diff options
677 files changed, 18980 insertions, 8008 deletions
diff --git a/.gitignore b/.gitignore index b93fb7eff942..946c7ec5c922 100644 --- a/.gitignore +++ b/.gitignore @@ -25,6 +25,7 @@ *.elf *.bin *.gz +*.bz2 *.lzma *.patch *.gcno diff --git a/Documentation/fb/framebuffer.txt b/Documentation/fb/framebuffer.txt index b3e3a0356839..fe79e3c8847d 100644 --- a/Documentation/fb/framebuffer.txt +++ b/Documentation/fb/framebuffer.txt @@ -312,10 +312,8 @@ and to the following documentation: 8. Mailing list --------------- -There are several frame buffer device related mailing lists at SourceForge: - - linux-fbdev-announce@lists.sourceforge.net, for announcements, - - linux-fbdev-user@lists.sourceforge.net, for generic user support, - - linux-fbdev-devel@lists.sourceforge.net, for project developers. +There is a frame buffer device related mailing list at kernel.org: +linux-fbdev@vger.kernel.org. Point your web browser to http://sourceforge.net/projects/linux-fbdev/ for subscription information and archive browsing. diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index bc693fffabe0..72ae06f73acf 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -302,18 +302,6 @@ Who: ocfs2-devel@oss.oracle.com --------------------------- -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SCTP_GET_PEER_ADDRS_OLD, - SCTP_GET_LOCAL_ADDRS_NUM_OLD, SCTP_GET_LOCAL_ADDRS_OLD -When: June 2009 -Why: A newer version of the options have been introduced in 2005 that - removes the limitions of the old API. The sctp library has been - converted to use these new options at the same time. Any user - space app that directly uses the old options should convert to using - the new options. -Who: Vlad Yasevich <vladislav.yasevich@hp.com> - ---------------------------- - What: Ability for non root users to shm_get hugetlb pages based on mlock resource limits When: 2.6.31 diff --git a/Documentation/filesystems/caching/fscache.txt b/Documentation/filesystems/caching/fscache.txt index 9e94b9491d89..a91e2e2095b0 100644 --- a/Documentation/filesystems/caching/fscache.txt +++ b/Documentation/filesystems/caching/fscache.txt @@ -235,6 +235,7 @@ proc files. neg=N Number of negative lookups made pos=N Number of positive lookups made crt=N Number of objects created by lookup + tmo=N Number of lookups timed out and requeued Updates n=N Number of update cookie requests seen nul=N Number of upd reqs given a NULL parent run=N Number of upd reqs granted CPU time @@ -250,8 +251,10 @@ proc files. ok=N Number of successful alloc reqs wt=N Number of alloc reqs that waited on lookup completion nbf=N Number of alloc reqs rejected -ENOBUFS + int=N Number of alloc reqs aborted -ERESTARTSYS ops=N Number of alloc reqs submitted owt=N Number of alloc reqs waited for CPU time + abt=N Number of alloc reqs aborted due to object death Retrvls n=N Number of retrieval (read) requests seen ok=N Number of successful retr reqs wt=N Number of retr reqs that waited on lookup completion @@ -261,6 +264,7 @@ proc files. oom=N Number of retr reqs failed -ENOMEM ops=N Number of retr reqs submitted owt=N Number of retr reqs waited for CPU time + abt=N Number of retr reqs aborted due to object death Stores n=N Number of storage (write) requests seen ok=N Number of successful store reqs agn=N Number of store reqs on a page already pending storage @@ -268,12 +272,37 @@ proc files. oom=N Number of store reqs failed -ENOMEM ops=N Number of store reqs submitted run=N Number of store reqs granted CPU time + pgs=N Number of pages given store req processing time + rxd=N Number of store reqs deleted from tracking tree + olm=N Number of store reqs over store limit + VmScan nos=N Number of release reqs against pages with no pending store + gon=N Number of release reqs against pages stored by time lock granted + bsy=N Number of release reqs ignored due to in-progress store + can=N Number of page stores cancelled due to release req Ops pend=N Number of times async ops added to pending queues run=N Number of times async ops given CPU time enq=N Number of times async ops queued for processing + can=N Number of async ops cancelled + rej=N Number of async ops rejected due to object lookup/create failure dfr=N Number of async ops queued for deferred release rel=N Number of async ops released gc=N Number of deferred-release async ops garbage collected + CacheOp alo=N Number of in-progress alloc_object() cache ops + luo=N Number of in-progress lookup_object() cache ops + luc=N Number of in-progress lookup_complete() cache ops + gro=N Number of in-progress grab_object() cache ops + upo=N Number of in-progress update_object() cache ops + dro=N Number of in-progress drop_object() cache ops + pto=N Number of in-progress put_object() cache ops + syn=N Number of in-progress sync_cache() cache ops + atc=N Number of in-progress attr_changed() cache ops + rap=N Number of in-progress read_or_alloc_page() cache ops + ras=N Number of in-progress read_or_alloc_pages() cache ops + alp=N Number of in-progress allocate_page() cache ops + als=N Number of in-progress allocate_pages() cache ops + wrp=N Number of in-progress write_page() cache ops + ucp=N Number of in-progress uncache_page() cache ops + dsp=N Number of in-progress dissociate_pages() cache ops (*) /proc/fs/fscache/histogram @@ -299,6 +328,87 @@ proc files. jiffy range covered, and the SECS field the equivalent number of seconds. +=========== +OBJECT LIST +=========== + +If CONFIG_FSCACHE_OBJECT_LIST is enabled, the FS-Cache facility will maintain a +list of all the objects currently allocated and allow them to be viewed +through: + + /proc/fs/fscache/objects + +This will look something like: + + [root@andromeda ~]# head /proc/fs/fscache/objects + OBJECT PARENT STAT CHLDN OPS OOP IPR EX READS EM EV F S | NETFS_COOKIE_DEF TY FL NETFS_DATA OBJECT_KEY, AUX_DATA + ======== ======== ==== ===== === === === == ===== == == = = | ================ == == ================ ================ + 17e4b 2 ACTV 0 0 0 0 0 0 7b 4 0 8 | NFS.fh DT 0 ffff88001dd82820 010006017edcf8bbc93b43298fdfbe71e50b57b13a172c0117f38472, e567634700000000000000000000000063f2404a000000000000000000000000c9030000000000000000000063f2404a + 1693a 2 ACTV 0 0 0 0 0 0 7b 4 0 8 | NFS.fh DT 0 ffff88002db23380 010006017edcf8bbc93b43298fdfbe71e50b57b1e0162c01a2df0ea6, 420ebc4a000000000000000000000000420ebc4a0000000000000000000000000e1801000000000000000000420ebc4a + +where the first set of columns before the '|' describe the object: + + COLUMN DESCRIPTION + ======= =============================================================== + OBJECT Object debugging ID (appears as OBJ%x in some debug messages) + PARENT Debugging ID of parent object + STAT Object state + CHLDN Number of child objects of this object + OPS Number of outstanding operations on this object + OOP Number of outstanding child object management operations + IPR + EX Number of outstanding exclusive operations + READS Number of outstanding read operations + EM Object's event mask + EV Events raised on this object + F Object flags + S Object slow-work work item flags + +and the second set of columns describe the object's cookie, if present: + + COLUMN DESCRIPTION + =============== ======================================================= + NETFS_COOKIE_DEF Name of netfs cookie definition + TY Cookie type (IX - index, DT - data, hex - special) + FL Cookie flags + NETFS_DATA Netfs private data stored in the cookie + OBJECT_KEY Object key } 1 column, with separating comma + AUX_DATA Object aux data } presence may be configured + +The data shown may be filtered by attaching the a key to an appropriate keyring +before viewing the file. Something like: + + keyctl add user fscache:objlist <restrictions> @s + +where <restrictions> are a selection of the following letters: + + K Show hexdump of object key (don't show if not given) + A Show hexdump of object aux data (don't show if not given) + +and the following paired letters: + + C Show objects that have a cookie + c Show objects that don't have a cookie + B Show objects that are busy + b Show objects that aren't busy + W Show objects that have pending writes + w Show objects that don't have pending writes + R Show objects that have outstanding reads + r Show objects that don't have outstanding reads + S Show objects that have slow work queued + s Show objects that don't have slow work queued + +If neither side of a letter pair is given, then both are implied. For example: + + keyctl add user fscache:objlist KB @s + +shows objects that are busy, and lists their object keys, but does not dump +their auxiliary data. It also implies "CcWwRrSs", but as 'B' is given, 'b' is +not implied. + +By default all objects and all fields will be shown. + + ========= DEBUGGING ========= diff --git a/Documentation/filesystems/caching/netfs-api.txt b/Documentation/filesystems/caching/netfs-api.txt index 2666b1ed5e9e..1902c57b72ef 100644 --- a/Documentation/filesystems/caching/netfs-api.txt +++ b/Documentation/filesystems/caching/netfs-api.txt @@ -641,7 +641,7 @@ data file must be retired (see the relinquish cookie function below). Furthermore, note that this does not cancel the asynchronous read or write operation started by the read/alloc and write functions, so the page -invalidation and release functions must use: +invalidation functions must use: bool fscache_check_page_write(struct fscache_cookie *cookie, struct page *page); @@ -654,6 +654,25 @@ to see if a page is being written to the cache, and: to wait for it to finish if it is. +When releasepage() is being implemented, a special FS-Cache function exists to +manage the heuristics of coping with vmscan trying to eject pages, which may +conflict with the cache trying to write pages to the cache (which may itself +need to allocate memory): + + bool fscache_maybe_release_page(struct fscache_cookie *cookie, + struct page *page, + gfp_t gfp); + +This takes the netfs cookie, and the page and gfp arguments as supplied to +releasepage(). It will return false if the page cannot be released yet for +some reason and if it returns true, the page has been uncached and can now be +released. + +To make a page available for release, this function may wait for an outstanding +storage request to complete, or it may attempt to cancel the storage request - +in which case the page will not be stored in the cache this time. + + ========================== INDEX AND DATA FILE UPDATE ========================== diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt index c2a0871280a0..c58b9f5ba002 100644 --- a/Documentation/filesystems/ocfs2.txt +++ b/Documentation/filesystems/ocfs2.txt @@ -20,15 +20,16 @@ Lots of code taken from ext3 and other projects. Authors in alphabetical order: Joel Becker <joel.becker@oracle.com> Zach Brown <zach.brown@oracle.com> -Mark Fasheh <mark.fasheh@oracle.com> +Mark Fasheh <mfasheh@suse.com> Kurt Hackel <kurt.hackel@oracle.com> +Tao Ma <tao.ma@oracle.com> Sunil Mushran <sunil.mushran@oracle.com> Manish Singh <manish.singh@oracle.com> +Tiger Yang <tiger.yang@oracle.com> Caveats ======= Features which OCFS2 does not support yet: - - quotas - Directory change notification (F_NOTIFY) - Distributed Caching (F_SETLEASE/F_GETLEASE/break_lease) @@ -70,7 +71,6 @@ commit=nrsec (*) Ocfs2 can be told to sync all its data and metadata performance. localalloc=8(*) Allows custom localalloc size in MB. If the value is too large, the fs will silently revert it to the default. - Localalloc is not enabled for local mounts. localflocks This disables cluster aware flock. inode64 Indicates that Ocfs2 is allowed to create inodes at any location in the filesystem, including those which diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index a0e134dd2523..006b39dec87d 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -164,6 +164,14 @@ tcp_congestion_control - STRING additional choices may be available based on kernel configuration. Default is set as part of kernel configuration. +tcp_cookie_size - INTEGER + Default size of TCP Cookie Transactions (TCPCT) option, that may be + overridden on a per socket basis by the TCPCT socket option. + Values greater than the maximum (16) are interpreted as the maximum. + Values greater than zero and less than the minimum (8) are interpreted + as the minimum. Odd values are interpreted as the next even value. + Default: 0 (off). + tcp_dsack - BOOLEAN Allows TCP to send "duplicate" SACKs. @@ -723,6 +731,12 @@ accept_source_route - BOOLEAN default TRUE (router) FALSE (host) +accept_local - BOOLEAN + Accept packets with local source addresses. In combination with + suitable routing, this can be used to direct packets between two + local interfaces over the wire and have them accepted properly. + default FALSE + rp_filter - INTEGER 0 - No source validation. 1 - Strict mode as defined in RFC3704 Strict Reverse Path @@ -738,8 +752,8 @@ rp_filter - INTEGER to prevent IP spoofing from DDos attacks. If using asymmetric routing or other complicated routing, then loose mode is recommended. - conf/all/rp_filter must also be set to non-zero to do source validation - on the interface + The max value from conf/{all,interface}/rp_filter is used + when doing source validation on the {interface}. Default value is 0. Note that some distributions enable it in startup scripts. diff --git a/Documentation/slow-work.txt b/Documentation/slow-work.txt index ebc50f808ea4..9dbf4470c7e1 100644 --- a/Documentation/slow-work.txt +++ b/Documentation/slow-work.txt @@ -41,6 +41,13 @@ expand files, provided the time taken to do so isn't too long. Operations of both types may sleep during execution, thus tying up the thread loaned to it. +A further class of work item is available, based on the slow work item class: + + (*) Delayed slow work items. + +These are slow work items that have a timer to defer queueing of the item for +a while. + THREAD-TO-CLASS ALLOCATION -------------------------- @@ -64,9 +71,11 @@ USING SLOW WORK ITEMS Firstly, a module or subsystem wanting to make use of slow work items must register its interest: - int ret = slow_work_register_user(); + int ret = slow_work_register_user(struct module *module); -This will return 0 if successful, or a -ve error upon failure. +This will return 0 if successful, or a -ve error upon failure. The module +pointer should be the module interested in using this facility (almost +certainly THIS_MODULE). Slow work items may then be set up by: @@ -93,6 +102,10 @@ Slow work items may then be set up by: or: + delayed_slow_work_init(&myitem, &myitem_ops); + + or: + vslow_work_init(&myitem, &myitem_ops); depending on its class. @@ -102,15 +115,92 @@ A suitably set up work item can then be enqueued for processing: int ret = slow_work_enqueue(&myitem); This will return a -ve error if the thread pool is unable to gain a reference -on the item, 0 otherwise. +on the item, 0 otherwise, or (for delayed work): + + int ret = delayed_slow_work_enqueue(&myitem, my_jiffy_delay); The items are reference counted, so there ought to be no need for a flush -operation. When all a module's slow work items have been processed, and the +operation. But as the reference counting is optional, means to cancel +existing work items are also included: + + cancel_slow_work(&myitem); + cancel_delayed_slow_work(&myitem); + +can be used to cancel pending work. The above cancel function waits for +existing work to have been executed (or prevent execution of them, depending +on timing). + + +When all a module's slow work items have been processed, and the module has no further interest in the facility, it should unregister its interest: - slow_work_unregister_user(); + slow_work_unregister_user(struct module *module); + +The module pointer is used to wait for all outstanding work items for that +module before completing the unregistration. This prevents the put_ref() code +from being taken away before it completes. module should almost certainly be +THIS_MODULE. + + +================ +HELPER FUNCTIONS +================ + +The slow-work facility provides a function by which it can be determined +whether or not an item is queued for later execution: + + bool queued = slow_work_is_queued(struct slow_work *work); + +If it returns false, then the item is not on the queue (it may be executing +with a requeue pending). This can be used to work out whether an item on which +another depends is on the queue, thus allowing a dependent item to be queued +after it. + +If the above shows an item on which another depends not to be queued, then the +owner of the dependent item might need to wait. However, to avoid locking up +the threads unnecessarily be sleeping in them, it can make sense under some +circumstances to return the work item to the queue, thus deferring it until +some other items have had a chance to make use of the yielded thread. + +To yield a thread and defer an item, the work function should simply enqueue +the work item again and return. However, this doesn't work if there's nothing +actually on the queue, as the thread just vacated will jump straight back into +the item's work function, thus busy waiting on a CPU. + +Instead, the item should use the thread to wait for the dependency to go away, +but rather than using schedule() or schedule_timeout() to sleep, it should use +the following function: + + bool requeue = slow_work_sleep_till_thread_needed( + struct slow_work *work, + signed long *_timeout); + +This will add a second wait and then sleep, such that it will be woken up if +either something appears on the queue that could usefully make use of the +thread - and behind which this item can be queued, or if the event the caller +set up to wait for happens. True will be returned if something else appeared +on the queue and this work function should perhaps return, of false if +something else woke it up. The timeout is as for schedule_timeout(). + +For example: + + wq = bit_waitqueue(&my_flags, MY_BIT); + init_wait(&wait); + requeue = false; + do { + prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); + if (!test_bit(MY_BIT, &my_flags)) + break; + requeue = slow_work_sleep_till_thread_needed(&my_work, + &timeout); + } while (timeout > 0 && !requeue); + finish_wait(wq, &wait); + if (!test_bit(MY_BIT, &my_flags) + goto do_my_thing; + if (requeue) + return; // to slow_work =============== @@ -118,7 +208,8 @@ ITEM OPERATIONS =============== Each work item requires a table of operations of type struct slow_work_ops. -All members are required: +Only ->execute() is required; the getting and putting of a reference and the +describing of an item are all optional. (*) Get a reference on an item: @@ -148,6 +239,16 @@ All members are required: This should perform the work required of the item. It may sleep, it may perform disk I/O and it may wait for locks. + (*) View an item through /proc: + + void (*desc)(struct slow_work *work, struct seq_file *m); + + If supplied, this should print to 'm' a small string describing the work + the item is to do. This should be no more than about 40 characters, and + shouldn't include a newline character. + + See the 'Viewing executing and queued items' section below. + ================== POOL CONFIGURATION @@ -172,3 +273,50 @@ The slow-work thread pool has a number of configurables: is bounded to between 1 and one fewer than the number of active threads. This ensures there is always at least one thread that can process very slow work items, and always at least one thread that won't. + + +================================== +VIEWING EXECUTING AND QUEUED ITEMS +================================== + +If CONFIG_SLOW_WORK_DEBUG is enabled, a debugfs file is made available: + + /sys/kernel/debug/slow_work/runqueue + +through which the list of work items being executed and the queues of items to +be executed may be viewed. The owner of a work item is given the chance to +add some information of its own. + +The contents look something like the following: + + THR PID ITEM ADDR FL MARK DESC + === ===== ================ == ===== ========== + 0 3005 ffff880023f52348 a 952ms FSC: OBJ17d3: LOOK + 1 3006 ffff880024e33668 2 160ms FSC: OBJ17e5 OP60d3b: Write1/Store fl=2 + 2 3165 ffff8800296dd180 a 424ms FSC: OBJ17e4: LOOK + 3 4089 ffff8800262c8d78 a 212ms FSC: OBJ17ea: CRTN + 4 4090 ffff88002792bed8 2 388ms FSC: OBJ17e8 OP60d36: Write1/Store fl=2 + 5 4092 ffff88002a0ef308 2 388ms FSC: OBJ17e7 OP60d2e: Write1/Store fl=2 + 6 4094 ffff88002abaf4b8 2 132ms FSC: OBJ17e2 OP60d4e: Write1/Store fl=2 + 7 4095 ffff88002bb188e0 a 388ms FSC: OBJ17e9: CRTN + vsq - ffff880023d99668 1 308ms FSC: OBJ17e0 OP60f91: Write1/EnQ fl=2 + vsq - ffff8800295d1740 1 212ms FSC: OBJ16be OP4d4b6: Write1/EnQ fl=2 + vsq - ffff880025ba3308 1 160ms FSC: OBJ179a OP58dec: Write1/EnQ fl=2 + vsq - ffff880024ec83e0 1 160ms FSC: OBJ17ae OP599f2: Write1/EnQ fl=2 + vsq - ffff880026618e00 1 160ms FSC: OBJ17e6 OP60d33: Write1/EnQ fl=2 + vsq - ffff880025a2a4b8 1 132ms FSC: OBJ16a2 OP4d583: Write1/EnQ fl=2 + vsq - ffff880023cbe6d8 9 212ms FSC: OBJ17eb: LOOK + vsq - ffff880024d37590 9 212ms FSC: OBJ17ec: LOOK + vsq - ffff880027746cb0 9 212ms FSC: OBJ17ed: LOOK + vsq - ffff880024d37ae8 9 212ms FSC: OBJ17ee: LOOK + vsq - ffff880024d37cb0 9 212ms FSC: OBJ17ef: LOOK + vsq - ffff880025036550 9 212ms FSC: OBJ17f0: LOOK + vsq - ffff8800250368e0 9 212ms FSC: OBJ17f1: LOOK + vsq - ffff880025036aa8 9 212ms FSC: OBJ17f2: LOOK + +In the 'THR' column, executing items show the thread they're occupying and +queued threads indicate which queue they're on. 'PID' shows the process ID of +a slow-work thread that's executing something. 'FL' shows the work item flags. +'MARK' indicates how long since an item was queued or began executing. Lastly, +the 'DESC' column permits the owner of an item to give some information. + diff --git a/MAINTAINERS b/MAINTAINERS index 5531e6fd10dd..1186b1978b2e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -512,10 +512,32 @@ W: http://www.arm.linux.org.uk/ S: Maintained F: arch/arm/ +ARM PRIMECELL AACI PL041 DRIVER +M: Russell King <linux@arm.linux.org.uk> +S: Maintained +F: sound/arm/aaci.* + +ARM PRIMECELL CLCD PL110 DRIVER +M: Russell King <linux@arm.linux.org.uk> +S: Maintained +F: drivers/video/amba-clcd.* + +ARM PRIMECELL KMI PL050 DRIVER +M: Russell King <linux@arm.linux.org.uk> +S: Maintained +F: drivers/input/serio/ambakmi.* +F: include/linux/amba/kmi.h + ARM PRIMECELL MMCI PL180/1 DRIVER S: Orphan F: drivers/mmc/host/mmci.* +ARM PRIMECELL BUS SUPPORT +M: Russell King <linux@arm.linux.org.uk> +S: Maintained +F: drivers/amba/ +F: include/linux/amba/bus.h + ARM/ADI ROADRUNNER MACHINE SUPPORT M: Lennert Buytenhek <kernel@wantstofly.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -1027,7 +1049,7 @@ F: drivers/serial/atmel_serial.c ATMEL LCDFB DRIVER M: Nicolas Ferre <nicolas.ferre@atmel.com> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/atmel_lcdfb.c F: include/video/atmel_lcdc.h @@ -2112,7 +2134,7 @@ F: drivers/net/wan/dlci.c F: drivers/net/wan/sdla.c FRAMEBUFFER LAYER -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org W: http://linux-fbdev.sourceforge.net/ S: Orphan F: Documentation/fb/ @@ -2135,7 +2157,7 @@ F: drivers/i2c/busses/i2c-cpm.c FREESCALE IMX / MXC FRAMEBUFFER DRIVER M: Sascha Hauer <kernel@pengutronix.de> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/plat-mxc/include/mach/imxfb.h @@ -2311,6 +2333,13 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-2.6.git S: Maintained F: drivers/media/video/gspca/finepix.c +GSPCA GL860 SUBDRIVER +M: Olivier Lorin <o.lorin@laposte.net> +L: linux-media@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-2.6.git +S: Maintained +F: drivers/media/video/gspca/gl860/ + GSPCA M5602 SUBDRIVER M: Erik Andren <erik.andren@gmail.com> L: linux-media@vger.kernel.org @@ -2532,8 +2561,7 @@ S: Maintained F: Documentation/i2c/ F: drivers/i2c/ F: include/linux/i2c.h -F: include/linux/i2c-dev.h -F: include/linux/i2c-id.h +F: include/linux/i2c-*.h I2C-TINY-USB DRIVER M: Till Harbaum <till@harbaum.org> @@ -2634,7 +2662,7 @@ S: Supported F: security/integrity/ima/ IMS TWINTURBO FRAMEBUFFER DRIVER -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Orphan F: drivers/video/imsttfb.c @@ -2669,14 +2697,14 @@ F: drivers/input/ INTEL FRAMEBUFFER DRIVER (excluding 810 and 815) M: Sylvain Meyer <sylvain.meyer@worldonline.fr> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: Documentation/fb/intelfb.txt F: drivers/video/intelfb/ INTEL 810/815 FRAMEBUFFER DRIVER M: Antonino Daplas <adaplas@gmail.com> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/i810/ @@ -3399,7 +3427,7 @@ S: Supported MATROX FRAMEBUFFER DRIVER M: Petr Vandrovec <vandrove@vc.cvut.cz> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/matrox/matroxfb_* F: include/linux/matroxfb.h @@ -3786,7 +3814,7 @@ F: fs/ntfs/ NVIDIA (rivafb and nvidiafb) FRAMEBUFFER DRIVER M: Antonino Daplas <adaplas@gmail.com> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/riva/ F: drivers/video/nvidia/ @@ -3821,7 +3849,7 @@ F: sound/soc/omap/ OMAP FRAMEBUFFER SUPPORT M: Imre Deak <imre.deak@nokia.com> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org L: linux-omap@vger.kernel.org S: Maintained F: drivers/video/omap/ @@ -4327,14 +4355,14 @@ F: include/linux/qnxtypes.h RADEON FRAMEBUFFER DISPLAY DRIVER M: Benjamin Herrenschmidt <benh@kernel.crashing.org> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/aty/radeon* F: include/linux/radeonfb.h RAGE128 FRAMEBUFFER DISPLAY DRIVER M: Paul Mackerras <paulus@samba.org> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/aty/aty128fb.c @@ -4473,7 +4501,7 @@ F: drivers/net/wireless/rtl818x/rtl8187* S3 SAVAGE FRAMEBUFFER DRIVER M: Antonino Daplas <adaplas@gmail.com> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/savage/ @@ -5636,7 +5664,7 @@ S: Maintained UVESAFB DRIVER M: Michal Januszewski <spock@gentoo.org> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org W: http://dev.gentoo.org/~spock/projects/uvesafb/ S: Maintained F: Documentation/fb/uvesafb.txt @@ -5669,7 +5697,7 @@ F: drivers/mmc/host/via-sdmmc.c VIA UNICHROME(PRO)/CHROME9 FRAMEBUFFER DRIVER M: Joseph Chan <JosephChan@via.com.tw> M: Scott Fang <ScottFang@viatech.com.cn> -L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers) +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/via/ @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 32 -EXTRAVERSION = -rc7 +EXTRAVERSION = -rc8 NAME = Man-Eating Seals of Antiquity # *DOCUMENTATION* diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h index 815680b585ed..b3e888638bb7 100644 --- a/arch/alpha/include/asm/thread_info.h +++ b/arch/alpha/include/asm/thread_info.h @@ -61,21 +61,24 @@ register struct thread_info *__current_thread_info __asm__("$8"); /* * Thread information flags: * - these are process state flags and used from assembly - * - pending work-to-be-done flags come first to fit in and immediate operand. + * - pending work-to-be-done flags come first and must be assigned to be + * within bits 0 to 7 to fit in and immediate operand. + * - ALPHA_UAC_SHIFT below must be kept consistent with the unaligned + * control flags. * * TIF_SYSCALL_TRACE is known to be 0 via blbs. */ #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ -#define TIF_SIGPENDING 1 /* signal pending */ -#define TIF_NEED_RESCHED 2 /* rescheduling necessary */ -#define TIF_POLLING_NRFLAG 3 /* poll_idle is polling NEED_RESCHED */ -#define TIF_DIE_IF_KERNEL 4 /* dik recursion lock */ -#define TIF_UAC_NOPRINT 5 /* see sysinfo.h */ -#define TIF_UAC_NOFIX 6 -#define TIF_UAC_SIGBUS 7 -#define TIF_MEMDIE 8 -#define TIF_RESTORE_SIGMASK 9 /* restore signal mask in do_signal */ -#define TIF_NOTIFY_RESUME 10 /* callback before returning to user */ +#define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ +#define TIF_SIGPENDING 2 /* signal pending */ +#define TIF_NEED_RESCHED 3 /* rescheduling necessary */ +#define TIF_POLLING_NRFLAG 8 /* poll_idle is polling NEED_RESCHED */ +#define TIF_DIE_IF_KERNEL 9 /* dik recursion lock */ +#define TIF_UAC_NOPRINT 10 /* see sysinfo.h */ +#define TIF_UAC_NOFIX 11 +#define TIF_UAC_SIGBUS 12 +#define TIF_MEMDIE 13 +#define TIF_RESTORE_SIGMASK 14 /* restore signal mask in do_signal */ #define TIF_FREEZE 16 /* is freezing for suspend */ #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) @@ -94,7 +97,7 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define _TIF_ALLWORK_MASK (_TIF_WORK_MASK \ | _TIF_SYSCALL_TRACE) -#define ALPHA_UAC_SHIFT 6 +#define ALPHA_UAC_SHIFT 10 #define ALPHA_UAC_MASK (1 << TIF_UAC_NOPRINT | 1 << TIF_UAC_NOFIX | \ 1 << TIF_UAC_SIGBUS) diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c index 8e059e58b0ac..53dd2f1a53aa 100644 --- a/arch/alpha/kernel/core_marvel.c +++ b/arch/alpha/kernel/core_marvel.c @@ -1103,6 +1103,8 @@ marvel_agp_info(void) * Allocate the info structure. */ agp = kmalloc(sizeof(*agp), GFP_KERNEL); + if (!agp) + return NULL; /* * Fill it in. diff --git a/arch/alpha/kernel/core_titan.c b/arch/alpha/kernel/core_titan.c index 76686497b1e2..219bf271c0ba 100644 --- a/arch/alpha/kernel/core_titan.c +++ b/arch/alpha/kernel/core_titan.c @@ -757,6 +757,8 @@ titan_agp_info(void) * Allocate the info structure. */ agp = kmalloc(sizeof(*agp), GFP_KERNEL); + if (!agp) + return NULL; /* * Fill it in. diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c index cc7834661427..c0de072b8305 100644 --- a/arch/alpha/kernel/irq.c +++ b/arch/alpha/kernel/irq.c @@ -92,7 +92,7 @@ show_interrupts(struct seq_file *p, void *v) for_each_online_cpu(j) seq_printf(p, "%10u ", kstat_irqs_cpu(irq, j)); #endif - seq_printf(p, " %14s", irq_desc[irq].chip->typename); + seq_printf(p, " %14s", irq_desc[irq].chip->name); seq_printf(p, " %c%s", (action->flags & IRQF_DISABLED)?'+':' ', action->name); diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c index 38c805dfc544..cfde865b78e0 100644 --- a/arch/alpha/kernel/irq_alpha.c +++ b/arch/alpha/kernel/irq_alpha.c @@ -228,7 +228,7 @@ struct irqaction timer_irqaction = { }; static struct irq_chip rtc_irq_type = { - .typename = "RTC", + .name = "RTC", .startup = rtc_startup, .shutdown = rtc_enable_disable, .enable = rtc_enable_disable, diff --git a/arch/alpha/kernel/irq_i8259.c b/arch/alpha/kernel/irq_i8259.c index 50bfec9b588f..83a9ac280890 100644 --- a/arch/alpha/kernel/irq_i8259.c +++ b/arch/alpha/kernel/irq_i8259.c @@ -84,7 +84,7 @@ i8259a_end_irq(unsigned int irq) } struct irq_chip i8259a_irq_type = { - .typename = "XT-PIC", + .name = "XT-PIC", .startup = i8259a_startup_irq, .shutdown = i8259a_disable_irq, .enable = i8259a_enable_irq, diff --git a/arch/alpha/kernel/irq_pyxis.c b/arch/alpha/kernel/irq_pyxis.c index 69199a76ec4a..989ce46a0cf3 100644 --- a/arch/alpha/kernel/irq_pyxis.c +++ b/arch/alpha/kernel/irq_pyxis.c @@ -71,7 +71,7 @@ pyxis_mask_and_ack_irq(unsigned int irq) } static struct irq_chip pyxis_irq_type = { - .typename = "PYXIS", + .name = "PYXIS", .startup = pyxis_startup_irq, .shutdown = pyxis_disable_irq, .enable = pyxis_enable_irq, diff --git a/arch/alpha/kernel/irq_srm.c b/arch/alpha/kernel/irq_srm.c index 85229369a1f8..d63e93e1e8bf 100644 --- a/arch/alpha/kernel/irq_srm.c +++ b/arch/alpha/kernel/irq_srm.c @@ -49,7 +49,7 @@ srm_end_irq(unsigned int irq) /* Handle interrupts from the SRM, assuming no additional weirdness. */ static struct irq_chip srm_irq_type = { - .typename = "SRM", + .name = "SRM", .startup = srm_startup_irq, .shutdown = srm_disable_irq, .enable = srm_enable_irq, diff --git a/arch/alpha/kernel/sys_alcor.c b/arch/alpha/kernel/sys_alcor.c index 382035ef7394..20a30b8b9655 100644 --- a/arch/alpha/kernel/sys_alcor.c +++ b/arch/alpha/kernel/sys_alcor.c @@ -90,7 +90,7 @@ alcor_end_irq(unsigned int irq) } static struct irq_chip alcor_irq_type = { - .typename = "ALCOR", + .name = "ALCOR", .startup = alcor_startup_irq, .shutdown = alcor_disable_irq, .enable = alcor_enable_irq, diff --git a/arch/alpha/kernel/sys_cabriolet.c b/arch/alpha/kernel/sys_cabriolet.c index ed349436732b..affd0f3f25df 100644 --- a/arch/alpha/kernel/sys_cabriolet.c +++ b/arch/alpha/kernel/sys_cabriolet.c @@ -72,7 +72,7 @@ cabriolet_end_irq(unsigned int irq) } static struct irq_chip cabriolet_irq_type = { - .typename = "CABRIOLET", + .name = "CABRIOLET", .startup = cabriolet_startup_irq, .shutdown = cabriolet_disable_irq, .enable = cabriolet_enable_irq, diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c index 46e70ece5176..d64e1e497e76 100644 --- a/arch/alpha/kernel/sys_dp264.c +++ b/arch/alpha/kernel/sys_dp264.c @@ -199,7 +199,7 @@ clipper_set_affinity(unsigned int irq, const struct cpumask *affinity) } static struct irq_chip dp264_irq_type = { - .typename = "DP264", + .name = "DP264", .startup = dp264_startup_irq, .shutdown = dp264_disable_irq, .enable = dp264_enable_irq, @@ -210,7 +210,7 @@ static struct irq_chip dp264_irq_type = { }; static struct irq_chip clipper_irq_type = { - .typename = "CLIPPER", + .name = "CLIPPER", .startup = clipper_startup_irq, .shutdown = clipper_disable_irq, .enable = clipper_enable_irq, diff --git a/arch/alpha/kernel/sys_eb64p.c b/arch/alpha/kernel/sys_eb64p.c index 660c23ef661f..df2090ce5e7f 100644 --- a/arch/alpha/kernel/sys_eb64p.c +++ b/arch/alpha/kernel/sys_eb64p.c @@ -70,7 +70,7 @@ eb64p_end_irq(unsigned int irq) } static struct irq_chip eb64p_irq_type = { - .typename = "EB64P", + .name = "EB64P", .startup = eb64p_startup_irq, .shutdown = eb64p_disable_irq, .enable = eb64p_enable_irq, diff --git a/arch/alpha/kernel/sys_eiger.c b/arch/alpha/kernel/sys_eiger.c index b99ea488d844..3ca1dbcf4044 100644 --- a/arch/alpha/kernel/sys_eiger.c +++ b/arch/alpha/kernel/sys_eiger.c @@ -81,7 +81,7 @@ eiger_end_irq(unsigned int irq) } static struct irq_chip eiger_irq_type = { - .typename = "EIGER", + .name = "EIGER", .startup = eiger_startup_irq, .shutdown = eiger_disable_irq, .enable = eiger_enable_irq, diff --git a/arch/alpha/kernel/sys_jensen.c b/arch/alpha/kernel/sys_jensen.c index ef0b83a070ac..7a7ae36fff91 100644 --- a/arch/alpha/kernel/sys_jensen.c +++ b/arch/alpha/kernel/sys_jensen.c @@ -119,7 +119,7 @@ jensen_local_end(unsigned int irq) } static struct irq_chip jensen_local_irq_type = { - .typename = "LOCAL", + .name = "LOCAL", .startup = jensen_local_startup, .shutdown = jensen_local_shutdown, .enable = jensen_local_enable, diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c index bbfc4f20ca72..0bb3b5c4f693 100644 --- a/arch/alpha/kernel/sys_marvel.c +++ b/arch/alpha/kernel/sys_marvel.c @@ -170,7 +170,7 @@ marvel_irq_noop_return(unsigned int irq) } static struct irq_chip marvel_legacy_irq_type = { - .typename = "LEGACY", + .name = "LEGACY", .startup = marvel_irq_noop_return, .shutdown = marvel_irq_noop, .enable = marvel_irq_noop, @@ -180,7 +180,7 @@ static struct irq_chip marvel_legacy_irq_type = { }; static struct irq_chip io7_lsi_irq_type = { - .typename = "LSI", + .name = "LSI", .startup = io7_startup_irq, .shutdown = io7_disable_irq, .enable = io7_enable_irq, @@ -190,7 +190,7 @@ static struct irq_chip io7_lsi_irq_type = { }; static struct irq_chip io7_msi_irq_type = { - .typename = "MSI", + .name = "MSI", .startup = io7_startup_irq, .shutdown = io7_disable_irq, .enable = io7_enable_irq, diff --git a/arch/alpha/kernel/sys_mikasa.c b/arch/alpha/kernel/sys_mikasa.c index 4e366641a08e..ee8865169811 100644 --- a/arch/alpha/kernel/sys_mikasa.c +++ b/arch/alpha/kernel/sys_mikasa.c @@ -69,7 +69,7 @@ mikasa_end_irq(unsigned int irq) } static struct irq_chip mikasa_irq_type = { - .typename = "MIKASA", + .name = "MIKASA", .startup = mikasa_startup_irq, .shutdown = mikasa_disable_irq, .enable = mikasa_enable_irq, diff --git a/arch/alpha/kernel/sys_noritake.c b/arch/alpha/kernel/sys_noritake.c index 35753a173bac..86503fe73a88 100644 --- a/arch/alpha/kernel/sys_noritake.c +++ b/arch/alpha/kernel/sys_noritake.c @@ -74,7 +74,7 @@ noritake_end_irq(unsigned int irq) } static struct irq_chip noritake_irq_type = { - .typename = "NORITAKE", + .name = "NORITAKE", .startup = noritake_startup_irq, .shutdown = noritake_disable_irq, .enable = noritake_enable_irq, diff --git a/arch/alpha/kernel/sys_rawhide.c b/arch/alpha/kernel/sys_rawhide.c index f3aec7e085c8..26c322bf89ee 100644 --- a/arch/alpha/kernel/sys_rawhide.c +++ b/arch/alpha/kernel/sys_rawhide.c @@ -136,7 +136,7 @@ rawhide_end_irq(unsigned int irq) } static struct irq_chip rawhide_irq_type = { - .typename = "RAWHIDE", + .name = "RAWHIDE", .startup = rawhide_startup_irq, .shutdown = rawhide_disable_irq, .enable = rawhide_enable_irq, diff --git a/arch/alpha/kernel/sys_ruffian.c b/arch/alpha/kernel/sys_ruffian.c index d9f9cfeb9931..8de1046fe91e 100644 --- a/arch/alpha/kernel/sys_ruffian.c +++ b/arch/alpha/kernel/sys_ruffian.c @@ -66,7 +66,7 @@ ruffian_init_irq(void) common_init_isa_dma(); } -#define RUFFIAN_LATCH ((PIT_TICK_RATE + HZ / 2) / HZ) +#define RUFFIAN_LATCH DIV_ROUND_CLOSEST(PIT_TICK_RATE, HZ) static void __init ruffian_init_rtc(void) diff --git a/arch/alpha/kernel/sys_rx164.c b/arch/alpha/kernel/sys_rx164.c index fc9246373452..be161129eab9 100644 --- a/arch/alpha/kernel/sys_rx164.c +++ b/arch/alpha/kernel/sys_rx164.c @@ -73,7 +73,7 @@ rx164_end_irq(unsigned int irq) } static struct irq_chip rx164_irq_type = { - .typename = "RX164", + .name = "RX164", .startup = rx164_startup_irq, .shutdown = rx164_disable_irq, .enable = rx164_enable_irq, diff --git a/arch/alpha/kernel/sys_sable.c b/arch/alpha/kernel/sys_sable.c index 426eb6906d01..b2abe27a23cf 100644 --- a/arch/alpha/kernel/sys_sable.c +++ b/arch/alpha/kernel/sys_sable.c @@ -502,7 +502,7 @@ sable_lynx_mask_and_ack_irq(unsigned int irq) } static struct irq_chip sable_lynx_irq_type = { - .typename = "SABLE/LYNX", + .name = "SABLE/LYNX", .startup = sable_lynx_startup_irq, .shutdown = sable_lynx_disable_irq, .enable = sable_lynx_enable_irq, diff --git a/arch/alpha/kernel/sys_takara.c b/arch/alpha/kernel/sys_takara.c index 830318c21661..230464885b5c 100644 --- a/arch/alpha/kernel/sys_takara.c +++ b/arch/alpha/kernel/sys_takara.c @@ -75,7 +75,7 @@ takara_end_irq(unsigned int irq) } static struct irq_chip takara_irq_type = { - .typename = "TAKARA", + .name = "TAKARA", .startup = takara_startup_irq, .shutdown = takara_disable_irq, .enable = takara_enable_irq, diff --git a/arch/alpha/kernel/sys_titan.c b/arch/alpha/kernel/sys_titan.c index 88978fc60f83..288053342c83 100644 --- a/arch/alpha/kernel/sys_titan.c +++ b/arch/alpha/kernel/sys_titan.c @@ -195,7 +195,7 @@ init_titan_irqs(struct irq_chip * ops, int imin, int imax) } static struct irq_chip titan_irq_type = { - .typename = "TITAN", + .name = "TITAN", .startup = titan_startup_irq, .shutdown = titan_disable_irq, .enable = titan_enable_irq, diff --git a/arch/alpha/kernel/sys_wildfire.c b/arch/alpha/kernel/sys_wildfire.c index e91b4c3838a8..62fd972e18ef 100644 --- a/arch/alpha/kernel/sys_wildfire.c +++ b/arch/alpha/kernel/sys_wildfire.c @@ -158,7 +158,7 @@ wildfire_end_irq(unsigned int irq) } static struct irq_chip wildfire_irq_type = { - .typename = "WILDFIRE", + .name = "WILDFIRE", .startup = wildfire_startup_irq, .shutdown = wildfire_disable_irq, .enable = wildfire_enable_irq, diff --git a/arch/arm/include/asm/kmap_types.h b/arch/arm/include/asm/kmap_types.h index d16ec97ec9a9..c019949a5189 100644 --- a/arch/arm/include/asm/kmap_types.h +++ b/arch/arm/include/asm/kmap_types.h @@ -22,4 +22,10 @@ enum km_type { KM_TYPE_NR }; +#ifdef CONFIG_DEBUG_HIGHMEM +#define KM_NMI (-1) +#define KM_NMI_PTE (-1) +#define KM_IRQ_PTE (-1) +#endif + #endif diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 2a573d4fea24..e7714f367eb8 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -662,8 +662,12 @@ static void do_signal(struct pt_regs *regs, int syscall) regs->ARM_sp -= 4; usp = (u32 __user *)regs->ARM_sp; - put_user(regs->ARM_pc, usp); - regs->ARM_pc = KERN_RESTART_CODE; + if (put_user(regs->ARM_pc, usp) == 0) { + regs->ARM_pc = KERN_RESTART_CODE; + } else { + regs->ARM_sp += 4; + force_sigsegv(0, current); + } #endif } } diff --git a/arch/arm/mach-pxa/cpufreq-pxa2xx.c b/arch/arm/mach-pxa/cpufreq-pxa2xx.c index 983cc8c20081..9e4d9816726a 100644 --- a/arch/arm/mach-pxa/cpufreq-pxa2xx.c +++ b/arch/arm/mach-pxa/cpufreq-pxa2xx.c @@ -447,6 +447,7 @@ static __init int pxa_cpufreq_init(struct cpufreq_policy *policy) pxa27x_freq_table[i].frequency = freq; pxa27x_freq_table[i].index = i; } + pxa27x_freq_table[i].index = i; pxa27x_freq_table[i].frequency = CPUFREQ_TABLE_END; /* diff --git a/arch/arm/mach-pxa/cpufreq-pxa3xx.c b/arch/arm/mach-pxa/cpufreq-pxa3xx.c index 67f34a8d8e60..149cdd9aee4d 100644 --- a/arch/arm/mach-pxa/cpufreq-pxa3xx.c +++ b/arch/arm/mach-pxa/cpufreq-pxa3xx.c @@ -102,7 +102,7 @@ static int setup_freqs_table(struct cpufreq_policy *policy, table[i].index = i; table[i].frequency = freqs[i].cpufreq_mhz * 1000; } - table[num].frequency = i; + table[num].index = i; table[num].frequency = CPUFREQ_TABLE_END; pxa3xx_freqs = freqs; diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 3da45d051743..d98023f55503 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -802,10 +802,12 @@ static void __init spitz_init(void) { spitz_ficp_platform_data.gpio_pwdown = SPITZ_GPIO_IR_ON; +#ifdef CONFIG_MACH_BORZOI if (machine_is_borzoi()) { sharpsl_nand_platform_data.badblock_pattern = &sharpsl_akita_bbt; sharpsl_nand_platform_data.ecc_layout = &akita_oobinfo; } +#endif platform_scoop_config = &spitz_pcmcia_config; diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types index 94be7bb6cb9a..07b976da6174 100644 --- a/arch/arm/tools/mach-types +++ b/arch/arm/tools/mach-types @@ -12,7 +12,7 @@ # # http://www.arm.linux.org.uk/developer/machines/?action=new # -# Last update: Fri Sep 18 21:42:00 2009 +# Last update: Wed Nov 25 22:14:58 2009 # # machine_is_xxx CONFIG_xxxx MACH_TYPE_xxx number # @@ -928,7 +928,7 @@ palmt5 MACH_PALMT5 PALMT5 917 palmtc MACH_PALMTC PALMTC 918 omap_apollon MACH_OMAP_APOLLON OMAP_APOLLON 919 mxc30030evb MACH_MXC30030EVB MXC30030EVB 920 -rea_2d MACH_REA_2D REA_2D 921 +rea_cpu2 MACH_REA_2D REA_2D 921 eti3e524 MACH_TI3E524 TI3E524 922 ateb9200 MACH_ATEB9200 ATEB9200 923 auckland MACH_AUCKLAND AUCKLAND 924 @@ -2421,3 +2421,118 @@ liberty MACH_LIBERTY LIBERTY 2434 mh355 MACH_MH355 MH355 2435 pc7802 MACH_PC7802 PC7802 2436 gnet_sgc MACH_GNET_SGC GNET_SGC 2437 +einstein15 MACH_EINSTEIN15 EINSTEIN15 2438 +cmpd MACH_CMPD CMPD 2439 +davinci_hase1 MACH_DAVINCI_HASE1 DAVINCI_HASE1 2440 +lgeincitephone MACH_LGEINCITEPHONE LGEINCITEPHONE 2441 +ea313x MACH_EA313X EA313X 2442 +fwbd_39064 MACH_FWBD_39064 FWBD_39064 2443 +fwbd_390128 MACH_FWBD_390128 FWBD_390128 2444 +pelco_moe MACH_PELCO_MOE PELCO_MOE 2445 +minimix27 MACH_MINIMIX27 MINIMIX27 2446 +omap3_thunder MACH_OMAP3_THUNDER OMAP3_THUNDER 2447 +passionc MACH_PASSIONC PASSIONC 2448 +mx27amata MACH_MX27AMATA MX27AMATA 2449 +bgat1 MACH_BGAT1 BGAT1 2450 +buzz MACH_BUZZ BUZZ 2451 +mb9g20 MACH_MB9G20 MB9G20 2452 +yushan MACH_YUSHAN YUSHAN 2453 +lizard MACH_LIZARD LIZARD 2454 +omap3polycom MACH_OMAP3POLYCOM OMAP3POLYCOM 2455 +smdkv210 MACH_SMDKV210 SMDKV210 2456 +bravo MACH_BRAVO BRAVO 2457 +siogentoo1 MACH_SIOGENTOO1 SIOGENTOO1 2458 +siogentoo2 MACH_SIOGENTOO2 SIOGENTOO2 2459 +sm3k MACH_SM3K SM3K 2460 +acer_tempo_f900 MACH_ACER_TEMPO_F900 ACER_TEMPO_F900 2461 +sst61vc010_dev MACH_SST61VC010_DEV SST61VC010_DEV 2462 +glittertind MACH_GLITTERTIND GLITTERTIND 2463 +omap_zoom3 MACH_OMAP_ZOOM3 OMAP_ZOOM3 2464 +omap_3630sdp MACH_OMAP_3630SDP OMAP_3630SDP 2465 +cybook2440 MACH_CYBOOK2440 CYBOOK2440 2466 +torino_s MACH_TORINO_S TORINO_S 2467 +havana MACH_HAVANA HAVANA 2468 +beaumont_11 MACH_BEAUMONT_11 BEAUMONT_11 2469 +vanguard MACH_VANGUARD VANGUARD 2470 +s5pc110_draco MACH_S5PC110_DRACO S5PC110_DRACO 2471 +cartesio_two MACH_CARTESIO_TWO CARTESIO_TWO 2472 +aster MACH_ASTER ASTER 2473 +voguesv210 MACH_VOGUESV210 VOGUESV210 2474 +acm500x MACH_ACM500X ACM500X 2475 +km9260 MACH_KM9260 KM9260 2476 +nideflexg1 MACH_NIDEFLEXG1 NIDEFLEXG1 2477 +ctera_plug_io MACH_CTERA_PLUG_IO CTERA_PLUG_IO 2478 +smartq7 MACH_SMARTQ7 SMARTQ7 2479 +at91sam9g10ek2 MACH_AT91SAM9G10EK2 AT91SAM9G10EK2 2480 +asusp527 MACH_ASUSP527 ASUSP527 2481 +at91sam9g20mpm2 MACH_AT91SAM9G20MPM2 AT91SAM9G20MPM2 2482 +topasa900 MACH_TOPASA900 TOPASA900 2483 +electrum_100 MACH_ELECTRUM_100 ELECTRUM_100 2484 +mx51grb MACH_MX51GRB MX51GRB 2485 +xea300 MACH_XEA300 XEA300 2486 +htcstartrek MACH_HTCSTARTREK HTCSTARTREK 2487 +lima MACH_LIMA LIMA 2488 +csb740 MACH_CSB740 CSB740 2489 +usb_s8815 MACH_USB_S8815 USB_S8815 2490 +watson_efm_plugin MACH_WATSON_EFM_PLUGIN WATSON_EFM_PLUGIN 2491 +milkyway MACH_MILKYWAY MILKYWAY 2492 +g4evm MACH_G4EVM G4EVM 2493 +picomod6 MACH_PICOMOD6 PICOMOD6 2494 +omapl138_hawkboard MACH_OMAPL138_HAWKBOARD OMAPL138_HAWKBOARD 2495 +ip6000 MACH_IP6000 IP6000 2496 +ip6010 MACH_IP6010 IP6010 2497 +utm400 MACH_UTM400 UTM400 2498 +omap3_zybex MACH_OMAP3_ZYBEX OMAP3_ZYBEX 2499 +wireless_space MACH_WIRELESS_SPACE WIRELESS_SPACE 2500 +sx560 MACH_SX560 SX560 2501 +ts41x MACH_TS41X TS41X 2502 +elphel10373 MACH_ELPHEL10373 ELPHEL10373 2503 +rhobot MACH_RHOBOT RHOBOT 2504 +mx51_refresh MACH_MX51_REFRESH MX51_REFRESH 2505 +ls9260 MACH_LS9260 LS9260 2506 +shank MACH_SHANK SHANK 2507 +qsd8x50_st1 MACH_QSD8X50_ST1 QSD8X50_ST1 2508 +at91sam9m10ekes MACH_AT91SAM9M10EKES AT91SAM9M10EKES 2509 +hiram MACH_HIRAM HIRAM 2510 +phy3250 MACH_PHY3250 PHY3250 2511 +ea3250 MACH_EA3250 EA3250 2512 +fdi3250 MACH_FDI3250 FDI3250 2513 +whitestone MACH_WHITESTONE WHITESTONE 2514 +at91sam9263nit MACH_AT91SAM9263NIT AT91SAM9263NIT 2515 +ccmx51 MACH_CCMX51 CCMX51 2516 +ccmx51js MACH_CCMX51JS CCMX51JS 2517 +ccwmx51 MACH_CCWMX51 CCWMX51 2518 +ccwmx51js MACH_CCWMX51JS CCWMX51JS 2519 +mini6410 MACH_MINI6410 MINI6410 2520 +tiny6410 MACH_TINY6410 TINY6410 2521 +nano6410 MACH_NANO6410 NANO6410 2522 +at572d940hfnldb MACH_AT572D940HFNLDB AT572D940HFNLDB 2523 +htcleo MACH_HTCLEO HTCLEO 2524 +avp13 MACH_AVP13 AVP13 2525 +xxsvideod MACH_XXSVIDEOD XXSVIDEOD 2526 +vpnext MACH_VPNEXT VPNEXT 2527 +swarco_itc3 MACH_SWARCO_ITC3 SWARCO_ITC3 2528 +tx51 MACH_TX51 TX51 2529 +dolby_cat1021 MACH_DOLBY_CAT1021 DOLBY_CAT1021 2530 +mx28evk MACH_MX28EVK MX28EVK 2531 +phoenix260 MACH_PHOENIX260 PHOENIX260 2532 +uvaca_stork MACH_UVACA_STORK UVACA_STORK 2533 +smartq5 MACH_SMARTQ5 SMARTQ5 2534 +all3078 MACH_ALL3078 ALL3078 2535 +ctera_2bay_ds MACH_CTERA_2BAY_DS CTERA_2BAY_DS 2536 +siogentoo3 MACH_SIOGENTOO3 SIOGENTOO3 2537 +epb5000 MACH_EPB5000 EPB5000 2538 +hy9263 MACH_HY9263 HY9263 2539 +acer_tempo_m900 MACH_ACER_TEMPO_M900 ACER_TEMPO_M900 2540 +acer_tempo_dx650 MACH_ACER_TEMPO_DX900 ACER_TEMPO_DX900 2541 +acer_tempo_x960 MACH_ACER_TEMPO_X960 ACER_TEMPO_X960 2542 +acer_eten_v900 MACH_ACER_ETEN_V900 ACER_ETEN_V900 2543 +acer_eten_x900 MACH_ACER_ETEN_X900 ACER_ETEN_X900 2544 +bonnell MACH_BONNELL BONNELL 2545 +oht_mx27 MACH_OHT_MX27 OHT_MX27 2546 +htcquartz MACH_HTCQUARTZ HTCQUARTZ 2547 +davinci_dm6467tevm MACH_DAVINCI_DM6467TEVM DAVINCI_DM6467TEVM 2548 +c3ax03 MACH_C3AX03 C3AX03 2549 +mxt_td60 MACH_MXT_TD60 MXT_TD60 2550 +esyx MACH_ESYX ESYX 2551 +bulldog MACH_BULLDOG BULLDOG 2553 diff --git a/arch/blackfin/kernel/bfin_dma_5xx.c b/arch/blackfin/kernel/bfin_dma_5xx.c index 1f170216d2f9..3946aff4f414 100644 --- a/arch/blackfin/kernel/bfin_dma_5xx.c +++ b/arch/blackfin/kernel/bfin_dma_5xx.c @@ -225,8 +225,13 @@ int blackfin_dma_suspend(void) void blackfin_dma_resume(void) { int i; - for (i = 0; i < MAX_DMA_SUSPEND_CHANNELS; ++i) - dma_ch[i].regs->peripheral_map = dma_ch[i].saved_peripheral_map; + + for (i = 0; i < MAX_DMA_CHANNELS; ++i) { + dma_ch[i].regs->cfg = 0; + + if (i < MAX_DMA_SUSPEND_CHANNELS) + dma_ch[i].regs->peripheral_map = dma_ch[i].saved_peripheral_map; + } } #endif diff --git a/arch/blackfin/kernel/cplb-mpu/cplbinit.c b/arch/blackfin/kernel/cplb-mpu/cplbinit.c index f7b9cdce8239..b52c1f8c4bc0 100644 --- a/arch/blackfin/kernel/cplb-mpu/cplbinit.c +++ b/arch/blackfin/kernel/cplb-mpu/cplbinit.c @@ -38,7 +38,7 @@ void __init generate_cplb_tables_cpu(unsigned int cpu) #ifdef CONFIG_BFIN_EXTMEM_DCACHEABLE d_cache = CPLB_L1_CHBL; -#ifdef CONFIG_BFIN_EXTMEM_WRITETROUGH +#ifdef CONFIG_BFIN_EXTMEM_WRITETHROUGH d_cache |= CPLB_L1_AOW | CPLB_WT; #endif #endif diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c index 430ae39456e8..5cc7e2e9e415 100644 --- a/arch/blackfin/kernel/process.c +++ b/arch/blackfin/kernel/process.c @@ -151,7 +151,7 @@ void start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_ regs->pc = new_ip; if (current->mm) regs->p5 = current->mm->start_data; -#ifdef CONFIG_SMP +#ifndef CONFIG_SMP task_thread_info(current)->l1_task_info.stack_start = (void *)current->mm->context.stack_start; task_thread_info(current)->l1_task_info.lowest_sp = (void *)new_sp; diff --git a/arch/blackfin/kernel/ptrace.c b/arch/blackfin/kernel/ptrace.c index 0982b5d5af10..56b0ba12175f 100644 --- a/arch/blackfin/kernel/ptrace.c +++ b/arch/blackfin/kernel/ptrace.c @@ -315,7 +315,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) case BFIN_MEM_ACCESS_CORE: case BFIN_MEM_ACCESS_CORE_ONLY: copied = access_process_vm(child, addr, &data, - to_copy, 0); + to_copy, 1); if (copied) break; diff --git a/arch/blackfin/mach-bf518/include/mach/anomaly.h b/arch/blackfin/mach-bf518/include/mach/anomaly.h index e9c65390edd1..2829dd0400f1 100644 --- a/arch/blackfin/mach-bf518/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf518/include/mach/anomaly.h @@ -1,9 +1,13 @@ /* - * File: include/asm-blackfin/mach-bf518/anomaly.h - * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * DO NOT EDIT THIS FILE + * This file is under version control at + * svn://sources.blackfin.uclinux.org/toolchain/trunk/proc-defs/header-frags/ + * and can be replaced with that version at any time + * DO NOT EDIT THIS FILE * - * Copyright (C) 2004-2009 Analog Devices Inc. - * Licensed under the GPL-2 or later. + * Copyright 2004-2009 Analog Devices Inc. + * Licensed under the ADI BSD license. + * https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd */ /* This file should be up to date with: @@ -70,6 +74,10 @@ #define ANOMALY_05000461 (1) /* Synchronization Problem at Startup May Cause SPORT Transmit Channels to Misalign */ #define ANOMALY_05000462 (1) +/* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */ +#define ANOMALY_05000473 (1) +/* TESTSET Instruction Cannot Be Interrupted */ +#define ANOMALY_05000477 (1) /* Anomalies that don't exist on this proc */ #define ANOMALY_05000099 (0) @@ -133,5 +141,7 @@ #define ANOMALY_05000450 (0) #define ANOMALY_05000465 (0) #define ANOMALY_05000467 (0) +#define ANOMALY_05000474 (0) +#define ANOMALY_05000475 (0) #endif diff --git a/arch/blackfin/mach-bf527/include/mach/anomaly.h b/arch/blackfin/mach-bf527/include/mach/anomaly.h index 3f9052687fa8..02040df8ec80 100644 --- a/arch/blackfin/mach-bf527/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf527/include/mach/anomaly.h @@ -1,14 +1,18 @@ /* - * File: include/asm-blackfin/mach-bf527/anomaly.h - * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * DO NOT EDIT THIS FILE + * This file is under version control at + * svn://sources.blackfin.uclinux.org/toolchain/trunk/proc-defs/header-frags/ + * and can be replaced with that version at any time + * DO NOT EDIT THIS FILE * - * Copyright (C) 2004-2009 Analog Devices Inc. - * Licensed under the GPL-2 or later. + * Copyright 2004-2009 Analog Devices Inc. + * Licensed under the ADI BSD license. + * https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd */ /* This file should be up to date with: * - Revision D, 08/14/2009; ADSP-BF526 Blackfin Processor Anomaly List - * - Revision F, 03/03/2009; ADSP-BF527 Blackfin Processor Anomaly List + * - Revision G, 08/25/2009; ADSP-BF527 Blackfin Processor Anomaly List */ #ifndef _MACH_ANOMALY_H_ @@ -200,6 +204,10 @@ #define ANOMALY_05000467 (1) /* PLL Latches Incorrect Settings During Reset */ #define ANOMALY_05000469 (1) +/* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */ +#define ANOMALY_05000473 (1) +/* TESTSET Instruction Cannot Be Interrupted */ +#define ANOMALY_05000477 (1) /* Anomalies that don't exist on this proc */ #define ANOMALY_05000099 (0) @@ -250,5 +258,7 @@ #define ANOMALY_05000412 (0) #define ANOMALY_05000447 (0) #define ANOMALY_05000448 (0) +#define ANOMALY_05000474 (0) +#define ANOMALY_05000475 (0) #endif diff --git a/arch/blackfin/mach-bf533/include/mach/anomaly.h b/arch/blackfin/mach-bf533/include/mach/anomaly.h index cd83db2fb1a1..9b3f7a27714d 100644 --- a/arch/blackfin/mach-bf533/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf533/include/mach/anomaly.h @@ -1,9 +1,13 @@ /* - * File: include/asm-blackfin/mach-bf533/anomaly.h - * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * DO NOT EDIT THIS FILE + * This file is under version control at + * svn://sources.blackfin.uclinux.org/toolchain/trunk/proc-defs/header-frags/ + * and can be replaced with that version at any time + * DO NOT EDIT THIS FILE * - * Copyright (C) 2004-2009 Analog Devices Inc. - * Licensed under the GPL-2 or later. + * Copyright 2004-2009 Analog Devices Inc. + * Licensed under the ADI BSD license. + * https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd */ /* This file should be up to date with: @@ -202,6 +206,10 @@ #define ANOMALY_05000443 (1) /* False Hardware Error when RETI Points to Invalid Memory */ #define ANOMALY_05000461 (1) +/* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */ +#define ANOMALY_05000473 (1) +/* TESTSET Instruction Cannot Be Interrupted */ +#define ANOMALY_05000477 (1) /* These anomalies have been "phased" out of analog.com anomaly sheets and are * here to show running on older silicon just isn't feasible. @@ -349,5 +357,7 @@ #define ANOMALY_05000450 (0) #define ANOMALY_05000465 (0) #define ANOMALY_05000467 (0) +#define ANOMALY_05000474 (0) +#define ANOMALY_05000475 (0) #endif diff --git a/arch/blackfin/mach-bf537/include/mach/anomaly.h b/arch/blackfin/mach-bf537/include/mach/anomaly.h index f091ad2d8ea8..d2c427bc6656 100644 --- a/arch/blackfin/mach-bf537/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf537/include/mach/anomaly.h @@ -1,9 +1,13 @@ /* - * File: include/asm-blackfin/mach-bf537/anomaly.h - * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * DO NOT EDIT THIS FILE + * This file is under version control at + * svn://sources.blackfin.uclinux.org/toolchain/trunk/proc-defs/header-frags/ + * and can be replaced with that version at any time + * DO NOT EDIT THIS FILE * - * Copyright (C) 2004-2009 Analog Devices Inc. - * Licensed under the GPL-2 or later. + * Copyright 2004-2009 Analog Devices Inc. + * Licensed under the ADI BSD license. + * https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd */ /* This file should be up to date with: @@ -156,6 +160,10 @@ #define ANOMALY_05000443 (1) /* False Hardware Error when RETI Points to Invalid Memory */ #define ANOMALY_05000461 (1) +/* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */ +#define ANOMALY_05000473 (1) +/* TESTSET Instruction Cannot Be Interrupted */ +#define ANOMALY_05000477 (1) /* Anomalies that don't exist on this proc */ #define ANOMALY_05000099 (0) @@ -202,5 +210,7 @@ #define ANOMALY_05000450 (0) #define ANOMALY_05000465 (0) #define ANOMALY_05000467 (0) +#define ANOMALY_05000474 (0) +#define ANOMALY_05000475 (0) #endif diff --git a/arch/blackfin/mach-bf538/include/mach/anomaly.h b/arch/blackfin/mach-bf538/include/mach/anomaly.h index 26b76083e14c..d882b7e6f59b 100644 --- a/arch/blackfin/mach-bf538/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf538/include/mach/anomaly.h @@ -1,9 +1,13 @@ /* - * File: include/asm-blackfin/mach-bf538/anomaly.h - * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * DO NOT EDIT THIS FILE + * This file is under version control at + * svn://sources.blackfin.uclinux.org/toolchain/trunk/proc-defs/header-frags/ + * and can be replaced with that version at any time + * DO NOT EDIT THIS FILE * - * Copyright (C) 2004-2009 Analog Devices Inc. - * Licensed under the GPL-2 or later. + * Copyright 2004-2009 Analog Devices Inc. + * Licensed under the ADI BSD license. + * https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd */ /* This file should be up to date with: @@ -128,6 +132,10 @@ #define ANOMALY_05000443 (1) /* False Hardware Error when RETI Points to Invalid Memory */ #define ANOMALY_05000461 (1) +/* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */ +#define ANOMALY_05000473 (1) +/* TESTSET Instruction Cannot Be Interrupted */ +#define ANOMALY_05000477 (1) /* Anomalies that don't exist on this proc */ #define ANOMALY_05000099 (0) @@ -176,5 +184,7 @@ #define ANOMALY_05000450 (0) #define ANOMALY_05000465 (0) #define ANOMALY_05000467 (0) +#define ANOMALY_05000474 (0) +#define ANOMALY_05000475 (0) #endif diff --git a/arch/blackfin/mach-bf548/include/mach/anomaly.h b/arch/blackfin/mach-bf548/include/mach/anomaly.h index 52b116ae522a..7d08c7524498 100644 --- a/arch/blackfin/mach-bf548/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf548/include/mach/anomaly.h @@ -1,9 +1,13 @@ /* - * File: include/asm-blackfin/mach-bf548/anomaly.h - * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * DO NOT EDIT THIS FILE + * This file is under version control at + * svn://sources.blackfin.uclinux.org/toolchain/trunk/proc-defs/header-frags/ + * and can be replaced with that version at any time + * DO NOT EDIT THIS FILE * - * Copyright (C) 2004-2009 Analog Devices Inc. - * Licensed under the GPL-2 or later. + * Copyright 2004-2009 Analog Devices Inc. + * Licensed under the ADI BSD license. + * https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd */ /* This file should be up to date with: @@ -24,6 +28,8 @@ #define ANOMALY_05000119 (1) /* Rx.H Cannot Be Used to Access 16-bit System MMR Registers */ #define ANOMALY_05000122 (1) +/* Data Corruption with Cached External Memory and Non-Cached On-Chip L2 Memory */ +#define ANOMALY_05000220 (1) /* False Hardware Error from an Access in the Shadow of a Conditional Branch */ #define ANOMALY_05000245 (1) /* Sensitivity To Noise with Slow Input Edge Rates on External SPORT TX and RX Clocks */ @@ -200,6 +206,14 @@ #define ANOMALY_05000466 (1) /* Possible RX data corruption when control & data EP FIFOs are accessed via the core */ #define ANOMALY_05000467 (1) +/* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */ +#define ANOMALY_05000473 (1) +/* Access to DDR-SDRAM causes system hang under certain PLL/VR settings */ +#define ANOMALY_05000474 (1) +/* Core Hang With L2/L3 Configured in Writeback Cache Mode */ +#define ANOMALY_05000475 (1) +/* TESTSET Instruction Cannot Be Interrupted */ +#define ANOMALY_05000477 (1) /* Anomalies that don't exist on this proc */ #define ANOMALY_05000099 (0) @@ -215,7 +229,6 @@ #define ANOMALY_05000198 (0) #define ANOMALY_05000202 (0) #define ANOMALY_05000215 (0) -#define ANOMALY_05000220 (0) #define ANOMALY_05000227 (0) #define ANOMALY_05000230 (0) #define ANOMALY_05000231 (0) diff --git a/arch/blackfin/mach-bf561/atomic.S b/arch/blackfin/mach-bf561/atomic.S index 0261a5e751b3..f99f174b129f 100644 --- a/arch/blackfin/mach-bf561/atomic.S +++ b/arch/blackfin/mach-bf561/atomic.S @@ -19,6 +19,16 @@ \reg\().h = _corelock; .endm +.macro safe_testset addr:req, scratch:req +#if ANOMALY_05000477 + cli \scratch; + testset (\addr); + sti \scratch; +#else + testset (\addr); +#endif +.endm + /* * r0 = address of atomic data to flush and invalidate (32bit). * @@ -33,7 +43,7 @@ ENTRY(_get_core_lock) cli r0; coreslot_loadaddr p0; .Lretry_corelock: - testset (p0); + safe_testset p0, r2; if cc jump .Ldone_corelock; SSYNC(r2); jump .Lretry_corelock @@ -56,7 +66,7 @@ ENTRY(_get_core_lock_noflush) cli r0; coreslot_loadaddr p0; .Lretry_corelock_noflush: - testset (p0); + safe_testset p0, r2; if cc jump .Ldone_corelock_noflush; SSYNC(r2); jump .Lretry_corelock_noflush diff --git a/arch/blackfin/mach-bf561/include/mach/anomaly.h b/arch/blackfin/mach-bf561/include/mach/anomaly.h index 70da495c9665..5ddc981e9937 100644 --- a/arch/blackfin/mach-bf561/include/mach/anomaly.h +++ b/arch/blackfin/mach-bf561/include/mach/anomaly.h @@ -1,9 +1,13 @@ /* - * File: include/asm-blackfin/mach-bf561/anomaly.h - * Bugs: Enter bugs at http://blackfin.uclinux.org/ + * DO NOT EDIT THIS FILE + * This file is under version control at + * svn://sources.blackfin.uclinux.org/toolchain/trunk/proc-defs/header-frags/ + * and can be replaced with that version at any time + * DO NOT EDIT THIS FILE * - * Copyright (C) 2004-2009 Analog Devices Inc. - * Licensed under the GPL-2 or later. + * Copyright 2004-2009 Analog Devices Inc. + * Licensed under the ADI BSD license. + * https://docs.blackfin.uclinux.org/doku.php?id=adi_bsd */ /* This file should be up to date with: @@ -213,7 +217,11 @@ /* Disabling Peripherals with DMA Running May Cause DMA System Instability */ #define ANOMALY_05000278 (__SILICON_REVISION__ < 5) /* False Hardware Error Exception when ISR Context Is Not Restored */ -#define ANOMALY_05000281 (__SILICON_REVISION__ < 5) +/* Temporarily walk around for bug 5423 till this issue is confirmed by + * official anomaly document. It looks 05000281 still exists on bf561 + * v0.5. + */ +#define ANOMALY_05000281 (__SILICON_REVISION__ <= 5) /* System MMR Write Is Stalled Indefinitely when Killed in a Particular Stage */ #define ANOMALY_05000283 (1) /* Reads Will Receive Incorrect Data under Certain Conditions */ @@ -280,6 +288,12 @@ #define ANOMALY_05000443 (1) /* False Hardware Error when RETI Points to Invalid Memory */ #define ANOMALY_05000461 (1) +/* Interrupted 32-Bit SPORT Data Register Access Results In Underflow */ +#define ANOMALY_05000473 (1) +/* Core Hang With L2/L3 Configured in Writeback Cache Mode */ +#define ANOMALY_05000475 (__SILICON_REVISION__ < 4) +/* TESTSET Instruction Cannot Be Interrupted */ +#define ANOMALY_05000477 (1) /* Anomalies that don't exist on this proc */ #define ANOMALY_05000119 (0) @@ -304,5 +318,6 @@ #define ANOMALY_05000450 (0) #define ANOMALY_05000465 (0) #define ANOMALY_05000467 (0) +#define ANOMALY_05000474 (0) #endif diff --git a/arch/blackfin/mach-common/arch_checks.c b/arch/blackfin/mach-common/arch_checks.c index 9dbafcdcf479..f2ca211a76a0 100644 --- a/arch/blackfin/mach-common/arch_checks.c +++ b/arch/blackfin/mach-common/arch_checks.c @@ -57,3 +57,8 @@ (!defined(CONFIG_BFIN_EXTMEM_DCACHEABLE) && defined(CONFIG_BFIN_L2_WRITEBACK))) # error You are exposing Anomaly 220 in this config, either config L2 as Write Through, or make External Memory WB. #endif + +#if ANOMALY_05000475 && \ + (defined(CONFIG_BFIN_EXTMEM_WRITEBACK) || defined(CONFIG_BFIN_L2_WRITEBACK)) +# error "Anomaly 475 does not allow you to use Write Back cache with L2 or External Memory" +#endif diff --git a/arch/blackfin/mach-common/smp.c b/arch/blackfin/mach-common/smp.c index d98585f3237d..d92b168c8328 100644 --- a/arch/blackfin/mach-common/smp.c +++ b/arch/blackfin/mach-common/smp.c @@ -276,10 +276,9 @@ void smp_send_reschedule(int cpu) if (cpu_is_offline(cpu)) return; - msg = kmalloc(sizeof(*msg), GFP_ATOMIC); + msg = kzalloc(sizeof(*msg), GFP_ATOMIC); if (!msg) return; - memset(msg, 0, sizeof(msg)); INIT_LIST_HEAD(&msg->list); msg->type = BFIN_IPI_RESCHEDULE; @@ -305,10 +304,9 @@ void smp_send_stop(void) if (cpus_empty(callmap)) return; - msg = kmalloc(sizeof(*msg), GFP_ATOMIC); + msg = kzalloc(sizeof(*msg), GFP_ATOMIC); if (!msg) return; - memset(msg, 0, sizeof(msg)); INIT_LIST_HEAD(&msg->list); msg->type = BFIN_IPI_CPU_STOP; diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 1aad0d9f5074..fd7620f025fa 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -358,7 +358,14 @@ config SGI_IP22 select SWAP_IO_SPACE select SYS_HAS_CPU_R4X00 select SYS_HAS_CPU_R5000 - select SYS_HAS_EARLY_PRINTK + # + # Disable EARLY_PRINTK for now since it leads to overwritten prom + # memory during early boot on some machines. + # + # See http://www.linux-mips.org/cgi-bin/mesg.cgi?a=linux-mips&i=20091119164009.GA15038%40deprecation.cyrius.com + # for a more details discussion + # + # select SYS_HAS_EARLY_PRINTK select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN @@ -410,7 +417,14 @@ config SGI_IP28 select SGI_HAS_ZILOG select SWAP_IO_SPACE select SYS_HAS_CPU_R10000 - select SYS_HAS_EARLY_PRINTK + # + # Disable EARLY_PRINTK for now since it leads to overwritten prom + # memory during early boot on some machines. + # + # See http://www.linux-mips.org/cgi-bin/mesg.cgi?a=linux-mips&i=20091119164009.GA15038%40deprecation.cyrius.com + # for a more details discussion + # + # select SYS_HAS_EARLY_PRINTK select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN help @@ -1439,6 +1453,7 @@ choice config PAGE_SIZE_4KB bool "4kB" + depends on !CPU_LOONGSON2 help This option select the standard 4kB Linux page size. On some R3000-family processors this is the only available page size. Using @@ -1763,7 +1778,7 @@ config SYS_SUPPORTS_SMARTMIPS config ARCH_FLATMEM_ENABLE def_bool y - depends on !NUMA + depends on !NUMA && !CPU_LOONGSON2 config ARCH_DISCONTIGMEM_ENABLE bool diff --git a/arch/mips/include/asm/mman.h b/arch/mips/include/asm/mman.h index a2250f390a29..c892bfb3e2c1 100644 --- a/arch/mips/include/asm/mman.h +++ b/arch/mips/include/asm/mman.h @@ -75,6 +75,7 @@ #define MADV_MERGEABLE 12 /* KSM may merge identical pages */ #define MADV_UNMERGEABLE 13 /* KSM may not merge identical pages */ +#define MADV_HWPOISON 100 /* poison a page for testing */ /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/mips/include/asm/system.h b/arch/mips/include/asm/system.h index fcf5f98d90cc..83b5509e09e8 100644 --- a/arch/mips/include/asm/system.h +++ b/arch/mips/include/asm/system.h @@ -12,6 +12,7 @@ #ifndef _ASM_SYSTEM_H #define _ASM_SYSTEM_H +#include <linux/kernel.h> #include <linux/types.h> #include <linux/irqflags.h> @@ -193,10 +194,6 @@ extern __u64 __xchg_u64_unsupported_on_32bit_kernels(volatile __u64 * m, __u64 v #define __xchg_u64 __xchg_u64_unsupported_on_32bit_kernels #endif -/* This function doesn't exist, so you'll get a linker error - if something tries to do an invalid xchg(). */ -extern void __xchg_called_with_bad_pointer(void); - static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size) { switch (size) { @@ -205,11 +202,17 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz case 8: return __xchg_u64(ptr, x); } - __xchg_called_with_bad_pointer(); + return x; } -#define xchg(ptr, x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr)))) +#define xchg(ptr, x) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) & ~0xc); \ + \ + ((__typeof__(*(ptr))) \ + __xchg((unsigned long)(x), (ptr), sizeof(*(ptr)))); \ +}) extern void set_handler(unsigned long offset, void *addr, unsigned long len); extern void set_uncached_handler(unsigned long offset, void *addr, unsigned long len); diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h index 8c9dfa9e9018..65c679ecbe6b 100644 --- a/arch/mips/include/asm/unistd.h +++ b/arch/mips/include/asm/unistd.h @@ -355,16 +355,17 @@ #define __NR_rt_tgsigqueueinfo (__NR_Linux + 332) #define __NR_perf_event_open (__NR_Linux + 333) #define __NR_accept4 (__NR_Linux + 334) +#define __NR_recvmmsg (__NR_Linux + 335) /* * Offset of the last Linux o32 flavoured syscall */ -#define __NR_Linux_syscalls 334 +#define __NR_Linux_syscalls 335 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */ #define __NR_O32_Linux 4000 -#define __NR_O32_Linux_syscalls 334 +#define __NR_O32_Linux_syscalls 335 #if _MIPS_SIM == _MIPS_SIM_ABI64 @@ -666,16 +667,17 @@ #define __NR_rt_tgsigqueueinfo (__NR_Linux + 291) #define __NR_perf_event_open (__NR_Linux + 292) #define __NR_accept4 (__NR_Linux + 293) +#define __NR_recvmmsg (__NR_Linux + 294) /* * Offset of the last Linux 64-bit flavoured syscall */ -#define __NR_Linux_syscalls 293 +#define __NR_Linux_syscalls 294 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */ #define __NR_64_Linux 5000 -#define __NR_64_Linux_syscalls 293 +#define __NR_64_Linux_syscalls 294 #if _MIPS_SIM == _MIPS_SIM_NABI32 @@ -981,16 +983,17 @@ #define __NR_rt_tgsigqueueinfo (__NR_Linux + 295) #define __NR_perf_event_open (__NR_Linux + 296) #define __NR_accept4 (__NR_Linux + 297) +#define __NR_recvmmsg (__NR_Linux + 298) /* * Offset of the last N32 flavoured syscall */ -#define __NR_Linux_syscalls 297 +#define __NR_Linux_syscalls 298 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */ #define __NR_N32_Linux 6000 -#define __NR_N32_Linux_syscalls 297 +#define __NR_N32_Linux_syscalls 298 #ifdef __KERNEL__ diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c index 69dad5a850a8..a36799e85693 100644 --- a/arch/parisc/kernel/unwind.c +++ b/arch/parisc/kernel/unwind.c @@ -28,7 +28,7 @@ #define dbg(x...) #endif -#define KERNEL_START (KERNEL_BINARY_TEXT_START - 0x1000) +#define KERNEL_START (KERNEL_BINARY_TEXT_START) extern struct unwind_table_entry __start___unwind[]; extern struct unwind_table_entry __stop___unwind[]; diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index fda4baa059b5..9dab4a4e09f7 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -78,9 +78,6 @@ SECTIONS */ . = ALIGN(PAGE_SIZE); data_start = .; - EXCEPTION_TABLE(16) - - NOTES /* unwind info */ .PARISC.unwind : { @@ -89,6 +86,9 @@ SECTIONS __stop___unwind = .; } + EXCEPTION_TABLE(16) + NOTES + /* Data */ RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) diff --git a/arch/powerpc/include/asm/kmap_types.h b/arch/powerpc/include/asm/kmap_types.h index b6bac6f61c16..916369575c97 100644 --- a/arch/powerpc/include/asm/kmap_types.h +++ b/arch/powerpc/include/asm/kmap_types.h @@ -29,5 +29,16 @@ enum km_type { KM_TYPE_NR }; +/* + * This is a temporary build fix that (so they say on lkml....) should no longer + * be required after 2.6.33, because of changes planned to the kmap code. + * Let's try to remove this cruft then. + */ +#ifdef CONFIG_DEBUG_HIGHMEM +#define KM_NMI (-1) +#define KM_NMI_PTE (-1) +#define KM_IRQ_PTE (-1) +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_KMAP_TYPES_H */ diff --git a/arch/sparc/mm/init_64.h b/arch/sparc/mm/init_64.h index c2f772dbd556..77d1b313e344 100644 --- a/arch/sparc/mm/init_64.h +++ b/arch/sparc/mm/init_64.h @@ -45,7 +45,7 @@ extern void free_initmem(void); #define VMEMMAP_ALIGN(x) (((x)+VMEMMAP_CHUNK-1UL)&VMEMMAP_CHUNK_MASK) #define VMEMMAP_SIZE ((((1UL << MAX_PHYSADDR_BITS) >> PAGE_SHIFT) * \ - sizeof(struct page *)) >> VMEMMAP_CHUNK_SHIFT) + sizeof(struct page)) >> VMEMMAP_CHUNK_SHIFT) extern unsigned long vmemmap_table[VMEMMAP_SIZE]; #endif diff --git a/arch/x86/kernel/acpi/processor.c b/arch/x86/kernel/acpi/processor.c index d296f4a195c9..d85d1b2432ba 100644 --- a/arch/x86/kernel/acpi/processor.c +++ b/arch/x86/kernel/acpi/processor.c @@ -79,7 +79,8 @@ void arch_acpi_processor_init_pdc(struct acpi_processor *pr) struct cpuinfo_x86 *c = &cpu_data(pr->id); pr->pdc = NULL; - if (c->x86_vendor == X86_VENDOR_INTEL) + if (c->x86_vendor == X86_VENDOR_INTEL || + c->x86_vendor == X86_VENDOR_CENTAUR) init_intel_pdc(pr, c); return; diff --git a/crypto/async_tx/Kconfig b/crypto/async_tx/Kconfig index e5aeb2b79e6f..e28e276ac611 100644 --- a/crypto/async_tx/Kconfig +++ b/crypto/async_tx/Kconfig @@ -23,3 +23,8 @@ config ASYNC_RAID6_RECOV select ASYNC_CORE select ASYNC_PQ +config ASYNC_TX_DISABLE_PQ_VAL_DMA + bool + +config ASYNC_TX_DISABLE_XOR_VAL_DMA + bool diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c index 6b5cc4fba59f..ec87f53d5059 100644 --- a/crypto/async_tx/async_pq.c +++ b/crypto/async_tx/async_pq.c @@ -240,6 +240,16 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks, } EXPORT_SYMBOL_GPL(async_gen_syndrome); +static inline struct dma_chan * +pq_val_chan(struct async_submit_ctl *submit, struct page **blocks, int disks, size_t len) +{ + #ifdef CONFIG_ASYNC_TX_DISABLE_PQ_VAL_DMA + return NULL; + #endif + return async_tx_find_channel(submit, DMA_PQ_VAL, NULL, 0, blocks, + disks, len); +} + /** * async_syndrome_val - asynchronously validate a raid6 syndrome * @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1 @@ -260,9 +270,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks, size_t len, enum sum_check_flags *pqres, struct page *spare, struct async_submit_ctl *submit) { - struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ_VAL, - NULL, 0, blocks, disks, - len); + struct dma_chan *chan = pq_val_chan(submit, blocks, disks, len); struct dma_device *device = chan ? chan->device : NULL; struct dma_async_tx_descriptor *tx; unsigned char coefs[disks-2]; diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index 79182dcb91b7..079ae8ca590b 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -234,6 +234,17 @@ static int page_is_zero(struct page *p, unsigned int offset, size_t len) memcmp(a, a + 4, len - 4) == 0); } +static inline struct dma_chan * +xor_val_chan(struct async_submit_ctl *submit, struct page *dest, + struct page **src_list, int src_cnt, size_t len) +{ + #ifdef CONFIG_ASYNC_TX_DISABLE_XOR_VAL_DMA + return NULL; + #endif + return async_tx_find_channel(submit, DMA_XOR_VAL, &dest, 1, src_list, + src_cnt, len); +} + /** * async_xor_val - attempt a xor parity check with a dma engine. * @dest: destination page used if the xor is performed synchronously @@ -255,9 +266,7 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset, int src_cnt, size_t len, enum sum_check_flags *result, struct async_submit_ctl *submit) { - struct dma_chan *chan = async_tx_find_channel(submit, DMA_XOR_VAL, - &dest, 1, src_list, - src_cnt, len); + struct dma_chan *chan = xor_val_chan(submit, dest, src_list, src_cnt, len); struct dma_device *device = chan ? chan->device : NULL; struct dma_async_tx_descriptor *tx = NULL; dma_addr_t *dma_src = NULL; diff --git a/crypto/gcm.c b/crypto/gcm.c index 5fc3292483ef..c6547130624c 100644 --- a/crypto/gcm.c +++ b/crypto/gcm.c @@ -40,7 +40,7 @@ struct crypto_rfc4106_ctx { struct crypto_gcm_ghash_ctx { unsigned int cryptlen; struct scatterlist *src; - crypto_completion_t complete; + void (*complete)(struct aead_request *req, int err); }; struct crypto_gcm_req_priv_ctx { @@ -267,23 +267,26 @@ static int gcm_hash_final(struct aead_request *req, return crypto_ahash_final(ahreq); } -static void gcm_hash_final_done(struct crypto_async_request *areq, - int err) +static void __gcm_hash_final_done(struct aead_request *req, int err) { - struct aead_request *req = areq->data; struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx; if (!err) crypto_xor(pctx->auth_tag, pctx->iauth_tag, 16); - gctx->complete(areq, err); + gctx->complete(req, err); } -static void gcm_hash_len_done(struct crypto_async_request *areq, - int err) +static void gcm_hash_final_done(struct crypto_async_request *areq, int err) { struct aead_request *req = areq->data; + + __gcm_hash_final_done(req, err); +} + +static void __gcm_hash_len_done(struct aead_request *req, int err) +{ struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); if (!err) { @@ -292,13 +295,18 @@ static void gcm_hash_len_done(struct crypto_async_request *areq, return; } - gcm_hash_final_done(areq, err); + __gcm_hash_final_done(req, err); } -static void gcm_hash_crypt_remain_done(struct crypto_async_request *areq, - int err) +static void gcm_hash_len_done(struct crypto_async_request *areq, int err) { struct aead_request *req = areq->data; + + __gcm_hash_len_done(req, err); +} + +static void __gcm_hash_crypt_remain_done(struct aead_request *req, int err) +{ struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); if (!err) { @@ -307,13 +315,19 @@ static void gcm_hash_crypt_remain_done(struct crypto_async_request *areq, return; } - gcm_hash_len_done(areq, err); + __gcm_hash_len_done(req, err); } -static void gcm_hash_crypt_done(struct crypto_async_request *areq, - int err) +static void gcm_hash_crypt_remain_done(struct crypto_async_request *areq, + int err) { struct aead_request *req = areq->data; + + __gcm_hash_crypt_remain_done(req, err); +} + +static void __gcm_hash_crypt_done(struct aead_request *req, int err) +{ struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx; unsigned int remain; @@ -327,13 +341,18 @@ static void gcm_hash_crypt_done(struct crypto_async_request *areq, return; } - gcm_hash_crypt_remain_done(areq, err); + __gcm_hash_crypt_remain_done(req, err); } -static void gcm_hash_assoc_remain_done(struct crypto_async_request *areq, - int err) +static void gcm_hash_crypt_done(struct crypto_async_request *areq, int err) { struct aead_request *req = areq->data; + + __gcm_hash_crypt_done(req, err); +} + +static void __gcm_hash_assoc_remain_done(struct aead_request *req, int err) +{ struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx; crypto_completion_t complete; @@ -350,15 +369,21 @@ static void gcm_hash_assoc_remain_done(struct crypto_async_request *areq, } if (remain) - gcm_hash_crypt_done(areq, err); + __gcm_hash_crypt_done(req, err); else - gcm_hash_crypt_remain_done(areq, err); + __gcm_hash_crypt_remain_done(req, err); } -static void gcm_hash_assoc_done(struct crypto_async_request *areq, - int err) +static void gcm_hash_assoc_remain_done(struct crypto_async_request *areq, + int err) { struct aead_request *req = areq->data; + + __gcm_hash_assoc_remain_done(req, err); +} + +static void __gcm_hash_assoc_done(struct aead_request *req, int err) +{ struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); unsigned int remain; @@ -371,13 +396,18 @@ static void gcm_hash_assoc_done(struct crypto_async_request *areq, return; } - gcm_hash_assoc_remain_done(areq, err); + __gcm_hash_assoc_remain_done(req, err); } -static void gcm_hash_init_done(struct crypto_async_request *areq, - int err) +static void gcm_hash_assoc_done(struct crypto_async_request *areq, int err) { struct aead_request *req = areq->data; + + __gcm_hash_assoc_done(req, err); +} + +static void __gcm_hash_init_done(struct aead_request *req, int err) +{ struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); crypto_completion_t complete; unsigned int remain = 0; @@ -393,9 +423,16 @@ static void gcm_hash_init_done(struct crypto_async_request *areq, } if (remain) - gcm_hash_assoc_done(areq, err); + __gcm_hash_assoc_done(req, err); else - gcm_hash_assoc_remain_done(areq, err); + __gcm_hash_assoc_remain_done(req, err); +} + +static void gcm_hash_init_done(struct crypto_async_request *areq, int err) +{ + struct aead_request *req = areq->data; + + __gcm_hash_init_done(req, err); } static int gcm_hash(struct aead_request *req, @@ -457,10 +494,8 @@ static void gcm_enc_copy_hash(struct aead_request *req, crypto_aead_authsize(aead), 1); } -static void gcm_enc_hash_done(struct crypto_async_request *areq, - int err) +static void gcm_enc_hash_done(struct aead_request *req, int err) { - struct aead_request *req = areq->data; struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); if (!err) @@ -469,8 +504,7 @@ static void gcm_enc_hash_done(struct crypto_async_request *areq, aead_request_complete(req, err); } -static void gcm_encrypt_done(struct crypto_async_request *areq, - int err) +static void gcm_encrypt_done(struct crypto_async_request *areq, int err) { struct aead_request *req = areq->data; struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); @@ -479,9 +513,13 @@ static void gcm_encrypt_done(struct crypto_async_request *areq, err = gcm_hash(req, pctx); if (err == -EINPROGRESS || err == -EBUSY) return; + else if (!err) { + crypto_xor(pctx->auth_tag, pctx->iauth_tag, 16); + gcm_enc_copy_hash(req, pctx); + } } - gcm_enc_hash_done(areq, err); + aead_request_complete(req, err); } static int crypto_gcm_encrypt(struct aead_request *req) @@ -538,9 +576,8 @@ static void gcm_decrypt_done(struct crypto_async_request *areq, int err) aead_request_complete(req, err); } -static void gcm_dec_hash_done(struct crypto_async_request *areq, int err) +static void gcm_dec_hash_done(struct aead_request *req, int err) { - struct aead_request *req = areq->data; struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req); struct ablkcipher_request *abreq = &pctx->u.abreq; struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx; @@ -552,9 +589,11 @@ static void gcm_dec_hash_done(struct crypto_async_request *areq, int err) err = crypto_ablkcipher_decrypt(abreq); if (err == -EINPROGRESS || err == -EBUSY) return; + else if (!err) + err = crypto_gcm_verify(req, pctx); } - gcm_decrypt_done(areq, err); + aead_request_complete(req, err); } static int crypto_gcm_decrypt(struct aead_request *req) diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h index cd80d1dd1950..57bdaf6ffab1 100644 --- a/drivers/acpi/acpica/acpredef.h +++ b/drivers/acpi/acpica/acpredef.h @@ -203,8 +203,9 @@ static const union acpi_predefined_info predefined_names[] = {{"_BCT", 1, ACPI_RTYPE_INTEGER}}, {{"_BDN", 0, ACPI_RTYPE_INTEGER}}, {{"_BFS", 1, 0}}, - {{"_BIF", 0, ACPI_RTYPE_PACKAGE}}, /* Fixed-length (9 Int),(4 Str) */ - {{{ACPI_PTYPE1_FIXED, ACPI_RTYPE_INTEGER, 9, ACPI_RTYPE_STRING}, 4,0}}, + {{"_BIF", 0, ACPI_RTYPE_PACKAGE} }, /* Fixed-length (9 Int),(4 Str/Buf) */ + {{{ACPI_PTYPE1_FIXED, ACPI_RTYPE_INTEGER, 9, + ACPI_RTYPE_STRING | ACPI_RTYPE_BUFFER}, 4, 0} }, {{"_BIX", 0, ACPI_RTYPE_PACKAGE}}, /* Fixed-length (16 Int),(4 Str) */ {{{ACPI_PTYPE1_FIXED, ACPI_RTYPE_INTEGER, 16, ACPI_RTYPE_STRING}, 4, diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c index e56b2a7b53db..23e5a0519af5 100644 --- a/drivers/acpi/blacklist.c +++ b/drivers/acpi/blacklist.c @@ -224,6 +224,7 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = { * _OSI(Linux) helps sound * DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad R61"), * DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T61"), + * T400, T500 * _OSI(Linux) has Linux specific hooks * DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X61"), * _OSI(Linux) is a NOP: @@ -254,6 +255,22 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = { DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X61"), }, }, + { + .callback = dmi_enable_osi_linux, + .ident = "Lenovo ThinkPad T400", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T400"), + }, + }, + { + .callback = dmi_enable_osi_linux, + .ident = "Lenovo ThinkPad T500", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T500"), + }, + }, {} }; diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 4cc1b8116e76..5f2c379ab7bf 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -430,6 +430,14 @@ static struct dmi_system_id __initdata acpisleep_dmi_table[] = { }, { .callback = init_set_sci_en_on_resume, + .ident = "Hewlett-Packard Compaq Presario C700 Notebook PC", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "Compaq Presario C700 Notebook PC"), + }, + }, + { + .callback = init_set_sci_en_on_resume, .ident = "Hewlett-Packard Compaq Presario CQ40 Notebook PC", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index d344db42a002..172b57e6543f 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -707,34 +707,17 @@ static unsigned int sata_fsl_dev_classify(struct ata_port *ap) return ata_dev_classify(&tf); } -static int sata_fsl_prereset(struct ata_link *link, unsigned long deadline) -{ - /* FIXME: Never skip softreset, sata_fsl_softreset() is - * combination of soft and hard resets. sata_fsl_softreset() - * needs to be splitted into soft and hard resets. - */ - return 0; -} - -static int sata_fsl_softreset(struct ata_link *link, unsigned int *class, +static int sata_fsl_hardreset(struct ata_link *link, unsigned int *class, unsigned long deadline) { struct ata_port *ap = link->ap; - struct sata_fsl_port_priv *pp = ap->private_data; struct sata_fsl_host_priv *host_priv = ap->host->private_data; void __iomem *hcr_base = host_priv->hcr_base; - int pmp = sata_srst_pmp(link); u32 temp; - struct ata_taskfile tf; - u8 *cfis; - u32 Serror; int i = 0; unsigned long start_jiffies; - DPRINTK("in xx_softreset\n"); - - if (pmp != SATA_PMP_CTRL_PORT) - goto issue_srst; + DPRINTK("in xx_hardreset\n"); try_offline_again: /* @@ -749,7 +732,7 @@ try_offline_again: if (temp & ONLINE) { ata_port_printk(ap, KERN_ERR, - "Softreset failed, not off-lined %d\n", i); + "Hardreset failed, not off-lined %d\n", i); /* * Try to offline controller atleast twice @@ -761,7 +744,7 @@ try_offline_again: goto try_offline_again; } - DPRINTK("softreset, controller off-lined\n"); + DPRINTK("hardreset, controller off-lined\n"); VPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS)); VPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL)); @@ -786,11 +769,11 @@ try_offline_again: if (!(temp & ONLINE)) { ata_port_printk(ap, KERN_ERR, - "Softreset failed, not on-lined\n"); + "Hardreset failed, not on-lined\n"); goto err; } - DPRINTK("softreset, controller off-lined & on-lined\n"); + DPRINTK("hardreset, controller off-lined & on-lined\n"); VPRINTK("HStatus = 0x%x\n", ioread32(hcr_base + HSTATUS)); VPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL)); @@ -806,7 +789,7 @@ try_offline_again: "No Device OR PHYRDY change,Hstatus = 0x%x\n", ioread32(hcr_base + HSTATUS)); *class = ATA_DEV_NONE; - goto out; + return 0; } /* @@ -819,11 +802,44 @@ try_offline_again: if ((temp & 0xFF) != 0x18) { ata_port_printk(ap, KERN_WARNING, "No Signature Update\n"); *class = ATA_DEV_NONE; - goto out; + goto do_followup_srst; } else { ata_port_printk(ap, KERN_INFO, "Signature Update detected @ %d msecs\n", jiffies_to_msecs(jiffies - start_jiffies)); + *class = sata_fsl_dev_classify(ap); + return 0; + } + +do_followup_srst: + /* + * request libATA to perform follow-up softreset + */ + return -EAGAIN; + +err: + return -EIO; +} + +static int sata_fsl_softreset(struct ata_link *link, unsigned int *class, + unsigned long deadline) +{ + struct ata_port *ap = link->ap; + struct sata_fsl_port_priv *pp = ap->private_data; + struct sata_fsl_host_priv *host_priv = ap->host->private_data; + void __iomem *hcr_base = host_priv->hcr_base; + int pmp = sata_srst_pmp(link); + u32 temp; + struct ata_taskfile tf; + u8 *cfis; + u32 Serror; + + DPRINTK("in xx_softreset\n"); + + if (ata_link_offline(link)) { + DPRINTK("PHY reports no device\n"); + *class = ATA_DEV_NONE; + return 0; } /* @@ -834,7 +850,6 @@ try_offline_again: * reached here, we can send a command to the target device */ -issue_srst: DPRINTK("Sending SRST/device reset\n"); ata_tf_init(link->device, &tf); @@ -860,6 +875,8 @@ issue_srst: ioread32(CA + hcr_base), ioread32(CC + hcr_base)); iowrite32(0xFFFF, CC + hcr_base); + if (pmp != SATA_PMP_CTRL_PORT) + iowrite32(pmp, CQPMP + hcr_base); iowrite32(1, CQ + hcr_base); temp = ata_wait_register(CQ + hcr_base, 0x1, 0x1, 1, 5000); @@ -926,7 +943,6 @@ issue_srst: VPRINTK("cereg = 0x%x\n", ioread32(hcr_base + CE)); } -out: return 0; err: @@ -988,18 +1004,6 @@ static void sata_fsl_error_intr(struct ata_port *ap) ehi->err_mask |= AC_ERR_ATA_BUS; ehi->action |= ATA_EH_SOFTRESET; - /* - * Ignore serror in case of fatal errors as we always want - * to do a soft-reset of the FSL SATA controller. Analyzing - * serror may cause libata to schedule a hard-reset action, - * and hard-reset currently does not do controller - * offline/online, causing command timeouts and leads to an - * un-recoverable state, hence make libATA ignore - * autopsy in case of fatal errors. - */ - - ehi->flags |= ATA_EHI_NO_AUTOPSY; - freeze = 1; } @@ -1267,8 +1271,8 @@ static struct ata_port_operations sata_fsl_ops = { .freeze = sata_fsl_freeze, .thaw = sata_fsl_thaw, - .prereset = sata_fsl_prereset, .softreset = sata_fsl_softreset, + .hardreset = sata_fsl_hardreset, .pmp_softreset = sata_fsl_softreset, .error_handler = sata_fsl_error_handler, .post_internal_cmd = sata_fsl_post_internal_cmd, diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index a770498a74ec..846d89e3d122 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -328,11 +328,11 @@ int __pm_runtime_resume(struct device *dev, bool from_wq) * necessary. */ parent = dev->parent; - spin_unlock_irq(&dev->power.lock); + spin_unlock(&dev->power.lock); pm_runtime_get_noresume(parent); - spin_lock_irq(&parent->power.lock); + spin_lock(&parent->power.lock); /* * We can resume if the parent's run-time PM is disabled or it * is set to ignore children. @@ -343,9 +343,9 @@ int __pm_runtime_resume(struct device *dev, bool from_wq) if (parent->power.runtime_status != RPM_ACTIVE) retval = -EBUSY; } - spin_unlock_irq(&parent->power.lock); + spin_unlock(&parent->power.lock); - spin_lock_irq(&dev->power.lock); + spin_lock(&dev->power.lock); if (retval) goto out; goto repeat; @@ -777,7 +777,7 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) } if (parent) { - spin_lock_irq(&parent->power.lock); + spin_lock(&parent->power.lock); /* * It is invalid to put an active child under a parent that is @@ -793,7 +793,7 @@ int __pm_runtime_set_status(struct device *dev, unsigned int status) atomic_inc(&parent->power.child_count); } - spin_unlock_irq(&parent->power.lock); + spin_unlock(&parent->power.lock); if (error) goto out; diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 6399e5090df4..92b126394fa1 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -482,7 +482,7 @@ static ssize_t host_store_rescan(struct device *dev, return count; } -DEVICE_ATTR(rescan, S_IWUSR, NULL, host_store_rescan); +static DEVICE_ATTR(rescan, S_IWUSR, NULL, host_store_rescan); static ssize_t dev_show_unique_id(struct device *dev, struct device_attribute *attr, @@ -512,7 +512,7 @@ static ssize_t dev_show_unique_id(struct device *dev, sn[8], sn[9], sn[10], sn[11], sn[12], sn[13], sn[14], sn[15]); } -DEVICE_ATTR(unique_id, S_IRUGO, dev_show_unique_id, NULL); +static DEVICE_ATTR(unique_id, S_IRUGO, dev_show_unique_id, NULL); static ssize_t dev_show_vendor(struct device *dev, struct device_attribute *attr, @@ -536,7 +536,7 @@ static ssize_t dev_show_vendor(struct device *dev, else return snprintf(buf, sizeof(vendor) + 1, "%s\n", drv->vendor); } -DEVICE_ATTR(vendor, S_IRUGO, dev_show_vendor, NULL); +static DEVICE_ATTR(vendor, S_IRUGO, dev_show_vendor, NULL); static ssize_t dev_show_model(struct device *dev, struct device_attribute *attr, @@ -560,7 +560,7 @@ static ssize_t dev_show_model(struct device *dev, else return snprintf(buf, sizeof(model) + 1, "%s\n", drv->model); } -DEVICE_ATTR(model, S_IRUGO, dev_show_model, NULL); +static DEVICE_ATTR(model, S_IRUGO, dev_show_model, NULL); static ssize_t dev_show_rev(struct device *dev, struct device_attribute *attr, @@ -584,7 +584,7 @@ static ssize_t dev_show_rev(struct device *dev, else return snprintf(buf, sizeof(rev) + 1, "%s\n", drv->rev); } -DEVICE_ATTR(rev, S_IRUGO, dev_show_rev, NULL); +static DEVICE_ATTR(rev, S_IRUGO, dev_show_rev, NULL); static ssize_t cciss_show_lunid(struct device *dev, struct device_attribute *attr, char *buf) @@ -609,7 +609,7 @@ static ssize_t cciss_show_lunid(struct device *dev, lunid[0], lunid[1], lunid[2], lunid[3], lunid[4], lunid[5], lunid[6], lunid[7]); } -DEVICE_ATTR(lunid, S_IRUGO, cciss_show_lunid, NULL); +static DEVICE_ATTR(lunid, S_IRUGO, cciss_show_lunid, NULL); static ssize_t cciss_show_raid_level(struct device *dev, struct device_attribute *attr, char *buf) @@ -632,7 +632,7 @@ static ssize_t cciss_show_raid_level(struct device *dev, return snprintf(buf, strlen(raid_label[raid]) + 7, "RAID %s\n", raid_label[raid]); } -DEVICE_ATTR(raid_level, S_IRUGO, cciss_show_raid_level, NULL); +static DEVICE_ATTR(raid_level, S_IRUGO, cciss_show_raid_level, NULL); static ssize_t cciss_show_usage_count(struct device *dev, struct device_attribute *attr, char *buf) @@ -651,7 +651,7 @@ static ssize_t cciss_show_usage_count(struct device *dev, spin_unlock_irqrestore(CCISS_LOCK(h->ctlr), flags); return snprintf(buf, 20, "%d\n", count); } -DEVICE_ATTR(usage_count, S_IRUGO, cciss_show_usage_count, NULL); +static DEVICE_ATTR(usage_count, S_IRUGO, cciss_show_usage_count, NULL); static struct attribute *cciss_host_attrs[] = { &dev_attr_rescan.attr, diff --git a/drivers/bluetooth/btmrvl_debugfs.c b/drivers/bluetooth/btmrvl_debugfs.c index 4617bd12f63b..d43b5cb864ef 100644 --- a/drivers/bluetooth/btmrvl_debugfs.c +++ b/drivers/bluetooth/btmrvl_debugfs.c @@ -29,7 +29,6 @@ struct btmrvl_debugfs_data { struct dentry *root_dir, *config_dir, *status_dir; /* config */ - struct dentry *drvdbg; struct dentry *psmode; struct dentry *pscmd; struct dentry *hsmode; diff --git a/drivers/bluetooth/btmrvl_drv.h b/drivers/bluetooth/btmrvl_drv.h index 411c7a77082d..523d197b9824 100644 --- a/drivers/bluetooth/btmrvl_drv.h +++ b/drivers/bluetooth/btmrvl_drv.h @@ -131,6 +131,7 @@ void btmrvl_check_evtpkt(struct btmrvl_private *priv, struct sk_buff *skb); int btmrvl_process_event(struct btmrvl_private *priv, struct sk_buff *skb); int btmrvl_send_module_cfg_cmd(struct btmrvl_private *priv, int subcmd); +int btmrvl_enable_ps(struct btmrvl_private *priv); int btmrvl_prepare_command(struct btmrvl_private *priv); #ifdef CONFIG_DEBUG_FS diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c index e605563b4eaa..f97771ce432c 100644 --- a/drivers/bluetooth/btmrvl_main.c +++ b/drivers/bluetooth/btmrvl_main.c @@ -189,6 +189,38 @@ int btmrvl_send_module_cfg_cmd(struct btmrvl_private *priv, int subcmd) } EXPORT_SYMBOL_GPL(btmrvl_send_module_cfg_cmd); +int btmrvl_enable_ps(struct btmrvl_private *priv) +{ + struct sk_buff *skb; + struct btmrvl_cmd *cmd; + + skb = bt_skb_alloc(sizeof(*cmd), GFP_ATOMIC); + if (skb == NULL) { + BT_ERR("No free skb"); + return -ENOMEM; + } + + cmd = (struct btmrvl_cmd *) skb_put(skb, sizeof(*cmd)); + cmd->ocf_ogf = cpu_to_le16(hci_opcode_pack(OGF, + BT_CMD_AUTO_SLEEP_MODE)); + cmd->length = 1; + + if (priv->btmrvl_dev.psmode) + cmd->data[0] = BT_PS_ENABLE; + else + cmd->data[0] = BT_PS_DISABLE; + + bt_cb(skb)->pkt_type = MRVL_VENDOR_PKT; + + skb->dev = (void *) priv->btmrvl_dev.hcidev; + skb_queue_head(&priv->adapter->tx_queue, skb); + + BT_DBG("Queue PSMODE Command:%d", cmd->data[0]); + + return 0; +} +EXPORT_SYMBOL_GPL(btmrvl_enable_ps); + static int btmrvl_enable_hs(struct btmrvl_private *priv) { struct sk_buff *skb; @@ -258,28 +290,7 @@ int btmrvl_prepare_command(struct btmrvl_private *priv) if (priv->btmrvl_dev.pscmd) { priv->btmrvl_dev.pscmd = 0; - - skb = bt_skb_alloc(sizeof(*cmd), GFP_ATOMIC); - if (skb == NULL) { - BT_ERR("No free skb"); - return -ENOMEM; - } - - cmd = (struct btmrvl_cmd *) skb_put(skb, sizeof(*cmd)); - cmd->ocf_ogf = cpu_to_le16(hci_opcode_pack(OGF, BT_CMD_AUTO_SLEEP_MODE)); - cmd->length = 1; - - if (priv->btmrvl_dev.psmode) - cmd->data[0] = BT_PS_ENABLE; - else - cmd->data[0] = BT_PS_DISABLE; - - bt_cb(skb)->pkt_type = MRVL_VENDOR_PKT; - - skb->dev = (void *) priv->btmrvl_dev.hcidev; - skb_queue_head(&priv->adapter->tx_queue, skb); - - BT_DBG("Queue PSMODE Command:%d", cmd->data[0]); + btmrvl_enable_ps(priv); } if (priv->btmrvl_dev.hscmd) { diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c index 5b33b85790f2..1e6eb1aeba2b 100644 --- a/drivers/bluetooth/btmrvl_sdio.c +++ b/drivers/bluetooth/btmrvl_sdio.c @@ -930,6 +930,8 @@ static int btmrvl_sdio_probe(struct sdio_func *func, priv->hw_wakeup_firmware = btmrvl_sdio_wakeup_fw; btmrvl_send_module_cfg_cmd(priv, MODULE_BRINGUP_REQ); + priv->btmrvl_dev.psmode = 1; + btmrvl_enable_ps(priv); return 0; @@ -1001,3 +1003,5 @@ MODULE_AUTHOR("Marvell International Ltd."); MODULE_DESCRIPTION("Marvell BT-over-SDIO driver ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL v2"); +MODULE_FIRMWARE("sd8688_helper.bin"); +MODULE_FIRMWARE("sd8688.bin"); diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index d5cde6d86f89..7595274103fd 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -41,8 +41,6 @@ #define VERSION "1.3" -static int minor = MISC_DYNAMIC_MINOR; - struct vhci_data { struct hci_dev *hdev; @@ -218,12 +216,6 @@ static unsigned int vhci_poll(struct file *file, poll_table *wait) return POLLOUT | POLLWRNORM; } -static int vhci_ioctl(struct inode *inode, struct file *file, - unsigned int cmd, unsigned long arg) -{ - return -EINVAL; -} - static int vhci_open(struct inode *inode, struct file *file) { struct vhci_data *data; @@ -284,10 +276,10 @@ static int vhci_release(struct inode *inode, struct file *file) } static const struct file_operations vhci_fops = { + .owner = THIS_MODULE, .read = vhci_read, .write = vhci_write, .poll = vhci_poll, - .ioctl = vhci_ioctl, .open = vhci_open, .release = vhci_release, }; @@ -302,18 +294,12 @@ static int __init vhci_init(void) { BT_INFO("Virtual HCI driver ver %s", VERSION); - if (misc_register(&vhci_miscdev) < 0) { - BT_ERR("Can't register misc device with minor %d", minor); - return -EIO; - } - - return 0; + return misc_register(&vhci_miscdev); } static void __exit vhci_exit(void) { - if (misc_deregister(&vhci_miscdev) < 0) - BT_ERR("Can't unregister misc device with minor %d", minor); + misc_deregister(&vhci_miscdev); } module_init(vhci_init); diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c index 10e1f0390bbb..3cb56a049e24 100644 --- a/drivers/char/agp/intel-agp.c +++ b/drivers/char/agp/intel-agp.c @@ -62,6 +62,7 @@ #define PCI_DEVICE_ID_INTEL_IGDNG_D_IG 0x0042 #define PCI_DEVICE_ID_INTEL_IGDNG_M_HB 0x0044 #define PCI_DEVICE_ID_INTEL_IGDNG_MA_HB 0x0062 +#define PCI_DEVICE_ID_INTEL_IGDNG_MC2_HB 0x006a #define PCI_DEVICE_ID_INTEL_IGDNG_M_IG 0x0046 /* cover 915 and 945 variants */ @@ -96,7 +97,8 @@ agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_B43_HB || \ agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_IGDNG_D_HB || \ agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_IGDNG_M_HB || \ - agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_IGDNG_MA_HB) + agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_IGDNG_MA_HB || \ + agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_IGDNG_MC2_HB) extern int agp_memory_reserved; @@ -1358,6 +1360,7 @@ static void intel_i965_get_gtt_range(int *gtt_offset, int *gtt_size) case PCI_DEVICE_ID_INTEL_IGDNG_D_HB: case PCI_DEVICE_ID_INTEL_IGDNG_M_HB: case PCI_DEVICE_ID_INTEL_IGDNG_MA_HB: + case PCI_DEVICE_ID_INTEL_IGDNG_MC2_HB: *gtt_offset = *gtt_size = MB(2); break; default: @@ -2359,6 +2362,8 @@ static const struct intel_driver_description { "IGDNG/M", NULL, &intel_i965_driver }, { PCI_DEVICE_ID_INTEL_IGDNG_MA_HB, PCI_DEVICE_ID_INTEL_IGDNG_M_IG, 0, "IGDNG/MA", NULL, &intel_i965_driver }, + { PCI_DEVICE_ID_INTEL_IGDNG_MC2_HB, PCI_DEVICE_ID_INTEL_IGDNG_M_IG, 0, + "IGDNG/MC2", NULL, &intel_i965_driver }, { 0, 0, 0, NULL, NULL, NULL } }; @@ -2560,6 +2565,7 @@ static struct pci_device_id agp_intel_pci_table[] = { ID(PCI_DEVICE_ID_INTEL_IGDNG_D_HB), ID(PCI_DEVICE_ID_INTEL_IGDNG_M_HB), ID(PCI_DEVICE_ID_INTEL_IGDNG_MA_HB), + ID(PCI_DEVICE_ID_INTEL_IGDNG_MC2_HB), { } }; diff --git a/drivers/char/keyboard.c b/drivers/char/keyboard.c index 737be953cc58..950837cf9e9c 100644 --- a/drivers/char/keyboard.c +++ b/drivers/char/keyboard.c @@ -1249,7 +1249,7 @@ static void kbd_keycode(unsigned int keycode, int down, int hw_raw) if (keycode >= NR_KEYS) if (keycode >= KEY_BRL_DOT1 && keycode <= KEY_BRL_DOT8) - keysym = K(KT_BRL, keycode - KEY_BRL_DOT1 + 1); + keysym = U(K(KT_BRL, keycode - KEY_BRL_DOT1 + 1)); else return; else diff --git a/drivers/char/tty_port.c b/drivers/char/tty_port.c index 2e8552dc5eda..c63f3d33914a 100644 --- a/drivers/char/tty_port.c +++ b/drivers/char/tty_port.c @@ -219,8 +219,11 @@ int tty_port_block_til_ready(struct tty_port *port, /* if non-blocking mode is set we can pass directly to open unless the port has just hung up or is in another error state */ - if ((filp->f_flags & O_NONBLOCK) || - (tty->flags & (1 << TTY_IO_ERROR))) { + if (tty->flags & (1 << TTY_IO_ERROR)) { + port->flags |= ASYNC_NORMAL_ACTIVE; + return 0; + } + if (filp->f_flags & O_NONBLOCK) { /* Indicate we are open */ if (tty->termios->c_cflag & CBAUD) tty_port_raise_dtr_rts(port); diff --git a/drivers/char/vt_ioctl.c b/drivers/char/vt_ioctl.c index ed86d3bf249a..6aa10284104a 100644 --- a/drivers/char/vt_ioctl.c +++ b/drivers/char/vt_ioctl.c @@ -103,8 +103,8 @@ void vt_event_post(unsigned int event, unsigned int old, unsigned int new) ve->event.event = event; /* kernel view is consoles 0..n-1, user space view is console 1..n with 0 meaning current, so we must bias */ - ve->event.old = old + 1; - ve->event.new = new + 1; + ve->event.oldev = old + 1; + ve->event.newev = new + 1; wake = 1; ve->done = 1; } @@ -186,7 +186,7 @@ int vt_waitactive(int n) vt_event_wait(&vw); if (vw.done == 0) return -EINTR; - } while (vw.event.new != n); + } while (vw.event.newev != n); return 0; } diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c index a9952b1236b0..84c51e177269 100644 --- a/drivers/crypto/padlock-aes.c +++ b/drivers/crypto/padlock-aes.c @@ -236,7 +236,7 @@ static inline void ecb_crypt(const u8 *in, u8 *out, u32 *key, /* Padlock in ECB mode fetches at least ecb_fetch_bytes of data. * We could avoid some copying here but it's probably not worth it. */ - if (unlikely(((unsigned long)in & PAGE_SIZE) + ecb_fetch_bytes > PAGE_SIZE)) { + if (unlikely(((unsigned long)in & ~PAGE_MASK) + ecb_fetch_bytes > PAGE_SIZE)) { ecb_crypt_copy(in, out, key, cword, count); return; } @@ -248,7 +248,7 @@ static inline u8 *cbc_crypt(const u8 *in, u8 *out, u32 *key, u8 *iv, struct cword *cword, int count) { /* Padlock in CBC mode fetches at least cbc_fetch_bytes of data. */ - if (unlikely(((unsigned long)in & PAGE_SIZE) + cbc_fetch_bytes > PAGE_SIZE)) + if (unlikely(((unsigned long)in & ~PAGE_MASK) + cbc_fetch_bytes > PAGE_SIZE)) return cbc_crypt_copy(in, out, key, iv, cword, count); return rep_xcrypt_cbc(in, out, key, iv, cword, count); diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 5903a88351bf..b401dadad4a8 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -26,6 +26,8 @@ config INTEL_IOATDMA select DMA_ENGINE select DCA select ASYNC_TX_DISABLE_CHANNEL_SWITCH + select ASYNC_TX_DISABLE_PQ_VAL_DMA + select ASYNC_TX_DISABLE_XOR_VAL_DMA help Enable support for the Intel(R) I/OAT DMA engine present in recent Intel Xeon chipsets. diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index bd0b248de2cf..8f99354082ce 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -632,11 +632,21 @@ static bool device_has_all_tx_types(struct dma_device *device) #if defined(CONFIG_ASYNC_XOR) || defined(CONFIG_ASYNC_XOR_MODULE) if (!dma_has_cap(DMA_XOR, device->cap_mask)) return false; + + #ifndef CONFIG_ASYNC_TX_DISABLE_XOR_VAL_DMA + if (!dma_has_cap(DMA_XOR_VAL, device->cap_mask)) + return false; + #endif #endif #if defined(CONFIG_ASYNC_PQ) || defined(CONFIG_ASYNC_PQ_MODULE) if (!dma_has_cap(DMA_PQ, device->cap_mask)) return false; + + #ifndef CONFIG_ASYNC_TX_DISABLE_PQ_VAL_DMA + if (!dma_has_cap(DMA_PQ_VAL, device->cap_mask)) + return false; + #endif #endif return true; diff --git a/drivers/dma/ioat/dca.c b/drivers/dma/ioat/dca.c index 69d02615c4d6..abd9038e06b1 100644 --- a/drivers/dma/ioat/dca.c +++ b/drivers/dma/ioat/dca.c @@ -98,17 +98,17 @@ static int dca_enabled_in_bios(struct pci_dev *pdev) cpuid_level_9 = cpuid_eax(9); res = test_bit(0, &cpuid_level_9); if (!res) - dev_err(&pdev->dev, "DCA is disabled in BIOS\n"); + dev_dbg(&pdev->dev, "DCA is disabled in BIOS\n"); return res; } -static int system_has_dca_enabled(struct pci_dev *pdev) +int system_has_dca_enabled(struct pci_dev *pdev) { if (boot_cpu_has(X86_FEATURE_DCA)) return dca_enabled_in_bios(pdev); - dev_err(&pdev->dev, "boot cpu doesn't have X86_FEATURE_DCA\n"); + dev_dbg(&pdev->dev, "boot cpu doesn't have X86_FEATURE_DCA\n"); return 0; } diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h index c14fdfeb7f33..45edde996480 100644 --- a/drivers/dma/ioat/dma.h +++ b/drivers/dma/ioat/dma.h @@ -297,9 +297,7 @@ static inline bool is_ioat_suspended(unsigned long status) /* channel was fatally programmed */ static inline bool is_ioat_bug(unsigned long err) { - return !!