm, NULL, sony_nc_resume); + static void sony_nc_rfkill_cleanup(void) { int i; @@ -1893,32 +1920,33 @@ static ssize_t sony_nc_battery_care_limit_store(struct device *dev, * bits 4,5: store the limit into the EC * bits 6,7: store the limit into the battery */ + cmd = 0; - /* - * handle 0x0115 should allow storing on battery too; - * handle 0x0136 same as 0x0115 + health status; - * handle 0x013f, same as 0x0136 but no storing on the battery - * - * Store only inside the EC for now, regardless the handle number - */ - if (value == 0) - /* disable limits */ - cmd = 0x0; + if (value > 0) { + if (value <= 50) + cmd = 0x20; - else if (value <= 50) - cmd = 0x21; + else if (value <= 80) + cmd = 0x10; - else if (value <= 80) - cmd = 0x11; + else if (value <= 100) + cmd = 0x30; - else if (value <= 100) - cmd = 0x31; + else + return -EINVAL; - else - return -EINVAL; + /* + * handle 0x0115 should allow storing on battery too; + * handle 0x0136 same as 0x0115 + health status; + * handle 0x013f, same as 0x0136 but no storing on the battery + */ + if (bcare_ctl->handle != 0x013f) + cmd = cmd | (cmd << 2); - if (sony_call_snc_handle(bcare_ctl->handle, (cmd << 0x10) | 0x0100, - &result)) + cmd = (cmd | 0x1) << 0x10; + } + + if (sony_call_snc_handle(bcare_ctl->handle, cmd | 0x0100, &result)) return -EIO; return count; @@ -2113,7 +2141,7 @@ static ssize_t sony_nc_thermal_mode_show(struct device *dev, struct device_attribute *attr, char *buffer) { ssize_t count = 0; - unsigned int mode = sony_nc_thermal_mode_get(); + int mode = sony_nc_thermal_mode_get(); if (mode < 0) return mode; @@ -2472,6 +2500,7 @@ static void sony_nc_backlight_ng_read_limits(int handle, { u64 offset; int i; + int lvl_table_len = 0; u8 min = 0xff, max = 0x00; unsigned char buffer[32] = { 0 }; @@ -2480,8 +2509,6 @@ static void sony_nc_backlight_ng_read_limits(int handle, props->maxlvl = 0xff; offset = sony_find_snc_handle(handle); - if (offset < 0) - return; /* try to read the boundaries from ACPI tables, if we fail the above * defaults should be reasonable @@ -2491,11 +2518,21 @@ static void sony_nc_backlight_ng_read_limits(int handle, if (i < 0) return; + switch (handle) { + case 0x012f: + case 0x0137: + lvl_table_len = 9; + break; + case 0x143: + lvl_table_len = 16; + break; + } + /* the buffer lists brightness levels available, brightness levels are * from position 0 to 8 in the array, other values are used by ALS * control. */ - for (i = 0; i < 9 && i < ARRAY_SIZE(buffer); i++) { + for (i = 0; i < lvl_table_len && i < ARRAY_SIZE(buffer); i++) { dprintk("Brightness level: %d\n", buffer[i]); @@ -2520,16 +2557,24 @@ static void sony_nc_backlight_setup(void) const struct backlight_ops *ops = NULL; struct backlight_properties props; - if (sony_find_snc_handle(0x12f) != -1) { + if (sony_find_snc_handle(0x12f) >= 0) { ops = &sony_backlight_ng_ops; + sony_bl_props.cmd_base = 0x0100; sony_nc_backlight_ng_read_limits(0x12f, &sony_bl_props); max_brightness = sony_bl_props.maxlvl - sony_bl_props.offset; - } else if (sony_find_snc_handle(0x137) != -1) { + } else if (sony_find_snc_handle(0x137) >= 0) { ops = &sony_backlight_ng_ops; + sony_bl_props.cmd_base = 0x0100; sony_nc_backlight_ng_read_limits(0x137, &sony_bl_props); max_brightness = sony_bl_props.maxlvl - sony_bl_props.offset; + } else if (sony_find_snc_handle(0x143) >= 0) { + ops = &sony_backlight_ng_ops; + sony_bl_props.cmd_base = 0x3000; + sony_nc_backlight_ng_read_limits(0x143, &sony_bl_props); + max_brightness = sony_bl_props.maxlvl - sony_bl_props.offset; + } else if (ACPI_SUCCESS(acpi_get_handle(sony_nc_acpi_handle, "GBRT", &unused))) { ops = &sony_backlight_ops; @@ -2597,6 +2642,12 @@ static int sony_nc_add(struct acpi_device *device) } } + result = sony_laptop_setup_input(device); + if (result) { + pr_err("Unable to create input devices\n"); + goto outplatform; + } + if (ACPI_SUCCESS(acpi_get_handle(sony_nc_acpi_handle, "ECON", &handle))) { int arg = 1; @@ -2614,12 +2665,6 @@ static int sony_nc_add(struct acpi_device *device) } /* setup input devices and helper fifo */ - result = sony_laptop_setup_input(device); - if (result) { - pr_err("Unable to create input devices\n"); - goto outsnc; - } - if (acpi_video_backlight_support()) { pr_info("brightness ignored, must be controlled by ACPI video driver\n"); } else { @@ -2667,22 +2712,21 @@ static int sony_nc_add(struct acpi_device *device) return 0; - out_sysfs: +out_sysfs: for (item = sony_nc_values; item->name; ++item) { device_remove_file(&sony_pf_device->dev, &item->devattr); } sony_nc_backlight_cleanup(); - - sony_laptop_remove_input(); - - outsnc: sony_nc_function_cleanup(sony_pf_device); sony_nc_handles_cleanup(sony_pf_device); - outpresent: +outplatform: + sony_laptop_remove_input(); + +outpresent: sony_pf_remove(); - outwalk: +outwalk: sony_nc_rfkill_cleanup(); return result; } @@ -2728,9 +2772,9 @@ static struct acpi_driver sony_nc_driver = { .ops = { .add = sony_nc_add, .remove = sony_nc_remove, - .resume = sony_nc_resume, .notify = sony_nc_notify, }, + .drv.pm = &sony_nc_pm, }; /*********** SPIC (SNY6001) Device ***********/ @@ -4243,19 +4287,22 @@ err_free_resources: return result; } -static int sony_pic_suspend(struct acpi_device *device, pm_message_t state) +static int sony_pic_suspend(struct device *dev) { - if (sony_pic_disable(device)) + if (sony_pic_disable(to_acpi_device(dev))) return -ENXIO; return 0; } -static int sony_pic_resume(struct acpi_device *device) +static int sony_pic_resume(struct device *dev) { - sony_pic_enable(device, spic_dev.cur_ioport, spic_dev.cur_irq); + sony_pic_enable(to_acpi_device(dev), + spic_dev.cur_ioport, spic_dev.cur_irq); return 0; } +static SIMPLE_DEV_PM_OPS(sony_pic_pm, sony_pic_suspend, sony_pic_resume); + static const struct acpi_device_id sony_pic_device_ids[] = { {SONY_PIC_HID, 0}, {"", 0}, @@ -4269,9 +4316,8 @@ static struct acpi_driver sony_pic_driver = { .ops = { .add = sony_pic_add, .remove = sony_pic_remove, - .suspend = sony_pic_suspend, - .resume = sony_pic_resume, }, + .drv.pm = &sony_pic_pm, }; static struct dmi_system_id __initdata sonypi_dmi_table[] = { diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 8b5610d88418..d5fd4a1193f8 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -277,7 +277,7 @@ struct ibm_struct { int (*write) (char *); void (*exit) (void); void (*resume) (void); - void (*suspend) (pm_message_t state); + void (*suspend) (void); void (*shutdown) (void); struct list_head all_drivers; @@ -922,8 +922,7 @@ static struct input_dev *tpacpi_inputdev; static struct mutex tpacpi_inputdev_send_mutex; static LIST_HEAD(tpacpi_all_drivers); -static int tpacpi_suspend_handler(struct platform_device *pdev, - pm_message_t state) +static int tpacpi_suspend_handler(struct device *dev) { struct ibm_struct *ibm, *itmp; @@ -931,13 +930,13 @@ static int tpacpi_suspend_handler(struct platform_device *pdev, &tpacpi_all_drivers, all_drivers) { if (ibm->suspend) - (ibm->suspend)(state); + (ibm->suspend)(); } return 0; } -static int tpacpi_resume_handler(struct platform_device *pdev) +static int tpacpi_resume_handler(struct device *dev) { struct ibm_struct *ibm, *itmp; @@ -951,6 +950,9 @@ static int tpacpi_resume_handler(struct platform_device *pdev) return 0; } +static SIMPLE_DEV_PM_OPS(tpacpi_pm, + tpacpi_suspend_handler, tpacpi_resume_handler); + static void tpacpi_shutdown_handler(struct platform_device *pdev) { struct ibm_struct *ibm, *itmp; @@ -967,9 +969,8 @@ static struct platform_driver tpacpi_pdriver = { .driver = { .name = TPACPI_DRVR_NAME, .owner = THIS_MODULE, + .pm = &tpacpi_pm, }, - .suspend = tpacpi_suspend_handler, - .resume = tpacpi_resume_handler, .shutdown = tpacpi_shutdown_handler, }; @@ -3758,7 +3759,7 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event) } } -static void hotkey_suspend(pm_message_t state) +static void hotkey_suspend(void) { /* Do these on suspend, we get the events on early resume! */ hotkey_wakeup_reason = TP_ACPI_WAKEUP_NONE; @@ -6329,7 +6330,7 @@ static int __init brightness_init(struct ibm_init_struct *iibm) return 0; } -static void brightness_suspend(pm_message_t state) +static void brightness_suspend(void) { tpacpi_brightness_checkpoint_nvram(); } @@ -6748,7 +6749,7 @@ static struct snd_kcontrol_new volume_alsa_control_mute __devinitdata = { .get = volume_alsa_mute_get, }; -static void volume_suspend(pm_message_t state) +static void volume_suspend(void) { tpacpi_volume_checkpoint_nvram(); } @@ -8107,7 +8108,7 @@ static void fan_exit(void) flush_workqueue(tpacpi_wq); } -static void fan_suspend(pm_message_t state) +static void fan_suspend(void) { int rc; diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index dab10f6edcd4..c13ba5bac93f 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -1296,10 +1296,9 @@ static void toshiba_acpi_notify(struct acpi_device *acpi_dev, u32 event) } } -static int toshiba_acpi_suspend(struct acpi_device *acpi_dev, - pm_message_t state) +static int toshiba_acpi_suspend(struct device *device) { - struct toshiba_acpi_dev *dev = acpi_driver_data(acpi_dev); + struct toshiba_acpi_dev *dev = acpi_driver_data(to_acpi_device(device)); u32 result; if (dev->hotkey_dev) @@ -1308,9 +1307,9 @@ static int toshiba_acpi_suspend(struct acpi_device *acpi_dev, return 0; } -static int toshiba_acpi_resume(struct acpi_device *acpi_dev) +static int toshiba_acpi_resume(struct device *device) { - struct toshiba_acpi_dev *dev = acpi_driver_data(acpi_dev); + struct toshiba_acpi_dev *dev = acpi_driver_data(to_acpi_device(device)); u32 result; if (dev->hotkey_dev) @@ -1319,6 +1318,9 @@ static int toshiba_acpi_resume(struct acpi_device *acpi_dev) return 0; } +static SIMPLE_DEV_PM_OPS(toshiba_acpi_pm, + toshiba_acpi_suspend, toshiba_acpi_resume); + static struct acpi_driver toshiba_acpi_driver = { .name = "Toshiba ACPI driver", .owner = THIS_MODULE, @@ -1328,9 +1330,8 @@ static struct acpi_driver toshiba_acpi_driver = { .add = toshiba_acpi_add, .remove = toshiba_acpi_remove, .notify = toshiba_acpi_notify, - .suspend = toshiba_acpi_suspend, - .resume = toshiba_acpi_resume, }, + .drv.pm = &toshiba_acpi_pm, }; static int __init toshiba_acpi_init(void) diff --git a/drivers/platform/x86/toshiba_bluetooth.c b/drivers/platform/x86/toshiba_bluetooth.c index 5fb7186694df..715a43cb5e3c 100644 --- a/drivers/platform/x86/toshiba_bluetooth.c +++ b/drivers/platform/x86/toshiba_bluetooth.c @@ -34,7 +34,6 @@ MODULE_LICENSE("GPL"); static int toshiba_bt_rfkill_add(struct acpi_device *device); static int toshiba_bt_rfkill_remove(struct acpi_device *device, int type); static void toshiba_bt_rfkill_notify(struct acpi_device *device, u32 event); -static int toshiba_bt_resume(struct acpi_device *device); static const struct acpi_device_id bt_device_ids[] = { { "TOS6205", 0}, @@ -42,6 +41,9 @@ static const struct acpi_device_id bt_device_ids[] = { }; MODULE_DEVICE_TABLE(acpi, bt_device_ids); +static int toshiba_bt_resume(struct device *dev); +static SIMPLE_DEV_PM_OPS(toshiba_bt_pm, NULL, toshiba_bt_resume); + static struct acpi_driver toshiba_bt_rfkill_driver = { .name = "Toshiba BT", .class = "Toshiba", @@ -50,9 +52,9 @@ static struct acpi_driver toshiba_bt_rfkill_driver = { .add = toshiba_bt_rfkill_add, .remove = toshiba_bt_rfkill_remove, .notify = toshiba_bt_rfkill_notify, - .resume = toshiba_bt_resume, }, .owner = THIS_MODULE, + .drv.pm = &toshiba_bt_pm, }; @@ -88,9 +90,9 @@ static void toshiba_bt_rfkill_notify(struct acpi_device *device, u32 event) toshiba_bluetooth_enable(device->handle); } -static int toshiba_bt_resume(struct acpi_device *device) +static int toshiba_bt_resume(struct device *dev) { - return toshiba_bluetooth_enable(device->handle); + return toshiba_bluetooth_enable(to_acpi_device(dev)->handle); } static int toshiba_bt_rfkill_add(struct acpi_device *device) diff --git a/drivers/platform/x86/xo15-ebook.c b/drivers/platform/x86/xo15-ebook.c index fad153dc0355..849c07c13bf6 100644 --- a/drivers/platform/x86/xo15-ebook.c +++ b/drivers/platform/x86/xo15-ebook.c @@ -77,11 +77,13 @@ static void ebook_switch_notify(struct acpi_device *device, u32 event) } } -static int ebook_switch_resume(struct acpi_device *device) +static int ebook_switch_resume(struct device *dev) { - return ebook_send_state(device); + return ebook_send_state(to_acpi_device(dev)); } +static SIMPLE_DEV_PM_OPS(ebook_switch_pm, NULL, ebook_switch_resume); + static int ebook_switch_add(struct acpi_device *device) { struct ebook_switch *button; @@ -161,10 +163,10 @@ static struct acpi_driver xo15_ebook_driver = { .ids = ebook_device_ids, .ops = { .add = ebook_switch_add, - .resume = ebook_switch_resume, .remove = ebook_switch_remove, .notify = ebook_switch_notify, }, + .drv.pm = &ebook_switch_pm, }; static int __init xo15_ebook_init(void) diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index c86b8864e411..f34c3be6c9fe 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -20,6 +20,7 @@ menuconfig REGULATOR If unsure, say no. + if REGULATOR config REGULATOR_DEBUG @@ -88,6 +89,13 @@ config REGULATOR_AAT2870 If you have a AnalogicTech AAT2870 say Y to enable the regulator driver. +config REGULATOR_ARIZONA + tristate "Wolfson Arizona class devices" + depends on MFD_ARIZONA + help + Support for the regulators found on Wolfson Arizona class + devices. + config REGULATOR_DA903X tristate "Dialog Semiconductor DA9030/DA9034 regulators" depends on PMIC_DA903X @@ -195,6 +203,14 @@ config REGULATOR_MAX8998 via I2C bus. The provided regulator is suitable for S3C6410 and S5PC1XX chips to control VCC_CORE and VCC_USIM voltages. +config REGULATOR_MAX77686 + tristate "Maxim 77686 regulator" + depends on MFD_MAX77686 + help + This driver controls a Maxim 77686 regulator + via I2C bus. The provided regulator is suitable for + Exynos-4 chips to control VARM and VINT voltages. + config REGULATOR_PCAP tristate "Motorola PCAP2 regulator driver" depends on EZX_PCAP @@ -216,6 +232,19 @@ config REGULATOR_LP3972 Say Y here to support the voltage regulators and convertors on National Semiconductors LP3972 PMIC +config REGULATOR_LP872X + bool "TI/National Semiconductor LP8720/LP8725 voltage regulators" + depends on I2C=y + select REGMAP_I2C + help + This driver supports LP8720/LP8725 PMIC + +config REGULATOR_LP8788 + bool "TI LP8788 Power Regulators" + depends on MFD_LP8788 + help + This driver supports LP8788 voltage regulator chip. + config REGULATOR_PCF50633 tristate "NXP PCF50633 regulator driver" depends on MFD_PCF50633 @@ -233,6 +262,14 @@ config REGULATOR_RC5T583 through regulator interface. The device supports multiple DCDC/LDO outputs which can be controlled by i2c communication. +config REGULATOR_S2MPS11 + tristate "Samsung S2MPS11 voltage regulator" + depends on MFD_SEC_CORE + help + This driver supports a Samsung S2MPS11 voltage output regulator + via I2C bus. S2MPS11 is comprised of high efficient Buck converters + including Dual-Phase Buck converter, Buck-Boost converter, various LDOs. + config REGULATOR_S5M8767 tristate "Samsung S5M8767A voltage regulator" depends on MFD_S5M_CORE diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile index 977fd46909ab..3342615cf25e 100644 --- a/drivers/regulator/Makefile +++ b/drivers/regulator/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_REGULATOR_AB3100) += ab3100.o obj-$(CONFIG_REGULATOR_AB8500) += ab8500.o obj-$(CONFIG_REGULATOR_AD5398) += ad5398.o obj-$(CONFIG_REGULATOR_ANATOP) += anatop-regulator.o +obj-$(CONFIG_REGULATOR_ARIZONA) += arizona-micsupp.o arizona-ldo1.o obj-$(CONFIG_REGULATOR_DA903X) += da903x.o obj-$(CONFIG_REGULATOR_DA9052) += da9052-regulator.o obj-$(CONFIG_REGULATOR_DBX500_PRCMU) += dbx500-prcmu.o @@ -23,6 +24,9 @@ obj-$(CONFIG_REGULATOR_GPIO) += gpio-regulator.o obj-$(CONFIG_REGULATOR_ISL6271A) += isl6271a-regulator.o obj-$(CONFIG_REGULATOR_LP3971) += lp3971.o obj-$(CONFIG_REGULATOR_LP3972) += lp3972.o +obj-$(CONFIG_REGULATOR_LP872X) += lp872x.o +obj-$(CONFIG_REGULATOR_LP8788) += lp8788-buck.o +obj-$(CONFIG_REGULATOR_LP8788) += lp8788-ldo.o obj-$(CONFIG_REGULATOR_MAX1586) += max1586.o obj-$(CONFIG_REGULATOR_MAX8649) += max8649.o obj-$(CONFIG_REGULATOR_MAX8660) += max8660.o @@ -30,6 +34,7 @@ obj-$(CONFIG_REGULATOR_MAX8925) += max8925-regulator.o obj-$(CONFIG_REGULATOR_MAX8952) += max8952.o obj-$(CONFIG_REGULATOR_MAX8997) += max8997.o obj-$(CONFIG_REGULATOR_MAX8998) += max8998.o +obj-$(CONFIG_REGULATOR_MAX77686) += max77686.o obj-$(CONFIG_REGULATOR_MC13783) += mc13783-regulator.o obj-$(CONFIG_REGULATOR_MC13892) += mc13892-regulator.o obj-$(CONFIG_REGULATOR_MC13XXX_CORE) += mc13xxx-regulator-core.o @@ -37,6 +42,7 @@ obj-$(CONFIG_REGULATOR_PALMAS) += palmas-regulator.o obj-$(CONFIG_REGULATOR_PCAP) += pcap-regulator.o obj-$(CONFIG_REGULATOR_PCF50633) += pcf50633-regulator.o obj-$(CONFIG_REGULATOR_RC5T583) += rc5t583-regulator.o +obj-$(CONFIG_REGULATOR_S2MPS11) += s2mps11.o obj-$(CONFIG_REGULATOR_S5M8767) += s5m8767.o obj-$(CONFIG_REGULATOR_TPS6105X) += tps6105x-regulator.o obj-$(CONFIG_REGULATOR_TPS62360) += tps62360-regulator.o diff --git a/drivers/regulator/aat2870-regulator.c b/drivers/regulator/aat2870-regulator.c index 06776ca945f2..6f45bfd22e83 100644 --- a/drivers/regulator/aat2870-regulator.c +++ b/drivers/regulator/aat2870-regulator.c @@ -33,11 +33,6 @@ struct aat2870_regulator { struct aat2870_data *aat2870; struct regulator_desc desc; - const int *voltages; /* uV */ - - int min_uV; - int max_uV; - u8 enable_addr; u8 enable_shift; u8 enable_mask; @@ -47,14 +42,6 @@ struct aat2870_regulator { u8 voltage_mask; }; -static int aat2870_ldo_list_voltage(struct regulator_dev *rdev, - unsigned selector) -{ - struct aat2870_regulator *ri = rdev_get_drvdata(rdev); - - return ri->voltages[selector]; -} - static int aat2870_ldo_set_voltage_sel(struct regulator_dev *rdev, unsigned selector) { @@ -111,7 +98,7 @@ static int aat2870_ldo_is_enabled(struct regulator_dev *rdev) } static struct regulator_ops aat2870_ldo_ops = { - .list_voltage = aat2870_ldo_list_voltage, + .list_voltage = regulator_list_voltage_table, .set_voltage_sel = aat2870_ldo_set_voltage_sel, .get_voltage_sel = aat2870_ldo_get_voltage_sel, .enable = aat2870_ldo_enable, @@ -119,7 +106,7 @@ static struct regulator_ops aat2870_ldo_ops = { .is_enabled = aat2870_ldo_is_enabled, }; -static const int aat2870_ldo_voltages[] = { +static const unsigned int aat2870_ldo_voltages[] = { 1200000, 1300000, 1500000, 1600000, 1800000, 2000000, 2200000, 2500000, 2600000, 2700000, 2800000, 2900000, @@ -132,13 +119,11 @@ static const int aat2870_ldo_voltages[] = { .name = #ids, \ .id = AAT2870_ID_##ids, \ .n_voltages = ARRAY_SIZE(aat2870_ldo_voltages), \ + .volt_table = aat2870_ldo_voltages, \ .ops = &aat2870_ldo_ops, \ .type = REGULATOR_VOLTAGE, \ .owner = THIS_MODULE, \ }, \ - .voltages = aat2870_ldo_voltages, \ - .min_uV = 1200000, \ - .max_uV = 3300000, \ } static struct aat2870_regulator aat2870_regulators[] = { diff --git a/drivers/regulator/ab3100.c b/drivers/regulator/ab3100.c index 03f4d9c604ec..182b553059c9 100644 --- a/drivers/regulator/ab3100.c +++ b/drivers/regulator/ab3100.c @@ -43,20 +43,12 @@ * @dev: handle to the device * @plfdata: AB3100 platform data passed in at probe time * @regreg: regulator register number in the AB3100 - * @fixed_voltage: a fixed voltage for this regulator, if this - * 0 the voltages array is used instead. - * @typ_voltages: an array of available typical voltages for - * this regulator - * @voltages_len: length of the array of available voltages */ struct ab3100_regulator { struct regulator_dev *rdev; struct device *dev; struct ab3100_platform_data *plfdata; u8 regreg; - int fixed_voltage; - int const *typ_voltages; - u8 voltages_len; }; /* The order in which registers are initialized */ @@ -80,7 +72,7 @@ static const u8 ab3100_reg_init_order[AB3100_NUM_REGULATORS+2] = { #define LDO_C_VOLTAGE 2650000 #define LDO_D_VOLTAGE 2650000 -static const int ldo_e_buck_typ_voltages[] = { +static const unsigned int ldo_e_buck_typ_voltages[] = { 1800000, 1400000, 1300000, @@ -90,7 +82,7 @@ static const int ldo_e_buck_typ_voltages[] = { 900000, }; -static const int ldo_f_typ_voltages[] = { +static const unsigned int ldo_f_typ_voltages[] = { 1800000, 1400000, 1300000, @@ -101,21 +93,21 @@ static const int ldo_f_typ_voltages[] = { 2650000, }; -static const int ldo_g_typ_voltages[] = { +static const unsigned int ldo_g_typ_voltages[] = { 2850000, 2750000, 1800000, 1500000, }; -static const int ldo_h_typ_voltages[] = { +static const unsigned int ldo_h_typ_voltages[] = { 2750000, 1800000, 1500000, 1200000, }; -static const int ldo_k_typ_voltages[] = { +static const unsigned int ldo_k_typ_voltages[] = { 2750000, 1800000, }; @@ -126,40 +118,27 @@ static struct ab3100_regulator ab3100_regulators[AB3100_NUM_REGULATORS] = { { .regreg = AB3100_LDO_A, - .fixed_voltage = LDO_A_VOLTAGE, }, { .regreg = AB3100_LDO_C, - .fixed_voltage = LDO_C_VOLTAGE, }, { .regreg = AB3100_LDO_D, - .fixed_voltage = LDO_D_VOLTAGE, }, { .regreg = AB3100_LDO_E, - .typ_voltages = ldo_e_buck_typ_voltages, - .voltages_len = ARRAY_SIZE(ldo_e_buck_typ_voltages), }, { .regreg = AB3100_LDO_F, - .typ_voltages = ldo_f_typ_voltages, - .voltages_len = ARRAY_SIZE(ldo_f_typ_voltages), }, { .regreg = AB3100_LDO_G, - .typ_voltages = ldo_g_typ_voltages, - .voltages_len = ARRAY_SIZE(ldo_g_typ_voltages), }, { .regreg = AB3100_LDO_H, - .typ_voltages = ldo_h_typ_voltages, - .voltages_len = ARRAY_SIZE(ldo_h_typ_voltages), }, { .regreg = AB3100_LDO_K, - .typ_voltages = ldo_k_typ_voltages, - .voltages_len = ARRAY_SIZE(ldo_k_typ_voltages), }, { .regreg = AB3100_LDO_EXT, @@ -167,8 +146,6 @@ ab3100_regulators[AB3100_NUM_REGULATORS] = { }, { .regreg = AB3100_BUCK, - .typ_voltages = ldo_e_buck_typ_voltages, - .voltages_len = ARRAY_SIZE(ldo_e_buck_typ_voltages), }, }; @@ -178,7 +155,7 @@ ab3100_regulators[AB3100_NUM_REGULATORS] = { */ static int ab3100_enable_regulator(struct regulator_dev *reg) { - struct ab3100_regulator *abreg = reg->reg_data; + struct ab3100_regulator *abreg = rdev_get_drvdata(reg); int err; u8 regval; @@ -209,7 +186,7 @@ static int ab3100_enable_regulator(struct regulator_dev *reg) static int ab3100_disable_regulator(struct regulator_dev *reg) { - struct ab3100_regulator *abreg = reg->reg_data; + struct ab3100_regulator *abreg = rdev_get_drvdata(reg); int err; u8 regval; @@ -242,7 +219,7 @@ static int ab3100_disable_regulator(struct regulator_dev *reg) static int ab3100_is_enabled_regulator(struct regulator_dev *reg) { - struct ab3100_regulator *abreg = reg->reg_data; + struct ab3100_regulator *abreg = rdev_get_drvdata(reg); u8 regval; int err; @@ -257,26 +234,12 @@ static int ab3100_is_enabled_regulator(struct regulator_dev *reg) return regval & AB3100_REG_ON_MASK; } -static int ab3100_list_voltage_regulator(struct regulator_dev *reg, - unsigned selector) -{ - struct ab3100_regulator *abreg = reg->reg_data; - - if (selector >= abreg->voltages_len) - return -EINVAL; - return abreg->typ_voltages[selector]; -} - static int ab3100_get_voltage_regulator(struct regulator_dev *reg) { - struct ab3100_regulator *abreg = reg->reg_data; + struct ab3100_regulator *abreg = rdev_get_drvdata(reg); u8 regval; int err; - /* Return the voltage for fixed regulators immediately */ - if (abreg->fixed_voltage) - return abreg->fixed_voltage; - /* * For variable types, read out setting and index into * supplied voltage list. @@ -294,20 +257,20 @@ static int ab3100_get_voltage_regulator(struct regulator_dev *reg) regval &= 0xE0; regval >>= 5; - if (regval >= abreg->voltages_len) { + if (regval >= reg->desc->n_voltages) { dev_err(®->dev, "regulator register %02x contains an illegal voltage setting\n", abreg->regreg); return -EINVAL; } - return abreg->typ_voltages[regval]; + return reg->desc->volt_table[regval]; } static int ab3100_set_voltage_regulator_sel(struct regulator_dev *reg, unsigned selector) { - struct ab3100_regulator *abreg = reg->reg_data; + struct ab3100_regulator *abreg = rdev_get_drvdata(reg); u8 regval; int err; @@ -336,7 +299,7 @@ static int ab3100_set_voltage_regulator_sel(struct regulator_dev *reg, static int ab3100_set_suspend_voltage_regulator(struct regulator_dev *reg, int uV) { - struct ab3100_regulator *abreg = reg->reg_data; + struct ab3100_regulator *abreg = rdev_get_drvdata(reg); u8 regval; int err; int bestindex; @@ -379,42 +342,22 @@ static int ab3100_set_suspend_voltage_regulator(struct regulator_dev *reg, */ static int ab3100_get_voltage_regulator_external(struct regulator_dev *reg) { - struct ab3100_regulator *abreg = reg->reg_data; + struct ab3100_regulator *abreg = rdev_get_drvdata(reg); return abreg->plfdata->external_voltage; } -static int ab3100_enable_time_regulator(struct regulator_dev *reg) +static int ab3100_get_fixed_voltage_regulator(struct regulator_dev *reg) { - struct ab3100_regulator *abreg = reg->reg_data; - - /* Per-regulator power on delay from spec */ - switch (abreg->regreg) { - case AB3100_LDO_A: /* Fallthrough */ - case AB3100_LDO_C: /* Fallthrough */ - case AB3100_LDO_D: /* Fallthrough */ - case AB3100_LDO_E: /* Fallthrough */ - case AB3100_LDO_H: /* Fallthrough */ - case AB3100_LDO_K: - return 200; - case AB3100_LDO_F: - return 600; - case AB3100_LDO_G: - return 400; - case AB3100_BUCK: - return 1000; - default: - break; - } - return 0; + return reg->desc->min_uV; } static struct regulator_ops regulator_ops_fixed = { + .list_voltage = regulator_list_voltage_linear, .enable = ab3100_enable_regulator, .disable = ab3100_disable_regulator, .is_enabled = ab3100_is_enabled_regulator, - .get_voltage = ab3100_get_voltage_regulator, - .enable_time = ab3100_enable_time_regulator, + .get_voltage = ab3100_get_fixed_voltage_regulator, }; static struct regulator_ops regulator_ops_variable = { @@ -423,8 +366,7 @@ static struct regulator_ops regulator_ops_variable = { .is_enabled = ab3100_is_enabled_regulator, .get_voltage = ab3100_get_voltage_regulator, .set_voltage_sel = ab3100_set_voltage_regulator_sel, - .list_voltage = ab3100_list_voltage_regulator, - .enable_time = ab3100_enable_time_regulator, + .list_voltage = regulator_list_voltage_table, }; static struct regulator_ops regulator_ops_variable_sleepable = { @@ -434,8 +376,7 @@ static struct regulator_ops regulator_ops_variable_sleepable = { .get_voltage = ab3100_get_voltage_regulator, .set_voltage_sel = ab3100_set_voltage_regulator_sel, .set_suspend_voltage = ab3100_set_suspend_voltage_regulator, - .list_voltage = ab3100_list_voltage_regulator, - .enable_time = ab3100_enable_time_regulator, + .list_voltage = regulator_list_voltage_table, }; /* @@ -457,62 +398,81 @@ ab3100_regulator_desc[AB3100_NUM_REGULATORS] = { .name = "LDO_A", .id = AB3100_LDO_A, .ops = ®ulator_ops_fixed, + .n_voltages = 1, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, + .min_uV = LDO_A_VOLTAGE, + .enable_time = 200, }, { .name = "LDO_C", .id = AB3100_LDO_C, .ops = ®ulator_ops_fixed, + .n_voltages = 1, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, + .min_uV = LDO_C_VOLTAGE, + .enable_time = 200, }, { .name = "LDO_D", .id = AB3100_LDO_D, .ops = ®ulator_ops_fixed, + .n_voltages = 1, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, + .min_uV = LDO_D_VOLTAGE, + .enable_time = 200, }, { .name = "LDO_E", .id = AB3100_LDO_E, .ops = ®ulator_ops_variable_sleepable, .n_voltages = ARRAY_SIZE(ldo_e_buck_typ_voltages), + .volt_table = ldo_e_buck_typ_voltages, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, + .enable_time = 200, }, { .name = "LDO_F", .id = AB3100_LDO_F, .ops = ®ulator_ops_variable, .n_voltages = ARRAY_SIZE(ldo_f_typ_voltages), + .volt_table = ldo_f_typ_voltages, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, + .enable_time = 600, }, { .name = "LDO_G", .id = AB3100_LDO_G, .ops = ®ulator_ops_variable, .n_voltages = ARRAY_SIZE(ldo_g_typ_voltages), + .volt_table = ldo_g_typ_voltages, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, + .enable_time = 400, }, { .name = "LDO_H", .id = AB3100_LDO_H, .ops = ®ulator_ops_variable, .n_voltages = ARRAY_SIZE(ldo_h_typ_voltages), + .volt_table = ldo_h_typ_voltages, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, + .enable_time = 200, }, { .name = "LDO_K", .id = AB3100_LDO_K, .ops = ®ulator_ops_variable, .n_voltages = ARRAY_SIZE(ldo_k_typ_voltages), + .volt_table = ldo_k_typ_voltages, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, + .enable_time = 200, }, { .name = "LDO_EXT", @@ -528,6 +488,7 @@ ab3100_regulator_desc[AB3100_NUM_REGULATORS] = { .n_voltages = ARRAY_SIZE(ldo_e_buck_typ_voltages), .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, + .enable_time = 1000, }, }; diff --git a/drivers/regulator/ab8500.c b/drivers/regulator/ab8500.c index a739f5ca936a..13d424fc1c14 100644 --- a/drivers/regulator/ab8500.c +++ b/drivers/regulator/ab8500.c @@ -30,9 +30,6 @@ * @dev: device pointer * @desc: regulator description * @regulator_dev: regulator device - * @max_uV: maximum voltage (for variable voltage supplies) - * @min_uV: minimum voltage (for variable voltage supplies) - * @fixed_uV: typical voltage (for fixed voltage supplies) * @update_bank: bank to control on/off * @update_reg: register to control on/off * @update_mask: mask to enable/disable regulator @@ -40,17 +37,12 @@ * @voltage_bank: bank to control regulator voltage * @voltage_reg: register to control regulator voltage * @voltage_mask: mask to control regulator voltage - * @voltages: supported voltage table - * @voltages_len: number of supported voltages for the regulator * @delay: startup/set voltage delay in us */ struct ab8500_regulator_info { struct device *dev; struct regulator_desc desc; struct regulator_dev *regulator; - int max_uV; - int min_uV; - int fixed_uV; u8 update_bank; u8 update_reg; u8 update_mask; @@ -58,13 +50,11 @@ struct ab8500_regulator_info { u8 voltage_bank; u8 voltage_reg; u8 voltage_mask; - int const *voltages; - int voltages_len; unsigned int delay; }; /* voltage tables for the vauxn/vintcore supplies */ -static const int ldo_vauxn_voltages[] = { +static const unsigned int ldo_vauxn_voltages[] = { 1100000, 1200000, 1300000, @@ -83,7 +73,7 @@ static const int ldo_vauxn_voltages[] = { 3300000, }; -static const int ldo_vaux3_voltages[] = { +static const unsigned int ldo_vaux3_voltages[] = { 1200000, 1500000, 1800000, @@ -94,7 +84,7 @@ static const int ldo_vaux3_voltages[] = { 2910000, }; -static const int ldo_vintcore_voltages[] = { +static const unsigned int ldo_vintcore_voltages[] = { 1200000, 1225000, 1250000, @@ -185,25 +175,6 @@ static int ab8500_regulator_is_enabled(struct regulator_dev *rdev) return false; } -static int ab8500_list_voltage(struct regulator_dev *rdev, unsigned selector) -{ - struct ab8500_regulator_info *info = rdev_get_drvdata(rdev); - - if (info == NULL) { - dev_err(rdev_get_dev(rdev), "regulator info null pointer\n"); - return -EINVAL; - } - - /* return the uV for the fixed regulators */ - if (info->fixed_uV) - return info->fixed_uV; - - if (selector >= info->voltages_len) - return -EINVAL; - - return info->voltages[selector]; -} - static int ab8500_regulator_get_voltage_sel(struct regulator_dev *rdev) { int ret, val; @@ -279,14 +250,7 @@ static int ab8500_regulator_set_voltage_time_sel(struct regulator_dev *rdev, unsigned int new_sel) { struct ab8500_regulator_info *info = rdev_get_drvdata(rdev); - int ret; - /* If the regulator isn't on, it won't take time here */ - ret = ab8500_regulator_is_enabled(rdev); - if (ret < 0) - return ret; - if (!ret) - return 0; return info->delay; } @@ -296,21 +260,14 @@ static struct regulator_ops ab8500_regulator_ops = { .is_enabled = ab8500_regulator_is_enabled, .get_voltage_sel = ab8500_regulator_get_voltage_sel, .set_voltage_sel = ab8500_regulator_set_voltage_sel, - .list_voltage = ab8500_list_voltage, + .list_voltage = regulator_list_voltage_table, .enable_time = ab8500_regulator_enable_time, .set_voltage_time_sel = ab8500_regulator_set_voltage_time_sel, }; static int ab8500_fixed_get_voltage(struct regulator_dev *rdev) { - struct ab8500_regulator_info *info = rdev_get_drvdata(rdev); - - if (info == NULL) { - dev_err(rdev_get_dev(rdev), "regulator info null pointer\n"); - return -EINVAL; - } - - return info->fixed_uV; + return rdev->desc->min_uV; } static struct regulator_ops ab8500_regulator_fixed_ops = { @@ -318,9 +275,8 @@ static struct regulator_ops ab8500_regulator_fixed_ops = { .disable = ab8500_regulator_disable, .is_enabled = ab8500_regulator_is_enabled, .get_voltage = ab8500_fixed_get_voltage, - .list_voltage = ab8500_list_voltage, + .list_voltage = regulator_list_voltage_linear, .enable_time = ab8500_regulator_enable_time, - .set_voltage_time_sel = ab8500_regulator_set_voltage_time_sel, }; static struct ab8500_regulator_info @@ -329,7 +285,7 @@ static struct ab8500_regulator_info * Variable Voltage Regulators * name, min mV, max mV, * update bank, reg, mask, enable val - * volt bank, reg, mask, table, table length + * volt bank, reg, mask */ [AB8500_LDO_AUX1] = { .desc = { @@ -339,9 +295,8 @@ static struct ab8500_regulator_info .id = AB8500_LDO_AUX1, .owner = THIS_MODULE, .n_voltages = ARRAY_SIZE(ldo_vauxn_voltages), + .volt_table = ldo_vauxn_voltages, }, - .min_uV = 1100000, - .max_uV = 3300000, .update_bank = 0x04, .update_reg = 0x09, .update_mask = 0x03, @@ -349,8 +304,6 @@ static struct ab8500_regulator_info .voltage_bank = 0x04, .voltage_reg = 0x1f, .voltage_mask = 0x0f, - .voltages = ldo_vauxn_voltages, - .voltages_len = ARRAY_SIZE(ldo_vauxn_voltages), }, [AB8500_LDO_AUX2] = { .desc = { @@ -360,9 +313,8 @@ static struct ab8500_regulator_info .id = AB8500_LDO_AUX2, .owner = THIS_MODULE, .n_voltages = ARRAY_SIZE(ldo_vauxn_voltages), + .volt_table = ldo_vauxn_voltages, }, - .min_uV = 1100000, - .max_uV = 3300000, .update_bank = 0x04, .update_reg = 0x09, .update_mask = 0x0c, @@ -370,8 +322,6 @@ static struct ab8500_regulator_info .voltage_bank = 0x04, .voltage_reg = 0x20, .voltage_mask = 0x0f, - .voltages = ldo_vauxn_voltages, - .voltages_len = ARRAY_SIZE(ldo_vauxn_voltages), }, [AB8500_LDO_AUX3] = { .desc = { @@ -381,9 +331,8 @@ static struct ab8500_regulator_info .id = AB8500_LDO_AUX3, .owner = THIS_MODULE, .n_voltages = ARRAY_SIZE(ldo_vaux3_voltages), + .volt_table = ldo_vaux3_voltages, }, - .min_uV = 1100000, - .max_uV = 3300000, .update_bank = 0x04, .update_reg = 0x0a, .update_mask = 0x03, @@ -391,8 +340,6 @@ static struct ab8500_regulator_info .voltage_bank = 0x04, .voltage_reg = 0x21, .voltage_mask = 0x07, - .voltages = ldo_vaux3_voltages, - .voltages_len = ARRAY_SIZE(ldo_vaux3_voltages), }, [AB8500_LDO_INTCORE] = { .desc = { @@ -402,9 +349,8 @@ static struct ab8500_regulator_info .id = AB8500_LDO_INTCORE, .owner = THIS_MODULE, .n_voltages = ARRAY_SIZE(ldo_vintcore_voltages), + .volt_table = ldo_vintcore_voltages, }, - .min_uV = 1100000, - .max_uV = 3300000, .update_bank = 0x03, .update_reg = 0x80, .update_mask = 0x44, @@ -412,8 +358,6 @@ static struct ab8500_regulator_info .voltage_bank = 0x03, .voltage_reg = 0x80, .voltage_mask = 0x38, - .voltages = ldo_vintcore_voltages, - .voltages_len = ARRAY_SIZE(ldo_vintcore_voltages), }, /* @@ -429,9 +373,9 @@ static struct ab8500_regulator_info .id = AB8500_LDO_TVOUT, .owner = THIS_MODULE, .n_voltages = 1, + .min_uV = 2000000, }, .delay = 10000, - .fixed_uV = 2000000, .update_bank = 0x03, .update_reg = 0x80, .update_mask = 0x82, @@ -445,8 +389,8 @@ static struct ab8500_regulator_info .id = AB8500_LDO_USB, .owner = THIS_MODULE, .n_voltages = 1, + .min_uV = 3300000, }, - .fixed_uV = 3300000, .update_bank = 0x03, .update_reg = 0x82, .update_mask = 0x03, @@ -460,8 +404,8 @@ static struct ab8500_regulator_info .id = AB8500_LDO_AUDIO, .owner = THIS_MODULE, .n_voltages = 1, + .min_uV = 2000000, }, - .fixed_uV = 2000000, .update_bank = 0x03, .update_reg = 0x83, .update_mask = 0x02, @@ -475,8 +419,8 @@ static struct ab8500_regulator_info .id = AB8500_LDO_ANAMIC1, .owner = THIS_MODULE, .n_voltages = 1, + .min_uV = 2050000, }, - .fixed_uV = 2050000, .update_bank = 0x03, .update_reg = 0x83, .update_mask = 0x08, @@ -490,8 +434,8 @@ static struct ab8500_regulator_info .id = AB8500_LDO_ANAMIC2, .owner = THIS_MODULE, .n_voltages = 1, + .min_uV = 2050000, }, - .fixed_uV = 2050000, .update_bank = 0x03, .update_reg = 0x83, .update_mask = 0x10, @@ -505,8 +449,8 @@ static struct ab8500_regulator_info .id = AB8500_LDO_DMIC, .owner = THIS_MODULE, .n_voltages = 1, + .min_uV = 1800000, }, - .fixed_uV = 1800000, .update_bank = 0x03, .update_reg = 0x83, .update_mask = 0x04, @@ -520,8 +464,8 @@ static struct ab8500_regulator_info .id = AB8500_LDO_ANA, .owner = THIS_MODULE, .n_voltages = 1, + .min_uV = 1200000, }, - .fixed_uV = 1200000, .update_bank = 0x04, .update_reg = 0x06, .update_mask = 0x0c, @@ -769,9 +713,7 @@ static __devinit int ab8500_regulator_register(struct platform_device *pdev, if (info->desc.id == AB8500_LDO_AUX3) { info->desc.n_voltages = ARRAY_SIZE(ldo_vauxn_voltages); - info->voltages = ldo_vauxn_voltages; - info->voltages_len = - ARRAY_SIZE(ldo_vauxn_voltages); + info->desc.volt_table = ldo_vauxn_voltages; info->voltage_mask = 0xf; } } diff --git a/drivers/regulator/ad5398.c b/drivers/regulator/ad5398.c index 46d05f38baf8..f123f7e3b752 100644 --- a/drivers/regulator/ad5398.c +++ b/drivers/regulator/ad5398.c @@ -89,9 +89,12 @@ static int ad5398_set_current_limit(struct regulator_dev *rdev, int min_uA, int unsigned short data; int ret; - if (min_uA > chip->max_uA || min_uA < chip->min_uA) - return -EINVAL; - if (max_uA > chip->max_uA || max_uA < chip->min_uA) + if (min_uA < chip->min_uA) + min_uA = chip->min_uA; + if (max_uA > chip->max_uA) + max_uA = chip->max_uA; + + if (min_uA > chip->max_uA || max_uA < chip->min_uA) return -EINVAL; selector = DIV_ROUND_UP((min_uA - chip->min_uA) * chip->current_level, diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c index e82e7eaac0f1..e9c2085f9dfb 100644 --- a/drivers/regulator/anatop-regulator.c +++ b/drivers/regulator/anatop-regulator.c @@ -43,33 +43,15 @@ struct anatop_regulator { struct regulator_init_data *initdata; }; -static int anatop_set_voltage(struct regulator_dev *reg, int min_uV, - int max_uV, unsigned *selector) +static int anatop_set_voltage_sel(struct regulator_dev *reg, unsigned selector) { struct anatop_regulator *anatop_reg = rdev_get_drvdata(reg); - u32 val, sel, mask; - int uv; - - uv = min_uV; - dev_dbg(®->dev, "%s: uv %d, min %d, max %d\n", __func__, - uv, anatop_reg->min_voltage, - anatop_reg->max_voltage); - - if (uv < anatop_reg->min_voltage) { - if (max_uV > anatop_reg->min_voltage) - uv = anatop_reg->min_voltage; - else - return -EINVAL; - } + u32 val, mask; if (!anatop_reg->control_reg) return -ENOTSUPP; - sel = DIV_ROUND_UP(uv - anatop_reg->min_voltage, 25000); - if (sel * 25000 + anatop_reg->min_voltage > anatop_reg->max_voltage) - return -EINVAL; - val = anatop_reg->min_bit_val + sel; - *selector = sel; + val = anatop_reg->min_bit_val + selector; dev_dbg(®->dev, "%s: calculated val %d\n", __func__, val); mask = ((1 << anatop_reg->vol_bit_width) - 1) << anatop_reg->vol_bit_shift; @@ -94,21 +76,11 @@ static int anatop_get_voltage_sel(struct regulator_dev *reg) return val - anatop_reg->min_bit_val; } -static int anatop_list_voltage(struct regulator_dev *reg, unsigned selector) -{ - struct anatop_regulator *anatop_reg = rdev_get_drvdata(reg); - int uv; - - uv = anatop_reg->min_voltage + selector * 25000; - dev_dbg(®->dev, "vddio = %d, selector = %u\n", uv, selector); - - return uv; -} - static struct regulator_ops anatop_rops = { - .set_voltage = anatop_set_voltage, + .set_voltage_sel = anatop_set_voltage_sel, .get_voltage_sel = anatop_get_voltage_sel, - .list_voltage = anatop_list_voltage, + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, }; static int __devinit anatop_regulator_probe(struct platform_device *pdev) @@ -176,6 +148,8 @@ static int __devinit anatop_regulator_probe(struct platform_device *pdev) rdesc->n_voltages = (sreg->max_voltage - sreg->min_voltage) / 25000 + 1; + rdesc->min_uV = sreg->min_voltage; + rdesc->uV_step = 25000; config.dev = &pdev->dev; config.init_data = initdata; diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c new file mode 100644 index 000000000000..c8f95c07adb6 --- /dev/null +++ b/drivers/regulator/arizona-ldo1.c @@ -0,0 +1,138 @@ +/* + * arizona-ldo1.c -- LDO1 supply for Arizona devices + * + * Copyright 2012 Wolfson Microelectronics PLC. + * + * Author: Mark Brown <broonie@opensource.wolfsonmicro.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/init.h> +#include <linux/bitops.h> +#include <linux/err.h> +#include <linux/platform_device.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/machine.h> +#include <linux/gpio.h> +#include <linux/slab.h> + +#include <linux/mfd/arizona/core.h> +#include <linux/mfd/arizona/pdata.h> +#include <linux/mfd/arizona/registers.h> + +struct arizona_ldo1 { + struct regulator_dev *regulator; + struct arizona *arizona; + + struct regulator_consumer_supply supply; + struct regulator_init_data init_data; +}; + +static struct regulator_ops arizona_ldo1_ops = { + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, +}; + +static const struct regulator_desc arizona_ldo1 = { + .name = "LDO1", + .supply_name = "LDOVDD", + .type = REGULATOR_VOLTAGE, + .ops = &arizona_ldo1_ops, + + .vsel_reg = ARIZONA_LDO1_CONTROL_1, + .vsel_mask = ARIZONA_LDO1_VSEL_MASK, + .min_uV = 900000, + .uV_step = 50000, + .n_voltages = 7, + + .owner = THIS_MODULE, +}; + +static const struct regulator_init_data arizona_ldo1_default = { + .constraints = { + .valid_ops_mask = REGULATOR_CHANGE_STATUS, + }, + .num_consumer_supplies = 1, +}; + +static __devinit int arizona_ldo1_probe(struct platform_device *pdev) +{ + struct arizona *arizona = dev_get_drvdata(pdev->dev.parent); + struct regulator_config config = { }; + struct arizona_ldo1 *ldo1; + int ret; + + ldo1 = devm_kzalloc(&pdev->dev, sizeof(*ldo1), GFP_KERNEL); + if (ldo1 == NULL) { + dev_err(&pdev->dev, "Unable to allocate private data\n"); + return -ENOMEM; + } + + ldo1->arizona = arizona; + + /* + * Since the chip usually supplies itself we provide some + * default init_data for it. This will be overridden with + * platform data if provided. + */ + ldo1->init_data = arizona_ldo1_default; + ldo1->init_data.consumer_supplies = &ldo1->supply; + ldo1->supply.supply = "DCVDD"; + ldo1->supply.dev_name = dev_name(arizona->dev); + + config.dev = arizona->dev; + config.driver_data = ldo1; + config.regmap = arizona->regmap; + config.ena_gpio = arizona->pdata.ldoena; + + if (arizona->pdata.ldo1) + config.init_data = arizona->pdata.ldo1; + else + config.init_data = &ldo1->init_data; + + ldo1->regulator = regulator_register(&arizona_ldo1, &config); + if (IS_ERR(ldo1->regulator)) { + ret = PTR_ERR(ldo1->regulator); + dev_err(arizona->dev, "Failed to register LDO1 supply: %d\n", + ret); + return ret; + } + + platform_set_drvdata(pdev, ldo1); + + return 0; +} + +static __devexit int arizona_ldo1_remove(struct platform_device *pdev) +{ + struct arizona_ldo1 *ldo1 = platform_get_drvdata(pdev); + + regulator_unregister(ldo1->regulator); + + return 0; +} + +static struct platform_driver arizona_ldo1_driver = { + .probe = arizona_ldo1_probe, + .remove = __devexit_p(arizona_ldo1_remove), + .driver = { + .name = "arizona-ldo1", + .owner = THIS_MODULE, + }, +}; + +module_platform_driver(arizona_ldo1_driver); + +/* Module information */ +MODULE_AUTHOR("Mark Brown <broonie@opensource.wolfsonmicro.com>"); +MODULE_DESCRIPTION("Arizona LDO1 driver"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:arizona-ldo1"); diff --git a/drivers/regulator/arizona-micsupp.c b/drivers/regulator/arizona-micsupp.c new file mode 100644 index 000000000000..450a069aa9b6 --- /dev/null +++ b/drivers/regulator/arizona-micsupp.c @@ -0,0 +1,188 @@ +/* + * arizona-micsupp.c -- Microphone supply for Arizona devices + * + * Copyright 2012 Wolfson Microelectronics PLC. + * + * Author: Mark Brown <broonie@opensource.wolfsonmicro.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/init.h> +#include <linux/bitops.h> +#include <linux/err.h> +#include <linux/platform_device.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/machine.h> +#include <linux/gpio.h> +#include <linux/slab.h> + +#include <linux/mfd/arizona/core.h> +#include <linux/mfd/arizona/pdata.h> +#include <linux/mfd/arizona/registers.h> + +#define ARIZONA_MICSUPP_MAX_SELECTOR 0x1f + +struct arizona_micsupp { + struct regulator_dev *regulator; + struct arizona *arizona; + + struct regulator_consumer_supply supply; + struct regulator_init_data init_data; +}; + +static int arizona_micsupp_list_voltage(struct regulator_dev *rdev, + unsigned int selector) +{ + if (selector > ARIZONA_MICSUPP_MAX_SELECTOR) + return -EINVAL; + + if (selector == ARIZONA_MICSUPP_MAX_SELECTOR) + return 3300000; + else + return (selector * 50000) + 1700000; +} + +static int arizona_micsupp_map_voltage(struct regulator_dev *rdev, + int min_uV, int max_uV) +{ + unsigned int voltage; + int selector; + + if (min_uV < 1700000) + min_uV = 1700000; + + if (min_uV > 3200000) + selector = ARIZONA_MICSUPP_MAX_SELECTOR; + else + selector = DIV_ROUND_UP(min_uV - 1700000, 50000); + + if (selector < 0) + return -EINVAL; + + voltage = arizona_micsupp_list_voltage(rdev, selector); + if (voltage < min_uV || voltage > max_uV) + return -EINVAL; + + return selector; +} + +static struct regulator_ops arizona_micsupp_ops = { + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + + .list_voltage = arizona_micsupp_list_voltage, + .map_voltage = arizona_micsupp_map_voltage, + + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, +}; + +static const struct regulator_desc arizona_micsupp = { + .name = "MICVDD", + .supply_name = "CPVDD", + .type = REGULATOR_VOLTAGE, + .n_voltages = ARIZONA_MICSUPP_MAX_SELECTOR + 1, + .ops = &arizona_micsupp_ops, + + .vsel_reg = ARIZONA_LDO2_CONTROL_1, + .vsel_mask = ARIZONA_LDO2_VSEL_MASK, + .enable_reg = ARIZONA_MIC_CHARGE_PUMP_1, + .enable_mask = ARIZONA_CPMIC_ENA, + + .owner = THIS_MODULE, +}; + +static const struct regulator_init_data arizona_micsupp_default = { + .constraints = { + .valid_ops_mask = REGULATOR_CHANGE_STATUS | + REGULATOR_CHANGE_VOLTAGE, + .min_uV = 1700000, + .max_uV = 3300000, + }, + + .num_consumer_supplies = 1, +}; + +static __devinit int arizona_micsupp_probe(struct platform_device *pdev) +{ + struct arizona *arizona = dev_get_drvdata(pdev->dev.parent); + struct regulator_config config = { }; + struct arizona_micsupp *micsupp; + int ret; + + micsupp = devm_kzalloc(&pdev->dev, sizeof(*micsupp), GFP_KERNEL); + if (micsupp == NULL) { + dev_err(&pdev->dev, "Unable to allocate private data\n"); + return -ENOMEM; + } + + micsupp->arizona = arizona; + + /* + * Since the chip usually supplies itself we provide some + * default init_data for it. This will be overridden with + * platform data if provided. + */ + micsupp->init_data = arizona_micsupp_default; + micsupp->init_data.consumer_supplies = &micsupp->supply; + micsupp->supply.supply = "MICVDD"; + micsupp->supply.dev_name = dev_name(arizona->dev); + + config.dev = arizona->dev; + config.driver_data = micsupp; + config.regmap = arizona->regmap; + + if (arizona->pdata.micvdd) + config.init_data = arizona->pdata.micvdd; + else + config.init_data = &micsupp->init_data; + + /* Default to regulated mode until the API supports bypass */ + regmap_update_bits(arizona->regmap, ARIZONA_MIC_CHARGE_PUMP_1, + ARIZONA_CPMIC_BYPASS, 0); + + micsupp->regulator = regulator_register(&arizona_micsupp, &config); + if (IS_ERR(micsupp->regulator)) { + ret = PTR_ERR(micsupp->regulator); + dev_err(arizona->dev, "Failed to register mic supply: %d\n", + ret); + return ret; + } + + platform_set_drvdata(pdev, micsupp); + + return 0; +} + +static __devexit int arizona_micsupp_remove(struct platform_device *pdev) +{ + struct arizona_micsupp *micsupp = platform_get_drvdata(pdev); + + regulator_unregister(micsupp->regulator); + + return 0; +} + +static struct platform_driver arizona_micsupp_driver = { + .probe = arizona_micsupp_probe, + .remove = __devexit_p(arizona_micsupp_remove), + .driver = { + .name = "arizona-micsupp", + .owner = THIS_MODULE, + }, +}; + +module_platform_driver(arizona_micsupp_driver); + +/* Module information */ +MODULE_AUTHOR("Mark Brown <broonie@opensource.wolfsonmicro.com>"); +MODULE_DESCRIPTION("Arizona microphone supply driver"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:arizona-micsupp"); diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 09a737c868b5..2e31dffbefe7 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -23,6 +23,7 @@ #include <linux/mutex.h> #include <linux/suspend.h> #include <linux/delay.h> +#include <linux/gpio.h> #include <linux/of.h> #include <linux/regmap.h> #include <linux/regulator/of_regulator.h> @@ -108,28 +109,6 @@ static const char *rdev_get_name(struct regulator_dev *rdev) return ""; } -/* gets the regulator for a given consumer device */ -static struct regulator *get_device_regulator(struct device *dev) -{ - struct regulator *regulator = NULL; - struct regulator_dev *rdev; - - mutex_lock(®ulator_list_mutex); - list_for_each_entry(rdev, ®ulator_list, list) { - mutex_lock(&rdev->mutex); - list_for_each_entry(regulator, &rdev->consumer_list, list) { - if (regulator->dev == dev) { - mutex_unlock(&rdev->mutex); - mutex_unlock(®ulator_list_mutex); - return regulator; - } - } - mutex_unlock(&rdev->mutex); - } - mutex_unlock(®ulator_list_mutex); - return NULL; -} - /** * of_get_regulator - get a regulator device node based on supply name * @dev: Device pointer for the consumer (of regulator) device @@ -303,18 +282,6 @@ static int regulator_check_drms(struct regulator_dev *rdev) return 0; } -static ssize_t device_requested_uA_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct regulator *regulator; - - regulator = get_device_regulator(dev); - if (regulator == NULL) - return 0; - - return sprintf(buf, "%d\n", regulator->uA_load); -} - static ssize_t regulator_uV_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -427,6 +394,9 @@ static ssize_t regulator_status_show(struct device *dev, case REGULATOR_STATUS_STANDBY: label = "standby"; break; + case REGULATOR_STATUS_UNDEFINED: + label = "undefined"; + break; default: return -ERANGE; } @@ -967,6 +937,14 @@ static int set_machine_constraints(struct regulator_dev *rdev, } } + if (rdev->constraints->ramp_delay && ops->set_ramp_delay) { + ret = ops->set_ramp_delay(rdev, rdev->constraints->ramp_delay); + if (ret < 0) { + rdev_err(rdev, "failed to set ramp_delay\n"); + goto out; + } + } + print_constraints(rdev); return 0; out: @@ -1097,48 +1075,29 @@ static struct regulator *create_regulator(struct regulator_dev *rdev, list_add(®ulator->list, &rdev->consumer_list); if (dev) { - /* create a 'requested_microamps_name' sysfs entry */ - size = scnprintf(buf, REG_STR_SIZE, - "microamps_requested_%s-%s", - dev_name(dev), supply_name); - if (size >= REG_STR_SIZE) - goto overflow_err; - regulator->dev = dev; - sysfs_attr_init(®ulator->dev_attr.attr); - regulator->dev_attr.attr.name = kstrdup(buf, GFP_KERNEL); - if (regulator->dev_attr.attr.name == NULL) - goto attr_name_err; - - regulator->dev_attr.attr.mode = 0444; - regulator->dev_attr.show = device_requested_uA_show; - err = device_create_file(dev, ®ulator->dev_attr); - if (err < 0) { - rdev_warn(rdev, "could not add regulator_dev requested microamps sysfs entry\n"); - goto attr_name_err; - } - /* also add a link to the device sysfs entry */ + /* Add a link to the device sysfs entry */ size = scnprintf(buf, REG_STR_SIZE, "%s-%s", dev->kobj.name, supply_name); if (size >= REG_STR_SIZE) - goto attr_err; + goto overflow_err; regulator->supply_name = kstrdup(buf, GFP_KERNEL); if (regulator->supply_name == NULL) - goto attr_err; + goto overflow_err; err = sysfs_create_link(&rdev->dev.kobj, &dev->kobj, buf); if (err) { rdev_warn(rdev, "could not add device link %s err %d\n", dev->kobj.name, err); - goto link_name_err; + /* non-fatal */ } } else { regulator->supply_name = kstrdup(supply_name, GFP_KERNEL); if (regulator->supply_name == NULL) - goto attr_err; + goto overflow_err; } regulator->debugfs = debugfs_create_dir(regulator->supply_name, @@ -1165,12 +1124,6 @@ static struct regulator *create_regulator(struct regulator_dev *rdev, mutex_unlock(&rdev->mutex); return regulator; -link_name_err: - kfree(regulator->supply_name); -attr_err: - device_remove_file(regulator->dev, ®ulator->dev_attr); -attr_name_err: - kfree(regulator->dev_attr.attr.name); overflow_err: list_del(®ulator->list); kfree(regulator); @@ -1181,7 +1134,7 @@ overflow_err: static int _regulator_get_enable_time(struct regulator_dev *rdev) { if (!rdev->desc->ops->enable_time) - return 0; + return rdev->desc->enable_time; return rdev->desc->ops->enable_time(rdev); } @@ -1420,11 +1373,8 @@ void regulator_put(struct regulator *regulator) debugfs_remove_recursive(regulator->debugfs); /* remove any sysfs entries */ - if (regulator->dev) { + if (regulator->dev) sysfs_remove_link(&rdev->dev.kobj, regulator->supply_name); - device_remove_file(regulator->dev, ®ulator->dev_attr); - kfree(regulator->dev_attr.attr.name); - } kfree(regulator->supply_name); list_del(®ulator->list); kfree(regulator); @@ -1459,19 +1409,61 @@ void devm_regulator_put(struct regulator *regulator) { int rc; - rc = devres_destroy(regulator->dev, devm_regulator_release, + rc = devres_release(regulator->dev, devm_regulator_release, devm_regulator_match, regulator); - if (rc == 0) - regulator_put(regulator); - else + if (rc != 0) WARN_ON(rc); } EXPORT_SYMBOL_GPL(devm_regulator_put); +static int _regulator_do_enable(struct regulator_dev *rdev) +{ + int ret, delay; + + /* Query before enabling in case configuration dependent. */ + ret = _regulator_get_enable_time(rdev); + if (ret >= 0) { + delay = ret; + } else { + rdev_warn(rdev, "enable_time() failed: %d\n", ret); + delay = 0; + } + + trace_regulator_enable(rdev_get_name(rdev)); + + if (rdev->ena_gpio) { + gpio_set_value_cansleep(rdev->ena_gpio, + !rdev->ena_gpio_invert); + rdev->ena_gpio_state = 1; + } else if (rdev->desc->ops->enable) { + ret = rdev->desc->ops->enable(rdev); + if (ret < 0) + return ret; + } else { + return -EINVAL; + } + + /* Allow the regulator to ramp; it would be useful to extend + * this for bulk operations so that the regulators can ramp + * together. */ + trace_regulator_enable_delay(rdev_get_name(rdev)); + + if (delay >= 1000) { + mdelay(delay / 1000); + udelay(delay % 1000); + } else if (delay) { + udelay(delay); + } + + trace_regulator_enable_complete(rdev_get_name(rdev)); + + return 0; +} + /* locks held by regulator_enable() */ static int _regulator_enable(struct regulator_dev *rdev) { - int ret, delay; + int ret; /* check voltage and requested load before enabling */ if (rdev->constraints && @@ -1485,40 +1477,10 @@ static int _regulator_enable(struct regulator_dev *rdev) if (!_regulator_can_change_status(rdev)) return -EPERM; - if (!rdev->desc->ops->enable) - return -EINVAL; - - /* Query before enabling in case configuration - * dependent. */ - ret = _regulator_get_enable_time(rdev); - if (ret >= 0) { - delay = ret; - } else { - rdev_warn(rdev, "enable_time() failed: %d\n", - ret); - delay = 0; - } - - trace_regulator_enable(rdev_get_name(rdev)); - - /* Allow the regulator to ramp; it would be useful - * to extend this for bulk operations so that the - * regulators can ramp together. */ - ret = rdev->desc->ops->enable(rdev); + ret = _regulator_do_enable(rdev); if (ret < 0) return ret; - trace_regulator_enable_delay(rdev_get_name(rdev)); - - if (delay >= 1000) { - mdelay(delay / 1000); - udelay(delay % 1000); - } else if (delay) { - udelay(delay); - } - - trace_regulator_enable_complete(rdev_get_name(rdev)); - } else if (ret < 0) { rdev_err(rdev, "is_enabled() failed: %d\n", ret); return ret; @@ -1567,6 +1529,30 @@ int regulator_enable(struct regulator *regulator) } EXPORT_SYMBOL_GPL(regulator_enable); +static int _regulator_do_disable(struct regulator_dev *rdev) +{ + int ret; + + trace_regulator_disable(rdev_get_name(rdev)); + + if (rdev->ena_gpio) { + gpio_set_value_cansleep(rdev->ena_gpio, + rdev->ena_gpio_invert); + rdev->ena_gpio_state = 0; + + } else if (rdev->desc->ops->disable) { + ret = rdev->desc->ops->disable(rdev); + if (ret != 0) + return ret; + } + + trace_regulator_disable_complete(rdev_get_name(rdev)); + + _notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE, + NULL); + return 0; +} + /* locks held by regulator_disable() */ static int _regulator_disable(struct regulator_dev *rdev) { @@ -1581,20 +1567,12 @@ static int _regulator_disable(struct regulator_dev *rdev) (rdev->constraints && !rdev->constraints->always_on)) { /* we are last user */ - if (_regulator_can_change_status(rdev) && - rdev->desc->ops->disable) { - trace_regulator_disable(rdev_get_name(rdev)); - - ret = rdev->desc->ops->disable(rdev); + if (_regulator_can_change_status(rdev)) { + ret = _regulator_do_disable(rdev); if (ret < 0) { rdev_err(rdev, "failed to disable\n"); return ret; } - - trace_regulator_disable_complete(rdev_get_name(rdev)); - - _notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE, - NULL); } rdev->use_count = 0; @@ -1812,6 +1790,10 @@ EXPORT_SYMBOL_GPL(regulator_disable_regmap); static int _regulator_is_enabled(struct regulator_dev *rdev) { + /* A GPIO control always takes precedence */ + if (rdev->ena_gpio) + return rdev->ena_gpio_state; + /* If we don't know then assume that the regulator is always on */ if (!rdev->desc->ops->is_enabled) return 1; @@ -1883,6 +1865,31 @@ int regulator_list_voltage_linear(struct regulator_dev *rdev, EXPORT_SYMBOL_GPL(regulator_list_voltage_linear); /** + * regulator_list_voltage_table - List voltages with table based mapping + * + * @rdev: Regulator device + * @selector: Selector to convert into a voltage + * + * Regulators with table based mapping between voltages and + * selectors can set volt_table in the regulator descriptor + * and then use this function as their list_voltage() operation. + */ +int regulator_list_voltage_table(struct regulator_dev *rdev, + unsigned int selector) +{ + if (!rdev->desc->volt_table) { + BUG_ON(!rdev->desc->volt_table); + return -EINVAL; + } + + if (selector >= rdev->desc->n_voltages) + return -EINVAL; + + return rdev->desc->volt_table[selector]; +} +EXPORT_SYMBOL_GPL(regulator_list_voltage_table); + +/** * regulator_list_voltage - enumerate supported voltages * @regulator: regulator source * @selector: identify voltage to list @@ -1928,8 +1935,18 @@ EXPORT_SYMBOL_GPL(regulator_list_voltage); int regulator_is_supported_voltage(struct regulator *regulator, int min_uV, int max_uV) { + struct regulator_dev *rdev = regulator->rdev; int i, voltages, ret; + /* If we can't change voltage check the current voltage */ + if (!(rdev->constraints->valid_ops_mask & REGULATOR_CHANGE_VOLTAGE)) { + ret = regulator_get_voltage(regulator); + if (ret >= 0) + return (min_uV >= ret && ret <= max_uV); + else + return ret; + } + ret = regulator_count_voltages(regulator); if (ret < 0) return ret; @@ -2045,6 +2062,14 @@ int regulator_map_voltage_linear(struct regulator_dev *rdev, { int ret, voltage; + /* Allow uV_step to be 0 for fixed voltage */ + if (rdev->desc->n_voltages == 1 && rdev->desc->uV_step == 0) { + if (min_uV <= rdev->desc->min_uV && rdev->desc->min_uV <= max_uV) + return 0; + else + return -EINVAL; + } + if (!rdev->desc->uV_step) { BUG_ON(!rdev->desc->uV_step); return -EINVAL; @@ -2071,7 +2096,7 @@ static int _regulator_do_set_voltage(struct regulator_dev *rdev, { int ret; int delay = 0; - int best_val; + int best_val = 0; unsigned int selector; int old_selector = -1; @@ -2084,7 +2109,8 @@ static int _regulator_do_set_voltage(struct regulator_dev *rdev, * If we can't obtain the old selector there is not enough * info to call set_voltage_time_sel(). */ - if (rdev->desc->ops->set_voltage_time_sel && + if (_regulator_is_enabled(rdev) && + rdev->desc->ops->set_voltage_time_sel && rdev->desc->ops->get_voltage_sel) { old_selector = rdev->desc->ops->get_voltage_sel(rdev); if (old_selector < 0) @@ -2094,29 +2120,45 @@ static int _regulator_do_set_voltage(struct regulator_dev *rdev, if (rdev->desc->ops->set_voltage) { ret = rdev->desc->ops->set_voltage(rdev, min_uV, max_uV, &selector); + + if (ret >= 0) { + if (rdev->desc->ops->list_voltage) + best_val = rdev->desc->ops->list_voltage(rdev, + selector); + else + best_val = _regulator_get_voltage(rdev); + } + } else if (rdev->desc->ops->set_voltage_sel) { - if (rdev->desc->ops->map_voltage) + if (rdev->desc->ops->map_voltage) { ret = rdev->desc->ops->map_voltage(rdev, min_uV, max_uV); - else - ret = regulator_map_voltage_iterate(rdev, min_uV, - max_uV); + } else { + if (rdev->desc->ops->list_voltage == + regulator_list_voltage_linear) + ret = regulator_map_voltage_linear(rdev, + min_uV, max_uV); + else + ret = regulator_map_voltage_iterate(rdev, + min_uV, max_uV); + } if (ret >= 0) { - selector = ret; - ret = rdev->desc->ops->set_voltage_sel(rdev, ret); + best_val = rdev->desc->ops->list_voltage(rdev, ret); + if (min_uV <= best_val && max_uV >= best_val) { + selector = ret; + ret = rdev->desc->ops->set_voltage_sel(rdev, + ret); + } else { + ret = -EINVAL; + } } } else { ret = -EINVAL; } - if (rdev->desc->ops->list_voltage) - best_val = rdev->desc->ops->list_voltage(rdev, selector); - else - best_val = -1; - /* Call set_voltage_time_sel if successfully obtained old_selector */ - if (ret == 0 && old_selector >= 0 && + if (ret == 0 && _regulator_is_enabled(rdev) && old_selector >= 0 && rdev->desc->ops->set_voltage_time_sel) { delay = rdev->desc->ops->set_voltage_time_sel(rdev, @@ -2126,19 +2168,19 @@ static int _regulator_do_set_voltage(struct regulator_dev *rdev, delay); delay = 0; } - } - /* Insert any necessary delays */ - if (delay >= 1000) { - mdelay(delay / 1000); - udelay(delay % 1000); - } else if (delay) { - udelay(delay); + /* Insert any necessary delays */ + if (delay >= 1000) { + mdelay(delay / 1000); + udelay(delay % 1000); + } else if (delay) { + udelay(delay); + } } - if (ret == 0) + if (ret == 0 && best_val >= 0) _notifier_call_chain(rdev, REGULATOR_EVENT_VOLTAGE_CHANGE, - NULL); + (void *)best_val); trace_regulator_set_voltage_complete(rdev_get_name(rdev), best_val); @@ -2249,6 +2291,46 @@ int regulator_set_voltage_time(struct regulator *regulator, EXPORT_SYMBOL_GPL(regulator_set_voltage_time); /** + *regulator_set_voltage_time_sel - get raise/fall time + * @regulator: regulator source + * @old_selector: selector for starting voltage + * @new_selector: selector for target voltage + * + * Provided with the starting and target voltage selectors, this function + * returns time in microseconds required to rise or fall to this new voltage + * + * Drivers providing ramp_delay in regulation_constraints can use this as their + * set_voltage_time_sel() operation. + */ +int regulator_set_voltage_time_sel(struct regulator_dev *rdev, + unsigned int old_selector, + unsigned int new_selector) +{ + unsigned int ramp_delay = 0; + int old_volt, new_volt; + + if (rdev->constraints->ramp_delay) + ramp_delay = rdev->constraints->ramp_delay; + else if (rdev->desc->ramp_delay) + ramp_delay = rdev->desc->ramp_delay; + + if (ramp_delay == 0) { + rdev_warn(rdev, "ramp_delay not set\n"); + return 0; + } + + /* sanity check */ + if (!rdev->desc->ops->list_voltage) + return -EINVAL; + + old_volt = rdev->desc->ops->list_voltage(rdev, old_selector); + new_volt = rdev->desc->ops->list_voltage(rdev, new_selector); + + return DIV_ROUND_UP(abs(new_volt - old_volt), ramp_delay); +} +EXPORT_SYMBOL_GPL(regulator_set_voltage_time_sel); + +/** * regulator_sync_voltage - re-apply last regulator output voltage * @regulator: regulator source * @@ -2519,9 +2601,12 @@ int regulator_set_optimum_mode(struct regulator *regulator, int uA_load) { struct regulator_dev *rdev = regulator->rdev; struct regulator *consumer; - int ret, output_uV, input_uV, total_uA_load = 0; + int ret, output_uV, input_uV = 0, total_uA_load = 0; unsigned int mode; + if (rdev->supply) + input_uV = regulator_get_voltage(rdev->supply); + mutex_lock(&rdev->mutex); /* @@ -2554,10 +2639,7 @@ int regulator_set_optimum_mode(struct regulator *regulator, int uA_load) goto out; } - /* get input voltage */ - input_uV = 0; - if (rdev->supply) - input_uV = regulator_get_voltage(rdev->supply); + /* No supply? Use constraint voltage */ if (input_uV <= 0) input_uV = rdev->constraints->input_uV; if (input_uV <= 0) { @@ -2628,7 +2710,7 @@ static void _notifier_call_chain(struct regulator_dev *rdev, unsigned long event, void *data) { /* call rdev chain first */ - blocking_notifier_call_chain(&rdev->notifier, event, NULL); + blocking_notifier_call_chain(&rdev->notifier, event, data); } /** @@ -2909,10 +2991,10 @@ int regulator_mode_to_status(unsigned int mode) return REGULATOR_STATUS_NORMAL; case REGULATOR_MODE_IDLE: return REGULATOR_STATUS_IDLE; - case REGULATOR_STATUS_STANDBY: + case REGULATOR_MODE_STANDBY: return REGULATOR_STATUS_STANDBY; default: - return 0; + return REGULATOR_STATUS_UNDEFINED; } } EXPORT_SYMBOL_GPL(regulator_mode_to_status); @@ -3105,7 +3187,10 @@ regulator_register(const struct regulator_desc *regulator_desc, rdev->reg_data = config->driver_data; rdev->owner = regulator_desc->owner; rdev->desc = regulator_desc; - rdev->regmap = config->regmap; + if (config->regmap) + rdev->regmap = config->regmap; + else + rdev->regmap = dev_get_regmap(dev, NULL); INIT_LIST_HEAD(&rdev->consumer_list); INIT_LIST_HEAD(&rdev->list); BLOCKING_INIT_NOTIFIER_HEAD(&rdev->notifier); @@ -3132,6 +3217,26 @@ regulator_register(const struct regulator_desc *regulator_desc, dev_set_drvdata(&rdev->dev, rdev); + if (config->ena_gpio) { + ret = gpio_request_one(config->ena_gpio, + GPIOF_DIR_OUT | config->ena_gpio_flags, + rdev_get_name(rdev)); + if (ret != 0) { + rdev_err(rdev, "Failed to request enable GPIO%d: %d\n", + config->ena_gpio, ret); + goto clean; + } + + rdev->ena_gpio = config->ena_gpio; + rdev->ena_gpio_invert = config->ena_gpio_invert; + + if (config->ena_gpio_flags & GPIOF_OUT_INIT_HIGH) + rdev->ena_gpio_state = 1; + + if (rdev->ena_gpio_invert) + rdev->ena_gpio_state = !rdev->ena_gpio_state; + } + /* set regulator constraints */ if (init_data) constraints = &init_data->constraints; @@ -3200,6 +3305,8 @@ unset_supplies: scrub: if (rdev->supply) regulator_put(rdev->supply); + if (rdev->ena_gpio) + gpio_free(rdev->ena_gpio); kfree(rdev->constraints); device_unregister(&rdev->dev); /* device core frees rdev */ @@ -3233,6 +3340,8 @@ void regulator_unregister(struct regulator_dev *rdev) unset_regulator_supplies(rdev); list_del(&rdev->list); kfree(rdev->constraints); + if (rdev->ena_gpio) + gpio_free(rdev->ena_gpio); device_unregister(&rdev->dev); mutex_unlock(®ulator_list_mutex); } @@ -3472,6 +3581,15 @@ static int __init regulator_init_complete(void) struct regulation_constraints *c; int enabled, ret; + /* + * Since DT doesn't provide an idiomatic mechanism for + * enabling full constraints and since it's much more natural + * with DT to provide them just assume that a DT enabled + * system has full constraints. + */ + if (of_have_populated_dt()) + has_full_constraints = true; + mutex_lock(®ulator_list_mutex); /* If we have a full configuration then disable any regulators diff --git a/drivers/regulator/da903x.c b/drivers/regulator/da903x.c index 1005f5f7e603..36c5b92fe0af 100644 --- a/drivers/regulator/da903x.c +++ b/drivers/regulator/da903x.c @@ -107,6 +107,9 @@ static int da903x_set_voltage_sel(struct regulator_dev *rdev, unsigned selector) struct device *da9034_dev = to_da903x_dev(rdev); uint8_t val, mask; + if (rdev->desc->n_voltages == 1) + return -EINVAL; + val = selector << info->vol_shift; mask = ((1 << info->vol_nbits) - 1) << info->vol_shift; @@ -120,6 +123,9 @@ static int da903x_get_voltage_sel(struct regulator_dev *rdev) uint8_t val, mask; int ret; + if (rdev->desc->n_voltages == 1) + return 0; + ret = da903x_read(da9034_dev, info->vol_reg, &val); if (ret) return ret; diff --git a/drivers/regulator/da9052-regulator.c b/drivers/regulator/da9052-regulator.c index 88976d8d44ed..903299cf15cf 100644 --- a/drivers/regulator/da9052-regulator.c +++ b/drivers/regulator/da9052-regulator.c @@ -405,12 +405,12 @@ static int __devinit da9052_regulator_probe(struct platform_device *pdev) if (!nproot) return -ENODEV; - for (np = of_get_next_child(nproot, NULL); np; - np = of_get_next_child(nproot, np)) { + for_each_child_of_node(nproot, np) { if (!of_node_cmp(np->name, regulator->info->reg_desc.name)) { config.init_data = of_get_regulator_init_data( &pdev->dev, np); + config.of_node = np; break; } } diff --git a/drivers/regulator/fixed-helper.c b/drivers/regulator/fixed-helper.c index cacd33c9d042..f9d027992aae 100644 --- a/drivers/regulator/fixed-helper.c +++ b/drivers/regulator/fixed-helper.c @@ -1,4 +1,5 @@ #include <linux/slab.h> +#include <linux/string.h> #include <linux/platform_device.h> #include <linux/regulator/machine.h> #include <linux/regulator/fixed.h> @@ -13,17 +14,20 @@ static void regulator_fixed_release(struct device *dev) { struct fixed_regulator_data *data = container_of(dev, struct fixed_regulator_data, pdev.dev); + kfree(data->cfg.supply_name); kfree(data); } /** - * regulator_register_fixed - register a no-op fixed regulator + * regulator_register_fixed_name - register a no-op fixed regulator * @id: platform device id + * @name: name to be used for the regulator * @supplies: consumers for this regulator * @num_supplies: number of consumers + * @uv: voltage in microvolts */ -struct platform_device *regulator_register_fixed(int id, - struct regulator_consumer_supply *supplies, int num_supplies) +struct platform_device *regulator_register_always_on(int id, const char *name, + struct regulator_consumer_supply *supplies, int num_supplies, int uv) { struct fixed_regulator_data *data; @@ -31,8 +35,13 @@ struct platform_device *regulator_register_fixed(int id, if (!data) return NULL; - data->cfg.supply_name = "fixed-dummy"; - data->cfg.microvolts = 0; + data->cfg.supply_name = kstrdup(name, GFP_KERNEL); + if (!data->cfg.supply_name) { + kfree(data); + return NULL; + } + + data->cfg.microvolts = uv; data->cfg.gpio = -EINVAL; data->cfg.enabled_at_boot = 1; data->cfg.init_data = &data->init_data; diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c index f09fe7b20e82..185468c4d38f 100644 --- a/drivers/regulator/fixed.c +++ b/drivers/regulator/fixed.c @@ -35,10 +35,6 @@ struct fixed_voltage_data { struct regulator_desc desc; struct regulator_dev *dev; int microvolts; - int gpio; - unsigned startup_delay; - bool enable_high; - bool is_enabled; }; @@ -61,11 +57,11 @@ of_get_fixed_voltage_config(struct device *dev) config = devm_kzalloc(dev, sizeof(struct fixed_voltage_config), GFP_KERNEL); if (!config) - return NULL; + return ERR_PTR(-ENOMEM); config->init_data = of_get_regulator_init_data(dev, dev->of_node); if (!config->init_data) - return NULL; + return ERR_PTR(-EINVAL); init_data = config->init_data; init_data->constraints.apply_uV = 0; @@ -76,13 +72,26 @@ of_get_fixed_voltage_config(struct device *dev) } else { dev_err(dev, "Fixed regulator specified with variable voltages\n"); - return NULL; + return ERR_PTR(-EINVAL); } if (init_data->constraints.boot_on) config->enabled_at_boot = true; config->gpio = of_get_named_gpio(np, "gpio", 0); + /* + * of_get_named_gpio() currently returns ENODEV rather than + * EPROBE_DEFER. This code attempts to be compatible with both + * for now; the ENODEV check can be removed once the API is fixed. + * of_get_named_gpio() doesn't differentiate between a missing + * property (which would be fine here, since the GPIO is optional) + * and some other error. Patches have been posted for both issues. + * Once they are check in, we should replace this with: + * if (config->gpio < 0 && config->gpio != -ENOENT) + */ + if ((config->gpio == -ENODEV) || (config->gpio == -EPROBE_DEFER)) + return ERR_PTR(-EPROBE_DEFER); + delay = of_get_property(np, "startup-delay-us", NULL); if (delay) config->startup_delay = be32_to_cpu(*delay); @@ -93,41 +102,10 @@ of_get_fixed_voltage_config(struct device *dev) if (of_find_property(np, "gpio-open-drain", NULL)) config->gpio_is_open_drain = true; - return config; -} - -static int fixed_voltage_is_enabled(struct regulator_dev *dev) -{ - struct fixed_voltage_data *data = rdev_get_drvdata(dev); - - return data->is_enabled; -} - -static int fixed_voltage_enable(struct regulator_dev *dev) -{ - struct fixed_voltage_data *data = rdev_get_drvdata(dev); - - gpio_set_value_cansleep(data->gpio, data->enable_high); - data->is_enabled = true; - - return 0; -} - -static int fixed_voltage_disable(struct regulator_dev *dev) -{ - struct fixed_voltage_data *data = rdev_get_drvdata(dev); - - gpio_set_value_cansleep(data->gpio, !data->enable_high); - data->is_enabled = false; - - return 0; -} + if (of_find_property(np, "vin-supply", NULL)) + config->input_supply = "vin"; -static int fixed_voltage_enable_time(struct regulator_dev *dev) -{ - struct fixed_voltage_data *data = rdev_get_drvdata(dev); - - return data->startup_delay; + return config; } static int fixed_voltage_get_voltage(struct regulator_dev *dev) @@ -151,15 +129,6 @@ static int fixed_voltage_list_voltage(struct regulator_dev *dev, return data->microvolts; } -static struct regulator_ops fixed_voltage_gpio_ops = { - .is_enabled = fixed_voltage_is_enabled, - .enable = fixed_voltage_enable, - .disable = fixed_voltage_disable, - .enable_time = fixed_voltage_enable_time, - .get_voltage = fixed_voltage_get_voltage, - .list_voltage = fixed_voltage_list_voltage, -}; - static struct regulator_ops fixed_voltage_ops = { .get_voltage = fixed_voltage_get_voltage, .list_voltage = fixed_voltage_list_voltage, @@ -172,10 +141,13 @@ static int __devinit reg_fixed_voltage_probe(struct platform_device *pdev) struct regulator_config cfg = { }; int ret; - if (pdev->dev.of_node) + if (pdev->dev.of_node) { config = of_get_fixed_voltage_config(&pdev->dev); - else + if (IS_ERR(config)) + return PTR_ERR(config); + } else { config = pdev->dev.platform_data; + } if (!config) return -ENOMEM; @@ -196,59 +168,44 @@ static int __devinit reg_fixed_voltage_probe(struct platform_device *pdev) } drvdata->desc.type = REGULATOR_VOLTAGE; drvdata->desc.owner = THIS_MODULE; + drvdata->desc.ops = &fixed_voltage_ops; - if (config->microvolts) - drvdata->desc.n_voltages = 1; + drvdata->desc.enable_time = config->startup_delay; - drvdata->microvolts = config->microvolts; - drvdata->gpio = config->gpio; - drvdata->startup_delay = config->startup_delay; - - if (gpio_is_valid(config->gpio)) { - int gpio_flag; - drvdata->enable_high = config->enable_high; - - /* FIXME: Remove below print warning - * - * config->gpio must be set to -EINVAL by platform code if - * GPIO control is not required. However, early adopters - * not requiring GPIO control may forget to initialize - * config->gpio to -EINVAL. This will cause GPIO 0 to be used - * for GPIO control. - * - * This warning will be removed once there are a couple of users - * for this driver. - */ - if (!config->gpio) - dev_warn(&pdev->dev, - "using GPIO 0 for regulator enable control\n"); - - /* - * set output direction without changing state - * to prevent glitch - */ - drvdata->is_enabled = config->enabled_at_boot; - ret = drvdata->is_enabled ? - config->enable_high : !config->enable_high; - gpio_flag = ret ? GPIOF_OUT_INIT_HIGH : GPIOF_OUT_INIT_LOW; - - if (config->gpio_is_open_drain) - gpio_flag |= GPIOF_OPEN_DRAIN; - - ret = gpio_request_one(config->gpio, gpio_flag, - config->supply_name); - if (ret) { + if (config->input_supply) { + drvdata->desc.supply_name = kstrdup(config->input_supply, + GFP_KERNEL); + if (!drvdata->desc.supply_name) { dev_err(&pdev->dev, - "Could not obtain regulator enable GPIO %d: %d\n", - config->gpio, ret); + "Failed to allocate input supply\n"); + ret = -ENOMEM; goto err_name; } + } + + if (config->microvolts) + drvdata->desc.n_voltages = 1; - drvdata->desc.ops = &fixed_voltage_gpio_ops; + drvdata->microvolts = config->microvolts; + if (config->gpio >= 0) + cfg.ena_gpio = config->gpio; + cfg.ena_gpio_invert = !config->enable_high; + if (config->enabled_at_boot) { + if (config->enable_high) { + cfg.ena_gpio_flags |= GPIOF_OUT_INIT_HIGH; + } else { + cfg.ena_gpio_flags |= GPIOF_OUT_INIT_LOW; + } } else { - drvdata->desc.ops = &fixed_voltage_ops; + if (config->enable_high) { + cfg.ena_gpio_flags |= GPIOF_OUT_INIT_LOW; + } else { + cfg.ena_gpio_flags |= GPIOF_OUT_INIT_HIGH; + } } + if (config->gpio_is_open_drain) + cfg.ena_gpio_flags |= GPIOF_OPEN_DRAIN; cfg.dev = &pdev->dev; cfg.init_data = config->init_data; @@ -259,7 +216,7 @@ static int __devinit reg_fixed_voltage_probe(struct platform_device *pdev) if (IS_ERR(drvdata->dev)) { ret = PTR_ERR(drvdata->dev); dev_err(&pdev->dev, "Failed to register regulator: %d\n", ret); - goto err_gpio; + goto err_input; } platform_set_drvdata(pdev, drvdata); @@ -269,9 +226,8 @@ static int __devinit reg_fixed_voltage_probe(struct platform_device *pdev) return 0; -err_gpio: - if (gpio_is_valid(config->gpio)) - gpio_free(config->gpio); +err_input: + kfree(drvdata->desc.supply_name); err_name: kfree(drvdata->desc.name); err: @@ -283,8 +239,7 @@ static int __devexit reg_fixed_voltage_remove(struct platform_device *pdev) struct fixed_voltage_data *drvdata = platform_get_drvdata(pdev); regulator_unregister(drvdata->dev); - if (gpio_is_valid(drvdata->gpio)) - gpio_free(drvdata->gpio); + kfree(drvdata->desc.supply_name); kfree(drvdata->desc.name); return 0; @@ -296,8 +251,6 @@ static const struct of_device_id fixed_of_match[] __devinitconst = { {}, }; MODULE_DEVICE_TABLE(of, fixed_of_match); -#else -#define fixed_of_match NULL #endif static struct platform_driver regulator_fixed_voltage_driver = { @@ -306,7 +259,7 @@ static struct platform_driver regulator_fixed_voltage_driver = { .driver = { .name = "reg-fixed-voltage", .owner = THIS_MODULE, - .of_match_table = fixed_of_match, + .of_match_table = of_match_ptr(fixed_of_match), }, }; diff --git a/drivers/regulator/gpio-regulator.c b/drivers/regulator/gpio-regulator.c index 242851a4c1a6..34b67bee9323 100644 --- a/drivers/regulator/gpio-regulator.c +++ b/drivers/regulator/gpio-regulator.c @@ -36,11 +36,6 @@ struct gpio_regulator_data { struct regulator_desc desc; struct regulator_dev *dev; - int enable_gpio; - bool enable_high; - bool is_enabled; - unsigned startup_delay; - struct gpio *gpios; int nr_gpios; @@ -50,44 +45,6 @@ struct gpio_regulator_data { int state; }; -static int gpio_regulator_is_enabled(struct regulator_dev *dev) -{ - struct gpio_regulator_data *data = rdev_get_drvdata(dev); - - return data->is_enabled; -} - -static int gpio_regulator_enable(struct regulator_dev *dev) -{ - struct gpio_regulator_data *data = rdev_get_drvdata(dev); - - if (gpio_is_valid(data->enable_gpio)) { - gpio_set_value_cansleep(data->enable_gpio, data->enable_high); - data->is_enabled = true; - } - - return 0; -} - -static int gpio_regulator_disable(struct regulator_dev *dev) -{ - struct gpio_regulator_data *data = rdev_get_drvdata(dev); - - if (gpio_is_valid(data->enable_gpio)) { - gpio_set_value_cansleep(data->enable_gpio, !data->enable_high); - data->is_enabled = false; - } - - return 0; -} - -static int gpio_regulator_enable_time(struct regulator_dev *dev) -{ - struct gpio_regulator_data *data = rdev_get_drvdata(dev); - - return data->startup_delay; -} - static int gpio_regulator_get_value(struct regulator_dev *dev) { struct gpio_regulator_data *data = rdev_get_drvdata(dev); @@ -153,20 +110,12 @@ static int gpio_regulator_set_current_limit(struct regulator_dev *dev, } static struct regulator_ops gpio_regulator_voltage_ops = { - .is_enabled = gpio_regulator_is_enabled, - .enable = gpio_regulator_enable, - .disable = gpio_regulator_disable, - .enable_time = gpio_regulator_enable_time, .get_voltage = gpio_regulator_get_value, .set_voltage = gpio_regulator_set_voltage, .list_voltage = gpio_regulator_list_voltage, }; static struct regulator_ops gpio_regulator_current_ops = { - .is_enabled = gpio_regulator_is_enabled, - .enable = gpio_regulator_enable, - .disable = gpio_regulator_disable, - .enable_time = gpio_regulator_enable_time, .get_current_limit = gpio_regulator_get_value, .set_current_limit = gpio_regulator_set_current_limit, }; @@ -213,6 +162,7 @@ static int __devinit gpio_regulator_probe(struct platform_device *pdev) drvdata->nr_states = config->nr_states; drvdata->desc.owner = THIS_MODULE; + drvdata->desc.enable_time = config->startup_delay; /* handle regulator type*/ switch (config->type) { @@ -232,52 +182,12 @@ static int __devinit gpio_regulator_probe(struct platform_device *pdev) break; } - drvdata->enable_gpio = config->enable_gpio; - drvdata->startup_delay = config->startup_delay; - - if (gpio_is_valid(config->enable_gpio)) { - drvdata->enable_high = config->enable_high; - - ret = gpio_request(config->enable_gpio, config->supply_name); - if (ret) { - dev_err(&pdev->dev, - "Could not obtain regulator enable GPIO %d: %d\n", - config->enable_gpio, ret); - goto err_memstate; - } - - /* set output direction without changing state - * to prevent glitch - */ - if (config->enabled_at_boot) { - drvdata->is_enabled = true; - ret = gpio_direction_output(config->enable_gpio, - config->enable_high); - } else { - drvdata->is_enabled = false; - ret = gpio_direction_output(config->enable_gpio, - !config->enable_high); - } - - if (ret) { - dev_err(&pdev->dev, - "Could not configure regulator enable GPIO %d direction: %d\n", - config->enable_gpio, ret); - goto err_enablegpio; - } - } else { - /* Regulator without GPIO control is considered - * always enabled - */ - drvdata->is_enabled = true; - } - drvdata->nr_gpios = config->nr_gpios; ret = gpio_request_array(drvdata->gpios, drvdata->nr_gpios); if (ret) { dev_err(&pdev->dev, "Could not obtain regulator setting GPIOs: %d\n", ret); - goto err_enablegpio; + goto err_memstate; } /* build initial state from gpio init data. */ @@ -292,6 +202,21 @@ static int __devinit gpio_regulator_probe(struct platform_device *pdev) cfg.init_data = config->init_data; cfg.driver_data = drvdata; + if (config->enable_gpio >= 0) + cfg.ena_gpio = config->enable_gpio; + cfg.ena_gpio_invert = !config->enable_high; + if (config->enabled_at_boot) { + if (config->enable_high) + cfg.ena_gpio_flags |= GPIOF_OUT_INIT_HIGH; + else + cfg.ena_gpio_flags |= GPIOF_OUT_INIT_LOW; + } else { + if (config->enable_high) + cfg.ena_gpio_flags |= GPIOF_OUT_INIT_LOW; + else + cfg.ena_gpio_flags |= GPIOF_OUT_INIT_HIGH; + } + drvdata->dev = regulator_register(&drvdata->desc, &cfg); if (IS_ERR(drvdata->dev)) { ret = PTR_ERR(drvdata->dev); @@ -305,9 +230,6 @@ static int __devinit gpio_regulator_probe(struct platform_device *pdev) err_stategpio: gpio_free_array(drvdata->gpios, drvdata->nr_gpios); -err_enablegpio: - if (gpio_is_valid(config->enable_gpio)) - gpio_free(config->enable_gpio); err_memstate: kfree(drvdata->states); err_memgpio: @@ -329,9 +251,6 @@ static int __devexit gpio_regulator_remove(struct platform_device *pdev) kfree(drvdata->states); kfree(drvdata->gpios); - if (gpio_is_valid(drvdata->enable_gpio)) - gpio_free(drvdata->enable_gpio); - kfree(drvdata->desc.name); return 0; diff --git a/drivers/regulator/isl6271a-regulator.c b/drivers/regulator/isl6271a-regulator.c index 56d273f25603..1d145a07ada9 100644 --- a/drivers/regulator/isl6271a-regulator.c +++ b/drivers/regulator/isl6271a-regulator.c @@ -75,19 +75,12 @@ static struct regulator_ops isl_core_ops = { static int isl6271a_get_fixed_voltage(struct regulator_dev *dev) { - int id = rdev_get_id(dev); - return (id == 1) ? 1100000 : 1300000; -} - -static int isl6271a_list_fixed_voltage(struct regulator_dev *dev, unsigned selector) -{ - int id = rdev_get_id(dev); - return (id == 1) ? 1100000 : 1300000; + return dev->desc->min_uV; } static struct regulator_ops isl_fixed_ops = { .get_voltage = isl6271a_get_fixed_voltage, - .list_voltage = isl6271a_list_fixed_voltage, + .list_voltage = regulator_list_voltage_linear, }; static const struct regulator_desc isl_rd[] = { @@ -107,6 +100,7 @@ static const struct regulator_desc isl_rd[] = { .ops = &isl_fixed_ops, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, + .min_uV = 1100000, }, { .name = "LDO2", .id = 2, @@ -114,6 +108,7 @@ static const struct regulator_desc isl_rd[] = { .ops = &isl_fixed_ops, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, + .min_uV = 1300000, }, }; diff --git a/drivers/regulator/lp3971.c b/drivers/regulator/lp3971.c index 981bea9cb9d7..7c6e3b8ff484 100644 --- a/drivers/regulator/lp3971.c +++ b/drivers/regulator/lp3971.c @@ -65,11 +65,11 @@ static const int buck_base_addr[] = { #define LP3971_BUCK_TARGET_VOL1_REG(x) (buck_base_addr[x]) #define LP3971_BUCK_TARGET_VOL2_REG(x) (buck_base_addr[x]+1) -static const int buck_voltage_map[] = { - 0, 800, 850, 900, 950, 1000, 1050, 1100, - 1150, 1200, 1250, 1300, 1350, 1400, 1450, 1500, - 1550, 1600, 1650, 1700, 1800, 1900, 2500, 2800, - 3000, 3300, +static const unsigned int buck_voltage_map[] = { + 0, 800000, 850000, 900000, 950000, 1000000, 1050000, 1100000, + 1150000, 1200000, 1250000, 1300000, 1350000, 1400000, 1450000, 1500000, + 1550000, 1600000, 1650000, 1700000, 1800000, 1900000, 2500000, 2800000, + 3000000, 3300000, }; #define BUCK_TARGET_VOL_MASK 0x3f @@ -98,39 +98,19 @@ static const int buck_voltage_map[] = { #define LDO_VOL_CONTR_SHIFT(x) ((x & 1) << 2) #define LDO_VOL_CONTR_MASK 0x0f -static const int ldo45_voltage_map[] = { - 1000, 1050, 1100, 1150, 1200, 1250, 1300, 1350, - 1400, 1500, 1800, 1900, 2500, 2800, 3000, 3300, +static const unsigned int ldo45_voltage_map[] = { + 1000000, 1050000, 1100000, 1150000, 1200000, 1250000, 1300000, 1350000, + 1400000, 1500000, 1800000, 1900000, 2500000, 2800000, 3000000, 3300000, }; -static const int ldo123_voltage_map[] = { - 1800, 1900, 2000, 2100, 2200, 2300, 2400, 2500, - 2600, 2700, 2800, 2900, 3000, 3100, 3200, 3300, +static const unsigned int ldo123_voltage_map[] = { + 1800000, 1900000, 2000000, 2100000, 2200000, 2300000, 2400000, 2500000, + 2600000, 2700000, 2800000, 2900000, 3000000, 3100000, 3200000, 3300000, }; -static const int *ldo_voltage_map[] = { - ldo123_voltage_map, /* LDO1 */ - ldo123_voltage_map, /* LDO2 */ - ldo123_voltage_map, /* LDO3 */ - ldo45_voltage_map, /* LDO4 */ - ldo45_voltage_map, /* LDO5 */ -}; - -#define LDO_VOL_VALUE_MAP(x) (ldo_voltage_map[(x - LP3971_LDO1)]) - #define LDO_VOL_MIN_IDX 0x00 #define LDO_VOL_MAX_IDX 0x0f -static int lp3971_ldo_list_voltage(struct regulator_dev *dev, unsigned index) -{ - int ldo = rdev_get_id(dev) - LP3971_LDO1; - - if (index > LDO_VOL_MAX_IDX) - return -EINVAL; - - return 1000 * LDO_VOL_VALUE_MAP(ldo)[index]; -} - static int lp3971_ldo_is_enabled(struct regulator_dev *dev) { struct lp3971 *lp3971 = rdev_get_drvdata(dev); @@ -169,7 +149,7 @@ static int lp3971_ldo_get_voltage(struct regulator_dev *dev) reg = lp3971_reg_read(lp3971, LP3971_LDO_VOL_CONTR_REG(ldo)); val = (reg >> LDO_VOL_CONTR_SHIFT(ldo)) & LDO_VOL_CONTR_MASK; - return 1000 * LDO_VOL_VALUE_MAP(ldo)[val]; + return dev->desc->volt_table[val]; } static int lp3971_ldo_set_voltage_sel(struct regulator_dev *dev, @@ -184,7 +164,7 @@ static int lp3971_ldo_set_voltage_sel(struct regulator_dev *dev, } static struct regulator_ops lp3971_ldo_ops = { - .list_voltage = lp3971_ldo_list_voltage, + .list_voltage = regulator_list_voltage_table, .is_enabled = lp3971_ldo_is_enabled, .enable = lp3971_ldo_enable, .disable = lp3971_ldo_disable, @@ -192,14 +172,6 @@ static struct regulator_ops lp3971_ldo_ops = { .set_voltage_sel = lp3971_ldo_set_voltage_sel, }; -static int lp3971_dcdc_list_voltage(struct regulator_dev *dev, unsigned index) -{ - if (index < BUCK_TARGET_VOL_MIN_IDX || index > BUCK_TARGET_VOL_MAX_IDX) - return -EINVAL; - - return 1000 * buck_voltage_map[index]; -} - static int lp3971_dcdc_is_enabled(struct regulator_dev *dev) { struct lp3971 *lp3971 = rdev_get_drvdata(dev); @@ -240,7 +212,7 @@ static int lp3971_dcdc_get_voltage(struct regulator_dev *dev) reg &= BUCK_TARGET_VOL_MASK; if (reg <= BUCK_TARGET_VOL_MAX_IDX) - val = 1000 * buck_voltage_map[reg]; + val = buck_voltage_map[reg]; else { val = 0; dev_warn(&dev->dev, "chip reported incorrect voltage value.\n"); @@ -273,7 +245,7 @@ static int lp3971_dcdc_set_voltage_sel(struct regulator_dev *dev, } static struct regulator_ops lp3971_dcdc_ops = { - .list_voltage = lp3971_dcdc_list_voltage, + .list_voltage = regulator_list_voltage_table, .is_enabled = lp3971_dcdc_is_enabled, .enable = lp3971_dcdc_enable, .disable = lp3971_dcdc_disable, @@ -287,6 +259,7 @@ static const struct regulator_desc regulators[] = { .id = LP3971_LDO1, .ops = &lp3971_ldo_ops, .n_voltages = ARRAY_SIZE(ldo123_voltage_map), + .volt_table = ldo123_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, @@ -295,6 +268,7 @@ static const struct regulator_desc regulators[] = { .id = LP3971_LDO2, .ops = &lp3971_ldo_ops, .n_voltages = ARRAY_SIZE(ldo123_voltage_map), + .volt_table = ldo123_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, @@ -303,6 +277,7 @@ static const struct regulator_desc regulators[] = { .id = LP3971_LDO3, .ops = &lp3971_ldo_ops, .n_voltages = ARRAY_SIZE(ldo123_voltage_map), + .volt_table = ldo123_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, @@ -311,6 +286,7 @@ static const struct regulator_desc regulators[] = { .id = LP3971_LDO4, .ops = &lp3971_ldo_ops, .n_voltages = ARRAY_SIZE(ldo45_voltage_map), + .volt_table = ldo45_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, @@ -319,6 +295,7 @@ static const struct regulator_desc regulators[] = { .id = LP3971_LDO5, .ops = &lp3971_ldo_ops, .n_voltages = ARRAY_SIZE(ldo45_voltage_map), + .volt_table = ldo45_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, @@ -327,6 +304,7 @@ static const struct regulator_desc regulators[] = { .id = LP3971_DCDC1, .ops = &lp3971_dcdc_ops, .n_voltages = ARRAY_SIZE(buck_voltage_map), + .volt_table = buck_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, @@ -335,6 +313,7 @@ static const struct regulator_desc regulators[] = { .id = LP3971_DCDC2, .ops = &lp3971_dcdc_ops, .n_voltages = ARRAY_SIZE(buck_voltage_map), + .volt_table = buck_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, @@ -343,6 +322,7 @@ static const struct regulator_desc regulators[] = { .id = LP3971_DCDC3, .ops = &lp3971_dcdc_ops, .n_voltages = ARRAY_SIZE(buck_voltage_map), + .volt_table = buck_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, diff --git a/drivers/regulator/lp3972.c b/drivers/regulator/lp3972.c index de073df7d344..3cdc755d9b22 100644 --- a/drivers/regulator/lp3972.c +++ b/drivers/regulator/lp3972.c @@ -74,54 +74,40 @@ struct lp3972 { #define LP3972_OVER2_LDO4_EN BIT(4) #define LP3972_OVER1_S_EN BIT(2) -static const int ldo1_voltage_map[] = { - 1700, 1725, 1750, 1775, 1800, 1825, 1850, 1875, - 1900, 1925, 1950, 1975, 2000, +static const unsigned int ldo1_voltage_map[] = { + 1700000, 1725000, 1750000, 1775000, 1800000, 1825000, 1850000, 1875000, + 1900000, 1925000, 1950000, 1975000, 2000000, }; -static const int ldo23_voltage_map[] = { - 1800, 1900, 2000, 2100, 2200, 2300, 2400, 2500, - 2600, 2700, 2800, 2900, 3000, 3100, 3200, 3300, +static const unsigned int ldo23_voltage_map[] = { + 1800000, 1900000, 2000000, 2100000, 2200000, 2300000, 2400000, 2500000, + 2600000, 2700000, 2800000, 2900000, 3000000, 3100000, 3200000, 3300000, }; -static const int ldo4_voltage_map[] = { - 1000, 1050, 1100, 1150, 1200, 1250, 1300, 1350, - 1400, 1500, 1800, 1900, 2500, 2800, 3000, 3300, +static const unsigned int ldo4_voltage_map[] = { + 1000000, 1050000, 1100000, 1150000, 1200000, 1250000, 1300000, 1350000, + 1400000, 1500000, 1800000, 1900000, 2500000, 2800000, 3000000, 3300000, }; -static const int ldo5_voltage_map[] = { - 0, 0, 0, 0, 0, 850, 875, 900, - 925, 950, 975, 1000, 1025, 1050, 1075, 1100, - 1125, 1150, 1175, 1200, 1225, 1250, 1275, 1300, - 1325, 1350, 1375, 1400, 1425, 1450, 1475, 1500, +static const unsigned int ldo5_voltage_map[] = { + 0, 0, 0, 0, 0, 850000, 875000, 900000, + 925000, 950000, 975000, 1000000, 1025000, 1050000, 1075000, 1100000, + 1125000, 1150000, 1175000, 1200000, 1225000, 1250000, 1275000, 1300000, + 1325000, 1350000, 1375000, 1400000, 1425000, 1450000, 1475000, 1500000, }; -static const int buck1_voltage_map[] = { - 725, 750, 775, 800, 825, 850, 875, 900, - 925, 950, 975, 1000, 1025, 1050, 1075, 1100, - 1125, 1150, 1175, 1200, 1225, 1250, 1275, 1300, - 1325, 1350, 1375, 1400, 1425, 1450, 1475, 1500, +static const unsigned int buck1_voltage_map[] = { + 725000, 750000, 775000, 800000, 825000, 850000, 875000, 900000, + 925000, 950000, 975000, 1000000, 1025000, 1050000, 1075000, 1100000, + 1125000, 1150000, 1175000, 1200000, 1225000, 1250000, 1275000, 1300000, + 1325000, 1350000, 1375000, 1400000, 1425000, 1450000, 1475000, 1500000, }; -static const int buck23_voltage_map[] = { - 0, 800, 850, 900, 950, 1000, 1050, 1100, - 1150, 1200, 1250, 1300, 1350, 1400, 1450, 1500, - 1550, 1600, 1650, 1700, 1800, 1900, 2500, 2800, - 3000, 3300, -}; - -static const int *ldo_voltage_map[] = { - ldo1_voltage_map, - ldo23_voltage_map, - ldo23_voltage_map, - ldo4_voltage_map, - ldo5_voltage_map, -}; - -static const int *buck_voltage_map[] = { - buck1_voltage_map, - buck23_voltage_map, - buck23_voltage_map, +static const unsigned int buck23_voltage_map[] = { + 0, 800000, 850000, 900000, 950000, 1000000, 1050000, 1100000, + 1150000, 1200000, 1250000, 1300000, 1350000, 1400000, 1450000, 1500000, + 1550000, 1600000, 1650000, 1700000, 1800000, 1900000, 2500000, 2800000, + 3000000, 3300000, }; static const int ldo_output_enable_mask[] = { @@ -160,7 +146,6 @@ static const int buck_base_addr[] = { LP3972_B3TV_REG, }; -#define LP3972_LDO_VOL_VALUE_MAP(x) (ldo_voltage_map[x]) #define LP3972_LDO_OUTPUT_ENABLE_MASK(x) (ldo_output_enable_mask[x]) #define LP3972_LDO_OUTPUT_ENABLE_REG(x) (ldo_output_enable_addr[x]) @@ -177,7 +162,6 @@ static const int buck_base_addr[] = { #define LP3972_LDO_VOL_MIN_IDX(x) (((x) == 4) ? 0x05 : 0x00) #define LP3972_LDO_VOL_MAX_IDX(x) ((x) ? (((x) == 4) ? 0x1f : 0x0f) : 0x0c) -#define LP3972_BUCK_VOL_VALUE_MAP(x) (buck_voltage_map[x]) #define LP3972_BUCK_VOL_ENABLE_REG(x) (buck_vol_enable_addr[x]) #define LP3972_BUCK_VOL1_REG(x) (buck_base_addr[x]) #define LP3972_BUCK_VOL_MASK 0x1f @@ -242,17 +226,6 @@ static int lp3972_set_bits(struct lp3972 *lp3972, u8 reg, u16 mask, u16 val) return ret; } -static int lp3972_ldo_list_voltage(struct regulator_dev *dev, unsigned index) -{ - int ldo = rdev_get_id(dev) - LP3972_LDO1; - - if (index < LP3972_LDO_VOL_MIN_IDX(ldo) || - index > LP3972_LDO_VOL_MAX_IDX(ldo)) - return -EINVAL; - - return 1000 * LP3972_LDO_VOL_VALUE_MAP(ldo)[index]; -} - static int lp3972_ldo_is_enabled(struct regulator_dev *dev) { struct lp3972 *lp3972 = rdev_get_drvdata(dev); @@ -294,7 +267,7 @@ static int lp3972_ldo_get_voltage(struct regulator_dev *dev) reg = lp3972_reg_read(lp3972, LP3972_LDO_VOL_CONTR_REG(ldo)); val = (reg >> LP3972_LDO_VOL_CONTR_SHIFT(ldo)) & mask; - return 1000 * LP3972_LDO_VOL_VALUE_MAP(ldo)[val]; + return dev->desc->volt_table[val]; } static int lp3972_ldo_set_voltage_sel(struct regulator_dev *dev, @@ -337,7 +310,7 @@ static int lp3972_ldo_set_voltage_sel(struct regulator_dev *dev, } static struct regulator_ops lp3972_ldo_ops = { - .list_voltage = lp3972_ldo_list_voltage, + .list_voltage = regulator_list_voltage_table, .is_enabled = lp3972_ldo_is_enabled, .enable = lp3972_ldo_enable, .disable = lp3972_ldo_disable, @@ -345,17 +318,6 @@ static struct regulator_ops lp3972_ldo_ops = { .set_voltage_sel = lp3972_ldo_set_voltage_sel, }; -static int lp3972_dcdc_list_voltage(struct regulator_dev *dev, unsigned index) -{ - int buck = rdev_get_id(dev) - LP3972_DCDC1; - - if (index < LP3972_BUCK_VOL_MIN_IDX(buck) || - index > LP3972_BUCK_VOL_MAX_IDX(buck)) - return -EINVAL; - - return 1000 * buck_voltage_map[buck][index]; -} - static int lp3972_dcdc_is_enabled(struct regulator_dev *dev) { struct lp3972 *lp3972 = rdev_get_drvdata(dev); @@ -401,7 +363,7 @@ static int lp3972_dcdc_get_voltage(struct regulator_dev *dev) reg = lp3972_reg_read(lp3972, LP3972_BUCK_VOL1_REG(buck)); reg &= LP3972_BUCK_VOL_MASK; if (reg <= LP3972_BUCK_VOL_MAX_IDX(buck)) - val = 1000 * buck_voltage_map[buck][reg]; + val = dev->desc->volt_table[reg]; else { val = 0; dev_warn(&dev->dev, "chip reported incorrect voltage value." @@ -436,7 +398,7 @@ static int lp3972_dcdc_set_voltage_sel(struct regulator_dev *dev, } static struct regulator_ops lp3972_dcdc_ops = { - .list_voltage = lp3972_dcdc_list_voltage, + .list_voltage = regulator_list_voltage_table, .is_enabled = lp3972_dcdc_is_enabled, .enable = lp3972_dcdc_enable, .disable = lp3972_dcdc_disable, @@ -450,6 +412,7 @@ static const struct regulator_desc regulators[] = { .id = LP3972_LDO1, .ops = &lp3972_ldo_ops, .n_voltages = ARRAY_SIZE(ldo1_voltage_map), + .volt_table = ldo1_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, @@ -458,6 +421,7 @@ static const struct regulator_desc regulators[] = { .id = LP3972_LDO2, .ops = &lp3972_ldo_ops, .n_voltages = ARRAY_SIZE(ldo23_voltage_map), + .volt_table = ldo23_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, @@ -466,6 +430,7 @@ static const struct regulator_desc regulators[] = { .id = LP3972_LDO3, .ops = &lp3972_ldo_ops, .n_voltages = ARRAY_SIZE(ldo23_voltage_map), + .volt_table = ldo23_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, @@ -474,6 +439,7 @@ static const struct regulator_desc regulators[] = { .id = LP3972_LDO4, .ops = &lp3972_ldo_ops, .n_voltages = ARRAY_SIZE(ldo4_voltage_map), + .volt_table = ldo4_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, @@ -482,6 +448,7 @@ static const struct regulator_desc regulators[] = { .id = LP3972_LDO5, .ops = &lp3972_ldo_ops, .n_voltages = ARRAY_SIZE(ldo5_voltage_map), + .volt_table = ldo5_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, @@ -490,6 +457,7 @@ static const struct regulator_desc regulators[] = { .id = LP3972_DCDC1, .ops = &lp3972_dcdc_ops, .n_voltages = ARRAY_SIZE(buck1_voltage_map), + .volt_table = buck1_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, @@ -498,6 +466,7 @@ static const struct regulator_desc regulators[] = { .id = LP3972_DCDC2, .ops = &lp3972_dcdc_ops, .n_voltages = ARRAY_SIZE(buck23_voltage_map), + .volt_table = buck23_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, @@ -506,6 +475,7 @@ static const struct regulator_desc regulators[] = { .id = LP3972_DCDC3, .ops = &lp3972_dcdc_ops, .n_voltages = ARRAY_SIZE(buck23_voltage_map), + .volt_table = buck23_voltage_map, .type = REGULATOR_VOLTAGE, .owner = THIS_MODULE, }, diff --git a/drivers/regulator/lp872x.c b/drivers/regulator/lp872x.c new file mode 100644 index 000000000000..212c38eaba70 --- /dev/null +++ b/drivers/regulator/lp872x.c @@ -0,0 +1,943 @@ +/* + * Copyright 2012 Texas Instruments + * + * Author: Milo(Woogyom) Kim <milo.kim@ti.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/i2c.h> +#include <linux/regmap.h> +#include <linux/err.h> +#include <linux/gpio.h> +#include <linux/regulator/lp872x.h> +#include <linux/regulator/driver.h> +#include <linux/platform_device.h> + +/* Registers : LP8720/8725 shared */ +#define LP872X_GENERAL_CFG 0x00 +#define LP872X_LDO1_VOUT 0x01 +#define LP872X_LDO2_VOUT 0x02 +#define LP872X_LDO3_VOUT 0x03 +#define LP872X_LDO4_VOUT 0x04 +#define LP872X_LDO5_VOUT 0x05 + +/* Registers : LP8720 */ +#define LP8720_BUCK_VOUT1 0x06 +#define LP8720_BUCK_VOUT2 0x07 +#define LP8720_ENABLE 0x08 + +/* Registers : LP8725 */ +#define LP8725_LILO1_VOUT 0x06 +#define LP8725_LILO2_VOUT 0x07 +#define LP8725_BUCK1_VOUT1 0x08 +#define LP8725_BUCK1_VOUT2 0x09 +#define LP8725_BUCK2_VOUT1 0x0A +#define LP8725_BUCK2_VOUT2 0x0B +#define LP8725_BUCK_CTRL 0x0C +#define LP8725_LDO_CTRL 0x0D + +/* Mask/shift : LP8720/LP8725 shared */ +#define LP872X_VOUT_M 0x1F +#define LP872X_START_DELAY_M 0xE0 +#define LP872X_START_DELAY_S 5 +#define LP872X_EN_LDO1_M BIT(0) +#define LP872X_EN_LDO2_M BIT(1) +#define LP872X_EN_LDO3_M BIT(2) +#define LP872X_EN_LDO4_M BIT(3) +#define LP872X_EN_LDO5_M BIT(4) + +/* Mask/shift : LP8720 */ +#define LP8720_TIMESTEP_S 0 /* Addr 00h */ +#define LP8720_TIMESTEP_M BIT(0) +#define LP8720_EXT_DVS_M BIT(2) +#define LP8720_BUCK_FPWM_S 5 /* Addr 07h */ +#define LP8720_BUCK_FPWM_M BIT(5) +#define LP8720_EN_BUCK_M BIT(5) /* Addr 08h */ +#define LP8720_DVS_SEL_M BIT(7) + +/* Mask/shift : LP8725 */ +#define LP8725_TIMESTEP_M 0xC0 /* Addr 00h */ +#define LP8725_TIMESTEP_S 6 +#define LP8725_BUCK1_EN_M BIT(0) +#define LP8725_DVS1_M BIT(2) +#define LP8725_DVS2_M BIT(3) +#define LP8725_BUCK2_EN_M BIT(4) +#define LP8725_BUCK_CL_M 0xC0 /* Addr 09h, 0Bh */ +#define LP8725_BUCK_CL_S 6 +#define LP8725_BUCK1_FPWM_S 1 /* Addr 0Ch */ +#define LP8725_BUCK1_FPWM_M BIT(1) +#define LP8725_BUCK2_FPWM_S 5 +#define LP8725_BUCK2_FPWM_M BIT(5) +#define LP8725_EN_LILO1_M BIT(5) /* Addr 0Dh */ +#define LP8725_EN_LILO2_M BIT(6) + +/* PWM mode */ +#define LP872X_FORCE_PWM 1 +#define LP872X_AUTO_PWM 0 + +#define LP8720_NUM_REGULATORS 6 +#define LP8725_NUM_REGULATORS 9 +#define EXTERN_DVS_USED 0 +#define MAX_DELAY 6 + +/* dump registers in regmap-debugfs */ +#define MAX_REGISTERS 0x0F + +enum lp872x_id { + LP8720, + LP8725, +}; + +struct lp872x { + struct regmap *regmap; + struct device *dev; + enum lp872x_id chipid; + struct lp872x_platform_data *pdata; + struct regulator_dev **regulators; + int num_regulators; + enum lp872x_dvs_state dvs_pin; + int dvs_gpio; +}; + +/* LP8720/LP8725 shared voltage table for LDOs */ +static const unsigned int lp872x_ldo_vtbl[] = { + 1200000, 1250000, 1300000, 1350000, 1400000, 1450000, 1500000, 1550000, + 1600000, 1650000, 1700000, 1750000, 1800000, 1850000, 1900000, 2000000, + 2100000, 2200000, 2300000, 2400000, 2500000, 2600000, 2650000, 2700000, + 2750000, 2800000, 2850000, 2900000, 2950000, 3000000, 3100000, 3300000, +}; + +/* LP8720 LDO4 voltage table */ +static const unsigned int lp8720_ldo4_vtbl[] = { + 800000, 850000, 900000, 1000000, 1100000, 1200000, 1250000, 1300000, + 1350000, 1400000, 1450000, 1500000, 1550000, 1600000, 1650000, 1700000, + 1750000, 1800000, 1850000, 1900000, 2000000, 2100000, 2200000, 2300000, + 2400000, 2500000, 2600000, 2650000, 2700000, 2750000, 2800000, 2850000, +}; + +/* LP8725 LILO(Low Input Low Output) voltage table */ +static const unsigned int lp8725_lilo_vtbl[] = { + 800000, 850000, 900000, 950000, 1000000, 1050000, 1100000, 1150000, + 1200000, 1250000, 1300000, 1350000, 1400000, 1500000, 1600000, 1700000, + 1800000, 1900000, 2000000, 2100000, 2200000, 2300000, 2400000, 2500000, + 2600000, 2700000, 2800000, 2850000, 2900000, 3000000, 3100000, 3300000, +}; + +/* LP8720 BUCK voltage table */ +#define EXT_R 0 /* external resistor divider */ +static const unsigned int lp8720_buck_vtbl[] = { + EXT_R, 800000, 850000, 900000, 950000, 1000000, 1050000, 1100000, + 1150000, 1200000, 1250000, 1300000, 1350000, 1400000, 1450000, 1500000, + 1550000, 1600000, 1650000, 1700000, 1750000, 1800000, 1850000, 1900000, + 1950000, 2000000, 2050000, 2100000, 2150000, 2200000, 2250000, 2300000, +}; + +/* LP8725 BUCK voltage table */ +static const unsigned int lp8725_buck_vtbl[] = { + 800000, 850000, 900000, 950000, 1000000, 1050000, 1100000, 1150000, + 1200000, 1250000, 1300000, 1350000, 1400000, 1500000, 1600000, 1700000, + 1750000, 1800000, 1850000, 1900000, 2000000, 2100000, 2200000, 2300000, + 2400000, 2500000, 2600000, 2700000, 2800000, 2850000, 2900000, 3000000, +}; + +/* LP8725 BUCK current limit */ +static const unsigned int lp8725_buck_uA[] = { + 460000, 780000, 1050000, 1370000, +}; + +static int lp872x_read_byte(struct lp872x *lp, u8 addr, u8 *data) +{ + int ret; + unsigned int val; + + ret = regmap_read(lp->regmap, addr, &val); + if (ret < 0) { + dev_err(lp->dev, "failed to read 0x%.2x\n", addr); + return ret; + } + + *data = (u8)val; + return 0; +} + +static inline int lp872x_write_byte(struct lp872x *lp, u8 addr, u8 data) +{ + return regmap_write(lp->regmap, addr, data); +} + +static inline int lp872x_update_bits(struct lp872x *lp, u8 addr, + unsigned int mask, u8 data) +{ + return regmap_update_bits(lp->regmap, addr, mask, data); +} + +static int _rdev_to_offset(struct regulator_dev *rdev) +{ + enum lp872x_regulator_id id = rdev_get_id(rdev); + + switch (id) { + case LP8720_ID_LDO1 ... LP8720_ID_BUCK: + return id; + case LP8725_ID_LDO1 ... LP8725_ID_BUCK2: + return id - LP8725_ID_BASE; + default: + return -EINVAL; + } +} + +static int lp872x_get_timestep_usec(struct lp872x *lp) +{ + enum lp872x_id chip = lp->chipid; + u8 val, mask, shift; + int *time_usec, size, ret; + int lp8720_time_usec[] = { 25, 50 }; + int lp8725_time_usec[] = { 32, 64, 128, 256 }; + + switch (chip) { + case LP8720: + mask = LP8720_TIMESTEP_M; + shift = LP8720_TIMESTEP_S; + time_usec = &lp8720_time_usec[0]; + size = ARRAY_SIZE(lp8720_time_usec); + break; + case LP8725: + mask = LP8725_TIMESTEP_M; + shift = LP8725_TIMESTEP_S; + time_usec = &lp8725_time_usec[0]; + size = ARRAY_SIZE(lp8725_time_usec); + break; + default: + return -EINVAL; + } + + ret = lp872x_read_byte(lp, LP872X_GENERAL_CFG, &val); + if (ret) + return -EINVAL; + + val = (val & mask) >> shift; + if (val >= size) + return -EINVAL; + + return *(time_usec + val); +} + +static int lp872x_regulator_enable_time(struct regulator_dev *rdev) +{ + struct lp872x *lp = rdev_get_drvdata(rdev); + enum lp872x_regulator_id regulator = rdev_get_id(rdev); + int time_step_us = lp872x_get_timestep_usec(lp); + int ret, offset; + u8 addr, val; + + if (time_step_us < 0) + return -EINVAL; + + switch (regulator) { + case LP8720_ID_LDO1 ... LP8720_ID_LDO5: + case LP8725_ID_LDO1 ... LP8725_ID_LILO2: + offset = _rdev_to_offset(rdev); + if (offset < 0) + return -EINVAL; + + addr = LP872X_LDO1_VOUT + offset; + break; + case LP8720_ID_BUCK: + addr = LP8720_BUCK_VOUT1; + break; + case LP8725_ID_BUCK1: + addr = LP8725_BUCK1_VOUT1; + break; + case LP8725_ID_BUCK2: + addr = LP8725_BUCK2_VOUT1; + break; + default: + return -EINVAL; + } + + ret = lp872x_read_byte(lp, addr, &val); + if (ret) + return ret; + + val = (val & LP872X_START_DELAY_M) >> LP872X_START_DELAY_S; + + return val > MAX_DELAY ? 0 : val * time_step_us; +} + +static void lp872x_set_dvs(struct lp872x *lp, int gpio) +{ + enum lp872x_dvs_sel dvs_sel = lp->pdata->dvs->vsel; + enum lp872x_dvs_state state; + + state = dvs_sel == SEL_V1 ? DVS_HIGH : DVS_LOW; + gpio_set_value(gpio, state); + lp->dvs_pin = state; +} + +static u8 lp872x_select_buck_vout_addr(struct lp872x *lp, + enum lp872x_regulator_id buck) +{ + u8 val, addr; + + if (lp872x_read_byte(lp, LP872X_GENERAL_CFG, &val)) + return 0; + + switch (buck) { + case LP8720_ID_BUCK: + if (val & LP8720_EXT_DVS_M) { + addr = (lp->dvs_pin == DVS_HIGH) ? + LP8720_BUCK_VOUT1 : LP8720_BUCK_VOUT2; + } else { + if (lp872x_read_byte(lp, LP8720_ENABLE, &val)) + return 0; + + addr = val & LP8720_DVS_SEL_M ? + LP8720_BUCK_VOUT1 : LP8720_BUCK_VOUT2; + } + break; + case LP8725_ID_BUCK1: + if (val & LP8725_DVS1_M) + addr = LP8725_BUCK1_VOUT1; + else + addr = (lp->dvs_pin == DVS_HIGH) ? + LP8725_BUCK1_VOUT1 : LP8725_BUCK1_VOUT2; + break; + case LP8725_ID_BUCK2: + addr = val & LP8725_DVS2_M ? + LP8725_BUCK2_VOUT1 : LP8725_BUCK2_VOUT2; + break; + default: + return 0; + } + + return addr; +} + +static bool lp872x_is_valid_buck_addr(u8 addr) +{ + switch (addr) { + case LP8720_BUCK_VOUT1: + case LP8720_BUCK_VOUT2: + case LP8725_BUCK1_VOUT1: + case LP8725_BUCK1_VOUT2: + case LP8725_BUCK2_VOUT1: + case LP8725_BUCK2_VOUT2: + return true; + default: + return false; + } +} + +static int lp872x_buck_set_voltage_sel(struct regulator_dev *rdev, + unsigned selector) +{ + struct lp872x *lp = rdev_get_drvdata(rdev); + enum lp872x_regulator_id buck = rdev_get_id(rdev); + u8 addr, mask = LP872X_VOUT_M; + struct lp872x_dvs *dvs = lp->pdata->dvs; + + if (dvs && gpio_is_valid(dvs->gpio)) + lp872x_set_dvs(lp, dvs->gpio); + + addr = lp872x_select_buck_vout_addr(lp, buck); + if (!lp872x_is_valid_buck_addr(addr)) + return -EINVAL; + + return lp872x_update_bits(lp, addr, mask, selector); +} + +static int lp872x_buck_get_voltage_sel(struct regulator_dev *rdev) +{ + struct lp872x *lp = rdev_get_drvdata(rdev); + enum lp872x_regulator_id buck = rdev_get_id(rdev); + u8 addr, val; + int ret; + + addr = lp872x_select_buck_vout_addr(lp, buck); + if (!lp872x_is_valid_buck_addr(addr)) + return -EINVAL; + + ret = lp872x_read_byte(lp, addr, &val); + if (ret) + return ret; + + return val & LP872X_VOUT_M; +} + +static int lp8725_buck_set_current_limit(struct regulator_dev *rdev, + int min_uA, int max_uA) +{ + struct lp872x *lp = rdev_get_drvdata(rdev); + enum lp872x_regulator_id buck = rdev_get_id(rdev); + int i, max = ARRAY_SIZE(lp8725_buck_uA); + u8 addr, val; + + switch (buck) { + case LP8725_ID_BUCK1: + addr = LP8725_BUCK1_VOUT2; + break; + case LP8725_ID_BUCK2: + addr = LP8725_BUCK2_VOUT2; + break; + default: + return -EINVAL; + } + + for (i = 0 ; i < max ; i++) + if (lp8725_buck_uA[i] >= min_uA && + lp8725_buck_uA[i] <= max_uA) + break; + + if (i == max) + return -EINVAL; + + val = i << LP8725_BUCK_CL_S; + + return lp872x_update_bits(lp, addr, LP8725_BUCK_CL_M, val); +} + +static int lp8725_buck_get_current_limit(struct regulator_dev *rdev) +{ + struct lp872x *lp = rdev_get_drvdata(rdev); + enum lp872x_regulator_id buck = rdev_get_id(rdev); + u8 addr, val; + int ret; + + switch (buck) { + case LP8725_ID_BUCK1: + addr = LP8725_BUCK1_VOUT2; + break; + case LP8725_ID_BUCK2: + addr = LP8725_BUCK2_VOUT2; + break; + default: + return -EINVAL; + } + + ret = lp872x_read_byte(lp, addr, &val); + if (ret) + return ret; + + val = (val & LP8725_BUCK_CL_M) >> LP8725_BUCK_CL_S; + + return (val < ARRAY_SIZE(lp8725_buck_uA)) ? + lp8725_buck_uA[val] : -EINVAL; +} + +static int lp872x_buck_set_mode(struct regulator_dev *rdev, unsigned int mode) +{ + struct lp872x *lp = rdev_get_drvdata(rdev); + enum lp872x_regulator_id buck = rdev_get_id(rdev); + u8 addr, mask, shift, val; + + switch (buck) { + case LP8720_ID_BUCK: + addr = LP8720_BUCK_VOUT2; + mask = LP8720_BUCK_FPWM_M; + shift = LP8720_BUCK_FPWM_S; + break; + case LP8725_ID_BUCK1: + addr = LP8725_BUCK_CTRL; + mask = LP8725_BUCK1_FPWM_M; + shift = LP8725_BUCK1_FPWM_S; + break; + case LP8725_ID_BUCK2: + addr = LP8725_BUCK_CTRL; + mask = LP8725_BUCK2_FPWM_M; + shift = LP8725_BUCK2_FPWM_S; + break; + default: + return -EINVAL; + } + + if (mode == REGULATOR_MODE_FAST) + val = LP872X_FORCE_PWM << shift; + else if (mode == REGULATOR_MODE_NORMAL) + val = LP872X_AUTO_PWM << shift; + else + return -EINVAL; + + return lp872x_update_bits(lp, addr, mask, val); +} + +static unsigned int lp872x_buck_get_mode(struct regulator_dev *rdev) +{ + struct lp872x *lp = rdev_get_drvdata(rdev); + enum lp872x_regulator_id buck = rdev_get_id(rdev); + u8 addr, mask, val; + int ret; + + switch (buck) { + case LP8720_ID_BUCK: + addr = LP8720_BUCK_VOUT2; + mask = LP8720_BUCK_FPWM_M; + break; + case LP8725_ID_BUCK1: + addr = LP8725_BUCK_CTRL; + mask = LP8725_BUCK1_FPWM_M; + break; + case LP8725_ID_BUCK2: + addr = LP8725_BUCK_CTRL; + mask = LP8725_BUCK2_FPWM_M; + break; + default: + return -EINVAL; + } + + ret = lp872x_read_byte(lp, addr, &val); + if (ret) + return ret; + + return val & mask ? REGULATOR_MODE_FAST : REGULATOR_MODE_NORMAL; +} + +static struct regulator_ops lp872x_ldo_ops = { + .list_voltage = regulator_list_voltage_table, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .enable_time = lp872x_regulator_enable_time, +}; + +static struct regulator_ops lp8720_buck_ops = { + .list_voltage = regulator_list_voltage_table, + .set_voltage_sel = lp872x_buck_set_voltage_sel, + .get_voltage_sel = lp872x_buck_get_voltage_sel, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .enable_time = lp872x_regulator_enable_time, + .set_mode = lp872x_buck_set_mode, + .get_mode = lp872x_buck_get_mode, +}; + +static struct regulator_ops lp8725_buck_ops = { + .list_voltage = regulator_list_voltage_table, + .set_voltage_sel = lp872x_buck_set_voltage_sel, + .get_voltage_sel = lp872x_buck_get_voltage_sel, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .enable_time = lp872x_regulator_enable_time, + .set_mode = lp872x_buck_set_mode, + .get_mode = lp872x_buck_get_mode, + .set_current_limit = lp8725_buck_set_current_limit, + .get_current_limit = lp8725_buck_get_current_limit, +}; + +static struct regulator_desc lp8720_regulator_desc[] = { + { + .name = "ldo1", + .id = LP8720_ID_LDO1, + .ops = &lp872x_ldo_ops, + .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), + .volt_table = lp872x_ldo_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP872X_LDO1_VOUT, + .vsel_mask = LP872X_VOUT_M, + .enable_reg = LP8720_ENABLE, + .enable_mask = LP872X_EN_LDO1_M, + }, + { + .name = "ldo2", + .id = LP8720_ID_LDO2, + .ops = &lp872x_ldo_ops, + .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), + .volt_table = lp872x_ldo_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP872X_LDO2_VOUT, + .vsel_mask = LP872X_VOUT_M, + .enable_reg = LP8720_ENABLE, + .enable_mask = LP872X_EN_LDO2_M, + }, + { + .name = "ldo3", + .id = LP8720_ID_LDO3, + .ops = &lp872x_ldo_ops, + .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), + .volt_table = lp872x_ldo_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP872X_LDO3_VOUT, + .vsel_mask = LP872X_VOUT_M, + .enable_reg = LP8720_ENABLE, + .enable_mask = LP872X_EN_LDO3_M, + }, + { + .name = "ldo4", + .id = LP8720_ID_LDO4, + .ops = &lp872x_ldo_ops, + .n_voltages = ARRAY_SIZE(lp8720_ldo4_vtbl), + .volt_table = lp8720_ldo4_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP872X_LDO4_VOUT, + .vsel_mask = LP872X_VOUT_M, + .enable_reg = LP8720_ENABLE, + .enable_mask = LP872X_EN_LDO4_M, + }, + { + .name = "ldo5", + .id = LP8720_ID_LDO5, + .ops = &lp872x_ldo_ops, + .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), + .volt_table = lp872x_ldo_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP872X_LDO5_VOUT, + .vsel_mask = LP872X_VOUT_M, + .enable_reg = LP8720_ENABLE, + .enable_mask = LP872X_EN_LDO5_M, + }, + { + .name = "buck", + .id = LP8720_ID_BUCK, + .ops = &lp8720_buck_ops, + .n_voltages = ARRAY_SIZE(lp8720_buck_vtbl), + .volt_table = lp8720_buck_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .enable_reg = LP8720_ENABLE, + .enable_mask = LP8720_EN_BUCK_M, + }, +}; + +static struct regulator_desc lp8725_regulator_desc[] = { + { + .name = "ldo1", + .id = LP8725_ID_LDO1, + .ops = &lp872x_ldo_ops, + .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), + .volt_table = lp872x_ldo_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP872X_LDO1_VOUT, + .vsel_mask = LP872X_VOUT_M, + .enable_reg = LP8725_LDO_CTRL, + .enable_mask = LP872X_EN_LDO1_M, + }, + { + .name = "ldo2", + .id = LP8725_ID_LDO2, + .ops = &lp872x_ldo_ops, + .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), + .volt_table = lp872x_ldo_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP872X_LDO2_VOUT, + .vsel_mask = LP872X_VOUT_M, + .enable_reg = LP8725_LDO_CTRL, + .enable_mask = LP872X_EN_LDO2_M, + }, + { + .name = "ldo3", + .id = LP8725_ID_LDO3, + .ops = &lp872x_ldo_ops, + .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), + .volt_table = lp872x_ldo_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP872X_LDO3_VOUT, + .vsel_mask = LP872X_VOUT_M, + .enable_reg = LP8725_LDO_CTRL, + .enable_mask = LP872X_EN_LDO3_M, + }, + { + .name = "ldo4", + .id = LP8725_ID_LDO4, + .ops = &lp872x_ldo_ops, + .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), + .volt_table = lp872x_ldo_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP872X_LDO4_VOUT, + .vsel_mask = LP872X_VOUT_M, + .enable_reg = LP8725_LDO_CTRL, + .enable_mask = LP872X_EN_LDO4_M, + }, + { + .name = "ldo5", + .id = LP8725_ID_LDO5, + .ops = &lp872x_ldo_ops, + .n_voltages = ARRAY_SIZE(lp872x_ldo_vtbl), + .volt_table = lp872x_ldo_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP872X_LDO5_VOUT, + .vsel_mask = LP872X_VOUT_M, + .enable_reg = LP8725_LDO_CTRL, + .enable_mask = LP872X_EN_LDO5_M, + }, + { + .name = "lilo1", + .id = LP8725_ID_LILO1, + .ops = &lp872x_ldo_ops, + .n_voltages = ARRAY_SIZE(lp8725_lilo_vtbl), + .volt_table = lp8725_lilo_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8725_LILO1_VOUT, + .vsel_mask = LP872X_VOUT_M, + .enable_reg = LP8725_LDO_CTRL, + .enable_mask = LP8725_EN_LILO1_M, + }, + { + .name = "lilo2", + .id = LP8725_ID_LILO2, + .ops = &lp872x_ldo_ops, + .n_voltages = ARRAY_SIZE(lp8725_lilo_vtbl), + .volt_table = lp8725_lilo_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8725_LILO2_VOUT, + .vsel_mask = LP872X_VOUT_M, + .enable_reg = LP8725_LDO_CTRL, + .enable_mask = LP8725_EN_LILO2_M, + }, + { + .name = "buck1", + .id = LP8725_ID_BUCK1, + .ops = &lp8725_buck_ops, + .n_voltages = ARRAY_SIZE(lp8725_buck_vtbl), + .volt_table = lp8725_buck_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .enable_reg = LP872X_GENERAL_CFG, + .enable_mask = LP8725_BUCK1_EN_M, + }, + { + .name = "buck2", + .id = LP8725_ID_BUCK2, + .ops = &lp8725_buck_ops, + .n_voltages = ARRAY_SIZE(lp8725_buck_vtbl), + .volt_table = lp8725_buck_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .enable_reg = LP872X_GENERAL_CFG, + .enable_mask = LP8725_BUCK2_EN_M, + }, +}; + +static int lp872x_check_dvs_validity(struct lp872x *lp) +{ + struct lp872x_dvs *dvs = lp->pdata->dvs; + u8 val = 0; + int ret; + + ret = lp872x_read_byte(lp, LP872X_GENERAL_CFG, &val); + if (ret) + return ret; + + ret = 0; + if (lp->chipid == LP8720) { + if (val & LP8720_EXT_DVS_M) + ret = dvs ? 0 : -EINVAL; + } else { + if ((val & LP8725_DVS1_M) == EXTERN_DVS_USED) + ret = dvs ? 0 : -EINVAL; + } + + return ret; +} + +static int lp872x_init_dvs(struct lp872x *lp) +{ + int ret, gpio; + struct lp872x_dvs *dvs = lp->pdata->dvs; + enum lp872x_dvs_state pinstate; + + ret = lp872x_check_dvs_validity(lp); + if (ret) { + dev_warn(lp->dev, "invalid dvs data: %d\n", ret); + return ret; + } + + gpio = dvs->gpio; + if (!gpio_is_valid(gpio)) { + dev_err(lp->dev, "invalid gpio: %d\n", gpio); + return -EINVAL; + } + + pinstate = dvs->init_state; + ret = devm_gpio_request_one(lp->dev, gpio, pinstate, "LP872X DVS"); + if (ret) { + dev_err(lp->dev, "gpio request err: %d\n", ret); + return ret; + } + + lp->dvs_pin = pinstate; + lp->dvs_gpio = gpio; + + return 0; +} + +static int lp872x_config(struct lp872x *lp) +{ + struct lp872x_platform_data *pdata = lp->pdata; + int ret; + + if (!pdata->update_config) + return 0; + + ret = lp872x_write_byte(lp, LP872X_GENERAL_CFG, pdata->general_config); + if (ret) + return ret; + + return lp872x_init_dvs(lp); +} + +static struct regulator_init_data +*lp872x_find_regulator_init_data(int id, struct lp872x *lp) +{ + int i; + + for (i = 0; i < lp->num_regulators; i++) { + if (lp->pdata->regulator_data[i].id == id) + return lp->pdata->regulator_data[i].init_data; + } + + return NULL; +} + +static int lp872x_regulator_register(struct lp872x *lp) +{ + struct regulator_desc *desc; + struct regulator_config cfg = { }; + struct regulator_dev *rdev; + int i, ret; + + for (i = 0 ; i < lp->num_regulators ; i++) { + desc = (lp->chipid == LP8720) ? &lp8720_regulator_desc[i] : + &lp8725_regulator_desc[i]; + + cfg.dev = lp->dev; + cfg.init_data = lp872x_find_regulator_init_data(desc->id, lp); + cfg.driver_data = lp; + cfg.regmap = lp->regmap; + + rdev = regulator_register(desc, &cfg); + if (IS_ERR(rdev)) { + dev_err(lp->dev, "regulator register err"); + ret = PTR_ERR(rdev); + goto err; + } + + *(lp->regulators + i) = rdev; + } + + return 0; +err: + while (--i >= 0) { + rdev = *(lp->regulators + i); + regulator_unregister(rdev); + } + return ret; +} + +static void lp872x_regulator_unregister(struct lp872x *lp) +{ + struct regulator_dev *rdev; + int i; + + for (i = 0 ; i < lp->num_regulators ; i++) { + rdev = *(lp->regulators + i); + regulator_unregister(rdev); + } +} + +static const struct regmap_config lp872x_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = MAX_REGISTERS, +}; + +static int lp872x_probe(struct i2c_client *cl, const struct i2c_device_id *id) +{ + struct lp872x *lp; + struct lp872x_platform_data *pdata = cl->dev.platform_data; + int ret, size, num_regulators; + const int lp872x_num_regulators[] = { + [LP8720] = LP8720_NUM_REGULATORS, + [LP8725] = LP8725_NUM_REGULATORS, + }; + + if (!pdata) { + dev_err(&cl->dev, "no platform data\n"); + return -EINVAL; + } + + lp = devm_kzalloc(&cl->dev, sizeof(struct lp872x), GFP_KERNEL); + if (!lp) + goto err_mem; + + num_regulators = lp872x_num_regulators[id->driver_data]; + size = sizeof(struct regulator_dev *) * num_regulators; + + lp->regulators = devm_kzalloc(&cl->dev, size, GFP_KERNEL); + if (!lp->regulators) + goto err_mem; + + lp->regmap = devm_regmap_init_i2c(cl, &lp872x_regmap_config); + if (IS_ERR(lp->regmap)) { + ret = PTR_ERR(lp->regmap); + dev_err(&cl->dev, "regmap init i2c err: %d\n", ret); + goto err_dev; + } + + lp->dev = &cl->dev; + lp->pdata = pdata; + lp->chipid = id->driver_data; + lp->num_regulators = num_regulators; + i2c_set_clientdata(cl, lp); + + ret = lp872x_config(lp); + if (ret) + goto err_dev; + + return lp872x_regulator_register(lp); + +err_mem: + return -ENOMEM; +err_dev: + return ret; +} + +static int __devexit lp872x_remove(struct i2c_client *cl) +{ + struct lp872x *lp = i2c_get_clientdata(cl); + + lp872x_regulator_unregister(lp); + return 0; +} + +static const struct i2c_device_id lp872x_ids[] = { + {"lp8720", LP8720}, + {"lp8725", LP8725}, + { } +}; +MODULE_DEVICE_TABLE(i2c, lp872x_ids); + +static struct i2c_driver lp872x_driver = { + .driver = { + .name = "lp872x", + .owner = THIS_MODULE, + }, + .probe = lp872x_probe, + .remove = __devexit_p(lp872x_remove), + .id_table = lp872x_ids, +}; + +module_i2c_driver(lp872x_driver); + +MODULE_DESCRIPTION("TI/National Semiconductor LP872x PMU Regulator Driver"); +MODULE_AUTHOR("Milo Kim"); +MODULE_LICENSE("GPL"); diff --git a/drivers/regulator/lp8788-buck.c b/drivers/regulator/lp8788-buck.c new file mode 100644 index 000000000000..6356e821400f --- /dev/null +++ b/drivers/regulator/lp8788-buck.c @@ -0,0 +1,629 @@ +/* + * TI LP8788 MFD - buck regulator driver + * + * Copyright 2012 Texas Instruments + * + * Author: Milo(Woogyom) Kim <milo.kim@ti.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/err.h> +#include <linux/platform_device.h> +#include <linux/regulator/driver.h> +#include <linux/mfd/lp8788.h> +#include <linux/gpio.h> + +/* register address */ +#define LP8788_EN_BUCK 0x0C +#define LP8788_BUCK_DVS_SEL 0x1D +#define LP8788_BUCK1_VOUT0 0x1E +#define LP8788_BUCK1_VOUT1 0x1F +#define LP8788_BUCK1_VOUT2 0x20 +#define LP8788_BUCK1_VOUT3 0x21 +#define LP8788_BUCK2_VOUT0 0x22 +#define LP8788_BUCK2_VOUT1 0x23 +#define LP8788_BUCK2_VOUT2 0x24 +#define LP8788_BUCK2_VOUT3 0x25 +#define LP8788_BUCK3_VOUT 0x26 +#define LP8788_BUCK4_VOUT 0x27 +#define LP8788_BUCK1_TIMESTEP 0x28 +#define LP8788_BUCK_PWM 0x2D + +/* mask/shift bits */ +#define LP8788_EN_BUCK1_M BIT(0) /* Addr 0Ch */ +#define LP8788_EN_BUCK2_M BIT(1) +#define LP8788_EN_BUCK3_M BIT(2) +#define LP8788_EN_BUCK4_M BIT(3) +#define LP8788_BUCK1_DVS_SEL_M 0x04 /* Addr 1Dh */ +#define LP8788_BUCK1_DVS_M 0x03 +#define LP8788_BUCK1_DVS_S 0 +#define LP8788_BUCK2_DVS_SEL_M 0x40 +#define LP8788_BUCK2_DVS_M 0x30 +#define LP8788_BUCK2_DVS_S 4 +#define LP8788_BUCK1_DVS_I2C BIT(2) +#define LP8788_BUCK2_DVS_I2C BIT(6) +#define LP8788_BUCK1_DVS_PIN (0 << 2) +#define LP8788_BUCK2_DVS_PIN (0 << 6) +#define LP8788_VOUT_M 0x1F /* Addr 1Eh ~ 27h */ +#define LP8788_STARTUP_TIME_M 0xF8 /* Addr 28h ~ 2Bh */ +#define LP8788_STARTUP_TIME_S 3 +#define LP8788_FPWM_BUCK1_M BIT(0) /* Addr 2Dh */ +#define LP8788_FPWM_BUCK1_S 0 +#define LP8788_FPWM_BUCK2_M BIT(1) +#define LP8788_FPWM_BUCK2_S 1 +#define LP8788_FPWM_BUCK3_M BIT(2) +#define LP8788_FPWM_BUCK3_S 2 +#define LP8788_FPWM_BUCK4_M BIT(3) +#define LP8788_FPWM_BUCK4_S 3 + +#define INVALID_ADDR 0xFF +#define LP8788_FORCE_PWM 1 +#define LP8788_AUTO_PWM 0 +#define PIN_LOW 0 +#define PIN_HIGH 1 +#define ENABLE_TIME_USEC 32 + +enum lp8788_dvs_state { + DVS_LOW = GPIOF_OUT_INIT_LOW, + DVS_HIGH = GPIOF_OUT_INIT_HIGH, +}; + +enum lp8788_dvs_mode { + REGISTER, + EXTPIN, +}; + +enum lp8788_buck_id { + BUCK1, + BUCK2, + BUCK3, + BUCK4, +}; + +struct lp8788_pwm_map { + u8 mask; + u8 shift; +}; + +struct lp8788_buck { + struct lp8788 *lp; + struct regulator_dev *regulator; + struct lp8788_pwm_map *pmap; + void *dvs; +}; + +/* BUCK 1 ~ 4 voltage table */ +static const int lp8788_buck_vtbl[] = { + 500000, 800000, 850000, 900000, 950000, 1000000, 1050000, 1100000, + 1150000, 1200000, 1250000, 1300000, 1350000, 1400000, 1450000, 1500000, + 1550000, 1600000, 1650000, 1700000, 1750000, 1800000, 1850000, 1900000, + 1950000, 2000000, +}; + +/* buck pwm mode selection : used for set/get_mode in regulator ops + * @forced pwm : fast mode + * @auto pwm : normal mode + */ +static struct lp8788_pwm_map buck_pmap[] = { + [BUCK1] = { + .mask = LP8788_FPWM_BUCK1_M, + .shift = LP8788_FPWM_BUCK1_S, + }, + [BUCK2] = { + .mask = LP8788_FPWM_BUCK2_M, + .shift = LP8788_FPWM_BUCK2_S, + }, + [BUCK3] = { + .mask = LP8788_FPWM_BUCK3_M, + .shift = LP8788_FPWM_BUCK3_S, + }, + [BUCK4] = { + .mask = LP8788_FPWM_BUCK4_M, + .shift = LP8788_FPWM_BUCK4_S, + }, +}; + +static const u8 buck1_vout_addr[] = { + LP8788_BUCK1_VOUT0, LP8788_BUCK1_VOUT1, + LP8788_BUCK1_VOUT2, LP8788_BUCK1_VOUT3, +}; + +static const u8 buck2_vout_addr[] = { + LP8788_BUCK2_VOUT0, LP8788_BUCK2_VOUT1, + LP8788_BUCK2_VOUT2, LP8788_BUCK2_VOUT3, +}; + +static void lp8788_buck1_set_dvs(struct lp8788_buck *buck) +{ + struct lp8788_buck1_dvs *dvs = (struct lp8788_buck1_dvs *)buck->dvs; + enum lp8788_dvs_state pinstate; + + if (!dvs) + return; + + pinstate = dvs->vsel == DVS_SEL_V0 ? DVS_LOW : DVS_HIGH; + if (gpio_is_valid(dvs->gpio)) + gpio_set_value(dvs->gpio, pinstate); +} + +static void lp8788_buck2_set_dvs(struct lp8788_buck *buck) +{ + struct lp8788_buck2_dvs *dvs = (struct lp8788_buck2_dvs *)buck->dvs; + enum lp8788_dvs_state pin1, pin2; + + if (!dvs) + return; + + switch (dvs->vsel) { + case DVS_SEL_V0: + pin1 = DVS_LOW; + pin2 = DVS_LOW; + break; + case DVS_SEL_V1: + pin1 = DVS_HIGH; + pin2 = DVS_LOW; + break; + case DVS_SEL_V2: + pin1 = DVS_LOW; + pin2 = DVS_HIGH; + break; + case DVS_SEL_V3: + pin1 = DVS_HIGH; + pin2 = DVS_HIGH; + break; + default: + return; + } + + if (gpio_is_valid(dvs->gpio[0])) + gpio_set_value(dvs->gpio[0], pin1); + + if (gpio_is_valid(dvs->gpio[1])) + gpio_set_value(dvs->gpio[1], pin2); +} + +static void lp8788_set_dvs(struct lp8788_buck *buck, enum lp8788_buck_id id) +{ + switch (id) { + case BUCK1: + lp8788_buck1_set_dvs(buck); + break; + case BUCK2: + lp8788_buck2_set_dvs(buck); + break; + default: + break; + } +} + +static enum lp8788_dvs_mode +lp8788_get_buck_dvs_ctrl_mode(struct lp8788_buck *buck, enum lp8788_buck_id id) +{ + u8 val, mask; + + switch (id) { + case BUCK1: + mask = LP8788_BUCK1_DVS_SEL_M; + break; + case BUCK2: + mask = LP8788_BUCK2_DVS_SEL_M; + break; + default: + return REGISTER; + } + + lp8788_read_byte(buck->lp, LP8788_BUCK_DVS_SEL, &val); + + return val & mask ? REGISTER : EXTPIN; +} + +static bool lp8788_is_valid_buck_addr(u8 addr) +{ + switch (addr) { + case LP8788_BUCK1_VOUT0: + case LP8788_BUCK1_VOUT1: + case LP8788_BUCK1_VOUT2: + case LP8788_BUCK1_VOUT3: + case LP8788_BUCK2_VOUT0: + case LP8788_BUCK2_VOUT1: + case LP8788_BUCK2_VOUT2: + case LP8788_BUCK2_VOUT3: + return true; + default: + return false; + } +} + +static u8 lp8788_select_buck_vout_addr(struct lp8788_buck *buck, + enum lp8788_buck_id id) +{ + enum lp8788_dvs_mode mode = lp8788_get_buck_dvs_ctrl_mode(buck, id); + struct lp8788_buck1_dvs *b1_dvs; + struct lp8788_buck2_dvs *b2_dvs; + u8 val, idx, addr; + int pin1, pin2; + + switch (id) { + case BUCK1: + if (mode == EXTPIN) { + b1_dvs = (struct lp8788_buck1_dvs *)buck->dvs; + if (!b1_dvs) + goto err; + + idx = gpio_get_value(b1_dvs->gpio) ? 1 : 0; + } else { + lp8788_read_byte(buck->lp, LP8788_BUCK_DVS_SEL, &val); + idx = (val & LP8788_BUCK1_DVS_M) >> LP8788_BUCK1_DVS_S; + } + addr = buck1_vout_addr[idx]; + break; + case BUCK2: + if (mode == EXTPIN) { + b2_dvs = (struct lp8788_buck2_dvs *)buck->dvs; + if (!b2_dvs) + goto err; + + pin1 = gpio_get_value(b2_dvs->gpio[0]); + pin2 = gpio_get_value(b2_dvs->gpio[1]); + + if (pin1 == PIN_LOW && pin2 == PIN_LOW) + idx = 0; + else if (pin1 == PIN_LOW && pin2 == PIN_HIGH) + idx = 2; + else if (pin1 == PIN_HIGH && pin2 == PIN_LOW) + idx = 1; + else + idx = 3; + } else { + lp8788_read_byte(buck->lp, LP8788_BUCK_DVS_SEL, &val); + idx = (val & LP8788_BUCK2_DVS_M) >> LP8788_BUCK2_DVS_S; + } + addr = buck2_vout_addr[idx]; + break; + default: + goto err; + } + + return addr; +err: + return INVALID_ADDR; +} + +static int lp8788_buck12_set_voltage_sel(struct regulator_dev *rdev, + unsigned selector) +{ + struct lp8788_buck *buck = rdev_get_drvdata(rdev); + enum lp8788_buck_id id = rdev_get_id(rdev); + u8 addr; + + if (buck->dvs) + lp8788_set_dvs(buck, id); + + addr = lp8788_select_buck_vout_addr(buck, id); + if (!lp8788_is_valid_buck_addr(addr)) + return -EINVAL; + + return lp8788_update_bits(buck->lp, addr, LP8788_VOUT_M, selector); +} + +static int lp8788_buck12_get_voltage_sel(struct regulator_dev *rdev) +{ + struct lp8788_buck *buck = rdev_get_drvdata(rdev); + enum lp8788_buck_id id = rdev_get_id(rdev); + int ret; + u8 val, addr; + + addr = lp8788_select_buck_vout_addr(buck, id); + if (!lp8788_is_valid_buck_addr(addr)) + return -EINVAL; + + ret = lp8788_read_byte(buck->lp, addr, &val); + if (ret) + return ret; + + return val & LP8788_VOUT_M; +} + +static int lp8788_buck_enable_time(struct regulator_dev *rdev) +{ + struct lp8788_buck *buck = rdev_get_drvdata(rdev); + enum lp8788_buck_id id = rdev_get_id(rdev); + u8 val, addr = LP8788_BUCK1_TIMESTEP + id; + + if (lp8788_read_byte(buck->lp, addr, &val)) + return -EINVAL; + + val = (val & LP8788_STARTUP_TIME_M) >> LP8788_STARTUP_TIME_S; + + return ENABLE_TIME_USEC * val; +} + +static int lp8788_buck_set_mode(struct regulator_dev *rdev, unsigned int mode) +{ + struct lp8788_buck *buck = rdev_get_drvdata(rdev); + struct lp8788_pwm_map *pmap = buck->pmap; + u8 val; + + if (!pmap) + return -EINVAL; + + switch (mode) { + case REGULATOR_MODE_FAST: + val = LP8788_FORCE_PWM << pmap->shift; + break; + case REGULATOR_MODE_NORMAL: + val = LP8788_AUTO_PWM << pmap->shift; + break; + default: + return -EINVAL; + } + + return lp8788_update_bits(buck->lp, LP8788_BUCK_PWM, pmap->mask, val); +} + +static unsigned int lp8788_buck_get_mode(struct regulator_dev *rdev) +{ + struct lp8788_buck *buck = rdev_get_drvdata(rdev); + struct lp8788_pwm_map *pmap = buck->pmap; + u8 val; + int ret; + + if (!pmap) + return -EINVAL; + + ret = lp8788_read_byte(buck->lp, LP8788_BUCK_PWM, &val); + if (ret) + return ret; + + return val & pmap->mask ? REGULATOR_MODE_FAST : REGULATOR_MODE_NORMAL; +} + +static struct regulator_ops lp8788_buck12_ops = { + .list_voltage = regulator_list_voltage_table, + .set_voltage_sel = lp8788_buck12_set_voltage_sel, + .get_voltage_sel = lp8788_buck12_get_voltage_sel, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .enable_time = lp8788_buck_enable_time, + .set_mode = lp8788_buck_set_mode, + .get_mode = lp8788_buck_get_mode, +}; + +static struct regulator_ops lp8788_buck34_ops = { + .list_voltage = regulator_list_voltage_table, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, + .enable_time = lp8788_buck_enable_time, + .set_mode = lp8788_buck_set_mode, + .get_mode = lp8788_buck_get_mode, +}; + +static struct regulator_desc lp8788_buck_desc[] = { + { + .name = "buck1", + .id = BUCK1, + .ops = &lp8788_buck12_ops, + .n_voltages = ARRAY_SIZE(lp8788_buck_vtbl), + .volt_table = lp8788_buck_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .enable_reg = LP8788_EN_BUCK, + .enable_mask = LP8788_EN_BUCK1_M, + }, + { + .name = "buck2", + .id = BUCK2, + .ops = &lp8788_buck12_ops, + .n_voltages = ARRAY_SIZE(lp8788_buck_vtbl), + .volt_table = lp8788_buck_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .enable_reg = LP8788_EN_BUCK, + .enable_mask = LP8788_EN_BUCK2_M, + }, + { + .name = "buck3", + .id = BUCK3, + .ops = &lp8788_buck34_ops, + .n_voltages = ARRAY_SIZE(lp8788_buck_vtbl), + .volt_table = lp8788_buck_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_BUCK3_VOUT, + .vsel_mask = LP8788_VOUT_M, + .enable_reg = LP8788_EN_BUCK, + .enable_mask = LP8788_EN_BUCK3_M, + }, + { + .name = "buck4", + .id = BUCK4, + .ops = &lp8788_buck34_ops, + .n_voltages = ARRAY_SIZE(lp8788_buck_vtbl), + .volt_table = lp8788_buck_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_BUCK4_VOUT, + .vsel_mask = LP8788_VOUT_M, + .enable_reg = LP8788_EN_BUCK, + .enable_mask = LP8788_EN_BUCK4_M, + }, +}; + +static int lp8788_set_default_dvs_ctrl_mode(struct lp8788 *lp, + enum lp8788_buck_id id) +{ + u8 mask, val; + + switch (id) { + case BUCK1: + mask = LP8788_BUCK1_DVS_SEL_M; + val = LP8788_BUCK1_DVS_I2C; + break; + case BUCK2: + mask = LP8788_BUCK2_DVS_SEL_M; + val = LP8788_BUCK2_DVS_I2C; + break; + default: + return 0; + } + + return lp8788_update_bits(lp, LP8788_BUCK_DVS_SEL, mask, val); +} + +static int _gpio_request(struct lp8788_buck *buck, int gpio, char *name) +{ + struct device *dev = buck->lp->dev; + + if (!gpio_is_valid(gpio)) { + dev_err(dev, "invalid gpio: %d\n", gpio); + return -EINVAL; + } + + return devm_gpio_request_one(dev, gpio, DVS_LOW, name); +} + +static int lp8788_dvs_gpio_request(struct lp8788_buck *buck, + enum lp8788_buck_id id) +{ + struct lp8788_platform_data *pdata = buck->lp->pdata; + char *b1_name = "LP8788_B1_DVS"; + char *b2_name[] = { "LP8788_B2_DVS1", "LP8788_B2_DVS2" }; + int i, gpio, ret; + + switch (id) { + case BUCK1: + gpio = pdata->buck1_dvs->gpio; + ret = _gpio_request(buck, gpio, b1_name); + if (ret) + return ret; + + buck->dvs = pdata->buck1_dvs; + break; + case BUCK2: + for (i = 0 ; i < LP8788_NUM_BUCK2_DVS ; i++) { + gpio = pdata->buck2_dvs->gpio[i]; + ret = _gpio_request(buck, gpio, b2_name[i]); + if (ret) + return ret; + } + buck->dvs = pdata->buck2_dvs; + break; + default: + break; + } + + return 0; +} + +static int lp8788_init_dvs(struct lp8788_buck *buck, enum lp8788_buck_id id) +{ + struct lp8788_platform_data *pdata = buck->lp->pdata; + u8 mask[] = { LP8788_BUCK1_DVS_SEL_M, LP8788_BUCK2_DVS_SEL_M }; + u8 val[] = { LP8788_BUCK1_DVS_PIN, LP8788_BUCK2_DVS_PIN }; + + /* no dvs for buck3, 4 */ + if (id == BUCK3 || id == BUCK4) + return 0; + + /* no dvs platform data, then dvs will be selected by I2C registers */ + if (!pdata) + goto set_default_dvs_mode; + + if ((id == BUCK1 && !pdata->buck1_dvs) || + (id == BUCK2 && !pdata->buck2_dvs)) + goto set_default_dvs_mode; + + if (lp8788_dvs_gpio_request(buck, id)) + goto set_default_dvs_mode; + + return lp8788_update_bits(buck->lp, LP8788_BUCK_DVS_SEL, mask[id], + val[id]); + +set_default_dvs_mode: + return lp8788_set_default_dvs_ctrl_mode(buck->lp, id); +} + +static __devinit int lp8788_buck_probe(struct platform_device *pdev) +{ + struct lp8788 *lp = dev_get_drvdata(pdev->dev.parent); + int id = pdev->id; + struct lp8788_buck *buck; + struct regulator_config cfg = { }; + struct regulator_dev *rdev; + int ret; + + buck = devm_kzalloc(lp->dev, sizeof(struct lp8788_buck), GFP_KERNEL); + if (!buck) + return -ENOMEM; + + buck->lp = lp; + buck->pmap = &buck_pmap[id]; + + ret = lp8788_init_dvs(buck, id); + if (ret) + return ret; + + cfg.dev = lp->dev; + cfg.init_data = lp->pdata ? lp->pdata->buck_data[id] : NULL; + cfg.driver_data = buck; + cfg.regmap = lp->regmap; + + rdev = regulator_register(&lp8788_buck_desc[id], &cfg); + if (IS_ERR(rdev)) { + ret = PTR_ERR(rdev); + dev_err(lp->dev, "BUCK%d regulator register err = %d\n", + id + 1, ret); + return ret; + } + + buck->regulator = rdev; + platform_set_drvdata(pdev, buck); + + return 0; +} + +static int __devexit lp8788_buck_remove(struct platform_device *pdev) +{ + struct lp8788_buck *buck = platform_get_drvdata(pdev); + + platform_set_drvdata(pdev, NULL); + regulator_unregister(buck->regulator); + + return 0; +} + +static struct platform_driver lp8788_buck_driver = { + .probe = lp8788_buck_probe, + .remove = __devexit_p(lp8788_buck_remove), + .driver = { + .name = LP8788_DEV_BUCK, + .owner = THIS_MODULE, + }, +}; + +static int __init lp8788_buck_init(void) +{ + return platform_driver_register(&lp8788_buck_driver); +} +subsys_initcall(lp8788_buck_init); + +static void __exit lp8788_buck_exit(void) +{ + platform_driver_unregister(&lp8788_buck_driver); +} +module_exit(lp8788_buck_exit); + +MODULE_DESCRIPTION("TI LP8788 BUCK Driver"); +MODULE_AUTHOR("Milo Kim"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:lp8788-buck"); diff --git a/drivers/regulator/lp8788-ldo.c b/drivers/regulator/lp8788-ldo.c new file mode 100644 index 000000000000..d2122e41a96d --- /dev/null +++ b/drivers/regulator/lp8788-ldo.c @@ -0,0 +1,842 @@ +/* + * TI LP8788 MFD - ldo regulator driver + * + * Copyright 2012 Texas Instruments + * + * Author: Milo(Woogyom) Kim <milo.kim@ti.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/err.h> +#include <linux/platform_device.h> +#include <linux/regulator/driver.h> +#include <linux/gpio.h> +#include <linux/mfd/lp8788.h> + +/* register address */ +#define LP8788_EN_LDO_A 0x0D /* DLDO 1 ~ 8 */ +#define LP8788_EN_LDO_B 0x0E /* DLDO 9 ~ 12, ALDO 1 ~ 4 */ +#define LP8788_EN_LDO_C 0x0F /* ALDO 5 ~ 10 */ +#define LP8788_EN_SEL 0x10 +#define LP8788_DLDO1_VOUT 0x2E +#define LP8788_DLDO2_VOUT 0x2F +#define LP8788_DLDO3_VOUT 0x30 +#define LP8788_DLDO4_VOUT 0x31 +#define LP8788_DLDO5_VOUT 0x32 +#define LP8788_DLDO6_VOUT 0x33 +#define LP8788_DLDO7_VOUT 0x34 +#define LP8788_DLDO8_VOUT 0x35 +#define LP8788_DLDO9_VOUT 0x36 +#define LP8788_DLDO10_VOUT 0x37 +#define LP8788_DLDO11_VOUT 0x38 +#define LP8788_DLDO12_VOUT 0x39 +#define LP8788_ALDO1_VOUT 0x3A +#define LP8788_ALDO2_VOUT 0x3B +#define LP8788_ALDO3_VOUT 0x3C +#define LP8788_ALDO4_VOUT 0x3D +#define LP8788_ALDO5_VOUT 0x3E +#define LP8788_ALDO6_VOUT 0x3F +#define LP8788_ALDO7_VOUT 0x40 +#define LP8788_ALDO8_VOUT 0x41 +#define LP8788_ALDO9_VOUT 0x42 +#define LP8788_ALDO10_VOUT 0x43 +#define LP8788_DLDO1_TIMESTEP 0x44 + +/* mask/shift bits */ +#define LP8788_EN_DLDO1_M BIT(0) /* Addr 0Dh ~ 0Fh */ +#define LP8788_EN_DLDO2_M BIT(1) +#define LP8788_EN_DLDO3_M BIT(2) +#define LP8788_EN_DLDO4_M BIT(3) +#define LP8788_EN_DLDO5_M BIT(4) +#define LP8788_EN_DLDO6_M BIT(5) +#define LP8788_EN_DLDO7_M BIT(6) +#define LP8788_EN_DLDO8_M BIT(7) +#define LP8788_EN_DLDO9_M BIT(0) +#define LP8788_EN_DLDO10_M BIT(1) +#define LP8788_EN_DLDO11_M BIT(2) +#define LP8788_EN_DLDO12_M BIT(3) +#define LP8788_EN_ALDO1_M BIT(4) +#define LP8788_EN_ALDO2_M BIT(5) +#define LP8788_EN_ALDO3_M BIT(6) +#define LP8788_EN_ALDO4_M BIT(7) +#define LP8788_EN_ALDO5_M BIT(0) +#define LP8788_EN_ALDO6_M BIT(1) +#define LP8788_EN_ALDO7_M BIT(2) +#define LP8788_EN_ALDO8_M BIT(3) +#define LP8788_EN_ALDO9_M BIT(4) +#define LP8788_EN_ALDO10_M BIT(5) +#define LP8788_EN_SEL_DLDO911_M BIT(0) /* Addr 10h */ +#define LP8788_EN_SEL_DLDO7_M BIT(1) +#define LP8788_EN_SEL_ALDO7_M BIT(2) +#define LP8788_EN_SEL_ALDO5_M BIT(3) +#define LP8788_EN_SEL_ALDO234_M BIT(4) +#define LP8788_EN_SEL_ALDO1_M BIT(5) +#define LP8788_VOUT_5BIT_M 0x1F /* Addr 2Eh ~ 43h */ +#define LP8788_VOUT_4BIT_M 0x0F +#define LP8788_VOUT_3BIT_M 0x07 +#define LP8788_VOUT_1BIT_M 0x01 +#define LP8788_STARTUP_TIME_M 0xF8 /* Addr 44h ~ 59h */ +#define LP8788_STARTUP_TIME_S 3 + +#define ENABLE_TIME_USEC 32 +#define ENABLE GPIOF_OUT_INIT_HIGH +#define DISABLE GPIOF_OUT_INIT_LOW + +enum lp8788_enable_mode { + REGISTER, + EXTPIN, +}; + +enum lp8788_ldo_id { + DLDO1, + DLDO2, + DLDO3, + DLDO4, + DLDO5, + DLDO6, + DLDO7, + DLDO8, + DLDO9, + DLDO10, + DLDO11, + DLDO12, + ALDO1, + ALDO2, + ALDO3, + ALDO4, + ALDO5, + ALDO6, + ALDO7, + ALDO8, + ALDO9, + ALDO10, +}; + +struct lp8788_ldo { + struct lp8788 *lp; + struct regulator_desc *desc; + struct regulator_dev *regulator; + struct lp8788_ldo_enable_pin *en_pin; +}; + +/* DLDO 1, 2, 3, 9 voltage table */ +const int lp8788_dldo1239_vtbl[] = { + 1800000, 1900000, 2000000, 2100000, 2200000, 2300000, 2400000, 2500000, + 2600000, 2700000, 2800000, 2900000, 3000000, 2850000, 2850000, 2850000, + 2850000, 2850000, 2850000, 2850000, 2850000, 2850000, 2850000, 2850000, + 2850000, 2850000, 2850000, 2850000, 2850000, 2850000, 2850000, 2850000, +}; + +/* DLDO 4 voltage table */ +static const int lp8788_dldo4_vtbl[] = { 1800000, 3000000 }; + +/* DLDO 5, 7, 8 and ALDO 6 voltage table */ +static const int lp8788_dldo578_aldo6_vtbl[] = { + 1800000, 1900000, 2000000, 2100000, 2200000, 2300000, 2400000, 2500000, + 2600000, 2700000, 2800000, 2900000, 3000000, 3000000, 3000000, 3000000, +}; + +/* DLDO 6 voltage table */ +static const int lp8788_dldo6_vtbl[] = { + 3000000, 3100000, 3200000, 3300000, 3400000, 3500000, 3600000, 3600000, +}; + +/* DLDO 10, 11 voltage table */ +static const int lp8788_dldo1011_vtbl[] = { + 1100000, 1150000, 1200000, 1250000, 1300000, 1350000, 1400000, 1450000, + 1500000, 1500000, 1500000, 1500000, 1500000, 1500000, 1500000, 1500000, +}; + +/* ALDO 1 voltage table */ +static const int lp8788_aldo1_vtbl[] = { 1800000, 2850000 }; + +/* ALDO 7 voltage table */ +static const int lp8788_aldo7_vtbl[] = { + 1200000, 1300000, 1400000, 1500000, 1600000, 1700000, 1800000, 1800000, +}; + +static enum lp8788_ldo_id lp8788_dldo_id[] = { + DLDO1, + DLDO2, + DLDO3, + DLDO4, + DLDO5, + DLDO6, + DLDO7, + DLDO8, + DLDO9, + DLDO10, + DLDO11, + DLDO12, +}; + +static enum lp8788_ldo_id lp8788_aldo_id[] = { + ALDO1, + ALDO2, + ALDO3, + ALDO4, + ALDO5, + ALDO6, + ALDO7, + ALDO8, + ALDO9, + ALDO10, +}; + +/* DLDO 7, 9 and 11, ALDO 1 ~ 5 and 7 + : can be enabled either by external pin or by i2c register */ +static enum lp8788_enable_mode +lp8788_get_ldo_enable_mode(struct lp8788_ldo *ldo, enum lp8788_ldo_id id) +{ + int ret; + u8 val, mask; + + ret = lp8788_read_byte(ldo->lp, LP8788_EN_SEL, &val); + if (ret) + return ret; + + switch (id) { + case DLDO7: + mask = LP8788_EN_SEL_DLDO7_M; + break; + case DLDO9: + case DLDO11: + mask = LP8788_EN_SEL_DLDO911_M; + break; + case ALDO1: + mask = LP8788_EN_SEL_ALDO1_M; + break; + case ALDO2 ... ALDO4: + mask = LP8788_EN_SEL_ALDO234_M; + break; + case ALDO5: + mask = LP8788_EN_SEL_ALDO5_M; + break; + case ALDO7: + mask = LP8788_EN_SEL_ALDO7_M; + break; + default: + return REGISTER; + } + + return val & mask ? EXTPIN : REGISTER; +} + +static int lp8788_ldo_ctrl_by_extern_pin(struct lp8788_ldo *ldo, int pinstate) +{ + struct lp8788_ldo_enable_pin *pin = ldo->en_pin; + + if (!pin) + return -EINVAL; + + if (gpio_is_valid(pin->gpio)) + gpio_set_value(pin->gpio, pinstate); + + return 0; +} + +static int lp8788_ldo_is_enabled_by_extern_pin(struct lp8788_ldo *ldo) +{ + struct lp8788_ldo_enable_pin *pin = ldo->en_pin; + + if (!pin) + return -EINVAL; + + return gpio_get_value(pin->gpio) ? 1 : 0; +} + +static int lp8788_ldo_enable(struct regulator_dev *rdev) +{ + struct lp8788_ldo *ldo = rdev_get_drvdata(rdev); + enum lp8788_ldo_id id = rdev_get_id(rdev); + enum lp8788_enable_mode mode = lp8788_get_ldo_enable_mode(ldo, id); + + switch (mode) { + case EXTPIN: + return lp8788_ldo_ctrl_by_extern_pin(ldo, ENABLE); + case REGISTER: + return regulator_enable_regmap(rdev); + default: + return -EINVAL; + } +} + +static int lp8788_ldo_disable(struct regulator_dev *rdev) +{ + struct lp8788_ldo *ldo = rdev_get_drvdata(rdev); + enum lp8788_ldo_id id = rdev_get_id(rdev); + enum lp8788_enable_mode mode = lp8788_get_ldo_enable_mode(ldo, id); + + switch (mode) { + case EXTPIN: + return lp8788_ldo_ctrl_by_extern_pin(ldo, DISABLE); + case REGISTER: + return regulator_disable_regmap(rdev); + default: + return -EINVAL; + } +} + +static int lp8788_ldo_is_enabled(struct regulator_dev *rdev) +{ + struct lp8788_ldo *ldo = rdev_get_drvdata(rdev); + enum lp8788_ldo_id id = rdev_get_id(rdev); + enum lp8788_enable_mode mode = lp8788_get_ldo_enable_mode(ldo, id); + + switch (mode) { + case EXTPIN: + return lp8788_ldo_is_enabled_by_extern_pin(ldo); + case REGISTER: + return regulator_is_enabled_regmap(rdev); + default: + return -EINVAL; + } +} + +static int lp8788_ldo_enable_time(struct regulator_dev *rdev) +{ + struct lp8788_ldo *ldo = rdev_get_drvdata(rdev); + enum lp8788_ldo_id id = rdev_get_id(rdev); + u8 val, addr = LP8788_DLDO1_TIMESTEP + id; + + if (lp8788_read_byte(ldo->lp, addr, &val)) + return -EINVAL; + + val = (val & LP8788_STARTUP_TIME_M) >> LP8788_STARTUP_TIME_S; + + return ENABLE_TIME_USEC * val; +} + +static int lp8788_ldo_fixed_get_voltage(struct regulator_dev *rdev) +{ + enum lp8788_ldo_id id = rdev_get_id(rdev); + + switch (id) { + case ALDO2 ... ALDO5: + return 2850000; + case DLDO12: + case ALDO8 ... ALDO9: + return 2500000; + case ALDO10: + return 1100000; + default: + return -EINVAL; + } +} + +static struct regulator_ops lp8788_ldo_voltage_table_ops = { + .list_voltage = regulator_list_voltage_table, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .enable = lp8788_ldo_enable, + .disable = lp8788_ldo_disable, + .is_enabled = lp8788_ldo_is_enabled, + .enable_time = lp8788_ldo_enable_time, +}; + +static struct regulator_ops lp8788_ldo_voltage_fixed_ops = { + .get_voltage = lp8788_ldo_fixed_get_voltage, + .enable = lp8788_ldo_enable, + .disable = lp8788_ldo_disable, + .is_enabled = lp8788_ldo_is_enabled, + .enable_time = lp8788_ldo_enable_time, +}; + +static struct regulator_desc lp8788_dldo_desc[] = { + { + .name = "dldo1", + .id = DLDO1, + .ops = &lp8788_ldo_voltage_table_ops, + .n_voltages = ARRAY_SIZE(lp8788_dldo1239_vtbl), + .volt_table = lp8788_dldo1239_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_DLDO1_VOUT, + .vsel_mask = LP8788_VOUT_5BIT_M, + .enable_reg = LP8788_EN_LDO_A, + .enable_mask = LP8788_EN_DLDO1_M, + }, + { + .name = "dldo2", + .id = DLDO2, + .ops = &lp8788_ldo_voltage_table_ops, + .n_voltages = ARRAY_SIZE(lp8788_dldo1239_vtbl), + .volt_table = lp8788_dldo1239_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_DLDO2_VOUT, + .vsel_mask = LP8788_VOUT_5BIT_M, + .enable_reg = LP8788_EN_LDO_A, + .enable_mask = LP8788_EN_DLDO2_M, + }, + { + .name = "dldo3", + .id = DLDO3, + .ops = &lp8788_ldo_voltage_table_ops, + .n_voltages = ARRAY_SIZE(lp8788_dldo1239_vtbl), + .volt_table = lp8788_dldo1239_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_DLDO3_VOUT, + .vsel_mask = LP8788_VOUT_5BIT_M, + .enable_reg = LP8788_EN_LDO_A, + .enable_mask = LP8788_EN_DLDO3_M, + }, + { + .name = "dldo4", + .id = DLDO4, + .ops = &lp8788_ldo_voltage_table_ops, + .n_voltages = ARRAY_SIZE(lp8788_dldo4_vtbl), + .volt_table = lp8788_dldo4_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_DLDO4_VOUT, + .vsel_mask = LP8788_VOUT_1BIT_M, + .enable_reg = LP8788_EN_LDO_A, + .enable_mask = LP8788_EN_DLDO4_M, + }, + { + .name = "dldo5", + .id = DLDO5, + .ops = &lp8788_ldo_voltage_table_ops, + .n_voltages = ARRAY_SIZE(lp8788_dldo578_aldo6_vtbl), + .volt_table = lp8788_dldo578_aldo6_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_DLDO5_VOUT, + .vsel_mask = LP8788_VOUT_4BIT_M, + .enable_reg = LP8788_EN_LDO_A, + .enable_mask = LP8788_EN_DLDO5_M, + }, + { + .name = "dldo6", + .id = DLDO6, + .ops = &lp8788_ldo_voltage_table_ops, + .n_voltages = ARRAY_SIZE(lp8788_dldo6_vtbl), + .volt_table = lp8788_dldo6_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_DLDO6_VOUT, + .vsel_mask = LP8788_VOUT_3BIT_M, + .enable_reg = LP8788_EN_LDO_A, + .enable_mask = LP8788_EN_DLDO6_M, + }, + { + .name = "dldo7", + .id = DLDO7, + .ops = &lp8788_ldo_voltage_table_ops, + .n_voltages = ARRAY_SIZE(lp8788_dldo578_aldo6_vtbl), + .volt_table = lp8788_dldo578_aldo6_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_DLDO7_VOUT, + .vsel_mask = LP8788_VOUT_4BIT_M, + .enable_reg = LP8788_EN_LDO_A, + .enable_mask = LP8788_EN_DLDO7_M, + }, + { + .name = "dldo8", + .id = DLDO8, + .ops = &lp8788_ldo_voltage_table_ops, + .n_voltages = ARRAY_SIZE(lp8788_dldo578_aldo6_vtbl), + .volt_table = lp8788_dldo578_aldo6_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_DLDO8_VOUT, + .vsel_mask = LP8788_VOUT_4BIT_M, + .enable_reg = LP8788_EN_LDO_A, + .enable_mask = LP8788_EN_DLDO8_M, + }, + { + .name = "dldo9", + .id = DLDO9, + .ops = &lp8788_ldo_voltage_table_ops, + .n_voltages = ARRAY_SIZE(lp8788_dldo1239_vtbl), + .volt_table = lp8788_dldo1239_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_DLDO9_VOUT, + .vsel_mask = LP8788_VOUT_5BIT_M, + .enable_reg = LP8788_EN_LDO_B, + .enable_mask = LP8788_EN_DLDO9_M, + }, + { + .name = "dldo10", + .id = DLDO10, + .ops = &lp8788_ldo_voltage_table_ops, + .n_voltages = ARRAY_SIZE(lp8788_dldo1011_vtbl), + .volt_table = lp8788_dldo1011_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_DLDO10_VOUT, + .vsel_mask = LP8788_VOUT_4BIT_M, + .enable_reg = LP8788_EN_LDO_B, + .enable_mask = LP8788_EN_DLDO10_M, + }, + { + .name = "dldo11", + .id = DLDO11, + .ops = &lp8788_ldo_voltage_table_ops, + .n_voltages = ARRAY_SIZE(lp8788_dldo1011_vtbl), + .volt_table = lp8788_dldo1011_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_DLDO11_VOUT, + .vsel_mask = LP8788_VOUT_4BIT_M, + .enable_reg = LP8788_EN_LDO_B, + .enable_mask = LP8788_EN_DLDO11_M, + }, + { + .name = "dldo12", + .id = DLDO12, + .ops = &lp8788_ldo_voltage_fixed_ops, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .enable_reg = LP8788_EN_LDO_B, + .enable_mask = LP8788_EN_DLDO12_M, + }, +}; + +static struct regulator_desc lp8788_aldo_desc[] = { + { + .name = "aldo1", + .id = ALDO1, + .ops = &lp8788_ldo_voltage_table_ops, + .n_voltages = ARRAY_SIZE(lp8788_aldo1_vtbl), + .volt_table = lp8788_aldo1_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_ALDO1_VOUT, + .vsel_mask = LP8788_VOUT_1BIT_M, + .enable_reg = LP8788_EN_LDO_B, + .enable_mask = LP8788_EN_ALDO1_M, + }, + { + .name = "aldo2", + .id = ALDO2, + .ops = &lp8788_ldo_voltage_fixed_ops, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .enable_reg = LP8788_EN_LDO_B, + .enable_mask = LP8788_EN_ALDO2_M, + }, + { + .name = "aldo3", + .id = ALDO3, + .ops = &lp8788_ldo_voltage_fixed_ops, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .enable_reg = LP8788_EN_LDO_B, + .enable_mask = LP8788_EN_ALDO3_M, + }, + { + .name = "aldo4", + .id = ALDO4, + .ops = &lp8788_ldo_voltage_fixed_ops, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .enable_reg = LP8788_EN_LDO_B, + .enable_mask = LP8788_EN_ALDO4_M, + }, + { + .name = "aldo5", + .id = ALDO5, + .ops = &lp8788_ldo_voltage_fixed_ops, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .enable_reg = LP8788_EN_LDO_C, + .enable_mask = LP8788_EN_ALDO5_M, + }, + { + .name = "aldo6", + .id = ALDO6, + .ops = &lp8788_ldo_voltage_table_ops, + .n_voltages = ARRAY_SIZE(lp8788_dldo578_aldo6_vtbl), + .volt_table = lp8788_dldo578_aldo6_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_ALDO6_VOUT, + .vsel_mask = LP8788_VOUT_4BIT_M, + .enable_reg = LP8788_EN_LDO_C, + .enable_mask = LP8788_EN_ALDO6_M, + }, + { + .name = "aldo7", + .id = ALDO7, + .ops = &lp8788_ldo_voltage_table_ops, + .n_voltages = ARRAY_SIZE(lp8788_aldo7_vtbl), + .volt_table = lp8788_aldo7_vtbl, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .vsel_reg = LP8788_ALDO7_VOUT, + .vsel_mask = LP8788_VOUT_3BIT_M, + .enable_reg = LP8788_EN_LDO_C, + .enable_mask = LP8788_EN_ALDO7_M, + }, + { + .name = "aldo8", + .id = ALDO8, + .ops = &lp8788_ldo_voltage_fixed_ops, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .enable_reg = LP8788_EN_LDO_C, + .enable_mask = LP8788_EN_ALDO8_M, + }, + { + .name = "aldo9", + .id = ALDO9, + .ops = &lp8788_ldo_voltage_fixed_ops, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .enable_reg = LP8788_EN_LDO_C, + .enable_mask = LP8788_EN_ALDO9_M, + }, + { + .name = "aldo10", + .id = ALDO10, + .ops = &lp8788_ldo_voltage_fixed_ops, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, + .enable_reg = LP8788_EN_LDO_C, + .enable_mask = LP8788_EN_ALDO10_M, + }, +}; + +static int lp8788_gpio_request_ldo_en(struct lp8788_ldo *ldo, + enum lp8788_ext_ldo_en_id id) +{ + struct device *dev = ldo->lp->dev; + struct lp8788_ldo_enable_pin *pin = ldo->en_pin; + int ret, gpio, pinstate; + char *name[] = { + [EN_ALDO1] = "LP8788_EN_ALDO1", + [EN_ALDO234] = "LP8788_EN_ALDO234", + [EN_ALDO5] = "LP8788_EN_ALDO5", + [EN_ALDO7] = "LP8788_EN_ALDO7", + [EN_DLDO7] = "LP8788_EN_DLDO7", + [EN_DLDO911] = "LP8788_EN_DLDO911", + }; + + gpio = pin->gpio; + if (!gpio_is_valid(gpio)) { + dev_err(dev, "invalid gpio: %d\n", gpio); + return -EINVAL; + } + + pinstate = pin->init_state; + ret = devm_gpio_request_one(dev, gpio, pinstate, name[id]); + if (ret == -EBUSY) { + dev_warn(dev, "gpio%d already used\n", gpio); + return 0; + } + + return ret; +} + +static int lp8788_config_ldo_enable_mode(struct lp8788_ldo *ldo, + enum lp8788_ldo_id id) +{ + int ret; + struct lp8788 *lp = ldo->lp; + struct lp8788_platform_data *pdata = lp->pdata; + enum lp8788_ext_ldo_en_id enable_id; + u8 en_mask[] = { + [EN_ALDO1] = LP8788_EN_SEL_ALDO1_M, + [EN_ALDO234] = LP8788_EN_SEL_ALDO234_M, + [EN_ALDO5] = LP8788_EN_SEL_ALDO5_M, + [EN_ALDO7] = LP8788_EN_SEL_ALDO7_M, + [EN_DLDO7] = LP8788_EN_SEL_DLDO7_M, + [EN_DLDO911] = LP8788_EN_SEL_DLDO911_M, + }; + u8 val[] = { + [EN_ALDO1] = 0 << 5, + [EN_ALDO234] = 0 << 4, + [EN_ALDO5] = 0 << 3, + [EN_ALDO7] = 0 << 2, + [EN_DLDO7] = 0 << 1, + [EN_DLDO911] = 0 << 0, + }; + + switch (id) { + case DLDO7: + enable_id = EN_DLDO7; + break; + case DLDO9: + case DLDO11: + enable_id = EN_DLDO911; + break; + case ALDO1: + enable_id = EN_ALDO1; + break; + case ALDO2 ... ALDO4: + enable_id = EN_ALDO234; + break; + case ALDO5: + enable_id = EN_ALDO5; + break; + case ALDO7: + enable_id = EN_ALDO7; + break; + default: + return 0; + } + + /* if no platform data for ldo pin, then set default enable mode */ + if (!pdata || !pdata->ldo_pin || !pdata->ldo_pin[enable_id]) + goto set_default_ldo_enable_mode; + + ldo->en_pin = pdata->ldo_pin[enable_id]; + + ret = lp8788_gpio_request_ldo_en(ldo, enable_id); + if (ret) + goto set_default_ldo_enable_mode; + + return ret; + +set_default_ldo_enable_mode: + return lp8788_update_bits(lp, LP8788_EN_SEL, en_mask[enable_id], + val[enable_id]); +} + +static __devinit int lp8788_dldo_probe(struct platform_device *pdev) +{ + struct lp8788 *lp = dev_get_drvdata(pdev->dev.parent); + int id = pdev->id; + struct lp8788_ldo *ldo; + struct regulator_config cfg = { }; + struct regulator_dev *rdev; + int ret; + + ldo = devm_kzalloc(lp->dev, sizeof(struct lp8788_ldo), GFP_KERNEL); + if (!ldo) + return -ENOMEM; + + ldo->lp = lp; + ret = lp8788_config_ldo_enable_mode(ldo, lp8788_dldo_id[id]); + if (ret) + return ret; + + cfg.dev = lp->dev; + cfg.init_data = lp->pdata ? lp->pdata->dldo_data[id] : NULL; + cfg.driver_data = ldo; + cfg.regmap = lp->regmap; + + rdev = regulator_register(&lp8788_dldo_desc[id], &cfg); + if (IS_ERR(rdev)) { + ret = PTR_ERR(rdev); + dev_err(lp->dev, "DLDO%d regulator register err = %d\n", + id + 1, ret); + return ret; + } + + ldo->regulator = rdev; + platform_set_drvdata(pdev, ldo); + + return 0; +} + +static int __devexit lp8788_dldo_remove(struct platform_device *pdev) +{ + struct lp8788_ldo *ldo = platform_get_drvdata(pdev); + + platform_set_drvdata(pdev, NULL); + regulator_unregister(ldo->regulator); + + return 0; +} + +static struct platform_driver lp8788_dldo_driver = { + .probe = lp8788_dldo_probe, + .remove = __devexit_p(lp8788_dldo_remove), + .driver = { + .name = LP8788_DEV_DLDO, + .owner = THIS_MODULE, + }, +}; + +static __devinit int lp8788_aldo_probe(struct platform_device *pdev) +{ + struct lp8788 *lp = dev_get_drvdata(pdev->dev.parent); + int id = pdev->id; + struct lp8788_ldo *ldo; + struct regulator_config cfg = { }; + struct regulator_dev *rdev; + int ret; + + ldo = devm_kzalloc(lp->dev, sizeof(struct lp8788_ldo), GFP_KERNEL); + if (!ldo) + return -ENOMEM; + + ldo->lp = lp; + ret = lp8788_config_ldo_enable_mode(ldo, lp8788_aldo_id[id]); + if (ret) + return ret; + + cfg.dev = lp->dev; + cfg.init_data = lp->pdata ? lp->pdata->aldo_data[id] : NULL; + cfg.driver_data = ldo; + cfg.regmap = lp->regmap; + + rdev = regulator_register(&lp8788_aldo_desc[id], &cfg); + if (IS_ERR(rdev)) { + ret = PTR_ERR(rdev); + dev_err(lp->dev, "ALDO%d regulator register err = %d\n", + id + 1, ret); + return ret; + } + + ldo->regulator = rdev; + platform_set_drvdata(pdev, ldo); + + return 0; +} + +static int __devexit lp8788_aldo_remove(struct platform_device *pdev) +{ + struct lp8788_ldo *ldo = platform_get_drvdata(pdev); + + platform_set_drvdata(pdev, NULL); + regulator_unregister(ldo->regulator); + + return 0; +} + +static struct platform_driver lp8788_aldo_driver = { + .probe = lp8788_aldo_probe, + .remove = __devexit_p(lp8788_aldo_remove), + .driver = { + .name = LP8788_DEV_ALDO, + .owner = THIS_MODULE, + }, +}; + +static int __init lp8788_ldo_init(void) +{ + int ret; + + ret = platform_driver_register(&lp8788_dldo_driver); + if (ret) + return ret; + + return platform_driver_register(&lp8788_aldo_driver); +} +subsys_initcall(lp8788_ldo_init); + +static void __exit lp8788_ldo_exit(void) +{ + platform_driver_unregister(&lp8788_aldo_driver); + platform_driver_unregister(&lp8788_dldo_driver); +} +module_exit(lp8788_ldo_exit); + +MODULE_DESCRIPTION("TI LP8788 LDO Driver"); +MODULE_AUTHOR("Milo Kim"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:lp8788-dldo"); +MODULE_ALIAS("platform:lp8788-aldo"); diff --git a/drivers/regulator/max1586.c b/drivers/regulator/max1586.c index b9444ee08da9..f67af3c1b963 100644 --- a/drivers/regulator/max1586.c +++ b/drivers/regulator/max1586.c @@ -48,6 +48,14 @@ struct max1586_data { }; /* + * V6 voltage + * On I2C bus, sending a "x" byte to the max1586 means : + * set V6 to either 0V, 1.8V, 2.5V, 3V depending on (x & 0x3) + * As regulator framework doesn't accept voltages to be 0V, we use 1uV. + */ +static int v6_voltages_uv[] = { 1, 1800000, 2500000, 3000000 }; + +/* * V3 voltage * On I2C bus, sending a "x" byte to the max1586 means : * set V3 to 0.700V + (x & 0x1f) * 0.025V @@ -55,113 +63,49 @@ struct max1586_data { * R24 and R25=100kOhm as described in the data sheet. * The gain is approximately: 1 + R24/R25 + R24/185.5kOhm */ -static int max1586_v3_calc_voltage(struct max1586_data *max1586, - unsigned selector) -{ - unsigned range_uV = max1586->max_uV - max1586->min_uV; - - return max1586->min_uV + (selector * range_uV / MAX1586_V3_MAX_VSEL); -} - -static int max1586_v3_set(struct regulator_dev *rdev, int min_uV, int max_uV, - unsigned *selector) +static int max1586_v3_set_voltage_sel(struct regulator_dev *rdev, + unsigned selector) { struct max1586_data *max1586 = rdev_get_drvdata(rdev); struct i2c_client *client = max1586->client; - unsigned range_uV = max1586->max_uV - max1586->min_uV; u8 v3_prog; - if (min_uV > max1586->max_uV || max_uV < max1586->min_uV) - return -EINVAL; - if (min_uV < max1586->min_uV) - min_uV = max1586->min_uV; - - *selector = DIV_ROUND_UP((min_uV - max1586->min_uV) * - MAX1586_V3_MAX_VSEL, range_uV); - if (max1586_v3_calc_voltage(max1586, *selector) > max_uV) - return -EINVAL; - dev_dbg(&client->dev, "changing voltage v3 to %dmv\n", - max1586_v3_calc_voltage(max1586, *selector) / 1000); + regulator_list_voltage_linear(rdev, selector) / 1000); - v3_prog = I2C_V3_SELECT | (u8) *selector; + v3_prog = I2C_V3_SELECT | (u8) selector; return i2c_smbus_write_byte(client, v3_prog); } -static int max1586_v3_list(struct regulator_dev *rdev, unsigned selector) -{ - struct max1586_data *max1586 = rdev_get_drvdata(rdev); - - if (selector > MAX1586_V3_MAX_VSEL) - return -EINVAL; - return max1586_v3_calc_voltage(max1586, selector); -} - -/* - * V6 voltage - * On I2C bus, sending a "x" byte to the max1586 means : - * set V6 to either 0V, 1.8V, 2.5V, 3V depending on (x & 0x3) - * As regulator framework doesn't accept voltages to be 0V, we use 1uV. - */ -static int max1586_v6_calc_voltage(unsigned selector) -{ - static int voltages_uv[] = { 1, 1800000, 2500000, 3000000 }; - - return voltages_uv[selector]; -} - -static int max1586_v6_set(struct regulator_dev *rdev, int min_uV, int max_uV, - unsigned int *selector) +static int max1586_v6_set_voltage_sel(struct regulator_dev *rdev, + unsigned int selector) { struct i2c_client *client = rdev_get_drvdata(rdev); u8 v6_prog; - if (min_uV < MAX1586_V6_MIN_UV || min_uV > MAX1586_V6_MAX_UV) - return -EINVAL; - if (max_uV < MAX1586_V6_MIN_UV || max_uV > MAX1586_V6_MAX_UV) - return -EINVAL; - - if (min_uV < 1800000) - *selector = 0; - else if (min_uV < 2500000) - *selector = 1; - else if (min_uV < 3000000) - *selector = 2; - else if (min_uV >= 3000000) - *selector = 3; - - if (max1586_v6_calc_voltage(*selector) > max_uV) - return -EINVAL; - dev_dbg(&client->dev, "changing voltage v6 to %dmv\n", - max1586_v6_calc_voltage(*selector) / 1000); + rdev->desc->volt_table[selector] / 1000); - v6_prog = I2C_V6_SELECT | (u8) *selector; + v6_prog = I2C_V6_SELECT | (u8) selector; return i2c_smbus_write_byte(client, v6_prog); } -static int max1586_v6_list(struct regulator_dev *rdev, unsigned selector) -{ - if (selector > MAX1586_V6_MAX_VSEL) - return -EINVAL; - return max1586_v6_calc_voltage(selector); -} - /* * The Maxim 1586 controls V3 and V6 voltages, but offers no way of reading back * the set up value. */ static struct regulator_ops max1586_v3_ops = { - .set_voltage = max1586_v3_set, - .list_voltage = max1586_v3_list, + .set_voltage_sel = max1586_v3_set_voltage_sel, + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, }; static struct regulator_ops max1586_v6_ops = { - .set_voltage = max1586_v6_set, - .list_voltage = max1586_v6_list, + .set_voltage_sel = max1586_v6_set_voltage_sel, + .list_voltage = regulator_list_voltage_table, }; -static const struct regulator_desc max1586_reg[] = { +static struct regulator_desc max1586_reg[] = { { .name = "Output_V3", .id = MAX1586_V3, @@ -176,6 +120,7 @@ static const struct regulator_desc max1586_reg[] = { .ops = &max1586_v6_ops, .type = REGULATOR_VOLTAGE, .n_voltages = MAX1586_V6_MAX_VSEL + 1, + .volt_table = v6_voltages_uv, .owner = THIS_MODULE, }, }; @@ -213,6 +158,13 @@ static int __devinit max1586_pmic_probe(struct i2c_client *client, goto err; } + if (id == MAX1586_V3) { + max1586_reg[id].min_uV = max1586->min_uV; + max1586_reg[id].uV_step = + (max1586->max_uV - max1586->min_uV) / + MAX1586_V3_MAX_VSEL; + } + config.dev = &client->dev; config.init_data = pdata->subdevs[i].platform_data; config.driver_data = max1586; diff --git a/drivers/regulator/max77686.c b/drivers/regulator/max77686.c new file mode 100644 index 000000000000..c564af6f05a3 --- /dev/null +++ b/drivers/regulator/max77686.c @@ -0,0 +1,389 @@ +/* + * max77686.c - Regulator driver for the Maxim 77686 + * + * Copyright (C) 2012 Samsung Electronics + * Chiwoong Byun <woong.byun@smasung.com> + * Jonghwa Lee <jonghwa3.lee@samsung.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * This driver is based on max8997.c + */ + +#include <linux/kernel.h> +#include <linux/bug.h> +#include <linux/delay.h> +#include <linux/err.h> +#include <linux/gpio.h> +#include <linux/slab.h> +#include <linux/platform_device.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/machine.h> +#include <linux/regulator/of_regulator.h> +#include <linux/mfd/max77686.h> +#include <linux/mfd/max77686-private.h> + +#define MAX77686_LDO_MINUV 800000 +#define MAX77686_LDO_UVSTEP 50000 +#define MAX77686_LDO_LOW_MINUV 800000 +#define MAX77686_LDO_LOW_UVSTEP 25000 +#define MAX77686_BUCK_MINUV 750000 +#define MAX77686_BUCK_UVSTEP 50000 +#define MAX77686_RAMP_DELAY 100000 /* uV/us */ +#define MAX77686_DVS_RAMP_DELAY 27500 /* uV/us */ +#define MAX77686_DVS_MINUV 600000 +#define MAX77686_DVS_UVSTEP 12500 + +#define MAX77686_OPMODE_SHIFT 6 +#define MAX77686_OPMODE_BUCK234_SHIFT 4 +#define MAX77686_OPMODE_MASK 0x3 + +#define MAX77686_VSEL_MASK 0x3F +#define MAX77686_DVS_VSEL_MASK 0xFF + +#define MAX77686_RAMP_RATE_MASK 0xC0 + +#define MAX77686_REGULATORS MAX77686_REG_MAX +#define MAX77686_LDOS 26 + +enum max77686_ramp_rate { + RAMP_RATE_13P75MV, + RAMP_RATE_27P5MV, + RAMP_RATE_55MV, + RAMP_RATE_NO_CTRL, /* 100mV/us */ +}; + +struct max77686_data { + struct regulator_dev **rdev; +}; + +static int max77686_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay) +{ + unsigned int ramp_value = RAMP_RATE_NO_CTRL; + + switch (ramp_delay) { + case 1 ... 13750: + ramp_value = RAMP_RATE_13P75MV; + break; + case 13751 ... 27500: + ramp_value = RAMP_RATE_27P5MV; + break; + case 27501 ... 55000: + ramp_value = RAMP_RATE_55MV; + break; + case 55001 ... 100000: + break; + default: + pr_warn("%s: ramp_delay: %d not supported, setting 100000\n", + rdev->desc->name, ramp_delay); + } + + return regmap_update_bits(rdev->regmap, rdev->desc->enable_reg, + MAX77686_RAMP_RATE_MASK, ramp_value << 6); +} + +static struct regulator_ops max77686_ops = { + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, + .is_enabled = regulator_is_enabled_regmap, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .set_voltage_time_sel = regulator_set_voltage_time_sel, +}; + +static struct regulator_ops max77686_buck_dvs_ops = { + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, + .is_enabled = regulator_is_enabled_regmap, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .set_voltage_time_sel = regulator_set_voltage_time_sel, + .set_ramp_delay = max77686_set_ramp_delay, +}; + +#define regulator_desc_ldo(num) { \ + .name = "LDO"#num, \ + .id = MAX77686_LDO##num, \ + .ops = &max77686_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = MAX77686_LDO_MINUV, \ + .uV_step = MAX77686_LDO_UVSTEP, \ + .ramp_delay = MAX77686_RAMP_DELAY, \ + .n_voltages = MAX77686_VSEL_MASK + 1, \ + .vsel_reg = MAX77686_REG_LDO1CTRL1 + num - 1, \ + .vsel_mask = MAX77686_VSEL_MASK, \ + .enable_reg = MAX77686_REG_LDO1CTRL1 + num - 1, \ + .enable_mask = MAX77686_OPMODE_MASK \ + << MAX77686_OPMODE_SHIFT, \ +} +#define regulator_desc_ldo_low(num) { \ + .name = "LDO"#num, \ + .id = MAX77686_LDO##num, \ + .ops = &max77686_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = MAX77686_LDO_LOW_MINUV, \ + .uV_step = MAX77686_LDO_LOW_UVSTEP, \ + .ramp_delay = MAX77686_RAMP_DELAY, \ + .n_voltages = MAX77686_VSEL_MASK + 1, \ + .vsel_reg = MAX77686_REG_LDO1CTRL1 + num - 1, \ + .vsel_mask = MAX77686_VSEL_MASK, \ + .enable_reg = MAX77686_REG_LDO1CTRL1 + num - 1, \ + .enable_mask = MAX77686_OPMODE_MASK \ + << MAX77686_OPMODE_SHIFT, \ +} +#define regulator_desc_buck(num) { \ + .name = "BUCK"#num, \ + .id = MAX77686_BUCK##num, \ + .ops = &max77686_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = MAX77686_BUCK_MINUV, \ + .uV_step = MAX77686_BUCK_UVSTEP, \ + .ramp_delay = MAX77686_RAMP_DELAY, \ + .n_voltages = MAX77686_VSEL_MASK + 1, \ + .vsel_reg = MAX77686_REG_BUCK5OUT + (num - 5) * 2, \ + .vsel_mask = MAX77686_VSEL_MASK, \ + .enable_reg = MAX77686_REG_BUCK5CTRL + (num - 5) * 2, \ + .enable_mask = MAX77686_OPMODE_MASK, \ +} +#define regulator_desc_buck1(num) { \ + .name = "BUCK"#num, \ + .id = MAX77686_BUCK##num, \ + .ops = &max77686_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = MAX77686_BUCK_MINUV, \ + .uV_step = MAX77686_BUCK_UVSTEP, \ + .ramp_delay = MAX77686_RAMP_DELAY, \ + .n_voltages = MAX77686_VSEL_MASK + 1, \ + .vsel_reg = MAX77686_REG_BUCK1OUT, \ + .vsel_mask = MAX77686_VSEL_MASK, \ + .enable_reg = MAX77686_REG_BUCK1CTRL, \ + .enable_mask = MAX77686_OPMODE_MASK, \ +} +#define regulator_desc_buck_dvs(num) { \ + .name = "BUCK"#num, \ + .id = MAX77686_BUCK##num, \ + .ops = &max77686_buck_dvs_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = MAX77686_DVS_MINUV, \ + .uV_step = MAX77686_DVS_UVSTEP, \ + .ramp_delay = MAX77686_DVS_RAMP_DELAY, \ + .n_voltages = MAX77686_DVS_VSEL_MASK + 1, \ + .vsel_reg = MAX77686_REG_BUCK2DVS1 + (num - 2) * 10, \ + .vsel_mask = MAX77686_DVS_VSEL_MASK, \ + .enable_reg = MAX77686_REG_BUCK2CTRL1 + (num - 2) * 10, \ + .enable_mask = MAX77686_OPMODE_MASK \ + << MAX77686_OPMODE_BUCK234_SHIFT, \ +} + +static struct regulator_desc regulators[] = { + regulator_desc_ldo_low(1), + regulator_desc_ldo_low(2), + regulator_desc_ldo(3), + regulator_desc_ldo(4), + regulator_desc_ldo(5), + regulator_desc_ldo_low(6), + regulator_desc_ldo_low(7), + regulator_desc_ldo_low(8), + regulator_desc_ldo(9), + regulator_desc_ldo(10), + regulator_desc_ldo(11), + regulator_desc_ldo(12), + regulator_desc_ldo(13), + regulator_desc_ldo(14), + regulator_desc_ldo_low(15), + regulator_desc_ldo(16), + regulator_desc_ldo(17), + regulator_desc_ldo(18), + regulator_desc_ldo(19), + regulator_desc_ldo(20), + regulator_desc_ldo(21), + regulator_desc_ldo(22), + regulator_desc_ldo(23), + regulator_desc_ldo(24), + regulator_desc_ldo(25), + regulator_desc_ldo(26), + regulator_desc_buck1(1), + regulator_desc_buck_dvs(2), + regulator_desc_buck_dvs(3), + regulator_desc_buck_dvs(4), + regulator_desc_buck(5), + regulator_desc_buck(6), + regulator_desc_buck(7), + regulator_desc_buck(8), + regulator_desc_buck(9), +}; + +#ifdef CONFIG_OF +static int max77686_pmic_dt_parse_pdata(struct max77686_dev *iodev, + struct max77686_platform_data *pdata) +{ + struct device_node *pmic_np, *regulators_np; + struct max77686_regulator_data *rdata; + struct of_regulator_match rmatch; + unsigned int i; + + pmic_np = iodev->dev->of_node; + regulators_np = of_find_node_by_name(pmic_np, "voltage-regulators"); + if (!regulators_np) { + dev_err(iodev->dev, "could not find regulators sub-node\n"); + return -EINVAL; + } + + pdata->num_regulators = ARRAY_SIZE(regulators); + rdata = devm_kzalloc(iodev->dev, sizeof(*rdata) * + pdata->num_regulators, GFP_KERNEL); + if (!rdata) { + dev_err(iodev->dev, + "could not allocate memory for regulator data\n"); + return -ENOMEM; + } + + for (i = 0; i < pdata->num_regulators; i++) { + rmatch.name = regulators[i].name; + rmatch.init_data = NULL; + rmatch.of_node = NULL; + of_regulator_match(iodev->dev, regulators_np, &rmatch, 1); + rdata[i].initdata = rmatch.init_data; + } + + pdata->regulators = rdata; + + return 0; +} +#else +static int max77686_pmic_dt_parse_pdata(struct max77686_dev *iodev, + struct max77686_platform_data *pdata) +{ + return 0; +} +#endif /* CONFIG_OF */ + +static __devinit int max77686_pmic_probe(struct platform_device *pdev) +{ + struct max77686_dev *iodev = dev_get_drvdata(pdev->dev.parent); + struct max77686_platform_data *pdata = dev_get_platdata(iodev->dev); + struct regulator_dev **rdev; + struct max77686_data *max77686; + int i, size; + int ret = 0; + struct regulator_config config = { }; + + dev_dbg(&pdev->dev, "%s\n", __func__); + + if (!pdata) { + dev_err(&pdev->dev, "no platform data found for regulator\n"); + return -ENODEV; + } + + if (iodev->dev->of_node) { + ret = max77686_pmic_dt_parse_pdata(iodev, pdata); + if (ret) + return ret; + } + + if (pdata->num_regulators != MAX77686_REGULATORS) { + dev_err(&pdev->dev, + "Invalid initial data for regulator's initialiation\n"); + return -EINVAL; + } + + max77686 = devm_kzalloc(&pdev->dev, sizeof(struct max77686_data), + GFP_KERNEL); + if (!max77686) + return -ENOMEM; + + size = sizeof(struct regulator_dev *) * MAX77686_REGULATORS; + max77686->rdev = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + if (!max77686->rdev) + return -ENOMEM; + + rdev = max77686->rdev; + config.dev = &pdev->dev; + config.regmap = iodev->regmap; + platform_set_drvdata(pdev, max77686); + + for (i = 0; i < MAX77686_REGULATORS; i++) { + config.init_data = pdata->regulators[i].initdata; + + rdev[i] = regulator_register(®ulators[i], &config); + if (IS_ERR(rdev[i])) { + ret = PTR_ERR(rdev[i]); + dev_err(&pdev->dev, + "regulator init failed for %d\n", i); + rdev[i] = NULL; + goto err; + } + } + + return 0; +err: + while (--i >= 0) + regulator_unregister(rdev[i]); + return ret; +} + +static int __devexit max77686_pmic_remove(struct platform_device *pdev) +{ + struct max77686_data *max77686 = platform_get_drvdata(pdev); + struct regulator_dev **rdev = max77686->rdev; + int i; + + for (i = 0; i < MAX77686_REGULATORS; i++) + if (rdev[i]) + regulator_unregister(rdev[i]); + + return 0; +} + +static const struct platform_device_id max77686_pmic_id[] = { + {"max77686-pmic", 0}, + { }, +}; +MODULE_DEVICE_TABLE(platform, max77686_pmic_id); + +static struct platform_driver max77686_pmic_driver = { + .driver = { + .name = "max77686-pmic", + .owner = THIS_MODULE, + }, + .probe = max77686_pmic_probe, + .remove = __devexit_p(max77686_pmic_remove), + .id_table = max77686_pmic_id, +}; + +static int __init max77686_pmic_init(void) +{ + return platform_driver_register(&max77686_pmic_driver); +} +subsys_initcall(max77686_pmic_init); + +static void __exit max77686_pmic_cleanup(void) +{ + platform_driver_unregister(&max77686_pmic_driver); +} +module_exit(max77686_pmic_cleanup); + +MODULE_DESCRIPTION("MAXIM 77686 Regulator Driver"); +MODULE_AUTHOR("Chiwoong Byun <woong.byun@samsung.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/regulator/max8952.c b/drivers/regulator/max8952.c index 910c9b26d499..355ca7bad9d5 100644 --- a/drivers/regulator/max8952.c +++ b/drivers/regulator/max8952.c @@ -51,7 +51,6 @@ struct max8952_data { bool vid0; bool vid1; - bool en; }; static int max8952_read_reg(struct max8952_data *max8952, u8 reg) @@ -80,38 +79,6 @@ static int max8952_list_voltage(struct regulator_dev *rdev, return (max8952->pdata->dvs_mode[selector] * 10 + 770) * 1000; } -static int max8952_is_enabled(struct regulator_dev *rdev) -{ - struct max8952_data *max8952 = rdev_get_drvdata(rdev); - return max8952->en; -} - -static int max8952_enable(struct regulator_dev *rdev) -{ - struct max8952_data *max8952 = rdev_get_drvdata(rdev); - - /* If not valid, assume "ALWAYS_HIGH" */ - if (gpio_is_valid(max8952->pdata->gpio_en)) - gpio_set_value(max8952->pdata->gpio_en, 1); - - max8952->en = true; - return 0; -} - -static int max8952_disable(struct regulator_dev *rdev) -{ - struct max8952_data *max8952 = rdev_get_drvdata(rdev); - - /* If not valid, assume "ALWAYS_HIGH" -> not permitted */ - if (gpio_is_valid(max8952->pdata->gpio_en)) - gpio_set_value(max8952->pdata->gpio_en, 0); - else - return -EPERM; - - max8952->en = false; - return 0; -} - static int max8952_get_voltage_sel(struct regulator_dev *rdev) { struct max8952_data *max8952 = rdev_get_drvdata(rdev); @@ -146,12 +113,8 @@ static int max8952_set_voltage_sel(struct regulator_dev *rdev, static struct regulator_ops max8952_ops = { .list_voltage = max8952_list_voltage, - .is_enabled = max8952_is_enabled, - .enable = max8952_enable, - .disable = max8952_disable, .get_voltage_sel = max8952_get_voltage_sel, .set_voltage_sel = max8952_set_voltage_sel, - .set_suspend_disable = max8952_disable, }; static const struct regulator_desc regulator = { @@ -194,6 +157,10 @@ static int __devinit max8952_pmic_probe(struct i2c_client *client, config.init_data = &pdata->reg_data; config.driver_data = max8952; + config.ena_gpio = pdata->gpio_en; + if (pdata->reg_data.constraints.boot_on) + config.ena_gpio_flags |= GPIOF_OUT_INIT_HIGH; + max8952->rdev = regulator_register(®ulator, &config); if (IS_ERR(max8952->rdev)) { @@ -202,27 +169,9 @@ static int __devinit max8952_pmic_probe(struct i2c_client *client, return ret; } - max8952->en = !!