From 0e74dc2646db04b644faa8ea10ff4f408d55cf90 Mon Sep 17 00:00:00 2001 From: Henrique de Moraes Holschuh Date: Mon, 21 Jul 2008 09:15:51 -0300 Subject: ACPI: thinkpad-acpi: add bluetooth and WWAN rfkill support Add a read/write rfkill interface to the bluetooth radio switch on the bluetooth submodule, and one for the wireless wan radio switch to the wan submodule. Since rfkill does care for when a switch changes state, use WLSW notifications to also check if the WWAN or Bluetooth switches did not change state (due to them being slaves of WLSW in firmware/hardware, but that reality not being always properly exported by the thinkpad firmware). Signed-off-by: Henrique de Moraes Holschuh Cc: Ivo van Doorn Cc: John W. Linville --- Documentation/laptops/thinkpad-acpi.txt | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'Documentation') diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt index 64b3f146e4b0..1c1c0217ebd1 100644 --- a/Documentation/laptops/thinkpad-acpi.txt +++ b/Documentation/laptops/thinkpad-acpi.txt @@ -621,7 +621,8 @@ Bluetooth --------- procfs: /proc/acpi/ibm/bluetooth -sysfs device attribute: bluetooth_enable +sysfs device attribute: bluetooth_enable (deprecated) +sysfs rfkill class: switch "tpacpi_bluetooth_sw" This feature shows the presence and current state of a ThinkPad Bluetooth device in the internal ThinkPad CDC slot. @@ -643,8 +644,12 @@ Sysfs notes: 0: disables Bluetooth / Bluetooth is disabled 1: enables Bluetooth / Bluetooth is enabled. - Note: this interface will be probably be superseded by the - generic rfkill class, so it is NOT to be considered stable yet. + Note: this interface has been superseded by the generic rfkill + class. It has been deprecated, and it will be removed in year + 2010. + + rfkill controller switch "tpacpi_bluetooth_sw": refer to + Documentation/rfkill.txt for details. Video output control -- /proc/acpi/ibm/video -------------------------------------------- @@ -1374,7 +1379,8 @@ EXPERIMENTAL: WAN ----------------- procfs: /proc/acpi/ibm/wan -sysfs device attribute: wwan_enable +sysfs device attribute: wwan_enable (deprecated) +sysfs rfkill class: switch "tpacpi_wwan_sw" This feature is marked EXPERIMENTAL because the implementation directly accesses hardware registers and may not work as expected. USE @@ -1404,8 +1410,12 @@ Sysfs notes: 0: disables WWAN card / WWAN card is disabled 1: enables WWAN card / WWAN card is enabled. - Note: this interface will be probably be superseded by the - generic rfkill class, so it is NOT to be considered stable yet. + Note: this interface has been superseded by the generic rfkill + class. It has been deprecated, and it will be removed in year + 2010. + + rfkill controller switch "tpacpi_wwan_sw": refer to + Documentation/rfkill.txt for details. Multiple Commands, Module Parameters ------------------------------------ -- cgit v1.2.3 From 490673dc98adfc7de1703cc88508902bd10f446b Mon Sep 17 00:00:00 2001 From: Henrique de Moraes Holschuh Date: Mon, 21 Jul 2008 09:15:51 -0300 Subject: ACPI: thinkpad-acpi: bump up version to 0.21 rfkill support deserves a new version checkpoint... Signed-off-by: Henrique de Moraes Holschuh --- Documentation/laptops/thinkpad-acpi.txt | 4 ++-- drivers/misc/thinkpad_acpi.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'Documentation') diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt index 1c1c0217ebd1..02dc748b76c4 100644 --- a/Documentation/laptops/thinkpad-acpi.txt +++ b/Documentation/laptops/thinkpad-acpi.txt @@ -1,7 +1,7 @@ ThinkPad ACPI Extras Driver - Version 0.20 - April 09th, 2008 + Version 0.21 + May 29th, 2008 Borislav Deianov Henrique de Moraes Holschuh diff --git a/drivers/misc/thinkpad_acpi.c b/drivers/misc/thinkpad_acpi.c index dc8d00a45701..3eb01afe4306 100644 --- a/drivers/misc/thinkpad_acpi.c +++ b/drivers/misc/thinkpad_acpi.c @@ -21,7 +21,7 @@ * 02110-1301, USA. */ -#define TPACPI_VERSION "0.20" +#define TPACPI_VERSION "0.21" #define TPACPI_SYSFS_VERSION 0x020200 /* -- cgit v1.2.3 From 79c28acb2b7d66ca48d23e1c8b5e9e043aa634f8 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Fri, 11 Jul 2008 16:17:57 -0600 Subject: of-bindings: Add binding documentation for SPI busses and devices Add documentation about how to describe SPI busses in the device tree. Signed-off-by: Grant Likely Acked-by: Segher Boessenkool --- Documentation/powerpc/booting-without-of.txt | 57 ++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) (limited to 'Documentation') diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt index aee243a846a2..ee92fedada1a 100644 --- a/Documentation/powerpc/booting-without-of.txt +++ b/Documentation/powerpc/booting-without-of.txt @@ -59,6 +59,7 @@ Table of Contents p) Freescale Synchronous Serial Interface q) USB EHCI controllers r) MDIO on GPIOs + s) SPI busses VII - Marvell Discovery mv64[345]6x System Controller chips 1) The /system-controller node @@ -1881,6 +1882,62 @@ platforms are moved over to use the flattened-device-tree model. &qe_pio_c 6>; }; + s) SPI (Serial Peripheral Interface) busses + + SPI busses can be described with a node for the SPI master device + and a set of child nodes for each SPI slave on the bus. For this + discussion, it is assumed that the system's SPI controller is in + SPI master mode. This binding does not describe SPI controllers + in slave mode. + + The SPI master node requires the following properties: + - #address-cells - number of cells required to define a chip select + address on the SPI bus. + - #size-cells - should be zero. + - compatible - name of SPI bus controller following generic names + recommended practice. + No other properties are required in the SPI bus node. It is assumed + that a driver for an SPI bus device will understand that it is an SPI bus. + However, the binding does not attempt to define the specific method for + assigning chip select numbers. Since SPI chip select configuration is + flexible and non-standardized, it is left out of this binding with the + assumption that board specific platform code will be used to manage + chip selects. Individual drivers can define additional properties to + support describing the chip select layout. + + SPI slave nodes must be children of the SPI master node and can + contain the following properties. + - reg - (required) chip select address of device. + - compatible - (required) name of SPI device following generic names + recommended practice + - spi-max-frequency - (required) Maximum SPI clocking speed of device in Hz + - spi-cpol - (optional) Empty property indicating device requires + inverse clock polarity (CPOL) mode + - spi-cpha - (optional) Empty property indicating device requires + shifted clock phase (CPHA) mode + + SPI example for an MPC5200 SPI bus: + spi@f00 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,mpc5200b-spi","fsl,mpc5200-spi"; + reg = <0xf00 0x20>; + interrupts = <2 13 0 2 14 0>; + interrupt-parent = <&mpc5200_pic>; + + ethernet-switch@0 { + compatible = "micrel,ks8995m"; + spi-max-frequency = <1000000>; + reg = <0>; + }; + + codec@1 { + compatible = "ti,tlv320aic26"; + spi-max-frequency = <100000>; + reg = <1>; + }; + }; + VII - Marvell Discovery mv64[345]6x System Controller chips =========================================================== -- cgit v1.2.3 From 78305de2f99e9f43ab860dd95bb430b20e26c695 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 23 Apr 2008 07:20:41 -0400 Subject: Remove mention of semaphores from kernel-locking Since the consensus seems to be to eliminate semaphores where possible, we shouldn't be educating people about how to use them as locks. Use mutexes instead. Semaphores should be described in a separate document if we end up keeping them. Signed-off-by: Matthew Wilcox Acked-by: Rusty Russell --- Documentation/DocBook/kernel-locking.tmpl | 57 +++++++++++++------------------ 1 file changed, 24 insertions(+), 33 deletions(-) (limited to 'Documentation') diff --git a/Documentation/DocBook/kernel-locking.tmpl b/Documentation/DocBook/kernel-locking.tmpl index 2510763295d0..084f6ad7b7a0 100644 --- a/Documentation/DocBook/kernel-locking.tmpl +++ b/Documentation/DocBook/kernel-locking.tmpl @@ -219,10 +219,10 @@ - Three Main Types of Kernel Locks: Spinlocks, Mutexes and Semaphores + Two Main Types of Kernel Locks: Spinlocks and Mutexes - There are three main types of kernel locks. The fundamental type + There are two main types of kernel locks. The fundamental type is the spinlock (include/asm/spinlock.h), which is a very simple single-holder lock: if you can't get the @@ -239,14 +239,6 @@ can't sleep (see ), and so have to use a spinlock instead. - - The third type is a semaphore - (include/linux/semaphore.h): it - can have more than one holder at any time (the number decided at - initialization time), although it is most commonly used as a - single-holder lock (a mutex). If you can't get a semaphore, your - task will be suspended and later on woken up - just like for mutexes. - Neither type of lock is recursive: see . @@ -278,7 +270,7 @@ - Semaphores still exist, because they are required for + Mutexes still exist, because they are required for synchronization between user contexts, as we will see below. @@ -289,18 +281,17 @@ If you have a data structure which is only ever accessed from - user context, then you can use a simple semaphore - (linux/linux/semaphore.h) to protect it. This - is the most trivial case: you initialize the semaphore to the number - of resources available (usually 1), and call - down_interruptible() to grab the semaphore, and - up() to release it. There is also a - down(), which should be avoided, because it + user context, then you can use a simple mutex + (include/linux/mutex.h) to protect it. This + is the most trivial case: you initialize the mutex. Then you can + call mutex_lock_interruptible() to grab the mutex, + and mutex_unlock() to release it. There is also a + mutex_lock(), which should be avoided, because it will not return if a signal is received. - Example: linux/net/core/netfilter.c allows + Example: net/netfilter/nf_sockopt.c allows registration of new setsockopt() and getsockopt() calls, with nf_register_sockopt(). Registration and @@ -515,7 +506,7 @@ If you are in a process context (any syscall) and want to - lock other process out, use a semaphore. You can take a semaphore + lock other process out, use a mutex. You can take a mutex and sleep (copy_from_user*( or kmalloc(x,GFP_KERNEL)). @@ -662,7 +653,7 @@ SLBH SLBH SLBH -DI +MLI None @@ -692,8 +683,8 @@ spin_lock_bh -DI -down_interruptible +MLI +mutex_lock_interruptible @@ -1310,7 +1301,7 @@ as Alan Cox says, Lock data, not code. There is a coding bug where a piece of code tries to grab a spinlock twice: it will spin forever, waiting for the lock to - be released (spinlocks, rwlocks and semaphores are not + be released (spinlocks, rwlocks and mutexes are not recursive in Linux). This is trivial to diagnose: not a stay-up-five-nights-talk-to-fluffy-code-bunnies kind of problem. @@ -1335,7 +1326,7 @@ as Alan Cox says, Lock data, not code. This complete lockup is easy to diagnose: on SMP boxes the - watchdog timer or compiling with DEBUG_SPINLOCKS set + watchdog timer or compiling with DEBUG_SPINLOCK set (include/linux/spinlock.h) will show this up immediately when it happens. @@ -1558,7 +1549,7 @@ the amount of locking which needs to be done. Read/Write Lock Variants - Both spinlocks and semaphores have read/write variants: + Both spinlocks and mutexes have read/write variants: rwlock_t and struct rw_semaphore. These divide users into two classes: the readers and the writers. If you are only reading the data, you can get a read lock, but to write to @@ -1681,7 +1672,7 @@ the amount of locking which needs to be done. #include <linux/slab.h> #include <linux/string.h> +#include <linux/rcupdate.h> - #include <linux/semaphore.h> + #include <linux/mutex.h> #include <asm/errno.h> struct object @@ -1913,7 +1904,7 @@ machines due to caching. - put_user() + put_user() @@ -1927,13 +1918,13 @@ machines due to caching. - down_interruptible() and - down() + mutex_lock_interruptible() and + mutex_lock() - There is a down_trylock() which can be + There is a mutex_trylock() which can be used inside interrupt context, as it will not sleep. - up() will also never sleep. + mutex_unlock() will also never sleep. @@ -2023,7 +2014,7 @@ machines due to caching. Prior to 2.5, or when CONFIG_PREEMPT is unset, processes in user context inside the kernel would not - preempt each other (ie. you had that CPU until you have it up, + preempt each other (ie. you had that CPU until you gave it up, except for interrupts). With the addition of CONFIG_PREEMPT in 2.5.4, this changed: when in user context, higher priority tasks can "cut in": spinlocks -- cgit v1.2.3 From 2351ec533ed0dd56052ab96988d2161d5ecc8ed9 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 24 Jul 2008 08:09:32 -0400 Subject: Remove asm/semaphore.h All users have now been converted to linux/semaphore.h and we don't need to keep these files around any longer. Signed-off-by: Matthew Wilcox --- Documentation/feature-removal-schedule.txt | 8 -------- include/asm-alpha/semaphore.h | 1 - include/asm-arm/semaphore.h | 1 - include/asm-avr32/semaphore.h | 1 - include/asm-blackfin/semaphore.h | 1 - include/asm-cris/semaphore.h | 1 - include/asm-frv/semaphore.h | 1 - include/asm-h8300/semaphore.h | 1 - include/asm-ia64/semaphore.h | 1 - include/asm-m32r/semaphore.h | 1 - include/asm-m68k/semaphore.h | 1 - include/asm-m68knommu/semaphore.h | 1 - include/asm-mips/semaphore.h | 1 - include/asm-mn10300/semaphore.h | 1 - include/asm-parisc/semaphore.h | 1 - include/asm-powerpc/semaphore.h | 1 - include/asm-s390/semaphore.h | 1 - include/asm-sh/semaphore.h | 1 - include/asm-sparc/semaphore.h | 1 - include/asm-sparc64/semaphore.h | 1 - include/asm-um/semaphore.h | 1 - include/asm-v850/semaphore.h | 1 - include/asm-x86/semaphore.h | 1 - include/asm-xtensa/semaphore.h | 1 - 24 files changed, 31 deletions(-) delete mode 100644 include/asm-alpha/semaphore.h delete mode 100644 include/asm-arm/semaphore.h delete mode 100644 include/asm-avr32/semaphore.h delete mode 100644 include/asm-blackfin/semaphore.h delete mode 100644 include/asm-cris/semaphore.h delete mode 100644 include/asm-frv/semaphore.h delete mode 100644 include/asm-h8300/semaphore.h delete mode 100644 include/asm-ia64/semaphore.h delete mode 100644 include/asm-m32r/semaphore.h delete mode 100644 include/asm-m68k/semaphore.h delete mode 100644 include/asm-m68knommu/semaphore.h delete mode 100644 include/asm-mips/semaphore.h delete mode 100644 include/asm-mn10300/semaphore.h delete mode 100644 include/asm-parisc/semaphore.h delete mode 100644 include/asm-powerpc/semaphore.h delete mode 100644 include/asm-s390/semaphore.h delete mode 100644 include/asm-sh/semaphore.h delete mode 100644 include/asm-sparc/semaphore.h delete mode 100644 include/asm-sparc64/semaphore.h delete mode 100644 include/asm-um/semaphore.h delete mode 100644 include/asm-v850/semaphore.h delete mode 100644 include/asm-x86/semaphore.h delete mode 100644 include/asm-xtensa/semaphore.h (limited to 'Documentation') diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 9f73587219e8..09c4a1efb8e3 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -300,14 +300,6 @@ Who: ocfs2-devel@oss.oracle.com --------------------------- -What: asm/semaphore.h -When: 2.6.26 -Why: Implementation became generic; users should now include - linux/semaphore.h instead. -Who: Matthew Wilcox - ---------------------------- - What: SCTP_GET_PEER_ADDRS_NUM_OLD, SCTP_GET_PEER_ADDRS_OLD, SCTP_GET_LOCAL_ADDRS_NUM_OLD, SCTP_GET_LOCAL_ADDRS_OLD When: June 2009 diff --git a/include/asm-alpha/semaphore.h b/include/asm-alpha/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-alpha/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-arm/semaphore.h b/include/asm-arm/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-arm/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-avr32/semaphore.h b/include/asm-avr32/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-avr32/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-blackfin/semaphore.h b/include/asm-blackfin/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-blackfin/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-cris/semaphore.h b/include/asm-cris/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-cris/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-frv/semaphore.h b/include/asm-frv/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-frv/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-h8300/semaphore.h b/include/asm-h8300/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-h8300/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-ia64/semaphore.h b/include/asm-ia64/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-ia64/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-m32r/semaphore.h b/include/asm-m32r/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-m32r/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-m68k/semaphore.h b/include/asm-m68k/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-m68k/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-m68knommu/semaphore.h b/include/asm-m68knommu/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-m68knommu/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-mips/semaphore.h b/include/asm-mips/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-mips/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-mn10300/semaphore.h b/include/asm-mn10300/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-mn10300/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-parisc/semaphore.h b/include/asm-parisc/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-parisc/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-powerpc/semaphore.h b/include/asm-powerpc/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-powerpc/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-s390/semaphore.h b/include/asm-s390/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-s390/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-sh/semaphore.h b/include/asm-sh/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-sh/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-sparc/semaphore.h b/include/asm-sparc/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-sparc/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-sparc64/semaphore.h b/include/asm-sparc64/semaphore.h deleted file mode 100644 index 39362afde5fe..000000000000 --- a/include/asm-sparc64/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-um/semaphore.h b/include/asm-um/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-um/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-v850/semaphore.h b/include/asm-v850/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-v850/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-x86/semaphore.h b/include/asm-x86/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-x86/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include diff --git a/include/asm-xtensa/semaphore.h b/include/asm-xtensa/semaphore.h deleted file mode 100644 index d9b2034ed1d2..000000000000 --- a/include/asm-xtensa/semaphore.h +++ /dev/null @@ -1 +0,0 @@ -#include -- cgit v1.2.3 From 6b74ab97bc12ce74acec900f1d89a4aee2e4d70d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 23 Jul 2008 21:26:49 -0700 Subject: mm: add a basic debugging framework for memory initialisation Boot initialisation is very complex, with significant numbers of architecture-specific routines, hooks and code ordering. While significant amounts of the initialisation is architecture-independent, it trusts the data received from the architecture layer. This is a mistake, and has resulted in a number of difficult-to-diagnose bugs. This patchset adds some validation and tracing to memory initialisation. It also introduces a few basic defensive measures. The validation code can be explicitly disabled for embedded systems. This patch: Add additional debugging and verification code for memory initialisation. Once enabled, the verification checks are always run and when required additional debugging information may be outputted via a mminit_loglevel= command-line parameter. The verification code is placed in a new file mm/mm_init.c. Ideally other mm initialisation code will be moved here over time. Signed-off-by: Mel Gorman Cc: Christoph Lameter Cc: Andy Whitcroft Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 8 ++++++++ lib/Kconfig.debug | 12 ++++++++++++ mm/Makefile | 1 + mm/internal.h | 27 +++++++++++++++++++++++++++ mm/mm_init.c | 18 ++++++++++++++++++ mm/page_alloc.c | 22 +++++++++++++--------- 6 files changed, 79 insertions(+), 9 deletions(-) create mode 100644 mm/mm_init.c (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 47e7d8794fc6..5e20ccb5a736 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1225,6 +1225,14 @@ and is between 256 and 4096 characters. It is defined in the file mga= [HW,DRM] + mminit_loglevel= + [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this + parameter allows control of the logging verbosity for + the additional memory initialisation checks. A value + of 0 disables mminit logging and a level of 4 will + log everything. Information is printed at KERN_DEBUG + so loglevel=8 may also need to be specified. + mousedev.tap_time= [MOUSE] Maximum time between finger touching and leaving touchpad surface for touch to be considered diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 882c51048993..e1d4764435ed 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -505,6 +505,18 @@ config DEBUG_WRITECOUNT If unsure, say N. +config DEBUG_MEMORY_INIT + bool "Debug memory initialisation" if EMBEDDED + default !EMBEDDED + help + Enable this for additional checks during memory initialisation. + The sanity checks verify aspects of the VM such as the memory model + and other information provided by the architecture. Verbose + information will be printed at KERN_DEBUG loglevel depending + on the mminit_loglevel= command-line option. + + If unsure, say Y + config DEBUG_LIST bool "Debug linked list manipulation" depends on DEBUG_KERNEL diff --git a/mm/Makefile b/mm/Makefile index 18c143b3c46c..4bbc8f094ff0 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -26,6 +26,7 @@ obj-$(CONFIG_TMPFS_POSIX_ACL) += shmem_acl.o obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o obj-$(CONFIG_SLOB) += slob.o obj-$(CONFIG_SLAB) += slab.o +obj-$(CONFIG_DEBUG_MEMORY_INIT) += mm_init.o obj-$(CONFIG_SLUB) += slub.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_FS_XIP) += filemap_xip.o diff --git a/mm/internal.h b/mm/internal.h index 0034e947e4bc..a7ee05253294 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -59,4 +59,31 @@ static inline unsigned long page_order(struct page *page) #define __paginginit __init #endif +/* Memory initialisation debug and verification */ +enum mminit_level { + MMINIT_WARNING, + MMINIT_VERIFY, + MMINIT_TRACE +}; + +#ifdef CONFIG_DEBUG_MEMORY_INIT + +extern int mminit_loglevel; + +#define mminit_dprintk(level, prefix, fmt, arg...) \ +do { \ + if (level < mminit_loglevel) { \ + printk(level <= MMINIT_WARNING ? KERN_WARNING : KERN_DEBUG); \ + printk(KERN_CONT "mminit::" prefix " " fmt, ##arg); \ + } \ +} while (0) + +#else + +static inline void mminit_dprintk(enum mminit_level level, + const char *prefix, const char *fmt, ...) +{ +} + +#endif /* CONFIG_DEBUG_MEMORY_INIT */ #endif diff --git a/mm/mm_init.c b/mm/mm_init.c new file mode 100644 index 000000000000..c01d8dfec817 --- /dev/null +++ b/mm/mm_init.c @@ -0,0 +1,18 @@ +/* + * mm_init.c - Memory initialisation verification and debugging + * + * Copyright 2008 IBM Corporation, 2008 + * Author Mel Gorman + * + */ +#include +#include + +int __meminitdata mminit_loglevel; + +static __init int set_mminit_loglevel(char *str) +{ + get_option(&str, &mminit_loglevel); + return 0; +} +early_param("mminit_loglevel", set_mminit_loglevel); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 79ac4afc908c..0908352ba727 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2975,7 +2975,8 @@ void __init sparse_memory_present_with_active_regions(int nid) void __init push_node_boundaries(unsigned int nid, unsigned long start_pfn, unsigned long end_pfn) { - printk(KERN_DEBUG "Entering push_node_boundaries(%u, %lu, %lu)\n", + mminit_dprintk(MMINIT_TRACE, "zoneboundary", + "Entering push_node_boundaries(%u, %lu, %lu)\n", nid, start_pfn, end_pfn); /* Initialise the boundary for this node if necessary */ @@ -2993,7 +2994,8 @@ void __init push_node_boundaries(unsigned int nid, static void __meminit account_node_boundary(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn) { - printk(KERN_DEBUG "Entering account_node_boundary(%u, %lu, %lu)\n", + mminit_dprintk(MMINIT_TRACE, "zoneboundary", + "Entering account_node_boundary(%u, %lu, %lu)\n", nid, *start_pfn, *end_pfn); /* Return if boundary information has not been provided */ @@ -3368,8 +3370,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, PAGE_ALIGN(size * sizeof(struct page)) >> PAGE_SHIFT; if (realsize >= memmap_pages) { realsize -= memmap_pages; - printk(KERN_DEBUG - " %s zone: %lu pages used for memmap\n", + mminit_dprintk(MMINIT_TRACE, "memmap_init", + "%s zone: %lu pages used for memmap\n", zone_names[j], memmap_pages); } else printk(KERN_WARNING @@ -3379,7 +3381,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, /* Account for reserved pages */ if (j == 0 && realsize > dma_reserve) { realsize -= dma_reserve; - printk(KERN_DEBUG " %s zone: %lu pages reserved\n", + mminit_dprintk(MMINIT_TRACE, "memmap_init", + "%s zone: %lu pages reserved\n", zone_names[0], dma_reserve); } @@ -3520,10 +3523,11 @@ void __init add_active_range(unsigned int nid, unsigned long start_pfn, { int i; - printk(KERN_DEBUG "Entering add_active_range(%d, %#lx, %#lx) " - "%d entries of %d used\n", - nid, start_pfn, end_pfn, - nr_nodemap_entries, MAX_ACTIVE_REGIONS); + mminit_dprintk(MMINIT_TRACE, "memory_register", + "Entering add_active_range(%d, %#lx, %#lx) " + "%d entries of %d used\n", + nid, start_pfn, end_pfn, + nr_nodemap_entries, MAX_ACTIVE_REGIONS); /* Merge with existing active regions if possible */ for (i = 0; i < nr_nodemap_entries; i++) { -- cgit v1.2.3 From 28b2ee20c7cba812b6f2ccf6d722cf86d00a84dc Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 23 Jul 2008 21:27:05 -0700 Subject: access_process_vm device memory infrastructure In order to be able to debug things like the X server and programs using the PPC Cell SPUs, the debugger needs to be able to access device memory through ptrace and /proc/pid/mem. This patch: Add the generic_access_phys access function and put the hooks in place to allow access_process_vm to access device or PPC Cell SPU memory. [riel@redhat.com: Add documentation for the vm_ops->access function] Signed-off-by: Rik van Riel Signed-off-by: Benjamin Herrensmidt Cc: Dave Airlie Cc: Hugh Dickins Cc: Paul Mackerras Cc: Arnd Bergmann Acked-by: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/Locking | 7 ++ arch/Kconfig | 3 + arch/x86/Kconfig | 1 + arch/x86/mm/ioremap.c | 8 +++ include/asm-x86/io_32.h | 2 + include/asm-x86/io_64.h | 2 + include/linux/mm.h | 8 +++ mm/memory.c | 131 ++++++++++++++++++++++++++++++++------ 8 files changed, 144 insertions(+), 18 deletions(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 8b22d7d8b991..680fb566b928 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -510,6 +510,7 @@ prototypes: void (*close)(struct vm_area_struct*); int (*fault)(struct vm_area_struct*, struct vm_fault *); int (*page_mkwrite)(struct vm_area_struct *, struct page *); + int (*access)(struct vm_area_struct *, unsigned long, void*, int, int); locking rules: BKL mmap_sem PageLocked(page) @@ -517,6 +518,7 @@ open: no yes close: no yes fault: no yes page_mkwrite: no yes no +access: no yes ->page_mkwrite() is called when a previously read-only page is about to become writeable. The file system is responsible for @@ -525,6 +527,11 @@ taking to lock out truncate, the page range should be verified to be within i_size. The page mapping should also be checked that it is not NULL. + ->access() is called when get_user_pages() fails in +acces_process_vm(), typically used to debug a process through +/proc/pid/mem or ptrace. This function is needed only for +VM_IO | VM_PFNMAP VMAs. + ================================================================================ Dubious stuff diff --git a/arch/Kconfig b/arch/Kconfig index 4d5ebbc1e72b..6093c0be58b0 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -31,6 +31,9 @@ config KRETPROBES def_bool y depends on KPROBES && HAVE_KRETPROBES +config HAVE_IOREMAP_PROT + def_bool n + config HAVE_KPROBES def_bool n diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 03980cb04291..b2ddfcf01728 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -21,6 +21,7 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_IDE select HAVE_OPROFILE + select HAVE_IOREMAP_PROT select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_DYNAMIC_FTRACE diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 24c1d3c30186..016f335bbeea 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -330,6 +330,14 @@ static void __iomem *ioremap_default(resource_size_t phys_addr, return (void __iomem *)ret; } +void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size, + unsigned long prot_val) +{ + return __ioremap_caller(phys_addr, size, (prot_val & _PAGE_CACHE_MASK), + __builtin_return_address(0)); +} +EXPORT_SYMBOL(ioremap_prot); + /** * iounmap - Free a IO remapping * @addr: virtual address from ioremap_* diff --git a/include/asm-x86/io_32.h b/include/asm-x86/io_32.h index 4df44ed54077..e876d89ac156 100644 --- a/include/asm-x86/io_32.h +++ b/include/asm-x86/io_32.h @@ -110,6 +110,8 @@ static inline void *phys_to_virt(unsigned long address) */ extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size); extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); +extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, + unsigned long prot_val); /* * The default ioremap() behavior is non-cached: diff --git a/include/asm-x86/io_64.h b/include/asm-x86/io_64.h index ddd8058a5026..22995c5c5adc 100644 --- a/include/asm-x86/io_64.h +++ b/include/asm-x86/io_64.h @@ -175,6 +175,8 @@ extern void early_iounmap(void *addr, unsigned long size); */ extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size); extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); +extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, + unsigned long prot_val); /* * The default ioremap() behavior is non-cached: diff --git a/include/linux/mm.h b/include/linux/mm.h index eb815cfc1b35..5c7f8f64f70e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -170,6 +170,12 @@ struct vm_operations_struct { /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ int (*page_mkwrite)(struct vm_area_struct *vma, struct page *page); + + /* called by access_process_vm when get_user_pages() fails, typically + * for use by special VMAs that can switch between memory and hardware + */ + int (*access)(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write); #ifdef CONFIG_NUMA /* * set_policy() op must add a reference to any non-NULL @new mempolicy @@ -771,6 +777,8 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); +int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write); static inline void unmap_shared_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen) diff --git a/mm/memory.c b/mm/memory.c index 46dbed4b7446..87350321e66f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2751,6 +2751,86 @@ int in_gate_area_no_task(unsigned long addr) #endif /* __HAVE_ARCH_GATE_AREA */ +#ifdef CONFIG_HAVE_IOREMAP_PROT +static resource_size_t follow_phys(struct vm_area_struct *vma, + unsigned long address, unsigned int flags, + unsigned long *prot) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *ptep, pte; + spinlock_t *ptl; + resource_size_t phys_addr = 0; + struct mm_struct *mm = vma->vm_mm; + + VM_BUG_ON(!(vma->vm_flags & (VM_IO | VM_PFNMAP))); + + pgd = pgd_offset(mm, address); + if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) + goto no_page_table; + + pud = pud_offset(pgd, address); + if (pud_none(*pud) || unlikely(pud_bad(*pud))) + goto no_page_table; + + pmd = pmd_offset(pud, address); + if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) + goto no_page_table; + + /* We cannot handle huge page PFN maps. Luckily they don't exist. */ + if (pmd_huge(*pmd)) + goto no_page_table; + + ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + if (!ptep) + goto out; + + pte = *ptep; + if (!pte_present(pte)) + goto unlock; + if ((flags & FOLL_WRITE) && !pte_write(pte)) + goto unlock; + phys_addr = pte_pfn(pte); + phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */ + + *prot = pgprot_val(pte_pgprot(pte)); + +unlock: + pte_unmap_unlock(ptep, ptl); +out: + return phys_addr; +no_page_table: + return 0; +} + +int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write) +{ + resource_size_t phys_addr; + unsigned long prot = 0; + void *maddr; + int offset = addr & (PAGE_SIZE-1); + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + return -EINVAL; + + phys_addr = follow_phys(vma, addr, write, &prot); + + if (!phys_addr) + return -EINVAL; + + maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot); + if (write) + memcpy_toio(maddr + offset, buf, len); + else + memcpy_fromio(buf, maddr + offset, len); + iounmap(maddr); + + return len; +} +#endif + /* * Access another process' address space. * Source/target buffer must be kernel space, @@ -2760,7 +2840,6 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in { struct mm_struct *mm; struct vm_area_struct *vma; - struct page *page; void *old_buf = buf; mm = get_task_mm(tsk); @@ -2772,28 +2851,44 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in while (len) { int bytes, ret, offset; void *maddr; + struct page *page = NULL; ret = get_user_pages(tsk, mm, addr, 1, write, 1, &page, &vma); - if (ret <= 0) - break; - - bytes = len; - offset = addr & (PAGE_SIZE-1); - if (bytes > PAGE_SIZE-offset) - bytes = PAGE_SIZE-offset; - - maddr = kmap(page); - if (write) { - copy_to_user_page(vma, page, addr, - maddr + offset, buf, bytes); - set_page_dirty_lock(page); + if (ret <= 0) { + /* + * Check if this is a VM_IO | VM_PFNMAP VMA, which + * we can access using slightly different code. + */ +#ifdef CONFIG_HAVE_IOREMAP_PROT + vma = find_vma(mm, addr); + if (!vma) + break; + if (vma->vm_ops && vma->vm_ops->access) + ret = vma->vm_ops->access(vma, addr, buf, + len, write); + if (ret <= 0) +#endif + break; + bytes = ret; } else { - copy_from_user_page(vma, page, addr, - buf, maddr + offset, bytes); + bytes = len; + offset = addr & (PAGE_SIZE-1); + if (bytes > PAGE_SIZE-offset) + bytes = PAGE_SIZE-offset; + + maddr = kmap(page); + if (write) { + copy_to_user_page(vma, page, addr, + maddr + offset, buf, bytes); + set_page_dirty_lock(page); + } else { + copy_from_user_page(vma, page, addr, + buf, maddr + offset, bytes); + } + kunmap(page); + page_cache_release(page); } - kunmap(page); - page_cache_release(page); len -= bytes; buf += bytes; addr += bytes; -- cgit v1.2.3 From a47a126ad5ea072aca3e611ed8f8dc6adad24bab Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 23 Jul 2008 21:27:38 -0700 Subject: vmallocinfo: add NUMA information Christoph recently added /proc/vmallocinfo file to get information about vmalloc allocations. This patch adds NUMA specific information, giving number of pages allocated on each memory node. This should help to check that vmalloc() is able to respect NUMA policies. Example of output on a four nodes machine (one cpu per node) 1) network hash tables are evenly spreaded on four nodes (OK) (Same point for inodes and dentries hash tables) 2) iptables tables (x_tables) are correctly allocated on each cpu node (OK). 3) sys_swapon() allocates its memory from one node only. 4) each loaded module is using memory on one node. Sysadmins could tune their setup to change points 3) and 4) if necessary. grep "pages=" /proc/vmallocinfo 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204/0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204/0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 0xffffc2000031a000-0xffffc2000031d000 12288 alloc_large_system_hash+0x204/0x2c0 pages=2 vmalloc N1=1 N2=1 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e/0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3 0xffffc2000033e000-0xffffc20000341000 12288 sys_swapon+0x640/0xac0 pages=2 vmalloc N0=2 0xffffc20000341000-0xffffc20000344000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N0=2 0xffffc20000344000-0xffffc20000347000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N1=2 0xffffc20000347000-0xffffc2000034a000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N2=2 0xffffc2000034a000-0xffffc2000034d000 12288 xt_alloc_table_info+0xfe/0x130 [x_tables] pages=2 vmalloc N3=2 0xffffc20004381000-0xffffc20004402000 528384 alloc_large_system_hash+0x204/0x2c0 pages=128 vmalloc N0=32 N1=32 N2=32 N3=32 0xffffc20004402000-0xffffc20004803000 4198400 alloc_large_system_hash+0x204/0x2c0 pages=1024 vmalloc vpages N0=256 N1=256 N2=256 N3=256 0xffffc20004803000-0xffffc20004904000 1052672 alloc_large_system_hash+0x204/0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 0xffffc20004904000-0xffffc20004bec000 3047424 sys_swapon+0x640/0xac0 pages=743 vmalloc vpages N0=743 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 pages=14 vmalloc N1=14 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 pages=4 vmalloc N0=4 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N0=2 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 pages=10 vmalloc N1=10 0xffffffffa0022000-0xffffffffa0028000 24576 sys_init_module+0xc27/0x1d00 pages=5 vmalloc N3=5 0xffffffffa0028000-0xffffffffa0050000 163840 sys_init_module+0xc27/0x1d00 pages=39 vmalloc N1=39 0xffffffffa0050000-0xffffffffa0052000 8192 sys_init_module+0xc27/0x1d00 pages=1 vmalloc N1=1 0xffffffffa0052000-0xffffffffa0056000 16384 sys_init_module+0xc27/0x1d00 pages=3 vmalloc N1=3 0xffffffffa0056000-0xffffffffa0081000 176128 sys_init_module+0xc27/0x1d00 pages=42 vmalloc N3=42 0xffffffffa0081000-0xffffffffa00ae000 184320 sys_init_module+0xc27/0x1d00 pages=44 vmalloc N3=44 0xffffffffa00ae000-0xffffffffa00b1000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N3=2 0xffffffffa00b1000-0xffffffffa00b9000 32768 sys_init_module+0xc27/0x1d00 pages=7 vmalloc N0=7 0xffffffffa00b9000-0xffffffffa00c4000 45056 sys_init_module+0xc27/0x1d00 pages=10 vmalloc N3=10 0xffffffffa00c6000-0xffffffffa00e0000 106496 sys_init_module+0xc27/0x1d00 pages=25 vmalloc N2=25 0xffffffffa00e0000-0xffffffffa00f1000 69632 sys_init_module+0xc27/0x1d00 pages=16 vmalloc N2=16 0xffffffffa00f1000-0xffffffffa00f4000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N3=2 0xffffffffa00f4000-0xffffffffa00f7000 12288 sys_init_module+0xc27/0x1d00 pages=2 vmalloc N3=2 [akpm@linux-foundation.org: fix comment] Signed-off-by: Eric Dumazet Cc: Christoph Lameter Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 44 ++++++++++++++++++++++++++++++++++++++ fs/proc/proc_misc.c | 15 +++++++++++-- mm/vmalloc.c | 20 +++++++++++++++++ 3 files changed, 77 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 7f268f327d75..8c6384bdfed4 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -296,6 +296,7 @@ Table 1-4: Kernel info in /proc uptime System uptime version Kernel version video bttv info of video resources (2.4) + vmallocinfo Show vmalloced areas .............................................................................. You can, for example, check which interrupts are currently in use and what @@ -557,6 +558,49 @@ VmallocTotal: total size of vmalloc memory area VmallocUsed: amount of vmalloc area which is used VmallocChunk: largest contigious block of vmalloc area which is free +.............................................................................. + +vmallocinfo: + +Provides information about vmalloced/vmaped areas. One line per area, +containing the virtual address range of the area, size in bytes, +caller information of the creator, and optional information depending +on the kind of area : + + pages=nr number of pages + phys=addr if a physical address was specified + ioremap I/O mapping (ioremap() and friends) + vmalloc vmalloc() area + vmap vmap()ed pages + user VM_USERMAP area + vpages buffer for pages pointers was vmalloced (huge area) + N=nr (Only on NUMA kernels) + Number of pages allocated on memory node + +> cat /proc/vmallocinfo +0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ... + /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128 +0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ... + /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 +0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f... + phys=7fee8000 ioremap +0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f... + phys=7fee7000 ioremap +0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210 +0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ... + /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3 +0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ... + pages=2 vmalloc N1=2 +0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ... + /0x130 [x_tables] pages=4 vmalloc N0=4 +0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ... + pages=14 vmalloc N2=14 +0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ... + pages=4 vmalloc N1=4 +0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ... + pages=2 vmalloc N1=2 +0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ... + pages=10 vmalloc N0=10 1.3 IDE devices in /proc/ide ---------------------------- diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index b14f43d25e9e..ded969862960 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -464,14 +464,25 @@ static const struct file_operations proc_slabstats_operations = { #ifdef CONFIG_MMU static int vmalloc_open(struct inode *inode, struct file *file) { - return seq_open(file, &vmalloc_op); + unsigned int *ptr = NULL; + int ret; + + if (NUMA_BUILD) + ptr = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); + ret = seq_open(file, &vmalloc_op); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = ptr; + } else + kfree(ptr); + return ret; } static const struct file_operations proc_vmalloc_operations = { .open = vmalloc_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, }; #endif diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 6e45b0f3d125..35f293816294 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -931,6 +931,25 @@ static void s_stop(struct seq_file *m, void *p) read_unlock(&vmlist_lock); } +static void show_numa_info(struct seq_file *m, struct vm_struct *v) +{ + if (NUMA_BUILD) { + unsigned int nr, *counters = m->private; + + if (!counters) + return; + + memset(counters, 0, nr_node_ids * sizeof(unsigned int)); + + for (nr = 0; nr < v->nr_pages; nr++) + counters[page_to_nid(v->pages[nr])]++; + + for_each_node_state(nr, N_HIGH_MEMORY) + if (counters[nr]) + seq_printf(m, " N%u=%u", nr, counters[nr]); + } +} + static int s_show(struct seq_file *m, void *p) { struct vm_struct *v = p; @@ -967,6 +986,7 @@ static int s_show(struct seq_file *m, void *p) if (v->flags & VM_VPAGES) seq_printf(m, " vpages"); + show_numa_info(m, v); seq_putc(m, '\n'); return 0; } -- cgit v1.2.3 From ff7ea79cf7c3a481851bd4b2185fdeb6ce4afa29 Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Wed, 23 Jul 2008 21:27:39 -0700 Subject: mm: create /sys/kernel/mm Add a kobject to create /sys/kernel/mm when sysfs is mounted. The kobject will exist regardless. This will allow for the hugepage related sysfs directories to exist under the mm "subsystem" directory. Add an ABI file appropriately. [kosaki.motohiro@jp.fujitsu.com: fix build] Signed-off-by: Nishanth Aravamudan Cc: Nick Piggin Cc: Mel Gorman Signed-off-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/ABI/testing/sysfs-kernel-mm | 6 ++++++ include/linux/kobject.h | 2 ++ mm/mm_init.c | 16 ++++++++++++++++ 3 files changed, 24 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-kernel-mm (limited to 'Documentation') diff --git a/Documentation/ABI/testing/sysfs-kernel-mm b/Documentation/ABI/testing/sysfs-kernel-mm new file mode 100644 index 000000000000..190d523ac159 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-mm @@ -0,0 +1,6 @@ +What: /sys/kernel/mm +Date: July 2008 +Contact: Nishanth Aravamudan , VM maintainers +Description: + /sys/kernel/mm/ should contain any and all VM + related information in /sys/kernel/. diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 60f0d418ae32..5437ac0276e2 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -186,6 +186,8 @@ extern struct kobject *kset_find_obj(struct kset *, const char *); /* The global /sys/kernel/ kobject for people to chain off of */ extern struct kobject *kernel_kobj; +/* The global /sys/kernel/mm/ kobject for people to chain off of */ +extern struct kobject *mm_kobj; /* The global /sys/hypervisor/ kobject for people to chain off of */ extern struct kobject *hypervisor_kobj; /* The global /sys/power/ kobject for people to chain off of */ diff --git a/mm/mm_init.c b/mm/mm_init.c index eaf0d3b47099..c6af41ea9994 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -7,6 +7,8 @@ */ #include #include +#include +#include #include "internal.h" #ifdef CONFIG_DEBUG_MEMORY_INIT @@ -134,3 +136,17 @@ static __init int set_mminit_loglevel(char *str) } early_param("mminit_loglevel", set_mminit_loglevel); #endif /* CONFIG_DEBUG_MEMORY_INIT */ + +struct kobject *mm_kobj; +EXPORT_SYMBOL_GPL(mm_kobj); + +static int __init mm_sysfs_init(void) +{ + mm_kobj = kobject_create_and_add("mm", kernel_kobj); + if (!mm_kobj) + return -ENOMEM; + + return 0; +} + +__initcall(mm_sysfs_init); -- cgit v1.2.3 From a3437870160cf2caaac6bdd76c7377a5a4145a8c Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Wed, 23 Jul 2008 21:27:44 -0700 Subject: hugetlb: new sysfs interface Provide new hugepages user APIs that are more suited to multiple hstates in sysfs. There is a new directory, /sys/kernel/hugepages. Underneath that directory there will be a directory per-supported hugepage size, e.g.: /sys/kernel/hugepages/hugepages-64kB /sys/kernel/hugepages/hugepages-16384kB /sys/kernel/hugepages/hugepages-16777216kB corresponding to 64k, 16m and 16g respectively. Within each hugepages-size directory there are a number of files, corresponding to the tracked counters in the hstate, e.g.: /sys/kernel/hugepages/hugepages-64/nr_hugepages /sys/kernel/hugepages/hugepages-64/nr_overcommit_hugepages /sys/kernel/hugepages/hugepages-64/free_hugepages /sys/kernel/hugepages/hugepages-64/resv_hugepages /sys/kernel/hugepages/hugepages-64/surplus_hugepages Of these files, the first two are read-write and the latter three are read-only. The size of the hugepage being manipulated is trivially deducible from the enclosing directory and is always expressed in kB (to match meminfo). [dave@linux.vnet.ibm.com: fix build] [nacc@us.ibm.com: hugetlb: hang off of /sys/kernel/mm rather than /sys/kernel] [nacc@us.ibm.com: hugetlb: remove CONFIG_SYSFS dependency] Acked-by: Greg Kroah-Hartman Signed-off-by: Nishanth Aravamudan Signed-off-by: Nick Piggin Cc: Dave Hansen Signed-off-by: Nishanth Aravamudan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .../ABI/testing/sysfs-kernel-mm-hugepages | 15 ++ Documentation/vm/hugetlbpage.txt | 23 ++ include/linux/hugetlb.h | 2 + mm/hugetlb.c | 288 ++++++++++++++++----- 4 files changed, 262 insertions(+), 66 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-kernel-mm-hugepages (limited to 'Documentation') diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-hugepages b/Documentation/ABI/testing/sysfs-kernel-mm-hugepages new file mode 100644 index 000000000000..e21c00571cf4 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-mm-hugepages @@ -0,0 +1,15 @@ +What: /sys/kernel/mm/hugepages/ +Date: June 2008 +Contact: Nishanth Aravamudan , hugetlb maintainers +Description: + /sys/kernel/mm/hugepages/ contains a number of subdirectories + of the form hugepages-kB, where is the page size + of the hugepages supported by the kernel/CPU