(err & (IOAT_CHANERR_SRC_ADDR_ERR|IOAT_CHANERR_DEST_ADDR_ERR| - IOAT_CHANERR_NEXT_ADDR_ERR|IOAT_CHANERR_CONTROL_ERR| - IOAT_CHANERR_LENGTH_ERR)); + return !!err; } static inline void ioat_unmap(struct pci_dev *pdev, dma_addr_t addr, size_t len, diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c index 96ffab7d37a7..8f1f7f05deaa 100644 --- a/drivers/dma/ioat/dma_v2.c +++ b/drivers/dma/ioat/dma_v2.c @@ -279,6 +279,8 @@ void ioat2_timer_event(unsigned long data) u32 chanerr; chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET); + dev_err(to_dev(chan), "%s: Channel halted (%x)\n", + __func__, chanerr); BUG_ON(is_ioat_bug(chanerr)); } diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c index 35d1e33afd5b..42f6f10fb0cc 100644 --- a/drivers/dma/ioat/dma_v3.c +++ b/drivers/dma/ioat/dma_v3.c @@ -378,6 +378,8 @@ static void ioat3_timer_event(unsigned long data) u32 chanerr; chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET); + dev_err(to_dev(chan), "%s: Channel halted (%x)\n", + __func__, chanerr); BUG_ON(is_ioat_bug(chanerr)); } @@ -569,7 +571,7 @@ __ioat3_prep_xor_lock(struct dma_chan *c, enum sum_check_flags *result, dump_desc_dbg(ioat, compl_desc); /* we leave the channel locked to ensure in order submission */ - return &desc->txd; + return &compl_desc->txd; } static struct dma_async_tx_descriptor * @@ -728,7 +730,7 @@ __ioat3_prep_pq_lock(struct dma_chan *c, enum sum_check_flags *result, dump_desc_dbg(ioat, compl_desc); /* we leave the channel locked to ensure in order submission */ - return &desc->txd; + return &compl_desc->txd; } static struct dma_async_tx_descriptor * @@ -736,10 +738,16 @@ ioat3_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src, unsigned int src_cnt, const unsigned char *scf, size_t len, unsigned long flags) { + /* specify valid address for disabled result */ + if (flags & DMA_PREP_PQ_DISABLE_P) + dst[0] = dst[1]; + if (flags & DMA_PREP_PQ_DISABLE_Q) + dst[1] = dst[0]; + /* handle the single source multiply case from the raid6 * recovery path */ - if (unlikely((flags & DMA_PREP_PQ_DISABLE_P) && src_cnt == 1)) { + if ((flags & DMA_PREP_PQ_DISABLE_P) && src_cnt == 1) { dma_addr_t single_source[2]; unsigned char single_source_coef[2]; @@ -761,6 +769,12 @@ ioat3_prep_pq_val(struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src, unsigned int src_cnt, const unsigned char *scf, size_t len, enum sum_check_flags *pqres, unsigned long flags) { + /* specify valid address for disabled result */ + if (flags & DMA_PREP_PQ_DISABLE_P) + pq[0] = pq[1]; + if (flags & DMA_PREP_PQ_DISABLE_Q) + pq[1] = pq[0]; + /* the cleanup routine only sets bits on validate failure, it * does not clear bits on validate success... so clear it here */ @@ -778,9 +792,9 @@ ioat3_prep_pqxor(struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src, dma_addr_t pq[2]; memset(scf, 0, src_cnt); - flags |= DMA_PREP_PQ_DISABLE_Q; pq[0] = dst; - pq[1] = ~0; + flags |= DMA_PREP_PQ_DISABLE_Q; + pq[1] = dst; /* specify valid address for disabled result */ return __ioat3_prep_pq_lock(chan, NULL, pq, src, src_cnt, scf, len, flags); @@ -800,9 +814,9 @@ ioat3_prep_pqxor_val(struct dma_chan *chan, dma_addr_t *src, *result = 0; memset(scf, 0, src_cnt); - flags |= DMA_PREP_PQ_DISABLE_Q; pq[0] = src[0]; - pq[1] = ~0; + flags |= DMA_PREP_PQ_DISABLE_Q; + pq[1] = pq[0]; /* specify valid address for disabled result */ return __ioat3_prep_pq_lock(chan, result, pq, &src[1], src_cnt - 1, scf, len, flags); @@ -1117,6 +1131,7 @@ static int __devinit ioat3_dma_self_test(struct ioatdma_device *device) int __devinit ioat3_dma_probe(struct ioatdma_device *device, int dca) { struct pci_dev *pdev = device->pdev; + int dca_en = system_has_dca_enabled(pdev); struct dma_device *dma; struct dma_chan *c; struct ioat_chan_common *chan; @@ -1137,6 +1152,11 @@ int __devinit ioat3_dma_probe(struct ioatdma_device *device, int dca) dma->device_prep_dma_interrupt = ioat3_prep_interrupt_lock; cap = readl(device->reg_base + IOAT_DMA_CAP_OFFSET); + + /* dca is incompatible with raid operations */ + if (dca_en && (cap & (IOAT_CAP_XOR|IOAT_CAP_PQ))) + cap &= ~(IOAT_CAP_XOR|IOAT_CAP_PQ); + if (cap & IOAT_CAP_XOR) { is_raid_device = true; dma->max_xor = 8; @@ -1186,6 +1206,16 @@ int __devinit ioat3_dma_probe(struct ioatdma_device *device, int dca) device->timer_fn = ioat2_timer_event; } + #ifdef CONFIG_ASYNC_TX_DISABLE_PQ_VAL_DMA + dma_cap_clear(DMA_PQ_VAL, dma->cap_mask); + dma->device_prep_dma_pq_val = NULL; + #endif + + #ifdef CONFIG_ASYNC_TX_DISABLE_XOR_VAL_DMA + dma_cap_clear(DMA_XOR_VAL, dma->cap_mask); + dma->device_prep_dma_xor_val = NULL; + #endif + /* -= IOAT ver.3 workarounds =- */ /* Write CHANERRMSK_INT with 3E07h to mask out the errors * that can cause stability issues for IOAT ver.3 diff --git a/drivers/dma/ioat/hw.h b/drivers/dma/ioat/hw.h index 99afb12bd409..60e675455b6a 100644 --- a/drivers/dma/ioat/hw.h +++ b/drivers/dma/ioat/hw.h @@ -39,6 +39,8 @@ #define IOAT_VER_3_0 0x30 /* Version 3.0 */ #define IOAT_VER_3_2 0x32 /* Version 3.2 */ +int system_has_dca_enabled(struct pci_dev *pdev); + struct ioat_dma_descriptor { uint32_t size; union { diff --git a/drivers/dma/ioat/registers.h b/drivers/dma/ioat/registers.h index 63038e18ab03..f015ec196700 100644 --- a/drivers/dma/ioat/registers.h +++ b/drivers/dma/ioat/registers.h @@ -92,9 +92,7 @@ #define IOAT_CHANCTRL_ERR_COMPLETION_EN 0x0004 #define IOAT_CHANCTRL_INT_REARM 0x0001 #define IOAT_CHANCTRL_RUN (IOAT_CHANCTRL_INT_REARM |\ - IOAT_CHANCTRL_ERR_COMPLETION_EN |\ - IOAT_CHANCTRL_ANY_ERR_ABORT_EN |\ - IOAT_CHANCTRL_ERR_INT_EN) + IOAT_CHANCTRL_ANY_ERR_ABORT_EN) #define IOAT_DMA_COMP_OFFSET 0x02 /* 16-bit DMA channel compatibility */ #define IOAT_DMA_COMP_V1 0x0001 /* Compatibility with DMA version 1 */ diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c index b3b065c4e5c1..034ecf0ace03 100644 --- a/drivers/dma/shdma.c +++ b/drivers/dma/shdma.c @@ -640,17 +640,16 @@ static int __init sh_dmae_probe(struct platform_device *pdev) #endif struct sh_dmae_device *shdev; + /* get platform data */ + if (!pdev->dev.platform_data) + return -ENODEV; + shdev = kzalloc(sizeof(struct sh_dmae_device), GFP_KERNEL); if (!shdev) { dev_err(&pdev->dev, "No enough memory\n"); - err = -ENOMEM; - goto shdev_err; + return -ENOMEM; } - /* get platform data */ - if (!pdev->dev.platform_data) - goto shdev_err; - /* platform data */ memcpy(&shdev->pdata, pdev->dev.platform_data, sizeof(struct sh_dmae_pdata)); @@ -722,7 +721,6 @@ eirq_err: rst_err: kfree(shdev); -shdev_err: return err; } diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 5d524254499e..94260aa76aa3 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -275,7 +275,7 @@ static void log_irqs(u32 evt) !(evt & OHCI1394_busReset)) return; - fw_notify("IRQ %08x%s%s%s%s%s%s%s%s%s%s%s%s%s\n", evt, + fw_notify("IRQ %08x%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n", evt, evt & OHCI1394_selfIDComplete ? " selfID" : "", evt & OHCI1394_RQPkt ? " AR_req" : "", evt & OHCI1394_RSPkt ? " AR_resp" : "", @@ -286,6 +286,7 @@ static void log_irqs(u32 evt) evt & OHCI1394_postedWriteErr ? " postedWriteErr" : "", evt & OHCI1394_cycleTooLong ? " cycleTooLong" : "", evt & OHCI1394_cycle64Seconds ? " cycle64Seconds" : "", + evt & OHCI1394_cycleInconsistent ? " cycleInconsistent" : "", evt & OHCI1394_regAccessFail ? " regAccessFail" : "", evt & OHCI1394_busReset ? " busReset" : "", evt & ~(OHCI1394_selfIDComplete | OHCI1394_RQPkt | @@ -293,6 +294,7 @@ static void log_irqs(u32 evt) OHCI1394_respTxComplete | OHCI1394_isochRx | OHCI1394_isochTx | OHCI1394_postedWriteErr | OHCI1394_cycleTooLong | OHCI1394_cycle64Seconds | + OHCI1394_cycleInconsistent | OHCI1394_regAccessFail | OHCI1394_busReset) ? " ?" : ""); } @@ -1439,6 +1441,17 @@ static irqreturn_t irq_handler(int irq, void *data) OHCI1394_LinkControl_cycleMaster); } + if (unlikely(event & OHCI1394_cycleInconsistent)) { + /* + * We need to clear this event bit in order to make + * cycleMatch isochronous I/O work. In theory we should + * stop active cycleMatch iso contexts now and restart + * them at least two cycles later. (FIXME?) + */ + if (printk_ratelimit()) + fw_notify("isochronous cycle inconsistent\n"); + } + if (event & OHCI1394_cycle64Seconds) { cycle_time = reg_read(ohci, OHCI1394_IsochronousCycleTimer); if ((cycle_time & 0x80000000) == 0) @@ -1528,6 +1541,7 @@ static int ohci_enable(struct fw_card *card, u32 *config_rom, size_t length) OHCI1394_reqTxComplete | OHCI1394_respTxComplete | OHCI1394_isochRx | OHCI1394_isochTx | OHCI1394_postedWriteErr | OHCI1394_cycleTooLong | + OHCI1394_cycleInconsistent | OHCI1394_cycle64Seconds | OHCI1394_regAccessFail | OHCI1394_masterIntEnable); if (param_debug & OHCI_PARAM_DEBUG_BUSRESETS) @@ -1890,15 +1904,30 @@ static int handle_it_packet(struct context *context, { struct iso_context *ctx = container_of(context, struct iso_context, context); + int i; + struct descriptor *pd; - if (last->transfer_status == 0) - /* This descriptor isn't done yet, stop iteration. */ + for (pd = d; pd <= last; pd++) + if (pd->transfer_status) + break; + if (pd > last) + /* Descriptor(s) not done yet, stop iteration */ return 0; - if (le16_to_cpu(last->control) & DESCRIPTOR_IRQ_ALWAYS) + i = ctx->header_length; + if (i + 4 < PAGE_SIZE) { + /* Present this value as big-endian to match the receive code */ + *(__be32 *)(ctx->header + i) = cpu_to_be32( + ((u32)le16_to_cpu(pd->transfer_status) << 16) | + le16_to_cpu(pd->res_count)); + ctx->header_length += 4; + } + if (le16_to_cpu(last->control) & DESCRIPTOR_IRQ_ALWAYS) { ctx->base.callback(&ctx->base, le16_to_cpu(last->res_count), - 0, NULL, ctx->base.callback_data); - + ctx->header_length, ctx->header, + ctx->base.callback_data); + ctx->header_length = 0; + } return 1; } diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index f831ea159291..96eddd17e050 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -92,6 +92,7 @@ config DRM_I830 config DRM_I915 tristate "i915 driver" depends on AGP_INTEL + select SHMEM select DRM_KMS_HELPER select FB_CFB_FILLRECT select FB_CFB_COPYAREA diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index cea665d86dd3..b54ba63d506e 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -662,6 +662,12 @@ static struct drm_display_mode *drm_mode_detailed(struct drm_device *dev, return NULL; } + /* Some EDIDs have bogus h/vtotal values */ + if (mode->hsync_end > mode->htotal) + mode->htotal = mode->hsync_end + 1; + if (mode->vsync_end > mode->vtotal) + mode->vtotal = mode->vsync_end + 1; + drm_mode_set_name(mode); if (pt->misc & DRM_EDID_PT_INTERLACED) diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index dc8e374a0b55..65ef011fa8ba 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -599,7 +599,7 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var, struct drm_framebuffer *fb = fb_helper->fb; int depth; - if (var->pixclock == -1 || !var->pixclock) + if (var->pixclock != 0) return -EINVAL; /* Need to resize the fb object !!! */ @@ -691,7 +691,7 @@ int drm_fb_helper_set_par(struct fb_info *info) int ret; int i; - if (var->pixclock != -1) { + if (var->pixclock != 0) { DRM_ERROR("PIXEL CLCOK SET\n"); return -EINVAL; } @@ -904,7 +904,7 @@ int drm_fb_helper_single_fb_probe(struct drm_device *dev, fb_helper->fb = fb; if (new_fb) { - info->var.pixclock = -1; + info->var.pixclock = 0; if (register_framebuffer(info) < 0) return -EINVAL; } else { diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 80391995bdec..e9dbb481c469 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -552,7 +552,7 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_flags |= VM_RESERVED | VM_IO | VM_PFNMAP | VM_DONTEXPAND; vma->vm_ops = obj->dev->driver->gem_vm_ops; vma->vm_private_data = map->handle; - vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); + vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); /* Take a ref for this mapping of the object, so that the fault * handler can dereference the mmap offset's pointer to the object. diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index c861d80fd779..97dc5a4f0de4 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -103,6 +103,11 @@ static struct drm_mm_node *drm_mm_kmalloc(struct drm_mm *mm, int atomic) return child; } +/* drm_mm_pre_get() - pre allocate drm_mm_node structure + * drm_mm: memory manager struct we are pre-allocating for + * + * Returns 0 on success or -ENOMEM if allocation fails. + */ int drm_mm_pre_get(struct drm_mm *mm) { struct drm_mm_node *node; @@ -253,12 +258,14 @@ void drm_mm_put_block(struct drm_mm_node *cur) prev_node->size += next_node->size; list_del(&next_node->ml_entry); list_del(&next_node->fl_entry); + spin_lock(&mm->unused_lock); if (mm->num_unused < MM_UNUSED_TARGET) { list_add(&next_node->fl_entry, &mm->unused_nodes); ++mm->num_unused; } else kfree(next_node); + spin_unlock(&mm->unused_lock); } else { next_node->size += cur->size; next_node->start = cur->start; @@ -271,11 +278,13 @@ void drm_mm_put_block(struct drm_mm_node *cur) list_add(&cur->fl_entry, &mm->fl_entry); } else { list_del(&cur->ml_entry); + spin_lock(&mm->unused_lock); if (mm->num_unused < MM_UNUSED_TARGET) { list_add(&cur->fl_entry, &mm->unused_nodes); ++mm->num_unused; } else kfree(cur); + spin_unlock(&mm->unused_lock); } } diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index f8ce9a3a420d..26bf0552b3cb 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -267,10 +267,10 @@ static void i915_dump_pages(struct seq_file *m, struct page **pages, int page_co uint32_t *mem; for (page = 0; page < page_count; page++) { - mem = kmap(pages[page]); + mem = kmap_atomic(pages[page], KM_USER0); for (i = 0; i < PAGE_SIZE; i += 4) seq_printf(m, "%08x : %08x\n", i, mem[i / 4]); - kunmap(pages[page]); + kunmap_atomic(pages[page], KM_USER0); } } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 57204e298975..a725f6591192 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -296,6 +296,7 @@ typedef struct drm_i915_private { u32 saveVBLANK_A; u32 saveVSYNC_A; u32 saveBCLRPAT_A; + u32 saveTRANSACONF; u32 saveTRANS_HTOTAL_A; u32 saveTRANS_HBLANK_A; u32 saveTRANS_HSYNC_A; @@ -326,6 +327,7 @@ typedef struct drm_i915_private { u32 saveVBLANK_B; u32 saveVSYNC_B; u32 saveBCLRPAT_B; + u32 saveTRANSBCONF; u32 saveTRANS_HTOTAL_B; u32 saveTRANS_HBLANK_B; u32 saveTRANS_HSYNC_B; @@ -414,6 +416,16 @@ typedef struct drm_i915_private { u32 savePFB_WIN_SZ; u32 savePFA_WIN_POS; u32 savePFB_WIN_POS; + u32 savePCH_DREF_CONTROL; + u32 saveDISP_ARB_CTL; + u32 savePIPEA_DATA_M1; + u32 savePIPEA_DATA_N1; + u32 savePIPEA_LINK_M1; + u32 savePIPEA_LINK_N1; + u32 savePIPEB_DATA_M1; + u32 savePIPEB_DATA_N1; + u32 savePIPEB_LINK_M1; + u32 savePIPEB_LINK_N1; struct { struct drm_mm gtt_space; diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index c3ceffa46ea0..aa7fd82aa6eb 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -254,10 +254,15 @@ irqreturn_t igdng_irq_handler(struct drm_device *dev) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; int ret = IRQ_NONE; - u32 de_iir, gt_iir; + u32 de_iir, gt_iir, de_ier; u32 new_de_iir, new_gt_iir; struct drm_i915_master_private *master_priv; + /* disable master interrupt before clearing iir */ + de_ier = I915_READ(DEIER); + I915_WRITE(DEIER, de_ier & ~DE_MASTER_IRQ_CONTROL); + (void)I915_READ(DEIER); + de_iir = I915_READ(DEIIR); gt_iir = I915_READ(GTIIR); @@ -290,6 +295,9 @@ irqreturn_t igdng_irq_handler(struct drm_device *dev) gt_iir = new_gt_iir; } + I915_WRITE(DEIER, de_ier); + (void)I915_READ(DEIER); + return ret; } diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c index 992d5617e798..6eec8171a44e 100644 --- a/drivers/gpu/drm/i915/i915_suspend.c +++ b/drivers/gpu/drm/i915/i915_suspend.c @@ -239,6 +239,11 @@ static void i915_save_modeset_reg(struct drm_device *dev) if (drm_core_check_feature(dev, DRIVER_MODESET)) return; + if (IS_IGDNG(dev)) { + dev_priv->savePCH_DREF_CONTROL = I915_READ(PCH_DREF_CONTROL); + dev_priv->saveDISP_ARB_CTL = I915_READ(DISP_ARB_CTL); + } + /* Pipe & plane A info */ dev_priv->savePIPEACONF = I915_READ(PIPEACONF); dev_priv->savePIPEASRC = I915_READ(PIPEASRC); @@ -263,6 +268,11 @@ static void i915_save_modeset_reg(struct drm_device *dev) dev_priv->saveBCLRPAT_A = I915_READ(BCLRPAT_A); if (IS_IGDNG(dev)) { + dev_priv->savePIPEA_DATA_M1 = I915_READ(PIPEA_DATA_M1); + dev_priv->savePIPEA_DATA_N1 = I915_READ(PIPEA_DATA_N1); + dev_priv->savePIPEA_LINK_M1 = I915_READ(PIPEA_LINK_M1); + dev_priv->savePIPEA_LINK_N1 = I915_READ(PIPEA_LINK_N1); + dev_priv->saveFDI_TXA_CTL = I915_READ(FDI_TXA_CTL); dev_priv->saveFDI_RXA_CTL = I915_READ(FDI_RXA_CTL); @@ -270,6 +280,7 @@ static void i915_save_modeset_reg(struct drm_device *dev) dev_priv->savePFA_WIN_SZ = I915_READ(PFA_WIN_SZ); dev_priv->savePFA_WIN_POS = I915_READ(PFA_WIN_POS); + dev_priv->saveTRANSACONF = I915_READ(TRANSACONF); dev_priv->saveTRANS_HTOTAL_A = I915_READ(TRANS_HTOTAL_A); dev_priv->saveTRANS_HBLANK_A = I915_READ(TRANS_HBLANK_A); dev_priv->saveTRANS_HSYNC_A = I915_READ(TRANS_HSYNC_A); @@ -314,6 +325,11 @@ static void i915_save_modeset_reg(struct drm_device *dev) dev_priv->saveBCLRPAT_B = I915_READ(BCLRPAT_B); if (IS_IGDNG(dev)) { + dev_priv->savePIPEB_DATA_M1 = I915_READ(PIPEB_DATA_M1); + dev_priv->savePIPEB_DATA_N1 = I915_READ(PIPEB_DATA_N1); + dev_priv->savePIPEB_LINK_M1 = I915_READ(PIPEB_LINK_M1); + dev_priv->savePIPEB_LINK_N1 = I915_READ(PIPEB_LINK_N1); + dev_priv->saveFDI_TXB_CTL = I915_READ(FDI_TXB_CTL); dev_priv->saveFDI_RXB_CTL = I915_READ(FDI_RXB_CTL); @@ -321,6 +337,7 @@ static void i915_save_modeset_reg(struct drm_device *dev) dev_priv->savePFB_WIN_SZ = I915_READ(PFB_WIN_SZ); dev_priv->savePFB_WIN_POS = I915_READ(PFB_WIN_POS); + dev_priv->saveTRANSBCONF = I915_READ(TRANSBCONF); dev_priv->saveTRANS_HTOTAL_B = I915_READ(TRANS_HTOTAL_B); dev_priv->saveTRANS_HBLANK_B = I915_READ(TRANS_HBLANK_B); dev_priv->saveTRANS_HSYNC_B = I915_READ(TRANS_HSYNC_B); @@ -368,6 +385,11 @@ static void i915_restore_modeset_reg(struct drm_device *dev) fpb1_reg = FPB1; } + if (IS_IGDNG(dev)) { + I915_WRITE(PCH_DREF_CONTROL, dev_priv->savePCH_DREF_CONTROL); + I915_WRITE(DISP_ARB_CTL, dev_priv->saveDISP_ARB_CTL); + } + /* Pipe & plane A info */ /* Prime the clock */ if (dev_priv->saveDPLL_A & DPLL_VCO_ENABLE) { @@ -395,6 +417,11 @@ static void i915_restore_modeset_reg(struct drm_device *dev) I915_WRITE(BCLRPAT_A, dev_priv->saveBCLRPAT_A); if (IS_IGDNG(dev)) { + I915_WRITE(PIPEA_DATA_M1, dev_priv->savePIPEA_DATA_M1); + I915_WRITE(PIPEA_DATA_N1, dev_priv->savePIPEA_DATA_N1); + I915_WRITE(PIPEA_LINK_M1, dev_priv->savePIPEA_LINK_M1); + I915_WRITE(PIPEA_LINK_N1, dev_priv->savePIPEA_LINK_N1); + I915_WRITE(FDI_RXA_CTL, dev_priv->saveFDI_RXA_CTL); I915_WRITE(FDI_TXA_CTL, dev_priv->saveFDI_TXA_CTL); @@ -402,6 +429,7 @@ static void i915_restore_modeset_reg(struct drm_device *dev) I915_WRITE(PFA_WIN_SZ, dev_priv->savePFA_WIN_SZ); I915_WRITE(PFA_WIN_POS, dev_priv->savePFA_WIN_POS); + I915_WRITE(TRANSACONF, dev_priv->saveTRANSACONF); I915_WRITE(TRANS_HTOTAL_A, dev_priv->saveTRANS_HTOTAL_A); I915_WRITE(TRANS_HBLANK_A, dev_priv->saveTRANS_HBLANK_A); I915_WRITE(TRANS_HSYNC_A, dev_priv->saveTRANS_HSYNC_A); @@ -439,7 +467,7 @@ static void i915_restore_modeset_reg(struct drm_device *dev) /* Actually enable it */ I915_WRITE(dpll_b_reg, dev_priv->saveDPLL_B); DRM_UDELAY(150); - if (IS_I965G(dev)) + if (IS_I965G(dev) && !IS_IGDNG(dev)) I915_WRITE(DPLL_B_MD, dev_priv->saveDPLL_B_MD); DRM_UDELAY(150); @@ -454,6 +482,11 @@ static void i915_restore_modeset_reg(struct drm_device *dev) I915_WRITE(BCLRPAT_B, dev_priv->saveBCLRPAT_B); if (IS_IGDNG(dev)) { + I915_WRITE(PIPEB_DATA_M1, dev_priv->savePIPEB_DATA_M1); + I915_WRITE(PIPEB_DATA_N1, dev_priv->savePIPEB_DATA_N1); + I915_WRITE(PIPEB_LINK_M1, dev_priv->savePIPEB_LINK_M1); + I915_WRITE(PIPEB_LINK_N1, dev_priv->savePIPEB_LINK_N1); + I915_WRITE(FDI_RXB_CTL, dev_priv->saveFDI_RXB_CTL); I915_WRITE(FDI_TXB_CTL, dev_priv->saveFDI_TXB_CTL); @@ -461,6 +494,7 @@ static void i915_restore_modeset_reg(struct drm_device *dev) I915_WRITE(PFB_WIN_SZ, dev_priv->savePFB_WIN_SZ); I915_WRITE(PFB_WIN_POS, dev_priv->savePFB_WIN_POS); + I915_WRITE(TRANSBCONF, dev_priv->saveTRANSBCONF); I915_WRITE(TRANS_HTOTAL_B, dev_priv->saveTRANS_HTOTAL_B); I915_WRITE(TRANS_HBLANK_B, dev_priv->saveTRANS_HBLANK_B); I915_WRITE(TRANS_HSYNC_B, dev_priv->saveTRANS_HSYNC_B); diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 212e22740fc1..e5051446c48e 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -262,8 +262,8 @@ static bool intel_crt_detect_hotplug(struct drm_connector *connector) } while (time_after(timeout, jiffies)); } - if ((I915_READ(PORT_HOTPLUG_STAT) & CRT_HOTPLUG_MONITOR_MASK) == - CRT_HOTPLUG_MONITOR_COLOR) + if ((I915_READ(PORT_HOTPLUG_STAT) & CRT_HOTPLUG_MONITOR_MASK) != + CRT_HOTPLUG_MONITOR_NONE) return true; return false; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 3ba6546b7c7f..099f420de57a 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -863,10 +863,8 @@ intel_igdng_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; intel_clock_t clock; - int max_n; - bool found; int err_most = 47; - found = false; + int err_min = 10000; /* eDP has only 2 clock choice, no n/m/p setting */ if (HAS_eDP) @@ -890,10 +888,9 @@ intel_igdng_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, } memset(best_clock, 0, sizeof(*best_clock)); - max_n = limit->n.max; for (clock.p1 = limit->p1.max; clock.p1 >= limit->p1.min; clock.p1--) { /* based on hardware requriment prefer smaller n to precision */ - for (clock.n = limit->n.min; clock.n <= max_n; clock.n++) { + for (clock.n = limit->n.min; clock.n <= limit->n.max; clock.n++) { /* based on hardware requirment prefere larger m1,m2 */ for (clock.m1 = limit->m1.max; clock.m1 >= limit->m1.min; clock.m1--) { @@ -907,18 +904,18 @@ intel_igdng_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, this_err = abs((10000 - (target*10000/clock.dot))); if (this_err < err_most) { *best_clock = clock; - err_most = this_err; - max_n = clock.n; - found = true; /* found on first matching */ goto out; + } else if (this_err < err_min) { + *best_clock = clock; + err_min = this_err; } } } } } out: - return found; + return true; } /* DisplayPort has only two frequencies, 162MHz and 270MHz */ diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 663ab6de0b58..c33451aec1bd 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -77,14 +77,32 @@ static void intel_hdmi_dpms(struct drm_encoder *encoder, int mode) struct intel_hdmi_priv *hdmi_priv = intel_output->dev_priv; u32 temp; - if (mode != DRM_MODE_DPMS_ON) { - temp = I915_READ(hdmi_priv->sdvox_reg); + temp = I915_READ(hdmi_priv->sdvox_reg); + + /* HW workaround, need to toggle enable bit off and on for 12bpc, but + * we do this anyway which shows more stable in testing. + */ + if (IS_IGDNG(dev)) { I915_WRITE(hdmi_priv->sdvox_reg, temp & ~SDVO_ENABLE); + POSTING_READ(hdmi_priv->sdvox_reg); + } + + if (mode != DRM_MODE_DPMS_ON) { + temp &= ~SDVO_ENABLE; } else { - temp = I915_READ(hdmi_priv->sdvox_reg); - I915_WRITE(hdmi_priv->sdvox_reg, temp | SDVO_ENABLE); + temp |= SDVO_ENABLE; } + + I915_WRITE(hdmi_priv->sdvox_reg, temp); POSTING_READ(hdmi_priv->sdvox_reg); + + /* HW workaround, need to write this twice for issue that may result + * in first write getting masked. + */ + if (IS_IGDNG(dev)) { + I915_WRITE(hdmi_priv->sdvox_reg, temp); + POSTING_READ(hdmi_priv->sdvox_reg); + } } static void intel_hdmi_save(struct drm_connector *connector) diff --git a/drivers/gpu/drm/radeon/atom.c b/drivers/gpu/drm/radeon/atom.c index 901befe03da2..d67c42555ab9 100644 --- a/drivers/gpu/drm/radeon/atom.c +++ b/drivers/gpu/drm/radeon/atom.c @@ -107,6 +107,7 @@ static uint32_t atom_iio_execute(struct atom_context *ctx, int base, base += 3; break; case ATOM_IIO_WRITE: + (void)ctx->card->reg_read(ctx->card, CU16(base + 1)); ctx->card->reg_write(ctx->card, CU16(base + 1), temp); base += 3; break; diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 757f5cd37744..224506a2f7b1 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -519,6 +519,7 @@ typedef int (*radeon_packet3_check_t)(struct radeon_cs_parser *p, * AGP */ int radeon_agp_init(struct radeon_device *rdev); +void radeon_agp_resume(struct radeon_device *rdev); void radeon_agp_fini(struct radeon_device *rdev); diff --git a/drivers/gpu/drm/radeon/radeon_agp.c b/drivers/gpu/drm/radeon/radeon_agp.c index 23ea9955ac59..54bf49a6d676 100644 --- a/drivers/gpu/drm/radeon/radeon_agp.c +++ b/drivers/gpu/drm/radeon/radeon_agp.c @@ -237,6 +237,18 @@ int radeon_agp_init(struct radeon_device *rdev) #endif } +void radeon_agp_resume(struct radeon_device *rdev) +{ +#if __OS_HAS_AGP + int r; + if (rdev->flags & RADEON_IS_AGP) { + r = radeon_agp_init(rdev); + if (r) + dev_warn(rdev->dev, "radeon AGP reinit failed\n"); + } +#endif +} + void radeon_agp_fini(struct radeon_device *rdev) { #if __OS_HAS_AGP diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index fce4c4087fda..29763ceae3af 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -566,8 +566,9 @@ static enum drm_connector_status radeon_vga_detect(struct drm_connector *connect radeon_i2c_do_lock(radeon_connector, 0); if (!radeon_connector->edid) { - DRM_ERROR("DDC responded but not EDID found for %s\n", - drm_get_connector_name(connector)); + DRM_ERROR("%s: probed a monitor but no|invalid EDID\n", + drm_get_connector_name(connector)); + ret = connector_status_connected; } else { radeon_connector->use_digital = !!(radeon_connector->edid->input & DRM_EDID_INPUT_DIGITAL); @@ -720,8 +721,8 @@ static enum drm_connector_status radeon_dvi_detect(struct drm_connector *connect radeon_i2c_do_lock(radeon_connector, 0); if (!radeon_connector->edid) { - DRM_ERROR("DDC responded but not EDID found for %s\n", - drm_get_connector_name(connector)); + DRM_ERROR("%s: probed a monitor but no|invalid EDID\n", + drm_get_connector_name(connector)); } else { radeon_connector->use_digital = !!(radeon_connector->edid->input & DRM_EDID_INPUT_DIGITAL); @@ -1149,6 +1150,13 @@ radeon_add_legacy_connector(struct drm_device *dev, if (ret) goto failed; radeon_connector->dac_load_detect = true; + /* RS400,RC410,RS480 chipset seems to report a lot + * of false positive on load detect, we haven't yet + * found a way to make load detect reliable on those + * chipset, thus just disable it for TV. + */ + if (rdev->family == CHIP_RS400 || rdev->family == CHIP_RS480) + radeon_connector->dac_load_detect = false; drm_connector_attach_property(&radeon_connector->base, rdev->mode_info.load_detect_property, 1); diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index e3f9edfa40fe..41bb76fbe734 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -688,6 +688,8 @@ int radeon_resume_kms(struct drm_device *dev) return -1; } pci_set_master(dev->pdev); + /* resume AGP if in use */ + radeon_agp_resume(rdev); radeon_resume(rdev); radeon_restore_bios_scratch_regs(rdev); fb_set_suspend(rdev->fbdev_info, 0); diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c index 7935f793bf62..ba68c9fe90a1 100644 --- a/drivers/gpu/drm/radeon/rv515.c +++ b/drivers/gpu/drm/radeon/rv515.c @@ -137,8 +137,6 @@ int rv515_mc_wait_for_idle(struct radeon_device *rdev) void rv515_vga_render_disable(struct radeon_device *rdev) { - WREG32(R_000330_D1VGA_CONTROL, 0); - WREG32(R_000338_D2VGA_CONTROL, 0); WREG32(R_000300_VGA_RENDER_CONTROL, RREG32(R_000300_VGA_RENDER_CONTROL) & C_000300_VGA_VSTATUS_CNTL); } @@ -382,7 +380,6 @@ void rv515_mc_stop(struct radeon_device *rdev, struct rv515_mc_save *save) save->d2crtc_control = RREG32(R_006880_D2CRTC_CONTROL); /* Stop all video */ - WREG32(R_000330_D1VGA_CONTROL, 0); WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 0); WREG32(R_000300_VGA_RENDER_CONTROL, 0); WREG32(R_0060E8_D1CRTC_UPDATE_LOCK, 1); @@ -391,6 +388,8 @@ void rv515_mc_stop(struct radeon_device *rdev, struct rv515_mc_save *save) WREG32(R_006880_D2CRTC_CONTROL, 0); WREG32(R_0060E8_D1CRTC_UPDATE_LOCK, 0); WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 0); + WREG32(R_000330_D1VGA_CONTROL, 0); + WREG32(R_000338_D2VGA_CONTROL, 0); } void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save) @@ -404,14 +403,14 @@ void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save) WREG32(R_000328_VGA_HDP_CONTROL, save->vga_hdp_control); mdelay(1); /* Restore video state */ + WREG32(R_000330_D1VGA_CONTROL, save->d1vga_control); + WREG32(R_000338_D2VGA_CONTROL, save->d2vga_control); WREG32(R_0060E8_D1CRTC_UPDATE_LOCK, 1); WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 1); WREG32(R_006080_D1CRTC_CONTROL, save->d1crtc_control); WREG32(R_006880_D2CRTC_CONTROL, save->d2crtc_control); WREG32(R_0060E8_D1CRTC_UPDATE_LOCK, 0); WREG32(R_0068E8_D2CRTC_UPDATE_LOCK, 0); - WREG32(R_000330_D1VGA_CONTROL, save->d1vga_control); - WREG32(R_000338_D2VGA_CONTROL, save->d2vga_control); WREG32(R_000300_VGA_RENDER_CONTROL, save->vga_render_control); } diff --git a/drivers/i2c/busses/i2c-pnx.c b/drivers/i2c/busses/i2c-pnx.c index 6ff6c20f1e78..fbab6846ae64 100644 --- a/drivers/i2c/busses/i2c-pnx.c +++ b/drivers/i2c/busses/i2c-pnx.c @@ -19,7 +19,9 @@ #include <linux/completion.h> #include <linux/platform_device.h> #include <linux/i2c-pnx.h> +#include <linux/io.h> #include <mach/hardware.h> +#include <mach/i2c.h> #include <asm/irq.h> #include <asm/uaccess.h> @@ -54,6 +56,9 @@ static inline void i2c_pnx_arm_timer(struct i2c_adapter *adap) struct timer_list *timer = &data->mif.timer; int expires = I2C_PNX_TIMEOUT / (1000 / HZ); + if (expires <= 1) + expires = 2; + del_timer_sync(timer); dev_dbg(&adap->dev, "Timer armed at %lu plus %u jiffies.\n", @@ -645,7 +650,7 @@ static int __devinit i2c_pnx_probe(struct platform_device *pdev) return 0; out_irq: - free_irq(alg_data->irq, alg_data); + free_irq(alg_data->irq, i2c_pnx->adapter); out_clock: i2c_pnx->set_clock_stop(pdev); out_unmap: @@ -664,7 +669,7 @@ static int __devexit i2c_pnx_remove(struct platform_device *pdev) struct i2c_adapter *adap = i2c_pnx->adapter; struct i2c_pnx_algo_data *alg_data = adap->algo_data; - free_irq(alg_data->irq, alg_data); + free_irq(alg_data->irq, i2c_pnx->adapter); i2c_del_adapter(adap); i2c_pnx->set_clock_stop(pdev); iounmap((void *)alg_data->ioaddr); diff --git a/drivers/i2c/chips/tsl2550.c b/drivers/i2c/chips/tsl2550.c index aa96bd2d27ea..a0702f36a72f 100644 --- a/drivers/i2c/chips/tsl2550.c +++ b/drivers/i2c/chips/tsl2550.c @@ -257,6 +257,7 @@ static DEVICE_ATTR(operating_mode, S_IWUSR | S_IRUGO, static ssize_t __tsl2550_show_lux(struct i2c_client *client, char *buf) { + struct tsl2550_data *data = i2c_get_clientdata(client); u8 ch0, ch1; int ret; @@ -274,6 +275,8 @@ static ssize_t __tsl2550_show_lux(struct i2c_client *client, char *buf) ret = tsl2550_calculate_lux(ch0, ch1); if (ret < 0) return ret; + if (data->operating_mode == 1) + ret *= 5; return sprintf(buf, "%d\n", ret); } diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index 8d80fceca6a4..296504355142 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -762,6 +762,7 @@ int i2c_del_adapter(struct i2c_adapter *adap) { int res = 0; struct i2c_adapter *found; + struct i2c_client *client, *next; /* First make sure that this adapter was ever added */ mutex_lock(&core_lock); @@ -781,6 +782,16 @@ int i2c_del_adapter(struct i2c_adapter *adap) if (res) return res; + /* Remove devices instantiated from sysfs */ + list_for_each_entry_safe(client, next, &userspace_devices, detected) { + if (client->adapter == adap) { + dev_dbg(&adap->dev, "Removing %s at 0x%x\n", + client->name, client->addr); + list_del(&client->detected); + i2c_unregister_device(client); + } + } + /* Detach any active clients. This can't fail, thus we do not checking the returned value. */ res = device_for_each_child(&adap->dev, NULL, __unregister_client); diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c index d3440b5010a5..6e7ae2b6cfc6 100644 --- a/drivers/ide/ide-ioctls.c +++ b/drivers/ide/ide-ioctls.c @@ -162,7 +162,7 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg) if (tf->command == ATA_CMD_SET_FEATURES && tf->feature == SETFEATURES_XFER && tf->nsect >= XFER_SW_DMA_0) { - xfer_rate = ide_find_dma_mode(drive, XFER_UDMA_6); + xfer_rate = ide_find_dma_mode(drive, tf->nsect); if (xfer_rate != tf->nsect) { err = -EINVAL; goto abort; diff --git a/drivers/ieee802154/fakehard.c b/drivers/ieee802154/fakehard.c index 617549f30ef9..d9d0e13efe47 100644 --- a/drivers/ieee802154/fakehard.c +++ b/drivers/ieee802154/fakehard.c @@ -282,15 +282,12 @@ static int ieee802154_fake_close(struct net_device *dev) static netdev_tx_t ieee802154_fake_xmit(struct sk_buff *skb, struct net_device *dev) { - skb->skb_iif = dev->ifindex; - skb->dev = dev; dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; - dev->trans_start = jiffies; - /* FIXME: do hardware work here ... */ + dev_kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/drivers/media/common/ir-functions.c b/drivers/media/common/ir-functions.c index 655474b29e21..abd4791acb0e 100644 --- a/drivers/media/common/ir-functions.c +++ b/drivers/media/common/ir-functions.c @@ -64,7 +64,7 @@ void ir_input_init(struct input_dev *dev, struct ir_input_state *ir, ir->ir_type = ir_type; - memset(ir->ir_codes, sizeof(ir->ir_codes), 0); + memset(ir->ir_codes, 0, sizeof(ir->ir_codes)); /* * FIXME: This is a temporary workaround to use the new IR tables diff --git a/drivers/media/dvb/dvb-usb/cxusb.c b/drivers/media/dvb/dvb-usb/cxusb.c index f65591fb7cec..2a53dd096eef 100644 --- a/drivers/media/dvb/dvb-usb/cxusb.c +++ b/drivers/media/dvb/dvb-usb/cxusb.c @@ -663,6 +663,14 @@ static struct zl10353_config cxusb_zl10353_xc3028_config = { .parallel_ts = 1, }; +static struct zl10353_config cxusb_zl10353_xc3028_config_no_i2c_gate = { + .demod_address = 0x0f, + .if2 = 45600, + .no_tuner = 1, + .parallel_ts = 1, + .disable_i2c_gate_ctrl = 1, +}; + static struct mt352_config cxusb_mt352_xc3028_config = { .demod_address = 0x0f, .if2 = 4560, @@ -894,7 +902,7 @@ static int cxusb_dualdig4_frontend_attach(struct dvb_usb_adapter *adap) cxusb_bluebird_gpio_pulse(adap->dev, 0x02, 1); if ((adap->fe = dvb_attach(zl10353_attach, - &cxusb_zl10353_xc3028_config, + &cxusb_zl10353_xc3028_config_no_i2c_gate, &adap->dev->i2c_adap)) == NULL) return -EIO; diff --git a/drivers/media/dvb/siano/Kconfig b/drivers/media/dvb/siano/Kconfig index 8c1aed77ea30..85a222c4eaa0 100644 --- a/drivers/media/dvb/siano/Kconfig +++ b/drivers/media/dvb/siano/Kconfig @@ -4,7 +4,7 @@ config SMS_SIANO_MDTV tristate "Siano SMS1xxx based MDTV receiver" - depends on DVB_CORE && INPUT + depends on DVB_CORE && INPUT && HAS_DMA ---help--- Choose Y or M here if you have MDTV receiver with a Siano chipset. diff --git a/drivers/media/radio/radio-gemtek-pci.c b/drivers/media/radio/radio-gemtek-pci.c index c3f579de6e71..c6cf11661868 100644 --- a/drivers/media/radio/radio-gemtek-pci.c +++ b/drivers/media/radio/radio-gemtek-pci.c @@ -181,12 +181,10 @@ static void gemtek_pci_mute(struct gemtek_pci *card) static void gemtek_pci_unmute(struct gemtek_pci *card) { - mutex_lock(&card->lock); if (card->mute) { gemtek_pci_setfrequency(card, card->current_frequency); card->mute = false; } - mutex_unlock(&card->lock); } static int gemtek_pci_getsignal(struct gemtek_pci *card) diff --git a/drivers/media/video/davinci/vpif_display.c b/drivers/media/video/davinci/vpif_display.c index c015da813dda..d14cfb200ed0 100644 --- a/drivers/media/video/davinci/vpif_display.c +++ b/drivers/media/video/davinci/vpif_display.c @@ -1426,7 +1426,6 @@ static __init int vpif_probe(struct platform_device *pdev) struct vpif_display_config *config; int i, j = 0, k, q, m, err = 0; struct i2c_adapter *i2c_adap; - struct vpif_config *config; struct common_obj *common; struct channel_obj *ch; struct video_device *vfd; diff --git a/drivers/media/video/em28xx/em28xx-cards.c b/drivers/media/video/em28xx/em28xx-cards.c index bdb249bd9d5d..c0fd5c6feeac 100644 --- a/drivers/media/video/em28xx/em28xx-cards.c +++ b/drivers/media/video/em28xx/em28xx-cards.c @@ -1584,8 +1584,8 @@ struct em28xx_board em28xx_boards[] = { [EM2870_BOARD_REDDO_DVB_C_USB_BOX] = { .name = "Reddo DVB-C USB TV Box", .tuner_type = TUNER_ABSENT, + .tuner_gpio = reddo_dvb_c_usb_box, .has_dvb = 1, - .dvb_gpio = reddo_dvb_c_usb_box, }, }; const unsigned int em28xx_bcount = ARRAY_SIZE(em28xx_boards); diff --git a/drivers/media/video/mx1_camera.c b/drivers/media/video/mx1_camera.c index 5f37952c75cf..72802291e812 100644 --- a/drivers/media/video/mx1_camera.c +++ b/drivers/media/video/mx1_camera.c @@ -28,6 +28,7 @@ #include <linux/moduleparam.h> #include <linux/mutex.h> #include <linux/platform_device.h> +#include <linux/sched.h> #include <linux/time.h> #include <linux/version.h> #include <linux/videodev2.h> diff --git a/drivers/media/video/mx3_camera.c b/drivers/media/video/mx3_camera.c index dff2e5e2d8c6..7db82bdf6f31 100644 --- a/drivers/media/video/mx3_camera.c +++ b/drivers/media/video/mx3_camera.c @@ -17,6 +17,7 @@ #include <linux/clk.h> #include <linux/vmalloc.h> #include <linux/interrupt.h> +#include <linux/sched.h> #include <media/v4l2-common.h> #include <media/v4l2-dev.h> diff --git a/drivers/media/video/sh_mobile_ceu_camera.c b/drivers/media/video/sh_mobile_ceu_camera.c index 2f78b4f263f5..9c8b7c7b89ee 100644 --- a/drivers/media/video/sh_mobile_ceu_camera.c +++ b/drivers/media/video/sh_mobile_ceu_camera.c @@ -31,6 +31,7 @@ #include <linux/platform_device.h> #include <linux/videodev2.h> #include <linux/pm_runtime.h> +#include <linux/sched.h> #include <media/v4l2-common.h> #include <media/v4l2-dev.h> @@ -1723,11 +1724,12 @@ static int __devinit sh_mobile_ceu_probe(struct platform_device *pdev) err = soc_camera_host_register(&pcdev->ici); if (err) - goto exit_free_irq; + goto exit_free_clk; return 0; -exit_free_irq: +exit_free_clk: + pm_runtime_disable(&pdev->dev); free_irq(pcdev->irq, pcdev); exit_release_mem: if (platform_get_resource(pdev, IORESOURCE_MEM, 1)) @@ -1747,6 +1749,7 @@ static int __devexit sh_mobile_ceu_remove(struct platform_device *pdev) struct sh_mobile_ceu_dev, ici); soc_camera_host_unregister(soc_host); + pm_runtime_disable(&pdev->dev); free_irq(pcdev->irq, pcdev); if (platform_get_resource(pdev, IORESOURCE_MEM, 1)) dma_release_declared_memory(&pdev->dev); diff --git a/drivers/media/video/soc_camera.c b/drivers/media/video/soc_camera.c index 36e617bd13c7..95fdeb23c2c1 100644 --- a/drivers/media/video/soc_camera.c +++ b/drivers/media/video/soc_camera.c @@ -1097,6 +1097,13 @@ static int default_s_crop(struct soc_camera_device *icd, struct v4l2_crop *a) return v4l2_subdev_call(sd, video, s_crop, a); } +static void soc_camera_device_init(struct device *dev, void *pdata) +{ + dev->platform_data = pdata; + dev->bus = &soc_camera_bus_type; + dev->release = dummy_release; +} + int soc_camera_host_register(struct soc_camera_host *ici) { struct soc_camera_host *ix; @@ -1158,6 +1165,7 @@ void soc_camera_host_unregister(struct soc_camera_host *ici) list_for_each_entry(icd, &devices, list) { if (icd->iface == ici->nr) { + void *pdata = icd->dev.platform_data; /* The bus->remove will be called */ device_unregister(&icd->dev); /* @@ -1169,6 +1177,7 @@ void soc_camera_host_unregister(struct soc_camera_host *ici) * device private data. */ memset(&icd->dev, 0, sizeof(icd->dev)); + soc_camera_device_init(&icd->dev, pdata); } } @@ -1200,10 +1209,7 @@ static int soc_camera_device_register(struct soc_camera_device *icd) * man, stay reasonable... */ return -ENOMEM; - icd->devnum = num; - icd->dev.bus = &soc_camera_bus_type; - - icd->dev.release = dummy_release; + icd->devnum = num; icd->use_count = 0; icd->host_priv = NULL; mutex_init(&icd->video_lock); @@ -1311,12 +1317,13 @@ static int __devinit soc_camera_pdrv_probe(struct platform_device *pdev) icd->iface = icl->bus_id; icd->pdev = &pdev->dev; platform_set_drvdata(pdev, icd); - icd->dev.platform_data = icl; ret = soc_camera_device_register(icd); if (ret < 0) goto escdevreg; + soc_camera_device_init(&icd->dev, icl); + icd->user_width = DEFAULT_WIDTH; icd->user_height = DEFAULT_HEIGHT; diff --git a/drivers/media/video/videobuf-dma-contig.c b/drivers/media/video/videobuf-dma-contig.c index 635ffc7b0391..c3065c4bcba9 100644 --- a/drivers/media/video/videobuf-dma-contig.c +++ b/drivers/media/video/videobuf-dma-contig.c @@ -19,6 +19,7 @@ #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/dma-mapping.h> +#include <linux/sched.h> #include <media/videobuf-dma-contig.h> struct videobuf_dma_contig_memory { diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index db39f4a52f53..2cb2736d65aa 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -158,6 +158,7 @@ static ssize_t at24_eeprom_read(struct at24_data *at24, char *buf, struct i2c_msg msg[2]; u8 msgbuf[2]; struct i2c_client *client; + unsigned long timeout, read_time; int status, i; memset(msg, 0, sizeof(msg)); @@ -183,47 +184,60 @@ static ssize_t at24_eeprom_read(struct at24_data *at24, char *buf, if (count > io_limit) count = io_limit; - /* Smaller eeproms can work given some SMBus extension calls */ if (at24->use_smbus) { + /* Smaller eeproms can work given some SMBus extension calls */ if (count > I2C_SMBUS_BLOCK_MAX) count = I2C_SMBUS_BLOCK_MAX; - status = i2c_smbus_read_i2c_block_data(client, offset, - count, buf); - dev_dbg(&client->dev, "smbus read %zu@%d --> %d\n", - count, offset, status); - return (status < 0) ? -EIO : status; + } else { + /* + * When we have a better choice than SMBus calls, use a + * combined I2C message. Write address; then read up to + * io_limit data bytes. Note that read page rollover helps us + * here (unlike writes). msgbuf is u8 and will cast to our + * needs. + */ + i = 0; + if (at24->chip.flags & AT24_FLAG_ADDR16) + msgbuf[i++] = offset >> 8; + msgbuf[i++] = offset; + + msg[0].addr = client->addr; + msg[0].buf = msgbuf; + msg[0].len = i; + + msg[1].addr = client->addr; + msg[1].flags = I2C_M_RD; + msg[1].buf = buf; + msg[1].len = count; } /* - * When we have a better choice than SMBus calls, use a combined - * I2C message. Write address; then read up to io_limit data bytes. - * Note that read page rollover helps us here (unlike writes). - * msgbuf is u8 and will cast to our needs. + * Reads fail if the previous write didn't complete yet. We may + * loop a few times until this one succeeds, waiting at least + * long enough for one entire page write to work. */ - i = 0; - if (at24->chip.flags & AT24_FLAG_ADDR16) - msgbuf[i++] = offset >> 8; - msgbuf[i++] = offset; - - msg[0].addr = client->addr; - msg[0].buf = msgbuf; - msg[0].len = i; + timeout = jiffies + msecs_to_jiffies(write_timeout); + do { + read_time = jiffies; + if (at24->use_smbus) { + status = i2c_smbus_read_i2c_block_data(client, offset, + count, buf); + } else { + status = i2c_transfer(client->adapter, msg, 2); + if (status == 2) + status = count; + } + dev_dbg(&client->dev, "read %zu@%d --> %d (%ld)\n", + count, offset, status, jiffies); - msg[1].addr = client->addr; - msg[1].flags = I2C_M_RD; - msg[1].buf = buf; - msg[1].len = count; + if (status == count) + return count; - status = i2c_transfer(client->adapter, msg, 2); - dev_dbg(&client->dev, "i2c read %zu@%d --> %d\n", - count, offset, status); + /* REVISIT: at HZ=100, this is sloooow */ + msleep(1); + } while (time_before(read_time, timeout)); - if (status == 2) - return count; - else if (status >= 0) - return -EIO; - else - return status; + return -ETIMEDOUT; } static ssize_t at24_read(struct at24_data *at24, diff --git a/drivers/net/3c501.c b/drivers/net/3c501.c index 62ceb2b4820c..4d4cad393dce 100644 --- a/drivers/net/3c501.c +++ b/drivers/net/3c501.c @@ -249,11 +249,11 @@ static int __init el1_probe1(struct net_device *dev, int ioaddr) * for the Sager NP943 prefix. */ - if (station_addr[0] == 0x02 && station_addr[1] == 0x60 - && station_addr[2] == 0x8c) + if (station_addr[0] == 0x02 && station_addr[1] == 0x60 && + station_addr[2] == 0x8c) mname = "3c501"; - else if (station_addr[0] == 0x00 && station_addr[1] == 0x80 - && station_addr[2] == 0xC8) + else if (station_addr[0] == 0x00 && station_addr[1] == 0x80 && + station_addr[2] == 0xC8) mname = "NP943"; else { release_region(ioaddr, EL1_IO_EXTENT); diff --git a/drivers/net/3c503.c b/drivers/net/3c503.c index c71e12d05f6e..66e0323c1839 100644 --- a/drivers/net/3c503.c +++ b/drivers/net/3c503.c @@ -214,8 +214,8 @@ el2_probe1(struct net_device *dev, int ioaddr) iobase_reg = inb(ioaddr+0x403); membase_reg = inb(ioaddr+0x404); /* ASIC location registers should be 0 or have only a single bit set. */ - if ( (iobase_reg & (iobase_reg - 1)) - || (membase_reg & (membase_reg - 1))) { + if ((iobase_reg & (iobase_reg - 1)) || + (membase_reg & (membase_reg - 1))) { retval = -ENODEV; goto out1; } @@ -291,8 +291,8 @@ el2_probe1(struct net_device *dev, int ioaddr) writel(0xba5eba5e, mem_base); for (i = sizeof(test_val); i < EL2_MEMSIZE; i+=sizeof(test_val)) { writel(test_val, mem_base + i); - if (readl(mem_base) != 0xba5eba5e - || readl(mem_base + i) != test_val) { + if (readl(mem_base) != 0xba5eba5e || + readl(mem_base + i) != test_val) { pr_warning("3c503: memory failure or memory address conflict.\n"); dev->mem_start = 0; ei_status.name = "3c503-PIO"; @@ -397,9 +397,10 @@ el2_open(struct net_device *dev) unsigned long cookie = probe_irq_on(); outb_p(0x04 << ((*irqp == 9) ? 2 : *irqp), E33G_IDCFR); outb_p(0x00, E33G_IDCFR); - if (*irqp == probe_irq_off(cookie) /* It's a good IRQ line! */ - && ((retval = request_irq(dev->irq = *irqp, - eip_interrupt, 0, dev->name, dev)) == 0)) + if (*irqp == probe_irq_off(cookie) && /* It's a good IRQ line! */ + ((retval = request_irq(dev->irq = *irqp, + eip_interrupt, 0, + dev->name, dev)) == 0)) break; } else { if (retval != -EBUSY) diff --git a/drivers/net/3c507.c b/drivers/net/3c507.c index 605f1d17a8f3..fbc231153e55 100644 --- a/drivers/net/3c507.c +++ b/drivers/net/3c507.c @@ -836,8 +836,8 @@ static void el16_rx(struct net_device *dev) void __iomem *data_frame = lp->base + data_buffer_addr; ushort pkt_len = readw(data_frame); - if (rfd_cmd != 0 || data_buffer_addr != rx_head + 22 - || (pkt_len & 0xC000) != 0xC000) { + if (rfd_cmd != 0 || data_buffer_addr != rx_head + 22 || + (pkt_len & 0xC000) != 0xC000) { pr_err("%s: Rx frame at %#x corrupted, " "status %04x cmd %04x next %04x " "data-buf @%04x %04x.\n", diff --git a/drivers/net/3c509.c b/drivers/net/3c509.c index 8d4ce0964073..9d85efce5916 100644 --- a/drivers/net/3c509.c +++ b/drivers/net/3c509.c @@ -253,9 +253,9 @@ static int el3_isa_id_sequence(__be16 *phys_addr) This check is needed in order not to register them twice. */ for (i = 0; i < el3_cards; i++) { struct el3_private *lp = netdev_priv(el3_devs[i]); - if (lp->type == EL3_PNP - && !memcmp(phys_addr, el3_devs[i]->dev_addr, - ETH_ALEN)) { + if (lp->type == EL3_PNP && + !memcmp(phys_addr, el3_devs[i]->dev_addr, + ETH_ALEN)) { if (el3_debug > 3) pr_debug("3c509 with address %02x %02x %02x %02x %02x %02x was found by ISAPnP\n", phys_addr[0] & 0xff, phys_addr[0] >> 8, @@ -835,8 +835,8 @@ el3_start_xmit(struct sk_buff *skb, struct net_device *dev) #ifndef final_version { /* Error-checking code, delete someday. */ ushort status = inw(ioaddr + EL3_STATUS); - if (status & 0x0001 /* IRQ line active, missed one. */ - && inw(ioaddr + EL3_STATUS) & 1) { /* Make sure. */ + if (status & 0x0001 && /* IRQ line active, missed one. */ + inw(ioaddr + EL3_STATUS) & 1) { /* Make sure. */ pr_debug("%s: Missed interrupt, status then %04x now %04x" " Tx %2.2x Rx %4.4x.\n", dev->name, status, inw(ioaddr + EL3_STATUS), inb(ioaddr + TX_STATUS), diff --git a/drivers/net/3c515.c b/drivers/net/3c515.c index 37faf36e2457..063b049ffe55 100644 --- a/drivers/net/3c515.c +++ b/drivers/net/3c515.c @@ -764,10 +764,11 @@ static int corkscrew_open(struct net_device *dev) /* Use the now-standard shared IRQ implementation. */ if (vp->capabilities == 0x11c7) { /* Corkscrew: Cannot share ISA resources. */ - if (dev->irq == 0 - || dev->dma == 0 - || request_irq(dev->irq, corkscrew_interrupt, 0, - vp->product_name, dev)) return -EAGAIN; + if (dev->irq == 0 || + dev->dma == 0 || + request_irq(dev->irq, corkscrew_interrupt, 0, + vp->product_name, dev)) + return -EAGAIN; enable_dma(dev->dma); set_dma_mode(dev->dma, DMA_MODE_CASCADE); } else if (request_irq(dev->irq, corkscrew_interrupt, IRQF_SHARED, @@ -1368,8 +1369,8 @@ static int boomerang_rx(struct net_device *dev) /* Check if the packet is long enough to just accept without copying to a properly sized skbuff. */ - if (pkt_len < rx_copybreak - && (skb = dev_alloc_skb(pkt_len + 4)) != NULL) { + if (pkt_len < rx_copybreak && + (skb = dev_alloc_skb(pkt_len + 4)) != NULL) { skb_reserve(skb, 2); /* Align IP on 16 byte boundaries */ /* 'skb_put()' points to the start of sk_buff data area. */ memcpy(skb_put(skb, pkt_len), diff --git a/drivers/net/3c527.c b/drivers/net/3c527.c index d91c3464fe72..36c4191e7bca 100644 --- a/drivers/net/3c527.c +++ b/drivers/net/3c527.c @@ -1168,8 +1168,8 @@ static void mc32_rx_ring(struct net_device *dev) /* Try to save time by avoiding a copy on big frames */ - if ((length > RX_COPYBREAK) - && ((newskb=dev_alloc_skb(1532)) != NULL)) + if ((length > RX_COPYBREAK) && + ((newskb=dev_alloc_skb(1532)) != NULL)) { skb=lp->rx_ring[rx_ring_tail].skb; skb_put(skb, length); diff --git a/drivers/net/3c59x.c b/drivers/net/3c59x.c index 32031eaf4910..78b7167a8ce3 100644 --- a/drivers/net/3c59x.c +++ b/drivers/net/3c59x.c @@ -1942,8 +1942,8 @@ vortex_error(struct net_device *dev, int status) if (status & TxComplete) { /* Really "TxError" for us. */ tx_status = ioread8(ioaddr + TxStatus); /* Presumably a tx-timeout. We must merely re-enable. */ - if (vortex_debug > 2 - || (tx_status != 0x88 && vortex_debug > 0)) { + if (vortex_debug > 2 || + (tx_status != 0x88 && vortex_debug > 0)) { pr_err("%s: Transmit error, Tx status register %2.2x.\n", dev->name, tx_status); if (tx_status == 0x82) { diff --git a/drivers/net/8139cp.c b/drivers/net/8139cp.c index ab451bb8995a..3f452bcbfb9e 100644 --- a/drivers/net/8139cp.c +++ b/drivers/net/8139cp.c @@ -909,8 +909,8 @@ static void __cp_set_rx_mode (struct net_device *dev) AcceptBroadcast | AcceptMulticast | AcceptMyPhys | AcceptAllPhys; mc_filter[1] = mc_filter[0] = 0xffffffff; - } else if ((dev->mc_count > multicast_filter_limit) - || (dev->flags & IFF_ALLMULTI)) { + } else if ((dev->mc_count > multicast_filter_limit) || + (dev->flags & IFF_ALLMULTI)) { /* Too many to filter perfectly -- accept all multicasts. */ rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0xffffffff; diff --git a/drivers/net/8139too.c b/drivers/net/8139too.c index 7e333f73b228..25f7339daabd 100644 --- a/drivers/net/8139too.c +++ b/drivers/net/8139too.c @@ -1549,8 +1549,8 @@ static inline void rtl8139_thread_iter (struct net_device *dev, mii_lpa = mdio_read (dev, tp->phys[0], MII_LPA); if (!tp->mii.force_media && mii_lpa != 0xffff) { - int duplex = (mii_lpa & LPA_100FULL) - || (mii_lpa & 0x01C0) == 0x0040; + int duplex = ((mii_lpa & LPA_100FULL) || + (mii_lpa & 0x01C0) == 0x0040); if (tp->mii.full_duplex != duplex) { tp->mii.full_duplex = duplex; @@ -1936,8 +1936,8 @@ static int rtl8139_rx(struct net_device *dev, struct rtl8139_private *tp, RTL_R16 (RxBufAddr), RTL_R16 (RxBufPtr), RTL_R8 (ChipCmd)); - while (netif_running(dev) && received < budget - && (RTL_R8 (ChipCmd) & RxBufEmpty) == 0) { + while (netif_running(dev) && received < budget && + (RTL_R8 (ChipCmd) & RxBufEmpty) == 0) { u32 ring_offset = cur_rx % RX_BUF_LEN; u32 rx_status; unsigned int pkt_size; @@ -2521,8 +2521,8 @@ static void __set_rx_mode (struct net_device *dev) AcceptBroadcast | AcceptMulticast | AcceptMyPhys | AcceptAllPhys; mc_filter[1] = mc_filter[0] = 0xffffffff; - } else if ((dev->mc_count > multicast_filter_limit) - || (dev->flags & IFF_ALLMULTI)) { + } else if ((dev->mc_count > multicast_filter_limit) || + (dev->flags & IFF_ALLMULTI)) { /* Too many to filter perfectly -- accept all multicasts. */ rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0xffffffff; diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 6399abbdad6b..0bbd5ae49862 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -975,7 +975,7 @@ config ENC28J60_WRITEVERIFY config ETHOC tristate "OpenCores 10/100 Mbps Ethernet MAC support" - depends on NET_ETHERNET && HAS_IOMEM + depends on NET_ETHERNET && HAS_IOMEM && HAS_DMA select MII select PHYLIB select CRC32 diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c index aaf14d306a4a..eb0448b03f41 100644 --- a/drivers/net/appletalk/ipddp.c +++ b/drivers/net/appletalk/ipddp.c @@ -230,9 +230,9 @@ static int ipddp_delete(struct ipddp_route *rt) spin_lock_bh(&ipddp_route_lock); while((tmp = *r) != NULL) { - if(tmp->ip == rt->ip - && tmp->at.s_net == rt->at.s_net - && tmp->at.s_node == rt->at.s_node) + if(tmp->ip == rt->ip && + tmp->at.s_net == rt->at.s_net && + tmp->at.s_node == rt->at.s_node) { *r = tmp->next; spin_unlock_bh(&ipddp_route_lock); @@ -255,9 +255,9 @@ static struct ipddp_route* __ipddp_find_route(struct ipddp_route *rt) for(f = ipddp_route_list; f != NULL; f = f->next) { - if(f->ip == rt->ip - && f->at.s_net == rt->at.s_net - && f->at.s_node == rt->at.s_node) + if(f->ip == rt->ip && + f->at.s_net == rt->at.s_net && + f->at.s_node == rt->at.s_node) return (f); } diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index c5b988140a91..e6afab2455b1 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -174,9 +174,9 @@ static int __init arcrimi_found(struct net_device *dev) * 2k (or there are no mirrors at all) but on some, it's 4k. */ mirror_size = MIRROR_SIZE; - if (readb(p) == TESTvalue - && check_mirror(shmem - MIRROR_SIZE, MIRROR_SIZE) == 0 - && check_mirror(shmem - 2 * MIRROR_SIZE, MIRROR_SIZE) == 1) + if (readb(p) == TESTvalue && + check_mirror(shmem - MIRROR_SIZE, MIRROR_SIZE) == 0 && + check_mirror(shmem - 2 * MIRROR_SIZE, MIRROR_SIZE) == 1) mirror_size = 2 * MIRROR_SIZE; first_mirror = shmem - mirror_size; diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c index 75a572560909..d8f029303754 100644 --- a/drivers/net/arcnet/arcnet.c +++ b/drivers/net/arcnet/arcnet.c @@ -301,8 +301,8 @@ static int choose_mtu(void) /* choose the smallest MTU of all available encaps */ for (count = 0; count < 256; count++) { - if (arc_proto_map[count] != &arc_proto_null - && arc_proto_map[count]->mtu < mtu) { + if (arc_proto_map[count] != &arc_proto_null && + arc_proto_map[count]->mtu < mtu) { mtu = arc_proto_map[count]->mtu; } } @@ -953,13 +953,13 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) * > RECON_THRESHOLD/min; * then print a warning message. */ - if (!lp->network_down - && (lp->last_recon - lp->first_recon) <= HZ * 60 - && lp->num_recons >= RECON_THRESHOLD) { + if (!lp->network_down && + (lp->last_recon - lp->first_recon) <= HZ * 60 && + lp->num_recons >= RECON_THRESHOLD) { lp->network_down = 1; BUGMSG(D_NORMAL, "many reconfigurations detected: cabling problem?\n"); - } else if (!lp->network_down - && lp->last_recon - lp->first_recon > HZ * 60) { + } else if (!lp->network_down && + lp->last_recon - lp->first_recon > HZ * 60) { /* reset counters if we've gone for over a minute. */ lp->first_recon = lp->last_recon; lp->num_recons = 1; diff --git a/drivers/net/arm/ep93xx_eth.c b/drivers/net/arm/ep93xx_eth.c index 2be49c817995..b25467ac895c 100644 --- a/drivers/net/arm/ep93xx_eth.c +++ b/drivers/net/arm/ep93xx_eth.c @@ -628,15 +628,6 @@ static int ep93xx_open(struct net_device *dev) if (ep93xx_alloc_buffers(ep)) return -ENOMEM; - if (is_zero_ether_addr(dev->dev_addr)) { - random_ether_addr(dev->dev_addr); - printk(KERN_INFO "%s: generated random MAC address " - "%.2x:%.2x:%.2x:%.2x:%.2x:%.2x.\n", dev->name, - dev->dev_addr[0], dev->dev_addr[1], - dev->dev_addr[2], dev->dev_addr[3], - dev->dev_addr[4], dev->dev_addr[5]); - } - napi_enable(&ep->napi); if (ep93xx_start_hw(dev)) { @@ -877,6 +868,9 @@ static int ep93xx_eth_probe(struct platform_device *pdev) ep->mii.mdio_write = ep93xx_mdio_write; ep->mdc_divisor = 40; /* Max HCLK 100 MHz, min MDIO clk 2.5 MHz. */ + if (is_zero_ether_addr(dev->dev_addr)) + random_ether_addr(dev->dev_addr); + err = register_netdev(dev); if (err) { dev_err(&pdev->dev, "Failed to register netdev\n"); diff --git a/drivers/net/at1700.c b/drivers/net/at1700.c index d4ab69f032be..b14f4799d5d1 100644 --- a/drivers/net/at1700.c +++ b/drivers/net/at1700.c @@ -350,13 +350,13 @@ static int __init at1700_probe1(struct net_device *dev, int ioaddr) slot = -1; /* We must check for the EEPROM-config boards first, else accessing IOCONFIG0 will move the board! */ - if (at1700_probe_list[inb(ioaddr + IOCONFIG1) & 0x07] == ioaddr - && read_eeprom(ioaddr, 4) == 0x0000 - && (read_eeprom(ioaddr, 5) & 0xff00) == 0xF400) + if (at1700_probe_list[inb(ioaddr + IOCONFIG1) & 0x07] == ioaddr && + read_eeprom(ioaddr, 4) == 0x0000 && + (read_eeprom(ioaddr, 5) & 0xff00) == 0xF400) is_at1700 = 1; - else if (inb(ioaddr + SAPROM ) == 0x00 - && inb(ioaddr + SAPROM + 1) == 0x00 - && inb(ioaddr + SAPROM + 2) == 0x0e) + else if (inb(ioaddr + SAPROM ) == 0x00 && + inb(ioaddr + SAPROM + 1) == 0x00 && + inb(ioaddr + SAPROM + 2) == 0x0e) is_fmv18x = 1; else { goto err_out; @@ -839,8 +839,8 @@ set_rx_mode(struct net_device *dev) if (dev->flags & IFF_PROMISC) { memset(mc_filter, 0xff, sizeof(mc_filter)); outb(3, ioaddr + RX_MODE); /* Enable promiscuous mode */ - } else if (dev->mc_count > MC_FILTERBREAK - || (dev->flags & IFF_ALLMULTI)) { + } else if (dev->mc_count > MC_FILTERBREAK || + (dev->flags & IFF_ALLMULTI)) { /* Too many to filter perfectly -- accept all multicasts. */ memset(mc_filter, 0xff, sizeof(mc_filter)); outb(2, ioaddr + RX_MODE); /* Use normal mode. */ diff --git a/drivers/net/atarilance.c b/drivers/net/atarilance.c index 0c0deceb6938..c5721cb38265 100644 --- a/drivers/net/atarilance.c +++ b/drivers/net/atarilance.c @@ -930,8 +930,8 @@ static irqreturn_t lance_interrupt( int irq, void *dev_id ) } #endif - if (lp->tx_full && (netif_queue_stopped(dev)) - && dirty_tx > lp->cur_tx - TX_RING_SIZE + 2) { + if (lp->tx_full && (netif_queue_stopped(dev)) && + dirty_tx > lp->cur_tx - TX_RING_SIZE + 2) { /* The ring is no longer full, clear tbusy. */ lp->tx_full = 0; netif_wake_queue (dev); diff --git a/drivers/net/atl1e/atl1e_ethtool.c b/drivers/net/atl1e/atl1e_ethtool.c index 60edb9f232bb..a76006c1bc6b 100644 --- a/drivers/net/atl1e/atl1e_ethtool.c +++ b/drivers/net/atl1e/atl1e_ethtool.c @@ -131,11 +131,6 @@ static int atl1e_set_settings(struct net_device *netdev, return 0; } -static u32 atl1e_get_tx_csum(struct net_device *netdev) -{ - return (netdev->features & NETIF_F_HW_CSUM) != 0; -} - static u32 atl1e_get_msglevel(struct net_device *netdev) { #ifdef DBG @@ -145,10 +140,6 @@ static u32 atl1e_get_msglevel(struct net_device *netdev) #endif } -static void atl1e_set_msglevel(struct net_device *netdev, u32 data) -{ -} - static int atl1e_get_regs_len(struct net_device *netdev) { return AT_REGS_LEN * sizeof(u32); @@ -387,18 +378,14 @@ static const struct ethtool_ops atl1e_ethtool_ops = { .get_wol = atl1e_get_wol, .set_wol = atl1e_set_wol, .get_msglevel = atl1e_get_msglevel, - .set_msglevel = atl1e_set_msglevel, .nway_reset = atl1e_nway_reset, .get_link = ethtool_op_get_link, .get_eeprom_len = atl1e_get_eeprom_len, .get_eeprom = atl1e_get_eeprom, .set_eeprom = atl1e_set_eeprom, - .get_tx_csum = atl1e_get_tx_csum, - .get_sg = ethtool_op_get_sg, + .set_tx_csum = ethtool_op_set_tx_hw_csum, .set_sg = ethtool_op_set_sg, -#ifdef NETIF_F_TSO - .get_tso = ethtool_op_get_tso, -#endif + .set_tso = ethtool_op_set_tso, }; void atl1e_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/atl1e/atl1e_main.c b/drivers/net/atl1e/atl1e_main.c index ad17e74e5662..08f8c0969e9b 100644 --- a/drivers/net/atl1e/atl1e_main.c +++ b/drivers/net/atl1e/atl1e_main.c @@ -1664,41 +1664,6 @@ static int atl1e_tso_csum(struct atl1e_adapter *adapter, } return 0; } - - if (offload_type & SKB_GSO_TCPV6) { - real_len = (((unsigned char *)ipv6_hdr(skb) - skb->data) - + ntohs(ipv6_hdr(skb)->payload_len)); - if (real_len < skb->len) - pskb_trim(skb, real_len); - - /* check payload == 0 byte ? */ - hdr_len = (skb_transport_offset(skb) + tcp_hdrlen(skb)); - if (unlikely(skb->len == hdr_len)) { - /* only xsum need */ - dev_warn(&pdev->dev, - "IPV6 tso with zero data??\n"); - goto check_sum; - } else { - tcp_hdr(skb)->check = ~csum_ipv6_magic( - &ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - 0, IPPROTO_TCP, 0); - tpd->word3 |= 1 << TPD_IP_VERSION_SHIFT; - hdr_len >>= 1; - tpd->word3 |= (hdr_len & TPD_V6_IPHLLO_MASK) << - TPD_V6_IPHLLO_SHIFT; - tpd->word3 |= ((hdr_len >> 3) & - TPD_V6_IPHLHI_MASK) << - TPD_V6_IPHLHI_SHIFT; - tpd->word3 |= (tcp_hdrlen(skb) >> 2 & - TPD_TCPHDRLEN_MASK) << - TPD_TCPHDRLEN_SHIFT; - tpd->word3 |= ((skb_shinfo(skb)->gso_size) & - TPD_MSS_MASK) << TPD_MSS_SHIFT; - tpd->word3 |= 1 << TPD_SEGMENT_EN_SHIFT; - } - } - return 0; } check_sum: @@ -2287,7 +2252,6 @@ static int atl1e_init_netdev(struct net_device *netdev, struct pci_dev *pdev) NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX; netdev->features |= NETIF_F_LLTX; netdev->features |= NETIF_F_TSO; - netdev->features |= NETIF_F_TSO6; return 0; } diff --git a/drivers/net/atlx/atl1.c b/drivers/net/atlx/atl1.c index e547f788a266..b6cf3263127c 100644 --- a/drivers/net/atlx/atl1.c +++ b/drivers/net/atlx/atl1.c @@ -1344,8 +1344,8 @@ static u32 atl1_check_link(struct atl1_adapter *adapter) /* link result is our setting */ if (!reconfig) { - if (adapter->link_speed != speed - || adapter->link_duplex != duplex) { + if (adapter->link_speed != speed || + adapter->link_duplex != duplex) { adapter->link_speed = speed; adapter->link_duplex = duplex; atl1_setup_mac_ctrl(adapter); @@ -2087,8 +2087,8 @@ static void atl1_intr_tx(struct atl1_adapter *adapter) } atomic_set(&tpd_ring->next_to_clean, sw_tpd_next_to_clean); - if (netif_queue_stopped(adapter->netdev) - && netif_carrier_ok(adapter->netdev)) + if (netif_queue_stopped(adapter->netdev) && + netif_carrier_ok(adapter->netdev)) netif_wake_queue(adapter->netdev); } diff --git a/drivers/net/atp.c b/drivers/net/atp.c index 001791775be3..2f8261c9614a 100644 --- a/drivers/net/atp.c +++ b/drivers/net/atp.c @@ -673,8 +673,8 @@ static irqreturn_t atp_interrupt(int irq, void *dev_instance) netif_wake_queue(dev); /* Inform upper layers. */ } num_tx_since_rx++; - } else if (num_tx_since_rx > 8 - && time_after(jiffies, dev->last_rx + HZ)) { + } else if (num_tx_since_rx > 8 && + time_after(jiffies, dev->last_rx + HZ)) { if (net_debug > 2) printk(KERN_DEBUG "%s: Missed packet? No Rx after %d Tx and " "%ld jiffies status %02x CMR1 %02x.\n", dev->name, diff --git a/drivers/net/au1000_eth.c b/drivers/net/au1000_eth.c index e67533cf78d8..6bac04603a88 100644 --- a/drivers/net/au1000_eth.c +++ b/drivers/net/au1000_eth.c @@ -1088,7 +1088,14 @@ static struct net_device * au1000_probe(int port_num) return NULL; } - if ((err = register_netdev(dev)) != 0) { + dev->base_addr = base; + dev->irq = irq; + dev->netdev_ops = &au1000_netdev_ops; + SET_ETHTOOL_OPS(dev, &au1000_ethtool_ops); + dev->watchdog_timeo = ETH_TX_TIMEOUT; + + err = register_netdev(dev); + if (err != 0) { printk(KERN_ERR "%s: Cannot register net device, error %d\n", DRV_NAME, err); free_netdev(dev); @@ -1209,12 +1216,6 @@ static struct net_device * au1000_probe(int port_num) aup->tx_db_inuse[i] = pDB; } - dev->base_addr = base; - dev->irq = irq; - dev->netdev_ops = &au1000_netdev_ops; - SET_ETHTOOL_OPS(dev, &au1000_ethtool_ops); - dev->watchdog_timeo = ETH_TX_TIMEOUT; - /* * The boot code uses the ethernet controller, so reset it to start * fresh. au1000_init() expects that the device is in reset state. diff --git a/drivers/net/b44.c b/drivers/net/b44.c index e046943ef29d..2a9132343b66 100644 --- a/drivers/net/b44.c +++ b/drivers/net/b44.c @@ -912,9 +912,6 @@ static irqreturn_t b44_interrupt(int irq, void *dev_id) bp->istat = istat; __b44_disable_ints(bp); __napi_schedule(&bp->napi); - } else { - printk(KERN_ERR PFX "%s: Error, poll already scheduled\n", - dev->name); } irq_ack: diff --git a/drivers/net/benet/be.h b/drivers/net/benet/be.h index dc7c19e49111..9e56014d27ed 100644 --- a/drivers/net/benet/be.h +++ b/drivers/net/benet/be.h @@ -32,7 +32,7 @@ #include "be_hw.h" -#define DRV_VER "2.101.205" +#define DRV_VER "2.101.346u" #define DRV_NAME "be2net" #define BE_NAME "ServerEngines BladeEngine2 10Gbps NIC" #define BE3_NAME "ServerEngines BladeEngine3 10Gbps NIC" @@ -170,7 +170,7 @@ struct be_drvr_stats { u32 cache_barrier[16]; u32 be_ethrx_post_fail;/* number of ethrx buffer alloc failures */ - u32 be_polls; /* number of times NAPI called poll function */ + u32 be_rx_polls; /* number of times NAPI called poll function */ u32 be_rx_events; /* number of ucast rx completion events */ u32 be_rx_compl; /* number of rx completion entries processed */ ulong be_rx_jiffies; @@ -269,9 +269,12 @@ struct be_adapter { bool link_up; u32 port_num; bool promiscuous; + bool wol; u32 cap; u32 rx_fc; /* Rx flow control */ u32 tx_fc; /* Tx flow control */ + int link_speed; + u8 port_type; }; extern const struct ethtool_ops be_ethtool_ops; diff --git a/drivers/net/benet/be_cmds.c b/drivers/net/benet/be_cmds.c index 8bd531560043..1b68bd98dc0c 100644 --- a/drivers/net/benet/be_cmds.c +++ b/drivers/net/benet/be_cmds.c @@ -71,8 +71,8 @@ static int be_mcc_compl_process(struct be_adapter *adapter, extd_status = (compl->status >> CQE_STATUS_EXTD_SHIFT) & CQE_STATUS_EXTD_MASK; dev_warn(&adapter->pdev->dev, - "Error in cmd completion: status(compl/extd)=%d/%d\n", - compl_status, extd_status); + "Error in cmd completion - opcode %d, compl %d, extd %d\n", + compl->tag0, compl_status, extd_status); } return compl_status; } @@ -277,7 +277,7 @@ static inline struct be_sge *nonembedded_sgl(struct be_mcc_wrb *wrb) /* Don't touch the hdr after it's prepared */ static void be_wrb_hdr_prepare(struct be_mcc_wrb *wrb, int payload_len, - bool embedded, u8 sge_cnt) + bool embedded, u8 sge_cnt, u32 opcode) { if (embedded) wrb->embedded |= MCC_WRB_EMBEDDED_MASK; @@ -285,6 +285,7 @@ static void be_wrb_hdr_prepare(struct be_mcc_wrb *wrb, int payload_len, wrb->embedded |= (sge_cnt & MCC_WRB_SGE_CNT_MASK) << MCC_WRB_SGE_CNT_SHIFT; wrb->payload_length = payload_len; + wrb->tag0 = opcode; be_dws_cpu_to_le(wrb, 20); } @@ -425,7 +426,7 @@ int be_cmd_eq_create(struct be_adapter *adapter, wrb = wrb_from_mbox(adapter); req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, OPCODE_COMMON_EQ_CREATE); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_EQ_CREATE, sizeof(*req)); @@ -469,7 +470,8 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr, wrb = wrb_from_mbox(adapter); req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_NTWK_MAC_QUERY); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_NTWK_MAC_QUERY, sizeof(*req)); @@ -509,7 +511,8 @@ int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr, } req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_NTWK_PMAC_ADD); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_NTWK_PMAC_ADD, sizeof(*req)); @@ -544,7 +547,8 @@ int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, u32 pmac_id) } req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_NTWK_PMAC_DEL); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_NTWK_PMAC_DEL, sizeof(*req)); @@ -576,7 +580,8 @@ int be_cmd_cq_create(struct be_adapter *adapter, req = embedded_payload(wrb); ctxt = &req->context; - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_CQ_CREATE); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_CQ_CREATE, sizeof(*req)); @@ -633,7 +638,8 @@ int be_cmd_mccq_create(struct be_adapter *adapter, req = embedded_payload(wrb); ctxt = &req->context; - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_MCC_CREATE); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_MCC_CREATE, sizeof(*req)); @@ -677,7 +683,8 @@ int be_cmd_txq_create(struct be_adapter *adapter, req = embedded_payload(wrb); ctxt = &req->context; - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_ETH_TX_CREATE); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ETH, OPCODE_ETH_TX_CREATE, sizeof(*req)); @@ -724,7 +731,8 @@ int be_cmd_rxq_create(struct be_adapter *adapter, wrb = wrb_from_mbox(adapter); req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_ETH_RX_CREATE); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ETH, OPCODE_ETH_RX_CREATE, sizeof(*req)); @@ -765,8 +773,6 @@ int be_cmd_q_destroy(struct be_adapter *adapter, struct be_queue_info *q, wrb = wrb_from_mbox(adapter); req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); - switch (queue_type) { case QTYPE_EQ: subsys = CMD_SUBSYSTEM_COMMON; @@ -791,6 +797,9 @@ int be_cmd_q_destroy(struct be_adapter *adapter, struct be_queue_info *q, default: BUG(); } + + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, opcode); + be_cmd_hdr_prepare(&req->hdr, subsys, opcode, sizeof(*req)); req->id = cpu_to_le16(q->id); @@ -816,7 +825,8 @@ int be_cmd_if_create(struct be_adapter *adapter, u32 cap_flags, u32 en_flags, wrb = wrb_from_mbox(adapter); req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_NTWK_INTERFACE_CREATE); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_NTWK_INTERFACE_CREATE, sizeof(*req)); @@ -851,7 +861,8 @@ int be_cmd_if_destroy(struct be_adapter *adapter, u32 interface_id) wrb = wrb_from_mbox(adapter); req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_NTWK_INTERFACE_DESTROY); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_NTWK_INTERFACE_DESTROY, sizeof(*req)); @@ -886,8 +897,8 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd) req = nonemb_cmd->va; sge = nonembedded_sgl(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), false, 1); - wrb->tag0 = OPCODE_ETH_GET_STATISTICS; + be_wrb_hdr_prepare(wrb, sizeof(*req), false, 1, + OPCODE_ETH_GET_STATISTICS); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ETH, OPCODE_ETH_GET_STATISTICS, sizeof(*req)); @@ -921,7 +932,8 @@ int be_cmd_link_status_query(struct be_adapter *adapter, *link_up = false; - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_NTWK_LINK_STATUS_QUERY); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_NTWK_LINK_STATUS_QUERY, sizeof(*req)); @@ -953,7 +965,8 @@ int be_cmd_get_fw_ver(struct be_adapter *adapter, char *fw_ver) wrb = wrb_from_mbox(adapter); req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_GET_FW_VERSION); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_GET_FW_VERSION, sizeof(*req)); @@ -986,7 +999,8 @@ int be_cmd_modify_eqd(struct be_adapter *adapter, u32 eq_id, u32 eqd) } req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_MODIFY_EQ_DELAY); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_MODIFY_EQ_DELAY, sizeof(*req)); @@ -1020,7 +1034,8 @@ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array, } req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_NTWK_VLAN_CONFIG); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_NTWK_VLAN_CONFIG, sizeof(*req)); @@ -1059,7 +1074,7 @@ int be_cmd_promiscuous_config(struct be_adapter *adapter, u8 port_num, bool en) } req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, OPCODE_ETH_PROMISCUOUS); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ETH, OPCODE_ETH_PROMISCUOUS, sizeof(*req)); @@ -1099,7 +1114,8 @@ int be_cmd_multicast_set(struct be_adapter *adapter, u32 if_id, sge = nonembedded_sgl(wrb); memset(req, 0, sizeof(*req)); - be_wrb_hdr_prepare(wrb, sizeof(*req), false, 1); + be_wrb_hdr_prepare(wrb, sizeof(*req), false, 1, + OPCODE_COMMON_NTWK_MULTICAST_SET); sge->pa_hi = cpu_to_le32(upper_32_bits(mem->dma)); sge->pa_lo = cpu_to_le32(mem->dma & 0xFFFFFFFF); sge->len = cpu_to_le32(mem->size); @@ -1143,7 +1159,8 @@ int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc) } req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_SET_FLOW_CONTROL); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_SET_FLOW_CONTROL, sizeof(*req)); @@ -1174,7 +1191,8 @@ int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc) } req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_GET_FLOW_CONTROL); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_GET_FLOW_CONTROL, sizeof(*req)); @@ -1204,7 +1222,8 @@ int be_cmd_query_fw_cfg(struct be_adapter *adapter, u32 *port_num, u32 *cap) wrb = wrb_from_mbox(adapter); req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_QUERY_FIRMWARE_CONFIG); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_QUERY_FIRMWARE_CONFIG, sizeof(*req)); @@ -1232,7 +1251,8 @@ int be_cmd_reset_function(struct be_adapter *adapter) wrb = wrb_from_mbox(adapter); req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_FUNCTION_RESET); be_cmd_hdr_prepare(req, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_FUNCTION_RESET, sizeof(*req)); @@ -1260,7 +1280,8 @@ int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num, } req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_ENABLE_DISABLE_BEACON); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_ENABLE_DISABLE_BEACON, sizeof(*req)); @@ -1293,7 +1314,8 @@ int be_cmd_get_beacon_state(struct be_adapter *adapter, u8 port_num, u32 *state) } req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_COMMON_GET_BEACON_STATE); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_GET_BEACON_STATE, sizeof(*req)); @@ -1329,7 +1351,8 @@ int be_cmd_read_port_type(struct be_adapter *adapter, u32 port, } req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(struct be_cmd_resp_port_type), true, 0); + be_wrb_hdr_prepare(wrb, sizeof(struct be_cmd_resp_port_type), true, 0, + OPCODE_COMMON_READ_TRANSRECV_DATA); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_READ_TRANSRECV_DATA, sizeof(*req)); @@ -1365,7 +1388,8 @@ int be_cmd_write_flashrom(struct be_adapter *adapter, struct be_dma_mem *cmd, req = cmd->va; sge = nonembedded_sgl(wrb); - be_wrb_hdr_prepare(wrb, cmd->size, false, 1); + be_wrb_hdr_prepare(wrb, cmd->size, false, 1, + OPCODE_COMMON_WRITE_FLASHROM); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_WRITE_FLASHROM, cmd->size); @@ -1399,7 +1423,8 @@ int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc) } req = embedded_payload(wrb); - be_wrb_hdr_prepare(wrb, sizeof(*req)+4, true, 0); + be_wrb_hdr_prepare(wrb, sizeof(*req)+4, true, 0, + OPCODE_COMMON_READ_FLASHROM); be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, OPCODE_COMMON_READ_FLASHROM, sizeof(*req)+4); @@ -1417,3 +1442,132 @@ err: spin_unlock_bh(&adapter->mcc_lock); return status; } + +extern int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac, + struct be_dma_mem *nonemb_cmd) +{ + struct be_mcc_wrb *wrb; + struct be_cmd_req_acpi_wol_magic_config *req; + struct be_sge *sge; + int status; + + spin_lock_bh(&adapter->mcc_lock); + + wrb = wrb_from_mccq(adapter); + if (!wrb) { + status = -EBUSY; + goto err; + } + req = nonemb_cmd->va; + sge = nonembedded_sgl(wrb); + + be_wrb_hdr_prepare(wrb, sizeof(*req), false, 1, + OPCODE_ETH_ACPI_WOL_MAGIC_CONFIG); + + be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ETH, + OPCODE_ETH_ACPI_WOL_MAGIC_CONFIG, sizeof(*req)); + memcpy(req->magic_mac, mac, ETH_ALEN); + + sge->pa_hi = cpu_to_le32(upper_32_bits(nonemb_cmd->dma)); + sge->pa_lo = cpu_to_le32(nonemb_cmd->dma & 0xFFFFFFFF); + sge->len = cpu_to_le32(nonemb_cmd->size); + + status = be_mcc_notify_wait(adapter); + +err: + spin_unlock_bh(&adapter->mcc_lock); + return status; +} + +int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num, + u32 loopback_type, u32 pkt_size, u32 num_pkts, u64 pattern) +{ + struct be_mcc_wrb *wrb; + struct be_cmd_req_loopback_test *req; + int status; + + spin_lock_bh(&adapter->mcc_lock); + + wrb = wrb_from_mccq(adapter); + if (!wrb) { + status = -EBUSY; + goto err; + } + + req = embedded_payload(wrb); + + be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0, + OPCODE_LOWLEVEL_LOOPBACK_TEST); + + be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_LOWLEVEL, + OPCODE_LOWLEVEL_LOOPBACK_TEST, sizeof(*req)); + + req->pattern = cpu_to_le64(pattern); + req->src_port = cpu_to_le32(port_num); + req->dest_port = cpu_to_le32(port_num); + req->pkt_size = cpu_to_le32(pkt_size); + req->num_pkts = cpu_to_le32(num_pkts); + req->loopback_type = cpu_to_le32(loopback_type); + + status = be_mcc_notify_wait(adapter); + if (!status) { + struct be_cmd_resp_loopback_test *resp = embedded_payload(wrb); + status = le32_to_cpu(resp->status); + } + +err: + spin_unlock_bh(&adapter->mcc_lock); + return status; +} + +int be_cmd_ddr_dma_test(struct be_adapter *adapter, u64 pattern, + u32 byte_cnt, struct be_dma_mem *cmd) +{ + struct be_mcc_wrb *wrb; + struct be_cmd_req_ddrdma_test *req; + struct be_sge *sge; + int status; + int i, j = 0; + + spin_lock_bh(&adapter->mcc_lock); + + wrb = wrb_from_mccq(adapter); + if (!wrb) { + status = -EBUSY; + goto err; + } + req = cmd->va; + sge = nonembedded_sgl(wrb); + be_wrb_hdr_prepare(wrb, cmd->size, false, 1, + OPCODE_LOWLEVEL_HOST_DDR_DMA); + be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_LOWLEVEL, + OPCODE_LOWLEVEL_HOST_DDR_DMA, cmd->size); + + sge->pa_hi = cpu_to_le32(upper_32_bits(cmd->dma)); + sge->pa_lo = cpu_to_le32(cmd->dma & 0xFFFFFFFF); + sge->len = cpu_to_le32(cmd->size); + + req->pattern = cpu_to_le64(pattern); + req->byte_count = cpu_to_le32(byte_cnt); + for (i = 0; i < byte_cnt; i++) { + req->snd_buff[i] = (u8)(pattern >> (j*8)); + j++; + if (j > 7) + j = 0; + } + + status = be_mcc_notify_wait(adapter); + + if (!status) { + struct be_cmd_resp_ddrdma_test *resp; + resp = cmd->va; + if ((memcmp(resp->rcv_buff, req->snd_buff, byte_cnt) != 0) || + resp->snd_err) { + status = -1; + } + } + +err: + spin_unlock_bh(&adapter->mcc_lock); + return status; +} diff --git a/drivers/net/benet/be_cmds.h b/drivers/net/benet/be_cmds.h index 8ec6528cb054..e7323be507d0 100644 --- a/drivers/net/benet/be_cmds.h +++ b/drivers/net/benet/be_cmds.h @@ -112,6 +112,7 @@ struct be_mcc_mailbox { #define CMD_SUBSYSTEM_COMMON 0x1 #define CMD_SUBSYSTEM_ETH 0x3 +#define CMD_SUBSYSTEM_LOWLEVEL 0xb #define OPCODE_COMMON_NTWK_MAC_QUERY 1 #define OPCODE_COMMON_NTWK_MAC_SET 2 @@ -150,6 +151,10 @@ struct be_mcc_mailbox { #define OPCODE_ETH_RX_CREATE 8 #define OPCODE_ETH_TX_DESTROY 9 #define OPCODE_ETH_RX_DESTROY 10 +#define OPCODE_ETH_ACPI_WOL_MAGIC_CONFIG 12 + +#define OPCODE_LOWLEVEL_HOST_DDR_DMA 17 +#define OPCODE_LOWLEVEL_LOOPBACK_TEST 18 struct be_cmd_req_hdr { u8 opcode; /* dword 0 */ @@ -788,6 +793,53 @@ struct be_cmd_write_flashrom { struct flashrom_params params; }; +/************************ WOL *******************************/ +struct be_cmd_req_acpi_wol_magic_config{ + struct be_cmd_req_hdr hdr; + u32 rsvd0[145]; + u8 magic_mac[6]; + u8 rsvd2[2]; +} __packed; + +/********************** LoopBack test *********************/ +struct be_cmd_req_loopback_test { + struct be_cmd_req_hdr hdr; + u32 loopback_type; + u32 num_pkts; + u64 pattern; + u32 src_port; + u32 dest_port; + u32 pkt_size; +}; + +struct be_cmd_resp_loopback_test { + struct be_cmd_resp_hdr resp_hdr; + u32 status; + u32 num_txfer; + u32 num_rx; + u32 miscomp_off; + u32 ticks_compl; +}; + +/********************** DDR DMA test *********************/ +struct be_cmd_req_ddrdma_test { + struct be_cmd_req_hdr hdr; + u64 pattern; + u32 byte_count; + u32 rsvd0; + u8 snd_buff[4096]; + u8 rsvd1[4096]; +}; + +struct be_cmd_resp_ddrdma_test { + struct be_cmd_resp_hdr hdr; + u64 pattern; + u32 byte_cnt; + u32 snd_err; + u8 rsvd0[4096]; + u8 rcv_buff[4096]; +}; + extern int be_pci_fnum_get(struct be_adapter *adapter); extern int be_cmd_POST(struct be_adapter *adapter); extern int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr, @@ -851,5 +903,12 @@ extern int be_cmd_write_flashrom(struct be_adapter *adapter, struct be_dma_mem *cmd, u32 flash_oper, u32 flash_opcode, u32 buf_size); extern int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc); +extern int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac, + struct be_dma_mem *nonemb_cmd); extern int be_cmd_fw_init(struct be_adapter *adapter); extern int be_cmd_fw_clean(struct be_adapter *adapter); +extern int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num, + u32 loopback_type, u32 pkt_size, + u32 num_pkts, u64 pattern); +extern int be_cmd_ddr_dma_test(struct be_adapter *adapter, u64 pattern, + u32 byte_cnt, struct be_dma_mem *cmd); diff --git a/drivers/net/benet/be_ethtool.c b/drivers/net/benet/be_ethtool.c index e8f92831021a..298b92cbd689 100644 --- a/drivers/net/benet/be_ethtool.c +++ b/drivers/net/benet/be_ethtool.c @@ -55,7 +55,7 @@ static const struct be_ethtool_stat et_stats[] = { {DRVSTAT_INFO(be_tx_stops)}, {DRVSTAT_INFO(be_fwd_reqs)}, {DRVSTAT_INFO(be_tx_wrbs)}, - {DRVSTAT_INFO(be_polls)}, + {DRVSTAT_INFO(be_rx_polls)}, {DRVSTAT_INFO(be_tx_events)}, {DRVSTAT_INFO(be_rx_events)}, {DRVSTAT_INFO(be_tx_compl)}, @@ -107,6 +107,18 @@ static const struct be_ethtool_stat et_stats[] = { }; #define ETHTOOL_STATS_NUM ARRAY_SIZE(et_stats) +static const char et_self_tests[][ETH_GSTRING_LEN] = { + "MAC Loopback test", + "PHY Loopback test", + "External Loopback test", + "DDR DMA test" +}; + +#define ETHTOOL_TESTS_NUM ARRAY_SIZE(et_self_tests) +#define BE_MAC_LOOPBACK 0x0 +#define BE_PHY_LOOPBACK 0x1 +#define BE_ONE_PORT_EXT_LOOPBACK 0x2 + static void be_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { @@ -278,12 +290,20 @@ be_get_stat_strings(struct net_device *netdev, uint32_t stringset, data += ETH_GSTRING_LEN; } break; + case ETH_SS_TEST: + for (i = 0; i < ETHTOOL_TESTS_NUM; i++) { + memcpy(data, et_self_tests[i], ETH_GSTRING_LEN); + data += ETH_GSTRING_LEN; + } + break; } } static int be_get_sset_count(struct net_device *netdev, int stringset) { switch (stringset) { + case ETH_SS_TEST: + return ETHTOOL_TESTS_NUM; case ETH_SS_STATS: return ETHTOOL_STATS_NUM; default: @@ -297,36 +317,48 @@ static int be_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) u8 mac_speed = 0, connector = 0; u16 link_speed = 0; bool link_up = false; + int status; - be_cmd_link_status_query(adapter, &link_up, &mac_speed, &link_speed); + if (adapter->link_speed < 0) { + status = be_cmd_link_status_query(adapter, &link_up, + &mac_speed, &link_speed); + + /* link_speed is in units of 10 Mbps */ + if (link_speed) { + ecmd->speed = link_speed*10; + } else { + switch (mac_speed) { + case PHY_LINK_SPEED_1GBPS: + ecmd->speed = SPEED_1000; + break; + case PHY_LINK_SPEED_10GBPS: + ecmd->speed = SPEED_10000; + break; + } + } - /* link_speed is in units of 10 Mbps */ - if (link_speed) { - ecmd->speed = link_speed*10; - } else { - switch (mac_speed) { - case PHY_LINK_SPEED_1GBPS: - ecmd->speed = SPEED_1000; + status = be_cmd_read_port_type(adapter, adapter->port_num, + &connector); + switch (connector) { + case 7: + ecmd->port = PORT_FIBRE; break; - case PHY_LINK_SPEED_10GBPS: - ecmd->speed = SPEED_10000; + default: + ecmd->port = PORT_TP; break; } + + /* Save for future use */ + adapter->link_speed = ecmd->speed; + adapter->port_type = ecmd->port; + } else { + ecmd->speed = adapter->link_speed; + ecmd->port = adapter->port_type; } + ecmd->duplex = DUPLEX_FULL; ecmd->autoneg = AUTONEG_DISABLE; ecmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_TP); - - be_cmd_read_port_type(adapter, adapter->port_num, &connector); - switch (connector) { - case 7: - ecmd->port = PORT_FIBRE; - break; - default: - ecmd->port = PORT_TP; - break; - } - ecmd->phy_address = adapter->port_num; ecmd->transceiver = XCVR_INTERNAL; @@ -380,9 +412,6 @@ be_phys_id(struct net_device *netdev, u32 data) int status; u32 cur; - if (!netif_running(netdev)) - return 0; - be_cmd_get_beacon_state(adapter, adapter->port_num, &cur); if (cur == BEACON_STATE_ENABLED) @@ -402,6 +431,97 @@ be_phys_id(struct net_device *netdev, u32 data) return status; } +static void +be_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) +{ + struct be_adapter *adapter = netdev_priv(netdev); + + wol->supported = WAKE_MAGIC; + if (adapter->wol) + wol->wolopts = WAKE_MAGIC; + else + wol->wolopts = 0; + memset(&wol->sopass, 0, sizeof(wol->sopass)); + return; +} + +static int +be_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) +{ + struct be_adapter *adapter = netdev_priv(netdev); + + if (wol->wolopts & ~WAKE_MAGIC) + return -EINVAL; + + if (wol->wolopts & WAKE_MAGIC) + adapter->wol = true; + else + adapter->wol = false; + + return 0; +} + +static int +be_test_ddr_dma(struct be_adapter *adapter) +{ + int ret, i; + struct be_dma_mem ddrdma_cmd; + u64 pattern[2] = {0x5a5a5a5a5a5a5a5a, 0xa5a5a5a5a5a5a5a5}; + + ddrdma_cmd.size = sizeof(struct be_cmd_req_ddrdma_test); + ddrdma_cmd.va = pci_alloc_consistent(adapter->pdev, ddrdma_cmd.size, + &ddrdma_cmd.dma); + if (!ddrdma_cmd.va) { + dev_err(&adapter->pdev->dev, "Memory allocation failure \n"); + return -ENOMEM; + } + + for (i = 0; i < 2; i++) { + ret = be_cmd_ddr_dma_test(adapter, pattern[i], + 4096, &ddrdma_cmd); + if (ret != 0) + goto err; + } + +err: + pci_free_consistent(adapter->pdev, ddrdma_cmd.size, + ddrdma_cmd.va, ddrdma_cmd.dma); + return ret; +} + +static void +be_self_test(struct net_device *netdev, struct ethtool_test *test, u64 *data) +{ + struct be_adapter *adapter = netdev_priv(netdev); + + memset(data, 0, sizeof(u64) * ETHTOOL_TESTS_NUM); + + if (test->flags & ETH_TEST_FL_OFFLINE) { + data[0] = be_cmd_loopback_test(adapter, adapter->port_num, + BE_MAC_LOOPBACK, 1500, + 2, 0xabc); + if (data[0] != 0) + test->flags |= ETH_TEST_FL_FAILED; + + data[1] = be_cmd_loopback_test(adapter, adapter->port_num, + BE_PHY_LOOPBACK, 1500, + 2, 0xabc); + if (data[1] != 0) + test->flags |= ETH_TEST_FL_FAILED; + + data[2] = be_cmd_loopback_test(adapter, adapter->port_num, + BE_ONE_PORT_EXT_LOOPBACK, + 1500, 2, 0xabc); + if (data[2] != 0) + test->flags |= ETH_TEST_FL_FAILED; + + data[3] = be_test_ddr_dma(adapter); + if (data[3] != 0) + test->flags |= ETH_TEST_FL_FAILED; + } + +} + static int be_do_flash(struct net_device *netdev, struct ethtool_flash *efl) { @@ -419,6 +539,8 @@ be_do_flash(struct net_device *netdev, struct ethtool_flash *efl) const struct ethtool_ops be_ethtool_ops = { .get_settings = be_get_settings, .get_drvinfo = be_get_drvinfo, + .get_wol = be_get_wol, + .set_wol = be_set_wol, .get_link = ethtool_op_get_link, .get_coalesce = be_get_coalesce, .set_coalesce = be_set_coalesce, @@ -438,4 +560,5 @@ const struct ethtool_ops be_ethtool_ops = { .get_sset_count = be_get_sset_count, .get_ethtool_stats = be_get_ethtool_stats, .flash_device = be_do_flash, + .self_test = be_self_test, }; diff --git a/drivers/net/benet/be_hw.h b/drivers/net/benet/be_hw.h index f53d5ca2da9e..e2b3beffd49d 100644 --- a/drivers/net/benet/be_hw.h +++ b/drivers/net/benet/be_hw.h @@ -52,6 +52,10 @@ */ #define MEMBAR_CTRL_INT_CTRL_HOSTINTR_MASK (1 << 29) /* bit 29 */ +/********* Power managment (WOL) **********/ +#define PCICFG_PM_CONTROL_OFFSET 0x44 +#define PCICFG_PM_CONTROL_MASK 0x108 /* bits 3 & 8 */ + /********* ISR0 Register offset **********/ #define CEV_ISR0_OFFSET 0xC18 #define CEV_ISR_SIZE 4 diff --git a/drivers/net/benet/be_main.c b/drivers/net/benet/be_main.c index 795936439498..957a0f7f2764 100644 --- a/drivers/net/benet/be_main.c +++ b/drivers/net/benet/be_main.c @@ -125,6 +125,9 @@ static int be_mac_addr_set(struct net_device *netdev, void *p) struct sockaddr *addr = p; int status = 0; + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + status = be_cmd_pmac_del(adapter, adapter->if_handle, adapter->pmac_id); if (status) return status; @@ -217,6 +220,7 @@ void be_link_status_update(struct be_adapter *adapter, bool link_up) /* If link came up or went down */ if (adapter->link_up != link_up) { + adapter->link_speed = -1; if (link_up) { netif_start_queue(netdev); netif_carrier_on(netdev); @@ -390,15 +394,11 @@ static int make_tx_wrbs(struct be_adapter *adapter, atomic_add(wrb_cnt, &txq->used); queue_head_inc(txq); - if (skb_dma_map(&pdev->dev, skb, DMA_TO_DEVICE)) { - dev_err(&pdev->dev, "TX DMA mapping failed\n"); - return 0; - } - if (skb->len > skb->data_len) { int len = skb->len - skb->data_len; + busaddr = pci_map_single(pdev, skb->data, len, + PCI_DMA_TODEVICE); wrb = queue_head_node(txq); - busaddr = skb_shinfo(skb)->dma_head; wrb_fill(wrb, busaddr, len); be_dws_cpu_to_le(wrb, sizeof(*wrb)); queue_head_inc(txq); @@ -408,8 +408,9 @@ static int make_tx_wrbs(struct be_adapter *adapter, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; - - busaddr = skb_shinfo(skb)->dma_maps[i]; + busaddr = pci_map_page(pdev, frag->page, + frag->page_offset, + frag->size, PCI_DMA_TODEVICE); wrb = queue_head_node(txq); wrb_fill(wrb, busaddr, frag->size); be_dws_cpu_to_le(wrb, sizeof(*wrb)); @@ -982,23 +983,41 @@ static struct be_eth_tx_compl *be_tx_compl_get(struct be_queue_info *tx_cq) static void be_tx_compl_process(struct be_adapter *adapter, u16 last_index) { struct be_queue_info *txq = &adapter->tx_obj.q; + struct be_eth_wrb *wrb; struct sk_buff **sent_skbs = adapter->tx_obj.sent_skb_list; struct sk_buff *sent_skb; + u64 busaddr; u16 cur_index, num_wrbs = 0; cur_index = txq->tail; sent_skb = sent_skbs[cur_index]; BUG_ON(!sent_skb); sent_skbs[cur_index] = NULL; + wrb = queue_tail_node(txq); + be_dws_le_to_cpu(wrb, sizeof(*wrb)); + busaddr = ((u64)wrb->frag_pa_hi << 32) | (u64)wrb->frag_pa_lo; + if (busaddr != 0) { + pci_unmap_single(adapter->pdev, busaddr, + wrb->frag_len, PCI_DMA_TODEVICE); + } + num_wrbs++; + queue_tail_inc(txq); - do { + while (cur_index != last_index) { cur_index = txq->tail; + wrb = queue_tail_node(txq); + be_dws_le_to_cpu(wrb, sizeof(*wrb)); + busaddr = ((u64)wrb->frag_pa_hi << 32) | (u64)wrb->frag_pa_lo; + if (busaddr != 0) { + pci_unmap_page(adapter->pdev, busaddr, + wrb->frag_len, PCI_DMA_TODEVICE); + } num_wrbs++; queue_tail_inc(txq); - } while (cur_index != last_index); + } atomic_sub(num_wrbs, &txq->used); - skb_dma_unmap(&adapter->pdev->dev, sent_skb, DMA_TO_DEVICE); + kfree_skb(sent_skb); } @@ -1378,6 +1397,7 @@ int be_poll_rx(struct napi_struct *napi, int budget) struct be_eth_rx_compl *rxcp; u32 work_done; + adapter->stats.drvr_stats.be_rx_polls++; for (work_done = 0; work_done < budget; work_done++) { rxcp = be_rx_compl_get(adapter); if (!rxcp) @@ -1639,6 +1659,44 @@ ret_sts: return status; } +static int be_setup_wol(struct be_adapter *adapter, bool enable) +{ + struct be_dma_mem cmd; + int status = 0; + u8 mac[ETH_ALEN]; + + memset(mac, 0, ETH_ALEN); + + cmd.size = sizeof(struct be_cmd_req_acpi_wol_magic_config); + cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma); + if (cmd.va == NULL) + return -1; + memset(cmd.va, 0, cmd.size); + + if (enable) { + status = pci_write_config_dword(adapter->pdev, + PCICFG_PM_CONTROL_OFFSET, PCICFG_PM_CONTROL_MASK); + if (status) { + dev_err(&adapter->pdev->dev, + "Could not enable Wake-on-lan \n"); + pci_free_consistent(adapter->pdev, cmd.size, cmd.va, + cmd.dma); + return status; + } + status = be_cmd_enable_magic_wol(adapter, + adapter->netdev->dev_addr, &cmd); + pci_enable_wake(adapter->pdev, PCI_D3hot, 1); + pci_enable_wake(adapter->pdev, PCI_D3cold, 1); + } else { + status = be_cmd_enable_magic_wol(adapter, mac, &cmd); + pci_enable_wake(adapter->pdev, PCI_D3hot, 0); + pci_enable_wake(adapter->pdev, PCI_D3cold, 0); + } + + pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma); + return status; +} + static int be_setup(struct be_adapter *adapter) { struct net_device *netdev = adapter->netdev; @@ -1670,6 +1728,8 @@ static int be_setup(struct be_adapter *adapter) if (status != 0) goto rx_qs_destroy; + adapter->link_speed = -1; + return 0; rx_qs_destroy: @@ -1951,6 +2011,8 @@ static void be_netdev_init(struct net_device *netdev) NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_FILTER | NETIF_F_HW_CSUM | NETIF_F_GRO; + netdev->vlan_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_HW_CSUM; + netdev->flags |= IFF_MULTICAST; adapter->rx_csum = true; @@ -2144,7 +2206,12 @@ static int be_get_config(struct be_adapter *adapter) MAC_ADDRESS_TYPE_NETWORK, true /*permanent */, 0); if (status) return status; + + if (!is_valid_ether_addr(mac)) + return -EADDRNOTAVAIL; + memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN); + memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN); return 0; } @@ -2253,6 +2320,9 @@ static int be_suspend(struct pci_dev *pdev, pm_message_t state) struct be_adapter *adapter = pci_get_drvdata(pdev); struct net_device *netdev = adapter->netdev; + if (adapter->wol) + be_setup_wol(adapter, true); + netif_device_detach(netdev); if (netif_running(netdev)) { rtnl_lock(); @@ -2295,6 +2365,9 @@ static int be_resume(struct pci_dev *pdev) rtnl_unlock(); } netif_device_attach(netdev); + + if (adapter->wol) + be_setup_wol(adapter, false); return 0; } @@ -2309,8 +2382,8 @@ static struct pci_driver be_driver = { static int __init be_init_module(void) { - if (rx_frag_size != 8192 && rx_frag_size != 4096 - && rx_frag_size != 2048) { + if (rx_frag_size != 8192 && rx_frag_size != 4096 && + rx_frag_size != 2048) { printk(KERN_WARNING DRV_NAME " : Module param rx_frag_size must be 2048/4096/8192." " Using 2048\n"); diff --git a/drivers/net/bfin_mac.c b/drivers/net/bfin_mac.c index 14bd3801f7d3..8ffea3990d07 100644 --- a/drivers/net/bfin_mac.c +++ b/drivers/net/bfin_mac.c @@ -554,8 +554,8 @@ static void adjust_tx_list(void) { int timeout_cnt = MAX_TIMEOUT_CNT; - if (tx_list_head->status.status_word != 0 - && current_tx_ptr != tx_list_head) { + if (tx_list_head->status.status_word != 0 && + current_tx_ptr != tx_list_head) { goto adjust_head; /* released something, just return; */ } @@ -567,8 +567,8 @@ static void adjust_tx_list(void) if (current_tx_ptr->next->next == tx_list_head) { while (tx_list_head->status.status_word == 0) { udelay(10); - if (tx_list_head->status.status_word != 0 - || !