(pdata->reg_data.constraints.boot_on); max8952->vid0 = pdata->default_mode & 0x1; max8952->vid1 = (pdata->default_mode >> 1) & 0x1; - if (gpio_is_valid(pdata->gpio_en)) { - if (!gpio_request(pdata->gpio_en, "MAX8952 EN")) - gpio_direction_output(pdata->gpio_en, max8952->en); - else - err = 1; - } else - err = 2; - - if (err) { - dev_info(max8952->dev, "EN gpio invalid: assume that EN" - "is always High\n"); - max8952->en = 1; - pdata->gpio_en = -1; /* Mark invalid */ - } - - err = 0; - if (gpio_is_valid(pdata->gpio_vid0) && gpio_is_valid(pdata->gpio_vid1)) { if (!gpio_request(pdata->gpio_vid0, "MAX8952 VID0")) @@ -308,7 +257,6 @@ static int __devexit max8952_pmic_remove(struct i2c_client *client) gpio_free(pdata->gpio_vid0); gpio_free(pdata->gpio_vid1); - gpio_free(pdata->gpio_en); return 0; } diff --git a/drivers/regulator/max8997.c b/drivers/regulator/max8997.c index 704cd49ef375..e39a0c7260dc 100644 --- a/drivers/regulator/max8997.c +++ b/drivers/regulator/max8997.c @@ -1025,7 +1025,6 @@ static __devinit int max8997_pmic_probe(struct platform_device *pdev) */ if (pdata->buck1_gpiodvs || pdata->buck2_gpiodvs || pdata->buck5_gpiodvs) { - bool gpio1set = false, gpio2set = false; if (!gpio_is_valid(pdata->buck125_gpios[0]) || !gpio_is_valid(pdata->buck125_gpios[1]) || @@ -1035,40 +1034,20 @@ static __devinit int max8997_pmic_probe(struct platform_device *pdev) goto err_out; } - ret = gpio_request(pdata->buck125_gpios[0], - "MAX8997 SET1"); - if (ret == -EBUSY) - dev_warn(&pdev->dev, "Duplicated gpio request" - " on SET1\n"); - else if (ret) + ret = devm_gpio_request(&pdev->dev, pdata->buck125_gpios[0], + "MAX8997 SET1"); + if (ret) goto err_out; - else - gpio1set = true; - - ret = gpio_request(pdata->buck125_gpios[1], - "MAX8997 SET2"); - if (ret == -EBUSY) - dev_warn(&pdev->dev, "Duplicated gpio request" - " on SET2\n"); - else if (ret) { - if (gpio1set) - gpio_free(pdata->buck125_gpios[0]); + + ret = devm_gpio_request(&pdev->dev, pdata->buck125_gpios[1], + "MAX8997 SET2"); + if (ret) goto err_out; - } else - gpio2set = true; - ret = gpio_request(pdata->buck125_gpios[2], + ret = devm_gpio_request(&pdev->dev, pdata->buck125_gpios[2], "MAX8997 SET3"); - if (ret == -EBUSY) - dev_warn(&pdev->dev, "Duplicated gpio request" - " on SET3\n"); - else if (ret) { - if (gpio1set) - gpio_free(pdata->buck125_gpios[0]); - if (gpio2set) - gpio_free(pdata->buck125_gpios[1]); + if (ret) goto err_out; - } gpio_direction_output(pdata->buck125_gpios[0], (max8997->buck125_gpioindex >> 2) @@ -1079,7 +1058,6 @@ static __devinit int max8997_pmic_probe(struct platform_device *pdev) gpio_direction_output(pdata->buck125_gpios[2], (max8997->buck125_gpioindex >> 0) & 0x1); /* SET3 */ - ret = 0; } /* DVS-GPIO disabled */ diff --git a/drivers/regulator/max8998.c b/drivers/regulator/max8998.c index 18bb58b9b96e..5dfa920ff0c8 100644 --- a/drivers/regulator/max8998.c +++ b/drivers/regulator/max8998.c @@ -111,27 +111,6 @@ static const struct voltage_map_desc *ldo_voltage_map[] = { &buck4_voltage_map_desc, /* BUCK4 */ }; -static int max8998_list_voltage(struct regulator_dev *rdev, - unsigned int selector) -{ - const struct voltage_map_desc *desc; - int ldo = rdev_get_id(rdev); - int val; - - if (ldo >= ARRAY_SIZE(ldo_voltage_map)) - return -EINVAL; - - desc = ldo_voltage_map[ldo]; - if (desc == NULL) - return -EINVAL; - - val = desc->min + desc->step * selector; - if (val > desc->max) - return -EINVAL; - - return val * 1000; -} - static int max8998_get_enable_register(struct regulator_dev *rdev, int *reg, int *shift) { @@ -297,41 +276,18 @@ static int max8998_get_voltage_sel(struct regulator_dev *rdev) return val; } -static int max8998_set_voltage_ldo(struct regulator_dev *rdev, - int min_uV, int max_uV, unsigned *selector) +static int max8998_set_voltage_ldo_sel(struct regulator_dev *rdev, + unsigned selector) { struct max8998_data *max8998 = rdev_get_drvdata(rdev); struct i2c_client *i2c = max8998->iodev->i2c; - int min_vol = min_uV / 1000, max_vol = max_uV / 1000; - const struct voltage_map_desc *desc; - int ldo = rdev_get_id(rdev); - int reg, shift = 0, mask, ret, i; - - if (ldo >= ARRAY_SIZE(ldo_voltage_map)) - return -EINVAL; - - desc = ldo_voltage_map[ldo]; - if (desc == NULL) - return -EINVAL; - - if (max_vol < desc->min || min_vol > desc->max) - return -EINVAL; - - if (min_vol < desc->min) - min_vol = desc->min; - - i = DIV_ROUND_UP(min_vol - desc->min, desc->step); - - if (desc->min + desc->step*i > max_vol) - return -EINVAL; - - *selector = i; + int reg, shift = 0, mask, ret; ret = max8998_get_voltage_register(rdev, ®, &shift, &mask); if (ret) return ret; - ret = max8998_update_reg(i2c, reg, i<<shift, mask<<shift); + ret = max8998_update_reg(i2c, reg, selector<<shift, mask<<shift); return ret; } @@ -347,41 +303,18 @@ static inline void buck2_gpio_set(int gpio, int v) gpio_set_value(gpio, v & 0x1); } -static int max8998_set_voltage_buck(struct regulator_dev *rdev, - int min_uV, int max_uV, unsigned *selector) +static int max8998_set_voltage_buck_sel(struct regulator_dev *rdev, + unsigned selector) { struct max8998_data *max8998 = rdev_get_drvdata(rdev); struct max8998_platform_data *pdata = dev_get_platdata(max8998->iodev->dev); struct i2c_client *i2c = max8998->iodev->i2c; - int min_vol = min_uV / 1000, max_vol = max_uV / 1000; - const struct voltage_map_desc *desc; int buck = rdev_get_id(rdev); int reg, shift = 0, mask, ret; - int i, j, previous_sel; + int j, previous_sel; static u8 buck1_last_val; - if (buck >= ARRAY_SIZE(ldo_voltage_map)) - return -EINVAL; - - desc = ldo_voltage_map[buck]; - - if (desc == NULL) - return -EINVAL; - - if (max_vol < desc->min || min_vol > desc->max) - return -EINVAL; - - if (min_vol < desc->min) - min_vol = desc->min; - - i = DIV_ROUND_UP(min_vol - desc->min, desc->step); - - if (desc->min + desc->step*i > max_vol) - return -EINVAL; - - *selector = i; - ret = max8998_get_voltage_register(rdev, ®, &shift, &mask); if (ret) return ret; @@ -390,19 +323,19 @@ static int max8998_set_voltage_buck(struct regulator_dev *rdev, /* Check if voltage needs to be changed */ /* if previous_voltage equal new voltage, return */ - if (previous_sel == i) { + if (previous_sel == selector) { dev_dbg(max8998->dev, "No voltage change, old:%d, new:%d\n", - max8998_list_voltage(rdev, previous_sel), - max8998_list_voltage(rdev, i)); + regulator_list_voltage_linear(rdev, previous_sel), + regulator_list_voltage_linear(rdev, selector)); return ret; } switch (buck) { case MAX8998_BUCK1: dev_dbg(max8998->dev, - "BUCK1, i:%d, buck1_vol1:%d, buck1_vol2:%d\n" + "BUCK1, selector:%d, buck1_vol1:%d, buck1_vol2:%d\n" "buck1_vol3:%d, buck1_vol4:%d\n", - i, max8998->buck1_vol[0], max8998->buck1_vol[1], + selector, max8998->buck1_vol[0], max8998->buck1_vol[1], max8998->buck1_vol[2], max8998->buck1_vol[3]); if (gpio_is_valid(pdata->buck1_set1) && @@ -411,7 +344,7 @@ static int max8998_set_voltage_buck(struct regulator_dev *rdev, /* check if requested voltage */ /* value is already defined */ for (j = 0; j < ARRAY_SIZE(max8998->buck1_vol); j++) { - if (max8998->buck1_vol[j] == i) { + if (max8998->buck1_vol[j] == selector) { max8998->buck1_idx = j; buck1_gpio_set(pdata->buck1_set1, pdata->buck1_set2, j); @@ -426,11 +359,11 @@ static int max8998_set_voltage_buck(struct regulator_dev *rdev, max8998->buck1_idx = (buck1_last_val % 2) + 2; dev_dbg(max8998->dev, "max8998->buck1_idx:%d\n", max8998->buck1_idx); - max8998->buck1_vol[max8998->buck1_idx] = i; + max8998->buck1_vol[max8998->buck1_idx] = selector; ret = max8998_get_voltage_register(rdev, ®, &shift, &mask); - ret = max8998_write_reg(i2c, reg, i); + ret = max8998_write_reg(i2c, reg, selector); buck1_gpio_set(pdata->buck1_set1, pdata->buck1_set2, max8998->buck1_idx); buck1_last_val++; @@ -440,20 +373,20 @@ buck1_exit: gpio_get_value(pdata->buck1_set2)); break; } else { - ret = max8998_write_reg(i2c, reg, i); + ret = max8998_write_reg(i2c, reg, selector); } break; case MAX8998_BUCK2: dev_dbg(max8998->dev, - "BUCK2, i:%d buck2_vol1:%d, buck2_vol2:%d\n" - , i, max8998->buck2_vol[0], max8998->buck2_vol[1]); + "BUCK2, selector:%d buck2_vol1:%d, buck2_vol2:%d\n", + selector, max8998->buck2_vol[0], max8998->buck2_vol[1]); if (gpio_is_valid(pdata->buck2_set3)) { /* check if requested voltage */ /* value is already defined */ for (j = 0; j < ARRAY_SIZE(max8998->buck2_vol); j++) { - if (max8998->buck2_vol[j] == i) { + if (max8998->buck2_vol[j] == selector) { max8998->buck2_idx = j; buck2_gpio_set(pdata->buck2_set3, j); goto buck2_exit; @@ -465,20 +398,21 @@ buck1_exit: max8998_get_voltage_register(rdev, ®, &shift, &mask); - ret = max8998_write_reg(i2c, reg, i); - max8998->buck2_vol[max8998->buck2_idx] = i; + ret = max8998_write_reg(i2c, reg, selector); + max8998->buck2_vol[max8998->buck2_idx] = selector; buck2_gpio_set(pdata->buck2_set3, max8998->buck2_idx); buck2_exit: dev_dbg(max8998->dev, "%s: SET3:%d\n", i2c->name, gpio_get_value(pdata->buck2_set3)); } else { - ret = max8998_write_reg(i2c, reg, i); + ret = max8998_write_reg(i2c, reg, selector); } break; case MAX8998_BUCK3: case MAX8998_BUCK4: - ret = max8998_update_reg(i2c, reg, i<<shift, mask<<shift); + ret = max8998_update_reg(i2c, reg, selector<<shift, + mask<<shift); break; } @@ -519,34 +453,30 @@ static int max8998_set_voltage_buck_time_sel(struct regulator_dev *rdev, } static struct regulator_ops max8998_ldo_ops = { - .list_voltage = max8998_list_voltage, + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, .is_enabled = max8998_ldo_is_enabled, .enable = max8998_ldo_enable, .disable = max8998_ldo_disable, .get_voltage_sel = max8998_get_voltage_sel, - .set_voltage = max8998_set_voltage_ldo, - .set_suspend_enable = max8998_ldo_enable, - .set_suspend_disable = max8998_ldo_disable, + .set_voltage_sel = max8998_set_voltage_ldo_sel, }; static struct regulator_ops max8998_buck_ops = { - .list_voltage = max8998_list_voltage, + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, .is_enabled = max8998_ldo_is_enabled, .enable = max8998_ldo_enable, .disable = max8998_ldo_disable, .get_voltage_sel = max8998_get_voltage_sel, - .set_voltage = max8998_set_voltage_buck, + .set_voltage_sel = max8998_set_voltage_buck_sel, .set_voltage_time_sel = max8998_set_voltage_buck_time_sel, - .set_suspend_enable = max8998_ldo_enable, - .set_suspend_disable = max8998_ldo_disable, }; static struct regulator_ops max8998_others_ops = { .is_enabled = max8998_ldo_is_enabled, .enable = max8998_ldo_enable, .disable = max8998_ldo_disable, - .set_suspend_enable = max8998_ldo_enable, - .set_suspend_disable = max8998_ldo_disable, }; static struct regulator_desc regulators[] = { @@ -860,7 +790,10 @@ static __devinit int max8998_pmic_probe(struct platform_device *pdev) desc = ldo_voltage_map[id]; if (desc && regulators[index].ops != &max8998_others_ops) { int count = (desc->max - desc->min) / desc->step + 1; + regulators[index].n_voltages = count; + regulators[index].min_uV = desc->min * 1000; + regulators[index].uV_step = desc->step * 1000; } config.dev = max8998->dev; diff --git a/drivers/regulator/mc13783-regulator.c b/drivers/regulator/mc13783-regulator.c index 7dcdfa283e93..4932e3449fe1 100644 --- a/drivers/regulator/mc13783-regulator.c +++ b/drivers/regulator/mc13783-regulator.c @@ -93,78 +93,78 @@ /* Voltage Values */ -static const int mc13783_sw3_val[] = { +static const unsigned int mc13783_sw3_val[] = { 5000000, 5000000, 5000000, 5500000, }; -static const int mc13783_vaudio_val[] = { +static const unsigned int mc13783_vaudio_val[] = { 2775000, }; -static const int mc13783_viohi_val[] = { +static const unsigned int mc13783_viohi_val[] = { 2775000, }; -static const int mc13783_violo_val[] = { +static const unsigned int mc13783_violo_val[] = { 1200000, 1300000, 1500000, 1800000, }; -static const int mc13783_vdig_val[] = { +static const unsigned int mc13783_vdig_val[] = { 1200000, 1300000, 1500000, 1800000, }; -static const int mc13783_vgen_val[] = { +static const unsigned int mc13783_vgen_val[] = { 1200000, 1300000, 1500000, 1800000, 1100000, 2000000, 2775000, 2400000, }; -static const int mc13783_vrfdig_val[] = { +static const unsigned int mc13783_vrfdig_val[] = { 1200000, 1500000, 1800000, 1875000, }; -static const int mc13783_vrfref_val[] = { +static const unsigned int mc13783_vrfref_val[] = { 2475000, 2600000, 2700000, 2775000, }; -static const int mc13783_vrfcp_val[] = { +static const unsigned int mc13783_vrfcp_val[] = { 2700000, 2775000, }; -static const int mc13783_vsim_val[] = { +static const unsigned int mc13783_vsim_val[] = { 1800000, 2900000, 3000000, }; -static const int mc13783_vesim_val[] = { +static const unsigned int mc13783_vesim_val[] = { 1800000, 2900000, }; -static const int mc13783_vcam_val[] = { +static const unsigned int mc13783_vcam_val[] = { 1500000, 1800000, 2500000, 2550000, 2600000, 2750000, 2800000, 3000000, }; -static const int mc13783_vrfbg_val[] = { +static const unsigned int mc13783_vrfbg_val[] = { 1250000, }; -static const int mc13783_vvib_val[] = { +static const unsigned int mc13783_vvib_val[] = { 1300000, 1800000, 2000000, 3000000, }; -static const int mc13783_vmmc_val[] = { +static const unsigned int mc13783_vmmc_val[] = { 1600000, 1800000, 2000000, 2600000, 2700000, 2800000, 2900000, 3000000, }; -static const int mc13783_vrf_val[] = { +static const unsigned int mc13783_vrf_val[] = { 1500000, 1875000, 2700000, 2775000, }; -static const int mc13783_gpo_val[] = { +static const unsigned int mc13783_gpo_val[] = { 3100000, }; -static const int mc13783_pwgtdrv_val[] = { +static const unsigned int mc13783_pwgtdrv_val[] = { 5500000, }; @@ -328,7 +328,7 @@ static struct regulator_ops mc13783_gpo_regulator_ops = { .enable = mc13783_gpo_regulator_enable, .disable = mc13783_gpo_regulator_disable, .is_enabled = mc13783_gpo_regulator_is_enabled, - .list_voltage = mc13xxx_regulator_list_voltage, + .list_voltage = regulator_list_voltage_table, .set_voltage = mc13xxx_fixed_regulator_set_voltage, .get_voltage = mc13xxx_fixed_regulator_get_voltage, }; diff --git a/drivers/regulator/mc13892-regulator.c b/drivers/regulator/mc13892-regulator.c index 970a233dbe46..b388b746452e 100644 --- a/drivers/regulator/mc13892-regulator.c +++ b/drivers/regulator/mc13892-regulator.c @@ -150,12 +150,12 @@ #define MC13892_USB1 50 #define MC13892_USB1_VUSBEN (1<<3) -static const int mc13892_vcoincell[] = { +static const unsigned int mc13892_vcoincell[] = { 2500000, 2700000, 2800000, 2900000, 3000000, 3100000, 3200000, 3300000, }; -static const int mc13892_sw1[] = { +static const unsigned int mc13892_sw1[] = { 600000, 625000, 650000, 675000, 700000, 725000, 750000, 775000, 800000, 825000, 850000, 875000, 900000, 925000, 950000, 975000, 1000000, 1025000, @@ -164,7 +164,7 @@ static const int mc13892_sw1[] = { 1350000, 1375000 }; -static const int mc13892_sw[] = { +static const unsigned int mc13892_sw[] = { 600000, 625000, 650000, 675000, 700000, 725000, 750000, 775000, 800000, 825000, 850000, 875000, 900000, 925000, 950000, 975000, 1000000, 1025000, @@ -176,65 +176,65 @@ static const int mc13892_sw[] = { 1800000, 1825000, 1850000, 1875000 }; -static const int mc13892_swbst[] = { +static const unsigned int mc13892_swbst[] = { 5000000, }; -static const int mc13892_viohi[] = { +static const unsigned int mc13892_viohi[] = { 2775000, }; -static const int mc13892_vpll[] = { +static const unsigned int mc13892_vpll[] = { 1050000, 1250000, 1650000, 1800000, }; -static const int mc13892_vdig[] = { +static const unsigned int mc13892_vdig[] = { 1050000, 1250000, 1650000, 1800000, }; -static const int mc13892_vsd[] = { +static const unsigned int mc13892_vsd[] = { 1800000, 2000000, 2600000, 2700000, 2800000, 2900000, 3000000, 3150000, }; -static const int mc13892_vusb2[] = { +static const unsigned int mc13892_vusb2[] = { 2400000, 2600000, 2700000, 2775000, }; -static const int mc13892_vvideo[] = { +static const unsigned int mc13892_vvideo[] = { 2700000, 2775000, 2500000, 2600000, }; -static const int mc13892_vaudio[] = { +static const unsigned int mc13892_vaudio[] = { 2300000, 2500000, 2775000, 3000000, }; -static const int mc13892_vcam[] = { +static const unsigned int mc13892_vcam[] = { 2500000, 2600000, 2750000, 3000000, }; -static const int mc13892_vgen1[] = { +static const unsigned int mc13892_vgen1[] = { 1200000, 1500000, 2775000, 3150000, }; -static const int mc13892_vgen2[] = { +static const unsigned int mc13892_vgen2[] = { 1200000, 1500000, 1600000, 1800000, 2700000, 2800000, 3000000, 3150000, }; -static const int mc13892_vgen3[] = { +static const unsigned int mc13892_vgen3[] = { 1800000, 2900000, }; -static const int mc13892_vusb[] = { +static const unsigned int mc13892_vusb[] = { 3300000, }; -static const int mc13892_gpo[] = { +static const unsigned int mc13892_gpo[] = { 2750000, }; -static const int mc13892_pwgtdrv[] = { +static const unsigned int mc13892_pwgtdrv[] = { 5000000, }; @@ -394,7 +394,7 @@ static struct regulator_ops mc13892_gpo_regulator_ops = { .enable = mc13892_gpo_regulator_enable, .disable = mc13892_gpo_regulator_disable, .is_enabled = mc13892_gpo_regulator_is_enabled, - .list_voltage = mc13xxx_regulator_list_voltage, + .list_voltage = regulator_list_voltage_table, .set_voltage = mc13xxx_fixed_regulator_set_voltage, .get_voltage = mc13xxx_fixed_regulator_get_voltage, }; @@ -436,7 +436,7 @@ static int mc13892_sw_regulator_set_voltage_sel(struct regulator_dev *rdev, u32 valread; int ret; - value = mc13892_regulators[id].voltages[selector]; + value = rdev->desc->volt_table[selector]; mc13xxx_lock(priv->mc13xxx); ret = mc13xxx_reg_read(priv->mc13xxx, @@ -469,8 +469,7 @@ err: } static struct regulator_ops mc13892_sw_regulator_ops = { - .is_enabled = mc13xxx_sw_regulator_is_enabled, - .list_voltage = mc13xxx_regulator_list_voltage, + .list_voltage = regulator_list_voltage_table, .set_voltage_sel = mc13892_sw_regulator_set_voltage_sel, .get_voltage = mc13892_sw_regulator_get_voltage, }; diff --git a/drivers/regulator/mc13xxx-regulator-core.c b/drivers/regulator/mc13xxx-regulator-core.c index 4fa9704739bc..d6eda28ca5d0 100644 --- a/drivers/regulator/mc13xxx-regulator-core.c +++ b/drivers/regulator/mc13xxx-regulator-core.c @@ -80,20 +80,6 @@ static int mc13xxx_regulator_is_enabled(struct regulator_dev *rdev) return (val & mc13xxx_regulators[id].enable_bit) != 0; } -int mc13xxx_regulator_list_voltage(struct regulator_dev *rdev, - unsigned selector) -{ - int id = rdev_get_id(rdev); - struct mc13xxx_regulator_priv *priv = rdev_get_drvdata(rdev); - struct mc13xxx_regulator *mc13xxx_regulators = priv->mc13xxx_regulators; - - if (selector >= mc13xxx_regulators[id].desc.n_voltages) - return -EINVAL; - - return mc13xxx_regulators[id].voltages[selector]; -} -EXPORT_SYMBOL_GPL(mc13xxx_regulator_list_voltage); - static int mc13xxx_regulator_set_voltage_sel(struct regulator_dev *rdev, unsigned selector) { @@ -135,14 +121,14 @@ static int mc13xxx_regulator_get_voltage(struct regulator_dev *rdev) BUG_ON(val >= mc13xxx_regulators[id].desc.n_voltages); - return mc13xxx_regulators[id].voltages[val]; + return rdev->desc->volt_table[val]; } struct regulator_ops mc13xxx_regulator_ops = { .enable = mc13xxx_regulator_enable, .disable = mc13xxx_regulator_disable, .is_enabled = mc13xxx_regulator_is_enabled, - .list_voltage = mc13xxx_regulator_list_voltage, + .list_voltage = regulator_list_voltage_table, .set_voltage_sel = mc13xxx_regulator_set_voltage_sel, .get_voltage = mc13xxx_regulator_get_voltage, }; @@ -151,15 +137,13 @@ EXPORT_SYMBOL_GPL(mc13xxx_regulator_ops); int mc13xxx_fixed_regulator_set_voltage(struct regulator_dev *rdev, int min_uV, int max_uV, unsigned *selector) { - struct mc13xxx_regulator_priv *priv = rdev_get_drvdata(rdev); - struct mc13xxx_regulator *mc13xxx_regulators = priv->mc13xxx_regulators; int id = rdev_get_id(rdev); dev_dbg(rdev_get_dev(rdev), "%s id: %d min_uV: %d max_uV: %d\n", __func__, id, min_uV, max_uV); - if (min_uV >= mc13xxx_regulators[id].voltages[0] && - max_uV <= mc13xxx_regulators[id].voltages[0]) + if (min_uV <= rdev->desc->volt_table[0] && + rdev->desc->volt_table[0] <= max_uV) return 0; else return -EINVAL; @@ -168,13 +152,11 @@ EXPORT_SYMBOL_GPL(mc13xxx_fixed_regulator_set_voltage); int mc13xxx_fixed_regulator_get_voltage(struct regulator_dev *rdev) { - struct mc13xxx_regulator_priv *priv = rdev_get_drvdata(rdev); - struct mc13xxx_regulator *mc13xxx_regulators = priv->mc13xxx_regulators; int id = rdev_get_id(rdev); dev_dbg(rdev_get_dev(rdev), "%s id: %d\n", __func__, id); - return mc13xxx_regulators[id].voltages[0]; + return rdev->desc->volt_table[0]; } EXPORT_SYMBOL_GPL(mc13xxx_fixed_regulator_get_voltage); @@ -182,18 +164,12 @@ struct regulator_ops mc13xxx_fixed_regulator_ops = { .enable = mc13xxx_regulator_enable, .disable = mc13xxx_regulator_disable, .is_enabled = mc13xxx_regulator_is_enabled, - .list_voltage = mc13xxx_regulator_list_voltage, + .list_voltage = regulator_list_voltage_table, .set_voltage = mc13xxx_fixed_regulator_set_voltage, .get_voltage = mc13xxx_fixed_regulator_get_voltage, }; EXPORT_SYMBOL_GPL(mc13xxx_fixed_regulator_ops); -int mc13xxx_sw_regulator_is_enabled(struct regulator_dev *rdev) -{ - return 1; -} -EXPORT_SYMBOL_GPL(mc13xxx_sw_regulator_is_enabled); - #ifdef CONFIG_OF int __devinit mc13xxx_get_num_regulators_dt(struct platform_device *pdev) { diff --git a/drivers/regulator/mc13xxx.h b/drivers/regulator/mc13xxx.h index 044aba4d28ec..eaff5510b6df 100644 --- a/drivers/regulator/mc13xxx.h +++ b/drivers/regulator/mc13xxx.h @@ -22,7 +22,6 @@ struct mc13xxx_regulator { int vsel_shift; int vsel_mask; int hi_bit; - int const *voltages; }; struct mc13xxx_regulator_priv { @@ -33,10 +32,6 @@ struct mc13xxx_regulator_priv { struct regulator_dev *regulators[]; }; -extern int mc13xxx_sw_regulator(struct regulator_dev *rdev); -extern int mc13xxx_sw_regulator_is_enabled(struct regulator_dev *rdev); -extern int mc13xxx_regulator_list_voltage(struct regulator_dev *rdev, - unsigned selector); extern int mc13xxx_fixed_regulator_set_voltage(struct regulator_dev *rdev, int min_uV, int max_uV, unsigned *selector); extern int mc13xxx_fixed_regulator_get_voltage(struct regulator_dev *rdev); @@ -68,6 +63,7 @@ extern struct regulator_ops mc13xxx_fixed_regulator_ops; .desc = { \ .name = #_name, \ .n_voltages = ARRAY_SIZE(_voltages), \ + .volt_table = _voltages, \ .ops = &_ops, \ .type = REGULATOR_VOLTAGE, \ .id = prefix ## _name, \ @@ -78,7 +74,6 @@ extern struct regulator_ops mc13xxx_fixed_regulator_ops; .vsel_reg = prefix ## _vsel_reg, \ .vsel_shift = prefix ## _vsel_reg ## _ ## _name ## VSEL,\ .vsel_mask = prefix ## _vsel_reg ## _ ## _name ## VSEL_M,\ - .voltages = _voltages, \ } #define MC13xxx_FIXED_DEFINE(prefix, _name, _reg, _voltages, _ops) \ @@ -86,6 +81,7 @@ extern struct regulator_ops mc13xxx_fixed_regulator_ops; .desc = { \ .name = #_name, \ .n_voltages = ARRAY_SIZE(_voltages), \ + .volt_table = _voltages, \ .ops = &_ops, \ .type = REGULATOR_VOLTAGE, \ .id = prefix ## _name, \ @@ -93,7 +89,6 @@ extern struct regulator_ops mc13xxx_fixed_regulator_ops; }, \ .reg = prefix ## _reg, \ .enable_bit = prefix ## _reg ## _ ## _name ## EN, \ - .voltages = _voltages, \ } #define MC13xxx_GPO_DEFINE(prefix, _name, _reg, _voltages, _ops) \ @@ -101,6 +96,7 @@ extern struct regulator_ops mc13xxx_fixed_regulator_ops; .desc = { \ .name = #_name, \ .n_voltages = ARRAY_SIZE(_voltages), \ + .volt_table = _voltages, \ .ops = &_ops, \ .type = REGULATOR_VOLTAGE, \ .id = prefix ## _name, \ @@ -108,7 +104,6 @@ extern struct regulator_ops mc13xxx_fixed_regulator_ops; }, \ .reg = prefix ## _reg, \ .enable_bit = prefix ## _reg ## _ ## _name ## EN, \ - .voltages = _voltages, \ } #define MC13xxx_DEFINE_SW(_name, _reg, _vsel_reg, _voltages, ops) \ diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c index 56593b75168a..3e4106f2bda9 100644 --- a/drivers/regulator/of_regulator.c +++ b/drivers/regulator/of_regulator.c @@ -20,7 +20,7 @@ static void of_get_regulation_constraints(struct device_node *np, struct regulator_init_data **init_data) { const __be32 *min_uV, *max_uV, *uV_offset; - const __be32 *min_uA, *max_uA; + const __be32 *min_uA, *max_uA, *ramp_delay; struct regulation_constraints *constraints = &(*init_data)->constraints; constraints->name = of_get_property(np, "regulator-name", NULL); @@ -60,6 +60,10 @@ static void of_get_regulation_constraints(struct device_node *np, constraints->always_on = true; else /* status change should be possible if not always on. */ constraints->valid_ops_mask |= REGULATOR_CHANGE_STATUS; + + ramp_delay = of_get_property(np, "regulator-ramp-delay", NULL); + if (ramp_delay) + constraints->ramp_delay = be32_to_cpu(*ramp_delay); } /** @@ -88,15 +92,17 @@ struct regulator_init_data *of_get_regulator_init_data(struct device *dev, EXPORT_SYMBOL_GPL(of_get_regulator_init_data); /** - * of_regulator_match - extract regulator init data + * of_regulator_match - extract regulator init data when node + * property "regulator-compatible" matches with the regulator name. * @dev: device requesting the data * @node: parent device node of the regulators * @matches: match table for the regulators * @num_matches: number of entries in match table * * This function uses a match table specified by the regulator driver and - * looks up the corresponding init data in the device tree. Note that the - * match table is modified in place. + * looks up the corresponding init data in the device tree if + * regulator-compatible matches. Note that the match table is modified + * in place. * * Returns the number of matches found or a negative error code on failure. */ @@ -106,27 +112,40 @@ int of_regulator_match(struct device *dev, struct device_node *node, { unsigned int count = 0; unsigned int i; + const char *regulator_comp; + struct device_node *child; if (!dev || !node) return -EINVAL; - for (i = 0; i < num_matches; i++) { - struct of_regulator_match *match = &matches[i]; - struct device_node *child; - - child = of_find_node_by_name(node, match->name); - if (!child) - continue; - - match->init_data = of_get_regulator_init_data(dev, child); - if (!match->init_data) { - dev_err(dev, "failed to parse DT for regulator %s\n", + for_each_child_of_node(node, child) { + regulator_comp = of_get_property(child, + "regulator-compatible", NULL); + if (!regulator_comp) { + dev_err(dev, "regulator-compatible is missing for node %s\n", child->name); - return -EINVAL; + continue; + } + for (i = 0; i < num_matches; i++) { + struct of_regulator_match *match = &matches[i]; + if (match->of_node) + continue; + + if (strcmp(match->name, regulator_comp)) + continue; + + match->init_data = + of_get_regulator_init_data(dev, child); + if (!match->init_data) { + dev_err(dev, + "failed to parse DT for regulator %s\n", + child->name); + return -EINVAL; + } + match->of_node = child; + count++; + break; } - - match->of_node = child; - count++; } return count; diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c index 795f75a6ac33..17d19fbbc490 100644 --- a/drivers/regulator/palmas-regulator.c +++ b/drivers/regulator/palmas-regulator.c @@ -257,8 +257,7 @@ static int palmas_set_mode_smps(struct regulator_dev *dev, unsigned int mode) unsigned int reg; palmas_smps_read(pmic->palmas, palmas_regs_info[id].ctrl_addr, ®); - reg &= ~PALMAS_SMPS12_CTRL_STATUS_MASK; - reg >>= PALMAS_SMPS12_CTRL_STATUS_SHIFT; + reg &= ~PALMAS_SMPS12_CTRL_MODE_ACTIVE_MASK; switch (mode) { case REGULATOR_MODE_NORMAL: @@ -374,11 +373,22 @@ static int palmas_set_voltage_smps_sel(struct regulator_dev *dev, static int palmas_map_voltage_smps(struct regulator_dev *rdev, int min_uV, int max_uV) { + struct palmas_pmic *pmic = rdev_get_drvdata(rdev); + int id = rdev_get_id(rdev); int ret, voltage; - ret = ((min_uV - 500000) / 10000) + 1; - if (ret < 0) - return ret; + if (min_uV == 0) + return 0; + + if (pmic->range[id]) { /* RANGE is x2 */ + if (min_uV < 1000000) + min_uV = 1000000; + ret = DIV_ROUND_UP(min_uV - 1000000, 20000) + 1; + } else { /* RANGE is x1 */ + if (min_uV < 500000) + min_uV = 500000; + ret = DIV_ROUND_UP(min_uV - 500000, 10000) + 1; + } /* Map back into a voltage to verify we're still in bounds */ voltage = palmas_list_voltage_smps(rdev, ret); @@ -400,19 +410,14 @@ static struct regulator_ops palmas_ops_smps = { .map_voltage = palmas_map_voltage_smps, }; -static int palmas_list_voltage_smps10(struct regulator_dev *dev, - unsigned selector) -{ - return 3750000 + (selector * 1250000); -} - static struct regulator_ops palmas_ops_smps10 = { .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_sel = regulator_set_voltage_sel_regmap, - .list_voltage = palmas_list_voltage_smps10, + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, }; static int palmas_is_enabled_ldo(struct regulator_dev *dev) @@ -522,7 +527,15 @@ static int palmas_smps_init(struct palmas *palmas, int id, if (ret) return ret; - if (id != PALMAS_REG_SMPS10) { + switch (id) { + case PALMAS_REG_SMPS10: + if (reg_init->mode_sleep) { + reg &= ~PALMAS_SMPS10_CTRL_MODE_SLEEP_MASK; + reg |= reg_init->mode_sleep << + PALMAS_SMPS10_CTRL_MODE_SLEEP_SHIFT; + } + break; + default: if (reg_init->warm_reset) reg |= PALMAS_SMPS12_CTRL_WR_S; @@ -534,14 +547,8 @@ static int palmas_smps_init(struct palmas *palmas, int id, reg |= reg_init->mode_sleep << PALMAS_SMPS12_CTRL_MODE_SLEEP_SHIFT; } - } else { - if (reg_init->mode_sleep) { - reg &= ~PALMAS_SMPS10_CTRL_MODE_SLEEP_MASK; - reg |= reg_init->mode_sleep << - PALMAS_SMPS10_CTRL_MODE_SLEEP_SHIFT; - } - } + ret = palmas_smps_write(palmas, addr, reg); if (ret) return ret; @@ -665,10 +672,8 @@ static __devinit int palmas_probe(struct platform_device *pdev) pmic->desc[id].name = palmas_regs_info[id].name; pmic->desc[id].id = id; - if (id != PALMAS_REG_SMPS10) { - pmic->desc[id].ops = &palmas_ops_smps; - pmic->desc[id].n_voltages = PALMAS_SMPS_NUM_VOLTAGES; - } else { + switch (id) { + case PALMAS_REG_SMPS10: pmic->desc[id].n_voltages = PALMAS_SMPS10_NUM_VOLTAGES; pmic->desc[id].ops = &palmas_ops_smps10; pmic->desc[id].vsel_reg = PALMAS_SMPS10_CTRL; @@ -677,6 +682,12 @@ static __devinit int palmas_probe(struct platform_device *pdev) PALMAS_BASE_TO_REG(PALMAS_SMPS_BASE, PALMAS_SMPS10_STATUS); pmic->desc[id].enable_mask = SMPS10_BOOST_EN; + pmic->desc[id].min_uV = 3750000; + pmic->desc[id].uV_step = 1250000; + break; + default: + pmic->desc[id].ops = &palmas_ops_smps; + pmic->desc[id].n_voltages = PALMAS_SMPS_NUM_VOLTAGES; } pmic->desc[id].type = REGULATOR_VOLTAGE; diff --git a/drivers/regulator/pcap-regulator.c b/drivers/regulator/pcap-regulator.c index 8211101121f0..68777acc099f 100644 --- a/drivers/regulator/pcap-regulator.c +++ b/drivers/regulator/pcap-regulator.c @@ -18,80 +18,80 @@ #include <linux/regulator/machine.h> #include <linux/mfd/ezx-pcap.h> -static const u16 V1_table[] = { - 2775, 1275, 1600, 1725, 1825, 1925, 2075, 2275, +static const unsigned int V1_table[] = { + 2775000, 1275000, 1600000, 1725000, 1825000, 1925000, 2075000, 2275000, }; -static const u16 V2_table[] = { - 2500, 2775, +static const unsigned int V2_table[] = { + 2500000, 2775000, }; -static const u16 V3_table[] = { - 1075, 1275, 1550, 1725, 1876, 1950, 2075, 2275, +static const unsigned int V3_table[] = { + 1075000, 1275000, 1550000, 1725000, 1876000, 1950000, 2075000, 2275000, }; -static const u16 V4_table[] = { - 1275, 1550, 1725, 1875, 1950, 2075, 2275, 2775, +static const unsigned int V4_table[] = { + 1275000, 1550000, 1725000, 1875000, 1950000, 2075000, 2275000, 2775000, }; -static const u16 V5_table[] = { - 1875, 2275, 2475, 2775, +static const unsigned int V5_table[] = { + 1875000, 2275000, 2475000, 2775000, }; -static const u16 V6_table[] = { - 2475, 2775, +static const unsigned int V6_table[] = { + 2475000, 2775000, }; -static const u16 V7_table[] = { - 1875, 2775, +static const unsigned int V7_table[] = { + 1875000, 2775000, }; #define V8_table V4_table -static const u16 V9_table[] = { - 1575, 1875, 2475, 2775, +static const unsigned int V9_table[] = { + 1575000, 1875000, 2475000, 2775000, }; -static const u16 V10_table[] = { - 5000, +static const unsigned int V10_table[] = { + 5000000, }; -static const u16 VAUX1_table[] = { - 1875, 2475, 2775, 3000, +static const unsigned int VAUX1_table[] = { + 1875000, 2475000, 2775000, 3000000, }; #define VAUX2_table VAUX1_table -static const u16 VAUX3_table[] = { - 1200, 1200, 1200, 1200, 1400, 1600, 1800, 2000, - 2200, 2400, 2600, 2800, 3000, 3200, 3400, 3600, +static const unsigned int VAUX3_table[] = { + 1200000, 1200000, 1200000, 1200000, 1400000, 1600000, 1800000, 2000000, + 2200000, 2400000, 2600000, 2800000, 3000000, 3200000, 3400000, 3600000, }; -static const u16 VAUX4_table[] = { - 1800, 1800, 3000, 5000, +static const unsigned int VAUX4_table[] = { + 1800000, 1800000, 3000000, 5000000, }; -static const u16 VSIM_table[] = { - 1875, 3000, +static const unsigned int VSIM_table[] = { + 1875000, 3000000, }; -static const u16 VSIM2_table[] = { - 1875, +static const unsigned int VSIM2_table[] = { + 1875000, }; -static const u16 VVIB_table[] = { - 1300, 1800, 2000, 3000, +static const unsigned int VVIB_table[] = { + 1300000, 1800000, 2000000, 3000000, }; -static const u16 SW1_table[] = { - 900, 950, 1000, 1050, 1100, 1150, 1200, 1250, - 1300, 1350, 1400, 1450, 1500, 1600, 1875, 2250, +static const unsigned int SW1_table[] = { + 900000, 950000, 1000000, 1050000, 1100000, 1150000, 1200000, 1250000, + 1300000, 1350000, 1400000, 1450000, 1500000, 1600000, 1875000, 2250000, }; #define SW2_table SW1_table -static const u16 SW3_table[] = { - 4000, 4500, 5000, 5500, +static const unsigned int SW3_table[] = { + 4000000, 4500000, 5000000, 5500000, }; struct pcap_regulator { @@ -100,8 +100,6 @@ struct pcap_regulator { const u8 index; const u8 stby; const u8 lowpwr; - const u8 n_voltages; - const u16 *voltage_table; }; #define NA 0xff @@ -113,8 +111,6 @@ struct pcap_regulator { .index = _index, \ .stby = _stby, \ .lowpwr = _lowpwr, \ - .n_voltages = ARRAY_SIZE(_vreg##_table), \ - .voltage_table = _vreg##_table, \ } static struct pcap_regulator vreg_table[] = { @@ -157,11 +153,11 @@ static int pcap_regulator_set_voltage_sel(struct regulator_dev *rdev, void *pcap = rdev_get_drvdata(rdev); /* the regulator doesn't support voltage switching */ - if (vreg->n_voltages == 1) + if (rdev->desc->n_voltages == 1) return -EINVAL; return ezx_pcap_set_bits(pcap, vreg->reg, - (vreg->n_voltages - 1) << vreg->index, + (rdev->desc->n_voltages - 1) << vreg->index, selector << vreg->index); } @@ -171,11 +167,11 @@ static int pcap_regulator_get_voltage_sel(struct regulator_dev *rdev) void *pcap = rdev_get_drvdata(rdev); u32 tmp; - if (vreg->n_voltages == 1) + if (rdev->desc->n_voltages == 1) return 0; ezx_pcap_read(pcap, vreg->reg, &tmp); - tmp = ((tmp >> vreg->index) & (vreg->n_voltages - 1)); + tmp = ((tmp >> vreg->index) & (rdev->desc->n_voltages - 1)); return tmp; } @@ -214,16 +210,8 @@ static int pcap_regulator_is_enabled(struct regulator_dev *rdev) return (tmp >> vreg->en) & 1; } -static int pcap_regulator_list_voltage(struct regulator_dev *rdev, - unsigned int index) -{ - struct pcap_regulator *vreg = &vreg_table[rdev_get_id(rdev)]; - - return vreg->voltage_table[index] * 1000; -} - static struct regulator_ops pcap_regulator_ops = { - .list_voltage = pcap_regulator_list_voltage, + .list_voltage = regulator_list_voltage_table, .set_voltage_sel = pcap_regulator_set_voltage_sel, .get_voltage_sel = pcap_regulator_get_voltage_sel, .enable = pcap_regulator_enable, @@ -236,6 +224,7 @@ static struct regulator_ops pcap_regulator_ops = { .name = #_vreg, \ .id = _vreg, \ .n_voltages = ARRAY_SIZE(_vreg##_table), \ + .volt_table = _vreg##_table, \ .ops = &pcap_regulator_ops, \ .type = REGULATOR_VOLTAGE, \ .owner = THIS_MODULE, \ diff --git a/drivers/regulator/pcf50633-regulator.c b/drivers/regulator/pcf50633-regulator.c index 3c9d14c0017b..092e5cb848a1 100644 --- a/drivers/regulator/pcf50633-regulator.c +++ b/drivers/regulator/pcf50633-regulator.c @@ -100,13 +100,12 @@ static unsigned int ldo_voltage_value(u8 bits) return 900 + (bits * 100); } -static int pcf50633_regulator_set_voltage(struct regulator_dev *rdev, - int min_uV, int max_uV, - unsigned *selector) +static int pcf50633_regulator_map_voltage(struct regulator_dev *rdev, + int min_uV, int max_uV) { struct pcf50633 *pcf; int regulator_id, millivolts; - u8 volt_bits, regnr; + u8 volt_bits; pcf = rdev_get_drvdata(rdev); @@ -116,15 +115,11 @@ static int pcf50633_regulator_set_voltage(struct regulator_dev *rdev, millivolts = min_uV / 1000; - regnr = rdev->desc->vsel_reg; - switch (regulator_id) { case PCF50633_REGULATOR_AUTO: volt_bits = auto_voltage_bits(millivolts); break; case PCF50633_REGULATOR_DOWN1: - volt_bits = down_voltage_bits(millivolts); - break; case PCF50633_REGULATOR_DOWN2: volt_bits = down_voltage_bits(millivolts); break; @@ -142,9 +137,7 @@ static int pcf50633_regulator_set_voltage(struct regulator_dev *rdev, return -EINVAL; } - *selector = volt_bits; - - return pcf50633_reg_write(pcf, regnr, volt_bits); + return volt_bits; } static int pcf50633_regulator_list_voltage(struct regulator_dev *rdev, @@ -159,8 +152,6 @@ static int pcf50633_regulator_list_voltage(struct regulator_dev *rdev, millivolts = auto_voltage_value(index); break; case PCF50633_REGULATOR_DOWN1: - millivolts = down_voltage_value(index); - break; case PCF50633_REGULATOR_DOWN2: millivolts = down_voltage_value(index); break; @@ -182,9 +173,10 @@ static int pcf50633_regulator_list_voltage(struct regulator_dev *rdev, } static struct regulator_ops pcf50633_regulator_ops = { - .set_voltage = pcf50633_regulator_set_voltage, + .set_voltage_sel = regulator_set_voltage_sel_regmap, .get_voltage_sel = regulator_get_voltage_sel_regmap, .list_voltage = pcf50633_regulator_list_voltage, + .map_voltage = pcf50633_regulator_map_voltage, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, .is_enabled = regulator_is_enabled_regmap, diff --git a/drivers/regulator/rc5t583-regulator.c b/drivers/regulator/rc5t583-regulator.c index 1d34e64a1307..8bf4e8c9de9a 100644 --- a/drivers/regulator/rc5t583-regulator.c +++ b/drivers/regulator/rc5t583-regulator.c @@ -42,7 +42,6 @@ struct rc5t583_regulator_info { /* Regulator specific turn-on delay and voltage settling time*/ int enable_uv_per_us; - int change_uv_per_us; /* Used by regulator core */ struct regulator_desc desc; @@ -66,25 +65,6 @@ static int rc5t583_regulator_enable_time(struct regulator_dev *rdev) return DIV_ROUND_UP(curr_uV, reg->reg_info->enable_uv_per_us); } -static int rc5t583_set_voltage_time_sel(struct regulator_dev *rdev, - unsigned int old_selector, unsigned int new_selector) -{ - struct rc5t583_regulator *reg = rdev_get_drvdata(rdev); - int old_uV, new_uV; - old_uV = regulator_list_voltage_linear(rdev, old_selector); - - if (old_uV < 0) - return old_uV; - - new_uV = regulator_list_voltage_linear(rdev, new_selector); - if (new_uV < 0) - return new_uV; - - return DIV_ROUND_UP(abs(old_uV - new_uV), - reg->reg_info->change_uv_per_us); -} - - static struct regulator_ops rc5t583_ops = { .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, @@ -94,7 +74,7 @@ static struct regulator_ops rc5t583_ops = { .set_voltage_sel = regulator_set_voltage_sel_regmap, .list_voltage = regulator_list_voltage_linear, .map_voltage = regulator_map_voltage_linear, - .set_voltage_time_sel = rc5t583_set_voltage_time_sel, + .set_voltage_time_sel = regulator_set_voltage_time_sel, }; #define RC5T583_REG(_id, _en_reg, _en_bit, _disc_reg, _disc_bit, \ @@ -104,7 +84,6 @@ static struct regulator_ops rc5t583_ops = { .disc_bit = _disc_bit, \ .deepsleep_reg = RC5T583_REG_##_id##DAC_DS, \ .enable_uv_per_us = _enable_mv * 1000, \ - .change_uv_per_us = 40 * 1000, \ .deepsleep_id = RC5T583_DS_##_id, \ .desc = { \ .name = "rc5t583-regulator-"#_id, \ @@ -119,6 +98,7 @@ static struct regulator_ops rc5t583_ops = { .enable_mask = BIT(_en_bit), \ .min_uV = _min_mv * 1000, \ .uV_step = _step_uV, \ + .ramp_delay = 40 * 1000, \ }, \ } diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c new file mode 100644 index 000000000000..4669dc9ac74a --- /dev/null +++ b/drivers/regulator/s2mps11.c @@ -0,0 +1,363 @@ +/* + * s2mps11.c + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd + * http://www.samsung.com + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + */ + +#include <linux/bug.h> +#include <linux/delay.h> +#include <linux/err.h> +#include <linux/gpio.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/machine.h> +#include <linux/mfd/samsung/core.h> +#include <linux/mfd/samsung/s2mps11.h> + +struct s2mps11_info { + struct regulator_dev **rdev; + + int ramp_delay2; + int ramp_delay34; + int ramp_delay5; + int ramp_delay16; + int ramp_delay7810; + int ramp_delay9; + + bool buck6_ramp; + bool buck2_ramp; + bool buck3_ramp; + bool buck4_ramp; +}; + +static int get_ramp_delay(int ramp_delay) +{ + unsigned char cnt = 0; + + ramp_delay /= 6; + + while (true) { + ramp_delay = ramp_delay >> 1; + if (ramp_delay == 0) + break; + cnt++; + } + return cnt; +} + +static struct regulator_ops s2mps11_ldo_ops = { + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, + .is_enabled = regulator_is_enabled_regmap, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .set_voltage_time_sel = regulator_set_voltage_time_sel, +}; + +static struct regulator_ops s2mps11_buck_ops = { + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, + .is_enabled = regulator_is_enabled_regmap, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .set_voltage_time_sel = regulator_set_voltage_time_sel, +}; + +#define regulator_desc_ldo1(num) { \ + .name = "LDO"#num, \ + .id = S2MPS11_LDO##num, \ + .ops = &s2mps11_ldo_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = S2MPS11_LDO_MIN, \ + .uV_step = S2MPS11_LDO_STEP1, \ + .n_voltages = S2MPS11_LDO_N_VOLTAGES, \ + .vsel_reg = S2MPS11_REG_L1CTRL + num - 1, \ + .vsel_mask = S2MPS11_LDO_VSEL_MASK, \ + .enable_reg = S2MPS11_REG_L1CTRL + num - 1, \ + .enable_mask = S2MPS11_ENABLE_MASK \ +} +#define regulator_desc_ldo2(num) { \ + .name = "LDO"#num, \ + .id = S2MPS11_LDO##num, \ + .ops = &s2mps11_ldo_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = S2MPS11_LDO_MIN, \ + .uV_step = S2MPS11_LDO_STEP2, \ + .n_voltages = S2MPS11_LDO_N_VOLTAGES, \ + .vsel_reg = S2MPS11_REG_L1CTRL + num - 1, \ + .vsel_mask = S2MPS11_LDO_VSEL_MASK, \ + .enable_reg = S2MPS11_REG_L1CTRL + num - 1, \ + .enable_mask = S2MPS11_ENABLE_MASK \ +} + +#define regulator_desc_buck1_4(num) { \ + .name = "BUCK"#num, \ + .id = S2MPS11_BUCK##num, \ + .ops = &s2mps11_buck_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = S2MPS11_BUCK_MIN1, \ + .uV_step = S2MPS11_BUCK_STEP1, \ + .n_voltages = S2MPS11_BUCK_N_VOLTAGES, \ + .vsel_reg = S2MPS11_REG_B1CTRL2 + (num - 1) * 2, \ + .vsel_mask = S2MPS11_BUCK_VSEL_MASK, \ + .enable_reg = S2MPS11_REG_B1CTRL1 + (num - 1) * 2, \ + .enable_mask = S2MPS11_ENABLE_MASK \ +} + +#define regulator_desc_buck5 { \ + .name = "BUCK5", \ + .id = S2MPS11_BUCK5, \ + .ops = &s2mps11_buck_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = S2MPS11_BUCK_MIN1, \ + .uV_step = S2MPS11_BUCK_STEP1, \ + .n_voltages = S2MPS11_BUCK_N_VOLTAGES, \ + .vsel_reg = S2MPS11_REG_B5CTRL2, \ + .vsel_mask = S2MPS11_BUCK_VSEL_MASK, \ + .enable_reg = S2MPS11_REG_B5CTRL1, \ + .enable_mask = S2MPS11_ENABLE_MASK \ +} + +#define regulator_desc_buck6_8(num) { \ + .name = "BUCK"#num, \ + .id = S2MPS11_BUCK##num, \ + .ops = &s2mps11_buck_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = S2MPS11_BUCK_MIN1, \ + .uV_step = S2MPS11_BUCK_STEP1, \ + .n_voltages = S2MPS11_BUCK_N_VOLTAGES, \ + .vsel_reg = S2MPS11_REG_B6CTRL2 + (num - 6) * 2, \ + .vsel_mask = S2MPS11_BUCK_VSEL_MASK, \ + .enable_reg = S2MPS11_REG_B6CTRL1 + (num - 6) * 2, \ + .enable_mask = S2MPS11_ENABLE_MASK \ +} + +#define regulator_desc_buck9 { \ + .name = "BUCK9", \ + .id = S2MPS11_BUCK9, \ + .ops = &s2mps11_buck_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = S2MPS11_BUCK_MIN3, \ + .uV_step = S2MPS11_BUCK_STEP3, \ + .n_voltages = S2MPS11_BUCK_N_VOLTAGES, \ + .vsel_reg = S2MPS11_REG_B9CTRL2, \ + .vsel_mask = S2MPS11_BUCK_VSEL_MASK, \ + .enable_reg = S2MPS11_REG_B9CTRL1, \ + .enable_mask = S2MPS11_ENABLE_MASK \ +} + +#define regulator_desc_buck10 { \ + .name = "BUCK10", \ + .id = S2MPS11_BUCK10, \ + .ops = &s2mps11_buck_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = S2MPS11_BUCK_MIN2, \ + .uV_step = S2MPS11_BUCK_STEP2, \ + .n_voltages = S2MPS11_BUCK_N_VOLTAGES, \ + .vsel_reg = S2MPS11_REG_B9CTRL2, \ + .vsel_mask = S2MPS11_BUCK_VSEL_MASK, \ + .enable_reg = S2MPS11_REG_B9CTRL1, \ + .enable_mask = S2MPS11_ENABLE_MASK \ +} + +static struct regulator_desc regulators[] = { + regulator_desc_ldo2(1), + regulator_desc_ldo1(2), + regulator_desc_ldo1(3), + regulator_desc_ldo1(4), + regulator_desc_ldo1(5), + regulator_desc_ldo2(6), + regulator_desc_ldo1(7), + regulator_desc_ldo1(8), + regulator_desc_ldo1(9), + regulator_desc_ldo1(10), + regulator_desc_ldo2(11), + regulator_desc_ldo1(12), + regulator_desc_ldo1(13), + regulator_desc_ldo1(14), + regulator_desc_ldo1(15), + regulator_desc_ldo1(16), + regulator_desc_ldo1(17), + regulator_desc_ldo1(18), + regulator_desc_ldo1(19), + regulator_desc_ldo1(20), + regulator_desc_ldo1(21), + regulator_desc_ldo2(22), + regulator_desc_ldo2(23), + regulator_desc_ldo1(24), + regulator_desc_ldo1(25), + regulator_desc_ldo1(26), + regulator_desc_ldo2(27), + regulator_desc_ldo1(28), + regulator_desc_ldo1(29), + regulator_desc_ldo1(30), + regulator_desc_ldo1(31), + regulator_desc_ldo1(32), + regulator_desc_ldo1(33), + regulator_desc_ldo1(34), + regulator_desc_ldo1(35), + regulator_desc_ldo1(36), + regulator_desc_ldo1(37), + regulator_desc_ldo1(38), + regulator_desc_buck1_4(1), + regulator_desc_buck1_4(2), + regulator_desc_buck1_4(3), + regulator_desc_buck1_4(4), + regulator_desc_buck5, + regulator_desc_buck6_8(6), + regulator_desc_buck6_8(7), + regulator_desc_buck6_8(8), + regulator_desc_buck9, + regulator_desc_buck10, +}; + +static __devinit int s2mps11_pmic_probe(struct platform_device *pdev) +{ + struct sec_pmic_dev *iodev = dev_get_drvdata(pdev->dev.parent); + struct sec_platform_data *pdata = dev_get_platdata(iodev->dev); + struct regulator_config config = { }; + struct regulator_dev **rdev; + struct s2mps11_info *s2mps11; + int i, ret, size; + unsigned char ramp_enable, ramp_reg = 0; + + if (!pdata) { + dev_err(pdev->dev.parent, "Platform data not supplied\n"); + return -ENODEV; + } + + s2mps11 = devm_kzalloc(&pdev->dev, sizeof(struct s2mps11_info), + GFP_KERNEL); + if (!s2mps11) + return -ENOMEM; + + size = sizeof(struct regulator_dev *) * S2MPS11_REGULATOR_MAX; + s2mps11->rdev = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + if (!s2mps11->rdev) { + return -ENOMEM; + } + + rdev = s2mps11->rdev; + platform_set_drvdata(pdev, s2mps11); + + s2mps11->ramp_delay2 = pdata->buck2_ramp_delay; + s2mps11->ramp_delay34 = pdata->buck34_ramp_delay; + s2mps11->ramp_delay5 = pdata->buck5_ramp_delay; + s2mps11->ramp_delay16 = pdata->buck16_ramp_delay; + s2mps11->ramp_delay7810 = pdata->buck7810_ramp_delay; + s2mps11->ramp_delay9 = pdata->buck9_ramp_delay; + + s2mps11->buck6_ramp = pdata->buck6_ramp_enable; + s2mps11->buck2_ramp = pdata->buck2_ramp_enable; + s2mps11->buck3_ramp = pdata->buck3_ramp_enable; + s2mps11->buck4_ramp = pdata->buck4_ramp_enable; + + ramp_enable = (s2mps11->buck2_ramp << 3) | (s2mps11->buck3_ramp << 2) | + (s2mps11->buck4_ramp << 1) | s2mps11->buck6_ramp ; + + if (ramp_enable) { + if (s2mps11->buck2_ramp) + ramp_reg |= get_ramp_delay(s2mps11->ramp_delay2) >> 6; + if (s2mps11->buck3_ramp || s2mps11->buck4_ramp) + ramp_reg |= get_ramp_delay(s2mps11->ramp_delay34) >> 4; + sec_reg_write(iodev, S2MPS11_REG_RAMP, ramp_reg | ramp_enable); + } + + ramp_reg &= 0x00; + ramp_reg |= get_ramp_delay(s2mps11->ramp_delay5) >> 6; + ramp_reg |= get_ramp_delay(s2mps11->ramp_delay16) >> 4; + ramp_reg |= get_ramp_delay(s2mps11->ramp_delay7810) >> 2; + ramp_reg |= get_ramp_delay(s2mps11->ramp_delay9); + sec_reg_write(iodev, S2MPS11_REG_RAMP_BUCK, ramp_reg); + + for (i = 0; i < S2MPS11_REGULATOR_MAX; i++) { + + config.dev = &pdev->dev; + config.regmap = iodev->regmap; + config.init_data = pdata->regulators[i].initdata; + config.driver_data = s2mps11; + + rdev[i] = regulator_register(®ulators[i], &config); + if (IS_ERR(rdev[i])) { + ret = PTR_ERR(rdev[i]); + dev_err(&pdev->dev, "regulator init failed for %d\n", + i); + rdev[i] = NULL; + goto err; + } + } + + return 0; +err: + for (i = 0; i < S2MPS11_REGULATOR_MAX; i++) + if (rdev[i]) + regulator_unregister(rdev[i]); + + return ret; +} + +static int __devexit s2mps11_pmic_remove(struct platform_device *pdev) +{ + struct s2mps11_info *s2mps11 = platform_get_drvdata(pdev); + struct regulator_dev **rdev = s2mps11->rdev; + int i; + + for (i = 0; i < S2MPS11_REGULATOR_MAX; i++) + if (rdev[i]) + regulator_unregister(rdev[i]); + + return 0; +} + +static const struct platform_device_id s2mps11_pmic_id[] = { + { "s2mps11-pmic", 0}, + { }, +}; +MODULE_DEVICE_TABLE(platform, s2mps11_pmic_id); + +static struct platform_driver s2mps11_pmic_driver = { + .driver = { + .name = "s2mps11-pmic", + .owner = THIS_MODULE, + }, + .probe = s2mps11_pmic_probe, + .remove = __devexit_p(s2mps11_pmic_remove), + .id_table = s2mps11_pmic_id, +}; + +static int __init s2mps11_pmic_init(void) +{ + return platform_driver_register(&s2mps11_pmic_driver); +} +subsys_initcall(s2mps11_pmic_init); + +static void __exit s2mps11_pmic_exit(void) +{ + platform_driver_unregister(&s2mps11_pmic_driver); +} +module_exit(s2mps11_pmic_exit); + +/* Module information */ +MODULE_AUTHOR("Sangbeom Kim <sbkim73@samsung.com>"); +MODULE_DESCRIPTION("SAMSUNG S2MPS11 Regulator Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c index 9caadb482178..102287fa7ecb 100644 --- a/drivers/regulator/s5m8767.c +++ b/drivers/regulator/s5m8767.c @@ -41,6 +41,7 @@ struct s5m8767_info { u8 buck3_vol[8]; u8 buck4_vol[8]; int buck_gpios[3]; + int buck_ds[3]; int buck_gpioindex; }; @@ -120,27 +121,6 @@ static const struct s5m_voltage_desc *reg_voltage_map[] = { [S5M8767_BUCK9] = &buck_voltage_val3, }; -static int s5m8767_list_voltage(struct regulator_dev *rdev, - unsigned int selector) -{ - const struct s5m_voltage_desc *desc; - int reg_id = rdev_get_id(rdev); - int val; - - if (reg_id >= ARRAY_SIZE(reg_voltage_map) || reg_id < 0) - return -EINVAL; - - desc = reg_voltage_map[reg_id]; - if (desc == NULL) - return -EINVAL; - - val = desc->min + desc->step * selector; - if (val > desc->max) - return -EINVAL; - - return val; -} - static unsigned int s5m8767_opmode_reg[][4] = { /* {OFF, ON, LOWPOWER, SUSPEND} */ /* LDO1 ... LDO28 */ @@ -283,17 +263,17 @@ static int s5m8767_get_voltage_register(struct regulator_dev *rdev, int *_reg) reg = S5M8767_REG_BUCK1CTRL2; break; case S5M8767_BUCK2: - reg = S5M8767_REG_BUCK2DVS1; + reg = S5M8767_REG_BUCK2DVS2; if (s5m8767->buck2_gpiodvs) reg += s5m8767->buck_gpioindex; break; case S5M8767_BUCK3: - reg = S5M8767_REG_BUCK3DVS1; + reg = S5M8767_REG_BUCK3DVS2; if (s5m8767->buck3_gpiodvs) reg += s5m8767->buck_gpioindex; break; case S5M8767_BUCK4: - reg = S5M8767_REG_BUCK4DVS1; + reg = S5M8767_REG_BUCK4DVS2; if (s5m8767->buck4_gpiodvs) reg += s5m8767->buck_gpioindex; break; @@ -357,32 +337,34 @@ static int s5m8767_convert_voltage_to_sel( return selector; } -static inline void s5m8767_set_high(struct s5m8767_info *s5m8767) +static inline int s5m8767_set_high(struct s5m8767_info *s5m8767) { int temp_index = s5m8767->buck_gpioindex; gpio_set_value(s5m8767->buck_gpios[0], (temp_index >> 2) & 0x1); gpio_set_value(s5m8767->buck_gpios[1], (temp_index >> 1) & 0x1); gpio_set_value(s5m8767->buck_gpios[2], temp_index & 0x1); + + return 0; } -static inline void s5m8767_set_low(struct s5m8767_info *s5m8767) +static inline int s5m8767_set_low(struct s5m8767_info *s5m8767) { int temp_index = s5m8767->buck_gpioindex; gpio_set_value(s5m8767->buck_gpios[2], temp_index & 0x1); gpio_set_value(s5m8767->buck_gpios[1], (temp_index >> 1) & 0x1); gpio_set_value(s5m8767->buck_gpios[0], (temp_index >> 2) & 0x1); + + return 0; } -static int s5m8767_set_voltage(struct regulator_dev *rdev, - int min_uV, int max_uV, unsigned *selector) +static int s5m8767_set_voltage_sel(struct regulator_dev *rdev, + unsigned selector) { struct s5m8767_info *s5m8767 = rdev_get_drvdata(rdev); - const struct s5m_voltage_desc *desc; int reg_id = rdev_get_id(rdev); - int sel, reg, mask, ret = 0, old_index, index = 0; - u8 val; + int reg, mask, ret = 0, old_index, index = 0; u8 *buck234_vol = NULL; switch (reg_id) { @@ -407,15 +389,9 @@ static int s5m8767_set_voltage(struct regulator_dev *rdev, return -EINVAL; } - desc = reg_voltage_map[reg_id]; - - sel = s5m8767_convert_voltage_to_sel(desc, min_uV, max_uV); - if (sel < 0) - return sel; - /* buck234_vol != NULL means to control buck234 voltage via DVS GPIO */ if (buck234_vol) { - while (*buck234_vol != sel) { + while (*buck234_vol != selector) { buck234_vol++; index++; } @@ -423,22 +399,16 @@ static int s5m8767_set_voltage(struct regulator_dev *rdev, s5m8767->buck_gpioindex = index; if (index > old_index) - s5m8767_set_high(s5m8767); + return s5m8767_set_high(s5m8767); else - s5m8767_set_low(s5m8767); + return s5m8767_set_low(s5m8767); } else { ret = s5m8767_get_voltage_register(rdev, ®); if (ret) return ret; - s5m_reg_read(s5m8767->iodev, reg, &val); - val = (val & ~mask) | sel; - - ret = s5m_reg_write(s5m8767->iodev, reg, val); + return s5m_reg_update(s5m8767->iodev, reg, selector, mask); } - - *selector = sel; - return ret; } static int s5m8767_set_voltage_time_sel(struct regulator_dev *rdev, @@ -458,15 +428,21 @@ static int s5m8767_set_voltage_time_sel(struct regulator_dev *rdev, } static struct regulator_ops s5m8767_ops = { - .list_voltage = s5m8767_list_voltage, + .list_voltage = regulator_list_voltage_linear, .is_enabled = s5m8767_reg_is_enabled, .enable = s5m8767_reg_enable, .disable = s5m8767_reg_disable, .get_voltage_sel = s5m8767_get_voltage_sel, - .set_voltage = s5m8767_set_voltage, + .set_voltage_sel = s5m8767_set_voltage_sel, .set_voltage_time_sel = s5m8767_set_voltage_time_sel, }; +static struct regulator_ops s5m8767_buck78_ops = { + .is_enabled = s5m8767_reg_is_enabled, + .enable = s5m8767_reg_enable, + .disable = s5m8767_reg_disable, +}; + #define s5m8767_regulator_desc(_name) { \ .name = #_name, \ .id = S5M8767_##_name, \ @@ -475,6 +451,14 @@ static struct regulator_ops s5m8767_ops = { .owner = THIS_MODULE, \ } +#define s5m8767_regulator_buck78_desc(_name) { \ + .name = #_name, \ + .id = S5M8767_##_name, \ + .ops = &s5m8767_buck78_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ +} + static struct regulator_desc regulators[] = { s5m8767_regulator_desc(LDO1), s5m8767_regulator_desc(LDO2), @@ -510,8 +494,8 @@ static struct regulator_desc regulators[] = { s5m8767_regulator_desc(BUCK4), s5m8767_regulator_desc(BUCK5), s5m8767_regulator_desc(BUCK6), - s5m8767_regulator_desc(BUCK7), - s5m8767_regulator_desc(BUCK8), + s5m8767_regulator_buck78_desc(BUCK7), + s5m8767_regulator_buck78_desc(BUCK8), s5m8767_regulator_desc(BUCK9), }; @@ -522,7 +506,7 @@ static __devinit int s5m8767_pmic_probe(struct platform_device *pdev) struct regulator_config config = { }; struct regulator_dev **rdev; struct s5m8767_info *s5m8767; - int i, ret, size; + int i, ret, size, buck_init; if (!pdata) { dev_err(pdev->dev.parent, "Platform data not supplied\n"); @@ -573,12 +557,37 @@ static __devinit int s5m8767_pmic_probe(struct platform_device *pdev) s5m8767->buck_gpios[0] = pdata->buck_gpios[0]; s5m8767->buck_gpios[1] = pdata->buck_gpios[1]; s5m8767->buck_gpios[2] = pdata->buck_gpios[2]; + s5m8767->buck_ds[0] = pdata->buck_ds[0]; + s5m8767->buck_ds[1] = pdata->buck_ds[1]; + s5m8767->buck_ds[2] = pdata->buck_ds[2]; + s5m8767->ramp_delay = pdata->buck_ramp_delay; s5m8767->buck2_ramp = pdata->buck2_ramp_enable; s5m8767->buck3_ramp = pdata->buck3_ramp_enable; s5m8767->buck4_ramp = pdata->buck4_ramp_enable; s5m8767->opmode = pdata->opmode; + buck_init = s5m8767_convert_voltage_to_sel(&buck_voltage_val2, + pdata->buck2_init, + pdata->buck2_init + + buck_voltage_val2.step); + + s5m_reg_write(s5m8767->iodev, S5M8767_REG_BUCK2DVS2, buck_init); + + buck_init = s5m8767_convert_voltage_to_sel(&buck_voltage_val2, + pdata->buck3_init, + pdata->buck3_init + + buck_voltage_val2.step); + + s5m_reg_write(s5m8767->iodev, S5M8767_REG_BUCK3DVS2, buck_init); + + buck_init = s5m8767_convert_voltage_to_sel(&buck_voltage_val2, + pdata->buck4_init, + pdata->buck4_init + + buck_voltage_val2.step); + + s5m_reg_write(s5m8767->iodev, S5M8767_REG_BUCK4DVS2, buck_init); + for (i = 0; i < 8; i++) { if (s5m8767->buck2_gpiodvs) { s5m8767->buck2_vol[i] = @@ -608,48 +617,70 @@ static __devinit int s5m8767_pmic_probe(struct platform_device *pdev) } } - if (pdata->buck2_gpiodvs || pdata->buck3_gpiodvs || - pdata->buck4_gpiodvs) { - if (gpio_is_valid(pdata->buck_gpios[0]) && - gpio_is_valid(pdata->buck_gpios[1]) && - gpio_is_valid(pdata->buck_gpios[2])) { - ret = gpio_request(pdata->buck_gpios[0], - "S5M8767 SET1"); - if (ret == -EBUSY) - dev_warn(&pdev->dev, "Duplicated gpio request for SET1\n"); - - ret = gpio_request(pdata->buck_gpios[1], - "S5M8767 SET2"); - if (ret == -EBUSY) - dev_warn(&pdev->dev, "Duplicated gpio request for SET2\n"); - - ret = gpio_request(pdata->buck_gpios[2], - "S5M8767 SET3"); - if (ret == -EBUSY) - dev_warn(&pdev->dev, "Duplicated gpio request for SET3\n"); - /* SET1 GPIO */ - gpio_direction_output(pdata->buck_gpios[0], - (s5m8767->buck_gpioindex >> 2) & 0x1); - /* SET2 GPIO */ - gpio_direction_output(pdata->buck_gpios[1], - (s5m8767->buck_gpioindex >> 1) & 0x1); - /* SET3 GPIO */ - gpio_direction_output(pdata->buck_gpios[2], - (s5m8767->buck_gpioindex >> 0) & 0x1); - ret = 0; - } else { - dev_err(&pdev->dev, "GPIO NOT VALID\n"); - ret = -EINVAL; + if (gpio_is_valid(pdata->buck_gpios[0]) && + gpio_is_valid(pdata->buck_gpios[1]) && + gpio_is_valid(pdata->buck_gpios[2])) { + ret = devm_gpio_request(&pdev->dev, pdata->buck_gpios[0], + "S5M8767 SET1"); + if (ret) return ret; - } + + ret = devm_gpio_request(&pdev->dev, pdata->buck_gpios[1], + "S5M8767 SET2"); + if (ret) + return ret; + + ret = devm_gpio_request(&pdev->dev, pdata->buck_gpios[2], + "S5M8767 SET3"); + if (ret) + return ret; + + /* SET1 GPIO */ + gpio_direction_output(pdata->buck_gpios[0], + (s5m8767->buck_gpioindex >> 2) & 0x1); + /* SET2 GPIO */ + gpio_direction_output(pdata->buck_gpios[1], + (s5m8767->buck_gpioindex >> 1) & 0x1); + /* SET3 GPIO */ + gpio_direction_output(pdata->buck_gpios[2], + (s5m8767->buck_gpioindex >> 0) & 0x1); + } else { + dev_err(&pdev->dev, "GPIO NOT VALID\n"); + ret = -EINVAL; + return ret; } - s5m_reg_update(s5m8767->iodev, S5M8767_REG_BUCK2CTRL, - (pdata->buck2_gpiodvs) ? (1 << 1) : (0 << 1), 1 << 1); - s5m_reg_update(s5m8767->iodev, S5M8767_REG_BUCK3CTRL, - (pdata->buck3_gpiodvs) ? (1 << 1) : (0 << 1), 1 << 1); - s5m_reg_update(s5m8767->iodev, S5M8767_REG_BUCK4CTRL, - (pdata->buck4_gpiodvs) ? (1 << 1) : (0 << 1), 1 << 1); + ret = devm_gpio_request(&pdev->dev, pdata->buck_ds[0], "S5M8767 DS2"); + if (ret) + return ret; + + ret = devm_gpio_request(&pdev->dev, pdata->buck_ds[1], "S5M8767 DS3"); + if (ret) + return ret; + + ret = devm_gpio_request(&pdev->dev, pdata->buck_ds[2], "S5M8767 DS4"); + if (ret) + return ret; + + /* DS2 GPIO */ + gpio_direction_output(pdata->buck_ds[0], 0x0); + /* DS3 GPIO */ + gpio_direction_output(pdata->buck_ds[1], 0x0); + /* DS4 GPIO */ + gpio_direction_output(pdata->buck_ds[2], 0x0); + + if (pdata->buck2_gpiodvs || pdata->buck3_gpiodvs || + pdata->buck4_gpiodvs) { + s5m_reg_update(s5m8767->iodev, S5M8767_REG_BUCK2CTRL, + (pdata->buck2_gpiodvs) ? (1 << 1) : (0 << 1), + 1 << 1); + s5m_reg_update(s5m8767->iodev, S5M8767_REG_BUCK3CTRL, + (pdata->buck3_gpiodvs) ? (1 << 1) : (0 << 1), + 1 << 1); + s5m_reg_update(s5m8767->iodev, S5M8767_REG_BUCK4CTRL, + (pdata->buck4_gpiodvs) ? (1 << 1) : (0 << 1), + 1 << 1); + } /* Initialize GPIO DVS registers */ for (i = 0; i < 8; i++) { @@ -668,9 +699,6 @@ static __devinit int s5m8767_pmic_probe(struct platform_device *pdev) s5m8767->buck4_vol[i]); } } - s5m_reg_update(s5m8767->iodev, S5M8767_REG_BUCK2CTRL, 0x78, 0xff); - s5m_reg_update(s5m8767->iodev, S5M8767_REG_BUCK3CTRL, 0x58, 0xff); - s5m_reg_update(s5m8767->iodev, S5M8767_REG_BUCK4CTRL, 0x78, 0xff); if (s5m8767->buck2_ramp) s5m_reg_update(s5m8767->iodev, S5M8767_REG_DVSRAMP, 0x08, 0x08); @@ -684,9 +712,13 @@ static __devinit int s5m8767_pmic_probe(struct platform_device *pdev) if (s5m8767->buck2_ramp || s5m8767->buck3_ramp || s5m8767->buck4_ramp) { switch (s5m8767->ramp_delay) { - case 15: + case 5: s5m_reg_update(s5m8767->iodev, S5M8767_REG_DVSRAMP, - 0xc0, 0xf0); + 0x40, 0xf0); + break; + case 10: + s5m_reg_update(s5m8767->iodev, S5M8767_REG_DVSRAMP, + 0x90, 0xf0); break; case 25: s5m_reg_update(s5m8767->iodev, S5M8767_REG_DVSRAMP, @@ -711,9 +743,12 @@ static __devinit int s5m8767_pmic_probe(struct platform_device *pdev) int id = pdata->regulators[i].id; desc = reg_voltage_map[id]; - if (desc) + if (desc) { regulators[id].n_voltages = (desc->max - desc->min) / desc->step + 1; + regulators[id].min_uV = desc->min; + regulators[id].uV_step = desc->step; + } config.dev = s5m8767->dev; config.init_data = pdata->regulators[i].initdata; diff --git a/drivers/regulator/tps6105x-regulator.c b/drivers/regulator/tps6105x-regulator.c index d840d8440a91..1378409efaec 100644 --- a/drivers/regulator/tps6105x-regulator.c +++ b/drivers/regulator/tps6105x-regulator.c @@ -20,7 +20,7 @@ #include <linux/mfd/core.h> #include <linux/mfd/tps6105x.h> -static const int tps6105x_voltages[] = { +static const unsigned int tps6105x_voltages[] = { 4500000, 5000000, 5250000, @@ -105,22 +105,13 @@ static int tps6105x_regulator_set_voltage_sel(struct regulator_dev *rdev, return 0; } -static int tps6105x_regulator_list_voltage(struct regulator_dev *rdev, - unsigned selector) -{ - if (selector >= ARRAY_SIZE(tps6105x_voltages)) - return -EINVAL; - - return tps6105x_voltages[selector]; -} - static struct regulator_ops tps6105x_regulator_ops = { .enable = tps6105x_regulator_enable, .disable = tps6105x_regulator_disable, .is_enabled = tps6105x_regulator_is_enabled, .get_voltage_sel = tps6105x_regulator_get_voltage_sel, .set_voltage_sel = tps6105x_regulator_set_voltage_sel, - .list_voltage = tps6105x_regulator_list_voltage, + .list_voltage = regulator_list_voltage_table, }; static const struct regulator_desc tps6105x_regulator_desc = { @@ -130,6 +121,7 @@ static const struct regulator_desc tps6105x_regulator_desc = { .id = 0, .owner = THIS_MODULE, .n_voltages = ARRAY_SIZE(tps6105x_voltages), + .volt_table = tps6105x_voltages, }; /* diff --git a/drivers/regulator/tps62360-regulator.c b/drivers/regulator/tps62360-regulator.c index e534269ed44a..68729a7c8709 100644 --- a/drivers/regulator/tps62360-regulator.c +++ b/drivers/regulator/tps62360-regulator.c @@ -65,10 +65,8 @@ struct tps62360_chip { struct regulator_desc desc; struct regulator_dev *rdev; struct regmap *regmap; - int chip_id; int vsel0_gpio; int vsel1_gpio; - int voltage_base; u8 voltage_reg_mask; bool en_internal_pulldn; bool en_discharge; @@ -76,7 +74,6 @@ struct tps62360_chip { int lru_index[4]; int curr_vset_vsel[4]; int curr_vset_id; - int change_uv_per_us; }; /* @@ -175,23 +172,6 @@ static int tps62360_dcdc_set_voltage_sel(struct regulator_dev *dev, return 0; } -static int tps62360_set_voltage_time_sel(struct regulator_dev *rdev, - unsigned int old_selector, unsigned int new_selector) -{ - struct tps62360_chip *tps = rdev_get_drvdata(rdev); - int old_uV, new_uV; - - old_uV = regulator_list_voltage_linear(rdev, old_selector); - if (old_uV < 0) - return old_uV; - - new_uV = regulator_list_voltage_linear(rdev, new_selector); - if (new_uV < 0) - return new_uV; - - return DIV_ROUND_UP(abs(old_uV - new_uV), tps->change_uv_per_us); -} - static int tps62360_set_mode(struct regulator_dev *rdev, unsigned int mode) { struct tps62360_chip *tps = rdev_get_drvdata(rdev); @@ -258,7 +238,7 @@ static struct regulator_ops tps62360_dcdc_ops = { .set_voltage_sel = tps62360_dcdc_set_voltage_sel, .list_voltage = regulator_list_voltage_linear, .map_voltage = regulator_map_voltage_linear, - .set_voltage_time_sel = tps62360_set_voltage_time_sel, + .set_voltage_time_sel = regulator_set_voltage_time_sel, .set_mode = tps62360_set_mode, .get_mode = tps62360_get_mode, }; @@ -301,7 +281,7 @@ static int __devinit tps62360_init_dcdc(struct tps62360_chip *tps, ramp_ctrl = (ramp_ctrl >> 4) & 0x7; /* ramp mV/us = 32/(2^ramp_ctrl) */ - tps->change_uv_per_us = DIV_ROUND_UP(32000, BIT(ramp_ctrl)); + tps->desc.ramp_delay = DIV_ROUND_UP(32000, BIT(ramp_ctrl)); return ret; } @@ -408,13 +388,13 @@ static int __devinit tps62360_probe(struct i2c_client *client, switch (chip_id) { case TPS62360: case TPS62362: - tps->voltage_base = TPS62360_BASE_VOLTAGE; + tps->desc.min_uV = TPS62360_BASE_VOLTAGE; tps->voltage_reg_mask = 0x3F; tps->desc.n_voltages = TPS62360_N_VOLTAGES; break; case TPS62361: case TPS62363: - tps->voltage_base = TPS62361_BASE_VOLTAGE; + tps->desc.min_uV = TPS62361_BASE_VOLTAGE; tps->voltage_reg_mask = 0x7F; tps->desc.n_voltages = TPS62361_N_VOLTAGES; break; @@ -427,7 +407,6 @@ static int __devinit tps62360_probe(struct i2c_client *client, tps->desc.ops = &tps62360_dcdc_ops; tps->desc.type = REGULATOR_VOLTAGE; tps->desc.owner = THIS_MODULE; - tps->desc.min_uV = tps->voltage_base; tps->desc.uV_step = 10000; tps->regmap = devm_regmap_init_i2c(client, &tps62360_regmap_config); @@ -449,24 +428,24 @@ static int __devinit tps62360_probe(struct i2c_client *client, int gpio_flags; gpio_flags = (pdata->vsel0_def_state) ? GPIOF_OUT_INIT_HIGH : GPIOF_OUT_INIT_LOW; - ret = gpio_request_one(tps->vsel0_gpio, + ret = devm_gpio_request_one(&client->dev, tps->vsel0_gpio, gpio_flags, "tps62360-vsel0"); if (ret) { dev_err(&client->dev, "%s(): Could not obtain vsel0 GPIO %d: %d\n", __func__, tps->vsel0_gpio, ret); - goto err_gpio0; + return ret; } gpio_flags = (pdata->vsel1_def_state) ? GPIOF_OUT_INIT_HIGH : GPIOF_OUT_INIT_LOW; - ret = gpio_request_one(tps->vsel1_gpio, + ret = devm_gpio_request_one(&client->dev, tps->vsel1_gpio, gpio_flags, "tps62360-vsel1"); if (ret) { dev_err(&client->dev, "%s(): Could not obtain vsel1 GPIO %d: %d\n", __func__, tps->vsel1_gpio, ret); - goto err_gpio1; + return ret; } tps->valid_gpios = true; @@ -484,7 +463,7 @@ static int __devinit tps62360_probe(struct i2c_client *client, if (ret < 0) { dev_err(tps->dev, "%s(): Init failed with err = %d\n", __func__, ret); - goto err_init; + return ret; } config.dev = &client->dev; @@ -498,21 +477,11 @@ static int __devinit tps62360_probe(struct i2c_client *client, dev_err(tps->dev, "%s(): regulator register failed with err %s\n", __func__, id->name); - ret = PTR_ERR(rdev); - goto err_init; + return PTR_ERR(rdev); } tps->rdev = rdev; return 0; - -err_init: - if (gpio_is_valid(tps->vsel1_gpio)) - gpio_free(tps->vsel1_gpio); -err_gpio1: - if (gpio_is_valid(tps->vsel0_gpio)) - gpio_free(tps->vsel0_gpio); -err_gpio0: - return ret; } /** @@ -525,12 +494,6 @@ static int __devexit tps62360_remove(struct i2c_client *client) { struct tps62360_chip *tps = i2c_get_clientdata(client); - if (gpio_is_valid(tps->vsel1_gpio)) - gpio_free(tps->vsel1_gpio); - - if (gpio_is_valid(tps->vsel0_gpio)) - gpio_free(tps->vsel0_gpio); - regulator_unregister(tps->rdev); return 0; } diff --git a/drivers/regulator/tps65023-regulator.c b/drivers/regulator/tps65023-regulator.c index 8f1be8586c72..6998d579d07b 100644 --- a/drivers/regulator/tps65023-regulator.c +++ b/drivers/regulator/tps65023-regulator.c @@ -69,10 +69,6 @@ #define TPS65023_REG_CTRL2_DCDC1 BIT(1) #define TPS65023_REG_CTRL2_DCDC3 BIT(0) -/* LDO_CTRL bitfields */ -#define TPS65023_LDO_CTRL_LDOx_SHIFT(ldo_id) ((ldo_id)*4) -#define TPS65023_LDO_CTRL_LDOx_MASK(ldo_id) (0x07 << ((ldo_id)*4)) - /* Number of step-down converters available */ #define TPS65023_NUM_DCDC 3 /* Number of LDO voltage regulators available */ @@ -91,48 +87,53 @@ #define TPS65023_MAX_REG_ID TPS65023_LDO_2 /* Supported voltage values for regulators */ -static const u16 VCORE_VSEL_table[] = { - 800, 825, 850, 875, - 900, 925, 950, 975, - 1000, 1025, 1050, 1075, - 1100, 1125, 1150, 1175, - 1200, 1225, 1250, 1275, - 1300, 1325, 1350, 1375, - 1400, 1425, 1450, 1475, - 1500, 1525, 1550, 1600, +static const unsigned int VCORE_VSEL_table[] = { + 800000, 825000, 850000, 875000, + 900000, 925000, 950000, 975000, + 1000000, 1025000, 1050000, 1075000, + 1100000, 1125000, 1150000, 1175000, + 1200000, 1225000, 1250000, 1275000, + 1300000, 1325000, 1350000, 1375000, + 1400000, 1425000, 1450000, 1475000, + 1500000, 1525000, 1550000, 1600000, +}; + +static const unsigned int DCDC_FIXED_3300000_VSEL_table[] = { + 3300000, +}; + +static const unsigned int DCDC_FIXED_1800000_VSEL_table[] = { + 1800000, }; /* Supported voltage values for LDO regulators for tps65020 */ -static const u16 TPS65020_LDO1_VSEL_table[] = { - 1000, 1050, 1100, 1300, - 1800, 2500, 3000, 3300, +static const unsigned int TPS65020_LDO1_VSEL_table[] = { + 1000000, 1050000, 1100000, 1300000, + 1800000, 2500000, 3000000, 3300000, }; -static const u16 TPS65020_LDO2_VSEL_table[] = { - 1000, 1050, 1100, 1300, - 1800, 2500, 3000, 3300, +static const unsigned int TPS65020_LDO2_VSEL_table[] = { + 1000000, 1050000, 1100000, 1300000, + 1800000, 2500000, 3000000, 3300000, }; /* Supported voltage values for LDO regulators * for tps65021 and tps65023 */ -static const u16 TPS65023_LDO1_VSEL_table[] = { - 1000, 1100, 1300, 1800, - 2200, 2600, 2800, 3150, +static const unsigned int TPS65023_LDO1_VSEL_table[] = { + 1000000, 1100000, 1300000, 1800000, + 2200000, 2600000, 2800000, 3150000, }; -static const u16 TPS65023_LDO2_VSEL_table[] = { - 1050, 1200, 1300, 1800, - 2500, 2800, 3000, 3300, +static const unsigned int TPS65023_LDO2_VSEL_table[] = { + 1050000, 1200000, 1300000, 1800000, + 2500000, 2800000, 3000000, 3300000, }; /* Regulator specific details */ struct tps_info { const char *name; - unsigned min_uV; - unsigned max_uV; - bool fixed; u8 table_len; - const u16 *table; + const unsigned int *table; }; /* PMIC details */ @@ -150,7 +151,7 @@ struct tps_driver_data { u8 core_regulator; }; -static int tps65023_dcdc_get_voltage(struct regulator_dev *dev) +static int tps65023_dcdc_get_voltage_sel(struct regulator_dev *dev) { struct tps_pmic *tps = rdev_get_drvdata(dev); int ret; @@ -164,9 +165,9 @@ static int tps65023_dcdc_get_voltage(struct regulator_dev *dev) if (ret != 0) return ret; data &= (tps->info[dcdc]->table_len - 1); - return tps->info[dcdc]->table[data] * 1000; + return data; } else - return tps->info[dcdc]->min_uV; + return 0; } static int tps65023_dcdc_set_voltage_sel(struct regulator_dev *dev, @@ -193,76 +194,14 @@ out: return ret; } -static int tps65023_ldo_get_voltage(struct regulator_dev *dev) -{ - struct tps_pmic *tps = rdev_get_drvdata(dev); - int data, ldo = rdev_get_id(dev); - int ret; - - if (ldo < TPS65023_LDO_1 || ldo > TPS65023_LDO_2) - return -EINVAL; - - ret = regmap_read(tps->regmap, TPS65023_REG_LDO_CTRL, &data); - if (ret != 0) - return ret; - - data >>= (TPS65023_LDO_CTRL_LDOx_SHIFT(ldo - TPS65023_LDO_1)); - data &= (tps->info[ldo]->table_len - 1); - return tps->info[ldo]->table[data] * 1000; -} - -static int tps65023_ldo_set_voltage_sel(struct regulator_dev *dev, - unsigned selector) -{ - struct tps_pmic *tps = rdev_get_drvdata(dev); - int ldo_index = rdev_get_id(dev) - TPS65023_LDO_1; - - return regmap_update_bits(tps->regmap, TPS65023_REG_LDO_CTRL, - TPS65023_LDO_CTRL_LDOx_MASK(ldo_index), - selector << TPS65023_LDO_CTRL_LDOx_SHIFT(ldo_index)); -} - -static int tps65023_dcdc_list_voltage(struct regulator_dev *dev, - unsigned selector) -{ - struct tps_pmic *tps = rdev_get_drvdata(dev); - int dcdc = rdev_get_id(dev); - - if (dcdc < TPS65023_DCDC_1 || dcdc > TPS65023_DCDC_3) - return -EINVAL; - - if (dcdc == tps->core_regulator) { - if (selector >= tps->info[dcdc]->table_len) - return -EINVAL; - else - return tps->info[dcdc]->table[selector] * 1000; - } else - return tps->info[dcdc]->min_uV; -} - -static int tps65023_ldo_list_voltage(struct regulator_dev *dev, - unsigned selector) -{ - struct tps_pmic *tps = rdev_get_drvdata(dev); - int ldo = rdev_get_id(dev); - - if (ldo < TPS65023_LDO_1 || ldo > TPS65023_LDO_2) - return -EINVAL; - - if (selector >= tps->info[ldo]->table_len) - return -EINVAL; - else - return tps->info[ldo]->table[selector] * 1000; -} - /* Operations permitted on VDCDCx */ static struct regulator_ops tps65023_dcdc_ops = { .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, - .get_voltage = tps65023_dcdc_get_voltage, + .get_voltage_sel = tps65023_dcdc_get_voltage_sel, .set_voltage_sel = tps65023_dcdc_set_voltage_sel, - .list_voltage = tps65023_dcdc_list_voltage, + .list_voltage = regulator_list_voltage_table, }; /* Operations permitted on LDOx */ @@ -270,9 +209,9 @@ static struct regulator_ops tps65023_ldo_ops = { .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, - .get_voltage = tps65023_ldo_get_voltage, - .set_voltage_sel = tps65023_ldo_set_voltage_sel, - .list_voltage = tps65023_ldo_list_voltage, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .list_voltage = regulator_list_voltage_table, }; static struct regmap_config tps65023_regmap_config = { @@ -325,19 +264,28 @@ static int __devinit tps_65023_probe(struct i2c_client *client, tps->desc[i].name = info->name; tps->desc[i].id = i; tps->desc[i].n_voltages = info->table_len; + tps->desc[i].volt_table = info->table; tps->desc[i].ops = (i > TPS65023_DCDC_3 ? &tps65023_ldo_ops : &tps65023_dcdc_ops); tps->desc[i].type = REGULATOR_VOLTAGE; tps->desc[i].owner = THIS_MODULE; tps->desc[i].enable_reg = TPS65023_REG_REG_CTRL; - if (i == TPS65023_LDO_1) + switch (i) { + case TPS65023_LDO_1: + tps->desc[i].vsel_reg = TPS65023_REG_LDO_CTRL; + tps->desc[i].vsel_mask = 0x07; tps->desc[i].enable_mask = 1 << 1; - else if (i == TPS65023_LDO_2) + break; + case TPS65023_LDO_2: + tps->desc[i].vsel_reg = TPS65023_REG_LDO_CTRL; + tps->desc[i].vsel_mask = 0x70; tps->desc[i].enable_mask = 1 << 2; - else /* DCDCx */ + break; + default: /* DCDCx */ tps->desc[i].enable_mask = 1 << (TPS65023_NUM_REGULATOR - i); + } config.dev = &client->dev; config.init_data = init_data; @@ -384,35 +332,26 @@ static int __devexit tps_65023_remove(struct i2c_client *client) static const struct tps_info tps65020_regs[] = { { .name = "VDCDC1", - .min_uV = 3300000, - .max_uV = 3300000, - .fixed = 1, + .table_len = ARRAY_SIZE(DCDC_FIXED_3300000_VSEL_table), + .table = DCDC_FIXED_3300000_VSEL_table, }, { .name = "VDCDC2", - .min_uV = 1800000, - .max_uV = 1800000, - .fixed = 1, + .table_len = ARRAY_SIZE(DCDC_FIXED_1800000_VSEL_table), + .table = DCDC_FIXED_1800000_VSEL_table, }, { .name = "VDCDC3", - .min_uV = 800000, - .max_uV = 1600000, .table_len = ARRAY_SIZE(VCORE_VSEL_table), .table = VCORE_VSEL_table, }, - { .name = "LDO1", - .min_uV = 1000000, - .max_uV = 3150000, .table_len = ARRAY_SIZE(TPS65020_LDO1_VSEL_table), .table = TPS65020_LDO1_VSEL_table, }, { .name = "LDO2", - .min_uV = 1050000, - .max_uV = 3300000, .table_len = ARRAY_SIZE(TPS65020_LDO2_VSEL_table), .table = TPS65020_LDO2_VSEL_table, }, @@ -421,34 +360,26 @@ static const struct tps_info tps65020_regs[] = { static const struct tps_info tps65021_regs[] = { { .name = "VDCDC1", - .min_uV = 3300000, - .max_uV = 3300000, - .fixed = 1, + .table_len = ARRAY_SIZE(DCDC_FIXED_3300000_VSEL_table), + .table = DCDC_FIXED_3300000_VSEL_table, }, { .name = "VDCDC2", - .min_uV = 1800000, - .max_uV = 1800000, - .fixed = 1, + .table_len = ARRAY_SIZE(DCDC_FIXED_1800000_VSEL_table), + .table = DCDC_FIXED_1800000_VSEL_table, }, { .name = "VDCDC3", - .min_uV = 800000, - .max_uV = 1600000, .table_len = ARRAY_SIZE(VCORE_VSEL_table), .table = VCORE_VSEL_table, }, { .name = "LDO1", - .min_uV = 1000000, - .max_uV = 3150000, .table_len = ARRAY_SIZE(TPS65023_LDO1_VSEL_table), .table = TPS65023_LDO1_VSEL_table, }, { .name = "LDO2", - .min_uV = 1050000, - .max_uV = 3300000, .table_len = ARRAY_SIZE(TPS65023_LDO2_VSEL_table), .table = TPS65023_LDO2_VSEL_table, }, @@ -457,34 +388,26 @@ static const struct tps_info tps65021_regs[] = { static const struct tps_info tps65023_regs[] = { { .name = "VDCDC1", - .min_uV = 800000, - .max_uV = 1600000, .table_len = ARRAY_SIZE(VCORE_VSEL_table), .table = VCORE_VSEL_table, }, { .name = "VDCDC2", - .min_uV = 3300000, - .max_uV = 3300000, - .fixed = 1, + .table_len = ARRAY_SIZE(DCDC_FIXED_3300000_VSEL_table), + .table = DCDC_FIXED_3300000_VSEL_table, }, { .name = "VDCDC3", - .min_uV = 1800000, - .max_uV = 1800000, - .fixed = 1, + .table_len = ARRAY_SIZE(DCDC_FIXED_1800000_VSEL_table), + .table = DCDC_FIXED_1800000_VSEL_table, }, { .name = "LDO1", - .min_uV = 1000000, - .max_uV = 3150000, .table_len = ARRAY_SIZE(TPS65023_LDO1_VSEL_table), .table = TPS65023_LDO1_VSEL_table, }, { .name = "LDO2", - .min_uV = 1050000, - .max_uV = 3300000, .table_len = ARRAY_SIZE(TPS65023_LDO2_VSEL_table), .table = TPS65023_LDO2_VSEL_table, }, diff --git a/drivers/regulator/tps6507x-regulator.c b/drivers/regulator/tps6507x-regulator.c index da38be1016aa..07d01ccdf308 100644 --- a/drivers/regulator/tps6507x-regulator.c +++ b/drivers/regulator/tps6507x-regulator.c @@ -43,58 +43,40 @@ /* Number of total regulators available */ #define TPS6507X_NUM_REGULATOR (TPS6507X_NUM_DCDC + TPS6507X_NUM_LDO) -/* Supported voltage values for regulators (in milliVolts) */ -static const u16 VDCDCx_VSEL_table[] = { - 725, 750, 775, 800, - 825, 850, 875, 900, - 925, 950, 975, 1000, - 1025, 1050, 1075, 1100, - 1125, 1150, 1175, 1200, - 1225, 1250, 1275, 1300, - 1325, 1350, 1375, 1400, - 1425, 1450, 1475, 1500, - 1550, 1600, 1650, 1700, - 1750, 1800, 1850, 1900, - 1950, 2000, 2050, 2100, - 2150, 2200, 2250, 2300, - 2350, 2400, 2450, 2500, - 2550, 2600, 2650, 2700, - 2750, 2800, 2850, 2900, - 3000, 3100, 3200, 3300, +/* Supported voltage values for regulators (in microVolts) */ +static const unsigned int VDCDCx_VSEL_table[] = { + 725000, 750000, 775000, 800000, + 825000, 850000, 875000, 900000, + 925000, 950000, 975000, 1000000, + 1025000, 1050000, 1075000, 1100000, + 1125000, 1150000, 1175000, 1200000, + 1225000, 1250000, 1275000, 1300000, + 1325000, 1350000, 1375000, 1400000, + 1425000, 1450000, 1475000, 1500000, + 1550000, 1600000, 1650000, 1700000, + 1750000, 1800000, 1850000, 1900000, + 1950000, 2000000, 2050000, 2100000, + 2150000, 2200000, 2250000, 2300000, + 2350000, 2400000, 2450000, 2500000, + 2550000, 2600000, 2650000, 2700000, + 2750000, 2800000, 2850000, 2900000, + 3000000, 3100000, 3200000, 3300000, }; -static const u16 LDO1_VSEL_table[] = { - 1000, 1100, 1200, 1250, - 1300, 1350, 1400, 1500, - 1600, 1800, 2500, 2750, - 2800, 3000, 3100, 3300, +static const unsigned int LDO1_VSEL_table[] = { + 1000000, 1100000, 1200000, 1250000, + 1300000, 1350000, 1400000, 1500000, + 1600000, 1800000, 2500000, 2750000, + 2800000, 3000000, 3100000, 3300000, }; -static const u16 LDO2_VSEL_table[] = { - 725, 750, 775, 800, - 825, 850, 875, 900, - 925, 950, 975, 1000, - 1025, 1050, 1075, 1100, - 1125, 1150, 1175, 1200, - 1225, 1250, 1275, 1300, - 1325, 1350, 1375, 1400, - 1425, 1450, 1475, 1500, - 1550, 1600, 1650, 1700, - 1750, 1800, 1850, 1900, - 1950, 2000, 2050, 2100, - 2150, 2200, 2250, 2300, - 2350, 2400, 2450, 2500, - 2550, 2600, 2650, 2700, - 2750, 2800, 2850, 2900, - 3000, 3100, 3200, 3300, -}; +/* The voltage mapping table for LDO2 is the same as VDCDCx */ +#define LDO2_VSEL_table VDCDCx_VSEL_table struct tps_info { const char *name; - unsigned min_uV; - unsigned max_uV; u8 table_len; - const u16 *table; + const unsigned int *table; /* Does DCDC high or the low register defines output voltage? */ bool defdcdc_default; @@ -103,36 +85,26 @@ struct tps_info { static struct tps_info tps6507x_pmic_regs[] = { { .name = "VDCDC1", - .min_uV = 725000, - .max_uV = 3300000, .table_len = ARRAY_SIZE(VDCDCx_VSEL_table), .table = VDCDCx_VSEL_table, }, { .name = "VDCDC2", - .min_uV = 725000, - .max_uV = 3300000, .table_len = ARRAY_SIZE(VDCDCx_VSEL_table), .table = VDCDCx_VSEL_table, }, { .name = "VDCDC3", - .min_uV = 725000, - .max_uV = 3300000, .table_len = ARRAY_SIZE(VDCDCx_VSEL_table), .table = VDCDCx_VSEL_table, }, { .name = "LDO1", - .min_uV = 1000000, - .max_uV = 3300000, .table_len = ARRAY_SIZE(LDO1_VSEL_table), .table = LDO1_VSEL_table, }, { .name = "LDO2", - .min_uV = 725000, - .max_uV = 3300000, .table_len = ARRAY_SIZE(LDO2_VSEL_table), .table = LDO2_VSEL_table, }, @@ -375,28 +347,13 @@ static int tps6507x_pmic_set_voltage_sel(struct regulator_dev *dev, return tps6507x_pmic_reg_write(tps, reg, data); } -static int tps6507x_pmic_list_voltage(struct regulator_dev *dev, - unsigned selector) -{ - struct tps6507x_pmic *tps = rdev_get_drvdata(dev); - int rid = rdev_get_id(dev); - - if (rid < TPS6507X_DCDC_1 || rid > TPS6507X_LDO_2) - return -EINVAL; - - if (selector >= tps->info[rid]->table_len) - return -EINVAL; - else - return tps->info[rid]->table[selector] * 1000; -} - static struct regulator_ops tps6507x_pmic_ops = { .is_enabled = tps6507x_pmic_is_enabled, .enable = tps6507x_pmic_enable, .disable = tps6507x_pmic_disable, .get_voltage_sel = tps6507x_pmic_get_voltage_sel, .set_voltage_sel = tps6507x_pmic_set_voltage_sel, - .list_voltage = tps6507x_pmic_list_voltage, + .list_voltage = regulator_list_voltage_table, }; static __devinit int tps6507x_pmic_probe(struct platform_device *pdev) @@ -449,6 +406,7 @@ static __devinit int tps6507x_pmic_probe(struct platform_device *pdev) tps->desc[i].name = info->name; tps->desc[i].id = i; tps->desc[i].n_voltages = info->table_len; + tps->desc[i].volt_table = info->table; tps->desc[i].ops = &tps6507x_pmic_ops; tps->desc[i].type = REGULATOR_VOLTAGE; tps->desc[i].owner = THIS_MODULE; diff --git a/drivers/regulator/tps65217-regulator.c b/drivers/regulator/tps65217-regulator.c index 9d371d2cbcae..6caa222af77a 100644 --- a/drivers/regulator/tps65217-regulator.c +++ b/drivers/regulator/tps65217-regulator.c @@ -26,7 +26,7 @@ #include <linux/regulator/machine.h> #include <linux/mfd/tps65217.h> -#define TPS65217_REGULATOR(_name, _id, _ops, _n) \ +#define TPS65217_REGULATOR(_name, _id, _ops, _n, _vr, _vm, _em, _t) \ { \ .name = _name, \ .id = _id, \ @@ -34,23 +34,23 @@ .n_voltages = _n, \ .type = REGULATOR_VOLTAGE, \ .owner = THIS_MODULE, \ + .vsel_reg = _vr, \ + .vsel_mask = _vm, \ + .enable_reg = TPS65217_REG_ENABLE, \ + .enable_mask = _em, \ + .volt_table = _t, \ } \ -#define TPS65217_INFO(_nm, _min, _max, _f1, _f2, _t, _n, _em, _vr, _vm) \ +#define TPS65217_INFO(_nm, _min, _max, _f1, _f2) \ { \ .name = _nm, \ .min_uV = _min, \ .max_uV = _max, \ .vsel_to_uv = _f1, \ .uv_to_vsel = _f2, \ - .table = _t, \ - .table_len = _n, \ - .enable_mask = _em, \ - .set_vout_reg = _vr, \ - .set_vout_mask = _vm, \ } -static const int LDO1_VSEL_table[] = { +static const unsigned int LDO1_VSEL_table[] = { 1000000, 1100000, 1200000, 1250000, 1300000, 1350000, 1400000, 1500000, 1600000, 1800000, 2500000, 2750000, @@ -78,7 +78,7 @@ static int tps65217_vsel_to_uv1(unsigned int vsel) static int tps65217_uv_to_vsel1(int uV, unsigned int *vsel) { - if ((uV < 0) && (uV > 3300000)) + if (uV < 0 || uV > 3300000) return -EINVAL; if (uV <= 1500000) @@ -112,7 +112,7 @@ static int tps65217_vsel_to_uv2(unsigned int vsel) static int tps65217_uv_to_vsel2(int uV, unsigned int *vsel) { - if ((uV < 0) && (uV > 3300000)) + if (uV < 0 || uV > 3300000) return -EINVAL; if (uV <= 1900000) @@ -127,46 +127,20 @@ static int tps65217_uv_to_vsel2(int uV, unsigned int *vsel) static struct tps_info tps65217_pmic_regs[] = { TPS65217_INFO("DCDC1", 900000, 1800000, tps65217_vsel_to_uv1, - tps65217_uv_to_vsel1, NULL, 64, TPS65217_ENABLE_DC1_EN, - TPS65217_REG_DEFDCDC1, TPS65217_DEFDCDCX_DCDC_MASK), + tps65217_uv_to_vsel1), TPS65217_INFO("DCDC2", 900000, 3300000, tps65217_vsel_to_uv1, - tps65217_uv_to_vsel1, NULL, 64, TPS65217_ENABLE_DC2_EN, - TPS65217_REG_DEFDCDC2, TPS65217_DEFDCDCX_DCDC_MASK), + tps65217_uv_to_vsel1), TPS65217_INFO("DCDC3", 900000, 1500000, tps65217_vsel_to_uv1, - tps65217_uv_to_vsel1, NULL, 64, TPS65217_ENABLE_DC3_EN, - TPS65217_REG_DEFDCDC3, TPS65217_DEFDCDCX_DCDC_MASK), - TPS65217_INFO("LDO1", 1000000, 3300000, NULL, NULL, LDO1_VSEL_table, - 16, TPS65217_ENABLE_LDO1_EN, TPS65217_REG_DEFLDO1, - TPS65217_DEFLDO1_LDO1_MASK), + tps65217_uv_to_vsel1), + TPS65217_INFO("LDO1", 1000000, 3300000, NULL, NULL), TPS65217_INFO("LDO2", 900000, 3300000, tps65217_vsel_to_uv1, - tps65217_uv_to_vsel1, NULL, 64, TPS65217_ENABLE_LDO2_EN, - TPS65217_REG_DEFLDO2, TPS65217_DEFLDO2_LDO2_MASK), + tps65217_uv_to_vsel1), TPS65217_INFO("LDO3", 1800000, 3300000, tps65217_vsel_to_uv2, - tps65217_uv_to_vsel2, NULL, 32, - TPS65217_ENABLE_LS1_EN | TPS65217_DEFLDO3_LDO3_EN, - TPS65217_REG_DEFLS1, TPS65217_DEFLDO3_LDO3_MASK), + tps65217_uv_to_vsel2), TPS65217_INFO("LDO4", 1800000, 3300000, tps65217_vsel_to_uv2, - tps65217_uv_to_vsel2, NULL, 32, - TPS65217_ENABLE_LS2_EN | TPS65217_DEFLDO4_LDO4_EN, - TPS65217_REG_DEFLS2, TPS65217_DEFLDO4_LDO4_MASK), + tps65217_uv_to_vsel2), }; -static int tps65217_pmic_is_enabled(struct regulator_dev *dev) -{ - int ret; - struct tps65217 *tps = rdev_get_drvdata(dev); - unsigned int data, rid = rdev_get_id(dev); - - if (rid < TPS65217_DCDC_1 || rid > TPS65217_LDO_4) - return -EINVAL; - - ret = tps65217_reg_read(tps, TPS65217_REG_ENABLE, &data); - if (ret) - return ret; - - return (data & tps->info[rid]->enable_mask) ? 1 : 0; -} - static int tps65217_pmic_enable(struct regulator_dev *dev) { struct tps65217 *tps = rdev_get_drvdata(dev); @@ -177,9 +151,8 @@ static int tps65217_pmic_enable(struct regulator_dev *dev) /* Enable the regulator and password protection is level 1 */ return tps65217_set_bits(tps, TPS65217_REG_ENABLE, - tps->info[rid]->enable_mask, - tps->info[rid]->enable_mask, - TPS65217_PROTECT_L1); + dev->desc->enable_mask, dev->desc->enable_mask, + TPS65217_PROTECT_L1); } static int tps65217_pmic_disable(struct regulator_dev *dev) @@ -192,25 +165,7 @@ static int tps65217_pmic_disable(struct regulator_dev *dev) /* Disable the regulator and password protection is level 1 */ return tps65217_clear_bits(tps, TPS65217_REG_ENABLE, - tps->info[rid]->enable_mask, TPS65217_PROTECT_L1); -} - -static int tps65217_pmic_get_voltage_sel(struct regulator_dev *dev) -{ - int ret; - struct tps65217 *tps = rdev_get_drvdata(dev); - unsigned int selector, rid = rdev_get_id(dev); - - if (rid < TPS65217_DCDC_1 || rid > TPS65217_LDO_4) - return -EINVAL; - - ret = tps65217_reg_read(tps, tps->info[rid]->set_vout_reg, &selector); - if (ret) - return ret; - - selector &= tps->info[rid]->set_vout_mask; - - return selector; + dev->desc->enable_mask, TPS65217_PROTECT_L1); } static int tps65217_pmic_set_voltage_sel(struct regulator_dev *dev, @@ -221,8 +176,7 @@ static int tps65217_pmic_set_voltage_sel(struct regulator_dev *dev, unsigned int rid = rdev_get_id(dev); /* Set the voltage based on vsel value and write protect level is 2 */ - ret = tps65217_set_bits(tps, tps->info[rid]->set_vout_reg, - tps->info[rid]->set_vout_mask, + ret = tps65217_set_bits(tps, dev->desc->vsel_reg, dev->desc->vsel_mask, selector, TPS65217_PROTECT_L2); /* Set GO bit for DCDCx to initiate voltage transistion */ @@ -252,10 +206,10 @@ static int tps65217_pmic_map_voltage(struct regulator_dev *dev, if (rid < TPS65217_DCDC_1 || rid > TPS65217_LDO_4) return -EINVAL; - if (min_uV < tps->info[rid]->min_uV || min_uV > tps->info[rid]->max_uV) - return -EINVAL; + if (min_uV < tps->info[rid]->min_uV) + min_uV = tps->info[rid]->min_uV; - if (max_uV < tps->info[rid]->min_uV || max_uV > tps->info[rid]->max_uV) + if (max_uV < tps->info[rid]->min_uV || min_uV > tps->info[rid]->max_uV) return -EINVAL; ret = tps->info[rid]->uv_to_vsel(min_uV, &sel); @@ -274,21 +228,18 @@ static int tps65217_pmic_list_voltage(struct regulator_dev *dev, if (rid < TPS65217_DCDC_1 || rid > TPS65217_LDO_4) return -EINVAL; - if (selector >= tps->info[rid]->table_len) + if (selector >= dev->desc->n_voltages) return -EINVAL; - if (tps->info[rid]->table) - return tps->info[rid]->table[selector]; - return tps->info[rid]->vsel_to_uv(selector); } /* Operations permitted on DCDCx, LDO2, LDO3 and LDO4 */ static struct regulator_ops tps65217_pmic_ops = { - .is_enabled = tps65217_pmic_is_enabled, + .is_enabled = regulator_is_enabled_regmap, .enable = tps65217_pmic_enable, .disable = tps65217_pmic_disable, - .get_voltage_sel = tps65217_pmic_get_voltage_sel, + .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_sel = tps65217_pmic_set_voltage_sel, .list_voltage = tps65217_pmic_list_voltage, .map_voltage = tps65217_pmic_map_voltage, @@ -296,22 +247,38 @@ static struct regulator_ops tps65217_pmic_ops = { /* Operations permitted on LDO1 */ static struct regulator_ops tps65217_pmic_ldo1_ops = { - .is_enabled = tps65217_pmic_is_enabled, + .is_enabled = regulator_is_enabled_regmap, .enable = tps65217_pmic_enable, .disable = tps65217_pmic_disable, - .get_voltage_sel = tps65217_pmic_get_voltage_sel, + .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_sel = tps65217_pmic_set_voltage_sel, - .list_voltage = tps65217_pmic_list_voltage, + .list_voltage = regulator_list_voltage_table, }; static const struct regulator_desc regulators[] = { - TPS65217_REGULATOR("DCDC1", TPS65217_DCDC_1, tps65217_pmic_ops, 64), - TPS65217_REGULATOR("DCDC2", TPS65217_DCDC_2, tps65217_pmic_ops, 64), - TPS65217_REGULATOR("DCDC3", TPS65217_DCDC_3, tps65217_pmic_ops, 64), - TPS65217_REGULATOR("LDO1", TPS65217_LDO_1, tps65217_pmic_ldo1_ops, 16), - TPS65217_REGULATOR("LDO2", TPS65217_LDO_2, tps65217_pmic_ops, 64), - TPS65217_REGULATOR("LDO3", TPS65217_LDO_3, tps65217_pmic_ops, 32), - TPS65217_REGULATOR("LDO4", TPS65217_LDO_4, tps65217_pmic_ops, 32), + TPS65217_REGULATOR("DCDC1", TPS65217_DCDC_1, tps65217_pmic_ops, 64, + TPS65217_REG_DEFDCDC1, TPS65217_DEFDCDCX_DCDC_MASK, + TPS65217_ENABLE_DC1_EN, NULL), + TPS65217_REGULATOR("DCDC2", TPS65217_DCDC_2, tps65217_pmic_ops, 64, + TPS65217_REG_DEFDCDC2, TPS65217_DEFDCDCX_DCDC_MASK, + TPS65217_ENABLE_DC2_EN, NULL), + TPS65217_REGULATOR("DCDC3", TPS65217_DCDC_3, tps65217_pmic_ops, 64, + TPS65217_REG_DEFDCDC3, TPS65217_DEFDCDCX_DCDC_MASK, + TPS65217_ENABLE_DC3_EN, NULL), + TPS65217_REGULATOR("LDO1", TPS65217_LDO_1, tps65217_pmic_ldo1_ops, 16, + TPS65217_REG_DEFLDO1, TPS65217_DEFLDO1_LDO1_MASK, + TPS65217_ENABLE_LDO1_EN, LDO1_VSEL_table), + TPS65217_REGULATOR("LDO2", TPS65217_LDO_2, tps65217_pmic_ops, 64, + TPS65217_REG_DEFLDO2, TPS65217_DEFLDO2_LDO2_MASK, + TPS65217_ENABLE_LDO2_EN, NULL), + TPS65217_REGULATOR("LDO3", TPS65217_LDO_3, tps65217_pmic_ops, 32, + TPS65217_REG_DEFLS1, TPS65217_DEFLDO3_LDO3_MASK, + TPS65217_ENABLE_LS1_EN | TPS65217_DEFLDO3_LDO3_EN, + NULL), + TPS65217_REGULATOR("LDO4", TPS65217_LDO_4, tps65217_pmic_ops, 32, + TPS65217_REG_DEFLS2, TPS65217_DEFLDO4_LDO4_MASK, + TPS65217_ENABLE_LS2_EN | TPS65217_DEFLDO4_LDO4_EN, + NULL), }; static int __devinit tps65217_regulator_probe(struct platform_device *pdev) @@ -326,6 +293,7 @@ static int __devinit tps65217_regulator_probe(struct platform_device *pdev) tps->info[pdev->id] = info; config.dev = &pdev->dev; + config.of_node = pdev->dev.of_node; config.init_data = pdev->dev.platform_data; config.driver_data = tps; diff --git a/drivers/regulator/tps6524x-regulator.c b/drivers/regulator/tps6524x-regulator.c index 1b299aacf22f..947ece933d90 100644 --- a/drivers/regulator/tps6524x-regulator.c +++ b/drivers/regulator/tps6524x-regulator.c @@ -110,9 +110,6 @@ #define N_SWITCH 2 #define N_REGULATORS (N_DCDC + N_LDO + N_SWITCH) -#define FIXED_ILIMSEL BIT(0) -#define FIXED_VOLTAGE BIT(1) - #define CMD_READ(reg) ((reg) << 6) #define CMD_WRITE(reg) (BIT(5) | (reg) << 6) #define STAT_CLK BIT(3) @@ -129,12 +126,9 @@ struct field { struct supply_info { const char *name; int n_voltages; - const int *voltages; - int fixed_voltage; + const unsigned int *voltages; int n_ilimsels; - const int *ilimsels; - int fixed_ilimsel; - int flags; + const unsigned int *ilimsels; struct field enable, voltage, ilimsel; }; @@ -307,7 +301,7 @@ static int write_field(struct tps6524x *hw, const struct field *field, val << field->shift); } -static const int dcdc1_voltages[] = { +static const unsigned int dcdc1_voltages[] = { 800000, 825000, 850000, 875000, 900000, 925000, 950000, 975000, 1000000, 1025000, 1050000, 1075000, @@ -318,7 +312,7 @@ static const int dcdc1_voltages[] = { 1500000, 1525000, 1550000, 1575000, }; -static const int dcdc2_voltages[] = { +static const unsigned int dcdc2_voltages[] = { 1400000, 1450000, 1500000, 1550000, 1600000, 1650000, 1700000, 1750000, 1800000, 1850000, 1900000, 1950000, @@ -329,7 +323,7 @@ static const int dcdc2_voltages[] = { 2800000, 2850000, 2900000, 2950000, }; -static const int dcdc3_voltages[] = { +static const unsigned int dcdc3_voltages[] = { 2400000, 2450000, 2500000, 2550000, 2600000, 2650000, 2700000, 2750000, 2800000, 2850000, 2900000, 2950000, 3000000, 3050000, 3100000, @@ -337,38 +331,54 @@ static const int dcdc3_voltages[] = { 3400000, 3450000, 3500000, 3550000, 3600000, }; -static const int ldo1_voltages[] = { +static const unsigned int ldo1_voltages[] = { 4300000, 4350000, 4400000, 4450000, 4500000, 4550000, 4600000, 4650000, 4700000, 4750000, 4800000, 4850000, 4900000, 4950000, 5000000, 5050000, }; -static const int ldo2_voltages[] = { +static const unsigned int ldo2_voltages[] = { 1100000, 1150000, 1200000, 1250000, 1300000, 1700000, 1750000, 1800000, 1850000, 1900000, 3150000, 3200000, 3250000, 3300000, 3350000, 3400000, }; -static const int ldo_ilimsel[] = { +static const unsigned int fixed_5000000_voltage[] = { + 5000000 +}; + +static const unsigned int ldo_ilimsel[] = { 400000, 1500000 }; -static const int usb_ilimsel[] = { +static const unsigned int usb_ilimsel[] = { 200000, 400000, 800000, 1000000 }; +static const unsigned int fixed_2400000_ilimsel[] = { + 2400000 +}; + +static const unsigned int fixed_1200000_ilimsel[] = { + 1200000 +}; + +static const unsigned int fixed_400000_ilimsel[] = { + 400000 +}; + #define __MK_FIELD(_reg, _mask, _shift) \ { .reg = (_reg), .mask = (_mask), .shift = (_shift), } static const struct supply_info supply_info[N_REGULATORS] = { { .name = "DCDC1", - .flags = FIXED_ILIMSEL, .n_voltages = ARRAY_SIZE(dcdc1_voltages), .voltages = dcdc1_voltages, - .fixed_ilimsel = 2400000, + .n_ilimsels = ARRAY_SIZE(fixed_2400000_ilimsel), + .ilimsels = fixed_2400000_ilimsel, .enable = __MK_FIELD(REG_DCDC_EN, DCDCDCDC_EN_MASK, DCDCDCDC1_EN_SHIFT), .voltage = __MK_FIELD(REG_DCDC_SET, DCDC_VDCDC_MASK, @@ -376,10 +386,10 @@ static const struct supply_info supply_info[N_REGULATORS] = { }, { .name = "DCDC2", - .flags = FIXED_ILIMSEL, .n_voltages = ARRAY_SIZE(dcdc2_voltages), .voltages = dcdc2_voltages, - .fixed_ilimsel = 1200000, + .n_ilimsels = ARRAY_SIZE(fixed_1200000_ilimsel), + .ilimsels = fixed_1200000_ilimsel, .enable = __MK_FIELD(REG_DCDC_EN, DCDCDCDC_EN_MASK, DCDCDCDC2_EN_SHIFT), .voltage = __MK_FIELD(REG_DCDC_SET, DCDC_VDCDC_MASK, @@ -387,10 +397,10 @@ static const struct supply_info supply_info[N_REGULATORS] = { }, { .name = "DCDC3", - .flags = FIXED_ILIMSEL, .n_voltages = ARRAY_SIZE(dcdc3_voltages), .voltages = dcdc3_voltages, - .fixed_ilimsel = 1200000, + .n_ilimsels = ARRAY_SIZE(fixed_1200000_ilimsel), + .ilimsels = fixed_1200000_ilimsel, .enable = __MK_FIELD(REG_DCDC_EN, DCDCDCDC_EN_MASK, DCDCDCDC3_EN_SHIFT), .voltage = __MK_FIELD(REG_DCDC_SET, DCDC_VDCDC_MASK, @@ -424,8 +434,8 @@ static const struct supply_info supply_info[N_REGULATORS] = { }, { .name = "USB", - .flags = FIXED_VOLTAGE, - .fixed_voltage = 5000000, + .n_voltages = ARRAY_SIZE(fixed_5000000_voltage), + .voltages = fixed_5000000_voltage, .n_ilimsels = ARRAY_SIZE(usb_ilimsel), .ilimsels = usb_ilimsel, .enable = __MK_FIELD(REG_BLOCK_EN, BLOCK_MASK, @@ -435,29 +445,15 @@ static const struct supply_info supply_info[N_REGULATORS] = { }, { .name = "LCD", - .flags = FIXED_VOLTAGE | FIXED_ILIMSEL, - .fixed_voltage = 5000000, - .fixed_ilimsel = 400000, + .n_voltages = ARRAY_SIZE(fixed_5000000_voltage), + .voltages = fixed_5000000_voltage, + .n_ilimsels = ARRAY_SIZE(fixed_400000_ilimsel), + .ilimsels = fixed_400000_ilimsel, .enable = __MK_FIELD(REG_BLOCK_EN, BLOCK_MASK, BLOCK_LCD_SHIFT), }, }; -static int list_voltage(struct regulator_dev *rdev, unsigned selector) -{ - const struct supply_info *info; - struct tps6524x *hw; - - hw = rdev_get_drvdata(rdev); - info = &supply_info[rdev_get_id(rdev)]; - - if (info->flags & FIXED_VOLTAGE) - return selector ? -EINVAL : info->fixed_voltage; - - return ((selector < info->n_voltages) ? - info->voltages[selector] : -EINVAL); -} - static int set_voltage_sel(struct regulator_dev *rdev, unsigned selector) { const struct supply_info *info; @@ -466,7 +462,7 @@ static int set_voltage_sel(struct regulator_dev *rdev, unsigned selector) hw = rdev_get_drvdata(rdev); info = &supply_info[rdev_get_id(rdev)]; - if (info->flags & FIXED_VOLTAGE) + if (rdev->desc->n_voltages == 1) return -EINVAL; return write_field(hw, &info->voltage, selector); @@ -481,7 +477,7 @@ static int get_voltage_sel(struct regulator_dev *rdev) hw = rdev_get_drvdata(rdev); info = &supply_info[rdev_get_id(rdev)]; - if (info->flags & FIXED_VOLTAGE) + if (rdev->desc->n_voltages == 1) return 0; ret = read_field(hw, &info->voltage); @@ -503,7 +499,7 @@ static int set_current_limit(struct regulator_dev *rdev, int min_uA, hw = rdev_get_drvdata(rdev); info = &supply_info[rdev_get_id(rdev)]; - if (info->flags & FIXED_ILIMSEL) + if (info->n_ilimsels == 1) return -EINVAL; for (i = 0; i < info->n_ilimsels; i++) @@ -526,8 +522,8 @@ static int get_current_limit(struct regulator_dev *rdev) hw = rdev_get_drvdata(rdev); info = &supply_info[rdev_get_id(rdev)]; - if (info->flags & FIXED_ILIMSEL) - return info->fixed_ilimsel; + if (info->n_ilimsels == 1) + return info->ilimsels[0]; ret = read_field(hw, &info->ilimsel); if (ret < 0) @@ -577,7 +573,7 @@ static struct regulator_ops regulator_ops = { .disable = disable_supply, .get_voltage_sel = get_voltage_sel, .set_voltage_sel = set_voltage_sel, - .list_voltage = list_voltage, + .list_voltage = regulator_list_voltage_table, .set_current_limit = set_current_limit, .get_current_limit = get_current_limit, }; @@ -629,13 +625,11 @@ static int __devinit pmic_probe(struct spi_device *spi) hw->desc[i].name = info->name; hw->desc[i].id = i; hw->desc[i].n_voltages = info->n_voltages; + hw->desc[i].volt_table = info->voltages; hw->desc[i].ops = ®ulator_ops; hw->desc[i].type = REGULATOR_VOLTAGE; hw->desc[i].owner = THIS_MODULE; - if (info->flags & FIXED_VOLTAGE) - hw->desc[i].n_voltages = 1; - config.dev = dev; config.init_data = init_data; config.driver_data = hw; diff --git a/drivers/regulator/tps6586x-regulator.c b/drivers/regulator/tps6586x-regulator.c index c0a214575380..e6da90ab5153 100644 --- a/drivers/regulator/tps6586x-regulator.c +++ b/drivers/regulator/tps6586x-regulator.c @@ -63,8 +63,6 @@ struct tps6586x_regulator { int enable_bit[2]; int enable_reg[2]; - int *voltages; - /* for DVM regulators */ int go_reg; int go_bit; @@ -72,22 +70,9 @@ struct tps6586x_regulator { static inline struct device *to_tps6586x_dev(struct regulator_dev *rdev) { - return rdev_get_dev(rdev)->parent->parent; + return rdev_get_dev(rdev)->parent; } -static int tps6586x_list_voltage(struct regulator_dev *rdev, unsigned selector) -{ - struct tps6586x_regulator *info = rdev_get_drvdata(rdev); - int rid = rdev_get_id(rdev); - - /* LDO0 has minimal voltage 1.2V rather than 1.25V */ - if ((rid == TPS6586X_ID_LDO_0) && (selector == 0)) - return (info->voltages[0] - 50) * 1000; - - return info->voltages[selector] * 1000; -} - - static int tps6586x_set_voltage_sel(struct regulator_dev *rdev, unsigned selector) { @@ -168,7 +153,7 @@ static int tps6586x_regulator_is_enabled(struct regulator_dev *rdev) } static struct regulator_ops tps6586x_regulator_ops = { - .list_voltage = tps6586x_list_voltage, + .list_voltage = regulator_list_voltage_table, .get_voltage_sel = tps6586x_get_voltage_sel, .set_voltage_sel = tps6586x_set_voltage_sel, @@ -177,39 +162,45 @@ static struct regulator_ops tps6586x_regulator_ops = { .disable = tps6586x_regulator_disable, }; -static int tps6586x_ldo_voltages[] = { - 1250, 1500, 1800, 2500, 2700, 2850, 3100, 3300, +static const unsigned int tps6586x_ldo0_voltages[] = { + 1200000, 1500000, 1800000, 2500000, 2700000, 2850000, 3100000, 3300000, +}; + +static const unsigned int tps6586x_ldo4_voltages[] = { + 1700000, 1725000, 1750000, 1775000, 1800000, 1825000, 1850000, 1875000, + 1900000, 1925000, 1950000, 1975000, 2000000, 2025000, 2050000, 2075000, + 2100000, 2125000, 2150000, 2175000, 2200000, 2225000, 2250000, 2275000, + 2300000, 2325000, 2350000, 2375000, 2400000, 2425000, 2450000, 2475000, }; -static int tps6586x_ldo4_voltages[] = { - 1700, 1725, 1750, 1775, 1800, 1825, 1850, 1875, - 1900, 1925, 1950, 1975, 2000, 2025, 2050, 2075, - 2100, 2125, 2150, 2175, 2200, 2225, 2250, 2275, - 2300, 2325, 2350, 2375, 2400, 2425, 2450, 2475, +static const unsigned int tps6586x_ldo_voltages[] = { + 1250000, 1500000, 1800000, 2500000, 2700000, 2850000, 3100000, 3300000, }; -static int tps6586x_sm2_voltages[] = { - 3000, 3050, 3100, 3150, 3200, 3250, 3300, 3350, - 3400, 3450, 3500, 3550, 3600, 3650, 3700, 3750, - 3800, 3850, 3900, 3950, 4000, 4050, 4100, 4150, - 4200, 4250, 4300, 4350, 4400, 4450, 4500, 4550, +static const unsigned int tps6586x_sm2_voltages[] = { + 3000000, 3050000, 3100000, 3150000, 3200000, 3250000, 3300000, 3350000, + 3400000, 3450000, 3500000, 3550000, 3600000, 3650000, 3700000, 3750000, + 3800000, 3850000, 3900000, 3950000, 4000000, 4050000, 4100000, 4150000, + 4200000, 4250000, 4300000, 4350000, 4400000, 4450000, 4500000, 4550000, }; -static int tps6586x_dvm_voltages[] = { - 725, 750, 775, 800, 825, 850, 875, 900, - 925, 950, 975, 1000, 1025, 1050, 1075, 1100, - 1125, 1150, 1175, 1200, 1225, 1250, 1275, 1300, - 1325, 1350, 1375, 1400, 1425, 1450, 1475, 1500, +static const unsigned int tps6586x_dvm_voltages[] = { + 725000, 750000, 775000, 800000, 825000, 850000, 875000, 900000, + 925000, 950000, 975000, 1000000, 1025000, 1050000, 1075000, 1100000, + 1125000, 1150000, 1175000, 1200000, 1225000, 1250000, 1275000, 1300000, + 1325000, 1350000, 1375000, 1400000, 1425000, 1450000, 1475000, 1500000, }; -#define TPS6586X_REGULATOR(_id, vdata, vreg, shift, nbits, \ +#define TPS6586X_REGULATOR(_id, _pin_name, vdata, vreg, shift, nbits, \ ereg0, ebit0, ereg1, ebit1) \ .desc = { \ + .supply_name = _pin_name, \ .name = "REG-" #_id, \ .ops = &tps6586x_regulator_ops, \ .type = REGULATOR_VOLTAGE, \ .id = TPS6586X_ID_##_id, \ .n_voltages = ARRAY_SIZE(tps6586x_##vdata##_voltages), \ + .volt_table = tps6586x_##vdata##_voltages, \ .owner = THIS_MODULE, \ }, \ .volt_reg = TPS6586X_##vreg, \ @@ -218,44 +209,45 @@ static int tps6586x_dvm_voltages[] = { .enable_reg[0] = TPS6586X_SUPPLY##ereg0, \ .enable_bit[0] = (ebit0), \ .enable_reg[1] = TPS6586X_SUPPLY##ereg1, \ - .enable_bit[1] = (ebit1), \ - .voltages = tps6586x_##vdata##_voltages, + .enable_bit[1] = (ebit1), #define TPS6586X_REGULATOR_DVM_GOREG(goreg, gobit) \ .go_reg = TPS6586X_##goreg, \ .go_bit = (gobit), -#define TPS6586X_LDO(_id, vdata, vreg, shift, nbits, \ +#define TPS6586X_LDO(_id, _pname, vdata, vreg, shift, nbits, \ ereg0, ebit0, ereg1, ebit1) \ { \ - TPS6586X_REGULATOR(_id, vdata, vreg, shift, nbits, \ + TPS6586X_REGULATOR(_id, _pname, vdata, vreg, shift, nbits, \ ereg0, ebit0, ereg1, ebit1) \ } -#define TPS6586X_DVM(_id, vdata, vreg, shift, nbits, \ +#define TPS6586X_DVM(_id, _pname, vdata, vreg, shift, nbits, \ ereg0, ebit0, ereg1, ebit1, goreg, gobit) \ { \ - TPS6586X_REGULATOR(_id, vdata, vreg, shift, nbits, \ + TPS6586X_REGULATOR(_id, _pname, vdata, vreg, shift, nbits, \ ereg0, ebit0, ereg1, ebit1) \ TPS6586X_REGULATOR_DVM_GOREG(goreg, gobit) \ } static struct tps6586x_regulator tps6586x_regulator[] = { - TPS6586X_LDO(LDO_0, ldo, SUPPLYV1, 5, 3, ENC, 0, END, 0), - TPS6586X_LDO(LDO_3, ldo, SUPPLYV4, 0, 3, ENC, 2, END, 2), - TPS6586X_LDO(LDO_5, ldo, SUPPLYV6, 0, 3, ENE, 6, ENE, 6), - TPS6586X_LDO(LDO_6, ldo, SUPPLYV3, 0, 3, ENC, 4, END, 4), - TPS6586X_LDO(LDO_7, ldo, SUPPLYV3, 3, 3, ENC, 5, END, 5), - TPS6586X_LDO(LDO_8, ldo, SUPPLYV2, 5, 3, ENC, 6, END, 6), - TPS6586X_LDO(LDO_9, ldo, SUPPLYV6, 3, 3, ENE, 7, ENE, 7), - TPS6586X_LDO(LDO_RTC, ldo, SUPPLYV4, 3, 3, V4, 7, V4, 7), - TPS6586X_LDO(LDO_1, dvm, SUPPLYV1, 0, 5, ENC, 1, END, 1), - TPS6586X_LDO(SM_2, sm2, SUPPLYV2, 0, 5, ENC, 7, END, 7), - - TPS6586X_DVM(LDO_2, dvm, LDO2BV1, 0, 5, ENA, 3, ENB, 3, VCC2, 6), - TPS6586X_DVM(LDO_4, ldo4, LDO4V1, 0, 5, ENC, 3, END, 3, VCC1, 6), - TPS6586X_DVM(SM_0, dvm, SM0V1, 0, 5, ENA, 1, ENB, 1, VCC1, 2), - TPS6586X_DVM(SM_1, dvm, SM1V1, 0, 5, ENA, 0, ENB, 0, VCC1, 0), + TPS6586X_LDO(LDO_0, "vinldo01", ldo0, SUPPLYV1, 5, 3, ENC, 0, END, 0), + TPS6586X_LDO(LDO_3, "vinldo23", ldo, SUPPLYV4, 0, 3, ENC, 2, END, 2), + TPS6586X_LDO(LDO_5, NULL, ldo, SUPPLYV6, 0, 3, ENE, 6, ENE, 6), + TPS6586X_LDO(LDO_6, "vinldo678", ldo, SUPPLYV3, 0, 3, ENC, 4, END, 4), + TPS6586X_LDO(LDO_7, "vinldo678", ldo, SUPPLYV3, 3, 3, ENC, 5, END, 5), + TPS6586X_LDO(LDO_8, "vinldo678", ldo, SUPPLYV2, 5, 3, ENC, 6, END, 6), + TPS6586X_LDO(LDO_9, "vinldo9", ldo, SUPPLYV6, 3, 3, ENE, 7, ENE, 7), + TPS6586X_LDO(LDO_RTC, NULL, ldo, SUPPLYV4, 3, 3, V4, 7, V4, 7), + TPS6586X_LDO(LDO_1, "vinldo01", dvm, SUPPLYV1, 0, 5, ENC, 1, END, 1), + TPS6586X_LDO(SM_2, "sm2", sm2, SUPPLYV2, 0, 5, ENC, 7, END, 7), + + TPS6586X_DVM(LDO_2, "vinldo23", dvm, LDO2BV1, 0, 5, ENA, 3, + ENB, 3, VCC2, 6), + TPS6586X_DVM(LDO_4, "vinldo4", ldo4, LDO4V1, 0, 5, ENC, 3, + END, 3, VCC1, 6), + TPS6586X_DVM(SM_0, "sm0", dvm, SM0V1, 0, 5, ENA, 1, ENB, 1, VCC1, 2), + TPS6586X_DVM(SM_1, "sm1", dvm, SM1V1, 0, 5, ENA, 0, ENB, 0, VCC1, 0), }; /* @@ -362,7 +354,7 @@ static int __devinit tps6586x_regulator_probe(struct platform_device *pdev) if (err) return err; - config.dev = &pdev->dev; + config.dev = pdev->dev.parent; config.of_node = pdev->dev.of_node; config.init_data = pdev->dev.platform_data; config.driver_data = ri; diff --git a/drivers/regulator/tps65910-regulator.c b/drivers/regulator/tps65910-regulator.c index 6bf864b4bdf6..793adda560c3 100644 --- a/drivers/regulator/tps65910-regulator.c +++ b/drivers/regulator/tps65910-regulator.c @@ -31,160 +31,147 @@ TPS65910_SLEEP_CONTROL_EXT_INPUT_EN3 | \ TPS65911_SLEEP_CONTROL_EXT_INPUT_SLEEP) -/* supported VIO voltages in millivolts */ -static const u16 VIO_VSEL_table[] = { - 1500, 1800, 2500, 3300, +/* supported VIO voltages in microvolts */ +static const unsigned int VIO_VSEL_table[] = { + 1500000, 1800000, 2500000, 3300000, }; /* VSEL tables for TPS65910 specific LDOs and dcdc's */ -/* supported VDD3 voltages in millivolts */ -static const u16 VDD3_VSEL_table[] = { - 5000, +/* supported VDD3 voltages in microvolts */ +static const unsigned int VDD3_VSEL_table[] = { + 5000000, }; -/* supported VDIG1 voltages in millivolts */ -static const u16 VDIG1_VSEL_table[] = { - 1200, 1500, 1800, 2700, +/* supported VDIG1 voltages in microvolts */ +static const unsigned int VDIG1_VSEL_table[] = { + 1200000, 1500000, 1800000, 2700000, }; -/* supported VDIG2 voltages in millivolts */ -static const u16 VDIG2_VSEL_table[] = { - 1000, 1100, 1200, 1800, +/* supported VDIG2 voltages in microvolts */ +static const unsigned int VDIG2_VSEL_table[] = { + 1000000, 1100000, 1200000, 1800000, }; -/* supported VPLL voltages in millivolts */ -static const u16 VPLL_VSEL_table[] = { - 1000, 1100, 1800, 2500, +/* supported VPLL voltages in microvolts */ +static const unsigned int VPLL_VSEL_table[] = { + 1000000, 1100000, 1800000, 2500000, }; -/* supported VDAC voltages in millivolts */ -static const u16 VDAC_VSEL_table[] = { - 1800, 2600, 2800, 2850, +/* supported VDAC voltages in microvolts */ +static const unsigned int VDAC_VSEL_table[] = { + 1800000, 2600000, 2800000, 2850000, }; -/* supported VAUX1 voltages in millivolts */ -static const u16 VAUX1_VSEL_table[] = { - 1800, 2500, 2800, 2850, +/* supported VAUX1 voltages in microvolts */ +static const unsigned int VAUX1_VSEL_table[] = { + 1800000, 2500000, 2800000, 2850000, }; -/* supported VAUX2 voltages in millivolts */ -static const u16 VAUX2_VSEL_table[] = { - 1800, 2800, 2900, 3300, +/* supported VAUX2 voltages in microvolts */ +static const unsigned int VAUX2_VSEL_table[] = { + 1800000, 2800000, 2900000, 3300000, }; -/* supported VAUX33 voltages in millivolts */ -static const u16 VAUX33_VSEL_table[] = { - 1800, 2000, 2800, 3300, +/* supported VAUX33 voltages in microvolts */ +static const unsigned int VAUX33_VSEL_table[] = { + 1800000, 2000000, 2800000, 3300000, }; -/* supported VMMC voltages in millivolts */ -static const u16 VMMC_VSEL_table[] = { - 1800, 2800, 3000, 3300, +/* supported VMMC voltages in microvolts */ +static const unsigned int VMMC_VSEL_table[] = { + 1800000, 2800000, 3000000, 3300000, }; struct tps_info { const char *name; - unsigned min_uV; - unsigned max_uV; + const char *vin_name; u8 n_voltages; - const u16 *voltage_table; + const unsigned int *voltage_table; int enable_time_us; }; static struct tps_info tps65910_regs[] = { { .name = "vrtc", + .vin_name = "vcc7", .enable_time_us = 2200, }, { .name = "vio", - .min_uV = 1500000, - .max_uV = 3300000, + .vin_name = "vccio", .n_voltages = ARRAY_SIZE(VIO_VSEL_table), .voltage_table = VIO_VSEL_table, .enable_time_us = 350, }, { .name = "vdd1", - .min_uV = 600000, - .max_uV = 4500000, + .vin_name = "vcc1", .enable_time_us = 350, }, { .name = "vdd2", - .min_uV = 600000, - .max_uV = 4500000, + .vin_name = "vcc2", .enable_time_us = 350, }, { .name = "vdd3", - .min_uV = 5000000, - .max_uV = 5000000, .n_voltages = ARRAY_SIZE(VDD3_VSEL_table), .voltage_table = VDD3_VSEL_table, .enable_time_us = 200, }, { .name = "vdig1", - .min_uV = 1200000, - .max_uV = 2700000, + .vin_name = "vcc6", .n_voltages = ARRAY_SIZE(VDIG1_VSEL_table), .voltage_table = VDIG1_VSEL_table, .enable_time_us = 100, }, { .name = "vdig2", - .min_uV = 1000000, - .max_uV = 1800000, + .vin_name = "vcc6", .n_voltages = ARRAY_SIZE(VDIG2_VSEL_table), .voltage_table = VDIG2_VSEL_table, .enable_time_us = 100, }, { .name = "vpll", - .min_uV = 1000000, - .max_uV = 2500000, + .vin_name = "vcc5", .n_voltages = ARRAY_SIZE(VPLL_VSEL_table), .voltage_table = VPLL_VSEL_table, .enable_time_us = 100, }, { .name = "vdac", - .min_uV = 1800000, - .max_uV = 2850000, + .vin_name = "vcc5", .n_voltages = ARRAY_SIZE(VDAC_VSEL_table), .voltage_table = VDAC_VSEL_table, .enable_time_us = 100, }, { .name = "vaux1", - .min_uV = 1800000, - .max_uV = 2850000, + .vin_name = "vcc4", .n_voltages = ARRAY_SIZE(VAUX1_VSEL_table), .voltage_table = VAUX1_VSEL_table, .enable_time_us = 100, }, { .name = "vaux2", - .min_uV = 1800000, - .max_uV = 3300000, + .vin_name = "vcc4", .n_voltages = ARRAY_SIZE(VAUX2_VSEL_table), .voltage_table = VAUX2_VSEL_table, .enable_time_us = 100, }, { .name = "vaux33", - .min_uV = 1800000, - .max_uV = 3300000, + .vin_name = "vcc3", .n_voltages = ARRAY_SIZE(VAUX33_VSEL_table), .voltage_table = VAUX33_VSEL_table, .enable_time_us = 100, }, { .name = "vmmc", - .min_uV = 1800000, - .max_uV = 3300000, + .vin_name = "vcc3", .n_voltages = ARRAY_SIZE(VMMC_VSEL_table), .voltage_table = VMMC_VSEL_table, .enable_time_us = 100, @@ -194,91 +181,79 @@ static struct tps_info tps65910_regs[] = { static struct tps_info tps65911_regs[] = { { .name = "vrtc", + .vin_name = "vcc7", .enable_time_us = 2200, }, { .name = "vio", - .min_uV = 1500000, - .max_uV = 3300000, + .vin_name = "vccio", .n_voltages = ARRAY_SIZE(VIO_VSEL_table), .voltage_table = VIO_VSEL_table, .enable_time_us = 350, }, { .name = "vdd1", - .min_uV = 600000, - .max_uV = 4500000, - .n_voltages = 73, + .vin_name = "vcc1", + .n_voltages = 0x4C, .enable_time_us = 350, }, { .name = "vdd2", - .min_uV = 600000, - .max_uV = 4500000, - .n_voltages = 73, + .vin_name = "vcc2", + .n_voltages = 0x4C, .enable_time_us = 350, }, { .name = "vddctrl", - .min_uV = 600000, - .max_uV = 1400000, - .n_voltages = 65, + .n_voltages = 0x44, .enable_time_us = 900, }, { .name = "ldo1", - .min_uV = 1000000, - .max_uV = 3300000, - .n_voltages = 47, + .vin_name = "vcc6", + .n_voltages = 0x33, .enable_time_us = 420, }, { .name = "ldo2", - .min_uV = 1000000, - .max_uV = 3300000, - .n_voltages = 47, + .vin_name = "vcc6", + .n_voltages = 0x33, .enable_time_us = 420, }, { .name = "ldo3", - .min_uV = 1000000, - .max_uV = 3300000, - .n_voltages = 24, + .vin_name = "vcc5", + .n_voltages = 0x1A, .enable_time_us = 230, }, { .name = "ldo4", - .min_uV = 1000000, - .max_uV = 3300000, - .n_voltages = 47, + .vin_name = "vcc5", + .n_voltages = 0x33, .enable_time_us = 230, }, { .name = "ldo5", - .min_uV = 1000000, - .max_uV = 3300000, - .n_voltages = 24, + .vin_name = "vcc4", + .n_voltages = 0x1A, .enable_time_us = 230, }, { .name = "ldo6", - .min_uV = 1000000, - .max_uV = 3300000, - .n_voltages = 24, + .vin_name = "vcc3", + .n_voltages = 0x1A, .enable_time_us = 230, }, { .name = "ldo7", - .min_uV = 1000000, - .max_uV = 3300000, - .n_voltages = 24, + .vin_name = "vcc3", + .n_voltages = 0x1A, .enable_time_us = 230, }, { .name = "ldo8", - .min_uV = 1000000, - .max_uV = 3300000, - .n_voltages = 24, + .vin_name = "vcc3", + .n_voltages = 0x1A, .enable_time_us = 230, }, }; @@ -321,7 +296,6 @@ struct tps65910_reg { struct tps65910 *mfd; struct regulator_dev **rdev; struct tps_info **info; - struct mutex mutex; int num_regulators; int mode; int (*get_ctrl_reg)(int); @@ -329,71 +303,6 @@ struct tps65910_reg { unsigned int board_ext_control[TPS65910_NUM_REGS]; }; -static inline int tps65910_read(struct tps65910_reg *pmic, u8 reg) -{ - unsigned int val; - int err; - - err = tps65910_reg_read(pmic->mfd, reg, &val); - if (err) - return err; - - return val; -} - -static int tps65910_modify_bits(struct tps65910_reg *pmic, u8 reg, - u8 set_mask, u8 clear_mask) -{ - int err, data; - - mutex_lock(&pmic->mutex); - - data = tps65910_read(pmic, reg); - if (data < 0) { - dev_err(pmic->mfd->dev, "Read from reg 0x%x failed\n", reg); - err = data; - goto out; - } - - data &= ~clear_mask; - data |= set_mask; - err = tps65910_reg_write(pmic->mfd, reg, data); - if (err) - dev_err(pmic->mfd->dev, "Write for reg 0x%x failed\n", reg); - -out: - mutex_unlock(&pmic->mutex); - return err; -} - -static int tps65910_reg_read_locked(struct tps65910_reg *pmic, u8 reg) -{ - int data; - - mutex_lock(&pmic->mutex); - - data = tps65910_read(pmic, reg); - if (data < 0) - dev_err(pmic->mfd->dev, "Read from reg 0x%x failed\n", reg); - - mutex_unlock(&pmic->mutex); - return data; -} - -static int tps65910_reg_write_locked(struct tps65910_reg *pmic, u8 reg, u8 val) -{ - int err; - - mutex_lock(&pmic->mutex); - - err = tps65910_reg_write(pmic->mfd, reg, val); - if (err < 0) - dev_err(pmic->mfd->dev, "Write for reg 0x%x failed\n", reg); - - mutex_unlock(&pmic->mutex); - return err; -} - static int tps65910_get_ctrl_register(int id) { switch (id) { @@ -462,13 +371,6 @@ static int tps65911_get_ctrl_register(int id) } } -static int tps65910_enable_time(struct regulator_dev *dev) -{ - struct tps65910_reg *pmic = rdev_get_drvdata(dev); - int id = rdev_get_id(dev); - return pmic->info[id]->enable_time_us; -} - static int tps65910_set_mode(struct regulator_dev *dev, unsigned int mode) { struct tps65910_reg *pmic = rdev_get_drvdata(dev); @@ -481,8 +383,9 @@ static int tps65910_set_mode(struct regulator_dev *dev, unsigned int mode) switch (mode) { case REGULATOR_MODE_NORMAL: - return tps65910_modify_bits(pmic, reg, LDO_ST_ON_BIT, - LDO_ST_MODE_BIT); + return tps65910_reg_update_bits(pmic->mfd, reg, + LDO_ST_MODE_BIT | LDO_ST_ON_BIT, + LDO_ST_ON_BIT); case REGULATOR_MODE_IDLE: value = LDO_ST_ON_BIT | LDO_ST_MODE_BIT; return tps65910_reg_set_bits(mfd, reg, value); @@ -496,15 +399,15 @@ static int tps65910_set_mode(struct regulator_dev *dev, unsigned int mode) static unsigned int tps65910_get_mode(struct regulator_dev *dev) { struct tps65910_reg *pmic = rdev_get_drvdata(dev); - int reg, value, id = rdev_get_id(dev); + int ret, reg, value, id = rdev_get_id(dev); reg = pmic->get_ctrl_reg(id); if (reg < 0) return reg; - value = tps65910_reg_read_locked(pmic, reg); - if (value < 0) - return value; + ret = tps65910_reg_read(pmic->mfd, reg, &value); + if (ret < 0) + return ret; if (!(value & LDO_ST_ON_BIT)) return REGULATOR_MODE_STANDBY; @@ -517,33 +420,51 @@ static unsigned int tps65910_get_mode(struct regulator_dev *dev) static int tps65910_get_voltage_dcdc_sel(struct regulator_dev *dev) { struct tps65910_reg *pmic = rdev_get_drvdata(dev); - int id = rdev_get_id(dev); + int ret, id = rdev_get_id(dev); int opvsel = 0, srvsel = 0, vselmax = 0, mult = 0, sr = 0; switch (id) { case TPS65910_REG_VDD1: - opvsel = tps65910_reg_read_locked(pmic, TPS65910_VDD1_OP); - mult = tps65910_reg_read_locked(pmic, TPS65910_VDD1); + ret = tps65910_reg_read(pmic->mfd, TPS65910_VDD1_OP, &opvsel); + if (ret < 0) + return ret; + ret = tps65910_reg_read(pmic->mfd, TPS65910_VDD1, &mult); + if (ret < 0) + return ret; mult = (mult & VDD1_VGAIN_SEL_MASK) >> VDD1_VGAIN_SEL_SHIFT; - srvsel = tps65910_reg_read_locked(pmic, TPS65910_VDD1_SR); + ret = tps65910_reg_read(pmic->mfd, TPS65910_VDD1_SR, &srvsel); + if (ret < 0) + return ret; sr = opvsel & VDD1_OP_CMD_MASK; opvsel &= VDD1_OP_SEL_MASK; srvsel &= VDD1_SR_SEL_MASK; vselmax = 75; break; case TPS65910_REG_VDD2: - opvsel = tps65910_reg_read_locked(pmic, TPS65910_VDD2_OP); - mult = tps65910_reg_read_locked(pmic, TPS65910_VDD2); + ret = tps65910_reg_read(pmic->mfd, TPS65910_VDD2_OP, &opvsel); + if (ret < 0) + return ret; + ret = tps65910_reg_read(pmic->mfd, TPS65910_VDD2, &mult); + if (ret < 0) + return ret; mult = (mult & VDD2_VGAIN_SEL_MASK) >> VDD2_VGAIN_SEL_SHIFT; - srvsel = tps65910_reg_read_locked(pmic, TPS65910_VDD2_SR); + ret = tps65910_reg_read(pmic->mfd, TPS65910_VDD2_SR, &srvsel); + if (ret < 0) + return ret; sr = opvsel & VDD2_OP_CMD_MASK; opvsel &= VDD2_OP_SEL_MASK; srvsel &= VDD2_SR_SEL_MASK; vselmax = 75; break; case TPS65911_REG_VDDCTRL: - opvsel = tps65910_reg_read_locked(pmic, TPS65911_VDDCTRL_OP); - srvsel = tps65910_reg_read_locked(pmic, TPS65911_VDDCTRL_SR); + ret = tps65910_reg_read(pmic->mfd, TPS65911_VDDCTRL_OP, + &opvsel); + if (ret < 0) + return ret; + ret = tps65910_reg_read(pmic->mfd, TPS65911_VDDCTRL_SR, + &srvsel); + if (ret < 0) + return ret; sr = opvsel & VDDCTRL_OP_CMD_MASK; opvsel &= VDDCTRL_OP_SEL_MASK; srvsel &= VDDCTRL_SR_SEL_MASK; @@ -577,15 +498,15 @@ static int tps65910_get_voltage_dcdc_sel(struct regulator_dev *dev) static int tps65910_get_voltage_sel(struct regulator_dev *dev) { struct tps65910_reg *pmic = rdev_get_drvdata(dev); - int reg, value, id = rdev_get_id(dev); + int ret, reg, value, id = rdev_get_id(dev); reg = pmic->get_ctrl_reg(id); if (reg < 0) return reg; - value = tps65910_reg_read_locked(pmic, reg); - if (value < 0) - return value; + ret = tps65910_reg_read(pmic->mfd, reg, &value); + if (ret < 0) + return ret; switch (id) { case TPS65910_REG_VIO: @@ -609,18 +530,20 @@ static int tps65910_get_voltage_sel(struct regulator_dev *dev) static int tps65910_get_voltage_vdd3(struct regulator_dev *dev) { - return 5 * 1000 * 1000; + return dev->desc->volt_table[0]; } static int tps65911_get_voltage_sel(struct regulator_dev *dev) { struct tps65910_reg *pmic = rdev_get_drvdata(dev); - int id = rdev_get_id(dev); - u8 value, reg; + int ret, id = rdev_get_id(dev); + unsigned int value, reg; reg = pmic->get_ctrl_reg(id); - value = tps65910_reg_read_locked(pmic, reg); + ret = tps65910_reg_read(pmic->mfd, reg, &value); + if (ret < 0) + return ret; switch (id) { case TPS65911_REG_LDO1: @@ -662,10 +585,10 @@ static int tps65910_set_voltage_dcdc_sel(struct regulator_dev *dev, dcdc_mult--; vsel = (selector % VDD1_2_NUM_VOLT_FINE) + 3; - tps65910_modify_bits(pmic, TPS65910_VDD1, - (dcdc_mult << VDD1_VGAIN_SEL_SHIFT), - VDD1_VGAIN_SEL_MASK); - tps65910_reg_write_locked(pmic, TPS65910_VDD1_OP, vsel); + tps65910_reg_update_bits(pmic->mfd, TPS65910_VDD1, + VDD1_VGAIN_SEL_MASK, + dcdc_mult << VDD1_VGAIN_SEL_SHIFT); + tps65910_reg_write(pmic->mfd, TPS65910_VDD1_OP, vsel); break; case TPS65910_REG_VDD2: dcdc_mult = (selector / VDD1_2_NUM_VOLT_FINE) + 1; @@ -673,14 +596,14 @@ static int tps65910_set_voltage_dcdc_sel(struct regulator_dev *dev, dcdc_mult--; vsel = (selector % VDD1_2_NUM_VOLT_FINE) + 3; - tps65910_modify_bits(pmic, TPS65910_VDD2, - (dcdc_mult << VDD2_VGAIN_SEL_SHIFT), - VDD1_VGAIN_SEL_MASK); - tps65910_reg_write_locked(pmic, TPS65910_VDD2_OP, vsel); + tps65910_reg_update_bits(pmic->mfd, TPS65910_VDD2, + VDD1_VGAIN_SEL_MASK, + dcdc_mult << VDD2_VGAIN_SEL_SHIFT); + tps65910_reg_write(pmic->mfd, TPS65910_VDD2_OP, vsel); break; case TPS65911_REG_VDDCTRL: vsel = selector + 3; - tps65910_reg_write_locked(pmic, TPS65911_VDDCTRL_OP, vsel); + tps65910_reg_write(pmic->mfd, TPS65911_VDDCTRL_OP, vsel); } return 0; @@ -706,8 +629,8 @@ static int tps65910_set_voltage_sel(struct regulator_dev *dev, case TPS65910_REG_VAUX2: case TPS65910_REG_VAUX33: case TPS65910_REG_VMMC: - return tps65910_modify_bits(pmic, reg, - (selector << LDO_SEL_SHIFT), LDO_SEL_MASK); + return tps65910_reg_update_bits(pmic->mfd, reg, LDO_SEL_MASK, + selector << LDO_SEL_SHIFT); } return -EINVAL; @@ -727,18 +650,18 @@ static int tps65911_set_voltage_sel(struct regulator_dev *dev, case TPS65911_REG_LDO1: case TPS65911_REG_LDO2: case TPS65911_REG_LDO4: - return tps65910_modify_bits(pmic, reg, - (selector << LDO_SEL_SHIFT), LDO1_SEL_MASK); + return tps65910_reg_update_bits(pmic->mfd, reg, LDO1_SEL_MASK, + selector << LDO_SEL_SHIFT); case TPS65911_REG_LDO3: case TPS65911_REG_LDO5: case TPS65911_REG_LDO6: case TPS65911_REG_LDO7: case TPS65911_REG_LDO8: - return tps65910_modify_bits(pmic, reg, - (selector << LDO_SEL_SHIFT), LDO3_SEL_MASK); + return tps65910_reg_update_bits(pmic->mfd, reg, LDO3_SEL_MASK, + selector << LDO_SEL_SHIFT); case TPS65910_REG_VIO: - return tps65910_modify_bits(pmic, reg, - (selector << LDO_SEL_SHIFT), LDO_SEL_MASK); + return tps65910_reg_update_bits(pmic->mfd, reg, LDO_SEL_MASK, + selector << LDO_SEL_SHIFT); } return -EINVAL; @@ -768,23 +691,6 @@ static int tps65910_list_voltage_dcdc(struct regulator_dev *dev, return volt * 100 * mult; } -static int tps65910_list_voltage(struct regulator_dev *dev, - unsigned selector) -{ - struct tps65910_reg *pmic = rdev_get_drvdata(dev); - int id = rdev_get_id(dev), voltage; - - if (id < TPS65910_REG_VIO || id > TPS65910_REG_VMMC) - return -EINVAL; - - if (selector >= pmic->info[id]->n_voltages) - return -EINVAL; - else - voltage = pmic->info[id]->voltage_table[selector] * 1000; - - return voltage; -} - static int tps65911_list_voltage(struct regulator_dev *dev, unsigned selector) { struct tps65910_reg *pmic = rdev_get_drvdata(dev); @@ -816,7 +722,7 @@ static int tps65911_list_voltage(struct regulator_dev *dev, unsigned selector) step_mv = 100; break; case TPS65910_REG_VIO: - return pmic->info[id]->voltage_table[selector] * 1000; + return pmic->info[id]->voltage_table[selector]; default: return -EINVAL; } @@ -824,42 +730,16 @@ static int tps65911_list_voltage(struct regulator_dev *dev, unsigned selector) return (LDO_MIN_VOLT + selector * step_mv) * 1000; } -static int tps65910_set_voltage_dcdc_time_sel(struct regulator_dev *dev, - unsigned int old_selector, unsigned int new_selector) -{ - int id = rdev_get_id(dev); - int old_volt, new_volt; - - old_volt = tps65910_list_voltage_dcdc(dev, old_selector); - if (old_volt < 0) - return old_volt; - - new_volt = tps65910_list_voltage_dcdc(dev, new_selector); - if (new_volt < 0) - return new_volt; - - /* VDD1 and VDD2 are 12.5mV/us, VDDCTRL is 100mV/20us */ - switch (id) { - case TPS65910_REG_VDD1: - case TPS65910_REG_VDD2: - return DIV_ROUND_UP(abs(old_volt - new_volt), 12500); - case TPS65911_REG_VDDCTRL: - return DIV_ROUND_UP(abs(old_volt - new_volt), 5000); - } - return -EINVAL; -} - /* Regulator ops (except VRTC) */ static struct regulator_ops tps65910_ops_dcdc = { .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, - .enable_time = tps65910_enable_time, .set_mode = tps65910_set_mode, .get_mode = tps65910_get_mode, .get_voltage_sel = tps65910_get_voltage_dcdc_sel, .set_voltage_sel = tps65910_set_voltage_dcdc_sel, - .set_voltage_time_sel = tps65910_set_voltage_dcdc_time_sel, + .set_voltage_time_sel = regulator_set_voltage_time_sel, .list_voltage = tps65910_list_voltage_dcdc, }; @@ -867,30 +747,27 @@ static struct regulator_ops tps65910_ops_vdd3 = { .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, - .enable_time = tps65910_enable_time, .set_mode = tps65910_set_mode, .get_mode = tps65910_get_mode, .get_voltage = tps65910_get_voltage_vdd3, - .list_voltage = tps65910_list_voltage, + .list_voltage = regulator_list_voltage_table, }; static struct regulator_ops tps65910_ops = { .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, - .enable_time = tps65910_enable_time, .set_mode = tps65910_set_mode, .get_mode = tps65910_get_mode, .get_voltage_sel = tps65910_get_voltage_sel, .set_voltage_sel = tps65910_set_voltage_sel, - .list_voltage = tps65910_list_voltage, + .list_voltage = regulator_list_voltage_table, }; static struct regulator_ops tps65911_ops = { .is_enabled = regulator_is_enabled_regmap, .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, - .enable_time = tps65910_enable_time, .set_mode = tps65910_set_mode, .get_mode = tps65910_get_mode, .get_voltage_sel = tps65911_get_voltage_sel, @@ -996,19 +873,27 @@ static int tps65910_set_ext_sleep_config(struct tps65910_reg *pmic, (tps65910_chip_id(mfd) == TPS65911))) { int op_reg_add = pmic->get_ctrl_reg(id) + 1; int sr_reg_add = pmic->get_ctrl_reg(id) + 2; - int opvsel = tps65910_reg_read_locked(pmic, op_reg_add); - int srvsel = tps65910_reg_read_locked(pmic, sr_reg_add); + int opvsel, srvsel; + + ret = tps65910_reg_read(pmic->mfd, op_reg_add, &opvsel); + if (ret < 0) + return ret; + ret = tps65910_reg_read(pmic->mfd, sr_reg_add, &srvsel); + if (ret < 0) + return ret; + if (opvsel & VDD1_OP_CMD_MASK) { u8 reg_val = srvsel & VDD1_OP_SEL_MASK; - ret = tps65910_reg_write_locked(pmic, op_reg_add, - reg_val); + + ret = tps65910_reg_write(pmic->mfd, op_reg_add, + reg_val); if (ret < 0) { dev_err(mfd->dev, "Error in configuring op register\n"); return ret; } } - ret = tps65910_reg_write_locked(pmic, sr_reg_add, 0); + ret = tps65910_reg_write(pmic->mfd, sr_reg_add, 0); if (ret < 0) { dev_err(mfd->dev, "Error in settting sr register\n"); return ret; @@ -1126,6 +1011,7 @@ static struct tps65910_board *tps65910_parse_dt_reg_data( "ti,regulator-ext-sleep-control", &prop); if (!ret) pmic_plat_data->regulator_ext_sleep_control[idx] = prop; + } return pmic_plat_data; @@ -1136,7 +1022,7 @@ static inline struct tps65910_board *tps65910_parse_dt_reg_data( struct of_regulator_match **tps65910_reg_matches) { *tps65910_reg_matches = NULL; - return 0; + return NULL; } #endif @@ -1168,7 +1054,6 @@ static __devinit int tps65910_probe(struct platform_device *pdev) return -ENOMEM; } - mutex_init(&pmic->mutex); pmic->mfd = tps65910; platform_set_drvdata(pdev, pmic); @@ -1229,23 +1114,31 @@ static __devinit int tps65910_probe(struct platform_device *pdev) pmic->info[i] = info; pmic->desc[i].name = info->name; + pmic->desc[i].supply_name = info->vin_name; pmic->desc[i].id = i; pmic->desc[i].n_voltages = info->n_voltages; + pmic->desc[i].enable_time = info->enable_time_us; if (i == TPS65910_REG_VDD1 || i == TPS65910_REG_VDD2) { pmic->desc[i].ops = &tps65910_ops_dcdc; pmic->desc[i].n_voltages = VDD1_2_NUM_VOLT_FINE * VDD1_2_NUM_VOLT_COARSE; + pmic->desc[i].ramp_delay = 12500; } else if (i == TPS65910_REG_VDD3) { - if (tps65910_chip_id(tps65910) == TPS65910) + if (tps65910_chip_id(tps65910) == TPS65910) { pmic->desc[i].ops = &tps65910_ops_vdd3; - else + pmic->desc[i].volt_table = info->voltage_table; + } else { pmic->desc[i].ops = &tps65910_ops_dcdc; + pmic->desc[i].ramp_delay = 5000; + } } else { - if (tps65910_chip_id(tps65910) == TPS65910) + if (tps65910_chip_id(tps65910) == TPS65910) { pmic->desc[i].ops = &tps65910_ops; - else + pmic->desc[i].volt_table = info->voltage_table; + } else { pmic->desc[i].ops = &tps65911_ops; + } } err = tps65910_set_ext_sleep_config(pmic, i, diff --git a/drivers/regulator/twl-regulator.c b/drivers/regulator/twl-regulator.c index c7390711d954..242fe90dc565 100644 --- a/drivers/regulator/twl-regulator.c +++ b/drivers/regulator/twl-regulator.c @@ -43,9 +43,6 @@ struct twlreg_info { u8 table_len; const u16 *table; - /* regulator specific turn-on delay */ - u16 delay; - /* State REMAP default configuration */ u8 remap; @@ -223,20 +220,6 @@ static int twl6030reg_enable(struct regulator_dev *rdev) return ret; } -static int twl4030reg_enable_time(struct regulator_dev *rdev) -{ - struct twlreg_info *info = rdev_get_drvdata(rdev); - - return info->delay; -} - -static int twl6030reg_enable_time(struct regulator_dev *rdev) -{ - struct twlreg_info *info = rdev_get_drvdata(rdev); - - return info->delay; -} - static int twl4030reg_disable(struct regulator_dev *rdev) { struct twlreg_info *info = rdev_get_drvdata(rdev); @@ -508,7 +491,6 @@ static struct regulator_ops twl4030ldo_ops = { .enable = twl4030reg_enable, .disable = twl4030reg_disable, .is_enabled = twl4030reg_is_enabled, - .enable_time = twl4030reg_enable_time, .set_mode = twl4030reg_set_mode, @@ -577,59 +559,53 @@ static struct regulator_ops twl6030coresmps_ops = { .get_voltage = twl6030coresmps_get_voltage, }; -static int twl6030ldo_list_voltage(struct regulator_dev *rdev, unsigned index) +static int twl6030ldo_list_voltage(struct regulator_dev *rdev, unsigned sel) { - struct twlreg_info *info = rdev_get_drvdata(rdev); + struct twlreg_info *info = rdev_get_drvdata(rdev); - return ((info->min_mV + (index * 100)) * 1000); + switch (sel) { + case 0: + return 0; + case 1 ... 24: + /* Linear mapping from 00000001 to 00011000: + * Absolute voltage value = 1.0 V + 0.1 V × (sel – 00000001) + */ + return (info->min_mV + 100 * (sel - 1)) * 1000; + case 25 ... 30: + return -EINVAL; + case 31: + return 2750000; + default: + return -EINVAL; + } } static int -twl6030ldo_set_voltage(struct regulator_dev *rdev, int min_uV, int max_uV, - unsigned *selector) +twl6030ldo_set_voltage_sel(struct regulator_dev *rdev, unsigned selector) { struct twlreg_info *info = rdev_get_drvdata(rdev); - int vsel; - - if ((min_uV/1000 < info->min_mV) || (max_uV/1000 > info->max_mV)) - return -EDOM; - - /* - * Use the below formula to calculate vsel - * mV = 1000mv + 100mv * (vsel - 1) - */ - vsel = (min_uV/1000 - 1000)/100 + 1; - *selector = vsel; - return twlreg_write(info, TWL_MODULE_PM_RECEIVER, VREG_VOLTAGE, vsel); + return twlreg_write(info, TWL_MODULE_PM_RECEIVER, VREG_VOLTAGE, + selector); } -static int twl6030ldo_get_voltage(struct regulator_dev *rdev) +static int twl6030ldo_get_voltage_sel(struct regulator_dev *rdev) { struct twlreg_info *info = rdev_get_drvdata(rdev); - int vsel = twlreg_read(info, TWL_MODULE_PM_RECEIVER, - VREG_VOLTAGE); - - if (vsel < 0) - return vsel; + int vsel = twlreg_read(info, TWL_MODULE_PM_RECEIVER, VREG_VOLTAGE); - /* - * Use the below formula to calculate vsel - * mV = 1000mv + 100mv * (vsel - 1) - */ - return (1000 + (100 * (vsel - 1))) * 1000; + return vsel; } static struct regulator_ops twl6030ldo_ops = { .list_voltage = twl6030ldo_list_voltage, - .set_voltage = twl6030ldo_set_voltage, - .get_voltage = twl6030ldo_get_voltage, + .set_voltage_sel = twl6030ldo_set_voltage_sel, + .get_voltage_sel = twl6030ldo_get_voltage_sel, .enable = twl6030reg_enable, .disable = twl6030reg_disable, .is_enabled = twl6030reg_is_enabled, - .enable_time = twl6030reg_enable_time, .set_mode = twl6030reg_set_mode, @@ -663,7 +639,6 @@ static struct regulator_ops twl4030fixed_ops = { .enable = twl4030reg_enable, .disable = twl4030reg_disable, .is_enabled = twl4030reg_is_enabled, - .enable_time = twl4030reg_enable_time, .set_mode = twl4030reg_set_mode, @@ -678,7 +653,6 @@ static struct regulator_ops twl6030fixed_ops = { .enable = twl6030reg_enable, .disable = twl6030reg_disable, .is_enabled = twl6030reg_is_enabled, - .enable_time = twl6030reg_enable_time, .set_mode = twl6030reg_set_mode, @@ -689,7 +663,6 @@ static struct regulator_ops twl6030_fixed_resource = { .enable = twl6030reg_enable, .disable = twl6030reg_disable, .is_enabled = twl6030reg_is_enabled, - .enable_time = twl6030reg_enable_time, .get_status = twl6030reg_get_status, }; @@ -886,7 +859,6 @@ static struct regulator_ops twlsmps_ops = { .enable = twl6030reg_enable, .disable = twl6030reg_disable, .is_enabled = twl6030reg_is_enabled, - .enable_time = twl6030reg_enable_time, .set_mode = twl6030reg_set_mode, @@ -909,7 +881,6 @@ static struct twlreg_info TWL4030_INFO_##label = { \ .id = num, \ .table_len = ARRAY_SIZE(label##_VSEL_table), \ .table = label##_VSEL_table, \ - .delay = turnon_delay, \ .remap = remap_conf, \ .desc = { \ .name = #label, \ @@ -918,6 +889,7 @@ static struct twlreg_info TWL4030_INFO_##label = { \ .ops = &twl4030ldo_ops, \ .type = REGULATOR_VOLTAGE, \ .owner = THIS_MODULE, \ + .enable_time = turnon_delay, \ }, \ } @@ -925,7 +897,6 @@ static struct twlreg_info TWL4030_INFO_##label = { \ static struct twlreg_info TWL4030_INFO_##label = { \ .base = offset, \ .id = num, \ - .delay = turnon_delay, \ .remap = remap_conf, \ .desc = { \ .name = #label, \ @@ -933,6 +904,7 @@ static struct twlreg_info TWL4030_INFO_##label = { \ .ops = &twl4030smps_ops, \ .type = REGULATOR_VOLTAGE, \ .owner = THIS_MODULE, \ + .enable_time = turnon_delay, \ }, \ } @@ -955,7 +927,7 @@ static struct twlreg_info TWL6030_INFO_##label = { \ .desc = { \ .name = #label, \ .id = TWL6030_REG_##label, \ - .n_voltages = (max_mVolts - min_mVolts)/100 + 1, \ + .n_voltages = 32, \ .ops = &twl6030ldo_ops, \ .type = REGULATOR_VOLTAGE, \ .owner = THIS_MODULE, \ @@ -970,7 +942,7 @@ static struct twlreg_info TWL6025_INFO_##label = { \ .desc = { \ .name = #label, \ .id = TWL6025_REG_##label, \ - .n_voltages = ((max_mVolts - min_mVolts)/100) + 1, \ + .n_voltages = 32, \ .ops = &twl6030ldo_ops, \ .type = REGULATOR_VOLTAGE, \ .owner = THIS_MODULE, \ @@ -983,7 +955,6 @@ static struct twlreg_info TWLFIXED_INFO_##label = { \ .base = offset, \ .id = num, \ .min_mV = mVolts, \ - .delay = turnon_delay, \ .remap = remap_conf, \ .desc = { \ .name = #label, \ @@ -992,19 +963,20 @@ static struct twlreg_info TWLFIXED_INFO_##label = { \ .ops = &operations, \ .type = REGULATOR_VOLTAGE, \ .owner = THIS_MODULE, \ + .enable_time = turnon_delay, \ }, \ } #define TWL6030_FIXED_RESOURCE(label, offset, turnon_delay) \ static struct twlreg_info TWLRES_INFO_##label = { \ .base = offset, \ - .delay = turnon_delay, \ .desc = { \ .name = #label, \ .id = TWL6030_REG_##label, \ .ops = &twl6030_fixed_resource, \ .type = REGULATOR_VOLTAGE, \ .owner = THIS_MODULE, \ + .enable_time = turnon_delay, \ }, \ } @@ -1109,7 +1081,6 @@ static u8 twl_get_smps_mult(void) #define TWL6030_OF_MATCH(comp, label) TWL_OF_MATCH(comp, TWL6030, label) #define TWL6025_OF_MATCH(comp, label) TWL_OF_MATCH(comp, TWL6025, label) #define TWLFIXED_OF_MATCH(comp, label) TWL_OF_MATCH(comp, TWLFIXED, label) -#define TWLRES_OF_MATCH(comp, label) TWL_OF_MATCH(comp, TWLRES, label) #define TWLSMPS_OF_MATCH(comp, label) TWL_OF_MATCH(comp, TWLSMPS, label) static const struct of_device_id twl_of_match[] __devinitconst = { @@ -1157,7 +1128,6 @@ static const struct of_device_id twl_of_match[] __devinitconst = { TWLFIXED_OF_MATCH("ti,twl6030-vusb", VUSB), TWLFIXED_OF_MATCH("ti,twl6030-v1v8", V1V8), TWLFIXED_OF_MATCH("ti,twl6030-v2v1", V2V1), - TWLRES_OF_MATCH("ti,twl6030-clk32kg", CLK32KG), TWLSMPS_OF_MATCH("ti,twl6025-smps3", SMPS3), TWLSMPS_OF_MATCH("ti,twl6025-smps4", SMPS4), TWLSMPS_OF_MATCH("ti,twl6025-vio", VIO), diff --git a/drivers/regulator/wm831x-dcdc.c b/drivers/regulator/wm831x-dcdc.c index 099da11e989f..7413885be01b 100644 --- a/drivers/regulator/wm831x-dcdc.c +++ b/drivers/regulator/wm831x-dcdc.c @@ -215,8 +215,8 @@ static int wm831x_buckv_list_voltage(struct regulator_dev *rdev, return -EINVAL; } -static int wm831x_buckv_select_min_voltage(struct regulator_dev *rdev, - int min_uV, int max_uV) +static int wm831x_buckv_map_voltage(struct regulator_dev *rdev, + int min_uV, int max_uV) { u16 vsel; @@ -251,20 +251,14 @@ static int wm831x_buckv_set_dvs(struct regulator_dev *rdev, int state) return 0; } -static int wm831x_buckv_set_voltage(struct regulator_dev *rdev, - int min_uV, int max_uV, unsigned *selector) +static int wm831x_buckv_set_voltage_sel(struct regulator_dev *rdev, + unsigned vsel) { struct wm831x_dcdc *dcdc = rdev_get_drvdata(rdev); struct wm831x *wm831x = dcdc->wm831x; int on_reg = dcdc->base + WM831X_DCDC_ON_CONFIG; int dvs_reg = dcdc->base + WM831X_DCDC_DVS_CONTROL; - int vsel, ret; - - vsel = wm831x_buckv_select_min_voltage(rdev, min_uV, max_uV); - if (vsel < 0) - return vsel; - - *selector = vsel; + int ret; /* If this value is already set then do a GPIO update if we can */ if (dcdc->dvs_gpio && dcdc->on_vsel == vsel) @@ -315,7 +309,7 @@ static int wm831x_buckv_set_suspend_voltage(struct regulator_dev *rdev, u16 reg = dcdc->base + WM831X_DCDC_SLEEP_CONTROL; int vsel; - vsel = wm831x_buckv_select_min_voltage(rdev, uV, uV); + vsel = wm831x_buckv_map_voltage(rdev, uV, uV); if (vsel < 0) return vsel; @@ -373,9 +367,10 @@ static int wm831x_buckv_get_current_limit(struct regulator_dev *rdev) } static struct regulator_ops wm831x_buckv_ops = { - .set_voltage = wm831x_buckv_set_voltage, + .set_voltage_sel = wm831x_buckv_set_voltage_sel, .get_voltage_sel = wm831x_buckv_get_voltage_sel, .list_voltage = wm831x_buckv_list_voltage, + .map_voltage = wm831x_buckv_map_voltage, .set_suspend_voltage = wm831x_buckv_set_suspend_voltage, .set_current_limit = wm831x_buckv_set_current_limit, .get_current_limit = wm831x_buckv_get_current_limit, @@ -599,60 +594,25 @@ static struct platform_driver wm831x_buckv_driver = { * BUCKP specifics */ -static int wm831x_buckp_list_voltage(struct regulator_dev *rdev, - unsigned selector) -{ - if (selector <= WM831X_BUCKP_MAX_SELECTOR) - return 850000 + (selector * 25000); - else - return -EINVAL; -} - -static int wm831x_buckp_set_voltage_int(struct regulator_dev *rdev, int reg, - int min_uV, int max_uV, int *selector) +static int wm831x_buckp_set_suspend_voltage(struct regulator_dev *rdev, int uV) { struct wm831x_dcdc *dcdc = rdev_get_drvdata(rdev); struct wm831x *wm831x = dcdc->wm831x; - u16 vsel; - - if (min_uV <= 34000000) - vsel = (min_uV - 850000) / 25000; - else - return -EINVAL; - - if (wm831x_buckp_list_voltage(rdev, vsel) > max_uV) - return -EINVAL; - - *selector = vsel; - - return wm831x_set_bits(wm831x, reg, WM831X_DC3_ON_VSEL_MASK, vsel); -} - -static int wm831x_buckp_set_voltage(struct regulator_dev *rdev, - int min_uV, int max_uV, - unsigned *selector) -{ - struct wm831x_dcdc *dcdc = rdev_get_drvdata(rdev); - u16 reg = dcdc->base + WM831X_DCDC_ON_CONFIG; - - return wm831x_buckp_set_voltage_int(rdev, reg, min_uV, max_uV, - selector); -} - -static int wm831x_buckp_set_suspend_voltage(struct regulator_dev *rdev, - int uV) -{ - struct wm831x_dcdc *dcdc = rdev_get_drvdata(rdev); u16 reg = dcdc->base + WM831X_DCDC_SLEEP_CONTROL; - unsigned selector; + int sel; + + sel = regulator_map_voltage_linear(rdev, uV, uV); + if (sel < 0) + return sel; - return wm831x_buckp_set_voltage_int(rdev, reg, uV, uV, &selector); + return wm831x_set_bits(wm831x, reg, WM831X_DC3_ON_VSEL_MASK, sel); } static struct regulator_ops wm831x_buckp_ops = { - .set_voltage = wm831x_buckp_set_voltage, + .set_voltage_sel = regulator_set_voltage_sel_regmap, .get_voltage_sel = regulator_get_voltage_sel_regmap, - .list_voltage = wm831x_buckp_list_voltage, + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, .set_suspend_voltage = wm831x_buckp_set_suspend_voltage, .is_enabled = regulator_is_enabled_regmap, @@ -715,6 +675,8 @@ static __devinit int wm831x_buckp_probe(struct platform_device *pdev) dcdc->desc.vsel_mask = WM831X_DC3_ON_VSEL_MASK; dcdc->desc.enable_reg = WM831X_DCDC_ENABLE; dcdc->desc.enable_mask = 1 << id; + dcdc->desc.min_uV = 850000; + dcdc->desc.uV_step = 25000; config.dev = pdev->dev.parent; if (pdata) diff --git a/drivers/regulator/wm831x-ldo.c b/drivers/regulator/wm831x-ldo.c index a9a28d8ac185..5cb70ca1e98d 100644 --- a/drivers/regulator/wm831x-ldo.c +++ b/drivers/regulator/wm831x-ldo.c @@ -78,13 +78,10 @@ static int wm831x_gp_ldo_list_voltage(struct regulator_dev *rdev, return -EINVAL; } -static int wm831x_gp_ldo_set_voltage_int(struct regulator_dev *rdev, int reg, - int min_uV, int max_uV, - unsigned *selector) +static int wm831x_gp_ldo_map_voltage(struct regulator_dev *rdev, + int min_uV, int max_uV) { - struct wm831x_ldo *ldo = rdev_get_drvdata(rdev); - struct wm831x *wm831x = ldo->wm831x; - int vsel, ret; + int volt, vsel; if (min_uV < 900000) vsel = 0; @@ -94,36 +91,25 @@ static int wm831x_gp_ldo_set_voltage_int(struct regulator_dev *rdev, int reg, vsel = ((min_uV - 1700000) / 100000) + WM831X_GP_LDO_SELECTOR_LOW + 1; - ret = wm831x_gp_ldo_list_voltage(rdev, vsel); - if (ret < 0) - return ret; - if (ret < min_uV || ret > max_uV) + volt = wm831x_gp_ldo_list_voltage(rdev, vsel); + if (volt < min_uV || volt > max_uV) return -EINVAL; - *selector = vsel; - - return wm831x_set_bits(wm831x, reg, WM831X_LDO1_ON_VSEL_MASK, vsel); -} - -static int wm831x_gp_ldo_set_voltage(struct regulator_dev *rdev, - int min_uV, int max_uV, - unsigned *selector) -{ - struct wm831x_ldo *ldo = rdev_get_drvdata(rdev); - int reg = ldo->base + WM831X_LDO_ON_CONTROL; - - return wm831x_gp_ldo_set_voltage_int(rdev, reg, min_uV, max_uV, - selector); + return vsel; } static int wm831x_gp_ldo_set_suspend_voltage(struct regulator_dev *rdev, int uV) { struct wm831x_ldo *ldo = rdev_get_drvdata(rdev); - int reg = ldo->base + WM831X_LDO_SLEEP_CONTROL; - unsigned int selector; + struct wm831x *wm831x = ldo->wm831x; + int sel, reg = ldo->base + WM831X_LDO_SLEEP_CONTROL; - return wm831x_gp_ldo_set_voltage_int(rdev, reg, uV, uV, &selector); + sel = wm831x_gp_ldo_map_voltage(rdev, uV, uV); + if (sel < 0) + return sel; + + return wm831x_set_bits(wm831x, reg, WM831X_LDO1_ON_VSEL_MASK, sel); } static unsigned int wm831x_gp_ldo_get_mode(struct regulator_dev *rdev) @@ -243,8 +229,9 @@ static unsigned int wm831x_gp_ldo_get_optimum_mode(struct regulator_dev *rdev, static struct regulator_ops wm831x_gp_ldo_ops = { .list_voltage = wm831x_gp_ldo_list_voltage, + .map_voltage = wm831x_gp_ldo_map_voltage, .get_voltage_sel = regulator_get_voltage_sel_regmap, - .set_voltage = wm831x_gp_ldo_set_voltage, + .set_voltage_sel = regulator_set_voltage_sel_regmap, .set_suspend_voltage = wm831x_gp_ldo_set_suspend_voltage, .get_mode = wm831x_gp_ldo_get_mode, .set_mode = wm831x_gp_ldo_set_mode, @@ -384,13 +371,10 @@ static int wm831x_aldo_list_voltage(struct regulator_dev *rdev, return -EINVAL; } -static int wm831x_aldo_set_voltage_int(struct regulator_dev *rdev, int reg, - int min_uV, int max_uV, - unsigned *selector) +static int wm831x_aldo_map_voltage(struct regulator_dev *rdev, + int min_uV, int max_uV) { - struct wm831x_ldo *ldo = rdev_get_drvdata(rdev); - struct wm831x *wm831x = ldo->wm831x; - int vsel, ret; + int volt, vsel; if (min_uV < 1000000) vsel = 0; @@ -400,35 +384,26 @@ static int wm831x_aldo_set_voltage_int(struct regulator_dev *rdev, int reg, vsel = ((min_uV - 1700000) / 100000) + WM831X_ALDO_SELECTOR_LOW + 1; - ret = wm831x_aldo_list_voltage(rdev, vsel); - if (ret < 0) - return ret; - if (ret < min_uV || ret > max_uV) + volt = wm831x_aldo_list_voltage(rdev, vsel); + if (volt < min_uV || volt > max_uV) return -EINVAL; - *selector = vsel; - - return wm831x_set_bits(wm831x, reg, WM831X_LDO7_ON_VSEL_MASK, vsel); -} - -static int wm831x_aldo_set_voltage(struct regulator_dev *rdev, - int min_uV, int max_uV, unsigned *selector) -{ - struct wm831x_ldo *ldo = rdev_get_drvdata(rdev); - int reg = ldo->base + WM831X_LDO_ON_CONTROL; + return vsel; - return wm831x_aldo_set_voltage_int(rdev, reg, min_uV, max_uV, - selector); } static int wm831x_aldo_set_suspend_voltage(struct regulator_dev *rdev, int uV) { struct wm831x_ldo *ldo = rdev_get_drvdata(rdev); - int reg = ldo->base + WM831X_LDO_SLEEP_CONTROL; - unsigned int selector; + struct wm831x *wm831x = ldo->wm831x; + int sel, reg = ldo->base + WM831X_LDO_SLEEP_CONTROL; + + sel = wm831x_aldo_map_voltage(rdev, uV, uV); + if (sel < 0) + return sel; - return wm831x_aldo_set_voltage_int(rdev, reg, uV, uV, &selector); + return wm831x_set_bits(wm831x, reg, WM831X_LDO7_ON_VSEL_MASK, sel); } static unsigned int wm831x_aldo_get_mode(struct regulator_dev *rdev) @@ -506,8 +481,9 @@ static int wm831x_aldo_get_status(struct regulator_dev *rdev) static struct regulator_ops wm831x_aldo_ops = { .list_voltage = wm831x_aldo_list_voltage, + .map_voltage = wm831x_aldo_map_voltage, .get_voltage_sel = regulator_get_voltage_sel_regmap, - .set_voltage = wm831x_aldo_set_voltage, + .set_voltage_sel = regulator_set_voltage_sel_regmap, .set_suspend_voltage = wm831x_aldo_set_suspend_voltage, .get_mode = wm831x_aldo_get_mode, .set_mode = wm831x_aldo_set_mode, @@ -628,47 +604,18 @@ static struct platform_driver wm831x_aldo_driver = { #define WM831X_ALIVE_LDO_MAX_SELECTOR 0xf -static int wm831x_alive_ldo_set_voltage_int(struct regulator_dev *rdev, - int reg, - int min_uV, int max_uV, - unsigned *selector) -{ - struct wm831x_ldo *ldo = rdev_get_drvdata(rdev); - struct wm831x *wm831x = ldo->wm831x; - int vsel, ret; - - vsel = (min_uV - 800000) / 50000; - - ret = regulator_list_voltage_linear(rdev, vsel); - if (ret < 0) - return ret; - if (ret < min_uV || ret > max_uV) - return -EINVAL; - - *selector = vsel; - - return wm831x_set_bits(wm831x, reg, WM831X_LDO11_ON_VSEL_MASK, vsel); -} - -static int wm831x_alive_ldo_set_voltage(struct regulator_dev *rdev, - int min_uV, int max_uV, - unsigned *selector) -{ - struct wm831x_ldo *ldo = rdev_get_drvdata(rdev); - int reg = ldo->base + WM831X_ALIVE_LDO_ON_CONTROL; - - return wm831x_alive_ldo_set_voltage_int(rdev, reg, min_uV, max_uV, - selector); -} - static int wm831x_alive_ldo_set_suspend_voltage(struct regulator_dev *rdev, int uV) { struct wm831x_ldo *ldo = rdev_get_drvdata(rdev); - int reg = ldo->base + WM831X_ALIVE_LDO_SLEEP_CONTROL; - unsigned selector; + struct wm831x *wm831x = ldo->wm831x; + int sel, reg = ldo->base + WM831X_ALIVE_LDO_SLEEP_CONTROL; + + sel = regulator_map_voltage_linear(rdev, uV, uV); + if (sel < 0) + return sel; - return wm831x_alive_ldo_set_voltage_int(rdev, reg, uV, uV, &selector); + return wm831x_set_bits(wm831x, reg, WM831X_LDO11_ON_VSEL_MASK, sel); } static int wm831x_alive_ldo_get_status(struct regulator_dev *rdev) @@ -690,8 +637,9 @@ static int wm831x_alive_ldo_get_status(struct regulator_dev *rdev) static struct regulator_ops wm831x_alive_ldo_ops = { .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, .get_voltage_sel = regulator_get_voltage_sel_regmap, - .set_voltage = wm831x_alive_ldo_set_voltage, + .set_voltage_sel = regulator_set_voltage_sel_regmap, .set_suspend_voltage = wm831x_alive_ldo_set_suspend_voltage, .get_status = wm831x_alive_ldo_get_status, @@ -753,6 +701,7 @@ static __devinit int wm831x_alive_ldo_probe(struct platform_device *pdev) ldo->desc.enable_mask = 1 << id; ldo->desc.min_uV = 800000; ldo->desc.uV_step = 50000; + ldo->desc.enable_time = 1000; config.dev = pdev->dev.parent; if (pdata) diff --git a/drivers/regulator/wm8350-regulator.c b/drivers/regulator/wm8350-regulator.c index 94e550dc70b6..7f0fa22ef2aa 100644 --- a/drivers/regulator/wm8350-regulator.c +++ b/drivers/regulator/wm8350-regulator.c @@ -108,33 +108,6 @@ static int get_isink_val(int min_uA, int max_uA, u16 *setting) return -EINVAL; } -static inline int wm8350_ldo_val_to_mvolts(unsigned int val) -{ - if (val < 16) - return (val * 50) + 900; - else - return ((val - 16) * 100) + 1800; - -} - -static inline unsigned int wm8350_ldo_mvolts_to_val(int mV) -{ - if (mV < 1800) - return (mV - 900) / 50; - else - return ((mV - 1800) / 100) + 16; -} - -static inline int wm8350_dcdc_val_to_mvolts(unsigned int val) -{ - return (val * 25) + 850; -} - -static inline unsigned int wm8350_dcdc_mvolts_to_val(int mV) -{ - return (mV - 850) / 25; -} - static int wm8350_isink_set_current(struct regulator_dev *rdev, int min_uA, int max_uA) { @@ -359,104 +332,13 @@ int wm8350_isink_set_flash(struct wm8350 *wm8350, int isink, u16 mode, } EXPORT_SYMBOL_GPL(wm8350_isink_set_flash); -static int wm8350_dcdc_set_voltage(struct regulator_dev *rdev, int min_uV, - int max_uV, unsigned *selector) -{ - struct wm8350 *wm8350 = rdev_get_drvdata(rdev); - int volt_reg, dcdc = rdev_get_id(rdev), mV, - min_mV = min_uV / 1000, max_mV = max_uV / 1000; - u16 val; - - if (min_mV < 850 || min_mV > 4025) - return -EINVAL; - if (max_mV < 850 || max_mV > 4025) - return -EINVAL; - - /* step size is 25mV */ - mV = (min_mV - 826) / 25; - if (wm8350_dcdc_val_to_mvolts(mV) > max_mV) - return -EINVAL; - BUG_ON(wm8350_dcdc_val_to_mvolts(mV) < min_mV); - - switch (dcdc) { - case WM8350_DCDC_1: - volt_reg = WM8350_DCDC1_CONTROL; - break; - case WM8350_DCDC_3: - volt_reg = WM8350_DCDC3_CONTROL; - break; - case WM8350_DCDC_4: - volt_reg = WM8350_DCDC4_CONTROL; - break; - case WM8350_DCDC_6: - volt_reg = WM8350_DCDC6_CONTROL; - break; - case WM8350_DCDC_2: - case WM8350_DCDC_5: - default: - return -EINVAL; - } - - *selector = mV; - - /* all DCDCs have same mV bits */ - val = wm8350_reg_read(wm8350, volt_reg) & ~WM8350_DC1_VSEL_MASK; - wm8350_reg_write(wm8350, volt_reg, val | mV); - return 0; -} - -static int wm8350_dcdc_get_voltage_sel(struct regulator_dev *rdev) -{ - struct wm8350 *wm8350 = rdev_get_drvdata(rdev); - int volt_reg, dcdc = rdev_get_id(rdev); - - switch (dcdc) { - case WM8350_DCDC_1: - volt_reg = WM8350_DCDC1_CONTROL; - break; - case WM8350_DCDC_3: - volt_reg = WM8350_DCDC3_CONTROL; - break; - case WM8350_DCDC_4: - volt_reg = WM8350_DCDC4_CONTROL; - break; - case WM8350_DCDC_6: - volt_reg = WM8350_DCDC6_CONTROL; - break; - case WM8350_DCDC_2: - case WM8350_DCDC_5: - default: - return -EINVAL; - } - - /* all DCDCs have same mV bits */ - return wm8350_reg_read(wm8350, volt_reg) & WM8350_DC1_VSEL_MASK; -} - -static int wm8350_dcdc_list_voltage(struct regulator_dev *rdev, - unsigned selector) -{ - if (selector > WM8350_DCDC_MAX_VSEL) - return -EINVAL; - return wm8350_dcdc_val_to_mvolts(selector) * 1000; -} - static int wm8350_dcdc_set_suspend_voltage(struct regulator_dev *rdev, int uV) { struct wm8350 *wm8350 = rdev_get_drvdata(rdev); - int volt_reg, mV = uV / 1000, dcdc = rdev_get_id(rdev); + int sel, volt_reg, dcdc = rdev_get_id(rdev); u16 val; - dev_dbg(wm8350->dev, "%s %d mV %d\n", __func__, dcdc, mV); - - if (mV && (mV < 850 || mV > 4025)) { - dev_err(wm8350->dev, - "DCDC%d suspend voltage %d mV out of range\n", - dcdc, mV); - return -EINVAL; - } - if (mV == 0) - mV = 850; + dev_dbg(wm8350->dev, "%s %d mV %d\n", __func__, dcdc, uV / 1000); switch (dcdc) { case WM8350_DCDC_1: @@ -477,10 +359,13 @@ static int wm8350_dcdc_set_suspend_voltage(struct regulator_dev *rdev, int uV) return -EINVAL; } + sel = regulator_map_voltage_linear(rdev, uV, uV); + if (sel < 0) + return -EINVAL; + /* all DCDCs have same mV bits */ val = wm8350_reg_read(wm8350, volt_reg) & ~WM8350_DC1_VSEL_MASK; - wm8350_reg_write(wm8350, volt_reg, - val | wm8350_dcdc_mvolts_to_val(mV)); + wm8350_reg_write(wm8350, volt_reg, val | sel); return 0; } @@ -657,19 +542,49 @@ static int wm8350_dcdc_set_suspend_mode(struct regulator_dev *rdev, return 0; } +static int wm8350_ldo_list_voltage(struct regulator_dev *rdev, + unsigned selector) +{ + if (selector > WM8350_LDO1_VSEL_MASK) + return -EINVAL; + + if (selector < 16) + return (selector * 50000) + 900000; + else + return ((selector - 16) * 100000) + 1800000; +} + +static int wm8350_ldo_map_voltage(struct regulator_dev *rdev, int min_uV, + int max_uV) +{ + int volt, sel; + int min_mV = min_uV / 1000; + int max_mV = max_uV / 1000; + + if (min_mV < 900 || min_mV > 3300) + return -EINVAL; + if (max_mV < 900 || max_mV > 3300) + return -EINVAL; + + if (min_mV < 1800) /* step size is 50mV < 1800mV */ + sel = DIV_ROUND_UP(min_uV - 900, 50); + else /* step size is 100mV > 1800mV */ + sel = DIV_ROUND_UP(min_uV - 1800, 100) + 16; + + volt = wm8350_ldo_list_voltage(rdev, sel); + if (volt < min_uV || volt > max_uV) + return -EINVAL; + + return sel; +} + static int wm8350_ldo_set_suspend_voltage(struct regulator_dev *rdev, int uV) { struct wm8350 *wm8350 = rdev_get_drvdata(rdev); - int volt_reg, mV = uV / 1000, ldo = rdev_get_id(rdev); + int sel, volt_reg, ldo = rdev_get_id(rdev); u16 val; - dev_dbg(wm8350->dev, "%s %d mV %d\n", __func__, ldo, mV); - - if (mV < 900 || mV > 3300) { - dev_err(wm8350->dev, "LDO%d voltage %d mV out of range\n", - ldo, mV); - return -EINVAL; - } + dev_dbg(wm8350->dev, "%s %d mV %d\n", __func__, ldo, uV / 1000); switch (ldo) { case WM8350_LDO_1: @@ -688,10 +603,13 @@ static int wm8350_ldo_set_suspend_voltage(struct regulator_dev *rdev, int uV) return -EINVAL; } + sel = wm8350_ldo_map_voltage(rdev, uV, uV); + if (sel < 0) + return -EINVAL; + /* all LDOs have same mV bits */ val = wm8350_reg_read(wm8350, volt_reg) & ~WM8350_LDO1_VSEL_MASK; - wm8350_reg_write(wm8350, volt_reg, - val | wm8350_ldo_mvolts_to_val(mV)); + wm8350_reg_write(wm8350, volt_reg, val | sel); return 0; } @@ -753,92 +671,6 @@ static int wm8350_ldo_set_suspend_disable(struct regulator_dev *rdev) return 0; } -static int wm8350_ldo_set_voltage(struct regulator_dev *rdev, int min_uV, - int max_uV, unsigned *selector) -{ - struct wm8350 *wm8350 = rdev_get_drvdata(rdev); - int volt_reg, ldo = rdev_get_id(rdev), mV, min_mV = min_uV / 1000, - max_mV = max_uV / 1000; - u16 val; - - if (min_mV < 900 || min_mV > 3300) - return -EINVAL; - if (max_mV < 900 || max_mV > 3300) - return -EINVAL; - - if (min_mV < 1800) { - /* step size is 50mV < 1800mV */ - mV = (min_mV - 851) / 50; - if (wm8350_ldo_val_to_mvolts(mV) > max_mV) - return -EINVAL; - BUG_ON(wm8350_ldo_val_to_mvolts(mV) < min_mV); - } else { - /* step size is 100mV > 1800mV */ - mV = ((min_mV - 1701) / 100) + 16; - if (wm8350_ldo_val_to_mvolts(mV) > max_mV) - return -EINVAL; - BUG_ON(wm8350_ldo_val_to_mvolts(mV) < min_mV); - } - - switch (ldo) { - case WM8350_LDO_1: - volt_reg = WM8350_LDO1_CONTROL; - break; - case WM8350_LDO_2: - volt_reg = WM8350_LDO2_CONTROL; - break; - case WM8350_LDO_3: - volt_reg = WM8350_LDO3_CONTROL; - break; - case WM8350_LDO_4: - volt_reg = WM8350_LDO4_CONTROL; - break; - default: - return -EINVAL; - } - - *selector = mV; - - /* all LDOs have same mV bits */ - val = wm8350_reg_read(wm8350, volt_reg) & ~WM8350_LDO1_VSEL_MASK; - wm8350_reg_write(wm8350, volt_reg, val | mV); - return 0; -} - -static int wm8350_ldo_get_voltage_sel(struct regulator_dev *rdev) -{ - struct wm8350 *wm8350 = rdev_get_drvdata(rdev); - int volt_reg, ldo = rdev_get_id(rdev); - - switch (ldo) { - case WM8350_LDO_1: - volt_reg = WM8350_LDO1_CONTROL; - break; - case WM8350_LDO_2: - volt_reg = WM8350_LDO2_CONTROL; - break; - case WM8350_LDO_3: - volt_reg = WM8350_LDO3_CONTROL; - break; - case WM8350_LDO_4: - volt_reg = WM8350_LDO4_CONTROL; - break; - default: - return -EINVAL; - } - - /* all LDOs have same mV bits */ - return wm8350_reg_read(wm8350, volt_reg) & WM8350_LDO1_VSEL_MASK; -} - -static int wm8350_ldo_list_voltage(struct regulator_dev *rdev, - unsigned selector) -{ - if (selector > WM8350_LDO1_VSEL_MASK) - return -EINVAL; - return wm8350_ldo_val_to_mvolts(selector) * 1000; -} - int wm8350_dcdc_set_slot(struct wm8350 *wm8350, int dcdc, u16 start, u16 stop, u16 fault) { @@ -959,63 +791,6 @@ int wm8350_dcdc25_set_mode(struct wm8350 *wm8350, int dcdc, u16 mode, } EXPORT_SYMBOL_GPL(wm8350_dcdc25_set_mode); -static int wm8350_dcdc_enable(struct regulator_dev *rdev) -{ - struct wm8350 *wm8350 = rdev_get_drvdata(rdev); - int dcdc = rdev_get_id(rdev); - u16 shift; - - if (dcdc < WM8350_DCDC_1 || dcdc > WM8350_DCDC_6) - return -EINVAL; - - shift = dcdc - WM8350_DCDC_1; - wm8350_set_bits(wm8350, WM8350_DCDC_LDO_REQUESTED, 1 << shift); - return 0; -} - -static int wm8350_dcdc_disable(struct regulator_dev *rdev) -{ - struct wm8350 *wm8350 = rdev_get_drvdata(rdev); - int dcdc = rdev_get_id(rdev); - u16 shift; - - if (dcdc < WM8350_DCDC_1 || dcdc > WM8350_DCDC_6) - return -EINVAL; - - shift = dcdc - WM8350_DCDC_1; - wm8350_clear_bits(wm8350, WM8350_DCDC_LDO_REQUESTED, 1 << shift); - - return 0; -} - -static int wm8350_ldo_enable(struct regulator_dev *rdev) -{ - struct wm8350 *wm8350 = rdev_get_drvdata(rdev); - int ldo = rdev_get_id(rdev); - u16 shift; - - if (ldo < WM8350_LDO_1 || ldo > WM8350_LDO_4) - return -EINVAL; - - shift = (ldo - WM8350_LDO_1) + 8; - wm8350_set_bits(wm8350, WM8350_DCDC_LDO_REQUESTED, 1 << shift); - return 0; -} - -static int wm8350_ldo_disable(struct regulator_dev *rdev) -{ - struct wm8350 *wm8350 = rdev_get_drvdata(rdev); - int ldo = rdev_get_id(rdev); - u16 shift; - - if (ldo < WM8350_LDO_1 || ldo > WM8350_LDO_4) - return -EINVAL; - - shift = (ldo - WM8350_LDO_1) + 8; - wm8350_clear_bits(wm8350, WM8350_DCDC_LDO_REQUESTED, 1 << shift); - return 0; -} - static int force_continuous_enable(struct wm8350 *wm8350, int dcdc, int enable) { int reg = 0, ret; @@ -1197,42 +972,17 @@ static unsigned int wm8350_dcdc_get_optimum_mode(struct regulator_dev *rdev, return mode; } -static int wm8350_dcdc_is_enabled(struct regulator_dev *rdev) -{ - struct wm8350 *wm8350 = rdev_get_drvdata(rdev); - int dcdc = rdev_get_id(rdev), shift; - - if (dcdc < WM8350_DCDC_1 || dcdc > WM8350_DCDC_6) - return -EINVAL; - - shift = dcdc - WM8350_DCDC_1; - return wm8350_reg_read(wm8350, WM8350_DCDC_LDO_REQUESTED) - & (1 << shift); -} - -static int wm8350_ldo_is_enabled(struct regulator_dev *rdev) -{ - struct wm8350 *wm8350 = rdev_get_drvdata(rdev); - int ldo = rdev_get_id(rdev), shift; - - if (ldo < WM8350_LDO_1 || ldo > WM8350_LDO_4) - return -EINVAL; - - shift = (ldo - WM8350_LDO_1) + 8; - return wm8350_reg_read(wm8350, WM8350_DCDC_LDO_REQUESTED) - & (1 << shift); -} - static struct regulator_ops wm8350_dcdc_ops = { - .set_voltage = wm8350_dcdc_set_voltage, - .get_voltage_sel = wm8350_dcdc_get_voltage_sel, - .list_voltage = wm8350_dcdc_list_voltage, - .enable = wm8350_dcdc_enable, - .disable = wm8350_dcdc_disable, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, .get_mode = wm8350_dcdc_get_mode, .set_mode = wm8350_dcdc_set_mode, .get_optimum_mode = wm8350_dcdc_get_optimum_mode, - .is_enabled = wm8350_dcdc_is_enabled, .set_suspend_voltage = wm8350_dcdc_set_suspend_voltage, .set_suspend_enable = wm8350_dcdc_set_suspend_enable, .set_suspend_disable = wm8350_dcdc_set_suspend_disable, @@ -1240,20 +990,21 @@ static struct regulator_ops wm8350_dcdc_ops = { }; static struct regulator_ops wm8350_dcdc2_5_ops = { - .enable = wm8350_dcdc_enable, - .disable = wm8350_dcdc_disable, - .is_enabled = wm8350_dcdc_is_enabled, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, .set_suspend_enable = wm8350_dcdc25_set_suspend_enable, .set_suspend_disable = wm8350_dcdc25_set_suspend_disable, }; static struct regulator_ops wm8350_ldo_ops = { - .set_voltage = wm8350_ldo_set_voltage, - .get_voltage_sel = wm8350_ldo_get_voltage_sel, + .map_voltage = wm8350_ldo_map_voltage, + .set_voltage_sel = regulator_set_voltage_sel_regmap, + .get_voltage_sel = regulator_get_voltage_sel_regmap, .list_voltage = wm8350_ldo_list_voltage, - .enable = wm8350_ldo_enable, - .disable = wm8350_ldo_disable, - .is_enabled = wm8350_ldo_is_enabled, + .enable = regulator_enable_regmap, + .disable = regulator_disable_regmap, + .is_enabled = regulator_is_enabled_regmap, .get_mode = wm8350_ldo_get_mode, .set_suspend_voltage = wm8350_ldo_set_suspend_voltage, .set_suspend_enable = wm8350_ldo_set_suspend_enable, @@ -1277,6 +1028,12 @@ static const struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = { .irq = WM8350_IRQ_UV_DC1, .type = REGULATOR_VOLTAGE, .n_voltages = WM8350_DCDC_MAX_VSEL + 1, + .min_uV = 850000, + .uV_step = 25000, + .vsel_reg = WM8350_DCDC1_CONTROL, + .vsel_mask = WM8350_DC1_VSEL_MASK, + .enable_reg = WM8350_DCDC_LDO_REQUESTED, + .enable_mask = WM8350_DC1_ENA, .owner = THIS_MODULE, }, { @@ -1285,6 +1042,8 @@ static const struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = { .ops = &wm8350_dcdc2_5_ops, .irq = WM8350_IRQ_UV_DC2, .type = REGULATOR_VOLTAGE, + .enable_reg = WM8350_DCDC_LDO_REQUESTED, + .enable_mask = WM8350_DC2_ENA, .owner = THIS_MODULE, }, { @@ -1294,6 +1053,12 @@ static const struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = { .irq = WM8350_IRQ_UV_DC3, .type = REGULATOR_VOLTAGE, .n_voltages = WM8350_DCDC_MAX_VSEL + 1, + .min_uV = 850000, + .uV_step = 25000, + .vsel_reg = WM8350_DCDC3_CONTROL, + .vsel_mask = WM8350_DC3_VSEL_MASK, + .enable_reg = WM8350_DCDC_LDO_REQUESTED, + .enable_mask = WM8350_DC3_ENA, .owner = THIS_MODULE, }, { @@ -1303,6 +1068,12 @@ static const struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = { .irq = WM8350_IRQ_UV_DC4, .type = REGULATOR_VOLTAGE, .n_voltages = WM8350_DCDC_MAX_VSEL + 1, + .min_uV = 850000, + .uV_step = 25000, + .vsel_reg = WM8350_DCDC4_CONTROL, + .vsel_mask = WM8350_DC4_VSEL_MASK, + .enable_reg = WM8350_DCDC_LDO_REQUESTED, + .enable_mask = WM8350_DC4_ENA, .owner = THIS_MODULE, }, { @@ -1311,6 +1082,8 @@ static const struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = { .ops = &wm8350_dcdc2_5_ops, .irq = WM8350_IRQ_UV_DC5, .type = REGULATOR_VOLTAGE, + .enable_reg = WM8350_DCDC_LDO_REQUESTED, + .enable_mask = WM8350_DC5_ENA, .owner = THIS_MODULE, }, { @@ -1320,6 +1093,12 @@ static const struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = { .irq = WM8350_IRQ_UV_DC6, .type = REGULATOR_VOLTAGE, .n_voltages = WM8350_DCDC_MAX_VSEL + 1, + .min_uV = 850000, + .uV_step = 25000, + .vsel_reg = WM8350_DCDC6_CONTROL, + .vsel_mask = WM8350_DC6_VSEL_MASK, + .enable_reg = WM8350_DCDC_LDO_REQUESTED, + .enable_mask = WM8350_DC6_ENA, .owner = THIS_MODULE, }, { @@ -1329,6 +1108,10 @@ static const struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = { .irq = WM8350_IRQ_UV_LDO1, .type = REGULATOR_VOLTAGE, .n_voltages = WM8350_LDO1_VSEL_MASK + 1, + .vsel_reg = WM8350_LDO1_CONTROL, + .vsel_mask = WM8350_LDO1_VSEL_MASK, + .enable_reg = WM8350_DCDC_LDO_REQUESTED, + .enable_mask = WM8350_LDO1_ENA, .owner = THIS_MODULE, }, { @@ -1338,6 +1121,10 @@ static const struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = { .irq = WM8350_IRQ_UV_LDO2, .type = REGULATOR_VOLTAGE, .n_voltages = WM8350_LDO2_VSEL_MASK + 1, + .vsel_reg = WM8350_LDO2_CONTROL, + .vsel_mask = WM8350_LDO2_VSEL_MASK, + .enable_reg = WM8350_DCDC_LDO_REQUESTED, + .enable_mask = WM8350_LDO2_ENA, .owner = THIS_MODULE, }, { @@ -1347,6 +1134,10 @@ static const struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = { .irq = WM8350_IRQ_UV_LDO3, .type = REGULATOR_VOLTAGE, .n_voltages = WM8350_LDO3_VSEL_MASK + 1, + .vsel_reg = WM8350_LDO3_CONTROL, + .vsel_mask = WM8350_LDO3_VSEL_MASK, + .enable_reg = WM8350_DCDC_LDO_REQUESTED, + .enable_mask = WM8350_LDO3_ENA, .owner = THIS_MODULE, }, { @@ -1356,6 +1147,10 @@ static const struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = { .irq = WM8350_IRQ_UV_LDO4, .type = REGULATOR_VOLTAGE, .n_voltages = WM8350_LDO4_VSEL_MASK + 1, + .vsel_reg = WM8350_LDO4_CONTROL, + .vsel_mask = WM8350_LDO4_VSEL_MASK, + .enable_reg = WM8350_DCDC_LDO_REQUESTED, + .enable_mask = WM8350_LDO4_ENA, .owner = THIS_MODULE, }, { @@ -1429,6 +1224,7 @@ static int wm8350_regulator_probe(struct platform_device *pdev) config.dev = &pdev->dev; config.init_data = pdev->dev.platform_data; config.driver_data = dev_get_drvdata(&pdev->dev); + config.regmap = wm8350->regmap; /* register regulator */ rdev = regulator_register(&wm8350_reg[pdev->id], &config); diff --git a/drivers/regulator/wm8400-regulator.c b/drivers/regulator/wm8400-regulator.c index 69a2b7ce5e4a..9035dd053611 100644 --- a/drivers/regulator/wm8400-regulator.c +++ b/drivers/regulator/wm8400-regulator.c @@ -28,34 +28,26 @@ static int wm8400_ldo_list_voltage(struct regulator_dev *dev, if (selector < 15) return 900000 + (selector * 50000); else - return 1600000 + ((selector - 14) * 100000); + return 1700000 + ((selector - 15) * 100000); } static int wm8400_ldo_map_voltage(struct regulator_dev *dev, int min_uV, int max_uV) { u16 val; + int volt; if (min_uV < 900000 || min_uV > 3300000) return -EINVAL; - if (min_uV < 1700000) { - /* Steps of 50mV from 900mV; */ + if (min_uV < 1700000) /* Steps of 50mV from 900mV; */ val = DIV_ROUND_UP(min_uV - 900000, 50000); + else /* Steps of 100mV from 1700mV */ + val = DIV_ROUND_UP(min_uV - 1700000, 100000) + 15; - if ((val * 50000) + 900000 > max_uV) - return -EINVAL; - BUG_ON((val * 50000) + 900000 < min_uV); - } else { - /* Steps of 100mV from 1700mV */ - val = DIV_ROUND_UP(min_uV - 1700000, 100000); - - if ((val * 100000) + 1700000 > max_uV) - return -EINVAL; - BUG_ON((val * 100000) + 1700000 < min_uV); - - val += 0xf; - } + volt = wm8400_ldo_list_voltage(dev, val); + if (volt < min_uV || volt > max_uV) + return -EINVAL; return val; } @@ -152,6 +144,7 @@ static struct regulator_ops wm8400_dcdc_ops = { .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_sel = regulator_set_voltage_sel_regmap, .get_mode = wm8400_dcdc_get_mode, diff --git a/drivers/regulator/wm8994-regulator.c b/drivers/regulator/wm8994-regulator.c index 9a994316e63c..86bb48db149e 100644 --- a/drivers/regulator/wm8994-regulator.c +++ b/drivers/regulator/wm8994-regulator.c @@ -26,8 +26,6 @@ #include <linux/mfd/wm8994/pdata.h> struct wm8994_ldo { - int enable; - bool is_enabled; struct regulator_dev *regulator; struct wm8994 *wm8994; }; @@ -35,64 +33,9 @@ struct wm8994_ldo { #define WM8994_LDO1_MAX_SELECTOR 0x7 #define WM8994_LDO2_MAX_SELECTOR 0x3 -static int wm8994_ldo_enable(struct regulator_dev *rdev) -{ - struct wm8994_ldo *ldo = rdev_get_drvdata(rdev); - - /* If we have no soft control assume that the LDO is always enabled. */ - if (!ldo->enable) - return 0; - - gpio_set_value_cansleep(ldo->enable, 1); - ldo->is_enabled = true; - - return 0; -} - -static int wm8994_ldo_disable(struct regulator_dev *rdev) -{ - struct wm8994_ldo *ldo = rdev_get_drvdata(rdev); - - /* If we have no soft control assume that the LDO is always enabled. */ - if (!ldo->enable) - return -EINVAL; - - gpio_set_value_cansleep(ldo->enable, 0); - ldo->is_enabled = false; - - return 0; -} - -static int wm8994_ldo_is_enabled(struct regulator_dev *rdev) -{ - struct wm8994_ldo *ldo = rdev_get_drvdata(rdev); - - return ldo->is_enabled; -} - -static int wm8994_ldo_enable_time(struct regulator_dev *rdev) -{ - /* 3ms is fairly conservative but this shouldn't be too performance - * critical; can be tweaked per-system if required. */ - return 3000; -} - -static int wm8994_ldo1_list_voltage(struct regulator_dev *rdev, - unsigned int selector) -{ - if (selector > WM8994_LDO1_MAX_SELECTOR) - return -EINVAL; - - return (selector * 100000) + 2400000; -} - static struct regulator_ops wm8994_ldo1_ops = { - .enable = wm8994_ldo_enable, - .disable = wm8994_ldo_disable, - .is_enabled = wm8994_ldo_is_enabled, - .enable_time = wm8994_ldo_enable_time, - - .list_voltage = wm8994_ldo1_list_voltage, + .list_voltage = regulator_list_voltage_linear, + .map_voltage = regulator_map_voltage_linear, .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_sel = regulator_set_voltage_sel_regmap, }; @@ -124,11 +67,6 @@ static int wm8994_ldo2_list_voltage(struct regulator_dev *rdev, } static struct regulator_ops wm8994_ldo2_ops = { - .enable = wm8994_ldo_enable, - .disable = wm8994_ldo_disable, - .is_enabled = wm8994_ldo_is_enabled, - .enable_time = wm8994_ldo_enable_time, - .list_voltage = wm8994_ldo2_list_voltage, .get_voltage_sel = regulator_get_voltage_sel_regmap, .set_voltage_sel = regulator_set_voltage_sel_regmap, @@ -143,6 +81,9 @@ static const struct regulator_desc wm8994_ldo_desc[] = { .vsel_reg = WM8994_LDO_1, .vsel_mask = WM8994_LDO1_VSEL_MASK, .ops = &wm8994_ldo1_ops, + .min_uV = 2400000, + .uV_step = 100000, + .enable_time = 3000, .owner = THIS_MODULE, }, { @@ -153,6 +94,7 @@ static const struct regulator_desc wm8994_ldo_desc[] = { .vsel_reg = WM8994_LDO_2, .vsel_mask = WM8994_LDO2_VSEL_MASK, .ops = &wm8994_ldo2_ops, + .enable_time = 3000, .owner = THIS_MODULE, }, }; @@ -176,39 +118,26 @@ static __devinit int wm8994_ldo_probe(struct platform_device *pdev) ldo->wm8994 = wm8994; - if (pdata->ldo[id].enable && gpio_is_valid(pdata->ldo[id].enable)) { - ldo->enable = pdata->ldo[id].enable; - - ret = gpio_request_one(ldo->enable, 0, "WM8994 LDO enable"); - if (ret < 0) { - dev_err(&pdev->dev, "Failed to get enable GPIO: %d\n", - ret); - goto err; - } - } else - ldo->is_enabled = true; - config.dev = wm8994->dev; config.driver_data = ldo; config.regmap = wm8994->regmap; - if (pdata) + if (pdata) { config.init_data = pdata->ldo[id].init_data; + config.ena_gpio = pdata->ldo[id].enable; + } ldo->regulator = regulator_register(&wm8994_ldo_desc[id], &config); if (IS_ERR(ldo->regulator)) { ret = PTR_ERR(ldo->regulator); dev_err(wm8994->dev, "Failed to register LDO%d: %d\n", id + 1, ret); - goto err_gpio; + goto err; } platform_set_drvdata(pdev, ldo); return 0; -err_gpio: - if (gpio_is_valid(ldo->enable)) - gpio_free(ldo->enable); err: return ret; } @@ -220,8 +149,6 @@ static __devexit int wm8994_ldo_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); regulator_unregister(ldo->regulator); - if (gpio_is_valid(ldo->enable)) - gpio_free(ldo->enable); return 0; } diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig index 24d880e78ec6..f8d818abf98c 100644 --- a/drivers/remoteproc/Kconfig +++ b/drivers/remoteproc/Kconfig @@ -4,9 +4,11 @@ menu "Remoteproc drivers (EXPERIMENTAL)" config REMOTEPROC tristate depends on EXPERIMENTAL + select FW_CONFIG config OMAP_REMOTEPROC tristate "OMAP remoteproc support" + depends on EXPERIMENTAL depends on ARCH_OMAP4 depends on OMAP_IOMMU select REMOTEPROC diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index 75506ec2840e..f56c8ba3a861 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -188,6 +188,26 @@ static int rpmsg_uevent(struct device *dev, struct kobj_uevent_env *env) rpdev->id.name); } +/** + * __ept_release() - deallocate an rpmsg endpoint + * @kref: the ept's reference count + * + * This function deallocates an ept, and is invoked when its @kref refcount + * drops to zero. + * + * Never invoke this function directly! + */ +static void __ept_release(struct kref *kref) +{ + struct rpmsg_endpoint *ept = container_of(kref, struct rpmsg_endpoint, + refcount); + /* + * At this point no one holds a reference to ept anymore, + * so we can directly free it + */ + kfree(ept); +} + /* for more info, see below documentation of rpmsg_create_ept() */ static struct rpmsg_endpoint *__rpmsg_create_ept(struct virtproc_info *vrp, struct rpmsg_channel *rpdev, rpmsg_rx_cb_t cb, @@ -206,6 +226,9 @@ static struct rpmsg_endpoint *__rpmsg_create_ept(struct virtproc_info *vrp, return NULL; } + kref_init(&ept->refcount); + mutex_init(&ept->cb_lock); + ept->rpdev = rpdev; ept->cb = cb; ept->priv = priv; @@ -238,7 +261,7 @@ rem_idr: idr_remove(&vrp->endpoints, request); free_ept: mutex_unlock(&vrp->endpoints_lock); - kfree(ept); + kref_put(&ept->refcount, __ept_release); return NULL; } @@ -302,11 +325,17 @@ EXPORT_SYMBOL(rpmsg_create_ept); static void __rpmsg_destroy_ept(struct virtproc_info *vrp, struct rpmsg_endpoint *ept) { + /* make sure new inbound messages can't find this ept anymore */ mutex_lock(&vrp->endpoints_lock); idr_remove(&vrp->endpoints, ept->addr); mutex_unlock(&vrp->endpoints_lock); - kfree(ept); + /* make sure in-flight inbound messages won't invoke cb anymore */ + mutex_lock(&ept->cb_lock); + ept->cb = NULL; + mutex_unlock(&ept->cb_lock); + + kref_put(&ept->refcount, __ept_release); } /** @@ -790,12 +819,28 @@ static void rpmsg_recv_done(struct virtqueue *rvq) /* use the dst addr to fetch the callback of the appropriate user */ mutex_lock(&vrp->endpoints_lock); + ept = idr_find(&vrp->endpoints, msg->dst); + + /* let's make sure no one deallocates ept while we use it */ + if (ept) + kref_get(&ept->refcount); + mutex_unlock(&vrp->endpoints_lock); - if (ept && ept->cb) - ept->cb(ept->rpdev, msg->data, msg->len, ept->priv, msg->src); - else + if (ept) { + /* make sure ept->cb doesn't go away while we use it */ + mutex_lock(&ept->cb_lock); + + if (ept->cb) + ept->cb(ept->rpdev, msg->data, msg->len, ept->priv, + msg->src); + + mutex_unlock(&ept->cb_lock); + + /* farewell, ept, we don't need you anymore */ + kref_put(&ept->refcount, __ept_release); + } else dev_warn(dev, "msg received with no recepient\n"); /* publish the real size of the buffer */ @@ -1040,7 +1085,7 @@ static int __init rpmsg_init(void) return ret; } -module_init(rpmsg_init); +subsys_initcall(rpmsg_init); static void __exit rpmsg_fini(void) { diff --git a/drivers/rtc/rtc-ab8500.c b/drivers/rtc/rtc-ab8500.c index 4bcf9ca2818a..370889d0489b 100644 --- a/drivers/rtc/rtc-ab8500.c +++ b/drivers/rtc/rtc-ab8500.c @@ -17,6 +17,7 @@ #include <linux/mfd/abx500.h> #include <linux/mfd/abx500/ab8500.h> #include <linux/delay.h> +#include <linux/of.h> #define AB8500_RTC_SOFF_STAT_REG 0x00 #define AB8500_RTC_CC_CONF_REG 0x01 @@ -422,7 +423,7 @@ static int __devinit ab8500_rtc_probe(struct platform_device *pdev) } err = request_threaded_irq(irq, NULL, rtc_alarm_handler, - IRQF_NO_SUSPEND, "ab8500-rtc", rtc); + IRQF_NO_SUSPEND | IRQF_ONESHOT, "ab8500-rtc", rtc); if (err < 0) { rtc_device_unregister(rtc); return err; @@ -430,7 +431,6 @@ static int __devinit ab8500_rtc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, rtc); - err = ab8500_sysfs_rtc_register(&pdev->dev); if (err) { dev_err(&pdev->dev, "sysfs RTC failed to register\n"); @@ -454,10 +454,16 @@ static int __devexit ab8500_rtc_remove(struct platform_device *pdev) return 0; } +static const struct of_device_id ab8500_rtc_match[] = { + { .compatible = "stericsson,ab8500-rtc", }, + {} +}; + static struct platform_driver ab8500_rtc_driver = { .driver = { .name = "ab8500-rtc", .owner = THIS_MODULE, + .of_match_table = ab8500_rtc_match, }, .probe = ab8500_rtc_probe, .remove = __devexit_p(ab8500_rtc_remove), diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 4267789ca995..132333d75408 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -568,6 +568,7 @@ static irqreturn_t cmos_interrupt(int irq, void *p) hpet_mask_rtc_irq_bit(RTC_AIE); CMOS_READ(RTC_INTR_FLAGS); + pm_wakeup_event(cmos_rtc.dev, 0); } spin_unlock(&rtc_lock); diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c index 5e1d64ee5228..e3e50d69baf8 100644 --- a/drivers/rtc/rtc-mxc.c +++ b/drivers/rtc/rtc-mxc.c @@ -202,10 +202,11 @@ static irqreturn_t mxc_rtc_interrupt(int irq, void *dev_id) struct platform_device *pdev = dev_id; struct rtc_plat_data *pdata = platform_get_drvdata(pdev); void __iomem *ioaddr = pdata->ioaddr; + unsigned long flags; u32 status; u32 events = 0; - spin_lock_irq(&pdata->rtc->irq_lock); + spin_lock_irqsave(&pdata->rtc->irq_lock, flags); status = readw(ioaddr + RTC_RTCISR) & readw(ioaddr + RTC_RTCIENR); /* clear interrupt sources */ writew(status, ioaddr + RTC_RTCISR); @@ -224,7 +225,7 @@ static irqreturn_t mxc_rtc_interrupt(int irq, void *dev_id) events |= (RTC_PF | RTC_IRQF); rtc_update_irq(pdata->rtc, 1, events); - spin_unlock_irq(&pdata->rtc->irq_lock); + spin_unlock_irqrestore(&pdata->rtc->irq_lock, flags); return IRQ_HANDLED; } diff --git a/drivers/rtc/rtc-spear.c b/drivers/rtc/rtc-spear.c index 1f76320e545b..e2785479113c 100644 --- a/drivers/rtc/rtc-spear.c +++ b/drivers/rtc/rtc-spear.c @@ -458,12 +458,12 @@ static int __devexit spear_rtc_remove(struct platform_device *pdev) clk_disable(config->clk); clk_put(config->clk); iounmap(config->ioaddr); - kfree(config); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (res) release_mem_region(res->start, resource_size(res)); platform_set_drvdata(pdev, NULL); rtc_device_unregister(config->rtc); + kfree(config); return 0; } diff --git a/drivers/rtc/rtc-twl.c b/drivers/rtc/rtc-twl.c index 258abeabf624..c5d06fe83bba 100644 --- a/drivers/rtc/rtc-twl.c +++ b/drivers/rtc/rtc-twl.c @@ -510,7 +510,7 @@ static int __devinit twl_rtc_probe(struct platform_device *pdev) } ret = request_threaded_irq(irq, NULL, twl_rtc_interrupt, - IRQF_TRIGGER_RISING, + IRQF_TRIGGER_RISING | IRQF_ONESHOT, dev_name(&rtc->dev), rtc); if (ret < 0) { dev_err(&pdev->dev, "IRQ is not free.\n"); diff --git a/drivers/scsi/aic94xx/aic94xx_task.c b/drivers/scsi/aic94xx/aic94xx_task.c index 532d212b6b2c..393e7ce8e95a 100644 --- a/drivers/scsi/aic94xx/aic94xx_task.c +++ b/drivers/scsi/aic94xx/aic94xx_task.c @@ -201,7 +201,7 @@ static void asd_get_response_tasklet(struct asd_ascb *ascb, if (SAS_STATUS_BUF_SIZE >= sizeof(*resp)) { resp->frame_len = le16_to_cpu(*(__le16 *)(r+6)); - memcpy(&resp->ending_fis[0], r+16, 24); + memcpy(&resp->ending_fis[0], r+16, ATA_RESP_FIS_SIZE); ts->buf_valid_size = sizeof(*resp); } } diff --git a/drivers/scsi/bnx2i/bnx2i.h b/drivers/scsi/bnx2i/bnx2i.h index 0c53c28dc3d3..7e77cf620291 100644 --- a/drivers/scsi/bnx2i/bnx2i.h +++ b/drivers/scsi/bnx2i/bnx2i.h @@ -350,6 +350,7 @@ struct bnx2i_hba { struct pci_dev *pcidev; struct net_device *netdev; void __iomem *regview; + resource_size_t reg_base; u32 age; unsigned long cnic_dev_type; diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c index ece47e502282..86a12b48e477 100644 --- a/drivers/scsi/bnx2i/bnx2i_hwi.c +++ b/drivers/scsi/bnx2i/bnx2i_hwi.c @@ -2724,7 +2724,6 @@ int bnx2i_map_ep_dbell_regs(struct bnx2i_endpoint *ep) goto arm_cq; } - reg_base = ep->hba->netdev->base_addr; if ((test_bit(BNX2I_NX2_DEV_5709, &ep->hba->cnic_dev_type)) && (ep->hba->mail_queue_access == BNX2I_MQ_BIN_MODE)) { config2 = REG_RD(ep->hba, BNX2_MQ_CONFIG2); @@ -2740,7 +2739,7 @@ int bnx2i_map_ep_dbell_regs(struct bnx2i_endpoint *ep) /* 5709 device in normal node and 5706/5708 devices */ reg_off = CTX_OFFSET + (MB_KERNEL_CTX_SIZE * cid_num); - ep->qp.ctx_base = ioremap_nocache(reg_base + reg_off, + ep->qp.ctx_base = ioremap_nocache(ep->hba->reg_base + reg_off, MB_KERNEL_CTX_SIZE); if (!ep->qp.ctx_base) return -ENOMEM; diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c index f8d516b53161..621538b8b544 100644 --- a/drivers/scsi/bnx2i/bnx2i_iscsi.c +++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c @@ -811,13 +811,13 @@ struct bnx2i_hba *bnx2i_alloc_hba(struct cnic_dev *cnic) bnx2i_identify_device(hba); bnx2i_setup_host_queue_size(hba, shost); + hba->reg_base = pci_resource_start(hba->pcidev, 0); if (test_bit(BNX2I_NX2_DEV_5709, &hba->cnic_dev_type)) { - hba->regview = ioremap_nocache(hba->netdev->base_addr, - BNX2_MQ_CONFIG2); + hba->regview = pci_iomap(hba->pcidev, 0, BNX2_MQ_CONFIG2); if (!hba->regview) goto ioreg_map_err; } else if (test_bit(BNX2I_NX2_DEV_57710, &hba->cnic_dev_type)) { - hba->regview = ioremap_nocache(hba->netdev->base_addr, 4096); + hba->regview = pci_iomap(hba->pcidev, 0, 4096); if (!hba->regview) goto ioreg_map_err; } @@ -884,7 +884,7 @@ cid_que_err: bnx2i_free_mp_bdt(hba); mp_bdt_mem_err: if (hba->regview) { - iounmap(hba->regview); + pci_iounmap(hba->pcidev, hba->regview); hba->regview = NULL; } ioreg_map_err: @@ -910,7 +910,7 @@ void bnx2i_free_hba(struct bnx2i_hba *hba) pci_dev_put(hba->pcidev); if (hba->regview) { - iounmap(hba->regview); + pci_iounmap(hba->pcidev, hba->regview); hba->regview = NULL; } bnx2i_free_mp_bdt(hba); diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 441d88ad99a7..d109cc3a17b6 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -139,12 +139,12 @@ static void sas_ata_task_done(struct sas_task *task) if (stat->stat == SAS_PROTO_RESPONSE || stat->stat == SAM_STAT_GOOD || ((stat->stat == SAM_STAT_CHECK_CONDITION && dev->sata_dev.command_set == ATAPI_COMMAND_SET))) { - ata_tf_from_fis(resp->ending_fis, &dev->sata_dev.tf); + memcpy(dev->sata_dev.fis, resp->ending_fis, ATA_RESP_FIS_SIZE); if (!link->sactive) { - qc->err_mask |= ac_err_mask(dev->sata_dev.tf.command); + qc->err_mask |= ac_err_mask(dev->sata_dev.fis[2]); } else { - link->eh_info.err_mask |= ac_err_mask(dev->sata_dev.tf.command); + link->eh_info.err_mask |= ac_err_mask(dev->sata_dev.fis[2]); if (unlikely(link->eh_info.err_mask)) qc->flags |= ATA_QCFLAG_FAILED; } @@ -161,8 +161,8 @@ static void sas_ata_task_done(struct sas_task *task) qc->flags |= ATA_QCFLAG_FAILED; } - dev->sata_dev.tf.feature = 0x04; /* status err */ - dev->sata_dev.tf.command = ATA_ERR; + dev->sata_dev.fis[3] = 0x04; /* status err */ + dev->sata_dev.fis[2] = ATA_ERR; } } @@ -269,7 +269,7 @@ static bool sas_ata_qc_fill_rtf(struct ata_queued_cmd *qc) { struct domain_device *dev = qc->ap->private_data; - memcpy(&qc->result_tf, &dev->sata_dev.tf, sizeof(qc->result_tf)); + ata_tf_from_fis(dev->sata_dev.fis, &qc->result_tf); return true; } diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 6986552b47e6..5b30132960c7 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -2643,19 +2643,9 @@ static void qlt_do_work(struct work_struct *work) spin_lock_irqsave(&ha->hardware_lock, flags); sess = ha->tgt.tgt_ops->find_sess_by_s_id(vha, atio->u.isp24.fcp_hdr.s_id); - if (sess) { - if (unlikely(sess->tearing_down)) { - sess = NULL; - spin_unlock_irqrestore(&ha->hardware_lock, flags); - goto out_term; - } else { - /* - * Do the extra kref_get() before dropping - * qla_hw_data->hardware_lock. - */ - kref_get(&sess->se_sess->sess_kref); - } - } + /* Do kref_get() before dropping qla_hw_data->hardware_lock. */ + if (sess) + kref_get(&sess->se_sess->sess_kref); spin_unlock_irqrestore(&ha->hardware_lock, flags); if (unlikely(!sess)) { @@ -3960,7 +3950,7 @@ void qlt_async_event(uint16_t code, struct scsi_qla_host *vha, { struct qla_hw_data *ha = vha->hw; struct qla_tgt *tgt = ha->tgt.qla_tgt; - int reason_code; + int login_code; ql_dbg(ql_dbg_tgt, vha, 0xe039, "scsi(%ld): ha state %d init_done %d oper_mode %d topo %d\n", @@ -4003,9 +3993,9 @@ void qlt_async_event(uint16_t code, struct scsi_qla_host *vha, { ql_dbg(ql_dbg_tgt_mgt, vha, 0xf03b, "qla_target(%d): Async LOOP_UP occured " - "(m[1]=%x, m[2]=%x, m[3]=%x, m[4]=%x)", vha->vp_idx, - le16_to_cpu(mailbox[1]), le16_to_cpu(mailbox[2]), - le16_to_cpu(mailbox[3]), le16_to_cpu(mailbox[4])); + "(m[0]=%x, m[1]=%x, m[2]=%x, m[3]=%x)", vha->vp_idx, + le16_to_cpu(mailbox[0]), le16_to_cpu(mailbox[1]), + le16_to_cpu(mailbox[2]), le16_to_cpu(mailbox[3])); if (tgt->link_reinit_iocb_pending) { qlt_send_notify_ack(vha, (void *)&tgt->link_reinit_iocb, 0, 0, 0, 0, 0, 0); @@ -4020,23 +4010,24 @@ void qlt_async_event(uint16_t code, struct scsi_qla_host *vha, case MBA_RSCN_UPDATE: ql_dbg(ql_dbg_tgt_mgt, vha, 0xf03c, "qla_target(%d): Async event %#x occured " - "(m[1]=%x, m[2]=%x, m[3]=%x, m[4]=%x)", vha->vp_idx, code, - le16_to_cpu(mailbox[1]), le16_to_cpu(mailbox[2]), - le16_to_cpu(mailbox[3]), le16_to_cpu(mailbox[4])); + "(m[0]=%x, m[1]=%x, m[2]=%x, m[3]=%x)", vha->vp_idx, code, + le16_to_cpu(mailbox[0]), le16_to_cpu(mailbox[1]), + le16_to_cpu(mailbox[2]), le16_to_cpu(mailbox[3])); break; case MBA_PORT_UPDATE: ql_dbg(ql_dbg_tgt_mgt, vha, 0xf03d, "qla_target(%d): Port update async event %#x " - "occured: updating the ports database (m[1]=%x, m[2]=%x, " - "m[3]=%x, m[4]=%x)", vha->vp_idx, code, - le16_to_cpu(mailbox[1]), le16_to_cpu(mailbox[2]), - le16_to_cpu(mailbox[3]), le16_to_cpu(mailbox[4])); - reason_code = le16_to_cpu(mailbox[2]); - if (reason_code == 0x4) + "occured: updating the ports database (m[0]=%x, m[1]=%x, " + "m[2]=%x, m[3]=%x)", vha->vp_idx, code, + le16_to_cpu(mailbox[0]), le16_to_cpu(mailbox[1]), + le16_to_cpu(mailbox[2]), le16_to_cpu(mailbox[3])); + + login_code = le16_to_cpu(mailbox[2]); + if (login_code == 0x4) ql_dbg(ql_dbg_tgt_mgt, vha, 0xf03e, "Async MB 2: Got PLOGI Complete\n"); - else if (reason_code == 0x7) + else if (login_code == 0x7) ql_dbg(ql_dbg_tgt_mgt, vha, 0xf03f, "Async MB 2: Port Logged Out\n"); break; @@ -4044,9 +4035,9 @@ void qlt_async_event(uint16_t code, struct scsi_qla_host *vha, default: ql_dbg(ql_dbg_tgt_mgt, vha, 0xf040, "qla_target(%d): Async event %#x occured: " - "ignore (m[1]=%x, m[2]=%x, m[3]=%x, m[4]=%x)", vha->vp_idx, - code, le16_to_cpu(mailbox[1]), le16_to_cpu(mailbox[2]), - le16_to_cpu(mailbox[3]), le16_to_cpu(mailbox[4])); + "ignore (m[0]=%x, m[1]=%x, m[2]=%x, m[3]=%x)", vha->vp_idx, + code, le16_to_cpu(mailbox[0]), le16_to_cpu(mailbox[1]), + le16_to_cpu(mailbox[2]), le16_to_cpu(mailbox[3])); break; } diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index 9f9ef1644fd9..170af1571214 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -639,7 +639,7 @@ struct qla_tgt_func_tmpl { int (*handle_cmd)(struct scsi_qla_host *, struct qla_tgt_cmd *, unsigned char *, uint32_t, int, int, int); - int (*handle_data)(struct qla_tgt_cmd *); + void (*handle_data)(struct qla_tgt_cmd *); int (*handle_tmr)(struct qla_tgt_mgmt_cmd *, uint32_t, uint8_t, uint32_t); void (*free_cmd)(struct qla_tgt_cmd *); @@ -813,7 +813,6 @@ struct qla_tgt_sess { unsigned int conf_compl_supported:1; unsigned int deleted:1; unsigned int local:1; - unsigned int tearing_down:1; struct se_session *se_sess; struct scsi_qla_host *vha; diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 6e64314dbbb3..4752f65a9272 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -38,8 +38,6 @@ #include <linux/string.h> #include <linux/configfs.h> #include <linux/ctype.h> -#include <linux/string.h> -#include <linux/ctype.h> #include <asm/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_host.h> @@ -466,8 +464,7 @@ static int tcm_qla2xxx_shutdown_session(struct se_session *se_sess) vha = sess->vha; spin_lock_irqsave(&vha->hw->hardware_lock, flags); - sess->tearing_down = 1; - target_splice_sess_cmd_list(se_sess); + target_sess_cmd_list_set_waiting(se_sess); spin_unlock_irqrestore(&vha->hw->hardware_lock, flags); return 1; @@ -600,28 +597,15 @@ static int tcm_qla2xxx_handle_cmd(scsi_qla_host_t *vha, struct qla_tgt_cmd *cmd, return -EINVAL; } - target_submit_cmd(se_cmd, se_sess, cdb, &cmd->sense_buffer[0], + return target_submit_cmd(se_cmd, se_sess, cdb, &cmd->sense_buffer[0], cmd->unpacked_lun, data_length, fcp_task_attr, data_dir, flags); - return 0; } -static void tcm_qla2xxx_do_rsp(struct work_struct *work) +static void tcm_qla2xxx_handle_data_work(struct work_struct *work) { struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work); - /* - * Dispatch ->queue_status from workqueue process context - */ - transport_generic_request_failure(&cmd->se_cmd); -} -/* - * Called from qla_target.c:qlt_do_ctio_completion() - */ -static int tcm_qla2xxx_handle_data(struct qla_tgt_cmd *cmd) -{ - struct se_cmd *se_cmd = &cmd->se_cmd; - unsigned long flags; /* * Ensure that the complete FCP WRITE payload has been received. * Otherwise return an exception via CHECK_CONDITION status. @@ -631,24 +615,26 @@ static int tcm_qla2xxx_handle_data(struct qla_tgt_cmd *cmd) * Check if se_cmd has already been aborted via LUN_RESET, and * waiting upon completion in tcm_qla2xxx_write_pending_status() */ - spin_lock_irqsave(&se_cmd->t_state_lock, flags); - if (se_cmd->transport_state & CMD_T_ABORTED) { - spin_unlock_irqrestore(&se_cmd->t_state_lock, flags); - complete(&se_cmd->t_transport_stop_comp); - return 0; + if (cmd->se_cmd.transport_state & CMD_T_ABORTED) { + complete(&cmd->se_cmd.t_transport_stop_comp); + return; } - spin_unlock_irqrestore(&se_cmd->t_state_lock, flags); - se_cmd->scsi_sense_reason = TCM_CHECK_CONDITION_ABORT_CMD; - INIT_WORK(&cmd->work, tcm_qla2xxx_do_rsp); - queue_work(tcm_qla2xxx_free_wq, &cmd->work); - return 0; + cmd->se_cmd.scsi_sense_reason = TCM_CHECK_CONDITION_ABORT_CMD; + transport_generic_request_failure(&cmd->se_cmd); + return; } - /* - * We now tell TCM to queue this WRITE CDB with TRANSPORT_PROCESS_WRITE - * status to the backstore processing thread. - */ - return transport_generic_handle_data(&cmd->se_cmd); + + return target_execute_cmd(&cmd->se_cmd); +} + +/* + * Called from qla_target.c:qlt_do_ctio_completion() + */ +static void tcm_qla2xxx_handle_data(struct qla_tgt_cmd *cmd) +{ + INIT_WORK(&cmd->work, tcm_qla2xxx_handle_data_work); + queue_work(tcm_qla2xxx_free_wq, &cmd->work); } /* @@ -1690,7 +1676,6 @@ static struct target_core_fabric_ops tcm_qla2xxx_ops = { .tpg_alloc_fabric_acl = tcm_qla2xxx_alloc_fabric_acl, .tpg_release_fabric_acl = tcm_qla2xxx_release_fabric_acl, .tpg_get_inst_index = tcm_qla2xxx_tpg_get_inst_index, - .new_cmd_map = NULL, .check_stop_free = tcm_qla2xxx_check_stop_free, .release_cmd = tcm_qla2xxx_release_cmd, .put_session = tcm_qla2xxx_put_session, diff --git a/drivers/scsi/scsi_wait_scan.c b/drivers/scsi/scsi_wait_scan.c index ae7814874618..072734538876 100644 --- a/drivers/scsi/scsi_wait_scan.c +++ b/drivers/scsi/scsi_wait_scan.c @@ -22,11 +22,6 @@ static int __init wait_scan_init(void) * and might not yet have reached the scsi async scanning */ wait_for_device_probe(); - /* - * and then we wait for the actual asynchronous scsi scan - * to finish. - */ - scsi_complete_async_scans(); return 0; } diff --git a/drivers/target/Makefile b/drivers/target/Makefile index 61648d84fbb6..9fdcb561422f 100644 --- a/drivers/target/Makefile +++ b/drivers/target/Makefile @@ -9,7 +9,8 @@ target_core_mod-y := target_core_configfs.o \ target_core_tmr.o \ target_core_tpg.o \ target_core_transport.o \ - target_core_cdb.o \ + target_core_sbc.o \ + target_core_spc.o \ target_core_ua.o \ target_core_rd.o \ target_core_stat.o diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index d57d10cb2e47..97c0f78c3c9c 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -429,19 +429,8 @@ int iscsit_reset_np_thread( int iscsit_del_np_comm(struct iscsi_np *np) { - if (!np->np_socket) - return 0; - - /* - * Some network transports allocate their own struct sock->file, - * see if we need to free any additional allocated resources. - */ - if (np->np_flags & NPF_SCTP_STRUCT_FILE) { - kfree(np->np_socket->file); - np->np_socket->file = NULL; - } - - sock_release(np->np_socket); + if (np->np_socket) + sock_release(np->np_socket); return 0; } @@ -1413,8 +1402,10 @@ static int iscsit_handle_data_out(struct iscsi_conn *conn, unsigned char *buf) spin_unlock_bh(&cmd->istate_lock); iscsit_stop_dataout_timer(cmd); - return (!ooo_cmdsn) ? transport_generic_handle_data( - &cmd->se_cmd) : 0; + if (ooo_cmdsn) + return 0; + target_execute_cmd(&cmd->se_cmd); + return 0; } else /* DATAOUT_CANNOT_RECOVER */ return -1; @@ -2683,7 +2674,7 @@ static int iscsit_send_logout_response( */ logout_conn = iscsit_get_conn_from_cid_rcfr(sess, cmd->logout_cid); - if ((logout_conn)) { + if (logout_conn) { iscsit_connection_reinstatement_rcfr(logout_conn); iscsit_dec_conn_usage_count(logout_conn); } @@ -4077,13 +4068,8 @@ int iscsit_close_connection( kfree(conn->conn_ops); conn->conn_ops = NULL; - if (conn->sock) { - if (conn->conn_flags & CONNFLAG_SCTP_STRUCT_FILE) { - kfree(conn->sock->file); - conn->sock->file = NULL; - } + if (conn->sock) sock_release(conn->sock); - } conn->thread_set = NULL; pr_debug("Moving to TARG_CONN_STATE_FREE.