combination. + + Under these directories are a number of files: + nr_hugepages + nr_overcommit_hugepages + free_hugepages + surplus_hugepages + resv_hugepages + See Documentation/vm/hugetlbpage.txt for details. diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt index 3102b81bef88..8a5b5763f0fe 100644 --- a/Documentation/vm/hugetlbpage.txt +++ b/Documentation/vm/hugetlbpage.txt @@ -95,6 +95,29 @@ this condition holds, however, no more surplus huge pages will be allowed on the system until one of the two sysctls are increased sufficiently, or the surplus huge pages go out of use and are freed. +With support for multiple hugepage pools at run-time available, much of +the hugepage userspace interface has been duplicated in sysfs. The above +information applies to the default hugepage size (which will be +controlled by the proc interfaces for backwards compatibility). The root +hugepage control directory is + + /sys/kernel/mm/hugepages + +For each hugepage size supported by the running kernel, a subdirectory +will exist, of the form + + hugepages-${size}kB + +Inside each of these directories, the same set of files will exist: + + nr_hugepages + nr_overcommit_hugepages + free_hugepages + resv_hugepages + surplus_hugepages + +which function as described above for the default hugepage-sized case. + If the user applications are going to request hugepages using mmap system call, then it is required that system administrator mount a file system of type hugetlbfs: diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ba9263e631b9..58c0de32e7f0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -164,6 +164,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, #ifdef CONFIG_HUGETLB_PAGE +#define HSTATE_NAME_LEN 32 /* Defines one hugetlb page size */ struct hstate { int hugetlb_next_nid; @@ -179,6 +180,7 @@ struct hstate { unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; + char name[HSTATE_NAME_LEN]; }; void __init hugetlb_add_hstate(unsigned order); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 4cf7a90e9140..bb49ce5d0067 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -942,72 +943,6 @@ static void __init report_hugepages(void) } } -static int __init hugetlb_init(void) -{ - BUILD_BUG_ON(HPAGE_SHIFT == 0); - - if (!size_to_hstate(HPAGE_SIZE)) { - hugetlb_add_hstate(HUGETLB_PAGE_ORDER); - parsed_hstate->max_huge_pages = default_hstate_max_huge_pages; - } - default_hstate_idx = size_to_hstate(HPAGE_SIZE) - hstates; - - hugetlb_init_hstates(); - - report_hugepages(); - - return 0; -} -module_init(hugetlb_init); - -/* Should be called on processing a hugepagesz=... option */ -void __init hugetlb_add_hstate(unsigned order) -{ - struct hstate *h; - if (size_to_hstate(PAGE_SIZE << order)) { - printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n"); - return; - } - BUG_ON(max_hstate >= HUGE_MAX_HSTATE); - BUG_ON(order == 0); - h = &hstates[max_hstate++]; - h->order = order; - h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1); - hugetlb_init_one_hstate(h); - parsed_hstate = h; -} - -static int __init hugetlb_setup(char *s) -{ - unsigned long *mhp; - - /* - * !max_hstate means we haven't parsed a hugepagesz= parameter yet, - * so this hugepages= parameter goes to the "default hstate". - */ - if (!max_hstate) - mhp = &default_hstate_max_huge_pages; - else - mhp = &parsed_hstate->max_huge_pages; - - if (sscanf(s, "%lu", mhp) <= 0) - *mhp = 0; - - return 1; -} -__setup("hugepages=", hugetlb_setup); - -static unsigned int cpuset_mems_nr(unsigned int *array) -{ - int node; - unsigned int nr = 0; - - for_each_node_mask(node, cpuset_current_mems_allowed) - nr += array[node]; - - return nr; -} - #ifdef CONFIG_SYSCTL #ifdef CONFIG_HIGHMEM static void try_to_free_low(struct hstate *h, unsigned long count) @@ -1105,6 +1040,227 @@ out: return ret; } +#define HSTATE_ATTR_RO(_name) \ + static struct kobj_attribute _name##_attr = __ATTR_RO(_name) + +#define HSTATE_ATTR(_name) \ + static struct kobj_attribute _name##_attr = \ + __ATTR(_name, 0644, _name##_show, _name##_store) + +static struct kobject *hugepages_kobj; +static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; + +static struct hstate *kobj_to_hstate(struct kobject *kobj) +{ + int i; + for (i = 0; i < HUGE_MAX_HSTATE; i++) + if (hstate_kobjs[i] == kobj) + return &hstates[i]; + BUG(); + return NULL; +} + +static ssize_t nr_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h = kobj_to_hstate(kobj); + return sprintf(buf, "%lu\n", h->nr_huge_pages); +} +static ssize_t nr_hugepages_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + int err; + unsigned long input; + struct hstate *h = kobj_to_hstate(kobj); + + err = strict_strtoul(buf, 10, &input); + if (err) + return 0; + + h->max_huge_pages = set_max_huge_pages(h, input); + + return count; +} +HSTATE_ATTR(nr_hugepages); + +static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h = kobj_to_hstate(kobj); + return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages); +} +static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + int err; + unsigned long input; + struct hstate *h = kobj_to_hstate(kobj); + + err = strict_strtoul(buf, 10, &input); + if (err) + return 0; + + spin_lock(&hugetlb_lock); + h->nr_overcommit_huge_pages = input; + spin_unlock(&hugetlb_lock); + + return count; +} +HSTATE_ATTR(nr_overcommit_hugepages); + +static ssize_t free_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h = kobj_to_hstate(kobj); + return sprintf(buf, "%lu\n", h->free_huge_pages); +} +HSTATE_ATTR_RO(free_hugepages); + +static ssize_t resv_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h = kobj_to_hstate(kobj); + return sprintf(buf, "%lu\n", h->resv_huge_pages); +} +HSTATE_ATTR_RO(resv_hugepages); + +static ssize_t surplus_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h = kobj_to_hstate(kobj); + return sprintf(buf, "%lu\n", h->surplus_huge_pages); +} +HSTATE_ATTR_RO(surplus_hugepages); + +static struct attribute *hstate_attrs[] = { + &nr_hugepages_attr.attr, + &nr_overcommit_hugepages_attr.attr, + &free_hugepages_attr.attr, + &resv_hugepages_attr.attr, + &surplus_hugepages_attr.attr, + NULL, +}; + +static struct attribute_group hstate_attr_group = { + .attrs = hstate_attrs, +}; + +static int __init hugetlb_sysfs_add_hstate(struct hstate *h) +{ + int retval; + + hstate_kobjs[h - hstates] = kobject_create_and_add(h->name, + hugepages_kobj); + if (!hstate_kobjs[h - hstates]) + return -ENOMEM; + + retval = sysfs_create_group(hstate_kobjs[h - hstates], + &hstate_attr_group); + if (retval) + kobject_put(hstate_kobjs[h - hstates]); + + return retval; +} + +static void __init hugetlb_sysfs_init(void) +{ + struct hstate *h; + int err; + + hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj); + if (!hugepages_kobj) + return; + + for_each_hstate(h) { + err = hugetlb_sysfs_add_hstate(h); + if (err) + printk(KERN_ERR "Hugetlb: Unable to add hstate %s", + h->name); + } +} + +static void __exit hugetlb_exit(void) +{ + struct hstate *h; + + for_each_hstate(h) { + kobject_put(hstate_kobjs[h - hstates]); + } + + kobject_put(hugepages_kobj); +} +module_exit(hugetlb_exit); + +static int __init hugetlb_init(void) +{ + BUILD_BUG_ON(HPAGE_SHIFT == 0); + + if (!size_to_hstate(HPAGE_SIZE)) { + hugetlb_add_hstate(HUGETLB_PAGE_ORDER); + parsed_hstate->max_huge_pages = default_hstate_max_huge_pages; + } + default_hstate_idx = size_to_hstate(HPAGE_SIZE) - hstates; + + hugetlb_init_hstates(); + + report_hugepages(); + + hugetlb_sysfs_init(); + + return 0; +} +module_init(hugetlb_init); + +/* Should be called on processing a hugepagesz=... option */ +void __init hugetlb_add_hstate(unsigned order) +{ + struct hstate *h; + if (size_to_hstate(PAGE_SIZE << order)) { + printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n"); + return; + } + BUG_ON(max_hstate >= HUGE_MAX_HSTATE); + BUG_ON(order == 0); + h = &hstates[max_hstate++]; + h->order = order; + h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1); + snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", + huge_page_size(h)/1024); + hugetlb_init_one_hstate(h); + parsed_hstate = h; +} + +static int __init hugetlb_setup(char *s) +{ + unsigned long *mhp; + + /* + * !max_hstate means we haven't parsed a hugepagesz= parameter yet, + * so this hugepages= parameter goes to the "default hstate". + */ + if (!max_hstate) + mhp = &default_hstate_max_huge_pages; + else + mhp = &parsed_hstate->max_huge_pages; + + if (sscanf(s, "%lu", mhp) <= 0) + *mhp = 0; + + return 1; +} +__setup("hugepages=", hugetlb_setup); + +static unsigned int cpuset_mems_nr(unsigned int *array) +{ + int node; + unsigned int nr = 0; + + for_each_node_mask(node, cpuset_current_mems_allowed) + nr += array[node]; + + return nr; +} + int hugetlb_sysctl_handler(struct ctl_table *table, int write, struct file *file, void __user *buffer, size_t *length, loff_t *ppos) -- cgit v1.2.3 From b4718e628dbf68a2dee23b5709e2aa3190409c56 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 23 Jul 2008 21:27:51 -0700 Subject: x86: add hugepagesz option on 64-bit Add an hugepagesz=... option similar to IA64, PPC etc. to x86-64. This finally allows to select GB pages for hugetlbfs in x86 now that all the infrastructure is in place. Signed-off-by: Andi Kleen Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 11 +++++++++-- arch/x86/mm/hugetlbpage.c | 17 +++++++++++++++++ include/asm-x86/page.h | 2 ++ 3 files changed, 28 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 5e20ccb5a736..d55fd88fd0a9 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -774,8 +774,15 @@ and is between 256 and 4096 characters. It is defined in the file hisax= [HW,ISDN] See Documentation/isdn/README.HiSax. - hugepages= [HW,X86-32,IA-64] Maximal number of HugeTLB pages. - hugepagesz= [HW,IA-64,PPC] The size of the HugeTLB pages. + hugepages= [HW,X86-32,IA-64] HugeTLB pages to allocate at boot. + hugepagesz= [HW,IA-64,PPC,X86-64] The size of the HugeTLB pages. + On x86 this option can be specified multiple times + interleaved with hugepages= to reserve huge pages + of different sizes. Valid pages sizes on x86-64 + are 2M (when the CPU supports "pse") and 1G (when the + CPU supports the "pdpe1gb" cpuinfo flag) + Note that 1GB pages can only be allocated at boot time + using hugepages= and not freed afterwards. i8042.direct [HW] Put keyboard port into non-translated mode i8042.dumbkbd [HW] Pretend that controller can only read data from diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index b7a65a07af03..8f307d914c2e 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -425,3 +425,20 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, #endif /*HAVE_ARCH_HUGETLB_UNMAPPED_AREA*/ +#ifdef CONFIG_X86_64 +static __init int setup_hugepagesz(char *opt) +{ + unsigned long ps = memparse(opt, &opt); + if (ps == PMD_SIZE) { + hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); + } else if (ps == PUD_SIZE && cpu_has_gbpages) { + hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); + } else { + printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n", + ps >> 20); + return 0; + } + return 1; +} +__setup("hugepagesz=", setup_hugepagesz); +#endif diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h index 6c846228948d..6e02098b1605 100644 --- a/include/asm-x86/page.h +++ b/include/asm-x86/page.h @@ -32,6 +32,8 @@ #define HPAGE_MASK (~(HPAGE_SIZE - 1)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) +#define HUGE_MAX_HSTATE 2 + /* to align the pointer to the (next) page boundary */ #define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) -- cgit v1.2.3 From e11bfbfcb08ef4223b863799897c19cdf7c5bc00 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 23 Jul 2008 21:27:52 -0700 Subject: hugetlb: override default huge page size Allow configurations with the default huge page size which is different to the traditional HPAGE_SIZE size. The default huge page size is the one represented in the legacy /proc ABIs, SHM, and which is defaulted to when mounting hugetlbfs filesystems. This is implemented with a new kernel option default_hugepagesz=, which defaults to HPAGE_SIZE if not specified. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 7 +++++++ mm/hugetlb.c | 23 +++++++++++++++++------ 2 files changed, 24 insertions(+), 6 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index d55fd88fd0a9..30278e9e5211 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -783,6 +783,13 @@ and is between 256 and 4096 characters. It is defined in the file CPU supports the "pdpe1gb" cpuinfo flag) Note that 1GB pages can only be allocated at boot time using hugepages= and not freed afterwards. + default_hugepagesz= + [same as hugepagesz=] The size of the default + HugeTLB page size. This is the size represented by + the legacy /proc/ hugepages APIs, used for SHM, and + default size when mounting hugetlbfs filesystems. + Defaults to the default architecture's huge page size + if not specified. i8042.direct [HW] Put keyboard port into non-translated mode i8042.dumbkbd [HW] Pretend that controller can only read data from diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 107c1ce223cb..2a2f6e869401 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -34,6 +34,7 @@ struct hstate hstates[HUGE_MAX_HSTATE]; /* for command line parsing */ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; +static unsigned long __initdata default_hstate_size; #define for_each_hstate(h) \ for ((h) = hstates; (h) < &hstates[max_hstate]; (h)++) @@ -1288,11 +1289,14 @@ static int __init hugetlb_init(void) { BUILD_BUG_ON(HPAGE_SHIFT == 0); - if (!size_to_hstate(HPAGE_SIZE)) { - hugetlb_add_hstate(HUGETLB_PAGE_ORDER); - parsed_hstate->max_huge_pages = default_hstate_max_huge_pages; + if (!size_to_hstate(default_hstate_size)) { + default_hstate_size = HPAGE_SIZE; + if (!size_to_hstate(default_hstate_size)) + hugetlb_add_hstate(HUGETLB_PAGE_ORDER); } - default_hstate_idx = size_to_hstate(HPAGE_SIZE) - hstates; + default_hstate_idx = size_to_hstate(default_hstate_size) - hstates; + if (default_hstate_max_huge_pages) + default_hstate.max_huge_pages = default_hstate_max_huge_pages; hugetlb_init_hstates(); @@ -1332,7 +1336,7 @@ void __init hugetlb_add_hstate(unsigned order) parsed_hstate = h; } -static int __init hugetlb_setup(char *s) +static int __init hugetlb_nrpages_setup(char *s) { unsigned long *mhp; static unsigned long *last_mhp; @@ -1367,7 +1371,14 @@ static int __init hugetlb_setup(char *s) return 1; } -__setup("hugepages=", hugetlb_setup); +__setup("hugepages=", hugetlb_nrpages_setup); + +static int __init hugetlb_default_setup(char *s) +{ + default_hstate_size = memparse(s, &s); + return 1; +} +__setup("default_hugepagesz=", hugetlb_default_setup); static unsigned int cpuset_mems_nr(unsigned int *array) { -- cgit v1.2.3 From 0d9ea75443dc7e37843e656b8ebc947a6d16d618 Mon Sep 17 00:00:00 2001 From: Jon Tollefson Date: Wed, 23 Jul 2008 21:27:56 -0700 Subject: powerpc: support multiple hugepage sizes Instead of using the variable mmu_huge_psize to keep track of the huge page size we use an array of MMU_PAGE_* values. For each supported huge page size we need to know the hugepte_shift value and have a pgtable_cache. The hstate or an mmu_huge_psizes index is passed to functions so that they know which huge page size they should use. The hugepage sizes 16M and 64K are setup(if available on the hardware) so that they don't have to be set on the boot cmd line in order to use them. The number of 16G pages have to be specified at boot-time though (e.g. hugepagesz=16G hugepages=5). Signed-off-by: Jon Tollefson Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 10 +- arch/powerpc/mm/hash_utils_64.c | 9 +- arch/powerpc/mm/hugetlbpage.c | 274 +++++++++++++++++++++++------------- arch/powerpc/mm/init_64.c | 8 +- arch/powerpc/mm/tlb_64.c | 2 +- include/asm-powerpc/hugetlb.h | 5 +- include/asm-powerpc/mmu-hash64.h | 4 +- include/asm-powerpc/page_64.h | 1 + include/asm-powerpc/pgalloc-64.h | 4 +- 9 files changed, 199 insertions(+), 118 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 30278e9e5211..01a2992b5754 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -776,11 +776,11 @@ and is between 256 and 4096 characters. It is defined in the file hugepages= [HW,X86-32,IA-64] HugeTLB pages to allocate at boot. hugepagesz= [HW,IA-64,PPC,X86-64] The size of the HugeTLB pages. - On x86 this option can be specified multiple times - interleaved with hugepages= to reserve huge pages - of different sizes. Valid pages sizes on x86-64 - are 2M (when the CPU supports "pse") and 1G (when the - CPU supports the "pdpe1gb" cpuinfo flag) + On x86-64 and powerpc, this option can be specified + multiple times interleaved with hugepages= to reserve + huge pages of different sizes. Valid pages sizes on + x86-64 are 2M (when the CPU supports "pse") and 1G + (when the CPU supports the "pdpe1gb" cpuinfo flag) Note that 1GB pages can only be allocated at boot time using hugepages= and not freed afterwards. default_hugepagesz= diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index ae4c717243a5..5ce5a4dcd008 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -103,7 +103,6 @@ int mmu_kernel_ssize = MMU_SEGSIZE_256M; int mmu_highuser_ssize = MMU_SEGSIZE_256M; u16 mmu_slb_size = 64; #ifdef CONFIG_HUGETLB_PAGE -int mmu_huge_psize = MMU_PAGE_16M; unsigned int HPAGE_SHIFT; #endif #ifdef CONFIG_PPC_64K_PAGES @@ -460,15 +459,15 @@ static void __init htab_init_page_sizes(void) /* Reserve 16G huge page memory sections for huge pages */ of_scan_flat_dt(htab_dt_scan_hugepage_blocks, NULL); -/* Init large page size. Currently, we pick 16M or 1M depending +/* Set default large page size. Currently, we pick 16M or 1M depending * on what is available */ if (mmu_psize_defs[MMU_PAGE_16M].shift) - set_huge_psize(MMU_PAGE_16M); + HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_16M].shift; /* With 4k/4level pagetables, we can't (for now) cope with a * huge page size < PMD_SIZE */ else if (mmu_psize_defs[MMU_PAGE_1M].shift) - set_huge_psize(MMU_PAGE_1M); + HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_1M].shift; #endif /* CONFIG_HUGETLB_PAGE */ } @@ -889,7 +888,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) #ifdef CONFIG_HUGETLB_PAGE /* Handle hugepage regions */ - if (HPAGE_SHIFT && psize == mmu_huge_psize) { + if (HPAGE_SHIFT && mmu_huge_psizes[psize]) { DBG_LOW(" -> huge page !\n"); return hash_huge_page(mm, access, ea, vsid, local, trap); } diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 19b1a9cec6d5..fb42c4dd3217 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -37,15 +37,30 @@ static unsigned long gpage_freearray[MAX_NUMBER_GPAGES]; static unsigned nr_gpages; -unsigned int hugepte_shift; -#define PTRS_PER_HUGEPTE (1 << hugepte_shift) -#define HUGEPTE_TABLE_SIZE (sizeof(pte_t) << hugepte_shift) +/* Array of valid huge page sizes - non-zero value(hugepte_shift) is + * stored for the huge page sizes that are valid. + */ +unsigned int mmu_huge_psizes[MMU_PAGE_COUNT] = { }; /* initialize all to 0 */ + +#define hugepte_shift mmu_huge_psizes +#define PTRS_PER_HUGEPTE(psize) (1 << hugepte_shift[psize]) +#define HUGEPTE_TABLE_SIZE(psize) (sizeof(pte_t) << hugepte_shift[psize]) + +#define HUGEPD_SHIFT(psize) (mmu_psize_to_shift(psize) \ + + hugepte_shift[psize]) +#define HUGEPD_SIZE(psize) (1UL << HUGEPD_SHIFT(psize)) +#define HUGEPD_MASK(psize) (~(HUGEPD_SIZE(psize)-1)) -#define HUGEPD_SHIFT (HPAGE_SHIFT + hugepte_shift) -#define HUGEPD_SIZE (1UL << HUGEPD_SHIFT) -#define HUGEPD_MASK (~(HUGEPD_SIZE-1)) +/* Subtract one from array size because we don't need a cache for 4K since + * is not a huge page size */ +#define huge_pgtable_cache(psize) (pgtable_cache[HUGEPTE_CACHE_NUM \ + + psize-1]) +#define HUGEPTE_CACHE_NAME(psize) (huge_pgtable_cache_name[psize]) -#define huge_pgtable_cache (pgtable_cache[HUGEPTE_CACHE_NUM]) +static const char *huge_pgtable_cache_name[MMU_PAGE_COUNT] = { + "unused_4K", "hugepte_cache_64K", "unused_64K_AP", + "hugepte_cache_1M", "hugepte_cache_16M", "hugepte_cache_16G" +}; /* Flag to mark huge PD pointers. This means pmd_bad() and pud_bad() * will choke on pointers to hugepte tables, which is handy for @@ -56,24 +71,49 @@ typedef struct { unsigned long pd; } hugepd_t; #define hugepd_none(hpd) ((hpd).pd == 0) +static inline int shift_to_mmu_psize(unsigned int shift) +{ + switch (shift) { +#ifndef CONFIG_PPC_64K_PAGES + case PAGE_SHIFT_64K: + return MMU_PAGE_64K; +#endif + case PAGE_SHIFT_16M: + return MMU_PAGE_16M; + case PAGE_SHIFT_16G: + return MMU_PAGE_16G; + } + return -1; +} + +static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize) +{ + if (mmu_psize_defs[mmu_psize].shift) + return mmu_psize_defs[mmu_psize].shift; + BUG(); +} + static inline pte_t *hugepd_page(hugepd_t hpd) { BUG_ON(!(hpd.pd & HUGEPD_OK)); return (pte_t *)(hpd.pd & ~HUGEPD_OK); } -static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr) +static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr, + struct hstate *hstate) { - unsigned long idx = ((addr >> HPAGE_SHIFT) & (PTRS_PER_HUGEPTE-1)); + unsigned int shift = huge_page_shift(hstate); + int psize = shift_to_mmu_psize(shift); + unsigned long idx = ((addr >> shift) & (PTRS_PER_HUGEPTE(psize)-1)); pte_t *dir = hugepd_page(*hpdp); return dir + idx; } static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, - unsigned long address) + unsigned long address, unsigned int psize) { - pte_t *new = kmem_cache_alloc(huge_pgtable_cache, + pte_t *new = kmem_cache_alloc(huge_pgtable_cache(psize), GFP_KERNEL|__GFP_REPEAT); if (! new) @@ -81,7 +121,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, spin_lock(&mm->page_table_lock); if (!hugepd_none(*hpdp)) - kmem_cache_free(huge_pgtable_cache, new); + kmem_cache_free(huge_pgtable_cache(psize), new); else hpdp->pd = (unsigned long)new | HUGEPD_OK; spin_unlock(&mm->page_table_lock); @@ -90,21 +130,22 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, /* Base page size affects how we walk hugetlb page tables */ #ifdef CONFIG_PPC_64K_PAGES -#define hpmd_offset(pud, addr) pmd_offset(pud, addr) -#define hpmd_alloc(mm, pud, addr) pmd_alloc(mm, pud, addr) +#define hpmd_offset(pud, addr, h) pmd_offset(pud, addr) +#define hpmd_alloc(mm, pud, addr, h) pmd_alloc(mm, pud, addr) #else static inline -pmd_t *hpmd_offset(pud_t *pud, unsigned long addr) +pmd_t *hpmd_offset(pud_t *pud, unsigned long addr, struct hstate *hstate) { - if (HPAGE_SHIFT == PAGE_SHIFT_64K) + if (huge_page_shift(hstate) == PAGE_SHIFT_64K) return pmd_offset(pud, addr); else return (pmd_t *) pud; } static inline -pmd_t *hpmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long addr) +pmd_t *hpmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long addr, + struct hstate *hstate) { - if (HPAGE_SHIFT == PAGE_SHIFT_64K) + if (huge_page_shift(hstate) == PAGE_SHIFT_64K) return pmd_alloc(mm, pud, addr); else return (pmd_t *) pud; @@ -128,8 +169,9 @@ void add_gpage(unsigned long addr, unsigned long page_size, } /* Moves the gigantic page addresses from the temporary list to the - * huge_boot_pages list. */ -int alloc_bootmem_huge_page(struct hstate *h) + * huge_boot_pages list. + */ +int alloc_bootmem_huge_page(struct hstate *hstate) { struct huge_bootmem_page *m; if (nr_gpages == 0) @@ -137,7 +179,7 @@ int alloc_bootmem_huge_page(struct hstate *h) m = phys_to_virt(gpage_freearray[--nr_gpages]); gpage_freearray[nr_gpages] = 0; list_add(&m->list, &huge_boot_pages); - m->hstate = h; + m->hstate = hstate; return 1; } @@ -149,17 +191,25 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) pud_t *pu; pmd_t *pm; - BUG_ON(get_slice_psize(mm, addr) != mmu_huge_psize); + unsigned int psize; + unsigned int shift; + unsigned long sz; + struct hstate *hstate; + psize = get_slice_psize(mm, addr); + shift = mmu_psize_to_shift(psize); + sz = ((1UL) << shift); + hstate = size_to_hstate(sz); - addr &= HPAGE_MASK; + addr &= hstate->mask; pg = pgd_offset(mm, addr); if (!pgd_none(*pg)) { pu = pud_offset(pg, addr); if (!pud_none(*pu)) { - pm = hpmd_offset(pu, addr); + pm = hpmd_offset(pu, addr, hstate); if (!pmd_none(*pm)) - return hugepte_offset((hugepd_t *)pm, addr); + return hugepte_offset((hugepd_t *)pm, addr, + hstate); } } @@ -173,16 +223,20 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pud_t *pu; pmd_t *pm; hugepd_t *hpdp = NULL; + struct hstate *hstate; + unsigned int psize; + hstate = size_to_hstate(sz); - BUG_ON(get_slice_psize(mm, addr) != mmu_huge_psize); + psize = get_slice_psize(mm, addr); + BUG_ON(!mmu_huge_psizes[psize]); - addr &= HPAGE_MASK; + addr &= hstate->mask; pg = pgd_offset(mm, addr); pu = pud_alloc(mm, pg, addr); if (pu) { - pm = hpmd_alloc(mm, pu, addr); + pm = hpmd_alloc(mm, pu, addr, hstate); if (pm) hpdp = (hugepd_t *)pm; } @@ -190,10 +244,10 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, if (! hpdp) return NULL; - if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr)) + if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, psize)) return NULL; - return hugepte_offset(hpdp, addr); + return hugepte_offset(hpdp, addr, hstate); } int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) @@ -201,19 +255,22 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) return 0; } -static void free_hugepte_range(struct mmu_gather *tlb, hugepd_t *hpdp) +static void free_hugepte_range(struct mmu_gather *tlb, hugepd_t *hpdp, + unsigned int psize) { pte_t *hugepte = hugepd_page(*hpdp); hpdp->pd = 0; tlb->need_flush = 1; - pgtable_free_tlb(tlb, pgtable_free_cache(hugepte, HUGEPTE_CACHE_NUM, + pgtable_free_tlb(tlb, pgtable_free_cache(hugepte, + HUGEPTE_CACHE_NUM+psize-1, PGF_CACHENUM_MASK)); } static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud, unsigned long addr, unsigned long end, - unsigned long floor, unsigned long ceiling) + unsigned long floor, unsigned long ceiling, + unsigned int psize) { pmd_t *pmd; unsigned long next; @@ -225,7 +282,7 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud, next = pmd_addr_end(addr, end); if (pmd_none(*pmd)) continue; - free_hugepte_range(tlb, (hugepd_t *)pmd); + free_hugepte_range(tlb, (hugepd_t *)pmd, psize); } while (pmd++, addr = next, addr != end); start &= PUD_MASK; @@ -251,6 +308,9 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, pud_t *pud; unsigned long next; unsigned long start; + unsigned int shift; + unsigned int psize = get_slice_psize(tlb->mm, addr); + shift = mmu_psize_to_shift(psize); start = addr; pud = pud_offset(pgd, addr); @@ -259,16 +319,18 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, #ifdef CONFIG_PPC_64K_PAGES if (pud_none_or_clear_bad(pud)) continue; - hugetlb_free_pmd_range(tlb, pud, addr, next, floor, ceiling); + hugetlb_free_pmd_range(tlb, pud, addr, next, floor, ceiling, + psize); #else - if (HPAGE_SHIFT == PAGE_SHIFT_64K) { + if (shift == PAGE_SHIFT_64K) { if (pud_none_or_clear_bad(pud)) continue; - hugetlb_free_pmd_range(tlb, pud, addr, next, floor, ceiling); + hugetlb_free_pmd_range(tlb, pud, addr, next, floor, + ceiling, psize); } else { if (pud_none(*pud)) continue; - free_hugepte_range(tlb, (hugepd_t *)pud); + free_hugepte_range(tlb, (hugepd_t *)pud, psize); } #endif } while (pud++, addr = next, addr != end); @@ -336,27 +398,29 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, * now has no other vmas using it, so can be freed, we don't * bother to round floor or end up - the tests don't need that. */ + unsigned int psize = get_slice_psize(tlb->mm, addr); - addr &= HUGEPD_MASK; + addr &= HUGEPD_MASK(psize); if (addr < floor) { - addr += HUGEPD_SIZE; + addr += HUGEPD_SIZE(psize); if (!addr) return; } if (ceiling) { - ceiling &= HUGEPD_MASK; + ceiling &= HUGEPD_MASK(psize); if (!ceiling) return; } if (end - 1 > ceiling - 1) - end -= HUGEPD_SIZE; + end -= HUGEPD_SIZE(psize); if (addr > end - 1) return; start = addr; pgd = pgd_offset(tlb->mm, addr); do { - BUG_ON(get_slice_psize(tlb->mm, addr) != mmu_huge_psize); + psize = get_slice_psize(tlb->mm, addr); + BUG_ON(!mmu_huge_psizes[psize]); next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; @@ -373,7 +437,11 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, * necessary anymore if we make hpte_need_flush() get the * page size from the slices */ - pte_update(mm, addr & HPAGE_MASK, ptep, ~0UL, 1); + unsigned int psize = get_slice_psize(mm, addr); + unsigned int shift = mmu_psize_to_shift(psize); + unsigned long sz = ((1UL) << shift); + struct hstate *hstate = size_to_hstate(sz); + pte_update(mm, addr & hstate->mask, ptep, ~0UL, 1); } *ptep = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS); } @@ -390,14 +458,19 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) { pte_t *ptep; struct page *page; + unsigned int mmu_psize = get_slice_psize(mm, address); - if (get_slice_psize(mm, address) != mmu_huge_psize) + /* Verify it is a huge page else bail. */ + if (!mmu_huge_psizes[mmu_psize]) return ERR_PTR(-EINVAL); ptep = huge_pte_offset(mm, address); page = pte_page(*ptep); - if (page) - page += (address % HPAGE_SIZE) / PAGE_SIZE; + if (page) { + unsigned int shift = mmu_psize_to_shift(mmu_psize); + unsigned long sz = ((1UL) << shift); + page += (address % sz) / PAGE_SIZE; + } return page; } @@ -425,15 +498,16 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { - return slice_get_unmapped_area(addr, len, flags, - mmu_huge_psize, 1, 0); + struct hstate *hstate = hstate_file(file); + int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate)); + return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1, 0); } /* * Called by asm hashtable.S for doing lazy icache flush */ static unsigned int hash_huge_page_do_lazy_icache(unsigned long rflags, - pte_t pte, int trap) + pte_t pte, int trap, unsigned long sz) { struct page *page; int i; @@ -446,7 +520,7 @@ static unsigned int hash_huge_page_do_lazy_icache(unsigned long rflags, /* page is dirty */ if (!test_bit(PG_arch_1, &page->flags) && !PageReserved(page)) { if (trap == 0x400) { - for (i = 0; i < (HPAGE_SIZE / PAGE_SIZE); i++) + for (i = 0; i < (sz / PAGE_SIZE); i++) __flush_dcache_icache(page_address(page+i)); set_bit(PG_arch_1, &page->flags); } else { @@ -462,11 +536,16 @@ int hash_huge_page(struct mm_struct *mm, unsigned long access, { pte_t *ptep; unsigned long old_pte, new_pte; - unsigned long va, rflags, pa; + unsigned long va, rflags, pa, sz; long slot; int err = 1; int ssize = user_segment_size(ea); + unsigned int mmu_psize; + int shift; + mmu_psize = get_slice_psize(mm, ea); + if (!mmu_huge_psizes[mmu_psize]) + goto out; ptep = huge_pte_offset(mm, ea); /* Search the Linux page table for a match with va */ @@ -509,30 +588,32 @@ int hash_huge_page(struct mm_struct *mm, unsigned long access, rflags = 0x2 | (!(new_pte & _PAGE_RW)); /* _PAGE_EXEC -> HW_NO_EXEC since it's inverted */ rflags |= ((new_pte & _PAGE_EXEC) ? 0 : HPTE_R_N); + shift = mmu_psize_to_shift(mmu_psize); + sz = ((1UL) << shift); if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) /* No CPU has hugepages but lacks no execute, so we * don't need to worry about that case */ rflags = hash_huge_page_do_lazy_icache(rflags, __pte(old_pte), - trap); + trap, sz); /* Check if pte already has an hpte (case 2) */ if (unlikely(old_pte & _PAGE_HASHPTE)) { /* There MIGHT be an HPTE for this pte */ unsigned long hash, slot; - hash = hpt_hash(va, HPAGE_SHIFT, ssize); + hash = hpt_hash(va, shift, ssize); if (old_pte & _PAGE_F_SECOND) hash = ~hash; slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; slot += (old_pte & _PAGE_F_GIX) >> 12; - if (ppc_md.hpte_updatepp(slot, rflags, va, mmu_huge_psize, + if (ppc_md.hpte_updatepp(slot, rflags, va, mmu_psize, ssize, local) == -1) old_pte &= ~_PAGE_HPTEFLAGS; } if (likely(!(old_pte & _PAGE_HASHPTE))) { - unsigned long hash = hpt_hash(va, HPAGE_SHIFT, ssize); + unsigned long hash = hpt_hash(va, shift, ssize); unsigned long hpte_group; pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT; @@ -553,7 +634,7 @@ repeat: /* Insert into the hash table, primary slot */ slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, 0, - mmu_huge_psize, ssize); + mmu_psize, ssize); /* Primary is full, try the secondary */ if (unlikely(slot == -1)) { @@ -561,7 +642,7 @@ repeat: HPTES_PER_GROUP) & ~0x7UL; slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, HPTE_V_SECONDARY, - mmu_huge_psize, ssize); + mmu_psize, ssize); if (slot == -1) { if (mftb() & 0x1) hpte_group = ((hash & htab_hash_mask) * @@ -598,66 +679,50 @@ void set_huge_psize(int psize) (mmu_psize_defs[psize].shift > MIN_HUGEPTE_SHIFT || mmu_psize_defs[psize].shift == PAGE_SHIFT_64K || mmu_psize_defs[psize].shift == PAGE_SHIFT_16G)) { - /* Return if huge page size is the same as the - * base page size. */ - if (mmu_psize_defs[psize].shift == PAGE_SHIFT) + /* Return if huge page size has already been setup or is the + * same as the base page size. */ + if (mmu_huge_psizes[psize] || + mmu_psize_defs[psize].shift == PAGE_SHIFT) return; + hugetlb_add_hstate(mmu_psize_defs[psize].shift - PAGE_SHIFT); - HPAGE_SHIFT = mmu_psize_defs[psize].shift; - mmu_huge_psize = psize; - - switch (HPAGE_SHIFT) { + switch (mmu_psize_defs[psize].shift) { case PAGE_SHIFT_64K: /* We only allow 64k hpages with 4k base page, * which was checked above, and always put them * at the PMD */ - hugepte_shift = PMD_SHIFT; + hugepte_shift[psize] = PMD_SHIFT; break; case PAGE_SHIFT_16M: /* 16M pages can be at two different levels * of pagestables based on base page size */ if (PAGE_SHIFT == PAGE_SHIFT_64K) - hugepte_shift = PMD_SHIFT; + hugepte_shift[psize] = PMD_SHIFT; else /* 4k base page */ - hugepte_shift = PUD_SHIFT; + hugepte_shift[psize] = PUD_SHIFT; break; case PAGE_SHIFT_16G: /* 16G pages are always at PGD level */ - hugepte_shift = PGDIR_SHIFT; + hugepte_shift[psize] = PGDIR_SHIFT; break; } - hugepte_shift -= HPAGE_SHIFT; + hugepte_shift[psize] -= mmu_psize_defs[psize].shift; } else - HPAGE_SHIFT = 0; + hugepte_shift[psize] = 0; } static int __init hugepage_setup_sz(char *str) { unsigned long long size; - int mmu_psize = -1; + int mmu_psize; int shift; size = memparse(str, &str); shift = __ffs(size); - switch (shift) { -#ifndef CONFIG_PPC_64K_PAGES - case PAGE_SHIFT_64K: - mmu_psize = MMU_PAGE_64K; - break; -#endif - case PAGE_SHIFT_16M: - mmu_psize = MMU_PAGE_16M; - break; - case PAGE_SHIFT_16G: - mmu_psize = MMU_PAGE_16G; - break; - } - - if (mmu_psize >= 0 && mmu_psize_defs[mmu_psize].shift) { + mmu_psize = shift_to_mmu_psize(shift); + if (mmu_psize >= 0 && mmu_psize_defs[mmu_psize].shift) set_huge_psize(mmu_psize); - hugetlb_add_hstate(shift - PAGE_SHIFT); - } else printk(KERN_WARNING "Invalid huge page size specified(%llu)\n", size); @@ -672,16 +737,31 @@ static void zero_ctor(struct kmem_cache *cache, void *addr) static int __init hugetlbpage_init(void) { + unsigned int psize; + if (!cpu_has_feature(CPU_FTR_16M_PAGE)) return -ENODEV; - - huge_pgtable_cache = kmem_cache_create("hugepte_cache", - HUGEPTE_TABLE_SIZE, - HUGEPTE_TABLE_SIZE, - 0, - zero_ctor); - if (! huge_pgtable_cache) - panic("hugetlbpage_init(): could not create hugepte cache\n"); + /* Add supported huge page sizes. Need to change HUGE_MAX_HSTATE + * and adjust PTE_NONCACHE_NUM if the number of supported huge page + * sizes changes. + */ + set_huge_psize(MMU_PAGE_16M); + set_huge_psize(MMU_PAGE_64K); + set_huge_psize(MMU_PAGE_16G); + + for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { + if (mmu_huge_psizes[psize]) { + huge_pgtable_cache(psize) = kmem_cache_create( + HUGEPTE_CACHE_NAME(psize), + HUGEPTE_TABLE_SIZE(psize), + HUGEPTE_TABLE_SIZE(psize), + 0, + zero_ctor); + if (!huge_pgtable_cache(psize)) + panic("hugetlbpage_init(): could not create %s"\ + "\n", HUGEPTE_CACHE_NAME(psize)); + } + } return 0; } diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 6ef63caca682..a41bc5aa2043 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -153,10 +153,10 @@ static const char *pgtable_cache_name[ARRAY_SIZE(pgtable_cache_size)] = { }; #ifdef CONFIG_HUGETLB_PAGE -/* Hugepages need one extra cache, initialized in hugetlbpage.c. We - * can't put into the tables above, because HPAGE_SHIFT is not compile - * time constant. */ -struct kmem_cache *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)+1]; +/* Hugepages need an extra cache per hugepagesize, initialized in + * hugetlbpage.c. We can't put into the tables above, because HPAGE_SHIFT + * is not compile time constant. */ +struct kmem_cache *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)+MMU_PAGE_COUNT]; #else struct kmem_cache *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)]; #endif diff --git a/arch/powerpc/mm/tlb_64.c b/arch/powerpc/mm/tlb_64.c index a01b5c608ff9..409fcc7b63ce 100644 --- a/arch/powerpc/mm/tlb_64.c +++ b/arch/powerpc/mm/tlb_64.c @@ -147,7 +147,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, */ if (huge) { #ifdef CONFIG_HUGETLB_PAGE - psize = mmu_huge_psize; + psize = get_slice_psize(mm, addr);; #else BUG(); psize = pte_pagesize_index(mm, addr, pte); /* shutup gcc */ diff --git a/include/asm-powerpc/hugetlb.h b/include/asm-powerpc/hugetlb.h index ca37c4af27b1..26f0d0ab27a5 100644 --- a/include/asm-powerpc/hugetlb.h +++ b/include/asm-powerpc/hugetlb.h @@ -24,9 +24,10 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, static inline int prepare_hugepage_range(struct file *file, unsigned long addr, unsigned long len) { - if (len & ~HPAGE_MASK) + struct hstate *h = hstate_file(file); + if (len & ~huge_page_mask(h)) return -EINVAL; - if (addr & ~HPAGE_MASK) + if (addr & ~huge_page_mask(h)) return -EINVAL; return 0; } diff --git a/include/asm-powerpc/mmu-hash64.h b/include/asm-powerpc/mmu-hash64.h index b61181aa7746..19c7a9403490 100644 --- a/include/asm-powerpc/mmu-hash64.h +++ b/include/asm-powerpc/mmu-hash64.h @@ -194,9 +194,9 @@ extern int mmu_ci_restrictions; #ifdef CONFIG_HUGETLB_PAGE /* - * The page size index of the huge pages for use by hugetlbfs + * The page size indexes of the huge pages for use by hugetlbfs */ -extern int mmu_huge_psize; +extern unsigned int mmu_huge_psizes[MMU_PAGE_COUNT]; #endif /* CONFIG_HUGETLB_PAGE */ diff --git a/include/asm-powerpc/page_64.h b/include/asm-powerpc/page_64.h index 02fd80710e9d..043bfdfe4f73 100644 --- a/include/asm-powerpc/page_64.h +++ b/include/asm-powerpc/page_64.h @@ -90,6 +90,7 @@ extern unsigned int HPAGE_SHIFT; #define HPAGE_SIZE ((1UL) << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) +#define HUGE_MAX_HSTATE 3 #endif /* __ASSEMBLY__ */ diff --git a/include/asm-powerpc/pgalloc-64.h b/include/asm-powerpc/pgalloc-64.h index 68980990f62a..812a1d8f35cb 100644 --- a/include/asm-powerpc/pgalloc-64.h +++ b/include/asm-powerpc/pgalloc-64.h @@ -22,7 +22,7 @@ extern struct kmem_cache *pgtable_cache[]; #define PUD_CACHE_NUM 1 #define PMD_CACHE_NUM 1 #define HUGEPTE_CACHE_NUM 2 -#define PTE_NONCACHE_NUM 3 /* from GFP rather than kmem_cache */ +#define PTE_NONCACHE_NUM 7 /* from GFP rather than kmem_cache */ static inline pgd_t *pgd_alloc(struct mm_struct *mm) { @@ -119,7 +119,7 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) __free_page(ptepage); } -#define PGF_CACHENUM_MASK 0x3 +#define PGF_CACHENUM_MASK 0x7 typedef struct pgtable_free { unsigned long val; -- cgit v1.2.3 From 5c755e9fd813810680abd56ec09a5f90143e815b Mon Sep 17 00:00:00 2001 From: Badari Pulavarty Date: Wed, 23 Jul 2008 21:28:19 -0700 Subject: memory-hotplug: add sysfs removable attribute for hotplug memory remove Memory may be hot-removed on a per-memory-block basis, particularly on POWER where the SPARSEMEM section size often matches the memory-block size. A user-level agent must be able to identify which sections of memory are likely to be removable before attempting the potentially expensive operation. This patch adds a file called "removable" to the memory directory in sysfs to help such an agent. In this patch, a memory block is considered removable if; o It contains only MOVABLE pageblocks o It contains only pageblocks with free pages regardless of pageblock type On the other hand, a memory block starting with a PageReserved() page will never be considered removable. Without this patch, the user-agent is forced to choose a memory block to remove randomly. Sample output of the sysfs files: ./memory/memory0/removable: 0 ./memory/memory1/removable: 0 ./memory/memory2/removable: 0 ./memory/memory3/removable: 0 ./memory/memory4/removable: 0 ./memory/memory5/removable: 0 ./memory/memory6/removable: 0 ./memory/memory7/removable: 1 ./memory/memory8/removable: 0 ./memory/memory9/removable: 0 ./memory/memory10/removable: 0 ./memory/memory11/removable: 0 ./memory/memory12/removable: 0 ./memory/memory13/removable: 0 ./memory/memory14/removable: 0 ./memory/memory15/removable: 0 ./memory/memory16/removable: 0 ./memory/memory17/removable: 1 ./memory/memory18/removable: 1 ./memory/memory19/removable: 1 ./memory/memory20/removable: 1 ./memory/memory21/removable: 1 ./memory/memory22/removable: 1 Signed-off-by: Badari Pulavarty Signed-off-by: Mel Gorman Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/ABI/testing/sysfs-devices-memory | 24 +++++++++++ drivers/base/memory.c | 19 ++++++++ include/linux/memory_hotplug.h | 12 ++++++ mm/memory_hotplug.c | 60 ++++++++++++++++++++++++++ 4 files changed, 115 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-devices-memory (limited to 'Documentation') diff --git a/Documentation/ABI/testing/sysfs-devices-memory b/Documentation/ABI/testing/sysfs-devices-memory new file mode 100644 index 000000000000..7a16fe1e2270 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-devices-memory @@ -0,0 +1,24 @@ +What: /sys/devices/system/memory +Date: June 2008 +Contact: Badari Pulavarty +Description: + The /sys/devices/system/memory contains a snapshot of the + internal state of the kernel memory blocks. Files could be + added or removed dynamically to represent hot-add/remove + operations. + +Users: hotplug memory add/remove tools + https://w3.opensource.ibm.com/projects/powerpc-utils/ + +What: /sys/devices/system/memory/memoryX/removable +Date: June 2008 +Contact: Badari Pulavarty +Description: + The file /sys/devices/system/memory/memoryX/removable + indicates whether this memory block is removable or not. + This is useful for a user-level agent to determine + identify removable sections of the memory before attempting + potentially expensive hot-remove memory operation + +Users: hotplug memory remove tools + https://w3.opensource.ibm.com/projects/powerpc-utils/ diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 4d4e0e7b6e92..855ed1a9f97b 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -100,6 +100,21 @@ static ssize_t show_mem_phys_index(struct sys_device *dev, return sprintf(buf, "%08lx\n", mem->phys_index); } +/* + * Show whether the section of memory is likely to be hot-removable + */ +static ssize_t show_mem_removable(struct sys_device *dev, char *buf) +{ + unsigned long start_pfn; + int ret; + struct memory_block *mem = + container_of(dev, struct memory_block, sysdev); + + start_pfn = section_nr_to_pfn(mem->phys_index); + ret = is_mem_section_removable(start_pfn, PAGES_PER_SECTION); + return sprintf(buf, "%d\n", ret); +} + /* * online, offline, going offline, etc. */ @@ -262,6 +277,7 @@ static ssize_t show_phys_device(struct sys_device *dev, static SYSDEV_ATTR(phys_index, 0444, show_mem_phys_index, NULL); static SYSDEV_ATTR(state, 0644, show_mem_state, store_mem_state); static SYSDEV_ATTR(phys_device, 0444, show_phys_device, NULL); +static SYSDEV_ATTR(removable, 0444, show_mem_removable, NULL); #define mem_create_simple_file(mem, attr_name) \ sysdev_create_file(&mem->sysdev, &attr_##attr_name) @@ -350,6 +366,8 @@ static int add_memory_block(unsigned long node_id, struct mem_section *section, ret = mem_create_simple_file(mem, state); if (!ret) ret = mem_create_simple_file(mem, phys_device); + if (!ret) + ret = mem_create_simple_file(mem, removable); return ret; } @@ -394,6 +412,7 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section, mem_remove_simple_file(mem, phys_index); mem_remove_simple_file(mem, state); mem_remove_simple_file(mem, phys_device); + mem_remove_simple_file(mem, removable); unregister_memory(mem, section); return 0; diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 3628e5088f64..763ba81fc0f0 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -199,6 +199,18 @@ extern int walk_memory_resource(unsigned long start_pfn, unsigned long nr_pages, void *arg, int (*func)(unsigned long, unsigned long, void *)); +#ifdef CONFIG_MEMORY_HOTREMOVE + +extern int is_mem_section_removable(unsigned long pfn, unsigned long nr_pages); + +#else +static inline int is_mem_section_removable(unsigned long pfn, + unsigned long nr_pages) +{ + return 0; +} +#endif /* CONFIG_MEMORY_HOTREMOVE */ + extern int add_memory(int nid, u64 start, u64 size); extern int arch_add_memory(int nid, u64 start, u64 size); extern int remove_memory(u64 start, u64 size); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 93aba78dc8b6..89fee2dcb039 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -522,6 +522,66 @@ error: EXPORT_SYMBOL_GPL(add_memory); #ifdef CONFIG_MEMORY_HOTREMOVE +/* + * A free page on the buddy free lists (not the per-cpu lists) has PageBuddy + * set and the size of the free page is given by page_order(). Using this, + * the function determines if the pageblock contains only free pages. + * Due to buddy contraints, a free page at least the size of a pageblock will + * be located at the start of the pageblock + */ +static inline int pageblock_free(struct page *page) +{ + return PageBuddy(page) && page_order(page) >= pageblock_order; +} + +/* Return the start of the next active pageblock after a given page */ +static struct page *next_active_pageblock(struct page *page) +{ + int pageblocks_stride; + + /* Ensure the starting page is pageblock-aligned */ + BUG_ON(page_to_pfn(page) & (pageblock_nr_pages - 1)); + + /* Move forward by at least 1 * pageblock_nr_pages */ + pageblocks_stride = 1; + + /* If the entire pageblock is free, move to the end of free page */ + if (pageblock_free(page)) + pageblocks_stride += page_order(page) - pageblock_order; + + return page + (pageblocks_stride * pageblock_nr_pages); +} + +/* Checks if this range of memory is likely to be hot-removable. */ +int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) +{ + int type; + struct page *page = pfn_to_page(start_pfn); + struct page *end_page = page + nr_pages; + + /* Check the starting page of each pageblock within the range */ + for (; page < end_page; page = next_active_pageblock(page)) { + type = get_pageblock_migratetype(page); + + /* + * A pageblock containing MOVABLE or free pages is considered + * removable + */ + if (type != MIGRATE_MOVABLE && !pageblock_free(page)) + return 0; + + /* + * A pageblock starting with a PageReserved page is not + * considered removable. + */ + if (PageReserved(page)) + return 0; + } + + /* All pageblocks in the memory block are likely to be hot-removable */ + return 1; +} + /* * Confirm all pages in a range [start, end) is belongs to the same zone. */ -- cgit v1.2.3 From 77437fd4e61f87cc94d9314baa5cbf50e3ccdf54 Mon Sep 17 00:00:00 2001 From: David Brownell Date: Wed, 23 Jul 2008 21:28:33 -0700 Subject: pm: boot time suspend selftest Boot-time test for system suspend states (STR or standby). The generic RTC framework triggers wakeup alarms, which are used to exit those states. - Measures some aspects of suspend time ... this uses "jiffies" until someone converts it to use a timebase that works properly even while timer IRQs are disabled. - Triggered by a command line parameter. By default nothing even vaguely troublesome will happen, but "test_suspend=mem" will give you a brief STR test during system boot. (Or you may need to use "test_suspend=standby" instead, if your hardware needs that.) This isn't without problems. It fires early enough during boot that for example both PCMCIA and MMC stacks have misbehaved. The workaround in those cases was to boot without such media cards inserted. [matthltc@us.ibm.com: fix compile failure in boot time suspend selftest] Signed-off-by: David Brownell Cc: Ingo Molnar Cc: Pavel Machek Cc: "Rafael J. Wysocki" Signed-off-by: Matt Helsley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 9 +- kernel/power/Kconfig | 11 ++ kernel/power/main.c | 194 +++++++++++++++++++++++++++++++++++- 3 files changed, 212 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 01a2992b5754..4d705713cabc 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -87,7 +87,8 @@ parameter is applicable: SH SuperH architecture is enabled. SMP The kernel is an SMP kernel. SPARC Sparc architecture is enabled. - SWSUSP Software suspend is enabled. + SWSUSP Software suspend (hibernation) is enabled. + SUSPEND System suspend states are enabled. TS Appropriate touchscreen support is enabled. USB USB support is enabled. USBHID USB Human Interface Device support is enabled. @@ -2123,6 +2124,12 @@ and is between 256 and 4096 characters. It is defined in the file tdfx= [HW,DRM] + test_suspend= [SUSPEND] + Specify "mem" (for Suspend-to-RAM) or "standby" (for + standby suspend) as the system sleep state to briefly + enter during system startup. The system is woken from + this state using a wakeup-capable RTC alarm. + thash_entries= [KNL,NET] Set number of hash buckets for TCP connection diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 59dfdf1e1d20..dcd165f92a88 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -94,6 +94,17 @@ config SUSPEND powered and thus its contents are preserved, such as the suspend-to-RAM state (e.g. the ACPI S3 state). +config PM_TEST_SUSPEND + bool "Test suspend/resume and wakealarm during bootup" + depends on SUSPEND && PM_DEBUG && RTC_LIB=y + ---help--- + This option will let you suspend your machine during bootup, and + make it wake up a few seconds later using an RTC wakeup alarm. + Enable this with a kernel parameter like "test_suspend=mem". + + You probably want to have your system's RTC driver statically + linked, ensuring that it's available when this test runs. + config SUSPEND_FREEZER bool "Enable freezer for suspend to RAM/standby" \ if ARCH_WANTS_FREEZER_CONTROL || BROKEN diff --git a/kernel/power/main.c b/kernel/power/main.c index 3398f4651aa1..95bff23ecdaa 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -132,6 +132,61 @@ static inline int suspend_test(int level) { return 0; } #ifdef CONFIG_SUSPEND +#ifdef CONFIG_PM_TEST_SUSPEND + +/* + * We test the system suspend code by setting an RTC wakealarm a short + * time in the future, then suspending. Suspending the devices won't + * normally take long ... some systems only need a few milliseconds. + * + * The time it takes is system-specific though, so when we test this + * during system bootup we allow a LOT of time. + */ +#define TEST_SUSPEND_SECONDS 5 + +static unsigned long suspend_test_start_time; + +static void suspend_test_start(void) +{ + /* FIXME Use better timebase than "jiffies", ideally a clocksource. + * What we want is a hardware counter that will work correctly even + * during the irqs-are-off stages of the suspend/resume cycle... + */ + suspend_test_start_time = jiffies; +} + +static void suspend_test_finish(const char *label) +{ + long nj = jiffies - suspend_test_start_time; + unsigned msec; + + msec = jiffies_to_msecs(abs(nj)); + pr_info("PM: %s took %d.