(bfin_read_DMA2_IRQ_STATUS() & DMA_RUN)) { + if (tx_list_head->status.status_word != 0 || + !(bfin_read_DMA2_IRQ_STATUS() & DMA_RUN)) { goto adjust_head; } if (timeout_cnt-- < 0) { @@ -596,8 +596,8 @@ adjust_head: ": no sk_buff in a transmitted frame!\n"); } tx_list_head = tx_list_head->next; - } while (tx_list_head->status.status_word != 0 - && current_tx_ptr != tx_list_head); + } while (tx_list_head->status.status_word != 0 && + current_tx_ptr != tx_list_head); return; } diff --git a/drivers/net/bmac.c b/drivers/net/bmac.c index 406f06424251..9b587c344194 100644 --- a/drivers/net/bmac.c +++ b/drivers/net/bmac.c @@ -438,8 +438,8 @@ bmac_init_phy(struct net_device *dev) ctrl = bmac_mif_read(dev, 0); capable = ((bmac_mif_read(dev, 1) & 0xf800) >> 6) | 1; - if (bmac_mif_read(dev, 4) != capable - || (ctrl & 0x1000) == 0) { + if (bmac_mif_read(dev, 4) != capable || + (ctrl & 0x1000) == 0) { bmac_mif_write(dev, 4, capable); bmac_mif_write(dev, 0, 0x1200); } else diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c index 539d23b594ce..4bfc80812926 100644 --- a/drivers/net/bnx2.c +++ b/drivers/net/bnx2.c @@ -59,8 +59,8 @@ #define DRV_MODULE_NAME "bnx2" #define PFX DRV_MODULE_NAME ": " -#define DRV_MODULE_VERSION "2.0.2" -#define DRV_MODULE_RELDATE "Aug 21, 2009" +#define DRV_MODULE_VERSION "2.0.3" +#define DRV_MODULE_RELDATE "Dec 03, 2009" #define FW_MIPS_FILE_06 "bnx2/bnx2-mips-06-5.0.0.j3.fw" #define FW_RV2P_FILE_06 "bnx2/bnx2-rv2p-06-5.0.0.j3.fw" #define FW_MIPS_FILE_09 "bnx2/bnx2-mips-09-5.0.0.j3.fw" @@ -2815,13 +2815,21 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget) } } - skb_dma_unmap(&bp->pdev->dev, skb, DMA_TO_DEVICE); + pci_unmap_single(bp->pdev, pci_unmap_addr(tx_buf, mapping), + skb_headlen(skb), PCI_DMA_TODEVICE); tx_buf->skb = NULL; last = tx_buf->nr_frags; for (i = 0; i < last; i++) { sw_cons = NEXT_TX_BD(sw_cons); + + pci_unmap_page(bp->pdev, + pci_unmap_addr( + &txr->tx_buf_ring[TX_RING_IDX(sw_cons)], + mapping), + skb_shinfo(skb)->frags[i].size, + PCI_DMA_TODEVICE); } sw_cons = NEXT_TX_BD(sw_cons); @@ -5150,8 +5158,12 @@ bnx2_init_rx_ring(struct bnx2 *bp, int ring_num) ring_prod = prod = rxr->rx_pg_prod; for (i = 0; i < bp->rx_pg_ring_size; i++) { - if (bnx2_alloc_rx_page(bp, rxr, ring_prod) < 0) + if (bnx2_alloc_rx_page(bp, rxr, ring_prod) < 0) { + printk(KERN_WARNING PFX "%s: init'ed rx page ring %d " + "with %d/%d pages only\n", + bp->dev->name, ring_num, i, bp->rx_pg_ring_size); break; + } prod = NEXT_RX_BD(prod); ring_prod = RX_PG_RING_IDX(prod); } @@ -5159,8 +5171,12 @@ bnx2_init_rx_ring(struct bnx2 *bp, int ring_num) ring_prod = prod = rxr->rx_prod; for (i = 0; i < bp->rx_ring_size; i++) { - if (bnx2_alloc_rx_skb(bp, rxr, ring_prod) < 0) + if (bnx2_alloc_rx_skb(bp, rxr, ring_prod) < 0) { + printk(KERN_WARNING PFX "%s: init'ed rx ring %d with " + "%d/%d skbs only\n", + bp->dev->name, ring_num, i, bp->rx_ring_size); break; + } prod = NEXT_RX_BD(prod); ring_prod = RX_RING_IDX(prod); } @@ -5295,17 +5311,29 @@ bnx2_free_tx_skbs(struct bnx2 *bp) for (j = 0; j < TX_DESC_CNT; ) { struct sw_tx_bd *tx_buf = &txr->tx_buf_ring[j]; struct sk_buff *skb = tx_buf->skb; + int k, last; if (skb == NULL) { j++; continue; } - skb_dma_unmap(&bp->pdev->dev, skb, DMA_TO_DEVICE); + pci_unmap_single(bp->pdev, + pci_unmap_addr(tx_buf, mapping), + skb_headlen(skb), + PCI_DMA_TODEVICE); tx_buf->skb = NULL; - j += skb_shinfo(skb)->nr_frags + 1; + last = tx_buf->nr_frags; + j++; + for (k = 0; k < last; k++, j++) { + tx_buf = &txr->tx_buf_ring[TX_RING_IDX(j)]; + pci_unmap_page(bp->pdev, + pci_unmap_addr(tx_buf, mapping), + skb_shinfo(skb)->frags[k].size, + PCI_DMA_TODEVICE); + } dev_kfree_skb(skb); } } @@ -5684,11 +5712,12 @@ bnx2_run_loopback(struct bnx2 *bp, int loopback_mode) for (i = 14; i < pkt_size; i++) packet[i] = (unsigned char) (i & 0xff); - if (skb_dma_map(&bp->pdev->dev, skb, DMA_TO_DEVICE)) { + map = pci_map_single(bp->pdev, skb->data, pkt_size, + PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(bp->pdev, map)) { dev_kfree_skb(skb); return -EIO; } - map = skb_shinfo(skb)->dma_head; REG_WR(bp, BNX2_HC_COMMAND, bp->hc_cmd | BNX2_HC_COMMAND_COAL_NOW_WO_INT); @@ -5723,7 +5752,7 @@ bnx2_run_loopback(struct bnx2 *bp, int loopback_mode) udelay(5); - skb_dma_unmap(&bp->pdev->dev, skb, DMA_TO_DEVICE); + pci_unmap_single(bp->pdev, map, pkt_size, PCI_DMA_TODEVICE); dev_kfree_skb(skb); if (bnx2_get_hw_tx_cons(tx_napi) != txr->tx_prod) @@ -6242,8 +6271,11 @@ bnx2_reset_task(struct work_struct *work) { struct bnx2 *bp = container_of(work, struct bnx2, reset_task); - if (!netif_running(bp->dev)) + rtnl_lock(); + if (!netif_running(bp->dev)) { + rtnl_unlock(); return; + } bnx2_netif_stop(bp); @@ -6251,6 +6283,28 @@ bnx2_reset_task(struct work_struct *work) atomic_set(&bp->intr_sem, 1); bnx2_netif_start(bp); + rtnl_unlock(); +} + +static void +bnx2_dump_state(struct bnx2 *bp) +{ + struct net_device *dev = bp->dev; + + printk(KERN_ERR PFX "%s DEBUG: intr_sem[%x]\n", dev->name, + atomic_read(&bp->intr_sem)); + printk(KERN_ERR PFX "%s DEBUG: EMAC_TX_STATUS[%08x] " + "RPM_MGMT_PKT_CTRL[%08x]\n", dev->name, + REG_RD(bp, BNX2_EMAC_TX_STATUS), + REG_RD(bp, BNX2_RPM_MGMT_PKT_CTRL)); + printk(KERN_ERR PFX "%s DEBUG: MCP_STATE_P0[%08x] MCP_STATE_P1[%08x]\n", + dev->name, bnx2_reg_rd_ind(bp, BNX2_MCP_STATE_P0), + bnx2_reg_rd_ind(bp, BNX2_MCP_STATE_P1)); + printk(KERN_ERR PFX "%s DEBUG: HC_STATS_INTERRUPT_STATUS[%08x]\n", + dev->name, REG_RD(bp, BNX2_HC_STATS_INTERRUPT_STATUS)); + if (bp->flags & BNX2_FLAG_USING_MSIX) + printk(KERN_ERR PFX "%s DEBUG: PBA[%08x]\n", dev->name, + REG_RD(bp, BNX2_PCI_GRC_WINDOW3_BASE)); } static void @@ -6258,6 +6312,8 @@ bnx2_tx_timeout(struct net_device *dev) { struct bnx2 *bp = netdev_priv(dev); + bnx2_dump_state(bp); + /* This allows the netif to be shutdown gracefully before resetting */ schedule_work(&bp->reset_task); } @@ -6302,7 +6358,6 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev) struct bnx2_napi *bnapi; struct bnx2_tx_ring_info *txr; struct netdev_queue *txq; - struct skb_shared_info *sp; /* Determine which tx ring we will be placed on */ i = skb_get_queue_mapping(skb); @@ -6367,16 +6422,15 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev) } else mss = 0; - if (skb_dma_map(&bp->pdev->dev, skb, DMA_TO_DEVICE)) { + mapping = pci_map_single(bp->pdev, skb->data, len, PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(bp->pdev, mapping)) { dev_kfree_skb(skb); return NETDEV_TX_OK; } - sp = skb_shinfo(skb); - mapping = sp->dma_head; - tx_buf = &txr->tx_buf_ring[ring_prod]; tx_buf->skb = skb; + pci_unmap_addr_set(tx_buf, mapping, mapping); txbd = &txr->tx_desc_ring[ring_prod]; @@ -6397,7 +6451,12 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev) txbd = &txr->tx_desc_ring[ring_prod]; len = frag->size; - mapping = sp->dma_maps[i]; + mapping = pci_map_page(bp->pdev, frag->page, frag->page_offset, + len, PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(bp->pdev, mapping)) + goto dma_error; + pci_unmap_addr_set(&txr->tx_buf_ring[ring_prod], mapping, + mapping); txbd->tx_bd_haddr_hi = (u64) mapping >> 32; txbd->tx_bd_haddr_lo = (u64) mapping & 0xffffffff; @@ -6424,6 +6483,30 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev) } return NETDEV_TX_OK; +dma_error: + /* save value of frag that failed */ + last_frag = i; + + /* start back at beginning and unmap skb */ + prod = txr->tx_prod; + ring_prod = TX_RING_IDX(prod); + tx_buf = &txr->tx_buf_ring[ring_prod]; + tx_buf->skb = NULL; + pci_unmap_single(bp->pdev, pci_unmap_addr(tx_buf, mapping), + skb_headlen(skb), PCI_DMA_TODEVICE); + + /* unmap remaining mapped pages */ + for (i = 0; i < last_frag; i++) { + prod = NEXT_TX_BD(prod); + ring_prod = TX_RING_IDX(prod); + tx_buf = &txr->tx_buf_ring[ring_prod]; + pci_unmap_page(bp->pdev, pci_unmap_addr(tx_buf, mapping), + skb_shinfo(skb)->frags[i].size, + PCI_DMA_TODEVICE); + } + + dev_kfree_skb(skb); + return NETDEV_TX_OK; } /* Called with rtnl_lock */ @@ -7639,6 +7722,86 @@ bnx2_get_pci_speed(struct bnx2 *bp) } +static void __devinit +bnx2_read_vpd_fw_ver(struct bnx2 *bp) +{ + int rc, i, v0_len = 0; + u8 *data; + u8 *v0_str = NULL; + bool mn_match = false; + +#define BNX2_VPD_NVRAM_OFFSET 0x300 +#define BNX2_VPD_LEN 128 +#define BNX2_MAX_VER_SLEN 30 + + data = kmalloc(256, GFP_KERNEL); + if (!data) + return; + + rc = bnx2_nvram_read(bp, BNX2_VPD_NVRAM_OFFSET, data + BNX2_VPD_LEN, + BNX2_VPD_LEN); + if (rc) + goto vpd_done; + + for (i = 0; i < BNX2_VPD_LEN; i += 4) { + data[i] = data[i + BNX2_VPD_LEN + 3]; + data[i + 1] = data[i + BNX2_VPD_LEN + 2]; + data[i + 2] = data[i + BNX2_VPD_LEN + 1]; + data[i + 3] = data[i + BNX2_VPD_LEN]; + } + + for (i = 0; i <= BNX2_VPD_LEN - 3; ) { + unsigned char val = data[i]; + unsigned int block_end; + + if (val == 0x82 || val == 0x91) { + i = (i + 3 + (data[i + 1] + (data[i + 2] << 8))); + continue; + } + + if (val != 0x90) + goto vpd_done; + + block_end = (i + 3 + (data[i + 1] + (data[i + 2] << 8))); + i += 3; + + if (block_end > BNX2_VPD_LEN) + goto vpd_done; + + while (i < (block_end - 2)) { + int len = data[i + 2]; + + if (i + 3 + len > block_end) + goto vpd_done; + + if (data[i] == 'M' && data[i + 1] == 'N') { + if (len != 4 || + memcmp(&data[i + 3], "1028", 4)) + goto vpd_done; + mn_match = true; + + } else if (data[i] == 'V' && data[i + 1] == '0') { + if (len > BNX2_MAX_VER_SLEN) + goto vpd_done; + + v0_len = len; + v0_str = &data[i + 3]; + } + i += 3 + len; + + if (mn_match && v0_str) { + memcpy(bp->fw_version, v0_str, v0_len); + bp->fw_version[v0_len] = ' '; + goto vpd_done; + } + } + goto vpd_done; + } + +vpd_done: + kfree(data); +} + static int __devinit bnx2_init_board(struct pci_dev *pdev, struct net_device *dev) { @@ -7812,10 +7975,18 @@ bnx2_init_board(struct pci_dev *pdev, struct net_device *dev) goto err_out_unmap; } + bnx2_read_vpd_fw_ver(bp); + + j = strlen(bp->fw_version); reg = bnx2_shmem_rd(bp, BNX2_DEV_INFO_BC_REV); - for (i = 0, j = 0; i < 3; i++) { + for (i = 0; i < 3 && j < 24; i++) { u8 num, k, skip0; + if (i == 0) { + bp->fw_version[j++] = 'b'; + bp->fw_version[j++] = 'c'; + bp->fw_version[j++] = ' '; + } num = (u8) (reg >> (24 - (i * 8))); for (k = 100, skip0 = 1; k >= 1; num %= k, k /= 10) { if (num >= k || !skip0 || k == 1) { @@ -7846,8 +8017,9 @@ bnx2_init_board(struct pci_dev *pdev, struct net_device *dev) reg != BNX2_CONDITION_MFW_RUN_NONE) { u32 addr = bnx2_shmem_rd(bp, BNX2_MFW_VER_PTR); - bp->fw_version[j++] = ' '; - for (i = 0; i < 3; i++) { + if (j < 32) + bp->fw_version[j++] = ' '; + for (i = 0; i < 3 && j < 28; i++) { reg = bnx2_reg_rd_ind(bp, addr + i * 4); reg = swab32(reg); memcpy(&bp->fw_version[j], ®, 4); @@ -8268,6 +8440,7 @@ static pci_ers_result_t bnx2_io_slot_reset(struct pci_dev *pdev) } pci_set_master(pdev); pci_restore_state(pdev); + pci_save_state(pdev); if (netif_running(dev)) { bnx2_set_power_state(bp, PCI_D0); diff --git a/drivers/net/bnx2.h b/drivers/net/bnx2.h index a4d83409f205..939dc44d50a0 100644 --- a/drivers/net/bnx2.h +++ b/drivers/net/bnx2.h @@ -6345,6 +6345,8 @@ struct l2_fhdr { #define BNX2_MCP_ROM 0x00150000 #define BNX2_MCP_SCRATCH 0x00160000 +#define BNX2_MCP_STATE_P1 0x0016f9c8 +#define BNX2_MCP_STATE_P0 0x0016fdc8 #define BNX2_SHM_HDR_SIGNATURE BNX2_MCP_SCRATCH #define BNX2_SHM_HDR_SIGNATURE_SIG_MASK 0xffff0000 @@ -6559,6 +6561,7 @@ struct sw_pg { struct sw_tx_bd { struct sk_buff *skb; + DECLARE_PCI_UNMAP_ADDR(mapping) unsigned short is_gso; unsigned short nr_frags; }; diff --git a/drivers/net/bnx2x_link.c b/drivers/net/bnx2x_link.c index 41b9b7bd3d8e..cf5778919b4b 100644 --- a/drivers/net/bnx2x_link.c +++ b/drivers/net/bnx2x_link.c @@ -4717,8 +4717,8 @@ static u8 bnx2x_ext_phy_is_link_up(struct link_params *params, 0xc809, &val1); DP(NETIF_MSG_LINK, "8705 1.c809 val=0x%x\n", val1); - ext_phy_link_up = ((rx_sd & 0x1) && (val1 & (1<<9)) - && ((val1 & (1<<8)) == 0)); + ext_phy_link_up = ((rx_sd & 0x1) && (val1 & (1<<9)) && + ((val1 & (1<<8)) == 0)); if (ext_phy_link_up) vars->line_speed = SPEED_10000; break; diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 88c3fe80b355..d69e6838f21e 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -561,12 +561,12 @@ static void __update_selected(struct lacpdu *lacpdu, struct port *port) const struct port_params *partner = &port->partner_oper; // check if any parameter is different - if (ntohs(lacpdu->actor_port) != partner->port_number - || ntohs(lacpdu->actor_port_priority) != partner->port_priority - || MAC_ADDRESS_COMPARE(&lacpdu->actor_system, &partner->system) - || ntohs(lacpdu->actor_system_priority) != partner->system_priority - || ntohs(lacpdu->actor_key) != partner->key - || (lacpdu->actor_state & AD_STATE_AGGREGATION) != (partner->port_state & AD_STATE_AGGREGATION)) { + if (ntohs(lacpdu->actor_port) != partner->port_number || + ntohs(lacpdu->actor_port_priority) != partner->port_priority || + MAC_ADDRESS_COMPARE(&lacpdu->actor_system, &partner->system) || + ntohs(lacpdu->actor_system_priority) != partner->system_priority || + ntohs(lacpdu->actor_key) != partner->key || + (lacpdu->actor_state & AD_STATE_AGGREGATION) != (partner->port_state & AD_STATE_AGGREGATION)) { // update the state machine Selected variable port->sm_vars &= ~AD_PORT_SELECTED; } @@ -592,12 +592,12 @@ static void __update_default_selected(struct port *port) const struct port_params *oper = &port->partner_oper; // check if any parameter is different - if (admin->port_number != oper->port_number - || admin->port_priority != oper->port_priority - || MAC_ADDRESS_COMPARE(&admin->system, &oper->system) - || admin->system_priority != oper->system_priority - || admin->key != oper->key - || (admin->port_state & AD_STATE_AGGREGATION) + if (admin->port_number != oper->port_number || + admin->port_priority != oper->port_priority || + MAC_ADDRESS_COMPARE(&admin->system, &oper->system) || + admin->system_priority != oper->system_priority || + admin->key != oper->key || + (admin->port_state & AD_STATE_AGGREGATION) != (oper->port_state & AD_STATE_AGGREGATION)) { // update the state machine Selected variable port->sm_vars &= ~AD_PORT_SELECTED; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 726bd755338f..af9b9c4eb496 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1852,8 +1852,8 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev) } if (!bond->params.fail_over_mac) { - if (!compare_ether_addr(bond_dev->dev_addr, slave->perm_hwaddr) - && bond->slave_cnt > 1) + if (!compare_ether_addr(bond_dev->dev_addr, slave->perm_hwaddr) && + bond->slave_cnt > 1) pr_warning(DRV_NAME ": %s: Warning: the permanent HWaddr of %s - " "%pM - is still in use by %s. " @@ -5103,42 +5103,28 @@ out_netdev: static int bond_net_init(struct net *net) { - struct bond_net *bn; - int err; - - err = -ENOMEM; - bn = kzalloc(sizeof(struct bond_net), GFP_KERNEL); - if (bn == NULL) - goto out; + struct bond_net *bn = net_generic(net, bond_net_id); bn->net = net; INIT_LIST_HEAD(&bn->dev_list); - err = net_assign_generic(net, bond_net_id, bn); - if (err) - goto out_free; - bond_create_proc_dir(bn); -out: - return err; -out_free: - kfree(bn); - goto out; + + return 0; } static void bond_net_exit(struct net *net) { - struct bond_net *bn; - - bn = net_generic(net, bond_net_id); + struct bond_net *bn = net_generic(net, bond_net_id); bond_destroy_proc_dir(bn); - kfree(bn); } static struct pernet_operations bond_net_ops = { .init = bond_net_init, .exit = bond_net_exit, + .id = &bond_net_id, + .size = sizeof(struct bond_net), }; static int __init bonding_init(void) @@ -5152,7 +5138,7 @@ static int __init bonding_init(void) if (res) goto out; - res = register_pernet_gen_subsys(&bond_net_id, &bond_net_ops); + res = register_pernet_subsys(&bond_net_ops); if (res) goto out; @@ -5178,7 +5164,7 @@ out: err: rtnl_link_unregister(&bond_link_ops); err_link: - unregister_pernet_gen_subsys(bond_net_id, &bond_net_ops); + unregister_pernet_subsys(&bond_net_ops); goto out; } @@ -5192,7 +5178,7 @@ static void __exit bonding_exit(void) bond_destroy_sysfs(); rtnl_link_unregister(&bond_link_ops); - unregister_pernet_gen_subsys(bond_net_id, &bond_net_ops); + unregister_pernet_subsys(&bond_net_ops); } module_init(bonding_init); diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index a51ae7dc8d51..558ec1352527 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -254,8 +254,8 @@ static inline struct bonding *bond_get_bond_by_slave(struct slave *slave) static inline bool bond_is_lb(const struct bonding *bond) { - return bond->params.mode == BOND_MODE_TLB - || bond->params.mode == BOND_MODE_ALB; + return (bond->params.mode == BOND_MODE_TLB || + bond->params.mode == BOND_MODE_ALB); } #define BOND_PRI_RESELECT_ALWAYS 0 diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index 3e4419054c81..591eb0eb1c2b 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -318,12 +318,12 @@ static void ems_usb_rx_can_msg(struct ems_usb *dev, struct ems_cpc_msg *msg) cf->can_id = le32_to_cpu(msg->msg.can_msg.id); cf->can_dlc = min_t(u8, msg->msg.can_msg.length, 8); - if (msg->type == CPC_MSG_TYPE_EXT_CAN_FRAME - || msg->type == CPC_MSG_TYPE_EXT_RTR_FRAME) + if (msg->type == CPC_MSG_TYPE_EXT_CAN_FRAME || + msg->type == CPC_MSG_TYPE_EXT_RTR_FRAME) cf->can_id |= CAN_EFF_FLAG; - if (msg->type == CPC_MSG_TYPE_RTR_FRAME - || msg->type == CPC_MSG_TYPE_EXT_RTR_FRAME) { + if (msg->type == CPC_MSG_TYPE_RTR_FRAME || + msg->type == CPC_MSG_TYPE_EXT_RTR_FRAME) { cf->can_id |= CAN_RTR_FLAG; } else { for (i = 0; i < cf->can_dlc; i++) diff --git a/drivers/net/cnic.c b/drivers/net/cnic.c index ee7eb9ee77e2..d4c6e7fcff53 100644 --- a/drivers/net/cnic.c +++ b/drivers/net/cnic.c @@ -667,14 +667,14 @@ static void cnic_free_dma(struct cnic_dev *dev, struct cnic_dma *dma) for (i = 0; i < dma->num_pages; i++) { if (dma->pg_arr[i]) { - pci_free_consistent(dev->pcidev, BCM_PAGE_SIZE, - dma->pg_arr[i], dma->pg_map_arr[i]); + dma_free_coherent(&dev->pcidev->dev, BCM_PAGE_SIZE, + dma->pg_arr[i], dma->pg_map_arr[i]); dma->pg_arr[i] = NULL; } } if (dma->pgtbl) { - pci_free_consistent(dev->pcidev, dma->pgtbl_size, - dma->pgtbl, dma->pgtbl_map); + dma_free_coherent(&dev->pcidev->dev, dma->pgtbl_size, + dma->pgtbl, dma->pgtbl_map); dma->pgtbl = NULL; } kfree(dma->pg_arr); @@ -725,9 +725,10 @@ static int cnic_alloc_dma(struct cnic_dev *dev, struct cnic_dma *dma, dma->num_pages = pages; for (i = 0; i < pages; i++) { - dma->pg_arr[i] = pci_alloc_consistent(dev->pcidev, - BCM_PAGE_SIZE, - &dma->pg_map_arr[i]); + dma->pg_arr[i] = dma_alloc_coherent(&dev->pcidev->dev, + BCM_PAGE_SIZE, + &dma->pg_map_arr[i], + GFP_ATOMIC); if (dma->pg_arr[i] == NULL) goto error; } @@ -736,8 +737,8 @@ static int cnic_alloc_dma(struct cnic_dev *dev, struct cnic_dma *dma, dma->pgtbl_size = ((pages * 8) + BCM_PAGE_SIZE - 1) & ~(BCM_PAGE_SIZE - 1); - dma->pgtbl = pci_alloc_consistent(dev->pcidev, dma->pgtbl_size, - &dma->pgtbl_map); + dma->pgtbl = dma_alloc_coherent(&dev->pcidev->dev, dma->pgtbl_size, + &dma->pgtbl_map, GFP_ATOMIC); if (dma->pgtbl == NULL) goto error; @@ -757,9 +758,9 @@ static void cnic_free_context(struct cnic_dev *dev) for (i = 0; i < cp->ctx_blks; i++) { if (cp->ctx_arr[i].ctx) { - pci_free_consistent(dev->pcidev, cp->ctx_blk_size, - cp->ctx_arr[i].ctx, - cp->ctx_arr[i].mapping); + dma_free_coherent(&dev->pcidev->dev, cp->ctx_blk_size, + cp->ctx_arr[i].ctx, + cp->ctx_arr[i].mapping); cp->ctx_arr[i].ctx = NULL; } } @@ -781,14 +782,14 @@ static void cnic_free_resc(struct cnic_dev *dev) } if (cp->l2_buf) { - pci_free_consistent(dev->pcidev, cp->l2_buf_size, - cp->l2_buf, cp->l2_buf_map); + dma_free_coherent(&dev->pcidev->dev, cp->l2_buf_size, + cp->l2_buf, cp->l2_buf_map); cp->l2_buf = NULL; } if (cp->l2_ring) { - pci_free_consistent(dev->pcidev, cp->l2_ring_size, - cp->l2_ring, cp->l2_ring_map); + dma_free_coherent(&dev->pcidev->dev, cp->l2_ring_size, + cp->l2_ring, cp->l2_ring_map); cp->l2_ring = NULL; } @@ -849,8 +850,10 @@ static int cnic_alloc_context(struct cnic_dev *dev) for (i = 0; i < cp->ctx_blks; i++) { cp->ctx_arr[i].ctx = - pci_alloc_consistent(dev->pcidev, BCM_PAGE_SIZE, - &cp->ctx_arr[i].mapping); + dma_alloc_coherent(&dev->pcidev->dev, + BCM_PAGE_SIZE, + &cp->ctx_arr[i].mapping, + GFP_KERNEL); if (cp->ctx_arr[i].ctx == NULL) return -ENOMEM; } @@ -863,15 +866,17 @@ static int cnic_alloc_l2_rings(struct cnic_dev *dev, int pages) struct cnic_local *cp = dev->cnic_priv; cp->l2_ring_size = pages * BCM_PAGE_SIZE; - cp->l2_ring = pci_alloc_consistent(dev->pcidev, cp->l2_ring_size, - &cp->l2_ring_map); + cp->l2_ring = dma_alloc_coherent(&dev->pcidev->dev, cp->l2_ring_size, + &cp->l2_ring_map, + GFP_KERNEL | __GFP_COMP); if (!cp->l2_ring) return -ENOMEM; cp->l2_buf_size = (cp->l2_rx_ring_size + 1) * cp->l2_single_buf_size; cp->l2_buf_size = PAGE_ALIGN(cp->l2_buf_size); - cp->l2_buf = pci_alloc_consistent(dev->pcidev, cp->l2_buf_size, - &cp->l2_buf_map); + cp->l2_buf = dma_alloc_coherent(&dev->pcidev->dev, cp->l2_buf_size, + &cp->l2_buf_map, + GFP_KERNEL | __GFP_COMP); if (!cp->l2_buf) return -ENOMEM; @@ -1006,8 +1011,9 @@ static int cnic_alloc_bnx2x_context(struct cnic_dev *dev) for (i = 0; i < blks; i++) { cp->ctx_arr[i].ctx = - pci_alloc_consistent(dev->pcidev, cp->ctx_blk_size, - &cp->ctx_arr[i].mapping); + dma_alloc_coherent(&dev->pcidev->dev, cp->ctx_blk_size, + &cp->ctx_arr[i].mapping, + GFP_KERNEL); if (cp->ctx_arr[i].ctx == NULL) return -ENOMEM; @@ -1500,9 +1506,9 @@ static int cnic_setup_bnx2x_ctx(struct cnic_dev *dev, struct kwqe *wqes[], ictx->timers_context.flags |= ISCSI_TIMERS_BLOCK_CONTEXT_CONN_VALID_FLG; ictx->ustorm_st_context.ring.rq.pbl_base.lo = - req2->rq_page_table_addr_lo & 0xffffffff; + req2->rq_page_table_addr_lo; ictx->ustorm_st_context.ring.rq.pbl_base.hi = - (u64) req2->rq_page_table_addr_hi >> 32; + req2->rq_page_table_addr_hi; ictx->ustorm_st_context.ring.rq.curr_pbe.lo = req3->qp_first_pte[0].hi; ictx->ustorm_st_context.ring.rq.curr_pbe.hi = req3->qp_first_pte[0].lo; ictx->ustorm_st_context.ring.r2tq.pbl_base.lo = @@ -3997,15 +4003,19 @@ static void cnic_get_bnx2x_iscsi_info(struct cnic_dev *dev) if (base < 0xa0000 || base >= 0xc0000) return; - val = BNX2X_SHMEM_ADDR(base, + addr = BNX2X_SHMEM_ADDR(base, dev_info.port_hw_config[port].iscsi_mac_upper); + val = CNIC_RD(dev, addr); + dev->mac_addr[0] = (u8) (val >> 8); dev->mac_addr[1] = (u8) val; - val = BNX2X_SHMEM_ADDR(base, + addr = BNX2X_SHMEM_ADDR(base, dev_info.port_hw_config[port].iscsi_mac_lower); + val = CNIC_RD(dev, addr); + dev->mac_addr[2] = (u8) (val >> 24); dev->mac_addr[3] = (u8) (val >> 16); dev->mac_addr[4] = (u8) (val >> 8); @@ -4131,22 +4141,20 @@ static void cnic_init_rings(struct cnic_dev *dev) cnic_init_bnx2_rx_ring(dev); } else if (test_bit(CNIC_F_BNX2X_CLASS, &dev->flags)) { struct cnic_local *cp = dev->cnic_priv; - struct cnic_eth_dev *ethdev = cp->ethdev; u32 cli = BNX2X_ISCSI_CL_ID(CNIC_E1HVN(cp)); union l5cm_specific_data l5_data; struct ustorm_eth_rx_producers rx_prods = {0}; - void __iomem *doorbell; - int i; + u32 off, i; rx_prods.bd_prod = 0; rx_prods.cqe_prod = BNX2X_MAX_RCQ_DESC_CNT; barrier(); - doorbell = ethdev->io_base2 + BAR_USTRORM_INTMEM + + off = BAR_USTRORM_INTMEM + USTORM_RX_PRODS_OFFSET(CNIC_PORT(cp), cli); for (i = 0; i < sizeof(struct ustorm_eth_rx_producers) / 4; i++) - writel(((u32 *) &rx_prods)[i], doorbell + i * 4); + CNIC_WR(dev, off + i * 4, ((u32 *) &rx_prods)[i]); cnic_init_bnx2x_tx_ring(dev); cnic_init_bnx2x_rx_ring(dev); @@ -4166,8 +4174,15 @@ static void cnic_shutdown_rings(struct cnic_dev *dev) } else if (test_bit(CNIC_F_BNX2X_CLASS, &dev->flags)) { struct cnic_local *cp = dev->cnic_priv; u32 cli = BNX2X_ISCSI_CL_ID(CNIC_E1HVN(cp)); + union l5cm_specific_data l5_data; cnic_ring_ctl(dev, BNX2X_ISCSI_L2_CID, cli, 0); + + l5_data.phy_address.lo = cli; + l5_data.phy_address.hi = 0; + cnic_submit_kwqe_16(dev, RAMROD_CMD_ID_ETH_HALT, + BNX2X_ISCSI_L2_CID, ETH_CONNECTION_TYPE, &l5_data); + msleep(10); } } diff --git a/drivers/net/cxgb3/cxgb3_main.c b/drivers/net/cxgb3/cxgb3_main.c index b1a5a00a78cd..cef3f882e2b6 100644 --- a/drivers/net/cxgb3/cxgb3_main.c +++ b/drivers/net/cxgb3/cxgb3_main.c @@ -2117,19 +2117,19 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) if (t.qset_idx >= SGE_QSETS) return -EINVAL; if (!in_range(t.intr_lat, 0, M_NEWTIMER) || - !in_range(t.cong_thres, 0, 255) || - !in_range(t.txq_size[0], MIN_TXQ_ENTRIES, - MAX_TXQ_ENTRIES) || - !in_range(t.txq_size[1], MIN_TXQ_ENTRIES, - MAX_TXQ_ENTRIES) || - !in_range(t.txq_size[2], MIN_CTRL_TXQ_ENTRIES, - MAX_CTRL_TXQ_ENTRIES) || - !in_range(t.fl_size[0], MIN_FL_ENTRIES, - MAX_RX_BUFFERS) - || !in_range(t.fl_size[1], MIN_FL_ENTRIES, - MAX_RX_JUMBO_BUFFERS) - || !in_range(t.rspq_size, MIN_RSPQ_ENTRIES, - MAX_RSPQ_ENTRIES)) + !in_range(t.cong_thres, 0, 255) || + !in_range(t.txq_size[0], MIN_TXQ_ENTRIES, + MAX_TXQ_ENTRIES) || + !in_range(t.txq_size[1], MIN_TXQ_ENTRIES, + MAX_TXQ_ENTRIES) || + !in_range(t.txq_size[2], MIN_CTRL_TXQ_ENTRIES, + MAX_CTRL_TXQ_ENTRIES) || + !in_range(t.fl_size[0], MIN_FL_ENTRIES, + MAX_RX_BUFFERS) || + !in_range(t.fl_size[1], MIN_FL_ENTRIES, + MAX_RX_JUMBO_BUFFERS) || + !in_range(t.rspq_size, MIN_RSPQ_ENTRIES, + MAX_RSPQ_ENTRIES)) return -EINVAL; if ((adapter->flags & FULL_INIT_DONE) && t.lro > 0) diff --git a/drivers/net/dl2k.c b/drivers/net/dl2k.c index a2f1860fdd16..2a8b6a7c0b87 100644 --- a/drivers/net/dl2k.c +++ b/drivers/net/dl2k.c @@ -163,8 +163,8 @@ rio_probe1 (struct pci_dev *pdev, const struct pci_device_id *ent) strcmp (media[card_idx], "4") == 0) { np->speed = 100; np->full_duplex = 1; - } else if (strcmp (media[card_idx], "100mbps_hd") == 0 - || strcmp (media[card_idx], "3") == 0) { + } else if (strcmp (media[card_idx], "100mbps_hd") == 0 || + strcmp (media[card_idx], "3") == 0) { np->speed = 100; np->full_duplex = 0; } else if (strcmp (media[card_idx], "10mbps_fd") == 0 || diff --git a/drivers/net/dm9000.c b/drivers/net/dm9000.c index 81590fbb9943..0cbe3c0e7c06 100644 --- a/drivers/net/dm9000.c +++ b/drivers/net/dm9000.c @@ -1024,8 +1024,8 @@ dm9000_rx(struct net_device *dev) } /* Move data from DM9000 */ - if (GoodPacket - && ((skb = dev_alloc_skb(RxLen + 4)) != NULL)) { + if (GoodPacket && + ((skb = dev_alloc_skb(RxLen + 4)) != NULL)) { skb_reserve(skb, 2); rdptr = (u8 *) skb_put(skb, RxLen - 4); diff --git a/drivers/net/e100.c b/drivers/net/e100.c index a81c7b0c41b0..929701ca07d3 100644 --- a/drivers/net/e100.c +++ b/drivers/net/e100.c @@ -157,6 +157,7 @@ #include <linux/init.h> #include <linux/pci.h> #include <linux/dma-mapping.h> +#include <linux/dmapool.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/mii.h> @@ -602,6 +603,7 @@ struct nic { struct mem *mem; dma_addr_t dma_addr; + struct pci_pool *cbs_pool; dma_addr_t cbs_dma_addr; u8 adaptive_ifs; u8 tx_threshold; @@ -1805,9 +1807,7 @@ static void e100_clean_cbs(struct nic *nic) nic->cb_to_clean = nic->cb_to_clean->next; nic->cbs_avail++; } - pci_free_consistent(nic->pdev, - sizeof(struct cb) * nic->params.cbs.count, - nic->cbs, nic->cbs_dma_addr); + pci_pool_free(nic->cbs_pool, nic->cbs, nic->cbs_dma_addr); nic->cbs = NULL; nic->cbs_avail = 0; } @@ -1825,8 +1825,8 @@ static int e100_alloc_cbs(struct nic *nic) nic->cb_to_use = nic->cb_to_send = nic->cb_to_clean = NULL; nic->cbs_avail = 0; - nic->cbs = pci_alloc_consistent(nic->pdev, - sizeof(struct cb) * count, &nic->cbs_dma_addr); + nic->cbs = pci_pool_alloc(nic->cbs_pool, GFP_KERNEL, + &nic->cbs_dma_addr); if (!nic->cbs) return -ENOMEM; @@ -2852,7 +2852,11 @@ static int __devinit e100_probe(struct pci_dev *pdev, DPRINTK(PROBE, ERR, "Cannot register net device, aborting.\n"); goto err_out_free; } - + nic->cbs_pool = pci_pool_create(netdev->name, + nic->pdev, + nic->params.cbs.count * sizeof(struct cb), + sizeof(u32), + 0); DPRINTK(PROBE, INFO, "addr 0x%llx, irq %d, MAC addr %pM\n", (unsigned long long)pci_resource_start(pdev, use_io ? 1 : 0), pdev->irq, netdev->dev_addr); @@ -2882,6 +2886,7 @@ static void __devexit e100_remove(struct pci_dev *pdev) unregister_netdev(netdev); e100_free(nic); pci_iounmap(pdev, nic->csr); + pci_pool_destroy(nic->cbs_pool); free_netdev(netdev); pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/e1000/e1000.h b/drivers/net/e1000/e1000.h index a5665287bd64..2a567df3ea71 100644 --- a/drivers/net/e1000/e1000.h +++ b/drivers/net/e1000/e1000.h @@ -167,6 +167,7 @@ struct e1000_buffer { unsigned long time_stamp; u16 length; u16 next_to_watch; + u16 mapped_as_page; }; struct e1000_tx_ring { diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c index c938114a34ab..7e855f9bbd97 100644 --- a/drivers/net/e1000/e1000_main.c +++ b/drivers/net/e1000/e1000_main.c @@ -1839,10 +1839,17 @@ void e1000_free_all_tx_resources(struct e1000_adapter *adapter) static void e1000_unmap_and_free_tx_resource(struct e1000_adapter *adapter, struct e1000_buffer *buffer_info) { - buffer_info->dma = 0; + if (buffer_info->dma) { + if (buffer_info->mapped_as_page) + pci_unmap_page(adapter->pdev, buffer_info->dma, + buffer_info->length, PCI_DMA_TODEVICE); + else + pci_unmap_single(adapter->pdev, buffer_info->dma, + buffer_info->length, + PCI_DMA_TODEVICE); + buffer_info->dma = 0; + } if (buffer_info->skb) { - skb_dma_unmap(&adapter->pdev->dev, buffer_info->skb, - DMA_TO_DEVICE); dev_kfree_skb_any(buffer_info->skb); buffer_info->skb = NULL; } @@ -2683,22 +2690,14 @@ static int e1000_tx_map(struct e1000_adapter *adapter, unsigned int mss) { struct e1000_hw *hw = &adapter->hw; + struct pci_dev *pdev = adapter->pdev; struct e1000_buffer *buffer_info; unsigned int len = skb_headlen(skb); - unsigned int offset, size, count = 0, i; + unsigned int offset = 0, size, count = 0, i; unsigned int f; - dma_addr_t *map; i = tx_ring->next_to_use; - if (skb_dma_map(&adapter->pdev->dev, skb, DMA_TO_DEVICE)) { - dev_err(&adapter->pdev->dev, "TX DMA map failed\n"); - return 0; - } - - map = skb_shinfo(skb)->dma_maps; - offset = 0; - while (len) { buffer_info = &tx_ring->buffer_info[i]; size = min(len, max_per_txd); @@ -2735,7 +2734,11 @@ static int e1000_tx_map(struct e1000_adapter *adapter, buffer_info->length = size; /* set time_stamp *before* dma to help avoid a possible race */ buffer_info->time_stamp = jiffies; - buffer_info->dma = skb_shinfo(skb)->dma_head + offset; + buffer_info->mapped_as_page = false; + buffer_info->dma = pci_map_single(pdev, skb->data + offset, + size, PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(pdev, buffer_info->dma)) + goto dma_error; buffer_info->next_to_watch = i; len -= size; @@ -2753,7 +2756,7 @@ static int e1000_tx_map(struct e1000_adapter *adapter, frag = &skb_shinfo(skb)->frags[f]; len = frag->size; - offset = 0; + offset = frag->page_offset; while (len) { i++; @@ -2777,7 +2780,12 @@ static int e1000_tx_map(struct e1000_adapter *adapter, buffer_info->length = size; buffer_info->time_stamp = jiffies; - buffer_info->dma = map[f] + offset; + buffer_info->mapped_as_page = true; + buffer_info->dma = pci_map_page(pdev, frag->page, + offset, size, + PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(pdev, buffer_info->dma)) + goto dma_error; buffer_info->next_to_watch = i; len -= size; @@ -2790,6 +2798,22 @@ static int e1000_tx_map(struct e1000_adapter *adapter, tx_ring->buffer_info[first].next_to_watch = i; return count; + +dma_error: + dev_err(&pdev->dev, "TX DMA map failed\n"); + buffer_info->dma = 0; + count--; + + while (count >= 0) { + count--; + i--; + if (i < 0) + i += tx_ring->count; + buffer_info = &tx_ring->buffer_info[i]; + e1000_unmap_and_free_tx_resource(adapter, buffer_info); + } + + return 0; } static void e1000_tx_queue(struct e1000_adapter *adapter, @@ -3483,8 +3507,8 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter, adapter->detect_tx_hung = false; if (tx_ring->buffer_info[eop].time_stamp && time_after(jiffies, tx_ring->buffer_info[eop].time_stamp + - (adapter->tx_timeout_factor * HZ)) - && !(er32(STATUS) & E1000_STATUS_TXOFF)) { + (adapter->tx_timeout_factor * HZ)) && + !(er32(STATUS) & E1000_STATUS_TXOFF)) { /* detected Tx unit hang */ DPRINTK(DRV, ERR, "Detected Tx Unit Hang\n" diff --git a/drivers/net/e1000e/82571.c b/drivers/net/e1000e/82571.c index 62bbc6e0a76a..c1a42cfc80ba 100644 --- a/drivers/net/e1000e/82571.c +++ b/drivers/net/e1000e/82571.c @@ -65,9 +65,11 @@ static s32 e1000_fix_nvm_checksum_82571(struct e1000_hw *hw); static void e1000_initialize_hw_bits_82571(struct e1000_hw *hw); static s32 e1000_setup_link_82571(struct e1000_hw *hw); static void e1000_clear_hw_cntrs_82571(struct e1000_hw *hw); +static void e1000_clear_vfta_82571(struct e1000_hw *hw); static bool e1000_check_mng_mode_82574(struct e1000_hw *hw); static s32 e1000_led_on_82574(struct e1000_hw *hw); static void e1000_put_hw_semaphore_82571(struct e1000_hw *hw); +static void e1000_power_down_phy_copper_82571(struct e1000_hw *hw); /** * e1000_init_phy_params_82571 - Init PHY func ptrs. @@ -87,6 +89,9 @@ static s32 e1000_init_phy_params_82571(struct e1000_hw *hw) phy->autoneg_mask = AUTONEG_ADVERTISE_SPEED_DEFAULT; phy->reset_delay_us = 100; + phy->ops.power_up = e1000_power_up_phy_copper; + phy->ops.power_down = e1000_power_down_phy_copper_82571; + switch (hw->mac.type) { case e1000_82571: case e1000_82572: @@ -949,7 +954,7 @@ static s32 e1000_init_hw_82571(struct e1000_hw *hw) /* Disabling VLAN filtering */ e_dbg("Initializing the IEEE VLAN\n"); - e1000e_clear_vfta(hw); + mac->ops.clear_vfta(hw); /* Setup the receive address. */ /* @@ -1128,13 +1133,13 @@ static void e1000_initialize_hw_bits_82571(struct e1000_hw *hw) } /** - * e1000e_clear_vfta - Clear VLAN filter table + * e1000_clear_vfta_82571 - Clear VLAN filter table * @hw: pointer to the HW structure * * Clears the register array which contains the VLAN filter table by * setting all the values to 0. **/ -void e1000e_clear_vfta(struct e1000_hw *hw) +static void e1000_clear_vfta_82571(struct e1000_hw *hw) { u32 offset; u32 vfta_value = 0; @@ -1351,8 +1356,20 @@ static s32 e1000_setup_fiber_serdes_link_82571(struct e1000_hw *hw) * e1000_check_for_serdes_link_82571 - Check for link (Serdes) * @hw: pointer to the HW structure * - * Checks for link up on the hardware. If link is not up and we have - * a signal, then we need to force link up. + * Reports the link state as up or down. + * + * If autonegotiation is supported by the link partner, the link state is + * determined by the result of autonegotiation. This is the most likely case. + * If autonegotiation is not supported by the link partner, and the link + * has a valid signal, force the link up. + * + * The link state is represented internally here by 4 states: + * + * 1) down + * 2) autoneg_progress + * 3) autoneg_complete (the link sucessfully autonegotiated) + * 4) forced_up (the link has been forced up, it did not autonegotiate) + * **/ static s32 e1000_check_for_serdes_link_82571(struct e1000_hw *hw) { @@ -1378,6 +1395,7 @@ static s32 e1000_check_for_serdes_link_82571(struct e1000_hw *hw) */ mac->serdes_link_state = e1000_serdes_link_autoneg_progress; + mac->serdes_has_link = false; e_dbg("AN_UP -> AN_PROG\n"); } break; @@ -1392,57 +1410,64 @@ static s32 e1000_check_for_serdes_link_82571(struct e1000_hw *hw) if (rxcw & E1000_RXCW_C) { /* Enable autoneg, and unforce link up */ ew32(TXCW, mac->txcw); - ew32(CTRL, - (ctrl & ~E1000_CTRL_SLU)); + ew32(CTRL, (ctrl & ~E1000_CTRL_SLU)); mac->serdes_link_state = e1000_serdes_link_autoneg_progress; + mac->serdes_has_link = false; e_dbg("FORCED_UP -> AN_PROG\n"); } break; case e1000_serdes_link_autoneg_progress: - /* - * If the LU bit is set in the STATUS register, - * autoneg has completed sucessfully. If not, - * try foring the link because the far end may be - * available but not capable of autonegotiation. - */ - if (status & E1000_STATUS_LU) { - mac->serdes_link_state = - e1000_serdes_link_autoneg_complete; - e_dbg("AN_PROG -> AN_UP\n"); + if (rxcw & E1000_RXCW_C) { + /* + * We received /C/ ordered sets, meaning the + * link partner has autonegotiated, and we can + * trust the Link Up (LU) status bit. + */ + if (status & E1000_STATUS_LU) { + mac->serdes_link_state = + e1000_serdes_link_autoneg_complete; + e_dbg("AN_PROG -> AN_UP\n"); + mac->serdes_has_link = true; + } else { + /* Autoneg completed, but failed. */ + mac->serdes_link_state = + e1000_serdes_link_down; + e_dbg("AN_PROG -> DOWN\n"); + } } else { /* - * Disable autoneg, force link up and - * full duplex, and change state to forced + * The link partner did not autoneg. + * Force link up and full duplex, and change + * state to forced. */ - ew32(TXCW, - (mac->txcw & ~E1000_TXCW_ANE)); + ew32(TXCW, (mac->txcw & ~E1000_TXCW_ANE)); ctrl |= (E1000_CTRL_SLU | E1000_CTRL_FD); ew32(CTRL, ctrl); /* Configure Flow Control after link up. */ - ret_val = - e1000e_config_fc_after_link_up(hw); + ret_val = e1000e_config_fc_after_link_up(hw); if (ret_val) { e_dbg("Error config flow control\n"); break; } mac->serdes_link_state = e1000_serdes_link_forced_up; + mac->serdes_has_link = true; e_dbg("AN_PROG -> FORCED_UP\n"); } - mac->serdes_has_link = true; break; case e1000_serdes_link_down: default: - /* The link was down but the receiver has now gained + /* + * The link was down but the receiver has now gained * valid sync, so lets see if we can bring the link - * up. */ + * up. + */ ew32(TXCW, mac->txcw); - ew32(CTRL, - (ctrl & ~E1000_CTRL_SLU)); + ew32(CTRL, (ctrl & ~E1000_CTRL_SLU)); mac->serdes_link_state = e1000_serdes_link_autoneg_progress; e_dbg("DOWN -> AN_PROG\n"); @@ -1455,9 +1480,9 @@ static s32 e1000_check_for_serdes_link_82571(struct e1000_hw *hw) e_dbg("ANYSTATE -> DOWN\n"); } else { /* - * We have sync, and can tolerate one - * invalid (IV) codeword before declaring - * link down, so reread to look again + * We have sync, and can tolerate one invalid (IV) + * codeword before declaring link down, so reread + * to look again. */ udelay(10); rxcw = er32(RXCW); @@ -1526,7 +1551,7 @@ bool e1000e_get_laa_state_82571(struct e1000_hw *hw) * @hw: pointer to the HW structure * @state: enable/disable locally administered address * - * Enable/Disable the current locally administers address state. + * Enable/Disable the current locally administered address state. **/ void e1000e_set_laa_state_82571(struct e1000_hw *hw, bool state) { @@ -1600,6 +1625,28 @@ static s32 e1000_fix_nvm_checksum_82571(struct e1000_hw *hw) } /** + * e1000_power_down_phy_copper_82571 - Remove link during PHY power down + * @hw: pointer to the HW structure + * + * In the case of a PHY power down to save power, or to turn off link during a + * driver unload, or wake on lan is not enabled, remove the link. + **/ +static void e1000_power_down_phy_copper_82571(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + struct e1000_mac_info *mac = &hw->mac; + + if (!(phy->ops.check_reset_block)) + return; + + /* If the management interface is not enabled, then power down */ + if (!(mac->ops.check_mng_mode(hw) || phy->ops.check_reset_block(hw))) + e1000_power_down_phy_copper(hw); + + return; +} + +/** * e1000_clear_hw_cntrs_82571 - Clear device specific hardware counters * @hw: pointer to the HW structure * @@ -1656,6 +1703,8 @@ static struct e1000_mac_operations e82571_mac_ops = { /* .led_on: mac type dependent */ .led_off = e1000e_led_off_generic, .update_mc_addr_list = e1000_update_mc_addr_list_82571, + .write_vfta = e1000_write_vfta_generic, + .clear_vfta = e1000_clear_vfta_82571, .reset_hw = e1000_reset_hw_82571, .init_hw = e1000_init_hw_82571, .setup_link = e1000_setup_link_82571, @@ -1665,6 +1714,7 @@ static struct e1000_mac_operations e82571_mac_ops = { static struct e1000_phy_operations e82_phy_ops_igp = { .acquire = e1000_get_hw_semaphore_82571, + .check_polarity = e1000_check_polarity_igp, .check_reset_block = e1000e_check_reset_block_generic, .commit = NULL, .force_speed_duplex = e1000e_phy_force_speed_duplex_igp, @@ -1682,6 +1732,7 @@ static struct e1000_phy_operations e82_phy_ops_igp = { static struct e1000_phy_operations e82_phy_ops_m88 = { .acquire = e1000_get_hw_semaphore_82571, + .check_polarity = e1000_check_polarity_m88, .check_reset_block = e1000e_check_reset_block_generic, .commit = e1000e_phy_sw_reset, .force_speed_duplex = e1000e_phy_force_speed_duplex_m88, @@ -1699,6 +1750,7 @@ static struct e1000_phy_operations e82_phy_ops_m88 = { static struct e1000_phy_operations e82_phy_ops_bm = { .acquire = e1000_get_hw_semaphore_82571, + .check_polarity = e1000_check_polarity_m88, .check_reset_block = e1000e_check_reset_block_generic, .commit = e1000e_phy_sw_reset, .force_speed_duplex = e1000e_phy_force_speed_duplex_m88, diff --git a/drivers/net/e1000e/e1000.h b/drivers/net/e1000e/e1000.h index c9fcef7f8462..cebbd9079d53 100644 --- a/drivers/net/e1000e/e1000.h +++ b/drivers/net/e1000e/e1000.h @@ -142,6 +142,8 @@ struct e1000_info; #define HV_TNCRS_UPPER PHY_REG(778, 29) /* Transmit with no CRS */ #define HV_TNCRS_LOWER PHY_REG(778, 30) +#define E1000_FCRTV_PCH 0x05F40 /* PCH Flow Control Refresh Timer Value */ + /* BM PHY Copper Specific Status */ #define BM_CS_STATUS 17 #define BM_CS_STATUS_LINK_UP 0x0400 @@ -192,12 +194,15 @@ struct e1000_buffer { unsigned long time_stamp; u16 length; u16 next_to_watch; + u16 mapped_as_page; }; /* Rx */ - /* arrays of page information for packet split */ - struct e1000_ps_page *ps_pages; + struct { + /* arrays of page information for packet split */ + struct e1000_ps_page *ps_pages; + struct page *page; + }; }; - struct page *page; }; struct e1000_ring { @@ -507,7 +512,7 @@ extern s32 e1000e_setup_fiber_serdes_link(struct e1000_hw *hw); extern s32 e1000e_copper_link_setup_m88(struct e1000_hw *hw); extern s32 e1000e_copper_link_setup_igp(struct e1000_hw *hw); extern s32 e1000e_setup_link(struct e1000_hw *hw); -extern void e1000e_clear_vfta(struct e1000_hw *hw); +extern void e1000_clear_vfta_generic(struct e1000_hw *hw); extern void e1000e_init_rx_addrs(struct e1000_hw *hw, u16 rar_count); extern void e1000e_update_mc_addr_list_generic(struct e1000_hw *hw, u8 *mc_addr_list, @@ -523,7 +528,7 @@ extern void e1000e_config_collision_dist(struct e1000_hw *hw); extern s32 e1000e_config_fc_after_link_up(struct e1000_hw *hw); extern s32 e1000e_force_mac_fc(struct e1000_hw *hw); extern s32 e1000e_blink_led(struct e1000_hw *hw); -extern void e1000e_write_vfta(struct e1000_hw *hw, u32 offset, u32 value); +extern void e1000_write_vfta_generic(struct e1000_hw *hw, u32 offset, u32 value); extern void e1000e_reset_adaptive(struct e1000_hw *hw); extern void e1000e_update_adaptive(struct e1000_hw *hw); @@ -566,6 +571,8 @@ extern s32 e1000e_read_kmrn_reg_locked(struct e1000_hw *hw, u32 offset, extern s32 e1000e_phy_has_link_generic(struct e1000_hw *hw, u32 iterations, u32 usec_interval, bool *success); extern s32 e1000e_phy_reset_dsp(struct e1000_hw *hw); +extern void e1000_power_up_phy_copper(struct e1000_hw *hw); +extern void e1000_power_down_phy_copper(struct e1000_hw *hw); extern s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data); extern s32 e1000e_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data); extern s32 e1000e_check_downshift(struct e1000_hw *hw); @@ -583,6 +590,12 @@ extern s32 e1000_get_phy_info_82577(struct e1000_hw *hw); extern s32 e1000_phy_force_speed_duplex_82577(struct e1000_hw *hw); extern s32 e1000_get_cable_length_82577(struct e1000_hw *hw); +extern s32 e1000_check_polarity_m88(struct e1000_hw *hw); +extern s32 e1000_get_phy_info_ife(struct e1000_hw *hw); +extern s32 e1000_check_polarity_ife(struct e1000_hw *hw); +extern s32 e1000_phy_force_speed_duplex_ife(struct e1000_hw *hw); +extern s32 e1000_check_polarity_igp(struct e1000_hw *hw); + static inline s32 e1000_phy_hw_reset(struct e1000_hw *hw) { return hw->phy.ops.reset(hw); diff --git a/drivers/net/e1000e/es2lan.c b/drivers/net/e1000e/es2lan.c index e50579859e06..d2a104794609 100644 --- a/drivers/net/e1000e/es2lan.c +++ b/drivers/net/e1000e/es2lan.c @@ -99,6 +99,8 @@ */ static const u16 e1000_gg82563_cable_length_table[] = { 0, 60, 115, 150, 150, 60, 115, 150, 180, 180, 0xFF }; +#define GG82563_CABLE_LENGTH_TABLE_SIZE \ + ARRAY_SIZE(e1000_gg82563_cable_length_table) static s32 e1000_setup_copper_link_80003es2lan(struct e1000_hw *hw); static s32 e1000_acquire_swfw_sync_80003es2lan(struct e1000_hw *hw, u16 mask); @@ -112,6 +114,7 @@ static s32 e1000_read_kmrn_reg_80003es2lan(struct e1000_hw *hw, u32 offset, u16 *data); static s32 e1000_write_kmrn_reg_80003es2lan(struct e1000_hw *hw, u32 offset, u16 data); +static void e1000_power_down_phy_copper_80003es2lan(struct e1000_hw *hw); /** * e1000_init_phy_params_80003es2lan - Init ESB2 PHY func ptrs. @@ -125,6 +128,9 @@ static s32 e1000_init_phy_params_80003es2lan(struct e1000_hw *hw) if (hw->phy.media_type != e1000_media_type_copper) { phy->type = e1000_phy_none; return 0; + } else { + phy->ops.power_up = e1000_power_up_phy_copper; + phy->ops.power_down = e1000_power_down_phy_copper_80003es2lan; } phy->addr = 1; @@ -694,20 +700,27 @@ static s32 e1000_phy_force_speed_duplex_80003es2lan(struct e1000_hw *hw) static s32 e1000_get_cable_length_80003es2lan(struct e1000_hw *hw) { struct e1000_phy_info *phy = &hw->phy; - s32 ret_val; + s32 ret_val = 0; u16 phy_data, index; ret_val = e1e_rphy(hw, GG82563_PHY_DSP_DISTANCE, &phy_data); if (ret_val) - return ret_val; + goto out; index = phy_data & GG82563_DSPD_CABLE_LENGTH; + + if (index >= GG82563_CABLE_LENGTH_TABLE_SIZE - 5) { + ret_val = -E1000_ERR_PHY; + goto out; + } + phy->min_cable_length = e1000_gg82563_cable_length_table[index]; - phy->max_cable_length = e1000_gg82563_cable_length_table[index+5]; + phy->max_cable_length = e1000_gg82563_cable_length_table[index + 5]; phy->cable_length = (phy->min_cable_length + phy->max_cable_length) / 2; - return 0; +out: + return ret_val; } /** @@ -807,7 +820,7 @@ static s32 e1000_init_hw_80003es2lan(struct e1000_hw *hw) /* Disabling VLAN filtering */ e_dbg("Initializing the IEEE VLAN\n"); - e1000e_clear_vfta(hw); + mac->ops.clear_vfta(hw); /* Setup the receive address. */ e1000e_init_rx_addrs(hw, mac->rar_entry_count); @@ -1294,6 +1307,23 @@ static s32 e1000_write_kmrn_reg_80003es2lan(struct e1000_hw *hw, u32 offset, } /** + * e1000_power_down_phy_copper_80003es2lan - Remove link during PHY power down + * @hw: pointer to the HW structure + * + * In the case of a PHY power down to save power, or to turn off link during a + * driver unload, or wake on lan is not enabled, remove the link. + **/ +static void e1000_power_down_phy_copper_80003es2lan(struct e1000_hw *hw) +{ + /* If the management interface is not enabled, then power down */ + if (!(hw->mac.ops.check_mng_mode(hw) || + hw->phy.ops.check_reset_block(hw))) + e1000_power_down_phy_copper(hw); + + return; +} + +/** * e1000_clear_hw_cntrs_80003es2lan - Clear device specific hardware counters * @hw: pointer to the HW structure * @@ -1350,6 +1380,8 @@ static struct e1000_mac_operations es2_mac_ops = { .led_on = e1000e_led_on_generic, .led_off = e1000e_led_off_generic, .update_mc_addr_list = e1000e_update_mc_addr_list_generic, + .write_vfta = e1000_write_vfta_generic, + .clear_vfta = e1000_clear_vfta_generic, .reset_hw = e1000_reset_hw_80003es2lan, .init_hw = e1000_init_hw_80003es2lan, .setup_link = e1000e_setup_link, @@ -1359,6 +1391,7 @@ static struct e1000_mac_operations es2_mac_ops = { static struct e1000_phy_operations es2_phy_ops = { .acquire = e1000_acquire_phy_80003es2lan, + .check_polarity = e1000_check_polarity_m88, .check_reset_block = e1000e_check_reset_block_generic, .commit = e1000e_phy_sw_reset, .force_speed_duplex = e1000_phy_force_speed_duplex_80003es2lan, diff --git a/drivers/net/e1000e/ethtool.c b/drivers/net/e1000e/ethtool.c index b6243cad3103..0aa50c229c79 100644 --- a/drivers/net/e1000e/ethtool.c +++ b/drivers/net/e1000e/ethtool.c @@ -535,7 +535,8 @@ static int e1000_get_eeprom(struct net_device *netdev, if (ret_val) { /* a read error occurred, throw away the result */ - memset(eeprom_buff, 0xff, sizeof(eeprom_buff)); + memset(eeprom_buff, 0xff, sizeof(u16) * + (last_word - first_word + 1)); } else { /* Device's eeprom is always little-endian, word addressable */ for (i = 0; i < last_word - first_word + 1; i++) diff --git a/drivers/net/e1000e/hw.h b/drivers/net/e1000e/hw.h index 426155c15cef..a7d08dae79c4 100644 --- a/drivers/net/e1000e/hw.h +++ b/drivers/net/e1000e/hw.h @@ -219,7 +219,7 @@ enum e1e_registers { E1000_HICR = 0x08F00, /* Host Interface Control */ }; -/* RSS registers */ +#define E1000_MAX_PHY_ADDR 4 /* IGP01E1000 Specific Registers */ #define IGP01E1000_PHY_PORT_CONFIG 0x10 /* Port Config */ @@ -356,6 +356,7 @@ enum e1e_registers { #define E1000_DEV_ID_80003ES2LAN_COPPER_SPT 0x10BA #define E1000_DEV_ID_80003ES2LAN_SERDES_SPT 0x10BB +#define E1000_DEV_ID_ICH8_82567V_3 0x1501 #define E1000_DEV_ID_ICH8_IGP_M_AMT 0x1049 #define E1000_DEV_ID_ICH8_IGP_AMT 0x104A #define E1000_DEV_ID_ICH8_IGP_C 0x104B @@ -741,6 +742,7 @@ struct e1000_mac_operations { s32 (*check_for_link)(struct e1000_hw *); s32 (*cleanup_led)(struct e1000_hw *); void (*clear_hw_cntrs)(struct e1000_hw *); + void (*clear_vfta)(struct e1000_hw *); s32 (*get_bus_info)(struct e1000_hw *); s32 (*get_link_up_info)(struct e1000_hw *, u16 *, u16 *); s32 (*led_on)(struct e1000_hw *); @@ -751,6 +753,7 @@ struct e1000_mac_operations { s32 (*setup_link)(struct e1000_hw *); s32 (*setup_physical_interface)(struct e1000_hw *); s32 (*setup_led)(struct e1000_hw *); + void (*write_vfta)(struct e1000_hw *, u32, u32); }; /* Function pointers for the PHY. */ @@ -772,6 +775,8 @@ struct e1000_phy_operations { s32 (*set_d3_lplu_state)(struct e1000_hw *, bool); s32 (*write_reg)(struct e1000_hw *, u32, u16); s32 (*write_reg_locked)(struct e1000_hw *, u32, u16); + void (*power_up)(struct e1000_hw *); + void (*power_down)(struct e1000_hw *); }; /* Function pointers for the NVM. */ diff --git a/drivers/net/e1000e/ich8lan.c b/drivers/net/e1000e/ich8lan.c index 568bb259c6fd..7b33be98a2ca 100644 --- a/drivers/net/e1000e/ich8lan.c +++ b/drivers/net/e1000e/ich8lan.c @@ -195,7 +195,6 @@ union ich8_flash_protected_range { static s32 e1000_setup_link_ich8lan(struct e1000_hw *hw); static void e1000_clear_hw_cntrs_ich8lan(struct e1000_hw *hw); static void e1000_initialize_hw_bits_ich8lan(struct e1000_hw *hw); -static s32 e1000_check_polarity_ife_ich8lan(struct e1000_hw *hw); static s32 e1000_erase_flash_bank_ich8lan(struct e1000_hw *hw, u32 bank); static s32 e1000_retry_write_flash_byte_ich8lan(struct e1000_hw *hw, u32 offset, u8 byte); @@ -217,6 +216,7 @@ static s32 e1000_cleanup_led_pchlan(struct e1000_hw *hw); static s32 e1000_led_on_pchlan(struct e1000_hw *hw); static s32 e1000_led_off_pchlan(struct e1000_hw *hw); static s32 e1000_set_lplu_state_pchlan(struct e1000_hw *hw, bool active); +static void e1000_power_down_phy_copper_ich8lan(struct e1000_hw *hw); static void e1000_lan_init_done_ich8lan(struct e1000_hw *hw); static s32 e1000_k1_gig_workaround_hv(struct e1000_hw *hw, bool link); @@ -259,26 +259,37 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw) phy->addr = 1; phy->reset_delay_us = 100; - phy->ops.check_polarity = e1000_check_polarity_ife_ich8lan; phy->ops.read_reg = e1000_read_phy_reg_hv; phy->ops.read_reg_locked = e1000_read_phy_reg_hv_locked; phy->ops.set_d0_lplu_state = e1000_set_lplu_state_pchlan; phy->ops.set_d3_lplu_state = e1000_set_lplu_state_pchlan; phy->ops.write_reg = e1000_write_phy_reg_hv; phy->ops.write_reg_locked = e1000_write_phy_reg_hv_locked; + phy->ops.power_up = e1000_power_up_phy_copper; + phy->ops.power_down = e1000_power_down_phy_copper_ich8lan; phy->autoneg_mask = AUTONEG_ADVERTISE_SPEED_DEFAULT; phy->id = e1000_phy_unknown; e1000e_get_phy_id(hw); phy->type = e1000e_get_phy_type_from_id(phy->id); - if (phy->type == e1000_phy_82577) { + switch (phy->type) { + case e1000_phy_82577: phy->ops.check_polarity = e1000_check_polarity_82577; phy->ops.force_speed_duplex = e1000_phy_force_speed_duplex_82577; - phy->ops.get_cable_length = e1000_get_cable_length_82577; + phy->ops.get_cable_length = e1000_get_cable_length_82577; phy->ops.get_info = e1000_get_phy_info_82577; phy->ops.commit = e1000e_phy_sw_reset; + case e1000_phy_82578: + phy->ops.check_polarity = e1000_check_polarity_m88; + phy->ops.force_speed_duplex = e1000e_phy_force_speed_duplex_m88; + phy->ops.get_cable_length = e1000e_get_cable_length_m88; + phy->ops.get_info = e1000e_get_phy_info_m88; + break; + default: + ret_val = -E1000_ERR_PHY; + break; } return ret_val; @@ -299,6 +310,9 @@ static s32 e1000_init_phy_params_ich8lan(struct e1000_hw *hw) phy->addr = 1; phy->reset_delay_us = 100; + phy->ops.power_up = e1000_power_up_phy_copper; + phy->ops.power_down = e1000_power_down_phy_copper_ich8lan; + /* * We may need to do this twice - once for IGP and if that fails, * we'll set BM func pointers and try again @@ -308,8 +322,10 @@ static s32 e1000_init_phy_params_ich8lan(struct e1000_hw *hw) phy->ops.write_reg = e1000e_write_phy_reg_bm; phy->ops.read_reg = e1000e_read_phy_reg_bm; ret_val = e1000e_determine_phy_address(hw); - if (ret_val) + if (ret_val) { + e_dbg("Cannot determine PHY addr. Erroring out\n"); return ret_val; + } } phy->id = 0; @@ -328,12 +344,18 @@ static s32 e1000_init_phy_params_ich8lan(struct e1000_hw *hw) phy->autoneg_mask = AUTONEG_ADVERTISE_SPEED_DEFAULT; phy->ops.read_reg_locked = e1000e_read_phy_reg_igp_locked; phy->ops.write_reg_locked = e1000e_write_phy_reg_igp_locked; + phy->ops.get_info = e1000e_get_phy_info_igp; + phy->ops.check_polarity = e1000_check_polarity_igp; + phy->ops.force_speed_duplex = e1000e_phy_force_speed_duplex_igp; break; case IFE_E_PHY_ID: case IFE_PLUS_E_PHY_ID: case IFE_C_E_PHY_ID: phy->type = e1000_phy_ife; phy->autoneg_mask = E1000_ALL_NOT_GIG; + phy->ops.get_info = e1000_get_phy_info_ife; + phy->ops.check_polarity = e1000_check_polarity_ife; + phy->ops.force_speed_duplex = e1000_phy_force_speed_duplex_ife; break; case BME1000_E_PHY_ID: phy->type = e1000_phy_bm; @@ -341,14 +363,15 @@ static s32 e1000_init_phy_params_ich8lan(struct e1000_hw *hw) phy->ops.read_reg = e1000e_read_phy_reg_bm; phy->ops.write_reg = e1000e_write_phy_reg_bm; phy->ops.commit = e1000e_phy_sw_reset; + phy->ops.get_info = e1000e_get_phy_info_m88; + phy->ops.check_polarity = e1000_check_polarity_m88; + phy->ops.force_speed_duplex = e1000e_phy_force_speed_duplex_m88; break; default: return -E1000_ERR_PHY; break; } - phy->ops.check_polarity = e1000_check_polarity_ife_ich8lan; - return 0; } @@ -732,77 +755,6 @@ static s32 e1000_check_reset_block_ich8lan(struct e1000_hw *hw) } /** - * e1000_phy_force_speed_duplex_ich8lan - Force PHY speed & duplex - * @hw: pointer to the HW structure - * - * Forces the speed and duplex settings of the PHY. - * This is a function pointer entry point only called by - * PHY setup routines. - **/ -static s32 e1000_phy_force_speed_duplex_ich8lan(struct e1000_hw *hw) -{ - struct e1000_phy_info *phy = &hw->phy; - s32 ret_val; - u16 data; - bool link; - - if (phy->type != e1000_phy_ife) { - ret_val = e1000e_phy_force_speed_duplex_igp(hw); - return ret_val; - } - - ret_val = e1e_rphy(hw, PHY_CONTROL, &data); - if (ret_val) - return ret_val; - - e1000e_phy_force_speed_duplex_setup(hw, &data); - - ret_val = e1e_wphy(hw, PHY_CONTROL, data); - if (ret_val) - return ret_val; - - /* Disable MDI-X support for 10/100 */ - ret_val = e1e_rphy(hw, IFE_PHY_MDIX_CONTROL, &data); - if (ret_val) - return ret_val; - - data &= ~IFE_PMC_AUTO_MDIX; - data &= ~IFE_PMC_FORCE_MDIX; - - ret_val = e1e_wphy(hw, IFE_PHY_MDIX_CONTROL, data); - if (ret_val) - return ret_val; - - e_dbg("IFE PMC: %X\n", data); - - udelay(1); - - if (phy->autoneg_wait_to_complete) { - e_dbg("Waiting for forced speed/duplex link on IFE phy.\n"); - - ret_val = e1000e_phy_has_link_generic(hw, - PHY_FORCE_LIMIT, - 100000, - &link); - if (ret_val) - return ret_val; - - if (!link) - e_dbg("Link taking longer than expected.\n"); - - /* Try once more */ - ret_val = e1000e_phy_has_link_generic(hw, - PHY_FORCE_LIMIT, - 100000, - &link); - if (ret_val) - return ret_val; - } - - return 0; -} - -/** * e1000_sw_lcd_config_ich8lan - SW-based LCD Configuration * @hw: pointer to the HW structure * @@ -1110,7 +1062,8 @@ static s32 e1000_oem_bits_config_ich8lan(struct e1000_hw *hw, bool d0_state) oem_reg |= HV_OEM_BITS_LPLU; } /* Restart auto-neg to activate the bits */ - oem_reg |= HV_OEM_BITS_RESTART_AN; + if (!e1000_check_reset_block(hw)) + oem_reg |= HV_OEM_BITS_RESTART_AN; ret_val = hw->phy.ops.write_reg_locked(hw, HV_OEM_BITS, oem_reg); out: @@ -1253,122 +1206,6 @@ out: } /** - * e1000_get_phy_info_ife_ich8lan - Retrieves various IFE PHY states - * @hw: pointer to the HW structure - * - * Populates "phy" structure with various feature states. - * This function is only called by other family-specific - * routines. - **/ -static s32 e1000_get_phy_info_ife_ich8lan(struct e1000_hw *hw) -{ - struct e1000_phy_info *phy = &hw->phy; - s32 ret_val; - u16 data; - bool link; - - ret_val = e1000e_phy_has_link_generic(hw, 1, 0, &link); - if (ret_val) - return ret_val; - - if (!link) { - e_dbg("Phy info is only valid if link is up\n"); - return -E1000_ERR_CONFIG; - } - - ret_val = e1e_rphy(hw, IFE_PHY_SPECIAL_CONTROL, &data); - if (ret_val) - return ret_val; - phy->polarity_correction = (!(data & IFE_PSC_AUTO_POLARITY_DISABLE)); - - if (phy->polarity_correction) { - ret_val = phy->ops.check_polarity(hw); - if (ret_val) - return ret_val; - } else { - /* Polarity is forced */ - phy->cable_polarity = (data & IFE_PSC_FORCE_POLARITY) - ? e1000_rev_polarity_reversed - : e1000_rev_polarity_normal; - } - - ret_val = e1e_rphy(hw, IFE_PHY_MDIX_CONTROL, &data); - if (ret_val) - return ret_val; - - phy->is_mdix = (data & IFE_PMC_MDIX_STATUS); - - /* The following parameters are undefined for 10/100 operation. */ - phy->cable_length = E1000_CABLE_LENGTH_UNDEFINED; - phy->local_rx = e1000_1000t_rx_status_undefined; - phy->remote_rx = e1000_1000t_rx_status_undefined; - - return 0; -} - -/** - * e1000_get_phy_info_ich8lan - Calls appropriate PHY type get_phy_info - * @hw: pointer to the HW structure - * - * Wrapper for calling the get_phy_info routines for the appropriate phy type. - * This is a function pointer entry point called by drivers - * or other shared routines. - **/ -static s32 e1000_get_phy_info_ich8lan(struct e1000_hw *hw) -{ - switch (hw->phy.type) { - case e1000_phy_ife: - return e1000_get_phy_info_ife_ich8lan(hw); - break; - case e1000_phy_igp_3: - case e1000_phy_bm: - case e1000_phy_82578: - case e1000_phy_82577: - return e1000e_get_phy_info_igp(hw); - break; - default: - break; - } - - return -E1000_ERR_PHY_TYPE; -} - -/** - * e1000_check_polarity_ife_ich8lan - Check cable polarity for IFE PHY - * @hw: pointer to the HW structure - * - * Polarity is determined on the polarity reversal feature being enabled. - * This function is only called by other family-specific - * routines. - **/ -static s32 e1000_check_polarity_ife_ich8lan(struct e1000_hw *hw) -{ - struct e1000_phy_info *phy = &hw->phy; - s32 ret_val; - u16 phy_data, offset, mask; - - /* - * Polarity is determined based on the reversal feature being enabled. - */ - if (phy->polarity_correction) { - offset = IFE_PHY_EXTENDED_STATUS_CONTROL; - mask = IFE_PESC_POLARITY_REVERSED; - } else { - offset = IFE_PHY_SPECIAL_CONTROL; - mask = IFE_PSC_FORCE_POLARITY; - } - - ret_val = e1e_rphy(hw, offset, &phy_data); - - if (!ret_val) - phy->cable_polarity = (phy_data & mask) - ? e1000_rev_polarity_reversed - : e1000_rev_polarity_normal; - - return ret_val; -} - -/** * e1000_set_lplu_state_pchlan - Set Low Power Link Up state * @hw: pointer to the HW structure * @active: true to enable LPLU, false to disable @@ -1740,7 +1577,7 @@ static s32 e1000_flash_cycle_init_ich8lan(struct e1000_hw *hw) if (hsfsts.hsf_status.flcinprog == 0) { /* * There is no cycle running at present, - * so we can start a cycle + * so we can start a cycle. * Begin by setting Flash Cycle Done. */ hsfsts.hsf_status.flcdone = 1; @@ -1748,7 +1585,7 @@ static s32 e1000_flash_cycle_init_ich8lan(struct e1000_hw *hw) ret_val = 0; } else { /* - * otherwise poll for sometime so the current + * Otherwise poll for sometime so the current * cycle has a chance to end before giving up. */ for (i = 0; i < ICH_FLASH_READ_COMMAND_TIMEOUT; i++) { @@ -2638,7 +2475,6 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw) ctrl |= E1000_CTRL_PHY_RST; } ret_val = e1000_acquire_swflag_ich8lan(hw); - /* Whether or not the swflag was acquired, we need to reset the part */ e_dbg("Issuing a global reset to ich8lan\n"); ew32(CTRL, (ctrl | E1000_CTRL_RST)); msleep(20); @@ -3197,6 +3033,7 @@ void e1000e_disable_gig_wol_ich8lan(struct e1000_hw *hw) u32 phy_ctrl; switch (hw->mac.type) { + case e1000_ich8lan: case e1000_ich9lan: case e1000_ich10lan: case e1000_pchlan: @@ -3391,6 +3228,23 @@ static s32 e1000_get_cfg_done_ich8lan(struct e1000_hw *hw) } /** + * e1000_power_down_phy_copper_ich8lan - Remove link during PHY power down + * @hw: pointer to the HW structure + * + * In the case of a PHY power down to save power, or to turn off link during a + * driver unload, or wake on lan is not enabled, remove the link. + **/ +static void e1000_power_down_phy_copper_ich8lan(struct e1000_hw *hw) +{ + /* If the management interface is not enabled, then power down */ + if (!(hw->mac.ops.check_mng_mode(hw) || + hw->phy.ops.check_reset_block(hw))) + e1000_power_down_phy_copper(hw); + + return; +} + +/** * e1000_clear_hw_cntrs_ich8lan - Clear statistical counters * @hw: pointer to the HW structure * @@ -3459,10 +3313,8 @@ static struct e1000_phy_operations ich8_phy_ops = { .acquire = e1000_acquire_swflag_ich8lan, .check_reset_block = e1000_check_reset_block_ich8lan, .commit = NULL, - .force_speed_duplex = e1000_phy_force_speed_duplex_ich8lan, .get_cfg_done = e1000_get_cfg_done_ich8lan, .get_cable_length = e1000e_get_cable_length_igp_2, - .get_info = e1000_get_phy_info_ich8lan, .read_reg = e1000e_read_phy_reg_igp, .release = e1000_release_swflag_ich8lan, .reset = e1000_phy_hw_reset_ich8lan, @@ -3545,6 +3397,7 @@ struct e1000_info e1000_pch_info = { | FLAG_HAS_AMT | FLAG_HAS_FLASH | FLAG_HAS_JUMBO_FRAMES + | FLAG_DISABLE_FC_PAUSE_TIME /* errata */ | FLAG_APME_IN_WUC, .pba = 26, .max_hw_frame_size = 4096, diff --git a/drivers/net/e1000e/lib.c b/drivers/net/e1000e/lib.c index f690a1055b41..a86c17548c1e 100644 --- a/drivers/net/e1000e/lib.c +++ b/drivers/net/e1000e/lib.c @@ -82,7 +82,24 @@ s32 e1000e_get_bus_info_pcie(struct e1000_hw *hw) } /** - * e1000e_write_vfta - Write value to VLAN filter table + * e1000_clear_vfta_generic - Clear VLAN filter table + * @hw: pointer to the HW structure + * + * Clears the register array which contains the VLAN filter table by + * setting all the values to 0. + **/ +void e1000_clear_vfta_generic(struct e1000_hw *hw) +{ + u32 offset; + + for (offset = 0; offset < E1000_VLAN_FILTER_TBL_SIZE; offset++) { + E1000_WRITE_REG_ARRAY(hw, E1000_VFTA, offset, 0); + e1e_flush(); + } +} + +/** + * e1000_write_vfta_generic - Write value to VLAN filter table * @hw: pointer to the HW structure * @offset: register offset in VLAN filter table * @value: register value written to VLAN filter table @@ -90,7 +107,7 @@ s32 e1000e_get_bus_info_pcie(struct e1000_hw *hw) * Writes value at the given offset in the register array which stores * the VLAN filter table. **/ -void e1000e_write_vfta(struct e1000_hw *hw, u32 offset, u32 value) +void e1000_write_vfta_generic(struct e1000_hw *hw, u32 offset, u32 value) { E1000_WRITE_REG_ARRAY(hw, E1000_VFTA, offset, value); e1e_flush(); @@ -1069,7 +1086,6 @@ s32 e1000e_config_fc_after_link_up(struct e1000_hw *hw) * 1 | 1 | 0 | 0 | e1000_fc_none * 1 | 1 | 0 | 1 | e1000_fc_rx_pause * - * * Are both PAUSE bits set to 1? If so, this implies * Symmetric Flow Control is enabled at both ends. The * ASM_DIR bits are irrelevant per the spec. @@ -1107,7 +1123,6 @@ s32 e1000e_config_fc_after_link_up(struct e1000_hw *hw) * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result *-------|---------|-------|---------|-------------------- * 0 | 1 | 1 | 1 | e1000_fc_tx_pause - * */ else if (!(mii_nway_adv_reg & NWAY_AR_PAUSE) && (mii_nway_adv_reg & NWAY_AR_ASM_DIR) && @@ -1123,7 +1138,6 @@ s32 e1000e_config_fc_after_link_up(struct e1000_hw *hw) * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result *-------|---------|-------|---------|-------------------- * 1 | 1 | 0 | 1 | e1000_fc_rx_pause - * */ else if ((mii_nway_adv_reg & NWAY_AR_PAUSE) && (mii_nway_adv_reg & NWAY_AR_ASM_DIR) && @@ -2346,7 +2360,7 @@ static s32 e1000_mng_write_cmd_header(struct e1000_hw *hw, } /** - * e1000_mng_host_if_write - Writes to the manageability host interface + * e1000_mng_host_if_write - Write to the manageability host interface * @hw: pointer to the HW structure * @buffer: pointer to the host interface buffer * @length: size of the buffer diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 11a527484e18..c3105c5087e0 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -534,10 +534,17 @@ next_desc: static void e1000_put_txbuf(struct e1000_adapter *adapter, struct e1000_buffer *buffer_info) { - buffer_info->dma = 0; + if (buffer_info->dma) { + if (buffer_info->mapped_as_page) + pci_unmap_page(adapter->pdev, buffer_info->dma, + buffer_info->length, PCI_DMA_TODEVICE); + else + pci_unmap_single(adapter->pdev, buffer_info->dma, + buffer_info->length, + PCI_DMA_TODEVICE); + buffer_info->dma = 0; + } if (buffer_info->skb) { - skb_dma_unmap(&adapter->pdev->dev, buffer_info->skb, - DMA_TO_DEVICE); dev_kfree_skb_any(buffer_info->skb); buffer_info->skb = NULL; } @@ -672,8 +679,8 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter) adapter->detect_tx_hung = 0; if (tx_ring->buffer_info[i].time_stamp && time_after(jiffies, tx_ring->buffer_info[i].time_stamp - + (adapter->tx_timeout_factor * HZ)) - && !(er32(STATUS) & E1000_STATUS_TXOFF)) { + + (adapter->tx_timeout_factor * HZ)) && + !(er32(STATUS) & E1000_STATUS_TXOFF)) { schedule_work(&adapter->print_hang_task); netif_stop_queue(netdev); } @@ -2031,11 +2038,14 @@ static void e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid) E1000_MNG_DHCP_COOKIE_STATUS_VLAN) && (vid == adapter->mng_vlan_id)) return; + /* add VID to filter table */ - index = (vid >> 5) & 0x7F; - vfta = E1000_READ_REG_ARRAY(hw, E1000_VFTA, index); - vfta |= (1 << (vid & 0x1F)); - e1000e_write_vfta(hw, index, vfta); + if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER) { + index = (vid >> 5) & 0x7F; + vfta = E1000_READ_REG_ARRAY(hw, E1000_VFTA, index); + vfta |= (1 << (vid & 0x1F)); + hw->mac.ops.write_vfta(hw, index, vfta); + } } static void e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) @@ -2060,10 +2070,12 @@ static void e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) } /* remove VID from filter table */ - index = (vid >> 5) & 0x7F; - vfta = E1000_READ_REG_ARRAY(hw, E1000_VFTA, index); - vfta &= ~(1 << (vid & 0x1F)); - e1000e_write_vfta(hw, index, vfta); + if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER) { + index = (vid >> 5) & 0x7F; + vfta = E1000_READ_REG_ARRAY(hw, E1000_VFTA, index); + vfta &= ~(1 << (vid & 0x1F)); + hw->mac.ops.write_vfta(hw, index, vfta); + } } static void e1000_update_mng_vlan(struct e1000_adapter *adapter) @@ -2636,18 +2648,8 @@ static void e1000_configure(struct e1000_adapter *adapter) **/ void e1000e_power_up_phy(struct e1000_adapter *adapter) { - u16 mii_reg = 0; - - /* Just clear the power down bit to wake the phy back up */ - if (adapter->hw.phy.media_type == e1000_media_type_copper) { - /* - * According to the manual, the phy will retain its - * settings across a power-down/up cycle - */ - e1e_rphy(&adapter->hw, PHY_CONTROL, &mii_reg); - mii_reg &= ~MII_CR_POWER_DOWN; - e1e_wphy(&adapter->hw, PHY_CONTROL, mii_reg); - } + if (adapter->hw.phy.ops.power_up) + adapter->hw.phy.ops.power_up(&adapter->hw); adapter->hw.mac.ops.setup_link(&adapter->hw); } @@ -2655,35 +2657,17 @@ void e1000e_power_up_phy(struct e1000_adapter *adapter) /** * e1000_power_down_phy - Power down the PHY * - * Power down the PHY so no link is implied when interface is down - * The PHY cannot be powered down is management or WoL is active + * Power down the PHY so no link is implied when interface is down. + * The PHY cannot be powered down if management or WoL is active. */ static void e1000_power_down_phy(struct e1000_adapter *adapter) { - struct e1000_hw *hw = &adapter->hw; - u16 mii_reg; - /* WoL is enabled */ if (adapter->wol) return; - /* non-copper PHY? */ - if (adapter->hw.phy.media_type != e1000_media_type_copper) - return; - - /* reset is blocked because of a SoL/IDER session */ - if (e1000e_check_mng_mode(hw) || e1000_check_reset_block(hw)) - return; - - /* manageability (AMT) is enabled */ - if (er32(MANC) & E1000_MANC_SMBUS_EN) - return; - - /* power down the PHY */ - e1e_rphy(hw, PHY_CONTROL, &mii_reg); - mii_reg |= MII_CR_POWER_DOWN; - e1e_wphy(hw, PHY_CONTROL, mii_reg); - mdelay(1); + if (adapter->hw.phy.ops.power_down) + adapter->hw.phy.ops.power_down(&adapter->hw); } /** @@ -2760,25 +2744,38 @@ void e1000e_reset(struct e1000_adapter *adapter) /* * flow control settings * - * The high water mark must be low enough to fit two full frame + * The high water mark must be low enough to fit one full frame * (or the size used for early receive) above it in the Rx FIFO. * Set it to the lower of: * - 90% of the Rx FIFO size, and * - the full Rx FIFO size minus the early receive size (for parts * with ERT support assuming ERT set to E1000_ERT_2048), or - * - the full Rx FIFO size minus two full frames + * - the full Rx FIFO size minus one full frame */ - if ((adapter->flags & FLAG_HAS_ERT) && - (adapter->netdev->mtu > ETH_DATA_LEN)) - hwm = min(((pba << 10) * 9 / 10), - ((pba << 10) - (E1000_ERT_2048 << 3))); - else - hwm = min(((pba << 10) * 9 / 10), - ((pba << 10) - (2 * adapter->max_frame_size))); + if (hw->mac.type == e1000_pchlan) { + /* + * Workaround PCH LOM adapter hangs with certain network + * loads. If hangs persist, try disabling Tx flow control. + */ + if (adapter->netdev->mtu > ETH_DATA_LEN) { + fc->high_water = 0x3500; + fc->low_water = 0x1500; + } else { + fc->high_water = 0x5000; + fc->low_water = 0x3000; + } + } else { + if ((adapter->flags & FLAG_HAS_ERT) && + (adapter->netdev->mtu > ETH_DATA_LEN)) + hwm = min(((pba << 10) * 9 / 10), + ((pba << 10) - (E1000_ERT_2048 << 3))); + else + hwm = min(((pba << 10) * 9 / 10), + ((pba << 10) - adapter->max_frame_size)); - fc->high_water = hwm & E1000_FCRTH_RTH; /* 8-byte granularity */ - fc->low_water = (fc->high_water - (2 * adapter->max_frame_size)); - fc->low_water &= E1000_FCRTL_RTL; /* 8-byte granularity */ + fc->high_water = hwm & E1000_FCRTH_RTH; /* 8-byte granularity */ + fc->low_water = fc->high_water - 8; + } if (adapter->flags & FLAG_DISABLE_FC_PAUSE_TIME) fc->pause_time = 0xFFFF; @@ -2804,6 +2801,10 @@ void e1000e_reset(struct e1000_adapter *adapter) if (mac->ops.init_hw(hw)) e_err("Hardware Error\n"); + /* additional part of the flow-control workaround above */ + if (hw->mac.type == e1000_pchlan) + ew32(FCRTV_PCH, 0x1000); + e1000_update_mng_vlan(adapter); /* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */ @@ -3612,7 +3613,7 @@ static void e1000_watchdog_task(struct work_struct *work) case SPEED_100: txb2b = 0; netdev->tx_queue_len = 100; - /* maybe add some timeout factor ? */ + adapter->tx_timeout_factor = 10; break; } @@ -3890,23 +3891,14 @@ static int e1000_tx_map(struct e1000_adapter *adapter, unsigned int mss) { struct e1000_ring *tx_ring = adapter->tx_ring; + struct pci_dev *pdev = adapter->pdev; struct e1000_buffer *buffer_info; unsigned int len = skb_headlen(skb); - unsigned int offset, size, count = 0, i; + unsigned int offset = 0, size, count = 0, i; unsigned int f; - dma_addr_t *map; i = tx_ring->next_to_use; - if (skb_dma_map(&adapter->pdev->dev, skb, DMA_TO_DEVICE)) { - dev_err(&adapter->pdev->dev, "TX DMA map failed\n"); - adapter->tx_dma_failed++; - return 0; - } - - map = skb_shinfo(skb)->dma_maps; - offset = 0; - while (len) { buffer_info = &tx_ring->buffer_info[i]; size = min(len, max_per_txd); @@ -3914,11 +3906,15 @@ static int e1000_tx_map(struct e1000_adapter *adapter, buffer_info->length = size; buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; - buffer_info->dma = skb_shinfo(skb)->dma_head + offset; - count++; + buffer_info->dma = pci_map_single(pdev, skb->data + offset, + size, PCI_DMA_TODEVICE); + buffer_info->mapped_as_page = false; + if (pci_dma_mapping_error(pdev, buffer_info->dma)) + goto dma_error; len -= size; offset += size; + count++; if (len) { i++; @@ -3932,7 +3928,7 @@ static int e1000_tx_map(struct e1000_adapter *adapter, frag = &skb_shinfo(skb)->frags[f]; len = frag->size; - offset = 0; + offset = frag->page_offset; while (len) { i++; @@ -3945,7 +3941,12 @@ static int e1000_tx_map(struct e1000_adapter *adapter, buffer_info->length = size; buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; - buffer_info->dma = map[f] + offset; + buffer_info->dma = pci_map_page(pdev, frag->page, + offset, size, + PCI_DMA_TODEVICE); + buffer_info->mapped_as_page = true; + if (pci_dma_mapping_error(pdev, buffer_info->dma)) + goto dma_error; len -= size; offset += size; @@ -3957,6 +3958,22 @@ static int e1000_tx_map(struct e1000_adapter *adapter, tx_ring->buffer_info[first].next_to_watch = i; return count; + +dma_error: + dev_err(&pdev->dev, "TX DMA map failed\n"); + buffer_info->dma = 0; + count--; + + while (count >= 0) { + count--; + i--; + if (i < 0) + i += tx_ring->count; + buffer_info = &tx_ring->buffer_info[i]; + e1000_put_txbuf(adapter, buffer_info);; + } + + return 0; } static void e1000_tx_queue(struct e1000_adapter *adapter, @@ -4029,8 +4046,8 @@ static int e1000_transfer_dhcp_info(struct e1000_adapter *adapter, u16 length, offset; if (vlan_tx_tag_present(skb)) { - if (!((vlan_tx_tag_get(skb) == adapter->hw.mng_cookie.vlan_id) - && (adapter->hw.mng_cookie.status & + if (!((vlan_tx_tag_get(skb) == adapter->hw.mng_cookie.vlan_id) && + (adapter->hw.mng_cookie.status & E1000_MNG_DHCP_COOKIE_STATUS_VLAN))) return 0; } @@ -4284,8 +4301,10 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) while (test_and_set_bit(__E1000_RESETTING, &adapter->state)) msleep(1); - /* e1000e_down has a dependency on max_frame_size */ + /* e1000e_down -> e1000e_reset dependent on max_frame_size & mtu */ adapter->max_frame_size = max_frame; + e_info("changing MTU from %d to %d\n", netdev->mtu, new_mtu); + netdev->mtu = new_mtu; if (netif_running(netdev)) e1000e_down(adapter); @@ -4315,9 +4334,6 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) adapter->rx_buffer_len = ETH_FRAME_LEN + VLAN_HLEN + ETH_FCS_LEN; - e_info("changing MTU from %d to %d\n", netdev->mtu, new_mtu); - netdev->mtu = new_mtu; - if (netif_running(netdev)) e1000e_up(adapter); else @@ -5273,17 +5289,17 @@ static void __devexit e1000_remove(struct pci_dev *pdev) cancel_work_sync(&adapter->print_hang_task); flush_scheduled_work(); + if (!(netdev->flags & IFF_UP)) + e1000_power_down_phy(adapter); + + unregister_netdev(netdev); + /* * Release control of h/w to f/w. If f/w is AMT enabled, this * would have already happened in close and is redundant. */ e1000_release_hw_control(adapter); - unregister_netdev(netdev); - - if (!e1000_check_reset_block(&adapter->hw)) - e1000_phy_hw_reset(&adapter->hw); - e1000e_reset_interrupt_capability(adapter); kfree(adapter->tx_ring); kfree(adapter->rx_ring); @@ -5349,6 +5365,7 @@ static struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IGP_C), board_ich8lan }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IGP_M), board_ich8lan }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_IGP_M_AMT), board_ich8lan }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH8_82567V_3), board_ich8lan }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IFE), board_ich9lan }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_ICH9_IFE_G), board_ich9lan }, diff --git a/drivers/net/e1000e/phy.c b/drivers/net/e1000e/phy.c index 99d53fae4307..55a2c0acfee7 100644 --- a/drivers/net/e1000e/phy.c +++ b/drivers/net/e1000e/phy.c @@ -44,6 +44,8 @@ static s32 e1000_access_phy_debug_regs_hv(struct e1000_hw *hw, u32 offset, /* Cable length tables */ static const u16 e1000_m88_cable_length_table[] = { 0, 50, 80, 110, 140, 140, E1000_CABLE_LENGTH_UNDEFINED }; +#define M88E1000_CABLE_LENGTH_TABLE_SIZE \ + ARRAY_SIZE(e1000_m88_cable_length_table) static const u16 e1000_igp_2_cable_length_table[] = { 0, 0, 0, 0, 0, 0, 0, 0, 3, 5, 8, 11, 13, 16, 18, 21, 0, 0, 0, 3, @@ -71,7 +73,6 @@ static const u16 e1000_igp_2_cable_length_table[] = #define I82577_CFG_ASSERT_CRS_ON_TX (1 << 15) #define I82577_CFG_ENABLE_DOWNSHIFT (3 << 10) /* auto downshift 100/10 */ #define I82577_CTRL_REG 23 -#define I82577_CTRL_DOWNSHIFT_MASK (7 << 10) /* 82577 specific PHY registers */ #define I82577_PHY_CTRL_2 18 @@ -152,10 +153,10 @@ s32 e1000e_get_phy_id(struct e1000_hw *hw) goto out; /* - * If the PHY ID is still unknown, we may have an 82577i - * without link. We will try again after setting Slow - * MDIC mode. No harm in trying again in this case since - * the PHY ID is unknown at this point anyway + * If the PHY ID is still unknown, we may have an 82577 + * without link. We will try again after setting Slow MDIC + * mode. No harm in trying again in this case since the PHY + * ID is unknown at this point anyway. */ ret_val = phy->ops.acquire(hw); if (ret_val) @@ -660,15 +661,6 @@ s32 e1000_copper_link_setup_82577(struct e1000_hw *hw) phy_data |= I82577_CFG_ENABLE_DOWNSHIFT; ret_val = phy->ops.write_reg(hw, I82577_CFG_REG, phy_data); - if (ret_val) - goto out; - - /* Set number of link attempts before downshift */ - ret_val = phy->ops.read_reg(hw, I82577_CTRL_REG, &phy_data); - if (ret_val) - goto out; - phy_data &= ~I82577_CTRL_DOWNSHIFT_MASK; - ret_val = phy->ops.write_reg(hw, I82577_CTRL_REG, phy_data); out: return ret_val; @@ -1330,17 +1322,22 @@ s32 e1000e_phy_force_speed_duplex_m88(struct e1000_hw *hw) return ret_val; if (!link) { - /* - * We didn't get link. - * Reset the DSP and cross our fingers. - */ - ret_val = e1e_wphy(hw, M88E1000_PHY_PAGE_SELECT, - 0x001d); - if (ret_val) - return ret_val; - ret_val = e1000e_phy_reset_dsp(hw); - if (ret_val) - return ret_val; + if (hw->phy.type != e1000_phy_m88) { + e_dbg("Link taking longer than expected.\n"); + } else { + /* + * We didn't get link. + * Reset the DSP and cross our fingers. + */ + ret_val = e1e_wphy(hw, + M88E1000_PHY_PAGE_SELECT, + 0x001d); + if (ret_val) + return ret_val; + ret_val = e1000e_phy_reset_dsp(hw); + if (ret_val) + return ret_val; + } } /* Try once more */ @@ -1350,6 +1347,9 @@ s32 e1000e_phy_force_speed_duplex_m88(struct e1000_hw *hw) return ret_val; } + if (hw->phy.type != e1000_phy_m88) + return 0; + ret_val = e1e_rphy(hw, M88E1000_EXT_PHY_SPEC_CTRL, &phy_data); if (ret_val) return ret_val; @@ -1379,6 +1379,73 @@ s32 e1000e_phy_force_speed_duplex_m88(struct e1000_hw *hw) } /** + * e1000_phy_force_speed_duplex_ife - Force PHY speed & duplex + * @hw: pointer to the HW structure + * + * Forces the speed and duplex settings of the PHY. + * This is a function pointer entry point only called by + * PHY setup routines. + **/ +s32 e1000_phy_force_speed_duplex_ife(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 data; + bool link; + + ret_val = e1e_rphy(hw, PHY_CONTROL, &data); + if (ret_val) + goto out; + + e1000e_phy_force_speed_duplex_setup(hw, &data); + + ret_val = e1e_wphy(hw, PHY_CONTROL, data); + if (ret_val) + goto out; + + /* Disable MDI-X support for 10/100 */ + ret_val = e1e_rphy(hw, IFE_PHY_MDIX_CONTROL, &data); + if (ret_val) + goto out; + + data &= ~IFE_PMC_AUTO_MDIX; + data &= ~IFE_PMC_FORCE_MDIX; + + ret_val = e1e_wphy(hw, IFE_PHY_MDIX_CONTROL, data); + if (ret_val) + goto out; + + e_dbg("IFE PMC: %X\n", data); + + udelay(1); + + if (phy->autoneg_wait_to_complete) { + e_dbg("Waiting for forced speed/duplex link on IFE phy.\n"); + + ret_val = e1000e_phy_has_link_generic(hw, + PHY_FORCE_LIMIT, + 100000, + &link); + if (ret_val) + goto out; + + if (!link) + e_dbg("Link taking longer than expected.\n"); + + /* Try once more */ + ret_val = e1000e_phy_has_link_generic(hw, + PHY_FORCE_LIMIT, + 100000, + &link); + if (ret_val) + goto out; + } + +out: + return ret_val; +} + +/** * e1000e_phy_force_speed_duplex_setup - Configure forced PHY speed/duplex * @hw: pointer to the HW structure * @phy_ctrl: pointer to current value of PHY_CONTROL @@ -1533,8 +1600,8 @@ s32 e1000e_check_downshift(struct e1000_hw *hw) switch (phy->type) { case e1000_phy_m88: case e1000_phy_gg82563: + case e1000_phy_bm: case e1000_phy_82578: - case e1000_phy_82577: offset = M88E1000_PHY_SPEC_STATUS; mask = M88E1000_PSSR_DOWNSHIFT; break; @@ -1565,7 +1632,7 @@ s32 e1000e_check_downshift(struct e1000_hw *hw) * * Polarity is determined based on the PHY specific status register. **/ -static s32 e1000_check_polarity_m88(struct e1000_hw *hw) +s32 e1000_check_polarity_m88(struct e1000_hw *hw) { struct e1000_phy_info *phy = &hw->phy; s32 ret_val; @@ -1590,7 +1657,7 @@ static s32 e1000_check_polarity_m88(struct e1000_hw *hw) * Polarity is determined based on the PHY port status register, and the * current speed (since there is no polarity at 100Mbps). **/ -static s32 e1000_check_polarity_igp(struct e1000_hw *hw) +s32 e1000_check_polarity_igp(struct e1000_hw *hw) { struct e1000_phy_info *phy = &hw->phy; s32 ret_val; @@ -1628,6 +1695,39 @@ static s32 e1000_check_polarity_igp(struct e1000_hw *hw) } /** + * e1000_check_polarity_ife - Check cable polarity for IFE PHY + * @hw: pointer to the HW structure + * + * Polarity is determined on the polarity reversal feature being enabled. + **/ +s32 e1000_check_polarity_ife(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 phy_data, offset, mask; + + /* + * Polarity is determined based on the reversal feature being enabled. + */ + if (phy->polarity_correction) { + offset = IFE_PHY_EXTENDED_STATUS_CONTROL; + mask = IFE_PESC_POLARITY_REVERSED; + } else { + offset = IFE_PHY_SPECIAL_CONTROL; + mask = IFE_PSC_FORCE_POLARITY; + } + + ret_val = e1e_rphy(hw, offset, &phy_data); + + if (!ret_val) + phy->cable_polarity = (phy_data & mask) + ? e1000_rev_polarity_reversed + : e1000_rev_polarity_normal; + + return ret_val; +} + +/** * e1000_wait_autoneg - Wait for auto-neg completion * @hw: pointer to the HW structure * @@ -1727,15 +1827,21 @@ s32 e1000e_get_cable_length_m88(struct e1000_hw *hw) ret_val = e1e_rphy(hw, M88E1000_PHY_SPEC_STATUS, &phy_data); if (ret_val) - return ret_val; + goto out; index = (phy_data & M88E1000_PSSR_CABLE_LENGTH) >> - M88E1000_PSSR_CABLE_LENGTH_SHIFT; + M88E1000_PSSR_CABLE_LENGTH_SHIFT; + if (index >= M88E1000_CABLE_LENGTH_TABLE_SIZE - 1) { + ret_val = -E1000_ERR_PHY; + goto out; + } + phy->min_cable_length = e1000_m88_cable_length_table[index]; - phy->max_cable_length = e1000_m88_cable_length_table[index+1]; + phy->max_cable_length = e1000_m88_cable_length_table[index + 1]; phy->cable_length = (phy->min_cable_length + phy->max_cable_length) / 2; +out: return ret_val; } @@ -1746,7 +1852,7 @@ s32 e1000e_get_cable_length_m88(struct e1000_hw *hw) * The automatic gain control (agc) normalizes the amplitude of the * received signal, adjusting for the attenuation produced by the * cable. By reading the AGC registers, which represent the - * combination of course and fine gain value, the value can be put + * combination of coarse and fine gain value, the value can be put * into a lookup table to obtain the approximate cable length * for each channel. **/ @@ -1771,7 +1877,7 @@ s32 e1000e_get_cable_length_igp_2(struct e1000_hw *hw) /* * Getting bits 15:9, which represent the combination of - * course and fine gain values. The result is a number + * coarse and fine gain values. The result is a number * that can be put into the lookup table to obtain the * approximate cable length. */ @@ -1825,7 +1931,7 @@ s32 e1000e_get_phy_info_m88(struct e1000_hw *hw) u16 phy_data; bool link; - if (hw->phy.media_type != e1000_media_type_copper) { + if (phy->media_type != e1000_media_type_copper) { e_dbg("Phy info is only valid for copper media\n"); return -E1000_ERR_CONFIG; } @@ -1946,6 +2052,61 @@ s32 e1000e_get_phy_info_igp(struct e1000_hw *hw) } /** + * e1000_get_phy_info_ife - Retrieves various IFE PHY states + * @hw: pointer to the HW structure + * + * Populates "phy" structure with various feature states. + **/ +s32 e1000_get_phy_info_ife(struct e1000_hw *hw) +{ + struct e1000_phy_info *phy = &hw->phy; + s32 ret_val; + u16 data; + bool link; + + ret_val = e1000e_phy_has_link_generic(hw, 1, 0, &link); + if (ret_val) + goto out; + + if (!link) { + e_dbg("Phy info is only valid if link is up\n"); + ret_val = -E1000_ERR_CONFIG; + goto out; + } + + ret_val = e1e_rphy(hw, IFE_PHY_SPECIAL_CONTROL, &data); + if (ret_val) + goto out; + phy->polarity_correction = (data & IFE_PSC_AUTO_POLARITY_DISABLE) + ? false : true; + + if (phy->polarity_correction) { + ret_val = e1000_check_polarity_ife(hw); + if (ret_val) + goto out; + } else { + /* Polarity is forced */ + phy->cable_polarity = (data & IFE_PSC_FORCE_POLARITY) + ? e1000_rev_polarity_reversed + : e1000_rev_polarity_normal; + } + + ret_val = e1e_rphy(hw, IFE_PHY_MDIX_CONTROL, &data); + if (ret_val) + goto out; + + phy->is_mdix = (data & IFE_PMC_MDIX_STATUS) ? true : false; + + /* The following parameters are undefined for 10/100 operation. */ + phy->cable_length = E1000_CABLE_LENGTH_UNDEFINED; + phy->local_rx = e1000_1000t_rx_status_undefined; + phy->remote_rx = e1000_1000t_rx_status_undefined; + +out: + return ret_val; +} + +/** * e1000e_phy_sw_reset - PHY software reset * @hw: pointer to the HW structure * @@ -2199,28 +2360,34 @@ enum e1000_phy_type e1000e_get_phy_type_from_id(u32 phy_id) s32 e1000e_determine_phy_address(struct e1000_hw *hw) { s32 ret_val = -E1000_ERR_PHY_TYPE; - u32 phy_addr= 0; - u32 i = 0; + u32 phy_addr = 0; + u32 i; enum e1000_phy_type phy_type = e1000_phy_unknown; - do { - for (phy_addr = 0; phy_addr < 4; phy_addr++) { - hw->phy.addr = phy_addr; + hw->phy.id = phy_type; + + for (phy_addr = 0; phy_addr < E1000_MAX_PHY_ADDR; phy_addr++) { + hw->phy.addr = phy_addr; + i = 0; + + do { e1000e_get_phy_id(hw); phy_type = e1000e_get_phy_type_from_id(hw->phy.id); - /* + /* * If phy_type is valid, break - we found our * PHY address */ if (phy_type != e1000_phy_unknown) { ret_val = 0; - break; + goto out; } - } - i++; - } while ((ret_val != 0) && (i < 100)); + msleep(1); + i++; + } while (i < 10); + } +out: return ret_val; } @@ -2474,7 +2641,7 @@ static s32 e1000_access_phy_wakeup_reg_bm(struct e1000_hw *hw, u32 offset, /* Gig must be disabled for MDIO accesses to page 800 */ if ((hw->mac.type == e1000_pchlan) && (!(er32(PHY_CTRL) & E1000_PHY_CTRL_GBE_DISABLE))) - e_dbg("Attempting to access page 800 while gig enabled\n"); + e_dbg("Attempting to access page 800 while gig enabled.\n"); /* All operations in this function are phy address 1 */ hw->phy.addr = 1; @@ -2484,20 +2651,26 @@ static s32 e1000_access_phy_wakeup_reg_bm(struct e1000_hw *hw, u32 offset, (BM_WUC_ENABLE_PAGE << IGP_PAGE_SHIFT)); ret_val = e1000e_read_phy_reg_mdic(hw, BM_WUC_ENABLE_REG, &phy_reg); - if (ret_val) + if (ret_val) { + e_dbg("Could not read PHY page 769\n"); goto out; + } /* First clear bit 4 to avoid a power state change */ phy_reg &= ~(BM_WUC_HOST_WU_BIT); ret_val = e1000e_write_phy_reg_mdic(hw, BM_WUC_ENABLE_REG, phy_reg); - if (ret_val) + if (ret_val) { + e_dbg("Could not clear PHY page 769 bit 4\n"); goto out; + } /* Write bit 2 = 1, and clear bit 4 to 769_17 */ ret_val = e1000e_write_phy_reg_mdic(hw, BM_WUC_ENABLE_REG, phy_reg | BM_WUC_ENABLE_BIT); - if (ret_val) + if (ret_val) { + e_dbg("Could not write PHY page 769 bit 2\n"); goto out; + } /* Select page 800 */ ret_val = e1000e_write_phy_reg_mdic(hw, IGP01E1000_PHY_PAGE_SELECT, @@ -2505,21 +2678,25 @@ static s32 e1000_access_phy_wakeup_reg_bm(struct e1000_hw *hw, u32 offset, /* Write the page 800 offset value using opcode 0x11 */ ret_val = e1000e_write_phy_reg_mdic(hw, BM_WUC_ADDRESS_OPCODE, reg); - if (ret_val) + if (ret_val) { + e_dbg("Could not write address opcode to page 800\n"); goto out; + } if (read) { /* Read the page 800 value using opcode 0x12 */ ret_val = e1000e_read_phy_reg_mdic(hw, BM_WUC_DATA_OPCODE, data); } else { - /* Read the page 800 value using opcode 0x12 */ + /* Write the page 800 value using opcode 0x12 */ ret_val = e1000e_write_phy_reg_mdic(hw, BM_WUC_DATA_OPCODE, *data); } - if (ret_val) + if (ret_val) { + e_dbg("Could not access data value from page 800\n"); goto out; + } /* * Restore 769_17.2 to its original value @@ -2530,12 +2707,53 @@ static s32 e1000_access_phy_wakeup_reg_bm(struct e1000_hw *hw, u32 offset, /* Clear 769_17.2 */ ret_val = e1000e_write_phy_reg_mdic(hw, BM_WUC_ENABLE_REG, phy_reg); + if (ret_val) { + e_dbg("Could not clear PHY page 769 bit 2\n"); + goto out; + } out: return ret_val; } /** + * e1000_power_up_phy_copper - Restore copper link in case of PHY power down + * @hw: pointer to the HW structure + * + * In the case of a PHY power down to save power, or to turn off link during a + * driver unload, or wake on lan is not enabled, restore the link to previous + * settings. + **/ +void e1000_power_up_phy_copper(struct e1000_hw *hw) +{ + u16 mii_reg = 0; + + /* The PHY will retain its settings across a power down/up cycle */ + e1e_rphy(hw, PHY_CONTROL, &mii_reg); + mii_reg &= ~MII_CR_POWER_DOWN; + e1e_wphy(hw, PHY_CONTROL, mii_reg); +} + +/** + * e1000_power_down_phy_copper - Restore copper link in case of PHY power down + * @hw: pointer to the HW structure + * + * In the case of a PHY power down to save power, or to turn off link during a + * driver unload, or wake on lan is not enabled, restore the link to previous + * settings. + **/ +void e1000_power_down_phy_copper(struct e1000_hw *hw) +{ + u16 mii_reg = 0; + + /* The PHY will retain its settings across a power down/up cycle */ + e1e_rphy(hw, PHY_CONTROL, &mii_reg); + mii_reg |= MII_CR_POWER_DOWN; + e1e_wphy(hw, PHY_CONTROL, mii_reg); + msleep(1); +} + +/** * e1000e_commit_phy - Soft PHY reset * @hw: pointer to the HW structure * @@ -2658,19 +2876,18 @@ static s32 __e1000_read_phy_reg_hv(struct e1000_hw *hw, u32 offset, u16 *data, page = 0; if (reg > MAX_PHY_MULTI_PAGE_REG) { - if ((hw->phy.type != e1000_phy_82578) || - ((reg != I82578_ADDR_REG) && - (reg != I82578_ADDR_REG + 1))) { - u32 phy_addr = hw->phy.addr; - - hw->phy.addr = 1; - - /* Page is shifted left, PHY expects (page x 32) */ - ret_val = e1000e_write_phy_reg_mdic(hw, - IGP01E1000_PHY_PAGE_SELECT, - (page << IGP_PAGE_SHIFT)); - hw->phy.addr = phy_addr; - } + u32 phy_addr = hw->phy.addr; + + hw->phy.addr = 1; + + /* Page is shifted left, PHY expects (page x 32) */ + ret_val = e1000e_write_phy_reg_mdic(hw, + IGP01E1000_PHY_PAGE_SELECT, + (page << IGP_PAGE_SHIFT)); + hw->phy.addr = phy_addr; + + if (ret_val) + goto out; } ret_val = e1000e_read_phy_reg_mdic(hw, MAX_PHY_REG_ADDRESS & reg, @@ -2678,7 +2895,7 @@ static s32 __e1000_read_phy_reg_hv(struct e1000_hw *hw, u32 offset, u16 *data, out: /* Revert to MDIO fast mode, if applicable */ if ((hw->phy.type == e1000_phy_82577) && in_slow_mode) - ret_val = e1000_set_mdio_slow_mode_hv(hw, false); + ret_val |= e1000_set_mdio_slow_mode_hv(hw, false); if (!locked) hw->phy.ops.release(hw); @@ -2784,19 +3001,18 @@ static s32 __e1000_write_phy_reg_hv(struct e1000_hw *hw, u32 offset, u16 data, } if (reg > MAX_PHY_MULTI_PAGE_REG) { - if ((hw->phy.type != e1000_phy_82578) || - ((reg != I82578_ADDR_REG) && - (reg != I82578_ADDR_REG + 1))) { - u32 phy_addr = hw->phy.addr; - - hw->phy.addr = 1; - - /* Page is shifted left, PHY expects (page x 32) */ - ret_val = e1000e_write_phy_reg_mdic(hw, - IGP01E1000_PHY_PAGE_SELECT, - (page << IGP_PAGE_SHIFT)); - hw->phy.addr = phy_addr; - } + u32 phy_addr = hw->phy.addr; + + hw->phy.addr = 1; + + /* Page is shifted left, PHY expects (page x 32) */ + ret_val = e1000e_write_phy_reg_mdic(hw, + IGP01E1000_PHY_PAGE_SELECT, + (page << IGP_PAGE_SHIFT)); + hw->phy.addr = phy_addr; + + if (ret_val) + goto out; } ret_val = e1000e_write_phy_reg_mdic(hw, MAX_PHY_REG_ADDRESS & reg, @@ -2805,7 +3021,7 @@ static s32 __e1000_write_phy_reg_hv(struct e1000_hw *hw, u32 offset, u16 data, out: /* Revert to MDIO fast mode, if applicable */ if ((hw->phy.type == e1000_phy_82577) && in_slow_mode) - ret_val = e1000_set_mdio_slow_mode_hv(hw, false); + ret_val |= e1000_set_mdio_slow_mode_hv(hw, false); if (!locked) hw->phy.ops.release(hw); diff --git a/drivers/net/e2100.c b/drivers/net/e2100.c index d2f6ee1a6290..ca93c9a9d372 100644 --- a/drivers/net/e2100.c +++ b/drivers/net/e2100.c @@ -186,9 +186,9 @@ static int __init e21_probe1(struct net_device *dev, int ioaddr) return -EBUSY; /* First check the station address for the Ctron prefix. */ - if (inb(ioaddr + E21_SAPROM + 0) != 0x00 - || inb(ioaddr + E21_SAPROM + 1) != 0x00 - || inb(ioaddr + E21_SAPROM + 2) != 0x1d) { + if (inb(ioaddr + E21_SAPROM + 0) != 0x00 || + inb(ioaddr + E21_SAPROM + 1) != 0x00 || + inb(ioaddr + E21_SAPROM + 2) != 0x1d) { retval = -ENODEV; goto out; } diff --git a/drivers/net/ehea/ehea_main.c b/drivers/net/ehea/ehea_main.c index 7f8fcc2fa748..7b62336e6736 100644 --- a/drivers/net/ehea/ehea_main.c +++ b/drivers/net/ehea/ehea_main.c @@ -189,8 +189,8 @@ static void ehea_update_firmware_handles(void) for (k = 0; k < EHEA_MAX_PORTS; k++) { struct ehea_port *port = adapter->port[k]; - if (!port || (port->state != EHEA_PORT_UP) - || (num_ports == 0)) + if (!port || (port->state != EHEA_PORT_UP) || + (num_ports == 0)) continue; for (l = 0; @@ -657,8 +657,8 @@ static int get_skb_hdr(struct sk_buff *skb, void **iphdr, static void ehea_proc_skb(struct ehea_port_res *pr, struct ehea_cqe *cqe, struct sk_buff *skb) { - int vlan_extracted = (cqe->status & EHEA_CQE_VLAN_TAG_XTRACT) - && pr->port->vgrp; + int vlan_extracted = ((cqe->status & EHEA_CQE_VLAN_TAG_XTRACT) && + pr->port->vgrp); if (use_lro) { if (vlan_extracted) @@ -1389,8 +1389,8 @@ out: int ehea_rem_smrs(struct ehea_port_res *pr) { - if ((ehea_rem_mr(&pr->send_mr)) - || (ehea_rem_mr(&pr->recv_mr))) + if ((ehea_rem_mr(&pr->send_mr)) || + (ehea_rem_mr(&pr->recv_mr))) return -EIO; else return 0; @@ -2031,8 +2031,8 @@ static void ehea_xmit2(struct sk_buff *skb, struct net_device *dev, write_ip_start_end(swqe, skb); if (iph->protocol == IPPROTO_UDP) { - if ((iph->frag_off & IP_MF) - || (iph->frag_off & IP_OFFSET)) + if ((iph->frag_off & IP_MF) || + (iph->frag_off & IP_OFFSET)) /* IP fragment, so don't change cs */ swqe->tx_control &= ~EHEA_SWQE_TCP_CHECKSUM; else @@ -2077,8 +2077,8 @@ static void ehea_xmit3(struct sk_buff *skb, struct net_device *dev, write_tcp_offset_end(swqe, skb); } else if (iph->protocol == IPPROTO_UDP) { - if ((iph->frag_off & IP_MF) - || (iph->frag_off & IP_OFFSET)) + if ((iph->frag_off & IP_MF) || + (iph->frag_off & IP_OFFSET)) /* IP fragment, so don't change cs */ swqe->tx_control |= EHEA_SWQE_CRC | EHEA_SWQE_IMM_DATA_PRESENT; diff --git a/drivers/net/ehea/ehea_qmr.c b/drivers/net/ehea/ehea_qmr.c index bc7c5b7abb88..18d405f78c0f 100644 --- a/drivers/net/ehea/ehea_qmr.c +++ b/drivers/net/ehea/ehea_qmr.c @@ -837,8 +837,8 @@ static u64 ehea_reg_mr_section(int top, int dir, int idx, u64 *pt, hret = ehea_h_register_rpage_mr(adapter->handle, mr->handle, 0, 0, pt_abs, EHEA_MAX_RPAGE); - if ((hret != H_SUCCESS) - && (hret != H_PAGE_REGISTERED)) { + if ((hret != H_SUCCESS) && + (hret != H_PAGE_REGISTERED)) { ehea_h_free_resource(adapter->handle, mr->handle, FORCE_FREE); ehea_error("register_rpage_mr failed"); diff --git a/drivers/net/epic100.c b/drivers/net/epic100.c index 703b4c8e9b4d..41494f7b2ec8 100644 --- a/drivers/net/epic100.c +++ b/drivers/net/epic100.c @@ -630,8 +630,8 @@ static int mdio_read(struct net_device *dev, int phy_id, int location) barrier(); if ((inl(ioaddr + MIICtrl) & MII_READOP) == 0) { /* Work around read failure bug. */ - if (phy_id == 1 && location < 6 - && inw(ioaddr + MIIData) == 0xffff) { + if (phy_id == 1 && location < 6 && + inw(ioaddr + MIIData) == 0xffff) { outl(read_cmd, ioaddr + MIICtrl); continue; } @@ -1205,8 +1205,8 @@ static int epic_rx(struct net_device *dev, int budget) } /* Check if the packet is long enough to accept without copying to a minimally-sized skbuff. */ - if (pkt_len < rx_copybreak - && (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { + if (pkt_len < rx_copybreak && + (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { skb_reserve(skb, 2); /* 16 byte align the IP header */ pci_dma_sync_single_for_cpu(ep->pci_dev, ep->rx_ring[entry].bufaddr, diff --git a/drivers/net/fealnx.c b/drivers/net/fealnx.c index e173515790c0..dac4e595589e 100644 --- a/drivers/net/fealnx.c +++ b/drivers/net/fealnx.c @@ -1629,8 +1629,8 @@ static int netdev_rx(struct net_device *dev) if (debug) printk(KERN_DEBUG " netdev_rx() status was %8.8x.