\n"); diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 69dc8e35c03a..a7b25e783b58 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -47,28 +47,6 @@ struct lio_target_configfs_attribute { ssize_t (*store)(void *, const char *, size_t); }; -struct iscsi_portal_group *lio_get_tpg_from_tpg_item( - struct config_item *item, - struct iscsi_tiqn **tiqn_out) -{ - struct se_portal_group *se_tpg = container_of(to_config_group(item), - struct se_portal_group, tpg_group); - struct iscsi_portal_group *tpg = se_tpg->se_tpg_fabric_ptr; - int ret; - - if (!tpg) { - pr_err("Unable to locate struct iscsi_portal_group " - "pointer\n"); - return NULL; - } - ret = iscsit_get_tpg(tpg); - if (ret < 0) - return NULL; - - *tiqn_out = tpg->tpg_tiqn; - return tpg; -} - /* Start items for lio_target_portal_cit */ static ssize_t lio_target_np_show_sctp( diff --git a/drivers/target/iscsi/iscsi_target_core.h b/drivers/target/iscsi/iscsi_target_core.h index 1c70144cdaf1..8a908b28d8b2 100644 --- a/drivers/target/iscsi/iscsi_target_core.h +++ b/drivers/target/iscsi/iscsi_target_core.h @@ -224,7 +224,6 @@ enum iscsi_timer_flags_table { /* Used for struct iscsi_np->np_flags */ enum np_flags_table { NPF_IP_NETWORK = 0x00, - NPF_SCTP_STRUCT_FILE = 0x01 /* Bugfix */ }; /* Used for struct iscsi_np->np_thread_state */ @@ -481,6 +480,7 @@ struct iscsi_tmr_req { bool task_reassign:1; u32 ref_cmd_sn; u32 exp_data_sn; + struct iscsi_cmd *ref_cmd; struct iscsi_conn_recovery *conn_recovery; struct se_tmr_req *se_tmr_req; }; @@ -503,7 +503,6 @@ struct iscsi_conn { u16 local_port; int net_size; u32 auth_id; -#define CONNFLAG_SCTP_STRUCT_FILE 0x01 u32 conn_flags; /* Used for iscsi_tx_login_rsp() */ u32 login_itt; diff --git a/drivers/target/iscsi/iscsi_target_erl1.c b/drivers/target/iscsi/iscsi_target_erl1.c index ecdd46deedda..3df8a2cef86f 100644 --- a/drivers/target/iscsi/iscsi_target_erl1.c +++ b/drivers/target/iscsi/iscsi_target_erl1.c @@ -965,8 +965,8 @@ int iscsit_execute_cmd(struct iscsi_cmd *cmd, int ooo) if (cmd->immediate_data) { if (cmd->cmd_flags & ICF_GOT_LAST_DATAOUT) { spin_unlock_bh(&cmd->istate_lock); - return transport_generic_handle_data( - &cmd->se_cmd); + target_execute_cmd(&cmd->se_cmd); + return 0; } spin_unlock_bh(&cmd->istate_lock); diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index a3656c9903a1..0694d9b1bce6 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -518,7 +518,7 @@ int iscsi_login_post_auth_non_zero_tsih( * initiator and release the new connection. */ conn_ptr = iscsit_get_conn_from_cid_rcfr(sess, cid); - if ((conn_ptr)) { + if (conn_ptr) { pr_err("Connection exists with CID %hu for %s," " performing connection reinstatement.\n", conn_ptr->cid, sess->sess_ops->InitiatorName); @@ -539,7 +539,7 @@ int iscsi_login_post_auth_non_zero_tsih( if (sess->sess_ops->ErrorRecoveryLevel == 2) { cr = iscsit_get_inactive_connection_recovery_entry( sess, cid); - if ((cr)) { + if (cr) { pr_debug("Performing implicit logout" " for connection recovery on CID: %hu\n", conn->cid); @@ -795,22 +795,6 @@ int iscsi_target_setup_login_socket( } np->np_socket = sock; /* - * The SCTP stack needs struct socket->file. - */ - if ((np->np_network_transport == ISCSI_SCTP_TCP) || - (np->np_network_transport == ISCSI_SCTP_UDP)) { - if (!sock->file) { - sock->file = kzalloc(sizeof(struct file), GFP_KERNEL); - if (!sock->file) { - pr_err("Unable to allocate struct" - " file for SCTP\n"); - ret = -ENOMEM; - goto fail; - } - np->np_flags |= NPF_SCTP_STRUCT_FILE; - } - } - /* * Setup the np->np_sockaddr from the passed sockaddr setup * in iscsi_target_configfs.c code.. */ @@ -869,21 +853,15 @@ int iscsi_target_setup_login_socket( fail: np->np_socket = NULL; - if (sock) { - if (np->np_flags & NPF_SCTP_STRUCT_FILE) { - kfree(sock->file); - sock->file = NULL; - } - + if (sock) sock_release(sock); - } return ret; } static int __iscsi_target_login_thread(struct iscsi_np *np) { u8 buffer[ISCSI_HDR_LEN], iscsi_opcode, zero_tsih = 0; - int err, ret = 0, set_sctp_conn_flag, stop; + int err, ret = 0, stop; struct iscsi_conn *conn = NULL; struct iscsi_login *login; struct iscsi_portal_group *tpg = NULL; @@ -894,7 +872,6 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) struct sockaddr_in6 sock_in6; flush_signals(current); - set_sctp_conn_flag = 0; sock = np->np_socket; spin_lock_bh(&np->np_thread_lock); @@ -917,35 +894,12 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) spin_unlock_bh(&np->np_thread_lock); goto out; } - /* - * The SCTP stack needs struct socket->file. - */ - if ((np->np_network_transport == ISCSI_SCTP_TCP) || - (np->np_network_transport == ISCSI_SCTP_UDP)) { - if (!new_sock->file) { - new_sock->file = kzalloc( - sizeof(struct file), GFP_KERNEL); - if (!new_sock->file) { - pr_err("Unable to allocate struct" - " file for SCTP\n"); - sock_release(new_sock); - /* Get another socket */ - return 1; - } - set_sctp_conn_flag = 1; - } - } - iscsi_start_login_thread_timer(np); conn = kzalloc(sizeof(struct iscsi_conn), GFP_KERNEL); if (!conn) { pr_err("Could not allocate memory for" " new connection\n"); - if (set_sctp_conn_flag) { - kfree(new_sock->file); - new_sock->file = NULL; - } sock_release(new_sock); /* Get another socket */ return 1; @@ -955,9 +909,6 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) conn->conn_state = TARG_CONN_STATE_FREE; conn->sock = new_sock; - if (set_sctp_conn_flag) - conn->conn_flags |= CONNFLAG_SCTP_STRUCT_FILE; - pr_debug("Moving to TARG_CONN_STATE_XPT_UP.\n"); conn->conn_state = TARG_CONN_STATE_XPT_UP; @@ -1081,7 +1032,7 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) goto new_sess_out; zero_tsih = (pdu->tsih == 0x0000); - if ((zero_tsih)) { + if (zero_tsih) { /* * This is the leading connection of a new session. * We wait until after authentication to check for @@ -1205,13 +1156,8 @@ old_sess_out: iscsi_release_param_list(conn->param_list); conn->param_list = NULL; } - if (conn->sock) { - if (conn->conn_flags & CONNFLAG_SCTP_STRUCT_FILE) { - kfree(conn->sock->file); - conn->sock->file = NULL; - } + if (conn->sock) sock_release(conn->sock); - } kfree(conn); if (tpg) { diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c index ed5241e7f12a..0c4760fabfc0 100644 --- a/drivers/target/iscsi/iscsi_target_parameters.c +++ b/drivers/target/iscsi/iscsi_target_parameters.c @@ -681,7 +681,7 @@ int iscsi_update_param_value(struct iscsi_param *param, char *value) param->value = kzalloc(strlen(value) + 1, GFP_KERNEL); if (!param->value) { pr_err("Unable to allocate memory for value.\n"); - return -1; + return -ENOMEM; } memcpy(param->value, value, strlen(value)); diff --git a/drivers/target/iscsi/iscsi_target_tmr.c b/drivers/target/iscsi/iscsi_target_tmr.c index f4e640b51fd1..f62fe123d902 100644 --- a/drivers/target/iscsi/iscsi_target_tmr.c +++ b/drivers/target/iscsi/iscsi_target_tmr.c @@ -19,6 +19,7 @@ ******************************************************************************/ #include <asm/unaligned.h> +#include <scsi/scsi_device.h> #include <scsi/iscsi_proto.h> #include <target/target_core_base.h> #include <target/target_core_fabric.h> @@ -61,7 +62,7 @@ u8 iscsit_tmr_abort_task( } se_tmr->ref_task_tag = hdr->rtt; - se_tmr->ref_cmd = &ref_cmd->se_cmd; + tmr_req->ref_cmd = ref_cmd; tmr_req->ref_cmd_sn = hdr->refcmdsn; tmr_req->exp_data_sn = hdr->exp_datasn; @@ -121,7 +122,7 @@ u8 iscsit_tmr_task_reassign( struct iscsi_tmr_req *tmr_req = cmd->tmr_req; struct se_tmr_req *se_tmr = cmd->se_cmd.se_tmr_req; struct iscsi_tm *hdr = (struct iscsi_tm *) buf; - int ret; + int ret, ref_lun; pr_debug("Got TASK_REASSIGN TMR ITT: 0x%08x," " RefTaskTag: 0x%08x, ExpDataSN: 0x%08x, CID: %hu\n", @@ -155,9 +156,16 @@ u8 iscsit_tmr_task_reassign( return ISCSI_TMF_RSP_REJECTED; } + ref_lun = scsilun_to_int(&hdr->lun); + if (ref_lun != ref_cmd->se_cmd.orig_fe_lun) { + pr_err("Unable to perform connection recovery for" + " differing ref_lun: %d ref_cmd orig_fe_lun: %u\n", + ref_lun, ref_cmd->se_cmd.orig_fe_lun); + return ISCSI_TMF_RSP_REJECTED; + } + se_tmr->ref_task_tag = hdr->rtt; - se_tmr->ref_cmd = &ref_cmd->se_cmd; - se_tmr->ref_task_lun = get_unaligned_le64(&hdr->lun); + tmr_req->ref_cmd = ref_cmd; tmr_req->ref_cmd_sn = hdr->refcmdsn; tmr_req->exp_data_sn = hdr->exp_datasn; tmr_req->conn_recovery = cr; @@ -191,9 +199,7 @@ static int iscsit_task_reassign_complete_nop_out( struct iscsi_tmr_req *tmr_req, struct iscsi_conn *conn) { - struct se_tmr_req *se_tmr = tmr_req->se_tmr_req; - struct se_cmd *se_cmd = se_tmr->ref_cmd; - struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd); + struct iscsi_cmd *cmd = tmr_req->ref_cmd; struct iscsi_conn_recovery *cr; if (!cmd->cr) { @@ -251,7 +257,8 @@ static int iscsit_task_reassign_complete_write( pr_debug("WRITE ITT: 0x%08x: t_state: %d" " never sent to transport\n", cmd->init_task_tag, cmd->se_cmd.t_state); - return transport_generic_handle_data(se_cmd); + target_execute_cmd(se_cmd); + return 0; } cmd->i_state = ISTATE_SEND_STATUS; @@ -360,9 +367,7 @@ static int iscsit_task_reassign_complete_scsi_cmnd( struct iscsi_tmr_req *tmr_req, struct iscsi_conn *conn) { - struct se_tmr_req *se_tmr = tmr_req->se_tmr_req; - struct se_cmd *se_cmd = se_tmr->ref_cmd; - struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd); + struct iscsi_cmd *cmd = tmr_req->ref_cmd; struct iscsi_conn_recovery *cr; if (!cmd->cr) { @@ -385,7 +390,7 @@ static int iscsit_task_reassign_complete_scsi_cmnd( list_add_tail(&cmd->i_conn_node, &conn->conn_cmd_list); spin_unlock_bh(&conn->cmd_lock); - if (se_cmd->se_cmd_flags & SCF_SENT_CHECK_CONDITION) { + if (cmd->se_cmd.se_cmd_flags & SCF_SENT_CHECK_CONDITION) { cmd->i_state = ISTATE_SEND_STATUS; iscsit_add_cmd_to_response_queue(cmd, conn, cmd->i_state); return 0; @@ -411,17 +416,14 @@ static int iscsit_task_reassign_complete( struct iscsi_tmr_req *tmr_req, struct iscsi_conn *conn) { - struct se_tmr_req *se_tmr = tmr_req->se_tmr_req; - struct se_cmd *se_cmd; struct iscsi_cmd *cmd; int ret = 0; - if (!se_tmr->ref_cmd) { + if (!tmr_req->ref_cmd) { pr_err("TMR Request is missing a RefCmd struct iscsi_cmd.\n"); return -1; } - se_cmd = se_tmr->ref_cmd; - cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd); + cmd = tmr_req->ref_cmd; cmd->conn = conn; @@ -547,9 +549,7 @@ int iscsit_task_reassign_prepare_write( struct iscsi_tmr_req *tmr_req, struct iscsi_conn *conn) { - struct se_tmr_req *se_tmr = tmr_req->se_tmr_req; - struct se_cmd *se_cmd = se_tmr->ref_cmd; - struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd); + struct iscsi_cmd *cmd = tmr_req->ref_cmd; struct iscsi_pdu *pdu = NULL; struct iscsi_r2t *r2t = NULL, *r2t_tmp; int first_incomplete_r2t = 1, i = 0; @@ -782,14 +782,12 @@ int iscsit_check_task_reassign_expdatasn( struct iscsi_tmr_req *tmr_req, struct iscsi_conn *conn) { - struct se_tmr_req *se_tmr = tmr_req->se_tmr_req; - struct se_cmd *se_cmd = se_tmr->ref_cmd; - struct iscsi_cmd *ref_cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd); + struct iscsi_cmd *ref_cmd = tmr_req->ref_cmd; if (ref_cmd->iscsi_opcode != ISCSI_OP_SCSI_CMD) return 0; - if (se_cmd->se_cmd_flags & SCF_SENT_CHECK_CONDITION) + if (ref_cmd->se_cmd.se_cmd_flags & SCF_SENT_CHECK_CONDITION) return 0; if (ref_cmd->data_direction == DMA_NONE) diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c index 879d8d0fa3fe..a38a3f8ab0d9 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.c +++ b/drivers/target/iscsi/iscsi_target_tpg.c @@ -303,6 +303,7 @@ int iscsit_tpg_enable_portal_group(struct iscsi_portal_group *tpg) { struct iscsi_param *param; struct iscsi_tiqn *tiqn = tpg->tpg_tiqn; + int ret; spin_lock(&tpg->tpg_state_lock); if (tpg->tpg_state == TPG_STATE_ACTIVE) { @@ -319,19 +320,19 @@ int iscsit_tpg_enable_portal_group(struct iscsi_portal_group *tpg) param = iscsi_find_param_from_key(AUTHMETHOD, tpg->param_list); if (!param) { spin_unlock(&tpg->tpg_state_lock); - return -ENOMEM; + return -EINVAL; } if (ISCSI_TPG_ATTRIB(tpg)->authentication) { - if (!strcmp(param->value, NONE)) - if (iscsi_update_param_value(param, CHAP) < 0) { - spin_unlock(&tpg->tpg_state_lock); - return -ENOMEM; - } - if (iscsit_ta_authentication(tpg, 1) < 0) { - spin_unlock(&tpg->tpg_state_lock); - return -ENOMEM; + if (!strcmp(param->value, NONE)) { + ret = iscsi_update_param_value(param, CHAP); + if (ret) + goto err; } + + ret = iscsit_ta_authentication(tpg, 1); + if (ret < 0) + goto err; } tpg->tpg_state = TPG_STATE_ACTIVE; @@ -344,6 +345,10 @@ int iscsit_tpg_enable_portal_group(struct iscsi_portal_group *tpg) spin_unlock(&tiqn->tiqn_tpg_lock); return 0; + +err: + spin_unlock(&tpg->tpg_state_lock); + return ret; } int iscsit_tpg_disable_portal_group(struct iscsi_portal_group *tpg, int force) @@ -558,7 +563,7 @@ int iscsit_ta_authentication(struct iscsi_portal_group *tpg, u32 authentication) if ((authentication != 1) && (authentication != 0)) { pr_err("Illegal value for authentication parameter:" " %u, ignoring request.\n", authentication); - return -1; + return -EINVAL; } memset(buf1, 0, sizeof(buf1)); @@ -593,7 +598,7 @@ int iscsit_ta_authentication(struct iscsi_portal_group *tpg, u32 authentication) } else { snprintf(buf1, sizeof(buf1), "%s", param->value); none = strstr(buf1, NONE); - if ((none)) + if (none) goto out; strncat(buf1, ",", strlen(",")); strncat(buf1, NONE, strlen(NONE)); diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index 38dfac2b0a1c..5491c632a15e 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -211,12 +211,11 @@ static void tcm_loop_submission_work(struct work_struct *work) /* * Because some userspace code via scsi-generic do not memset their * associated read buffers, go ahead and do that here for type - * SCF_SCSI_CONTROL_SG_IO_CDB. Also note that this is currently - * guaranteed to be a single SGL for SCF_SCSI_CONTROL_SG_IO_CDB - * by target core in target_setup_cmd_from_cdb() -> - * transport_generic_cmd_sequencer(). + * non-data CDBs. Also note that this is currently guaranteed to be a + * single SGL for this case by target core in + * target_setup_cmd_from_cdb() -> transport_generic_cmd_sequencer(). */ - if (se_cmd->se_cmd_flags & SCF_SCSI_CONTROL_SG_IO_CDB && + if (!(se_cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) && se_cmd->data_direction == DMA_FROM_DEVICE) { struct scatterlist *sg = scsi_sglist(sc); unsigned char *buf = kmap(sg_page(sg)) + sg->offset; @@ -779,7 +778,7 @@ static int tcm_loop_write_pending(struct se_cmd *se_cmd) * We now tell TCM to add this WRITE CDB directly into the TCM storage * object execution queue. */ - transport_generic_process_write(se_cmd); + target_execute_cmd(se_cmd); return 0; } diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c index 7e6136e2ce81..39ddba584b30 100644 --- a/drivers/target/sbp/sbp_target.c +++ b/drivers/target/sbp/sbp_target.c @@ -1219,28 +1219,14 @@ static void sbp_handle_command(struct sbp_target_request *req) ret = sbp_fetch_command(req); if (ret) { pr_debug("sbp_handle_command: fetch command failed: %d\n", ret); - req->status.status |= cpu_to_be32( - STATUS_BLOCK_RESP(STATUS_RESP_TRANSPORT_FAILURE) | - STATUS_BLOCK_DEAD(0) | - STATUS_BLOCK_LEN(1) | - STATUS_BLOCK_SBP_STATUS(SBP_STATUS_UNSPECIFIED_ERROR)); - sbp_send_status(req); - sbp_free_request(req); - return; + goto err; } ret = sbp_fetch_page_table(req); if (ret) { pr_debug("sbp_handle_command: fetch page table failed: %d\n", ret); - req->status.status |= cpu_to_be32( - STATUS_BLOCK_RESP(STATUS_RESP_TRANSPORT_FAILURE) | - STATUS_BLOCK_DEAD(0) | - STATUS_BLOCK_LEN(1) | - STATUS_BLOCK_SBP_STATUS(SBP_STATUS_UNSPECIFIED_ERROR)); - sbp_send_status(req); - sbp_free_request(req); - return; + goto err; } unpacked_lun = req->login->lun->unpacked_lun; @@ -1249,9 +1235,21 @@ static void sbp_handle_command(struct sbp_target_request *req) pr_debug("sbp_handle_command ORB:0x%llx unpacked_lun:%d data_len:%d data_dir:%d\n", req->orb_pointer, unpacked_lun, data_length, data_dir); - target_submit_cmd(&req->se_cmd, sess->se_sess, req->cmd_buf, - req->sense_buf, unpacked_lun, data_length, - MSG_SIMPLE_TAG, data_dir, 0); + if (target_submit_cmd(&req->se_cmd, sess->se_sess, req->cmd_buf, + req->sense_buf, unpacked_lun, data_length, + MSG_SIMPLE_TAG, data_dir, 0)) + goto err; + + return; + +err: + req->status.status |= cpu_to_be32( + STATUS_BLOCK_RESP(STATUS_RESP_TRANSPORT_FAILURE) | + STATUS_BLOCK_DEAD(0) | + STATUS_BLOCK_LEN(1) | + STATUS_BLOCK_SBP_STATUS(SBP_STATUS_UNSPECIFIED_ERROR)); + sbp_send_status(req); + sbp_free_request(req); } /* @@ -1784,8 +1782,7 @@ static int sbp_write_pending(struct se_cmd *se_cmd) return ret; } - transport_generic_process_write(se_cmd); - + target_execute_cmd(se_cmd); return 0; } diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 5ad972856a8d..cf2c66f3c116 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -300,8 +300,8 @@ int core_free_device_list_for_node( lun = deve->se_lun; spin_unlock_irq(&nacl->device_list_lock); - core_update_device_list_for_node(lun, NULL, deve->mapped_lun, - TRANSPORT_LUNFLAGS_NO_ACCESS, nacl, tpg, 0); + core_disable_device_list_for_node(lun, NULL, deve->mapped_lun, + TRANSPORT_LUNFLAGS_NO_ACCESS, nacl, tpg); spin_lock_irq(&nacl->device_list_lock); } spin_unlock_irq(&nacl->device_list_lock); @@ -342,72 +342,46 @@ void core_update_device_list_access( spin_unlock_irq(&nacl->device_list_lock); } -/* core_update_device_list_for_node(): +/* core_enable_device_list_for_node(): * * */ -int core_update_device_list_for_node( +int core_enable_device_list_for_node( struct se_lun *lun, struct se_lun_acl *lun_acl, u32 mapped_lun, u32 lun_access, struct se_node_acl *nacl, - struct se_portal_group *tpg, - int enable) + struct se_portal_group *tpg) { struct se_port *port = lun->lun_sep; - struct se_dev_entry *deve = nacl->device_list[mapped_lun]; - int trans = 0; - /* - * If the MappedLUN entry is being disabled, the entry in - * port->sep_alua_list must be removed now before clearing the - * struct se_dev_entry pointers below as logic in - * core_alua_do_transition_tg_pt() depends on these being present. - */ - if (!enable) { - /* - * deve->se_lun_acl will be NULL for demo-mode created LUNs - * that have not been explicitly concerted to MappedLUNs -> - * struct se_lun_acl, but we remove deve->alua_port_list from - * port->sep_alua_list. This also means that active UAs and - * NodeACL context specific PR metadata for demo-mode - * MappedLUN *deve will be released below.. - */ - spin_lock_bh(&port->sep_alua_lock); - list_del(&deve->alua_port_list); - spin_unlock_bh(&port->sep_alua_lock); - } + struct se_dev_entry *deve; spin_lock_irq(&nacl->device_list_lock); - if (enable) { - /* - * Check if the call is handling demo mode -> explict LUN ACL - * transition. This transition must be for the same struct se_lun - * + mapped_lun that was setup in demo mode.. - */ - if (deve->lun_flags & TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) { - if (deve->se_lun_acl != NULL) { - pr_err("struct se_dev_entry->se_lun_acl" - " already set for demo mode -> explict" - " LUN ACL transition\n"); - spin_unlock_irq(&nacl->device_list_lock); - return -EINVAL; - } - if (deve->se_lun != lun) { - pr_err("struct se_dev_entry->se_lun does" - " match passed struct se_lun for demo mode" - " -> explict LUN ACL transition\n"); - spin_unlock_irq(&nacl->device_list_lock); - return -EINVAL; - } - deve->se_lun_acl = lun_acl; - trans = 1; - } else { - deve->se_lun = lun; - deve->se_lun_acl = lun_acl; - deve->mapped_lun = mapped_lun; - deve->lun_flags |= TRANSPORT_LUNFLAGS_INITIATOR_ACCESS; + + deve = nacl->device_list[mapped_lun]; + + /* + * Check if the call is handling demo mode -> explict LUN ACL + * transition. This transition must be for the same struct se_lun + * + mapped_lun that was setup in demo mode.. + */ + if (deve->lun_flags & TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) { + if (deve->se_lun_acl != NULL) { + pr_err("struct se_dev_entry->se_lun_acl" + " already set for demo mode -> explict" + " LUN ACL transition\n"); + spin_unlock_irq(&nacl->device_list_lock); + return -EINVAL; } + if (deve->se_lun != lun) { + pr_err("struct se_dev_entry->se_lun does" + " match passed struct se_lun for demo mode" + " -> explict LUN ACL transition\n"); + spin_unlock_irq(&nacl->device_list_lock); + return -EINVAL; + } + deve->se_lun_acl = lun_acl; if (lun_access & TRANSPORT_LUNFLAGS_READ_WRITE) { deve->lun_flags &= ~TRANSPORT_LUNFLAGS_READ_ONLY; @@ -417,27 +391,72 @@ int core_update_device_list_for_node( deve->lun_flags |= TRANSPORT_LUNFLAGS_READ_ONLY; } - if (trans) { - spin_unlock_irq(&nacl->device_list_lock); - return 0; - } - deve->creation_time = get_jiffies_64(); - deve->attach_count++; spin_unlock_irq(&nacl->device_list_lock); + return 0; + } - spin_lock_bh(&port->sep_alua_lock); - list_add_tail(&deve->alua_port_list, &port->sep_alua_list); - spin_unlock_bh(&port->sep_alua_lock); + deve->se_lun = lun; + deve->se_lun_acl = lun_acl; + deve->mapped_lun = mapped_lun; + deve->lun_flags |= TRANSPORT_LUNFLAGS_INITIATOR_ACCESS; - return 0; + if (lun_access & TRANSPORT_LUNFLAGS_READ_WRITE) { + deve->lun_flags &= ~TRANSPORT_LUNFLAGS_READ_ONLY; + deve->lun_flags |= TRANSPORT_LUNFLAGS_READ_WRITE; + } else { + deve->lun_flags &= ~TRANSPORT_LUNFLAGS_READ_WRITE; + deve->lun_flags |= TRANSPORT_LUNFLAGS_READ_ONLY; } + + deve->creation_time = get_jiffies_64(); + deve->attach_count++; + spin_unlock_irq(&nacl->device_list_lock); + + spin_lock_bh(&port->sep_alua_lock); + list_add_tail(&deve->alua_port_list, &port->sep_alua_list); + spin_unlock_bh(&port->sep_alua_lock); + + return 0; +} + +/* core_disable_device_list_for_node(): + * + * + */ +int core_disable_device_list_for_node( + struct se_lun *lun, + struct se_lun_acl *lun_acl, + u32 mapped_lun, + u32 lun_access, + struct se_node_acl *nacl, + struct se_portal_group *tpg) +{ + struct se_port *port = lun->lun_sep; + struct se_dev_entry *deve = nacl->device_list[mapped_lun]; + + /* + * If the MappedLUN entry is being disabled, the entry in + * port->sep_alua_list must be removed now before clearing the + * struct se_dev_entry pointers below as logic in + * core_alua_do_transition_tg_pt() depends on these being present. + * + * deve->se_lun_acl will be NULL for demo-mode created LUNs + * that have not been explicitly converted to MappedLUNs -> + * struct se_lun_acl, but we remove deve->alua_port_list from + * port->sep_alua_list. This also means that active UAs and + * NodeACL context specific PR metadata for demo-mode + * MappedLUN *deve will be released below.. + */ + spin_lock_bh(&port->sep_alua_lock); + list_del(&deve->alua_port_list); + spin_unlock_bh(&port->sep_alua_lock); /* * Wait for any in process SPEC_I_PT=1 or REGISTER_AND_MOVE * PR operation to complete. */ - spin_unlock_irq(&nacl->device_list_lock); while (atomic_read(&deve->pr_ref_count) != 0) cpu_relax(); + spin_lock_irq(&nacl->device_list_lock); /* * Disable struct se_dev_entry LUN ACL mapping @@ -475,9 +494,9 @@ void core_clear_lun_from_tpg(struct se_lun *lun, struct se_portal_group *tpg) continue; spin_unlock_irq(&nacl->device_list_lock); - core_update_device_list_for_node(lun, NULL, + core_disable_device_list_for_node(lun, NULL, deve->mapped_lun, TRANSPORT_LUNFLAGS_NO_ACCESS, - nacl, tpg, 0); + nacl, tpg); spin_lock_irq(&nacl->device_list_lock); } @@ -715,7 +734,7 @@ void se_release_device_for_hba(struct se_device *dev) se_dev_stop(dev); if (dev->dev_ptr) { - kthread_stop(dev->process_thread); + destroy_workqueue(dev->tmr_wq); if (dev->transport->free_device) dev->transport->free_device(dev->dev_ptr); } @@ -822,7 +841,7 @@ int se_dev_check_shutdown(struct se_device *dev) return ret; } -u32 se_dev_align_max_sectors(u32 max_sectors, u32 block_size) +static u32 se_dev_align_max_sectors(u32 max_sectors, u32 block_size) { u32 tmp, aligned_max_sectors; /* @@ -1273,7 +1292,6 @@ int se_dev_set_block_size(struct se_device *dev, u32 block_size) struct se_lun *core_dev_add_lun( struct se_portal_group *tpg, - struct se_hba *hba, struct se_device *dev, u32 lun) { @@ -1298,7 +1316,7 @@ struct se_lun *core_dev_add_lun( pr_debug("%s_TPG[%u]_LUN[%u] - Activated %s Logical Unit from" " CORE HBA: %u\n", tpg->se_tpg_tfo->get_fabric_name(), tpg->se_tpg_tfo->tpg_get_tag(tpg), lun_p->unpacked_lun, - tpg->se_tpg_tfo->get_fabric_name(), hba->hba_id); + tpg->se_tpg_tfo->get_fabric_name(), dev->se_hba->hba_id); /* * Update LUN maps for dynamically added initiators when * generate_node_acl is enabled. @@ -1470,8 +1488,8 @@ int core_dev_add_initiator_node_lun_acl( lacl->se_lun = lun; - if (core_update_device_list_for_node(lun, lacl, lacl->mapped_lun, - lun_access, nacl, tpg, 1) < 0) + if (core_enable_device_list_for_node(lun, lacl, lacl->mapped_lun, + lun_access, nacl, tpg) < 0) return -EINVAL; spin_lock(&lun->lun_acl_lock); @@ -1514,8 +1532,8 @@ int core_dev_del_initiator_node_lun_acl( smp_mb__after_atomic_dec(); spin_unlock(&lun->lun_acl_lock); - core_update_device_list_for_node(lun, NULL, lacl->mapped_lun, - TRANSPORT_LUNFLAGS_NO_ACCESS, nacl, tpg, 0); + core_disable_device_list_for_node(lun, NULL, lacl->mapped_lun, + TRANSPORT_LUNFLAGS_NO_ACCESS, nacl, tpg); lacl->se_lun = NULL; diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index 405cc98eaed6..ea479e54f5fd 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -764,8 +764,7 @@ static int target_fabric_port_link( goto out; } - lun_p = core_dev_add_lun(se_tpg, dev->se_hba, dev, - lun->unpacked_lun); + lun_p = core_dev_add_lun(se_tpg, dev, lun->unpacked_lun); if (IS_ERR(lun_p)) { pr_err("core_dev_add_lun() failed\n"); ret = PTR_ERR(lun_p); diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 9f99d0404908..9e2100551c78 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -331,7 +331,7 @@ static int fd_do_writev(struct se_cmd *cmd, struct scatterlist *sgl, return 1; } -static void fd_emulate_sync_cache(struct se_cmd *cmd) +static int fd_execute_sync_cache(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; struct fd_dev *fd_dev = dev->dev_ptr; @@ -365,7 +365,7 @@ static void fd_emulate_sync_cache(struct se_cmd *cmd) pr_err("FILEIO: vfs_fsync_range() failed: %d\n", ret); if (immed) - return; + return 0; if (ret) { cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; @@ -373,11 +373,15 @@ static void fd_emulate_sync_cache(struct se_cmd *cmd) } else { target_complete_cmd(cmd, SAM_STAT_GOOD); } + + return 0; } -static int fd_execute_cmd(struct se_cmd *cmd, struct scatterlist *sgl, - u32 sgl_nents, enum dma_data_direction data_direction) +static int fd_execute_rw(struct se_cmd *cmd) { + struct scatterlist *sgl = cmd->t_data_sg; + u32 sgl_nents = cmd->t_data_nents; + enum dma_data_direction data_direction = cmd->data_direction; struct se_device *dev = cmd->se_dev; int ret = 0; @@ -550,6 +554,16 @@ static sector_t fd_get_blocks(struct se_device *dev) return div_u64(dev_size, dev->se_sub_dev->se_dev_attrib.block_size); } +static struct spc_ops fd_spc_ops = { + .execute_rw = fd_execute_rw, + .execute_sync_cache = fd_execute_sync_cache, +}; + +static int fd_parse_cdb(struct se_cmd *cmd) +{ + return sbc_parse_cdb(cmd, &fd_spc_ops); +} + static struct se_subsystem_api fileio_template = { .name = "fileio", .owner = THIS_MODULE, @@ -561,8 +575,7 @@ static struct se_subsystem_api fileio_template = { .allocate_virtdevice = fd_allocate_virtdevice, .create_virtdevice = fd_create_virtdevice, .free_device = fd_free_device, - .execute_cmd = fd_execute_cmd, - .do_sync_cache = fd_emulate_sync_cache, + .parse_cdb = fd_parse_cdb, .check_configfs_dev_params = fd_check_configfs_dev_params, .set_configfs_dev_params = fd_set_configfs_dev_params, .show_configfs_dev_params = fd_show_configfs_dev_params, diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index fd47950727b4..76db75e836ed 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -40,6 +40,7 @@ #include <linux/module.h> #include <scsi/scsi.h> #include <scsi/scsi_host.h> +#include <asm/unaligned.h> #include <target/target_core_base.h> #include <target/target_core_backend.h> @@ -96,6 +97,7 @@ static struct se_device *iblock_create_virtdevice( struct request_queue *q; struct queue_limits *limits; u32 dev_flags = 0; + fmode_t mode; int ret = -EINVAL; if (!ib_dev) { @@ -117,8 +119,11 @@ static struct se_device *iblock_create_virtdevice( pr_debug( "IBLOCK: Claiming struct block_device: %s\n", ib_dev->ibd_udev_path); - bd = blkdev_get_by_path(ib_dev->ibd_udev_path, - FMODE_WRITE|FMODE_READ|FMODE_EXCL, ib_dev); + mode = FMODE_READ|FMODE_EXCL; + if (!ib_dev->ibd_readonly) + mode |= FMODE_WRITE; + + bd = blkdev_get_by_path(ib_dev->ibd_udev_path, mode, ib_dev); if (IS_ERR(bd)) { ret = PTR_ERR(bd); goto failed; @@ -292,7 +297,7 @@ static void iblock_end_io_flush(struct bio *bio, int err) * Implement SYCHRONIZE CACHE. Note that we can't handle lba ranges and must * always flush the whole cache. */ -static void iblock_emulate_sync_cache(struct se_cmd *cmd) +static int iblock_execute_sync_cache(struct se_cmd *cmd) { struct iblock_dev *ib_dev = cmd->se_dev->dev_ptr; int immed = (cmd->t_task_cdb[1] & 0x2); @@ -311,23 +316,98 @@ static void iblock_emulate_sync_cache(struct se_cmd *cmd) if (!immed) bio->bi_private = cmd; submit_bio(WRITE_FLUSH, bio); + return 0; } -static int iblock_do_discard(struct se_device *dev, sector_t lba, u32 range) +static int iblock_execute_unmap(struct se_cmd *cmd) { + struct se_device *dev = cmd->se_dev; struct iblock_dev *ibd = dev->dev_ptr; - struct block_device *bd = ibd->ibd_bd; - int barrier = 0; + unsigned char *buf, *ptr = NULL; + sector_t lba; + int size = cmd->data_length; + u32 range; + int ret = 0; + int dl, bd_dl; + + buf = transport_kmap_data_sg(cmd); + + dl = get_unaligned_be16(&buf[0]); + bd_dl = get_unaligned_be16(&buf[2]); + + size = min(size - 8, bd_dl); + if (size / 16 > dev->se_sub_dev->se_dev_attrib.max_unmap_block_desc_count) { + cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST; + ret = -EINVAL; + goto err; + } + + /* First UNMAP block descriptor starts at 8 byte offset */ + ptr = &buf[8]; + pr_debug("UNMAP: Sub: %s Using dl: %u bd_dl: %u size: %u" + " ptr: %p\n", dev->transport->name, dl, bd_dl, size, ptr); + + while (size >= 16) { + lba = get_unaligned_be64(&ptr[0]); + range = get_unaligned_be32(&ptr[8]); + pr_debug("UNMAP: Using lba: %llu and range: %u\n", + (unsigned long long)lba, range); + + if (range > dev->se_sub_dev->se_dev_attrib.max_unmap_lba_count) { + cmd->scsi_sense_reason = TCM_INVALID_PARAMETER_LIST; + ret = -EINVAL; + goto err; + } + + if (lba + range > dev->transport->get_blocks(dev) + 1) { + cmd->scsi_sense_reason = TCM_ADDRESS_OUT_OF_RANGE; + ret = -EINVAL; + goto err; + } - return blkdev_issue_discard(bd, lba, range, GFP_KERNEL, barrier); + ret = blkdev_issue_discard(ibd->ibd_bd, lba, range, + GFP_KERNEL, 0); + if (ret < 0) { + pr_err("blkdev_issue_discard() failed: %d\n", + ret); + goto err; + } + + ptr += 16; + size -= 16; + } + +err: + transport_kunmap_data_sg(cmd); + if (!ret) + target_complete_cmd(cmd, GOOD); + return ret; +} + +static int iblock_execute_write_same(struct se_cmd *cmd) +{ + struct iblock_dev *ibd = cmd->se_dev->dev_ptr; + int ret; + + ret = blkdev_issue_discard(ibd->ibd_bd, cmd->t_task_lba, + spc_get_write_same_sectors(cmd), GFP_KERNEL, + 0); + if (ret < 0) { + pr_debug("blkdev_issue_discard() failed for WRITE_SAME\n"); + return ret; + } + + target_complete_cmd(cmd, GOOD); + return 0; } enum { - Opt_udev_path, Opt_force, Opt_err + Opt_udev_path, Opt_readonly, Opt_force, Opt_err }; static match_table_t tokens = { {Opt_udev_path, "udev_path=%s"}, + {Opt_readonly, "readonly=%d"}, {Opt_force, "force=%d"}, {Opt_err, NULL} }; @@ -340,6 +420,7 @@ static ssize_t iblock_set_configfs_dev_params(struct se_hba *hba, char *orig, *ptr, *arg_p, *opts; substring_t args[MAX_OPT_ARGS]; int ret = 0, token; + unsigned long tmp_readonly; opts = kstrdup(page, GFP_KERNEL); if (!opts) @@ -372,6 +453,22 @@ static ssize_t iblock_set_configfs_dev_params(struct se_hba *hba, ib_dev->ibd_udev_path); ib_dev->ibd_flags |= IBDF_HAS_UDEV_PATH; break; + case Opt_readonly: + arg_p = match_strdup(&args[0]); + if (!arg_p) { + ret = -ENOMEM; + break; + } + ret = strict_strtoul(arg_p, 0, &tmp_readonly); + kfree(arg_p); + if (ret < 0) { + pr_err("strict_strtoul() failed for" + " readonly=\n"); + goto out; + } + ib_dev->ibd_readonly = tmp_readonly; + pr_debug("IBLOCK: readonly: %d\n", ib_dev->ibd_readonly); + break; case Opt_force: break; default: @@ -411,11 +508,10 @@ static ssize_t iblock_show_configfs_dev_params( if (bd) bl += sprintf(b + bl, "iBlock device: %s", bdevname(bd, buf)); - if (ibd->ibd_flags & IBDF_HAS_UDEV_PATH) { - bl += sprintf(b + bl, " UDEV PATH: %s\n", + if (ibd->ibd_flags & IBDF_HAS_UDEV_PATH) + bl += sprintf(b + bl, " UDEV PATH: %s", ibd->ibd_udev_path); - } else - bl += sprintf(b + bl, "\n"); + bl += sprintf(b + bl, " readonly: %d\n", ibd->ibd_readonly); bl += sprintf(b + bl, " "); if (bd) { @@ -493,9 +589,11 @@ static void iblock_submit_bios(struct bio_list *list, int rw) blk_finish_plug(&plug); } -static int iblock_execute_cmd(struct se_cmd *cmd, struct scatterlist *sgl, - u32 sgl_nents, enum dma_data_direction data_direction) +static int iblock_execute_rw(struct se_cmd *cmd) { + struct scatterlist *sgl = cmd->t_data_sg; + u32 sgl_nents = cmd->t_data_nents; + enum dma_data_direction data_direction = cmd->data_direction; struct se_device *dev = cmd->se_dev; struct iblock_req *ibr; struct bio *bio; @@ -642,6 +740,18 @@ static void iblock_bio_done(struct bio *bio, int err) iblock_complete_cmd(cmd); } +static struct spc_ops iblock_spc_ops = { + .execute_rw = iblock_execute_rw, + .execute_sync_cache = iblock_execute_sync_cache, + .execute_write_same = iblock_execute_write_same, + .execute_unmap = iblock_execute_unmap, +}; + +static int iblock_parse_cdb(struct se_cmd *cmd) +{ + return sbc_parse_cdb(cmd, &iblock_spc_ops); +} + static struct se_subsystem_api iblock_template = { .name = "iblock", .owner = THIS_MODULE, @@ -653,9 +763,7 @@ static struct se_subsystem_api iblock_template = { .allocate_virtdevice = iblock_allocate_virtdevice, .create_virtdevice = iblock_create_virtdevice, .free_device = iblock_free_device, - .execute_cmd = iblock_execute_cmd, - .do_discard = iblock_do_discard, - .do_sync_cache = iblock_emulate_sync_cache, + .parse_cdb = iblock_parse_cdb, .check_configfs_dev_params = iblock_check_configfs_dev_params, .set_configfs_dev_params = iblock_set_configfs_dev_params, .show_configfs_dev_params = iblock_show_configfs_dev_params, diff --git a/drivers/target/target_core_iblock.h b/drivers/target/target_core_iblock.h index 66cf7b9e205e..533627ae79ec 100644 --- a/drivers/target/target_core_iblock.h +++ b/drivers/target/target_core_iblock.h @@ -18,6 +18,7 @@ struct iblock_dev { u32 ibd_flags; struct bio_set *ibd_bio_set; struct block_device *ibd_bd; + bool ibd_readonly; } ____cacheline_aligned; #endif /* TARGET_CORE_IBLOCK_H */ diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h index 165e82429687..0fd428225d11 100644 --- a/drivers/target/target_core_internal.h +++ b/drivers/target/target_core_internal.h @@ -4,25 +4,16 @@ /* target_core_alua.c */ extern struct t10_alua_lu_gp *default_lu_gp; -/* target_core_cdb.c */ -int target_emulate_inquiry(struct se_cmd *cmd); -int target_emulate_readcapacity(struct se_cmd *cmd); -int target_emulate_readcapacity_16(struct se_cmd *cmd); -int target_emulate_modesense(struct se_cmd *cmd); -int target_emulate_request_sense(struct se_cmd *cmd); -int target_emulate_unmap(struct se_cmd *cmd); -int target_emulate_write_same(struct se_cmd *cmd); -int target_emulate_synchronize_cache(struct se_cmd *cmd); -int target_emulate_noop(struct se_cmd *cmd); - /* target_core_device.c */ struct se_dev_entry *core_get_se_deve_from_rtpi(struct se_node_acl *, u16); int core_free_device_list_for_node(struct se_node_acl *, struct se_portal_group *); void core_dec_lacl_count(struct se_node_acl *, struct se_cmd *); void core_update_device_list_access(u32, u32, struct se_node_acl *); -int core_update_device_list_for_node(struct se_lun *, struct se_lun_acl *, - u32, u32, struct se_node_acl *, struct se_portal_group *, int); +int core_enable_device_list_for_node(struct se_lun *, struct se_lun_acl *, + u32, u32, struct se_node_acl *, struct se_portal_group *); +int core_disable_device_list_for_node(struct se_lun *, struct se_lun_acl *, + u32, u32, struct se_node_acl *, struct se_portal_group *); void core_clear_lun_from_tpg(struct se_lun *, struct se_portal_group *); int core_dev_export(struct se_device *, struct se_portal_group *, struct se_lun *); @@ -56,8 +47,7 @@ int se_dev_set_max_sectors(struct se_device *, u32); int se_dev_set_fabric_max_sectors(struct se_device *, u32); int se_dev_set_optimal_sectors(struct se_device *, u32); int se_dev_set_block_size(struct se_device *, u32); -struct se_lun *core_dev_add_lun(struct se_portal_group *, struct se_hba *, - struct se_device *, u32); +struct se_lun *core_dev_add_lun(struct se_portal_group *, struct se_device *, u32); int core_dev_del_lun(struct se_portal_group *, u32); struct se_lun *core_get_lun_from_tpg(struct se_portal_group *, u32); struct se_lun_acl *core_dev_init_initiator_node_lun_acl(struct se_portal_group *, @@ -104,7 +94,6 @@ void release_se_kmem_caches(void); u32 scsi_get_new_index(scsi_index_t); void transport_subsystem_check_init(void); void transport_cmd_finish_abort(struct se_cmd *, int); -void __target_remove_from_execute_list(struct se_cmd *); unsigned char *transport_dump_cmd_direction(struct se_cmd *); void transport_dump_dev_state(struct se_device *, char *, int *); void transport_dump_dev_info(struct se_device *, struct se_lun *, @@ -116,6 +105,7 @@ int transport_dump_vpd_ident(struct t10_vpd *, unsigned char *, int); bool target_stop_cmd(struct se_cmd *cmd, unsigned long *flags); int transport_clear_lun_from_sessions(struct se_lun *); void transport_send_task_abort(struct se_cmd *); +int target_cmd_size_check(struct se_cmd *cmd, unsigned int size); /* target_core_stat.c */ void target_stat_setup_dev_default_groups(struct se_subsystem_dev *); diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 85564998500a..1e946502c378 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -507,7 +507,7 @@ static int core_scsi3_pr_seq_non_holder( * Check if write exclusive initiator ports *NOT* holding the * WRITE_EXCLUSIVE_* reservation. */ - if ((we) && !(registered_nexus)) { + if (we && !registered_nexus) { if (cmd->data_direction == DMA_TO_DEVICE) { /* * Conflict for write exclusive @@ -2031,7 +2031,7 @@ static int __core_scsi3_write_aptpl_to_file( if (IS_ERR(file) || !file || !file->f_dentry) { pr_err("filp_open(%s) for APTPL metadata" " failed\n", path); - return (PTR_ERR(file) < 0 ? PTR_ERR(file) : -ENOENT); + return IS_ERR(file) ? PTR_ERR(file) : -ENOENT; } iov[0].iov_base = &buf[0]; @@ -2486,7 +2486,7 @@ static int core_scsi3_pro_reserve( */ spin_lock(&dev->dev_reservation_lock); pr_res_holder = dev->dev_pr_res_holder; - if ((pr_res_holder)) { + if (pr_res_holder) { /* * From spc4r17 Section 5.7.9: Reserving: * @@ -3818,7 +3818,7 @@ int target_scsi3_emulate_pr_out(struct se_cmd *cmd) " SPC-2 reservation is held, returning" " RESERVATION_CONFLICT\n"); cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT; - ret = EINVAL; + ret = -EINVAL; goto out; } @@ -3828,7 +3828,8 @@ int target_scsi3_emulate_pr_out(struct se_cmd *cmd) */ if (!cmd->se_sess) { cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - return -EINVAL; + ret = -EINVAL; + goto out; } if (cmd->data_length < 24) { @@ -4029,7 +4030,7 @@ static int core_scsi3_pri_read_reservation(struct se_cmd *cmd) spin_lock(&se_dev->dev_reservation_lock); pr_reg = se_dev->dev_pr_res_holder; - if ((pr_reg)) { + if (pr_reg) { /* * Set the hardcoded Additional Length */ diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 4ce2cf642fce..6e32ff6f2fa0 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -35,8 +35,10 @@ #include <linux/spinlock.h> #include <linux/genhd.h> #include <linux/cdrom.h> -#include <linux/file.h> +#include <linux/ratelimit.h> #include <linux/module.h> +#include <asm/unaligned.h> + #include <scsi/scsi.h> #include <scsi/scsi_device.h> #include <scsi/scsi_cmnd.h> @@ -46,12 +48,14 @@ #include <target/target_core_base.h> #include <target/target_core_backend.h> +#include "target_core_alua.h" #include "target_core_pscsi.h" #define ISPRINT(a) ((a >= ' ') && (a <= '~')) static struct se_subsystem_api pscsi_template; +static int pscsi_execute_cmd(struct se_cmd *cmd); static void pscsi_req_done(struct request *, int); /* pscsi_attach_hba(): @@ -1019,9 +1023,79 @@ fail: return -ENOMEM; } -static int pscsi_execute_cmd(struct se_cmd *cmd, struct scatterlist *sgl, - u32 sgl_nents, enum dma_data_direction data_direction) +/* + * Clear a lun set in the cdb if the initiator talking to use spoke + * and old standards version, as we can't assume the underlying device + * won't choke up on it. + */ +static inline void pscsi_clear_cdb_lun(unsigned char *cdb) +{ + switch (cdb[0]) { + case READ_10: /* SBC - RDProtect */ + case READ_12: /* SBC - RDProtect */ + case READ_16: /* SBC - RDProtect */ + case SEND_DIAGNOSTIC: /* SPC - SELF-TEST Code */ + case VERIFY: /* SBC - VRProtect */ + case VERIFY_16: /* SBC - VRProtect */ + case WRITE_VERIFY: /* SBC - VRProtect */ + case WRITE_VERIFY_12: /* SBC - VRProtect */ + case MAINTENANCE_IN: /* SPC - Parameter Data Format for SA RTPG */ + break; + default: + cdb[1] &= 0x1f; /* clear logical unit number */ + break; + } +} + +static int pscsi_parse_cdb(struct se_cmd *cmd) +{ + unsigned char *cdb = cmd->t_task_cdb; + unsigned int dummy_size; + int ret; + + if (cmd->se_cmd_flags & SCF_BIDI) { + cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; + cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE; + return -EINVAL; + } + + pscsi_clear_cdb_lun(cdb); + + /* + * For REPORT LUNS we always need to emulate the response, for everything + * else the default for pSCSI is to pass the command to the underlying + * LLD / physical hardware. + */ + switch (cdb[0]) { + case REPORT_LUNS: + ret = spc_parse_cdb(cmd, &dummy_size); + if (ret) + return ret; + break; + case READ_6: + case READ_10: + case READ_12: + case READ_16: + case WRITE_6: + case WRITE_10: + case WRITE_12: + case WRITE_16: + case WRITE_VERIFY: + cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; + /* FALLTHROUGH*/ + default: + cmd->execute_cmd = pscsi_execute_cmd; + break; + } + + return 0; +} + +static int pscsi_execute_cmd(struct se_cmd *cmd) { + struct scatterlist *sgl = cmd->t_data_sg; + u32 sgl_nents = cmd->t_data_nents; + enum dma_data_direction data_direction = cmd->data_direction; struct pscsi_dev_virt *pdv = cmd->se_dev->dev_ptr; struct pscsi_plugin_task *pt; struct request *req; @@ -1042,7 +1116,7 @@ static int pscsi_execute_cmd(struct se_cmd *cmd, struct scatterlist *sgl, memcpy(pt->pscsi_cdb, cmd->t_task_cdb, scsi_command_size(cmd->t_task_cdb)); - if (cmd->se_cmd_flags & SCF_SCSI_NON_DATA_CDB) { + if (!sgl) { req = blk_get_request(pdv->pdv_sd->request_queue, (data_direction == DMA_TO_DEVICE), GFP_KERNEL); @@ -1188,7 +1262,7 @@ static struct se_subsystem_api pscsi_template = { .create_virtdevice = pscsi_create_virtdevice, .free_device = pscsi_free_device, .transport_complete = pscsi_transport_complete, - .execute_cmd = pscsi_execute_cmd, + .parse_cdb = pscsi_parse_cdb, .check_configfs_dev_params = pscsi_check_configfs_dev_params, .set_configfs_dev_params = pscsi_set_configfs_dev_params, .show_configfs_dev_params = pscsi_show_configfs_dev_params, diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c index d0ceb873c0e5..d00bbe33ff8b 100644 --- a/drivers/target/target_core_rd.c +++ b/drivers/target/target_core_rd.c @@ -284,9 +284,11 @@ static struct rd_dev_sg_table *rd_get_sg_table(struct rd_dev *rd_dev, u32 page) return NULL; } -static int rd_execute_cmd(struct se_cmd *cmd, struct scatterlist *sgl, - u32 sgl_nents, enum dma_data_direction data_direction) +static int rd_execute_rw(struct se_cmd *cmd) { + struct scatterlist *sgl = cmd->t_data_sg; + u32 sgl_nents = cmd->t_data_nents; + enum dma_data_direction data_direction = cmd->data_direction; struct se_device *se_dev = cmd->se_dev; struct rd_dev *dev = se_dev->dev_ptr; struct rd_dev_sg_table *table; @@ -460,6 +462,15 @@ static sector_t rd_get_blocks(struct se_device *dev) return blocks_long; } +static struct spc_ops rd_spc_ops = { + .execute_rw = rd_execute_rw, +}; + +static int rd_parse_cdb(struct se_cmd *cmd) +{ + return sbc_parse_cdb(cmd, &rd_spc_ops); +} + static struct se_subsystem_api rd_mcp_template = { .name = "rd_mcp", .transport_type = TRANSPORT_PLUGIN_VHBA_VDEV, @@ -468,7 +479,7 @@ static struct se_subsystem_api rd_mcp_template = { .allocate_virtdevice = rd_allocate_virtdevice, .create_virtdevice = rd_create_virtdevice, .free_device = rd_free_device, - .execute_cmd = rd_execute_cmd, + .parse_cdb = rd_parse_cdb, .check_configfs_dev_params = rd_check_configfs_dev_params, .set_configfs_dev_params = rd_set_configfs_dev_params, .show_configfs_dev_params = rd_show_configfs_dev_params, diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c new file mode 100644 index 000000000000..a9dd9469e3bd --- /dev/null +++ b/drivers/target/target_core_sbc.c @@ -0,0 +1,581 @@ +/* + * SCSI Block Commands (SBC) parsing and emulation. + * + * Copyright (c) 2002, 2003, 2004, 2005 PyX Technologies, Inc. + * Copyright (c) 2005, 2006, 2007 SBE, Inc. + * Copyright (c) 2007-2010 Rising Tide Systems + * Copyright (c) 2008-2010 Linux-iSCSI.org + * + * Nicholas A. Bellinger <nab@kernel.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/ratelimit.h> +#include <asm/unaligned.h> +#include <scsi/scsi.h> + +#include <target/target_core_base.h> +#include <target/target_core_backend.h> +#include <target/target_core_fabric.h> + +#include "target_core_internal.h" +#include "target_core_ua.h" + + +static int sbc_emulate_readcapacity(struct se_cmd *cmd) +{ + struct se_device *dev = cmd->se_dev; + unsigned char *buf; + unsigned long long blocks_long = dev->transport->get_blocks(dev); + u32 blocks; + + if (blocks_long >= 0x00000000ffffffff) + blocks = 0xffffffff; + else + blocks = (u32)blocks_long; + + buf = transport_kmap_data_sg(cmd); + + buf[0] = (blocks >> 24) & 0xff; + buf[1] = (blocks >> 16) & 0xff; + buf[2] = (blocks >> 8) & 0xff; + buf[3] = blocks & 0xff; + buf[4] = (dev->se_sub_dev->se_dev_attrib.block_size >> 24) & 0xff; + buf[5] = (dev->se_sub_dev->se_dev_attrib.block_size >> 16) & 0xff; + buf[6] = (dev->se_sub_dev->se_dev_attrib.block_size >> 8) & 0xff; + buf[7] = dev->se_sub_dev->se_dev_attrib.block_size & 0xff; + + transport_kunmap_data_sg(cmd); + + target_complete_cmd(cmd, GOOD); + return 0; +} + +static int sbc_emulate_readcapacity_16(struct se_cmd *cmd) +{ + struct se_device *dev = cmd->se_dev; + unsigned char *buf; + unsigned long long blocks = dev->transport->get_blocks(dev); + + buf = transport_kmap_data_sg(cmd); + + buf[0] = (blocks >> 56) & 0xff; + buf[1] = (blocks >> 48) & 0xff; + buf[2] = (blocks >> 40) & 0xff; + buf[3] = (blocks >> 32) & 0xff; + buf[4] = (blocks >> 24) & 0xff; + buf[5] = (blocks >> 16) & 0xff; + buf[6] = (blocks >> 8) & 0xff; + buf[7] = blocks & 0xff; + buf[8] = (dev->se_sub_dev->se_dev_attrib.block_size >> 24) & 0xff; + buf[9] = (dev->se_sub_dev->se_dev_attrib.block_size >> 16) & 0xff; + buf[10] = (dev->se_sub_dev->se_dev_attrib.block_size >> 8) & 0xff; + buf[11] = dev->se_sub_dev->se_dev_attrib.block_size & 0xff; + /* + * Set Thin Provisioning Enable bit following sbc3r22 in section + * READ CAPACITY (16) byte 14 if emulate_tpu or emulate_tpws is enabled. + */ + if (dev->se_sub_dev->se_dev_attrib.emulate_tpu || dev->se_sub_dev->se_dev_attrib.emulate_tpws) + buf[14] = 0x80; + + transport_kunmap_data_sg(cmd); + + target_complete_cmd(cmd, GOOD); + return 0; +} + +int spc_get_write_same_sectors(struct se_cmd *cmd) +{ + u32 num_blocks; + + if (cmd->t_task_cdb[0] == WRITE_SAME) + num_blocks = get_unaligned_be16(&cmd->t_task_cdb[7]); + else if (cmd->t_task_cdb[0] == WRITE_SAME_16) + num_blocks = get_unaligned_be32(&cmd->t_task_cdb[10]); + else /* WRITE_SAME_32 via VARIABLE_LENGTH_CMD */ + num_blocks = get_unaligned_be32(&cmd->t_task_cdb[28]); + + /* + * Use the explicit range when non zero is supplied, otherwise calculate + * the remaining range based on ->get_blocks() - starting LBA. + */ + if (num_blocks) + return num_blocks; + + return cmd->se_dev->transport->get_blocks(cmd->se_dev) - + cmd->t_task_lba + 1; +} +EXPORT_SYMBOL(spc_get_write_same_sectors); + +static int sbc_emulate_verify(struct se_cmd *cmd) +{ + target_complete_cmd(cmd, GOOD); + return 0; +} + +static inline u32 sbc_get_size(struct se_cmd *cmd, u32 sectors) +{ + return cmd->se_dev->se_sub_dev->se_dev_attrib.block_size * sectors; +} + +static int sbc_check_valid_sectors(struct se_cmd *cmd) +{ + struct se_device *dev = cmd->se_dev; + unsigned long long end_lba; + u32 sectors; + + sectors = cmd->data_length / dev->se_sub_dev->se_dev_attrib.block_size; + end_lba = dev->transport->get_blocks(dev) + 1; + + if (cmd->t_task_lba + sectors > end_lba) { + pr_err("target: lba %llu, sectors %u exceeds end lba %llu\n", + cmd->t_task_lba, sectors, end_lba); + return -EINVAL; + } + + return 0; +} + +static inline u32 transport_get_sectors_6(unsigned char *cdb) +{ + /* + * Use 8-bit sector value. SBC-3 says: + * + * A TRANSFER LENGTH field set to zero specifies that 256 + * logical blocks shall be written. Any other value + * specifies the number of logical blocks that shall be + * written. + */ + return cdb[4] ? : 256; +} + +static inline u32 transport_get_sectors_10(unsigned char *cdb) +{ + return (u32)(cdb[7] << 8) + cdb[8]; +} + +static inline u32 transport_get_sectors_12(unsigned char *cdb) +{ + return (u32)(cdb[6] << 24) + (cdb[7] << 16) + (cdb[8] << 8) + cdb[9]; +} + +static inline u32 transport_get_sectors_16(unsigned char *cdb) +{ + return (u32)(cdb[10] << 24) + (cdb[11] << 16) + + (cdb[12] << 8) + cdb[13]; +} + +/* + * Used for VARIABLE_LENGTH_CDB WRITE_32 and READ_32 variants + */ +static inline u32 transport_get_sectors_32(unsigned char *cdb) +{ + return (u32)(cdb[28] << 24) + (cdb[29] << 16) + + (cdb[30] << 8) + cdb[31]; + +} + +static inline u32 transport_lba_21(unsigned char *cdb) +{ + return ((cdb[1] & 0x1f) << 16) | (cdb[2] << 8) | cdb[3]; +} + +static inline u32 transport_lba_32(unsigned char *cdb) +{ + return (cdb[2] << 24) | (cdb[3] << 16) | (cdb[4] << 8) | cdb[5]; +} + +static inline unsigned long long transport_lba_64(unsigned char *cdb) +{ + unsigned int __v1, __v2; + + __v1 = (cdb[2] << 24) | (cdb[3] << 16) | (cdb[4] << 8) | cdb[5]; + __v2 = (cdb[6] << 24) | (cdb[7] << 16) | (cdb[8] << 8) | cdb[9]; + + return ((unsigned long long)__v2) | (unsigned long long)__v1 << 32; +} + +/* + * For VARIABLE_LENGTH_CDB w/ 32 byte extended CDBs + */ +static inline unsigned long long transport_lba_64_ext(unsigned char *cdb) +{ + unsigned int __v1, __v2; + + __v1 = (cdb[12] << 24) | (cdb[13] << 16) | (cdb[14] << 8) | cdb[15]; + __v2 = (cdb[16] << 24) | (cdb[17] << 16) | (cdb[18] << 8) | cdb[19]; + + return ((unsigned long long)__v2) | (unsigned long long)__v1 << 32; +} + +static int sbc_write_same_supported(struct se_device *dev, + unsigned char *flags) +{ + if ((flags[0] & 0x04) || (flags[0] & 0x02)) { + pr_err("WRITE_SAME PBDATA and LBDATA" + " bits not supported for Block Discard" + " Emulation\n"); + return -ENOSYS; + } + + /* + * Currently for the emulated case we only accept + * tpws with the UNMAP=1 bit set. + */ + if (!(flags[0] & 0x08)) { + pr_err("WRITE_SAME w/o UNMAP bit not" + " supported for Block Discard Emulation\n"); + return -ENOSYS; + } + + return 0; +} + +static void xdreadwrite_callback(struct se_cmd *cmd) +{ + unsigned char *buf, *addr; + struct scatterlist *sg; + unsigned int offset; + int i; + int count; + /* + * From sbc3r22.pdf section 5.48 XDWRITEREAD (10) command + * + * 1) read the specified logical block(s); + * 2) transfer logical blocks from the data-out buffer; + * 3) XOR the logical blocks transferred from the data-out buffer with + * the logical blocks read, storing the resulting XOR data in a buffer; + * 4) if the DISABLE WRITE bit is set to zero, then write the logical + * blocks transferred from the data-out buffer; and + * 5) transfer the resulting XOR data to the data-in buffer. + */ + buf = kmalloc(cmd->data_length, GFP_KERNEL); + if (!buf) { + pr_err("Unable to allocate xor_callback buf\n"); + return; + } + /* + * Copy the scatterlist WRITE buffer located at cmd->t_data_sg + * into the locally allocated *buf + */ + sg_copy_to_buffer(cmd->t_data_sg, + cmd->t_data_nents, + buf, + cmd->data_length); + + /* + * Now perform the XOR against the BIDI read memory located at + * cmd->t_mem_bidi_list + */ + + offset = 0; + for_each_sg(cmd->t_bidi_data_sg, sg, cmd->t_bidi_data_nents, count) { + addr = kmap_atomic(sg_page(sg)); + if (!addr) + goto out; + + for (i = 0; i < sg->length; i++) + *(addr + sg->offset + i) ^= *(buf + offset + i); + + offset += sg->length; + kunmap_atomic(addr); + } + +out: + kfree(buf); +} + +int sbc_parse_cdb(struct se_cmd *cmd, struct spc_ops *ops) +{ + struct se_subsystem_dev *su_dev = cmd->se_dev->se_sub_dev; + struct se_device *dev = cmd->se_dev; + unsigned char *cdb = cmd->t_task_cdb; + unsigned int size; + u32 sectors = 0; + int ret; + + switch (cdb[0]) { + case READ_6: + sectors = transport_get_sectors_6(cdb); + cmd->t_task_lba = transport_lba_21(cdb); + cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; + cmd->execute_cmd = ops->execute_rw; + break; + case READ_10: + sectors = transport_get_sectors_10(cdb); + cmd->t_task_lba = transport_lba_32(cdb); + cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; + cmd->execute_cmd = ops->execute_rw; + break; + case READ_12: + sectors = transport_get_sectors_12(cdb); + cmd->t_task_lba = transport_lba_32(cdb); + cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; + cmd->execute_cmd = ops->execute_rw; + break; + case READ_16: + sectors = transport_get_sectors_16(cdb); + cmd->t_task_lba = transport_lba_64(cdb); + cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; + cmd->execute_cmd = ops->execute_rw; + break; + case WRITE_6: + sectors = transport_get_sectors_6(cdb); + cmd->t_task_lba = transport_lba_21(cdb); + cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; + cmd->execute_cmd = ops->execute_rw; + break; + case WRITE_10: + case WRITE_VERIFY: + sectors = transport_get_sectors_10(cdb); + cmd->t_task_lba = transport_lba_32(cdb); + if (cdb[1] & 0x8) + cmd->se_cmd_flags |= SCF_FUA; + cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; + cmd->execute_cmd = ops->execute_rw; + break; + case WRITE_12: + sectors = transport_get_sectors_12(cdb); + cmd->t_task_lba = transport_lba_32(cdb); + if (cdb[1] & 0x8) + cmd->se_cmd_flags |= SCF_FUA; + cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; + cmd->execute_cmd = ops->execute_rw; + break; + case WRITE_16: + sectors = transport_get_sectors_16(cdb); + cmd->t_task_lba = transport_lba_64(cdb); + if (cdb[1] & 0x8) + cmd->se_cmd_flags |= SCF_FUA; + cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; + cmd->execute_cmd = ops->execute_rw; + break; + case XDWRITEREAD_10: + if ((cmd->data_direction != DMA_TO_DEVICE) || + !(cmd->se_cmd_flags & SCF_BIDI)) + goto out_invalid_cdb_field; + sectors = transport_get_sectors_10(cdb); + + cmd->t_task_lba = transport_lba_32(cdb); + cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; + + /* + * Setup BIDI XOR callback to be run after I/O completion. + */ + cmd->execute_cmd = ops->execute_rw; + cmd->transport_complete_callback = &xdreadwrite_callback; + if (cdb[1] & 0x8) + cmd->se_cmd_flags |= SCF_FUA; + break; + case VARIABLE_LENGTH_CMD: + { + u16 service_action = get_unaligned_be16(&cdb[8]); + switch (service_action) { + case XDWRITEREAD_32: + sectors = transport_get_sectors_32(cdb); + + /* + * Use WRITE_32 and READ_32 opcodes for the emulated + * XDWRITE_READ_32 logic. + */ + cmd->t_task_lba = transport_lba_64_ext(cdb); + cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB; + + /* + * Setup BIDI XOR callback to be run during after I/O + * completion. + */ + cmd->execute_cmd = ops->execute_rw; + cmd->transport_complete_callback = &xdreadwrite_callback; + if (cdb[1] & 0x8) + cmd->se_cmd_flags |= SCF_FUA; + break; + case WRITE_SAME_32: + if (!ops->execute_write_same) + goto out_unsupported_cdb; + + sectors = transport_get_sectors_32(cdb); + if (!sectors) { + pr_err("WSNZ=1, WRITE_SAME w/sectors=0 not" + " supported\n"); + goto out_invalid_cdb_field; + } + + size = sbc_get_size(cmd, 1); + cmd->t_task_lba = get_unaligned_be64(&cdb[12]); + + if (sbc_write_same_supported(dev, &cdb[10]) < 0) + goto out_unsupported_cdb; + cmd->execute_cmd = ops->execute_write_same; + break; + default: + pr_err("VARIABLE_LENGTH_CMD service action" + " 0x%04x not supported\n", service_action); + goto out_unsupported_cdb; + } + break; + } + case READ_CAPACITY: + size = READ_CAP_LEN; + cmd->execute_cmd = sbc_emulate_readcapacity; + break; + case SERVICE_ACTION_IN: + switch (cmd->t_task_cdb[1] & 0x1f) { + case SAI_READ_CAPACITY_16: + cmd->execute_cmd = sbc_emulate_readcapacity_16; + break; + default: + pr_err("Unsupported SA: 0x%02x\n", + cmd->t_task_cdb[1] & 0x1f); + goto out_invalid_cdb_field; + } + size = (cdb[10] << 24) | (cdb[11] << 16) | + (cdb[12] << 8) | cdb[13]; + break; + case SYNCHRONIZE_CACHE: + case SYNCHRONIZE_CACHE_16: + if (!ops->execute_sync_cache) + goto out_unsupported_cdb; + + /* + * Extract LBA and range to be flushed for emulated SYNCHRONIZE_CACHE + */ + if (cdb[0] == SYNCHRONIZE_CACHE) { + sectors = transport_get_sectors_10(cdb); + cmd->t_task_lba = transport_lba_32(cdb); + } else { + sectors = transport_get_sectors_16(cdb); + cmd->t_task_lba = transport_lba_64(cdb); + } + + size = sbc_get_size(cmd, sectors); + + /* + * Check to ensure that LBA + Range does not exceed past end of + * device for IBLOCK and FILEIO ->do_sync_cache() backend calls + */ + if (cmd->t_task_lba || sectors) { + if (sbc_check_valid_sectors(cmd) < 0) + goto out_invalid_cdb_field; + } + cmd->execute_cmd = ops->execute_sync_cache; + break; + case UNMAP: + if (!ops->execute_unmap) + goto out_unsupported_cdb; + + size = get_unaligned_be16(&cdb[7]); + cmd->execute_cmd = ops->execute_unmap; + break; + case WRITE_SAME_16: + if (!ops->execute_write_same) + goto out_unsupported_cdb; + + sectors = transport_get_sectors_16(cdb); + if (!sectors) { + pr_err("WSNZ=1, WRITE_SAME w/sectors=0 not supported\n"); + goto out_invalid_cdb_field; + } + + size = sbc_get_size(cmd, 1); + cmd->t_task_lba = get_unaligned_be64(&cdb[2]); + + if (sbc_write_same_supported(dev, &cdb[1]) < 0) + goto out_unsupported_cdb; + cmd->execute_cmd = ops->execute_write_same; + break; + case WRITE_SAME: + if (!ops->execute_write_same) + goto out_unsupported_cdb; + + sectors = transport_get_sectors_10(cdb); + if (!sectors) { + pr_err("WSNZ=1, WRITE_SAME w/sectors=0 not supported\n"); + goto out_invalid_cdb_field; + } + + size = sbc_get_size(cmd, 1); + cmd->t_task_lba = get_unaligned_be32(&cdb[2]); + + /* + * Follow sbcr26 with WRITE_SAME (10) and check for the existence + * of byte 1 bit 3 UNMAP instead of original reserved field + */ + if (sbc_write_same_supported(dev, &cdb[1]) < 0) + goto out_unsupported_cdb; + cmd->execute_cmd = ops->execute_write_same; + break; + case VERIFY: + size = 0; + cmd->execute_cmd = sbc_emulate_verify; + break; + default: + ret = spc_parse_cdb(cmd, &size); + if (ret) + return ret; + } + + /* reject any command that we don't have a handler for */ + if (!(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) && !cmd->execute_cmd) + goto out_unsupported_cdb; + + if (cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) { + unsigned long long end_lba; + + if (sectors > su_dev->se_dev_attrib.fabric_max_sectors) { + printk_ratelimited(KERN_ERR "SCSI OP %02xh with too" + " big sectors %u exceeds fabric_max_sectors:" + " %u\n", cdb[0], sectors, + su_dev->se_dev_attrib.fabric_max_sectors); + goto out_invalid_cdb_field; + } + if (sectors > su_dev->se_dev_attrib.hw_max_sectors) { + printk_ratelimited(KERN_ERR "SCSI OP %02xh with too" + " big sectors %u exceeds backend hw_max_sectors:" + " %u\n", cdb[0], sectors, + su_dev->se_dev_attrib.hw_max_sectors); + goto out_invalid_cdb_field; + } + + end_lba = dev->transport->get_blocks(dev) + 1; + if (cmd->t_task_lba + sectors > end_lba) { + pr_err("cmd exceeds last lba %llu " + "(lba %llu, sectors %u)\n", + end_lba, cmd->t_task_lba, sectors); + goto out_invalid_cdb_field; + } + + size = sbc_get_size(cmd, sectors); + } + + ret = target_cmd_size_check(cmd, size); + if (ret < 0) + return ret; + + return 0; + +out_unsupported_cdb: + cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; + cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE; + return -EINVAL; +out_invalid_cdb_field: + cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; + cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD; + return -EINVAL; +} +EXPORT_SYMBOL(sbc_parse_cdb); diff --git a/drivers/target/target_core_cdb.c b/drivers/target/target_core_spc.c index 9888693a18fe..4c861de538c9 100644 --- a/drivers/target/target_core_cdb.c +++ b/drivers/target/target_core_spc.c @@ -1,5 +1,5 @@ /* - * CDB emulation for non-READ/WRITE commands. + * SCSI Primary Commands (SPC) parsing and emulation. * * Copyright (c) 2002, 2003, 2004, 2005 PyX Technologies, Inc. * Copyright (c) 2005, 2006, 2007 SBE, Inc. @@ -26,17 +26,21 @@ #include <linux/kernel.h> #include <linux/module.h> #include <asm/unaligned.h> + #include <scsi/scsi.h> +#include <scsi/scsi_tcq.h> #include <target/target_core_base.h> #include <target/target_core_backend.h> #include <target/target_core_fabric.h> #include "target_core_internal.h" +#include "target_core_alua.h" +#include "target_core_pr.h" #include "target_core_ua.h" -static void -target_fill_alua_data(struct se_port *port, unsigned char *buf) + +static void spc_fill_alua_data(struct se_port *port, unsigned char *buf) { struct t10_alua_tg_pt_gp *tg_pt_gp; struct t10_alua_tg_pt_gp_member *tg_pt_gp_mem; @@ -65,8 +69,7 @@ target_fill_alua_data(struct se_port *port, unsigned char *buf) spin_unlock(&tg_pt_gp_mem->tg_pt_gp_mem_lock); } -static int -target_emulate_inquiry_std(struct se_cmd *cmd, char *buf) +static int spc_emulate_inquiry_std(struct se_cmd *cmd, char *buf) { struct se_lun *lun = cmd->se_lun; struct se_device *dev = cmd->se_dev; @@ -93,7 +96,7 @@ target_emulate_inquiry_std(struct se_cmd *cmd, char *buf) * Enable SCCS and TPGS fields for Emulated ALUA */ if (dev->se_sub_dev->t10_alua.alua_type == SPC3_ALUA_EMULATED) - target_fill_alua_data(lun->lun_sep, buf); + spc_fill_alua_data(lun->lun_sep, buf); buf[7] = 0x2; /* CmdQue=1 */ @@ -106,8 +109,7 @@ target_emulate_inquiry_std(struct se_cmd *cmd, char *buf) } /* unit serial number */ -static int -target_emulate_evpd_80(struct se_cmd *cmd, unsigned char *buf) +static int spc_emulate_evpd_80(struct se_cmd *cmd, unsigned char *buf) { struct se_device *dev = cmd->se_dev; u16 len = 0; @@ -127,8 +129,8 @@ target_emulate_evpd_80(struct se_cmd *cmd, unsigned char *buf) return 0; } -static void -target_parse_naa_6h_vendor_specific(struct se_device *dev, unsigned char *buf) +static void spc_parse_naa_6h_vendor_specific(struct se_device *dev, + unsigned char *buf) { unsigned char *p = &dev->se_sub_dev->t10_wwn.unit_serial[0]; int cnt; @@ -162,8 +164,7 @@ target_parse_naa_6h_vendor_specific(struct se_device *dev, unsigned char *buf) * Device identification VPD, for a complete list of * DESIGNATOR TYPEs see spc4r17 Table 459. */ -static int -target_emulate_evpd_83(struct se_cmd *cmd, unsigned char *buf) +static int spc_emulate_evpd_83(struct se_cmd *cmd, unsigned char *buf) { struct se_device *dev = cmd->se_dev; struct se_lun *lun = cmd->se_lun; @@ -220,7 +221,7 @@ target_emulate_evpd_83(struct se_cmd *cmd, unsigned char *buf) * VENDOR_SPECIFIC_IDENTIFIER and * VENDOR_SPECIFIC_IDENTIFIER_EXTENTION */ - target_parse_naa_6h_vendor_specific(dev, &buf[off]); + spc_parse_naa_6h_vendor_specific(dev, &buf[off]); len = 20; off = (len + 4); @@ -414,8 +415,7 @@ check_scsi_name: } /* Extended INQUIRY Data VPD Page */ -static int -target_emulate_evpd_86(struct se_cmd *cmd, unsigned char *buf) +static int spc_emulate_evpd_86(struct se_cmd *cmd, unsigned char *buf) { buf[3] = 0x3c; /* Set HEADSUP, ORDSUP, SIMPSUP */ @@ -428,15 +428,14 @@ target_emulate_evpd_86(struct se_cmd *cmd, unsigned char *buf) } /* Block Limits VPD page */ -static int -target_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf) +static int spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf) { struct se_device *dev = cmd->se_dev; u32 max_sectors; int have_tp = 0; /* - * Following sbc3r22 section 6.5.3 Block Limits VPD page, when + * Following spc3r22 section 6.5.3 Block Limits VPD page, when * emulate_tpu=1 or emulate_tpws=1 we will be expect a * different page length for Thin Provisioning. */ @@ -500,8 +499,7 @@ target_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf) } /* Block Device Characteristics VPD page */ -static int -target_emulate_evpd_b1(struct se_cmd *cmd, unsigned char *buf) +static int spc_emulate_evpd_b1(struct se_cmd *cmd, unsigned char *buf) { struct se_device *dev = cmd->se_dev; @@ -513,13 +511,12 @@ target_emulate_evpd_b1(struct se_cmd *cmd, unsigned char *buf) } /* Thin Provisioning VPD */ -static int -target_emulate_evpd_b2(struct se_cmd *cmd, unsigned char *buf) +static int spc_emulate_evpd_b2(struct se_cmd *cmd, unsigned char *buf) { struct se_device *dev = cmd->se_dev; /* - * From sbc3r22 section 6.5.4 Thin Provisioning VPD page: + * From spc3r22 section 6.5.4 Thin Provisioning VPD page: * * The PAGE LENGTH field is defined in SPC-4. If the DP bit is set to * zero, then the page length shall be set to 0004h. If the DP bit @@ -564,25 +561,23 @@ target_emulate_evpd_b2(struct se_cmd *cmd, unsigned char *buf) return 0; } -static int -target_emulate_evpd_00(struct se_cmd *cmd, unsigned char *buf); +static int spc_emulate_evpd_00(struct se_cmd *cmd, unsigned char *buf); static struct { uint8_t page; int (*emulate)(struct se_cmd *, unsigned char *); } evpd_handlers[] = { - { .page = 0x00, .emulate = target_emulate_evpd_00 }, - { .page = 0x80, .emulate = target_emulate_evpd_80 }, - { .page = 0x83, .emulate = target_emulate_evpd_83 }, - { .page = 0x86, .emulate = target_emulate_evpd_86 }, - { .page = 0xb0, .emulate = target_emulate_evpd_b0 }, - { .page = 0xb1, .emulate = target_emulate_evpd_b1 }, - { .page = 0xb2, .emulate = target_emulate_evpd_b2 }, + { .page = 0x00, .emulate = spc_emulate_evpd_00 }, + { .page = 0x80, .emulate = spc_emulate_evpd_80 }, + { .page = 0x83, .emulate = spc_emulate_evpd_83 }, + { .page = 0x86, .emulate = spc_emulate_evpd_86 }, + { .page = 0xb0, .emulate = spc_emulate_evpd_b0 }, + { .page = 0xb1, .emulate = spc_emulate_evpd_b1 }, + { .page = 0xb2, .emulate = spc_emulate_evpd_b2 }, }; /* supported vital product data pages */ -static int -target_emulate_evpd_00(struct se_cmd *cmd, unsigned char *buf) +static int spc_emulate_evpd_00(struct se_cmd *cmd, unsigned char *buf) { int p; @@ -601,7 +596,7 @@ target_emulate_evpd_00(struct se_cmd *cmd, unsigned char *buf) return 0; } -int target_emulate_inquiry(struct se_cmd *cmd) +static int spc_emulate_inquiry(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; struct se_portal_group *tpg = cmd->se_lun->lun_sep->sep_tpg; @@ -643,7 +638,7 @@ int target_emulate_inquiry(struct se_cmd *cmd) goto out; } - ret = target_emulate_inquiry_std(cmd, buf); + ret = spc_emulate_inquiry_std(cmd, buf); goto out; } @@ -671,70 +666,7 @@ out: return ret; } -int target_emulate_readcapacity(struct se_cmd *cmd) -{ - struct se_device *dev = cmd->se_dev; - unsigned char *buf; - unsigned long long blocks_long = dev->transport->get_blocks(dev); - u32 blocks; - - if (blocks_long >= 0x00000000ffffffff) - blocks = 0xffffffff; - else - blocks = (u32)blocks_long; - - buf = transport_kmap_data_sg(cmd); - - buf[0] = (blocks >> 24) & 0xff; - buf[1] = (blocks >> 16) & 0xff; - buf[2] = (blocks >> 8) & 0xff; - buf[3] = blocks & 0xff; - buf[4] = (dev->se_sub_dev->se_dev_attrib.block_size >> 24) & 0xff; - buf[5] = (dev->se_sub_dev->se_dev_attrib.block_size >> 16) & 0xff; - buf[6] = (dev->se_sub_dev->se_dev_attrib.block_size >> 8) & 0xff; - buf[7] = dev->se_sub_dev->se_dev_attrib.block_size & 0xff; - - transport_kunmap_data_sg(cmd); - - target_complete_cmd(cmd, GOOD); - return 0; -} - -int target_emulate_readcapacity_16(struct se_cmd *cmd) -{ - struct se_device *dev = cmd->se_dev; - unsigned char *buf; - unsigned long long blocks = dev->transport->get_blocks(dev); - - buf = transport_kmap_data_sg(cmd); - - buf[0] = (blocks >> 56) & 0xff; - buf[1] = (blocks >> 48) & 0xff; - buf[2] = (blocks >> 40) & 0xff; - buf[3] = (blocks >> 32) & 0xff; - buf[4] = (blocks >> 24) & 0xff; - buf[5] = (blocks >> 16) & 0xff; - buf[6] = (blocks >> 8) & 0xff; - buf[7] = blocks & 0xff; - buf[8] = (dev->se_sub_dev->se_dev_attrib.block_size >> 24) & 0xff; - buf[9] = (dev->se_sub_dev->se_dev_attrib.block_size >> 16) & 0xff; - buf[10] = (dev->se_sub_dev->se_dev_attrib.block_size >> 8) & 0xff; - buf[11] = dev->se_sub_dev->se_dev_attrib.block_size & 0xff; - /* - * Set Thin Provisioning Enable bit following sbc3r22 in section - * READ CAPACITY (16) byte 14 if emulate_tpu or emulate_tpws is enabled. - */ - if (dev->se_sub_dev->se_dev_attrib.emulate_tpu || dev->se_sub_dev->se_dev_attrib.emulate_tpws) - buf[14] = 0x80; - - transport_kunmap_data_sg(cmd); - - target_complete_cmd(cmd, GOOD); - return 0; -} - -static int -target_modesense_rwrecovery(unsigned char *p) +static int spc_modesense_rwrecovery(unsigned char *p) { p[0] = 0x01; p[1] = 0x0a; @@ -742,8 +674,7 @@ target_modesense_rwrecovery(unsigned char *p) return 12; } -static int -target_modesense_control(struct se_device *dev, unsigned char *p) +static int spc_modesense_control(struct se_device *dev, unsigned char *p) { p[0] = 0x0a; p[1] = 0x0a; @@ -828,8 +759,7 @@ target_modesense_control(struct se_device *dev, unsigned char *p) return 12; } -static int -target_modesense_caching(struct se_device *dev, unsigned char *p) +static int spc_modesense_caching(struct se_device *dev, unsigned char *p) { p[0] = 0x08; p[1] = 0x12; @@ -840,8 +770,7 @@ target_modesense_caching(struct se_device *dev, unsigned char *p) return 20; } -static void -target_modesense_write_protect(unsigned char *buf, int type) +static void spc_modesense_write_protect(unsigned char *buf, int type) { /* * I believe that the WP bit (bit 7) in the mode header is the same for @@ -856,8 +785,7 @@ target_modesense_write_protect(unsigned char *buf, int type) } } -static void -target_modesense_dpofua(unsigned char *buf, int type) +static void spc_modesense_dpofua(unsigned char *buf, int type) { switch (type) { case TYPE_DISK: @@ -868,7 +796,7 @@ target_modesense_dpofua(unsigned char *buf, int type) } } -int target_emulate_modesense(struct se_cmd *cmd) +static int spc_emulate_modesense(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; char *cdb = cmd->t_task_cdb; @@ -883,18 +811,18 @@ int target_emulate_modesense(struct se_cmd *cmd) switch (cdb[2] & 0x3f) { case 0x01: - length = target_modesense_rwrecovery(&buf[offset]); + length = spc_modesense_rwrecovery(&buf[offset]); break; case 0x08: - length = target_modesense_caching(dev, &buf[offset]); + length = spc_modesense_caching(dev, &buf[offset]); break; case 0x0a: - length = target_modesense_control(dev, &buf[offset]); + length = spc_modesense_control(dev, &buf[offset]); break; case 0x3f: - length = target_modesense_rwrecovery(&buf[offset]); - length += target_modesense_caching(dev, &buf[offset+length]); - length += target_modesense_control(dev, &buf[offset+length]); + length = spc_modesense_rwrecovery(&buf[offset]); + length += spc_modesense_caching(dev, &buf[offset+length]); + length += spc_modesense_control(dev, &buf[offset+length]); break; default: pr_err("MODE SENSE: unimplemented page/subpage: 0x%02x/0x%02x\n", @@ -912,11 +840,11 @@ int target_emulate_modesense(struct se_cmd *cmd) if ((cmd->se_lun->lun_access & TRANSPORT_LUNFLAGS_READ_ONLY) || (cmd->se_deve && (cmd->se_deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY))) - target_modesense_write_protect(&buf[3], type); + spc_modesense_write_protect(&buf[3], type); if ((dev->se_sub_dev->se_dev_attrib.emulate_write_cache > 0) && (dev->se_sub_dev->se_dev_attrib.emulate_fua_write > 0)) - target_modesense_dpofua(&buf[3], type); + spc_modesense_dpofua(&buf[3], type); if ((offset + 2) > cmd->data_length) offset = cmd->data_length; @@ -928,11 +856,11 @@ int target_emulate_modesense(struct se_cmd *cmd) if ((cmd->se_lun->lun_access & TRANSPORT_LUNFLAGS_READ_ONLY) || (cmd->se_deve && (cmd->se_deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY))) - target_modesense_write_protect(&buf[2], type); + spc_modesense_write_protect(&buf[2], type); if ((dev->se_sub_dev->se_dev_attrib.emulate_write_cache > 0) && (dev->se_sub_dev->se_dev_attrib.emulate_fua_write > 0)) - target_modesense_dpofua(&buf[2], type); + spc_modesense_dpofua(&buf[2], type); if ((offset + 1) > cmd->data_length) offset = cmd->data_length; @@ -946,7 +874,7 @@ int target_emulate_modesense(struct se_cmd *cmd) return 0; } -int target_emulate_request_sense(struct se_cmd *cmd) +static int spc_emulate_request_sense(struct se_cmd *cmd) { unsigned char *cdb = cmd->t_task_cdb; unsigned char *buf; @@ -1005,126 +933,172 @@ end: return 0; } -/* - * Used for TCM/IBLOCK and TCM/FILEIO for block/blk-lib.c level discard support. - * Note this is not used for TCM/pSCSI passthrough - */ -int target_emulate_unmap(struct se_cmd *cmd) +static int spc_emulate_testunitready(struct se_cmd *cmd) { - struct se_device *dev = cmd->se_dev; - unsigned char *buf, *ptr = NULL; - unsigned char *cdb = &cmd->t_task_cdb[0]; - sector_t lba; - unsigned int size = cmd->data_length, range; - int ret = 0, offset; - unsigned short dl, bd_dl; - - if (!dev->transport->do_discard) { - pr_err("UNMAP emulation not supported for: %s\n", - dev->transport->name); - cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE; - return -ENOSYS; - } - - /* First UNMAP block descriptor starts at 8 byte offset */ - offset = 8; - size -= 8; - dl = get_unaligned_be16(&cdb[0]); - bd_dl = get_unaligned_be16(&cdb[2]); - - buf = transport_kmap_data_sg(cmd); - - ptr = &buf[offset]; - pr_debug("UNMAP: Sub: %s Using dl: %hu bd_dl: %hu size: %hu" - " ptr: %p\n", dev->transport->name, dl, bd_dl, size, ptr); - - while (size) { - lba = get_unaligned_be64(&ptr[0]); - range = get_unaligned_be32(&ptr[8]); - pr_debug("UNMAP: Using lba: %llu and range: %u\n", - (unsigned long long)lba, range); - - ret = dev->transport->do_discard(dev, lba, range); - if (ret < 0) { - pr_err("blkdev_issue_discard() failed: %d\n", - ret); - goto err; - } - - ptr += 16; - size -= 16; - } - -err: - transport_kunmap_data_sg(cmd); - if (!ret) - target_complete_cmd(cmd, GOOD); - return ret; + target_complete_cmd(cmd, GOOD); + return 0; } -/* - * Used for TCM/IBLOCK and TCM/FILEIO for block/blk-lib.c level discard support. - * Note this is not used for TCM/pSCSI passthrough - */ -int target_emulate_write_same(struct se_cmd *cmd) +int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size) { struct se_device *dev = cmd->se_dev; - sector_t range; - sector_t lba = cmd->t_task_lba; - u32 num_blocks; - int ret; - - if (!dev->transport->do_discard) { - pr_err("WRITE_SAME emulation not supported" - " for: %s\n", dev->transport->name); - cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE; - return -ENOSYS; - } - - if (cmd->t_task_cdb[0] == WRITE_SAME) - num_blocks = get_unaligned_be16(&cmd->t_task_cdb[7]); - else if (cmd->t_task_cdb[0] == WRITE_SAME_16) - num_blocks = get_unaligned_be32(&cmd->t_task_cdb[10]); - else /* WRITE_SAME_32 via VARIABLE_LENGTH_CMD */ - num_blocks = get_unaligned_be32(&cmd->t_task_cdb[28]); - - /* - * Use the explicit range when non zero is supplied, otherwise calculate - * the remaining range based on ->get_blocks() - starting LBA. - */ - if (num_blocks != 0) - range = num_blocks; - else - range = (dev->transport->get_blocks(dev) - lba); - - pr_debug("WRITE_SAME UNMAP: LBA: %llu Range: %llu\n", - (unsigned long long)lba, (unsigned long long)range); + struct se_subsystem_dev *su_dev = dev->se_sub_dev; + unsigned char *cdb = cmd->t_task_cdb; - ret = dev->transport->do_discard(dev, lba, range); - if (ret < 0) { - pr_debug("blkdev_issue_discard() failed for WRITE_SAME\n"); - return ret; - } + switch (cdb[0]) { + case MODE_SELECT: + *size = cdb[4]; + break; + case MODE_SELECT_10: + *size = (cdb[7] << 8) + cdb[8]; + break; + case MODE_SENSE: + *size = cdb[4]; + cmd->execute_cmd = spc_emulate_modesense; + break; + case MODE_SENSE_10: + *size = (cdb[7] << 8) + cdb[8]; + cmd->execute_cmd = spc_emulate_modesense; + break; + case LOG_SELECT: + case LOG_SENSE: + *size = (cdb[7] << 8) + cdb[8]; + break; + case PERSISTENT_RESERVE_IN: + if (su_dev->t10_pr.res_type == SPC3_PERSISTENT_RESERVATIONS) + cmd->execute_cmd = target_scsi3_emulate_pr_in; + *size = (cdb[7] << 8) + cdb[8]; + break; + case PERSISTENT_RESERVE_OUT: + if (su_dev->t10_pr.res_type == SPC3_PERSISTENT_RESERVATIONS) + cmd->execute_cmd = target_scsi3_emulate_pr_out; + *size = (cdb[7] << 8) + cdb[8]; + break; + case RELEASE: + case RELEASE_10: + if (cdb[0] == RELEASE_10) + *size = (cdb[7] << 8) | cdb[8]; + else + *size = cmd->data_length; + + if (su_dev->t10_pr.res_type != SPC_PASSTHROUGH) + cmd->execute_cmd = target_scsi2_reservation_release; + break; + case RESERVE: + case RESERVE_10: + /* + * The SPC-2 RESERVE does not contain a size in the SCSI CDB. + * Assume the passthrough or $FABRIC_MOD will tell us about it. + */ + if (cdb[0] == RESERVE_10) + *size = (cdb[7] << 8) | cdb[8]; + else + *size = cmd->data_length; - target_complete_cmd(cmd, GOOD); - return 0; -} + /* + * Setup the legacy emulated handler for SPC-2 and + * >= SPC-3 compatible reservation handling (CRH=1) + * Otherwise, we assume the underlying SCSI logic is + * is running in SPC_PASSTHROUGH, and wants reservations + * emulation disabled. + */ + if (su_dev->t10_pr.res_type != SPC_PASSTHROUGH) + cmd->execute_cmd = target_scsi2_reservation_reserve; + break; + case REQUEST_SENSE: + *size = cdb[4]; + cmd->execute_cmd = spc_emulate_request_sense; + break; + case INQUIRY: + *size = (cdb[3] << 8) + cdb[4]; -int target_emulate_synchronize_cache(struct se_cmd *cmd) -{ - if (!cmd->se_dev->transport->do_sync_cache) { - pr_err("SYNCHRONIZE_CACHE emulation not supported" - " for: %s\n", cmd->se_dev->transport->name); + /* + * Do implict HEAD_OF_QUEUE processing for INQUIRY. + * See spc4r17 section 5.3 + */ + if (cmd->se_dev->dev_task_attr_type == SAM_TASK_ATTR_EMULATED) + cmd->sam_task_attr = MSG_HEAD_TAG; + cmd->execute_cmd = spc_emulate_inquiry; + break; + case SECURITY_PROTOCOL_IN: + case SECURITY_PROTOCOL_OUT: + *size = (cdb[6] << 24) | (cdb[7] << 16) | (cdb[8] << 8) | cdb[9]; + break; + case EXTENDED_COPY: + case READ_ATTRIBUTE: + case RECEIVE_COPY_RESULTS: + case WRITE_ATTRIBUTE: + *size = (cdb[10] << 24) | (cdb[11] << 16) | + (cdb[12] << 8) | cdb[13]; + break; + case RECEIVE_DIAGNOSTIC: + case SEND_DIAGNOSTIC: + *size = (cdb[3] << 8) | cdb[4]; + break; + case WRITE_BUFFER: + *size = (cdb[6] << 16) + (cdb[7] << 8) + cdb[8]; + break; + case REPORT_LUNS: + cmd->execute_cmd = target_report_luns; + *size = (cdb[6] << 24) | (cdb[7] << 16) | (cdb[8] << 8) | cdb[9]; + /* + * Do implict HEAD_OF_QUEUE processing for REPORT_LUNS + * See spc4r17 section 5.3 + */ + if (cmd->se_dev->dev_task_attr_type == SAM_TASK_ATTR_EMULATED) + cmd->sam_task_attr = MSG_HEAD_TAG; + break; + case TEST_UNIT_READY: + cmd->execute_cmd = spc_emulate_testunitready; + *size = 0; + break; + case MAINTENANCE_IN: + if (dev->transport->get_device_type(dev) != TYPE_ROM) { + /* + * MAINTENANCE_IN from SCC-2 + * Check for emulated MI_REPORT_TARGET_PGS + */ + if ((cdb[1] & 0x1f) == MI_REPORT_TARGET_PGS && + su_dev->t10_alua.alua_type == SPC3_ALUA_EMULATED) { + cmd->execute_cmd = + target_emulate_report_target_port_groups; + } + *size = get_unaligned_be32(&cdb[6]); + } else { + /* + * GPCMD_SEND_KEY from multi media commands + */ + *size = get_unaligned_be16(&cdb[8]); + } + break; + case MAINTENANCE_OUT: + if (dev->transport->get_device_type(dev) != TYPE_ROM) { + /* + * MAINTENANCE_OUT from SCC-2 + * Check for emulated MO_SET_TARGET_PGS. + */ + if (cdb[1] == MO_SET_TARGET_PGS && + su_dev->t10_alua.alua_type == SPC3_ALUA_EMULATED) { + cmd->execute_cmd = + target_emulate_set_target_port_groups; + } + *size = get_unaligned_be32(&cdb[6]); + } else { + /* + * GPCMD_SEND_KEY from multi media commands + */ + *size = get_unaligned_be16(&cdb[8]); + } + break; + default: + pr_warn("TARGET_CORE[%s]: Unsupported SCSI Opcode" + " 0x%02x, sending CHECK_CONDITION.\n", + cmd->se_tfo->get_fabric_name(), cdb[0]); + cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE; - return -ENOSYS; + return -EINVAL; } - cmd->se_dev->transport->do_sync_cache(cmd); - return 0; -} - -int target_emulate_noop(struct se_cmd *cmd) -{ - target_complete_cmd(cmd, GOOD); return 0; } +EXPORT_SYMBOL(spc_parse_cdb); diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index 84caf1bed9a3..1c59a3c23b2c 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -295,9 +295,6 @@ static void core_tmr_drain_state_list( list_move_tail(&cmd->state_list, &drain_task_list); cmd->state_active = false; - - if (!list_empty(&cmd->execute_list)) - __target_remove_from_execute_list(cmd); } spin_unlock_irqrestore(&dev->execute_task_lock, flags); @@ -354,57 +351,6 @@ static void core_tmr_drain_state_list( } } -static void core_tmr_drain_cmd_list( - struct se_device *dev, - struct se_cmd *prout_cmd, - struct se_node_acl *tmr_nacl, - int tas, - struct list_head *preempt_and_abort_list) -{ - LIST_HEAD(drain_cmd_list); - struct se_queue_obj *qobj = &dev->dev_queue_obj; - struct se_cmd *cmd, *tcmd; - unsigned long flags; - - /* - * Release all commands remaining in the per-device command queue. - * - * This follows the same logic as above for the state list. - */ - spin_lock_irqsave(&qobj->cmd_queue_lock, flags); - list_for_each_entry_safe(cmd, tcmd, &qobj->qobj_list, se_queue_node) { - /* - * For PREEMPT_AND_ABORT usage, only process commands - * with a matching reservation key. - */ - if (target_check_cdb_and_preempt(preempt_and_abort_list, cmd)) - continue; - /* - * Not aborting PROUT PREEMPT_AND_ABORT CDB.. - */ - if (prout_cmd == cmd) - continue; - - cmd->transport_state &= ~CMD_T_QUEUED; - atomic_dec(&qobj->queue_cnt); - list_move_tail(&cmd->se_queue_node, &drain_cmd_list); - } - spin_unlock_irqrestore(&qobj->cmd_queue_lock, flags); - - while (!list_empty(&drain_cmd_list)) { - cmd = list_entry(drain_cmd_list.next, struct se_cmd, se_queue_node); - list_del_init(&cmd->se_queue_node); - - pr_debug("LUN_RESET: %s from Device Queue: cmd: %p t_state:" - " %d t_fe_count: %d\n", (preempt_and_abort_list) ? - "Preempt" : "", cmd, cmd->t_state, - atomic_read(&cmd->t_fe_count)); - - core_tmr_handle_tas_abort(tmr_nacl, cmd, tas, - atomic_read(&cmd->t_fe_count)); - } -} - int core_tmr_lun_reset( struct se_device *dev, struct se_tmr_req *tmr, @@ -447,8 +393,7 @@ int core_tmr_lun_reset( core_tmr_drain_tmr_list(dev, tmr, preempt_and_abort_list); core_tmr_drain_state_list(dev, prout_cmd, tmr_nacl, tas, preempt_and_abort_list); - core_tmr_drain_cmd_list(dev, prout_cmd, tmr_nacl, tas, - preempt_and_abort_list); + /* * Clear any legacy SPC-2 reservation when called during * LOGICAL UNIT RESET diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index 8bd58e284185..b8628a5014b9 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -77,8 +77,8 @@ static void core_clear_initiator_node_from_tpg( lun = deve->se_lun; spin_unlock_irq(&nacl->device_list_lock); - core_update_device_list_for_node(lun, NULL, deve->mapped_lun, - TRANSPORT_LUNFLAGS_NO_ACCESS, nacl, tpg, 0); + core_disable_device_list_for_node(lun, NULL, deve->mapped_lun, + TRANSPORT_LUNFLAGS_NO_ACCESS, nacl, tpg); spin_lock_irq(&nacl->device_list_lock); } @@ -172,8 +172,8 @@ void core_tpg_add_node_to_devs( (lun_access == TRANSPORT_LUNFLAGS_READ_WRITE) ? "READ-WRITE" : "READ-ONLY"); - core_update_device_list_for_node(lun, NULL, lun->unpacked_lun, - lun_access, acl, tpg, 1); + core_enable_device_list_for_node(lun, NULL, lun->unpacked_lun, + lun_access, acl, tpg); spin_lock(&tpg->tpg_lun_lock); } spin_unlock(&tpg->tpg_lun_lock); @@ -306,10 +306,8 @@ struct se_node_acl *core_tpg_check_initiator_node_acl( * TPG LUNs if the fabric is not explictly asking for * tpg_check_demo_mode_login_only() == 1. */ - if ((tpg->se_tpg_tfo->tpg_check_demo_mode_login_only != NULL) && - (tpg->se_tpg_tfo->tpg_check_demo_mode_login_only(tpg) == 1)) - do { ; } while (0); - else + if ((tpg->se_tpg_tfo->tpg_check_demo_mode_login_only == NULL) || + (tpg->se_tpg_tfo->tpg_check_demo_mode_login_only(tpg) != 1)) core_tpg_add_node_to_devs(acl, tpg); spin_lock_irq(&tpg->acl_node_lock); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 634d0f31a28c..0eaae23d12b5 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -66,15 +66,12 @@ struct kmem_cache *t10_alua_lu_gp_mem_cache; struct kmem_cache *t10_alua_tg_pt_gp_cache; struct kmem_cache *t10_alua_tg_pt_gp_mem_cache; -static int transport_generic_write_pending(struct se_cmd *); -static int transport_processing_thread(void *param); -static int __transport_execute_tasks(struct se_device *dev, struct se_cmd *); static void transport_complete_task_attr(struct se_cmd *cmd); static void transport_handle_queue_full(struct se_cmd *cmd, struct se_device *dev); static int transport_generic_get_mem(struct se_cmd *cmd); +static int target_get_sess_cmd(struct se_session *, struct se_cmd *, bool); static void transport_put_cmd(struct se_cmd *cmd); -static void transport_remove_cmd_from_queue(struct se_cmd *cmd); static int transport_set_sense_codes(struct se_cmd *cmd, u8 asc, u8 ascq); static void target_complete_ok_work(struct work_struct *work); @@ -195,14 +192,6 @@ u32 scsi_get_new_index(scsi_index_t type) return new_index; } -static void transport_init_queue_obj(struct se_queue_obj *qobj) -{ - atomic_set(&qobj->queue_cnt, 0); - INIT_LIST_HEAD(&qobj->qobj_list); - init_waitqueue_head(&qobj->thread_wq); - spin_lock_init(&qobj->cmd_queue_lock); -} - void transport_subsystem_check_init(void) { int ret; @@ -243,7 +232,6 @@ struct se_session *transport_init_session(void) INIT_LIST_HEAD(&se_sess->sess_list); INIT_LIST_HEAD(&se_sess->sess_acl_list); INIT_LIST_HEAD(&se_sess->sess_cmd_list); - INIT_LIST_HEAD(&se_sess->sess_wait_list); spin_lock_init(&se_sess->sess_cmd_lock); kref_init(&se_sess->sess_kref); @@ -468,18 +456,7 @@ static void target_remove_from_state_list(struct se_cmd *cmd) spin_unlock_irqrestore(&dev->execute_task_lock, flags); } -/* transport_cmd_check_stop(): - * - * 'transport_off = 1' determines if CMD_T_ACTIVE should be cleared. - * 'transport_off = 2' determines if task_dev_state should be removed. - * - * A non-zero u8 t_state sets cmd->t_state. - * Returns 1 when command is stopped, else 0. - */ -static int transport_cmd_check_stop( - struct se_cmd *cmd, - int transport_off, - u8 t_state) +static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists) { unsigned long flags; @@ -493,13 +470,23 @@ static int transport_cmd_check_stop( __func__, __LINE__, cmd->se_tfo->get_task_tag(cmd)); cmd->transport_state &= ~CMD_T_ACTIVE; - if (transport_off == 2) + if (remove_from_lists) target_remove_from_state_list(cmd); spin_unlock_irqrestore(&cmd->t_state_lock, flags); complete(&cmd->transport_lun_stop_comp); return 1; } + + if (remove_from_lists) { + target_remove_from_state_list(cmd); + + /* + * Clear struct se_cmd->se_lun before the handoff to FE. + */ + cmd->se_lun = NULL; + } + /* * Determine if frontend context caller is requesting the stopping of * this command for frontend exceptions. @@ -509,58 +496,36 @@ static int transport_cmd_check_stop( __func__, __LINE__, cmd->se_tfo->get_task_tag(cmd)); - if (transport_off == 2) - target_remove_from_state_list(cmd); - - /* - * Clear struct se_cmd->se_lun before the transport_off == 2 handoff - * to FE. - */ - if (transport_off == 2) - cmd->se_lun = NULL; spin_unlock_irqrestore(&cmd->t_state_lock, flags); complete(&cmd->t_transport_stop_comp); return 1; } - if (transport_off) { - cmd->transport_state &= ~CMD_T_ACTIVE; - if (transport_off == 2) { - target_remove_from_state_list(cmd); - /* - * Clear struct se_cmd->se_lun before the transport_off == 2 - * handoff to fabric module. - */ - cmd->se_lun = NULL; - /* - * Some fabric modules like tcm_loop can release - * their internally allocated I/O reference now and - * struct se_cmd now. - * - * Fabric modules are expected to return '1' here if the - * se_cmd being passed is released at this point, - * or zero if not being released. - */ - if (cmd->se_tfo->check_stop_free != NULL) { - spin_unlock_irqrestore( - &cmd->t_state_lock, flags); - - return cmd->se_tfo->check_stop_free(cmd); - } + + cmd->transport_state &= ~CMD_T_ACTIVE; + if (remove_from_lists) { + /* + * Some fabric modules like tcm_loop can release + * their internally allocated I/O reference now and + * struct se_cmd now. + * + * Fabric modules are expected to return '1' here if the + * se_cmd being passed is released at this point, + * or zero if not being released. + */ + if (cmd->se_tfo->check_stop_free != NULL) { + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + return cmd->se_tfo->check_stop_free(cmd); } - spin_unlock_irqrestore(&cmd->t_state_lock, flags); + } - return 0; - } else if (t_state) - cmd->t_state = t_state; spin_unlock_irqrestore(&cmd->t_state_lock, flags); - return 0; } static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd) { - return transport_cmd_check_stop(cmd, 2, 0); + return transport_cmd_check_stop(cmd, true); } static void transport_lun_remove_cmd(struct se_cmd *cmd) @@ -591,79 +556,8 @@ void transport_cmd_finish_abort(struct se_cmd *cmd, int remove) if (transport_cmd_check_stop_to_fabric(cmd)) return; - if (remove) { - transport_remove_cmd_from_queue(cmd); + if (remove) transport_put_cmd(cmd); - } -} - -static void transport_add_cmd_to_queue(struct se_cmd *cmd, int t_state, - bool at_head) -{ - struct se_device *dev = cmd->se_dev; - struct se_queue_obj *qobj = &dev->dev_queue_obj; - unsigned long flags; - - if (t_state) { - spin_lock_irqsave(&cmd->t_state_lock, flags); - cmd->t_state = t_state; - cmd->transport_state |= CMD_T_ACTIVE; - spin_unlock_irqrestore(&cmd->t_state_lock, flags); - } - - spin_lock_irqsave(&qobj->cmd_queue_lock, flags); - - /* If the cmd is already on the list, remove it before we add it */ - if (!list_empty(&cmd->se_queue_node)) - list_del(&cmd->se_queue_node); - else - atomic_inc(&qobj->queue_cnt); - - if (at_head) - list_add(&cmd->se_queue_node, &qobj->qobj_list); - else - list_add_tail(&cmd->se_queue_node, &qobj->qobj_list); - cmd->transport_state |= CMD_T_QUEUED; - spin_unlock_irqrestore(&qobj->cmd_queue_lock, flags); - - wake_up_interruptible(&qobj->thread_wq); -} - -static struct se_cmd * -transport_get_cmd_from_queue(struct se_queue_obj *qobj) -{ - struct se_cmd *cmd; - unsigned long flags; - - spin_lock_irqsave(&qobj->cmd_queue_lock, flags); - if (list_empty(&qobj->qobj_list)) { - spin_unlock_irqrestore(&qobj->cmd_queue_lock, flags); - return NULL; - } - cmd = list_first_entry(&qobj->qobj_list, struct se_cmd, se_queue_node); - - cmd->transport_state &= ~CMD_T_QUEUED; - list_del_init(&cmd->se_queue_node); - atomic_dec(&qobj->queue_cnt); - spin_unlock_irqrestore(&qobj->cmd_queue_lock, flags); - - return cmd; -} - -static void transport_remove_cmd_from_queue(struct se_cmd *cmd) -{ - struct se_queue_obj *qobj = &cmd->se_dev->dev_queue_obj; - unsigned long flags; - - spin_lock_irqsave(&qobj->cmd_queue_lock, flags); - if (!(cmd->transport_state & CMD_T_QUEUED)) { - spin_unlock_irqrestore(&qobj->cmd_queue_lock, flags); - return; - } - cmd->transport_state &= ~CMD_T_QUEUED; - atomic_dec(&qobj->queue_cnt); - list_del_init(&cmd->se_queue_node); - spin_unlock_irqrestore(&qobj->cmd_queue_lock, flags); } static void target_complete_failure_work(struct work_struct *work) @@ -742,68 +636,11 @@ static void target_add_to_state_list(struct se_cmd *cmd) spin_unlock_irqrestore(&dev->execute_task_lock, flags); } -static void __target_add_to_execute_list(struct se_cmd *cmd) -{ - struct se_device *dev = cmd->se_dev; - bool head_of_queue = false; - - if (!list_empty(&cmd->execute_list)) - return; - - if (dev->dev_task_attr_type == SAM_TASK_ATTR_EMULATED && - cmd->sam_task_attr == MSG_HEAD_TAG) - head_of_queue = true; - - if (head_of_queue) - list_add(&cmd->execute_list, &dev->execute_list); - else - list_add_tail(&cmd->execute_list, &dev->execute_list); - - atomic_inc(&dev->execute_tasks); - - if (cmd->state_active) - return; - - if (head_of_queue) - list_add(&cmd->state_list, &dev->state_list); - else - list_add_tail(&cmd->state_list, &dev->state_list); - - cmd->state_active = true; -} - -static void target_add_to_execute_list(struct se_cmd *cmd) -{ - unsigned long flags; - struct se_device *dev = cmd->se_dev; - - spin_lock_irqsave(&dev->execute_task_lock, flags); - __target_add_to_execute_list(cmd); - spin_unlock_irqrestore(&dev->execute_task_lock, flags); -} - -void __target_remove_from_execute_list(struct se_cmd *cmd) -{ - list_del_init(&cmd->execute_list); - atomic_dec(&cmd->se_dev->execute_tasks); -} - -static void target_remove_from_execute_list(struct se_cmd *cmd) -{ - struct se_device *dev = cmd->se_dev; - unsigned long flags; - - if (WARN_ON(list_empty(&cmd->execute_list))) - return; - - spin_lock_irqsave(&dev->execute_task_lock, flags); - __target_remove_from_execute_list(cmd); - spin_unlock_irqrestore(&dev->execute_task_lock, flags); -} - /* * Handle QUEUE_FULL / -EAGAIN and -ENOMEM status */ +static void transport_write_pending_qf(struct se_cmd *cmd); +static void transport_complete_qf(struct se_cmd *cmd); static void target_qf_do_work(struct work_struct *work) { @@ -827,7 +664,10 @@ static void target_qf_do_work(struct work_struct *work) (cmd->t_state == TRANSPORT_COMPLETE_QF_WP) ? "WRITE_PENDING" : "UNKNOWN"); - transport_add_cmd_to_queue(cmd, cmd->t_state, true); + if (cmd->t_state == TRANSPORT_COMPLETE_QF_WP) + transport_write_pending_qf(cmd); + else if (cmd->t_state == TRANSPORT_COMPLETE_QF_OK) + transport_complete_qf(cmd); } } @@ -874,8 +714,7 @@ void transport_dump_dev_state( break; } - *bl += sprintf(b + *bl, " Execute/Max Queue Depth: %d/%d", - atomic_read(&dev->execute_tasks), dev->queue_depth); + *bl += sprintf(b + *bl, " Max Queue Depth: %d", dev->queue_depth); *bl += sprintf(b + *bl, " SectorSize: %u HwMaxSectors: %u\n", dev->se_sub_dev->se_dev_attrib.block_size, dev->se_sub_dev->se_dev_attrib.hw_max_sectors); @@ -1212,7 +1051,6 @@ struct se_device *transport_add_device_to_core_hba( return NULL; } - transport_init_queue_obj(&dev->dev_queue_obj); dev->dev_flags = device_flags; dev->dev_status |= TRANSPORT_DEVICE_DEACTIVATED; dev->dev_ptr = transport_dev; @@ -1222,7 +1060,6 @@ struct se_device *transport_add_device_to_core_hba( INIT_LIST_HEAD(&dev->dev_list); INIT_LIST_HEAD(&dev->dev_sep_list); INIT_LIST_HEAD(&dev->dev_tmr_list); - INIT_LIST_HEAD(&dev->execute_list); INIT_LIST_HEAD(&dev->delayed_cmd_list); INIT_LIST_HEAD(&dev->state_list); INIT_LIST_HEAD(&dev->qf_cmd_list); @@ -1261,17 +1098,17 @@ struct se_device *transport_add_device_to_core_hba( * Setup the Asymmetric Logical Unit Assignment for struct se_device */ if (core_setup_alua(dev, force_pt) < 0) - goto out; + goto err_dev_list; /* * Startup the struct se_device processing thread */ - dev->process_thread = kthread_run(transport_processing_thread, dev, - "LIO_%s", dev->transport->name); - if (IS_ERR(dev->process_thread)) { - pr_err("Unable to create kthread: LIO_%s\n", + dev->tmr_wq = alloc_workqueue("tmr-%s", WQ_MEM_RECLAIM | WQ_UNBOUND, 1, + dev->transport->name); + if (!dev->tmr_wq) { + pr_err("Unable to create tmr workqueue for %s\n", dev->transport->name); - goto out; + goto err_dev_list; } /* * Setup work_queue for QUEUE_FULL @@ -1289,7 +1126,7 @@ struct se_device *transport_add_device_to_core_hba( if (!inquiry_prod || !inquiry_rev) { pr_err("All non TCM/pSCSI plugins require" " INQUIRY consts\n"); - goto out; + goto err_wq; } strncpy(&dev->se_sub_dev->t10_wwn.vendor[0], "LIO-ORG", 8); @@ -1299,9 +1136,10 @@ struct se_device *transport_add_device_to_core_hba( scsi_dump_inquiry(dev); return dev; -out: - kthread_stop(dev->process_thread); +err_wq: + destroy_workqueue(dev->tmr_wq); +err_dev_list: spin_lock(&hba->device_lock); list_del(&dev->dev_list); hba->dev_count--; @@ -1315,35 +1153,54 @@ out: } EXPORT_SYMBOL(transport_add_device_to_core_hba); -/* transport_generic_prepare_cdb(): - * - * Since the Initiator sees iSCSI devices as LUNs, the SCSI CDB will - * contain the iSCSI LUN in bits 7-5 of byte 1 as per SAM-2. - * The point of this is since we are mapping iSCSI LUNs to - * SCSI Target IDs having a non-zero LUN in the CDB will throw the - * devices and HBAs for a loop. - */ -static inline void transport_generic_prepare_cdb( - unsigned char *cdb) +int target_cmd_size_check(struct se_cmd *cmd, unsigned int size) { - switch (cdb[0]) { - case READ_10: /* SBC - RDProtect */ - case READ_12: /* SBC - RDProtect */ - case READ_16: /* SBC - RDProtect */ - case SEND_DIAGNOSTIC: /* SPC - SELF-TEST Code */ - case VERIFY: /* SBC - VRProtect */ - case VERIFY_16: /* SBC - VRProtect */ - case WRITE_VERIFY: /* SBC - VRProtect */ - case WRITE_VERIFY_12: /* SBC - VRProtect */ - case MAINTENANCE_IN: /* SPC - Parameter Data Format for SA RTPG */ - break; - default: - cdb[1] &= 0x1f; /* clear logical unit number */ - break; + struct se_device *dev = cmd->se_dev; + + if (cmd->unknown_data_length) { + cmd->data_length = size; + } else if (size != cmd->data_length) { + pr_warn("TARGET_CORE[%s]: Expected Transfer Length:" + " %u does not match SCSI CDB Length: %u for SAM Opcode:" + " 0x%02x\n", cmd->se_tfo->get_fabric_name(), + cmd->data_length, size, cmd->t_task_cdb[0]); + + cmd->cmd_spdtl = size; + + if (cmd->data_direction == DMA_TO_DEVICE) { + pr_err("Rejecting underflow/overflow" + " WRITE data\n"); + goto out_invalid_cdb_field; + } + /* + * Reject READ_* or WRITE_* with overflow/underflow for + * type SCF_SCSI_DATA_CDB. + */ + if (dev->se_sub_dev->se_dev_attrib.block_size != 512) { + pr_err("Failing OVERFLOW/UNDERFLOW for LBA op" + " CDB on non 512-byte sector setup subsystem" + " plugin: %s\n", dev->transport->name); + /* Returns CHECK_CONDITION + INVALID_CDB_FIELD */ + goto out_invalid_cdb_field; + } + + if (size > cmd->data_length) { + cmd->se_cmd_flags |= SCF_OVERFLOW_BIT; + cmd->residual_count = (size - cmd->data_length); + } else { + cmd->se_cmd_flags |= SCF_UNDERFLOW_BIT; + cmd->residual_count = (cmd->data_length - size); + } + cmd->data_length = size; } -} -static int transport_generic_cmd_sequencer(struct se_cmd *, unsigned char *); + return 0; + +out_invalid_cdb_field: + cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; + cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD; + return -EINVAL; +} /* * Used by fabric modules containing a local struct se_cmd within their @@ -1361,9 +1218,7 @@ void transport_init_se_cmd( INIT_LIST_HEAD(&cmd->se_lun_node); INIT_LIST_HEAD(&cmd->se_delayed_node); INIT_LIST_HEAD(&cmd->se_qf_node); - INIT_LIST_HEAD(&cmd->se_queue_node); INIT_LIST_HEAD(&cmd->se_cmd_list); - INIT_LIST_HEAD(&cmd->execute_list); INIT_LIST_HEAD(&cmd->state_list); init_completion(&cmd->transport_lun_fe_stop_comp); init_completion(&cmd->transport_lun_stop_comp); @@ -1418,9 +1273,12 @@ int target_setup_cmd_from_cdb( struct se_cmd *cmd, unsigned char *cdb) { + struct se_subsystem_dev *su_dev = cmd->se_dev->se_sub_dev; + u32 pr_reg_type = 0; + u8 alua_ascq = 0; + unsigned long flags; int ret; - transport_generic_prepare_cdb(cdb); /* * Ensure that the received CDB is less than the max (252 + 8) bytes * for VARIABLE_LENGTH_CMD @@ -1457,15 +1315,66 @@ int target_setup_cmd_from_cdb( * Copy the original CDB into cmd-> */ memcpy(cmd->t_task_cdb, cdb, scsi_command_size(cdb)); + /* - * Setup the received CDB based on SCSI defined opcodes and - * perform unit attention, persistent reservations and ALUA - * checks for virtual device backends. The cmd->t_task_cdb - * pointer is expected to be setup before we reach this point. + * Check for an existing UNIT ATTENTION condition */ - ret = transport_generic_cmd_sequencer(cmd, cdb); + if (core_scsi3_ua_check(cmd, cdb) < 0) { + cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; + cmd->scsi_sense_reason = TCM_CHECK_CONDITION_UNIT_ATTENTION; + return -EINVAL; + } + + ret = su_dev->t10_alua.alua_state_check(cmd, cdb, &alua_ascq); + if (ret != 0) { + /* + * Set SCSI additional sense code (ASC) to 'LUN Not Accessible'; + * The ALUA additional sense code qualifier (ASCQ) is determined + * by the ALUA primary or secondary access state.. + */ + if (ret > 0) { + pr_debug("[%s]: ALUA TG Port not available, " + "SenseKey: NOT_READY, ASC/ASCQ: " + "0x04/0x%02x\n", + cmd->se_tfo->get_fabric_name(), alua_ascq); + + transport_set_sense_codes(cmd, 0x04, alua_ascq); + cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; + cmd->scsi_sense_reason = TCM_CHECK_CONDITION_NOT_READY; + return -EINVAL; + } + cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; + cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD; + return -EINVAL; + } + + /* + * Check status for SPC-3 Persistent Reservations + */ + if (su_dev->t10_pr.pr_ops.t10_reservation_check(cmd, &pr_reg_type)) { + if (su_dev->t10_pr.pr_ops.t10_seq_non_holder( + cmd, cdb, pr_reg_type) != 0) { + cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; + cmd->se_cmd_flags |= SCF_SCSI_RESERVATION_CONFLICT; + cmd->scsi_status = SAM_STAT_RESERVATION_CONFLICT; + cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT; + return -EBUSY; + } + /* + * This means the CDB is allowed for the SCSI Initiator port + * when said port is *NOT* holding the legacy SPC-2 or + * SPC-3 Persistent Reservation. + */ + } + + ret = cmd->se_dev->transport->parse_cdb(cmd); if (ret < 0) return ret; + + spin_lock_irqsave(&cmd->t_state_lock, flags); + cmd->se_cmd_flags |= SCF_SUPPORTED_SAM_OPCODE; + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + /* * Check for SAM Task Attribute Emulation */ @@ -1503,10 +1412,9 @@ int transport_handle_cdb_direct( return -EINVAL; } /* - * Set TRANSPORT_NEW_CMD state and CMD_T_ACTIVE following - * transport_generic_handle_cdb*() -> transport_add_cmd_to_queue() - * in existing usage to ensure that outstanding descriptors are handled - * correctly during shutdown via transport_wait_for_tasks() + * Set TRANSPORT_NEW_CMD state and CMD_T_ACTIVE to ensure that + * outstanding descriptors are handled correctly during shutdown via + * transport_wait_for_tasks() * * Also, we don't take cmd->t_state_lock here as we only expect * this to be called for initial descriptor submission. @@ -1540,10 +1448,14 @@ EXPORT_SYMBOL(transport_handle_cdb_direct); * @data_dir: DMA data direction * @flags: flags for command submission from target_sc_flags_tables * + * Returns non zero to signal active I/O shutdown failure. All other + * setup exceptions will be returned as a SCSI CHECK_CONDITION response, + * but still return zero here. + * * This may only be called from process context, and also currently * assumes internal allocation of fabric payload buffer by target-core. **/ -void target_submit_cmd(struct se_cmd *se_cmd, struct se_session *se_sess, +int target_submit_cmd(struct se_cmd *se_cmd, struct se_session *se_sess, unsigned char *cdb, unsigned char *sense, u32 unpacked_lun, u32 data_length, int task_attr, int data_dir, int flags) { @@ -1569,7 +1481,9 @@ void target_submit_cmd(struct se_cmd *se_cmd, struct se_session *se_sess, * for fabrics using TARGET_SCF_ACK_KREF that expect a second * kref_put() to happen during fabric packet acknowledgement. */ - target_get_sess_cmd(se_sess, se_cmd, (flags & TARGET_SCF_ACK_KREF)); + rc = target_get_sess_cmd(se_sess, se_cmd, (flags & TARGET_SCF_ACK_KREF)); + if (rc) + return rc; /* * Signal bidirectional data payloads to target-core */ @@ -1582,16 +1496,13 @@ void target_submit_cmd(struct se_cmd *se_cmd, struct se_session *se_sess, transport_send_check_condition_and_sense(se_cmd, se_cmd->scsi_sense_reason, 0); target_put_sess_cmd(se_sess, se_cmd); - return; + return 0; } - /* - * Sanitize CDBs via transport_generic_cmd_sequencer() and - * allocate the necessary tasks to complete the received CDB+data - */ + rc = target_setup_cmd_from_cdb(se_cmd, cdb); if (rc != 0) { transport_generic_request_failure(se_cmd); - return; + return 0; } /* @@ -1600,14 +1511,8 @@ void target_submit_cmd(struct se_cmd *se_cmd, struct se_session *se_sess, */ core_alua_check_nonop_delay(se_cmd); - /* - * Dispatch se_cmd descriptor to se_lun->lun_se_dev backend - * for immediate execution of READs, otherwise wait for - * transport_generic_handle_data() to be called for WRITEs - * when fabric has filled the incoming buffer. - */ transport_handle_cdb_direct(se_cmd); - return; + return 0; } EXPORT_SYMBOL(target_submit_cmd); @@ -1662,7 +1567,11 @@ int target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess, se_cmd->se_tmr_req->ref_task_tag = tag; /* See target_submit_cmd for commentary */ - target_get_sess_cmd(se_sess, se_cmd, (flags & TARGET_SCF_ACK_KREF)); + ret = target_get_sess_cmd(se_sess, se_cmd, (flags & TARGET_SCF_ACK_KREF)); + if (ret) { + core_tmr_release_req(se_cmd->se_tmr_req); + return ret; + } ret = transport_lookup_tmr_lun(se_cmd, unpacked_lun); if (ret) { @@ -1680,67 +1589,6 @@ int target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess, EXPORT_SYMBOL(target_submit_tmr); /* - * Used by fabric module frontends defining a TFO->new_cmd_map() caller - * to queue up a newly setup se_cmd w/ TRANSPORT_NEW_CMD_MAP in order to - * complete setup in TCM process context w/ TFO->new_cmd_map(). - */ -int transport_generic_handle_cdb_map( - struct se_cmd *cmd) -{ - if (!cmd->se_lun) { - dump_stack(); - pr_err("cmd->se_lun is NULL\n"); - return -EINVAL; - } - - transport_add_cmd_to_queue(cmd, TRANSPORT_NEW_CMD_MAP, false); - return 0; -} -EXPORT_SYMBOL(transport_generic_handle_cdb_map); - -/* transport_generic_handle_data(): - * - * - */ -int transport_generic_handle_data( - struct se_cmd *cmd) -{ - /* - * For the software fabric case, then we assume the nexus is being - * failed/shutdown when signals are pending from the kthread context - * caller, so we return a failure. For the HW target mode case running - * in interrupt code, the signal_pending() check is skipped. - */ - if (!in_interrupt() && signal_pending(current)) - return -EPERM; - /* - * If the received CDB has aleady been ABORTED by the generic - * target engine, we now call transport_check_aborted_status() - * to queue any delated TASK_ABORTED status for the received CDB to the - * fabric module as we are expecting no further incoming DATA OUT - * sequences at this point. - */ - if (transport_check_aborted_status(cmd, 1) != 0) - return 0; - - transport_add_cmd_to_queue(cmd, TRANSPORT_PROCESS_WRITE, false); - return 0; -} -EXPORT_SYMBOL(transport_generic_handle_data); - -/* transport_generic_handle_tmr(): - * - * - */ -int transport_generic_handle_tmr( - struct se_cmd *cmd) -{ - transport_add_cmd_to_queue(cmd, TRANSPORT_PROCESS_TMR, false); - return 0; -} -EXPORT_SYMBOL(transport_generic_handle_tmr); - -/* * If the cmd is active, request it to be stopped and sleep until it * has completed. */ @@ -1797,6 +1645,7 @@ void transport_generic_request_failure(struct se_cmd *cmd) case TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE: case TCM_UNKNOWN_MODE_PAGE: case TCM_WRITE_PROTECTED: + case TCM_ADDRESS_OUT_OF_RANGE: case TCM_CHECK_CONDITION_ABORT_CMD: case TCM_CHECK_CONDITION_UNIT_ATTENTION: case TCM_CHECK_CONDITION_NOT_READY: @@ -1832,13 +1681,7 @@ void transport_generic_request_failure(struct se_cmd *cmd) cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE; break; } - /* - * If a fabric does not define a cmd->se_tfo->new_cmd_map caller, - * make the call to transport_send_check_condition_and_sense() - * directly. Otherwise expect the fabric to make the call to - * transport_send_check_condition_and_sense() after handling - * possible unsoliticied write data payloads. - */ + ret = transport_send_check_condition_and_sense(cmd, cmd->scsi_sense_reason, 0); if (ret == -EAGAIN || ret == -ENOMEM) @@ -1856,406 +1699,123 @@ queue_full: } EXPORT_SYMBOL(transport_generic_request_failure); -static inline u32 transport_lba_21(unsigned char *cdb) +static void __target_execute_cmd(struct se_cmd *cmd) { - return ((cdb[1] & 0x1f) << 16) | (cdb[2] << 8) | cdb[3]; -} + int error = 0; -static inline u32 transport_lba_32(unsigned char *cdb) -{ - return (cdb[2] << 24) | (cdb[3] << 16) | (cdb[4] << 8) | cdb[5]; -} - -static inline unsigned long long transport_lba_64(unsigned char *cdb) -{ - unsigned int __v1, __v2; - - __v1 = (cdb[2] << 24) | (cdb[3] << 16) | (cdb[4] << 8) | cdb[5]; - __v2 = (cdb[6] << 24) | (cdb[7] << 16) | (cdb[8] << 8) | cdb[9]; - - return ((unsigned long long)__v2) | (unsigned long long)__v1 << 32; -} - -/* - * For VARIABLE_LENGTH_CDB w/ 32 byte extended CDBs - */ -static inline unsigned long long transport_lba_64_ext(unsigned char *cdb) -{ - unsigned int __v1, __v2; - - __v1 = (cdb[12] << 24) | (cdb[13] << 16) | (cdb[14] << 8) | cdb[15]; - __v2 = (cdb[16] << 24) | (cdb[17] << 16) | (cdb[18] << 8) | cdb[19]; - - return ((unsigned long long)__v2) | (unsigned long long)__v1 << 32; -} - -static void transport_set_supported_SAM_opcode(struct se_cmd *se_cmd) -{ - unsigned long flags; - - spin_lock_irqsave(&se_cmd->t_state_lock, flags); - se_cmd->se_cmd_flags |= SCF_SUPPORTED_SAM_OPCODE; - spin_unlock_irqrestore(&se_cmd->t_state_lock, flags); -} - -/* - * Called from Fabric Module context from transport_execute_tasks() - * - * The return of this function determins if the tasks from struct se_cmd - * get added to the execution queue in transport_execute_tasks(), - * or are added to the delayed or ordered lists here. - */ -static inline int transport_execute_task_attr(struct se_cmd *cmd) -{ - if (cmd->se_dev->dev_task_attr_type != SAM_TASK_ATTR_EMULATED) - return 1; - /* - * Check for the existence of HEAD_OF_QUEUE, and if true return 1 - * to allow the passed struct se_cmd list of tasks to the front of the list. - */ - if (cmd->sam_task_attr == MSG_HEAD_TAG) { - pr_debug("Added HEAD_OF_QUEUE for CDB:" - " 0x%02x, se_ordered_id: %u\n", - cmd->t_task_cdb[0], - cmd->se_ordered_id); - return 1; - } else if (cmd->sam_task_attr == MSG_ORDERED_TAG) { - atomic_inc(&cmd->se_dev->dev_ordered_sync); - smp_mb__after_atomic_inc(); - - pr_debug("Added ORDERED for CDB: 0x%02x to ordered" - " list, se_ordered_id: %u\n", - cmd->t_task_cdb[0], - cmd->se_ordered_id); - /* - * Add ORDERED command to tail of execution queue if - * no other older commands exist that need to be - * completed first. - */ - if (!atomic_read(&cmd->se_dev->simple_cmds)) - return 1; - } else { - /* - * For SIMPLE and UNTAGGED Task Attribute commands - */ - atomic_inc(&cmd->se_dev->simple_cmds); - smp_mb__after_atomic_inc(); - } - /* - * Otherwise if one or more outstanding ORDERED task attribute exist, - * add the dormant task(s) built for the passed struct se_cmd to the - * execution queue and become in Active state for this struct se_device. - */ - if (atomic_read(&cmd->se_dev->dev_ordered_sync) != 0) { - /* - * Otherwise, add cmd w/ tasks to delayed cmd queue that - * will be drained upon completion of HEAD_OF_QUEUE task. - */ - spin_lock(&cmd->se_dev->delayed_cmd_lock); - cmd->se_cmd_flags |= SCF_DELAYED_CMD_FROM_SAM_ATTR; - list_add_tail(&cmd->se_delayed_node, - &cmd->se_dev->delayed_cmd_list); - spin_unlock(&cmd->se_dev->delayed_cmd_lock); - - pr_debug("Added CDB: 0x%02x Task Attr: 0x%02x to" - " delayed CMD list, se_ordered_id: %u\n", - cmd->t_task_cdb[0], cmd->sam_task_attr, - cmd->se_ordered_id); - /* - * Return zero to let transport_execute_tasks() know - * not to add the delayed tasks to the execution list. - */ - return 0; - } - /* - * Otherwise, no ORDERED task attributes exist.. - */ - return 1; -} - -/* - * Called from fabric module context in transport_generic_new_cmd() and - * transport_generic_process_write() - */ -static void transport_execute_tasks(struct se_cmd *cmd) -{ - int add_tasks; - struct se_device *se_dev = cmd->se_dev; - /* - * Call transport_cmd_check_stop() to see if a fabric exception - * has occurred that prevents execution. - */ - if (!transport_cmd_check_stop(cmd, 0, TRANSPORT_PROCESSING)) { - /* - * Check for SAM Task Attribute emulation and HEAD_OF_QUEUE - * attribute for the tasks of the received struct se_cmd CDB - */ - add_tasks = transport_execute_task_attr(cmd); - if (add_tasks) { - __transport_execute_tasks(se_dev, cmd); - return; - } - } - __transport_execute_tasks(se_dev, NULL); -} - -static int __transport_execute_tasks(struct se_device *dev, struct se_cmd *new_cmd) -{ - int error; - struct se_cmd *cmd = NULL; - unsigned long flags; - -check_depth: - spin_lock_irq(&dev->execute_task_lock); - if (new_cmd != NULL) - __target_add_to_execute_list(new_cmd); - - if (list_empty(&dev->execute_list)) { - spin_unlock_irq(&dev->execute_task_lock); - return 0; - } - cmd = list_first_entry(&dev->execute_list, struct se_cmd, execute_list); - __target_remove_from_execute_list(cmd); - spin_unlock_irq(&dev->execute_task_lock); - - spin_lock_irqsave(&cmd->t_state_lock, flags); - cmd->transport_state |= CMD_T_BUSY; - cmd->transport_state |= CMD_T_SENT; - - spin_unlock_irqrestore(&cmd->t_state_lock, flags); + spin_lock_irq(&cmd->t_state_lock); + cmd->transport_state |= (CMD_T_BUSY|CMD_T_SENT); + spin_unlock_irq(&cmd->t_state_lock); if (cmd->execute_cmd) error = cmd->execute_cmd(cmd); - else { - error = dev->transport->execute_cmd(cmd, cmd->t_data_sg, - cmd->t_data_nents, cmd->data_direction); - } - if (error != 0) { - spin_lock_irqsave(&cmd->t_state_lock, flags); - cmd->transport_state &= ~CMD_T_BUSY; - cmd->transport_state &= ~CMD_T_SENT; - spin_unlock_irqrestore(&cmd->t_state_lock, flags); + if (error) { + spin_lock_irq(&cmd->t_state_lock); + cmd->transport_state &= ~(CMD_T_BUSY|CMD_T_SENT); + spin_unlock_irq(&cmd->t_state_lock); transport_generic_request_failure(cmd); } - - new_cmd = NULL; - goto check_depth; - - return 0; } -static inline u32 transport_get_sectors_6( - unsigned char *cdb, - struct se_cmd *cmd, - int *ret) +void target_execute_cmd(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; /* - * Assume TYPE_DISK for non struct se_device objects. - * Use 8-bit sector value. - */ - if (!dev) - goto type_disk; - - /* - * Use 24-bit allocation length for TYPE_TAPE. + * If the received CDB has aleady been aborted stop processing it here. */ - if (dev->transport->get_device_type(dev) == TYPE_TAPE) - return (u32)(cdb[2] << 16) + (cdb[3] << 8) + cdb[4]; - - /* - * Everything else assume TYPE_DISK Sector CDB location. - * Use 8-bit sector value. SBC-3 says: - * - * A TRANSFER LENGTH field set to zero specifies that 256 - * logical blocks shall be written. Any other value - * specifies the number of logical blocks that shall be - * written. - */ -type_disk: - return cdb[4] ? : 256; -} - -static inline u32 transport_get_sectors_10( - unsigned char *cdb, - struct se_cmd *cmd, - int *ret) -{ - struct se_device *dev = cmd->se_dev; + if (transport_check_aborted_status(cmd, 1)) + return; /* - * Assume TYPE_DISK for non struct se_device objects. - * Use 16-bit sector value. + * Determine if IOCTL context caller in requesting the stopping of this + * command for LUN shutdown purposes. */ - if (!dev) - goto type_disk; + spin_lock_irq(&cmd->t_state_lock); + if (cmd->transport_state & CMD_T_LUN_STOP) { + pr_debug("%s:%d CMD_T_LUN_STOP for ITT: 0x%08x\n", + __func__, __LINE__, cmd->se_tfo->get_task_tag(cmd)); - /* - * XXX_10 is not defined in SSC, throw an exception - */ - if (dev->transport->get_device_type(dev) == TYPE_TAPE) { - *ret = -EINVAL; - return 0; + cmd->transport_state &= ~CMD_T_ACTIVE; + spin_unlock_irq(&cmd->t_state_lock); + complete(&cmd->transport_lun_stop_comp); + return; } - /* - * Everything else assume TYPE_DISK Sector CDB location. - * Use 16-bit sector value. - */ -type_disk: - return (u32)(cdb[7] << 8) + cdb[8]; -} - -static inline u32 transport_get_sectors_12( - unsigned char *cdb, - struct se_cmd *cmd, - int *ret) -{ - struct se_device *dev = cmd->se_dev; - - /* - * Assume TYPE_DISK for non struct se_device objects. - * Use 32-bit sector value. + * Determine if frontend context caller is requesting the stopping of + * this command for frontend exceptions. */ - if (!dev) - goto type_disk; + if (cmd->transport_state & CMD_T_STOP) { + pr_debug("%s:%d CMD_T_STOP for ITT: 0x%08x\n", + __func__, __LINE__, + cmd->se_tfo->get_task_tag(cmd)); - /* - * XXX_12 is not defined in SSC, throw an exception - */ - if (dev->transport->get_device_type(dev) == TYPE_TAPE) { - *ret = -EINVAL; - return 0; + spin_unlock_irq(&cmd->t_state_lock); + complete(&cmd->t_transport_stop_comp); + return; } - /* - * Everything else assume TYPE_DISK Sector CDB location. - * Use 32-bit sector value. - */ -type_disk: - return (u32)(cdb[6] << 24) + (cdb[7] << 16) + (cdb[8] << 8) + cdb[9]; -} - -static inline u32 transport_get_sectors_16( - unsigned char *cdb, - struct se_cmd *cmd, - int *ret) -{ - struct se_device *dev = cmd->se_dev; - - /* - * Assume TYPE_DISK for non struct se_device objects. - * Use 32-bit sector value. - */ - if (!dev) - goto type_disk; + cmd->t_state = TRANSPORT_PROCESSING; + spin_unlock_irq(&cmd->t_state_lock); - /* - * Use 24-bit allocation length for TYPE_TAPE. - */ - if (dev->transport->get_device_type(dev) == TYPE_TAPE) - return (u32)(cdb[12] << 16) + (cdb[13] << 8) + cdb[14]; - -type_disk: - return (u32)(cdb[10] << 24) + (cdb[11] << 16) + - (cdb[12] << 8) + cdb[13]; -} + if (dev->dev_task_attr_type != SAM_TASK_ATTR_EMULATED) + goto execute; -/* - * Used for VARIABLE_LENGTH_CDB WRITE_32 and READ_32 variants - */ -static inline u32 transport_get_sectors_32( - unsigned char *cdb, - struct se_cmd *cmd, - int *ret) -{ /* - * Assume TYPE_DISK for non struct se_device objects. - * Use 32-bit sector value. + * Check for the existence of HEAD_OF_QUEUE, and if true return 1 + * to allow the passed struct se_cmd list of tasks to the front of the list. */ - return (u32)(cdb[28] << 24) + (cdb[29] << 16) + - (cdb[30] << 8) + cdb[31]; + switch (cmd->sam_task_attr) { + case MSG_HEAD_TAG: + pr_debug("Added HEAD_OF_QUEUE for CDB: 0x%02x, " + "se_ordered_id: %u\n", + cmd->t_task_cdb[0], cmd->se_ordered_id); + goto execute; + case MSG_ORDERED_TAG: + atomic_inc(&dev->dev_ordered_sync); + smp_mb__after_atomic_inc(); -} + pr_debug("Added ORDERED for CDB: 0x%02x to ordered list, " + " se_ordered_id: %u\n", + cmd->t_task_cdb[0], cmd->se_ordered_id); -static inline u32 transport_get_size( - u32 sectors, - unsigned char *cdb, - struct se_cmd *cmd) -{ - struct se_device *dev = cmd->se_dev; - - if (dev->transport->get_device_type(dev) == TYPE_TAPE) { - if (cdb[1] & 1) { /* sectors */ - return dev->se_sub_dev->se_dev_attrib.block_size * sectors; - } else /* bytes */ - return sectors; + /* + * Execute an ORDERED command if no other older commands + * exist that need to be completed first. + */ + if (!atomic_read(&dev->simple_cmds)) + goto execute; + break; + default: + /* + * For SIMPLE and UNTAGGED Task Attribute commands + */ + atomic_inc(&dev->simple_cmds); + smp_mb__after_atomic_inc(); + break; } - pr_debug("Returning block_size: %u, sectors: %u == %u for" - " %s object\n", dev->se_sub_dev->se_dev_attrib.block_size, - sectors, dev->se_sub_dev->se_dev_attrib.block_size * sectors, - dev->transport->name); - - return dev->se_sub_dev->se_dev_attrib.block_size * sectors; -} + if (atomic_read(&dev->dev_ordered_sync) != 0) { + spin_lock(&dev->delayed_cmd_lock); + list_add_tail(&cmd->se_delayed_node, &dev->delayed_cmd_list); + spin_unlock(&dev->delayed_cmd_lock); -static void transport_xor_callback(struct se_cmd *cmd) -{ - unsigned char *buf, *addr; - struct scatterlist *sg; - unsigned int offset; - int i; - int count; - /* - * From sbc3r22.pdf section 5.48 XDWRITEREAD (10) command - * - * 1) read the specified logical block(s); - * 2) transfer logical blocks from the data-out buffer; - * 3) XOR the logical blocks transferred from the data-out buffer with - * the logical blocks read, storing the resulting XOR data in a buffer; - * 4) if the DISABLE WRITE bit is set to zero, then write the logical - * blocks transferred from the data-out buffer; and - * 5) transfer the resulting XOR data to the data-in buffer. - */ - buf = kmalloc(cmd->data_length, GFP_KERNEL); - if (!buf) { - pr_err("Unable to allocate xor_callback buf\n"); + pr_debug("Added CDB: 0x%02x Task Attr: 0x%02x to" + " delayed CMD list, se_ordered_id: %u\n", + cmd->t_task_cdb[0], cmd->sam_task_attr, + cmd->se_ordered_id); return; } - /* - * Copy the scatterlist WRITE buffer located at cmd->t_data_sg - * into the locally allocated *buf - */ - sg_copy_to_buffer(cmd->t_data_sg, - cmd->t_data_nents, - buf, - cmd->data_length); +execute: /* - * Now perform the XOR against the BIDI read memory located at - * cmd->t_mem_bidi_list + * Otherwise, no ORDERED task attributes exist.. */ - - offset = 0; - for_each_sg(cmd->t_bidi_data_sg, sg, cmd->t_bidi_data_nents, count) { - addr = kmap_atomic(sg_page(sg)); - if (!addr) - goto out; - - for (i = 0; i < sg->length; i++) - *(addr + sg->offset + i) ^= *(buf + offset + i); - - offset += sg->length; - kunmap_atomic(addr); - } - -out: - kfree(buf); + __target_execute_cmd(cmd); } +EXPORT_SYMBOL(target_execute_cmd); /* * Used to obtain Sense Data from underlying Linux/SCSI struct scsi_cmnd @@ -2312,737 +1872,31 @@ out: return -1; } -static inline long long transport_dev_end_lba(struct se_device *dev) -{ - return dev->transport->get_blocks(dev) + 1; -} - -static int transport_cmd_get_valid_sectors(struct se_cmd *cmd) -{ - struct se_device *dev = cmd->se_dev; - u32 sectors; - - if (dev->transport->get_device_type(dev) != TYPE_DISK) - return 0; - - sectors = (cmd->data_length / dev->se_sub_dev->se_dev_attrib.block_size); - - if ((cmd->t_task_lba + sectors) > transport_dev_end_lba(dev)) { - pr_err("LBA: %llu Sectors: %u exceeds" - " transport_dev_end_lba(): %llu\n", - cmd->t_task_lba, sectors, - transport_dev_end_lba(dev)); - return -EINVAL; - } - - return 0; -} - -static int target_check_write_same_discard(unsigned char *flags, struct se_device *dev) -{ - /* - * Determine if the received WRITE_SAME is used to for direct - * passthrough into Linux/SCSI with struct request via TCM/pSCSI - * or we are signaling the use of internal WRITE_SAME + UNMAP=1 - * emulation for -> Linux/BLOCK disbard with TCM/IBLOCK code. - */ - int passthrough = (dev->transport->transport_type == - TRANSPORT_PLUGIN_PHBA_PDEV); - - if (!passthrough) { - if ((flags[0] & 0x04) || (flags[0] & 0x02)) { - pr_err("WRITE_SAME PBDATA and LBDATA" - " bits not supported for Block Discard" - " Emulation\n"); - return -ENOSYS; - } - /* - * Currently for the emulated case we only accept - * tpws with the UNMAP=1 bit set. - */ - if (!(flags[0] & 0x08)) { - pr_err("WRITE_SAME w/o UNMAP bit not" - " supported for Block Discard Emulation\n"); - return -ENOSYS; - } - } - - return 0; -} - -/* transport_generic_cmd_sequencer(): - * - * Generic Command Sequencer that should work for most DAS transport - * drivers. - * - * Called from target_setup_cmd_from_cdb() in the $FABRIC_MOD - * RX Thread. - * - * FIXME: Need to support other SCSI OPCODES where as well. +/* + * Process all commands up to the last received ORDERED task attribute which + * requires another blocking boundary */ -static int transport_generic_cmd_sequencer( - struct se_cmd *cmd, - unsigned char *cdb) +static void target_restart_delayed_cmds(struct se_device *dev) { - struct se_device *dev = cmd->se_dev; - struct se_subsystem_dev *su_dev = dev->se_sub_dev; - int ret = 0, sector_ret = 0, passthrough; - u32 sectors = 0, size = 0, pr_reg_type = 0; - u16 service_action; - u8 alua_ascq = 0; - /* - * Check for an existing UNIT ATTENTION condition - */ - if (core_scsi3_ua_check(cmd, cdb) < 0) { - cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; - cmd->scsi_sense_reason = TCM_CHECK_CONDITION_UNIT_ATTENTION; - return -EINVAL; - } - /* - * Check status of Asymmetric Logical Unit Assignment port - */ - ret = su_dev->t10_alua.alua_state_check(cmd, cdb, &alua_ascq); - if (ret != 0) { - /* - * Set SCSI additional sense code (ASC) to 'LUN Not Accessible'; - * The ALUA additional sense code qualifier (ASCQ) is determined - * by the ALUA primary or secondary access state.. - */ - if (ret > 0) { - pr_debug("[%s]: ALUA TG Port not available," - " SenseKey: NOT_READY, ASC/ASCQ: 0x04/0x%02x\n", - cmd->se_tfo->get_fabric_name(), alua_ascq); + for (;;) { + struct se_cmd *cmd; - transport_set_sense_codes(cmd, 0x04, alua_ascq); - cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; - cmd->scsi_sense_reason = TCM_CHECK_CONDITION_NOT_READY; - return -EINVAL; - } - goto out_invalid_cdb_field; - } - /* - * Check status for SPC-3 Persistent Reservations - */ - if (su_dev->t10_pr.pr_ops.t10_reservation_check(cmd, &pr_reg_type) != 0) { - if (su_dev->t10_pr.pr_ops.t10_seq_non_holder( - cmd, cdb, pr_reg_type) != 0) { - cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; - cmd->se_cmd_flags |= SCF_SCSI_RESERVATION_CONFLICT; - cmd->scsi_status = SAM_STAT_RESERVATION_CONFLICT; - cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT; - return -EBUSY; - } - /* - * This means the CDB is allowed for the SCSI Initiator port - * when said port is *NOT* holding the legacy SPC-2 or - * SPC-3 Persistent Reservation. - */ - } - - /* - * If we operate in passthrough mode we skip most CDB emulation and - * instead hand the commands down to the physical SCSI device. - */ - passthrough = - (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV); - - switch (cdb[0]) { - case READ_6: - sectors = transport_get_sectors_6(cdb, cmd, §or_ret); - if (sector_ret) - goto out_unsupported_cdb; - size = transport_get_size(sectors, cdb, cmd); - cmd->t_task_lba = transport_lba_21(cdb); - cmd->se_cmd_flags |= SCF_SCSI_DATA_SG_IO_CDB; - break; - case READ_10: - sectors = transport_get_sectors_10(cdb, cmd, §or_ret); - if (sector_ret) - goto out_unsupported_cdb; - size = transport_get_size(sectors, cdb, cmd); - cmd->t_task_lba = transport_lba_32(cdb); - cmd->se_cmd_flags |= SCF_SCSI_DATA_SG_IO_CDB; - break; - case READ_12: - sectors = transport_get_sectors_12(cdb, cmd, §or_ret); - if (sector_ret) - goto out_unsupported_cdb; - size = transport_get_size(sectors, cdb, cmd); - cmd->t_task_lba = transport_lba_32(cdb); - cmd->se_cmd_flags |= SCF_SCSI_DATA_SG_IO_CDB; - break; - case READ_16: - sectors = transport_get_sectors_16(cdb, cmd, §or_ret); - if (sector_ret) - goto out_unsupported_cdb; - size = transport_get_size(sectors, cdb, cmd); - cmd->t_task_lba = transport_lba_64(cdb); - cmd->se_cmd_flags |= SCF_SCSI_DATA_SG_IO_CDB; - break; - case WRITE_6: - sectors = transport_get_sectors_6(cdb, cmd, §or_ret); - if (sector_ret) - goto out_unsupported_cdb; - size = transport_get_size(sectors, cdb, cmd); - cmd->t_task_lba = transport_lba_21(cdb); - cmd->se_cmd_flags |= SCF_SCSI_DATA_SG_IO_CDB; - break; - case WRITE_10: - case WRITE_VERIFY: - sectors = transport_get_sectors_10(cdb, cmd, §or_ret); - if (sector_ret) - goto out_unsupported_cdb; - size = transport_get_size(sectors, cdb, cmd); - cmd->t_task_lba = transport_lba_32(cdb); - if (cdb[1] & 0x8) - cmd->se_cmd_flags |= SCF_FUA; - cmd->se_cmd_flags |= SCF_SCSI_DATA_SG_IO_CDB; - break; - case WRITE_12: - sectors = transport_get_sectors_12(cdb, cmd, §or_ret); - if (sector_ret) - goto out_unsupported_cdb; - size = transport_get_size(sectors, cdb, cmd); - cmd->t_task_lba = transport_lba_32(cdb); - if (cdb[1] & 0x8) - cmd->se_cmd_flags |= SCF_FUA; - cmd->se_cmd_flags |= SCF_SCSI_DATA_SG_IO_CDB; - break; - case WRITE_16: - sectors = transport_get_sectors_16(cdb, cmd, §or_ret); - if (sector_ret) - goto out_unsupported_cdb; - size = transport_get_size(sectors, cdb, cmd); - cmd->t_task_lba = transport_lba_64(cdb); - if (cdb[1] & 0x8) - cmd->se_cmd_flags |= SCF_FUA; - cmd->se_cmd_flags |= SCF_SCSI_DATA_SG_IO_CDB; - break; - case XDWRITEREAD_10: - if ((cmd->data_direction != DMA_TO_DEVICE) || - !(cmd->se_cmd_flags & SCF_BIDI)) - goto out_invalid_cdb_field; - sectors = transport_get_sectors_10(cdb, cmd, §or_ret); - if (sector_ret) - goto out_unsupported_cdb; - size = transport_get_size(sectors, cdb, cmd); - cmd->t_task_lba = transport_lba_32(cdb); - cmd->se_cmd_flags |= SCF_SCSI_DATA_SG_IO_CDB; - - /* - * Do now allow BIDI commands for passthrough mode. - */ - if (passthrough) - goto out_unsupported_cdb; - - /* - * Setup BIDI XOR callback to be run after I/O completion. - */ - cmd->transport_complete_callback = &transport_xor_callback; - if (cdb[1] & 0x8) - cmd->se_cmd_flags |= SCF_FUA; - break; - case VARIABLE_LENGTH_CMD: - service_action = get_unaligned_be16(&cdb[8]); - switch (service_action) { - case XDWRITEREAD_32: - sectors = transport_get_sectors_32(cdb, cmd, §or_ret); - if (sector_ret) - goto out_unsupported_cdb; - size = transport_get_size(sectors, cdb, cmd); - /* - * Use WRITE_32 and READ_32 opcodes for the emulated - * XDWRITE_READ_32 logic. - */ - cmd->t_task_lba = transport_lba_64_ext(cdb); - cmd->se_cmd_flags |= SCF_SCSI_DATA_SG_IO_CDB; - - /* - * Do now allow BIDI commands for passthrough mode. - */ - if (passthrough) - goto out_unsupported_cdb; - - /* - * Setup BIDI XOR callback to be run during after I/O - * completion. - */ - cmd->transport_complete_callback = &transport_xor_callback; - if (cdb[1] & 0x8) - cmd->se_cmd_flags |= SCF_FUA; - break; - case WRITE_SAME_32: - sectors = transport_get_sectors_32(cdb, cmd, §or_ret); - if (sector_ret) - goto out_unsupported_cdb; - - if (sectors) - size = transport_get_size(1, cdb, cmd); - else { - pr_err("WSNZ=1, WRITE_SAME w/sectors=0 not" - " supported\n"); - goto out_invalid_cdb_field; - } - - cmd->t_task_lba = get_unaligned_be64(&cdb[12]); - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - - if (target_check_write_same_discard(&cdb[10], dev) < 0) - goto out_unsupported_cdb; - if (!passthrough) - cmd->execute_cmd = target_emulate_write_same; - break; - default: - pr_err("VARIABLE_LENGTH_CMD service action" - " 0x%04x not supported\n", service_action); - goto out_unsupported_cdb; - } - break; - case MAINTENANCE_IN: - if (dev->transport->get_device_type(dev) != TYPE_ROM) { - /* MAINTENANCE_IN from SCC-2 */ - /* - * Check for emulated MI_REPORT_TARGET_PGS. - */ - if ((cdb[1] & 0x1f) == MI_REPORT_TARGET_PGS && - su_dev->t10_alua.alua_type == SPC3_ALUA_EMULATED) { - cmd->execute_cmd = - target_emulate_report_target_port_groups; - } - size = (cdb[6] << 24) | (cdb[7] << 16) | - (cdb[8] << 8) | cdb[9]; - } else { - /* GPCMD_SEND_KEY from multi media commands */ - size = (cdb[8] << 8) + cdb[9]; - } - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case MODE_SELECT: - size = cdb[4]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case MODE_SELECT_10: - size = (cdb[7] << 8) + cdb[8]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case MODE_SENSE: - size = cdb[4]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - if (!passthrough) - cmd->execute_cmd = target_emulate_modesense; - break; - case MODE_SENSE_10: - size = (cdb[7] << 8) + cdb[8]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - if (!passthrough) - cmd->execute_cmd = target_emulate_modesense; - break; - case GPCMD_READ_BUFFER_CAPACITY: - case GPCMD_SEND_OPC: - case LOG_SELECT: - case LOG_SENSE: - size = (cdb[7] << 8) + cdb[8]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case READ_BLOCK_LIMITS: - size = READ_BLOCK_LEN; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case GPCMD_GET_CONFIGURATION: - case GPCMD_READ_FORMAT_CAPACITIES: - case GPCMD_READ_DISC_INFO: - case GPCMD_READ_TRACK_RZONE_INFO: - size = (cdb[7] << 8) + cdb[8]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case PERSISTENT_RESERVE_IN: - if (su_dev->t10_pr.res_type == SPC3_PERSISTENT_RESERVATIONS) - cmd->execute_cmd = target_scsi3_emulate_pr_in; - size = (cdb[7] << 8) + cdb[8]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case PERSISTENT_RESERVE_OUT: - if (su_dev->t10_pr.res_type == SPC3_PERSISTENT_RESERVATIONS) - cmd->execute_cmd = target_scsi3_emulate_pr_out; - size = (cdb[7] << 8) + cdb[8]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case GPCMD_MECHANISM_STATUS: - case GPCMD_READ_DVD_STRUCTURE: - size = (cdb[8] << 8) + cdb[9]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case READ_POSITION: - size = READ_POSITION_LEN; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case MAINTENANCE_OUT: - if (dev->transport->get_device_type(dev) != TYPE_ROM) { - /* MAINTENANCE_OUT from SCC-2 - * - * Check for emulated MO_SET_TARGET_PGS. - */ - if (cdb[1] == MO_SET_TARGET_PGS && - su_dev->t10_alua.alua_type == SPC3_ALUA_EMULATED) { - cmd->execute_cmd = - target_emulate_set_target_port_groups; - } - - size = (cdb[6] << 24) | (cdb[7] << 16) | - (cdb[8] << 8) | cdb[9]; - } else { - /* GPCMD_REPORT_KEY from multi media commands */ - size = (cdb[8] << 8) + cdb[9]; - } - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case INQUIRY: - size = (cdb[3] << 8) + cdb[4]; - /* - * Do implict HEAD_OF_QUEUE processing for INQUIRY. - * See spc4r17 section 5.3 - */ - if (cmd->se_dev->dev_task_attr_type == SAM_TASK_ATTR_EMULATED) - cmd->sam_task_attr = MSG_HEAD_TAG; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - if (!passthrough) - cmd->execute_cmd = target_emulate_inquiry; - break; - case READ_BUFFER: - size = (cdb[6] << 16) + (cdb[7] << 8) + cdb[8]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case READ_CAPACITY: - size = READ_CAP_LEN; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - if (!passthrough) - cmd->execute_cmd = target_emulate_readcapacity; - break; - case READ_MEDIA_SERIAL_NUMBER: - case SECURITY_PROTOCOL_IN: - case SECURITY_PROTOCOL_OUT: - size = (cdb[6] << 24) | (cdb[7] << 16) | (cdb[8] << 8) | cdb[9]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case SERVICE_ACTION_IN: - switch (cmd->t_task_cdb[1] & 0x1f) { - case SAI_READ_CAPACITY_16: - if (!passthrough) - cmd->execute_cmd = - target_emulate_readcapacity_16; - break; - default: - if (passthrough) - break; - - pr_err("Unsupported SA: 0x%02x\n", - cmd->t_task_cdb[1] & 0x1f); - goto out_invalid_cdb_field; - } - /*FALLTHROUGH*/ - case ACCESS_CONTROL_IN: - case ACCESS_CONTROL_OUT: - case EXTENDED_COPY: - case READ_ATTRIBUTE: - case RECEIVE_COPY_RESULTS: - case WRITE_ATTRIBUTE: - size = (cdb[10] << 24) | (cdb[11] << 16) | - (cdb[12] << 8) | cdb[13]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case RECEIVE_DIAGNOSTIC: - case SEND_DIAGNOSTIC: - size = (cdb[3] << 8) | cdb[4]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; -/* #warning FIXME: Figure out correct GPCMD_READ_CD blocksize. */ -#if 0 - case GPCMD_READ_CD: - sectors = (cdb[6] << 16) + (cdb[7] << 8) + cdb[8]; - size = (2336 * sectors); - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; -#endif - case READ_TOC: - size = cdb[8]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case REQUEST_SENSE: - size = cdb[4]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - if (!passthrough) - cmd->execute_cmd = target_emulate_request_sense; - break; - case READ_ELEMENT_STATUS: - size = 65536 * cdb[7] + 256 * cdb[8] + cdb[9]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case WRITE_BUFFER: - size = (cdb[6] << 16) + (cdb[7] << 8) + cdb[8]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case RESERVE: - case RESERVE_10: - /* - * The SPC-2 RESERVE does not contain a size in the SCSI CDB. - * Assume the passthrough or $FABRIC_MOD will tell us about it. - */ - if (cdb[0] == RESERVE_10) - size = (cdb[7] << 8) | cdb[8]; - else - size = cmd->data_length; - - /* - * Setup the legacy emulated handler for SPC-2 and - * >= SPC-3 compatible reservation handling (CRH=1) - * Otherwise, we assume the underlying SCSI logic is - * is running in SPC_PASSTHROUGH, and wants reservations - * emulation disabled. - */ - if (su_dev->t10_pr.res_type != SPC_PASSTHROUGH) - cmd->execute_cmd = target_scsi2_reservation_reserve; - cmd->se_cmd_flags |= SCF_SCSI_NON_DATA_CDB; - break; - case RELEASE: - case RELEASE_10: - /* - * The SPC-2 RELEASE does not contain a size in the SCSI CDB. - * Assume the passthrough or $FABRIC_MOD will tell us about it. - */ - if (cdb[0] == RELEASE_10) - size = (cdb[7] << 8) | cdb[8]; - else - size = cmd->data_length; - - if (su_dev->t10_pr.res_type != SPC_PASSTHROUGH) - cmd->execute_cmd = target_scsi2_reservation_release; - cmd->se_cmd_flags |= SCF_SCSI_NON_DATA_CDB; - break; - case SYNCHRONIZE_CACHE: - case SYNCHRONIZE_CACHE_16: - /* - * Extract LBA and range to be flushed for emulated SYNCHRONIZE_CACHE - */ - if (cdb[0] == SYNCHRONIZE_CACHE) { - sectors = transport_get_sectors_10(cdb, cmd, §or_ret); - cmd->t_task_lba = transport_lba_32(cdb); - } else { - sectors = transport_get_sectors_16(cdb, cmd, §or_ret); - cmd->t_task_lba = transport_lba_64(cdb); - } - if (sector_ret) - goto out_unsupported_cdb; - - size = transport_get_size(sectors, cdb, cmd); - cmd->se_cmd_flags |= SCF_SCSI_NON_DATA_CDB; - - if (passthrough) + spin_lock(&dev->delayed_cmd_lock); + if (list_empty(&dev->delayed_cmd_list)) { + spin_unlock(&dev->delayed_cmd_lock); break; - - /* - * Check to ensure that LBA + Range does not exceed past end of - * device for IBLOCK and FILEIO ->do_sync_cache() backend calls - */ - if ((cmd->t_task_lba != 0) || (sectors != 0)) { - if (transport_cmd_get_valid_sectors(cmd) < 0) - goto out_invalid_cdb_field; - } - cmd->execute_cmd = target_emulate_synchronize_cache; - break; - case UNMAP: - size = get_unaligned_be16(&cdb[7]); - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - if (!passthrough) - cmd->execute_cmd = target_emulate_unmap; - break; - case WRITE_SAME_16: - sectors = transport_get_sectors_16(cdb, cmd, §or_ret); - if (sector_ret) - goto out_unsupported_cdb; - - if (sectors) - size = transport_get_size(1, cdb, cmd); - else { - pr_err("WSNZ=1, WRITE_SAME w/sectors=0 not supported\n"); - goto out_invalid_cdb_field; } - cmd->t_task_lba = get_unaligned_be64(&cdb[2]); - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - - if (target_check_write_same_discard(&cdb[1], dev) < 0) - goto out_unsupported_cdb; - if (!passthrough) - cmd->execute_cmd = target_emulate_write_same; - break; - case WRITE_SAME: - sectors = transport_get_sectors_10(cdb, cmd, §or_ret); - if (sector_ret) - goto out_unsupported_cdb; + cmd = list_entry(dev->delayed_cmd_list.next, + struct se_cmd, se_delayed_node); + list_del(&cmd->se_delayed_node); + spin_unlock(&dev->delayed_cmd_lock); - if (sectors) - size = transport_get_size(1, cdb, cmd); - else { - pr_err("WSNZ=1, WRITE_SAME w/sectors=0 not supported\n"); - goto out_invalid_cdb_field; - } + __target_execute_cmd(cmd); - cmd->t_task_lba = get_unaligned_be32(&cdb[2]); - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - /* - * Follow sbcr26 with WRITE_SAME (10) and check for the existence - * of byte 1 bit 3 UNMAP instead of original reserved field - */ - if (target_check_write_same_discard(&cdb[1], dev) < 0) - goto out_unsupported_cdb; - if (!passthrough) - cmd->execute_cmd = target_emulate_write_same; - break; - case ALLOW_MEDIUM_REMOVAL: - case ERASE: - case REZERO_UNIT: - case SEEK_10: - case SPACE: - case START_STOP: - case TEST_UNIT_READY: - case VERIFY: - case WRITE_FILEMARKS: - cmd->se_cmd_flags |= SCF_SCSI_NON_DATA_CDB; - if (!passthrough) - cmd->execute_cmd = target_emulate_noop; - break; - case GPCMD_CLOSE_TRACK: - case INITIALIZE_ELEMENT_STATUS: - case GPCMD_LOAD_UNLOAD: - case GPCMD_SET_SPEED: - case MOVE_MEDIUM: - cmd->se_cmd_flags |= SCF_SCSI_NON_DATA_CDB; - break; - case REPORT_LUNS: - cmd->execute_cmd = target_report_luns; - size = (cdb[6] << 24) | (cdb[7] << 16) | (cdb[8] << 8) | cdb[9]; - /* - * Do implict HEAD_OF_QUEUE processing for REPORT_LUNS - * See spc4r17 section 5.3 - */ - if (cmd->se_dev->dev_task_attr_type == SAM_TASK_ATTR_EMULATED) - cmd->sam_task_attr = MSG_HEAD_TAG; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case GET_EVENT_STATUS_NOTIFICATION: - size = (cdb[7] << 8) | cdb[8]; - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - case ATA_16: - /* Only support ATA passthrough to pSCSI backends.. */ - if (!passthrough) - goto out_unsupported_cdb; - - /* T_LENGTH */ - switch (cdb[2] & 0x3) { - case 0x0: - sectors = 0; - break; - case 0x1: - sectors = (((cdb[1] & 0x1) ? cdb[3] : 0) << 8) | cdb[4]; - break; - case 0x2: - sectors = (((cdb[1] & 0x1) ? cdb[5] : 0) << 8) | cdb[6]; + if (cmd->sam_task_attr == MSG_ORDERED_TAG) break; - case 0x3: - pr_err("T_LENGTH=0x3 not supported for ATA_16\n"); - goto out_invalid_cdb_field; - } - - /* BYTE_BLOCK */ - if (cdb[2] & 0x4) { - /* BLOCK T_TYPE: 512 or sector */ - size = sectors * ((cdb[2] & 0x10) ? - dev->se_sub_dev->se_dev_attrib.block_size : 512); - } else { - /* BYTE */ - size = sectors; - } - cmd->se_cmd_flags |= SCF_SCSI_CONTROL_SG_IO_CDB; - break; - default: - pr_warn("TARGET_CORE[%s]: Unsupported SCSI Opcode" - " 0x%02x, sending CHECK_CONDITION.\n", - cmd->se_tfo->get_fabric_name(), cdb[0]); - goto out_unsupported_cdb; - } - - if (cmd->unknown_data_length) - cmd->data_length = size; - - if (size != cmd->data_length) { - pr_warn("TARGET_CORE[%s]: Expected Transfer Length:" - " %u does not match SCSI CDB Length: %u for SAM Opcode:" - " 0x%02x\n", cmd->se_tfo->get_fabric_name(), - cmd->data_length, size, cdb[0]); - - cmd->cmd_spdtl = size; - - if (cmd->data_direction == DMA_TO_DEVICE) { - pr_err("Rejecting underflow/overflow" - " WRITE data\n"); - goto out_invalid_cdb_field; - } - /* - * Reject READ_* or WRITE_* with overflow/underflow for - * type SCF_SCSI_DATA_SG_IO_CDB. - */ - if (!ret && (dev->se_sub_dev->se_dev_attrib.block_size != 512)) { - pr_err("Failing OVERFLOW/UNDERFLOW for LBA op" - " CDB on non 512-byte sector setup subsystem" - " plugin: %s\n", dev->transport->name); - /* Returns CHECK_CONDITION + INVALID_CDB_FIELD */ - goto out_invalid_cdb_field; - } - - if (size > cmd->data_length) { - cmd->se_cmd_flags |= SCF_OVERFLOW_BIT; - cmd->residual_count = (size - cmd->data_length); - } else { - cmd->se_cmd_flags |= SCF_UNDERFLOW_BIT; - cmd->residual_count = (cmd->data_length - size); - } - cmd->data_length = size; } - - if (cmd->se_cmd_flags & SCF_SCSI_DATA_SG_IO_CDB) { - if (sectors > su_dev->se_dev_attrib.fabric_max_sectors) { - printk_ratelimited(KERN_ERR "SCSI OP %02xh with too" - " big sectors %u exceeds fabric_max_sectors:" - " %u\n", cdb[0], sectors, - su_dev->se_dev_attrib.fabric_max_sectors); - goto out_invalid_cdb_field; - } - if (sectors > su_dev->se_dev_attrib.hw_max_sectors) { - printk_ratelimited(KERN_ERR "SCSI OP %02xh with too" - " big sectors %u exceeds backend hw_max_sectors:" - " %u\n", cdb[0], sectors, - su_dev->se_dev_attrib.hw_max_sectors); - goto out_invalid_cdb_field; - } - } - - /* reject any command that we don't have a handler for */ - if (!(passthrough || cmd->execute_cmd || - (cmd->se_cmd_flags & SCF_SCSI_DATA_SG_IO_CDB))) - goto out_unsupported_cdb; - - transport_set_supported_SAM_opcode(cmd); - return ret; - -out_unsupported_cdb: - cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; - cmd->scsi_sense_reason = TCM_UNSUPPORTED_SCSI_OPCODE; - return -EINVAL; -out_invalid_cdb_field: - cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; - cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD; - return -EINVAL; } /* @@ -3052,8 +1906,6 @@ out_invalid_cdb_field: static void transport_complete_task_attr(struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; - struct se_cmd *cmd_p, *cmd_tmp; - int new_active_tasks = 0; if (cmd->sam_task_attr == MSG_SIMPLE_TAG) { atomic_dec(&dev->simple_cmds); @@ -3075,38 +1927,8 @@ static void transport_complete_task_attr(struct se_cmd *cmd) pr_debug("Incremented dev_cur_ordered_id: %u for ORDERED:" " %u\n", dev->dev_cur_ordered_id, cmd->se_ordered_id); } - /* - * Process all commands up to the last received - * ORDERED task attribute which requires another blocking - * boundary - */ - spin_lock(&dev->delayed_cmd_lock); - list_for_each_entry_safe(cmd_p, cmd_tmp, - &dev->delayed_cmd_list, se_delayed_node) { - - list_del(&cmd_p->se_delayed_node); - spin_unlock(&dev->delayed_cmd_lock); - - pr_debug("Calling add_tasks() for" - " cmd_p: 0x%02x Task Attr: 0x%02x" - " Dormant -> Active, se_ordered_id: %u\n", - cmd_p->t_task_cdb[0], - cmd_p->sam_task_attr, cmd_p->se_ordered_id); - target_add_to_execute_list(cmd_p); - new_active_tasks++; - - spin_lock(&dev->delayed_cmd_lock); - if (cmd_p->sam_task_attr == MSG_ORDERED_TAG) - break; - } - spin_unlock(&dev->delayed_cmd_lock); - /* - * If new tasks have become active, wake up the transport thread - * to do the processing of the Active tasks. - */ - if (new_active_tasks != 0) - wake_up_interruptible(&dev->dev_queue_obj.thread_wq); + target_restart_delayed_cmds(dev); } static void transport_complete_qf(struct se_cmd *cmd) @@ -3365,31 +2187,27 @@ int transport_generic_map_mem_to_cmd( if (!sgl || !sgl_count) return 0; - if ((cmd->se_cmd_flags & SCF_SCSI_DATA_SG_IO_CDB) || - (cmd->se_cmd_flags & SCF_SCSI_CONTROL_SG_IO_CDB)) { - /* - * Reject SCSI data overflow with map_mem_to_cmd() as incoming - * scatterlists already have been set to follow what the fabric - * passes for the original expected data transfer length. - */ - if (cmd->se_cmd_flags & SCF_OVERFLOW_BIT) { - pr_warn("Rejecting SCSI DATA overflow for fabric using" - " SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC\n"); - cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; - cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD; - return -EINVAL; - } + /* + * Reject SCSI data overflow with map_mem_to_cmd() as incoming + * scatterlists already have been set to follow what the fabric + * passes for the original expected data transfer length. + */ + if (cmd->se_cmd_flags & SCF_OVERFLOW_BIT) { + pr_warn("Rejecting SCSI DATA overflow for fabric using" + " SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC\n"); + cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; + cmd->scsi_sense_reason = TCM_INVALID_CDB_FIELD; + return -EINVAL; + } - cmd->t_data_sg = sgl; - cmd->t_data_nents = sgl_count; + cmd->t_data_sg = sgl; + cmd->t_data_nents = sgl_count; - if (sgl_bidi && sgl_bidi_count) { - cmd->t_bidi_data_sg = sgl_bidi; - cmd->t_bidi_data_nents = sgl_bidi_count; - } - cmd->se_cmd_flags |= SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC; + if (sgl_bidi && sgl_bidi_count) { + cmd->t_bidi_data_sg = sgl_bidi; + cmd->t_bidi_data_nents = sgl_bidi_count; } - + cmd->se_cmd_flags |= SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC; return 0; } EXPORT_SYMBOL(transport_generic_map_mem_to_cmd); @@ -3461,7 +2279,7 @@ transport_generic_get_mem(struct se_cmd *cmd) cmd->t_data_nents = nents; sg_init_table(cmd->t_data_sg, nents); - zero_flag = cmd->se_cmd_flags & SCF_SCSI_DATA_SG_IO_CDB ? 0 : __GFP_ZERO; + zero_flag = cmd->se_cmd_flags & SCF_SCSI_DATA_CDB ? 0 : __GFP_ZERO; while (length) { u32 page_len = min_t(u32, length, PAGE_SIZE); @@ -3492,7 +2310,6 @@ out: */ int transport_generic_new_cmd(struct se_cmd *cmd) { - struct se_device *dev = cmd->se_dev; int ret = 0; /* @@ -3508,8 +2325,7 @@ int transport_generic_new_cmd(struct se_cmd *cmd) } /* Workaround for handling zero-length control CDBs */ - if ((cmd->se_cmd_flags & SCF_SCSI_CONTROL_SG_IO_CDB) && - !cmd->data_length) { + if (!(cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) && !cmd->data_length) { spin_lock_irq(&cmd->t_state_lock); cmd->t_state = TRANSPORT_COMPLETE; cmd->transport_state |= CMD_T_ACTIVE; @@ -3527,52 +2343,45 @@ int transport_generic_new_cmd(struct se_cmd *cmd) return 0; } - if (cmd->se_cmd_flags & SCF_SCSI_DATA_SG_IO_CDB) { - struct se_dev_attrib *attr = &dev->se_sub_dev->se_dev_attrib; - - if (transport_cmd_get_valid_sectors(cmd) < 0) - return -EINVAL; - - BUG_ON(cmd->data_length % attr->block_size); - BUG_ON(DIV_ROUND_UP(cmd->data_length, attr->block_size) > - attr->hw_max_sectors); - } - atomic_inc(&cmd->t_fe_count); /* - * For WRITEs, let the fabric know its buffer is ready. - * - * The command will be added to the execution queue after its write - * data has arrived. + * If this command is not a write we can execute it right here, + * for write buffers we need to notify the fabric driver first + * and let it call back once the write buffers are ready. */ - if (cmd->data_direction == DMA_TO_DEVICE) { - target_add_to_state_list(cmd); - return transport_generic_write_pending(cmd); + target_add_to_state_list(cmd); + if (cmd->data_direction != DMA_TO_DEVICE) { + target_execute_cmd(cmd); + return 0; } - /* - * Everything else but a WRITE, add the command to the execution queue. - */ - transport_execute_tasks(cmd); - return 0; + + spin_lock_irq(&cmd->t_state_lock); + cmd->t_state = TRANSPORT_WRITE_PENDING; + spin_unlock_irq(&cmd->t_state_lock); + + transport_cmd_check_stop(cmd, false); + + ret = cmd->se_tfo->write_pending(cmd); + if (ret == -EAGAIN || ret == -ENOMEM) + goto queue_full; + + if (ret < 0) + return ret; + return 1; out_fail: cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; cmd->scsi_sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; return -EINVAL; +queue_full: + pr_debug("Handling write_pending QUEUE__FULL: se_cmd: %p\n", cmd); + cmd->t_state = TRANSPORT_COMPLETE_QF_WP; + transport_handle_queue_full(cmd, cmd->se_dev); + return 0; } EXPORT_SYMBOL(transport_generic_new_cmd); -/* transport_generic_process_write(): - * - * - */ -void transport_generic_process_write(struct se_cmd *cmd) -{ - transport_execute_tasks(cmd); -} -EXPORT_SYMBOL(transport_generic_process_write); - static void transport_write_pending_qf(struct se_cmd *cmd) { int ret; @@ -3585,43 +2394,6 @@ static void transport_write_pending_qf(struct se_cmd *cmd) } } -static int transport_generic_write_pending(struct se_cmd *cmd) -{ - unsigned long flags; - int ret; - - spin_lock_irqsave(&cmd->t_state_lock, flags); - cmd->t_state = TRANSPORT_WRITE_PENDING; - spin_unlock_irqrestore(&cmd->t_state_lock, flags); - - /* - * Clear the se_cmd for WRITE_PENDING status in order to set - * CMD_T_ACTIVE so that transport_generic_handle_data can be called - * from HW target mode interrupt code. This is safe to be called - * with transport_off=1 before the cmd->se_tfo->write_pending - * because the se_cmd->se_lun pointer is not being cleared. - */ - transport_cmd_check_stop(cmd, 1, 0); - - /* - * Call the fabric write_pending function here to let the - * frontend know that WRITE buffers are ready. - */ - ret = cmd->se_tfo->write_pending(cmd); - if (ret == -EAGAIN || ret == -ENOMEM) - goto queue_full; - else if (ret < 0) - return ret; - - return 1; - -queue_full: - pr_debug("Handling write_pending QUEUE__FULL: se_cmd: %p\n", cmd); - cmd->t_state = TRANSPORT_COMPLETE_QF_WP; - transport_handle_queue_full(cmd, cmd->se_dev); - return 0; -} - void transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks) { if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD)) { @@ -3648,10 +2420,11 @@ EXPORT_SYMBOL(transport_generic_free_cmd); * @se_cmd: command descriptor to add * @ack_kref: Signal that fabric will perform an ack target_put_sess_cmd() */ -void target_get_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd, - bool ack_kref) +static int target_get_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd, + bool ack_kref) { unsigned long flags; + int ret = 0; kref_init(&se_cmd->cmd_kref); /* @@ -3665,11 +2438,17 @@ void target_get_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd, } spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); + if (se_sess->sess_tearing_down) { + ret = -ESHUTDOWN; + goto out; + } list_add_tail(&se_cmd->se_cmd_list, &se_sess->sess_cmd_list); se_cmd->check_release = 1; + +out: spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); + return ret; } -EXPORT_SYMBOL(target_get_sess_cmd); static void target_release_cmd_kref(struct kref *kref) { @@ -3704,28 +2483,27 @@ int target_put_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd) } EXPORT_SYMBOL(target_put_sess_cmd); -/* target_splice_sess_cmd_list - Split active cmds into sess_wait_list - * @se_sess: session to split +/* target_sess_cmd_list_set_waiting - Flag all commands in + * sess_cmd_list to complete cmd_wait_comp. Set + * sess_tearing_down so no more commands are queued. + * @se_sess: session to flag */ -void target_splice_sess_cmd_list(struct se_session *se_sess) +void target_sess_cmd_list_set_waiting(struct se_session *se_sess) { struct se_cmd *se_cmd; unsigned long flags; - WARN_ON(!list_empty(&se_sess->sess_wait_list)); - INIT_LIST_HEAD(&se_sess->sess_wait_list); - spin_lock_irqsave(&se_sess->sess_cmd_lock, flags); - se_sess->sess_tearing_down = 1; - list_splice_init(&se_sess->sess_cmd_list, &se_sess->sess_wait_list); + WARN_ON(se_sess->sess_tearing_down); + se_sess->sess_tearing_down = 1; - list_for_each_entry(se_cmd, &se_sess->sess_wait_list, se_cmd_list) + list_for_each_entry(se_cmd, &se_sess->sess_cmd_list, se_cmd_list) se_cmd->cmd_wait_set = 1; spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); } -EXPORT_SYMBOL(target_splice_sess_cmd_list); +EXPORT_SYMBOL(target_sess_cmd_list_set_waiting); /* target_wait_for_sess_cmds - Wait for outstanding descriptors * @se_sess: session to wait for active I/O @@ -3739,7 +2517,7 @@ void target_wait_for_sess_cmds( bool rc = false; list_for_each_entry_safe(se_cmd, tmp_cmd, - &se_sess->sess_wait_list, se_cmd_list) { + &se_sess->sess_cmd_list, se_cmd_list) { list_del(&se_cmd->se_cmd_list); pr_debug("Waiting for se_cmd: %p t_state: %d, fabric state:" @@ -3791,26 +2569,20 @@ static int transport_lun_wait_for_tasks(struct se_cmd *cmd, struct se_lun *lun) pr_debug("ConfigFS ITT[0x%08x] - CMD_T_STOP, skipping\n", cmd->se_tfo->get_task_tag(cmd)); spin_unlock_irqrestore(&cmd->t_state_lock, flags); - transport_cmd_check_stop(cmd, 1, 0); + transport_cmd_check_stop(cmd, false); return -EPERM; } cmd->transport_state |= CMD_T_LUN_FE_STOP; spin_unlock_irqrestore(&cmd->t_state_lock, flags); - wake_up_interruptible(&cmd->se_dev->dev_queue_obj.thread_wq); - // XXX: audit task_flags checks. spin_lock_irqsave(&cmd->t_state_lock, flags); if ((cmd->transport_state & CMD_T_BUSY) && (cmd->transport_state & CMD_T_SENT)) { if (!target_stop_cmd(cmd, &flags)) ret++; - spin_unlock_irqrestore(&cmd->t_state_lock, flags); - } else { - spin_unlock_irqrestore(&cmd->t_state_lock, - flags); - target_remove_from_execute_list(cmd); } + spin_unlock_irqrestore(&cmd->t_state_lock, flags); pr_debug("ConfigFS: cmd: %p stop tasks ret:" " %d\n", cmd, ret); @@ -3821,7 +2593,6 @@ static int transport_lun_wait_for_tasks(struct se_cmd *cmd, struct se_lun *lun) pr_debug("ConfigFS: ITT[0x%08x] - stopped cmd....\n", cmd->se_tfo->get_task_tag(cmd)); } - transport_remove_cmd_from_queue(cmd); return 0; } @@ -3840,11 +2611,6 @@ static void __transport_clear_lun_from_sessions(struct se_lun *lun) struct se_cmd, se_lun_node); list_del_init(&cmd->se_lun_node); - /* - * This will notify iscsi_target_transport.c: - * transport_cmd_check_stop() that a LUN shutdown is in - * progress for the iscsi_cmd_t. - */ spin_lock(&cmd->t_state_lock); pr_debug("SE_LUN[%d] - Setting cmd->transport" "_lun_stop for ITT: 0x%08x\n", @@ -3911,7 +2677,7 @@ check_cond: spin_unlock_irqrestore(&cmd->t_state_lock, cmd_flags); - transport_cmd_check_stop(cmd, 1, 0); + transport_cmd_check_stop(cmd, false); complete(&cmd->transport_lun_fe_stop_comp); spin_lock_irqsave(&lun->lun_cmd_lock, lun_flags); continue; @@ -3967,10 +2733,7 @@ bool transport_wait_for_tasks(struct se_cmd *cmd) spin_unlock_irqrestore(&cmd->t_state_lock, flags); return false; } - /* - * Only perform a possible wait_for_tasks if SCF_SUPPORTED_SAM_OPCODE - * has been set in transport_set_supported_SAM_opcode(). - */ + if (!(cmd->se_cmd_flags & SCF_SUPPORTED_SAM_OPCODE) && !(cmd->se_cmd_flags & SCF_SCSI_TMR_CDB)) { spin_unlock_irqrestore(&cmd->t_state_lock, flags); @@ -4028,8 +2791,6 @@ bool transport_wait_for_tasks(struct se_cmd *cmd) spin_unlock_irqrestore(&cmd->t_state_lock, flags); - wake_up_interruptible(&cmd->se_dev->dev_queue_obj.thread_wq); - wait_for_completion(&cmd->t_transport_stop_comp); spin_lock_irqsave(&cmd->t_state_lock, flags); @@ -4212,6 +2973,15 @@ int transport_send_check_condition_and_sense( /* WRITE PROTECTED */ buffer[offset+SPC_ASC_KEY_OFFSET] = 0x27; break; + case TCM_ADDRESS_OUT_OF_RANGE: + /* CURRENT ERROR */ + buffer[offset] = 0x70; + buffer[offset+SPC_ADD_SENSE_LEN_OFFSET] = 10; + /* ILLEGAL REQUEST */ + buffer[offset+SPC_SENSE_KEY_OFFSET] = ILLEGAL_REQUEST; + /* LOGICAL BLOCK ADDRESS OUT OF RANGE */ + buffer[offset+SPC_ASC_KEY_OFFSET] = 0x21; + break; case TCM_CHECK_CONDITION_UNIT_ATTENTION: /* CURRENT ERROR */ buffer[offset] = 0x70; @@ -4312,8 +3082,9 @@ void transport_send_task_abort(struct se_cmd *cmd) cmd->se_tfo->queue_status(cmd); } -static int transport_generic_do_tmr(struct se_cmd *cmd) +static void target_tmr_work(struct work_struct *work) { + struct se_cmd *cmd = container_of(work, struct se_cmd, work); struct se_device *dev = cmd->se_dev; struct se_tmr_req *tmr = cmd->se_tmr_req; int ret; @@ -4349,80 +3120,13 @@ static int transport_generic_do_tmr(struct se_cmd *cmd) cmd->se_tfo->queue_tm_rsp(cmd); transport_cmd_check_stop_to_fabric(cmd); - return 0; } -/* transport_processing_thread(): - * - * - */ -static int transport_processing_thread(void *param) +int transport_generic_handle_tmr( + struct se_cmd *cmd) { - int ret; - struct se_cmd *cmd; - struct se_device *dev = param; - - while (!kthread_should_stop()) { - ret = wait_event_interruptible(dev->dev_queue_obj.thread_wq, - atomic_read(&dev->dev_queue_obj.queue_cnt) || - kthread_should_stop()); - if (ret < 0) - goto out; - -get_cmd: - cmd = transport_get_cmd_from_queue(&dev->dev_queue_obj); - if (!cmd) - continue; - - switch (cmd->t_state) { - case TRANSPORT_NEW_CMD: - BUG(); - break; - case TRANSPORT_NEW_CMD_MAP: - if (!cmd->se_tfo->new_cmd_map) { - pr_err("cmd->se_tfo->new_cmd_map is" - " NULL for TRANSPORT_NEW_CMD_MAP\n"); - BUG(); - } - ret = cmd->se_tfo->new_cmd_map(cmd); - if (ret < 0) { - transport_generic_request_failure(cmd); - break; - } - ret = transport_generic_new_cmd(cmd); - if (ret < 0) { - transport_generic_request_failure(cmd); - break; - } - break; - case TRANSPORT_PROCESS_WRITE: - transport_generic_process_write(cmd); - break; - case TRANSPORT_PROCESS_TMR: - transport_generic_do_tmr(cmd); - break; - case TRANSPORT_COMPLETE_QF_WP: - transport_write_pending_qf(cmd); - break; - case TRANSPORT_COMPLETE_QF_OK: - transport_complete_qf(cmd); - break; - default: - pr_err("Unknown t_state: %d for ITT: 0x%08x " - "i_state: %d on SE LUN: %u\n", - cmd->t_state, - cmd->se_tfo->get_task_tag(cmd), - cmd->se_tfo->get_cmd_state(cmd), - cmd->se_lun->unpacked_lun); - BUG(); - } - - goto get_cmd; - } - -out: - WARN_ON(!list_empty(&dev->state_list)); - WARN_ON(!list_empty(&dev->dev_queue_obj.qobj_list)); - dev->process_thread = NULL; + INIT_WORK(&cmd->work, target_tmr_work); + queue_work(cmd->se_dev->tmr_wq, &cmd->work); return 0; } +EXPORT_SYMBOL(transport_generic_handle_tmr); diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c index f03fb9730f5b..b9cb5006177e 100644 --- a/drivers/target/tcm_fc/tfc_cmd.c +++ b/drivers/target/tcm_fc/tfc_cmd.c @@ -215,7 +215,7 @@ int ft_write_pending(struct se_cmd *se_cmd) */ if ((ep->xid <= lport->lro_xid) && (fh->fh_r_ctl == FC_RCTL_DD_DATA_DESC)) { - if ((se_cmd->se_cmd_flags & SCF_SCSI_DATA_SG_IO_CDB) && + if ((se_cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) && lport->tt.ddp_target(lport, ep->xid, se_cmd->t_data_sg, se_cmd->t_data_nents)) @@ -230,6 +230,8 @@ u32 ft_get_task_tag(struct se_cmd *se_cmd) { struct ft_cmd *cmd = container_of(se_cmd, struct ft_cmd, se_cmd); + if (cmd->aborted) + return ~0; return fc_seq_exch(cmd->seq)->rxid; } @@ -541,9 +543,11 @@ static void ft_send_work(struct work_struct *work) * Use a single se_cmd->cmd_kref as we expect to release se_cmd * directly from ft_check_stop_free callback in response path. */ - target_submit_cmd(&cmd->se_cmd, cmd->sess->se_sess, fcp->fc_cdb, - &cmd->ft_sense_buffer[0], scsilun_to_int(&fcp->fc_lun), - ntohl(fcp->fc_dl), task_attr, data_dir, 0); + if (target_submit_cmd(&cmd->se_cmd, cmd->sess->se_sess, fcp->fc_cdb, + &cmd->ft_sense_buffer[0], scsilun_to_int(&fcp->fc_lun), + ntohl(fcp->fc_dl), task_attr, data_dir, 0)) + goto err; + pr_debug("r_ctl %x alloc target_submit_cmd\n", fh->fh_r_ctl); return; diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c index 071a505f98fc..ad36ede1a1ea 100644 --- a/drivers/target/tcm_fc/tfc_io.c +++ b/drivers/target/tcm_fc/tfc_io.c @@ -183,6 +183,13 @@ int ft_queue_data_in(struct se_cmd *se_cmd) return ft_queue_status(se_cmd); } +static void ft_execute_work(struct work_struct *work) +{ + struct ft_cmd *cmd = container_of(work, struct ft_cmd, work); + + target_execute_cmd(&cmd->se_cmd); +} + /* * Receive write data frame. */ @@ -307,8 +314,10 @@ void ft_recv_write_data(struct ft_cmd *cmd, struct fc_frame *fp) cmd->write_data_len += tlen; } last_frame: - if (cmd->write_data_len == se_cmd->data_length) - transport_generic_handle_data(se_cmd); + if (cmd->write_data_len == se_cmd->data_length) { + INIT_WORK(&cmd->work, ft_execute_work); + queue_work(cmd->sess->tport->tpg->workqueue, &cmd->work); + } drop: fc_frame_free(fp); } diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c index cb99da920068..87901fa74dd7 100644 --- a/drivers/target/tcm_fc/tfc_sess.c +++ b/drivers/target/tcm_fc/tfc_sess.c @@ -58,7 +58,8 @@ static struct ft_tport *ft_tport_create(struct fc_lport *lport) struct ft_tport *tport; int i; - tport = rcu_dereference(lport->prov[FC_TYPE_FCP]); + tport = rcu_dereference_protected(lport->prov[FC_TYPE_FCP], + lockdep_is_held(&ft_lport_lock)); if (tport && tport->tpg) return tport; diff --git a/drivers/tty/hvc/hvc_opal.c b/drivers/tty/hvc/hvc_opal.c index ced26c8ccd57..0d2ea0c224c3 100644 --- a/drivers/tty/hvc/hvc_opal.c +++ b/drivers/tty/hvc/hvc_opal.c @@ -401,7 +401,7 @@ out: } #ifdef CONFIG_PPC_EARLY_DEBUG_OPAL_RAW -void __init udbg_init_debug_opal(void) +void __init udbg_init_debug_opal_raw(void) { u32 index = CONFIG_PPC_EARLY_DEBUG_OPAL_VTERMNO; hvc_opal_privs[index] = &hvc_opal_boot_priv; diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 8fd398dffced..ee469274a3fe 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -500,6 +500,8 @@ retry: goto retry; } if (!desc->reslength) { /* zero length read */ + dev_dbg(&desc->intf->dev, "%s: zero length - clearing WDM_READ\n", __func__); + clear_bit(WDM_READ, &desc->flags); spin_unlock_irq(&desc->iuspin); goto retry; } diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 25a7422ee657..8fb484984c86 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2324,12 +2324,16 @@ static unsigned hub_is_wusb(struct usb_hub *hub) static int hub_port_reset(struct usb_hub *hub, int port1, struct usb_device *udev, unsigned int delay, bool warm); -/* Is a USB 3.0 port in the Inactive state? */ -static bool hub_port_inactive(struct usb_hub *hub, u16 portstatus) +/* Is a USB 3.0 port in the Inactive or Complinance Mode state? + * Port worm reset is required to recover + */ +static bool hub_port_warm_reset_required(struct usb_hub *hub, u16 portstatus) { return hub_is_superspeed(hub->hdev) && - (portstatus & USB_PORT_STAT_LINK_STATE) == - USB_SS_PORT_LS_SS_INACTIVE; + (((portstatus & USB_PORT_STAT_LINK_STATE) == + USB_SS_PORT_LS_SS_INACTIVE) || + ((portstatus & USB_PORT_STAT_LINK_STATE) == + USB_SS_PORT_LS_COMP_MOD)) ; } static int hub_port_wait_reset(struct usb_hub *hub, int port1, @@ -2365,7 +2369,7 @@ static int hub_port_wait_reset(struct usb_hub *hub, int port1, * * See https://bugzilla.kernel.org/show_bug.cgi?id=41752 */ - if (hub_port_inactive(hub, portstatus)) { + if (hub_port_warm_reset_required(hub, portstatus)) { int ret; if ((portchange & USB_PORT_STAT_C_CONNECTION)) @@ -4408,9 +4412,7 @@ static void hub_events(void) /* Warm reset a USB3 protocol port if it's in * SS.Inactive state. */ - if (hub_is_superspeed(hub->hdev) && - (portstatus & USB_PORT_STAT_LINK_STATE) - == USB_SS_PORT_LS_SS_INACTIVE) { + if (hub_port_warm_reset_required(hub, portstatus)) { dev_dbg(hub_dev, "warm reset port %d\n", i); hub_port_reset(hub, i, NULL, HUB_BH_RESET_TIME, true); diff --git a/drivers/usb/gadget/tcm_usb_gadget.c b/drivers/usb/gadget/tcm_usb_gadget.c index c46439c8dd74..5444866e13ef 100644 --- a/drivers/usb/gadget/tcm_usb_gadget.c +++ b/drivers/usb/gadget/tcm_usb_gadget.c @@ -294,7 +294,7 @@ static int bot_send_write_request(struct usbg_cmd *cmd) pr_err("%s(%d)\n", __func__, __LINE__); wait_for_completion(&cmd->write_complete); - transport_generic_process_write(se_cmd); + target_execute_cmd(se_cmd); cleanup: return ret; } @@ -725,7 +725,7 @@ static int uasp_send_write_request(struct usbg_cmd *cmd) } wait_for_completion(&cmd->write_complete); - transport_generic_process_write(se_cmd); + target_execute_cmd(se_cmd); cleanup: return ret; } @@ -1065,16 +1065,20 @@ static void usbg_cmd_work(struct work_struct *work) tv_nexus->tvn_se_sess->se_tpg->se_tpg_tfo, tv_nexus->tvn_se_sess, cmd->data_len, DMA_NONE, cmd->prio_attr, cmd->sense_iu.sense); - - transport_send_check_condition_and_sense(se_cmd, - TCM_UNSUPPORTED_SCSI_OPCODE, 1); - usbg_cleanup_cmd(cmd); - return; + goto out; } - target_submit_cmd(se_cmd, tv_nexus->tvn_se_sess, + if (target_submit_cmd(se_cmd, tv_nexus->tvn_se_sess, cmd->cmd_buf, cmd->sense_iu.sense, cmd->unpacked_lun, - 0, cmd->prio_attr, dir, TARGET_SCF_UNKNOWN_SIZE); + 0, cmd->prio_attr, dir, TARGET_SCF_UNKNOWN_SIZE) < 0) + goto out; + + return; + +out: + transport_send_check_condition_and_sense(se_cmd, + TCM_UNSUPPORTED_SCSI_OPCODE, 1); + usbg_cleanup_cmd(cmd); } static int usbg_submit_command(struct f_uas *fu, @@ -1177,16 +1181,20 @@ static void bot_cmd_work(struct work_struct *work) tv_nexus->tvn_se_sess->se_tpg->se_tpg_tfo, tv_nexus->tvn_se_sess, cmd->data_len, DMA_NONE, cmd->prio_attr, cmd->sense_iu.sense); - - transport_send_check_condition_and_sense(se_cmd, - TCM_UNSUPPORTED_SCSI_OPCODE, 1); - usbg_cleanup_cmd(cmd); - return; + goto out; } - target_submit_cmd(se_cmd, tv_nexus->tvn_se_sess, + if (target_submit_cmd(se_cmd, tv_nexus->tvn_se_sess, cmd->cmd_buf, cmd->sense_iu.sense, cmd->unpacked_lun, - cmd->data_len, cmd->prio_attr, dir, 0); + cmd->data_len, cmd->prio_attr, dir, 0) < 0) + goto out; + + return; + +out: + transport_send_check_condition_and_sense(se_cmd, + TCM_UNSUPPORTED_SCSI_OPCODE, 1); + usbg_cleanup_cmd(cmd); } static int bot_submit_command(struct f_uas *fu, @@ -1400,19 +1408,6 @@ static u32 usbg_tpg_get_inst_index(struct se_portal_group *se_tpg) return 1; } -static int usbg_new_cmd(struct se_cmd *se_cmd) -{ - struct usbg_cmd *cmd = container_of(se_cmd, struct usbg_cmd, - se_cmd); - int ret; - - ret = target_setup_cmd_from_cdb(se_cmd, cmd->cmd_buf); - if (ret) - return ret; - - return transport_generic_map_mem_to_cmd(se_cmd, NULL, 0, NULL, 0); -} - static void usbg_cmd_release(struct kref *ref) { struct usbg_cmd *cmd = container_of(ref, struct usbg_cmd, @@ -1902,7 +1897,6 @@ static struct target_core_fabric_ops usbg_ops = { .tpg_alloc_fabric_acl = usbg_alloc_fabric_acl, .tpg_release_fabric_acl = usbg_release_fabric_acl, .tpg_get_inst_index = usbg_tpg_get_inst_index, - .new_cmd_map = usbg_new_cmd, .release_cmd = usbg_release_cmd, .shutdown_session = usbg_shutdown_session, .close_session = usbg_close_session, diff --git a/drivers/usb/host/ehci-omap.c b/drivers/usb/host/ehci-omap.c index 17cfb8a1131c..c30435499a02 100644 --- a/drivers/usb/host/ehci-omap.c +++ b/drivers/usb/host/ehci-omap.c @@ -281,14 +281,13 @@ static int ehci_hcd_omap_probe(struct platform_device *pdev) } } + /* Hold PHYs in reset while initializing EHCI controller */ if (pdata->phy_reset) { if (gpio_is_valid(pdata->reset_gpio_port[0])) - gpio_request_one(pdata->reset_gpio_port[0], - GPIOF_OUT_INIT_LOW, "USB1 PHY reset"); + gpio_set_value_cansleep(pdata->reset_gpio_port[0], 0); if (gpio_is_valid(pdata->reset_gpio_port[1])) - gpio_request_one(pdata->reset_gpio_port[1], - GPIOF_OUT_INIT_LOW, "USB2 PHY reset"); + gpio_set_value_cansleep(pdata->reset_gpio_port[1], 0); /* Hold the PHY in RESET for enough time till DIR is high */ udelay(10); @@ -330,6 +329,11 @@ static int ehci_hcd_omap_probe(struct platform_device *pdev) omap_ehci->hcs_params = readl(&omap_ehci->caps->hcs_params); ehci_reset(omap_ehci); + ret = usb_add_hcd(hcd, irq, IRQF_SHARED); + if (ret) { + dev_err(dev, "failed to add hcd with err %d\n", ret); + goto err_add_hcd; + } if (pdata->phy_reset) { /* Hold the PHY in RESET for enough time till @@ -344,12 +348,6 @@ static int ehci_hcd_omap_probe(struct platform_device *pdev) gpio_set_value_cansleep(pdata->reset_gpio_port[1], 1); } - ret = usb_add_hcd(hcd, irq, IRQF_SHARED); - if (ret) { - dev_err(dev, "failed to add hcd with err %d\n", ret); - goto err_add_hcd; - } - /* root ports should always stay powered */ ehci_port_power(omap_ehci, 1); diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 2732ef660c5c..7b01094d7993 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -462,6 +462,42 @@ void xhci_test_and_clear_bit(struct xhci_hcd *xhci, __le32 __iomem **port_array, } } +/* Updates Link Status for super Speed port */ +static void xhci_hub_report_link_state(u32 *status, u32 status_reg) +{ + u32 pls = status_reg & PORT_PLS_MASK; + + /* resume state is a xHCI internal state. + * Do not report it to usb core. + */ + if (pls == XDEV_RESUME) + return; + + /* When the CAS bit is set then warm reset + * should be performed on port + */ + if (status_reg & PORT_CAS) { + /* The CAS bit can be set while the port is + * in any link state. + * Only roothubs have CAS bit, so we + * pretend to be in compliance mode + * unless we're already in compliance + * or the inactive state. + */ + if (pls != USB_SS_PORT_LS_COMP_MOD && + pls != USB_SS_PORT_LS_SS_INACTIVE) { + pls = USB_SS_PORT_LS_COMP_MOD; + } + /* Return also connection bit - + * hub state machine resets port + * when this bit is set. + */ + pls |= USB_PORT_STAT_CONNECTION; + } + /* update status field */ + *status |= pls; +} + int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, u16 wIndex, char *buf, u16 wLength) { @@ -606,13 +642,9 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, else status |= USB_PORT_STAT_POWER; } - /* Port Link State */ + /* Update Port Link State for super speed ports*/ if (hcd->speed == HCD_USB3) { - /* resume state is a xHCI internal state. - * Do not report it to usb core. - */ - if ((temp & PORT_PLS_MASK) != XDEV_RESUME) - status |= (temp & PORT_PLS_MASK); + xhci_hub_report_link_state(&status, temp); } if (bus_state->port_c_suspend & (1 << wIndex)) status |= 1 << USB_PORT_FEAT_C_SUSPEND; diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 23b4aefd1036..8275645889da 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -885,6 +885,17 @@ static void update_ring_for_set_deq_completion(struct xhci_hcd *xhci, num_trbs_free_temp = ep_ring->num_trbs_free; dequeue_temp = ep_ring->dequeue; + /* If we get two back-to-back stalls, and the first stalled transfer + * ends just before a link TRB, the dequeue pointer will be left on + * the link TRB by the code in the while loop. So we have to update + * the dequeue pointer one segment further, or we'll jump off + * the segment into la-la-land. + */ + if (last_trb(xhci, ep_ring, ep_ring->deq_seg, ep_ring->dequeue)) { + ep_ring->deq_seg = ep_ring->deq_seg->next; + ep_ring->dequeue = ep_ring->deq_seg->trbs; + } + while (ep_ring->dequeue != dev->eps[ep_index].queued_deq_ptr) { /* We have more usable TRBs */ ep_ring->num_trbs_free++; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index de3d6e3e57be..55c0785810c9 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -341,7 +341,11 @@ struct xhci_op_regs { #define PORT_PLC (1 << 22) /* port configure error change - port failed to configure its link partner */ #define PORT_CEC (1 << 23) -/* bit 24 reserved */ +/* Cold Attach Status - xHC can set this bit to report device attached during + * Sx state. Warm port reset should be perfomed to clear this bit and move port + * to connected state. + */ +#define PORT_CAS (1 << 24) /* wake on connect (enable) */ #define PORT_WKCONN_E (1 << 25) /* wake on disconnect (enable) */ diff --git a/drivers/usb/serial/metro-usb.c b/drivers/usb/serial/metro-usb.c index 81423f7361db..d47eb06fe463 100644 --- a/drivers/usb/serial/metro-usb.c +++ b/drivers/usb/serial/metro-usb.c @@ -222,14 +222,6 @@ static int metrousb_open(struct tty_struct *tty, struct usb_serial_port *port) metro_priv->throttled = 0; spin_unlock_irqrestore(&metro_priv->lock, flags); - /* - * Force low_latency on so that our tty_push actually forces the data - * through, otherwise it is scheduled, and with high data rates (like - * with OHCI) data can get lost. - */ - if (tty) - tty->low_latency = 1; - /* Clear the urb pipe. */ usb_clear_halt(serial->dev, port->interrupt_in_urb->pipe); diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index adf8ce72be50..417ab1b0aa30 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -497,6 +497,15 @@ static void option_instat_callback(struct urb *urb); /* MediaTek products */ #define MEDIATEK_VENDOR_ID 0x0e8d +#define MEDIATEK_PRODUCT_DC_1COM 0x00a0 +#define MEDIATEK_PRODUCT_DC_4COM 0x00a5 +#define MEDIATEK_PRODUCT_DC_5COM 0x00a4 +#define MEDIATEK_PRODUCT_7208_1COM 0x7101 +#define MEDIATEK_PRODUCT_7208_2COM 0x7102 +#define MEDIATEK_PRODUCT_FP_1COM 0x0003 +#define MEDIATEK_PRODUCT_FP_2COM 0x0023 +#define MEDIATEK_PRODUCT_FPDC_1COM 0x0043 +#define MEDIATEK_PRODUCT_FPDC_2COM 0x0033 /* Cellient products */ #define CELLIENT_VENDOR_ID 0x2692 @@ -554,6 +563,10 @@ static const struct option_blacklist_info net_intf1_blacklist = { .reserved = BIT(1), }; +static const struct option_blacklist_info net_intf2_blacklist = { + .reserved = BIT(2), +}; + static const struct option_blacklist_info net_intf3_blacklist = { .reserved = BIT(3), }; @@ -1099,6 +1112,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1298, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1299, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1300, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1402, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&net_intf2_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x2002, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t)&zte_k3765_z_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x2003, 0xff, 0xff, 0xff) }, @@ -1240,6 +1255,17 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, 0x00a1, 0xff, 0x02, 0x01) }, { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, 0x00a2, 0xff, 0x00, 0x00) }, { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, 0x00a2, 0xff, 0x02, 0x01) }, /* MediaTek MT6276M modem & app port */ + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_DC_1COM, 0x0a, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_DC_5COM, 0xff, 0x02, 0x01) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_DC_5COM, 0xff, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_DC_4COM, 0xff, 0x02, 0x01) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_DC_4COM, 0xff, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_7208_1COM, 0x02, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_7208_2COM, 0x02, 0x02, 0x01) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_FP_1COM, 0x0a, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_FP_2COM, 0x0a, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_FPDC_1COM, 0x0a, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_FPDC_2COM, 0x0a, 0x00, 0x00) }, { USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MEN200) }, { } /* Terminating entry */ }; diff --git a/drivers/video/omap2/dss/core.c b/drivers/video/omap2/dss/core.c index 5066eee10ccf..58bd9c27369d 100644 --- a/drivers/video/omap2/dss/core.c +++ b/drivers/video/omap2/dss/core.c @@ -32,6 +32,7 @@ #include <linux/io.h> #include <linux/device.h> #include <linux/regulator/consumer.h> +#include <linux/suspend.h> #include <video/omapdss.h> @@ -201,6 +202,28 @@ int dss_debugfs_create_file(const char *name, void (*write)(struct seq_file *)) #endif /* CONFIG_DEBUG_FS && CONFIG_OMAP2_DSS_DEBUG_SUPPORT */ /* PLATFORM DEVICE */ +static int omap_dss_pm_notif(struct notifier_block *b, unsigned long v, void *d) +{ + DSSDBG("pm notif %lu\n", v); + + switch (v) { + case PM_SUSPEND_PREPARE: + DSSDBG("suspending displays\n"); + return dss_suspend_all_devices(); + + case PM_POST_SUSPEND: + DSSDBG("resuming displays\n"); + return dss_resume_all_devices(); + + default: + return 0; + } +} + +static struct notifier_block omap_dss_pm_notif_block = { + .notifier_call = omap_dss_pm_notif, +}; + static int __init omap_dss_probe(struct platform_device *pdev) { struct omap_dss_board_info *pdata = pdev->dev.platform_data; @@ -224,6 +247,8 @@ static int __init omap_dss_probe(struct platform_device *pdev) else if (pdata->default_device) core.default_display_name = pdata->default_device->name; + register_pm_notifier(&omap_dss_pm_notif_block); + return 0; err_debugfs: @@ -233,6 +258,8 @@ err_debugfs: static int omap_dss_remove(struct platform_device *pdev) { + unregister_pm_notifier(&omap_dss_pm_notif_block); + dss_uninitialize_debugfs(); dss_uninit_overlays(pdev); @@ -247,25 +274,9 @@ static void omap_dss_shutdown(struct platform_device *pdev) dss_disable_all_devices(); } -static int omap_dss_suspend(struct platform_device *pdev, pm_message_t state) -{ - DSSDBG("suspend %d\n", state.event); - - return dss_suspend_all_devices(); -} - -static int omap_dss_resume(struct platform_device *pdev) -{ - DSSDBG("resume\n"); - - return dss_resume_all_devices(); -} - static struct platform_driver omap_dss_driver = { .remove = omap_dss_remove, .shutdown = omap_dss_shutdown, - .suspend = omap_dss_suspend, - .resume = omap_dss_resume, .driver = { .name = "omapdss", .owner = THIS_MODULE, diff --git a/drivers/video/omap2/dss/dispc.c b/drivers/video/omap2/dss/dispc.c index 4749ac356469..397d4eee11bb 100644 --- a/drivers/video/omap2/dss/dispc.c +++ b/drivers/video/omap2/dss/dispc.c @@ -384,7 +384,7 @@ void dispc_runtime_put(void) DSSDBG("dispc_runtime_put\n"); r = pm_runtime_put_sync(&dispc.pdev->dev); - WARN_ON(r < 0); + WARN_ON(r < 0 && r != -ENOSYS); } static inline bool dispc_mgr_is_lcd(enum omap_channel channel) diff --git a/drivers/video/omap2/dss/dsi.c b/drivers/video/omap2/dss/dsi.c index ca8382d346e9..14ce8cc079e3 100644 --- a/drivers/video/omap2/dss/dsi.c +++ b/drivers/video/omap2/dss/dsi.c @@ -1075,7 +1075,7 @@ void dsi_runtime_put(struct platform_device *dsidev) DSSDBG("dsi_runtime_put\n"); r = pm_runtime_put_sync(&dsi->pdev->dev); - WARN_ON(r < 0); + WARN_ON(r < 0 && r != -ENOSYS); } /* source clock for DSI PLL. this could also be PCLKFREE */ diff --git a/drivers/video/omap2/dss/dss.c b/drivers/video/omap2/dss/dss.c index 770632359a17..d2b57197b292 100644 --- a/drivers/video/omap2/dss/dss.c +++ b/drivers/video/omap2/dss/dss.c @@ -731,7 +731,7 @@ static void dss_runtime_put(void) DSSDBG("dss_runtime_put\n"); r = pm_runtime_put_sync(&dss.pdev->dev); - WARN_ON(r < 0 && r != -EBUSY); + WARN_ON(r < 0 && r != -ENOSYS && r != -EBUSY); } /* DEBUGFS */ diff --git a/drivers/video/omap2/dss/hdmi.c b/drivers/video/omap2/dss/hdmi.c index 8195c7166d20..26a2430a7028 100644 --- a/drivers/video/omap2/dss/hdmi.c +++ b/drivers/video/omap2/dss/hdmi.c @@ -138,7 +138,7 @@ static void hdmi_runtime_put(void) DSSDBG("hdmi_runtime_put\n"); r = pm_runtime_put_sync(&hdmi.pdev->dev); - WARN_ON(r < 0); + WARN_ON(r < 0 && r != -ENOSYS); } static int __init hdmi_init_display(struct omap_dss_device *dssdev) diff --git a/drivers/video/omap2/dss/rfbi.c b/drivers/video/omap2/dss/rfbi.c index 3d8c206e90e5..7985fa12b9b4 100644 --- a/drivers/video/omap2/dss/rfbi.c +++ b/drivers/video/omap2/dss/rfbi.c @@ -141,7 +141,7 @@ static void rfbi_runtime_put(void) DSSDBG("rfbi_runtime_put\n"); r = pm_runtime_put_sync(&rfbi.pdev->dev); - WARN_ON(r < 0); + WARN_ON(r < 0 && r != -ENOSYS); } void rfbi_bus_lock(void) diff --git a/drivers/video/omap2/dss/venc.c b/drivers/video/omap2/dss/venc.c index 2b8973931ff4..3907c8b6ecbc 100644 --- a/drivers/video/omap2/dss/venc.c +++ b/drivers/video/omap2/dss/venc.c @@ -402,7 +402,7 @@ static void venc_runtime_put(void) DSSDBG("venc_runtime_put\n"); r = pm_runtime_put_sync(&venc.pdev->dev); - WARN_ON(r < 0); + WARN_ON(r < 0 && r != -ENOSYS); } static const struct venc_config *venc_timings_to_config( diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index bfbc15ca38dd..0908e6044333 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -47,7 +47,7 @@ struct virtio_balloon struct task_struct *thread; /* Waiting for host to ack the pages we released. */ - struct completion acked; + wait_queue_head_t acked; /* Number of balloon pages we've told the Host we're not using. */ unsigned int num_pages; @@ -89,29 +89,25 @@ static struct page *balloon_pfn_to_page(u32 pfn) static void balloon_ack(struct virtqueue *vq) { - struct virtio_balloon *vb; - unsigned int len; + struct virtio_balloon *vb = vq->vdev->priv; - vb = virtqueue_get_buf(vq, &len); - if (vb) - complete(&vb->acked); + wake_up(&vb->acked); } static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq) { struct scatterlist sg; + unsigned int len; sg_init_one(&sg, vb->pfns, sizeof(vb->pfns[0]) * vb->num_pfns); - init_completion(&vb->acked); - /* We should always be able to add one buffer to an empty queue. */ if (virtqueue_add_buf(vq, &sg, 1, 0, vb, GFP_KERNEL) < 0) BUG(); virtqueue_kick(vq); /* When host has read buffer, this completes via balloon_ack */ - wait_for_completion(&vb->acked); + wait_event(vb->acked, virtqueue_get_buf(vq, &len)); } static void set_page_pfns(u32 pfns[], struct page *page) @@ -231,12 +227,8 @@ static void update_balloon_stats(struct virtio_balloon *vb) */ static void stats_request(struct virtqueue *vq) { - struct virtio_balloon *vb; - unsigned int len; + struct virtio_balloon *vb = vq->vdev->priv; - vb = virtqueue_get_buf(vq, &len); - if (!vb) - return; vb->need_stats_update = 1; wake_up(&vb->config_change); } @@ -245,11 +237,14 @@ static void stats_handle_request(struct virtio_balloon *vb) { struct virtqueue *vq; struct scatterlist sg; + unsigned int len; vb->need_stats_update = 0; update_balloon_stats(vb); vq = vb->stats_vq; + if (!virtqueue_get_buf(vq, &len)) + return; sg_init_one(&sg, vb->stats, sizeof(vb->stats)); if (virtqueue_add_buf(vq, &sg, 1, 0, vb, GFP_KERNEL) < 0) BUG(); @@ -358,6 +353,7 @@ static int virtballoon_probe(struct virtio_device *vdev) INIT_LIST_HEAD(&vb->pages); vb->num_pages = 0; init_waitqueue_head(&vb->config_change); + init_waitqueue_head(&vb->acked); vb->vdev = vdev; vb->need_stats_update = 0; diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index e78956cbd702..34c59f14a1c9 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -144,7 +144,7 @@ extern void v9fs_session_close(struct v9fs_session_info *v9ses); extern void v9fs_session_cancel(struct v9fs_session_info *v9ses); extern void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses); extern struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nameidata); + unsigned int flags); extern int v9fs_vfs_unlink(struct inode *i, struct dentry *d); extern int v9fs_vfs_rmdir(struct inode *i, struct dentry *d); extern int v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry, diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index d529437ff442..64600b5d0522 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -100,13 +100,13 @@ static void v9fs_dentry_release(struct dentry *dentry) } } -static int v9fs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) +static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) { struct p9_fid *fid; struct inode *inode; struct v9fs_inode *v9inode; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; inode = dentry->d_inode; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 57ccb7537dae..cbf9dbb1b2a2 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -712,88 +712,34 @@ error: } /** - * v9fs_vfs_create - VFS hook to create files + * v9fs_vfs_create - VFS hook to create a regular file + * + * open(.., O_CREAT) is handled in v9fs_vfs_atomic_open(). This is only called + * for mknod(2). + * * @dir: directory inode that is being created * @dentry: dentry that is being deleted * @mode: create permissions - * @nd: path information * */ static int v9fs_vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { - int err; - u32 perm; - int flags; - struct file *filp; - struct v9fs_inode *v9inode; - struct v9fs_session_info *v9ses; - struct p9_fid *fid, *inode_fid; - - err = 0; - fid = NULL; - v9ses = v9fs_inode2v9ses(dir); - perm = unixmode2p9mode(v9ses, mode); - if (nd) - flags = nd->intent.open.flags; - else - flags = O_RDWR; + struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir); + u32 perm = unixmode2p9mode(v9ses, mode); + struct p9_fid *fid; - fid = v9fs_create(v9ses, dir, dentry, NULL, perm, - v9fs_uflags2omode(flags, - v9fs_proto_dotu(v9ses))); - if (IS_ERR(fid)) { - err = PTR_ERR(fid); - fid = NULL; - goto error; - } + /* P9_OEXCL? */ + fid = v9fs_create(v9ses, dir, dentry, NULL, perm, P9_ORDWR); + if (IS_ERR(fid)) + return PTR_ERR(fid); v9fs_invalidate_inode_attr(dir); - /* if we are opening a file, assign the open fid to the file */ - if (nd) { - v9inode = V9FS_I(dentry->d_inode); - mutex_lock(&v9inode->v_mutex); - if (v9ses->cache && !v9inode->writeback_fid && - ((flags & O_ACCMODE) != O_RDONLY)) { - /* - * clone a fid and add it to writeback_fid - * we do it during open time instead of - * page dirty time via write_begin/page_mkwrite - * because we want write after unlink usecase - * to work. - */ - inode_fid = v9fs_writeback_fid(dentry); - if (IS_ERR(inode_fid)) { - err = PTR_ERR(inode_fid); - mutex_unlock(&v9inode->v_mutex); - goto error; - } - v9inode->writeback_fid = (void *) inode_fid; - } - mutex_unlock(&v9inode->v_mutex); - filp = lookup_instantiate_filp(nd, dentry, generic_file_open); - if (IS_ERR(filp)) { - err = PTR_ERR(filp); - goto error; - } - - filp->private_data = fid; -#ifdef CONFIG_9P_FSCACHE - if (v9ses->cache) - v9fs_cache_inode_set_cookie(dentry->d_inode, filp); -#endif - } else - p9_client_clunk(fid); + p9_client_clunk(fid); return 0; - -error: - if (fid) - p9_client_clunk(fid); - - return err; } /** @@ -839,7 +785,7 @@ static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode */ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nameidata) + unsigned int flags) { struct dentry *res; struct super_block *sb; @@ -849,8 +795,8 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, char *name; int result = 0; - p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%s) %p nameidata: %p\n", - dir, dentry->d_name.name, dentry, nameidata); + p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%s) %p flags: %x\n", + dir, dentry->d_name.name, dentry, flags); if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); @@ -910,6 +856,86 @@ error: return ERR_PTR(result); } +static int +v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned flags, umode_t mode, + int *opened) +{ + int err; + u32 perm; + struct v9fs_inode *v9inode; + struct v9fs_session_info *v9ses; + struct p9_fid *fid, *inode_fid; + struct dentry *res = NULL; + + if (d_unhashed(dentry)) { + res = v9fs_vfs_lookup(dir, dentry, 0); + if (IS_ERR(res)) + return PTR_ERR(res); + + if (res) + dentry = res; + } + + /* Only creates */ + if (!