%03d seconds\n", label, + msec / 1000, msec % 1000); + + /* Warning on suspend means the RTC alarm period needs to be + * larger -- the system was sooo slooowwww to suspend that the + * alarm (should have) fired before the system went to sleep! + * + * Warning on either suspend or resume also means the system + * has some performance issues. The stack dump of a WARN_ON + * is more likely to get the right attention than a printk... + */ + WARN_ON(msec > (TEST_SUSPEND_SECONDS * 1000)); +} + +#else + +static void suspend_test_start(void) +{ +} + +static void suspend_test_finish(const char *label) +{ +} + +#endif + /* This is just an arbitrary number */ #define FREE_PAGE_NUMBER (100) @@ -266,12 +321,13 @@ int suspend_devices_and_enter(suspend_state_t state) goto Close; } suspend_console(); + suspend_test_start(); error = device_suspend(PMSG_SUSPEND); if (error) { printk(KERN_ERR "PM: Some devices failed to suspend\n"); goto Recover_platform; } - + suspend_test_finish("suspend devices"); if (suspend_test(TEST_DEVICES)) goto Recover_platform; @@ -293,7 +349,9 @@ int suspend_devices_and_enter(suspend_state_t state) if (suspend_ops->finish) suspend_ops->finish(); Resume_devices: + suspend_test_start(); device_resume(PMSG_RESUME); + suspend_test_finish("resume devices"); resume_console(); Close: if (suspend_ops->end) @@ -521,3 +579,137 @@ static int __init pm_init(void) } core_initcall(pm_init); + + +#ifdef CONFIG_PM_TEST_SUSPEND + +#include + +/* + * To test system suspend, we need a hands-off mechanism to resume the + * system. RTCs wake alarms are a common self-contained mechanism. + */ + +static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state) +{ + static char err_readtime[] __initdata = + KERN_ERR "PM: can't read %s time, err %d\n"; + static char err_wakealarm [] __initdata = + KERN_ERR "PM: can't set %s wakealarm, err %d\n"; + static char err_suspend[] __initdata = + KERN_ERR "PM: suspend test failed, error %d\n"; + static char info_test[] __initdata = + KERN_INFO "PM: test RTC wakeup from '%s' suspend\n"; + + unsigned long now; + struct rtc_wkalrm alm; + int status; + + /* this may fail if the RTC hasn't been initialized */ + status = rtc_read_time(rtc, &alm.time); + if (status < 0) { + printk(err_readtime, rtc->dev.bus_id, status); + return; + } + rtc_tm_to_time(&alm.time, &now); + + memset(&alm, 0, sizeof alm); + rtc_time_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time); + alm.enabled = true; + + status = rtc_set_alarm(rtc, &alm); + if (status < 0) { + printk(err_wakealarm, rtc->dev.bus_id, status); + return; + } + + if (state == PM_SUSPEND_MEM) { + printk(info_test, pm_states[state]); + status = pm_suspend(state); + if (status == -ENODEV) + state = PM_SUSPEND_STANDBY; + } + if (state == PM_SUSPEND_STANDBY) { + printk(info_test, pm_states[state]); + status = pm_suspend(state); + } + if (status < 0) + printk(err_suspend, status); +} + +static int __init has_wakealarm(struct device *dev, void *name_ptr) +{ + struct rtc_device *candidate = to_rtc_device(dev); + + if (!candidate->ops->set_alarm) + return 0; + if (!device_may_wakeup(candidate->dev.parent)) + return 0; + + *(char **)name_ptr = dev->bus_id; + return 1; +} + +/* + * Kernel options like "test_suspend=mem" force suspend/resume sanity tests + * at startup time. They're normally disabled, for faster boot and because + * we can't know which states really work on this particular system. + */ +static suspend_state_t test_state __initdata = PM_SUSPEND_ON; + +static char warn_bad_state[] __initdata = + KERN_WARNING "PM: can't test '%s' suspend state\n"; + +static int __init setup_test_suspend(char *value) +{ + unsigned i; + + /* "=mem" ==> "mem" */ + value++; + for (i = 0; i < PM_SUSPEND_MAX; i++) { + if (!pm_states[i]) + continue; + if (strcmp(pm_states[i], value) != 0) + continue; + test_state = (__force suspend_state_t) i; + return 0; + } + printk(warn_bad_state, value); + return 0; +} +__setup("test_suspend", setup_test_suspend); + +static int __init test_suspend(void) +{ + static char warn_no_rtc[] __initdata = + KERN_WARNING "PM: no wakealarm-capable RTC driver is ready\n"; + + char *pony = NULL; + struct rtc_device *rtc = NULL; + + /* PM is initialized by now; is that state testable? */ + if (test_state == PM_SUSPEND_ON) + goto done; + if (!valid_state(test_state)) { + printk(warn_bad_state, pm_states[test_state]); + goto done; + } + + /* RTCs have initialized by now too ... can we use one? */ + class_find_device(rtc_class, NULL, &pony, has_wakealarm); + if (pony) + rtc = rtc_class_open(pony); + if (!rtc) { + printk(warn_no_rtc); + goto done; + } + + /* go for it */ + test_wakealarm(rtc, test_state); + rtc_class_close(rtc); +done: + return 0; +} +late_initcall(test_suspend); + +#endif /* CONFIG_PM_TEST_SUSPEND */ -- cgit v1.2.3 From 40b4ac33b4d1bdd5cbeb2241be2399c550fa3696 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 23 Jul 2008 21:28:36 -0700 Subject: pm: remove obsolete piece of PM documentation Remove some obsolete PM documentation. The majority of contents of Documentation/power/pm.txt are outdated. Remove the outdated parts of this file and move the rest to Documentation/power/apm-acpi.txt . Update the index in Documentation/power/ as appropriate. Signed-off-by: Rafael J. Wysocki Acked-by: Pavel Machek Acked-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/power/00-INDEX | 4 +- Documentation/power/apm-acpi.txt | 32 +++++ Documentation/power/pm.txt | 257 --------------------------------------- 3 files changed, 34 insertions(+), 259 deletions(-) create mode 100644 Documentation/power/apm-acpi.txt delete mode 100644 Documentation/power/pm.txt (limited to 'Documentation') diff --git a/Documentation/power/00-INDEX b/Documentation/power/00-INDEX index a55d7f1c836d..fb742c213c9e 100644 --- a/Documentation/power/00-INDEX +++ b/Documentation/power/00-INDEX @@ -1,5 +1,7 @@ 00-INDEX - This file +apm-acpi.txt + - basic info about the APM and ACPI support. basic-pm-debugging.txt - Debugging suspend and resume devices.txt @@ -14,8 +16,6 @@ notifiers.txt - Registering suspend notifiers in device drivers pci.txt - How the PCI Subsystem Does Power Management -pm.txt - - info on Linux power management support. pm_qos_interface.txt - info on Linux PM Quality of Service interface power_supply_class.txt diff --git a/Documentation/power/apm-acpi.txt b/Documentation/power/apm-acpi.txt new file mode 100644 index 000000000000..1bd799dc17e8 --- /dev/null +++ b/Documentation/power/apm-acpi.txt @@ -0,0 +1,32 @@ +APM or ACPI? +------------ +If you have a relatively recent x86 mobile, desktop, or server system, +odds are it supports either Advanced Power Management (APM) or +Advanced Configuration and Power Interface (ACPI). ACPI is the newer +of the two technologies and puts power management in the hands of the +operating system, allowing for more intelligent power management than +is possible with BIOS controlled APM. + +The best way to determine which, if either, your system supports is to +build a kernel with both ACPI and APM enabled (as of 2.3.x ACPI is +enabled by default). If a working ACPI implementation is found, the +ACPI driver will override and disable APM, otherwise the APM driver +will be used. + +No, sorry, you cannot have both ACPI and APM enabled and running at +once. Some people with broken ACPI or broken APM implementations +would like to use both to get a full set of working features, but you +simply cannot mix and match the two. Only one power management +interface can be in control of the machine at once. Think about it.. + +User-space Daemons +------------------ +Both APM and ACPI rely on user-space daemons, apmd and acpid +respectively, to be completely functional. Obtain both of these +daemons from your Linux distribution or from the Internet (see below) +and be sure that they are started sometime in the system boot process. +Go ahead and start both. If ACPI or APM is not available on your +system the associated daemon will exit gracefully. + + apmd: http://worldvisions.ca/~apenwarr/apmd/ + acpid: http://acpid.sf.net/ diff --git a/Documentation/power/pm.txt b/Documentation/power/pm.txt deleted file mode 100644 index be841507e43f..000000000000 --- a/Documentation/power/pm.txt +++ /dev/null @@ -1,257 +0,0 @@ - Linux Power Management Support - -This document briefly describes how to use power management with your -Linux system and how to add power management support to Linux drivers. - -APM or ACPI? ------------- -If you have a relatively recent x86 mobile, desktop, or server system, -odds are it supports either Advanced Power Management (APM) or -Advanced Configuration and Power Interface (ACPI). ACPI is the newer -of the two technologies and puts power management in the hands of the -operating system, allowing for more intelligent power management than -is possible with BIOS controlled APM. - -The best way to determine which, if either, your system supports is to -build a kernel with both ACPI and APM enabled (as of 2.3.x ACPI is -enabled by default). If a working ACPI implementation is found, the -ACPI driver will override and disable APM, otherwise the APM driver -will be used. - -No, sorry, you cannot have both ACPI and APM enabled and running at -once. Some people with broken ACPI or broken APM implementations -would like to use both to get a full set of working features, but you -simply cannot mix and match the two. Only one power management -interface can be in control of the machine at once. Think about it.. - -User-space Daemons ------------------- -Both APM and ACPI rely on user-space daemons, apmd and acpid -respectively, to be completely functional. Obtain both of these -daemons from your Linux distribution or from the Internet (see below) -and be sure that they are started sometime in the system boot process. -Go ahead and start both. If ACPI or APM is not available on your -system the associated daemon will exit gracefully. - - apmd: http://worldvisions.ca/~apenwarr/apmd/ - acpid: http://acpid.sf.net/ - -Driver Interface -- OBSOLETE, DO NOT USE! -----------------************************* - -Note: pm_register(), pm_access(), pm_dev_idle() and friends are -obsolete. Please do not use them. Instead you should properly hook -your driver into the driver model, and use its suspend()/resume() -callbacks to do this kind of stuff. - -If you are writing a new driver or maintaining an old driver, it -should include power management support. Without power management -support, a single driver may prevent a system with power management -capabilities from ever being able to suspend (safely). - -Overview: -1) Register each instance of a device with "pm_register" -2) Call "pm_access" before accessing the hardware. - (this will ensure that the hardware is awake and ready) -3) Your "pm_callback" is called before going into a - suspend state (ACPI D1-D3) or after resuming (ACPI D0) - from a suspend. -4) Call "pm_dev_idle" when the device is not being used - (optional but will improve device idle detection) -5) When unloaded, unregister the device with "pm_unregister" - -/* - * Description: Register a device with the power-management subsystem - * - * Parameters: - * type - device type (PCI device, system device, ...) - * id - instance number or unique identifier - * cback - request handler callback (suspend, resume, ...) - * - * Returns: Registered PM device or NULL on error - * - * Examples: - * dev = pm_register(PM_SYS_DEV, PM_SYS_VGA, vga_callback); - * - * struct pci_dev *pci_dev = pci_find_dev(...); - * dev = pm_register(PM_PCI_DEV, PM_PCI_ID(pci_dev), callback); - */ -struct pm_dev *pm_register(pm_dev_t type, unsigned long id, pm_callback cback); - -/* - * Description: Unregister a device with the power management subsystem - * - * Parameters: - * dev - PM device previously returned from pm_register - */ -void pm_unregister(struct pm_dev *dev); - -/* - * Description: Unregister all devices with a matching callback function - * - * Parameters: - * cback - previously registered request callback - * - * Notes: Provided for easier porting from old APM interface - */ -void pm_unregister_all(pm_callback cback); - -/* - * Power management request callback - * - * Parameters: - * dev - PM device previously returned from pm_register - * rqst - request type - * data - data, if any, associated with the request - * - * Returns: 0 if the request is successful - * EINVAL if the request is not supported - * EBUSY if the device is now busy and cannot handle the request - * ENOMEM if the device was unable to handle the request due to memory - * - * Details: The device request callback will be called before the - * device/system enters a suspend state (ACPI D1-D3) or - * or after the device/system resumes from suspend (ACPI D0). - * For PM_SUSPEND, the ACPI D-state being entered is passed - * as the "data" argument to the callback. The device - * driver should save (PM_SUSPEND) or restore (PM_RESUME) - * device context when the request callback is called. - * - * Once a driver returns 0 (success) from a suspend - * request, it should not process any further requests or - * access the device hardware until a call to "pm_access" is made. - */ -typedef int (*pm_callback)(struct pm_dev *dev, pm_request_t rqst, void *data); - -Driver Details --------------- -This is just a quick Q&A as a stopgap until a real driver writers' -power management guide is available. - -Q: When is a device suspended? - -Devices can be suspended based on direct user request (eg. laptop lid -closes), system power policy (eg. sleep after 30 minutes of console -inactivity), or device power policy (eg. power down device after 5 -minutes of inactivity) - -Q: Must a driver honor a suspend request? - -No, a driver can return -EBUSY from a suspend request and this -will stop the system from suspending. When a suspend request -fails, all suspended devices are resumed and the system continues -to run. Suspend can be retried at a later time. - -Q: Can the driver block suspend/resume requests? - -Yes, a driver can delay its return from a suspend or resume -request until the device is ready to handle requests. It -is advantageous to return as quickly as possible from a -request as suspend/resume are done serially. - -Q: What context is a suspend/resume initiated from? - -A suspend or resume is initiated from a kernel thread context. -It is safe to block, allocate memory, initiate requests -or anything else you can do within the kernel. - -Q: Will requests continue to arrive after a suspend? - -Possibly. It is the driver's responsibility to queue(*), -fail, or drop any requests that arrive after returning -success to a suspend request. It is important that the -driver not access its device until after it receives -a resume request as the device's bus may no longer -be active. - -(*) If a driver queues requests for processing after - resume be aware that the device, network, etc. - might be in a different state than at suspend time. - It's probably better to drop requests unless - the driver is a storage device. - -Q: Do I have to manage bus-specific power management registers - -No. It is the responsibility of the bus driver to manage -PCI, USB, etc. power management registers. The bus driver -or the power management subsystem will also enable any -wake-on functionality that the device has. - -Q: So, really, what do I need to do to support suspend/resume? - -You need to save any device context that would -be lost if the device was powered off and then restore -it at resume time. When ACPI is active, there are -three levels of device suspend states; D1, D2, and D3. -(The suspend state is passed as the "data" argument -to the device callback.) With D3, the device is powered -off and loses all context, D1 and D2 are shallower power -states and require less device context to be saved. To -play it safe, just save everything at suspend and restore -everything at resume. - -Q: Where do I store device context for suspend? - -Anywhere in memory, kmalloc a buffer or store it -in the device descriptor. You are guaranteed that the -contents of memory will be restored and accessible -before resume, even when the system suspends to disk. - -Q: What do I need to do for ACPI vs. APM vs. etc? - -Drivers need not be aware of the specific power management -technology that is active. They just need to be aware -of when the overlying power management system requests -that they suspend or resume. - -Q: What about device dependencies? - -When a driver registers a device, the power management -subsystem uses the information provided to build a -tree of device dependencies (eg. USB device X is on -USB controller Y which is on PCI bus Z) When power -management wants to suspend a device, it first sends -a suspend request to its driver, then the bus driver, -and so on up to the system bus. Device resumes -proceed in the opposite direction. - -Q: Who do I contact for additional information about - enabling power management for my specific driver/device? - -ACPI Development mailing list: linux-acpi@vger.kernel.org - -System Interface -- OBSOLETE, DO NOT USE! -----------------************************* -If you are providing new power management support to Linux (ie. -adding support for something like APM or ACPI), you should -communicate with drivers through the existing generic power -management interface. - -/* - * Send a request to all devices - * - * Parameters: - * rqst - request type - * data - data, if any, associated with the request - * - * Returns: 0 if the request is successful - * See "pm_callback" return for errors - * - * Details: Walk list of registered devices and call pm_send - * for each until complete or an error is encountered. - * If an error is encountered for a suspend request, - * return all devices to the state they were in before - * the suspend request. - */ -int pm_send_all(pm_request_t rqst, void *data); - -/* - * Find a matching device - * - * Parameters: - * type - device type (PCI device, system device, or 0 to match all devices) - * from - previous match or NULL to start from the beginning - * - * Returns: Matching device or NULL if none found - */ -struct pm_dev *pm_find(pm_dev_t type, struct pm_dev *from); -- cgit v1.2.3 From bdfe6b7c681669148dae4db27eb24ee5408ba371 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 23 Jul 2008 21:28:41 -0700 Subject: pm: acpi hibernation: utilize hardware signature ACPI defines a hardware signature. BIOS calculates the signature according to hardware configure and if hardware changes while hibernated, the signature will change. In that case, S4 resume should fail. Still, there may be systems on which this mechanism does not work correctly, so it is better to provide a workaround for them. For this reason, add a new switch to the acpi_sleep= command line argument allowing one to disable hardware signature checking. [shaohua.li@intel.com: build fix] Signed-off-by: Shaohua Li Signed-off-by: Rafael J. Wysocki Cc: Andi Kleen Cc: Len Brown Acked-by: Pavel Machek Cc: Cc: Shaohua Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 4 +++- arch/x86/kernel/acpi/sleep.c | 4 ++++ drivers/acpi/sleep/main.c | 22 ++++++++++++++++++++++ include/linux/acpi.h | 1 + 4 files changed, 30 insertions(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 4d705713cabc..497a98dafdaa 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -148,10 +148,12 @@ and is between 256 and 4096 characters. It is defined in the file default: 0 acpi_sleep= [HW,ACPI] Sleep options - Format: { s3_bios, s3_mode, s3_beep, old_ordering } + Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig, old_ordering } See Documentation/power/video.txt for s3_bios and s3_mode. s3_beep is for debugging; it makes the PC's speaker beep as soon as the kernel's real-mode entry point is called. + s4_nohwsig prevents ACPI hardware signature from being + used during resume from hibernation. old_ordering causes the ACPI 1.0 ordering of the _PTS control method, wrt putting devices into low power states, to be enforced (the ACPI 2.0 ordering of _PTS is diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index a3ddad18aaa3..fa2161d5003b 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -150,6 +150,10 @@ static int __init acpi_sleep_setup(char *str) acpi_realmode_flags |= 2; if (strncmp(str, "s3_beep", 7) == 0) acpi_realmode_flags |= 4; +#ifdef CONFIG_HIBERNATION + if (strncmp(str, "s4_nohwsig", 10) == 0) + acpi_no_s4_hw_signature(); +#endif if (strncmp(str, "old_ordering", 12) == 0) acpi_old_suspend_ordering(); str = strchr(str, ','); diff --git a/drivers/acpi/sleep/main.c b/drivers/acpi/sleep/main.c index 0489a7d1d42c..313507accf18 100644 --- a/drivers/acpi/sleep/main.c +++ b/drivers/acpi/sleep/main.c @@ -283,6 +283,15 @@ static struct platform_suspend_ops acpi_suspend_ops_old = { #endif /* CONFIG_SUSPEND */ #ifdef CONFIG_HIBERNATION +static unsigned long s4_hardware_signature; +static struct acpi_table_facs *facs; +static bool nosigcheck; + +void __init acpi_no_s4_hw_signature(void) +{ + nosigcheck = true; +} + static int acpi_hibernation_begin(void) { acpi_target_sleep_state = ACPI_STATE_S4; @@ -316,6 +325,12 @@ static void acpi_hibernation_leave(void) acpi_enable(); /* Reprogram control registers and execute _BFS */ acpi_leave_sleep_state_prep(ACPI_STATE_S4); + /* Check the hardware signature */ + if (facs && s4_hardware_signature != facs->hardware_signature) { + printk(KERN_EMERG "ACPI: Hardware changed while hibernated, " + "cannot resume!\n"); + panic("ACPI S4 hardware signature mismatch"); + } } static void acpi_pm_enable_gpes(void) @@ -544,6 +559,13 @@ int __init acpi_sleep_init(void) &acpi_hibernation_ops_old : &acpi_hibernation_ops); sleep_states[ACPI_STATE_S4] = 1; printk(" S4"); + if (!nosigcheck) { + acpi_get_table_by_index(ACPI_TABLE_INDEX_FACS, + (struct acpi_table_header **)&facs); + if (facs) + s4_hardware_signature = + facs->hardware_signature; + } } #endif status = acpi_get_sleep_type_data(ACPI_STATE_S5, &type_a, &type_b); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index a17177639376..702f79dad16a 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -236,6 +236,7 @@ int acpi_check_mem_region(resource_size_t start, resource_size_t n, const char *name); #ifdef CONFIG_PM_SLEEP +void __init acpi_no_s4_hw_signature(void); void __init acpi_old_suspend_ordering(void); #endif /* CONFIG_PM_SLEEP */ #else /* CONFIG_ACPI */ -- cgit v1.2.3 From a90ed92ed852a3d4b8a6f20b10bba771997f5ede Mon Sep 17 00:00:00 2001 From: Krzysztof Helt Date: Wed, 23 Jul 2008 21:31:22 -0700 Subject: tridentfb: documentation update Make the tridentfb documentation closer to current state of the tridentfb driver. Fix also some formatting. Signed-off-by: Krzysztof Helt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/fb/tridentfb.txt | 46 ++++++++++++++++++++++++++++-------------- 1 file changed, 31 insertions(+), 15 deletions(-) (limited to 'Documentation') diff --git a/Documentation/fb/tridentfb.txt b/Documentation/fb/tridentfb.txt index 8a6c8a43e6a3..45d9de5b13a3 100644 --- a/Documentation/fb/tridentfb.txt +++ b/Documentation/fb/tridentfb.txt @@ -3,11 +3,25 @@ Tridentfb is a framebuffer driver for some Trident chip based cards. The following list of chips is thought to be supported although not all are tested: -those from the Image series with Cyber in their names - accelerated -those with Blade in their names (Blade3D,CyberBlade...) - accelerated -the newer CyberBladeXP family - nonaccelerated - -Only PCI/AGP based cards are supported, none of the older Tridents. +those from the TGUI series 9440/96XX and with Cyber in their names +those from the Image series and with Cyber in their names +those with Blade in their names (Blade3D,CyberBlade...) +the newer CyberBladeXP family + +All families are accelerated. Only PCI/AGP based cards are supported, +none of the older Tridents. +The driver supports 8, 16 and 32 bits per pixel depths. +The TGUI family requires a line length to be power of 2 if acceleration +is enabled. This means that range of possible resolutions and bpp is +limited comparing to the range if acceleration is disabled (see list +of parameters below). + +Known bugs: +1. The driver randomly locks up on 3DImage975 chip with acceleration + enabled. The same happens in X11 (Xorg). +2. The ramdac speeds require some more fine tuning. It is possible to + switch resolution which the chip does not support at some depths for + older chips. How to use it? ============== @@ -17,12 +31,11 @@ video=tridentfb The parameters for tridentfb are concatenated with a ':' as in this example. -video=tridentfb:800x600,bpp=16,noaccel +video=tridentfb:800x600-16@75,noaccel The second level parameters that tridentfb understands are: noaccel - turns off acceleration (when it doesn't work for your card) -accel - force text acceleration (for boards which by default are noacceled) fp - use flat panel related stuff crt - assume monitor is present instead of fp @@ -31,21 +44,24 @@ center - for flat panels and resolutions smaller than native size center the image, otherwise use stretch -memsize - integer value in Kb, use if your card's memory size is misdetected. +memsize - integer value in KB, use if your card's memory size is misdetected. look at the driver output to see what it says when initializing. -memdiff - integer value in Kb,should be nonzero if your card reports - more memory than it actually has.For instance mine is 192K less than + +memdiff - integer value in KB, should be nonzero if your card reports + more memory than it actually has. For instance mine is 192K less than detection says in all three BIOS selectable situations 2M, 4M, 8M. Only use if your video memory is taken from main memory hence of - configurable size.Otherwise use memsize. - If in some modes which barely fit the memory you see garbage at the bottom - this might help by not letting change to that mode anymore. + configurable size. Otherwise use memsize. + If in some modes which barely fit the memory you see garbage + at the bottom this might help by not letting change to that mode + anymore. nativex - the width in pixels of the flat panel.If you know it (usually 1024 800 or 1280) and it is not what the driver seems to detect use it. -bpp - bits per pixel (8,16 or 32) -mode - a mode name like 800x600 (as described in Documentation/fb/modedb.txt) +bpp - bits per pixel (8,16 or 32) +mode - a mode name like 800x600-8@75 as described in + Documentation/fb/modedb.txt Using insane values for the above parameters will probably result in driver misbehaviour so take care(for instance memsize=12345678 or memdiff=23784 or -- cgit v1.2.3 From 4a25e41831ee851c1365d8b41decc22493b18e6d Mon Sep 17 00:00:00 2001 From: Nobuhiro Iwamatsu Date: Wed, 23 Jul 2008 21:31:46 -0700 Subject: video: sh7760fb: SH7760/SH7763 LCDC framebuffer driver Framebuffer driver for the SH7760/SH7763 integrated LCD controller. Signed-off-by: Manuel Lauss Signed-off-by: Nobuhiro Iwamatsu Reviewed-by: Paul Mundt Cc: Krzysztof Helt Cc: "Antonino A. Daplas" Cc: Siegfried Schaefer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/fb/sh7760fb.txt | 131 +++++++++ drivers/video/Kconfig | 13 + drivers/video/Makefile | 1 + drivers/video/sh7760fb.c | 658 ++++++++++++++++++++++++++++++++++++++++++ include/asm-sh/sh7760fb.h | 197 +++++++++++++ 5 files changed, 1000 insertions(+) create mode 100644 Documentation/fb/sh7760fb.txt create mode 100644 drivers/video/sh7760fb.c create mode 100644 include/asm-sh/sh7760fb.h (limited to 'Documentation') diff --git a/Documentation/fb/sh7760fb.txt b/Documentation/fb/sh7760fb.txt new file mode 100644 index 000000000000..c87bfe5c630a --- /dev/null +++ b/Documentation/fb/sh7760fb.txt @@ -0,0 +1,131 @@ +SH7760/SH7763 integrated LCDC Framebuffer driver +================================================ + +0. Overwiew +----------- +The SH7760/SH7763 have an integrated LCD Display controller (LCDC) which +supports (in theory) resolutions ranging from 1x1 to 1024x1024, +with color depths ranging from 1 to 16 bits, on STN, DSTN and TFT Panels. + +Caveats: +* Framebuffer memory must be a large chunk allocated at the top + of Area3 (HW requirement). Because of this requirement you should NOT + make the driver a module since at runtime it may become impossible to + get a large enough contiguous chunk of memory. + +* The driver does not support changing resolution while loaded + (displays aren't hotpluggable anyway) + +* Heavy flickering may be observed + a) if you're using 15/16bit color modes at >= 640x480 px resolutions, + b) during PCMCIA (or any other slow bus) activity. + +* Rotation works only 90degress clockwise, and only if horizontal + resolution is <= 320 pixels. + +files: drivers/video/sh7760fb.c + include/asm-sh/sh7760fb.h + Documentation/fb/sh7760fb.txt + +1. Platform setup +----------------- +SH7760: + Video data is fetched via the DMABRG DMA engine, so you have to + configure the SH DMAC for DMABRG mode (write 0x94808080 to the + DMARSRA register somewhere at boot). + + PFC registers PCCR and PCDR must be set to peripheral mode. + (write zeros to both). + +The driver does NOT do the above for you since board setup is, well, job +of the board setup code. + +2. Panel definitions +-------------------- +The LCDC must explicitly be told about the type of LCD panel +attached. Data must be wrapped in a "struct sh7760fb_platdata" and +passed to the driver as platform_data. + +Suggest you take a closer look at the SH7760 Manual, Section 30. +(http://documentation.renesas.com/eng/products/mpumcu/e602291_sh7760.pdf) + +The following code illustrates what needs to be done to +get the framebuffer working on a 640x480 TFT: + +====================== cut here ====================================== + +#include +#include + +/* + * NEC NL6440bc26-01 640x480 TFT + * dotclock 25175 kHz + * Xres 640 Yres 480 + * Htotal 800 Vtotal 525 + * HsynStart 656 VsynStart 490 + * HsynLenn 30 VsynLenn 2 + * + * The linux framebuffer layer does not use the syncstart/synclen + * values but right/left/upper/lower margin values. The comments + * for the x_margin explain how to calculate those from given + * panel sync timings. + */ +static struct fb_videomode nl6448bc26 = { + .name = "NL6448BC26", + .refresh = 60, + .xres = 640, + .yres = 480, + .pixclock = 39683, /* in picoseconds! */ + .hsync_len = 30, + .vsync_len = 2, + .left_margin = 114, /* HTOT - (HSYNSLEN + HSYNSTART) */ + .right_margin = 16, /* HSYNSTART - XRES */ + .upper_margin = 33, /* VTOT - (VSYNLEN + VSYNSTART) */ + .lower_margin = 10, /* VSYNSTART - YRES */ + .sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, + .vmode = FB_VMODE_NONINTERLACED, + .flag = 0, +}; + +static struct sh7760fb_platdata sh7760fb_nl6448 = { + .def_mode = &nl6448bc26, + .ldmtr = LDMTR_TFT_COLOR_16, /* 16bit TFT panel */ + .lddfr = LDDFR_8BPP, /* we want 8bit output */ + .ldpmmr = 0x0070, + .ldpspr = 0x0500, + .ldaclnr = 0, + .ldickr = LDICKR_CLKSRC(LCDC_CLKSRC_EXTERNAL) | + LDICKR_CLKDIV(1), + .rotate = 0, + .novsync = 1, + .blank = NULL, +}; + +/* SH7760: + * 0xFE300800: 256 * 4byte xRGB palette ram + * 0xFE300C00: 42 bytes ctrl registers + */ +static struct resource sh7760_lcdc_res[] = { + [0] = { + .start = 0xFE300800, + .end = 0xFE300CFF, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = 65, + .end = 65, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device sh7760_lcdc_dev = { + .dev = { + .platform_data = &sh7760fb_nl6448, + }, + .name = "sh7760-lcdc", + .id = -1, + .resource = sh7760_lcdc_res, + .num_resources = ARRAY_SIZE(sh7760_lcdc_res), +}; + +====================== cut here ====================================== diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig index c1b7db843411..70d135e0cc47 100644 --- a/drivers/video/Kconfig +++ b/drivers/video/Kconfig @@ -1991,6 +1991,19 @@ config FB_COBALT tristate "Cobalt server LCD frame buffer support" depends on FB && MIPS_COBALT +config FB_SH7760 + bool "SH7760/SH7763 LCDC support" + depends on FB && (CPU_SUBTYPE_SH7760 || CPU_SUBTYPE_SH7763) + select FB_CFB_FILLRECT + select FB_CFB_COPYAREA + select FB_CFB_IMAGEBLIT + help + Support for the SH7760/SH7763 integrated (D)STN/TFT LCD Controller. + Supports display resolutions up to 1024x1024 pixel, grayscale and + color operation, with depths ranging from 1 bpp to 8 bpp monochrome + and 8, 15 or 16 bpp color; 90 degrees clockwise display rotation for + panels <= 320 pixel horizontal resolution. + config FB_VIRTUAL tristate "Virtual Frame Buffer support (ONLY FOR TESTING!)" depends on FB diff --git a/drivers/video/Makefile b/drivers/video/Makefile index 358032597757..0ebc1bfd2514 100644 --- a/drivers/video/Makefile +++ b/drivers/video/Makefile @@ -106,6 +106,7 @@ obj-$(CONFIG_FB_PMAGB_B) += pmagb-b-fb.o obj-$(CONFIG_FB_MAXINE) += maxinefb.o obj-$(CONFIG_FB_METRONOME) += metronomefb.o obj-$(CONFIG_FB_S1D13XXX) += s1d13xxxfb.o +obj-$(CONFIG_FB_SH7760) += sh7760fb.o obj-$(CONFIG_FB_IMX) += imxfb.o obj-$(CONFIG_FB_S3C2410) += s3c2410fb.o obj-$(CONFIG_FB_FSL_DIU) += fsl-diu-fb.o diff --git a/drivers/video/sh7760fb.c b/drivers/video/sh7760fb.c new file mode 100644 index 000000000000..4d0e28c5790b --- /dev/null +++ b/drivers/video/sh7760fb.c @@ -0,0 +1,658 @@ +/* + * SH7760/SH7763 LCDC Framebuffer driver. + * + * (c) 2006-2008 MSC Vertriebsges.m.b.H., + * Manuel Lauss + * (c) 2008 Nobuhiro Iwamatsu + * + * 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. + * + * PLEASE HAVE A LOOK AT Documentation/fb/sh7760fb.txt! + * + * Thanks to Siegfried Schaefer + * for his original source and testing! + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +struct sh7760fb_par { + void __iomem *base; + int irq; + + struct sh7760fb_platdata *pd; /* display information */ + + dma_addr_t fbdma; /* physical address */ + + int rot; /* rotation enabled? */ + + u32 pseudo_palette[16]; + + struct platform_device *dev; + struct resource *ioarea; + struct completion vsync; /* vsync irq event */ +}; + +static irqreturn_t sh7760fb_irq(int irq, void *data) +{ + struct completion *c = data; + + complete(c); + + return IRQ_HANDLED; +} + +static void sh7760fb_wait_vsync(struct fb_info *info) +{ + struct sh7760fb_par *par = info->par; + + if (par->pd->novsync) + return; + + iowrite16(ioread16(par->base + LDINTR) & ~VINT_CHECK, + par->base + LDINTR); + + if (par->irq < 0) { + /* poll for vert. retrace: status bit is sticky */ + while (!(ioread16(par->base + LDINTR) & VINT_CHECK)) + cpu_relax(); + } else { + /* a "wait_for_irq_event(par->irq)" would be extremely nice */ + init_completion(&par->vsync); + enable_irq(par->irq); + wait_for_completion(&par->vsync); + disable_irq_nosync(par->irq); + } +} + +/* wait_for_lps - wait until power supply has reached a certain state. */ +static int wait_for_lps(struct sh7760fb_par *par, int val) +{ + int i = 100; + while (--i && ((ioread16(par->base + LDPMMR) & 3) != val)) + msleep(1); + + if (i <= 0) + return -ETIMEDOUT; + + return 0; +} + +/* en/disable the LCDC */ +static int sh7760fb_blank(int blank, struct fb_info *info) +{ + struct sh7760fb_par *par = info->par; + struct sh7760fb_platdata *pd = par->pd; + unsigned short cntr = ioread16(par->base + LDCNTR); + unsigned short intr = ioread16(par->base + LDINTR); + int lps; + + if (blank == FB_BLANK_UNBLANK) { + intr |= VINT_START; + cntr = LDCNTR_DON2 | LDCNTR_DON; + lps = 3; + } else { + intr &= ~VINT_START; + cntr = LDCNTR_DON2; + lps = 0; + } + + if (pd->blank) + pd->blank(blank); + + iowrite16(intr, par->base + LDINTR); + iowrite16(cntr, par->base + LDCNTR); + + return wait_for_lps(par, lps); +} + +/* set color registers */ +static int sh7760fb_setcmap(struct fb_cmap *cmap, struct fb_info *info) +{ + struct sh7760fb_par *par = info->par; + u32 s = cmap->start; + u32 l = cmap->len; + u16 *r = cmap->red; + u16 *g = cmap->green; + u16 *b = cmap->blue; + u32 col, tmo; + int ret; + + ret = 0; + + sh7760fb_wait_vsync(info); + + /* request palette access */ + iowrite16(LDPALCR_PALEN, par->base + LDPALCR); + + /* poll for access grant */ + tmo = 100; + while (!(ioread16(par->base + LDPALCR) & LDPALCR_PALS) && (--tmo)) + cpu_relax(); + + if (!tmo) { + ret = 1; + dev_dbg(info->dev, "no palette access!\n"); + goto out; + } + + while (l && (s < 256)) { + col = ((*r) & 0xff) << 16; + col |= ((*g) & 0xff) << 8; + col |= ((*b) & 0xff); + col &= SH7760FB_PALETTE_MASK; + + if (s < 16) + ((u32 *) (info->pseudo_palette))[s] = s; + + s++; + l--; + r++; + g++; + b++; + } +out: + iowrite16(0, par->base + LDPALCR); + return ret; +} + +static void encode_fix(struct fb_fix_screeninfo *fix, struct fb_info *info, + unsigned long stride) +{ + memset(fix, 0, sizeof(struct fb_fix_screeninfo)); + strcpy(fix->id, "sh7760-lcdc"); + + fix->smem_start = (unsigned long)info->screen_base; + fix->smem_len = info->screen_size; + + fix->line_length = stride; +} + +static int sh7760fb_get_color_info(struct device *dev, + u16 lddfr, int *bpp, int *gray) +{ + int lbpp, lgray; + + lgray = lbpp = 0; + + switch (lddfr & LDDFR_COLOR_MASK) { + case LDDFR_1BPP_MONO: + lgray = 1; + lbpp = 1; + break; + case LDDFR_2BPP_MONO: + lgray = 1; + lbpp = 2; + break; + case LDDFR_4BPP_MONO: + lgray = 1; + case LDDFR_4BPP: + lbpp = 4; + break; + case LDDFR_6BPP_MONO: + lgray = 1; + case LDDFR_8BPP: + lbpp = 8; + break; + case LDDFR_16BPP_RGB555: + case LDDFR_16BPP_RGB565: + lbpp = 16; + lgray = 0; + break; + default: + dev_dbg(dev, "unsupported LDDFR bit depth.\n"); + return -EINVAL; + } + + if (bpp) + *bpp = lbpp; + if (gray) + *gray = lgray; + + return 0; +} + +static int sh7760fb_check_var(struct fb_var_screeninfo *var, + struct fb_info *info) +{ + struct fb_fix_screeninfo *fix = &info->fix; + struct sh7760fb_par *par = info->par; + int ret, bpp; + + /* get color info from register value */ + ret = sh7760fb_get_color_info(info->dev, par->pd->lddfr, &bpp, NULL); + if (ret) + return ret; + + var->bits_per_pixel = bpp; + + if ((var->grayscale) && (var->bits_per_pixel == 1)) + fix->visual = FB_VISUAL_MONO10; + else if (var->bits_per_pixel >= 15) + fix->visual = FB_VISUAL_TRUECOLOR; + else + fix->visual = FB_VISUAL_PSEUDOCOLOR; + + /* TODO: add some more validation here */ + return 0; +} + +/* + * sh7760fb_set_par - set videomode. + * + * NOTE: The rotation, grayscale and DSTN codepaths are + * totally untested! + */ +static int sh7760fb_set_par(struct fb_info *info) +{ + struct sh7760fb_par *par = info->par; + struct fb_videomode *vm = par->pd->def_mode; + unsigned long sbase, dstn_off, ldsarl, stride; + unsigned short hsynp, hsynw, htcn, hdcn; + unsigned short vsynp, vsynw, vtln, vdln; + unsigned short lddfr, ldmtr; + int ret, bpp, gray; + + par->rot = par->pd->rotate; + + /* rotate only works with xres <= 320 */ + if (par->rot && (vm->xres > 320)) { + dev_dbg(info->dev, "rotation disabled due to display size\n"); + par->rot = 0; + } + + /* calculate LCDC reg vals from display parameters */ + hsynp = vm->right_margin + vm->xres; + hsynw = vm->hsync_len; + htcn = vm->left_margin + hsynp + hsynw; + hdcn = vm->xres; + vsynp = vm->lower_margin + vm->yres; + vsynw = vm->vsync_len; + vtln = vm->upper_margin + vsynp + vsynw; + vdln = vm->yres; + + /* get color info from register value */ + ret = sh7760fb_get_color_info(info->dev, par->pd->lddfr, &bpp, &gray); + if (ret) + return ret; + + dev_dbg(info->dev, "%dx%d %dbpp %s (orientation %s)\n", hdcn, + vdln, bpp, gray ? "grayscale" : "color", + par->rot ? "rotated" : "normal"); + +#ifdef CONFIG_CPU_LITTLE_ENDIAN + lddfr = par->pd->lddfr | (1 << 8); +#else + lddfr = par->pd->lddfr & ~(1 << 8); +#endif + + ldmtr = par->pd->ldmtr; + + if (!(vm->sync & FB_SYNC_HOR_HIGH_ACT)) + ldmtr |= LDMTR_CL1POL; + if (!(vm->sync & FB_SYNC_VERT_HIGH_ACT)) + ldmtr |= LDMTR_FLMPOL; + + /* shut down LCDC before changing display parameters */ + sh7760fb_blank(FB_BLANK_POWERDOWN, info); + + iowrite16(par->pd->ldickr, par->base + LDICKR); /* pixclock */ + iowrite16(ldmtr, par->base + LDMTR); /* polarities */ + iowrite16(lddfr, par->base + LDDFR); /* color/depth */ + iowrite16((par->rot ? 1 << 13 : 0), par->base + LDSMR); /* rotate */ + iowrite16(par->pd->ldpmmr, par->base + LDPMMR); /* Power Management */ + iowrite16(par->pd->ldpspr, par->base + LDPSPR); /* Power Supply Ctrl */ + + /* display resolution */ + iowrite16(((htcn >> 3) - 1) | (((hdcn >> 3) - 1) << 8), + par->base + LDHCNR); + iowrite16(vdln - 1, par->base + LDVDLNR); + iowrite16(vtln - 1, par->base + LDVTLNR); + /* h/v sync signals */ + iowrite16((vsynp - 1) | ((vsynw - 1) << 12), par->base + LDVSYNR); + iowrite16(((hsynp >> 3) - 1) | (((hsynw >> 3) - 1) << 12), + par->base + LDHSYNR); + /* AC modulation sig */ + iowrite16(par->pd->ldaclnr, par->base + LDACLNR); + + stride = (par->rot) ? vtln : hdcn; + if (!gray) + stride *= (bpp + 7) >> 3; + else { + if (bpp == 1) + stride >>= 3; + else if (bpp == 2) + stride >>= 2; + else if (bpp == 4) + stride >>= 1; + /* 6 bpp == 8 bpp */ + } + + /* if rotated, stride must be power of 2 */ + if (par->rot) { + unsigned long bit = 1 << 31; + while (bit) { + if (stride & bit) + break; + bit >>= 1; + } + if (stride & ~bit) + stride = bit << 1; /* not P-o-2, round up */ + } + iowrite16(stride, par->base + LDLAOR); + + /* set display mem start address */ + sbase = (unsigned long)par->fbdma; + if (par->rot) + sbase += (hdcn - 1) * stride; + + iowrite32(sbase, par->base + LDSARU); + + /* + * for DSTN need to set address for lower half. + * I (mlau) don't know which address to set it to, + * so I guessed at (stride * yres/2). + */ + if (((ldmtr & 0x003f) >= LDMTR_DSTN_MONO_8) && + ((ldmtr & 0x003f) <= LDMTR_DSTN_COLOR_16)) { + + dev_dbg(info->dev, " ***** DSTN untested! *****\n"); + + dstn_off = stride; + if (par->rot) + dstn_off *= hdcn >> 1; + else + dstn_off *= vdln >> 1; + + ldsarl = sbase + dstn_off; + } else + ldsarl = 0; + + iowrite32(ldsarl, par->base + LDSARL); /* mem for lower half of DSTN */ + + encode_fix(&info->fix, info, stride); + sh7760fb_check_var(&info->var, info); + + sh7760fb_blank(FB_BLANK_UNBLANK, info); /* panel on! */ + + dev_dbg(info->dev, "hdcn : %6d htcn : %6d\n", hdcn, htcn); + dev_dbg(info->dev, "hsynw : %6d hsynp : %6d\n", hsynw, hsynp); + dev_dbg(info->dev, "vdln : %6d vtln : %6d\n", vdln, vtln); + dev_dbg(info->dev, "vsynw : %6d vsynp : %6d\n", vsynw, vsynp); + dev_dbg(info->dev, "clksrc: %6d clkdiv: %6d\n", + (par->pd->ldickr >> 12) & 3, par->pd->ldickr & 0x1f); + dev_dbg(info->dev, "ldpmmr: 0x%04x ldpspr: 0x%04x\n", par->pd->ldpmmr, + par->pd->ldpspr); + dev_dbg(info->dev, "ldmtr : 0x%04x lddfr : 0x%04x\n", ldmtr, lddfr); + dev_dbg(info->dev, "ldlaor: %ld\n", stride); + dev_dbg(info->dev, "ldsaru: 0x%08lx ldsarl: 0x%08lx\n", sbase, ldsarl); + + return 0; +} + +static struct fb_ops sh7760fb_ops = { + .owner = THIS_MODULE, + .fb_blank = sh7760fb_blank, + .fb_check_var = sh7760fb_check_var, + .fb_setcmap = sh7760fb_setcmap, + .fb_set_par = sh7760fb_set_par, + .fb_fillrect = cfb_fillrect, + .fb_copyarea = cfb_copyarea, + .fb_imageblit = cfb_imageblit, +}; + +static void sh7760fb_free_mem(struct fb_info *info) +{ + struct sh7760fb_par *par = info->par; + + if (!info->screen_base) + return; + + dma_free_coherent(info->dev, info->screen_size, + info->screen_base, par->fbdma); + + par->fbdma = 0; + info->screen_base = NULL; + info->screen_size = 0; +} + +/* allocate the framebuffer memory. This memory must be in Area3, + * (dictated by the DMA engine) and contiguous, at a 512 byte boundary. + */ +static int sh7760fb_alloc_mem(struct fb_info *info) +{ + struct sh7760fb_par *par = info->par; + void *fbmem; + unsigned long vram; + int ret, bpp; + + if (info->screen_base) + return 0; + + /* get color info from register value */ + ret = sh7760fb_get_color_info(info->dev, par->pd->lddfr, &bpp, NULL); + if (ret) { + printk(KERN_ERR "colinfo\n"); + return ret; + } + + /* min VRAM: xres_min = 16, yres_min = 1, bpp = 1: 2byte -> 1 page + max VRAM: xres_max = 1024, yres_max = 1024, bpp = 16: 2MB */ + + vram = info->var.xres * info->var.yres; + if (info->var.grayscale) { + if (bpp == 1) + vram >>= 3; + else if (bpp == 2) + vram >>= 2; + else if (bpp == 4) + vram >>= 1; + } else if (bpp > 8) + vram *= 2; + if ((vram < 1) || (vram > 1024 * 2048)) { + dev_dbg(info->dev, "too much VRAM required. Check settings\n"); + return -ENODEV; + } + + if (vram < PAGE_SIZE) + vram = PAGE_SIZE; + + fbmem = dma_alloc_coherent(info->dev, vram, &par->fbdma, GFP_KERNEL); + + if (!fbmem) + return -ENOMEM; + + if ((par->fbdma & SH7760FB_DMA_MASK) != SH7760FB_DMA_MASK) { + sh7760fb_free_mem(info); + dev_err(info->dev, "kernel gave me memory at 0x%08lx, which is" + "unusable for the LCDC\n", (unsigned long)par->fbdma); + return -ENOMEM; + } + + info->screen_base = fbmem; + info->screen_size = vram; + + return 0; +} + +static int __devinit sh7760fb_probe(struct platform_device *pdev) +{ + struct fb_info *info; + struct resource *res; + struct sh7760fb_par *par; + int ret; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (unlikely(res == NULL)) { + dev_err(&pdev->dev, "invalid resource\n"); + return -EINVAL; + } + + info = framebuffer_alloc(sizeof(struct sh7760fb_par), &pdev->dev); + if (!info) + return -ENOMEM; + + par = info->par; + par->dev = pdev; + + par->pd = pdev->dev.platform_data; + if (!par->pd) { + dev_dbg(info->dev, "no display setup data!