\n", rx_status); - if ((!((rx_status & RXFSD) && (rx_status & RXLSD))) - || (rx_status & ErrorSummary)) { + if ((!((rx_status & RXFSD) && (rx_status & RXLSD))) || + (rx_status & ErrorSummary)) { if (rx_status & ErrorSummary) { /* there was a fatal error */ if (debug) printk(KERN_DEBUG @@ -1655,8 +1655,8 @@ static int netdev_rx(struct net_device *dev) cur = np->cur_rx; while (desno <= np->really_rx_count) { ++desno; - if ((!(cur->status & RXOWN)) - && (cur->status & RXLSD)) + if ((!(cur->status & RXOWN)) && + (cur->status & RXLSD)) break; /* goto next rx descriptor */ cur = cur->next_desc_logical; @@ -1786,8 +1786,8 @@ static void __set_rx_mode(struct net_device *dev) if (dev->flags & IFF_PROMISC) { /* Set promiscuous. */ memset(mc_filter, 0xff, sizeof(mc_filter)); rx_mode = CR_W_PROM | CR_W_AB | CR_W_AM; - } else if ((dev->mc_count > multicast_filter_limit) - || (dev->flags & IFF_ALLMULTI)) { + } else if ((dev->mc_count > multicast_filter_limit) || + (dev->flags & IFF_ALLMULTI)) { /* Too many to match, or accept all multicasts. */ memset(mc_filter, 0xff, sizeof(mc_filter)); rx_mode = CR_W_AB | CR_W_AM; diff --git a/drivers/net/gianfar_sysfs.c b/drivers/net/gianfar_sysfs.c index b31c9c8876e6..b98c6c512299 100644 --- a/drivers/net/gianfar_sysfs.c +++ b/drivers/net/gianfar_sysfs.c @@ -62,8 +62,8 @@ static ssize_t gfar_set_bd_stash(struct device *dev, /* Find out the new setting */ if (!strncmp("on", buf, count - 1) || !strncmp("1", buf, count - 1)) new_setting = 1; - else if (!strncmp("off", buf, count - 1) - || !strncmp("0", buf, count - 1)) + else if (!strncmp("off", buf, count - 1) || + !strncmp("0", buf, count - 1)) new_setting = 0; else return count; diff --git a/drivers/net/hamachi.c b/drivers/net/hamachi.c index 5d8c6333070e..ea85075a89a2 100644 --- a/drivers/net/hamachi.c +++ b/drivers/net/hamachi.c @@ -1566,8 +1566,8 @@ static int hamachi_rx(struct net_device *dev) #endif /* Check if the packet is long enough to accept without copying to a minimally-sized skbuff. */ - if (pkt_len < rx_copybreak - && (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { + if (pkt_len < rx_copybreak && + (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { #ifdef RX_CHECKSUM printk(KERN_ERR "%s: rx_copybreak non-zero " "not good with RX_CHECKSUM\n", dev->name); @@ -1722,10 +1722,10 @@ static void hamachi_error(struct net_device *dev, int intr_status) readl(ioaddr + 0x370); readl(ioaddr + 0x3F0); } - if ((intr_status & ~(LinkChange|StatsMax|NegotiationChange|IntrRxDone|IntrTxDone)) - && hamachi_debug) + if ((intr_status & ~(LinkChange|StatsMax|NegotiationChange|IntrRxDone|IntrTxDone)) && + hamachi_debug) printk(KERN_ERR "%s: Something Wicked happened! %4.4x.\n", - dev->name, intr_status); + dev->name, intr_status); /* Hmmmmm, it's not clear how to recover from PCI faults. */ if (intr_status & (IntrTxPCIErr | IntrTxPCIFault)) hmp->stats.tx_fifo_errors++; diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index fe893c91a01b..ae5f11c8fc13 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -167,10 +167,7 @@ static inline struct net_device *bpq_get_ax25_dev(struct net_device *dev) static inline int dev_is_ethdev(struct net_device *dev) { - return ( - dev->type == ARPHRD_ETHER - && strncmp(dev->name, "dummy", 5) - ); + return (dev->type == ARPHRD_ETHER && strncmp(dev->name, "dummy", 5)); } /* ------------------------------------------------------------------------ */ @@ -186,7 +183,7 @@ static int bpq_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_ty struct ethhdr *eth; struct bpqdev *bpq; - if (dev_net(dev) != &init_net) + if (!net_eq(dev_net(dev), &init_net)) goto drop; if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) @@ -552,7 +549,7 @@ static int bpq_device_event(struct notifier_block *this,unsigned long event, voi { struct net_device *dev = (struct net_device *)ptr; - if (dev_net(dev) != &init_net) + if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; if (!dev_is_ethdev(dev)) diff --git a/drivers/net/hamradio/dmascc.c b/drivers/net/hamradio/dmascc.c index 950f3bb21f9d..9ee76b42668f 100644 --- a/drivers/net/hamradio/dmascc.c +++ b/drivers/net/hamradio/dmascc.c @@ -331,8 +331,8 @@ static int __init dmascc_init(void) for (i = 0; i < MAX_NUM_DEVS && io[i]; i++) { j = (io[i] - hw[h].io_region) / hw[h].io_delta; - if (j >= 0 && j < hw[h].num_devs - && hw[h].io_region + + if (j >= 0 && j < hw[h].num_devs && + hw[h].io_region + j * hw[h].io_delta == io[i]) { base[j] = io[i]; } @@ -396,8 +396,8 @@ static int __init dmascc_init(void) t_val = inb(t1[i]) + (inb(t1[i]) << 8); /* Also check whether counter did wrap */ - if (t_val == 0 - || t_val > TMR_0_HZ / HZ * 10) + if (t_val == 0 || + t_val > TMR_0_HZ / HZ * 10) counting[i] = 0; delay[i] = jiffies - start[i]; } diff --git a/drivers/net/hp-plus.c b/drivers/net/hp-plus.c index 0486cbe01adb..efdbcad63c67 100644 --- a/drivers/net/hp-plus.c +++ b/drivers/net/hp-plus.c @@ -187,8 +187,8 @@ static int __init hpp_probe1(struct net_device *dev, int ioaddr) return -EBUSY; /* Check for the HP+ signature, 50 48 0x 53. */ - if (inw(ioaddr + HP_ID) != 0x4850 - || (inw(ioaddr + HP_PAGING) & 0xfff0) != 0x5300) { + if (inw(ioaddr + HP_ID) != 0x4850 || + (inw(ioaddr + HP_PAGING) & 0xfff0) != 0x5300) { retval = -ENODEV; goto out; } diff --git a/drivers/net/hp100.c b/drivers/net/hp100.c index dd8665138062..90f890e7c5e1 100644 --- a/drivers/net/hp100.c +++ b/drivers/net/hp100.c @@ -993,8 +993,8 @@ static void hp100_mmuinit(struct net_device *dev) if (lp->mode == 1) { /* only needed for Busmaster */ int xmit_stop, recv_stop; - if ((lp->chip == HP100_CHIPID_RAINIER) - || (lp->chip == HP100_CHIPID_SHASTA)) { + if ((lp->chip == HP100_CHIPID_RAINIER) || + (lp->chip == HP100_CHIPID_SHASTA)) { int pdl_stop; /* diff --git a/drivers/net/ibm_newemac/core.c b/drivers/net/ibm_newemac/core.c index af117c626e73..fb5e019169ee 100644 --- a/drivers/net/ibm_newemac/core.c +++ b/drivers/net/ibm_newemac/core.c @@ -1976,27 +1976,27 @@ static int emac_ethtool_set_settings(struct net_device *ndev, if (cmd->autoneg == AUTONEG_DISABLE) { switch (cmd->speed) { case SPEED_10: - if (cmd->duplex == DUPLEX_HALF - && !(f & SUPPORTED_10baseT_Half)) + if (cmd->duplex == DUPLEX_HALF && + !(f & SUPPORTED_10baseT_Half)) return -EINVAL; - if (cmd->duplex == DUPLEX_FULL - && !(f & SUPPORTED_10baseT_Full)) + if (cmd->duplex == DUPLEX_FULL && + !(f & SUPPORTED_10baseT_Full)) return -EINVAL; break; case SPEED_100: - if (cmd->duplex == DUPLEX_HALF - && !(f & SUPPORTED_100baseT_Half)) + if (cmd->duplex == DUPLEX_HALF && + !(f & SUPPORTED_100baseT_Half)) return -EINVAL; - if (cmd->duplex == DUPLEX_FULL - && !(f & SUPPORTED_100baseT_Full)) + if (cmd->duplex == DUPLEX_FULL && + !(f & SUPPORTED_100baseT_Full)) return -EINVAL; break; case SPEED_1000: - if (cmd->duplex == DUPLEX_HALF - && !(f & SUPPORTED_1000baseT_Half)) + if (cmd->duplex == DUPLEX_HALF && + !(f & SUPPORTED_1000baseT_Half)) return -EINVAL; - if (cmd->duplex == DUPLEX_FULL - && !(f & SUPPORTED_1000baseT_Full)) + if (cmd->duplex == DUPLEX_FULL && + !(f & SUPPORTED_1000baseT_Full)) return -EINVAL; break; default: diff --git a/drivers/net/igb/igb.h b/drivers/net/igb/igb.h index c458d9b188ba..b1c1eb88893f 100644 --- a/drivers/net/igb/igb.h +++ b/drivers/net/igb/igb.h @@ -137,12 +137,13 @@ struct igb_buffer { unsigned long time_stamp; u16 length; u16 next_to_watch; + u16 mapped_as_page; }; /* RX */ struct { struct page *page; - u64 page_dma; - unsigned int page_offset; + dma_addr_t page_dma; + u16 page_offset; }; }; }; diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c index bb1a6eeade06..16349ba68736 100644 --- a/drivers/net/igb/igb_main.c +++ b/drivers/net/igb/igb_main.c @@ -2654,16 +2654,27 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter) void igb_unmap_and_free_tx_resource(struct igb_ring *tx_ring, struct igb_buffer *buffer_info) { - buffer_info->dma = 0; + if (buffer_info->dma) { + if (buffer_info->mapped_as_page) + pci_unmap_page(tx_ring->pdev, + buffer_info->dma, + buffer_info->length, + PCI_DMA_TODEVICE); + else + pci_unmap_single(tx_ring->pdev, + buffer_info->dma, + buffer_info->length, + PCI_DMA_TODEVICE); + buffer_info->dma = 0; + } if (buffer_info->skb) { - skb_dma_unmap(&tx_ring->pdev->dev, - buffer_info->skb, - DMA_TO_DEVICE); dev_kfree_skb_any(buffer_info->skb); buffer_info->skb = NULL; } buffer_info->time_stamp = 0; - /* buffer_info must be completely set up in the transmit path */ + buffer_info->length = 0; + buffer_info->next_to_watch = 0; + buffer_info->mapped_as_page = false; } /** @@ -3561,24 +3572,19 @@ static inline int igb_tx_map_adv(struct igb_ring *tx_ring, struct sk_buff *skb, unsigned int len = skb_headlen(skb); unsigned int count = 0, i; unsigned int f; - dma_addr_t *map; i = tx_ring->next_to_use; - if (skb_dma_map(&pdev->dev, skb, DMA_TO_DEVICE)) { - dev_err(&pdev->dev, "TX DMA map failed\n"); - return 0; - } - - map = skb_shinfo(skb)->dma_maps; - buffer_info = &tx_ring->buffer_info[i]; BUG_ON(len >= IGB_MAX_DATA_PER_TXD); buffer_info->length = len; /* set time_stamp *before* dma to help avoid a possible race */ buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; - buffer_info->dma = skb_shinfo(skb)->dma_head; + buffer_info->dma = pci_map_single(pdev, skb->data, len, + PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(pdev, buffer_info->dma)) + goto dma_error; for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) { struct skb_frag_struct *frag; @@ -3595,7 +3601,15 @@ static inline int igb_tx_map_adv(struct igb_ring *tx_ring, struct sk_buff *skb, buffer_info->length = len; buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; - buffer_info->dma = map[count]; + buffer_info->mapped_as_page = true; + buffer_info->dma = pci_map_page(pdev, + frag->page, + frag->page_offset, + len, + PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(pdev, buffer_info->dma)) + goto dma_error; + count++; } @@ -3603,6 +3617,29 @@ static inline int igb_tx_map_adv(struct igb_ring *tx_ring, struct sk_buff *skb, tx_ring->buffer_info[first].next_to_watch = i; return ++count; + +dma_error: + dev_err(&pdev->dev, "TX DMA map failed\n"); + + /* clear timestamp and dma mappings for failed buffer_info mapping */ + buffer_info->dma = 0; + buffer_info->time_stamp = 0; + buffer_info->length = 0; + buffer_info->next_to_watch = 0; + buffer_info->mapped_as_page = false; + count--; + + /* clear timestamp and dma mappings for remaining portion of packet */ + while (count >= 0) { + count--; + i--; + if (i < 0) + i += tx_ring->count; + buffer_info = &tx_ring->buffer_info[i]; + igb_unmap_and_free_tx_resource(tx_ring, buffer_info); + } + + return 0; } static inline void igb_tx_queue_adv(struct igb_ring *tx_ring, @@ -3755,7 +3792,7 @@ netdev_tx_t igb_xmit_frame_ring_adv(struct sk_buff *skb, * has occured and we need to rewind the descriptor queue */ count = igb_tx_map_adv(tx_ring, skb, first); - if (count <= 0) { + if (!count) { dev_kfree_skb_any(skb); tx_ring->buffer_info[first].time_stamp = 0; tx_ring->next_to_use = first; @@ -4937,9 +4974,8 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) tx_ring->detect_tx_hung = false; if (tx_ring->buffer_info[i].time_stamp && time_after(jiffies, tx_ring->buffer_info[i].time_stamp + - (adapter->tx_timeout_factor * HZ)) - && !(rd32(E1000_STATUS) & - E1000_STATUS_TXOFF)) { + (adapter->tx_timeout_factor * HZ)) && + !(rd32(E1000_STATUS) & E1000_STATUS_TXOFF)) { /* detected Tx unit hang */ dev_err(&tx_ring->pdev->dev, diff --git a/drivers/net/igbvf/igbvf.h b/drivers/net/igbvf/igbvf.h index 8e9b67ebbf8b..3d1ee7a8478e 100644 --- a/drivers/net/igbvf/igbvf.h +++ b/drivers/net/igbvf/igbvf.h @@ -117,6 +117,7 @@ struct igbvf_buffer { unsigned long time_stamp; u16 length; u16 next_to_watch; + u16 mapped_as_page; }; /* Rx */ struct { diff --git a/drivers/net/igbvf/netdev.c b/drivers/net/igbvf/netdev.c index e01f44597a26..a127620dc653 100644 --- a/drivers/net/igbvf/netdev.c +++ b/drivers/net/igbvf/netdev.c @@ -366,10 +366,20 @@ next_desc: static void igbvf_put_txbuf(struct igbvf_adapter *adapter, struct igbvf_buffer *buffer_info) { - buffer_info->dma = 0; + if (buffer_info->dma) { + if (buffer_info->mapped_as_page) + pci_unmap_page(adapter->pdev, + buffer_info->dma, + buffer_info->length, + PCI_DMA_TODEVICE); + else + pci_unmap_single(adapter->pdev, + buffer_info->dma, + buffer_info->length, + PCI_DMA_TODEVICE); + buffer_info->dma = 0; + } if (buffer_info->skb) { - skb_dma_unmap(&adapter->pdev->dev, buffer_info->skb, - DMA_TO_DEVICE); dev_kfree_skb_any(buffer_info->skb); buffer_info->skb = NULL; } @@ -817,8 +827,8 @@ static bool igbvf_clean_tx_irq(struct igbvf_ring *tx_ring) adapter->detect_tx_hung = false; if (tx_ring->buffer_info[i].time_stamp && time_after(jiffies, tx_ring->buffer_info[i].time_stamp + - (adapter->tx_timeout_factor * HZ)) - && !(er32(STATUS) & E1000_STATUS_TXOFF)) { + (adapter->tx_timeout_factor * HZ)) && + !(er32(STATUS) & E1000_STATUS_TXOFF)) { tx_desc = IGBVF_TX_DESC_ADV(*tx_ring, i); /* detected Tx unit hang */ @@ -2088,27 +2098,24 @@ static inline int igbvf_tx_map_adv(struct igbvf_adapter *adapter, unsigned int first) { struct igbvf_buffer *buffer_info; + struct pci_dev *pdev = adapter->pdev; unsigned int len = skb_headlen(skb); unsigned int count = 0, i; unsigned int f; - dma_addr_t *map; i = tx_ring->next_to_use; - if (skb_dma_map(&adapter->pdev->dev, skb, DMA_TO_DEVICE)) { - dev_err(&adapter->pdev->dev, "TX DMA map failed\n"); - return 0; - } - - map = skb_shinfo(skb)->dma_maps; - buffer_info = &tx_ring->buffer_info[i]; BUG_ON(len >= IGBVF_MAX_DATA_PER_TXD); buffer_info->length = len; /* set time_stamp *before* dma to help avoid a possible race */ buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; - buffer_info->dma = skb_shinfo(skb)->dma_head; + buffer_info->dma = pci_map_single(pdev, skb->data, len, + PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(pdev, buffer_info->dma)) + goto dma_error; + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) { struct skb_frag_struct *frag; @@ -2125,14 +2132,44 @@ static inline int igbvf_tx_map_adv(struct igbvf_adapter *adapter, buffer_info->length = len; buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; - buffer_info->dma = map[count]; + buffer_info->mapped_as_page = true; + buffer_info->dma = pci_map_page(pdev, + frag->page, + frag->page_offset, + len, + PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(pdev, buffer_info->dma)) + goto dma_error; count++; } tx_ring->buffer_info[i].skb = skb; tx_ring->buffer_info[first].next_to_watch = i; - return count + 1; + return ++count; + +dma_error: + dev_err(&pdev->dev, "TX DMA map failed\n"); + + /* clear timestamp and dma mappings for failed buffer_info mapping */ + buffer_info->dma = 0; + buffer_info->time_stamp = 0; + buffer_info->length = 0; + buffer_info->next_to_watch = 0; + buffer_info->mapped_as_page = false; + count--; + + /* clear timestamp and dma mappings for remaining portion of packet */ + while (count >= 0) { + count--; + i--; + if (i < 0) + i += tx_ring->count; + buffer_info = &tx_ring->buffer_info[i]; + igbvf_put_txbuf(adapter, buffer_info); + } + + return 0; } static inline void igbvf_tx_queue_adv(struct igbvf_adapter *adapter, diff --git a/drivers/net/irda/irda-usb.c b/drivers/net/irda/irda-usb.c index ae6eab3e5eed..e8e33bb9d876 100644 --- a/drivers/net/irda/irda-usb.c +++ b/drivers/net/irda/irda-usb.c @@ -1124,11 +1124,11 @@ static int stir421x_patch_device(struct irda_usb_cb *self) * The actual image starts after the "STMP" keyword * so forward to the firmware header tag */ - for (i = 0; (fw->data[i] != STIR421X_PATCH_END_OF_HDR_TAG) - && (i < fw->size); i++) ; + for (i = 0; (fw->data[i] != STIR421X_PATCH_END_OF_HDR_TAG) && + (i < fw->size); i++) ; /* here we check for the out of buffer case */ - if ((STIR421X_PATCH_END_OF_HDR_TAG == fw->data[i]) - && (i < STIR421X_PATCH_CODE_OFFSET)) { + if ((STIR421X_PATCH_END_OF_HDR_TAG == fw->data[i]) && + (i < STIR421X_PATCH_CODE_OFFSET)) { if (!memcmp(fw->data + i + 1, STIR421X_PATCH_STMP_TAG, sizeof(STIR421X_PATCH_STMP_TAG) - 1)) { diff --git a/drivers/net/irda/stir4200.c b/drivers/net/irda/stir4200.c index 528767dec9d7..e5698fa30a4f 100644 --- a/drivers/net/irda/stir4200.c +++ b/drivers/net/irda/stir4200.c @@ -612,16 +612,16 @@ static int fifo_txwait(struct stir_cb *stir, int space) pr_debug("fifo status 0x%lx count %lu\n", status, count); /* is fifo receiving already, or empty */ - if (!(status & FIFOCTL_DIR) - || (status & FIFOCTL_EMPTY)) + if (!(status & FIFOCTL_DIR) || + (status & FIFOCTL_EMPTY)) return 0; if (signal_pending(current)) return -EINTR; /* shutting down? */ - if (!netif_running(stir->netdev) - || !netif_device_present(stir->netdev)) + if (!netif_running(stir->netdev) || + !netif_device_present(stir->netdev)) return -ESHUTDOWN; /* only waiting for some space */ @@ -776,8 +776,8 @@ static int stir_transmit_thread(void *arg) } /* nothing to send? start receiving */ - if (!stir->receiving - && irda_device_txqueue_empty(dev)) { + if (!stir->receiving && + irda_device_txqueue_empty(dev)) { /* Wait otherwise chip gets confused. */ if (fifo_txwait(stir, -1)) break; diff --git a/drivers/net/irda/via-ircc.c b/drivers/net/irda/via-ircc.c index a5ca71cec028..fddb4efd5453 100644 --- a/drivers/net/irda/via-ircc.c +++ b/drivers/net/irda/via-ircc.c @@ -1185,8 +1185,8 @@ F01_E */ * if frame size,data ptr,or skb ptr are wrong ,the get next * entry. */ - if ((skb == NULL) || (skb->data == NULL) - || (self->rx_buff.data == NULL) || (len < 6)) { + if ((skb == NULL) || (skb->data == NULL) || + (self->rx_buff.data == NULL) || (len < 6)) { self->netdev->stats.rx_dropped++; return TRUE; } @@ -1284,8 +1284,8 @@ static int RxTimerHandler(struct via_ircc_cb *self, int iobase) self->RetryCount++; if ((self->RetryCount >= 1) || - ((st_fifo->pending_bytes + 2048) > self->rx_buff.truesize) - || (st_fifo->len >= (MAX_RX_WINDOW))) { + ((st_fifo->pending_bytes + 2048) > self->rx_buff.truesize) || + (st_fifo->len >= (MAX_RX_WINDOW))) { while (st_fifo->len > 0) { //upload frame // Put this entry back in fifo if (st_fifo->head > MAX_RX_WINDOW) @@ -1300,8 +1300,8 @@ static int RxTimerHandler(struct via_ircc_cb *self, int iobase) * if frame size, data ptr, or skb ptr are wrong, * then get next entry. */ - if ((skb == NULL) || (skb->data == NULL) - || (self->rx_buff.data == NULL) || (len < 6)) { + if ((skb == NULL) || (skb->data == NULL) || + (self->rx_buff.data == NULL) || (len < 6)) { self->netdev->stats.rx_dropped++; continue; } @@ -1332,8 +1332,8 @@ static int RxTimerHandler(struct via_ircc_cb *self, int iobase) * if frame is receive complete at this routine ,then upload * frame. */ - if ((GetRXStatus(iobase) & 0x10) - && (RxCurCount(iobase, self) != self->RxLastCount)) { + if ((GetRXStatus(iobase) & 0x10) && + (RxCurCount(iobase, self) != self->RxLastCount)) { upload_rxdata(self, iobase); if (irda_device_txqueue_empty(self->netdev)) via_ircc_dma_receive(self); diff --git a/drivers/net/irda/vlsi_ir.c b/drivers/net/irda/vlsi_ir.c index 7cfb8b6593c6..bd3c6b5ee76a 100644 --- a/drivers/net/irda/vlsi_ir.c +++ b/drivers/net/irda/vlsi_ir.c @@ -431,8 +431,8 @@ static struct vlsi_ring *vlsi_alloc_ring(struct pci_dev *pdev, struct ring_descr memset(rd, 0, sizeof(*rd)); rd->hw = hwmap + i; rd->buf = kmalloc(len, GFP_KERNEL|GFP_DMA); - if (rd->buf == NULL - || !(busaddr = pci_map_single(pdev, rd->buf, len, dir))) { + if (rd->buf == NULL || + !(busaddr = pci_map_single(pdev, rd->buf, len, dir))) { if (rd->buf) { IRDA_ERROR("%s: failed to create PCI-MAP for %p", __func__, rd->buf); @@ -955,8 +955,8 @@ static netdev_tx_t vlsi_hard_start_xmit(struct sk_buff *skb, } for(;;) { do_gettimeofday(&now); - if (now.tv_sec > ready.tv_sec - || (now.tv_sec==ready.tv_sec && now.tv_usec>=ready.tv_usec)) + if (now.tv_sec > ready.tv_sec || + (now.tv_sec==ready.tv_sec && now.tv_usec>=ready.tv_usec)) break; udelay(100); /* must not sleep here - called under netif_tx_lock! */ @@ -1594,8 +1594,8 @@ static int vlsi_irda_init(struct net_device *ndev) * see include file for details why we need these 2 masks, in this order! */ - if (pci_set_dma_mask(pdev,DMA_MASK_USED_BY_HW) - || pci_set_dma_mask(pdev,DMA_MASK_MSTRPAGE)) { + if (pci_set_dma_mask(pdev,DMA_MASK_USED_BY_HW) || + pci_set_dma_mask(pdev,DMA_MASK_MSTRPAGE)) { IRDA_ERROR("%s: aborting due to PCI BM-DMA address limitations\n", __func__); return -1; } @@ -1641,8 +1641,8 @@ vlsi_irda_probe(struct pci_dev *pdev, const struct pci_device_id *id) IRDA_MESSAGE("%s: IrDA PCI controller %s detected\n", drivername, pci_name(pdev)); - if ( !pci_resource_start(pdev,0) - || !(pci_resource_flags(pdev,0) & IORESOURCE_IO) ) { + if ( !pci_resource_start(pdev,0) || + !(pci_resource_flags(pdev,0) & IORESOURCE_IO) ) { IRDA_ERROR("%s: bar 0 invalid", __func__); goto out_disable; } diff --git a/drivers/net/isa-skeleton.c b/drivers/net/isa-skeleton.c index 0e71e2a93160..04d0502726c0 100644 --- a/drivers/net/isa-skeleton.c +++ b/drivers/net/isa-skeleton.c @@ -214,9 +214,9 @@ static int __init netcard_probe1(struct net_device *dev, int ioaddr) * contains the manufacturer's unique code. That might be a good probe * method. Ideally you would add additional checks. */ - if (inb(ioaddr + 0) != SA_ADDR0 - || inb(ioaddr + 1) != SA_ADDR1 - || inb(ioaddr + 2) != SA_ADDR2) + if (inb(ioaddr + 0) != SA_ADDR0 || + inb(ioaddr + 1) != SA_ADDR1 || + inb(ioaddr + 2) != SA_ADDR2) goto out; if (net_debug && version_printed++ == 0) diff --git a/drivers/net/iseries_veth.c b/drivers/net/iseries_veth.c index aa7286bc4364..49997194bdd0 100644 --- a/drivers/net/iseries_veth.c +++ b/drivers/net/iseries_veth.c @@ -604,10 +604,10 @@ static int veth_process_caps(struct veth_lpar_connection *cnx) /* Convert timer to jiffies */ cnx->ack_timeout = remote_caps->ack_timeout * HZ / 1000000; - if ( (remote_caps->num_buffers == 0) - || (remote_caps->ack_threshold > VETH_MAX_ACKS_PER_MSG) - || (remote_caps->ack_threshold == 0) - || (cnx->ack_timeout == 0) ) { + if ( (remote_caps->num_buffers == 0) || + (remote_caps->ack_threshold > VETH_MAX_ACKS_PER_MSG) || + (remote_caps->ack_threshold == 0) || + (cnx->ack_timeout == 0) ) { veth_error("Received incompatible capabilities from LPAR %d.\n", cnx->remote_lp); return HvLpEvent_Rc_InvalidSubtypeData; @@ -714,8 +714,8 @@ static void veth_statemachine(struct work_struct *work) cnx->state |= VETH_STATE_OPEN; } - if ( (cnx->state & VETH_STATE_OPEN) - && !(cnx->state & VETH_STATE_SENTMON) ) { + if ( (cnx->state & VETH_STATE_OPEN) && + !(cnx->state & VETH_STATE_SENTMON) ) { rc = veth_signalevent(cnx, VETH_EVENT_MONITOR, HvLpEvent_AckInd_DoAck, HvLpEvent_AckType_DeferredAck, @@ -724,8 +724,8 @@ static void veth_statemachine(struct work_struct *work) if (rc == HvLpEvent_Rc_Good) { cnx->state |= VETH_STATE_SENTMON; } else { - if ( (rc != HvLpEvent_Rc_PartitionDead) - && (rc != HvLpEvent_Rc_PathClosed) ) + if ( (rc != HvLpEvent_Rc_PartitionDead) && + (rc != HvLpEvent_Rc_PathClosed) ) veth_error("Error sending monitor to LPAR %d, " "rc = %d\n", rlp, rc); @@ -735,8 +735,8 @@ static void veth_statemachine(struct work_struct *work) } } - if ( (cnx->state & VETH_STATE_OPEN) - && !(cnx->state & VETH_STATE_SENTCAPS)) { + if ( (cnx->state & VETH_STATE_OPEN) && + !(cnx->state & VETH_STATE_SENTCAPS)) { u64 *rawcap = (u64 *)&cnx->local_caps; rc = veth_signalevent(cnx, VETH_EVENT_CAP, @@ -748,8 +748,8 @@ static void veth_statemachine(struct work_struct *work) if (rc == HvLpEvent_Rc_Good) { cnx->state |= VETH_STATE_SENTCAPS; } else { - if ( (rc != HvLpEvent_Rc_PartitionDead) - && (rc != HvLpEvent_Rc_PathClosed) ) + if ( (rc != HvLpEvent_Rc_PartitionDead) && + (rc != HvLpEvent_Rc_PathClosed) ) veth_error("Error sending caps to LPAR %d, " "rc = %d\n", rlp, rc); @@ -759,8 +759,8 @@ static void veth_statemachine(struct work_struct *work) } } - if ((cnx->state & VETH_STATE_GOTCAPS) - && !(cnx->state & VETH_STATE_SENTCAPACK)) { + if ((cnx->state & VETH_STATE_GOTCAPS) && + !(cnx->state & VETH_STATE_SENTCAPACK)) { struct veth_cap_data *remote_caps = &cnx->remote_caps; memcpy(remote_caps, &cnx->cap_event.u.caps_data, @@ -783,9 +783,9 @@ static void veth_statemachine(struct work_struct *work) goto cant_cope; } - if ((cnx->state & VETH_STATE_GOTCAPACK) - && (cnx->state & VETH_STATE_GOTCAPS) - && !(cnx->state & VETH_STATE_READY)) { + if ((cnx->state & VETH_STATE_GOTCAPACK) && + (cnx->state & VETH_STATE_GOTCAPS) && + !(cnx->state & VETH_STATE_READY)) { if (cnx->cap_ack_event.base_event.xRc == HvLpEvent_Rc_Good) { /* Start the ACK timer */ cnx->ack_timer.expires = jiffies + cnx->ack_timeout; @@ -818,8 +818,8 @@ static int veth_init_connection(u8 rlp) struct veth_msg *msgs; int i; - if ( (rlp == this_lp) - || ! HvLpConfig_doLpsCommunicateOnVirtualLan(this_lp, rlp) ) + if ( (rlp == this_lp) || + ! HvLpConfig_doLpsCommunicateOnVirtualLan(this_lp, rlp) ) return 0; cnx = kzalloc(sizeof(*cnx), GFP_KERNEL); @@ -1538,8 +1538,8 @@ static void veth_receive(struct veth_lpar_connection *cnx, cnx->pending_acks[cnx->num_pending_acks++] = event->base_event.xCorrelationToken; - if ( (cnx->num_pending_acks >= cnx->remote_caps.ack_threshold) - || (cnx->num_pending_acks >= VETH_MAX_ACKS_PER_MSG) ) + if ( (cnx->num_pending_acks >= cnx->remote_caps.ack_threshold) || + (cnx->num_pending_acks >= VETH_MAX_ACKS_PER_MSG) ) veth_flush_acks(cnx); spin_unlock_irqrestore(&cnx->lock, flags); diff --git a/drivers/net/ixgb/ixgb.h b/drivers/net/ixgb/ixgb.h index e95d9b6f1f2d..5257ae08b9f9 100644 --- a/drivers/net/ixgb/ixgb.h +++ b/drivers/net/ixgb/ixgb.h @@ -117,6 +117,7 @@ struct ixgb_buffer { unsigned long time_stamp; u16 length; u16 next_to_watch; + u16 mapped_as_page; }; struct ixgb_desc_ring { diff --git a/drivers/net/ixgb/ixgb_main.c b/drivers/net/ixgb/ixgb_main.c index 73646062e8dd..bcd0f01d5feb 100644 --- a/drivers/net/ixgb/ixgb_main.c +++ b/drivers/net/ixgb/ixgb_main.c @@ -892,10 +892,18 @@ static void ixgb_unmap_and_free_tx_resource(struct ixgb_adapter *adapter, struct ixgb_buffer *buffer_info) { - buffer_info->dma = 0; + if (buffer_info->dma) { + if (buffer_info->mapped_as_page) + pci_unmap_page(adapter->pdev, buffer_info->dma, + buffer_info->length, PCI_DMA_TODEVICE); + else + pci_unmap_single(adapter->pdev, buffer_info->dma, + buffer_info->length, + PCI_DMA_TODEVICE); + buffer_info->dma = 0; + } + if (buffer_info->skb) { - skb_dma_unmap(&adapter->pdev->dev, buffer_info->skb, - DMA_TO_DEVICE); dev_kfree_skb_any(buffer_info->skb); buffer_info->skb = NULL; } @@ -1272,24 +1280,16 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb, unsigned int first) { struct ixgb_desc_ring *tx_ring = &adapter->tx_ring; + struct pci_dev *pdev = adapter->pdev; struct ixgb_buffer *buffer_info; int len = skb_headlen(skb); unsigned int offset = 0, size, count = 0, i; unsigned int mss = skb_shinfo(skb)->gso_size; - unsigned int nr_frags = skb_shinfo(skb)->nr_frags; unsigned int f; - dma_addr_t *map; i = tx_ring->next_to_use; - if (skb_dma_map(&adapter->pdev->dev, skb, DMA_TO_DEVICE)) { - dev_err(&adapter->pdev->dev, "TX DMA map failed\n"); - return 0; - } - - map = skb_shinfo(skb)->dma_maps; - while (len) { buffer_info = &tx_ring->buffer_info[i]; size = min(len, IXGB_MAX_DATA_PER_TXD); @@ -1301,11 +1301,11 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb, buffer_info->length = size; WARN_ON(buffer_info->dma != 0); buffer_info->time_stamp = jiffies; - buffer_info->dma = skb_shinfo(skb)->dma_head + offset; - pci_map_single(adapter->pdev, - skb->data + offset, - size, - PCI_DMA_TODEVICE); + buffer_info->mapped_as_page = false; + buffer_info->dma = pci_map_single(pdev, skb->data + offset, + size, PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(pdev, buffer_info->dma)) + goto dma_error; buffer_info->next_to_watch = 0; len -= size; @@ -1323,7 +1323,7 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb, frag = &skb_shinfo(skb)->frags[f]; len = frag->size; - offset = 0; + offset = frag->page_offset; while (len) { i++; @@ -1341,7 +1341,13 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb, buffer_info->length = size; buffer_info->time_stamp = jiffies; - buffer_info->dma = map[f] + offset; + buffer_info->mapped_as_page = true; + buffer_info->dma = + pci_map_page(pdev, frag->page, + offset, size, + PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(pdev, buffer_info->dma)) + goto dma_error; buffer_info->next_to_watch = 0; len -= size; @@ -1353,6 +1359,22 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb, tx_ring->buffer_info[first].next_to_watch = i; return count; + +dma_error: + dev_err(&pdev->dev, "TX DMA map failed\n"); + buffer_info->dma = 0; + count--; + + while (count >= 0) { + count--; + i--; + if (i < 0) + i += tx_ring->count; + buffer_info = &tx_ring->buffer_info[i]; + ixgb_unmap_and_free_tx_resource(adapter, buffer_info); + } + + return 0; } static void diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h index 76b052fa3643..8da8eb535084 100644 --- a/drivers/net/ixgbe/ixgbe.h +++ b/drivers/net/ixgbe/ixgbe.h @@ -51,11 +51,11 @@ __func__ , ## args))) /* TX/RX descriptor defines */ -#define IXGBE_DEFAULT_TXD 1024 +#define IXGBE_DEFAULT_TXD 512 #define IXGBE_MAX_TXD 4096 #define IXGBE_MIN_TXD 64 -#define IXGBE_DEFAULT_RXD 1024 +#define IXGBE_DEFAULT_RXD 512 #define IXGBE_MAX_RXD 4096 #define IXGBE_MIN_RXD 64 @@ -106,6 +106,7 @@ struct ixgbe_tx_buffer { unsigned long time_stamp; u16 length; u16 next_to_watch; + u16 mapped_as_page; }; struct ixgbe_rx_buffer { @@ -160,10 +161,12 @@ struct ixgbe_ring { unsigned long reinit_state; u64 rsc_count; /* stat for coalesced packets */ u64 rsc_flush; /* stats for flushed packets */ + u32 restart_queue; /* track tx queue restarts */ + u32 non_eop_descs; /* track hardware descriptor chaining */ unsigned int size; /* length in bytes */ dma_addr_t dma; /* phys. address of descriptor ring */ -}; +} ____cacheline_internodealigned_in_smp; enum ixgbe_ring_f_enum { RING_F_NONE = 0, @@ -188,7 +191,7 @@ enum ixgbe_ring_f_enum { struct ixgbe_ring_feature { int indices; int mask; -}; +} ____cacheline_internodealigned_in_smp; #define MAX_RX_QUEUES 128 #define MAX_TX_QUEUES 128 @@ -274,29 +277,25 @@ struct ixgbe_adapter { u16 eitr_high; /* TX */ - struct ixgbe_ring *tx_ring; /* One per active queue */ + struct ixgbe_ring *tx_ring ____cacheline_aligned_in_smp; /* One per active queue */ int num_tx_queues; - u64 restart_queue; - u64 hw_csum_tx_good; - u64 lsc_int; - u64 hw_tso_ctxt; - u64 hw_tso6_ctxt; u32 tx_timeout_count; bool detect_tx_hung; + u64 restart_queue; + u64 lsc_int; + /* RX */ - struct ixgbe_ring *rx_ring; /* One per active queue */ + struct ixgbe_ring *rx_ring ____cacheline_aligned_in_smp; /* One per active queue */ int num_rx_queues; u64 hw_csum_rx_error; u64 hw_rx_no_dma_resources; - u64 hw_csum_rx_good; u64 non_eop_descs; int num_msix_vectors; int max_msix_q_vectors; /* true count of q_vectors for device */ struct ixgbe_ring_feature ring_feature[RING_F_ARRAY_SIZE]; struct msix_entry *msix_entries; - u64 rx_hdr_split; u32 alloc_rx_page_failed; u32 alloc_rx_buff_failed; diff --git a/drivers/net/ixgbe/ixgbe_common.c b/drivers/net/ixgbe/ixgbe_common.c index 40ff120a9ad4..688b8ca5da32 100644 --- a/drivers/net/ixgbe/ixgbe_common.c +++ b/drivers/net/ixgbe/ixgbe_common.c @@ -1382,10 +1382,10 @@ s32 ixgbe_update_uc_addr_list_generic(struct ixgbe_hw *hw, hw->addr_ctrl.overflow_promisc = 0; /* Zero out the other receive addresses */ - hw_dbg(hw, "Clearing RAR[1-%d]\n", uc_addr_in_use); - for (i = 1; i <= uc_addr_in_use; i++) { - IXGBE_WRITE_REG(hw, IXGBE_RAL(i), 0); - IXGBE_WRITE_REG(hw, IXGBE_RAH(i), 0); + hw_dbg(hw, "Clearing RAR[1-%d]\n", uc_addr_in_use + 1); + for (i = 0; i < uc_addr_in_use; i++) { + IXGBE_WRITE_REG(hw, IXGBE_RAL(1+i), 0); + IXGBE_WRITE_REG(hw, IXGBE_RAH(1+i), 0); } /* Add the new addresses */ @@ -1755,17 +1755,24 @@ s32 ixgbe_fc_autoneg(struct ixgbe_hw *hw) /* * On backplane, bail out if * - backplane autoneg was not completed, or if - * - link partner is not AN enabled + * - we are 82599 and link partner is not AN enabled */ if (hw->phy.media_type == ixgbe_media_type_backplane) { links = IXGBE_READ_REG(hw, IXGBE_LINKS); - links2 = IXGBE_READ_REG(hw, IXGBE_LINKS2); - if (((links & IXGBE_LINKS_KX_AN_COMP) == 0) || - ((links2 & IXGBE_LINKS2_AN_SUPPORTED) == 0)) { + if ((links & IXGBE_LINKS_KX_AN_COMP) == 0) { hw->fc.fc_was_autonegged = false; hw->fc.current_mode = hw->fc.requested_mode; goto out; } + + if (hw->mac.type == ixgbe_mac_82599EB) { + links2 = IXGBE_READ_REG(hw, IXGBE_LINKS2); + if ((links2 & IXGBE_LINKS2_AN_SUPPORTED) == 0) { + hw->fc.fc_was_autonegged = false; + hw->fc.current_mode = hw->fc.requested_mode; + goto out; + } + } } /* @@ -1784,6 +1791,20 @@ s32 ixgbe_fc_autoneg(struct ixgbe_hw *hw) } /* + * Bail out on + * - copper or CX4 adapters + * - fiber adapters running at 10gig + */ + if ((hw->phy.media_type == ixgbe_media_type_copper) || + (hw->phy.media_type == ixgbe_media_type_cx4) || + ((hw->phy.media_type == ixgbe_media_type_fiber) && + (speed == IXGBE_LINK_SPEED_10GB_FULL))) { + hw->fc.fc_was_autonegged = false; + hw->fc.current_mode = hw->fc.requested_mode; + goto out; + } + + /* * Read the AN advertisement and LP ability registers and resolve * local flow control settings accordingly */ diff --git a/drivers/net/ixgbe/ixgbe_ethtool.c b/drivers/net/ixgbe/ixgbe_ethtool.c index 84ab4db7074f..06a9d18bbdbc 100644 --- a/drivers/net/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ixgbe/ixgbe_ethtool.c @@ -93,16 +93,11 @@ static struct ixgbe_stats ixgbe_gstrings_stats[] = { {"tx_restart_queue", IXGBE_STAT(restart_queue)}, {"rx_long_length_errors", IXGBE_STAT(stats.roc)}, {"rx_short_length_errors", IXGBE_STAT(stats.ruc)}, - {"tx_tcp4_seg_ctxt", IXGBE_STAT(hw_tso_ctxt)}, - {"tx_tcp6_seg_ctxt", IXGBE_STAT(hw_tso6_ctxt)}, {"tx_flow_control_xon", IXGBE_STAT(stats.lxontxc)}, {"rx_flow_control_xon", IXGBE_STAT(stats.lxonrxc)}, {"tx_flow_control_xoff", IXGBE_STAT(stats.lxofftxc)}, {"rx_flow_control_xoff", IXGBE_STAT(stats.lxoffrxc)}, - {"rx_csum_offload_good", IXGBE_STAT(hw_csum_rx_good)}, {"rx_csum_offload_errors", IXGBE_STAT(hw_csum_rx_error)}, - {"tx_csum_offload_ctxt", IXGBE_STAT(hw_csum_tx_good)}, - {"rx_header_split", IXGBE_STAT(rx_hdr_split)}, {"alloc_rx_page_failed", IXGBE_STAT(alloc_rx_page_failed)}, {"alloc_rx_buff_failed", IXGBE_STAT(alloc_rx_buff_failed)}, {"rx_no_dma_resources", IXGBE_STAT(hw_rx_no_dma_resources)}, @@ -205,6 +200,56 @@ static int ixgbe_get_settings(struct net_device *netdev, ecmd->autoneg = AUTONEG_DISABLE; } + /* Get PHY type */ + switch (adapter->hw.phy.type) { + case ixgbe_phy_tn: + case ixgbe_phy_cu_unknown: + /* Copper 10G-BASET */ + ecmd->port = PORT_TP; + break; + case ixgbe_phy_qt: + ecmd->port = PORT_FIBRE; + break; + case ixgbe_phy_nl: + case ixgbe_phy_tw_tyco: + case ixgbe_phy_tw_unknown: + case ixgbe_phy_sfp_ftl: + case ixgbe_phy_sfp_avago: + case ixgbe_phy_sfp_intel: + case ixgbe_phy_sfp_unknown: + switch (adapter->hw.phy.sfp_type) { + /* SFP+ devices, further checking needed */ + case ixgbe_sfp_type_da_cu: + case ixgbe_sfp_type_da_cu_core0: + case ixgbe_sfp_type_da_cu_core1: + ecmd->port = PORT_DA; + break; + case ixgbe_sfp_type_sr: + case ixgbe_sfp_type_lr: + case ixgbe_sfp_type_srlr_core0: + case ixgbe_sfp_type_srlr_core1: + ecmd->port = PORT_FIBRE; + break; + case ixgbe_sfp_type_not_present: + ecmd->port = PORT_NONE; + break; + case ixgbe_sfp_type_unknown: + default: + ecmd->port = PORT_OTHER; + break; + } + break; + case ixgbe_phy_xaui: + ecmd->port = PORT_NONE; + break; + case ixgbe_phy_unknown: + case ixgbe_phy_generic: + case ixgbe_phy_sfp_unsupported: + default: + ecmd->port = PORT_OTHER; + break; + } + hw->mac.ops.check_link(hw, &link_speed, &link_up, false); if (link_up) { ecmd->speed = (link_speed == IXGBE_LINK_SPEED_10GB_FULL) ? @@ -1972,6 +2017,10 @@ static int ixgbe_get_coalesce(struct net_device *netdev, break; } + /* if in mixed tx/rx queues per vector mode, report only rx settings */ + if (adapter->q_vector[0]->txr_count && adapter->q_vector[0]->rxr_count) + return 0; + /* only valid if in constant ITR mode */ switch (adapter->tx_itr_setting) { case 0: @@ -1997,12 +2046,9 @@ static int ixgbe_set_coalesce(struct net_device *netdev, struct ixgbe_q_vector *q_vector; int i; - /* - * don't accept tx specific changes if we've got mixed RxTx vectors - * test and jump out here if needed before changing the rx numbers - */ - if ((1000000/ec->tx_coalesce_usecs) != adapter->tx_eitr_param && - adapter->q_vector[0]->txr_count && adapter->q_vector[0]->rxr_count) + /* don't accept tx specific changes if we've got mixed RxTx vectors */ + if (adapter->q_vector[0]->txr_count && adapter->q_vector[0]->rxr_count + && ec->tx_coalesce_usecs) return -EINVAL; if (ec->tx_max_coalesced_frames_irq) diff --git a/drivers/net/ixgbe/ixgbe_fcoe.c b/drivers/net/ixgbe/ixgbe_fcoe.c index edecdc853c14..da32a108a7b4 100644 --- a/drivers/net/ixgbe/ixgbe_fcoe.c +++ b/drivers/net/ixgbe/ixgbe_fcoe.c @@ -499,6 +499,10 @@ void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; struct ixgbe_fcoe *fcoe = &adapter->fcoe; struct ixgbe_ring_feature *f = &adapter->ring_feature[RING_F_FCOE]; +#ifdef CONFIG_IXGBE_DCB + u8 tc; + u32 up2tc; +#endif /* create the pool for ddp if not created yet */ if (!fcoe->pool) { @@ -540,6 +544,17 @@ void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter) IXGBE_FCRXCTRL_FCOELLI | IXGBE_FCRXCTRL_FCCRCBO | (FC_FCOE_VER << IXGBE_FCRXCTRL_FCOEVER_SHIFT)); +#ifdef CONFIG_IXGBE_DCB + up2tc = IXGBE_READ_REG(&adapter->hw, IXGBE_RTTUP2TC); + for (i = 0; i < MAX_USER_PRIORITY; i++) { + tc = (u8)(up2tc >> (i * IXGBE_RTTUP2TC_UP_SHIFT)); + tc &= (MAX_TRAFFIC_CLASS - 1); + if (fcoe->tc == tc) { + fcoe->up = i; + break; + } + } +#endif } /** @@ -671,19 +686,7 @@ out_disable: */ u8 ixgbe_fcoe_getapp(struct ixgbe_adapter *adapter) { - int i; - u8 tc; - u32 up2tc; - - up2tc = IXGBE_READ_REG(&adapter->hw, IXGBE_RTTUP2TC); - for (i = 0; i < MAX_USER_PRIORITY; i++) { - tc = (u8)(up2tc >> (i * IXGBE_RTTUP2TC_UP_SHIFT)); - tc &= (MAX_TRAFFIC_CLASS - 1); - if (adapter->fcoe.tc == tc) - return 1 << i; - } - - return 0; + return 1 << adapter->fcoe.up; } /** @@ -710,6 +713,7 @@ u8 ixgbe_fcoe_setapp(struct ixgbe_adapter *adapter, u8 up) up2tc >>= (i * IXGBE_RTTUP2TC_UP_SHIFT); up2tc &= (MAX_TRAFFIC_CLASS - 1); adapter->fcoe.tc = (u8)up2tc; + adapter->fcoe.up = i; return 0; } } diff --git a/drivers/net/ixgbe/ixgbe_fcoe.h b/drivers/net/ixgbe/ixgbe_fcoe.h index b5dee7b3ef1c..de8ff53187da 100644 --- a/drivers/net/ixgbe/ixgbe_fcoe.h +++ b/drivers/net/ixgbe/ixgbe_fcoe.h @@ -62,7 +62,10 @@ struct ixgbe_fcoe_ddp { }; struct ixgbe_fcoe { +#ifdef CONFIG_IXGBE_DCB u8 tc; + u8 up; +#endif spinlock_t lock; struct pci_pool *pool; struct ixgbe_fcoe_ddp ddp[IXGBE_FCOE_DDP_MAX]; diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index 5182b2893431..247ed2a24769 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -218,10 +218,20 @@ static void ixgbe_unmap_and_free_tx_resource(struct ixgbe_adapter *adapter, struct ixgbe_tx_buffer *tx_buffer_info) { - tx_buffer_info->dma = 0; + if (tx_buffer_info->dma) { + if (tx_buffer_info->mapped_as_page) + pci_unmap_page(adapter->pdev, + tx_buffer_info->dma, + tx_buffer_info->length, + PCI_DMA_TODEVICE); + else + pci_unmap_single(adapter->pdev, + tx_buffer_info->dma, + tx_buffer_info->length, + PCI_DMA_TODEVICE); + tx_buffer_info->dma = 0; + } if (tx_buffer_info->skb) { - skb_dma_unmap(&adapter->pdev->dev, tx_buffer_info->skb, - DMA_TO_DEVICE); dev_kfree_skb_any(tx_buffer_info->skb); tx_buffer_info->skb = NULL; } @@ -242,11 +252,11 @@ static void ixgbe_unmap_and_free_tx_resource(struct ixgbe_adapter *adapter, static inline bool ixgbe_tx_is_paused(struct ixgbe_adapter *adapter, struct ixgbe_ring *tx_ring) { - int tc; u32 txoff = IXGBE_TFCS_TXOFF; #ifdef CONFIG_IXGBE_DCB if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) { + int tc; int reg_idx = tx_ring->reg_idx; int dcb_i = adapter->ring_feature[RING_F_DCB].indices; @@ -403,7 +413,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, if (__netif_subqueue_stopped(netdev, tx_ring->queue_index) && !test_bit(__IXGBE_DOWN, &adapter->state)) { netif_wake_subqueue(netdev, tx_ring->queue_index); - ++adapter->restart_queue; + ++tx_ring->restart_queue; } } @@ -614,7 +624,6 @@ static inline void ixgbe_rx_checksum(struct ixgbe_adapter *adapter, /* It must be a TCP or UDP packet with a valid checksum */ skb->ip_summed = CHECKSUM_UNNECESSARY; - adapter->hw_csum_rx_good++; } static inline void ixgbe_release_rx_desc(struct ixgbe_hw *hw, @@ -671,14 +680,19 @@ static void ixgbe_alloc_rx_buffers(struct ixgbe_adapter *adapter, if (!bi->skb) { struct sk_buff *skb; - skb = netdev_alloc_skb_ip_align(adapter->netdev, - rx_ring->rx_buf_len); + /* netdev_alloc_skb reserves 32 bytes up front!! */ + uint bufsz = rx_ring->rx_buf_len + SMP_CACHE_BYTES; + skb = netdev_alloc_skb(adapter->netdev, bufsz); if (!skb) { adapter->alloc_rx_buff_failed++; goto no_buffers; } + /* advance the data pointer to the next cache line */ + skb_reserve(skb, (PTR_ALIGN(skb->data, SMP_CACHE_BYTES) + - skb->data)); + bi->skb = skb; bi->dma = pci_map_single(pdev, skb->data, rx_ring->rx_buf_len, @@ -791,8 +805,6 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, hdr_info = le16_to_cpu(ixgbe_get_hdr_info(rx_desc)); len = (hdr_info & IXGBE_RXDADV_HDRBUFLEN_MASK) >> IXGBE_RXDADV_HDRBUFLEN_SHIFT; - if (hdr_info & IXGBE_RXDADV_SPH) - adapter->rx_hdr_split++; if (len > IXGBE_RX_HDR_SIZE) len = IXGBE_RX_HDR_SIZE; upper_len = le16_to_cpu(rx_desc->wb.upper.length); @@ -802,7 +814,7 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, cleaned = true; skb = rx_buffer_info->skb; - prefetch(skb->data - NET_IP_ALIGN); + prefetch(skb->data); rx_buffer_info->skb = NULL; if (rx_buffer_info->dma) { @@ -874,7 +886,7 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, skb->next = next_buffer->skb; skb->next->prev = skb; } - adapter->non_eop_descs++; + rx_ring->non_eop_descs++; goto next_desc; } @@ -1317,8 +1329,7 @@ static irqreturn_t ixgbe_msix_clean_tx(int irq, void *data) r_idx + 1); } - /* disable interrupts on this vector only */ - ixgbe_irq_disable_queues(adapter, ((u64)1 << q_vector->v_idx)); + /* EIAM disabled interrupts (on this vector) for us */ napi_schedule(&q_vector->napi); return IRQ_HANDLED; @@ -1350,7 +1361,7 @@ static irqreturn_t ixgbe_msix_clean_rx(int irq, void *data) return IRQ_HANDLED; /* disable interrupts on this vector only */ - ixgbe_irq_disable_queues(adapter, ((u64)1 << q_vector->v_idx)); + /* EIAM disabled interrupts (on this vector) for us */ napi_schedule(&q_vector->napi); return IRQ_HANDLED; @@ -1385,8 +1396,7 @@ static irqreturn_t ixgbe_msix_clean_many(int irq, void *data) r_idx + 1); } - /* disable interrupts on this vector only */ - ixgbe_irq_disable_queues(adapter, ((u64)1 << q_vector->v_idx)); + /* EIAM disabled interrupts (on this vector) for us */ napi_schedule(&q_vector->napi); return IRQ_HANDLED; @@ -2704,7 +2714,22 @@ static int ixgbe_up_complete(struct ixgbe_adapter *adapter) IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie); } - if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) { + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { + /* + * use EIAM to auto-mask when MSI-X interrupt is asserted + * this saves a register write for every interrupt + */ + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + IXGBE_WRITE_REG(hw, IXGBE_EIAM, IXGBE_EICS_RTX_QUEUE); + break; + default: + case ixgbe_mac_82599EB: + IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(0), 0xFFFFFFFF); + IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(1), 0xFFFFFFFF); + break; + } + } else { /* legacy interrupts, use EIAM to auto-mask when reading EICR, * specifically only auto mask tx and rx interrupts */ IXGBE_WRITE_REG(hw, IXGBE_EIAM, IXGBE_EICS_RTX_QUEUE); @@ -3948,8 +3973,10 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter) adapter->flags |= IXGBE_FLAG_FCOE_CAPABLE; adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED; adapter->ring_feature[RING_F_FCOE].indices = 0; +#ifdef CONFIG_IXGBE_DCB /* Default traffic class to use for FCoE */ adapter->fcoe.tc = IXGBE_FCOE_DEFTC; +#endif #endif /* IXGBE_FCOE */ } @@ -4499,6 +4526,13 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) adapter->rsc_total_flush = rsc_flush; } + /* gather some stats to the adapter struct that are per queue */ + for (i = 0; i < adapter->num_tx_queues; i++) + adapter->restart_queue += adapter->tx_ring[i].restart_queue; + + for (i = 0; i < adapter->num_rx_queues; i++) + adapter->non_eop_descs += adapter->tx_ring[i].non_eop_descs; + adapter->stats.crcerrs += IXGBE_READ_REG(hw, IXGBE_CRCERRS); for (i = 0; i < 8; i++) { /* for packet buffers not used, the register should read 0 */ @@ -4881,14 +4915,12 @@ static int ixgbe_tso(struct ixgbe_adapter *adapter, iph->daddr, 0, IPPROTO_TCP, 0); - adapter->hw_tso_ctxt++; } else if (skb_shinfo(skb)->gso_type == SKB_GSO_TCPV6) { ipv6_hdr(skb)->payload_len = 0; tcp_hdr(skb)->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0); - adapter->hw_tso6_ctxt++; } i = tx_ring->next_to_use; @@ -5007,7 +5039,6 @@ static bool ixgbe_tx_csum(struct ixgbe_adapter *adapter, tx_buffer_info->time_stamp = jiffies; tx_buffer_info->next_to_watch = i; - adapter->hw_csum_tx_good++; i++; if (i == tx_ring->count) i = 0; @@ -5024,23 +5055,16 @@ static int ixgbe_tx_map(struct ixgbe_adapter *adapter, struct sk_buff *skb, u32 tx_flags, unsigned int first) { + struct pci_dev *pdev = adapter->pdev; struct ixgbe_tx_buffer *tx_buffer_info; unsigned int len; unsigned int total = skb->len; unsigned int offset = 0, size, count = 0, i; unsigned int nr_frags = skb_shinfo(skb)->nr_frags; unsigned int f; - dma_addr_t *map; i = tx_ring->next_to_use; - if (skb_dma_map(&adapter->pdev->dev, skb, DMA_TO_DEVICE)) { - dev_err(&adapter->pdev->dev, "TX DMA map failed\n"); - return 0; - } - - map = skb_shinfo(skb)->dma_maps; - if (tx_flags & IXGBE_TX_FLAGS_FCOE) /* excluding fcoe_crc_eof for FCoE */ total -= sizeof(struct fcoe_crc_eof); @@ -5051,7 +5075,12 @@ static int ixgbe_tx_map(struct ixgbe_adapter *adapter, size = min(len, (uint)IXGBE_MAX_DATA_PER_TXD); tx_buffer_info->length = size; - tx_buffer_info->dma = skb_shinfo(skb)->dma_head + offset; + tx_buffer_info->mapped_as_page = false; + tx_buffer_info->dma = pci_map_single(pdev, + skb->data + offset, + size, PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(pdev, tx_buffer_info->dma)) + goto dma_error; tx_buffer_info->time_stamp = jiffies; tx_buffer_info->next_to_watch = i; @@ -5072,7 +5101,7 @@ static int ixgbe_tx_map(struct ixgbe_adapter *adapter, frag = &skb_shinfo(skb)->frags[f]; len = min((unsigned int)frag->size, total); - offset = 0; + offset = frag->page_offset; while (len) { i++; @@ -5083,7 +5112,13 @@ static int ixgbe_tx_map(struct ixgbe_adapter *adapter, size = min(len, (uint)IXGBE_MAX_DATA_PER_TXD); tx_buffer_info->length = size; - tx_buffer_info->dma = map[f] + offset; + tx_buffer_info->dma = pci_map_page(adapter->pdev, + frag->page, + offset, size, + PCI_DMA_TODEVICE); + tx_buffer_info->mapped_as_page = true; + if (pci_dma_mapping_error(pdev, tx_buffer_info->dma)) + goto dma_error; tx_buffer_info->time_stamp = jiffies; tx_buffer_info->next_to_watch = i; @@ -5100,6 +5135,27 @@ static int ixgbe_tx_map(struct ixgbe_adapter *adapter, tx_ring->tx_buffer_info[first].next_to_watch = i; return count; + +dma_error: + dev_err(&pdev->dev, "TX DMA map failed\n"); + + /* clear timestamp and dma mappings for failed tx_buffer_info map */ + tx_buffer_info->dma = 0; + tx_buffer_info->time_stamp = 0; + tx_buffer_info->next_to_watch = 0; + count--; + + /* clear timestamp and dma mappings for remaining portion of packet */ + while (count >= 0) { + count--; + i--; + if (i < 0) + i += tx_ring->count; + tx_buffer_info = &tx_ring->tx_buffer_info[i]; + ixgbe_unmap_and_free_tx_resource(adapter, tx_buffer_info); + } + + return count; } static void ixgbe_tx_queue(struct ixgbe_adapter *adapter, @@ -5219,8 +5275,6 @@ static void ixgbe_atr(struct ixgbe_adapter *adapter, struct sk_buff *skb, static int __ixgbe_maybe_stop_tx(struct net_device *netdev, struct ixgbe_ring *tx_ring, int size) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); - netif_stop_subqueue(netdev, tx_ring->queue_index); /* Herbert's original patch had: * smp_mb__after_netif_stop_queue(); @@ -5234,7 +5288,7 @@ static int __ixgbe_maybe_stop_tx(struct net_device *netdev, /* A reprieve! - use start_queue because it doesn't call schedule */ netif_start_subqueue(netdev, tx_ring->queue_index); - ++adapter->restart_queue; + ++tx_ring->restart_queue; return 0; } @@ -5249,10 +5303,19 @@ static int ixgbe_maybe_stop_tx(struct net_device *netdev, static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb) { struct ixgbe_adapter *adapter = netdev_priv(dev); + int txq = smp_processor_id(); if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) - return smp_processor_id(); + return txq; +#ifdef IXGBE_FCOE + if ((adapter->flags & IXGBE_FLAG_FCOE_ENABLED) && + (skb->protocol == htons(ETH_P_FCOE))) { + txq &= (adapter->ring_feature[RING_F_FCOE].indices - 1); + txq += adapter->ring_feature[RING_F_FCOE].mask; + return txq; + } +#endif if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) return (skb->vlan_tci & IXGBE_TX_FLAGS_VLAN_PRIO_MASK) >> 13; @@ -5267,7 +5330,7 @@ static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb, unsigned int first; unsigned int tx_flags = 0; u8 hdr_len = 0; - int r_idx = 0, tso; + int tso; int count = 0; unsigned int f; @@ -5275,13 +5338,13 @@ static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb, tx_flags |= vlan_tx_tag_get(skb); if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) { tx_flags &= ~IXGBE_TX_FLAGS_VLAN_PRIO_MASK; - tx_flags |= (skb->queue_mapping << 13); + tx_flags |= ((skb->queue_mapping & 0x7) << 13); } tx_flags <<= IXGBE_TX_FLAGS_VLAN_SHIFT; tx_flags |= IXGBE_TX_FLAGS_VLAN; } else if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) { if (skb->priority != TC_PRIO_CONTROL) { - tx_flags |= (skb->queue_mapping << 13); + tx_flags |= ((skb->queue_mapping & 0x7) << 13); tx_flags <<= IXGBE_TX_FLAGS_VLAN_SHIFT; tx_flags |= IXGBE_TX_FLAGS_VLAN; } else { @@ -5290,17 +5353,18 @@ static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb, } } - r_idx = skb->queue_mapping; - tx_ring = &adapter->tx_ring[r_idx]; + tx_ring = &adapter->tx_ring[skb->queue_mapping]; if ((adapter->flags & IXGBE_FLAG_FCOE_ENABLED) && (skb->protocol == htons(ETH_P_FCOE))) { tx_flags |= IXGBE_TX_FLAGS_FCOE; #ifdef IXGBE_FCOE - r_idx = smp_processor_id(); - r_idx &= (adapter->ring_feature[RING_F_FCOE].indices - 1); - r_idx += adapter->ring_feature[RING_F_FCOE].mask; - tx_ring = &adapter->tx_ring[r_idx]; +#ifdef CONFIG_IXGBE_DCB + tx_flags &= ~(IXGBE_TX_FLAGS_VLAN_PRIO_MASK + << IXGBE_TX_FLAGS_VLAN_SHIFT); + tx_flags |= ((adapter->fcoe.up << 13) + << IXGBE_TX_FLAGS_VLAN_SHIFT); +#endif #endif } /* four things can cause us to need a context descriptor */ diff --git a/drivers/net/jazzsonic.c b/drivers/net/jazzsonic.c index 35d5bed450da..f47d4d663b19 100644 --- a/drivers/net/jazzsonic.c +++ b/drivers/net/jazzsonic.c @@ -130,8 +130,8 @@ static int __devinit sonic_probe1(struct net_device *dev) printk("SONIC Silicon Revision = 0x%04x\n",silicon_revision); i = 0; - while (known_revisions[i] != 0xffff - && known_revisions[i] != silicon_revision) + while (known_revisions[i] != 0xffff && + known_revisions[i] != silicon_revision) i++; if (known_revisions[i] == 0xffff) { diff --git a/drivers/net/jme.c b/drivers/net/jme.c index 6c1b92fa0b0c..792b88fc3574 100644 --- a/drivers/net/jme.c +++ b/drivers/net/jme.c @@ -1050,8 +1050,8 @@ jme_dynamic_pcc(struct jme_adapter *jme) if ((NET_STAT(jme).rx_bytes - dpi->last_bytes) > PCC_P3_THRESHOLD) jme_attempt_pcc(dpi, PCC_P3); - else if ((NET_STAT(jme).rx_packets - dpi->last_pkts) > PCC_P2_THRESHOLD - || dpi->intr_cnt > PCC_INTR_THRESHOLD) + else if ((NET_STAT(jme).rx_packets - dpi->last_pkts) > PCC_P2_THRESHOLD || + dpi->intr_cnt > PCC_INTR_THRESHOLD) jme_attempt_pcc(dpi, PCC_P2); else jme_attempt_pcc(dpi, PCC_P1); @@ -2199,8 +2199,8 @@ jme_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecmd) if (netif_running(netdev)) return -EBUSY; - if (ecmd->use_adaptive_rx_coalesce - && test_bit(JME_FLAG_POLL, &jme->flags)) { + if (ecmd->use_adaptive_rx_coalesce && + test_bit(JME_FLAG_POLL, &jme->flags)) { clear_bit(JME_FLAG_POLL, &jme->flags); jme->jme_rx = netif_rx; jme->jme_vlan_rx = vlan_hwaccel_rx; @@ -2209,8 +2209,8 @@ jme_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecmd) dpi->cnt = 0; jme_set_rx_pcc(jme, PCC_P1); jme_interrupt_mode(jme); - } else if (!(ecmd->use_adaptive_rx_coalesce) - && !(test_bit(JME_FLAG_POLL, &jme->flags))) { + } else if (!(ecmd->use_adaptive_rx_coalesce) && + !(test_bit(JME_FLAG_POLL, &jme->flags))) { set_bit(JME_FLAG_POLL, &jme->flags); jme->jme_rx = netif_receive_skb; jme->jme_vlan_rx = vlan_hwaccel_receive_skb; diff --git a/drivers/net/ks8851.c b/drivers/net/ks8851.c index a23f739d222f..6d3ac65bc35c 100644 --- a/drivers/net/ks8851.c +++ b/drivers/net/ks8851.c @@ -1,4 +1,4 @@ -/* drivers/net/ks8651.c +/* drivers/net/ks8851.c * * Copyright 2009 Simtec Electronics * http://www.simtec.co.uk/ @@ -714,7 +714,7 @@ static void ks8851_tx_work(struct work_struct *work) { struct ks8851_net *ks = container_of(work, struct ks8851_net, tx_work); struct sk_buff *txb; - bool last = false; + bool last = skb_queue_empty(&ks->txq); mutex_lock(&ks->lock); diff --git a/drivers/net/ks8851_mll.c b/drivers/net/ks8851_mll.c index 0be14d702beb..c146304d8d6c 100644 --- a/drivers/net/ks8851_mll.c +++ b/drivers/net/ks8851_mll.c @@ -568,6 +568,16 @@ static inline void ks_outblk(struct ks_net *ks, u16 *wptr, u32 len) iowrite16(*wptr++, ks->hw_addr); } +static void ks_disable_int(struct ks_net *ks) +{ + ks_wrreg16(ks, KS_IER, 0x0000); +} /* ks_disable_int */ + +static void ks_enable_int(struct ks_net *ks) +{ + ks_wrreg16(ks, KS_IER, ks->rc_ier); +} /* ks_enable_int */ + /** * ks_tx_fifo_space - return the available hardware buffer size. * @ks: The chip information @@ -681,6 +691,47 @@ static void ks_soft_reset(struct ks_net *ks, unsigned op) } +void ks_enable_qmu(struct ks_net *ks) +{ + u16 w; + + w = ks_rdreg16(ks, KS_TXCR); + /* Enables QMU Transmit (TXCR). */ + ks_wrreg16(ks, KS_TXCR, w | TXCR_TXE); + + /* + * RX Frame Count Threshold Enable and Auto-Dequeue RXQ Frame + * Enable + */ + + w = ks_rdreg16(ks, KS_RXQCR); + ks_wrreg16(ks, KS_RXQCR, w | RXQCR_RXFCTE); + + /* Enables QMU Receive (RXCR1). */ + w = ks_rdreg16(ks, KS_RXCR1); + ks_wrreg16(ks, KS_RXCR1, w | RXCR1_RXE); + ks->enabled = true; +} /* ks_enable_qmu */ + +static void ks_disable_qmu(struct ks_net *ks) +{ + u16 w; + + w = ks_rdreg16(ks, KS_TXCR); + + /* Disables QMU Transmit (TXCR). */ + w &= ~TXCR_TXE; + ks_wrreg16(ks, KS_TXCR, w); + + /* Disables QMU Receive (RXCR1). */ + w = ks_rdreg16(ks, KS_RXCR1); + w &= ~RXCR1_RXE ; + ks_wrreg16(ks, KS_RXCR1, w); + + ks->enabled = false; + +} /* ks_disable_qmu */ + /** * ks_read_qmu - read 1 pkt data from the QMU. * @ks: The chip information @@ -752,7 +803,7 @@ static void ks_rcv(struct ks_net *ks, struct net_device *netdev) (frame_hdr->len < RX_BUF_SIZE) && frame_hdr->len)) { skb_reserve(skb, 2); /* read data block including CRC 4 bytes */ - ks_read_qmu(ks, (u16 *)skb->data, frame_hdr->len + 4); + ks_read_qmu(ks, (u16 *)skb->data, frame_hdr->len); skb_put(skb, frame_hdr->len); skb->dev = netdev; skb->protocol = eth_type_trans(skb, netdev); @@ -861,7 +912,7 @@ static int ks_net_open(struct net_device *netdev) ks_dbg(ks, "%s - entry\n", __func__); /* reset the HW */ - err = request_irq(ks->irq, ks_irq, KS_INT_FLAGS, DRV_NAME, ks); + err = request_irq(ks->irq, ks_irq, KS_INT_FLAGS, DRV_NAME, netdev); if (err) { printk(KERN_ERR "Failed to request IRQ: %d: %d\n", @@ -869,6 +920,15 @@ static int ks_net_open(struct net_device *netdev) return err; } + /* wake up powermode to normal mode */ + ks_set_powermode(ks, PMECR_PM_NORMAL); + mdelay(1); /* wait for normal mode to take effect */ + + ks_wrreg16(ks, KS_ISR, 0xffff); + ks_enable_int(ks); + ks_enable_qmu(ks); + netif_start_queue(ks->netdev); + if (netif_msg_ifup(ks)) ks_dbg(ks, "network device %s up\n", netdev->name); @@ -892,19 +952,14 @@ static int ks_net_stop(struct net_device *netdev) netif_stop_queue(netdev); - kfree(ks->frame_head_info); - mutex_lock(&ks->lock); /* turn off the IRQs and ack any outstanding */ ks_wrreg16(ks, KS_IER, 0x0000); ks_wrreg16(ks, KS_ISR, 0xffff); - /* shutdown RX process */ - ks_wrreg16(ks, KS_RXCR1, 0x0000); - - /* shutdown TX process */ - ks_wrreg16(ks, KS_TXCR, 0x0000); + /* shutdown RX/TX QMU */ + ks_disable_qmu(ks); /* set powermode to soft power down to save power */ ks_set_powermode(ks, PMECR_PM_SOFTDOWN); @@ -929,17 +984,8 @@ static int ks_net_stop(struct net_device *netdev) */ static void ks_write_qmu(struct ks_net *ks, u8 *pdata, u16 len) { - unsigned fid = ks->fid; - - fid = ks->fid; - ks->fid = (ks->fid + 1) & TXFR_TXFID_MASK; - - /* reduce the tx interrupt occurrances. */ - if (!fid) - fid |= TXFR_TXIC; /* irq on completion */ - /* start header at txb[0] to align txw entries */ - ks->txh.txw[0] = cpu_to_le16(fid); + ks->txh.txw[0] = 0; ks->txh.txw[1] = cpu_to_le16(len); /* 1. set sudo-DMA mode */ @@ -957,16 +1003,6 @@ static void ks_write_qmu(struct ks_net *ks, u8 *pdata, u16 len) ; } -static void ks_disable_int(struct ks_net *ks) -{ - ks_wrreg16(ks, KS_IER, 0x0000); -} /* ks_disable_int */ - -static void ks_enable_int(struct ks_net *ks) -{ - ks_wrreg16(ks, KS_IER, ks->rc_ier); -} /* ks_enable_int */ - /** * ks_start_xmit - transmit packet * @skb : The buffer to transmit @@ -1410,25 +1446,6 @@ static int ks_read_selftest(struct ks_net *ks) return ret; } -static void ks_disable(struct ks_net *ks) -{ - u16 w; - - w = ks_rdreg16(ks, KS_TXCR); - - /* Disables QMU Transmit (TXCR). */ - w &= ~TXCR_TXE; - ks_wrreg16(ks, KS_TXCR, w); - - /* Disables QMU Receive (RXCR1). */ - w = ks_rdreg16(ks, KS_RXCR1); - w &= ~RXCR1_RXE ; - ks_wrreg16(ks, KS_RXCR1, w); - - ks->enabled = false; - -} /* ks_disable */ - static void ks_setup(struct ks_net *ks) { u16 w; @@ -1463,7 +1480,7 @@ static void ks_setup(struct ks_net *ks) w = TXCR_TXFCE | TXCR_TXPE | TXCR_TXCRC | TXCR_TCGIP; ks_wrreg16(ks, KS_TXCR, w); - w = RXCR1_RXFCE | RXCR1_RXBE | RXCR1_RXUE; + w = RXCR1_RXFCE | RXCR1_RXBE | RXCR1_RXUE | RXCR1_RXME | RXCR1_RXIPFCC; if (ks->promiscuous) /* bPromiscuous */ w |= (RXCR1_RXAE | RXCR1_RXINVF); @@ -1486,28 +1503,6 @@ static void ks_setup_int(struct ks_net *ks) ks->rc_ier = (IRQ_LCI | IRQ_TXI | IRQ_RXI); } /* ks_setup_int */ -void ks_enable(struct ks_net *ks) -{ - u16 w; - - w = ks_rdreg16(ks, KS_TXCR); - /* Enables QMU Transmit (TXCR). */ - ks_wrreg16(ks, KS_TXCR, w | TXCR_TXE); - - /* - * RX Frame Count Threshold Enable and Auto-Dequeue RXQ Frame - * Enable - */ - - w = ks_rdreg16(ks, KS_RXQCR); - ks_wrreg16(ks, KS_RXQCR, w | RXQCR_RXFCTE); - - /* Enables QMU Receive (RXCR1). */ - w = ks_rdreg16(ks, KS_RXCR1); - ks_wrreg16(ks, KS_RXCR1, w | RXCR1_RXE); - ks->enabled = true; -} /* ks_enable */ - static int ks_hw_init(struct ks_net *ks) { #define MHEADER_SIZE (sizeof(struct type_frame_head) * MAX_RECV_FRAMES) @@ -1612,11 +1607,9 @@ static int __devinit ks8851_probe(struct platform_device *pdev) ks_soft_reset(ks, GRR_GSR); ks_hw_init(ks); - ks_disable(ks); + ks_disable_qmu(ks); ks_setup(ks); ks_setup_int(ks); - ks_enable_int(ks); - ks_enable(ks); memcpy(netdev->dev_addr, ks->mac_addr, 6); data = ks_rdreg16(ks, KS_OBCR); @@ -1658,6 +1651,7 @@ static int __devexit ks8851_remove(struct platform_device *pdev) struct ks_net *ks = netdev_priv(netdev); struct resource *iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + kfree(ks->frame_head_info); unregister_netdev(netdev); iounmap(ks->hw_addr); free_netdev(netdev); diff --git a/drivers/net/lance.c b/drivers/net/lance.c index 7b2c42992c35..8d7d3d4625f6 100644 --- a/drivers/net/lance.c +++ b/drivers/net/lance.c @@ -493,14 +493,14 @@ static int __init lance_probe1(struct net_device *dev, int ioaddr, int irq, int static const short ioaddr_table[] = { 0x300, 0x320, 0x340, 0x360}; int hp_port = (readl(bios + 1) & 1) ? 0x499 : 0x99; /* We can have boards other than the built-in! Verify this is on-board. */ - if ((inb(hp_port) & 0xc0) == 0x80 - && ioaddr_table[inb(hp_port) & 3] == ioaddr) + if ((inb(hp_port) & 0xc0) == 0x80 && + ioaddr_table[inb(hp_port) & 3] == ioaddr) hp_builtin = hp_port; } iounmap(bios); /* We also recognize the HP Vectra on-board here, but check below. */ - hpJ2405A = (inb(ioaddr) == 0x08 && inb(ioaddr+1) == 0x00 - && inb(ioaddr+2) == 0x09); + hpJ2405A = (inb(ioaddr) == 0x08 && inb(ioaddr+1) == 0x00 && + inb(ioaddr+2) == 0x09); /* Reset the LANCE. */ reset_val = inw(ioaddr+LANCE_RESET); /* Reset the LANCE */ @@ -1035,8 +1035,8 @@ static irqreturn_t lance_interrupt(int irq, void *dev_id) spin_lock (&lp->devlock); outw(0x00, dev->base_addr + LANCE_ADDR); - while ((csr0 = inw(dev->base_addr + LANCE_DATA)) & 0x8600 - && --boguscnt >= 0) { + while ((csr0 = inw(dev->base_addr + LANCE_DATA)) & 0x8600 && + --boguscnt >= 0) { /* Acknowledge all of the current interrupt sources ASAP. */ outw(csr0 & ~0x004f, dev->base_addr + LANCE_DATA); diff --git a/drivers/net/lib8390.c b/drivers/net/lib8390.c index 256119882b1e..57f25848fe80 100644 --- a/drivers/net/lib8390.c +++ b/drivers/net/lib8390.c @@ -464,8 +464,8 @@ static irqreturn_t __ei_interrupt(int irq, void *dev_id) ei_inb_p(e8390_base + EN0_ISR)); /* !!Assumption!! -- we stay in page 0. Don't break this. */ - while ((interrupts = ei_inb_p(e8390_base + EN0_ISR)) != 0 - && ++nr_serviced < MAX_SERVICE) + while ((interrupts = ei_inb_p(e8390_base + EN0_ISR)) != 0 && + ++nr_serviced < MAX_SERVICE) { if (!netif_running(dev)) { printk(KERN_WARNING "%s: interrupt from stopped card\n", dev->name); @@ -721,10 +721,10 @@ static void ei_receive(struct net_device *dev) /* Check for bogosity warned by 3c503 book: the status byte is never written. This happened a lot during testing! This code should be cleaned up someday. */ - if (rx_frame.next != next_frame - && rx_frame.next != next_frame + 1 - && rx_frame.next != next_frame - num_rx_pages - && rx_frame.next != next_frame + 1 - num_rx_pages) { + if (rx_frame.next != next_frame && + rx_frame.next != next_frame + 1 && + rx_frame.next != next_frame - num_rx_pages && + rx_frame.next != next_frame + 1 - num_rx_pages) { ei_local->current_page = rxing_page; ei_outb(ei_local->current_page-1, e8390_base+EN0_BOUNDARY); dev->stats.rx_errors++; diff --git a/drivers/net/ll_temac_main.c b/drivers/net/ll_temac_main.c index f2a197fd47a5..336e7c7a9275 100644 --- a/drivers/net/ll_temac_main.c +++ b/drivers/net/ll_temac_main.c @@ -231,8 +231,8 @@ static void temac_set_multicast_list(struct net_device *ndev) int i; mutex_lock(&lp->indirect_mutex); - if (ndev->flags & (IFF_ALLMULTI | IFF_PROMISC) - || ndev->mc_count > MULTICAST_CAM_TABLE_NUM) { + if (ndev->flags & (IFF_ALLMULTI | IFF_PROMISC) || + ndev->mc_count > MULTICAST_CAM_TABLE_NUM) { /* * We must make the kernel realise we had to move * into promisc mode or we start all out war on diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 1bc654a73c47..eae4ad749e9d 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -207,20 +207,12 @@ static __net_init int loopback_net_init(struct net *net) out_free_netdev: free_netdev(dev); out: - if (net == &init_net) + if (net_eq(net, &init_net)) panic("loopback: Failed to register netdevice: %d\n", err); return err; } -static __net_exit void loopback_net_exit(struct net *net) -{ - struct net_device *dev = net->loopback_dev; - - unregister_netdev(dev); -} - /* Registered in net/core/dev.c */ struct pernet_operations __net_initdata loopback_net_ops = { .init = loopback_net_init, - .exit = loopback_net_exit, }; diff --git a/drivers/net/mac89x0.c b/drivers/net/mac89x0.c index c244ec34fc43..23b633e2ac42 100644 --- a/drivers/net/mac89x0.c +++ b/drivers/net/mac89x0.c @@ -222,8 +222,8 @@ struct net_device * __init mac89x0_probe(int unit) int card_present; local_irq_save(flags); - card_present = hwreg_present((void*) ioaddr+4) - && hwreg_present((void*) ioaddr + DATA_PORT); + card_present = (hwreg_present((void*) ioaddr+4) && + hwreg_present((void*) ioaddr + DATA_PORT)); local_irq_restore(flags); if (!card_present) diff --git a/drivers/net/mace.c b/drivers/net/mace.c index 7d7577b598ea..d9fbad386389 100644 --- a/drivers/net/mace.c +++ b/drivers/net/mace.c @@ -897,8 +897,8 @@ static irqreturn_t mace_rxdma_intr(int irq, void *dev_id) if (next >= N_RX_RING) next = 0; np = mp->rx_cmds + next; - if (next != mp->rx_fill - && (ld_le16(&np->xfer_status) & ACTIVE) != 0) { + if (next != mp->rx_fill && + (ld_le16(&np->xfer_status) & ACTIVE) != 0) { printk(KERN_DEBUG "mace: lost a status word\n"); ++mace_lost_status; } else diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index ae2b5c79c55e..21a9c9ab4b34 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -29,6 +29,7 @@ #include <linux/if_link.h> #include <linux/if_macvlan.h> #include <net/rtnetlink.h> +#include <net/xfrm.h> #define MACVLAN_HASH_SIZE (1 << BITS_PER_BYTE) @@ -59,6 +60,7 @@ struct macvlan_dev { struct macvlan_port *port; struct net_device *lowerdev; struct macvlan_rx_stats *rx_stats; + enum macvlan_mode mode; }; @@ -116,42 +118,67 @@ static int macvlan_addr_busy(const struct macvlan_port *port, return 0; } +static inline void macvlan_count_rx(const struct macvlan_dev *vlan, + unsigned int len, bool success, + bool multicast) +{ + struct macvlan_rx_stats *rx_stats; + + rx_stats = per_cpu_ptr(vlan->rx_stats, smp_processor_id()); + if (likely(success)) { + rx_stats->rx_packets++;; + rx_stats->rx_bytes += len; + if (multicast) + rx_stats->multicast++; + } else { + rx_stats->rx_errors++; + } +} + +static int macvlan_broadcast_one(struct sk_buff *skb, struct net_device *dev, + const struct ethhdr *eth, bool local) +{ + if (!skb) + return NET_RX_DROP; + + if (local) + return dev_forward_skb(dev, skb); + + skb->dev = dev; + if (!compare_ether_addr_64bits(eth->h_dest, + dev->broadcast)) + skb->pkt_type = PACKET_BROADCAST; + else + skb->pkt_type = PACKET_MULTICAST; + + return netif_rx(skb); +} + static void macvlan_broadcast(struct sk_buff *skb, - const struct macvlan_port *port) + const struct macvlan_port *port, + struct net_device *src, + enum macvlan_mode mode) { const struct ethhdr *eth = eth_hdr(skb); const struct macvlan_dev *vlan; struct hlist_node *n; - struct net_device *dev; struct sk_buff *nskb; unsigned int i; - struct macvlan_rx_stats *rx_stats; + int err; if (skb->protocol == htons(ETH_P_PAUSE)) return; for (i = 0; i < MACVLAN_HASH_SIZE; i++) { hlist_for_each_entry_rcu(vlan, n, &port->vlan_hash[i], hlist) { - dev = vlan->dev; - rx_stats = per_cpu_ptr(vlan->rx_stats, smp_processor_id()); - - nskb = skb_clone(skb, GFP_ATOMIC); - if (nskb == NULL) { - rx_stats->rx_errors++; + if (vlan->dev == src || !(vlan->mode & mode)) continue; - } - - rx_stats->rx_bytes += skb->len + ETH_HLEN; - rx_stats->rx_packets++; - rx_stats->multicast++; - nskb->dev = dev; - if (!compare_ether_addr_64bits(eth->h_dest, dev->broadcast)) - nskb->pkt_type = PACKET_BROADCAST; - else - nskb->pkt_type = PACKET_MULTICAST; - - netif_rx(nskb); + nskb = skb_clone(skb, GFP_ATOMIC); + err = macvlan_broadcast_one(nskb, vlan->dev, eth, + mode == MACVLAN_MODE_BRIDGE); + macvlan_count_rx(vlan, skb->len + ETH_HLEN, + err == NET_RX_SUCCESS, 1); } } } @@ -162,15 +189,34 @@ static struct sk_buff *macvlan_handle_frame(struct sk_buff *skb) const struct ethhdr *eth = eth_hdr(skb); const struct macvlan_port *port; const struct macvlan_dev *vlan; + const struct macvlan_dev *src; struct net_device *dev; - struct macvlan_rx_stats *rx_stats; + unsigned int len; port = rcu_dereference(skb->dev->macvlan_port); if (port == NULL) return skb; if (is_multicast_ether_addr(eth->h_dest)) { - macvlan_broadcast(skb, port); + src = macvlan_hash_lookup(port, eth->h_source); + if (!src) + /* frame comes from an external address */ + macvlan_broadcast(skb, port, NULL, + MACVLAN_MODE_PRIVATE | + MACVLAN_MODE_VEPA | + MACVLAN_MODE_BRIDGE); + else if (src->mode == MACVLAN_MODE_VEPA) + /* flood to everyone except source */ + macvlan_broadcast(skb, port, src->dev, + MACVLAN_MODE_VEPA | + MACVLAN_MODE_BRIDGE); + else if (src->mode == MACVLAN_MODE_BRIDGE) + /* + * flood only to VEPA ports, bridge ports + * already saw the frame on the way out. + */ + macvlan_broadcast(skb, port, src->dev, + MACVLAN_MODE_VEPA); return skb; } @@ -183,15 +229,11 @@ static struct sk_buff *macvlan_handle_frame(struct sk_buff *skb) kfree_skb(skb); return NULL; } - rx_stats = per_cpu_ptr(vlan->rx_stats, smp_processor_id()); + len = skb->len + ETH_HLEN; skb = skb_share_check(skb, GFP_ATOMIC); - if (skb == NULL) { - rx_stats->rx_errors++; + macvlan_count_rx(vlan, len, skb != NULL, 0); + if (!skb) return NULL; - } - - rx_stats->rx_bytes += skb->len + ETH_HLEN; - rx_stats->rx_packets++; skb->dev = dev; skb->pkt_type = PACKET_HOST; @@ -200,18 +242,46 @@ static struct sk_buff *macvlan_handle_frame(struct sk_buff *skb) return NULL; } +static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) +{ + const struct macvlan_dev *vlan = netdev_priv(dev); + const struct macvlan_port *port = vlan->port; + const struct macvlan_dev *dest; + + if (vlan->mode == MACVLAN_MODE_BRIDGE) { + const struct ethhdr *eth = (void *)skb->data; + + /* send to other bridge ports directly */ + if (is_multicast_ether_addr(eth->h_dest)) { + macvlan_broadcast(skb, port, dev, MACVLAN_MODE_BRIDGE); + goto xmit_world; + } + + dest = macvlan_hash_lookup(port, eth->h_dest); + if (dest && dest->mode == MACVLAN_MODE_BRIDGE) { + unsigned int length = skb->len + ETH_HLEN; + int ret = dev_forward_skb(dest->dev, skb); + macvlan_count_rx(dest, length, + ret == NET_RX_SUCCESS, 0); + + return NET_XMIT_SUCCESS; + } + } + +xmit_world: + skb->dev = vlan->lowerdev; + return dev_queue_xmit(skb); +} + static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, struct net_device *dev) { int i = skb_get_queue_mapping(skb); struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - const struct macvlan_dev *vlan = netdev_priv(dev); unsigned int len = skb->len; int ret; - skb->dev = vlan->lowerdev; - ret = dev_queue_xmit(skb); - + ret = macvlan_queue_xmit(skb, dev); if (likely(ret == NET_XMIT_SUCCESS)) { txq->tx_packets++; txq->tx_bytes += len; @@ -376,6 +446,7 @@ static int macvlan_init(struct net_device *dev) dev->state = (dev->state & ~MACVLAN_STATE_MASK) | (lowerdev->state & MACVLAN_STATE_MASK); dev->features = lowerdev->features & MACVLAN_FEATURES; + dev->gso_max_size = lowerdev->gso_max_size; dev->iflink = lowerdev->ifindex; dev->hard_header_len = lowerdev->hard_header_len; @@ -511,25 +582,6 @@ static void macvlan_port_destroy(struct net_device *dev) kfree(port); } -static void macvlan_transfer_operstate(struct net_device *dev) -{ - struct macvlan_dev *vlan = netdev_priv(dev); - const struct net_device *lowerdev = vlan->lowerdev; - - if (lowerdev->operstate == IF_OPER_DORMANT) - netif_dormant_on(dev); - else - netif_dormant_off(dev); - - if (netif_carrier_ok(lowerdev)) { - if (!netif_carrier_ok(dev)) - netif_carrier_on(dev); - } else { - if (netif_carrier_ok(dev)) - netif_carrier_off(dev); - } -} - static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[]) { if (tb[IFLA_ADDRESS]) { @@ -538,6 +590,17 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[]) if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } + + if (data && data[IFLA_MACVLAN_MODE]) { + switch (nla_get_u32(data[IFLA_MACVLAN_MODE])) { + case MACVLAN_MODE_PRIVATE: + case MACVLAN_MODE_VEPA: + case MACVLAN_MODE_BRIDGE: + break; + default: + return -EINVAL; + } + } return 0; } @@ -602,12 +665,16 @@ static int macvlan_newlink(struct net *src_net, struct net_device *dev, vlan->dev = dev; vlan->port = port; + vlan->mode = MACVLAN_MODE_VEPA; + if (data && data[IFLA_MACVLAN_MODE]) + vlan->mode = nla_get_u32(data[IFLA_MACVLAN_MODE]); + err = register_netdevice(dev); if (err < 0) return err; list_add_tail(&vlan->list, &port->vlans); - macvlan_transfer_operstate(dev); + netif_stacked_transfer_operstate(lowerdev, dev); return 0; } @@ -623,6 +690,36 @@ static void macvlan_dellink(struct net_device *dev, struct list_head *head) macvlan_port_destroy(port->dev); } +static int macvlan_changelink(struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[]) +{ + struct macvlan_dev *vlan = netdev_priv(dev); + if (data && data[IFLA_MACVLAN_MODE]) + vlan->mode = nla_get_u32(data[IFLA_MACVLAN_MODE]); + return 0; +} + +static size_t macvlan_get_size(const struct net_device *dev) +{ + return nla_total_size(4); +} + +static int macvlan_fill_info(struct sk_buff *skb, + const struct net_device *dev) +{ + struct macvlan_dev *vlan = netdev_priv(dev); + + NLA_PUT_U32(skb, IFLA_MACVLAN_MODE, vlan->mode); + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy macvlan_policy[IFLA_MACVLAN_MAX + 1] = { + [IFLA_MACVLAN_MODE] = { .type = NLA_U32 }, +}; + static struct rtnl_link_ops macvlan_link_ops __read_mostly = { .kind = "macvlan", .priv_size = sizeof(struct macvlan_dev), @@ -631,6 +728,11 @@ static struct rtnl_link_ops macvlan_link_ops __read_mostly = { .validate = macvlan_validate, .newlink = macvlan_newlink, .dellink = macvlan_dellink, + .maxtype = IFLA_MACVLAN_MAX, + .policy = macvlan_policy, + .changelink = macvlan_changelink, + .get_size = macvlan_get_size, + .fill_info = macvlan_fill_info, }; static int macvlan_device_event(struct notifier_block *unused, @@ -647,11 +749,13 @@ static int macvlan_device_event(struct notifier_block *unused, switch (event) { case NETDEV_CHANGE: list_for_each_entry(vlan, &port->vlans, list) - macvlan_transfer_operstate(vlan->dev); + netif_stacked_transfer_operstate(vlan->lowerdev, + vlan->dev); break; case NETDEV_FEAT_CHANGE: list_for_each_entry(vlan, &port->vlans, list) { vlan->dev->features = dev->features & MACVLAN_FEATURES; + vlan->dev->gso_max_size = dev->gso_max_size; netdev_features_change(vlan->dev); } break; diff --git a/drivers/net/mv643xx_eth.c b/drivers/net/mv643xx_eth.c index b62e61d4ca3e..796a493f95ab 100644 --- a/drivers/net/mv643xx_eth.c +++ b/drivers/net/mv643xx_eth.c @@ -849,7 +849,7 @@ no_csum: return 0; } -static int mv643xx_eth_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t mv643xx_eth_xmit(struct sk_buff *skb, struct net_device *dev) { struct mv643xx_eth_private *mp = netdev_priv(dev); int queue; diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c index 85e1b6a3ac1b..d38921906bb7 100644 --- a/drivers/net/myri10ge/myri10ge.c +++ b/drivers/net/myri10ge/myri10ge.c @@ -410,8 +410,8 @@ myri10ge_send_cmd(struct myri10ge_priv *mgp, u32 cmd, * and try to get the completion quickly * (1ms will be enough for those commands) */ for (sleep_total = 0; - sleep_total < 1000 - && response->result == htonl(MYRI10GE_NO_RESPONSE_RESULT); + sleep_total < 1000 && + response->result == htonl(MYRI10GE_NO_RESPONSE_RESULT); sleep_total += 10) { udelay(10); mb(); @@ -419,8 +419,8 @@ myri10ge_send_cmd(struct myri10ge_priv *mgp, u32 cmd, } else { /* use msleep for most command */ for (sleep_total = 0; - sleep_total < 15 - && response->result == htonl(MYRI10GE_NO_RESPONSE_RESULT); + sleep_total < 15 && + response->result == htonl(MYRI10GE_NO_RESPONSE_RESULT); sleep_total++) msleep(1); } @@ -557,8 +557,8 @@ myri10ge_validate_firmware(struct myri10ge_priv *mgp, sscanf(mgp->fw_version, "%d.%d.%d", &mgp->fw_ver_major, &mgp->fw_ver_minor, &mgp->fw_ver_tiny); - if (!(mgp->fw_ver_major == MXGEFW_VERSION_MAJOR - && mgp->fw_ver_minor == MXGEFW_VERSION_MINOR)) { + if (!(mgp->fw_ver_major == MXGEFW_VERSION_MAJOR && + mgp->fw_ver_minor == MXGEFW_VERSION_MINOR)) { dev_err(dev, "Found firmware version %s\n", mgp->fw_version); dev_err(dev, "Driver needs %d.%d\n", MXGEFW_VERSION_MAJOR, MXGEFW_VERSION_MINOR); @@ -1412,8 +1412,8 @@ myri10ge_tx_done(struct myri10ge_slice_state *ss, int mcp_index) } /* start the queue if we've stopped it */ - if (netif_tx_queue_stopped(dev_queue) - && tx->req - tx->done < (tx->mask >> 1)) { + if (netif_tx_queue_stopped(dev_queue) && + tx->req - tx->done < (tx->mask >> 1)) { tx->wake_queue++; netif_tx_wake_queue(dev_queue); } diff --git a/drivers/net/natsemi.c b/drivers/net/natsemi.c index 9a8d3ab4709b..797fe164ce27 100644 --- a/drivers/net/natsemi.c +++ b/drivers/net/natsemi.c @@ -683,8 +683,8 @@ static ssize_t natsemi_set_dspcfg_workaround(struct device *dev, /* Find out the new setting */ if (!strncmp("on", buf, count - 1) || !strncmp("1", buf, count - 1)) new_setting = 1; - else if (!strncmp("off", buf, count - 1) - || !strncmp("0", buf, count - 1)) + else if (!strncmp("off", buf, count - 1) || + !strncmp("0", buf, count - 1)) new_setting = 0; else return count; @@ -757,8 +757,8 @@ static void __devinit natsemi_init_media (struct net_device *dev) np->autoneg = (tmp & BMCR_ANENABLE)? AUTONEG_ENABLE: AUTONEG_DISABLE; np->advertising= mdio_read(dev, MII_ADVERTISE); - if ((np->advertising & ADVERTISE_ALL) != ADVERTISE_ALL - && netif_msg_probe(np)) { + if ((np->advertising & ADVERTISE_ALL) != ADVERTISE_ALL && + netif_msg_probe(np)) { printk(KERN_INFO "natsemi %s: Transceiver default autonegotiation %s " "10%s %s duplex.\n", pci_name(np->pci_dev), @@ -1153,8 +1153,8 @@ static void init_phy_fixup(struct net_device *dev) tmp = mdio_read(dev, MII_BMCR); if (np->autoneg == AUTONEG_ENABLE) { /* renegotiate if something changed */ - if ((tmp & BMCR_ANENABLE) == 0 - || np->advertising != mdio_read(dev, MII_ADVERTISE)) + if ((tmp & BMCR_ANENABLE) == 0 || + np->advertising != mdio_read(dev, MII_ADVERTISE)) { /* turn on autonegotiation and force negotiation */ tmp |= (BMCR_ANENABLE | BMCR_ANRESTART); @@ -2164,8 +2164,8 @@ static void netdev_tx_done(struct net_device *dev) dev_kfree_skb_irq(np->tx_skbuff[entry]); np->tx_skbuff[entry] = NULL; } - if (netif_queue_stopped(dev) - && np->cur_tx - np->dirty_tx < TX_QUEUE_LEN - 4) { + if (netif_queue_stopped(dev) && + np->cur_tx - np->dirty_tx < TX_QUEUE_LEN - 4) { /* The ring is no longer full, wake queue. */ netif_wake_queue(dev); } @@ -2343,8 +2343,8 @@ static void netdev_rx(struct net_device *dev, int *work_done, int work_to_do) /* Omit CRC size. */ /* Check if the packet is long enough to accept * without copying to a minimally-sized skbuff. */ - if (pkt_len < rx_copybreak - && (skb = dev_alloc_skb(pkt_len + RX_OFFSET)) != NULL) { + if (pkt_len < rx_copybreak && + (skb = dev_alloc_skb(pkt_len + RX_OFFSET)) != NULL) { /* 16 byte align the IP header */ skb_reserve(skb, RX_OFFSET); pci_dma_sync_single_for_cpu(np->pci_dev, @@ -2390,8 +2390,8 @@ static void netdev_error(struct net_device *dev, int intr_status) spin_lock(&np->lock); if (intr_status & LinkChange) { u16 lpa = mdio_read(dev, MII_LPA); - if (mdio_read(dev, MII_BMCR) & BMCR_ANENABLE - && netif_msg_link(np)) { + if (mdio_read(dev, MII_BMCR) & BMCR_ANENABLE && + netif_msg_link(np)) { printk(KERN_INFO "%s: Autonegotiation advertising" " %#04x partner %#04x.\n", dev->name, @@ -2488,8 +2488,8 @@ static void __set_rx_mode(struct net_device *dev) if (dev->flags & IFF_PROMISC) { /* Set promiscuous. */ rx_mode = RxFilterEnable | AcceptBroadcast | AcceptAllMulticast | AcceptAllPhys | AcceptMyPhys; - } else if ((dev->mc_count > multicast_filter_limit) - || (dev->flags & IFF_ALLMULTI)) { + } else if ((dev->mc_count > multicast_filter_limit) || + (dev->flags & IFF_ALLMULTI)) { rx_mode = RxFilterEnable | AcceptBroadcast | AcceptAllMulticast | AcceptMyPhys; } else { diff --git a/drivers/net/netxen/netxen_nic.h b/drivers/net/netxen/netxen_nic.h index 645450d93f4e..76cd1f3e9fc8 100644 --- a/drivers/net/netxen/netxen_nic.h +++ b/drivers/net/netxen/netxen_nic.h @@ -1202,6 +1202,8 @@ struct netxen_adapter { u32 int_vec_bit; u32 heartbit; + u8 mac_addr[ETH_ALEN]; + struct netxen_adapter_stats stats; struct netxen_recv_context recv_ctx; diff --git a/drivers/net/netxen/netxen_nic_ethtool.c b/drivers/net/netxen/netxen_nic_ethtool.c index c86095eb5d9e..ddd704ae0188 100644 --- a/drivers/net/netxen/netxen_nic_ethtool.c +++ b/drivers/net/netxen/netxen_nic_ethtool.c @@ -257,18 +257,18 @@ netxen_nic_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd) /* read which mode */ if (adapter->ahw.port_type == NETXEN_NIC_GBE) { /* autonegotiation */ - if (adapter->phy_write - && adapter->phy_write(adapter, - NETXEN_NIU_GB_MII_MGMT_ADDR_AUTONEG, - ecmd->autoneg) != 0) + if (adapter->phy_write && + adapter->phy_write(adapter, + NETXEN_NIU_GB_MII_MGMT_ADDR_AUTONEG, + ecmd->autoneg) != 0) return -EIO; else adapter->link_autoneg = ecmd->autoneg; - if (adapter->phy_read - && adapter->phy_read(adapter, - NETXEN_NIU_GB_MII_MGMT_ADDR_PHY_STATUS, - &status) != 0) + if (adapter->phy_read && + adapter->phy_read(adapter, + NETXEN_NIU_GB_MII_MGMT_ADDR_PHY_STATUS, + &status) != 0) return -EIO; /* speed */ @@ -288,10 +288,10 @@ netxen_nic_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd) netxen_clear_phy_duplex(status); if (ecmd->duplex == DUPLEX_FULL) netxen_set_phy_duplex(status); - if (adapter->phy_write - && adapter->phy_write(adapter, - NETXEN_NIU_GB_MII_MGMT_ADDR_PHY_STATUS, - *((int *)&status)) != 0) + if (adapter->phy_write && + adapter->phy_write(adapter, + NETXEN_NIU_GB_MII_MGMT_ADDR_PHY_STATUS, + *((int *)&status)) != 0) return -EIO; else { adapter->link_speed = ecmd->speed; @@ -442,10 +442,10 @@ static u32 netxen_nic_test_link(struct net_device *dev) /* read which mode */ if (adapter->ahw.port_type == NETXEN_NIC_GBE) { - if (adapter->phy_read - && adapter->phy_read(adapter, - NETXEN_NIU_GB_MII_MGMT_ADDR_PHY_STATUS, - &status) != 0) + if (adapter->phy_read && + adapter->phy_read(adapter, + NETXEN_NIU_GB_MII_MGMT_ADDR_PHY_STATUS, + &status) != 0) return -EIO; else { val = netxen_get_phy_link(status); diff --git a/drivers/net/netxen/netxen_nic_hdr.h b/drivers/net/netxen/netxen_nic_hdr.h index a39155d61bad..d138fc22927a 100644 --- a/drivers/net/netxen/netxen_nic_hdr.h +++ b/drivers/net/netxen/netxen_nic_hdr.h @@ -545,6 +545,8 @@ enum { #define NETXEN_NIU_TEST_MUX_CTL (NETXEN_CRB_NIU + 0x00094) #define NETXEN_NIU_XG_PAUSE_CTL (NETXEN_CRB_NIU + 0x00098) #define NETXEN_NIU_XG_PAUSE_LEVEL (NETXEN_CRB_NIU + 0x000dc) +#define NETXEN_NIU_FRAME_COUNT_SELECT (NETXEN_CRB_NIU + 0x000ac) +#define NETXEN_NIU_FRAME_COUNT (NETXEN_CRB_NIU + 0x000b0) #define NETXEN_NIU_XG_SEL (NETXEN_CRB_NIU + 0x00128) #define NETXEN_NIU_GB_PAUSE_CTL (NETXEN_CRB_NIU + 0x0030c) diff --git a/drivers/net/netxen/netxen_nic_hw.c b/drivers/net/netxen/netxen_nic_hw.c index b3054c6cc608..2e364fee3cbb 100644 --- a/drivers/net/netxen/netxen_nic_hw.c +++ b/drivers/net/netxen/netxen_nic_hw.c @@ -389,24 +389,51 @@ int netxen_niu_disable_xg_port(struct netxen_adapter *adapter) int netxen_p2_nic_set_promisc(struct netxen_adapter *adapter, u32 mode) { - __u32 reg; + u32 mac_cfg; + u32 cnt = 0; + __u32 reg = 0x0200; u32 port = adapter->physical_port; + u16 board_type = adapter->ahw.board_type; if (port > NETXEN_NIU_MAX_XG_PORTS) return -EINVAL; - reg = NXRD32(adapter, NETXEN_NIU_XGE_CONFIG_1 + (0x10000 * port)); - if (mode == NETXEN_NIU_PROMISC_MODE) - reg = (reg | 0x2000UL); - else - reg = (reg & ~0x2000UL); + mac_cfg = NXRD32(adapter, NETXEN_NIU_XGE_CONFIG_0 + (0x10000 * port)); + mac_cfg &= ~0x4; + NXWR32(adapter, NETXEN_NIU_XGE_CONFIG_0 + (0x10000 * port), mac_cfg); - if (mode == NETXEN_NIU_ALLMULTI_MODE) - reg = (reg | 0x1000UL); - else - reg = (reg & ~0x1000UL); + if ((board_type == NETXEN_BRDTYPE_P2_SB31_10G_IMEZ) || + (board_type == NETXEN_BRDTYPE_P2_SB31_10G_HMEZ)) + reg = (0x20 << port); + + NXWR32(adapter, NETXEN_NIU_FRAME_COUNT_SELECT, reg); + + mdelay(10); + + while (NXRD32(adapter, NETXEN_NIU_FRAME_COUNT) && ++cnt < 20) + mdelay(10); + + if (cnt < 20) { - NXWR32(adapter, NETXEN_NIU_XGE_CONFIG_1 + (0x10000 * port), reg); + reg = NXRD32(adapter, + NETXEN_NIU_XGE_CONFIG_1 + (0x10000 * port)); + + if (mode == NETXEN_NIU_PROMISC_MODE) + reg = (reg | 0x2000UL); + else + reg = (reg & ~0x2000UL); + + if (mode == NETXEN_NIU_ALLMULTI_MODE) + reg = (reg | 0x1000UL); + else + reg = (reg & ~0x1000UL); + + NXWR32(adapter, + NETXEN_NIU_XGE_CONFIG_1 + (0x10000 * port), reg); + } + + mac_cfg |= 0x4; + NXWR32(adapter, NETXEN_NIU_XGE_CONFIG_0 + (0x10000 * port), mac_cfg); return 0; } @@ -442,7 +469,7 @@ netxen_nic_enable_mcast_filter(struct netxen_adapter *adapter) { u32 val = 0; u16 port = adapter->physical_port; - u8 *addr = adapter->netdev->dev_addr; + u8 *addr = adapter->mac_addr; if (adapter->mc_enabled) return 0; @@ -471,7 +498,7 @@ netxen_nic_disable_mcast_filter(struct netxen_adapter *adapter) { u32 val = 0; u16 port = adapter->physical_port; - u8 *addr = adapter->netdev->dev_addr; + u8 *addr = adapter->mac_addr; if (!adapter->mc_enabled) return 0; @@ -666,7 +693,7 @@ void netxen_p3_nic_set_multi(struct net_device *netdev) list_splice_tail_init(&adapter->mac_list, &del_list); - nx_p3_nic_add_mac(adapter, netdev->dev_addr, &del_list); + nx_p3_nic_add_mac(adapter, adapter->mac_addr, &del_list); nx_p3_nic_add_mac(adapter, bcast_addr, &del_list); if (netdev->flags & IFF_PROMISC) { @@ -1148,24 +1175,46 @@ netxen_nic_pci_set_crbwindow_2M(struct netxen_adapter *adapter, ulong off) adapter->ahw.crb_win = window; } +static void __iomem * +netxen_nic_map_indirect_address_128M(struct netxen_adapter *adapter, + ulong win_off, void __iomem **mem_ptr) +{ + ulong off = win_off; + void __iomem *addr; + resource_size_t mem_base; + + if (ADDR_IN_WINDOW1(win_off)) + off = NETXEN_CRB_NORMAL(win_off); + + addr = pci_base_offset(adapter, off); + if (addr) + return addr; + + if (adapter->ahw.pci_len0 == 0) + off -= NETXEN_PCI_CRBSPACE; + + mem_base = pci_resource_start(adapter->pdev, 0); + *mem_ptr = ioremap(mem_base + (off & PAGE_MASK), PAGE_SIZE); + if (*mem_ptr) + addr = *mem_ptr + (off & (PAGE_SIZE - 1)); + + return addr; +} + static int netxen_nic_hw_write_wx_128M(struct netxen_adapter *adapter, ulong off, u32 data) { unsigned long flags; - void __iomem *addr; - - if (ADDR_IN_WINDOW1(off)) - addr = NETXEN_CRB_NORMALIZE(adapter, off); - else - addr = pci_base_offset(adapter, off); + void __iomem *addr, *mem_ptr = NULL; - BUG_ON(!addr); + addr = netxen_nic_map_indirect_address_128M(adapter, off, &mem_ptr); + if (!addr) + return -EIO; - if (ADDR_IN_WINDOW1(off)) { /* Window 1 */ + if (ADDR_IN_WINDOW1(off)) { /* Window 1 */ netxen_nic_io_write_128M(adapter, addr, data); - } else { /* Window 0 */ + } else { /* Window 0 */ write_lock_irqsave(&adapter->ahw.crb_lock, flags); - addr = pci_base_offset(adapter, off); netxen_nic_pci_set_crbwindow_128M(adapter, 0); writel(data, addr); netxen_nic_pci_set_crbwindow_128M(adapter, @@ -1173,6 +1222,9 @@ netxen_nic_hw_write_wx_128M(struct netxen_adapter *adapter, ulong off, u32 data) write_unlock_irqrestore(&adapter->ahw.crb_lock, flags); } + if (mem_ptr) + iounmap(mem_ptr); + return 0; } @@ -1180,19 +1232,16 @@ static u32 netxen_nic_hw_read_wx_128M(struct netxen_adapter *adapter, ulong off) { unsigned long flags; - void __iomem *addr; + void __iomem *addr, *mem_ptr = NULL; u32 data; - if (ADDR_IN_WINDOW1(off)) - addr = NETXEN_CRB_NORMALIZE(adapter, off); - else - addr = pci_base_offset(adapter, off); - - BUG_ON(!addr); + addr = netxen_nic_map_indirect_address_128M(adapter, off, &mem_ptr); + if (!addr) + return -EIO; - if (ADDR_IN_WINDOW1(off)) { /* Window 1 */ + if (ADDR_IN_WINDOW1(off)) { /* Window 1 */ data = netxen_nic_io_read_128M(adapter, addr); - } else { /* Window 0 */ + } else { /* Window 0 */ write_lock_irqsave(&adapter->ahw.crb_lock, flags); netxen_nic_pci_set_crbwindow_128M(adapter, 0); data = readl(addr); @@ -1201,6 +1250,9 @@ netxen_nic_hw_read_wx_128M(struct netxen_adapter *adapter, ulong off) write_unlock_irqrestore(&adapter->ahw.crb_lock, flags); } + if (mem_ptr) + iounmap(mem_ptr); + return data; } @@ -1884,10 +1936,10 @@ void netxen_nic_set_link_parameters(struct netxen_adapter *adapter) return; } - if (adapter->phy_read - && adapter->phy_read(adapter, - NETXEN_NIU_GB_MII_MGMT_ADDR_PHY_STATUS, - &status) == 0) { + if (adapter->phy_read && + adapter->phy_read(adapter, + NETXEN_NIU_GB_MII_MGMT_ADDR_PHY_STATUS, + &status) == 0) { if (netxen_get_phy_link(status)) { switch (netxen_get_phy_speed(status)) { case 0: @@ -1914,10 +1966,10 @@ void netxen_nic_set_link_parameters(struct netxen_adapter *adapter) adapter->link_duplex = -1; break; } - if (adapter->phy_read - && adapter->phy_read(adapter, - NETXEN_NIU_GB_MII_MGMT_ADDR_AUTONEG, - &autoneg) != 0) + if (adapter->phy_read && + adapter->phy_read(adapter, + NETXEN_NIU_GB_MII_MGMT_ADDR_AUTONEG, + &autoneg) != 0) adapter->link_autoneg = autoneg; } else goto link_down; diff --git a/drivers/net/netxen/netxen_nic_init.c b/drivers/net/netxen/netxen_nic_init.c index 6ee27a630d89..80a667460514 100644 --- a/drivers/net/netxen/netxen_nic_init.c +++ b/drivers/net/netxen/netxen_nic_init.c @@ -528,6 +528,8 @@ int netxen_pinit_from_rom(struct netxen_adapter *adapter) continue; if (off == (ROMUSB_GLB + 0x1c)) /* MS clock */ continue; + if ((off & 0x0ff00000) == NETXEN_CRB_DDR_NET) + continue; if (off == (NETXEN_CRB_PEG_NET_1 + 0x18) && !NX_IS_REVISION_P3P(adapter->ahw.revision_id)) buf[i].data = 0x1020; diff --git a/drivers/net/netxen/netxen_nic_main.c b/drivers/net/netxen/netxen_nic_main.c index bfbf75c17cf8..e5d187fce51b 100644 --- a/drivers/net/netxen/netxen_nic_main.c +++ b/drivers/net/netxen/netxen_nic_main.c @@ -445,6 +445,7 @@ netxen_read_mac_addr(struct netxen_adapter *adapter) netdev->dev_addr[i] = *(p + 5 - i); memcpy(netdev->perm_addr, netdev->dev_addr, netdev->addr_len); + memcpy(adapter->mac_addr, netdev->dev_addr, netdev->addr_len); /* set station address */ @@ -467,6 +468,7 @@ int netxen_nic_set_mac(struct net_device *netdev, void *p) netxen_napi_disable(adapter); } + memcpy(adapter->mac_addr, addr->sa_data, netdev->addr_len); memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); adapter->macaddr_set(adapter, addr->sa_data); @@ -817,7 +819,7 @@ netxen_start_firmware(struct netxen_adapter *adapter) if (err < 0) goto err_out; if (err == 0) - goto ready; + goto wait_init; if (first_boot != 0x55555555) { NXWR32(adapter, CRB_CMDPEG_STATE, 0); @@ -860,9 +862,6 @@ netxen_start_firmware(struct netxen_adapter *adapter) | (_NETXEN_NIC_LINUX_SUBVERSION); NXWR32(adapter, CRB_DRIVER_VERSION, val); -ready: - NXWR32(adapter, NX_CRB_DEV_STATE, NX_DEV_READY); - wait_init: /* Handshake with the card before we register the devices. */ err = netxen_phantom_init(adapter, NETXEN_NIC_PEG_TUNE); @@ -871,6 +870,8 @@ wait_init: goto err_out; } + NXWR32(adapter, NX_CRB_DEV_STATE, NX_DEV_READY); + nx_update_dma_mask(adapter); netxen_check_options(adapter); @@ -960,7 +961,7 @@ netxen_nic_up(struct netxen_adapter *adapter, struct net_device *netdev) return err; } if (NX_IS_REVISION_P2(adapter->ahw.revision_id)) - adapter->macaddr_set(adapter, netdev->dev_addr); + adapter->macaddr_set(adapter, adapter->mac_addr); adapter->set_multi(netdev); adapter->set_mtu(adapter, netdev->mtu); @@ -1280,7 +1281,7 @@ netxen_nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = netxen_start_firmware(adapter); if (err) - goto err_out_iounmap; + goto err_out_decr_ref; /* * See if the firmware gave us a virtual-physical port mapping. @@ -1324,6 +1325,7 @@ err_out_disable_msi: netxen_free_dummy_dma(adapter); +err_out_decr_ref: nx_decr_dev_ref_cnt(adapter); err_out_iounmap: @@ -2187,14 +2189,13 @@ netxen_fwinit_work(struct work_struct *work) netxen_fwinit_work, 2 * FW_POLL_DELAY); return; } - break; case NX_DEV_FAILED: default: + nx_incr_dev_ref_cnt(adapter); break; } - nx_incr_dev_ref_cnt(adapter); clear_bit(__NX_RESETTING, &adapter->state); } @@ -2216,18 +2217,23 @@ netxen_detach_work(struct work_struct *work) status = NXRD32(adapter, NETXEN_PEG_HALT_STATUS1); - ref_cnt = nx_decr_dev_ref_cnt(adapter); - if (status & NX_RCODE_FATAL_ERROR) - return; + goto err_ret; if (adapter->temp == NX_TEMP_PANIC) - return; + goto err_ret; + + ref_cnt = nx_decr_dev_ref_cnt(adapter); delay = (ref_cnt == 0) ? 