(flags & O_CREAT) || dentry->d_inode) + return finish_no_open(file, res); + + err = 0; + fid = NULL; + v9ses = v9fs_inode2v9ses(dir); + perm = unixmode2p9mode(v9ses, mode); + fid = v9fs_create(v9ses, dir, dentry, NULL, perm, + v9fs_uflags2omode(flags, + v9fs_proto_dotu(v9ses))); + if (IS_ERR(fid)) { + err = PTR_ERR(fid); + fid = NULL; + goto error; + } + + v9fs_invalidate_inode_attr(dir); + v9inode = V9FS_I(dentry->d_inode); + mutex_lock(&v9inode->v_mutex); + if (v9ses->cache && !v9inode->writeback_fid && + ((flags & O_ACCMODE) != O_RDONLY)) { + /* + * clone a fid and add it to writeback_fid + * we do it during open time instead of + * page dirty time via write_begin/page_mkwrite + * because we want write after unlink usecase + * to work. + */ + inode_fid = v9fs_writeback_fid(dentry); + if (IS_ERR(inode_fid)) { + err = PTR_ERR(inode_fid); + mutex_unlock(&v9inode->v_mutex); + goto error; + } + v9inode->writeback_fid = (void *) inode_fid; + } + mutex_unlock(&v9inode->v_mutex); + err = finish_open(file, dentry, generic_file_open, opened); + if (err) + goto error; + + file->private_data = fid; +#ifdef CONFIG_9P_FSCACHE + if (v9ses->cache) + v9fs_cache_inode_set_cookie(dentry->d_inode, file); +#endif + + *opened |= FILE_CREATED; +out: + dput(res); + return err; + +error: + if (fid) + p9_client_clunk(fid); + goto out; +} + /** * v9fs_vfs_unlink - VFS unlink hook to delete an inode * @i: inode that is being unlinked @@ -1488,6 +1514,7 @@ out: static const struct inode_operations v9fs_dir_inode_operations_dotu = { .create = v9fs_vfs_create, .lookup = v9fs_vfs_lookup, + .atomic_open = v9fs_vfs_atomic_open, .symlink = v9fs_vfs_symlink, .link = v9fs_vfs_link, .unlink = v9fs_vfs_unlink, @@ -1502,6 +1529,7 @@ static const struct inode_operations v9fs_dir_inode_operations_dotu = { static const struct inode_operations v9fs_dir_inode_operations = { .create = v9fs_vfs_create, .lookup = v9fs_vfs_lookup, + .atomic_open = v9fs_vfs_atomic_open, .unlink = v9fs_vfs_unlink, .mkdir = v9fs_vfs_mkdir, .rmdir = v9fs_vfs_rmdir, diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index e3dd2a1e2bfc..40895546e103 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -230,20 +230,25 @@ int v9fs_open_to_dotl_flags(int flags) * @dir: directory inode that is being created * @dentry: dentry that is being deleted * @mode: create permissions - * @nd: path information * */ static int v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, - struct nameidata *nd) + bool excl) +{ + return v9fs_vfs_mknod_dotl(dir, dentry, omode, 0); +} + +static int +v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned flags, umode_t omode, + int *opened) { int err = 0; gid_t gid; - int flags; umode_t mode; char *name = NULL; - struct file *filp; struct p9_qid qid; struct inode *inode; struct p9_fid *fid = NULL; @@ -251,19 +256,23 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, struct p9_fid *dfid, *ofid, *inode_fid; struct v9fs_session_info *v9ses; struct posix_acl *pacl = NULL, *dacl = NULL; + struct dentry *res = NULL; - v9ses = v9fs_inode2v9ses(dir); - if (nd) - flags = nd->intent.open.flags; - else { - /* - * create call without LOOKUP_OPEN is due - * to mknod of regular files. So use mknod - * operation. - */ - return v9fs_vfs_mknod_dotl(dir, dentry, omode, 0); + if (d_unhashed(dentry)) { + res = v9fs_vfs_lookup(dir, dentry, 0); + if (IS_ERR(res)) + return PTR_ERR(res); + + if (res) + dentry = res; } + /* Only creates */ + if (!(flags & O_CREAT) || dentry->d_inode) + return finish_no_open(file, res); + + v9ses = v9fs_inode2v9ses(dir); + name = (char *) dentry->d_name.name; p9_debug(P9_DEBUG_VFS, "name:%s flags:0x%x mode:0x%hx\n", name, flags, omode); @@ -272,7 +281,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, if (IS_ERR(dfid)) { err = PTR_ERR(dfid); p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err); - return err; + goto out; } /* clone a fid to use for creation */ @@ -280,7 +289,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, if (IS_ERR(ofid)) { err = PTR_ERR(ofid); p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err); - return err; + goto out; } gid = v9fs_get_fsgid_for_create(dir); @@ -345,17 +354,18 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, } mutex_unlock(&v9inode->v_mutex); /* Since we are opening a file, assign the open fid to the file */ - filp = lookup_instantiate_filp(nd, dentry, generic_file_open); - if (IS_ERR(filp)) { - err = PTR_ERR(filp); + err = finish_open(file, dentry, generic_file_open, opened); + if (err) goto err_clunk_old_fid; - } - filp->private_data = ofid; + file->private_data = ofid; #ifdef CONFIG_9P_FSCACHE if (v9ses->cache) - v9fs_cache_inode_set_cookie(inode, filp); + v9fs_cache_inode_set_cookie(inode, file); #endif - return 0; + *opened |= FILE_CREATED; +out: + dput(res); + return err; error: if (fid) @@ -364,7 +374,7 @@ err_clunk_old_fid: if (ofid) p9_client_clunk(ofid); v9fs_set_create_acl(NULL, &dacl, &pacl); - return err; + goto out; } /** @@ -982,6 +992,7 @@ out: const struct inode_operations v9fs_dir_inode_operations_dotl = { .create = v9fs_vfs_create_dotl, + .atomic_open = v9fs_vfs_atomic_open_dotl, .lookup = v9fs_vfs_lookup, .link = v9fs_vfs_link_dotl, .symlink = v9fs_vfs_symlink_dotl, diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 8c92a9ba8330..137d50396898 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -89,7 +89,7 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses, if (v9ses->cache) sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_CACHE_SIZE; - sb->s_flags = flags | MS_ACTIVE | MS_DIRSYNC | MS_NOATIME; + sb->s_flags |= MS_ACTIVE | MS_DIRSYNC | MS_NOATIME; if (!v9ses->cache) sb->s_flags |= MS_SYNCHRONOUS; @@ -137,7 +137,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, goto close_session; } - sb = sget(fs_type, NULL, v9fs_set_super, v9ses); + sb = sget(fs_type, NULL, v9fs_set_super, flags, v9ses); if (IS_ERR(sb)) { retval = PTR_ERR(sb); goto clunk_fid; diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c index 3d83075aaa2e..b3be2e7c5643 100644 --- a/fs/adfs/dir.c +++ b/fs/adfs/dir.c @@ -266,7 +266,7 @@ const struct dentry_operations adfs_dentry_operations = { }; static struct dentry * -adfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +adfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode = NULL; struct object_info obj; diff --git a/fs/adfs/super.c b/fs/adfs/super.c index 06fdcc9382c4..bdaec92353c2 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -246,7 +246,6 @@ static struct inode *adfs_alloc_inode(struct super_block *sb) static void adfs_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); - INIT_LIST_HEAD(&inode->i_dentry); kmem_cache_free(adfs_inode_cachep, ADFS_I(inode)); } diff --git a/fs/affs/affs.h b/fs/affs/affs.h index 1fceb320d2f2..6e216419f340 100644 --- a/fs/affs/affs.h +++ b/fs/affs/affs.h @@ -3,6 +3,7 @@ #include <linux/buffer_head.h> #include <linux/amigaffs.h> #include <linux/mutex.h> +#include <linux/workqueue.h> /* AmigaOS allows file names with up to 30 characters length. * Names longer than that will be silently truncated. If you @@ -100,6 +101,10 @@ struct affs_sb_info { char *s_prefix; /* Prefix for volumes and assigns. */ char s_volume[32]; /* Volume prefix for absolute symlinks. */ spinlock_t symlink_lock; /* protects the previous two */ + struct super_block *sb; /* the VFS superblock object */ + int work_queued; /* non-zero delayed work is queued */ + struct delayed_work sb_work; /* superblock flush delayed work */ + spinlock_t work_lock; /* protects sb_work and work_queued */ }; #define SF_INTL 0x0001 /* International filesystem. */ @@ -120,6 +125,8 @@ static inline struct affs_sb_info *AFFS_SB(struct super_block *sb) return sb->s_fs_info; } +void affs_mark_sb_dirty(struct super_block *sb); + /* amigaffs.c */ extern int affs_insert_hash(struct inode *inode, struct buffer_head *bh); @@ -146,9 +153,9 @@ extern void affs_free_bitmap(struct super_block *sb); /* namei.c */ extern int affs_hash_name(struct super_block *sb, const u8 *name, unsigned int len); -extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *); +extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int); extern int affs_unlink(struct inode *dir, struct dentry *dentry); -extern int affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *); +extern int affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool); extern int affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); extern int affs_rmdir(struct inode *dir, struct dentry *dentry); extern int affs_link(struct dentry *olddentry, struct inode *dir, diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index 52a6407682e6..eb82ee53ee0b 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -122,22 +122,16 @@ affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh) } static void -affs_fix_dcache(struct dentry *dentry, u32 entry_ino) +affs_fix_dcache(struct inode *inode, u32 entry_ino) { - struct inode *inode = dentry->d_inode; - void *data = dentry->d_fsdata; - struct list_head *head, *next; - + struct dentry *dentry; + struct hlist_node *p; spin_lock(&inode->i_lock); - head = &inode->i_dentry; - next = head->next; - while (next != head) { - dentry = list_entry(next, struct dentry, d_alias); + hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { if (entry_ino == (u32)(long)dentry->d_fsdata) { - dentry->d_fsdata = data; + dentry->d_fsdata = (void *)inode->i_ino; break; } - next = next->next; } spin_unlock(&inode->i_lock); } @@ -177,7 +171,11 @@ affs_remove_link(struct dentry *dentry) } affs_lock_dir(dir); - affs_fix_dcache(dentry, link_ino); + /* + * if there's a dentry for that block, make it + * refer to inode itself. + */ + affs_fix_dcache(inode, link_ino); retval = affs_remove_hash(dir, link_bh); if (retval) { affs_unlock_dir(dir); diff --git a/fs/affs/bitmap.c b/fs/affs/bitmap.c index 3e262711ae06..6e0be43ef6ef 100644 --- a/fs/affs/bitmap.c +++ b/fs/affs/bitmap.c @@ -103,7 +103,7 @@ affs_free_block(struct super_block *sb, u32 block) *(__be32 *)bh->b_data = cpu_to_be32(tmp - mask); mark_buffer_dirty(bh); - sb->s_dirt = 1; + affs_mark_sb_dirty(sb); bm->bm_free++; mutex_unlock(&sbi->s_bmlock); @@ -248,7 +248,7 @@ find_bit: *(__be32 *)bh->b_data = cpu_to_be32(tmp + mask); mark_buffer_dirty(bh); - sb->s_dirt = 1; + affs_mark_sb_dirty(sb); mutex_unlock(&sbi->s_bmlock); diff --git a/fs/affs/namei.c b/fs/affs/namei.c index 47806940aac0..ff65884a7839 100644 --- a/fs/affs/namei.c +++ b/fs/affs/namei.c @@ -211,7 +211,7 @@ affs_find_entry(struct inode *dir, struct dentry *dentry) } struct dentry * -affs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct super_block *sb = dir->i_sb; struct buffer_head *bh; @@ -255,7 +255,7 @@ affs_unlink(struct inode *dir, struct dentry *dentry) } int -affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd) +affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct super_block *sb = dir->i_sb; struct inode *inode; diff --git a/fs/affs/super.c b/fs/affs/super.c index 0782653a05a2..c70f1e5fc024 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -17,6 +17,7 @@ #include <linux/magic.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/writeback.h> #include "affs.h" extern struct timezone sys_tz; @@ -25,15 +26,17 @@ static int affs_statfs(struct dentry *dentry, struct kstatfs *buf); static int affs_remount (struct super_block *sb, int *flags, char *data); static void -affs_commit_super(struct super_block *sb, int wait, int clean) +affs_commit_super(struct super_block *sb, int wait) { struct affs_sb_info *sbi = AFFS_SB(sb); struct buffer_head *bh = sbi->s_root_bh; struct affs_root_tail *tail = AFFS_ROOT_TAIL(sb, bh); - tail->bm_flag = cpu_to_be32(clean); + lock_buffer(bh); secs_to_datestamp(get_seconds(), &tail->disk_change); affs_fix_checksum(sb, bh); + unlock_buffer(bh); + mark_buffer_dirty(bh); if (wait) sync_dirty_buffer(bh); @@ -45,9 +48,7 @@ affs_put_super(struct super_block *sb) struct affs_sb_info *sbi = AFFS_SB(sb); pr_debug("AFFS: put_super()\n"); - if (!(sb->s_flags & MS_RDONLY) && sb->s_dirt) - affs_commit_super(sb, 1, 1); - + cancel_delayed_work_sync(&sbi->sb_work); kfree(sbi->s_prefix); affs_free_bitmap(sb); affs_brelse(sbi->s_root_bh); @@ -55,26 +56,43 @@ affs_put_super(struct super_block *sb) sb->s_fs_info = NULL; } -static void -affs_write_super(struct super_block *sb) +static int +affs_sync_fs(struct super_block *sb, int wait) { - lock_super(sb); - if (!(sb->s_flags & MS_RDONLY)) - affs_commit_super(sb, 1, 2); - sb->s_dirt = 0; - unlock_super(sb); + affs_commit_super(sb, wait); + return 0; +} + +static void flush_superblock(struct work_struct *work) +{ + struct affs_sb_info *sbi; + struct super_block *sb; + + sbi = container_of(work, struct affs_sb_info, sb_work.work); + sb = sbi->sb; - pr_debug("AFFS: write_super() at %lu, clean=2\n", get_seconds()); + spin_lock(&sbi->work_lock); + sbi->work_queued = 0; + spin_unlock(&sbi->work_lock); + + affs_commit_super(sb, 1); } -static int -affs_sync_fs(struct super_block *sb, int wait) +void affs_mark_sb_dirty(struct super_block *sb) { - lock_super(sb); - affs_commit_super(sb, wait, 2); - sb->s_dirt = 0; - unlock_super(sb); - return 0; + struct affs_sb_info *sbi = AFFS_SB(sb); + unsigned long delay; + + if (sb->s_flags & MS_RDONLY) + return; + + spin_lock(&sbi->work_lock); + if (!sbi->work_queued) { + delay = msecs_to_jiffies(dirty_writeback_interval * 10); + queue_delayed_work(system_long_wq, &sbi->sb_work, delay); + sbi->work_queued = 1; + } + spin_unlock(&sbi->work_lock); } static struct kmem_cache * affs_inode_cachep; @@ -138,7 +156,6 @@ static const struct super_operations affs_sops = { .write_inode = affs_write_inode, .evict_inode = affs_evict_inode, .put_super = affs_put_super, - .write_super = affs_write_super, .sync_fs = affs_sync_fs, .statfs = affs_statfs, .remount_fs = affs_remount, @@ -305,8 +322,11 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent) return -ENOMEM; sb->s_fs_info = sbi; + sbi->sb = sb; mutex_init(&sbi->s_bmlock); spin_lock_init(&sbi->symlink_lock); + spin_lock_init(&sbi->work_lock); + INIT_DELAYED_WORK(&sbi->sb_work, flush_superblock); if (!parse_options(data,&uid,&gid,&i,&reserved,&root_block, &blocksize,&sbi->s_prefix, @@ -531,6 +551,7 @@ affs_remount(struct super_block *sb, int *flags, char *data) return -EINVAL; } + flush_delayed_work_sync(&sbi->sb_work); replace_mount_options(sb, new_opts); sbi->s_flags = mount_flags; @@ -549,10 +570,9 @@ affs_remount(struct super_block *sb, int *flags, char *data) if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) return 0; - if (*flags & MS_RDONLY) { - affs_write_super(sb); + if (*flags & MS_RDONLY) affs_free_bitmap(sb); - } else + else res = affs_init_bitmap(sb, flags); return res; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index e22dc4b4a503..db477906ba4f 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -20,16 +20,16 @@ #include "internal.h" static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd); + unsigned int flags); static int afs_dir_open(struct inode *inode, struct file *file); static int afs_readdir(struct file *file, void *dirent, filldir_t filldir); -static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd); +static int afs_d_revalidate(struct dentry *dentry, unsigned int flags); static int afs_d_delete(const struct dentry *dentry); static void afs_d_release(struct dentry *dentry); static int afs_lookup_filldir(void *_cookie, const char *name, int nlen, loff_t fpos, u64 ino, unsigned dtype); static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd); + bool excl); static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); static int afs_rmdir(struct inode *dir, struct dentry *dentry); static int afs_unlink(struct inode *dir, struct dentry *dentry); @@ -516,7 +516,7 @@ out: * look up an entry in a directory */ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct afs_vnode *vnode; struct afs_fid fid; @@ -598,7 +598,7 @@ success: * - NOTE! the hit can be a negative hit too, so we can't assume we have an * inode */ -static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd) +static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) { struct afs_vnode *vnode, *dir; struct afs_fid uninitialized_var(fid); @@ -607,7 +607,7 @@ static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd) void *dir_version; int ret; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; vnode = AFS_FS_I(dentry->d_inode); @@ -949,7 +949,7 @@ error: * create a regular file on an AFS filesystem */ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct afs_file_status status; struct afs_callback cb; diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 298cf8919ec7..9682c33d5daf 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -22,7 +22,7 @@ static struct dentry *afs_mntpt_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd); + unsigned int flags); static int afs_mntpt_open(struct inode *inode, struct file *file); static void afs_mntpt_expiry_timed_out(struct work_struct *work); @@ -104,7 +104,7 @@ out: */ static struct dentry *afs_mntpt_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { _enter("%p,%p{%p{%s},%s}", dir, diff --git a/fs/afs/super.c b/fs/afs/super.c index f02b31e7e648..df8c6047c2a1 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -395,7 +395,7 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, as->volume = vol; /* allocate a deviceless superblock */ - sb = sget(fs_type, afs_test_super, afs_set_super, as); + sb = sget(fs_type, afs_test_super, afs_set_super, flags, as); if (IS_ERR(sb)) { ret = PTR_ERR(sb); afs_put_volume(vol); @@ -406,7 +406,6 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, if (!sb->s_root) { /* initial superblock/root creation */ _debug("create"); - sb->s_flags = flags; ret = afs_fill_super(sb, ¶ms); if (ret < 0) { deactivate_locked_super(sb); @@ -56,13 +56,6 @@ static struct kmem_cache *kioctx_cachep; static struct workqueue_struct *aio_wq; -/* Used for rare fput completion. */ -static void aio_fput_routine(struct work_struct *); -static DECLARE_WORK(fput_work, aio_fput_routine); - -static DEFINE_SPINLOCK(fput_lock); -static LIST_HEAD(fput_head); - static void aio_kick_handler(struct work_struct *); static void aio_queue_work(struct kioctx *); @@ -479,7 +472,6 @@ static int kiocb_batch_refill(struct kioctx *ctx, struct kiocb_batch *batch) { unsigned short allocated, to_alloc; long avail; - bool called_fput = false; struct kiocb *req, *n; struct aio_ring *ring; @@ -495,28 +487,11 @@ static int kiocb_batch_refill(struct kioctx *ctx, struct kiocb_batch *batch) if (allocated == 0) goto out; -retry: spin_lock_irq(&ctx->ctx_lock); ring = kmap_atomic(ctx->ring_info.ring_pages[0]); avail = aio_ring_avail(&ctx->ring_info, ring) - ctx->reqs_active; BUG_ON(avail < 0); - if (avail == 0 && !called_fput) { - /* - * Handle a potential starvation case. It is possible that - * we hold the last reference on a struct file, causing us - * to delay the final fput to non-irq context. In this case, - * ctx->reqs_active is artificially high. Calling the fput - * routine here may free up a slot in the event completion - * ring, allowing this allocation to succeed. - */ - kunmap_atomic(ring); - spin_unlock_irq(&ctx->ctx_lock); - aio_fput_routine(NULL); - called_fput = true; - goto retry; - } - if (avail < allocated) { /* Trim back the number of requests. */ list_for_each_entry_safe(req, n, &batch->head, ki_batch) { @@ -570,36 +545,6 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req) wake_up_all(&ctx->wait); } -static void aio_fput_routine(struct work_struct *data) -{ - spin_lock_irq(&fput_lock); - while (likely(!list_empty(&fput_head))) { - struct kiocb *req = list_kiocb(fput_head.next); - struct kioctx *ctx = req->ki_ctx; - - list_del(&req->ki_list); - spin_unlock_irq(&fput_lock); - - /* Complete the fput(s) */ - if (req->ki_filp != NULL) - fput(req->ki_filp); - - /* Link the iocb into the context's free list */ - rcu_read_lock(); - spin_lock_irq(&ctx->ctx_lock); - really_put_req(ctx, req); - /* - * at that point ctx might've been killed, but actual - * freeing is RCU'd - */ - spin_unlock_irq(&ctx->ctx_lock); - rcu_read_unlock(); - - spin_lock_irq(&fput_lock); - } - spin_unlock_irq(&fput_lock); -} - /* __aio_put_req * Returns true if this put was the last user of the request. */ @@ -618,21 +563,9 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req) req->ki_cancel = NULL; req->ki_retry = NULL; - /* - * Try to optimize the aio and eventfd file* puts, by avoiding to - * schedule work in case it is not final fput() time. In normal cases, - * we would not be holding the last reference to the file*, so - * this function will be executed w/out any aio kthread wakeup. - */ - if (unlikely(!fput_atomic(req->ki_filp))) { - spin_lock(&fput_lock); - list_add(&req->ki_list, &fput_head); - spin_unlock(&fput_lock); - schedule_work(&fput_work); - } else { - req->ki_filp = NULL; - really_put_req(ctx, req); - } + fput(req->ki_filp); + req->ki_filp = NULL; + really_put_req(ctx, req); return 1; } diff --git a/fs/attr.c b/fs/attr.c index 0da90951d277..29e38a1f7f77 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -171,6 +171,8 @@ int notify_change(struct dentry * dentry, struct iattr * attr) struct timespec now; unsigned int ia_valid = attr->ia_valid; + WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex)); + if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) { if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) return -EPERM; @@ -250,5 +252,4 @@ int notify_change(struct dentry * dentry, struct iattr * attr) return error; } - EXPORT_SYMBOL(notify_change); diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index aa9103f8f01b..abf645c1703b 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -257,8 +257,8 @@ static int autofs_dev_ioctl_open_mountpoint(const char *name, dev_t devid) * corresponding to the autofs fs we want to open. */ - filp = dentry_open(path.dentry, path.mnt, O_RDONLY, - current_cred()); + filp = dentry_open(&path, O_RDONLY, current_cred()); + path_put(&path); if (IS_ERR(filp)) { err = PTR_ERR(filp); goto out; diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 75e5f1c8e028..e7396cfdb109 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -32,7 +32,7 @@ static long autofs4_root_ioctl(struct file *,unsigned int,unsigned long); static long autofs4_root_compat_ioctl(struct file *,unsigned int,unsigned long); #endif static int autofs4_dir_open(struct inode *inode, struct file *file); -static struct dentry *autofs4_lookup(struct inode *,struct dentry *, struct nameidata *); +static struct dentry *autofs4_lookup(struct inode *,struct dentry *, unsigned int); static struct vfsmount *autofs4_d_automount(struct path *); static int autofs4_d_manage(struct dentry *, bool); static void autofs4_dentry_release(struct dentry *); @@ -458,7 +458,7 @@ int autofs4_d_manage(struct dentry *dentry, bool rcu_walk) } /* Lookups in the root directory */ -static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct autofs_sb_info *sbi; struct autofs_info *ino; diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 1b35d6bd06b0..b1342ffb3cf6 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -173,13 +173,13 @@ static const struct file_operations bad_file_ops = }; static int bad_inode_create (struct inode *dir, struct dentry *dentry, - umode_t mode, struct nameidata *nd) + umode_t mode, bool excl) { return -EIO; } static struct dentry *bad_inode_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) + struct dentry *dentry, unsigned int flags) { return ERR_PTR(-EIO); } diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index e18da23d42b5..cf7f3c67c8b7 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -34,7 +34,7 @@ static int befs_readdir(struct file *, void *, filldir_t); static int befs_get_block(struct inode *, sector_t, struct buffer_head *, int); static int befs_readpage(struct file *file, struct page *page); static sector_t befs_bmap(struct address_space *mapping, sector_t block); -static struct dentry *befs_lookup(struct inode *, struct dentry *, struct nameidata *); +static struct dentry *befs_lookup(struct inode *, struct dentry *, unsigned int); static struct inode *befs_iget(struct super_block *, unsigned long); static struct inode *befs_alloc_inode(struct super_block *sb); static void befs_destroy_inode(struct inode *inode); @@ -159,7 +159,7 @@ befs_get_block(struct inode *inode, sector_t block, } static struct dentry * -befs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode = NULL; struct super_block *sb = dir->i_sb; diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index d12c7966db27..2785ef91191a 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -85,7 +85,7 @@ const struct file_operations bfs_dir_operations = { extern void dump_imap(const char *, struct super_block *); static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { int err; struct inode *inode; @@ -133,7 +133,7 @@ static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, } static struct dentry *bfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct inode *inode = NULL; struct buffer_head *bh; diff --git a/fs/block_dev.c b/fs/block_dev.c index c2bbe1fb1326..1e519195d45b 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1710,3 +1710,39 @@ int __invalidate_device(struct block_device *bdev, bool kill_dirty) return res; } EXPORT_SYMBOL(__invalidate_device); + +void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) +{ + struct inode *inode, *old_inode = NULL; + + spin_lock(&inode_sb_list_lock); + list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) { + struct address_space *mapping = inode->i_mapping; + + spin_lock(&inode->i_lock); + if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) || + mapping->nrpages == 0) { + spin_unlock(&inode->i_lock); + continue; + } + __iget(inode); + spin_unlock(&inode->i_lock); + spin_unlock(&inode_sb_list_lock); + /* + * We hold a reference to 'inode' so it couldn't have been + * removed from s_inodes list while we dropped the + * inode_sb_list_lock. We cannot iput the inode now as we can + * be holding the last reference and we cannot iput it under + * inode_sb_list_lock. So we keep the reference and iput it + * later. + */ + iput(old_inode); + old_inode = inode; + + func(I_BDEV(inode), arg); + + spin_lock(&inode_sb_list_lock); + } + spin_unlock(&inode_sb_list_lock); + iput(old_inode); +} diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 7301cdb4b2cb..a383c18e74e8 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -301,10 +301,14 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info, goto out; eb = path->nodes[level]; - if (!eb) { - WARN_ON(1); - ret = 1; - goto out; + while (!eb) { + if (!level) { + WARN_ON(1); + ret = 1; + goto out; + } + level--; + eb = path->nodes[level]; } ret = add_all_parents(root, path, parents, level, &ref->key_for_search, @@ -835,6 +839,7 @@ again: } ret = __add_delayed_refs(head, delayed_ref_seq, &prefs_delayed); + mutex_unlock(&head->mutex); if (ret) { spin_unlock(&delayed_refs->lock); goto out; @@ -928,8 +933,6 @@ again: } out: - if (head) - mutex_unlock(&head->mutex); btrfs_free_path(path); while (!list_empty(&prefs)) { ref = list_first_entry(&prefs, struct __prelim_ref, list); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 15cbc2bf4ff0..8206b3900587 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1024,11 +1024,18 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info, if (!looped && !tm) return 0; /* - * we must have key remove operations in the log before the - * replace operation. + * if there are no tree operation for the oldest root, we simply + * return it. this should only happen if that (old) root is at + * level 0. */ - BUG_ON(!tm); + if (!tm) + break; + /* + * if there's an operation that's not a root replacement, we + * found the oldest version of our root. normally, we'll find a + * MOD_LOG_KEY_REMOVE_WHILE_FREEING operation here. + */ if (tm->op != MOD_LOG_ROOT_REPLACE) break; @@ -1087,11 +1094,7 @@ __tree_mod_log_rewind(struct extent_buffer *eb, u64 time_seq, tm->generation); break; case MOD_LOG_KEY_ADD: - if (tm->slot != n - 1) { - o_dst = btrfs_node_key_ptr_offset(tm->slot); - o_src = btrfs_node_key_ptr_offset(tm->slot + 1); - memmove_extent_buffer(eb, o_dst, o_src, p_size); - } + /* if a move operation is needed it's in the log */ n--; break; case MOD_LOG_MOVE_KEYS: @@ -1192,16 +1195,8 @@ get_old_root(struct btrfs_root *root, u64 time_seq) } tm = tree_mod_log_search(root->fs_info, logical, time_seq); - /* - * there was an item in the log when __tree_mod_log_oldest_root - * returned. this one must not go away, because the time_seq passed to - * us must be blocking its removal. - */ - BUG_ON(!tm); - if (old_root) - eb = alloc_dummy_extent_buffer(tm->index << PAGE_CACHE_SHIFT, - root->nodesize); + eb = alloc_dummy_extent_buffer(logical, root->nodesize); else eb = btrfs_clone_extent_buffer(root->node); btrfs_tree_read_unlock(root->node); @@ -1216,7 +1211,10 @@ get_old_root(struct btrfs_root *root, u64 time_seq) btrfs_set_header_level(eb, old_root->level); btrfs_set_header_generation(eb, old_generation); } - __tree_mod_log_rewind(eb, time_seq, tm); + if (tm) + __tree_mod_log_rewind(eb, time_seq, tm); + else + WARN_ON(btrfs_header_level(eb) != 0); extent_buffer_get(eb); return eb; @@ -2995,7 +2993,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, static void insert_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, struct btrfs_disk_key *key, u64 bytenr, - int slot, int level, int tree_mod_log) + int slot, int level) { struct extent_buffer *lower; int nritems; @@ -3008,7 +3006,7 @@ static void insert_ptr(struct btrfs_trans_handle *trans, BUG_ON(slot > nritems); BUG_ON(nritems == BTRFS_NODEPTRS_PER_BLOCK(root)); if (slot != nritems) { - if (tree_mod_log && level) + if (level) tree_mod_log_eb_move(root->fs_info, lower, slot + 1, slot, nritems - slot); memmove_extent_buffer(lower, @@ -3016,7 +3014,7 @@ static void insert_ptr(struct btrfs_trans_handle *trans, btrfs_node_key_ptr_offset(slot), (nritems - slot) * sizeof(struct btrfs_key_ptr)); } - if (tree_mod_log && level) { + if (level) { ret = tree_mod_log_insert_key(root->fs_info, lower, slot, MOD_LOG_KEY_ADD); BUG_ON(ret < 0); @@ -3104,7 +3102,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans, btrfs_mark_buffer_dirty(split); insert_ptr(trans, root, path, &disk_key, split->start, - path->slots[level + 1] + 1, level + 1, 1); + path->slots[level + 1] + 1, level + 1); if (path->slots[level] >= mid) { path->slots[level] -= mid; @@ -3641,7 +3639,7 @@ static noinline void copy_for_split(struct btrfs_trans_handle *trans, btrfs_set_header_nritems(l, mid); btrfs_item_key(right, &disk_key, 0); insert_ptr(trans, root, path, &disk_key, right->start, - path->slots[1] + 1, 1, 0); + path->slots[1] + 1, 1); btrfs_mark_buffer_dirty(right); btrfs_mark_buffer_dirty(l); @@ -3848,7 +3846,7 @@ again: if (mid <= slot) { btrfs_set_header_nritems(right, 0); insert_ptr(trans, root, path, &disk_key, right->start, - path->slots[1] + 1, 1, 0); + path->slots[1] + 1, 1); btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; @@ -3857,7 +3855,7 @@ again: } else { btrfs_set_header_nritems(right, 0); insert_ptr(trans, root, path, &disk_key, right->start, - path->slots[1], 1, 0); + path->slots[1], 1); btrfs_tree_unlock(path->nodes[0]); free_extent_buffer(path->nodes[0]); path->nodes[0] = right; @@ -5121,6 +5119,18 @@ again: if (!path->skip_locking) { ret = btrfs_try_tree_read_lock(next); + if (!ret && time_seq) { + /* + * If we don't get the lock, we may be racing + * with push_leaf_left, holding that lock while + * itself waiting for the leaf we've currently + * locked. To solve this situation, we give up + * on our lock and cycle. + */ + btrfs_release_path(path); + cond_resched(); + goto again; + } if (!ret) { btrfs_set_path_blocking(path); btrfs_tree_read_lock(next); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 7b845ff4af99..2936ca49b3b4 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2354,12 +2354,17 @@ retry_root_backup: BTRFS_CSUM_TREE_OBJECTID, csum_root); if (ret) goto recovery_tree_root; - csum_root->track_dirty = 1; fs_info->generation = generation; fs_info->last_trans_committed = generation; + ret = btrfs_recover_balance(fs_info); + if (ret) { + printk(KERN_WARNING "btrfs: failed to recover balance\n"); + goto fail_block_groups; + } + ret = btrfs_init_dev_stats(fs_info); if (ret) { printk(KERN_ERR "btrfs: failed to init dev_stats: %d\n", @@ -2485,20 +2490,23 @@ retry_root_backup: goto fail_trans_kthread; } - if (!(sb->s_flags & MS_RDONLY)) { - down_read(&fs_info->cleanup_work_sem); - err = btrfs_orphan_cleanup(fs_info->fs_root); - if (!err) - err = btrfs_orphan_cleanup(fs_info->tree_root); - up_read(&fs_info->cleanup_work_sem); + if (sb->s_flags & MS_RDONLY) + return 0; - if (!err) - err = btrfs_recover_balance(fs_info->tree_root); + down_read(&fs_info->cleanup_work_sem); + if ((ret = btrfs_orphan_cleanup(fs_info->fs_root)) || + (ret = btrfs_orphan_cleanup(fs_info->tree_root))) { + up_read(&fs_info->cleanup_work_sem); + close_ctree(tree_root); + return ret; + } + up_read(&fs_info->cleanup_work_sem); - if (err) { - close_ctree(tree_root); - return err; - } + ret = btrfs_resume_balance_async(fs_info); + if (ret) { + printk(KERN_WARNING "btrfs: failed to resume balance\n"); + close_ctree(tree_root); + return ret; } return 0; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 4b5a1e1bdefb..6e1d36702ff7 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2347,12 +2347,10 @@ next: return count; } - static void wait_for_more_refs(struct btrfs_delayed_ref_root *delayed_refs, - unsigned long num_refs) + unsigned long num_refs, + struct list_head *first_seq) { - struct list_head *first_seq = delayed_refs->seq_head.next; - spin_unlock(&delayed_refs->lock); pr_debug("waiting for more refs (num %ld, first %p)\n", num_refs, first_seq); @@ -2381,6 +2379,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_delayed_ref_node *ref; struct list_head cluster; + struct list_head *first_seq = NULL; int ret; u64 delayed_start; int run_all = count == (unsigned long)-1; @@ -2436,8 +2435,10 @@ again: */ consider_waiting = 1; num_refs = delayed_refs->num_entries; + first_seq = root->fs_info->tree_mod_seq_list.next; } else { - wait_for_more_refs(delayed_refs, num_refs); + wait_for_more_refs(delayed_refs, + num_refs, first_seq); /* * after waiting, things have changed. we * dropped the lock and someone else might have diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index aaa12c1eb348..01c21b6c6d43 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3324,6 +3324,7 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, writepage_t writepage, void *data, void (*flush_fn)(void *)) { + struct inode *inode = mapping->host; int ret = 0; int done = 0; int nr_to_write_done = 0; @@ -3334,6 +3335,18 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, int scanned = 0; int tag; + /* + * We have to hold onto the inode so that ordered extents can do their + * work when the IO finishes. The alternative to this is failing to add + * an ordered extent if the igrab() fails there and that is a huge pain + * to deal with, so instead just hold onto the inode throughout the + * writepages operation. If it fails here we are freeing up the inode + * anyway and we'd rather not waste our time writing out stuff that is + * going to be truncated anyway. + */ + if (!igrab(inode)) + return 0; + pagevec_init(&pvec, 0); if (wbc->range_cyclic) { index = mapping->writeback_index; /* Start from prev offset */ @@ -3428,6 +3441,7 @@ retry: index = 0; goto retry; } + btrfs_add_delayed_iput(inode); return ret; } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 70dc8ca73e25..9aa01ec2138d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1334,7 +1334,6 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, loff_t *ppos, size_t count, size_t ocount) { struct file *file = iocb->ki_filp; - struct inode *inode = fdentry(file)->d_inode; struct iov_iter i; ssize_t written; ssize_t written_buffered; @@ -1344,18 +1343,6 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, written = generic_file_direct_write(iocb, iov, &nr_segs, pos, ppos, count, ocount); - /* - * the generic O_DIRECT will update in-memory i_size after the - * DIOs are done. But our endio handlers that update the on - * disk i_size never update past the in memory i_size. So we - * need one more update here to catch any additions to the - * file - */ - if (inode->i_size != BTRFS_I(inode)->disk_i_size) { - btrfs_ordered_update_i_size(inode, inode->i_size, NULL); - mark_inode_dirty(inode); - } - if (written < 0 || written == count) return written; diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 81296c57405a..6c4e2baa9290 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1543,29 +1543,26 @@ again: end = bitmap_info->offset + (u64)(BITS_PER_BITMAP * ctl->unit) - 1; /* - * XXX - this can go away after a few releases. - * - * since the only user of btrfs_remove_free_space is the tree logging - * stuff, and the only way to test that is under crash conditions, we - * want to have this debug stuff here just in case somethings not - * working. Search the bitmap for the space we are trying to use to - * make sure its actually there. If its not there then we need to stop - * because something has gone wrong. + * We need to search for bits in this bitmap. We could only cover some + * of the extent in this bitmap thanks to how we add space, so we need + * to search for as much as it as we can and clear that amount, and then + * go searching for the next bit. */ search_start = *offset; - search_bytes = *bytes; + search_bytes = ctl->unit; search_bytes = min(search_bytes, end - search_start + 1); ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes); BUG_ON(ret < 0 || search_start != *offset); - if (*offset > bitmap_info->offset && *offset + *bytes > end) { - bitmap_clear_bits(ctl, bitmap_info, *offset, end - *offset + 1); - *bytes -= end - *offset + 1; - *offset = end + 1; - } else if (*offset >= bitmap_info->offset && *offset + *bytes <= end) { - bitmap_clear_bits(ctl, bitmap_info, *offset, *bytes); - *bytes = 0; - } + /* We may have found more bits than what we need */ + search_bytes = min(search_bytes, *bytes); + + /* Cannot clear past the end of the bitmap */ + search_bytes = min(search_bytes, end - search_start + 1); + + bitmap_clear_bits(ctl, bitmap_info, search_start, search_bytes); + *offset += search_bytes; + *bytes -= search_bytes; if (*bytes) { struct rb_node *next = rb_next(&bitmap_info->offset_index); @@ -1596,7 +1593,7 @@ again: * everything over again. */ search_start = *offset; - search_bytes = *bytes; + search_bytes = ctl->unit; ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes); if (ret < 0 || search_start != *offset) @@ -1879,12 +1876,14 @@ int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *info; - struct btrfs_free_space *next_info = NULL; int ret = 0; spin_lock(&ctl->tree_lock); again: + if (!bytes) + goto out_lock; + info = tree_search_offset(ctl, offset, 0, 0); if (!info) { /* @@ -1905,88 +1904,48 @@ again: } } - if (info->bytes < bytes && rb_next(&info->offset_index)) { - u64 end; - next_info = rb_entry(rb_next(&info->offset_index), - struct btrfs_free_space, - offset_index); - - if (next_info->bitmap) - end = next_info->offset + - BITS_PER_BITMAP * ctl->unit - 1; - else - end = next_info->offset + next_info->bytes; - - if (next_info->bytes < bytes || - next_info->offset > offset || offset > end) { - printk(KERN_CRIT "Found free space at %llu, size %llu," - " trying to use %llu\n", - (unsigned long long)info->offset, - (unsigned long long)info->bytes, - (unsigned long long)bytes); - WARN_ON(1); - ret = -EINVAL; - goto out_lock; - } - - info = next_info; - } - - if (info->bytes == bytes) { + if (!info->bitmap) { unlink_free_space(ctl, info); - if (info->bitmap) { - kfree(info->bitmap); - ctl->total_bitmaps--; - } - kmem_cache_free(btrfs_free_space_cachep, info); - ret = 0; - goto out_lock; - } - - if (!info->bitmap && info->offset == offset) { - unlink_free_space(ctl, info); - info->offset += bytes; - info->bytes -= bytes; - ret = link_free_space(ctl, info); - WARN_ON(ret); - goto out_lock; - } + if (offset == info->offset) { + u64 to_free = min(bytes, info->bytes); + + info->bytes -= to_free; + info->offset += to_free; + if (info->bytes) { + ret = link_free_space(ctl, info); + WARN_ON(ret); + } else { + kmem_cache_free(btrfs_free_space_cachep, info); + } - if (!info->bitmap && info->offset <= offset && - info->offset + info->bytes >= offset + bytes) { - u64 old_start = info->offset; - /* - * we're freeing space in the middle of the info, - * this can happen during tree log replay - * - * first unlink the old info and then - * insert it again after the hole we're creating - */ - unlink_free_space(ctl, info); - if (offset + bytes < info->offset + info->bytes) { - u64 old_end = info->offset + info->bytes; + offset += to_free; + bytes -= to_free; + goto again; + } else { + u64 old_end = info->bytes + info->offset; - info->offset = offset + bytes; - info->bytes = old_end - info->offset; + info->bytes = offset - info->offset; ret = link_free_space(ctl, info); WARN_ON(ret); if (ret) goto out_lock; - } else { - /* the hole we're creating ends at the end - * of the info struct, just free the info - */ - kmem_cache_free(btrfs_free_space_cachep, info); - } - spin_unlock(&ctl->tree_lock); - /* step two, insert a new info struct to cover - * anything before the hole - */ - ret = btrfs_add_free_space(block_group, old_start, - offset - old_start); - WARN_ON(ret); /* -ENOMEM */ - goto out; + /* Not enough bytes in this entry to satisfy us */ + if (old_end < offset + bytes) { + bytes -= old_end - offset; + offset = old_end; + goto again; + } else if (old_end == offset + bytes) { + /* all done */ + goto out_lock; + } + spin_unlock(&ctl->tree_lock); + + ret = btrfs_add_free_space(block_group, offset + bytes, + old_end - (offset + bytes)); + WARN_ON(ret); + goto out; + } } ret = remove_from_bitmap(ctl, info, &offset, &bytes); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d8bb0dbc4941..fb8d671d00e6 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3754,7 +3754,7 @@ void btrfs_evict_inode(struct inode *inode) btrfs_wait_ordered_range(inode, 0, (u64)-1); if (root->fs_info->log_root_recovering) { - BUG_ON(!test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, + BUG_ON(test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, &BTRFS_I(inode)->runtime_flags)); goto no_delete; } @@ -4247,7 +4247,7 @@ static void btrfs_dentry_release(struct dentry *dentry) } static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct dentry *ret; @@ -4893,7 +4893,7 @@ out_unlock: } static int btrfs_create(struct inode *dir, struct dentry *dentry, - umode_t mode, struct nameidata *nd) + umode_t mode, bool excl) { struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(dir)->root; @@ -5876,8 +5876,17 @@ map: bh_result->b_size = len; bh_result->b_bdev = em->bdev; set_buffer_mapped(bh_result); - if (create && !test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) - set_buffer_new(bh_result); + if (create) { + if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) + set_buffer_new(bh_result); + + /* + * Need to update the i_size under the extent lock so buffered + * readers will get the updated i_size when we unlock. + */ + if (start + len > i_size_read(inode)) + i_size_write(inode, start + len); + } free_extent_map(em); @@ -6360,12 +6369,48 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, */ ordered = btrfs_lookup_ordered_range(inode, lockstart, lockend - lockstart + 1); - if (!ordered) + + /* + * We need to make sure there are no buffered pages in this + * range either, we could have raced between the invalidate in + * generic_file_direct_write and locking the extent. The + * invalidate needs to happen so that reads after a write do not + * get stale data. + */ + if (!ordered && (!writing || + !test_range_bit(&BTRFS_I(inode)->io_tree, + lockstart, lockend, EXTENT_UPTODATE, 0, + cached_state))) break; + unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, &cached_state, GFP_NOFS); - btrfs_start_ordered_extent(inode, ordered, 1); - btrfs_put_ordered_extent(ordered); + + if (ordered) { + btrfs_start_ordered_extent(inode, ordered, 1); + btrfs_put_ordered_extent(ordered); + } else { + /* Screw you mmap */ + ret = filemap_write_and_wait_range(file->f_mapping, + lockstart, + lockend); + if (ret) + goto out; + + /* + * If we found a page that couldn't be invalidated just + * fall back to buffered. + */ + ret = invalidate_inode_pages2_range(file->f_mapping, + lockstart >> PAGE_CACHE_SHIFT, + lockend >> PAGE_CACHE_SHIFT); + if (ret) { + if (ret == -EBUSY) + ret = 0; + goto out; + } + } + cond_resched(); } @@ -6942,7 +6987,7 @@ void btrfs_destroy_inode(struct inode *inode) struct btrfs_ordered_extent *ordered; struct btrfs_root *root = BTRFS_I(inode)->root; - WARN_ON(!list_empty(&inode->i_dentry)); + WARN_ON(!hlist_empty(&inode->i_dentry)); WARN_ON(inode->i_data.nrpages); WARN_ON(BTRFS_I(inode)->outstanding_extents); WARN_ON(BTRFS_I(inode)->reserved_extents); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 0e92e5763005..1e9f6c019ad0 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3268,7 +3268,7 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg) if (fs_info->sb->s_flags & MS_RDONLY) return -EROFS; - ret = mnt_want_write(file->f_path.mnt); + ret = mnt_want_write_file(file); if (ret) return ret; @@ -3338,7 +3338,7 @@ out_bargs: out: mutex_unlock(&fs_info->balance_mutex); mutex_unlock(&fs_info->volume_mutex); - mnt_drop_write(file->f_path.mnt); + mnt_drop_write_file(file); return ret; } diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index 497c530724cf..e440aa653c30 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -339,7 +339,7 @@ struct btrfs_ioctl_get_dev_stats { #define BTRFS_IOC_WAIT_SYNC _IOW(BTRFS_IOCTL_MAGIC, 22, __u64) #define BTRFS_IOC_SNAP_CREATE_V2 _IOW(BTRFS_IOCTL_MAGIC, 23, \ struct btrfs_ioctl_vol_args_v2) -#define BTRFS_IOC_SUBVOL_GETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 25, __u64) +#define BTRFS_IOC_SUBVOL_GETFLAGS _IOR(BTRFS_IOCTL_MAGIC, 25, __u64) #define BTRFS_IOC_SUBVOL_SETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 26, __u64) #define BTRFS_IOC_SCRUB _IOWR(BTRFS_IOCTL_MAGIC, 27, \ struct btrfs_ioctl_scrub_args) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0eb9a4da069e..b19d75567728 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1068,7 +1068,8 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, } bdev = fs_devices->latest_bdev; - s = sget(fs_type, btrfs_test_super, btrfs_set_super, fs_info); + s = sget(fs_type, btrfs_test_super, btrfs_set_super, flags | MS_NOSEC, + fs_info); if (IS_ERR(s)) { error = PTR_ERR(s); goto error_close_devices; @@ -1082,7 +1083,6 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, } else { char b[BDEVNAME_SIZE]; - s->s_flags = flags | MS_NOSEC; strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); btrfs_sb(s)->bdev_holder = fs_type; error = btrfs_fill_super(s, fs_devices, data, @@ -1187,6 +1187,10 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) if (ret) goto restore; + ret = btrfs_resume_balance_async(fs_info); + if (ret) + goto restore; + sb->s_flags &= ~MS_RDONLY; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 2017d0ff511c..8abeae4224f9 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -690,6 +690,8 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, kfree(name); iput(inode); + + btrfs_run_delayed_items(trans, root); return ret; } @@ -895,6 +897,7 @@ again: ret = btrfs_unlink_inode(trans, root, dir, inode, victim_name, victim_name_len); + btrfs_run_delayed_items(trans, root); } kfree(victim_name); ptr = (unsigned long)(victim_ref + 1) + victim_name_len; @@ -1475,6 +1478,9 @@ again: ret = btrfs_unlink_inode(trans, root, dir, inode, name, name_len); BUG_ON(ret); + + btrfs_run_delayed_items(trans, root); + kfree(name); iput(inode); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 8a3d2594b807..ecaad40e7ef4 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2845,31 +2845,48 @@ out: static int balance_kthread(void *data) { - struct btrfs_balance_control *bctl = - (struct btrfs_balance_control *)data; - struct btrfs_fs_info *fs_info = bctl->fs_info; + struct btrfs_fs_info *fs_info = data; int ret = 0; mutex_lock(&fs_info->volume_mutex); mutex_lock(&fs_info->balance_mutex); - set_balance_control(bctl); - - if (btrfs_test_opt(fs_info->tree_root, SKIP_BALANCE)) { - printk(KERN_INFO "btrfs: force skipping balance\n"); - } else { + if (fs_info->balance_ctl) { printk(KERN_INFO "btrfs: continuing balance\n"); - ret = btrfs_balance(bctl, NULL); + ret = btrfs_balance(fs_info->balance_ctl, NULL); } mutex_unlock(&fs_info->balance_mutex); mutex_unlock(&fs_info->volume_mutex); + return ret; } -int btrfs_recover_balance(struct btrfs_root *tree_root) +int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info) { struct task_struct *tsk; + + spin_lock(&fs_info->balance_lock); + if (!fs_info->balance_ctl) { + spin_unlock(&fs_info->balance_lock); + return 0; + } + spin_unlock(&fs_info->balance_lock); + + if (btrfs_test_opt(fs_info->tree_root, SKIP_BALANCE)) { + printk(KERN_INFO "btrfs: force skipping balance\n"); + return 0; + } + + tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance"); + if (IS_ERR(tsk)) + return PTR_ERR(tsk); + + return 0; +} + +int btrfs_recover_balance(struct btrfs_fs_info *fs_info) +{ struct btrfs_balance_control *bctl; struct btrfs_balance_item *item; struct btrfs_disk_balance_args disk_bargs; @@ -2882,29 +2899,30 @@ int btrfs_recover_balance(struct btrfs_root *tree_root) if (!path) return -ENOMEM; - bctl = kzalloc(sizeof(*bctl), GFP_NOFS); - if (!bctl) { - ret = -ENOMEM; - goto out; - } - key.objectid = BTRFS_BALANCE_OBJECTID; key.type = BTRFS_BALANCE_ITEM_KEY; key.offset = 0; - ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0); + ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0); if (ret < 0) - goto out_bctl; + goto out; if (ret > 0) { /* ret = -ENOENT; */ ret = 0; - goto out_bctl; + goto out; + } + + bctl = kzalloc(sizeof(*bctl), GFP_NOFS); + if (!bctl) { + ret = -ENOMEM; + goto out; } leaf = path->nodes[0]; item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_balance_item); - bctl->fs_info = tree_root->fs_info; - bctl->flags = btrfs_balance_flags(leaf, item) | BTRFS_BALANCE_RESUME; + bctl->fs_info = fs_info; + bctl->flags = btrfs_balance_flags(leaf, item); + bctl->flags |= BTRFS_BALANCE_RESUME; btrfs_balance_data(leaf, item, &disk_bargs); btrfs_disk_balance_args_to_cpu(&bctl->data, &disk_bargs); @@ -2913,14 +2931,13 @@ int btrfs_recover_balance(struct btrfs_root *tree_root) btrfs_balance_sys(leaf, item, &disk_bargs); btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs); - tsk = kthread_run(balance_kthread, bctl, "btrfs-balance"); - if (IS_ERR(tsk)) - ret = PTR_ERR(tsk); - else - goto out; + mutex_lock(&fs_info->volume_mutex); + mutex_lock(&fs_info->balance_mutex); -out_bctl: - kfree(bctl); + set_balance_control(bctl); + + mutex_unlock(&fs_info->balance_mutex); + mutex_unlock(&fs_info->volume_mutex); out: btrfs_free_path(path); return ret; @@ -4061,16 +4078,18 @@ static void btrfs_end_bio(struct bio *bio, int err) BUG_ON(stripe_index >= bbio->num_stripes); dev = bbio->stripes[stripe_index].dev; - if (bio->bi_rw & WRITE) - btrfs_dev_stat_inc(dev, - BTRFS_DEV_STAT_WRITE_ERRS); - else - btrfs_dev_stat_inc(dev, - BTRFS_DEV_STAT_READ_ERRS); - if ((bio->bi_rw & WRITE_FLUSH) == WRITE_FLUSH) - btrfs_dev_stat_inc(dev, - BTRFS_DEV_STAT_FLUSH_ERRS); - btrfs_dev_stat_print_on_error(dev); + if (dev->bdev) { + if (bio->bi_rw & WRITE) + btrfs_dev_stat_inc(dev, + BTRFS_DEV_STAT_WRITE_ERRS); + else + btrfs_dev_stat_inc(dev, + BTRFS_DEV_STAT_READ_ERRS); + if ((bio->bi_rw & WRITE_FLUSH) == WRITE_FLUSH) + btrfs_dev_stat_inc(dev, + BTRFS_DEV_STAT_FLUSH_ERRS); + btrfs_dev_stat_print_on_error(dev); + } } } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 74366f27a76b..95f6637614db 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -281,7 +281,8 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size); int btrfs_init_new_device(struct btrfs_root *root, char *path); int btrfs_balance(struct btrfs_balance_control *bctl, struct btrfs_ioctl_balance_args *bargs); -int btrfs_recover_balance(struct btrfs_root *tree_root); +int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info); +int btrfs_recover_balance(struct btrfs_fs_info *fs_info); int btrfs_pause_balance(struct btrfs_fs_info *fs_info); int btrfs_cancel_balance(struct btrfs_fs_info *fs_info); int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset); diff --git a/fs/buffer.c b/fs/buffer.c index 838a9cf246bd..c7062c896d7c 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1036,6 +1036,9 @@ grow_buffers(struct block_device *bdev, sector_t block, int size) static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, int size) { + int ret; + struct buffer_head *bh; + /* Size must be multiple of hard sectorsize */ if (unlikely(size & (bdev_logical_block_size(bdev)-1) || (size < 512 || size > PAGE_SIZE))) { @@ -1048,20 +1051,21 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size) return NULL; } - for (;;) { - struct buffer_head * bh; - int ret; +retry: + bh = __find_get_block(bdev, block, size); + if (bh) + return bh; + ret = grow_buffers(bdev, block, size); + if (ret == 0) { + free_more_memory(); + goto retry; + } else if (ret > 0) { bh = __find_get_block(bdev, block, size); if (bh) return bh; - - ret = grow_buffers(bdev, block, size); - if (ret < 0) - return NULL; - if (ret == 0) - free_more_memory(); } + return NULL; } /* diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 7f0771d3894e..b0b5f7cdfffa 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -567,7 +567,7 @@ lookup_again: if (ret < 0) goto create_error; start = jiffies; - ret = vfs_create(dir->d_inode, next, S_IFREG, NULL); + ret = vfs_create(dir->d_inode, next, S_IFREG, true); cachefiles_hist(cachefiles_create_histogram, start); if (ret < 0) goto create_error; diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 0e3c0924cc3a..c0353dfac51f 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -891,6 +891,7 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page) struct cachefiles_cache *cache; mm_segment_t old_fs; struct file *file; + struct path path; loff_t pos, eof; size_t len; void *data; @@ -916,10 +917,9 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page) /* write the page to the backing filesystem and let it store it in its * own time */ - dget(object->backer); - mntget(cache->mnt); - file = dentry_open(object->backer, cache->mnt, O_RDWR, - cache->cache_cred); + path.mnt = cache->mnt; + path.dentry = object->backer; + file = dentry_open(&path, O_RDWR, cache->cache_cred); if (IS_ERR(file)) { ret = PTR_ERR(file); } else { diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 3e8094be4604..00894ff9246c 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -576,7 +576,7 @@ static int is_root_ceph_dentry(struct inode *inode, struct dentry *dentry) * the MDS so that it gets our 'caps wanted' value in a single op. */ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb); struct ceph_mds_client *mdsc = fsc->mdsc; @@ -594,14 +594,6 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry, if (err < 0) return ERR_PTR(err); - /* open (but not create!) intent? */ - if (nd && - (nd->flags & LOOKUP_OPEN) && - !(nd->intent.open.flags & O_CREAT)) { - int mode = nd->intent.open.create_mode & ~current->fs->umask; - return ceph_lookup_open(dir, dentry, nd, mode, 1); - } - /* can we conclude ENOENT locally? */ if (dentry->d_inode == NULL) { struct ceph_inode_info *ci = ceph_inode(dir); @@ -642,13 +634,51 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry, return dentry; } +int ceph_atomic_open(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned flags, umode_t mode, + int *opened) +{ + int err; + struct dentry *res = NULL; + + if (!(flags & O_CREAT)) { + if (dentry->d_name.len > NAME_MAX) + return -ENAMETOOLONG; + + err = ceph_init_dentry(dentry); + if (err < 0) + return err; + + return ceph_lookup_open(dir, dentry, file, flags, mode, opened); + } + + if (d_unhashed(dentry)) { + res = ceph_lookup(dir, dentry, 0); + if (IS_ERR(res)) + return PTR_ERR(res); + + if (res) + dentry = res; + } + + /* We don't deal with positive dentries here */ + if (dentry->d_inode) + return finish_no_open(file, res); + + *opened |= FILE_CREATED; + err = ceph_lookup_open(dir, dentry, file, flags, mode, opened); + dput(res); + + return err; +} + /* * If we do a create but get no trace back from the MDS, follow up with * a lookup (the VFS expects us to link up the provided dentry). */ int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry) { - struct dentry *result = ceph_lookup(dir, dentry, NULL); + struct dentry *result = ceph_lookup(dir, dentry, 0); if (result && !IS_ERR(result)) { /* @@ -700,25 +730,9 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry, } static int ceph_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { - dout("create in dir %p dentry %p name '%.*s'\n", - dir, dentry, dentry->d_name.len, dentry->d_name.name); - - if (ceph_snap(dir) != CEPH_NOSNAP) - return -EROFS; - - if (nd) { - BUG_ON((nd->flags & LOOKUP_OPEN) == 0); - dentry = ceph_lookup_open(dir, dentry, nd, mode, 0); - /* hrm, what should i do here if we get aliased? */ - if (IS_ERR(dentry)) - return PTR_ERR(dentry); - return 0; - } - - /* fall back to mknod */ - return ceph_mknod(dir, dentry, (mode & ~S_IFMT) | S_IFREG, 0); + return ceph_mknod(dir, dentry, mode, 0); } static int ceph_symlink(struct inode *dir, struct dentry *dentry, @@ -1028,12 +1042,12 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry) /* * Check if cached dentry can be trusted. */ -static int ceph_d_revalidate(struct dentry *dentry, struct nameidata *nd) +static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) { int valid = 0; struct inode *dir; - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; dout("d_revalidate %p '%.*s' inode %p offset %lld\n", dentry, @@ -1080,7 +1094,7 @@ static void ceph_d_release(struct dentry *dentry) } static int ceph_snapdir_d_revalidate(struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { /* * Eventually, we'll want to revalidate snapped metadata @@ -1357,6 +1371,7 @@ const struct inode_operations ceph_dir_iops = { .rmdir = ceph_unlink, .rename = ceph_rename, .create = ceph_create, + .atomic_open = ceph_atomic_open, }; const struct dentry_operations ceph_dentry_ops = { diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 988d4f302e48..1b81d6c31878 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -213,22 +213,15 @@ out: * may_open() fails, the struct *file gets cleaned up (i.e. * ceph_release gets called). So fear not! */ -/* - * flags - * path_lookup_open -> LOOKUP_OPEN - * path_lookup_create -> LOOKUP_OPEN|LOOKUP_CREATE - */ -struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry, - struct nameidata *nd, int mode, - int locked_dir) +int ceph_lookup_open(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned flags, umode_t mode, + int *opened) { struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb); struct ceph_mds_client *mdsc = fsc->mdsc; - struct file *file; struct ceph_mds_request *req; struct dentry *ret; int err; - int flags = nd->intent.open.flags; dout("ceph_lookup_open dentry %p '%.*s' flags %d mode 0%o\n", dentry, dentry->d_name.len, dentry->d_name.name, flags, mode); @@ -236,7 +229,7 @@ struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry, /* do the open */ req = prepare_open_request(dir->i_sb, flags, mode); if (IS_ERR(req)) - return ERR_CAST(req); + return PTR_ERR(req); req->r_dentry = dget(dentry); req->r_num_caps = 2; if (flags & O_CREAT) { @@ -254,14 +247,17 @@ struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry, err = ceph_handle_notrace_create(dir, dentry); if (err) goto out; - file = lookup_instantiate_filp(nd, req->r_dentry, ceph_open); - if (IS_ERR(file)) - err = PTR_ERR(file); + err = finish_open(file, req->r_dentry, ceph_open, opened); out: ret = ceph_finish_lookup(req, dentry, err); ceph_mdsc_put_request(req); dout("ceph_lookup_open result=%p\n", ret); - return ret; + + if (IS_ERR(ret)) + return PTR_ERR(ret); + + dput(ret); + return err; } int ceph_release(struct inode *inode, struct file *file) diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 1e67dd7305a4..7076109f014d 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -871,7 +871,7 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type, if (ceph_test_opt(fsc->client, NOSHARE)) compare_super = NULL; - sb = sget(fs_type, compare_super, ceph_set_super, fsc); + sb = sget(fs_type, compare_super, ceph_set_super, flags, fsc); if (IS_ERR(sb)) { res = ERR_CAST(sb); goto out; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index fc35036d258d..f4d5522cb619 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -806,9 +806,9 @@ extern int ceph_copy_from_page_vector(struct page **pages, loff_t off, size_t len); extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); extern int ceph_open(struct inode *inode, struct file *file); -extern struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry, - struct nameidata *nd, int mode, - int locked_dir); +extern int ceph_lookup_open(struct inode *dir, struct dentry *dentry, + struct file *od, unsigned flags, + umode_t mode, int *opened); extern int ceph_release(struct inode *inode, struct file *filp); /* dir.c */ diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 8b6e344eb0ba..a7610cfedf0a 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -257,7 +257,6 @@ cifs_alloc_inode(struct super_block *sb) static void cifs_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); - INIT_LIST_HEAD(&inode->i_dentry); kmem_cache_free(cifs_inode_cachep, CIFS_I(inode)); } @@ -638,7 +637,10 @@ cifs_do_mount(struct file_system_type *fs_type, mnt_data.cifs_sb = cifs_sb; mnt_data.flags = flags; - sb = sget(fs_type, cifs_match_super, cifs_set_super, &mnt_data); + /* BB should we make this contingent on mount parm? */ + flags |= MS_NODIRATIME | MS_NOATIME; + + sb = sget(fs_type, cifs_match_super, cifs_set_super, flags, &mnt_data); if (IS_ERR(sb)) { root = ERR_CAST(sb); cifs_umount(cifs_sb); @@ -649,10 +651,6 @@ cifs_do_mount(struct file_system_type *fs_type, cFYI(1, "Use existing superblock"); cifs_umount(cifs_sb); } else { - sb->s_flags = flags; - /* BB should we make this contingent on mount parm? */ - sb->s_flags |= MS_NODIRATIME | MS_NOATIME; - rc = cifs_read_super(sb); if (rc) { root = ERR_PTR(rc); @@ -778,6 +776,7 @@ struct file_system_type cifs_fs_type = { }; const struct inode_operations cifs_dir_inode_ops = { .create = cifs_create, + .atomic_open = cifs_atomic_open, .lookup = cifs_lookup, .getattr = cifs_getattr, .unlink = cifs_unlink, diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 65365358c976..1c49c5a9b27a 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -45,9 +45,12 @@ extern const struct address_space_operations cifs_addr_ops_smallbuf; extern const struct inode_operations cifs_dir_inode_ops; extern struct inode *cifs_root_iget(struct super_block *); extern int cifs_create(struct inode *, struct dentry *, umode_t, - struct nameidata *); + bool excl); +extern int cifs_atomic_open(struct inode *, struct dentry *, + struct file *, unsigned, umode_t, + int *); extern struct dentry *cifs_lookup(struct inode *, struct dentry *, - struct nameidata *); + unsigned int); extern int cifs_unlink(struct inode *dir, struct dentry *dentry); extern int cifs_hardlink(struct dentry *, struct inode *, struct dentry *); extern int cifs_mknod(struct inode *, struct dentry *, umode_t, dev_t); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 5b400730c213..4ee522b3f66f 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -86,7 +86,31 @@ static struct { #endif /* CONFIG_CIFS_WEAK_PW_HASH */ #endif /* CIFS_POSIX */ -/* Forward declarations */ +#ifdef CONFIG_HIGHMEM +/* + * On arches that have high memory, kmap address space is limited. By + * serializing the kmap operations on those arches, we ensure that we don't + * end up with a bunch of threads in writeback with partially mapped page + * arrays, stuck waiting for kmap to come back. That situation prevents + * progress and can deadlock. + */ +static DEFINE_MUTEX(cifs_kmap_mutex); + +static inline void +cifs_kmap_lock(void) +{ + mutex_lock(&cifs_kmap_mutex); +} + +static inline void +cifs_kmap_unlock(void) +{ + mutex_unlock(&cifs_kmap_mutex); +} +#else /* !CONFIG_HIGHMEM */ +#define cifs_kmap_lock() do { ; } while(0) +#define cifs_kmap_unlock() do { ; } while(0) +#endif /* CONFIG_HIGHMEM */ /* Mark as invalid, all open files on tree connections since they were closed when session to server was lost */ @@ -1503,7 +1527,9 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) } /* marshal up the page array */ + cifs_kmap_lock(); len = rdata->marshal_iov(rdata, data_len); + cifs_kmap_unlock(); data_len -= len; /* issue the read if we have any iovecs left to fill */ @@ -2069,7 +2095,9 @@ cifs_async_writev(struct cifs_writedata *wdata) * and set the iov_len properly for each one. It may also set * wdata->bytes too. */ + cifs_kmap_lock(); wdata->marshal_iov(iov, wdata); + cifs_kmap_unlock(); cFYI(1, "async write at %llu %u bytes", wdata->offset, wdata->bytes); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 78db68a5cf44..94b7788c3189 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1653,24 +1653,26 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, * If yes, we have encountered a double deliminator * reset the NULL character to the deliminator */ - if (tmp_end < end && tmp_end[1] == delim) + if (tmp_end < end && tmp_end[1] == delim) { tmp_end[0] = delim; - /* Keep iterating until we get to a single deliminator - * OR the end - */ - while ((tmp_end = strchr(tmp_end, delim)) != NULL && - (tmp_end[1] == delim)) { - tmp_end = (char *) &tmp_end[2]; - } + /* Keep iterating until we get to a single + * deliminator OR the end + */ + while ((tmp_end = strchr(tmp_end, delim)) + != NULL && (tmp_end[1] == delim)) { + tmp_end = (char *) &tmp_end[2]; + } - /* Reset var options to point to next element */ - if (tmp_end) { - tmp_end[0] = '\0'; - options = (char *) &tmp_end[1]; - } else - /* Reached the end of the mount option string */ - options = end; + /* Reset var options to point to next element */ + if (tmp_end) { + tmp_end[0] = '\0'; + options = (char *) &tmp_end[1]; + } else + /* Reached the end of the mount option + * string */ + options = end; + } /* Now build new password string */ temp_len = strlen(value); @@ -3443,6 +3445,18 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info, #define CIFS_DEFAULT_NON_POSIX_RSIZE (60 * 1024) #define CIFS_DEFAULT_NON_POSIX_WSIZE (65536) +/* + * On hosts with high memory, we can't currently support wsize/rsize that are + * larger than we can kmap at once. Cap the rsize/wsize at + * LAST_PKMAP * PAGE_SIZE. We'll never be able to fill a read or write request + * larger than that anyway. + */ +#ifdef CONFIG_HIGHMEM +#define CIFS_KMAP_SIZE_LIMIT (LAST_PKMAP * PAGE_CACHE_SIZE) +#else /* CONFIG_HIGHMEM */ +#define CIFS_KMAP_SIZE_LIMIT (1<<24) +#endif /* CONFIG_HIGHMEM */ + static unsigned int cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) { @@ -3473,6 +3487,9 @@ cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) wsize = min_t(unsigned int, wsize, server->maxBuf - sizeof(WRITE_REQ) + 4); + /* limit to the amount that we can kmap at once */ + wsize = min_t(unsigned int, wsize, CIFS_KMAP_SIZE_LIMIT); + /* hard limit of CIFS_MAX_WSIZE */ wsize = min_t(unsigned int, wsize, CIFS_MAX_WSIZE); @@ -3493,18 +3510,15 @@ cifs_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) * MS-CIFS indicates that servers are only limited by the client's * bufsize for reads, testing against win98se shows that it throws * INVALID_PARAMETER errors if you try to request too large a read. + * OS/2 just sends back short reads. * - * If the server advertises a MaxBufferSize of less than one page, - * assume that it also can't satisfy reads larger than that either. - * - * FIXME: Is there a better heuristic for this? + * If the server doesn't advertise CAP_LARGE_READ_X, then assume that + * it can't handle a read request larger than its MaxBufferSize either. */ if (tcon->unix_ext && (unix_cap & CIFS_UNIX_LARGE_READ_CAP)) defsize = CIFS_DEFAULT_IOSIZE; else if (server->capabilities & CAP_LARGE_READ_X) defsize = CIFS_DEFAULT_NON_POSIX_RSIZE; - else if (server->maxBuf >= PAGE_CACHE_SIZE) - defsize = CIFSMaxBufSize; else defsize = server->maxBuf - sizeof(READ_RSP); @@ -3517,6 +3531,9 @@ cifs_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) if (!(server->capabilities & CAP_LARGE_READ_X)) rsize = min_t(unsigned int, CIFSMaxBufSize, rsize); + /* limit to the amount that we can kmap at once */ + rsize = min_t(unsigned int, rsize, CIFS_KMAP_SIZE_LIMIT); + /* hard limit of CIFS_MAX_RSIZE */ rsize = min_t(unsigned int, rsize, CIFS_MAX_RSIZE); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index ec4e9a2a12f8..a180265a10b5 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -133,108 +133,141 @@ cifs_bp_rename_retry: return full_path; } +/* + * Don't allow the separator character in a path component. + * The VFS will not allow "/", but "\" is allowed by posix. + */ +static int +check_name(struct dentry *direntry) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); + int i; + + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) { + for (i = 0; i < direntry->d_name.len; i++) { + if (direntry->d_name.name[i] == '\\') { + cFYI(1, "Invalid file name"); + return -EINVAL; + } + } + } + return 0; +} + + /* Inode operations in similar order to how they appear in Linux file fs.h */ -int -cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, - struct nameidata *nd) +static int cifs_do_create(struct inode *inode, struct dentry *direntry, + int xid, struct tcon_link *tlink, unsigned oflags, + umode_t mode, __u32 *oplock, __u16 *fileHandle, + int *created) { int rc = -ENOENT; - int xid; int create_options = CREATE_NOT_DIR; - __u32 oplock = 0; - int oflags; - /* - * BB below access is probably too much for mknod to request - * but we have to do query and setpathinfo so requesting - * less could fail (unless we want to request getatr and setatr - * permissions (only). At least for POSIX we do not have to - * request so much. - */ - int desiredAccess = GENERIC_READ | GENERIC_WRITE; - __u16 fileHandle; - struct cifs_sb_info *cifs_sb; - struct tcon_link *tlink; - struct cifs_tcon *tcon; + int desiredAccess; + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_tcon *tcon = tlink_tcon(tlink); char *full_path = NULL; FILE_ALL_INFO *buf = NULL; struct inode *newinode = NULL; - int disposition = FILE_OVERWRITE_IF; - - xid = GetXid(); - - cifs_sb = CIFS_SB(inode->i_sb); - tlink = cifs_sb_tlink(cifs_sb); - if (IS_ERR(tlink)) { - FreeXid(xid); - return PTR_ERR(tlink); - } - tcon = tlink_tcon(tlink); + int disposition; + *oplock = 0; if (tcon->ses->server->oplocks) - oplock = REQ_OPLOCK; - - if (nd) - oflags = nd->intent.open.file->f_flags; - else - oflags = O_RDONLY | O_CREAT; + *oplock = REQ_OPLOCK; full_path = build_path_from_dentry(direntry); if (full_path == NULL) { rc = -ENOMEM; - goto cifs_create_out; + goto out; } if (tcon->unix_ext && (tcon->ses->capabilities & CAP_UNIX) && + !tcon->broken_posix_open && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { rc = cifs_posix_open(full_path, &newinode, - inode->i_sb, mode, oflags, &oplock, &fileHandle, xid); - /* EIO could indicate that (posix open) operation is not - supported, despite what server claimed in capability - negotiation. EREMOTE indicates DFS junction, which is not - handled in posix open */ - - if (rc == 0) { - if (newinode == NULL) /* query inode info */ + inode->i_sb, mode, oflags, oplock, fileHandle, xid); + switch (rc) { + case 0: + if (newinode == NULL) { + /* query inode info */ goto cifs_create_get_file_info; - else /* success, no need to query */ - goto cifs_create_set_dentry; - } else if ((rc != -EIO) && (rc != -EREMOTE) && - (rc != -EOPNOTSUPP) && (rc != -EINVAL)) - goto cifs_create_out; - /* else fallthrough to retry, using older open call, this is - case where server does not support this SMB level, and - falsely claims capability (also get here for DFS case - which should be rare for path not covered on files) */ - } + } + + if (!S_ISREG(newinode->i_mode)) { + /* + * The server may allow us to open things like + * FIFOs, but the client isn't set up to deal + * with that. If it's not a regular file, just + * close it and proceed as if it were a normal + * lookup. + */ + CIFSSMBClose(xid, tcon, *fileHandle); + goto cifs_create_get_file_info; + } + /* success, no need to query */ + goto cifs_create_set_dentry; + + case -ENOENT: + goto cifs_create_get_file_info; + + case -EIO: + case -EINVAL: + /* + * EIO could indicate that (posix open) operation is not + * supported, despite what server claimed in capability + * negotiation. + * + * POSIX open in samba versions 3.3.1 and earlier could + * incorrectly fail with invalid parameter. + */ + tcon->broken_posix_open = true; + break; + + case -EREMOTE: + case -EOPNOTSUPP: + /* + * EREMOTE indicates DFS junction, which is not handled + * in posix open. If either that or op not supported + * returned, follow the normal lookup. + */ + break; - if (nd) { - /* if the file is going to stay open, then we - need to set the desired access properly */ - desiredAccess = 0; - if (OPEN_FMODE(oflags) & FMODE_READ) - desiredAccess |= GENERIC_READ; /* is this too little? */ - if (OPEN_FMODE(oflags) & FMODE_WRITE) - desiredAccess |= GENERIC_WRITE; - - if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) - disposition = FILE_CREATE; - else if ((oflags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC)) - disposition = FILE_OVERWRITE_IF; - else if ((oflags & O_CREAT) == O_CREAT) - disposition = FILE_OPEN_IF; - else - cFYI(1, "Create flag not set in create function"); + default: + goto out; + } + /* + * fallthrough to retry, using older open call, this is case + * where server does not support this SMB level, and falsely + * claims capability (also get here for DFS case which should be + * rare for path not covered on files) + */ } + desiredAccess = 0; + if (OPEN_FMODE(oflags) & FMODE_READ) + desiredAccess |= GENERIC_READ; /* is this too little? */ + if (OPEN_FMODE(oflags) & FMODE_WRITE) + desiredAccess |= GENERIC_WRITE; + + disposition = FILE_OVERWRITE_IF; + if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) + disposition = FILE_CREATE; + else if ((oflags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC)) + disposition = FILE_OVERWRITE_IF; + else if ((oflags & O_CREAT) == O_CREAT) + disposition = FILE_OPEN_IF; + else + cFYI(1, "Create flag not set in create function"); + /* BB add processing to set equivalent of mode - e.g. via CreateX with ACLs */ buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); if (buf == NULL) { rc = -ENOMEM; - goto cifs_create_out; + goto out; } /* @@ -250,7 +283,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, if (tcon->ses->capabilities & CAP_NT_SMBS) rc = CIFSSMBOpen(xid, tcon, full_path, disposition, desiredAccess, create_options, - &fileHandle, &oplock, buf, cifs_sb->local_nls, + fileHandle, oplock, buf, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); else rc = -EIO; /* no NT SMB support fall into legacy open below */ @@ -259,17 +292,17 @@ cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, /* old server, retry the open legacy style */ rc = SMBLegacyOpen(xid, tcon, full_path, disposition, desiredAccess, create_options, - &fileHandle, &oplock, buf, cifs_sb->local_nls, + fileHandle, oplock, buf, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); } if (rc) { cFYI(1, "cifs_create returned 0x%x", rc); - goto cifs_create_out; + goto out; } /* If Open reported that we actually created a file then we now have to set the mode if possible */ - if ((tcon->unix_ext) && (oplock & CIFS_CREATE_ACTION)) { + if ((tcon->unix_ext) && (*oplock & CIFS_CREATE_ACTION)) { struct cifs_unix_set_info_args args = { .mode = mode, .ctime = NO_CHANGE_64, @@ -278,6 +311,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, .device = 0, }; + *created |= FILE_CREATED; if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { args.uid = (__u64) current_fsuid(); if (inode->i_mode & S_ISGID) @@ -288,7 +322,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, args.uid = NO_CHANGE_64; args.gid = NO_CHANGE_64; } - CIFSSMBUnixSetFileInfo(xid, tcon, &args, fileHandle, + CIFSSMBUnixSetFileInfo(xid, tcon, &args, *fileHandle, current->tgid); } else { /* BB implement mode setting via Windows security @@ -305,11 +339,11 @@ cifs_create_get_file_info: inode->i_sb, xid); else { rc = cifs_get_inode_info(&newinode, full_path, buf, - inode->i_sb, xid, &fileHandle); + inode->i_sb, xid, fileHandle); if (newinode) { if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) newinode->i_mode = mode; - if ((oplock & CIFS_CREATE_ACTION) && + if ((*oplock & CIFS_CREATE_ACTION) && (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) { newinode->i_uid = current_fsuid(); if (inode->i_mode & S_ISGID) @@ -321,40 +355,139 @@ cifs_create_get_file_info: } cifs_create_set_dentry: - if (rc == 0) - d_instantiate(direntry, newinode); - else + if (rc != 0) { cFYI(1, "Create worked, get_inode_info failed rc = %d", rc); + goto out; + } + d_drop(direntry); + d_add(direntry, newinode); - if (newinode && nd) { - struct cifsFileInfo *pfile_info; - struct file *filp; + /* ENOENT for create? How weird... */ + rc = -ENOENT; + if (!newinode) { + CIFSSMBClose(xid, tcon, *fileHandle); + goto out; + } + rc = 0; - filp = lookup_instantiate_filp(nd, direntry, generic_file_open); - if (IS_ERR(filp)) { - rc = PTR_ERR(filp); - CIFSSMBClose(xid, tcon, fileHandle); - goto cifs_create_out; - } +out: + kfree(buf); + kfree(full_path); + return rc; +} - pfile_info = cifs_new_fileinfo(fileHandle, filp, tlink, oplock); - if (pfile_info == NULL) { - fput(filp); - CIFSSMBClose(xid, tcon, fileHandle); - rc = -ENOMEM; - } - } else { +int +cifs_atomic_open(struct inode *inode, struct dentry *direntry, + struct file *file, unsigned oflags, umode_t mode, + int *opened) +{ + int rc; + int xid; + struct tcon_link *tlink; + struct cifs_tcon *tcon; + __u16 fileHandle; + __u32 oplock; + struct file *filp; + struct cifsFileInfo *pfile_info; + + /* Posix open is only called (at lookup time) for file create now. For + * opens (rather than creates), because we do not know if it is a file + * or directory yet, and current Samba no longer allows us to do posix + * open on dirs, we could end up wasting an open call on what turns out + * to be a dir. For file opens, we wait to call posix open till + * cifs_open. It could be added to atomic_open in the future but the + * performance tradeoff of the extra network request when EISDIR or + * EACCES is returned would have to be weighed against the 50% reduction + * in network traffic in the other paths. + */ + if (!(oflags & O_CREAT)) { + struct dentry *res = cifs_lookup(inode, direntry, 0); + if (IS_ERR(res)) + return PTR_ERR(res); + + return finish_no_open(file, res); + } + + rc = check_name(direntry); + if (rc) + return rc; + + xid = GetXid(); + + cFYI(1, "parent inode = 0x%p name is: %s and dentry = 0x%p", + inode, direntry->d_name.name, direntry); + + tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb)); + filp = ERR_CAST(tlink); + if (IS_ERR(tlink)) + goto free_xid; + + tcon = tlink_tcon(tlink); + + rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode, + &oplock, &fileHandle, opened); + + if (rc) + goto out; + + rc = finish_open(file, direntry, generic_file_open, opened); + if (rc) { CIFSSMBClose(xid, tcon, fileHandle); + goto out; } -cifs_create_out: - kfree(buf); - kfree(full_path); + pfile_info = cifs_new_fileinfo(fileHandle, filp, tlink, oplock); + if (pfile_info == NULL) { + CIFSSMBClose(xid, tcon, fileHandle); + fput(filp); + rc = -ENOMEM; + } + +out: cifs_put_tlink(tlink); +free_xid: FreeXid(xid); return rc; } +int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode, + bool excl) +{ + int rc; + int xid = GetXid(); + /* + * BB below access is probably too much for mknod to request + * but we have to do query and setpathinfo so requesting + * less could fail (unless we want to request getatr and setatr + * permissions (only). At least for POSIX we do not have to + * request so much. + */ + unsigned oflags = O_EXCL | O_CREAT | O_RDWR; + struct tcon_link *tlink; + __u16 fileHandle; + __u32 oplock; + int created = FILE_CREATED; + + cFYI(1, "cifs_create parent inode = 0x%p name is: %s and dentry = 0x%p", + inode, direntry->d_name.name, direntry); + + tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb)); + rc = PTR_ERR(tlink); + if (IS_ERR(tlink)) + goto free_xid; + + rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode, + &oplock, &fileHandle, &created); + if (!rc) + CIFSSMBClose(xid, tlink_tcon(tlink), fileHandle); + + cifs_put_tlink(tlink); +free_xid: + FreeXid(xid); + + return rc; +} + int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode, dev_t device_number) { @@ -488,20 +621,15 @@ mknod_out: struct dentry * cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, - struct nameidata *nd) + unsigned int flags) { int xid; int rc = 0; /* to get around spurious gcc warning, set to zero here */ - __u32 oplock; - __u16 fileHandle = 0; - bool posix_open = false; struct cifs_sb_info *cifs_sb; struct tcon_link *tlink; struct cifs_tcon *pTcon; - struct cifsFileInfo *cfile; struct inode *newInode = NULL; char *full_path = NULL; - struct file *filp; xid = GetXid(); @@ -518,31 +646,9 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, } pTcon = tlink_tcon(tlink); - oplock = pTcon->ses->server->oplocks ? REQ_OPLOCK : 0; - - /* - * Don't allow the separator character in a path component. - * The VFS will not allow "/", but "\" is allowed by posix. - */ - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) { - int i; - for (i = 0; i < direntry->d_name.len; i++) - if (direntry->d_name.name[i] == '\\') { - cFYI(1, "Invalid file name"); - rc = -EINVAL; - goto lookup_out; - } - } - - /* - * O_EXCL: optimize away the lookup, but don't hash the dentry. Let - * the VFS handle the create. - */ - if (nd && (nd->flags & LOOKUP_EXCL)) { - d_instantiate(direntry, NULL); - rc = 0; + rc = check_name(direntry); + if (rc) goto lookup_out; - } /* can not grab the rename sem here since it would deadlock in the cases (beginning of sys_rename itself) @@ -560,80 +666,16 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, } cFYI(1, "Full path: %s inode = 0x%p", full_path, direntry->d_inode); - /* Posix open is only called (at lookup time) for file create now. - * For opens (rather than creates), because we do not know if it - * is a file or directory yet, and current Samba no longer allows - * us to do posix open on dirs, we could end up wasting an open call - * on what turns out to be a dir. For file opens, we wait to call posix - * open till cifs_open. It could be added here (lookup) in the future - * but the performance tradeoff of the extra network request when EISDIR - * or EACCES is returned would have to be weighed against the 50% - * reduction in network traffic in the other paths. - */ if (pTcon->unix_ext) { - if (nd && !(nd->flags & LOOKUP_DIRECTORY) && - (nd->flags & LOOKUP_OPEN) && !pTcon->broken_posix_open && - (nd->intent.open.file->f_flags & O_CREAT)) { - rc = cifs_posix_open(full_path, &newInode, - parent_dir_inode->i_sb, - nd->intent.open.create_mode, - nd->intent.open.file->f_flags, &oplock, - &fileHandle, xid); - /* - * The check below works around a bug in POSIX - * open in samba versions 3.3.1 and earlier where - * open could incorrectly fail with invalid parameter. - * If either that or op not supported returned, follow - * the normal lookup. - */ - switch (rc) { - case 0: - /* - * The server may allow us to open things like - * FIFOs, but the client isn't set up to deal - * with that. If it's not a regular file, just - * close it and proceed as if it were a normal - * lookup. - */ - if (newInode && !S_ISREG(newInode->i_mode)) { - CIFSSMBClose(xid, pTcon, fileHandle); - break; - } - case -ENOENT: - posix_open = true; - case -EOPNOTSUPP: - break; - default: - pTcon->broken_posix_open = true; - } - } - if (!posix_open) - rc = cifs_get_inode_info_unix(&newInode, full_path, - parent_dir_inode->i_sb, xid); - } else + rc = cifs_get_inode_info_unix(&newInode, full_path, + parent_dir_inode->i_sb, xid); + } else { rc = cifs_get_inode_info(&newInode, full_path, NULL, parent_dir_inode->i_sb, xid, NULL); + } if ((rc == 0) && (newInode != NULL)) { d_add(direntry, newInode); - if (posix_open) { - filp = lookup_instantiate_filp(nd, direntry, - generic_file_open); - if (IS_ERR(filp)) { - rc = PTR_ERR(filp); - CIFSSMBClose(xid, pTcon, fileHandle); - goto lookup_out; - } - - cfile = cifs_new_fileinfo(fileHandle, filp, tlink, - oplock); - if (cfile == NULL) { - fput(filp); - CIFSSMBClose(xid, pTcon, fileHandle); - rc = -ENOMEM; - goto lookup_out; - } - } /* since paths are not looked up by component - the parent directories are presumed to be good here */ renew_parental_timestamps(direntry); @@ -658,9 +700,9 @@ lookup_out: } static int -cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd) +cifs_d_revalidate(struct dentry *direntry, unsigned int flags) { - if (nd && (nd->flags & LOOKUP_RCU)) + if (flags & LOOKUP_RCU) return -ECHILD; if (direntry->d_inode) { @@ -689,7 +731,7 @@ cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd) * This may be nfsd (or something), anyway, we can't see the * intent of this. So, since this can be for creation, drop it. */ - if (!nd) + if (!flags) return 0; /* @@ -697,7 +739,7 @@ cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd) * case sensitive name which is specified by user if this is * for creation. */ - if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) + if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) return 0; if (time_after(jiffies, direntry->d_time + HZ) || !lookupCacheEnabled) diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 745da3d0653e..8e8bb49112ff 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -800,7 +800,7 @@ cifs_find_inode(struct inode *inode, void *opaque) return 0; /* if it's not a directory or has no dentries, then flag it */ - if (S_ISDIR(inode->i_mode) && !list_empty(&inode->i_dentry)) + if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) fattr->cf_flags |= CIFS_FATTR_INO_COLLISION; return 1; @@ -825,9 +825,10 @@ static bool inode_has_hashed_dentries(struct inode *inode) { struct dentry *dentry; + struct hlist_node *p; spin_lock(&inode->i_lock); - list_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { if (!d_unhashed(dentry) || IS_ROOT(dentry)) { spin_unlock(&inode->i_lock); return true; diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 0a8224d1c4c5..a4217f02fab2 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -86,9 +86,12 @@ cifs_readdir_lookup(struct dentry *parent, struct qstr *name, dentry = d_lookup(parent, name); if (dentry) { - /* FIXME: check for inode number changes? */ - if (dentry->d_inode != NULL) + inode = dentry->d_inode; + /* update inode in place if i_ino didn't change */ + if (inode && CIFS_I(inode)->uniqueid == fattr->cf_uniqueid) { + cifs_fattr_to_inode(inode, fattr); return dentry; + } d_drop(dentry); dput(dentry); } diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 3097ee58fd7d..f25d4ea14be4 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -365,16 +365,14 @@ cifs_setup_async_request(struct TCP_Server_Info *server, struct kvec *iov, if (mid == NULL) return -ENOMEM; - /* put it on the pending_mid_q */ - spin_lock(&GlobalMid_Lock); - list_add_tail(&mid->qhead, &server->pending_mid_q); - spin_unlock(&GlobalMid_Lock); - rc = cifs_sign_smb2(iov, nvec, server, &mid->sequence_number); - if (rc) - delete_mid(mid); + if (rc) { + DeleteMidQEntry(mid); + return rc; + } + *ret_mid = mid; - return rc; + return 0; } /* @@ -407,17 +405,21 @@ cifs_call_async(struct TCP_Server_Info *server, struct kvec *iov, mid->callback_data = cbdata; mid->mid_state = MID_REQUEST_SUBMITTED; + /* put it on the pending_mid_q */ + spin_lock(&GlobalMid_Lock); + list_add_tail(&mid->qhead, &server->pending_mid_q); + spin_unlock(&GlobalMid_Lock); + + cifs_in_send_inc(server); rc = smb_sendv(server, iov, nvec); cifs_in_send_dec(server); cifs_save_when_sent(mid); mutex_unlock(&server->srv_mutex); - if (rc) - goto out_err; + if (rc == 0) + return 0; - return rc; -out_err: delete_mid(mid); add_credits(server, 1); wake_up(&server->request_q); diff --git a/fs/coda/cache.c b/fs/coda/cache.c index 690157876184..958ae0e0ff8c 100644 --- a/fs/coda/cache.c +++ b/fs/coda/cache.c @@ -89,17 +89,13 @@ int coda_cache_check(struct inode *inode, int mask) /* this won't do any harm: just flag all children */ static void coda_flag_children(struct dentry *parent, int flag) { - struct list_head *child; struct dentry *de; spin_lock(&parent->d_lock); - list_for_each(child, &parent->d_subdirs) - { - de = list_entry(child, struct dentry, d_u.d_child); + list_for_each_entry(de, &parent->d_subdirs, d_u.d_child) { /* don't know what to do with negative dentries */ - if ( ! de->d_inode ) - continue; - coda_flag_inode(de->d_inode, flag); + if (de->d_inode ) + coda_flag_inode(de->d_inode, flag); } spin_unlock(&parent->d_lock); return; diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 177515829062..49fe52d25600 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -30,8 +30,8 @@ #include "coda_int.h" /* dir inode-ops */ -static int coda_create(struct inode *dir, struct dentry *new, umode_t mode, struct nameidata *nd); -static struct dentry *coda_lookup(struct inode *dir, struct dentry *target, struct nameidata *nd); +static int coda_create(struct inode *dir, struct dentry *new, umode_t mode, bool excl); +static struct dentry *coda_lookup(struct inode *dir, struct dentry *target, unsigned int flags); static int coda_link(struct dentry *old_dentry, struct inode *dir_inode, struct dentry *entry); static int coda_unlink(struct inode *dir_inode, struct dentry *entry); @@ -46,7 +46,7 @@ static int coda_rename(struct inode *old_inode, struct dentry *old_dentry, static int coda_readdir(struct file *file, void *buf, filldir_t filldir); /* dentry ops */ -static int coda_dentry_revalidate(struct dentry *de, struct nameidata *nd); +static int coda_dentry_revalidate(struct dentry *de, unsigned int flags); static int coda_dentry_delete(const struct dentry *); /* support routines */ @@ -94,7 +94,7 @@ const struct file_operations coda_dir_operations = { /* inode operations for directories */ /* access routines: lookup, readlink, permission */ -static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, struct nameidata *nd) +static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, unsigned int flags) { struct super_block *sb = dir->i_sb; const char *name = entry->d_name.name; @@ -188,7 +188,7 @@ static inline void coda_dir_drop_nlink(struct inode *dir) } /* creation routines: create, mknod, mkdir, link, symlink */ -static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, struct nameidata *nd) +static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, bool excl) { int error; const char *name=de->d_name.name; @@ -536,12 +536,12 @@ out: } /* called when a cache lookup succeeds */ -static int coda_dentry_revalidate(struct dentry *de, struct nameidata *nd) +static int coda_dentry_revalidate(struct dentry *de, unsigned int flags) { struct inode *inode; struct coda_inode_info *cii; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; inode = de->d_inode; diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 7e6c52d8a207..7414ae24a79b 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -442,7 +442,7 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den static struct dentry * configfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct configfs_dirent * parent_sd = dentry->d_parent->d_fsdata; struct configfs_dirent * sd; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index d013c46402ed..28cca01ca9c9 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -417,7 +417,7 @@ static int cramfs_readdir(struct file *filp, void *dirent, filldir_t filldir) /* * Lookup and fill in the inode data.. */ -static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { unsigned int offset = 0; struct inode *inode = NULL; diff --git a/fs/dcache.c b/fs/dcache.c index 40469044088d..8086636bf796 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -218,7 +218,7 @@ static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); - WARN_ON(!list_empty(&dentry->d_alias)); + WARN_ON(!hlist_unhashed(&dentry->d_alias)); if (dname_external(dentry)) kfree(dentry->d_name.name); kmem_cache_free(dentry_cache, dentry); @@ -267,7 +267,7 @@ static void dentry_iput(struct dentry * dentry) struct inode *inode = dentry->d_inode; if (inode) { dentry->d_inode = NULL; - list_del_init(&dentry->d_alias); + hlist_del_init(&dentry->d_alias); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) @@ -291,7 +291,7 @@ static void dentry_unlink_inode(struct dentry * dentry) { struct inode *inode = dentry->d_inode; dentry->d_inode = NULL; - list_del_init(&dentry->d_alias); + hlist_del_init(&dentry->d_alias); dentry_rcuwalk_barrier(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); @@ -699,10 +699,11 @@ EXPORT_SYMBOL(dget_parent); static struct dentry *__d_find_alias(struct inode *inode, int want_discon) { struct dentry *alias, *discon_alias; + struct hlist_node *p; again: discon_alias = NULL; - list_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) { spin_lock(&alias->d_lock); if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) { if (IS_ROOT(alias) && @@ -737,7 +738,7 @@ struct dentry *d_find_alias(struct inode *inode) { struct dentry *de = NULL; - if (!list_empty(&inode->i_dentry)) { + if (!hlist_empty(&inode->i_dentry)) { spin_lock(&inode->i_lock); de = __d_find_alias(inode, 0); spin_unlock(&inode->i_lock); @@ -753,9 +754,10 @@ EXPORT_SYMBOL(d_find_alias); void d_prune_aliases(struct inode *inode) { struct dentry *dentry; + struct hlist_node *p; restart: spin_lock(&inode->i_lock); - list_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_count) { __dget_dlock(dentry); @@ -977,7 +979,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) inode = dentry->d_inode; if (inode) { dentry->d_inode = NULL; - list_del_init(&dentry->d_alias); + hlist_del_init(&dentry->d_alias); if (dentry->d_op && dentry->d_op->d_iput) dentry->d_op->d_iput(dentry, inode); else @@ -1312,7 +1314,7 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_LIST_HEAD(&dentry->d_subdirs); - INIT_LIST_HEAD(&dentry->d_alias); + INIT_HLIST_NODE(&dentry->d_alias); INIT_LIST_HEAD(&dentry->d_u.d_child); d_set_d_op(dentry, dentry->d_sb->s_d_op); @@ -1400,7 +1402,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) if (inode) { if (unlikely(IS_AUTOMOUNT(inode))) dentry->d_flags |= DCACHE_NEED_AUTOMOUNT; - list_add(&dentry->d_alias, &inode->i_dentry); + hlist_add_head(&dentry->d_alias, &inode->i_dentry); } dentry->d_inode = inode; dentry_rcuwalk_barrier(dentry); @@ -1425,7 +1427,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) void d_instantiate(struct dentry *entry, struct inode * inode) { - BUG_ON(!list_empty(&entry->d_alias)); + BUG_ON(!hlist_unhashed(&entry->d_alias)); if (inode) spin_lock(&inode->i_lock); __d_instantiate(entry, inode); @@ -1458,13 +1460,14 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry, int len = entry->d_name.len; const char *name = entry->d_name.name; unsigned int hash = entry->d_name.hash; + struct hlist_node *p; if (!inode) { __d_instantiate(entry, NULL); return NULL; } - list_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) { /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or @@ -1490,7 +1493,7 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode) { struct dentry *result; - BUG_ON(!list_empty(&entry->d_alias)); + BUG_ON(!hlist_unhashed(&entry->d_alias)); if (inode) spin_lock(&inode->i_lock); @@ -1531,9 +1534,9 @@ static struct dentry * __d_find_any_alias(struct inode *inode) { struct dentry *alias; - if (list_empty(&inode->i_dentry)) + if (hlist_empty(&inode->i_dentry)) return NULL; - alias = list_first_entry(&inode->i_dentry, struct dentry, d_alias); + alias = hlist_entry(inode->i_dentry.first, struct dentry, d_alias); __dget(alias); return alias; } @@ -1607,7 +1610,7 @@ struct dentry *d_obtain_alias(struct inode *inode) spin_lock(&tmp->d_lock); tmp->d_inode = inode; tmp->d_flags |= DCACHE_DISCONNECTED; - list_add(&tmp->d_alias, &inode->i_dentry); + hlist_add_head(&tmp->d_alias, &inode->i_dentry); hlist_bl_lock(&tmp->d_sb->s_anon); hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon); hlist_bl_unlock(&tmp->d_sb->s_anon); @@ -2384,14 +2387,13 @@ static struct dentry *__d_unalias(struct inode *inode, struct dentry *dentry, struct dentry *alias) { struct mutex *m1 = NULL, *m2 = NULL; - struct dentry *ret; + struct dentry *ret = ERR_PTR(-EBUSY); /* If alias and dentry share a parent, then no extra locks required */ if (alias->d_parent == dentry->d_parent) goto out_unalias; /* See lock_rename() */ - ret = ERR_PTR(-EBUSY); if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex)) goto out_err; m1 = &dentry->d_sb->s_vfs_rename_mutex; @@ -2399,8 +2401,10 @@ static struct dentry *__d_unalias(struct inode *inode, goto out_err; m2 = &alias->d_parent->d_inode->i_mutex; out_unalias: - __d_move(alias, dentry); - ret = alias; + if (likely(!d_mountpoint(alias))) { + __d_move(alias, dentry); + ret = alias; + } out_err: spin_unlock(&inode->i_lock); if (m2) @@ -2622,7 +2626,7 @@ global_root: if (!slash) error = prepend(buffer, buflen, "/", 1); if (!error) - error = real_mount(vfsmnt)->mnt_ns ? 1 : 2; + error = is_mounted(vfsmnt) ? 1 : 2; goto out; } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index b80bc846a15a..d17c20fd74e6 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -54,13 +54,12 @@ static struct inode *debugfs_get_inode(struct super_block *sb, umode_t mode, dev break; case S_IFLNK: inode->i_op = &debugfs_link_operations; - inode->i_fop = fops; inode->i_private = data; break; case S_IFDIR: inode->i_op = &simple_dir_inode_operations; - inode->i_fop = fops ? fops : &simple_dir_operations; - inode->i_private = data; + inode->i_fop = &simple_dir_operations; + inode->i_private = NULL; /* directory inodes start off with i_nlink == 2 * (for "." entry) */ @@ -91,13 +90,12 @@ static int debugfs_mknod(struct inode *dir, struct dentry *dentry, return error; } -static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode, - void *data, const struct file_operations *fops) +static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { int res; mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR; - res = debugfs_mknod(dir, dentry, mode, 0, data, fops); + res = debugfs_mknod(dir, dentry, mode, 0, NULL, NULL); if (!res) { inc_nlink(dir); fsnotify_mkdir(dir, dentry); @@ -106,10 +104,10 @@ static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode, } static int debugfs_link(struct inode *dir, struct dentry *dentry, umode_t mode, - void *data, const struct file_operations *fops) + void *data) { mode = (mode & S_IALLUGO) | S_IFLNK; - return debugfs_mknod(dir, dentry, mode, 0, data, fops); + return debugfs_mknod(dir, dentry, mode, 0, data, NULL); } static int debugfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, @@ -293,13 +291,19 @@ static struct file_system_type debug_fs_type = { .kill_sb = kill_litter_super, }; -static int debugfs_create_by_name(const char *name, umode_t mode, - struct dentry *parent, - struct dentry **dentry, - void *data, - const struct file_operations *fops) +struct dentry *__create_file(const char *name, umode_t mode, + struct dentry *parent, void *data, + const struct file_operations *fops) { - int error = 0; + struct dentry *dentry = NULL; + int error; + + pr_debug("debugfs: creating file '%s'\n",name); + + error = simple_pin_fs(&debug_fs_type, &debugfs_mount, + &debugfs_mount_count); + if (error) + goto exit; /* If the parent is not specified, we create it in the root. * We need the root dentry to do this, which is in the super @@ -309,30 +313,35 @@ static int debugfs_create_by_name(const char *name, umode_t mode, if (!parent) parent = debugfs_mount->mnt_root; - *dentry = NULL; + dentry = NULL; mutex_lock(&parent->d_inode->i_mutex); - *dentry = lookup_one_len(name, parent, strlen(name)); - if (!IS_ERR(*dentry)) { + dentry = lookup_one_len(name, parent, strlen(name)); + if (!IS_ERR(dentry)) { switch (mode & S_IFMT) { case S_IFDIR: - error = debugfs_mkdir(parent->d_inode, *dentry, mode, - data, fops); + error = debugfs_mkdir(parent->d_inode, dentry, mode); + break; case S_IFLNK: - error = debugfs_link(parent->d_inode, *dentry, mode, - data, fops); + error = debugfs_link(parent->d_inode, dentry, mode, + data); break; default: - error = debugfs_create(parent->d_inode, *dentry, mode, + error = debugfs_create(parent->d_inode, dentry, mode, data, fops); break; } - dput(*dentry); + dput(dentry); } else - error = PTR_ERR(*dentry); + error = PTR_ERR(dentry); mutex_unlock(&parent->d_inode->i_mutex); - return error; + if (error) { + dentry = NULL; + simple_release_fs(&debugfs_mount, &debugfs_mount_count); + } +exit: + return dentry; } /** @@ -365,25 +374,15 @@ struct dentry *debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) { - struct dentry *dentry = NULL; - int error; - - pr_debug("debugfs: creating file '%s'\n",name); - - error = simple_pin_fs(&debug_fs_type, &debugfs_mount, - &debugfs_mount_count); - if (error) - goto exit; - - error = debugfs_create_by_name(name, mode, parent, &dentry, - data, fops); - if (error) { - dentry = NULL; - simple_release_fs(&debugfs_mount, &debugfs_mount_count); - goto exit; + switch (mode & S_IFMT) { + case S_IFREG: + case 0: + break; + default: + BUG(); } -exit: - return dentry; + + return __create_file(name, mode, parent, data, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file); @@ -407,8 +406,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_file); */ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) { - return debugfs_create_file(name, - S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO, + return __create_file(name, S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO, parent, NULL, NULL); } EXPORT_SYMBOL_GPL(debugfs_create_dir); @@ -446,8 +444,7 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, if (!link) return NULL; - result = debugfs_create_file(name, S_IFLNK | S_IRWXUGO, parent, link, - NULL); + result = __create_file(name, S_IFLNK | S_IRWXUGO, parent, link, NULL); if (!result) kfree(link); return result; diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 979c1e309c73..14afbabe6546 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -439,15 +439,15 @@ static struct dentry *devpts_mount(struct file_system_type *fs_type, return ERR_PTR(error); if (opts.newinstance) - s = sget(fs_type, NULL, set_anon_super, NULL); + s = sget(fs_type, NULL, set_anon_super, flags, NULL); else - s = sget(fs_type, compare_init_pts_sb, set_anon_super, NULL); + s = sget(fs_type, compare_init_pts_sb, set_anon_super, flags, + NULL); if (IS_ERR(s)) return ERR_CAST(s); if (!s->s_root) { - s->s_flags = flags; error = devpts_fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) goto out_undo_sget; diff --git a/fs/direct-io.c b/fs/direct-io.c index 0c85fae37666..1faf4cb56f39 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1258,7 +1258,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, */ BUG_ON(retval == -EIOCBQUEUED); if (dio->is_async && retval == 0 && dio->result && - ((rw & READ) || (dio->result == sdio.size))) + ((rw == READ) || (dio->result == sdio.size))) retval = -EIOCBQUEUED; if (retval != -EIOCBQUEUED) diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c index 534c1d46e69e..1b5d9af937df 100644 --- a/fs/ecryptfs/dentry.c +++ b/fs/ecryptfs/dentry.c @@ -32,7 +32,7 @@ /** * ecryptfs_d_revalidate - revalidate an ecryptfs dentry * @dentry: The ecryptfs dentry - * @nd: The associated nameidata + * @flags: lookup flags * * Called when the VFS needs to revalidate a dentry. This * is called whenever a name lookup finds a dentry in the @@ -42,32 +42,20 @@ * Returns 1 if valid, 0 otherwise. * */ -static int ecryptfs_d_revalidate(struct dentry *dentry, struct nameidata *nd) +static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags) { struct dentry *lower_dentry; struct vfsmount *lower_mnt; - struct dentry *dentry_save = NULL; - struct vfsmount *vfsmount_save = NULL; int rc = 1; - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; lower_dentry = ecryptfs_dentry_to_lower(dentry); lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry); if (!lower_dentry->d_op || !lower_dentry->d_op->d_revalidate) goto out; - if (nd) { - dentry_save = nd->path.dentry; - vfsmount_save = nd->path.mnt; - nd->path.dentry = lower_dentry; - nd->path.mnt = lower_mnt; - } - rc = lower_dentry->d_op->d_revalidate(lower_dentry, nd); - if (nd) { - nd->path.dentry = dentry_save; - nd->path.mnt = vfsmount_save; - } + rc = lower_dentry->d_op->d_revalidate(lower_dentry, flags); if (dentry->d_inode) { struct inode *lower_inode = ecryptfs_inode_to_lower(dentry->d_inode); diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index 867b64c5d84f..989e034f02bd 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -550,20 +550,6 @@ extern struct kmem_cache *ecryptfs_key_record_cache; extern struct kmem_cache *ecryptfs_key_sig_cache; extern struct kmem_cache *ecryptfs_global_auth_tok_cache; extern struct kmem_cache *ecryptfs_key_tfm_cache; -extern struct kmem_cache *ecryptfs_open_req_cache; - -struct ecryptfs_open_req { -#define ECRYPTFS_REQ_PROCESSED 0x00000001 -#define ECRYPTFS_REQ_DROPPED 0x00000002 -#define ECRYPTFS_REQ_ZOMBIE 0x00000004 - u32 flags; - struct file **lower_file; - struct dentry *lower_dentry; - struct vfsmount *lower_mnt; - wait_queue_head_t wait; - struct mutex mux; - struct list_head kthread_ctl_list; -}; struct inode *ecryptfs_get_inode(struct inode *lower_inode, struct super_block *sb); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index a07441a0a878..ffa2be57804d 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -173,7 +173,7 @@ ecryptfs_do_create(struct inode *directory_inode, inode = ERR_CAST(lower_dir_dentry); goto out; } - rc = vfs_create(lower_dir_dentry->d_inode, lower_dentry, mode, NULL); + rc = vfs_create(lower_dir_dentry->d_inode, lower_dentry, mode, true); if (rc) { printk(KERN_ERR "%s: Failure to create dentry in lower fs; " "rc = [%d]\n", __func__, rc); @@ -240,7 +240,6 @@ out: * @dir: The inode of the directory in which to create the file. * @dentry: The eCryptfs dentry * @mode: The mode of the new file. - * @nd: nameidata * * Creates a new file. * @@ -248,7 +247,7 @@ out: */ static int ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry, - umode_t mode, struct nameidata *nd) + umode_t mode, bool excl) { struct inode *ecryptfs_inode; int rc; @@ -270,8 +269,8 @@ ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry, iput(ecryptfs_inode); goto out; } - d_instantiate(ecryptfs_dentry, ecryptfs_inode); unlock_new_inode(ecryptfs_inode); + d_instantiate(ecryptfs_dentry, ecryptfs_inode); out: return rc; } @@ -374,7 +373,7 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry, */ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, struct dentry *ecryptfs_dentry, - struct nameidata *ecryptfs_nd) + unsigned int flags) { char *encrypted_and_encoded_name = NULL; size_t encrypted_and_encoded_name_size; diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c index 69f994a7d524..809e67d05ca3 100644 --- a/fs/ecryptfs/kthread.c +++ b/fs/ecryptfs/kthread.c @@ -27,7 +27,12 @@ #include <linux/mount.h> #include "ecryptfs_kernel.h" -struct kmem_cache *ecryptfs_open_req_cache; +struct ecryptfs_open_req { + struct file **lower_file; + struct path path; + struct completion done; + struct list_head kthread_ctl_list; +}; static struct ecryptfs_kthread_ctl { #define ECRYPTFS_KTHREAD_ZOMBIE 0x00000001 @@ -67,18 +72,10 @@ static int ecryptfs_threadfn(void *ignored) req = list_first_entry(&ecryptfs_kthread_ctl.req_list, struct ecryptfs_open_req, kthread_ctl_list); - mutex_lock(&req->mux); list_del(&req->kthread_ctl_list); - if (!(req->flags & ECRYPTFS_REQ_ZOMBIE)) { - dget(req->lower_dentry); - mntget(req->lower_mnt); - (*req->lower_file) = dentry_open( - req->lower_dentry, req->lower_mnt, - (O_RDWR | O_LARGEFILE), current_cred()); - req->flags |= ECRYPTFS_REQ_PROCESSED; - } - wake_up(&req->wait); - mutex_unlock(&req->mux); + *req->lower_file = dentry_open(&req->path, + (O_RDWR | O_LARGEFILE), current_cred()); + complete(&req->done); } mutex_unlock(&ecryptfs_kthread_ctl.mux); } @@ -111,10 +108,9 @@ void ecryptfs_destroy_kthread(void) ecryptfs_kthread_ctl.flags |= ECRYPTFS_KTHREAD_ZOMBIE; list_for_each_entry(req, &ecryptfs_kthread_ctl.req_list, kthread_ctl_list) { - mutex_lock(&req->mux); - req->flags |= ECRYPTFS_REQ_ZOMBIE; - wake_up(&req->wait); - mutex_unlock(&req->mux); + list_del(&req->kthread_ctl_list); + *req->lower_file = ERR_PTR(-EIO); + complete(&req->done); } mutex_unlock(&ecryptfs_kthread_ctl.mux); kthread_stop(ecryptfs_kthread); @@ -136,34 +132,26 @@ int ecryptfs_privileged_open(struct file **lower_file, struct vfsmount *lower_mnt, const struct cred *cred) { - struct ecryptfs_open_req *req; + struct ecryptfs_open_req req; int flags = O_LARGEFILE; int rc = 0; + init_completion(&req.done); + req.lower_file = lower_file; + req.path.dentry = lower_dentry; + req.path.mnt = lower_mnt; + /* Corresponding dput() and mntput() are done when the * lower file is fput() when all eCryptfs files for the inode are * released. */ - dget(lower_dentry); - mntget(lower_mnt); flags |= IS_RDONLY(lower_dentry->d_inode) ? O_RDONLY : O_RDWR; - (*lower_file) = dentry_open(lower_dentry, lower_mnt, flags, cred); + (*lower_file) = dentry_open(&req.path, flags, cred); if (!IS_ERR(*lower_file)) goto out; - if (flags & O_RDONLY) { + if ((flags & O_ACCMODE) == O_RDONLY) { rc = PTR_ERR((*lower_file)); goto out; } - req = kmem_cache_alloc(ecryptfs_open_req_cache, GFP_KERNEL); - if (!req) { - rc = -ENOMEM; - goto out; - } - mutex_init(&req->mux); - req->lower_file = lower_file; - req->lower_dentry = lower_dentry; - req->lower_mnt = lower_mnt; - init_waitqueue_head(&req->wait); - req->flags = 0; mutex_lock(&ecryptfs_kthread_ctl.mux); if (ecryptfs_kthread_ctl.flags & ECRYPTFS_KTHREAD_ZOMBIE) { rc = -EIO; @@ -171,27 +159,14 @@ int ecryptfs_privileged_open(struct file **lower_file, printk(KERN_ERR "%s: We are in the middle of shutting down; " "aborting privileged request to open lower file\n", __func__); - goto out_free; + goto out; } - list_add_tail(&req->kthread_ctl_list, &ecryptfs_kthread_ctl.req_list); + list_add_tail(&req.kthread_ctl_list, &ecryptfs_kthread_ctl.req_list); mutex_unlock(&ecryptfs_kthread_ctl.mux); wake_up(&ecryptfs_kthread_ctl.wait); - wait_event(req->wait, (req->flags != 0)); - mutex_lock(&req->mux); - BUG_ON(req->flags == 0); - if (req->flags & ECRYPTFS_REQ_DROPPED - || req->flags & ECRYPTFS_REQ_ZOMBIE) { - rc = -EIO; - printk(KERN_WARNING "%s: Privileged open request dropped\n", - __func__); - goto out_unlock; - } - if (IS_ERR(*req->lower_file)) - rc = PTR_ERR(*req->lower_file); -out_unlock: - mutex_unlock(&req->mux); -out_free: - kmem_cache_free(ecryptfs_open_req_cache, req); + wait_for_completion(&req.done); + if (IS_ERR(*lower_file)) + rc = PTR_ERR(*lower_file); out: return rc; } diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 68954937a071..1c0b3b6b75c6 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -499,13 +499,12 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags goto out; } - s = sget(fs_type, NULL, set_anon_super, NULL); + s = sget(fs_type, NULL, set_anon_super, flags, NULL); if (IS_ERR(s)) { rc = PTR_ERR(s); goto out; } - s->s_flags = flags; rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs", BDI_CAP_MAP_COPY); if (rc) goto out1; @@ -682,11 +681,6 @@ static struct ecryptfs_cache_info { .name = "ecryptfs_key_tfm_cache", .size = sizeof(struct ecryptfs_key_tfm), }, - { - .cache = &ecryptfs_open_req_cache, - .name = "ecryptfs_open_req_cache", - .size = sizeof(struct ecryptfs_open_req), - }, }; static void ecryptfs_free_kmem_caches(void) diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c index 3a06f4043df4..c0038f6566d4 100644 --- a/fs/ecryptfs/miscdev.c +++ b/fs/ecryptfs/miscdev.c @@ -49,7 +49,10 @@ ecryptfs_miscdev_poll(struct file *file, poll_table *pt) mutex_lock(&ecryptfs_daemon_hash_mux); /* TODO: Just use file->private_data? */ rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); - BUG_ON(rc || !daemon); + if (rc || !daemon) { + mutex_unlock(&ecryptfs_daemon_hash_mux); + return -EINVAL; + } mutex_lock(&daemon->mux); mutex_unlock(&ecryptfs_daemon_hash_mux); if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) { @@ -122,6 +125,7 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file) goto out_unlock_daemon; } daemon->flags |= ECRYPTFS_DAEMON_MISCDEV_OPEN; + file->private_data = daemon; atomic_inc(&ecryptfs_num_miscdev_opens); out_unlock_daemon: mutex_unlock(&daemon->mux); @@ -152,9 +156,9 @@ ecryptfs_miscdev_release(struct inode *inode, struct file *file) mutex_lock(&ecryptfs_daemon_hash_mux); rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); - BUG_ON(rc || !daemon); + if (rc || !daemon) + daemon = file->private_data; mutex_lock(&daemon->mux); - BUG_ON(daemon->pid != task_pid(current)); BUG_ON(!(daemon->flags & ECRYPTFS_DAEMON_MISCDEV_OPEN)); daemon->flags &= ~ECRYPTFS_DAEMON_MISCDEV_OPEN; atomic_dec(&ecryptfs_num_miscdev_opens); @@ -191,31 +195,32 @@ int ecryptfs_send_miscdev(char *data, size_t data_size, struct ecryptfs_msg_ctx *msg_ctx, u8 msg_type, u16 msg_flags, struct ecryptfs_daemon *daemon) { - int rc = 0; + struct ecryptfs_message *msg; - mutex_lock(&msg_ctx->mux); - msg_ctx->msg = kmalloc((sizeof(*msg_ctx->msg) + data_size), - GFP_KERNEL); - if (!msg_ctx->msg) { - rc = -ENOMEM; + msg = kmalloc((sizeof(*msg) + data_size), GFP_KERNEL); + if (!msg) { printk(KERN_ERR "%s: Out of memory whilst attempting " "to kmalloc(%zd, GFP_KERNEL)\n", __func__, - (sizeof(*msg_ctx->msg) + data_size)); - goto out_unlock; + (sizeof(*msg) + data_size)); + return -ENOMEM; } + + mutex_lock(&msg_ctx->mux); + msg_ctx->msg = msg; msg_ctx->msg->index = msg_ctx->index; msg_ctx->msg->data_len = data_size; msg_ctx->type = msg_type; memcpy(msg_ctx->msg->data, data, data_size); msg_ctx->msg_size = (sizeof(*msg_ctx->msg) + data_size); - mutex_lock(&daemon->mux); list_add_tail(&msg_ctx->daemon_out_list, &daemon->msg_ctx_out_queue); + mutex_unlock(&msg_ctx->mux); + + mutex_lock(&daemon->mux); daemon->num_queued_msg_ctx++; wake_up_interruptible(&daemon->wait); mutex_unlock(&daemon->mux); -out_unlock: - mutex_unlock(&msg_ctx->mux); - return rc; + + return 0; } /* @@ -269,8 +274,16 @@ ecryptfs_miscdev_read(struct file *file, char __user *buf, size_t count, mutex_lock(&ecryptfs_daemon_hash_mux); /* TODO: Just use file->private_data? */ rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); - BUG_ON(rc || !daemon); + if (rc || !daemon) { + mutex_unlock(&ecryptfs_daemon_hash_mux); + return -EINVAL; + } mutex_lock(&daemon->mux); + if (task_pid(current) != daemon->pid) { + mutex_unlock(&daemon->mux); + mutex_unlock(&ecryptfs_daemon_hash_mux); + return -EPERM; + } if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) { rc = 0; mutex_unlock(&ecryptfs_daemon_hash_mux); @@ -307,9 +320,6 @@ check_list: * message from the queue; try again */ goto check_list; } - BUG_ON(euid != daemon->euid); - BUG_ON(current_user_ns() != daemon->user_ns); - BUG_ON(task_pid(current) != daemon->pid); msg_ctx = list_first_entry(&daemon->msg_ctx_out_queue, struct ecryptfs_msg_ctx, daemon_out_list); BUG_ON(!msg_ctx); diff --git a/fs/efs/efs.h b/fs/efs/efs.h index d8305b582ab0..5528926ac7f6 100644 --- a/fs/efs/efs.h +++ b/fs/efs/efs.h @@ -129,7 +129,7 @@ extern struct inode *efs_iget(struct super_block *, unsigned long); extern efs_block_t efs_map_block(struct inode *, efs_block_t); extern int efs_get_block(struct inode *, sector_t, struct buffer_head *, int); -extern struct dentry *efs_lookup(struct inode *, struct dentry *, struct nameidata *); +extern struct dentry *efs_lookup(struct inode *, struct dentry *, unsigned int); extern struct dentry *efs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type); extern struct dentry *efs_fh_to_parent(struct super_block *sb, struct fid *fid, diff --git a/fs/efs/namei.c b/fs/efs/namei.c index 832b10ded82f..96f66d213a19 100644 --- a/fs/efs/namei.c +++ b/fs/efs/namei.c @@ -58,7 +58,8 @@ static efs_ino_t efs_find_entry(struct inode *inode, const char *name, int len) return(0); } -struct dentry *efs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) { +struct dentry *efs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) +{ efs_ino_t inodenum; struct inode *inode = NULL; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 74598f67efeb..1c8b55670804 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1710,7 +1710,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, goto error_tgt_fput; /* Check if EPOLLWAKEUP is allowed */ - if ((epds.events & EPOLLWAKEUP) && !capable(CAP_EPOLLWAKEUP)) + if ((epds.events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND)) epds.events &= ~EPOLLWAKEUP; /* diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c index fc7161d6bf6b..4731fd991efe 100644 --- a/fs/exofs/namei.c +++ b/fs/exofs/namei.c @@ -46,7 +46,7 @@ static inline int exofs_add_nondir(struct dentry *dentry, struct inode *inode) } static struct dentry *exofs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct inode *inode; ino_t ino; @@ -60,7 +60,7 @@ static struct dentry *exofs_lookup(struct inode *dir, struct dentry *dentry, } static int exofs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct inode *inode = exofs_new_inode(dir, mode); int err = PTR_ERR(inode); diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c index 49cf230554a2..24a49d47e935 100644 --- a/fs/exofs/ore.c +++ b/fs/exofs/ore.c @@ -735,13 +735,7 @@ static int _prepare_for_striping(struct ore_io_state *ios) out: ios->numdevs = devs_in_group; ios->pages_consumed = cur_pg; - if (unlikely(ret)) { - if (length == ios->length) - return ret; - else - ios->length -= length; - } - return 0; + return ret; } int ore_create(struct ore_io_state *ios) diff --git a/fs/exofs/ore_raid.c b/fs/exofs/ore_raid.c index d222c77cfa1b..5f376d14fdcc 100644 --- a/fs/exofs/ore_raid.c +++ b/fs/exofs/ore_raid.c @@ -144,26 +144,26 @@ static void _sp2d_reset(struct __stripe_pages_2d *sp2d, { unsigned data_devs = sp2d->data_devs; unsigned group_width = data_devs + sp2d->parity; - unsigned p; + int p, c; if (!sp2d->needed) return; - for (p = 0; p < sp2d->pages_in_unit; p++) { - struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p]; - - if (_1ps->write_count < group_width) { - unsigned c; + for (c = data_devs - 1; c >= 0; --c) + for (p = sp2d->pages_in_unit - 1; p >= 0; --p) { + struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p]; - for (c = 0; c < data_devs; c++) - if (_1ps->page_is_read[c]) { - struct page *page = _1ps->pages[c]; + if (_1ps->page_is_read[c]) { + struct page *page = _1ps->pages[c]; - r4w->put_page(priv, page); - _1ps->page_is_read[c] = false; - } + r4w->put_page(priv, page); + _1ps->page_is_read[c] = false; + } } + for (p = 0; p < sp2d->pages_in_unit; p++) { + struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p]; + memset(_1ps->pages, 0, group_width * sizeof(*_1ps->pages)); _1ps->write_count = 0; _1ps->tx = NULL; @@ -461,16 +461,12 @@ static void _mark_read4write_pages_uptodate(struct ore_io_state *ios, int ret) * ios->sp2d[p][*], xor is calculated the same way. These pages are * allocated/freed and don't go through cache */ -static int _read_4_write(struct ore_io_state *ios) +static int _read_4_write_first_stripe(struct ore_io_state *ios) { - struct ore_io_state *ios_read; struct ore_striping_info read_si; struct __stripe_pages_2d *sp2d = ios->sp2d; u64 offset = ios->si.first_stripe_start; - u64 last_stripe_end; - unsigned bytes_in_stripe = ios->si.bytes_in_stripe; - unsigned i, c, p, min_p = sp2d->pages_in_unit, max_p = -1; - int ret; + unsigned c, p, min_p = sp2d->pages_in_unit, max_p = -1; if (offset == ios->offset) /* Go to start collect $200 */ goto read_last_stripe; @@ -478,6 +474,9 @@ static int _read_4_write(struct ore_io_state *ios) min_p = _sp2d_min_pg(sp2d); max_p = _sp2d_max_pg(sp2d); + ORE_DBGMSG("stripe_start=0x%llx ios->offset=0x%llx min_p=%d max_p=%d\n", + offset, ios->offset, min_p, max_p); + for (c = 0; ; c++) { ore_calc_stripe_info(ios->layout, offset, 0, &read_si); read_si.obj_offset += min_p * PAGE_SIZE; @@ -512,6 +511,18 @@ static int _read_4_write(struct ore_io_state *ios) } read_last_stripe: + return 0; +} + +static int _read_4_write_last_stripe(struct ore_io_state *ios) +{ + struct ore_striping_info read_si; + struct __stripe_pages_2d *sp2d = ios->sp2d; + u64 offset; + u64 last_stripe_end; + unsigned bytes_in_stripe = ios->si.bytes_in_stripe; + unsigned c, p, min_p = sp2d->pages_in_unit, max_p = -1; + offset = ios->offset + ios->length; if (offset % PAGE_SIZE) _add_to_r4w_last_page(ios, &offset); @@ -527,15 +538,15 @@ read_last_stripe: c = _dev_order(ios->layout->group_width * ios->layout->mirrors_p1, ios->layout->mirrors_p1, read_si.par_dev, read_si.dev); - BUG_ON(ios->si.first_stripe_start + bytes_in_stripe != last_stripe_end); - /* unaligned IO must be within a single stripe */ - if (min_p == sp2d->pages_in_unit) { /* Didn't do it yet */ min_p = _sp2d_min_pg(sp2d); max_p = _sp2d_max_pg(sp2d); } + ORE_DBGMSG("offset=0x%llx stripe_end=0x%llx min_p=%d max_p=%d\n", + offset, last_stripe_end, min_p, max_p); + while (offset < last_stripe_end) { struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p]; @@ -568,6 +579,15 @@ read_last_stripe: } read_it: + return 0; +} + +static int _read_4_write_execute(struct ore_io_state *ios) +{ + struct ore_io_state *ios_read; + unsigned i; + int ret; + ios_read = ios->ios_read_4_write; if (!ios_read) return 0; @@ -591,6 +611,8 @@ read_it: } _mark_read4write_pages_uptodate(ios_read, ret); + ore_put_io_state(ios_read); + ios->ios_read_4_write = NULL; /* Might need a reuse at last stripe */ return 0; } @@ -626,8 +648,11 @@ int _ore_add_parity_unit(struct ore_io_state *ios, /* If first stripe, Read in all read4write pages * (if needed) before we calculate the first parity. */ - _read_4_write(ios); + _read_4_write_first_stripe(ios); } + if (!cur_len) /* If last stripe r4w pages of last stripe */ + _read_4_write_last_stripe(ios); + _read_4_write_execute(ios); for (i = 0; i < num_pages; i++) { pages[i] = _raid_page_alloc(); @@ -654,34 +679,14 @@ int _ore_add_parity_unit(struct ore_io_state *ios, int _ore_post_alloc_raid_stuff(struct ore_io_state *ios) { - struct ore_layout *layout = ios->layout; - if (ios->parity_pages) { + struct ore_layout *layout = ios->layout; unsigned pages_in_unit = layout->stripe_unit / PAGE_SIZE; - unsigned stripe_size = ios->si.bytes_in_stripe; - u64 last_stripe, first_stripe; if (_sp2d_alloc(pages_in_unit, layout->group_width, layout->parity, &ios->sp2d)) { return -ENOMEM; } - - /* Round io down to last full strip */ - first_stripe = div_u64(ios->offset, stripe_size); - last_stripe = div_u64(ios->offset + ios->length, stripe_size); - - /* If an IO spans more then a single stripe it must end at - * a stripe boundary. The reminder at the end is pushed into the - * next IO. - */ - if (last_stripe != first_stripe) { - ios->length = last_stripe * stripe_size - ios->offset; - - BUG_ON(!ios->length); - ios->nr_pages = (ios->length + PAGE_SIZE - 1) / - PAGE_SIZE; - ios->si.length = ios->length; /*make it consistent */ - } } return 0; } diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index b0201ca6e9c6..29ab099e3e08 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -19,19 +19,19 @@ #define dprintk(fmt, args...) do{}while(0) -static int get_name(struct vfsmount *mnt, struct dentry *dentry, char *name, - struct dentry *child); +static int get_name(const struct path *path, char *name, struct dentry *child); static int exportfs_get_name(struct vfsmount *mnt, struct dentry *dir, char *name, struct dentry *child) { const struct export_operations *nop = dir->d_sb->s_export_op; + struct path path = {.mnt = mnt, .dentry = dir}; if (nop->get_name) return nop->get_name(dir, name, child); else - return get_name(mnt, dir, name, child); + return get_name(&path, name, child); } /* @@ -44,13 +44,14 @@ find_acceptable_alias(struct dentry *result, { struct dentry *dentry, *toput = NULL; struct inode *inode; + struct hlist_node *p; if (acceptable(context, result)) return result; inode = result->d_inode; spin_lock(&inode->i_lock); - list_for_each_entry(dentry, &inode->i_dentry, d_alias) { + hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { dget(dentry); spin_unlock(&inode->i_lock); if (toput) @@ -248,11 +249,10 @@ static int filldir_one(void * __buf, const char * name, int len, * calls readdir on the parent until it finds an entry with * the same inode number as the child, and returns that. */ -static int get_name(struct vfsmount *mnt, struct dentry *dentry, - char *name, struct dentry *child) +static int get_name(const struct path *path, char *name, struct dentry *child) { const struct cred *cred = current_cred(); - struct inode *dir = dentry->d_inode; + struct inode *dir = path->dentry->d_inode; int error; struct file *file; struct getdents_callback buffer; @@ -266,7 +266,7 @@ static int get_name(struct vfsmount *mnt, struct dentry *dentry, /* * Open the directory ... */ - file = dentry_open(dget(dentry), mntget(mnt), O_RDONLY, cred); + file = dentry_open(path, O_RDONLY, cred); error = PTR_ERR(file); if (IS_ERR(file)) goto out; diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index f663a67d7bf0..73b0d9519836 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -41,8 +41,8 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode) { int err = ext2_add_link(dentry, inode); if (!err) { - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); return 0; } inode_dec_link_count(inode); @@ -55,7 +55,7 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode) * Methods themselves. */ -static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags) { struct inode * inode; ino_t ino; @@ -94,7 +94,7 @@ struct dentry *ext2_get_parent(struct dentry *child) * If the create succeeds, we fill in the inode information * with d_instantiate(). */ -static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode, struct nameidata *nd) +static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode, bool excl) { struct inode *inode; @@ -242,8 +242,8 @@ static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode) if (err) goto out_fail; - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); out: return err; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index b3621cb7ea31..5df3d2d8169c 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -1184,6 +1184,12 @@ static int ext2_sync_fs(struct super_block *sb, int wait) struct ext2_sb_info *sbi = EXT2_SB(sb); struct ext2_super_block *es = EXT2_SB(sb)->s_es; + /* + * Write quota structures to quota file, sync_blockdev() will write + * them to disk later + */ + dquot_writeback_dquots(sb, -1); + spin_lock(&sbi->s_lock); if (es->s_state & cpu_to_le16(EXT2_VALID_FS)) { ext2_debug("setting valid to 0\n"); diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c index 92490e9f85ca..c8fff930790d 100644 --- a/fs/ext3/dir.c +++ b/fs/ext3/dir.c @@ -300,10 +300,11 @@ loff_t ext3_dir_llseek(struct file *file, loff_t offset, int origin) { struct inode *inode = file->f_mapping->host; int dx_dir = is_dx_dir(inode); + loff_t htree_max = ext3_get_htree_eof(file); if (likely(dx_dir)) return generic_file_llseek_size(file, offset, origin, - ext3_get_htree_eof(file)); + htree_max, htree_max); else return generic_file_llseek(file, offset, origin); } diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index eeb63dfc5d20..8f4fddac01a6 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1011,7 +1011,7 @@ errout: return NULL; } -static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags) { struct inode * inode; struct ext3_dir_entry_2 * de; @@ -1671,8 +1671,8 @@ static int ext3_add_nondir(handle_t *handle, int err = ext3_add_entry(handle, dentry, inode); if (!err) { ext3_mark_inode_dirty(handle, inode); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); return 0; } drop_nlink(inode); @@ -1690,7 +1690,7 @@ static int ext3_add_nondir(handle_t *handle, * with d_instantiate(). */ static int ext3_create (struct inode * dir, struct dentry * dentry, umode_t mode, - struct nameidata *nd) + bool excl) { handle_t *handle; struct inode * inode; @@ -1836,8 +1836,8 @@ out_clear_inode: if (err) goto out_clear_inode; - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); out_stop: brelse(dir_block); ext3_journal_stop(handle); diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 8c3a44b7c375..4ac304c55c53 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -2526,6 +2526,11 @@ static int ext3_sync_fs(struct super_block *sb, int wait) tid_t target; trace_ext3_sync_fs(sb, wait); + /* + * Writeback quota in non-journalled quota case - journalled quota has + * no dirty dquots + */ + dquot_writeback_dquots(sb, -1); if (journal_start_commit(EXT3_SB(sb)->s_journal, &target)) { if (wait) log_wait_commit(EXT3_SB(sb)->s_journal, target); diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index aa39e600d159..8e07d2a5a139 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -324,74 +324,27 @@ static inline loff_t ext4_get_htree_eof(struct file *filp) /* - * ext4_dir_llseek() based on generic_file_llseek() to handle both - * non-htree and htree directories, where the "offset" is in terms - * of the filename hash value instead of the byte offset. + * ext4_dir_llseek() calls generic_file_llseek_size to handle htree + * directories, where the "offset" is in terms of the filename hash + * value instead of the byte offset. * - * NOTE: offsets obtained *before* ext4_set_inode_flag(dir, EXT4_INODE_INDEX) - * will be invalid once the directory was converted into a dx directory + * Because we may return a 64-bit hash that is well beyond offset limits, + * we need to pass the max hash as the maximum allowable offset in + * the htree directory case. + * + * For non-htree, ext4_llseek already chooses the proper max offset. */ loff_t ext4_dir_llseek(struct file *file, loff_t offset, int origin) { struct inode *inode = file->f_mapping->host; - loff_t ret = -EINVAL; int dx_dir = is_dx_dir(inode); + loff_t htree_max = ext4_get_htree_eof(file); - mutex_lock(&inode->i_mutex); - - /* NOTE: relative offsets with dx directories might not work - * as expected, as it is difficult to figure out the - * correct offset between dx hashes */ - - switch (origin) { - case SEEK_END: - if (unlikely(offset > 0)) - goto out_err; /* not supported for directories */ - - /* so only negative offsets are left, does that have a - * meaning for directories at all? */ - if (dx_dir) - offset += ext4_get_htree_eof(file); - else - offset += inode->i_size; - break; - case SEEK_CUR: - /* - * Here we special-case the lseek(fd, 0, SEEK_CUR) - * position-querying operation. Avoid rewriting the "same" - * f_pos value back to the file because a concurrent read(), - * write() or lseek() might have altered it - */ - if (offset == 0) { - offset = file->f_pos; - goto out_ok; - } - - offset += file->f_pos; - break; - } - - if (unlikely(offset < 0)) - goto out_err; - - if (!dx_dir) { - if (offset > inode->i_sb->s_maxbytes) - goto out_err; - } else if (offset > ext4_get_htree_eof(file)) - goto out_err; - - /* Special lock needed here? */ - if (offset != file->f_pos) { - file->f_pos = offset; - file->f_version = 0; - } - -out_ok: - ret = offset; -out_err: - mutex_unlock(&inode->i_mutex); - - return ret; + if (likely(dx_dir)) + return generic_file_llseek_size(file, offset, origin, + htree_max, htree_max); + else + return ext4_llseek(file, offset, origin); } /* diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 8c7642a00054..782eecb57e43 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -211,9 +211,9 @@ static int ext4_file_open(struct inode * inode, struct file * filp) } /* - * ext4_llseek() copied from generic_file_llseek() to handle both - * block-mapped and extent-mapped maxbytes values. This should - * otherwise be identical with generic_file_llseek(). + * ext4_llseek() handles both block-mapped and extent-mapped maxbytes values + * by calling generic_file_llseek_size() with the appropriate maxbytes + * value for each. */ loff_t ext4_llseek(struct file *file, loff_t offset, int origin) { @@ -225,7 +225,8 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int origin) else maxbytes = inode->i_sb->s_maxbytes; - return generic_file_llseek_size(file, offset, origin, maxbytes); + return generic_file_llseek_size(file, offset, origin, + maxbytes, i_size_read(inode)); } const struct file_operations ext4_file_operations = { diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index bb6c7d811313..2a1dcea4f12e 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -135,14 +135,7 @@ static int ext4_sync_parent(struct inode *inode) inode = igrab(inode); while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) { ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY); - dentry = NULL; - spin_lock(&inode->i_lock); - if (!list_empty(&inode->i_dentry)) { - dentry = list_first_entry(&inode->i_dentry, - struct dentry, d_alias); - dget(dentry); - } - spin_unlock(&inode->i_lock); + dentry = d_find_any_alias(inode); if (!dentry) break; next = igrab(dentry->d_parent->d_inode); @@ -232,7 +225,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) if (!journal) { ret = __sync_inode(inode, datasync); - if (!ret && !list_empty(&inode->i_dentry)) + if (!ret && !hlist_empty(&inode->i_dentry)) ret = ext4_sync_parent(inode); goto out; } diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index e34deac3f366..7f7dad787603 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -268,7 +268,6 @@ group_extend_out: err = ext4_move_extents(filp, donor_filp, me.orig_start, me.donor_start, me.len, &me.moved_len); mnt_drop_write_file(filp); - mnt_drop_write(filp->f_path.mnt); if (copy_to_user((struct move_extent __user *)arg, &me, sizeof(me))) @@ -390,7 +389,7 @@ group_add_out: if (err) return err; - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) goto resizefs_out; @@ -402,7 +401,7 @@ group_add_out: } if (err == 0) err = err2; - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); resizefs_out: ext4_resize_end(sb); return err; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 5845cd97bf8b..d0d3f0e87f99 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1312,7 +1312,7 @@ errout: return NULL; } -static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode; struct ext4_dir_entry_2 *de; @@ -2072,8 +2072,8 @@ static int ext4_add_nondir(handle_t *handle, int err = ext4_add_entry(handle, dentry, inode); if (!err) { ext4_mark_inode_dirty(handle, inode); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); return 0; } drop_nlink(inode); @@ -2091,7 +2091,7 @@ static int ext4_add_nondir(handle_t *handle, * with d_instantiate(). */ static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { handle_t *handle; struct inode *inode; @@ -2249,8 +2249,8 @@ out_clear_inode: err = ext4_mark_inode_dirty(handle, dir); if (err) goto out_clear_inode; - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); out_stop: brelse(dir_block); ext4_journal_stop(handle); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index eb7aa3e4ef05..d8759401ecae 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4325,6 +4325,11 @@ static int ext4_sync_fs(struct super_block *sb, int wait) trace_ext4_sync_fs(sb, wait); flush_workqueue(sbi->dio_unwritten_wq); + /* + * Writeback quota in non-journalled quota case - journalled quota has + * no dirty dquots + */ + dquot_writeback_dquots(sb, -1); if (jbd2_journal_start_commit(sbi->s_journal, &target)) { if (wait) jbd2_log_wait_commit(sbi->s_journal, target); diff --git a/fs/fat/inode.c b/fs/fat/inode.c index a3d81ebf6d86..0038b32cb362 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -738,22 +738,21 @@ static int fat_encode_fh(struct inode *inode, __u32 *fh, int *lenp, struct inode *parent) { int len = *lenp; - u32 ipos_h, ipos_m, ipos_l; + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + loff_t i_pos; if (len < 5) { *lenp = 5; return 255; /* no room */ } - ipos_h = MSDOS_I(inode)->i_pos >> 8; - ipos_m = (MSDOS_I(inode)->i_pos & 0xf0) << 24; - ipos_l = (MSDOS_I(inode)->i_pos & 0x0f) << 28; + i_pos = fat_i_pos_read(sbi, inode); *lenp = 5; fh[0] = inode->i_ino; fh[1] = inode->i_generation; - fh[2] = ipos_h; - fh[3] = ipos_m | MSDOS_I(inode)->i_logstart; - fh[4] = ipos_l; + fh[2] = i_pos >> 8; + fh[3] = ((i_pos & 0xf0) << 24) | MSDOS_I(inode)->i_logstart; + fh[4] = (i_pos & 0x0f) << 28; if (parent) fh[4] |= MSDOS_I(parent)->i_logstart; return 3; diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index c5938c9084b9..70d993a93805 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -201,7 +201,7 @@ static const struct dentry_operations msdos_dentry_operations = { /***** Get inode using directory and name */ static struct dentry *msdos_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct super_block *sb = dir->i_sb; struct fat_slot_info sinfo; @@ -265,7 +265,7 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name, /***** Create a file */ static int msdos_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct super_block *sb = dir->i_sb; struct inode *inode = NULL; diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 98ae804f5273..6cc480652433 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -41,9 +41,9 @@ static int vfat_revalidate_shortname(struct dentry *dentry) return ret; } -static int vfat_revalidate(struct dentry *dentry, struct nameidata *nd) +static int vfat_revalidate(struct dentry *dentry, unsigned int flags) { - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; /* This is not negative dentry. Always valid. */ @@ -52,9 +52,9 @@ static int vfat_revalidate(struct dentry *dentry, struct nameidata *nd) return vfat_revalidate_shortname(dentry); } -static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd) +static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags) { - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; /* @@ -74,7 +74,7 @@ static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd) * This may be nfsd (or something), anyway, we can't see the * intent of this. So, since this can be for creation, drop it. */ - if (!nd) + if (!flags) return 0; /* @@ -82,7 +82,7 @@ static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd) * case sensitive name which is specified by user if this is * for creation. */ - if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) + if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) return 0; return vfat_revalidate_shortname(dentry); @@ -714,7 +714,7 @@ static int vfat_d_anon_disconn(struct dentry *dentry) } static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct super_block *sb = dir->i_sb; struct fat_slot_info sinfo; @@ -772,7 +772,7 @@ error: } static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct super_block *sb = dir->i_sb; struct inode *inode; diff --git a/fs/fifo.c b/fs/fifo.c index b1a524d798e7..cf6f4345ceb0 100644 --- a/fs/fifo.c +++ b/fs/fifo.c @@ -14,7 +14,7 @@ #include <linux/sched.h> #include <linux/pipe_fs_i.h> -static void wait_for_partner(struct inode* inode, unsigned int *cnt) +static int wait_for_partner(struct inode* inode, unsigned int *cnt) { int cur = *cnt; @@ -23,6 +23,7 @@ static void wait_for_partner(struct inode* inode, unsigned int *cnt) if (signal_pending(current)) break; } + return cur == *cnt ? -ERESTARTSYS : 0; } static void wake_up_partner(struct inode* inode) @@ -67,8 +68,7 @@ static int fifo_open(struct inode *inode, struct file *filp) * seen a writer */ filp->f_version = pipe->w_counter; } else { - wait_for_partner(inode, &pipe->w_counter); - if(signal_pending(current)) + if (wait_for_partner(inode, &pipe->w_counter)) goto err_rd; } } @@ -90,8 +90,7 @@ static int fifo_open(struct inode *inode, struct file *filp) wake_up_partner(inode); if (!pipe->readers) { - wait_for_partner(inode, &pipe->r_counter); - if (signal_pending(current)) + if (wait_for_partner(inode, &pipe->r_counter)) goto err_wr; } break; diff --git a/fs/file_table.c b/fs/file_table.c index a305d9e2d1b2..b3fc4d67a26b 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -23,6 +23,8 @@ #include <linux/lglock.h> #include <linux/percpu_counter.h> #include <linux/percpu.h> +#include <linux/hardirq.h> +#include <linux/task_work.h> #include <linux/ima.h> #include <linux/atomic.h> @@ -251,7 +253,6 @@ static void __fput(struct file *file) } fops_put(file->f_op); put_pid(file->f_owner.pid); - file_sb_list_del(file); if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_dec(inode); if (file->f_mode & FMODE_WRITE) @@ -263,10 +264,77 @@ static void __fput(struct file *file) mntput(mnt); } +static DEFINE_SPINLOCK(delayed_fput_lock); +static LIST_HEAD(delayed_fput_list); +static void delayed_fput(struct work_struct *unused) +{ + LIST_HEAD(head); + spin_lock_irq(&delayed_fput_lock); + list_splice_init(&delayed_fput_list, &head); + spin_unlock_irq(&delayed_fput_lock); + while (!list_empty(&head)) { + struct file *f = list_first_entry(&head, struct file, f_u.fu_list); + list_del_init(&f->f_u.fu_list); + __fput(f); + } +} + +static void ____fput(struct callback_head *work) +{ + __fput(container_of(work, struct file, f_u.fu_rcuhead)); +} + +/* + * If kernel thread really needs to have the final fput() it has done + * to complete, call this. The only user right now is the boot - we + * *do* need to make sure our writes to binaries on initramfs has + * not left us with opened struct file waiting for __fput() - execve() + * won't work without that. Please, don't add more callers without + * very good reasons; in particular, never call that with locks + * held and never call that from a thread that might need to do + * some work on any kind of umount. + */ +void flush_delayed_fput(void) +{ + delayed_fput(NULL); +} + +static DECLARE_WORK(delayed_fput_work, delayed_fput); + void fput(struct file *file) { - if (atomic_long_dec_and_test(&file->f_count)) + if (atomic_long_dec_and_test(&file->f_count)) { + struct task_struct *task = current; + file_sb_list_del(file); + if (unlikely(in_interrupt() || task->flags & PF_KTHREAD)) { + unsigned long flags; + spin_lock_irqsave(&delayed_fput_lock, flags); + list_add(&file->f_u.fu_list, &delayed_fput_list); + schedule_work(&delayed_fput_work); + spin_unlock_irqrestore(&delayed_fput_lock, flags); + return; + } + init_task_work(&file->f_u.fu_rcuhead, ____fput); + task_work_add(task, &file->f_u.fu_rcuhead, true); + } +} + +/* + * synchronous analog of fput(); for kernel threads that might be needed + * in some umount() (and thus can't use flush_delayed_fput() without + * risking deadlocks), need to wait for completion of __fput() and know + * for this specific struct file it won't involve anything that would + * need them. Use only if you really need it - at the very least, + * don't blindly convert fput() by kernel thread to that. + */ +void __fput_sync(struct file *file) +{ + if (atomic_long_dec_and_test(&file->f_count)) { + struct task_struct *task = current; + file_sb_list_del(file); + BUG_ON(!(task->flags & PF_KTHREAD)); __fput(file); + } } EXPORT_SYMBOL(fput); @@ -483,10 +551,8 @@ void mark_files_ro(struct super_block *sb) { struct file *f; -retry: lg_global_lock(&files_lglock); do_file_list_for_each_entry(sb, f) { - struct vfsmount *mnt; if (!S_ISREG(f->f_path.dentry->d_inode->i_mode)) continue; if (!file_count(f)) @@ -499,12 +565,7 @@ retry: if (file_check_writeable(f) != 0) continue; file_release_write(f); - mnt = mntget(f->f_path.mnt); - /* This can sleep, so we can't hold the spinlock. */ - lg_global_unlock(&files_lglock); - mnt_drop_write(mnt); - mntput(mnt); - goto retry; + mnt_drop_write_file(f); } while_file_list_for_each_entry; lg_global_unlock(&files_lglock); } diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c index 3360f1e678ad..bd447e88f208 100644 --- a/fs/freevxfs/vxfs_lookup.c +++ b/fs/freevxfs/vxfs_lookup.c @@ -48,7 +48,7 @@ #define VXFS_BLOCK_PER_PAGE(sbp) ((PAGE_CACHE_SIZE / (sbp)->s_blocksize)) -static struct dentry * vxfs_lookup(struct inode *, struct dentry *, struct nameidata *); +static struct dentry * vxfs_lookup(struct inode *, struct dentry *, unsigned int); static int vxfs_readdir(struct file *, void *, filldir_t); const struct inode_operations vxfs_dir_inode_ops = { @@ -203,7 +203,7 @@ vxfs_inode_by_name(struct inode *dip, struct dentry *dp) * in the return pointer. */ static struct dentry * -vxfs_lookup(struct inode *dip, struct dentry *dp, struct nameidata *nd) +vxfs_lookup(struct inode *dip, struct dentry *dp, unsigned int flags) { struct inode *ip = NULL; ino_t ino; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 41a3ccff18d8..8f660dd6137a 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1315,6 +1315,8 @@ void writeback_inodes_sb_nr(struct super_block *sb, .reason = reason, }; + if (sb->s_bdi == &noop_backing_dev_info) + return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); bdi_queue_work(sb->s_bdi, &work); wait_for_completion(&done); @@ -1398,6 +1400,9 @@ void sync_inodes_sb(struct super_block *sb) .reason = WB_REASON_SYNC, }; + /* Nothing to do? */ + if (sb->s_bdi == &noop_backing_dev_info) + return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); bdi_queue_work(sb->s_bdi, &work); diff --git a/fs/fs_struct.c b/fs/fs_struct.c index e159e682ad4c..5df4775fea03 100644 --- a/fs/fs_struct.c +++ b/fs/fs_struct.c @@ -6,18 +6,6 @@ #include <linux/fs_struct.h> #include "internal.h" -static inline void path_get_longterm(struct path *path) -{ - path_get(path); - mnt_make_longterm(path->mnt); -} - -static inline void path_put_longterm(struct path *path) -{ - mnt_make_shortterm(path->mnt); - path_put(path); -} - /* * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. * It can block. @@ -26,7 +14,7 @@ void set_fs_root(struct fs_struct *fs, struct path *path) { struct path old_root; - path_get_longterm(path); + path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_root = fs->root; @@ -34,7 +22,7 @@ void set_fs_root(struct fs_struct *fs, struct path *path) write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_root.dentry) - path_put_longterm(&old_root); + path_put(&old_root); } /* @@ -45,7 +33,7 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path) { struct path old_pwd; - path_get_longterm(path); + path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_pwd = fs->pwd; @@ -54,7 +42,7 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path) spin_unlock(&fs->lock); if (old_pwd.dentry) - path_put_longterm(&old_pwd); + path_put(&old_pwd); } static inline int replace_path(struct path *p, const struct path *old, const struct path *new) @@ -84,7 +72,7 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root) write_seqcount_end(&fs->seq); while (hits--) { count++; - path_get_longterm(new_root); + path_get(new_root); } spin_unlock(&fs->lock); } @@ -92,13 +80,13 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root) } while_each_thread(g, p); read_unlock(&tasklist_lock); while (count--) - path_put_longterm(old_root); + path_put(old_root); } void free_fs_struct(struct fs_struct *fs) { - path_put_longterm(&fs->root); - path_put_longterm(&fs->pwd); + path_put(&fs->root); + path_put(&fs->pwd); kmem_cache_free(fs_cachep, fs); } @@ -132,9 +120,9 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old) spin_lock(&old->lock); fs->root = old->root; - path_get_longterm(&fs->root); + path_get(&fs->root); fs->pwd = old->pwd; - path_get_longterm(&fs->pwd); + path_get(&fs->pwd); spin_unlock(&old->lock); } return fs; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 334e0b18a014..8964cf3999b2 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -154,7 +154,7 @@ u64 fuse_get_attr_version(struct fuse_conn *fc) * the lookup once more. If the lookup results in the same inode, * then refresh the attributes, timeouts and mark the dentry valid. */ -static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) +static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) { struct inode *inode; @@ -174,7 +174,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) if (!inode) return 0; - if (nd && (nd->flags & LOOKUP_RCU)) + if (flags & LOOKUP_RCU) return -ECHILD; fc = get_fuse_conn(inode); @@ -249,7 +249,7 @@ static struct dentry *fuse_d_add_directory(struct dentry *entry, /* This tries to shrink the subtree below alias */ fuse_invalidate_entry(alias); dput(alias); - if (!list_empty(&inode->i_dentry)) + if (!hlist_empty(&inode->i_dentry)) return ERR_PTR(-EBUSY); } else { dput(alias); @@ -316,7 +316,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name, } static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, - struct nameidata *nd) + unsigned int flags) { int err; struct fuse_entry_out outarg; @@ -370,7 +370,8 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, * 'mknod' + 'open' requests. */ static int fuse_create_open(struct inode *dir, struct dentry *entry, - umode_t mode, struct nameidata *nd) + struct file *file, unsigned flags, + umode_t mode, int *opened) { int err; struct inode *inode; @@ -381,15 +382,11 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, struct fuse_open_out outopen; struct fuse_entry_out outentry; struct fuse_file *ff; - struct file *file; - int flags = nd->intent.open.flags; - - if (fc->no_create) - return -ENOSYS; forget = fuse_alloc_forget(); + err = -ENOMEM; if (!forget) - return -ENOMEM; + goto out_err; req = fuse_get_req(fc); err = PTR_ERR(req); @@ -428,11 +425,8 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, req->out.args[1].value = &outopen; fuse_request_send(fc, req); err = req->out.h.error; - if (err) { - if (err == -ENOSYS) - fc->no_create = 1; + if (err) goto out_free_ff; - } err = -EIO; if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid)) @@ -448,28 +442,74 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, flags &= ~(O_CREAT | O_EXCL | O_TRUNC); fuse_sync_release(ff, flags); fuse_queue_forget(fc, forget, outentry.nodeid, 1); - return -ENOMEM; + err = -ENOMEM; + goto out_err; } kfree(forget); d_instantiate(entry, inode); fuse_change_entry_timeout(entry, &outentry); fuse_invalidate_attr(dir); - file = lookup_instantiate_filp(nd, entry, generic_file_open); - if (IS_ERR(file)) { + err = finish_open(file, entry, generic_file_open, opened); + if (err) { fuse_sync_release(ff, flags); - return PTR_ERR(file); + } else { + file->private_data = fuse_file_get(ff); + fuse_finish_open(inode, file); } - file->private_data = fuse_file_get(ff); - fuse_finish_open(inode, file); - return 0; + return err; - out_free_ff: +out_free_ff: fuse_file_free(ff); - out_put_request: +out_put_request: fuse_put_request(fc, req); - out_put_forget_req: +out_put_forget_req: kfree(forget); +out_err: + return err; +} + +static int fuse_mknod(struct inode *, struct dentry *, umode_t, dev_t); +static int fuse_atomic_open(struct inode *dir, struct dentry *entry, + struct file *file, unsigned flags, + umode_t mode, int *opened) +{ + int err; + struct fuse_conn *fc = get_fuse_conn(dir); + struct dentry *res = NULL; + + if (d_unhashed(entry)) { + res = fuse_lookup(dir, entry, 0); + if (IS_ERR(res)) + return PTR_ERR(res); + + if (res) + entry = res; + } + + if (!(flags & O_CREAT) || entry->d_inode) + goto no_open; + + /* Only creates */ + *opened |= FILE_CREATED; + + if (fc->no_create) + goto mknod; + + err = fuse_create_open(dir, entry, file, flags, mode, opened); + if (err == -ENOSYS) { + fc->no_create = 1; + goto mknod; + } +out_dput: + dput(res); return err; + +mknod: + err = fuse_mknod(dir, entry, mode, 0); + if (err) + goto out_dput; +no_open: + return finish_no_open(file, res); } /* @@ -571,14 +611,8 @@ static int fuse_mknod(struct inode *dir, struct dentry *entry, umode_t mode, } static int fuse_create(struct inode *dir, struct dentry *entry, umode_t mode, - struct nameidata *nd) + bool excl) { - if (nd) { - int err = fuse_create_open(dir, entry, mode, nd); - if (err != -ENOSYS) - return err; - /* Fall back on mknod */ - } return fuse_mknod(dir, entry, mode, 0); } @@ -1646,6 +1680,7 @@ static const struct inode_operations fuse_dir_inode_operations = { .link = fuse_link, .setattr = fuse_setattr, .create = fuse_create, + .atomic_open = fuse_atomic_open, .mknod = fuse_mknod, .permission = fuse_permission, .getattr = fuse_getattr, diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c index 0da8da2c991d..4fddb3c22d25 100644 --- a/fs/gfs2/dentry.c +++ b/fs/gfs2/dentry.c @@ -25,7 +25,7 @@ /** * gfs2_drevalidate - Check directory lookup consistency * @dentry: the mapping to check - * @nd: + * @flags: lookup flags * * Check to make sure the lookup necessary to arrive at this inode from its * parent is still good. @@ -33,7 +33,7 @@ * Returns: 1 if the dentry is ok, 0 if it isn't */ -static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd) +static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags) { struct dentry *parent; struct gfs2_sbd *sdp; @@ -44,7 +44,7 @@ static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd) int error; int had_lock = 0; - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; parent = dget_parent(dentry); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index a9ba2444e077..867674785fcf 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -755,11 +755,8 @@ fail: */ static int gfs2_create(struct inode *dir, struct dentry *dentry, - umode_t mode, struct nameidata *nd) + umode_t mode, bool excl) { - int excl = 0; - if (nd && (nd->flags & LOOKUP_EXCL)) - excl = 1; return gfs2_create_inode(dir, dentry, S_IFREG | mode, 0, NULL, 0, excl); } @@ -775,7 +772,7 @@ static int gfs2_create(struct inode *dir, struct dentry *dentry, */ static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct inode *inode = gfs2_lookupi(dir, &dentry->d_name, 0); if (inode && !IS_ERR(inode)) { diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index b8c250fc4922..6c906078f657 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1286,7 +1286,7 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags, error = -EBUSY; goto error_bdev; } - s = sget(fs_type, test_gfs2_super, set_gfs2_super, bdev); + s = sget(fs_type, test_gfs2_super, set_gfs2_super, flags, bdev); mutex_unlock(&bdev->bd_fsfreeze_mutex); error = PTR_ERR(s); if (IS_ERR(s)) @@ -1316,7 +1316,6 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags, } else { char b[BDEVNAME_SIZE]; - s->s_flags = flags; s->s_mode = mode; strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); sb_set_blocksize(s, block_size(bdev)); @@ -1360,7 +1359,7 @@ static struct dentry *gfs2_mount_meta(struct file_system_type *fs_type, dev_name, error); return ERR_PTR(error); } - s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super, + s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super, flags, path.dentry->d_inode->i_sb->s_bdev); path_put(&path); if (IS_ERR(s)) { diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index b97178e7d397..27b5cc7d6881 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1108,7 +1108,7 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change, } } -int gfs2_quota_sync(struct super_block *sb, int type, int wait) +int gfs2_quota_sync(struct super_block *sb, int type) { struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_quota_data **qda; @@ -1154,7 +1154,7 @@ int gfs2_quota_sync(struct super_block *sb, int type, int wait) static int gfs2_quota_sync_timeo(struct super_block *sb, int type) { - return gfs2_quota_sync(sb, type, 0); + return gfs2_quota_sync(sb, type); } int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id) diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index 90bf1c302a98..f25d98b87904 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -26,7 +26,7 @@ extern int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid); extern void gfs2_quota_change(struct gfs2_inode *ip, s64 change, u32 uid, u32 gid); -extern int gfs2_quota_sync(struct super_block *sb, int type, int wait); +extern int gfs2_quota_sync(struct super_block *sb, int type); extern int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id); extern int gfs2_quota_init(struct gfs2_sbd *sdp); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 713e621c240b..f3d6bbfb32c5 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -838,7 +838,7 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) int error; flush_workqueue(gfs2_delete_workqueue); - gfs2_quota_sync(sdp->sd_vfs, 0, 1); + gfs2_quota_sync(sdp->sd_vfs, 0); gfs2_statfs_sync(sdp->sd_vfs, 0); error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE, @@ -952,6 +952,8 @@ restart: static int gfs2_sync_fs(struct super_block *sb, int wait) { struct gfs2_sbd *sdp = sb->s_fs_info; + + gfs2_quota_sync(sb, -1); if (wait && sdp) gfs2_log_flush(sdp, NULL); return 0; diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 9c2592b1d5ff..73ecc34c4342 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -168,7 +168,7 @@ static ssize_t quota_sync_store(struct gfs2_sbd *sdp, const char *buf, if (simple_strtol(buf, NULL, 0) != 1) return -EINVAL; - gfs2_quota_sync(sdp->sd_vfs, 0, 1); + gfs2_quota_sync(sdp->sd_vfs, 0); return len; } diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c index 62fc14ea4b73..422dde2ec0a1 100644 --- a/fs/hfs/dir.c +++ b/fs/hfs/dir.c @@ -18,7 +18,7 @@ * hfs_lookup() */ static struct dentry *hfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { hfs_cat_rec rec; struct hfs_find_data fd; @@ -187,7 +187,7 @@ static int hfs_dir_release(struct inode *inode, struct file *file) * the directory and the name (and its length) of the new file. */ static int hfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct inode *inode; int res; diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c index 2c16316d2917..a67955a0c36f 100644 --- a/fs/hfs/extent.c +++ b/fs/hfs/extent.c @@ -432,7 +432,7 @@ out: if (inode->i_ino < HFS_FIRSTUSER_CNID) set_bit(HFS_FLG_ALT_MDB_DIRTY, &HFS_SB(sb)->flags); set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags); - sb->s_dirt = 1; + hfs_mark_mdb_dirty(sb); } return res; diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h index 1bf967c6bfdc..8275175acf6e 100644 --- a/fs/hfs/hfs_fs.h +++ b/fs/hfs/hfs_fs.h @@ -14,6 +14,7 @@ #include <linux/mutex.h> #include <linux/buffer_head.h> #include <linux/fs.h> +#include <linux/workqueue.h> #include <asm/byteorder.h> #include <asm/uaccess.h> @@ -137,16 +138,15 @@ struct hfs_sb_info { gid_t s_gid; /* The gid of all files */ int session, part; - struct nls_table *nls_io, *nls_disk; - struct mutex bitmap_lock; - unsigned long flags; - u16 blockoffset; - int fs_div; + struct super_block *sb; + int work_queued; /* non-zero delayed work is queued */ + struct delayed_work mdb_work; /* MDB flush delayed work */ + spinlock_t work_lock; /* protects mdb_work and work_queued */ }; #define HFS_FLG_BITMAP_DIRTY 0 @@ -226,6 +226,9 @@ extern int hfs_compare_dentry(const struct dentry *parent, extern void hfs_asc2mac(struct super_block *, struct hfs_name *, struct qstr *); extern int hfs_mac2asc(struct super_block *, char *, const struct hfs_name *); +/* super.c */ +extern void hfs_mark_mdb_dirty(struct super_block *sb); + extern struct timezone sys_tz; /* @@ -253,7 +256,7 @@ static inline const char *hfs_mdb_name(struct super_block *sb) static inline void hfs_bitmap_dirty(struct super_block *sb) { set_bit(HFS_FLG_BITMAP_DIRTY, &HFS_SB(sb)->flags); - sb->s_dirt = 1; + hfs_mark_mdb_dirty(sb); } #define sb_bread512(sb, sec, data) ({ \ diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 761ec06354b4..ee1bc55677f1 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -220,7 +220,7 @@ struct inode *hfs_new_inode(struct inode *dir, struct qstr *name, umode_t mode) insert_inode_hash(inode); mark_inode_dirty(inode); set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags); - sb->s_dirt = 1; + hfs_mark_mdb_dirty(sb); return inode; } @@ -235,7 +235,7 @@ void hfs_delete_inode(struct inode *inode) if (HFS_I(inode)->cat_key.ParID == cpu_to_be32(HFS_ROOT_CNID)) HFS_SB(sb)->root_dirs--; set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags); - sb->s_dirt = 1; + hfs_mark_mdb_dirty(sb); return; } HFS_SB(sb)->file_count--; @@ -248,7 +248,7 @@ void hfs_delete_inode(struct inode *inode) } } set_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags); - sb->s_dirt = 1; + hfs_mark_mdb_dirty(sb); } void hfs_inode_read_fork(struct inode *inode, struct hfs_extent *ext, @@ -489,7 +489,7 @@ out: } static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct inode *inode = NULL; hfs_cat_rec rec; @@ -644,13 +644,7 @@ static int hfs_file_fsync(struct file *filp, loff_t start, loff_t end, /* sync the superblock to buffers */ sb = inode->i_sb; - if (sb->s_dirt) { - lock_super(sb); - sb->s_dirt = 0; - if (!(sb->s_flags & MS_RDONLY)) - hfs_mdb_commit(sb); - unlock_super(sb); - } + flush_delayed_work_sync(&HFS_SB(sb)->mdb_work); /* .. finally sync the buffers to disk */ err = sync_blockdev(sb->s_bdev); if (!ret) diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index 1563d5ce5764..5fd51a5833ff 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -260,6 +260,10 @@ void hfs_mdb_commit(struct super_block *sb) { struct hfs_mdb *mdb = HFS_SB(sb)->mdb; + if (sb->s_flags & MS_RDONLY) + return; + + lock_buffer(HFS_SB(sb)->mdb_bh); if (test_and_clear_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags)) { /* These parameters may have been modified, so write them back */ mdb->drLsMod = hfs_mtime(); @@ -283,9 +287,13 @@ void hfs_mdb_commit(struct super_block *sb) &mdb->drXTFlSize, NULL); hfs_inode_write_fork(HFS_SB(sb)->cat_tree->inode, mdb->drCTExtRec, &mdb->drCTFlSize, NULL); + + lock_buffer(HFS_SB(sb)->alt_mdb_bh); memcpy(HFS_SB(sb)->alt_mdb, HFS_SB(sb)->mdb, HFS_SECTOR_SIZE); HFS_SB(sb)->alt_mdb->drAtrb |= cpu_to_be16(HFS_SB_ATTRIB_UNMNT); HFS_SB(sb)->alt_mdb->drAtrb &= cpu_to_be16(~HFS_SB_ATTRIB_INCNSTNT); + unlock_buffer(HFS_SB(sb)->alt_mdb_bh); + mark_buffer_dirty(HFS_SB(sb)->alt_mdb_bh); sync_dirty_buffer(HFS_SB(sb)->alt_mdb_bh); } @@ -308,7 +316,11 @@ void hfs_mdb_commit(struct super_block *sb) break; } len = min((int)sb->s_blocksize - off, size); + + lock_buffer(bh); memcpy(bh->b_data + off, ptr, len); + unlock_buffer(bh); + mark_buffer_dirty(bh); brelse(bh); block++; @@ -317,6 +329,7 @@ void hfs_mdb_commit(struct super_block *sb) size -= len; } } + unlock_buffer(HFS_SB(sb)->mdb_bh); } void hfs_mdb_close(struct super_block *sb) diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 7b4c537d6e13..4eb873e0c07b 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -29,43 +29,9 @@ static struct kmem_cache *hfs_inode_cachep; MODULE_LICENSE("GPL"); -/* - * hfs_write_super() - * - * Description: - * This function is called by the VFS only. When the filesystem - * is mounted r/w it updates the MDB on disk. - * Input Variable(s): - * struct super_block *sb: Pointer to the hfs superblock - * Output Variable(s): - * NONE - * Returns: - * void - * Preconditions: - * 'sb' points to a "valid" (struct super_block). - * Postconditions: - * The MDB is marked 'unsuccessfully unmounted' by clearing bit 8 of drAtrb - * (hfs_put_super() must set this flag!). Some MDB fields are updated - * and the MDB buffer is written to disk by calling hfs_mdb_commit(). - */ -static void hfs_write_super(struct super_block *sb) -{ - lock_super(sb); - sb->s_dirt = 0; - - /* sync everything to the buffers */ - if (!(sb->s_flags & MS_RDONLY)) - hfs_mdb_commit(sb); - unlock_super(sb); -} - static int hfs_sync_fs(struct super_block *sb, int wait) { - lock_super(sb); hfs_mdb_commit(sb); - sb->s_dirt = 0; - unlock_super(sb); - return 0; } @@ -78,13 +44,44 @@ static int hfs_sync_fs(struct super_block *sb, int wait) */ static void hfs_put_super(struct super_block *sb) { - if (sb->s_dirt) - hfs_write_super(sb); + cancel_delayed_work_sync(&HFS_SB(sb)->mdb_work); hfs_mdb_close(sb); /* release the MDB's resources */ hfs_mdb_put(sb); } +static void flush_mdb(struct work_struct *work) +{ + struct hfs_sb_info *sbi; + struct super_block *sb; + + sbi = container_of(work, struct hfs_sb_info, mdb_work.work); + sb = sbi->sb; + + spin_lock(&sbi->work_lock); + sbi->work_queued = 0; + spin_unlock(&sbi->work_lock); + + hfs_mdb_commit(sb); +} + +void hfs_mark_mdb_dirty(struct super_block *sb) +{ + struct hfs_sb_info *sbi = HFS_SB(sb); + unsigned long delay; + + if (sb->s_flags & MS_RDONLY) + return; + + spin_lock(&sbi->work_lock); + if (!sbi->work_queued) { + delay = msecs_to_jiffies(dirty_writeback_interval * 10); + queue_delayed_work(system_long_wq, &sbi->mdb_work, delay); + sbi->work_queued = 1; + } + spin_unlock(&sbi->work_lock); +} + /* * hfs_statfs() * @@ -184,7 +181,6 @@ static const struct super_operations hfs_super_operations = { .write_inode = hfs_write_inode, .evict_inode = hfs_evict_inode, .put_super = hfs_put_super, - .write_super = hfs_write_super, .sync_fs = hfs_sync_fs, .statfs = hfs_statfs, .remount_fs = hfs_remount, @@ -387,7 +383,10 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) if (!sbi) return -ENOMEM; + sbi->sb = sb; sb->s_fs_info = sbi; + spin_lock_init(&sbi->work_lock); + INIT_DELAYED_WORK(&sbi->mdb_work, flush_mdb); res = -EINVAL; if (!parse_options((char *)data, sbi)) { diff --git a/fs/hfs/sysdep.c b/fs/hfs/sysdep.c index 19cf291eb91f..91b91fd3a901 100644 --- a/fs/hfs/sysdep.c +++ b/fs/hfs/sysdep.c @@ -13,12 +13,12 @@ /* dentry case-handling: just lowercase everything */ -static int hfs_revalidate_dentry(struct dentry *dentry, struct nameidata *nd) +static int hfs_revalidate_dentry(struct dentry *dentry, unsigned int flags) { struct inode *inode; int diff; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; inode = dentry->d_inode; diff --git a/fs/hfsplus/bitmap.c b/fs/hfsplus/bitmap.c index 1cad80c789cb..4cfbe2edd296 100644 --- a/fs/hfsplus/bitmap.c +++ b/fs/hfsplus/bitmap.c @@ -153,7 +153,7 @@ done: kunmap(page); *max = offset + (curr - pptr) * 32 + i - start; sbi->free_blocks -= *max; - sb->s_dirt = 1; + hfsplus_mark_mdb_dirty(sb); dprint(DBG_BITMAP, "-> %u,%u\n", start, *max); out: mutex_unlock(&sbi->alloc_mutex); @@ -228,7 +228,7 @@ out: set_page_dirty(page); kunmap(page); sbi->free_blocks += len; - sb->s_dirt = 1; + hfsplus_mark_mdb_dirty(sb); mutex_unlock(&sbi->alloc_mutex); return 0; diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 26b53fb09f68..6b9f921ef2fa 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -25,7 +25,7 @@ static inline void hfsplus_instantiate(struct dentry *dentry, /* Find the entry inside dir named dentry->d_name */ static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct inode *inode = NULL; struct hfs_find_data fd; @@ -316,7 +316,7 @@ static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir, inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); sbi->file_count++; - dst_dir->i_sb->s_dirt = 1; + hfsplus_mark_mdb_dirty(dst_dir->i_sb); out: mutex_unlock(&sbi->vh_mutex); return res; @@ -465,7 +465,7 @@ out: } static int hfsplus_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { return hfsplus_mknod(dir, dentry, mode, 0); } diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 4e75ac646fea..558dbb463a4e 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -153,8 +153,11 @@ struct hfsplus_sb_info { gid_t gid; int part, session; - unsigned long flags; + + int work_queued; /* non-zero delayed work is queued */ + struct delayed_work sync_work; /* FS sync delayed work */ + spinlock_t work_lock; /* protects sync_work and work_queued */ }; #define HFSPLUS_SB_WRITEBACKUP 0 @@ -428,7 +431,7 @@ int hfsplus_show_options(struct seq_file *, struct dentry *); /* super.c */ struct inode *hfsplus_iget(struct super_block *, unsigned long); -int hfsplus_sync_fs(struct super_block *sb, int wait); +void hfsplus_mark_mdb_dirty(struct super_block *sb); /* tables.c */ extern u16 hfsplus_case_fold_table[]; diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 82b69ee4dacc..3d8b4a675ba0 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -168,7 +168,7 @@ const struct dentry_operations hfsplus_dentry_operations = { }; static struct dentry *hfsplus_file_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) + struct dentry *dentry, unsigned int flags) { struct hfs_find_data fd; struct super_block *sb = dir->i_sb; @@ -431,7 +431,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode) sbi->file_count++; insert_inode_hash(inode); mark_inode_dirty(inode); - sb->s_dirt = 1; + hfsplus_mark_mdb_dirty(sb); return inode; } @@ -442,7 +442,7 @@ void hfsplus_delete_inode(struct inode *inode) if (S_ISDIR(inode->i_mode)) { HFSPLUS_SB(sb)->folder_count--; - sb->s_dirt = 1; + hfsplus_mark_mdb_dirty(sb); return; } HFSPLUS_SB(sb)->file_count--; @@ -455,7 +455,7 @@ void hfsplus_delete_inode(struct inode *inode) inode->i_size = 0; hfsplus_file_truncate(inode); } - sb->s_dirt = 1; + hfsplus_mark_mdb_dirty(sb); } void hfsplus_inode_read_fork(struct inode *inode, struct hfsplus_fork_raw *fork) diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index a9bca4b8768b..473332098013 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -124,7 +124,7 @@ static int hfsplus_system_write_inode(struct inode *inode) if (fork->total_size != cpu_to_be64(inode->i_size)) { set_bit(HFSPLUS_SB_WRITEBACKUP, &sbi->flags); - inode->i_sb->s_dirt = 1; + hfsplus_mark_mdb_dirty(inode->i_sb); } hfsplus_inode_write_fork(inode, fork); if (tree) @@ -161,7 +161,7 @@ static void hfsplus_evict_inode(struct inode *inode) } } -int hfsplus_sync_fs(struct super_block *sb, int wait) +static int hfsplus_sync_fs(struct super_block *sb, int wait) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); struct hfsplus_vh *vhdr = sbi->s_vhdr; @@ -171,9 +171,7 @@ int hfsplus_sync_fs(struct super_block *sb, int wait) if (!wait) return 0; - dprint(DBG_SUPER, "hfsplus_write_super\n"); - - sb->s_dirt = 0; + dprint(DBG_SUPER, "hfsplus_sync_fs\n"); /* * Explicitly write out the special metadata inodes. @@ -226,12 +224,34 @@ out: return error; } -static void hfsplus_write_super(struct super_block *sb) +static void delayed_sync_fs(struct work_struct *work) { - if (!(sb->s_flags & MS_RDONLY)) - hfsplus_sync_fs(sb, 1); - else - sb->s_dirt = 0; + struct hfsplus_sb_info *sbi; + + sbi = container_of(work, struct hfsplus_sb_info, sync_work.work); + + spin_lock(&sbi->work_lock); + sbi->work_queued = 0; + spin_unlock(&sbi->work_lock); + + hfsplus_sync_fs(sbi->alloc_file->i_sb, 1); +} + +void hfsplus_mark_mdb_dirty(struct super_block *sb) +{ + struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); + unsigned long delay; + + if (sb->s_flags & MS_RDONLY) + return; + + spin_lock(&sbi->work_lock); + if (!sbi->work_queued) { + delay = msecs_to_jiffies(dirty_writeback_interval * 10); + queue_delayed_work(system_long_wq, &sbi->sync_work, delay); + sbi->work_queued = 1; + } + spin_unlock(&sbi->work_lock); } static void hfsplus_put_super(struct super_block *sb) @@ -240,8 +260,7 @@ static void hfsplus_put_super(struct super_block *sb) dprint(DBG_SUPER, "hfsplus_put_super\n"); - if (!sb->s_fs_info) - return; + cancel_delayed_work_sync(&sbi->sync_work); if (!