\n"); + ret = -ENODEV; + goto out_fb; + } + + par->ioarea = request_mem_region(res->start, + (res->end - res->start), pdev->name); + if (!par->ioarea) { + dev_err(&pdev->dev, "mmio area busy\n"); + ret = -EBUSY; + goto out_fb; + } + + par->base = ioremap_nocache(res->start, res->end - res->start + 1); + if (!par->base) { + dev_err(&pdev->dev, "cannot remap\n"); + ret = -ENODEV; + goto out_res; + } + + iowrite16(0, par->base + LDINTR); /* disable vsync irq */ + par->irq = platform_get_irq(pdev, 0); + if (par->irq >= 0) { + ret = request_irq(par->irq, sh7760fb_irq, 0, + "sh7760-lcdc", &par->vsync); + if (ret) { + dev_err(&pdev->dev, "cannot grab IRQ\n"); + par->irq = -ENXIO; + } else + disable_irq_nosync(par->irq); + } + + fb_videomode_to_var(&info->var, par->pd->def_mode); + + ret = sh7760fb_alloc_mem(info); + if (ret) { + dev_dbg(info->dev, "framebuffer memory allocation failed!\n"); + goto out_unmap; + } + + info->pseudo_palette = par->pseudo_palette; + + /* fixup color register bitpositions. These are fixed by hardware */ + info->var.red.offset = 11; + info->var.red.length = 5; + info->var.red.msb_right = 0; + + info->var.green.offset = 5; + info->var.green.length = 6; + info->var.green.msb_right = 0; + + info->var.blue.offset = 0; + info->var.blue.length = 5; + info->var.blue.msb_right = 0; + + info->var.transp.offset = 0; + info->var.transp.length = 0; + info->var.transp.msb_right = 0; + + /* set the DON2 bit now, before cmap allocation, as it will randomize + * palette memory. + */ + iowrite16(LDCNTR_DON2, par->base + LDCNTR); + info->fbops = &sh7760fb_ops; + + ret = fb_alloc_cmap(&info->cmap, 256, 0); + if (ret) { + dev_dbg(info->dev, "Unable to allocate cmap memory\n"); + goto out_mem; + } + + ret = register_framebuffer(info); + if (ret < 0) { + dev_dbg(info->dev, "cannot register fb!\n"); + goto out_cmap; + } + platform_set_drvdata(pdev, info); + + printk(KERN_INFO "%s: memory at phys 0x%08lx-0x%08lx, size %ld KiB\n", + pdev->name, + (unsigned long)par->fbdma, + (unsigned long)(par->fbdma + info->screen_size - 1), + info->screen_size >> 10); + + return 0; + +out_cmap: + sh7760fb_blank(FB_BLANK_POWERDOWN, info); + fb_dealloc_cmap(&info->cmap); +out_mem: + sh7760fb_free_mem(info); +out_unmap: + if (par->irq >= 0) + free_irq(par->irq, &par->vsync); + iounmap(par->base); +out_res: + release_resource(par->ioarea); + kfree(par->ioarea); +out_fb: + framebuffer_release(info); + return ret; +} + +static int __devexit sh7760fb_remove(struct platform_device *dev) +{ + struct fb_info *info = platform_get_drvdata(dev); + struct sh7760fb_par *par = info->par; + + sh7760fb_blank(FB_BLANK_POWERDOWN, info); + unregister_framebuffer(info); + fb_dealloc_cmap(&info->cmap); + sh7760fb_free_mem(info); + if (par->irq >= 0) + free_irq(par->irq, par); + iounmap(par->base); + release_resource(par->ioarea); + kfree(par->ioarea); + framebuffer_release(info); + platform_set_drvdata(dev, NULL); + + return 0; +} + +static struct platform_driver sh7760_lcdc_driver = { + .driver = { + .name = "sh7760-lcdc", + .owner = THIS_MODULE, + }, + .probe = sh7760fb_probe, + .remove = __devexit_p(sh7760fb_remove), +}; + +static int __init sh7760fb_init(void) +{ + return platform_driver_register(&sh7760_lcdc_driver); +} + +static void __exit sh7760fb_exit(void) +{ + platform_driver_unregister(&sh7760_lcdc_driver); +} + +module_init(sh7760fb_init); +module_exit(sh7760fb_exit); + +MODULE_AUTHOR("Nobuhiro Iwamatsu, Manuel Lauss"); +MODULE_DESCRIPTION("FBdev for SH7760/63 integrated LCD Controller"); +MODULE_LICENSE("GPL"); diff --git a/include/asm-sh/sh7760fb.h b/include/asm-sh/sh7760fb.h new file mode 100644 index 000000000000..8767f61aceca --- /dev/null +++ b/include/asm-sh/sh7760fb.h @@ -0,0 +1,197 @@ +/* + * sh7760fb.h -- platform data for SH7760/SH7763 LCDC framebuffer driver. + * + * (c) 2006-2008 MSC Vertriebsges.m.b.H., + * Manuel Lauss + * (c) 2008 Nobuhiro Iwamatsu + */ + +#ifndef _ASM_SH_SH7760FB_H +#define _ASM_SH_SH7760FB_H + +/* + * some bits of the colormap registers should be written as zero. + * create a mask for that. + */ +#define SH7760FB_PALETTE_MASK 0x00f8fcf8 + +/* The LCDC dma engine always sets bits 27-26 to 1: this is Area3 */ +#define SH7760FB_DMA_MASK 0x0C000000 + +/* palette */ +#define LDPR(x) (((x) << 2)) + +/* framebuffer registers and bits */ +#define LDICKR 0x400 +#define LDMTR 0x402 +/* see sh7760fb.h for LDMTR bits */ +#define LDDFR 0x404 +#define LDDFR_PABD (1 << 8) +#define LDDFR_COLOR_MASK 0x7F +#define LDSMR 0x406 +#define LDSMR_ROT (1 << 13) +#define LDSARU 0x408 +#define LDSARL 0x40c +#define LDLAOR 0x410 +#define LDPALCR 0x412 +#define LDPALCR_PALS (1 << 4) +#define LDPALCR_PALEN (1 << 0) +#define LDHCNR 0x414 +#define LDHSYNR 0x416 +#define LDVDLNR 0x418 +#define LDVTLNR 0x41a +#define LDVSYNR 0x41c +#define LDACLNR 0x41e +#define LDINTR 0x420 +#define LDPMMR 0x424 +#define LDPSPR 0x426 +#define LDCNTR 0x428 +#define LDCNTR_DON (1 << 0) +#define LDCNTR_DON2 (1 << 4) + +#ifdef CONFIG_CPU_SUBTYPE_SH7763 +# define LDLIRNR 0x440 +/* LDINTR bit */ +# define LDINTR_MINTEN (1 << 15) +# define LDINTR_FINTEN (1 << 14) +# define LDINTR_VSINTEN (1 << 13) +# define LDINTR_VEINTEN (1 << 12) +# define LDINTR_MINTS (1 << 11) +# define LDINTR_FINTS (1 << 10) +# define LDINTR_VSINTS (1 << 9) +# define LDINTR_VEINTS (1 << 8) +# define VINT_START (LDINTR_VSINTEN) +# define VINT_CHECK (LDINTR_VSINTS) +#else +/* LDINTR bit */ +# define LDINTR_VINTSEL (1 << 12) +# define LDINTR_VINTE (1 << 8) +# define LDINTR_VINTS (1 << 0) +# define VINT_START (LDINTR_VINTSEL) +# define VINT_CHECK (LDINTR_VINTS) +#endif + +/* HSYNC polarity inversion */ +#define LDMTR_FLMPOL (1 << 15) + +/* VSYNC polarity inversion */ +#define LDMTR_CL1POL (1 << 14) + +/* DISPLAY-ENABLE polarity inversion */ +#define LDMTR_DISPEN_LOWACT (1 << 13) + +/* DISPLAY DATA BUS polarity inversion */ +#define LDMTR_DPOL_LOWACT (1 << 12) + +/* AC modulation signal enable */ +#define LDMTR_MCNT (1 << 10) + +/* Disable output of HSYNC during VSYNC period */ +#define LDMTR_CL1CNT (1 << 9) + +/* Disable output of VSYNC during VSYNC period */ +#define LDMTR_CL2CNT (1 << 8) + +/* Display types supported by the LCDC */ +#define LDMTR_STN_MONO_4 0x00 +#define LDMTR_STN_MONO_8 0x01 +#define LDMTR_STN_COLOR_4 0x08 +#define LDMTR_STN_COLOR_8 0x09 +#define LDMTR_STN_COLOR_12 0x0A +#define LDMTR_STN_COLOR_16 0x0B +#define LDMTR_DSTN_MONO_8 0x11 +#define LDMTR_DSTN_MONO_16 0x13 +#define LDMTR_DSTN_COLOR_8 0x19 +#define LDMTR_DSTN_COLOR_12 0x1A +#define LDMTR_DSTN_COLOR_16 0x1B +#define LDMTR_TFT_COLOR_16 0x2B + +/* framebuffer color layout */ +#define LDDFR_1BPP_MONO 0x00 +#define LDDFR_2BPP_MONO 0x01 +#define LDDFR_4BPP_MONO 0x02 +#define LDDFR_6BPP_MONO 0x04 +#define LDDFR_4BPP 0x0A +#define LDDFR_8BPP 0x0C +#define LDDFR_16BPP_RGB555 0x1D +#define LDDFR_16BPP_RGB565 0x2D + +/* LCDC Pixclock sources */ +#define LCDC_CLKSRC_BUSCLOCK 0 +#define LCDC_CLKSRC_PERIPHERAL 1 +#define LCDC_CLKSRC_EXTERNAL 2 + +#define LDICKR_CLKSRC(x) \ + (((x) & 3) << 12) + +/* LCDC pixclock input divider. Set to 1 at a minimum! */ +#define LDICKR_CLKDIV(x) \ + ((x) & 0x1f) + +struct sh7760fb_platdata { + + /* Set this member to a valid fb_videmode for the display you + * wish to use. The following members must be initialized: + * xres, yres, hsync_len, vsync_len, sync, + * {left,right,upper,lower}_margin. + * The driver uses the above members to calculate register values + * and memory requirements. Other members are ignored but may + * be used by other framebuffer layer components. + */ + struct fb_videomode *def_mode; + + /* LDMTR includes display type and signal polarity. The + * HSYNC/VSYNC polarities are derived from the fb_var_screeninfo + * data above; however the polarities of the following signals + * must be encoded in the ldmtr member: + * Display Enable signal (default high-active) DISPEN_LOWACT + * Display Data signals (default high-active) DPOL_LOWACT + * AC Modulation signal (default off) MCNT + * Hsync-During-Vsync suppression (default off) CL1CNT + * Vsync-during-vsync suppression (default off) CL2CNT + * NOTE: also set a display type! + * (one of LDMTR_{STN,DSTN,TFT}_{MONO,COLOR}_{4,8,12,16}) + */ + u16 ldmtr; + + /* LDDFR controls framebuffer image format (depth, organization) + * Use ONE of the LDDFR_?BPP_* macros! + */ + u16 lddfr; + + /* LDPMMR and LDPSPR control the timing of the power signals + * for the display. Please read the SH7760 Hardware Manual, + * Chapters 30.3.17, 30.3.18 and 30.4.6! + */ + u16 ldpmmr; + u16 ldpspr; + + /* LDACLNR contains the line numbers after which the AC modulation + * signal is to toggle. Set to ZERO for TFTs or displays which + * do not need it. (Chapter 30.3.15 in SH7760 Hardware Manual). + */ + u16 ldaclnr; + + /* LDICKR contains information on pixelclock source and config. + * Please use the LDICKR_CLKSRC() and LDICKR_CLKDIV() macros. + * minimal value for CLKDIV() must be 1!. + */ + u16 ldickr; + + /* set this member to 1 if you wish to use the LCDC's hardware + * rotation function. This is limited to displays <= 320x200 + * pixels resolution! + */ + int rotate; /* set to 1 to rotate 90 CCW */ + + /* set this to 1 to suppress vsync irq use. */ + int novsync; + + /* blanking hook for platform. Set this if your platform can do + * more than the LCDC in terms of blanking (e.g. disable clock + * generator / backlight power supply / etc. + */ + void (*blank) (int); +}; + +#endif /* _ASM_SH_SH7760FB_H */ -- cgit v1.2.3 From 58340a07c194e0aed7bc58b61ff24330bb2a409f Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 25 Jul 2008 01:45:33 -0700 Subject: introduce HAVE_EFFICIENT_UNALIGNED_ACCESS Kconfig symbol In many cases, especially in networking, it can be beneficial to know at compile time whether the architecture can do unaligned accesses efficiently. This patch introduces a new Kconfig symbol HAVE_EFFICIENT_UNALIGNED_ACCESS for that purpose and adds it to the powerpc and x86 architectures. Also add some documentation about alignment and networking, and especially one intended use of this symbol. Signed-off-by: Johannes Berg Acked-by: Sam Ravnborg Acked-by: Ingo Molnar [x86 architecture part] Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/unaligned-memory-access.txt | 32 ++++++++++++++++++++++++++++--- arch/Kconfig | 19 ++++++++++++++++++ arch/powerpc/Kconfig | 1 + arch/x86/Kconfig | 1 + 4 files changed, 50 insertions(+), 3 deletions(-) (limited to 'Documentation') diff --git a/Documentation/unaligned-memory-access.txt b/Documentation/unaligned-memory-access.txt index b0472ac5226a..f866c72291bf 100644 --- a/Documentation/unaligned-memory-access.txt +++ b/Documentation/unaligned-memory-access.txt @@ -218,9 +218,35 @@ If use of such macros is not convenient, another option is to use memcpy(), where the source or destination (or both) are of type u8* or unsigned char*. Due to the byte-wise nature of this operation, unaligned accesses are avoided. + +Alignment vs. Networking +======================== + +On architectures that require aligned loads, networking requires that the IP +header is aligned on a four-byte boundary to optimise the IP stack. For +regular ethernet hardware, the constant NET_IP_ALIGN is used. On most +architectures this constant has the value 2 because the normal ethernet +header is 14 bytes long, so in order to get proper alignment one needs to +DMA to an address which can be expressed as 4*n + 2. One notable exception +here is powerpc which defines NET_IP_ALIGN to 0 because DMA to unaligned +addresses can be very expensive and dwarf the cost of unaligned loads. + +For some ethernet hardware that cannot DMA to unaligned addresses like +4*n+2 or non-ethernet hardware, this can be a problem, and it is then +required to copy the incoming frame into an aligned buffer. Because this is +unnecessary on architectures that can do unaligned accesses, the code can be +made dependent on CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS like so: + +#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + skb = original skb +#else + skb = copy skb +#endif + -- -Author: Daniel Drake +Authors: Daniel Drake , + Johannes Berg With help from: Alan Cox, Avuton Olrich, Heikki Orsila, Jan Engelhardt, -Johannes Berg, Kyle McMartin, Kyle Moffett, Randy Dunlap, Robert Hancock, -Uli Kunitz, Vadim Lobanov +Kyle McMartin, Kyle Moffett, Randy Dunlap, Robert Hancock, Uli Kunitz, +Vadim Lobanov diff --git a/arch/Kconfig b/arch/Kconfig index 6093c0be58b0..b0fabfa864ff 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -27,6 +27,25 @@ config KPROBES for kernel debugging, non-intrusive instrumentation and testing. If in doubt, say "N". +config HAVE_EFFICIENT_UNALIGNED_ACCESS + def_bool n + help + Some architectures are unable to perform unaligned accesses + without the use of get_unaligned/put_unaligned. Others are + unable to perform such accesses efficiently (e.g. trap on + unaligned access and require fixing it up in the exception + handler.) + + This symbol should be selected by an architecture if it can + perform unaligned accesses efficiently to allow different + code paths to be selected for these cases. Some network + drivers, for example, could opt to not fix up alignment + problems with received packets if doing so would not help + much. + + See Documentation/unaligned-memory-access.txt for more + information on the topic of unaligned memory accesses. + config KRETPROBES def_bool y depends on KPROBES && HAVE_KRETPROBES diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a487671c282f..de6b49cd6be8 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -112,6 +112,7 @@ config PPC select HAVE_FTRACE select HAVE_IDE select HAVE_IOREMAP_PROT + select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_KPROBES select HAVE_ARCH_KGDB select HAVE_KRETPROBES diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b2ddfcf01728..66f3ab05b18c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -28,6 +28,7 @@ config X86 select HAVE_FTRACE select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64) select HAVE_ARCH_KGDB if !X86_VOYAGER + select HAVE_EFFICIENT_UNALIGNED_ACCESS config ARCH_DEFCONFIG string -- cgit v1.2.3 From f557d0996a6f9c06912528ea85e1dba0fb7d485f Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 01:45:37 -0700 Subject: remove some more tipar bits Some bits were missed when the tipar driver was removed. Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/00-INDEX | 2 -- Documentation/kernel-parameters.txt | 7 ------- drivers/char/Makefile | 1 - 3 files changed, 10 deletions(-) (limited to 'Documentation') diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX index 1977fab38656..6de71308a906 100644 --- a/Documentation/00-INDEX +++ b/Documentation/00-INDEX @@ -361,8 +361,6 @@ telephony/ - directory with info on telephony (e.g. voice over IP) support. time_interpolators.txt - info on time interpolators. -tipar.txt - - information about Parallel link cable for Texas Instruments handhelds. tty.txt - guide to the locking policies of the tty layer. uml/ diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 497a98dafdaa..e7bea3e85304 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2159,13 +2159,6 @@ and is between 256 and 4096 characters. It is defined in the file : poll all this frequency 0: no polling (default) - tipar.timeout= [HW,PPT] - Set communications timeout in tenths of a second - (default 15). - - tipar.delay= [HW,PPT] - Set inter-bit delay in microseconds (default 10). - tmscsim= [HW,SCSI] See comment before function dc390_setup() in drivers/scsi/tmscsim.c. diff --git a/drivers/char/Makefile b/drivers/char/Makefile index eb02c3506800..f7a0d1a754fc 100644 --- a/drivers/char/Makefile +++ b/drivers/char/Makefile @@ -64,7 +64,6 @@ obj-$(CONFIG_BRIQ_PANEL) += briq_panel.o obj-$(CONFIG_BFIN_OTP) += bfin-otp.o obj-$(CONFIG_PRINTER) += lp.o -obj-$(CONFIG_TIPAR) += tipar.o obj-$(CONFIG_APM_EMULATION) += apm-emulation.o -- cgit v1.2.3 From a7f371e54fac49ff62bb640d4a7276fca01527e8 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 25 Jul 2008 01:45:51 -0700 Subject: documentation: update CodingStyle tips for Emacs users Describe a setup that integrates better with Emacs' cc-mode and also fixes up the alignment of continuation lines to really only use tabs. Signed-off-by: Johannes Weiner Cc: Jonathan Corbet Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/CodingStyle | 42 +++++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 19 deletions(-) (limited to 'Documentation') diff --git a/Documentation/CodingStyle b/Documentation/CodingStyle index 6caa14615578..1875e502f872 100644 --- a/Documentation/CodingStyle +++ b/Documentation/CodingStyle @@ -474,25 +474,29 @@ make a good program). So, you can either get rid of GNU emacs, or change it to use saner values. To do the latter, you can stick the following in your .emacs file: -(defun linux-c-mode () - "C mode with adjusted defaults for use with the Linux kernel." - (interactive) - (c-mode) - (c-set-style "K&R") - (setq tab-width 8) - (setq indent-tabs-mode t) - (setq c-basic-offset 8)) - -This will define the M-x linux-c-mode command. When hacking on a -module, if you put the string -*- linux-c -*- somewhere on the first -two lines, this mode will be automatically invoked. Also, you may want -to add - -(setq auto-mode-alist (cons '("/usr/src/linux.*/.*\\.[ch]$" . linux-c-mode) - auto-mode-alist)) - -to your .emacs file if you want to have linux-c-mode switched on -automagically when you edit source files under /usr/src/linux. +(defun c-lineup-arglist-tabs-only (ignored) + "Line up argument lists by tabs, not spaces" + (let* ((anchor (c-langelem-pos c-syntactic-element)) + (column (c-langelem-2nd-pos c-syntactic-element)) + (offset (- (1+ column) anchor)) + (steps (floor offset c-basic-offset))) + (* (max steps 1) + c-basic-offset))) + +(add-hook 'c-mode-hook + (lambda () + (let ((filename (buffer-file-name))) + ;; Enable kernel mode for the appropriate files + (when (and filename + (string-match "~/src/linux-trees" filename)) + (setq indent-tabs-mode t) + (c-set-style "linux") + (c-set-offset 'arglist-cont-nonempty + '(c-lineup-gcc-asm-reg + c-lineup-arglist-tabs-only)))))) + +This will make emacs go better with the kernel coding style for C +files below ~/src/linux-trees. But even if you fail in getting emacs to do sane formatting, not everything is lost: use "indent". -- cgit v1.2.3 From d8f388d8dc8d4f36539dd37c1fff62cc404ea0fc Mon Sep 17 00:00:00 2001 From: David Brownell Date: Fri, 25 Jul 2008 01:46:07 -0700 Subject: gpio: sysfs interface This adds a simple sysfs interface for GPIOs. /sys/class/gpio /export ... asks the kernel to export a GPIO to userspace /unexport ... to return a GPIO to the kernel /gpioN ... for each exported GPIO #N /value ... always readable, writes fail for input GPIOs /direction ... r/w as: in, out (default low); write high, low /gpiochipN ... for each gpiochip; #N is its first GPIO /base ... (r/o) same as N /label ... (r/o) descriptive, not necessarily unique /ngpio ... (r/o) number of GPIOs; numbered N .. N+(ngpio - 1) GPIOs claimed by kernel code may be exported by its owner using a new gpio_export() call, which should be most useful for driver debugging. Such exports may optionally be done without a "direction" attribute. Userspace may ask to take over a GPIO by writing to a sysfs control file, helping to cope with incomplete board support or other "one-off" requirements that don't merit full kernel support: echo 23 > /sys/class/gpio/export ... will gpio_request(23, "sysfs") and gpio_export(23); use /sys/class/gpio/gpio-23/direction to (re)configure it, when that GPIO can be used as both input and output. echo 23 > /sys/class/gpio/unexport ... will gpio_free(23), when it was exported as above The extra D-space footprint is a few hundred bytes, except for the sysfs resources associated with each exported GPIO. The additional I-space footprint is about two thirds of the current size of gpiolib (!). Since no /dev node creation is involved, no "udev" support is needed. Related changes: * This adds a device pointer to "struct gpio_chip". When GPIO providers initialize that, sysfs gpio class devices become children of that device instead of being "virtual" devices. * The (few) gpio_chip providers which have such a device node have been updated. * Some gpio_chip drivers also needed to update their module "owner" field ... for which missing kerneldoc was added. * Some gpio_chips don't support input GPIOs. Those GPIOs are now flagged appropriately when the chip is registered. Based on previous patches, and discussion both on and off LKML. A Documentation/ABI/testing/sysfs-gpio update is ready to submit once this merges to mainline. [akpm@linux-foundation.org: a few maintenance build fixes] Signed-off-by: David Brownell Cc: Guennadi Liakhovetski Cc: Greg KH Cc: Kay Sievers Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/gpio.txt | 123 +++++++++- arch/arm/plat-omap/gpio.c | 3 + arch/avr32/mach-at32ap/pio.c | 2 + drivers/gpio/Kconfig | 15 ++ drivers/gpio/gpiolib.c | 536 +++++++++++++++++++++++++++++++++++++++++-- drivers/gpio/mcp23s08.c | 1 + drivers/gpio/pca953x.c | 1 + drivers/gpio/pcf857x.c | 1 + drivers/i2c/chips/tps65010.c | 2 + drivers/mfd/htc-egpio.c | 2 + include/asm-generic/gpio.h | 33 ++- include/linux/gpio.h | 13 ++ 12 files changed, 712 insertions(+), 20 deletions(-) (limited to 'Documentation') diff --git a/Documentation/gpio.txt b/Documentation/gpio.txt index c35ca9e40d4c..8b69811a9642 100644 --- a/Documentation/gpio.txt +++ b/Documentation/gpio.txt @@ -347,15 +347,12 @@ necessarily be nonportable. Dynamic definition of GPIOs is not currently standard; for example, as a side effect of configuring an add-on board with some GPIO expanders. -These calls are purely for kernel space, but a userspace API could be built -on top of them. - GPIO implementor's framework (OPTIONAL) ======================================= As noted earlier, there is an optional implementation framework making it easier for platforms to support different kinds of GPIO controller using -the same programming interface. +the same programming interface. This framework is called "gpiolib". As a debugging aid, if debugfs is available a /sys/kernel/debug/gpio file will be found there. That will list all the controllers registered through @@ -439,4 +436,120 @@ becomes available. That may mean the device should not be registered until calls for that GPIO can work. One way to address such dependencies is for such gpio_chip controllers to provide setup() and teardown() callbacks to board specific code; those board specific callbacks would register devices -once all the necessary resources are available. +once all the necessary resources are available, and remove them later when +the GPIO controller device becomes unavailable. + + +Sysfs Interface for Userspace (OPTIONAL) +======================================== +Platforms which use the "gpiolib" implementors framework may choose to +configure a sysfs user interface to GPIOs. This is different from the +debugfs interface, since it provides control over GPIO direction and +value instead of just showing a gpio state summary. Plus, it could be +present on production systems without debugging support. + +Given approprate hardware documentation for the system, userspace could +know for example that GPIO #23 controls the write protect line used to +protect boot loader segments in flash memory. System upgrade procedures +may need to temporarily remove that protection, first importing a GPIO, +then changing its output state, then updating the code before re-enabling +the write protection. In normal use, GPIO #23 would never be touched, +and the kernel would have no need to know about it. + +Again depending on appropriate hardware documentation, on some systems +userspace GPIO can be used to determine system configuration data that +standard kernels won't know about. And for some tasks, simple userspace +GPIO drivers could be all that the system really needs. + +Note that standard kernel drivers exist for common "LEDs and Buttons" +GPIO tasks: "leds-gpio" and "gpio_keys", respectively. Use those +instead of talking directly to the GPIOs; they integrate with kernel +frameworks better than your userspace code could. + + +Paths in Sysfs +-------------- +There are three kinds of entry in /sys/class/gpio: + + - Control interfaces used to get userspace control over GPIOs; + + - GPIOs themselves; and + + - GPIO controllers ("gpio_chip" instances). + +That's in addition to standard files including the "device" symlink. + +The control interfaces are write-only: + + /sys/class/gpio/ + + "export" ... Userspace may ask the kernel to export control of + a GPIO to userspace by writing its number to this file. + + Example: "echo 19 > export" will create a "gpio19" node + for GPIO #19, if that's not requested by kernel code. + + "unexport" ... Reverses the effect of exporting to userspace. + + Example: "echo 19 > unexport" will remove a "gpio19" + node exported using the "export" file. + +GPIO signals have paths like /sys/class/gpio/gpio42/ (for GPIO #42) +and have the following read/write attributes: + + /sys/class/gpio/gpioN/ + + "direction" ... reads as either "in" or "out". This value may + normally be written. Writing as "out" defaults to + initializing the value as low. To ensure glitch free + operation, values "low" and "high" may be written to + configure the GPIO as an output with that initial value. + + Note that this attribute *will not exist* if the kernel + doesn't support changing the direction of a GPIO, or + it was exported by kernel code that didn't explicitly + allow userspace to reconfigure this GPIO's direction. + + "value" ... reads as either 0 (low) or 1 (high). If the GPIO + is configured as an output, this value may be written; + any nonzero value is treated as high. + +GPIO controllers have paths like /sys/class/gpio/chipchip42/ (for the +controller implementing GPIOs starting at #42) and have the following +read-only attributes: + + /sys/class/gpio/gpiochipN/ + + "base" ... same as N, the first GPIO managed by this chip + + "label" ... provided for diagnostics (not always unique) + + "ngpio" ... how many GPIOs this manges (N to N + ngpio - 1) + +Board documentation should in most cases cover what GPIOs are used for +what purposes. However, those numbers are not always stable; GPIOs on +a daughtercard might be different depending on the base board being used, +or other cards in the stack. In such cases, you may need to use the +gpiochip nodes (possibly in conjunction with schematics) to determine +the correct GPIO number to use for a given signal. + + +Exporting from Kernel code +-------------------------- +Kernel code can explicitly manage exports of GPIOs which have already been +requested using gpio_request(): + + /* export the GPIO to userspace */ + int gpio_export(unsigned gpio, bool direction_may_change); + + /* reverse gpio_export() */ + void gpio_unexport(); + +After a kernel driver requests a GPIO, it may only be made available in +the sysfs interface by gpio_export(). The driver can control whether the +signal direction may change. This helps drivers prevent userspace code +from accidentally clobbering important system state. + +This explicit exporting can help with debugging (by making some kinds +of experiments easier), or can provide an always-there interface that's +suitable for documenting as part of a board support package. diff --git a/arch/arm/plat-omap/gpio.c b/arch/arm/plat-omap/gpio.c index 1903a3491ee9..d8e9c2c3f0f6 100644 --- a/arch/arm/plat-omap/gpio.c +++ b/arch/arm/plat-omap/gpio.c @@ -1488,6 +1488,9 @@ static int __init _omap_gpio_init(void) bank->chip.set = gpio_set; if (bank_is_mpuio(bank)) { bank->chip.label = "mpuio"; +#ifdef CONFIG_ARCH_OMAP1 + bank->chip.dev = &omap_mpuio_device.dev; +#endif bank->chip.base = OMAP_MPUIO(0); } else { bank->chip.label = "gpio"; diff --git a/arch/avr32/mach-at32ap/pio.c b/arch/avr32/mach-at32ap/pio.c index 60da03ba7117..296294f8ed81 100644 --- a/arch/avr32/mach-at32ap/pio.c +++ b/arch/avr32/mach-at32ap/pio.c @@ -360,6 +360,8 @@ static int __init pio_probe(struct platform_device *pdev) pio->chip.label = pio->name; pio->chip.base = pdev->id * 32; pio->chip.ngpio = 32; + pio->chip.dev = &pdev->dev; + pio->chip.owner = THIS_MODULE; pio->chip.direction_input = direction_input; pio->chip.get = gpio_get; diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index fced1909cbba..6ec0e35b98e3 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -23,6 +23,21 @@ config DEBUG_GPIO slower. The diagnostics help catch the type of setup errors that are most common when setting up new platforms or boards. +config GPIO_SYSFS + bool "/sys/class/gpio/... (sysfs interface)" + depends on SYSFS && EXPERIMENTAL + help + Say Y here to add a sysfs interface for GPIOs. + + This is mostly useful to work around omissions in a system's + kernel support. Those are common in custom and semicustom + hardware assembled using standard kernels with a minimum of + custom patches. In those cases, userspace code may import + a given GPIO from the kernel, if no kernel driver requested it. + + Kernel drivers may also request that a particular GPIO be + exported to userspace; this can be useful when debugging. + # put expanders in the right section, in alphabetical order comment "I2C GPIO expanders:" diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index beaf6b3a37dc..8d2940517c99 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -2,8 +2,11 @@ #include #include #include - -#include +#include +#include +#include +#include +#include /* Optional implementation infrastructure for GPIO interfaces. @@ -44,6 +47,8 @@ struct gpio_desc { #define FLAG_REQUESTED 0 #define FLAG_IS_OUT 1 #define FLAG_RESERVED 2 +#define FLAG_EXPORT 3 /* protected by sysfs_lock */ +#define FLAG_SYSFS 4 /* exported via /sys/class/gpio/control */ #ifdef CONFIG_DEBUG_FS const char *label; @@ -151,6 +156,482 @@ err: return ret; } +#ifdef CONFIG_GPIO_SYSFS + +/* lock protects against unexport_gpio() being called while + * sysfs files are active. + */ +static DEFINE_MUTEX(sysfs_lock); + +/* + * /sys/class/gpio/gpioN... only for GPIOs that are exported + * /direction + * * MAY BE OMITTED if kernel won't allow direction changes + * * is read/write as "in" or "out" + * * may also be written as "high" or "low", initializing + * output value as specified ("out" implies "low") + * /value + * * always readable, subject to hardware behavior + * * may be writable, as zero/nonzero + * + * REVISIT there will likely be an attribute for configuring async + * notifications, e.g. to specify polling interval or IRQ trigger type + * that would for example trigger a poll() on the "value". + */ + +static ssize_t gpio_direction_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + const struct gpio_desc *desc = dev_get_drvdata(dev); + ssize_t status; + + mutex_lock(&sysfs_lock); + + if (!test_bit(FLAG_EXPORT, &desc->flags)) + status = -EIO; + else + status = sprintf(buf, "%s\n", + test_bit(FLAG_IS_OUT, &desc->flags) + ? "out" : "in"); + + mutex_unlock(&sysfs_lock); + return status; +} + +static ssize_t gpio_direction_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t size) +{ + const struct gpio_desc *desc = dev_get_drvdata(dev); + unsigned gpio = desc - gpio_desc; + ssize_t status; + + mutex_lock(&sysfs_lock); + + if (!test_bit(FLAG_EXPORT, &desc->flags)) + status = -EIO; + else if (sysfs_streq(buf, "high")) + status = gpio_direction_output(gpio, 1); + else if (sysfs_streq(buf, "out") || sysfs_streq(buf, "low")) + status = gpio_direction_output(gpio, 0); + else if (sysfs_streq(buf, "in")) + status = gpio_direction_input(gpio); + else + status = -EINVAL; + + mutex_unlock(&sysfs_lock); + return status ? : size; +} + +static const DEVICE_ATTR(direction, 0644, + gpio_direction_show, gpio_direction_store); + +static ssize_t gpio_value_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + const struct gpio_desc *desc = dev_get_drvdata(dev); + unsigned gpio = desc - gpio_desc; + ssize_t status; + + mutex_lock(&sysfs_lock); + + if (!test_bit(FLAG_EXPORT, &desc->flags)) + status = -EIO; + else + status = sprintf(buf, "%d\n", gpio_get_value_cansleep(gpio)); + + mutex_unlock(&sysfs_lock); + return status; +} + +static ssize_t gpio_value_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t size) +{ + const struct gpio_desc *desc = dev_get_drvdata(dev); + unsigned gpio = desc - gpio_desc; + ssize_t status; + + mutex_lock(&sysfs_lock); + + if (!test_bit(FLAG_EXPORT, &desc->flags)) + status = -EIO; + else if (!test_bit(FLAG_IS_OUT, &desc->flags)) + status = -EPERM; + else { + long value; + + status = strict_strtol(buf, 0, &value); + if (status == 0) { + gpio_set_value_cansleep(gpio, value != 0); + status = size; + } + } + + mutex_unlock(&sysfs_lock); + return status; +} + +static /*const*/ DEVICE_ATTR(value, 0644, + gpio_value_show, gpio_value_store); + +static const struct attribute *gpio_attrs[] = { + &dev_attr_direction.attr, + &dev_attr_value.attr, + NULL, +}; + +static const struct attribute_group gpio_attr_group = { + .attrs = (struct attribute **) gpio_attrs, +}; + +/* + * /sys/class/gpio/gpiochipN/ + * /base ... matching gpio_chip.base (N) + * /label ... matching gpio_chip.label + * /ngpio ... matching gpio_chip.ngpio + */ + +static ssize_t chip_base_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + const struct gpio_chip *chip = dev_get_drvdata(dev); + + return sprintf(buf, "%d\n", chip->base); +} +static DEVICE_ATTR(base, 0444, chip_base_show, NULL); + +static ssize_t chip_label_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + const struct gpio_chip *chip = dev_get_drvdata(dev); + + return sprintf(buf, "%s\n", chip->label ? : ""); +} +static DEVICE_ATTR(label, 0444, chip_label_show, NULL); + +static ssize_t chip_ngpio_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + const struct gpio_chip *chip = dev_get_drvdata(dev); + + return sprintf(buf, "%u\n", chip->ngpio); +} +static DEVICE_ATTR(ngpio, 0444, chip_ngpio_show, NULL); + +static const struct attribute *gpiochip_attrs[] = { + &dev_attr_base.attr, + &dev_attr_label.attr, + &dev_attr_ngpio.attr, + NULL, +}; + +static const struct attribute_group gpiochip_attr_group = { + .attrs = (struct attribute **) gpiochip_attrs, +}; + +/* + * /sys/class/gpio/export ... write-only + * integer N ... number of GPIO to export (full access) + * /sys/class/gpio/unexport ... write-only + * integer N ... number of GPIO to unexport + */ +static ssize_t export_store(struct class *class, const char *buf, size_t len) +{ + long gpio; + int status; + + status = strict_strtol(buf, 0, &gpio); + if (status < 0) + goto done; + + /* No extra locking here; FLAG_SYSFS just signifies that the + * request and export were done by on behalf of userspace, so + * they may be undone on its behalf too. + */ + + status = gpio_request(gpio, "sysfs"); + if (status < 0) + goto done; + + status = gpio_export(gpio, true); + if (status < 0) + gpio_free(gpio); + else + set_bit(FLAG_SYSFS, &gpio_desc[gpio].flags); + +done: + if (status) + pr_debug("%s: status %d\n", __func__, status); + return status ? : len; +} + +static ssize_t unexport_store(struct class *class, const char *buf, size_t len) +{ + long gpio; + int status; + + status = strict_strtol(buf, 0, &gpio); + if (status < 0) + goto done; + + status = -EINVAL; + + /* reject bogus commands (gpio_unexport ignores them) */ + if (!gpio_is_valid(gpio)) + goto done; + + /* No extra locking here; FLAG_SYSFS just signifies that the + * request and export were done by on behalf of userspace, so + * they may be undone on its behalf too. + */ + if (test_and_clear_bit(FLAG_SYSFS, &gpio_desc[gpio].flags)) { + status = 0; + gpio_free(gpio); + } +done: + if (status) + pr_debug("%s: status %d\n", __func__, status); + return status ? : len; +} + +static struct class_attribute gpio_class_attrs[] = { + __ATTR(export, 0200, NULL, export_store), + __ATTR(unexport, 0200, NULL, unexport_store), + __ATTR_NULL, +}; + +static struct class gpio_class = { + .name = "gpio", + .owner = THIS_MODULE, + + .class_attrs = gpio_class_attrs, +}; + + +/** + * gpio_export - export a GPIO through sysfs + * @gpio: gpio to make available, already requested + * @direction_may_change: true if userspace may change gpio direction + * Context: arch_initcall or later + * + * When drivers want to make a GPIO accessible to userspace after they + * have requested it -- perhaps while debugging, or as part of their + * public interface -- they may use this routine. If the GPIO can + * change direction (some can't) and the caller allows it, userspace + * will see "direction" sysfs attribute which may be used to change + * the gpio's direction. A "value" attribute will always be provided. + * + * Returns zero on success, else an error. + */ +int gpio_export(unsigned gpio, bool direction_may_change) +{ + unsigned long flags; + struct gpio_desc *desc; + int status = -EINVAL; + + /* can't export until sysfs is available ... */ + if (!gpio_class.p) { + pr_debug("%s: called too early!\n", __func__); + return -ENOENT; + } + + if (!gpio_is_valid(gpio)) + goto done; + + mutex_lock(&sysfs_lock); + + spin_lock_irqsave(&gpio_lock, flags); + desc = &gpio_desc[gpio]; + if (test_bit(FLAG_REQUESTED, &desc->flags) + && !test_bit(FLAG_EXPORT, &desc->flags)) { + status = 0; + if (!desc->chip->direction_input + || !desc->chip->direction_output) + direction_may_change = false; + } + spin_unlock_irqrestore(&gpio_lock, flags); + + if (status == 0) { + struct device *dev; + + dev = device_create(&gpio_class, desc->chip->dev, MKDEV(0, 0), + desc, "gpio%d", gpio); + if (dev) { + if (direction_may_change) + status = sysfs_create_group(&dev->kobj, + &gpio_attr_group); + else + status = device_create_file(dev, + &dev_attr_value); + if (status != 0) + device_unregister(dev); + } else + status = -ENODEV; + if (status == 0) + set_bit(FLAG_EXPORT, &desc->flags); + } + + mutex_unlock(&sysfs_lock); + +done: + if (status) + pr_debug("%s: gpio%d status %d\n", __func__, gpio, status); + + return status; +} +EXPORT_SYMBOL_GPL(gpio_export); + +static int match_export(struct device *dev, void *data) +{ + return dev_get_drvdata(dev) == data; +} + +/** + * gpio_unexport - reverse effect of gpio_export() + * @gpio: gpio to make unavailable + * + * This is implicit on gpio_free(). + */ +void gpio_unexport(unsigned gpio) +{ + struct gpio_desc *desc; + int status = -EINVAL; + + if (!gpio_is_valid(gpio)) + goto done; + + mutex_lock(&sysfs_lock); + + desc = &gpio_desc[gpio]; + if (test_bit(FLAG_EXPORT, &desc->flags)) { + struct device *dev = NULL; + + dev = class_find_device(&gpio_class, NULL, desc, match_export); + if (dev) { + clear_bit(FLAG_EXPORT, &desc->flags); + put_device(dev); + device_unregister(dev); + status = 0; + } else + status = -ENODEV; + } + + mutex_unlock(&sysfs_lock); +done: + if (status) + pr_debug("%s: gpio%d status %d\n", __func__, gpio, status); +} +EXPORT_SYMBOL_GPL(gpio_unexport); + +static int gpiochip_export(struct gpio_chip *chip) +{ + int status; + struct device *dev; + + /* Many systems register gpio chips for SOC support very early, + * before driver model support is available. In those cases we + * export this later, in gpiolib_sysfs_init() ... here we just + * verify that _some_ field of gpio_class got initialized. + */ + if (!gpio_class.p) + return 0; + + /* use chip->base for the ID; it's already known to be unique */ + mutex_lock(&sysfs_lock); + dev = device_create(&gpio_class, chip->dev, MKDEV(0, 0), chip, + "gpiochip%d", chip->base); + if (dev) { + status = sysfs_create_group(&dev->kobj, + &gpiochip_attr_group); + } else + status = -ENODEV; + chip->exported = (status == 0); + mutex_unlock(&sysfs_lock); + + if (status) { + unsigned long flags; + unsigned gpio; + + spin_lock_irqsave(&gpio_lock, flags); + gpio = chip->base; + while (gpio_desc[gpio].chip == chip) + gpio_desc[gpio++].chip = NULL; + spin_unlock_irqrestore(&gpio_lock, flags); + + pr_debug("%s: chip %s status %d\n", __func__, + chip->label, status); + } + + return status; +} + +static void gpiochip_unexport(struct gpio_chip *chip) +{ + int status; + struct device *dev; + + mutex_lock(&sysfs_lock); + dev = class_find_device(&gpio_class, NULL, chip, match_export); + if (dev) { + put_device(dev); + device_unregister(dev); + chip->exported = 0; + status = 0; + } else + status = -ENODEV; + mutex_unlock(&sysfs_lock); + + if (status) + pr_debug("%s: chip %s status %d\n", __func__, + chip->label, status); +} + +static int __init gpiolib_sysfs_init(void) +{ + int status; + unsigned long flags; + unsigned gpio; + + status = class_register(&gpio_class); + if (status < 0) + return status; + + /* Scan and register the gpio_chips which registered very + * early (e.g. before the class_register above was called). + * + * We run before arch_initcall() so chip->dev nodes can have + * registered, and so arch_initcall() can always gpio_export(). + */ + spin_lock_irqsave(&gpio_lock, flags); + for (gpio = 0; gpio < ARCH_NR_GPIOS; gpio++) { + struct gpio_chip *chip; + + chip = gpio_desc[gpio].chip; + if (!chip || chip->exported) + continue; + + spin_unlock_irqrestore(&gpio_lock, flags); + status = gpiochip_export(chip); + spin_lock_irqsave(&gpio_lock, flags); + } + spin_unlock_irqrestore(&gpio_lock, flags); + + + return status; +} +postcore_initcall(gpiolib_sysfs_init); + +#else +static inline int gpiochip_export(struct gpio_chip *chip) +{ + return 0; +} + +static inline void gpiochip_unexport(struct gpio_chip *chip) +{ +} + +#endif /* CONFIG_GPIO_SYSFS */ + /** * gpiochip_add() - register a gpio_chip * @chip: the chip to register, with chip->base initialized @@ -160,6 +641,11 @@ err: * because the chip->base is invalid or already associated with a * different chip. Otherwise it returns zero as a success code. * + * When gpiochip_add() is called very early during boot, so that GPIOs + * can be freely used, the chip->dev device must be registered before + * the gpio framework's arch_initcall(). Otherwise sysfs initialization + * for GPIOs will fail rudely. + * * If chip->base is negative, this requests dynamic assignment of * a range of valid GPIOs. */ @@ -182,7 +668,7 @@ int gpiochip_add(struct gpio_chip *chip) base = gpiochip_find_base(chip->ngpio); if (base < 0) { status = base; - goto fail_unlock; + goto unlock; } chip->base = base; } @@ -197,12 +683,23 @@ int gpiochip_add(struct gpio_chip *chip) if (status == 0) { for (id = base; id < base + chip->ngpio; id++) { gpio_desc[id].chip = chip; - gpio_desc[id].flags = 0; + + /* REVISIT: most hardware initializes GPIOs as + * inputs (often with pullups enabled) so power + * usage is minimized. Linux code should set the + * gpio direction first thing; but until it does, + * we may expose the wrong direction in sysfs. + */ + gpio_desc[id].flags = !chip->direction_input + ? (1 << FLAG_IS_OUT) + : 0; } } -fail_unlock: +unlock: spin_unlock_irqrestore(&gpio_lock, flags); + if (status == 0) + status = gpiochip_export(chip); fail: /* failures here can mean systems won't boot... */ if (status) @@ -239,6 +736,10 @@ int gpiochip_remove(struct gpio_chip *chip) } spin_unlock_irqrestore(&gpio_lock, flags); + + if (status == 0) + gpiochip_unexport(chip); + return status; } EXPORT_SYMBOL_GPL(gpiochip_remove); @@ -296,6 +797,8 @@ void gpio_free(unsigned gpio) return; } + gpio_unexport(gpio); + spin_lock_irqsave(&gpio_lock, flags); desc = &gpio_desc[gpio]; @@ -534,10 +1037,6 @@ EXPORT_SYMBOL_GPL(gpio_set_value_cansleep); #ifdef CONFIG_DEBUG_FS -#include -#include - - static void gpiolib_dbg_show(struct seq_file *s, struct gpio_chip *chip) { unsigned i; @@ -614,17 +1113,28 @@ static int gpiolib_show(struct seq_file *s, void *unused) /* REVISIT this isn't locked against gpio_chip removal ... */ for (gpio = 0; gpio_is_valid(gpio); gpio++) { + struct device *dev; + if (chip == gpio_desc[gpio].chip) continue; chip = gpio_desc[gpio].chip; if (!chip) continue; - seq_printf(s, "%sGPIOs %d-%d, %s%s:\n", + seq_printf(s, "%sGPIOs %d-%d", started ? "\n" : "", - chip->base, chip->base + chip->ngpio - 1, - chip->label ? : "generic", - chip->can_sleep ? ", can sleep" : ""); + chip->base, chip->base + chip->ngpio - 1); + dev = chip->dev; + if (dev) + seq_printf(s, ", %s/%s", + dev->bus ? dev->bus->name : "no-bus", + dev->bus_id); + if (chip->label) + seq_printf(s, ", %s", chip->label); + if (chip->can_sleep) + seq_printf(s, ", can sleep"); + seq_printf(s, ":\n"); + started = 1; if (chip->dbg_show) chip->dbg_show(s, chip); diff --git a/drivers/gpio/mcp23s08.c b/drivers/gpio/mcp23s08.c index 7f92fdd5f0e2..7efd7d3a81f9 100644 --- a/drivers/gpio/mcp23s08.c +++ b/drivers/gpio/mcp23s08.c @@ -239,6 +239,7 @@ static int mcp23s08_probe(struct spi_device *spi) mcp->chip.base = pdata->base; mcp->chip.ngpio = 8; mcp->chip.can_sleep = 1; + mcp->chip.dev = &spi->dev; mcp->chip.owner = THIS_MODULE; spi_set_drvdata(spi, mcp); diff --git a/drivers/gpio/pca953x.c b/drivers/gpio/pca953x.c index a380730b61ab..cc8468692ae0 100644 --- a/drivers/gpio/pca953x.c +++ b/drivers/gpio/pca953x.c @@ -188,6 +188,7 @@ static void pca953x_setup_gpio(struct pca953x_chip *chip, int gpios) gc->base = chip->gpio_start; gc->ngpio = gpios; gc->label = chip->client->name; + gc->dev = &chip->client->dev; gc->owner = THIS_MODULE; } diff --git a/drivers/gpio/pcf857x.c b/drivers/gpio/pcf857x.c index d25d356c4f20..fc9c6ae739ee 100644 --- a/drivers/gpio/pcf857x.c +++ b/drivers/gpio/pcf857x.c @@ -200,6 +200,7 @@ static int pcf857x_probe(struct i2c_client *client, gpio->chip.base = pdata->gpio_base; gpio->chip.can_sleep = 1; + gpio->chip.dev = &client->dev; gpio->chip.owner = THIS_MODULE; /* NOTE: the OnSemi jlc1562b is also largely compatible with diff --git a/drivers/i2c/chips/tps65010.c b/drivers/i2c/chips/tps65010.c index 85949685191b..cf02e8fceb42 100644 --- a/drivers/i2c/chips/tps65010.c +++ b/drivers/i2c/chips/tps65010.c @@ -636,6 +636,8 @@ static int tps65010_probe(struct i2c_client *client, tps->outmask = board->outmask; tps->chip.label = client->name; + tps->chip.dev = &client->dev; + tps->chip.owner = THIS_MODULE; tps->chip.set = tps65010_gpio_set; tps->chip.direction_output = tps65010_output; diff --git a/drivers/mfd/htc-egpio.c b/drivers/mfd/htc-egpio.c index 8872cc077519..6be43172dc65 100644 --- a/drivers/mfd/htc-egpio.c +++ b/drivers/mfd/htc-egpio.c @@ -318,6 +318,8 @@ static int __init egpio_probe(struct platform_device *pdev) ei->chip[i].dev = &(pdev->dev); chip = &(ei->chip[i].chip); chip->label = "htc-egpio"; + chip->dev = &pdev->dev; + chip->owner = THIS_MODULE; chip->get = egpio_get; chip->set = egpio_set; chip->direction_input = egpio_direction_input; diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h index 6be061d09da9..1beff5166e53 100644 --- a/include/asm-generic/gpio.h +++ b/include/asm-generic/gpio.h @@ -32,6 +32,8 @@ struct module; /** * struct gpio_chip - abstract a GPIO controller * @label: for diagnostics + * @dev: optional device providing the GPIOs + * @owner: helps prevent removal of modules exporting active GPIOs * @direction_input: configures signal "offset" as input, or returns error * @get: returns value for signal "offset"; for output signals this * returns either the value actually sensed, or zero @@ -59,6 +61,7 @@ struct module; */ struct gpio_chip { char *label; + struct device *dev; struct module *owner; int (*direction_input)(struct gpio_chip *chip, @@ -74,6 +77,7 @@ struct gpio_chip { int base; u16 ngpio; unsigned can_sleep:1; + unsigned exported:1; }; extern const char *gpiochip_is_requested(struct gpio_chip *chip, @@ -108,7 +112,18 @@ extern void __gpio_set_value(unsigned gpio, int value); extern int __gpio_cansleep(unsigned gpio); -#else +#ifdef CONFIG_GPIO_SYSFS + +/* + * A sysfs interface can be exported by individual drivers if they want, + * but more typically is configured entirely from userspace. + */ +extern int gpio_export(unsigned gpio, bool direction_may_change); +extern void gpio_unexport(unsigned gpio); + +#endif /* CONFIG_GPIO_SYSFS */ + +#else /* !CONFIG_HAVE_GPIO_LIB */ static inline int gpio_is_valid(int number) { @@ -137,6 +152,20 @@ static inline void gpio_set_value_cansleep(unsigned gpio, int value) gpio_set_value(gpio, value); } -#endif +#endif /* !CONFIG_HAVE_GPIO_LIB */ + +#ifndef CONFIG_GPIO_SYSFS + +/* sysfs support is only available with gpiolib, where it's optional */ + +static inline int gpio_export(unsigned gpio, bool direction_may_change) +{ + return -ENOSYS; +} + +static inline void gpio_unexport(unsigned gpio) +{ +} +#endif /* CONFIG_GPIO_SYSFS */ #endif /* _ASM_GENERIC_GPIO_H */ diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 98be6c5762b9..730a20b83576 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -79,6 +79,19 @@ static inline void gpio_set_value_cansleep(unsigned gpio, int value) WARN_ON(1); } +static inline int gpio_export(unsigned gpio, bool direction_may_change) +{ + /* GPIO can never have been requested or set as {in,out}put */ + WARN_ON(1); + return -EINVAL; +} + +static inline void gpio_unexport(unsigned gpio) +{ + /* GPIO can never have been exported */ + WARN_ON(1); +} + static inline int gpio_to_irq(unsigned gpio) { /* GPIO can never have been requested or set as input */ -- cgit v1.2.3 From ff1d5c2f0268f4e32103536e2e65480b5b7b6530 Mon Sep 17 00:00:00 2001 From: Michael Buesch Date: Fri, 25 Jul 2008 01:46:10 -0700 Subject: gpio: add bt8xxgpio driver This adds the bt8xxgpio driver. The purpose of the bt8xxgpio driver is to export all of the 24 GPIO pins available on Brooktree 8xx chips to the kernel GPIO infrastructure. This makes it possible to use a physically modified BT8xx card as cheap digital GPIO card. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Michael Buesch Cc: David Brownell Cc: Stephen Rothwell Cc: Mauro Carvalho Chehab Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/bt8xxgpio.txt | 67 +++++++++ MAINTAINERS | 6 + drivers/gpio/Kconfig | 18 +++ drivers/gpio/Makefile | 1 + drivers/gpio/bt8xxgpio.c | 348 ++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 440 insertions(+) create mode 100644 Documentation/bt8xxgpio.txt create mode 100644 drivers/gpio/bt8xxgpio.c (limited to 'Documentation') diff --git a/Documentation/bt8xxgpio.txt b/Documentation/bt8xxgpio.txt new file mode 100644 index 000000000000..d8297e4ebd26 --- /dev/null +++ b/Documentation/bt8xxgpio.txt @@ -0,0 +1,67 @@ +=============================================================== +== BT8XXGPIO driver == +== == +== A driver for a selfmade cheap BT8xx based PCI GPIO-card == +== == +== For advanced documentation, see == +== http://www.bu3sch.de/btgpio.php == +=============================================================== + + +A generic digital 24-port PCI GPIO card can be built out of an ordinary +Brooktree bt848, bt849, bt878 or bt879 based analog TV tuner card. The +Brooktree chip is used in old analog Hauppauge WinTV PCI cards. You can easily +find them used for low prices on the net. + +The bt8xx chip does have 24 digital GPIO ports. +These ports are accessible via 24 pins on the SMD chip package. + + +============================================== +== How to physically access the GPIO pins == +============================================== + +The are several ways to access these pins. One might unsolder the whole chip +and put it on a custom PCI board, or one might only unsolder each individual +GPIO pin and solder that to some tiny wire. As the chip package really is tiny +there are some advanced soldering skills needed in any case. + +The physical pinouts are drawn in the following ASCII art. +The GPIO pins are marked with G00-G23 + + G G G G G G G G G G G G G G G G G G + 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 + 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 + | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | + --------------------------------------------------------------------------- + --| ^ ^ |-- + --| pin 86 pin 67 |-- + --| |-- + --| pin 61 > |-- G18 + --| |-- G19 + --| |-- G20 + --| |-- G21 + --| |-- G22 + --| pin 56 > |-- G23 + --| |-- + --| Brooktree 878/879 |-- + --| |-- + --| |-- + --| |-- + --| |-- + --| |-- + --| |-- + --| |-- + --| |-- + --| |-- + --| |-- + --| |-- + --| |-- + --| |-- + --| O |-- + --| |-- + --------------------------------------------------------------------------- + | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | + ^ + This is pin 1 + diff --git a/MAINTAINERS b/MAINTAINERS index be05ef9b7b42..4cbf6016a9b9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1043,6 +1043,12 @@ M: fujita.tomonori@lab.ntt.co.jp L: linux-scsi@vger.kernel.org S: Supported +BT8XXGPIO DRIVER +P: Michael Buesch +M: mb@bu3sch.de +W: http://bu3sch.de/btgpio.php +S: Maintained + BTTV VIDEO4LINUX DRIVER P: Mauro Carvalho Chehab M: mchehab@infradead.org diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 6ec0e35b98e3..de202dbe5300 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -83,6 +83,24 @@ config GPIO_PCF857X This driver provides an in-kernel interface to those GPIOs using platform-neutral GPIO calls. +comment "PCI GPIO expanders:" + +config GPIO_BT8XX + tristate "BT8XX GPIO abuser" + depends on PCI && VIDEO_BT848=n + help + The BT8xx frame grabber chip has 24 GPIO pins than can be abused + as a cheap PCI GPIO card. + + This chip can be found on Miro, Hauppauge and STB TV-cards. + + The card needs to be physically altered for using it as a + GPIO card. For more information on how to build a GPIO card + from a BT8xx TV card, see the documentation file at + Documentation/bt8xxgpio.txt + + If unsure, say N. + comment "SPI GPIO expanders:" config GPIO_MAX7301 diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile index 16e796dc5410..eeb2f2b20282 100644 --- a/drivers/gpio/Makefile +++ b/drivers/gpio/Makefile @@ -8,3 +8,4 @@ obj-$(CONFIG_GPIO_MAX7301) += max7301.o obj-$(CONFIG_GPIO_MCP23S08) += mcp23s08.o obj-$(CONFIG_GPIO_PCA953X) += pca953x.o obj-$(CONFIG_GPIO_PCF857X) += pcf857x.o +obj-$(CONFIG_GPIO_BT8XX) += bt8xxgpio.o diff --git a/drivers/gpio/bt8xxgpio.c b/drivers/gpio/bt8xxgpio.c new file mode 100644 index 000000000000..7a1168249dd5 --- /dev/null +++ b/drivers/gpio/bt8xxgpio.c @@ -0,0 +1,348 @@ +/* + + bt8xx GPIO abuser + + Copyright (C) 2008 Michael Buesch + + Please do _only_ contact the people listed _above_ with issues related to this driver. + All the other people listed below are not related to this driver. Their names + are only here, because this driver is derived from the bt848 driver. + + + Derived from the bt848 driver: + + Copyright (C) 1996,97,98 Ralph Metzler + & Marcus Metzler + (c) 1999-2002 Gerd Knorr + + some v4l2 code lines are taken from Justin's bttv2 driver which is + (c) 2000 Justin Schoeman + + V4L1 removal from: + (c) 2005-2006 Nickolay V. Shmyrev + + Fixes to be fully V4L2 compliant by + (c) 2006 Mauro Carvalho Chehab + + Cropping and overscan support + Copyright (C) 2005, 2006 Michael H. Schimek + Sponsored by OPQ Systems AB + + 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., 675 Mass Ave, Cambridge, MA 02139, USA. +*/ + +#include +#include +#include + +#include + +/* Steal the hardware definitions from the bttv driver. */ +#include "../media/video/bt8xx/bt848.h" + + +#define BT8XXGPIO_NR_GPIOS 24 /* We have 24 GPIO pins */ + + +struct bt8xxgpio { + spinlock_t lock; + + void __iomem *mmio; + struct pci_dev *pdev; + struct gpio_chip gpio; + +#ifdef CONFIG_PM + u32 saved_outen; + u32 saved_data; +#endif +}; + +#define bgwrite(dat, adr) writel((dat), bg->mmio+(adr)) +#define bgread(adr) readl(bg->mmio+(adr)) + + +static int modparam_gpiobase = -1/* dynamic */; +module_param_named(gpiobase, modparam_gpiobase, int, 0444); +MODULE_PARM_DESC(gpiobase, "The GPIO number base. -1 means dynamic, which is the default."); + + +static int bt8xxgpio_gpio_direction_input(struct gpio_chip *gpio, unsigned nr) +{ + struct bt8xxgpio *bg = container_of(gpio, struct bt8xxgpio, gpio); + unsigned long flags; + u32 outen, data; + + spin_lock_irqsave(&bg->lock, flags); + + data = bgread(BT848_GPIO_DATA); + data &= ~(1 << nr); + bgwrite(data, BT848_GPIO_DATA); + + outen = bgread(BT848_GPIO_OUT_EN); + outen &= ~(1 << nr); + bgwrite(outen, BT848_GPIO_OUT_EN); + + spin_unlock_irqrestore(&bg->lock, flags); + + return 0; +} + +static int bt8xxgpio_gpio_get(struct gpio_chip *gpio, unsigned nr) +{ + struct bt8xxgpio *bg = container_of(gpio, struct bt8xxgpio, gpio); + unsigned long flags; + u32 val; + + spin_lock_irqsave(&bg->lock, flags); + val = bgread(BT848_GPIO_DATA); + spin_unlock_irqrestore(&bg->lock, flags); + + return !!(val & (1 << nr)); +} + +static int bt8xxgpio_gpio_direction_output(struct gpio_chip *gpio, + unsigned nr, int val) +{ + struct bt8xxgpio *bg = container_of(gpio, struct bt8xxgpio, gpio); + unsigned long flags; + u32 outen, data; + + spin_lock_irqsave(&bg->lock, flags); + + outen = bgread(BT848_GPIO_OUT_EN); + outen |= (1 << nr); + bgwrite(outen, BT848_GPIO_OUT_EN); + + data = bgread(BT848_GPIO_DATA); + if (val) + data |= (1 << nr); + else + data &= ~(1 << nr); + bgwrite(data, BT848_GPIO_DATA); + + spin_unlock_irqrestore(&bg->lock, flags); + + return 0; +} + +static void bt8xxgpio_gpio_set(struct gpio_chip *gpio, + unsigned nr, int val) +{ + struct bt8xxgpio *bg = container_of(gpio, struct bt8xxgpio, gpio); + unsigned long flags; + u32 data; + + spin_lock_irqsave(&bg->lock, flags); + + data = bgread(BT848_GPIO_DATA); + if (val) + data |= (1 << nr); + else + data &= ~(1 << nr); + bgwrite(data, BT848_GPIO_DATA); + + spin_unlock_irqrestore(&bg->lock, flags); +} + +static void bt8xxgpio_gpio_setup(struct bt8xxgpio *bg) +{ + struct gpio_chip *c = &bg->gpio; + + c->label = bg->pdev->dev.bus_id; + c->owner = THIS_MODULE; + c->direction_input = bt8xxgpio_gpio_direction_input; + c->get = bt8xxgpio_gpio_get; + c->direction_output = bt8xxgpio_gpio_direction_output; + c->set = bt8xxgpio_gpio_set; + c->dbg_show = NULL; + c->base = modparam_gpiobase; + c->ngpio = BT8XXGPIO_NR_GPIOS; + c->can_sleep = 0; +} + +static int bt8xxgpio_probe(struct pci_dev *dev, + const struct pci_device_id *pci_id) +{ + struct bt8xxgpio *bg; + int err; + + bg = kzalloc(sizeof(*bg), GFP_KERNEL); + if (!bg) + return -ENOMEM; + + bg->pdev = dev; + spin_lock_init(&bg->lock); + + err = pci_enable_device(dev); + if (err) { + printk(KERN_ERR "bt8xxgpio: Can't enable device.\n"); + goto err_freebg; + } + if (!request_mem_region(pci_resource_start(dev, 0), + pci_resource_len(dev, 0), + "bt8xxgpio")) { + printk(KERN_WARNING "bt8xxgpio: Can't request iomem (0x%llx).\n", + (unsigned long long)pci_resource_start(dev, 0)); + err = -EBUSY; + goto err_disable; + } + pci_set_master(dev); + pci_set_drvdata(dev, bg); + + bg->mmio = ioremap(pci_resource_start(dev, 0), 0x1000); + if (!bg->mmio) { + printk(KERN_ERR "bt8xxgpio: ioremap() failed\n"); + err = -EIO; + goto err_release_mem; + } + + /* Disable interrupts */ + bgwrite(0, BT848_INT_MASK); + + /* gpio init */ + bgwrite(0, BT848_GPIO_DMA_CTL); + bgwrite(0, BT848_GPIO_REG_INP); + bgwrite(0, BT848_GPIO_OUT_EN); + + bt8xxgpio_gpio_setup(bg); + err = gpiochip_add(&bg->gpio); + if (err) { + printk(KERN_ERR "bt8xxgpio: Failed to register GPIOs\n"); + goto err_release_mem; + } + + printk(KERN_INFO "bt8xxgpio: Abusing BT8xx card for GPIOs %d to %d\n", + bg->gpio.base, bg->gpio.base + BT8XXGPIO_NR_GPIOS - 1); + + return 0; + +err_release_mem: + release_mem_region(pci_resource_start(dev, 0), + pci_resource_len(dev, 0)); + pci_set_drvdata(dev, NULL); +err_disable: + pci_disable_device(dev); +err_freebg: + kfree(bg); + + return err; +} + +static void bt8xxgpio_remove(struct pci_dev *pdev) +{ + struct bt8xxgpio *bg = pci_get_drvdata(pdev); + + gpiochip_remove(&bg->gpio); + + bgwrite(0, BT848_INT_MASK); + bgwrite(~0x0, BT848_INT_STAT); + bgwrite(0x0, BT848_GPIO_OUT_EN); + + iounmap(bg->mmio); + release_mem_region(pci_resource_start(pdev, 0), + pci_resource_len(pdev, 0)); + pci_disable_device(pdev); + + pci_set_drvdata(pdev, NULL); + kfree(bg); +} + +#ifdef CONFIG_PM +static int bt8xxgpio_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct bt8xxgpio *bg = pci_get_drvdata(pdev); + unsigned long flags; + + spin_lock_irqsave(&bg->lock, flags); + + bg->saved_outen = bgread(BT848_GPIO_OUT_EN); + bg->saved_data = bgread(BT848_GPIO_DATA); + + bgwrite(0, BT848_INT_MASK); + bgwrite(~0x0, BT848_INT_STAT); + bgwrite(0x0, BT848_GPIO_OUT_EN); + + spin_unlock_irqrestore(&bg->lock, flags); + + pci_save_state(pdev); + pci_disable_device(pdev); + pci_set_power_state(pdev, pci_choose_state(pdev, state)); + + return 0; +} + +static int bt8xxgpio_resume(struct pci_dev *pdev) +{ + struct bt8xxgpio *bg = pci_get_drvdata(pdev); + unsigned long flags; + int err; + + pci_set_power_state(pdev, 0); + err = pci_enable_device(pdev); + if (err) + return err; + pci_restore_state(pdev); + + spin_lock_irqsave(&bg->lock, flags); + + bgwrite(0, BT848_INT_MASK); + bgwrite(0, BT848_GPIO_DMA_CTL); + bgwrite(0, BT848_GPIO_REG_INP); + bgwrite(bg->saved_outen, BT848_GPIO_OUT_EN); + bgwrite(bg->saved_data & bg->saved_outen, + BT848_GPIO_DATA); + + spin_unlock_irqrestore(&bg->lock, flags); + + return 0; +} +#else +#define bt8xxgpio_suspend NULL +#define bt8xxgpio_resume NULL +#endif /* CONFIG_PM */ + +static struct pci_device_id bt8xxgpio_pci_tbl[] = { + { PCI_DEVICE(PCI_VENDOR_ID_BROOKTREE, PCI_DEVICE_ID_BT848) }, + { PCI_DEVICE(PCI_VENDOR_ID_BROOKTREE, PCI_DEVICE_ID_BT849) }, + { PCI_DEVICE(PCI_VENDOR_ID_BROOKTREE, PCI_DEVICE_ID_BT878) }, + { PCI_DEVICE(PCI_VENDOR_ID_BROOKTREE, PCI_DEVICE_ID_BT879) }, + { 0, }, +}; +MODULE_DEVICE_TABLE(pci, bt8xxgpio_pci_tbl); + +static struct pci_driver bt8xxgpio_pci_driver = { + .name = "bt8xxgpio", + .id_table = bt8xxgpio_pci_tbl, + .probe = bt8xxgpio_probe, + .remove = bt8xxgpio_remove, + .suspend = bt8xxgpio_suspend, + .resume = bt8xxgpio_resume, +}; + +static int bt8xxgpio_init(void) +{ + return pci_register_driver(&bt8xxgpio_pci_driver); +} +module_init(bt8xxgpio_init) + +static void bt8xxgpio_exit(void) +{ + pci_unregister_driver(&bt8xxgpio_pci_driver); +} +module_exit(bt8xxgpio_exit) + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Michael Buesch"); +MODULE_DESCRIPTION("Abuse a BT8xx framegrabber card as generic GPIO card"); -- cgit v1.2.3 From 7444a72effa632fcd8edc566f880d96fe213c73b Mon Sep 17 00:00:00 2001 From: Michael Buesch Date: Fri, 25 Jul 2008 01:46:11 -0700 Subject: gpiolib: allow user-selection This patch adds functionality to the gpio-lib subsystem to make it possible to enable the gpio-lib code even if the architecture code didn't request to get it built in. The archtitecture code does still need to implement the gpiolib accessor functions in its asm/gpio.h file. This patch adds the implementations for x86 and PPC. With these changes it is possible to run generic GPIO expansion cards on every architecture that implements the trivial wrapper functions. Support for more architectures can easily be added. Signed-off-by: Michael Buesch Cc: Benjamin Herrenschmidt Cc: Stephen Rothwell Cc: David Brownell Cc: Russell King Cc: Haavard Skinnemoen Cc: Jesper Nilsson Cc: Ralf Baechle Cc: Paul Mackerras Cc: Benjamin Herrenschmidt Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Jean Delvare Cc: Samuel Ortiz Cc: Kumar Gala Cc: Sam Ravnborg Cc: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/gpio.txt | 12 +++++++- arch/arm/Kconfig | 8 +++--- arch/avr32/Kconfig | 2 +- arch/mips/Kconfig | 2 +- arch/powerpc/Kconfig | 1 + arch/powerpc/platforms/52xx/Kconfig | 2 +- arch/powerpc/sysdev/qe_lib/Kconfig | 2 +- arch/x86/Kconfig | 1 + drivers/Makefile | 2 +- drivers/gpio/Kconfig | 33 ++++++++++++++++++--- drivers/gpio/Makefile | 2 +- drivers/i2c/chips/Kconfig | 2 +- drivers/mfd/Kconfig | 4 +-- drivers/of/Kconfig | 2 +- include/asm-generic/gpio.h | 2 +- include/asm-mips/mach-generic/gpio.h | 2 +- include/asm-powerpc/gpio.h | 4 +-- include/asm-x86/gpio.h | 56 ++++++++++++++++++++++++++++++++++++ 18 files changed, 116 insertions(+), 23 deletions(-) (limited to 'Documentation') diff --git a/Documentation/gpio.txt b/Documentation/gpio.txt index 8b69811a9642..18022e249c53 100644 --- a/Documentation/gpio.txt +++ b/Documentation/gpio.txt @@ -389,11 +389,21 @@ either NULL or the label associated with that GPIO when it was requested. Platform Support ---------------- -To support this framework, a platform's Kconfig will "select HAVE_GPIO_LIB" +To support this framework, a platform's Kconfig will "select" either +ARCH_REQUIRE_GPIOLIB or ARCH_WANT_OPTIONAL_GPIOLIB and arrange that its includes and defines three functions: gpio_get_value(), gpio_set_value(), and gpio_cansleep(). They may also want to provide a custom value for ARCH_NR_GPIOS. +ARCH_REQUIRE_GPIOLIB means that the gpio-lib code will always get compiled +into the kernel on that architecture. + +ARCH_WANT_OPTIONAL_GPIOLIB means the gpio-lib code defaults to off and the user +can enable it and build it into the kernel optionally. + +If neither of these options are selected, the platform does not support +GPIOs through GPIO-lib and the code cannot be enabled by the user. + Trivial implementations of those functions can directly use framework code, which always dispatches through the gpio_chip: diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 6fb4f03369f2..dabb015aa40b 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -268,7 +268,7 @@ config ARCH_EP93XX select GENERIC_GPIO select HAVE_CLK select HAVE_CLK - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB help This enables support for the Cirrus EP93xx series of CPUs. @@ -447,7 +447,7 @@ config ARCH_PXA select ARCH_MTD_XIP select GENERIC_GPIO select HAVE_CLK - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB select GENERIC_TIME select GENERIC_CLOCKEVENTS select TICK_ONESHOT @@ -479,7 +479,7 @@ config ARCH_SA1100 select GENERIC_CLOCKEVENTS select HAVE_CLK select TICK_ONESHOT - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB help Support for StrongARM 11x0 based boards. @@ -522,7 +522,7 @@ config ARCH_OMAP bool "TI OMAP" select GENERIC_GPIO select HAVE_CLK - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB select GENERIC_TIME select GENERIC_CLOCKEVENTS help diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig index df4adefedb42..7c239a916275 100644 --- a/arch/avr32/Kconfig +++ b/arch/avr32/Kconfig @@ -88,7 +88,7 @@ config PLATFORM_AT32AP select SUBARCH_AVR32B select MMU select PERFORMANCE_COUNTERS - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB select GENERIC_ALLOCATOR # diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index b9c754f4070c..b4c4eaa5dd26 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -713,7 +713,7 @@ config CSRC_SB1250 config GPIO_TXX9 select GENERIC_GPIO - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB bool config CFE diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index de6b49cd6be8..fe88418167c5 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -110,6 +110,7 @@ config PPC default y select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE + select ARCH_WANT_OPTIONAL_GPIOLIB select HAVE_IDE select HAVE_IOREMAP_PROT select HAVE_EFFICIENT_UNALIGNED_ACCESS diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig index d664b1bce381..ccbd4958412e 100644 --- a/arch/powerpc/platforms/52xx/Kconfig +++ b/arch/powerpc/platforms/52xx/Kconfig @@ -48,6 +48,6 @@ config PPC_MPC5200_BUGFIX config PPC_MPC5200_GPIO bool "MPC5200 GPIO support" depends on PPC_MPC52xx - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB help Enable gpiolib support for mpc5200 based boards diff --git a/arch/powerpc/sysdev/qe_lib/Kconfig b/arch/powerpc/sysdev/qe_lib/Kconfig index 4bb18f57901e..1ce546462be5 100644 --- a/arch/powerpc/sysdev/qe_lib/Kconfig +++ b/arch/powerpc/sysdev/qe_lib/Kconfig @@ -29,7 +29,7 @@ config QE_GPIO bool "QE GPIO support" depends on QUICC_ENGINE select GENERIC_GPIO - select HAVE_GPIO_LIB + select ARCH_REQUIRE_GPIOLIB help Say Y here if you're going to use hardware that connects to the QE GPIOs. diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 66f3ab05b18c..e3cba0b45600 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -23,6 +23,7 @@ config X86 select HAVE_OPROFILE select HAVE_IOREMAP_PROT select HAVE_KPROBES + select ARCH_WANT_OPTIONAL_GPIOLIB if !X86_RDC321X select HAVE_KRETPROBES select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE diff --git a/drivers/Makefile b/drivers/Makefile index 808e0ae66aa8..54ec5e718c0e 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -5,7 +5,7 @@ # Rewritten to use lists instead of if-statements. # -obj-$(CONFIG_HAVE_GPIO_LIB) += gpio/ +obj-y += gpio/ obj-$(CONFIG_PCI) += pci/ obj-$(CONFIG_PARISC) += parisc/ obj-$(CONFIG_RAPIDIO) += rapidio/ diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index de202dbe5300..5a355f829167 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -2,15 +2,40 @@ # GPIO infrastructure and expanders # -config HAVE_GPIO_LIB +config ARCH_WANT_OPTIONAL_GPIOLIB bool + help + Select this config option from the architecture Kconfig, if + it is possible to use gpiolib on the architecture, but let the + user decide whether to actually build it or not. + Select this instead of ARCH_REQUIRE_GPIOLIB, if your architecture does + not depend on GPIOs being available, but rather let the user + decide whether he needs it or not. + +config ARCH_REQUIRE_GPIOLIB + bool + select GPIOLIB help Platforms select gpiolib if they use this infrastructure for all their GPIOs, usually starting with ones integrated into SOC processors. + Selecting this from the architecture code will cause the gpiolib + code to always get built in. + + + +menuconfig GPIOLIB + bool "GPIO Support" + depends on ARCH_WANT_OPTIONAL_GPIOLIB || ARCH_REQUIRE_GPIOLIB + select GENERIC_GPIO + help + This enables GPIO support through the generic GPIO library. + You only need to enable this, if you also want to enable + one or more of the GPIO expansion card drivers below. + + If unsure, say N. -menu "GPIO Support" - depends on HAVE_GPIO_LIB +if GPIOLIB config DEBUG_GPIO bool "Debug GPIO calls" @@ -116,4 +141,4 @@ config GPIO_MCP23S08 SPI driver for Microchip MCP23S08 I/O expander. This provides a GPIO interface supporting inputs and outputs. -endmenu +endif diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile index eeb2f2b20282..8c45948d1fe7 100644 --- a/drivers/gpio/Makefile +++ b/drivers/gpio/Makefile @@ -2,7 +2,7 @@ ccflags-$(CONFIG_DEBUG_GPIO) += -DDEBUG -obj-$(CONFIG_HAVE_GPIO_LIB) += gpiolib.o +obj-$(CONFIG_GPIOLIB) += gpiolib.o obj-$(CONFIG_GPIO_MAX7301) += max7301.o obj-$(CONFIG_GPIO_MCP23S08) += mcp23s08.o diff --git a/drivers/i2c/chips/Kconfig b/drivers/i2c/chips/Kconfig index 50e0a4653741..a95cb9465d65 100644 --- a/drivers/i2c/chips/Kconfig +++ b/drivers/i2c/chips/Kconfig @@ -126,7 +126,7 @@ config ISP1301_OMAP config TPS65010 tristate "TPS6501x Power Management chips" - depends on HAVE_GPIO_LIB + depends on GPIOLIB default y if MACH_OMAP_H2 || MACH_OMAP_H3 || MACH_OMAP_OSK help If you say yes here you get support for the TPS6501x series of diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index bac9e973ece0..1f57a99fd968 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -36,7 +36,7 @@ config MFD_ASIC3 config HTC_EGPIO bool "HTC EGPIO support" - depends on GENERIC_HARDIRQS && HAVE_GPIO_LIB && ARM + depends on GENERIC_HARDIRQS && GPIOLIB && ARM help This driver supports the CPLD egpio chip present on several HTC phones. It provides basic support for input @@ -52,7 +52,7 @@ config HTC_PASIC3 config MFD_TC6393XB bool "Support Toshiba TC6393XB" - depends on HAVE_GPIO_LIB + depends on GPIOLIB select MFD_CORE help Support for Toshiba Mobile IO Controller TC6393XB diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig index 3a7a11a75fb4..1d7ec3129349 100644 --- a/drivers/of/Kconfig +++ b/drivers/of/Kconfig @@ -4,7 +4,7 @@ config OF_DEVICE config OF_GPIO def_bool y - depends on OF && PPC_OF && HAVE_GPIO_LIB + depends on OF && PPC_OF && GPIOLIB help OpenFirmware GPIO accessors diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h index 1beff5166e53..a3034d20ebd5 100644 --- a/include/asm-generic/gpio.h +++ b/include/asm-generic/gpio.h @@ -3,7 +3,7 @@ #include -#ifdef CONFIG_HAVE_GPIO_LIB +#ifdef CONFIG_GPIOLIB #include diff --git a/include/asm-mips/mach-generic/gpio.h b/include/asm-mips/mach-generic/gpio.h index e6b376bd9d06..b4e70208da64 100644 --- a/include/asm-mips/mach-generic/gpio.h +++ b/include/asm-mips/mach-generic/gpio.h @@ -1,7 +1,7 @@ #ifndef __ASM_MACH_GENERIC_GPIO_H #define __ASM_MACH_GENERIC_GPIO_H -#ifdef CONFIG_HAVE_GPIO_LIB +#ifdef CONFIG_GPIOLIB #define gpio_get_value __gpio_get_value #define gpio_set_value __gpio_set_value #define gpio_cansleep __gpio_cansleep diff --git a/include/asm-powerpc/gpio.h b/include/asm-powerpc/gpio.h index 77ad3a890f30..ea04632399d8 100644 --- a/include/asm-powerpc/gpio.h +++ b/include/asm-powerpc/gpio.h @@ -17,7 +17,7 @@ #include #include -#ifdef CONFIG_HAVE_GPIO_LIB +#ifdef CONFIG_GPIOLIB /* * We don't (yet) implement inlined/rapid versions for on-chip gpios. @@ -51,6 +51,6 @@ static inline int irq_to_gpio(unsigned int irq) return -EINVAL; } -#endif /* CONFIG_HAVE_GPIO_LIB */ +#endif /* CONFIG_GPIOLIB */ #endif /* __ASM_POWERPC_GPIO_H */ diff --git a/include/asm-x86/gpio.h b/include/asm-x86/gpio.h index ff87fca0caf9..116e9147fe66 100644 --- a/include/asm-x86/gpio.h +++ b/include/asm-x86/gpio.h @@ -1,6 +1,62 @@ +/* + * Generic GPIO API implementation for x86. + * + * Derived from the generic GPIO API for powerpc: + * + * Copyright (c) 2007-2008 MontaVista Software, Inc. + * + * Author: Anton Vorontsov + * + * 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. + */ + #ifndef _ASM_I386_GPIO_H #define _ASM_I386_GPIO_H +#ifdef CONFIG_X86_RDC321X #include +#else /* CONFIG_X86_RDC321X */ + +#include + +#ifdef CONFIG_GPIOLIB + +/* + * Just call gpiolib. + */ +static inline int gpio_get_value(unsigned int gpio) +{ + return __gpio_get_value(gpio); +} + +static inline void gpio_set_value(unsigned int gpio, int value) +{ + __gpio_set_value(gpio, value); +} + +static inline int gpio_cansleep(unsigned int gpio) +{ + return __gpio_cansleep(gpio); +} + +/* + * Not implemented, yet. + */ +static inline int gpio_to_irq(unsigned int gpio) +{ + return -ENOSYS; +} + +static inline int irq_to_gpio(unsigned int irq) +{ + return -EINVAL; +} + +#endif /* CONFIG_GPIOLIB */ + +#endif /* CONFIG_X86_RDC321X */ #endif /* _ASM_I386_GPIO_H */ -- cgit v1.2.3 From 41003cde95e7e976d3876dbdcdc83dd0a9059279 Mon Sep 17 00:00:00 2001 From: Joe Peterson Date: Fri, 25 Jul 2008 01:46:48 -0700 Subject: UTC timestamp option for FAT filesystems fix Signed-off-by: Joe Peterson Acked-by: OGAWA Hirofumi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/vfat.txt | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'Documentation') diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt index 2d5e1e582e13..bbac4f1d9056 100644 --- a/Documentation/filesystems/vfat.txt +++ b/Documentation/filesystems/vfat.txt @@ -96,6 +96,14 @@ shortname=lower|win95|winnt|mixed emulate the Windows 95 rule for create. Default setting is `lower'. +tz=UTC -- Interpret timestamps as UTC rather than local time. + This option disables the conversion of timestamps + between local time (as used by Windows on FAT) and UTC + (which Linux uses internally). This is particuluarly + useful when mounting devices (like digital cameras) + that are set to UTC in order to avoid the pitfalls of + local time. + : 0,1,yes,no,true,false TODO -- cgit v1.2.3 From 9d96d82da437ed5f2053821779ed5d7797ed1f81 Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Fri, 25 Jul 2008 01:46:53 -0700 Subject: procfs-guide: drop pointless   entities Having trailing   entities in a revision numer seems pretty pointless to me. More so, it's causing me pains, so just drop them since no other guide is doing this. Signed-off-by: Mike Frysinger Acked-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/DocBook/procfs-guide.tmpl | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/DocBook/procfs-guide.tmpl b/Documentation/DocBook/procfs-guide.tmpl index 1fd6a1ec7591..8a5dc6e021ff 100644 --- a/Documentation/DocBook/procfs-guide.tmpl +++ b/Documentation/DocBook/procfs-guide.tmpl @@ -29,12 +29,12 @@ - 1.0  + 1.0 May 30, 2001 Initial revision posted to linux-kernel - 1.1  + 1.1 June 3, 2001 Revised after comments from linux-kernel -- cgit v1.2.3 From 628f42355389cfb596ca3a5a5f64fb9054a2a06a Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Fri, 25 Jul 2008 01:47:20 -0700 Subject: memcg: limit change shrink usage Shrinking memory usage at limit change. [akpm@linux-foundation.org: coding-style fixes] Acked-by: Balbir Singh Acked-by: Pavel Emelyanov Signed-off-by: KAMEZAWA Hiroyuki Cc: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/controllers/memory.txt | 3 +-- mm/memcontrol.c | 48 +++++++++++++++++++++++++++++++++--- 2 files changed, 45 insertions(+), 6 deletions(-) (limited to 'Documentation') diff --git a/Documentation/controllers/memory.txt b/Documentation/controllers/memory.txt index 866b9cd9a959..9b53d5827361 100644 --- a/Documentation/controllers/memory.txt +++ b/Documentation/controllers/memory.txt @@ -242,8 +242,7 @@ rmdir() if there are no tasks. 1. Add support for accounting huge pages (as a separate controller) 2. Make per-cgroup scanner reclaim not-shared pages first 3. Teach controller to account for shared-pages -4. Start reclamation when the limit is lowered -5. Start reclamation in the background when the limit is +4. Start reclamation in the background when the limit is not yet hit but the usage is getting closer Summary diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0c035647d36a..fba566c51322 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -812,6 +812,30 @@ int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask) return 0; } +int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val) +{ + + int retry_count = MEM_CGROUP_RECLAIM_RETRIES; + int progress; + int ret = 0; + + while (res_counter_set_limit(&memcg->res, val)) { + if (signal_pending(current)) { + ret = -EINTR; + break; + } + if (!retry_count) { + ret = -EBUSY; + break; + } + progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL); + if (!progress) + retry_count--; + } + return ret; +} + + /* * This routine traverse page_cgroup in given list and drop them all. * *And* this routine doesn't reclaim page itself, just removes page_cgroup. @@ -896,13 +920,29 @@ static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft) return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res, cft->private); } - +/* + * The user of this function is... + * RES_LIMIT. + */ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, const char *buffer) { - return res_counter_write(&mem_cgroup_from_cont(cont)->res, - cft->private, buffer, - res_counter_memparse_write_strategy); + struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + unsigned long long val; + int ret; + + switch (cft->private) { + case RES_LIMIT: + /* This function does all necessary parse...reuse it */ + ret = res_counter_memparse_write_strategy(buffer, &val); + if (!ret) + ret = mem_cgroup_resize_limit(memcg, val); + break; + default: + ret = -EINVAL; /* should be BUG() ? */ + break; + } + return ret; } static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) -- cgit v1.2.3 From 729f0edbecd0c59c82ee9bf92009acc7e984c425 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 25 Jul 2008 01:48:20 -0700 Subject: Char: mxser, update documentation Update Documentation/moxa-smartio to the later document from the mxser package. Signed-off-by: Jiri Slaby Acked-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/moxa-smartio | 392 +++++++++++++++++++++++++++++---------------- 1 file changed, 252 insertions(+), 140 deletions(-) (limited to 'Documentation') diff --git a/Documentation/moxa-smartio b/Documentation/moxa-smartio index fe24ecc6372e..5337e80a5b96 100644 --- a/Documentation/moxa-smartio +++ b/Documentation/moxa-smartio @@ -1,14 +1,22 @@ ============================================================================= - - MOXA Smartio Family Device Driver Ver 1.1 Installation Guide - for Linux Kernel 2.2.x and 2.0.3x - Copyright (C) 1999, Moxa Technologies Co, Ltd. + MOXA Smartio/Industio Family Device Driver Installation Guide + for Linux Kernel 2.4.x, 2.6.x + Copyright (C) 2008, Moxa Inc. ============================================================================= +Date: 01/21/2008 + Content 1. Introduction 2. System Requirement 3. Installation + 3.1 Hardware installation + 3.2 Driver files + 3.3 Device naming convention + 3.4 Module driver configuration + 3.5 Static driver configuration for Linux kernel 2.4.x and 2.6.x. + 3.6 Custom configuration + 3.7 Verify driver installation 4. Utilities 5. Setserial 6. Troubleshooting @@ -16,27 +24,48 @@ Content ----------------------------------------------------------------------------- 1. Introduction - The Smartio family Linux driver, Ver. 1.1, supports following multiport + The Smartio/Industio/UPCI family Linux driver supports following multiport boards. - -C104P/H/HS, C104H/PCI, C104HS/PCI, CI-104J 4 port multiport board. - -C168P/H/HS, C168H/PCI 8 port multiport board. - - This driver has been modified a little and cleaned up from the Moxa - contributed driver code and merged into Linux 2.2.14pre. In particular - official major/minor numbers have been assigned which are different to - those the original Moxa supplied driver used. + - 2 ports multiport board + CP-102U, CP-102UL, CP-102UF + CP-132U-I, CP-132UL, + CP-132, CP-132I, CP132S, CP-132IS, + CI-132, CI-132I, CI-132IS, + (C102H, C102HI, C102HIS, C102P, CP-102, CP-102S) + + - 4 ports multiport board + CP-104EL, + CP-104UL, CP-104JU, + CP-134U, CP-134U-I, + C104H/PCI, C104HS/PCI, + CP-114, CP-114I, CP-114S, CP-114IS, CP-114UL, + C104H, C104HS, + CI-104J, CI-104JS, + CI-134, CI-134I, CI-134IS, + (C114HI, CT-114I, C104P) + POS-104UL, + CB-114, + CB-134I + + - 8 ports multiport board + CP-118EL, CP-168EL, + CP-118U, CP-168U, + C168H/PCI, + C168H, C168HS, + (C168P), + CB-108 This driver and installation procedure have been developed upon Linux Kernel - 2.2.5 and backward compatible to 2.0.3x. This driver supports Intel x86 and - Alpha hardware platform. In order to maintain compatibility, this version - has also been properly tested with RedHat, OpenLinux, TurboLinux and - S.u.S.E Linux. However, if compatibility problem occurs, please contact - Moxa at support@moxa.com.tw. + 2.4.x and 2.6.x. This driver supports Intel x86 hardware platform. In order + to maintain compatibility, this version has also been properly tested with + RedHat, Mandrake, Fedora and S.u.S.E Linux. However, if compatibility problem + occurs, please contact Moxa at support@moxa.com.tw. In addition to device driver, useful utilities are also provided in this version. They are - - msdiag Diagnostic program for detecting installed Moxa Smartio boards. + - msdiag Diagnostic program for displaying installed Moxa + Smartio/Industio boards. - msmon Monitor program to observe data count and line status signals. - msterm A simple terminal program which is useful in testing serial ports. @@ -47,8 +76,7 @@ Content GNU General Public License in this version. Please refer to GNU General Public License announcement in each source code file for more detail. - In Moxa's ftp sites, you may always find latest driver at - ftp://ftp.moxa.com or ftp://ftp.moxa.com.tw. + In Moxa's Web sites, you may always find latest driver at http://web.moxa.com. This version of driver can be installed as Loadable Module (Module driver) or built-in into kernel (Static driver). You may refer to following @@ -61,18 +89,27 @@ Content ----------------------------------------------------------------------------- 2. System Requirement - - Hardware platform: Intel x86 or Alpha machine - - Kernel version: 2.0.3x or 2.2.x + - Hardware platform: Intel x86 machine + - Kernel version: 2.4.x or 2.6.x - gcc version 2.72 or later - Maximum 4 boards can be installed in combination ----------------------------------------------------------------------------- 3. Installation + 3.1 Hardware installation + 3.2 Driver files + 3.3 Device naming convention + 3.4 Module driver configuration + 3.5 Static driver configuration for Linux kernel 2.4.x, 2.6.x. + 3.6 Custom configuration + 3.7 Verify driver installation + + 3.1 Hardware installation - There are two types of buses, ISA and PCI, for Smartio family multiport - board. + There are two types of buses, ISA and PCI, for Smartio/Industio + family multiport board. ISA board --------- @@ -81,47 +118,57 @@ Content installation procedure in User's Manual before proceed any further. Please make sure the JP1 is open after the ISA board is set properly. - PCI board - --------- + PCI/UPCI board + -------------- You may need to adjust IRQ usage in BIOS to avoid from IRQ conflict with other ISA devices. Please refer to hardware installation procedure in User's Manual in advance. - IRQ Sharing + PCI IRQ Sharing ----------- Each port within the same multiport board shares the same IRQ. Up to - 4 Moxa Smartio Family multiport boards can be installed together on - one system and they can share the same IRQ. + 4 Moxa Smartio/Industio PCI Family multiport boards can be installed + together on one system and they can share the same IRQ. + - 3.2 Driver files and device naming convention + 3.2 Driver files The driver file may be obtained from ftp, CD-ROM or floppy disk. The first step, anyway, is to copy driver file "mxser.tgz" into specified directory. e.g. /moxa. The execute commands as below. + # cd / + # mkdir moxa # cd /moxa - # tar xvf /dev/fd0 + # tar xvf /dev/fd0 + or + + # cd / + # mkdir moxa # cd /moxa # cp /mnt/cdrom//mxser.tgz . # tar xvfz mxser.tgz + + 3.3 Device naming convention + You may find all the driver and utilities files in /moxa/mxser. Following installation procedure depends on the model you'd like to - run the driver. If you prefer module driver, please refer to 3.3. - If static driver is required, please refer to 3.4. + run the driver. If you prefer module driver, please refer to 3.4. + If static driver is required, please refer to 3.5. Dialin and callout port ----------------------- - This driver remains traditional serial device properties. There're + This driver remains traditional serial device properties. There are two special file name for each serial port. One is dial-in port which is named "ttyMxx". For callout port, the naming convention is "cumxx". Device naming when more than 2 boards installed ----------------------------------------------- - Naming convention for each Smartio multiport board is pre-defined - as below. + Naming convention for each Smartio/Industio multiport board is + pre-defined as below. Board Num. Dial-in Port Callout port 1st board ttyM0 - ttyM7 cum0 - cum7 @@ -129,6 +176,12 @@ Content 3rd board ttyM16 - ttyM23 cum16 - cum23 4th board ttyM24 - ttym31 cum24 - cum31 + + !!!!!!!!!!!!!!!!!!!! NOTE !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! + Under Kernel 2.6 the cum Device is Obsolete. So use ttyM* + device instead. + !!!!!!!!!!!!!!!!!!!! NOTE !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! + Board sequence -------------- This driver will activate ISA boards according to the parameter set @@ -138,69 +191,131 @@ Content For PCI boards, their sequence will be after ISA boards and C168H/PCI has higher priority than C104H/PCI boards. - 3.3 Module driver configuration + 3.4 Module driver configuration Module driver is easiest way to install. If you prefer static driver installation, please skip this paragraph. - 1. Find "Makefile" in /moxa/mxser, then run - # make install + + ------------- Prepare to use the MOXA driver-------------------- + 3.4.1 Create tty device with correct major number + Before using MOXA driver, your system must have the tty devices + which are created with driver's major number. We offer one shell + script "msmknod" to simplify the procedure. + This step is only needed to be executed once. But you still + need to do this procedure when: + a. You change the driver's major number. Please refer the "3.7" + section. + b. Your total installed MOXA boards number is changed. Maybe you + add/delete one MOXA board. + c. You want to change the tty name. This needs to modify the + shell script "msmknod" + + The procedure is: + # cd /moxa/mxser/driver + # ./msmknod + + This shell script will require the major number for dial-in + device and callout device to create tty device. You also need + to specify the total installed MOXA board number. Default major + numbers for dial-in device and callout device are 30, 35. If + you need to change to other number, please refer section "3.7" + for more detailed procedure. + Msmknod will delete any special files occupying the same device + naming. + + 3.4.2 Build the MOXA driver and utilities + Before using the MOXA driver and utilities, you need compile the + all the source code. This step is only need to be executed once. + But you still re-compile the source code if you modify the source + code. For example, if you change the driver's major number (see + "3.7" section), then you need to do this step again. + + Find "Makefile" in /moxa/mxser, then run + + # make clean; make install + + !!!!!!!!!! NOTE !!!!!!!!!!!!!!!!! + For Red Hat 9, Red Hat Enterprise Linux AS3/ES3/WS3 & Fedora Core1: + # make clean; make installsp1 + + For Red Hat Enterprise Linux AS4/ES4/WS4: + # make clean; make installsp2 + !!!!!!!!!! NOTE !!!!!!!!!!!!!!!!! The driver files "mxser.o" and utilities will be properly compiled - and copied to system directories respectively.Then run + and copied to system directories respectively. - # insmod mxser + ------------- Load MOXA driver-------------------- + 3.4.3 Load the MOXA driver - to activate the modular driver. You may run "lsmod" to check - if "mxser.o" is activated. + # modprobe mxser - 2. Create special files by executing "msmknod". - # cd /moxa/mxser/driver - # ./msmknod + will activate the module driver. You may run "lsmod" to check + if "mxser" is activated. If the MOXA board is ISA board, the + is needed. Please refer to section "3.4.5" for more + information. + + + ------------- Load MOXA driver on boot -------------------- + 3.4.4 For the above description, you may manually execute + "modprobe mxser" to activate this driver and run + "rmmod mxser" to remove it. + However, it's better to have a boot time configuration to + eliminate manual operation. Boot time configuration can be + achieved by rc file. We offer one "rc.mxser" file to simplify + the procedure under "moxa/mxser/driver". - Default major numbers for dial-in device and callout device are - 174, 175. Msmknod will delete any special files occupying the same - device naming. + But if you use ISA board, please modify the "modprobe ..." command + to add the argument (see "3.4.5" section). After modifying the + rc.mxser, please try to execute "/moxa/mxser/driver/rc.mxser" + manually to make sure the modification is ok. If any error + encountered, please try to modify again. If the modification is + completed, follow the below step. - 3. Up to now, you may manually execute "insmod mxser" to activate - this driver and run "rmmod mxser" to remove it. However, it's - better to have a boot time configuration to eliminate manual - operation. - Boot time configuration can be achieved by rc file. Run following - command for setting rc files. + Run following command for setting rc files. # cd /moxa/mxser/driver # cp ./rc.mxser /etc/rc.d # cd /etc/rc.d - You may have to modify part of the content in rc.mxser to specify - parameters for ISA board. Please refer to rc.mxser for more detail. - Find "rc.serial". If "rc.serial" doesn't exist, create it by vi. - Add "rc.mxser" in last line. Next, open rc.local by vi - and append following content. + Check "rc.serial" is existed or not. If "rc.serial" doesn't exist, + create it by vi, run "chmod 755 rc.serial" to change the permission. + Add "/etc/rc.d/rc.mxser" in last line, - if [ -f /etc/rc.d/rc.serial ]; then - sh /etc/rc.d/rc.serial - fi + Reboot and check if moxa.o activated by "lsmod" command. - 4. Reboot and check if mxser.o activated by "lsmod" command. - 5. If you'd like to drive Smartio ISA boards in the system, you'll - have to add parameter to specify CAP address of given board while - activating "mxser.o". The format for parameters are as follows. + 3.4.5. If you'd like to drive Smartio/Industio ISA boards in the system, + you'll have to add parameter to specify CAP address of given + board while activating "mxser.o". The format for parameters are + as follows. - insmod mxser ioaddr=0x???,0x???,0x???,0x??? + modprobe mxser ioaddr=0x???,0x???,0x???,0x??? | | | | | | | +- 4th ISA board | | +------ 3rd ISA board | +------------ 2nd ISA board +------------------- 1st ISA board - 3.4 Static driver configuration + 3.5 Static driver configuration for Linux kernel 2.4.x and 2.6.x + + Note: To use static driver, you must install the linux kernel + source package. + + 3.5.1 Backup the built-in driver in the kernel. + # cd /usr/src/linux/drivers/char + # mv mxser.c mxser.c.old + + For Red Hat 7.x user, you need to create link: + # cd /usr/src + # ln -s linux-2.4 linux - 1. Create link + 3.5.2 Create link # cd /usr/src/linux/drivers/char # ln -s /moxa/mxser/driver/mxser.c mxser.c - 2. Add CAP address list for ISA boards + 3.5.3 Add CAP address list for ISA boards. For PCI boards user, + please skip this step. + In module mode, the CAP address for ISA board is given by parameter. In static driver configuration, you'll have to assign it within driver's source code. If you will not @@ -222,73 +337,55 @@ Content static int mxserBoardCAP[] = {0x280, 0x180, 0x00, 0x00}; - 3. Modify tty_io.c - # cd /usr/src/linux/drivers/char/ - # vi tty_io.c - Find pty_init(), insert "mxser_init()" as + 3.5.4 Setup kernel configuration - pty_init(); - mxser_init(); + Configure the kernel: - 4. Modify tty.h - # cd /usr/src/linux/include/linux - # vi tty.h - Find extern int tty_init(void), insert "mxser_init()" as + # cd /usr/src/linux + # make menuconfig - extern int tty_init(void); - extern int mxser_init(void); - - 5. Modify Makefile - # cd /usr/src/linux/drivers/char - # vi Makefile - Find L_OBJS := tty_io.o ...... random.o, add - "mxser.o" at last of this line as - L_OBJS := tty_io.o ....... mxser.o + You will go into a menu-driven system. Please select [Character + devices][Non-standard serial port support], enable the [Moxa + SmartIO support] driver with "[*]" for built-in (not "[M]"), then + select [Exit] to exit this program. - 6. Rebuild kernel - The following are for Linux kernel rebuilding,for your reference only. + 3.5.5 Rebuild kernel + The following are for Linux kernel rebuilding, for your + reference only. For appropriate details, please refer to the Linux document. - If 'lilo' utility is installed, please use 'make zlilo' to rebuild - kernel. If 'lilo' is not installed, please follow the following steps. - a. cd /usr/src/linux - b. make clean /* take a few minutes */ - c. make bzImage /* take probably 10-20 minutes */ - d. Backup original boot kernel. /* optional step */ - e. cp /usr/src/linux/arch/i386/boot/bzImage /boot/vmlinuz + b. make clean /* take a few minutes */ + c. make dep /* take a few minutes */ + d. make bzImage /* take probably 10-20 minutes */ + e. make install /* copy boot image to correct position */ f. Please make sure the boot kernel (vmlinuz) is in the - correct position. If you use 'lilo' utility, you should - check /etc/lilo.conf 'image' item specified the path - which is the 'vmlinuz' path, or you will load wrong - (or old) boot kernel image (vmlinuz). - g. chmod 400 /vmlinuz - h. lilo - i. rdev -R /vmlinuz 1 - j. sync - - Note that if the result of "make zImage" is ERROR, then you have to - go back to Linux configuration Setup. Type "make config" in directory - /usr/src/linux or "setup". - - Since system include file, /usr/src/linux/include/linux/interrupt.h, - is modified each time the MOXA driver is installed, kernel rebuilding - is inevitable. And it takes about 10 to 20 minutes depends on the - machine. - - 7. Make utility - # cd /moxa/mxser/utility - # make install - - 8. Make special file + correct position. + g. If you use 'lilo' utility, you should check /etc/lilo.conf + 'image' item specified the path which is the 'vmlinuz' path, + or you will load wrong (or old) boot kernel image (vmlinuz). + After checking /etc/lilo.conf, please run "lilo". + + Note that if the result of "make bzImage" is ERROR, then you have to + go back to Linux configuration Setup. Type "make menuconfig" in + directory /usr/src/linux. + + + 3.5.6 Make tty device and special