0 : (2 * FW_POLL_DELAY); adapter->fw_wait_cnt = 0; netxen_schedule_work(adapter, netxen_fwinit_work, delay); + + return; + +err_ret: + clear_bit(__NX_RESETTING, &adapter->state); } static int diff --git a/drivers/net/ni52.c b/drivers/net/ni52.c index 305f4ba36999..b42f5e522f90 100644 --- a/drivers/net/ni52.c +++ b/drivers/net/ni52.c @@ -477,8 +477,8 @@ static int __init ni52_probe1(struct net_device *dev, int ioaddr) for (i = 0; i < ETH_ALEN; i++) dev->dev_addr[i] = inb(dev->base_addr+i); - if (dev->dev_addr[0] != NI52_ADDR0 || dev->dev_addr[1] != NI52_ADDR1 - || dev->dev_addr[2] != NI52_ADDR2) { + if (dev->dev_addr[0] != NI52_ADDR0 || dev->dev_addr[1] != NI52_ADDR1 || + dev->dev_addr[2] != NI52_ADDR2) { retval = -ENODEV; goto out; } diff --git a/drivers/net/ns83820.c b/drivers/net/ns83820.c index 57fd483dbb1f..1f6327d41536 100644 --- a/drivers/net/ns83820.c +++ b/drivers/net/ns83820.c @@ -648,8 +648,8 @@ static void phy_intr(struct net_device *ndev) dprintk("phy_intr: tbisr=%08x, tanar=%08x, tanlpar=%08x\n", tbisr, tanar, tanlpar); - if ( (fullduplex = (tanlpar & TANAR_FULL_DUP) - && (tanar & TANAR_FULL_DUP)) ) { + if ( (fullduplex = (tanlpar & TANAR_FULL_DUP) && + (tanar & TANAR_FULL_DUP)) ) { /* both of us are full duplex */ writel(readl(dev->base + TXCFG) @@ -661,12 +661,12 @@ static void phy_intr(struct net_device *ndev) writel(readl(dev->base + GPIOR) | GPIOR_GP1_OUT, dev->base + GPIOR); - } else if(((tanlpar & TANAR_HALF_DUP) - && (tanar & TANAR_HALF_DUP)) - || ((tanlpar & TANAR_FULL_DUP) - && (tanar & TANAR_HALF_DUP)) - || ((tanlpar & TANAR_HALF_DUP) - && (tanar & TANAR_FULL_DUP))) { + } else if (((tanlpar & TANAR_HALF_DUP) && + (tanar & TANAR_HALF_DUP)) || + ((tanlpar & TANAR_FULL_DUP) && + (tanar & TANAR_HALF_DUP)) || + ((tanlpar & TANAR_HALF_DUP) && + (tanar & TANAR_FULL_DUP))) { /* one or both of us are half duplex */ writel((readl(dev->base + TXCFG) @@ -720,16 +720,16 @@ static void phy_intr(struct net_device *ndev) newlinkstate = (cfg & CFG_LNKSTS) ? LINK_UP : LINK_DOWN; - if (newlinkstate & LINK_UP - && dev->linkstate != newlinkstate) { + if (newlinkstate & LINK_UP && + dev->linkstate != newlinkstate) { netif_start_queue(ndev); netif_wake_queue(ndev); printk(KERN_INFO "%s: link now %s mbps, %s duplex and up.\n", ndev->name, speeds[speed], fullduplex ? "full" : "half"); - } else if (newlinkstate & LINK_DOWN - && dev->linkstate != newlinkstate) { + } else if (newlinkstate & LINK_DOWN && + dev->linkstate != newlinkstate) { netif_stop_queue(ndev); printk(KERN_INFO "%s: link now down.\n", ndev->name); } diff --git a/drivers/net/pci-skeleton.c b/drivers/net/pci-skeleton.c index 0c44b48f1384..480af402affd 100644 --- a/drivers/net/pci-skeleton.c +++ b/drivers/net/pci-skeleton.c @@ -1225,8 +1225,8 @@ static void netdrv_timer (unsigned long data) mii_lpa = mdio_read (dev, tp->phys[0], MII_LPA); if (!tp->duplex_lock && mii_lpa != 0xffff) { - int duplex = (mii_lpa & LPA_100FULL) - || (mii_lpa & 0x01C0) == 0x0040; + int duplex = ((mii_lpa & LPA_100FULL) || + (mii_lpa & 0x01C0) == 0x0040); if (tp->full_duplex != duplex) { tp->full_duplex = duplex; printk (KERN_INFO @@ -1612,8 +1612,8 @@ static void netdrv_weird_interrupt (struct net_device *dev, (tp->drv_flags & HAS_LNK_CHNG)) { /* Really link-change on new chips. */ int lpar = NETDRV_R16 (NWayLPAR); - int duplex = (lpar & 0x0100) || (lpar & 0x01C0) == 0x0040 - || tp->duplex_lock; + int duplex = ((lpar & 0x0100) || (lpar & 0x01C0) == 0x0040 || + tp->duplex_lock); if (tp->full_duplex != duplex) { tp->full_duplex = duplex; NETDRV_W8 (Cfg9346, Cfg9346_Unlock); @@ -1820,8 +1820,8 @@ static void netdrv_set_rx_mode (struct net_device *dev) AcceptBroadcast | AcceptMulticast | AcceptMyPhys | AcceptAllPhys; mc_filter[1] = mc_filter[0] = 0xffffffff; - } else if ((dev->mc_count > multicast_filter_limit) - || (dev->flags & IFF_ALLMULTI)) { + } else if ((dev->mc_count > multicast_filter_limit) || + (dev->flags & IFF_ALLMULTI)) { /* Too many to filter perfectly -- accept all multicasts. */ rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0xffffffff; diff --git a/drivers/net/pcmcia/axnet_cs.c b/drivers/net/pcmcia/axnet_cs.c index 3131a59a8d32..ca711f46814e 100644 --- a/drivers/net/pcmcia/axnet_cs.c +++ b/drivers/net/pcmcia/axnet_cs.c @@ -1232,8 +1232,8 @@ static irqreturn_t ax_interrupt(int irq, void *dev_id) ei_local->irqlock = 1; /* !!Assumption!! -- we stay in page 0. Don't break this. */ - while ((interrupts = inb_p(e8390_base + EN0_ISR)) != 0 - && ++nr_serviced < MAX_SERVICE) + while ((interrupts = inb_p(e8390_base + EN0_ISR)) != 0 && + ++nr_serviced < MAX_SERVICE) { if (!netif_running(dev) || (interrupts == 0xff)) { if (ei_debug > 1) diff --git a/drivers/net/pcmcia/fmvj18x_cs.c b/drivers/net/pcmcia/fmvj18x_cs.c index 57e09616330a..a6961215cd56 100644 --- a/drivers/net/pcmcia/fmvj18x_cs.c +++ b/drivers/net/pcmcia/fmvj18x_cs.c @@ -371,9 +371,9 @@ static int fmvj18x_config(struct pcmcia_device *link) switch (link->manf_id) { case MANFID_TDK: cardtype = TDK; - if (link->card_id == PRODID_TDK_GN3410 - || link->card_id == PRODID_TDK_NP9610 - || link->card_id == PRODID_TDK_MN3200) { + if (link->card_id == PRODID_TDK_GN3410 || + link->card_id == PRODID_TDK_NP9610 || + link->card_id == PRODID_TDK_MN3200) { /* MultiFunction Card */ link->conf.ConfigBase = 0x800; link->conf.ConfigIndex = 0x47; @@ -590,11 +590,11 @@ static int fmvj18x_get_hwinfo(struct pcmcia_device *link, u_char *node_id) */ for (i = 0; i < 0x200; i++) { if (readb(base+i*2) == 0x22) { - if (readb(base+(i-1)*2) == 0xff - && readb(base+(i+5)*2) == 0x04 - && readb(base+(i+6)*2) == 0x06 - && readb(base+(i+13)*2) == 0xff) - break; + if (readb(base+(i-1)*2) == 0xff && + readb(base+(i+5)*2) == 0x04 && + readb(base+(i+6)*2) == 0x06 && + readb(base+(i+13)*2) == 0xff) + break; } } @@ -1219,8 +1219,8 @@ static void set_rx_mode(struct net_device *dev) if (dev->flags & IFF_PROMISC) { memset(mc_filter, 0xff, sizeof(mc_filter)); outb(3, ioaddr + RX_MODE); /* Enable promiscuous mode */ - } else if (dev->mc_count > MC_FILTERBREAK - || (dev->flags & IFF_ALLMULTI)) { + } else if (dev->mc_count > MC_FILTERBREAK || + (dev->flags & IFF_ALLMULTI)) { /* Too many to filter perfectly -- accept all multicasts. */ memset(mc_filter, 0xff, sizeof(mc_filter)); outb(2, ioaddr + RX_MODE); /* Use normal mode. */ diff --git a/drivers/net/pcmcia/pcnet_cs.c b/drivers/net/pcmcia/pcnet_cs.c index 469684474b72..347eaee855c0 100644 --- a/drivers/net/pcmcia/pcnet_cs.c +++ b/drivers/net/pcmcia/pcnet_cs.c @@ -601,8 +601,8 @@ static int pcnet_config(struct pcmcia_device *link) dev->if_port = 0; } - if ((link->conf.ConfigBase == 0x03c0) - && (link->manf_id == 0x149) && (link->card_id == 0xc1ab)) { + if ((link->conf.ConfigBase == 0x03c0) && + (link->manf_id == 0x149) && (link->card_id == 0xc1ab)) { printk(KERN_INFO "pcnet_cs: this is an AX88190 card!\n"); printk(KERN_INFO "pcnet_cs: use axnet_cs instead.\n"); goto failed; diff --git a/drivers/net/pcmcia/smc91c92_cs.c b/drivers/net/pcmcia/smc91c92_cs.c index 7bde2cd34c7e..117b083a10cb 100644 --- a/drivers/net/pcmcia/smc91c92_cs.c +++ b/drivers/net/pcmcia/smc91c92_cs.c @@ -526,10 +526,10 @@ static int mhz_mfc_config(struct pcmcia_device *link) mem.CardOffset = link->conf.ConfigBase; i = pcmcia_map_mem_page(link->win, &mem); - if ((i == 0) - && (smc->manfid == MANFID_MEGAHERTZ) - && (smc->cardid == PRODID_MEGAHERTZ_EM3288)) - mhz_3288_power(link); + if ((i == 0) && + (smc->manfid == MANFID_MEGAHERTZ) && + (smc->cardid == PRODID_MEGAHERTZ_EM3288)) + mhz_3288_power(link); free_cfg_mem: kfree(cfg_mem); diff --git a/drivers/net/pcmcia/xirc2ps_cs.c b/drivers/net/pcmcia/xirc2ps_cs.c index cf8423102538..187da21f720b 100644 --- a/drivers/net/pcmcia/xirc2ps_cs.c +++ b/drivers/net/pcmcia/xirc2ps_cs.c @@ -421,9 +421,9 @@ PrintRegisters(struct net_device *dev) printk("\n"); } for (page=0x40 ; page <= 0x5f; page++) { - if (page == 0x43 || (page >= 0x46 && page <= 0x4f) - || (page >= 0x51 && page <=0x5e)) - continue; + if (page == 0x43 || (page >= 0x46 && page <= 0x4f) || + (page >= 0x51 && page <=0x5e)) + continue; printk(KDBG_XIRC "Register page %2x: ", page); SelectPage(page); for (i = 8; i < 16; i++) @@ -834,9 +834,9 @@ xirc2ps_config(struct pcmcia_device * link) /* Once I saw two CISTPL_FUNCE_LAN_NODE_ID entries: * the first one with a length of zero the second correct - * so I skip all entries with length 0 */ - if (parse.funce.type == CISTPL_FUNCE_LAN_NODE_ID - && ((cistpl_lan_node_id_t *)parse.funce.data)->nb) - break; + if (parse.funce.type == CISTPL_FUNCE_LAN_NODE_ID && + ((cistpl_lan_node_id_t *)parse.funce.data)->nb) + break; } if (err) { /* not found: try to get the node-id from tuple 0x89 */ tuple.DesiredTuple = 0x89; /* data layout looks like tuple 0x22 */ @@ -852,8 +852,8 @@ xirc2ps_config(struct pcmcia_device * link) tuple.DesiredTuple = CISTPL_FUNCE; for (err = first_tuple(link, &tuple, &parse); !err; err = next_tuple(link, &tuple, &parse)) { - if (parse.funce.type == 0x02 && parse.funce.data[0] == 1 - && parse.funce.data[1] == 6 && tuple.TupleDataLen == 13) { + if (parse.funce.type == 0x02 && parse.funce.data[0] == 1 && + parse.funce.data[1] == 6 && tuple.TupleDataLen == 13) { buf[1] = 4; memcpy(&parse, buf+1, 8); break; diff --git a/drivers/net/pcnet32.c b/drivers/net/pcnet32.c index 076f23a10517..dcc67a35e8f2 100644 --- a/drivers/net/pcnet32.c +++ b/drivers/net/pcnet32.c @@ -1515,8 +1515,8 @@ static void __devinit pcnet32_probe_vlbus(unsigned int *pcnet32_portlist) if (request_region (ioaddr, PCNET32_TOTAL_SIZE, "pcnet32_probe_vlbus")) { /* check if there is really a pcnet chip on that ioaddr */ - if ((inb(ioaddr + 14) == 0x57) - && (inb(ioaddr + 15) == 0x57)) { + if ((inb(ioaddr + 14) == 0x57) && + (inb(ioaddr + 15) == 0x57)) { pcnet32_probe1(ioaddr, 0, NULL); } else { release_region(ioaddr, PCNET32_TOTAL_SIZE); @@ -1610,8 +1610,8 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) a = &pcnet32_wio; } else { pcnet32_dwio_reset(ioaddr); - if (pcnet32_dwio_read_csr(ioaddr, 0) == 4 - && pcnet32_dwio_check(ioaddr)) { + if (pcnet32_dwio_read_csr(ioaddr, 0) == 4 && + pcnet32_dwio_check(ioaddr)) { a = &pcnet32_dwio; } else { if (pcnet32_debug & NETIF_MSG_PROBE) @@ -1750,8 +1750,8 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) for (i = 0; i < 6; i++) promaddr[i] = inb(ioaddr + i); - if (memcmp(promaddr, dev->dev_addr, 6) - || !is_valid_ether_addr(dev->dev_addr)) { + if (memcmp(promaddr, dev->dev_addr, 6) || + !is_valid_ether_addr(dev->dev_addr)) { if (is_valid_ether_addr(promaddr)) { if (pcnet32_debug & NETIF_MSG_PROBE) { printk(" warning: CSR address invalid,\n"); @@ -1840,8 +1840,8 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) lp->mii = mii; lp->chip_version = chip_version; lp->msg_enable = pcnet32_debug; - if ((cards_found >= MAX_UNITS) - || (options[cards_found] >= sizeof(options_mapping))) + if ((cards_found >= MAX_UNITS) || + (options[cards_found] >= sizeof(options_mapping))) lp->options = PCNET32_PORT_ASEL; else lp->options = options_mapping[options[cards_found]]; @@ -1866,8 +1866,8 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) goto err_free_ring; } /* detect special T1/E1 WAN card by checking for MAC address */ - if (dev->dev_addr[0] == 0x00 && dev->dev_addr[1] == 0xe0 - && dev->dev_addr[2] == 0x75) + if (dev->dev_addr[0] == 0x00 && dev->dev_addr[1] == 0xe0 && + dev->dev_addr[2] == 0x75) lp->options = PCNET32_PORT_FD | PCNET32_PORT_GPSI; lp->init_block->mode = cpu_to_le16(0x0003); /* Disable Rx and Tx. */ diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 6b71b0034060..b0e9f9c51721 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -254,12 +254,12 @@ int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd) if (cmd->autoneg == AUTONEG_ENABLE && cmd->advertising == 0) return -EINVAL; - if (cmd->autoneg == AUTONEG_DISABLE - && ((cmd->speed != SPEED_1000 - && cmd->speed != SPEED_100 - && cmd->speed != SPEED_10) - || (cmd->duplex != DUPLEX_HALF - && cmd->duplex != DUPLEX_FULL))) + if (cmd->autoneg == AUTONEG_DISABLE && + ((cmd->speed != SPEED_1000 && + cmd->speed != SPEED_100 && + cmd->speed != SPEED_10) || + (cmd->duplex != DUPLEX_HALF && + cmd->duplex != DUPLEX_FULL))) return -EINVAL; phydev->autoneg = cmd->autoneg; @@ -353,9 +353,9 @@ int phy_mii_ioctl(struct phy_device *phydev, phy_write(phydev, mii_data->reg_num, val); - if (mii_data->reg_num == MII_BMCR - && val & BMCR_RESET - && phydev->drv->config_init) { + if (mii_data->reg_num == MII_BMCR && + val & BMCR_RESET && + phydev->drv->config_init) { phy_scan_fixups(phydev); phydev->drv->config_init(phydev); } diff --git a/drivers/net/plip.c b/drivers/net/plip.c index 00487f569cfd..3327e9fc7b51 100644 --- a/drivers/net/plip.c +++ b/drivers/net/plip.c @@ -372,8 +372,8 @@ plip_bh(struct work_struct *work) nl->is_deferred = 0; f = connection_state_table[nl->connection]; - if ((r = (*f)(nl->dev, nl, snd, rcv)) != OK - && (r = plip_bh_timeout_error(nl->dev, nl, snd, rcv, r)) != OK) { + if ((r = (*f)(nl->dev, nl, snd, rcv)) != OK && + (r = plip_bh_timeout_error(nl->dev, nl, snd, rcv, r)) != OK) { nl->is_deferred = 1; schedule_delayed_work(&nl->deferred, 1); } @@ -416,9 +416,8 @@ plip_bh_timeout_error(struct net_device *dev, struct net_local *nl, if (error != ERROR) { /* Timeout */ nl->timeout_count++; - if ((error == HS_TIMEOUT - && nl->timeout_count <= 10) - || nl->timeout_count <= 3) { + if ((error == HS_TIMEOUT && nl->timeout_count <= 10) || + nl->timeout_count <= 3) { spin_unlock_irq(&nl->lock); /* Try again later */ return TIMEOUT; @@ -624,8 +623,8 @@ plip_receive_packet(struct net_device *dev, struct net_local *nl, if (plip_receive(nibble_timeout, dev, &rcv->nibble, &rcv->length.b.msb)) return TIMEOUT; - if (rcv->length.h > dev->mtu + dev->hard_header_len - || rcv->length.h < 8) { + if (rcv->length.h > dev->mtu + dev->hard_header_len || + rcv->length.h < 8) { printk(KERN_WARNING "%s: bogus packet size %d.\n", dev->name, rcv->length.h); return ERROR; } diff --git a/drivers/net/ppp_async.c b/drivers/net/ppp_async.c index c311fa6597f5..6a375ea4947d 100644 --- a/drivers/net/ppp_async.c +++ b/drivers/net/ppp_async.c @@ -558,8 +558,8 @@ ppp_async_encode(struct asyncppp *ap) * Start of a new packet - insert the leading FLAG * character if necessary. */ - if (islcp || flag_time == 0 - || time_after_eq(jiffies, ap->last_xmit + flag_time)) + if (islcp || flag_time == 0 || + time_after_eq(jiffies, ap->last_xmit + flag_time)) *buf++ = PPP_FLAG; ap->last_xmit = jiffies; fcs = PPP_INITFCS; @@ -696,8 +696,8 @@ ppp_async_push(struct asyncppp *ap) */ clear_bit(XMIT_BUSY, &ap->xmit_flags); /* any more work to do? if not, exit the loop */ - if (!(test_bit(XMIT_WAKEUP, &ap->xmit_flags) - || (!tty_stuffed && ap->tpkt))) + if (!(test_bit(XMIT_WAKEUP, &ap->xmit_flags) || + (!tty_stuffed && ap->tpkt))) break; /* more work to do, see if we can do it now */ if (test_and_set_bit(XMIT_BUSY, &ap->xmit_flags)) @@ -754,8 +754,8 @@ scan_ordinary(struct asyncppp *ap, const unsigned char *buf, int count) for (i = 0; i < count; ++i) { c = buf[i]; - if (c == PPP_ESCAPE || c == PPP_FLAG - || (c < 0x20 && (ap->raccm & (1 << c)) != 0)) + if (c == PPP_ESCAPE || c == PPP_FLAG || + (c < 0x20 && (ap->raccm & (1 << c)) != 0)) break; } return i; diff --git a/drivers/net/ppp_deflate.c b/drivers/net/ppp_deflate.c index 034c1c650bcb..695bc83e0cfd 100644 --- a/drivers/net/ppp_deflate.c +++ b/drivers/net/ppp_deflate.c @@ -111,11 +111,11 @@ static void *z_comp_alloc(unsigned char *options, int opt_len) struct ppp_deflate_state *state; int w_size; - if (opt_len != CILEN_DEFLATE - || (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) - || options[1] != CILEN_DEFLATE - || DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL - || options[3] != DEFLATE_CHK_SEQUENCE) + if (opt_len != CILEN_DEFLATE || + (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) || + options[1] != CILEN_DEFLATE || + DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL || + options[3] != DEFLATE_CHK_SEQUENCE) return NULL; w_size = DEFLATE_SIZE(options[2]); if (w_size < DEFLATE_MIN_SIZE || w_size > DEFLATE_MAX_SIZE) @@ -163,12 +163,12 @@ static int z_comp_init(void *arg, unsigned char *options, int opt_len, { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; - if (opt_len < CILEN_DEFLATE - || (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) - || options[1] != CILEN_DEFLATE - || DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL - || DEFLATE_SIZE(options[2]) != state->w_size - || options[3] != DEFLATE_CHK_SEQUENCE) + if (opt_len < CILEN_DEFLATE || + (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) || + options[1] != CILEN_DEFLATE || + DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL || + DEFLATE_SIZE(options[2]) != state->w_size || + options[3] != DEFLATE_CHK_SEQUENCE) return 0; state->seqno = 0; @@ -330,11 +330,11 @@ static void *z_decomp_alloc(unsigned char *options, int opt_len) struct ppp_deflate_state *state; int w_size; - if (opt_len != CILEN_DEFLATE - || (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) - || options[1] != CILEN_DEFLATE - || DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL - || options[3] != DEFLATE_CHK_SEQUENCE) + if (opt_len != CILEN_DEFLATE || + (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) || + options[1] != CILEN_DEFLATE || + DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL || + options[3] != DEFLATE_CHK_SEQUENCE) return NULL; w_size = DEFLATE_SIZE(options[2]); if (w_size < DEFLATE_MIN_SIZE || w_size > DEFLATE_MAX_SIZE) @@ -381,12 +381,12 @@ static int z_decomp_init(void *arg, unsigned char *options, int opt_len, { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; - if (opt_len < CILEN_DEFLATE - || (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) - || options[1] != CILEN_DEFLATE - || DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL - || DEFLATE_SIZE(options[2]) != state->w_size - || options[3] != DEFLATE_CHK_SEQUENCE) + if (opt_len < CILEN_DEFLATE || + (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) || + options[1] != CILEN_DEFLATE || + DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL || + DEFLATE_SIZE(options[2]) != state->w_size || + options[3] != DEFLATE_CHK_SEQUENCE) return 0; state->seqno = 0; diff --git a/drivers/net/ppp_generic.c b/drivers/net/ppp_generic.c index 0a56a778af0a..2282e729edbe 100644 --- a/drivers/net/ppp_generic.c +++ b/drivers/net/ppp_generic.c @@ -425,8 +425,8 @@ static ssize_t ppp_read(struct file *file, char __user *buf, * network traffic (demand mode). */ struct ppp *ppp = PF_TO_PPP(pf); - if (ppp->n_channels == 0 - && (ppp->flags & SC_LOOP_TRAFFIC) == 0) + if (ppp->n_channels == 0 && + (ppp->flags & SC_LOOP_TRAFFIC) == 0) break; } ret = -EAGAIN; @@ -511,8 +511,8 @@ static unsigned int ppp_poll(struct file *file, poll_table *wait) else if (pf->kind == INTERFACE) { /* see comment in ppp_read */ struct ppp *ppp = PF_TO_PPP(pf); - if (ppp->n_channels == 0 - && (ppp->flags & SC_LOOP_TRAFFIC) == 0) + if (ppp->n_channels == 0 && + (ppp->flags & SC_LOOP_TRAFFIC) == 0) mask |= POLLIN | POLLRDNORM; } @@ -864,12 +864,7 @@ static const struct file_operations ppp_device_fops = { static __net_init int ppp_init_net(struct net *net) { - struct ppp_net *pn; - int err; - - pn = kzalloc(sizeof(*pn), GFP_KERNEL); - if (!pn) - return -ENOMEM; + struct ppp_net *pn = net_generic(net, ppp_net_id); idr_init(&pn->units_idr); mutex_init(&pn->all_ppp_mutex); @@ -879,32 +874,21 @@ static __net_init int ppp_init_net(struct net *net) spin_lock_init(&pn->all_channels_lock); - err = net_assign_generic(net, ppp_net_id, pn); - if (err) { - kfree(pn); - return err; - } - return 0; } static __net_exit void ppp_exit_net(struct net *net) { - struct ppp_net *pn; + struct ppp_net *pn = net_generic(net, ppp_net_id); - pn = net_generic(net, ppp_net_id); idr_destroy(&pn->units_idr); - /* - * if someone has cached our net then - * further net_generic call will return NULL - */ - net_assign_generic(net, ppp_net_id, NULL); - kfree(pn); } static struct pernet_operations ppp_net_ops = { .init = ppp_init_net, .exit = ppp_exit_net, + .id = &ppp_net_id, + .size = sizeof(struct ppp_net), }; #define PPP_MAJOR 108 @@ -917,7 +901,7 @@ static int __init ppp_init(void) printk(KERN_INFO "PPP generic driver version " PPP_VERSION "\n"); - err = register_pernet_gen_device(&ppp_net_id, &ppp_net_ops); + err = register_pernet_device(&ppp_net_ops); if (err) { printk(KERN_ERR "failed to register PPP pernet device (%d)\n", err); goto out; @@ -943,7 +927,7 @@ static int __init ppp_init(void) out_chrdev: unregister_chrdev(PPP_MAJOR, "ppp"); out_net: - unregister_pernet_gen_device(ppp_net_id, &ppp_net_ops); + unregister_pernet_device(&ppp_net_ops); out: return err; } @@ -1073,8 +1057,8 @@ ppp_xmit_process(struct ppp *ppp) ppp_xmit_lock(ppp); if (!ppp->closing) { ppp_push(ppp); - while (!ppp->xmit_pending - && (skb = skb_dequeue(&ppp->file.xq))) + while (!ppp->xmit_pending && + (skb = skb_dequeue(&ppp->file.xq))) ppp_send_frame(ppp, skb); /* If there's no work left to do, tell the core net code that we can accept some more. */ @@ -1153,18 +1137,18 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) /* the filter instructions are constructed assuming a four-byte PPP header on each packet */ *skb_push(skb, 2) = 1; - if (ppp->pass_filter - && sk_run_filter(skb, ppp->pass_filter, - ppp->pass_len) == 0) { + if (ppp->pass_filter && + sk_run_filter(skb, ppp->pass_filter, + ppp->pass_len) == 0) { if (ppp->debug & 1) printk(KERN_DEBUG "PPP: outbound frame not passed\n"); kfree_skb(skb); return; } /* if this packet passes the active filter, record the time */ - if (!(ppp->active_filter - && sk_run_filter(skb, ppp->active_filter, - ppp->active_len) == 0)) + if (!(ppp->active_filter && + sk_run_filter(skb, ppp->active_filter, + ppp->active_len) == 0)) ppp->last_xmit = jiffies; skb_pull(skb, 2); #else @@ -1218,8 +1202,8 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) } /* try to do packet compression */ - if ((ppp->xstate & SC_COMP_RUN) && ppp->xc_state - && proto != PPP_LCP && proto != PPP_CCP) { + if ((ppp->xstate & SC_COMP_RUN) && ppp->xc_state && + proto != PPP_LCP && proto != PPP_CCP) { if (!(ppp->flags & SC_CCP_UP) && (ppp->flags & SC_MUST_COMP)) { if (net_ratelimit()) printk(KERN_ERR "ppp: compression required but down - pkt dropped.\n"); @@ -1593,8 +1577,8 @@ ppp_input(struct ppp_channel *chan, struct sk_buff *skb) /* put it on the channel queue */ skb_queue_tail(&pch->file.rq, skb); /* drop old frames if queue too long */ - while (pch->file.rq.qlen > PPP_MAX_RQLEN - && (skb = skb_dequeue(&pch->file.rq))) + while (pch->file.rq.qlen > PPP_MAX_RQLEN && + (skb = skb_dequeue(&pch->file.rq))) kfree_skb(skb); wake_up_interruptible(&pch->file.rwait); } else { @@ -1670,8 +1654,8 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) * Note that some decompressors need to see uncompressed frames * that come in as well as compressed frames. */ - if (ppp->rc_state && (ppp->rstate & SC_DECOMP_RUN) - && (ppp->rstate & (SC_DC_FERROR | SC_DC_ERROR)) == 0) + if (ppp->rc_state && (ppp->rstate & SC_DECOMP_RUN) && + (ppp->rstate & (SC_DC_FERROR | SC_DC_ERROR)) == 0) skb = ppp_decompress_frame(ppp, skb); if (ppp->flags & SC_MUST_COMP && ppp->rstate & SC_DC_FERROR) @@ -1742,8 +1726,8 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) /* control or unknown frame - pass it to pppd */ skb_queue_tail(&ppp->file.rq, skb); /* limit queue length by dropping old frames */ - while (ppp->file.rq.qlen > PPP_MAX_RQLEN - && (skb = skb_dequeue(&ppp->file.rq))) + while (ppp->file.rq.qlen > PPP_MAX_RQLEN && + (skb = skb_dequeue(&ppp->file.rq))) kfree_skb(skb); /* wake up any process polling or blocking on read */ wake_up_interruptible(&ppp->file.rwait); @@ -1761,26 +1745,26 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) goto err; *skb_push(skb, 2) = 0; - if (ppp->pass_filter - && sk_run_filter(skb, ppp->pass_filter, - ppp->pass_len) == 0) { + if (ppp->pass_filter && + sk_run_filter(skb, ppp->pass_filter, + ppp->pass_len) == 0) { if (ppp->debug & 1) printk(KERN_DEBUG "PPP: inbound frame " "not passed\n"); kfree_skb(skb); return; } - if (!(ppp->active_filter - && sk_run_filter(skb, ppp->active_filter, - ppp->active_len) == 0)) + if (!(ppp->active_filter && + sk_run_filter(skb, ppp->active_filter, + ppp->active_len) == 0)) ppp->last_recv = jiffies; __skb_pull(skb, 2); } else #endif /* CONFIG_PPP_FILTER */ ppp->last_recv = jiffies; - if ((ppp->dev->flags & IFF_UP) == 0 - || ppp->npmode[npi] != NPMODE_PASS) { + if ((ppp->dev->flags & IFF_UP) == 0 || + ppp->npmode[npi] != NPMODE_PASS) { kfree_skb(skb); } else { /* chop off protocol */ @@ -2244,13 +2228,13 @@ ppp_set_compress(struct ppp *ppp, unsigned long arg) unsigned char ccp_option[CCP_MAX_OPTION_LENGTH]; err = -EFAULT; - if (copy_from_user(&data, (void __user *) arg, sizeof(data)) - || (data.length <= CCP_MAX_OPTION_LENGTH - && copy_from_user(ccp_option, (void __user *) data.ptr, data.length))) + if (copy_from_user(&data, (void __user *) arg, sizeof(data)) || + (data.length <= CCP_MAX_OPTION_LENGTH && + copy_from_user(ccp_option, (void __user *) data.ptr, data.length))) goto out; err = -EINVAL; - if (data.length > CCP_MAX_OPTION_LENGTH - || ccp_option[1] < 2 || ccp_option[1] > data.length) + if (data.length > CCP_MAX_OPTION_LENGTH || + ccp_option[1] < 2 || ccp_option[1] > data.length) goto out; cp = try_then_request_module( @@ -2835,7 +2819,7 @@ static void __exit ppp_cleanup(void) unregister_chrdev(PPP_MAJOR, "ppp"); device_destroy(ppp_class, MKDEV(PPP_MAJOR, 0)); class_destroy(ppp_class); - unregister_pernet_gen_device(ppp_net_id, &ppp_net_ops); + unregister_pernet_device(&ppp_net_ops); } /* diff --git a/drivers/net/ppp_mppe.c b/drivers/net/ppp_mppe.c index 88f03c9e9403..6d1a1b80cc3e 100644 --- a/drivers/net/ppp_mppe.c +++ b/drivers/net/ppp_mppe.c @@ -195,8 +195,8 @@ static void *mppe_alloc(unsigned char *options, int optlen) struct ppp_mppe_state *state; unsigned int digestsize; - if (optlen != CILEN_MPPE + sizeof(state->master_key) - || options[0] != CI_MPPE || options[1] != CILEN_MPPE) + if (optlen != CILEN_MPPE + sizeof(state->master_key) || + options[0] != CI_MPPE || options[1] != CILEN_MPPE) goto out; state = kzalloc(sizeof(*state), GFP_KERNEL); @@ -276,8 +276,8 @@ mppe_init(void *arg, unsigned char *options, int optlen, int unit, int debug, struct ppp_mppe_state *state = (struct ppp_mppe_state *) arg; unsigned char mppe_opts; - if (optlen != CILEN_MPPE - || options[0] != CI_MPPE || options[1] != CILEN_MPPE) + if (optlen != CILEN_MPPE || + options[0] != CI_MPPE || options[1] != CILEN_MPPE) return 0; MPPE_CI_TO_OPTS(&options[2], mppe_opts); diff --git a/drivers/net/ppp_synctty.c b/drivers/net/ppp_synctty.c index c908b08dc981..3a13cecae3e2 100644 --- a/drivers/net/ppp_synctty.c +++ b/drivers/net/ppp_synctty.c @@ -662,8 +662,8 @@ ppp_sync_push(struct syncppp *ap) } /* haven't made any progress */ spin_unlock_bh(&ap->xmit_lock); - if (!(test_bit(XMIT_WAKEUP, &ap->xmit_flags) - || (!tty_stuffed && ap->tpkt))) + if (!(test_bit(XMIT_WAKEUP, &ap->xmit_flags) || + (!tty_stuffed && ap->tpkt))) break; if (!spin_trylock_bh(&ap->xmit_lock)) break; diff --git a/drivers/net/pppoe.c b/drivers/net/pppoe.c index a1dcba255b06..cdd11ba100ea 100644 --- a/drivers/net/pppoe.c +++ b/drivers/net/pppoe.c @@ -323,8 +323,8 @@ static void pppoe_flush_dev(struct net_device *dev) write_unlock_bh(&pn->hash_lock); lock_sock(sk); - if (po->pppoe_dev == dev - && sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) { + if (po->pppoe_dev == dev && + sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) { pppox_unbind_sock(sk); sk->sk_state = PPPOX_ZOMBIE; sk->sk_state_change(sk); @@ -1139,59 +1139,37 @@ static struct pppox_proto pppoe_proto = { static __net_init int pppoe_init_net(struct net *net) { - struct pppoe_net *pn; + struct pppoe_net *pn = pppoe_pernet(net); struct proc_dir_entry *pde; - int err; - - pn = kzalloc(sizeof(*pn), GFP_KERNEL); - if (!pn) - return -ENOMEM; rwlock_init(&pn->hash_lock); - err = net_assign_generic(net, pppoe_net_id, pn); - if (err) - goto out; - pde = proc_net_fops_create(net, "pppoe", S_IRUGO, &pppoe_seq_fops); #ifdef CONFIG_PROC_FS - if (!pde) { - err = -ENOMEM; - goto out; - } + if (!pde) + return -ENOMEM; #endif return 0; - -out: - kfree(pn); - return err; } static __net_exit void pppoe_exit_net(struct net *net) { - struct pppoe_net *pn; - proc_net_remove(net, "pppoe"); - pn = net_generic(net, pppoe_net_id); - /* - * if someone has cached our net then - * further net_generic call will return NULL - */ - net_assign_generic(net, pppoe_net_id, NULL); - kfree(pn); } static struct pernet_operations pppoe_net_ops = { .init = pppoe_init_net, .exit = pppoe_exit_net, + .id = &pppoe_net_id, + .size = sizeof(struct pppoe_net), }; static int __init pppoe_init(void) { int err; - err = register_pernet_gen_device(&pppoe_net_id, &pppoe_net_ops); + err = register_pernet_device(&pppoe_net_ops); if (err) goto out; @@ -1212,7 +1190,7 @@ static int __init pppoe_init(void) out_unregister_pppoe_proto: proto_unregister(&pppoe_sk_proto); out_unregister_net_ops: - unregister_pernet_gen_device(pppoe_net_id, &pppoe_net_ops); + unregister_pernet_device(&pppoe_net_ops); out: return err; } @@ -1224,7 +1202,7 @@ static void __exit pppoe_exit(void) dev_remove_pack(&pppoes_ptype); unregister_pppox_proto(PX_PROTO_OE); proto_unregister(&pppoe_sk_proto); - unregister_pernet_gen_device(pppoe_net_id, &pppoe_net_ops); + unregister_pernet_device(&pppoe_net_ops); } module_init(pppoe_init); diff --git a/drivers/net/pppol2tp.c b/drivers/net/pppol2tp.c index c58b50f8ba3b..9fbb2eba9a06 100644 --- a/drivers/net/pppol2tp.c +++ b/drivers/net/pppol2tp.c @@ -2605,53 +2605,31 @@ static struct pppox_proto pppol2tp_proto = { static __net_init int pppol2tp_init_net(struct net *net) { - struct pppol2tp_net *pn; + struct pppol2tp_net *pn = pppol2tp_pernet(net); struct proc_dir_entry *pde; - int err; - - pn = kzalloc(sizeof(*pn), GFP_KERNEL); - if (!pn) - return -ENOMEM; INIT_LIST_HEAD(&pn->pppol2tp_tunnel_list); rwlock_init(&pn->pppol2tp_tunnel_list_lock); - err = net_assign_generic(net, pppol2tp_net_id, pn); - if (err) - goto out; - pde = proc_net_fops_create(net, "pppol2tp", S_IRUGO, &pppol2tp_proc_fops); #ifdef CONFIG_PROC_FS - if (!pde) { - err = -ENOMEM; - goto out; - } + if (!pde) + return -ENOMEM; #endif return 0; - -out: - kfree(pn); - return err; } static __net_exit void pppol2tp_exit_net(struct net *net) { - struct pppoe_net *pn; - proc_net_remove(net, "pppol2tp"); - pn = net_generic(net, pppol2tp_net_id); - /* - * if someone has cached our net then - * further net_generic call will return NULL - */ - net_assign_generic(net, pppol2tp_net_id, NULL); - kfree(pn); } static struct pernet_operations pppol2tp_net_ops = { .init = pppol2tp_init_net, .exit = pppol2tp_exit_net, + .id = &pppol2tp_net_id, + .size = sizeof(struct pppol2tp_net), }; static int __init pppol2tp_init(void) @@ -2665,7 +2643,7 @@ static int __init pppol2tp_init(void) if (err) goto out_unregister_pppol2tp_proto; - err = register_pernet_gen_device(&pppol2tp_net_id, &pppol2tp_net_ops); + err = register_pernet_device(&pppol2tp_net_ops); if (err) goto out_unregister_pppox_proto; @@ -2684,7 +2662,7 @@ out_unregister_pppol2tp_proto: static void __exit pppol2tp_exit(void) { unregister_pppox_proto(PX_PROTO_OL2TP); - unregister_pernet_gen_device(pppol2tp_net_id, &pppol2tp_net_ops); + unregister_pernet_device(&pppol2tp_net_ops); proto_unregister(&pppol2tp_sk_proto); } diff --git a/drivers/net/ps3_gelic_net.c b/drivers/net/ps3_gelic_net.c index b211613e9dbd..89c4948300a5 100644 --- a/drivers/net/ps3_gelic_net.c +++ b/drivers/net/ps3_gelic_net.c @@ -95,11 +95,11 @@ static void gelic_card_get_ether_port_status(struct gelic_card *card, lv1_net_control(bus_id(card), dev_id(card), GELIC_LV1_GET_ETH_PORT_STATUS, - GELIC_LV1_VLAN_TX_ETHERNET, 0, 0, + GELIC_LV1_VLAN_TX_ETHERNET_0, 0, 0, &card->ether_port_status, &v2); if (inform) { - ether_netdev = card->netdev[GELIC_PORT_ETHERNET]; + ether_netdev = card->netdev[GELIC_PORT_ETHERNET_0]; if (card->ether_port_status & GELIC_LV1_ETHER_LINK_UP) netif_carrier_on(ether_netdev); else @@ -107,6 +107,24 @@ static void gelic_card_get_ether_port_status(struct gelic_card *card, } } +static int gelic_card_set_link_mode(struct gelic_card *card, int mode) +{ + int status; + u64 v1, v2; + + status = lv1_net_control(bus_id(card), dev_id(card), + GELIC_LV1_SET_NEGOTIATION_MODE, + GELIC_LV1_PHY_ETHERNET_0, mode, 0, &v1, &v2); + if (status) { + pr_info("%s: failed setting negotiation mode %d\n", __func__, + status); + return -EBUSY; + } + + card->link_mode = mode; + return 0; +} + void gelic_card_up(struct gelic_card *card) { pr_debug("%s: called\n", __func__); @@ -451,14 +469,14 @@ static void gelic_descr_release_tx(struct gelic_card *card, static void gelic_card_stop_queues(struct gelic_card *card) { - netif_stop_queue(card->netdev[GELIC_PORT_ETHERNET]); + netif_stop_queue(card->netdev[GELIC_PORT_ETHERNET_0]); if (card->netdev[GELIC_PORT_WIRELESS]) netif_stop_queue(card->netdev[GELIC_PORT_WIRELESS]); } static void gelic_card_wake_queues(struct gelic_card *card) { - netif_wake_queue(card->netdev[GELIC_PORT_ETHERNET]); + netif_wake_queue(card->netdev[GELIC_PORT_ETHERNET_0]); if (card->netdev[GELIC_PORT_WIRELESS]) netif_wake_queue(card->netdev[GELIC_PORT_WIRELESS]); @@ -999,7 +1017,7 @@ static int gelic_card_decode_one_descr(struct gelic_card *card) goto refill; } } else - netdev = card->netdev[GELIC_PORT_ETHERNET]; + netdev = card->netdev[GELIC_PORT_ETHERNET_0]; if ((status == GELIC_DESCR_DMA_RESPONSE_ERROR) || (status == GELIC_DESCR_DMA_PROTECTION_ERROR) || @@ -1244,14 +1262,58 @@ static int gelic_ether_get_settings(struct net_device *netdev, cmd->supported = SUPPORTED_TP | SUPPORTED_Autoneg | SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full | SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full | - SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full; + SUPPORTED_1000baseT_Full; cmd->advertising = cmd->supported; - cmd->autoneg = AUTONEG_ENABLE; /* always enabled */ + if (card->link_mode & GELIC_LV1_ETHER_AUTO_NEG) { + cmd->autoneg = AUTONEG_ENABLE; + } else { + cmd->autoneg = AUTONEG_DISABLE; + cmd->advertising &= ~ADVERTISED_Autoneg; + } cmd->port = PORT_TP; return 0; } +static int gelic_ether_set_settings(struct net_device *netdev, + struct ethtool_cmd *cmd) +{ + struct gelic_card *card = netdev_card(netdev); + u64 mode; + int ret; + + if (cmd->autoneg == AUTONEG_ENABLE) { + mode = GELIC_LV1_ETHER_AUTO_NEG; + } else { + switch (cmd->speed) { + case SPEED_10: + mode = GELIC_LV1_ETHER_SPEED_10; + break; + case SPEED_100: + mode = GELIC_LV1_ETHER_SPEED_100; + break; + case SPEED_1000: + mode = GELIC_LV1_ETHER_SPEED_1000; + break; + default: + return -EINVAL; + } + if (cmd->duplex == DUPLEX_FULL) + mode |= GELIC_LV1_ETHER_FULL_DUPLEX; + else if (cmd->speed == SPEED_1000) { + pr_info("1000 half duplex is not supported.\n"); + return -EINVAL; + } + } + + ret = gelic_card_set_link_mode(card, mode); + + if (ret) + return ret; + + return 0; +} + u32 gelic_net_get_rx_csum(struct net_device *netdev) { struct gelic_card *card = netdev_card(netdev); @@ -1349,6 +1411,7 @@ done: static const struct ethtool_ops gelic_ether_ethtool_ops = { .get_drvinfo = gelic_net_get_drvinfo, .get_settings = gelic_ether_get_settings, + .set_settings = gelic_ether_set_settings, .get_link = ethtool_op_get_link, .get_tx_csum = ethtool_op_get_tx_csum, .set_tx_csum = ethtool_op_set_tx_csum, @@ -1369,7 +1432,7 @@ static void gelic_net_tx_timeout_task(struct work_struct *work) { struct gelic_card *card = container_of(work, struct gelic_card, tx_timeout_task); - struct net_device *netdev = card->netdev[GELIC_PORT_ETHERNET]; + struct net_device *netdev = card->netdev[GELIC_PORT_ETHERNET_0]; dev_info(ctodev(card), "%s:Timed out. Restarting... \n", __func__); @@ -1531,10 +1594,10 @@ static struct gelic_card * __devinit gelic_alloc_card_net(struct net_device **ne /* gelic_port */ port->netdev = *netdev; port->card = card; - port->type = GELIC_PORT_ETHERNET; + port->type = GELIC_PORT_ETHERNET_0; /* gelic_card */ - card->netdev[GELIC_PORT_ETHERNET] = *netdev; + card->netdev[GELIC_PORT_ETHERNET_0] = *netdev; INIT_WORK(&card->tx_timeout_task, gelic_net_tx_timeout_task); init_waitqueue_head(&card->waitq); @@ -1554,9 +1617,9 @@ static void __devinit gelic_card_get_vlan_info(struct gelic_card *card) int tx; int rx; } vlan_id_ix[2] = { - [GELIC_PORT_ETHERNET] = { - .tx = GELIC_LV1_VLAN_TX_ETHERNET, - .rx = GELIC_LV1_VLAN_RX_ETHERNET + [GELIC_PORT_ETHERNET_0] = { + .tx = GELIC_LV1_VLAN_TX_ETHERNET_0, + .rx = GELIC_LV1_VLAN_RX_ETHERNET_0 }, [GELIC_PORT_WIRELESS] = { .tx = GELIC_LV1_VLAN_TX_WIRELESS, @@ -1601,7 +1664,7 @@ static void __devinit gelic_card_get_vlan_info(struct gelic_card *card) i, card->vlan[i].tx, card->vlan[i].rx); } - if (card->vlan[GELIC_PORT_ETHERNET].tx) { + if (card->vlan[GELIC_PORT_ETHERNET_0].tx) { BUG_ON(!card->vlan[GELIC_PORT_WIRELESS].tx); card->vlan_required = 1; } else @@ -1657,6 +1720,8 @@ static int __devinit ps3_gelic_driver_probe(struct ps3_system_bus_device *dev) /* get internal vlan info */ gelic_card_get_vlan_info(card); + card->link_mode = GELIC_LV1_ETHER_AUTO_NEG; + /* setup interrupt */ result = lv1_net_set_interrupt_status_indicator(bus_id(card), dev_id(card), @@ -1773,6 +1838,9 @@ static int ps3_gelic_driver_remove(struct ps3_system_bus_device *dev) struct net_device *netdev0; pr_debug("%s: called\n", __func__); + /* set auto-negotiation */ + gelic_card_set_link_mode(card, GELIC_LV1_ETHER_AUTO_NEG); + #ifdef CONFIG_GELIC_WIRELESS gelic_wl_driver_remove(card); #endif @@ -1790,7 +1858,7 @@ static int ps3_gelic_driver_remove(struct ps3_system_bus_device *dev) gelic_card_free_chain(card, card->tx_top); gelic_card_free_chain(card, card->rx_top); - netdev0 = card->netdev[GELIC_PORT_ETHERNET]; + netdev0 = card->netdev[GELIC_PORT_ETHERNET_0]; /* disconnect event port */ free_irq(card->irq, card); netdev0->irq = NO_IRQ; diff --git a/drivers/net/ps3_gelic_net.h b/drivers/net/ps3_gelic_net.h index 8b413868bbe2..32521ae5e824 100644 --- a/drivers/net/ps3_gelic_net.h +++ b/drivers/net/ps3_gelic_net.h @@ -186,7 +186,7 @@ enum gelic_lv1_net_control_code { GELIC_LV1_GET_CHANNEL = 6, GELIC_LV1_POST_WLAN_CMD = 9, GELIC_LV1_GET_WLAN_CMD_RESULT = 10, - GELIC_LV1_GET_WLAN_EVENT = 11 + GELIC_LV1_GET_WLAN_EVENT = 11, }; /* for GELIC_LV1_SET_WOL */ @@ -217,24 +217,29 @@ enum gelic_lv1_ether_port_status { GELIC_LV1_ETHER_SPEED_10 = 0x0000000000000010L, GELIC_LV1_ETHER_SPEED_100 = 0x0000000000000020L, GELIC_LV1_ETHER_SPEED_1000 = 0x0000000000000040L, - GELIC_LV1_ETHER_SPEED_MASK = 0x0000000000000070L + GELIC_LV1_ETHER_SPEED_MASK = 0x0000000000000070L, }; enum gelic_lv1_vlan_index { /* for outgoing packets */ - GELIC_LV1_VLAN_TX_ETHERNET = 0x0000000000000002L, + GELIC_LV1_VLAN_TX_ETHERNET_0 = 0x0000000000000002L, GELIC_LV1_VLAN_TX_WIRELESS = 0x0000000000000003L, + /* for incoming packets */ - GELIC_LV1_VLAN_RX_ETHERNET = 0x0000000000000012L, - GELIC_LV1_VLAN_RX_WIRELESS = 0x0000000000000013L + GELIC_LV1_VLAN_RX_ETHERNET_0 = 0x0000000000000012L, + GELIC_LV1_VLAN_RX_WIRELESS = 0x0000000000000013L, +}; + +enum gelic_lv1_phy { + GELIC_LV1_PHY_ETHERNET_0 = 0x0000000000000002L, }; /* size of hardware part of gelic descriptor */ #define GELIC_DESCR_SIZE (32) enum gelic_port_type { - GELIC_PORT_ETHERNET = 0, - GELIC_PORT_WIRELESS = 1, + GELIC_PORT_ETHERNET_0 = 0, + GELIC_PORT_WIRELESS = 1, GELIC_PORT_MAX }; @@ -302,6 +307,8 @@ struct gelic_card { atomic_t users; u64 ether_port_status; + int link_mode; + /* original address returned by kzalloc */ void *unalign; diff --git a/drivers/net/qla3xxx.c b/drivers/net/qla3xxx.c index 4c610511eb40..e3e6bc917c87 100644 --- a/drivers/net/qla3xxx.c +++ b/drivers/net/qla3xxx.c @@ -1969,8 +1969,8 @@ static void ql_update_lrg_bufq_prod_index(struct ql3_adapter *qdev) struct ql_rcv_buf_cb *lrg_buf_cb; struct ql3xxx_port_registers __iomem *port_regs = qdev->mem_map_registers; - if ((qdev->lrg_buf_free_count >= 8) - && (qdev->lrg_buf_release_cnt >= 16)) { + if ((qdev->lrg_buf_free_count >= 8) && + (qdev->lrg_buf_release_cnt >= 16)) { if (qdev->lrg_buf_skb_check) if (!ql_populate_free_queue(qdev)) @@ -1978,8 +1978,8 @@ static void ql_update_lrg_bufq_prod_index(struct ql3_adapter *qdev) lrg_buf_q_ele = qdev->lrg_buf_next_free; - while ((qdev->lrg_buf_release_cnt >= 16) - && (qdev->lrg_buf_free_count >= 8)) { + while ((qdev->lrg_buf_release_cnt >= 16) && + (qdev->lrg_buf_free_count >= 8)) { for (i = 0; i < 8; i++) { lrg_buf_cb = diff --git a/drivers/net/qlge/qlge_main.c b/drivers/net/qlge/qlge_main.c index 7692299e7826..707b391afa02 100644 --- a/drivers/net/qlge/qlge_main.c +++ b/drivers/net/qlge/qlge_main.c @@ -2347,8 +2347,8 @@ static int ql_alloc_tx_resources(struct ql_adapter *qdev, pci_alloc_consistent(qdev->pdev, tx_ring->wq_size, &tx_ring->wq_base_dma); - if ((tx_ring->wq_base == NULL) - || tx_ring->wq_base_dma & WQ_ADDR_ALIGN) { + if ((tx_ring->wq_base == NULL) || + tx_ring->wq_base_dma & WQ_ADDR_ALIGN) { QPRINTK(qdev, IFUP, ERR, "tx_ring alloc failed.\n"); return -ENOMEM; } diff --git a/drivers/net/r6040.c b/drivers/net/r6040.c index 0f30ea4e97ec..f03e2e4a15a8 100644 --- a/drivers/net/r6040.c +++ b/drivers/net/r6040.c @@ -958,8 +958,7 @@ static void r6040_multicast_list(struct net_device *dev) } /* Too many multicast addresses * accept all traffic */ - else if ((dev->mc_count > MCAST_MAX) - || (dev->flags & IFF_ALLMULTI)) + else if ((dev->mc_count > MCAST_MAX) || (dev->flags & IFF_ALLMULTI)) reg |= 0x0020; iowrite16(reg, ioaddr); diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index 98f6c51b7608..acfc5a3aa490 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -794,7 +794,7 @@ static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) struct rtl8169_private *tp = netdev_priv(dev); void __iomem *ioaddr = tp->mmio_addr; unsigned int i; - static struct { + static const struct { u32 opt; u16 reg; u8 mask; @@ -1277,7 +1277,7 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp, * * (RTL_R32(TxConfig) & 0x700000) == 0x200000 ? 8101Eb : 8101Ec */ - const struct { + static const struct { u32 mask; u32 val; int mac_version; @@ -1351,7 +1351,7 @@ struct phy_reg { u16 val; }; -static void rtl_phy_write(void __iomem *ioaddr, struct phy_reg *regs, int len) +static void rtl_phy_write(void __iomem *ioaddr, const struct phy_reg *regs, int len) { while (len-- > 0) { mdio_write(ioaddr, regs->reg, regs->val); @@ -1361,7 +1361,7 @@ static void rtl_phy_write(void __iomem *ioaddr, struct phy_reg *regs, int len) static void rtl8169s_hw_phy_config(void __iomem *ioaddr) { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0001 }, { 0x06, 0x006e }, { 0x08, 0x0708 }, @@ -1428,7 +1428,7 @@ static void rtl8169s_hw_phy_config(void __iomem *ioaddr) static void rtl8169sb_hw_phy_config(void __iomem *ioaddr) { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0002 }, { 0x01, 0x90d0 }, { 0x1f, 0x0000 } @@ -1457,7 +1457,7 @@ static void rtl8169scd_hw_phy_config_quirk(struct rtl8169_private *tp, static void rtl8169scd_hw_phy_config(struct rtl8169_private *tp, void __iomem *ioaddr) { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0001 }, { 0x04, 0x0000 }, { 0x03, 0x00a1 }, @@ -1504,7 +1504,7 @@ static void rtl8169scd_hw_phy_config(struct rtl8169_private *tp, static void rtl8169sce_hw_phy_config(void __iomem *ioaddr) { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0001 }, { 0x04, 0x0000 }, { 0x03, 0x00a1 }, @@ -1557,7 +1557,7 @@ static void rtl8169sce_hw_phy_config(void __iomem *ioaddr) static void rtl8168bb_hw_phy_config(void __iomem *ioaddr) { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x10, 0xf41b }, { 0x1f, 0x0000 } }; @@ -1570,7 +1570,7 @@ static void rtl8168bb_hw_phy_config(void __iomem *ioaddr) static void rtl8168bef_hw_phy_config(void __iomem *ioaddr) { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0001 }, { 0x10, 0xf41b }, { 0x1f, 0x0000 } @@ -1581,7 +1581,7 @@ static void rtl8168bef_hw_phy_config(void __iomem *ioaddr) static void rtl8168cp_1_hw_phy_config(void __iomem *ioaddr) { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0000 }, { 0x1d, 0x0f00 }, { 0x1f, 0x0002 }, @@ -1594,7 +1594,7 @@ static void rtl8168cp_1_hw_phy_config(void __iomem *ioaddr) static void rtl8168cp_2_hw_phy_config(void __iomem *ioaddr) { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0001 }, { 0x1d, 0x3d98 }, { 0x1f, 0x0000 } @@ -1609,7 +1609,7 @@ static void rtl8168cp_2_hw_phy_config(void __iomem *ioaddr) static void rtl8168c_1_hw_phy_config(void __iomem *ioaddr) { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0001 }, { 0x12, 0x2300 }, { 0x1f, 0x0002 }, @@ -1638,7 +1638,7 @@ static void rtl8168c_1_hw_phy_config(void __iomem *ioaddr) static void rtl8168c_2_hw_phy_config(void __iomem *ioaddr) { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0001 }, { 0x12, 0x2300 }, { 0x03, 0x802f }, @@ -1666,7 +1666,7 @@ static void rtl8168c_2_hw_phy_config(void __iomem *ioaddr) static void rtl8168c_3_hw_phy_config(void __iomem *ioaddr) { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0001 }, { 0x12, 0x2300 }, { 0x1d, 0x3d98 }, @@ -1693,7 +1693,7 @@ static void rtl8168c_4_hw_phy_config(void __iomem *ioaddr) static void rtl8168d_1_hw_phy_config(void __iomem *ioaddr) { - static struct phy_reg phy_reg_init_0[] = { + static const struct phy_reg phy_reg_init_0[] = { { 0x1f, 0x0001 }, { 0x06, 0x4064 }, { 0x07, 0x2863 }, @@ -1712,14 +1712,14 @@ static void rtl8168d_1_hw_phy_config(void __iomem *ioaddr) { 0x1a, 0x05ad }, { 0x14, 0x94c0 } }; - static struct phy_reg phy_reg_init_1[] = { + static const struct phy_reg phy_reg_init_1[] = { { 0x1f, 0x0002 }, { 0x06, 0x5561 }, { 0x1f, 0x0005 }, { 0x05, 0x8332 }, { 0x06, 0x5561 } }; - static struct phy_reg phy_reg_init_2[] = { + static const struct phy_reg phy_reg_init_2[] = { { 0x1f, 0x0005 }, { 0x05, 0xffc2 }, { 0x1f, 0x0005 }, @@ -2084,7 +2084,7 @@ static void rtl8168d_1_hw_phy_config(void __iomem *ioaddr) rtl_phy_write(ioaddr, phy_reg_init_1, ARRAY_SIZE(phy_reg_init_1)); if (rtl8168d_efuse_read(ioaddr, 0x01) == 0xb1) { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0002 }, { 0x05, 0x669a }, { 0x1f, 0x0005 }, @@ -2099,7 +2099,7 @@ static void rtl8168d_1_hw_phy_config(void __iomem *ioaddr) val = mdio_read(ioaddr, 0x0d); if ((val & 0x00ff) != 0x006c) { - u32 set[] = { + static const u32 set[] = { 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c }; @@ -2112,7 +2112,7 @@ static void rtl8168d_1_hw_phy_config(void __iomem *ioaddr) mdio_write(ioaddr, 0x0d, val | set[i]); } } else { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0002 }, { 0x05, 0x6662 }, { 0x1f, 0x0005 }, @@ -2136,7 +2136,7 @@ static void rtl8168d_1_hw_phy_config(void __iomem *ioaddr) static void rtl8168d_2_hw_phy_config(void __iomem *ioaddr) { - static struct phy_reg phy_reg_init_0[] = { + static const struct phy_reg phy_reg_init_0[] = { { 0x1f, 0x0001 }, { 0x06, 0x4064 }, { 0x07, 0x2863 }, @@ -2161,7 +2161,7 @@ static void rtl8168d_2_hw_phy_config(void __iomem *ioaddr) { 0x05, 0x8332 }, { 0x06, 0x5561 } }; - static struct phy_reg phy_reg_init_1[] = { + static const struct phy_reg phy_reg_init_1[] = { { 0x1f, 0x0005 }, { 0x05, 0xffc2 }, { 0x1f, 0x0005 }, @@ -2477,7 +2477,7 @@ static void rtl8168d_2_hw_phy_config(void __iomem *ioaddr) rtl_phy_write(ioaddr, phy_reg_init_0, ARRAY_SIZE(phy_reg_init_0)); if (rtl8168d_efuse_read(ioaddr, 0x01) == 0xb1) { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0002 }, { 0x05, 0x669a }, { 0x1f, 0x0005 }, @@ -2505,7 +2505,7 @@ static void rtl8168d_2_hw_phy_config(void __iomem *ioaddr) mdio_write(ioaddr, 0x0d, val | set[i]); } } else { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0002 }, { 0x05, 0x2642 }, { 0x1f, 0x0005 }, @@ -2531,7 +2531,7 @@ static void rtl8168d_2_hw_phy_config(void __iomem *ioaddr) static void rtl8168d_3_hw_phy_config(void __iomem *ioaddr) { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0002 }, { 0x10, 0x0008 }, { 0x0d, 0x006c }, @@ -2592,7 +2592,7 @@ static void rtl8168d_3_hw_phy_config(void __iomem *ioaddr) static void rtl8102e_hw_phy_config(void __iomem *ioaddr) { - struct phy_reg phy_reg_init[] = { + static const struct phy_reg phy_reg_init[] = { { 0x1f, 0x0003 }, { 0x08, 0x441d }, { 0x01, 0x9100 }, @@ -3235,6 +3235,10 @@ static void __devexit rtl8169_remove_one(struct pci_dev *pdev) flush_scheduled_work(); unregister_netdev(dev); + + /* restore original MAC address */ + rtl_rar_set(tp, dev->perm_addr); + rtl_disable_msi(pdev, tp); rtl8169_release_board(pdev, dev, tp->mmio_addr); pci_set_drvdata(pdev, NULL); @@ -3384,7 +3388,7 @@ static void rtl_set_rx_max_size(void __iomem *ioaddr, unsigned int rx_buf_sz) static void rtl8169_set_magic_reg(void __iomem *ioaddr, unsigned mac_version) { - struct { + static const struct { u32 mac_version; u32 clk; u32 val; @@ -3508,7 +3512,7 @@ struct ephy_info { u16 bits; }; -static void rtl_ephy_init(void __iomem *ioaddr, struct ephy_info *e, int len) +static void rtl_ephy_init(void __iomem *ioaddr, const struct ephy_info *e, int len) { u16 w; @@ -3579,7 +3583,7 @@ static void __rtl_hw_start_8168cp(void __iomem *ioaddr, struct pci_dev *pdev) static void rtl_hw_start_8168cp_1(void __iomem *ioaddr, struct pci_dev *pdev) { - static struct ephy_info e_info_8168cp[] = { + static const struct ephy_info e_info_8168cp[] = { { 0x01, 0, 0x0001 }, { 0x02, 0x0800, 0x1000 }, { 0x03, 0, 0x0042 }, @@ -3623,7 +3627,7 @@ static void rtl_hw_start_8168cp_3(void __iomem *ioaddr, struct pci_dev *pdev) static void rtl_hw_start_8168c_1(void __iomem *ioaddr, struct pci_dev *pdev) { - static struct ephy_info e_info_8168c_1[] = { + static const struct ephy_info e_info_8168c_1[] = { { 0x02, 0x0800, 0x1000 }, { 0x03, 0, 0x0002 }, { 0x06, 0x0080, 0x0000 } @@ -3640,7 +3644,7 @@ static void rtl_hw_start_8168c_1(void __iomem *ioaddr, struct pci_dev *pdev) static void rtl_hw_start_8168c_2(void __iomem *ioaddr, struct pci_dev *pdev) { - static struct ephy_info e_info_8168c_2[] = { + static const struct ephy_info e_info_8168c_2[] = { { 0x01, 0, 0x0001 }, { 0x03, 0x0400, 0x0220 } }; @@ -3783,7 +3787,7 @@ static void rtl_hw_start_8168(struct net_device *dev) static void rtl_hw_start_8102e_1(void __iomem *ioaddr, struct pci_dev *pdev) { - static struct ephy_info e_info_8102e_1[] = { + static const struct ephy_info e_info_8102e_1[] = { { 0x01, 0, 0x6e65 }, { 0x02, 0, 0x091f }, { 0x03, 0, 0xc2f9 }, @@ -4759,8 +4763,8 @@ static void rtl_set_rx_mode(struct net_device *dev) AcceptBroadcast | AcceptMulticast | AcceptMyPhys | AcceptAllPhys; mc_filter[1] = mc_filter[0] = 0xffffffff; - } else if ((dev->mc_count > multicast_filter_limit) - || (dev->flags & IFF_ALLMULTI)) { + } else if ((dev->mc_count > multicast_filter_limit) || + (dev->flags & IFF_ALLMULTI)) { /* Too many to filter perfectly -- accept all multicasts. */ rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0xffffffff; @@ -4880,6 +4884,9 @@ static void rtl_shutdown(struct pci_dev *pdev) rtl8169_net_suspend(dev); + /* restore original MAC address */ + rtl_rar_set(tp, dev->perm_addr); + spin_lock_irq(&tp->lock); rtl8169_asic_down(ioaddr); diff --git a/drivers/net/s6gmac.c b/drivers/net/s6gmac.c index d81706e91aa7..45f26344b368 100644 --- a/drivers/net/s6gmac.c +++ b/drivers/net/s6gmac.c @@ -373,9 +373,9 @@ struct s6gmac { static void s6gmac_rx_fillfifo(struct s6gmac *pd) { struct sk_buff *skb; - while ((((u8)(pd->rx_skb_i - pd->rx_skb_o)) < S6_NUM_RX_SKB) - && (!s6dmac_fifo_full(pd->rx_dma, pd->rx_chan)) - && (skb = dev_alloc_skb(S6_MAX_FRLEN + 2))) { + while ((((u8)(pd->rx_skb_i - pd->rx_skb_o)) < S6_NUM_RX_SKB) && + (!s6dmac_fifo_full(pd->rx_dma, pd->rx_chan)) && + (skb = dev_alloc_skb(S6_MAX_FRLEN + 2))) { pd->rx_skb[(pd->rx_skb_i++) % S6_NUM_RX_SKB] = skb; s6dmac_put_fifo_cache(pd->rx_dma, pd->rx_chan, pd->io, (u32)skb->data, S6_MAX_FRLEN); diff --git a/drivers/net/sc92031.c b/drivers/net/sc92031.c index b7e0eb40a8bd..e35050322f97 100644 --- a/drivers/net/sc92031.c +++ b/drivers/net/sc92031.c @@ -428,9 +428,9 @@ static void _sc92031_set_mar(struct net_device *dev) void __iomem *port_base = priv->port_base; u32 mar0 = 0, mar1 = 0; - if ((dev->flags & IFF_PROMISC) - || dev->mc_count > multicast_filter_limit - || (dev->flags & IFF_ALLMULTI)) + if ((dev->flags & IFF_PROMISC) || + dev->mc_count > multicast_filter_limit || + (dev->flags & IFF_ALLMULTI)) mar0 = mar1 = 0xffffffff; else if (dev->flags & IFF_MULTICAST) { struct dev_mc_list *mc_list; @@ -777,10 +777,10 @@ static void _sc92031_rx_tasklet(struct net_device *dev) rx_ring_offset = (rx_ring_offset + 4) % RX_BUF_LEN; - if (unlikely(rx_status == 0 - || rx_size > (MAX_ETH_FRAME_SIZE + 4) - || rx_size < 16 - || !(rx_status & RxStatesOK))) { + if (unlikely(rx_status == 0 || + rx_size > (MAX_ETH_FRAME_SIZE + 4) || + rx_size < 16 || + !(rx_status & RxStatesOK))) { _sc92031_rx_tasklet_error(dev, rx_status, rx_size); break; } diff --git a/drivers/net/sfc/Kconfig b/drivers/net/sfc/Kconfig index 260aafaac235..a65c98638398 100644 --- a/drivers/net/sfc/Kconfig +++ b/drivers/net/sfc/Kconfig @@ -1,5 +1,5 @@ config SFC - tristate "Solarflare Solarstorm SFC4000 support" + tristate "Solarflare Solarstorm SFC4000/SFC9000-family support" depends on PCI && INET select MDIO select CRC32 @@ -7,15 +7,16 @@ config SFC select I2C_ALGOBIT help This driver supports 10-gigabit Ethernet cards based on - the Solarflare Communications Solarstorm SFC4000 controller. + the Solarflare Communications Solarstorm SFC4000 and + SFC9000-family controllers. To compile this driver as a module, choose M here. The module will be called sfc. config SFC_MTD - bool "Solarflare Solarstorm SFC4000 flash MTD support" + bool "Solarflare Solarstorm SFC4000/SFC9000-family MTD support" depends on SFC && MTD && !(SFC=y && MTD=m) default y help - This exposes the on-board flash memory as an MTD device (e.g. - /dev/mtd1). This makes it possible to upload new boot code - to the NIC. + This exposes the on-board flash memory as MTD devices (e.g. + /dev/mtd1). This makes it possible to upload new firmware + to the NIC. diff --git a/drivers/net/sfc/Makefile b/drivers/net/sfc/Makefile index 7b52fe10d38f..1047b19c60a5 100644 --- a/drivers/net/sfc/Makefile +++ b/drivers/net/sfc/Makefile @@ -1,6 +1,7 @@ -sfc-y += efx.o falcon.o tx.o rx.o falcon_gmac.o \ - falcon_xmac.o selftest.o ethtool.o qt202x_phy.o \ - mdio_10g.o tenxpress.o falcon_boards.o +sfc-y += efx.o nic.o falcon.o siena.o tx.o rx.o \ + falcon_gmac.o falcon_xmac.o mcdi_mac.o \ + selftest.o ethtool.o qt202x_phy.o mdio_10g.o \ + tenxpress.o falcon_boards.o mcdi.o mcdi_phy.o sfc-$(CONFIG_SFC_MTD) += mtd.o obj-$(CONFIG_SFC) += sfc.o diff --git a/drivers/net/sfc/bitfield.h b/drivers/net/sfc/bitfield.h index 6ad909bba957..098ac2ad757d 100644 --- a/drivers/net/sfc/bitfield.h +++ b/drivers/net/sfc/bitfield.h @@ -1,7 +1,7 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards * Copyright 2005-2006 Fen Systems Ltd. - * Copyright 2006-2008 Solarflare Communications Inc. + * Copyright 2006-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -37,6 +37,8 @@ #define EFX_DWORD_2_WIDTH 32 #define EFX_DWORD_3_LBN 96 #define EFX_DWORD_3_WIDTH 32 +#define EFX_QWORD_0_LBN 0 +#define EFX_QWORD_0_WIDTH 64 /* Specified attribute (e.g. LBN) of the specified field */ #define EFX_VAL(field, attribute) field ## _ ## attribute diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c index 4787faaf30c1..f983e3b507cc 100644 --- a/drivers/net/sfc/efx.c +++ b/drivers/net/sfc/efx.c @@ -1,7 +1,7 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards * Copyright 2005-2006 Fen Systems Ltd. - * Copyright 2005-2008 Solarflare Communications Inc. + * Copyright 2005-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -23,7 +23,9 @@ #include "net_driver.h" #include "efx.h" #include "mdio_10g.h" -#include "falcon.h" +#include "nic.h" + +#include "mcdi.h" /************************************************************************** * @@ -36,15 +38,32 @@ const unsigned int efx_loopback_mode_max = LOOPBACK_MAX; const char *efx_loopback_mode_names[] = { [LOOPBACK_NONE] = "NONE", + [LOOPBACK_DATA] = "DATAPATH", [LOOPBACK_GMAC] = "GMAC", [LOOPBACK_XGMII] = "XGMII", [LOOPBACK_XGXS] = "XGXS", [LOOPBACK_XAUI] = "XAUI", + [LOOPBACK_GMII] = "GMII", + [LOOPBACK_SGMII] = "SGMII", + [LOOPBACK_XGBR] = "XGBR", + [LOOPBACK_XFI] = "XFI", + [LOOPBACK_XAUI_FAR] = "XAUI_FAR", + [LOOPBACK_GMII_FAR] = "GMII_FAR", + [LOOPBACK_SGMII_FAR] = "SGMII_FAR", + [LOOPBACK_XFI_FAR] = "XFI_FAR", [LOOPBACK_GPHY] = "GPHY", [LOOPBACK_PHYXS] = "PHYXS", [LOOPBACK_PCS] = "PCS", [LOOPBACK_PMAPMD] = "PMA/PMD", - [LOOPBACK_NETWORK] = "NETWORK", + [LOOPBACK_XPORT] = "XPORT", + [LOOPBACK_XGMII_WS] = "XGMII_WS", + [LOOPBACK_XAUI_WS] = "XAUI_WS", + [LOOPBACK_XAUI_WS_FAR] = "XAUI_WS_FAR", + [LOOPBACK_XAUI_WS_NEAR] = "XAUI_WS_NEAR", + [LOOPBACK_GMII_WS] = "GMII_WS", + [LOOPBACK_XFI_WS] = "XFI_WS", + [LOOPBACK_XFI_WS_FAR] = "XFI_WS_FAR", + [LOOPBACK_PHYXS_WS] = "PHYXS_WS", }; /* Interrupt mode names (see INT_MODE())) */ @@ -67,6 +86,7 @@ const char *efx_reset_type_names[] = { [RESET_TYPE_RX_DESC_FETCH] = "RX_DESC_FETCH", [RESET_TYPE_TX_DESC_FETCH] = "TX_DESC_FETCH", [RESET_TYPE_TX_SKIP] = "TX_SKIP", + [RESET_TYPE_MC_FAILURE] = "MC_FAILURE", }; #define EFX_MAX_MTU (9 * 1024) @@ -186,7 +206,8 @@ static void efx_fini_channels(struct efx_nic *efx); #define EFX_ASSERT_RESET_SERIALISED(efx) \ do { \ - if (efx->state == STATE_RUNNING) \ + if ((efx->state == STATE_RUNNING) || \ + (efx->state == STATE_DISABLED)) \ ASSERT_RTNL(); \ } while (0) @@ -212,7 +233,7 @@ static int efx_process_channel(struct efx_channel *channel, int rx_quota) !channel->enabled)) return 0; - rx_packets = falcon_process_eventq(channel, rx_quota); + rx_packets = efx_nic_process_eventq(channel, rx_quota); if (rx_packets == 0) return 0; @@ -244,7 +265,7 @@ static inline void efx_channel_processed(struct efx_channel *channel) channel->work_pending = false; smp_wmb(); - falcon_eventq_read_ack(channel); + efx_nic_eventq_read_ack(channel); } /* NAPI poll handler @@ -273,14 +294,14 @@ static int efx_poll(struct napi_struct *napi, int budget) irq_adapt_low_thresh)) { if (channel->irq_moderation > 1) { channel->irq_moderation -= 1; - falcon_set_int_moderation(channel); + efx->type->push_irq_moderation(channel); } } else if (unlikely(channel->irq_mod_score > irq_adapt_high_thresh)) { if (channel->irq_moderation < efx->irq_rx_moderation) { channel->irq_moderation += 1; - falcon_set_int_moderation(channel); + efx->type->push_irq_moderation(channel); } } channel->irq_count = 0; @@ -315,7 +336,7 @@ void efx_process_channel_now(struct efx_channel *channel) BUG_ON(!channel->enabled); /* Disable interrupts and wait for ISRs to complete */ - falcon_disable_interrupts(efx); + efx_nic_disable_interrupts(efx); if (efx->legacy_irq) synchronize_irq(efx->legacy_irq); if (channel->irq) @@ -332,7 +353,7 @@ void efx_process_channel_now(struct efx_channel *channel) efx_channel_processed(channel); napi_enable(&channel->napi_str); - falcon_enable_interrupts(efx); + efx_nic_enable_interrupts(efx); } /* Create event queue @@ -344,7 +365,7 @@ static int efx_probe_eventq(struct efx_channel *channel) { EFX_LOG(channel->efx, "chan %d create event queue\n", channel->channel); - return falcon_probe_eventq(channel); + return efx_nic_probe_eventq(channel); } /* Prepare channel's event queue */ @@ -354,21 +375,21 @@ static void efx_init_eventq(struct efx_channel *channel) channel->eventq_read_ptr = 0; - falcon_init_eventq(channel); + efx_nic_init_eventq(channel); } static void efx_fini_eventq(struct efx_channel *channel) { EFX_LOG(channel->efx, "chan %d fini event queue\n", channel->channel); - falcon_fini_eventq(channel); + efx_nic_fini_eventq(channel); } static void efx_remove_eventq(struct efx_channel *channel) { EFX_LOG(channel->efx, "chan %d remove event queue\n", channel->channel); - falcon_remove_eventq(channel); + efx_nic_remove_eventq(channel); } /************************************************************************** @@ -534,7 +555,7 @@ static void efx_fini_channels(struct efx_nic *efx) EFX_ASSERT_RESET_SERIALISED(efx); BUG_ON(efx->port_enabled); - rc = falcon_flush_queues(efx); + rc = efx_nic_flush_queues(efx); if (rc) EFX_ERR(efx, "failed to flush queues\n"); else @@ -582,7 +603,7 @@ void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue, int delay) * netif_carrier_on/off) of the link status, and also maintains the * link status's stop on the port's TX queue. */ -static void efx_link_status_changed(struct efx_nic *efx) +void efx_link_status_changed(struct efx_nic *efx) { struct efx_link_state *link_state = &efx->link_state; @@ -619,16 +640,49 @@ static void efx_link_status_changed(struct efx_nic *efx) } +void efx_link_set_advertising(struct efx_nic *efx, u32 advertising) +{ + efx->link_advertising = advertising; + if (advertising) { + if (advertising & ADVERTISED_Pause) + efx->wanted_fc |= (EFX_FC_TX | EFX_FC_RX); + else + efx->wanted_fc &= ~(EFX_FC_TX | EFX_FC_RX); + if (advertising & ADVERTISED_Asym_Pause) + efx->wanted_fc ^= EFX_FC_TX; + } +} + +void efx_link_set_wanted_fc(struct efx_nic *efx, enum efx_fc_type wanted_fc) +{ + efx->wanted_fc = wanted_fc; + if (efx->link_advertising) { + if (wanted_fc & EFX_FC_RX) + efx->link_advertising |= (ADVERTISED_Pause | + ADVERTISED_Asym_Pause); + else + efx->link_advertising &= ~(ADVERTISED_Pause | + ADVERTISED_Asym_Pause); + if (wanted_fc & EFX_FC_TX) + efx->link_advertising ^= ADVERTISED_Asym_Pause; + } +} + static void efx_fini_port(struct efx_nic *efx); -/* This call reinitialises the MAC to pick up new PHY settings. The - * caller must hold the mac_lock */ -void __efx_reconfigure_port(struct efx_nic *efx) +/* Push loopback/power/transmit disable settings to the PHY, and reconfigure + * the MAC appropriately. All other PHY configuration changes are pushed + * through phy_op->set_settings(), and pushed asynchronously to the MAC + * through efx_monitor(). + * + * Callers must hold the mac_lock + */ +int __efx_reconfigure_port(struct efx_nic *efx) { - WARN_ON(!mutex_is_locked(&efx->mac_lock)); + enum efx_phy_mode phy_mode; + int rc; - EFX_LOG(efx, "reconfiguring MAC from PHY settings on CPU %d\n", - raw_smp_processor_id()); + WARN_ON(!mutex_is_locked(&efx->mac_lock)); /* Serialise the promiscuous flag with efx_set_multicast_list. */ if (efx_dev_registered(efx)) { @@ -636,61 +690,48 @@ void __efx_reconfigure_port(struct efx_nic *efx) netif_addr_unlock_bh(efx->net_dev); } - falcon_deconfigure_mac_wrapper(efx); - - /* Reconfigure the PHY, disabling transmit in mac level loopback. */ + /* Disable PHY transmit in mac level loopbacks */ + phy_mode = efx->phy_mode; if (LOOPBACK_INTERNAL(efx)) efx->phy_mode |= PHY_MODE_TX_DISABLED; else efx->phy_mode &= ~PHY_MODE_TX_DISABLED; - efx->phy_op->reconfigure(efx); - if (falcon_switch_mac(efx)) - goto fail; - - efx->mac_op->reconfigure(efx); + rc = efx->type->reconfigure_port(efx); - /* Inform kernel of loss/gain of carrier */ - efx_link_status_changed(efx); - return; + if (rc) + efx->phy_mode = phy_mode; -fail: - EFX_ERR(efx, "failed to reconfigure MAC\n"); - efx->port_enabled = false; - efx_fini_port(efx); + return rc; } /* Reinitialise the MAC to pick up new PHY settings, even if the port is * disabled. */ -void efx_reconfigure_port(struct efx_nic *efx) +int efx_reconfigure_port(struct efx_nic *efx) { + int rc; + EFX_ASSERT_RESET_SERIALISED(efx); mutex_lock(&efx->mac_lock); - __efx_reconfigure_port(efx); + rc = __efx_reconfigure_port(efx); mutex_unlock(&efx->mac_lock); -} - -/* Asynchronous efx_reconfigure_port work item. To speed up efx_flush_all() - * we don't efx_reconfigure_port() if the port is disabled. Care is taken - * in efx_stop_all() and efx_start_port() to prevent PHY events being lost */ -static void efx_phy_work(struct work_struct *data) -{ - struct efx_nic *efx = container_of(data, struct efx_nic, phy_work); - mutex_lock(&efx->mac_lock); - if (efx->port_enabled) - __efx_reconfigure_port(efx); - mutex_unlock(&efx->mac_lock); + return rc; } +/* Asynchronous work item for changing MAC promiscuity and multicast + * hash. Avoid a drain/rx_ingress enable by reconfiguring the current + * MAC directly. */ static void efx_mac_work(struct work_struct *data) { struct efx_nic *efx = container_of(data, struct efx_nic, mac_work); mutex_lock(&efx->mac_lock); - if (efx->port_enabled) - efx->mac_op->irq(efx); + if (efx->port_enabled) { + efx->type->push_multicast_hash(efx); + efx->mac_op->reconfigure(efx); + } mutex_unlock(&efx->mac_lock); } @@ -700,8 +741,8 @@ static int efx_probe_port(struct efx_nic *efx) EFX_LOG(efx, "create port\n"); - /* Connect up MAC/PHY operations table and read MAC address */ - rc = falcon_probe_port(efx); + /* Connect up MAC/PHY operations table */ + rc = efx->type->probe_port(efx); if (rc) goto err; @@ -736,29 +777,33 @@ static int efx_init_port(struct efx_nic *efx) EFX_LOG(efx, "init port\n"); - rc = efx->phy_op->init(efx); - if (rc) - return rc; mutex_lock(&efx->mac_lock); - efx->phy_op->reconfigure(efx); - rc = falcon_switch_mac(efx); - mutex_unlock(&efx->mac_lock); + + rc = efx->phy_op->init(efx); if (rc) - goto fail; - efx->mac_op->reconfigure(efx); + goto fail1; efx->port_initialized = true; - efx_stats_enable(efx); + + /* Reconfigure the MAC before creating dma queues (required for + * Falcon/A1 where RX_INGR_EN/TX_DRAIN_EN isn't supported) */ + efx->mac_op->reconfigure(efx); + + /* Ensure the PHY advertises the correct flow control settings */ + rc = efx->phy_op->reconfigure(efx); + if (rc) + goto fail2; + + mutex_unlock(&efx->mac_lock); return 0; -fail: +fail2: efx->phy_op->fini(efx); +fail1: + mutex_unlock(&efx->mac_lock); return rc; } -/* Allow efx_reconfigure_port() to be scheduled, and close the window - * between efx_stop_port and efx_flush_all whereby a previously scheduled - * efx_phy_work()/efx_mac_work() may have been cancelled */ static void efx_start_port(struct efx_nic *efx) { EFX_LOG(efx, "start port\n"); @@ -766,15 +811,16 @@ static void efx_start_port(struct efx_nic *efx) mutex_lock(&efx->mac_lock); efx->port_enabled = true; - __efx_reconfigure_port(efx); - efx->mac_op->irq(efx); + + /* efx_mac_work() might have been scheduled after efx_stop_port(), + * and then cancelled by efx_flush_all() */ + efx->type->push_multicast_hash(efx); + efx->mac_op->reconfigure(efx); + mutex_unlock(&efx->mac_lock); } -/* Prevent efx_phy_work, efx_mac_work, and efx_monitor() from executing, - * and efx_set_multicast_list() from scheduling efx_phy_work. efx_phy_work - * and efx_mac_work may still be scheduled via NAPI processing until - * efx_flush_all() is called */ +/* Prevent efx_mac_work() and efx_monitor() from working */ static void efx_stop_port(struct efx_nic *efx) { EFX_LOG(efx, "stop port\n"); @@ -797,7 +843,6 @@ static void efx_fini_port(struct efx_nic *efx) if (!efx->port_initialized) return; - efx_stats_disable(efx); efx->phy_op->fini(efx); efx->port_initialized = false; @@ -809,7 +854,7 @@ static void efx_remove_port(struct efx_nic *efx) { EFX_LOG(efx, "destroying port\n"); - falcon_remove_port(efx); + efx->type->remove_port(efx); } /************************************************************************** @@ -1046,7 +1091,7 @@ static int efx_probe_nic(struct efx_nic *efx) EFX_LOG(efx, "creating NIC\n"); /* Carry out hardware-type specific initialisation */ - rc = falcon_probe_nic(efx); + rc = efx->type->probe(efx); if (rc) return rc; @@ -1067,7 +1112,7 @@ static void efx_remove_nic(struct efx_nic *efx) EFX_LOG(efx, "destroying NIC\n"); efx_remove_interrupts(efx); - falcon_remove_nic(efx); + efx->type->remove(efx); } /************************************************************************** @@ -1147,12 +1192,31 @@ static void efx_start_all(struct efx_nic *efx) efx_for_each_channel(channel, efx) efx_start_channel(channel); - falcon_enable_interrupts(efx); - - /* Start hardware monitor if we're in RUNNING */ - if (efx->state == STATE_RUNNING) + efx_nic_enable_interrupts(efx); + + /* Switch to event based MCDI completions after enabling interrupts. + * If a reset has been scheduled, then we need to stay in polled mode. + * Rather than serialising efx_mcdi_mode_event() [which sleeps] and + * reset_pending [modified from an atomic context], we instead guarantee + * that efx_mcdi_mode_poll() isn't reverted erroneously */ + efx_mcdi_mode_event(efx); + if (efx->reset_pending != RESET_TYPE_NONE) + efx_mcdi_mode_poll(efx); + + /* Start the hardware monitor if there is one. Otherwise (we're link + * event driven), we have to poll the PHY because after an event queue + * flush, we could have a missed a link state change */ + if (efx->type->monitor != NULL) { queue_delayed_work(efx->workqueue, &efx->monitor_work, efx_monitor_interval); + } else { + mutex_lock(&efx->mac_lock); + if (efx->phy_op->poll(efx)) + efx_link_status_changed(efx); + mutex_unlock(&efx->mac_lock); + } + + efx->type->start_stats(efx); } /* Flush all delayed work. Should only be called when no more delayed work @@ -1171,8 +1235,6 @@ static void efx_flush_all(struct efx_nic *efx) /* Stop scheduled port reconfigurations */ cancel_work_sync(&efx->mac_work); - cancel_work_sync(&efx->phy_work); - } /* Quiesce hardware and software without bringing the link down. @@ -1190,8 +1252,13 @@ static void efx_stop_all(struct efx_nic *efx) if (!efx->port_enabled) return; + efx->type->stop_stats(efx); + + /* Switch to MCDI polling on Siena before disabling interrupts */ + efx_mcdi_mode_poll(efx); + /* Disable interrupts and wait for ISR to complete */ - falcon_disable_interrupts(efx); + efx_nic_disable_interrupts(efx); if (efx->legacy_irq) synchronize_irq(efx->legacy_irq); efx_for_each_channel(channel, efx) { @@ -1208,15 +1275,9 @@ static void efx_stop_all(struct efx_nic *efx) * window to loose phy events */ efx_stop_port(efx); - /* Flush efx_phy_work, efx_mac_work, refill_workqueue, monitor_work */ + /* Flush efx_mac_work(), refill_workqueue, monitor_work */ efx_flush_all(efx); - /* Isolate the MAC from the TX and RX engines, so that queue - * flushes will complete in a timely fashion. */ - falcon_deconfigure_mac_wrapper(efx); - msleep(10); /* Let the Rx FIFO drain */ - falcon_drain_tx_fifo(efx); - /* Stop the kernel transmit interface late, so the watchdog * timer isn't ticking over the flush */ if (efx_dev_registered(efx)) { @@ -1236,19 +1297,6 @@ static void efx_remove_all(struct efx_nic *efx) efx_remove_nic(efx); } -/* A convinience function to safely flush all the queues */ -void efx_flush_queues(struct efx_nic *efx) -{ - EFX_ASSERT_RESET_SERIALISED(efx); - - efx_stop_all(efx); - - efx_fini_channels(efx); - efx_init_channels(efx); - - efx_start_all(efx); -} - /************************************************************************** * * Interrupt moderation @@ -1270,8 +1318,8 @@ void efx_init_irq_moderation(struct efx_nic *efx, int tx_usecs, int rx_usecs, { struct efx_tx_queue *tx_queue; struct efx_rx_queue *rx_queue; - unsigned tx_ticks = irq_mod_ticks(tx_usecs, FALCON_IRQ_MOD_RESOLUTION); - unsigned rx_ticks = irq_mod_ticks(rx_usecs, FALCON_IRQ_MOD_RESOLUTION); + unsigned tx_ticks = irq_mod_ticks(tx_usecs, EFX_IRQ_MOD_RESOLUTION); + unsigned rx_ticks = irq_mod_ticks(rx_usecs, EFX_IRQ_MOD_RESOLUTION); EFX_ASSERT_RESET_SERIALISED(efx); @@ -1296,10 +1344,10 @@ static void efx_monitor(struct work_struct *data) { struct efx_nic *efx = container_of(data, struct efx_nic, monitor_work.work); - int rc; EFX_TRACE(efx, "hardware monitor executing on CPU %d\n", raw_smp_processor_id()); + BUG_ON(efx->type->monitor == NULL); /* If the mac_lock is already held then it is likely a port * reconfiguration is already in place, which will likely do @@ -1308,15 +1356,7 @@ static void efx_monitor(struct work_struct *data) goto out_requeue; if (!efx->port_enabled) goto out_unlock; - rc = falcon_board(efx)->monitor(efx); - if (rc) { - EFX_ERR(efx, "Board sensor %s; shutting down PHY\n", - (rc == -ERANGE) ? "reported fault" : "failed"); - efx->phy_mode |= PHY_MODE_LOW_POWER; - falcon_sim_phy_event(efx); - } - efx->phy_op->poll(efx); - efx->mac_op->poll(efx); + efx->type->monitor(efx); out_unlock: mutex_unlock(&efx->mac_lock); @@ -1420,6 +1460,12 @@ static int efx_net_open(struct net_device *net_dev) return -EIO; if (efx->phy_mode & PHY_MODE_SPECIAL) return -EBUSY; + if (efx_mcdi_poll_reboot(efx) && efx_reset(efx, RESET_TYPE_ALL)) + return -EIO; + + /* Notify the kernel of the link state polled during driver load, + * before the monitor starts running */ + efx_link_status_changed(efx); efx_start_all(efx); return 0; @@ -1446,20 +1492,6 @@ static int efx_net_stop(struct net_device *net_dev) return 0; } -void efx_stats_disable(struct efx_nic *efx) -{ - spin_lock(&efx->stats_lock); - ++efx->stats_disable_count; - spin_unlock(&efx->stats_lock); -} - -void efx_stats_enable(struct efx_nic *efx) -{ - spin_lock(&efx->stats_lock); - --efx->stats_disable_count; - spin_unlock(&efx->stats_lock); -} - /* Context: process, dev_base_lock or RTNL held, non-blocking. */ static struct net_device_stats *efx_net_stats(struct net_device *net_dev) { @@ -1467,17 +1499,9 @@ static struct net_device_stats *efx_net_stats(struct net_device *net_dev) struct efx_mac_stats *mac_stats = &efx->mac_stats; struct net_device_stats *stats = &net_dev->stats; - /* Update stats if possible, but do not wait if another thread - * is updating them or if MAC stats fetches are temporarily - * disabled; slightly stale stats are acceptable. - */ - if (!spin_trylock(&efx->stats_lock)) - return stats; - if (!efx->stats_disable_count) { - efx->mac_op->update_stats(efx); - falcon_update_nic_stats(efx); - } - spin_unlock(&efx->stats_lock); + spin_lock_bh(&efx->stats_lock); + efx->type->update_stats(efx); + spin_unlock_bh(&efx->stats_lock); stats->rx_packets = mac_stats->rx_packets; stats->tx_packets = mac_stats->tx_packets; @@ -1536,7 +1560,14 @@ static int efx_change_mtu(struct net_device *net_dev, int new_mtu) EFX_LOG(efx, "changing MTU to %d\n", new_mtu); efx_fini_channels(efx); + + mutex_lock(&efx->mac_lock); + /* Reconfigure the MAC before enabling the dma queues so that + * the RX buffers don't overflow */ net_dev->mtu = new_mtu; + efx->mac_op->reconfigure(efx); + mutex_unlock(&efx->mac_lock); + efx_init_channels(efx); efx_start_all(efx); @@ -1560,7 +1591,9 @@ static int efx_set_mac_address(struct net_device *net_dev, void *data) memcpy(net_dev->dev_addr, new_addr, net_dev->addr_len); /* Reconfigure the MAC */ - efx_reconfigure_port(efx); + mutex_lock(&efx->mac_lock); + efx->mac_op->reconfigure(efx); + mutex_unlock(&efx->mac_lock); return 0; } @@ -1571,16 +1604,14 @@ static void efx_set_multicast_list(struct net_device *net_dev) struct efx_nic *efx = netdev_priv(net_dev); struct dev_mc_list *mc_list = net_dev->mc_list; union efx_multicast_hash *mc_hash = &efx->multicast_hash; - bool promiscuous = !!(net_dev->flags & IFF_PROMISC); - bool changed = (efx->promiscuous != promiscuous); u32 crc; int bit; int i; - efx->promiscuous = promiscuous; + efx->promiscuous = !!(net_dev->flags & IFF_PROMISC); /* Build multicast hash table */ - if (promiscuous || (net_dev->flags & IFF_ALLMULTI)) { + if (efx->promiscuous || (net_dev->flags & IFF_ALLMULTI)) { memset(mc_hash, 0xff, sizeof(*mc_hash)); } else { memset(mc_hash, 0x00, sizeof(*mc_hash)); @@ -1590,17 +1621,17 @@ static void efx_set_multicast_list(struct net_device *net_dev) set_bit_le(bit, mc_hash->byte); mc_list = mc_list->next; } - } - if (!efx->port_enabled) - /* Delay pushing settings until efx_start_port() */ - return; - - if (changed) - queue_work(efx->workqueue, &efx->phy_work); + /* Broadcast packets go through the multicast hash filter. + * ether_crc_le() of the broadcast address is 0xbe2612ff + * so we always add bit 0xff to the mask. + */ + set_bit_le(0xff, mc_hash->byte); + } - /* Create and activate new global multicast hash table */ - falcon_set_multicast_hash(efx); + if (efx->port_enabled) + queue_work(efx->workqueue, &efx->mac_work); + /* Otherwise efx_start_port() will do this */ } static const struct net_device_ops efx_netdev_ops = { @@ -1729,21 +1760,18 @@ static void efx_unregister_netdev(struct efx_nic *efx) /* Tears down the entire software state and most of the hardware state * before reset. */ -void efx_reset_down(struct efx_nic *efx, enum reset_type method, - struct ethtool_cmd *ecmd) +void efx_reset_down(struct efx_nic *efx, enum reset_type method) { EFX_ASSERT_RESET_SERIALISED(efx); - efx_stats_disable(efx); efx_stop_all(efx); mutex_lock(&efx->mac_lock); mutex_lock(&efx->spi_lock); - efx->phy_op->get_settings(efx, ecmd); - efx_fini_channels(efx); if (efx->port_initialized && method != RESET_TYPE_INVISIBLE) efx->phy_op->fini(efx); + efx->type->fini(efx); } /* This function will always ensure that the locks acquired in @@ -1751,79 +1779,67 @@ void efx_reset_down(struct efx_nic *efx, enum reset_type method, * that we were unable to reinitialise the hardware, and the * driver should be disabled. If ok is false, then the rx and tx * engines are not restarted, pending a RESET_DISABLE. */ -int efx_reset_up(struct efx_nic *efx, enum reset_type method, - struct ethtool_cmd *ecmd, bool ok) +int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok) { int rc; EFX_ASSERT_RESET_SERIALISED(efx); - rc = falcon_init_nic(efx); + rc = efx->type->init(efx); if (rc) { EFX_ERR(efx, "failed to initialise NIC\n"); - ok = false; + goto fail; } + if (!ok) + goto fail; + if (efx->port_initialized && method != RESET_TYPE_INVISIBLE) { - if (ok) { - rc = efx->phy_op->init(efx); - if (rc) - ok = false; - } - if (!ok) - efx->port_initialized = false; + rc = efx->phy_op->init(efx); + if (rc) + goto fail; + if (efx->phy_op->reconfigure(efx)) + EFX_ERR(efx, "could not restore PHY settings\n"); } - if (ok) { - efx_init_channels(efx); + efx->mac_op->reconfigure(efx); - if (efx->phy_op->set_settings(efx, ecmd)) - EFX_ERR(efx, "could not restore PHY settings\n"); - } + efx_init_channels(efx); + + mutex_unlock(&efx->spi_lock); + mutex_unlock(&efx->mac_lock); + + efx_start_all(efx); + + return 0; + +fail: + efx->port_initialized = false; mutex_unlock(&efx->spi_lock); mutex_unlock(&efx->mac_lock); - if (ok) { - efx_start_all(efx); - efx_stats_enable(efx); - } return rc; } -/* Reset the NIC as transparently as possible. Do not reset the PHY - * Note that the reset may fail, in which case the card will be left - * in a most-probably-unusable state. +/* Reset the NIC using the specified method. Note that the reset may + * fail, in which case the card will be left in an unusable state. * - * This function will sleep. You cannot reset from within an atomic - * state; use efx_schedule_reset() instead. - * - * Grabs the rtnl_lock. + * Caller must hold the rtnl_lock. */ -static int efx_reset(struct efx_nic *efx) +int efx_reset(struct efx_nic *efx, enum reset_type method) { - struct ethtool_cmd ecmd; - enum reset_type method = efx->reset_pending; - int rc = 0; - - /* Serialise with kernel interfaces */ - rtnl_lock(); - - /* If we're not RUNNING then don't reset. Leave the reset_pending - * flag set so that efx_pci_probe_main will be retried */ - if (efx->state != STATE_RUNNING) { - EFX_INFO(efx, "scheduled reset quenched. NIC not RUNNING\n"); - goto out_unlock; - } + int rc, rc2; + bool disabled; EFX_INFO(efx, "resetting (%s)\n", RESET_TYPE(method)); - efx_reset_down(efx, method, &ecmd); + efx_reset_down(efx, method); - rc = falcon_reset_hw(efx, method); + rc = efx->type->reset(efx, method); if (rc) { EFX_ERR(efx, "failed to reset hardware\n"); - goto out_disable; + goto out; } /* Allow resets to be rescheduled. */ @@ -1835,25 +1851,22 @@ static int efx_reset(struct efx_nic *efx) * can respond to requests. */ pci_set_master(efx->pci_dev); +out: /* Leave device stopped if necessary */ - if (method == RESET_TYPE_DISABLE) { - efx_reset_up(efx, method, &ecmd, false); - rc = -EIO; - } else { - rc = efx_reset_up(efx, method, &ecmd, true); + disabled = rc || method == RESET_TYPE_DISABLE; + rc2 = efx_reset_up(efx, method, !disabled); + if (rc2) { + disabled = true; + if (!rc) + rc = rc2; } -out_disable: - if (rc) { + if (disabled) { EFX_ERR(efx, "has been disabled\n"); efx->state = STATE_DISABLED; - dev_close(efx->net_dev); } else { EFX_LOG(efx, "reset complete\n"); } - -out_unlock: - rtnl_unlock(); return rc; } @@ -1862,9 +1875,19 @@ out_unlock: */ static void efx_reset_work(struct work_struct *data) { - struct efx_nic *nic = container_of(data, struct efx_nic, reset_work); + struct efx_nic *efx = container_of(data, struct efx_nic, reset_work); - efx_reset(nic); + /* If we're not RUNNING then don't reset. Leave the reset_pending + * flag set so that efx_pci_probe_main will be retried */ + if (efx->state != STATE_RUNNING) { + EFX_INFO(efx, "scheduled reset quenched. NIC not RUNNING\n"); + return; + } + + rtnl_lock(); + if (efx_reset(efx, efx->reset_pending)) + dev_close(efx->net_dev); + rtnl_unlock(); } void efx_schedule_reset(struct efx_nic *efx, enum reset_type type) @@ -1889,6 +1912,7 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type) case RESET_TYPE_TX_SKIP: method = RESET_TYPE_INVISIBLE; break; + case RESET_TYPE_MC_FAILURE: default: method = RESET_TYPE_ALL; break; @@ -1902,6 +1926,10 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type) efx->reset_pending = method; + /* efx_process_channel() will no longer read events once a + * reset is scheduled. So switch back to poll'd MCDI completions. */ + efx_mcdi_mode_poll(efx); + queue_work(reset_workqueue, &efx->reset_work); } @@ -1914,9 +1942,13 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type) /* PCI device ID table */ static struct pci_device_id efx_pci_table[] __devinitdata = { {PCI_DEVICE(EFX_VENDID_SFC, FALCON_A_P_DEVID), - .driver_data = (unsigned long) &falcon_a_nic_type}, + .driver_data = (unsigned long) &falcon_a1_nic_type}, {PCI_DEVICE(EFX_VENDID_SFC, FALCON_B_P_DEVID), - .driver_data = (unsigned long) &falcon_b_nic_type}, + .driver_data = (unsigned long) &falcon_b0_nic_type}, + {PCI_DEVICE(EFX_VENDID_SFC, BETHPAGE_A_P_DEVID), + .driver_data = (unsigned long) &siena_a0_nic_type}, + {PCI_DEVICE(EFX_VENDID_SFC, SIENA_A_P_DEVID), + .driver_data = (unsigned long) &siena_a0_nic_type}, {0} /* end of list */ }; @@ -1937,19 +1969,16 @@ void efx_port_dummy_op_void(struct efx_nic *efx) {} void efx_port_dummy_op_set_id_led(struct efx_nic *efx, enum efx_led_mode mode) { } - -static struct efx_mac_operations efx_dummy_mac_operations = { - .reconfigure = efx_port_dummy_op_void, - .poll = efx_port_dummy_op_void, - .irq = efx_port_dummy_op_void, -}; +bool efx_port_dummy_op_poll(struct efx_nic *efx) +{ + return false; +} static struct efx_phy_operations efx_dummy_phy_operations = { .init = efx_port_dummy_op_int, - .reconfigure = efx_port_dummy_op_void, - .poll = efx_port_dummy_op_void, + .reconfigure = efx_port_dummy_op_int, + .poll = efx_port_dummy_op_poll, .fini = efx_port_dummy_op_void, - .clear_interrupt = efx_port_dummy_op_void, }; /************************************************************************** @@ -1972,8 +2001,11 @@ static int efx_init_struct(struct efx_nic *efx, struct efx_nic_type *type, /* Initialise common structures */ memset(efx, 0, sizeof(*efx)); spin_lock_init(&efx->biu_lock); - spin_lock_init(&efx->phy_lock); + mutex_init(&efx->mdio_lock); mutex_init(&efx->spi_lock); +#ifdef CONFIG_SFC_MTD + INIT_LIST_HEAD(&efx->mtd_list); +#endif INIT_WORK(&efx->reset_work, efx_reset_work); INIT_DELAYED_WORK(&efx->monitor_work, efx_monitor); efx->pci_dev = pci_dev; @@ -1985,12 +2017,10 @@ static int efx_init_struct(struct efx_nic *efx, struct efx_nic_type *type, efx->rx_checksum_enabled = true; spin_lock_init(&efx->netif_stop_lock); spin_lock_init(&efx->stats_lock); - efx->stats_disable_count = 1; mutex_init(&efx->mac_lock); - efx->mac_op = &efx_dummy_mac_operations; + efx->mac_op = type->default_mac_ops; efx->phy_op = &efx_dummy_phy_operations; efx->mdio.dev = net_dev; - INIT_WORK(&efx->phy_work, efx_phy_work); INIT_WORK(&efx->mac_work, efx_mac_work); atomic_set(&efx->netif_stop_count, 1); @@ -2058,9 +2088,10 @@ static void efx_fini_struct(struct efx_nic *efx) */ static void efx_pci_remove_main(struct efx_nic *efx) { - falcon_fini_interrupt(efx); + efx_nic_fini_interrupt(efx); efx_fini_channels(efx); efx_fini_port(efx); + efx->type->fini(efx); efx_fini_napi(efx); efx_remove_all(efx); } @@ -2120,7 +2151,7 @@ static int efx_pci_probe_main(struct efx_nic *efx) if (rc) goto fail2; - rc = falcon_init_nic(efx); + rc = efx->type->init(efx); if (rc) { EFX_ERR(efx, "failed to initialise NIC\n"); goto fail3; @@ -2134,7 +2165,7 @@ static int efx_pci_probe_main(struct efx_nic *efx) efx_init_channels(efx); - rc = falcon_init_interrupt(efx); + rc = efx_nic_init_interrupt(efx); if (rc) goto fail5; @@ -2144,6 +2175,7 @@ static int efx_pci_probe_main(struct efx_nic *efx) efx_fini_channels(efx); efx_fini_port(efx); fail4: + efx->type->fini(efx); fail3: efx_fini_napi(efx); fail2: @@ -2173,9 +2205,11 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev, net_dev = alloc_etherdev(sizeof(*efx)); if (!net_dev) return -ENOMEM; - net_dev->features |= (NETIF_F_IP_CSUM | NETIF_F_SG | + net_dev->features |= (type->offload_features | NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_TSO | NETIF_F_GRO); + if (type->offload_features & NETIF_F_V6_CSUM) + net_dev->features |= NETIF_F_TSO6; /* Mask for features that also apply to VLAN devices */ net_dev->vlan_features |= (NETIF_F_ALL_CSUM | NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_TSO); @@ -2227,9 +2261,8 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev, goto fail4; } - /* Switch to the running state before we expose the device to - * the OS. This is to ensure that the initial gathering of - * MAC stats succeeds. */ + /* Switch to the running state before we expose the device to the OS, + * so that dev_open()|efx_start_all() will actually start the device */ efx->state = STATE_RUNNING; rc = efx_register_netdev(efx); @@ -2256,11 +2289,107 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev, return rc; } +static int efx_pm_freeze(struct device *dev) +{ + struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + + efx->state = STATE_FINI; + + netif_device_detach(efx->net_dev); + + efx_stop_all(efx); + efx_fini_channels(efx); + + return 0; +} + +static int efx_pm_thaw(struct device *dev) +{ + struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + + efx->state = STATE_INIT; + + efx_init_channels(efx); + + mutex_lock(&efx->mac_lock); + efx->phy_op->reconfigure(efx); + mutex_unlock(&efx->mac_lock); + + efx_start_all(efx); + + netif_device_attach(efx->net_dev); + + efx->state = STATE_RUNNING; + + efx->type->resume_wol(efx); + + return 0; +} + +static int efx_pm_poweroff(struct device *dev) +{ + struct pci_dev *pci_dev = to_pci_dev(dev); + struct efx_nic *efx = pci_get_drvdata(pci_dev); + + efx->type->fini(efx); + + efx->reset_pending = RESET_TYPE_NONE; + + pci_save_state(pci_dev); + return pci_set_power_state(pci_dev, PCI_D3hot); +} + +/* Used for both resume and restore */ +static int efx_pm_resume(struct device *dev) +{ + struct pci_dev *pci_dev = to_pci_dev(dev); + struct efx_nic *efx = pci_get_drvdata(pci_dev); + int rc; + + rc = pci_set_power_state(pci_dev, PCI_D0); + if (rc) + return rc; + pci_restore_state(pci_dev); + rc = pci_enable_device(pci_dev); + if (rc) + return rc; + pci_set_master(efx->pci_dev); + rc = efx->type->reset(efx, RESET_TYPE_ALL); + if (rc) + return rc; + rc = efx->type->init(efx); + if (rc) + return rc; + efx_pm_thaw(dev); + return 0; +} + +static int efx_pm_suspend(struct device *dev) +{ + int rc; + + efx_pm_freeze(dev); + rc = efx_pm_poweroff(dev); + if (rc) + efx_pm_resume(dev); + return rc; +} + +static struct dev_pm_ops efx_pm_ops = { + .suspend = efx_pm_suspend, + .resume = efx_pm_resume, + .freeze = efx_pm_freeze, + .thaw = efx_pm_thaw, + .poweroff = efx_pm_poweroff, + .restore = efx_pm_resume, +}; + static struct pci_driver efx_pci_driver = { .name = EFX_DRIVER_NAME, .id_table = efx_pci_table, .probe = efx_pci_probe, .remove = efx_pci_remove, + .driver.pm = &efx_pm_ops, }; /************************************************************************** @@ -2324,8 +2453,8 @@ static void __exit efx_exit_module(void) module_init(efx_init_module); module_exit(efx_exit_module); -MODULE_AUTHOR("Michael Brown <mbrown@fensystems.co.uk> and " - "Solarflare Communications"); +MODULE_AUTHOR("Solarflare Communications and " + "Michael Brown <mbrown@fensystems.co.uk>"); MODULE_DESCRIPTION("Solarflare Communications network driver"); MODULE_LICENSE("GPL"); MODULE_DEVICE_TABLE(pci, efx_pci_table); diff --git a/drivers/net/sfc/efx.h b/drivers/net/sfc/efx.h index 3497b036f408..a615ac051530 100644 --- a/drivers/net/sfc/efx.h +++ b/drivers/net/sfc/efx.h @@ -1,7 +1,7 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards * Copyright 2005-2006 Fen Systems Ltd. - * Copyright 2006-2008 Solarflare Communications Inc. + * Copyright 2006-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -18,6 +18,8 @@ #define FALCON_A_P_DEVID 0x0703 #define FALCON_A_S_DEVID 0x6703 #define FALCON_B_P_DEVID 0x0710 +#define BETHPAGE_A_P_DEVID 0x0803 +#define SIENA_A_P_DEVID 0x0813 /* Solarstorm controllers use BAR 0 for I/O space and BAR 2(&3) for memory */ #define EFX_MEM_BAR 2 @@ -56,15 +58,12 @@ extern void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue, int delay); /* Channels */ extern void efx_process_channel_now(struct efx_channel *channel); -extern void efx_flush_queues(struct efx_nic *efx); #define EFX_EVQ_SIZE 4096 #define EFX_EVQ_MASK (EFX_EVQ_SIZE - 1) /* Ports */ -extern void efx_stats_disable(struct efx_nic *efx); -extern void efx_stats_enable(struct efx_nic *efx); -extern void efx_reconfigure_port(struct efx_nic *efx); -extern void __efx_reconfigure_port(struct efx_nic *efx); +extern int efx_reconfigure_port(struct efx_nic *efx); +extern int __efx_reconfigure_port(struct efx_nic *efx); /* Ethtool support */ extern int efx_ethtool_get_settings(struct net_device *net_dev, @@ -74,10 +73,9 @@ extern int efx_ethtool_set_settings(struct net_device *net_dev, extern const struct ethtool_ops efx_ethtool_ops; /* Reset handling */ -extern void efx_reset_down(struct efx_nic *efx, enum reset_type method, - struct ethtool_cmd *ecmd); -extern int efx_reset_up(struct efx_nic *efx, enum reset_type method, - struct ethtool_cmd *ecmd, bool ok); +extern int efx_reset(struct efx_nic *efx, enum reset_type method); +extern void efx_reset_down(struct efx_nic *efx, enum reset_type method); +extern int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok); /* Global */ extern void efx_schedule_reset(struct efx_nic *efx, enum reset_type type); @@ -93,6 +91,7 @@ extern int efx_port_dummy_op_int(struct efx_nic *efx); extern void efx_port_dummy_op_void(struct efx_nic *efx); extern void efx_port_dummy_op_set_id_led(struct efx_nic *efx, enum efx_led_mode mode); +extern bool efx_port_dummy_op_poll(struct efx_nic *efx); /* MTD */ #ifdef CONFIG_SFC_MTD @@ -116,4 +115,8 @@ static inline void efx_schedule_channel(struct efx_channel *channel) napi_schedule(&channel->napi_str); } +extern void efx_link_status_changed(struct efx_nic *efx); +extern void efx_link_set_advertising(struct efx_nic *efx, u32); +extern void efx_link_set_wanted_fc(struct efx_nic *efx, enum efx_fc_type); + #endif /* EFX_EFX_H */ diff --git a/drivers/net/sfc/enum.h b/drivers/net/sfc/enum.h index fcd14b73f24d..384cfe3b1be1 100644 --- a/drivers/net/sfc/enum.h +++ b/drivers/net/sfc/enum.h @@ -1,6 +1,6 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards - * Copyright 2007-2008 Solarflare Communications Inc. + * Copyright 2007-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -13,38 +13,101 @@ /** * enum efx_loopback_mode - loopback modes * @LOOPBACK_NONE: no loopback - * @LOOPBACK_GMAC: loopback within GMAC at unspecified level - * @LOOPBACK_XGMII: loopback within XMAC at XGMII level - * @LOOPBACK_XGXS: loopback within XMAC at XGXS level - * @LOOPBACK_XAUI: loopback within XMAC at XAUI level + * @LOOPBACK_DATA: data path loopback + * @LOOPBACK_GMAC: loopback within GMAC + * @LOOPBACK_XGMII: loopback after XMAC + * @LOOPBACK_XGXS: loopback within BPX after XGXS + * @LOOPBACK_XAUI: loopback within BPX before XAUI serdes + * @LOOPBACK_GMII: loopback within BPX after GMAC + * @LOOPBACK_SGMII: loopback within BPX within SGMII + * @LOOPBACK_XGBR: loopback within BPX within XGBR + * @LOOPBACK_XFI: loopback within BPX before XFI serdes + * @LOOPBACK_XAUI_FAR: loopback within BPX after XAUI serdes + * @LOOPBACK_GMII_FAR: loopback within BPX before SGMII + * @LOOPBACK_SGMII_FAR: loopback within BPX after SGMII + * @LOOPBACK_XFI_FAR: loopback after XFI serdes * @LOOPBACK_GPHY: loopback within 1G PHY at unspecified level * @LOOPBACK_PHYXS: loopback within 10G PHY at PHYXS level * @LOOPBACK_PCS: loopback within 10G PHY at PCS level * @LOOPBACK_PMAPMD: loopback within 10G PHY at PMAPMD level - * @LOOPBACK_NETWORK: reflecting loopback (even further than furthest!) + * @LOOPBACK_XPORT: cross port loopback + * @LOOPBACK_XGMII_WS: wireside loopback excluding XMAC + * @LOOPBACK_XAUI_WS: wireside loopback within BPX within XAUI serdes + * @LOOPBACK_XAUI_WS_FAR: wireside loopback within BPX including XAUI serdes + * @LOOPBACK_XAUI_WS_NEAR: wireside loopback within BPX excluding XAUI serdes + * @LOOPBACK_GMII_WS: wireside loopback excluding GMAC + * @LOOPBACK_XFI_WS: wireside loopback excluding XFI serdes + * @LOOPBACK_XFI_WS_FAR: wireside loopback including XFI serdes + * @LOOPBACK_PHYXS_WS: wireside loopback within 10G PHY at PHYXS level */ -/* Please keep in order and up-to-date w.r.t the following two #defines */ +/* Please keep up-to-date w.r.t the following two #defines */ enum efx_loopback_mode { LOOPBACK_NONE = 0, - LOOPBACK_GMAC = 1, - LOOPBACK_XGMII = 2, - LOOPBACK_XGXS = 3, - LOOPBACK_XAUI = 4, - LOOPBACK_GPHY = 5, - LOOPBACK_PHYXS = 6, - LOOPBACK_PCS = 7, - LOOPBACK_PMAPMD = 8, - LOOPBACK_NETWORK = 9, + LOOPBACK_DATA = 1, + LOOPBACK_GMAC = 2, + LOOPBACK_XGMII = 3, + LOOPBACK_XGXS = 4, + LOOPBACK_XAUI = 5, + LOOPBACK_GMII = 6, + LOOPBACK_SGMII = 7, + LOOPBACK_XGBR = 8, + LOOPBACK_XFI = 9, + LOOPBACK_XAUI_FAR = 10, + LOOPBACK_GMII_FAR = 11, + LOOPBACK_SGMII_FAR = 12, + LOOPBACK_XFI_FAR = 13, + LOOPBACK_GPHY = 14, + LOOPBACK_PHYXS = 15, + LOOPBACK_PCS = 16, + LOOPBACK_PMAPMD = 17, + LOOPBACK_XPORT = 18, + LOOPBACK_XGMII_WS = 19, + LOOPBACK_XAUI_WS = 20, + LOOPBACK_XAUI_WS_FAR = 21, + LOOPBACK_XAUI_WS_NEAR = 22, + LOOPBACK_GMII_WS = 23, + LOOPBACK_XFI_WS = 24, + LOOPBACK_XFI_WS_FAR = 25, + LOOPBACK_PHYXS_WS = 26, LOOPBACK_MAX }; - #define LOOPBACK_TEST_MAX LOOPBACK_PMAPMD /* These loopbacks occur within the controller */ -#define LOOPBACKS_INTERNAL ((1 << LOOPBACK_GMAC) | \ - (1 << LOOPBACK_XGMII)| \ - (1 << LOOPBACK_XGXS) | \ - (1 << LOOPBACK_XAUI)) +#define LOOPBACKS_INTERNAL ((1 << LOOPBACK_DATA) | \ + (1 << LOOPBACK_GMAC) | \ + (1 << LOOPBACK_XGMII)| \ + (1 << LOOPBACK_XGXS) | \ + (1 << LOOPBACK_XAUI) | \ + (1 << LOOPBACK_GMII) | \ + (1 << LOOPBACK_SGMII) | \ + (1 << LOOPBACK_SGMII) | \ + (1 << LOOPBACK_XGBR) | \ + (1 << LOOPBACK_XFI) | \ + (1 << LOOPBACK_XAUI_FAR) | \ + (1 << LOOPBACK_GMII_FAR) | \ + (1 << LOOPBACK_SGMII_FAR) | \ + (1 << LOOPBACK_XFI_FAR) | \ + (1 << LOOPBACK_XGMII_WS) | \ + (1 << LOOPBACK_XAUI_WS) | \ + (1 << LOOPBACK_XAUI_WS_FAR) | \ + (1 << LOOPBACK_XAUI_WS_NEAR) | \ + (1 << LOOPBACK_GMII_WS) | \ + (1 << LOOPBACK_XFI_WS) | \ + (1 << LOOPBACK_XFI_WS_FAR)) + +#define LOOPBACKS_WS ((1 << LOOPBACK_XGMII_WS) | \ + (1 << LOOPBACK_XAUI_WS) | \ + (1 << LOOPBACK_XAUI_WS_FAR) | \ + (1 << LOOPBACK_XAUI_WS_NEAR) | \ + (1 << LOOPBACK_GMII_WS) | \ + (1 << LOOPBACK_XFI_WS) | \ + (1 << LOOPBACK_XFI_WS_FAR) | \ + (1 << LOOPBACK_PHYXS_WS)) + +#define LOOPBACKS_EXTERNAL(_efx) \ + ((_efx)->loopback_modes & ~LOOPBACKS_INTERNAL & \ + ~(1 << LOOPBACK_NONE)) #define LOOPBACK_MASK(_efx) \ (1 << (_efx)->loopback_mode) @@ -52,6 +115,9 @@ enum efx_loopback_mode { #define LOOPBACK_INTERNAL(_efx) \ (!!(LOOPBACKS_INTERNAL & LOOPBACK_MASK(_efx))) +#define LOOPBACK_EXTERNAL(_efx) \ + (!!(LOOPBACK_MASK(_efx) & LOOPBACKS_EXTERNAL(_efx))) + #define LOOPBACK_CHANGED(_from, _to, _mask) \ (!!