(sb->s_flags & MS_RDONLY) && sbi->s_vhdr) { struct hfsplus_vh *vhdr = sbi->s_vhdr; @@ -328,7 +347,6 @@ static const struct super_operations hfsplus_sops = { .write_inode = hfsplus_write_inode, .evict_inode = hfsplus_evict_inode, .put_super = hfsplus_put_super, - .write_super = hfsplus_write_super, .sync_fs = hfsplus_sync_fs, .statfs = hfsplus_statfs, .remount_fs = hfsplus_remount, @@ -355,6 +373,8 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) sb->s_fs_info = sbi; mutex_init(&sbi->alloc_mutex); mutex_init(&sbi->vh_mutex); + spin_lock_init(&sbi->work_lock); + INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs); hfsplus_fill_defaults(sbi); err = -EINVAL; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 2afa5bbccf9b..124146543aa7 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -553,7 +553,7 @@ static int read_name(struct inode *ino, char *name) } int hostfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct inode *inode; char *name; @@ -595,7 +595,7 @@ int hostfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, } struct dentry *hostfs_lookup(struct inode *ino, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct inode *inode; char *name; diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c index b8472f803f4e..78e12b2e0ea2 100644 --- a/fs/hpfs/dir.c +++ b/fs/hpfs/dir.c @@ -189,7 +189,7 @@ out: * to tell read_inode to read fnode or not. */ -struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { const unsigned char *name = dentry->d_name.name; unsigned len = dentry->d_name.len; diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h index c07ef1f1ced6..ac1ead194db5 100644 --- a/fs/hpfs/hpfs_fn.h +++ b/fs/hpfs/hpfs_fn.h @@ -220,7 +220,7 @@ extern const struct dentry_operations hpfs_dentry_operations; /* dir.c */ -struct dentry *hpfs_lookup(struct inode *, struct dentry *, struct nameidata *); +struct dentry *hpfs_lookup(struct inode *, struct dentry *, unsigned int); extern const struct file_operations hpfs_dir_ops; /* dnode.c */ diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 9083ef8af58c..bc9082482f68 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -115,7 +115,7 @@ bail: return err; } -static int hpfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd) +static int hpfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { const unsigned char *name = dentry->d_name.name; unsigned len = dentry->d_name.len; diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c index d4f93b52cec5..c1dffe47fde2 100644 --- a/fs/hppfs/hppfs.c +++ b/fs/hppfs/hppfs.c @@ -138,7 +138,7 @@ static int file_removed(struct dentry *dentry, const char *file) } static struct dentry *hppfs_lookup(struct inode *ino, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct dentry *proc_dentry, *parent; struct qstr *name = &dentry->d_name; @@ -420,8 +420,7 @@ static int hppfs_open(struct inode *inode, struct file *file) { const struct cred *cred = file->f_cred; struct hppfs_private *data; - struct vfsmount *proc_mnt; - struct dentry *proc_dentry; + struct path path; char *host_file; int err, fd, type, filter; @@ -434,12 +433,11 @@ static int hppfs_open(struct inode *inode, struct file *file) if (host_file == NULL) goto out_free2; - proc_dentry = HPPFS_I(inode)->proc_dentry; - proc_mnt = inode->i_sb->s_fs_info; + path.mnt = inode->i_sb->s_fs_info; + path.dentry = HPPFS_I(inode)->proc_dentry; /* XXX This isn't closed anywhere */ - data->proc_file = dentry_open(dget(proc_dentry), mntget(proc_mnt), - file_mode(file->f_mode), cred); + data->proc_file = dentry_open(&path, file_mode(file->f_mode), cred); err = PTR_ERR(data->proc_file); if (IS_ERR(data->proc_file)) goto out_free1; @@ -484,8 +482,7 @@ static int hppfs_dir_open(struct inode *inode, struct file *file) { const struct cred *cred = file->f_cred; struct hppfs_private *data; - struct vfsmount *proc_mnt; - struct dentry *proc_dentry; + struct path path; int err; err = -ENOMEM; @@ -493,10 +490,9 @@ static int hppfs_dir_open(struct inode *inode, struct file *file) if (data == NULL) goto out; - proc_dentry = HPPFS_I(inode)->proc_dentry; - proc_mnt = inode->i_sb->s_fs_info; - data->proc_file = dentry_open(dget(proc_dentry), mntget(proc_mnt), - file_mode(file->f_mode), cred); + path.mnt = inode->i_sb->s_fs_info; + path.dentry = HPPFS_I(inode)->proc_dentry; + data->proc_file = dentry_open(&path, file_mode(file->f_mode), cred); err = PTR_ERR(data->proc_file); if (IS_ERR(data->proc_file)) goto out_free; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index cc9281b6c628..e13e9bdb0bf5 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -565,7 +565,7 @@ static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mod return retval; } -static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd) +static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0); } diff --git a/fs/inode.c b/fs/inode.c index c99163b1b310..775cbabd4fa5 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -182,7 +182,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) } inode->i_private = NULL; inode->i_mapping = mapping; - INIT_LIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ + INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ #ifdef CONFIG_FS_POSIX_ACL inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED; #endif diff --git a/fs/internal.h b/fs/internal.h index 18bc216ea09d..a6fd56c68b11 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -42,6 +42,11 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait) extern void __init chrdev_init(void); /* + * namei.c + */ +extern int __inode_permission(struct inode *, int); + +/* * namespace.c */ extern int copy_mount_options(const void __user *, unsigned long *); @@ -50,8 +55,6 @@ extern int copy_mount_string(const void __user *, char **); extern struct vfsmount *lookup_mnt(struct path *); extern int finish_automount(struct vfsmount *, struct path *); -extern void mnt_make_longterm(struct vfsmount *); -extern void mnt_make_shortterm(struct vfsmount *); extern int sb_prepare_remount_readonly(struct super_block *); extern void __init mnt_init(void); @@ -84,9 +87,6 @@ extern struct super_block *user_get_super(dev_t); /* * open.c */ -struct nameidata; -extern struct file *nameidata_to_filp(struct nameidata *); -extern void release_open_intent(struct nameidata *); struct open_flags { int open_flag; umode_t mode; diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h index 0e73f63d9274..3620ad1ea9bc 100644 --- a/fs/isofs/isofs.h +++ b/fs/isofs/isofs.h @@ -114,7 +114,7 @@ extern int isofs_name_translate(struct iso_directory_record *, char *, struct in int get_joliet_filename(struct iso_directory_record *, unsigned char *, struct inode *); int get_acorn_filename(struct iso_directory_record *, char *, struct inode *); -extern struct dentry *isofs_lookup(struct inode *, struct dentry *, struct nameidata *); +extern struct dentry *isofs_lookup(struct inode *, struct dentry *, unsigned int flags); extern struct buffer_head *isofs_bread(struct inode *, sector_t); extern int isofs_get_blocks(struct inode *, sector_t, struct buffer_head **, unsigned long); diff --git a/fs/isofs/namei.c b/fs/isofs/namei.c index 1e2946f2a69e..c167028844ed 100644 --- a/fs/isofs/namei.c +++ b/fs/isofs/namei.c @@ -163,7 +163,7 @@ isofs_find_entry(struct inode *dir, struct dentry *dentry, return 0; } -struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { int found; unsigned long uninitialized_var(block); diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index b56018896d5e..ad7774d32095 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -25,9 +25,9 @@ static int jffs2_readdir (struct file *, void *, filldir_t); static int jffs2_create (struct inode *,struct dentry *,umode_t, - struct nameidata *); + bool); static struct dentry *jffs2_lookup (struct inode *,struct dentry *, - struct nameidata *); + unsigned int); static int jffs2_link (struct dentry *,struct inode *,struct dentry *); static int jffs2_unlink (struct inode *,struct dentry *); static int jffs2_symlink (struct inode *,struct dentry *,const char *); @@ -74,7 +74,7 @@ const struct inode_operations jffs2_dir_inode_operations = nice and simple */ static struct dentry *jffs2_lookup(struct inode *dir_i, struct dentry *target, - struct nameidata *nd) + unsigned int flags) { struct jffs2_inode_info *dir_f; struct jffs2_full_dirent *fd = NULL, *fd_list; @@ -175,7 +175,7 @@ static int jffs2_readdir(struct file *filp, void *dirent, filldir_t filldir) static int jffs2_create(struct inode *dir_i, struct dentry *dentry, - umode_t mode, struct nameidata *nd) + umode_t mode, bool excl) { struct jffs2_raw_inode *ri; struct jffs2_inode_info *f, *dir_f; @@ -226,8 +226,8 @@ static int jffs2_create(struct inode *dir_i, struct dentry *dentry, __func__, inode->i_ino, inode->i_mode, inode->i_nlink, f->inocache->pino_nlink, inode->i_mapping->nrpages); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); return 0; fail: @@ -446,8 +446,8 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char mutex_unlock(&dir_f->sem); jffs2_complete_reservation(c); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); return 0; fail: @@ -591,8 +591,8 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode mutex_unlock(&dir_f->sem); jffs2_complete_reservation(c); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); return 0; fail: @@ -766,8 +766,8 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode mutex_unlock(&dir_f->sem); jffs2_complete_reservation(c); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); return 0; fail: diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 07c91ca6017d..3b91a7ad6086 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -73,7 +73,7 @@ static inline void free_ea_wmap(struct inode *inode) * */ static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { int rc = 0; tid_t tid; /* transaction id */ @@ -176,8 +176,8 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode, unlock_new_inode(ip); iput(ip); } else { - d_instantiate(dentry, ip); unlock_new_inode(ip); + d_instantiate(dentry, ip); } out2: @@ -309,8 +309,8 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, umode_t mode) unlock_new_inode(ip); iput(ip); } else { - d_instantiate(dentry, ip); unlock_new_inode(ip); + d_instantiate(dentry, ip); } out2: @@ -1043,8 +1043,8 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry, unlock_new_inode(ip); iput(ip); } else { - d_instantiate(dentry, ip); unlock_new_inode(ip); + d_instantiate(dentry, ip); } out2: @@ -1424,8 +1424,8 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry, unlock_new_inode(ip); iput(ip); } else { - d_instantiate(dentry, ip); unlock_new_inode(ip); + d_instantiate(dentry, ip); } out1: @@ -1436,7 +1436,7 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry, return rc; } -static struct dentry *jfs_lookup(struct inode *dip, struct dentry *dentry, struct nameidata *nd) +static struct dentry *jfs_lookup(struct inode *dip, struct dentry *dentry, unsigned int flags) { struct btstack btstack; ino_t inum; @@ -1570,7 +1570,7 @@ out: return result; } -static int jfs_ci_revalidate(struct dentry *dentry, struct nameidata *nd) +static int jfs_ci_revalidate(struct dentry *dentry, unsigned int flags) { /* * This is not negative dentry. Always valid. @@ -1589,7 +1589,7 @@ static int jfs_ci_revalidate(struct dentry *dentry, struct nameidata *nd) * This may be nfsd (or something), anyway, we can't see the * intent of this. So, since this can be for creation, drop it. */ - if (!nd) + if (!flags) return 0; /* @@ -1597,7 +1597,7 @@ static int jfs_ci_revalidate(struct dentry *dentry, struct nameidata *nd) * case sensitive name which is specified by user if this is * for creation. */ - if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) + if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) return 0; return 1; } diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 4a82950f412f..c55c7452d285 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -601,6 +601,11 @@ static int jfs_sync_fs(struct super_block *sb, int wait) /* log == NULL indicates read-only mount */ if (log) { + /* + * Write quota structures to quota file, sync_blockdev() will + * write them to disk later + */ + dquot_writeback_dquots(sb, -1); jfs_flush_journal(log, wait); jfs_syncpt(log, 0); } diff --git a/fs/libfs.c b/fs/libfs.c index f86ec27a4230..a74cb1725ac6 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -53,7 +53,7 @@ static int simple_delete_dentry(const struct dentry *dentry) * Lookup the data. This is trivial - if the dentry didn't already * exist, we know it is negative. Set d_op to delete negative dentries. */ -struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { static const struct dentry_operations simple_dentry_operations = { .d_delete = simple_delete_dentry, @@ -222,15 +222,15 @@ struct dentry *mount_pseudo(struct file_system_type *fs_type, char *name, const struct super_operations *ops, const struct dentry_operations *dops, unsigned long magic) { - struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL); + struct super_block *s; struct dentry *dentry; struct inode *root; struct qstr d_name = QSTR_INIT(name, strlen(name)); + s = sget(fs_type, NULL, set_anon_super, MS_NOUSER, NULL); if (IS_ERR(s)) return ERR_CAST(s); - s->s_flags = MS_NOUSER; s->s_maxbytes = MAX_LFS_FILESIZE; s->s_blocksize = PAGE_SIZE; s->s_blocksize_bits = PAGE_SHIFT; diff --git a/fs/locks.c b/fs/locks.c index 814c51d0de47..82c353304f9e 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -308,7 +308,7 @@ static int flock_make_lock(struct file *filp, struct file_lock **lock, return 0; } -static int assign_type(struct file_lock *fl, int type) +static int assign_type(struct file_lock *fl, long type) { switch (type) { case F_RDLCK: @@ -445,7 +445,7 @@ static const struct lock_manager_operations lease_manager_ops = { /* * Initialize a lease, use the default lock manager operations */ -static int lease_init(struct file *filp, int type, struct file_lock *fl) +static int lease_init(struct file *filp, long type, struct file_lock *fl) { if (assign_type(fl, type) != 0) return -EINVAL; @@ -463,7 +463,7 @@ static int lease_init(struct file *filp, int type, struct file_lock *fl) } /* Allocate a file_lock initialised to this type of lease */ -static struct file_lock *lease_alloc(struct file *filp, int type) +static struct file_lock *lease_alloc(struct file *filp, long type) { struct file_lock *fl = locks_alloc_lock(); int error = -ENOMEM; @@ -1465,7 +1465,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp) case F_WRLCK: return generic_add_lease(filp, arg, flp); default: - BUG(); + return -EINVAL; } } EXPORT_SYMBOL(generic_setlease); diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c index bea5d1b9954b..26e4a941532f 100644 --- a/fs/logfs/dir.c +++ b/fs/logfs/dir.c @@ -349,7 +349,7 @@ static void logfs_set_name(struct logfs_disk_dentry *dd, struct qstr *name) } static struct dentry *logfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct page *page; struct logfs_disk_dentry *dd; @@ -502,7 +502,7 @@ static int logfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) } static int logfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct inode *inode; diff --git a/fs/logfs/super.c b/fs/logfs/super.c index 97bca623d893..345c24b8a6f8 100644 --- a/fs/logfs/super.c +++ b/fs/logfs/super.c @@ -519,7 +519,7 @@ static struct dentry *logfs_get_sb_device(struct logfs_super *super, log_super("LogFS: Start mount %x\n", mount_count++); err = -EINVAL; - sb = sget(type, logfs_sb_test, logfs_sb_set, super); + sb = sget(type, logfs_sb_test, logfs_sb_set, flags | MS_NOATIME, super); if (IS_ERR(sb)) { super->s_devops->put_device(super); kfree(super); @@ -542,7 +542,6 @@ static struct dentry *logfs_get_sb_device(struct logfs_super *super, sb->s_maxbytes = (1ull << 43) - 1; sb->s_max_links = LOGFS_LINK_MAX; sb->s_op = &logfs_super_operations; - sb->s_flags = flags | MS_NOATIME; err = logfs_read_sb(sb, sb->s_flags & MS_RDONLY); if (err) diff --git a/fs/minix/namei.c b/fs/minix/namei.c index 2d0ee1786305..0db73d9dd668 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -18,7 +18,7 @@ static int add_nondir(struct dentry *dentry, struct inode *inode) return err; } -static struct dentry *minix_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *minix_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags) { struct inode * inode = NULL; ino_t ino; @@ -55,7 +55,7 @@ static int minix_mknod(struct inode * dir, struct dentry *dentry, umode_t mode, } static int minix_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { return minix_mknod(dir, dentry, mode, 0); } diff --git a/fs/mount.h b/fs/mount.h index 4ef36d93e5a2..4f291f9de641 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -22,7 +22,6 @@ struct mount { struct vfsmount mnt; #ifdef CONFIG_SMP struct mnt_pcp __percpu *mnt_pcp; - atomic_t mnt_longterm; /* how many of the refs are longterm */ #else int mnt_count; int mnt_writers; @@ -49,6 +48,8 @@ struct mount { int mnt_ghosts; }; +#define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ + static inline struct mount *real_mount(struct vfsmount *mnt) { return container_of(mnt, struct mount, mnt); @@ -59,6 +60,12 @@ static inline int mnt_has_parent(struct mount *mnt) return mnt != mnt->mnt_parent; } +static inline int is_mounted(struct vfsmount *mnt) +{ + /* neither detached nor internal? */ + return !IS_ERR_OR_NULL(real_mount(mnt)); +} + extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *, int); static inline void get_mnt_ns(struct mnt_namespace *ns) @@ -67,10 +74,12 @@ static inline void get_mnt_ns(struct mnt_namespace *ns) } struct proc_mounts { - struct seq_file m; /* must be the first element */ + struct seq_file m; struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); }; +#define proc_mounts(p) (container_of((p), struct proc_mounts, m)) + extern const struct seq_operations mounts_op; diff --git a/fs/namei.c b/fs/namei.c index 7d694194024a..2ccc35c4dc24 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -315,31 +315,22 @@ static inline int do_inode_permission(struct inode *inode, int mask) } /** - * inode_permission - check for access rights to a given inode - * @inode: inode to check permission on - * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, ...) + * __inode_permission - Check for access rights to a given inode + * @inode: Inode to check permission on + * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * - * Used to check for read/write/execute permissions on an inode. - * We use "fsuid" for this, letting us set arbitrary permissions - * for filesystem access without changing the "normal" uids which - * are used for other things. + * Check for read/write/execute permissions on an inode. * * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. + * + * This does not check for a read-only file system. You probably want + * inode_permission(). */ -int inode_permission(struct inode *inode, int mask) +int __inode_permission(struct inode *inode, int mask) { int retval; if (unlikely(mask & MAY_WRITE)) { - umode_t mode = inode->i_mode; - - /* - * Nobody gets write access to a read-only fs. - */ - if (IS_RDONLY(inode) && - (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) - return -EROFS; - /* * Nobody gets write access to an immutable file. */ @@ -359,6 +350,47 @@ int inode_permission(struct inode *inode, int mask) } /** + * sb_permission - Check superblock-level permissions + * @sb: Superblock of inode to check permission on + * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) + * + * Separate out file-system wide checks from inode-specific permission checks. + */ +static int sb_permission(struct super_block *sb, struct inode *inode, int mask) +{ + if (unlikely(mask & MAY_WRITE)) { + umode_t mode = inode->i_mode; + + /* Nobody gets write access to a read-only fs. */ + if ((sb->s_flags & MS_RDONLY) && + (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) + return -EROFS; + } + return 0; +} + +/** + * inode_permission - Check for access rights to a given inode + * @inode: Inode to check permission on + * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) + * + * Check for read/write/execute permissions on an inode. We use fs[ug]id for + * this, letting us set arbitrary permissions for filesystem access without + * changing the "normal" UIDs which are used for other things. + * + * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. + */ +int inode_permission(struct inode *inode, int mask) +{ + int retval; + + retval = sb_permission(inode->i_sb, inode, mask); + if (retval) + return retval; + return __inode_permission(inode, mask); +} + +/** * path_get - get a reference to a path * @path: path to get the reference to * @@ -395,6 +427,18 @@ EXPORT_SYMBOL(path_put); * to restart the path walk from the beginning in ref-walk mode. */ +static inline void lock_rcu_walk(void) +{ + br_read_lock(&vfsmount_lock); + rcu_read_lock(); +} + +static inline void unlock_rcu_walk(void) +{ + rcu_read_unlock(); + br_read_unlock(&vfsmount_lock); +} + /** * unlazy_walk - try to switch to ref-walk mode. * @nd: nameidata pathwalk data @@ -448,8 +492,7 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry) } mntget(nd->path.mnt); - rcu_read_unlock(); - br_read_unlock(&vfsmount_lock); + unlock_rcu_walk(); nd->flags &= ~LOOKUP_RCU; return 0; @@ -463,25 +506,9 @@ err_root: return -ECHILD; } -/** - * release_open_intent - free up open intent resources - * @nd: pointer to nameidata - */ -void release_open_intent(struct nameidata *nd) +static inline int d_revalidate(struct dentry *dentry, unsigned int flags) { - struct file *file = nd->intent.open.file; - - if (file && !IS_ERR(file)) { - if (file->f_path.dentry == NULL) - put_filp(file); - else - fput(file); - } -} - -static inline int d_revalidate(struct dentry *dentry, struct nameidata *nd) -{ - return dentry->d_op->d_revalidate(dentry, nd); + return dentry->d_op->d_revalidate(dentry, flags); } /** @@ -506,15 +533,13 @@ static int complete_walk(struct nameidata *nd) spin_lock(&dentry->d_lock); if (unlikely(!__d_rcu_to_refcount(dentry, nd->seq))) { spin_unlock(&dentry->d_lock); - rcu_read_unlock(); - br_read_unlock(&vfsmount_lock); + unlock_rcu_walk(); return -ECHILD; } BUG_ON(nd->inode != dentry->d_inode); spin_unlock(&dentry->d_lock); mntget(nd->path.mnt); - rcu_read_unlock(); - br_read_unlock(&vfsmount_lock); + unlock_rcu_walk(); } if (likely(!(nd->flags & LOOKUP_JUMPED))) @@ -527,7 +552,7 @@ static int complete_walk(struct nameidata *nd) return 0; /* Note: we do not d_invalidate() */ - status = d_revalidate(dentry, nd); + status = d_revalidate(dentry, nd->flags); if (status > 0) return 0; @@ -602,10 +627,25 @@ static inline void path_to_nameidata(const struct path *path, nd->path.dentry = path->dentry; } +/* + * Helper to directly jump to a known parsed path from ->follow_link, + * caller must have taken a reference to path beforehand. + */ +void nd_jump_link(struct nameidata *nd, struct path *path) +{ + path_put(&nd->path); + + nd->path = *path; + nd->inode = nd->path.dentry->d_inode; + nd->flags |= LOOKUP_JUMPED; + + BUG_ON(nd->inode->i_op->follow_link); +} + static inline void put_link(struct nameidata *nd, struct path *link, void *cookie) { struct inode *inode = link->dentry->d_inode; - if (!IS_ERR(cookie) && inode->i_op->put_link) + if (inode->i_op->put_link) inode->i_op->put_link(link->dentry, nd, cookie); path_put(link); } @@ -613,19 +653,19 @@ static inline void put_link(struct nameidata *nd, struct path *link, void *cooki static __always_inline int follow_link(struct path *link, struct nameidata *nd, void **p) { - int error; struct dentry *dentry = link->dentry; + int error; + char *s; BUG_ON(nd->flags & LOOKUP_RCU); if (link->mnt == nd->path.mnt) mntget(link->mnt); - if (unlikely(current->total_link_count >= 40)) { - *p = ERR_PTR(-ELOOP); /* no ->put_link(), please */ - path_put(&nd->path); - return -ELOOP; - } + error = -ELOOP; + if (unlikely(current->total_link_count >= 40)) + goto out_put_nd_path; + cond_resched(); current->total_link_count++; @@ -633,30 +673,28 @@ follow_link(struct path *link, struct nameidata *nd, void **p) nd_set_link(nd, NULL); error = security_inode_follow_link(link->dentry, nd); - if (error) { - *p = ERR_PTR(error); /* no ->put_link(), please */ - path_put(&nd->path); - return error; - } + if (error) + goto out_put_nd_path; nd->last_type = LAST_BIND; *p = dentry->d_inode->i_op->follow_link(dentry, nd); error = PTR_ERR(*p); - if (!IS_ERR(*p)) { - char *s = nd_get_link(nd); - error = 0; - if (s) - error = __vfs_follow_link(nd, s); - else if (nd->last_type == LAST_BIND) { - nd->flags |= LOOKUP_JUMPED; - nd->inode = nd->path.dentry->d_inode; - if (nd->inode->i_op->follow_link) { - /* stepped on a _really_ weird one */ - path_put(&nd->path); - error = -ELOOP; - } - } + if (IS_ERR(*p)) + goto out_put_nd_path; + + error = 0; + s = nd_get_link(nd); + if (s) { + error = __vfs_follow_link(nd, s); + if (unlikely(error)) + put_link(nd, link, *p); } + + return error; + +out_put_nd_path: + path_put(&nd->path); + path_put(link); return error; } @@ -675,6 +713,16 @@ static int follow_up_rcu(struct path *path) return 1; } +/* + * follow_up - Find the mountpoint of path's vfsmount + * + * Given a path, find the mountpoint of its source file system. + * Replace @path with the path of the mountpoint in the parent mount. + * Up is towards /. + * + * Return 1 if we went up a level and 0 if we were already at the + * root. + */ int follow_up(struct path *path) { struct mount *mnt = real_mount(path->mnt); @@ -683,7 +731,7 @@ int follow_up(struct path *path) br_read_lock(&vfsmount_lock); parent = mnt->mnt_parent; - if (&parent->mnt == path->mnt) { + if (parent == mnt) { br_read_unlock(&vfsmount_lock); return 0; } @@ -946,8 +994,7 @@ failed: nd->flags &= ~LOOKUP_RCU; if (!(nd->flags & LOOKUP_ROOT)) nd->root.mnt = NULL; - rcu_read_unlock(); - br_read_unlock(&vfsmount_lock); + unlock_rcu_walk(); return -ECHILD; } @@ -1048,7 +1095,7 @@ static void follow_dotdot(struct nameidata *nd) * dir->d_inode->i_mutex must be held */ static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir, - struct nameidata *nd, bool *need_lookup) + unsigned int flags, bool *need_lookup) { struct dentry *dentry; int error; @@ -1059,7 +1106,7 @@ static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir, if (d_need_lookup(dentry)) { *need_lookup = true; } else if (dentry->d_flags & DCACHE_OP_REVALIDATE) { - error = d_revalidate(dentry, nd); + error = d_revalidate(dentry, flags); if (unlikely(error <= 0)) { if (error < 0) { dput(dentry); @@ -1089,7 +1136,7 @@ static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir, * dir->d_inode->i_mutex must be held */ static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct dentry *old; @@ -1099,7 +1146,7 @@ static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry, return ERR_PTR(-ENOENT); } - old = dir->i_op->lookup(dir, dentry, nd); + old = dir->i_op->lookup(dir, dentry, flags); if (unlikely(old)) { dput(dentry); dentry = old; @@ -1108,16 +1155,16 @@ static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry, } static struct dentry *__lookup_hash(struct qstr *name, - struct dentry *base, struct nameidata *nd) + struct dentry *base, unsigned int flags) { bool need_lookup; struct dentry *dentry; - dentry = lookup_dcache(name, base, nd, &need_lookup); + dentry = lookup_dcache(name, base, flags, &need_lookup); if (!need_lookup) return dentry; - return lookup_real(base->d_inode, dentry, nd); + return lookup_real(base->d_inode, dentry, flags); } /* @@ -1167,7 +1214,7 @@ static int lookup_fast(struct nameidata *nd, struct qstr *name, if (unlikely(d_need_lookup(dentry))) goto unlazy; if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) { - status = d_revalidate(dentry, nd); + status = d_revalidate(dentry, nd->flags); if (unlikely(status <= 0)) { if (status != -ECHILD) need_reval = 0; @@ -1197,7 +1244,7 @@ unlazy: } if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval) - status = d_revalidate(dentry, nd); + status = d_revalidate(dentry, nd->flags); if (unlikely(status <= 0)) { if (status < 0) { dput(dentry); @@ -1236,7 +1283,7 @@ static int lookup_slow(struct nameidata *nd, struct qstr *name, BUG_ON(nd->inode != parent->d_inode); mutex_lock(&parent->d_inode->i_mutex); - dentry = __lookup_hash(name, parent, nd); + dentry = __lookup_hash(name, parent, nd->flags); mutex_unlock(&parent->d_inode->i_mutex); if (IS_ERR(dentry)) return PTR_ERR(dentry); @@ -1284,8 +1331,7 @@ static void terminate_walk(struct nameidata *nd) nd->flags &= ~LOOKUP_RCU; if (!(nd->flags & LOOKUP_ROOT)) nd->root.mnt = NULL; - rcu_read_unlock(); - br_read_unlock(&vfsmount_lock); + unlock_rcu_walk(); } } @@ -1383,9 +1429,10 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd) void *cookie; res = follow_link(&link, nd, &cookie); - if (!res) - res = walk_component(nd, path, &nd->last, - nd->last_type, LOOKUP_FOLLOW); + if (res) + break; + res = walk_component(nd, path, &nd->last, + nd->last_type, LOOKUP_FOLLOW); put_link(nd, &link, cookie); } while (res > 0); @@ -1651,8 +1698,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, nd->path = nd->root; nd->inode = inode; if (flags & LOOKUP_RCU) { - br_read_lock(&vfsmount_lock); - rcu_read_lock(); + lock_rcu_walk(); nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); } else { path_get(&nd->path); @@ -1664,8 +1710,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, if (*name=='/') { if (flags & LOOKUP_RCU) { - br_read_lock(&vfsmount_lock); - rcu_read_lock(); + lock_rcu_walk(); set_root_rcu(nd); } else { set_root(nd); @@ -1677,8 +1722,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, struct fs_struct *fs = current->fs; unsigned seq; - br_read_lock(&vfsmount_lock); - rcu_read_lock(); + lock_rcu_walk(); do { seq = read_seqcount_begin(&fs->seq); @@ -1713,8 +1757,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, if (fput_needed) *fp = file; nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); - br_read_lock(&vfsmount_lock); - rcu_read_lock(); + lock_rcu_walk(); } else { path_get(&file->f_path); fput_light(file, fput_needed); @@ -1777,8 +1820,9 @@ static int path_lookupat(int dfd, const char *name, struct path link = path; nd->flags |= LOOKUP_PARENT; err = follow_link(&link, nd, &cookie); - if (!err) - err = lookup_last(nd, &path); + if (err) + break; + err = lookup_last(nd, &path); put_link(nd, &link, cookie); } } @@ -1821,9 +1865,27 @@ static int do_path_lookup(int dfd, const char *name, return retval; } -int kern_path_parent(const char *name, struct nameidata *nd) +/* does lookup, returns the object with parent locked */ +struct dentry *kern_path_locked(const char *name, struct path *path) { - return do_path_lookup(AT_FDCWD, name, LOOKUP_PARENT, nd); + struct nameidata nd; + struct dentry *d; + int err = do_path_lookup(AT_FDCWD, name, LOOKUP_PARENT, &nd); + if (err) + return ERR_PTR(err); + if (nd.last_type != LAST_NORM) { + path_put(&nd.path); + return ERR_PTR(-EINVAL); + } + mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); + d = __lookup_hash(&nd.last, nd.path.dentry, 0); + if (IS_ERR(d)) { + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + path_put(&nd.path); + return d; + } + *path = nd.path; + return d; } int kern_path(const char *name, unsigned int flags, struct path *path) @@ -1866,7 +1928,7 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, */ static struct dentry *lookup_hash(struct nameidata *nd) { - return __lookup_hash(&nd->last, nd->path.dentry, nd); + return __lookup_hash(&nd->last, nd->path.dentry, nd->flags); } /** @@ -1913,7 +1975,7 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) if (err) return ERR_PTR(err); - return __lookup_hash(&this, base, NULL); + return __lookup_hash(&this, base, 0); } int user_path_at_empty(int dfd, const char __user *name, unsigned flags, @@ -2086,10 +2148,9 @@ void unlock_rename(struct dentry *p1, struct dentry *p2) } int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool want_excl) { int error = may_create(dir, dentry); - if (error) return error; @@ -2100,7 +2161,7 @@ int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, error = security_inode_create(dir, dentry, mode); if (error) return error; - error = dir->i_op->create(dir, dentry, mode, nd); + error = dir->i_op->create(dir, dentry, mode, want_excl); if (!error) fsnotify_create(dir, dentry); return error; @@ -2187,21 +2248,275 @@ static inline int open_to_namei_flags(int flag) return flag; } +static int may_o_create(struct path *dir, struct dentry *dentry, umode_t mode) +{ + int error = security_path_mknod(dir, dentry, mode, 0); + if (error) + return error; + + error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); + if (error) + return error; + + return security_inode_create(dir->dentry->d_inode, dentry, mode); +} + /* - * Handle the last step of open() + * Attempt to atomically look up, create and open a file from a negative + * dentry. + * + * Returns 0 if successful. The file will have been created and attached to + * @file by the filesystem calling finish_open(). + * + * Returns 1 if the file was looked up only or didn't need creating. The + * caller will need to perform the open themselves. @path will have been + * updated to point to the new dentry. This may be negative. + * + * Returns an error code otherwise. + */ +static int atomic_open(struct nameidata *nd, struct dentry *dentry, + struct path *path, struct file *file, + const struct open_flags *op, + bool *want_write, bool need_lookup, + int *opened) +{ + struct inode *dir = nd->path.dentry->d_inode; + unsigned open_flag = open_to_namei_flags(op->open_flag); + umode_t mode; + int error; + int acc_mode; + int create_error = 0; + struct dentry *const DENTRY_NOT_SET = (void *) -1UL; + + BUG_ON(dentry->d_inode); + + /* Don't create child dentry for a dead directory. */ + if (unlikely(IS_DEADDIR(dir))) { + error = -ENOENT; + goto out; + } + + mode = op->mode & S_IALLUGO; + if ((open_flag & O_CREAT) && !IS_POSIXACL(dir)) + mode &= ~current_umask(); + + if (open_flag & O_EXCL) { + open_flag &= ~O_TRUNC; + *opened |= FILE_CREATED; + } + + /* + * Checking write permission is tricky, bacuse we don't know if we are + * going to actually need it: O_CREAT opens should work as long as the + * file exists. But checking existence breaks atomicity. The trick is + * to check access and if not granted clear O_CREAT from the flags. + * + * Another problem is returing the "right" error value (e.g. for an + * O_EXCL open we want to return EEXIST not EROFS). + */ + if ((open_flag & (O_CREAT | O_TRUNC)) || + (open_flag & O_ACCMODE) != O_RDONLY) { + error = mnt_want_write(nd->path.mnt); + if (!error) { + *want_write = true; + } else if (!(open_flag & O_CREAT)) { + /* + * No O_CREATE -> atomicity not a requirement -> fall + * back to lookup + open + */ + goto no_open; + } else if (open_flag & (O_EXCL | O_TRUNC)) { + /* Fall back and fail with the right error */ + create_error = error; + goto no_open; + } else { + /* No side effects, safe to clear O_CREAT */ + create_error = error; + open_flag &= ~O_CREAT; + } + } + + if (open_flag & O_CREAT) { + error = may_o_create(&nd->path, dentry, op->mode); + if (error) { + create_error = error; + if (open_flag & O_EXCL) + goto no_open; + open_flag &= ~O_CREAT; + } + } + + if (nd->flags & LOOKUP_DIRECTORY) + open_flag |= O_DIRECTORY; + + file->f_path.dentry = DENTRY_NOT_SET; + file->f_path.mnt = nd->path.mnt; + error = dir->i_op->atomic_open(dir, dentry, file, open_flag, mode, + opened); + if (error < 0) { + if (create_error && error == -ENOENT) + error = create_error; + goto out; + } + + acc_mode = op->acc_mode; + if (*opened & FILE_CREATED) { + fsnotify_create(dir, dentry); + acc_mode = MAY_OPEN; + } + + if (error) { /* returned 1, that is */ + if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) { + error = -EIO; + goto out; + } + if (file->f_path.dentry) { + dput(dentry); + dentry = file->f_path.dentry; + } + goto looked_up; + } + + /* + * We didn't have the inode before the open, so check open permission + * here. + */ + error = may_open(&file->f_path, acc_mode, open_flag); + if (error) + fput(file); + +out: + dput(dentry); + return error; + +no_open: + if (need_lookup) { + dentry = lookup_real(dir, dentry, nd->flags); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + + if (create_error) { + int open_flag = op->open_flag; + + error = create_error; + if ((open_flag & O_EXCL)) { + if (!dentry->d_inode) + goto out; + } else if (!dentry->d_inode) { + goto out; + } else if ((open_flag & O_TRUNC) && + S_ISREG(dentry->d_inode->i_mode)) { + goto out; + } + /* will fail later, go on to get the right error */ + } + } +looked_up: + path->dentry = dentry; + path->mnt = nd->path.mnt; + return 1; +} + +/* + * Look up and maybe create and open the last component. + * + * Must be called with i_mutex held on parent. + * + * Returns 0 if the file was successfully atomically created (if necessary) and + * opened. In this case the file will be returned attached to @file. + * + * Returns 1 if the file was not completely opened at this time, though lookups + * and creations will have been performed and the dentry returned in @path will + * be positive upon return if O_CREAT was specified. If O_CREAT wasn't + * specified then a negative dentry may be returned. + * + * An error code is returned otherwise. + * + * FILE_CREATE will be set in @*opened if the dentry was created and will be + * cleared otherwise prior to returning. */ -static struct file *do_last(struct nameidata *nd, struct path *path, - const struct open_flags *op, const char *pathname) +static int lookup_open(struct nameidata *nd, struct path *path, + struct file *file, + const struct open_flags *op, + bool *want_write, int *opened) { struct dentry *dir = nd->path.dentry; + struct inode *dir_inode = dir->d_inode; struct dentry *dentry; + int error; + bool need_lookup; + + *opened &= ~FILE_CREATED; + dentry = lookup_dcache(&nd->last, dir, nd->flags, &need_lookup); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + + /* Cached positive dentry: will open in f_op->open */ + if (!need_lookup && dentry->d_inode) + goto out_no_open; + + if ((nd->flags & LOOKUP_OPEN) && dir_inode->i_op->atomic_open) { + return atomic_open(nd, dentry, path, file, op, want_write, + need_lookup, opened); + } + + if (need_lookup) { + BUG_ON(dentry->d_inode); + + dentry = lookup_real(dir_inode, dentry, nd->flags); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + } + + /* Negative dentry, just create the file */ + if (!dentry->d_inode && (op->open_flag & O_CREAT)) { + umode_t mode = op->mode; + if (!IS_POSIXACL(dir->d_inode)) + mode &= ~current_umask(); + /* + * This write is needed to ensure that a + * rw->ro transition does not occur between + * the time when the file is created and when + * a permanent write count is taken through + * the 'struct file' in finish_open(). + */ + error = mnt_want_write(nd->path.mnt); + if (error) + goto out_dput; + *want_write = true; + *opened |= FILE_CREATED; + error = security_path_mknod(&nd->path, dentry, mode, 0); + if (error) + goto out_dput; + error = vfs_create(dir->d_inode, dentry, mode, + nd->flags & LOOKUP_EXCL); + if (error) + goto out_dput; + } +out_no_open: + path->dentry = dentry; + path->mnt = nd->path.mnt; + return 1; + +out_dput: + dput(dentry); + return error; +} + +/* + * Handle the last step of open() + */ +static int do_last(struct nameidata *nd, struct path *path, + struct file *file, const struct open_flags *op, + int *opened, const char *pathname) +{ + struct dentry *dir = nd->path.dentry; int open_flag = op->open_flag; - int will_truncate = open_flag & O_TRUNC; - int want_write = 0; + bool will_truncate = (open_flag & O_TRUNC) != 0; + bool want_write = false; int acc_mode = op->acc_mode; - struct file *filp; struct inode *inode; - int symlink_ok = 0; + bool symlink_ok = false; struct path save_parent = { .dentry = NULL, .mnt = NULL }; bool retried = false; int error; @@ -2214,112 +2529,99 @@ static struct file *do_last(struct nameidata *nd, struct path *path, case LAST_DOT: error = handle_dots(nd, nd->last_type); if (error) - return ERR_PTR(error); + return error; /* fallthrough */ case LAST_ROOT: error = complete_walk(nd); if (error) - return ERR_PTR(error); + return error; audit_inode(pathname, nd->path.dentry); if (open_flag & O_CREAT) { error = -EISDIR; - goto exit; + goto out; } - goto ok; + goto finish_open; case LAST_BIND: error = complete_walk(nd); if (error) - return ERR_PTR(error); + return error; audit_inode(pathname, dir); - goto ok; + goto finish_open; } if (!(open_flag & O_CREAT)) { if (nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; if (open_flag & O_PATH && !(nd->flags & LOOKUP_FOLLOW)) - symlink_ok = 1; + symlink_ok = true; /* we _can_ be in RCU mode here */ error = lookup_fast(nd, &nd->last, path, &inode); - if (unlikely(error)) { - if (error < 0) - goto exit; + if (likely(!error)) + goto finish_lookup; - error = lookup_slow(nd, &nd->last, path); - if (error < 0) - goto exit; + if (error < 0) + goto out; - inode = path->dentry->d_inode; - } - goto finish_lookup; - } - - /* create side of things */ - /* - * This will *only* deal with leaving RCU mode - LOOKUP_JUMPED has been - * cleared when we got to the last component we are about to look up - */ - error = complete_walk(nd); - if (error) - return ERR_PTR(error); + BUG_ON(nd->inode != dir->d_inode); + } else { + /* create side of things */ + /* + * This will *only* deal with leaving RCU mode - LOOKUP_JUMPED + * has been cleared when we got to the last component we are + * about to look up + */ + error = complete_walk(nd); + if (error) + return error; - audit_inode(pathname, dir); - error = -EISDIR; - /* trailing slashes? */ - if (nd->last.name[nd->last.len]) - goto exit; + audit_inode(pathname, dir); + error = -EISDIR; + /* trailing slashes? */ + if (nd->last.name[nd->last.len]) + goto out; + } retry_lookup: mutex_lock(&dir->d_inode->i_mutex); + error = lookup_open(nd, path, file, op, &want_write, opened); + mutex_unlock(&dir->d_inode->i_mutex); - dentry = lookup_hash(nd); - error = PTR_ERR(dentry); - if (IS_ERR(dentry)) { - mutex_unlock(&dir->d_inode->i_mutex); - goto exit; - } + if (error <= 0) { + if (error) + goto out; - path->dentry = dentry; - path->mnt = nd->path.mnt; + if ((*opened & FILE_CREATED) || + !S_ISREG(file->f_path.dentry->d_inode->i_mode)) + will_truncate = false; - /* Negative dentry, just create the file */ - if (!dentry->d_inode) { - umode_t mode = op->mode; - if (!IS_POSIXACL(dir->d_inode)) - mode &= ~current_umask(); - /* - * This write is needed to ensure that a - * rw->ro transition does not occur between - * the time when the file is created and when - * a permanent write count is taken through - * the 'struct file' in nameidata_to_filp(). - */ - error = mnt_want_write(nd->path.mnt); - if (error) - goto exit_mutex_unlock; - want_write = 1; + audit_inode(pathname, file->f_path.dentry); + goto opened; + } + + if (*opened & FILE_CREATED) { /* Don't check for write permission, don't truncate */ open_flag &= ~O_TRUNC; - will_truncate = 0; + will_truncate = false; acc_mode = MAY_OPEN; - error = security_path_mknod(&nd->path, dentry, mode, 0); - if (error) - goto exit_mutex_unlock; - error = vfs_create(dir->d_inode, dentry, mode, nd); - if (error) - goto exit_mutex_unlock; - mutex_unlock(&dir->d_inode->i_mutex); - dput(nd->path.dentry); - nd->path.dentry = dentry; - goto common; + path_to_nameidata(path, nd); + goto finish_open_created; } /* * It already exists. */ - mutex_unlock(&dir->d_inode->i_mutex); audit_inode(pathname, path->dentry); + /* + * If atomic_open() acquired write access it is dropped now due to + * possible mount and symlink following (this might be optimized away if + * necessary...) + */ + if (want_write) { + mnt_drop_write(nd->path.mnt); + want_write = false; + } + error = -EEXIST; if (open_flag & O_EXCL) goto exit_dput; @@ -2338,18 +2640,18 @@ finish_lookup: error = -ENOENT; if (!inode) { path_to_nameidata(path, nd); - goto exit; + goto out; } if (should_follow_link(inode, !symlink_ok)) { if (nd->flags & LOOKUP_RCU) { if (unlikely(unlazy_walk(nd, path->dentry))) { error = -ECHILD; - goto exit; + goto out; } } BUG_ON(inode != path->dentry->d_inode); - return NULL; + return 1; } if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path->mnt) { @@ -2365,119 +2667,122 @@ finish_lookup: error = complete_walk(nd); if (error) { path_put(&save_parent); - return ERR_PTR(error); + return error; } error = -EISDIR; if ((open_flag & O_CREAT) && S_ISDIR(nd->inode->i_mode)) - goto exit; + goto out; error = -ENOTDIR; if ((nd->flags & LOOKUP_DIRECTORY) && !nd->inode->i_op->lookup) - goto exit; + goto out; audit_inode(pathname, nd->path.dentry); -ok: +finish_open: if (!S_ISREG(nd->inode->i_mode)) - will_truncate = 0; + will_truncate = false; if (will_truncate) { error = mnt_want_write(nd->path.mnt); if (error) - goto exit; - want_write = 1; + goto out; + want_write = true; } -common: +finish_open_created: error = may_open(&nd->path, acc_mode, open_flag); if (error) - goto exit; - filp = nameidata_to_filp(nd); - if (filp == ERR_PTR(-EOPENSTALE) && save_parent.dentry && !retried) { - BUG_ON(save_parent.dentry != dir); - path_put(&nd->path); - nd->path = save_parent; - nd->inode = dir->d_inode; - save_parent.mnt = NULL; - save_parent.dentry = NULL; - if (want_write) { - mnt_drop_write(nd->path.mnt); - want_write = 0; - } - retried = true; - goto retry_lookup; - } - if (!IS_ERR(filp)) { - error = ima_file_check(filp, op->acc_mode); - if (error) { - fput(filp); - filp = ERR_PTR(error); - } + goto out; + file->f_path.mnt = nd->path.mnt; + error = finish_open(file, nd->path.dentry, NULL, opened); + if (error) { + if (error == -EOPENSTALE) + goto stale_open; + goto out; } - if (!IS_ERR(filp)) { - if (will_truncate) { - error = handle_truncate(filp); - if (error) { - fput(filp); - filp = ERR_PTR(error); - } - } +opened: + error = open_check_o_direct(file); + if (error) + goto exit_fput; + error = ima_file_check(file, op->acc_mode); + if (error) + goto exit_fput; + + if (will_truncate) { + error = handle_truncate(file); + if (error) + goto exit_fput; } out: if (want_write) mnt_drop_write(nd->path.mnt); path_put(&save_parent); terminate_walk(nd); - return filp; + return error; -exit_mutex_unlock: - mutex_unlock(&dir->d_inode->i_mutex); exit_dput: path_put_conditional(path, nd); -exit: - filp = ERR_PTR(error); goto out; +exit_fput: + fput(file); + goto out; + +stale_open: + /* If no saved parent or already retried then can't retry */ + if (!save_parent.dentry || retried) + goto out; + + BUG_ON(save_parent.dentry != dir); + path_put(&nd->path); + nd->path = save_parent; + nd->inode = dir->d_inode; + save_parent.mnt = NULL; + save_parent.dentry = NULL; + if (want_write) { + mnt_drop_write(nd->path.mnt); + want_write = false; + } + retried = true; + goto retry_lookup; } static struct file *path_openat(int dfd, const char *pathname, struct nameidata *nd, const struct open_flags *op, int flags) { struct file *base = NULL; - struct file *filp; + struct file *file; struct path path; + int opened = 0; int error; - filp = get_empty_filp(); - if (!filp) + file = get_empty_filp(); + if (!file) return ERR_PTR(-ENFILE); - filp->f_flags = op->open_flag; - nd->intent.open.file = filp; - nd->intent.open.flags = open_to_namei_flags(op->open_flag); - nd->intent.open.create_mode = op->mode; + file->f_flags = op->open_flag; error = path_init(dfd, pathname, flags | LOOKUP_PARENT, nd, &base); if (unlikely(error)) - goto out_filp; + goto out; current->total_link_count = 0; error = link_path_walk(pathname, nd); if (unlikely(error)) - goto out_filp; + goto out; - filp = do_last(nd, &path, op, pathname); - while (unlikely(!filp)) { /* trailing symlink */ + error = do_last(nd, &path, file, op, &opened, pathname); + while (unlikely(error > 0)) { /* trailing symlink */ struct path link = path; void *cookie; if (!(nd->flags & LOOKUP_FOLLOW)) { path_put_conditional(&path, nd); path_put(&nd->path); - filp = ERR_PTR(-ELOOP); + error = -ELOOP; break; } nd->flags |= LOOKUP_PARENT; nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL); error = follow_link(&link, nd, &cookie); if (unlikely(error)) - filp = ERR_PTR(error); - else - filp = do_last(nd, &path, op, pathname); + break; + error = do_last(nd, &path, file, op, &opened, pathname); put_link(nd, &link, cookie); } out: @@ -2485,18 +2790,20 @@ out: path_put(&nd->root); if (base) fput(base); - release_open_intent(nd); - if (filp == ERR_PTR(-EOPENSTALE)) { - if (flags & LOOKUP_RCU) - filp = ERR_PTR(-ECHILD); - else - filp = ERR_PTR(-ESTALE); + if (!(opened & FILE_OPENED)) { + BUG_ON(!error); + put_filp(file); } - return filp; - -out_filp: - filp = ERR_PTR(error); - goto out; + if (unlikely(error)) { + if (error == -EOPENSTALE) { + if (flags & LOOKUP_RCU) + error = -ECHILD; + else + error = -ESTALE; + } + file = ERR_PTR(error); + } + return file; } struct file *do_filp_open(int dfd, const char *pathname, @@ -2551,7 +2858,6 @@ struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path goto out; nd.flags &= ~LOOKUP_PARENT; nd.flags |= LOOKUP_CREATE | LOOKUP_EXCL; - nd.intent.open.flags = O_EXCL; /* * Do the final lookup. @@ -2670,7 +2976,7 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, goto out_drop_write; switch (mode & S_IFMT) { case 0: case S_IFREG: - error = vfs_create(path.dentry->d_inode,dentry,mode,NULL); + error = vfs_create(path.dentry->d_inode,dentry,mode,true); break; case S_IFCHR: case S_IFBLK: error = vfs_mknod(path.dentry->d_inode,dentry,mode, diff --git a/fs/namespace.c b/fs/namespace.c index 1e4a5fe3d7b7..c53d3381b0d0 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -515,8 +515,20 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry, } /* - * lookup_mnt increments the ref count before returning - * the vfsmount struct. + * lookup_mnt - Return the first child mount mounted at path + * + * "First" means first mounted chronologically. If you create the + * following mounts: + * + * mount /dev/sda1 /mnt + * mount /dev/sda2 /mnt + * mount /dev/sda3 /mnt + * + * Then lookup_mnt() on the base /mnt dentry in the root mount will + * return successively the root dentry and vfsmount of /dev/sda1, then + * /dev/sda2, then /dev/sda3, then NULL. + * + * lookup_mnt takes a reference to the found vfsmount. */ struct vfsmount *lookup_mnt(struct path *path) { @@ -621,21 +633,6 @@ static void attach_mnt(struct mount *mnt, struct path *path) list_add_tail(&mnt->mnt_child, &real_mount(path->mnt)->mnt_mounts); } -static inline void __mnt_make_longterm(struct mount *mnt) -{ -#ifdef CONFIG_SMP - atomic_inc(&mnt->mnt_longterm); -#endif -} - -/* needs vfsmount lock for write */ -static inline void __mnt_make_shortterm(struct mount *mnt) -{ -#ifdef CONFIG_SMP - atomic_dec(&mnt->mnt_longterm); -#endif -} - /* * vfsmount lock must be held for write */ @@ -649,10 +646,8 @@ static void commit_tree(struct mount *mnt) BUG_ON(parent == mnt); list_add_tail(&head, &mnt->mnt_list); - list_for_each_entry(m, &head, mnt_list) { + list_for_each_entry(m, &head, mnt_list) m->mnt_ns = n; - __mnt_make_longterm(m); - } list_splice(&head, n->list.prev); @@ -725,56 +720,60 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { struct super_block *sb = old->mnt.mnt_sb; - struct mount *mnt = alloc_vfsmnt(old->mnt_devname); + struct mount *mnt; + int err; - if (mnt) { - if (flag & (CL_SLAVE | CL_PRIVATE)) - mnt->mnt_group_id = 0; /* not a peer of original */ - else - mnt->mnt_group_id = old->mnt_group_id; - - if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) { - int err = mnt_alloc_group_id(mnt); - if (err) - goto out_free; - } + mnt = alloc_vfsmnt(old->mnt_devname); + if (!mnt) + return ERR_PTR(-ENOMEM); - mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD; - atomic_inc(&sb->s_active); - mnt->mnt.mnt_sb = sb; - mnt->mnt.mnt_root = dget(root); - mnt->mnt_mountpoint = mnt->mnt.mnt_root; - mnt->mnt_parent = mnt; - br_write_lock(&vfsmount_lock); - list_add_tail(&mnt->mnt_instance, &sb->s_mounts); - br_write_unlock(&vfsmount_lock); + if (flag & (CL_SLAVE | CL_PRIVATE)) + mnt->mnt_group_id = 0; /* not a peer of original */ + else + mnt->mnt_group_id = old->mnt_group_id; - if (flag & CL_SLAVE) { - list_add(&mnt->mnt_slave, &old->mnt_slave_list); - mnt->mnt_master = old; - CLEAR_MNT_SHARED(mnt); - } else if (!(flag & CL_PRIVATE)) { - if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old)) - list_add(&mnt->mnt_share, &old->mnt_share); - if (IS_MNT_SLAVE(old)) - list_add(&mnt->mnt_slave, &old->mnt_slave); - mnt->mnt_master = old->mnt_master; - } - if (flag & CL_MAKE_SHARED) - set_mnt_shared(mnt); - - /* stick the duplicate mount on the same expiry list - * as the original if that was on one */ - if (flag & CL_EXPIRE) { - if (!list_empty(&old->mnt_expire)) - list_add(&mnt->mnt_expire, &old->mnt_expire); - } + if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) { + err = mnt_alloc_group_id(mnt); + if (err) + goto out_free; } + + mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD; + atomic_inc(&sb->s_active); + mnt->mnt.mnt_sb = sb; + mnt->mnt.mnt_root = dget(root); + mnt->mnt_mountpoint = mnt->mnt.mnt_root; + mnt->mnt_parent = mnt; + br_write_lock(&vfsmount_lock); + list_add_tail(&mnt->mnt_instance, &sb->s_mounts); + br_write_unlock(&vfsmount_lock); + + if (flag & CL_SLAVE) { + list_add(&mnt->mnt_slave, &old->mnt_slave_list); + mnt->mnt_master = old; + CLEAR_MNT_SHARED(mnt); + } else if (!(flag & CL_PRIVATE)) { + if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old)) + list_add(&mnt->mnt_share, &old->mnt_share); + if (IS_MNT_SLAVE(old)) + list_add(&mnt->mnt_slave, &old->mnt_slave); + mnt->mnt_master = old->mnt_master; + } + if (flag & CL_MAKE_SHARED) + set_mnt_shared(mnt); + + /* stick the duplicate mount on the same expiry list + * as the original if that was on one */ + if (flag & CL_EXPIRE) { + if (!list_empty(&old->mnt_expire)) + list_add(&mnt->mnt_expire, &old->mnt_expire); + } + return mnt; out_free: free_vfsmnt(mnt); - return NULL; + return ERR_PTR(err); } static inline void mntfree(struct mount *mnt) @@ -804,7 +803,8 @@ static void mntput_no_expire(struct mount *mnt) put_again: #ifdef CONFIG_SMP br_read_lock(&vfsmount_lock); - if (likely(atomic_read(&mnt->mnt_longterm))) { + if (likely(mnt->mnt_ns)) { + /* shouldn't be the last one */ mnt_add_count(mnt, -1); br_read_unlock(&vfsmount_lock); return; @@ -939,7 +939,7 @@ EXPORT_SYMBOL(replace_mount_options); /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) { - struct proc_mounts *p = container_of(m, struct proc_mounts, m); + struct proc_mounts *p = proc_mounts(m); down_read(&namespace_sem); return seq_list_start(&p->ns->list, *pos); @@ -947,7 +947,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) static void *m_next(struct seq_file *m, void *v, loff_t *pos) { - struct proc_mounts *p = container_of(m, struct proc_mounts, m); + struct proc_mounts *p = proc_mounts(m); return seq_list_next(v, &p->ns->list, pos); } @@ -959,7 +959,7 @@ static void m_stop(struct seq_file *m, void *v) static int m_show(struct seq_file *m, void *v) { - struct proc_mounts *p = container_of(m, struct proc_mounts, m); + struct proc_mounts *p = proc_mounts(m); struct mount *r = list_entry(v, struct mount, mnt_list); return p->show(m, &r->mnt); } @@ -1074,8 +1074,6 @@ void umount_tree(struct mount *mnt, int propagate, struct list_head *kill) list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); __touch_mnt_namespace(p->mnt_ns); - if (p->mnt_ns) - __mnt_make_shortterm(p); p->mnt_ns = NULL; list_del_init(&p->mnt_child); if (mnt_has_parent(p)) { @@ -1260,11 +1258,12 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, struct path path; if (!(flag & CL_COPY_ALL) && IS_MNT_UNBINDABLE(mnt)) - return NULL; + return ERR_PTR(-EINVAL); res = q = clone_mnt(mnt, dentry, flag); - if (!q) - goto Enomem; + if (IS_ERR(q)) + return q; + q->mnt_mountpoint = mnt->mnt_mountpoint; p = mnt; @@ -1286,8 +1285,8 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, path.mnt = &q->mnt; path.dentry = p->mnt_mountpoint; q = clone_mnt(p, p->mnt.mnt_root, flag); - if (!q) - goto Enomem; + if (IS_ERR(q)) + goto out; br_write_lock(&vfsmount_lock); list_add_tail(&q->mnt_list, &res->mnt_list); attach_mnt(q, &path); @@ -1295,7 +1294,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, } } return res; -Enomem: +out: if (res) { LIST_HEAD(umount_list); br_write_lock(&vfsmount_lock); @@ -1303,9 +1302,11 @@ Enomem: br_write_unlock(&vfsmount_lock); release_mounts(&umount_list); } - return NULL; + return q; } +/* Caller should check returned pointer for errors */ + struct vfsmount *collect_mounts(struct path *path) { struct mount *tree; @@ -1313,7 +1314,9 @@ struct vfsmount *collect_mounts(struct path *path) tree = copy_tree(real_mount(path->mnt), path->dentry, CL_COPY_ALL | CL_PRIVATE); up_write(&namespace_sem); - return tree ? &tree->mnt : NULL; + if (IS_ERR(tree)) + return NULL; + return &tree->mnt; } void drop_collected_mounts(struct vfsmount *mnt) @@ -1608,14 +1611,15 @@ static int do_loopback(struct path *path, char *old_name, if (!check_mnt(real_mount(path->mnt)) || !check_mnt(old)) goto out2; - err = -ENOMEM; if (recurse) mnt = copy_tree(old, old_path.dentry, 0); else mnt = clone_mnt(old, old_path.dentry, 0); - if (!mnt) - goto out2; + if (IS_ERR(mnt)) { + err = PTR_ERR(mnt); + goto out; + } err = graft_tree(mnt, path); if (err) { @@ -2209,23 +2213,6 @@ static struct mnt_namespace *alloc_mnt_ns(void) return new_ns; } -void mnt_make_longterm(struct vfsmount *mnt) -{ - __mnt_make_longterm(real_mount(mnt)); -} - -void mnt_make_shortterm(struct vfsmount *m) -{ -#ifdef CONFIG_SMP - struct mount *mnt = real_mount(m); - if (atomic_add_unless(&mnt->mnt_longterm, -1, 1)) - return; - br_write_lock(&vfsmount_lock); - atomic_dec(&mnt->mnt_longterm); - br_write_unlock(&vfsmount_lock); -#endif -} - /* * Allocate a new namespace structure and populate it with contents * copied from the namespace of the passed in task structure. @@ -2246,10 +2233,10 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns, down_write(&namespace_sem); /* First pass: copy the tree topology */ new = copy_tree(old, old->mnt.mnt_root, CL_COPY_ALL | CL_EXPIRE); - if (!new) { + if (IS_ERR(new)) { up_write(&namespace_sem); kfree(new_ns); - return ERR_PTR(-ENOMEM); + return ERR_CAST(new); } new_ns->root = new; br_write_lock(&vfsmount_lock); @@ -2265,18 +2252,13 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns, q = new; while (p) { q->mnt_ns = new_ns; - __mnt_make_longterm(q); if (fs) { if (&p->mnt == fs->root.mnt) { fs->root.mnt = mntget(&q->mnt); - __mnt_make_longterm(q); - mnt_make_shortterm(&p->mnt); rootmnt = &p->mnt; } if (&p->mnt == fs->pwd.mnt) { fs->pwd.mnt = mntget(&q->mnt); - __mnt_make_longterm(q); - mnt_make_shortterm(&p->mnt); pwdmnt = &p->mnt; } } @@ -2320,7 +2302,6 @@ static struct mnt_namespace *create_mnt_ns(struct vfsmount *m) if (!IS_ERR(new_ns)) { struct mount *mnt = real_mount(m); mnt->mnt_ns = new_ns; - __mnt_make_longterm(mnt); new_ns->root = mnt; list_add(&new_ns->list, &mnt->mnt_list); } else { @@ -2615,7 +2596,7 @@ struct vfsmount *kern_mount_data(struct file_system_type *type, void *data) * it is a longterm mount, don't release mnt until * we unmount before file sys is unregistered */ - mnt_make_longterm(mnt); + real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL; } return mnt; } @@ -2625,7 +2606,9 @@ void kern_unmount(struct vfsmount *mnt) { /* release long term mount so mount point can be released */ if (!IS_ERR_OR_NULL(mnt)) { - mnt_make_shortterm(mnt); + br_write_lock(&vfsmount_lock); + real_mount(mnt)->mnt_ns = NULL; + br_write_unlock(&vfsmount_lock); mntput(mnt); } } diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index aeed93a6bde0..4117e7b377bb 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -30,8 +30,8 @@ static void ncp_do_readdir(struct file *, void *, filldir_t, static int ncp_readdir(struct file *, void *, filldir_t); -static int ncp_create(struct inode *, struct dentry *, umode_t, struct nameidata *); -static struct dentry *ncp_lookup(struct inode *, struct dentry *, struct nameidata *); +static int ncp_create(struct inode *, struct dentry *, umode_t, bool); +static struct dentry *ncp_lookup(struct inode *, struct dentry *, unsigned int); static int ncp_unlink(struct inode *, struct dentry *); static int ncp_mkdir(struct inode *, struct dentry *, umode_t); static int ncp_rmdir(struct inode *, struct dentry *); @@ -72,7 +72,7 @@ const struct inode_operations ncp_dir_inode_operations = /* * Dentry operations routines */ -static int ncp_lookup_validate(struct dentry *, struct nameidata *); +static int ncp_lookup_validate(struct dentry *, unsigned int); static int ncp_hash_dentry(const struct dentry *, const struct inode *, struct qstr *); static int ncp_compare_dentry(const struct dentry *, const struct inode *, @@ -290,7 +290,7 @@ leave_me:; static int -ncp_lookup_validate(struct dentry *dentry, struct nameidata *nd) +ncp_lookup_validate(struct dentry *dentry, unsigned int flags) { struct ncp_server *server; struct dentry *parent; @@ -302,7 +302,7 @@ ncp_lookup_validate(struct dentry *dentry, struct nameidata *nd) if (dentry == dentry->d_sb->s_root) return 1; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; parent = dget_parent(dentry); @@ -836,7 +836,7 @@ out: return result; } -static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct ncp_server *server = NCP_SERVER(dir); struct inode *inode = NULL; @@ -980,7 +980,7 @@ out: } static int ncp_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { return ncp_create_new(dir, dentry, mode, 0, 0); } diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index f430057ff3b3..a6b1c7fb8232 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -46,8 +46,8 @@ static int nfs_opendir(struct inode *, struct file *); static int nfs_closedir(struct inode *, struct file *); static int nfs_readdir(struct file *, void *, filldir_t); -static struct dentry *nfs_lookup(struct inode *, struct dentry *, struct nameidata *); -static int nfs_create(struct inode *, struct dentry *, umode_t, struct nameidata *); +static struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); +static int nfs_create(struct inode *, struct dentry *, umode_t, bool); static int nfs_mkdir(struct inode *, struct dentry *, umode_t); static int nfs_rmdir(struct inode *, struct dentry *); static int nfs_unlink(struct inode *, struct dentry *); @@ -111,11 +111,13 @@ const struct inode_operations nfs3_dir_inode_operations = { #ifdef CONFIG_NFS_V4 -static struct dentry *nfs_atomic_lookup(struct inode *, struct dentry *, struct nameidata *); -static int nfs_open_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd); +static int nfs_atomic_open(struct inode *, struct dentry *, + struct file *, unsigned, umode_t, + int *); const struct inode_operations nfs4_dir_inode_operations = { - .create = nfs_open_create, - .lookup = nfs_atomic_lookup, + .create = nfs_create, + .lookup = nfs_lookup, + .atomic_open = nfs_atomic_open, .link = nfs_link, .unlink = nfs_unlink, .symlink = nfs_symlink, @@ -1029,27 +1031,14 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry) } /* - * Return the intent data that applies to this particular path component - * - * Note that the current set of intents only apply to the very last - * component of the path and none of them is set before that last - * component. - */ -static inline unsigned int nfs_lookup_check_intent(struct nameidata *nd, - unsigned int mask) -{ - return nd->flags & mask; -} - -/* * Use intent information to check whether or not we're going to do * an O_EXCL create using this path component. */ -static int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd) +static int nfs_is_exclusive_create(struct inode *dir, unsigned int flags) { if (NFS_PROTO(dir)->version == 2) return 0; - return nd && nfs_lookup_check_intent(nd, LOOKUP_EXCL); + return flags & LOOKUP_EXCL; } /* @@ -1061,25 +1050,20 @@ static int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd) * */ static inline -int nfs_lookup_verify_inode(struct inode *inode, struct nameidata *nd) +int nfs_lookup_verify_inode(struct inode *inode, unsigned int flags) { struct nfs_server *server = NFS_SERVER(inode); if (IS_AUTOMOUNT(inode)) return 0; - if (nd != NULL) { - /* VFS wants an on-the-wire revalidation */ - if (nd->flags & LOOKUP_REVAL) - goto out_force; - /* This is an open(2) */ - if (nfs_lookup_check_intent(nd, LOOKUP_OPEN) != 0 && - !(server->flags & NFS_MOUNT_NOCTO) && - (S_ISREG(inode->i_mode) || - S_ISDIR(inode->i_mode))) - goto out_force; - return 0; - } - return nfs_revalidate_inode(server, inode); + /* VFS wants an on-the-wire revalidation */ + if (flags & LOOKUP_REVAL) + goto out_force; + /* This is an open(2) */ + if ((flags & LOOKUP_OPEN) && !(server->flags & NFS_MOUNT_NOCTO) && + (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) + goto out_force; + return 0; out_force: return __nfs_revalidate_inode(server, inode); } @@ -1093,10 +1077,10 @@ out_force: */ static inline int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { /* Don't revalidate a negative dentry if we're creating a new file */ - if (nd != NULL && nfs_lookup_check_intent(nd, LOOKUP_CREATE) != 0) + if (flags & LOOKUP_CREATE) return 0; if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) return 1; @@ -1114,7 +1098,7 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry, * If the parent directory is seen to have changed, we throw out the * cached dentry and do a new lookup. */ -static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) +static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) { struct inode *dir; struct inode *inode; @@ -1123,7 +1107,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) struct nfs_fattr *fattr = NULL; int error; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; parent = dget_parent(dentry); @@ -1132,7 +1116,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) inode = dentry->d_inode; if (!inode) { - if (nfs_neg_need_reval(dir, dentry, nd)) + if (nfs_neg_need_reval(dir, dentry, flags)) goto out_bad; goto out_valid_noent; } @@ -1148,8 +1132,8 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) goto out_set_verifier; /* Force a full look up iff the parent directory has changed */ - if (!nfs_is_exclusive_create(dir, nd) && nfs_check_verifier(dir, dentry)) { - if (nfs_lookup_verify_inode(inode, nd)) + if (!nfs_is_exclusive_create(dir, flags) && nfs_check_verifier(dir, dentry)) { + if (nfs_lookup_verify_inode(inode, flags)) goto out_zap_parent; goto out_valid; } @@ -1286,7 +1270,7 @@ const struct dentry_operations nfs_dentry_operations = { .d_release = nfs_d_release, }; -static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) +static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { struct dentry *res; struct dentry *parent; @@ -1307,7 +1291,7 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru * If we're doing an exclusive create, optimize away the lookup * but don't hash the dentry. */ - if (nfs_is_exclusive_create(dir, nd)) { + if (nfs_is_exclusive_create(dir, flags)) { d_instantiate(dentry, NULL); res = NULL; goto out; @@ -1354,7 +1338,7 @@ out: } #ifdef CONFIG_NFS_V4 -static int nfs4_lookup_revalidate(struct dentry *, struct nameidata *); +static int nfs4_lookup_revalidate(struct dentry *, unsigned int); const struct dentry_operations nfs4_dentry_operations = { .d_revalidate = nfs4_lookup_revalidate, @@ -1364,24 +1348,6 @@ const struct dentry_operations nfs4_dentry_operations = { .d_release = nfs_d_release, }; -/* - * Use intent information to determine whether we need to substitute - * the NFSv4-style stateful OPEN for the LOOKUP call - */ -static int is_atomic_open(struct nameidata *nd) -{ - if (nd == NULL || nfs_lookup_check_intent(nd, LOOKUP_OPEN) == 0) - return 0; - /* NFS does not (yet) have a stateful open for directories */ - if (nd->flags & LOOKUP_DIRECTORY) - return 0; - /* Are we trying to write to a read only partition? */ - if (__mnt_is_readonly(nd->path.mnt) && - (nd->intent.open.flags & (O_CREAT|O_TRUNC|O_ACCMODE))) - return 0; - return 1; -} - static fmode_t flags_to_mode(int flags) { fmode_t res = (__force fmode_t)flags & FMODE_EXEC; @@ -1403,136 +1369,143 @@ static int do_open(struct inode *inode, struct file *filp) return 0; } -static int nfs_intent_set_file(struct nameidata *nd, struct nfs_open_context *ctx) +static int nfs_finish_open(struct nfs_open_context *ctx, + struct dentry *dentry, + struct file *file, unsigned open_flags, + int *opened) { - struct file *filp; - int ret = 0; + int err; + + if (ctx->dentry != dentry) { + dput(ctx->dentry); + ctx->dentry = dget(dentry); + } /* If the open_intent is for execute, we have an extra check to make */ if (ctx->mode & FMODE_EXEC) { - ret = nfs_may_open(ctx->dentry->d_inode, - ctx->cred, - nd->intent.open.flags); - if (ret < 0) + err = nfs_may_open(dentry->d_inode, ctx->cred, open_flags); + if (err < 0) goto out; } - filp = lookup_instantiate_filp(nd, ctx->dentry, do_open); - if (IS_ERR(filp)) - ret = PTR_ERR(filp); - else - nfs_file_set_open_context(filp, ctx); + + err = finish_open(file, dentry, do_open, opened); + if (err) + goto out; + nfs_file_set_open_context(file, ctx); + out: put_nfs_open_context(ctx); - return ret; + return err; } -static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static int nfs_atomic_open(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned open_flags, + umode_t mode, int *opened) { struct nfs_open_context *ctx; - struct iattr attr; - struct dentry *res = NULL; + struct dentry *res; + struct iattr attr = { .ia_valid = ATTR_OPEN }; struct inode *inode; - int open_flags; int err; - dfprintk(VFS, "NFS: atomic_lookup(%s/%ld), %s\n", + /* Expect a negative dentry */ + BUG_ON(dentry->d_inode); + + dfprintk(VFS, "NFS: atomic_open(%s/%ld), %s\n", dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); - /* Check that we are indeed trying to open this file */ - if (!is_atomic_open(nd)) + /* NFS only supports OPEN on regular files */ + if ((open_flags & O_DIRECTORY)) { + if (!d_unhashed(dentry)) { + /* + * Hashed negative dentry with O_DIRECTORY: dentry was + * revalidated and is fine, no need to perform lookup + * again + */ + return -ENOENT; + } goto no_open; - - if (dentry->d_name.len > NFS_SERVER(dir)->namelen) { - res = ERR_PTR(-ENAMETOOLONG); - goto out; - } - - /* Let vfs_create() deal with O_EXCL. Instantiate, but don't hash - * the dentry. */ - if (nd->flags & LOOKUP_EXCL) { - d_instantiate(dentry, NULL); - goto out; } - open_flags = nd->intent.open.flags; - attr.ia_valid = ATTR_OPEN; - - ctx = create_nfs_open_context(dentry, open_flags); - res = ERR_CAST(ctx); - if (IS_ERR(ctx)) - goto out; + if (dentry->d_name.len > NFS_SERVER(dir)->namelen) + return -ENAMETOOLONG; - if (nd->flags & LOOKUP_CREATE) { - attr.ia_mode = nd->intent.open.create_mode; + if (open_flags & O_CREAT) { attr.ia_valid |= ATTR_MODE; - attr.ia_mode &= ~current_umask(); - } else - open_flags &= ~(O_EXCL | O_CREAT); - + attr.ia_mode = mode & ~current_umask(); + } if (open_flags & O_TRUNC) { attr.ia_valid |= ATTR_SIZE; attr.ia_size = 0; } - /* Open the file on the server */ + ctx = create_nfs_open_context(dentry, open_flags); + err = PTR_ERR(ctx); + if (IS_ERR(ctx)) + goto out; + nfs_block_sillyrename(dentry->d_parent); inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr); + d_drop(dentry); if (IS_ERR(inode)) { nfs_unblock_sillyrename(dentry->d_parent); put_nfs_open_context(ctx); - switch (PTR_ERR(inode)) { - /* Make a negative dentry */ - case -ENOENT: - d_add(dentry, NULL); - res = NULL; - goto out; - /* This turned out not to be a regular file */ - case -EISDIR: - case -ENOTDIR: + err = PTR_ERR(inode); + switch (err) { + case -ENOENT: + d_add(dentry, NULL); + break; + case -EISDIR: + case -ENOTDIR: + goto no_open; + case -ELOOP: + if (!(open_flags & O_NOFOLLOW)) goto no_open; - case -ELOOP: - if (!(nd->intent.open.flags & O_NOFOLLOW)) - goto no_open; + break; /* case -EINVAL: */ - default: - res = ERR_CAST(inode); - goto out; + default: + break; } + goto out; } res = d_add_unique(dentry, inode); - nfs_unblock_sillyrename(dentry->d_parent); - if (res != NULL) { - dput(ctx->dentry); - ctx->dentry = dget(res); + if (res != NULL) dentry = res; - } - err = nfs_intent_set_file(nd, ctx); - if (err < 0) { - if (res != NULL) - dput(res); - return ERR_PTR(err); - } -out: + + nfs_unblock_sillyrename(dentry->d_parent); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); - return res; + + err = nfs_finish_open(ctx, dentry, file, open_flags, opened); + + dput(res); +out: + return err; + no_open: - return nfs_lookup(dir, dentry, nd); + res = nfs_lookup(dir, dentry, 0); + err = PTR_ERR(res); + if (IS_ERR(res)) + goto out; + + return finish_no_open(file, res); } -static int nfs4_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) +static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) { struct dentry *parent = NULL; struct inode *inode; struct inode *dir; - int openflags, ret = 0; + int ret = 0; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; - inode = dentry->d_inode; - if (!is_atomic_open(nd) || d_mountpoint(dentry)) + if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY)) + goto no_open; + if (d_mountpoint(dentry)) goto no_open; + inode = dentry->d_inode; parent = dget_parent(dentry); dir = parent->d_inode; @@ -1540,7 +1513,7 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) * optimize away revalidation of negative dentries. */ if (inode == NULL) { - if (!nfs_neg_need_reval(dir, dentry, nd)) + if (!nfs_neg_need_reval(dir, dentry, flags)) ret = 1; goto out; } @@ -1548,9 +1521,8 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) /* NFS only supports OPEN on regular files */ if (!S_ISREG(inode->i_mode)) goto no_open_dput; - openflags = nd->intent.open.flags; /* We cannot do exclusive creation on a positive dentry */ - if ((openflags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL)) + if (flags & LOOKUP_EXCL) goto no_open_dput; /* Let f_op->open() actually open (and revalidate) the file */ @@ -1563,48 +1535,7 @@ out: no_open_dput: dput(parent); no_open: - return nfs_lookup_revalidate(dentry, nd); -} - -static int nfs_open_create(struct inode *dir, struct dentry *dentry, - umode_t mode, struct nameidata *nd) -{ - struct nfs_open_context *ctx = NULL; - struct iattr attr; - int error; - int open_flags = O_CREAT|O_EXCL; - - dfprintk(VFS, "NFS: create(%s/%ld), %s\n", - dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); - - attr.ia_mode = mode; - attr.ia_valid = ATTR_MODE; - - if (nd) - open_flags = nd->intent.open.flags; - - ctx = create_nfs_open_context(dentry, open_flags); - error = PTR_ERR(ctx); - if (IS_ERR(ctx)) - goto out_err_drop; - - error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, ctx); - if (error != 0) - goto out_put_ctx; - if (nd) { - error = nfs_intent_set_file(nd, ctx); - if (error < 0) - goto out_err; - } else { - put_nfs_open_context(ctx); - } - return 0; -out_put_ctx: - put_nfs_open_context(ctx); -out_err_drop: - d_drop(dentry); -out_err: - return error; + return nfs_lookup_revalidate(dentry, flags); } #endif /* CONFIG_NFSV4 */ @@ -1658,11 +1589,11 @@ out_error: * reply path made it appear to have failed. */ static int nfs_create(struct inode *dir, struct dentry *dentry, - umode_t mode, struct nameidata *nd) + umode_t mode, bool excl) { struct iattr attr; + int open_flags = excl ? O_CREAT | O_EXCL : O_CREAT; int error; - int open_flags = O_CREAT|O_EXCL; dfprintk(VFS, "NFS: create(%s/%ld), %s\n", dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); @@ -1670,10 +1601,7 @@ static int nfs_create(struct inode *dir, struct dentry *dentry, attr.ia_mode = mode; attr.ia_valid = ATTR_MODE; - if (nd) - open_flags = nd->intent.open.flags; - - error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, NULL); + error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags); if (error != 0) goto out_err; return 0; diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 9a4cbfc85d81..48253372ab1d 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -484,6 +484,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) list_for_each_entry_safe(req, tmp, &reqs, wb_list) { if (!nfs_pageio_add_request(&desc, req)) { + nfs_list_remove_request(req); nfs_list_add_request(req, &failed); spin_lock(cinfo.lock); dreq->flags = 0; @@ -494,8 +495,11 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) } nfs_pageio_complete(&desc); - while (!list_empty(&failed)) + while (!list_empty(&failed)) { + req = nfs_list_entry(failed.next); + nfs_list_remove_request(req); nfs_unlock_and_release_request(req); + } if (put_dreq(dreq)) nfs_direct_write_complete(dreq, dreq->inode); diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 8abfb19bd3aa..a67990f90bd7 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -62,7 +62,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i */ spin_lock(&sb->s_root->d_inode->i_lock); spin_lock(&sb->s_root->d_lock); - list_del_init(&sb->s_root->d_alias); + hlist_del_init(&sb->s_root->d_alias); spin_unlock(&sb->s_root->d_lock); spin_unlock(&sb->s_root->d_inode->i_lock); } diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 2292a0fd2bff..3187e24e8f78 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -314,7 +314,7 @@ static void nfs3_free_createdata(struct nfs3_createdata *data) */ static int nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, - int flags, struct nfs_open_context *ctx) + int flags) { struct nfs3_createdata *data; umode_t mode = sattr->ia_mode; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 15fc7e4664ed..c157b2089b47 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2806,37 +2806,22 @@ static int nfs4_proc_readlink(struct inode *inode, struct page *page, } /* - * Got race? - * We will need to arrange for the VFS layer to provide an atomic open. - * Until then, this create/open method is prone to inefficiency and race - * conditions due to the lookup, create, and open VFS calls from sys_open() - * placed on the wire. - * - * Given the above sorry state of affairs, I'm simply sending an OPEN. - * The file will be opened again in the subsequent VFS open call - * (nfs4_proc_file_open). - * - * The open for read will just hang around to be used by any process that - * opens the file O_RDONLY. This will all be resolved with the VFS changes. + * This is just for mknod. open(O_CREAT) will always do ->open_context(). */ - static int nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, - int flags, struct nfs_open_context *ctx) + int flags) { - struct dentry *de = dentry; + struct nfs_open_context *ctx; struct nfs4_state *state; - struct rpc_cred *cred = NULL; - fmode_t fmode = 0; int status = 0; - if (ctx != NULL) { - cred = ctx->cred; - de = ctx->dentry; - fmode = ctx->mode; - } + ctx = alloc_nfs_open_context(dentry, FMODE_READ); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + sattr->ia_mode &= ~current_umask(); - state = nfs4_do_open(dir, de, fmode, flags, sattr, cred, NULL); + state = nfs4_do_open(dir, dentry, ctx->mode, flags, sattr, ctx->cred, NULL); d_drop(dentry); if (IS_ERR(state)) { status = PTR_ERR(state); @@ -2844,11 +2829,9 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, } d_add(dentry, igrab(state->inode)); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); - if (ctx != NULL) - ctx->state = state; - else - nfs4_close_sync(state, fmode); + ctx->state = state; out: + put_nfs_open_context(ctx); return status; } diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index b47277baebab..f50d3e8d6f22 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -454,7 +454,10 @@ int objio_read_pagelist(struct nfs_read_data *rdata) objios->ios->done = _read_done; dprintk("%s: offset=0x%llx length=0x%x\n", __func__, rdata->args.offset, rdata->args.count); - return ore_read(objios->ios); + ret = ore_read(objios->ios); + if (unlikely(ret)) + objio_free_result(&objios->oir); + return ret; } /* @@ -486,8 +489,16 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) struct nfs_write_data *wdata = objios->oir.rpcdata; struct address_space *mapping = wdata->header->inode->i_mapping; pgoff_t index = offset / PAGE_SIZE; - struct page *page = find_get_page(mapping, index); + struct page *page; + loff_t i_size = i_size_read(wdata->header->inode); + + if (offset >= i_size) { + *uptodate = true; + dprintk("%s: g_zero_page index=0x%lx\n", __func__, index); + return ZERO_PAGE(0); + } + page = find_get_page(mapping, index); if (!page) { page = find_or_create_page(mapping, index, GFP_NOFS); if (unlikely(!page)) { @@ -507,8 +518,10 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) static void __r4w_put_page(void *priv, struct page *page) { - dprintk("%s: index=0x%lx\n", __func__, page->index); - page_cache_release(page); + dprintk("%s: index=0x%lx\n", __func__, + (page == ZERO_PAGE(0)) ? -1UL : page->index); + if (ZERO_PAGE(0) != page) + page_cache_release(page); return; } @@ -539,8 +552,10 @@ int objio_write_pagelist(struct nfs_write_data *wdata, int how) dprintk("%s: offset=0x%llx length=0x%x\n", __func__, wdata->args.offset, wdata->args.count); ret = ore_write(objios->ios); - if (unlikely(ret)) + if (unlikely(ret)) { + objio_free_result(&objios->oir); return ret; + } if (objios->sync) _write_done(objios->ios, objios); diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 617c7419a08e..4433806e116f 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -259,7 +259,7 @@ static void nfs_free_createdata(const struct nfs_createdata *data) static int nfs_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, - int flags, struct nfs_open_context *ctx) + int flags) { struct nfs_createdata *data; struct rpc_message msg = { diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 906f09c7d842..8b2a2977b720 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2419,7 +2419,7 @@ static struct dentry *nfs_fs_mount_common(struct file_system_type *fs_type, sb_mntdata.mntflags |= MS_SYNCHRONOUS; /* Get a superblock - note that we may end up sharing one that already exists */ - s = sget(fs_type, compare_super, nfs_set_super, &sb_mntdata); + s = sget(fs_type, compare_super, nfs_set_super, flags, &sb_mntdata); if (IS_ERR(s)) { mntroot = ERR_CAST(s); goto out_err_nosb; @@ -2860,6 +2860,8 @@ static struct dentry *nfs4_try_mount(int flags, const char *dev_name, dfprintk(MOUNT, "--> nfs4_try_mount()\n"); + mount_info->fill_super = nfs4_fill_super; + export_path = data->nfs_server.export_path; data->nfs_server.export_path = "/"; root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index c8bd9c3be7f7..4700a0a929d7 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -745,7 +745,7 @@ __be32 nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int may_flags, struct file **filp) { - struct dentry *dentry; + struct path path; struct inode *inode; int flags = O_RDONLY|O_LARGEFILE; __be32 err; @@ -762,8 +762,9 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, if (err) goto out; - dentry = fhp->fh_dentry; - inode = dentry->d_inode; + path.mnt = fhp->fh_export->ex_path.mnt; + path.dentry = fhp->fh_dentry; + inode = path.dentry->d_inode; /* Disallow write access to files with the append-only bit set * or any access when mandatory locking enabled @@ -792,8 +793,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, else flags = O_WRONLY|O_LARGEFILE; } - *filp = dentry_open(dget(dentry), mntget(fhp->fh_export->ex_path.mnt), - flags, current_cred()); + *filp = dentry_open(&path, flags, current_cred()); if (IS_ERR(*filp)) host_err = PTR_ERR(*filp); else { @@ -1329,7 +1329,7 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, err = 0; switch (type) { case S_IFREG: - host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL); + host_err = vfs_create(dirp, dchild, iap->ia_mode, true); if (!host_err) nfsd_check_ignore_resizing(iap); break; @@ -1492,7 +1492,7 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out; } - host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL); + host_err = vfs_create(dirp, dchild, iap->ia_mode, true); if (host_err < 0) { fh_drop_write(fhp); goto out_nfserr; diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index b72847988b78..1d0c0b84c5a3 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -63,7 +63,7 @@ static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode) */ static struct dentry * -nilfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode; ino_t ino; @@ -85,7 +85,7 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) * with d_instantiate(). */ static int nilfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct inode *inode; struct nilfs_transaction_info ti; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 1099a76cee59..d57c42f974ea 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1288,7 +1288,8 @@ nilfs_mount(struct file_system_type *fs_type, int flags, err = -EBUSY; goto failed; } - s = sget(fs_type, nilfs_test_bdev_super, nilfs_set_bdev_super, sd.bdev); + s = sget(fs_type, nilfs_test_bdev_super, nilfs_set_bdev_super, flags, + sd.bdev); mutex_unlock(&sd.bdev->bd_fsfreeze_mutex); if (IS_ERR(s)) { err = PTR_ERR(s); @@ -1301,7 +1302,6 @@ nilfs_mount(struct file_system_type *fs_type, int flags, s_new = true; /* New superblock instance created */ - s->s_flags = flags; s->s_mode = mode; strlcpy(s->s_id, bdevname(sd.bdev, b), sizeof(s->s_id)); sb_set_blocksize(s, block_size(sd.bdev)); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 3568c8a8b138..d43803669739 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -61,8 +61,6 @@ static struct fsnotify_event *get_one_event(struct fsnotify_group *group, static int create_fd(struct fsnotify_group *group, struct fsnotify_event *event) { int client_fd; - struct dentry *dentry; - struct vfsmount *mnt; struct file *new_file; pr_debug("%s: group=%p event=%p\n", __func__, group, event); @@ -81,12 +79,10 @@ static int create_fd(struct fsnotify_group *group, struct fsnotify_event *event) * we need a new file handle for the userspace program so it can read even if it was * originally opened O_WRONLY. */ - dentry = dget(event->path.dentry); - mnt = mntget(event->path.mnt); /* it's possible this event was an overflow event. in that case dentry and mnt * are NULL; That's fine, just don't call dentry open */ - if (dentry && mnt) - new_file = dentry_open(dentry, mnt, + if (event->path.dentry && event->path.mnt) + new_file = dentry_open(&event->path, group->fanotify_data.f_flags | FMODE_NONOTIFY, current_cred()); else diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index b39c5c161adb..6baadb5a8430 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -52,6 +52,7 @@ void __fsnotify_vfsmount_delete(struct vfsmount *mnt) void __fsnotify_update_child_dentry_flags(struct inode *inode) { struct dentry *alias; + struct hlist_node *p; int watched; if (!S_ISDIR(inode->i_mode)) @@ -63,7 +64,7 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode) spin_lock(&inode->i_lock); /* run all of the dentries associated with this inode. Since this is a * directory, there damn well better only be one item on this list */ - list_for_each_entry(alias, &inode->i_dentry, d_alias) { + hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) { struct dentry *child; /* run all of the children of the original inode and fix their diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c index 358273e59ade..436f36037e09 100644 --- a/fs/ntfs/namei.c +++ b/fs/ntfs/namei.c @@ -101,7 +101,7 @@ * Locking: Caller must hold i_mutex on the directory. */ static struct dentry *ntfs_lookup(struct inode *dir_ino, struct dentry *dent, - struct nameidata *nd) + unsigned int flags) { ntfs_volume *vol = NTFS_SB(dir_ino->i_sb); struct inode *dent_inode; diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index e5ba34818332..8db4b58b2e4b 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -49,14 +49,13 @@ void ocfs2_dentry_attach_gen(struct dentry *dentry) } -static int ocfs2_dentry_revalidate(struct dentry *dentry, - struct nameidata *nd) +static int ocfs2_dentry_revalidate(struct dentry *dentry, unsigned int flags) { struct inode *inode; int ret = 0; /* if all else fails, just return false */ struct ocfs2_super *osb; - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; inode = dentry->d_inode; @@ -170,13 +169,11 @@ struct dentry *ocfs2_find_local_alias(struct inode *inode, u64 parent_blkno, int skip_unhashed) { - struct list_head *p; - struct dentry *dentry = NULL; + struct hlist_node *p; + struct dentry *dentry; spin_lock(&inode->i_lock); - list_for_each(p, &inode->i_dentry) { - dentry = list_entry(p, struct dentry, d_alias); - + hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) { spin_lock(&dentry->d_lock); if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) { trace_ocfs2_find_local_alias(dentry->d_name.len, @@ -184,16 +181,13 @@ struct dentry *ocfs2_find_local_alias(struct inode *inode, dget_dlock(dentry); spin_unlock(&dentry->d_lock); - break; + spin_unlock(&inode->i_lock); + return dentry; } spin_unlock(&dentry->d_lock); - - dentry = NULL; } - spin_unlock(&inode->i_lock); - - return dentry; + return NULL; } DEFINE_SPINLOCK(dentry_attach_lock); diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index e31d6ae013ab..83b6f98e0665 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -526,7 +526,7 @@ bail: static int dlmfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { int status = 0; struct inode *inode; diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 81a4cd22f80b..4f7795fb5fc0 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -456,7 +456,7 @@ static void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, int level, stats->ls_gets++; stats->ls_total += ktime_to_ns(kt); /* overflow */ - if (unlikely(stats->ls_gets) == 0) { + if (unlikely(stats->ls_gets == 0)) { stats->ls_gets++; stats->ls_total = ktime_to_ns(kt); } @@ -3932,6 +3932,8 @@ unqueue: static void ocfs2_schedule_blocked_lock(struct ocfs2_super *osb, struct ocfs2_lock_res *lockres) { + unsigned long flags; + assert_spin_locked(&lockres->l_lock); if (lockres->l_flags & OCFS2_LOCK_FREEING) { @@ -3945,21 +3947,22 @@ static void ocfs2_schedule_blocked_lock(struct ocfs2_super *osb, lockres_or_flags(lockres, OCFS2_LOCK_QUEUED); - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); if (list_empty(&lockres->l_blocked_list)) { list_add_tail(&lockres->l_blocked_list, &osb->blocked_lock_list); osb->blocked_lock_count++; } - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); } static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb) { unsigned long processed; + unsigned long flags; struct ocfs2_lock_res *lockres; - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); /* grab this early so we know to try again if a state change and * wake happens part-way through our work */ osb->dc_work_sequence = osb->dc_wake_sequence; @@ -3972,38 +3975,40 @@ static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb) struct ocfs2_lock_res, l_blocked_list); list_del_init(&lockres->l_blocked_list); osb->blocked_lock_count--; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); BUG_ON(!processed); processed--; ocfs2_process_blocked_lock(osb, lockres); - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); } - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); } static int ocfs2_downconvert_thread_lists_empty(struct ocfs2_super *osb) { int empty = 0; + unsigned long flags; - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); if (list_empty(&osb->blocked_lock_list)) empty = 1; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); return empty; } static int ocfs2_downconvert_thread_should_wake(struct ocfs2_super *osb) { int should_wake = 0; + unsigned long flags; - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); if (osb->dc_work_sequence != osb->dc_wake_sequence) should_wake = 1; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); return should_wake; } @@ -4033,10 +4038,12 @@ static int ocfs2_downconvert_thread(void *arg) void ocfs2_wake_downconvert_thread(struct ocfs2_super *osb) { - spin_lock(&osb->dc_task_lock); + unsigned long flags; + + spin_lock_irqsave(&osb->dc_task_lock, flags); /* make sure the voting thread gets a swipe at whatever changes * the caller may have made to the voting state */ osb->dc_wake_sequence++; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); wake_up(&osb->dc_event); } diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index 2f5b92ef0e53..70b5863a2d64 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -923,8 +923,6 @@ out_unlock: ocfs2_inode_unlock(inode, 0); out: - if (ret && ret != -ENXIO) - ret = -ENXIO; return ret; } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 061591a3ab08..7602783d7f41 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1950,7 +1950,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, if (ret < 0) mlog_errno(ret); - if (file->f_flags & O_SYNC) + if (file && (file->f_flags & O_SYNC)) handle->h_sync = 1; ocfs2_commit_trans(osb, handle); @@ -2422,8 +2422,10 @@ out_dio: unaligned_dio = 0; } - if (unaligned_dio) + if (unaligned_dio) { + ocfs2_iocb_clear_unaligned_aio(iocb); atomic_dec(&OCFS2_I(inode)->ip_unaligned_aio); + } out: if (rw_level != -1) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 9f39c640cddf..f1fd0741162b 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -98,7 +98,7 @@ static int ocfs2_create_symlink_data(struct ocfs2_super *osb, #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64))) static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { int status; u64 blkno; @@ -618,7 +618,7 @@ static int ocfs2_mkdir(struct inode *dir, static int ocfs2_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { int ret; diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 92fcd575775a..0a86e302655f 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -399,8 +399,6 @@ int ocfs2_global_read_info(struct super_block *sb, int type) msecs_to_jiffies(oinfo->dqi_syncms)); out_err: - if (status) - mlog_errno(status); return status; out_unlock: ocfs2_unlock_global_qf(oinfo, 0); diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c index f00576ec320f..fb5b3ff79dc6 100644 --- a/fs/omfs/dir.c +++ b/fs/omfs/dir.c @@ -285,13 +285,13 @@ static int omfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) } static int omfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { return omfs_add_node(dir, dentry, mode | S_IFREG); } static struct dentry *omfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct buffer_head *bh; struct inode *inode = NULL; diff --git a/fs/open.c b/fs/open.c index d6c79a0dffc7..1e914b397e12 100644 --- a/fs/open.c +++ b/fs/open.c @@ -397,10 +397,10 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd) { struct file *file; struct inode *inode; - int error; + int error, fput_needed; error = -EBADF; - file = fget(fd); + file = fget_raw_light(fd, &fput_needed); if (!file) goto out; @@ -414,7 +414,7 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd) if (!error) set_fs_pwd(current->fs, &file->f_path); out_putf: - fput(file); + fput_light(file, fput_needed); out: return error; } @@ -537,25 +537,6 @@ static int chown_common(struct path *path, uid_t user, gid_t group) return error; } -SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group) -{ - struct path path; - int error; - - error = user_path(filename, &path); - if (error) - goto out; - error = mnt_want_write(path.mnt); - if (error) - goto out_release; - error = chown_common(&path, user, group); - mnt_drop_write(path.mnt); -out_release: - path_put(&path); -out: - return error; -} - SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, gid_t, group, int, flag) { @@ -583,23 +564,15 @@ out: return error; } -SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group) +SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group) { - struct path path; - int error; + return sys_fchownat(AT_FDCWD, filename, user, group, 0); +} - error = user_lpath(filename, &path); - if (error) - goto out; - error = mnt_want_write(path.mnt); - if (error) - goto out_release; - error = chown_common(&path, user, group); - mnt_drop_write(path.mnt); -out_release: - path_put(&path); -out: - return error; +SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group) +{ + return sys_fchownat(AT_FDCWD, filename, user, group, + AT_SYMLINK_NOFOLLOW); } SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) @@ -667,10 +640,9 @@ int open_check_o_direct(struct file *f) return 0; } -static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt, - struct file *f, - int (*open)(struct inode *, struct file *), - const struct cred *cred) +static int do_dentry_open(struct file *f, + int (*open)(struct inode *, struct file *), + const struct cred *cred) { static const struct file_operations empty_fops = {}; struct inode *inode; @@ -682,9 +654,9 @@ static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt, if (unlikely(f->f_flags & O_PATH)) f->f_mode = FMODE_PATH; - inode = dentry->d_inode; + inode = f->f_path.dentry->d_inode; if (f->f_mode & FMODE_WRITE) { - error = __get_file_write_access(inode, mnt); + error = __get_file_write_access(inode, f->f_path.mnt); if (error) goto cleanup_file; if (!special_file(inode->i_mode)) @@ -692,14 +664,12 @@ static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt, } f->f_mapping = inode->i_mapping; - f->f_path.dentry = dentry; - f->f_path.mnt = mnt; f->f_pos = 0; file_sb_list_add(f, inode->i_sb); if (unlikely(f->f_mode & FMODE_PATH)) { f->f_op = &empty_fops; - return f; + return 0; } f->f_op = fops_get(inode->i_fop); @@ -726,10 +696,11 @@ static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt, file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping); - return f; + return 0; cleanup_all: fops_put(f->f_op); + file_sb_list_del(f); if (f->f_mode & FMODE_WRITE) { put_write_access(inode); if (!special_file(inode->i_mode)) { @@ -740,124 +711,62 @@ cleanup_all: * here, so just reset the state. */ file_reset_write(f); - mnt_drop_write(mnt); + mnt_drop_write(f->f_path.mnt); } } - file_sb_list_del(f); - f->f_path.dentry = NULL; - f->f_path.mnt = NULL; cleanup_file: - dput(dentry); - mntput(mnt); - return ERR_PTR(error); -} - -static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, - struct file *f, - int (*open)(struct inode *, struct file *), - const struct cred *cred) -{ - struct file *res = do_dentry_open(dentry, mnt, f, open, cred); - if (!IS_ERR(res)) { - int error = open_check_o_direct(f); - if (error) { - fput(res); - res = ERR_PTR(error); - } - } else { - put_filp(f); - } - return res; + path_put(&f->f_path); + f->f_path.mnt = NULL; + f->f_path.dentry = NULL; + return error; } /** - * lookup_instantiate_filp - instantiates the open intent filp - * @nd: pointer to nameidata + * finish_open - finish opening a file + * @od: opaque open data * @dentry: pointer to dentry * @open: open callback * - * Helper for filesystems that want to use lookup open intents and pass back - * a fully instantiated struct file to the caller. - * This function is meant to be called from within a filesystem's - * lookup method. - * Beware of calling it for non-regular files! Those ->open methods might block - * (e.g. in fifo_open), leaving you with parent locked (and in case of fifo, - * leading to a deadlock, as nobody can open that fifo anymore, because - * another process to open fifo will block on locked parent when doing lookup). - * Note that in case of error, nd->intent.open.file is destroyed, but the - * path information remains valid. + * This can be used to finish opening a file passed to i_op->atomic_open(). + * * If the open callback is set to NULL, then the standard f_op->open() * filesystem callback is substituted. */ -struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry, - int (*open)(struct inode *, struct file *)) +int finish_open(struct file *file, struct dentry *dentry, + int (*open)(struct inode *, struct file *), + int *opened) { - const struct cred *cred = current_cred(); + int error; + BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */ - if (IS_ERR(nd->intent.open.file)) - goto out; - if (IS_ERR(dentry)) - goto out_err; - nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->path.mnt), - nd->intent.open.file, - open, cred); -out: - return nd->intent.open.file; -out_err: - release_open_intent(nd); - nd->intent.open.file = ERR_CAST(dentry); - goto out; + mntget(file->f_path.mnt); + file->f_path.dentry = dget(dentry); + + error = do_dentry_open(file, open, current_cred()); + if (!error) + *opened |= FILE_OPENED; + + return error; } -EXPORT_SYMBOL_GPL(lookup_instantiate_filp); +EXPORT_SYMBOL(finish_open); /** - * nameidata_to_filp - convert a nameidata to an open filp. - * @nd: pointer to nameidata - * @flags: open flags + * finish_no_open - finish ->atomic_open() without opening the file + * + * @od: opaque open data + * @dentry: dentry or NULL (as returned from ->lookup()) * - * Note that this function destroys the original nameidata + * This can be used to set the result of a successful lookup in ->atomic_open(). + * The filesystem's atomic_open() method shall return NULL after calling this. */ -struct file *nameidata_to_filp(struct nameidata *nd) +int finish_no_open(struct file *file, struct dentry *dentry) { - const struct cred *cred = current_cred(); - struct file *filp; - - /* Pick up the filp from the open intent */ - filp = nd->intent.open.file; - - /* Has the filesystem initialised the file for us? */ - if (filp->f_path.dentry != NULL) { - nd->intent.open.file = NULL; - } else { - struct file *res; - - path_get(&nd->path); - res = do_dentry_open(nd->path.dentry, nd->path.mnt, - filp, NULL, cred); - if (!IS_ERR(res)) { - int error; - - nd->intent.open.file = NULL; - BUG_ON(res != filp); - - error = open_check_o_direct(filp); - if (error) { - fput(filp); - filp = ERR_PTR(error); - } - } else { - /* Allow nd->intent.open.file to be recycled */ - filp = res; - } - } - return filp; + file->f_path.dentry = dentry; + return 1; } +EXPORT_SYMBOL(finish_no_open); -/* - * dentry_open() will have done dput(dentry) and mntput(mnt) if it returns an - * error. - */ -struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags, +struct file *dentry_open(const struct path *path, int flags, const struct cred *cred) { int error; @@ -866,18 +775,28 @@ struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags, validate_creds(cred); /* We must always pass in a valid mount pointer. */ - BUG_ON(!mnt); + BUG_ON(!path->mnt); error = -ENFILE; f = get_empty_filp(); - if (f == NULL) { - dput(dentry); - mntput(mnt); + if (f == NULL) return ERR_PTR(error); - } f->f_flags = flags; - return __dentry_open(dentry, mnt, f, NULL, cred); + f->f_path = *path; + path_get(&f->f_path); + error = do_dentry_open(f, NULL, cred); + if (!error) { + error = open_check_o_direct(f); + if (error) { + fput(f); + f = ERR_PTR(error); + } + } else { + put_filp(f); + f = ERR_PTR(error); + } + return f; } EXPORT_SYMBOL(dentry_open); diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index bc49c975d501..4a3477949bca 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -170,13 +170,13 @@ static const struct file_operations openprom_operations = { .llseek = generic_file_llseek, }; -static struct dentry *openpromfs_lookup(struct inode *, struct dentry *, struct nameidata *); +static struct dentry *openpromfs_lookup(struct inode *, struct dentry *, unsigned int); static const struct inode_operations openprom_inode_operations = { .lookup = openpromfs_lookup, }; -static struct dentry *openpromfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *openpromfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct op_inode_info *ent_oi, *oi = OP_I(dir); struct device_node *dp, *child; diff --git a/fs/pnode.c b/fs/pnode.c index bed378db0758..3e000a51ac0d 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -237,8 +237,9 @@ int propagate_mnt(struct mount *dest_mnt, struct dentry *dest_dentry, source = get_source(m, prev_dest_mnt, prev_src_mnt, &type); - if (!(child = copy_tree(source, source->mnt.mnt_root, type))) { - ret = -ENOMEM; + child = copy_tree(source, source->mnt.mnt_root, type); + if (IS_ERR(child)) { + ret = PTR_ERR(child); list_splice(tree_list, tmp_list.prev); goto out; } diff --git a/fs/proc/base.c b/fs/proc/base.c index 437195f204e1..2772208338f8 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1427,16 +1427,19 @@ static int proc_exe_link(struct dentry *dentry, struct path *exe_path) static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd) { struct inode *inode = dentry->d_inode; + struct path path; int error = -EACCES; - /* We don't need a base pointer in the /proc filesystem */ - path_put(&nd->path); - /* Are we allowed to snoop on the tasks file descriptors? */ if (!proc_fd_access_allowed(inode)) goto out; - error = PROC_I(inode)->op.proc_get_link(dentry, &nd->path); + error = PROC_I(inode)->op.proc_get_link(dentry, &path); + if (error) + goto out; + + nd_jump_link(nd, &path); + return NULL; out: return ERR_PTR(error); } @@ -1601,13 +1604,13 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) * made this apply to all per process world readable and executable * directories. */ -int pid_revalidate(struct dentry *dentry, struct nameidata *nd) +int pid_revalidate(struct dentry *dentry, unsigned int flags) { struct inode *inode; struct task_struct *task; const struct cred *cred; - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; inode = dentry->d_inode; @@ -1781,7 +1784,7 @@ static int proc_fd_link(struct dentry *dentry, struct path *path) return proc_fd_info(dentry->d_inode, path, NULL); } -static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) +static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags) { struct inode *inode; struct task_struct *task; @@ -1789,7 +1792,7 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) struct files_struct *files; const struct cred *cred; - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; inode = dentry->d_inode; @@ -1868,7 +1871,7 @@ static struct dentry *proc_fd_instantiate(struct inode *dir, d_set_d_op(dentry, &tid_fd_dentry_operations); d_add(dentry, inode); /* Close the race of the process dying before we return the dentry */ - if (tid_fd_revalidate(dentry, NULL)) + if (tid_fd_revalidate(dentry, 0)) error = NULL; out: @@ -1956,7 +1959,7 @@ out_no_task: } static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { return proc_lookupfd_common(dir, dentry, proc_fd_instantiate); } @@ -2003,7 +2006,7 @@ static int dname_to_vma_addr(struct dentry *dentry, return 0; } -static int map_files_d_revalidate(struct dentry *dentry, struct nameidata *nd) +static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) { unsigned long vm_start, vm_end; bool exact_vma_exists = false; @@ -2013,7 +2016,7 @@ static int map_files_d_revalidate(struct dentry *dentry, struct nameidata *nd) struct inode *inode; int status = 0; - if (nd && nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; if (!capable(CAP_SYS_ADMIN)) { @@ -2145,7 +2148,7 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry, } static struct dentry *proc_map_files_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) + struct dentry *dentry, unsigned int flags) { unsigned long vm_start, vm_end; struct vm_area_struct *vma; @@ -2371,7 +2374,7 @@ static struct dentry *proc_fdinfo_instantiate(struct inode *dir, d_set_d_op(dentry, &tid_fd_dentry_operations); d_add(dentry, inode); /* Close the race of the process dying before we return the dentry */ - if (tid_fd_revalidate(dentry, NULL)) + if (tid_fd_revalidate(dentry, 0)) error = NULL; out: @@ -2380,7 +2383,7 @@ static struct dentry *proc_fdinfo_instantiate(struct inode *dir, static struct dentry *proc_lookupfdinfo(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate); } @@ -2430,7 +2433,7 @@ static struct dentry *proc_pident_instantiate(struct inode *dir, d_set_d_op(dentry, &pid_dentry_operations); d_add(dentry, inode); /* Close the race of the process dying before we return the dentry */ - if (pid_revalidate(dentry, NULL)) + if (pid_revalidate(dentry, 0)) error = NULL; out: return error; @@ -2630,7 +2633,7 @@ static const struct file_operations proc_attr_dir_operations = { }; static struct dentry *proc_attr_dir_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) + struct dentry *dentry, unsigned int flags) { return proc_pident_lookup(dir, dentry, attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff)); @@ -3114,7 +3117,8 @@ static const struct file_operations proc_tgid_base_operations = { .llseek = default_llseek, }; -static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ +static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) +{ return proc_pident_lookup(dir, dentry, tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); } @@ -3237,13 +3241,13 @@ static struct dentry *proc_pid_instantiate(struct inode *dir, d_add(dentry, inode); /* Close the race of the process dying before we return the dentry */ - if (pid_revalidate(dentry, NULL)) + if (pid_revalidate(dentry, 0)) error = NULL; out: return error; } -struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) +struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { struct dentry *result; struct task_struct *task; @@ -3470,7 +3474,8 @@ static int proc_tid_base_readdir(struct file * filp, tid_base_stuff,ARRAY_SIZE(tid_base_stuff)); } -static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ +static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) +{ return proc_pident_lookup(dir, dentry, tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); } @@ -3508,13 +3513,13 @@ static struct dentry *proc_task_instantiate(struct inode *dir, d_add(dentry, inode); /* Close the race of the process dying before we return the dentry */ - if (pid_revalidate(dentry, NULL)) + if (pid_revalidate(dentry, 0)) error = NULL; out: return error; } -static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) +static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { struct dentry *result = ERR_PTR(-ENOENT); struct task_struct *task; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 2edf34f2eb61..b3647fe6a608 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -446,7 +446,7 @@ out_unlock: } struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { return proc_lookup_de(PDE(dir), dir, dentry); } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index eca4aca5b6e2..e1167a1c9126 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -106,7 +106,7 @@ void pde_users_dec(struct proc_dir_entry *pde); extern spinlock_t proc_subdir_lock; -struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *); +struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int); int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir); unsigned long task_vsize(struct mm_struct *); unsigned long task_statm(struct mm_struct *, @@ -132,7 +132,7 @@ int proc_remount(struct super_block *sb, int *flags, char *data); * of the /proc/<pid> subdirectories. */ int proc_readdir(struct file *, void *, filldir_t); -struct dentry *proc_lookup(struct inode *, struct dentry *, struct nameidata *); +struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int); @@ -142,7 +142,7 @@ typedef struct dentry *instantiate_t(struct inode *, struct dentry *, int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir, const char *name, int len, instantiate_t instantiate, struct task_struct *task, const void *ptr); -int pid_revalidate(struct dentry *dentry, struct nameidata *nd); +int pid_revalidate(struct dentry *dentry, unsigned int flags); struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task); extern const struct dentry_operations pid_dentry_operations; int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index 0d9e23a39e49..b178ed733c36 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -56,7 +56,7 @@ static struct dentry *proc_ns_instantiate(struct inode *dir, d_set_d_op(dentry, &pid_dentry_operations); d_add(dentry, inode); /* Close the race of the process dying before we return the dentry */ - if (pid_revalidate(dentry, NULL)) + if (pid_revalidate(dentry, 0)) error = NULL; out: return error; @@ -140,7 +140,7 @@ const struct file_operations proc_ns_dir_operations = { }; static struct dentry *proc_ns_dir_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) + struct dentry *dentry, unsigned int flags) { struct dentry *error; struct task_struct *task = get_proc_task(dir); diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 06e1cc17caf6..fe72cd073dea 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -119,7 +119,7 @@ static struct net *get_proc_task_net(struct inode *dir) } static struct dentry *proc_tgid_net_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) + struct dentry *dentry, unsigned int flags) { struct dentry *de; struct net *net; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 3476bca8f7af..dfafeb2b05a0 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -433,7 +433,7 @@ static struct ctl_table_header *grab_header(struct inode *inode) } static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct ctl_table_header *head = grab_header(dir); struct ctl_table_header *h = NULL; @@ -794,9 +794,9 @@ static const struct inode_operations proc_sys_dir_operations = { .getattr = proc_sys_getattr, }; -static int proc_sys_revalidate(struct dentry *dentry, struct nameidata *nd) +static int proc_sys_revalidate(struct dentry *dentry, unsigned int flags) { - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; return !PROC_I(dentry->d_inode)->sysctl->unregistering; } diff --git a/fs/proc/root.c b/fs/proc/root.c index 7c30fce037c0..9a2d9fd7cadd 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -111,7 +111,7 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, options = data; } - sb = sget(fs_type, proc_test_super, proc_set_super, ns); + sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns); if (IS_ERR(sb)) return ERR_CAST(sb); @@ -121,7 +121,6 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, } if (!sb->s_root) { - sb->s_flags = flags; err = proc_fill_super(sb); if (err) { deactivate_locked_super(sb); @@ -200,13 +199,12 @@ static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct return 0; } -static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd) +static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags) { - if (!proc_lookup(dir, dentry, nd)) { + if (!proc_lookup(dir, dentry, flags)) return NULL; - } - return proc_pid_lookup(dir, dentry, nd); + return proc_pid_lookup(dir, dentry, flags); } static int proc_root_readdir(struct file * filp, diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 5e289a7cbad1..5fe34c355e85 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -17,7 +17,7 @@ static unsigned mounts_poll(struct file *file, poll_table *wait) { - struct proc_mounts *p = file->private_data; + struct proc_mounts *p = proc_mounts(file->private_data); struct mnt_namespace *ns = p->ns; unsigned res = POLLIN | POLLRDNORM; @@ -121,7 +121,7 @@ out: static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt) { - struct proc_mounts *p = m->private; + struct proc_mounts *p = proc_mounts(m); struct mount *r = real_mount(mnt); struct super_block *sb = mnt->mnt_sb; struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; @@ -268,7 +268,6 @@ static int mounts_open_common(struct inode *inode, struct file *file, if (ret) goto err_free; - p->m.private = p; p->ns = ns; p->root = root; p->m.poll_event = ns->event; @@ -288,7 +287,7 @@ static int mounts_open_common(struct inode *inode, struct file *file, static int mounts_release(struct inode *inode, struct file *file) { - struct proc_mounts *p = file->private_data; + struct proc_mounts *p = proc_mounts(file->private_data); path_put(&p->root); put_mnt_ns(p->ns); return seq_release(inode, file); diff --git a/fs/qnx4/namei.c b/fs/qnx4/namei.c index a512c0b30e8e..d024505ba007 100644 --- a/fs/qnx4/namei.c +++ b/fs/qnx4/namei.c @@ -95,7 +95,7 @@ static struct buffer_head *qnx4_find_entry(int len, struct inode *dir, return NULL; } -struct dentry * qnx4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +struct dentry * qnx4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { int ino; struct qnx4_inode_entry *de; diff --git a/fs/qnx4/qnx4.h b/fs/qnx4/qnx4.h index 244d4620189b..34e2d329c97e 100644 --- a/fs/qnx4/qnx4.h +++ b/fs/qnx4/qnx4.h @@ -23,7 +23,7 @@ struct qnx4_inode_info { }; extern struct inode *qnx4_iget(struct super_block *, unsigned long); -extern struct dentry *qnx4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd); +extern struct dentry *qnx4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); extern unsigned long qnx4_count_free_blocks(struct super_block *sb); extern unsigned long qnx4_block_map(struct inode *inode, long iblock); diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index e44012dc5645..2049c814bda4 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -622,7 +622,6 @@ static struct inode *qnx6_alloc_inode(struct super_block *sb) static void qnx6_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); - INIT_LIST_HEAD(&inode->i_dentry); kmem_cache_free(qnx6_inode_cachep, QNX6_I(inode)); } diff --git a/fs/qnx6/namei.c b/fs/qnx6/namei.c index 8a97289e04ad..0561326a94f5 100644 --- a/fs/qnx6/namei.c +++ b/fs/qnx6/namei.c @@ -13,7 +13,7 @@ #include "qnx6.h" struct dentry *qnx6_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { unsigned ino; struct page *page; diff --git a/fs/qnx6/qnx6.h b/fs/qnx6/qnx6.h index 6c5e02a0b6a8..b00fcc960d37 100644 --- a/fs/qnx6/qnx6.h +++ b/fs/qnx6/qnx6.h @@ -45,7 +45,7 @@ struct qnx6_inode_info { extern struct inode *qnx6_iget(struct super_block *sb, unsigned ino); extern struct dentry *qnx6_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd); + unsigned int flags); #ifdef CONFIG_QNX6FS_DEBUG extern void qnx6_superblock_debug(struct qnx6_super_block *, diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 10cbe841cb7e..d679fc48ef27 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -595,12 +595,14 @@ out: } EXPORT_SYMBOL(dquot_scan_active); -int dquot_quota_sync(struct super_block *sb, int type, int wait) +/* Write all dquot structures to quota files */ +int dquot_writeback_dquots(struct super_block *sb, int type) { struct list_head *dirty; struct dquot *dquot; struct quota_info *dqopt = sb_dqopt(sb); int cnt; + int err, ret = 0; mutex_lock(&dqopt->dqonoff_mutex); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { @@ -624,7 +626,9 @@ int dquot_quota_sync(struct super_block *sb, int type, int wait) atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); dqstats_inc(DQST_LOOKUPS); - sb->dq_op->write_dquot(dquot); + err = sb->dq_op->write_dquot(dquot); + if (!ret && err) + err = ret; dqput(dquot); spin_lock(&dq_list_lock); } @@ -638,7 +642,21 @@ int dquot_quota_sync(struct super_block *sb, int type, int wait) dqstats_inc(DQST_SYNCS); mutex_unlock(&dqopt->dqonoff_mutex); - if (!wait || (dqopt->flags & DQUOT_QUOTA_SYS_FILE)) + return ret; +} +EXPORT_SYMBOL(dquot_writeback_dquots); + +/* Write all dquot structures to disk and make them visible from userspace */ +int dquot_quota_sync(struct super_block *sb, int type) +{ + struct quota_info *dqopt = sb_dqopt(sb); + int cnt; + int ret; + + ret = dquot_writeback_dquots(sb, type); + if (ret) + return ret; + if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) return 0; /* This is not very clever (and fast) but currently I don't know about diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 9a391204ca27..c659f92298d3 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -47,7 +47,7 @@ static int check_quotactl_permission(struct super_block *sb, int type, int cmd, static void quota_sync_one(struct super_block *sb, void *arg) { if (sb->s_qcop && sb->s_qcop->quota_sync) - sb->s_qcop->quota_sync(sb, *(int *)arg, 1); + sb->s_qcop->quota_sync(sb, *(int *)arg); } static int quota_sync_all(int type) @@ -270,7 +270,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, case Q_SYNC: if (!sb->s_qcop->quota_sync) return -ENOSYS; - return sb->s_qcop->quota_sync(sb, type, 1); + return sb->s_qcop->quota_sync(sb, type); case Q_XQUOTAON: case Q_XQUOTAOFF: case Q_XQUOTARM: diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index fbb0b478a346..d5378d028589 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -110,6 +110,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) /* prevent the page from being discarded on memory pressure */ SetPageDirty(page); + SetPageUptodate(page); unlock_page(page); put_page(page); diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index a1fdabe21dec..eab8c09d3801 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -114,7 +114,7 @@ static int ramfs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode) return retval; } -static int ramfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd) +static int ramfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return ramfs_mknod(dir, dentry, mode | S_IFREG, 0); } diff --git a/fs/read_write.c b/fs/read_write.c index c20614f86c01..1adfb691e4f1 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -55,10 +55,11 @@ static loff_t lseek_execute(struct file *file, struct inode *inode, * @file: file structure to seek on * @offset: file offset to seek to * @origin: type of seek - * @size: max size of file system + * @size: max size of this file in file system + * @eof: offset used for SEEK_END position * * This is a variant of generic_file_llseek that allows passing in a custom - * file size. + * maximum file size and a custom EOF position, for e.g. hashed directories * * Synchronization: * SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms) @@ -67,13 +68,13 @@ static loff_t lseek_execute(struct file *file, struct inode *inode, */ loff_t generic_file_llseek_size(struct file *file, loff_t offset, int origin, - loff_t maxsize) + loff_t maxsize, loff_t eof) { struct inode *inode = file->f_mapping->host; switch (origin) { case SEEK_END: - offset += i_size_read(inode); + offset += eof; break; case SEEK_CUR: /* @@ -99,7 +100,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int origin, * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ - if (offset >= i_size_read(inode)) + if (offset >= eof) return -ENXIO; break; case SEEK_HOLE: @@ -107,9 +108,9 @@ generic_file_llseek_size(struct file *file, loff_t offset, int origin, * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ - if (offset >= i_size_read(inode)) + if (offset >= eof) return -ENXIO; - offset = i_size_read(inode); + offset = eof; break; } @@ -132,7 +133,8 @@ loff_t generic_file_llseek(struct file *file, loff_t offset, int origin) struct inode *inode = file->f_mapping->host; return generic_file_llseek_size(file, offset, origin, - inode->i_sb->s_maxbytes); + inode->i_sb->s_maxbytes, + i_size_read(inode)); } EXPORT_SYMBOL(generic_file_llseek); diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 84e8a69cee9d..8567fb847601 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -322,7 +322,7 @@ static int reiserfs_find_entry(struct inode *dir, const char *name, int namelen, } static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { int retval; int lock_depth; @@ -573,7 +573,7 @@ static int new_inode_init(struct inode *inode, struct inode *dir, umode_t mode) } static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { int retval; struct inode *inode; @@ -634,8 +634,8 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mod reiserfs_update_inode_transaction(inode); reiserfs_update_inode_transaction(dir); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); retval = journal_end(&th, dir->i_sb, jbegin_count); out_failed: @@ -712,8 +712,8 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode goto out_failed; } - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); retval = journal_end(&th, dir->i_sb, jbegin_count); out_failed: @@ -800,8 +800,8 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode // the above add_entry did not update dir's stat data reiserfs_update_sd(&th, dir); - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); retval = journal_end(&th, dir->i_sb, jbegin_count); out_failed: reiserfs_write_unlock_once(dir->i_sb, lock_depth); @@ -1096,8 +1096,8 @@ static int reiserfs_symlink(struct inode *parent_dir, goto out_failed; } - d_instantiate(dentry, inode); unlock_new_inode(inode); + d_instantiate(dentry, inode); retval = journal_end(&th, parent_dir->i_sb, jbegin_count); out_failed: reiserfs_write_unlock(parent_dir->i_sb); diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c index 2c1ade692cc8..e60e87035bb3 100644 --- a/fs/reiserfs/procfs.c +++ b/fs/reiserfs/procfs.c @@ -403,7 +403,7 @@ static void *r_start(struct seq_file *m, loff_t * pos) if (l) return NULL; - if (IS_ERR(sget(&reiserfs_fs_type, test_sb, set_sb, s))) + if (IS_ERR(sget(&reiserfs_fs_type, test_sb, set_sb, 0, s))) return NULL; up_write(&s->s_umount); diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 651ce767b55d..7a37dabf5a96 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -68,6 +68,11 @@ static int reiserfs_sync_fs(struct super_block *s, int wait) { struct reiserfs_transaction_handle th; + /* + * Writeback quota in non-journalled quota case - journalled quota has + * no dirty dquots + */ + dquot_writeback_dquots(s, -1); reiserfs_write_lock(s); if (!journal_begin(&th, s, 1)) if (!journal_end_sync(&th, s, 1)) diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 46fc1c20a6b1..d319963aeb11 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -62,7 +62,7 @@ static int xattr_create(struct inode *dir, struct dentry *dentry, int mode) { BUG_ON(!mutex_is_locked(&dir->i_mutex)); - return dir->i_op->create(dir, dentry, mode, NULL); + return dir->i_op->create(dir, dentry, mode, true); } #endif @@ -942,7 +942,7 @@ int reiserfs_permission(struct inode *inode, int mask) return generic_permission(inode, mask); } -static int xattr_hide_revalidate(struct dentry *dentry, struct nameidata *nd) +static int xattr_hide_revalidate(struct dentry *dentry, unsigned int flags) { return -EPERM; } diff --git a/fs/romfs/super.c b/fs/romfs/super.c index e64f6b5f7ae5..77c5f2173983 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -210,7 +210,7 @@ out: * look up an entry in a directory */ static struct dentry *romfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { unsigned long offset, maxoff; struct inode *inode; diff --git a/fs/splice.c b/fs/splice.c index c9f1318a3b82..7bf08fa22ec9 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -273,13 +273,16 @@ void spd_release_page(struct splice_pipe_desc *spd, unsigned int i) * Check if we need to grow the arrays holding pages and partial page * descriptions. */ -int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) +int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { - if (pipe->buffers <= PIPE_DEF_BUFFERS) + unsigned int buffers = ACCESS_ONCE(pipe->buffers); + + spd->nr_pages_max = buffers; + if (buffers <= PIPE_DEF_BUFFERS) return 0; - spd->pages = kmalloc(pipe->buffers * sizeof(struct page *), GFP_KERNEL); - spd->partial = kmalloc(pipe->buffers * sizeof(struct partial_page), GFP_KERNEL); + spd->pages = kmalloc(buffers * sizeof(struct page *), GFP_KERNEL); + spd->partial = kmalloc(buffers * sizeof(struct partial_page), GFP_KERNEL); if (spd->pages && spd->partial) return 0; @@ -289,10 +292,9 @@ int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) return -ENOMEM; } -void splice_shrink_spd(struct pipe_inode_info *pipe, - struct splice_pipe_desc *spd) +void splice_shrink_spd(struct splice_pipe_desc *spd) { - if (pipe->buffers <= PIPE_DEF_BUFFERS) + if (spd->nr_pages_max <= PIPE_DEF_BUFFERS) return; kfree(spd->pages); @@ -315,6 +317,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &page_cache_pipe_buf_ops, .spd_release = spd_release_page, @@ -326,7 +329,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, index = *ppos >> PAGE_CACHE_SHIFT; loff = *ppos & ~PAGE_CACHE_MASK; req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - nr_pages = min(req_pages, pipe->buffers); + nr_pages = min(req_pages, spd.nr_pages_max); /* * Lookup the (hopefully) full range of pages we need. @@ -497,7 +500,7 @@ fill_it: if (spd.nr_pages) error = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return error; } @@ -598,6 +601,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &default_pipe_buf_ops, .spd_release = spd_release_page, @@ -608,8 +612,8 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, res = -ENOMEM; vec = __vec; - if (pipe->buffers > PIPE_DEF_BUFFERS) { - vec = kmalloc(pipe->buffers * sizeof(struct iovec), GFP_KERNEL); + if (spd.nr_pages_max > PIPE_DEF_BUFFERS) { + vec = kmalloc(spd.nr_pages_max * sizeof(struct iovec), GFP_KERNEL); if (!vec) goto shrink_ret; } @@ -617,7 +621,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, offset = *ppos & ~PAGE_CACHE_MASK; nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - for (i = 0; i < nr_pages && i < pipe->buffers && len; i++) { + for (i = 0; i < nr_pages && i < spd.nr_pages_max && len; i++) { struct page *page; page = alloc_page(GFP_USER); @@ -665,7 +669,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, shrink_ret: if (vec != __vec) kfree(vec); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return res; err: @@ -1614,6 +1618,7 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &user_page_pipe_buf_ops, .spd_release = spd_release_page, @@ -1629,13 +1634,13 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov, spd.nr_pages = get_iovec_page_array(iov, nr_segs, spd.pages, spd.partial, false, - pipe->buffers); + spd.nr_pages_max); if (spd.nr_pages <= 0) ret = spd.nr_pages; else ret = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return ret; } diff --git a/fs/squashfs/namei.c b/fs/squashfs/namei.c index abcc58f3c152..7834a517f7f4 100644 --- a/fs/squashfs/namei.c +++ b/fs/squashfs/namei.c @@ -134,7 +134,7 @@ out: static struct dentry *squashfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { const unsigned char *name = dentry->d_name.name; int len = dentry->d_name.len; diff --git a/fs/super.c b/fs/super.c index cf001775617f..c743fb3be4b8 100644 --- a/fs/super.c +++ b/fs/super.c @@ -105,11 +105,12 @@ static int prune_super(struct shrinker *shrink, struct shrink_control *sc) /** * alloc_super - create new superblock * @type: filesystem type superblock should belong to + * @flags: the mount flags * * Allocates and initializes a new &struct super_block. alloc_super() * returns a pointer new superblock or %NULL if allocation had failed. */ -static struct super_block *alloc_super(struct file_system_type *type) +static struct super_block *alloc_super(struct file_system_type *type, int flags) { struct super_block *s = kzalloc(sizeof(struct super_block), GFP_USER); static const struct super_operations default_op; @@ -136,6 +137,7 @@ static struct super_block *alloc_super(struct file_system_type *type) #else INIT_LIST_HEAD(&s->s_files); #endif + s->s_flags = flags; s->s_bdi = &default_backing_dev_info; INIT_HLIST_NODE(&s->s_instances); INIT_HLIST_BL_HEAD(&s->s_anon); @@ -415,11 +417,13 @@ EXPORT_SYMBOL(generic_shutdown_super); * @type: filesystem type superblock should belong to * @test: comparison callback * @set: setup callback + * @flags: mount flags * @data: argument to each of them */ struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), + int flags, void *data) { struct super_block *s = NULL; @@ -450,7 +454,7 @@ retry: } if (!s) { spin_unlock(&sb_lock); - s = alloc_super(type); + s = alloc_super(type, flags); if (!s) return ERR_PTR(-ENOMEM); goto retry; @@ -925,13 +929,12 @@ struct dentry *mount_ns(struct file_system_type *fs_type, int flags, { struct super_block *sb; - sb = sget(fs_type, ns_test_super, ns_set_super, data); + sb = sget(fs_type, ns_test_super, ns_set_super, flags, data); if (IS_ERR(sb)) return ERR_CAST(sb); if (!sb->s_root) { int err; - sb->s_flags = flags; err = fill_super(sb, data, flags & MS_SILENT ? 1 : 0); if (err) { deactivate_locked_super(sb); @@ -992,7 +995,8 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, error = -EBUSY; goto error_bdev; } - s = sget(fs_type, test_bdev_super, set_bdev_super, bdev); + s = sget(fs_type, test_bdev_super, set_bdev_super, flags | MS_NOSEC, + bdev); mutex_unlock(&bdev->bd_fsfreeze_mutex); if (IS_ERR(s)) goto error_s; @@ -1017,7 +1021,6 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, } else { char b[BDEVNAME_SIZE]; - s->s_flags = flags | MS_NOSEC; s->s_mode = mode; strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); sb_set_blocksize(s, block_size(bdev)); @@ -1062,13 +1065,11 @@ struct dentry *mount_nodev(struct file_system_type *fs_type, int (*fill_super)(struct super_block *, void *, int)) { int error; - struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL); + struct super_block *s = sget(fs_type, NULL, set_anon_super, flags, NULL); if (IS_ERR(s)) return ERR_CAST(s); - s->s_flags = flags; - error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) { deactivate_locked_super(s); @@ -1091,11 +1092,10 @@ struct dentry *mount_single(struct file_system_type *fs_type, struct super_block *s; int error; - s = sget(fs_type, compare_single, set_anon_super, NULL); + s = sget(fs_type, compare_single, set_anon_super, flags, NULL); if (IS_ERR(s)) return ERR_CAST(s); if (!s->s_root) { - s->s_flags = flags; error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) { deactivate_locked_super(s); diff --git a/fs/sync.c b/fs/sync.c index 11e3d1c44901..eb8722dc556f 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -29,16 +29,6 @@ */ static int __sync_filesystem(struct super_block *sb, int wait) { - /* - * This should be safe, as we require bdi backing to actually - * write out data in the first place - */ - if (sb->s_bdi == &noop_backing_dev_info) - return 0; - - if (sb->s_qcop && sb->s_qcop->quota_sync) - sb->s_qcop->quota_sync(sb, -1, wait); - if (wait) sync_inodes_sb(sb); else @@ -77,29 +67,48 @@ int sync_filesystem(struct super_block *sb) } EXPORT_SYMBOL_GPL(sync_filesystem); -static void sync_one_sb(struct super_block *sb, void *arg) +static void sync_inodes_one_sb(struct super_block *sb, void *arg) { if (!(sb->s_flags & MS_RDONLY)) - __sync_filesystem(sb, *(int *)arg); + sync_inodes_sb(sb); } -/* - * Sync all the data for all the filesystems (called by sys_sync() and - * emergency sync) - */ -static void sync_filesystems(int wait) + +static void sync_fs_one_sb(struct super_block *sb, void *arg) { - iterate_supers(sync_one_sb, &wait); + if (!(sb->s_flags & MS_RDONLY) && sb->s_op->sync_fs) + sb->s_op->sync_fs(sb, *(int *)arg); +} + +static void fdatawrite_one_bdev(struct block_device *bdev, void *arg) +{ + filemap_fdatawrite(bdev->bd_inode->i_mapping); +} + +static void fdatawait_one_bdev(struct block_device *bdev, void *arg) +{ + filemap_fdatawait(bdev->bd_inode->i_mapping); } /* - * sync everything. Start out by waking pdflush, because that writes back - * all queues in parallel. + * Sync everything. We start by waking flusher threads so that most of + * writeback runs on all devices in parallel. Then we sync all inodes reliably + * which effectively also waits for all flusher threads to finish doing + * writeback. At this point all data is on disk so metadata should be stable + * and we tell filesystems to sync their metadata via ->sync_fs() calls. + * Finally, we writeout all block devices because some filesystems (e.g. ext2) + * just write metadata (such as inodes or bitmaps) to block device page cache + * and do not sync it on their own in ->sync_fs(). */ SYSCALL_DEFINE0(sync) { + int nowait = 0, wait = 1; + wakeup_flusher_threads(0, WB_REASON_SYNC); - sync_filesystems(0); - sync_filesystems(1); + iterate_supers(sync_inodes_one_sb, NULL); + iterate_supers(sync_fs_one_sb, &nowait); + iterate_supers(sync_fs_one_sb, &wait); + iterate_bdevs(fdatawrite_one_bdev, NULL); + iterate_bdevs(fdatawait_one_bdev, NULL); if (unlikely(laptop_mode)) laptop_sync_completion(); return 0; @@ -107,12 +116,18 @@ SYSCALL_DEFINE0(sync) static void do_sync_work(struct work_struct *work) { + int nowait = 0; + /* * Sync twice to reduce the possibility we skipped some inodes / pages * because they were temporarily locked */ - sync_filesystems(0); - sync_filesystems(0); + iterate_supers(sync_inodes_one_sb, &nowait); + iterate_supers(sync_fs_one_sb, &nowait); + iterate_bdevs(fdatawrite_one_bdev, NULL); + iterate_supers(sync_inodes_one_sb, &nowait); + iterate_supers(sync_fs_one_sb, &nowait); + iterate_bdevs(fdatawrite_one_bdev, NULL); printk("Emergency Sync complete\n"); kfree(work); } diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index e6bb9b2a4cbe..a5cf784f9cc2 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -300,15 +300,15 @@ void release_sysfs_dirent(struct sysfs_dirent * sd) static int sysfs_dentry_delete(const struct dentry *dentry) { struct sysfs_dirent *sd = dentry->d_fsdata; - return !!(sd->s_flags & SYSFS_FLAG_REMOVED); + return !(sd && !(sd->s_flags & SYSFS_FLAG_REMOVED)); } -static int sysfs_dentry_revalidate(struct dentry *dentry, struct nameidata *nd) +static int sysfs_dentry_revalidate(struct dentry *dentry, unsigned int flags) { struct sysfs_dirent *sd; int is_dir; - if (nd->flags & LOOKUP_RCU) + if (flags & LOOKUP_RCU) return -ECHILD; sd = dentry->d_fsdata; @@ -355,18 +355,15 @@ out_bad: return 0; } -static void sysfs_dentry_iput(struct dentry *dentry, struct inode *inode) +static void sysfs_dentry_release(struct dentry *dentry) { - struct sysfs_dirent * sd = dentry->d_fsdata; - - sysfs_put(sd); - iput(inode); + sysfs_put(dentry->d_fsdata); } -static const struct dentry_operations sysfs_dentry_ops = { +const struct dentry_operations sysfs_dentry_ops = { .d_revalidate = sysfs_dentry_revalidate, .d_delete = sysfs_dentry_delete, - .d_iput = sysfs_dentry_iput, + .d_release = sysfs_dentry_release, }; struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type) @@ -764,7 +761,7 @@ int sysfs_create_dir(struct kobject * kobj) } static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct dentry *ret = NULL; struct dentry *parent = dentry->d_parent; @@ -786,6 +783,7 @@ static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry, ret = ERR_PTR(-ENOENT); goto out_unlock; } + dentry->d_fsdata = sysfs_get(sd); /* attach dentry and inode */ inode = sysfs_get_inode(dir->i_sb, sd); @@ -795,16 +793,7 @@ static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry, } /* instantiate and hash dentry */ - ret = d_find_alias(inode); - if (!ret) { - d_set_d_op(dentry, &sysfs_dentry_ops); - dentry->d_fsdata = sysfs_get(sd); - d_add(dentry, inode); - } else { - d_move(ret, dentry); - iput(inode); - } - + ret = d_materialise_unique(dentry, inode); out_unlock: mutex_unlock(&sysfs_mutex); return ret; diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 52c3bdb66a84..71eb7e253927 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -68,6 +68,7 @@ static int sysfs_fill_super(struct super_block *sb, void *data, int silent) } root->d_fsdata = &sysfs_root; sb->s_root = root; + sb->s_d_op = &sysfs_dentry_ops; return 0; } @@ -117,13 +118,12 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) info->ns[type] = kobj_ns_grab_current(type); - sb = sget(fs_type, sysfs_test_super, sysfs_set_super, info); + sb = sget(fs_type, sysfs_test_super, sysfs_set_super, flags, info); if (IS_ERR(sb) || sb->s_fs_info != info) free_sysfs_super_info(info); if (IS_ERR(sb)) return ERR_CAST(sb); if (!sb->s_root) { - sb->s_flags = flags; error = sysfs_fill_super(sb, data, flags & MS_SILENT ? 1 : 0); if (error) { deactivate_locked_super(sb); diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index 661a9639570b..d73c0932bbd6 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -157,6 +157,7 @@ extern struct kmem_cache *sysfs_dir_cachep; */ extern struct mutex sysfs_mutex; extern spinlock_t sysfs_assoc_lock; +extern const struct dentry_operations sysfs_dentry_ops; extern const struct file_operations sysfs_dir_operations; extern const struct inode_operations sysfs_dir_inode_operations; diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 08d0b2568cd3..80e1e2b18df1 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -43,7 +43,6 @@ static int sysv_sync_fs(struct super_block *sb, int wait) * then attach current time stamp. * But if the filesystem was marked clean, keep it clean. */ - sb->s_dirt = 0; old_time = fs32_to_cpu(sbi, *sbi->s_sb_time); if (sbi->s_type == FSTYPE_SYSV4) { if (*sbi->s_sb_state == cpu_to_fs32(sbi, 0x7c269d38 - old_time)) @@ -57,23 +56,12 @@ static int sysv_sync_fs(struct super_block *sb, int wait) return 0; } -static void sysv_write_super(struct super_block *sb) -{ - if (!(sb->s_flags & MS_RDONLY)) - sysv_sync_fs(sb, 1); - else - sb->s_dirt = 0; -} - static int sysv_remount(struct super_block *sb, int *flags, char *data) { struct sysv_sb_info *sbi = SYSV_SB(sb); - lock_super(sb); + if (sbi->s_forced_ro) *flags |= MS_RDONLY; - if (*flags & MS_RDONLY) - sysv_write_super(sb); - unlock_super(sb); return 0; } @@ -81,9 +69,6 @@ static void sysv_put_super(struct super_block *sb) { struct sysv_sb_info *sbi = SYSV_SB(sb); - if (sb->s_dirt) - sysv_write_super(sb); - if (!(sb->s_flags & MS_RDONLY)) { /* XXX ext2 also updates the state here */ mark_buffer_dirty(sbi->s_bh1); @@ -357,7 +342,6 @@ const struct super_operations sysv_sops = { .write_inode = sysv_write_inode, .evict_inode = sysv_evict_inode, .put_super = sysv_put_super, - .write_super = sysv_write_super, .sync_fs = sysv_sync_fs, .remount_fs = sysv_remount, .statfs = sysv_statfs, diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index d7466e293614..1c0d5f264767 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -43,7 +43,7 @@ const struct dentry_operations sysv_dentry_operations = { .d_hash = sysv_hash, }; -static struct dentry *sysv_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd) +static struct dentry *sysv_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags) { struct inode * inode = NULL; ino_t ino; @@ -80,7 +80,7 @@ static int sysv_mknod(struct inode * dir, struct dentry * dentry, umode_t mode, return err; } -static int sysv_create(struct inode * dir, struct dentry * dentry, umode_t mode, struct nameidata *nd) +static int sysv_create(struct inode * dir, struct dentry * dentry, umode_t mode, bool excl) { return sysv_mknod(dir, dentry, mode, 0); } diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h index 11b07672f6c5..0bc35fdc58e2 100644 --- a/fs/sysv/sysv.h +++ b/fs/sysv/sysv.h @@ -117,7 +117,6 @@ static inline void dirty_sb(struct super_block *sb) mark_buffer_dirty(sbi->s_bh1); if (sbi->s_bh1 != sbi->s_bh2) mark_buffer_dirty(sbi->s_bh2); - sb->s_dirt = 1; } diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 92df3b081539..bb3167257aab 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -2802,6 +2802,8 @@ static ssize_t dfs_file_read(struct file *file, char __user *u, size_t count, val = d->chk_fs; else if (dent == d->dfs_tst_rcvry) val = d->tst_rcvry; + else if (dent == d->dfs_ro_error) + val = c->ro_error; else return -EINVAL; @@ -2885,6 +2887,8 @@ static ssize_t dfs_file_write(struct file *file, const char __user *u, d->chk_fs = val; else if (dent == d->dfs_tst_rcvry) d->tst_rcvry = val; + else if (dent == d->dfs_ro_error) + c->ro_error = !!val; else return -EINVAL; @@ -2996,6 +3000,13 @@ int dbg_debugfs_init_fs(struct ubifs_info *c) goto out_remove; d->dfs_tst_rcvry = dent; + fname = "ro_error"; + dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, d->dfs_dir, c, + &dfs_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + d->dfs_ro_error = dent; + return 0; out_remove: diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h index 486a8e024fb6..8b8cc4e945f4 100644 --- a/fs/ubifs/debug.h +++ b/fs/ubifs/debug.h @@ -79,6 +79,10 @@ typedef int (*dbg_znode_callback)(struct ubifs_info *c, * @dfs_chk_lprops: debugfs knob to enable UBIFS LEP properties extra checks * @dfs_chk_fs: debugfs knob to enable UBIFS contents extra checks * @dfs_tst_rcvry: debugfs knob to enable UBIFS recovery testing + * @dfs_ro_error: debugfs knob to switch UBIFS to R/O mode (different to + * re-mounting to R/O mode because it does not flush any buffers + * and UBIFS just starts returning -EROFS on all write + * operations) */ struct ubifs_debug_info { struct ubifs_zbranch old_zroot; @@ -122,6 +126,7 @@ struct ubifs_debug_info { struct dentry *dfs_chk_lprops; struct dentry *dfs_chk_fs; struct dentry *dfs_tst_rcvry; + struct dentry *dfs_ro_error; }; /** diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index a6d42efc76d2..c95681cf1b71 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -184,7 +184,7 @@ static int dbg_check_name(const struct ubifs_info *c, } static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { int err; union ubifs_key key; @@ -246,7 +246,7 @@ out: } static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct inode *inode; struct ubifs_info *c = dir->i_sb->s_fs_info; @@ -969,7 +969,7 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry, struct ubifs_budget_req ino_req = { .dirtied_ino = 1, .dirtied_ino_d = ALIGN(old_inode_ui->data_len, 8) }; struct timespec time; - unsigned int saved_nlink; + unsigned int uninitialized_var(saved_nlink); /* * Budget request settings: deletion direntry, new direntry, removing diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c index b02734db187c..cebf17ea0458 100644 --- a/fs/ubifs/orphan.c +++ b/fs/ubifs/orphan.c @@ -176,7 +176,7 @@ int ubifs_orphan_start_commit(struct ubifs_info *c) *last = orphan; last = &orphan->cnext; } - *last = orphan->cnext; + *last = NULL; c->cmt_orphans = c->new_orphans; c->new_orphans = 0; dbg_cmt("%d orphans to commit", c->cmt_orphans); @@ -382,7 +382,7 @@ static int consolidate(struct ubifs_info *c) last = &orphan->cnext; cnt += 1; } - *last = orphan->cnext; + *last = NULL; ubifs_assert(cnt == c->tot_orphans - c->new_orphans); c->cmt_orphans = cnt; c->ohead_lnum = c->orph_first; diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index 3a2da7e476e5..eba46d4a7619 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -1007,7 +1007,7 @@ out: */ int ubifs_replay_journal(struct ubifs_info *c) { - int err, i, lnum, offs, free; + int err, lnum, free; BUILD_BUG_ON(UBIFS_TRUN_KEY > 5); @@ -1025,25 +1025,17 @@ int ubifs_replay_journal(struct ubifs_info *c) dbg_mnt("start replaying the journal"); c->replaying = 1; lnum = c->ltail_lnum = c->lhead_lnum; - offs = c->lhead_offs; - for (i = 0; i < c->log_lebs; i++, lnum++) { - if (lnum >= UBIFS_LOG_LNUM + c->log_lebs) { - /* - * The log is logically circular, we reached the last - * LEB, switch to the first one. - */ - lnum = UBIFS_LOG_LNUM; - offs = 0; - } - err = replay_log_leb(c, lnum, offs, c->sbuf); + lnum = UBIFS_LOG_LNUM; + do { + err = replay_log_leb(c, lnum, 0, c->sbuf); if (err == 1) /* We hit the end of the log */ break; if (err) goto out; - offs = 0; - } + lnum = ubifs_next_log_lnum(c, lnum); + } while (lnum != UBIFS_LOG_LNUM); err = replay_buds(c); if (err) diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c index ef3d1ba6d992..15e2fc5aa60b 100644 --- a/fs/ubifs/sb.c +++ b/fs/ubifs/sb.c @@ -718,8 +718,12 @@ static int fixup_free_space(struct ubifs_info *c) lnum = ubifs_next_log_lnum(c, lnum); } - /* Fixup the current log head */ - err = fixup_leb(c, c->lhead_lnum, c->lhead_offs); + /* + * Fixup the log head which contains the only a CS node at the + * beginning. + */ + err = fixup_leb(c, c->lhead_lnum, + ALIGN(UBIFS_CS_NODE_SZ, c->min_io_size)); if (err) goto out; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 5862dd9d2784..1c766c39c038 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2136,7 +2136,7 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, dbg_gen("opened ubi%d_%d", c->vi.ubi_num, c->vi.vol_id); - sb = sget(fs_type, sb_test, sb_set, c); + sb = sget(fs_type, sb_test, sb_set, flags, c); if (IS_ERR(sb)) { err = PTR_ERR(sb); kfree(c); @@ -2153,7 +2153,6 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, goto out_deact; } } else { - sb->s_flags = flags; err = ubifs_fill_super(sb, data, flags & MS_SILENT ? 1 : 0); if (err) goto out_deact; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 18024178ac4c..544b2799a911 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -251,7 +251,7 @@ out_ok: } static struct dentry *udf_lookup(struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct inode *inode = NULL; struct fileIdentDesc cfi; @@ -551,7 +551,7 @@ static int udf_delete_entry(struct inode *inode, struct fileIdentDesc *fi, } static int udf_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct udf_fileident_bh fibh; struct inode *inode; diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index 42694e11c23d..1b3e410bf334 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -116,7 +116,7 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count) ubh_mark_buffer_dirty (UCPI_UBH(ucpi)); if (sb->s_flags & MS_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); unlock_super (sb); UFSD("EXIT\n"); @@ -214,7 +214,7 @@ do_more: goto do_more; } - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); unlock_super (sb); UFSD("EXIT\n"); return; @@ -557,7 +557,7 @@ static u64 ufs_add_fragments(struct inode *inode, u64 fragment, ubh_mark_buffer_dirty (UCPI_UBH(ucpi)); if (sb->s_flags & MS_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); UFSD("EXIT, fragment %llu\n", (unsigned long long)fragment); @@ -677,7 +677,7 @@ succed: ubh_mark_buffer_dirty (UCPI_UBH(ucpi)); if (sb->s_flags & MS_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); result += cgno * uspi->s_fpg; UFSD("EXIT3, result %llu\n", (unsigned long long)result); diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c index 4ec5c1085a87..e84cbe21b986 100644 --- a/fs/ufs/ialloc.c +++ b/fs/ufs/ialloc.c @@ -116,7 +116,7 @@ void ufs_free_inode (struct inode * inode) if (sb->s_flags & MS_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); unlock_super (sb); UFSD("EXIT\n"); } @@ -288,7 +288,7 @@ cg_found: ubh_mark_buffer_dirty (UCPI_UBH(ucpi)); if (sb->s_flags & MS_SYNCHRONOUS) ubh_sync_block(UCPI_UBH(ucpi)); - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); inode->i_ino = cg * uspi->s_ipg + bit; inode_init_owner(inode, dir, mode); diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index a2281cadefa1..90d74b8f8eba 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -46,7 +46,7 @@ static inline int ufs_add_nondir(struct dentry *dentry, struct inode *inode) return err; } -static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags) { struct inode * inode = NULL; ino_t ino; @@ -71,7 +71,7 @@ static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, stru * with d_instantiate(). */ static int ufs_create (struct inode * dir, struct dentry * dentry, umode_t mode, - struct nameidata *nd) + bool excl) { struct inode *inode; int err; diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 302f340d0071..444927e5706b 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -302,7 +302,7 @@ void ufs_error (struct super_block * sb, const char * function, if (!(sb->s_flags & MS_RDONLY)) { usb1->fs_clean = UFS_FSBAD; ubh_mark_buffer_dirty(USPI_UBH(uspi)); - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); sb->s_flags |= MS_RDONLY; } va_start (args, fmt); @@ -334,7 +334,7 @@ void ufs_panic (struct super_block * sb, const char * function, if (!(sb->s_flags & MS_RDONLY)) { usb1->fs_clean = UFS_FSBAD; ubh_mark_buffer_dirty(USPI_UBH(uspi)); - sb->s_dirt = 1; + ufs_mark_sb_dirty(sb); } va_start (args, fmt); vsnprintf (error_buf, sizeof(error_buf), fmt, args); @@ -691,6 +691,83 @@ static void ufs_put_super_internal(struct super_block *sb) UFSD("EXIT\n"); } +static int ufs_sync_fs(struct super_block *sb, int wait) +{ + struct ufs_sb_private_info * uspi; + struct ufs_super_block_first * usb1; + struct ufs_super_block_third * usb3; + unsigned flags; + + lock_ufs(sb); + lock_super(sb); + + UFSD("ENTER\n"); + + flags = UFS_SB(sb)->s_flags; + uspi = UFS_SB(sb)->s_uspi; + usb1 = ubh_get_usb_first(uspi); + usb3 = ubh_get_usb_third(uspi); + + usb1->fs_time = cpu_to_fs32(sb, get_seconds()); + if ((flags & UFS_ST_MASK) == UFS_ST_SUN || + (flags & UFS_ST_MASK) == UFS_ST_SUNOS || + (flags & UFS_ST_MASK) == UFS_ST_SUNx86) + ufs_set_fs_state(sb, usb1, usb3, + UFS_FSOK - fs32_to_cpu(sb, usb1->fs_time)); + ufs_put_cstotal(sb); + + UFSD("EXIT\n"); + unlock_super(sb); + unlock_ufs(sb); + + return 0; +} + +static void delayed_sync_fs(struct work_struct *work) +{ + struct ufs_sb_info *sbi; + + sbi = container_of(work, struct ufs_sb_info, sync_work.work); + + spin_lock(&sbi->work_lock); + sbi->work_queued = 0; + spin_unlock(&sbi->work_lock); + + ufs_sync_fs(sbi->sb, 1); +} + +void ufs_mark_sb_dirty(struct super_block *sb) +{ + struct ufs_sb_info *sbi = UFS_SB(sb); + unsigned long delay; + + spin_lock(&sbi->work_lock); + if (!sbi->work_queued) { + delay = msecs_to_jiffies(dirty_writeback_interval * 10); + queue_delayed_work(system_long_wq, &sbi->sync_work, delay); + sbi->work_queued = 1; + } + spin_unlock(&sbi->work_lock); +} + +static void ufs_put_super(struct super_block *sb) +{ + struct ufs_sb_info * sbi = UFS_SB(sb); + + UFSD("ENTER\n"); + + if (!(sb->s_flags & MS_RDONLY)) + ufs_put_super_internal(sb); + cancel_delayed_work_sync(&sbi->sync_work); + + ubh_brelse_uspi (sbi->s_uspi); + kfree (sbi->s_uspi); + kfree (sbi); + sb->s_fs_info = NULL; + UFSD("EXIT\n"); + return; +} + static int ufs_fill_super(struct super_block *sb, void *data, int silent) { struct ufs_sb_info * sbi; @@ -716,6 +793,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) if (!sbi) goto failed_nomem; sb->s_fs_info = sbi; + sbi->sb = sb; UFSD("flag %u\n", (int)(sb->s_flags & MS_RDONLY)); @@ -727,6 +805,8 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) } #endif mutex_init(&sbi->mutex); + spin_lock_init(&sbi->work_lock); + INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs); /* * Set default mount options * Parse mount options @@ -1191,68 +1271,6 @@ failed_nomem: return -ENOMEM; } -static int ufs_sync_fs(struct super_block *sb, int wait) -{ - struct ufs_sb_private_info * uspi; - struct ufs_super_block_first * usb1; - struct ufs_super_block_third * usb3; - unsigned flags; - - lock_ufs(sb); - lock_super(sb); - - UFSD("ENTER\n"); - - flags = UFS_SB(sb)->s_flags; - uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(uspi); - usb3 = ubh_get_usb_third(uspi); - - usb1->fs_time = cpu_to_fs32(sb, get_seconds()); - if ((flags & UFS_ST_MASK) == UFS_ST_SUN || - (flags & UFS_ST_MASK) == UFS_ST_SUNOS || - (flags & UFS_ST_MASK) == UFS_ST_SUNx86) - ufs_set_fs_state(sb, usb1, usb3, - UFS_FSOK - fs32_to_cpu(sb, usb1->fs_time)); - ufs_put_cstotal(sb); - sb->s_dirt = 0; - - UFSD("EXIT\n"); - unlock_super(sb); - unlock_ufs(sb); - - return 0; -} - -static void ufs_write_super(struct super_block *sb) -{ - if (!(sb->s_flags & MS_RDONLY)) - ufs_sync_fs(sb, 1); - else - sb->s_dirt = 0; -} - -static void ufs_put_super(struct super_block *sb) -{ - struct ufs_sb_info * sbi = UFS_SB(sb); - - UFSD("ENTER\n"); - - if (sb->s_dirt) - ufs_write_super(sb); - - if (!(sb->s_flags & MS_RDONLY)) - ufs_put_super_internal(sb); - - ubh_brelse_uspi (sbi->s_uspi); - kfree (sbi->s_uspi); - kfree (sbi); - sb->s_fs_info = NULL; - UFSD("EXIT\n"); - return; -} - - static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) { struct ufs_sb_private_info * uspi; @@ -1308,7 +1326,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) ufs_set_fs_state(sb, usb1, usb3, UFS_FSOK - fs32_to_cpu(sb, usb1->fs_time)); ubh_mark_buffer_dirty (USPI_UBH(uspi)); - sb->s_dirt = 0; sb->s_flags |= MS_RDONLY; } else { /* @@ -1458,7 +1475,6 @@ static const struct super_operations ufs_super_ops = { .write_inode = ufs_write_inode, .evict_inode = ufs_evict_inode, .put_super = ufs_put_super, - .write_super = ufs_write_super, .sync_fs = ufs_sync_fs, .statfs = ufs_statfs, .remount_fs = ufs_remount, diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h index 528750b7e701..343e6fc571e5 100644 --- a/fs/ufs/ufs.h +++ b/fs/ufs/ufs.h @@ -20,6 +20,10 @@ struct ufs_sb_info { unsigned s_mount_opt; struct mutex mutex; struct task_struct *mutex_owner; + struct super_block *sb; + int work_queued; /* non-zero if the delayed work is queued */ + struct delayed_work sync_work; /* FS sync delayed work */ + spinlock_t work_lock; /* protects sync_work and work_queued */ }; struct ufs_inode_info { @@ -123,6 +127,7 @@ extern __printf(3, 4) void ufs_error(struct super_block *, const char *, const char *, ...); extern __printf(3, 4) void ufs_panic(struct super_block *, const char *, const char *, ...); +void ufs_mark_sb_dirty(struct super_block *sb); /* symlink.c */ extern const struct inode_operations ufs_fast_symlink_inode_operations; diff --git a/fs/ufs/ufs_fs.h b/fs/ufs/ufs_fs.h index 8aba544f9fad..0cbd5d340b67 100644 --- a/fs/ufs/ufs_fs.h +++ b/fs/ufs/ufs_fs.h @@ -34,6 +34,7 @@ #include <linux/kernel.h> #include <linux/stat.h> #include <linux/fs.h> +#include <linux/workqueue.h> #include <asm/div64.h> typedef __u64 __bitwise __fs64; diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index 9d1aeb7e2734..4f33c32affe3 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -1074,13 +1074,13 @@ restart: * If we couldn't get anything, give up. */ if (bno_cur_lt == NULL && bno_cur_gt == NULL) { + xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); + if (!forced++) { trace_xfs_alloc_near_busy(args); xfs_log_force(args->mp, XFS_LOG_SYNC); goto restart; } - - xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); trace_xfs_alloc_size_neither(args); args->agbno = NULLAGBLOCK; return 0; @@ -2434,13 +2434,22 @@ xfs_alloc_vextent_worker( current_restore_flags_nested(&pflags, PF_FSTRANS); } - -int /* error */ +/* + * Data allocation requests often come in with little stack to work on. Push + * them off to a worker thread so there is lots of stack to use. Metadata + * requests, OTOH, are generally from low stack usage paths, so avoid the + * context switch overhead here. + */ +int xfs_alloc_vextent( - xfs_alloc_arg_t *args) /* allocation argument structure */ + struct xfs_alloc_arg *args) { DECLARE_COMPLETION_ONSTACK(done); + if (!args->userdata) + return __xfs_alloc_vextent(args); + + args->done = &done; INIT_WORK_ONSTACK(&args->work, xfs_alloc_vextent_worker); queue_work(xfs_alloc_wq, &args->work); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index a4beb421018a..269b35c084da 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -989,27 +989,6 @@ xfs_buf_ioerror_alert( (__uint64_t)XFS_BUF_ADDR(bp), func, bp->b_error, bp->b_length); } -int -xfs_bwrite( - struct xfs_buf *bp) -{ - int error; - - ASSERT(xfs_buf_islocked(bp)); - - bp->b_flags |= XBF_WRITE; - bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q); - - xfs_bdstrat_cb(bp); - - error = xfs_buf_iowait(bp); - if (error) { - xfs_force_shutdown(bp->b_target->bt_mount, - SHUTDOWN_META_IO_ERROR); - } - return error; -} - /* * Called when we want to stop a buffer from getting written or read. * We attach the EIO error, muck with its flags, and call xfs_buf_ioend @@ -1079,14 +1058,7 @@ xfs_bioerror_relse( return EIO; } - -/* - * All xfs metadata buffers except log state machine buffers - * get this attached as their b_bdstrat callback function. - * This is so that we can catch a buffer - * after prematurely unpinning it to forcibly shutdown the filesystem. - */ -int +STATIC int xfs_bdstrat_cb( struct xfs_buf *bp) { @@ -1107,6 +1079,27 @@ xfs_bdstrat_cb( return 0; } +int +xfs_bwrite( + struct xfs_buf *bp) +{ + int error; + + ASSERT(xfs_buf_islocked(bp)); + + bp->b_flags |= XBF_WRITE; + bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q); + + xfs_bdstrat_cb(bp); + + error = xfs_buf_iowait(bp); + if (error) { + xfs_force_shutdown(bp->b_target->bt_mount, + SHUTDOWN_META_IO_ERROR); + } + return error; +} + /* * Wrapper around bdstrat so that we can stop data from going to disk in case * we are shutting down the filesystem. Typically user data goes thru this @@ -1243,7 +1236,7 @@ xfs_buf_iorequest( */ atomic_set(&bp->b_io_remaining, 1); _xfs_buf_ioapply(bp); - _xfs_buf_ioend(bp, 0); + _xfs_buf_ioend(bp, 1); xfs_buf_rele(bp); } diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 7f1d1392ce37..79344c48008e 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -180,7 +180,6 @@ extern void xfs_buf_unlock(xfs_buf_t *); extern int xfs_bwrite(struct xfs_buf *bp); extern void xfsbdstrat(struct xfs_mount *, struct xfs_buf *); -extern int xfs_bdstrat_cb(struct xfs_buf *); extern void xfs_buf_ioend(xfs_buf_t *, int); extern void xfs_buf_ioerror(xfs_buf_t *, int); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 45df2b857d48..d9e451115f98 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -954,7 +954,7 @@ xfs_buf_iodone_callbacks( if (!XFS_BUF_ISSTALE(bp)) { bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE; - xfs_bdstrat_cb(bp); + xfs_buf_iorequest(bp); } else { xfs_buf_relse(bp); } diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 3a05a41b5d76..1f1535d25a9b 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -208,6 +208,7 @@ xfs_open_by_handle( struct inode *inode; struct dentry *dentry; fmode_t fmode; + struct path path; if (!capable(CAP_SYS_ADMIN)) return -XFS_ERROR(EPERM); @@ -252,8 +253,10 @@ xfs_open_by_handle( goto out_dput; } - filp = dentry_open(dentry, mntget(parfilp->f_path.mnt), - hreq->oflags, cred); + path.mnt = parfilp->f_path.mnt; + path.dentry = dentry; + filp = dentry_open(&path, hreq->oflags, cred); + dput(dentry); if (IS_ERR(filp)) { put_unused_fd(fd); return PTR_ERR(filp); diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 1a25fd802798..9c4340f5c3e0 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -179,7 +179,7 @@ xfs_vn_create( struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool flags) { return xfs_vn_mknod(dir, dentry, mode, 0); } @@ -197,7 +197,7 @@ STATIC struct dentry * xfs_vn_lookup( struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct xfs_inode *cip; struct xfs_name name; @@ -222,7 +222,7 @@ STATIC struct dentry * xfs_vn_ci_lookup( struct inode *dir, struct dentry *dentry, - struct nameidata *nd) + unsigned int flags) { struct xfs_inode *ip; struct xfs_name xname; diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 9e6e1c6eb60a..18fd41033e03 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -117,9 +117,6 @@ struct acpi_device; typedef int (*acpi_op_add) (struct acpi_device * device); typedef int (*acpi_op_remove) (struct acpi_device * device, int type); typedef int (*acpi_op_start) (struct acpi_device * device); -typedef int (*acpi_op_suspend) (struct acpi_device * device, - pm_message_t state); -typedef int (*acpi_op_resume) (struct acpi_device * device); typedef int (*acpi_op_bind) (struct acpi_device * device); typedef int (*acpi_op_unbind) (struct acpi_device * device); typedef void (*acpi_op_notify) (struct acpi_device * device, u32 event); @@ -133,8 +130,6 @@ struct acpi_device_ops { acpi_op_add add; acpi_op_remove remove; acpi_op_start start; - acpi_op_suspend suspend; - acpi_op_resume resume; acpi_op_bind bind; acpi_op_unbind unbind; acpi_op_notify notify; diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 9d650476d5dc..64ec644808bc 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -59,10 +59,7 @@ struct acpi_processor_cx { u8 entry_method; u8 index; u32 latency; - u32 latency_ticks; u32 power; - u32 usage; - u64 time; u8 bm_sts_skip; char desc[ACPI_CX_DESC_LEN]; }; @@ -334,8 +331,8 @@ int acpi_processor_cst_has_changed(struct acpi_processor *pr); int acpi_processor_hotplug(struct acpi_processor *pr); int acpi_processor_power_exit(struct acpi_processor *pr, struct acpi_device *device); -int acpi_processor_suspend(struct acpi_device * device, pm_message_t state); -int acpi_processor_resume(struct acpi_device * device); +int acpi_processor_suspend(struct device *dev); +int acpi_processor_resume(struct device *dev); extern struct cpuidle_driver acpi_idle_driver; /* in processor_thermal.c */ diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h index c544356b374b..294b1e755ab2 100644 --- a/include/asm-generic/dma-contiguous.h +++ b/include/asm-generic/dma-contiguous.h @@ -18,7 +18,7 @@ static inline void dev_set_cma_area(struct device *dev, struct cma *cma) { if (dev) dev->cma_area = cma; - if (!dev || !dma_contiguous_default_area) + if (!dev && !dma_contiguous_default_area) dma_contiguous_default_area = cma; } diff --git a/include/linux/aio.h b/include/linux/aio.h index 2314ad8b3c9c..b1a520ec8b59 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -140,6 +140,7 @@ struct kiocb { (x)->ki_dtor = NULL; \ (x)->ki_obj.tsk = tsk; \ (x)->ki_user_data = 0; \ + (x)->private = NULL; \ } while (0) #define AIO_RING_MAGIC 0xa10a10a1 diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ba43f408baa3..07954b05b86c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -827,7 +827,6 @@ extern bool __blk_end_request_err(struct request *rq, int error); extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); -extern void blk_abort_queue(struct request_queue *); extern void blk_unprep_request(struct request *); /* diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 324fe08ea3b1..6d6795d46a75 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -91,6 +91,11 @@ extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal); +void *___alloc_bootmem_node_nopanic(pg_data_t *pgdat, + unsigned long size, + unsigned long align, + unsigned long goal, + unsigned long limit); extern void *__alloc_bootmem_low(unsigned long size, unsigned long align, unsigned long goal); diff --git a/include/linux/capability.h b/include/linux/capability.h index 68d56effc328..d10b7ed595b1 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -360,11 +360,11 @@ struct cpu_vfs_cap_data { #define CAP_WAKE_ALARM 35 -/* Allow preventing system suspends while epoll events are pending */ +/* Allow preventing system suspends */ -#define CAP_EPOLLWAKEUP 36 +#define CAP_BLOCK_SUSPEND 36 -#define CAP_LAST_CAP CAP_EPOLLWAKEUP +#define CAP_LAST_CAP CAP_BLOCK_SUSPEND #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP) diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 2521a95fa6d9..44c87e731e9d 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -163,16 +163,8 @@ struct ceph_connection { /* connection negotiation temps */ char in_banner[CEPH_BANNER_MAX_LEN]; - union { - struct { /* outgoing connection */ - struct ceph_msg_connect out_connect; - struct ceph_msg_connect_reply in_reply; - }; - struct { /* incoming */ - struct ceph_msg_connect in_connect; - struct ceph_msg_connect_reply out_reply; - }; - }; + struct ceph_msg_connect out_connect; + struct ceph_msg_connect_reply in_reply; struct ceph_entity_addr actual_peer_addr; /* message out temps */ diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 6c26a3da0e03..89dcd30ac8ea 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -34,6 +34,7 @@ struct cpuidle_driver; struct cpuidle_state_usage { void *driver_data; + unsigned long long disable; unsigned long long usage; unsigned long long time; /* in US */ }; @@ -46,7 +47,7 @@ struct cpuidle_state { unsigned int exit_latency; /* in US */ int power_usage; /* in mW */ unsigned int target_residency; /* in US */ - unsigned int disable; + bool disabled; /* disabled on all CPUs */ int (*enter) (struct cpuidle_device *dev, struct cpuidle_driver *drv, @@ -136,13 +137,17 @@ struct cpuidle_driver { extern void disable_cpuidle(void); extern int cpuidle_idle_call(void); extern int cpuidle_register_driver(struct cpuidle_driver *drv); -struct cpuidle_driver *cpuidle_get_driver(void); +extern struct cpuidle_driver *cpuidle_get_driver(void); +extern struct cpuidle_driver *cpuidle_driver_ref(void); +extern void cpuidle_driver_unref(void); extern void cpuidle_unregister_driver(struct cpuidle_driver *drv); extern int cpuidle_register_device(struct cpuidle_device *dev); extern void cpuidle_unregister_device(struct cpuidle_device *dev); extern void cpuidle_pause_and_lock(void); extern void cpuidle_resume_and_unlock(void); +extern void cpuidle_pause(void); +extern void cpuidle_resume(void); extern int cpuidle_enable_device(struct cpuidle_device *dev); extern void cpuidle_disable_device(struct cpuidle_device *dev); extern int cpuidle_wrap_enter(struct cpuidle_device *dev, @@ -157,6 +162,8 @@ static inline int cpuidle_idle_call(void) { return -ENODEV; } static inline int cpuidle_register_driver(struct cpuidle_driver *drv) {return -ENODEV; } static inline struct cpuidle_driver *cpuidle_get_driver(void) {return NULL; } +static inline struct cpuidle_driver *cpuidle_driver_ref(void) {return NULL; } +static inline void cpuidle_driver_unref(void) {} static inline void cpuidle_unregister_driver(struct cpuidle_driver *drv) { } static inline int cpuidle_register_device(struct cpuidle_device *dev) {return -ENODEV; } @@ -164,6 +171,8 @@ static inline void cpuidle_unregister_device(struct cpuidle_device *dev) { } static inline void cpuidle_pause_and_lock(void) { } static inline void cpuidle_resume_and_unlock(void) { } +static inline void cpuidle_pause(void) { } +static inline void cpuidle_resume(void) { } static inline int cpuidle_enable_device(struct cpuidle_device *dev) {return -ENODEV; } static inline void cpuidle_disable_device(struct cpuidle_device *dev) { } @@ -202,14 +211,7 @@ struct cpuidle_governor { extern int cpuidle_register_governor(struct cpuidle_governor *gov); extern void cpuidle_unregister_governor(struct cpuidle_governor *gov); -#ifdef CONFIG_INTEL_IDLE -extern int intel_idle_cpu_init(int cpu); #else -static inline int intel_idle_cpu_init(int cpu) { return -1; } -#endif - -#else -static inline int intel_idle_cpu_init(int cpu) { return -1; } static inline int cpuidle_register_governor(struct cpuidle_governor *gov) {return 0;} diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 094789ff3e9f..caa34e50537e 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -128,7 +128,7 @@ struct dentry { struct rcu_head d_rcu; } d_u; struct list_head d_subdirs; /* our children */ - struct list_head d_alias; /* inode alias list */ + struct hlist_node d_alias; /* inode alias list */ }; /* @@ -144,7 +144,7 @@ enum dentry_d_lock_class }; struct dentry_operations { - int (*d_revalidate)(struct dentry *, struct nameidata *); + int (*d_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, const struct inode *, struct qstr *); int (*d_compare)(const struct dentry *, const struct inode *, diff --git a/include/linux/device.h b/include/linux/device.h index 161d96241b1b..6de94151ff6f 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -865,8 +865,6 @@ extern int (*platform_notify_remove)(struct device *dev); extern struct device *get_device(struct device *dev); extern void put_device(struct device *dev); -extern void wait_for_device_probe(void); - #ifdef CONFIG_DEVTMPFS extern int devtmpfs_create_node(struct device *dev); extern int devtmpfs_delete_node(struct device *dev); diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 6f8be328770a..f4bb378ccf6a 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -34,7 +34,7 @@ * re-allowed until epoll_wait is called again after consuming the wakeup * event(s). * - * Requires CAP_EPOLLWAKEUP + * Requires CAP_BLOCK_SUSPEND */ #define EPOLLWAKEUP (1 << 29) diff --git a/include/linux/file.h b/include/linux/file.h index 58bf158c53d9..a22408bac0d0 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -39,4 +39,7 @@ extern void put_unused_fd(unsigned int fd); extern void fd_install(unsigned int fd, struct file *file); +extern void flush_delayed_fput(void); +extern void __fput_sync(struct file *); + #endif /* __LINUX_FILE_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 17fd887c798f..8fabb037a48d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -826,7 +826,7 @@ struct inode { struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; union { - struct list_head i_dentry; + struct hlist_head i_dentry; struct rcu_head i_rcu; }; u64 i_version; @@ -1571,7 +1571,7 @@ extern void unlock_super(struct super_block *); /* * VFS helper functions.. */ -extern int vfs_create(struct inode *, struct dentry *, umode_t, struct nameidata *); +extern int vfs_create(struct inode *, struct dentry *, umode_t, bool); extern int vfs_mkdir(struct inode *, struct dentry *, umode_t); extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); extern int vfs_symlink(struct inode *, struct dentry *, const char *); @@ -1666,7 +1666,7 @@ struct file_operations { }; struct inode_operations { - struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *); + struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); void * (*follow_link) (struct dentry *, struct nameidata *); int (*permission) (struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); @@ -1674,7 +1674,7 @@ struct inode_operations { int (*readlink) (struct dentry *, char __user *,int); void (*put_link) (struct dentry *, struct nameidata *, void *); - int (*create) (struct inode *,struct dentry *,umode_t,struct nameidata *); + int (*create) (struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct inode *,struct dentry *,const char *); @@ -1693,6 +1693,9 @@ struct inode_operations { int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); int (*update_time)(struct inode *, struct timespec *, int); + int (*atomic_open)(struct inode *, struct dentry *, + struct file *, unsigned open_flag, + umode_t create_mode, int *opened); } ____cacheline_aligned; struct seq_file; @@ -1911,7 +1914,7 @@ void free_anon_bdev(dev_t); struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), - void *data); + int flags, void *data); extern struct dentry *mount_pseudo(struct file_system_type *, char *, const struct super_operations *ops, const struct dentry_operations *dops, @@ -2057,10 +2060,17 @@ extern long do_sys_open(int dfd, const char __user *filename, int flags, extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int); -extern struct file * dentry_open(struct dentry *, struct vfsmount *, int, - const struct cred *); +extern struct file * dentry_open(const struct path *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); extern char * getname(const char __user *); +enum { + FILE_CREATED = 1, + FILE_OPENED = 2 +}; +extern int finish_open(struct file *file, struct dentry *dentry, + int (*open)(struct inode *, struct file *), + int *opened); +extern int finish_no_open(struct file *file, struct dentry *dentry); /* fs/ioctl.c */ @@ -2091,6 +2101,7 @@ extern sector_t blkdev_max_block(struct block_device *bdev); extern void bd_forget(struct inode *inode); extern void bdput(struct block_device *); extern void invalidate_bdev(struct block_device *); +extern void iterate_bdevs(void (*)(struct block_device *, void *), void *); extern int sync_blockdev(struct block_device *bdev); extern void kill_bdev(struct block_device *); extern struct super_block *freeze_bdev(struct block_device *); @@ -2112,6 +2123,10 @@ static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb) { return 0; } + +static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg) +{ +} #endif extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; @@ -2438,7 +2453,7 @@ extern loff_t noop_llseek(struct file *file, loff_t offset, int origin); extern loff_t no_llseek(struct file *file, loff_t offset, int origin); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, - int origin, loff_t maxsize); + int origin, loff_t maxsize, loff_t eof); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); @@ -2560,7 +2575,7 @@ extern int simple_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); -extern struct dentry *simple_lookup(struct inode *, struct dentry *, struct nameidata *); +extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); extern const struct file_operations simple_dir_operations; extern const struct inode_operations simple_dir_inode_operations; diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 176a939d1547..af961d6f7ab1 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -65,7 +65,7 @@ struct trace_iterator { void *private; int cpu_file; struct mutex mutex; - struct ring_buffer_iter *buffer_iter[NR_CPUS]; + struct ring_buffer_iter **buffer_iter; unsigned long iter_flags; /* trace_seq for __print_flags() and __print_symbolic() etc. */ @@ -207,6 +207,9 @@ struct ftrace_event_call { * bit 1: enabled * bit 2: filter_active * bit 3: enabled cmd record + * bit 4: allow trace by non root (cap any) + * bit 5: failed to apply filter + * bit 6: ftrace internal event (do not enable) * * Changes to flags must hold the event_mutex. * diff --git a/include/linux/gpio.h b/include/linux/gpio.h index f07fc2d08159..2e31e8b3a190 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -22,8 +22,8 @@ /* Gpio pin is open source */ #define GPIOF_OPEN_SOURCE (1 << 3) -#define GPIOF_EXPORT (1 << 2) -#define GPIOF_EXPORT_CHANGEABLE (1 << 3) +#define GPIOF_EXPORT (1 << 4) +#define GPIOF_EXPORT_CHANGEABLE (1 << 5) #define GPIOF_EXPORT_DIR_FIXED (GPIOF_EXPORT) #define GPIOF_EXPORT_DIR_CHANGEABLE (GPIOF_EXPORT | GPIOF_EXPORT_CHANGEABLE) diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index fd0dc30c9f15..cc07d2777bbe 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -165,6 +165,7 @@ enum hrtimer_base_type { * @lock: lock protecting the base and associated clock bases * and timers * @active_bases: Bitfield to mark bases with active timers + * @clock_was_set: Indicates that clock was set from irq context. * @expires_next: absolute time of the next event which was scheduled * via clock_set_next_event() * @hres_active: State of high resolution mode @@ -177,7 +178,8 @@ enum hrtimer_base_type { */ struct hrtimer_cpu_base { raw_spinlock_t lock; - unsigned long active_bases; + unsigned int active_bases; + unsigned int clock_was_set; #ifdef CONFIG_HIGH_RES_TIMERS ktime_t expires_next; int hres_active; @@ -286,6 +288,8 @@ extern void hrtimer_peek_ahead_timers(void); # define MONOTONIC_RES_NSEC HIGH_RES_NSEC # define KTIME_MONOTONIC_RES KTIME_HIGH_RES +extern void clock_was_set_delayed(void); + #else # define MONOTONIC_RES_NSEC LOW_RES_NSEC @@ -306,6 +310,9 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer) { return 0; } + +static inline void clock_was_set_delayed(void) { } + #endif extern void clock_was_set(void); @@ -320,6 +327,7 @@ extern ktime_t ktime_get(void); extern ktime_t ktime_get_real(void); extern ktime_t ktime_get_boottime(void); extern ktime_t ktime_get_monotonic_offset(void); +extern ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot); DECLARE_PER_CPU(struct tick_device, tick_cpu_device); diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 9e65eff6af3b..8a7476186990 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -168,8 +168,8 @@ extern struct cred init_cred; .children = LIST_HEAD_INIT(tsk.children), \ .sibling = LIST_HEAD_INIT(tsk.sibling), \ .group_leader = &tsk, \ - RCU_INIT_POINTER(.real_cred, &init_cred), \ - RCU_INIT_POINTER(.cred, &init_cred), \ + RCU_POINTER_INITIALIZER(real_cred, &init_cred), \ + RCU_POINTER_INITIALIZER(cred, &init_cred), \ .comm = INIT_TASK_COMM, \ .thread = INIT_THREAD, \ .fs = &init_fs, \ diff --git a/include/linux/input.h b/include/linux/input.h index a81671453575..2740d080ec6b 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -116,6 +116,7 @@ struct input_keymap_entry { /** * EVIOCGMTSLOTS(len) - get MT slot values + * @len: size of the data buffer in bytes * * The ioctl buffer argument should be binary equivalent to * diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index e6ca56de9936..78e2ada50cd5 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -308,6 +308,8 @@ enum { struct intel_iommu { void __iomem *reg; /* Pointer to hardware regs, virtual addr */ + u64 reg_phys; /* physical address of hw register set */ + u64 reg_size; /* size of hw register set */ u64 cap; u64 ecap; u32 gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */ diff --git a/include/linux/irq.h b/include/linux/irq.h index a5261e3d2e3c..553fb66da130 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -150,9 +150,7 @@ struct irq_data { void *handler_data; void *chip_data; struct msi_desc *msi_desc; -#ifdef CONFIG_SMP cpumask_var_t affinity; -#endif }; /* diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index c513a40510f5..0976fc46d1e0 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -42,8 +42,7 @@ * allowed. * * Not initializing the key (static data is initialized to 0s anyway) is the - * same as using STATIC_KEY_INIT_FALSE and static_key_false() is - * equivalent with static_branch(). + * same as using STATIC_KEY_INIT_FALSE. * */ @@ -107,12 +106,6 @@ static __always_inline bool static_key_true(struct static_key *key) return !static_key_false(key); } -/* Deprecated. Please use 'static_key_false() instead. */ -static __always_inline bool static_branch(struct static_key *key) -{ - return arch_static_branch(key); -} - extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; @@ -166,14 +159,6 @@ static __always_inline bool static_key_true(struct static_key *key) return false; } -/* Deprecated. Please use 'static_key_false() instead. */ -static __always_inline bool static_branch(struct static_key *key) -{ - if (unlikely(atomic_read(&key->enabled)) > 0) - return true; - return false; -} - static inline void static_key_slow_inc(struct static_key *key) { atomic_inc(&key->enabled); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e07f5e0c5df4..604382143bcf 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -377,7 +377,6 @@ extern enum system_states { SYSTEM_HALT, SYSTEM_POWER_OFF, SYSTEM_RESTART, - SYSTEM_SUSPEND_DISK, } system_state; #define TAINT_PROPRIETARY_MODULE 0 diff --git a/include/linux/key.h b/include/linux/key.h index 4cd22ed627ef..cef3b315ba7c 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -303,7 +303,9 @@ static inline bool key_is_instantiated(const struct key *key) rwsem_is_locked(&((struct key *)(KEY))->sem))) #define rcu_assign_keypointer(KEY, PAYLOAD) \ - (rcu_assign_pointer((KEY)->payload.rcudata, PAYLOAD)) +do { \ + rcu_assign_pointer((KEY)->payload.rcudata, (PAYLOAD)); \ +} while (0) #ifdef CONFIG_SYSCTL extern ctl_table key_sysctls[]; diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index d6bd50110ec2..2e7a1e032c71 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -55,12 +55,17 @@ struct kmsg_dumper { #ifdef CONFIG_PRINTK void kmsg_dump(enum kmsg_dump_reason reason); +bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len); + bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, char *line, size_t size, size_t *len); bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, char *buf, size_t size, size_t *len); +void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper); + void kmsg_dump_rewind(struct kmsg_dumper *dumper); int kmsg_dump_register(struct kmsg_dumper *dumper); @@ -71,6 +76,13 @@ static inline void kmsg_dump(enum kmsg_dump_reason reason) { } +static inline bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, + bool syslog, const char *line, + size_t size, size_t *len) +{ + return false; +} + static inline bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, const char *line, size_t size, size_t *len) { @@ -83,6 +95,10 @@ static inline bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, return false; } +static inline void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper) +{ +} + static inline void kmsg_dump_rewind(struct kmsg_dumper *dumper) { } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c4464356b35b..96c158a37d3e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -815,7 +815,7 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {} #ifdef CONFIG_HAVE_KVM_EVENTFD void kvm_eventfd_init(struct kvm *kvm); -int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags); +int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args); void kvm_irqfd_release(struct kvm *kvm); void kvm_irq_routing_update(struct kvm *, struct kvm_irq_routing_table *); int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args); @@ -824,7 +824,7 @@ int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args); static inline void kvm_eventfd_init(struct kvm *kvm) {} -static inline int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags) +static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) { return -EINVAL; } diff --git a/include/linux/memblock.h b/include/linux/memblock.h index a6bb10235148..19dc455b4f3d 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -50,9 +50,7 @@ phys_addr_t memblock_find_in_range_node(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid); phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align); -int memblock_free_reserved_regions(void); -int memblock_reserve_reserved_regions(void); - +phys_addr_t get_allocated_memblock_reserved_regions_info(phys_addr_t *addr); void memblock_allow_resize(void); int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); int memblock_add(phys_addr_t base, phys_addr_t size); diff --git a/include/linux/mfd/s5m87xx/s5m-core.h b/include/linux/mfd/s5m87xx/s5m-core.h index 21603b42f22f..0b2e0ed309f5 100644 --- a/include/linux/mfd/s5m87xx/s5m-core.h +++ b/include/linux/mfd/s5m87xx/s5m-core.h @@ -347,6 +347,7 @@ struct s5m_platform_data { bool buck_voltage_lock; int buck_gpios[3]; + int buck_ds[3]; int buck2_voltage[8]; bool buck2_gpiodvs; int buck3_voltage[8]; @@ -369,6 +370,10 @@ struct s5m_platform_data { bool buck2_ramp_enable; bool buck3_ramp_enable; bool buck4_ramp_enable; + + int buck2_init; + int buck3_init; + int buck4_init; }; #endif /* __LINUX_MFD_S5M_CORE_H */ diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index f5171dbf8850..d83af39815ab 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -101,6 +101,7 @@ struct tmio_mmc_host; struct tmio_mmc_data { unsigned int hclk; unsigned long capabilities; + unsigned long capabilities2; unsigned long flags; u32 ocr_mask; /* available voltages */ struct tmio_mmc_dma *dma; @@ -110,6 +111,9 @@ struct tmio_mmc_data { void (*set_clk_div)(struct platform_device *host, int state); int (*get_cd)(struct platform_device *host); int (*write16_hook)(struct tmio_mmc_host *host, int addr); + /* clock management callbacks */ + int (*clk_enable)(struct platform_device *pdev, unsigned int *f); + void (*clk_disable)(struct platform_device *pdev); }; /* diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h index e030ef9a64ee..12c06870829a 100644 --- a/include/linux/mfd/tps65217.h +++ b/include/linux/mfd/tps65217.h @@ -217,7 +217,8 @@ enum tps65217_regulator_id { * Board data may be used to initialize regulator. */ struct tps65217_board { - struct regulator_init_data *tps65217_init_data; + struct regulator_init_data *tps65217_init_data[TPS65217_NUM_REGULATOR]; + struct device_node *of_node[TPS65217_NUM_REGULATOR]; }; /** @@ -227,11 +228,6 @@ struct tps65217_board { * @max_uV: minimum micro volts * @vsel_to_uv: Function pointer to get voltage from selector * @uv_to_vsel: Function pointer to get selector from voltage - * @table: Table for non-uniform voltage step-size - * @table_len: Length of the voltage table - * @enable_mask: Regulator enable mask bits - * @set_vout_reg: Regulator output voltage set register - * @set_vout_mask: Regulator output voltage set mask * * This data is used to check the regualtor voltage limits while setting. */ @@ -241,11 +237,6 @@ struct tps_info { int max_uV; int (*vsel_to_uv)(unsigned int vsel); int (*uv_to_vsel)(int uV, unsigned int *vsel); - const int *table; - unsigned int table_len; - unsigned int enable_mask; - unsigned int set_vout_reg; - unsigned int set_vout_mask; }; /** diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h index dd8dc0a6c462..6c4c478e21a4 100644 --- a/include/linux/mfd/tps65910.h +++ b/include/linux/mfd/tps65910.h @@ -880,4 +880,10 @@ static inline int tps65910_reg_clear_bits(struct tps65910 *tps65910, u8 reg, return regmap_update_bits(tps65910->regmap, reg, mask, 0); } +static inline int tps65910_reg_update_bits(struct tps65910 *tps65910, u8 reg, + u8 mask, u8 val) +{ + return regmap_update_bits(tps65910->regmap, reg, mask, val); +} + #endif /* __LINUX_MFD_TPS65910_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index b36d08ce5c57..f9f279cf5b1b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1591,6 +1591,7 @@ void vmemmap_populate_print_last(void); enum mf_flags { MF_COUNT_INCREASED = 1 << 0, MF_ACTION_REQUIRED = 1 << 1, + MF_MUST_KILL = 1 << 2, }; extern int memory_failure(unsigned long pfn, int trapno, int flags); extern void memory_failure_queue(unsigned long pfn, int trapno, int flags); diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index d76513b5b263..111aca5e97f3 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -149,6 +149,7 @@ struct sd_switch_caps { #define SD_SET_CURRENT_LIMIT_400 1 #define SD_SET_CURRENT_LIMIT_600 2 #define SD_SET_CURRENT_LIMIT_800 3 +#define SD_SET_CURRENT_NO_CHANGE (-1) #define SD_MAX_CURRENT_200 (1 << SD_SET_CURRENT_LIMIT_200) #define SD_MAX_CURRENT_400 (1 << SD_SET_CURRENT_LIMIT_400) diff --git a/include/linux/mmc/cd-gpio.h b/include/linux/mmc/cd-gpio.h deleted file mode 100644 index cefaba038ccb..000000000000 --- a/include/linux/mmc/cd-gpio.