file # cd /moxa/mxser/driver # ./msmknod - 9. Reboot + 3.5.7 Make utility + # cd /moxa/mxser/utility + # make clean; make install + + 3.5.8 Reboot - 3.5 Custom configuration + + + 3.6 Custom configuration Although this driver already provides you default configuration, you - still can change the device name and major number.The instruction to + still can change the device name and major number. The instruction to change these parameters are shown as below. Change Device name @@ -306,33 +403,37 @@ Content 2 free major numbers for this driver. There are 3 steps to change major numbers. - 1. Find free major numbers + 3.6.1 Find free major numbers In /proc/devices, you may find all the major numbers occupied in the system. Please select 2 major numbers that are available. e.g. 40, 45. - 2. Create special files + 3.6.2 Create special files Run /moxa/mxser/driver/msmknod to create special files with specified major numbers. - 3. Modify driver with new major number + 3.6.3 Modify driver with new major number Run vi to open /moxa/mxser/driver/mxser.c. Locate the line contains "MXSERMAJOR". Change the content as below. #define MXSERMAJOR 40 #define MXSERCUMAJOR 45 - 4. Run # make install in /moxa/mxser/driver. + 3.6.4 Run "make clean; make install" in /moxa/mxser/driver. - 3.6 Verify driver installation + 3.7 Verify driver installation You may refer to /var/log/messages to check the latest status log reported by this driver whenever it's activated. + ----------------------------------------------------------------------------- 4. Utilities There are 3 utilities contained in this driver. They are msdiag, msmon and msterm. These 3 utilities are released in form of source code. They should be compiled into executable file and copied into /usr/bin. + Before using these utilities, please load driver (refer 3.4 & 3.5) and + make sure you had run the "msmknod" utility. + msdiag - Diagnostic -------------------- - This utility provides the function to detect what Moxa Smartio multiport - board exists in the system. + This utility provides the function to display what Moxa Smartio/Industio + board found by driver in the system. msmon - Port Monitoring ----------------------- @@ -353,12 +454,13 @@ Content application, for example, sending AT command to a modem connected to the port or used as a terminal for login purpose. Note that this is only a dumb terminal emulation without handling full screen operation. + ----------------------------------------------------------------------------- 5. Setserial Supported Setserial parameters are listed as below. - uart set UART type(16450-->disable FIFO, 16550A-->enable FIFO) + uart set UART type(16450-->disable FIFO, 16550A-->enable FIFO) close_delay set the amount of time(in 1/100 of a second) that DTR should be kept low while being closed. closing_wait set the amount of time(in 1/100 of a second) that the @@ -366,7 +468,13 @@ Content being closed, before the receiver is disable. spd_hi Use 57.6kb when the application requests 38.4kb. spd_vhi Use 115.2kb when the application requests 38.4kb. + spd_shi Use 230.4kb when the application requests 38.4kb. + spd_warp Use 460.8kb when the application requests 38.4kb. spd_normal Use 38.4kb when the application requests 38.4kb. + spd_cust Use the custom divisor to set the speed when the + application requests 38.4kb. + divisor This option set the custom divison. + baud_base This option set the base baud rate. ----------------------------------------------------------------------------- 6. Troubleshooting @@ -375,8 +483,9 @@ Content possible. If all the possible solutions fail, please contact our technical support team to get more help. - Error msg: More than 4 Moxa Smartio family boards found. Fifth board and - after are ignored. + + Error msg: More than 4 Moxa Smartio/Industio family boards found. Fifth board + and after are ignored. Solution: To avoid this problem, please unplug fifth and after board, because Moxa driver supports up to 4 boards. @@ -384,7 +493,7 @@ Content Error msg: Request_irq fail, IRQ(?) may be conflict with another device. Solution: Other PCI or ISA devices occupy the assigned IRQ. If you are not sure - which device causes the situation,please check /proc/interrupts to find + which device causes the situation, please check /proc/interrupts to find free IRQ and simply change another free IRQ for Moxa board. Error msg: Board #: C1xx Series(CAP=xxx) interrupt number invalid. @@ -397,15 +506,18 @@ Content Moxa ISA board needs an interrupt vector.Please refer to user's manual "Hardware Installation" chapter to set interrupt vector. - Error msg: Couldn't install MOXA Smartio family driver! + Error msg: Couldn't install MOXA Smartio/Industio family driver! Solution: Load Moxa driver fail, the major number may conflict with other devices. - Please refer to previous section 3.5 to change a free major number for + Please refer to previous section 3.7 to change a free major number for Moxa driver. - Error msg: Couldn't install MOXA Smartio family callout driver! + Error msg: Couldn't install MOXA Smartio/Industio family callout driver! Solution: Load Moxa callout driver fail, the callout device major number may - conflict with other devices. Please refer to previous section 3.5 to + conflict with other devices. Please refer to previous section 3.7 to change a free callout device major number for Moxa driver. + + ----------------------------------------------------------------------------- + -- cgit v1.2.3 From dbda0de52618d13d1b927c7ba7bb839cfddc4e8c Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Fri, 25 Jul 2008 01:48:37 -0700 Subject: pidns: remove find_task_by_pid, unused for a long time It seems to me that it was a mistake marking this function as deprecated and scheduling it for removal, rather than resolutely removing it after the last caller's death. Anyway - better late, then never. Signed-off-by: Pavel Emelyanov Cc: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/feature-removal-schedule.txt | 18 ------------------ include/linux/pid.h | 2 +- include/linux/sched.h | 6 ------ 3 files changed, 1 insertion(+), 25 deletions(-) (limited to 'Documentation') diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 09c4a1efb8e3..721c71b86e06 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -138,24 +138,6 @@ Who: Kay Sievers --------------------------- -What: find_task_by_pid -When: 2.6.26 -Why: With pid namespaces, calling this funciton will return the - wrong task when called from inside a namespace. - - The best way to save a task pid and find a task by this - pid later, is to find this task's struct pid pointer (or get - it directly from the task) and call pid_task() later. - - If someone really needs to get a task by its pid_t, then - he most likely needs the find_task_by_vpid() to get the - task from the same namespace as the current task is in, but - this may be not so in general. - -Who: Pavel Emelyanov - ---------------------------- - What: ACPI procfs interface When: July 2008 Why: ACPI sysfs conversion should be finished by January 2008. diff --git a/include/linux/pid.h b/include/linux/pid.h index ff1b2a5814d4..22921ac4cfd9 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -107,7 +107,7 @@ extern struct pid_namespace init_pid_ns; * find_pid_ns() finds the pid in the namespace specified * find_vpid() finr the pid by its virtual id, i.e. in the current namespace * - * see also find_task_by_pid() set in include/linux/sched.h + * see also find_task_by_vpid() set in include/linux/sched.h */ extern struct pid *find_pid_ns(int nr, struct pid_namespace *ns); extern struct pid *find_vpid(int nr); diff --git a/include/linux/sched.h b/include/linux/sched.h index 182da1550fad..354ef478a80d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1715,8 +1715,6 @@ extern struct pid_namespace init_pid_ns; * finds a task by its pid in the specified namespace * find_task_by_vpid(): * finds a task by its virtual pid - * find_task_by_pid(): - * finds a task by its global pid * * see also find_vpid() etc in include/linux/pid.h */ @@ -1724,10 +1722,6 @@ extern struct pid_namespace init_pid_ns; extern struct task_struct *find_task_by_pid_type_ns(int type, int pid, struct pid_namespace *ns); -static inline struct task_struct *__deprecated find_task_by_pid(pid_t nr) -{ - return find_task_by_pid_type_ns(PIDTYPE_PID, nr, &init_pid_ns); -} extern struct task_struct *find_task_by_vpid(pid_t nr); extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns); -- cgit v1.2.3 From 016ae219b920c4e606088761d3d6070cdf8ba706 Mon Sep 17 00:00:00 2001 From: Keika Kobayashi Date: Fri, 25 Jul 2008 01:48:53 -0700 Subject: per-task-delay-accounting: update taskstats for memory reclaim delay Add members for memory reclaim delay to taskstats, and accumulate them in __delayacct_add_tsk() . Signed-off-by: Keika Kobayashi Cc: Hiroshi Shimamoto Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/accounting/taskstats-struct.txt | 7 +++++++ include/linux/taskstats.h | 6 +++++- kernel/delayacct.c | 3 +++ 3 files changed, 15 insertions(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/accounting/taskstats-struct.txt b/Documentation/accounting/taskstats-struct.txt index cd784f46bf8a..b988d110db59 100644 --- a/Documentation/accounting/taskstats-struct.txt +++ b/Documentation/accounting/taskstats-struct.txt @@ -26,6 +26,8 @@ There are three different groups of fields in the struct taskstats: 5) Time accounting for SMT machines +6) Extended delay accounting fields for memory reclaim + Future extension should add fields to the end of the taskstats struct, and should not change the relative position of each field within the struct. @@ -170,4 +172,9 @@ struct taskstats { __u64 ac_utimescaled; /* utime scaled on frequency etc */ __u64 ac_stimescaled; /* stime scaled on frequency etc */ __u64 cpu_scaled_run_real_total; /* scaled cpu_run_real_total */ + +6) Extended delay accounting fields for memory reclaim + /* Delay waiting for memory reclaim */ + __u64 freepages_count; + __u64 freepages_delay_total; } diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h index 5d69c0744fff..18269e956a71 100644 --- a/include/linux/taskstats.h +++ b/include/linux/taskstats.h @@ -31,7 +31,7 @@ */ -#define TASKSTATS_VERSION 6 +#define TASKSTATS_VERSION 7 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -157,6 +157,10 @@ struct taskstats { __u64 ac_utimescaled; /* utime scaled on frequency etc */ __u64 ac_stimescaled; /* stime scaled on frequency etc */ __u64 cpu_scaled_run_real_total; /* scaled cpu_run_real_total */ + + /* Delay waiting for memory reclaim */ + __u64 freepages_count; + __u64 freepages_delay_total; }; diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 84b6782a2ce4..b3179dad71be 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -145,8 +145,11 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp; tmp = d->swapin_delay_total + tsk->delays->swapin_delay; d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp; + tmp = d->freepages_delay_total + tsk->delays->freepages_delay; + d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; + d->freepages_count += tsk->delays->freepages_count; spin_unlock_irqrestore(&tsk->delays->lock, flags); done: -- cgit v1.2.3 From 9b0975a20af1ff2f367e3b6b7c150eb114c6b500 Mon Sep 17 00:00:00 2001 From: Keika Kobayashi Date: Fri, 25 Jul 2008 01:48:54 -0700 Subject: per-task-delay-accounting: update document and getdelays.c for memory reclaim Update document and make getdelays.c show delay accounting for memory reclaim. For making a distinction between "swapping in pages" and "memory reclaim" in getdelays.c, MEM is changed to SWAP. Signed-off-by: Keika Kobayashi Acked-by: Balbir Singh Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/accounting/delay-accounting.txt | 11 ++++++++--- Documentation/accounting/getdelays.c | 8 ++++++-- 2 files changed, 14 insertions(+), 5 deletions(-) (limited to 'Documentation') diff --git a/Documentation/accounting/delay-accounting.txt b/Documentation/accounting/delay-accounting.txt index 1443cd71d263..8a12f0730c94 100644 --- a/Documentation/accounting/delay-accounting.txt +++ b/Documentation/accounting/delay-accounting.txt @@ -11,6 +11,7 @@ the delays experienced by a task while a) waiting for a CPU (while being runnable) b) completion of synchronous block I/O initiated by the task c) swapping in pages +d) memory reclaim and makes these statistics available to userspace through the taskstats interface. @@ -41,7 +42,7 @@ this structure. See include/linux/taskstats.h for a description of the fields pertaining to delay accounting. It will generally be in the form of counters returning the cumulative -delay seen for cpu, sync block I/O, swapin etc. +delay seen for cpu, sync block I/O, swapin, memory reclaim etc. Taking the difference of two successive readings of a given counter (say cpu_delay_total) for a task will give the delay @@ -94,7 +95,9 @@ CPU count real total virtual total delay total 7876 92005750 100000000 24001500 IO count delay total 0 0 -MEM count delay total +SWAP count delay total + 0 0 +RECLAIM count delay total 0 0 Get delays seen in executing a given simple command @@ -108,5 +111,7 @@ CPU count real total virtual total delay total 6 4000250 4000000 0 IO count delay total 0 0 -MEM count delay total +SWAP count delay total + 0 0 +RECLAIM count delay total 0 0 diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c index 40121b5cca14..3f7755f3963f 100644 --- a/Documentation/accounting/getdelays.c +++ b/Documentation/accounting/getdelays.c @@ -196,14 +196,18 @@ void print_delayacct(struct taskstats *t) " %15llu%15llu%15llu%15llu\n" "IO %15s%15s\n" " %15llu%15llu\n" - "MEM %15s%15s\n" + "SWAP %15s%15s\n" + " %15llu%15llu\n" + "RECLAIM %12s%15s\n" " %15llu%15llu\n", "count", "real total", "virtual total", "delay total", t->cpu_count, t->cpu_run_real_total, t->cpu_run_virtual_total, t->cpu_delay_total, "count", "delay total", t->blkio_count, t->blkio_delay_total, - "count", "delay total", t->swapin_count, t->swapin_delay_total); + "count", "delay total", t->swapin_count, t->swapin_delay_total, + "count", "delay total", + t->freepages_count, t->freepages_delay_total); } void task_context_switch_counts(struct taskstats *t) -- cgit v1.2.3 From 327dafb1c61c9da7b95ac6cc7634a2340cc9509c Mon Sep 17 00:00:00 2001 From: Arthur Jones Date: Fri, 25 Jul 2008 01:49:10 -0700 Subject: edac: core fix redundant sysfs controls to parameters /sys/devices/system/edac/mc has a few files which are duplicated in /sys/module/edac_core/parameters. Now that all the functionality is duplicated between these two locations, we remove the former kobject attributes and update the documentation. Signed-off-by: Arthur Jones Signed-off-by: Doug Thompson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/edac.txt | 151 +++++++++++++++++++++---------------------- drivers/edac/edac_mc_sysfs.c | 117 +-------------------------------- 2 files changed, 73 insertions(+), 195 deletions(-) (limited to 'Documentation') diff --git a/Documentation/edac.txt b/Documentation/edac.txt index a5c36842ecef..ced527388001 100644 --- a/Documentation/edac.txt +++ b/Documentation/edac.txt @@ -222,74 +222,9 @@ both csrow2 and csrow3 are populated, this indicates a dual ranked set of DIMMs for channels 0 and 1. -Within each of the 'mc','mcX' and 'csrowX' directories are several +Within each of the 'mcX' and 'csrowX' directories are several EDAC control and attribute files. - -============================================================================ -DIRECTORY 'mc' - -In directory 'mc' are EDAC system overall control and attribute files: - - -Panic on UE control file: - - 'edac_mc_panic_on_ue' - - An uncorrectable error will cause a machine panic. This is usually - desirable. It is a bad idea to continue when an uncorrectable error - occurs - it is indeterminate what was uncorrected and the operating - system context might be so mangled that continuing will lead to further - corruption. If the kernel has MCE configured, then EDAC will never - notice the UE. - - LOAD TIME: module/kernel parameter: panic_on_ue=[0|1] - - RUN TIME: echo "1" >/sys/devices/system/edac/mc/edac_mc_panic_on_ue - - -Log UE control file: - - 'edac_mc_log_ue' - - Generate kernel messages describing uncorrectable errors. These errors - are reported through the system message log system. UE statistics - will be accumulated even when UE logging is disabled. - - LOAD TIME: module/kernel parameter: log_ue=[0|1] - - RUN TIME: echo "1" >/sys/devices/system/edac/mc/edac_mc_log_ue - - -Log CE control file: - - 'edac_mc_log_ce' - - Generate kernel messages describing correctable errors. These - errors are reported through the system message log system. - CE statistics will be accumulated even when CE logging is disabled. - - LOAD TIME: module/kernel parameter: log_ce=[0|1] - - RUN TIME: echo "1" >/sys/devices/system/edac/mc/edac_mc_log_ce - - -Polling period control file: - - 'edac_mc_poll_msec' - - The time period, in milliseconds, for polling for error information. - Too small a value wastes resources. Too large a value might delay - necessary handling of errors and might loose valuable information for - locating the error. 1000 milliseconds (once each second) is the current - default. Systems which require all the bandwidth they can get, may - increase this. - - LOAD TIME: module/kernel parameter: poll_msec=[0|1] - - RUN TIME: echo "1000" >/sys/devices/system/edac/mc/edac_mc_poll_msec - - ============================================================================ 'mcX' DIRECTORIES @@ -537,7 +472,6 @@ Channel 1 DIMM Label control file: motherboard specific and determination of this information must occur in userland at this time. - ============================================================================ SYSTEM LOGGING @@ -570,7 +504,6 @@ error type, a notice of "no info" and then an optional, driver-specific error message. - ============================================================================ PCI Bus Parity Detection @@ -604,6 +537,74 @@ Enable/Disable PCI Parity checking control file: echo "0" >/sys/devices/system/edac/pci/check_pci_parity +Parity Count: + + 'pci_parity_count' + + This attribute file will display the number of parity errors that + have been detected. + + +============================================================================ +MODULE PARAMETERS + +Panic on UE control file: + + 'edac_mc_panic_on_ue' + + An uncorrectable error will cause a machine panic. This is usually + desirable. It is a bad idea to continue when an uncorrectable error + occurs - it is indeterminate what was uncorrected and the operating + system context might be so mangled that continuing will lead to further + corruption. If the kernel has MCE configured, then EDAC will never + notice the UE. + + LOAD TIME: module/kernel parameter: edac_mc_panic_on_ue=[0|1] + + RUN TIME: echo "1" > /sys/module/edac_core/parameters/edac_mc_panic_on_ue + + +Log UE control file: + + 'edac_mc_log_ue' + + Generate kernel messages describing uncorrectable errors. These errors + are reported through the system message log system. UE statistics + will be accumulated even when UE logging is disabled. + + LOAD TIME: module/kernel parameter: edac_mc_log_ue=[0|1] + + RUN TIME: echo "1" > /sys/module/edac_core/parameters/edac_mc_log_ue + + +Log CE control file: + + 'edac_mc_log_ce' + + Generate kernel messages describing correctable errors. These + errors are reported through the system message log system. + CE statistics will be accumulated even when CE logging is disabled. + + LOAD TIME: module/kernel parameter: edac_mc_log_ce=[0|1] + + RUN TIME: echo "1" > /sys/module/edac_core/parameters/edac_mc_log_ce + + +Polling period control file: + + 'edac_mc_poll_msec' + + The time period, in milliseconds, for polling for error information. + Too small a value wastes resources. Too large a value might delay + necessary handling of errors and might loose valuable information for + locating the error. 1000 milliseconds (once each second) is the current + default. Systems which require all the bandwidth they can get, may + increase this. + + LOAD TIME: module/kernel parameter: edac_mc_poll_msec=[0|1] + + RUN TIME: echo "1000" > /sys/module/edac_core/parameters/edac_mc_poll_msec + Panic on PCI PARITY Error: @@ -614,21 +615,13 @@ Panic on PCI PARITY Error: error has been detected. - module/kernel parameter: panic_on_pci_parity=[0|1] + module/kernel parameter: edac_panic_on_pci_pe=[0|1] Enable: - echo "1" >/sys/devices/system/edac/pci/panic_on_pci_parity + echo "1" > /sys/module/edac_core/parameters/edac_panic_on_pci_pe Disable: - echo "0" >/sys/devices/system/edac/pci/panic_on_pci_parity - - -Parity Count: - - 'pci_parity_count' - - This attribute file will display the number of parity errors that - have been detected. + echo "0" > /sys/module/edac_core/parameters/edac_panic_on_pci_pe diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index 7bb9c1532b90..cbe1a17e42f7 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -123,16 +123,6 @@ static const char *edac_caps[] = { -/* - * /sys/devices/system/edac/mc; - * data structures and methods - */ -static ssize_t memctrl_int_show(void *ptr, char *buffer) -{ - int *value = (int *)ptr; - return sprintf(buffer, "%u\n", *value); -} - static ssize_t memctrl_int_store(void *ptr, const char *buffer, size_t count) { int *value = (int *)ptr; @@ -143,23 +133,6 @@ static ssize_t memctrl_int_store(void *ptr, const char *buffer, size_t count) return count; } -/* - * mc poll_msec time value - */ -static ssize_t poll_msec_int_store(void *ptr, const char *buffer, size_t count) -{ - int *value = (int *)ptr; - - if (isdigit(*buffer)) { - *value = simple_strtoul(buffer, NULL, 0); - - /* notify edac_mc engine to reset the poll period */ - edac_mc_reset_delay_period(*value); - } - - return count; -} - /* EDAC sysfs CSROW data structures and methods */ @@ -669,98 +642,10 @@ static struct kobj_type ktype_mci = { .default_attrs = (struct attribute **)mci_attr, }; -/* show/store, tables, etc for the MC kset */ - - -struct memctrl_dev_attribute { - struct attribute attr; - void *value; - ssize_t(*show) (void *, char *); - ssize_t(*store) (void *, const char *, size_t); -}; - -/* Set of show/store abstract level functions for memory control object */ -static ssize_t memctrl_dev_show(struct kobject *kobj, - struct attribute *attr, char *buffer) -{ - struct memctrl_dev_attribute *memctrl_dev; - memctrl_dev = (struct memctrl_dev_attribute *)attr; - - if (memctrl_dev->show) - return memctrl_dev->show(memctrl_dev->value, buffer); - - return -EIO; -} - -static ssize_t memctrl_dev_store(struct kobject *kobj, struct attribute *attr, - const char *buffer, size_t count) -{ - struct memctrl_dev_attribute *memctrl_dev; - memctrl_dev = (struct memctrl_dev_attribute *)attr; - - if (memctrl_dev->store) - return memctrl_dev->store(memctrl_dev->value, buffer, count); - - return -EIO; -} - -static struct sysfs_ops memctrlfs_ops = { - .show = memctrl_dev_show, - .store = memctrl_dev_store -}; - -#define MEMCTRL_ATTR(_name, _mode, _show, _store) \ -static struct memctrl_dev_attribute attr_##_name = { \ - .attr = {.name = __stringify(_name), .mode = _mode }, \ - .value = &_name, \ - .show = _show, \ - .store = _store, \ -}; - -#define MEMCTRL_STRING_ATTR(_name, _data, _mode, _show, _store) \ -static struct memctrl_dev_attribute attr_##_name = { \ - .attr = {.name = __stringify(_name), .mode = _mode }, \ - .value = _data, \ - .show = _show, \ - .store = _store, \ -}; - -/* csrow control files */ -MEMCTRL_ATTR(edac_mc_panic_on_ue, - S_IRUGO | S_IWUSR, memctrl_int_show, memctrl_int_store); - -MEMCTRL_ATTR(edac_mc_log_ue, - S_IRUGO | S_IWUSR, memctrl_int_show, memctrl_int_store); - -MEMCTRL_ATTR(edac_mc_log_ce, - S_IRUGO | S_IWUSR, memctrl_int_show, memctrl_int_store); - -MEMCTRL_ATTR(edac_mc_poll_msec, - S_IRUGO | S_IWUSR, memctrl_int_show, poll_msec_int_store); - -/* Base Attributes of the memory ECC object */ -static struct memctrl_dev_attribute *memctrl_attr[] = { - &attr_edac_mc_panic_on_ue, - &attr_edac_mc_log_ue, - &attr_edac_mc_log_ce, - &attr_edac_mc_poll_msec, - NULL, -}; - - -/* the ktype for the mc_kset internal kobj */ -static struct kobj_type ktype_mc_set_attribs = { - .sysfs_ops = &memctrlfs_ops, - .default_attrs = (struct attribute **)memctrl_attr, -}; - /* EDAC memory controller sysfs kset: * /sys/devices/system/edac/mc */ -static struct kset mc_kset = { - .kobj = {.ktype = &ktype_mc_set_attribs }, -}; - +static struct kset mc_kset; /* * edac_mc_register_sysfs_main_kobj -- cgit v1.2.3 From 8d8bb39b9eba32dd70e87fd5ad5c5dd4ba118e06 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Fri, 25 Jul 2008 19:44:49 -0700 Subject: dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori Cc: Muli Ben-Yehuda Cc: Andi Kleen Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Avi Kivity Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/DMA-API.txt | 4 +- arch/arm/common/dmabounce.c | 2 +- arch/ia64/hp/common/hwsw_iommu.c | 5 +- arch/ia64/hp/common/sba_iommu.c | 2 +- arch/ia64/sn/pci/pci_dma.c | 2 +- arch/mips/mm/dma-default.c | 2 +- arch/powerpc/platforms/cell/celleb_scc_pciex.c | 2 +- arch/powerpc/platforms/cell/spider-pci.c | 2 +- arch/powerpc/platforms/iseries/mf.c | 2 +- arch/x86/kernel/pci-calgary_64.c | 2 +- arch/x86/kernel/pci-dma.c | 27 ++++--- arch/x86/kernel/pci-gart_64.c | 3 +- arch/x86/kernel/pci-nommu.c | 14 +--- arch/x86/kernel/pci-swiotlb_64.c | 2 +- drivers/firewire/fw-iso.c | 2 +- drivers/firewire/fw-ohci.c | 2 +- drivers/firewire/fw-sbp2.c | 8 +-- drivers/infiniband/hw/ipath/ipath_sdma.c | 2 +- drivers/infiniband/hw/ipath/ipath_user_sdma.c | 6 +- drivers/infiniband/hw/mthca/mthca_eq.c | 2 +- drivers/media/dvb/pluto2/pluto2.c | 2 +- drivers/mmc/host/sdhci.c | 4 +- drivers/net/arm/ep93xx_eth.c | 4 +- drivers/net/bnx2x_main.c | 4 +- drivers/net/cxgb3/sge.c | 2 +- drivers/net/e100.c | 2 +- drivers/net/e1000e/ethtool.c | 4 +- drivers/net/e1000e/netdev.c | 11 +-- drivers/net/ibmveth.c | 38 +++++----- drivers/net/iseries_veth.c | 4 +- drivers/net/mlx4/eq.c | 2 +- drivers/net/pasemi_mac.c | 6 +- drivers/net/qla3xxx.c | 12 ++-- drivers/net/s2io.c | 48 +++++++------ drivers/net/sfc/rx.c | 4 +- drivers/net/sfc/tx.c | 7 +- drivers/net/spider_net.c | 4 +- drivers/net/tc35815.c | 4 +- drivers/net/wireless/ath5k/base.c | 4 +- drivers/scsi/ibmvscsi/ibmvfc.c | 4 +- drivers/scsi/ibmvscsi/ibmvscsi.c | 4 +- drivers/scsi/ibmvscsi/ibmvstgt.c | 2 +- drivers/scsi/ibmvscsi/rpa_vscsi.c | 2 +- drivers/spi/atmel_spi.c | 4 +- drivers/spi/au1550_spi.c | 6 +- drivers/spi/omap2_mcspi.c | 4 +- drivers/spi/pxa2xx_spi.c | 4 +- drivers/spi/spi_imx.c | 6 +- include/asm-alpha/dma-mapping.h | 6 +- include/asm-alpha/pci.h | 2 +- include/asm-arm/dma-mapping.h | 2 +- include/asm-avr32/dma-mapping.h | 2 +- include/asm-cris/dma-mapping.h | 2 +- include/asm-frv/dma-mapping.h | 2 +- include/asm-generic/dma-mapping-broken.h | 2 +- include/asm-generic/dma-mapping.h | 4 +- include/asm-generic/pci-dma-compat.h | 4 +- include/asm-ia64/machvec.h | 2 +- include/asm-m68k/dma-mapping.h | 2 +- include/asm-mips/dma-mapping.h | 2 +- include/asm-mn10300/dma-mapping.h | 2 +- include/asm-parisc/dma-mapping.h | 2 +- include/asm-powerpc/dma-mapping.h | 2 +- include/asm-sh/dma-mapping.h | 2 +- include/asm-sparc/dma-mapping_64.h | 2 +- include/asm-sparc/pci_32.h | 3 +- include/asm-sparc/pci_64.h | 5 +- include/asm-x86/device.h | 3 + include/asm-x86/dma-mapping.h | 99 ++++++++++++++++++-------- include/asm-x86/swiotlb.h | 2 +- include/asm-xtensa/dma-mapping.h | 2 +- include/linux/i2o.h | 2 +- include/linux/ssb/ssb.h | 4 +- include/rdma/ib_verbs.h | 2 +- lib/swiotlb.c | 4 +- net/sunrpc/xprtrdma/svc_rdma_sendto.c | 3 +- 76 files changed, 256 insertions(+), 210 deletions(-) (limited to 'Documentation') diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt index 80d150458c80..d8b63d164e41 100644 --- a/Documentation/DMA-API.txt +++ b/Documentation/DMA-API.txt @@ -298,10 +298,10 @@ recommended that you never use these unless you really know what the cache width is. int -dma_mapping_error(dma_addr_t dma_addr) +dma_mapping_error(struct device *dev, dma_addr_t dma_addr) int -pci_dma_mapping_error(dma_addr_t dma_addr) +pci_dma_mapping_error(struct pci_dev *hwdev, dma_addr_t dma_addr) In some circumstances dma_map_single and dma_map_page will fail to create a mapping. A driver can check for these errors by testing the returned diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c index dd2947342604..69130f365904 100644 --- a/arch/arm/common/dmabounce.c +++ b/arch/arm/common/dmabounce.c @@ -280,7 +280,7 @@ unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size, /* * Trying to unmap an invalid mapping */ - if (dma_mapping_error(dma_addr)) { + if (dma_mapping_error(dev, dma_addr)) { dev_err(dev, "Trying to unmap invalid mapping\n"); return; } diff --git a/arch/ia64/hp/common/hwsw_iommu.c b/arch/ia64/hp/common/hwsw_iommu.c index 1c44ec2a1d58..88b6e6f3fd88 100644 --- a/arch/ia64/hp/common/hwsw_iommu.c +++ b/arch/ia64/hp/common/hwsw_iommu.c @@ -186,9 +186,10 @@ hwsw_dma_supported (struct device *dev, u64 mask) } int -hwsw_dma_mapping_error (dma_addr_t dma_addr) +hwsw_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { - return hwiommu_dma_mapping_error (dma_addr) || swiotlb_dma_mapping_error(dma_addr); + return hwiommu_dma_mapping_error(dev, dma_addr) || + swiotlb_dma_mapping_error(dev, dma_addr); } EXPORT_SYMBOL(hwsw_dma_mapping_error); diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index 34421aed1e2a..4956be40d7b5 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -2147,7 +2147,7 @@ sba_dma_supported (struct device *dev, u64 mask) } int -sba_dma_mapping_error (dma_addr_t dma_addr) +sba_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return 0; } diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c index 52175af299a0..53ebb6484495 100644 --- a/arch/ia64/sn/pci/pci_dma.c +++ b/arch/ia64/sn/pci/pci_dma.c @@ -350,7 +350,7 @@ void sn_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, } EXPORT_SYMBOL(sn_dma_sync_sg_for_device); -int sn_dma_mapping_error(dma_addr_t dma_addr) +int sn_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return 0; } diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c index ae39dd88b9aa..891312f8e5a6 100644 --- a/arch/mips/mm/dma-default.c +++ b/arch/mips/mm/dma-default.c @@ -348,7 +348,7 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nele EXPORT_SYMBOL(dma_sync_sg_for_device); -int dma_mapping_error(dma_addr_t dma_addr) +int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return 0; } diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c index 0e04f8fb152a..3e7e0f1568ef 100644 --- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c +++ b/arch/powerpc/platforms/cell/celleb_scc_pciex.c @@ -281,7 +281,7 @@ static int __init scc_pciex_iowa_init(struct iowa_bus *bus, void *data) dummy_page_da = dma_map_single(bus->phb->parent, dummy_page_va, PAGE_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(dummy_page_da)) { + if (dma_mapping_error(bus->phb->parent, dummy_page_da)) { pr_err("PCIEX:Map dummy page failed.\n"); kfree(dummy_page_va); return -1; diff --git a/arch/powerpc/platforms/cell/spider-pci.c b/arch/powerpc/platforms/cell/spider-pci.c index 418b605ac35a..5122ec145271 100644 --- a/arch/powerpc/platforms/cell/spider-pci.c +++ b/arch/powerpc/platforms/cell/spider-pci.c @@ -111,7 +111,7 @@ static int __init spiderpci_pci_setup_chip(struct pci_controller *phb, dummy_page_da = dma_map_single(phb->parent, dummy_page_va, PAGE_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(dummy_page_da)) { + if (dma_mapping_error(phb->parent, dummy_page_da)) { pr_err("SPIDER-IOWA:Map dummy page filed.\n"); kfree(dummy_page_va); return -1; diff --git a/arch/powerpc/platforms/iseries/mf.c b/arch/powerpc/platforms/iseries/mf.c index 1dc7295746da..731d7b157749 100644 --- a/arch/powerpc/platforms/iseries/mf.c +++ b/arch/powerpc/platforms/iseries/mf.c @@ -871,7 +871,7 @@ static int proc_mf_dump_cmdline(char *page, char **start, off_t off, count = 256 - off; dma_addr = iseries_hv_map(page, off + count, DMA_FROM_DEVICE); - if (dma_mapping_error(dma_addr)) + if (dma_mapping_error(NULL, dma_addr)) return -ENOMEM; memset(page, 0, off + count); memset(&vsp_cmd, 0, sizeof(vsp_cmd)); diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 19e7fc7c2c4f..1eb86be93d7a 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -544,7 +544,7 @@ error: return ret; } -static const struct dma_mapping_ops calgary_dma_ops = { +static struct dma_mapping_ops calgary_dma_ops = { .alloc_coherent = calgary_alloc_coherent, .map_single = calgary_map_single, .unmap_single = calgary_unmap_single, diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index cbecb05551bb..37544123896d 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -11,7 +11,7 @@ static int forbid_dac __read_mostly; -const struct dma_mapping_ops *dma_ops; +struct dma_mapping_ops *dma_ops; EXPORT_SYMBOL(dma_ops); static int iommu_sac_force __read_mostly; @@ -312,6 +312,8 @@ static int dma_release_coherent(struct device *dev, int order, void *vaddr) int dma_supported(struct device *dev, u64 mask) { + struct dma_mapping_ops *ops = get_dma_ops(dev); + #ifdef CONFIG_PCI if (mask > 0xffffffff && forbid_dac > 0) { dev_info(dev, "PCI: Disallowing DAC for device\n"); @@ -319,8 +321,8 @@ int dma_supported(struct device *dev, u64 mask) } #endif - if (dma_ops->dma_supported) - return dma_ops->dma_supported(dev, mask); + if (ops->dma_supported) + return ops->dma_supported(dev, mask); /* Copied from i386. Doesn't make much sense, because it will only work for pci_alloc_coherent. @@ -367,6 +369,7 @@ void * dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { + struct dma_mapping_ops *ops = get_dma_ops(dev); void *memory = NULL; struct page *page; unsigned long dma_mask = 0; @@ -435,8 +438,8 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, /* Let low level make its own zone decisions */ gfp &= ~(GFP_DMA32|GFP_DMA); - if (dma_ops->alloc_coherent) - return dma_ops->alloc_coherent(dev, size, + if (ops->alloc_coherent) + return ops->alloc_coherent(dev, size, dma_handle, gfp); return NULL; } @@ -448,14 +451,14 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, } } - if (dma_ops->alloc_coherent) { + if (ops->alloc_coherent) { free_pages((unsigned long)memory, get_order(size)); gfp &= ~(GFP_DMA|GFP_DMA32); - return dma_ops->alloc_coherent(dev, size, dma_handle, gfp); + return ops->alloc_coherent(dev, size, dma_handle, gfp); } - if (dma_ops->map_simple) { - *dma_handle = dma_ops->map_simple(dev, virt_to_phys(memory), + if (ops->map_simple) { + *dma_handle = ops->map_simple(dev, virt_to_phys(memory), size, PCI_DMA_BIDIRECTIONAL); if (*dma_handle != bad_dma_address) @@ -477,12 +480,14 @@ EXPORT_SYMBOL(dma_alloc_coherent); void dma_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t bus) { + struct dma_mapping_ops *ops = get_dma_ops(dev); + int order = get_order(size); WARN_ON(irqs_disabled()); /* for portability */ if (dma_release_coherent(dev, order, vaddr)) return; - if (dma_ops->unmap_single) - dma_ops->unmap_single(dev, bus, size, 0); + if (ops->unmap_single) + ops->unmap_single(dev, bus, size, 0); free_pages((unsigned long)vaddr, order); } EXPORT_SYMBOL(dma_free_coherent); diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index df5f142657d2..744126e64950 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -692,8 +692,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info) extern int agp_amd64_init(void); -static const struct dma_mapping_ops gart_dma_ops = { - .mapping_error = NULL, +static struct dma_mapping_ops gart_dma_ops = { .map_single = gart_map_single, .map_simple = gart_map_simple, .unmap_single = gart_unmap_single, diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index 792b9179eff3..3f91f71cdc3e 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -72,21 +72,9 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, return nents; } -/* Make sure we keep the same behaviour */ -static int nommu_mapping_error(dma_addr_t dma_addr) -{ -#ifdef CONFIG_X86_32 - return 0; -#else - return (dma_addr == bad_dma_address); -#endif -} - - -const struct dma_mapping_ops nommu_dma_ops = { +struct dma_mapping_ops nommu_dma_ops = { .map_single = nommu_map_single, .map_sg = nommu_map_sg, - .mapping_error = nommu_mapping_error, .is_phys = 1, }; diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c index 20df839b9c20..c4ce0332759e 100644 --- a/arch/x86/kernel/pci-swiotlb_64.c +++ b/arch/x86/kernel/pci-swiotlb_64.c @@ -18,7 +18,7 @@ swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size, return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction); } -const struct dma_mapping_ops swiotlb_dma_ops = { +struct dma_mapping_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, .alloc_coherent = swiotlb_alloc_coherent, .free_coherent = swiotlb_free_coherent, diff --git a/drivers/firewire/fw-iso.c b/drivers/firewire/fw-iso.c index bcbe794a3ea5..e14c03dc0065 100644 --- a/drivers/firewire/fw-iso.c +++ b/drivers/firewire/fw-iso.c @@ -50,7 +50,7 @@ fw_iso_buffer_init(struct fw_iso_buffer *buffer, struct fw_card *card, address = dma_map_page(card->device, buffer->pages[i], 0, PAGE_SIZE, direction); - if (dma_mapping_error(address)) { + if (dma_mapping_error(card->device, address)) { __free_page(buffer->pages[i]); goto out_pages; } diff --git a/drivers/firewire/fw-ohci.c b/drivers/firewire/fw-ohci.c index 333b12544dd1..566672e0bcff 100644 --- a/drivers/firewire/fw-ohci.c +++ b/drivers/firewire/fw-ohci.c @@ -953,7 +953,7 @@ at_context_queue_packet(struct context *ctx, struct fw_packet *packet) payload_bus = dma_map_single(ohci->card.device, packet->payload, packet->payload_length, DMA_TO_DEVICE); - if (dma_mapping_error(payload_bus)) { + if (dma_mapping_error(ohci->card.device, payload_bus)) { packet->ack = RCODE_SEND_ERROR; return -1; } diff --git a/drivers/firewire/fw-sbp2.c b/drivers/firewire/fw-sbp2.c index 53fc5a641e6d..aaff50ebba1d 100644 --- a/drivers/firewire/fw-sbp2.c +++ b/drivers/firewire/fw-sbp2.c @@ -543,7 +543,7 @@ sbp2_send_management_orb(struct sbp2_logical_unit *lu, int node_id, orb->response_bus = dma_map_single(device->card->device, &orb->response, sizeof(orb->response), DMA_FROM_DEVICE); - if (dma_mapping_error(orb->response_bus)) + if (dma_mapping_error(device->card->device, orb->response_bus)) goto fail_mapping_response; orb->request.response.high = 0; @@ -577,7 +577,7 @@ sbp2_send_management_orb(struct sbp2_logical_unit *lu, int node_id, orb->base.request_bus = dma_map_single(device->card->device, &orb->request, sizeof(orb->request), DMA_TO_DEVICE); - if (dma_mapping_error(orb->base.request_bus)) + if (dma_mapping_error(device->card->device, orb->base.request_bus)) goto fail_mapping_request; sbp2_send_orb(&orb->base, lu, node_id, generation, @@ -1424,7 +1424,7 @@ sbp2_map_scatterlist(struct sbp2_command_orb *orb, struct fw_device *device, orb->page_table_bus = dma_map_single(device->card->device, orb->page_table, sizeof(orb->page_table), DMA_TO_DEVICE); - if (dma_mapping_error(orb->page_table_bus)) + if (dma_mapping_error(device->card->device, orb->page_table_bus)) goto fail_page_table; /* @@ -1509,7 +1509,7 @@ static int sbp2_scsi_queuecommand(struct scsi_cmnd *cmd, scsi_done_fn_t done) orb->base.request_bus = dma_map_single(device->card->device, &orb->request, sizeof(orb->request), DMA_TO_DEVICE); - if (dma_mapping_error(orb->base.request_bus)) + if (dma_mapping_error(device->card->device, orb->base.request_bus)) goto out; sbp2_send_orb(&orb->base, lu, lu->tgt->node_id, lu->generation, diff --git a/drivers/infiniband/hw/ipath/ipath_sdma.c b/drivers/infiniband/hw/ipath/ipath_sdma.c index eaba03273e4f..284c9bca517e 100644 --- a/drivers/infiniband/hw/ipath/ipath_sdma.c +++ b/drivers/infiniband/hw/ipath/ipath_sdma.c @@ -698,7 +698,7 @@ retry: addr = dma_map_single(&dd->pcidev->dev, tx->txreq.map_addr, tx->map_len, DMA_TO_DEVICE); - if (dma_mapping_error(addr)) { + if (dma_mapping_error(&dd->pcidev->dev, addr)) { ret = -EIO; goto unlock; } diff --git a/drivers/infiniband/hw/ipath/ipath_user_sdma.c b/drivers/infiniband/hw/ipath/ipath_user_sdma.c index 86e016916cd1..82d9a0b5ca2f 100644 --- a/drivers/infiniband/hw/ipath/ipath_user_sdma.c +++ b/drivers/infiniband/hw/ipath/ipath_user_sdma.c @@ -206,7 +206,7 @@ static int ipath_user_sdma_coalesce(const struct ipath_devdata *dd, dma_addr = dma_map_page(&dd->pcidev->dev, page, 0, len, DMA_TO_DEVICE); - if (dma_mapping_error(dma_addr)) { + if (dma_mapping_error(&dd->pcidev->dev, dma_addr)) { ret = -ENOMEM; goto free_unmap; } @@ -301,7 +301,7 @@ static int ipath_user_sdma_pin_pages(const struct ipath_devdata *dd, pages[j], 0, flen, DMA_TO_DEVICE); unsigned long fofs = addr & ~PAGE_MASK; - if (dma_mapping_error(dma_addr)) { + if (dma_mapping_error(&dd->pcidev->dev, dma_addr)) { ret = -ENOMEM; goto done; } @@ -508,7 +508,7 @@ static int ipath_user_sdma_queue_pkts(const struct ipath_devdata *dd, if (page) { dma_addr = dma_map_page(&dd->pcidev->dev, page, 0, len, DMA_TO_DEVICE); - if (dma_mapping_error(dma_addr)) { + if (dma_mapping_error(&dd->pcidev->dev, dma_addr)) { ret = -ENOMEM; goto free_pbc; } diff --git a/drivers/infiniband/hw/mthca/mthca_eq.c b/drivers/infiniband/hw/mthca/mthca_eq.c index 4e36aa7cb3d2..cc6858f0b65b 100644 --- a/drivers/infiniband/hw/mthca/mthca_eq.c +++ b/drivers/infiniband/hw/mthca/mthca_eq.c @@ -780,7 +780,7 @@ int mthca_map_eq_icm(struct mthca_dev *dev, u64 icm_virt) return -ENOMEM; dev->eq_table.icm_dma = pci_map_page(dev->pdev, dev->eq_table.icm_page, 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); - if (pci_dma_mapping_error(dev->eq_table.icm_dma)) { + if (pci_dma_mapping_error(dev->pdev, dev->eq_table.icm_dma)) { __free_page(dev->eq_table.icm_page); return -ENOMEM; } diff --git a/drivers/media/dvb/pluto2/pluto2.c b/drivers/media/dvb/pluto2/pluto2.c index 1360403b88b6..a9653c63f4db 100644 --- a/drivers/media/dvb/pluto2/pluto2.c +++ b/drivers/media/dvb/pluto2/pluto2.c @@ -242,7 +242,7 @@ static int __devinit pluto_dma_map(struct pluto *pluto) pluto->dma_addr = pci_map_single(pluto->pdev, pluto->dma_buf, TS_DMA_BYTES, PCI_DMA_FROMDEVICE); - return pci_dma_mapping_error(pluto->dma_addr); + return pci_dma_mapping_error(pluto->pdev, pluto->dma_addr); } static void pluto_dma_unmap(struct pluto *pluto) diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index c3a5db72ddd7..5f95e10229b5 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -337,7 +337,7 @@ static int sdhci_adma_table_pre(struct sdhci_host *host, host->align_addr = dma_map_single(mmc_dev(host->mmc), host->align_buffer, 128 * 4, direction); - if (dma_mapping_error(host->align_addr)) + if (dma_mapping_error(mmc_dev(host->mmc), host->align_addr)) goto fail; BUG_ON(host->align_addr & 0x3); @@ -439,7 +439,7 @@ static int sdhci_adma_table_pre(struct sdhci_host *host, host->adma_addr = dma_map_single(mmc_dev(host->mmc), host->adma_desc, (128 * 2 + 1) * 4, DMA_TO_DEVICE); - if (dma_mapping_error(host->align_addr)) + if (dma_mapping_error(mmc_dev(host->mmc), host->align_addr)) goto unmap_entries; BUG_ON(host->adma_addr & 0x3); diff --git a/drivers/net/arm/ep93xx_eth.c b/drivers/net/arm/ep93xx_eth.c index 7a14980f3472..18d3eeb7eab2 100644 --- a/drivers/net/arm/ep93xx_eth.c +++ b/drivers/net/arm/ep93xx_eth.c @@ -482,7 +482,7 @@ static int ep93xx_alloc_buffers(struct ep93xx_priv *ep) goto err; d = dma_map_single(NULL, page, PAGE_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(d)) { + if (dma_mapping_error(NULL, d)) { free_page((unsigned long)page); goto err; } @@ -505,7 +505,7 @@ static int ep93xx_alloc_buffers(struct ep93xx_priv *ep) goto err; d = dma_map_single(NULL, page, PAGE_SIZE, DMA_TO_DEVICE); - if (dma_mapping_error(d)) { + if (dma_mapping_error(NULL, d)) { free_page((unsigned long)page); goto err; } diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c index 0263bef9cc6d..c7cc760a1777 100644 --- a/drivers/net/bnx2x_main.c +++ b/drivers/net/bnx2x_main.c @@ -1020,7 +1020,7 @@ static inline int bnx2x_alloc_rx_sge(struct bnx2x *bp, mapping = pci_map_page(bp->pdev, page, 0, BCM_PAGE_SIZE*PAGES_PER_SGE, PCI_DMA_FROMDEVICE); - if (unlikely(dma_mapping_error(mapping))) { + if (unlikely(dma_mapping_error(&bp->pdev->dev, mapping))) { __free_pages(page, PAGES_PER_SGE_SHIFT); return -ENOMEM; } @@ -1048,7 +1048,7 @@ static inline int bnx2x_alloc_rx_skb(struct bnx2x *bp, mapping = pci_map_single(bp->pdev, skb->data, bp->rx_buf_use_size, PCI_DMA_FROMDEVICE); - if (unlikely(dma_mapping_error(mapping))) { + if (unlikely(dma_mapping_error(&bp->pdev->dev, mapping))) { dev_kfree_skb(skb); return -ENOMEM; } diff --git a/drivers/net/cxgb3/sge.c b/drivers/net/cxgb3/sge.c index a96331c875e6..1b0861d73ab7 100644 --- a/drivers/net/cxgb3/sge.c +++ b/drivers/net/cxgb3/sge.c @@ -386,7 +386,7 @@ static inline int add_one_rx_buf(void *va, unsigned int len, dma_addr_t mapping; mapping = pci_map_single(pdev, va, len, PCI_DMA_FROMDEVICE); - if (unlikely(pci_dma_mapping_error(mapping))) + if (unlikely(pci_dma_mapping_error(pdev, mapping))) return -ENOMEM; pci_unmap_addr_set(sd, dma_addr, mapping); diff --git a/drivers/net/e100.c b/drivers/net/e100.c index 1037b1332312..19d32a227be1 100644 --- a/drivers/net/e100.c +++ b/drivers/net/e100.c @@ -1790,7 +1790,7 @@ static int e100_rx_alloc_skb(struct nic *nic, struct rx *rx) rx->dma_addr = pci_map_single(nic->pdev, rx->skb->data, RFD_BUF_LEN, PCI_DMA_BIDIRECTIONAL); - if (pci_dma_mapping_error(rx->dma_addr)) { + if (pci_dma_mapping_error(nic->pdev, rx->dma_addr)) { dev_kfree_skb_any(rx->skb); rx->skb = NULL; rx->dma_addr = 0; diff --git a/drivers/net/e1000e/ethtool.c b/drivers/net/e1000e/ethtool.c index a14561f40db0..9350564065e7 100644 --- a/drivers/net/e1000e/ethtool.c +++ b/drivers/net/e1000e/ethtool.c @@ -1090,7 +1090,7 @@ static int e1000_setup_desc_rings(struct e1000_adapter *adapter) tx_ring->buffer_info[i].dma = pci_map_single(pdev, skb->data, skb->len, PCI_DMA_TODEVICE); - if (pci_dma_mapping_error(tx_ring->buffer_info[i].dma)) { + if (pci_dma_mapping_error(pdev, tx_ring->buffer_info[i].dma)) { ret_val = 4; goto err_nomem; } @@ -1153,7 +1153,7 @@ static int e1000_setup_desc_rings(struct e1000_adapter *adapter) rx_ring->buffer_info[i].dma = pci_map_single(pdev, skb->data, 2048, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(rx_ring->buffer_info[i].dma)) { + if (pci_dma_mapping_error(pdev, rx_ring->buffer_info[i].dma)) { ret_val = 8; goto err_nomem; } diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 9c0f56b3c518..d13677899767 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -195,7 +195,7 @@ map_skb: buffer_info->dma = pci_map_single(pdev, skb->data, adapter->rx_buffer_len, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(buffer_info->dma)) { + if (pci_dma_mapping_error(pdev, buffer_info->dma)) { dev_err(&pdev->dev, "RX DMA map failed\n"); adapter->rx_dma_failed++; break; @@ -265,7 +265,7 @@ static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter, ps_page->page, 0, PAGE_SIZE, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(ps_page->dma)) { + if (pci_dma_mapping_error(pdev, ps_page->dma)) { dev_err(&adapter->pdev->dev, "RX DMA page map failed\n"); adapter->rx_dma_failed++; @@ -300,7 +300,7 @@ static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter, buffer_info->dma = pci_map_single(pdev, skb->data, adapter->rx_ps_bsize0, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(buffer_info->dma)) { + if (pci_dma_mapping_error(pdev, buffer_info->dma)) { dev_err(&pdev->dev, "RX DMA map failed\n"); adapter->rx_dma_failed++; /* cleanup skb */ @@ -3344,7 +3344,7 @@ static int e1000_tx_map(struct e1000_adapter *adapter, skb->data + offset, size, PCI_DMA_TODEVICE); - if (pci_dma_mapping_error(buffer_info->dma)) { + if (pci_dma_mapping_error(adapter->pdev, buffer_info->dma)) { dev_err(&adapter->pdev->dev, "TX DMA map failed\n"); adapter->tx_dma_failed++; return -1; @@ -3382,7 +3382,8 @@ static int e1000_tx_map(struct e1000_adapter *adapter, offset, size, PCI_DMA_TODEVICE); - if (pci_dma_mapping_error(buffer_info->dma)) { + if (pci_dma_mapping_error(adapter->pdev, + buffer_info->dma)) { dev_err(&adapter->pdev->dev, "TX DMA page map failed\n"); adapter->tx_dma_failed++; diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c