((LOOPBACK_MASK(_from) ^ LOOPBACK_MASK(_to)) & (_mask))) @@ -78,6 +144,7 @@ enum efx_loopback_mode { * @RESET_TYPE_RX_DESC_FETCH: pcie error during rx descriptor fetch * @RESET_TYPE_TX_DESC_FETCH: pcie error during tx descriptor fetch * @RESET_TYPE_TX_SKIP: hardware completed empty tx descriptors + * @RESET_TYPE_MC_FAILURE: MC reboot/assertion */ enum reset_type { RESET_TYPE_NONE = -1, @@ -92,6 +159,7 @@ enum reset_type { RESET_TYPE_RX_DESC_FETCH, RESET_TYPE_TX_DESC_FETCH, RESET_TYPE_TX_SKIP, + RESET_TYPE_MC_FAILURE, RESET_TYPE_MAX, }; diff --git a/drivers/net/sfc/ethtool.c b/drivers/net/sfc/ethtool.c index d8915b95e65a..6c0bbed8c477 100644 --- a/drivers/net/sfc/ethtool.c +++ b/drivers/net/sfc/ethtool.c @@ -1,7 +1,7 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards * Copyright 2005-2006 Fen Systems Ltd. - * Copyright 2006-2008 Solarflare Communications Inc. + * Copyright 2006-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -10,13 +10,12 @@ #include <linux/netdevice.h> #include <linux/ethtool.h> -#include <linux/mdio.h> #include <linux/rtnetlink.h> #include "net_driver.h" #include "workarounds.h" #include "selftest.h" #include "efx.h" -#include "falcon.h" +#include "nic.h" #include "spi.h" #include "mdio_10g.h" @@ -153,6 +152,7 @@ static struct efx_ethtool_stat efx_ethtool_stats[] = { EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_tobe_disc), EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_ip_hdr_chksum_err), EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_tcp_udp_chksum_err), + EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_mcast_mismatch), EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_frm_trunc), }; @@ -174,14 +174,14 @@ static int efx_ethtool_phys_id(struct net_device *net_dev, u32 count) struct efx_nic *efx = netdev_priv(net_dev); do { - falcon_board(efx)->set_id_led(efx, EFX_LED_ON); + efx->type->set_id_led(efx, EFX_LED_ON); schedule_timeout_interruptible(HZ / 2); - falcon_board(efx)->set_id_led(efx, EFX_LED_OFF); + efx->type->set_id_led(efx, EFX_LED_OFF); schedule_timeout_interruptible(HZ / 2); } while (!signal_pending(current) && --count != 0); - falcon_board(efx)->set_id_led(efx, EFX_LED_DEFAULT); + efx->type->set_id_led(efx, EFX_LED_DEFAULT); return 0; } @@ -190,6 +190,7 @@ int efx_ethtool_get_settings(struct net_device *net_dev, struct ethtool_cmd *ecmd) { struct efx_nic *efx = netdev_priv(net_dev); + struct efx_link_state *link_state = &efx->link_state; mutex_lock(&efx->mac_lock); efx->phy_op->get_settings(efx, ecmd); @@ -197,6 +198,13 @@ int efx_ethtool_get_settings(struct net_device *net_dev, /* Falcon GMAC does not support 1000Mbps HD */ ecmd->supported &= ~SUPPORTED_1000baseT_Half; + /* Both MACs support pause frames (bidirectional and respond-only) */ + ecmd->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + + if (LOOPBACK_INTERNAL(efx)) { + ecmd->speed = link_state->speed; + ecmd->duplex = link_state->fd ? DUPLEX_FULL : DUPLEX_HALF; + } return 0; } @@ -218,9 +226,6 @@ int efx_ethtool_set_settings(struct net_device *net_dev, mutex_lock(&efx->mac_lock); rc = efx->phy_op->set_settings(efx, ecmd); mutex_unlock(&efx->mac_lock); - if (!rc) - efx_reconfigure_port(efx); - return rc; } @@ -231,6 +236,9 @@ static void efx_ethtool_get_drvinfo(struct net_device *net_dev, strlcpy(info->driver, EFX_DRIVER_NAME, sizeof(info->driver)); strlcpy(info->version, EFX_DRIVER_VERSION, sizeof(info->version)); + if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0) + siena_print_fwver(efx, info->fw_version, + sizeof(info->fw_version)); strlcpy(info->bus_info, pci_name(efx->pci_dev), sizeof(info->bus_info)); } @@ -360,9 +368,21 @@ static int efx_ethtool_fill_self_tests(struct efx_nic *efx, efx_fill_test(n++, strings, data, &tests->registers, "core", 0, "registers", NULL); - for (i = 0; i < efx->phy_op->num_tests; i++) - efx_fill_test(n++, strings, data, &tests->phy[i], - "phy", 0, efx->phy_op->test_names[i], NULL); + if (efx->phy_op->run_tests != NULL) { + EFX_BUG_ON_PARANOID(efx->phy_op->test_name == NULL); + + for (i = 0; true; ++i) { + const char *name; + + EFX_BUG_ON_PARANOID(i >= EFX_MAX_PHY_TESTS); + name = efx->phy_op->test_name(efx, i); + if (name == NULL) + break; + + efx_fill_test(n++, strings, data, &tests->phy[i], + "phy", 0, name, NULL); + } + } /* Loopback tests */ for (mode = LOOPBACK_NONE; mode <= LOOPBACK_TEST_MAX; mode++) { @@ -451,6 +471,36 @@ static void efx_ethtool_get_stats(struct net_device *net_dev, } } +static int efx_ethtool_set_tso(struct net_device *net_dev, u32 enable) +{ + struct efx_nic *efx __attribute__ ((unused)) = netdev_priv(net_dev); + unsigned long features; + + features = NETIF_F_TSO; + if (efx->type->offload_features & NETIF_F_V6_CSUM) + features |= NETIF_F_TSO6; + + if (enable) + net_dev->features |= features; + else + net_dev->features &= ~features; + + return 0; +} + +static int efx_ethtool_set_tx_csum(struct net_device *net_dev, u32 enable) +{ + struct efx_nic *efx = netdev_priv(net_dev); + unsigned long features = efx->type->offload_features & NETIF_F_ALL_CSUM; + + if (enable) + net_dev->features |= features; + else + net_dev->features &= ~features; + + return 0; +} + static int efx_ethtool_set_rx_csum(struct net_device *net_dev, u32 enable) { struct efx_nic *efx = netdev_priv(net_dev); @@ -550,7 +600,8 @@ static int efx_ethtool_get_eeprom(struct net_device *net_dev, rc = mutex_lock_interruptible(&efx->spi_lock); if (rc) return rc; - rc = falcon_spi_read(spi, eeprom->offset + EFX_EEPROM_BOOTCONFIG_START, + rc = falcon_spi_read(efx, spi, + eeprom->offset + EFX_EEPROM_BOOTCONFIG_START, eeprom->len, &len, buf); mutex_unlock(&efx->spi_lock); @@ -573,7 +624,8 @@ static int efx_ethtool_set_eeprom(struct net_device *net_dev, rc = mutex_lock_interruptible(&efx->spi_lock); if (rc) return rc; - rc = falcon_spi_write(spi, eeprom->offset + EFX_EEPROM_BOOTCONFIG_START, + rc = falcon_spi_write(efx, spi, + eeprom->offset + EFX_EEPROM_BOOTCONFIG_START, eeprom->len, &len, buf); mutex_unlock(&efx->spi_lock); @@ -606,8 +658,8 @@ static int efx_ethtool_get_coalesce(struct net_device *net_dev, coalesce->use_adaptive_rx_coalesce = efx->irq_rx_adaptive; coalesce->rx_coalesce_usecs_irq = efx->irq_rx_moderation; - coalesce->tx_coalesce_usecs_irq *= FALCON_IRQ_MOD_RESOLUTION; - coalesce->rx_coalesce_usecs_irq *= FALCON_IRQ_MOD_RESOLUTION; + coalesce->tx_coalesce_usecs_irq *= EFX_IRQ_MOD_RESOLUTION; + coalesce->rx_coalesce_usecs_irq *= EFX_IRQ_MOD_RESOLUTION; return 0; } @@ -648,7 +700,7 @@ static int efx_ethtool_set_coalesce(struct net_device *net_dev, efx_init_irq_moderation(efx, tx_usecs, rx_usecs, adaptive); efx_for_each_channel(channel, efx) - falcon_set_int_moderation(channel); + efx->type->push_irq_moderation(channel); return 0; } @@ -657,8 +709,12 @@ static int efx_ethtool_set_pauseparam(struct net_device *net_dev, struct ethtool_pauseparam *pause) { struct efx_nic *efx = netdev_priv(net_dev); - enum efx_fc_type wanted_fc; + enum efx_fc_type wanted_fc, old_fc; + u32 old_adv; bool reset; + int rc = 0; + + mutex_lock(&efx->mac_lock); wanted_fc = ((pause->rx_pause ? EFX_FC_RX : 0) | (pause->tx_pause ? EFX_FC_TX : 0) | @@ -666,14 +722,14 @@ static int efx_ethtool_set_pauseparam(struct net_device *net_dev, if ((wanted_fc & EFX_FC_TX) && !(wanted_fc & EFX_FC_RX)) { EFX_LOG(efx, "Flow control unsupported: tx ON rx OFF\n"); - return -EINVAL; + rc = -EINVAL; + goto out; } - if (!(efx->phy_op->mmds & MDIO_DEVS_AN) && - (wanted_fc & EFX_FC_AUTO)) { - EFX_LOG(efx, "PHY does not support flow control " - "autonegotiation\n"); - return -EINVAL; + if ((wanted_fc & EFX_FC_AUTO) && !efx->link_advertising) { + EFX_LOG(efx, "Autonegotiation is disabled\n"); + rc = -EINVAL; + goto out; } /* TX flow control may automatically turn itself off if the @@ -683,27 +739,40 @@ static int efx_ethtool_set_pauseparam(struct net_device *net_dev, * and fix it be cycling transmit flow control on this end. */ reset = (wanted_fc & EFX_FC_TX) && !(efx->wanted_fc & EFX_FC_TX); if (EFX_WORKAROUND_11482(efx) && reset) { - if (falcon_rev(efx) >= FALCON_REV_B0) { + if (efx_nic_rev(efx) == EFX_REV_FALCON_B0) { /* Recover by resetting the EM block */ - if (efx->link_state.up) - falcon_drain_tx_fifo(efx); + falcon_stop_nic_stats(efx); + falcon_drain_tx_fifo(efx); + efx->mac_op->reconfigure(efx); + falcon_start_nic_stats(efx); } else { /* Schedule a reset to recover */ efx_schedule_reset(efx, RESET_TYPE_INVISIBLE); } } - /* Try to push the pause parameters */ - mutex_lock(&efx->mac_lock); + old_adv = efx->link_advertising; + old_fc = efx->wanted_fc; + efx_link_set_wanted_fc(efx, wanted_fc); + if (efx->link_advertising != old_adv || + (efx->wanted_fc ^ old_fc) & EFX_FC_AUTO) { + rc = efx->phy_op->reconfigure(efx); + if (rc) { + EFX_ERR(efx, "Unable to advertise requested flow " + "control setting\n"); + goto out; + } + } - efx->wanted_fc = wanted_fc; - if (efx->phy_op->mmds & MDIO_DEVS_AN) - mdio45_ethtool_spauseparam_an(&efx->mdio, pause); - __efx_reconfigure_port(efx); + /* Reconfigure the MAC. The PHY *may* generate a link state change event + * if the user just changed the advertised capabilities, but there's no + * harm doing this twice */ + efx->mac_op->reconfigure(efx); +out: mutex_unlock(&efx->mac_lock); - return 0; + return rc; } static void efx_ethtool_get_pauseparam(struct net_device *net_dev, @@ -717,6 +786,50 @@ static void efx_ethtool_get_pauseparam(struct net_device *net_dev, } +static void efx_ethtool_get_wol(struct net_device *net_dev, + struct ethtool_wolinfo *wol) +{ + struct efx_nic *efx = netdev_priv(net_dev); + return efx->type->get_wol(efx, wol); +} + + +static int efx_ethtool_set_wol(struct net_device *net_dev, + struct ethtool_wolinfo *wol) +{ + struct efx_nic *efx = netdev_priv(net_dev); + return efx->type->set_wol(efx, wol->wolopts); +} + +extern int efx_ethtool_reset(struct net_device *net_dev, u32 *flags) +{ + struct efx_nic *efx = netdev_priv(net_dev); + enum reset_type method; + enum { + ETH_RESET_EFX_INVISIBLE = (ETH_RESET_DMA | ETH_RESET_FILTER | + ETH_RESET_OFFLOAD | ETH_RESET_MAC) + }; + + /* Check for minimal reset flags */ + if ((*flags & ETH_RESET_EFX_INVISIBLE) != ETH_RESET_EFX_INVISIBLE) + return -EINVAL; + *flags ^= ETH_RESET_EFX_INVISIBLE; + method = RESET_TYPE_INVISIBLE; + + if (*flags & ETH_RESET_PHY) { + *flags ^= ETH_RESET_PHY; + method = RESET_TYPE_ALL; + } + + if ((*flags & efx->type->reset_world_flags) == + efx->type->reset_world_flags) { + *flags ^= efx->type->reset_world_flags; + method = RESET_TYPE_WORLD; + } + + return efx_reset(efx, method); +} + const struct ethtool_ops efx_ethtool_ops = { .get_settings = efx_ethtool_get_settings, .set_settings = efx_ethtool_set_settings, @@ -733,11 +846,13 @@ const struct ethtool_ops efx_ethtool_ops = { .get_rx_csum = efx_ethtool_get_rx_csum, .set_rx_csum = efx_ethtool_set_rx_csum, .get_tx_csum = ethtool_op_get_tx_csum, - .set_tx_csum = ethtool_op_set_tx_csum, + /* Need to enable/disable IPv6 too */ + .set_tx_csum = efx_ethtool_set_tx_csum, .get_sg = ethtool_op_get_sg, .set_sg = ethtool_op_set_sg, .get_tso = ethtool_op_get_tso, - .set_tso = ethtool_op_set_tso, + /* Need to enable/disable TSO-IPv6 too */ + .set_tso = efx_ethtool_set_tso, .get_flags = ethtool_op_get_flags, .set_flags = ethtool_op_set_flags, .get_sset_count = efx_ethtool_get_sset_count, @@ -745,4 +860,7 @@ const struct ethtool_ops efx_ethtool_ops = { .get_strings = efx_ethtool_get_strings, .phys_id = efx_ethtool_phys_id, .get_ethtool_stats = efx_ethtool_get_stats, + .get_wol = efx_ethtool_get_wol, + .set_wol = efx_ethtool_set_wol, + .reset = efx_ethtool_reset, }; diff --git a/drivers/net/sfc/falcon.c b/drivers/net/sfc/falcon.c index 41a321b0e8c6..17afcd26e870 100644 --- a/drivers/net/sfc/falcon.c +++ b/drivers/net/sfc/falcon.c @@ -1,7 +1,7 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards * Copyright 2005-2006 Fen Systems Ltd. - * Copyright 2006-2008 Solarflare Communications Inc. + * Copyright 2006-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -20,41 +20,14 @@ #include "efx.h" #include "mac.h" #include "spi.h" -#include "falcon.h" +#include "nic.h" #include "regs.h" #include "io.h" #include "mdio_10g.h" #include "phy.h" #include "workarounds.h" -/* Falcon hardware control. - * Falcon is the internal codename for the SFC4000 controller that is - * present in SFE400X evaluation boards - */ - -/************************************************************************** - * - * Configurable values - * - ************************************************************************** - */ - -static int disable_dma_stats; - -/* This is set to 16 for a good reason. In summary, if larger than - * 16, the descriptor cache holds more than a default socket - * buffer's worth of packets (for UDP we can only have at most one - * socket buffer's worth outstanding). This combined with the fact - * that we only get 1 TX event per descriptor cache means the NIC - * goes idle. - */ -#define TX_DC_ENTRIES 16 -#define TX_DC_ENTRIES_ORDER 0 -#define TX_DC_BASE 0x130000 - -#define RX_DC_ENTRIES 64 -#define RX_DC_ENTRIES_ORDER 2 -#define RX_DC_BASE 0x100000 +/* Hardware control for SFC4000 (aka Falcon). */ static const unsigned int /* "Large" EEPROM device: Atmel AT25640 or similar @@ -70,90 +43,6 @@ default_flash_type = ((17 << SPI_DEV_TYPE_SIZE_LBN) | (15 << SPI_DEV_TYPE_ERASE_SIZE_LBN) | (8 << SPI_DEV_TYPE_BLOCK_SIZE_LBN)); -/* RX FIFO XOFF watermark - * - * When the amount of the RX FIFO increases used increases past this - * watermark send XOFF. Only used if RX flow control is enabled (ethtool -A) - * This also has an effect on RX/TX arbitration - */ -static int rx_xoff_thresh_bytes = -1; -module_param(rx_xoff_thresh_bytes, int, 0644); -MODULE_PARM_DESC(rx_xoff_thresh_bytes, "RX fifo XOFF threshold"); - -/* RX FIFO XON watermark - * - * When the amount of the RX FIFO used decreases below this - * watermark send XON. Only used if TX flow control is enabled (ethtool -A) - * This also has an effect on RX/TX arbitration - */ -static int rx_xon_thresh_bytes = -1; -module_param(rx_xon_thresh_bytes, int, 0644); -MODULE_PARM_DESC(rx_xon_thresh_bytes, "RX fifo XON threshold"); - -/* If FALCON_MAX_INT_ERRORS internal errors occur within - * FALCON_INT_ERROR_EXPIRE seconds, we consider the NIC broken and - * disable it. - */ -#define FALCON_INT_ERROR_EXPIRE 3600 -#define FALCON_MAX_INT_ERRORS 5 - -/* We poll for events every FLUSH_INTERVAL ms, and check FLUSH_POLL_COUNT times - */ -#define FALCON_FLUSH_INTERVAL 10 -#define FALCON_FLUSH_POLL_COUNT 100 - -/************************************************************************** - * - * Falcon constants - * - ************************************************************************** - */ - -/* Size and alignment of special buffers (4KB) */ -#define FALCON_BUF_SIZE 4096 - -/* Dummy SRAM size code */ -#define SRM_NB_BSZ_ONCHIP_ONLY (-1) - -#define FALCON_IS_DUAL_FUNC(efx) \ - (falcon_rev(efx) < FALCON_REV_B0) - -/************************************************************************** - * - * Falcon hardware access - * - **************************************************************************/ - -static inline void falcon_write_buf_tbl(struct efx_nic *efx, efx_qword_t *value, - unsigned int index) -{ - efx_sram_writeq(efx, efx->membase + efx->type->buf_tbl_base, - value, index); -} - -/* Read the current event from the event queue */ -static inline efx_qword_t *falcon_event(struct efx_channel *channel, - unsigned int index) -{ - return (((efx_qword_t *) (channel->eventq.addr)) + index); -} - -/* See if an event is present - * - * We check both the high and low dword of the event for all ones. We - * wrote all ones when we cleared the event, and no valid event can - * have all ones in either its high or low dwords. This approach is - * robust against reordering. - * - * Note that using a single 64-bit comparison is incorrect; even - * though the CPU read will be atomic, the DMA write may not be. - */ -static inline int falcon_event_present(efx_qword_t *event) -{ - return (!(EFX_DWORD_IS_ALL_ONES(event->dword[0]) | - EFX_DWORD_IS_ALL_ONES(event->dword[1]))); -} - /************************************************************************** * * I2C bus - this is a bit-bashing interface using GPIO pins @@ -210,843 +99,7 @@ static struct i2c_algo_bit_data falcon_i2c_bit_operations = { .timeout = DIV_ROUND_UP(HZ, 20), }; -/************************************************************************** - * - * Falcon special buffer handling - * Special buffers are used for event queues and the TX and RX - * descriptor rings. - * - *************************************************************************/ - -/* - * Initialise a Falcon special buffer - * - * This will define a buffer (previously allocated via - * falcon_alloc_special_buffer()) in Falcon's buffer table, allowing - * it to be used for event queues, descriptor rings etc. - */ -static void -falcon_init_special_buffer(struct efx_nic *efx, - struct efx_special_buffer *buffer) -{ - efx_qword_t buf_desc; - int index; - dma_addr_t dma_addr; - int i; - - EFX_BUG_ON_PARANOID(!buffer->addr); - - /* Write buffer descriptors to NIC */ - for (i = 0; i < buffer->entries; i++) { - index = buffer->index + i; - dma_addr = buffer->dma_addr + (i * 4096); - EFX_LOG(efx, "mapping special buffer %d at %llx\n", - index, (unsigned long long)dma_addr); - EFX_POPULATE_QWORD_3(buf_desc, - FRF_AZ_BUF_ADR_REGION, 0, - FRF_AZ_BUF_ADR_FBUF, dma_addr >> 12, - FRF_AZ_BUF_OWNER_ID_FBUF, 0); - falcon_write_buf_tbl(efx, &buf_desc, index); - } -} - -/* Unmaps a buffer from Falcon and clears the buffer table entries */ -static void -falcon_fini_special_buffer(struct efx_nic *efx, - struct efx_special_buffer *buffer) -{ - efx_oword_t buf_tbl_upd; - unsigned int start = buffer->index; - unsigned int end = (buffer->index + buffer->entries - 1); - - if (!buffer->entries) - return; - - EFX_LOG(efx, "unmapping special buffers %d-%d\n", - buffer->index, buffer->index + buffer->entries - 1); - - EFX_POPULATE_OWORD_4(buf_tbl_upd, - FRF_AZ_BUF_UPD_CMD, 0, - FRF_AZ_BUF_CLR_CMD, 1, - FRF_AZ_BUF_CLR_END_ID, end, - FRF_AZ_BUF_CLR_START_ID, start); - efx_writeo(efx, &buf_tbl_upd, FR_AZ_BUF_TBL_UPD); -} - -/* - * Allocate a new Falcon special buffer - * - * This allocates memory for a new buffer, clears it and allocates a - * new buffer ID range. It does not write into Falcon's buffer table. - * - * This call will allocate 4KB buffers, since Falcon can't use 8KB - * buffers for event queues and descriptor rings. - */ -static int falcon_alloc_special_buffer(struct efx_nic *efx, - struct efx_special_buffer *buffer, - unsigned int len) -{ - len = ALIGN(len, FALCON_BUF_SIZE); - - buffer->addr = pci_alloc_consistent(efx->pci_dev, len, - &buffer->dma_addr); - if (!buffer->addr) - return -ENOMEM; - buffer->len = len; - buffer->entries = len / FALCON_BUF_SIZE; - BUG_ON(buffer->dma_addr & (FALCON_BUF_SIZE - 1)); - - /* All zeros is a potentially valid event so memset to 0xff */ - memset(buffer->addr, 0xff, len); - - /* Select new buffer ID */ - buffer->index = efx->next_buffer_table; - efx->next_buffer_table += buffer->entries; - - EFX_LOG(efx, "allocating special buffers %d-%d at %llx+%x " - "(virt %p phys %llx)\n", buffer->index, - buffer->index + buffer->entries - 1, - (u64)buffer->dma_addr, len, - buffer->addr, (u64)virt_to_phys(buffer->addr)); - - return 0; -} - -static void falcon_free_special_buffer(struct efx_nic *efx, - struct efx_special_buffer *buffer) -{ - if (!buffer->addr) - return; - - EFX_LOG(efx, "deallocating special buffers %d-%d at %llx+%x " - "(virt %p phys %llx)\n", buffer->index, - buffer->index + buffer->entries - 1, - (u64)buffer->dma_addr, buffer->len, - buffer->addr, (u64)virt_to_phys(buffer->addr)); - - pci_free_consistent(efx->pci_dev, buffer->len, buffer->addr, - buffer->dma_addr); - buffer->addr = NULL; - buffer->entries = 0; -} - -/************************************************************************** - * - * Falcon generic buffer handling - * These buffers are used for interrupt status and MAC stats - * - **************************************************************************/ - -static int falcon_alloc_buffer(struct efx_nic *efx, - struct efx_buffer *buffer, unsigned int len) -{ - buffer->addr = pci_alloc_consistent(efx->pci_dev, len, - &buffer->dma_addr); - if (!buffer->addr) - return -ENOMEM; - buffer->len = len; - memset(buffer->addr, 0, len); - return 0; -} - -static void falcon_free_buffer(struct efx_nic *efx, struct efx_buffer *buffer) -{ - if (buffer->addr) { - pci_free_consistent(efx->pci_dev, buffer->len, - buffer->addr, buffer->dma_addr); - buffer->addr = NULL; - } -} - -/************************************************************************** - * - * Falcon TX path - * - **************************************************************************/ - -/* Returns a pointer to the specified transmit descriptor in the TX - * descriptor queue belonging to the specified channel. - */ -static inline efx_qword_t *falcon_tx_desc(struct efx_tx_queue *tx_queue, - unsigned int index) -{ - return (((efx_qword_t *) (tx_queue->txd.addr)) + index); -} - -/* This writes to the TX_DESC_WPTR; write pointer for TX descriptor ring */ -static inline void falcon_notify_tx_desc(struct efx_tx_queue *tx_queue) -{ - unsigned write_ptr; - efx_dword_t reg; - - write_ptr = tx_queue->write_count & EFX_TXQ_MASK; - EFX_POPULATE_DWORD_1(reg, FRF_AZ_TX_DESC_WPTR_DWORD, write_ptr); - efx_writed_page(tx_queue->efx, ®, - FR_AZ_TX_DESC_UPD_DWORD_P0, tx_queue->queue); -} - - -/* For each entry inserted into the software descriptor ring, create a - * descriptor in the hardware TX descriptor ring (in host memory), and - * write a doorbell. - */ -void falcon_push_buffers(struct efx_tx_queue *tx_queue) -{ - - struct efx_tx_buffer *buffer; - efx_qword_t *txd; - unsigned write_ptr; - - BUG_ON(tx_queue->write_count == tx_queue->insert_count); - - do { - write_ptr = tx_queue->write_count & EFX_TXQ_MASK; - buffer = &tx_queue->buffer[write_ptr]; - txd = falcon_tx_desc(tx_queue, write_ptr); - ++tx_queue->write_count; - - /* Create TX descriptor ring entry */ - EFX_POPULATE_QWORD_4(*txd, - FSF_AZ_TX_KER_CONT, buffer->continuation, - FSF_AZ_TX_KER_BYTE_COUNT, buffer->len, - FSF_AZ_TX_KER_BUF_REGION, 0, - FSF_AZ_TX_KER_BUF_ADDR, buffer->dma_addr); - } while (tx_queue->write_count != tx_queue->insert_count); - - wmb(); /* Ensure descriptors are written before they are fetched */ - falcon_notify_tx_desc(tx_queue); -} - -/* Allocate hardware resources for a TX queue */ -int falcon_probe_tx(struct efx_tx_queue *tx_queue) -{ - struct efx_nic *efx = tx_queue->efx; - BUILD_BUG_ON(EFX_TXQ_SIZE < 512 || EFX_TXQ_SIZE > 4096 || - EFX_TXQ_SIZE & EFX_TXQ_MASK); - return falcon_alloc_special_buffer(efx, &tx_queue->txd, - EFX_TXQ_SIZE * sizeof(efx_qword_t)); -} - -void falcon_init_tx(struct efx_tx_queue *tx_queue) -{ - efx_oword_t tx_desc_ptr; - struct efx_nic *efx = tx_queue->efx; - - tx_queue->flushed = false; - - /* Pin TX descriptor ring */ - falcon_init_special_buffer(efx, &tx_queue->txd); - - /* Push TX descriptor ring to card */ - EFX_POPULATE_OWORD_10(tx_desc_ptr, - FRF_AZ_TX_DESCQ_EN, 1, - FRF_AZ_TX_ISCSI_DDIG_EN, 0, - FRF_AZ_TX_ISCSI_HDIG_EN, 0, - FRF_AZ_TX_DESCQ_BUF_BASE_ID, tx_queue->txd.index, - FRF_AZ_TX_DESCQ_EVQ_ID, - tx_queue->channel->channel, - FRF_AZ_TX_DESCQ_OWNER_ID, 0, - FRF_AZ_TX_DESCQ_LABEL, tx_queue->queue, - FRF_AZ_TX_DESCQ_SIZE, - __ffs(tx_queue->txd.entries), - FRF_AZ_TX_DESCQ_TYPE, 0, - FRF_BZ_TX_NON_IP_DROP_DIS, 1); - - if (falcon_rev(efx) >= FALCON_REV_B0) { - int csum = tx_queue->queue == EFX_TX_QUEUE_OFFLOAD_CSUM; - EFX_SET_OWORD_FIELD(tx_desc_ptr, FRF_BZ_TX_IP_CHKSM_DIS, !csum); - EFX_SET_OWORD_FIELD(tx_desc_ptr, FRF_BZ_TX_TCP_CHKSM_DIS, - !csum); - } - - efx_writeo_table(efx, &tx_desc_ptr, efx->type->txd_ptr_tbl_base, - tx_queue->queue); - - if (falcon_rev(efx) < FALCON_REV_B0) { - efx_oword_t reg; - - /* Only 128 bits in this register */ - BUILD_BUG_ON(EFX_TX_QUEUE_COUNT >= 128); - - efx_reado(efx, ®, FR_AA_TX_CHKSM_CFG); - if (tx_queue->queue == EFX_TX_QUEUE_OFFLOAD_CSUM) - clear_bit_le(tx_queue->queue, (void *)®); - else - set_bit_le(tx_queue->queue, (void *)®); - efx_writeo(efx, ®, FR_AA_TX_CHKSM_CFG); - } -} - -static void falcon_flush_tx_queue(struct efx_tx_queue *tx_queue) -{ - struct efx_nic *efx = tx_queue->efx; - efx_oword_t tx_flush_descq; - - /* Post a flush command */ - EFX_POPULATE_OWORD_2(tx_flush_descq, - FRF_AZ_TX_FLUSH_DESCQ_CMD, 1, - FRF_AZ_TX_FLUSH_DESCQ, tx_queue->queue); - efx_writeo(efx, &tx_flush_descq, FR_AZ_TX_FLUSH_DESCQ); -} - -void falcon_fini_tx(struct efx_tx_queue *tx_queue) -{ - struct efx_nic *efx = tx_queue->efx; - efx_oword_t tx_desc_ptr; - - /* The queue should have been flushed */ - WARN_ON(!tx_queue->flushed); - - /* Remove TX descriptor ring from card */ - EFX_ZERO_OWORD(tx_desc_ptr); - efx_writeo_table(efx, &tx_desc_ptr, efx->type->txd_ptr_tbl_base, - tx_queue->queue); - - /* Unpin TX descriptor ring */ - falcon_fini_special_buffer(efx, &tx_queue->txd); -} - -/* Free buffers backing TX queue */ -void falcon_remove_tx(struct efx_tx_queue *tx_queue) -{ - falcon_free_special_buffer(tx_queue->efx, &tx_queue->txd); -} - -/************************************************************************** - * - * Falcon RX path - * - **************************************************************************/ - -/* Returns a pointer to the specified descriptor in the RX descriptor queue */ -static inline efx_qword_t *falcon_rx_desc(struct efx_rx_queue *rx_queue, - unsigned int index) -{ - return (((efx_qword_t *) (rx_queue->rxd.addr)) + index); -} - -/* This creates an entry in the RX descriptor queue */ -static inline void falcon_build_rx_desc(struct efx_rx_queue *rx_queue, - unsigned index) -{ - struct efx_rx_buffer *rx_buf; - efx_qword_t *rxd; - - rxd = falcon_rx_desc(rx_queue, index); - rx_buf = efx_rx_buffer(rx_queue, index); - EFX_POPULATE_QWORD_3(*rxd, - FSF_AZ_RX_KER_BUF_SIZE, - rx_buf->len - - rx_queue->efx->type->rx_buffer_padding, - FSF_AZ_RX_KER_BUF_REGION, 0, - FSF_AZ_RX_KER_BUF_ADDR, rx_buf->dma_addr); -} - -/* This writes to the RX_DESC_WPTR register for the specified receive - * descriptor ring. - */ -void falcon_notify_rx_desc(struct efx_rx_queue *rx_queue) -{ - efx_dword_t reg; - unsigned write_ptr; - - while (rx_queue->notified_count != rx_queue->added_count) { - falcon_build_rx_desc(rx_queue, - rx_queue->notified_count & - EFX_RXQ_MASK); - ++rx_queue->notified_count; - } - - wmb(); - write_ptr = rx_queue->added_count & EFX_RXQ_MASK; - EFX_POPULATE_DWORD_1(reg, FRF_AZ_RX_DESC_WPTR_DWORD, write_ptr); - efx_writed_page(rx_queue->efx, ®, - FR_AZ_RX_DESC_UPD_DWORD_P0, rx_queue->queue); -} - -int falcon_probe_rx(struct efx_rx_queue *rx_queue) -{ - struct efx_nic *efx = rx_queue->efx; - BUILD_BUG_ON(EFX_RXQ_SIZE < 512 || EFX_RXQ_SIZE > 4096 || - EFX_RXQ_SIZE & EFX_RXQ_MASK); - return falcon_alloc_special_buffer(efx, &rx_queue->rxd, - EFX_RXQ_SIZE * sizeof(efx_qword_t)); -} - -void falcon_init_rx(struct efx_rx_queue *rx_queue) -{ - efx_oword_t rx_desc_ptr; - struct efx_nic *efx = rx_queue->efx; - bool is_b0 = falcon_rev(efx) >= FALCON_REV_B0; - bool iscsi_digest_en = is_b0; - - EFX_LOG(efx, "RX queue %d ring in special buffers %d-%d\n", - rx_queue->queue, rx_queue->rxd.index, - rx_queue->rxd.index + rx_queue->rxd.entries - 1); - - rx_queue->flushed = false; - - /* Pin RX descriptor ring */ - falcon_init_special_buffer(efx, &rx_queue->rxd); - - /* Push RX descriptor ring to card */ - EFX_POPULATE_OWORD_10(rx_desc_ptr, - FRF_AZ_RX_ISCSI_DDIG_EN, iscsi_digest_en, - FRF_AZ_RX_ISCSI_HDIG_EN, iscsi_digest_en, - FRF_AZ_RX_DESCQ_BUF_BASE_ID, rx_queue->rxd.index, - FRF_AZ_RX_DESCQ_EVQ_ID, - rx_queue->channel->channel, - FRF_AZ_RX_DESCQ_OWNER_ID, 0, - FRF_AZ_RX_DESCQ_LABEL, rx_queue->queue, - FRF_AZ_RX_DESCQ_SIZE, - __ffs(rx_queue->rxd.entries), - FRF_AZ_RX_DESCQ_TYPE, 0 /* kernel queue */ , - /* For >=B0 this is scatter so disable */ - FRF_AZ_RX_DESCQ_JUMBO, !is_b0, - FRF_AZ_RX_DESCQ_EN, 1); - efx_writeo_table(efx, &rx_desc_ptr, efx->type->rxd_ptr_tbl_base, - rx_queue->queue); -} - -static void falcon_flush_rx_queue(struct efx_rx_queue *rx_queue) -{ - struct efx_nic *efx = rx_queue->efx; - efx_oword_t rx_flush_descq; - - /* Post a flush command */ - EFX_POPULATE_OWORD_2(rx_flush_descq, - FRF_AZ_RX_FLUSH_DESCQ_CMD, 1, - FRF_AZ_RX_FLUSH_DESCQ, rx_queue->queue); - efx_writeo(efx, &rx_flush_descq, FR_AZ_RX_FLUSH_DESCQ); -} - -void falcon_fini_rx(struct efx_rx_queue *rx_queue) -{ - efx_oword_t rx_desc_ptr; - struct efx_nic *efx = rx_queue->efx; - - /* The queue should already have been flushed */ - WARN_ON(!rx_queue->flushed); - - /* Remove RX descriptor ring from card */ - EFX_ZERO_OWORD(rx_desc_ptr); - efx_writeo_table(efx, &rx_desc_ptr, efx->type->rxd_ptr_tbl_base, - rx_queue->queue); - - /* Unpin RX descriptor ring */ - falcon_fini_special_buffer(efx, &rx_queue->rxd); -} - -/* Free buffers backing RX queue */ -void falcon_remove_rx(struct efx_rx_queue *rx_queue) -{ - falcon_free_special_buffer(rx_queue->efx, &rx_queue->rxd); -} - -/************************************************************************** - * - * Falcon event queue processing - * Event queues are processed by per-channel tasklets. - * - **************************************************************************/ - -/* Update a channel's event queue's read pointer (RPTR) register - * - * This writes the EVQ_RPTR_REG register for the specified channel's - * event queue. - * - * Note that EVQ_RPTR_REG contains the index of the "last read" event, - * whereas channel->eventq_read_ptr contains the index of the "next to - * read" event. - */ -void falcon_eventq_read_ack(struct efx_channel *channel) -{ - efx_dword_t reg; - struct efx_nic *efx = channel->efx; - - EFX_POPULATE_DWORD_1(reg, FRF_AZ_EVQ_RPTR, channel->eventq_read_ptr); - efx_writed_table(efx, ®, efx->type->evq_rptr_tbl_base, - channel->channel); -} - -/* Use HW to insert a SW defined event */ -void falcon_generate_event(struct efx_channel *channel, efx_qword_t *event) -{ - efx_oword_t drv_ev_reg; - - BUILD_BUG_ON(FRF_AZ_DRV_EV_DATA_LBN != 0 || - FRF_AZ_DRV_EV_DATA_WIDTH != 64); - drv_ev_reg.u32[0] = event->u32[0]; - drv_ev_reg.u32[1] = event->u32[1]; - drv_ev_reg.u32[2] = 0; - drv_ev_reg.u32[3] = 0; - EFX_SET_OWORD_FIELD(drv_ev_reg, FRF_AZ_DRV_EV_QID, channel->channel); - efx_writeo(channel->efx, &drv_ev_reg, FR_AZ_DRV_EV); -} - -/* Handle a transmit completion event - * - * Falcon batches TX completion events; the message we receive is of - * the form "complete all TX events up to this index". - */ -static void falcon_handle_tx_event(struct efx_channel *channel, - efx_qword_t *event) -{ - unsigned int tx_ev_desc_ptr; - unsigned int tx_ev_q_label; - struct efx_tx_queue *tx_queue; - struct efx_nic *efx = channel->efx; - - if (likely(EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_COMP))) { - /* Transmit completion */ - tx_ev_desc_ptr = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_DESC_PTR); - tx_ev_q_label = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_Q_LABEL); - tx_queue = &efx->tx_queue[tx_ev_q_label]; - channel->irq_mod_score += - (tx_ev_desc_ptr - tx_queue->read_count) & - EFX_TXQ_MASK; - efx_xmit_done(tx_queue, tx_ev_desc_ptr); - } else if (EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_WQ_FF_FULL)) { - /* Rewrite the FIFO write pointer */ - tx_ev_q_label = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_Q_LABEL); - tx_queue = &efx->tx_queue[tx_ev_q_label]; - - if (efx_dev_registered(efx)) - netif_tx_lock(efx->net_dev); - falcon_notify_tx_desc(tx_queue); - if (efx_dev_registered(efx)) - netif_tx_unlock(efx->net_dev); - } else if (EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_PKT_ERR) && - EFX_WORKAROUND_10727(efx)) { - efx_schedule_reset(efx, RESET_TYPE_TX_DESC_FETCH); - } else { - EFX_ERR(efx, "channel %d unexpected TX event " - EFX_QWORD_FMT"\n", channel->channel, - EFX_QWORD_VAL(*event)); - } -} - -/* Detect errors included in the rx_evt_pkt_ok bit. */ -static void falcon_handle_rx_not_ok(struct efx_rx_queue *rx_queue, - const efx_qword_t *event, - bool *rx_ev_pkt_ok, - bool *discard) -{ - struct efx_nic *efx = rx_queue->efx; - bool rx_ev_buf_owner_id_err, rx_ev_ip_hdr_chksum_err; - bool rx_ev_tcp_udp_chksum_err, rx_ev_eth_crc_err; - bool rx_ev_frm_trunc, rx_ev_drib_nib, rx_ev_tobe_disc; - bool rx_ev_other_err, rx_ev_pause_frm; - bool rx_ev_ip_frag_err, rx_ev_hdr_type, rx_ev_mcast_pkt; - unsigned rx_ev_pkt_type; - - rx_ev_hdr_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_HDR_TYPE); - rx_ev_mcast_pkt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_PKT); - rx_ev_tobe_disc = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_TOBE_DISC); - rx_ev_pkt_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PKT_TYPE); - rx_ev_buf_owner_id_err = EFX_QWORD_FIELD(*event, - FSF_AZ_RX_EV_BUF_OWNER_ID_ERR); - rx_ev_ip_frag_err = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_IP_FRAG_ERR); - rx_ev_ip_hdr_chksum_err = EFX_QWORD_FIELD(*event, - FSF_AZ_RX_EV_IP_HDR_CHKSUM_ERR); - rx_ev_tcp_udp_chksum_err = EFX_QWORD_FIELD(*event, - FSF_AZ_RX_EV_TCP_UDP_CHKSUM_ERR); - rx_ev_eth_crc_err = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_ETH_CRC_ERR); - rx_ev_frm_trunc = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_FRM_TRUNC); - rx_ev_drib_nib = ((falcon_rev(efx) >= FALCON_REV_B0) ? - 0 : EFX_QWORD_FIELD(*event, FSF_AA_RX_EV_DRIB_NIB)); - rx_ev_pause_frm = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PAUSE_FRM_ERR); - - /* Every error apart from tobe_disc and pause_frm */ - rx_ev_other_err = (rx_ev_drib_nib | rx_ev_tcp_udp_chksum_err | - rx_ev_buf_owner_id_err | rx_ev_eth_crc_err | - rx_ev_frm_trunc | rx_ev_ip_hdr_chksum_err); - - /* Count errors that are not in MAC stats. Ignore expected - * checksum errors during self-test. */ - if (rx_ev_frm_trunc) - ++rx_queue->channel->n_rx_frm_trunc; - else if (rx_ev_tobe_disc) - ++rx_queue->channel->n_rx_tobe_disc; - else if (!efx->loopback_selftest) { - if (rx_ev_ip_hdr_chksum_err) - ++rx_queue->channel->n_rx_ip_hdr_chksum_err; - else if (rx_ev_tcp_udp_chksum_err) - ++rx_queue->channel->n_rx_tcp_udp_chksum_err; - } - if (rx_ev_ip_frag_err) - ++rx_queue->channel->n_rx_ip_frag_err; - - /* The frame must be discarded if any of these are true. */ - *discard = (rx_ev_eth_crc_err | rx_ev_frm_trunc | rx_ev_drib_nib | - rx_ev_tobe_disc | rx_ev_pause_frm); - - /* TOBE_DISC is expected on unicast mismatches; don't print out an - * error message. FRM_TRUNC indicates RXDP dropped the packet due - * to a FIFO overflow. - */ -#ifdef EFX_ENABLE_DEBUG - if (rx_ev_other_err) { - EFX_INFO_RL(efx, " RX queue %d unexpected RX event " - EFX_QWORD_FMT "%s%s%s%s%s%s%s%s\n", - rx_queue->queue, EFX_QWORD_VAL(*event), - rx_ev_buf_owner_id_err ? " [OWNER_ID_ERR]" : "", - rx_ev_ip_hdr_chksum_err ? - " [IP_HDR_CHKSUM_ERR]" : "", - rx_ev_tcp_udp_chksum_err ? - " [TCP_UDP_CHKSUM_ERR]" : "", - rx_ev_eth_crc_err ? " [ETH_CRC_ERR]" : "", - rx_ev_frm_trunc ? " [FRM_TRUNC]" : "", - rx_ev_drib_nib ? " [DRIB_NIB]" : "", - rx_ev_tobe_disc ? " [TOBE_DISC]" : "", - rx_ev_pause_frm ? " [PAUSE]" : ""); - } -#endif -} - -/* Handle receive events that are not in-order. */ -static void falcon_handle_rx_bad_index(struct efx_rx_queue *rx_queue, - unsigned index) -{ - struct efx_nic *efx = rx_queue->efx; - unsigned expected, dropped; - - expected = rx_queue->removed_count & EFX_RXQ_MASK; - dropped = (index - expected) & EFX_RXQ_MASK; - EFX_INFO(efx, "dropped %d events (index=%d expected=%d)\n", - dropped, index, expected); - - efx_schedule_reset(efx, EFX_WORKAROUND_5676(efx) ? - RESET_TYPE_RX_RECOVERY : RESET_TYPE_DISABLE); -} - -/* Handle a packet received event - * - * Falcon silicon gives a "discard" flag if it's a unicast packet with the - * wrong destination address - * Also "is multicast" and "matches multicast filter" flags can be used to - * discard non-matching multicast packets. - */ -static void falcon_handle_rx_event(struct efx_channel *channel, - const efx_qword_t *event) -{ - unsigned int rx_ev_desc_ptr, rx_ev_byte_cnt; - unsigned int rx_ev_hdr_type, rx_ev_mcast_pkt; - unsigned expected_ptr; - bool rx_ev_pkt_ok, discard = false, checksummed; - struct efx_rx_queue *rx_queue; - struct efx_nic *efx = channel->efx; - - /* Basic packet information */ - rx_ev_byte_cnt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_BYTE_CNT); - rx_ev_pkt_ok = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PKT_OK); - rx_ev_hdr_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_HDR_TYPE); - WARN_ON(EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_JUMBO_CONT)); - WARN_ON(EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_SOP) != 1); - WARN_ON(EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_Q_LABEL) != - channel->channel); - - rx_queue = &efx->rx_queue[channel->channel]; - - rx_ev_desc_ptr = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_DESC_PTR); - expected_ptr = rx_queue->removed_count & EFX_RXQ_MASK; - if (unlikely(rx_ev_desc_ptr != expected_ptr)) - falcon_handle_rx_bad_index(rx_queue, rx_ev_desc_ptr); - - if (likely(rx_ev_pkt_ok)) { - /* If packet is marked as OK and packet type is TCP/IPv4 or - * UDP/IPv4, then we can rely on the hardware checksum. - */ - checksummed = - efx->rx_checksum_enabled && - (rx_ev_hdr_type == FSE_AB_RX_EV_HDR_TYPE_IPV4_TCP || - rx_ev_hdr_type == FSE_AB_RX_EV_HDR_TYPE_IPV4_UDP); - } else { - falcon_handle_rx_not_ok(rx_queue, event, &rx_ev_pkt_ok, - &discard); - checksummed = false; - } - - /* Detect multicast packets that didn't match the filter */ - rx_ev_mcast_pkt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_PKT); - if (rx_ev_mcast_pkt) { - unsigned int rx_ev_mcast_hash_match = - EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_HASH_MATCH); - - if (unlikely(!rx_ev_mcast_hash_match)) - discard = true; - } - - channel->irq_mod_score += 2; - - /* Handle received packet */ - efx_rx_packet(rx_queue, rx_ev_desc_ptr, rx_ev_byte_cnt, - checksummed, discard); -} - -/* Global events are basically PHY events */ -static void falcon_handle_global_event(struct efx_channel *channel, - efx_qword_t *event) -{ - struct efx_nic *efx = channel->efx; - bool handled = false; - - if (EFX_QWORD_FIELD(*event, FSF_AB_GLB_EV_G_PHY0_INTR) || - EFX_QWORD_FIELD(*event, FSF_AB_GLB_EV_XG_PHY0_INTR) || - EFX_QWORD_FIELD(*event, FSF_AB_GLB_EV_XFP_PHY0_INTR)) { - efx->phy_op->clear_interrupt(efx); - queue_work(efx->workqueue, &efx->phy_work); - handled = true; - } - - if ((falcon_rev(efx) >= FALCON_REV_B0) && - EFX_QWORD_FIELD(*event, FSF_BB_GLB_EV_XG_MGT_INTR)) { - queue_work(efx->workqueue, &efx->mac_work); - handled = true; - } - - if (falcon_rev(efx) <= FALCON_REV_A1 ? - EFX_QWORD_FIELD(*event, FSF_AA_GLB_EV_RX_RECOVERY) : - EFX_QWORD_FIELD(*event, FSF_BB_GLB_EV_RX_RECOVERY)) { - EFX_ERR(efx, "channel %d seen global RX_RESET " - "event. Resetting.\n", channel->channel); - - atomic_inc(&efx->rx_reset); - efx_schedule_reset(efx, EFX_WORKAROUND_6555(efx) ? - RESET_TYPE_RX_RECOVERY : RESET_TYPE_DISABLE); - handled = true; - } - - if (!handled) - EFX_ERR(efx, "channel %d unknown global event " - EFX_QWORD_FMT "\n", channel->channel, - EFX_QWORD_VAL(*event)); -} - -static void falcon_handle_driver_event(struct efx_channel *channel, - efx_qword_t *event) -{ - struct efx_nic *efx = channel->efx; - unsigned int ev_sub_code; - unsigned int ev_sub_data; - - ev_sub_code = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_SUBCODE); - ev_sub_data = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_SUBDATA); - - switch (ev_sub_code) { - case FSE_AZ_TX_DESCQ_FLS_DONE_EV: - EFX_TRACE(efx, "channel %d TXQ %d flushed\n", - channel->channel, ev_sub_data); - break; - case FSE_AZ_RX_DESCQ_FLS_DONE_EV: - EFX_TRACE(efx, "channel %d RXQ %d flushed\n", - channel->channel, ev_sub_data); - break; - case FSE_AZ_EVQ_INIT_DONE_EV: - EFX_LOG(efx, "channel %d EVQ %d initialised\n", - channel->channel, ev_sub_data); - break; - case FSE_AZ_SRM_UPD_DONE_EV: - EFX_TRACE(efx, "channel %d SRAM update done\n", - channel->channel); - break; - case FSE_AZ_WAKE_UP_EV: - EFX_TRACE(efx, "channel %d RXQ %d wakeup event\n", - channel->channel, ev_sub_data); - break; - case FSE_AZ_TIMER_EV: - EFX_TRACE(efx, "channel %d RX queue %d timer expired\n", - channel->channel, ev_sub_data); - break; - case FSE_AA_RX_RECOVER_EV: - EFX_ERR(efx, "channel %d seen DRIVER RX_RESET event. " - "Resetting.\n", channel->channel); - atomic_inc(&efx->rx_reset); - efx_schedule_reset(efx, - EFX_WORKAROUND_6555(efx) ? - RESET_TYPE_RX_RECOVERY : - RESET_TYPE_DISABLE); - break; - case FSE_BZ_RX_DSC_ERROR_EV: - EFX_ERR(efx, "RX DMA Q %d reports descriptor fetch error." - " RX Q %d is disabled.\n", ev_sub_data, ev_sub_data); - efx_schedule_reset(efx, RESET_TYPE_RX_DESC_FETCH); - break; - case FSE_BZ_TX_DSC_ERROR_EV: - EFX_ERR(efx, "TX DMA Q %d reports descriptor fetch error." - " TX Q %d is disabled.\n", ev_sub_data, ev_sub_data); - efx_schedule_reset(efx, RESET_TYPE_TX_DESC_FETCH); - break; - default: - EFX_TRACE(efx, "channel %d unknown driver event code %d " - "data %04x\n", channel->channel, ev_sub_code, - ev_sub_data); - break; - } -} - -int falcon_process_eventq(struct efx_channel *channel, int rx_quota) -{ - unsigned int read_ptr; - efx_qword_t event, *p_event; - int ev_code; - int rx_packets = 0; - - read_ptr = channel->eventq_read_ptr; - - do { - p_event = falcon_event(channel, read_ptr); - event = *p_event; - - if (!falcon_event_present(&event)) - /* End of events */ - break; - - EFX_TRACE(channel->efx, "channel %d event is "EFX_QWORD_FMT"\n", - channel->channel, EFX_QWORD_VAL(event)); - - /* Clear this event by marking it all ones */ - EFX_SET_QWORD(*p_event); - - ev_code = EFX_QWORD_FIELD(event, FSF_AZ_EV_CODE); - - switch (ev_code) { - case FSE_AZ_EV_CODE_RX_EV: - falcon_handle_rx_event(channel, &event); - ++rx_packets; - break; - case FSE_AZ_EV_CODE_TX_EV: - falcon_handle_tx_event(channel, &event); - break; - case FSE_AZ_EV_CODE_DRV_GEN_EV: - channel->eventq_magic = EFX_QWORD_FIELD( - event, FSF_AZ_DRV_GEN_EV_MAGIC); - EFX_LOG(channel->efx, "channel %d received generated " - "event "EFX_QWORD_FMT"\n", channel->channel, - EFX_QWORD_VAL(event)); - break; - case FSE_AZ_EV_CODE_GLOBAL_EV: - falcon_handle_global_event(channel, &event); - break; - case FSE_AZ_EV_CODE_DRIVER_EV: - falcon_handle_driver_event(channel, &event); - break; - default: - EFX_ERR(channel->efx, "channel %d unknown event type %d" - " (data " EFX_QWORD_FMT ")\n", channel->channel, - ev_code, EFX_QWORD_VAL(event)); - } - - /* Increment read pointer */ - read_ptr = (read_ptr + 1) & EFX_EVQ_MASK; - - } while (rx_packets < rx_quota); - - channel->eventq_read_ptr = read_ptr; - return rx_packets; -} - -void falcon_set_int_moderation(struct efx_channel *channel) +static void falcon_push_irq_moderation(struct efx_channel *channel) { efx_dword_t timer_cmd; struct efx_nic *efx = channel->efx; @@ -1067,265 +120,18 @@ void falcon_set_int_moderation(struct efx_channel *channel) BUILD_BUG_ON(FR_AA_TIMER_COMMAND_KER != FR_BZ_TIMER_COMMAND_P0); efx_writed_page_locked(efx, &timer_cmd, FR_BZ_TIMER_COMMAND_P0, channel->channel); - -} - -/* Allocate buffer table entries for event queue */ -int falcon_probe_eventq(struct efx_channel *channel) -{ - struct efx_nic *efx = channel->efx; - BUILD_BUG_ON(EFX_EVQ_SIZE < 512 || EFX_EVQ_SIZE > 32768 || - EFX_EVQ_SIZE & EFX_EVQ_MASK); - return falcon_alloc_special_buffer(efx, &channel->eventq, - EFX_EVQ_SIZE * sizeof(efx_qword_t)); -} - -void falcon_init_eventq(struct efx_channel *channel) -{ - efx_oword_t evq_ptr; - struct efx_nic *efx = channel->efx; - - EFX_LOG(efx, "channel %d event queue in special buffers %d-%d\n", - channel->channel, channel->eventq.index, - channel->eventq.index + channel->eventq.entries - 1); - - /* Pin event queue buffer */ - falcon_init_special_buffer(efx, &channel->eventq); - - /* Fill event queue with all ones (i.e. empty events) */ - memset(channel->eventq.addr, 0xff, channel->eventq.len); - - /* Push event queue to card */ - EFX_POPULATE_OWORD_3(evq_ptr, - FRF_AZ_EVQ_EN, 1, - FRF_AZ_EVQ_SIZE, __ffs(channel->eventq.entries), - FRF_AZ_EVQ_BUF_BASE_ID, channel->eventq.index); - efx_writeo_table(efx, &evq_ptr, efx->type->evq_ptr_tbl_base, - channel->channel); - - falcon_set_int_moderation(channel); -} - -void falcon_fini_eventq(struct efx_channel *channel) -{ - efx_oword_t eventq_ptr; - struct efx_nic *efx = channel->efx; - - /* Remove event queue from card */ - EFX_ZERO_OWORD(eventq_ptr); - efx_writeo_table(efx, &eventq_ptr, efx->type->evq_ptr_tbl_base, - channel->channel); - - /* Unpin event queue */ - falcon_fini_special_buffer(efx, &channel->eventq); -} - -/* Free buffers backing event queue */ -void falcon_remove_eventq(struct efx_channel *channel) -{ - falcon_free_special_buffer(channel->efx, &channel->eventq); -} - - -/* Generates a test event on the event queue. A subsequent call to - * process_eventq() should pick up the event and place the value of - * "magic" into channel->eventq_magic; - */ -void falcon_generate_test_event(struct efx_channel *channel, unsigned int magic) -{ - efx_qword_t test_event; - - EFX_POPULATE_QWORD_2(test_event, FSF_AZ_EV_CODE, - FSE_AZ_EV_CODE_DRV_GEN_EV, - FSF_AZ_DRV_GEN_EV_MAGIC, magic); - falcon_generate_event(channel, &test_event); -} - -void falcon_sim_phy_event(struct efx_nic *efx) -{ - efx_qword_t phy_event; - - EFX_POPULATE_QWORD_1(phy_event, FSF_AZ_EV_CODE, - FSE_AZ_EV_CODE_GLOBAL_EV); - if (EFX_IS10G(efx)) - EFX_SET_QWORD_FIELD(phy_event, FSF_AB_GLB_EV_XG_PHY0_INTR, 1); - else - EFX_SET_QWORD_FIELD(phy_event, FSF_AB_GLB_EV_G_PHY0_INTR, 1); - - falcon_generate_event(&efx->channel[0], &phy_event); -} - -/************************************************************************** - * - * Flush handling - * - **************************************************************************/ - - -static void falcon_poll_flush_events(struct efx_nic *efx) -{ - struct efx_channel *channel = &efx->channel[0]; - struct efx_tx_queue *tx_queue; - struct efx_rx_queue *rx_queue; - unsigned int read_ptr = channel->eventq_read_ptr; - unsigned int end_ptr = (read_ptr - 1) & EFX_EVQ_MASK; - - do { - efx_qword_t *event = falcon_event(channel, read_ptr); - int ev_code, ev_sub_code, ev_queue; - bool ev_failed; - - if (!falcon_event_present(event)) - break; - - ev_code = EFX_QWORD_FIELD(*event, FSF_AZ_EV_CODE); - ev_sub_code = EFX_QWORD_FIELD(*event, - FSF_AZ_DRIVER_EV_SUBCODE); - if (ev_code == FSE_AZ_EV_CODE_DRIVER_EV && - ev_sub_code == FSE_AZ_TX_DESCQ_FLS_DONE_EV) { - ev_queue = EFX_QWORD_FIELD(*event, - FSF_AZ_DRIVER_EV_SUBDATA); - if (ev_queue < EFX_TX_QUEUE_COUNT) { - tx_queue = efx->tx_queue + ev_queue; - tx_queue->flushed = true; - } - } else if (ev_code == FSE_AZ_EV_CODE_DRIVER_EV && - ev_sub_code == FSE_AZ_RX_DESCQ_FLS_DONE_EV) { - ev_queue = EFX_QWORD_FIELD( - *event, FSF_AZ_DRIVER_EV_RX_DESCQ_ID); - ev_failed = EFX_QWORD_FIELD( - *event, FSF_AZ_DRIVER_EV_RX_FLUSH_FAIL); - if (ev_queue < efx->n_rx_queues) { - rx_queue = efx->rx_queue + ev_queue; - - /* retry the rx flush */ - if (ev_failed) - falcon_flush_rx_queue(rx_queue); - else - rx_queue->flushed = true; - } - } - - read_ptr = (read_ptr + 1) & EFX_EVQ_MASK; - } while (read_ptr != end_ptr); -} - -/* Handle tx and rx flushes at the same time, since they run in - * parallel in the hardware and there's no reason for us to - * serialise them */ -int falcon_flush_queues(struct efx_nic *efx) -{ - struct efx_rx_queue *rx_queue; - struct efx_tx_queue *tx_queue; - int i; - bool outstanding; - - /* Issue flush requests */ - efx_for_each_tx_queue(tx_queue, efx) { - tx_queue->flushed = false; - falcon_flush_tx_queue(tx_queue); - } - efx_for_each_rx_queue(rx_queue, efx) { - rx_queue->flushed = false; - falcon_flush_rx_queue(rx_queue); - } - - /* Poll the evq looking for flush completions. Since we're not pushing - * any more rx or tx descriptors at this point, we're in no danger of - * overflowing the evq whilst we wait */ - for (i = 0; i < FALCON_FLUSH_POLL_COUNT; ++i) { - msleep(FALCON_FLUSH_INTERVAL); - falcon_poll_flush_events(efx); - - /* Check if every queue has been succesfully flushed */ - outstanding = false; - efx_for_each_tx_queue(tx_queue, efx) - outstanding |= !tx_queue->flushed; - efx_for_each_rx_queue(rx_queue, efx) - outstanding |= !rx_queue->flushed; - if (!outstanding) - return 0; - } - - /* Mark the queues as all flushed. We're going to return failure - * leading to a reset, or fake up success anyway. "flushed" now - * indicates that we tried to flush. */ - efx_for_each_tx_queue(tx_queue, efx) { - if (!tx_queue->flushed) - EFX_ERR(efx, "tx queue %d flush command timed out\n", - tx_queue->queue); - tx_queue->flushed = true; - } - efx_for_each_rx_queue(rx_queue, efx) { - if (!rx_queue->flushed) - EFX_ERR(efx, "rx queue %d flush command timed out\n", - rx_queue->queue); - rx_queue->flushed = true; - } - - if (EFX_WORKAROUND_7803(efx)) - return 0; - - return -ETIMEDOUT; } -/************************************************************************** - * - * Falcon hardware interrupts - * The hardware interrupt handler does very little work; all the event - * queue processing is carried out by per-channel tasklets. - * - **************************************************************************/ +static void falcon_deconfigure_mac_wrapper(struct efx_nic *efx); -/* Enable/disable/generate Falcon interrupts */ -static inline void falcon_interrupts(struct efx_nic *efx, int enabled, - int force) +static void falcon_prepare_flush(struct efx_nic *efx) { - efx_oword_t int_en_reg_ker; + falcon_deconfigure_mac_wrapper(efx); - EFX_POPULATE_OWORD_2(int_en_reg_ker, - FRF_AZ_KER_INT_KER, force, - FRF_AZ_DRV_INT_EN_KER, enabled); - efx_writeo(efx, &int_en_reg_ker, FR_AZ_INT_EN_KER); -} - -void falcon_enable_interrupts(struct efx_nic *efx) -{ - efx_oword_t int_adr_reg_ker; - struct efx_channel *channel; - - EFX_ZERO_OWORD(*((efx_oword_t *) efx->irq_status.addr)); - wmb(); /* Ensure interrupt vector is clear before interrupts enabled */ - - /* Program address */ - EFX_POPULATE_OWORD_2(int_adr_reg_ker, - FRF_AZ_NORM_INT_VEC_DIS_KER, - EFX_INT_MODE_USE_MSI(efx), - FRF_AZ_INT_ADR_KER, efx->irq_status.dma_addr); - efx_writeo(efx, &int_adr_reg_ker, FR_AZ_INT_ADR_KER); - - /* Enable interrupts */ - falcon_interrupts(efx, 1, 0); - - /* Force processing of all the channels to get the EVQ RPTRs up to - date */ - efx_for_each_channel(channel, efx) - efx_schedule_channel(channel); -} - -void falcon_disable_interrupts(struct efx_nic *efx) -{ - /* Disable interrupts */ - falcon_interrupts(efx, 0, 0); -} - -/* Generate a Falcon test interrupt - * Interrupt must already have been enabled, otherwise nasty things - * may happen. - */ -void falcon_generate_interrupt(struct efx_nic *efx) -{ - falcon_interrupts(efx, 1, 1); + /* Wait for the tx and rx fifo's to get to the next packet boundary + * (~1ms without back-pressure), then to drain the remainder of the + * fifo's at data path speeds (negligible), with a healthy margin. */ + msleep(10); } /* Acknowledge a legacy interrupt from Falcon @@ -1338,7 +144,7 @@ void falcon_generate_interrupt(struct efx_nic *efx) * * NB most hardware supports MSI interrupts */ -static inline void falcon_irq_ack_a1(struct efx_nic *efx) +inline void falcon_irq_ack_a1(struct efx_nic *efx) { efx_dword_t reg; @@ -1347,104 +153,8 @@ static inline void falcon_irq_ack_a1(struct efx_nic *efx) efx_readd(efx, ®, FR_AA_WORK_AROUND_BROKEN_PCI_READS); } -/* Process a fatal interrupt - * Disable bus mastering ASAP and schedule a reset - */ -static irqreturn_t falcon_fatal_interrupt(struct efx_nic *efx) -{ - struct falcon_nic_data *nic_data = efx->nic_data; - efx_oword_t *int_ker = efx->irq_status.addr; - efx_oword_t fatal_intr; - int error, mem_perr; - - efx_reado(efx, &fatal_intr, FR_AZ_FATAL_INTR_KER); - error = EFX_OWORD_FIELD(fatal_intr, FRF_AZ_FATAL_INTR); - - EFX_ERR(efx, "SYSTEM ERROR " EFX_OWORD_FMT " status " - EFX_OWORD_FMT ": %s\n", EFX_OWORD_VAL(*int_ker), - EFX_OWORD_VAL(fatal_intr), - error ? "disabling bus mastering" : "no recognised error"); - if (error == 0) - goto out; - - /* If this is a memory parity error dump which blocks are offending */ - mem_perr = EFX_OWORD_FIELD(fatal_intr, FRF_AZ_MEM_PERR_INT_KER); - if (mem_perr) { - efx_oword_t reg; - efx_reado(efx, ®, FR_AZ_MEM_STAT); - EFX_ERR(efx, "SYSTEM ERROR: memory parity error " - EFX_OWORD_FMT "\n", EFX_OWORD_VAL(reg)); - } - - /* Disable both devices */ - pci_clear_master(efx->pci_dev); - if (FALCON_IS_DUAL_FUNC(efx)) - pci_clear_master(nic_data->pci_dev2); - falcon_disable_interrupts(efx); - - /* Count errors and reset or disable the NIC accordingly */ - if (efx->int_error_count == 0 || - time_after(jiffies, efx->int_error_expire)) { - efx->int_error_count = 0; - efx->int_error_expire = - jiffies + FALCON_INT_ERROR_EXPIRE * HZ; - } - if (++efx->int_error_count < FALCON_MAX_INT_ERRORS) { - EFX_ERR(efx, "SYSTEM ERROR - reset scheduled\n"); - efx_schedule_reset(efx, RESET_TYPE_INT_ERROR); - } else { - EFX_ERR(efx, "SYSTEM ERROR - max number of errors seen." - "NIC will be disabled\n"); - efx_schedule_reset(efx, RESET_TYPE_DISABLE); - } -out: - return IRQ_HANDLED; -} - -/* Handle a legacy interrupt from Falcon - * Acknowledges the interrupt and schedule event queue processing. - */ -static irqreturn_t falcon_legacy_interrupt_b0(int irq, void *dev_id) -{ - struct efx_nic *efx = dev_id; - efx_oword_t *int_ker = efx->irq_status.addr; - irqreturn_t result = IRQ_NONE; - struct efx_channel *channel; - efx_dword_t reg; - u32 queues; - int syserr; - - /* Read the ISR which also ACKs the interrupts */ - efx_readd(efx, ®, FR_BZ_INT_ISR0); - queues = EFX_EXTRACT_DWORD(reg, 0, 31); - - /* Check to see if we have a serious error condition */ - syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT); - if (unlikely(syserr)) - return falcon_fatal_interrupt(efx); - - /* Schedule processing of any interrupting queues */ - efx_for_each_channel(channel, efx) { - if ((queues & 1) || - falcon_event_present( - falcon_event(channel, channel->eventq_read_ptr))) { - efx_schedule_channel(channel); - result = IRQ_HANDLED; - } - queues >>= 1; - } - - if (result == IRQ_HANDLED) { - efx->last_irq_cpu = raw_smp_processor_id(); - EFX_TRACE(efx, "IRQ %d on CPU %d status " EFX_DWORD_FMT "\n", - irq, raw_smp_processor_id(), EFX_DWORD_VAL(reg)); - } - - return result; -} - -static irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id) +irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id) { struct efx_nic *efx = dev_id; efx_oword_t *int_ker = efx->irq_status.addr; @@ -1467,13 +177,13 @@ static irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id) /* Check to see if we have a serious error condition */ syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT); if (unlikely(syserr)) - return falcon_fatal_interrupt(efx); + return efx_nic_fatal_interrupt(efx); /* Determine interrupting queues, clear interrupt status * register and acknowledge the device interrupt. */ - BUILD_BUG_ON(INT_EVQS_WIDTH > EFX_MAX_CHANNELS); - queues = EFX_OWORD_FIELD(*int_ker, INT_EVQS); + BUILD_BUG_ON(FSF_AZ_NET_IVEC_INT_Q_WIDTH > EFX_MAX_CHANNELS); + queues = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_INT_Q); EFX_ZERO_OWORD(*int_ker); wmb(); /* Ensure the vector is cleared before interrupt ack */ falcon_irq_ack_a1(efx); @@ -1489,126 +199,6 @@ static irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id) return IRQ_HANDLED; } - -/* Handle an MSI interrupt from Falcon - * - * Handle an MSI hardware interrupt. This routine schedules event - * queue processing. No interrupt acknowledgement cycle is necessary. - * Also, we never need to check that the interrupt is for us, since - * MSI interrupts cannot be shared. - */ -static irqreturn_t falcon_msi_interrupt(int irq, void *dev_id) -{ - struct efx_channel *channel = dev_id; - struct efx_nic *efx = channel->efx; - efx_oword_t *int_ker = efx->irq_status.addr; - int syserr; - - efx->last_irq_cpu = raw_smp_processor_id(); - EFX_TRACE(efx, "IRQ %d on CPU %d status " EFX_OWORD_FMT "\n", - irq, raw_smp_processor_id(), EFX_OWORD_VAL(*int_ker)); - - /* Check to see if we have a serious error condition */ - syserr = EFX_OWORD_FIELD(*int_ker, FATAL_INT); - if (unlikely(syserr)) - return falcon_fatal_interrupt(efx); - - /* Schedule processing of the channel */ - efx_schedule_channel(channel); - - return IRQ_HANDLED; -} - - -/* Setup RSS indirection table. - * This maps from the hash value of the packet to RXQ - */ -static void falcon_setup_rss_indir_table(struct efx_nic *efx) -{ - int i = 0; - unsigned long offset; - efx_dword_t dword; - - if (falcon_rev(efx) < FALCON_REV_B0) - return; - - for (offset = FR_BZ_RX_INDIRECTION_TBL; - offset < FR_BZ_RX_INDIRECTION_TBL + 0x800; - offset += 0x10) { - EFX_POPULATE_DWORD_1(dword, FRF_BZ_IT_QUEUE, - i % efx->n_rx_queues); - efx_writed(efx, &dword, offset); - i++; - } -} - -/* Hook interrupt handler(s) - * Try MSI and then legacy interrupts. - */ -int falcon_init_interrupt(struct efx_nic *efx) -{ - struct efx_channel *channel; - int rc; - - if (!EFX_INT_MODE_USE_MSI(efx)) { - irq_handler_t handler; - if (falcon_rev(efx) >= FALCON_REV_B0) - handler = falcon_legacy_interrupt_b0; - else - handler = falcon_legacy_interrupt_a1; - - rc = request_irq(efx->legacy_irq, handler, IRQF_SHARED, - efx->name, efx); - if (rc) { - EFX_ERR(efx, "failed to hook legacy IRQ %d\n", - efx->pci_dev->irq); - goto fail1; - } - return 0; - } - - /* Hook MSI or MSI-X interrupt */ - efx_for_each_channel(channel, efx) { - rc = request_irq(channel->irq, falcon_msi_interrupt, - IRQF_PROBE_SHARED, /* Not shared */ - channel->name, channel); - if (rc) { - EFX_ERR(efx, "failed to hook IRQ %d\n", channel->irq); - goto fail2; - } - } - - return 0; - - fail2: - efx_for_each_channel(channel, efx) - free_irq(channel->irq, channel); - fail1: - return rc; -} - -void falcon_fini_interrupt(struct efx_nic *efx) -{ - struct efx_channel *channel; - efx_oword_t reg; - - /* Disable MSI/MSI-X interrupts */ - efx_for_each_channel(channel, efx) { - if (channel->irq) - free_irq(channel->irq, channel); - } - - /* ACK legacy interrupt */ - if (falcon_rev(efx) >= FALCON_REV_B0) - efx_reado(efx, ®, FR_BZ_INT_ISR0); - else - falcon_irq_ack_a1(efx); - - /* Disable legacy interrupt */ - if (efx->legacy_irq) - free_irq(efx->legacy_irq, efx); -} - /************************************************************************** * * EEPROM/flash @@ -1652,11 +242,10 @@ static int falcon_spi_wait(struct efx_nic *efx) } } -int falcon_spi_cmd(const struct efx_spi_device *spi, +int falcon_spi_cmd(struct efx_nic *efx, const struct efx_spi_device *spi, unsigned int command, int address, const void *in, void *out, size_t len) { - struct efx_nic *efx = spi->efx; bool addressed = (address >= 0); bool reading = (out != NULL); efx_oword_t reg; @@ -1725,15 +314,15 @@ efx_spi_munge_command(const struct efx_spi_device *spi, } /* Wait up to 10 ms for buffered write completion */ -int falcon_spi_wait_write(const struct efx_spi_device *spi) +int +falcon_spi_wait_write(struct efx_nic *efx, const struct efx_spi_device *spi) { - struct efx_nic *efx = spi->efx; unsigned long timeout = jiffies + 1 + DIV_ROUND_UP(HZ, 100); u8 status; int rc; for (;;) { - rc = falcon_spi_cmd(spi, SPI_RDSR, -1, NULL, + rc = falcon_spi_cmd(efx, spi, SPI_RDSR, -1, NULL, &status, sizeof(status)); if (rc) return rc; @@ -1749,8 +338,8 @@ int falcon_spi_wait_write(const struct efx_spi_device *spi) } } -int falcon_spi_read(const struct efx_spi_device *spi, loff_t start, - size_t len, size_t *retlen, u8 *buffer) +int falcon_spi_read(struct efx_nic *efx, const struct efx_spi_device *spi, + loff_t start, size_t len, size_t *retlen, u8 *buffer) { size_t block_len, pos = 0; unsigned int command; @@ -1760,7 +349,7 @@ int falcon_spi_read(const struct efx_spi_device *spi, loff_t start, block_len = min(len - pos, FALCON_SPI_MAX_LEN); command = efx_spi_munge_command(spi, SPI_READ, start + pos); - rc = falcon_spi_cmd(spi, command, start + pos, NULL, + rc = falcon_spi_cmd(efx, spi, command, start + pos, NULL, buffer + pos, block_len); if (rc) break; @@ -1779,8 +368,9 @@ int falcon_spi_read(const struct efx_spi_device *spi, loff_t start, return rc; } -int falcon_spi_write(const struct efx_spi_device *spi, loff_t start, - size_t len, size_t *retlen, const u8 *buffer) +int +falcon_spi_write(struct efx_nic *efx, const struct efx_spi_device *spi, + loff_t start, size_t len, size_t *retlen, const u8 *buffer) { u8 verify_buffer[FALCON_SPI_MAX_LEN]; size_t block_len, pos = 0; @@ -1788,24 +378,24 @@ int falcon_spi_write(const struct efx_spi_device *spi, loff_t start, int rc = 0; while (pos < len) { - rc = falcon_spi_cmd(spi, SPI_WREN, -1, NULL, NULL, 0); + rc = falcon_spi_cmd(efx, spi, SPI_WREN, -1, NULL, NULL, 0); if (rc) break; block_len = min(len - pos, falcon_spi_write_limit(spi, start + pos)); command = efx_spi_munge_command(spi, SPI_WRITE, start + pos); - rc = falcon_spi_cmd(spi, command, start + pos, + rc = falcon_spi_cmd(efx, spi, command, start + pos, buffer + pos, NULL, block_len); if (rc) break; - rc = falcon_spi_wait_write(spi); + rc = falcon_spi_wait_write(efx, spi); if (rc) break; command = efx_spi_munge_command(spi, SPI_READ, start + pos); - rc = falcon_spi_cmd(spi, command, start + pos, + rc = falcon_spi_cmd(efx, spi, command, start + pos, NULL, verify_buffer, block_len); if (memcmp(verify_buffer, buffer + pos, block_len)) { rc = -EIO; @@ -1834,12 +424,23 @@ int falcon_spi_write(const struct efx_spi_device *spi, loff_t start, ************************************************************************** */ -static int falcon_reset_macs(struct efx_nic *efx) +static void falcon_push_multicast_hash(struct efx_nic *efx) { - efx_oword_t reg; + union efx_multicast_hash *mc_hash = &efx->multicast_hash; + + WARN_ON(!mutex_is_locked(&efx->mac_lock)); + + efx_writeo(efx, &mc_hash->oword[0], FR_AB_MAC_MC_HASH_REG0); + efx_writeo(efx, &mc_hash->oword[1], FR_AB_MAC_MC_HASH_REG1); +} + +static void falcon_reset_macs(struct efx_nic *efx) +{ + struct falcon_nic_data *nic_data = efx->nic_data; + efx_oword_t reg, mac_ctrl; int count; - if (falcon_rev(efx) < FALCON_REV_B0) { + if (efx_nic_rev(efx) < EFX_REV_FALCON_B0) { /* It's not safe to use GLB_CTL_REG to reset the * macs, so instead use the internal MAC resets */ @@ -1851,7 +452,7 @@ static int falcon_reset_macs(struct efx_nic *efx) EFX_POPULATE_OWORD_1(reg, FRF_AB_GM_SW_RST, 0); efx_writeo(efx, ®, FR_AB_GM_CFG1); udelay(1000); - return 0; + return; } else { EFX_POPULATE_OWORD_1(reg, FRF_AB_XM_CORE_RST, 1); efx_writeo(efx, ®, FR_AB_XM_GLB_CFG); @@ -1860,22 +461,20 @@ static int falcon_reset_macs(struct efx_nic *efx) efx_reado(efx, ®, FR_AB_XM_GLB_CFG); if (EFX_OWORD_FIELD(reg, FRF_AB_XM_CORE_RST) == 0) - return 0; + return; udelay(10); } EFX_ERR(efx, "timed out waiting for XMAC core reset\n"); - return -ETIMEDOUT; } } - /* MAC stats will fail whilst the TX fifo is draining. Serialise - * the drain sequence with the statistics fetch */ - efx_stats_disable(efx); + /* Mac stats will fail whist the TX fifo is draining */ + WARN_ON(nic_data->stats_disable_count == 0); - efx_reado(efx, ®, FR_AB_MAC_CTRL); - EFX_SET_OWORD_FIELD(reg, FRF_BB_TXFIFO_DRAIN_EN, 1); - efx_writeo(efx, ®, FR_AB_MAC_CTRL); + efx_reado(efx, &mac_ctrl, FR_AB_MAC_CTRL); + EFX_SET_OWORD_FIELD(mac_ctrl, FRF_BB_TXFIFO_DRAIN_EN, 1); + efx_writeo(efx, &mac_ctrl, FR_AB_MAC_CTRL); efx_reado(efx, ®, FR_AB_GLB_CTL); EFX_SET_OWORD_FIELD(reg, FRF_AB_RST_XGTX, 1); @@ -1901,21 +500,16 @@ static int falcon_reset_macs(struct efx_nic *efx) udelay(10); } - efx_stats_enable(efx); - - /* If we've reset the EM block and the link is up, then - * we'll have to kick the XAUI link so the PHY can recover */ - if (efx->link_state.up && EFX_IS10G(efx) && EFX_WORKAROUND_5147(efx)) - falcon_reset_xaui(efx); - - return 0; + /* Ensure the correct MAC is selected before statistics + * are re-enabled by the caller */ + efx_writeo(efx, &mac_ctrl, FR_AB_MAC_CTRL); } void falcon_drain_tx_fifo(struct efx_nic *efx) { efx_oword_t reg; - if ((falcon_rev(efx) < FALCON_REV_B0) || + if ((efx_nic_rev(efx) < EFX_REV_FALCON_B0) || (efx->loopback_mode != LOOPBACK_NONE)) return; @@ -1927,11 +521,11 @@ void falcon_drain_tx_fifo(struct efx_nic *efx) falcon_reset_macs(efx); } -void falcon_deconfigure_mac_wrapper(struct efx_nic *efx) +static void falcon_deconfigure_mac_wrapper(struct efx_nic *efx) { efx_oword_t reg; - if (falcon_rev(efx) < FALCON_REV_B0) + if (efx_nic_rev(efx) < EFX_REV_FALCON_B0) return; /* Isolate the MAC -> RX */ @@ -1939,8 +533,8 @@ void falcon_deconfigure_mac_wrapper(struct efx_nic *efx) EFX_SET_OWORD_FIELD(reg, FRF_BZ_RX_INGR_EN, 0); efx_writeo(efx, ®, FR_AZ_RX_CFG); - if (!efx->link_state.up) - falcon_drain_tx_fifo(efx); + /* Isolate TX -> MAC */ + falcon_drain_tx_fifo(efx); } void falcon_reconfigure_mac_wrapper(struct efx_nic *efx) @@ -1948,7 +542,6 @@ void falcon_reconfigure_mac_wrapper(struct efx_nic *efx) struct efx_link_state *link_state = &efx->link_state; efx_oword_t reg; int link_speed; - bool tx_fc; switch (link_state->speed) { case 10000: link_speed = 3; break; @@ -1968,7 +561,7 @@ void falcon_reconfigure_mac_wrapper(struct efx_nic *efx) FRF_AB_MAC_SPEED, link_speed); /* On B0, MAC backpressure can be disabled and packets get * discarded. */ - if (falcon_rev(efx) >= FALCON_REV_B0) { + if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) { EFX_SET_OWORD_FIELD(reg, FRF_BB_TXFIFO_DRAIN_EN, !link_state->up); } @@ -1976,40 +569,31 @@ void falcon_reconfigure_mac_wrapper(struct efx_nic *efx) efx_writeo(efx, ®, FR_AB_MAC_CTRL); /* Restore the multicast hash registers. */ - falcon_set_multicast_hash(efx); + falcon_push_multicast_hash(efx); - /* Transmission of pause frames when RX crosses the threshold is - * covered by RX_XOFF_MAC_EN and XM_TX_CFG_REG:XM_FCNTL. - * Action on receipt of pause frames is controller by XM_DIS_FCNTL */ - tx_fc = !!(efx->link_state.fc & EFX_FC_TX); efx_reado(efx, ®, FR_AZ_RX_CFG); - EFX_SET_OWORD_FIELD(reg, FRF_AZ_RX_XOFF_MAC_EN, tx_fc); - + /* Enable XOFF signal from RX FIFO (we enabled it during NIC + * initialisation but it may read back as 0) */ + EFX_SET_OWORD_FIELD(reg, FRF_AZ_RX_XOFF_MAC_EN, 1); /* Unisolate the MAC -> RX */ - if (falcon_rev(efx) >= FALCON_REV_B0) + if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) EFX_SET_OWORD_FIELD(reg, FRF_BZ_RX_INGR_EN, 1); efx_writeo(efx, ®, FR_AZ_RX_CFG); } -int falcon_dma_stats(struct efx_nic *efx, unsigned int done_offset) +static void falcon_stats_request(struct efx_nic *efx) { + struct falcon_nic_data *nic_data = efx->nic_data; efx_oword_t reg; - u32 *dma_done; - int i; - if (disable_dma_stats) - return 0; + WARN_ON(nic_data->stats_pending); + WARN_ON(nic_data->stats_disable_count); - /* Statistics fetch will fail if the MAC is in TX drain */ - if (falcon_rev(efx) >= FALCON_REV_B0) { - efx_oword_t temp; - efx_reado(efx, &temp, FR_AB_MAC_CTRL); - if (EFX_OWORD_FIELD(temp, FRF_BB_TXFIFO_DRAIN_EN)) - return 0; - } + if (nic_data->stats_dma_done == NULL) + return; /* no mac selected */ - dma_done = (efx->stats_buffer.addr + done_offset); - *dma_done = FALCON_STATS_NOT_DONE; + *nic_data->stats_dma_done = FALCON_STATS_NOT_DONE; + nic_data->stats_pending = true; wmb(); /* ensure done flag is clear */ /* Initiate DMA transfer of stats */ @@ -2019,17 +603,90 @@ int falcon_dma_stats(struct efx_nic *efx, unsigned int done_offset) efx->stats_buffer.dma_addr); efx_writeo(efx, ®, FR_AB_MAC_STAT_DMA); - /* Wait for transfer to complete */ - for (i = 0; i < 400; i++) { - if (*(volatile u32 *)dma_done == FALCON_STATS_DONE) { - rmb(); /* Ensure the stats are valid. */ - return 0; - } - udelay(10); + mod_timer(&nic_data->stats_timer, round_jiffies_up(jiffies + HZ / 2)); +} + +static void falcon_stats_complete(struct efx_nic *efx) +{ + struct falcon_nic_data *nic_data = efx->nic_data; + + if (!nic_data->stats_pending) + return; + + nic_data->stats_pending = 0; + if (*nic_data->stats_dma_done == FALCON_STATS_DONE) { + rmb(); /* read the done flag before the stats */ + efx->mac_op->update_stats(efx); + } else { + EFX_ERR(efx, "timed out waiting for statistics\n"); } +} - EFX_ERR(efx, "timed out waiting for statistics\n"); - return -ETIMEDOUT; +static void falcon_stats_timer_func(unsigned long context) +{ + struct efx_nic *efx = (struct efx_nic *)context; + struct falcon_nic_data *nic_data = efx->nic_data; + + spin_lock(&efx->stats_lock); + + falcon_stats_complete(efx); + if (nic_data->stats_disable_count == 0) + falcon_stats_request(efx); + + spin_unlock(&efx->stats_lock); +} + +static void falcon_switch_mac(struct efx_nic *efx); + +static bool falcon_loopback_link_poll(struct efx_nic *efx) +{ + struct efx_link_state old_state = efx->link_state; + + WARN_ON(!mutex_is_locked(&efx->mac_lock)); + WARN_ON(!LOOPBACK_INTERNAL(efx)); + + efx->link_state.fd = true; + efx->link_state.fc = efx->wanted_fc; + efx->link_state.up = true; + + if (efx->loopback_mode == LOOPBACK_GMAC) + efx->link_state.speed = 1000; + else + efx->link_state.speed = 10000; + + return !efx_link_state_equal(&efx->link_state, &old_state); +} + +static int falcon_reconfigure_port(struct efx_nic *efx) +{ + int rc; + + WARN_ON(efx_nic_rev(efx) > EFX_REV_FALCON_B0); + + /* Poll the PHY link state *before* reconfiguring it. This means we + * will pick up the correct speed (in loopback) to select the correct + * MAC. + */ + if (LOOPBACK_INTERNAL(efx)) + falcon_loopback_link_poll(efx); + else + efx->phy_op->poll(efx); + + falcon_stop_nic_stats(efx); + falcon_deconfigure_mac_wrapper(efx); + + falcon_switch_mac(efx); + + efx->phy_op->reconfigure(efx); + rc = efx->mac_op->reconfigure(efx); + BUG_ON(rc); + + falcon_start_nic_stats(efx); + + /* Synchronise efx->link_state with the kernel */ + efx_link_status_changed(efx); + + return 0; } /************************************************************************** @@ -2042,18 +699,18 @@ int falcon_dma_stats(struct efx_nic *efx, unsigned int done_offset) /* Wait for GMII access to complete */ static int falcon_gmii_wait(struct efx_nic *efx) { - efx_dword_t md_stat; + efx_oword_t md_stat; int count; /* wait upto 50ms - taken max from datasheet */ for (count = 0; count < 5000; count++) { - efx_readd(efx, &md_stat, FR_AB_MD_STAT); - if (EFX_DWORD_FIELD(md_stat, FRF_AB_MD_BSY) == 0) { - if (EFX_DWORD_FIELD(md_stat, FRF_AB_MD_LNFL) != 0 || - EFX_DWORD_FIELD(md_stat, FRF_AB_MD_BSERR) != 0) { + efx_reado(efx, &md_stat, FR_AB_MD_STAT); + if (EFX_OWORD_FIELD(md_stat, FRF_AB_MD_BSY) == 0) { + if (EFX_OWORD_FIELD(md_stat, FRF_AB_MD_LNFL) != 0 || + EFX_OWORD_FIELD(md_stat, FRF_AB_MD_BSERR) != 0) { EFX_ERR(efx, "error from GMII access " - EFX_DWORD_FMT"\n", - EFX_DWORD_VAL(md_stat)); + EFX_OWORD_FMT"\n", + EFX_OWORD_VAL(md_stat)); return -EIO; } return 0; @@ -2075,7 +732,7 @@ static int falcon_mdio_write(struct net_device *net_dev, EFX_REGDUMP(efx, "writing MDIO %d register %d.%d with 0x%04x\n", prtad, devad, addr, value); - spin_lock_bh(&efx->phy_lock); + mutex_lock(&efx->mdio_lock); /* Check MDIO not currently being accessed */ rc = falcon_gmii_wait(efx); @@ -2110,8 +767,8 @@ static int falcon_mdio_write(struct net_device *net_dev, udelay(10); } - out: - spin_unlock_bh(&efx->phy_lock); +out: + mutex_unlock(&efx->mdio_lock); return rc; } @@ -2123,7 +780,7 @@ static int falcon_mdio_read(struct net_device *net_dev, efx_oword_t reg; int rc; - spin_lock_bh(&efx->phy_lock); + mutex_lock(&efx->mdio_lock); /* Check MDIO not currently being accessed */ rc = falcon_gmii_wait(efx); @@ -2159,39 +816,20 @@ static int falcon_mdio_read(struct net_device *net_dev, prtad, devad, addr, rc); } - out: - spin_unlock_bh(&efx->phy_lock); +out: + mutex_unlock(&efx->mdio_lock); return rc; } -int falcon_switch_mac(struct efx_nic *efx) +static void falcon_clock_mac(struct efx_nic *efx) { - struct efx_mac_operations *old_mac_op = efx->mac_op; - efx_oword_t nic_stat; unsigned strap_val; - int rc = 0; - - /* Don't try to fetch MAC stats while we're switching MACs */ - efx_stats_disable(efx); - - /* Internal loopbacks override the phy speed setting */ - if (efx->loopback_mode == LOOPBACK_GMAC) { - efx->link_state.speed = 1000; - efx->link_state.fd = true; - } else if (LOOPBACK_INTERNAL(efx)) { - efx->link_state.speed = 10000; - efx->link_state.fd = true; - } - - WARN_ON(!mutex_is_locked(&efx->mac_lock)); - efx->mac_op = (EFX_IS10G(efx) ? - &falcon_xmac_operations : &falcon_gmac_operations); + efx_oword_t nic_stat; - /* Always push the NIC_STAT_REG setting even if the mac hasn't - * changed, because this function is run post online reset */ + /* Configure the NIC generated MAC clock correctly */ efx_reado(efx, &nic_stat, FR_AB_NIC_STAT); strap_val = EFX_IS10G(efx) ? 5 : 3; - if (falcon_rev(efx) >= FALCON_REV_B0) { + if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) { EFX_SET_OWORD_FIELD(nic_stat, FRF_BB_EE_STRAP_EN, 1); EFX_SET_OWORD_FIELD(nic_stat, FRF_BB_EE_STRAP, strap_val); efx_writeo(efx, &nic_stat, FR_AB_NIC_STAT); @@ -2201,22 +839,39 @@ int falcon_switch_mac(struct efx_nic *efx) BUG_ON(EFX_OWORD_FIELD(nic_stat, FRF_AB_STRAP_PINS) != strap_val); } +} + +static void falcon_switch_mac(struct efx_nic *efx) +{ + struct efx_mac_operations *old_mac_op = efx->mac_op; + struct falcon_nic_data *nic_data = efx->nic_data; + unsigned int stats_done_offset; + + WARN_ON(!mutex_is_locked(&efx->mac_lock)); + WARN_ON(nic_data->stats_disable_count == 0); + + efx->mac_op = (EFX_IS10G(efx) ? + &falcon_xmac_operations : &falcon_gmac_operations); + + if (EFX_IS10G(efx)) + stats_done_offset = XgDmaDone_offset; + else + stats_done_offset = GDmaDone_offset; + nic_data->stats_dma_done = efx->stats_buffer.addr + stats_done_offset; if (old_mac_op == efx->mac_op) - goto out; + return; + + falcon_clock_mac(efx); EFX_LOG(efx, "selected %cMAC\n", EFX_IS10G(efx) ? 'X' : 'G'); /* Not all macs support a mac-level link state */ - efx->mac_up = true; - - rc = falcon_reset_macs(efx); -out: - efx_stats_enable(efx); - return rc; + efx->xmac_poll_required = false; + falcon_reset_macs(efx); } /* This call is responsible for hooking in the MAC and PHY operations */ -int falcon_probe_port(struct efx_nic *efx) +static int falcon_probe_port(struct efx_nic *efx) { int rc; @@ -2238,29 +893,26 @@ int falcon_probe_port(struct efx_nic *efx) return -ENODEV; } - if (efx->phy_op->macs & EFX_XMAC) - efx->loopback_modes |= ((1 << LOOPBACK_XGMII) | - (1 << LOOPBACK_XGXS) | - (1 << LOOPBACK_XAUI)); - if (efx->phy_op->macs & EFX_GMAC) - efx->loopback_modes |= (1 << LOOPBACK_GMAC); - efx->loopback_modes |= efx->phy_op->loopbacks; - - /* Set up MDIO structure for PHY */ - efx->mdio.mmds = efx->phy_op->mmds; - efx->mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22; + /* Fill out MDIO structure and loopback modes */ efx->mdio.mdio_read = falcon_mdio_read; efx->mdio.mdio_write = falcon_mdio_write; + rc = efx->phy_op->probe(efx); + if (rc != 0) + return rc; + + /* Initial assumption */ + efx->link_state.speed = 10000; + efx->link_state.fd = true; /* Hardware flow ctrl. FalconA RX FIFO too small for pause generation */ - if (falcon_rev(efx) >= FALCON_REV_B0) + if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) efx->wanted_fc = EFX_FC_RX | EFX_FC_TX; else efx->wanted_fc = EFX_FC_RX; /* Allocate buffer for stats */ - rc = falcon_alloc_buffer(efx, &efx->stats_buffer, - FALCON_MAC_STATS_SIZE); + rc = efx_nic_alloc_buffer(efx, &efx->stats_buffer, + FALCON_MAC_STATS_SIZE); if (rc) return rc; EFX_LOG(efx, "stats buffer at %llx (virt %p phys %llx)\n", @@ -2271,40 +923,19 @@ int falcon_probe_port(struct efx_nic *efx) return 0; } -void falcon_remove_port(struct efx_nic *efx) +static void falcon_remove_port(struct efx_nic *efx) { - falcon_free_buffer(efx, &efx->stats_buffer); -} - -/************************************************************************** - * - * Multicast filtering - * - ************************************************************************** - */ - -void falcon_set_multicast_hash(struct efx_nic *efx) -{ - union efx_multicast_hash *mc_hash = &efx->multicast_hash; - - /* Broadcast packets go through the multicast hash filter. - * ether_crc_le() of the broadcast address is 0xbe2612ff - * so we always add bit 0xff to the mask. - */ - set_bit_le(0xff, mc_hash->byte); - - efx_writeo(efx, &mc_hash->oword[0], FR_AB_MAC_MC_HASH_REG0); - efx_writeo(efx, &mc_hash->oword[1], FR_AB_MAC_MC_HASH_REG1); + efx_nic_free_buffer(efx, &efx->stats_buffer); } - /************************************************************************** * * Falcon test code * **************************************************************************/ -int falcon_read_nvram(struct efx_nic *efx, struct falcon_nvconfig *nvconfig_out) +static int +falcon_read_nvram(struct efx_nic *efx, struct falcon_nvconfig *nvconfig_out) { struct falcon_nvconfig *nvconfig; struct efx_spi_device *spi; @@ -2323,7 +954,7 @@ int falcon_read_nvram(struct efx_nic *efx, struct falcon_nvconfig *nvconfig_out) nvconfig = region + FALCON_NVCONFIG_OFFSET; mutex_lock(&efx->spi_lock); - rc = falcon_spi_read(spi, 0, FALCON_NVCONFIG_END, NULL, region); + rc = falcon_spi_read(efx, spi, 0, FALCON_NVCONFIG_END, NULL, region); mutex_unlock(&efx->spi_lock); if (rc) { EFX_ERR(efx, "Failed to read %s\n", @@ -2367,11 +998,12 @@ int falcon_read_nvram(struct efx_nic *efx, struct falcon_nvconfig *nvconfig_out) return rc; } -/* Registers tested in the falcon register test */ -static struct { - unsigned address; - efx_oword_t mask; -} efx_test_registers[] = { +static int falcon_test_nvram(struct efx_nic *efx) +{ + return falcon_read_nvram(efx, NULL); +} + +static const struct efx_nic_register_test falcon_b0_register_tests[] = { { FR_AZ_ADR_REGION, EFX_OWORD32(0x0001FFFF, 0x0001FFFF, 0x0001FFFF, 0x0001FFFF) }, { FR_AZ_RX_CFG, @@ -2410,64 +1042,10 @@ static struct { EFX_OWORD32(0x0003FF0F, 0x00000000, 0x00000000, 0x00000000) }, }; -static bool efx_masked_compare_oword(const efx_oword_t *a, const efx_oword_t *b, - const efx_oword_t *mask) -{ - return ((a->u64[0] ^ b->u64[0]) & mask->u64[0]) || - ((a->u64[1] ^ b->u64[1]) & mask->u64[1]); -} - -int falcon_test_registers(struct efx_nic *efx) +static int falcon_b0_test_registers(struct efx_nic *efx) { - unsigned address = 0, i, j; - efx_oword_t mask, imask, original, reg, buf; - - /* Falcon should be in loopback to isolate the XMAC from the PHY */ - WARN_ON(!LOOPBACK_INTERNAL(efx)); - - for (i = 0; i < ARRAY_SIZE(efx_test_registers); ++i) { - address = efx_test_registers[i].address; - mask = imask = efx_test_registers[i].mask; - EFX_INVERT_OWORD(imask); - - efx_reado(efx, &original, address); - - /* bit sweep on and off */ - for (j = 0; j < 128; j++) { - if (!EFX_EXTRACT_OWORD32(mask, j, j)) - continue; - - /* Test this testable bit can be set in isolation */ - EFX_AND_OWORD(reg, original, mask); - EFX_SET_OWORD32(reg, j, j, 1); - - efx_writeo(efx, ®, address); - efx_reado(efx, &buf, address); - - if (efx_masked_compare_oword(®, &buf, &mask)) - goto fail; - - /* Test this testable bit can be cleared in isolation */ - EFX_OR_OWORD(reg, original, mask); - EFX_SET_OWORD32(reg, j, j, 0); - - efx_writeo(efx, ®, address); - efx_reado(efx, &buf, address); - - if (efx_masked_compare_oword(®, &buf, &mask)) - goto fail; - } - - efx_writeo(efx, &original, address); - } - - return 0; - -fail: - EFX_ERR(efx, "wrote "EFX_OWORD_FMT" read "EFX_OWORD_FMT - " at address 0x%x mask "EFX_OWORD_FMT"\n", EFX_OWORD_VAL(reg), - EFX_OWORD_VAL(buf), address, EFX_OWORD_VAL(mask)); - return -EIO; + return efx_nic_test_registers(efx, falcon_b0_register_tests, + ARRAY_SIZE(falcon_b0_register_tests)); } /************************************************************************** @@ -2479,7 +1057,7 @@ fail: /* Resets NIC to known state. This routine must be called in process * context and is allowed to sleep. */ -int falcon_reset_hw(struct efx_nic *efx, enum reset_type method) +static int falcon_reset_hw(struct efx_nic *efx, enum reset_type method) { struct falcon_nic_data *nic_data = efx->nic_data; efx_oword_t glb_ctl_reg_ker; @@ -2495,7 +1073,7 @@ int falcon_reset_hw(struct efx_nic *efx, enum reset_type method) "function prior to hardware reset\n"); goto fail1; } - if (FALCON_IS_DUAL_FUNC(efx)) { + if (efx_nic_is_dual_func(efx)) { rc = pci_save_state(nic_data->pci_dev2); if (rc) { EFX_ERR(efx, "failed to backup PCI state of " @@ -2530,7 +1108,7 @@ int falcon_reset_hw(struct efx_nic *efx, enum reset_type method) /* Restore PCI configuration if needed */ if (method == RESET_TYPE_WORLD) { - if (FALCON_IS_DUAL_FUNC(efx)) { + if (efx_nic_is_dual_func(efx)) { rc = pci_restore_state(nic_data->pci_dev2); if (rc) { EFX_ERR(efx, "failed to restore PCI config for " @@ -2568,6 +1146,44 @@ fail5: return rc; } +static void falcon_monitor(struct efx_nic *efx) +{ + bool link_changed; + int rc; + + BUG_ON(!mutex_is_locked(&efx->mac_lock)); + + rc = falcon_board(efx)->type->monitor(efx); + if (rc) { + EFX_ERR(efx, "Board sensor %s; shutting down PHY\n", + (rc == -ERANGE) ? "reported fault" : "failed"); + efx->phy_mode |= PHY_MODE_LOW_POWER; + rc = __efx_reconfigure_port(efx); + WARN_ON(rc); + } + + if (LOOPBACK_INTERNAL(efx)) + link_changed = falcon_loopback_link_poll(efx); + else + link_changed = efx->phy_op->poll(efx); + + if (link_changed) { + falcon_stop_nic_stats(efx); + falcon_deconfigure_mac_wrapper(efx); + + falcon_switch_mac(efx); + rc = efx->mac_op->reconfigure(efx); + BUG_ON(rc); + + falcon_start_nic_stats(efx); + + efx_link_status_changed(efx); + } + + if (EFX_IS10G(efx)) + falcon_poll_xmac(efx); +} + /* Zeroes out the SRAM contents. This routine must be called in * process context and is allowed to sleep. */ @@ -2634,8 +1250,6 @@ static int falcon_spi_device_init(struct efx_nic *efx, spi_device->block_size = 1 << SPI_DEV_TYPE_FIELD(device_type, SPI_DEV_TYPE_BLOCK_SIZE); - - spi_device->efx = efx; } else { spi_device = NULL; } @@ -2645,7 +1259,6 @@ static int falcon_spi_device_init(struct efx_nic *efx, return 0; } - static void falcon_remove_spi_devices(struct efx_nic *efx) { kfree(efx->spi_eeprom); @@ -2715,49 +1328,6 @@ static int falcon_probe_nvconfig(struct efx_nic *efx) return rc; } -/* Probe the NIC variant (revision, ASIC vs FPGA, function count, port - * count, port speed). Set workaround and feature flags accordingly. - */ -static int falcon_probe_nic_variant(struct efx_nic *efx) -{ - efx_oword_t altera_build; - efx_oword_t nic_stat; - - efx_reado(efx, &altera_build, FR_AZ_ALTERA_BUILD); - if (EFX_OWORD_FIELD(altera_build, FRF_AZ_ALTERA_BUILD_VER)) { - EFX_ERR(efx, "Falcon FPGA not supported\n"); - return -ENODEV; - } - - efx_reado(efx, &nic_stat, FR_AB_NIC_STAT); - - switch (falcon_rev(efx)) { - case FALCON_REV_A0: - case 0xff: - EFX_ERR(efx, "Falcon rev A0 not supported\n"); - return -ENODEV; - - case FALCON_REV_A1: - if (EFX_OWORD_FIELD(nic_stat, FRF_AA_STRAP_PCIE) == 0) { - EFX_ERR(efx, "Falcon rev A1 PCI-X not supported\n"); - return -ENODEV; - } - break; - - case FALCON_REV_B0: - break; - - default: - EFX_ERR(efx, "Unknown Falcon rev %d\n", falcon_rev(efx)); - return -ENODEV; - } - - /* Initial assumed speed */ - efx->link_state.speed = EFX_OWORD_FIELD(nic_stat, FRF_AB_STRAP_10G) ? 10000 : 1000; - - return 0; -} - /* Probe all SPI devices on the NIC */ static void falcon_probe_spi_devices(struct efx_nic *efx) { @@ -2797,7 +1367,7 @@ static void falcon_probe_spi_devices(struct efx_nic *efx) large_eeprom_type); } -int falcon_probe_nic(struct efx_nic *efx) +static int falcon_probe_nic(struct efx_nic *efx) { struct falcon_nic_data *nic_data; struct falcon_board *board; @@ -2809,15 +1379,33 @@ int falcon_probe_nic(struct efx_nic *efx) return -ENOMEM; efx->nic_data = nic_data; - /* Determine number of ports etc. */ - rc = falcon_probe_nic_variant(efx); - if (rc) + rc = -ENODEV; + + if (efx_nic_fpga_ver(efx) != 0) { + EFX_ERR(efx, "Falcon FPGA not supported\n"); goto fail1; + } - /* Probe secondary function if expected */ - if (FALCON_IS_DUAL_FUNC(efx)) { - struct pci_dev *dev = pci_dev_get(efx->pci_dev); + if (efx_nic_rev(efx) <= EFX_REV_FALCON_A1) { + efx_oword_t nic_stat; + struct pci_dev *dev; + u8 pci_rev = efx->pci_dev->revision; + if ((pci_rev == 0xff) || (pci_rev == 0)) { + EFX_ERR(efx, "Falcon rev A0 not supported\n"); + goto fail1; + } + efx_reado(efx, &nic_stat, FR_AB_NIC_STAT); + if (EFX_OWORD_FIELD(nic_stat, FRF_AB_STRAP_10G) == 0) { + EFX_ERR(efx, "Falcon rev A1 1G not supported\n"); + goto fail1; + } + if (EFX_OWORD_FIELD(nic_stat, FRF_AA_STRAP_PCIE) == 0) { + EFX_ERR(efx, "Falcon rev A1 PCI-X not supported\n"); + goto fail1; + } + + dev = pci_dev_get(efx->pci_dev); while ((dev = pci_get_device(EFX_VENDID_SFC, FALCON_A_S_DEVID, dev))) { if (dev->bus == efx->pci_dev->bus && @@ -2841,7 +1429,7 @@ int falcon_probe_nic(struct efx_nic *efx) } /* Allocate memory for INT_KER */ - rc = falcon_alloc_buffer(efx, &efx->irq_status, sizeof(efx_oword_t)); + rc = efx_nic_alloc_buffer(efx, &efx->irq_status, sizeof(efx_oword_t)); if (rc) goto fail4; BUG_ON(efx->irq_status.dma_addr & 0x0f); @@ -2870,12 +1458,16 @@ int falcon_probe_nic(struct efx_nic *efx) if (rc) goto fail5; - rc = falcon_board(efx)->init(efx); + rc = falcon_board(efx)->type->init(efx); if (rc) { EFX_ERR(efx, "failed to initialise board\n"); goto fail6; } + nic_data->stats_disable_count = 1; + setup_timer(&nic_data->stats_timer, &falcon_stats_timer_func, + (unsigned long)efx); + return 0; fail6: @@ -2883,7 +1475,7 @@ int falcon_probe_nic(struct efx_nic *efx) memset(&board->i2c_adap, 0, sizeof(board->i2c_adap)); fail5: falcon_remove_spi_devices(efx); - falcon_free_buffer(efx, &efx->irq_status); + efx_nic_free_buffer(efx, &efx->irq_status); fail4: fail3: if (nic_data->pci_dev2) { @@ -2906,12 +1498,12 @@ static void falcon_init_rx_cfg(struct efx_nic *efx) const unsigned ctrl_xon_thr = 20; const unsigned ctrl_xoff_thr = 25; /* RX data FIFO thresholds (256-byte units; size varies) */ - int data_xon_thr = rx_xon_thresh_bytes >> 8; - int data_xoff_thr = rx_xoff_thresh_bytes >> 8; + int data_xon_thr = efx_nic_rx_xon_thresh >> 8; + int data_xoff_thr = efx_nic_rx_xoff_thresh >> 8; efx_oword_t reg; efx_reado(efx, ®, FR_AZ_RX_CFG); - if (falcon_rev(efx) <= FALCON_REV_A1) { + if (efx_nic_rev(efx) <= EFX_REV_FALCON_A1) { /* Data FIFO size is 5.5K */ if (data_xon_thr < 0) data_xon_thr = 512 >> 8; @@ -2939,6 +1531,9 @@ static void falcon_init_rx_cfg(struct efx_nic *efx) EFX_SET_OWORD_FIELD(reg, FRF_BZ_RX_XOFF_TX_TH, ctrl_xoff_thr); EFX_SET_OWORD_FIELD(reg, FRF_BZ_RX_INGR_EN, 1); } + /* Always enable XOFF signal from RX FIFO. We enable + * or disable transmission of pause frames at the MAC. */ + EFX_SET_OWORD_FIELD(reg, FRF_AZ_RX_XOFF_MAC_EN, 1); efx_writeo(efx, ®, FR_AZ_RX_CFG); } @@ -2946,7 +1541,7 @@ static void falcon_init_rx_cfg(struct efx_nic *efx) * defining the descriptor cache sizes and number of RSS channels. * It does not set up any buffers, descriptor rings or event queues. */ -int falcon_init_nic(struct efx_nic *efx) +static int falcon_init_nic(struct efx_nic *efx) { efx_oword_t temp; int rc; @@ -2957,36 +1552,19 @@ int falcon_init_nic(struct efx_nic *efx) efx_writeo(efx, &temp, FR_AB_NIC_STAT); /* Set the source of the GMAC clock */ - if (falcon_rev(efx) == FALCON_REV_B0) { + if (efx_nic_rev(efx) == EFX_REV_FALCON_B0) { efx_reado(efx, &temp, FR_AB_GPIO_CTL); EFX_SET_OWORD_FIELD(temp, FRF_AB_USE_NIC_CLK, true); efx_writeo(efx, &temp, FR_AB_GPIO_CTL); } + /* Select the correct MAC */ + falcon_clock_mac(efx); + rc = falcon_reset_sram(efx); if (rc) return rc; - /* Set positions of descriptor caches in SRAM. */ - EFX_POPULATE_OWORD_1(temp, FRF_AZ_SRM_TX_DC_BASE_ADR, TX_DC_BASE / 8); - efx_writeo(efx, &temp, FR_AZ_SRM_TX_DC_CFG); - EFX_POPULATE_OWORD_1(temp, FRF_AZ_SRM_RX_DC_BASE_ADR, RX_DC_BASE / 8); - efx_writeo(efx, &temp, FR_AZ_SRM_RX_DC_CFG); - - /* Set TX descriptor cache size. */ - BUILD_BUG_ON(TX_DC_ENTRIES != (16 << TX_DC_ENTRIES_ORDER)); - EFX_POPULATE_OWORD_1(temp, FRF_AZ_TX_DC_SIZE, TX_DC_ENTRIES_ORDER); - efx_writeo(efx, &temp, FR_AZ_TX_DC_CFG); - - /* Set RX descriptor cache size. Set low watermark to size-8, as - * this allows most efficient prefetching. - */ - BUILD_BUG_ON(RX_DC_ENTRIES != (16 << RX_DC_ENTRIES_ORDER)); - EFX_POPULATE_OWORD_1(temp, FRF_AZ_RX_DC_SIZE, RX_DC_ENTRIES_ORDER); - efx_writeo(efx, &temp, FR_AZ_RX_DC_CFG); - EFX_POPULATE_OWORD_1(temp, FRF_AZ_RX_DC_PF_LWM, RX_DC_ENTRIES - 8); - efx_writeo(efx, &temp, FR_AZ_RX_DC_PF_WM); - /* Clear the parity enables on the TX data fifos as * they produce false parity errors because of timing issues */ @@ -2996,19 +1574,6 @@ int falcon_init_nic(struct efx_nic *efx) efx_writeo(efx, &temp, FR_AZ_CSR_SPARE); } - /* Enable all the genuinely fatal interrupts. (They are still - * masked by the overall interrupt mask, controlled by - * falcon_interrupts()). - * - * Note: All other fatal interrupts are enabled - */ - EFX_POPULATE_OWORD_3(temp, - FRF_AZ_ILL_ADR_INT_KER_EN, 1, - FRF_AZ_RBUF_OWN_INT_KER_EN, 1, - FRF_AZ_TBUF_OWN_INT_KER_EN, 1); - EFX_INVERT_OWORD(temp); - efx_writeo(efx, &temp, FR_AZ_FATAL_INTR_KER); - if (EFX_WORKAROUND_7244(efx)) { efx_reado(efx, &temp, FR_BZ_RX_FILTER_CTL); EFX_SET_OWORD_FIELD(temp, FRF_BZ_UDP_FULL_SRCH_LIMIT, 8); @@ -3018,8 +1583,6 @@ int falcon_init_nic(struct efx_nic *efx) efx_writeo(efx, &temp, FR_BZ_RX_FILTER_CTL); } - falcon_setup_rss_indir_table(efx); - /* XXX This is documented only for Falcon A0/A1 */ /* Setup RX. Wait for descriptor is broken and must * be disabled. RXDP recovery shouldn't be needed, but is. @@ -3031,24 +1594,6 @@ int falcon_init_nic(struct efx_nic *efx) EFX_SET_OWORD_FIELD(temp, FRF_AA_RX_ISCSI_DIS, 1); efx_writeo(efx, &temp, FR_AA_RX_SELF_RST); - /* Disable the ugly timer-based TX DMA backoff and allow TX DMA to be - * controlled by the RX FIFO fill level. Set arbitration to one pkt/Q. - */ - efx_reado(efx, &temp, FR_AZ_TX_RESERVED); - EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_RX_SPACER, 0xfe); - EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_RX_SPACER_EN, 1); - EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_ONE_PKT_PER_Q, 1); - EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_PUSH_EN, 0); - EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_DIS_NON_IP_EV, 1); - /* Enable SW_EV to inherit in char driver - assume harmless here */ - EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_SOFT_EVT_EN, 1); - /* Prefetch threshold 2 => fetch when descriptor cache half empty */ - EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_PREF_THRESHOLD, 2); - /* Squash TX of packets of 16 bytes or less */ - if (falcon_rev(efx) >= FALCON_REV_B0 && EFX_WORKAROUND_9141(efx)) - EFX_SET_OWORD_FIELD(temp, FRF_BZ_TX_FLUSH_MIN_LEN_EN, 1); - efx_writeo(efx, &temp, FR_AZ_TX_RESERVED); - /* Do not enable TX_NO_EOP_DISC_EN, since it limits packets to 16 * descriptors (which is bad). */ @@ -3059,21 +1604,23 @@ int falcon_init_nic(struct efx_nic *efx) falcon_init_rx_cfg(efx); /* Set destination of both TX and RX Flush events */ - if (falcon_rev(efx) >= FALCON_REV_B0) { + if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) { EFX_POPULATE_OWORD_1(temp, FRF_BZ_FLS_EVQ_ID, 0); efx_writeo(efx, &temp, FR_BZ_DP_CTRL); } + efx_nic_init_common(efx); + return 0; } -void falcon_remove_nic(struct efx_nic *efx) +static void falcon_remove_nic(struct efx_nic *efx) { struct falcon_nic_data *nic_data = efx->nic_data; struct falcon_board *board = falcon_board(efx); int rc; - falcon_board(efx)->fini(efx); + board->type->fini(efx); /* Remove I2C adapter and clear it in preparation for a retry */ rc = i2c_del_adapter(&board->i2c_adap); @@ -3081,7 +1628,7 @@ void falcon_remove_nic(struct efx_nic *efx) memset(&board->i2c_adap, 0, sizeof(board->i2c_adap)); falcon_remove_spi_devices(efx); - falcon_free_buffer(efx, &efx->irq_status); + efx_nic_free_buffer(efx, &efx->irq_status); falcon_reset_hw(efx, RESET_TYPE_ALL); @@ -3096,13 +1643,86 @@ void falcon_remove_nic(struct efx_nic *efx) efx->nic_data = NULL; } -void falcon_update_nic_stats(struct efx_nic *efx) +static void falcon_update_nic_stats(struct efx_nic *efx) { + struct falcon_nic_data *nic_data = efx->nic_data; efx_oword_t cnt; + if (nic_data->stats_disable_count) + return; + efx_reado(efx, &cnt, FR_AZ_RX_NODESC_DROP); efx->n_rx_nodesc_drop_cnt += EFX_OWORD_FIELD(cnt, FRF_AB_RX_NODESC_DROP_CNT); + + if (nic_data->stats_pending && + *nic_data->stats_dma_done == FALCON_STATS_DONE) { + nic_data->stats_pending = false; + rmb(); /* read the done flag before the stats */ + efx->mac_op->update_stats(efx); + } +} + +void falcon_start_nic_stats(struct efx_nic *efx) +{ + struct falcon_nic_data *nic_data = efx->nic_data; + + spin_lock_bh(&efx->stats_lock); + if (--nic_data->stats_disable_count == 0) + falcon_stats_request(efx); + spin_unlock_bh(&efx->stats_lock); +} + +void falcon_stop_nic_stats(struct efx_nic *efx) +{ + struct falcon_nic_data *nic_data = efx->nic_data; + int i; + + might_sleep(); + + spin_lock_bh(&efx->stats_lock); + ++nic_data->stats_disable_count; + spin_unlock_bh(&efx->stats_lock); + + del_timer_sync(&nic_data->stats_timer); + + /* Wait enough time for the most recent transfer to + * complete. */ + for (i = 0; i < 4 && nic_data->stats_pending; i++) { + if (*nic_data->stats_dma_done == FALCON_STATS_DONE) + break; + msleep(1); + } + + spin_lock_bh(&efx->stats_lock); + falcon_stats_complete(efx); + spin_unlock_bh(&efx->stats_lock); +} + +static void falcon_set_id_led(struct efx_nic *efx, enum efx_led_mode mode) +{ + falcon_board(efx)->type->set_id_led(efx, mode); +} + +/************************************************************************** + * + * Wake on LAN + * + ************************************************************************** + */ + +static void falcon_get_wol(struct efx_nic *efx, struct ethtool_wolinfo *wol) +{ + wol->supported = 0; + wol->wolopts = 0; + memset(&wol->sopass, 0, sizeof(wol->sopass)); +} + +static int falcon_set_wol(struct efx_nic *efx, u32 type) +{ + if (type != 0) + return -EINVAL; + return 0; } /************************************************************************** @@ -3112,7 +1732,30 @@ void falcon_update_nic_stats(struct efx_nic *efx) ************************************************************************** */ -struct efx_nic_type falcon_a_nic_type = { +struct efx_nic_type falcon_a1_nic_type = { + .probe = falcon_probe_nic, + .remove = falcon_remove_nic, + .init = falcon_init_nic, + .fini = efx_port_dummy_op_void, + .monitor = falcon_monitor, + .reset = falcon_reset_hw, + .probe_port = falcon_probe_port, + .remove_port = falcon_remove_port, + .prepare_flush = falcon_prepare_flush, + .update_stats = falcon_update_nic_stats, + .start_stats = falcon_start_nic_stats, + .stop_stats = falcon_stop_nic_stats, + .set_id_led = falcon_set_id_led, + .push_irq_moderation = falcon_push_irq_moderation, + .push_multicast_hash = falcon_push_multicast_hash, + .reconfigure_port = falcon_reconfigure_port, + .get_wol = falcon_get_wol, + .set_wol = falcon_set_wol, + .resume_wol = efx_port_dummy_op_void, + .test_nvram = falcon_test_nvram, + .default_mac_ops = &falcon_xmac_operations, + + .revision = EFX_REV_FALCON_A1, .mem_map_size = 0x20000, .txd_ptr_tbl_base = FR_AA_TX_DESC_PTR_TBL_KER, .rxd_ptr_tbl_base = FR_AA_RX_DESC_PTR_TBL_KER, @@ -3123,9 +1766,37 @@ struct efx_nic_type falcon_a_nic_type = { .rx_buffer_padding = 0x24, .max_interrupt_mode = EFX_INT_MODE_MSI, .phys_addr_channels = 4, + .tx_dc_base = 0x130000, + .rx_dc_base = 0x100000, + .offload_features = NETIF_F_IP_CSUM, + .reset_world_flags = ETH_RESET_IRQ, }; -struct efx_nic_type falcon_b_nic_type = { +struct efx_nic_type falcon_b0_nic_type = { + .probe = falcon_probe_nic, + .remove = falcon_remove_nic, + .init = falcon_init_nic, + .fini = efx_port_dummy_op_void, + .monitor = falcon_monitor, + .reset = falcon_reset_hw, + .probe_port = falcon_probe_port, + .remove_port = falcon_remove_port, + .prepare_flush = falcon_prepare_flush, + .update_stats = falcon_update_nic_stats, + .start_stats = falcon_start_nic_stats, + .stop_stats = falcon_stop_nic_stats, + .set_id_led = falcon_set_id_led, + .push_irq_moderation = falcon_push_irq_moderation, + .push_multicast_hash = falcon_push_multicast_hash, + .reconfigure_port = falcon_reconfigure_port, + .get_wol = falcon_get_wol, + .set_wol = falcon_set_wol, + .resume_wol = efx_port_dummy_op_void, + .test_registers = falcon_b0_test_registers, + .test_nvram = falcon_test_nvram, + .default_mac_ops = &falcon_xmac_operations, + + .revision = EFX_REV_FALCON_B0, /* Map everything up to and including the RSS indirection * table. Don't map MSI-X table, MSI-X PBA since Linux * requires that they not be mapped. */ @@ -3143,5 +1814,9 @@ struct efx_nic_type falcon_b_nic_type = { .phys_addr_channels = 32, /* Hardware limit is 64, but the legacy * interrupt handler only supports 32 * channels */ + .tx_dc_base = 0x130000, + .rx_dc_base = 0x100000, + .offload_features = NETIF_F_IP_CSUM, + .reset_world_flags = ETH_RESET_IRQ, }; diff --git a/drivers/net/sfc/falcon.h b/drivers/net/sfc/falcon.h deleted file mode 100644 index 0da5ea7908b0..000000000000 --- a/drivers/net/sfc/falcon.h +++ /dev/null @@ -1,191 +0,0 @@ -/**************************************************************************** - * Driver for Solarflare Solarstorm network controllers and boards - * Copyright 2005-2006 Fen Systems Ltd. - * Copyright 2006-2008 Solarflare Communications Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation, incorporated herein by reference. - */ - -#ifndef EFX_FALCON_H -#define EFX_FALCON_H - -#include <linux/i2c-algo-bit.h> -#include "net_driver.h" -#include "efx.h" - -/* - * Falcon hardware control - */ - -enum falcon_revision { - FALCON_REV_A0 = 0, - FALCON_REV_A1 = 1, - FALCON_REV_B0 = 2, -}; - -static inline int falcon_rev(struct efx_nic *efx) -{ - return efx->pci_dev->revision; -} - -/** - * struct falcon_board - board information - * @type: Board model type - * @major: Major rev. ('A', 'B' ...) - * @minor: Minor rev. (0, 1, ...) - * @init: Allocate resources and initialise peripheral hardware - * @init_phy: Do board-specific PHY initialisation - * @set_id_led: Set state of identifying LED or revert to automatic function - * @monitor: Board-specific health check function - * @fini: Shut down hardware and free resources - * @i2c_adap: I2C adapter for on-board peripherals - * @i2c_data: Data for bit-banging algorithm - * @hwmon_client: I2C client for hardware monitor - * @ioexp_client: I2C client for power/port control - */ -struct falcon_board { - int type; - int major; - int minor; - int (*init) (struct efx_nic *nic); - void (*init_phy) (struct efx_nic *efx); - void (*set_id_led) (struct efx_nic *efx, enum efx_led_mode mode); - int (*monitor) (struct efx_nic *nic); - void (*fini) (struct efx_nic *nic); - struct i2c_adapter i2c_adap; - struct i2c_algo_bit_data i2c_data; - struct i2c_client *hwmon_client, *ioexp_client; -}; - -/** - * struct falcon_nic_data - Falcon NIC state - * @pci_dev2: The secondary PCI device if present - * @board: Board state and functions - */ -struct falcon_nic_data { - struct pci_dev *pci_dev2; - struct falcon_board board; -}; - -static inline struct falcon_board *falcon_board(struct efx_nic *efx) -{ - struct falcon_nic_data *data = efx->nic_data; - return &data->board; -} - -extern struct efx_nic_type falcon_a_nic_type; -extern struct efx_nic_type falcon_b_nic_type; - -/************************************************************************** - * - * Externs - * - ************************************************************************** - */ - -extern void falcon_probe_board(struct efx_nic *efx, u16 revision_info); - -/* TX data path */ -extern int falcon_probe_tx(struct efx_tx_queue *tx_queue); -extern void falcon_init_tx(struct efx_tx_queue *tx_queue); -extern void falcon_fini_tx(struct efx_tx_queue *tx_queue); -extern void falcon_remove_tx(struct efx_tx_queue *tx_queue); -extern void falcon_push_buffers(struct efx_tx_queue *tx_queue); - -/* RX data path */ -extern int falcon_probe_rx(struct efx_rx_queue *rx_queue); -extern void falcon_init_rx(struct efx_rx_queue *rx_queue); -extern void falcon_fini_rx(struct efx_rx_queue *rx_queue); -extern void falcon_remove_rx(struct efx_rx_queue *rx_queue); -extern void falcon_notify_rx_desc(struct efx_rx_queue *rx_queue); - -/* Event data path */ -extern int falcon_probe_eventq(struct efx_channel *channel); -extern void falcon_init_eventq(struct efx_channel *channel); -extern void falcon_fini_eventq(struct efx_channel *channel); -extern void falcon_remove_eventq(struct efx_channel *channel); -extern int falcon_process_eventq(struct efx_channel *channel, int rx_quota); -extern void falcon_eventq_read_ack(struct efx_channel *channel); - -/* Ports */ -extern int falcon_probe_port(struct efx_nic *efx); -extern void falcon_remove_port(struct efx_nic *efx); - -/* MAC/PHY */ -extern int falcon_switch_mac(struct efx_nic *efx); -extern bool falcon_xaui_link_ok(struct efx_nic *efx); -extern int falcon_dma_stats(struct efx_nic *efx, - unsigned int done_offset); -extern void falcon_drain_tx_fifo(struct efx_nic *efx); -extern void falcon_deconfigure_mac_wrapper(struct efx_nic *efx); -extern void falcon_reconfigure_mac_wrapper(struct efx_nic *efx); - -/* Interrupts and test events */ -extern int falcon_init_interrupt(struct efx_nic *efx); -extern void falcon_enable_interrupts(struct efx_nic *efx); -extern void falcon_generate_test_event(struct efx_channel *channel, - unsigned int magic); -extern void falcon_sim_phy_event(struct efx_nic *efx); -extern void falcon_generate_interrupt(struct efx_nic *efx); -extern void falcon_set_int_moderation(struct efx_channel *channel); -extern void falcon_disable_interrupts(struct efx_nic *efx); -extern void falcon_fini_interrupt(struct efx_nic *efx); - -#define FALCON_IRQ_MOD_RESOLUTION 5 - -/* Global Resources */ -extern int falcon_probe_nic(struct efx_nic *efx); -extern int falcon_init_nic(struct efx_nic *efx); -extern int falcon_flush_queues(struct efx_nic *efx); -extern int falcon_reset_hw(struct efx_nic *efx, enum reset_type method); -extern void falcon_remove_nic(struct efx_nic *efx); -extern void falcon_update_nic_stats(struct efx_nic *efx); -extern void falcon_set_multicast_hash(struct efx_nic *efx); -extern int falcon_reset_xaui(struct efx_nic *efx); - -/* Tests */ -struct falcon_nvconfig; -extern int falcon_read_nvram(struct efx_nic *efx, - struct falcon_nvconfig *nvconfig); -extern int falcon_test_registers(struct efx_nic *efx); - -/************************************************************************** - * - * Falcon MAC stats - * - ************************************************************************** - */ - -#define FALCON_STAT_OFFSET(falcon_stat) EFX_VAL(falcon_stat, offset) -#define FALCON_STAT_WIDTH(falcon_stat) EFX_VAL(falcon_stat, WIDTH) - -/* Retrieve statistic from statistics block */ -#define FALCON_STAT(efx, falcon_stat, efx_stat) do { \ - if (FALCON_STAT_WIDTH(falcon_stat) == 16) \ - (efx)->mac_stats.efx_stat += le16_to_cpu( \ - *((__force __le16 *) \ - (efx->stats_buffer.addr + \ - FALCON_STAT_OFFSET(falcon_stat)))); \ - else if (FALCON_STAT_WIDTH(falcon_stat) == 32) \ - (efx)->mac_stats.efx_stat += le32_to_cpu( \ - *((__force __le32 *) \ - (efx->stats_buffer.addr + \ - FALCON_STAT_OFFSET(falcon_stat)))); \ - else \ - (efx)->mac_stats.efx_stat += le64_to_cpu( \ - *((__force __le64 *) \ - (efx->stats_buffer.addr + \ - FALCON_STAT_OFFSET(falcon_stat)))); \ - } while (0) - -#define FALCON_MAC_STATS_SIZE 0x100 - -#define MAC_DATA_LBN 0 -#define MAC_DATA_WIDTH 32 - -extern void falcon_generate_event(struct efx_channel *channel, - efx_qword_t *event); - -#endif /* EFX_FALCON_H */ diff --git a/drivers/net/sfc/falcon_boards.c b/drivers/net/sfc/falcon_boards.c index 333ccc14e523..bf0b96af5334 100644 --- a/drivers/net/sfc/falcon_boards.c +++ b/drivers/net/sfc/falcon_boards.c @@ -1,6 +1,6 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards - * Copyright 2007-2008 Solarflare Communications Inc. + * Copyright 2007-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -12,7 +12,7 @@ #include "net_driver.h" #include "phy.h" #include "efx.h" -#include "falcon.h" +#include "nic.h" #include "regs.h" #include "io.h" #include "workarounds.h" @@ -144,7 +144,7 @@ static inline int efx_check_lm87(struct efx_nic *efx, unsigned mask) */ /************************************************************************** - * Support for I2C IO Expander device on SFE40001 + * Support for I2C IO Expander device on SFE4001 */ #define PCA9539 0x74 @@ -347,14 +347,15 @@ static ssize_t set_phy_flash_cfg(struct device *dev, * MAC stats accordingly. */ efx->phy_mode = new_mode; if (new_mode & PHY_MODE_SPECIAL) - efx_stats_disable(efx); - if (falcon_board(efx)->type == FALCON_BOARD_SFE4001) + falcon_stop_nic_stats(efx); + if (falcon_board(efx)->type->id == FALCON_BOARD_SFE4001) err = sfe4001_poweron(efx); else err = sfn4111t_reset(efx); - efx_reconfigure_port(efx); + if (!err) + err = efx_reconfigure_port(efx); if (!