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * Generic GPIO card-detect helper header - * - * Copyright (C) 2011, Guennadi Liakhovetski <g.liakhovetski@gmx.de> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef MMC_CD_GPIO_H -#define MMC_CD_GPIO_H - -struct mmc_host; -int mmc_cd_gpio_request(struct mmc_host *host, unsigned int gpio); -void mmc_cd_gpio_free(struct mmc_host *host); - -#endif diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 0707d228d7f1..f578a71d82a6 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -11,6 +11,7 @@ #define LINUX_MMC_HOST_H #include <linux/leds.h> +#include <linux/mutex.h> #include <linux/sched.h> #include <linux/device.h> #include <linux/fault-inject.h> @@ -150,11 +151,31 @@ struct mmc_async_req { int (*err_check) (struct mmc_card *, struct mmc_async_req *); }; -struct mmc_hotplug { - unsigned int irq; +/** + * struct mmc_slot - MMC slot functions + * + * @cd_irq: MMC/SD-card slot hotplug detection IRQ or -EINVAL + * @lock: protect the @handler_priv pointer + * @handler_priv: MMC/SD-card slot context + * + * Some MMC/SD host controllers implement slot-functions like card and + * write-protect detection natively. However, a large number of controllers + * leave these functions to the CPU. This struct provides a hook to attach + * such slot-function drivers. + */ +struct mmc_slot { + int cd_irq; + struct mutex lock; void *handler_priv; }; +struct regulator; + +struct mmc_supply { + struct regulator *vmmc; /* Card power supply */ + struct regulator *vqmmc; /* Optional Vccq supply */ +}; + struct mmc_host { struct device *parent; struct device class_dev; @@ -168,6 +189,9 @@ struct mmc_host { u32 ocr_avail_sd; /* SD-specific OCR */ u32 ocr_avail_mmc; /* MMC-specific OCR */ struct notifier_block pm_notify; + u32 max_current_330; + u32 max_current_300; + u32 max_current_180; #define MMC_VDD_165_195 0x00000080 /* VDD voltage 1.65 - 1.95 */ #define MMC_VDD_20_21 0x00000100 /* VDD voltage 2.0 ~ 2.1 */ @@ -211,16 +235,9 @@ struct mmc_host { #define MMC_CAP_UHS_SDR50 (1 << 17) /* Host supports UHS SDR50 mode */ #define MMC_CAP_UHS_SDR104 (1 << 18) /* Host supports UHS SDR104 mode */ #define MMC_CAP_UHS_DDR50 (1 << 19) /* Host supports UHS DDR50 mode */ -#define MMC_CAP_SET_XPC_330 (1 << 20) /* Host supports >150mA current at 3.3V */ -#define MMC_CAP_SET_XPC_300 (1 << 21) /* Host supports >150mA current at 3.0V */ -#define MMC_CAP_SET_XPC_180 (1 << 22) /* Host supports >150mA current at 1.8V */ #define MMC_CAP_DRIVER_TYPE_A (1 << 23) /* Host supports Driver Type A */ #define MMC_CAP_DRIVER_TYPE_C (1 << 24) /* Host supports Driver Type C */ #define MMC_CAP_DRIVER_TYPE_D (1 << 25) /* Host supports Driver Type D */ -#define MMC_CAP_MAX_CURRENT_200 (1 << 26) /* Host max current limit is 200mA */ -#define MMC_CAP_MAX_CURRENT_400 (1 << 27) /* Host max current limit is 400mA */ -#define MMC_CAP_MAX_CURRENT_600 (1 << 28) /* Host max current limit is 600mA */ -#define MMC_CAP_MAX_CURRENT_800 (1 << 29) /* Host max current limit is 800mA */ #define MMC_CAP_CMD23 (1 << 30) /* CMD23 supported. */ #define MMC_CAP_HW_RESET (1 << 31) /* Hardware reset */ @@ -238,6 +255,8 @@ struct mmc_host { #define MMC_CAP2_BROKEN_VOLTAGE (1 << 7) /* Use the broken voltage */ #define MMC_CAP2_DETECT_ON_ERR (1 << 8) /* On I/O err check card removal */ #define MMC_CAP2_HC_ERASE_SZ (1 << 9) /* High-capacity erase size */ +#define MMC_CAP2_CD_ACTIVE_HIGH (1 << 10) /* Card-detect signal active high */ +#define MMC_CAP2_RO_ACTIVE_HIGH (1 << 11) /* Write-protect signal active high */ mmc_pm_flag_t pm_caps; /* supported pm features */ unsigned int power_notify_type; @@ -290,7 +309,7 @@ struct mmc_host { struct delayed_work detect; int detect_change; /* card detect flag */ - struct mmc_hotplug hotplug; + struct mmc_slot slot; const struct mmc_bus_ops *bus_ops; /* current bus driver */ unsigned int bus_refs; /* reference counter */ @@ -309,6 +328,7 @@ struct mmc_host { #ifdef CONFIG_REGULATOR bool regulator_enabled; /* regulator state */ #endif + struct mmc_supply supply; struct dentry *debugfs_root; @@ -357,13 +377,12 @@ static inline void mmc_signal_sdio_irq(struct mmc_host *host) wake_up_process(host->sdio_irq_thread); } -struct regulator; - #ifdef CONFIG_REGULATOR int mmc_regulator_get_ocrmask(struct regulator *supply); int mmc_regulator_set_ocr(struct mmc_host *mmc, struct regulator *supply, unsigned short vdd_bit); +int mmc_regulator_get_supply(struct mmc_host *mmc); #else static inline int mmc_regulator_get_ocrmask(struct regulator *supply) { @@ -376,6 +395,11 @@ static inline int mmc_regulator_set_ocr(struct mmc_host *mmc, { return 0; } + +static inline int mmc_regulator_get_supply(struct mmc_host *mmc) +{ + return 0; +} #endif int mmc_card_awake(struct mmc_host *host); diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h index e9051e1cb1ce..ac83b105bedd 100644 --- a/include/linux/mmc/sdhci.h +++ b/include/linux/mmc/sdhci.h @@ -122,6 +122,7 @@ struct sdhci_host { #define SDHCI_PV_ENABLED (1<<8) /* Preset value enabled */ #define SDHCI_SDIO_IRQ_ENABLED (1<<9) /* SDIO irq enabled */ #define SDHCI_HS200_NEEDS_TUNING (1<<10) /* HS200 needs tuning */ +#define SDHCI_USING_RETUNING_TIMER (1<<11) /* Host is using a retuning timer for the card */ unsigned int version; /* SDHCI spec. version */ @@ -155,7 +156,8 @@ struct sdhci_host { struct timer_list timer; /* Timer for timeouts */ - unsigned int caps; /* Alternative capabilities */ + unsigned int caps; /* Alternative CAPABILITY_0 */ + unsigned int caps1; /* Alternative CAPABILITY_1 */ unsigned int ocr_avail_sdio; /* OCR bit masks */ unsigned int ocr_avail_sd; diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h index 05f0e3db1c12..c2f73cbb4d5c 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/mmc/sh_mmcif.h @@ -44,6 +44,8 @@ struct sh_mmcif_plat_data { struct sh_mmcif_dma *dma; /* Deprecated. Instead */ unsigned int slave_id_tx; /* use embedded slave_id_[tr]x */ unsigned int slave_id_rx; + bool use_cd_gpio : 1; + unsigned int cd_gpio; u8 sup_pclk; /* 1 :SH7757, 0: SH7724/SH7372 */ unsigned long caps; u32 ocr; diff --git a/include/linux/mmc/sh_mobile_sdhi.h b/include/linux/mmc/sh_mobile_sdhi.h index e94e620aeddc..b65679ffa880 100644 --- a/include/linux/mmc/sh_mobile_sdhi.h +++ b/include/linux/mmc/sh_mobile_sdhi.h @@ -23,6 +23,7 @@ struct sh_mobile_sdhi_info { int dma_slave_rx; unsigned long tmio_flags; unsigned long tmio_caps; + unsigned long tmio_caps2; u32 tmio_ocr_mask; /* available MMC voltages */ unsigned int cd_gpio; struct tmio_mmc_data *pdata; diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h new file mode 100644 index 000000000000..7d88d27bfafa --- /dev/null +++ b/include/linux/mmc/slot-gpio.h @@ -0,0 +1,24 @@ +/* + * Generic GPIO card-detect helper header + * + * Copyright (C) 2011, Guennadi Liakhovetski <g.liakhovetski@gmx.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef MMC_SLOT_GPIO_H +#define MMC_SLOT_GPIO_H + +struct mmc_host; + +int mmc_gpio_get_ro(struct mmc_host *host); +int mmc_gpio_request_ro(struct mmc_host *host, unsigned int gpio); +void mmc_gpio_free_ro(struct mmc_host *host); + +int mmc_gpio_get_cd(struct mmc_host *host); +int mmc_gpio_request_cd(struct mmc_host *host, unsigned int gpio); +void mmc_gpio_free_cd(struct mmc_host *host); + +#endif diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2427706f78b4..68c569fcbb66 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -694,7 +694,7 @@ typedef struct pglist_data { range, including holes */ int node_id; wait_queue_head_t kswapd_wait; - struct task_struct *kswapd; + struct task_struct *kswapd; /* Protected by lock_memory_hotplug() */ int kswapd_max_order; enum zone_type classzone_idx; } pg_data_t; diff --git a/include/linux/namei.h b/include/linux/namei.h index ffc02135c483..d2ef8b34b967 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -7,12 +7,6 @@ struct vfsmount; -struct open_intent { - int flags; - int create_mode; - struct file *file; -}; - enum { MAX_NESTED_LINKS = 8 }; struct nameidata { @@ -25,11 +19,6 @@ struct nameidata { int last_type; unsigned depth; char *saved_names[MAX_NESTED_LINKS + 1]; - - /* Intent data */ - union { - struct open_intent open; - } intent; }; /* @@ -78,13 +67,10 @@ extern int kern_path(const char *, unsigned, struct path *); extern struct dentry *kern_path_create(int, const char *, struct path *, int); extern struct dentry *user_path_create(int, const char __user *, struct path *, int); -extern int kern_path_parent(const char *, struct nameidata *); +extern struct dentry *kern_path_locked(const char *, struct path *); extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); -extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry, - int (*open)(struct inode *, struct file *)); - extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern int follow_down_one(struct path *); @@ -94,6 +80,8 @@ extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); +extern void nd_jump_link(struct nameidata *nd, struct path *path); + static inline void nd_set_link(struct nameidata *nd, char *path) { nd->saved_names[nd->depth] = path; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 8aadd90b808a..d3b7c18b18f4 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1374,7 +1374,7 @@ struct nfs_rpc_ops { int (*readlink)(struct inode *, struct page *, unsigned int, unsigned int); int (*create) (struct inode *, struct dentry *, - struct iattr *, int, struct nfs_open_context *); + struct iattr *, int); int (*remove) (struct inode *, struct qstr *); void (*unlink_setup) (struct rpc_message *, struct inode *dir); void (*unlink_rpc_prepare) (struct rpc_task *, struct nfs_unlinkdata *); diff --git a/include/linux/pci.h b/include/linux/pci.h index fefb4e19bf6a..d8c379dba6ad 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -176,8 +176,6 @@ enum pci_dev_flags { PCI_DEV_FLAGS_NO_D3 = (__force pci_dev_flags_t) 2, /* Provide indication device is assigned by a Virtual Machine Manager */ PCI_DEV_FLAGS_ASSIGNED = (__force pci_dev_flags_t) 4, - /* Device causes system crash if in D3 during S3 sleep */ - PCI_DEV_FLAGS_NO_D3_DURING_SLEEP = (__force pci_dev_flags_t) 8, }; enum pci_irq_reroute_variant { diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index ab741b0d0074..fc3526077348 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -517,6 +517,7 @@ #define PCI_DEVICE_ID_AMD_11H_NB_DRAM 0x1302 #define PCI_DEVICE_ID_AMD_11H_NB_MISC 0x1303 #define PCI_DEVICE_ID_AMD_11H_NB_LINK 0x1304 +#define PCI_DEVICE_ID_AMD_15H_M10H_F3 0x1403 #define PCI_DEVICE_ID_AMD_15H_NB_F0 0x1600 #define PCI_DEVICE_ID_AMD_15H_NB_F1 0x1601 #define PCI_DEVICE_ID_AMD_15H_NB_F2 0x1602 @@ -2755,6 +2756,17 @@ #define PCI_DEVICE_ID_INTEL_IOAT_SNB7 0x3c27 #define PCI_DEVICE_ID_INTEL_IOAT_SNB8 0x3c2e #define PCI_DEVICE_ID_INTEL_IOAT_SNB9 0x3c2f +#define PCI_DEVICE_ID_INTEL_UNC_HA 0x3c46 +#define PCI_DEVICE_ID_INTEL_UNC_IMC0 0x3cb0 +#define PCI_DEVICE_ID_INTEL_UNC_IMC1 0x3cb1 +#define PCI_DEVICE_ID_INTEL_UNC_IMC2 0x3cb4 +#define PCI_DEVICE_ID_INTEL_UNC_IMC3 0x3cb5 +#define PCI_DEVICE_ID_INTEL_UNC_QPI0 0x3c41 +#define PCI_DEVICE_ID_INTEL_UNC_QPI1 0x3c42 +#define PCI_DEVICE_ID_INTEL_UNC_R2PCIE 0x3c43 +#define PCI_DEVICE_ID_INTEL_UNC_R3QPI0 0x3c44 +#define PCI_DEVICE_ID_INTEL_UNC_R3QPI1 0x3c45 +#define PCI_DEVICE_ID_INTEL_JAKETOWN_UBOX 0x3ce0 #define PCI_DEVICE_ID_INTEL_IOAT_SNB 0x402f #define PCI_DEVICE_ID_INTEL_5100_16 0x65f0 #define PCI_DEVICE_ID_INTEL_5100_21 0x65f5 diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 45db49f64bb4..76c5c8b724a7 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -677,6 +677,7 @@ struct hw_perf_event { u64 last_tag; unsigned long config_base; unsigned long event_base; + int event_base_rdpmc; int idx; int last_cpu; @@ -1106,6 +1107,8 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, struct task_struct *task, perf_overflow_handler_t callback, void *context); +extern void perf_pmu_migrate_context(struct pmu *pmu, + int src_cpu, int dst_cpu); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 30f794eb3826..a7d6172922d4 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -15,6 +15,7 @@ #include <linux/err.h> #include <linux/of.h> #include <linux/notifier.h> +#include <linux/cpuidle.h> enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ @@ -45,6 +46,11 @@ struct gpd_dev_ops { bool (*active_wakeup)(struct device *dev); }; +struct gpd_cpu_data { + unsigned int saved_exit_latency; + struct cpuidle_state *idle_state; +}; + struct generic_pm_domain { struct dev_pm_domain domain; /* PM domain operations */ struct list_head gpd_list_node; /* Node in the global PM domains list */ @@ -75,6 +81,7 @@ struct generic_pm_domain { bool max_off_time_changed; bool cached_power_down_ok; struct device_node *of_node; /* Node in device tree */ + struct gpd_cpu_data *cpu_data; }; static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd) @@ -105,6 +112,7 @@ struct generic_pm_domain_data { struct gpd_timing_data td; struct notifier_block nb; struct mutex lock; + unsigned int refcount; bool need_restore; bool always_on; }; @@ -155,6 +163,8 @@ extern int pm_genpd_add_callbacks(struct device *dev, struct gpd_dev_ops *ops, struct gpd_timing_data *td); extern int __pm_genpd_remove_callbacks(struct device *dev, bool clear_td); +extern int genpd_attach_cpuidle(struct generic_pm_domain *genpd, int state); +extern int genpd_detach_cpuidle(struct generic_pm_domain *genpd); extern void pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off); @@ -211,6 +221,14 @@ static inline int __pm_genpd_remove_callbacks(struct device *dev, bool clear_td) { return -ENOSYS; } +static inline int genpd_attach_cpuidle(struct generic_pm_domain *genpd, int st) +{ + return -ENOSYS; +} +static inline int genpd_detach_cpuidle(struct generic_pm_domain *genpd) +{ + return -ENOSYS; +} static inline void pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off) { diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 233149cb19f4..9924ea1f22e0 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -66,7 +66,7 @@ enum pm_qos_req_action { static inline int dev_pm_qos_request_active(struct dev_pm_qos_request *req) { - return req->dev != 0; + return req->dev != NULL; } int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node, diff --git a/include/linux/prctl.h b/include/linux/prctl.h index 3988012255dc..289760f424aa 100644 --- a/include/linux/prctl.h +++ b/include/linux/prctl.h @@ -141,6 +141,8 @@ * Changing LSM security domain is considered a new privilege. So, for example, * asking selinux for a specific new context (e.g. with runcon) will result * in execve returning -EPERM. + * + * See Documentation/prctl/no_new_privs.txt for more details. */ #define PR_SET_NO_NEW_PRIVS 38 #define PR_GET_NO_NEW_PRIVS 39 diff --git a/include/linux/quota.h b/include/linux/quota.h index c09fa042b5ea..524ede8a160a 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -333,7 +333,7 @@ struct quotactl_ops { int (*quota_on)(struct super_block *, int, int, struct path *); int (*quota_on_meta)(struct super_block *, int, int); int (*quota_off)(struct super_block *, int); - int (*quota_sync)(struct super_block *, int, int); + int (*quota_sync)(struct super_block *, int); int (*get_info)(struct super_block *, int, struct if_dqinfo *); int (*set_info)(struct super_block *, int, struct if_dqinfo *); int (*get_dqblk)(struct super_block *, int, qid_t, struct fs_disk_quota *); diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 17b977304a09..ec6b65feaaba 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -83,7 +83,8 @@ int dquot_quota_on(struct super_block *sb, int type, int format_id, int dquot_quota_on_mount(struct super_block *sb, char *qf_name, int format_id, int type); int dquot_quota_off(struct super_block *sb, int type); -int dquot_quota_sync(struct super_block *sb, int type, int wait); +int dquot_writeback_dquots(struct super_block *sb, int type); +int dquot_quota_sync(struct super_block *sb, int type); int dquot_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); int dquot_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); int dquot_get_dqblk(struct super_block *sb, int type, qid_t id, @@ -255,6 +256,11 @@ static inline int dquot_resume(struct super_block *sb, int type) #define dquot_file_open generic_file_open +static inline int dquot_writeback_dquots(struct super_block *sb, int type) +{ + return 0; +} + #endif /* CONFIG_QUOTA */ static inline int dquot_alloc_space_nodirty(struct inode *inode, qsize_t nr) diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 26d1a47591f1..115ead2b5155 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -147,6 +147,7 @@ extern void synchronize_sched(void); extern void __rcu_read_lock(void); extern void __rcu_read_unlock(void); +extern void rcu_read_unlock_special(struct task_struct *t); void synchronize_rcu(void); /* @@ -184,7 +185,6 @@ static inline int rcu_preempt_depth(void) /* Internal to kernel */ extern void rcu_sched_qs(int cpu); extern void rcu_bh_qs(int cpu); -extern void rcu_preempt_note_context_switch(void); extern void rcu_check_callbacks(int cpu, int user); struct notifier_block; extern void rcu_idle_enter(void); @@ -256,6 +256,10 @@ static inline void destroy_rcu_head_on_stack(struct rcu_head *head) } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP) +extern int rcu_is_cpu_idle(void); +#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP) */ + #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ @@ -267,15 +271,6 @@ static inline bool rcu_lockdep_current_cpu_online(void) #ifdef CONFIG_DEBUG_LOCK_ALLOC -#ifdef CONFIG_PROVE_RCU -extern int rcu_is_cpu_idle(void); -#else /* !CONFIG_PROVE_RCU */ -static inline int rcu_is_cpu_idle(void) -{ - return 0; -} -#endif /* else !CONFIG_PROVE_RCU */ - static inline void rcu_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 0, 2, 1, NULL, _THIS_IP_); @@ -432,8 +427,7 @@ extern int rcu_my_thread_group_empty(void); static inline void rcu_preempt_sleep_check(void) { rcu_lockdep_assert(!lock_is_held(&rcu_lock_map), - "Illegal context switch in RCU read-side " - "critical section"); + "Illegal context switch in RCU read-side critical section"); } #else /* #ifdef CONFIG_PROVE_RCU */ static inline void rcu_preempt_sleep_check(void) @@ -514,10 +508,10 @@ static inline void rcu_preempt_sleep_check(void) (_________p1); \ }) #define __rcu_assign_pointer(p, v, space) \ - ({ \ + do { \ smp_wmb(); \ (p) = (typeof(*v) __force space *)(v); \ - }) + } while (0) /** @@ -852,7 +846,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * * Assigns the specified value to the specified RCU-protected * pointer, ensuring that any concurrent RCU readers will see - * any prior initialization. Returns the value assigned. + * any prior initialization. * * Inserts memory barriers on architectures that require them * (which is most of them), and also prevents the compiler from @@ -904,25 +898,17 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * the reader-accessible portions of the linked structure. */ #define RCU_INIT_POINTER(p, v) \ - p = (typeof(*v) __force __rcu *)(v) - -static __always_inline bool __is_kfree_rcu_offset(unsigned long offset) -{ - return offset < 4096; -} - -static __always_inline -void __kfree_rcu(struct rcu_head *head, unsigned long offset) -{ - typedef void (*rcu_callback)(struct rcu_head *); - - BUILD_BUG_ON(!__builtin_constant_p(offset)); - - /* See the kfree_rcu() header comment. */ - BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); + do { \ + p = (typeof(*v) __force __rcu *)(v); \ + } while (0) - kfree_call_rcu(head, (rcu_callback)offset); -} +/** + * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer + * + * GCC-style initialization for an RCU-protected pointer in a structure field. + */ +#define RCU_POINTER_INITIALIZER(p, v) \ + .p = (typeof(*v) __force __rcu *)(v) /* * Does the specified offset indicate that the corresponding rcu_head @@ -936,7 +922,7 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset) #define __kfree_rcu(head, offset) \ do { \ BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \ - call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \ + kfree_call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \ } while (0) /** diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 854dc4c5c271..4e56a9c69a35 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -87,6 +87,10 @@ static inline void kfree_call_rcu(struct rcu_head *head, #ifdef CONFIG_TINY_RCU +static inline void rcu_preempt_note_context_switch(void) +{ +} + static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies) { *delta_jiffies = ULONG_MAX; @@ -95,6 +99,7 @@ static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies) #else /* #ifdef CONFIG_TINY_RCU */ +void rcu_preempt_note_context_switch(void); int rcu_preempt_needs_cpu(void); static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies) @@ -108,6 +113,7 @@ static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies) static inline void rcu_note_context_switch(int cpu) { rcu_sched_qs(cpu); + rcu_preempt_note_context_switch(); } /* diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 56af22ec9aba..7f7e00df3adf 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -14,12 +14,14 @@ */ #include <linux/list.h> +#include <linux/rbtree.h> struct module; struct device; struct i2c_client; struct spi_device; struct regmap; +struct regmap_range_cfg; /* An enum of all the supported cache types */ enum regcache_type { @@ -43,6 +45,14 @@ struct reg_default { #ifdef CONFIG_REGMAP +enum regmap_endian { + /* Unspecified -> 0 -> Backwards compatible default */ + REGMAP_ENDIAN_DEFAULT = 0, + REGMAP_ENDIAN_BIG, + REGMAP_ENDIAN_LITTLE, + REGMAP_ENDIAN_NATIVE, +}; + /** * Configuration for the register map of a device. * @@ -84,6 +94,15 @@ struct reg_default { * @reg_defaults_raw: Power on reset values for registers (for use with * register cache support). * @num_reg_defaults_raw: Number of elements in reg_defaults_raw. + * @reg_format_endian: Endianness for formatted register addresses. If this is + * DEFAULT, the @reg_format_endian_default value from the + * regmap bus is used. + * @val_format_endian: Endianness for formatted register values. If this is + * DEFAULT, the @reg_format_endian_default value from the + * regmap bus is used. + * + * @ranges: Array of configuration entries for virtual address ranges. + * @num_ranges: Number of range configuration entries. */ struct regmap_config { const char *name; @@ -109,6 +128,43 @@ struct regmap_config { u8 write_flag_mask; bool use_single_rw; + + enum regmap_endian reg_format_endian; + enum regmap_endian val_format_endian; + + const struct regmap_range_cfg *ranges; + unsigned int n_ranges; +}; + +/** + * Configuration for indirectly accessed or paged registers. + * Registers, mapped to this virtual range, are accessed in two steps: + * 1. page selector register update; + * 2. access through data window registers. + * + * @range_min: Address of the lowest register address in virtual range. + * @range_max: Address of the highest register in virtual range. + * + * @page_sel_reg: Register with selector field. + * @page_sel_mask: Bit shift for selector value. + * @page_sel_shift: Bit mask for selector value. + * + * @window_start: Address of first (lowest) register in data window. + * @window_len: Number of registers in data window. + */ +struct regmap_range_cfg { + /* Registers of virtual address range */ + unsigned int range_min; + unsigned int range_max; + + /* Page selector for indirect addressing */ + unsigned int selector_reg; + unsigned int selector_mask; + int selector_shift; + + /* Data window (per each page) */ + unsigned int window_start; + unsigned int window_len; }; typedef int (*regmap_hw_write)(void *context, const void *data, @@ -133,6 +189,12 @@ typedef void (*regmap_hw_free_context)(void *context); * data. * @read_flag_mask: Mask to be set in the top byte of the register when doing * a read. + * @reg_format_endian_default: Default endianness for formatted register + * addresses. Used when the regmap_config specifies DEFAULT. If this is + * DEFAULT, BIG is assumed. + * @val_format_endian_default: Default endianness for formatted register + * values. Used when the regmap_config specifies DEFAULT. If this is + * DEFAULT, BIG is assumed. */ struct regmap_bus { bool fast_io; @@ -141,6 +203,8 @@ struct regmap_bus { regmap_hw_read read; regmap_hw_free_context free_context; u8 read_flag_mask; + enum regmap_endian reg_format_endian_default; + enum regmap_endian val_format_endian_default; }; struct regmap *regmap_init(struct device *dev, @@ -219,6 +283,7 @@ struct regmap_irq { * @status_base: Base status register address. * @mask_base: Base mask register address. * @ack_base: Base ack address. If zero then the chip is clear on read. + * @wake_base: Base address for wake enables. If zero unsupported. * @irq_reg_stride: Stride to use for chips where registers are not contiguous. * * @num_regs: Number of registers in each control bank. @@ -232,6 +297,7 @@ struct regmap_irq_chip { unsigned int status_base; unsigned int mask_base; unsigned int ack_base; + unsigned int wake_base; unsigned int irq_reg_stride; int num_regs; @@ -243,7 +309,7 @@ struct regmap_irq_chip { struct regmap_irq_chip_data; int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, - int irq_base, struct regmap_irq_chip *chip, + int irq_base, const struct regmap_irq_chip *chip, struct regmap_irq_chip_data **data); void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *data); int regmap_irq_chip_get_base(struct regmap_irq_chip_data *data); @@ -361,7 +427,6 @@ static inline int regmap_register_patch(struct regmap *map, static inline struct regmap *dev_get_regmap(struct device *dev, const char *name) { - WARN_ONCE(1, "regmap API is disabled"); return NULL; } diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 4ed1b30ac5fc..da339fd8c755 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -291,6 +291,12 @@ static inline int regulator_set_voltage(struct regulator *regulator, static inline int regulator_get_voltage(struct regulator *regulator) { + return -EINVAL; +} + +static inline int regulator_is_supported_voltage(struct regulator *regulator, + int min_uV, int max_uV) +{ return 0; } diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index b0432cc2b169..bac4c871f3bd 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -32,6 +32,8 @@ enum regulator_status { REGULATOR_STATUS_NORMAL, REGULATOR_STATUS_IDLE, REGULATOR_STATUS_STANDBY, + /* in case that any other status doesn't apply */ + REGULATOR_STATUS_UNDEFINED, }; /** @@ -67,6 +69,8 @@ enum regulator_status { * * @enable_time: Time taken for the regulator voltage output voltage to * stabilise after being enabled, in microseconds. + * @set_ramp_delay: Set the ramp delay for the regulator. The driver should + * select ramp delay equal to or less than(closest) ramp_delay. * @set_voltage_time_sel: Time taken for the regulator voltage output voltage * to stabilise after being set to a new value, in microseconds. * The function provides the from and to voltage selector, the @@ -113,6 +117,7 @@ struct regulator_ops { /* Time taken to enable or set voltage on the regulator */ int (*enable_time) (struct regulator_dev *); + int (*set_ramp_delay) (struct regulator_dev *, int ramp_delay); int (*set_voltage_time_sel) (struct regulator_dev *, unsigned int old_selector, unsigned int new_selector); @@ -170,11 +175,15 @@ enum regulator_type { * * @min_uV: Voltage given by the lowest selector (if linear mapping) * @uV_step: Voltage increase with each selector (if linear mapping) + * @ramp_delay: Time to settle down after voltage change (unit: uV/us) + * @volt_table: Voltage mapping table (if table based mapping) * * @vsel_reg: Register for selector when using regulator_regmap_X_voltage_ * @vsel_mask: Mask for register bitfield used for selector * @enable_reg: Register for control when using regmap enable/disable ops * @enable_mask: Mask for control when using regmap enable/disable ops + * + * @enable_time: Time taken for initial enable of regulator (in uS). */ struct regulator_desc { const char *name; @@ -188,11 +197,16 @@ struct regulator_desc { unsigned int min_uV; unsigned int uV_step; + unsigned int ramp_delay; + + const unsigned int *volt_table; unsigned int vsel_reg; unsigned int vsel_mask; unsigned int enable_reg; unsigned int enable_mask; + + unsigned int enable_time; }; /** @@ -208,6 +222,9 @@ struct regulator_desc { * @of_node: OpenFirmware node to parse for device tree bindings (may be * NULL). * @regmap: regmap to use for core regmap helpers + * @ena_gpio: GPIO controlling regulator enable. + * @ena_gpio_invert: Sense for GPIO enable control. + * @ena_gpio_flags: Flags to use when calling gpio_request_one() */ struct regulator_config { struct device *dev; @@ -215,6 +232,10 @@ struct regulator_config { void *driver_data; struct device_node *of_node; struct regmap *regmap; + + int ena_gpio; + unsigned int ena_gpio_invert:1; + unsigned int ena_gpio_flags; }; /* @@ -253,6 +274,10 @@ struct regulator_dev { void *reg_data; /* regulator_dev data */ struct dentry *debugfs; + + int ena_gpio; + unsigned int ena_gpio_invert:1; + unsigned int ena_gpio_state:1; }; struct regulator_dev * @@ -271,6 +296,8 @@ int regulator_mode_to_status(unsigned int); int regulator_list_voltage_linear(struct regulator_dev *rdev, unsigned int selector); +int regulator_list_voltage_table(struct regulator_dev *rdev, + unsigned int selector); int regulator_map_voltage_linear(struct regulator_dev *rdev, int min_uV, int max_uV); int regulator_map_voltage_iterate(struct regulator_dev *rdev, @@ -280,6 +307,9 @@ int regulator_set_voltage_sel_regmap(struct regulator_dev *rdev, unsigned sel); int regulator_is_enabled_regmap(struct regulator_dev *rdev); int regulator_enable_regmap(struct regulator_dev *rdev); int regulator_disable_regmap(struct regulator_dev *rdev); +int regulator_set_voltage_time_sel(struct regulator_dev *rdev, + unsigned int old_selector, + unsigned int new_selector); void *regulator_get_init_drvdata(struct regulator_init_data *reg_init_data); diff --git a/include/linux/regulator/fixed.h b/include/linux/regulator/fixed.h index f83f7440b488..48918be649d4 100644 --- a/include/linux/regulator/fixed.h +++ b/include/linux/regulator/fixed.h @@ -22,6 +22,7 @@ struct regulator_init_data; /** * struct fixed_voltage_config - fixed_voltage_config structure * @supply_name: Name of the regulator supply + * @input_supply: Name of the input regulator supply * @microvolts: Output voltage of regulator * @gpio: GPIO to use for enable control * set to -EINVAL if not used @@ -46,6 +47,7 @@ struct regulator_init_data; */ struct fixed_voltage_config { const char *supply_name; + const char *input_supply; int microvolts; int gpio; unsigned startup_delay; @@ -58,14 +60,17 @@ struct fixed_voltage_config { struct regulator_consumer_supply; #if IS_ENABLED(CONFIG_REGULATOR) -struct platform_device *regulator_register_fixed(int id, - struct regulator_consumer_supply *supplies, int num_supplies); +struct platform_device *regulator_register_always_on(int id, const char *name, + struct regulator_consumer_supply *supplies, int num_supplies, int uv); #else -static inline struct platform_device *regulator_register_fixed(int id, - struct regulator_consumer_supply *supplies, int num_supplies) +static inline struct platform_device *regulator_register_always_on(int id, const char *name, + struct regulator_consumer_supply *supplies, int num_supplies, int uv) { return NULL; } #endif +#define regulator_register_fixed(id, s, ns) regulator_register_always_on(id, \ + "fixed-dummy", s, ns, 0) + #endif diff --git a/include/linux/regulator/lp872x.h b/include/linux/regulator/lp872x.h new file mode 100644 index 000000000000..132e05c46661 --- /dev/null +++ b/include/linux/regulator/lp872x.h @@ -0,0 +1,90 @@ +/* + * Copyright 2012 Texas Instruments + * + * Author: Milo(Woogyom) Kim <milo.kim@ti.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#ifndef __LP872X_REGULATOR_H__ +#define __LP872X_REGULATOR_H__ + +#include <linux/regulator/machine.h> +#include <linux/platform_device.h> +#include <linux/gpio.h> + +#define LP872X_MAX_REGULATORS 9 + +enum lp872x_regulator_id { + LP8720_ID_BASE, + LP8720_ID_LDO1 = LP8720_ID_BASE, + LP8720_ID_LDO2, + LP8720_ID_LDO3, + LP8720_ID_LDO4, + LP8720_ID_LDO5, + LP8720_ID_BUCK, + + LP8725_ID_BASE, + LP8725_ID_LDO1 = LP8725_ID_BASE, + LP8725_ID_LDO2, + LP8725_ID_LDO3, + LP8725_ID_LDO4, + LP8725_ID_LDO5, + LP8725_ID_LILO1, + LP8725_ID_LILO2, + LP8725_ID_BUCK1, + LP8725_ID_BUCK2, + + LP872X_ID_MAX, +}; + +enum lp872x_dvs_state { + DVS_LOW = GPIOF_OUT_INIT_LOW, + DVS_HIGH = GPIOF_OUT_INIT_HIGH, +}; + +enum lp872x_dvs_sel { + SEL_V1, + SEL_V2, +}; + +/** + * lp872x_dvs + * @gpio : gpio pin number for dvs control + * @vsel : dvs selector for buck v1 or buck v2 register + * @init_state : initial dvs pin state + */ +struct lp872x_dvs { + int gpio; + enum lp872x_dvs_sel vsel; + enum lp872x_dvs_state init_state; +}; + +/** + * lp872x_regdata + * @id : regulator id + * @init_data : init data for each regulator + */ +struct lp872x_regulator_data { + enum lp872x_regulator_id id; + struct regulator_init_data *init_data; +}; + +/** + * lp872x_platform_data + * @general_config : the value of LP872X_GENERAL_CFG register + * @update_config : if LP872X_GENERAL_CFG register is updated, set true + * @regulator_data : platform regulator id and init data + * @dvs : dvs data for buck voltage control + */ +struct lp872x_platform_data { + u8 general_config; + bool update_config; + struct lp872x_regulator_data regulator_data[LP872X_MAX_REGULATORS]; + struct lp872x_dvs *dvs; +}; + +#endif diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index b02108446be7..40dd0a394cfa 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -92,6 +92,7 @@ struct regulator_state { * mode. * @initial_state: Suspend state to set by default. * @initial_mode: Mode to set at startup. + * @ramp_delay: Time to settle down after voltage change (unit: uV/us) */ struct regulation_constraints { @@ -125,6 +126,8 @@ struct regulation_constraints { /* mode to set on startup */ unsigned int initial_mode; + unsigned int ramp_delay; + /* constraint flags */ unsigned always_on:1; /* regulator never off when system is on */ unsigned boot_on:1; /* bootloader/firmware enabled regulator */ diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index a8e50e44203c..82a673905edb 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -38,6 +38,8 @@ #include <linux/types.h> #include <linux/device.h> #include <linux/mod_devicetable.h> +#include <linux/kref.h> +#include <linux/mutex.h> /* The feature bitmap for virtio rpmsg */ #define VIRTIO_RPMSG_F_NS 0 /* RP supports name service notifications */ @@ -120,7 +122,9 @@ typedef void (*rpmsg_rx_cb_t)(struct rpmsg_channel *, void *, int, void *, u32); /** * struct rpmsg_endpoint - binds a local rpmsg address to its user * @rpdev: rpmsg channel device + * @refcount: when this drops to zero, the ept is deallocated * @cb: rx callback handler + * @cb_lock: must be taken before accessing/changing @cb * @addr: local rpmsg address * @priv: private data for the driver's use * @@ -140,7 +144,9 @@ typedef void (*rpmsg_rx_cb_t)(struct rpmsg_channel *, void *, int, void *, u32); */ struct rpmsg_endpoint { struct rpmsg_channel *rpdev; + struct kref refcount; rpmsg_rx_cb_t cb; + struct mutex cb_lock; u32 addr; void *priv; }; diff --git a/include/linux/sched.h b/include/linux/sched.h index 4059c0f33f07..1a2ebd39b800 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1405,7 +1405,7 @@ struct task_struct { int (*notifier)(void *priv); void *notifier_data; sigset_t *notifier_mask; - struct hlist_head task_works; + struct callback_head *task_works; struct audit_context *audit_context; #ifdef CONFIG_AUDITSYSCALL @@ -1546,7 +1546,6 @@ struct task_struct { unsigned long timer_slack_ns; unsigned long default_timer_slack_ns; - struct list_head *scm_work_list; #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack */ int curr_ret_stack; @@ -1581,7 +1580,6 @@ struct task_struct { #endif #ifdef CONFIG_UPROBES struct uprobe_task *utask; - int uprobe_srcu_id; #endif }; @@ -1871,22 +1869,12 @@ static inline void rcu_copy_process(struct task_struct *p) INIT_LIST_HEAD(&p->rcu_node_entry); } -static inline void rcu_switch_from(struct task_struct *prev) -{ - if (prev->rcu_read_lock_nesting != 0) - rcu_preempt_note_context_switch(); -} - #else static inline void rcu_copy_process(struct task_struct *p) { } -static inline void rcu_switch_from(struct task_struct *prev) -{ -} - #endif #ifdef CONFIG_SMP @@ -1909,6 +1897,14 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, } #endif +#ifdef CONFIG_NO_HZ +void calc_load_enter_idle(void); +void calc_load_exit_idle(void); +#else +static inline void calc_load_enter_idle(void) { } +static inline void calc_load_exit_idle(void) { } +#endif /* CONFIG_NO_HZ */ + #ifndef CONFIG_CPUMASK_OFFSTACK static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) { diff --git a/include/linux/smp.h b/include/linux/smp.h index 717fb746c9a8..dd6f06be3c9f 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -90,10 +90,6 @@ void kick_all_cpus_sync(void); void __init call_function_init(void); void generic_smp_call_function_single_interrupt(void); void generic_smp_call_function_interrupt(void); -void ipi_call_lock(void); -void ipi_call_unlock(void); -void ipi_call_lock_irq(void); -void ipi_call_unlock_irq(void); #else static inline void call_function_init(void) { } #endif @@ -181,7 +177,6 @@ static inline int up_smp_call_function(smp_call_func_t func, void *info) } while (0) static inline void smp_send_reschedule(int cpu) { } -#define num_booting_cpus() 1 #define smp_prepare_boot_cpu() do {} while (0) #define smp_call_function_many(mask, func, info, wait) \ (up_smp_call_function(func, info)) diff --git a/include/linux/splice.h b/include/linux/splice.h index 26e5b613deda..09a545a7dfa3 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -51,7 +51,8 @@ struct partial_page { struct splice_pipe_desc { struct page **pages; /* page map */ struct partial_page *partial; /* pages[] may not be contig */ - int nr_pages; /* number of pages in map */ + int nr_pages; /* number of populated pages in map */ + unsigned int nr_pages_max; /* pages[] & partial[] arrays size */ unsigned int flags; /* splice flags */ const struct pipe_buf_operations *ops;/* ops associated with output pipe */ void (*spd_release)(struct splice_pipe_desc *, unsigned int); @@ -85,9 +86,8 @@ extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *, /* * for dynamic pipe sizing */ -extern int splice_grow_spd(struct pipe_inode_info *, struct splice_pipe_desc *); -extern void splice_shrink_spd(struct pipe_inode_info *, - struct splice_pipe_desc *); +extern int splice_grow_spd(const struct pipe_inode_info *, struct splice_pipe_desc *); +extern void splice_shrink_spd(struct splice_pipe_desc *); extern void spd_release_page(struct splice_pipe_desc *, unsigned int); extern const struct pipe_buf_operations page_cache_pipe_buf_ops; diff --git a/include/linux/suspend.h b/include/linux/suspend.h index cd83059fb592..0c808d7fa579 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -408,6 +408,12 @@ static inline void unlock_system_sleep(void) {} #endif /* !CONFIG_PM_SLEEP */ +#ifdef CONFIG_PM_SLEEP_DEBUG +extern bool pm_print_times_enabled; +#else +#define pm_print_times_enabled (false) +#endif + #ifdef CONFIG_PM_AUTOSLEEP /* kernel/power/autosleep.c */ diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 294d5d5e90b1..fb46b03b1852 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -4,29 +4,21 @@ #include <linux/list.h> #include <linux/sched.h> -struct task_work; -typedef void (*task_work_func_t)(struct task_work *); - -struct task_work { - struct hlist_node hlist; - task_work_func_t func; - void *data; -}; +typedef void (*task_work_func_t)(struct callback_head *); static inline void -init_task_work(struct task_work *twork, task_work_func_t func, void *data) +init_task_work(struct callback_head *twork, task_work_func_t func) { twork->func = func; - twork->data = data; } -int task_work_add(struct task_struct *task, struct task_work *twork, bool); -struct task_work *task_work_cancel(struct task_struct *, task_work_func_t); +int task_work_add(struct task_struct *task, struct callback_head *twork, bool); +struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t); void task_work_run(void); static inline void exit_task_work(struct task_struct *task) { - if (unlikely(!hlist_empty(&task->task_works))) + if (unlikely(task->task_works)) task_work_run(); } diff --git a/include/linux/tick.h b/include/linux/tick.h index ab8be90b5cc9..f37fceb69b73 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -31,10 +31,10 @@ enum tick_nohz_mode { * struct tick_sched - sched tick emulation and no idle tick control/stats * @sched_timer: hrtimer to schedule the periodic tick in high * resolution mode - * @idle_tick: Store the last idle tick expiry time when the tick - * timer is modified for idle sleeps. This is necessary + * @last_tick: Store the last tick expiry time when the tick + * timer is modified for nohz sleeps. This is necessary * to resume the tick timer operation in the timeline - * when the CPU returns from idle + * when the CPU returns from nohz sleep. * @tick_stopped: Indicator that the idle tick has been stopped * @idle_jiffies: jiffies at the entry to idle for idle time accounting * @idle_calls: Total number of idle calls @@ -51,7 +51,7 @@ struct tick_sched { struct hrtimer sched_timer; unsigned long check_clocks; enum tick_nohz_mode nohz_mode; - ktime_t idle_tick; + ktime_t last_tick; int inidle; int tick_stopped; unsigned long idle_jiffies; diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 6a4d82bedb03..1e98b5530425 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -192,7 +192,7 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) * hlist_add_head(task->task_works); */ smp_mb__after_clear_bit(); - if (unlikely(!hlist_empty(¤t->task_works))) + if (unlikely(current->task_works)) task_work_run(); } diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index bd96ecd0e05c..802de56c41e8 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -153,7 +153,7 @@ static inline void tracepoint_synchronize_unregister(void) } \ static inline void trace_##name##_rcuidle(proto) \ { \ - if (static_branch(&__tracepoint_##name.key)) \ + if (static_key_false(&__tracepoint_##name.key)) \ __DO_TRACE(&__tracepoint_##name, \ TP_PROTO(data_proto), \ TP_ARGS(data_args), \ diff --git a/include/linux/types.h b/include/linux/types.h index 9c1bd539ea70..bf0dd7524b2a 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -246,14 +246,15 @@ struct ustat { }; /** - * struct rcu_head - callback structure for use with RCU + * struct callback_head - callback structure for use with RCU and task_work * @next: next update requests in a list * @func: actual update function to call after the grace period. */ -struct rcu_head { - struct rcu_head *next; - void (*func)(struct rcu_head *head); +struct callback_head { + struct callback_head *next; + void (*func)(struct callback_head *head); }; +#define rcu_head callback_head #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index d6146b4811c2..95374d1696a1 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1425,7 +1425,7 @@ static inline void ip_vs_notrack(struct sk_buff *skb) struct nf_conn *ct = nf_ct_get(skb, &ctinfo); if (!ct || !nf_ct_is_untracked(ct)) { - nf_reset(skb); + nf_conntrack_put(skb->nfct); skb->nfct = &nf_ct_untracked_get()->ct_general; skb->nfctinfo = IP_CT_NEW; nf_conntrack_get(skb->nfct); diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index a88fb6939387..e1ce1048fe5f 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -78,7 +78,7 @@ nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct) struct net *net = nf_ct_net(ct); struct nf_conntrack_ecache *e; - if (net->ct.nf_conntrack_event_cb == NULL) + if (!rcu_access_pointer(net->ct.nf_conntrack_event_cb)) return; e = nf_ct_ecache_find(ct); diff --git a/include/net/scm.h b/include/net/scm.h index d456f4c71a32..079d7887dac1 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -13,7 +13,6 @@ #define SCM_MAX_FD 253 struct scm_fp_list { - struct list_head list; short count; short max; struct file *fp[SCM_MAX_FD]; diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index e4652fe58958..fecdf31816f2 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -912,6 +912,9 @@ struct sctp_transport { /* Is this structure kfree()able? */ malloced:1; + /* Has this transport moved the ctsn since we last sacked */ + __u32 sack_generation; + struct flowi fl; /* This is the peer's IP address and port. */ @@ -1584,6 +1587,7 @@ struct sctp_association { */ __u8 sack_needed; /* Do we need to sack the peer? */ __u32 sack_cnt; + __u32 sack_generation; /* These are capabilities which our peer advertised. */ __u8 ecn_capable:1, /* Can peer do ECN? */ diff --git a/include/net/sctp/tsnmap.h b/include/net/sctp/tsnmap.h index e7728bc14ccf..2c5d2b4d5d1e 100644 --- a/include/net/sctp/tsnmap.h +++ b/include/net/sctp/tsnmap.h @@ -117,7 +117,8 @@ void sctp_tsnmap_free(struct sctp_tsnmap *map); int sctp_tsnmap_check(const struct sctp_tsnmap *, __u32 tsn); /* Mark this TSN as seen. */ -int sctp_tsnmap_mark(struct sctp_tsnmap *, __u32 tsn); +int sctp_tsnmap_mark(struct sctp_tsnmap *, __u32 tsn, + struct sctp_transport *trans); /* Mark this TSN and all lower as seen. */ void sctp_tsnmap_skip(struct sctp_tsnmap *map, __u32 tsn); diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index f4f1c96dca72..10ce74f589c5 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -163,6 +163,8 @@ enum ata_command_set { ATAPI_COMMAND_SET = 1, }; +#define ATA_RESP_FIS_SIZE 24 + struct sata_device { enum ata_command_set command_set; struct smp_resp rps_resp; /* report_phy_sata_resp */ @@ -171,7 +173,7 @@ struct sata_device { struct ata_port *ap; struct ata_host ata_host; - struct ata_taskfile tf; + u8 fis[ATA_RESP_FIS_SIZE]; }; enum { @@ -537,7 +539,7 @@ enum exec_status { */ struct ata_task_resp { u16 frame_len; - u8 ending_fis[24]; /* dev to host or data-in */ + u8 ending_fis[ATA_RESP_FIS_SIZE]; /* dev to host or data-in */ }; #define SAS_STATUS_BUF_SIZE 96 diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 1e1198546c72..ac06cc595890 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -134,10 +134,16 @@ struct scsi_cmnd { static inline struct scsi_driver *scsi_cmd_to_driver(struct scsi_cmnd *cmd) { + struct scsi_driver **sdp; + if (!cmd->request->rq_disk) return NULL; - return *(struct scsi_driver **)cmd->request->rq_disk->private_data; + sdp = (struct scsi_driver **)cmd->request->rq_disk->private_data; + if (!sdp) + return NULL; + + return *sdp; } extern struct scsi_cmnd *scsi_get_command(struct scsi_device *, gfp_t); diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 2d7db85e93ae..f1405d335a96 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -24,10 +24,8 @@ struct se_subsystem_api { struct se_subsystem_dev *, void *); void (*free_device)(void *); int (*transport_complete)(struct se_cmd *cmd, struct scatterlist *); - int (*execute_cmd)(struct se_cmd *, struct scatterlist *, u32, - enum dma_data_direction); - int (*do_discard)(struct se_device *, sector_t, u32); - void (*do_sync_cache)(struct se_cmd *); + + int (*parse_cdb)(struct se_cmd *cmd); ssize_t (*check_configfs_dev_params)(struct se_hba *, struct se_subsystem_dev *); ssize_t (*set_configfs_dev_params)(struct se_hba *, @@ -40,6 +38,13 @@ struct se_subsystem_api { unsigned char *(*get_sense_buffer)(struct se_cmd *); }; +struct spc_ops { + int (*execute_rw)(struct se_cmd *cmd); + int (*execute_sync_cache)(struct se_cmd *cmd); + int (*execute_write_same)(struct se_cmd *cmd); + int (*execute_unmap)(struct se_cmd *cmd); +}; + int transport_subsystem_register(struct se_subsystem_api *); void transport_subsystem_release(struct se_subsystem_api *); @@ -49,6 +54,10 @@ struct se_device *transport_add_device_to_core_hba(struct se_hba *, void target_complete_cmd(struct se_cmd *, u8); +int sbc_parse_cdb(struct se_cmd *cmd, struct spc_ops *ops); +int spc_parse_cdb(struct se_cmd *cmd, unsigned int *size); +int spc_get_write_same_sectors(struct se_cmd *cmd); + void transport_set_vpd_proto_id(struct t10_vpd *, unsigned char *); int transport_set_vpd_assoc(struct t10_vpd *, unsigned char *); int transport_set_vpd_ident_type(struct t10_vpd *, unsigned char *); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index dc35d8660aa6..128ce46fa48a 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -145,12 +145,9 @@ enum transport_state_table { TRANSPORT_NO_STATE = 0, TRANSPORT_NEW_CMD = 1, TRANSPORT_WRITE_PENDING = 3, - TRANSPORT_PROCESS_WRITE = 4, TRANSPORT_PROCESSING = 5, TRANSPORT_COMPLETE = 6, - TRANSPORT_PROCESS_TMR = 9, TRANSPORT_ISTATE_PROCESSING = 11, - TRANSPORT_NEW_CMD_MAP = 16, TRANSPORT_COMPLETE_QF_WP = 18, TRANSPORT_COMPLETE_QF_OK = 19, }; @@ -160,25 +157,20 @@ enum se_cmd_flags_table { SCF_SUPPORTED_SAM_OPCODE = 0x00000001, SCF_TRANSPORT_TASK_SENSE = 0x00000002, SCF_EMULATED_TASK_SENSE = 0x00000004, - SCF_SCSI_DATA_SG_IO_CDB = 0x00000008, - SCF_SCSI_CONTROL_SG_IO_CDB = 0x00000010, - SCF_SCSI_NON_DATA_CDB = 0x00000020, - SCF_SCSI_TMR_CDB = 0x00000040, - SCF_SCSI_CDB_EXCEPTION = 0x00000080, - SCF_SCSI_RESERVATION_CONFLICT = 0x00000100, - SCF_FUA = 0x00000200, - SCF_SE_LUN_CMD = 0x00000800, - SCF_SE_ALLOW_EOO = 0x00001000, - SCF_BIDI = 0x00002000, - SCF_SENT_CHECK_CONDITION = 0x00004000, - SCF_OVERFLOW_BIT = 0x00008000, - SCF_UNDERFLOW_BIT = 0x00010000, - SCF_SENT_DELAYED_TAS = 0x00020000, - SCF_ALUA_NON_OPTIMIZED = 0x00040000, - SCF_DELAYED_CMD_FROM_SAM_ATTR = 0x00080000, - SCF_UNUSED = 0x00100000, - SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC = 0x00200000, - SCF_ACK_KREF = 0x00400000, + SCF_SCSI_DATA_CDB = 0x00000008, + SCF_SCSI_TMR_CDB = 0x00000010, + SCF_SCSI_CDB_EXCEPTION = 0x00000020, + SCF_SCSI_RESERVATION_CONFLICT = 0x00000040, + SCF_FUA = 0x00000080, + SCF_SE_LUN_CMD = 0x00000100, + SCF_BIDI = 0x00000400, + SCF_SENT_CHECK_CONDITION = 0x00000800, + SCF_OVERFLOW_BIT = 0x00001000, + SCF_UNDERFLOW_BIT = 0x00002000, + SCF_SENT_DELAYED_TAS = 0x00004000, + SCF_ALUA_NON_OPTIMIZED = 0x00008000, + SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC = 0x00020000, + SCF_ACK_KREF = 0x00040000, }; /* struct se_dev_entry->lun_flags and struct se_lun->lun_access */ @@ -220,6 +212,7 @@ enum tcm_sense_reason_table { TCM_CHECK_CONDITION_UNIT_ATTENTION = 0x0e, TCM_CHECK_CONDITION_NOT_READY = 0x0f, TCM_RESERVATION_CONFLICT = 0x10, + TCM_ADDRESS_OUT_OF_RANGE = 0x11, }; enum target_sc_flags_table { @@ -471,13 +464,6 @@ struct t10_reservation { struct t10_reservation_ops pr_ops; }; -struct se_queue_obj { - atomic_t queue_cnt; - spinlock_t cmd_queue_lock; - struct list_head qobj_list; - wait_queue_head_t thread_wq; -}; - struct se_tmr_req { /* Task Management function to be performed */ u8 function; @@ -486,11 +472,8 @@ struct se_tmr_req { int call_transport; /* Reference to ITT that Task Mgmt should be performed */ u32 ref_task_tag; - /* 64-bit encoded SAM LUN from $FABRIC_MOD TMR header */ - u64 ref_task_lun; void *fabric_tmr_ptr; struct se_cmd *task_cmd; - struct se_cmd *ref_cmd; struct se_device *tmr_dev; struct se_lun *tmr_lun; struct list_head tmr_list; @@ -537,7 +520,6 @@ struct se_cmd { /* Only used for internal passthrough and legacy TCM fabric modules */ struct se_session *se_sess; struct se_tmr_req *se_tmr_req; - struct list_head se_queue_node; struct list_head se_cmd_list; struct completion cmd_wait_comp; struct kref cmd_kref; @@ -575,7 +557,6 @@ struct se_cmd { struct scatterlist *t_bidi_data_sg; unsigned int t_bidi_data_nents; - struct list_head execute_list; struct list_head state_list; bool state_active; @@ -633,7 +614,6 @@ struct se_session { struct list_head sess_list; struct list_head sess_acl_list; struct list_head sess_cmd_list; - struct list_head sess_wait_list; spinlock_t sess_cmd_lock; struct kref sess_kref; }; @@ -780,13 +760,11 @@ struct se_device { /* Active commands on this virtual SE device */ atomic_t simple_cmds; atomic_t dev_ordered_id; - atomic_t execute_tasks; atomic_t dev_ordered_sync; atomic_t dev_qf_count; struct se_obj dev_obj; struct se_obj dev_access_obj; struct se_obj dev_export_obj; - struct se_queue_obj dev_queue_obj; spinlock_t delayed_cmd_lock; spinlock_t execute_task_lock; spinlock_t dev_reservation_lock; @@ -802,11 +780,9 @@ struct se_device { struct t10_pr_registration *dev_pr_res_holder; struct list_head dev_sep_list; struct list_head dev_tmr_list; - /* Pointer to descriptor for processing thread */ - struct task_struct *process_thread; + struct workqueue_struct *tmr_wq; struct work_struct qf_work_queue; struct list_head delayed_cmd_list; - struct list_head execute_list; struct list_head state_list; struct list_head qf_cmd_list; /* Pointer to associated SE HBA */ diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index c78a23333c4f..69fb3cfd02d7 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -33,12 +33,6 @@ struct target_core_fabric_ops { struct se_node_acl *); u32 (*tpg_get_inst_index)(struct se_portal_group *); /* - * Optional function pointer for TCM to perform command map - * from TCM processing thread context, for those struct se_cmd - * initially allocated in interrupt context. - */ - int (*new_cmd_map)(struct se_cmd *); - /* * Optional to release struct se_cmd and fabric dependent allocated * I/O descriptor in transport_cmd_check_stop(). * @@ -108,20 +102,18 @@ void transport_init_se_cmd(struct se_cmd *, struct target_core_fabric_ops *, struct se_session *, u32, int, int, unsigned char *); int transport_lookup_cmd_lun(struct se_cmd *, u32); int target_setup_cmd_from_cdb(struct se_cmd *, unsigned char *); -void target_submit_cmd(struct se_cmd *, struct se_session *, unsigned char *, +int target_submit_cmd(struct se_cmd *, struct se_session *, unsigned char *, unsigned char *, u32, u32, int, int, int); int target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess, unsigned char *sense, u32 unpacked_lun, void *fabric_tmr_ptr, unsigned char tm_type, gfp_t, unsigned int, int); int transport_handle_cdb_direct(struct se_cmd *); -int transport_generic_handle_cdb_map(struct se_cmd *); -int transport_generic_handle_data(struct se_cmd *); int transport_generic_map_mem_to_cmd(struct se_cmd *cmd, struct scatterlist *, u32, struct scatterlist *, u32); int transport_generic_new_cmd(struct se_cmd *); -void transport_generic_process_write(struct se_cmd *); +void target_execute_cmd(struct se_cmd *cmd); void transport_generic_free_cmd(struct se_cmd *, int); @@ -129,9 +121,8 @@ bool transport_wait_for_tasks(struct se_cmd *); int transport_check_aborted_status(struct se_cmd *, int); int transport_send_check_condition_and_sense(struct se_cmd *, u8, int); -void target_get_sess_cmd(struct se_session *, struct se_cmd *, bool); int target_put_sess_cmd(struct se_session *, struct se_cmd *); -void target_splice_sess_cmd_list(struct se_session *); +void target_sess_cmd_list_set_waiting(struct se_session *); void target_wait_for_sess_cmds(struct se_session *, int); int core_alua_check_nonop_delay(struct se_cmd *); diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index d274734b2aa4..5bde94d8585b 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -541,6 +541,50 @@ TRACE_EVENT(rcu_torture_read, __entry->rcutorturename, __entry->rhp) ); +/* + * Tracepoint for _rcu_barrier() execution. The string "s" describes + * the _rcu_barrier phase: + * "Begin": rcu_barrier_callback() started. + * "Check": rcu_barrier_callback() checking for piggybacking. + * "EarlyExit": rcu_barrier_callback() piggybacked, thus early exit. + * "Inc1": rcu_barrier_callback() piggyback check counter incremented. + * "Offline": rcu_barrier_callback() found offline CPU + * "OnlineQ": rcu_barrier_callback() found online CPU with callbacks. + * "OnlineNQ": rcu_barrier_callback() found online CPU, no callbacks. + * "IRQ": An rcu_barrier_callback() callback posted on remote CPU. + * "CB": An rcu_barrier_callback() invoked a callback, not the last. + * "LastCB": An rcu_barrier_callback() invoked the last callback. + * "Inc2": rcu_barrier_callback() piggyback check counter incremented. + * The "cpu" argument is the CPU or -1 if meaningless, the "cnt" argument + * is the count of remaining callbacks, and "done" is the piggybacking count. + */ +TRACE_EVENT(rcu_barrier, + + TP_PROTO(char *rcuname, char *s, int cpu, int cnt, unsigned long done), + + TP_ARGS(rcuname, s, cpu, cnt, done), + + TP_STRUCT__entry( + __field(char *, rcuname) + __field(char *, s) + __field(int, cpu) + __field(int, cnt) + __field(unsigned long, done) + ), + + TP_fast_assign( + __entry->rcuname = rcuname; + __entry->s = s; + __entry->cpu = cpu; + __entry->cnt = cnt; + __entry->done = done; + ), + + TP_printk("%s %s cpu %d remaining %d # %lu", + __entry->rcuname, __entry->s, __entry->cpu, __entry->cnt, + __entry->done) +); + #else /* #ifdef CONFIG_RCU_TRACE */ #define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0) @@ -564,6 +608,7 @@ TRACE_EVENT(rcu_torture_read, #define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \ do { } while (0) #define trace_rcu_torture_read(rcutorturename, rhp) do { } while (0) +#define trace_rcu_barrier(name, s, cpu, cnt, done) do { } while (0) #endif /* #else #ifdef CONFIG_RCU_TRACE */ diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 769724944fc6..c6bc2faaf261 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -571,6 +571,7 @@ static inline void ftrace_test_probe_##call(void) \ #undef __print_flags #undef __print_symbolic +#undef __print_hex #undef __get_dynamic_array #undef __get_str diff --git a/init/main.c b/init/main.c index b5cc0a7c4708..3f151f6c6da7 100644 --- a/init/main.c +++ b/init/main.c @@ -68,6 +68,7 @@ #include <linux/shmem_fs.h> #include <linux/slab.h> #include <linux/perf_event.h> +#include <linux/file.h> #include <asm/io.h> #include <asm/bugs.h> @@ -804,8 +805,8 @@ static noinline int init_post(void) system_state = SYSTEM_RUNNING; numa_default_policy(); - current->signal->flags |= SIGNAL_UNKILLABLE; + flush_delayed_fput(); if (ramdisk_execute_command) { run_init_process(ramdisk_execute_command); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 8ce57691e7b6..f8e54f5b9080 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -413,7 +413,7 @@ static void mqueue_evict_inode(struct inode *inode) } static int mqueue_create(struct inode *dir, struct dentry *dentry, - umode_t mode, struct nameidata *nd) + umode_t mode, bool excl) { struct inode *inode; struct mq_attr *attr = dentry->d_fsdata; @@ -721,8 +721,8 @@ static int mq_attr_ok(struct ipc_namespace *ipc_ns, struct mq_attr *attr) /* * Invoked when creating a new queue via sys_mq_open */ -static struct file *do_create(struct ipc_namespace *ipc_ns, struct dentry *dir, - struct dentry *dentry, int oflag, umode_t mode, +static struct file *do_create(struct ipc_namespace *ipc_ns, struct inode *dir, + struct path *path, int oflag, umode_t mode, struct mq_attr *attr) { const struct cred *cred = current_cred(); @@ -732,9 +732,9 @@ static struct file *do_create(struct ipc_namespace *ipc_ns, struct dentry *dir, if (attr) { ret = mq_attr_ok(ipc_ns, attr); if (ret) - goto out; + return ERR_PTR(ret); /* store for use during create */ - dentry->d_fsdata = attr; + path->dentry->d_fsdata = attr; } else { struct mq_attr def_attr; @@ -744,71 +744,51 @@ static struct file *do_create(struct ipc_namespace *ipc_ns, struct dentry *dir, ipc_ns->mq_msgsize_default); ret = mq_attr_ok(ipc_ns, &def_attr); if (ret) - goto out; + return ERR_PTR(ret); } mode &= ~current_umask(); - ret = mnt_want_write(ipc_ns->mq_mnt); + ret = mnt_want_write(path->mnt); if (ret) - goto out; - ret = vfs_create(dir->d_inode, dentry, mode, NULL); - dentry->d_fsdata = NULL; - if (ret) - goto out_drop_write; - - result = dentry_open(dentry, ipc_ns->mq_mnt, oflag, cred); + return ERR_PTR(ret); + ret = vfs_create(dir, path->dentry, mode, true); + path->dentry->d_fsdata = NULL; + if (!ret) + result = dentry_open(path, oflag, cred); + else + result = ERR_PTR(ret); /* * dentry_open() took a persistent mnt_want_write(), * so we can now drop this one. */ - mnt_drop_write(ipc_ns->mq_mnt); + mnt_drop_write(path->mnt); return result; - -out_drop_write: - mnt_drop_write(ipc_ns->mq_mnt); -out: - dput(dentry); - mntput(ipc_ns->mq_mnt); - return ERR_PTR(ret); } /* Opens existing queue */ -static struct file *do_open(struct ipc_namespace *ipc_ns, - struct dentry *dentry, int oflag) +static struct file *do_open(struct path *path, int oflag) { - int ret; - const struct cred *cred = current_cred(); - static const int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE, MAY_READ | MAY_WRITE }; - - if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY)) { - ret = -EINVAL; - goto err; - } - - if (inode_permission(dentry->d_inode, oflag2acc[oflag & O_ACCMODE])) { - ret = -EACCES; - goto err; - } - - return dentry_open(dentry, ipc_ns->mq_mnt, oflag, cred); - -err: - dput(dentry); - mntput(ipc_ns->mq_mnt); - return ERR_PTR(ret); + int acc; + if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY)) + return ERR_PTR(-EINVAL); + acc = oflag2acc[oflag & O_ACCMODE]; + if (inode_permission(path->dentry->d_inode, acc)) + return ERR_PTR(-EACCES); + return dentry_open(path, oflag, current_cred()); } SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, struct mq_attr __user *, u_attr) { - struct dentry *dentry; + struct path path; struct file *filp; char *name; struct mq_attr attr; int fd, error; struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns; + struct dentry *root = ipc_ns->mq_mnt->mnt_root; if (u_attr && copy_from_user(&attr, u_attr, sizeof(struct mq_attr))) return -EFAULT; @@ -822,52 +802,49 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, if (fd < 0) goto out_putname; - mutex_lock(&ipc_ns->mq_mnt->mnt_root->d_inode->i_mutex); - dentry = lookup_one_len(name, ipc_ns->mq_mnt->mnt_root, strlen(name)); - if (IS_ERR(dentry)) { - error = PTR_ERR(dentry); + error = 0; + mutex_lock(&root->d_inode->i_mutex); + path.dentry = lookup_one_len(name, root, strlen(name)); + if (IS_ERR(path.dentry)) { + error = PTR_ERR(path.dentry); goto out_putfd; } - mntget(ipc_ns->mq_mnt); + path.mnt = mntget(ipc_ns->mq_mnt); if (oflag & O_CREAT) { - if (dentry->d_inode) { /* entry already exists */ - audit_inode(name, dentry); + if (path.dentry->d_inode) { /* entry already exists */ + audit_inode(name, path.dentry); if (oflag & O_EXCL) { error = -EEXIST; goto out; } - filp = do_open(ipc_ns, dentry, oflag); + filp = do_open(&path, oflag); } else { - filp = do_create(ipc_ns, ipc_ns->mq_mnt->mnt_root, - dentry, oflag, mode, + filp = do_create(ipc_ns, root->d_inode, + &path, oflag, mode, u_attr ? &attr : NULL); } } else { - if (!dentry->d_inode) { + if (!path.dentry->d_inode) { error = -ENOENT; goto out; } - audit_inode(name, dentry); - filp = do_open(ipc_ns, dentry, oflag); + audit_inode(name, path.dentry); + filp = do_open(&path, oflag); } - if (IS_ERR(filp)) { + if (!IS_ERR(filp)) + fd_install(fd, filp); + else error = PTR_ERR(filp); - goto out_putfd; - } - - fd_install(fd, filp); - goto out_upsem; - out: - dput(dentry); - mntput(ipc_ns->mq_mnt); + path_put(&path); out_putfd: - put_unused_fd(fd); - fd = error; -out_upsem: - mutex_unlock(&ipc_ns->mq_mnt->mnt_root->d_inode->i_mutex); + if (error) { + put_unused_fd(fd); + fd = error; + } + mutex_unlock(&root->d_inode->i_mutex); out_putname: putname(name); return fd; diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 5bf0790497e7..3a5ca582ba1e 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -595,7 +595,7 @@ void audit_trim_trees(void) root_mnt = collect_mounts(&path); path_put(&path); - if (!root_mnt) + if (IS_ERR(root_mnt)) goto skip_it; spin_lock(&hash_lock); @@ -669,8 +669,8 @@ int audit_add_tree_rule(struct audit_krule *rule) goto Err; mnt = collect_mounts(&path); path_put(&path); - if (!mnt) { - err = -ENOMEM; + if (IS_ERR(mnt)) { + err = PTR_ERR(mnt); goto Err; } @@ -719,8 +719,8 @@ int audit_tag_tree(char *old, char *new) return err; tagged = collect_mounts(&path2); path_put(&path2); - if (!tagged) - return -ENOMEM; + if (IS_ERR(tagged)) + return PTR_ERR(tagged); err = kern_path(old, 0, &path1); if (err) { diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index e683869365d9..3823281401b5 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -355,34 +355,15 @@ static void audit_remove_parent_watches(struct audit_parent *parent) /* Get path information necessary for adding watches. */ static int audit_get_nd(struct audit_watch *watch, struct path *parent) { - struct nameidata nd; - struct dentry *d; - int err; - - err = kern_path_parent(watch->path, &nd); - if (err) - return err; - - if (nd.last_type != LAST_NORM) { - path_put(&nd.path); - return -EINVAL; - } - - mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); - d = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len); - if (IS_ERR(d)) { - mutex_unlock(&nd.path.dentry->d_inode->i_mutex); - path_put(&nd.path); + struct dentry *d = kern_path_locked(watch->path, parent); + if (IS_ERR(d)) return PTR_ERR(d); - } + mutex_unlock(&parent->dentry->d_inode->i_mutex); if (d->d_inode) { /* update watch filter fields */ watch->dev = d->d_inode->i_sb->s_dev; watch->ino = d->d_inode->i_ino; } - mutex_unlock(&nd.path.dentry->d_inode->i_mutex); - - *parent = nd.path; dput(d); return 0; } diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 2097684cf194..af2b5641fc8b 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -822,7 +822,7 @@ EXPORT_SYMBOL_GPL(cgroup_unlock); */ static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); -static struct dentry *cgroup_lookup(struct inode *, struct dentry *, struct nameidata *); +static struct dentry *cgroup_lookup(struct inode *, struct dentry *, unsigned int); static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry); static int cgroup_populate_dir(struct cgroup *cgrp); static const struct inode_operations cgroup_dir_inode_operations; @@ -901,13 +901,10 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode) mutex_unlock(&cgroup_mutex); /* - * We want to drop the active superblock reference from the - * cgroup creation after all the dentry refs are gone - - * kill_sb gets mighty unhappy otherwise. Mark - * dentry->d_fsdata with cgroup_diput() to tell - * cgroup_d_release() to call deactivate_super(). + * Drop the active superblock reference that we took when we + * created the cgroup */ - dentry->d_fsdata = cgroup_diput; + deactivate_super(cgrp->root->sb); /* * if we're getting rid of the cgroup, refcount should ensure @@ -933,13 +930,6 @@ static int cgroup_delete(const struct dentry *d) return 1; } -static void cgroup_d_release(struct dentry *dentry) -{ - /* did cgroup_diput() tell me to deactivate super? */ - if (dentry->d_fsdata == cgroup_diput) - deactivate_super(dentry->d_sb); -} - static void remove_dir(struct dentry *d) { struct dentry *parent = dget(d->d_parent); @@ -1547,7 +1537,6 @@ static int cgroup_get_rootdir(struct super_block *sb) static const struct dentry_operations cgroup_dops = { .d_iput = cgroup_diput, .d_delete = cgroup_delete, - .d_release = cgroup_d_release, }; struct inode *inode = @@ -1598,7 +1587,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, opts.new_root = new_root; /* Locate an existing or new sb for this hierarchy */ - sb = sget(fs_type, cgroup_test_super, cgroup_set_super, &opts); + sb = sget(fs_type, cgroup_test_super, cgroup_set_super, 0, &opts); if (IS_ERR(sb)) { ret = PTR_ERR(sb); cgroup_drop_root(opts.new_root); @@ -2581,7 +2570,7 @@ static const struct inode_operations cgroup_dir_inode_operations = { .rename = cgroup_rename, }; -static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); @@ -3894,8 +3883,12 @@ static void css_dput_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, dput_work); + struct dentry *dentry = css->cgroup->dentry; + struct super_block *sb = dentry->d_sb; - dput(css->cgroup->dentry); + atomic_inc(&sb->s_active); + dput(dentry); + deactivate_super(sb); } static void init_cgroup_css(struct cgroup_subsys_state *css, diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 67b847dfa2bb..1f91413edb87 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -14,6 +14,7 @@ #include <linux/ctype.h> #include <linux/string.h> #include <linux/kernel.h> +#include <linux/kmsg_dump.h> #include <linux/reboot.h> #include <linux/sched.h> #include <linux/sysrq.h> @@ -2040,8 +2041,15 @@ static int kdb_env(int argc, const char **argv) */ static int kdb_dmesg(int argc, const char **argv) { - char *syslog_data[4], *start, *end, c = '\0', *p; - int diag, logging, logsize, lines = 0, adjust = 0, n; + int diag; + int logging; + int lines = 0; + int adjust = 0; + int n = 0; + int skip = 0; + struct kmsg_dumper dumper = { .active = 1 }; + size_t len; + char buf[201]; if (argc > 2) return KDB_ARGCOUNT; @@ -2064,22 +2072,10 @@ static int kdb_dmesg(int argc, const char **argv) kdb_set(2, setargs); } - /* syslog_data[0,1] physical start, end+1. syslog_data[2,3] - * logical start, end+1. */ - kdb_syslog_data(syslog_data); - if (syslog_data[2] == syslog_data[3]) - return 0; - logsize = syslog_data[1] - syslog_data[0]; - start = syslog_data[2]; - end = syslog_data[3]; -#define KDB_WRAP(p) (((p - syslog_data[0]) % logsize) + syslog_data[0]) - for (n = 0, p = start; p < end; ++p) { - c = *KDB_WRAP(p); - if (c == '\n') - ++n; - } - if (c != '\n') - ++n; + kmsg_dump_rewind_nolock(&dumper); + while (kmsg_dump_get_line_nolock(&dumper, 1, NULL, 0, NULL)) + n++; + if (lines < 0) { if (adjust >= n) kdb_printf("buffer only contains %d lines, nothing " @@ -2087,21 +2083,11 @@ static int kdb_dmesg(int argc, const char **argv) else if (adjust - lines >= n) kdb_printf("buffer only contains %d lines, last %d " "lines printed\n", n, n - adjust); - if (adjust) { - for (; start < end && adjust; ++start) { - if (*KDB_WRAP(start) == '\n') - --adjust; - } - if (start < end) - ++start; - } - for (p = start; p < end && lines; ++p) { - if (*KDB_WRAP(p) == '\n') - ++lines; - } - end = p; + skip = adjust; + lines = abs(lines); } else if (lines > 0) { - int skip = n - (adjust + lines); + skip = n - lines - adjust; + lines = abs(lines); if (adjust >= n) { kdb_printf("buffer only contains %d lines, " "nothing printed\n", n); @@ -2112,35 +2098,24 @@ static int kdb_dmesg(int argc, const char **argv) kdb_printf("buffer only contains %d lines, first " "%d lines printed\n", n, lines); } - for (; start < end && skip; ++start) { - if (*KDB_WRAP(start) == '\n') - --skip; - } - for (p = start; p < end && lines; ++p) { - if (*KDB_WRAP(p) == '\n') - --lines; - } - end = p; + } else { + lines = n; } - /* Do a line at a time (max 200 chars) to reduce protocol overhead */ - c = '\n'; - while (start != end) { - char buf[201]; - p = buf; - if (KDB_FLAG(CMD_INTERRUPT)) - return 0; - while (start < end && (c = *KDB_WRAP(start)) && - (p - buf) < sizeof(buf)-1) { - ++start; - *p++ = c; - if (c == '\n') - break; + + if (skip >= n || skip < 0) + return 0; + + kmsg_dump_rewind_nolock(&dumper); + while (kmsg_dump_get_line_nolock(&dumper, 1, buf, sizeof(buf), &len)) { + if (skip) { + skip--; + continue; } - *p = '\0'; - kdb_printf("%s", buf); + if (!lines--) + break; + + kdb_printf("%.*s\n", (int)len - 1, buf); } - if (c != '\n') - kdb_printf("\n"); return 0; } diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 47c4e56e513b..392ec6a25844 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -205,7 +205,6 @@ extern char kdb_grep_string[]; extern int kdb_grep_leading; extern int kdb_grep_trailing; extern char *kdb_cmds[]; -extern void kdb_syslog_data(char *syslog_data[]); extern unsigned long kdb_task_state_string(const char *); extern char kdb_task_state_char (const struct task_struct *); extern unsigned long kdb_task_state(const struct task_struct *p, diff --git a/kernel/events/core.c b/kernel/events/core.c index d7d71d6ec972..f1cf0edeb39a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1645,6 +1645,8 @@ perf_install_in_context(struct perf_event_context *ctx, lockdep_assert_held(&ctx->mutex); event->ctx = ctx; + if (event->cpu != -1) + event->cpu = cpu; if (!task) { /* @@ -6252,6 +6254,8 @@ SYSCALL_DEFINE5(perf_event_open, } } + get_online_cpus(); + event = perf_event_alloc(&attr, cpu, task, group_leader, NULL, NULL, NULL); if (IS_ERR(event)) { @@ -6304,7 +6308,7 @@ SYSCALL_DEFINE5(perf_event_open, /* * Get the target context (task or percpu): */ - ctx = find_get_context(pmu, task, cpu); + ctx = find_get_context(pmu, task, event->cpu); if (IS_ERR(ctx)) { err = PTR_ERR(ctx); goto err_alloc; @@ -6377,20 +6381,23 @@ SYSCALL_DEFINE5(perf_event_open, mutex_lock(&ctx->mutex); if (move_group) { - perf_install_in_context(ctx, group_leader, cpu); + synchronize_rcu(); + perf_install_in_context(ctx, group_leader, event->cpu); get_ctx(ctx); list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { - perf_install_in_context(ctx, sibling, cpu); + perf_install_in_context(ctx, sibling, event->cpu); get_ctx(ctx); } } - perf_install_in_context(ctx, event, cpu); + perf_install_in_context(ctx, event, event->cpu); ++ctx->generation; perf_unpin_context(ctx); mutex_unlock(&ctx->mutex); + put_online_cpus(); + event->owner = current; mutex_lock(¤t->perf_event_mutex); @@ -6419,6 +6426,7 @@ err_context: err_alloc: free_event(event); err_task: + put_online_cpus(); if (task) put_task_struct(task); err_group_fd: @@ -6479,6 +6487,39 @@ err: } EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter); +void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) +{ + struct perf_event_context *src_ctx; + struct perf_event_context *dst_ctx; + struct perf_event *event, *tmp; + LIST_HEAD(events); + + src_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, src_cpu)->ctx; + dst_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, dst_cpu)->ctx; + + mutex_lock(&src_ctx->mutex); + list_for_each_entry_safe(event, tmp, &src_ctx->event_list, + event_entry) { + perf_remove_from_context(event); + put_ctx(src_ctx); + list_add(&event->event_entry, &events); + } + mutex_unlock(&src_ctx->mutex); + + synchronize_rcu(); + + mutex_lock(&dst_ctx->mutex); + list_for_each_entry_safe(event, tmp, &events, event_entry) { + list_del(&event->event_entry); + if (event->state >= PERF_EVENT_STATE_OFF) + event->state = PERF_EVENT_STATE_INACTIVE; + perf_install_in_context(dst_ctx, event, dst_cpu); + get_ctx(dst_ctx); + } + mutex_unlock(&dst_ctx->mutex); +} +EXPORT_SYMBOL_GPL(perf_pmu_migrate_context); + static void sync_child_event(struct perf_event *child_event, struct task_struct *child) { diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 985be4d80fe8..f93532748bca 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -38,13 +38,29 @@ #define UINSNS_PER_PAGE (PAGE_SIZE/UPROBE_XOL_SLOT_BYTES) #define MAX_UPROBE_XOL_SLOTS UINSNS_PER_PAGE -static struct srcu_struct uprobes_srcu; static struct rb_root uprobes_tree = RB_ROOT; static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */ #define UPROBES_HASH_SZ 13 +/* + * We need separate register/unregister and mmap/munmap lock hashes because + * of mmap_sem nesting. + * + * uprobe_register() needs to install probes on (potentially) all processes + * and thus needs to acquire multiple mmap_sems (consequtively, not + * concurrently), whereas uprobe_mmap() is called while holding mmap_sem + * for the particular process doing the mmap. + * + * uprobe_register()->register_for_each_vma() needs to drop/acquire mmap_sem + * because of lock order against i_mmap_mutex. This means there's a hole in + * the register vma iteration where a mmap() can happen. + * + * Thus uprobe_register() can race with uprobe_mmap() and we can try and + * install a probe where one is already installed. + */ + /* serialize (un)register */ static struct mutex uprobes_mutex[UPROBES_HASH_SZ]; @@ -61,17 +77,6 @@ static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ]; */ static atomic_t uprobe_events = ATOMIC_INIT(0); -/* - * Maintain a temporary per vma info that can be used to search if a vma - * has already been handled. This structure is introduced since extending - * vm_area_struct wasnt recommended. - */ -struct vma_info { - struct list_head probe_list; - struct mm_struct *mm; - loff_t vaddr; -}; - struct uprobe { struct rb_node rb_node; /* node in the rb tree */ atomic_t ref; @@ -100,7 +105,8 @@ static bool valid_vma(struct vm_area_struct *vma, bool is_register) if (!is_register) return true; - if ((vma->vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) == (VM_READ|VM_EXEC)) + if ((vma->vm_flags & (VM_HUGETLB|VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) + == (VM_READ|VM_EXEC)) return true; return false; @@ -129,33 +135,17 @@ static loff_t vma_address(struct vm_area_struct *vma, loff_t offset) static int __replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage) { struct mm_struct *mm = vma->vm_mm; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *ptep; - spinlock_t *ptl; unsigned long addr; - int err = -EFAULT; + spinlock_t *ptl; + pte_t *ptep; addr = page_address_in_vma(page, vma); if (addr == -EFAULT) - goto out; - - pgd = pgd_offset(mm, addr); - if (!pgd_present(*pgd)) - goto out; - - pud = pud_offset(pgd, addr); - if (!pud_present(*pud)) - goto out; - - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) - goto out; + return -EFAULT; - ptep = pte_offset_map_lock(mm, pmd, addr, &ptl); + ptep = page_check_address(page, mm, addr, &ptl, 0); if (!ptep) - goto out; + return -EAGAIN; get_page(kpage); page_add_new_anon_rmap(kpage, vma, addr); @@ -174,10 +164,8 @@ static int __replace_page(struct vm_area_struct *vma, struct page *page, struct try_to_free_swap(page); put_page(page); pte_unmap_unlock(ptep, ptl); - err = 0; -out: - return err; + return 0; } /** @@ -222,9 +210,8 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, void *vaddr_old, *vaddr_new; struct vm_area_struct *vma; struct uprobe *uprobe; - loff_t addr; int ret; - +retry: /* Read the page with vaddr into memory */ ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma); if (ret <= 0) @@ -246,10 +233,6 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, if (mapping != vma->vm_file->f_mapping) goto put_out; - addr = vma_address(vma, uprobe->offset); - if (vaddr != (unsigned long)addr) - goto put_out; - ret = -ENOMEM; new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); if (!new_page) @@ -267,11 +250,7 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, vaddr_new = kmap_atomic(new_page); memcpy(vaddr_new, vaddr_old, PAGE_SIZE); - - /* poke the new insn in, ASSUMES we don't cross page boundary */ - vaddr &= ~PAGE_MASK; - BUG_ON(vaddr + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); - memcpy(vaddr_new + vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); + memcpy(vaddr_new + (vaddr & ~PAGE_MASK), &opcode, UPROBE_SWBP_INSN_SIZE); kunmap_atomic(vaddr_new); kunmap_atomic(vaddr_old); @@ -291,6 +270,8 @@ unlock_out: put_out: put_page(old_page); + if (unlikely(ret == -EAGAIN)) + goto retry; return ret; } @@ -312,7 +293,7 @@ static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_ void *vaddr_new; int ret; - ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &page, NULL); + ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL); if (ret <= 0) return ret; @@ -333,10 +314,20 @@ static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr) uprobe_opcode_t opcode; int result; + if (current->mm == mm) { + pagefault_disable(); + result = __copy_from_user_inatomic(&opcode, (void __user*)vaddr, + sizeof(opcode)); + pagefault_enable(); + + if (likely(result == 0)) + goto out; + } + result = read_opcode(mm, vaddr, &opcode); if (result) return result; - +out: if (is_swbp_insn(&opcode)) return 1; @@ -355,7 +346,9 @@ static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr) int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) { int result; - + /* + * See the comment near uprobes_hash(). + */ result = is_swbp_at_addr(mm, vaddr); if (result == 1) return -EEXIST; @@ -520,7 +513,6 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) uprobe->inode = igrab(inode); uprobe->offset = offset; init_rwsem(&uprobe->consumer_rwsem); - INIT_LIST_HEAD(&uprobe->pending_list); /* add to uprobes_tree, sorted on inode:offset */ cur_uprobe = insert_uprobe(uprobe); @@ -588,20 +580,22 @@ static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc) } static int -__copy_insn(struct address_space *mapping, struct vm_area_struct *vma, char *insn, - unsigned long nbytes, unsigned long offset) +__copy_insn(struct address_space *mapping, struct file *filp, char *insn, + unsigned long nbytes, loff_t offset) { - struct file *filp = vma->vm_file; struct page *page; void *vaddr; - unsigned long off1; - unsigned long idx; + unsigned long off; + pgoff_t idx; if (!filp) return -EINVAL; - idx = (unsigned long)(offset >> PAGE_CACHE_SHIFT); - off1 = offset &= ~PAGE_MASK; + if (!mapping->a_ops->readpage) + return -EIO; + + idx = offset >> PAGE_CACHE_SHIFT; + off = offset & ~PAGE_MASK; /* * Ensure that the page that has the original instruction is @@ -612,22 +606,20 @@ __copy_insn(struct address_space *mapping, struct vm_area_struct *vma, char *ins return PTR_ERR(page); vaddr = kmap_atomic(page); - memcpy(insn, vaddr + off1, nbytes); + memcpy(insn, vaddr + off, nbytes); kunmap_atomic(vaddr); page_cache_release(page); return 0; } -static int -copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr) +static int copy_insn(struct uprobe *uprobe, struct file *filp) { struct address_space *mapping; unsigned long nbytes; int bytes; - addr &= ~PAGE_MASK; - nbytes = PAGE_SIZE - addr; + nbytes = PAGE_SIZE - (uprobe->offset & ~PAGE_MASK); mapping = uprobe->inode->i_mapping; /* Instruction at end of binary; copy only available bytes */ @@ -638,13 +630,13 @@ copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr) /* Instruction at the page-boundary; copy bytes in second page */ if (nbytes < bytes) { - if (__copy_insn(mapping, vma, uprobe->arch.insn + nbytes, - bytes - nbytes, uprobe->offset + nbytes)) - return -ENOMEM; - + int err = __copy_insn(mapping, filp, uprobe->arch.insn + nbytes, + bytes - nbytes, uprobe->offset + nbytes); + if (err) + return err; bytes = nbytes; } - return __copy_insn(mapping, vma, uprobe->arch.insn, bytes, uprobe->offset); + return __copy_insn(mapping, filp, uprobe->arch.insn, bytes, uprobe->offset); } /* @@ -672,9 +664,8 @@ copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr) */ static int install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, - struct vm_area_struct *vma, loff_t vaddr) + struct vm_area_struct *vma, unsigned long vaddr) { - unsigned long addr; int ret; /* @@ -687,20 +678,22 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, if (!uprobe->consumers) return -EEXIST; - addr = (unsigned long)vaddr; - if (!(uprobe->flags & UPROBE_COPY_INSN)) { - ret = copy_insn(uprobe, vma, addr); + ret = copy_insn(uprobe, vma->vm_file); if (ret) return ret; if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn)) - return -EEXIST; + return -ENOTSUPP; - ret = arch_uprobe_analyze_insn(&uprobe->arch, mm); + ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr); if (ret) return ret; + /* write_opcode() assumes we don't cross page boundary */ + BUG_ON((uprobe->offset & ~PAGE_MASK) + + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); + uprobe->flags |= UPROBE_COPY_INSN; } @@ -713,7 +706,7 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, * Hence increment before and decrement on failure. */ atomic_inc(&mm->uprobes_state.count); - ret = set_swbp(&uprobe->arch, mm, addr); + ret = set_swbp(&uprobe->arch, mm, vaddr); if (ret) atomic_dec(&mm->uprobes_state.count); @@ -721,27 +714,21 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, } static void -remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, loff_t vaddr) +remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr) { - if (!set_orig_insn(&uprobe->arch, mm, (unsigned long)vaddr, true)) + if (!set_orig_insn(&uprobe->arch, mm, vaddr, true)) atomic_dec(&mm->uprobes_state.count); } /* - * There could be threads that have hit the breakpoint and are entering the - * notifier code and trying to acquire the uprobes_treelock. The thread - * calling delete_uprobe() that is removing the uprobe from the rb_tree can - * race with these threads and might acquire the uprobes_treelock compared - * to some of the breakpoint hit threads. In such a case, the breakpoint - * hit threads will not find the uprobe. The current unregistering thread - * waits till all other threads have hit a breakpoint, to acquire the - * uprobes_treelock before the uprobe is removed from the rbtree. + * There could be threads that have already hit the breakpoint. They + * will recheck the current insn and restart if find_uprobe() fails. + * See find_active_uprobe(). */ static void delete_uprobe(struct uprobe *uprobe) { unsigned long flags; - synchronize_srcu(&uprobes_srcu); spin_lock_irqsave(&uprobes_treelock, flags); rb_erase(&uprobe->rb_node, &uprobes_tree); spin_unlock_irqrestore(&uprobes_treelock, flags); @@ -750,139 +737,135 @@ static void delete_uprobe(struct uprobe *uprobe) atomic_dec(&uprobe_events); } -static struct vma_info * -__find_next_vma_info(struct address_space *mapping, struct list_head *head, - struct vma_info *vi, loff_t offset, bool is_register) +struct map_info { + struct map_info *next; + struct mm_struct *mm; + unsigned long vaddr; +}; + +static inline struct map_info *free_map_info(struct map_info *info) +{ + struct map_info *next = info->next; + kfree(info); + return next; +} + +static struct map_info * +build_map_info(struct address_space *mapping, loff_t offset, bool is_register) { + unsigned long pgoff = offset >> PAGE_SHIFT; struct prio_tree_iter iter; struct vm_area_struct *vma; - struct vma_info *tmpvi; - unsigned long pgoff; - int existing_vma; - loff_t vaddr; - - pgoff = offset >> PAGE_SHIFT; + struct map_info *curr = NULL; + struct map_info *prev = NULL; + struct map_info *info; + int more = 0; + again: + mutex_lock(&mapping->i_mmap_mutex); vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { if (!valid_vma(vma, is_register)) continue; - existing_vma = 0; - vaddr = vma_address(vma, offset); - - list_for_each_entry(tmpvi, head, probe_list) { - if (tmpvi->mm == vma->vm_mm && tmpvi->vaddr == vaddr) { - existing_vma = 1; - break; - } + if (!prev && !more) { + /* + * Needs GFP_NOWAIT to avoid i_mmap_mutex recursion through + * reclaim. This is optimistic, no harm done if it fails. + */ + prev = kmalloc(sizeof(struct map_info), + GFP_NOWAIT | __GFP_NOMEMALLOC | __GFP_NOWARN); + if (prev) + prev->next = NULL; } - - /* - * Another vma needs a probe to be installed. However skip - * installing the probe if the vma is about to be unlinked. - */ - if (!existing_vma && atomic_inc_not_zero(&vma->vm_mm->mm_users)) { - vi->mm = vma->vm_mm; - vi->vaddr = vaddr; - list_add(&vi->probe_list, head); - - return vi; + if (!prev) { + more++; + continue; } - } - return NULL; -} - -/* - * Iterate in the rmap prio tree and find a vma where a probe has not - * yet been inserted. - */ -static struct vma_info * -find_next_vma_info(struct address_space *mapping, struct list_head *head, - loff_t offset, bool is_register) -{ - struct vma_info *vi, *retvi; + if (!atomic_inc_not_zero(&vma->vm_mm->mm_users)) + continue; - vi = kzalloc(sizeof(struct vma_info), GFP_KERNEL); - if (!vi) - return ERR_PTR(-ENOMEM); + info = prev; + prev = prev->next; + info->next = curr; + curr = info; - mutex_lock(&mapping->i_mmap_mutex); - retvi = __find_next_vma_info(mapping, head, vi, offset, is_register); + info->mm = vma->vm_mm; + info->vaddr = vma_address(vma, offset); + } mutex_unlock(&mapping->i_mmap_mutex); - if (!retvi) - kfree(vi); + if (!more) + goto out; + + prev = curr; + while (curr) { + mmput(curr->mm); + curr = curr->next; + } - return retvi; + do { + info = kmalloc(sizeof(struct map_info), GFP_KERNEL); + if (!info) { + curr = ERR_PTR(-ENOMEM); + goto out; + } + info->next = prev; + prev = info; + } while (--more); + + goto again; + out: + while (prev) + prev = free_map_info(prev); + return curr; } static int register_for_each_vma(struct uprobe *uprobe, bool is_register) { - struct list_head try_list; - struct vm_area_struct *vma; - struct address_space *mapping; - struct vma_info *vi, *tmpvi; - struct mm_struct *mm; - loff_t vaddr; - int ret; + struct map_info *info; + int err = 0; - mapping = uprobe->inode->i_mapping; - INIT_LIST_HEAD(&try_list); + info = build_map_info(uprobe->inode->i_mapping, + uprobe->offset, is_register); + if (IS_ERR(info)) + return PTR_ERR(info); - ret = 0; + while (info) { + struct mm_struct *mm = info->mm; + struct vm_area_struct *vma; - for (;;) { - vi = find_next_vma_info(mapping, &try_list, uprobe->offset, is_register); - if (!vi) - break; + if (err) + goto free; - if (IS_ERR(vi)) { - ret = PTR_ERR(vi); - break; - } + down_write(&mm->mmap_sem); + vma = find_vma(mm, (unsigned long)info->vaddr); + if (!vma || !valid_vma(vma, is_register)) + goto unlock; - mm = vi->mm; - down_read(&mm->mmap_sem); - vma = find_vma(mm, (unsigned long)vi->vaddr); - if (!vma || !valid_vma(vma, is_register)) { - list_del(&vi->probe_list); - kfree(vi); - up_read(&mm->mmap_sem); - mmput(mm); - continue; - } - vaddr = vma_address(vma, uprobe->offset); if (vma->vm_file->f_mapping->host != uprobe->inode || - vaddr != vi->vaddr) { - list_del(&vi->probe_list); - kfree(vi); - up_read(&mm->mmap_sem); - mmput(mm); - continue; - } - - if (is_register) - ret = install_breakpoint(uprobe, mm, vma, vi->vaddr); - else - remove_breakpoint(uprobe, mm, vi->vaddr); + vma_address(vma, uprobe->offset) != info->vaddr) + goto unlock; - up_read(&mm->mmap_sem); - mmput(mm); if (is_register) { - if (ret && ret == -EEXIST) - ret = 0; - if (ret) - break; + err = install_breakpoint(uprobe, mm, vma, info->vaddr); + /* + * We can race against uprobe_mmap(), see the + * comment near uprobe_hash(). + */ + if (err == -EEXIST) + err = 0; + } else { + remove_breakpoint(uprobe, mm, info->vaddr); } + unlock: + up_write(&mm->mmap_sem); + free: + mmput(mm); + info = free_map_info(info); } - list_for_each_entry_safe(vi, tmpvi, &try_list, probe_list) { - list_del(&vi->probe_list); - kfree(vi); - } - - return ret; + return err; } static int __uprobe_register(struct uprobe *uprobe) @@ -1048,7 +1031,7 @@ static void build_probe_list(struct inode *inode, struct list_head *head) int uprobe_mmap(struct vm_area_struct *vma) { struct list_head tmp_list; - struct uprobe *uprobe, *u; + struct uprobe *uprobe; struct inode *inode; int ret, count; @@ -1066,12 +1049,9 @@ int uprobe_mmap(struct vm_area_struct *vma) ret = 0; count = 0; - list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { - loff_t vaddr; - - list_del(&uprobe->pending_list); + list_for_each_entry(uprobe, &tmp_list, pending_list) { if (!ret) { - vaddr = vma_address(vma, uprobe->offset); + loff_t vaddr = vma_address(vma, uprobe->offset); if (vaddr < vma->vm_start || vaddr >= vma->vm_end) { put_uprobe(uprobe); @@ -1079,8 +1059,10 @@ int uprobe_mmap(struct vm_area_struct *vma) } ret = install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); - - /* Ignore double add: */ + /* + * We can race against uprobe_register(), see the + * comment near uprobe_hash(). + */ if (ret == -EEXIST) { ret = 0; @@ -1115,7 +1097,7 @@ int uprobe_mmap(struct vm_area_struct *vma) void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct list_head tmp_list; - struct uprobe *uprobe, *u; + struct uprobe *uprobe; struct inode *inode; if (!atomic_read(&uprobe_events) || !valid_vma(vma, false)) @@ -1132,11 +1114,8 @@ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned lon mutex_lock(uprobes_mmap_hash(inode)); build_probe_list(inode, &tmp_list); - list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { - loff_t vaddr; - - list_del(&uprobe->pending_list); - vaddr = vma_address(vma, uprobe->offset); + list_for_each_entry(uprobe, &tmp_list, pending_list) { + loff_t vaddr = vma_address(vma, uprobe->offset); if (vaddr >= start && vaddr < end) { /* @@ -1378,9 +1357,6 @@ void uprobe_free_utask(struct task_struct *t) { struct uprobe_task *utask = t->utask; - if (t->uprobe_srcu_id != -1) - srcu_read_unlock_raw(&uprobes_srcu, t->uprobe_srcu_id); - if (!utask) return; @@ -1398,7 +1374,6 @@ void uprobe_free_utask(struct task_struct *t) void uprobe_copy_process(struct task_struct *t) { t->utask = NULL; - t->uprobe_srcu_id = -1; } /* @@ -1417,7 +1392,6 @@ static struct uprobe_task *add_utask(void) if (unlikely(!utask)) return NULL; - utask->active_uprobe = NULL; current->utask = utask; return utask; } @@ -1479,41 +1453,64 @@ static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs) return false; } +static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) +{ + struct mm_struct *mm = current->mm; + struct uprobe *uprobe = NULL; + struct vm_area_struct *vma; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, bp_vaddr); + if (vma && vma->vm_start <= bp_vaddr) { + if (valid_vma(vma, false)) { + struct inode *inode; + loff_t offset; + + inode = vma->vm_file->f_mapping->host; + offset = bp_vaddr - vma->vm_start; + offset += (vma->vm_pgoff << PAGE_SHIFT); + uprobe = find_uprobe(inode, offset); + } + + if (!uprobe) + *is_swbp = is_swbp_at_addr(mm, bp_vaddr); + } else { + *is_swbp = -EFAULT; + } + up_read(&mm->mmap_sem); + + return uprobe; +} + /* * Run handler and ask thread to singlestep. * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. */ static void handle_swbp(struct pt_regs *regs) { - struct vm_area_struct *vma; struct uprobe_task *utask; struct uprobe *uprobe; - struct mm_struct *mm; unsigned long bp_vaddr; + int uninitialized_var(is_swbp); - uprobe = NULL; bp_vaddr = uprobe_get_swbp_addr(regs); - mm = current->mm; - down_read(&mm->mmap_sem); - vma = find_vma(mm, bp_vaddr); - - if (vma && vma->vm_start <= bp_vaddr && valid_vma(vma, false)) { - struct inode *inode; - loff_t offset; - - inode = vma->vm_file->f_mapping->host; - offset = bp_vaddr - vma->vm_start; - offset += (vma->vm_pgoff << PAGE_SHIFT); - uprobe = find_uprobe(inode, offset); - } - - srcu_read_unlock_raw(&uprobes_srcu, current->uprobe_srcu_id); - current->uprobe_srcu_id = -1; - up_read(&mm->mmap_sem); + uprobe = find_active_uprobe(bp_vaddr, &is_swbp); if (!uprobe) { - /* No matching uprobe; signal SIGTRAP. */ - send_sig(SIGTRAP, current, 0); + if (is_swbp > 0) { + /* No matching uprobe; signal SIGTRAP. */ + send_sig(SIGTRAP, current, 0); + } else { + /* + * Either we raced with uprobe_unregister() or we can't + * access this memory. The latter is only possible if + * another thread plays with our ->mm. In both cases + * we can simply restart. If this vma was unmapped we + * can pretend this insn was not executed yet and get + * the (correct) SIGSEGV after restart. + */ + instruction_pointer_set(regs, bp_vaddr); + } return; } @@ -1620,7 +1617,6 @@ int uprobe_pre_sstep_notifier(struct pt_regs *regs) utask->state = UTASK_BP_HIT; set_thread_flag(TIF_UPROBE); - current->uprobe_srcu_id = srcu_read_lock_raw(&uprobes_srcu); return 1; } @@ -1655,7 +1651,6 @@ static int __init init_uprobes(void) mutex_init(&uprobes_mutex[i]); mutex_init(&uprobes_mmap_mutex[i]); } - init_srcu_struct(&uprobes_srcu); return register_die_notifier(&uprobe_exception_nb); } diff --git a/kernel/exit.c b/kernel/exit.c index 2f59cc334516..d17f6c4ddfa9 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -953,14 +953,11 @@ void do_exit(long code) exit_signals(tsk); /* sets PF_EXITING */ /* * tsk->flags are checked in the futex code to protect against - * an exiting task cleaning up the robust pi futexes, and in - * task_work_add() to avoid the race with exit_task_work(). + * an exiting task cleaning up the robust pi futexes. */ smp_mb(); raw_spin_unlock_wait(&tsk->pi_lock); - exit_task_work(tsk); - if (unlikely(in_atomic())) printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n", current->comm, task_pid_nr(current), @@ -995,6 +992,7 @@ void do_exit(long code) exit_shm(tsk); exit_files(tsk); exit_fs(tsk); + exit_task_work(tsk); check_stack_usage(); exit_thread(); diff --git a/kernel/fork.c b/kernel/fork.c index ab5211b9e622..ff1cad3b7bdc 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -304,12 +304,17 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) } err = arch_dup_task_struct(tsk, orig); - if (err) - goto out; + /* + * We defer looking at err, because we will need this setup + * for the clean up path to work correctly. + */ tsk->stack = ti; - setup_thread_stack(tsk, orig); + + if (err) + goto out; + clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); stackend = end_of_stack(tsk); @@ -1415,7 +1420,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, */ p->group_leader = p; INIT_LIST_HEAD(&p->thread_group); - INIT_HLIST_HEAD(&p->task_works); + p->task_works = NULL; /* Now that the task is set up, run cgroup callbacks if * necessary. We need to run them before the task is visible diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index ae34bf51682b..6db7a5ed52b5 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -657,6 +657,14 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, return 0; } +static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) +{ + ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; + ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; + + return ktime_get_update_offsets(offs_real, offs_boot); +} + /* * Retrigger next event is called after clock was set * @@ -665,22 +673,12 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, static void retrigger_next_event(void *arg) { struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases); - struct timespec realtime_offset, xtim, wtm, sleep; if (!hrtimer_hres_active()) return; - /* Optimized out for !HIGH_RES */ - get_xtime_and_monotonic_and_sleep_offset(&xtim, &wtm, &sleep); - set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec); - - /* Adjust CLOCK_REALTIME offset */ raw_spin_lock(&base->lock); - base->clock_base[HRTIMER_BASE_REALTIME].offset = - timespec_to_ktime(realtime_offset); - base->clock_base[HRTIMER_BASE_BOOTTIME].offset = - timespec_to_ktime(sleep); - + hrtimer_update_base(base); hrtimer_force_reprogram(base, 0); raw_spin_unlock(&base->lock); } @@ -710,13 +708,25 @@ static int hrtimer_switch_to_hres(void) base->clock_base[i].resolution = KTIME_HIGH_RES; tick_setup_sched_timer(); - /* "Retrigger" the interrupt to get things going */ retrigger_next_event(NULL); local_irq_restore(flags); return 1; } +/* + * Called from timekeeping code to reprogramm the hrtimer interrupt + * device. If called from the timer interrupt context we defer it to + * softirq context. + */ +void clock_was_set_delayed(void) +{ + struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); + + cpu_base->clock_was_set = 1; + __raise_softirq_irqoff(HRTIMER_SOFTIRQ); +} + #else static inline int hrtimer_hres_active(void) { return 0; } @@ -1250,11 +1260,10 @@ void hrtimer_interrupt(struct clock_event_device *dev) cpu_base->nr_events++; dev->next_event.tv64 = KTIME_MAX; - entry_time = now = ktime_get(); + raw_spin_lock(&cpu_base->lock); + entry_time = now = hrtimer_update_base(cpu_base); retry: expires_next.tv64 = KTIME_MAX; - - raw_spin_lock(&cpu_base->lock); /* * We set expires_next to KTIME_MAX here with cpu_base->lock * held to prevent that a timer is enqueued in our queue via @@ -1330,8 +1339,12 @@ retry: * We need to prevent that we loop forever in the hrtimer * interrupt routine. We give it 3 attempts to avoid * overreacting on some spurious event. + * + * Acquire base lock for updating the offsets and retrieving + * the current time. */ - now = ktime_get(); + raw_spin_lock(&cpu_base->lock); + now = hrtimer_update_base(cpu_base); cpu_base->nr_retries++; if (++retries < 3) goto retry; @@ -1343,6 +1356,7 @@ retry: */ cpu_base->nr_hangs++; cpu_base->hang_detected = 1; + raw_spin_unlock(&cpu_base->lock); delta = ktime_sub(now, entry_time); if (delta.tv64 > cpu_base->max_hang_time.tv64) cpu_base->max_hang_time = delta; @@ -1395,6 +1409,13 @@ void hrtimer_peek_ahead_timers(void) static void run_hrtimer_softirq(struct softirq_action *h) { + struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); + + if (cpu_base->clock_was_set) { + cpu_base->clock_was_set = 0; + clock_was_set(); + } + hrtimer_peek_ahead_timers(); } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 8c548232ba39..814c9ef6bba1 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -781,7 +781,7 @@ static void wake_threads_waitq(struct irq_desc *desc) wake_up(&desc->wait_for_threads); } -static void irq_thread_dtor(struct task_work *unused) +static void irq_thread_dtor(struct callback_head *unused) { struct task_struct *tsk = current; struct irq_desc *desc; @@ -813,7 +813,7 @@ static void irq_thread_dtor(struct task_work *unused) */ static int irq_thread(void *data) { - struct task_work on_exit_work; + struct callback_head on_exit_work; static const struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO/2, }; @@ -830,7 +830,7 @@ static int irq_thread(void *data) sched_setscheduler(current, SCHED_FIFO, ¶m); - init_task_work(&on_exit_work, irq_thread_dtor, NULL); + init_task_work(&on_exit_work, irq_thread_dtor); task_work_add(current, &on_exit_work, false); while (!irq_wait_for_interrupt(action)) { diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 8f9b4eb974e0..a70518c9d82f 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -175,7 +175,7 @@ config PM_TEST_SUSPEND You probably want to have your system's RTC driver statically linked, ensuring that it's available when this test runs. -config CAN_PM_TRACE +config PM_SLEEP_DEBUG def_bool y depends on PM_DEBUG && PM_SLEEP @@ -196,7 +196,7 @@ config PM_TRACE config PM_TRACE_RTC bool "Suspend/resume event tracing" - depends on CAN_PM_TRACE + depends on PM_SLEEP_DEBUG depends on X86 select PM_TRACE ---help--- diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 8b53db38a279..b26f5f1e773e 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -5,6 +5,7 @@ * Copyright (c) 2003 Open Source Development Lab * Copyright (c) 2004 Pavel Machek <pavel@ucw.cz> * Copyright (c) 2009 Rafael J. Wysocki, Novell Inc. + * Copyright (C) 2012 Bojan Smojver <bojan@rexursive.com> * * This file is released under the GPLv2. */ @@ -27,7 +28,6 @@ #include <linux/syscore_ops.h> #include <linux/ctype.h> #include <linux/genhd.h> -#include <scsi/scsi_scan.h> #include "power.h" @@ -46,6 +46,9 @@ enum { HIBERNATION_PLATFORM, HIBERNATION_SHUTDOWN, HIBERNATION_REBOOT, +#ifdef CONFIG_SUSPEND + HIBERNATION_SUSPEND, +#endif /* keep last */ __HIBERNATION_AFTER_LAST }; @@ -354,6 +357,7 @@ int hibernation_snapshot(int platform_mode) } suspend_console(); + ftrace_stop(); pm_restrict_gfp_mask(); error = dpm_suspend(PMSG_FREEZE); @@ -379,6 +383,7 @@ int hibernation_snapshot(int platform_mode) if (error || !in_suspend) pm_restore_gfp_mask(); + ftrace_start(); resume_console(); dpm_complete(msg); @@ -481,6 +486,7 @@ int hibernation_restore(int platform_mode) pm_prepare_console(); suspend_console(); + ftrace_stop(); pm_restrict_gfp_mask(); error = dpm_suspend_start(PMSG_QUIESCE); if (!error) { @@ -488,6 +494,7 @@ int hibernation_restore(int platform_mode) dpm_resume_end(PMSG_RECOVER); } pm_restore_gfp_mask(); + ftrace_start(); resume_console(); pm_restore_console(); return error; @@ -514,6 +521,7 @@ int hibernation_platform_enter(void) entering_platform_hibernation = true; suspend_console(); + ftrace_stop(); error = dpm_suspend_start(PMSG_HIBERNATE); if (error) { if (hibernation_ops->recover) @@ -557,6 +565,7 @@ int hibernation_platform_enter(void) Resume_devices: entering_platform_hibernation = false; dpm_resume_end(PMSG_RESTORE); + ftrace_start(); resume_console(); Close: @@ -574,6 +583,10 @@ int hibernation_platform_enter(void) */ static void power_down(void) { +#ifdef CONFIG_SUSPEND + int error; +#endif + switch (hibernation_mode) { case HIBERNATION_REBOOT: kernel_restart(NULL); @@ -583,6 +596,25 @@ static void power_down(void) case HIBERNATION_SHUTDOWN: kernel_power_off(); break; +#ifdef CONFIG_SUSPEND + case HIBERNATION_SUSPEND: + error = suspend_devices_and_enter(PM_SUSPEND_MEM); + if (error) { + if (hibernation_ops) + hibernation_mode = HIBERNATION_PLATFORM; + else + hibernation_mode = HIBERNATION_SHUTDOWN; + power_down(); + } + /* + * Restore swap signature. + */ + error = swsusp_unmark(); + if (error) + printk(KERN_ERR "PM: Swap will be unusable! " + "Try swapon -a.\n"); + return; +#endif } kernel_halt(); /* @@ -748,13 +780,6 @@ static int software_resume(void) async_synchronize_full(); } - /* - * We can't depend on SCSI devices being available after loading - * one of their modules until scsi_complete_async_scans() is - * called and the resume device usually is a SCSI one. - */ - scsi_complete_async_scans(); - swsusp_resume_device = name_to_dev_t(resume_file); if (!swsusp_resume_device) { error = -ENODEV; @@ -827,6 +852,9 @@ static const char * const hibernation_modes[] = { [HIBERNATION_PLATFORM] = "platform", [HIBERNATION_SHUTDOWN] = "shutdown", [HIBERNATION_REBOOT] = "reboot", +#ifdef CONFIG_SUSPEND + [HIBERNATION_SUSPEND] = "suspend", +#endif }; /* @@ -867,6 +895,9 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr, switch (i) { case HIBERNATION_SHUTDOWN: case HIBERNATION_REBOOT: +#ifdef CONFIG_SUSPEND + case HIBERNATION_SUSPEND: +#endif break; case HIBERNATION_PLATFORM: if (hibernation_ops) @@ -907,6 +938,9 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, switch (mode) { case HIBERNATION_SHUTDOWN: case HIBERNATION_REBOOT: +#ifdef CONFIG_SUSPEND + case HIBERNATION_SUSPEND: +#endif hibernation_mode = mode; break; case HIBERNATION_PLATFORM: diff --git a/kernel/power/main.c b/kernel/power/main.c index 428f8a034e96..f458238109cc 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -235,6 +235,47 @@ late_initcall(pm_debugfs_init); #endif /* CONFIG_PM_SLEEP */ +#ifdef CONFIG_PM_SLEEP_DEBUG +/* + * pm_print_times: print time taken by devices to suspend and resume. + * + * show() returns whether printing of suspend and resume times is enabled. + * store() accepts 0 or 1. 0 disables printing and 1 enables it. + */ +bool pm_print_times_enabled; + +static ssize_t pm_print_times_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", pm_print_times_enabled); +} + +static ssize_t pm_print_times_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + unsigned long val; + + if (kstrtoul(buf, 10, &val)) + return -EINVAL; + + if (val > 1) + return -EINVAL; + + pm_print_times_enabled = !!val; + return n; +} + +power_attr(pm_print_times); + +static inline void pm_print_times_init(void) +{ + pm_print_times_enabled = !!initcall_debug; +} +#else /* !CONFIG_PP_SLEEP_DEBUG */ +static inline void pm_print_times_init(void) {} +#endif /* CONFIG_PM_SLEEP_DEBUG */ + struct kobject *power_kobj; /** @@ -531,6 +572,9 @@ static struct attribute * g[] = { #ifdef CONFIG_PM_DEBUG &pm_test_attr.attr, #endif +#ifdef CONFIG_PM_SLEEP_DEBUG + &pm_print_times_attr.attr, +#endif #endif NULL, }; @@ -566,6 +610,7 @@ static int __init pm_init(void) error = sysfs_create_group(power_kobj, &attr_group); if (error) return error; + pm_print_times_init(); return pm_autosleep_init(); } diff --git a/kernel/power/power.h b/kernel/power/power.h index b0bd4beaebfe..7d4b7ffb3c1d 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -156,6 +156,9 @@ extern void swsusp_free(void); extern int swsusp_read(unsigned int *flags_p); extern int swsusp_write(unsigned int flags); extern void swsusp_close(fmode_t); +#ifdef CONFIG_SUSPEND +extern int swsusp_unmark(void); +#endif /* kernel/power/block_io.c */ extern struct block_device *hib_resume_bdev; diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 396d262b8fd0..c8b7446b27df 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -24,6 +24,7 @@ #include <linux/export.h> #include <linux/suspend.h> #include <linux/syscore_ops.h> +#include <linux/ftrace.h> #include <trace/events/power.h> #include "power.h" @@ -212,6 +213,7 @@ int suspend_devices_and_enter(suspend_state_t state) goto Close; } suspend_console(); + ftrace_stop(); suspend_test_start(); error = dpm_suspend_start(PMSG_SUSPEND); if (error) { @@ -231,6 +233,7 @@ int suspend_devices_and_enter(suspend_state_t state) suspend_test_start(); dpm_resume_end(PMSG_RESUME); suspend_test_finish("resume devices"); + ftrace_start(); resume_console(); Close: if (suspend_ops->end) diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 11e22c068e8b..3c9d764eb0d8 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -448,9 +448,9 @@ static int save_image(struct swap_map_handle *handle, struct timeval start; struct timeval stop; - printk(KERN_INFO "PM: Saving image data pages (%u pages) ... ", + printk(KERN_INFO "PM: Saving image data pages (%u pages)...\n", nr_to_write); - m = nr_to_write / 100; + m = nr_to_write / 10; if (!m) m = 1; nr_pages = 0; @@ -464,7 +464,8 @@ static int save_image(struct swap_map_handle *handle, if (ret) break; if (!(nr_pages % m)) - printk(KERN_CONT "\b\b\b\b%3d%%", nr_pages / m); + printk(KERN_INFO "PM: Image saving progress: %3d%%\n", + nr_pages / m * 10); nr_pages++; } err2 = hib_wait_on_bio_chain(&bio); @@ -472,9 +473,7 @@ static int save_image(struct swap_map_handle *handle, if (!ret) ret = err2; if (!ret) - printk(KERN_CONT "\b\b\b\bdone\n"); - else - printk(KERN_CONT "\n"); + printk(KERN_INFO "PM: Image saving done.\n"); swsusp_show_speed(&start, &stop, nr_to_write, "Wrote"); return ret; } @@ -668,9 +667,9 @@ static int save_image_lzo(struct swap_map_handle *handle, printk(KERN_INFO "PM: Using %u thread(s) for compression.\n" - "PM: Compressing and saving image data (%u pages) ... ", + "PM: Compressing and saving image data (%u pages)...\n", nr_threads, nr_to_write); - m = nr_to_write / 100; + m = nr_to_write / 10; if (!m) m = 1; nr_pages = 0; @@ -690,8 +689,10 @@ static int save_image_lzo(struct swap_map_handle *handle, data_of(*snapshot), PAGE_SIZE); if (!(nr_pages % m)) - printk(KERN_CONT "\b\b\b\b%3d%%", - nr_pages / m); + printk(KERN_INFO + "PM: Image saving progress: " + "%3d%%\n", + nr_pages / m * 10); nr_pages++; } if (!off) @@ -761,11 +762,8 @@ out_finish: do_gettimeofday(&stop); if (!ret) ret = err2; - if (!ret) { - printk(KERN_CONT "\b\b\b\bdone\n"); - } else { - printk(KERN_CONT "\n"); - } + if (!ret) + printk(KERN_INFO "PM: Image saving done.\n"); swsusp_show_speed(&start, &stop, nr_to_write, "Wrote"); out_clean: if (crc) { @@ -973,9 +971,9 @@ static int load_image(struct swap_map_handle *handle, int err2; unsigned nr_pages; - printk(KERN_INFO "PM: Loading image data pages (%u pages) ... ", + printk(KERN_INFO "PM: Loading image data pages (%u pages)...\n", nr_to_read); - m = nr_to_read / 100; + m = nr_to_read / 10; if (!m) m = 1; nr_pages = 0; @@ -993,7 +991,8 @@ static int load_image(struct swap_map_handle *handle, if (ret) break; if (!(nr_pages % m)) - printk("\b\b\b\b%3d%%", nr_pages / m); + printk(KERN_INFO "PM: Image loading progress: %3d%%\n", + nr_pages / m * 10); nr_pages++; } err2 = hib_wait_on_bio_chain(&bio); @@ -1001,12 +1000,11 @@ static int load_image(struct swap_map_handle *handle, if (!ret) ret = err2; if (!ret) { - printk("\b\b\b\bdone\n"); + printk(KERN_INFO "PM: Image loading done.\n"); snapshot_write_finalize(snapshot); if (!snapshot_image_loaded(snapshot)) ret = -ENODATA; - } else - printk("\n"); + } swsusp_show_speed(&start, &stop, nr_to_read, "Read"); return ret; } @@ -1185,9 +1183,9 @@ static int load_image_lzo(struct swap_map_handle *handle, printk(KERN_INFO "PM: Using %u thread(s) for decompression.\n" - "PM: Loading and decompressing image data (%u pages) ... ", + "PM: Loading and decompressing image data (%u pages)...\n", nr_threads, nr_to_read); - m = nr_to_read / 100; + m = nr_to_read / 10; if (!m) m = 1; nr_pages = 0; @@ -1319,7 +1317,10 @@ static int load_image_lzo(struct swap_map_handle *handle, data[thr].unc + off, PAGE_SIZE); if (!(nr_pages % m)) - printk("\b\b\b\b%3d%%", nr_pages / m); + printk(KERN_INFO + "PM: Image loading progress: " + "%3d%%\n", + nr_pages / m * 10); nr_pages++; ret = snapshot_write_next(snapshot); @@ -1344,7 +1345,7 @@ out_finish: } do_gettimeofday(&stop); if (!ret) { - printk("\b\b\b\bdone\n"); + printk(KERN_INFO "PM: Image loading done.\n"); snapshot_write_finalize(snapshot); if (!snapshot_image_loaded(snapshot)) ret = -ENODATA; @@ -1357,8 +1358,7 @@ out_finish: } } } - } else - printk("\n"); + } swsusp_show_speed(&start, &stop, nr_to_read, "Read"); out_clean: for (i = 0; i < ring_size; i++) @@ -1472,6 +1472,34 @@ void swsusp_close(fmode_t mode) blkdev_put(hib_resume_bdev, mode); } +/** + * swsusp_unmark - Unmark swsusp signature in the resume device + */ + +#ifdef CONFIG_SUSPEND +int swsusp_unmark(void) +{ + int error; + + hib_bio_read_page(swsusp_resume_block, swsusp_header, NULL); + if (!memcmp(HIBERNATE_SIG,swsusp_header->sig, 10)) { + memcpy(swsusp_header->sig,swsusp_header->orig_sig, 10); + error = hib_bio_write_page(swsusp_resume_block, + swsusp_header, NULL); + } else { + printk(KERN_ERR "PM: Cannot find swsusp signature!\n"); + error = -ENODEV; + } + + /* + * We just returned from suspend, we don't need the image any more. + */ + free_all_swap_pages(root_swap); + + return error; +} +#endif + static int swsusp_header_init(void) { swsusp_header = (struct swsusp_header*) __get_free_page(GFP_KERNEL); diff --git a/kernel/power/user.c b/kernel/power/user.c index 91b0fd021a95..4ed81e74f86f 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -24,7 +24,6 @@ #include <linux/console.h> #include <linux/cpu.h> #include <linux/freezer.h> -#include <scsi/scsi_scan.h> #include <asm/uaccess.h> @@ -84,7 +83,6 @@ static int snapshot_open(struct inode *inode, struct file *filp) * appear. */ wait_for_device_probe(); - scsi_complete_async_scans(); data->swap = -1; data->mode = O_WRONLY; diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c index c8fba3380076..8f50de394d22 100644 --- a/kernel/power/wakelock.c +++ b/kernel/power/wakelock.c @@ -9,6 +9,7 @@ * manipulate wakelocks on Android. */ +#include <linux/capability.h> #include <linux/ctype.h> #include <linux/device.h> #include <linux/err.h> @@ -188,6 +189,9 @@ int pm_wake_lock(const char *buf) size_t len; int ret = 0; + if (!capable(CAP_BLOCK_SUSPEND)) + return -EPERM; + while (*str && !isspace(*str)) str++; @@ -231,6 +235,9 @@ int pm_wake_unlock(const char *buf) size_t len; int ret = 0; + if (!capable(CAP_BLOCK_SUSPEND)) + return -EPERM; + len = strlen(buf); if (!len) return -EINVAL; diff --git a/kernel/printk.c b/kernel/printk.c index dba18211685e..ac4bc9e79465 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -194,8 +194,10 @@ static int console_may_schedule; */ enum log_flags { - LOG_DEFAULT = 0, - LOG_NOCONS = 1, /* already flushed, do not print to console */ + LOG_NOCONS = 1, /* already flushed, do not print to console */ + LOG_NEWLINE = 2, /* text ended with a newline */ + LOG_PREFIX = 4, /* text started with a prefix */ + LOG_CONT = 8, /* text is a fragment of a continuation line */ }; struct log { @@ -217,6 +219,8 @@ static DEFINE_RAW_SPINLOCK(logbuf_lock); /* the next printk record to read by syslog(READ) or /proc/kmsg */ static u64 syslog_seq; static u32 syslog_idx; +static enum log_flags syslog_prev; +static size_t syslog_partial; /* index and sequence number of the first record stored in the buffer */ static u64 log_first_seq; @@ -430,20 +434,20 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, ret = mutex_lock_interruptible(&user->lock); if (ret) return ret; - raw_spin_lock(&logbuf_lock); + raw_spin_lock_irq(&logbuf_lock); while (user->seq == log_next_seq) { if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; - raw_spin_unlock(&logbuf_lock); + raw_spin_unlock_irq(&logbuf_lock); goto out; } - raw_spin_unlock(&logbuf_lock); + raw_spin_unlock_irq(&logbuf_lock); ret = wait_event_interruptible(log_wait, user->seq != log_next_seq); if (ret) goto out; - raw_spin_lock(&logbuf_lock); + raw_spin_lock_irq(&logbuf_lock); } if (user->seq < log_first_seq) { @@ -451,7 +455,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, user->idx = log_first_idx; user->seq = log_first_seq; ret = -EPIPE; - raw_spin_unlock(&logbuf_lock); + raw_spin_unlock_irq(&logbuf_lock); goto out; } @@ -465,7 +469,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, for (i = 0; i < msg->text_len; i++) { unsigned char c = log_text(msg)[i]; - if (c < ' ' || c >= 128) + if (c < ' ' || c >= 127 || c == '\\') len += sprintf(user->buf + len, "\\x%02x", c); else user->buf[len++] = c; @@ -489,7 +493,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, continue; } - if (c < ' ' || c >= 128) { + if (c < ' ' || c >= 127 || c == '\\') { len += sprintf(user->buf + len, "\\x%02x", c); continue; } @@ -501,7 +505,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, user->idx = log_next(user->idx); user->seq++; - raw_spin_unlock(&logbuf_lock); + raw_spin_unlock_irq(&logbuf_lock); if (len > count) { ret = -EINVAL; @@ -528,7 +532,7 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) if (offset) return -ESPIPE; - raw_spin_lock(&logbuf_lock); + raw_spin_lock_irq(&logbuf_lock); switch (whence) { case SEEK_SET: /* the first record */ @@ -552,7 +556,7 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) default: ret = -EINVAL; } - raw_spin_unlock(&logbuf_lock); + raw_spin_unlock_irq(&logbuf_lock); return ret; } @@ -566,14 +570,14 @@ static unsigned int devkmsg_poll(struct file *file, poll_table *wait) poll_wait(file, &log_wait, wait); - raw_spin_lock(&logbuf_lock); + raw_spin_lock_irq(&logbuf_lock); if (user->seq < log_next_seq) { /* return error when data has vanished underneath us */ if (user->seq < log_first_seq) ret = POLLIN|POLLRDNORM|POLLERR|POLLPRI; ret = POLLIN|POLLRDNORM; } - raw_spin_unlock(&logbuf_lock); + raw_spin_unlock_irq(&logbuf_lock); return ret; } @@ -597,10 +601,10 @@ static int devkmsg_open(struct inode *inode, struct file *file) mutex_init(&user->lock); - raw_spin_lock(&logbuf_lock); + raw_spin_lock_irq(&logbuf_lock); user->idx = log_first_idx; user->seq = log_first_seq; - raw_spin_unlock(&logbuf_lock); + raw_spin_unlock_irq(&logbuf_lock); file->private_data = user; return 0; @@ -818,15 +822,18 @@ static size_t print_time(u64 ts, char *buf) static size_t print_prefix(const struct log *msg, bool syslog, char *buf) { size_t len = 0; + unsigned int prefix = (msg->facility << 3) | msg->level; if (syslog) { if (buf) { - len += sprintf(buf, "<%u>", msg->level); + len += sprintf(buf, "<%u>", prefix); } else { len += 3; - if (msg->level > 9) - len++; - if (msg->level > 99) + if (prefix > 999) + len += 3; + else if (prefix > 99) + len += 2; + else if (prefix > 9) len++; } } @@ -835,13 +842,26 @@ static size_t print_prefix(const struct log *msg, bool syslog, char *buf) return len; } -static size_t msg_print_text(const struct log *msg, bool syslog, - char *buf, size_t size) +static size_t msg_print_text(const struct log *msg, enum log_flags prev, + bool syslog, char *buf, size_t size) { const char *text = log_text(msg); size_t text_size = msg->text_len; + bool prefix = true; + bool newline = true; size_t len = 0; + if ((prev & LOG_CONT) && !(msg->flags & LOG_PREFIX)) + prefix = false; + + if (msg->flags & LOG_CONT) { + if ((prev & LOG_CONT) && !(prev & LOG_NEWLINE)) + prefix = false; + + if (!(msg->flags & LOG_NEWLINE)) + newline = false; + } + do { const char *next = memchr(text, '\n', text_size); size_t text_len; @@ -859,16 +879,22 @@ static size_t msg_print_text(const struct log *msg, bool syslog, text_len + 1>= size - len) break; - len += print_prefix(msg, syslog, buf + len); + if (prefix) + len += print_prefix(msg, syslog, buf + len); memcpy(buf + len, text, text_len); len += text_len; - buf[len++] = '\n'; + if (next || newline) + buf[len++] = '\n'; } else { /* SYSLOG_ACTION_* buffer size only calculation */ - len += print_prefix(msg, syslog, NULL); - len += text_len + 1; + if (prefix) + len += print_prefix(msg, syslog, NULL); + len += text_len; + if (next || newline) + len++; } + prefix = true; text = next; } while (text); @@ -887,22 +913,35 @@ static int syslog_print(char __user *buf, int size) while (size > 0) { size_t n; + size_t skip; raw_spin_lock_irq(&logbuf_lock); if (syslog_seq < log_first_seq) { /* messages are gone, move to first one */ syslog_seq = log_first_seq; syslog_idx = log_first_idx; + syslog_prev = 0; + syslog_partial = 0; } if (syslog_seq == log_next_seq) { raw_spin_unlock_irq(&logbuf_lock); break; } + + skip = syslog_partial; msg = log_from_idx(syslog_idx); - n = msg_print_text(msg, true, text, LOG_LINE_MAX); - if (n <= size) { + n = msg_print_text(msg, syslog_prev, true, text, LOG_LINE_MAX); + if (n - syslog_partial <= size) { + /* message fits into buffer, move forward */ syslog_idx = log_next(syslog_idx); syslog_seq++; + syslog_prev = msg->flags; + n -= syslog_partial; + syslog_partial = 0; + } else if (!len){ + /* partial read(), remember position */ + n = size; + syslog_partial += n; } else n = 0; raw_spin_unlock_irq(&logbuf_lock); @@ -910,17 +949,15 @@ static int syslog_print(char __user *buf, int size) if (!n) break; - len += n; - size -= n; - buf += n; - n = copy_to_user(buf - n, text, n); - - if (n) { - len -= n; + if (copy_to_user(buf, text + skip, n)) { if (!len) len = -EFAULT; break; } + + len += n; + size -= n; + buf += n; } kfree(text); @@ -941,6 +978,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) u64 next_seq; u64 seq; u32 idx; + enum log_flags prev; if (clear_seq < log_first_seq) { /* messages are gone, move to first available one */ @@ -954,10 +992,11 @@ static int syslog_print_all(char __user *buf, int size, bool clear) */ seq = clear_seq; idx = clear_idx; + prev = 0; while (seq < log_next_seq) { struct log *msg = log_from_idx(idx); - len += msg_print_text(msg, true, NULL, 0); + len += msg_print_text(msg, prev, true, NULL, 0); idx = log_next(idx); seq++; } @@ -965,10 +1004,11 @@ static int syslog_print_all(char __user *buf, int size, bool clear) /* move first record forward until length fits into the buffer */ seq = clear_seq; idx = clear_idx; + prev = 0; while (len > size && seq < log_next_seq) { struct log *msg = log_from_idx(idx); - len -= msg_print_text(msg, true, NULL, 0); + len -= msg_print_text(msg, prev, true, NULL, 0); idx = log_next(idx); seq++; } @@ -977,17 +1017,19 @@ static int syslog_print_all(char __user *buf, int size, bool clear) next_seq = log_next_seq; len = 0; + prev = 0; while (len >= 0 && seq < next_seq) { struct log *msg = log_from_idx(idx); int textlen; - textlen = msg_print_text(msg, true, text, LOG_LINE_MAX); + textlen = msg_print_text(msg, prev, true, text, LOG_LINE_MAX); if (textlen < 0) { len = textlen; break; } idx = log_next(idx); seq++; + prev = msg->flags; raw_spin_unlock_irq(&logbuf_lock); if (copy_to_user(buf + len, text, textlen)) @@ -1000,6 +1042,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) /* messages are gone, move to next one */ seq = log_first_seq; idx = log_first_idx; + prev = 0; } } } @@ -1018,7 +1061,6 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) { bool clear = false; static int saved_console_loglevel = -1; - static DEFINE_MUTEX(syslog_mutex); int error; error = check_syslog_permissions(type, from_file); @@ -1045,17 +1087,11 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) error = -EFAULT; goto out; } - error = mutex_lock_interruptible(&syslog_mutex); - if (error) - goto out; error = wait_event_interruptible(log_wait, syslog_seq != log_next_seq); - if (error) { - mutex_unlock(&syslog_mutex); + if (error) goto out; - } error = syslog_print(buf, len); - mutex_unlock(&syslog_mutex); break; /* Read/clear last kernel messages */ case SYSLOG_ACTION_READ_CLEAR: @@ -1111,6 +1147,8 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) /* messages are gone, move to first one */ syslog_seq = log_first_seq; syslog_idx = log_first_idx; + syslog_prev = 0; + syslog_partial = 0; } if (from_file) { /* @@ -1120,19 +1158,20 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) */ error = log_next_idx - syslog_idx; } else { - u64 seq; - u32 idx; + u64 seq = syslog_seq; + u32 idx = syslog_idx; + enum log_flags prev = syslog_prev; error = 0; - seq = syslog_seq; - idx = syslog_idx; while (seq < log_next_seq) { struct log *msg = log_from_idx(idx); - error += msg_print_text(msg, true, NULL, 0); + error += msg_print_text(msg, prev, true, NULL, 0); idx = log_next(idx); seq++; + prev = msg->flags; } + error -= syslog_partial; } raw_spin_unlock_irq(&logbuf_lock); break; @@ -1153,21 +1192,6 @@ SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) return do_syslog(type, buf, len, SYSLOG_FROM_CALL); } -#ifdef CONFIG_KGDB_KDB -/* kdb dmesg command needs access to the syslog buffer. do_syslog() - * uses locks so it cannot be used during debugging. Just tell kdb - * where the start and end of the physical and logical logs are. This - * is equivalent to do_syslog(3). - */ -void kdb_syslog_data(char *syslog_data[4]) -{ - syslog_data[0] = log_buf; - syslog_data[1] = log_buf + log_buf_len; - syslog_data[2] = log_buf + log_first_idx; - syslog_data[3] = log_buf + log_next_idx; -} -#endif /* CONFIG_KGDB_KDB */ - static bool __read_mostly ignore_loglevel; static int __init ignore_loglevel_setup(char *str) @@ -1400,10 +1424,9 @@ asmlinkage int vprintk_emit(int facility, int level, static char textbuf[LOG_LINE_MAX]; char *text = textbuf; size_t text_len; + enum log_flags lflags = 0; unsigned long flags; int this_cpu; - bool newline = false; - bool prefix = false; int printed_len = 0; boot_delay_msec(); @@ -1442,7 +1465,7 @@ asmlinkage int vprintk_emit(int facility, int level, recursion_bug = 0; printed_len += strlen(recursion_msg); /* emit KERN_CRIT message */ - log_store(0, 2, LOG_DEFAULT, 0, + log_store(0, 2, LOG_PREFIX|LOG_NEWLINE, 0, NULL, 0, recursion_msg, printed_len); } @@ -1455,7 +1478,7 @@ asmlinkage int vprintk_emit(int facility, int level, /* mark and strip a trailing newline */ if (text_len && text[text_len-1] == '\n') { text_len--; - newline = true; + lflags |= LOG_NEWLINE; } /* strip syslog prefix and extract log level or control flags */ @@ -1465,7 +1488,7 @@ asmlinkage int vprintk_emit(int facility, int level, if (level == -1) level = text[1] - '0'; case 'd': /* KERN_DEFAULT */ - prefix = true; + lflags |= LOG_PREFIX; case 'c': /* KERN_CONT */ text += 3; text_len -= 3; @@ -1475,22 +1498,20 @@ asmlinkage int vprintk_emit(int facility, int level, if (level == -1) level = default_message_loglevel; - if (dict) { - prefix = true; - newline = true; - } + if (dict) + lflags |= LOG_PREFIX|LOG_NEWLINE; - if (!newline) { + if (!(lflags & LOG_NEWLINE)) { /* * Flush the conflicting buffer. An earlier newline was missing, * or another task also prints continuation lines. */ - if (cont.len && (prefix || cont.owner != current)) + if (cont.len && (lflags & LOG_PREFIX || cont.owner != current)) cont_flush(); /* buffer line if possible, otherwise store it right away */ if (!cont_add(facility, level, text, text_len)) - log_store(facility, level, LOG_DEFAULT, 0, + log_store(facility, level, lflags | LOG_CONT, 0, dict, dictlen, text, text_len); } else { bool stored = false; @@ -1502,13 +1523,13 @@ asmlinkage int vprintk_emit(int facility, int level, * flush it out and store this line separately. */ if (cont.len && cont.owner == current) { - if (!prefix) + if (!(lflags & LOG_PREFIX)) stored = cont_add(facility, level, text, text_len); cont_flush(); } if (!stored) - log_store(facility, level, LOG_DEFAULT, 0, + log_store(facility, level, lflags, 0, dict, dictlen, text, text_len); } printed_len += text_len; @@ -1607,8 +1628,8 @@ static struct cont { static struct log *log_from_idx(u32 idx) { return NULL; } static u32 log_next(u32 idx) { return 0; } static void call_console_drivers(int level, const char *text, size_t len) {} -static size_t msg_print_text(const struct log *msg, bool syslog, - char *buf, size_t size) { return 0; } +static size_t msg_print_text(const struct log *msg, enum log_flags prev, + bool syslog, char *buf, size_t size) { return 0; } static size_t cont_print_text(char *text, size_t size) { return 0; } #endif /* CONFIG_PRINTK */ @@ -1884,6 +1905,7 @@ void wake_up_klogd(void) /* the next printk record to write to the console */ static u64 console_seq; static u32 console_idx; +static enum log_flags console_prev; /** * console_unlock - unlock the console system @@ -1944,6 +1966,7 @@ again: /* messages are gone, move to first one */ console_seq = log_first_seq; console_idx = log_first_idx; + console_prev = 0; } skip: if (console_seq == log_next_seq) @@ -1957,14 +1980,21 @@ skip: */ console_idx = log_next(console_idx); console_seq++; + /* + * We will get here again when we register a new + * CON_PRINTBUFFER console. Clear the flag so we + * will properly dump everything later. + */ + msg->flags &= ~LOG_NOCONS; goto skip; } level = msg->level; - len = msg_print_text(msg, false, text, sizeof(text)); - + len = msg_print_text(msg, console_prev, false, + text, sizeof(text)); console_idx = log_next(console_idx); console_seq++; + console_prev = msg->flags; raw_spin_unlock(&logbuf_lock); stop_critical_timings(); /* don't trace print latency */ @@ -2227,6 +2257,7 @@ void register_console(struct console *newcon) raw_spin_lock_irqsave(&logbuf_lock, flags); console_seq = syslog_seq; console_idx = syslog_idx; + console_prev = syslog_prev; raw_spin_unlock_irqrestore(&logbuf_lock, flags); /* * We're about to replay the log buffer. Only do this to the @@ -2479,7 +2510,7 @@ void kmsg_dump(enum kmsg_dump_reason reason) } /** - * kmsg_dump_get_line - retrieve one kmsg log line + * kmsg_dump_get_line_nolock - retrieve one kmsg log line (unlocked version) * @dumper: registered kmsg dumper * @syslog: include the "<4>" prefixes * @line: buffer to copy the line to @@ -2494,11 +2525,12 @@ void kmsg_dump(enum kmsg_dump_reason reason) * * A return value of FALSE indicates that there are no more records to * read. + * + * The function is similar to kmsg_dump_get_line(), but grabs no locks. */ -bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, - char *line, size_t size, size_t *len) +bool kmsg_dump_get_line_nolock(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len) { - unsigned long flags; struct log *msg; size_t l = 0; bool ret = false; @@ -2506,7 +2538,6 @@ bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, if (!dumper->active) goto out; - raw_spin_lock_irqsave(&logbuf_lock, flags); if (dumper->cur_seq < log_first_seq) { /* messages are gone, move to first available one */ dumper->cur_seq = log_first_seq; @@ -2514,24 +2545,50 @@ bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, } /* last entry */ - if (dumper->cur_seq >= log_next_seq) { - raw_spin_unlock_irqrestore(&logbuf_lock, flags); + if (dumper->cur_seq >= log_next_seq) goto out; - } msg = log_from_idx(dumper->cur_idx); - l = msg_print_text(msg, syslog, - line, size); + l = msg_print_text(msg, 0, syslog, line, size); dumper->cur_idx = log_next(dumper->cur_idx); dumper->cur_seq++; ret = true; - raw_spin_unlock_irqrestore(&logbuf_lock, flags); out: if (len) *len = l; return ret; } + +/** + * kmsg_dump_get_line - retrieve one kmsg log line + * @dumper: registered kmsg dumper + * @syslog: include the "<4>" prefixes + * @line: buffer to copy the line to + * @size: maximum size of the buffer + * @len: length of line placed into buffer + * + * Start at the beginning of the kmsg buffer, with the oldest kmsg + * record, and copy one record into the provided buffer. + * + * Consecutive calls will return the next available record moving + * towards the end of the buffer with the youngest messages. + * + * A return value of FALSE indicates that there are no more records to + * read. + */ +bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog, + char *line, size_t size, size_t *len) +{ + unsigned long flags; + bool ret; + + raw_spin_lock_irqsave(&logbuf_lock, flags); + ret = kmsg_dump_get_line_nolock(dumper, syslog, line, size, len); + raw_spin_unlock_irqrestore(&logbuf_lock, flags); + + return ret; +} EXPORT_SYMBOL_GPL(kmsg_dump_get_line); /** @@ -2561,6 +2618,7 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, u32 idx; u64 next_seq; u32 next_idx; + enum log_flags prev; size_t l = 0; bool ret = false; @@ -2583,23 +2641,27 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, /* calculate length of entire buffer */ seq = dumper->cur_seq; idx = dumper->cur_idx; + prev = 0; while (seq < dumper->next_seq) { struct log *msg = log_from_idx(idx); - l += msg_print_text(msg, true, NULL, 0); + l += msg_print_text(msg, prev, true, NULL, 0); idx = log_next(idx); seq++; + prev = msg->flags; } /* move first record forward until length fits into the buffer */ seq = dumper->cur_seq; idx = dumper->cur_idx; + prev = 0; while (l > size && seq < dumper->next_seq) { struct log *msg = log_from_idx(idx); - l -= msg_print_text(msg, true, NULL, 0); + l -= msg_print_text(msg, prev, true, NULL, 0); idx = log_next(idx); seq++; + prev = msg->flags; } /* last message in next interation */ @@ -2607,14 +2669,14 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, next_idx = idx; l = 0; + prev = 0; while (seq < dumper->next_seq) { struct log *msg = log_from_idx(idx); - l += msg_print_text(msg, syslog, - buf + l, size - l); - + l += msg_print_text(msg, prev, syslog, buf + l, size - l); idx = log_next(idx); seq++; + prev = msg->flags; } dumper->next_seq = next_seq; @@ -2629,6 +2691,24 @@ out: EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); /** + * kmsg_dump_rewind_nolock - reset the interator (unlocked version) + * @dumper: registered kmsg dumper + * + * Reset the dumper's iterator so that kmsg_dump_get_line() and + * kmsg_dump_get_buffer() can be called again and used multiple + * times within the same dumper.dump() callback. + * + * The function is similar to kmsg_dump_rewind(), but grabs no locks. + */ +void kmsg_dump_rewind_nolock(struct kmsg_dumper *dumper) +{ + dumper->cur_seq = clear_seq; + dumper->cur_idx = clear_idx; + dumper->next_seq = log_next_seq; + dumper->next_idx = log_next_idx; +} + +/** * kmsg_dump_rewind - reset the interator * @dumper: registered kmsg dumper * @@ -2641,10 +2721,7 @@ void kmsg_dump_rewind(struct kmsg_dumper *dumper) unsigned long flags; raw_spin_lock_irqsave(&logbuf_lock, flags); - dumper->cur_seq = clear_seq; - dumper->cur_idx = clear_idx; - dumper->next_seq = log_next_seq; - dumper->next_idx = log_next_idx; + kmsg_dump_rewind_nolock(dumper); raw_spin_unlock_irqrestore(&logbuf_lock, flags); } EXPORT_SYMBOL_GPL(kmsg_dump_rewind); diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 95cba41ce1e9..4e6a61b15e86 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -54,6 +54,50 @@ #ifdef CONFIG_PREEMPT_RCU /* + * Preemptible RCU implementation for rcu_read_lock(). + * Just increment ->rcu_read_lock_nesting, shared state will be updated + * if we block. + */ +void __rcu_read_lock(void) +{ + current->rcu_read_lock_nesting++; + barrier(); /* critical section after entry code. */ +} +EXPORT_SYMBOL_GPL(__rcu_read_lock); + +/* + * Preemptible RCU implementation for rcu_read_unlock(). + * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost + * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then + * invoke rcu_read_unlock_special() to clean up after a context switch + * in an RCU read-side critical section and other special cases. + */ +void __rcu_read_unlock(void) +{ + struct task_struct *t = current; + + if (t->rcu_read_lock_nesting != 1) { + --t->rcu_read_lock_nesting; + } else { + barrier(); /* critical section before exit code. */ + t->rcu_read_lock_nesting = INT_MIN; + barrier(); /* assign before ->rcu_read_unlock_special load */ + if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) + rcu_read_unlock_special(t); + barrier(); /* ->rcu_read_unlock_special load before assign */ + t->rcu_read_lock_nesting = 0; + } +#ifdef CONFIG_PROVE_LOCKING + { + int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); + + WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); + } +#endif /* #ifdef CONFIG_PROVE_LOCKING */ +} +EXPORT_SYMBOL_GPL(__rcu_read_unlock); + +/* * Check for a task exiting while in a preemptible-RCU read-side * critical section, clean up if so. No need to issue warnings, * as debug_check_no_locks_held() already does this if lockdep diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 37a5444204d2..547b1fe5b052 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -172,7 +172,7 @@ void rcu_irq_enter(void) local_irq_restore(flags); } -#ifdef CONFIG_PROVE_RCU +#ifdef CONFIG_DEBUG_LOCK_ALLOC /* * Test whether RCU thinks that the current CPU is idle. @@ -183,7 +183,7 @@ int rcu_is_cpu_idle(void) } EXPORT_SYMBOL(rcu_is_cpu_idle); -#endif /* #ifdef CONFIG_PROVE_RCU */ +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /* * Test whether the current CPU was interrupted from idle. Nested diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index fc31a2d65100..918fd1e8509c 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -132,7 +132,6 @@ static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = { RCU_TRACE(.rcb.name = "rcu_preempt") }; -static void rcu_read_unlock_special(struct task_struct *t); static int rcu_preempted_readers_exp(void); static void rcu_report_exp_done(void); @@ -351,8 +350,9 @@ static int rcu_initiate_boost(void) rcu_preempt_ctrlblk.boost_tasks = rcu_preempt_ctrlblk.gp_tasks; invoke_rcu_callbacks(); - } else + } else { RCU_TRACE(rcu_initiate_boost_trace()); + } return 1; } @@ -527,23 +527,11 @@ void rcu_preempt_note_context_switch(void) } /* - * Tiny-preemptible RCU implementation for rcu_read_lock(). - * Just increment ->rcu_read_lock_nesting, shared state will be updated - * if we block. - */ -void __rcu_read_lock(void) -{ - current->rcu_read_lock_nesting++; - barrier(); /* needed if we ever invoke rcu_read_lock in rcutiny.c */ -} -EXPORT_SYMBOL_GPL(__rcu_read_lock); - -/* * Handle special cases during rcu_read_unlock(), such as needing to * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -static noinline void rcu_read_unlock_special(struct task_struct *t) +void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; @@ -627,38 +615,6 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) } /* - * Tiny-preemptible RCU implementation for rcu_read_unlock(). - * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost - * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then - * invoke rcu_read_unlock_special() to clean up after a context switch - * in an RCU read-side critical section and other special cases. - */ -void __rcu_read_unlock(void) -{ - struct task_struct *t = current; - - barrier(); /* needed if we ever invoke rcu_read_unlock in rcutiny.c */ - if (t->rcu_read_lock_nesting != 1) - --t->rcu_read_lock_nesting; - else { - t->rcu_read_lock_nesting = INT_MIN; - barrier(); /* assign before ->rcu_read_unlock_special load */ - if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) - rcu_read_unlock_special(t); - barrier(); /* ->rcu_read_unlock_special load before assign */ - t->rcu_read_lock_nesting = 0; - } -#ifdef CONFIG_PROVE_LOCKING - { - int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); - - WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); - } -#endif /* #ifdef CONFIG_PROVE_LOCKING */ -} -EXPORT_SYMBOL_GPL(__rcu_read_unlock); - -/* * Check for a quiescent state from the current CPU. When a task blocks, * the task is recorded in the rcu_preempt_ctrlblk structure, which is * checked elsewhere. This is called from the scheduling-clock interrupt. @@ -823,9 +779,9 @@ void synchronize_rcu_expedited(void) rpcp->exp_tasks = NULL; /* Wait for tail of ->blkd_tasks list to drain. */ - if (!rcu_preempted_readers_exp()) + if (!rcu_preempted_readers_exp()) { local_irq_restore(flags); - else { + } else { rcu_initiate_boost(); local_irq_restore(flags); wait_event(sync_rcu_preempt_exp_wq, @@ -846,8 +802,6 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); */ int rcu_preempt_needs_cpu(void) { - if (!rcu_preempt_running_reader()) - rcu_preempt_cpu_qs(); return rcu_preempt_ctrlblk.rcb.rcucblist != NULL; } diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index e66b34ab7555..25b15033c61f 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -49,8 +49,7 @@ #include <asm/byteorder.h> MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and " - "Josh Triplett <josh@freedesktop.org>"); +MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@freedesktop.org>"); static int nreaders = -1; /* # reader threads, defaults to 2*ncpus */ static int nfakewriters = 4; /* # fake writer threads */ @@ -206,6 +205,7 @@ static unsigned long boost_starttime; /* jiffies of next boost test start. */ DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ /* and boost task create/destroy. */ static atomic_t barrier_cbs_count; /* Barrier callbacks registered. */ +static bool barrier_phase; /* Test phase. */ static atomic_t barrier_cbs_invoked; /* Barrier callbacks invoked. */ static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */ static DECLARE_WAIT_QUEUE_HEAD(barrier_wq); @@ -407,8 +407,9 @@ rcu_torture_cb(struct rcu_head *p) if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) { rp->rtort_mbtest = 0; rcu_torture_free(rp); - } else + } else { cur_ops->deferred_free(rp); + } } static int rcu_no_completed(void) @@ -635,6 +636,17 @@ static void srcu_torture_synchronize(void) synchronize_srcu(&srcu_ctl); } +static void srcu_torture_call(struct rcu_head *head, + void (*func)(struct rcu_head *head)) +{ + call_srcu(&srcu_ctl, head, func); +} + +static void srcu_torture_barrier(void) +{ + srcu_barrier(&srcu_ctl); +} + static int srcu_torture_stats(char *page) { int cnt = 0; @@ -661,8 +673,8 @@ static struct rcu_torture_ops srcu_ops = { .completed = srcu_torture_completed, .deferred_free = srcu_torture_deferred_free, .sync = srcu_torture_synchronize, - .call = NULL, - .cb_barrier = NULL, + .call = srcu_torture_call, + .cb_barrier = srcu_torture_barrier, .stats = srcu_torture_stats, .name = "srcu" }; @@ -1013,7 +1025,11 @@ rcu_torture_fakewriter(void *arg) do { schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10); udelay(rcu_random(&rand) & 0x3ff); - cur_ops->sync(); + if (cur_ops->cb_barrier != NULL && + rcu_random(&rand) % (nfakewriters * 8) == 0) + cur_ops->cb_barrier(); + else + cur_ops->sync(); rcu_stutter_wait("rcu_torture_fakewriter"); } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); @@ -1183,27 +1199,27 @@ rcu_torture_printk(char *page) } cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG); cnt += sprintf(&page[cnt], - "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d " - "rtmbe: %d rtbke: %ld rtbre: %ld " - "rtbf: %ld rtb: %ld nt: %ld " - "onoff: %ld/%ld:%ld/%ld " - "barrier: %ld/%ld:%ld", + "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ", rcu_torture_current, rcu_torture_current_version, list_empty(&rcu_torture_freelist), atomic_read(&n_rcu_torture_alloc), atomic_read(&n_rcu_torture_alloc_fail), - atomic_read(&n_rcu_torture_free), + atomic_read(&n_rcu_torture_free)); + cnt += sprintf(&page[cnt], "rtmbe: %d rtbke: %ld rtbre: %ld ", atomic_read(&n_rcu_torture_mberror), n_rcu_torture_boost_ktrerror, - n_rcu_torture_boost_rterror, + n_rcu_torture_boost_rterror); + cnt += sprintf(&page[cnt], "rtbf: %ld rtb: %ld nt: %ld ", n_rcu_torture_boost_failure, n_rcu_torture_boosts, - n_rcu_torture_timers, + n_rcu_torture_timers); + cnt += sprintf(&page[cnt], "onoff: %ld/%ld:%ld/%ld ", n_online_successes, n_online_attempts, n_offline_successes, - n_offline_attempts, + n_offline_attempts); + cnt += sprintf(&page[cnt], "barrier: %ld/%ld:%ld", n_barrier_successes, n_barrier_attempts, n_rcu_torture_barrier_error); @@ -1445,8 +1461,7 @@ rcu_torture_shutdown(void *arg) delta = shutdown_time - jiffies_snap; if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_shutdown task: %lu " - "jiffies remaining\n", + "rcu_torture_shutdown task: %lu jiffies remaining\n", torture_type, delta); schedule_timeout_interruptible(delta); jiffies_snap = ACCESS_ONCE(jiffies); @@ -1498,8 +1513,7 @@ rcu_torture_onoff(void *arg) if (cpu_down(cpu) == 0) { if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_onoff task: " - "offlined %d\n", + "rcu_torture_onoff task: offlined %d\n", torture_type, cpu); n_offline_successes++; } @@ -1512,8 +1526,7 @@ rcu_torture_onoff(void *arg) if (cpu_up(cpu) == 0) { if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_onoff task: " - "onlined %d\n", + "rcu_torture_onoff task: onlined %d\n", torture_type, cpu); n_online_successes++; } @@ -1631,6 +1644,7 @@ void rcu_torture_barrier_cbf(struct rcu_head *rcu) static int rcu_torture_barrier_cbs(void *arg) { long myid = (long)arg; + bool lastphase = 0; struct rcu_head rcu; init_rcu_head_on_stack(&rcu); @@ -1638,9 +1652,11 @@ static int rcu_torture_barrier_cbs(void *arg) set_user_nice(current, 19); do { wait_event(barrier_cbs_wq[myid], - atomic_read(&barrier_cbs_count) == n_barrier_cbs || + barrier_phase != lastphase || kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP); + lastphase = barrier_phase; + smp_mb(); /* ensure barrier_phase load before ->call(). */ if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP) break; cur_ops->call(&rcu, rcu_torture_barrier_cbf); @@ -1665,7 +1681,8 @@ static int rcu_torture_barrier(void *arg) do { atomic_set(&barrier_cbs_invoked, 0); atomic_set(&barrier_cbs_count, n_barrier_cbs); - /* wake_up() path contains the required barriers. */ + smp_mb(); /* Ensure barrier_phase after prior assignments. */ + barrier_phase = !barrier_phase; for (i = 0; i < n_barrier_cbs; i++) wake_up(&barrier_cbs_wq[i]); wait_event(barrier_wq, @@ -1684,7 +1701,7 @@ static int rcu_torture_barrier(void *arg) schedule_timeout_interruptible(HZ / 10); } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); VERBOSE_PRINTK_STRING("rcu_torture_barrier task stopping"); - rcutorture_shutdown_absorb("rcu_torture_barrier_cbs"); + rcutorture_shutdown_absorb("rcu_torture_barrier"); while (!kthread_should_stop()) schedule_timeout_interruptible(1); return 0; @@ -1908,8 +1925,8 @@ rcu_torture_init(void) static struct rcu_torture_ops *torture_ops[] = { &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops, &rcu_bh_ops, &rcu_bh_sync_ops, &rcu_bh_expedited_ops, - &srcu_ops, &srcu_sync_ops, &srcu_raw_ops, - &srcu_raw_sync_ops, &srcu_expedited_ops, + &srcu_ops, &srcu_sync_ops, &srcu_expedited_ops, + &srcu_raw_ops, &srcu_raw_sync_ops, &sched_ops, &sched_sync_ops, &sched_expedited_ops, }; mutex_lock(&fullstop_mutex); @@ -1931,8 +1948,7 @@ rcu_torture_init(void) return -EINVAL; } if (cur_ops->fqs == NULL && fqs_duration != 0) { - printk(KERN_ALERT "rcu-torture: ->fqs NULL and non-zero " - "fqs_duration, fqs disabled.\n"); + printk(KERN_ALERT "rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n"); fqs_duration = 0; } if (cur_ops->init) diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 38ecdda3f55f..f280e542e3e9 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -60,36 +60,44 @@ /* Data structures. */ -static struct lock_class_key rcu_node_class[NUM_RCU_LVLS]; - -#define RCU_STATE_INITIALIZER(structname) { \ - .level = { &structname##_state.node[0] }, \ - .levelcnt = { \ - NUM_RCU_LVL_0, /* root of hierarchy. */ \ - NUM_RCU_LVL_1, \ - NUM_RCU_LVL_2, \ - NUM_RCU_LVL_3, \ - NUM_RCU_LVL_4, /* == MAX_RCU_LVLS */ \ - }, \ +static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; + +#define RCU_STATE_INITIALIZER(sname, cr) { \ + .level = { &sname##_state.node[0] }, \ + .call = cr, \ .fqs_state = RCU_GP_IDLE, \ .gpnum = -300, \ .completed = -300, \ - .onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname##_state.onofflock), \ - .orphan_nxttail = &structname##_state.orphan_nxtlist, \ - .orphan_donetail = &structname##_state.orphan_donelist, \ - .fqslock = __RAW_SPIN_LOCK_UNLOCKED(&structname##_state.fqslock), \ - .n_force_qs = 0, \ - .n_force_qs_ngp = 0, \ - .name = #structname, \ + .onofflock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.onofflock), \ + .orphan_nxttail = &sname##_state.orphan_nxtlist, \ + .orphan_donetail = &sname##_state.orphan_donelist, \ + .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ + .fqslock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.fqslock), \ + .name = #sname, \ } -struct rcu_state rcu_sched_state = RCU_STATE_INITIALIZER(rcu_sched); +struct rcu_state rcu_sched_state = + RCU_STATE_INITIALIZER(rcu_sched, call_rcu_sched); DEFINE_PER_CPU(struct rcu_data, rcu_sched_data); -struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh); +struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh, call_rcu_bh); DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); static struct rcu_state *rcu_state; +LIST_HEAD(rcu_struct_flavors); + +/* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */ +static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF; +module_param(rcu_fanout_leaf, int, 0); +int rcu_num_lvls __read_mostly = RCU_NUM_LVLS; +static int num_rcu_lvl[] = { /* Number of rcu_nodes at specified level. */ + NUM_RCU_LVL_0, + NUM_RCU_LVL_1, + NUM_RCU_LVL_2, + NUM_RCU_LVL_3, + NUM_RCU_LVL_4, +}; +int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */ /* * The rcu_scheduler_active variable transitions from zero to one just @@ -147,13 +155,6 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); unsigned long rcutorture_testseq; unsigned long rcutorture_vernum; -/* State information for rcu_barrier() and friends. */ - -static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL}; -static atomic_t rcu_barrier_cpu_count; -static DEFINE_MUTEX(rcu_barrier_mutex); -static struct completion rcu_barrier_completion; - /* * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s * permit this function to be invoked without holding the root rcu_node @@ -201,6 +202,7 @@ void rcu_note_context_switch(int cpu) { trace_rcu_utilization("Start context switch"); rcu_sched_qs(cpu); + rcu_preempt_note_context_switch(cpu); trace_rcu_utilization("End context switch"); } EXPORT_SYMBOL_GPL(rcu_note_context_switch); @@ -357,7 +359,7 @@ static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval) struct task_struct *idle = idle_task(smp_processor_id()); trace_rcu_dyntick("Error on entry: not idle task", oldval, 0); - ftrace_dump(DUMP_ALL); + ftrace_dump(DUMP_ORIG); WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ @@ -467,7 +469,7 @@ static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval) trace_rcu_dyntick("Error on exit: not idle task", oldval, rdtp->dynticks_nesting); - ftrace_dump(DUMP_ALL); + ftrace_dump(DUMP_ORIG); WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ @@ -584,8 +586,6 @@ void rcu_nmi_exit(void) WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); } -#ifdef CONFIG_PROVE_RCU - /** * rcu_is_cpu_idle - see if RCU thinks that the current CPU is idle * @@ -603,7 +603,7 @@ int rcu_is_cpu_idle(void) } EXPORT_SYMBOL(rcu_is_cpu_idle); -#ifdef CONFIG_HOTPLUG_CPU +#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) /* * Is the current CPU online? Disable preemption to avoid false positives @@ -644,9 +644,7 @@ bool rcu_lockdep_current_cpu_online(void) } EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - -#endif /* #ifdef CONFIG_PROVE_RCU */ +#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */ /** * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle @@ -732,7 +730,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) int cpu; long delta; unsigned long flags; - int ndetected; + int ndetected = 0; struct rcu_node *rnp = rcu_get_root(rsp); /* Only let one CPU complain about others per time interval. */ @@ -773,7 +771,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) */ rnp = rcu_get_root(rsp); raw_spin_lock_irqsave(&rnp->lock, flags); - ndetected = rcu_print_task_stall(rnp); + ndetected += rcu_print_task_stall(rnp); raw_spin_unlock_irqrestore(&rnp->lock, flags); print_cpu_stall_info_end(); @@ -859,9 +857,10 @@ static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr) */ void rcu_cpu_stall_reset(void) { - rcu_sched_state.jiffies_stall = jiffies + ULONG_MAX / 2; - rcu_bh_state.jiffies_stall = jiffies + ULONG_MAX / 2; - rcu_preempt_stall_reset(); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + rsp->jiffies_stall = jiffies + ULONG_MAX / 2; } static struct notifier_block rcu_panic_block = { @@ -893,8 +892,9 @@ static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct if (rnp->qsmask & rdp->grpmask) { rdp->qs_pending = 1; rdp->passed_quiesce = 0; - } else + } else { rdp->qs_pending = 0; + } zero_cpu_stall_ticks(rdp); } } @@ -936,6 +936,18 @@ check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp) } /* + * Initialize the specified rcu_data structure's callback list to empty. + */ +static void init_callback_list(struct rcu_data *rdp) +{ + int i; + + rdp->nxtlist = NULL; + for (i = 0; i < RCU_NEXT_SIZE; i++) + rdp->nxttail[i] = &rdp->nxtlist; +} + +/* * Advance this CPU's callbacks, but only if the current grace period * has ended. This may be called only from the CPU to whom the rdp * belongs. In addition, the corresponding leaf rcu_node structure's @@ -1327,8 +1339,6 @@ static void rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { - int i; - /* * Orphan the callbacks. First adjust the counts. This is safe * because ->onofflock excludes _rcu_barrier()'s adoption of @@ -1339,7 +1349,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, rsp->qlen += rdp->qlen; rdp->n_cbs_orphaned += rdp->qlen; rdp->qlen_lazy = 0; - rdp->qlen = 0; + ACCESS_ONCE(rdp->qlen) = 0; } /* @@ -1368,9 +1378,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, } /* Finally, initialize the rcu_data structure's list to empty. */ - rdp->nxtlist = NULL; - for (i = 0; i < RCU_NEXT_SIZE; i++) - rdp->nxttail[i] = &rdp->nxtlist; + init_callback_list(rdp); } /* @@ -1504,6 +1512,9 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp->lock, flags); if (need_report & RCU_OFL_TASKS_EXP_GP) rcu_report_exp_rnp(rsp, rnp, true); + WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL, + "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n", + cpu, rdp->qlen, rdp->nxtlist); } #else /* #ifdef CONFIG_HOTPLUG_CPU */ @@ -1591,7 +1602,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) } smp_mb(); /* List handling before counting for rcu_barrier(). */ rdp->qlen_lazy -= count_lazy; - rdp->qlen -= count; + ACCESS_ONCE(rdp->qlen) -= count; rdp->n_cbs_invoked += count; /* Reinstate batch limit if we have worked down the excess. */ @@ -1604,6 +1615,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) rdp->n_force_qs_snap = rsp->n_force_qs; } else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark) rdp->qlen_last_fqs_check = rdp->qlen; + WARN_ON_ONCE((rdp->nxtlist == NULL) != (rdp->qlen == 0)); local_irq_restore(flags); @@ -1744,8 +1756,6 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) break; /* grace period idle or initializing, ignore. */ case RCU_SAVE_DYNTICK: - if (RCU_SIGNAL_INIT != RCU_SAVE_DYNTICK) - break; /* So gcc recognizes the dead code. */ raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ @@ -1787,9 +1797,10 @@ unlock_fqs_ret: * whom the rdp belongs. */ static void -__rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) +__rcu_process_callbacks(struct rcu_state *rsp) { unsigned long flags; + struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); WARN_ON_ONCE(rdp->beenonline == 0); @@ -1825,11 +1836,11 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) */ static void rcu_process_callbacks(struct softirq_action *unused) { + struct rcu_state *rsp; + trace_rcu_utilization("Start RCU core"); - __rcu_process_callbacks(&rcu_sched_state, - &__get_cpu_var(rcu_sched_data)); - __rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data)); - rcu_preempt_process_callbacks(); + for_each_rcu_flavor(rsp) + __rcu_process_callbacks(rsp); trace_rcu_utilization("End RCU core"); } @@ -1856,6 +1867,56 @@ static void invoke_rcu_core(void) raise_softirq(RCU_SOFTIRQ); } +/* + * Handle any core-RCU processing required by a call_rcu() invocation. + */ +static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, + struct rcu_head *head, unsigned long flags) +{ + /* + * If called from an extended quiescent state, invoke the RCU + * core in order to force a re-evaluation of RCU's idleness. + */ + if (rcu_is_cpu_idle() && cpu_online(smp_processor_id())) + invoke_rcu_core(); + + /* If interrupts were disabled or CPU offline, don't invoke RCU core. */ + if (irqs_disabled_flags(flags) || cpu_is_offline(smp_processor_id())) + return; + + /* + * Force the grace period if too many callbacks or too long waiting. + * Enforce hysteresis, and don't invoke force_quiescent_state() + * if some other CPU has recently done so. Also, don't bother + * invoking force_quiescent_state() if the newly enqueued callback + * is the only one waiting for a grace period to complete. + */ + if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) { + + /* Are we ignoring a completed grace period? */ + rcu_process_gp_end(rsp, rdp); + check_for_new_grace_period(rsp, rdp); + + /* Start a new grace period if one not already started. */ + if (!rcu_gp_in_progress(rsp)) { + unsigned long nestflag; + struct rcu_node *rnp_root = rcu_get_root(rsp); + + raw_spin_lock_irqsave(&rnp_root->lock, nestflag); + rcu_start_gp(rsp, nestflag); /* rlses rnp_root->lock */ + } else { + /* Give the grace period a kick. */ + rdp->blimit = LONG_MAX; + if (rsp->n_force_qs == rdp->n_force_qs_snap && + *rdp->nxttail[RCU_DONE_TAIL] != head) + force_quiescent_state(rsp, 0); + rdp->n_force_qs_snap = rsp->n_force_qs; + rdp->qlen_last_fqs_check = rdp->qlen; + } + } else if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies)) + force_quiescent_state(rsp, 1); +} + static void __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), struct rcu_state *rsp, bool lazy) @@ -1880,7 +1941,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), rdp = this_cpu_ptr(rsp->rda); /* Add the callback to our list. */ - rdp->qlen++; + ACCESS_ONCE(rdp->qlen)++; if (lazy) rdp->qlen_lazy++; else @@ -1895,43 +1956,8 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), else trace_rcu_callback(rsp->name, head, rdp->qlen_lazy, rdp->qlen); - /* If interrupts were disabled, don't dive into RCU core. */ - if (irqs_disabled_flags(flags)) { - local_irq_restore(flags); - return; - } - - /* - * Force the grace period if too many callbacks or too long waiting. - * Enforce hysteresis, and don't invoke force_quiescent_state() - * if some other CPU has recently done so. Also, don't bother - * invoking force_quiescent_state() if the newly enqueued callback - * is the only one waiting for a grace period to complete. - */ - if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) { - - /* Are we ignoring a completed grace period? */ - rcu_process_gp_end(rsp, rdp); - check_for_new_grace_period(rsp, rdp); - - /* Start a new grace period if one not already started. */ - if (!rcu_gp_in_progress(rsp)) { - unsigned long nestflag; - struct rcu_node *rnp_root = rcu_get_root(rsp); - - raw_spin_lock_irqsave(&rnp_root->lock, nestflag); - rcu_start_gp(rsp, nestflag); /* rlses rnp_root->lock */ - } else { - /* Give the grace period a kick. */ - rdp->blimit = LONG_MAX; - if (rsp->n_force_qs == rdp->n_force_qs_snap && - *rdp->nxttail[RCU_DONE_TAIL] != head) - force_quiescent_state(rsp, 0); - rdp->n_force_qs_snap = rsp->n_force_qs; - rdp->qlen_last_fqs_check = rdp->qlen; - } - } else if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies)) - force_quiescent_state(rsp, 1); + /* Go handle any RCU core processing required. */ + __call_rcu_core(rsp, rdp, head, flags); local_irq_restore(flags); } @@ -1961,28 +1987,16 @@ EXPORT_SYMBOL_GPL(call_rcu_bh); * occasionally incorrectly indicate that there are multiple CPUs online * when there was in fact only one the whole time, as this just adds * some overhead: RCU still operates correctly. - * - * Of course, sampling num_online_cpus() with preemption enabled can - * give erroneous results if there are concurrent CPU-hotplug operations. - * For example, given a demonic sequence of preemptions in num_online_cpus() - * and CPU-hotplug operations, there could be two or more CPUs online at - * all times, but num_online_cpus() might well return one (or even zero). - * - * However, all such demonic sequences require at least one CPU-offline - * operation. Furthermore, rcu_blocking_is_gp() giving the wrong answer - * is only a problem if there is an RCU read-side critical section executing - * throughout. But RCU-sched and RCU-bh read-side critical sections - * disable either preemption or bh, which prevents a CPU from going offline. - * Therefore, the only way that rcu_blocking_is_gp() can incorrectly return - * that there is only one CPU when in fact there was more than one throughout - * is when there were no RCU readers in the system. If there are no - * RCU readers, the grace period by definition can be of zero length, - * regardless of the number of online CPUs. */ static inline int rcu_blocking_is_gp(void) { + int ret; + might_sleep(); /* Check for RCU read-side critical section. */ - return num_online_cpus() <= 1; + preempt_disable(); + ret = num_online_cpus() <= 1; + preempt_enable(); + return ret; } /** @@ -2117,9 +2131,9 @@ void synchronize_sched_expedited(void) put_online_cpus(); /* No joy, try again later. Or just synchronize_sched(). */ - if (trycount++ < 10) + if (trycount++ < 10) { udelay(trycount * num_online_cpus()); - else { + } else { synchronize_sched(); return; } @@ -2240,9 +2254,12 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) */ static int rcu_pending(int cpu) { - return __rcu_pending(&rcu_sched_state, &per_cpu(rcu_sched_data, cpu)) || - __rcu_pending(&rcu_bh_state, &per_cpu(rcu_bh_data, cpu)) || - rcu_preempt_pending(cpu); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + if (__rcu_pending(rsp, per_cpu_ptr(rsp->rda, cpu))) + return 1; + return 0; } /* @@ -2252,20 +2269,41 @@ static int rcu_pending(int cpu) */ static int rcu_cpu_has_callbacks(int cpu) { + struct rcu_state *rsp; + /* RCU callbacks either ready or pending? */ - return per_cpu(rcu_sched_data, cpu).nxtlist || - per_cpu(rcu_bh_data, cpu).nxtlist || - rcu_preempt_cpu_has_callbacks(cpu); + for_each_rcu_flavor(rsp) + if (per_cpu_ptr(rsp->rda, cpu)->nxtlist) + return 1; + return 0; +} + +/* + * Helper function for _rcu_barrier() tracing. If tracing is disabled, + * the compiler is expected to optimize this away. + */ +static void _rcu_barrier_trace(struct rcu_state *rsp, char *s, + int cpu, unsigned long done) +{ + trace_rcu_barrier(rsp->name, s, cpu, + atomic_read(&rsp->barrier_cpu_count), done); } /* * RCU callback function for _rcu_barrier(). If we are last, wake * up the task executing _rcu_barrier(). */ -static void rcu_barrier_callback(struct rcu_head *notused) +static void rcu_barrier_callback(struct rcu_head *rhp) { - if (atomic_dec_and_test(&rcu_barrier_cpu_count)) - complete(&rcu_barrier_completion); + struct rcu_data *rdp = container_of(rhp, struct rcu_data, barrier_head); + struct rcu_state *rsp = rdp->rsp; + + if (atomic_dec_and_test(&rsp->barrier_cpu_count)) { + _rcu_barrier_trace(rsp, "LastCB", -1, rsp->n_barrier_done); + complete(&rsp->barrier_completion); + } else { + _rcu_barrier_trace(rsp, "CB", -1, rsp->n_barrier_done); + } } /* @@ -2273,35 +2311,63 @@ static void rcu_barrier_callback(struct rcu_head *notused) */ static void rcu_barrier_func(void *type) { - int cpu = smp_processor_id(); - struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu); - void (*call_rcu_func)(struct rcu_head *head, - void (*func)(struct rcu_head *head)); + struct rcu_state *rsp = type; + struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); - atomic_inc(&rcu_barrier_cpu_count); - call_rcu_func = type; - call_rcu_func(head, rcu_barrier_callback); + _rcu_barrier_trace(rsp, "IRQ", -1, rsp->n_barrier_done); + atomic_inc(&rsp->barrier_cpu_count); + rsp->call(&rdp->barrier_head, rcu_barrier_callback); } /* * Orchestrate the specified type of RCU barrier, waiting for all * RCU callbacks of the specified type to complete. */ -static void _rcu_barrier(struct rcu_state *rsp, - void (*call_rcu_func)(struct rcu_head *head, - void (*func)(struct rcu_head *head))) +static void _rcu_barrier(struct rcu_state *rsp) { int cpu; unsigned long flags; struct rcu_data *rdp; - struct rcu_head rh; + struct rcu_data rd; + unsigned long snap = ACCESS_ONCE(rsp->n_barrier_done); + unsigned long snap_done; - init_rcu_head_on_stack(&rh); + init_rcu_head_on_stack(&rd.barrier_head); + _rcu_barrier_trace(rsp, "Begin", -1, snap); /* Take mutex to serialize concurrent rcu_barrier() requests. */ - mutex_lock(&rcu_barrier_mutex); + mutex_lock(&rsp->barrier_mutex); + + /* + * Ensure that all prior references, including to ->n_barrier_done, + * are ordered before the _rcu_barrier() machinery. + */ + smp_mb(); /* See above block comment. */ + + /* + * Recheck ->n_barrier_done to see if others did our work for us. + * This means checking ->n_barrier_done for an even-to-odd-to-even + * transition. The "if" expression below therefore rounds the old + * value up to the next even number and adds two before comparing. + */ + snap_done = ACCESS_ONCE(rsp->n_barrier_done); + _rcu_barrier_trace(rsp, "Check", -1, snap_done); + if (ULONG_CMP_GE(snap_done, ((snap + 1) & ~0x1) + 2)) { + _rcu_barrier_trace(rsp, "EarlyExit", -1, snap_done); + smp_mb(); /* caller's subsequent code after above check. */ + mutex_unlock(&rsp->barrier_mutex); + return; + } - smp_mb(); /* Prevent any prior operations from leaking in. */ + /* + * Increment ->n_barrier_done to avoid duplicate work. Use + * ACCESS_ONCE() to prevent the compiler from speculating + * the increment to precede the early-exit check. + */ + ACCESS_ONCE(rsp->n_barrier_done)++; + WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1); + _rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done); + smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */ /* * Initialize the count to one rather than to zero in order to @@ -2320,8 +2386,8 @@ static void _rcu_barrier(struct rcu_state *rsp, * 6. Both rcu_barrier_callback() callbacks are invoked, awakening * us -- but before CPU 1's orphaned callbacks are invoked!!! */ - init_completion(&rcu_barrier_completion); - atomic_set(&rcu_barrier_cpu_count, 1); + init_completion(&rsp->barrier_completion); + atomic_set(&rsp->barrier_cpu_count, 1); raw_spin_lock_irqsave(&rsp->onofflock, flags); rsp->rcu_barrier_in_progress = current; raw_spin_unlock_irqrestore(&rsp->onofflock, flags); @@ -2337,14 +2403,19 @@ static void _rcu_barrier(struct rcu_state *rsp, preempt_disable(); rdp = per_cpu_ptr(rsp->rda, cpu); if (cpu_is_offline(cpu)) { + _rcu_barrier_trace(rsp, "Offline", cpu, + rsp->n_barrier_done); preempt_enable(); while (cpu_is_offline(cpu) && ACCESS_ONCE(rdp->qlen)) schedule_timeout_interruptible(1); } else if (ACCESS_ONCE(rdp->qlen)) { - smp_call_function_single(cpu, rcu_barrier_func, - (void *)call_rcu_func, 1); + _rcu_barrier_trace(rsp, "OnlineQ", cpu, + rsp->n_barrier_done); + smp_call_function_single(cpu, rcu_barrier_func, rsp, 1); preempt_enable(); } else { + _rcu_barrier_trace(rsp, "OnlineNQ", cpu, + rsp->n_barrier_done); preempt_enable(); } } @@ -2361,24 +2432,32 @@ static void _rcu_barrier(struct rcu_state *rsp, rcu_adopt_orphan_cbs(rsp); rsp->rcu_barrier_in_progress = NULL; raw_spin_unlock_irqrestore(&rsp->onofflock, flags); - atomic_inc(&rcu_barrier_cpu_count); + atomic_inc(&rsp->barrier_cpu_count); smp_mb__after_atomic_inc(); /* Ensure atomic_inc() before callback. */ - call_rcu_func(&rh, rcu_barrier_callback); + rd.rsp = rsp; + rsp->call(&rd.barrier_head, rcu_barrier_callback); /* * Now that we have an rcu_barrier_callback() callback on each * CPU, and thus each counted, remove the initial count. */ - if (atomic_dec_and_test(&rcu_barrier_cpu_count)) - complete(&rcu_barrier_completion); + if (atomic_dec_and_test(&rsp->barrier_cpu_count)) + complete(&rsp->barrier_completion); + + /* Increment ->n_barrier_done to prevent duplicate work. */ + smp_mb(); /* Keep increment after above mechanism. */ + ACCESS_ONCE(rsp->n_barrier_done)++; + WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0); + _rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done); + smp_mb(); /* Keep increment before caller's subsequent code. */ /* Wait for all rcu_barrier_callback() callbacks to be invoked. */ - wait_for_completion(&rcu_barrier_completion); + wait_for_completion(&rsp->barrier_completion); /* Other rcu_barrier() invocations can now safely proceed. */ - mutex_unlock(&rcu_barrier_mutex); + mutex_unlock(&rsp->barrier_mutex); - destroy_rcu_head_on_stack(&rh); + destroy_rcu_head_on_stack(&rd.barrier_head); } /** @@ -2386,7 +2465,7 @@ static void _rcu_barrier(struct rcu_state *rsp, */ void rcu_barrier_bh(void) { - _rcu_barrier(&rcu_bh_state, call_rcu_bh); + _rcu_barrier(&rcu_bh_state); } EXPORT_SYMBOL_GPL(rcu_barrier_bh); @@ -2395,7 +2474,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier_bh); */ void rcu_barrier_sched(void) { - _rcu_barrier(&rcu_sched_state, call_rcu_sched); + _rcu_barrier(&rcu_sched_state); } EXPORT_SYMBOL_GPL(rcu_barrier_sched); @@ -2406,18 +2485,15 @@ static void __init rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) { unsigned long flags; - int i; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rcu_get_root(rsp); /* Set up local state, ensuring consistent view of global state. */ raw_spin_lock_irqsave(&rnp->lock, flags); rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo); - rdp->nxtlist = NULL; - for (i = 0; i < RCU_NEXT_SIZE; i++) - rdp->nxttail[i] = &rdp->nxtlist; + init_callback_list(rdp); rdp->qlen_lazy = 0; - rdp->qlen = 0; + ACCESS_ONCE(rdp->qlen) = 0; rdp->dynticks = &per_cpu(rcu_dynticks, cpu); WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE); WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); @@ -2491,9 +2567,11 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) static void __cpuinit rcu_prepare_cpu(int cpu) { - rcu_init_percpu_data(cpu, &rcu_sched_state, 0); - rcu_init_percpu_data(cpu, &rcu_bh_state, 0); - rcu_preempt_init_percpu_data(cpu); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + rcu_init_percpu_data(cpu, rsp, + strcmp(rsp->name, "rcu_preempt") == 0); } /* @@ -2505,6 +2583,7 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, long cpu = (long)hcpu; struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); struct rcu_node *rnp = rdp->mynode; + struct rcu_state *rsp; trace_rcu_utilization("Start CPU hotplug"); switch (action) { @@ -2529,18 +2608,16 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, * touch any data without introducing corruption. We send the * dying CPU's callbacks to an arbitrarily chosen online CPU. */ - rcu_cleanup_dying_cpu(&rcu_bh_state); - rcu_cleanup_dying_cpu(&rcu_sched_state); - rcu_preempt_cleanup_dying_cpu(); + for_each_rcu_flavor(rsp) + rcu_cleanup_dying_cpu(rsp); rcu_cleanup_after_idle(cpu); break; case CPU_DEAD: case CPU_DEAD_FROZEN: case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: - rcu_cleanup_dead_cpu(cpu, &rcu_bh_state); - rcu_cleanup_dead_cpu(cpu, &rcu_sched_state); - rcu_preempt_cleanup_dead_cpu(cpu); + for_each_rcu_flavor(rsp) + rcu_cleanup_dead_cpu(cpu, rsp); break; default: break; @@ -2573,9 +2650,9 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp) { int i; - for (i = NUM_RCU_LVLS - 1; i > 0; i--) + for (i = rcu_num_lvls - 1; i > 0; i--) rsp->levelspread[i] = CONFIG_RCU_FANOUT; - rsp->levelspread[0] = CONFIG_RCU_FANOUT_LEAF; + rsp->levelspread[0] = rcu_fanout_leaf; } #else /* #ifdef CONFIG_RCU_FANOUT_EXACT */ static void __init rcu_init_levelspread(struct rcu_state *rsp) @@ -2585,7 +2662,7 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp) int i; cprv = NR_CPUS; - for (i = NUM_RCU_LVLS - 1; i >= 0; i--) { + for (i = rcu_num_lvls - 1; i >= 0; i--) { ccur = rsp->levelcnt[i]; rsp->levelspread[i] = (cprv + ccur - 1) / ccur; cprv = ccur; @@ -2612,13 +2689,15 @@ static void __init rcu_init_one(struct rcu_state *rsp, /* Initialize the level-tracking arrays. */ - for (i = 1; i < NUM_RCU_LVLS; i++) + for (i = 0; i < rcu_num_lvls; i++) + rsp->levelcnt[i] = num_rcu_lvl[i]; + for (i = 1; i < rcu_num_lvls; i++) rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1]; rcu_init_levelspread(rsp); /* Initialize the elements themselves, starting from the leaves. */ - for (i = NUM_RCU_LVLS - 1; i >= 0; i--) { + for (i = rcu_num_lvls - 1; i >= 0; i--) { cpustride *= rsp->levelspread[i]; rnp = rsp->level[i]; for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) { @@ -2648,13 +2727,74 @@ static void __init rcu_init_one(struct rcu_state *rsp, } rsp->rda = rda; - rnp = rsp->level[NUM_RCU_LVLS - 1]; + rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { while (i > rnp->grphi) rnp++; per_cpu_ptr(rsp->rda, i)->mynode = rnp; rcu_boot_init_percpu_data(i, rsp); } + list_add(&rsp->flavors, &rcu_struct_flavors); +} + +/* + * Compute the rcu_node tree geometry from kernel parameters. This cannot + * replace the definitions in rcutree.h because those are needed to size + * the ->node array in the rcu_state structure. + */ +static void __init rcu_init_geometry(void) +{ + int i; + int j; + int n = nr_cpu_ids; + int rcu_capacity[MAX_RCU_LVLS + 1]; + + /* If the compile-time values are accurate, just leave. */ + if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF) + return; + + /* + * Compute number of nodes that can be handled an rcu_node tree + * with the given number of levels. Setting rcu_capacity[0] makes + * some of the arithmetic easier. + */ + rcu_capacity[0] = 1; + rcu_capacity[1] = rcu_fanout_leaf; + for (i = 2; i <= MAX_RCU_LVLS; i++) + rcu_capacity[i] = rcu_capacity[i - 1] * CONFIG_RCU_FANOUT; + + /* + * The boot-time rcu_fanout_leaf parameter is only permitted + * to increase the leaf-level fanout, not decrease it. Of course, + * the leaf-level fanout cannot exceed the number of bits in + * the rcu_node masks. Finally, the tree must be able to accommodate + * the configured number of CPUs. Complain and fall back to the + * compile-time values if these limits are exceeded. + */ + if (rcu_fanout_leaf < CONFIG_RCU_FANOUT_LEAF || + rcu_fanout_leaf > sizeof(unsigned long) * 8 || + n > rcu_capacity[MAX_RCU_LVLS]) { + WARN_ON(1); + return; + } + + /* Calculate the number of rcu_nodes at each level of the tree. */ + for (i = 1; i <= MAX_RCU_LVLS; i++) + if (n <= rcu_capacity[i]) { + for (j = 0; j <= i; j++) + num_rcu_lvl[j] = + DIV_ROUND_UP(n, rcu_capacity[i - j]); + rcu_num_lvls = i; + for (j = i + 1; j <= MAX_RCU_LVLS; j++) + num_rcu_lvl[j] = 0; + break; + } + + /* Calculate the total number of rcu_node structures. */ + rcu_num_nodes = 0; + for (i = 0; i <= MAX_RCU_LVLS; i++) + rcu_num_nodes += num_rcu_lvl[i]; + rcu_num_nodes -= n; } void __init rcu_init(void) @@ -2662,6 +2802,7 @@ void __init rcu_init(void) int cpu; rcu_bootup_announce(); + rcu_init_geometry(); rcu_init_one(&rcu_sched_state, &rcu_sched_data); rcu_init_one(&rcu_bh_state, &rcu_bh_data); __rcu_init_preempt(); diff --git a/kernel/rcutree.h b/kernel/rcutree.h index ea056495783e..4d29169f2124 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -42,28 +42,28 @@ #define RCU_FANOUT_4 (RCU_FANOUT_3 * CONFIG_RCU_FANOUT) #if NR_CPUS <= RCU_FANOUT_1 -# define NUM_RCU_LVLS 1 +# define RCU_NUM_LVLS 1 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 (NR_CPUS) # define NUM_RCU_LVL_2 0 # define NUM_RCU_LVL_3 0 # define NUM_RCU_LVL_4 0 #elif NR_CPUS <= RCU_FANOUT_2 -# define NUM_RCU_LVLS 2 +# define RCU_NUM_LVLS 2 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) # define NUM_RCU_LVL_2 (NR_CPUS) # define NUM_RCU_LVL_3 0 # define NUM_RCU_LVL_4 0 #elif NR_CPUS <= RCU_FANOUT_3 -# define NUM_RCU_LVLS 3 +# define RCU_NUM_LVLS 3 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1) # define NUM_RCU_LVL_3 (NR_CPUS) # define NUM_RCU_LVL_4 0 #elif NR_CPUS <= RCU_FANOUT_4 -# define NUM_RCU_LVLS 4 +# define RCU_NUM_LVLS 4 # define NUM_RCU_LVL_0 1 # define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3) # define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2) @@ -76,6 +76,9 @@ #define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4) #define NUM_RCU_NODES (RCU_SUM - NR_CPUS) +extern int rcu_num_lvls; +extern int rcu_num_nodes; + /* * Dynticks per-CPU state. */ @@ -97,6 +100,7 @@ struct rcu_dynticks { /* # times non-lazy CBs posted to CPU. */ unsigned long nonlazy_posted_snap; /* idle-period nonlazy_posted snapshot. */ + int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */ #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ }; @@ -206,7 +210,7 @@ struct rcu_node { */ #define rcu_for_each_node_breadth_first(rsp, rnp) \ for ((rnp) = &(rsp)->node[0]; \ - (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++) + (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) /* * Do a breadth-first scan of the non-leaf rcu_node structures for the @@ -215,7 +219,7 @@ struct rcu_node { */ #define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \ for ((rnp) = &(rsp)->node[0]; \ - (rnp) < (rsp)->level[NUM_RCU_LVLS - 1]; (rnp)++) + (rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++) /* * Scan the leaves of the rcu_node hierarchy for the specified rcu_state @@ -224,8 +228,8 @@ struct rcu_node { * It is still a leaf node, even if it is also the root node. */ #define rcu_for_each_leaf_node(rsp, rnp) \ - for ((rnp) = (rsp)->level[NUM_RCU_LVLS - 1]; \ - (rnp) < &(rsp)->node[NUM_RCU_NODES]; (rnp)++) + for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \ + (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) /* Index values for nxttail array in struct rcu_data. */ #define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */ @@ -311,6 +315,9 @@ struct rcu_data { unsigned long n_rp_need_fqs; unsigned long n_rp_need_nothing; + /* 6) _rcu_barrier() callback. */ + struct rcu_head barrier_head; + int cpu; struct rcu_state *rsp; }; @@ -357,10 +364,12 @@ do { \ */ struct rcu_state { struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */ - struct rcu_node *level[NUM_RCU_LVLS]; /* Hierarchy levels. */ + struct rcu_node *level[RCU_NUM_LVLS]; /* Hierarchy levels. */ u32 levelcnt[MAX_RCU_LVLS + 1]; /* # nodes in each level. */ - u8 levelspread[NUM_RCU_LVLS]; /* kids/node in each level. */ + u8 levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */ struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */ + void (*call)(struct rcu_head *head, /* call_rcu() flavor. */ + void (*func)(struct rcu_head *head)); /* The following fields are guarded by the root rcu_node's lock. */ @@ -392,6 +401,11 @@ struct rcu_state { struct task_struct *rcu_barrier_in_progress; /* Task doing rcu_barrier(), */ /* or NULL if no barrier. */ + struct mutex barrier_mutex; /* Guards barrier fields. */ + atomic_t barrier_cpu_count; /* # CPUs waiting on. */ + struct completion barrier_completion; /* Wake at barrier end. */ + unsigned long n_barrier_done; /* ++ at start and end of */ + /* _rcu_barrier(). */ raw_spinlock_t fqslock; /* Only one task forcing */ /* quiescent states. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ @@ -409,8 +423,13 @@ struct rcu_state { unsigned long gp_max; /* Maximum GP duration in */ /* jiffies. */ char *name; /* Name of structure. */ + struct list_head flavors; /* List of RCU flavors. */ }; +extern struct list_head rcu_struct_flavors; +#define for_each_rcu_flavor(rsp) \ + list_for_each_entry((rsp), &rcu_struct_flavors, flavors) + /* Return values for rcu_preempt_offline_tasks(). */ #define RCU_OFL_TASKS_NORM_GP 0x1 /* Tasks blocking normal */ @@ -444,6 +463,7 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work); /* Forward declarations for rcutree_plugin.h */ static void rcu_bootup_announce(void); long rcu_batches_completed(void); +static void rcu_preempt_note_context_switch(int cpu); static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, @@ -452,25 +472,18 @@ static void rcu_stop_cpu_kthread(int cpu); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ static void rcu_print_detail_task_stall(struct rcu_state *rsp); static int rcu_print_task_stall(struct rcu_node *rnp); -static void rcu_preempt_stall_reset(void); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static int rcu_preempt_offline_tasks(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ -static void rcu_preempt_cleanup_dead_cpu(int cpu); static void rcu_preempt_check_callbacks(int cpu); -static void rcu_preempt_process_callbacks(void); void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake); #endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */ -static int rcu_preempt_pending(int cpu); -static int rcu_preempt_cpu_has_callbacks(int cpu); -static void __cpuinit rcu_preempt_init_percpu_data(int cpu); -static void rcu_preempt_cleanup_dying_cpu(void); static void __init __rcu_init_preempt(void); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 5271a020887e..7f3244c0df01 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -68,17 +68,21 @@ static void __init rcu_bootup_announce_oddness(void) printk(KERN_INFO "\tAdditional per-CPU info printed with stalls.\n"); #endif #if NUM_RCU_LVL_4 != 0 - printk(KERN_INFO "\tExperimental four-level hierarchy is enabled.\n"); + printk(KERN_INFO "\tFour-level hierarchy is enabled.\n"); #endif + if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF) + printk(KERN_INFO "\tExperimental boot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); + if (nr_cpu_ids != NR_CPUS) + printk(KERN_INFO "\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids); } #ifdef CONFIG_TREE_PREEMPT_RCU -struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt); +struct rcu_state rcu_preempt_state = + RCU_STATE_INITIALIZER(rcu_preempt, call_rcu); DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data); static struct rcu_state *rcu_state = &rcu_preempt_state; -static void rcu_read_unlock_special(struct task_struct *t); static int rcu_preempted_readers_exp(struct rcu_node *rnp); /* @@ -153,7 +157,7 @@ static void rcu_preempt_qs(int cpu) * * Caller must disable preemption. */ -void rcu_preempt_note_context_switch(void) +static void rcu_preempt_note_context_switch(int cpu) { struct task_struct *t = current; unsigned long flags; @@ -164,7 +168,7 @@ void rcu_preempt_note_context_switch(void) (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) { /* Possibly blocking in an RCU read-side critical section. */ - rdp = __this_cpu_ptr(rcu_preempt_state.rda); + rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu); rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED; @@ -228,23 +232,11 @@ void rcu_preempt_note_context_switch(void) * means that we continue to block the current grace period. */ local_irq_save(flags); - rcu_preempt_qs(smp_processor_id()); + rcu_preempt_qs(cpu); local_irq_restore(flags); } /* - * Tree-preemptible RCU implementation for rcu_read_lock(). - * Just increment ->rcu_read_lock_nesting, shared state will be updated - * if we block. - */ -void __rcu_read_lock(void) -{ - current->rcu_read_lock_nesting++; - barrier(); /* needed if we ever invoke rcu_read_lock in rcutree.c */ -} -EXPORT_SYMBOL_GPL(__rcu_read_lock); - -/* * Check for preempted RCU readers blocking the current grace period * for the specified rcu_node structure. If the caller needs a reliable * answer, it must hold the rcu_node's ->lock. @@ -310,7 +302,7 @@ static struct list_head *rcu_next_node_entry(struct task_struct *t, * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -static noinline void rcu_read_unlock_special(struct task_struct *t) +void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; @@ -398,8 +390,9 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) rnp->grphi, !!rnp->gp_tasks); rcu_report_unblock_qs_rnp(rnp, flags); - } else + } else { raw_spin_unlock_irqrestore(&rnp->lock, flags); + } #ifdef CONFIG_RCU_BOOST /* Unboost if we were boosted. */ @@ -418,38 +411,6 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) } } -/* - * Tree-preemptible RCU implementation for rcu_read_unlock(). - * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost - * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then - * invoke rcu_read_unlock_special() to clean up after a context switch - * in an RCU read-side critical section and other special cases. - */ -void __rcu_read_unlock(void) -{ - struct task_struct *t = current; - - if (t->rcu_read_lock_nesting != 1) - --t->rcu_read_lock_nesting; - else { - barrier(); /* critical section before exit code. */ - t->rcu_read_lock_nesting = INT_MIN; - barrier(); /* assign before ->rcu_read_unlock_special load */ - if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) - rcu_read_unlock_special(t); - barrier(); /* ->rcu_read_unlock_special load before assign */ - t->rcu_read_lock_nesting = 0; - } -#ifdef CONFIG_PROVE_LOCKING - { - int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); - - WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); - } -#endif /* #ifdef CONFIG_PROVE_LOCKING */ -} -EXPORT_SYMBOL_GPL(__rcu_read_unlock); - #ifdef CONFIG_RCU_CPU_STALL_VERBOSE /* @@ -540,16 +501,6 @@ static int rcu_print_task_stall(struct rcu_node *rnp) } /* - * Suppress preemptible RCU's CPU stall warnings by pushing the - * time of the next stall-warning message comfortably far into the - * future. - */ -static void rcu_preempt_stall_reset(void) -{ - rcu_preempt_state.jiffies_stall = jiffies + ULONG_MAX / 2; -} - -/* * Check that the list of blocked tasks for the newly completed grace * period is in fact empty. It is a serious bug to complete a grace * period that still has RCU readers blocked! This function must be @@ -650,14 +601,6 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, #endif /* #ifdef CONFIG_HOTPLUG_CPU */ /* - * Do CPU-offline processing for preemptible RCU. - */ -static void rcu_preempt_cleanup_dead_cpu(int cpu) -{ - rcu_cleanup_dead_cpu(cpu, &rcu_preempt_state); -} - -/* * Check for a quiescent state from the current CPU. When a task blocks, * the task is recorded in the corresponding CPU's rcu_node structure, * which is checked elsewhere. @@ -677,15 +620,6 @@ static void rcu_preempt_check_callbacks(int cpu) t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; } -/* - * Process callbacks for preemptible RCU. - */ -static void rcu_preempt_process_callbacks(void) -{ - __rcu_process_callbacks(&rcu_preempt_state, - &__get_cpu_var(rcu_preempt_data)); -} - #ifdef CONFIG_RCU_BOOST static void rcu_preempt_do_callbacks(void) @@ -824,9 +758,9 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) int must_wait = 0; raw_spin_lock_irqsave(&rnp->lock, flags); - if (list_empty(&rnp->blkd_tasks)) + if (list_empty(&rnp->blkd_tasks)) { raw_spin_unlock_irqrestore(&rnp->lock, flags); - else { + } else { rnp->exp_tasks = rnp->blkd_tasks.next; rcu_initiate_boost(rnp, flags); /* releases rnp->lock */ must_wait = 1; @@ -870,9 +804,9 @@ void synchronize_rcu_expedited(void) * expedited grace period for us, just leave. */ while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) { - if (trycount++ < 10) + if (trycount++ < 10) { udelay(trycount * num_online_cpus()); - else { + } else { synchronize_rcu(); return; } @@ -917,51 +851,16 @@ mb_ret: } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); -/* - * Check to see if there is any immediate preemptible-RCU-related work - * to be done. - */ -static int rcu_preempt_pending(int cpu) -{ - return __rcu_pending(&rcu_preempt_state, - &per_cpu(rcu_preempt_data, cpu)); -} - -/* - * Does preemptible RCU have callbacks on this CPU? - */ -static int rcu_preempt_cpu_has_callbacks(int cpu) -{ - return !!per_cpu(rcu_preempt_data, cpu).nxtlist; -} - /** * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete. */ void rcu_barrier(void) { - _rcu_barrier(&rcu_preempt_state, call_rcu); + _rcu_barrier(&rcu_preempt_state); } EXPORT_SYMBOL_GPL(rcu_barrier); /* - * Initialize preemptible RCU's per-CPU data. - */ -static void __cpuinit rcu_preempt_init_percpu_data(int cpu) -{ - rcu_init_percpu_data(cpu, &rcu_preempt_state, 1); -} - -/* - * Move preemptible RCU's callbacks from dying CPU to other online CPU - * and record a quiescent state. - */ -static void rcu_preempt_cleanup_dying_cpu(void) -{ - rcu_cleanup_dying_cpu(&rcu_preempt_state); -} - -/* * Initialize preemptible RCU's state structures. */ static void __init __rcu_init_preempt(void) @@ -1002,6 +901,14 @@ void rcu_force_quiescent_state(void) EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); /* + * Because preemptible RCU does not exist, we never have to check for + * CPUs being in quiescent states. + */ +static void rcu_preempt_note_context_switch(int cpu) +{ +} + +/* * Because preemptible RCU does not exist, there are never any preempted * RCU readers. */ @@ -1038,14 +945,6 @@ static int rcu_print_task_stall(struct rcu_node *rnp) } /* - * Because preemptible RCU does not exist, there is no need to suppress - * its CPU stall warnings. - */ -static void rcu_preempt_stall_reset(void) -{ -} - -/* * Because there is no preemptible RCU, there can be no readers blocked, * so there is no need to check for blocked tasks. So check only for * bogus qsmask values. @@ -1073,14 +972,6 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, #endif /* #ifdef CONFIG_HOTPLUG_CPU */ /* - * Because preemptible RCU does not exist, it never needs CPU-offline - * processing. - */ -static void rcu_preempt_cleanup_dead_cpu(int cpu) -{ -} - -/* * Because preemptible RCU does not exist, it never has any callbacks * to check. */ @@ -1089,14 +980,6 @@ static void rcu_preempt_check_callbacks(int cpu) } /* - * Because preemptible RCU does not exist, it never has any callbacks - * to process. - */ -static void rcu_preempt_process_callbacks(void) -{ -} - -/* * Queue an RCU callback for lazy invocation after a grace period. * This will likely be later named something like "call_rcu_lazy()", * but this change will require some way of tagging the lazy RCU @@ -1137,22 +1020,6 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, #endif /* #ifdef CONFIG_HOTPLUG_CPU */ /* - * Because preemptible RCU does not exist, it never has any work to do. - */ -static int rcu_preempt_pending(int cpu) -{ - return 0; -} - -/* - * Because preemptible RCU does not exist, it never has callbacks - */ -static int rcu_preempt_cpu_has_callbacks(int cpu) -{ - return 0; -} - -/* * Because preemptible RCU does not exist, rcu_barrier() is just * another name for rcu_barrier_sched(). */ @@ -1163,21 +1030,6 @@ void rcu_barrier(void) EXPORT_SYMBOL_GPL(rcu_barrier); /* - * Because preemptible RCU does not exist, there is no per-CPU - * data to initialize. - */ -static void __cpuinit rcu_preempt_init_percpu_data(int cpu) -{ -} - -/* - * Because there is no preemptible RCU, there is no cleanup to do. - */ -static void rcu_preempt_cleanup_dying_cpu(void) -{ -} - -/* * Because preemptible RCU does not exist, it need not be initialized. */ static void __init __rcu_init_preempt(void) @@ -1960,9 +1812,11 @@ static void rcu_idle_count_callbacks_posted(void) */ #define RCU_IDLE_FLUSHES 5 /* Number of dyntick-idle tries. */ #define RCU_IDLE_OPT_FLUSHES 3 /* Optional dyntick-idle tries. */ -#define RCU_IDLE_GP_DELAY 6 /* Roughly one grace period. */ +#define RCU_IDLE_GP_DELAY 4 /* Roughly one grace period. */ #define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */ +extern int tick_nohz_enabled; + /* * Does the specified flavor of RCU have non-lazy callbacks pending on * the specified CPU? Both RCU flavor and CPU are specified by the @@ -2039,10 +1893,13 @@ int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies) return 1; } /* Set up for the possibility that RCU will post a timer. */ - if (rcu_cpu_has_nonlazy_callbacks(cpu)) - *delta_jiffies = RCU_IDLE_GP_DELAY; - else - *delta_jiffies = RCU_IDLE_LAZY_GP_DELAY; + if (rcu_cpu_has_nonlazy_callbacks(cpu)) { + *delta_jiffies = round_up(RCU_IDLE_GP_DELAY + jiffies, + RCU_IDLE_GP_DELAY) - jiffies; + } else { + *delta_jiffies = jiffies + RCU_IDLE_LAZY_GP_DELAY; + *delta_jiffies = round_jiffies(*delta_jiffies) - jiffies; + } return 0; } @@ -2101,6 +1958,7 @@ static void rcu_cleanup_after_idle(int cpu) del_timer(&rdtp->idle_gp_timer); trace_rcu_prep_idle("Cleanup after idle"); + rdtp->tick_nohz_enabled_snap = ACCESS_ONCE(tick_nohz_enabled); } /* @@ -2126,6 +1984,18 @@ static void rcu_prepare_for_idle(int cpu) { struct timer_list *tp; struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); + int tne; + + /* Handle nohz enablement switches conservatively. */ + tne = ACCESS_ONCE(tick_nohz_enabled); + if (tne != rdtp->tick_nohz_enabled_snap) { + if (rcu_cpu_has_callbacks(cpu)) + invoke_rcu_core(); /* force nohz to see update. */ + rdtp->tick_nohz_enabled_snap = tne; + return; + } + if (!tne) + return; /* * If this is an idle re-entry, for example, due to use of @@ -2179,10 +2049,11 @@ static void rcu_prepare_for_idle(int cpu) if (rcu_cpu_has_nonlazy_callbacks(cpu)) { trace_rcu_prep_idle("Dyntick with callbacks"); rdtp->idle_gp_timer_expires = - jiffies + RCU_IDLE_GP_DELAY; + round_up(jiffies + RCU_IDLE_GP_DELAY, + RCU_IDLE_GP_DELAY); } else { rdtp->idle_gp_timer_expires = - jiffies + RCU_IDLE_LAZY_GP_DELAY; + round_jiffies(jiffies + RCU_IDLE_LAZY_GP_DELAY); trace_rcu_prep_idle("Dyntick with lazy callbacks"); } tp = &rdtp->idle_gp_timer; @@ -2223,8 +2094,9 @@ static void rcu_prepare_for_idle(int cpu) if (rcu_cpu_has_callbacks(cpu)) { trace_rcu_prep_idle("More callbacks"); invoke_rcu_core(); - } else + } else { trace_rcu_prep_idle("Callbacks drained"); + } } /* @@ -2261,6 +2133,7 @@ static void print_cpu_stall_fast_no_hz(char *cp, int cpu) static void print_cpu_stall_fast_no_hz(char *cp, int cpu) { + *cp = '\0'; } #endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */ diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index d4bc16ddd1d4..abffb486e94e 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -46,6 +46,31 @@ #define RCU_TREE_NONCORE #include "rcutree.h" +static int show_rcubarrier(struct seq_file *m, void *unused) +{ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + seq_printf(m, "%s: %c bcc: %d nbd: %lu\n", + rsp->name, rsp->rcu_barrier_in_progress ? 'B' : '.', + atomic_read(&rsp->barrier_cpu_count), + rsp->n_barrier_done); + return 0; +} + +static int rcubarrier_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcubarrier, NULL); +} + +static const struct file_operations rcubarrier_fops = { + .owner = THIS_MODULE, + .open = rcubarrier_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + #ifdef CONFIG_RCU_BOOST static char convert_kthread_status(unsigned int kthread_status) @@ -95,24 +120,16 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted); } -#define PRINT_RCU_DATA(name, func, m) \ - do { \ - int _p_r_d_i; \ - \ - for_each_possible_cpu(_p_r_d_i) \ - func(m, &per_cpu(name, _p_r_d_i)); \ - } while (0) - static int show_rcudata(struct seq_file *m, void *unused) { -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "rcu_preempt:\n"); - PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data, m); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "rcu_sched:\n"); - PRINT_RCU_DATA(rcu_sched_data, print_one_rcu_data, m); - seq_puts(m, "rcu_bh:\n"); - PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data, m); + int cpu; + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) { + seq_printf(m, "%s:\n", rsp->name); + for_each_possible_cpu(cpu) + print_one_rcu_data(m, per_cpu_ptr(rsp->rda, cpu)); + } return 0; } @@ -166,6 +183,9 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) static int show_rcudata_csv(struct seq_file *m, void *unused) { + int cpu; + struct rcu_state *rsp; + seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pgp\",\"pq\","); seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\","); seq_puts(m, "\"of\",\"qll\",\"ql\",\"qs\""); @@ -173,14 +193,11 @@ static int show_rcudata_csv(struct seq_file *m, void *unused) seq_puts(m, "\"kt\",\"ktl\""); #endif /* #ifdef CONFIG_RCU_BOOST */ seq_puts(m, ",\"b\",\"ci\",\"co\",\"ca\"\n"); -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "\"rcu_preempt:\"\n"); - PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data_csv, m); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "\"rcu_sched:\"\n"); - PRINT_RCU_DATA(rcu_sched_data, print_one_rcu_data_csv, m); - seq_puts(m, "\"rcu_bh:\"\n"); - PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data_csv, m); + for_each_rcu_flavor(rsp) { + seq_printf(m, "\"%s:\"\n", rsp->name); + for_each_possible_cpu(cpu) + print_one_rcu_data_csv(m, per_cpu_ptr(rsp->rda, cpu)); + } return 0; } @@ -201,8 +218,7 @@ static const struct file_operations rcudata_csv_fops = { static void print_one_rcu_node_boost(struct seq_file *m, struct rcu_node *rnp) { - seq_printf(m, "%d:%d tasks=%c%c%c%c kt=%c ntb=%lu neb=%lu nnb=%lu " - "j=%04x bt=%04x\n", + seq_printf(m, "%d:%d tasks=%c%c%c%c kt=%c ntb=%lu neb=%lu nnb=%lu ", rnp->grplo, rnp->grphi, "T."[list_empty(&rnp->blkd_tasks)], "N."[!rnp->gp_tasks], @@ -210,11 +226,11 @@ static void print_one_rcu_node_boost(struct seq_file *m, struct rcu_node *rnp) "B."[!rnp->boost_tasks], convert_kthread_status(rnp->boost_kthread_status), rnp->n_tasks_boosted, rnp->n_exp_boosts, - rnp->n_normal_boosts, + rnp->n_normal_boosts); + seq_printf(m, "j=%04x bt=%04x\n", (int)(jiffies & 0xffff), (int)(rnp->boost_time & 0xffff)); - seq_printf(m, "%s: nt=%lu egt=%lu bt=%lu nb=%lu ny=%lu nos=%lu\n", - " balk", + seq_printf(m, " balk: nt=%lu egt=%lu bt=%lu nb=%lu ny=%lu nos=%lu\n", rnp->n_balk_blkd_tasks, rnp->n_balk_exp_gp_tasks, rnp->n_balk_boost_tasks, @@ -270,15 +286,15 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) struct rcu_node *rnp; gpnum = rsp->gpnum; - seq_printf(m, "c=%lu g=%lu s=%d jfq=%ld j=%x " - "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n", - rsp->completed, gpnum, rsp->fqs_state, + seq_printf(m, "%s: c=%lu g=%lu s=%d jfq=%ld j=%x ", + rsp->name, rsp->completed, gpnum, rsp->fqs_state, (long)(rsp->jiffies_force_qs - jiffies), - (int)(jiffies & 0xffff), + (int)(jiffies & 0xffff)); + seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n", rsp->n_force_qs, rsp->n_force_qs_ngp, rsp->n_force_qs - rsp->n_force_qs_ngp, rsp->n_force_qs_lh, rsp->qlen_lazy, rsp->qlen); - for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) { + for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) { if (rnp->level != level) { seq_puts(m, "\n"); level = rnp->level; @@ -295,14 +311,10 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) static int show_rcuhier(struct seq_file *m, void *unused) { -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "rcu_preempt:\n"); - print_one_rcu_state(m, &rcu_preempt_state); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "rcu_sched:\n"); - print_one_rcu_state(m, &rcu_sched_state); - seq_puts(m, "rcu_bh:\n"); - print_one_rcu_state(m, &rcu_bh_state); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + print_one_rcu_state(m, rsp); return 0; } @@ -343,11 +355,10 @@ static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp) static int show_rcugp(struct seq_file *m, void *unused) { -#ifdef CONFIG_TREE_PREEMPT_RCU - show_one_rcugp(m, &rcu_preempt_state); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - show_one_rcugp(m, &rcu_sched_state); - show_one_rcugp(m, &rcu_bh_state); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + show_one_rcugp(m, rsp); return 0; } @@ -366,44 +377,36 @@ static const struct file_operations rcugp_fops = { static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp) { - seq_printf(m, "%3d%cnp=%ld " - "qsp=%ld rpq=%ld cbr=%ld cng=%ld " - "gpc=%ld gps=%ld nf=%ld nn=%ld\n", + seq_printf(m, "%3d%cnp=%ld ", rdp->cpu, cpu_is_offline(rdp->cpu) ? '!' : ' ', - rdp->n_rcu_pending, + rdp->n_rcu_pending); + seq_printf(m, "qsp=%ld rpq=%ld cbr=%ld cng=%ld ", rdp->n_rp_qs_pending, rdp->n_rp_report_qs, rdp->n_rp_cb_ready, - rdp->n_rp_cpu_needs_gp, + rdp->n_rp_cpu_needs_gp); + seq_printf(m, "gpc=%ld gps=%ld nf=%ld nn=%ld\n", rdp->n_rp_gp_completed, rdp->n_rp_gp_started, rdp->n_rp_need_fqs, rdp->n_rp_need_nothing); } -static void print_rcu_pendings(struct seq_file *m, struct rcu_state *rsp) +static int show_rcu_pending(struct seq_file *m, void *unused) { int cpu; struct rcu_data *rdp; - - for_each_possible_cpu(cpu) { - rdp = per_cpu_ptr(rsp->rda, cpu); - if (rdp->beenonline) - print_one_rcu_pending(m, rdp); + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) { + seq_printf(m, "%s:\n", rsp->name); + for_each_possible_cpu(cpu) { + rdp = per_cpu_ptr(rsp->rda, cpu); + if (rdp->beenonline) + print_one_rcu_pending(m, rdp); + } } -} - -static int show_rcu_pending(struct seq_file *m, void *unused) -{ -#ifdef CONFIG_TREE_PREEMPT_RCU - seq_puts(m, "rcu_preempt:\n"); - print_rcu_pendings(m, &rcu_preempt_state); -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_puts(m, "rcu_sched:\n"); - print_rcu_pendings(m, &rcu_sched_state); - seq_puts(m, "rcu_bh:\n"); - print_rcu_pendings(m, &rcu_bh_state); return 0; } @@ -453,6 +456,11 @@ static int __init rcutree_trace_init(void) if (!rcudir) goto free_out; + retval = debugfs_create_file("rcubarrier", 0444, rcudir, + NULL, &rcubarrier_fops); + if (!retval) + goto free_out; + retval = debugfs_create_file("rcudata", 0444, rcudir, NULL, &rcudata_fops); if (!retval) diff --git a/kernel/relay.c b/kernel/relay.c index ab56a1764d4d..e8cd2027abbd 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -1235,6 +1235,7 @@ static ssize_t subbuf_splice_actor(struct file *in, struct splice_pipe_desc spd = { .pages = pages, .nr_pages = 0, + .nr_pages_max = PIPE_DEF_BUFFERS, .partial = partial, .flags = flags, .ops = &relay_pipe_buf_ops, @@ -1302,8 +1303,8 @@ static ssize_t subbuf_splice_actor(struct file *in, ret += padding; out: - splice_shrink_spd(pipe, &spd); - return ret; + splice_shrink_spd(&spd); + return ret; } static ssize_t relay_file_splice_read(struct file *in, diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d5594a4268d4..468bdd44c1ba 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2081,7 +2081,6 @@ context_switch(struct rq *rq, struct task_struct *prev, #endif /* Here we just switch the register state and the stack. */ - rcu_switch_from(prev); switch_to(prev, next, prev); barrier(); @@ -2161,11 +2160,73 @@ unsigned long this_cpu_load(void) } +/* + * Global load-average calculations + * + * We take a distributed and async approach to calculating the global load-avg + * in order to minimize overhead. + * + * The global load average is an exponentially decaying average of nr_running + + * nr_uninterruptible. + * + * Once every LOAD_FREQ: + * + * nr_active = 0; + * for_each_possible_cpu(cpu) + * nr_active += cpu_of(cpu)->nr_running + cpu_of(cpu)->nr_uninterruptible; + * + * avenrun[n] = avenrun[0] * exp_n + nr_active * (1 - exp_n) + * + * Due to a number of reasons the above turns in the mess below: + * + * - for_each_possible_cpu() is prohibitively expensive on machines with + * serious number of cpus, therefore we need to take a distributed approach + * to calculating nr_active. + * + * \Sum_i x_i(t) = \Sum_i x_i(t) - x_i(t_0) | x_i(t_0) := 0 + * = \Sum_i { \Sum_j=1 x_i(t_j) - x_i(t_j-1) } + * + * So assuming nr_active := 0 when we start out -- true per definition, we + * can simply take per-cpu deltas and fold those into a global accumulate + * to obtain the same result. See calc_load_fold_active(). + * + * Furthermore, in order to avoid synchronizing all per-cpu delta folding + * across the machine, we assume 10 ticks is sufficient time for every + * cpu to have completed this task. + * + * This places an upper-bound on the IRQ-off latency of the machine. Then + * again, being late doesn't loose the delta, just wrecks the sample. + * + * - cpu_rq()->nr_uninterruptible isn't accurately tracked per-cpu because + * this would add another cross-cpu cacheline miss and atomic operation + * to the wakeup path. Instead we increment on whatever cpu the task ran + * when it went into uninterruptible state and decrement on whatever cpu + * did the wakeup. This means that only the sum of nr_uninterruptible over + * all cpus yields the correct result. + * + * This covers the NO_HZ=n code, for extra head-aches, see the comment below. + */ + /* Variables and functions for calc_load */ static atomic_long_t calc_load_tasks; static unsigned long calc_load_update; unsigned long avenrun[3]; -EXPORT_SYMBOL(avenrun); +EXPORT_SYMBOL(avenrun); /* should be removed */ + +/** + * get_avenrun - get the load average array + * @loads: pointer to dest load array + * @offset: offset to add + * @shift: shift count to shift the result left + * + * These values are estimates at best, so no need for locking. + */ +void get_avenrun(unsigned long *loads, unsigned long offset, int shift) +{ + loads[0] = (avenrun[0] + offset) << shift; + loads[1] = (avenrun[1] + offset) << shift; + loads[2] = (avenrun[2] + offset) << shift; +} static long calc_load_fold_active(struct rq *this_rq) { @@ -2182,6 +2243,9 @@ static long calc_load_fold_active(struct rq *this_rq) return delta; } +/* + * a1 = a0 * e + a * (1 - e) + */ static unsigned long calc_load(unsigned long load, unsigned long exp, unsigned long active) { @@ -2193,30 +2257,118 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) #ifdef CONFIG_NO_HZ /* - * For NO_HZ we delay the active fold to the next LOAD_FREQ update. + * Handle NO_HZ for the global load-average. + * + * Since the above described distributed algorithm to compute the global + * load-average relies on per-cpu sampling from the tick, it is affected by + * NO_HZ. + * + * The basic idea is to fold the nr_active delta into a global idle-delta upon + * entering NO_HZ state such that we can include this as an 'extra' cpu delta + * when we read the global state. + * + * Obviously reality has to ruin such a delightfully simple scheme: + * + * - When we go NO_HZ idle during the window, we can negate our sample + * contribution, causing under-accounting. + * + * We avoid this by keeping two idle-delta counters and flipping them + * when the window starts, thus separating old and new NO_HZ load. + * + * The only trick is the slight shift in index flip for read vs write. + * + * 0s 5s 10s 15s + * +10 +10 +10 +10 + * |-|-----------|-|-----------|-|-----------|-| + * r:0 0 1 1 0 0 1 1 0 + * w:0 1 1 0 0 1 1 0 0 + * + * This ensures we'll fold the old idle contribution in this window while + * accumlating the new one. + * + * - When we wake up from NO_HZ idle during the window, we push up our + * contribution, since we effectively move our sample point to a known + * busy state. + * + * This is solved by pushing the window forward, and thus skipping the + * sample, for this cpu (effectively using the idle-delta for this cpu which + * was in effect at the time the window opened). This also solves the issue + * of having to deal with a cpu having been in NOHZ idle for multiple + * LOAD_FREQ intervals. * * When making the ILB scale, we should try to pull this in as well. */ -static atomic_long_t calc_load_tasks_idle; +static atomic_long_t calc_load_idle[2]; +static int calc_load_idx; -void calc_load_account_idle(struct rq *this_rq) +static inline int calc_load_write_idx(void) { + int idx = calc_load_idx; + + /* + * See calc_global_nohz(), if we observe the new index, we also + * need to observe the new update time. + */ + smp_rmb(); + + /* + * If the folding window started, make sure we start writing in the + * next idle-delta. + */ + if (!time_before(jiffies, calc_load_update)) + idx++; + + return idx & 1; +} + +static inline int calc_load_read_idx(void) +{ + return calc_load_idx & 1; +} + +void calc_load_enter_idle(void) +{ + struct rq *this_rq = this_rq(); long delta; + /* + * We're going into NOHZ mode, if there's any pending delta, fold it + * into the pending idle delta. + */ delta = calc_load_fold_active(this_rq); - if (delta) - atomic_long_add(delta, &calc_load_tasks_idle); + if (delta) { + int idx = calc_load_write_idx(); + atomic_long_add(delta, &calc_load_idle[idx]); + } } -static long calc_load_fold_idle(void) +void calc_load_exit_idle(void) { - long delta = 0; + struct rq *this_rq = this_rq(); + + /* + * If we're still before the sample window, we're done. + */ + if (time_before(jiffies, this_rq->calc_load_update)) + return; /* - * Its got a race, we don't care... + * We woke inside or after the sample window, this means we're already + * accounted through the nohz accounting, so skip the entire deal and + * sync up for the next window. */ - if (atomic_long_read(&calc_load_tasks_idle)) - delta = atomic_long_xchg(&calc_load_tasks_idle, 0); + this_rq->calc_load_update = calc_load_update; + if (time_before(jiffies, this_rq->calc_load_update + 10)) + this_rq->calc_load_update += LOAD_FREQ; +} + +static long calc_load_fold_idle(void) +{ + int idx = calc_load_read_idx(); + long delta = 0; + + if (atomic_long_read(&calc_load_idle[idx])) + delta = atomic_long_xchg(&calc_load_idle[idx], 0); return delta; } @@ -2302,66 +2454,39 @@ static void calc_global_nohz(void) { long delta, active, n; - /* - * If we crossed a calc_load_update boundary, make sure to fold - * any pending idle changes, the respective CPUs might have - * missed the tick driven calc_load_account_active() update - * due to NO_HZ. - */ - delta = calc_load_fold_idle(); - if (delta) - atomic_long_add(delta, &calc_load_tasks); - - /* - * It could be the one fold was all it took, we done! - */ - if (time_before(jiffies, calc_load_update + 10)) - return; - - /* - * Catch-up, fold however many we are behind still - */ - delta = jiffies - calc_load_update - 10; - n = 1 + (delta / LOAD_FREQ); + if (!time_before(jiffies, calc_load_update + 10)) { + /* + * Catch-up, fold however many we are behind still + */ + delta = jiffies - calc_load_update - 10; + n = 1 + (delta / LOAD_FREQ); - active = atomic_long_read(&calc_load_tasks); - active = active > 0 ? active * FIXED_1 : 0; + active = atomic_long_read(&calc_load_tasks); + active = active > 0 ? active * FIXED_1 : 0; - avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n); - avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); - avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); + avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n); + avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); + avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); - calc_load_update += n * LOAD_FREQ; -} -#else -void calc_load_account_idle(struct rq *this_rq) -{ -} + calc_load_update += n * LOAD_FREQ; + } -static inline long calc_load_fold_idle(void) -{ - return 0; + /* + * Flip the idle index... + * + * Make sure we first write the new time then flip the index, so that + * calc_load_write_idx() will see the new time when it reads the new + * index, this avoids a double flip messing things up. + */ + smp_wmb(); + calc_load_idx++; } +#else /* !CONFIG_NO_HZ */ -static void calc_global_nohz(void) -{ -} -#endif +static inline long calc_load_fold_idle(void) { return 0; } +static inline void calc_global_nohz(void) { } -/** - * get_avenrun - get the load average array - * @loads: pointer to dest load array - * @offset: offset to add - * @shift: shift count to shift the result left - * - * These values are estimates at best, so no need for locking. - */ -void get_avenrun(unsigned long *loads, unsigned long offset, int shift) -{ - loads[0] = (avenrun[0] + offset) << shift; - loads[1] = (avenrun[1] + offset) << shift; - loads[2] = (avenrun[2] + offset) << shift; -} +#endif /* CONFIG_NO_HZ */ /* * calc_load - update the avenrun load estimates 10 ticks after the @@ -2369,11 +2494,18 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift) */ void calc_global_load(unsigned long ticks) { - long active; + long active, delta; if (time_before(jiffies, calc_load_update + 10)) return; + /* + * Fold the 'old' idle-delta to include all NO_HZ cpus. + */ + delta = calc_load_fold_idle(); + if (delta) + atomic_long_add(delta, &calc_load_tasks); + active = atomic_long_read(&calc_load_tasks); active = active > 0 ? active * FIXED_1 : 0; @@ -2384,12 +2516,7 @@ void calc_global_load(unsigned long ticks) calc_load_update += LOAD_FREQ; /* - * Account one period with whatever state we found before - * folding in the nohz state and ageing the entire idle period. - * - * This avoids loosing a sample when we go idle between - * calc_load_account_active() (10 ticks ago) and now and thus - * under-accounting. + * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk. */ calc_global_nohz(); } @@ -2406,7 +2533,6 @@ static void calc_load_account_active(struct rq *this_rq) return; delta = calc_load_fold_active(this_rq); - delta += calc_load_fold_idle(); if (delta) atomic_long_add(delta, &calc_load_tasks); @@ -2414,6 +2540,10 @@ static void calc_load_account_active(struct rq *this_rq) } /* + * End of global load-average stuff + */ + +/* * The exact cpuload at various idx values, calculated at every tick would be * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load * diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index b44d604b35d1..b6baf370cae9 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -25,7 +25,6 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static struct task_struct *pick_next_task_idle(struct rq *rq) { schedstat_inc(rq, sched_goidle); - calc_load_account_idle(rq); return rq->idle; } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 6d52cea7f33d..55844f24435a 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -942,8 +942,6 @@ static inline u64 sched_avg_period(void) return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2; } -void calc_load_account_idle(struct rq *this_rq); - #ifdef CONFIG_SCHED_HRTICK /* diff --git a/kernel/signal.c b/kernel/signal.c index 677102789cf2..be4f856d52f8 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1971,6 +1971,13 @@ static void ptrace_do_notify(int signr, int exit_code, int why) void ptrace_notify(int exit_code) { BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP); + if (unlikely(current->task_works)) { + if (test_and_clear_ti_thread_flag(current_thread_info(), + TIF_NOTIFY_RESUME)) { + smp_mb__after_clear_bit(); + task_work_run(); + } + } spin_lock_irq(¤t->sighand->siglock); ptrace_do_notify(SIGTRAP, exit_code, CLD_TRAPPED); @@ -2191,6 +2198,14 @@ int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka, struct signal_struct *signal = current->signal; int signr; + if (unlikely(current->task_works)) { + if (test_and_clear_ti_thread_flag(current_thread_info(), + TIF_NOTIFY_RESUME)) { + smp_mb__after_clear_bit(); + task_work_run(); + } + } + if (unlikely(uprobe_deny_signal())) return 0; diff --git a/kernel/smp.c b/kernel/smp.c index d0ae5b24875e..29dd40a9f2f4 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -581,26 +581,6 @@ int smp_call_function(smp_call_func_t func, void *info, int wait) return 0; } EXPORT_SYMBOL(smp_call_function); - -void ipi_call_lock(void) -{ - raw_spin_lock(&call_function.lock); -} - -void ipi_call_unlock(void) -{ - raw_spin_unlock(&call_function.lock); -} - -void ipi_call_lock_irq(void) -{ - raw_spin_lock_irq(&call_function.lock); -} - -void ipi_call_unlock_irq(void) -{ - raw_spin_unlock_irq(&call_function.lock); -} #endif /* USE_GENERIC_SMP_HELPERS */ /* Setup configured maximum number of CPUs to activate */ diff --git a/kernel/smpboot.h b/kernel/smpboot.h index 80c0acfb8472..6ef9433e1c70 100644 --- a/kernel/smpboot.h +++ b/kernel/smpboot.h @@ -3,8 +3,6 @@ struct task_struct; -int smpboot_prepare(unsigned int cpu); - #ifdef CONFIG_GENERIC_SMP_IDLE_THREAD struct task_struct *idle_thread_get(unsigned int cpu); void idle_thread_set_boot_cpu(void); diff --git a/kernel/sys.c b/kernel/sys.c index e0c8ffc50d7f..2d39a84cd857 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1788,7 +1788,6 @@ SYSCALL_DEFINE1(umask, int, mask) #ifdef CONFIG_CHECKPOINT_RESTORE static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) { - struct vm_area_struct *vma; struct file *exe_file; struct dentry *dentry; int err; @@ -1816,13 +1815,17 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) down_write(&mm->mmap_sem); /* - * Forbid mm->exe_file change if there are mapped other files. + * Forbid mm->exe_file change if old file still mapped. */ err = -EBUSY; - for (vma = mm->mmap; vma; vma = vma->vm_next) { - if (vma->vm_file && !path_equal(&vma->vm_file->f_path, - &exe_file->f_path)) - goto exit_unlock; + if (mm->exe_file) { + struct vm_area_struct *vma; + + for (vma = mm->mmap; vma; vma = vma->vm_next) + if (vma->vm_file && + path_equal(&vma->vm_file->f_path, + &mm->exe_file->f_path)) + goto exit_unlock; } /* @@ -1835,6 +1838,7 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) if (test_and_set_bit(MMF_EXE_FILE_CHANGED, &mm->flags)) goto exit_unlock; + err = 0; set_mm_exe_file(mm, exe_file); exit_unlock: up_write(&mm->mmap_sem); diff --git a/kernel/task_work.c b/kernel/task_work.c index 82d1c794066d..91d4e1742a0c 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -3,82 +3,78 @@ #include <linux/tracehook.h> int -task_work_add(struct task_struct *task, struct task_work *twork, bool notify) +task_work_add(struct task_struct *task, struct callback_head *twork, bool notify) { + struct callback_head *last, *first; unsigned long flags; - int err = -ESRCH; -#ifndef TIF_NOTIFY_RESUME - if (notify) - return -ENOTSUPP; -#endif /* - * We must not insert the new work if the task has already passed - * exit_task_work(). We rely on do_exit()->raw_spin_unlock_wait() - * and check PF_EXITING under pi_lock. + * Not inserting the new work if the task has already passed + * exit_task_work() is the responisbility of callers. */ raw_spin_lock_irqsave(&task->pi_lock, flags); - if (likely(!(task->flags & PF_EXITING))) { - hlist_add_head(&twork->hlist, &task->task_works); - err = 0; - } + last = task->task_works; + first = last ? last->next : twork; + twork->next = first; + if (last) + last->next = twork; + task->task_works = twork; raw_spin_unlock_irqrestore(&task->pi_lock, flags); /* test_and_set_bit() implies mb(), see tracehook_notify_resume(). */ - if (likely(!err) && notify) + if (notify) set_notify_resume(task); - return err; + return 0; } -struct task_work * +struct callback_head * task_work_cancel(struct task_struct *task, task_work_func_t func) { unsigned long flags; - struct task_work *twork; - struct hlist_node *pos; + struct callback_head *last, *res = NULL; raw_spin_lock_irqsave(&task->pi_lock, flags); - hlist_for_each_entry(twork, pos, &task->task_works, hlist) { - if (twork->func == func) { - hlist_del(&twork->hlist); - goto found; + last = task->task_works; + if (last) { + struct callback_head *q = last, *p = q->next; + while (1) { + if (p->func == func) { + q->next = p->next; + if (p == last) + task->task_works = q == p ? NULL : q; + res = p; + break; + } + if (p == last) + break; + q = p; + p = q->next; } } - twork = NULL; - found: raw_spin_unlock_irqrestore(&task->pi_lock, flags); - - return twork; + return res; } void task_work_run(void) { struct task_struct *task = current; - struct hlist_head task_works; - struct hlist_node *pos; + struct callback_head *p, *q; - raw_spin_lock_irq(&task->pi_lock); - hlist_move_list(&task->task_works, &task_works); - raw_spin_unlock_irq(&task->pi_lock); + while (1) { + raw_spin_lock_irq(&task->pi_lock); + p = task->task_works; + task->task_works = NULL; + raw_spin_unlock_irq(&task->pi_lock); - if (unlikely(hlist_empty(&task_works))) - return; - /* - * We use hlist to save the space in task_struct, but we want fifo. - * Find the last entry, the list should be short, then process them - * in reverse order. - */ - for (pos = task_works.first; pos->next; pos = pos->next) - ; + if (unlikely(!p)) + return; - for (;;) { - struct hlist_node **pprev = pos->pprev; - struct task_work *twork = container_of(pos, struct task_work, - hlist); - twork->func(twork); - - if (pprev == &task_works.first) - break; - pos = container_of(pprev, struct hlist_node, next); + q = p->next; /* head */ + p->next = NULL; /* cut it */ + while (q) { + p = q->next; + q->func(q); + q = p; + } } } diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 70b33abcc7bb..b7fbadc5c973 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -409,7 +409,9 @@ int second_overflow(unsigned long secs) time_state = TIME_DEL; break; case TIME_INS: - if (secs % 86400 == 0) { + if (!(time_status & STA_INS)) + time_state = TIME_OK; + else if (secs % 86400 == 0) { leap = -1; time_state = TIME_OOP; time_tai++; @@ -418,7 +420,9 @@ int second_overflow(unsigned long secs) } break; case TIME_DEL: - if ((secs + 1) % 86400 == 0) { + if (!(time_status & STA_DEL)) + time_state = TIME_OK; + else if ((secs + 1) % 86400 == 0) { leap = 1; time_tai--; time_state = TIME_WAIT; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 869997833928..024540f97f74 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -105,7 +105,7 @@ static ktime_t tick_init_jiffy_update(void) /* * NO HZ enabled ? */ -static int tick_nohz_enabled __read_mostly = 1; +int tick_nohz_enabled __read_mostly = 1; /* * Enable / Disable tickless mode @@ -271,50 +271,15 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) } EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us); -static void tick_nohz_stop_sched_tick(struct tick_sched *ts) +static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, + ktime_t now, int cpu) { unsigned long seq, last_jiffies, next_jiffies, delta_jiffies; + ktime_t last_update, expires, ret = { .tv64 = 0 }; unsigned long rcu_delta_jiffies; - ktime_t last_update, expires, now; struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev; u64 time_delta; - int cpu; - - cpu = smp_processor_id(); - ts = &per_cpu(tick_cpu_sched, cpu); - - now = tick_nohz_start_idle(cpu, ts); - - /* - * If this cpu is offline and it is the one which updates - * jiffies, then give up the assignment and let it be taken by - * the cpu which runs the tick timer next. If we don't drop - * this here the jiffies might be stale and do_timer() never - * invoked. - */ - if (unlikely(!cpu_online(cpu))) { - if (cpu == tick_do_timer_cpu) - tick_do_timer_cpu = TICK_DO_TIMER_NONE; - } - - if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) - return; - if (need_resched()) - return; - - if (unlikely(local_softirq_pending() && cpu_online(cpu))) { - static int ratelimit; - - if (ratelimit < 10) { - printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", - (unsigned int) local_softirq_pending()); - ratelimit++; - } - return; - } - - ts->idle_calls++; /* Read jiffies and the time when jiffies were updated last */ do { seq = read_seqbegin(&xtime_lock); @@ -397,6 +362,8 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts) if (ts->tick_stopped && ktime_equal(expires, dev->next_event)) goto out; + ret = expires; + /* * nohz_stop_sched_tick can be called several times before * the nohz_restart_sched_tick is called. This happens when @@ -406,17 +373,12 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts) */ if (!ts->tick_stopped) { select_nohz_load_balancer(1); + calc_load_enter_idle(); - ts->idle_tick = hrtimer_get_expires(&ts->sched_timer); + ts->last_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; - ts->idle_jiffies = last_jiffies; } - ts->idle_sleeps++; - - /* Mark expires */ - ts->idle_expires = expires; - /* * If the expiration time == KTIME_MAX, then * in this case we simply stop the tick timer. @@ -447,6 +409,65 @@ out: ts->next_jiffies = next_jiffies; ts->last_jiffies = last_jiffies; ts->sleep_length = ktime_sub(dev->next_event, now); + + return ret; +} + +static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) +{ + /* + * If this cpu is offline and it is the one which updates + * jiffies, then give up the assignment and let it be taken by + * the cpu which runs the tick timer next. If we don't drop + * this here the jiffies might be stale and do_timer() never + * invoked. + */ + if (unlikely(!cpu_online(cpu))) { + if (cpu == tick_do_timer_cpu) + tick_do_timer_cpu = TICK_DO_TIMER_NONE; + } + + if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) + return false; + + if (need_resched()) + return false; + + if (unlikely(local_softirq_pending() && cpu_online(cpu))) { + static int ratelimit; + + if (ratelimit < 10) { + printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", + (unsigned int) local_softirq_pending()); + ratelimit++; + } + return false; + } + + return true; +} + +static void __tick_nohz_idle_enter(struct tick_sched *ts) +{ + ktime_t now, expires; + int cpu = smp_processor_id(); + + now = tick_nohz_start_idle(cpu, ts); + + if (can_stop_idle_tick(cpu, ts)) { + int was_stopped = ts->tick_stopped; + + ts->idle_calls++; + + expires = tick_nohz_stop_sched_tick(ts, now, cpu); + if (expires.tv64 > 0LL) { + ts->idle_sleeps++; + ts->idle_expires = expires; + } + + if (!was_stopped && ts->tick_stopped) + ts->idle_jiffies = ts->last_jiffies; + } } /** @@ -484,7 +505,7 @@ void tick_nohz_idle_enter(void) * update of the idle time accounting in tick_nohz_start_idle(). */ ts->inidle = 1; - tick_nohz_stop_sched_tick(ts); + __tick_nohz_idle_enter(ts); local_irq_enable(); } @@ -504,7 +525,7 @@ void tick_nohz_irq_exit(void) if (!ts->inidle) return; - tick_nohz_stop_sched_tick(ts); + __tick_nohz_idle_enter(ts); } /** @@ -522,7 +543,7 @@ ktime_t tick_nohz_get_sleep_length(void) static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) { hrtimer_cancel(&ts->sched_timer); - hrtimer_set_expires(&ts->sched_timer, ts->idle_tick); + hrtimer_set_expires(&ts->sched_timer, ts->last_tick); while (1) { /* Forward the time to expire in the future */ @@ -545,6 +566,41 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) } } +static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) +{ + /* Update jiffies first */ + select_nohz_load_balancer(0); + tick_do_update_jiffies64(now); + update_cpu_load_nohz(); + + touch_softlockup_watchdog(); + /* + * Cancel the scheduled timer and restore the tick + */ + ts->tick_stopped = 0; + ts->idle_exittime = now; + + tick_nohz_restart(ts, now); +} + +static void tick_nohz_account_idle_ticks(struct tick_sched *ts) +{ +#ifndef CONFIG_VIRT_CPU_ACCOUNTING + unsigned long ticks; + /* + * We stopped the tick in idle. Update process times would miss the + * time we slept as update_process_times does only a 1 tick + * accounting. Enforce that this is accounted to idle ! + */ + ticks = jiffies - ts->idle_jiffies; + /* + * We might be one off. Do not randomly account a huge number of ticks! + */ + if (ticks && ticks < LONG_MAX) + account_idle_ticks(ticks); +#endif +} + /** * tick_nohz_idle_exit - restart the idle tick from the idle task * @@ -556,9 +612,6 @@ void tick_nohz_idle_exit(void) { int cpu = smp_processor_id(); struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); -#ifndef CONFIG_VIRT_CPU_ACCOUNTING - unsigned long ticks; -#endif ktime_t now; local_irq_disable(); @@ -573,39 +626,11 @@ void tick_nohz_idle_exit(void) if (ts->idle_active) tick_nohz_stop_idle(cpu, now); - if (!ts->tick_stopped) { - local_irq_enable(); - return; + if (ts->tick_stopped) { + tick_nohz_restart_sched_tick(ts, now); + tick_nohz_account_idle_ticks(ts); } - /* Update jiffies first */ - select_nohz_load_balancer(0); - tick_do_update_jiffies64(now); - update_cpu_load_nohz(); - -#ifndef CONFIG_VIRT_CPU_ACCOUNTING - /* - * We stopped the tick in idle. Update process times would miss the - * time we slept as update_process_times does only a 1 tick - * accounting. Enforce that this is accounted to idle ! - */ - ticks = jiffies - ts->idle_jiffies; - /* - * We might be one off. Do not randomly account a huge number of ticks! - */ - if (ticks && ticks < LONG_MAX) - account_idle_ticks(ticks); -#endif - - touch_softlockup_watchdog(); - /* - * Cancel the scheduled timer and restore the tick - */ - ts->tick_stopped = 0; - ts->idle_exittime = now; - - tick_nohz_restart(ts, now); - local_irq_enable(); } @@ -809,7 +834,8 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer) */ if (ts->tick_stopped) { touch_softlockup_watchdog(); - ts->idle_jiffies++; + if (idle_cpu(cpu)) + ts->idle_jiffies++; } update_process_times(user_mode(regs)); profile_tick(CPU_PROFILING); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 6f46a00a1e8a..f045cc50832d 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -24,32 +24,32 @@ /* Structure holding internal timekeeping values. */ struct timekeeper { /* Current clocksource used for timekeeping. */ - struct clocksource *clock; + struct clocksource *clock; /* NTP adjusted clock multiplier */ - u32 mult; + u32 mult; /* The shift value of the current clocksource. */ - int shift; - + u32 shift; /* Number of clock cycles in one NTP interval. */ - cycle_t cycle_interval; + cycle_t cycle_interval; /* Number of clock shifted nano seconds in one NTP interval. */ - u64 xtime_interval; + u64 xtime_interval; /* shifted nano seconds left over when rounding cycle_interval */ - s64 xtime_remainder; + s64 xtime_remainder; /* Raw nano seconds accumulated per NTP interval. */ - u32 raw_interval; + u32 raw_interval; + + /* Current CLOCK_REALTIME time in seconds */ + u64 xtime_sec; + /* Clock shifted nano seconds */ + u64 xtime_nsec; - /* Clock shifted nano seconds remainder not stored in xtime.tv_nsec. */ - u64 xtime_nsec; /* Difference between accumulated time and NTP time in ntp * shifted nano seconds. */ - s64 ntp_error; + s64 ntp_error; /* Shift conversion between clock shifted nano seconds and * ntp shifted nano seconds. */ - int ntp_error_shift; + u32 ntp_error_shift; - /* The current time */ - struct timespec xtime; /* * wall_to_monotonic is what we need to add to xtime (or xtime corrected * for sub jiffie times) to get to monotonic time. Monotonic is pegged @@ -64,14 +64,17 @@ struct timekeeper { * - wall_to_monotonic is no longer the boot time, getboottime must be * used instead. */ - struct timespec wall_to_monotonic; + struct timespec wall_to_monotonic; /* time spent in suspend */ - struct timespec total_sleep_time; + struct timespec total_sleep_time; /* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */ - struct timespec raw_time; - + struct timespec raw_time; + /* Offset clock monotonic -> clock realtime */ + ktime_t offs_real; + /* Offset clock monotonic -> clock boottime */ + ktime_t offs_boot; /* Seqlock for all timekeeper values */ - seqlock_t lock; + seqlock_t lock; }; static struct timekeeper timekeeper; @@ -82,11 +85,37 @@ static struct timekeeper timekeeper; */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock); - /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; +static inline void tk_normalize_xtime(struct timekeeper *tk) +{ + while (tk->xtime_nsec >= ((u64)NSEC_PER_SEC << tk->shift)) { + tk->xtime_nsec -= (u64)NSEC_PER_SEC << tk->shift; + tk->xtime_sec++; + } +} + +static struct timespec tk_xtime(struct timekeeper *tk) +{ + struct timespec ts; + + ts.tv_sec = tk->xtime_sec; + ts.tv_nsec = (long)(tk->xtime_nsec >> tk->shift); + return ts; +} + +static void tk_set_xtime(struct timekeeper *tk, const struct timespec *ts) +{ + tk->xtime_sec = ts->tv_sec; + tk->xtime_nsec = ts->tv_nsec << tk->shift; +} +static void tk_xtime_add(struct timekeeper *tk, const struct timespec *ts) +{ + tk->xtime_sec += ts->tv_sec; + tk->xtime_nsec += ts->tv_nsec << tk->shift; +} /** * timekeeper_setup_internals - Set up internals to use clocksource clock. @@ -98,12 +127,14 @@ int __read_mostly timekeeping_suspended; * * Unless you're the timekeeping code, you should not be using this! */ -static void timekeeper_setup_internals(struct clocksource *clock) +static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) { cycle_t interval; u64 tmp, ntpinterval; + struct clocksource *old_clock; - timekeeper.clock = clock; + old_clock = tk->clock; + tk->clock = clock; clock->cycle_last = clock->read(clock); /* Do the ns -> cycle conversion first, using original mult */ @@ -116,71 +147,96 @@ static void timekeeper_setup_internals(struct clocksource *clock) tmp = 1; interval = (cycle_t) tmp; - timekeeper.cycle_interval = interval; + tk->cycle_interval = interval; /* Go back from cycles -> shifted ns */ - timekeeper.xtime_interval = (u64) interval * clock->mult; - timekeeper.xtime_remainder = ntpinterval - timekeeper.xtime_interval; - timekeeper.raw_interval = + tk->xtime_interval = (u64) interval * clock->mult; + tk->xtime_remainder = ntpinterval - tk->xtime_interval; + tk->raw_interval = ((u64) interval * clock->mult) >> clock->shift; - timekeeper.xtime_nsec = 0; - timekeeper.shift = clock->shift; + /* if changing clocks, convert xtime_nsec shift units */ + if (old_clock) { + int shift_change = clock->shift - old_clock->shift; + if (shift_change < 0) + tk->xtime_nsec >>= -shift_change; + else + tk->xtime_nsec <<= shift_change; + } + tk->shift = clock->shift; - timekeeper.ntp_error = 0; - timekeeper.ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; + tk->ntp_error = 0; + tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; /* * The timekeeper keeps its own mult values for the currently * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ - timekeeper.mult = clock->mult; + tk->mult = clock->mult; } /* Timekeeper helper functions. */ -static inline s64 timekeeping_get_ns(void) +static inline s64 timekeeping_get_ns(struct timekeeper *tk) { cycle_t cycle_now, cycle_delta; struct clocksource *clock; + s64 nsec; /* read clocksource: */ - clock = timekeeper.clock; + clock = tk->clock; cycle_now = clock->read(clock); /* calculate the delta since the last update_wall_time: */ cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; - /* return delta convert to nanoseconds using ntp adjusted mult. */ - return clocksource_cyc2ns(cycle_delta, timekeeper.mult, - timekeeper.shift); + nsec = cycle_delta * tk->mult + tk->xtime_nsec; + nsec >>= tk->shift; + + /* If arch requires, add in gettimeoffset() */ + return nsec + arch_gettimeoffset(); } -static inline s64 timekeeping_get_ns_raw(void) +static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) { cycle_t cycle_now, cycle_delta; struct clocksource *clock; + s64 nsec; /* read clocksource: */ - clock = timekeeper.clock; + clock = tk->clock; cycle_now = clock->read(clock); /* calculate the delta since the last update_wall_time: */ cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; - /* return delta convert to nanoseconds. */ - return clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift); + /* convert delta to nanoseconds. */ + nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift); + + /* If arch requires, add in gettimeoffset() */ + return nsec + arch_gettimeoffset(); +} + +static void update_rt_offset(struct timekeeper *tk) +{ + struct timespec tmp, *wtm = &tk->wall_to_monotonic; + + set_normalized_timespec(&tmp, -wtm->tv_sec, -wtm->tv_nsec); + tk->offs_real = timespec_to_ktime(tmp); } /* must hold write on timekeeper.lock */ -static void timekeeping_update(bool clearntp) +static void timekeeping_update(struct timekeeper *tk, bool clearntp) { + struct timespec xt; + if (clearntp) { - timekeeper.ntp_error = 0; + tk->ntp_error = 0; ntp_clear(); } - update_vsyscall(&timekeeper.xtime, &timekeeper.wall_to_monotonic, - timekeeper.clock, timekeeper.mult); + update_rt_offset(tk); + xt = tk_xtime(tk); + update_vsyscall(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult); } @@ -191,27 +247,26 @@ static void timekeeping_update(bool clearntp) * update_wall_time(). This is useful before significant clock changes, * as it avoids having to deal with this time offset explicitly. */ -static void timekeeping_forward_now(void) +static void timekeeping_forward_now(struct timekeeper *tk) { cycle_t cycle_now, cycle_delta; struct clocksource *clock; s64 nsec; - clock = timekeeper.clock; + clock = tk->clock; cycle_now = clock->read(clock); cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; clock->cycle_last = cycle_now; - nsec = clocksource_cyc2ns(cycle_delta, timekeeper.mult, - timekeeper.shift); + tk->xtime_nsec += cycle_delta * tk->mult; /* If arch requires, add in gettimeoffset() */ - nsec += arch_gettimeoffset(); + tk->xtime_nsec += arch_gettimeoffset() << tk->shift; - timespec_add_ns(&timekeeper.xtime, nsec); + tk_normalize_xtime(tk); nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift); - timespec_add_ns(&timekeeper.raw_time, nsec); + timespec_add_ns(&tk->raw_time, nsec); } /** @@ -223,18 +278,15 @@ static void timekeeping_forward_now(void) void getnstimeofday(struct timespec *ts) { unsigned long seq; - s64 nsecs; + s64 nsecs = 0; WARN_ON(timekeeping_suspended); do { seq = read_seqbegin(&timekeeper.lock); - *ts = timekeeper.xtime; - nsecs = timekeeping_get_ns(); - - /* If arch requires, add in gettimeoffset() */ - nsecs += arch_gettimeoffset(); + ts->tv_sec = timekeeper.xtime_sec; + ts->tv_nsec = timekeeping_get_ns(&timekeeper); } while (read_seqretry(&timekeeper.lock, seq)); @@ -251,13 +303,10 @@ ktime_t ktime_get(void) do { seq = read_seqbegin(&timekeeper.lock); - secs = timekeeper.xtime.tv_sec + + secs = timekeeper.xtime_sec + timekeeper.wall_to_monotonic.tv_sec; - nsecs = timekeeper.xtime.tv_nsec + + nsecs = timekeeping_get_ns(&timekeeper) + timekeeper.wall_to_monotonic.tv_nsec; - nsecs += timekeeping_get_ns(); - /* If arch requires, add in gettimeoffset() */ - nsecs += arch_gettimeoffset(); } while (read_seqretry(&timekeeper.lock, seq)); /* @@ -280,22 +329,19 @@ void ktime_get_ts(struct timespec *ts) { struct timespec tomono; unsigned int seq; - s64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqbegin(&timekeeper.lock); - *ts = timekeeper.xtime; + ts->tv_sec = timekeeper.xtime_sec; + ts->tv_nsec = timekeeping_get_ns(&timekeeper); tomono = timekeeper.wall_to_monotonic; - nsecs = timekeeping_get_ns(); - /* If arch requires, add in gettimeoffset() */ - nsecs += arch_gettimeoffset(); } while (read_seqretry(&timekeeper.lock, seq)); set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec, - ts->tv_nsec + tomono.tv_nsec + nsecs); + ts->tv_nsec + tomono.tv_nsec); } EXPORT_SYMBOL_GPL(ktime_get_ts); @@ -318,20 +364,14 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) WARN_ON_ONCE(timekeeping_suspended); do { - u32 arch_offset; - seq = read_seqbegin(&timekeeper.lock); *ts_raw = timekeeper.raw_time; - *ts_real = timekeeper.xtime; - - nsecs_raw = timekeeping_get_ns_raw(); - nsecs_real = timekeeping_get_ns(); + ts_real->tv_sec = timekeeper.xtime_sec; + ts_real->tv_nsec = 0; - /* If arch requires, add in gettimeoffset() */ - arch_offset = arch_gettimeoffset(); - nsecs_raw += arch_offset; - nsecs_real += arch_offset; + nsecs_raw = timekeeping_get_ns_raw(&timekeeper); + nsecs_real = timekeeping_get_ns(&timekeeper); } while (read_seqretry(&timekeeper.lock, seq)); @@ -366,7 +406,7 @@ EXPORT_SYMBOL(do_gettimeofday); */ int do_settimeofday(const struct timespec *tv) { - struct timespec ts_delta; + struct timespec ts_delta, xt; unsigned long flags; if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) @@ -374,15 +414,18 @@ int do_settimeofday(const struct timespec *tv) write_seqlock_irqsave(&timekeeper.lock, flags); - timekeeping_forward_now(); + timekeeping_forward_now(&timekeeper); + + xt = tk_xtime(&timekeeper); + ts_delta.tv_sec = tv->tv_sec - xt.tv_sec; + ts_delta.tv_nsec = tv->tv_nsec - xt.tv_nsec; - ts_delta.tv_sec = tv->tv_sec - timekeeper.xtime.tv_sec; - ts_delta.tv_nsec = tv->tv_nsec - timekeeper.xtime.tv_nsec; timekeeper.wall_to_monotonic = timespec_sub(timekeeper.wall_to_monotonic, ts_delta); - timekeeper.xtime = *tv; - timekeeping_update(true); + tk_set_xtime(&timekeeper, tv); + + timekeeping_update(&timekeeper, true); write_sequnlock_irqrestore(&timekeeper.lock, flags); @@ -409,13 +452,14 @@ int timekeeping_inject_offset(struct timespec *ts) write_seqlock_irqsave(&timekeeper.lock, flags); - timekeeping_forward_now(); + timekeeping_forward_now(&timekeeper); - timekeeper.xtime = timespec_add(timekeeper.xtime, *ts); + + tk_xtime_add(&timekeeper, ts); timekeeper.wall_to_monotonic = timespec_sub(timekeeper.wall_to_monotonic, *ts); - timekeeping_update(true); + timekeeping_update(&timekeeper, true); write_sequnlock_irqrestore(&timekeeper.lock, flags); @@ -440,14 +484,14 @@ static int change_clocksource(void *data) write_seqlock_irqsave(&timekeeper.lock, flags); - timekeeping_forward_now(); + timekeeping_forward_now(&timekeeper); if (!new->enable || new->enable(new) == 0) { old = timekeeper.clock; - timekeeper_setup_internals(new); + tk_setup_internals(&timekeeper, new); if (old->disable) old->disable(old); } - timekeeping_update(true); + timekeeping_update(&timekeeper, true); write_sequnlock_irqrestore(&timekeeper.lock, flags); @@ -497,7 +541,7 @@ void getrawmonotonic(struct timespec *ts) do { seq = read_seqbegin(&timekeeper.lock); - nsecs = timekeeping_get_ns_raw(); + nsecs = timekeeping_get_ns_raw(&timekeeper); *ts = timekeeper.raw_time; } while (read_seqretry(&timekeeper.lock, seq)); @@ -532,6 +576,7 @@ u64 timekeeping_max_deferment(void) { unsigned long seq; u64 ret; + do { seq = read_seqbegin(&timekeeper.lock); @@ -592,18 +637,17 @@ void __init timekeeping_init(void) clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); - timekeeper_setup_internals(clock); + tk_setup_internals(&timekeeper, clock); - timekeeper.xtime.tv_sec = now.tv_sec; - timekeeper.xtime.tv_nsec = now.tv_nsec; + tk_set_xtime(&timekeeper, &now); timekeeper.raw_time.tv_sec = 0; timekeeper.raw_time.tv_nsec = 0; - if (boot.tv_sec == 0 && boot.tv_nsec == 0) { - boot.tv_sec = timekeeper.xtime.tv_sec; - boot.tv_nsec = timekeeper.xtime.tv_nsec; - } + if (boot.tv_sec == 0 && boot.tv_nsec == 0) + boot = tk_xtime(&timekeeper); + set_normalized_timespec(&timekeeper.wall_to_monotonic, -boot.tv_sec, -boot.tv_nsec); + update_rt_offset(&timekeeper); timekeeper.total_sleep_time.tv_sec = 0; timekeeper.total_sleep_time.tv_nsec = 0; write_sequnlock_irqrestore(&timekeeper.lock, flags); @@ -612,6 +656,12 @@ void __init timekeeping_init(void) /* time in seconds when suspend began */ static struct timespec timekeeping_suspend_time; +static void update_sleep_time(struct timespec t) +{ + timekeeper.total_sleep_time = t; + timekeeper.offs_boot = timespec_to_ktime(t); +} + /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval * @delta: pointer to a timespec delta value @@ -619,7 +669,8 @@ static struct timespec timekeeping_suspend_time; * Takes a timespec offset measuring a suspend interval and properly * adds the sleep offset to the timekeeping variables. */ -static void __timekeeping_inject_sleeptime(struct timespec *delta) +static void __timekeeping_inject_sleeptime(struct timekeeper *tk, + struct timespec *delta) { if (!timespec_valid(delta)) { printk(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " @@ -627,11 +678,9 @@ static void __timekeeping_inject_sleeptime(struct timespec *delta) return; } - timekeeper.xtime = timespec_add(timekeeper.xtime, *delta); - timekeeper.wall_to_monotonic = - timespec_sub(timekeeper.wall_to_monotonic, *delta); - timekeeper.total_sleep_time = timespec_add( - timekeeper.total_sleep_time, *delta); + tk_xtime_add(tk, delta); + tk->wall_to_monotonic = timespec_sub(tk->wall_to_monotonic, *delta); + update_sleep_time(timespec_add(tk->total_sleep_time, *delta)); } @@ -657,11 +706,11 @@ void timekeeping_inject_sleeptime(struct timespec *delta) write_seqlock_irqsave(&timekeeper.lock, flags); - timekeeping_forward_now(); + timekeeping_forward_now(&timekeeper); - __timekeeping_inject_sleeptime(delta); + __timekeeping_inject_sleeptime(&timekeeper, delta); - timekeeping_update(true); + timekeeping_update(&timekeeper, true); write_sequnlock_irqrestore(&timekeeper.lock, flags); @@ -690,12 +739,13 @@ static void timekeeping_resume(void) if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) { ts = timespec_sub(ts, timekeeping_suspend_time); - __timekeeping_inject_sleeptime(&ts); + __timekeeping_inject_sleeptime(&timekeeper, &ts); } /* re-base the last cycle value */ timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock); timekeeper.ntp_error = 0; timekeeping_suspended = 0; + timekeeping_update(&timekeeper, false); write_sequnlock_irqrestore(&timekeeper.lock, flags); touch_softlockup_watchdog(); @@ -715,7 +765,7 @@ static int timekeeping_suspend(void) read_persistent_clock(&timekeeping_suspend_time); write_seqlock_irqsave(&timekeeper.lock, flags); - timekeeping_forward_now(); + timekeeping_forward_now(&timekeeper); timekeeping_suspended = 1; /* @@ -724,7 +774,7 @@ static int timekeeping_suspend(void) * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ - delta = timespec_sub(timekeeper.xtime, timekeeping_suspend_time); + delta = timespec_sub(tk_xtime(&timekeeper), timekeeping_suspend_time); delta_delta = timespec_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* @@ -763,7 +813,8 @@ device_initcall(timekeeping_init_ops); * If the error is already larger, we look ahead even further * to compensate for late or lost adjustments. */ -static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval, +static __always_inline int timekeeping_bigadjust(struct timekeeper *tk, + s64 error, s64 *interval, s64 *offset) { s64 tick_error, i; @@ -779,7 +830,7 @@ static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval, * here. This is tuned so that an error of about 1 msec is adjusted * within about 1 sec (or 2^20 nsec in 2^SHIFT_HZ ticks). */ - error2 = timekeeper.ntp_error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ); + error2 = tk->ntp_error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ); error2 = abs(error2); for (look_ahead = 0; error2 > 0; look_ahead++) error2 >>= 2; @@ -788,8 +839,8 @@ static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval, * Now calculate the error in (1 << look_ahead) ticks, but first * remove the single look ahead already included in the error. */ - tick_error = ntp_tick_length() >> (timekeeper.ntp_error_shift + 1); - tick_error -= timekeeper.xtime_interval >> 1; + tick_error = ntp_tick_length() >> (tk->ntp_error_shift + 1); + tick_error -= tk->xtime_interval >> 1; error = ((error - tick_error) >> look_ahead) + tick_error; /* Finally calculate the adjustment shift value. */ @@ -814,9 +865,9 @@ static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval, * this is optimized for the most common adjustments of -1,0,1, * for other values we can do a bit more work. */ -static void timekeeping_adjust(s64 offset) +static void timekeeping_adjust(struct timekeeper *tk, s64 offset) { - s64 error, interval = timekeeper.cycle_interval; + s64 error, interval = tk->cycle_interval; int adj; /* @@ -832,7 +883,7 @@ static void timekeeping_adjust(s64 offset) * * Note: It does not "save" on aggravation when reading the code. */ - error = timekeeper.ntp_error >> (timekeeper.ntp_error_shift - 1); + error = tk->ntp_error >> (tk->ntp_error_shift - 1); if (error > interval) { /* * We now divide error by 4(via shift), which checks if @@ -854,7 +905,8 @@ static void timekeeping_adjust(s64 offset) if (likely(error <= interval)) adj = 1; else - adj = timekeeping_bigadjust(error, &interval, &offset); + adj = timekeeping_bigadjust(tk, error, &interval, + &offset); } else if (error < -interval) { /* See comment above, this is just switched for the negative */ error >>= 2; @@ -863,18 +915,17 @@ static void timekeeping_adjust(s64 offset) interval = -interval; offset = -offset; } else - adj = timekeeping_bigadjust(error, &interval, &offset); - } else /* No adjustment needed */ + adj = timekeeping_bigadjust(tk, error, &interval, + &offset); + } else return; - if (unlikely(timekeeper.clock->maxadj && - (timekeeper.mult + adj > - timekeeper.clock->mult + timekeeper.clock->maxadj))) { + if (unlikely(tk->clock->maxadj && + (tk->mult + adj > tk->clock->mult + tk->clock->maxadj))) { printk_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", - timekeeper.clock->name, (long)timekeeper.mult + adj, - (long)timekeeper.clock->mult + - timekeeper.clock->maxadj); + tk->clock->name, (long)tk->mult + adj, + (long)tk->clock->mult + tk->clock->maxadj); } /* * So the following can be confusing. @@ -925,11 +976,60 @@ static void timekeeping_adjust(s64 offset) * * XXX - TODO: Doc ntp_error calculation. */ - timekeeper.mult += adj; - timekeeper.xtime_interval += interval; - timekeeper.xtime_nsec -= offset; - timekeeper.ntp_error -= (interval - offset) << - timekeeper.ntp_error_shift; + tk->mult += adj; + tk->xtime_interval += interval; + tk->xtime_nsec -= offset; + tk->ntp_error -= (interval - offset) << tk->ntp_error_shift; + + /* + * It may be possible that when we entered this function, xtime_nsec + * was very small. Further, if we're slightly speeding the clocksource + * in the code above, its possible the required corrective factor to + * xtime_nsec could cause it to underflow. + * + * Now, since we already accumulated the second, cannot simply roll + * the accumulated second back, since the NTP subsystem has been + * notified via second_overflow. So instead we push xtime_nsec forward + * by the amount we underflowed, and add that amount into the error. + * + * We'll correct this error next time through this function, when + * xtime_nsec is not as small. + */ + if (unlikely((s64)tk->xtime_nsec < 0)) { + s64 neg = -(s64)tk->xtime_nsec; + tk->xtime_nsec = 0; + tk->ntp_error += neg << tk->ntp_error_shift; + } + +} + + +/** + * accumulate_nsecs_to_secs - Accumulates nsecs into secs + * + * Helper function that accumulates a the nsecs greater then a second + * from the xtime_nsec field to the xtime_secs field. + * It also calls into the NTP code to handle leapsecond processing. + * + */ +static inline void accumulate_nsecs_to_secs(struct timekeeper *tk) +{ + u64 nsecps = (u64)NSEC_PER_SEC << tk->shift; + + while (tk->xtime_nsec >= nsecps) { + int leap; + + tk->xtime_nsec -= nsecps; + tk->xtime_sec++; + + /* Figure out if its a leap sec and apply if needed */ + leap = second_overflow(tk->xtime_sec); + tk->xtime_sec += leap; + tk->wall_to_monotonic.tv_sec -= leap; + if (leap) + clock_was_set_delayed(); + + } } @@ -942,44 +1042,36 @@ static void timekeeping_adjust(s64 offset) * * Returns the unconsumed cycles. */ -static cycle_t logarithmic_accumulation(cycle_t offset, int shift) +static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, + u32 shift) { - u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift; u64 raw_nsecs; - /* If the offset is smaller than a shifted interval, do nothing */ - if (offset < timekeeper.cycle_interval<<shift) + /* If the offset is smaller then a shifted interval, do nothing */ + if (offset < tk->cycle_interval<<shift) return offset; /* Accumulate one shifted interval */ - offset -= timekeeper.cycle_interval << shift; - timekeeper.clock->cycle_last += timekeeper.cycle_interval << shift; + offset -= tk->cycle_interval << shift; + tk->clock->cycle_last += tk->cycle_interval << shift; - timekeeper.xtime_nsec += timekeeper.xtime_interval << shift; - while (timekeeper.xtime_nsec >= nsecps) { - int leap; - timekeeper.xtime_nsec -= nsecps; - timekeeper.xtime.tv_sec++; - leap = second_overflow(timekeeper.xtime.tv_sec); - timekeeper.xtime.tv_sec += leap; - timekeeper.wall_to_monotonic.tv_sec -= leap; - } + tk->xtime_nsec += tk->xtime_interval << shift; + accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ - raw_nsecs = timekeeper.raw_interval << shift; - raw_nsecs += timekeeper.raw_time.tv_nsec; + raw_nsecs = tk->raw_interval << shift; + raw_nsecs += tk->raw_time.tv_nsec; if (raw_nsecs >= NSEC_PER_SEC) { u64 raw_secs = raw_nsecs; raw_nsecs = do_div(raw_secs, NSEC_PER_SEC); - timekeeper.raw_time.tv_sec += raw_secs; + tk->raw_time.tv_sec += raw_secs; } - timekeeper.raw_time.tv_nsec = raw_nsecs; + tk->raw_time.tv_nsec = raw_nsecs; /* Accumulate error between NTP and clock interval */ - timekeeper.ntp_error += ntp_tick_length() << shift; - timekeeper.ntp_error -= - (timekeeper.xtime_interval + timekeeper.xtime_remainder) << - (timekeeper.ntp_error_shift + shift); + tk->ntp_error += ntp_tick_length() << shift; + tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << + (tk->ntp_error_shift + shift); return offset; } @@ -995,6 +1087,7 @@ static void update_wall_time(void) cycle_t offset; int shift = 0, maxshift; unsigned long flags; + s64 remainder; write_seqlock_irqsave(&timekeeper.lock, flags); @@ -1009,8 +1102,6 @@ static void update_wall_time(void) #else offset = (clock->read(clock) - clock->cycle_last) & clock->mask; #endif - timekeeper.xtime_nsec = (s64)timekeeper.xtime.tv_nsec << - timekeeper.shift; /* * With NO_HZ we may have to accumulate many cycle_intervals @@ -1026,62 +1117,36 @@ static void update_wall_time(void) maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; shift = min(shift, maxshift); while (offset >= timekeeper.cycle_interval) { - offset = logarithmic_accumulation(offset, shift); + offset = logarithmic_accumulation(&timekeeper, offset, shift); if(offset < timekeeper.cycle_interval<<shift) shift--; } /* correct the clock when NTP error is too big */ - timekeeping_adjust(offset); - - /* - * Since in the loop above, we accumulate any amount of time - * in xtime_nsec over a second into xtime.tv_sec, its possible for - * xtime_nsec to be fairly small after the loop. Further, if we're - * slightly speeding the clocksource up in timekeeping_adjust(), - * its possible the required corrective factor to xtime_nsec could - * cause it to underflow. - * - * Now, we cannot simply roll the accumulated second back, since - * the NTP subsystem has been notified via second_overflow. So - * instead we push xtime_nsec forward by the amount we underflowed, - * and add that amount into the error. - * - * We'll correct this error next time through this function, when - * xtime_nsec is not as small. - */ - if (unlikely((s64)timekeeper.xtime_nsec < 0)) { - s64 neg = -(s64)timekeeper.xtime_nsec; - timekeeper.xtime_nsec = 0; - timekeeper.ntp_error += neg << timekeeper.ntp_error_shift; - } + timekeeping_adjust(&timekeeper, offset); /* - * Store full nanoseconds into xtime after rounding it up and - * add the remainder to the error difference. - */ - timekeeper.xtime.tv_nsec = ((s64)timekeeper.xtime_nsec >> - timekeeper.shift) + 1; - timekeeper.xtime_nsec -= (s64)timekeeper.xtime.tv_nsec << - timekeeper.shift; - timekeeper.ntp_error += timekeeper.xtime_nsec << - timekeeper.ntp_error_shift; + * Store only full nanoseconds into xtime_nsec after rounding + * it up and add the remainder to the error difference. + * XXX - This is necessary to avoid small 1ns inconsistnecies caused + * by truncating the remainder in vsyscalls. However, it causes + * additional work to be done in timekeeping_adjust(). Once + * the vsyscall implementations are converted to use xtime_nsec + * (shifted nanoseconds), this can be killed. + */ + remainder = timekeeper.xtime_nsec & ((1 << timekeeper.shift) - 1); + timekeeper.xtime_nsec -= remainder; + timekeeper.xtime_nsec += 1 << timekeeper.shift; + timekeeper.ntp_error += remainder << timekeeper.ntp_error_shift; /* * Finally, make sure that after the rounding - * xtime.tv_nsec isn't larger than NSEC_PER_SEC + * xtime_nsec isn't larger than NSEC_PER_SEC */ - if (unlikely(timekeeper.xtime.tv_nsec >= NSEC_PER_SEC)) { - int leap; - timekeeper.xtime.tv_nsec -= NSEC_PER_SEC; - timekeeper.xtime.tv_sec++; - leap = second_overflow(timekeeper.xtime.tv_sec); - timekeeper.xtime.tv_sec += leap; - timekeeper.wall_to_monotonic.tv_sec -= leap; - } + accumulate_nsecs_to_secs(&timekeeper); - timekeeping_update(false); + timekeeping_update(&timekeeper, false); out: write_sequnlock_irqrestore(&timekeeper.lock, flags); @@ -1126,21 +1191,20 @@ void get_monotonic_boottime(struct timespec *ts) { struct timespec tomono, sleep; unsigned int seq; - s64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqbegin(&timekeeper.lock); - *ts = timekeeper.xtime; + ts->tv_sec = timekeeper.xtime_sec; + ts->tv_nsec = timekeeping_get_ns(&timekeeper); tomono = timekeeper.wall_to_monotonic; sleep = timekeeper.total_sleep_time; - nsecs = timekeeping_get_ns(); } while (read_seqretry(&timekeeper.lock, seq)); set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec, - ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs); + ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec); } EXPORT_SYMBOL_GPL(get_monotonic_boottime); @@ -1173,13 +1237,13 @@ EXPORT_SYMBOL_GPL(monotonic_to_bootbased); unsigned long get_seconds(void) { - return timekeeper.xtime.tv_sec; + return timekeeper.xtime_sec; } EXPORT_SYMBOL(get_seconds); struct timespec __current_kernel_time(void) { - return timekeeper.xtime; + return tk_xtime(&timekeeper); } struct timespec current_kernel_time(void) @@ -1190,7 +1254,7 @@ struct timespec current_kernel_time(void) do { seq = read_seqbegin(&timekeeper.lock); - now = timekeeper.xtime; + now = tk_xtime(&timekeeper); } while (read_seqretry(&timekeeper.lock, seq)); return now; @@ -1205,7 +1269,7 @@ struct timespec get_monotonic_coarse(void) do { seq = read_seqbegin(&timekeeper.lock); - now = timekeeper.xtime; + now = tk_xtime(&timekeeper); mono = timekeeper.wall_to_monotonic; } while (read_seqretry(&timekeeper.lock, seq)); @@ -1240,12 +1304,43 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, do { seq = read_seqbegin(&timekeeper.lock); - *xtim = timekeeper.xtime; + *xtim = tk_xtime(&timekeeper); *wtom = timekeeper.wall_to_monotonic; *sleep = timekeeper.total_sleep_time; } while (read_seqretry(&timekeeper.lock, seq)); } +#ifdef CONFIG_HIGH_RES_TIMERS +/** + * ktime_get_update_offsets - hrtimer helper + * @offs_real: pointer to storage for monotonic -> realtime offset + * @offs_boot: pointer to storage for monotonic -> boottime offset + * + * Returns current monotonic time and updates the offsets + * Called from hrtimer_interupt() or retrigger_next_event() + */ +ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot) +{ + ktime_t now; + unsigned int seq; + u64 secs, nsecs; + + do { + seq = read_seqbegin(&timekeeper.lock); + + secs = timekeeper.xtime_sec; + nsecs = timekeeping_get_ns(&timekeeper); + + *offs_real = timekeeper.offs_real; + *offs_boot = timekeeper.offs_boot; + } while (read_seqretry(&timekeeper.lock, seq)); + + now = ktime_add_ns(ktime_set(secs, 0), nsecs); + now = ktime_sub(now, *offs_real); + return now; +} +#endif + /** * ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format */ diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 3258455549f4..af5a7e9f164b 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -167,7 +167,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now) { struct tick_sched *ts = tick_get_tick_sched(cpu); P(nohz_mode); - P_ns(idle_tick); + P_ns(last_tick); P(tick_stopped); P(idle_jiffies); P(idle_calls); @@ -259,7 +259,7 @@ static int timer_list_show(struct seq_file *m, void *v) u64 now = ktime_to_ns(ktime_get()); int cpu; - SEQ_printf(m, "Timer List Version: v0.6\n"); + SEQ_printf(m, "Timer List Version: v0.7\n"); SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES); SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now); diff --git a/kernel/timer.c b/kernel/timer.c index 6ec7e7e0db43..a61c09374eba 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -77,6 +77,7 @@ struct tvec_base { struct timer_list *running_timer; unsigned long timer_jiffies; unsigned long next_timer; + unsigned long active_timers; struct tvec_root tv1; struct tvec tv2; struct tvec tv3; @@ -330,7 +331,8 @@ void set_timer_slack(struct timer_list *timer, int slack_hz) } EXPORT_SYMBOL_GPL(set_timer_slack); -static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) +static void +__internal_add_timer(struct tvec_base *base, struct timer_list *timer) { unsigned long expires = timer->expires; unsigned long idx = expires - base->timer_jiffies; @@ -372,6 +374,19 @@ static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) list_add_tail(&timer->entry, vec); } +static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) +{ + __internal_add_timer(base, timer); + /* + * Update base->active_timers and base->next_timer + */ + if (!tbase_get_deferrable(timer->base)) { + if (time_before(timer->expires, base->next_timer)) + base->next_timer = timer->expires; + base->active_timers++; + } +} + #ifdef CONFIG_TIMER_STATS void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr) { @@ -654,8 +669,7 @@ void init_timer_deferrable_key(struct timer_list *timer, } EXPORT_SYMBOL(init_timer_deferrable_key); -static inline void detach_timer(struct timer_list *timer, - int clear_pending) +static inline void detach_timer(struct timer_list *timer, bool clear_pending) { struct list_head *entry = &timer->entry; @@ -667,6 +681,29 @@ static inline void detach_timer(struct timer_list *timer, entry->prev = LIST_POISON2; } +static inline void +detach_expired_timer(struct timer_list *timer, struct tvec_base *base) +{ + detach_timer(timer, true); + if (!tbase_get_deferrable(timer->base)) + timer->base->active_timers--; +} + +static int detach_if_pending(struct timer_list *timer, struct tvec_base *base, + bool clear_pending) +{ + if (!timer_pending(timer)) + return 0; + + detach_timer(timer, clear_pending); + if (!tbase_get_deferrable(timer->base)) { + timer->base->active_timers--; + if (timer->expires == base->next_timer) + base->next_timer = base->timer_jiffies; + } + return 1; +} + /* * We are using hashed locking: holding per_cpu(tvec_bases).lock * means that all timers which are tied to this base via timer->base are @@ -712,16 +749,9 @@ __mod_timer(struct timer_list *timer, unsigned long expires, base = lock_timer_base(timer, &flags); - if (timer_pending(timer)) { - detach_timer(timer, 0); - if (timer->expires == base->next_timer && - !tbase_get_deferrable(timer->base)) - base->next_timer = base->timer_jiffies; - ret = 1; - } else { - if (pending_only) - goto out_unlock; - } + ret = detach_if_pending(timer, base, false); + if (!ret && pending_only) + goto out_unlock; debug_activate(timer, expires); @@ -752,9 +782,6 @@ __mod_timer(struct timer_list *timer, unsigned long expires, } timer->expires = expires; - if (time_before(timer->expires, base->next_timer) && - !tbase_get_deferrable(timer->base)) - base->next_timer = timer->expires; internal_add_timer(base, timer); out_unlock: @@ -920,9 +947,6 @@ void add_timer_on(struct timer_list *timer, int cpu) spin_lock_irqsave(&base->lock, flags); timer_set_base(timer, base); debug_activate(timer, timer->expires); - if (time_before(timer->expires, base->next_timer) && - !tbase_get_deferrable(timer->base)) - base->next_timer = timer->expires; internal_add_timer(base, timer); /* * Check whether the other CPU is idle and needs to be @@ -959,13 +983,7 @@ int del_timer(struct timer_list *timer) timer_stats_timer_clear_start_info(timer); if (timer_pending(timer)) { base = lock_timer_base(timer, &flags); - if (timer_pending(timer)) { - detach_timer(timer, 1); - if (timer->expires == base->next_timer && - !tbase_get_deferrable(timer->base)) - base->next_timer = base->timer_jiffies; - ret = 1; - } + ret = detach_if_pending(timer, base, true); spin_unlock_irqrestore(&base->lock, flags); } @@ -990,19 +1008,10 @@ int try_to_del_timer_sync(struct timer_list *timer) base = lock_timer_base(timer, &flags); - if (base->running_timer == timer) - goto out; - - timer_stats_timer_clear_start_info(timer); - ret = 0; - if (timer_pending(timer)) { - detach_timer(timer, 1); - if (timer->expires == base->next_timer && - !tbase_get_deferrable(timer->base)) - base->next_timer = base->timer_jiffies; - ret = 1; + if (base->running_timer != timer) { + timer_stats_timer_clear_start_info(timer); + ret = detach_if_pending(timer, base, true); } -out: spin_unlock_irqrestore(&base->lock, flags); return ret; @@ -1089,7 +1098,8 @@ static int cascade(struct tvec_base *base, struct tvec *tv, int index) */ list_for_each_entry_safe(timer, tmp, &tv_list, entry) { BUG_ON(tbase_get_base(timer->base) != base); - internal_add_timer(base, timer); + /* No accounting, while moving them */ + __internal_add_timer(base, timer); } return index; @@ -1178,7 +1188,7 @@ static inline void __run_timers(struct tvec_base *base) timer_stats_account_timer(timer); base->running_timer = timer; - detach_timer(timer, 1); + detach_expired_timer(timer, base); spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, data); @@ -1316,18 +1326,21 @@ static unsigned long cmp_next_hrtimer_event(unsigned long now, unsigned long get_next_timer_interrupt(unsigned long now) { struct tvec_base *base = __this_cpu_read(tvec_bases); - unsigned long expires; + unsigned long expires = now + NEXT_TIMER_MAX_DELTA; /* * Pretend that there is no timer pending if the cpu is offline. * Possible pending timers will be migrated later to an active cpu. */ if (cpu_is_offline(smp_processor_id())) - return now + NEXT_TIMER_MAX_DELTA; + return expires; + spin_lock(&base->lock); - if (time_before_eq(base->next_timer, base->timer_jiffies)) - base->next_timer = __next_timer_interrupt(base); - expires = base->next_timer; + if (base->active_timers) { + if (time_before_eq(base->next_timer, base->timer_jiffies)) + base->next_timer = __next_timer_interrupt(base); + expires = base->next_timer; + } spin_unlock(&base->lock); if (time_before_eq(expires, now)) @@ -1704,6 +1717,7 @@ static int __cpuinit init_timers_cpu(int cpu) base->timer_jiffies = jiffies; base->next_timer = base->timer_jiffies; + base->active_timers = 0; return 0; } @@ -1714,11 +1728,9 @@ static void migrate_timer_list(struct tvec_base *new_base, struct list_head *hea while (!list_empty(head)) { timer = list_first_entry(head, struct timer_list, entry); - detach_timer(timer, 0); + /* We ignore the accounting on the dying cpu */ + detach_timer(timer, false); timer_set_base(timer, new_base); - if (time_before(timer->expires, new_base->next_timer) && - !tbase_get_deferrable(timer->base)) - new_base->next_timer = timer->expires; internal_add_timer(new_base, timer); } } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index a008663d86c8..b4f20fba09fc 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -312,7 +312,7 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list, static int __register_ftrace_function(struct ftrace_ops *ops) { - if (ftrace_disabled) + if (unlikely(ftrace_disabled)) return -ENODEV; if (FTRACE_WARN_ON(ops == &global_ops)) @@ -4299,16 +4299,12 @@ int register_ftrace_function(struct ftrace_ops *ops) mutex_lock(&ftrace_lock); - if (unlikely(ftrace_disabled)) - goto out_unlock; - ret = __register_ftrace_function(ops); if (!ret) ret = ftrace_startup(ops, 0); - - out_unlock: mutex_unlock(&ftrace_lock); + return ret; } EXPORT_SYMBOL_GPL(register_ftrace_function); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 1d0f6a8a0e5e..49491fa7daa2 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1075,6 +1075,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu) rb_init_page(bpage->page); INIT_LIST_HEAD(&cpu_buffer->reader_page->list); + INIT_LIST_HEAD(&cpu_buffer->new_pages); ret = rb_allocate_pages(cpu_buffer, nr_pages); if (ret < 0) @@ -1346,10 +1347,9 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned int nr_pages) * If something was added to this page, it was full * since it is not the tail page. So we deduct the * bytes consumed in ring buffer from here. - * No need to update overruns, since this page is - * deleted from ring buffer and its entries are - * already accounted for. + * Increment overrun to account for the lost events. */ + local_add(page_entries, &cpu_buffer->overrun); local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes); } @@ -3239,6 +3239,10 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) if (cpu_buffer->commit_page == cpu_buffer->reader_page) goto out; + /* Don't bother swapping if the ring buffer is empty */ + if (rb_num_of_entries(cpu_buffer) == 0) + goto out; + /* * Reset the reader page to size zero. */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 49249c28690d..a120f98c4112 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -830,6 +830,8 @@ int register_tracer(struct tracer *type) current_trace = saved_tracer; if (ret) { printk(KERN_CONT "FAILED!\n"); + /* Add the warning after printing 'FAILED' */ + WARN_ON(1); goto out; } /* Only reset on passing, to avoid touching corrupted buffers */ @@ -1708,9 +1710,11 @@ EXPORT_SYMBOL_GPL(trace_vprintk); static void trace_iterator_increment(struct trace_iterator *iter) { + struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, iter->cpu); + iter->idx++; - if (iter->buffer_iter[iter->cpu]) - ring_buffer_read(iter->buffer_iter[iter->cpu], NULL); + if (buf_iter) + ring_buffer_read(buf_iter, NULL); } static struct trace_entry * @@ -1718,7 +1722,7 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts, unsigned long *lost_events) { struct ring_buffer_event *event; - struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu]; + struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, cpu); if (buf_iter) event = ring_buffer_iter_peek(buf_iter, ts); @@ -1856,10 +1860,10 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) tr->data[cpu]->skipped_entries = 0; - if (!iter->buffer_iter[cpu]) + buf_iter = trace_buffer_iter(iter, cpu); + if (!buf_iter) return; - buf_iter = iter->buffer_iter[cpu]; ring_buffer_iter_reset(buf_iter); /* @@ -2205,13 +2209,15 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter) int trace_empty(struct trace_iterator *iter) { + struct ring_buffer_iter *buf_iter; int cpu; /* If we are looking at one CPU buffer, only check that one */ if (iter->cpu_file != TRACE_PIPE_ALL_CPU) { cpu = iter->cpu_file; - if (iter->buffer_iter[cpu]) { - if (!ring_buffer_iter_empty(iter->buffer_iter[cpu])) + buf_iter = trace_buffer_iter(iter, cpu); + if (buf_iter) { + if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) @@ -2221,8 +2227,9 @@ int trace_empty(struct trace_iterator *iter) } for_each_tracing_cpu(cpu) { - if (iter->buffer_iter[cpu]) { - if (!ring_buffer_iter_empty(iter->buffer_iter[cpu])) + buf_iter = trace_buffer_iter(iter, cpu); + if (buf_iter) { + if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) @@ -2381,6 +2388,11 @@ __tracing_open(struct inode *inode, struct file *file) if (!iter) return ERR_PTR(-ENOMEM); + iter->buffer_iter = kzalloc(sizeof(*iter->buffer_iter) * num_possible_cpus(), + GFP_KERNEL); + if (!iter->buffer_iter) + goto release; + /* * We make a copy of the current tracer to avoid concurrent * changes on it while we are reading. @@ -2441,6 +2453,8 @@ __tracing_open(struct inode *inode, struct file *file) fail: mutex_unlock(&trace_types_lock); kfree(iter->trace); + kfree(iter->buffer_iter); +release: seq_release_private(inode, file); return ERR_PTR(-ENOMEM); } @@ -2481,6 +2495,7 @@ static int tracing_release(struct inode *inode, struct file *file) mutex_destroy(&iter->mutex); free_cpumask_var(iter->started); kfree(iter->trace); + kfree(iter->buffer_iter); seq_release_private(inode, file); return 0; } @@ -3609,6 +3624,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, .pages = pages_def, .partial = partial_def, .nr_pages = 0, /* This gets updated below. */ + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &tracing_pipe_buf_ops, .spd_release = tracing_spd_release_pipe, @@ -3680,7 +3696,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, ret = splice_to_pipe(pipe, &spd); out: - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return ret; out_err: @@ -4231,6 +4247,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages_def, .partial = partial_def, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &buffer_pipe_buf_ops, .spd_release = buffer_spd_release, @@ -4318,7 +4335,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, } ret = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); out: return ret; } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 5aec220d2de0..55e1f7f0db12 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -317,6 +317,14 @@ struct tracer { #define TRACE_PIPE_ALL_CPU -1 +static inline struct ring_buffer_iter * +trace_buffer_iter(struct trace_iterator *iter, int cpu) +{ + if (iter->buffer_iter && iter->buffer_iter[cpu]) + return iter->buffer_iter[cpu]; + return NULL; +} + int tracer_init(struct tracer *t, struct trace_array *tr); int tracing_is_enabled(void); void trace_wake_up(void); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index a7d2a4c653d8..ce27c8ba8d31 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -538,7 +538,7 @@ get_return_for_leaf(struct trace_iterator *iter, next = &data->ret; } else { - ring_iter = iter->buffer_iter[iter->cpu]; + ring_iter = trace_buffer_iter(iter, iter->cpu); /* First peek to compare current entry and the next one */ if (ring_iter) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index df611a0e76c5..123b189c732c 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1325,4 +1325,4 @@ __init static int init_events(void) return 0; } -device_initcall(init_events); +early_initcall(init_events); diff --git a/lib/dma-debug.c b/lib/dma-debug.c index 518aea714d21..66ce41489133 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -78,7 +78,7 @@ static LIST_HEAD(free_entries); static DEFINE_SPINLOCK(free_entries_lock); /* Global disable flag - will be set in case of an error */ -static bool global_disable __read_mostly; +static u32 global_disable __read_mostly; /* Global error count */ static u32 error_count; @@ -657,7 +657,7 @@ static int dma_debug_fs_init(void) global_disable_dent = debugfs_create_bool("disabled", 0444, dma_debug_dent, - (u32 *)&global_disable); + &global_disable); if (!global_disable_dent) goto out_err; diff --git a/lib/list_debug.c b/lib/list_debug.c index 23a5e031cd8b..c24c2f7e296f 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -87,12 +87,10 @@ void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { WARN(next->prev != prev, - "list_add_rcu corruption. next->prev should be " - "prev (%p), but was %p. (next=%p).\n", + "list_add_rcu corruption. next->prev should be prev (%p), but was %p. (next=%p).\n", prev, next->prev, next); WARN(prev->next != next, - "list_add_rcu corruption. prev->next should be " - "next (%p), but was %p. (prev=%p).\n", + "list_add_rcu corruption. prev->next should be next (%p), but was %p. (prev=%p).\n", next, prev->next, prev); new->next = next; new->prev = prev; diff --git a/mm/bootmem.c b/mm/bootmem.c index ec4fcb7a56c8..bcb63ac48cc5 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -698,7 +698,7 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align, return ___alloc_bootmem(size, align, goal, limit); } -static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, +void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal, unsigned long limit) { @@ -710,6 +710,10 @@ again: if (ptr) return ptr; + /* do not panic in alloc_bootmem_bdata() */ + if (limit && goal + size > limit) + limit = 0; + ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, goal, limit); if (ptr) return ptr; diff --git a/mm/compaction.c b/mm/compaction.c index 7ea259d82a99..2f42d9528539 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -701,8 +701,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) if (err) { putback_lru_pages(&cc->migratepages); cc->nr_migratepages = 0; + if (err == -ENOMEM) { + ret = COMPACT_PARTIAL; + goto out; + } } - } out: diff --git a/mm/madvise.c b/mm/madvise.c index deff1b64a08c..14d260fa0d17 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -15,6 +15,7 @@ #include <linux/sched.h> #include <linux/ksm.h> #include <linux/fs.h> +#include <linux/file.h> /* * Any behaviour which results in changes to the vma->vm_flags needs to @@ -204,14 +205,16 @@ static long madvise_remove(struct vm_area_struct *vma, { loff_t offset; int error; + struct file *f; *prev = NULL; /* tell sys_madvise we drop mmap_sem */ if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB)) return -EINVAL; - if (!vma->vm_file || !vma->vm_file->f_mapping - || !vma->vm_file->f_mapping->host) { + f = vma->vm_file; + + if (!f || !f->f_mapping || !f->f_mapping->host) { return -EINVAL; } @@ -221,11 +224,18 @@ static long madvise_remove(struct vm_area_struct *vma, offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); - /* filesystem's fallocate may need to take i_mutex */ + /* + * Filesystem's fallocate may need to take i_mutex. We need to + * explicitly grab a reference because the vma (and hence the + * vma's reference to the file) can go away as soon as we drop + * mmap_sem. + */ + get_file(f); up_read(¤t->mm->mmap_sem); - error = do_fallocate(vma->vm_file, + error = do_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); + fput(f); down_read(¤t->mm->mmap_sem); return error; } diff --git a/mm/memblock.c b/mm/memblock.c index d4382095f8bd..5cc6731b00cc 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -143,30 +143,6 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, MAX_NUMNODES); } -/* - * Free memblock.reserved.regions - */ -int __init_memblock memblock_free_reserved_regions(void) -{ - if (memblock.reserved.regions == memblock_reserved_init_regions) - return 0; - - return memblock_free(__pa(memblock.reserved.regions), - sizeof(struct memblock_region) * memblock.reserved.max); -} - -/* - * Reserve memblock.reserved.regions - */ -int __init_memblock memblock_reserve_reserved_regions(void) -{ - if (memblock.reserved.regions == memblock_reserved_init_regions) - return 0; - - return memblock_reserve(__pa(memblock.reserved.regions), - sizeof(struct memblock_region) * memblock.reserved.max); -} - static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r) { type->total_size -= type->regions[r].size; @@ -184,6 +160,18 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u } } +phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info( + phys_addr_t *addr) +{ + if (memblock.reserved.regions == memblock_reserved_init_regions) + return 0; + + *addr = __pa(memblock.reserved.regions); + + return PAGE_ALIGN(sizeof(struct memblock_region) * + memblock.reserved.max); +} + /** * memblock_double_array - double the size of the memblock regions array * @type: memblock type of the regions array being doubled @@ -204,6 +192,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, phys_addr_t new_area_size) { struct memblock_region *new_array, *old_array; + phys_addr_t old_alloc_size, new_alloc_size; phys_addr_t old_size, new_size, addr; int use_slab = slab_is_available(); int *in_slab; @@ -217,6 +206,12 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, /* Calculate new doubled size */ old_size = type->max * sizeof(struct memblock_region); new_size = old_size << 1; + /* + * We need to allocated new one align to PAGE_SIZE, + * so we can free them completely later. + */ + old_alloc_size = PAGE_ALIGN(old_size); + new_alloc_size = PAGE_ALIGN(new_size); /* Retrieve the slab flag */ if (type == &memblock.memory) @@ -245,11 +240,11 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, addr = memblock_find_in_range(new_area_start + new_area_size, memblock.current_limit, - new_size, sizeof(phys_addr_t)); + new_alloc_size, PAGE_SIZE); if (!addr && new_area_size) addr = memblock_find_in_range(0, min(new_area_start, memblock.current_limit), - new_size, sizeof(phys_addr_t)); + new_alloc_size, PAGE_SIZE); new_array = addr ? __va(addr) : 0; } @@ -279,13 +274,13 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) - memblock_free(__pa(old_array), old_size); + memblock_free(__pa(old_array), old_alloc_size); /* Reserve the new array if that comes from the memblock. * Otherwise, we needn't do it */ if (!use_slab) - BUG_ON(memblock_reserve(addr, new_size)); + BUG_ON(memblock_reserve(addr, new_alloc_size)); /* Update slab flag */ *in_slab = use_slab; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index ab1e7145e290..de4ce7058450 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -345,14 +345,14 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, * Also when FAIL is set do a force kill because something went * wrong earlier. */ -static void kill_procs(struct list_head *to_kill, int doit, int trapno, +static void kill_procs(struct list_head *to_kill, int forcekill, int trapno, int fail, struct page *page, unsigned long pfn, int flags) { struct to_kill *tk, *next; list_for_each_entry_safe (tk, next, to_kill, nd) { - if (doit) { + if (forcekill) { /* * In case something went wrong with munmapping * make sure the process doesn't catch the @@ -858,7 +858,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, struct address_space *mapping; LIST_HEAD(tokill); int ret; - int kill = 1; + int kill = 1, forcekill; struct page *hpage = compound_head(p); struct page *ppage; @@ -888,7 +888,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * be called inside page lock (it's recommended but not enforced). */ mapping = page_mapping(hpage); - if (!PageDirty(hpage) && mapping && + if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping && mapping_cap_writeback_dirty(mapping)) { if (page_mkclean(hpage)) { SetPageDirty(hpage); @@ -965,12 +965,14 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * Now that the dirty bit has been propagated to the * struct page and all unmaps done we can decide if * killing is needed or not. Only kill when the page - * was dirty, otherwise the tokill list is merely + * was dirty or the process is not restartable, + * otherwise the tokill list is merely * freed. When there was a problem unmapping earlier * use a more force-full uncatchable kill to prevent * any accesses to the poisoned memory. */ - kill_procs(&tokill, !!PageDirty(ppage), trapno, + forcekill = PageDirty(ppage) || (flags & MF_MUST_KILL); + kill_procs(&tokill, forcekill, trapno, ret != SWAP_SUCCESS, p, pfn, flags); return ret; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0d7e3ec8e0f3..427bb291dd0f 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -618,7 +618,7 @@ int __ref add_memory(int nid, u64 start, u64 size) pgdat = hotadd_new_pgdat(nid, start); ret = -ENOMEM; if (!pgdat) - goto out; + goto error; new_pgdat = 1; } diff --git a/mm/nobootmem.c b/mm/nobootmem.c index d23415c001bc..405573010f99 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -105,27 +105,35 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end) __free_pages_bootmem(pfn_to_page(i), 0); } +static unsigned long __init __free_memory_core(phys_addr_t start, + phys_addr_t end) +{ + unsigned long start_pfn = PFN_UP(start); + unsigned long end_pfn = min_t(unsigned long, + PFN_DOWN(end), max_low_pfn); + + if (start_pfn > end_pfn) + return 0; + + __free_pages_memory(start_pfn, end_pfn); + + return end_pfn - start_pfn; +} + unsigned long __init free_low_memory_core_early(int nodeid) { unsigned long count = 0; - phys_addr_t start, end; + phys_addr_t start, end, size; u64 i; - /* free reserved array temporarily so that it's treated as free area */ - memblock_free_reserved_regions(); - - for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) { - unsigned long start_pfn = PFN_UP(start); - unsigned long end_pfn = min_t(unsigned long, - PFN_DOWN(end), max_low_pfn); - if (start_pfn < end_pfn) { - __free_pages_memory(start_pfn, end_pfn); - count += end_pfn - start_pfn; - } - } + for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) + count += __free_memory_core(start, end); + + /* free range that is used for reserved array if we allocate it */ + size = get_allocated_memblock_reserved_regions_info(&start); + if (size) + count += __free_memory_core(start, start + size); - /* put region array back? */ - memblock_reserve_reserved_regions(); return count; } @@ -274,7 +282,7 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align, return ___alloc_bootmem(size, align, goal, limit); } -static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, +void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 44030096da63..4a4f9219683f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5635,7 +5635,12 @@ static struct page * __alloc_contig_migrate_alloc(struct page *page, unsigned long private, int **resultp) { - return alloc_page(GFP_HIGHUSER_MOVABLE); + gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE; + + if (PageHighMem(page)) + gfp_mask |= __GFP_HIGHMEM; + + return alloc_page(gfp_mask); } /* [start, end) must belong to a single zone. */ diff --git a/mm/shmem.c b/mm/shmem.c index a15a466d0d1d..c15b998e5a86 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -264,46 +264,55 @@ static int shmem_radix_tree_replace(struct address_space *mapping, } /* + * Sometimes, before we decide whether to proceed or to fail, we must check + * that an entry was not already brought back from swap by a racing thread. + * + * Checking page is not enough: by the time a SwapCache page is locked, it + * might be reused, and again be SwapCache, using the same swap as before. + */ +static bool shmem_confirm_swap(struct address_space *mapping, + pgoff_t index, swp_entry_t swap) +{ + void *item; + + rcu_read_lock(); + item = radix_tree_lookup(&mapping->page_tree, index); + rcu_read_unlock(); + return item == swp_to_radix_entry(swap); +} + +/* * Like add_to_page_cache_locked, but error if expected item has gone. */ static int shmem_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp, void *expected) { - int error = 0; + int error; VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(!PageSwapBacked(page)); + page_cache_get(page); + page->mapping = mapping; + page->index = index; + + spin_lock_irq(&mapping->tree_lock); if (!expected) - error = radix_tree_preload(gfp & GFP_RECLAIM_MASK); + error = radix_tree_insert(&mapping->page_tree, index, page); + else + error = shmem_radix_tree_replace(mapping, index, expected, + page); if (!error) { - page_cache_get(page); - page->mapping = mapping; - page->index = index; - - spin_lock_irq(&mapping->tree_lock); - if (!expected) - error = radix_tree_insert(&mapping->page_tree, - index, page); - else - error = shmem_radix_tree_replace(mapping, index, - expected, page); - if (!error) { - mapping->nrpages++; - __inc_zone_page_state(page, NR_FILE_PAGES); - __inc_zone_page_state(page, NR_SHMEM); - spin_unlock_irq(&mapping->tree_lock); - } else { - page->mapping = NULL; - spin_unlock_irq(&mapping->tree_lock); - page_cache_release(page); - } - if (!expected) - radix_tree_preload_end(); + mapping->nrpages++; + __inc_zone_page_state(page, NR_FILE_PAGES); + __inc_zone_page_state(page, NR_SHMEM); + spin_unlock_irq(&mapping->tree_lock); + } else { + page->mapping = NULL; + spin_unlock_irq(&mapping->tree_lock); + page_cache_release(page); } - if (error) - mem_cgroup_uncharge_cache_page(page); return error; } @@ -1124,9 +1133,9 @@ repeat: /* We have to do this with page locked to prevent races */ lock_page(page); if (!PageSwapCache(page) || page_private(page) != swap.val || - page->mapping) { + !shmem_confirm_swap(mapping, index, swap)) { error = -EEXIST; /* try again */ - goto failed; + goto unlock; } if (!PageUptodate(page)) { error = -EIO; @@ -1142,9 +1151,12 @@ repeat: error = mem_cgroup_cache_charge(page, current->mm, gfp & GFP_RECLAIM_MASK); - if (!error) + if (!error) { error = shmem_add_to_page_cache(page, mapping, index, gfp, swp_to_radix_entry(swap)); + /* We already confirmed swap, and make no allocation */ + VM_BUG_ON(error); + } if (error) goto failed; @@ -1181,11 +1193,18 @@ repeat: __set_page_locked(page); error = mem_cgroup_cache_charge(page, current->mm, gfp & GFP_RECLAIM_MASK); - if (!error) - error = shmem_add_to_page_cache(page, mapping, index, - gfp, NULL); if (error) goto decused; + error = radix_tree_preload(gfp & GFP_RECLAIM_MASK); + if (!error) { + error = shmem_add_to_page_cache(page, mapping, index, + gfp, NULL); + radix_tree_preload_end(); + } + if (error) { + mem_cgroup_uncharge_cache_page(page); + goto decused; + } lru_cache_add_anon(page); spin_lock(&info->lock); @@ -1245,14 +1264,10 @@ decused: unacct: shmem_unacct_blocks(info->flags, 1); failed: - if (swap.val && error != -EINVAL) { - struct page *test = find_get_page(mapping, index); - if (test && !radix_tree_exceptional_entry(test)) - page_cache_release(test); - /* Have another try if the entry has changed */ - if (test != swp_to_radix_entry(swap)) - error = -EEXIST; - } + if (swap.val && error != -EINVAL && + !shmem_confirm_swap(mapping, index, swap)) + error = -EEXIST; +unlock: if (page) { unlock_page(page); page_cache_release(page); @@ -1264,7 +1279,7 @@ failed: spin_unlock(&info->lock); goto repeat; } - if (error == -EEXIST) + if (error == -EEXIST) /* from above or from radix_tree_insert */ goto repeat; return error; } @@ -1594,6 +1609,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &page_cache_pipe_buf_ops, .spd_release = spd_release_page, @@ -1682,7 +1698,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, if (spd.nr_pages) error = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); if (error > 0) { *ppos += error; @@ -1691,98 +1707,6 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, return error; } -/* - * llseek SEEK_DATA or SEEK_HOLE through the radix_tree. - */ -static pgoff_t shmem_seek_hole_data(struct address_space *mapping, - pgoff_t index, pgoff_t end, int origin) -{ - struct page *page; - struct pagevec pvec; - pgoff_t indices[PAGEVEC_SIZE]; - bool done = false; - int i; - - pagevec_init(&pvec, 0); - pvec.nr = 1; /* start small: we may be there already */ - while (!done) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - pvec.nr, pvec.pages, indices); - if (!pvec.nr) { - if (origin == SEEK_DATA) - index = end; - break; - } - for (i = 0; i < pvec.nr; i++, index++) { - if (index < indices[i]) { - if (origin == SEEK_HOLE) { - done = true; - break; - } - index = indices[i]; - } - page = pvec.pages[i]; - if (page && !radix_tree_exceptional_entry(page)) { - if (!PageUptodate(page)) - page = NULL; - } - if (index >= end || - (page && origin == SEEK_DATA) || - (!page && origin == SEEK_HOLE)) { - done = true; - break; - } - } - shmem_deswap_pagevec(&pvec); - pagevec_release(&pvec); - pvec.nr = PAGEVEC_SIZE; - cond_resched(); - } - return index; -} - -static loff_t shmem_file_llseek(struct file *file, loff_t offset, int origin) -{ - struct address_space *mapping; - struct inode *inode; - pgoff_t start, end; - loff_t new_offset; - - if (origin != SEEK_DATA && origin != SEEK_HOLE) - return generic_file_llseek_size(file, offset, origin, - MAX_LFS_FILESIZE); - mapping = file->f_mapping; - inode = mapping->host; - mutex_lock(&inode->i_mutex); - /* We're holding i_mutex so we can access i_size directly */ - - if (offset < 0) - offset = -EINVAL; - else if (offset >= inode->i_size) - offset = -ENXIO; - else { - start = offset >> PAGE_CACHE_SHIFT; - end = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - new_offset = shmem_seek_hole_data(mapping, start, end, origin); - new_offset <<= PAGE_CACHE_SHIFT; - if (new_offset > offset) { - if (new_offset < inode->i_size) - offset = new_offset; - else if (origin == SEEK_DATA) - offset = -ENXIO; - else - offset = inode->i_size; - } - } - - if (offset >= 0 && offset != file->f_pos) { - file->f_pos = offset; - file->f_version = 0; - } - mutex_unlock(&inode->i_mutex); - return offset; -} - static long shmem_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { @@ -1953,7 +1877,7 @@ static int shmem_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) } static int shmem_create(struct inode *dir, struct dentry *dentry, umode_t mode, - struct nameidata *nd) + bool excl) { return shmem_mknod(dir, dentry, mode | S_IFREG, 0); } @@ -2786,7 +2710,7 @@ static const struct address_space_operations shmem_aops = { static const struct file_operations shmem_file_operations = { .mmap = shmem_mmap, #ifdef CONFIG_TMPFS - .llseek = shmem_file_llseek, + .llseek = generic_file_llseek, .read = do_sync_read, .write = do_sync_write, .aio_read = shmem_file_aio_read, diff --git a/mm/sparse.c b/mm/sparse.c index 6a4bf9160e85..c7bb952400c8 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -275,8 +275,9 @@ static unsigned long * __init sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, unsigned long size) { - pg_data_t *host_pgdat; - unsigned long goal; + unsigned long goal, limit; + unsigned long *p; + int nid; /* * A page may contain usemaps for other sections preventing the * page being freed and making a section unremovable while @@ -287,10 +288,17 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, * from the same section as the pgdat where possible to avoid * this problem. */ - goal = __pa(pgdat) & PAGE_SECTION_MASK; - host_pgdat = NODE_DATA(early_pfn_to_nid(goal >> PAGE_SHIFT)); - return __alloc_bootmem_node_nopanic(host_pgdat, size, - SMP_CACHE_BYTES, goal); + goal = __pa(pgdat) & (PAGE_SECTION_MASK << PAGE_SHIFT); + limit = goal + (1UL << PA_SECTION_SHIFT); + nid = early_pfn_to_nid(goal >> PAGE_SHIFT); +again: + p = ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size, + SMP_CACHE_BYTES, goal, limit); + if (!p && limit) { + limit = 0; + goto again; + } + return p; } static void __init check_usemap_section_nr(int nid, unsigned long *usemap) diff --git a/mm/vmscan.c b/mm/vmscan.c index eeb3bc9d1d36..66e431060c05 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2688,7 +2688,10 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) * them before going back to sleep. */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); - schedule(); + + if (!kthread_should_stop()) + schedule(); + set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); } else { if (remaining) @@ -2955,14 +2958,17 @@ int kswapd_run(int nid) } /* - * Called by memory hotplug when all memory in a node is offlined. + * Called by memory hotplug when all memory in a node is offlined. Caller must + * hold lock_memory_hotplug(). */ void kswapd_stop(int nid) { struct task_struct *kswapd = NODE_DATA(nid)->kswapd; - if (kswapd) + if (kswapd) { kthread_stop(kswapd); + NODE_DATA(nid)->kswapd = NULL; + } } static int __init kswapd_init(void) diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 6089f0cf23b4..9096bcb08132 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -403,6 +403,9 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, break; case NETDEV_DOWN: + if (dev->features & NETIF_F_HW_VLAN_FILTER) + vlan_vid_del(dev, 0); + /* Put all VLANs for this dev in the down state too. */ for (i = 0; i < VLAN_N_VID; i++) { vlandev = vlan_group_get_device(grp, i); diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 051f7abae66d..779095ded689 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -842,6 +842,7 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol, case AX25_P_NETROM: if (ax25_protocol_is_registered(AX25_P_NETROM)) return -ESOCKTNOSUPPORT; + break; #endif #ifdef CONFIG_ROSE_MODULE case AX25_P_ROSE: diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 8bf97515a77d..c5863f499133 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1351,6 +1351,7 @@ void bla_free(struct bat_priv *bat_priv) * @bat_priv: the bat priv with all the soft interface information * @skb: the frame to be checked * @vid: the VLAN ID of the frame + * @is_bcast: the packet came in a broadcast packet type. * * bla_rx avoidance checks if: * * we have to race for a claim @@ -1361,7 +1362,8 @@ void bla_free(struct bat_priv *bat_priv) * process the skb. * */ -int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid) +int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid, + bool is_bcast) { struct ethhdr *ethhdr; struct claim search_claim, *claim = NULL; @@ -1380,7 +1382,7 @@ int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid) if (unlikely(atomic_read(&bat_priv->bla_num_requests))) /* don't allow broadcasts while requests are in flight */ - if (is_multicast_ether_addr(ethhdr->h_dest)) + if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) goto handled; memcpy(search_claim.addr, ethhdr->h_source, ETH_ALEN); @@ -1406,8 +1408,13 @@ int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid) } /* if it is a broadcast ... */ - if (is_multicast_ether_addr(ethhdr->h_dest)) { - /* ... drop it. the responsible gateway is in charge. */ + if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) { + /* ... drop it. the responsible gateway is in charge. + * + * We need to check is_bcast because with the gateway + * feature, broadcasts (like DHCP requests) may be sent + * using a unicast packet type. + */ goto handled; } else { /* seems the client considers us as its best gateway. diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index e39f93acc28f..dc5227b398d4 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -23,7 +23,8 @@ #define _NET_BATMAN_ADV_BLA_H_ #ifdef CONFIG_BATMAN_ADV_BLA -int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid); +int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid, + bool is_bcast); int bla_tx(struct bat_priv *bat_priv, struct sk_buff *skb, short vid); int bla_is_backbone_gw(struct sk_buff *skb, struct orig_node *orig_node, int hdr_size); @@ -41,7 +42,7 @@ void bla_free(struct bat_priv *bat_priv); #else /* ifdef CONFIG_BATMAN_ADV_BLA */ static inline int bla_rx(struct bat_priv *bat_priv, struct sk_buff *skb, - short vid) + short vid, bool is_bcast) { return 0; } diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 6e2530b02043..a0ec0e4ada4c 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -256,7 +256,11 @@ void interface_rx(struct net_device *soft_iface, struct bat_priv *bat_priv = netdev_priv(soft_iface); struct ethhdr *ethhdr; struct vlan_ethhdr *vhdr; + struct batman_header *batadv_header = (struct batman_header *)skb->data; short vid __maybe_unused = -1; + bool is_bcast; + + is_bcast = (batadv_header->packet_type == BAT_BCAST); /* check if enough space is available for pulling, and pull */ if (!pskb_may_pull(skb, hdr_size)) @@ -302,7 +306,7 @@ void interface_rx(struct net_device *soft_iface, /* Let the bridge loop avoidance check the packet. If will * not handle it, we can safely push it up. */ - if (bla_rx(bat_priv, skb, vid)) + if (bla_rx(bat_priv, skb, vid, is_bcast)) goto out; netif_rx(skb); diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 554b31289607..8c83c175b03a 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -561,9 +561,9 @@ static int __init caif_device_init(void) static void __exit caif_device_exit(void) { - unregister_pernet_subsys(&caif_net_ops); unregister_netdevice_notifier(&caif_device_notifier); dev_remove_pack(&caif_packet_type); + unregister_pernet_subsys(&caif_net_ops); } module_init(caif_device_init); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index b332c3d76059..10255e81be79 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1423,7 +1423,7 @@ static int process_connect(struct ceph_connection *con) * dropped messages. */ dout("process_connect got RESET peer seq %u\n", - le32_to_cpu(con->in_connect.connect_seq)); + le32_to_cpu(con->in_reply.connect_seq)); pr_err("%s%lld %s connection reset\n", ENTITY_NAME(con->peer_name), ceph_pr_addr(&con->peer_addr.in_addr)); @@ -1450,10 +1450,10 @@ static int process_connect(struct ceph_connection *con) * If we sent a smaller connect_seq than the peer has, try * again with a larger value. */ - dout("process_connect got RETRY my seq = %u, peer_seq = %u\n", + dout("process_connect got RETRY_SESSION my seq %u, peer %u\n", le32_to_cpu(con->out_connect.connect_seq), - le32_to_cpu(con->in_connect.connect_seq)); - con->connect_seq = le32_to_cpu(con->in_connect.connect_seq); + le32_to_cpu(con->in_reply.connect_seq)); + con->connect_seq = le32_to_cpu(con->in_reply.connect_seq); ceph_con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) @@ -1468,9 +1468,9 @@ static int process_connect(struct ceph_connection *con) */ dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n", con->peer_global_seq, - le32_to_cpu(con->in_connect.global_seq)); + le32_to_cpu(con->in_reply.global_seq)); get_global_seq(con->msgr, - le32_to_cpu(con->in_connect.global_seq)); + le32_to_cpu(con->in_reply.global_seq)); ceph_con_out_kvec_reset(con); ret = prepare_write_connect(con); if (ret < 0) diff --git a/net/core/dev.c b/net/core/dev.c index 6df214041a5e..1cb0d8a6aa6c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1136,8 +1136,8 @@ void dev_load(struct net *net, const char *name) no_module = request_module("netdev-%s", name); if (no_module && capable(CAP_SYS_MODULE)) { if (!request_module("%s", name)) - pr_err("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n", - name); + pr_warn("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n", + name); } } EXPORT_SYMBOL(dev_load); @@ -2444,8 +2444,12 @@ static void skb_update_prio(struct sk_buff *skb) { struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); - if ((!skb->priority) && (skb->sk) && map) - skb->priority = map->priomap[skb->sk->sk_cgrp_prioidx]; + if (!skb->priority && skb->sk && map) { + unsigned int prioidx = skb->sk->sk_cgrp_prioidx; + + if (prioidx < map->priomap_len) + skb->priority = map->priomap[prioidx]; + } } #else #define skb_update_prio(skb) @@ -6279,7 +6283,8 @@ static struct hlist_head *netdev_create_hash(void) /* Initialize per network namespace state */ static int __net_init netdev_init(struct net *net) { - INIT_LIST_HEAD(&net->dev_base_head); + if (net != &init_net) + INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index dddbacb8f28c..42f1e1c7514f 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -27,7 +27,9 @@ static DEFINE_MUTEX(net_mutex); LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); -struct net init_net; +struct net init_net = { + .dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head), +}; EXPORT_SYMBOL(init_net); #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 5b8aa2fae48b..b2e9caa1ad1a 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -49,8 +49,9 @@ static int get_prioidx(u32 *prio) return -ENOSPC; } set_bit(prioidx, prioidx_map); + if (atomic_read(&max_prioidx) < prioidx) + atomic_set(&max_prioidx, prioidx); spin_unlock_irqrestore(&prioidx_map_lock, flags); - atomic_set(&max_prioidx, prioidx); *prio = prioidx; return 0; } @@ -64,7 +65,7 @@ static void put_prioidx(u32 idx) spin_unlock_irqrestore(&prioidx_map_lock, flags); } -static void extend_netdev_table(struct net_device *dev, u32 new_len) +static int extend_netdev_table(struct net_device *dev, u32 new_len) { size_t new_size = sizeof(struct netprio_map) + ((sizeof(u32) * new_len)); @@ -76,7 +77,7 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len) if (!new_priomap) { pr_warn("Unable to alloc new priomap!\n"); - return; + return -ENOMEM; } for (i = 0; @@ -89,46 +90,79 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len) rcu_assign_pointer(dev->priomap, new_priomap); if (old_priomap) kfree_rcu(old_priomap, rcu); + return 0; } -static void update_netdev_tables(void) +static int write_update_netdev_table(struct net_device *dev) { + int ret = 0; + u32 max_len; + struct netprio_map *map; + + rtnl_lock(); + max_len = atomic_read(&max_prioidx) + 1; + map = rtnl_dereference(dev->priomap); + if (!map || map->priomap_len < max_len) + ret = extend_netdev_table(dev, max_len); + rtnl_unlock(); + + return ret; +} + +static int update_netdev_tables(void) +{ + int ret = 0; struct net_device *dev; - u32 max_len = atomic_read(&max_prioidx) + 1; + u32 max_len; struct netprio_map *map; rtnl_lock(); + max_len = atomic_read(&max_prioidx) + 1; for_each_netdev(&init_net, dev) { map = rtnl_dereference(dev->priomap); - if ((!map) || - (map->priomap_len < max_len)) - extend_netdev_table(dev, max_len); + /* + * don't allocate priomap if we didn't + * change net_prio.ifpriomap (map == NULL), + * this will speed up skb_update_prio. + */ + if (map && map->priomap_len < max_len) { + ret = extend_netdev_table(dev, max_len); + if (ret < 0) + break; + } } rtnl_unlock(); + return ret; } static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp) { struct cgroup_netprio_state *cs; - int ret; + int ret = -EINVAL; cs = kzalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); - if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) { - kfree(cs); - return ERR_PTR(-EINVAL); - } + if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) + goto out; ret = get_prioidx(&cs->prioidx); - if (ret != 0) { + if (ret < 0) { pr_warn("No space in priority index array\n"); - kfree(cs); - return ERR_PTR(ret); + goto out; + } + + ret = update_netdev_tables(); + if (ret < 0) { + put_prioidx(cs->prioidx); + goto out; } return &cs->css; +out: + kfree(cs); + return ERR_PTR(ret); } static void cgrp_destroy(struct cgroup *cgrp) @@ -141,7 +175,7 @@ static void cgrp_destroy(struct cgroup *cgrp) rtnl_lock(); for_each_netdev(&init_net, dev) { map = rtnl_dereference(dev->priomap); - if (map) + if (map && cs->prioidx < map->priomap_len) map->priomap[cs->prioidx] = 0; } rtnl_unlock(); @@ -165,7 +199,7 @@ static int read_priomap(struct cgroup *cont, struct cftype *cft, rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) { map = rcu_dereference(dev->priomap); - priority = map ? map->priomap[prioidx] : 0; + priority = (map && prioidx < map->priomap_len) ? map->priomap[prioidx] : 0; cb->fill(cb, dev->name, priority); } rcu_read_unlock(); @@ -220,13 +254,17 @@ static int write_priomap(struct cgroup *cgrp, struct cftype *cft, if (!dev) goto out_free_devname; - update_netdev_tables(); - ret = 0; + ret = write_update_netdev_table(dev); + if (ret < 0) + goto out_put_dev; + rcu_read_lock(); map = rcu_dereference(dev->priomap); if (map) map->priomap[prioidx] = priority; rcu_read_unlock(); + +out_put_dev: dev_put(dev); out_free_devname: diff --git a/net/core/scm.c b/net/core/scm.c index 611c5efd4cb0..8f6ccfd68ef4 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -109,25 +109,9 @@ void __scm_destroy(struct scm_cookie *scm) if (fpl) { scm->fp = NULL; - if (current->scm_work_list) { - list_add_tail(&fpl->list, current->scm_work_list); - } else { - LIST_HEAD(work_list); - - current->scm_work_list = &work_list; - - list_add(&fpl->list, &work_list); - while (!list_empty(&work_list)) { - fpl = list_first_entry(&work_list, struct scm_fp_list, list); - - list_del(&fpl->list); - for (i=fpl->count-1; i>=0; i--) - fput(fpl->fp[i]); - kfree(fpl); - } - - current->scm_work_list = NULL; - } + for (i=fpl->count-1; i>=0; i--) + fput(fpl->fp[i]); + kfree(fpl); } } EXPORT_SYMBOL(__scm_destroy); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d78671e9d545..d124306b81fd 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -353,7 +353,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int fragsz = SKB_DATA_ALIGN(length + NET_SKB_PAD) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - if (fragsz <= PAGE_SIZE && !(gfp_mask & __GFP_WAIT)) { + if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) { void *data = netdev_alloc_frag(fragsz); if (likely(data)) { @@ -1755,6 +1755,7 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = MAX_SKB_FRAGS, .flags = flags, .ops = &sock_pipe_buf_ops, .spd_release = sock_spd_release, diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 6fbb2ad7bb6d..16705611589a 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -230,6 +230,12 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, mtu = dev->mtu; pr_debug("name = %s, mtu = %u\n", dev->name, mtu); + if (size > mtu) { + pr_debug("size = %Zu, mtu = %u\n", size, mtu); + err = -EINVAL; + goto out_dev; + } + hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = sock_alloc_send_skb(sk, hlen + tlen + size, @@ -258,12 +264,6 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, if (err < 0) goto out_skb; - if (size > mtu) { - pr_debug("size = %Zu, mtu = %u\n", size, mtu); - err = -EINVAL; - goto out_skb; - } - skb->dev = dev; skb->sk = sk; skb->protocol = htons(ETH_P_IEEE802154); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index c48adc565e92..667c1d4ca984 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1725,8 +1725,10 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) case CIPSO_V4_TAG_LOCAL: /* This is a non-standard tag that we only allow for * local connections, so if the incoming interface is - * not the loopback device drop the packet. */ - if (!(skb->dev->flags & IFF_LOOPBACK)) { + * not the loopback device drop the packet. Further, + * there is no legitimate reason for setting this from + * userspace so reject it if skb is NULL. */ + if (skb == NULL || !(skb->dev->flags & IFF_LOOPBACK)) { err_offset = opt_iter; goto validate_return_locked; } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 66e4fcdd1c6b..0db5d34a06b6 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1342,7 +1342,6 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct sta_info *sta; u32 changed = 0; - u8 bssid[ETH_ALEN]; ASSERT_MGD_MTX(ifmgd); @@ -1354,10 +1353,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_stop_poll(sdata); - memcpy(bssid, ifmgd->associated->bssid, ETH_ALEN); - ifmgd->associated = NULL; - memset(ifmgd->bssid, 0, ETH_ALEN); /* * we need to commit the associated = NULL change because the @@ -1377,7 +1373,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, netif_carrier_off(sdata->dev); mutex_lock(&local->sta_mtx); - sta = sta_info_get(sdata, bssid); + sta = sta_info_get(sdata, ifmgd->bssid); if (sta) { set_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_sta_tear_down_BA_sessions(sta, tx); @@ -1386,13 +1382,16 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, /* deauthenticate/disassociate now */ if (tx || frame_buf) - ieee80211_send_deauth_disassoc(sdata, bssid, stype, reason, - tx, frame_buf); + ieee80211_send_deauth_disassoc(sdata, ifmgd->bssid, stype, + reason, tx, frame_buf); /* flush out frame */ if (tx) drv_flush(local, false); + /* clear bssid only after building the needed mgmt frames */ + memset(ifmgd->bssid, 0, ETH_ALEN); + /* remove AP and TDLS peers */ sta_info_flush(local, sdata); @@ -2175,15 +2174,13 @@ ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, sdata->name, mgmt->sa, status_code); ieee80211_destroy_assoc_data(sdata, false); } else { - printk(KERN_DEBUG "%s: associated\n", sdata->name); - if (!ieee80211_assoc_success(sdata, *bss, mgmt, len)) { /* oops -- internal error -- send timeout for now */ - ieee80211_destroy_assoc_data(sdata, true); - sta_info_destroy_addr(sdata, mgmt->bssid); + ieee80211_destroy_assoc_data(sdata, false); cfg80211_put_bss(*bss); return RX_MGMT_CFG80211_ASSOC_TIMEOUT; } + printk(KERN_DEBUG "%s: associated\n", sdata->name); /* * destroy assoc_data afterwards, as otherwise an idle diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 2d1acc6c5445..f9e51ef8dfa2 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -809,7 +809,7 @@ minstrel_ht_alloc_sta(void *priv, struct ieee80211_sta *sta, gfp_t gfp) max_rates = sband->n_bitrates; } - msp = kzalloc(sizeof(struct minstrel_ht_sta), gfp); + msp = kzalloc(sizeof(*msp), gfp); if (!msp) return NULL; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 7bcecf73aafb..965e6ec0adb6 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2455,7 +2455,7 @@ ieee80211_rx_h_action_return(struct ieee80211_rx_data *rx) * frames that we didn't handle, including returning unknown * ones. For all other modes we will return them to the sender, * setting the 0x80 bit in the action category, as required by - * 802.11-2007 7.3.1.11. + * 802.11-2012 9.24.4. * Newer versions of hostapd shall also use the management frame * registration mechanisms, but older ones still use cooked * monitor interfaces so push all frames there. @@ -2465,6 +2465,9 @@ ieee80211_rx_h_action_return(struct ieee80211_rx_data *rx) sdata->vif.type == NL80211_IFTYPE_AP_VLAN)) return RX_DROP_MONITOR; + if (is_multicast_ether_addr(mgmt->da)) + return RX_DROP_MONITOR; + /* do not return rejected action frames */ if (mgmt->u.action.category & 0x80) return RX_DROP_UNUSABLE; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 819c342f5b30..9730882697aa 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -640,6 +640,14 @@ find_free_id(const char *name, ip_set_id_t *index, struct ip_set **set) } static int +ip_set_none(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const attr[]) +{ + return -EOPNOTSUPP; +} + +static int ip_set_create(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const attr[]) @@ -1539,6 +1547,10 @@ nlmsg_failure: } static const struct nfnl_callback ip_set_netlink_subsys_cb[IPSET_MSG_MAX] = { + [IPSET_CMD_NONE] = { + .call = ip_set_none, + .attr_count = IPSET_ATTR_CMD_MAX, + }, [IPSET_CMD_CREATE] = { .call = ip_set_create, .attr_count = IPSET_ATTR_CMD_MAX, diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index ee863943c826..d5d3607ae7bc 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -38,30 +38,6 @@ struct iface_node { #define iface_data(n) (rb_entry(n, struct iface_node, node)->iface) -static inline long -ifname_compare(const char *_a, const char *_b) -{ - const long *a = (const long *)_a; - const long *b = (const long *)_b; - - BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); - if (a[0] != b[0]) - return a[0] - b[0]; - if (IFNAMSIZ > sizeof(long)) { - if (a[1] != b[1]) - return a[1] - b[1]; - } - if (IFNAMSIZ > 2 * sizeof(long)) { - if (a[2] != b[2]) - return a[2] - b[2]; - } - if (IFNAMSIZ > 3 * sizeof(long)) { - if (a[3] != b[3]) - return a[3] - b[3]; - } - return 0; -} - static void rbtree_destroy(struct rb_root *root) { @@ -99,7 +75,7 @@ iface_test(struct rb_root *root, const char **iface) while (n) { const char *d = iface_data(n); - long res = ifname_compare(*iface, d); + int res = strcmp(*iface, d); if (res < 0) n = n->rb_left; @@ -121,7 +97,7 @@ iface_add(struct rb_root *root, const char **iface) while (*n) { char *ifname = iface_data(*n); - long res = ifname_compare(*iface, ifname); + int res = strcmp(*iface, ifname); p = *n; if (res < 0) @@ -366,7 +342,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], struct hash_netiface4_elem data = { .cidr = HOST_MASK }; u32 ip = 0, ip_to, last; u32 timeout = h->timeout; - char iface[IFNAMSIZ] = {}; + char iface[IFNAMSIZ]; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || @@ -663,7 +639,7 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netiface6_elem data = { .cidr = HOST_MASK }; u32 timeout = h->timeout; - char iface[IFNAMSIZ] = {}; + char iface[IFNAMSIZ]; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index dd811b8dd97c..84444dda194b 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -76,19 +76,19 @@ static void __ip_vs_del_service(struct ip_vs_service *svc); #ifdef CONFIG_IP_VS_IPV6 /* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */ -static int __ip_vs_addr_is_local_v6(struct net *net, - const struct in6_addr *addr) +static bool __ip_vs_addr_is_local_v6(struct net *net, + const struct in6_addr *addr) { - struct rt6_info *rt; struct flowi6 fl6 = { .daddr = *addr, }; + struct dst_entry *dst = ip6_route_output(net, NULL, &fl6); + bool is_local; - rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6); - if (rt && rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK)) - return 1; + is_local = !dst->error && dst->dev && (dst->dev->flags & IFF_LOOPBACK); - return 0; + dst_release(dst); + return is_local; } #endif @@ -1521,11 +1521,12 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = ptr; struct net *net = dev_net(dev); + struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_service *svc; struct ip_vs_dest *dest; unsigned int idx; - if (event != NETDEV_UNREGISTER) + if (event != NETDEV_UNREGISTER || !ipvs) return NOTIFY_DONE; IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name); EnterFunction(2); @@ -1551,7 +1552,7 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, } } - list_for_each_entry(dest, &net_ipvs(net)->dest_trash, n_list) { + list_for_each_entry(dest, &ipvs->dest_trash, n_list) { __ip_vs_dev_reset(dest, dev); } mutex_unlock(&__ip_vs_mutex); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 3e797d1fcb94..791d56bbd74a 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -169,8 +169,10 @@ replay: err = nla_parse(cda, ss->cb[cb_id].attr_count, attr, attrlen, ss->cb[cb_id].policy); - if (err < 0) + if (err < 0) { + rcu_read_unlock(); return err; + } if (nc->call_rcu) { err = nc->call_rcu(net->nfnl, skb, nlh, diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index 035960ec5cb9..c6f7db720d84 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -16,6 +16,7 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_set.h> +#include <linux/netfilter/ipset/ip_set_timeout.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); @@ -310,7 +311,8 @@ set_target_v2(struct sk_buff *skb, const struct xt_action_param *par) info->del_set.flags, 0, UINT_MAX); /* Normalize to fit into jiffies */ - if (add_opt.timeout > UINT_MAX/MSEC_PER_SEC) + if (add_opt.timeout != IPSET_NO_TIMEOUT && + add_opt.timeout > UINT_MAX/MSEC_PER_SEC) add_opt.timeout = UINT_MAX/MSEC_PER_SEC; if (info->add_set.index != IPSET_INVALID_ID) ip_set_add(info->add_set.index, skb, par, &add_opt); diff --git a/net/nfc/llcp/sock.c b/net/nfc/llcp/sock.c index 17a707db40eb..e06d458fc719 100644 --- a/net/nfc/llcp/sock.c +++ b/net/nfc/llcp/sock.c @@ -292,7 +292,7 @@ static int llcp_sock_getname(struct socket *sock, struct sockaddr *addr, pr_debug("%p\n", sk); - if (llcp_sock == NULL) + if (llcp_sock == NULL || llcp_sock->dev == NULL) return -EBADFD; addr->sa_family = AF_NFC; diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index cb2646179e5f..2ab196a9f228 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -106,7 +106,7 @@ static __u8 *nci_extract_rf_params_nfca_passive_poll(struct nci_dev *ndev, nfca_poll->sens_res = __le16_to_cpu(*((__u16 *)data)); data += 2; - nfca_poll->nfcid1_len = *data++; + nfca_poll->nfcid1_len = min_t(__u8, *data++, NFC_NFCID1_MAXSIZE); pr_debug("sens_res 0x%x, nfcid1_len %d\n", nfca_poll->sens_res, nfca_poll->nfcid1_len); @@ -130,7 +130,7 @@ static __u8 *nci_extract_rf_params_nfcb_passive_poll(struct nci_dev *ndev, struct rf_tech_specific_params_nfcb_poll *nfcb_poll, __u8 *data) { - nfcb_poll->sensb_res_len = *data++; + nfcb_poll->sensb_res_len = min_t(__u8, *data++, NFC_SENSB_RES_MAXSIZE); pr_debug("sensb_res_len %d\n", nfcb_poll->sensb_res_len); @@ -145,7 +145,7 @@ static __u8 *nci_extract_rf_params_nfcf_passive_poll(struct nci_dev *ndev, __u8 *data) { nfcf_poll->bit_rate = *data++; - nfcf_poll->sensf_res_len = *data++; + nfcf_poll->sensf_res_len = min_t(__u8, *data++, NFC_SENSF_RES_MAXSIZE); pr_debug("bit_rate %d, sensf_res_len %d\n", nfcf_poll->bit_rate, nfcf_poll->sensf_res_len); @@ -331,7 +331,7 @@ static int nci_extract_activation_params_iso_dep(struct nci_dev *ndev, switch (ntf->activation_rf_tech_and_mode) { case NCI_NFC_A_PASSIVE_POLL_MODE: nfca_poll = &ntf->activation_params.nfca_poll_iso_dep; - nfca_poll->rats_res_len = *data++; + nfca_poll->rats_res_len = min_t(__u8, *data++, 20); pr_debug("rats_res_len %d\n", nfca_poll->rats_res_len); if (nfca_poll->rats_res_len > 0) { memcpy(nfca_poll->rats_res, @@ -341,7 +341,7 @@ static int nci_extract_activation_params_iso_dep(struct nci_dev *ndev, case NCI_NFC_B_PASSIVE_POLL_MODE: nfcb_poll = &ntf->activation_params.nfcb_poll_iso_dep; - nfcb_poll->attrib_res_len = *data++; + nfcb_poll->attrib_res_len = min_t(__u8, *data++, 50); pr_debug("attrib_res_len %d\n", nfcb_poll->attrib_res_len); if (nfcb_poll->attrib_res_len > 0) { memcpy(nfcb_poll->attrib_res, diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index ec1134c9e07f..8b8a6a2b2bad 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -54,7 +54,10 @@ static int rawsock_release(struct socket *sock) { struct sock *sk = sock->sk; - pr_debug("sock=%p\n", sock); + pr_debug("sock=%p sk=%p\n", sock, sk); + + if (!sk) + return 0; sock_orphan(sk); sock_put(sk); diff --git a/net/rxrpc/ar-peer.c b/net/rxrpc/ar-peer.c index 2754f098d436..bebaa43484bc 100644 --- a/net/rxrpc/ar-peer.c +++ b/net/rxrpc/ar-peer.c @@ -229,7 +229,7 @@ found_UDP_peer: return peer; new_UDP_peer: - _net("Rx UDP DGRAM from NEW peer %d", peer->debug_id); + _net("Rx UDP DGRAM from NEW peer"); read_unlock_bh(&rxrpc_peer_lock); _leave(" = -EBUSY [new]"); return ERR_PTR(-EBUSY); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index a2a95aabf9c2..c412ad0d0308 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -331,29 +331,22 @@ static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sche return PSCHED_NS2TICKS(ticks); } -static int tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) +static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) { struct sk_buff_head *list = &sch->q; psched_time_t tnext = netem_skb_cb(nskb)->time_to_send; - struct sk_buff *skb; - - if (likely(skb_queue_len(list) < sch->limit)) { - skb = skb_peek_tail(list); - /* Optimize for add at tail */ - if (likely(!skb || tnext >= netem_skb_cb(skb)->time_to_send)) - return qdisc_enqueue_tail(nskb, sch); + struct sk_buff *skb = skb_peek_tail(list); - skb_queue_reverse_walk(list, skb) { - if (tnext >= netem_skb_cb(skb)->time_to_send) - break; - } + /* Optimize for add at tail */ + if (likely(!skb || tnext >= netem_skb_cb(skb)->time_to_send)) + return __skb_queue_tail(list, nskb); - __skb_queue_after(list, skb, nskb); - sch->qstats.backlog += qdisc_pkt_len(nskb); - return NET_XMIT_SUCCESS; + skb_queue_reverse_walk(list, skb) { + if (tnext >= netem_skb_cb(skb)->time_to_send) + break; } - return qdisc_reshape_fail(nskb, sch); + __skb_queue_after(list, skb, nskb); } /* @@ -368,7 +361,6 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; struct sk_buff *skb2; - int ret; int count = 1; /* Random duplication */ @@ -419,6 +411,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) skb->data[net_random() % skb_headlen(skb)] ^= 1<<(net_random() % 8); } + if (unlikely(skb_queue_len(&sch->q) >= sch->limit)) + return qdisc_reshape_fail(skb, sch); + + sch->qstats.backlog += qdisc_pkt_len(skb); + cb = netem_skb_cb(skb); if (q->gap == 0 || /* not doing reordering */ q->counter < q->gap - 1 || /* inside last reordering gap */ @@ -450,7 +447,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) cb->time_to_send = now + delay; ++q->counter; - ret = tfifo_enqueue(skb, sch); + tfifo_enqueue(skb, sch); } else { /* * Do re-ordering by putting one out of N packets at the front @@ -460,16 +457,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) q->counter = 0; __skb_queue_head(&sch->q, skb); - sch->qstats.backlog += qdisc_pkt_len(skb); sch->qstats.requeues++; - ret = NET_XMIT_SUCCESS; - } - - if (ret != NET_XMIT_SUCCESS) { - if (net_xmit_drop_count(ret)) { - sch->qstats.drops++; - return ret; - } } return NET_XMIT_SUCCESS; diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 74305c883bd3..30ea4674cabd 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -570,6 +570,8 @@ static int sfb_dump(struct Qdisc *sch, struct sk_buff *skb) sch->qstats.backlog = q->qdisc->qstats.backlog; opts = nla_nest_start(skb, TCA_OPTIONS); + if (opts == NULL) + goto nla_put_failure; if (nla_put(skb, TCA_SFB_PARMS, sizeof(opt), &opt)) goto nla_put_failure; return nla_nest_end(skb, opts); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 5bc9ab161b37..b16517ee1aaf 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -271,6 +271,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a */ asoc->peer.sack_needed = 1; asoc->peer.sack_cnt = 0; + asoc->peer.sack_generation = 1; /* Assume that the peer will tell us if he recognizes ASCONF * as part of INIT exchange. diff --git a/net/sctp/input.c b/net/sctp/input.c index 80564fe03024..8b9b6790a3df 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -736,15 +736,12 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep) epb = &ep->base; - if (hlist_unhashed(&epb->node)) - return; - epb->hashent = sctp_ep_hashfn(epb->bind_addr.port); head = &sctp_ep_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - __hlist_del(&epb->node); + hlist_del_init(&epb->node); sctp_write_unlock(&head->lock); } @@ -825,7 +822,7 @@ static void __sctp_unhash_established(struct sctp_association *asoc) head = &sctp_assoc_hashtable[epb->hashent]; sctp_write_lock(&head->lock); - __hlist_del(&epb->node); + hlist_del_init(&epb->node); sctp_write_unlock(&head->lock); } diff --git a/net/sctp/output.c b/net/sctp/output.c index f1b7d4bb591e..6ae47acaaec6 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -248,6 +248,11 @@ static sctp_xmit_t sctp_packet_bundle_sack(struct sctp_packet *pkt, /* If the SACK timer is running, we have a pending SACK */ if (timer_pending(timer)) { struct sctp_chunk *sack; + + if (pkt->transport->sack_generation != + pkt->transport->asoc->peer.sack_generation) + return retval; + asoc->a_rwnd = asoc->rwnd; sack = sctp_make_sack(asoc); if (sack) { diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index a85eeeb55dd0..b6de71efb140 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -734,8 +734,10 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) int len; __u32 ctsn; __u16 num_gabs, num_dup_tsns; + struct sctp_association *aptr = (struct sctp_association *)asoc; struct sctp_tsnmap *map = (struct sctp_tsnmap *)&asoc->peer.tsn_map; struct sctp_gap_ack_block gabs[SCTP_MAX_GABS]; + struct sctp_transport *trans; memset(gabs, 0, sizeof(gabs)); ctsn = sctp_tsnmap_get_ctsn(map); @@ -805,6 +807,20 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) sctp_addto_chunk(retval, sizeof(__u32) * num_dup_tsns, sctp_tsnmap_get_dups(map)); + /* Once we have a sack generated, check to see what our sack + * generation is, if its 0, reset the transports to 0, and reset + * the association generation to 1 + * + * The idea is that zero is never used as a valid generation for the + * association so no transport will match after a wrap event like this, + * Until the next sack + */ + if (++aptr->peer.sack_generation == 0) { + list_for_each_entry(trans, &asoc->peer.transport_addr_list, + transports) + trans->sack_generation = 0; + aptr->peer.sack_generation = 1; + } nodata: return retval; } diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index c96d1a81cf42..8716da1a8592 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1268,7 +1268,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_REPORT_TSN: /* Record the arrival of a TSN. */ error = sctp_tsnmap_mark(&asoc->peer.tsn_map, - cmd->obj.u32); + cmd->obj.u32, NULL); break; case SCTP_CMD_REPORT_FWDTSN: diff --git a/net/sctp/socket.c b/net/sctp/socket.c index b3b8a8d813eb..31c7bfcd9b58 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1231,8 +1231,14 @@ out_free: SCTP_DEBUG_PRINTK("About to exit __sctp_connect() free asoc: %p" " kaddrs: %p err: %d\n", asoc, kaddrs, err); - if (asoc) + if (asoc) { + /* sctp_primitive_ASSOCIATE may have added this association + * To the hash table, try to unhash it, just in case, its a noop + * if it wasn't hashed so we're safe + */ + sctp_unhash_established(asoc); sctp_association_free(asoc); + } return err; } @@ -1942,8 +1948,10 @@ SCTP_STATIC int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, goto out_unlock; out_free: - if (new_asoc) + if (new_asoc) { + sctp_unhash_established(asoc); sctp_association_free(asoc); + } out_unlock: sctp_release_sock(sk); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index b026ba0c6992..1dcceb6e0ce6 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -68,6 +68,8 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, peer->af_specific = sctp_get_af_specific(addr->sa.sa_family); memset(&peer->saddr, 0, sizeof(union sctp_addr)); + peer->sack_generation = 0; + /* From 6.3.1 RTO Calculation: * * C1) Until an RTT measurement has been made for a packet sent to the diff --git a/net/sctp/tsnmap.c b/net/sctp/tsnmap.c index f1e40cebc981..b5fb7c409023 100644 --- a/net/sctp/tsnmap.c +++ b/net/sctp/tsnmap.c @@ -114,7 +114,8 @@ int sctp_tsnmap_check(const struct sctp_tsnmap *map, __u32 tsn) /* Mark this TSN as seen. */ -int sctp_tsnmap_mark(struct sctp_tsnmap *map, __u32 tsn) +int sctp_tsnmap_mark(struct sctp_tsnmap *map, __u32 tsn, + struct sctp_transport *trans) { u16 gap; @@ -133,6 +134,9 @@ int sctp_tsnmap_mark(struct sctp_tsnmap *map, __u32 tsn) */ map->max_tsn_seen++; map->cumulative_tsn_ack_point++; + if (trans) + trans->sack_generation = + trans->asoc->peer.sack_generation; map->base_tsn++; } else { /* Either we already have a gap, or about to record a gap, so diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 8a84017834c2..33d894776192 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -715,7 +715,8 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, * can mark it as received so the tsn_map is updated correctly. */ if (sctp_tsnmap_mark(&asoc->peer.tsn_map, - ntohl(chunk->subh.data_hdr->tsn))) + ntohl(chunk->subh.data_hdr->tsn), + chunk->transport)) goto fail_mark; /* First calculate the padding, so we don't inadvertently diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index f2d1de7f2ffb..f5a6a4f4faf7 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -1051,7 +1051,7 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, if (chunk && (freed >= needed)) { __u32 tsn; tsn = ntohl(chunk->subh.data_hdr->tsn); - sctp_tsnmap_mark(&asoc->peer.tsn_map, tsn); + sctp_tsnmap_mark(&asoc->peer.tsn_map, tsn, chunk->transport); sctp_ulpq_tail_data(ulpq, chunk, gfp); sctp_ulpq_partial_delivery(ulpq, chunk, gfp); diff --git a/security/keys/internal.h b/security/keys/internal.h index 3dcbf86b0d31..c246ba5d43ab 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -149,7 +149,7 @@ extern key_ref_t lookup_user_key(key_serial_t id, unsigned long flags, #define KEY_LOOKUP_FOR_UNLINK 0x04 extern long join_session_keyring(const char *name); -extern void key_change_session_keyring(struct task_work *twork); +extern void key_change_session_keyring(struct callback_head *twork); extern struct work_struct key_gc_work; extern unsigned key_gc_delay; diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 0f5b3f027299..f1b59ae39d7e 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -1456,7 +1456,7 @@ long keyctl_session_to_parent(void) { struct task_struct *me, *parent; const struct cred *mycred, *pcred; - struct task_work *newwork, *oldwork; + struct callback_head *newwork, *oldwork; key_ref_t keyring_r; struct cred *cred; int ret; @@ -1466,19 +1466,17 @@ long keyctl_session_to_parent(void) return PTR_ERR(keyring_r); ret = -ENOMEM; - newwork = kmalloc(sizeof(struct task_work), GFP_KERNEL); - if (!newwork) - goto error_keyring; /* our parent is going to need a new cred struct, a new tgcred struct * and new security data, so we allocate them here to prevent ENOMEM in * our parent */ cred = cred_alloc_blank(); if (!cred) - goto error_newwork; + goto error_keyring; + newwork = &cred->rcu; cred->tgcred->session_keyring = key_ref_to_ptr(keyring_r); - init_task_work(newwork, key_change_session_keyring, cred); + init_task_work(newwork, key_change_session_keyring); me = current; rcu_read_lock(); @@ -1488,6 +1486,7 @@ long keyctl_session_to_parent(void) oldwork = NULL; parent = me->real_parent; + task_lock(parent); /* the parent mustn't be init and mustn't be a kernel thread */ if (parent->pid <= 1 || !parent->mm) goto unlock; @@ -1531,20 +1530,15 @@ long keyctl_session_to_parent(void) if (!ret) newwork = NULL; unlock: + task_unlock(parent); write_unlock_irq(&tasklist_lock); rcu_read_unlock(); - if (oldwork) { - put_cred(oldwork->data); - kfree(oldwork); - } - if (newwork) { - put_cred(newwork->data); - kfree(newwork); - } + if (oldwork) + put_cred(container_of(oldwork, struct cred, rcu)); + if (newwork) + put_cred(cred); return ret; -error_newwork: - kfree(newwork); error_keyring: key_ref_put(keyring_r); return ret; diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index 4ad54eea1ea4..54339cfd6734 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -834,12 +834,11 @@ error: * Replace a process's session keyring on behalf of one of its children when * the target process is about to resume userspace execution. */ -void key_change_session_keyring(struct task_work *twork) +void key_change_session_keyring(struct callback_head *twork) { const struct cred *old = current_cred(); - struct cred *new = twork->data; + struct cred *new = container_of(twork, struct cred, rcu); - kfree(twork); if (unlikely(current->flags & PF_EXITING)) { put_cred(new); return; diff --git a/security/security.c b/security/security.c index 3efc9b12aef4..860aeb349cb3 100644 --- a/security/security.c +++ b/security/security.c @@ -23,6 +23,7 @@ #include <linux/mman.h> #include <linux/mount.h> #include <linux/personality.h> +#include <linux/backing-dev.h> #include <net/flow.h> #define MAX_LSM_EVM_XATTR 2 diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 372ec6502aa8..9292a8971e66 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -2157,8 +2157,7 @@ static inline void flush_unauthorized_files(const struct cred *cred, get_file(devnull); } else { devnull = dentry_open( - dget(selinux_null), - mntget(selinuxfs_mount), + &selinux_null, O_RDWR, cred); if (IS_ERR(devnull)) { devnull = NULL; @@ -2717,7 +2716,7 @@ static int selinux_inode_setattr(struct dentry *dentry, struct iattr *iattr) ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_TIMES_SET)) return dentry_has_perm(cred, dentry, FILE__SETATTR); - if (ia_valid & ATTR_SIZE) + if (selinux_policycap_openperm && (ia_valid & ATTR_SIZE)) av |= FILE__OPEN; return dentry_has_perm(cred, dentry, av); diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index b8c53723e09b..df2de54a958d 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -145,7 +145,9 @@ struct security_class_mapping secclass_map[] = { "node_bind", "name_connect", NULL } }, { "memprotect", { "mmap_zero", NULL } }, { "peer", { "recv", NULL } }, - { "capability2", { "mac_override", "mac_admin", "syslog", NULL } }, + { "capability2", + { "mac_override", "mac_admin", "syslog", "wake_alarm", "block_suspend", + NULL } }, { "kernel_service", { "use_as_override", "create_files_as", NULL } }, { "tun_socket", { COMMON_SOCK_PERMS, NULL } }, diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h index dde2005407aa..6d3885165d14 100644 --- a/security/selinux/include/security.h +++ b/security/selinux/include/security.h @@ -221,7 +221,7 @@ extern void selinux_status_update_policyload(int seqno); extern void selinux_complete_init(void); extern int selinux_disable(void); extern void exit_sel_fs(void); -extern struct dentry *selinux_null; +extern struct path selinux_null; extern struct vfsmount *selinuxfs_mount; extern void selnl_notify_setenforce(int val); extern void selnl_notify_policyload(u32 seqno); diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 3ad290251288..298e695d6822 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -1297,7 +1297,7 @@ out: #define NULL_FILE_NAME "null" -struct dentry *selinux_null; +struct path selinux_null; static ssize_t sel_read_avc_cache_threshold(struct file *filp, char __user *buf, size_t count, loff_t *ppos) @@ -1838,7 +1838,7 @@ static int sel_fill_super(struct super_block *sb, void *data, int silent) init_special_inode(inode, S_IFCHR | S_IRUGO | S_IWUGO, MKDEV(MEM_MAJOR, 3)); d_add(dentry, inode); - selinux_null = dentry; + selinux_null.dentry = dentry; dentry = sel_make_dir(sb->s_root, "avc", &sel_last_ino); if (IS_ERR(dentry)) { @@ -1912,7 +1912,7 @@ static int __init init_sel_fs(void) return err; } - selinuxfs_mount = kern_mount(&sel_fs_type); + selinux_null.mnt = selinuxfs_mount = kern_mount(&sel_fs_type); if (IS_ERR(selinuxfs_mount)) { printk(KERN_ERR "selinuxfs: could not mount!\n"); err = PTR_ERR(selinuxfs_mount); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 5ccf10a4d593..aa4c25e0f327 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6688,6 +6688,31 @@ static const struct alc_model_fixup alc662_fixup_models[] = { {} }; +static void alc662_fill_coef(struct hda_codec *codec) +{ + int val, coef; + + coef = alc_get_coef0(codec); + + switch (codec->vendor_id) { + case 0x10ec0662: + if ((coef & 0x00f0) == 0x0030) { + val = alc_read_coef_idx(codec, 0x4); /* EAPD Ctrl */ + alc_write_coef_idx(codec, 0x4, val & ~(1<<10)); + } + break; + case 0x10ec0272: + case 0x10ec0273: + case 0x10ec0663: + case 0x10ec0665: + case 0x10ec0670: + case 0x10ec0671: + case 0x10ec0672: + val = alc_read_coef_idx(codec, 0xd); /* EAPD Ctrl */ + alc_write_coef_idx(codec, 0xd, val | (1<<14)); + break; + } +} /* */ @@ -6707,6 +6732,9 @@ static int patch_alc662(struct hda_codec *codec) alc_fix_pll_init(codec, 0x20, 0x04, 15); + spec->init_hook = alc662_fill_coef; + alc662_fill_coef(codec); + alc_pick_fixup(codec, alc662_fixup_models, alc662_fixup_tbl, alc662_fixups); alc_apply_fixup(codec, ALC_FIXUP_ACT_PRE_PROBE); diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c index 64d2a4fa34b2..e9b62b5ea637 100644 --- a/sound/soc/codecs/tlv320aic3x.c +++ b/sound/soc/codecs/tlv320aic3x.c @@ -935,9 +935,7 @@ static int aic3x_hw_params(struct snd_pcm_substream *substream, } found: - data = snd_soc_read(codec, AIC3X_PLL_PROGA_REG); - snd_soc_write(codec, AIC3X_PLL_PROGA_REG, - data | (pll_p << PLLP_SHIFT)); + snd_soc_update_bits(codec, AIC3X_PLL_PROGA_REG, PLLP_MASK, pll_p); snd_soc_write(codec, AIC3X_OVRF_STATUS_AND_PLLR_REG, pll_r << PLLR_SHIFT); snd_soc_write(codec, AIC3X_PLL_PROGB_REG, pll_j << PLLJ_SHIFT); diff --git a/sound/soc/codecs/tlv320aic3x.h b/sound/soc/codecs/tlv320aic3x.h index 6f097fb60683..08c7f6685ff0 100644 --- a/sound/soc/codecs/tlv320aic3x.h +++ b/sound/soc/codecs/tlv320aic3x.h @@ -166,6 +166,7 @@ /* PLL registers bitfields */ #define PLLP_SHIFT 0 +#define PLLP_MASK 7 #define PLLQ_SHIFT 3 #define PLLR_SHIFT 0 #define PLLJ_SHIFT 2 diff --git a/sound/soc/codecs/wm2200.c b/sound/soc/codecs/wm2200.c index acbdc5fde923..32682c1b7cde 100644 --- a/sound/soc/codecs/wm2200.c +++ b/sound/soc/codecs/wm2200.c @@ -1491,6 +1491,7 @@ static int wm2200_bclk_rates_dat[WM2200_NUM_BCLK_RATES] = { static int wm2200_bclk_rates_cd[WM2200_NUM_BCLK_RATES] = { 5644800, + 3763200, 2882400, 1881600, 1411200, diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index e6906901debb..0f647d22cb4a 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -414,7 +414,7 @@ struct snd_usb_endpoint *snd_usb_add_endpoint(struct snd_usb_audio *chip, { struct list_head *p; struct snd_usb_endpoint *ep; - int ret, is_playback = direction == SNDRV_PCM_STREAM_PLAYBACK; + int is_playback = direction == SNDRV_PCM_STREAM_PLAYBACK; mutex_lock(&chip->mutex); @@ -434,16 +434,6 @@ struct snd_usb_endpoint *snd_usb_add_endpoint(struct snd_usb_audio *chip, type == SND_USB_ENDPOINT_TYPE_DATA ? "data" : "sync", ep_num); - /* select the alt setting once so the endpoints become valid */ - ret = usb_set_interface(chip->dev, alts->desc.bInterfaceNumber, - alts->desc.bAlternateSetting); - if (ret < 0) { - snd_printk(KERN_ERR "%s(): usb_set_interface() failed, ret = %d\n", - __func__, ret); - ep = NULL; - goto __exit_unlock; - } - ep = kzalloc(sizeof(*ep), GFP_KERNEL); if (!ep) goto __exit_unlock; @@ -831,9 +821,6 @@ int snd_usb_endpoint_start(struct snd_usb_endpoint *ep) if (++ep->use_count != 1) return 0; - if (snd_BUG_ON(!test_bit(EP_FLAG_ACTIVATED, &ep->flags))) - return -EINVAL; - /* just to be sure */ deactivate_urbs(ep, 0, 1); wait_clear_urbs(ep); @@ -911,9 +898,6 @@ void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep, if (snd_BUG_ON(ep->use_count == 0)) return; - if (snd_BUG_ON(!test_bit(EP_FLAG_ACTIVATED, &ep->flags))) - return; - if (--ep->use_count == 0) { deactivate_urbs(ep, force, can_sleep); ep->data_subs = NULL; @@ -927,42 +911,6 @@ void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep, } /** - * snd_usb_endpoint_activate: activate an snd_usb_endpoint - * - * @ep: the endpoint to activate - * - * If the endpoint is not currently in use, this functions will select the - * correct alternate interface setting for the interface of this endpoint. - * - * In case of any active users, this functions does nothing. - * - * Returns an error if usb_set_interface() failed, 0 in all other - * cases. - */ -int snd_usb_endpoint_activate(struct snd_usb_endpoint *ep) -{ - if (ep->use_count != 0) - return 0; - - if (!ep->chip->shutdown && - !test_and_set_bit(EP_FLAG_ACTIVATED, &ep->flags)) { - int ret; - - ret = usb_set_interface(ep->chip->dev, ep->iface, ep->alt_idx); - if (ret < 0) { - snd_printk(KERN_ERR "%s() usb_set_interface() failed, ret = %d\n", - __func__, ret); - clear_bit(EP_FLAG_ACTIVATED, &ep->flags); - return ret; - } - - return 0; - } - - return -EBUSY; -} - -/** * snd_usb_endpoint_deactivate: deactivate an snd_usb_endpoint * * @ep: the endpoint to deactivate @@ -980,24 +928,15 @@ int snd_usb_endpoint_deactivate(struct snd_usb_endpoint *ep) if (!ep) return -EINVAL; + deactivate_urbs(ep, 1, 1); + wait_clear_urbs(ep); + if (ep->use_count != 0) return 0; - if (!ep->chip->shutdown && - test_and_clear_bit(EP_FLAG_ACTIVATED, &ep->flags)) { - int ret; - - ret = usb_set_interface(ep->chip->dev, ep->iface, 0); - if (ret < 0) { - snd_printk(KERN_ERR "%s(): usb_set_interface() failed, ret = %d\n", - __func__, ret); - return ret; - } + clear_bit(EP_FLAG_ACTIVATED, &ep->flags); - return 0; - } - - return -EBUSY; + return 0; } /** diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 54607f8c4f66..a1298f379428 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -261,19 +261,6 @@ static void stop_endpoints(struct snd_usb_substream *subs, force, can_sleep, wait); } -static int activate_endpoints(struct snd_usb_substream *subs) -{ - if (subs->sync_endpoint) { - int ret; - - ret = snd_usb_endpoint_activate(subs->sync_endpoint); - if (ret < 0) - return ret; - } - - return snd_usb_endpoint_activate(subs->data_endpoint); -} - static int deactivate_endpoints(struct snd_usb_substream *subs) { int reta, retb; @@ -314,6 +301,33 @@ static int set_format(struct snd_usb_substream *subs, struct audioformat *fmt) if (fmt == subs->cur_audiofmt) return 0; + /* close the old interface */ + if (subs->interface >= 0 && subs->interface != fmt->iface) { + err = usb_set_interface(subs->dev, subs->interface, 0); + if (err < 0) { + snd_printk(KERN_ERR "%d:%d:%d: return to setting 0 failed (%d)\n", + dev->devnum, fmt->iface, fmt->altsetting, err); + return -EIO; + } + subs->interface = -1; + subs->altset_idx = 0; + } + + /* set interface */ + if (subs->interface != fmt->iface || + subs->altset_idx != fmt->altset_idx) { + err = usb_set_interface(dev, fmt->iface, fmt->altsetting); + if (err < 0) { + snd_printk(KERN_ERR "%d:%d:%d: usb_set_interface failed (%d)\n", + dev->devnum, fmt->iface, fmt->altsetting, err); + return -EIO; + } + snd_printdd(KERN_INFO "setting usb interface %d:%d\n", + fmt->iface, fmt->altsetting); + subs->interface = fmt->iface; + subs->altset_idx = fmt->altset_idx; + } + subs->data_endpoint = snd_usb_add_endpoint(subs->stream->chip, alts, fmt->endpoint, subs->direction, SND_USB_ENDPOINT_TYPE_DATA); @@ -387,7 +401,7 @@ add_sync_ep: subs->data_endpoint->sync_master = subs->sync_endpoint; } - if ((err = snd_usb_init_pitch(subs->stream->chip, subs->interface, alts, fmt)) < 0) + if ((err = snd_usb_init_pitch(subs->stream->chip, fmt->iface, alts, fmt)) < 0) return err; subs->cur_audiofmt = fmt; @@ -450,7 +464,7 @@ static int snd_usb_hw_params(struct snd_pcm_substream *substream, struct usb_interface *iface; iface = usb_ifnum_to_if(subs->dev, fmt->iface); alts = &iface->altsetting[fmt->altset_idx]; - ret = snd_usb_init_sample_rate(subs->stream->chip, subs->interface, alts, fmt, rate); + ret = snd_usb_init_sample_rate(subs->stream->chip, fmt->iface, alts, fmt, rate); if (ret < 0) return ret; subs->cur_rate = rate; @@ -460,12 +474,6 @@ static int snd_usb_hw_params(struct snd_pcm_substream *substream, mutex_lock(&subs->stream->chip->shutdown_mutex); /* format changed */ stop_endpoints(subs, 0, 0, 0); - deactivate_endpoints(subs); - - ret = activate_endpoints(subs); - if (ret < 0) - goto unlock; - ret = snd_usb_endpoint_set_params(subs->data_endpoint, hw_params, fmt, subs->sync_endpoint); if (ret < 0) @@ -500,6 +508,7 @@ static int snd_usb_hw_free(struct snd_pcm_substream *substream) subs->period_bytes = 0; mutex_lock(&subs->stream->chip->shutdown_mutex); stop_endpoints(subs, 0, 1, 1); + deactivate_endpoints(subs); mutex_unlock(&subs->stream->chip->shutdown_mutex); return snd_pcm_lib_free_vmalloc_buffer(substream); } @@ -938,16 +947,20 @@ static int snd_usb_pcm_open(struct snd_pcm_substream *substream, int direction) static int snd_usb_pcm_close(struct snd_pcm_substream *substream, int direction) { - int ret; struct snd_usb_stream *as = snd_pcm_substream_chip(substream); struct snd_usb_substream *subs = &as->substream[direction]; stop_endpoints(subs, 0, 0, 0); - ret = deactivate_endpoints(subs); + + if (!as->chip->shutdown && subs->interface >= 0) { + usb_set_interface(subs->dev, subs->interface, 0); + subs->interface = -1; + } + subs->pcm_substream = NULL; snd_usb_autosuspend(subs->stream->chip); - return ret; + return 0; } /* Since a URB can handle only a single linear buffer, we must use double diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index 3d69aa9ff51e..46c2f6b7b123 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -250,8 +250,12 @@ endef all_objs := $(sort $(ALL_OBJS)) all_deps := $(all_objs:%.o=.%.d) +# let .d file also depends on the source and header files define check_deps - $(CC) -M $(CFLAGS) $< > $@; + @set -e; $(RM) $@; \ + $(CC) -M $(CFLAGS) $< > $@.$$$$; \ + sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \ + $(RM) $@.$$$$ endef $(gui_deps): ks_version.h @@ -270,11 +274,13 @@ endif tags: force $(RM) tags - find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px + find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \ + --regex-c++='/_PE\(([^,)]*).*/PEVENT_ERRNO__\1/' TAGS: force $(RM) TAGS - find . -name '*.[ch]' | xargs etags + find . -name '*.[ch]' | xargs etags \ + --regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/' define do_install $(print_install) \ @@ -290,7 +296,7 @@ install_lib: all_cmd install_plugins install_python install: install_lib clean: - $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES).*.d + $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d $(RM) tags TAGS endif # skip-makefile diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 554828219c33..5f34aa371b56 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -467,8 +467,10 @@ int pevent_register_function(struct pevent *pevent, char *func, item->mod = NULL; item->addr = addr; - pevent->funclist = item; + if (!item->func || (mod && !item->mod)) + die("malloc func"); + pevent->funclist = item; pevent->func_count++; return 0; @@ -511,12 +513,12 @@ struct printk_list { static int printk_cmp(const void *a, const void *b) { - const struct func_map *fa = a; - const struct func_map *fb = b; + const struct printk_map *pa = a; + const struct printk_map *pb = b; - if (fa->addr < fb->addr) + if (pa->addr < pb->addr) return -1; - if (fa->addr > fb->addr) + if (pa->addr > pb->addr) return 1; return 0; @@ -583,10 +585,13 @@ int pevent_register_print_string(struct pevent *pevent, char *fmt, item = malloc_or_die(sizeof(*item)); item->next = pevent->printklist; - pevent->printklist = item; item->printk = strdup(fmt); item->addr = addr; + if (!item->printk) + die("malloc fmt"); + + pevent->printklist = item; pevent->printk_count++; return 0; @@ -616,7 +621,9 @@ static struct event_format *alloc_event(void) { struct event_format *event; - event = malloc_or_die(sizeof(*event)); + event = malloc(sizeof(*event)); + if (!event) + return NULL; memset(event, 0, sizeof(*event)); return event; @@ -626,12 +633,8 @@ static void add_event(struct pevent *pevent, struct event_format *event) { int i; - if (!pevent->events) - pevent->events = malloc_or_die(sizeof(event)); - else - pevent->events = - realloc(pevent->events, sizeof(event) * - (pevent->nr_events + 1)); + pevent->events = realloc(pevent->events, sizeof(event) * + (pevent->nr_events + 1)); if (!pevent->events) die("Can not allocate events"); @@ -697,6 +700,10 @@ static void free_arg(struct print_arg *arg) free_arg(arg->symbol.field); free_flag_sym(arg->symbol.symbols); break; + case PRINT_HEX: + free_arg(arg->hex.field); + free_arg(arg->hex.size); + break; case PRINT_TYPE: free(arg->typecast.type); free_arg(arg->typecast.item); @@ -775,6 +782,25 @@ int pevent_peek_char(void) return __peek_char(); } +static int extend_token(char **tok, char *buf, int size) +{ + char *newtok = realloc(*tok, size); + + if (!newtok) { + free(*tok); + *tok = NULL; + return -1; + } + + if (!*tok) + strcpy(newtok, buf); + else + strcat(newtok, buf); + *tok = newtok; + + return 0; +} + static enum event_type force_token(const char *str, char **tok); static enum event_type __read_token(char **tok) @@ -859,17 +885,10 @@ static enum event_type __read_token(char **tok) do { if (i == (BUFSIZ - 1)) { buf[i] = 0; - if (*tok) { - *tok = realloc(*tok, tok_size + BUFSIZ); - if (!*tok) - return EVENT_NONE; - strcat(*tok, buf); - } else - *tok = strdup(buf); + tok_size += BUFSIZ; - if (!*tok) + if (extend_token(tok, buf, tok_size) < 0) return EVENT_NONE; - tok_size += BUFSIZ; i = 0; } last_ch = ch; @@ -908,17 +927,10 @@ static enum event_type __read_token(char **tok) while (get_type(__peek_char()) == type) { if (i == (BUFSIZ - 1)) { buf[i] = 0; - if (*tok) { - *tok = realloc(*tok, tok_size + BUFSIZ); - if (!*tok) - return EVENT_NONE; - strcat(*tok, buf); - } else - *tok = strdup(buf); + tok_size += BUFSIZ; - if (!*tok) + if (extend_token(tok, buf, tok_size) < 0) return EVENT_NONE; - tok_size += BUFSIZ; i = 0; } ch = __read_char(); @@ -927,14 +939,7 @@ static enum event_type __read_token(char **tok) out: buf[i] = 0; - if (*tok) { - *tok = realloc(*tok, tok_size + i); - if (!*tok) - return EVENT_NONE; - strcat(*tok, buf); - } else - *tok = strdup(buf); - if (!*tok) + if (extend_token(tok, buf, tok_size + i + 1) < 0) return EVENT_NONE; if (type == EVENT_ITEM) { @@ -1255,9 +1260,15 @@ static int event_read_fields(struct event_format *event, struct format_field **f field->flags |= FIELD_IS_POINTER; if (field->type) { - field->type = realloc(field->type, - strlen(field->type) + - strlen(last_token) + 2); + char *new_type; + new_type = realloc(field->type, + strlen(field->type) + + strlen(last_token) + 2); + if (!new_type) { + free(last_token); + goto fail; + } + field->type = new_type; strcat(field->type, " "); strcat(field->type, last_token); free(last_token); @@ -1282,6 +1293,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f if (strcmp(token, "[") == 0) { enum event_type last_type = type; char *brackets = token; + char *new_brackets; int len; field->flags |= FIELD_IS_ARRAY; @@ -1301,9 +1313,14 @@ static int event_read_fields(struct event_format *event, struct format_field **f len = 1; last_type = type; - brackets = realloc(brackets, - strlen(brackets) + - strlen(token) + len); + new_brackets = realloc(brackets, + strlen(brackets) + + strlen(token) + len); + if (!new_brackets) { + free(brackets); + goto fail; + } + brackets = new_brackets; if (len == 2) strcat(brackets, " "); strcat(brackets, token); @@ -1319,7 +1336,12 @@ static int event_read_fields(struct event_format *event, struct format_field **f free_token(token); - brackets = realloc(brackets, strlen(brackets) + 2); + new_brackets = realloc(brackets, strlen(brackets) + 2); + if (!new_brackets) { + free(brackets); + goto fail; + } + brackets = new_brackets; strcat(brackets, "]"); /* add brackets to type */ @@ -1330,10 +1352,16 @@ static int event_read_fields(struct event_format *event, struct format_field **f * the format: type [] item; */ if (type == EVENT_ITEM) { - field->type = realloc(field->type, - strlen(field->type) + - strlen(field->name) + - strlen(brackets) + 2); + char *new_type; + new_type = realloc(field->type, + strlen(field->type) + + strlen(field->name) + + strlen(brackets) + 2); + if (!new_type) { + free(brackets); + goto fail; + } + field->type = new_type; strcat(field->type, " "); strcat(field->type, field->name); free_token(field->name); @@ -1341,9 +1369,15 @@ static int event_read_fields(struct event_format *event, struct format_field **f field->name = token; type = read_token(&token); } else { - field->type = realloc(field->type, - strlen(field->type) + - strlen(brackets) + 1); + char *new_type; + new_type = realloc(field->type, + strlen(field->type) + + strlen(brackets) + 1); + if (!new_type) { + free(brackets); + goto fail; + } + field->type = new_type; strcat(field->type, brackets); } free(brackets); @@ -1726,10 +1760,16 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok) /* could just be a type pointer */ if ((strcmp(arg->op.op, "*") == 0) && type == EVENT_DELIM && (strcmp(token, ")") == 0)) { + char *new_atom; + if (left->type != PRINT_ATOM) die("bad pointer type"); - left->atom.atom = realloc(left->atom.atom, + new_atom = realloc(left->atom.atom, strlen(left->atom.atom) + 3); + if (!new_atom) + goto out_free; + + left->atom.atom = new_atom; strcat(left->atom.atom, " *"); free(arg->op.op); *arg = *left; @@ -2146,6 +2186,8 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char ** if (value == NULL) goto out_free; field->value = strdup(value); + if (field->value == NULL) + goto out_free; free_arg(arg); arg = alloc_arg(); @@ -2159,6 +2201,8 @@ process_fields(struct event_format *event, struct print_flag_sym **list, char ** if (value == NULL) goto out_free; field->str = strdup(value); + if (field->str == NULL) + goto out_free; free_arg(arg); arg = NULL; @@ -2260,6 +2304,45 @@ process_symbols(struct event_format *event, struct print_arg *arg, char **tok) } static enum event_type +process_hex(struct event_format *event, struct print_arg *arg, char **tok) +{ + struct print_arg *field; + enum event_type type; + char *token; + + memset(arg, 0, sizeof(*arg)); + arg->type = PRINT_HEX; + + field = alloc_arg(); + type = process_arg(event, field, &token); + + if (test_type_token(type, token, EVENT_DELIM, ",")) + goto out_free; + + arg->hex.field = field; + + free_token(token); + + field = alloc_arg(); + type = process_arg(event, field, &token); + + if (test_type_token(type, token, EVENT_DELIM, ")")) + goto out_free; + + arg->hex.size = field; + + free_token(token); + type = read_token_item(tok); + return type; + + out_free: + free_arg(field); + free_token(token); + *tok = NULL; + return EVENT_ERROR; +} + +static enum event_type process_dynamic_array(struct event_format *event, struct print_arg *arg, char **tok) { struct format_field *field; @@ -2488,6 +2571,10 @@ process_function(struct event_format *event, struct print_arg *arg, is_symbolic_field = 1; return process_symbols(event, arg, tok); } + if (strcmp(token, "__print_hex") == 0) { + free_token(token); + return process_hex(event, arg, tok); + } if (strcmp(token, "__get_str") == 0) { free_token(token); return process_str(event, arg, tok); @@ -2541,7 +2628,16 @@ process_arg_token(struct event_format *event, struct print_arg *arg, } /* atoms can be more than one token long */ while (type == EVENT_ITEM) { - atom = realloc(atom, strlen(atom) + strlen(token) + 2); + char *new_atom; + new_atom = realloc(atom, + strlen(atom) + strlen(token) + 2); + if (!new_atom) { + free(atom); + *tok = NULL; + free_token(token); + return EVENT_ERROR; + } + atom = new_atom; strcat(atom, " "); strcat(atom, token); free_token(token); @@ -2835,7 +2931,7 @@ static int get_common_info(struct pevent *pevent, event = pevent->events[0]; field = pevent_find_common_field(event, type); if (!field) - die("field '%s' not found", type); + return -1; *offset = field->offset; *size = field->size; @@ -2886,15 +2982,16 @@ static int parse_common_flags(struct pevent *pevent, void *data) static int parse_common_lock_depth(struct pevent *pevent, void *data) { - int ret; - - ret = __parse_common(pevent, data, - &pevent->ld_size, &pevent->ld_offset, - "common_lock_depth"); - if (ret < 0) - return -1; + return __parse_common(pevent, data, + &pevent->ld_size, &pevent->ld_offset, + "common_lock_depth"); +} - return ret; +static int parse_common_migrate_disable(struct pevent *pevent, void *data) +{ + return __parse_common(pevent, data, + &pevent->ld_size, &pevent->ld_offset, + "common_migrate_disable"); } static int events_id_cmp(const void *a, const void *b); @@ -2995,6 +3092,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg break; case PRINT_FLAGS: case PRINT_SYMBOL: + case PRINT_HEX: break; case PRINT_TYPE: val = eval_num_arg(data, size, event, arg->typecast.item); @@ -3214,11 +3312,13 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, { struct pevent *pevent = event->pevent; struct print_flag_sym *flag; + struct format_field *field; unsigned long long val, fval; unsigned long addr; char *str; + unsigned char *hex; int print; - int len; + int i, len; switch (arg->type) { case PRINT_NULL: @@ -3228,27 +3328,29 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, print_str_to_seq(s, format, len_arg, arg->atom.atom); return; case PRINT_FIELD: - if (!arg->field.field) { - arg->field.field = pevent_find_any_field(event, arg->field.name); - if (!arg->field.field) + field = arg->field.field; + if (!field) { + field = pevent_find_any_field(event, arg->field.name); + if (!field) die("field %s not found", arg->field.name); + arg->field.field = field; } /* Zero sized fields, mean the rest of the data */ - len = arg->field.field->size ? : size - arg->field.field->offset; + len = field->size ? : size - field->offset; /* * Some events pass in pointers. If this is not an array * and the size is the same as long_size, assume that it * is a pointer. */ - if (!(arg->field.field->flags & FIELD_IS_ARRAY) && - arg->field.field->size == pevent->long_size) { - addr = *(unsigned long *)(data + arg->field.field->offset); + if (!