index e5a6e2e84540..91ec9fdc7184 100644 --- a/drivers/net/ibmveth.c +++ b/drivers/net/ibmveth.c @@ -260,7 +260,7 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, struc dma_addr = dma_map_single(&adapter->vdev->dev, skb->data, pool->buff_size, DMA_FROM_DEVICE); - if (dma_mapping_error(dma_addr)) + if (dma_mapping_error((&adapter->vdev->dev, dma_addr)) goto failure; pool->free_map[free_index] = IBM_VETH_INVALID_MAP; @@ -294,7 +294,7 @@ failure: pool->consumer_index = pool->size - 1; else pool->consumer_index--; - if (!dma_mapping_error(dma_addr)) + if (!dma_mapping_error((&adapter->vdev->dev, dma_addr)) dma_unmap_single(&adapter->vdev->dev, pool->dma_addr[index], pool->buff_size, DMA_FROM_DEVICE); @@ -448,11 +448,11 @@ static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter) static void ibmveth_cleanup(struct ibmveth_adapter *adapter) { int i; + struct device *dev = &adapter->vdev->dev; if(adapter->buffer_list_addr != NULL) { - if(!dma_mapping_error(adapter->buffer_list_dma)) { - dma_unmap_single(&adapter->vdev->dev, - adapter->buffer_list_dma, 4096, + if (!dma_mapping_error(dev, adapter->buffer_list_dma)) { + dma_unmap_single(dev, adapter->buffer_list_dma, 4096, DMA_BIDIRECTIONAL); adapter->buffer_list_dma = DMA_ERROR_CODE; } @@ -461,9 +461,8 @@ static void ibmveth_cleanup(struct ibmveth_adapter *adapter) } if(adapter->filter_list_addr != NULL) { - if(!dma_mapping_error(adapter->filter_list_dma)) { - dma_unmap_single(&adapter->vdev->dev, - adapter->filter_list_dma, 4096, + if (!dma_mapping_error(dev, adapter->filter_list_dma)) { + dma_unmap_single(dev, adapter->filter_list_dma, 4096, DMA_BIDIRECTIONAL); adapter->filter_list_dma = DMA_ERROR_CODE; } @@ -472,8 +471,8 @@ static void ibmveth_cleanup(struct ibmveth_adapter *adapter) } if(adapter->rx_queue.queue_addr != NULL) { - if(!dma_mapping_error(adapter->rx_queue.queue_dma)) { - dma_unmap_single(&adapter->vdev->dev, + if (!dma_mapping_error(dev, adapter->rx_queue.queue_dma)) { + dma_unmap_single(dev, adapter->rx_queue.queue_dma, adapter->rx_queue.queue_len, DMA_BIDIRECTIONAL); @@ -535,6 +534,7 @@ static int ibmveth_open(struct net_device *netdev) int rc; union ibmveth_buf_desc rxq_desc; int i; + struct device *dev; ibmveth_debug_printk("open starting\n"); @@ -563,17 +563,19 @@ static int ibmveth_open(struct net_device *netdev) return -ENOMEM; } - adapter->buffer_list_dma = dma_map_single(&adapter->vdev->dev, + dev = &adapter->vdev->dev; + + adapter->buffer_list_dma = dma_map_single(dev, adapter->buffer_list_addr, 4096, DMA_BIDIRECTIONAL); - adapter->filter_list_dma = dma_map_single(&adapter->vdev->dev, + adapter->filter_list_dma = dma_map_single(dev, adapter->filter_list_addr, 4096, DMA_BIDIRECTIONAL); - adapter->rx_queue.queue_dma = dma_map_single(&adapter->vdev->dev, + adapter->rx_queue.queue_dma = dma_map_single(dev, adapter->rx_queue.queue_addr, adapter->rx_queue.queue_len, DMA_BIDIRECTIONAL); - if((dma_mapping_error(adapter->buffer_list_dma) ) || - (dma_mapping_error(adapter->filter_list_dma)) || - (dma_mapping_error(adapter->rx_queue.queue_dma))) { + if ((dma_mapping_error(dev, adapter->buffer_list_dma)) || + (dma_mapping_error(dev, adapter->filter_list_dma)) || + (dma_mapping_error(dev, adapter->rx_queue.queue_dma))) { ibmveth_error_printk("unable to map filter or buffer list pages\n"); ibmveth_cleanup(adapter); napi_disable(&adapter->napi); @@ -645,7 +647,7 @@ static int ibmveth_open(struct net_device *netdev) adapter->bounce_buffer_dma = dma_map_single(&adapter->vdev->dev, adapter->bounce_buffer, netdev->mtu + IBMVETH_BUFF_OH, DMA_BIDIRECTIONAL); - if (dma_mapping_error(adapter->bounce_buffer_dma)) { + if (dma_mapping_error(dev, adapter->bounce_buffer_dma)) { ibmveth_error_printk("unable to map bounce buffer\n"); ibmveth_cleanup(adapter); napi_disable(&adapter->napi); @@ -922,7 +924,7 @@ static int ibmveth_start_xmit(struct sk_buff *skb, struct net_device *netdev) buf[1] = 0; } - if (dma_mapping_error(data_dma_addr)) { + if (dma_mapping_error((&adapter->vdev->dev, data_dma_addr)) { if (!firmware_has_feature(FW_FEATURE_CMO)) ibmveth_error_printk("tx: unable to map xmit buffer\n"); skb_copy_from_linear_data(skb, adapter->bounce_buffer, diff --git a/drivers/net/iseries_veth.c b/drivers/net/iseries_veth.c index b8d0639c1cdf..c46864d626b2 100644 --- a/drivers/net/iseries_veth.c +++ b/drivers/net/iseries_veth.c @@ -1128,7 +1128,7 @@ static int veth_transmit_to_one(struct sk_buff *skb, HvLpIndex rlp, msg->data.addr[0] = dma_map_single(port->dev, skb->data, skb->len, DMA_TO_DEVICE); - if (dma_mapping_error(msg->data.addr[0])) + if (dma_mapping_error(port->dev, msg->data.addr[0])) goto recycle_and_drop; msg->dev = port->dev; @@ -1226,7 +1226,7 @@ static void veth_recycle_msg(struct veth_lpar_connection *cnx, dma_address = msg->data.addr[0]; dma_length = msg->data.len[0]; - if (!dma_mapping_error(dma_address)) + if (!dma_mapping_error(msg->dev, dma_address)) dma_unmap_single(msg->dev, dma_address, dma_length, DMA_TO_DEVICE); diff --git a/drivers/net/mlx4/eq.c b/drivers/net/mlx4/eq.c index ea3a09aaa844..7df928d3a3d8 100644 --- a/drivers/net/mlx4/eq.c +++ b/drivers/net/mlx4/eq.c @@ -526,7 +526,7 @@ int mlx4_map_eq_icm(struct mlx4_dev *dev, u64 icm_virt) return -ENOMEM; priv->eq_table.icm_dma = pci_map_page(dev->pdev, priv->eq_table.icm_page, 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); - if (pci_dma_mapping_error(priv->eq_table.icm_dma)) { + if (pci_dma_mapping_error(dev->pdev, priv->eq_table.icm_dma)) { __free_page(priv->eq_table.icm_page); return -ENOMEM; } diff --git a/drivers/net/pasemi_mac.c b/drivers/net/pasemi_mac.c index 993d87c9296f..edc0fd588985 100644 --- a/drivers/net/pasemi_mac.c +++ b/drivers/net/pasemi_mac.c @@ -650,7 +650,7 @@ static void pasemi_mac_replenish_rx_ring(const struct net_device *dev, mac->bufsz - LOCAL_SKB_ALIGN, PCI_DMA_FROMDEVICE); - if (unlikely(dma_mapping_error(dma))) { + if (unlikely(pci_dma_mapping_error(mac->dma_pdev, dma))) { dev_kfree_skb_irq(info->skb); break; } @@ -1519,7 +1519,7 @@ static int pasemi_mac_start_tx(struct sk_buff *skb, struct net_device *dev) map[0] = pci_map_single(mac->dma_pdev, skb->data, skb_headlen(skb), PCI_DMA_TODEVICE); map_size[0] = skb_headlen(skb); - if (dma_mapping_error(map[0])) + if (pci_dma_mapping_error(mac->dma_pdev, map[0])) goto out_err_nolock; for (i = 0; i < nfrags; i++) { @@ -1529,7 +1529,7 @@ static int pasemi_mac_start_tx(struct sk_buff *skb, struct net_device *dev) frag->page_offset, frag->size, PCI_DMA_TODEVICE); map_size[i+1] = frag->size; - if (dma_mapping_error(map[i+1])) { + if (pci_dma_mapping_error(mac->dma_pdev, map[i+1])) { nfrags = i; goto out_err_nolock; } diff --git a/drivers/net/qla3xxx.c b/drivers/net/qla3xxx.c index e7d48a352beb..e82b37bbd6c3 100644 --- a/drivers/net/qla3xxx.c +++ b/drivers/net/qla3xxx.c @@ -328,7 +328,7 @@ static void ql_release_to_lrg_buf_free_list(struct ql3_adapter *qdev, qdev->lrg_buffer_len - QL_HEADER_SPACE, PCI_DMA_FROMDEVICE); - err = pci_dma_mapping_error(map); + err = pci_dma_mapping_error(qdev->pdev, map); if(err) { printk(KERN_ERR "%s: PCI mapping failed with error: %d\n", qdev->ndev->name, err); @@ -1919,7 +1919,7 @@ static int ql_populate_free_queue(struct ql3_adapter *qdev) QL_HEADER_SPACE, PCI_DMA_FROMDEVICE); - err = pci_dma_mapping_error(map); + err = pci_dma_mapping_error(qdev->pdev, map); if(err) { printk(KERN_ERR "%s: PCI mapping failed with error: %d\n", qdev->ndev->name, err); @@ -2454,7 +2454,7 @@ static int ql_send_map(struct ql3_adapter *qdev, */ map = pci_map_single(qdev->pdev, skb->data, len, PCI_DMA_TODEVICE); - err = pci_dma_mapping_error(map); + err = pci_dma_mapping_error(qdev->pdev, map); if(err) { printk(KERN_ERR "%s: PCI mapping failed with error: %d\n", qdev->ndev->name, err); @@ -2487,7 +2487,7 @@ static int ql_send_map(struct ql3_adapter *qdev, sizeof(struct oal), PCI_DMA_TODEVICE); - err = pci_dma_mapping_error(map); + err = pci_dma_mapping_error(qdev->pdev, map); if(err) { printk(KERN_ERR "%s: PCI mapping outbound address list with error: %d\n", @@ -2514,7 +2514,7 @@ static int ql_send_map(struct ql3_adapter *qdev, frag->page_offset, frag->size, PCI_DMA_TODEVICE); - err = pci_dma_mapping_error(map); + err = pci_dma_mapping_error(qdev->pdev, map); if(err) { printk(KERN_ERR "%s: PCI mapping frags failed with error: %d\n", qdev->ndev->name, err); @@ -2916,7 +2916,7 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev) QL_HEADER_SPACE, PCI_DMA_FROMDEVICE); - err = pci_dma_mapping_error(map); + err = pci_dma_mapping_error(qdev->pdev, map); if(err) { printk(KERN_ERR "%s: PCI mapping failed with error: %d\n", qdev->ndev->name, err); diff --git a/drivers/net/s2io.c b/drivers/net/s2io.c index 9dae40ccf048..86d77d05190a 100644 --- a/drivers/net/s2io.c +++ b/drivers/net/s2io.c @@ -2512,8 +2512,8 @@ static void stop_nic(struct s2io_nic *nic) * Return Value: * SUCCESS on success or an appropriate -ve value on failure. */ - -static int fill_rx_buffers(struct ring_info *ring, int from_card_up) +static int fill_rx_buffers(struct s2io_nic *nic, struct ring_info *ring, + int from_card_up) { struct sk_buff *skb; struct RxD_t *rxdp; @@ -2602,7 +2602,8 @@ static int fill_rx_buffers(struct ring_info *ring, int from_card_up) rxdp1->Buffer0_ptr = pci_map_single (ring->pdev, skb->data, size - NET_IP_ALIGN, PCI_DMA_FROMDEVICE); - if(pci_dma_mapping_error(rxdp1->Buffer0_ptr)) + if (pci_dma_mapping_error(nic->pdev, + rxdp1->Buffer0_ptr)) goto pci_map_failed; rxdp->Control_2 = @@ -2636,7 +2637,8 @@ static int fill_rx_buffers(struct ring_info *ring, int from_card_up) rxdp3->Buffer0_ptr = pci_map_single(ring->pdev, ba->ba_0, BUF0_LEN, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(rxdp3->Buffer0_ptr)) + if (pci_dma_mapping_error(nic->pdev, + rxdp3->Buffer0_ptr)) goto pci_map_failed; } else pci_dma_sync_single_for_device(ring->pdev, @@ -2655,7 +2657,8 @@ static int fill_rx_buffers(struct ring_info *ring, int from_card_up) (ring->pdev, skb->data, ring->mtu + 4, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(rxdp3->Buffer2_ptr)) + if (pci_dma_mapping_error(nic->pdev, + rxdp3->Buffer2_ptr)) goto pci_map_failed; if (from_card_up) { @@ -2664,8 +2667,8 @@ static int fill_rx_buffers(struct ring_info *ring, int from_card_up) ba->ba_1, BUF1_LEN, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error - (rxdp3->Buffer1_ptr)) { + if (pci_dma_mapping_error(nic->pdev, + rxdp3->Buffer1_ptr)) { pci_unmap_single (ring->pdev, (dma_addr_t)(unsigned long) @@ -2806,9 +2809,9 @@ static void free_rx_buffers(struct s2io_nic *sp) } } -static int s2io_chk_rx_buffers(struct ring_info *ring) +static int s2io_chk_rx_buffers(struct s2io_nic *nic, struct ring_info *ring) { - if (fill_rx_buffers(ring, 0) == -ENOMEM) { + if (fill_rx_buffers(nic, ring, 0) == -ENOMEM) { DBG_PRINT(INFO_DBG, "%s:Out of memory", ring->dev->name); DBG_PRINT(INFO_DBG, " in Rx Intr!!\n"); } @@ -2848,7 +2851,7 @@ static int s2io_poll_msix(struct napi_struct *napi, int budget) return 0; pkts_processed = rx_intr_handler(ring, budget); - s2io_chk_rx_buffers(ring); + s2io_chk_rx_buffers(nic, ring); if (pkts_processed < budget_org) { netif_rx_complete(dev, napi); @@ -2882,7 +2885,7 @@ static int s2io_poll_inta(struct napi_struct *napi, int budget) for (i = 0; i < config->rx_ring_num; i++) { ring = &mac_control->rings[i]; ring_pkts_processed = rx_intr_handler(ring, budget); - s2io_chk_rx_buffers(ring); + s2io_chk_rx_buffers(nic, ring); pkts_processed += ring_pkts_processed; budget -= ring_pkts_processed; if (budget <= 0) @@ -2939,7 +2942,8 @@ static void s2io_netpoll(struct net_device *dev) rx_intr_handler(&mac_control->rings[i], 0); for (i = 0; i < config->rx_ring_num; i++) { - if (fill_rx_buffers(&mac_control->rings[i], 0) == -ENOMEM) { + if (fill_rx_buffers(nic, &mac_control->rings[i], 0) == + -ENOMEM) { DBG_PRINT(INFO_DBG, "%s:Out of memory", dev->name); DBG_PRINT(INFO_DBG, " in Rx Netpoll!!\n"); break; @@ -4235,14 +4239,14 @@ static int s2io_xmit(struct sk_buff *skb, struct net_device *dev) txdp->Buffer_Pointer = pci_map_single(sp->pdev, fifo->ufo_in_band_v, sizeof(u64), PCI_DMA_TODEVICE); - if (pci_dma_mapping_error(txdp->Buffer_Pointer)) + if (pci_dma_mapping_error(sp->pdev, txdp->Buffer_Pointer)) goto pci_map_failed; txdp++; } txdp->Buffer_Pointer = pci_map_single (sp->pdev, skb->data, frg_len, PCI_DMA_TODEVICE); - if (pci_dma_mapping_error(txdp->Buffer_Pointer)) + if (pci_dma_mapping_error(sp->pdev, txdp->Buffer_Pointer)) goto pci_map_failed; txdp->Host_Control = (unsigned long) skb; @@ -4345,7 +4349,7 @@ static irqreturn_t s2io_msix_ring_handle(int irq, void *dev_id) netif_rx_schedule(dev, &ring->napi); } else { rx_intr_handler(ring, 0); - s2io_chk_rx_buffers(ring); + s2io_chk_rx_buffers(sp, ring); } return IRQ_HANDLED; @@ -4826,7 +4830,7 @@ static irqreturn_t s2io_isr(int irq, void *dev_id) */ if (!config->napi) { for (i = 0; i < config->rx_ring_num; i++) - s2io_chk_rx_buffers(&mac_control->rings[i]); + s2io_chk_rx_buffers(sp, &mac_control->rings[i]); } writeq(sp->general_int_mask, &bar0->general_int_mask); readl(&bar0->general_int_status); @@ -6859,7 +6863,7 @@ static int set_rxd_buffer_pointer(struct s2io_nic *sp, struct RxD_t *rxdp, pci_map_single( sp->pdev, (*skb)->data, size - NET_IP_ALIGN, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(rxdp1->Buffer0_ptr)) + if (pci_dma_mapping_error(sp->pdev, rxdp1->Buffer0_ptr)) goto memalloc_failed; rxdp->Host_Control = (unsigned long) (*skb); } @@ -6886,12 +6890,13 @@ static int set_rxd_buffer_pointer(struct s2io_nic *sp, struct RxD_t *rxdp, pci_map_single(sp->pdev, (*skb)->data, dev->mtu + 4, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(rxdp3->Buffer2_ptr)) + if (pci_dma_mapping_error(sp->pdev, rxdp3->Buffer2_ptr)) goto memalloc_failed; rxdp3->Buffer0_ptr = *temp0 = pci_map_single( sp->pdev, ba->ba_0, BUF0_LEN, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(rxdp3->Buffer0_ptr)) { + if (pci_dma_mapping_error(sp->pdev, + rxdp3->Buffer0_ptr)) { pci_unmap_single (sp->pdev, (dma_addr_t)rxdp3->Buffer2_ptr, dev->mtu + 4, PCI_DMA_FROMDEVICE); @@ -6903,7 +6908,8 @@ static int set_rxd_buffer_pointer(struct s2io_nic *sp, struct RxD_t *rxdp, rxdp3->Buffer1_ptr = *temp1 = pci_map_single(sp->pdev, ba->ba_1, BUF1_LEN, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(rxdp3->Buffer1_ptr)) { + if (pci_dma_mapping_error(sp->pdev, + rxdp3->Buffer1_ptr)) { pci_unmap_single (sp->pdev, (dma_addr_t)rxdp3->Buffer0_ptr, BUF0_LEN, PCI_DMA_FROMDEVICE); @@ -7187,7 +7193,7 @@ static int s2io_card_up(struct s2io_nic * sp) for (i = 0; i < config->rx_ring_num; i++) { mac_control->rings[i].mtu = dev->mtu; - ret = fill_rx_buffers(&mac_control->rings[i], 1); + ret = fill_rx_buffers(sp, &mac_control->rings[i], 1); if (ret) { DBG_PRINT(ERR_DBG, "%s: Out of memory in Open\n", dev->name); diff --git a/drivers/net/sfc/rx.c b/drivers/net/sfc/rx.c index 601b001437c0..0d27dd39bc09 100644 --- a/drivers/net/sfc/rx.c +++ b/drivers/net/sfc/rx.c @@ -233,7 +233,7 @@ static inline int efx_init_rx_buffer_skb(struct efx_rx_queue *rx_queue, rx_buf->data, rx_buf->len, PCI_DMA_FROMDEVICE); - if (unlikely(pci_dma_mapping_error(rx_buf->dma_addr))) { + if (unlikely(pci_dma_mapping_error(efx->pci_dev, rx_buf->dma_addr))) { dev_kfree_skb_any(rx_buf->skb); rx_buf->skb = NULL; return -EIO; @@ -275,7 +275,7 @@ static inline int efx_init_rx_buffer_page(struct efx_rx_queue *rx_queue, 0, efx_rx_buf_size(efx), PCI_DMA_FROMDEVICE); - if (unlikely(pci_dma_mapping_error(dma_addr))) { + if (unlikely(pci_dma_mapping_error(efx->pci_dev, dma_addr))) { __free_pages(rx_buf->page, efx->rx_buffer_order); rx_buf->page = NULL; return -EIO; diff --git a/drivers/net/sfc/tx.c b/drivers/net/sfc/tx.c index 5cdd082ab8f6..5e8374ab28ee 100644 --- a/drivers/net/sfc/tx.c +++ b/drivers/net/sfc/tx.c @@ -172,7 +172,7 @@ static inline int efx_enqueue_skb(struct efx_tx_queue *tx_queue, /* Process all fragments */ while (1) { - if (unlikely(pci_dma_mapping_error(dma_addr))) + if (unlikely(pci_dma_mapping_error(pci_dev, dma_addr))) goto pci_err; /* Store fields for marking in the per-fragment final @@ -661,7 +661,8 @@ efx_tsoh_heap_alloc(struct efx_tx_queue *tx_queue, size_t header_len) tsoh->dma_addr = pci_map_single(tx_queue->efx->pci_dev, TSOH_BUFFER(tsoh), header_len, PCI_DMA_TODEVICE); - if (unlikely(pci_dma_mapping_error(tsoh->dma_addr))) { + if (unlikely(pci_dma_mapping_error(tx_queue->efx->pci_dev, + tsoh->dma_addr))) { kfree(tsoh); return NULL; } @@ -863,7 +864,7 @@ static inline int tso_get_fragment(struct tso_state *st, struct efx_nic *efx, st->ifc.unmap_addr = pci_map_page(efx->pci_dev, page, page_off, len, PCI_DMA_TODEVICE); - if (likely(!pci_dma_mapping_error(st->ifc.unmap_addr))) { + if (likely(!pci_dma_mapping_error(efx->pci_dev, st->ifc.unmap_addr))) { st->ifc.unmap_len = len; st->ifc.len = len; st->ifc.dma_addr = st->ifc.unmap_addr; diff --git a/drivers/net/spider_net.c b/drivers/net/spider_net.c index 00aa0b108cb9..b6435d0d71f9 100644 --- a/drivers/net/spider_net.c +++ b/drivers/net/spider_net.c @@ -452,7 +452,7 @@ spider_net_prepare_rx_descr(struct spider_net_card *card, /* iommu-map the skb */ buf = pci_map_single(card->pdev, descr->skb->data, SPIDER_NET_MAX_FRAME, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(buf)) { + if (pci_dma_mapping_error(card->pdev, buf)) { dev_kfree_skb_any(descr->skb); descr->skb = NULL; if (netif_msg_rx_err(card) && net_ratelimit()) @@ -691,7 +691,7 @@ spider_net_prepare_tx_descr(struct spider_net_card *card, unsigned long flags; buf = pci_map_single(card->pdev, skb->data, skb->len, PCI_DMA_TODEVICE); - if (pci_dma_mapping_error(buf)) { + if (pci_dma_mapping_error(card->pdev, buf)) { if (netif_msg_tx_err(card) && net_ratelimit()) dev_err(&card->netdev->dev, "could not iommu-map packet (%p, %i). " "Dropping packet\n", skb->data, skb->len); diff --git a/drivers/net/tc35815.c b/drivers/net/tc35815.c index a645e5028c14..8487ace9d2e3 100644 --- a/drivers/net/tc35815.c +++ b/drivers/net/tc35815.c @@ -506,7 +506,7 @@ static void *alloc_rxbuf_page(struct pci_dev *hwdev, dma_addr_t *dma_handle) return NULL; *dma_handle = pci_map_single(hwdev, buf, PAGE_SIZE, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(*dma_handle)) { + if (pci_dma_mapping_error(hwdev, *dma_handle)) { free_page((unsigned long)buf); return NULL; } @@ -536,7 +536,7 @@ static struct sk_buff *alloc_rxbuf_skb(struct net_device *dev, return NULL; *dma_handle = pci_map_single(hwdev, skb->data, RX_BUF_SIZE, PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(*dma_handle)) { + if (pci_dma_mapping_error(hwdev, *dma_handle)) { dev_kfree_skb_any(skb); return NULL; } diff --git a/drivers/net/wireless/ath5k/base.c b/drivers/net/wireless/ath5k/base.c index 217d506527a9..d9769c527346 100644 --- a/drivers/net/wireless/ath5k/base.c +++ b/drivers/net/wireless/ath5k/base.c @@ -1166,7 +1166,7 @@ ath5k_rxbuf_setup(struct ath5k_softc *sc, struct ath5k_buf *bf) bf->skb = skb; bf->skbaddr = pci_map_single(sc->pdev, skb->data, sc->rxbufsize, PCI_DMA_FROMDEVICE); - if (unlikely(pci_dma_mapping_error(bf->skbaddr))) { + if (unlikely(pci_dma_mapping_error(sc->pdev, bf->skbaddr))) { ATH5K_ERR(sc, "%s: DMA mapping failed\n", __func__); dev_kfree_skb(skb); bf->skb = NULL; @@ -1918,7 +1918,7 @@ ath5k_beacon_setup(struct ath5k_softc *sc, struct ath5k_buf *bf) ATH5K_DBG(sc, ATH5K_DEBUG_BEACON, "skb %p [data %p len %u] " "skbaddr %llx\n", skb, skb->data, skb->len, (unsigned long long)bf->skbaddr); - if (pci_dma_mapping_error(bf->skbaddr)) { + if (pci_dma_mapping_error(sc->pdev, bf->skbaddr)) { ATH5K_ERR(sc, "beacon DMA mapping failed\n"); return -EIO; } diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index c4a7c06793c5..61f8fdea2d96 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -3525,7 +3525,7 @@ static int ibmvfc_init_crq(struct ibmvfc_host *vhost) crq->msg_token = dma_map_single(dev, crq->msgs, PAGE_SIZE, DMA_BIDIRECTIONAL); - if (dma_mapping_error(crq->msg_token)) + if (dma_mapping_error(dev, crq->msg_token)) goto map_failed; retrc = rc = plpar_hcall_norets(H_REG_CRQ, vdev->unit_address, @@ -3618,7 +3618,7 @@ static int ibmvfc_alloc_mem(struct ibmvfc_host *vhost) async_q->size * sizeof(*async_q->msgs), DMA_BIDIRECTIONAL); - if (dma_mapping_error(async_q->msg_token)) { + if (dma_mapping_error(dev, async_q->msg_token)) { dev_err(dev, "Failed to map async queue\n"); goto free_async_crq; } diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index 20000ec79b04..6b24b9cdb04c 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -859,7 +859,7 @@ static void send_mad_adapter_info(struct ibmvscsi_host_data *hostdata) sizeof(hostdata->madapter_info), DMA_BIDIRECTIONAL); - if (dma_mapping_error(req->buffer)) { + if (dma_mapping_error(hostdata->dev, req->buffer)) { if (!firmware_has_feature(FW_FEATURE_CMO)) dev_err(hostdata->dev, "Unable to map request_buffer for " @@ -1407,7 +1407,7 @@ static int ibmvscsi_do_host_config(struct ibmvscsi_host_data *hostdata, length, DMA_BIDIRECTIONAL); - if (dma_mapping_error(host_config->buffer)) { + if (dma_mapping_error(hostdata->dev, host_config->buffer)) { if (!firmware_has_feature(FW_FEATURE_CMO)) dev_err(hostdata->dev, "dma_mapping error getting host config\n"); diff --git a/drivers/scsi/ibmvscsi/ibmvstgt.c b/drivers/scsi/ibmvscsi/ibmvstgt.c index 3b9514c8f1f1..2e13ec00172a 100644 --- a/drivers/scsi/ibmvscsi/ibmvstgt.c +++ b/drivers/scsi/ibmvscsi/ibmvstgt.c @@ -564,7 +564,7 @@ static int crq_queue_create(struct crq_queue *queue, struct srp_target *target) queue->size * sizeof(*queue->msgs), DMA_BIDIRECTIONAL); - if (dma_mapping_error(queue->msg_token)) + if (dma_mapping_error(target->dev, queue->msg_token)) goto map_failed; err = h_reg_crq(vport->dma_dev->unit_address, queue->msg_token, diff --git a/drivers/scsi/ibmvscsi/rpa_vscsi.c b/drivers/scsi/ibmvscsi/rpa_vscsi.c index 182146100dc1..462a8574dad9 100644 --- a/drivers/scsi/ibmvscsi/rpa_vscsi.c +++ b/drivers/scsi/ibmvscsi/rpa_vscsi.c @@ -253,7 +253,7 @@ static int rpavscsi_init_crq_queue(struct crq_queue *queue, queue->size * sizeof(*queue->msgs), DMA_BIDIRECTIONAL); - if (dma_mapping_error(queue->msg_token)) + if (dma_mapping_error(hostdata->dev, queue->msg_token)) goto map_failed; gather_partition_info(); diff --git a/drivers/spi/atmel_spi.c b/drivers/spi/atmel_spi.c index e81d59d78910..0c7165660853 100644 --- a/drivers/spi/atmel_spi.c +++ b/drivers/spi/atmel_spi.c @@ -313,14 +313,14 @@ atmel_spi_dma_map_xfer(struct atmel_spi *as, struct spi_transfer *xfer) xfer->tx_dma = dma_map_single(dev, (void *) xfer->tx_buf, xfer->len, DMA_TO_DEVICE); - if (dma_mapping_error(xfer->tx_dma)) + if (dma_mapping_error(dev, xfer->tx_dma)) return -ENOMEM; } if (xfer->rx_buf) { xfer->rx_dma = dma_map_single(dev, xfer->rx_buf, xfer->len, DMA_FROM_DEVICE); - if (dma_mapping_error(xfer->rx_dma)) { + if (dma_mapping_error(dev, xfer->rx_dma)) { if (xfer->tx_buf) dma_unmap_single(dev, xfer->tx_dma, xfer->len, diff --git a/drivers/spi/au1550_spi.c b/drivers/spi/au1550_spi.c index 9149689c79d9..87b73e0169c5 100644 --- a/drivers/spi/au1550_spi.c +++ b/drivers/spi/au1550_spi.c @@ -334,7 +334,7 @@ static int au1550_spi_dma_rxtmp_alloc(struct au1550_spi *hw, unsigned size) hw->dma_rx_tmpbuf_size = size; hw->dma_rx_tmpbuf_addr = dma_map_single(hw->dev, hw->dma_rx_tmpbuf, size, DMA_FROM_DEVICE); - if (dma_mapping_error(hw->dma_rx_tmpbuf_addr)) { + if (dma_mapping_error(hw->dev, hw->dma_rx_tmpbuf_addr)) { kfree(hw->dma_rx_tmpbuf); hw->dma_rx_tmpbuf = 0; hw->dma_rx_tmpbuf_size = 0; @@ -378,7 +378,7 @@ static int au1550_spi_dma_txrxb(struct spi_device *spi, struct spi_transfer *t) dma_rx_addr = dma_map_single(hw->dev, (void *)t->rx_buf, t->len, DMA_FROM_DEVICE); - if (dma_mapping_error(dma_rx_addr)) + if (dma_mapping_error(hw->dev, dma_rx_addr)) dev_err(hw->dev, "rx dma map error\n"); } } else { @@ -401,7 +401,7 @@ static int au1550_spi_dma_txrxb(struct spi_device *spi, struct spi_transfer *t) dma_tx_addr = dma_map_single(hw->dev, (void *)t->tx_buf, t->len, DMA_TO_DEVICE); - if (dma_mapping_error(dma_tx_addr)) + if (dma_mapping_error(hw->dev, dma_tx_addr)) dev_err(hw->dev, "tx dma map error\n"); } } else { diff --git a/drivers/spi/omap2_mcspi.c b/drivers/spi/omap2_mcspi.c index b1cc148036c1..f6f987bb71ca 100644 --- a/drivers/spi/omap2_mcspi.c +++ b/drivers/spi/omap2_mcspi.c @@ -836,7 +836,7 @@ static int omap2_mcspi_transfer(struct spi_device *spi, struct spi_message *m) if (tx_buf != NULL) { t->tx_dma = dma_map_single(&spi->dev, (void *) tx_buf, len, DMA_TO_DEVICE); - if (dma_mapping_error(t->tx_dma)) { + if (dma_mapping_error(&spi->dev, t->tx_dma)) { dev_dbg(&spi->dev, "dma %cX %d bytes error\n", 'T', len); return -EINVAL; @@ -845,7 +845,7 @@ static int omap2_mcspi_transfer(struct spi_device *spi, struct spi_message *m) if (rx_buf != NULL) { t->rx_dma = dma_map_single(&spi->dev, rx_buf, t->len, DMA_FROM_DEVICE); - if (dma_mapping_error(t->rx_dma)) { + if (dma_mapping_error(&spi->dev, t->rx_dma)) { dev_dbg(&spi->dev, "dma %cX %d bytes error\n", 'R', len); if (tx_buf != NULL) diff --git a/drivers/spi/pxa2xx_spi.c b/drivers/spi/pxa2xx_spi.c index 0c452c46ab07..067299d6d192 100644 --- a/drivers/spi/pxa2xx_spi.c +++ b/drivers/spi/pxa2xx_spi.c @@ -353,7 +353,7 @@ static int map_dma_buffers(struct driver_data *drv_data) drv_data->rx_dma = dma_map_single(dev, drv_data->rx, drv_data->rx_map_len, DMA_FROM_DEVICE); - if (dma_mapping_error(drv_data->rx_dma)) + if (dma_mapping_error(dev, drv_data->rx_dma)) return 0; /* Stream map the tx buffer */ @@ -361,7 +361,7 @@ static int map_dma_buffers(struct driver_data *drv_data) drv_data->tx_map_len, DMA_TO_DEVICE); - if (dma_mapping_error(drv_data->tx_dma)) { + if (dma_mapping_error(dev, drv_data->tx_dma)) { dma_unmap_single(dev, drv_data->rx_dma, drv_data->rx_map_len, DMA_FROM_DEVICE); return 0; diff --git a/drivers/spi/spi_imx.c b/drivers/spi/spi_imx.c index 54ac7bea5f8c..6fb77fcc4971 100644 --- a/drivers/spi/spi_imx.c +++ b/drivers/spi/spi_imx.c @@ -491,7 +491,7 @@ static int map_dma_buffers(struct driver_data *drv_data) buf, drv_data->tx_map_len, DMA_TO_DEVICE); - if (dma_mapping_error(drv_data->tx_dma)) + if (dma_mapping_error(dev, drv_data->tx_dma)) return -1; drv_data->tx_dma_needs_unmap = 1; @@ -516,7 +516,7 @@ static int map_dma_buffers(struct driver_data *drv_data) buf, drv_data->len, DMA_FROM_DEVICE); - if (dma_mapping_error(drv_data->rx_dma)) + if (dma_mapping_error(dev, drv_data->rx_dma)) return -1; drv_data->rx_dma_needs_unmap = 1; } @@ -534,7 +534,7 @@ static int map_dma_buffers(struct driver_data *drv_data) buf, drv_data->tx_map_len, DMA_TO_DEVICE); - if (dma_mapping_error(drv_data->tx_dma)) { + if (dma_mapping_error(dev, drv_data->tx_dma)) { if (drv_data->rx_dma) { dma_unmap_single(dev, drv_data->rx_dma, diff --git a/include/asm-alpha/dma-mapping.h b/include/asm-alpha/dma-mapping.h index db351d1296f4..a5801ae02e4b 100644 --- a/include/asm-alpha/dma-mapping.h +++ b/include/asm-alpha/dma-mapping.h @@ -24,8 +24,8 @@ pci_unmap_sg(alpha_gendev_to_pci(dev), sg, nents, dir) #define dma_supported(dev, mask) \ pci_dma_supported(alpha_gendev_to_pci(dev), mask) -#define dma_mapping_error(addr) \ - pci_dma_mapping_error(addr) +#define dma_mapping_error(dev, addr) \ + pci_dma_mapping_error(alpha_gendev_to_pci(dev), addr) #else /* no PCI - no IOMMU. */ @@ -45,7 +45,7 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, #define dma_unmap_page(dev, addr, size, dir) ((void)0) #define dma_unmap_sg(dev, sg, nents, dir) ((void)0) -#define dma_mapping_error(addr) (0) +#define dma_mapping_error(dev, addr) (0) #endif /* !CONFIG_PCI */ diff --git a/include/asm-alpha/pci.h b/include/asm-alpha/pci.h index d31fd49ff79a..2a14302c17a3 100644 --- a/include/asm-alpha/pci.h +++ b/include/asm-alpha/pci.h @@ -106,7 +106,7 @@ extern dma_addr_t pci_map_page(struct pci_dev *, struct page *, /* Test for pci_map_single or pci_map_page having generated an error. */ static inline int -pci_dma_mapping_error(dma_addr_t dma_addr) +pci_dma_mapping_error(struct pci_dev *pdev, dma_addr_t dma_addr) { return dma_addr == 0; } diff --git a/include/asm-arm/dma-mapping.h b/include/asm-arm/dma-mapping.h index e99406a7bece..f41335ba6337 100644 --- a/include/asm-arm/dma-mapping.h +++ b/include/asm-arm/dma-mapping.h @@ -56,7 +56,7 @@ static inline int dma_is_consistent(struct device *dev, dma_addr_t handle) /* * DMA errors are defined by all-bits-set in the DMA address. */ -static inline int dma_mapping_error(dma_addr_t dma_addr) +static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return dma_addr == ~0; } diff --git a/include/asm-avr32/dma-mapping.h b/include/asm-avr32/dma-mapping.h index 57dc672bab8e..0399359ab5d8 100644 --- a/include/asm-avr32/dma-mapping.h +++ b/include/asm-avr32/dma-mapping.h @@ -35,7 +35,7 @@ static inline int dma_set_mask(struct device *dev, u64 dma_mask) /* * dma_map_single can't fail as it is implemented now. */ -static inline int dma_mapping_error(dma_addr_t addr) +static inline int dma_mapping_error(struct device *dev, dma_addr_t addr) { return 0; } diff --git a/include/asm-cris/dma-mapping.h b/include/asm-cris/dma-mapping.h index edc8d1bfaae2..cb2fb25ff8d9 100644 --- a/include/asm-cris/dma-mapping.h +++ b/include/asm-cris/dma-mapping.h @@ -120,7 +120,7 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, } static inline int -dma_mapping_error(dma_addr_t dma_addr) +dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return 0; } diff --git a/include/asm-frv/dma-mapping.h b/include/asm-frv/dma-mapping.h index 2e8966ca030d..b2898877c07b 100644 --- a/include/asm-frv/dma-mapping.h +++ b/include/asm-frv/dma-mapping.h @@ -126,7 +126,7 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nele } static inline -int dma_mapping_error(dma_addr_t dma_addr) +int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return 0; } diff --git a/include/asm-generic/dma-mapping-broken.h b/include/asm-generic/dma-mapping-broken.h index e2468f894d2a..82cd0cb1c3fe 100644 --- a/include/asm-generic/dma-mapping-broken.h +++ b/include/asm-generic/dma-mapping-broken.h @@ -61,7 +61,7 @@ dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, #define dma_sync_sg_for_device dma_sync_sg_for_cpu extern int -dma_mapping_error(dma_addr_t dma_addr); +dma_mapping_error(struct device *dev, dma_addr_t dma_addr); extern int dma_supported(struct device *dev, u64 mask); diff --git a/include/asm-generic/dma-mapping.h b/include/asm-generic/dma-mapping.h index 783ab9944d70..189486c3f92e 100644 --- a/include/asm-generic/dma-mapping.h +++ b/include/asm-generic/dma-mapping.h @@ -144,9 +144,9 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, } static inline int -dma_mapping_error(dma_addr_t dma_addr) +dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { - return pci_dma_mapping_error(dma_addr); + return pci_dma_mapping_error(to_pci_dev(dev), dma_addr); } diff --git a/include/asm-generic/pci-dma-compat.h b/include/asm-generic/pci-dma-compat.h index 25c10e96b2b7..37b3706226e7 100644 --- a/include/asm-generic/pci-dma-compat.h +++ b/include/asm-generic/pci-dma-compat.h @@ -99,9 +99,9 @@ pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sg, } static inline int -pci_dma_mapping_error(dma_addr_t dma_addr) +pci_dma_mapping_error(struct pci_dev *pdev, dma_addr_t dma_addr) { - return dma_mapping_error(dma_addr); + return dma_mapping_error(&pdev->dev, dma_addr); } #endif diff --git a/include/asm-ia64/machvec.h b/include/asm-ia64/machvec.h index 0721a5e8271e..a6d50c77b6bf 100644 --- a/include/asm-ia64/machvec.h +++ b/include/asm-ia64/machvec.h @@ -54,7 +54,7 @@ typedef void ia64_mv_dma_sync_single_for_cpu (struct device *, dma_addr_t, size_ typedef void ia64_mv_dma_sync_sg_for_cpu (struct device *, struct scatterlist *, int, int); typedef void ia64_mv_dma_sync_single_for_device (struct device *, dma_addr_t, size_t, int); typedef void ia64_mv_dma_sync_sg_for_device (struct device *, struct scatterlist *, int, int); -typedef int ia64_mv_dma_mapping_error (dma_addr_t dma_addr); +typedef int ia64_mv_dma_mapping_error(struct device *, dma_addr_t dma_addr); typedef int ia64_mv_dma_supported (struct device *, u64); typedef dma_addr_t ia64_mv_dma_map_single_attrs (struct device *, void *, size_t, int, struct dma_attrs *); diff --git a/include/asm-m68k/dma-mapping.h b/include/asm-m68k/dma-mapping.h index a26cdeb46a57..91f7944333d4 100644 --- a/include/asm-m68k/dma-mapping.h +++ b/include/asm-m68k/dma-mapping.h @@ -84,7 +84,7 @@ static inline void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *s { } -static inline int dma_mapping_error(dma_addr_t handle) +static inline int dma_mapping_error(struct device *dev, dma_addr_t handle) { return 0; } diff --git a/include/asm-mips/dma-mapping.h b/include/asm-mips/dma-mapping.h index 230b3f1b69b1..c64afb40cd06 100644 --- a/include/asm-mips/dma-mapping.h +++ b/include/asm-mips/dma-mapping.h @@ -42,7 +42,7 @@ extern void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction direction); extern void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction direction); -extern int dma_mapping_error(dma_addr_t dma_addr); +extern int dma_mapping_error(struct device *dev, dma_addr_t dma_addr); extern int dma_supported(struct device *dev, u64 mask); static inline int diff --git a/include/asm-mn10300/dma-mapping.h b/include/asm-mn10300/dma-mapping.h index 7c882fca9ec8..ccae8f6c6326 100644 --- a/include/asm-mn10300/dma-mapping.h +++ b/include/asm-mn10300/dma-mapping.h @@ -182,7 +182,7 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, } static inline -int dma_mapping_error(dma_addr_t dma_addr) +int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return 0; } diff --git a/include/asm-parisc/dma-mapping.h b/include/asm-parisc/dma-mapping.h index c6c0e9ff6bde..53af696f23d2 100644 --- a/include/asm-parisc/dma-mapping.h +++ b/include/asm-parisc/dma-mapping.h @@ -248,6 +248,6 @@ void * sba_get_iommu(struct parisc_device *dev); #endif /* At the moment, we panic on error for IOMMU resource exaustion */ -#define dma_mapping_error(x) 0 +#define dma_mapping_error(dev, x) 0 #endif diff --git a/include/asm-powerpc/dma-mapping.h b/include/asm-powerpc/dma-mapping.h index 74c549780987..c7ca45f97dd2 100644 --- a/include/asm-powerpc/dma-mapping.h +++ b/include/asm-powerpc/dma-mapping.h @@ -415,7 +415,7 @@ static inline void dma_sync_sg_for_device(struct device *dev, __dma_sync_page(sg_page(sg), sg->offset, sg->length, direction); } -static inline int dma_mapping_error(dma_addr_t dma_addr) +static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { #ifdef CONFIG_PPC64 return (dma_addr == DMA_ERROR_CODE); diff --git a/include/asm-sh/dma-mapping.h b/include/asm-sh/dma-mapping.h index 22cc419389fe..6c0b8a2de143 100644 --- a/include/asm-sh/dma-mapping.h +++ b/include/asm-sh/dma-mapping.h @@ -171,7 +171,7 @@ static inline int dma_get_cache_alignment(void) return L1_CACHE_BYTES; } -static inline int dma_mapping_error(dma_addr_t dma_addr) +static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return dma_addr == 0; } diff --git a/include/asm-sparc/dma-mapping_64.h b/include/asm-sparc/dma-mapping_64.h index 38cbec76a33f..bfa64f9702d5 100644 --- a/include/asm-sparc/dma-mapping_64.h +++ b/include/asm-sparc/dma-mapping_64.h @@ -135,7 +135,7 @@ static inline void dma_sync_sg_for_device(struct device *dev, /* No flushing needed to sync cpu writes to the device. */ } -static inline int dma_mapping_error(dma_addr_t dma_addr) +static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return (dma_addr == DMA_ERROR_CODE); } diff --git a/include/asm-sparc/pci_32.h b/include/asm-sparc/pci_32.h index b93b6c79e08f..0ee949d220c0 100644 --- a/include/asm-sparc/pci_32.h +++ b/include/asm-sparc/pci_32.h @@ -154,7 +154,8 @@ static inline void pci_dma_burst_advice(struct pci_dev *pdev, #define PCI_DMA_ERROR_CODE (~(dma_addr_t)0x0) -static inline int pci_dma_mapping_error(dma_addr_t dma_addr) +static inline int pci_dma_mapping_error(struct pci_dev *pdev, + dma_addr_t dma_addr) { return (dma_addr == PCI_DMA_ERROR_CODE); } diff --git a/include/asm-sparc/pci_64.h b/include/asm-sparc/pci_64.h index f59f2571295b..4f79a54948f6 100644 --- a/include/asm-sparc/pci_64.h +++ b/include/asm-sparc/pci_64.h @@ -140,9 +140,10 @@ extern int pci_dma_supported(struct pci_dev *hwdev, u64 mask); #define PCI64_REQUIRED_MASK (~(dma64_addr_t)0) #define PCI64_ADDR_BASE 0xfffc000000000000UL -static inline int pci_dma_mapping_error(dma_addr_t dma_addr) +static inline int pci_dma_mapping_error(struct pci_dev *pdev, + dma_addr_t dma_addr) { - return dma_mapping_error(dma_addr); + return dma_mapping_error(&pdev->dev, dma_addr); } #ifdef CONFIG_PCI diff --git a/include/asm-x86/device.h b/include/asm-x86/device.h index 87a715367a1b..3c034f48fdb0 100644 --- a/include/asm-x86/device.h +++ b/include/asm-x86/device.h @@ -5,6 +5,9 @@ struct dev_archdata { #ifdef CONFIG_ACPI void *acpi_handle; #endif +#ifdef CONFIG_X86_64 +struct dma_mapping_ops *dma_ops; +#endif #ifdef CONFIG_DMAR void *iommu; /* hook for IOMMU specific extension */ #endif diff --git a/include/asm-x86/dma-mapping.h b/include/asm-x86/dma-mapping.h index c2ddd3d1b883..0eaa9bf6011f 100644 --- a/include/asm-x86/dma-mapping.h +++ b/include/asm-x86/dma-mapping.h @@ -17,7 +17,8 @@ extern int panic_on_overflow; extern int force_iommu; struct dma_mapping_ops { - int (*mapping_error)(dma_addr_t dma_addr); + int (*mapping_error)(struct device *dev, + dma_addr_t dma_addr); void* (*alloc_coherent)(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp); void (*free_coherent)(struct device *dev, size_t size, @@ -56,14 +57,32 @@ struct dma_mapping_ops { int is_phys; }; -extern const struct dma_mapping_ops *dma_ops; +extern struct dma_mapping_ops *dma_ops; -static inline int dma_mapping_error(dma_addr_t dma_addr) +static inline struct dma_mapping_ops *get_dma_ops(struct device *dev) { - if (dma_ops->mapping_error) - return dma_ops->mapping_error(dma_addr); +#ifdef CONFIG_X86_32 + return dma_ops; +#else + if (unlikely(!dev) || !dev->archdata.dma_ops) + return dma_ops; + else + return dev->archdata.dma_ops; +#endif +} + +/* Make sure we keep the same behaviour */ +static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ +#ifdef CONFIG_X86_32 + return 0; +#else + struct dma_mapping_ops *ops = get_dma_ops(dev); + if (ops->mapping_error) + return ops->mapping_error(dev, dma_addr); return (dma_addr == bad_dma_address); +#endif } #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) @@ -83,44 +102,53 @@ static inline dma_addr_t dma_map_single(struct device *hwdev, void *ptr, size_t size, int direction) { + struct dma_mapping_ops *ops = get_dma_ops(hwdev); + BUG_ON(!valid_dma_direction(direction)); - return dma_ops->map_single(hwdev, virt_to_phys(ptr), size, direction); + return ops->map_single(hwdev, virt_to_phys(ptr), size, direction); } static inline void dma_unmap_single(struct device *dev, dma_addr_t addr, size_t size, int direction) { + struct dma_mapping_ops *ops = get_dma_ops(dev); + BUG_ON(!valid_dma_direction(direction)); - if (dma_ops->unmap_single) - dma_ops->unmap_single(dev, addr, size, direction); + if (ops->unmap_single) + ops->unmap_single(dev, addr, size, direction); } static inline int dma_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, int direction) { + struct dma_mapping_ops *ops = get_dma_ops(hwdev); + BUG_ON(!valid_dma_direction(direction)); - return dma_ops->map_sg(hwdev, sg, nents, direction); + return ops->map_sg(hwdev, sg, nents, direction); } static inline void dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents, int direction) { + struct dma_mapping_ops *ops = get_dma_ops(hwdev); + BUG_ON(!valid_dma_direction(direction)); - if (dma_ops->unmap_sg) - dma_ops->unmap_sg(hwdev, sg, nents, direction); + if (ops->unmap_sg) + ops->unmap_sg(hwdev, sg, nents, direction); } static inline void dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle, size_t size, int direction) { + struct dma_mapping_ops *ops = get_dma_ops(hwdev); + BUG_ON(!valid_dma_direction(direction)); - if (dma_ops->sync_single_for_cpu) - dma_ops->sync_single_for_cpu(hwdev, dma_handle, size, - direction); + if (ops->sync_single_for_cpu) + ops->sync_single_for_cpu(hwdev, dma_handle, size, direction); flush_write_buffers(); } @@ -128,10 +156,11 @@ static inline void dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle, size_t size, int direction) { + struct dma_mapping_ops *ops = get_dma_ops(hwdev); + BUG_ON(!valid_dma_direction(direction)); - if (dma_ops->sync_single_for_device) - dma_ops->sync_single_for_device(hwdev, dma_handle, size, - direction); + if (ops->sync_single_for_device) + ops->sync_single_for_device(hwdev, dma_handle, size, direction); flush_write_buffers(); } @@ -139,11 +168,12 @@ static inline void dma_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dma_handle, unsigned long offset, size_t size, int direction) { - BUG_ON(!valid_dma_direction(direction)); - if (dma_ops->sync_single_range_for_cpu) - dma_ops->sync_single_range_for_cpu(hwdev, dma_handle, offset, - size, direction); + struct dma_mapping_ops *ops = get_dma_ops(hwdev); + BUG_ON(!valid_dma_direction(direction)); + if (ops->sync_single_range_for_cpu) + ops->sync_single_range_for_cpu(hwdev, dma_handle, offset, + size, direction); flush_write_buffers(); } @@ -152,11 +182,12 @@ dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle, unsigned long offset, size_t size, int direction) { - BUG_ON(!valid_dma_direction(direction)); - if (dma_ops->sync_single_range_for_device) - dma_ops->sync_single_range_for_device(hwdev, dma_handle, - offset, size, direction); + struct dma_mapping_ops *ops = get_dma_ops(hwdev); + BUG_ON(!valid_dma_direction(direction)); + if (ops->sync_single_range_for_device) + ops->sync_single_range_for_device(hwdev, dma_handle, + offset, size, direction); flush_write_buffers(); } @@ -164,9 +195,11 @@ static inline void dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, int nelems, int direction) { + struct dma_mapping_ops *ops = get_dma_ops(hwdev); + BUG_ON(!valid_dma_direction(direction)); - if (dma_ops->sync_sg_for_cpu) - dma_ops->sync_sg_for_cpu(hwdev, sg, nelems, direction); + if (ops->sync_sg_for_cpu) + ops->sync_sg_for_cpu(hwdev, sg, nelems, direction); flush_write_buffers(); } @@ -174,9 +207,11 @@ static inline void dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, int nelems, int direction) { + struct dma_mapping_ops *ops = get_dma_ops(hwdev); + BUG_ON(!valid_dma_direction(direction)); - if (dma_ops->sync_sg_for_device) - dma_ops->sync_sg_for_device(hwdev, sg, nelems, direction); + if (ops->sync_sg_for_device) + ops->sync_sg_for_device(hwdev, sg, nelems, direction); flush_write_buffers(); } @@ -185,9 +220,11 @@ static inline dma_addr_t dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, int direction) { + struct dma_mapping_ops *ops = get_dma_ops(dev); + BUG_ON(!valid_dma_direction(direction)); - return dma_ops->map_single(dev, page_to_phys(page)+offset, - size, direction); + return ops->map_single(dev, page_to_phys(page) + offset, + size, direction); } static inline void dma_unmap_page(struct device *dev, dma_addr_t addr, diff --git a/include/asm-x86/swiotlb.h b/include/asm-x86/swiotlb.h index c706a7442633..2730b351afcf 100644 --- a/include/asm-x86/swiotlb.h +++ b/include/asm-x86/swiotlb.h @@ -35,7 +35,7 @@ extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, int direction); extern void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents, int direction); -extern int swiotlb_dma_mapping_error(dma_addr_t dma_addr); +extern int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr); extern void swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle); extern int swiotlb_dma_supported(struct device *hwdev, u64 mask); diff --git a/include/asm-xtensa/dma-mapping.h b/include/asm-xtensa/dma-mapping.h index 3c7d537dd15d..51882ae3db4d 100644 --- a/include/asm-xtensa/dma-mapping.h +++ b/include/asm-xtensa/dma-mapping.h @@ -139,7 +139,7 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, consistent_sync(sg_virt(sg), sg->length, dir); } static inline int -dma_mapping_error(dma_addr_t dma_addr) +dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return 0; } diff --git a/include/linux/i2o.h b/include/linux/i2o.h index 7d51cbca49ab..75ae6d8aba4f 100644 --- a/include/linux/i2o.h +++ b/include/linux/i2o.h @@ -758,7 +758,7 @@ static inline dma_addr_t i2o_dma_map_single(struct i2o_controller *c, void *ptr, } dma_addr = dma_map_single(&c->pdev->dev, ptr, size, direction); - if (!dma_mapping_error(dma_addr)) { + if (!dma_mapping_error(&c->pdev->dev, dma_addr)) { #ifdef CONFIG_I2O_EXT_ADAPTEC_DMA64 if ((sizeof(dma_addr_t) > 4) && c->pae_support) { *mptr++ = cpu_to_le32(0x7C020002); diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 4bf8cade9dbc..e530026eedf7 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -427,9 +427,9 @@ static inline int ssb_dma_mapping_error(struct ssb_device *dev, dma_addr_t addr) { switch (dev->bus->bustype) { case SSB_BUSTYPE_PCI: - return pci_dma_mapping_error(addr); + return pci_dma_mapping_error(dev->bus->host_pci, addr); case SSB_BUSTYPE_SSB: - return dma_mapping_error(addr); + return dma_mapping_error(dev->dev, addr); default: __ssb_dma_not_implemented(dev); } diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 90b529f7a154..936e333e7ce5 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1590,7 +1590,7 @@ static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr) { if (dev->dma_ops) return dev->dma_ops->mapping_error(dev, dma_addr); - return dma_mapping_error(dma_addr); + return dma_mapping_error(dev->dma_device, dma_addr); } /** diff --git a/lib/swiotlb.c b/lib/swiotlb.c index d568894df8cc..977edbdbc1de 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -492,7 +492,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size, */ dma_addr_t handle; handle = swiotlb_map_single(NULL, NULL, size, DMA_FROM_DEVICE); - if (swiotlb_dma_mapping_error(handle)) + if (swiotlb_dma_mapping_error(hwdev, handle)) return NULL; ret = bus_to_virt(handle); @@ -824,7 +824,7 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, } int -swiotlb_dma_mapping_error(dma_addr_t dma_addr) +swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr) { return (dma_addr == virt_to_bus(io_tlb_overflow_buffer)); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index a19b22b452a3..84d328329d98 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -169,7 +169,8 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, (void *) vec->sge[xdr_sge_no].iov_base + sge_off, sge_bytes, DMA_TO_DEVICE); - if (dma_mapping_error(sge[sge_no].addr)) + if (dma_mapping_error(xprt->sc_cm_id->device->dma_device, + sge[sge_no].addr)) goto err; sge_off = 0; sge_no++; -- cgit v1.2.3 From 20d8b67c06fa5e74f44e80b0a0fd68c8327f7c6a Mon Sep 17 00:00:00 2001 From: Eduard - Gabriel Munteanu Date: Fri, 25 Jul 2008 19:45:12 -0700 Subject: relay: add buffer-only channels; useful for early logging Allows one to create and use a channel with no associated files. Files can be initialized later. This is useful in scenarios such as logging in early code, before VFS is up. Therefore, such channels can be created and used as soon as kmem_cache_init() completed. This is needed by kmemtrace to do tracing in early kernel code. [kosaki.motohiro@jp.fujitsu.com: build fix] Signed-off-by: Eduard - Gabriel Munteanu Cc: Tom Zanussi Signed-off-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/relay.txt | 10 +++ include/linux/relay.h | 5 ++ kernel/relay.c | 170 ++++++++++++++++++++++++++++++------ 3 files changed, 156 insertions(+), 29 deletions(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/relay.txt b/Documentation/filesystems/relay.txt index 094f2d2f38b1..510b722667ac 100644 --- a/Documentation/filesystems/relay.txt +++ b/Documentation/filesystems/relay.txt @@ -294,6 +294,16 @@ user-defined data with a channel, and is immediately available (including in create_buf_file()) via chan->private_data or buf->chan->private_data. +Buffer-only channels +-------------------- + +These channels have no files associated and can be created with +relay_open(NULL, NULL, ...). Such channels are useful in scenarios such +as when doing early tracing in the kernel, before the VFS is up. In these +cases, one may open a buffer-only channel and then call +relay_late_setup_files() when the kernel is ready to handle files, +to expose the buffered data to the userspace. + Channel 'modes' --------------- diff --git a/include/linux/relay.h b/include/linux/relay.h index 6cd8c4425fc7..953fc055e875 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -48,6 +48,7 @@ struct rchan_buf size_t *padding; /* padding counts per sub-buffer */ size_t prev_padding; /* temporary variable */ size_t bytes_consumed; /* bytes consumed in cur read subbuf */ + size_t early_bytes; /* bytes consumed before VFS inited */ unsigned int cpu; /* this buf's cpu */ } ____cacheline_aligned; @@ -68,6 +69,7 @@ struct rchan int is_global; /* One global buffer ? */ struct list_head list; /* for channel list */ struct dentry *parent; /* parent dentry passed to open */ + int has_base_filename; /* has a filename associated? */ char base_filename[NAME_MAX]; /* saved base filename */ }; @@ -169,6 +171,9 @@ struct rchan *relay_open(const char *base_filename, size_t n_subbufs, struct rchan_callbacks *cb, void *private_data); +extern int relay_late_setup_files(struct rchan *chan, + const char *base_filename, + struct dentry *parent); extern void relay_close(struct rchan *chan); extern void relay_flush(struct rchan *chan); extern void relay_subbufs_consumed(struct rchan *chan, diff --git a/kernel/relay.c b/kernel/relay.c index 7de644cdec43..04006ef970b8 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -407,6 +407,35 @@ void relay_reset(struct rchan *chan) } EXPORT_SYMBOL_GPL(relay_reset); +static inline void relay_set_buf_dentry(struct rchan_buf *buf, + struct dentry *dentry) +{ + buf->dentry = dentry; + buf->dentry->d_inode->i_size = buf->early_bytes; +} + +static struct dentry *relay_create_buf_file(struct rchan *chan, + struct rchan_buf *buf, + unsigned int cpu) +{ + struct dentry *dentry; + char *tmpname; + + tmpname = kzalloc(NAME_MAX + 1, GFP_KERNEL); + if (!tmpname) + return NULL; + snprintf(tmpname, NAME_MAX, "%s%d", chan->base_filename, cpu); + + /* Create file in fs */ + dentry = chan->cb->create_buf_file(tmpname, chan->parent, + S_IRUSR, buf, + &chan->is_global); + + kfree(tmpname); + + return dentry; +} + /* * relay_open_buf - create a new relay channel buffer * @@ -416,45 +445,34 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu) { struct rchan_buf *buf = NULL; struct dentry *dentry; - char *tmpname; if (chan->is_global) return chan->buf[0]; - tmpname = kzalloc(NAME_MAX + 1, GFP_KERNEL); - if (!tmpname) - goto end; - snprintf(tmpname, NAME_MAX, "%s%d", chan->base_filename, cpu); - buf = relay_create_buf(chan); if (!buf) - goto free_name; + return NULL; + + if (chan->has_base_filename) { + dentry = relay_create_buf_file(chan, buf, cpu); + if (!dentry) + goto free_buf; + relay_set_buf_dentry(buf, dentry); + } buf->cpu = cpu; __relay_reset(buf, 1); - /* Create file in fs */ - dentry = chan->cb->create_buf_file(tmpname, chan->parent, S_IRUSR, - buf, &chan->is_global); - if (!dentry) - goto free_buf; - - buf->dentry = dentry; - if(chan->is_global) { chan->buf[0] = buf; buf->cpu = 0; } - goto free_name; + return buf; free_buf: relay_destroy_buf(buf); - buf = NULL; -free_name: - kfree(tmpname); -end: - return buf; + return NULL; } /** @@ -537,8 +555,8 @@ static int __cpuinit relay_hotcpu_callback(struct notifier_block *nb, /** * relay_open - create a new relay channel - * @base_filename: base name of files to create - * @parent: dentry of parent directory, %NULL for root directory + * @base_filename: base name of files to create, %NULL for buffering only + * @parent: dentry of parent directory, %NULL for root directory or buffer * @subbuf_size: size of sub-buffers * @n_subbufs: number of sub-buffers * @cb: client callback functions @@ -560,8 +578,6 @@ struct rchan *relay_open(const char *base_filename, { unsigned int i; struct rchan *chan; - if (!base_filename) - return NULL; if (!