(new_mode & PHY_MODE_SPECIAL)) - efx_stats_enable(efx); + falcon_start_nic_stats(efx); } rtnl_unlock(); @@ -380,7 +381,7 @@ static int sfe4001_check_hw(struct efx_nic *efx) s32 status; /* If XAUI link is up then do not monitor */ - if (EFX_WORKAROUND_7884(efx) && efx->mac_up) + if (EFX_WORKAROUND_7884(efx) && !efx->xmac_poll_required) return 0; /* Check the powered status of the PHY. Lack of power implies that @@ -438,17 +439,10 @@ static int sfe4001_init(struct efx_nic *efx) goto fail_hwmon; } - /* 10Xpress has fixed-function LED pins, so there is no board-specific - * blink code. */ - board->set_id_led = tenxpress_set_id_led; - - board->monitor = sfe4001_check_hw; - board->fini = sfe4001_fini; - if (efx->phy_mode & PHY_MODE_SPECIAL) { /* PHY won't generate a 156.25 MHz clock and MAC stats fetch * will fail. */ - efx_stats_disable(efx); + falcon_stop_nic_stats(efx); } rc = sfe4001_poweron(efx); if (rc) @@ -475,7 +469,7 @@ static int sfn4111t_check_hw(struct efx_nic *efx) s32 status; /* If XAUI link is up then do not monitor */ - if (EFX_WORKAROUND_7884(efx) && efx->mac_up) + if (EFX_WORKAROUND_7884(efx) && !efx->xmac_poll_required) return 0; /* Test LHIGH, RHIGH, FAULT, EOT and IOT alarms */ @@ -511,7 +505,7 @@ static void sfn4111t_init_phy(struct efx_nic *efx) return; efx->phy_mode = PHY_MODE_SPECIAL; - efx_stats_disable(efx); + falcon_stop_nic_stats(efx); } sfn4111t_reset(efx); @@ -531,11 +525,6 @@ static int sfn4111t_init(struct efx_nic *efx) if (!board->hwmon_client) return -EIO; - board->init_phy = sfn4111t_init_phy; - board->set_id_led = tenxpress_set_id_led; - board->monitor = sfn4111t_check_hw; - board->fini = sfn4111t_fini; - rc = device_create_file(&efx->pci_dev->dev, &dev_attr_phy_flash_cfg); if (rc) goto fail_hwmon; @@ -543,7 +532,7 @@ static int sfn4111t_init(struct efx_nic *efx) if (efx->phy_mode & PHY_MODE_SPECIAL) /* PHY may not generate a 156.25 MHz clock and MAC * stats fetch will fail. */ - efx_stats_disable(efx); + falcon_stop_nic_stats(efx); return 0; @@ -620,15 +609,7 @@ static int sfe4002_check_hw(struct efx_nic *efx) static int sfe4002_init(struct efx_nic *efx) { - struct falcon_board *board = falcon_board(efx); - int rc = efx_init_lm87(efx, &sfe4002_hwmon_info, sfe4002_lm87_regs); - if (rc) - return rc; - board->monitor = sfe4002_check_hw; - board->init_phy = sfe4002_init_phy; - board->set_id_led = sfe4002_set_id_led; - board->fini = efx_fini_lm87; - return 0; + return efx_init_lm87(efx, &sfe4002_hwmon_info, sfe4002_lm87_regs); } /***************************************************************************** @@ -692,67 +673,80 @@ static int sfn4112f_check_hw(struct efx_nic *efx) static int sfn4112f_init(struct efx_nic *efx) { - struct falcon_board *board = falcon_board(efx); - - int rc = efx_init_lm87(efx, &sfn4112f_hwmon_info, sfn4112f_lm87_regs); - if (rc) - return rc; - board->monitor = sfn4112f_check_hw; - board->init_phy = sfn4112f_init_phy; - board->set_id_led = sfn4112f_set_id_led; - board->fini = efx_fini_lm87; - return 0; + return efx_init_lm87(efx, &sfn4112f_hwmon_info, sfn4112f_lm87_regs); } -/* This will get expanded as board-specific details get moved out of the - * PHY drivers. */ -struct falcon_board_data { - u8 type; - const char *ref_model; - const char *gen_type; - int (*init) (struct efx_nic *nic); -}; - - -static struct falcon_board_data board_data[] = { - { FALCON_BOARD_SFE4001, "SFE4001", "10GBASE-T adapter", sfe4001_init }, - { FALCON_BOARD_SFE4002, "SFE4002", "XFP adapter", sfe4002_init }, - { FALCON_BOARD_SFN4111T, "SFN4111T", "100/1000/10GBASE-T adapter", - sfn4111t_init }, - { FALCON_BOARD_SFN4112F, "SFN4112F", "SFP+ adapter", - sfn4112f_init }, +static const struct falcon_board_type board_types[] = { + { + .id = FALCON_BOARD_SFE4001, + .ref_model = "SFE4001", + .gen_type = "10GBASE-T adapter", + .init = sfe4001_init, + .init_phy = efx_port_dummy_op_void, + .fini = sfe4001_fini, + .set_id_led = tenxpress_set_id_led, + .monitor = sfe4001_check_hw, + }, + { + .id = FALCON_BOARD_SFE4002, + .ref_model = "SFE4002", + .gen_type = "XFP adapter", + .init = sfe4002_init, + .init_phy = sfe4002_init_phy, + .fini = efx_fini_lm87, + .set_id_led = sfe4002_set_id_led, + .monitor = sfe4002_check_hw, + }, + { + .id = FALCON_BOARD_SFN4111T, + .ref_model = "SFN4111T", + .gen_type = "100/1000/10GBASE-T adapter", + .init = sfn4111t_init, + .init_phy = sfn4111t_init_phy, + .fini = sfn4111t_fini, + .set_id_led = tenxpress_set_id_led, + .monitor = sfn4111t_check_hw, + }, + { + .id = FALCON_BOARD_SFN4112F, + .ref_model = "SFN4112F", + .gen_type = "SFP+ adapter", + .init = sfn4112f_init, + .init_phy = sfn4112f_init_phy, + .fini = efx_fini_lm87, + .set_id_led = sfn4112f_set_id_led, + .monitor = sfn4112f_check_hw, + }, }; -static struct falcon_board falcon_dummy_board = { +static const struct falcon_board_type falcon_dummy_board = { .init = efx_port_dummy_op_int, .init_phy = efx_port_dummy_op_void, + .fini = efx_port_dummy_op_void, .set_id_led = efx_port_dummy_op_set_id_led, .monitor = efx_port_dummy_op_int, - .fini = efx_port_dummy_op_void, }; void falcon_probe_board(struct efx_nic *efx, u16 revision_info) { struct falcon_board *board = falcon_board(efx); - struct falcon_board_data *data = NULL; + u8 type_id = FALCON_BOARD_TYPE(revision_info); int i; - *board = falcon_dummy_board; - board->type = FALCON_BOARD_TYPE(revision_info); board->major = FALCON_BOARD_MAJOR(revision_info); board->minor = FALCON_BOARD_MINOR(revision_info); - for (i = 0; i < ARRAY_SIZE(board_data); i++) - if (board_data[i].type == board->type) - data = &board_data[i]; + for (i = 0; i < ARRAY_SIZE(board_types); i++) + if (board_types[i].id == type_id) + board->type = &board_types[i]; - if (data) { + if (board->type) { EFX_INFO(efx, "board is %s rev %c%d\n", (efx->pci_dev->subsystem_vendor == EFX_VENDID_SFC) - ? data->ref_model : data->gen_type, + ? board->type->ref_model : board->type->gen_type, 'A' + board->major, board->minor); - board->init = data->init; } else { - EFX_ERR(efx, "unknown board type %d\n", board->type); + EFX_ERR(efx, "unknown board type %d\n", type_id); + board->type = &falcon_dummy_board; } } diff --git a/drivers/net/sfc/falcon_gmac.c b/drivers/net/sfc/falcon_gmac.c index 967f3fb397c9..7dadfcbd6ce7 100644 --- a/drivers/net/sfc/falcon_gmac.c +++ b/drivers/net/sfc/falcon_gmac.c @@ -1,7 +1,7 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards * Copyright 2005-2006 Fen Systems Ltd. - * Copyright 2006-2008 Solarflare Communications Inc. + * Copyright 2006-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -11,7 +11,7 @@ #include <linux/delay.h> #include "net_driver.h" #include "efx.h" -#include "falcon.h" +#include "nic.h" #include "mac.h" #include "regs.h" #include "io.h" @@ -22,7 +22,7 @@ * *************************************************************************/ -static void falcon_reconfigure_gmac(struct efx_nic *efx) +static int falcon_reconfigure_gmac(struct efx_nic *efx) { struct efx_link_state *link_state = &efx->link_state; bool loopback, tx_fc, rx_fc, bytemode; @@ -123,6 +123,8 @@ static void falcon_reconfigure_gmac(struct efx_nic *efx) udelay(10); falcon_reconfigure_mac_wrapper(efx); + + return 0; } static void falcon_update_stats_gmac(struct efx_nic *efx) @@ -130,11 +132,6 @@ static void falcon_update_stats_gmac(struct efx_nic *efx) struct efx_mac_stats *mac_stats = &efx->mac_stats; unsigned long old_rx_pause, old_tx_pause; unsigned long new_rx_pause, new_tx_pause; - int rc; - - rc = falcon_dma_stats(efx, GDmaDone_offset); - if (rc) - return; /* Pause frames are erroneously counted as errors (SFC bug 3269) */ old_rx_pause = mac_stats->rx_pause; @@ -221,9 +218,13 @@ static void falcon_update_stats_gmac(struct efx_nic *efx) mac_stats->rx_lt64 = mac_stats->rx_good_lt64 + mac_stats->rx_bad_lt64; } +static bool falcon_gmac_check_fault(struct efx_nic *efx) +{ + return false; +} + struct efx_mac_operations falcon_gmac_operations = { .reconfigure = falcon_reconfigure_gmac, .update_stats = falcon_update_stats_gmac, - .irq = efx_port_dummy_op_void, - .poll = efx_port_dummy_op_void, + .check_fault = falcon_gmac_check_fault, }; diff --git a/drivers/net/sfc/falcon_xmac.c b/drivers/net/sfc/falcon_xmac.c index 69cb55fc615a..3da933f8f079 100644 --- a/drivers/net/sfc/falcon_xmac.c +++ b/drivers/net/sfc/falcon_xmac.c @@ -1,7 +1,7 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards * Copyright 2005-2006 Fen Systems Ltd. - * Copyright 2006-2008 Solarflare Communications Inc. + * Copyright 2006-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -11,7 +11,7 @@ #include <linux/delay.h> #include "net_driver.h" #include "efx.h" -#include "falcon.h" +#include "nic.h" #include "regs.h" #include "io.h" #include "mac.h" @@ -60,11 +60,15 @@ static void falcon_setup_xaui(struct efx_nic *efx) int falcon_reset_xaui(struct efx_nic *efx) { + struct falcon_nic_data *nic_data = efx->nic_data; efx_oword_t reg; int count; + /* Don't fetch MAC statistics over an XMAC reset */ + WARN_ON(nic_data->stats_disable_count == 0); + /* Start reset sequence */ - EFX_POPULATE_DWORD_1(reg, FRF_AB_XX_RST_XX_EN, 1); + EFX_POPULATE_OWORD_1(reg, FRF_AB_XX_RST_XX_EN, 1); efx_writeo(efx, ®, FR_AB_XX_PWR_RST); /* Wait up to 10 ms for completion, then reinitialise */ @@ -85,7 +89,7 @@ static void falcon_mask_status_intr(struct efx_nic *efx, bool enable) { efx_oword_t reg; - if ((falcon_rev(efx) != FALCON_REV_B0) || LOOPBACK_INTERNAL(efx)) + if ((efx_nic_rev(efx) != EFX_REV_FALCON_B0) || LOOPBACK_INTERNAL(efx)) return; /* We expect xgmii faults if the wireside link is up */ @@ -94,7 +98,7 @@ static void falcon_mask_status_intr(struct efx_nic *efx, bool enable) /* We can only use this interrupt to signal the negative edge of * xaui_align [we have to poll the positive edge]. */ - if (!efx->mac_up) + if (efx->xmac_poll_required) return; /* Flush the ISR */ @@ -108,7 +112,7 @@ static void falcon_mask_status_intr(struct efx_nic *efx, bool enable) } /* Get status of XAUI link */ -bool falcon_xaui_link_ok(struct efx_nic *efx) +static bool falcon_xaui_link_ok(struct efx_nic *efx) { efx_oword_t reg; bool align_done, link_ok = false; @@ -133,37 +137,38 @@ bool falcon_xaui_link_ok(struct efx_nic *efx) /* If the link is up, then check the phy side of the xaui link */ if (efx->link_state.up && link_ok) - if (efx->phy_op->mmds & (1 << MDIO_MMD_PHYXS)) + if (efx->mdio.mmds & (1 << MDIO_MMD_PHYXS)) link_ok = efx_mdio_phyxgxs_lane_sync(efx); return link_ok; } -static void falcon_reconfigure_xmac_core(struct efx_nic *efx) +void falcon_reconfigure_xmac_core(struct efx_nic *efx) { unsigned int max_frame_len; efx_oword_t reg; bool rx_fc = !!(efx->link_state.fc & EFX_FC_RX); + bool tx_fc = !!(efx->link_state.fc & EFX_FC_TX); /* Configure MAC - cut-thru mode is hard wired on */ - EFX_POPULATE_DWORD_3(reg, + EFX_POPULATE_OWORD_3(reg, FRF_AB_XM_RX_JUMBO_MODE, 1, FRF_AB_XM_TX_STAT_EN, 1, FRF_AB_XM_RX_STAT_EN, 1); efx_writeo(efx, ®, FR_AB_XM_GLB_CFG); /* Configure TX */ - EFX_POPULATE_DWORD_6(reg, + EFX_POPULATE_OWORD_6(reg, FRF_AB_XM_TXEN, 1, FRF_AB_XM_TX_PRMBL, 1, FRF_AB_XM_AUTO_PAD, 1, FRF_AB_XM_TXCRC, 1, - FRF_AB_XM_FCNTL, 1, + FRF_AB_XM_FCNTL, tx_fc, FRF_AB_XM_IPG, 0x3); efx_writeo(efx, ®, FR_AB_XM_TX_CFG); /* Configure RX */ - EFX_POPULATE_DWORD_5(reg, + EFX_POPULATE_OWORD_5(reg, FRF_AB_XM_RXEN, 1, FRF_AB_XM_AUTO_DEPAD, 0, FRF_AB_XM_ACPT_ALL_MCAST, 1, @@ -173,14 +178,14 @@ static void falcon_reconfigure_xmac_core(struct efx_nic *efx) /* Set frame length */ max_frame_len = EFX_MAX_FRAME_LEN(efx->net_dev->mtu); - EFX_POPULATE_DWORD_1(reg, FRF_AB_XM_MAX_RX_FRM_SIZE, max_frame_len); + EFX_POPULATE_OWORD_1(reg, FRF_AB_XM_MAX_RX_FRM_SIZE, max_frame_len); efx_writeo(efx, ®, FR_AB_XM_RX_PARAM); - EFX_POPULATE_DWORD_2(reg, + EFX_POPULATE_OWORD_2(reg, FRF_AB_XM_MAX_TX_FRM_SIZE, max_frame_len, FRF_AB_XM_TX_JUMBO_MODE, 1); efx_writeo(efx, ®, FR_AB_XM_TX_PARAM); - EFX_POPULATE_DWORD_2(reg, + EFX_POPULATE_OWORD_2(reg, FRF_AB_XM_PAUSE_TIME, 0xfffe, /* MAX PAUSE TIME */ FRF_AB_XM_DIS_FCNTL, !rx_fc); efx_writeo(efx, ®, FR_AB_XM_FC); @@ -239,28 +244,38 @@ static void falcon_reconfigure_xgxs_core(struct efx_nic *efx) } -/* Try and bring the Falcon side of the Falcon-Phy XAUI link fails - * to come back up. Bash it until it comes back up */ -static void falcon_check_xaui_link_up(struct efx_nic *efx, int tries) +/* Try to bring up the Falcon side of the Falcon-Phy XAUI link */ +static bool falcon_check_xaui_link_up(struct efx_nic *efx, int tries) { - efx->mac_up = falcon_xaui_link_ok(efx); + bool mac_up = falcon_xaui_link_ok(efx); - if ((efx->loopback_mode == LOOPBACK_NETWORK) || + if (LOOPBACK_MASK(efx) & LOOPBACKS_EXTERNAL(efx) & LOOPBACKS_WS || efx_phy_mode_disabled(efx->phy_mode)) /* XAUI link is expected to be down */ - return; + return mac_up; - while (!efx->mac_up && tries) { + falcon_stop_nic_stats(efx); + + while (!mac_up && tries) { EFX_LOG(efx, "bashing xaui\n"); falcon_reset_xaui(efx); udelay(200); - efx->mac_up = falcon_xaui_link_ok(efx); + mac_up = falcon_xaui_link_ok(efx); --tries; } + + falcon_start_nic_stats(efx); + + return mac_up; +} + +static bool falcon_xmac_check_fault(struct efx_nic *efx) +{ + return !falcon_check_xaui_link_up(efx, 5); } -static void falcon_reconfigure_xmac(struct efx_nic *efx) +static int falcon_reconfigure_xmac(struct efx_nic *efx) { falcon_mask_status_intr(efx, false); @@ -269,18 +284,15 @@ static void falcon_reconfigure_xmac(struct efx_nic *efx) falcon_reconfigure_mac_wrapper(efx); - falcon_check_xaui_link_up(efx, 5); + efx->xmac_poll_required = !falcon_check_xaui_link_up(efx, 5); falcon_mask_status_intr(efx, true); + + return 0; } static void falcon_update_stats_xmac(struct efx_nic *efx) { struct efx_mac_stats *mac_stats = &efx->mac_stats; - int rc; - - rc = falcon_dma_stats(efx, XgDmaDone_offset); - if (rc) - return; /* Update MAC stats from DMAed values */ FALCON_STAT(efx, XgRxOctets, rx_bytes); @@ -338,35 +350,19 @@ static void falcon_update_stats_xmac(struct efx_nic *efx) mac_stats->rx_control * 64); } -static void falcon_xmac_irq(struct efx_nic *efx) -{ - /* The XGMII link has a transient fault, which indicates either: - * - there's a transient xgmii fault - * - falcon's end of the xaui link may need a kick - * - the wire-side link may have gone down, but the lasi/poll() - * hasn't noticed yet. - * - * We only want to even bother polling XAUI if we're confident it's - * not (1) or (3). In both cases, the only reliable way to spot this - * is to wait a bit. We do this here by forcing the mac link state - * to down, and waiting for the mac poll to come round and check - */ - efx->mac_up = false; -} - -static void falcon_poll_xmac(struct efx_nic *efx) +void falcon_poll_xmac(struct efx_nic *efx) { - if (!EFX_WORKAROUND_5147(efx) || !efx->link_state.up || efx->mac_up) + if (!EFX_WORKAROUND_5147(efx) || !efx->link_state.up || + !efx->xmac_poll_required) return; falcon_mask_status_intr(efx, false); - falcon_check_xaui_link_up(efx, 1); + efx->xmac_poll_required = !falcon_check_xaui_link_up(efx, 1); falcon_mask_status_intr(efx, true); } struct efx_mac_operations falcon_xmac_operations = { .reconfigure = falcon_reconfigure_xmac, .update_stats = falcon_update_stats_xmac, - .irq = falcon_xmac_irq, - .poll = falcon_poll_xmac, + .check_fault = falcon_xmac_check_fault, }; diff --git a/drivers/net/sfc/mac.h b/drivers/net/sfc/mac.h index 4e7074278fe1..f1aa5f374890 100644 --- a/drivers/net/sfc/mac.h +++ b/drivers/net/sfc/mac.h @@ -1,7 +1,7 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards * Copyright 2005-2006 Fen Systems Ltd. - * Copyright 2006-2008 Solarflare Communications Inc. + * Copyright 2006-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -15,5 +15,9 @@ extern struct efx_mac_operations falcon_gmac_operations; extern struct efx_mac_operations falcon_xmac_operations; +extern struct efx_mac_operations efx_mcdi_mac_operations; +extern void falcon_reconfigure_xmac_core(struct efx_nic *efx); +extern int efx_mcdi_mac_stats(struct efx_nic *efx, dma_addr_t dma_addr, + u32 dma_len, int enable, int clear); #endif diff --git a/drivers/net/sfc/mcdi.c b/drivers/net/sfc/mcdi.c new file mode 100644 index 000000000000..683353b904c7 --- /dev/null +++ b/drivers/net/sfc/mcdi.c @@ -0,0 +1,1112 @@ +/**************************************************************************** + * Driver for Solarflare Solarstorm network controllers and boards + * Copyright 2008-2009 Solarflare Communications Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +#include <linux/delay.h> +#include "net_driver.h" +#include "nic.h" +#include "io.h" +#include "regs.h" +#include "mcdi_pcol.h" +#include "phy.h" + +/************************************************************************** + * + * Management-Controller-to-Driver Interface + * + ************************************************************************** + */ + +/* Software-defined structure to the shared-memory */ +#define CMD_NOTIFY_PORT0 0 +#define CMD_NOTIFY_PORT1 4 +#define CMD_PDU_PORT0 0x008 +#define CMD_PDU_PORT1 0x108 +#define REBOOT_FLAG_PORT0 0x3f8 +#define REBOOT_FLAG_PORT1 0x3fc + +#define MCDI_RPC_TIMEOUT 10 /*seconds */ + +#define MCDI_PDU(efx) \ + (efx_port_num(efx) ? CMD_PDU_PORT1 : CMD_PDU_PORT0) +#define MCDI_DOORBELL(efx) \ + (efx_port_num(efx) ? CMD_NOTIFY_PORT1 : CMD_NOTIFY_PORT0) +#define MCDI_REBOOT_FLAG(efx) \ + (efx_port_num(efx) ? REBOOT_FLAG_PORT1 : REBOOT_FLAG_PORT0) + +#define SEQ_MASK \ + EFX_MASK32(EFX_WIDTH(MCDI_HEADER_SEQ)) + +static inline struct efx_mcdi_iface *efx_mcdi(struct efx_nic *efx) +{ + struct siena_nic_data *nic_data; + EFX_BUG_ON_PARANOID(efx_nic_rev(efx) < EFX_REV_SIENA_A0); + nic_data = efx->nic_data; + return &nic_data->mcdi; +} + +void efx_mcdi_init(struct efx_nic *efx) +{ + struct efx_mcdi_iface *mcdi; + + if (efx_nic_rev(efx) < EFX_REV_SIENA_A0) + return; + + mcdi = efx_mcdi(efx); + init_waitqueue_head(&mcdi->wq); + spin_lock_init(&mcdi->iface_lock); + atomic_set(&mcdi->state, MCDI_STATE_QUIESCENT); + mcdi->mode = MCDI_MODE_POLL; + + (void) efx_mcdi_poll_reboot(efx); +} + +static void efx_mcdi_copyin(struct efx_nic *efx, unsigned cmd, + const u8 *inbuf, size_t inlen) +{ + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + unsigned pdu = FR_CZ_MC_TREG_SMEM + MCDI_PDU(efx); + unsigned doorbell = FR_CZ_MC_TREG_SMEM + MCDI_DOORBELL(efx); + unsigned int i; + efx_dword_t hdr; + u32 xflags, seqno; + + BUG_ON(atomic_read(&mcdi->state) == MCDI_STATE_QUIESCENT); + BUG_ON(inlen & 3 || inlen >= 0x100); + + seqno = mcdi->seqno & SEQ_MASK; + xflags = 0; + if (mcdi->mode == MCDI_MODE_EVENTS) + xflags |= MCDI_HEADER_XFLAGS_EVREQ; + + EFX_POPULATE_DWORD_6(hdr, + MCDI_HEADER_RESPONSE, 0, + MCDI_HEADER_RESYNC, 1, + MCDI_HEADER_CODE, cmd, + MCDI_HEADER_DATALEN, inlen, + MCDI_HEADER_SEQ, seqno, + MCDI_HEADER_XFLAGS, xflags); + + efx_writed(efx, &hdr, pdu); + + for (i = 0; i < inlen; i += 4) + _efx_writed(efx, *((__le32 *)(inbuf + i)), pdu + 4 + i); + + /* Ensure the payload is written out before the header */ + wmb(); + + /* ring the doorbell with a distinctive value */ + _efx_writed(efx, (__force __le32) 0x45789abc, doorbell); +} + +static void efx_mcdi_copyout(struct efx_nic *efx, u8 *outbuf, size_t outlen) +{ + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + unsigned int pdu = FR_CZ_MC_TREG_SMEM + MCDI_PDU(efx); + int i; + + BUG_ON(atomic_read(&mcdi->state) == MCDI_STATE_QUIESCENT); + BUG_ON(outlen & 3 || outlen >= 0x100); + + for (i = 0; i < outlen; i += 4) + *((__le32 *)(outbuf + i)) = _efx_readd(efx, pdu + 4 + i); +} + +static int efx_mcdi_poll(struct efx_nic *efx) +{ + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + unsigned int time, finish; + unsigned int respseq, respcmd, error; + unsigned int pdu = FR_CZ_MC_TREG_SMEM + MCDI_PDU(efx); + unsigned int rc, spins; + efx_dword_t reg; + + /* Check for a reboot atomically with respect to efx_mcdi_copyout() */ + rc = efx_mcdi_poll_reboot(efx); + if (rc) + goto out; + + /* Poll for completion. Poll quickly (once a us) for the 1st jiffy, + * because generally mcdi responses are fast. After that, back off + * and poll once a jiffy (approximately) + */ + spins = TICK_USEC; + finish = get_seconds() + MCDI_RPC_TIMEOUT; + + while (1) { + if (spins != 0) { + --spins; + udelay(1); + } else + schedule(); + + time = get_seconds(); + + rmb(); + efx_readd(efx, ®, pdu); + + /* All 1's indicates that shared memory is in reset (and is + * not a valid header). Wait for it to come out reset before + * completing the command */ + if (EFX_DWORD_FIELD(reg, EFX_DWORD_0) != 0xffffffff && + EFX_DWORD_FIELD(reg, MCDI_HEADER_RESPONSE)) + break; + + if (time >= finish) + return -ETIMEDOUT; + } + + mcdi->resplen = EFX_DWORD_FIELD(reg, MCDI_HEADER_DATALEN); + respseq = EFX_DWORD_FIELD(reg, MCDI_HEADER_SEQ); + respcmd = EFX_DWORD_FIELD(reg, MCDI_HEADER_CODE); + error = EFX_DWORD_FIELD(reg, MCDI_HEADER_ERROR); + + if (error && mcdi->resplen == 0) { + EFX_ERR(efx, "MC rebooted\n"); + rc = EIO; + } else if ((respseq ^ mcdi->seqno) & SEQ_MASK) { + EFX_ERR(efx, "MC response mismatch tx seq 0x%x rx seq 0x%x\n", + respseq, mcdi->seqno); + rc = EIO; + } else if (error) { + efx_readd(efx, ®, pdu + 4); + switch (EFX_DWORD_FIELD(reg, EFX_DWORD_0)) { +#define TRANSLATE_ERROR(name) \ + case MC_CMD_ERR_ ## name: \ + rc = name; \ + break + TRANSLATE_ERROR(ENOENT); + TRANSLATE_ERROR(EINTR); + TRANSLATE_ERROR(EACCES); + TRANSLATE_ERROR(EBUSY); + TRANSLATE_ERROR(EINVAL); + TRANSLATE_ERROR(EDEADLK); + TRANSLATE_ERROR(ENOSYS); + TRANSLATE_ERROR(ETIME); +#undef TRANSLATE_ERROR + default: + rc = EIO; + break; + } + } else + rc = 0; + +out: + mcdi->resprc = rc; + if (rc) + mcdi->resplen = 0; + + /* Return rc=0 like wait_event_timeout() */ + return 0; +} + +/* Test and clear MC-rebooted flag for this port/function */ +int efx_mcdi_poll_reboot(struct efx_nic *efx) +{ + unsigned int addr = FR_CZ_MC_TREG_SMEM + MCDI_REBOOT_FLAG(efx); + efx_dword_t reg; + uint32_t value; + + if (efx_nic_rev(efx) < EFX_REV_SIENA_A0) + return false; + + efx_readd(efx, ®, addr); + value = EFX_DWORD_FIELD(reg, EFX_DWORD_0); + + if (value == 0) + return 0; + + EFX_ZERO_DWORD(reg); + efx_writed(efx, ®, addr); + + if (value == MC_STATUS_DWORD_ASSERT) + return -EINTR; + else + return -EIO; +} + +static void efx_mcdi_acquire(struct efx_mcdi_iface *mcdi) +{ + /* Wait until the interface becomes QUIESCENT and we win the race + * to mark it RUNNING. */ + wait_event(mcdi->wq, + atomic_cmpxchg(&mcdi->state, + MCDI_STATE_QUIESCENT, + MCDI_STATE_RUNNING) + == MCDI_STATE_QUIESCENT); +} + +static int efx_mcdi_await_completion(struct efx_nic *efx) +{ + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + + if (wait_event_timeout( + mcdi->wq, + atomic_read(&mcdi->state) == MCDI_STATE_COMPLETED, + msecs_to_jiffies(MCDI_RPC_TIMEOUT * 1000)) == 0) + return -ETIMEDOUT; + + /* Check if efx_mcdi_set_mode() switched us back to polled completions. + * In which case, poll for completions directly. If efx_mcdi_ev_cpl() + * completed the request first, then we'll just end up completing the + * request again, which is safe. + * + * We need an smp_rmb() to synchronise with efx_mcdi_mode_poll(), which + * wait_event_timeout() implicitly provides. + */ + if (mcdi->mode == MCDI_MODE_POLL) + return efx_mcdi_poll(efx); + + return 0; +} + +static bool efx_mcdi_complete(struct efx_mcdi_iface *mcdi) +{ + /* If the interface is RUNNING, then move to COMPLETED and wake any + * waiters. If the interface isn't in RUNNING then we've received a + * duplicate completion after we've already transitioned back to + * QUIESCENT. [A subsequent invocation would increment seqno, so would + * have failed the seqno check]. + */ + if (atomic_cmpxchg(&mcdi->state, + MCDI_STATE_RUNNING, + MCDI_STATE_COMPLETED) == MCDI_STATE_RUNNING) { + wake_up(&mcdi->wq); + return true; + } + + return false; +} + +static void efx_mcdi_release(struct efx_mcdi_iface *mcdi) +{ + atomic_set(&mcdi->state, MCDI_STATE_QUIESCENT); + wake_up(&mcdi->wq); +} + +static void efx_mcdi_ev_cpl(struct efx_nic *efx, unsigned int seqno, + unsigned int datalen, unsigned int errno) +{ + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + bool wake = false; + + spin_lock(&mcdi->iface_lock); + + if ((seqno ^ mcdi->seqno) & SEQ_MASK) { + if (mcdi->credits) + /* The request has been cancelled */ + --mcdi->credits; + else + EFX_ERR(efx, "MC response mismatch tx seq 0x%x rx " + "seq 0x%x\n", seqno, mcdi->seqno); + } else { + mcdi->resprc = errno; + mcdi->resplen = datalen; + + wake = true; + } + + spin_unlock(&mcdi->iface_lock); + + if (wake) + efx_mcdi_complete(mcdi); +} + +/* Issue the given command by writing the data into the shared memory PDU, + * ring the doorbell and wait for completion. Copyout the result. */ +int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd, + const u8 *inbuf, size_t inlen, u8 *outbuf, size_t outlen, + size_t *outlen_actual) +{ + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + int rc; + BUG_ON(efx_nic_rev(efx) < EFX_REV_SIENA_A0); + + efx_mcdi_acquire(mcdi); + + /* Serialise with efx_mcdi_ev_cpl() and efx_mcdi_ev_death() */ + spin_lock_bh(&mcdi->iface_lock); + ++mcdi->seqno; + spin_unlock_bh(&mcdi->iface_lock); + + efx_mcdi_copyin(efx, cmd, inbuf, inlen); + + if (mcdi->mode == MCDI_MODE_POLL) + rc = efx_mcdi_poll(efx); + else + rc = efx_mcdi_await_completion(efx); + + if (rc != 0) { + /* Close the race with efx_mcdi_ev_cpl() executing just too late + * and completing a request we've just cancelled, by ensuring + * that the seqno check therein fails. + */ + spin_lock_bh(&mcdi->iface_lock); + ++mcdi->seqno; + ++mcdi->credits; + spin_unlock_bh(&mcdi->iface_lock); + + EFX_ERR(efx, "MC command 0x%x inlen %d mode %d timed out\n", + cmd, (int)inlen, mcdi->mode); + } else { + size_t resplen; + + /* At the very least we need a memory barrier here to ensure + * we pick up changes from efx_mcdi_ev_cpl(). Protect against + * a spurious efx_mcdi_ev_cpl() running concurrently by + * acquiring the iface_lock. */ + spin_lock_bh(&mcdi->iface_lock); + rc = -mcdi->resprc; + resplen = mcdi->resplen; + spin_unlock_bh(&mcdi->iface_lock); + + if (rc == 0) { + efx_mcdi_copyout(efx, outbuf, + min(outlen, mcdi->resplen + 3) & ~0x3); + if (outlen_actual != NULL) + *outlen_actual = resplen; + } else if (cmd == MC_CMD_REBOOT && rc == -EIO) + ; /* Don't reset if MC_CMD_REBOOT returns EIO */ + else if (rc == -EIO || rc == -EINTR) { + EFX_ERR(efx, "MC fatal error %d\n", -rc); + efx_schedule_reset(efx, RESET_TYPE_MC_FAILURE); + } else + EFX_ERR(efx, "MC command 0x%x inlen %d failed rc=%d\n", + cmd, (int)inlen, -rc); + } + + efx_mcdi_release(mcdi); + return rc; +} + +void efx_mcdi_mode_poll(struct efx_nic *efx) +{ + struct efx_mcdi_iface *mcdi; + + if (efx_nic_rev(efx) < EFX_REV_SIENA_A0) + return; + + mcdi = efx_mcdi(efx); + if (mcdi->mode == MCDI_MODE_POLL) + return; + + /* We can switch from event completion to polled completion, because + * mcdi requests are always completed in shared memory. We do this by + * switching the mode to POLL'd then completing the request. + * efx_mcdi_await_completion() will then call efx_mcdi_poll(). + * + * We need an smp_wmb() to synchronise with efx_mcdi_await_completion(), + * which efx_mcdi_complete() provides for us. + */ + mcdi->mode = MCDI_MODE_POLL; + + efx_mcdi_complete(mcdi); +} + +void efx_mcdi_mode_event(struct efx_nic *efx) +{ + struct efx_mcdi_iface *mcdi; + + if (efx_nic_rev(efx) < EFX_REV_SIENA_A0) + return; + + mcdi = efx_mcdi(efx); + + if (mcdi->mode == MCDI_MODE_EVENTS) + return; + + /* We can't switch from polled to event completion in the middle of a + * request, because the completion method is specified in the request. + * So acquire the interface to serialise the requestors. We don't need + * to acquire the iface_lock to change the mode here, but we do need a + * write memory barrier ensure that efx_mcdi_rpc() sees it, which + * efx_mcdi_acquire() provides. + */ + efx_mcdi_acquire(mcdi); + mcdi->mode = MCDI_MODE_EVENTS; + efx_mcdi_release(mcdi); +} + +static void efx_mcdi_ev_death(struct efx_nic *efx, int rc) +{ + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + + /* If there is an outstanding MCDI request, it has been terminated + * either by a BADASSERT or REBOOT event. If the mcdi interface is + * in polled mode, then do nothing because the MC reboot handler will + * set the header correctly. However, if the mcdi interface is waiting + * for a CMDDONE event it won't receive it [and since all MCDI events + * are sent to the same queue, we can't be racing with + * efx_mcdi_ev_cpl()] + * + * There's a race here with efx_mcdi_rpc(), because we might receive + * a REBOOT event *before* the request has been copied out. In polled + * mode (during startup) this is irrelevent, because efx_mcdi_complete() + * is ignored. In event mode, this condition is just an edge-case of + * receiving a REBOOT event after posting the MCDI request. Did the mc + * reboot before or after the copyout? The best we can do always is + * just return failure. + */ + spin_lock(&mcdi->iface_lock); + if (efx_mcdi_complete(mcdi)) { + if (mcdi->mode == MCDI_MODE_EVENTS) { + mcdi->resprc = rc; + mcdi->resplen = 0; + } + } else + /* Nobody was waiting for an MCDI request, so trigger a reset */ + efx_schedule_reset(efx, RESET_TYPE_MC_FAILURE); + + spin_unlock(&mcdi->iface_lock); +} + +static unsigned int efx_mcdi_event_link_speed[] = { + [MCDI_EVENT_LINKCHANGE_SPEED_100M] = 100, + [MCDI_EVENT_LINKCHANGE_SPEED_1G] = 1000, + [MCDI_EVENT_LINKCHANGE_SPEED_10G] = 10000, +}; + + +static void efx_mcdi_process_link_change(struct efx_nic *efx, efx_qword_t *ev) +{ + u32 flags, fcntl, speed, lpa; + + speed = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_SPEED); + EFX_BUG_ON_PARANOID(speed >= ARRAY_SIZE(efx_mcdi_event_link_speed)); + speed = efx_mcdi_event_link_speed[speed]; + + flags = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_LINK_FLAGS); + fcntl = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_FCNTL); + lpa = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_LP_CAP); + + /* efx->link_state is only modified by efx_mcdi_phy_get_link(), + * which is only run after flushing the event queues. Therefore, it + * is safe to modify the link state outside of the mac_lock here. + */ + efx_mcdi_phy_decode_link(efx, &efx->link_state, speed, flags, fcntl); + + efx_mcdi_phy_check_fcntl(efx, lpa); + + efx_link_status_changed(efx); +} + +static const char *sensor_names[] = { + [MC_CMD_SENSOR_CONTROLLER_TEMP] = "Controller temp. sensor", + [MC_CMD_SENSOR_PHY_COMMON_TEMP] = "PHY shared temp. sensor", + [MC_CMD_SENSOR_CONTROLLER_COOLING] = "Controller cooling", + [MC_CMD_SENSOR_PHY0_TEMP] = "PHY 0 temp. sensor", + [MC_CMD_SENSOR_PHY0_COOLING] = "PHY 0 cooling", + [MC_CMD_SENSOR_PHY1_TEMP] = "PHY 1 temp. sensor", + [MC_CMD_SENSOR_PHY1_COOLING] = "PHY 1 cooling", + [MC_CMD_SENSOR_IN_1V0] = "1.0V supply sensor", + [MC_CMD_SENSOR_IN_1V2] = "1.2V supply sensor", + [MC_CMD_SENSOR_IN_1V8] = "1.8V supply sensor", + [MC_CMD_SENSOR_IN_2V5] = "2.5V supply sensor", + [MC_CMD_SENSOR_IN_3V3] = "3.3V supply sensor", + [MC_CMD_SENSOR_IN_12V0] = "12V supply sensor" +}; + +static const char *sensor_status_names[] = { + [MC_CMD_SENSOR_STATE_OK] = "OK", + [MC_CMD_SENSOR_STATE_WARNING] = "Warning", + [MC_CMD_SENSOR_STATE_FATAL] = "Fatal", + [MC_CMD_SENSOR_STATE_BROKEN] = "Device failure", +}; + +static void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev) +{ + unsigned int monitor, state, value; + const char *name, *state_txt; + monitor = EFX_QWORD_FIELD(*ev, MCDI_EVENT_SENSOREVT_MONITOR); + state = EFX_QWORD_FIELD(*ev, MCDI_EVENT_SENSOREVT_STATE); + value = EFX_QWORD_FIELD(*ev, MCDI_EVENT_SENSOREVT_VALUE); + /* Deal gracefully with the board having more drivers than we + * know about, but do not expect new sensor states. */ + name = (monitor >= ARRAY_SIZE(sensor_names)) + ? "No sensor name available" : + sensor_names[monitor]; + EFX_BUG_ON_PARANOID(state >= ARRAY_SIZE(sensor_status_names)); + state_txt = sensor_status_names[state]; + + EFX_ERR(efx, "Sensor %d (%s) reports condition '%s' for raw value %d\n", + monitor, name, state_txt, value); +} + +/* Called from falcon_process_eventq for MCDI events */ +void efx_mcdi_process_event(struct efx_channel *channel, + efx_qword_t *event) +{ + struct efx_nic *efx = channel->efx; + int code = EFX_QWORD_FIELD(*event, MCDI_EVENT_CODE); + u32 data = EFX_QWORD_FIELD(*event, MCDI_EVENT_DATA); + + switch (code) { + case MCDI_EVENT_CODE_BADSSERT: + EFX_ERR(efx, "MC watchdog or assertion failure at 0x%x\n", data); + efx_mcdi_ev_death(efx, EINTR); + break; + + case MCDI_EVENT_CODE_PMNOTICE: + EFX_INFO(efx, "MCDI PM event.\n"); + break; + + case MCDI_EVENT_CODE_CMDDONE: + efx_mcdi_ev_cpl(efx, + MCDI_EVENT_FIELD(*event, CMDDONE_SEQ), + MCDI_EVENT_FIELD(*event, CMDDONE_DATALEN), + MCDI_EVENT_FIELD(*event, CMDDONE_ERRNO)); + break; + + case MCDI_EVENT_CODE_LINKCHANGE: + efx_mcdi_process_link_change(efx, event); + break; + case MCDI_EVENT_CODE_SENSOREVT: + efx_mcdi_sensor_event(efx, event); + break; + case MCDI_EVENT_CODE_SCHEDERR: + EFX_INFO(efx, "MC Scheduler error address=0x%x\n", data); + break; + case MCDI_EVENT_CODE_REBOOT: + EFX_INFO(efx, "MC Reboot\n"); + efx_mcdi_ev_death(efx, EIO); + break; + case MCDI_EVENT_CODE_MAC_STATS_DMA: + /* MAC stats are gather lazily. We can ignore this. */ + break; + + default: + EFX_ERR(efx, "Unknown MCDI event 0x%x\n", code); + } +} + +/************************************************************************** + * + * Specific request functions + * + ************************************************************************** + */ + +int efx_mcdi_fwver(struct efx_nic *efx, u64 *version, u32 *build) +{ + u8 outbuf[ALIGN(MC_CMD_GET_VERSION_V1_OUT_LEN, 4)]; + size_t outlength; + const __le16 *ver_words; + int rc; + + BUILD_BUG_ON(MC_CMD_GET_VERSION_IN_LEN != 0); + + rc = efx_mcdi_rpc(efx, MC_CMD_GET_VERSION, NULL, 0, + outbuf, sizeof(outbuf), &outlength); + if (rc) + goto fail; + + if (outlength == MC_CMD_GET_VERSION_V0_OUT_LEN) { + *version = 0; + *build = MCDI_DWORD(outbuf, GET_VERSION_OUT_FIRMWARE); + return 0; + } + + if (outlength < MC_CMD_GET_VERSION_V1_OUT_LEN) { + rc = -EMSGSIZE; + goto fail; + } + + ver_words = (__le16 *)MCDI_PTR(outbuf, GET_VERSION_OUT_VERSION); + *version = (((u64)le16_to_cpu(ver_words[0]) << 48) | + ((u64)le16_to_cpu(ver_words[1]) << 32) | + ((u64)le16_to_cpu(ver_words[2]) << 16) | + le16_to_cpu(ver_words[3])); + *build = MCDI_DWORD(outbuf, GET_VERSION_OUT_FIRMWARE); + + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating, + bool *was_attached) +{ + u8 inbuf[MC_CMD_DRV_ATTACH_IN_LEN]; + u8 outbuf[MC_CMD_DRV_ATTACH_OUT_LEN]; + size_t outlen; + int rc; + + MCDI_SET_DWORD(inbuf, DRV_ATTACH_IN_NEW_STATE, + driver_operating ? 1 : 0); + MCDI_SET_DWORD(inbuf, DRV_ATTACH_IN_UPDATE, 1); + + rc = efx_mcdi_rpc(efx, MC_CMD_DRV_ATTACH, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), &outlen); + if (rc) + goto fail; + if (outlen < MC_CMD_DRV_ATTACH_OUT_LEN) + goto fail; + + if (was_attached != NULL) + *was_attached = MCDI_DWORD(outbuf, DRV_ATTACH_OUT_OLD_STATE); + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address, + u16 *fw_subtype_list) +{ + uint8_t outbuf[MC_CMD_GET_BOARD_CFG_OUT_LEN]; + size_t outlen; + int port_num = efx_port_num(efx); + int offset; + int rc; + + BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_IN_LEN != 0); + + rc = efx_mcdi_rpc(efx, MC_CMD_GET_BOARD_CFG, NULL, 0, + outbuf, sizeof(outbuf), &outlen); + if (rc) + goto fail; + + if (outlen < MC_CMD_GET_BOARD_CFG_OUT_LEN) { + rc = -EMSGSIZE; + goto fail; + } + + offset = (port_num) + ? MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1_OFST + : MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0_OFST; + if (mac_address) + memcpy(mac_address, outbuf + offset, ETH_ALEN); + if (fw_subtype_list) + memcpy(fw_subtype_list, + outbuf + MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_OFST, + MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_LEN); + + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d len=%d\n", __func__, rc, (int)outlen); + + return rc; +} + +int efx_mcdi_log_ctrl(struct efx_nic *efx, bool evq, bool uart, u32 dest_evq) +{ + u8 inbuf[MC_CMD_LOG_CTRL_IN_LEN]; + u32 dest = 0; + int rc; + + if (uart) + dest |= MC_CMD_LOG_CTRL_IN_LOG_DEST_UART; + if (evq) + dest |= MC_CMD_LOG_CTRL_IN_LOG_DEST_EVQ; + + MCDI_SET_DWORD(inbuf, LOG_CTRL_IN_LOG_DEST, dest); + MCDI_SET_DWORD(inbuf, LOG_CTRL_IN_LOG_DEST_EVQ, dest_evq); + + BUILD_BUG_ON(MC_CMD_LOG_CTRL_OUT_LEN != 0); + + rc = efx_mcdi_rpc(efx, MC_CMD_LOG_CTRL, inbuf, sizeof(inbuf), + NULL, 0, NULL); + if (rc) + goto fail; + + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +int efx_mcdi_nvram_types(struct efx_nic *efx, u32 *nvram_types_out) +{ + u8 outbuf[MC_CMD_NVRAM_TYPES_OUT_LEN]; + size_t outlen; + int rc; + + BUILD_BUG_ON(MC_CMD_NVRAM_TYPES_IN_LEN != 0); + + rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_TYPES, NULL, 0, + outbuf, sizeof(outbuf), &outlen); + if (rc) + goto fail; + if (outlen < MC_CMD_NVRAM_TYPES_OUT_LEN) + goto fail; + + *nvram_types_out = MCDI_DWORD(outbuf, NVRAM_TYPES_OUT_TYPES); + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", + __func__, rc); + return rc; +} + +int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type, + size_t *size_out, size_t *erase_size_out, + bool *protected_out) +{ + u8 inbuf[MC_CMD_NVRAM_INFO_IN_LEN]; + u8 outbuf[MC_CMD_NVRAM_INFO_OUT_LEN]; + size_t outlen; + int rc; + + MCDI_SET_DWORD(inbuf, NVRAM_INFO_IN_TYPE, type); + + rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_INFO, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), &outlen); + if (rc) + goto fail; + if (outlen < MC_CMD_NVRAM_INFO_OUT_LEN) + goto fail; + + *size_out = MCDI_DWORD(outbuf, NVRAM_INFO_OUT_SIZE); + *erase_size_out = MCDI_DWORD(outbuf, NVRAM_INFO_OUT_ERASESIZE); + *protected_out = !!(MCDI_DWORD(outbuf, NVRAM_INFO_OUT_FLAGS) & + (1 << MC_CMD_NVRAM_PROTECTED_LBN)); + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +int efx_mcdi_nvram_update_start(struct efx_nic *efx, unsigned int type) +{ + u8 inbuf[MC_CMD_NVRAM_UPDATE_START_IN_LEN]; + int rc; + + MCDI_SET_DWORD(inbuf, NVRAM_UPDATE_START_IN_TYPE, type); + + BUILD_BUG_ON(MC_CMD_NVRAM_UPDATE_START_OUT_LEN != 0); + + rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_UPDATE_START, inbuf, sizeof(inbuf), + NULL, 0, NULL); + if (rc) + goto fail; + + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +int efx_mcdi_nvram_read(struct efx_nic *efx, unsigned int type, + loff_t offset, u8 *buffer, size_t length) +{ + u8 inbuf[MC_CMD_NVRAM_READ_IN_LEN]; + u8 outbuf[MC_CMD_NVRAM_READ_OUT_LEN(length)]; + size_t outlen; + int rc; + + MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_TYPE, type); + MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_OFFSET, offset); + MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_LENGTH, length); + + rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_READ, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), &outlen); + if (rc) + goto fail; + + memcpy(buffer, MCDI_PTR(outbuf, NVRAM_READ_OUT_READ_BUFFER), length); + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +int efx_mcdi_nvram_write(struct efx_nic *efx, unsigned int type, + loff_t offset, const u8 *buffer, size_t length) +{ + u8 inbuf[MC_CMD_NVRAM_WRITE_IN_LEN(length)]; + int rc; + + MCDI_SET_DWORD(inbuf, NVRAM_WRITE_IN_TYPE, type); + MCDI_SET_DWORD(inbuf, NVRAM_WRITE_IN_OFFSET, offset); + MCDI_SET_DWORD(inbuf, NVRAM_WRITE_IN_LENGTH, length); + memcpy(MCDI_PTR(inbuf, NVRAM_WRITE_IN_WRITE_BUFFER), buffer, length); + + BUILD_BUG_ON(MC_CMD_NVRAM_WRITE_OUT_LEN != 0); + + rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_WRITE, inbuf, sizeof(inbuf), + NULL, 0, NULL); + if (rc) + goto fail; + + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type, + loff_t offset, size_t length) +{ + u8 inbuf[MC_CMD_NVRAM_ERASE_IN_LEN]; + int rc; + + MCDI_SET_DWORD(inbuf, NVRAM_ERASE_IN_TYPE, type); + MCDI_SET_DWORD(inbuf, NVRAM_ERASE_IN_OFFSET, offset); + MCDI_SET_DWORD(inbuf, NVRAM_ERASE_IN_LENGTH, length); + + BUILD_BUG_ON(MC_CMD_NVRAM_ERASE_OUT_LEN != 0); + + rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_ERASE, inbuf, sizeof(inbuf), + NULL, 0, NULL); + if (rc) + goto fail; + + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type) +{ + u8 inbuf[MC_CMD_NVRAM_UPDATE_FINISH_IN_LEN]; + int rc; + + MCDI_SET_DWORD(inbuf, NVRAM_UPDATE_FINISH_IN_TYPE, type); + + BUILD_BUG_ON(MC_CMD_NVRAM_UPDATE_FINISH_OUT_LEN != 0); + + rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_UPDATE_FINISH, inbuf, sizeof(inbuf), + NULL, 0, NULL); + if (rc) + goto fail; + + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +int efx_mcdi_handle_assertion(struct efx_nic *efx) +{ + union { + u8 asserts[MC_CMD_GET_ASSERTS_IN_LEN]; + u8 reboot[MC_CMD_REBOOT_IN_LEN]; + } inbuf; + u8 assertion[MC_CMD_GET_ASSERTS_OUT_LEN]; + unsigned int flags, index, ofst; + const char *reason; + size_t outlen; + int retry; + int rc; + + /* Check if the MC is in the assertion handler, retrying twice. Once + * because a boot-time assertion might cause this command to fail + * with EINTR. And once again because GET_ASSERTS can race with + * MC_CMD_REBOOT running on the other port. */ + retry = 2; + do { + MCDI_SET_DWORD(inbuf.asserts, GET_ASSERTS_IN_CLEAR, 0); + rc = efx_mcdi_rpc(efx, MC_CMD_GET_ASSERTS, + inbuf.asserts, MC_CMD_GET_ASSERTS_IN_LEN, + assertion, sizeof(assertion), &outlen); + } while ((rc == -EINTR || rc == -EIO) && retry-- > 0); + + if (rc) + return rc; + if (outlen < MC_CMD_GET_ASSERTS_OUT_LEN) + return -EINVAL; + + flags = MCDI_DWORD(assertion, GET_ASSERTS_OUT_GLOBAL_FLAGS); + if (flags == MC_CMD_GET_ASSERTS_FLAGS_NO_FAILS) + return 0; + + /* Reset the hardware atomically such that only one port with succeed. + * This command will succeed if a reboot is no longer required (because + * the other port did it first), but fail with EIO if it succeeds. + */ + BUILD_BUG_ON(MC_CMD_REBOOT_OUT_LEN != 0); + MCDI_SET_DWORD(inbuf.reboot, REBOOT_IN_FLAGS, + MC_CMD_REBOOT_FLAGS_AFTER_ASSERTION); + efx_mcdi_rpc(efx, MC_CMD_REBOOT, inbuf.reboot, MC_CMD_REBOOT_IN_LEN, + NULL, 0, NULL); + + /* Print out the assertion */ + reason = (flags == MC_CMD_GET_ASSERTS_FLAGS_SYS_FAIL) + ? "system-level assertion" + : (flags == MC_CMD_GET_ASSERTS_FLAGS_THR_FAIL) + ? "thread-level assertion" + : (flags == MC_CMD_GET_ASSERTS_FLAGS_WDOG_FIRED) + ? "watchdog reset" + : "unknown assertion"; + EFX_ERR(efx, "MCPU %s at PC = 0x%.8x in thread 0x%.8x\n", reason, + MCDI_DWORD(assertion, GET_ASSERTS_OUT_SAVED_PC_OFFS), + MCDI_DWORD(assertion, GET_ASSERTS_OUT_THREAD_OFFS)); + + /* Print out the registers */ + ofst = MC_CMD_GET_ASSERTS_OUT_GP_REGS_OFFS_OFST; + for (index = 1; index < 32; index++) { + EFX_ERR(efx, "R%.2d (?): 0x%.8x\n", index, + MCDI_DWORD2(assertion, ofst)); + ofst += sizeof(efx_dword_t); + } + + return 0; +} + +void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode) +{ + u8 inbuf[MC_CMD_SET_ID_LED_IN_LEN]; + int rc; + + BUILD_BUG_ON(EFX_LED_OFF != MC_CMD_LED_OFF); + BUILD_BUG_ON(EFX_LED_ON != MC_CMD_LED_ON); + BUILD_BUG_ON(EFX_LED_DEFAULT != MC_CMD_LED_DEFAULT); + + BUILD_BUG_ON(MC_CMD_SET_ID_LED_OUT_LEN != 0); + + MCDI_SET_DWORD(inbuf, SET_ID_LED_IN_STATE, mode); + + rc = efx_mcdi_rpc(efx, MC_CMD_SET_ID_LED, inbuf, sizeof(inbuf), + NULL, 0, NULL); + if (rc) + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); +} + +int efx_mcdi_reset_port(struct efx_nic *efx) +{ + int rc = efx_mcdi_rpc(efx, MC_CMD_PORT_RESET, NULL, 0, NULL, 0, NULL); + if (rc) + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +int efx_mcdi_reset_mc(struct efx_nic *efx) +{ + u8 inbuf[MC_CMD_REBOOT_IN_LEN]; + int rc; + + BUILD_BUG_ON(MC_CMD_REBOOT_OUT_LEN != 0); + MCDI_SET_DWORD(inbuf, REBOOT_IN_FLAGS, 0); + rc = efx_mcdi_rpc(efx, MC_CMD_REBOOT, inbuf, sizeof(inbuf), + NULL, 0, NULL); + /* White is black, and up is down */ + if (rc == -EIO) + return 0; + if (rc == 0) + rc = -EIO; + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +int efx_mcdi_wol_filter_set(struct efx_nic *efx, u32 type, + const u8 *mac, int *id_out) +{ + u8 inbuf[MC_CMD_WOL_FILTER_SET_IN_LEN]; + u8 outbuf[MC_CMD_WOL_FILTER_SET_OUT_LEN]; + size_t outlen; + int rc; + + MCDI_SET_DWORD(inbuf, WOL_FILTER_SET_IN_WOL_TYPE, type); + MCDI_SET_DWORD(inbuf, WOL_FILTER_SET_IN_FILTER_MODE, + MC_CMD_FILTER_MODE_SIMPLE); + memcpy(MCDI_PTR(inbuf, WOL_FILTER_SET_IN_MAGIC_MAC), mac, ETH_ALEN); + + rc = efx_mcdi_rpc(efx, MC_CMD_WOL_FILTER_SET, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), &outlen); + if (rc) + goto fail; + + if (outlen < MC_CMD_WOL_FILTER_SET_OUT_LEN) { + rc = -EMSGSIZE; + goto fail; + } + + *id_out = (int)MCDI_DWORD(outbuf, WOL_FILTER_SET_OUT_FILTER_ID); + + return 0; + +fail: + *id_out = -1; + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; + +} + + +int +efx_mcdi_wol_filter_set_magic(struct efx_nic *efx, const u8 *mac, int *id_out) +{ + return efx_mcdi_wol_filter_set(efx, MC_CMD_WOL_TYPE_MAGIC, mac, id_out); +} + + +int efx_mcdi_wol_filter_get_magic(struct efx_nic *efx, int *id_out) +{ + u8 outbuf[MC_CMD_WOL_FILTER_GET_OUT_LEN]; + size_t outlen; + int rc; + + rc = efx_mcdi_rpc(efx, MC_CMD_WOL_FILTER_GET, NULL, 0, + outbuf, sizeof(outbuf), &outlen); + if (rc) + goto fail; + + if (outlen < MC_CMD_WOL_FILTER_GET_OUT_LEN) { + rc = -EMSGSIZE; + goto fail; + } + + *id_out = (int)MCDI_DWORD(outbuf, WOL_FILTER_GET_OUT_FILTER_ID); + + return 0; + +fail: + *id_out = -1; + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + + +int efx_mcdi_wol_filter_remove(struct efx_nic *efx, int id) +{ + u8 inbuf[MC_CMD_WOL_FILTER_REMOVE_IN_LEN]; + int rc; + + MCDI_SET_DWORD(inbuf, WOL_FILTER_REMOVE_IN_FILTER_ID, (u32)id); + + rc = efx_mcdi_rpc(efx, MC_CMD_WOL_FILTER_REMOVE, inbuf, sizeof(inbuf), + NULL, 0, NULL); + if (rc) + goto fail; + + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + + +int efx_mcdi_wol_filter_reset(struct efx_nic *efx) +{ + int rc; + + rc = efx_mcdi_rpc(efx, MC_CMD_WOL_FILTER_RESET, NULL, 0, NULL, 0, NULL); + if (rc) + goto fail; + + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + diff --git a/drivers/net/sfc/mcdi.h b/drivers/net/sfc/mcdi.h new file mode 100644 index 000000000000..de916728c2e3 --- /dev/null +++ b/drivers/net/sfc/mcdi.h @@ -0,0 +1,130 @@ +/**************************************************************************** + * Driver for Solarflare Solarstorm network controllers and boards + * Copyright 2008-2009 Solarflare Communications Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +#ifndef EFX_MCDI_H +#define EFX_MCDI_H + +/** + * enum efx_mcdi_state + * @MCDI_STATE_QUIESCENT: No pending MCDI requests. If the caller holds the + * mcdi_lock then they are able to move to MCDI_STATE_RUNNING + * @MCDI_STATE_RUNNING: There is an MCDI request pending. Only the thread that + * moved into this state is allowed to move out of it. + * @MCDI_STATE_COMPLETED: An MCDI request has completed, but the owning thread + * has not yet consumed the result. For all other threads, equivalent to + * MCDI_STATE_RUNNING. + */ +enum efx_mcdi_state { + MCDI_STATE_QUIESCENT, + MCDI_STATE_RUNNING, + MCDI_STATE_COMPLETED, +}; + +enum efx_mcdi_mode { + MCDI_MODE_POLL, + MCDI_MODE_EVENTS, +}; + +/** + * struct efx_mcdi_iface + * @state: Interface state. Waited for by mcdi_wq. + * @wq: Wait queue for threads waiting for state != STATE_RUNNING + * @iface_lock: Protects @credits, @seqno, @resprc, @resplen + * @mode: Poll for mcdi completion, or wait for an mcdi_event. + * Serialised by @lock + * @seqno: The next sequence number to use for mcdi requests. + * Serialised by @lock + * @credits: Number of spurious MCDI completion events allowed before we + * trigger a fatal error. Protected by @lock + * @resprc: Returned MCDI completion + * @resplen: Returned payload length + */ +struct efx_mcdi_iface { + atomic_t state; + wait_queue_head_t wq; + spinlock_t iface_lock; + enum efx_mcdi_mode mode; + unsigned int credits; + unsigned int seqno; + unsigned int resprc; + size_t resplen; +}; + +extern void efx_mcdi_init(struct efx_nic *efx); + +extern int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd, const u8 *inbuf, + size_t inlen, u8 *outbuf, size_t outlen, + size_t *outlen_actual); + +extern int efx_mcdi_poll_reboot(struct efx_nic *efx); +extern void efx_mcdi_mode_poll(struct efx_nic *efx); +extern void efx_mcdi_mode_event(struct efx_nic *efx); + +extern void efx_mcdi_process_event(struct efx_channel *channel, + efx_qword_t *event); + +#define MCDI_PTR2(_buf, _ofst) \ + (((u8 *)_buf) + _ofst) +#define MCDI_SET_DWORD2(_buf, _ofst, _value) \ + EFX_POPULATE_DWORD_1(*((efx_dword_t *)MCDI_PTR2(_buf, _ofst)), \ + EFX_DWORD_0, _value) +#define MCDI_DWORD2(_buf, _ofst) \ + EFX_DWORD_FIELD(*((efx_dword_t *)MCDI_PTR2(_buf, _ofst)), \ + EFX_DWORD_0) +#define MCDI_QWORD2(_buf, _ofst) \ + EFX_QWORD_FIELD64(*((efx_qword_t *)MCDI_PTR2(_buf, _ofst)), \ + EFX_QWORD_0) + +#define MCDI_PTR(_buf, _ofst) \ + MCDI_PTR2(_buf, MC_CMD_ ## _ofst ## _OFST) +#define MCDI_SET_DWORD(_buf, _ofst, _value) \ + MCDI_SET_DWORD2(_buf, MC_CMD_ ## _ofst ## _OFST, _value) +#define MCDI_DWORD(_buf, _ofst) \ + MCDI_DWORD2(_buf, MC_CMD_ ## _ofst ## _OFST) +#define MCDI_QWORD(_buf, _ofst) \ + MCDI_QWORD2(_buf, MC_CMD_ ## _ofst ## _OFST) + +#define MCDI_EVENT_FIELD(_ev, _field) \ + EFX_QWORD_FIELD(_ev, MCDI_EVENT_ ## _field) + +extern int efx_mcdi_fwver(struct efx_nic *efx, u64 *version, u32 *build); +extern int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating, + bool *was_attached_out); +extern int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address, + u16 *fw_subtype_list); +extern int efx_mcdi_log_ctrl(struct efx_nic *efx, bool evq, bool uart, + u32 dest_evq); +extern int efx_mcdi_nvram_types(struct efx_nic *efx, u32 *nvram_types_out); +extern int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type, + size_t *size_out, size_t *erase_size_out, + bool *protected_out); +extern int efx_mcdi_nvram_update_start(struct efx_nic *efx, + unsigned int type); +extern int efx_mcdi_nvram_read(struct efx_nic *efx, unsigned int type, + loff_t offset, u8 *buffer, size_t length); +extern int efx_mcdi_nvram_write(struct efx_nic *efx, unsigned int type, + loff_t offset, const u8 *buffer, + size_t length); +extern int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type, + loff_t offset, size_t length); +extern int efx_mcdi_nvram_update_finish(struct efx_nic *efx, + unsigned int type); +extern int efx_mcdi_handle_assertion(struct efx_nic *efx); +extern void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode); +extern int efx_mcdi_reset_port(struct efx_nic *efx); +extern int efx_mcdi_reset_mc(struct efx_nic *efx); +extern int efx_mcdi_wol_filter_set(struct efx_nic *efx, u32 type, + const u8 *mac, int *id_out); +extern int efx_mcdi_wol_filter_set_magic(struct efx_nic *efx, + const u8 *mac, int *id_out); +extern int efx_mcdi_wol_filter_get_magic(struct efx_nic *efx, int *id_out); +extern int efx_mcdi_wol_filter_remove(struct efx_nic *efx, int id); +extern int efx_mcdi_wol_filter_reset(struct efx_nic *efx); + +#endif /* EFX_MCDI_H */ diff --git a/drivers/net/sfc/mcdi_mac.c b/drivers/net/sfc/mcdi_mac.c new file mode 100644 index 000000000000..06d24a1e412a --- /dev/null +++ b/drivers/net/sfc/mcdi_mac.c @@ -0,0 +1,152 @@ +/**************************************************************************** + * Driver for Solarflare Solarstorm network controllers and boards + * Copyright 2009 Solarflare Communications Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +#include "net_driver.h" +#include "efx.h" +#include "mac.h" +#include "mcdi.h" +#include "mcdi_pcol.h" + +static int efx_mcdi_set_mac(struct efx_nic *efx) +{ + u32 reject, fcntl; + u8 cmdbytes[MC_CMD_SET_MAC_IN_LEN]; + + memcpy(cmdbytes + MC_CMD_SET_MAC_IN_ADDR_OFST, + efx->net_dev->dev_addr, ETH_ALEN); + + MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_MTU, + EFX_MAX_FRAME_LEN(efx->net_dev->mtu)); + MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_DRAIN, 0); + + /* The MCDI command provides for controlling accept/reject + * of broadcast packets too, but the driver doesn't currently + * expose this. */ + reject = (efx->promiscuous) ? 0 : + (1 << MC_CMD_SET_MAC_IN_REJECT_UNCST_LBN); + MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_REJECT, reject); + + switch (efx->wanted_fc) { + case EFX_FC_RX | EFX_FC_TX: + fcntl = MC_CMD_FCNTL_BIDIR; + break; + case EFX_FC_RX: + fcntl = MC_CMD_FCNTL_RESPOND; + break; + default: + fcntl = MC_CMD_FCNTL_OFF; + break; + } + if (efx->wanted_fc & EFX_FC_AUTO) + fcntl = MC_CMD_FCNTL_AUTO; + + MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_FCNTL, fcntl); + + return efx_mcdi_rpc(efx, MC_CMD_SET_MAC, cmdbytes, sizeof(cmdbytes), + NULL, 0, NULL); +} + +static int efx_mcdi_get_mac_faults(struct efx_nic *efx, u32 *faults) +{ + u8 outbuf[MC_CMD_GET_LINK_OUT_LEN]; + size_t outlength; + int rc; + + BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0); + + rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0, + outbuf, sizeof(outbuf), &outlength); + if (rc) + goto fail; + + *faults = MCDI_DWORD(outbuf, GET_LINK_OUT_MAC_FAULT); + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", + __func__, rc); + return rc; +} + +int efx_mcdi_mac_stats(struct efx_nic *efx, dma_addr_t dma_addr, + u32 dma_len, int enable, int clear) +{ + u8 inbuf[MC_CMD_MAC_STATS_IN_LEN]; + int rc; + efx_dword_t *cmd_ptr; + int period = 1000; + u32 addr_hi; + u32 addr_lo; + + BUILD_BUG_ON(MC_CMD_MAC_STATS_OUT_LEN != 0); + + addr_lo = ((u64)dma_addr) >> 0; + addr_hi = ((u64)dma_addr) >> 32; + + MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_ADDR_LO, addr_lo); + MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_ADDR_HI, addr_hi); + cmd_ptr = (efx_dword_t *)MCDI_PTR(inbuf, MAC_STATS_IN_CMD); + if (enable) + EFX_POPULATE_DWORD_6(*cmd_ptr, + MC_CMD_MAC_STATS_CMD_DMA, 1, + MC_CMD_MAC_STATS_CMD_CLEAR, clear, + MC_CMD_MAC_STATS_CMD_PERIODIC_CHANGE, 1, + MC_CMD_MAC_STATS_CMD_PERIODIC_ENABLE, 1, + MC_CMD_MAC_STATS_CMD_PERIODIC_CLEAR, 0, + MC_CMD_MAC_STATS_CMD_PERIOD_MS, period); + else + EFX_POPULATE_DWORD_5(*cmd_ptr, + MC_CMD_MAC_STATS_CMD_DMA, 0, + MC_CMD_MAC_STATS_CMD_CLEAR, clear, + MC_CMD_MAC_STATS_CMD_PERIODIC_CHANGE, 1, + MC_CMD_MAC_STATS_CMD_PERIODIC_ENABLE, 0, + MC_CMD_MAC_STATS_CMD_PERIODIC_CLEAR, 0); + MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_LEN, dma_len); + + rc = efx_mcdi_rpc(efx, MC_CMD_MAC_STATS, inbuf, sizeof(inbuf), + NULL, 0, NULL); + if (rc) + goto fail; + + return 0; + +fail: + EFX_ERR(efx, "%s: %s failed rc=%d\n", + __func__, enable ? "enable" : "disable", rc); + return rc; +} + +static int efx_mcdi_mac_reconfigure(struct efx_nic *efx) +{ + int rc; + + rc = efx_mcdi_set_mac(efx); + if (rc != 0) + return rc; + + /* Restore the multicast hash registers. */ + efx->type->push_multicast_hash(efx); + + return 0; +} + + +static bool efx_mcdi_mac_check_fault(struct efx_nic *efx) +{ + u32 faults; + int rc = efx_mcdi_get_mac_faults(efx, &faults); + return (rc != 0) || (faults != 0); +} + + +struct efx_mac_operations efx_mcdi_mac_operations = { + .reconfigure = efx_mcdi_mac_reconfigure, + .update_stats = efx_port_dummy_op_void, + .check_fault = efx_mcdi_mac_check_fault, +}; diff --git a/drivers/net/sfc/mcdi_pcol.h b/drivers/net/sfc/mcdi_pcol.h new file mode 100644 index 000000000000..2a85360a46f0 --- /dev/null +++ b/drivers/net/sfc/mcdi_pcol.h @@ -0,0 +1,1578 @@ +/**************************************************************************** + * Driver for Solarflare Solarstorm network controllers and boards + * Copyright 2009 Solarflare Communications Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + + +#ifndef MCDI_PCOL_H +#define MCDI_PCOL_H + +/* Values to be written into FMCR_CZ_RESET_STATE_REG to control boot. */ +/* Power-on reset state */ +#define MC_FW_STATE_POR (1) +/* If this is set in MC_RESET_STATE_REG then it should be + * possible to jump into IMEM without loading code from flash. */ +#define MC_FW_WARM_BOOT_OK (2) +/* The MC main image has started to boot. */ +#define MC_FW_STATE_BOOTING (4) +/* The Scheduler has started. */ +#define MC_FW_STATE_SCHED (8) + +/* Values to be written to the per-port status dword in shared + * memory on reboot and assert */ +#define MC_STATUS_DWORD_REBOOT (0xb007b007) +#define MC_STATUS_DWORD_ASSERT (0xdeaddead) + +/* The current version of the MCDI protocol. + * + * Note that the ROM burnt into the card only talks V0, so at the very + * least every driver must support version 0 and MCDI_PCOL_VERSION + */ +#define MCDI_PCOL_VERSION 1 + +/** + * MCDI version 1 + * + * Each MCDI request starts with an MCDI_HEADER, which is a 32byte + * structure, filled in by the client. + * + * 0 7 8 16 20 22 23 24 31 + * | CODE | R | LEN | SEQ | Rsvd | E | R | XFLAGS | + * | | | + * | | \--- Response + * | \------- Error + * \------------------------------ Resync (always set) + * + * The client writes it's request into MC shared memory, and rings the + * doorbell. Each request is completed by either by the MC writting + * back into shared memory, or by writting out an event. + * + * All MCDI commands support completion by shared memory response. Each + * request may also contain additional data (accounted for by HEADER.LEN), + * and some response's may also contain additional data (again, accounted + * for by HEADER.LEN). + * + * Some MCDI commands support completion by event, in which any associated + * response data is included in the event. + * + * The protocol requires one response to be delivered for every request, a + * request should not be sent unless the response for the previous request + * has been received (either by polling shared memory, or by receiving + * an event). + */ + +/** Request/Response structure */ +#define MCDI_HEADER_OFST 0 +#define MCDI_HEADER_CODE_LBN 0 +#define MCDI_HEADER_CODE_WIDTH 7 +#define MCDI_HEADER_RESYNC_LBN 7 +#define MCDI_HEADER_RESYNC_WIDTH 1 +#define MCDI_HEADER_DATALEN_LBN 8 +#define MCDI_HEADER_DATALEN_WIDTH 8 +#define MCDI_HEADER_SEQ_LBN 16 +#define MCDI_HEADER_RSVD_LBN 20 +#define MCDI_HEADER_RSVD_WIDTH 2 +#define MCDI_HEADER_SEQ_WIDTH 4 +#define MCDI_HEADER_ERROR_LBN 22 +#define MCDI_HEADER_ERROR_WIDTH 1 +#define MCDI_HEADER_RESPONSE_LBN 23 +#define MCDI_HEADER_RESPONSE_WIDTH 1 +#define MCDI_HEADER_XFLAGS_LBN 24 +#define MCDI_HEADER_XFLAGS_WIDTH 8 +/* Request response using event */ +#define MCDI_HEADER_XFLAGS_EVREQ 0x01 + +/* Maximum number of payload bytes */ +#define MCDI_CTL_SDU_LEN_MAX 0xfc + +/* The MC can generate events for two reasons: + * - To complete a shared memory request if XFLAGS_EVREQ was set + * - As a notification (link state, i2c event), controlled + * via MC_CMD_LOG_CTRL + * + * Both events share a common structure: + * + * 0 32 33 36 44 52 60 + * | Data | Cont | Level | Src | Code | Rsvd | + * | + * \ There is another event pending in this notification + * + * If Code==CMDDONE, then the fields are further interpreted as: + * + * - LEVEL==INFO Command succeded + * - LEVEL==ERR Command failed + * + * 0 8 16 24 32 + * | Seq | Datalen | Errno | Rsvd | + * + * These fields are taken directly out of the standard MCDI header, i.e., + * LEVEL==ERR, Datalen == 0 => Reboot + * + * Events can be squirted out of the UART (using LOG_CTRL) without a + * MCDI header. An event can be distinguished from a MCDI response by + * examining the first byte which is 0xc0. This corresponds to the + * non-existent MCDI command MC_CMD_DEBUG_LOG. + * + * 0 7 8 + * | command | Resync | = 0xc0 + * + * Since the event is written in big-endian byte order, this works + * providing bits 56-63 of the event are 0xc0. + * + * 56 60 63 + * | Rsvd | Code | = 0xc0 + * + * Which means for convenience the event code is 0xc for all MC + * generated events. + */ +#define FSE_AZ_EV_CODE_MCDI_EVRESPONSE 0xc + +#define MCDI_EVENT_DATA_LBN 0 +#define MCDI_EVENT_DATA_WIDTH 32 +#define MCDI_EVENT_CONT_LBN 32 +#define MCDI_EVENT_CONT_WIDTH 1 +#define MCDI_EVENT_LEVEL_LBN 33 +#define MCDI_EVENT_LEVEL_WIDTH 3 +#define MCDI_EVENT_LEVEL_INFO (0) +#define MCDI_EVENT_LEVEL_WARN (1) +#define MCDI_EVENT_LEVEL_ERR (2) +#define MCDI_EVENT_LEVEL_FATAL (3) +#define MCDI_EVENT_SRC_LBN 36 +#define MCDI_EVENT_SRC_WIDTH 8 +#define MCDI_EVENT_CODE_LBN 44 +#define MCDI_EVENT_CODE_WIDTH 8 +#define MCDI_EVENT_CODE_BADSSERT (1) +#define MCDI_EVENT_CODE_PMNOTICE (2) +#define MCDI_EVENT_CODE_CMDDONE (3) +#define MCDI_EVENT_CMDDONE_SEQ_LBN 0 +#define MCDI_EVENT_CMDDONE_SEQ_WIDTH 8 +#define MCDI_EVENT_CMDDONE_DATALEN_LBN 8 +#define MCDI_EVENT_CMDDONE_DATALEN_WIDTH 8 +#define MCDI_EVENT_CMDDONE_ERRNO_LBN 16 +#define MCDI_EVENT_CMDDONE_ERRNO_WIDTH 8 +#define MCDI_EVENT_CODE_LINKCHANGE (4) +#define MCDI_EVENT_LINKCHANGE_LP_CAP_LBN 0 +#define MCDI_EVENT_LINKCHANGE_LP_CAP_WIDTH 16 +#define MCDI_EVENT_LINKCHANGE_SPEED_LBN 16 +#define MCDI_EVENT_LINKCHANGE_SPEED_WIDTH 4 +#define MCDI_EVENT_LINKCHANGE_SPEED_100M 1 +#define MCDI_EVENT_LINKCHANGE_SPEED_1G 2 +#define MCDI_EVENT_LINKCHANGE_SPEED_10G 3 +#define MCDI_EVENT_LINKCHANGE_FCNTL_LBN 20 +#define MCDI_EVENT_LINKCHANGE_FCNTL_WIDTH 4 +#define MCDI_EVENT_LINKCHANGE_LINK_FLAGS_LBN 24 +#define MCDI_EVENT_LINKCHANGE_LINK_FLAGS_WIDTH 8 +#define MCDI_EVENT_CODE_SENSOREVT (5) +#define MCDI_EVENT_SENSOREVT_MONITOR_LBN 0 +#define MCDI_EVENT_SENSOREVT_MONITOR_WIDTH 8 +#define MCDI_EVENT_SENSOREVT_STATE_LBN 8 +#define MCDI_EVENT_SENSOREVT_STATE_WIDTH 8 +#define MCDI_EVENT_SENSOREVT_VALUE_LBN 16 +#define MCDI_EVENT_SENSOREVT_VALUE_WIDTH 16 +#define MCDI_EVENT_CODE_SCHEDERR (6) +#define MCDI_EVENT_CODE_REBOOT (7) +#define MCDI_EVENT_CODE_MAC_STATS_DMA (8) +#define MCDI_EVENT_MAC_STATS_DMA_GENERATION_LBN 0 +#define MCDI_EVENT_MAC_STATS_DMA_GENERATION_WIDTH 32 + +/* Non-existent command target */ +#define MC_CMD_ERR_ENOENT 2 +/* assert() has killed the MC */ +#define MC_CMD_ERR_EINTR 4 +/* Caller does not hold required locks */ +#define MC_CMD_ERR_EACCES 13 +/* Resource is currently unavailable (e.g. lock contention) */ +#define MC_CMD_ERR_EBUSY 16 +/* Invalid argument to target */ +#define MC_CMD_ERR_EINVAL 22 +/* Non-recursive resource is already acquired */ +#define MC_CMD_ERR_EDEADLK 35 +/* Operation not implemented */ +#define MC_CMD_ERR_ENOSYS 38 +/* Operation timed out */ +#define MC_CMD_ERR_ETIME 62 + +#define MC_CMD_ERR_CODE_OFST 0 + + +/* MC_CMD_READ32: (debug, variadic out) + * Read multiple 32byte words from MC memory + */ +#define MC_CMD_READ32 0x01 +#define MC_CMD_READ32_IN_LEN 8 +#define MC_CMD_READ32_IN_ADDR_OFST 0 +#define MC_CMD_READ32_IN_NUMWORDS_OFST 4 +#define MC_CMD_READ32_OUT_LEN(_numwords) \ + (4 * (_numwords)) +#define MC_CMD_READ32_OUT_BUFFER_OFST 0 + +/* MC_CMD_WRITE32: (debug, variadic in) + * Write multiple 32byte words to MC memory + */ +#define MC_CMD_WRITE32 0x02 +#define MC_CMD_WRITE32_IN_LEN(_numwords) (((_numwords) * 4) + 4) +#define MC_CMD_WRITE32_IN_ADDR_OFST 0 +#define MC_CMD_WRITE32_IN_BUFFER_OFST 4 +#define MC_CMD_WRITE32_OUT_LEN 0 + +/* MC_CMD_COPYCODE: (debug) + * Copy MC code between two locations and jump + */ +#define MC_CMD_COPYCODE 0x03 +#define MC_CMD_COPYCODE_IN_LEN 16 +#define MC_CMD_COPYCODE_IN_SRC_ADDR_OFST 0 +#define MC_CMD_COPYCODE_IN_DEST_ADDR_OFST 4 +#define MC_CMD_COPYCODE_IN_NUMWORDS_OFST 8 +#define MC_CMD_COPYCODE_IN_JUMP_OFST 12 +/* Control should return to the caller rather than jumping */ +#define MC_CMD_COPYCODE_JUMP_NONE 1 +#define MC_CMD_COPYCODE_OUT_LEN 0 + +/* MC_CMD_SET_FUNC: (debug) + * Select function for function-specific commands. + */ +#define MC_CMD_SET_FUNC 0x04 +#define MC_CMD_SET_FUNC_IN_LEN 4 +#define MC_CMD_SET_FUNC_IN_FUNC_OFST 0 +#define MC_CMD_SET_FUNC_OUT_LEN 0 + +/* MC_CMD_GET_BOOT_STATUS: + * Get the instruction address from which the MC booted. + */ +#define MC_CMD_GET_BOOT_STATUS 0x05 +#define MC_CMD_GET_BOOT_STATUS_IN_LEN 0 +#define MC_CMD_GET_BOOT_STATUS_OUT_LEN 8 +#define MC_CMD_GET_BOOT_STATUS_OUT_BOOT_OFFSET_OFST 0 +#define MC_CMD_GET_BOOT_STATUS_OUT_FLAGS_OFST 4 +/* Reboot caused by watchdog */ +#define MC_CMD_GET_BOOT_STATUS_FLAGS_WATCHDOG_LBN (0) +#define MC_CMD_GET_BOOT_STATUS_FLAGS_WATCHDOG_WIDTH (1) +/* MC booted from primary flash partition */ +#define MC_CMD_GET_BOOT_STATUS_FLAGS_PRIMARY_LBN (1) +#define MC_CMD_GET_BOOT_STATUS_FLAGS_PRIMARY_WIDTH (1) +/* MC booted from backup flash partition */ +#define MC_CMD_GET_BOOT_STATUS_FLAGS_BACKUP_LBN (2) +#define MC_CMD_GET_BOOT_STATUS_FLAGS_BACKUP_WIDTH (1) + +/* MC_CMD_GET_ASSERTS: (debug, variadic out) + * Get (and optionally clear) the current assertion status. + * + * Only OUT.GLOBAL_FLAGS is guaranteed to exist in the completion + * payload. The other fields will only be present if + * OUT.GLOBAL_FLAGS != NO_FAILS + */ +#define MC_CMD_GET_ASSERTS 0x06 +#define MC_CMD_GET_ASSERTS_IN_LEN 4 +#define MC_CMD_GET_ASSERTS_IN_CLEAR_OFST 0 +#define MC_CMD_GET_ASSERTS_OUT_LEN 140 +/* Assertion status flag */ +#define MC_CMD_GET_ASSERTS_OUT_GLOBAL_FLAGS_OFST 0 +/*! No assertions have failed. */ +#define MC_CMD_GET_ASSERTS_FLAGS_NO_FAILS 1 +/*! A system-level assertion has failed. */ +#define MC_CMD_GET_ASSERTS_FLAGS_SYS_FAIL 2 +/*! A thread-level assertion has failed. */ +#define MC_CMD_GET_ASSERTS_FLAGS_THR_FAIL 3 +/*! The system was reset by the watchdog. */ +#define MC_CMD_GET_ASSERTS_FLAGS_WDOG_FIRED 4 +/* Failing PC value */ +#define MC_CMD_GET_ASSERTS_OUT_SAVED_PC_OFFS_OFST 4 +/* Saved GP regs */ +#define MC_CMD_GET_ASSERTS_OUT_GP_REGS_OFFS_OFST 8 +#define MC_CMD_GET_ASSERTS_OUT_GP_REGS_LEN 124 +/* Failing thread address */ +#define MC_CMD_GET_ASSERTS_OUT_THREAD_OFFS_OFST 132 + +/* MC_CMD_LOG_CTRL: + * Determine the output stream for various events and messages + */ +#define MC_CMD_LOG_CTRL 0x07 +#define MC_CMD_LOG_CTRL_IN_LEN 8 +#define MC_CMD_LOG_CTRL_IN_LOG_DEST_OFST 0 +#define MC_CMD_LOG_CTRL_IN_LOG_DEST_UART (1) +#define MC_CMD_LOG_CTRL_IN_LOG_DEST_EVQ (2) +#define MC_CMD_LOG_CTRL_IN_LOG_DEST_EVQ_OFST 4 +#define MC_CMD_LOG_CTRL_OUT_LEN 0 + +/* MC_CMD_GET_VERSION: + * Get version information about the MC firmware + */ +#define MC_CMD_GET_VERSION 0x08 +#define MC_CMD_GET_VERSION_IN_LEN 0 +#define MC_CMD_GET_VERSION_V0_OUT_LEN 4 +#define MC_CMD_GET_VERSION_V1_OUT_LEN 32 +#define MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0 +/* Reserved version number to indicate "any" version. */ +#define MC_CMD_GET_VERSION_OUT_FIRMWARE_ANY 0xffffffff +/* The version response of a boot ROM awaiting rescue */ +#define MC_CMD_GET_VERSION_OUT_FIRMWARE_BOOTROM 0xb0070000 +#define MC_CMD_GET_VERSION_V1_OUT_PCOL_OFST 4 +/* 128bit mask of functions supported by the current firmware */ +#define MC_CMD_GET_VERSION_V1_OUT_SUPPORTED_FUNCS_OFST 8 +/* The command set exported by the boot ROM (MCDI v0) */ +#define MC_CMD_GET_VERSION_V0_SUPPORTED_FUNCS { \ + (1 << MC_CMD_READ32) | \ + (1 << MC_CMD_WRITE32) | \ + (1 << MC_CMD_COPYCODE) | \ + (1 << MC_CMD_GET_VERSION), \ + 0, 0, 0 } +#define MC_CMD_GET_VERSION_OUT_VERSION_OFST 24 + +/* Vectors in the boot ROM */ +/* Point to the copycode entry point. */ +#define MC_BOOTROM_COPYCODE_VEC (0x7f4) +/* Points to the recovery mode entry point. */ +#define MC_BOOTROM_NOFLASH_VEC (0x7f8) + +/* Test execution limits */ +#define MC_TESTEXEC_VARIANT_COUNT 16 +#define MC_TESTEXEC_RESULT_COUNT 7 + +/* MC_CMD_SET_TESTVARS: (debug, variadic in) + * Write variant words for test. + * + * The user supplies a bitmap of the variants they wish to set. + * They must ensure that IN.LEN >= 4 + 4 * ffs(BITMAP) + */ +#define MC_CMD_SET_TESTVARS 0x09 +#define MC_CMD_SET_TESTVARS_IN_LEN(_numwords) \ + (4 + 4*(_numwords)) +#define MC_CMD_SET_TESTVARS_IN_ARGS_BITMAP_OFST 0 +/* Up to MC_TESTEXEC_VARIANT_COUNT of 32byte words start here */ +#define MC_CMD_SET_TESTVARS_IN_ARGS_BUFFER_OFST 4 +#define MC_CMD_SET_TESTVARS_OUT_LEN 0 + +/* MC_CMD_GET_TESTRCS: (debug, variadic out) + * Return result words from test. + */ +#define MC_CMD_GET_TESTRCS 0x0a +#define MC_CMD_GET_TESTRCS_IN_LEN 4 +#define MC_CMD_GET_TESTRCS_IN_NUMWORDS_OFST 0 +#define MC_CMD_GET_TESTRCS_OUT_LEN(_numwords) \ + (4 * (_numwords)) +#define MC_CMD_GET_TESTRCS_OUT_BUFFER_OFST 0 + +/* MC_CMD_RUN_TEST: (debug) + * Run the test exported by this firmware image + */ +#define MC_CMD_RUN_TEST 0x0b +#define MC_CMD_RUN_TEST_IN_LEN 0 +#define MC_CMD_RUN_TEST_OUT_LEN 0 + +/* MC_CMD_CSR_READ32: (debug, variadic out) + * Read 32bit words from the indirect memory map + */ +#define MC_CMD_CSR_READ32 0x0c +#define MC_CMD_CSR_READ32_IN_LEN 12 +#define MC_CMD_CSR_READ32_IN_ADDR_OFST 0 +#define MC_CMD_CSR_READ32_IN_STEP_OFST 4 +#define MC_CMD_CSR_READ32_IN_NUMWORDS_OFST 8 +#define MC_CMD_CSR_READ32_OUT_LEN(_numwords) \ + (((_numwords) * 4) + 4) +/* IN.NUMWORDS of 32bit words start here */ +#define MC_CMD_CSR_READ32_OUT_BUFFER_OFST 0 +#define MC_CMD_CSR_READ32_OUT_IREG_STATUS_OFST(_numwords) \ + ((_numwords) * 4) + +/* MC_CMD_CSR_WRITE32: (debug, variadic in) + * Write 32bit dwords to the indirect memory map + */ +#define MC_CMD_CSR_WRITE32 0x0d +#define MC_CMD_CSR_WRITE32_IN_LEN(_numwords) \ + (((_numwords) * 4) + 8) +#define MC_CMD_CSR_WRITE32_IN_ADDR_OFST 0 +#define MC_CMD_CSR_WRITE32_IN_STEP_OFST 4 +/* Multiple 32bit words of data to write start here */ +#define MC_CMD_CSR_WRITE32_IN_BUFFER_OFST 8 +#define MC_CMD_CSR_WRITE32_OUT_LEN 4 +#define MC_CMD_CSR_WRITE32_OUT_STATUS_OFST 0 + +/* MC_CMD_JTAG_WORK: (debug, fpga only) + * Process JTAG work buffer for RBF acceleration. + * + * Host: bit count, (up to) 32 words of data to clock out to JTAG + * (bits 1,0=TMS,TDO for first bit; bits 3,2=TMS,TDO for second bit, etc.) + * MC: bit count, (up to) 32 words of data clocked in from JTAG + * (bit 0=TDI for first bit, bit 1=TDI for second bit, etc.; [31:16] unused) + */ +#define MC_CMD_JTAG_WORK 0x0e + +/* MC_CMD_STACKINFO: (debug, variadic out) + * Get stack information + * + * Host: nothing + * MC: (thread ptr, stack size, free space) for each thread in system + */ +#define MC_CMD_STACKINFO 0x0f + +/* MC_CMD_MDIO_READ: + * MDIO register read + */ +#define MC_CMD_MDIO_READ 0x10 +#define MC_CMD_MDIO_READ_IN_LEN 16 +#define MC_CMD_MDIO_READ_IN_BUS_OFST 0 +#define MC_CMD_MDIO_READ_IN_PRTAD_OFST 4 +#define MC_CMD_MDIO_READ_IN_DEVAD_OFST 8 +#define MC_CMD_MDIO_READ_IN_ADDR_OFST 12 +#define MC_CMD_MDIO_READ_OUT_LEN 8 +#define MC_CMD_MDIO_READ_OUT_VALUE_OFST 0 +#define MC_CMD_MDIO_READ_OUT_STATUS_OFST 4 + +/* MC_CMD_MDIO_WRITE: + * MDIO register write + */ +#define MC_CMD_MDIO_WRITE 0x11 +#define MC_CMD_MDIO_WRITE_IN_LEN 20 +#define MC_CMD_MDIO_WRITE_IN_BUS_OFST 0 +#define MC_CMD_MDIO_WRITE_IN_PRTAD_OFST 4 +#define MC_CMD_MDIO_WRITE_IN_DEVAD_OFST 8 +#define MC_CMD_MDIO_WRITE_IN_ADDR_OFST 12 +#define MC_CMD_MDIO_WRITE_IN_VALUE_OFST 16 +#define MC_CMD_MDIO_WRITE_OUT_LEN 4 +#define MC_CMD_MDIO_WRITE_OUT_STATUS_OFST 0 + +/* By default all the MCDI MDIO operations perform clause45 mode. + * If you want to use clause22 then set DEVAD = MC_CMD_MDIO_CLAUSE22. + */ +#define MC_CMD_MDIO_CLAUSE22 32 + +/* There are two MDIO buses: one for the internal PHY, and one for external + * devices. + */ +#define MC_CMD_MDIO_BUS_INTERNAL 0 +#define MC_CMD_MDIO_BUS_EXTERNAL 1 + +/* The MDIO commands return the raw status bits from the MDIO block. A "good" + * transaction should have the DONE bit set and all other bits clear. + */ +#define MC_CMD_MDIO_STATUS_GOOD 0x08 + + +/* MC_CMD_DBI_WRITE: (debug) + * Write DBI register(s) + * + * Host: address, byte-enables (and VF selection, and cs2 flag), + * value [,address ...] + * MC: nothing + */ +#define MC_CMD_DBI_WRITE 0x12 +#define MC_CMD_DBI_WRITE_IN_LEN(_numwords) \ + (12 * (_numwords)) +#define MC_CMD_DBI_WRITE_IN_ADDRESS_OFST(_word) \ + (((_word) * 12) + 0) +#define MC_CMD_DBI_WRITE_IN_BYTE_MASK_OFST(_word) \ + (((_word) * 12) + 4) +#define MC_CMD_DBI_WRITE_IN_VALUE_OFST(_word) \ + (((_word) * 12) + 8) +#define MC_CMD_DBI_WRITE_OUT_LEN 0 + +/* MC_CMD_DBI_READ: (debug) + * Read DBI register(s) + * + * Host: address, [,address ...] + * MC: value [,value ...] + * (note: this does not support reading from VFs, but is retained for backwards + * compatibility; see MC_CMD_DBI_READX below) + */ +#define MC_CMD_DBI_READ 0x13 +#define MC_CMD_DBI_READ_IN_LEN(_numwords) \ + (4 * (_numwords)) +#define MC_CMD_DBI_READ_OUT_LEN(_numwords) \ + (4 * (_numwords)) + +/* MC_CMD_PORT_READ32: (debug) + * Read a 32-bit register from the indirect port register map. + * + * The port to access is implied by the Shared memory channel used. + */ +#define MC_CMD_PORT_READ32 0x14 +#define MC_CMD_PORT_READ32_IN_LEN 4 +#define MC_CMD_PORT_READ32_IN_ADDR_OFST 0 +#define MC_CMD_PORT_READ32_OUT_LEN 8 +#define MC_CMD_PORT_READ32_OUT_VALUE_OFST 0 +#define MC_CMD_PORT_READ32_OUT_STATUS_OFST 4 + +/* MC_CMD_PORT_WRITE32: (debug) + * Write a 32-bit register to the indirect port register map. + * + * The port to access is implied by the Shared memory channel used. + */ +#define MC_CMD_PORT_WRITE32 0x15 +#define MC_CMD_PORT_WRITE32_IN_LEN 8 +#define MC_CMD_PORT_WRITE32_IN_ADDR_OFST 0 +#define MC_CMD_PORT_WRITE32_IN_VALUE_OFST 4 +#define MC_CMD_PORT_WRITE32_OUT_LEN 4 +#define MC_CMD_PORT_WRITE32_OUT_STATUS_OFST 0 + +/* MC_CMD_PORT_READ128: (debug) + * Read a 128-bit register from indirect port register map + * + * The port to access is implied by the Shared memory channel used. + */ +#define MC_CMD_PORT_READ128 0x16 +#define MC_CMD_PORT_READ128_IN_LEN 4 +#define MC_CMD_PORT_READ128_IN_ADDR_OFST 0 +#define MC_CMD_PORT_READ128_OUT_LEN 20 +#define MC_CMD_PORT_READ128_OUT_VALUE_OFST 0 +#define MC_CMD_PORT_READ128_OUT_STATUS_OFST 16 + +/* MC_CMD_PORT_WRITE128: (debug) + * Write a 128-bit register to indirect port register map. + * + * The port to access is implied by the Shared memory channel used. + */ +#define MC_CMD_PORT_WRITE128 0x17 +#define MC_CMD_PORT_WRITE128_IN_LEN 20 +#define MC_CMD_PORT_WRITE128_IN_ADDR_OFST 0 +#define MC_CMD_PORT_WRITE128_IN_VALUE_OFST 4 +#define MC_CMD_PORT_WRITE128_OUT_LEN 4 +#define MC_CMD_PORT_WRITE128_OUT_STATUS_OFST 0 + +/* MC_CMD_GET_BOARD_CFG: + * Returns the MC firmware configuration structure + * + * The FW_SUBTYPE_LIST contains a 16-bit value for each of the 12 types of + * NVRAM area. The values are defined in the firmware/mc/platform/<xxx>.c file + * for a specific board type, but otherwise have no meaning to the MC; they + * are used by the driver to manage selection of appropriate firmware updates. + */ +#define MC_CMD_GET_BOARD_CFG 0x18 +#define MC_CMD_GET_BOARD_CFG_IN_LEN 0 +#define MC_CMD_GET_BOARD_CFG_OUT_LEN 96 +#define MC_CMD_GET_BOARD_CFG_OUT_BOARD_TYPE_OFST 0 +#define MC_CMD_GET_BOARD_CFG_OUT_BOARD_NAME_OFST 4 +#define MC_CMD_GET_BOARD_CFG_OUT_BOARD_NAME_LEN 32 +#define MC_CMD_GET_BOARD_CFG_OUT_CAPABILITIES_PORT0_OFST 36 +#define MC_CMD_GET_BOARD_CFG_OUT_CAPABILITIES_PORT1_OFST 40 +#define MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0_OFST 44 +#define MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0_LEN 6 +#define MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1_OFST 50 +#define MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1_LEN 6 +#define MC_CMD_GET_BOARD_CFG_OUT_MAC_COUNT_PORT0_OFST 56 +#define MC_CMD_GET_BOARD_CFG_OUT_MAC_COUNT_PORT1_OFST 60 +#define MC_CMD_GET_BOARD_CFG_OUT_MAC_STRIDE_PORT0_OFST 64 +#define MC_CMD_GET_BOARD_CFG_OUT_MAC_STRIDE_PORT1_OFST 68 +#define MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_OFST 72 +#define MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_LEN 24 + +/* MC_CMD_DBI_READX: (debug) + * Read DBI register(s) -- extended functionality + * + * Host: vf selection, address, [,vf selection ...] + * MC: value [,value ...] + */ +#define MC_CMD_DBI_READX 0x19 +#define MC_CMD_DBI_READX_IN_LEN(_numwords) \ + (8*(_numwords)) +#define MC_CMD_DBI_READX_OUT_LEN(_numwords) \ + (4*(_numwords)) + +/* MC_CMD_SET_RAND_SEED: + * Set the 16byte seed for the MC psuedo-random generator + */ +#define MC_CMD_SET_RAND_SEED 0x1a +#define MC_CMD_SET_RAND_SEED_IN_LEN 16 +#define MC_CMD_SET_RAND_SEED_IN_SEED_OFST 0 +#define MC_CMD_SET_RAND_SEED_OUT_LEN 0 + +/* MC_CMD_LTSSM_HIST: (debug) + * Retrieve the history of the LTSSM, if the build supports it. + * + * Host: nothing + * MC: variable number of LTSSM values, as bytes + * The history is read-to-clear. + */ +#define MC_CMD_LTSSM_HIST 0x1b + +/* MC_CMD_DRV_ATTACH: + * Inform MCPU that this port is managed on the host (i.e. driver active) + */ +#define MC_CMD_DRV_ATTACH 0x1c +#define MC_CMD_DRV_ATTACH_IN_LEN 8 +#define MC_CMD_DRV_ATTACH_IN_NEW_STATE_OFST 0 +#define MC_CMD_DRV_ATTACH_IN_UPDATE_OFST 4 +#define MC_CMD_DRV_ATTACH_OUT_LEN 4 +#define MC_CMD_DRV_ATTACH_OUT_OLD_STATE_OFST 0 + +/* MC_CMD_NCSI_PROD: (debug) + * Trigger an NC-SI event (and possibly an AEN in response) + */ +#define MC_CMD_NCSI_PROD 0x1d +#define MC_CMD_NCSI_PROD_IN_LEN 4 +#define MC_CMD_NCSI_PROD_IN_EVENTS_OFST 0 +#define MC_CMD_NCSI_PROD_LINKCHANGE_LBN 0 +#define MC_CMD_NCSI_PROD_LINKCHANGE_WIDTH 1 +#define MC_CMD_NCSI_PROD_RESET_LBN 1 +#define MC_CMD_NCSI_PROD_RESET_WIDTH 1 +#define MC_CMD_NCSI_PROD_DRVATTACH_LBN 2 +#define MC_CMD_NCSI_PROD_DRVATTACH_WIDTH 1 +#define MC_CMD_NCSI_PROD_OUT_LEN 0 + +/* Enumeration */ +#define MC_CMD_NCSI_PROD_LINKCHANGE 0 +#define MC_CMD_NCSI_PROD_RESET 1 +#define MC_CMD_NCSI_PROD_DRVATTACH 2 + +/* MC_CMD_DEVEL: (debug) + * Reserved for development + */ +#define MC_CMD_DEVEL 0x1e + +/* MC_CMD_SHMUART: (debug) + * Route UART output to circular buffer in shared memory instead. + */ +#define MC_CMD_SHMUART 0x1f +#define MC_CMD_SHMUART_IN_FLAG_OFST 0 +#define MC_CMD_SHMUART_IN_LEN 4 +#define MC_CMD_SHMUART_OUT_LEN 0 + +/* MC_CMD_PORT_RESET: + * Generic per-port reset. There is no equivalent for per-board reset. + * + * Locks required: None + * Return code: 0, ETIME + */ +#define MC_CMD_PORT_RESET 0x20 +#define MC_CMD_PORT_RESET_IN_LEN 0 +#define MC_CMD_PORT_RESET_OUT_LEN 0 + +/* MC_CMD_RESOURCE_LOCK: + * Generic resource lock/unlock interface. + * + * Locks required: None + * Return code: 0, + * EBUSY (if trylock is contended by other port), + * EDEADLK (if trylock is already acquired by this port) + * EINVAL (if unlock doesn't own the lock) + */ +#define MC_CMD_RESOURCE_LOCK 0x21 +#define MC_CMD_RESOURCE_LOCK_IN_LEN 8 +#define MC_CMD_RESOURCE_LOCK_IN_ACTION_OFST 0 +#define MC_CMD_RESOURCE_LOCK_ACTION_TRYLOCK 1 +#define MC_CMD_RESOURCE_LOCK_ACTION_UNLOCK 0 +#define MC_CMD_RESOURCE_LOCK_IN_RESOURCE_OFST 4 +#define MC_CMD_RESOURCE_LOCK_I2C 2 +#define MC_CMD_RESOURCE_LOCK_PHY 3 +#define MC_CMD_RESOURCE_LOCK_OUT_LEN 0 + +/* MC_CMD_SPI_COMMAND: (variadic in, variadic out) + * Read/Write to/from the SPI device. + * + * Locks required: SPI_LOCK + * Return code: 0, ETIME, EINVAL, EACCES (if SPI_LOCK is not held) + */ +#define MC_CMD_SPI_COMMAND 0x22 +#define MC_CMD_SPI_COMMAND_IN_LEN(_write_bytes) (12 + (_write_bytes)) +#define MC_CMD_SPI_COMMAND_IN_ARGS_OFST 0 +#define MC_CMD_SPI_COMMAND_IN_ARGS_ADDRESS_OFST 0 +#define MC_CMD_SPI_COMMAND_IN_ARGS_READ_BYTES_OFST 4 +#define MC_CMD_SPI_COMMAND_IN_ARGS_CHIP_SELECT_OFST 8 +/* Data to write here */ +#define MC_CMD_SPI_COMMAND_IN_WRITE_BUFFER_OFST 12 +#define MC_CMD_SPI_COMMAND_OUT_LEN(_read_bytes) (_read_bytes) +/* Data read here */ +#define MC_CMD_SPI_COMMAND_OUT_READ_BUFFER_OFST 0 + +/* MC_CMD_I2C_READ_WRITE: (variadic in, variadic out) + * Read/Write to/from the I2C bus. + * + * Locks required: I2C_LOCK + * Return code: 0, ETIME, EINVAL, EACCES (if I2C_LOCK is not held) + */ +#define MC_CMD_I2C_RW 0x23 +#define MC_CMD_I2C_RW_IN_LEN(_write_bytes) (8 + (_write_bytes)) +#define MC_CMD_I2C_RW_IN_ARGS_OFST 0 +#define MC_CMD_I2C_RW_IN_ARGS_ADDR_OFST 0 +#define MC_CMD_I2C_RW_IN_ARGS_READ_BYTES_OFST 4 +/* Data to write here */ +#define MC_CMD_I2C_RW_IN_WRITE_BUFFER_OFSET 8 +#define MC_CMD_I2C_RW_OUT_LEN(_read_bytes) (_read_bytes) +/* Data read here */ +#define MC_CMD_I2C_RW_OUT_READ_BUFFER_OFST 0 + +/* Generic phy capability bitmask */ +#define MC_CMD_PHY_CAP_10HDX_LBN 1 +#define MC_CMD_PHY_CAP_10HDX_WIDTH 1 +#define MC_CMD_PHY_CAP_10FDX_LBN 2 +#define MC_CMD_PHY_CAP_10FDX_WIDTH 1 +#define MC_CMD_PHY_CAP_100HDX_LBN 3 +#define MC_CMD_PHY_CAP_100HDX_WIDTH 1 +#define MC_CMD_PHY_CAP_100FDX_LBN 4 +#define MC_CMD_PHY_CAP_100FDX_WIDTH 1 +#define MC_CMD_PHY_CAP_1000HDX_LBN 5 +#define MC_CMD_PHY_CAP_1000HDX_WIDTH 1 +#define MC_CMD_PHY_CAP_1000FDX_LBN 6 +#define MC_CMD_PHY_CAP_1000FDX_WIDTH 1 +#define MC_CMD_PHY_CAP_10000FDX_LBN 7 +#define MC_CMD_PHY_CAP_10000FDX_WIDTH 1 +#define MC_CMD_PHY_CAP_PAUSE_LBN 8 +#define MC_CMD_PHY_CAP_PAUSE_WIDTH 1 +#define MC_CMD_PHY_CAP_ASYM_LBN 9 +#define MC_CMD_PHY_CAP_ASYM_WIDTH 1 +#define MC_CMD_PHY_CAP_AN_LBN 10 +#define MC_CMD_PHY_CAP_AN_WIDTH 1 + +/* Generic loopback enumeration */ +#define MC_CMD_LOOPBACK_NONE 0 +#define MC_CMD_LOOPBACK_DATA 1 +#define MC_CMD_LOOPBACK_GMAC 2 +#define MC_CMD_LOOPBACK_XGMII 3 +#define MC_CMD_LOOPBACK_XGXS 4 +#define MC_CMD_LOOPBACK_XAUI 5 +#define MC_CMD_LOOPBACK_GMII 6 +#define MC_CMD_LOOPBACK_SGMII 7 +#define MC_CMD_LOOPBACK_XGBR 8 +#define MC_CMD_LOOPBACK_XFI 9 +#define MC_CMD_LOOPBACK_XAUI_FAR 10 +#define MC_CMD_LOOPBACK_GMII_FAR 11 +#define MC_CMD_LOOPBACK_SGMII_FAR 12 +#define MC_CMD_LOOPBACK_XFI_FAR 13 +#define MC_CMD_LOOPBACK_GPHY 14 +#define MC_CMD_LOOPBACK_PHYXS 15 +#define MC_CMD_LOOPBACK_PCS 16 +#define MC_CMD_LOOPBACK_PMAPMD 17 +#define MC_CMD_LOOPBACK_XPORT 18 +#define MC_CMD_LOOPBACK_XGMII_WS 19 +#define MC_CMD_LOOPBACK_XAUI_WS 20 +#define MC_CMD_LOOPBACK_XAUI_WS_FAR 21 +#define MC_CMD_LOOPBACK_XAUI_WS_NEAR 22 +#define MC_CMD_LOOPBACK_GMII_WS 23 +#define MC_CMD_LOOPBACK_XFI_WS 24 +#define MC_CMD_LOOPBACK_XFI_WS_FAR 25 +#define MC_CMD_LOOPBACK_PHYXS_WS 26 + +/* Generic PHY statistics enumeration */ +#define MC_CMD_OUI 0 +#define MC_CMD_PMA_PMD_LINK_UP 1 +#define MC_CMD_PMA_PMD_RX_FAULT 2 +#define MC_CMD_PMA_PMD_TX_FAULT 3 +#define MC_CMD_PMA_PMD_SIGNAL 4 +#define MC_CMD_PMA_PMD_SNR_A 5 +#define MC_CMD_PMA_PMD_SNR_B 6 +#define MC_CMD_PMA_PMD_SNR_C 7 +#define MC_CMD_PMA_PMD_SNR_D 8 +#define MC_CMD_PCS_LINK_UP 9 +#define MC_CMD_PCS_RX_FAULT 10 +#define MC_CMD_PCS_TX_FAULT 11 +#define MC_CMD_PCS_BER 12 +#define MC_CMD_PCS_BLOCK_ERRORS 13 +#define MC_CMD_PHYXS_LINK_UP 14 +#define MC_CMD_PHYXS_RX_FAULT 15 +#define MC_CMD_PHYXS_TX_FAULT 16 +#define MC_CMD_PHYXS_ALIGN 17 +#define MC_CMD_PHYXS_SYNC 18 +#define MC_CMD_AN_LINK_UP 19 +#define MC_CMD_AN_COMPLETE 20 +#define MC_CMD_AN_10GBT_STATUS 21 +#define MC_CMD_CL22_LINK_UP 22 +#define MC_CMD_PHY_NSTATS 23 + +/* MC_CMD_GET_PHY_CFG: + * Report PHY configuration. This guarantees to succeed even if the PHY is in + * a "zombie" state. + * + * Locks required: None + * Return code: 0 + */ +#define MC_CMD_GET_PHY_CFG 0x24 + +#define MC_CMD_GET_PHY_CFG_IN_LEN 0 +#define MC_CMD_GET_PHY_CFG_OUT_LEN 72 + +#define MC_CMD_GET_PHY_CFG_OUT_FLAGS_OFST 0 +#define MC_CMD_GET_PHY_CFG_PRESENT_LBN 0 +#define MC_CMD_GET_PHY_CFG_PRESENT_WIDTH 1 +#define MC_CMD_GET_PHY_CFG_SHORTBIST_LBN 1 +#define MC_CMD_GET_PHY_CFG_SHORTBIST_WIDTH 1 +#define MC_CMD_GET_PHY_CFG_LONGBIST_LBN 2 +#define MC_CMD_GET_PHY_CFG_LONGBIST_WIDTH 1 +#define MC_CMD_GET_PHY_CFG_LOWPOWER_LBN 3 +#define MC_CMD_GET_PHY_CFG_LOWPOWER_WIDTH 1 +#define MC_CMD_GET_PHY_CFG_POWEROFF_LBN 4 +#define MC_CMD_GET_PHY_CFG_POWEROFF_WIDTH 1 +#define MC_CMD_GET_PHY_CFG_TXDIS_LBN 5 +#define MC_CMD_GET_PHY_CFG_TXDIS_WIDTH 1 +#define MC_CMD_GET_PHY_CFG_OUT_TYPE_OFST 4 +/* Bitmask of supported capabilities */ +#define MC_CMD_GET_PHY_CFG_OUT_SUPPORTED_CAP_OFST 8 +#define MC_CMD_GET_PHY_CFG_OUT_CHANNEL_OFST 12 +#define MC_CMD_GET_PHY_CFG_OUT_PRT_OFST 16 +/* PHY statistics bitmap */ +#define MC_CMD_GET_PHY_CFG_OUT_STATS_MASK_OFST 20 +/* PHY type/name string */ +#define MC_CMD_GET_PHY_CFG_OUT_NAME_OFST 24 +#define MC_CMD_GET_PHY_CFG_OUT_NAME_LEN 20 +#define MC_CMD_GET_PHY_CFG_OUT_MEDIA_TYPE_OFST 44 +#define MC_CMD_MEDIA_XAUI 1 +#define MC_CMD_MEDIA_CX4 2 +#define MC_CMD_MEDIA_KX4 3 +#define MC_CMD_MEDIA_XFP 4 +#define MC_CMD_MEDIA_SFP_PLUS 5 +#define MC_CMD_MEDIA_BASE_T 6 +/* MDIO "MMDS" supported */ +#define MC_CMD_GET_PHY_CFG_OUT_MMD_MASK_OFST 48 +/* Native clause 22 */ +#define MC_CMD_MMD_CLAUSE22 0 +#define MC_CMD_MMD_CLAUSE45_PMAPMD 1 +#define MC_CMD_MMD_CLAUSE45_WIS 2 +#define MC_CMD_MMD_CLAUSE45_PCS 3 +#define MC_CMD_MMD_CLAUSE45_PHYXS 4 +#define MC_CMD_MMD_CLAUSE45_DTEXS 5 +#define MC_CMD_MMD_CLAUSE45_TC 6 +#define MC_CMD_MMD_CLAUSE45_AN 7 +/* Clause22 proxied over clause45 by PHY */ +#define MC_CMD_MMD_CLAUSE45_C22EXT 29 +#define MC_CMD_MMD_CLAUSE45_VEND1 30 +#define MC_CMD_MMD_CLAUSE45_VEND2 31 +/* PHY stepping version */ +#define MC_CMD_GET_PHY_CFG_OUT_REVISION_OFST 52 +#define MC_CMD_GET_PHY_CFG_OUT_REVISION_LEN 20 + +/* MC_CMD_START_PHY_BIST: + * Start a BIST test on the PHY. + * + * Locks required: PHY_LOCK if doing a PHY BIST + * Return code: 0, EINVAL, EACCES (if PHY_LOCK is not held) + */ +#define MC_CMD_START_BIST 0x25 +#define MC_CMD_START_BIST_IN_LEN 4 +#define MC_CMD_START_BIST_TYPE_OFST 0 + +/* Run the PHY's short BIST */ +#define MC_CMD_PHY_BIST_SHORT 1 +/* Run the PHY's long BIST */ +#define MC_CMD_PHY_BIST_LONG 2 +/* Run BIST on the currently selected BPX Serdes (XAUI or XFI) */ +#define MC_CMD_BPX_SERDES_BIST 3 + +/* MC_CMD_POLL_PHY_BIST: (variadic output) + * Poll for BIST completion + * + * Returns a single status code, and a binary blob of phy-specific + * bist output. If the driver can't succesfully parse the BIST output, + * it should still respect the Pass/Fail in OUT.RESULT. + * + * Locks required: PHY_LOCK if doing a PHY BIST + * Return code: 0, EACCES (if PHY_LOCK is not held) + */ +#define MC_CMD_POLL_BIST 0x26 +#define MC_CMD_POLL_BIST_IN_LEN 0 +#define MC_CMD_POLL_BIST_OUT_LEN UNKNOWN +#define MC_CMD_POLL_BIST_OUT_RESULT_OFST 0 +#define MC_CMD_POLL_BIST_RUNNING 1 +#define MC_CMD_POLL_BIST_PASSED 2 +#define MC_CMD_POLL_BIST_FAILED 3 +#define MC_CMD_POLL_BIST_TIMEOUT 4 +#define MC_CMD_POLL_BIST_OUT_PRIVATE_OFST 4 + +/* MC_CMD_PHY_SPI: (variadic in, variadic out) + * Read/Write/Erase the PHY SPI device + * + * Locks required: PHY_LOCK + * Return code: 0, ETIME, EINVAL, EACCES (if PHY_LOCK is not held) + */ +#define MC_CMD_PHY_SPI 0x27 +#define MC_CMD_PHY_SPI_IN_LEN(_write_bytes) (12 + (_write_bytes)) +#define MC_CMD_PHY_SPI_IN_ARGS_OFST 0 +#define MC_CMD_PHY_SPI_IN_ARGS_ADDR_OFST 0 +#define MC_CMD_PHY_SPI_IN_ARGS_READ_BYTES_OFST 4 +#define MC_CMD_PHY_SPI_IN_ARGS_ERASE_ALL_OFST 8 +/* Data to write here */ +#define MC_CMD_PHY_SPI_IN_WRITE_BUFFER_OFSET 12 +#define MC_CMD_PHY_SPI_OUT_LEN(_read_bytes) (_read_bytes) +/* Data read here */ +#define MC_CMD_PHY_SPI_OUT_READ_BUFFER_OFST 0 + + +/* MC_CMD_GET_LOOPBACK_MODES: + * Returns a bitmask of loopback modes evailable at each speed. + * + * Locks required: None + * Return code: 0 + */ +#define MC_CMD_GET_LOOPBACK_MODES 0x28 +#define MC_CMD_GET_LOOPBACK_MODES_IN_LEN 0 +#define MC_CMD_GET_LOOPBACK_MODES_OUT_LEN 32 +#define MC_CMD_GET_LOOPBACK_MODES_100M_OFST 0 +#define MC_CMD_GET_LOOPBACK_MODES_1G_OFST 8 +#define MC_CMD_GET_LOOPBACK_MODES_10G_OFST 16 +#define MC_CMD_GET_LOOPBACK_MODES_SUGGESTED_OFST 24 + +/* Flow control enumeration */ +#define MC_CMD_FCNTL_OFF 0 +#define MC_CMD_FCNTL_RESPOND 1 +#define MC_CMD_FCNTL_BIDIR 2 +/* Auto - Use what the link has autonegotiated + * - The driver should modify the advertised capabilities via SET_LINK.CAP + * to control the negotiated flow control mode. + * - Can only be set if the PHY supports PAUSE+ASYM capabilities + * - Never returned by GET_LINK as the value programmed into the MAC + */ +#define MC_CMD_FCNTL_AUTO 3 + +/* Generic mac fault bitmask */ +#define MC_CMD_MAC_FAULT_XGMII_LOCAL_LBN 0 +#define MC_CMD_MAC_FAULT_XGMII_LOCAL_WIDTH 1 +#define MC_CMD_MAC_FAULT_XGMII_REMOTE_LBN 1 +#define MC_CMD_MAC_FAULT_XGMII_REMOTE_WIDTH 1 +#define MC_CMD_MAC_FAULT_SGMII_REMOTE_LBN 2 +#define MC_CMD_MAC_FAULT_SGMII_REMOTE_WIDTH 1 + +/* MC_CMD_GET_LINK: + * Read the unified MAC/PHY link state + * + * Locks required: None + * Return code: 0, ETIME + */ +#define MC_CMD_GET_LINK 0x29 +#define MC_CMD_GET_LINK_IN_LEN 0 +#define MC_CMD_GET_LINK_OUT_LEN 28 +/* near-side and link-partner advertised capabilities */ +#define MC_CMD_GET_LINK_OUT_CAP_OFST 0 +#define MC_CMD_GET_LINK_OUT_LP_CAP_OFST 4 +/* Autonegotiated speed in mbit/s. The link may still be down + * even if this reads non-zero */ +#define MC_CMD_GET_LINK_OUT_LINK_SPEED_OFST 8 +#define MC_CMD_GET_LINK_OUT_LOOPBACK_MODE_OFST 12 +#define MC_CMD_GET_LINK_OUT_FLAGS_OFST 16 +/* Whether we have overall link up */ +#define MC_CMD_GET_LINK_LINK_UP_LBN 0 +#define MC_CMD_GET_LINK_LINK_UP_WIDTH 1 +#define MC_CMD_GET_LINK_FULL_DUPLEX_LBN 1 +#define MC_CMD_GET_LINK_FULL_DUPLEX_WIDTH 1 +/* Whether we have link at the layers provided by the BPX */ +#define MC_CMD_GET_LINK_BPX_LINK_LBN 2 +#define MC_CMD_GET_LINK_BPX_LINK_WIDTH 1 +/* Whether the PHY has external link */ +#define MC_CMD_GET_LINK_PHY_LINK_LBN 