(field->flags & FIELD_IS_ARRAY) && + field->size == pevent->long_size) { + addr = *(unsigned long *)(data + field->offset); trace_seq_printf(s, "%lx", addr); break; } str = malloc_or_die(len + 1); - memcpy(str, data + arg->field.field->offset, len); + memcpy(str, data + field->offset, len); str[len] = 0; print_str_to_seq(s, format, len_arg, str); free(str); @@ -3281,6 +3383,23 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, } } break; + case PRINT_HEX: + field = arg->hex.field->field.field; + if (!field) { + str = arg->hex.field->field.name; + field = pevent_find_any_field(event, str); + if (!field) + die("field %s not found", str); + arg->hex.field->field.field = field; + } + hex = data + field->offset; + len = eval_num_arg(data, size, event, arg->hex.size); + for (i = 0; i < len; i++) { + if (i) + trace_seq_putc(s, ' '); + trace_seq_printf(s, "%02x", hex[i]); + } + break; case PRINT_TYPE: break; @@ -3299,7 +3418,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, break; } case PRINT_BSTRING: - trace_seq_printf(s, format, arg->string.string); + print_str_to_seq(s, format, len_arg, arg->string.string); break; case PRINT_OP: /* @@ -3363,6 +3482,10 @@ process_defined_func(struct trace_seq *s, void *data, int size, string = malloc_or_die(sizeof(*string)); string->next = strings; string->str = strdup(str.buffer); + if (!string->str) + die("malloc str"); + + args[i] = (unsigned long long)string->str; strings = string; trace_seq_destroy(&str); break; @@ -3400,6 +3523,7 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc unsigned long long ip, val; char *ptr; void *bptr; + int vsize; field = pevent->bprint_buf_field; ip_field = pevent->bprint_ip_field; @@ -3448,6 +3572,8 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc goto process_again; case '0' ... '9': goto process_again; + case '.': + goto process_again; case 'p': ls = 1; /* fall through */ @@ -3455,23 +3581,30 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc case 'u': case 'x': case 'i': - /* the pointers are always 4 bytes aligned */ - bptr = (void *)(((unsigned long)bptr + 3) & - ~3); switch (ls) { case 0: - ls = 4; + vsize = 4; break; case 1: - ls = pevent->long_size; + vsize = pevent->long_size; break; case 2: - ls = 8; + vsize = 8; + break; default: + vsize = ls; /* ? */ break; } - val = pevent_read_number(pevent, bptr, ls); - bptr += ls; + /* fall through */ + case '*': + if (*ptr == '*') + vsize = 4; + + /* the pointers are always 4 bytes aligned */ + bptr = (void *)(((unsigned long)bptr + 3) & + ~3); + val = pevent_read_number(pevent, bptr, vsize); + bptr += vsize; arg = alloc_arg(); arg->next = NULL; arg->type = PRINT_ATOM; @@ -3479,12 +3612,21 @@ static struct print_arg *make_bprint_args(char *fmt, void *data, int size, struc sprintf(arg->atom.atom, "%lld", val); *next = arg; next = &arg->next; + /* + * The '*' case means that an arg is used as the length. + * We need to continue to figure out for what. + */ + if (*ptr == '*') + goto process_again; + break; case 's': arg = alloc_arg(); arg->next = NULL; arg->type = PRINT_BSTRING; arg->string.string = strdup(bptr); + if (!arg->string.string) + break; bptr += strlen(bptr) + 1; *next = arg; next = &arg->next; @@ -3589,6 +3731,16 @@ static void print_mac_arg(struct trace_seq *s, int mac, void *data, int size, trace_seq_printf(s, fmt, buf[0], buf[1], buf[2], buf[3], buf[4], buf[5]); } +static int is_printable_array(char *p, unsigned int len) +{ + unsigned int i; + + for (i = 0; i < len && p[i]; i++) + if (!isprint(p[i])) + return 0; + return 1; +} + static void print_event_fields(struct trace_seq *s, void *data, int size, struct event_format *event) { @@ -3608,7 +3760,8 @@ static void print_event_fields(struct trace_seq *s, void *data, int size, len = offset >> 16; offset &= 0xffff; } - if (field->flags & FIELD_IS_STRING) { + if (field->flags & FIELD_IS_STRING && + is_printable_array(data + offset, len)) { trace_seq_printf(s, "%s", (char *)data + offset); } else { trace_seq_puts(s, "ARRAY["); @@ -3619,6 +3772,7 @@ static void print_event_fields(struct trace_seq *s, void *data, int size, *((unsigned char *)data + offset + i)); } trace_seq_putc(s, ']'); + field->flags &= ~FIELD_IS_STRING; } } else { val = pevent_read_number(event->pevent, data + field->offset, @@ -3758,6 +3912,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event } else if (*(ptr+1) == 'M' || *(ptr+1) == 'm') { print_mac_arg(s, *(ptr+1), data, size, event, arg); ptr++; + arg = arg->next; break; } @@ -3794,14 +3949,15 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event break; } } - if (pevent->long_size == 8 && ls) { + if (pevent->long_size == 8 && ls && + sizeof(long) != 8) { char *p; ls = 2; /* make %l into %ll */ p = strchr(format, 'l'); if (p) - memmove(p, p+1, strlen(p)+1); + memmove(p+1, p, strlen(p)+1); else if (strcmp(format, "%p") == 0) strcpy(format, "0x%llx"); } @@ -3878,8 +4034,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event * pevent_data_lat_fmt - parse the data for the latency format * @pevent: a handle to the pevent * @s: the trace_seq to write to - * @data: the raw data to read from - * @size: currently unused. + * @record: the record to read from * * This parses out the Latency format (interrupts disabled, * need rescheduling, in hard/soft interrupt, preempt count @@ -3889,10 +4044,13 @@ void pevent_data_lat_fmt(struct pevent *pevent, struct trace_seq *s, struct pevent_record *record) { static int check_lock_depth = 1; + static int check_migrate_disable = 1; static int lock_depth_exists; + static int migrate_disable_exists; unsigned int lat_flags; unsigned int pc; int lock_depth; + int migrate_disable; int hardirq; int softirq; void *data = record->data; @@ -3900,18 +4058,26 @@ void pevent_data_lat_fmt(struct pevent *pevent, lat_flags = parse_common_flags(pevent, data); pc = parse_common_pc(pevent, data); /* lock_depth may not always exist */ - if (check_lock_depth) { - struct format_field *field; - struct event_format *event; - - check_lock_depth = 0; - event = pevent->events[0]; - field = pevent_find_common_field(event, "common_lock_depth"); - if (field) - lock_depth_exists = 1; - } if (lock_depth_exists) lock_depth = parse_common_lock_depth(pevent, data); + else if (check_lock_depth) { + lock_depth = parse_common_lock_depth(pevent, data); + if (lock_depth < 0) + check_lock_depth = 0; + else + lock_depth_exists = 1; + } + + /* migrate_disable may not always exist */ + if (migrate_disable_exists) + migrate_disable = parse_common_migrate_disable(pevent, data); + else if (check_migrate_disable) { + migrate_disable = parse_common_migrate_disable(pevent, data); + if (migrate_disable < 0) + check_migrate_disable = 0; + else + migrate_disable_exists = 1; + } hardirq = lat_flags & TRACE_FLAG_HARDIRQ; softirq = lat_flags & TRACE_FLAG_SOFTIRQ; @@ -3930,6 +4096,13 @@ void pevent_data_lat_fmt(struct pevent *pevent, else trace_seq_putc(s, '.'); + if (migrate_disable_exists) { + if (migrate_disable < 0) + trace_seq_putc(s, '.'); + else + trace_seq_printf(s, "%d", migrate_disable); + } + if (lock_depth_exists) { if (lock_depth < 0) trace_seq_putc(s, '.'); @@ -3996,10 +4169,7 @@ const char *pevent_data_comm_from_pid(struct pevent *pevent, int pid) * pevent_data_comm_from_pid - parse the data into the print format * @s: the trace_seq to write to * @event: the handle to the event - * @cpu: the cpu the event was recorded on - * @data: the raw data - * @size: the size of the raw data - * @nsecs: the timestamp of the event + * @record: the record to read from * * This parses the raw @data using the given @event information and * writes the print format into the trace_seq. @@ -4279,6 +4449,13 @@ static void print_args(struct print_arg *args) trace_seq_destroy(&s); printf(")"); break; + case PRINT_HEX: + printf("__print_hex("); + print_args(args->hex.field); + printf(", "); + print_args(args->hex.size); + printf(")"); + break; case PRINT_STRING: case PRINT_BSTRING: printf("__get_str(%s)", args->string.string); @@ -4541,6 +4718,8 @@ int pevent_parse_event(struct pevent *pevent, die("failed to read event id"); event->system = strdup(sys); + if (!event->system) + die("failed to allocate system"); /* Add pevent to event so that it can be referenced */ event->pevent = pevent; @@ -4582,6 +4761,11 @@ int pevent_parse_event(struct pevent *pevent, list = &arg->next; arg->type = PRINT_FIELD; arg->field.name = strdup(field->name); + if (!arg->field.name) { + do_warning("failed to allocate field name"); + event->flags |= EVENT_FL_FAILED; + return -1; + } arg->field.field = field; } return 0; @@ -4753,7 +4937,7 @@ int pevent_get_any_field_val(struct trace_seq *s, struct event_format *event, * @record: The record with the field name. * @err: print default error if failed. * - * Returns: 0 on success, -1 field not fould, or 1 if buffer is full. + * Returns: 0 on success, -1 field not found, or 1 if buffer is full. */ int pevent_print_num_field(struct trace_seq *s, const char *fmt, struct event_format *event, const char *name, @@ -4795,11 +4979,12 @@ static void free_func_handle(struct pevent_function_handler *func) * pevent_register_print_function - register a helper function * @pevent: the handle to the pevent * @func: the function to process the helper function + * @ret_type: the return type of the helper function * @name: the name of the helper function * @parameters: A list of enum pevent_func_arg_type * * Some events may have helper functions in the print format arguments. - * This allows a plugin to dynmically create a way to process one + * This allows a plugin to dynamically create a way to process one * of these functions. * * The @parameters is a variable list of pevent_func_arg_type enums that @@ -4870,12 +5055,13 @@ int pevent_register_print_function(struct pevent *pevent, } /** - * pevent_register_event_handle - register a way to parse an event + * pevent_register_event_handler - register a way to parse an event * @pevent: the handle to the pevent * @id: the id of the event to register * @sys_name: the system name the event belongs to * @event_name: the name of the event * @func: the function to call to parse the event information + * @context: the data to be passed to @func * * This function allows a developer to override the parsing of * a given event. If for some reason the default print format @@ -4925,6 +5111,11 @@ int pevent_register_event_handler(struct pevent *pevent, if (sys_name) handle->sys_name = strdup(sys_name); + if ((event_name && !handle->event_name) || + (sys_name && !handle->sys_name)) { + die("Failed to allocate event/sys name"); + } + handle->func = func; handle->next = pevent->handlers; pevent->handlers = handle; diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index ac997bc7b592..5772ad8cb386 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -226,6 +226,11 @@ struct print_arg_symbol { struct print_flag_sym *symbols; }; +struct print_arg_hex { + struct print_arg *field; + struct print_arg *size; +}; + struct print_arg_dynarray { struct format_field *field; struct print_arg *index; @@ -253,6 +258,7 @@ enum print_arg_type { PRINT_FIELD, PRINT_FLAGS, PRINT_SYMBOL, + PRINT_HEX, PRINT_TYPE, PRINT_STRING, PRINT_BSTRING, @@ -270,6 +276,7 @@ struct print_arg { struct print_arg_typecast typecast; struct print_arg_flags flags; struct print_arg_symbol symbol; + struct print_arg_hex hex; struct print_arg_func func; struct print_arg_string string; struct print_arg_op op; diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c index dfcfe2c131de..ad17855528f9 100644 --- a/tools/lib/traceevent/parse-filter.c +++ b/tools/lib/traceevent/parse-filter.c @@ -96,7 +96,7 @@ static enum event_type read_token(char **tok) (strcmp(token, "=") == 0 || strcmp(token, "!") == 0) && pevent_peek_char() == '~') { /* append it */ - *tok = malloc(3); + *tok = malloc_or_die(3); sprintf(*tok, "%c%c", *token, '~'); free_token(token); /* Now remove the '~' from the buffer */ @@ -148,17 +148,11 @@ add_filter_type(struct event_filter *filter, int id) if (filter_type) return filter_type; - if (!filter->filters) - filter->event_filters = - malloc_or_die(sizeof(*filter->event_filters)); - else { - filter->event_filters = - realloc(filter->event_filters, - sizeof(*filter->event_filters) * - (filter->filters + 1)); - if (!filter->event_filters) - die("Could not allocate filter"); - } + filter->event_filters = realloc(filter->event_filters, + sizeof(*filter->event_filters) * + (filter->filters + 1)); + if (!filter->event_filters) + die("Could not allocate filter"); for (i = 0; i < filter->filters; i++) { if (filter->event_filters[i].event_id > id) @@ -1480,7 +1474,7 @@ void pevent_filter_clear_trivial(struct event_filter *filter, { struct filter_type *filter_type; int count = 0; - int *ids; + int *ids = NULL; int i; if (!filter->filters) @@ -1504,10 +1498,8 @@ void pevent_filter_clear_trivial(struct event_filter *filter, default: break; } - if (count) - ids = realloc(ids, sizeof(*ids) * (count + 1)); - else - ids = malloc(sizeof(*ids)); + + ids = realloc(ids, sizeof(*ids) * (count + 1)); if (!ids) die("Can't allocate ids"); ids[count++] = filter_type->event_id; @@ -1710,18 +1702,43 @@ static int test_num(struct event_format *event, static const char *get_field_str(struct filter_arg *arg, struct pevent_record *record) { - const char *val = record->data + arg->str.field->offset; + struct event_format *event; + struct pevent *pevent; + unsigned long long addr; + const char *val = NULL; + char hex[64]; - /* - * We need to copy the data since we can't be sure the field - * is null terminated. - */ - if (*(val + arg->str.field->size - 1)) { - /* copy it */ - memcpy(arg->str.buffer, val, arg->str.field->size); - /* the buffer is already NULL terminated */ - val = arg->str.buffer; + /* If the field is not a string convert it */ + if (arg->str.field->flags & FIELD_IS_STRING) { + val = record->data + arg->str.field->offset; + + /* + * We need to copy the data since we can't be sure the field + * is null terminated. + */ + if (*(val + arg->str.field->size - 1)) { + /* copy it */ + memcpy(arg->str.buffer, val, arg->str.field->size); + /* the buffer is already NULL terminated */ + val = arg->str.buffer; + } + + } else { + event = arg->str.field->event; + pevent = event->pevent; + addr = get_value(event, arg->str.field, record); + + if (arg->str.field->flags & (FIELD_IS_POINTER | FIELD_IS_LONG)) + /* convert to a kernel symbol */ + val = pevent_find_function(pevent, addr); + + if (val == NULL) { + /* just use the hex of the string name */ + snprintf(hex, 64, "0x%llx", addr); + val = hex; + } } + return val; } @@ -2001,11 +2018,13 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg) char *lstr; char *rstr; char *op; - char *str; + char *str = NULL; int len; lstr = arg_to_str(filter, arg->exp.left); rstr = arg_to_str(filter, arg->exp.right); + if (!lstr || !rstr) + goto out; switch (arg->exp.type) { case FILTER_EXP_ADD: @@ -2045,6 +2064,7 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg) len = strlen(op) + strlen(lstr) + strlen(rstr) + 4; str = malloc_or_die(len); snprintf(str, len, "%s %s %s", lstr, op, rstr); +out: free(lstr); free(rstr); @@ -2061,6 +2081,8 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg) lstr = arg_to_str(filter, arg->num.left); rstr = arg_to_str(filter, arg->num.right); + if (!lstr || !rstr) + goto out; switch (arg->num.type) { case FILTER_CMP_EQ: @@ -2097,6 +2119,7 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg) break; } +out: free(lstr); free(rstr); return str; @@ -2247,7 +2270,12 @@ int pevent_filter_compare(struct event_filter *filter1, struct event_filter *fil /* The best way to compare complex filters is with strings */ str1 = arg_to_str(filter1, filter_type1->filter); str2 = arg_to_str(filter2, filter_type2->filter); - result = strcmp(str1, str2) != 0; + if (str1 && str2) + result = strcmp(str1, str2) != 0; + else + /* bail out if allocation fails */ + result = 1; + free(str1); free(str2); if (result) diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt index a3dbadb26ef5..7065cd6fbdfc 100644 --- a/tools/perf/Documentation/perf-bench.txt +++ b/tools/perf/Documentation/perf-bench.txt @@ -12,7 +12,7 @@ SYNOPSIS DESCRIPTION ----------- -This 'perf bench' command is general framework for benchmark suites. +This 'perf bench' command is a general framework for benchmark suites. COMMON OPTIONS -------------- @@ -45,14 +45,20 @@ SUBSYSTEM 'sched':: Scheduler and IPC mechanisms. +'mem':: + Memory access performance. + +'all':: + All benchmark subsystems. + SUITES FOR 'sched' ~~~~~~~~~~~~~~~~~~ *messaging*:: Suite for evaluating performance of scheduler and IPC mechanisms. Based on hackbench by Rusty Russell. -Options of *pipe* -^^^^^^^^^^^^^^^^^ +Options of *messaging* +^^^^^^^^^^^^^^^^^^^^^^ -p:: --pipe:: Use pipe() instead of socketpair() @@ -115,6 +121,72 @@ Example of *pipe* 59004 ops/sec --------------------- +SUITES FOR 'mem' +~~~~~~~~~~~~~~~~ +*memcpy*:: +Suite for evaluating performance of simple memory copy in various ways. + +Options of *memcpy* +^^^^^^^^^^^^^^^^^^^ +-l:: +--length:: +Specify length of memory to copy (default: 1MB). +Available units are B, KB, MB, GB and TB (case insensitive). + +-r:: +--routine:: +Specify routine to copy (default: default). +Available routines are depend on the architecture. +On x86-64, x86-64-unrolled, x86-64-movsq and x86-64-movsb are supported. + +-i:: +--iterations:: +Repeat memcpy invocation this number of times. + +-c:: +--cycle:: +Use perf's cpu-cycles event instead of gettimeofday syscall. + +-o:: +--only-prefault:: +Show only the result with page faults before memcpy. + +-n:: +--no-prefault:: +Show only the result without page faults before memcpy. + +*memset*:: +Suite for evaluating performance of simple memory set in various ways. + +Options of *memset* +^^^^^^^^^^^^^^^^^^^ +-l:: +--length:: +Specify length of memory to set (default: 1MB). +Available units are B, KB, MB, GB and TB (case insensitive). + +-r:: +--routine:: +Specify routine to set (default: default). +Available routines are depend on the architecture. +On x86-64, x86-64-unrolled, x86-64-stosq and x86-64-stosb are supported. + +-i:: +--iterations:: +Repeat memset invocation this number of times. + +-c:: +--cycle:: +Use perf's cpu-cycles event instead of gettimeofday syscall. + +-o:: +--only-prefault:: +Show only the result with page faults before memset. + +-n:: +--no-prefault:: +Show only the result without page faults before memset. + SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 2d89f02719b5..495210a612c4 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -57,7 +57,7 @@ OPTIONS -s:: --sort=:: - Sort by key(s): pid, comm, dso, symbol, parent. + Sort by key(s): pid, comm, dso, symbol, parent, srcline. -p:: --parent=<regex>:: diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 4a5680cb242e..5b80d84d6b4a 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -112,7 +112,7 @@ Default is to monitor all CPUS. -s:: --sort:: - Sort by key(s): pid, comm, dso, symbol, parent + Sort by key(s): pid, comm, dso, symbol, parent, srcline. -n:: --show-nr-samples:: diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 0eee64cfe9a0..75d74e5db8d5 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -155,7 +155,7 @@ endif ### --- END CONFIGURATION SECTION --- -BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)/util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE +BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE BASIC_LDFLAGS = # Guard against environment variables @@ -503,6 +503,7 @@ else LIB_OBJS += $(OUTPUT)ui/progress.o LIB_OBJS += $(OUTPUT)ui/util.o LIB_OBJS += $(OUTPUT)ui/tui/setup.o + LIB_OBJS += $(OUTPUT)ui/tui/util.o LIB_H += ui/browser.h LIB_H += ui/browsers/map.h LIB_H += ui/helpline.h @@ -522,13 +523,18 @@ else msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev); BASIC_CFLAGS += -DNO_GTK2_SUPPORT else + ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2)),y) + BASIC_CFLAGS += -DHAVE_GTK_INFO_BAR + endif BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0) EXTLIBS += $(shell pkg-config --libs gtk+-2.0) LIB_OBJS += $(OUTPUT)ui/gtk/browser.o LIB_OBJS += $(OUTPUT)ui/gtk/setup.o + LIB_OBJS += $(OUTPUT)ui/gtk/util.o # Make sure that it'd be included only once. ifneq ($(findstring -DNO_NEWT_SUPPORT,$(BASIC_CFLAGS)),) LIB_OBJS += $(OUTPUT)ui/setup.o + LIB_OBJS += $(OUTPUT)ui/util.o endif endif endif diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c index 71557225bf92..02dad5d3359b 100644 --- a/tools/perf/bench/mem-memcpy.c +++ b/tools/perf/bench/mem-memcpy.c @@ -24,21 +24,21 @@ static const char *length_str = "1MB"; static const char *routine = "default"; static int iterations = 1; -static bool use_clock; -static int clock_fd; +static bool use_cycle; +static int cycle_fd; static bool only_prefault; static bool no_prefault; static const struct option options[] = { OPT_STRING('l', "length", &length_str, "1MB", "Specify length of memory to copy. " - "available unit: B, MB, GB (upper and lower)"), + "Available units: B, KB, MB, GB and TB (upper and lower)"), OPT_STRING('r', "routine", &routine, "default", "Specify routine to copy"), OPT_INTEGER('i', "iterations", &iterations, "repeat memcpy() invocation this number of times"), - OPT_BOOLEAN('c', "clock", &use_clock, - "Use CPU clock for measuring"), + OPT_BOOLEAN('c', "cycle", &use_cycle, + "Use cycles event instead of gettimeofday() for measuring"), OPT_BOOLEAN('o', "only-prefault", &only_prefault, "Show only the result with page faults before memcpy()"), OPT_BOOLEAN('n', "no-prefault", &no_prefault, @@ -76,27 +76,27 @@ static const char * const bench_mem_memcpy_usage[] = { NULL }; -static struct perf_event_attr clock_attr = { +static struct perf_event_attr cycle_attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }; -static void init_clock(void) +static void init_cycle(void) { - clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0); + cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0); - if (clock_fd < 0 && errno == ENOSYS) + if (cycle_fd < 0 && errno == ENOSYS) die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); else - BUG_ON(clock_fd < 0); + BUG_ON(cycle_fd < 0); } -static u64 get_clock(void) +static u64 get_cycle(void) { int ret; u64 clk; - ret = read(clock_fd, &clk, sizeof(u64)); + ret = read(cycle_fd, &clk, sizeof(u64)); BUG_ON(ret != sizeof(u64)); return clk; @@ -119,9 +119,9 @@ static void alloc_mem(void **dst, void **src, size_t length) die("memory allocation failed - maybe length is too large?\n"); } -static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault) +static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault) { - u64 clock_start = 0ULL, clock_end = 0ULL; + u64 cycle_start = 0ULL, cycle_end = 0ULL; void *src = NULL, *dst = NULL; int i; @@ -130,14 +130,14 @@ static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault) if (prefault) fn(dst, src, len); - clock_start = get_clock(); + cycle_start = get_cycle(); for (i = 0; i < iterations; ++i) fn(dst, src, len); - clock_end = get_clock(); + cycle_end = get_cycle(); free(src); free(dst); - return clock_end - clock_start; + return cycle_end - cycle_start; } static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault) @@ -182,17 +182,17 @@ int bench_mem_memcpy(int argc, const char **argv, int i; size_t len; double result_bps[2]; - u64 result_clock[2]; + u64 result_cycle[2]; argc = parse_options(argc, argv, options, bench_mem_memcpy_usage, 0); - if (use_clock) - init_clock(); + if (use_cycle) + init_cycle(); len = (size_t)perf_atoll((char *)length_str); - result_clock[0] = result_clock[1] = 0ULL; + result_cycle[0] = result_cycle[1] = 0ULL; result_bps[0] = result_bps[1] = 0.0; if ((s64)len <= 0) { @@ -223,11 +223,11 @@ int bench_mem_memcpy(int argc, const char **argv, if (!only_prefault && !no_prefault) { /* show both of results */ - if (use_clock) { - result_clock[0] = - do_memcpy_clock(routines[i].fn, len, false); - result_clock[1] = - do_memcpy_clock(routines[i].fn, len, true); + if (use_cycle) { + result_cycle[0] = + do_memcpy_cycle(routines[i].fn, len, false); + result_cycle[1] = + do_memcpy_cycle(routines[i].fn, len, true); } else { result_bps[0] = do_memcpy_gettimeofday(routines[i].fn, @@ -237,9 +237,9 @@ int bench_mem_memcpy(int argc, const char **argv, len, true); } } else { - if (use_clock) { - result_clock[pf] = - do_memcpy_clock(routines[i].fn, + if (use_cycle) { + result_cycle[pf] = + do_memcpy_cycle(routines[i].fn, len, only_prefault); } else { result_bps[pf] = @@ -251,12 +251,12 @@ int bench_mem_memcpy(int argc, const char **argv, switch (bench_format) { case BENCH_FORMAT_DEFAULT: if (!only_prefault && !no_prefault) { - if (use_clock) { - printf(" %14lf Clock/Byte\n", - (double)result_clock[0] + if (use_cycle) { + printf(" %14lf Cycle/Byte\n", + (double)result_cycle[0] / (double)len); - printf(" %14lf Clock/Byte (with prefault)\n", - (double)result_clock[1] + printf(" %14lf Cycle/Byte (with prefault)\n", + (double)result_cycle[1] / (double)len); } else { print_bps(result_bps[0]); @@ -265,9 +265,9 @@ int bench_mem_memcpy(int argc, const char **argv, printf(" (with prefault)\n"); } } else { - if (use_clock) { - printf(" %14lf Clock/Byte", - (double)result_clock[pf] + if (use_cycle) { + printf(" %14lf Cycle/Byte", + (double)result_cycle[pf] / (double)len); } else print_bps(result_bps[pf]); @@ -277,17 +277,17 @@ int bench_mem_memcpy(int argc, const char **argv, break; case BENCH_FORMAT_SIMPLE: if (!only_prefault && !no_prefault) { - if (use_clock) { + if (use_cycle) { printf("%lf %lf\n", - (double)result_clock[0] / (double)len, - (double)result_clock[1] / (double)len); + (double)result_cycle[0] / (double)len, + (double)result_cycle[1] / (double)len); } else { printf("%lf %lf\n", result_bps[0], result_bps[1]); } } else { - if (use_clock) { - printf("%lf\n", (double)result_clock[pf] + if (use_cycle) { + printf("%lf\n", (double)result_cycle[pf] / (double)len); } else printf("%lf\n", result_bps[pf]); diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c index e9079185bd72..350cc9557265 100644 --- a/tools/perf/bench/mem-memset.c +++ b/tools/perf/bench/mem-memset.c @@ -24,21 +24,21 @@ static const char *length_str = "1MB"; static const char *routine = "default"; static int iterations = 1; -static bool use_clock; -static int clock_fd; +static bool use_cycle; +static int cycle_fd; static bool only_prefault; static bool no_prefault; static const struct option options[] = { OPT_STRING('l', "length", &length_str, "1MB", - "Specify length of memory to copy. " - "available unit: B, MB, GB (upper and lower)"), + "Specify length of memory to set. " + "Available units: B, KB, MB, GB and TB (upper and lower)"), OPT_STRING('r', "routine", &routine, "default", - "Specify routine to copy"), + "Specify routine to set"), OPT_INTEGER('i', "iterations", &iterations, "repeat memset() invocation this number of times"), - OPT_BOOLEAN('c', "clock", &use_clock, - "Use CPU clock for measuring"), + OPT_BOOLEAN('c', "cycle", &use_cycle, + "Use cycles event instead of gettimeofday() for measuring"), OPT_BOOLEAN('o', "only-prefault", &only_prefault, "Show only the result with page faults before memset()"), OPT_BOOLEAN('n', "no-prefault", &no_prefault, @@ -76,27 +76,27 @@ static const char * const bench_mem_memset_usage[] = { NULL }; -static struct perf_event_attr clock_attr = { +static struct perf_event_attr cycle_attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES }; -static void init_clock(void) +static void init_cycle(void) { - clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0); + cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0); - if (clock_fd < 0 && errno == ENOSYS) + if (cycle_fd < 0 && errno == ENOSYS) die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); else - BUG_ON(clock_fd < 0); + BUG_ON(cycle_fd < 0); } -static u64 get_clock(void) +static u64 get_cycle(void) { int ret; u64 clk; - ret = read(clock_fd, &clk, sizeof(u64)); + ret = read(cycle_fd, &clk, sizeof(u64)); BUG_ON(ret != sizeof(u64)); return clk; @@ -115,9 +115,9 @@ static void alloc_mem(void **dst, size_t length) die("memory allocation failed - maybe length is too large?\n"); } -static u64 do_memset_clock(memset_t fn, size_t len, bool prefault) +static u64 do_memset_cycle(memset_t fn, size_t len, bool prefault) { - u64 clock_start = 0ULL, clock_end = 0ULL; + u64 cycle_start = 0ULL, cycle_end = 0ULL; void *dst = NULL; int i; @@ -126,13 +126,13 @@ static u64 do_memset_clock(memset_t fn, size_t len, bool prefault) if (prefault) fn(dst, -1, len); - clock_start = get_clock(); + cycle_start = get_cycle(); for (i = 0; i < iterations; ++i) fn(dst, i, len); - clock_end = get_clock(); + cycle_end = get_cycle(); free(dst); - return clock_end - clock_start; + return cycle_end - cycle_start; } static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault) @@ -176,17 +176,17 @@ int bench_mem_memset(int argc, const char **argv, int i; size_t len; double result_bps[2]; - u64 result_clock[2]; + u64 result_cycle[2]; argc = parse_options(argc, argv, options, bench_mem_memset_usage, 0); - if (use_clock) - init_clock(); + if (use_cycle) + init_cycle(); len = (size_t)perf_atoll((char *)length_str); - result_clock[0] = result_clock[1] = 0ULL; + result_cycle[0] = result_cycle[1] = 0ULL; result_bps[0] = result_bps[1] = 0.0; if ((s64)len <= 0) { @@ -217,11 +217,11 @@ int bench_mem_memset(int argc, const char **argv, if (!only_prefault && !no_prefault) { /* show both of results */ - if (use_clock) { - result_clock[0] = - do_memset_clock(routines[i].fn, len, false); - result_clock[1] = - do_memset_clock(routines[i].fn, len, true); + if (use_cycle) { + result_cycle[0] = + do_memset_cycle(routines[i].fn, len, false); + result_cycle[1] = + do_memset_cycle(routines[i].fn, len, true); } else { result_bps[0] = do_memset_gettimeofday(routines[i].fn, @@ -231,9 +231,9 @@ int bench_mem_memset(int argc, const char **argv, len, true); } } else { - if (use_clock) { - result_clock[pf] = - do_memset_clock(routines[i].fn, + if (use_cycle) { + result_cycle[pf] = + do_memset_cycle(routines[i].fn, len, only_prefault); } else { result_bps[pf] = @@ -245,12 +245,12 @@ int bench_mem_memset(int argc, const char **argv, switch (bench_format) { case BENCH_FORMAT_DEFAULT: if (!only_prefault && !no_prefault) { - if (use_clock) { - printf(" %14lf Clock/Byte\n", - (double)result_clock[0] + if (use_cycle) { + printf(" %14lf Cycle/Byte\n", + (double)result_cycle[0] / (double)len); - printf(" %14lf Clock/Byte (with prefault)\n ", - (double)result_clock[1] + printf(" %14lf Cycle/Byte (with prefault)\n ", + (double)result_cycle[1] / (double)len); } else { print_bps(result_bps[0]); @@ -259,9 +259,9 @@ int bench_mem_memset(int argc, const char **argv, printf(" (with prefault)\n"); } } else { - if (use_clock) { - printf(" %14lf Clock/Byte", - (double)result_clock[pf] + if (use_cycle) { + printf(" %14lf Cycle/Byte", + (double)result_cycle[pf] / (double)len); } else print_bps(result_bps[pf]); @@ -271,17 +271,17 @@ int bench_mem_memset(int argc, const char **argv, break; case BENCH_FORMAT_SIMPLE: if (!only_prefault && !no_prefault) { - if (use_clock) { + if (use_cycle) { printf("%lf %lf\n", - (double)result_clock[0] / (double)len, - (double)result_clock[1] / (double)len); + (double)result_cycle[0] / (double)len, + (double)result_cycle[1] / (double)len); } else { printf("%lf %lf\n", result_bps[0], result_bps[1]); } } else { - if (use_clock) { - printf("%lf\n", (double)result_clock[pf] + if (use_cycle) { + printf("%lf\n", (double)result_cycle[pf] / (double)len); } else printf("%lf\n", result_bps[pf]); diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index b0e74ab2d7a2..1f3100216448 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -33,7 +33,7 @@ struct bench_suite { }; \ /* sentinel: easy for help */ -#define suite_all { "all", "test all suite (pseudo suite)", NULL } +#define suite_all { "all", "Test all benchmark suites", NULL } static struct bench_suite sched_suites[] = { { "messaging", @@ -75,7 +75,7 @@ static struct bench_subsys subsystems[] = { "memory access performance", mem_suites }, { "all", /* sentinel: easy for help */ - "test all subsystem (pseudo subsystem)", + "all benchmark subsystem", NULL }, { NULL, NULL, diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index acd78dc28341..0dd5a058f766 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -60,7 +60,7 @@ static int __cmd_evlist(const char *input_name, struct perf_attr_details *detail list_for_each_entry(pos, &session->evlist->entries, node) { bool first = true; - printf("%s", event_name(pos)); + printf("%s", perf_evsel__name(pos)); if (details->verbose || details->freq) { comma_printf(&first, " sample_freq=%" PRIu64, diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 547af48deb4f..ce35015f2dc6 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -57,6 +57,11 @@ static unsigned long nr_allocs, nr_cross_allocs; #define PATH_SYS_NODE "/sys/devices/system/node" +struct perf_kmem { + struct perf_tool tool; + struct perf_session *session; +}; + static void init_cpunode_map(void) { FILE *fp; @@ -278,14 +283,16 @@ static void process_free_event(void *data, s_alloc->alloc_cpu = -1; } -static void process_raw_event(union perf_event *raw_event __used, void *data, +static void process_raw_event(struct perf_tool *tool, + union perf_event *raw_event __used, void *data, int cpu, u64 timestamp, struct thread *thread) { + struct perf_kmem *kmem = container_of(tool, struct perf_kmem, tool); struct event_format *event; int type; - type = trace_parse_common_type(data); - event = trace_find_event(type); + type = trace_parse_common_type(kmem->session->pevent, data); + event = pevent_find_event(kmem->session->pevent, type); if (!strcmp(event->name, "kmalloc") || !strcmp(event->name, "kmem_cache_alloc")) { @@ -306,7 +313,7 @@ static void process_raw_event(union perf_event *raw_event __used, void *data, } } -static int process_sample_event(struct perf_tool *tool __used, +static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel __used, @@ -322,16 +329,18 @@ static int process_sample_event(struct perf_tool *tool __used, dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid); - process_raw_event(event, sample->raw_data, sample->cpu, + process_raw_event(tool, event, sample->raw_data, sample->cpu, sample->time, thread); return 0; } -static struct perf_tool perf_kmem = { - .sample = process_sample_event, - .comm = perf_event__process_comm, - .ordered_samples = true, +static struct perf_kmem perf_kmem = { + .tool = { + .sample = process_sample_event, + .comm = perf_event__process_comm, + .ordered_samples = true, + }, }; static double fragmentation(unsigned long n_req, unsigned long n_alloc) @@ -486,11 +495,15 @@ static void sort_result(void) static int __cmd_kmem(void) { int err = -EINVAL; - struct perf_session *session = perf_session__new(input_name, O_RDONLY, - 0, false, &perf_kmem); + struct perf_session *session; + + session = perf_session__new(input_name, O_RDONLY, 0, false, + &perf_kmem.tool); if (session == NULL) return -ENOMEM; + perf_kmem.session = session; + if (perf_session__create_kernel_maps(session) < 0) goto out_delete; @@ -498,7 +511,7 @@ static int __cmd_kmem(void) goto out_delete; setup_pager(); - err = perf_session__process_events(session, &perf_kmem); + err = perf_session__process_events(session, &perf_kmem.tool); if (err != 0) goto out_delete; sort_result(); diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index fd53319de20d..b3c428548868 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -724,8 +724,8 @@ process_raw_event(void *data, int cpu, u64 timestamp, struct thread *thread) struct event_format *event; int type; - type = trace_parse_common_type(data); - event = trace_find_event(type); + type = trace_parse_common_type(session->pevent, data); + event = pevent_find_event(session->pevent, type); if (!strcmp(event->name, "lock_acquire")) process_lock_acquire_event(data, event, cpu, timestamp, thread); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f95840d04e4c..f5a6452931e6 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -265,7 +265,7 @@ try_again: if (err == ENOENT) { ui__error("The %s event is not supported.\n", - event_name(pos)); + perf_evsel__name(pos)); exit(EXIT_FAILURE); } @@ -916,7 +916,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) usage_with_options(record_usage, record_options); list_for_each_entry(pos, &evsel_list->entries, node) { - if (perf_header__push_event(pos->attr.config, event_name(pos))) + if (perf_header__push_event(pos->attr.config, perf_evsel__name(pos))) goto out_free_fd; } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 25249f76329d..69b1c1185159 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -69,7 +69,7 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool, if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { - err = machine__resolve_callchain(machine, evsel, al->thread, + err = machine__resolve_callchain(machine, al->thread, sample->callchain, &parent); if (err) return err; @@ -140,7 +140,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel, struct hist_entry *he; if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { - err = machine__resolve_callchain(machine, evsel, al->thread, + err = machine__resolve_callchain(machine, al->thread, sample->callchain, &parent); if (err) return err; @@ -230,7 +230,7 @@ static int process_read_event(struct perf_tool *tool, struct perf_report *rep = container_of(tool, struct perf_report, tool); if (rep->show_threads) { - const char *name = evsel ? event_name(evsel) : "unknown"; + const char *name = evsel ? perf_evsel__name(evsel) : "unknown"; perf_read_values_add_value(&rep->show_threads_values, event->read.pid, event->read.tid, event->read.id, @@ -239,17 +239,18 @@ static int process_read_event(struct perf_tool *tool, } dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid, - evsel ? event_name(evsel) : "FAIL", + evsel ? perf_evsel__name(evsel) : "FAIL", event->read.value); return 0; } +/* For pipe mode, sample_type is not currently set */ static int perf_report__setup_sample_type(struct perf_report *rep) { struct perf_session *self = rep->session; - if (!(self->sample_type & PERF_SAMPLE_CALLCHAIN)) { + if (!self->fd_pipe && !(self->sample_type & PERF_SAMPLE_CALLCHAIN)) { if (sort__has_parent) { ui__error("Selected --sort parent, but no " "callchain data. Did you call " @@ -272,7 +273,8 @@ static int perf_report__setup_sample_type(struct perf_report *rep) } if (sort__branch_mode == 1) { - if (!(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) { + if (!self->fd_pipe && + !(self->sample_type & PERF_SAMPLE_BRANCH_STACK)) { ui__error("Selected -b but no branch data. " "Did you call perf record without -b?\n"); return -1; @@ -314,7 +316,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, list_for_each_entry(pos, &evlist->entries, node) { struct hists *hists = &pos->hists; - const char *evname = event_name(pos); + const char *evname = perf_evsel__name(pos); hists__fprintf_nr_sample_events(hists, evname, stdout); hists__fprintf(hists, NULL, false, true, 0, 0, stdout); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index b125e07eb399..7a9ad2b1ee76 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -43,6 +43,11 @@ static u64 sleep_measurement_overhead; static unsigned long nr_tasks; +struct perf_sched { + struct perf_tool tool; + struct perf_session *session; +}; + struct sched_atom; struct task_desc { @@ -1597,11 +1602,13 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool, struct perf_evsel *evsel, struct machine *machine) { + struct perf_sched *sched = container_of(tool, struct perf_sched, tool); + struct pevent *pevent = sched->session->pevent; struct thread *thread = machine__findnew_thread(machine, sample->pid); if (thread == NULL) { pr_debug("problem processing %s event, skipping it.\n", - evsel->name); + perf_evsel__name(evsel)); return -1; } @@ -1612,7 +1619,8 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool, tracepoint_handler f = evsel->handler.func; if (evsel->handler.data == NULL) - evsel->handler.data = trace_find_event(evsel->attr.config); + evsel->handler.data = pevent_find_event(pevent, + evsel->attr.config); f(tool, evsel->handler.data, sample, machine, thread); } @@ -1620,12 +1628,14 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool, return 0; } -static struct perf_tool perf_sched = { - .sample = perf_sched__process_tracepoint_sample, - .comm = perf_event__process_comm, - .lost = perf_event__process_lost, - .fork = perf_event__process_task, - .ordered_samples = true, +static struct perf_sched perf_sched = { + .tool = { + .sample = perf_sched__process_tracepoint_sample, + .comm = perf_event__process_comm, + .lost = perf_event__process_lost, + .fork = perf_event__process_task, + .ordered_samples = true, + }, }; static void read_events(bool destroy, struct perf_session **psession) @@ -1640,16 +1650,20 @@ static void read_events(bool destroy, struct perf_session **psession) { "sched:sched_process_exit", process_sched_exit_event, }, { "sched:sched_migrate_task", process_sched_migrate_task_event, }, }; - struct perf_session *session = perf_session__new(input_name, O_RDONLY, - 0, false, &perf_sched); + struct perf_session *session; + + session = perf_session__new(input_name, O_RDONLY, 0, false, + &perf_sched.tool); if (session == NULL) die("No Memory"); - err = perf_evlist__set_tracepoints_handlers_array(session->evlist, handlers); + perf_sched.session = session; + + err = perf_session__set_tracepoints_handlers(session, handlers); assert(err == 0); if (perf_session__has_traces(session, "record -R")) { - err = perf_session__process_events(session, &perf_sched); + err = perf_session__process_events(session, &perf_sched.tool); if (err) die("Failed to process events, error %d", err); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 8e395a538eb9..1e60ab70b2b1 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -28,6 +28,11 @@ static bool system_wide; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); +struct perf_script { + struct perf_tool tool; + struct perf_session *session; +}; + enum perf_output_field { PERF_OUTPUT_COMM = 1U << 0, PERF_OUTPUT_TID = 1U << 1, @@ -137,10 +142,11 @@ static const char *output_field2str(enum perf_output_field field) #define PRINT_FIELD(x) (output[attr->type].fields & PERF_OUTPUT_##x) -static int perf_event_attr__check_stype(struct perf_event_attr *attr, - u64 sample_type, const char *sample_msg, - enum perf_output_field field) +static int perf_evsel__check_stype(struct perf_evsel *evsel, + u64 sample_type, const char *sample_msg, + enum perf_output_field field) { + struct perf_event_attr *attr = &evsel->attr; int type = attr->type; const char *evname; @@ -148,7 +154,7 @@ static int perf_event_attr__check_stype(struct perf_event_attr *attr, return 0; if (output[type].user_set) { - evname = __event_name(attr->type, attr->config); + evname = perf_evsel__name(evsel); pr_err("Samples for '%s' event do not have %s attribute set. " "Cannot print '%s' field.\n", evname, sample_msg, output_field2str(field)); @@ -157,7 +163,7 @@ static int perf_event_attr__check_stype(struct perf_event_attr *attr, /* user did not ask for it explicitly so remove from the default list */ output[type].fields &= ~field; - evname = __event_name(attr->type, attr->config); + evname = perf_evsel__name(evsel); pr_debug("Samples for '%s' event do not have %s attribute set. " "Skipping '%s' field.\n", evname, sample_msg, output_field2str(field)); @@ -175,8 +181,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, return -EINVAL; if (PRINT_FIELD(IP)) { - if (perf_event_attr__check_stype(attr, PERF_SAMPLE_IP, "IP", - PERF_OUTPUT_IP)) + if (perf_evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP", + PERF_OUTPUT_IP)) return -EINVAL; if (!no_callchain && @@ -185,8 +191,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, } if (PRINT_FIELD(ADDR) && - perf_event_attr__check_stype(attr, PERF_SAMPLE_ADDR, "ADDR", - PERF_OUTPUT_ADDR)) + perf_evsel__check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR", + PERF_OUTPUT_ADDR)) return -EINVAL; if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) { @@ -208,18 +214,18 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, } if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) && - perf_event_attr__check_stype(attr, PERF_SAMPLE_TID, "TID", - PERF_OUTPUT_TID|PERF_OUTPUT_PID)) + perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID", + PERF_OUTPUT_TID|PERF_OUTPUT_PID)) return -EINVAL; if (PRINT_FIELD(TIME) && - perf_event_attr__check_stype(attr, PERF_SAMPLE_TIME, "TIME", - PERF_OUTPUT_TIME)) + perf_evsel__check_stype(evsel, PERF_SAMPLE_TIME, "TIME", + PERF_OUTPUT_TIME)) return -EINVAL; if (PRINT_FIELD(CPU) && - perf_event_attr__check_stype(attr, PERF_SAMPLE_CPU, "CPU", - PERF_OUTPUT_CPU)) + perf_evsel__check_stype(evsel, PERF_SAMPLE_CPU, "CPU", + PERF_OUTPUT_CPU)) return -EINVAL; return 0; @@ -256,11 +262,13 @@ static int perf_session__check_output_opt(struct perf_session *session) return 0; } -static void print_sample_start(struct perf_sample *sample, +static void print_sample_start(struct pevent *pevent, + struct perf_sample *sample, struct thread *thread, - struct perf_event_attr *attr) + struct perf_evsel *evsel) { int type; + struct perf_event_attr *attr = &evsel->attr; struct event_format *event; const char *evname = NULL; unsigned long secs; @@ -300,12 +308,18 @@ static void print_sample_start(struct perf_sample *sample, if (PRINT_FIELD(EVNAME)) { if (attr->type == PERF_TYPE_TRACEPOINT) { - type = trace_parse_common_type(sample->raw_data); - event = trace_find_event(type); + /* + * XXX Do we really need this here? + * perf_evlist__set_tracepoint_names should have done + * this already + */ + type = trace_parse_common_type(pevent, + sample->raw_data); + event = pevent_find_event(pevent, type); if (event) evname = event->name; } else - evname = __event_name(attr->type, attr->config); + evname = perf_evsel__name(evsel); printf("%s: ", evname ? evname : "[unknown]"); } @@ -387,7 +401,7 @@ static void print_sample_bts(union perf_event *event, printf(" "); else printf("\n"); - perf_event__print_ip(event, sample, machine, evsel, + perf_event__print_ip(event, sample, machine, PRINT_FIELD(SYM), PRINT_FIELD(DSO), PRINT_FIELD(SYMOFFSET)); } @@ -402,6 +416,7 @@ static void print_sample_bts(union perf_event *event, } static void process_event(union perf_event *event __unused, + struct pevent *pevent, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine, @@ -412,7 +427,7 @@ static void process_event(union perf_event *event __unused, if (output[attr->type].fields == 0) return; - print_sample_start(sample, thread, attr); + print_sample_start(pevent, sample, thread, evsel); if (is_bts_event(attr)) { print_sample_bts(event, sample, evsel, machine, thread); @@ -420,7 +435,7 @@ static void process_event(union perf_event *event __unused, } if (PRINT_FIELD(TRACE)) - print_trace_event(sample->cpu, sample->raw_data, + print_trace_event(pevent, sample->cpu, sample->raw_data, sample->raw_size); if (PRINT_FIELD(ADDR)) @@ -431,7 +446,7 @@ static void process_event(union perf_event *event __unused, printf(" "); else printf("\n"); - perf_event__print_ip(event, sample, machine, evsel, + perf_event__print_ip(event, sample, machine, PRINT_FIELD(SYM), PRINT_FIELD(DSO), PRINT_FIELD(SYMOFFSET)); } @@ -451,7 +466,8 @@ static int default_stop_script(void) return 0; } -static int default_generate_script(const char *outfile __unused) +static int default_generate_script(struct pevent *pevent __unused, + const char *outfile __unused) { return 0; } @@ -489,6 +505,7 @@ static int process_sample_event(struct perf_tool *tool __used, struct machine *machine) { struct addr_location al; + struct perf_script *scr = container_of(tool, struct perf_script, tool); struct thread *thread = machine__findnew_thread(machine, event->ip.tid); if (thread == NULL) { @@ -520,24 +537,27 @@ static int process_sample_event(struct perf_tool *tool __used, if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) return 0; - scripting_ops->process_event(event, sample, evsel, machine, thread); + scripting_ops->process_event(event, scr->session->pevent, + sample, evsel, machine, thread); evsel->hists.stats.total_period += sample->period; return 0; } -static struct perf_tool perf_script = { - .sample = process_sample_event, - .mmap = perf_event__process_mmap, - .comm = perf_event__process_comm, - .exit = perf_event__process_task, - .fork = perf_event__process_task, - .attr = perf_event__process_attr, - .event_type = perf_event__process_event_type, - .tracing_data = perf_event__process_tracing_data, - .build_id = perf_event__process_build_id, - .ordered_samples = true, - .ordering_requires_timestamps = true, +static struct perf_script perf_script = { + .tool = { + .sample = process_sample_event, + .mmap = perf_event__process_mmap, + .comm = perf_event__process_comm, + .exit = perf_event__process_task, + .fork = perf_event__process_task, + .attr = perf_event__process_attr, + .event_type = perf_event__process_event_type, + .tracing_data = perf_event__process_tracing_data, + .build_id = perf_event__process_build_id, + .ordered_samples = true, + .ordering_requires_timestamps = true, + }, }; extern volatile int session_done; @@ -553,7 +573,7 @@ static int __cmd_script(struct perf_session *session) signal(SIGINT, sig_handler); - ret = perf_session__process_events(session, &perf_script); + ret = perf_session__process_events(session, &perf_script.tool); if (debug_mode) pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered); @@ -1335,10 +1355,13 @@ int cmd_script(int argc, const char **argv, const char *prefix __used) if (!script_name) setup_pager(); - session = perf_session__new(input_name, O_RDONLY, 0, false, &perf_script); + session = perf_session__new(input_name, O_RDONLY, 0, false, + &perf_script.tool); if (session == NULL) return -ENOMEM; + perf_script.session = session; + if (cpu_list) { if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap)) return -1; @@ -1384,7 +1407,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __used) return -1; } - err = scripting_ops->generate_script("perf-script"); + err = scripting_ops->generate_script(session->pevent, + "perf-script"); goto out; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 07b5c7703dd1..861f0aec77ae 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -391,7 +391,7 @@ static int read_counter_aggr(struct perf_evsel *counter) if (verbose) { fprintf(output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n", - event_name(counter), count[0], count[1], count[2]); + perf_evsel__name(counter), count[0], count[1], count[2]); } /* @@ -496,7 +496,7 @@ static int run_perf_stat(int argc __used, const char **argv) errno == ENXIO) { if (verbose) ui__warning("%s event is not supported by the kernel.\n", - event_name(counter)); + perf_evsel__name(counter)); counter->supported = false; continue; } @@ -594,7 +594,7 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg) csv_output ? 0 : -4, evsel_list->cpus->map[cpu], csv_sep); - fprintf(output, fmt, cpustr, msecs, csv_sep, event_name(evsel)); + fprintf(output, fmt, cpustr, msecs, csv_sep, perf_evsel__name(evsel)); if (evsel->cgrp) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); @@ -792,7 +792,7 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) else cpu = 0; - fprintf(output, fmt, cpustr, avg, csv_sep, event_name(evsel)); + fprintf(output, fmt, cpustr, avg, csv_sep, perf_evsel__name(evsel)); if (evsel->cgrp) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); @@ -908,7 +908,7 @@ static void print_counter_aggr(struct perf_evsel *counter) counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, csv_sep, csv_output ? 0 : -24, - event_name(counter)); + perf_evsel__name(counter)); if (counter->cgrp) fprintf(output, "%s%s", csv_sep, counter->cgrp->name); @@ -961,7 +961,7 @@ static void print_counter(struct perf_evsel *counter) counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, csv_sep, csv_output ? 0 : -24, - event_name(counter)); + perf_evsel__name(counter)); if (counter->cgrp) fprintf(output, "%s%s", diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 5a8727c08757..5ce30305462b 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -583,7 +583,7 @@ static int test__basic_mmap(void) if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) { pr_debug("expected %d %s events, got %d\n", expected_nr_events[evsel->idx], - event_name(evsel), nr_events[evsel->idx]); + perf_evsel__name(evsel), nr_events[evsel->idx]); goto out_munmap; } } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 6bb0277b7dfe..e3cab5f088f8 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -245,7 +245,7 @@ static void perf_top__show_details(struct perf_top *top) if (notes->src == NULL) goto out_unlock; - printf("Showing %s for %s\n", event_name(top->sym_evsel), symbol->name); + printf("Showing %s for %s\n", perf_evsel__name(top->sym_evsel), symbol->name); printf(" Events Pcnt (>=%d%%)\n", top->sym_pcnt_filter); more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel->idx, @@ -408,7 +408,7 @@ static void perf_top__print_mapped_keys(struct perf_top *top) fprintf(stdout, "\t[e] display entries (lines). \t(%d)\n", top->print_entries); if (top->evlist->nr_entries > 1) - fprintf(stdout, "\t[E] active event counter. \t(%s)\n", event_name(top->sym_evsel)); + fprintf(stdout, "\t[E] active event counter. \t(%s)\n", perf_evsel__name(top->sym_evsel)); fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", top->count_filter); @@ -503,13 +503,13 @@ static void perf_top__handle_keypress(struct perf_top *top, int c) fprintf(stderr, "\nAvailable events:"); list_for_each_entry(top->sym_evsel, &top->evlist->entries, node) - fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, event_name(top->sym_evsel)); + fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, perf_evsel__name(top->sym_evsel)); prompt_integer(&counter, "Enter details event counter"); if (counter >= top->evlist->nr_entries) { top->sym_evsel = list_entry(top->evlist->entries.next, struct perf_evsel, node); - fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(top->sym_evsel)); + fprintf(stderr, "Sorry, no such event, using %s.\n", perf_evsel__name(top->sym_evsel)); sleep(1); break; } @@ -774,7 +774,7 @@ static void perf_event__process_sample(struct perf_tool *tool, if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { - err = machine__resolve_callchain(machine, evsel, al.thread, + err = machine__resolve_callchain(machine, al.thread, sample->callchain, &parent); if (err) return; @@ -960,7 +960,7 @@ try_again: if (err == ENOENT) { ui__error("The %s event is not supported.\n", - event_name(counter)); + perf_evsel__name(counter)); goto out_err; } else if (err == EMFILE) { ui__error("Too many events are opened.\n" diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak index d9084e03ce56..6c18785a6417 100644 --- a/tools/perf/config/feature-tests.mak +++ b/tools/perf/config/feature-tests.mak @@ -78,6 +78,19 @@ int main(int argc, char *argv[]) return 0; } endef + +define SOURCE_GTK2_INFOBAR +#pragma GCC diagnostic ignored \"-Wstrict-prototypes\" +#include <gtk/gtk.h> +#pragma GCC diagnostic error \"-Wstrict-prototypes\" + +int main(void) +{ + gtk_info_bar_new(); + + return 0; +} +endef endif ifndef NO_LIBPERL diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 34b1c46eaf42..67a2703e666a 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -814,7 +814,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, { struct disasm_line *pos, *n; struct annotation *notes; - const size_t size = symbol__size(sym); + size_t size; struct map_symbol ms = { .map = map, .sym = sym, @@ -834,6 +834,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, if (sym == NULL) return -1; + size = symbol__size(sym); + if (map->dso->annotate_warned) return -1; diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 53f6697d014e..482f0517b61e 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -23,6 +23,7 @@ struct hist_browser { struct hists *hists; struct hist_entry *he_selection; struct map_symbol *selection; + int print_seq; bool has_symbols; }; @@ -800,6 +801,196 @@ do_offset: } } +static int hist_browser__fprintf_callchain_node_rb_tree(struct hist_browser *browser, + struct callchain_node *chain_node, + u64 total, int level, + FILE *fp) +{ + struct rb_node *node; + int offset = level * LEVEL_OFFSET_STEP; + u64 new_total, remaining; + int printed = 0; + + if (callchain_param.mode == CHAIN_GRAPH_REL) + new_total = chain_node->children_hit; + else + new_total = total; + + remaining = new_total; + node = rb_first(&chain_node->rb_root); + while (node) { + struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); + struct rb_node *next = rb_next(node); + u64 cumul = callchain_cumul_hits(child); + struct callchain_list *chain; + char folded_sign = ' '; + int first = true; + int extra_offset = 0; + + remaining -= cumul; + + list_for_each_entry(chain, &child->val, list) { + char ipstr[BITS_PER_LONG / 4 + 1], *alloc_str; + const char *str; + bool was_first = first; + + if (first) + first = false; + else + extra_offset = LEVEL_OFFSET_STEP; + + folded_sign = callchain_list__folded(chain); + + alloc_str = NULL; + str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); + if (was_first) { + double percent = cumul * 100.0 / new_total; + + if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0) + str = "Not enough memory!"; + else + str = alloc_str; + } + + printed += fprintf(fp, "%*s%c %s\n", offset + extra_offset, " ", folded_sign, str); + free(alloc_str); + if (folded_sign == '+') + break; + } + + if (folded_sign == '-') { + const int new_level = level + (extra_offset ? 2 : 1); + printed += hist_browser__fprintf_callchain_node_rb_tree(browser, child, new_total, + new_level, fp); + } + + node = next; + } + + return printed; +} + +static int hist_browser__fprintf_callchain_node(struct hist_browser *browser, + struct callchain_node *node, + int level, FILE *fp) +{ + struct callchain_list *chain; + int offset = level * LEVEL_OFFSET_STEP; + char folded_sign = ' '; + int printed = 0; + + list_for_each_entry(chain, &node->val, list) { + char ipstr[BITS_PER_LONG / 4 + 1], *s; + + folded_sign = callchain_list__folded(chain); + s = callchain_list__sym_name(chain, ipstr, sizeof(ipstr)); + printed += fprintf(fp, "%*s%c %s\n", offset, " ", folded_sign, s); + } + + if (folded_sign == '-') + printed += hist_browser__fprintf_callchain_node_rb_tree(browser, node, + browser->hists->stats.total_period, + level + 1, fp); + return printed; +} + +static int hist_browser__fprintf_callchain(struct hist_browser *browser, + struct rb_root *chain, int level, FILE *fp) +{ + struct rb_node *nd; + int printed = 0; + + for (nd = rb_first(chain); nd; nd = rb_next(nd)) { + struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node); + + printed += hist_browser__fprintf_callchain_node(browser, node, level, fp); + } + + return printed; +} + +static int hist_browser__fprintf_entry(struct hist_browser *browser, + struct hist_entry *he, FILE *fp) +{ + char s[8192]; + double percent; + int printed = 0; + char folded_sign = ' '; + + if (symbol_conf.use_callchain) + folded_sign = hist_entry__folded(he); + + hist_entry__snprintf(he, s, sizeof(s), browser->hists); + percent = (he->period * 100.0) / browser->hists->stats.total_period; + + if (symbol_conf.use_callchain) + printed += fprintf(fp, "%c ", folded_sign); + + printed += fprintf(fp, " %5.2f%%", percent); + + if (symbol_conf.show_nr_samples) + printed += fprintf(fp, " %11u", he->nr_events); + + if (symbol_conf.show_total_period) + printed += fprintf(fp, " %12" PRIu64, he->period); + + printed += fprintf(fp, "%s\n", rtrim(s)); + + if (folded_sign == '-') + printed += hist_browser__fprintf_callchain(browser, &he->sorted_chain, 1, fp); + + return printed; +} + +static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp) +{ + struct rb_node *nd = hists__filter_entries(rb_first(browser->b.entries)); + int printed = 0; + + while (nd) { + struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); + + printed += hist_browser__fprintf_entry(browser, h, fp); + nd = hists__filter_entries(rb_next(nd)); + } + + return printed; +} + +static int hist_browser__dump(struct hist_browser *browser) +{ + char filename[64]; + FILE *fp; + + while (1) { + scnprintf(filename, sizeof(filename), "perf.hist.%d", browser->print_seq); + if (access(filename, F_OK)) + break; + /* + * XXX: Just an arbitrary lazy upper limit + */ + if (++browser->print_seq == 8192) { + ui_helpline__fpush("Too many perf.hist.N files, nothing written!"); + return -1; + } + } + + fp = fopen(filename, "w"); + if (fp == NULL) { + char bf[64]; + strerror_r(errno, bf, sizeof(bf)); + ui_helpline__fpush("Couldn't write to %s: %s", filename, bf); + return -1; + } + + ++browser->print_seq; + hist_browser__fprintf(browser, fp); + fclose(fp); + ui_helpline__fpush("%s written!", filename); + + return 0; +} + static struct hist_browser *hist_browser__new(struct hists *hists) { struct hist_browser *browser = zalloc(sizeof(*browser)); @@ -937,6 +1128,9 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, browser->selection->map->dso->annotate_warned) continue; goto do_annotate; + case 'P': + hist_browser__dump(browser); + continue; case 'd': goto zoom_dso; case 't': @@ -969,6 +1163,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, "E Expand all callchains\n" "d Zoom into current DSO\n" "t Zoom into current Thread\n" + "P Print histograms to perf.hist.N\n" "/ Filter symbol by name"); continue; case K_ENTER: @@ -1172,7 +1367,7 @@ static void perf_evsel_menu__write(struct ui_browser *browser, struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node); bool current_entry = ui_browser__is_current_entry(browser, row); unsigned long nr_events = evsel->hists.stats.nr_events[PERF_RECORD_SAMPLE]; - const char *ev_name = event_name(evsel); + const char *ev_name = perf_evsel__name(evsel); char bf[256], unit; const char *warn = " "; size_t printed; @@ -1240,7 +1435,7 @@ browse_hists: */ if (timer) timer(arg); - ev_name = event_name(pos); + ev_name = perf_evsel__name(pos); key = perf_evsel__hists_browse(pos, nr_events, help, ev_name, true, timer, arg, delay_secs); @@ -1309,17 +1504,11 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, ui_helpline__push("Press ESC to exit"); list_for_each_entry(pos, &evlist->entries, node) { - const char *ev_name = event_name(pos); + const char *ev_name = perf_evsel__name(pos); size_t line_len = strlen(ev_name) + 7; if (menu.b.width < line_len) menu.b.width = line_len; - /* - * Cache the evsel name, tracepoints have a _high_ cost per - * event_name() call. - */ - if (pos->name == NULL) - pos->name = strdup(ev_name); } return perf_evsel_menu__run(&menu, evlist->nr_entries, help, timer, @@ -1330,11 +1519,10 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, void(*timer)(void *arg), void *arg, int delay_secs) { - if (evlist->nr_entries == 1) { struct perf_evsel *first = list_entry(evlist->entries.next, struct perf_evsel, node); - const char *ev_name = event_name(first); + const char *ev_name = perf_evsel__name(first); return perf_evsel__hists_browse(first, evlist->nr_entries, help, ev_name, false, timer, arg, delay_secs); diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c index 0656c381a89c..ec12e0b4ded6 100644 --- a/tools/perf/ui/gtk/browser.c +++ b/tools/perf/ui/gtk/browser.c @@ -11,8 +11,8 @@ static void perf_gtk__signal(int sig) { + perf_gtk__exit(false); psignal(sig, "perf"); - gtk_main_quit(); } static void perf_gtk__resize_window(GtkWidget *window) @@ -122,13 +122,59 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) gtk_container_add(GTK_CONTAINER(window), view); } +#ifdef HAVE_GTK_INFO_BAR +static GtkWidget *perf_gtk__setup_info_bar(void) +{ + GtkWidget *info_bar; + GtkWidget *label; + GtkWidget *content_area; + + info_bar = gtk_info_bar_new(); + gtk_widget_set_no_show_all(info_bar, TRUE); + + label = gtk_label_new(""); + gtk_widget_show(label); + + content_area = gtk_info_bar_get_content_area(GTK_INFO_BAR(info_bar)); + gtk_container_add(GTK_CONTAINER(content_area), label); + + gtk_info_bar_add_button(GTK_INFO_BAR(info_bar), GTK_STOCK_OK, + GTK_RESPONSE_OK); + g_signal_connect(info_bar, "response", + G_CALLBACK(gtk_widget_hide), NULL); + + pgctx->info_bar = info_bar; + pgctx->message_label = label; + + return info_bar; +} +#endif + +static GtkWidget *perf_gtk__setup_statusbar(void) +{ + GtkWidget *stbar; + unsigned ctxid; + + stbar = gtk_statusbar_new(); + + ctxid = gtk_statusbar_get_context_id(GTK_STATUSBAR(stbar), + "perf report"); + pgctx->statbar = stbar; + pgctx->statbar_ctx_id = ctxid; + + return stbar; +} + int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, const char *help __used, void (*timer) (void *arg)__used, void *arg __used, int delay_secs __used) { struct perf_evsel *pos; + GtkWidget *vbox; GtkWidget *notebook; + GtkWidget *info_bar; + GtkWidget *statbar; GtkWidget *window; signal(SIGSEGV, perf_gtk__signal); @@ -143,11 +189,17 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, g_signal_connect(window, "delete_event", gtk_main_quit, NULL); + pgctx = perf_gtk__activate_context(window); + if (!pgctx) + return -1; + + vbox = gtk_vbox_new(FALSE, 0); + notebook = gtk_notebook_new(); list_for_each_entry(pos, &evlist->entries, node) { struct hists *hists = &pos->hists; - const char *evname = event_name(pos); + const char *evname = perf_evsel__name(pos); GtkWidget *scrolled_window; GtkWidget *tab_label; @@ -164,7 +216,16 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, gtk_notebook_append_page(GTK_NOTEBOOK(notebook), scrolled_window, tab_label); } - gtk_container_add(GTK_CONTAINER(window), notebook); + gtk_box_pack_start(GTK_BOX(vbox), notebook, TRUE, TRUE, 0); + + info_bar = perf_gtk__setup_info_bar(); + if (info_bar) + gtk_box_pack_start(GTK_BOX(vbox), info_bar, FALSE, FALSE, 0); + + statbar = perf_gtk__setup_statusbar(); + gtk_box_pack_start(GTK_BOX(vbox), statbar, FALSE, FALSE, 0); + + gtk_container_add(GTK_CONTAINER(window), vbox); gtk_widget_show_all(window); @@ -174,5 +235,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, gtk_main(); + perf_gtk__deactivate_context(&pgctx); + return 0; } diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h index 75177ee04032..a4d0f2b4a2dc 100644 --- a/tools/perf/ui/gtk/gtk.h +++ b/tools/perf/ui/gtk/gtk.h @@ -1,8 +1,39 @@ #ifndef _PERF_GTK_H_ #define _PERF_GTK_H_ 1 +#include <stdbool.h> + #pragma GCC diagnostic ignored "-Wstrict-prototypes" #include <gtk/gtk.h> #pragma GCC diagnostic error "-Wstrict-prototypes" + +struct perf_gtk_context { + GtkWidget *main_window; + +#ifdef HAVE_GTK_INFO_BAR + GtkWidget *info_bar; + GtkWidget *message_label; +#endif + GtkWidget *statbar; + guint statbar_ctx_id; +}; + +extern struct perf_gtk_context *pgctx; + +static inline bool perf_gtk__is_active_context(struct perf_gtk_context *ctx) +{ + return ctx && ctx->main_window; +} + +struct perf_gtk_context *perf_gtk__activate_context(GtkWidget *window); +int perf_gtk__deactivate_context(struct perf_gtk_context **ctx); + +#ifndef HAVE_GTK_INFO_BAR +static inline GtkWidget *perf_gtk__setup_info_bar(void) +{ + return NULL; +} +#endif + #endif /* _PERF_GTK_H_ */ diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c index 829529957766..92879ce61e2f 100644 --- a/tools/perf/ui/gtk/setup.c +++ b/tools/perf/ui/gtk/setup.c @@ -1,12 +1,17 @@ #include "gtk.h" #include "../../util/cache.h" +#include "../../util/debug.h" + +extern struct perf_error_ops perf_gtk_eops; int perf_gtk__init(void) { + perf_error__register(&perf_gtk_eops); return gtk_init_check(NULL, NULL) ? 0 : -1; } void perf_gtk__exit(bool wait_for_ok __used) { + perf_error__unregister(&perf_gtk_eops); gtk_main_quit(); } diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c new file mode 100644 index 000000000000..0ead373c0dfb --- /dev/null +++ b/tools/perf/ui/gtk/util.c @@ -0,0 +1,129 @@ +#include "../util.h" +#include "../../util/debug.h" +#include "gtk.h" + +#include <string.h> + + +struct perf_gtk_context *pgctx; + +struct perf_gtk_context *perf_gtk__activate_context(GtkWidget *window) +{ + struct perf_gtk_context *ctx; + + ctx = malloc(sizeof(*pgctx)); + if (ctx) + ctx->main_window = window; + + return ctx; +} + +int perf_gtk__deactivate_context(struct perf_gtk_context **ctx) +{ + if (!perf_gtk__is_active_context(*ctx)) + return -1; + + free(*ctx); + *ctx = NULL; + return 0; +} + +static int perf_gtk__error(const char *format, va_list args) +{ + char *msg; + GtkWidget *dialog; + + if (!perf_gtk__is_active_context(pgctx) || + vasprintf(&msg, format, args) < 0) { + fprintf(stderr, "Error:\n"); + vfprintf(stderr, format, args); + fprintf(stderr, "\n"); + return -1; + } + + dialog = gtk_message_dialog_new_with_markup(GTK_WINDOW(pgctx->main_window), + GTK_DIALOG_DESTROY_WITH_PARENT, + GTK_MESSAGE_ERROR, + GTK_BUTTONS_CLOSE, + "<b>Error</b>\n\n%s", msg); + gtk_dialog_run(GTK_DIALOG(dialog)); + + gtk_widget_destroy(dialog); + free(msg); + return 0; +} + +#ifdef HAVE_GTK_INFO_BAR +static int perf_gtk__warning_info_bar(const char *format, va_list args) +{ + char *msg; + + if (!perf_gtk__is_active_context(pgctx) || + vasprintf(&msg, format, args) < 0) { + fprintf(stderr, "Warning:\n"); + vfprintf(stderr, format, args); + fprintf(stderr, "\n"); + return -1; + } + + gtk_label_set_text(GTK_LABEL(pgctx->message_label), msg); + gtk_info_bar_set_message_type(GTK_INFO_BAR(pgctx->info_bar), + GTK_MESSAGE_WARNING); + gtk_widget_show(pgctx->info_bar); + + free(msg); + return 0; +} +#else +static int perf_gtk__warning_statusbar(const char *format, va_list args) +{ + char *msg, *p; + + if (!perf_gtk__is_active_context(pgctx) || + vasprintf(&msg, format, args) < 0) { + fprintf(stderr, "Warning:\n"); + vfprintf(stderr, format, args); + fprintf(stderr, "\n"); + return -1; + } + + gtk_statusbar_pop(GTK_STATUSBAR(pgctx->statbar), + pgctx->statbar_ctx_id); + + /* Only first line can be displayed */ + p = strchr(msg, '\n'); + if (p) + *p = '\0'; + + gtk_statusbar_push(GTK_STATUSBAR(pgctx->statbar), + pgctx->statbar_ctx_id, msg); + + free(msg); + return 0; +} +#endif + +struct perf_error_ops perf_gtk_eops = { + .error = perf_gtk__error, +#ifdef HAVE_GTK_INFO_BAR + .warning = perf_gtk__warning_info_bar, +#else + .warning = perf_gtk__warning_statusbar, +#endif +}; + +/* + * FIXME: Functions below should be implemented properly. + * For now, just add stubs for NO_NEWT=1 build. + */ +#ifdef NO_NEWT_SUPPORT +int ui_helpline__show_help(const char *format __used, va_list ap __used) +{ + return 0; +} + +void ui_progress__update(u64 curr __used, u64 total __used, + const char *title __used) +{ +} +#endif diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index d33e943ac434..e813c1d17346 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -15,6 +15,8 @@ pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER; static volatile int ui__need_resize; +extern struct perf_error_ops perf_tui_eops; + void ui__refresh_dimensions(bool force) { if (force || ui__need_resize) { @@ -122,6 +124,8 @@ int ui__init(void) signal(SIGINT, ui__signal); signal(SIGQUIT, ui__signal); signal(SIGTERM, ui__signal); + + perf_error__register(&perf_tui_eops); out: return err; } @@ -137,4 +141,6 @@ void ui__exit(bool wait_for_ok) SLsmg_refresh(); SLsmg_reset_smg(); SLang_reset_tty(); + + perf_error__unregister(&perf_tui_eops); } diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c new file mode 100644 index 000000000000..092902e30cee --- /dev/null +++ b/tools/perf/ui/tui/util.c @@ -0,0 +1,243 @@ +#include "../../util/util.h" +#include <signal.h> +#include <stdbool.h> +#include <string.h> +#include <sys/ttydefaults.h> + +#include "../../util/cache.h" +#include "../../util/debug.h" +#include "../browser.h" +#include "../keysyms.h" +#include "../helpline.h" +#include "../ui.h" +#include "../util.h" +#include "../libslang.h" + +static void ui_browser__argv_write(struct ui_browser *browser, + void *entry, int row) +{ + char **arg = entry; + bool current_entry = ui_browser__is_current_entry(browser, row); + + ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED : + HE_COLORSET_NORMAL); + slsmg_write_nstring(*arg, browser->width); +} + +static int popup_menu__run(struct ui_browser *menu) +{ + int key; + + if (ui_browser__show(menu, " ", "ESC: exit, ENTER|->: Select option") < 0) + return -1; + + while (1) { + key = ui_browser__run(menu, 0); + + switch (key) { + case K_RIGHT: + case K_ENTER: + key = menu->index; + break; + case K_LEFT: + case K_ESC: + case 'q': + case CTRL('c'): + key = -1; + break; + default: + continue; + } + + break; + } + + ui_browser__hide(menu); + return key; +} + +int ui__popup_menu(int argc, char * const argv[]) +{ + struct ui_browser menu = { + .entries = (void *)argv, + .refresh = ui_browser__argv_refresh, + .seek = ui_browser__argv_seek, + .write = ui_browser__argv_write, + .nr_entries = argc, + }; + + return popup_menu__run(&menu); +} + +int ui_browser__input_window(const char *title, const char *text, char *input, + const char *exit_msg, int delay_secs) +{ + int x, y, len, key; + int max_len = 60, nr_lines = 0; + static char buf[50]; + const char *t; + + t = text; + while (1) { + const char *sep = strchr(t, '\n'); + + if (sep == NULL) + sep = strchr(t, '\0'); + len = sep - t; + if (max_len < len) + max_len = len; + ++nr_lines; + if (*sep == '\0') + break; + t = sep + 1; + } + + max_len += 2; + nr_lines += 8; + y = SLtt_Screen_Rows / 2 - nr_lines / 2; + x = SLtt_Screen_Cols / 2 - max_len / 2; + + SLsmg_set_color(0); + SLsmg_draw_box(y, x++, nr_lines, max_len); + if (title) { + SLsmg_gotorc(y, x + 1); + SLsmg_write_string((char *)title); + } + SLsmg_gotorc(++y, x); + nr_lines -= 7; + max_len -= 2; + SLsmg_write_wrapped_string((unsigned char *)text, y, x, + nr_lines, max_len, 1); + y += nr_lines; + len = 5; + while (len--) { + SLsmg_gotorc(y + len - 1, x); + SLsmg_write_nstring((char *)" ", max_len); + } + SLsmg_draw_box(y++, x + 1, 3, max_len - 2); + + SLsmg_gotorc(y + 3, x); + SLsmg_write_nstring((char *)exit_msg, max_len); + SLsmg_refresh(); + + x += 2; + len = 0; + key = ui__getch(delay_secs); + while (key != K_TIMER && key != K_ENTER && key != K_ESC) { + if (key == K_BKSPC) { + if (len == 0) + goto next_key; + SLsmg_gotorc(y, x + --len); + SLsmg_write_char(' '); + } else { + buf[len] = key; + SLsmg_gotorc(y, x + len++); + SLsmg_write_char(key); + } + SLsmg_refresh(); + + /* XXX more graceful overflow handling needed */ + if (len == sizeof(buf) - 1) { + ui_helpline__push("maximum size of symbol name reached!"); + key = K_ENTER; + break; + } +next_key: + key = ui__getch(delay_secs); + } + + buf[len] = '\0'; + strncpy(input, buf, len+1); + return key; +} + +int ui__question_window(const char *title, const char *text, + const char *exit_msg, int delay_secs) +{ + int x, y; + int max_len = 0, nr_lines = 0; + const char *t; + + t = text; + while (1) { + const char *sep = strchr(t, '\n'); + int len; + + if (sep == NULL) + sep = strchr(t, '\0'); + len = sep - t; + if (max_len < len) + max_len = len; + ++nr_lines; + if (*sep == '\0') + break; + t = sep + 1; + } + + max_len += 2; + nr_lines += 4; + y = SLtt_Screen_Rows / 2 - nr_lines / 2, + x = SLtt_Screen_Cols / 2 - max_len / 2; + + SLsmg_set_color(0); + SLsmg_draw_box(y, x++, nr_lines, max_len); + if (title) { + SLsmg_gotorc(y, x + 1); + SLsmg_write_string((char *)title); + } + SLsmg_gotorc(++y, x); + nr_lines -= 2; + max_len -= 2; + SLsmg_write_wrapped_string((unsigned char *)text, y, x, + nr_lines, max_len, 1); + SLsmg_gotorc(y + nr_lines - 2, x); + SLsmg_write_nstring((char *)" ", max_len); + SLsmg_gotorc(y + nr_lines - 1, x); + SLsmg_write_nstring((char *)exit_msg, max_len); + SLsmg_refresh(); + return ui__getch(delay_secs); +} + +int ui__help_window(const char *text) +{ + return ui__question_window("Help", text, "Press any key...", 0); +} + +int ui__dialog_yesno(const char *msg) +{ + return ui__question_window(NULL, msg, "Enter: Yes, ESC: No", 0); +} + +static int __ui__warning(const char *title, const char *format, va_list args) +{ + char *s; + + if (vasprintf(&s, format, args) > 0) { + int key; + + pthread_mutex_lock(&ui__lock); + key = ui__question_window(title, s, "Press any key...", 0); + pthread_mutex_unlock(&ui__lock); + free(s); + return key; + } + + fprintf(stderr, "%s\n", title); + vfprintf(stderr, format, args); + return K_ESC; +} + +static int perf_tui__error(const char *format, va_list args) +{ + return __ui__warning("Error:", format, args); +} + +static int perf_tui__warning(const char *format, va_list args) +{ + return __ui__warning("Warning:", format, args); +} + +struct perf_error_ops perf_tui_eops = { + .error = perf_tui__error, + .warning = perf_tui__warning, +}; diff --git a/tools/perf/ui/util.c b/tools/perf/ui/util.c index ad4374a16bb0..4f989774c8c6 100644 --- a/tools/perf/ui/util.c +++ b/tools/perf/ui/util.c @@ -1,250 +1,85 @@ -#include "../util.h" -#include <signal.h> -#include <stdbool.h> -#include <string.h> -#include <sys/ttydefaults.h> - -#include "../cache.h" -#include "../debug.h" -#include "browser.h" -#include "keysyms.h" -#include "helpline.h" -#include "ui.h" #include "util.h" -#include "libslang.h" - -static void ui_browser__argv_write(struct ui_browser *browser, - void *entry, int row) -{ - char **arg = entry; - bool current_entry = ui_browser__is_current_entry(browser, row); - - ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED : - HE_COLORSET_NORMAL); - slsmg_write_nstring(*arg, browser->width); -} - -static int popup_menu__run(struct ui_browser *menu) -{ - int key; - - if (ui_browser__show(menu, " ", "ESC: exit, ENTER|->: Select option") < 0) - return -1; +#include "../debug.h" - while (1) { - key = ui_browser__run(menu, 0); - - switch (key) { - case K_RIGHT: - case K_ENTER: - key = menu->index; - break; - case K_LEFT: - case K_ESC: - case 'q': - case CTRL('c'): - key = -1; - break; - default: - continue; - } - - break; - } - - ui_browser__hide(menu); - return key; -} -int ui__popup_menu(int argc, char * const argv[]) +/* + * Default error logging functions + */ +static int perf_stdio__error(const char *format, va_list args) { - struct ui_browser menu = { - .entries = (void *)argv, - .refresh = ui_browser__argv_refresh, - .seek = ui_browser__argv_seek, - .write = ui_browser__argv_write, - .nr_entries = argc, - }; - - return popup_menu__run(&menu); + fprintf(stderr, "Error:\n"); + vfprintf(stderr, format, args); + return 0; } -int ui_browser__input_window(const char *title, const char *text, char *input, - const char *exit_msg, int delay_secs) +static int perf_stdio__warning(const char *format, va_list args) { - int x, y, len, key; - int max_len = 60, nr_lines = 0; - static char buf[50]; - const char *t; - - t = text; - while (1) { - const char *sep = strchr(t, '\n'); - - if (sep == NULL) - sep = strchr(t, '\0'); - len = sep - t; - if (max_len < len) - max_len = len; - ++nr_lines; - if (*sep == '\0') - break; - t = sep + 1; - } - - max_len += 2; - nr_lines += 8; - y = SLtt_Screen_Rows / 2 - nr_lines / 2; - x = SLtt_Screen_Cols / 2 - max_len / 2; - - SLsmg_set_color(0); - SLsmg_draw_box(y, x++, nr_lines, max_len); - if (title) { - SLsmg_gotorc(y, x + 1); - SLsmg_write_string((char *)title); - } - SLsmg_gotorc(++y, x); - nr_lines -= 7; - max_len -= 2; - SLsmg_write_wrapped_string((unsigned char *)text, y, x, - nr_lines, max_len, 1); - y += nr_lines; - len = 5; - while (len--) { - SLsmg_gotorc(y + len - 1, x); - SLsmg_write_nstring((char *)" ", max_len); - } - SLsmg_draw_box(y++, x + 1, 3, max_len - 2); - - SLsmg_gotorc(y + 3, x); - SLsmg_write_nstring((char *)exit_msg, max_len); - SLsmg_refresh(); - - x += 2; - len = 0; - key = ui__getch(delay_secs); - while (key != K_TIMER && key != K_ENTER && key != K_ESC) { - if (key == K_BKSPC) { - if (len == 0) - goto next_key; - SLsmg_gotorc(y, x + --len); - SLsmg_write_char(' '); - } else { - buf[len] = key; - SLsmg_gotorc(y, x + len++); - SLsmg_write_char(key); - } - SLsmg_refresh(); - - /* XXX more graceful overflow handling needed */ - if (len == sizeof(buf) - 1) { - ui_helpline__push("maximum size of symbol name reached!"); - key = K_ENTER; - break; - } -next_key: - key = ui__getch(delay_secs); - } - - buf[len] = '\0'; - strncpy(input, buf, len+1); - return key; + fprintf(stderr, "Warning:\n"); + vfprintf(stderr, format, args); + return 0; } -int ui__question_window(const char *title, const char *text, - const char *exit_msg, int delay_secs) +static struct perf_error_ops default_eops = { - int x, y; - int max_len = 0, nr_lines = 0; - const char *t; - - t = text; - while (1) { - const char *sep = strchr(t, '\n'); - int len; - - if (sep == NULL) - sep = strchr(t, '\0'); - len = sep - t; - if (max_len < len) - max_len = len; - ++nr_lines; - if (*sep == '\0') - break; - t = sep + 1; - } - - max_len += 2; - nr_lines += 4; - y = SLtt_Screen_Rows / 2 - nr_lines / 2, - x = SLtt_Screen_Cols / 2 - max_len / 2; - - SLsmg_set_color(0); - SLsmg_draw_box(y, x++, nr_lines, max_len); - if (title) { - SLsmg_gotorc(y, x + 1); - SLsmg_write_string((char *)title); - } - SLsmg_gotorc(++y, x); - nr_lines -= 2; - max_len -= 2; - SLsmg_write_wrapped_string((unsigned char *)text, y, x, - nr_lines, max_len, 1); - SLsmg_gotorc(y + nr_lines - 2, x); - SLsmg_write_nstring((char *)" ", max_len); - SLsmg_gotorc(y + nr_lines - 1, x); - SLsmg_write_nstring((char *)exit_msg, max_len); - SLsmg_refresh(); - return ui__getch(delay_secs); -} + .error = perf_stdio__error, + .warning = perf_stdio__warning, +}; -int ui__help_window(const char *text) -{ - return ui__question_window("Help", text, "Press any key...", 0); -} +static struct perf_error_ops *perf_eops = &default_eops; -int ui__dialog_yesno(const char *msg) -{ - return ui__question_window(NULL, msg, "Enter: Yes, ESC: No", 0); -} -int __ui__warning(const char *title, const char *format, va_list args) +int ui__error(const char *format, ...) { - char *s; - - if (use_browser > 0 && vasprintf(&s, format, args) > 0) { - int key; + int ret; + va_list args; - pthread_mutex_lock(&ui__lock); - key = ui__question_window(title, s, "Press any key...", 0); - pthread_mutex_unlock(&ui__lock); - free(s); - return key; - } + va_start(args, format); + ret = perf_eops->error(format, args); + va_end(args); - fprintf(stderr, "%s:\n", title); - vfprintf(stderr, format, args); - return K_ESC; + return ret; } int ui__warning(const char *format, ...) { - int key; + int ret; va_list args; va_start(args, format); - key = __ui__warning("Warning", format, args); + ret = perf_eops->warning(format, args); va_end(args); - return key; + + return ret; } -int ui__error(const char *format, ...) + +/** + * perf_error__register - Register error logging functions + * @eops: The pointer to error logging function struct + * + * Register UI-specific error logging functions. Before calling this, + * other logging functions should be unregistered, if any. + */ +int perf_error__register(struct perf_error_ops *eops) { - int key; - va_list args; + if (perf_eops != &default_eops) + return -1; - va_start(args, format); - key = __ui__warning("Error", format, args); - va_end(args); - return key; + perf_eops = eops; + return 0; +} + +/** + * perf_error__unregister - Unregister error logging functions + * @eops: The pointer to error logging function struct + * + * Unregister already registered error logging functions. + */ +int perf_error__unregister(struct perf_error_ops *eops) +{ + if (perf_eops != eops) + return -1; + + perf_eops = &default_eops; + return 0; } diff --git a/tools/perf/ui/util.h b/tools/perf/ui/util.h index 2d1738bd71c8..361f08c52d37 100644 --- a/tools/perf/ui/util.h +++ b/tools/perf/ui/util.h @@ -9,6 +9,13 @@ int ui__help_window(const char *text); int ui__dialog_yesno(const char *msg); int ui__question_window(const char *title, const char *text, const char *exit_msg, int delay_secs); -int __ui__warning(const char *title, const char *format, va_list args); + +struct perf_error_ops { + int (*error)(const char *format, va_list args); + int (*warning)(const char *format, va_list args); +}; + +int perf_error__register(struct perf_error_ops *eops); +int perf_error__unregister(struct perf_error_ops *eops); #endif /* _PERF_UI_UTIL_H_ */ diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index efb1fce259a4..4dfe0bb3c322 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -47,7 +47,7 @@ int dump_printf(const char *fmt, ...) return ret; } -#ifdef NO_NEWT_SUPPORT +#if defined(NO_NEWT_SUPPORT) && defined(NO_GTK2_SUPPORT) int ui__warning(const char *format, ...) { va_list args; diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 6bebe7f0a20c..015c91dbc096 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -12,8 +12,9 @@ int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); void trace_event(union perf_event *event); struct ui_progress; +struct perf_error_ops; -#ifdef NO_NEWT_SUPPORT +#if defined(NO_NEWT_SUPPORT) && defined(NO_GTK2_SUPPORT) static inline int ui_helpline__show_help(const char *format __used, va_list ap __used) { return 0; @@ -23,12 +24,28 @@ static inline void ui_progress__update(u64 curr __used, u64 total __used, const char *title __used) {} #define ui__error(format, arg...) ui__warning(format, ##arg) -#else + +static inline int +perf_error__register(struct perf_error_ops *eops __used) +{ + return 0; +} + +static inline int +perf_error__unregister(struct perf_error_ops *eops __used) +{ + return 0; +} + +#else /* NO_NEWT_SUPPORT && NO_GTK2_SUPPORT */ + extern char ui_helpline__last_msg[]; int ui_helpline__show_help(const char *format, va_list ap); #include "../ui/progress.h" int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2))); -#endif +#include "../ui/util.h" + +#endif /* NO_NEWT_SUPPORT && NO_GTK2_SUPPORT */ int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2))); int ui__error_paranoid(void); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 7400fb3fc50c..f74e9560350e 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -224,8 +224,8 @@ out_free_attrs: return err; } -static struct perf_evsel * - perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id) +struct perf_evsel * +perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id) { struct perf_evsel *evsel; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 989bee9624c2..40d4d3cdced0 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -73,6 +73,9 @@ int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist, #define perf_evlist__set_tracepoints_handlers_array(evlist, array) \ perf_evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array)) +struct perf_evsel * +perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id); + void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, int cpu, int thread, u64 id); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 9f6cebd798ee..e81771364867 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -15,7 +15,7 @@ #include "cpumap.h" #include "thread_map.h" #include "target.h" -#include "../../include/linux/perf_event.h" +#include "../../../include/linux/hw_breakpoint.h" #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) #define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0)) @@ -78,7 +78,7 @@ static const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = { "ref-cycles", }; -const char *__perf_evsel__hw_name(u64 config) +static const char *__perf_evsel__hw_name(u64 config) { if (config < PERF_COUNT_HW_MAX && perf_evsel__hw_names[config]) return perf_evsel__hw_names[config]; @@ -86,16 +86,15 @@ const char *__perf_evsel__hw_name(u64 config) return "unknown-hardware"; } -static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__add_modifiers(struct perf_evsel *evsel, char *bf, size_t size) { - int colon = 0; + int colon = 0, r = 0; struct perf_event_attr *attr = &evsel->attr; - int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(attr->config)); bool exclude_guest_default = false; #define MOD_PRINT(context, mod) do { \ if (!attr->exclude_##context) { \ - if (!colon) colon = r++; \ + if (!colon) colon = ++r; \ r += scnprintf(bf + r, size - r, "%c", mod); \ } } while(0) @@ -108,7 +107,7 @@ static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size) if (attr->precise_ip) { if (!colon) - colon = r++; + colon = ++r; r += scnprintf(bf + r, size - r, "%.*s", attr->precise_ip, "ppp"); exclude_guest_default = true; } @@ -119,39 +118,211 @@ static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size) } #undef MOD_PRINT if (colon) - bf[colon] = ':'; + bf[colon - 1] = ':'; return r; } -int perf_evsel__name(struct perf_evsel *evsel, char *bf, size_t size) +static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size) +{ + int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->attr.config)); + return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); +} + +static const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = { + "cpu-clock", + "task-clock", + "page-faults", + "context-switches", + "CPU-migrations", + "minor-faults", + "major-faults", + "alignment-faults", + "emulation-faults", +}; + +static const char *__perf_evsel__sw_name(u64 config) { - int ret; + if (config < PERF_COUNT_SW_MAX && perf_evsel__sw_names[config]) + return perf_evsel__sw_names[config]; + return "unknown-software"; +} + +static int perf_evsel__sw_name(struct perf_evsel *evsel, char *bf, size_t size) +{ + int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->attr.config)); + return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); +} + +static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type) +{ + int r; + + r = scnprintf(bf, size, "mem:0x%" PRIx64 ":", addr); + + if (type & HW_BREAKPOINT_R) + r += scnprintf(bf + r, size - r, "r"); + + if (type & HW_BREAKPOINT_W) + r += scnprintf(bf + r, size - r, "w"); + + if (type & HW_BREAKPOINT_X) + r += scnprintf(bf + r, size - r, "x"); + + return r; +} + +static int perf_evsel__bp_name(struct perf_evsel *evsel, char *bf, size_t size) +{ + struct perf_event_attr *attr = &evsel->attr; + int r = __perf_evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type); + return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); +} + +const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX] + [PERF_EVSEL__MAX_ALIASES] = { + { "L1-dcache", "l1-d", "l1d", "L1-data", }, + { "L1-icache", "l1-i", "l1i", "L1-instruction", }, + { "LLC", "L2", }, + { "dTLB", "d-tlb", "Data-TLB", }, + { "iTLB", "i-tlb", "Instruction-TLB", }, + { "branch", "branches", "bpu", "btb", "bpc", }, + { "node", }, +}; + +const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_EVSEL__MAX_ALIASES] = { + { "load", "loads", "read", }, + { "store", "stores", "write", }, + { "prefetch", "prefetches", "speculative-read", "speculative-load", }, +}; + +const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] + [PERF_EVSEL__MAX_ALIASES] = { + { "refs", "Reference", "ops", "access", }, + { "misses", "miss", }, +}; + +#define C(x) PERF_COUNT_HW_CACHE_##x +#define CACHE_READ (1 << C(OP_READ)) +#define CACHE_WRITE (1 << C(OP_WRITE)) +#define CACHE_PREFETCH (1 << C(OP_PREFETCH)) +#define COP(x) (1 << x) + +/* + * cache operartion stat + * L1I : Read and prefetch only + * ITLB and BPU : Read-only + */ +static unsigned long perf_evsel__hw_cache_stat[C(MAX)] = { + [C(L1D)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), + [C(L1I)] = (CACHE_READ | CACHE_PREFETCH), + [C(LL)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), + [C(DTLB)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), + [C(ITLB)] = (CACHE_READ), + [C(BPU)] = (CACHE_READ), + [C(NODE)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), +}; + +bool perf_evsel__is_cache_op_valid(u8 type, u8 op) +{ + if (perf_evsel__hw_cache_stat[type] & COP(op)) + return true; /* valid */ + else + return false; /* invalid */ +} + +int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, + char *bf, size_t size) +{ + if (result) { + return scnprintf(bf, size, "%s-%s-%s", perf_evsel__hw_cache[type][0], + perf_evsel__hw_cache_op[op][0], + perf_evsel__hw_cache_result[result][0]); + } + + return scnprintf(bf, size, "%s-%s", perf_evsel__hw_cache[type][0], + perf_evsel__hw_cache_op[op][1]); +} + +static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size) +{ + u8 op, result, type = (config >> 0) & 0xff; + const char *err = "unknown-ext-hardware-cache-type"; + + if (type > PERF_COUNT_HW_CACHE_MAX) + goto out_err; + + op = (config >> 8) & 0xff; + err = "unknown-ext-hardware-cache-op"; + if (op > PERF_COUNT_HW_CACHE_OP_MAX) + goto out_err; + + result = (config >> 16) & 0xff; + err = "unknown-ext-hardware-cache-result"; + if (result > PERF_COUNT_HW_CACHE_RESULT_MAX) + goto out_err; + + err = "invalid-cache"; + if (!perf_evsel__is_cache_op_valid(type, op)) + goto out_err; + + return __perf_evsel__hw_cache_type_op_res_name(type, op, result, bf, size); +out_err: + return scnprintf(bf, size, "%s", err); +} + +static int perf_evsel__hw_cache_name(struct perf_evsel *evsel, char *bf, size_t size) +{ + int ret = __perf_evsel__hw_cache_name(evsel->attr.config, bf, size); + return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); +} + +static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size) +{ + int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config); + return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); +} + +const char *perf_evsel__name(struct perf_evsel *evsel) +{ + char bf[128]; + + if (evsel->name) + return evsel->name; switch (evsel->attr.type) { case PERF_TYPE_RAW: - ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config); + perf_evsel__raw_name(evsel, bf, sizeof(bf)); break; case PERF_TYPE_HARDWARE: - ret = perf_evsel__hw_name(evsel, bf, size); + perf_evsel__hw_name(evsel, bf, sizeof(bf)); + break; + + case PERF_TYPE_HW_CACHE: + perf_evsel__hw_cache_name(evsel, bf, sizeof(bf)); + break; + + case PERF_TYPE_SOFTWARE: + perf_evsel__sw_name(evsel, bf, sizeof(bf)); break; + + case PERF_TYPE_TRACEPOINT: + scnprintf(bf, sizeof(bf), "%s", "unknown tracepoint"); + break; + + case PERF_TYPE_BREAKPOINT: + perf_evsel__bp_name(evsel, bf, sizeof(bf)); + break; + default: - /* - * FIXME - * - * This is the minimal perf_evsel__name so that we can - * reconstruct event names taking into account event modifiers. - * - * The old event_name uses it now for raw anr hw events, so that - * we don't drag all the parsing stuff into the python binding. - * - * On the next devel cycle the rest of the event naming will be - * brought here. - */ - return 0; - } - - return ret; + scnprintf(bf, sizeof(bf), "%s", "unknown attr type"); + break; + } + + evsel->name = strdup(bf); + + return evsel->name ?: "unknown"; } void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts, diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 4ba8b564e6f4..67cc5033d192 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -83,8 +83,19 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts, struct perf_evsel *first); -const char* __perf_evsel__hw_name(u64 config); -int perf_evsel__name(struct perf_evsel *evsel, char *bf, size_t size); +bool perf_evsel__is_cache_op_valid(u8 type, u8 op); + +#define PERF_EVSEL__MAX_ALIASES 8 + +extern const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX] + [PERF_EVSEL__MAX_ALIASES]; +extern const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_EVSEL__MAX_ALIASES]; +const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] + [PERF_EVSEL__MAX_ALIASES]; +int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, + char *bf, size_t size); +const char *perf_evsel__name(struct perf_evsel *evsel); int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index e909d43cf542..5a47aba46759 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -641,7 +641,7 @@ static int write_event_desc(int fd, struct perf_header *h __used, /* * write event string as passed on cmdline */ - ret = do_write_string(fd, event_name(attr)); + ret = do_write_string(fd, perf_evsel__name(attr)); if (ret < 0) return ret; /* @@ -1474,15 +1474,15 @@ out: static int process_tracing_data(struct perf_file_section *section __unused, struct perf_header *ph __unused, - int feat __unused, int fd) + int feat __unused, int fd, void *data) { - trace_report(fd, false); + trace_report(fd, data, false); return 0; } static int process_build_id(struct perf_file_section *section, struct perf_header *ph, - int feat __unused, int fd) + int feat __unused, int fd, void *data __used) { if (perf_header__read_build_ids(ph, fd, section->offset, section->size)) pr_debug("Failed to read buildids, continuing...\n"); @@ -1493,7 +1493,7 @@ struct feature_ops { int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist); void (*print)(struct perf_header *h, int fd, FILE *fp); int (*process)(struct perf_file_section *section, - struct perf_header *h, int feat, int fd); + struct perf_header *h, int feat, int fd, void *data); const char *name; bool full_only; }; @@ -1988,7 +1988,7 @@ int perf_file_header__read(struct perf_file_header *header, static int perf_file_section__process(struct perf_file_section *section, struct perf_header *ph, - int feat, int fd, void *data __used) + int feat, int fd, void *data) { if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { pr_debug("Failed to lseek to %" PRIu64 " offset for feature " @@ -2004,7 +2004,7 @@ static int perf_file_section__process(struct perf_file_section *section, if (!feat_ops[feat].process) return 0; - return feat_ops[feat].process(section, ph, feat, fd); + return feat_ops[feat].process(section, ph, feat, fd, data); } static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, @@ -2093,9 +2093,11 @@ static int read_attr(int fd, struct perf_header *ph, return ret <= 0 ? -1 : 0; } -static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel) +static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel, + struct pevent *pevent) { - struct event_format *event = trace_find_event(evsel->attr.config); + struct event_format *event = pevent_find_event(pevent, + evsel->attr.config); char bf[128]; if (event == NULL) @@ -2109,13 +2111,14 @@ static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel) return 0; } -static int perf_evlist__set_tracepoint_names(struct perf_evlist *evlist) +static int perf_evlist__set_tracepoint_names(struct perf_evlist *evlist, + struct pevent *pevent) { struct perf_evsel *pos; list_for_each_entry(pos, &evlist->entries, node) { if (pos->attr.type == PERF_TYPE_TRACEPOINT && - perf_evsel__set_tracepoint_name(pos)) + perf_evsel__set_tracepoint_name(pos, pevent)) return -1; } @@ -2198,12 +2201,12 @@ int perf_session__read_header(struct perf_session *session, int fd) event_count = f_header.event_types.size / sizeof(struct perf_trace_event_type); } - perf_header__process_sections(header, fd, NULL, + perf_header__process_sections(header, fd, &session->pevent, perf_file_section__process); lseek(fd, header->data_offset, SEEK_SET); - if (perf_evlist__set_tracepoint_names(session->evlist)) + if (perf_evlist__set_tracepoint_names(session->evlist, session->pevent)) goto out_delete_evlist; header->frozen = 1; @@ -2419,8 +2422,8 @@ int perf_event__process_tracing_data(union perf_event *event, lseek(session->fd, offset + sizeof(struct tracing_data_event), SEEK_SET); - size_read = trace_report(session->fd, session->repipe); - + size_read = trace_report(session->fd, &session->pevent, + session->repipe); padding = ALIGN(size_read, sizeof(u64)) - size_read; if (read(session->fd, buf, padding) < 0) diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 34bb556d6219..0b096c27a419 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -47,6 +47,7 @@ enum hist_column { HISTC_SYMBOL_TO, HISTC_DSO_FROM, HISTC_DSO_TO, + HISTC_SRCLINE, HISTC_NR_COLS, /* Last entry */ }; diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h index 1eb804fd3fbf..b6842c1d02a8 100644 --- a/tools/perf/util/include/linux/kernel.h +++ b/tools/perf/util/include/linux/kernel.h @@ -108,4 +108,14 @@ int eprintf(int level, #define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__) #define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__) +/* + * This looks more complex than it should be. But we need to + * get the type for the ~ right in round_down (it needs to be + * as wide as the result!), and we want to evaluate the macro + * arguments just once each. + */ +#define __round_mask(x, y) ((__typeof__(x))((y)-1)) +#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) +#define round_down(x, y) ((x) & ~__round_mask(x, y)) + #endif diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 35ae56864e4f..a1f4e3669142 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -669,25 +669,26 @@ struct machine *machines__find(struct rb_root *self, pid_t pid) struct machine *machines__findnew(struct rb_root *self, pid_t pid) { char path[PATH_MAX]; - const char *root_dir; + const char *root_dir = ""; struct machine *machine = machines__find(self, pid); - if (!machine || machine->pid != pid) { - if (pid == HOST_KERNEL_ID || pid == DEFAULT_GUEST_KERNEL_ID) - root_dir = ""; - else { - if (!symbol_conf.guestmount) - goto out; - sprintf(path, "%s/%d", symbol_conf.guestmount, pid); - if (access(path, R_OK)) { - pr_err("Can't access file %s\n", path); - goto out; - } - root_dir = path; + if (machine && (machine->pid == pid)) + goto out; + + if ((pid != HOST_KERNEL_ID) && + (pid != DEFAULT_GUEST_KERNEL_ID) && + (symbol_conf.guestmount)) { + sprintf(path, "%s/%d", symbol_conf.guestmount, pid); + if (access(path, R_OK)) { + pr_err("Can't access file %s\n", path); + machine = NULL; + goto out; } - machine = machines__add(self, pid, root_dir); + root_dir = path; } + machine = machines__add(self, pid, root_dir); + out: return machine; } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 81371bad4ef0..c14c665d9a25 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -157,7 +157,7 @@ void machine__exit(struct machine *self); void machine__delete(struct machine *self); int machine__resolve_callchain(struct machine *machine, - struct perf_evsel *evsel, struct thread *thread, + struct thread *thread, struct ip_callchain *chain, struct symbol **parent); int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, diff --git a/tools/perf/util/parse-events-test.c b/tools/perf/util/parse-events-test.c index 76b98e2a587d..1b997d2b89ce 100644 --- a/tools/perf/util/parse-events-test.c +++ b/tools/perf/util/parse-events-test.c @@ -181,6 +181,22 @@ static int test__checkevent_breakpoint_w(struct perf_evlist *evlist) return 0; } +static int test__checkevent_breakpoint_rw(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = list_entry(evlist->entries.next, + struct perf_evsel, node); + + TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries); + TEST_ASSERT_VAL("wrong type", + PERF_TYPE_BREAKPOINT == evsel->attr.type); + TEST_ASSERT_VAL("wrong config", 0 == evsel->attr.config); + TEST_ASSERT_VAL("wrong bp_type", + (HW_BREAKPOINT_R|HW_BREAKPOINT_W) == evsel->attr.bp_type); + TEST_ASSERT_VAL("wrong bp_len", + HW_BREAKPOINT_LEN_4 == evsel->attr.bp_len); + return 0; +} + static int test__checkevent_tracepoint_modifier(struct perf_evlist *evlist) { struct perf_evsel *evsel = list_entry(evlist->entries.next, @@ -309,6 +325,8 @@ static int test__checkevent_breakpoint_modifier(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong name", + !strcmp(perf_evsel__name(evsel), "mem:0x0:rw:u")); return test__checkevent_breakpoint(evlist); } @@ -322,6 +340,8 @@ static int test__checkevent_breakpoint_x_modifier(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong name", + !strcmp(perf_evsel__name(evsel), "mem:0x0:x:k")); return test__checkevent_breakpoint_x(evlist); } @@ -335,6 +355,8 @@ static int test__checkevent_breakpoint_r_modifier(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong name", + !strcmp(perf_evsel__name(evsel), "mem:0x0:r:hp")); return test__checkevent_breakpoint_r(evlist); } @@ -348,10 +370,27 @@ static int test__checkevent_breakpoint_w_modifier(struct perf_evlist *evlist) TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong name", + !strcmp(perf_evsel__name(evsel), "mem:0x0:w:up")); return test__checkevent_breakpoint_w(evlist); } +static int test__checkevent_breakpoint_rw_modifier(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = list_entry(evlist->entries.next, + struct perf_evsel, node); + + TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user); + TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel); + TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv); + TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip); + TEST_ASSERT_VAL("wrong name", + !strcmp(perf_evsel__name(evsel), "mem:0x0:rw:kp")); + + return test__checkevent_breakpoint_rw(evlist); +} + static int test__checkevent_pmu(struct perf_evlist *evlist) { @@ -413,19 +452,63 @@ static int test__checkevent_pmu_name(struct perf_evlist *evlist) { struct perf_evsel *evsel; - /* cpu/config=1,name=krava1/u */ + /* cpu/config=1,name=krava/u */ evsel = list_entry(evlist->entries.next, struct perf_evsel, node); TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config); - TEST_ASSERT_VAL("wrong name", !strcmp(evsel->name, "krava")); + TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "krava")); - /* cpu/config=2/" */ + /* cpu/config=2/u" */ evsel = list_entry(evsel->node.next, struct perf_evsel, node); TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries); TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type); TEST_ASSERT_VAL("wrong config", 2 == evsel->attr.config); - TEST_ASSERT_VAL("wrong name", !strcmp(evsel->name, "raw 0x2")); + TEST_ASSERT_VAL("wrong name", + !strcmp(perf_evsel__name(evsel), "raw 0x2:u")); + + return 0; +} + +static int test__checkterms_simple(struct list_head *terms) +{ + struct parse_events__term *term; + + /* config=10 */ + term = list_entry(terms->next, struct parse_events__term, list); + TEST_ASSERT_VAL("wrong type term", + term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG); + TEST_ASSERT_VAL("wrong type val", + term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); + TEST_ASSERT_VAL("wrong val", term->val.num == 10); + TEST_ASSERT_VAL("wrong config", !term->config); + + /* config1 */ + term = list_entry(term->list.next, struct parse_events__term, list); + TEST_ASSERT_VAL("wrong type term", + term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG1); + TEST_ASSERT_VAL("wrong type val", + term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); + TEST_ASSERT_VAL("wrong val", term->val.num == 1); + TEST_ASSERT_VAL("wrong config", !term->config); + + /* config2=3 */ + term = list_entry(term->list.next, struct parse_events__term, list); + TEST_ASSERT_VAL("wrong type term", + term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG2); + TEST_ASSERT_VAL("wrong type val", + term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); + TEST_ASSERT_VAL("wrong val", term->val.num == 3); + TEST_ASSERT_VAL("wrong config", !term->config); + + /* umask=1*/ + term = list_entry(term->list.next, struct parse_events__term, list); + TEST_ASSERT_VAL("wrong type term", + term->type_term == PARSE_EVENTS__TERM_TYPE_USER); + TEST_ASSERT_VAL("wrong type val", + term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); + TEST_ASSERT_VAL("wrong val", term->val.num == 1); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "umask")); return 0; } @@ -541,10 +624,16 @@ static struct test__event_st test__events[] = { .name = "instructions:H", .check = test__checkevent_exclude_guest_modifier, }, + [26] = { + .name = "mem:0:rw", + .check = test__checkevent_breakpoint_rw, + }, + [27] = { + .name = "mem:0:rw:kp", + .check = test__checkevent_breakpoint_rw_modifier, + }, }; -#define TEST__EVENTS_CNT (sizeof(test__events) / sizeof(struct test__event_st)) - static struct test__event_st test__events_pmu[] = { [0] = { .name = "cpu/config=10,config1,config2=3,period=1000/u", @@ -556,10 +645,23 @@ static struct test__event_st test__events_pmu[] = { }, }; -#define TEST__EVENTS_PMU_CNT (sizeof(test__events_pmu) / \ - sizeof(struct test__event_st)) +struct test__term { + const char *str; + __u32 type; + int (*check)(struct list_head *terms); +}; + +static struct test__term test__terms[] = { + [0] = { + .str = "config=10,config1,config2=3,umask=1", + .check = test__checkterms_simple, + }, +}; + +#define TEST__TERMS_CNT (sizeof(test__terms) / \ + sizeof(struct test__term)) -static int test(struct test__event_st *e) +static int test_event(struct test__event_st *e) { struct perf_evlist *evlist; int ret; @@ -590,7 +692,48 @@ static int test_events(struct test__event_st *events, unsigned cnt) struct test__event_st *e = &events[i]; pr_debug("running test %d '%s'\n", i, e->name); - ret = test(e); + ret = test_event(e); + if (ret) + break; + } + + return ret; +} + +static int test_term(struct test__term *t) +{ + struct list_head *terms; + int ret; + + terms = malloc(sizeof(*terms)); + if (!terms) + return -ENOMEM; + + INIT_LIST_HEAD(terms); + + ret = parse_events_terms(terms, t->str); + if (ret) { + pr_debug("failed to parse terms '%s', err %d\n", + t->str , ret); + return ret; + } + + ret = t->check(terms); + parse_events__free_terms(terms); + + return ret; +} + +static int test_terms(struct test__term *terms, unsigned cnt) +{ + int ret = 0; + unsigned i; + + for (i = 0; i < cnt; i++) { + struct test__term *t = &terms[i]; + + pr_debug("running test %d '%s'\n", i, t->str); + ret = test_term(t); if (ret) break; } @@ -617,9 +760,17 @@ int parse_events__test(void) { int ret; - ret = test_events(test__events, TEST__EVENTS_CNT); - if (!ret && test_pmu()) - ret = test_events(test__events_pmu, TEST__EVENTS_PMU_CNT); +#define TEST_EVENTS(tests) \ +do { \ + ret = test_events(tests, ARRAY_SIZE(tests)); \ + if (ret) \ + return ret; \ +} while (0) - return ret; + TEST_EVENTS(test__events); + + if (test_pmu()) + TEST_EVENTS(test__events_pmu); + + return test_terms(test__terms, ARRAY_SIZE(test__terms)); } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 05dbc8b3c767..1aa721d7c10f 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -11,14 +11,14 @@ #include "cache.h" #include "header.h" #include "debugfs.h" +#include "parse-events-bison.h" +#define YY_EXTRA_TYPE int #include "parse-events-flex.h" #include "pmu.h" #define MAX_NAME_LEN 100 struct event_symbol { - u8 type; - u64 config; const char *symbol; const char *alias; }; @@ -26,32 +26,88 @@ struct event_symbol { #ifdef PARSER_DEBUG extern int parse_events_debug; #endif -int parse_events_parse(struct list_head *list, int *idx); - -#define CHW(x) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_##x -#define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x - -static struct event_symbol event_symbols[] = { - { CHW(CPU_CYCLES), "cpu-cycles", "cycles" }, - { CHW(STALLED_CYCLES_FRONTEND), "stalled-cycles-frontend", "idle-cycles-frontend" }, - { CHW(STALLED_CYCLES_BACKEND), "stalled-cycles-backend", "idle-cycles-backend" }, - { CHW(INSTRUCTIONS), "instructions", "" }, - { CHW(CACHE_REFERENCES), "cache-references", "" }, - { CHW(CACHE_MISSES), "cache-misses", "" }, - { CHW(BRANCH_INSTRUCTIONS), "branch-instructions", "branches" }, - { CHW(BRANCH_MISSES), "branch-misses", "" }, - { CHW(BUS_CYCLES), "bus-cycles", "" }, - { CHW(REF_CPU_CYCLES), "ref-cycles", "" }, - - { CSW(CPU_CLOCK), "cpu-clock", "" }, - { CSW(TASK_CLOCK), "task-clock", "" }, - { CSW(PAGE_FAULTS), "page-faults", "faults" }, - { CSW(PAGE_FAULTS_MIN), "minor-faults", "" }, - { CSW(PAGE_FAULTS_MAJ), "major-faults", "" }, - { CSW(CONTEXT_SWITCHES), "context-switches", "cs" }, - { CSW(CPU_MIGRATIONS), "cpu-migrations", "migrations" }, - { CSW(ALIGNMENT_FAULTS), "alignment-faults", "" }, - { CSW(EMULATION_FAULTS), "emulation-faults", "" }, +int parse_events_parse(void *data, void *scanner); + +static struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { + [PERF_COUNT_HW_CPU_CYCLES] = { + .symbol = "cpu-cycles", + .alias = "cycles", + }, + [PERF_COUNT_HW_INSTRUCTIONS] = { + .symbol = "instructions", + .alias = "", + }, + [PERF_COUNT_HW_CACHE_REFERENCES] = { + .symbol = "cache-references", + .alias = "", + }, + [PERF_COUNT_HW_CACHE_MISSES] = { + .symbol = "cache-misses", + .alias = "", + }, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = { + .symbol = "branch-instructions", + .alias = "branches", + }, + [PERF_COUNT_HW_BRANCH_MISSES] = { + .symbol = "branch-misses", + .alias = "", + }, + [PERF_COUNT_HW_BUS_CYCLES] = { + .symbol = "bus-cycles", + .alias = "", + }, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = { + .symbol = "stalled-cycles-frontend", + .alias = "idle-cycles-frontend", + }, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = { + .symbol = "stalled-cycles-backend", + .alias = "idle-cycles-backend", + }, + [PERF_COUNT_HW_REF_CPU_CYCLES] = { + .symbol = "ref-cycles", + .alias = "", + }, +}; + +static struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { + [PERF_COUNT_SW_CPU_CLOCK] = { + .symbol = "cpu-clock", + .alias = "", + }, + [PERF_COUNT_SW_TASK_CLOCK] = { + .symbol = "task-clock", + .alias = "", + }, + [PERF_COUNT_SW_PAGE_FAULTS] = { + .symbol = "page-faults", + .alias = "faults", + }, + [PERF_COUNT_SW_CONTEXT_SWITCHES] = { + .symbol = "context-switches", + .alias = "cs", + }, + [PERF_COUNT_SW_CPU_MIGRATIONS] = { + .symbol = "cpu-migrations", + .alias = "migrations", + }, + [PERF_COUNT_SW_PAGE_FAULTS_MIN] = { + .symbol = "minor-faults", + .alias = "", + }, + [PERF_COUNT_SW_PAGE_FAULTS_MAJ] = { + .symbol = "major-faults", + .alias = "", + }, + [PERF_COUNT_SW_ALIGNMENT_FAULTS] = { + .symbol = "alignment-faults", + .alias = "", + }, + [PERF_COUNT_SW_EMULATION_FAULTS] = { + .symbol = "emulation-faults", + .alias = "", + }, }; #define __PERF_EVENT_FIELD(config, name) \ @@ -62,63 +118,6 @@ static struct event_symbol event_symbols[] = { #define PERF_EVENT_TYPE(config) __PERF_EVENT_FIELD(config, TYPE) #define PERF_EVENT_ID(config) __PERF_EVENT_FIELD(config, EVENT) -static const char *sw_event_names[PERF_COUNT_SW_MAX] = { - "cpu-clock", - "task-clock", - "page-faults", - "context-switches", - "CPU-migrations", - "minor-faults", - "major-faults", - "alignment-faults", - "emulation-faults", -}; - -#define MAX_ALIASES 8 - -static const char *hw_cache[PERF_COUNT_HW_CACHE_MAX][MAX_ALIASES] = { - { "L1-dcache", "l1-d", "l1d", "L1-data", }, - { "L1-icache", "l1-i", "l1i", "L1-instruction", }, - { "LLC", "L2", }, - { "dTLB", "d-tlb", "Data-TLB", }, - { "iTLB", "i-tlb", "Instruction-TLB", }, - { "branch", "branches", "bpu", "btb", "bpc", }, - { "node", }, -}; - -static const char *hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX][MAX_ALIASES] = { - { "load", "loads", "read", }, - { "store", "stores", "write", }, - { "prefetch", "prefetches", "speculative-read", "speculative-load", }, -}; - -static const char *hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] - [MAX_ALIASES] = { - { "refs", "Reference", "ops", "access", }, - { "misses", "miss", }, -}; - -#define C(x) PERF_COUNT_HW_CACHE_##x -#define CACHE_READ (1 << C(OP_READ)) -#define CACHE_WRITE (1 << C(OP_WRITE)) -#define CACHE_PREFETCH (1 << C(OP_PREFETCH)) -#define COP(x) (1 << x) - -/* - * cache operartion stat - * L1I : Read and prefetch only - * ITLB and BPU : Read-only - */ -static unsigned long hw_cache_stat[C(MAX)] = { - [C(L1D)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), - [C(L1I)] = (CACHE_READ | CACHE_PREFETCH), - [C(LL)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), - [C(DTLB)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), - [C(ITLB)] = (CACHE_READ), - [C(BPU)] = (CACHE_READ), - [C(NODE)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), -}; - #define for_each_subsystem(sys_dir, sys_dirent, sys_next) \ while (!readdir_r(sys_dir, &sys_dirent, &sys_next) && sys_next) \ if (sys_dirent.d_type == DT_DIR && \ @@ -218,48 +217,6 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) return NULL; } -#define TP_PATH_LEN (MAX_EVENT_LENGTH * 2 + 1) -static const char *tracepoint_id_to_name(u64 config) -{ - static char buf[TP_PATH_LEN]; - struct tracepoint_path *path; - - path = tracepoint_id_to_path(config); - if (path) { - snprintf(buf, TP_PATH_LEN, "%s:%s", path->system, path->name); - free(path->name); - free(path->system); - free(path); - } else - snprintf(buf, TP_PATH_LEN, "%s:%s", "unknown", "unknown"); - - return buf; -} - -static int is_cache_op_valid(u8 cache_type, u8 cache_op) -{ - if (hw_cache_stat[cache_type] & COP(cache_op)) - return 1; /* valid */ - else - return 0; /* invalid */ -} - -static char *event_cache_name(u8 cache_type, u8 cache_op, u8 cache_result) -{ - static char name[50]; - - if (cache_result) { - sprintf(name, "%s-%s-%s", hw_cache[cache_type][0], - hw_cache_op[cache_op][0], - hw_cache_result[cache_result][0]); - } else { - sprintf(name, "%s-%s", hw_cache[cache_type][0], - hw_cache_op[cache_op][1]); - } - - return name; -} - const char *event_type(int type) { switch (type) { @@ -282,76 +239,6 @@ const char *event_type(int type) return "unknown"; } -const char *event_name(struct perf_evsel *evsel) -{ - u64 config = evsel->attr.config; - int type = evsel->attr.type; - - if (type == PERF_TYPE_RAW || type == PERF_TYPE_HARDWARE) { - /* - * XXX minimal fix, see comment on perf_evsen__name, this static buffer - * will go away together with event_name in the next devel cycle. - */ - static char bf[128]; - perf_evsel__name(evsel, bf, sizeof(bf)); - return bf; - } - - if (evsel->name) - return evsel->name; - - return __event_name(type, config); -} - -const char *__event_name(int type, u64 config) -{ - static char buf[32]; - - if (type == PERF_TYPE_RAW) { - sprintf(buf, "raw 0x%" PRIx64, config); - return buf; - } - - switch (type) { - case PERF_TYPE_HARDWARE: - return __perf_evsel__hw_name(config); - - case PERF_TYPE_HW_CACHE: { - u8 cache_type, cache_op, cache_result; - - cache_type = (config >> 0) & 0xff; - if (cache_type > PERF_COUNT_HW_CACHE_MAX) - return "unknown-ext-hardware-cache-type"; - - cache_op = (config >> 8) & 0xff; - if (cache_op > PERF_COUNT_HW_CACHE_OP_MAX) - return "unknown-ext-hardware-cache-op"; - - cache_result = (config >> 16) & 0xff; - if (cache_result > PERF_COUNT_HW_CACHE_RESULT_MAX) - return "unknown-ext-hardware-cache-result"; - - if (!is_cache_op_valid(cache_type, cache_op)) - return "invalid-cache"; - - return event_cache_name(cache_type, cache_op, cache_result); - } - - case PERF_TYPE_SOFTWARE: - if (config < PERF_COUNT_SW_MAX && sw_event_names[config]) - return sw_event_names[config]; - return "unknown-software"; - - case PERF_TYPE_TRACEPOINT: - return tracepoint_id_to_name(config); - - default: - break; - } - - return "unknown"; -} - static int add_event(struct list_head **_list, int *idx, struct perf_event_attr *attr, char *name) { @@ -373,19 +260,20 @@ static int add_event(struct list_head **_list, int *idx, return -ENOMEM; } - evsel->name = strdup(name); + if (name) + evsel->name = strdup(name); list_add_tail(&evsel->node, list); *_list = list; return 0; } -static int parse_aliases(char *str, const char *names[][MAX_ALIASES], int size) +static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size) { int i, j; int n, longest = -1; for (i = 0; i < size; i++) { - for (j = 0; j < MAX_ALIASES && names[i][j]; j++) { + for (j = 0; j < PERF_EVSEL__MAX_ALIASES && names[i][j]; j++) { n = strlen(names[i][j]); if (n > longest && !strncasecmp(str, names[i][j], n)) longest = n; @@ -410,7 +298,7 @@ int parse_events_add_cache(struct list_head **list, int *idx, * No fallback - if we cannot get a clear cache type * then bail out: */ - cache_type = parse_aliases(type, hw_cache, + cache_type = parse_aliases(type, perf_evsel__hw_cache, PERF_COUNT_HW_CACHE_MAX); if (cache_type == -1) return -EINVAL; @@ -423,18 +311,18 @@ int parse_events_add_cache(struct list_head **list, int *idx, snprintf(name + n, MAX_NAME_LEN - n, "-%s\n", str); if (cache_op == -1) { - cache_op = parse_aliases(str, hw_cache_op, + cache_op = parse_aliases(str, perf_evsel__hw_cache_op, PERF_COUNT_HW_CACHE_OP_MAX); if (cache_op >= 0) { - if (!is_cache_op_valid(cache_type, cache_op)) + if (!perf_evsel__is_cache_op_valid(cache_type, cache_op)) return -EINVAL; continue; } } if (cache_result == -1) { - cache_result = parse_aliases(str, hw_cache_result, - PERF_COUNT_HW_CACHE_RESULT_MAX); + cache_result = parse_aliases(str, perf_evsel__hw_cache_result, + PERF_COUNT_HW_CACHE_RESULT_MAX); if (cache_result >= 0) continue; } @@ -549,21 +437,31 @@ parse_breakpoint_type(const char *type, struct perf_event_attr *attr) if (!type || !type[i]) break; +#define CHECK_SET_TYPE(bit) \ +do { \ + if (attr->bp_type & bit) \ + return -EINVAL; \ + else \ + attr->bp_type |= bit; \ +} while (0) + switch (type[i]) { case 'r': - attr->bp_type |= HW_BREAKPOINT_R; + CHECK_SET_TYPE(HW_BREAKPOINT_R); break; case 'w': - attr->bp_type |= HW_BREAKPOINT_W; + CHECK_SET_TYPE(HW_BREAKPOINT_W); break; case 'x': - attr->bp_type |= HW_BREAKPOINT_X; + CHECK_SET_TYPE(HW_BREAKPOINT_X); break; default: return -EINVAL; } } +#undef CHECK_SET_TYPE + if (!attr->bp_type) /* Default */ attr->bp_type = HW_BREAKPOINT_R | HW_BREAKPOINT_W; @@ -574,7 +472,6 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx, void *ptr, char *type) { struct perf_event_attr attr; - char name[MAX_NAME_LEN]; memset(&attr, 0, sizeof(attr)); attr.bp_addr = (unsigned long) ptr; @@ -593,8 +490,7 @@ int parse_events_add_breakpoint(struct list_head **list, int *idx, attr.type = PERF_TYPE_BREAKPOINT; - snprintf(name, MAX_NAME_LEN, "mem:%p:%s", ptr, type ? type : "rw"); - return add_event(list, idx, &attr, name); + return add_event(list, idx, &attr, NULL); } static int config_term(struct perf_event_attr *attr, @@ -666,8 +562,7 @@ int parse_events_add_numeric(struct list_head **list, int *idx, config_attr(&attr, head_config, 1)) return -EINVAL; - return add_event(list, idx, &attr, - (char *) __event_name(type, config)); + return add_event(list, idx, &attr, NULL); } static int parse_events__is_name_term(struct parse_events__term *term) @@ -675,8 +570,7 @@ static int parse_events__is_name_term(struct parse_events__term *term) return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME; } -static char *pmu_event_name(struct perf_event_attr *attr, - struct list_head *head_terms) +static char *pmu_event_name(struct list_head *head_terms) { struct parse_events__term *term; @@ -684,7 +578,7 @@ static char *pmu_event_name(struct perf_event_attr *attr, if (parse_events__is_name_term(term)) return term->val.str; - return (char *) __event_name(PERF_TYPE_RAW, attr->config); + return NULL; } int parse_events_add_pmu(struct list_head **list, int *idx, @@ -699,6 +593,9 @@ int parse_events_add_pmu(struct list_head **list, int *idx, memset(&attr, 0, sizeof(attr)); + if (perf_pmu__check_alias(pmu, head_config)) + return -EINVAL; + /* * Configure hardcoded terms first, no need to check * return value when called with fail == 0 ;) @@ -709,7 +606,7 @@ int parse_events_add_pmu(struct list_head **list, int *idx, return -EINVAL; return add_event(list, idx, &attr, - pmu_event_name(&attr, head_config)); + pmu_event_name(head_config)); } void parse_events_update_lists(struct list_head *list_event, @@ -787,27 +684,62 @@ int parse_events_modifier(struct list_head *list, char *str) return 0; } -int parse_events(struct perf_evlist *evlist, const char *str, int unset __used) +static int parse_events__scanner(const char *str, void *data, int start_token) { - LIST_HEAD(list); - LIST_HEAD(list_tmp); YY_BUFFER_STATE buffer; - int ret, idx = evlist->nr_entries; + void *scanner; + int ret; + + ret = parse_events_lex_init_extra(start_token, &scanner); + if (ret) + return ret; - buffer = parse_events__scan_string(str); + buffer = parse_events__scan_string(str, scanner); #ifdef PARSER_DEBUG parse_events_debug = 1; #endif - ret = parse_events_parse(&list, &idx); + ret = parse_events_parse(data, scanner); - parse_events__flush_buffer(buffer); - parse_events__delete_buffer(buffer); - parse_events_lex_destroy(); + parse_events__flush_buffer(buffer, scanner); + parse_events__delete_buffer(buffer, scanner); + parse_events_lex_destroy(scanner); + return ret; +} + +/* + * parse event config string, return a list of event terms. + */ +int parse_events_terms(struct list_head *terms, const char *str) +{ + struct parse_events_data__terms data = { + .terms = NULL, + }; + int ret; + ret = parse_events__scanner(str, &data, PE_START_TERMS); if (!ret) { - int entries = idx - evlist->nr_entries; - perf_evlist__splice_list_tail(evlist, &list, entries); + list_splice(data.terms, terms); + free(data.terms); + return 0; + } + + parse_events__free_terms(data.terms); + return ret; +} + +int parse_events(struct perf_evlist *evlist, const char *str, int unset __used) +{ + struct parse_events_data__events data = { + .list = LIST_HEAD_INIT(data.list), + .idx = evlist->nr_entries, + }; + int ret; + + ret = parse_events__scanner(str, &data, PE_START_EVENTS); + if (!ret) { + int entries = data.idx - evlist->nr_entries; + perf_evlist__splice_list_tail(evlist, &data.list, entries); return 0; } @@ -946,16 +878,13 @@ int is_valid_tracepoint(const char *event_string) return 0; } -void print_events_type(u8 type) +static void __print_events_type(u8 type, struct event_symbol *syms, + unsigned max) { - struct event_symbol *syms = event_symbols; - unsigned int i; char name[64]; + unsigned i; - for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) { - if (type != syms->type) - continue; - + for (i = 0; i < max ; i++, syms++) { if (strlen(syms->alias)) snprintf(name, sizeof(name), "%s OR %s", syms->symbol, syms->alias); @@ -967,19 +896,28 @@ void print_events_type(u8 type) } } +void print_events_type(u8 type) +{ + if (type == PERF_TYPE_SOFTWARE) + __print_events_type(type, event_symbols_sw, PERF_COUNT_SW_MAX); + else + __print_events_type(type, event_symbols_hw, PERF_COUNT_HW_MAX); +} + int print_hwcache_events(const char *event_glob) { unsigned int type, op, i, printed = 0; + char name[64]; for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { /* skip invalid cache type */ - if (!is_cache_op_valid(type, op)) + if (!perf_evsel__is_cache_op_valid(type, op)) continue; for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { - char *name = event_cache_name(type, op, i); - + __perf_evsel__hw_cache_type_op_res_name(type, op, i, + name, sizeof(name)); if (event_glob != NULL && !strglobmatch(name, event_glob)) continue; @@ -993,26 +931,13 @@ int print_hwcache_events(const char *event_glob) return printed; } -/* - * Print the help text for the event symbols: - */ -void print_events(const char *event_glob) +static void print_symbol_events(const char *event_glob, unsigned type, + struct event_symbol *syms, unsigned max) { - unsigned int i, type, prev_type = -1, printed = 0, ntypes_printed = 0; - struct event_symbol *syms = event_symbols; + unsigned i, printed = 0; char name[MAX_NAME_LEN]; - printf("\n"); - printf("List of pre-defined events (to be used in -e):\n"); - - for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) { - type = syms->type; - - if (type != prev_type && printed) { - printf("\n"); - printed = 0; - ntypes_printed++; - } + for (i = 0; i < max; i++, syms++) { if (event_glob != NULL && !(strglobmatch(syms->symbol, event_glob) || @@ -1023,17 +948,31 @@ void print_events(const char *event_glob) snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias); else strncpy(name, syms->symbol, MAX_NAME_LEN); - printf(" %-50s [%s]\n", name, - event_type_descriptors[type]); - prev_type = type; - ++printed; + printf(" %-50s [%s]\n", name, event_type_descriptors[type]); + + printed++; } - if (ntypes_printed) { - printed = 0; + if (printed) printf("\n"); - } +} + +/* + * Print the help text for the event symbols: + */ +void print_events(const char *event_glob) +{ + + printf("\n"); + printf("List of pre-defined events (to be used in -e):\n"); + + print_symbol_events(event_glob, PERF_TYPE_HARDWARE, + event_symbols_hw, PERF_COUNT_HW_MAX); + + print_symbol_events(event_glob, PERF_TYPE_SOFTWARE, + event_symbols_sw, PERF_COUNT_SW_MAX); + print_hwcache_events(event_glob); if (event_glob != NULL) @@ -1106,6 +1045,13 @@ int parse_events__term_str(struct parse_events__term **term, config, str, 0); } +int parse_events__term_clone(struct parse_events__term **new, + struct parse_events__term *term) +{ + return new_term(new, term->type_val, term->type_term, term->config, + term->val.str, term->val.num); +} + void parse_events__free_terms(struct list_head *terms) { struct parse_events__term *term, *h; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 8cac57ab4ee6..ee9c218a193c 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -26,13 +26,12 @@ extern struct tracepoint_path *tracepoint_id_to_path(u64 config); extern bool have_tracepoints(struct list_head *evlist); const char *event_type(int type); -const char *event_name(struct perf_evsel *event); -extern const char *__event_name(int type, u64 config); extern int parse_events_option(const struct option *opt, const char *str, int unset); extern int parse_events(struct perf_evlist *evlist, const char *str, int unset); +extern int parse_events_terms(struct list_head *terms, const char *str); extern int parse_filter(const struct option *opt, const char *str, int unset); #define EVENTS_HELP_MAX (128*1024) @@ -63,11 +62,22 @@ struct parse_events__term { struct list_head list; }; +struct parse_events_data__events { + struct list_head list; + int idx; +}; + +struct parse_events_data__terms { + struct list_head *terms; +}; + int parse_events__is_hardcoded_term(struct parse_events__term *term); int parse_events__term_num(struct parse_events__term **_term, int type_term, char *config, long num); int parse_events__term_str(struct parse_events__term **_term, int type_term, char *config, char *str); +int parse_events__term_clone(struct parse_events__term **new, + struct parse_events__term *term); void parse_events__free_terms(struct list_head *terms); int parse_events_modifier(struct list_head *list, char *str); int parse_events_add_tracepoint(struct list_head **list, int *idx, @@ -83,8 +93,7 @@ int parse_events_add_pmu(struct list_head **list, int *idx, char *pmu , struct list_head *head_config); void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all); -void parse_events_error(struct list_head *list_all, - int *idx, char const *msg); +void parse_events_error(void *data, void *scanner, char const *msg); int parse_events__test(void); void print_events(const char *event_glob); diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 618a8e788399..384ca74c6b22 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -1,4 +1,6 @@ +%option reentrant +%option bison-bridge %option prefix="parse_events_" %option stack @@ -8,7 +10,10 @@ #include "parse-events-bison.h" #include "parse-events.h" -static int __value(char *str, int base, int token) +char *parse_events_get_text(yyscan_t yyscanner); +YYSTYPE *parse_events_get_lval(yyscan_t yyscanner); + +static int __value(YYSTYPE *yylval, char *str, int base, int token) { long num; @@ -17,35 +22,48 @@ static int __value(char *str, int base, int token) if (errno) return PE_ERROR; - parse_events_lval.num = num; + yylval->num = num; return token; } -static int value(int base) +static int value(yyscan_t scanner, int base) { - return __value(parse_events_text, base, PE_VALUE); + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + + return __value(yylval, text, base, PE_VALUE); } -static int raw(void) +static int raw(yyscan_t scanner) { - return __value(parse_events_text + 1, 16, PE_RAW); + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + + return __value(yylval, text + 1, 16, PE_RAW); } -static int str(int token) +static int str(yyscan_t scanner, int token) { - parse_events_lval.str = strdup(parse_events_text); + YYSTYPE *yylval = parse_events_get_lval(scanner); + char *text = parse_events_get_text(scanner); + + yylval->str = strdup(text); return token; } -static int sym(int type, int config) +static int sym(yyscan_t scanner, int type, int config) { - parse_events_lval.num = (type << 16) + config; - return PE_VALUE_SYM; + YYSTYPE *yylval = parse_events_get_lval(scanner); + + yylval->num = (type << 16) + config; + return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW; } -static int term(int type) +static int term(yyscan_t scanner, int type) { - parse_events_lval.num = type; + YYSTYPE *yylval = parse_events_get_lval(scanner); + + yylval->num = type; return PE_TERM; } @@ -58,28 +76,41 @@ num_hex 0x[a-fA-F0-9]+ num_raw_hex [a-fA-F0-9]+ name [a-zA-Z_*?][a-zA-Z0-9_*?]* modifier_event [ukhpGH]{1,8} -modifier_bp [rwx] +modifier_bp [rwx]{1,3} %% -cpu-cycles|cycles { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); } -stalled-cycles-frontend|idle-cycles-frontend { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } -stalled-cycles-backend|idle-cycles-backend { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); } -instructions { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); } -cache-references { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); } -cache-misses { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); } -branch-instructions|branches { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); } -branch-misses { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); } -bus-cycles { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); } -ref-cycles { return sym(PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); } -cpu-clock { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); } -task-clock { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); } -page-faults|faults { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); } -minor-faults { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); } -major-faults { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); } -context-switches|cs { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); } -cpu-migrations|migrations { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); } -alignment-faults { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); } -emulation-faults { return sym(PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); } + +%{ + { + int start_token; + + start_token = (int) parse_events_get_extra(yyscanner); + if (start_token) { + parse_events_set_extra(NULL, yyscanner); + return start_token; + } + } +%} + +cpu-cycles|cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); } +stalled-cycles-frontend|idle-cycles-frontend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); } +stalled-cycles-backend|idle-cycles-backend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); } +instructions { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); } +cache-references { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); } +cache-misses { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); } +branch-instructions|branches { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); } +branch-misses { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); } +bus-cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); } +ref-cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); } +cpu-clock { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); } +task-clock { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); } +page-faults|faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); } +minor-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); } +major-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); } +context-switches|cs { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); } +cpu-migrations|migrations { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); } +alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); } +emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); } L1-dcache|l1-d|l1d|L1-data | L1-icache|l1-i|l1i|L1-instruction | @@ -87,14 +118,14 @@ LLC|L2 | dTLB|d-tlb|Data-TLB | iTLB|i-tlb|Instruction-TLB | branch|branches|bpu|btb|bpc | -node { return str(PE_NAME_CACHE_TYPE); } +node { return str(yyscanner, PE_NAME_CACHE_TYPE); } load|loads|read | store|stores|write | prefetch|prefetches | speculative-read|speculative-load | refs|Reference|ops|access | -misses|miss { return str(PE_NAME_CACHE_OP_RESULT); } +misses|miss { return str(yyscanner, PE_NAME_CACHE_OP_RESULT); } /* * These are event config hardcoded term names to be specified @@ -102,38 +133,39 @@ misses|miss { return str(PE_NAME_CACHE_OP_RESULT); } * so we can put them here directly. In case the we have a conflict * in future, this needs to go into '//' condition block. */ -config { return term(PARSE_EVENTS__TERM_TYPE_CONFIG); } -config1 { return term(PARSE_EVENTS__TERM_TYPE_CONFIG1); } -config2 { return term(PARSE_EVENTS__TERM_TYPE_CONFIG2); } -name { return term(PARSE_EVENTS__TERM_TYPE_NAME); } -period { return term(PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); } -branch_type { return term(PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); } +config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); } +config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); } +config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); } +name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); } +period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); } +branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); } mem: { BEGIN(mem); return PE_PREFIX_MEM; } -r{num_raw_hex} { return raw(); } -{num_dec} { return value(10); } -{num_hex} { return value(16); } +r{num_raw_hex} { return raw(yyscanner); } +{num_dec} { return value(yyscanner, 10); } +{num_hex} { return value(yyscanner, 16); } -{modifier_event} { return str(PE_MODIFIER_EVENT); } -{name} { return str(PE_NAME); } +{modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); } +{name} { return str(yyscanner, PE_NAME); } "/" { return '/'; } - { return '-'; } , { return ','; } : { return ':'; } = { return '='; } +\n { } <mem>{ -{modifier_bp} { return str(PE_MODIFIER_BP); } +{modifier_bp} { return str(yyscanner, PE_MODIFIER_BP); } : { return ':'; } -{num_dec} { return value(10); } -{num_hex} { return value(16); } +{num_dec} { return value(yyscanner, 10); } +{num_hex} { return value(yyscanner, 16); } /* * We need to separate 'mem:' scanner part, in order to get specific * modifier bits parsed out. Otherwise we would need to handle PE_NAME * and we'd need to parse it manually. During the escape from <mem> * state we need to put the escaping char back, so we dont miss it. */ -. { unput(*parse_events_text); BEGIN(INITIAL); } +. { unput(*yytext); BEGIN(INITIAL); } /* * We destroy the scanner after reaching EOF, * but anyway just to be sure get back to INIT state. @@ -143,7 +175,7 @@ r{num_raw_hex} { return raw(); } %% -int parse_events_wrap(void) +int parse_events_wrap(void *scanner __used) { return 1; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 362cc59332ae..2bc5fbff2b5d 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -1,7 +1,8 @@ - +%pure-parser %name-prefix "parse_events_" -%parse-param {struct list_head *list_all} -%parse-param {int *idx} +%parse-param {void *_data} +%parse-param {void *scanner} +%lex-param {void* scanner} %{ @@ -12,8 +13,9 @@ #include "types.h" #include "util.h" #include "parse-events.h" +#include "parse-events-bison.h" -extern int parse_events_lex (void); +extern int parse_events_lex (YYSTYPE* lvalp, void* scanner); #define ABORT_ON(val) \ do { \ @@ -23,14 +25,16 @@ do { \ %} -%token PE_VALUE PE_VALUE_SYM PE_RAW PE_TERM +%token PE_START_EVENTS PE_START_TERMS +%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM %token PE_NAME %token PE_MODIFIER_EVENT PE_MODIFIER_BP %token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT %token PE_PREFIX_MEM PE_PREFIX_RAW %token PE_ERROR %type <num> PE_VALUE -%type <num> PE_VALUE_SYM +%type <num> PE_VALUE_SYM_HW +%type <num> PE_VALUE_SYM_SW %type <num> PE_RAW %type <num> PE_TERM %type <str> PE_NAME @@ -38,6 +42,7 @@ do { \ %type <str> PE_NAME_CACHE_OP_RESULT %type <str> PE_MODIFIER_EVENT %type <str> PE_MODIFIER_BP +%type <num> value_sym %type <head> event_config %type <term> event_term %type <head> event_pmu @@ -58,24 +63,33 @@ do { \ } %% +start: +PE_START_EVENTS events +| +PE_START_TERMS terms + events: events ',' event | event event: event_def PE_MODIFIER_EVENT { + struct parse_events_data__events *data = _data; + /* * Apply modifier on all events added by single event definition * (there could be more events added for multiple tracepoint * definitions via '*?'. */ ABORT_ON(parse_events_modifier($1, $2)); - parse_events_update_lists($1, list_all); + parse_events_update_lists($1, &data->list); } | event_def { - parse_events_update_lists($1, list_all); + struct parse_events_data__events *data = _data; + + parse_events_update_lists($1, &data->list); } event_def: event_pmu | @@ -89,104 +103,131 @@ event_def: event_pmu | event_pmu: PE_NAME '/' event_config '/' { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_pmu(&list, idx, $1, $3)); + ABORT_ON(parse_events_add_pmu(&list, &data->idx, $1, $3)); parse_events__free_terms($3); $$ = list; } +value_sym: +PE_VALUE_SYM_HW +| +PE_VALUE_SYM_SW + event_legacy_symbol: -PE_VALUE_SYM '/' event_config '/' +value_sym '/' event_config '/' { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; int type = $1 >> 16; int config = $1 & 255; - ABORT_ON(parse_events_add_numeric(&list, idx, type, config, $3)); + ABORT_ON(parse_events_add_numeric(&list, &data->idx, + type, config, $3)); parse_events__free_terms($3); $$ = list; } | -PE_VALUE_SYM sep_slash_dc +value_sym sep_slash_dc { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; int type = $1 >> 16; int config = $1 & 255; - ABORT_ON(parse_events_add_numeric(&list, idx, type, config, NULL)); + ABORT_ON(parse_events_add_numeric(&list, &data->idx, + type, config, NULL)); $$ = list; } event_legacy_cache: PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_cache(&list, idx, $1, $3, $5)); + ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, $5)); $$ = list; } | PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_cache(&list, idx, $1, $3, NULL)); + ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, NULL)); $$ = list; } | PE_NAME_CACHE_TYPE { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_cache(&list, idx, $1, NULL, NULL)); + ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, NULL, NULL)); $$ = list; } event_legacy_mem: PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_breakpoint(&list, idx, (void *) $2, $4)); + ABORT_ON(parse_events_add_breakpoint(&list, &data->idx, + (void *) $2, $4)); $$ = list; } | PE_PREFIX_MEM PE_VALUE sep_dc { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_breakpoint(&list, idx, (void *) $2, NULL)); + ABORT_ON(parse_events_add_breakpoint(&list, &data->idx, + (void *) $2, NULL)); $$ = list; } event_legacy_tracepoint: PE_NAME ':' PE_NAME { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_tracepoint(&list, idx, $1, $3)); + ABORT_ON(parse_events_add_tracepoint(&list, &data->idx, $1, $3)); $$ = list; } event_legacy_numeric: PE_VALUE ':' PE_VALUE { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_numeric(&list, idx, $1, $3, NULL)); + ABORT_ON(parse_events_add_numeric(&list, &data->idx, $1, $3, NULL)); $$ = list; } event_legacy_raw: PE_RAW { + struct parse_events_data__events *data = _data; struct list_head *list = NULL; - ABORT_ON(parse_events_add_numeric(&list, idx, PERF_TYPE_RAW, $1, NULL)); + ABORT_ON(parse_events_add_numeric(&list, &data->idx, + PERF_TYPE_RAW, $1, NULL)); $$ = list; } +terms: event_config +{ + struct parse_events_data__terms *data = _data; + data->terms = $1; +} + event_config: event_config ',' event_term { @@ -267,8 +308,7 @@ sep_slash_dc: '/' | ':' | %% -void parse_events_error(struct list_head *list_all __used, - int *idx __used, +void parse_events_error(void *data __used, void *scanner __used, char const *msg __used) { } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index a119a5371699..67715a42cd6d 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -72,7 +72,7 @@ static int pmu_format(char *name, struct list_head *format) "%s/bus/event_source/devices/%s/format", sysfs, name); if (stat(path, &st) < 0) - return -1; + return 0; /* no error if format does not exist */ if (pmu_format_parse(path, format)) return -1; @@ -80,6 +80,114 @@ static int pmu_format(char *name, struct list_head *format) return 0; } +static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file) +{ + struct perf_pmu__alias *alias; + char buf[256]; + int ret; + + ret = fread(buf, 1, sizeof(buf), file); + if (ret == 0) + return -EINVAL; + buf[ret] = 0; + + alias = malloc(sizeof(*alias)); + if (!alias) + return -ENOMEM; + + INIT_LIST_HEAD(&alias->terms); + ret = parse_events_terms(&alias->terms, buf); + if (ret) { + free(alias); + return ret; + } + + alias->name = strdup(name); + list_add_tail(&alias->list, list); + return 0; +} + +/* + * Process all the sysfs attributes located under the directory + * specified in 'dir' parameter. + */ +static int pmu_aliases_parse(char *dir, struct list_head *head) +{ + struct dirent *evt_ent; + DIR *event_dir; + int ret = 0; + + event_dir = opendir(dir); + if (!event_dir) + return -EINVAL; + + while (!ret && (evt_ent = readdir(event_dir))) { + char path[PATH_MAX]; + char *name = evt_ent->d_name; + FILE *file; + + if (!strcmp(name, ".") || !strcmp(name, "..")) + continue; + + snprintf(path, PATH_MAX, "%s/%s", dir, name); + + ret = -EINVAL; + file = fopen(path, "r"); + if (!file) + break; + ret = perf_pmu__new_alias(head, name, file); + fclose(file); + } + + closedir(event_dir); + return ret; +} + +/* + * Reading the pmu event aliases definition, which should be located at: + * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes. + */ +static int pmu_aliases(char *name, struct list_head *head) +{ + struct stat st; + char path[PATH_MAX]; + const char *sysfs; + + sysfs = sysfs_find_mountpoint(); + if (!sysfs) + return -1; + + snprintf(path, PATH_MAX, + "%s/bus/event_source/devices/%s/events", sysfs, name); + + if (stat(path, &st) < 0) + return -1; + + if (pmu_aliases_parse(path, head)) + return -1; + + return 0; +} + +static int pmu_alias_terms(struct perf_pmu__alias *alias, + struct list_head *terms) +{ + struct parse_events__term *term, *clone; + LIST_HEAD(list); + int ret; + + list_for_each_entry(term, &alias->terms, list) { + ret = parse_events__term_clone(&clone, term); + if (ret) { + parse_events__free_terms(&list); + return ret; + } + list_add_tail(&clone->list, &list); + } + list_splice(&list, terms); + return 0; +} + /* * Reading/parsing the default pmu type value, which should be * located at: @@ -118,6 +226,7 @@ static struct perf_pmu *pmu_lookup(char *name) { struct perf_pmu *pmu; LIST_HEAD(format); + LIST_HEAD(aliases); __u32 type; /* @@ -135,10 +244,15 @@ static struct perf_pmu *pmu_lookup(char *name) if (!pmu) return NULL; + pmu_aliases(name, &aliases); + INIT_LIST_HEAD(&pmu->format); + INIT_LIST_HEAD(&pmu->aliases); list_splice(&format, &pmu->format); + list_splice(&aliases, &pmu->aliases); pmu->name = strdup(name); pmu->type = type; + list_add_tail(&pmu->list, &pmus); return pmu; } @@ -279,6 +393,59 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, return pmu_config(&pmu->format, attr, head_terms); } +static struct perf_pmu__alias *pmu_find_alias(struct perf_pmu *pmu, + struct parse_events__term *term) +{ + struct perf_pmu__alias *alias; + char *name; + + if (parse_events__is_hardcoded_term(term)) + return NULL; + + if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) { + if (term->val.num != 1) + return NULL; + if (pmu_find_format(&pmu->format, term->config)) + return NULL; + name = term->config; + } else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) { + if (strcasecmp(term->config, "event")) + return NULL; + name = term->val.str; + } else { + return NULL; + } + + list_for_each_entry(alias, &pmu->aliases, list) { + if (!strcasecmp(alias->name, name)) + return alias; + } + return NULL; +} + +/* + * Find alias in the terms list and replace it with the terms + * defined for the alias + */ +int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms) +{ + struct parse_events__term *term, *h; + struct perf_pmu__alias *alias; + int ret; + + list_for_each_entry_safe(term, h, head_terms, list) { + alias = pmu_find_alias(pmu, term); + if (!alias) + continue; + ret = pmu_alias_terms(alias, &term->list); + if (ret) + return ret; + list_del(&term->list); + free(term); + } + return 0; +} + int perf_pmu__new_format(struct list_head *list, char *name, int config, unsigned long *bits) { diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 68c0db965e1f..535f2c5258ab 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -19,17 +19,26 @@ struct perf_pmu__format { struct list_head list; }; +struct perf_pmu__alias { + char *name; + struct list_head terms; + struct list_head list; +}; + struct perf_pmu { char *name; __u32 type; struct list_head format; + struct list_head aliases; struct list_head list; }; struct perf_pmu *perf_pmu__find(char *name); int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, struct list_head *head_terms); - +int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms); +struct list_head *perf_pmu__alias(struct perf_pmu *pmu, + struct list_head *head_terms); int perf_pmu_wrap(void); void perf_pmu_error(struct list_head *list, char *name, char const *msg); diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 4c1b3d72a1d2..02dfa19a467f 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -209,6 +209,10 @@ static void define_event_symbols(struct event_format *event, define_symbolic_values(args->symbol.symbols, ev_name, cur_field_name); break; + case PRINT_HEX: + define_event_symbols(event, ev_name, args->hex.field); + define_event_symbols(event, ev_name, args->hex.size); + break; case PRINT_BSTRING: case PRINT_DYNAMIC_ARRAY: case PRINT_STRING: @@ -233,7 +237,8 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->next); } -static inline struct event_format *find_cache_event(int type) +static inline +struct event_format *find_cache_event(struct pevent *pevent, int type) { static char ev_name[256]; struct event_format *event; @@ -241,7 +246,7 @@ static inline struct event_format *find_cache_event(int type) if (events[type]) return events[type]; - events[type] = event = trace_find_event(type); + events[type] = event = pevent_find_event(pevent, type); if (!event) return NULL; @@ -252,7 +257,8 @@ static inline struct event_format *find_cache_event(int type) return event; } -static void perl_process_tracepoint(union perf_event *pevent __unused, +static void perl_process_tracepoint(union perf_event *perf_event __unused, + struct pevent *pevent, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine __unused, @@ -275,13 +281,13 @@ static void perl_process_tracepoint(union perf_event *pevent __unused, if (evsel->attr.type != PERF_TYPE_TRACEPOINT) return; - type = trace_parse_common_type(data); + type = trace_parse_common_type(pevent, data); - event = find_cache_event(type); + event = find_cache_event(pevent, type); if (!event) die("ug! no event found for type %d", type); - pid = trace_parse_common_pid(data); + pid = trace_parse_common_pid(pevent, data); sprintf(handler, "%s::%s", event->system, event->name); @@ -314,7 +320,8 @@ static void perl_process_tracepoint(union perf_event *pevent __unused, offset = field->offset; XPUSHs(sv_2mortal(newSVpv((char *)data + offset, 0))); } else { /* FIELD_IS_NUMERIC */ - val = read_size(data + field->offset, field->size); + val = read_size(pevent, data + field->offset, + field->size); if (field->flags & FIELD_IS_SIGNED) { XPUSHs(sv_2mortal(newSViv(val))); } else { @@ -368,14 +375,15 @@ static void perl_process_event_generic(union perf_event *pevent __unused, LEAVE; } -static void perl_process_event(union perf_event *pevent, +static void perl_process_event(union perf_event *event, + struct pevent *pevent, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine, struct thread *thread) { - perl_process_tracepoint(pevent, sample, evsel, machine, thread); - perl_process_event_generic(pevent, sample, evsel, machine, thread); + perl_process_tracepoint(event, pevent, sample, evsel, machine, thread); + perl_process_event_generic(event, sample, evsel, machine, thread); } static void run_start_sub(void) @@ -448,7 +456,7 @@ static int perl_stop_script(void) return 0; } -static int perl_generate_script(const char *outfile) +static int perl_generate_script(struct pevent *pevent, const char *outfile) { struct event_format *event = NULL; struct format_field *f; @@ -495,7 +503,7 @@ static int perl_generate_script(const char *outfile) fprintf(ofp, "sub trace_begin\n{\n\t# optional\n}\n\n"); fprintf(ofp, "sub trace_end\n{\n\t# optional\n}\n\n"); - while ((event = trace_find_next_event(event))) { + while ((event = trace_find_next_event(pevent, event))) { fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name); fprintf(ofp, "\tmy ("); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index acb9795286c4..ce4d1b0c3862 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -166,6 +166,10 @@ static void define_event_symbols(struct event_format *event, define_values(PRINT_SYMBOL, args->symbol.symbols, ev_name, cur_field_name); break; + case PRINT_HEX: + define_event_symbols(event, ev_name, args->hex.field); + define_event_symbols(event, ev_name, args->hex.size); + break; case PRINT_STRING: break; case PRINT_TYPE: @@ -190,7 +194,8 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->next); } -static inline struct event_format *find_cache_event(int type) +static inline +struct event_format *find_cache_event(struct pevent *pevent, int type) { static char ev_name[256]; struct event_format *event; @@ -198,7 +203,7 @@ static inline struct event_format *find_cache_event(int type) if (events[type]) return events[type]; - events[type] = event = trace_find_event(type); + events[type] = event = pevent_find_event(pevent, type); if (!event) return NULL; @@ -209,7 +214,8 @@ static inline struct event_format *find_cache_event(int type) return event; } -static void python_process_event(union perf_event *pevent __unused, +static void python_process_event(union perf_event *perf_event __unused, + struct pevent *pevent, struct perf_sample *sample, struct perf_evsel *evsel __unused, struct machine *machine __unused, @@ -233,13 +239,13 @@ static void python_process_event(union perf_event *pevent __unused, if (!t) Py_FatalError("couldn't create Python tuple"); - type = trace_parse_common_type(data); + type = trace_parse_common_type(pevent, data); - event = find_cache_event(type); + event = find_cache_event(pevent, type); if (!event) die("ug! no event found for type %d", type); - pid = trace_parse_common_pid(data); + pid = trace_parse_common_pid(pevent, data); sprintf(handler_name, "%s__%s", event->system, event->name); @@ -284,7 +290,8 @@ static void python_process_event(union perf_event *pevent __unused, offset = field->offset; obj = PyString_FromString((char *)data + offset); } else { /* FIELD_IS_NUMERIC */ - val = read_size(data + field->offset, field->size); + val = read_size(pevent, data + field->offset, + field->size); if (field->flags & FIELD_IS_SIGNED) { if ((long long)val >= LONG_MIN && (long long)val <= LONG_MAX) @@ -438,7 +445,7 @@ out: return err; } -static int python_generate_script(const char *outfile) +static int python_generate_script(struct pevent *pevent, const char *outfile) { struct event_format *event = NULL; struct format_field *f; @@ -487,7 +494,7 @@ static int python_generate_script(const char *outfile) fprintf(ofp, "def trace_end():\n"); fprintf(ofp, "\tprint \"in trace_end\"\n\n"); - while ((event = trace_find_next_event(event))) { + while ((event = trace_find_next_event(pevent, event))) { fprintf(ofp, "def %s__%s(", event->system, event->name); fprintf(ofp, "event_name, "); fprintf(ofp, "context, "); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index c3e399bcf18d..8e485592ca20 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -14,6 +14,7 @@ #include "sort.h" #include "util.h" #include "cpumap.h" +#include "event-parse.h" static int perf_session__open(struct perf_session *self, bool force) { @@ -289,7 +290,6 @@ struct branch_info *machine__resolve_bstack(struct machine *self, } int machine__resolve_callchain(struct machine *self, - struct perf_evsel *evsel __used, struct thread *thread, struct ip_callchain *chain, struct symbol **parent) @@ -926,7 +926,7 @@ static struct machine * else pid = event->ip.pid; - return perf_session__find_machine(session, pid); + return perf_session__findnew_machine(session, pid); } return perf_session__find_host_machine(session); @@ -1449,7 +1449,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) ret += hists__fprintf_nr_events(&session->hists, fp); list_for_each_entry(pos, &session->evlist->entries, node) { - ret += fprintf(fp, "%s stats:\n", event_name(pos)); + ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos)); ret += hists__fprintf_nr_events(&pos->hists, fp); } @@ -1490,8 +1490,8 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, } void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, - struct machine *machine, struct perf_evsel *evsel, - int print_sym, int print_dso, int print_symoffset) + struct machine *machine, int print_sym, + int print_dso, int print_symoffset) { struct addr_location al; struct callchain_cursor_node *node; @@ -1505,7 +1505,7 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, if (symbol_conf.use_callchain && sample->callchain) { - if (machine__resolve_callchain(machine, evsel, al.thread, + if (machine__resolve_callchain(machine, al.thread, sample->callchain, NULL) != 0) { if (verbose) error("Failed to resolve callchain. Skipping\n"); @@ -1611,3 +1611,58 @@ void perf_session__fprintf_info(struct perf_session *session, FILE *fp, perf_header__fprintf_info(session, fp, full); fprintf(fp, "# ========\n#\n"); } + + +int __perf_session__set_tracepoints_handlers(struct perf_session *session, + const struct perf_evsel_str_handler *assocs, + size_t nr_assocs) +{ + struct perf_evlist *evlist = session->evlist; + struct event_format *format; + struct perf_evsel *evsel; + char *tracepoint, *name; + size_t i; + int err; + + for (i = 0; i < nr_assocs; i++) { + err = -ENOMEM; + tracepoint = strdup(assocs[i].name); + if (tracepoint == NULL) + goto out; + + err = -ENOENT; + name = strchr(tracepoint, ':'); + if (name == NULL) + goto out_free; + + *name++ = '\0'; + format = pevent_find_event_by_name(session->pevent, + tracepoint, name); + if (format == NULL) { + /* + * Adding a handler for an event not in the session, + * just ignore it. + */ + goto next; + } + + evsel = perf_evlist__find_tracepoint_by_id(evlist, format->id); + if (evsel == NULL) + goto next; + + err = -EEXIST; + if (evsel->handler.func != NULL) + goto out_free; + evsel->handler.func = assocs[i].handler; +next: + free(tracepoint); + } + + err = 0; +out: + return err; + +out_free: + free(tracepoint); + goto out; +} diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 0c702e3f0a36..7c435bde6eb0 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -33,6 +33,7 @@ struct perf_session { struct machine host_machine; struct rb_root machines; struct perf_evlist *evlist; + struct pevent *pevent; /* * FIXME: Need to split this up further, we need global * stats + per event stats. 'perf diff' also needs @@ -151,11 +152,20 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, unsigned int type); void perf_event__print_ip(union perf_event *event, struct perf_sample *sample, - struct machine *machine, struct perf_evsel *evsel, - int print_sym, int print_dso, int print_symoffset); + struct machine *machine, int print_sym, + int print_dso, int print_symoffset); int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap); void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full); + +struct perf_evsel_str_handler; + +int __perf_session__set_tracepoints_handlers(struct perf_session *session, + const struct perf_evsel_str_handler *assocs, + size_t nr_assocs); + +#define perf_session__set_tracepoints_handlers(session, array) \ + __perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array)) #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index a27237430c5f..0f5a0a496bc4 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -241,6 +241,54 @@ struct sort_entry sort_sym = { .se_width_idx = HISTC_SYMBOL, }; +/* --sort srcline */ + +static int64_t +sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return (int64_t)(right->ip - left->ip); +} + +static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width __used) +{ + FILE *fp; + char cmd[PATH_MAX + 2], *path = self->srcline, *nl; + size_t line_len; + + if (path != NULL) + goto out_path; + + snprintf(cmd, sizeof(cmd), "addr2line -e %s %016" PRIx64, + self->ms.map->dso->long_name, self->ip); + fp = popen(cmd, "r"); + if (!fp) + goto out_ip; + + if (getline(&path, &line_len, fp) < 0 || !line_len) + goto out_ip; + fclose(fp); + self->srcline = strdup(path); + if (self->srcline == NULL) + goto out_ip; + + nl = strchr(self->srcline, '\n'); + if (nl != NULL) + *nl = '\0'; + path = self->srcline; +out_path: + return repsep_snprintf(bf, size, "%s", path); +out_ip: + return repsep_snprintf(bf, size, "%-#*llx", BITS_PER_LONG / 4, self->ip); +} + +struct sort_entry sort_srcline = { + .se_header = "Source:Line", + .se_cmp = sort__srcline_cmp, + .se_snprintf = hist_entry__srcline_snprintf, + .se_width_idx = HISTC_SRCLINE, +}; + /* --sort parent */ static int64_t @@ -439,6 +487,7 @@ static struct sort_dimension sort_dimensions[] = { DIM(SORT_PARENT, "parent", sort_parent), DIM(SORT_CPU, "cpu", sort_cpu), DIM(SORT_MISPREDICT, "mispredict", sort_mispredict), + DIM(SORT_SRCLINE, "srcline", sort_srcline), }; int sort_dimension__add(const char *tok) diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 472aa5a63a58..e724b26acd51 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -71,6 +71,7 @@ struct hist_entry { char level; bool used; u8 filtered; + char *srcline; struct symbol *parent; union { unsigned long position; @@ -93,6 +94,7 @@ enum sort_type { SORT_SYM_FROM, SORT_SYM_TO, SORT_MISPREDICT, + SORT_SRCLINE, }; /* diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index d5836382ff2c..199bc4d8905d 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -313,3 +313,25 @@ int strtailcmp(const char *s1, const char *s2) return 0; } +/** + * rtrim - Removes trailing whitespace from @s. + * @s: The string to be stripped. + * + * Note that the first trailing whitespace is replaced with a %NUL-terminator + * in the given string @s. Returns @s. + */ +char *rtrim(char *s) +{ + size_t size = strlen(s); + char *end; + + if (!size) + return s; + + end = s + size - 1; + while (end >= s && isspace(*end)) + end--; + *(end + 1) = '\0'; + + return s; +} diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 3e2e5ea0f03f..50958bbeb26a 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1478,14 +1478,31 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size) goto out; } - sec = elf_section_by_name(elf, &ehdr, &shdr, - ".note.gnu.build-id", NULL); - if (sec == NULL) { + /* + * Check following sections for notes: + * '.note.gnu.build-id' + * '.notes' + * '.note' (VDSO specific) + */ + do { + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".note.gnu.build-id", NULL); + if (sec) + break; + sec = elf_section_by_name(elf, &ehdr, &shdr, ".notes", NULL); - if (sec == NULL) - goto out; - } + if (sec) + break; + + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".note", NULL); + if (sec) + break; + + return err; + + } while (0); data = elf_getdata(sec, NULL); if (data == NULL) @@ -1590,11 +1607,62 @@ out: return err; } +static int filename__read_debuglink(const char *filename, + char *debuglink, size_t size) +{ + int fd, err = -1; + Elf *elf; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + Elf_Data *data; + Elf_Scn *sec; + Elf_Kind ek; + + fd = open(filename, O_RDONLY); + if (fd < 0) + goto out; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) { + pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename); + goto out_close; + } + + ek = elf_kind(elf); + if (ek != ELF_K_ELF) + goto out_close; + + if (gelf_getehdr(elf, &ehdr) == NULL) { + pr_err("%s: cannot get elf header.\n", __func__); + goto out_close; + } + + sec = elf_section_by_name(elf, &ehdr, &shdr, + ".gnu_debuglink", NULL); + if (sec == NULL) + goto out_close; + + data = elf_getdata(sec, NULL); + if (data == NULL) + goto out_close; + + /* the start of this section is a zero-terminated string */ + strncpy(debuglink, data->d_buf, size); + + elf_end(elf); + +out_close: + close(fd); +out: + return err; +} + char dso__symtab_origin(const struct dso *dso) { static const char origin[] = { [SYMTAB__KALLSYMS] = 'k', [SYMTAB__JAVA_JIT] = 'j', + [SYMTAB__DEBUGLINK] = 'l', [SYMTAB__BUILD_ID_CACHE] = 'B', [SYMTAB__FEDORA_DEBUGINFO] = 'f', [SYMTAB__UBUNTU_DEBUGINFO] = 'u', @@ -1662,10 +1730,22 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) */ want_symtab = 1; restart: - for (dso->symtab_type = SYMTAB__BUILD_ID_CACHE; + for (dso->symtab_type = SYMTAB__DEBUGLINK; dso->symtab_type != SYMTAB__NOT_FOUND; dso->symtab_type++) { switch (dso->symtab_type) { + case SYMTAB__DEBUGLINK: { + char *debuglink; + strncpy(name, dso->long_name, size); + debuglink = name + dso->long_name_len; + while (debuglink != name && *debuglink != '/') + debuglink--; + if (*debuglink == '/') + debuglink++; + filename__read_debuglink(dso->long_name, debuglink, + size - (debuglink - name)); + } + break; case SYMTAB__BUILD_ID_CACHE: /* skip the locally configured cache if a symfs is given */ if (symbol_conf.symfs[0] || diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index af0752b1aca1..a884b99017f0 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -257,6 +257,7 @@ enum symtab_type { SYMTAB__KALLSYMS = 0, SYMTAB__GUEST_KALLSYMS, SYMTAB__JAVA_JIT, + SYMTAB__DEBUGLINK, SYMTAB__BUILD_ID_CACHE, SYMTAB__FEDORA_DEBUGINFO, SYMTAB__UBUNTU_DEBUGINFO, diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index abe0e8e95068..7eeebcee291c 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -65,7 +65,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) top->freq ? "Hz" : ""); } - ret += SNPRINTF(bf + ret, size - ret, "%s", event_name(top->sym_evsel)); + ret += SNPRINTF(bf + ret, size - ret, "%s", perf_evsel__name(top->sym_evsel)); ret += SNPRINTF(bf + ret, size - ret, "], "); diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index df2fddbf0cd2..0715c843c2e7 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -32,29 +32,25 @@ int header_page_size_size; int header_page_ts_size; int header_page_data_offset; -struct pevent *perf_pevent; -static struct pevent *pevent; - bool latency_format; -int read_trace_init(int file_bigendian, int host_bigendian) +struct pevent *read_trace_init(int file_bigendian, int host_bigendian) { - if (pevent) - return 0; - - perf_pevent = pevent_alloc(); - pevent = perf_pevent; + struct pevent *pevent = pevent_alloc(); - pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT); - pevent_set_file_bigendian(pevent, file_bigendian); - pevent_set_host_bigendian(pevent, host_bigendian); + if (pevent != NULL) { + pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT); + pevent_set_file_bigendian(pevent, file_bigendian); + pevent_set_host_bigendian(pevent, host_bigendian); + } - return 0; + return pevent; } static int get_common_field(struct scripting_context *context, int *offset, int *size, const char *type) { + struct pevent *pevent = context->pevent; struct event_format *event; struct format_field *field; @@ -150,7 +146,7 @@ void *raw_field_ptr(struct event_format *event, const char *name, void *data) return data + field->offset; } -int trace_parse_common_type(void *data) +int trace_parse_common_type(struct pevent *pevent, void *data) { struct pevent_record record; @@ -158,7 +154,7 @@ int trace_parse_common_type(void *data) return pevent_data_type(pevent, &record); } -int trace_parse_common_pid(void *data) +int trace_parse_common_pid(struct pevent *pevent, void *data) { struct pevent_record record; @@ -166,27 +162,21 @@ int trace_parse_common_pid(void *data) return pevent_data_pid(pevent, &record); } -unsigned long long read_size(void *ptr, int size) +unsigned long long read_size(struct pevent *pevent, void *ptr, int size) { return pevent_read_number(pevent, ptr, size); } -struct event_format *trace_find_event(int type) -{ - return pevent_find_event(pevent, type); -} - - -void print_trace_event(int cpu, void *data, int size) +void print_trace_event(struct pevent *pevent, int cpu, void *data, int size) { struct event_format *event; struct pevent_record record; struct trace_seq s; int type; - type = trace_parse_common_type(data); + type = trace_parse_common_type(pevent, data); - event = trace_find_event(type); + event = pevent_find_event(pevent, type); if (!event) { warning("ug! no event found for type %d", type); return; @@ -198,13 +188,12 @@ void print_trace_event(int cpu, void *data, int size) record.data = data; trace_seq_init(&s); - pevent_print_event(pevent, &s, &record); + pevent_event_info(&s, event, &record); trace_seq_do_printf(&s); - printf("\n"); } -void print_event(int cpu, void *data, int size, unsigned long long nsecs, - char *comm) +void print_event(struct pevent *pevent, int cpu, void *data, int size, + unsigned long long nsecs, char *comm) { struct pevent_record record; struct trace_seq s; @@ -227,7 +216,8 @@ void print_event(int cpu, void *data, int size, unsigned long long nsecs, printf("\n"); } -void parse_proc_kallsyms(char *file, unsigned int size __unused) +void parse_proc_kallsyms(struct pevent *pevent, + char *file, unsigned int size __unused) { unsigned long long addr; char *func; @@ -258,7 +248,8 @@ void parse_proc_kallsyms(char *file, unsigned int size __unused) } } -void parse_ftrace_printk(char *file, unsigned int size __unused) +void parse_ftrace_printk(struct pevent *pevent, + char *file, unsigned int size __unused) { unsigned long long addr; char *printk; @@ -282,17 +273,19 @@ void parse_ftrace_printk(char *file, unsigned int size __unused) } } -int parse_ftrace_file(char *buf, unsigned long size) +int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size) { return pevent_parse_event(pevent, buf, size, "ftrace"); } -int parse_event_file(char *buf, unsigned long size, char *sys) +int parse_event_file(struct pevent *pevent, + char *buf, unsigned long size, char *sys) { return pevent_parse_event(pevent, buf, size, sys); } -struct event_format *trace_find_next_event(struct event_format *event) +struct event_format *trace_find_next_event(struct pevent *pevent, + struct event_format *event) { static int idx; diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index f097e0dd6c5c..719ed74a8565 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -114,20 +114,20 @@ static void skip(int size) }; } -static unsigned int read4(void) +static unsigned int read4(struct pevent *pevent) { unsigned int data; read_or_die(&data, 4); - return __data2host4(perf_pevent, data); + return __data2host4(pevent, data); } -static unsigned long long read8(void) +static unsigned long long read8(struct pevent *pevent) { unsigned long long data; read_or_die(&data, 8); - return __data2host8(perf_pevent, data); + return __data2host8(pevent, data); } static char *read_string(void) @@ -168,12 +168,12 @@ static char *read_string(void) return str; } -static void read_proc_kallsyms(void) +static void read_proc_kallsyms(struct pevent *pevent) { unsigned int size; char *buf; - size = read4(); + size = read4(pevent); if (!size) return; @@ -181,29 +181,29 @@ static void read_proc_kallsyms(void) read_or_die(buf, size); buf[size] = '\0'; - parse_proc_kallsyms(buf, size); + parse_proc_kallsyms(pevent, buf, size); free(buf); } -static void read_ftrace_printk(void) +static void read_ftrace_printk(struct pevent *pevent) { unsigned int size; char *buf; - size = read4(); + size = read4(pevent); if (!size) return; buf = malloc_or_die(size); read_or_die(buf, size); - parse_ftrace_printk(buf, size); + parse_ftrace_printk(pevent, buf, size); free(buf); } -static void read_header_files(void) +static void read_header_files(struct pevent *pevent) { unsigned long long size; char *header_event; @@ -214,7 +214,7 @@ static void read_header_files(void) if (memcmp(buf, "header_page", 12) != 0) die("did not read header page"); - size = read8(); + size = read8(pevent); skip(size); /* @@ -227,47 +227,48 @@ static void read_header_files(void) if (memcmp(buf, "header_event", 13) != 0) die("did not read header event"); - size = read8(); + size = read8(pevent); header_event = malloc_or_die(size); read_or_die(header_event, size); free(header_event); } -static void read_ftrace_file(unsigned long long size) +static void read_ftrace_file(struct pevent *pevent, unsigned long long size) { char *buf; buf = malloc_or_die(size); read_or_die(buf, size); - parse_ftrace_file(buf, size); + parse_ftrace_file(pevent, buf, size); free(buf); } -static void read_event_file(char *sys, unsigned long long size) +static void read_event_file(struct pevent *pevent, char *sys, + unsigned long long size) { char *buf; buf = malloc_or_die(size); read_or_die(buf, size); - parse_event_file(buf, size, sys); + parse_event_file(pevent, buf, size, sys); free(buf); } -static void read_ftrace_files(void) +static void read_ftrace_files(struct pevent *pevent) { unsigned long long size; int count; int i; - count = read4(); + count = read4(pevent); for (i = 0; i < count; i++) { - size = read8(); - read_ftrace_file(size); + size = read8(pevent); + read_ftrace_file(pevent, size); } } -static void read_event_files(void) +static void read_event_files(struct pevent *pevent) { unsigned long long size; char *sys; @@ -275,15 +276,15 @@ static void read_event_files(void) int count; int i,x; - systems = read4(); + systems = read4(pevent); for (i = 0; i < systems; i++) { sys = read_string(); - count = read4(); + count = read4(pevent); for (x=0; x < count; x++) { - size = read8(); - read_event_file(sys, size); + size = read8(pevent); + read_event_file(pevent, sys, size); } } } @@ -377,7 +378,7 @@ static int calc_index(void *ptr, int cpu) return (unsigned long)ptr - (unsigned long)cpu_data[cpu].page; } -struct pevent_record *trace_peek_data(int cpu) +struct pevent_record *trace_peek_data(struct pevent *pevent, int cpu) { struct pevent_record *data; void *page = cpu_data[cpu].page; @@ -399,15 +400,15 @@ struct pevent_record *trace_peek_data(int cpu) /* FIXME: handle header page */ if (header_page_ts_size != 8) die("expected a long long type for timestamp"); - cpu_data[cpu].timestamp = data2host8(perf_pevent, ptr); + cpu_data[cpu].timestamp = data2host8(pevent, ptr); ptr += 8; switch (header_page_size_size) { case 4: - cpu_data[cpu].page_size = data2host4(perf_pevent, ptr); + cpu_data[cpu].page_size = data2host4(pevent, ptr); ptr += 4; break; case 8: - cpu_data[cpu].page_size = data2host8(perf_pevent, ptr); + cpu_data[cpu].page_size = data2host8(pevent, ptr); ptr += 8; break; default: @@ -421,10 +422,10 @@ read_again: if (idx >= cpu_data[cpu].page_size) { get_next_page(cpu); - return trace_peek_data(cpu); + return trace_peek_data(pevent, cpu); } - type_len_ts = data2host4(perf_pevent, ptr); + type_len_ts = data2host4(pevent, ptr); ptr += 4; type_len = type_len4host(type_len_ts); @@ -434,14 +435,14 @@ read_again: case RINGBUF_TYPE_PADDING: if (!delta) die("error, hit unexpected end of page"); - length = data2host4(perf_pevent, ptr); + length = data2host4(pevent, ptr); ptr += 4; length *= 4; ptr += length; goto read_again; case RINGBUF_TYPE_TIME_EXTEND: - extend = data2host4(perf_pevent, ptr); + extend = data2host4(pevent, ptr); ptr += 4; extend <<= TS_SHIFT; extend += delta; @@ -452,7 +453,7 @@ read_again: ptr += 12; break; case 0: - length = data2host4(perf_pevent, ptr); + length = data2host4(pevent, ptr); ptr += 4; die("here! length=%d", length); break; @@ -477,17 +478,17 @@ read_again: return data; } -struct pevent_record *trace_read_data(int cpu) +struct pevent_record *trace_read_data(struct pevent *pevent, int cpu) { struct pevent_record *data; - data = trace_peek_data(cpu); + data = trace_peek_data(pevent, cpu); cpu_data[cpu].next = NULL; return data; } -ssize_t trace_report(int fd, bool __repipe) +ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe) { char buf[BUFSIZ]; char test[] = { 23, 8, 68 }; @@ -519,30 +520,32 @@ ssize_t trace_report(int fd, bool __repipe) file_bigendian = buf[0]; host_bigendian = bigendian(); - read_trace_init(file_bigendian, host_bigendian); + *ppevent = read_trace_init(file_bigendian, host_bigendian); + if (*ppevent == NULL) + die("read_trace_init failed"); read_or_die(buf, 1); long_size = buf[0]; - page_size = read4(); + page_size = read4(*ppevent); - read_header_files(); + read_header_files(*ppevent); - read_ftrace_files(); - read_event_files(); - read_proc_kallsyms(); - read_ftrace_printk(); + read_ftrace_files(*ppevent); + read_event_files(*ppevent); + read_proc_kallsyms(*ppevent); + read_ftrace_printk(*ppevent); size = calc_data_size - 1; calc_data_size = 0; repipe = false; if (show_funcs) { - pevent_print_funcs(perf_pevent); + pevent_print_funcs(*ppevent); return size; } if (show_printk) { - pevent_print_printk(perf_pevent); + pevent_print_printk(*ppevent); return size; } diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 18ae6c1831d3..474aa7a7df43 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -36,6 +36,7 @@ static int stop_script_unsupported(void) } static void process_event_unsupported(union perf_event *event __unused, + struct pevent *pevent __unused, struct perf_sample *sample __unused, struct perf_evsel *evsel __unused, struct machine *machine __unused, @@ -61,7 +62,8 @@ static int python_start_script_unsupported(const char *script __unused, return -1; } -static int python_generate_script_unsupported(const char *outfile __unused) +static int python_generate_script_unsupported(struct pevent *pevent __unused, + const char *outfile __unused) { print_python_unsupported_msg(); @@ -122,7 +124,8 @@ static int perl_start_script_unsupported(const char *script __unused, return -1; } -static int perl_generate_script_unsupported(const char *outfile __unused) +static int perl_generate_script_unsupported(struct pevent *pevent __unused, + const char *outfile __unused) { print_perl_unsupported_msg(); diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index 639852ac1117..8fef1d6687b7 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -8,6 +8,7 @@ struct machine; struct perf_sample; union perf_event; +struct perf_tool; struct thread; extern int header_page_size_size; @@ -29,35 +30,36 @@ enum { int bigendian(void); -int read_trace_init(int file_bigendian, int host_bigendian); -void print_trace_event(int cpu, void *data, int size); +struct pevent *read_trace_init(int file_bigendian, int host_bigendian); +void print_trace_event(struct pevent *pevent, int cpu, void *data, int size); -void print_event(int cpu, void *data, int size, unsigned long long nsecs, - char *comm); +void print_event(struct pevent *pevent, int cpu, void *data, int size, + unsigned long long nsecs, char *comm); -int parse_ftrace_file(char *buf, unsigned long size); -int parse_event_file(char *buf, unsigned long size, char *sys); +int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size); +int parse_event_file(struct pevent *pevent, + char *buf, unsigned long size, char *sys); -struct pevent_record *trace_peek_data(int cpu); -struct event_format *trace_find_event(int type); +struct pevent_record *trace_peek_data(struct pevent *pevent, int cpu); unsigned long long raw_field_value(struct event_format *event, const char *name, void *data); void *raw_field_ptr(struct event_format *event, const char *name, void *data); -void parse_proc_kallsyms(char *file, unsigned int size __unused); -void parse_ftrace_printk(char *file, unsigned int size __unused); +void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size); +void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size); -ssize_t trace_report(int fd, bool repipe); +ssize_t trace_report(int fd, struct pevent **pevent, bool repipe); -int trace_parse_common_type(void *data); -int trace_parse_common_pid(void *data); +int trace_parse_common_type(struct pevent *pevent, void *data); +int trace_parse_common_pid(struct pevent *pevent, void *data); -struct event_format *trace_find_next_event(struct event_format *event); -unsigned long long read_size(void *ptr, int size); +struct event_format *trace_find_next_event(struct pevent *pevent, + struct event_format *event); +unsigned long long read_size(struct pevent *pevent, void *ptr, int size); unsigned long long eval_flag(const char *flag); -struct pevent_record *trace_read_data(int cpu); +struct pevent_record *trace_read_data(struct pevent *pevent, int cpu); int read_tracing_data(int fd, struct list_head *pattrs); struct tracing_data { @@ -77,11 +79,12 @@ struct scripting_ops { int (*start_script) (const char *script, int argc, const char **argv); int (*stop_script) (void); void (*process_event) (union perf_event *event, + struct pevent *pevent, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine, struct thread *thread); - int (*generate_script) (const char *outfile); + int (*generate_script) (struct pevent *pevent, const char *outfile); }; int script_spec_register(const char *spec, struct scripting_ops *ops); @@ -90,6 +93,7 @@ void setup_perl_scripting(void); void setup_python_scripting(void); struct scripting_context { + struct pevent *pevent; void *event_data; }; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 2daaedb83d84..b13c7331eaf8 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -264,4 +264,6 @@ bool is_power_of_2(unsigned long n) size_t hex_width(u64 v); +char *rtrim(char *s); + #endif diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c index b1e091ae2f37..23a41a9f8db9 100644 --- a/virt/kvm/assigned-dev.c +++ b/virt/kvm/assigned-dev.c @@ -334,6 +334,11 @@ static int assigned_device_enable_host_intx(struct kvm *kvm, } #ifdef __KVM_HAVE_MSI +static irqreturn_t kvm_assigned_dev_msi(int irq, void *dev_id) +{ + return IRQ_WAKE_THREAD; +} + static int assigned_device_enable_host_msi(struct kvm *kvm, struct kvm_assigned_dev_kernel *dev) { @@ -346,7 +351,7 @@ static int assigned_device_enable_host_msi(struct kvm *kvm, } dev->host_irq = dev->dev->irq; - if (request_threaded_irq(dev->host_irq, NULL, + if (request_threaded_irq(dev->host_irq, kvm_assigned_dev_msi, kvm_assigned_dev_thread_msi, 0, dev->irq_name, dev)) { pci_disable_msi(dev->dev); @@ -358,6 +363,11 @@ static int assigned_device_enable_host_msi(struct kvm *kvm, #endif #ifdef __KVM_HAVE_MSIX +static irqreturn_t kvm_assigned_dev_msix(int irq, void *dev_id) +{ + return IRQ_WAKE_THREAD; +} + static int assigned_device_enable_host_msix(struct kvm *kvm, struct kvm_assigned_dev_kernel *dev) { @@ -374,7 +384,8 @@ static int assigned_device_enable_host_msix(struct kvm *kvm, for (i = 0; i < dev->entries_nr; i++) { r = request_threaded_irq(dev->host_msix_entries[i].vector, - NULL, kvm_assigned_dev_thread_msix, + kvm_assigned_dev_msix, + kvm_assigned_dev_thread_msix, 0, dev->irq_name, dev); if (r) goto err; diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index f59c1e8de7a2..7d7e2aaffece 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -198,7 +198,7 @@ static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd, } static int -kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi) +kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) { struct kvm_irq_routing_table *irq_rt; struct _irqfd *irqfd, *tmp; @@ -212,12 +212,12 @@ kvm_irqfd_assign(struct kvm *kvm, int fd, int gsi) return -ENOMEM; irqfd->kvm = kvm; - irqfd->gsi = gsi; + irqfd->gsi = args->gsi; INIT_LIST_HEAD(&irqfd->list); INIT_WORK(&irqfd->inject, irqfd_inject); INIT_WORK(&irqfd->shutdown, irqfd_shutdown); - file = eventfd_fget(fd); + file = eventfd_fget(args->fd); if (IS_ERR(file)) { ret = PTR_ERR(file); goto fail; @@ -298,19 +298,19 @@ kvm_eventfd_init(struct kvm *kvm) * shutdown any irqfd's that match fd+gsi */ static int -kvm_irqfd_deassign(struct kvm *kvm, int fd, int gsi) +kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args) { struct _irqfd *irqfd, *tmp; struct eventfd_ctx *eventfd; - eventfd = eventfd_ctx_fdget(fd); + eventfd = eventfd_ctx_fdget(args->fd); if (IS_ERR(eventfd)) return PTR_ERR(eventfd); spin_lock_irq(&kvm->irqfds.lock); list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list) { - if (irqfd->eventfd == eventfd && irqfd->gsi == gsi) { + if (irqfd->eventfd == eventfd && irqfd->gsi == args->gsi) { /* * This rcu_assign_pointer is needed for when * another thread calls kvm_irq_routing_update before @@ -338,12 +338,15 @@ kvm_irqfd_deassign(struct kvm *kvm, int fd, int gsi) } int -kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags) +kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) { - if (flags & KVM_IRQFD_FLAG_DEASSIGN) - return kvm_irqfd_deassign(kvm, fd, gsi); + if (args->flags & ~KVM_IRQFD_FLAG_DEASSIGN) + return -EINVAL; + + if (args->flags & KVM_IRQFD_FLAG_DEASSIGN) + return kvm_irqfd_deassign(kvm, args); - return kvm_irqfd_assign(kvm, fd, gsi); + return kvm_irqfd_assign(kvm, args); } /* diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 7e140683ff14..44ee7124b16d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2047,7 +2047,7 @@ static long kvm_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&data, argp, sizeof data)) goto out; - r = kvm_irqfd(kvm, data.fd, data.gsi, data.flags); + r = kvm_irqfd(kvm, &data); break; } case KVM_IOEVENTFD: { @@ -2845,6 +2845,7 @@ void kvm_exit(void) kvm_arch_hardware_unsetup(); kvm_arch_exit(); free_cpumask_var(cpus_hardware_enabled); + __free_page(fault_page); __free_page(hwpoison_page); __free_page(bad_page); } |