(subbuf_size && n_subbufs)) return NULL; @@ -576,7 +592,10 @@ struct rchan *relay_open(const char *base_filename, chan->alloc_size = FIX_SIZE(subbuf_size * n_subbufs); chan->parent = parent; chan->private_data = private_data; - strlcpy(chan->base_filename, base_filename, NAME_MAX); + if (base_filename) { + chan->has_base_filename = 1; + strlcpy(chan->base_filename, base_filename, NAME_MAX); + } setup_callbacks(chan, cb); kref_init(&chan->kref); @@ -604,6 +623,94 @@ free_bufs: } EXPORT_SYMBOL_GPL(relay_open); +struct rchan_percpu_buf_dispatcher { + struct rchan_buf *buf; + struct dentry *dentry; +}; + +/* Called in atomic context. */ +static void __relay_set_buf_dentry(void *info) +{ + struct rchan_percpu_buf_dispatcher *p = info; + + relay_set_buf_dentry(p->buf, p->dentry); +} + +/** + * relay_late_setup_files - triggers file creation + * @chan: channel to operate on + * @base_filename: base name of files to create + * @parent: dentry of parent directory, %NULL for root directory + * + * Returns 0 if successful, non-zero otherwise. + * + * Use to setup files for a previously buffer-only channel. + * Useful to do early tracing in kernel, before VFS is up, for example. + */ +int relay_late_setup_files(struct rchan *chan, + const char *base_filename, + struct dentry *parent) +{ + int err = 0; + unsigned int i, curr_cpu; + unsigned long flags; + struct dentry *dentry; + struct rchan_percpu_buf_dispatcher disp; + + if (!chan || !base_filename) + return -EINVAL; + + strlcpy(chan->base_filename, base_filename, NAME_MAX); + + mutex_lock(&relay_channels_mutex); + /* Is chan already set up? */ + if (unlikely(chan->has_base_filename)) + return -EEXIST; + chan->has_base_filename = 1; + chan->parent = parent; + curr_cpu = get_cpu(); + /* + * The CPU hotplug notifier ran before us and created buffers with + * no files associated. So it's safe to call relay_setup_buf_file() + * on all currently online CPUs. + */ + for_each_online_cpu(i) { + if (unlikely(!chan->buf[i])) { + printk(KERN_ERR "relay_late_setup_files: CPU %u " + "has no buffer, it must have!\n", i); + BUG(); + err = -EINVAL; + break; + } + + dentry = relay_create_buf_file(chan, chan->buf[i], i); + if (unlikely(!dentry)) { + err = -EINVAL; + break; + } + + if (curr_cpu == i) { + local_irq_save(flags); + relay_set_buf_dentry(chan->buf[i], dentry); + local_irq_restore(flags); + } else { + disp.buf = chan->buf[i]; + disp.dentry = dentry; + smp_mb(); + /* relay_channels_mutex must be held, so wait. */ + err = smp_call_function_single(i, + __relay_set_buf_dentry, + &disp, 1); + } + if (unlikely(err)) + break; + } + put_cpu(); + mutex_unlock(&relay_channels_mutex); + + return err; +} + /** * relay_switch_subbuf - switch to a new sub-buffer * @buf: channel buffer @@ -627,8 +734,13 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length) old_subbuf = buf->subbufs_produced % buf->chan->n_subbufs; buf->padding[old_subbuf] = buf->prev_padding; buf->subbufs_produced++; - buf->dentry->d_inode->i_size += buf->chan->subbuf_size - - buf->padding[old_subbuf]; + if (buf->dentry) + buf->dentry->d_inode->i_size += + buf->chan->subbuf_size - + buf->padding[old_subbuf]; + else + buf->early_bytes += buf->chan->subbuf_size - + buf->padding[old_subbuf]; smp_mb(); if (waitqueue_active(&buf->read_wait)) /* @@ -1237,4 +1349,4 @@ static __init int relay_init(void) return 0; } -module_init(relay_init); +early_initcall(relay_init); -- cgit v1.2.3 From a14e4b572b0ee5c6dbe4aceb83d00b2c969324e9 Mon Sep 17 00:00:00 2001 From: Bob Copeland Date: Fri, 25 Jul 2008 19:45:14 -0700 Subject: omfs: add filesystem documentation These patches add the Optimized MPEG Filesystem, a proprietary filesystem used by the embedded devices Rio Karma and ReplayTV, which are no longer manufactured. This filesystem module enables people to access files on these devices. This patch: OMFS is a proprietary filesystem created for the ReplayTV and also used by the Rio Karma. It uses hash tables with unordered, unbounded lists in each bucket for directories, extents for data blocks, 64-bit addressing for blocks, with up to 8K blocks (only 2K of a given block is ever used for metadata, so the FS still works with 4K pages). Document the filesystem usage and structures. Signed-off-by: Bob Copeland Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/omfs.txt | 106 +++++++++++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 Documentation/filesystems/omfs.txt (limited to 'Documentation') diff --git a/Documentation/filesystems/omfs.txt b/Documentation/filesystems/omfs.txt new file mode 100644 index 000000000000..1d0d41ff5c65 --- /dev/null +++ b/Documentation/filesystems/omfs.txt @@ -0,0 +1,106 @@ +Optimized MPEG Filesystem (OMFS) + +Overview +======== + +OMFS is a filesystem created by SonicBlue for use in the ReplayTV DVR +and Rio Karma MP3 player. The filesystem is extent-based, utilizing +block sizes from 2k to 8k, with hash-based directories. This +filesystem driver may be used to read and write disks from these +devices. + +Note, it is not recommended that this FS be used in place of a general +filesystem for your own streaming media device. Native Linux filesystems +will likely perform better. + +More information is available at: + + http://linux-karma.sf.net/ + +Various utilities, including mkomfs and omfsck, are included with +omfsprogs, available at: + + http://bobcopeland.com/karma/ + +Instructions are included in its README. + +Options +======= + +OMFS supports the following mount-time options: + + uid=n - make all files owned by specified user + gid=n - make all files owned by specified group + umask=xxx - set permission umask to xxx + fmask=xxx - set umask to xxx for files + dmask=xxx - set umask to xxx for directories + +Disk format +=========== + +OMFS discriminates between "sysblocks" and normal data blocks. The sysblock +group consists of super block information, file metadata, directory structures, +and extents. Each sysblock has a header containing CRCs of the entire +sysblock, and may be mirrored in successive blocks on the disk. A sysblock may +have a smaller size than a data block, but since they are both addressed by the +same 64-bit block number, any remaining space in the smaller sysblock is +unused. + +Sysblock header information: + +struct omfs_header { + __be64 h_self; /* FS block where this is located */ + __be32 h_body_size; /* size of useful data after header */ + __be16 h_crc; /* crc-ccitt of body_size bytes */ + char h_fill1[2]; + u8 h_version; /* version, always 1 */ + char h_type; /* OMFS_INODE_X */ + u8 h_magic; /* OMFS_IMAGIC */ + u8 h_check_xor; /* XOR of header bytes before this */ + __be32 h_fill2; +}; + +Files and directories are both represented by omfs_inode: + +struct omfs_inode { + struct omfs_header i_head; /* header */ + __be64 i_parent; /* parent containing this inode */ + __be64 i_sibling; /* next inode in hash bucket */ + __be64 i_ctime; /* ctime, in milliseconds */ + char i_fill1[35]; + char i_type; /* OMFS_[DIR,FILE] */ + __be32 i_fill2; + char i_fill3[64]; + char i_name[OMFS_NAMELEN]; /* filename */ + __be64 i_size; /* size of file, in bytes */ +}; + +Directories in OMFS are implemented as a large hash table. Filenames are +hashed then prepended into the bucket list beginning at OMFS_DIR_START. +Lookup requires hashing the filename, then seeking across i_sibling pointers +until a match is found on i_name. Empty buckets are represented by block +pointers with all-1s (~0). + +A file is an omfs_inode structure followed by an extent table beginning at +OMFS_EXTENT_START: + +struct omfs_extent_entry { + __be64 e_cluster; /* start location of a set of blocks */ + __be64 e_blocks; /* number of blocks after e_cluster */ +}; + +struct omfs_extent { + __be64 e_next; /* next extent table location */ + __be32 e_extent_count; /* total # extents in this table */ + __be32 e_fill; + struct omfs_extent_entry e_entry; /* start of extent entries */ +}; + +Each extent holds the block offset followed by number of blocks allocated to +the extent. The final extent in each table is a terminator with e_cluster +being ~0 and e_blocks being ones'-complement of the total number of blocks +in the table. + +If this table overflows, a continuation inode is written and pointed to by +e_next. These have a header but lack the rest of the inode structure. + -- cgit v1.2.3 From d91958815d214ea365b98cbff6215383897edcb6 Mon Sep 17 00:00:00 2001 From: Matt LaPlante Date: Fri, 25 Jul 2008 19:45:33 -0700 Subject: Documentation cleanup: trivial misspelling, punctuation, and grammar corrections. Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/Intel-IOMMU.txt | 4 ++-- Documentation/accounting/taskstats-struct.txt | 2 +- Documentation/cpu-freq/governors.txt | 2 +- Documentation/edac.txt | 2 +- Documentation/filesystems/proc.txt | 4 ++-- Documentation/filesystems/vfs.txt | 6 +++--- Documentation/ia64/kvm.txt | 8 ++++---- Documentation/input/cs461x.txt | 2 +- Documentation/ioctl/ioctl-decoding.txt | 4 ++-- Documentation/iostats.txt | 2 +- Documentation/keys.txt | 2 +- Documentation/leds-class.txt | 2 +- Documentation/local_ops.txt | 2 +- Documentation/networking/bonding.txt | 2 +- Documentation/networking/can.txt | 4 ++-- Documentation/networking/packet_mmap.txt | 2 +- Documentation/networking/tc-actions-env-rules.txt | 15 ++++++++------- Documentation/powerpc/booting-without-of.txt | 8 ++++---- Documentation/powerpc/qe_firmware.txt | 2 +- Documentation/s390/driver-model.txt | 2 +- Documentation/scsi/ibmmca.txt | 6 +++--- Documentation/scsi/lpfc.txt | 2 +- Documentation/scsi/scsi_fc_transport.txt | 6 +++--- Documentation/sh/clk.txt | 2 +- Documentation/sound/alsa/Audiophile-Usb.txt | 10 +++++----- Documentation/sound/alsa/hda_codec.txt | 2 +- Documentation/sound/alsa/soc/dapm.txt | 2 +- Documentation/sysctl/vm.txt | 2 +- Documentation/timers/highres.txt | 2 +- Documentation/usb/authorization.txt | 2 +- Documentation/video4linux/sn9c102.txt | 2 +- Documentation/vm/hugetlbpage.txt | 2 +- Documentation/vm/numa_memory_policy.txt | 4 ++-- Documentation/volatile-considered-harmful.txt | 2 +- drivers/message/fusion/lsi/mpi_history.txt | 6 +++--- 35 files changed, 65 insertions(+), 64 deletions(-) (limited to 'Documentation') diff --git a/Documentation/Intel-IOMMU.txt b/Documentation/Intel-IOMMU.txt index c2321903aa09..21bc416d887e 100644 --- a/Documentation/Intel-IOMMU.txt +++ b/Documentation/Intel-IOMMU.txt @@ -48,7 +48,7 @@ IOVA generation is pretty generic. We used the same technique as vmalloc() but these are not global address spaces, but separate for each domain. Different DMA engines may support different number of domains. -We also allocate gaurd pages with each mapping, so we can attempt to catch +We also allocate guard pages with each mapping, so we can attempt to catch any overflow that might happen. @@ -112,4 +112,4 @@ TBD - For compatibility testing, could use unity map domain for all devices, just provide a 1-1 for all useful memory under a single domain for all devices. -- API for paravirt ops for abstracting functionlity for VMM folks. +- API for paravirt ops for abstracting functionality for VMM folks. diff --git a/Documentation/accounting/taskstats-struct.txt b/Documentation/accounting/taskstats-struct.txt index b988d110db59..e7512c061c15 100644 --- a/Documentation/accounting/taskstats-struct.txt +++ b/Documentation/accounting/taskstats-struct.txt @@ -6,7 +6,7 @@ This document contains an explanation of the struct taskstats fields. There are three different groups of fields in the struct taskstats: 1) Common and basic accounting fields - If CONFIG_TASKSTATS is set, the taskstats inteface is enabled and + If CONFIG_TASKSTATS is set, the taskstats interface is enabled and the common fields and basic accounting fields are collected for delivery at do_exit() of a task. 2) Delay accounting fields diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt index dcec0564d040..5b0cfa67aff9 100644 --- a/Documentation/cpu-freq/governors.txt +++ b/Documentation/cpu-freq/governors.txt @@ -122,7 +122,7 @@ around '10000' or more. show_sampling_rate_(min|max): the minimum and maximum sampling rates available that you may set 'sampling_rate' to. -up_threshold: defines what the average CPU usaged between the samplings +up_threshold: defines what the average CPU usage between the samplings of 'sampling_rate' needs to be for the kernel to make a decision on whether it should increase the frequency. For example when it is set to its default value of '80' it means that between the checking diff --git a/Documentation/edac.txt b/Documentation/edac.txt index ced527388001..8eda3fb66416 100644 --- a/Documentation/edac.txt +++ b/Documentation/edac.txt @@ -327,7 +327,7 @@ Sdram memory scrubbing rate: 'sdram_scrub_rate' Read/Write attribute file that controls memory scrubbing. The scrubbing - rate is set by writing a minimum bandwith in bytes/sec to the attribute + rate is set by writing a minimum bandwidth in bytes/sec to the attribute file. The rate will be translated to an internal value that gives at least the specified rate. diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 8c6384bdfed4..64557821ee59 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -931,7 +931,7 @@ group_prealloc max_to_scan mb_groups mb_history min_to_scan order2_req stats stream_req mb_groups: -This file gives the details of mutiblock allocator buddy cache of free blocks +This file gives the details of multiblock allocator buddy cache of free blocks mb_history: Multiblock allocation history. @@ -1474,7 +1474,7 @@ used because pages_free(1355) is smaller than watermark + protection[2] normal page requirement. If requirement is DMA zone(index=0), protection[0] (=0) is used. -zone[i]'s protection[j] is calculated by following exprssion. +zone[i]'s protection[j] is calculated by following expression. (i < j): zone[i]->protection[j] diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index b7522c6cbae3..c4d348dabe94 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -143,7 +143,7 @@ struct file_system_type { The get_sb() method has the following arguments: - struct file_system_type *fs_type: decribes the filesystem, partly initialized + struct file_system_type *fs_type: describes the filesystem, partly initialized by the specific filesystem code int flags: mount flags @@ -895,9 +895,9 @@ struct dentry_operations { iput() yourself d_dname: called when the pathname of a dentry should be generated. - Usefull for some pseudo filesystems (sockfs, pipefs, ...) to delay + Useful for some pseudo filesystems (sockfs, pipefs, ...) to delay pathname generation. (Instead of doing it when dentry is created, - its done only when the path is needed.). Real filesystems probably + it's done only when the path is needed.). Real filesystems probably dont want to use it, because their dentries are present in global dcache hash, so their hash should be an invariant. As no lock is held, d_dname() should not try to modify the dentry itself, unless diff --git a/Documentation/ia64/kvm.txt b/Documentation/ia64/kvm.txt index bec9d815da33..914d07f49268 100644 --- a/Documentation/ia64/kvm.txt +++ b/Documentation/ia64/kvm.txt @@ -50,9 +50,9 @@ Note: For step 2, please make sure that host page size == TARGET_PAGE_SIZE of qe /usr/local/bin/qemu-system-ia64 -smp xx -m 512 -hda $your_image (xx is the number of virtual processors for the guest, now the maximum value is 4) -5. Known possibile issue on some platforms with old Firmware. +5. Known possible issue on some platforms with old Firmware. -If meet strange host crashe issues, try to solve it through either of the following ways: +In the event of strange host crash issues, try to solve it through either of the following ways: (1): Upgrade your Firmware to the latest one. @@ -65,8 +65,8 @@ index 0b53344..f02b0f7 100644 mov ar.pfs = loc1 mov rp = loc0 ;; -- srlz.d // seralize restoration of psr.l -+ srlz.i // seralize restoration of psr.l +- srlz.d // serialize restoration of psr.l ++ srlz.i // serialize restoration of psr.l + ;; br.ret.sptk.many b0 END(ia64_pal_call_static) diff --git a/Documentation/input/cs461x.txt b/Documentation/input/cs461x.txt index afe0d6543e09..202e9dbacec3 100644 --- a/Documentation/input/cs461x.txt +++ b/Documentation/input/cs461x.txt @@ -31,7 +31,7 @@ The driver works with ALSA drivers simultaneously. For example, the xracer uses joystick as input device and PCM device as sound output in one time. There are no sound or input collisions detected. The source code have comments about them; but I've found the joystick can be initialized -separately of ALSA modules. So, you canm use only one joystick driver +separately of ALSA modules. So, you can use only one joystick driver without ALSA drivers. The ALSA drivers are not needed to compile or run this driver. diff --git a/Documentation/ioctl/ioctl-decoding.txt b/Documentation/ioctl/ioctl-decoding.txt index bfdf7f3ee4f0..e35efb0cec2e 100644 --- a/Documentation/ioctl/ioctl-decoding.txt +++ b/Documentation/ioctl/ioctl-decoding.txt @@ -1,6 +1,6 @@ To decode a hex IOCTL code: -Most architecures use this generic format, but check +Most architectures use this generic format, but check include/ARCH/ioctl.h for specifics, e.g. powerpc uses 3 bits to encode read/write and 13 bits for size. @@ -18,7 +18,7 @@ uses 3 bits to encode read/write and 13 bits for size. 7-0 function # - So for example 0x82187201 is a read with arg length of 0x218, +So for example 0x82187201 is a read with arg length of 0x218, character 'r' function 1. Grepping the source reveals this is: #define VFAT_IOCTL_READDIR_BOTH _IOR('r', 1, struct dirent [2]) diff --git a/Documentation/iostats.txt b/Documentation/iostats.txt index 5925c3cd030d..59a69ec67c40 100644 --- a/Documentation/iostats.txt +++ b/Documentation/iostats.txt @@ -143,7 +143,7 @@ disk and partition statistics are consistent again. Since we still don't keep record of the partition-relative address, an operation is attributed to the partition which contains the first sector of the request after the eventual merges. As requests can be merged across partition, this could lead -to some (probably insignificant) innacuracy. +to some (probably insignificant) inaccuracy. Additional notes ---------------- diff --git a/Documentation/keys.txt b/Documentation/keys.txt index d5c7a57d1700..b56aacc1fff8 100644 --- a/Documentation/keys.txt +++ b/Documentation/keys.txt @@ -864,7 +864,7 @@ payload contents" for more information. request_key_with_auxdata() respectively. These two functions return with the key potentially still under - construction. To wait for contruction completion, the following should be + construction. To wait for construction completion, the following should be called: int wait_for_key_construction(struct key *key, bool intr); diff --git a/Documentation/leds-class.txt b/Documentation/leds-class.txt index 18860ad9935a..6399557cdab3 100644 --- a/Documentation/leds-class.txt +++ b/Documentation/leds-class.txt @@ -59,7 +59,7 @@ Hardware accelerated blink of LEDs Some LEDs can be programmed to blink without any CPU interaction. To support this feature, a LED driver can optionally implement the -blink_set() function (see ). If implemeted, triggers can +blink_set() function (see ). If implemented, triggers can attempt to use it before falling back to software timers. The blink_set() function should return 0 if the blink setting is supported, or -EINVAL otherwise, which means that LED blinking will be handled by software. diff --git a/Documentation/local_ops.txt b/Documentation/local_ops.txt index 4269a1105b37..f4f8b1c6c8ba 100644 --- a/Documentation/local_ops.txt +++ b/Documentation/local_ops.txt @@ -36,7 +36,7 @@ It can be done by slightly modifying the standard atomic operations : only their UP variant must be kept. It typically means removing LOCK prefix (on i386 and x86_64) and any SMP sychronization barrier. If the architecture does not have a different behavior between SMP and UP, including asm-generic/local.h -in your archtecture's local.h is sufficient. +in your architecture's local.h is sufficient. The local_t type is defined as an opaque signed long by embedding an atomic_long_t inside a structure. This is made so a cast from this type to a diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index 7fa7fe71d7a8..688dfe1e6b70 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -631,7 +631,7 @@ xmit_hash_policy in environments where a layer3 gateway device is required to reach most destinations. - This algorithm is 802.3ad complient. + This algorithm is 802.3ad compliant. layer3+4 diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt index 641d2afacffa..297ba7b1ccaf 100644 --- a/Documentation/networking/can.txt +++ b/Documentation/networking/can.txt @@ -186,7 +186,7 @@ solution for a couple of reasons: The Linux network devices (by default) just can handle the transmission and reception of media dependent frames. Due to the - arbritration on the CAN bus the transmission of a low prio CAN-ID + arbitration on the CAN bus the transmission of a low prio CAN-ID may be delayed by the reception of a high prio CAN frame. To reflect the correct* traffic on the node the loopback of the sent data has to be performed right after a successful transmission. If @@ -481,7 +481,7 @@ solution for a couple of reasons: - stats_timer: To calculate the Socket CAN core statistics (e.g. current/maximum frames per second) this 1 second timer is invoked at can.ko module start time by default. This timer can be - disabled by using stattimer=0 on the module comandline. + disabled by using stattimer=0 on the module commandline. - debug: (removed since SocketCAN SVN r546) diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt index db0cd5169581..07c53d596035 100644 --- a/Documentation/networking/packet_mmap.txt +++ b/Documentation/networking/packet_mmap.txt @@ -326,7 +326,7 @@ just one call to mmap is needed: mmap(0, size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); If tp_frame_size is a divisor of tp_block_size frames will be -contiguosly spaced by tp_frame_size bytes. If not, each +contiguously spaced by tp_frame_size bytes. If not, each tp_block_size/tp_frame_size frames there will be a gap between the frames. This is because a frame cannot be spawn across two blocks. diff --git a/Documentation/networking/tc-actions-env-rules.txt b/Documentation/networking/tc-actions-env-rules.txt index 01e716d185f4..dcadf6f88e34 100644 --- a/Documentation/networking/tc-actions-env-rules.txt +++ b/Documentation/networking/tc-actions-env-rules.txt @@ -4,26 +4,27 @@ The "enviromental" rules for authors of any new tc actions are: 1) If you stealeth or borroweth any packet thou shalt be branching from the righteous path and thou shalt cloneth. -For example if your action queues a packet to be processed later -or intentionaly branches by redirecting a packet then you need to +For example if your action queues a packet to be processed later, +or intentionally branches by redirecting a packet, then you need to clone the packet. + There are certain fields in the skb tc_verd that need to be reset so we -avoid loops etc. A few are generic enough so much so that skb_act_clone() -resets them for you. So invoke skb_act_clone() rather than skb_clone() +avoid loops, etc. A few are generic enough that skb_act_clone() +resets them for you, so invoke skb_act_clone() rather than skb_clone(). 2) If you munge any packet thou shalt call pskb_expand_head in the case someone else is referencing the skb. After that you "own" the skb. You must also tell us if it is ok to munge the packet (TC_OK2MUNGE), this way any action downstream can stomp on the packet. -3) dropping packets you dont own is a nono. You simply return +3) Dropping packets you don't own is a no-no. You simply return TC_ACT_SHOT to the caller and they will drop it. The "enviromental" rules for callers of actions (qdiscs etc) are: -*) thou art responsible for freeing anything returned as being +*) Thou art responsible for freeing anything returned as being TC_ACT_SHOT/STOLEN/QUEUED. If none of TC_ACT_SHOT/STOLEN/QUEUED is -returned then all is great and you dont need to do anything. +returned, then all is great and you don't need to do anything. Post on netdev if something is unclear. diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt index 99514ced82c5..928a79ceb7aa 100644 --- a/Documentation/powerpc/booting-without-of.txt +++ b/Documentation/powerpc/booting-without-of.txt @@ -708,7 +708,7 @@ device or bus to be described by the device tree. In general, the format of an address for a device is defined by the parent bus type, based on the #address-cells and #size-cells properties. Note that the parent's parent definitions of #address-cells -and #size-cells are not inhereted so every node with children must specify +and #size-cells are not inherited so every node with children must specify them. The kernel requires the root node to have those properties defining addresses format for devices directly mapped on the processor bus. @@ -1777,7 +1777,7 @@ platforms are moved over to use the flattened-device-tree model. Xilinx uartlite devices are simple fixed speed serial ports. - Requred properties: + Required properties: - current-speed : Baud rate of uartlite v) Xilinx hwicap @@ -1799,7 +1799,7 @@ platforms are moved over to use the flattened-device-tree model. Xilinx UART 16550 devices are very similar to the NS16550 but with different register spacing and an offset from the base address. - Requred properties: + Required properties: - clock-frequency : Frequency of the clock input - reg-offset : A value of 3 is required - reg-shift : A value of 2 is required @@ -1953,7 +1953,7 @@ prefixed with the string "marvell,", for Marvell Technology Group Ltd. 1) The /system-controller node This node is used to represent the system-controller and must be - present when the system uses a system contller chip. The top-level + present when the system uses a system controller chip. The top-level system-controller node contains information that is global to all devices within the system controller chip. The node name begins with "system-controller" followed by the unit address, which is diff --git a/Documentation/powerpc/qe_firmware.txt b/Documentation/powerpc/qe_firmware.txt index 896266432d33..06da4d4b44f9 100644 --- a/Documentation/powerpc/qe_firmware.txt +++ b/Documentation/powerpc/qe_firmware.txt @@ -217,7 +217,7 @@ Although it is not recommended, you can specify '0' in the soc.model field to skip matching SOCs altogether. The 'model' field is a 16-bit number that matches the actual SOC. The -'major' and 'minor' fields are the major and minor revision numbrs, +'major' and 'minor' fields are the major and minor revision numbers, respectively, of the SOC. For example, to match the 8323, revision 1.0: diff --git a/Documentation/s390/driver-model.txt b/Documentation/s390/driver-model.txt index e938c442277d..bde473df748d 100644 --- a/Documentation/s390/driver-model.txt +++ b/Documentation/s390/driver-model.txt @@ -25,7 +25,7 @@ device 4711 via subchannel 1 in subchannel set 0, and subchannel 2 is a non-I/O subchannel. Device 1234 is accessed via subchannel 0 in subchannel set 1. The subchannel named 'defunct' does not represent any real subchannel on the -system; it is a pseudo subchannel where disconnnected ccw devices are moved to +system; it is a pseudo subchannel where disconnected ccw devices are moved to if they are displaced by another ccw device becoming operational on their former subchannel. The ccw devices will be moved again to a proper subchannel if they become operational again on that subchannel. diff --git a/Documentation/scsi/ibmmca.txt b/Documentation/scsi/ibmmca.txt index a810421f1fb3..3920f28710c4 100644 --- a/Documentation/scsi/ibmmca.txt +++ b/Documentation/scsi/ibmmca.txt @@ -524,7 +524,7 @@ - Michael Lang June 25 1997: (v1.8b) - 1) Some cosmetical changes for the handling of SCSI-device-types. + 1) Some cosmetic changes for the handling of SCSI-device-types. Now, also CD-Burners / WORMs and SCSI-scanners should work. For MO-drives I have no experience, therefore not yet supported. In logical_devices I changed from different type-variables to one @@ -914,7 +914,7 @@ in version 4.0. This was never really necessary, as all troubles were based on non-command related reasons up to now, so bypassing commands did not help to avoid any bugs. It is kept in 3.2X for debugging reasons. - 5) Dynamical reassignment of ldns was again verified and analyzed to be + 5) Dynamic reassignment of ldns was again verified and analyzed to be completely inoperational. This is corrected and should work now. 6) All commands that get sent to the SCSI adapter were verified and completed in such a way, that they are now completely conform to the @@ -1386,7 +1386,7 @@ concerning the Linux-kernel in special, this SCSI-driver comes without any warranty. Its functionality is tested as good as possible on certain machines and combinations of computer hardware, which does not exclude, - that dataloss or severe damage of hardware is possible while using this + that data loss or severe damage of hardware is possible while using this part of software on some arbitrary computer hardware or in combination with other software packages. It is highly recommended to make backup copies of your data before using this software. Furthermore, personal diff --git a/Documentation/scsi/lpfc.txt b/Documentation/scsi/lpfc.txt index 4dbe41370a6d..5741ea8aa88a 100644 --- a/Documentation/scsi/lpfc.txt +++ b/Documentation/scsi/lpfc.txt @@ -36,7 +36,7 @@ Cable pull and temporary device Loss: being removed, a switch rebooting, or a device reboot), the driver could hide the disappearance of the device from the midlayer. I/O's issued to the LLDD would simply be queued for a short duration, allowing the device - to reappear or link come back alive, with no inadvertant side effects + to reappear or link come back alive, with no inadvertent side effects to the system. If the driver did not hide these conditions, i/o would be errored by the driver, the mid-layer would exhaust its retries, and the device would be taken offline. Manual intervention would be required to diff --git a/Documentation/scsi/scsi_fc_transport.txt b/Documentation/scsi/scsi_fc_transport.txt index d403e46d8463..75143f0c23b6 100644 --- a/Documentation/scsi/scsi_fc_transport.txt +++ b/Documentation/scsi/scsi_fc_transport.txt @@ -65,7 +65,7 @@ Overview: discussion will concentrate on NPIV. Note: World Wide Name assignment (and uniqueness guarantees) are left - up to an administrative entity controling the vport. For example, + up to an administrative entity controlling the vport. For example, if vports are to be associated with virtual machines, a XEN mgmt utility would be responsible for creating wwpn/wwnn's for the vport, using it's own naming authority and OUI. (Note: it already does this @@ -91,7 +91,7 @@ Device Trees and Vport Objects: Here's what to expect in the device tree : The typical Physical Port's Scsi_Host: /sys/devices/.../host17/ - and it has the typical decendent tree: + and it has the typical descendant tree: /sys/devices/.../host17/rport-17:0-0/target17:0:0/17:0:0:0: and then the vport is created on the Physical Port: /sys/devices/.../host17/vport-17:0-0 @@ -192,7 +192,7 @@ Vport States: independent of the adapter's link state. - Instantiation of the vport on the FC link via ELS traffic, etc. This is equivalent to a "link up" and successfull link initialization. - Futher information can be found in the interfaces section below for + Further information can be found in the interfaces section below for Vport Creation. Once a vport has been instantiated with the kernel/LLDD, a vport state diff --git a/Documentation/sh/clk.txt b/Documentation/sh/clk.txt index 9aef710e9a4b..114b595cfa97 100644 --- a/Documentation/sh/clk.txt +++ b/Documentation/sh/clk.txt @@ -12,7 +12,7 @@ means no changes to adjanced clock Internally, the clk_set_rate_ex forwards request to clk->ops->set_rate method, if it is present in ops structure. The method should set the clock rate and adjust all needed clocks according to the passed algo_id. -Exact values for algo_id are machine-dependend. For the sh7722, the following +Exact values for algo_id are machine-dependent. For the sh7722, the following values are defined: NO_CHANGE = 0, diff --git a/Documentation/sound/alsa/Audiophile-Usb.txt b/Documentation/sound/alsa/Audiophile-Usb.txt index 2ad5e6306c44..a4c53d8961e1 100644 --- a/Documentation/sound/alsa/Audiophile-Usb.txt +++ b/Documentation/sound/alsa/Audiophile-Usb.txt @@ -236,15 +236,15 @@ The parameter can be given: alias snd-card-1 snd-usb-audio options snd-usb-audio index=1 device_setup=0x09 -CAUTION when initializaing the device +CAUTION when initializing the device ------------------------------------- * Correct initialization on the device requires that device_setup is given to the module BEFORE the device is turned on. So, if you use the "manual probing" method described above, take care to power-on the device AFTER this initialization. - * Failing to respect this will lead in a misconfiguration of the device. In this case - turn off the device, unproble the snd-usb-audio module, then probe it again with + * Failing to respect this will lead to a misconfiguration of the device. In this case + turn off the device, unprobe the snd-usb-audio module, then probe it again with correct device_setup parameter and then (and only then) turn on the device again. * If you've correctly initialized the device in a valid mode and then want to switch @@ -388,9 +388,9 @@ There are 2 main potential issues when using Jackd with the device: Jack supports big endian devices only in recent versions (thanks to Andreas Steinmetz for his first big-endian patch). I can't remember -extacly when this support was released into jackd, let's just say that +exactly when this support was released into jackd, let's just say that with jackd version 0.103.0 it's almost ok (just a small bug is affecting -16bits Big-Endian devices, but since you've read carefully the above +16bits Big-Endian devices, but since you've read carefully the above paragraphs, you're now using kernel >= 2.6.23 and your 16bits devices are now Little Endians ;-) ). diff --git a/Documentation/sound/alsa/hda_codec.txt b/Documentation/sound/alsa/hda_codec.txt index 8e1b02526698..34e87ec1379c 100644 --- a/Documentation/sound/alsa/hda_codec.txt +++ b/Documentation/sound/alsa/hda_codec.txt @@ -67,7 +67,7 @@ CONFIG_SND_HDA_POWER_SAVE kconfig. It's called when the codec needs to power up or may power down. The controller should check the all belonging codecs on the bus whether they are actually powered off (check codec->power_on), and optionally the driver may power down the -contoller side, too. +controller side, too. The bus instance is created via snd_hda_bus_new(). You need to pass the card instance, the template, and the pointer to store the diff --git a/Documentation/sound/alsa/soc/dapm.txt b/Documentation/sound/alsa/soc/dapm.txt index c784a18b94dc..b2ed6983f40d 100644 --- a/Documentation/sound/alsa/soc/dapm.txt +++ b/Documentation/sound/alsa/soc/dapm.txt @@ -68,7 +68,7 @@ Audio DAPM widgets fall into a number of types:- (Widgets are defined in include/sound/soc-dapm.h) Widgets are usually added in the codec driver and the machine driver. There are -convience macros defined in soc-dapm.h that can be used to quickly build a +convenience macros defined in soc-dapm.h that can be used to quickly build a list of widgets of the codecs and machines DAPM widgets. Most widgets have a name, register, shift and invert. Some widgets have extra diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 8a4863c4edd4..d79eeda7a699 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -116,7 +116,7 @@ of kilobytes free. The VM uses this number to compute a pages_min value for each lowmem zone in the system. Each lowmem zone gets a number of reserved free pages based proportionally on its size. -Some minimal ammount of memory is needed to satisfy PF_MEMALLOC +Some minimal amount of memory is needed to satisfy PF_MEMALLOC allocations; if you set this to lower than 1024KB, your system will become subtly broken, and prone to deadlock under high loads. diff --git a/Documentation/timers/highres.txt b/Documentation/timers/highres.txt index a73ecf5b4bdb..21332233cef1 100644 --- a/Documentation/timers/highres.txt +++ b/Documentation/timers/highres.txt @@ -125,7 +125,7 @@ increase of flexibility and the avoidance of duplicated code across architectures justifies the slight increase of the binary size. The conversion of an architecture has no functional impact, but allows to -utilize the high resolution and dynamic tick functionalites without any change +utilize the high resolution and dynamic tick functionalities without any change to the clock event device and timer interrupt code. After the conversion the enabling of high resolution timers and dynamic ticks is simply provided by adding the kernel/time/Kconfig file to the architecture specific Kconfig and diff --git a/Documentation/usb/authorization.txt b/Documentation/usb/authorization.txt index 2af400609498..381b22ee7834 100644 --- a/Documentation/usb/authorization.txt +++ b/Documentation/usb/authorization.txt @@ -8,7 +8,7 @@ not) in a system. This feature will allow you to implement a lock-down of USB devices, fully controlled by user space. As of now, when a USB device is connected it is configured and -it's interfaces inmediately made available to the users. With this +its interfaces are immediately made available to the users. With this modification, only if root authorizes the device to be configured will then it be possible to use it. diff --git a/Documentation/video4linux/sn9c102.txt b/Documentation/video4linux/sn9c102.txt index b26f5195af51..73de4050d637 100644 --- a/Documentation/video4linux/sn9c102.txt +++ b/Documentation/video4linux/sn9c102.txt @@ -157,7 +157,7 @@ Loading can be done as shown below: [root@localhost home]# modprobe sn9c102 -Note that the module is called "sn9c102" for historic reasons, althought it +Note that the module is called "sn9c102" for historic reasons, although it does not just support the SN9C102. At this point all the devices supported by the driver and connected to the USB diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt index 8a5b5763f0fe..ea8714fcc3ad 100644 --- a/Documentation/vm/hugetlbpage.txt +++ b/Documentation/vm/hugetlbpage.txt @@ -77,7 +77,7 @@ memory that is preset in system at this time. System administrators may want to put this command in one of the local rc init files. This will enable the kernel to request huge pages early in the boot process (when the possibility of getting physical contiguous pages is still very high). In either -case, adminstrators will want to verify the number of hugepages actually +case, administrators will want to verify the number of hugepages actually allocated by checking the sysctl or meminfo. /proc/sys/vm/nr_overcommit_hugepages indicates how large the pool of diff --git a/Documentation/vm/numa_memory_policy.txt b/Documentation/vm/numa_memory_policy.txt index bad16d3f6a47..6aaaeb38730c 100644 --- a/Documentation/vm/numa_memory_policy.txt +++ b/Documentation/vm/numa_memory_policy.txt @@ -58,7 +58,7 @@ most general to most specific: the policy at the time they were allocated. VMA Policy: A "VMA" or "Virtual Memory Area" refers to a range of a task's - virtual adddress space. A task may define a specific policy for a range + virtual address space. A task may define a specific policy for a range of its virtual address space. See the MEMORY POLICIES APIS section, below, for an overview of the mbind() system call used to set a VMA policy. @@ -353,7 +353,7 @@ follows: Because of this extra reference counting, and because we must lookup shared policies in a tree structure under spinlock, shared policies are - more expensive to use in the page allocation path. This is expecially + more expensive to use in the page allocation path. This is especially true for shared policies on shared memory regions shared by tasks running on different NUMA nodes. This extra overhead can be avoided by always falling back to task or system default policy for shared memory regions, diff --git a/Documentation/volatile-considered-harmful.txt b/Documentation/volatile-considered-harmful.txt index 10c2e411cca8..991c26a6ef64 100644 --- a/Documentation/volatile-considered-harmful.txt +++ b/Documentation/volatile-considered-harmful.txt @@ -114,6 +114,6 @@ CREDITS Original impetus and research by Randy Dunlap Written by Jonathan Corbet -Improvements via coments from Satyam Sharma, Johannes Stezenbach, Jesper +Improvements via comments from Satyam Sharma, Johannes Stezenbach, Jesper Juhl, Heikki Orsila, H. Peter Anvin, Philipp Hahn, and Stefan Richter. diff --git a/drivers/message/fusion/lsi/mpi_history.txt b/drivers/message/fusion/lsi/mpi_history.txt index 241592ab13ad..3f15fcfe4a2e 100644 --- a/drivers/message/fusion/lsi/mpi_history.txt +++ b/drivers/message/fusion/lsi/mpi_history.txt @@ -127,7 +127,7 @@ mpi_ioc.h * 08-08-01 01.02.01 Original release for v1.2 work. * New format for FWVersion and ProductId in * MSG_IOC_FACTS_REPLY and MPI_FW_HEADER. - * 08-31-01 01.02.02 Addded event MPI_EVENT_SCSI_DEVICE_STATUS_CHANGE and + * 08-31-01 01.02.02 Added event MPI_EVENT_SCSI_DEVICE_STATUS_CHANGE and * related structure and defines. * Added event MPI_EVENT_ON_BUS_TIMER_EXPIRED. * Added MPI_IOCINIT_FLAGS_DISCARD_FW_IMAGE. @@ -187,7 +187,7 @@ mpi_ioc.h * 10-11-06 01.05.12 Added MPI_IOCFACTS_EXCEPT_METADATA_UNSUPPORTED. * Added MaxInitiators field to PortFacts reply. * Added SAS Device Status Change ReasonCode for - * asynchronous notificaiton. + * asynchronous notification. * Added MPI_EVENT_SAS_EXPANDER_STATUS_CHANGE and event * data structure. * Added new ImageType values for FWDownload and FWUpload @@ -213,7 +213,7 @@ mpi_cnfg.h * Added _RESPONSE_ID_MASK definition to SCSI_PORT_1 * page and updated the page version. * Added Information field and _INFO_PARAMS_NEGOTIATED - * definitionto SCSI_DEVICE_0 page. + * definition to SCSI_DEVICE_0 page. * 06-22-00 01.00.03 Removed batch controls from LAN_0 page and updated the * page version. * Added BucketsRemaining to LAN_1 page, redefined the -- cgit v1.2.3 From e4ac9bc1f6686dcb8c34e2756aa93cc9546fa6ae Mon Sep 17 00:00:00 2001 From: Karsten Keil Date: Sat, 26 Jul 2008 18:52:11 +0200 Subject: Add mISDN driver mISDN is a new modular ISDN driver, in the long term it should replace the old I4L driver architecture for passiv ISDN cards. Signed-off-by: Karsten Keil --- Documentation/isdn/README.mISDN | 6 ++++++ drivers/isdn/Kconfig | 4 +++- drivers/isdn/Makefile | 1 + drivers/isdn/hardware/Makefile | 1 + 4 files changed, 11 insertions(+), 1 deletion(-) create mode 100644 Documentation/isdn/README.mISDN (limited to 'Documentation') diff --git a/Documentation/isdn/README.mISDN b/Documentation/isdn/README.mISDN new file mode 100644 index 000000000000..cd8bf920e77b --- /dev/null +++ b/Documentation/isdn/README.mISDN @@ -0,0 +1,6 @@ +mISDN is a new modular ISDN driver, in the long term it should replace +the old I4L driver architecture for passiv ISDN cards. +It was designed to allow a broad range of applications and interfaces +but only have the basic function in kernel, the interface to the user +space is based on sockets with a own address family AF_ISDN. + diff --git a/drivers/isdn/Kconfig b/drivers/isdn/Kconfig index 66f946aa30b3..3d113c6e4a70 100644 --- a/drivers/isdn/Kconfig +++ b/drivers/isdn/Kconfig @@ -3,7 +3,7 @@ # menuconfig ISDN - tristate "ISDN support" + bool "ISDN support" depends on NET depends on !S390 ---help--- @@ -21,6 +21,8 @@ menuconfig ISDN if ISDN +source "drivers/isdn/mISDN/Kconfig" + menuconfig ISDN_I4L tristate "Old ISDN4Linux (deprecated)" ---help--- diff --git a/drivers/isdn/Makefile b/drivers/isdn/Makefile index 988142c30a6d..8380a4568d11 100644 --- a/drivers/isdn/Makefile +++ b/drivers/isdn/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_ISDN_I4L) += i4l/ obj-$(CONFIG_ISDN_CAPI) += capi/ +obj-$(CONFIG_MISDN) += mISDN/ obj-$(CONFIG_ISDN_CAPI) += hardware/ obj-$(CONFIG_ISDN_DIVERSION) += divert/ obj-$(CONFIG_ISDN_DRV_HISAX) += hisax/ diff --git a/drivers/isdn/hardware/Makefile b/drivers/isdn/hardware/Makefile index 11c8a183948c..a5d8fce4c4c4 100644 --- a/drivers/isdn/hardware/Makefile +++ b/drivers/isdn/hardware/Makefile @@ -4,3 +4,4 @@ obj-$(CONFIG_CAPI_AVM) += avm/ obj-$(CONFIG_CAPI_EICON) += eicon/ +obj-$(CONFIG_MISDN) += mISDN/ -- cgit v1.2.3