3 +#define MC_CMD_GET_LINK_PHY_LINK_WIDTH 1 +#define MC_CMD_GET_LINK_OUT_FCNTL_OFST 20 +#define MC_CMD_GET_LINK_OUT_MAC_FAULT_OFST 24 + +/* MC_CMD_SET_LINK: + * Write the unified MAC/PHY link configuration + * + * A loopback speed of "0" is supported, and means + * (choose any available speed) + * + * Locks required: None + * Return code: 0, EINVAL, ETIME + */ +#define MC_CMD_SET_LINK 0x2a +#define MC_CMD_SET_LINK_IN_LEN 16 +#define MC_CMD_SET_LINK_IN_CAP_OFST 0 +#define MC_CMD_SET_LINK_IN_FLAGS_OFST 4 +#define MC_CMD_SET_LINK_LOWPOWER_LBN 0 +#define MC_CMD_SET_LINK_LOWPOWER_WIDTH 1 +#define MC_CMD_SET_LINK_POWEROFF_LBN 1 +#define MC_CMD_SET_LINK_POWEROFF_WIDTH 1 +#define MC_CMD_SET_LINK_TXDIS_LBN 2 +#define MC_CMD_SET_LINK_TXDIS_WIDTH 1 +#define MC_CMD_SET_LINK_IN_LOOPBACK_MODE_OFST 8 +#define MC_CMD_SET_LINK_IN_LOOPBACK_SPEED_OFST 12 +#define MC_CMD_SET_LINK_OUT_LEN 0 + +/* MC_CMD_SET_ID_LED: + * Set indentification LED state + * + * Locks required: None + * Return code: 0, EINVAL + */ +#define MC_CMD_SET_ID_LED 0x2b +#define MC_CMD_SET_ID_LED_IN_LEN 4 +#define MC_CMD_SET_ID_LED_IN_STATE_OFST 0 +#define MC_CMD_LED_OFF 0 +#define MC_CMD_LED_ON 1 +#define MC_CMD_LED_DEFAULT 2 +#define MC_CMD_SET_ID_LED_OUT_LEN 0 + +/* MC_CMD_SET_MAC: + * Set MAC configuration + * + * The MTU is the MTU programmed directly into the XMAC/GMAC + * (inclusive of EtherII, VLAN, bug16011 padding) + * + * Locks required: None + * Return code: 0, EINVAL + */ +#define MC_CMD_SET_MAC 0x2c +#define MC_CMD_SET_MAC_IN_LEN 24 +#define MC_CMD_SET_MAC_IN_MTU_OFST 0 +#define MC_CMD_SET_MAC_IN_DRAIN_OFST 4 +#define MC_CMD_SET_MAC_IN_ADDR_OFST 8 +#define MC_CMD_SET_MAC_IN_REJECT_OFST 16 +#define MC_CMD_SET_MAC_IN_REJECT_UNCST_LBN 0 +#define MC_CMD_SET_MAC_IN_REJECT_UNCST_WIDTH 1 +#define MC_CMD_SET_MAC_IN_REJECT_BRDCST_LBN 1 +#define MC_CMD_SET_MAC_IN_REJECT_BRDCST_WIDTH 1 +#define MC_CMD_SET_MAC_IN_FCNTL_OFST 20 +#define MC_CMD_SET_MAC_OUT_LEN 0 + +/* MC_CMD_PHY_STATS: + * Get generic PHY statistics + * + * This call returns the statistics for a generic PHY, by direct DMA + * into host memory, in a sparse array (indexed by the enumerate). + * Each value is represented by a 32bit number. + * + * Locks required: None + * Returns: 0, ETIME + * Response methods: shared memory, event + */ +#define MC_CMD_PHY_STATS 0x2d +#define MC_CMD_PHY_STATS_IN_LEN 8 +#define MC_CMD_PHY_STATS_IN_DMA_ADDR_LO_OFST 0 +#define MC_CMD_PHY_STATS_IN_DMA_ADDR_HI_OFST 4 +#define MC_CMD_PHY_STATS_OUT_LEN 0 + +/* Unified MAC statistics enumeration */ +#define MC_CMD_MAC_GENERATION_START 0 +#define MC_CMD_MAC_TX_PKTS 1 +#define MC_CMD_MAC_TX_PAUSE_PKTS 2 +#define MC_CMD_MAC_TX_CONTROL_PKTS 3 +#define MC_CMD_MAC_TX_UNICAST_PKTS 4 +#define MC_CMD_MAC_TX_MULTICAST_PKTS 5 +#define MC_CMD_MAC_TX_BROADCAST_PKTS 6 +#define MC_CMD_MAC_TX_BYTES 7 +#define MC_CMD_MAC_TX_BAD_BYTES 8 +#define MC_CMD_MAC_TX_LT64_PKTS 9 +#define MC_CMD_MAC_TX_64_PKTS 10 +#define MC_CMD_MAC_TX_65_TO_127_PKTS 11 +#define MC_CMD_MAC_TX_128_TO_255_PKTS 12 +#define MC_CMD_MAC_TX_256_TO_511_PKTS 13 +#define MC_CMD_MAC_TX_512_TO_1023_PKTS 14 +#define MC_CMD_MAC_TX_1024_TO_15XX_PKTS 15 +#define MC_CMD_MAC_TX_15XX_TO_JUMBO_PKTS 16 +#define MC_CMD_MAC_TX_GTJUMBO_PKTS 17 +#define MC_CMD_MAC_TX_BAD_FCS_PKTS 18 +#define MC_CMD_MAC_TX_SINGLE_COLLISION_PKTS 19 +#define MC_CMD_MAC_TX_MULTIPLE_COLLISION_PKTS 20 +#define MC_CMD_MAC_TX_EXCESSIVE_COLLISION_PKTS 21 +#define MC_CMD_MAC_TX_LATE_COLLISION_PKTS 22 +#define MC_CMD_MAC_TX_DEFERRED_PKTS 23 +#define MC_CMD_MAC_TX_EXCESSIVE_DEFERRED_PKTS 24 +#define MC_CMD_MAC_TX_NON_TCPUDP_PKTS 25 +#define MC_CMD_MAC_TX_MAC_SRC_ERR_PKTS 26 +#define MC_CMD_MAC_TX_IP_SRC_ERR_PKTS 27 +#define MC_CMD_MAC_RX_PKTS 28 +#define MC_CMD_MAC_RX_PAUSE_PKTS 29 +#define MC_CMD_MAC_RX_GOOD_PKTS 30 +#define MC_CMD_MAC_RX_CONTROL_PKTS 31 +#define MC_CMD_MAC_RX_UNICAST_PKTS 32 +#define MC_CMD_MAC_RX_MULTICAST_PKTS 33 +#define MC_CMD_MAC_RX_BROADCAST_PKTS 34 +#define MC_CMD_MAC_RX_BYTES 35 +#define MC_CMD_MAC_RX_BAD_BYTES 36 +#define MC_CMD_MAC_RX_64_PKTS 37 +#define MC_CMD_MAC_RX_65_TO_127_PKTS 38 +#define MC_CMD_MAC_RX_128_TO_255_PKTS 39 +#define MC_CMD_MAC_RX_256_TO_511_PKTS 40 +#define MC_CMD_MAC_RX_512_TO_1023_PKTS 41 +#define MC_CMD_MAC_RX_1024_TO_15XX_PKTS 42 +#define MC_CMD_MAC_RX_15XX_TO_JUMBO_PKTS 43 +#define MC_CMD_MAC_RX_GTJUMBO_PKTS 44 +#define MC_CMD_MAC_RX_UNDERSIZE_PKTS 45 +#define MC_CMD_MAC_RX_BAD_FCS_PKTS 46 +#define MC_CMD_MAC_RX_OVERFLOW_PKTS 47 +#define MC_CMD_MAC_RX_FALSE_CARRIER_PKTS 48 +#define MC_CMD_MAC_RX_SYMBOL_ERROR_PKTS 49 +#define MC_CMD_MAC_RX_ALIGN_ERROR_PKTS 50 +#define MC_CMD_MAC_RX_LENGTH_ERROR_PKTS 51 +#define MC_CMD_MAC_RX_INTERNAL_ERROR_PKTS 52 +#define MC_CMD_MAC_RX_JABBER_PKTS 53 +#define MC_CMD_MAC_RX_NODESC_DROPS 54 +#define MC_CMD_MAC_RX_LANES01_CHAR_ERR 55 +#define MC_CMD_MAC_RX_LANES23_CHAR_ERR 56 +#define MC_CMD_MAC_RX_LANES01_DISP_ERR 57 +#define MC_CMD_MAC_RX_LANES23_DISP_ERR 58 +#define MC_CMD_MAC_RX_MATCH_FAULT 59 +/* Insert new members here. */ +#define MC_CMD_MAC_GENERATION_END 60 +#define MC_CMD_MAC_NSTATS (MC_CMD_MAC_GENERATION_END+1) + +/* MC_CMD_MAC_STATS: + * Get unified GMAC/XMAC statistics + * + * This call returns unified statistics maintained by the MC as it + * switches between the GMAC and XMAC. The MC will write out all + * supported stats. The driver should zero initialise the buffer to + * guarantee consistent results. + * + * Locks required: None + * Returns: 0 + * Response methods: shared memory, event + */ +#define MC_CMD_MAC_STATS 0x2e +#define MC_CMD_MAC_STATS_IN_LEN 16 +#define MC_CMD_MAC_STATS_IN_DMA_ADDR_LO_OFST 0 +#define MC_CMD_MAC_STATS_IN_DMA_ADDR_HI_OFST 4 +#define MC_CMD_MAC_STATS_IN_CMD_OFST 8 +#define MC_CMD_MAC_STATS_CMD_DMA_LBN 0 +#define MC_CMD_MAC_STATS_CMD_DMA_WIDTH 1 +#define MC_CMD_MAC_STATS_CMD_CLEAR_LBN 1 +#define MC_CMD_MAC_STATS_CMD_CLEAR_WIDTH 1 +#define MC_CMD_MAC_STATS_CMD_PERIODIC_CHANGE_LBN 2 +#define MC_CMD_MAC_STATS_CMD_PERIODIC_CHANGE_WIDTH 1 +/* Fields only relevent when PERIODIC_CHANGE is set */ +#define MC_CMD_MAC_STATS_CMD_PERIODIC_ENABLE_LBN 3 +#define MC_CMD_MAC_STATS_CMD_PERIODIC_ENABLE_WIDTH 1 +#define MC_CMD_MAC_STATS_CMD_PERIODIC_CLEAR_LBN 4 +#define MC_CMD_MAC_STATS_CMD_PERIODIC_CLEAR_WIDTH 1 +#define MC_CMD_MAC_STATS_CMD_PERIOD_MS_LBN 16 +#define MC_CMD_MAC_STATS_CMD_PERIOD_MS_WIDTH 16 +#define MC_CMD_MAC_STATS_IN_DMA_LEN_OFST 12 + +#define MC_CMD_MAC_STATS_OUT_LEN 0 + +/* Callisto flags */ +#define MC_CMD_SFT9001_ROBUST_LBN 0 +#define MC_CMD_SFT9001_ROBUST_WIDTH 1 +#define MC_CMD_SFT9001_SHORT_REACH_LBN 1 +#define MC_CMD_SFT9001_SHORT_REACH_WIDTH 1 + +/* MC_CMD_SFT9001_GET: + * Read current callisto specific setting + * + * Locks required: None + * Returns: 0, ETIME + */ +#define MC_CMD_SFT9001_GET 0x30 +#define MC_CMD_SFT9001_GET_IN_LEN 0 +#define MC_CMD_SFT9001_GET_OUT_LEN 4 +#define MC_CMD_SFT9001_GET_OUT_FLAGS_OFST 0 + +/* MC_CMD_SFT9001_SET: + * Write current callisto specific setting + * + * Locks required: None + * Returns: 0, ETIME, EINVAL + */ +#define MC_CMD_SFT9001_SET 0x31 +#define MC_CMD_SFT9001_SET_IN_LEN 4 +#define MC_CMD_SFT9001_SET_IN_FLAGS_OFST 0 +#define MC_CMD_SFT9001_SET_OUT_LEN 0 + + +/* MC_CMD_WOL_FILTER_SET: + * Set a WoL filter + * + * Locks required: None + * Returns: 0, EBUSY, EINVAL, ENOSYS + */ +#define MC_CMD_WOL_FILTER_SET 0x32 +#define MC_CMD_WOL_FILTER_SET_IN_LEN 192 /* 190 rounded up to a word */ +#define MC_CMD_WOL_FILTER_SET_IN_FILTER_MODE_OFST 0 +#define MC_CMD_WOL_FILTER_SET_IN_WOL_TYPE_OFST 4 + +/* There is a union at offset 8, following defines overlap due to + * this */ +#define MC_CMD_WOL_FILTER_SET_IN_DATA_OFST 8 + +#define MC_CMD_WOL_FILTER_SET_IN_MAGIC_MAC_OFST \ + MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + +#define MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN_SRC_IP_OFST \ + MC_CMD_WOL_FILTER_SET_IN_DATA_OFST +#define MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN_DST_IP_OFST \ + (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 4) +#define MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN_SRC_PORT_OFST \ + (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 8) +#define MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN_DST_PORT_OFST \ + (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 10) + +#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_SRC_IP_OFST \ + MC_CMD_WOL_FILTER_SET_IN_DATA_OFST +#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_DST_IP_OFST \ + (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 16) +#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_SRC_PORT_OFST \ + (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 32) +#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_DST_PORT_OFST \ + (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 34) + +#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_MASK_OFST \ + MC_CMD_WOL_FILTER_SET_IN_DATA_OFST +#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_OFST \ + (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 48) +#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_LEN_OFST \ + (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 176) +#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_LAYER3_OFST \ + (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 177) +#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_LAYER4_OFST \ + (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 178) + +#define MC_CMD_WOL_FILTER_SET_OUT_LEN 4 +#define MC_CMD_WOL_FILTER_SET_OUT_FILTER_ID_OFST 0 + +/* WOL Filter types enumeration */ +#define MC_CMD_WOL_TYPE_MAGIC 0x0 + /* unused 0x1 */ +#define MC_CMD_WOL_TYPE_WIN_MAGIC 0x2 +#define MC_CMD_WOL_TYPE_IPV4_SYN 0x3 +#define MC_CMD_WOL_TYPE_IPV6_SYN 0x4 +#define MC_CMD_WOL_TYPE_BITMAP 0x5 +#define MC_CMD_WOL_TYPE_MAX 0x6 + +#define MC_CMD_FILTER_MODE_SIMPLE 0x0 +#define MC_CMD_FILTER_MODE_STRUCTURED 0xffffffff + +/* MC_CMD_WOL_FILTER_REMOVE: + * Remove a WoL filter + * + * Locks required: None + * Returns: 0, EINVAL, ENOSYS + */ +#define MC_CMD_WOL_FILTER_REMOVE 0x33 +#define MC_CMD_WOL_FILTER_REMOVE_IN_LEN 4 +#define MC_CMD_WOL_FILTER_REMOVE_IN_FILTER_ID_OFST 0 +#define MC_CMD_WOL_FILTER_REMOVE_OUT_LEN 0 + + +/* MC_CMD_WOL_FILTER_RESET: + * Reset (i.e. remove all) WoL filters + * + * Locks required: None + * Returns: 0, ENOSYS + */ +#define MC_CMD_WOL_FILTER_RESET 0x34 +#define MC_CMD_WOL_FILTER_RESET_IN_LEN 0 +#define MC_CMD_WOL_FILTER_RESET_OUT_LEN 0 + +/* MC_CMD_SET_MCAST_HASH: + * Set the MCASH hash value without otherwise + * reconfiguring the MAC + */ +#define MC_CMD_SET_MCAST_HASH 0x35 +#define MC_CMD_SET_MCAST_HASH_IN_LEN 32 +#define MC_CMD_SET_MCAST_HASH_IN_HASH0_OFST 0 +#define MC_CMD_SET_MCAST_HASH_IN_HASH1_OFST 16 +#define MC_CMD_SET_MCAST_HASH_OUT_LEN 0 + +/* MC_CMD_NVRAM_TYPES: + * Return bitfield indicating available types of virtual NVRAM partitions + * + * Locks required: none + * Returns: 0 + */ +#define MC_CMD_NVRAM_TYPES 0x36 +#define MC_CMD_NVRAM_TYPES_IN_LEN 0 +#define MC_CMD_NVRAM_TYPES_OUT_LEN 4 +#define MC_CMD_NVRAM_TYPES_OUT_TYPES_OFST 0 + +/* Supported NVRAM types */ +#define MC_CMD_NVRAM_TYPE_DISABLED_CALLISTO 0 +#define MC_CMD_NVRAM_TYPE_MC_FW 1 +#define MC_CMD_NVRAM_TYPE_MC_FW_BACKUP 2 +#define MC_CMD_NVRAM_TYPE_STATIC_CFG_PORT0 3 +#define MC_CMD_NVRAM_TYPE_STATIC_CFG_PORT1 4 +#define MC_CMD_NVRAM_TYPE_DYNAMIC_CFG_PORT0 5 +#define MC_CMD_NVRAM_TYPE_DYNAMIC_CFG_PORT1 6 +#define MC_CMD_NVRAM_TYPE_EXP_ROM 7 +#define MC_CMD_NVRAM_TYPE_EXP_ROM_CFG_PORT0 8 +#define MC_CMD_NVRAM_TYPE_EXP_ROM_CFG_PORT1 9 +#define MC_CMD_NVRAM_TYPE_PHY_PORT0 10 +#define MC_CMD_NVRAM_TYPE_PHY_PORT1 11 +#define MC_CMD_NVRAM_TYPE_LOG 12 + +/* MC_CMD_NVRAM_INFO: + * Read info about a virtual NVRAM partition + * + * Locks required: none + * Returns: 0, EINVAL (bad type) + */ +#define MC_CMD_NVRAM_INFO 0x37 +#define MC_CMD_NVRAM_INFO_IN_LEN 4 +#define MC_CMD_NVRAM_INFO_IN_TYPE_OFST 0 +#define MC_CMD_NVRAM_INFO_OUT_LEN 24 +#define MC_CMD_NVRAM_INFO_OUT_TYPE_OFST 0 +#define MC_CMD_NVRAM_INFO_OUT_SIZE_OFST 4 +#define MC_CMD_NVRAM_INFO_OUT_ERASESIZE_OFST 8 +#define MC_CMD_NVRAM_INFO_OUT_FLAGS_OFST 12 +#define MC_CMD_NVRAM_PROTECTED_LBN 0 +#define MC_CMD_NVRAM_PROTECTED_WIDTH 1 +#define MC_CMD_NVRAM_INFO_OUT_PHYSDEV_OFST 16 +#define MC_CMD_NVRAM_INFO_OUT_PHYSADDR_OFST 20 + +/* MC_CMD_NVRAM_UPDATE_START: + * Start a group of update operations on a virtual NVRAM partition + * + * Locks required: PHY_LOCK if type==*PHY* + * Returns: 0, EINVAL (bad type), EACCES (if PHY_LOCK required and not held) + */ +#define MC_CMD_NVRAM_UPDATE_START 0x38 +#define MC_CMD_NVRAM_UPDATE_START_IN_LEN 4 +#define MC_CMD_NVRAM_UPDATE_START_IN_TYPE_OFST 0 +#define MC_CMD_NVRAM_UPDATE_START_OUT_LEN 0 + +/* MC_CMD_NVRAM_READ: + * Read data from a virtual NVRAM partition + * + * Locks required: PHY_LOCK if type==*PHY* + * Returns: 0, EINVAL (bad type/offset/length), EACCES (if PHY_LOCK required and not held) + */ +#define MC_CMD_NVRAM_READ 0x39 +#define MC_CMD_NVRAM_READ_IN_LEN 12 +#define MC_CMD_NVRAM_READ_IN_TYPE_OFST 0 +#define MC_CMD_NVRAM_READ_IN_OFFSET_OFST 4 +#define MC_CMD_NVRAM_READ_IN_LENGTH_OFST 8 +#define MC_CMD_NVRAM_READ_OUT_LEN(_read_bytes) (_read_bytes) +#define MC_CMD_NVRAM_READ_OUT_READ_BUFFER_OFST 0 + +/* MC_CMD_NVRAM_WRITE: + * Write data to a virtual NVRAM partition + * + * Locks required: PHY_LOCK if type==*PHY* + * Returns: 0, EINVAL (bad type/offset/length), EACCES (if PHY_LOCK required and not held) + */ +#define MC_CMD_NVRAM_WRITE 0x3a +#define MC_CMD_NVRAM_WRITE_IN_TYPE_OFST 0 +#define MC_CMD_NVRAM_WRITE_IN_OFFSET_OFST 4 +#define MC_CMD_NVRAM_WRITE_IN_LENGTH_OFST 8 +#define MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_OFST 12 +#define MC_CMD_NVRAM_WRITE_IN_LEN(_write_bytes) (12 + _write_bytes) +#define MC_CMD_NVRAM_WRITE_OUT_LEN 0 + +/* MC_CMD_NVRAM_ERASE: + * Erase sector(s) from a virtual NVRAM partition + * + * Locks required: PHY_LOCK if type==*PHY* + * Returns: 0, EINVAL (bad type/offset/length), EACCES (if PHY_LOCK required and not held) + */ +#define MC_CMD_NVRAM_ERASE 0x3b +#define MC_CMD_NVRAM_ERASE_IN_LEN 12 +#define MC_CMD_NVRAM_ERASE_IN_TYPE_OFST 0 +#define MC_CMD_NVRAM_ERASE_IN_OFFSET_OFST 4 +#define MC_CMD_NVRAM_ERASE_IN_LENGTH_OFST 8 +#define MC_CMD_NVRAM_ERASE_OUT_LEN 0 + +/* MC_CMD_NVRAM_UPDATE_FINISH: + * Finish a group of update operations on a virtual NVRAM partition + * + * Locks required: PHY_LOCK if type==*PHY* + * Returns: 0, EINVAL (bad type/offset/length), EACCES (if PHY_LOCK required and not held) + */ +#define MC_CMD_NVRAM_UPDATE_FINISH 0x3c +#define MC_CMD_NVRAM_UPDATE_FINISH_IN_LEN 4 +#define MC_CMD_NVRAM_UPDATE_FINISH_IN_TYPE_OFST 0 +#define MC_CMD_NVRAM_UPDATE_FINISH_OUT_LEN 0 + +/* MC_CMD_REBOOT: + * Reboot the MC. The AFTER_ASSERTION flag is intended to be used + * when the driver notices an assertion failure, to allow two ports to + * both recover (semi-)gracefully. + * + * Locks required: NONE + * Returns: Nothing. You get back a response with ERR=1, DATALEN=0 + */ +#define MC_CMD_REBOOT 0x3d +#define MC_CMD_REBOOT_IN_LEN 4 +#define MC_CMD_REBOOT_IN_FLAGS_OFST 0 +#define MC_CMD_REBOOT_FLAGS_AFTER_ASSERTION 1 +#define MC_CMD_REBOOT_OUT_LEN 0 + +/* MC_CMD_SCHEDINFO: + * Request scheduler info. from the MC. + * + * Locks required: NONE + * Returns: An array of (timeslice,maximum overrun), one for each thread, + * in ascending order of thread address.s + */ +#define MC_CMD_SCHEDINFO 0x3e +#define MC_CMD_SCHEDINFO_IN_LEN 0 + + +/* MC_CMD_SET_REBOOT_MODE: (debug) + * Set the mode for the next MC reboot. + * + * Locks required: NONE + * + * Sets the reboot mode to the specified value. Returns the old mode. + */ +#define MC_CMD_REBOOT_MODE 0x3f +#define MC_CMD_REBOOT_MODE_IN_LEN 4 +#define MC_CMD_REBOOT_MODE_IN_VALUE_OFST 0 +#define MC_CMD_REBOOT_MODE_OUT_LEN 4 +#define MC_CMD_REBOOT_MODE_OUT_VALUE_OFST 0 +#define MC_CMD_REBOOT_MODE_NORMAL 0 +#define MC_CMD_REBOOT_MODE_SNAPPER 3 + +/* MC_CMD_DEBUG_LOG: + * Null request/response command (debug) + * - sequence number is always zero + * - only supported on the UART interface + * (the same set of bytes is delivered as an + * event over PCI) + */ +#define MC_CMD_DEBUG_LOG 0x40 +#define MC_CMD_DEBUG_LOG_IN_LEN 0 +#define MC_CMD_DEBUG_LOG_OUT_LEN 0 + +/* Generic sensor enumeration. Note that a dual port NIC + * will EITHER expose PHY_COMMON_TEMP OR PHY0_TEMP and + * PHY1_TEMP depending on whether there is a single sensor + * in the vicinity of the two port, or one per port. + */ +#define MC_CMD_SENSOR_CONTROLLER_TEMP 0 /* degC */ +#define MC_CMD_SENSOR_PHY_COMMON_TEMP 1 /* degC */ +#define MC_CMD_SENSOR_CONTROLLER_COOLING 2 /* bool */ +#define MC_CMD_SENSOR_PHY0_TEMP 3 /* degC */ +#define MC_CMD_SENSOR_PHY0_COOLING 4 /* bool */ +#define MC_CMD_SENSOR_PHY1_TEMP 5 /* degC */ +#define MC_CMD_SENSOR_PHY1_COOLING 6 /* bool */ +#define MC_CMD_SENSOR_IN_1V0 7 /* mV */ +#define MC_CMD_SENSOR_IN_1V2 8 /* mV */ +#define MC_CMD_SENSOR_IN_1V8 9 /* mV */ +#define MC_CMD_SENSOR_IN_2V5 10 /* mV */ +#define MC_CMD_SENSOR_IN_3V3 11 /* mV */ +#define MC_CMD_SENSOR_IN_12V0 12 /* mV */ + + +/* Sensor state */ +#define MC_CMD_SENSOR_STATE_OK 0 +#define MC_CMD_SENSOR_STATE_WARNING 1 +#define MC_CMD_SENSOR_STATE_FATAL 2 +#define MC_CMD_SENSOR_STATE_BROKEN 3 + +/* MC_CMD_SENSOR_INFO: + * Returns information about every available sensor. + * + * Each sensor has a single (16bit) value, and a corresponding state. + * The mapping between value and sensor is nominally determined by the + * MC, but in practise is implemented as zero (BROKEN), one (TEMPERATURE), + * or two (VOLTAGE) ranges per sensor per state. + * + * This call returns a mask (32bit) of the sensors that are supported + * by this platform, then an array (indexed by MC_CMD_SENSOR) of byte + * offsets to the per-sensor arrays. Each sensor array has four 16bit + * numbers, min1, max1, min2, max2. + * + * Locks required: None + * Returns: 0 + */ +#define MC_CMD_SENSOR_INFO 0x41 +#define MC_CMD_SENSOR_INFO_IN_LEN 0 +#define MC_CMD_SENSOR_INFO_OUT_MASK_OFST 0 +#define MC_CMD_SENSOR_INFO_OUT_OFFSET_OFST(_x) \ + (4 + (_x)) +#define MC_CMD_SENSOR_INFO_OUT_MIN1_OFST(_ofst) \ + ((_ofst) + 0) +#define MC_CMD_SENSOR_INFO_OUT_MAX1_OFST(_ofst) \ + ((_ofst) + 2) +#define MC_CMD_SENSOR_INFO_OUT_MIN2_OFST(_ofst) \ + ((_ofst) + 4) +#define MC_CMD_SENSOR_INFO_OUT_MAX2_OFST(_ofst) \ + ((_ofst) + 6) + +/* MC_CMD_READ_SENSORS + * Returns the current (value, state) for each sensor + * + * Returns the current (value, state) [each 16bit] of each sensor supported by + * this board, by DMA'ing a sparse array (indexed by the sensor type) into host + * memory. + * + * The MC will send a SENSOREVT event every time any sensor changes state. The + * driver is responsible for ensuring that it doesn't miss any events. The board + * will function normally if all sensors are in STATE_OK or state_WARNING. + * Otherwise the board should not be expected to function. + */ +#define MC_CMD_READ_SENSORS 0x42 +#define MC_CMD_READ_SENSORS_IN_LEN 8 +#define MC_CMD_READ_SENSORS_IN_DMA_ADDR_LO_OFST 0 +#define MC_CMD_READ_SENSORS_IN_DMA_ADDR_HI_OFST 4 +#define MC_CMD_READ_SENSORS_OUT_LEN 0 + + +/* MC_CMD_GET_PHY_STATE: + * Report current state of PHY. A "zombie" PHY is a PHY that has failed to + * boot (e.g. due to missing or corrupted firmware). + * + * Locks required: None + * Return code: 0 + */ +#define MC_CMD_GET_PHY_STATE 0x43 + +#define MC_CMD_GET_PHY_STATE_IN_LEN 0 +#define MC_CMD_GET_PHY_STATE_OUT_LEN 4 +#define MC_CMD_GET_PHY_STATE_STATE_OFST 0 +/* PHY state enumeration: */ +#define MC_CMD_PHY_STATE_OK 1 +#define MC_CMD_PHY_STATE_ZOMBIE 2 + + +/* 802.1Qbb control. 8 Tx queues that map to priorities 0 - 7. Use all 1s to + * disable 802.Qbb for a given priority. */ +#define MC_CMD_SETUP_8021QBB 0x44 +#define MC_CMD_SETUP_8021QBB_IN_LEN 32 +#define MC_CMD_SETUP_8021QBB_OUT_LEN 0 +#define MC_CMD_SETUP_8021QBB_IN_TXQS_OFFST 0 + + +/* MC_CMD_WOL_FILTER_GET: + * Retrieve ID of any WoL filters + * + * Locks required: None + * Returns: 0, ENOSYS + */ +#define MC_CMD_WOL_FILTER_GET 0x45 +#define MC_CMD_WOL_FILTER_GET_IN_LEN 0 +#define MC_CMD_WOL_FILTER_GET_OUT_LEN 4 +#define MC_CMD_WOL_FILTER_GET_OUT_FILTER_ID_OFST 0 + + +/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD: + * Offload a protocol to NIC for lights-out state + * + * Locks required: None + * Returns: 0, ENOSYS + */ +#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD 0x46 + +#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_LEN 16 +#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0 + +/* There is a union at offset 4, following defines overlap due to + * this */ +#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_OFST 4 +#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARPMAC_OFST 4 +#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARPIP_OFST 10 +#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NSMAC_OFST 4 +#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NSSNIPV6_OFST 10 +#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NSIPV6_OFST 26 + +#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_OUT_LEN 4 +#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_OUT_FILTER_ID_OFST 0 + + +/* MC_CMD_REMOVE_LIGHTSOUT_PROTOCOL_OFFLOAD: + * Offload a protocol to NIC for lights-out state + * + * Locks required: None + * Returns: 0, ENOSYS + */ +#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD 0x47 +#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_LEN 8 +#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_OUT_LEN 0 + +#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0 +#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_FILTER_ID_OFST 4 + +/* Lights-out offload protocols enumeration */ +#define MC_CMD_LIGHTSOUT_OFFLOAD_PROTOCOL_ARP 0x1 +#define MC_CMD_LIGHTSOUT_OFFLOAD_PROTOCOL_NS 0x2 + + +/* MC_CMD_MAC_RESET_RESTORE: + * Restore MAC after block reset + * + * Locks required: None + * Returns: 0 + */ + +#define MC_CMD_MAC_RESET_RESTORE 0x48 +#define MC_CMD_MAC_RESET_RESTORE_IN_LEN 0 +#define MC_CMD_MAC_RESET_RESTORE_OUT_LEN 0 + +#endif /* MCDI_PCOL_H */ diff --git a/drivers/net/sfc/mcdi_phy.c b/drivers/net/sfc/mcdi_phy.c new file mode 100644 index 000000000000..0e1bcc5a0d52 --- /dev/null +++ b/drivers/net/sfc/mcdi_phy.c @@ -0,0 +1,597 @@ +/**************************************************************************** + * Driver for Solarflare Solarstorm network controllers and boards + * Copyright 2009 Solarflare Communications Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +/* + * Driver for PHY related operations via MCDI. + */ + +#include "efx.h" +#include "phy.h" +#include "mcdi.h" +#include "mcdi_pcol.h" +#include "mdio_10g.h" + +struct efx_mcdi_phy_cfg { + u32 flags; + u32 type; + u32 supported_cap; + u32 channel; + u32 port; + u32 stats_mask; + u8 name[20]; + u32 media; + u32 mmd_mask; + u8 revision[20]; + u32 forced_cap; +}; + +static int +efx_mcdi_get_phy_cfg(struct efx_nic *efx, struct efx_mcdi_phy_cfg *cfg) +{ + u8 outbuf[MC_CMD_GET_PHY_CFG_OUT_LEN]; + size_t outlen; + int rc; + + BUILD_BUG_ON(MC_CMD_GET_PHY_CFG_IN_LEN != 0); + BUILD_BUG_ON(MC_CMD_GET_PHY_CFG_OUT_NAME_LEN != sizeof(cfg->name)); + + rc = efx_mcdi_rpc(efx, MC_CMD_GET_PHY_CFG, NULL, 0, + outbuf, sizeof(outbuf), &outlen); + if (rc) + goto fail; + + if (outlen < MC_CMD_GET_PHY_CFG_OUT_LEN) { + rc = -EMSGSIZE; + goto fail; + } + + cfg->flags = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_FLAGS); + cfg->type = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_TYPE); + cfg->supported_cap = + MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_SUPPORTED_CAP); + cfg->channel = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_CHANNEL); + cfg->port = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_PRT); + cfg->stats_mask = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_STATS_MASK); + memcpy(cfg->name, MCDI_PTR(outbuf, GET_PHY_CFG_OUT_NAME), + sizeof(cfg->name)); + cfg->media = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_MEDIA_TYPE); + cfg->mmd_mask = MCDI_DWORD(outbuf, GET_PHY_CFG_OUT_MMD_MASK); + memcpy(cfg->revision, MCDI_PTR(outbuf, GET_PHY_CFG_OUT_REVISION), + sizeof(cfg->revision)); + + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +static int efx_mcdi_set_link(struct efx_nic *efx, u32 capabilities, + u32 flags, u32 loopback_mode, + u32 loopback_speed) +{ + u8 inbuf[MC_CMD_SET_LINK_IN_LEN]; + int rc; + + BUILD_BUG_ON(MC_CMD_SET_LINK_OUT_LEN != 0); + + MCDI_SET_DWORD(inbuf, SET_LINK_IN_CAP, capabilities); + MCDI_SET_DWORD(inbuf, SET_LINK_IN_FLAGS, flags); + MCDI_SET_DWORD(inbuf, SET_LINK_IN_LOOPBACK_MODE, loopback_mode); + MCDI_SET_DWORD(inbuf, SET_LINK_IN_LOOPBACK_SPEED, loopback_speed); + + rc = efx_mcdi_rpc(efx, MC_CMD_SET_LINK, inbuf, sizeof(inbuf), + NULL, 0, NULL); + if (rc) + goto fail; + + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +static int efx_mcdi_loopback_modes(struct efx_nic *efx, u64 *loopback_modes) +{ + u8 outbuf[MC_CMD_GET_LOOPBACK_MODES_OUT_LEN]; + size_t outlen; + int rc; + + rc = efx_mcdi_rpc(efx, MC_CMD_GET_LOOPBACK_MODES, NULL, 0, + outbuf, sizeof(outbuf), &outlen); + if (rc) + goto fail; + + if (outlen < MC_CMD_GET_LOOPBACK_MODES_OUT_LEN) { + rc = -EMSGSIZE; + goto fail; + } + + *loopback_modes = MCDI_QWORD(outbuf, GET_LOOPBACK_MODES_SUGGESTED); + + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +int efx_mcdi_mdio_read(struct efx_nic *efx, unsigned int bus, + unsigned int prtad, unsigned int devad, u16 addr, + u16 *value_out, u32 *status_out) +{ + u8 inbuf[MC_CMD_MDIO_READ_IN_LEN]; + u8 outbuf[MC_CMD_MDIO_READ_OUT_LEN]; + size_t outlen; + int rc; + + MCDI_SET_DWORD(inbuf, MDIO_READ_IN_BUS, bus); + MCDI_SET_DWORD(inbuf, MDIO_READ_IN_PRTAD, prtad); + MCDI_SET_DWORD(inbuf, MDIO_READ_IN_DEVAD, devad); + MCDI_SET_DWORD(inbuf, MDIO_READ_IN_ADDR, addr); + + rc = efx_mcdi_rpc(efx, MC_CMD_MDIO_READ, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), &outlen); + if (rc) + goto fail; + + *value_out = (u16)MCDI_DWORD(outbuf, MDIO_READ_OUT_VALUE); + *status_out = MCDI_DWORD(outbuf, MDIO_READ_OUT_STATUS); + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +int efx_mcdi_mdio_write(struct efx_nic *efx, unsigned int bus, + unsigned int prtad, unsigned int devad, u16 addr, + u16 value, u32 *status_out) +{ + u8 inbuf[MC_CMD_MDIO_WRITE_IN_LEN]; + u8 outbuf[MC_CMD_MDIO_WRITE_OUT_LEN]; + size_t outlen; + int rc; + + MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_BUS, bus); + MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_PRTAD, prtad); + MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_DEVAD, devad); + MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_ADDR, addr); + MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_VALUE, value); + + rc = efx_mcdi_rpc(efx, MC_CMD_MDIO_WRITE, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), &outlen); + if (rc) + goto fail; + + *status_out = MCDI_DWORD(outbuf, MDIO_WRITE_OUT_STATUS); + return 0; + +fail: + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return rc; +} + +static u32 mcdi_to_ethtool_cap(u32 media, u32 cap) +{ + u32 result = 0; + + switch (media) { + case MC_CMD_MEDIA_KX4: + result |= SUPPORTED_Backplane; + if (cap & (1 << MC_CMD_PHY_CAP_1000FDX_LBN)) + result |= SUPPORTED_1000baseKX_Full; + if (cap & (1 << MC_CMD_PHY_CAP_10000FDX_LBN)) + result |= SUPPORTED_10000baseKX4_Full; + break; + + case MC_CMD_MEDIA_XFP: + case MC_CMD_MEDIA_SFP_PLUS: + result |= SUPPORTED_FIBRE; + break; + + case MC_CMD_MEDIA_BASE_T: + result |= SUPPORTED_TP; + if (cap & (1 << MC_CMD_PHY_CAP_10HDX_LBN)) + result |= SUPPORTED_10baseT_Half; + if (cap & (1 << MC_CMD_PHY_CAP_10FDX_LBN)) + result |= SUPPORTED_10baseT_Full; + if (cap & (1 << MC_CMD_PHY_CAP_100HDX_LBN)) + result |= SUPPORTED_100baseT_Half; + if (cap & (1 << MC_CMD_PHY_CAP_100FDX_LBN)) + result |= SUPPORTED_100baseT_Full; + if (cap & (1 << MC_CMD_PHY_CAP_1000HDX_LBN)) + result |= SUPPORTED_1000baseT_Half; + if (cap & (1 << MC_CMD_PHY_CAP_1000FDX_LBN)) + result |= SUPPORTED_1000baseT_Full; + if (cap & (1 << MC_CMD_PHY_CAP_10000FDX_LBN)) + result |= SUPPORTED_10000baseT_Full; + break; + } + + if (cap & (1 << MC_CMD_PHY_CAP_PAUSE_LBN)) + result |= SUPPORTED_Pause; + if (cap & (1 << MC_CMD_PHY_CAP_ASYM_LBN)) + result |= SUPPORTED_Asym_Pause; + if (cap & (1 << MC_CMD_PHY_CAP_AN_LBN)) + result |= SUPPORTED_Autoneg; + + return result; +} + +static u32 ethtool_to_mcdi_cap(u32 cap) +{ + u32 result = 0; + + if (cap & SUPPORTED_10baseT_Half) + result |= (1 << MC_CMD_PHY_CAP_10HDX_LBN); + if (cap & SUPPORTED_10baseT_Full) + result |= (1 << MC_CMD_PHY_CAP_10FDX_LBN); + if (cap & SUPPORTED_100baseT_Half) + result |= (1 << MC_CMD_PHY_CAP_100HDX_LBN); + if (cap & SUPPORTED_100baseT_Full) + result |= (1 << MC_CMD_PHY_CAP_100FDX_LBN); + if (cap & SUPPORTED_1000baseT_Half) + result |= (1 << MC_CMD_PHY_CAP_1000HDX_LBN); + if (cap & (SUPPORTED_1000baseT_Full | SUPPORTED_1000baseKX_Full)) + result |= (1 << MC_CMD_PHY_CAP_1000FDX_LBN); + if (cap & (SUPPORTED_10000baseT_Full | SUPPORTED_10000baseKX4_Full)) + result |= (1 << MC_CMD_PHY_CAP_10000FDX_LBN); + if (cap & SUPPORTED_Pause) + result |= (1 << MC_CMD_PHY_CAP_PAUSE_LBN); + if (cap & SUPPORTED_Asym_Pause) + result |= (1 << MC_CMD_PHY_CAP_ASYM_LBN); + if (cap & SUPPORTED_Autoneg) + result |= (1 << MC_CMD_PHY_CAP_AN_LBN); + + return result; +} + +static u32 efx_get_mcdi_phy_flags(struct efx_nic *efx) +{ + struct efx_mcdi_phy_cfg *phy_cfg = efx->phy_data; + enum efx_phy_mode mode, supported; + u32 flags; + + /* TODO: Advertise the capabilities supported by this PHY */ + supported = 0; + if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_TXDIS_LBN)) + supported |= PHY_MODE_TX_DISABLED; + if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_LOWPOWER_LBN)) + supported |= PHY_MODE_LOW_POWER; + if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_POWEROFF_LBN)) + supported |= PHY_MODE_OFF; + + mode = efx->phy_mode & supported; + + flags = 0; + if (mode & PHY_MODE_TX_DISABLED) + flags |= (1 << MC_CMD_SET_LINK_TXDIS_LBN); + if (mode & PHY_MODE_LOW_POWER) + flags |= (1 << MC_CMD_SET_LINK_LOWPOWER_LBN); + if (mode & PHY_MODE_OFF) + flags |= (1 << MC_CMD_SET_LINK_POWEROFF_LBN); + + return flags; +} + +static u32 mcdi_to_ethtool_media(u32 media) +{ + switch (media) { + case MC_CMD_MEDIA_XAUI: + case MC_CMD_MEDIA_CX4: + case MC_CMD_MEDIA_KX4: + return PORT_OTHER; + + case MC_CMD_MEDIA_XFP: + case MC_CMD_MEDIA_SFP_PLUS: + return PORT_FIBRE; + + case MC_CMD_MEDIA_BASE_T: + return PORT_TP; + + default: + return PORT_OTHER; + } +} + +static int efx_mcdi_phy_probe(struct efx_nic *efx) +{ + struct efx_mcdi_phy_cfg *phy_cfg; + int rc; + + /* TODO: Move phy_data initialisation to + * phy_op->probe/remove, rather than init/fini */ + phy_cfg = kzalloc(sizeof(*phy_cfg), GFP_KERNEL); + if (phy_cfg == NULL) { + rc = -ENOMEM; + goto fail_alloc; + } + rc = efx_mcdi_get_phy_cfg(efx, phy_cfg); + if (rc != 0) + goto fail; + + efx->phy_type = phy_cfg->type; + + efx->mdio_bus = phy_cfg->channel; + efx->mdio.prtad = phy_cfg->port; + efx->mdio.mmds = phy_cfg->mmd_mask & ~(1 << MC_CMD_MMD_CLAUSE22); + efx->mdio.mode_support = 0; + if (phy_cfg->mmd_mask & (1 << MC_CMD_MMD_CLAUSE22)) + efx->mdio.mode_support |= MDIO_SUPPORTS_C22; + if (phy_cfg->mmd_mask & ~(1 << MC_CMD_MMD_CLAUSE22)) + efx->mdio.mode_support |= MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22; + + /* Assert that we can map efx -> mcdi loopback modes */ + BUILD_BUG_ON(LOOPBACK_NONE != MC_CMD_LOOPBACK_NONE); + BUILD_BUG_ON(LOOPBACK_DATA != MC_CMD_LOOPBACK_DATA); + BUILD_BUG_ON(LOOPBACK_GMAC != MC_CMD_LOOPBACK_GMAC); + BUILD_BUG_ON(LOOPBACK_XGMII != MC_CMD_LOOPBACK_XGMII); + BUILD_BUG_ON(LOOPBACK_XGXS != MC_CMD_LOOPBACK_XGXS); + BUILD_BUG_ON(LOOPBACK_XAUI != MC_CMD_LOOPBACK_XAUI); + BUILD_BUG_ON(LOOPBACK_GMII != MC_CMD_LOOPBACK_GMII); + BUILD_BUG_ON(LOOPBACK_SGMII != MC_CMD_LOOPBACK_SGMII); + BUILD_BUG_ON(LOOPBACK_XGBR != MC_CMD_LOOPBACK_XGBR); + BUILD_BUG_ON(LOOPBACK_XFI != MC_CMD_LOOPBACK_XFI); + BUILD_BUG_ON(LOOPBACK_XAUI_FAR != MC_CMD_LOOPBACK_XAUI_FAR); + BUILD_BUG_ON(LOOPBACK_GMII_FAR != MC_CMD_LOOPBACK_GMII_FAR); + BUILD_BUG_ON(LOOPBACK_SGMII_FAR != MC_CMD_LOOPBACK_SGMII_FAR); + BUILD_BUG_ON(LOOPBACK_XFI_FAR != MC_CMD_LOOPBACK_XFI_FAR); + BUILD_BUG_ON(LOOPBACK_GPHY != MC_CMD_LOOPBACK_GPHY); + BUILD_BUG_ON(LOOPBACK_PHYXS != MC_CMD_LOOPBACK_PHYXS); + BUILD_BUG_ON(LOOPBACK_PCS != MC_CMD_LOOPBACK_PCS); + BUILD_BUG_ON(LOOPBACK_PMAPMD != MC_CMD_LOOPBACK_PMAPMD); + BUILD_BUG_ON(LOOPBACK_XPORT != MC_CMD_LOOPBACK_XPORT); + BUILD_BUG_ON(LOOPBACK_XGMII_WS != MC_CMD_LOOPBACK_XGMII_WS); + BUILD_BUG_ON(LOOPBACK_XAUI_WS != MC_CMD_LOOPBACK_XAUI_WS); + BUILD_BUG_ON(LOOPBACK_XAUI_WS_FAR != MC_CMD_LOOPBACK_XAUI_WS_FAR); + BUILD_BUG_ON(LOOPBACK_XAUI_WS_NEAR != MC_CMD_LOOPBACK_XAUI_WS_NEAR); + BUILD_BUG_ON(LOOPBACK_GMII_WS != MC_CMD_LOOPBACK_GMII_WS); + BUILD_BUG_ON(LOOPBACK_XFI_WS != MC_CMD_LOOPBACK_XFI_WS); + BUILD_BUG_ON(LOOPBACK_XFI_WS_FAR != MC_CMD_LOOPBACK_XFI_WS_FAR); + BUILD_BUG_ON(LOOPBACK_PHYXS_WS != MC_CMD_LOOPBACK_PHYXS_WS); + + rc = efx_mcdi_loopback_modes(efx, &efx->loopback_modes); + if (rc != 0) + goto fail; + /* The MC indicates that LOOPBACK_NONE is a valid loopback mode, + * but by convention we don't */ + efx->loopback_modes &= ~(1 << LOOPBACK_NONE); + + kfree(phy_cfg); + + return 0; + +fail: + kfree(phy_cfg); +fail_alloc: + return rc; +} + +static int efx_mcdi_phy_init(struct efx_nic *efx) +{ + struct efx_mcdi_phy_cfg *phy_data; + u8 outbuf[MC_CMD_GET_LINK_OUT_LEN]; + u32 caps; + int rc; + + phy_data = kzalloc(sizeof(*phy_data), GFP_KERNEL); + if (phy_data == NULL) + return -ENOMEM; + + rc = efx_mcdi_get_phy_cfg(efx, phy_data); + if (rc != 0) + goto fail; + + efx->phy_data = phy_data; + + BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0); + rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0, + outbuf, sizeof(outbuf), NULL); + if (rc) + goto fail; + + caps = MCDI_DWORD(outbuf, GET_LINK_OUT_CAP); + if (caps & (1 << MC_CMD_PHY_CAP_AN_LBN)) + efx->link_advertising = + mcdi_to_ethtool_cap(phy_data->media, caps); + else + phy_data->forced_cap = caps; + + return 0; + +fail: + kfree(phy_data); + return rc; +} + +int efx_mcdi_phy_reconfigure(struct efx_nic *efx) +{ + struct efx_mcdi_phy_cfg *phy_cfg = efx->phy_data; + u32 caps = (efx->link_advertising ? + ethtool_to_mcdi_cap(efx->link_advertising) : + phy_cfg->forced_cap); + + return efx_mcdi_set_link(efx, caps, efx_get_mcdi_phy_flags(efx), + efx->loopback_mode, 0); +} + +void efx_mcdi_phy_decode_link(struct efx_nic *efx, + struct efx_link_state *link_state, + u32 speed, u32 flags, u32 fcntl) +{ + switch (fcntl) { + case MC_CMD_FCNTL_AUTO: + WARN_ON(1); /* This is not a link mode */ + link_state->fc = EFX_FC_AUTO | EFX_FC_TX | EFX_FC_RX; + break; + case MC_CMD_FCNTL_BIDIR: + link_state->fc = EFX_FC_TX | EFX_FC_RX; + break; + case MC_CMD_FCNTL_RESPOND: + link_state->fc = EFX_FC_RX; + break; + default: + WARN_ON(1); + case MC_CMD_FCNTL_OFF: + link_state->fc = 0; + break; + } + + link_state->up = !!(flags & (1 << MC_CMD_GET_LINK_LINK_UP_LBN)); + link_state->fd = !!(flags & (1 << MC_CMD_GET_LINK_FULL_DUPLEX_LBN)); + link_state->speed = speed; +} + +/* Verify that the forced flow control settings (!EFX_FC_AUTO) are + * supported by the link partner. Warn the user if this isn't the case + */ +void efx_mcdi_phy_check_fcntl(struct efx_nic *efx, u32 lpa) +{ + struct efx_mcdi_phy_cfg *phy_cfg = efx->phy_data; + u32 rmtadv; + + /* The link partner capabilities are only relevent if the + * link supports flow control autonegotiation */ + if (~phy_cfg->supported_cap & (1 << MC_CMD_PHY_CAP_ASYM_LBN)) + return; + + /* If flow control autoneg is supported and enabled, then fine */ + if (efx->wanted_fc & EFX_FC_AUTO) + return; + + rmtadv = 0; + if (lpa & (1 << MC_CMD_PHY_CAP_PAUSE_LBN)) + rmtadv |= ADVERTISED_Pause; + if (lpa & (1 << MC_CMD_PHY_CAP_ASYM_LBN)) + rmtadv |= ADVERTISED_Asym_Pause; + + if ((efx->wanted_fc & EFX_FC_TX) && rmtadv == ADVERTISED_Asym_Pause) + EFX_ERR(efx, "warning: link partner doesn't support " + "pause frames"); +} + +static bool efx_mcdi_phy_poll(struct efx_nic *efx) +{ + struct efx_link_state old_state = efx->link_state; + u8 outbuf[MC_CMD_GET_LINK_OUT_LEN]; + int rc; + + WARN_ON(!mutex_is_locked(&efx->mac_lock)); + + BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0); + + rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0, + outbuf, sizeof(outbuf), NULL); + if (rc) { + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + efx->link_state.up = false; + } else { + efx_mcdi_phy_decode_link( + efx, &efx->link_state, + MCDI_DWORD(outbuf, GET_LINK_OUT_LINK_SPEED), + MCDI_DWORD(outbuf, GET_LINK_OUT_FLAGS), + MCDI_DWORD(outbuf, GET_LINK_OUT_FCNTL)); + } + + return !efx_link_state_equal(&efx->link_state, &old_state); +} + +static void efx_mcdi_phy_fini(struct efx_nic *efx) +{ + struct efx_mcdi_phy_data *phy_data = efx->phy_data; + + efx->phy_data = NULL; + kfree(phy_data); +} + +static void efx_mcdi_phy_get_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd) +{ + struct efx_mcdi_phy_cfg *phy_cfg = efx->phy_data; + u8 outbuf[MC_CMD_GET_LINK_OUT_LEN]; + int rc; + + ecmd->supported = + mcdi_to_ethtool_cap(phy_cfg->media, phy_cfg->supported_cap); + ecmd->advertising = efx->link_advertising; + ecmd->speed = efx->link_state.speed; + ecmd->duplex = efx->link_state.fd; + ecmd->port = mcdi_to_ethtool_media(phy_cfg->media); + ecmd->phy_address = phy_cfg->port; + ecmd->transceiver = XCVR_INTERNAL; + ecmd->autoneg = !!(efx->link_advertising & ADVERTISED_Autoneg); + ecmd->mdio_support = (efx->mdio.mode_support & + (MDIO_SUPPORTS_C45 | MDIO_SUPPORTS_C22)); + + BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0); + rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0, + outbuf, sizeof(outbuf), NULL); + if (rc) { + EFX_ERR(efx, "%s: failed rc=%d\n", __func__, rc); + return; + } + ecmd->lp_advertising = + mcdi_to_ethtool_cap(phy_cfg->media, + MCDI_DWORD(outbuf, GET_LINK_OUT_LP_CAP)); +} + +static int efx_mcdi_phy_set_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd) +{ + struct efx_mcdi_phy_cfg *phy_cfg = efx->phy_data; + u32 caps; + int rc; + + if (ecmd->autoneg) { + caps = (ethtool_to_mcdi_cap(ecmd->advertising) | + 1 << MC_CMD_PHY_CAP_AN_LBN); + } else if (ecmd->duplex) { + switch (ecmd->speed) { + case 10: caps = 1 << MC_CMD_PHY_CAP_10FDX_LBN; break; + case 100: caps = 1 << MC_CMD_PHY_CAP_100FDX_LBN; break; + case 1000: caps = 1 << MC_CMD_PHY_CAP_1000FDX_LBN; break; + case 10000: caps = 1 << MC_CMD_PHY_CAP_10000FDX_LBN; break; + default: return -EINVAL; + } + } else { + switch (ecmd->speed) { + case 10: caps = 1 << MC_CMD_PHY_CAP_10HDX_LBN; break; + case 100: caps = 1 << MC_CMD_PHY_CAP_100HDX_LBN; break; + case 1000: caps = 1 << MC_CMD_PHY_CAP_1000HDX_LBN; break; + default: return -EINVAL; + } + } + + rc = efx_mcdi_set_link(efx, caps, efx_get_mcdi_phy_flags(efx), + efx->loopback_mode, 0); + if (rc) + return rc; + + if (ecmd->autoneg) { + efx_link_set_advertising( + efx, ecmd->advertising | ADVERTISED_Autoneg); + phy_cfg->forced_cap = 0; + } else { + efx_link_set_advertising(efx, 0); + phy_cfg->forced_cap = caps; + } + return 0; +} + +struct efx_phy_operations efx_mcdi_phy_ops = { + .probe = efx_mcdi_phy_probe, + .init = efx_mcdi_phy_init, + .reconfigure = efx_mcdi_phy_reconfigure, + .poll = efx_mcdi_phy_poll, + .fini = efx_mcdi_phy_fini, + .get_settings = efx_mcdi_phy_get_settings, + .set_settings = efx_mcdi_phy_set_settings, + .run_tests = NULL, + .test_name = NULL, +}; diff --git a/drivers/net/sfc/mdio_10g.c b/drivers/net/sfc/mdio_10g.c index 231e580acc9a..1574e52f0594 100644 --- a/drivers/net/sfc/mdio_10g.c +++ b/drivers/net/sfc/mdio_10g.c @@ -1,6 +1,6 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards - * Copyright 2006-2008 Solarflare Communications Inc. + * Copyright 2006-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -15,6 +15,7 @@ #include "net_driver.h" #include "mdio_10g.h" #include "workarounds.h" +#include "nic.h" unsigned efx_mdio_id_oui(u32 id) { @@ -173,7 +174,7 @@ bool efx_mdio_links_ok(struct efx_nic *efx, unsigned int mmd_mask) * of mmd's */ if (LOOPBACK_INTERNAL(efx)) return true; - else if (efx->loopback_mode == LOOPBACK_NETWORK) + else if (LOOPBACK_MASK(efx) & LOOPBACKS_WS) return false; else if (efx_phy_mode_disabled(efx->phy_mode)) return false; @@ -210,7 +211,7 @@ void efx_mdio_phy_reconfigure(struct efx_nic *efx) efx->loopback_mode == LOOPBACK_PCS); efx_mdio_set_flag(efx, MDIO_MMD_PHYXS, MDIO_CTRL1, MDIO_PHYXS_CTRL1_LOOPBACK, - efx->loopback_mode == LOOPBACK_NETWORK); + efx->loopback_mode == LOOPBACK_PHYXS_WS); } static void efx_mdio_set_mmd_lpower(struct efx_nic *efx, @@ -248,8 +249,6 @@ void efx_mdio_set_mmds_lpower(struct efx_nic *efx, int efx_mdio_set_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd) { struct ethtool_cmd prev; - bool xnp; - int reg; efx->phy_op->get_settings(efx, &prev); @@ -269,44 +268,58 @@ int efx_mdio_set_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd) (ecmd->advertising | SUPPORTED_Autoneg) & ~prev.supported) return -EINVAL; - xnp = (ecmd->advertising & ADVERTISED_10000baseT_Full - || EFX_WORKAROUND_13204(efx)); + efx_link_set_advertising(efx, ecmd->advertising | ADVERTISED_Autoneg); + efx_mdio_an_reconfigure(efx); + return 0; +} + +/** + * efx_mdio_an_reconfigure - Push advertising flags and restart autonegotiation + * @efx: Efx NIC + */ +void efx_mdio_an_reconfigure(struct efx_nic *efx) +{ + bool xnp = (efx->link_advertising & ADVERTISED_10000baseT_Full + || EFX_WORKAROUND_13204(efx)); + int reg; + + WARN_ON(!(efx->mdio.mmds & MDIO_DEVS_AN)); /* Set up the base page */ reg = ADVERTISE_CSMA; - if (ecmd->advertising & ADVERTISED_10baseT_Half) + if (efx->link_advertising & ADVERTISED_10baseT_Half) reg |= ADVERTISE_10HALF; - if (ecmd->advertising & ADVERTISED_10baseT_Full) + if (efx->link_advertising & ADVERTISED_10baseT_Full) reg |= ADVERTISE_10FULL; - if (ecmd->advertising & ADVERTISED_100baseT_Half) + if (efx->link_advertising & ADVERTISED_100baseT_Half) reg |= ADVERTISE_100HALF; - if (ecmd->advertising & ADVERTISED_100baseT_Full) + if (efx->link_advertising & ADVERTISED_100baseT_Full) reg |= ADVERTISE_100FULL; if (xnp) reg |= ADVERTISE_RESV; - else if (ecmd->advertising & (ADVERTISED_1000baseT_Half | - ADVERTISED_1000baseT_Full)) + else if (efx->link_advertising & (ADVERTISED_1000baseT_Half | + ADVERTISED_1000baseT_Full)) reg |= ADVERTISE_NPAGE; - reg |= mii_advertise_flowctrl(efx->wanted_fc); + if (efx->link_advertising & ADVERTISED_Pause) + reg |= ADVERTISE_PAUSE_CAP; + if (efx->link_advertising & ADVERTISED_Asym_Pause) + reg |= ADVERTISE_PAUSE_ASYM; efx_mdio_write(efx, MDIO_MMD_AN, MDIO_AN_ADVERTISE, reg); /* Set up the (extended) next page if necessary */ if (efx->phy_op->set_npage_adv) - efx->phy_op->set_npage_adv(efx, ecmd->advertising); + efx->phy_op->set_npage_adv(efx, efx->link_advertising); /* Enable and restart AN */ reg = efx_mdio_read(efx, MDIO_MMD_AN, MDIO_CTRL1); reg |= MDIO_AN_CTRL1_ENABLE; - if (!(EFX_WORKAROUND_15195(efx) && - LOOPBACK_MASK(efx) & efx->phy_op->loopbacks)) + if (!(EFX_WORKAROUND_15195(efx) && LOOPBACK_EXTERNAL(efx))) reg |= MDIO_AN_CTRL1_RESTART; if (xnp) reg |= MDIO_AN_CTRL1_XNP; else reg &= ~MDIO_AN_CTRL1_XNP; efx_mdio_write(efx, MDIO_MMD_AN, MDIO_CTRL1, reg); - - return 0; } enum efx_fc_type efx_mdio_get_pause(struct efx_nic *efx) diff --git a/drivers/net/sfc/mdio_10g.h b/drivers/net/sfc/mdio_10g.h index 75b37f101231..f6ac9503339d 100644 --- a/drivers/net/sfc/mdio_10g.h +++ b/drivers/net/sfc/mdio_10g.h @@ -1,6 +1,6 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards - * Copyright 2006-2008 Solarflare Communications Inc. + * Copyright 2006-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -86,6 +86,9 @@ extern void efx_mdio_set_mmds_lpower(struct efx_nic *efx, /* Set (some of) the PHY settings over MDIO */ extern int efx_mdio_set_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd); +/* Push advertising flags and restart autonegotiation */ +extern void efx_mdio_an_reconfigure(struct efx_nic *efx); + /* Get pause parameters from AN if available (otherwise return * requested pause parameters) */ diff --git a/drivers/net/sfc/mtd.c b/drivers/net/sfc/mtd.c index 820c233c3ea0..3a464529a46b 100644 --- a/drivers/net/sfc/mtd.c +++ b/drivers/net/sfc/mtd.c @@ -1,36 +1,80 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards * Copyright 2005-2006 Fen Systems Ltd. - * Copyright 2006-2008 Solarflare Communications Inc. + * Copyright 2006-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published * by the Free Software Foundation, incorporated herein by reference. */ +#include <linux/bitops.h> #include <linux/module.h> #include <linux/mtd/mtd.h> #include <linux/delay.h> +#include <linux/rtnetlink.h> #define EFX_DRIVER_NAME "sfc_mtd" #include "net_driver.h" #include "spi.h" #include "efx.h" +#include "nic.h" +#include "mcdi.h" +#include "mcdi_pcol.h" #define EFX_SPI_VERIFY_BUF_LEN 16 +#define EFX_MCDI_CHUNK_LEN 128 -struct efx_mtd { - const struct efx_spi_device *spi; +struct efx_mtd_partition { struct mtd_info mtd; + union { + struct { + bool updating; + u8 nvram_type; + u16 fw_subtype; + } mcdi; + size_t offset; + }; + const char *type_name; char name[IFNAMSIZ + 20]; }; +struct efx_mtd_ops { + int (*read)(struct mtd_info *mtd, loff_t start, size_t len, + size_t *retlen, u8 *buffer); + int (*erase)(struct mtd_info *mtd, loff_t start, size_t len); + int (*write)(struct mtd_info *mtd, loff_t start, size_t len, + size_t *retlen, const u8 *buffer); + int (*sync)(struct mtd_info *mtd); +}; + +struct efx_mtd { + struct list_head node; + struct efx_nic *efx; + const struct efx_spi_device *spi; + const char *name; + const struct efx_mtd_ops *ops; + size_t n_parts; + struct efx_mtd_partition part[0]; +}; + +#define efx_for_each_partition(part, efx_mtd) \ + for ((part) = &(efx_mtd)->part[0]; \ + (part) != &(efx_mtd)->part[(efx_mtd)->n_parts]; \ + (part)++) + +#define to_efx_mtd_partition(mtd) \ + container_of(mtd, struct efx_mtd_partition, mtd) + +static int falcon_mtd_probe(struct efx_nic *efx); +static int siena_mtd_probe(struct efx_nic *efx); + /* SPI utilities */ static int efx_spi_slow_wait(struct efx_mtd *efx_mtd, bool uninterruptible) { const struct efx_spi_device *spi = efx_mtd->spi; - struct efx_nic *efx = spi->efx; + struct efx_nic *efx = efx_mtd->efx; u8 status; int rc, i; @@ -39,7 +83,7 @@ static int efx_spi_slow_wait(struct efx_mtd *efx_mtd, bool uninterruptible) __set_current_state(uninterruptible ? TASK_UNINTERRUPTIBLE : TASK_INTERRUPTIBLE); schedule_timeout(HZ / 10); - rc = falcon_spi_cmd(spi, SPI_RDSR, -1, NULL, + rc = falcon_spi_cmd(efx, spi, SPI_RDSR, -1, NULL, &status, sizeof(status)); if (rc) return rc; @@ -52,32 +96,35 @@ static int efx_spi_slow_wait(struct efx_mtd *efx_mtd, bool uninterruptible) return -ETIMEDOUT; } -static int efx_spi_unlock(const struct efx_spi_device *spi) +static int +efx_spi_unlock(struct efx_nic *efx, const struct efx_spi_device *spi) { const u8 unlock_mask = (SPI_STATUS_BP2 | SPI_STATUS_BP1 | SPI_STATUS_BP0); u8 status; int rc; - rc = falcon_spi_cmd(spi, SPI_RDSR, -1, NULL, &status, sizeof(status)); + rc = falcon_spi_cmd(efx, spi, SPI_RDSR, -1, NULL, + &status, sizeof(status)); if (rc) return rc; if (!(status & unlock_mask)) return 0; /* already unlocked */ - rc = falcon_spi_cmd(spi, SPI_WREN, -1, NULL, NULL, 0); + rc = falcon_spi_cmd(efx, spi, SPI_WREN, -1, NULL, NULL, 0); if (rc) return rc; - rc = falcon_spi_cmd(spi, SPI_SST_EWSR, -1, NULL, NULL, 0); + rc = falcon_spi_cmd(efx, spi, SPI_SST_EWSR, -1, NULL, NULL, 0); if (rc) return rc; status &= ~unlock_mask; - rc = falcon_spi_cmd(spi, SPI_WRSR, -1, &status, NULL, sizeof(status)); + rc = falcon_spi_cmd(efx, spi, SPI_WRSR, -1, &status, + NULL, sizeof(status)); if (rc) return rc; - rc = falcon_spi_wait_write(spi); + rc = falcon_spi_wait_write(efx, spi); if (rc) return rc; @@ -87,6 +134,7 @@ static int efx_spi_unlock(const struct efx_spi_device *spi) static int efx_spi_erase(struct efx_mtd *efx_mtd, loff_t start, size_t len) { const struct efx_spi_device *spi = efx_mtd->spi; + struct efx_nic *efx = efx_mtd->efx; unsigned pos, block_len; u8 empty[EFX_SPI_VERIFY_BUF_LEN]; u8 buffer[EFX_SPI_VERIFY_BUF_LEN]; @@ -98,13 +146,14 @@ static int efx_spi_erase(struct efx_mtd *efx_mtd, loff_t start, size_t len) if (spi->erase_command == 0) return -EOPNOTSUPP; - rc = efx_spi_unlock(spi); + rc = efx_spi_unlock(efx, spi); if (rc) return rc; - rc = falcon_spi_cmd(spi, SPI_WREN, -1, NULL, NULL, 0); + rc = falcon_spi_cmd(efx, spi, SPI_WREN, -1, NULL, NULL, 0); if (rc) return rc; - rc = falcon_spi_cmd(spi, spi->erase_command, start, NULL, NULL, 0); + rc = falcon_spi_cmd(efx, spi, spi->erase_command, start, NULL, + NULL, 0); if (rc) return rc; rc = efx_spi_slow_wait(efx_mtd, false); @@ -113,7 +162,8 @@ static int efx_spi_erase(struct efx_mtd *efx_mtd, loff_t start, size_t len) memset(empty, 0xff, sizeof(empty)); for (pos = 0; pos < len; pos += block_len) { block_len = min(len - pos, sizeof(buffer)); - rc = falcon_spi_read(spi, start + pos, block_len, NULL, buffer); + rc = falcon_spi_read(efx, spi, start + pos, block_len, + NULL, buffer); if (rc) return rc; if (memcmp(empty, buffer, block_len)) @@ -130,140 +180,473 @@ static int efx_spi_erase(struct efx_mtd *efx_mtd, loff_t start, size_t len) /* MTD interface */ -static int efx_mtd_read(struct mtd_info *mtd, loff_t start, size_t len, - size_t *retlen, u8 *buffer) +static int efx_mtd_erase(struct mtd_info *mtd, struct erase_info *erase) { struct efx_mtd *efx_mtd = mtd->priv; + int rc; + + rc = efx_mtd->ops->erase(mtd, erase->addr, erase->len); + if (rc == 0) { + erase->state = MTD_ERASE_DONE; + } else { + erase->state = MTD_ERASE_FAILED; + erase->fail_addr = 0xffffffff; + } + mtd_erase_callback(erase); + return rc; +} + +static void efx_mtd_sync(struct mtd_info *mtd) +{ + struct efx_mtd *efx_mtd = mtd->priv; + struct efx_nic *efx = efx_mtd->efx; + int rc; + + rc = efx_mtd->ops->sync(mtd); + if (rc) + EFX_ERR(efx, "%s sync failed (%d)\n", efx_mtd->name, rc); +} + +static void efx_mtd_remove_partition(struct efx_mtd_partition *part) +{ + int rc; + + for (;;) { + rc = del_mtd_device(&part->mtd); + if (rc != -EBUSY) + break; + ssleep(1); + } + WARN_ON(rc); +} + +static void efx_mtd_remove_device(struct efx_mtd *efx_mtd) +{ + struct efx_mtd_partition *part; + + efx_for_each_partition(part, efx_mtd) + efx_mtd_remove_partition(part); + list_del(&efx_mtd->node); + kfree(efx_mtd); +} + +static void efx_mtd_rename_device(struct efx_mtd *efx_mtd) +{ + struct efx_mtd_partition *part; + + efx_for_each_partition(part, efx_mtd) + if (efx_nic_rev(efx_mtd->efx) >= EFX_REV_SIENA_A0) + snprintf(part->name, sizeof(part->name), + "%s %s:%02x", efx_mtd->efx->name, + part->type_name, part->mcdi.fw_subtype); + else + snprintf(part->name, sizeof(part->name), + "%s %s", efx_mtd->efx->name, + part->type_name); +} + +static int efx_mtd_probe_device(struct efx_nic *efx, struct efx_mtd *efx_mtd) +{ + struct efx_mtd_partition *part; + + efx_mtd->efx = efx; + + efx_mtd_rename_device(efx_mtd); + + efx_for_each_partition(part, efx_mtd) { + part->mtd.writesize = 1; + + part->mtd.owner = THIS_MODULE; + part->mtd.priv = efx_mtd; + part->mtd.name = part->name; + part->mtd.erase = efx_mtd_erase; + part->mtd.read = efx_mtd->ops->read; + part->mtd.write = efx_mtd->ops->write; + part->mtd.sync = efx_mtd_sync; + + if (add_mtd_device(&part->mtd)) + goto fail; + } + + list_add(&efx_mtd->node, &efx->mtd_list); + return 0; + +fail: + while (part != &efx_mtd->part[0]) { + --part; + efx_mtd_remove_partition(part); + } + /* add_mtd_device() returns 1 if the MTD table is full */ + return -ENOMEM; +} + +void efx_mtd_remove(struct efx_nic *efx) +{ + struct efx_mtd *efx_mtd, *next; + + WARN_ON(efx_dev_registered(efx)); + + list_for_each_entry_safe(efx_mtd, next, &efx->mtd_list, node) + efx_mtd_remove_device(efx_mtd); +} + +void efx_mtd_rename(struct efx_nic *efx) +{ + struct efx_mtd *efx_mtd; + + ASSERT_RTNL(); + + list_for_each_entry(efx_mtd, &efx->mtd_list, node) + efx_mtd_rename_device(efx_mtd); +} + +int efx_mtd_probe(struct efx_nic *efx) +{ + if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0) + return siena_mtd_probe(efx); + else + return falcon_mtd_probe(efx); +} + +/* Implementation of MTD operations for Falcon */ + +static int falcon_mtd_read(struct mtd_info *mtd, loff_t start, + size_t len, size_t *retlen, u8 *buffer) +{ + struct efx_mtd_partition *part = to_efx_mtd_partition(mtd); + struct efx_mtd *efx_mtd = mtd->priv; const struct efx_spi_device *spi = efx_mtd->spi; - struct efx_nic *efx = spi->efx; + struct efx_nic *efx = efx_mtd->efx; int rc; rc = mutex_lock_interruptible(&efx->spi_lock); if (rc) return rc; - rc = falcon_spi_read(spi, FALCON_FLASH_BOOTCODE_START + start, - len, retlen, buffer); + rc = falcon_spi_read(efx, spi, part->offset + start, len, + retlen, buffer); mutex_unlock(&efx->spi_lock); return rc; } -static int efx_mtd_erase(struct mtd_info *mtd, struct erase_info *erase) +static int falcon_mtd_erase(struct mtd_info *mtd, loff_t start, size_t len) { + struct efx_mtd_partition *part = to_efx_mtd_partition(mtd); struct efx_mtd *efx_mtd = mtd->priv; - struct efx_nic *efx = efx_mtd->spi->efx; + struct efx_nic *efx = efx_mtd->efx; int rc; rc = mutex_lock_interruptible(&efx->spi_lock); if (rc) return rc; - rc = efx_spi_erase(efx_mtd, FALCON_FLASH_BOOTCODE_START + erase->addr, - erase->len); + rc = efx_spi_erase(efx_mtd, part->offset + start, len); mutex_unlock(&efx->spi_lock); - - if (rc == 0) { - erase->state = MTD_ERASE_DONE; - } else { - erase->state = MTD_ERASE_FAILED; - erase->fail_addr = 0xffffffff; - } - mtd_erase_callback(erase); return rc; } -static int efx_mtd_write(struct mtd_info *mtd, loff_t start, - size_t len, size_t *retlen, const u8 *buffer) +static int falcon_mtd_write(struct mtd_info *mtd, loff_t start, + size_t len, size_t *retlen, const u8 *buffer) { + struct efx_mtd_partition *part = to_efx_mtd_partition(mtd); struct efx_mtd *efx_mtd = mtd->priv; const struct efx_spi_device *spi = efx_mtd->spi; - struct efx_nic *efx = spi->efx; + struct efx_nic *efx = efx_mtd->efx; int rc; rc = mutex_lock_interruptible(&efx->spi_lock); if (rc) return rc; - rc = falcon_spi_write(spi, FALCON_FLASH_BOOTCODE_START + start, - len, retlen, buffer); + rc = falcon_spi_write(efx, spi, part->offset + start, len, + retlen, buffer); mutex_unlock(&efx->spi_lock); return rc; } -static void efx_mtd_sync(struct mtd_info *mtd) +static int falcon_mtd_sync(struct mtd_info *mtd) { struct efx_mtd *efx_mtd = mtd->priv; - struct efx_nic *efx = efx_mtd->spi->efx; + struct efx_nic *efx = efx_mtd->efx; int rc; mutex_lock(&efx->spi_lock); rc = efx_spi_slow_wait(efx_mtd, true); mutex_unlock(&efx->spi_lock); + return rc; +} + +static struct efx_mtd_ops falcon_mtd_ops = { + .read = falcon_mtd_read, + .erase = falcon_mtd_erase, + .write = falcon_mtd_write, + .sync = falcon_mtd_sync, +}; + +static int falcon_mtd_probe(struct efx_nic *efx) +{ + struct efx_spi_device *spi = efx->spi_flash; + struct efx_mtd *efx_mtd; + int rc; + + ASSERT_RTNL(); + if (!spi || spi->size <= FALCON_FLASH_BOOTCODE_START) + return -ENODEV; + + efx_mtd = kzalloc(sizeof(*efx_mtd) + sizeof(efx_mtd->part[0]), + GFP_KERNEL); + if (!efx_mtd) + return -ENOMEM; + + efx_mtd->spi = spi; + efx_mtd->name = "flash"; + efx_mtd->ops = &falcon_mtd_ops; + + efx_mtd->n_parts = 1; + efx_mtd->part[0].mtd.type = MTD_NORFLASH; + efx_mtd->part[0].mtd.flags = MTD_CAP_NORFLASH; + efx_mtd->part[0].mtd.size = spi->size - FALCON_FLASH_BOOTCODE_START; + efx_mtd->part[0].mtd.erasesize = spi->erase_size; + efx_mtd->part[0].offset = FALCON_FLASH_BOOTCODE_START; + efx_mtd->part[0].type_name = "sfc_flash_bootrom"; + + rc = efx_mtd_probe_device(efx, efx_mtd); if (rc) - EFX_ERR(efx, "%s sync failed (%d)\n", efx_mtd->name, rc); - return; + kfree(efx_mtd); + return rc; } -void efx_mtd_remove(struct efx_nic *efx) +/* Implementation of MTD operations for Siena */ + +static int siena_mtd_read(struct mtd_info *mtd, loff_t start, + size_t len, size_t *retlen, u8 *buffer) { - if (efx->spi_flash && efx->spi_flash->mtd) { - struct efx_mtd *efx_mtd = efx->spi_flash->mtd; - int rc; - - for (;;) { - rc = del_mtd_device(&efx_mtd->mtd); - if (rc != -EBUSY) - break; - ssleep(1); - } - WARN_ON(rc); - kfree(efx_mtd); + struct efx_mtd_partition *part = to_efx_mtd_partition(mtd); + struct efx_mtd *efx_mtd = mtd->priv; + struct efx_nic *efx = efx_mtd->efx; + loff_t offset = start; + loff_t end = min_t(loff_t, start + len, mtd->size); + size_t chunk; + int rc = 0; + + while (offset < end) { + chunk = min_t(size_t, end - offset, EFX_MCDI_CHUNK_LEN); + rc = efx_mcdi_nvram_read(efx, part->mcdi.nvram_type, offset, + buffer, chunk); + if (rc) + goto out; + offset += chunk; + buffer += chunk; } +out: + *retlen = offset - start; + return rc; } -void efx_mtd_rename(struct efx_nic *efx) +static int siena_mtd_erase(struct mtd_info *mtd, loff_t start, size_t len) { - if (efx->spi_flash && efx->spi_flash->mtd) { - struct efx_mtd *efx_mtd = efx->spi_flash->mtd; - snprintf(efx_mtd->name, sizeof(efx_mtd->name), - "%s sfc_flash_bootrom", efx->name); + struct efx_mtd_partition *part = to_efx_mtd_partition(mtd); + struct efx_mtd *efx_mtd = mtd->priv; + struct efx_nic *efx = efx_mtd->efx; + loff_t offset = start & ~((loff_t)(mtd->erasesize - 1)); + loff_t end = min_t(loff_t, start + len, mtd->size); + size_t chunk = part->mtd.erasesize; + int rc = 0; + + if (!part->mcdi.updating) { + rc = efx_mcdi_nvram_update_start(efx, part->mcdi.nvram_type); + if (rc) + goto out; + part->mcdi.updating = 1; + } + + /* The MCDI interface can in fact do multiple erase blocks at once; + * but erasing may be slow, so we make multiple calls here to avoid + * tripping the MCDI RPC timeout. */ + while (offset < end) { + rc = efx_mcdi_nvram_erase(efx, part->mcdi.nvram_type, offset, + chunk); + if (rc) + goto out; + offset += chunk; } +out: + return rc; } -int efx_mtd_probe(struct efx_nic *efx) +static int siena_mtd_write(struct mtd_info *mtd, loff_t start, + size_t len, size_t *retlen, const u8 *buffer) { - struct efx_spi_device *spi = efx->spi_flash; - struct efx_mtd *efx_mtd; + struct efx_mtd_partition *part = to_efx_mtd_partition(mtd); + struct efx_mtd *efx_mtd = mtd->priv; + struct efx_nic *efx = efx_mtd->efx; + loff_t offset = start; + loff_t end = min_t(loff_t, start + len, mtd->size); + size_t chunk; + int rc = 0; + + if (!part->mcdi.updating) { + rc = efx_mcdi_nvram_update_start(efx, part->mcdi.nvram_type); + if (rc) + goto out; + part->mcdi.updating = 1; + } - if (!spi || spi->size <= FALCON_FLASH_BOOTCODE_START) + while (offset < end) { + chunk = min_t(size_t, end - offset, EFX_MCDI_CHUNK_LEN); + rc = efx_mcdi_nvram_write(efx, part->mcdi.nvram_type, offset, + buffer, chunk); + if (rc) + goto out; + offset += chunk; + buffer += chunk; + } +out: + *retlen = offset - start; + return rc; +} + +static int siena_mtd_sync(struct mtd_info *mtd) +{ + struct efx_mtd_partition *part = to_efx_mtd_partition(mtd); + struct efx_mtd *efx_mtd = mtd->priv; + struct efx_nic *efx = efx_mtd->efx; + int rc = 0; + + if (part->mcdi.updating) { + part->mcdi.updating = 0; + rc = efx_mcdi_nvram_update_finish(efx, part->mcdi.nvram_type); + } + + return rc; +} + +static struct efx_mtd_ops siena_mtd_ops = { + .read = siena_mtd_read, + .erase = siena_mtd_erase, + .write = siena_mtd_write, + .sync = siena_mtd_sync, +}; + +struct siena_nvram_type_info { + int port; + const char *name; +}; + +static struct siena_nvram_type_info siena_nvram_types[] = { + [MC_CMD_NVRAM_TYPE_DISABLED_CALLISTO] = { 0, "sfc_dummy_phy" }, + [MC_CMD_NVRAM_TYPE_MC_FW] = { 0, "sfc_mcfw" }, + [MC_CMD_NVRAM_TYPE_MC_FW_BACKUP] = { 0, "sfc_mcfw_backup" }, + [MC_CMD_NVRAM_TYPE_STATIC_CFG_PORT0] = { 0, "sfc_static_cfg" }, + [MC_CMD_NVRAM_TYPE_STATIC_CFG_PORT1] = { 1, "sfc_static_cfg" }, + [MC_CMD_NVRAM_TYPE_DYNAMIC_CFG_PORT0] = { 0, "sfc_dynamic_cfg" }, + [MC_CMD_NVRAM_TYPE_DYNAMIC_CFG_PORT1] = { 1, "sfc_dynamic_cfg" }, + [MC_CMD_NVRAM_TYPE_EXP_ROM] = { 0, "sfc_exp_rom" }, + [MC_CMD_NVRAM_TYPE_EXP_ROM_CFG_PORT0] = { 0, "sfc_exp_rom_cfg" }, + [MC_CMD_NVRAM_TYPE_EXP_ROM_CFG_PORT1] = { 1, "sfc_exp_rom_cfg" }, + [MC_CMD_NVRAM_TYPE_PHY_PORT0] = { 0, "sfc_phy_fw" }, + [MC_CMD_NVRAM_TYPE_PHY_PORT1] = { 1, "sfc_phy_fw" }, +}; + +static int siena_mtd_probe_partition(struct efx_nic *efx, + struct efx_mtd *efx_mtd, + unsigned int part_id, + unsigned int type) +{ + struct efx_mtd_partition *part = &efx_mtd->part[part_id]; + struct siena_nvram_type_info *info; + size_t size, erase_size; + bool protected; + int rc; + + if (type >= ARRAY_SIZE(siena_nvram_types)) return -ENODEV; - efx_mtd = kzalloc(sizeof(*efx_mtd), GFP_KERNEL); + info = &siena_nvram_types[type]; + + if (info->port != efx_port_num(efx)) + return -ENODEV; + + rc = efx_mcdi_nvram_info(efx, type, &size, &erase_size, &protected); + if (rc) + return rc; + if (protected) + return -ENODEV; /* hide it */ + + part->mcdi.nvram_type = type; + part->type_name = info->name; + + part->mtd.type = MTD_NORFLASH; + part->mtd.flags = MTD_CAP_NORFLASH; + part->mtd.size = size; + part->mtd.erasesize = erase_size; + + return 0; +} + +static int siena_mtd_get_fw_subtypes(struct efx_nic *efx, + struct efx_mtd *efx_mtd) +{ + struct efx_mtd_partition *part; + uint16_t fw_subtype_list[MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_LEN / + sizeof(uint16_t)]; + int rc; + + rc = efx_mcdi_get_board_cfg(efx, NULL, fw_subtype_list); + if (rc) + return rc; + + efx_for_each_partition(part, efx_mtd) + part->mcdi.fw_subtype = fw_subtype_list[part->mcdi.nvram_type]; + + return 0; +} + +static int siena_mtd_probe(struct efx_nic *efx) +{ + struct efx_mtd *efx_mtd; + int rc = -ENODEV; + u32 nvram_types; + unsigned int type; + + ASSERT_RTNL(); + + rc = efx_mcdi_nvram_types(efx, &nvram_types); + if (rc) + return rc; + + efx_mtd = kzalloc(sizeof(*efx_mtd) + + hweight32(nvram_types) * sizeof(efx_mtd->part[0]), + GFP_KERNEL); if (!efx_mtd) return -ENOMEM; - efx_mtd->spi = spi; - spi->mtd = efx_mtd; - - efx_mtd->mtd.type = MTD_NORFLASH; - efx_mtd->mtd.flags = MTD_CAP_NORFLASH; - efx_mtd->mtd.size = spi->size - FALCON_FLASH_BOOTCODE_START; - efx_mtd->mtd.erasesize = spi->erase_size; - efx_mtd->mtd.writesize = 1; - efx_mtd_rename(efx); - - efx_mtd->mtd.owner = THIS_MODULE; - efx_mtd->mtd.priv = efx_mtd; - efx_mtd->mtd.name = efx_mtd->name; - efx_mtd->mtd.erase = efx_mtd_erase; - efx_mtd->mtd.read = efx_mtd_read; - efx_mtd->mtd.write = efx_mtd_write; - efx_mtd->mtd.sync = efx_mtd_sync; - - if (add_mtd_device(&efx_mtd->mtd)) { - kfree(efx_mtd); - spi->mtd = NULL; - /* add_mtd_device() returns 1 if the MTD table is full */ - return -ENOMEM; + efx_mtd->name = "Siena NVRAM manager"; + + efx_mtd->ops = &siena_mtd_ops; + + type = 0; + efx_mtd->n_parts = 0; + + while (nvram_types != 0) { + if (nvram_types & 1) { + rc = siena_mtd_probe_partition(efx, efx_mtd, + efx_mtd->n_parts, type); + if (rc == 0) + efx_mtd->n_parts++; + else if (rc != -ENODEV) + goto fail; + } + type++; + nvram_types >>= 1; } - return 0; + rc = siena_mtd_get_fw_subtypes(efx, efx_mtd); + if (rc) + goto fail; + + rc = efx_mtd_probe_device(efx, efx_mtd); +fail: + if (rc) + kfree(efx_mtd); + return rc; } + diff --git a/drivers/net/sfc/net_driver.h b/drivers/net/sfc/net_driver.h index ac808d5f24a0..34c381f009b7 100644 --- a/drivers/net/sfc/net_driver.h +++ b/drivers/net/sfc/net_driver.h @@ -1,7 +1,7 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards * Copyright 2005-2006 Fen Systems Ltd. - * Copyright 2005-2008 Solarflare Communications Inc. + * Copyright 2005-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -38,7 +38,7 @@ #ifndef EFX_DRIVER_NAME #define EFX_DRIVER_NAME "sfc" #endif -#define EFX_DRIVER_VERSION "2.3" +#define EFX_DRIVER_VERSION "3.0" #ifdef EFX_ENABLE_DEBUG #define EFX_BUG_ON_PARANOID(x) BUG_ON(x) @@ -113,6 +113,13 @@ struct efx_special_buffer { int entries; }; +enum efx_flush_state { + FLUSH_NONE, + FLUSH_PENDING, + FLUSH_FAILED, + FLUSH_DONE, +}; + /** * struct efx_tx_buffer - An Efx TX buffer * @skb: The associated socket buffer. @@ -189,7 +196,7 @@ struct efx_tx_queue { struct efx_nic *nic; struct efx_tx_buffer *buffer; struct efx_special_buffer txd; - bool flushed; + enum efx_flush_state flushed; /* Members used mainly on the completion path */ unsigned int read_count ____cacheline_aligned_in_smp; @@ -284,7 +291,7 @@ struct efx_rx_queue { struct page *buf_page; dma_addr_t buf_dma_addr; char *buf_data; - bool flushed; + enum efx_flush_state flushed; }; /** @@ -343,9 +350,9 @@ enum efx_rx_alloc_method { * @rx_alloc_push_pages: RX allocation method currently in use for pushing * descriptors * @n_rx_tobe_disc: Count of RX_TOBE_DISC errors - * @n_rx_ip_frag_err: Count of RX IP fragment errors * @n_rx_ip_hdr_chksum_err: Count of RX IP header checksum errors * @n_rx_tcp_udp_chksum_err: Count of RX TCP and UDP checksum errors + * @n_rx_mcast_mismatch: Count of unmatched multicast frames * @n_rx_frm_trunc: Count of RX_FRM_TRUNC errors * @n_rx_overlength: Count of RX_OVERLENGTH errors * @n_skbuff_leaks: Count of skbuffs leaked due to RX overrun @@ -373,9 +380,9 @@ struct efx_channel { int rx_alloc_push_pages; unsigned n_rx_tobe_disc; - unsigned n_rx_ip_frag_err; unsigned n_rx_ip_hdr_chksum_err; unsigned n_rx_tcp_udp_chksum_err; + unsigned n_rx_mcast_mismatch; unsigned n_rx_frm_trunc; unsigned n_rx_overlength; unsigned n_skbuff_leaks; @@ -421,19 +428,6 @@ enum efx_int_mode { }; #define EFX_INT_MODE_USE_MSI(x) (((x)->interrupt_mode) <= EFX_INT_MODE_MSI) -enum phy_type { - PHY_TYPE_NONE = 0, - PHY_TYPE_TXC43128 = 1, - PHY_TYPE_88E1111 = 2, - PHY_TYPE_SFX7101 = 3, - PHY_TYPE_QT2022C2 = 4, - PHY_TYPE_PM8358 = 6, - PHY_TYPE_SFT9001A = 8, - PHY_TYPE_QT2025C = 9, - PHY_TYPE_SFT9001B = 10, - PHY_TYPE_MAX /* Insert any new items before this */ -}; - #define EFX_IS10G(efx) ((efx)->link_state.speed == 10000) enum nic_state { @@ -476,12 +470,6 @@ enum efx_fc_type { EFX_FC_AUTO = 4, }; -/* Supported MAC bit-mask */ -enum efx_mac_type { - EFX_GMAC = 1, - EFX_XMAC = 2, -}; - /** * struct efx_link_state - Current state of the link * @up: Link is up @@ -496,55 +484,55 @@ struct efx_link_state { unsigned int speed; }; +static inline bool efx_link_state_equal(const struct efx_link_state *left, + const struct efx_link_state *right) +{ + return left->up == right->up && left->fd == right->fd && + left->fc == right->fc && left->speed == right->speed; +} + /** * struct efx_mac_operations - Efx MAC operations table * @reconfigure: Reconfigure MAC. Serialised by the mac_lock * @update_stats: Update statistics - * @irq: Hardware MAC event callback. Serialised by the mac_lock - * @poll: Poll for hardware state. Serialised by the mac_lock + * @check_fault: Check fault state. True if fault present. */ struct efx_mac_operations { - void (*reconfigure) (struct efx_nic *efx); + int (*reconfigure) (struct efx_nic *efx); void (*update_stats) (struct efx_nic *efx); - void (*irq) (struct efx_nic *efx); - void (*poll) (struct efx_nic *efx); + bool (*check_fault)(struct efx_nic *efx); }; /** * struct efx_phy_operations - Efx PHY operations table + * @probe: Probe PHY and initialise efx->mdio.mode_support, efx->mdio.mmds, + * efx->loopback_modes. * @init: Initialise PHY * @fini: Shut down PHY * @reconfigure: Reconfigure PHY (e.g. for new link parameters) - * @clear_interrupt: Clear down interrupt - * @poll: Poll for hardware state. Serialised by the mac_lock. + * @poll: Update @link_state and report whether it changed. + * Serialised by the mac_lock. * @get_settings: Get ethtool settings. Serialised by the mac_lock. * @set_settings: Set ethtool settings. Serialised by the mac_lock. * @set_npage_adv: Set abilities advertised in (Extended) Next Page * (only needed where AN bit is set in mmds) - * @num_tests: Number of PHY-specific tests/results - * @test_names: Names of the tests/results + * @test_name: Get the name of a PHY-specific test/result * @run_tests: Run tests and record results as appropriate. * Flags are the ethtool tests flags. - * @mmds: MMD presence mask - * @loopbacks: Supported loopback modes mask */ struct efx_phy_operations { - enum efx_mac_type macs; + int (*probe) (struct efx_nic *efx); int (*init) (struct efx_nic *efx); void (*fini) (struct efx_nic *efx); - void (*reconfigure) (struct efx_nic *efx); - void (*clear_interrupt) (struct efx_nic *efx); - void (*poll) (struct efx_nic *efx); + int (*reconfigure) (struct efx_nic *efx); + bool (*poll) (struct efx_nic *efx); void (*get_settings) (struct efx_nic *efx, struct ethtool_cmd *ecmd); int (*set_settings) (struct efx_nic *efx, struct ethtool_cmd *ecmd); void (*set_npage_adv) (struct efx_nic *efx, u32); - u32 num_tests; - const char *const *test_names; + const char *(*test_name) (struct efx_nic *efx, unsigned int index); int (*run_tests) (struct efx_nic *efx, int *results, unsigned flags); - int mmds; - unsigned loopbacks; }; /** @@ -686,19 +674,20 @@ union efx_multicast_hash { * interrupt is handled. It is used by falcon_test_interrupt() * to verify that an interrupt has occurred. * @spi_flash: SPI flash device - * This field will be %NULL if no flash device is present. + * This field will be %NULL if no flash device is present (or for Siena). * @spi_eeprom: SPI EEPROM device - * This field will be %NULL if no EEPROM device is present. + * This field will be %NULL if no EEPROM device is present (or for Siena). * @spi_lock: SPI bus lock + * @mtd_list: List of MTDs attached to the NIC * @n_rx_nodesc_drop_cnt: RX no descriptor drop count * @nic_data: Hardware dependant state * @mac_lock: MAC access lock. Protects @port_enabled, @phy_mode, * @port_inhibited, efx_monitor() and efx_reconfigure_port() * @port_enabled: Port enabled indicator. - * Serialises efx_stop_all(), efx_start_all(), efx_monitor(), - * efx_phy_work(), and efx_mac_work() with kernel interfaces. Safe to read - * under any one of the rtnl_lock, mac_lock, or netif_tx_lock, but all - * three must be held to modify it. + * Serialises efx_stop_all(), efx_start_all(), efx_monitor() and + * efx_mac_work() with kernel interfaces. Safe to read under any + * one of the rtnl_lock, mac_lock, or netif_tx_lock, but all three must + * be held to modify it. * @port_inhibited: If set, the netif_carrier is always off. Hold the mac_lock * @port_initialized: Port initialized? * @net_dev: Operating system network device. Consider holding the rtnl lock @@ -710,23 +699,23 @@ union efx_multicast_hash { * &struct net_device_stats. * @stats_buffer: DMA buffer for statistics * @stats_lock: Statistics update lock. Serialises statistics fetches - * @stats_disable_count: Nest count for disabling statistics fetches * @mac_op: MAC interface * @mac_address: Permanent MAC address * @phy_type: PHY type - * @phy_lock: PHY access lock + * @mdio_lock: MDIO lock * @phy_op: PHY interface * @phy_data: PHY private data (including PHY-specific stats) * @mdio: PHY MDIO interface + * @mdio_bus: PHY MDIO bus ID (only used by Siena) * @phy_mode: PHY operating mode. Serialised by @mac_lock. - * @mac_up: MAC link state + * @xmac_poll_required: XMAC link state needs polling + * @link_advertising: Autonegotiation advertising flags * @link_state: Current state of the link * @n_link_state_changes: Number of times the link has changed state * @promiscuous: Promiscuous flag. Protected by netif_tx_lock. * @multicast_hash: Multicast hash table * @wanted_fc: Wanted flow control flags - * @phy_work: work item for dealing with PHY events - * @mac_work: work item for dealing with MAC events + * @mac_work: Work item for changing MAC promiscuity and multicast hash * @loopback_mode: Loopback status * @loopback_modes: Supported loopback mode bitmask * @loopback_selftest: Offline self-test private state @@ -768,14 +757,18 @@ struct efx_nic { struct efx_buffer irq_status; volatile signed int last_irq_cpu; + unsigned long irq_zero_count; struct efx_spi_device *spi_flash; struct efx_spi_device *spi_eeprom; struct mutex spi_lock; +#ifdef CONFIG_SFC_MTD + struct list_head mtd_list; +#endif unsigned n_rx_nodesc_drop_cnt; - struct falcon_nic_data *nic_data; + void *nic_data; struct mutex mac_lock; struct work_struct mac_work; @@ -792,20 +785,20 @@ struct efx_nic { struct efx_mac_stats mac_stats; struct efx_buffer stats_buffer; spinlock_t stats_lock; - unsigned int stats_disable_count; struct efx_mac_operations *mac_op; unsigned char mac_address[ETH_ALEN]; - enum phy_type phy_type; - spinlock_t phy_lock; - struct work_struct phy_work; + unsigned int phy_type; + struct mutex mdio_lock; struct efx_phy_operations *phy_op; void *phy_data; struct mdio_if_info mdio; + unsigned int mdio_bus; enum efx_phy_mode phy_mode; - bool mac_up; + bool xmac_poll_required; + u32 link_advertising; struct efx_link_state link_state; unsigned int n_link_state_changes; @@ -815,7 +808,7 @@ struct efx_nic { atomic_t rx_reset; enum efx_loopback_mode loopback_mode; - unsigned int loopback_modes; + u64 loopback_modes; void *loopback_selftest; }; @@ -834,8 +827,37 @@ static inline const char *efx_dev_name(struct efx_nic *efx) return efx_dev_registered(efx) ? efx->name : ""; } +static inline unsigned int efx_port_num(struct efx_nic *efx) +{ + return PCI_FUNC(efx->pci_dev->devfn); +} + /** * struct efx_nic_type - Efx device type definition + * @probe: Probe the controller + * @remove: Free resources allocated by probe() + * @init: Initialise the controller + * @fini: Shut down the controller + * @monitor: Periodic function for polling link state and hardware monitor + * @reset: Reset the controller hardware and possibly the PHY. This will + * be called while the controller is uninitialised. + * @probe_port: Probe the MAC and PHY + * @remove_port: Free resources allocated by probe_port() + * @prepare_flush: Prepare the hardware for flushing the DMA queues + * @update_stats: Update statistics not provided by event handling + * @start_stats: Start the regular fetching of statistics + * @stop_stats: Stop the regular fetching of statistics + * @set_id_led: Set state of identifying LED or revert to automatic function + * @push_irq_moderation: Apply interrupt moderation value + * @push_multicast_hash: Apply multicast hash table + * @reconfigure_port: Push loopback/power/txdis changes to the MAC and PHY + * @get_wol: Get WoL configuration from driver state + * @set_wol: Push WoL configuration to the NIC + * @resume_wol: Synchronise WoL state between driver and MC (e.g. after resume) + * @test_registers: Test read/write functionality of control registers + * @test_nvram: Test validity of NVRAM contents + * @default_mac_ops: efx_mac_operations to set at startup + * @revision: Hardware architecture revision * @mem_map_size: Memory BAR mapped size * @txd_ptr_tbl_base: TX descriptor ring base address * @rxd_ptr_tbl_base: RX descriptor ring base address @@ -848,20 +870,52 @@ static inline const char *efx_dev_name(struct efx_nic *efx) * from &enum efx_init_mode. * @phys_addr_channels: Number of channels with physically addressed * descriptors + * @tx_dc_base: Base address in SRAM of TX queue descriptor caches + * @rx_dc_base: Base address in SRAM of RX queue descriptor caches + * @offload_features: net_device feature flags for protocol offload + * features implemented in hardware + * @reset_world_flags: Flags for additional components covered by + * reset method RESET_TYPE_WORLD */ struct efx_nic_type { + int (*probe)(struct efx_nic *efx); + void (*remove)(struct efx_nic *efx); + int (*init)(struct efx_nic *efx); + void (*fini)(struct efx_nic *efx); + void (*monitor)(struct efx_nic *efx); + int (*reset)(struct efx_nic *efx, enum reset_type method); + int (*probe_port)(struct efx_nic *efx); + void (*remove_port)(struct efx_nic *efx); + void (*prepare_flush)(struct efx_nic *efx); + void (*update_stats)(struct efx_nic *efx); + void (*start_stats)(struct efx_nic *efx); + void (*stop_stats)(struct efx_nic *efx); + void (*set_id_led)(struct efx_nic *efx, enum efx_led_mode mode); + void (*push_irq_moderation)(struct efx_channel *channel); + void (*push_multicast_hash)(struct efx_nic *efx); + int (*reconfigure_port)(struct efx_nic *efx); + void (*get_wol)(struct efx_nic *efx, struct ethtool_wolinfo *wol); + int (*set_wol)(struct efx_nic *efx, u32 type); + void (*resume_wol)(struct efx_nic *efx); + int (*test_registers)(struct efx_nic *efx); + int (*test_nvram)(struct efx_nic *efx); + struct efx_mac_operations *default_mac_ops; + + int revision; unsigned int mem_map_size; unsigned int txd_ptr_tbl_base; unsigned int rxd_ptr_tbl_base; unsigned int buf_tbl_base; unsigned int evq_ptr_tbl_base; unsigned int evq_rptr_tbl_base; - u64 max_dma_mask; - unsigned int rx_buffer_padding; unsigned int max_interrupt_mode; unsigned int phys_addr_channels; + unsigned int tx_dc_base; + unsigned int rx_dc_base; + unsigned long offload_features; + u32 reset_world_flags; }; /************************************************************************** diff --git a/drivers/net/sfc/nic.c b/drivers/net/sfc/nic.c new file mode 100644 index 000000000000..a577be227862 --- /dev/null +++ b/drivers/net/sfc/nic.c @@ -0,0 +1,1583 @@ +/**************************************************************************** + * Driver for Solarflare Solarstorm network controllers and boards + * Copyright 2005-2006 Fen Systems Ltd. + * Copyright 2006-2009 Solarflare Communications Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +#include <linux/bitops.h> +#include <linux/delay.h> +#include <linux/pci.h> +#include <linux/module.h> +#include <linux/seq_file.h> +#include "net_driver.h" +#include "bitfield.h" +#include "efx.h" +#include "nic.h" +#include "regs.h" +#include "io.h" +#include "workarounds.h" + +/************************************************************************** + * + * Configurable values + * + ************************************************************************** + */ + +/* This is set to 16 for a good reason. In summary, if larger than + * 16, the descriptor cache holds more than a default socket + * buffer's worth of packets (for UDP we can only have at most one + * socket buffer's worth outstanding). This combined with the fact + * that we only get 1 TX event per descriptor cache means the NIC + * goes idle. + */ +#define TX_DC_ENTRIES 16 +#define TX_DC_ENTRIES_ORDER 1 + +#define RX_DC_ENTRIES 64 +#define RX_DC_ENTRIES_ORDER 3 + +/* RX FIFO XOFF watermark + * + * When the amount of the RX FIFO increases used increases past this + * watermark send XOFF. Only used if RX flow control is enabled (ethtool -A) + * This also has an effect on RX/TX arbitration + */ +int efx_nic_rx_xoff_thresh = -1; +module_param_named(rx_xoff_thresh_bytes, efx_nic_rx_xoff_thresh, int, 0644); +MODULE_PARM_DESC(rx_xoff_thresh_bytes, "RX fifo XOFF threshold"); + +/* RX FIFO XON watermark + * + * When the amount of the RX FIFO used decreases below this + * watermark send XON. Only used if TX flow control is enabled (ethtool -A) + * This also has an effect on RX/TX arbitration + */ +int efx_nic_rx_xon_thresh = -1; +module_param_named(rx_xon_thresh_bytes, efx_nic_rx_xon_thresh, int, 0644); +MODULE_PARM_DESC(rx_xon_thresh_bytes, "RX fifo XON threshold"); + +/* If EFX_MAX_INT_ERRORS internal errors occur within + * EFX_INT_ERROR_EXPIRE seconds, we consider the NIC broken and + * disable it. + */ +#define EFX_INT_ERROR_EXPIRE 3600 +#define EFX_MAX_INT_ERRORS 5 + +/* We poll for events every FLUSH_INTERVAL ms, and check FLUSH_POLL_COUNT times + */ +#define EFX_FLUSH_INTERVAL 10 +#define EFX_FLUSH_POLL_COUNT 100 + +/* Size and alignment of special buffers (4KB) */ +#define EFX_BUF_SIZE 4096 + +/* Depth of RX flush request fifo */ +#define EFX_RX_FLUSH_COUNT 4 + +/************************************************************************** + * + * Solarstorm hardware access + * + **************************************************************************/ + +static inline void efx_write_buf_tbl(struct efx_nic *efx, efx_qword_t *value, + unsigned int index) +{ + efx_sram_writeq(efx, efx->membase + efx->type->buf_tbl_base, + value, index); +} + +/* Read the current event from the event queue */ +static inline efx_qword_t *efx_event(struct efx_channel *channel, + unsigned int index) +{ + return (((efx_qword_t *) (channel->eventq.addr)) + index); +} + +/* See if an event is present + * + * We check both the high and low dword of the event for all ones. We + * wrote all ones when we cleared the event, and no valid event can + * have all ones in either its high or low dwords. This approach is + * robust against reordering. + * + * Note that using a single 64-bit comparison is incorrect; even + * though the CPU read will be atomic, the DMA write may not be. + */ +static inline int efx_event_present(efx_qword_t *event) +{ + return (!(EFX_DWORD_IS_ALL_ONES(event->dword[0]) | + EFX_DWORD_IS_ALL_ONES(event->dword[1]))); +} + +static bool efx_masked_compare_oword(const efx_oword_t *a, const efx_oword_t *b, + const efx_oword_t *mask) +{ + return ((a->u64[0] ^ b->u64[0]) & mask->u64[0]) || + ((a->u64[1] ^ b->u64[1]) & mask->u64[1]); +} + +int efx_nic_test_registers(struct efx_nic *efx, + const struct efx_nic_register_test *regs, + size_t n_regs) +{ + unsigned address = 0, i, j; + efx_oword_t mask, imask, original, reg, buf; + + /* Falcon should be in loopback to isolate the XMAC from the PHY */ + WARN_ON(!LOOPBACK_INTERNAL(efx)); + + for (i = 0; i < n_regs; ++i) { + address = regs[i].address; + mask = imask = regs[i].mask; + EFX_INVERT_OWORD(imask); + + efx_reado(efx, &original, address); + + /* bit sweep on and off */ + for (j = 0; j < 128; j++) { + if (!EFX_EXTRACT_OWORD32(mask, j, j)) + continue; + + /* Test this testable bit can be set in isolation */ + EFX_AND_OWORD(reg, original, mask); + EFX_SET_OWORD32(reg, j, j, 1); + + efx_writeo(efx, ®, address); + efx_reado(efx, &buf, address); + + if (efx_masked_compare_oword(®, &buf, &mask)) + goto fail; + + /* Test this testable bit can be cleared in isolation */ + EFX_OR_OWORD(reg, original, mask); + EFX_SET_OWORD32(reg, j, j, 0); + + efx_writeo(efx, ®, address); + efx_reado(efx, &buf, address); + + if (efx_masked_compare_oword(®, &buf, &mask)) + goto fail; + } + + efx_writeo(efx, &original, address); + } + + return 0; + +fail: + EFX_ERR(efx, "wrote "EFX_OWORD_FMT" read "EFX_OWORD_FMT + " at address 0x%x mask "EFX_OWORD_FMT"\n", EFX_OWORD_VAL(reg), + EFX_OWORD_VAL(buf), address, EFX_OWORD_VAL(mask)); + return -EIO; +} + +/************************************************************************** + * + * Special buffer handling + * Special buffers are used for event queues and the TX and RX + * descriptor rings. + * + *************************************************************************/ + +/* + * Initialise a special buffer + * + * This will define a buffer (previously allocated via + * efx_alloc_special_buffer()) in the buffer table, allowing + * it to be used for event queues, descriptor rings etc. + */ +static void +efx_init_special_buffer(struct efx_nic *efx, struct efx_special_buffer *buffer) +{ + efx_qword_t buf_desc; + int index; + dma_addr_t dma_addr; + int i; + + EFX_BUG_ON_PARANOID(!buffer->addr); + + /* Write buffer descriptors to NIC */ + for (i = 0; i < buffer->entries; i++) { + index = buffer->index + i; + dma_addr = buffer->dma_addr + (i * 4096); + EFX_LOG(efx, "mapping special buffer %d at %llx\n", + index, (unsigned long long)dma_addr); + EFX_POPULATE_QWORD_3(buf_desc, + FRF_AZ_BUF_ADR_REGION, 0, + FRF_AZ_BUF_ADR_FBUF, dma_addr >> 12, + FRF_AZ_BUF_OWNER_ID_FBUF, 0); + efx_write_buf_tbl(efx, &buf_desc, index); + } +} + +/* Unmaps a buffer and clears the buffer table entries */ +static void +efx_fini_special_buffer(struct efx_nic *efx, struct efx_special_buffer *buffer) +{ + efx_oword_t buf_tbl_upd; + unsigned int start = buffer->index; + unsigned int end = (buffer->index + buffer->entries - 1); + + if (!buffer->entries) + return; + + EFX_LOG(efx, "unmapping special buffers %d-%d\n", + buffer->index, buffer->index + buffer->entries - 1); + + EFX_POPULATE_OWORD_4(buf_tbl_upd, + FRF_AZ_BUF_UPD_CMD, 0, + FRF_AZ_BUF_CLR_CMD, 1, + FRF_AZ_BUF_CLR_END_ID, end, + FRF_AZ_BUF_CLR_START_ID, start); + efx_writeo(efx, &buf_tbl_upd, FR_AZ_BUF_TBL_UPD); +} + +/* + * Allocate a new special buffer + * + * This allocates memory for a new buffer, clears it and allocates a + * new buffer ID range. It does not write into the buffer table. + * + * This call will allocate 4KB buffers, since 8KB buffers can't be + * used for event queues and descriptor rings. + */ +static int efx_alloc_special_buffer(struct efx_nic *efx, + struct efx_special_buffer *buffer, + unsigned int len) +{ + len = ALIGN(len, EFX_BUF_SIZE); + + buffer->addr = pci_alloc_consistent(efx->pci_dev, len, + &buffer->dma_addr); + if (!buffer->addr) + return -ENOMEM; + buffer->len = len; + buffer->entries = len / EFX_BUF_SIZE; + BUG_ON(buffer->dma_addr & (EFX_BUF_SIZE - 1)); + + /* All zeros is a potentially valid event so memset to 0xff */ + memset(buffer->addr, 0xff, len); + + /* Select new buffer ID */ + buffer->index = efx->next_buffer_table; + efx->next_buffer_table += buffer->entries; + + EFX_LOG(efx, "allocating special buffers %d-%d at %llx+%x " + "(virt %p phys %llx)\n", buffer->index, + buffer->index + buffer->entries - 1, + (u64)buffer->dma_addr, len, + buffer->addr, (u64)virt_to_phys(buffer->addr)); + + return 0; +} + +static void +efx_free_special_buffer(struct efx_nic *efx, struct efx_special_buffer *buffer) +{ + if (!buffer->addr) + return; + + EFX_LOG(efx, "deallocating special buffers %d-%d at %llx+%x " + "(virt %p phys %llx)\n", buffer->index, + buffer->index + buffer->entries - 1, + (u64)buffer->dma_addr, buffer->len, + buffer->addr, (u64)virt_to_phys(buffer->addr)); + + pci_free_consistent(efx->pci_dev, buffer->len, buffer->addr, + buffer->dma_addr); + buffer->addr = NULL; + buffer->entries = 0; +} + +/************************************************************************** + * + * Generic buffer handling + * These buffers are used for interrupt status and MAC stats + * + **************************************************************************/ + +int efx_nic_alloc_buffer(struct efx_nic *efx, struct efx_buffer *buffer, + unsigned int len) +{ + buffer->addr = pci_alloc_consistent(efx->pci_dev, len, + &buffer->dma_addr); + if (!buffer->addr) + return -ENOMEM; + buffer->len = len; + memset(buffer->addr, 0, len); + return 0; +} + +void efx_nic_free_buffer(struct efx_nic *efx, struct efx_buffer *buffer) +{ + if (buffer->addr) { + pci_free_consistent(efx->pci_dev, buffer->len, + buffer->addr, buffer->dma_addr); + buffer->addr = NULL; + } +} + +/************************************************************************** + * + * TX path + * + **************************************************************************/ + +/* Returns a pointer to the specified transmit descriptor in the TX + * descriptor queue belonging to the specified channel. + */ +static inline efx_qword_t * +efx_tx_desc(struct efx_tx_queue *tx_queue, unsigned int index) +{ + return (((efx_qword_t *) (tx_queue->txd.addr)) + index); +} + +/* This writes to the TX_DESC_WPTR; write pointer for TX descriptor ring */ +static inline void efx_notify_tx_desc(struct efx_tx_queue *tx_queue) +{ + unsigned write_ptr; + efx_dword_t reg; + + write_ptr = tx_queue->write_count & EFX_TXQ_MASK; + EFX_POPULATE_DWORD_1(reg, FRF_AZ_TX_DESC_WPTR_DWORD, write_ptr); + efx_writed_page(tx_queue->efx, ®, + FR_AZ_TX_DESC_UPD_DWORD_P0, tx_queue->queue); +} + + +/* For each entry inserted into the software descriptor ring, create a + * descriptor in the hardware TX descriptor ring (in host memory), and + * write a doorbell. + */ +void efx_nic_push_buffers(struct efx_tx_queue *tx_queue) +{ + + struct efx_tx_buffer *buffer; + efx_qword_t *txd; + unsigned write_ptr; + + BUG_ON(tx_queue->write_count == tx_queue->insert_count); + + do { + write_ptr = tx_queue->write_count & EFX_TXQ_MASK; + buffer = &tx_queue->buffer[write_ptr]; + txd = efx_tx_desc(tx_queue, write_ptr); + ++tx_queue->write_count; + + /* Create TX descriptor ring entry */ + EFX_POPULATE_QWORD_4(*txd, + FSF_AZ_TX_KER_CONT, buffer->continuation, + FSF_AZ_TX_KER_BYTE_COUNT, buffer->len, + FSF_AZ_TX_KER_BUF_REGION, 0, + FSF_AZ_TX_KER_BUF_ADDR, buffer->dma_addr); + } while (tx_queue->write_count != tx_queue->insert_count); + + wmb(); /* Ensure descriptors are written before they are fetched */ + efx_notify_tx_desc(tx_queue); +} + +/* Allocate hardware resources for a TX queue */ +int efx_nic_probe_tx(struct efx_tx_queue *tx_queue) +{ + struct efx_nic *efx = tx_queue->efx; + BUILD_BUG_ON(EFX_TXQ_SIZE < 512 || EFX_TXQ_SIZE > 4096 || + EFX_TXQ_SIZE & EFX_TXQ_MASK); + return efx_alloc_special_buffer(efx, &tx_queue->txd, + EFX_TXQ_SIZE * sizeof(efx_qword_t)); +} + +void efx_nic_init_tx(struct efx_tx_queue *tx_queue) +{ + efx_oword_t tx_desc_ptr; + struct efx_nic *efx = tx_queue->efx; + + tx_queue->flushed = FLUSH_NONE; + + /* Pin TX descriptor ring */ + efx_init_special_buffer(efx, &tx_queue->txd); + + /* Push TX descriptor ring to card */ + EFX_POPULATE_OWORD_10(tx_desc_ptr, + FRF_AZ_TX_DESCQ_EN, 1, + FRF_AZ_TX_ISCSI_DDIG_EN, 0, + FRF_AZ_TX_ISCSI_HDIG_EN, 0, + FRF_AZ_TX_DESCQ_BUF_BASE_ID, tx_queue->txd.index, + FRF_AZ_TX_DESCQ_EVQ_ID, + tx_queue->channel->channel, + FRF_AZ_TX_DESCQ_OWNER_ID, 0, + FRF_AZ_TX_DESCQ_LABEL, tx_queue->queue, + FRF_AZ_TX_DESCQ_SIZE, + __ffs(tx_queue->txd.entries), + FRF_AZ_TX_DESCQ_TYPE, 0, + FRF_BZ_TX_NON_IP_DROP_DIS, 1); + + if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) { + int csum = tx_queue->queue == EFX_TX_QUEUE_OFFLOAD_CSUM; + EFX_SET_OWORD_FIELD(tx_desc_ptr, FRF_BZ_TX_IP_CHKSM_DIS, !csum); + EFX_SET_OWORD_FIELD(tx_desc_ptr, FRF_BZ_TX_TCP_CHKSM_DIS, + !csum); + } + + efx_writeo_table(efx, &tx_desc_ptr, efx->type->txd_ptr_tbl_base, + tx_queue->queue); + + if (efx_nic_rev(efx) < EFX_REV_FALCON_B0) { + efx_oword_t reg; + + /* Only 128 bits in this register */ + BUILD_BUG_ON(EFX_TX_QUEUE_COUNT >= 128); + + efx_reado(efx, ®, FR_AA_TX_CHKSM_CFG); + if (tx_queue->queue == EFX_TX_QUEUE_OFFLOAD_CSUM) + clear_bit_le(tx_queue->queue, (void *)®); + else + set_bit_le(tx_queue->queue, (void *)®); + efx_writeo(efx, ®, FR_AA_TX_CHKSM_CFG); + } +} + +static void efx_flush_tx_queue(struct efx_tx_queue *tx_queue) +{ + struct efx_nic *efx = tx_queue->efx; + efx_oword_t tx_flush_descq; + + tx_queue->flushed = FLUSH_PENDING; + + /* Post a flush command */ + EFX_POPULATE_OWORD_2(tx_flush_descq, + FRF_AZ_TX_FLUSH_DESCQ_CMD, 1, + FRF_AZ_TX_FLUSH_DESCQ, tx_queue->queue); + efx_writeo(efx, &tx_flush_descq, FR_AZ_TX_FLUSH_DESCQ); +} + +void efx_nic_fini_tx(struct efx_tx_queue *tx_queue) +{ + struct efx_nic *efx = tx_queue->efx; + efx_oword_t tx_desc_ptr; + + /* The queue should have been flushed */ + WARN_ON(tx_queue->flushed != FLUSH_DONE); + + /* Remove TX descriptor ring from card */ + EFX_ZERO_OWORD(tx_desc_ptr); + efx_writeo_table(efx, &tx_desc_ptr, efx->type->txd_ptr_tbl_base, + tx_queue->queue); + + /* Unpin TX descriptor ring */ + efx_fini_special_buffer(efx, &tx_queue->txd); +} + +/* Free buffers backing TX queue */ +void efx_nic_remove_tx(struct efx_tx_queue *tx_queue) +{ + efx_free_special_buffer(tx_queue->efx, &tx_queue->txd); +} + +/************************************************************************** + * + * RX path + * + **************************************************************************/ + +/* Returns a pointer to the specified descriptor in the RX descriptor queue */ +static inline efx_qword_t * +efx_rx_desc(struct efx_rx_queue *rx_queue, unsigned int index) +{ + return (((efx_qword_t *) (rx_queue->rxd.addr)) + index); +} + +/* This creates an entry in the RX descriptor queue */ +static inline void +efx_build_rx_desc(struct efx_rx_queue *rx_queue, unsigned index) +{ + struct efx_rx_buffer *rx_buf; + efx_qword_t *rxd; + + rxd = efx_rx_desc(rx_queue, index); + rx_buf = efx_rx_buffer(rx_queue, index); + EFX_POPULATE_QWORD_3(*rxd, + FSF_AZ_RX_KER_BUF_SIZE, + rx_buf->len - + rx_queue->efx->type->rx_buffer_padding, + FSF_AZ_RX_KER_BUF_REGION, 0, + FSF_AZ_RX_KER_BUF_ADDR, rx_buf->dma_addr); +} + +/* This writes to the RX_DESC_WPTR register for the specified receive + * descriptor ring. + */ +void efx_nic_notify_rx_desc(struct efx_rx_queue *rx_queue) +{ + efx_dword_t reg; + unsigned write_ptr; + + while (rx_queue->notified_count != rx_queue->added_count) { + efx_build_rx_desc(rx_queue, + rx_queue->notified_count & + EFX_RXQ_MASK); + ++rx_queue->notified_count; + } + + wmb(); + write_ptr = rx_queue->added_count & EFX_RXQ_MASK; + EFX_POPULATE_DWORD_1(reg, FRF_AZ_RX_DESC_WPTR_DWORD, write_ptr); + efx_writed_page(rx_queue->efx, ®, + FR_AZ_RX_DESC_UPD_DWORD_P0, rx_queue->queue); +} + +int efx_nic_probe_rx(struct efx_rx_queue *rx_queue) +{ + struct efx_nic *efx = rx_queue->efx; + BUILD_BUG_ON(EFX_RXQ_SIZE < 512 || EFX_RXQ_SIZE > 4096 || + EFX_RXQ_SIZE & EFX_RXQ_MASK); + return efx_alloc_special_buffer(efx, &rx_queue->rxd, + EFX_RXQ_SIZE * sizeof(efx_qword_t)); +} + +void efx_nic_init_rx(struct efx_rx_queue *rx_queue) +{ + efx_oword_t rx_desc_ptr; + struct efx_nic *efx = rx_queue->efx; + bool is_b0 = efx_nic_rev(efx) >= EFX_REV_FALCON_B0; + bool iscsi_digest_en = is_b0; + + EFX_LOG(efx, "RX queue %d ring in special buffers %d-%d\n", + rx_queue->queue, rx_queue->rxd.index, + rx_queue->rxd.index + rx_queue->rxd.entries - 1); + + rx_queue->flushed = FLUSH_NONE; + + /* Pin RX descriptor ring */ + efx_init_special_buffer(efx, &rx_queue->rxd); + + /* Push RX descriptor ring to card */ + EFX_POPULATE_OWORD_10(rx_desc_ptr, + FRF_AZ_RX_ISCSI_DDIG_EN, iscsi_digest_en, + FRF_AZ_RX_ISCSI_HDIG_EN, iscsi_digest_en, + FRF_AZ_RX_DESCQ_BUF_BASE_ID, rx_queue->rxd.index, + FRF_AZ_RX_DESCQ_EVQ_ID, + rx_queue->channel->channel, + FRF_AZ_RX_DESCQ_OWNER_ID, 0, + FRF_AZ_RX_DESCQ_LABEL, rx_queue->queue, + FRF_AZ_RX_DESCQ_SIZE, + __ffs(rx_queue->rxd.entries), + FRF_AZ_RX_DESCQ_TYPE, 0 /* kernel queue */ , + /* For >=B0 this is scatter so disable */ + FRF_AZ_RX_DESCQ_JUMBO, !is_b0, + FRF_AZ_RX_DESCQ_EN, 1); + efx_writeo_table(efx, &rx_desc_ptr, efx->type->rxd_ptr_tbl_base, + rx_queue->queue); +} + +static void efx_flush_rx_queue(struct efx_rx_queue *rx_queue) +{ + struct efx_nic *efx = rx_queue->efx; + efx_oword_t rx_flush_descq; + + rx_queue->flushed = FLUSH_PENDING; + + /* Post a flush command */ + EFX_POPULATE_OWORD_2(rx_flush_descq, + FRF_AZ_RX_FLUSH_DESCQ_CMD, 1, + FRF_AZ_RX_FLUSH_DESCQ, rx_queue->queue); + efx_writeo(efx, &rx_flush_descq, FR_AZ_RX_FLUSH_DESCQ); +} + +void efx_nic_fini_rx(struct efx_rx_queue *rx_queue) +{ + efx_oword_t rx_desc_ptr; + struct efx_nic *efx = rx_queue->efx; + + /* The queue should already have been flushed */ + WARN_ON(rx_queue->flushed != FLUSH_DONE); + + /* Remove RX descriptor ring from card */ + EFX_ZERO_OWORD(rx_desc_ptr); + efx_writeo_table(efx, &rx_desc_ptr, efx->type->rxd_ptr_tbl_base, + rx_queue->queue); + + /* Unpin RX descriptor ring */ + efx_fini_special_buffer(efx, &rx_queue->rxd); +} + +/* Free buffers backing RX queue */ +void efx_nic_remove_rx(struct efx_rx_queue *rx_queue) +{ + efx_free_special_buffer(rx_queue->efx, &rx_queue->rxd); +} + +/************************************************************************** + * + * Event queue processing + * Event queues are processed by per-channel tasklets. + * + **************************************************************************/ + +/* Update a channel's event queue's read pointer (RPTR) register + * + * This writes the EVQ_RPTR_REG register for the specified channel's + * event queue. + * + * Note that EVQ_RPTR_REG contains the index of the "last read" event, + * whereas channel->eventq_read_ptr contains the index of the "next to + * read" event. + */ +void efx_nic_eventq_read_ack(struct efx_channel *channel) +{ + efx_dword_t reg; + struct efx_nic *efx = channel->efx; + + EFX_POPULATE_DWORD_1(reg, FRF_AZ_EVQ_RPTR, channel->eventq_read_ptr); + efx_writed_table(efx, ®, efx->type->evq_rptr_tbl_base, + channel->channel); +} + +/* Use HW to insert a SW defined event */ +void efx_generate_event(struct efx_channel *channel, efx_qword_t *event) +{ + efx_oword_t drv_ev_reg; + + BUILD_BUG_ON(FRF_AZ_DRV_EV_DATA_LBN != 0 || + FRF_AZ_DRV_EV_DATA_WIDTH != 64); + drv_ev_reg.u32[0] = event->u32[0]; + drv_ev_reg.u32[1] = event->u32[1]; + drv_ev_reg.u32[2] = 0; + drv_ev_reg.u32[3] = 0; + EFX_SET_OWORD_FIELD(drv_ev_reg, FRF_AZ_DRV_EV_QID, channel->channel); + efx_writeo(channel->efx, &drv_ev_reg, FR_AZ_DRV_EV); +} + +/* Handle a transmit completion event + * + * The NIC batches TX completion events; the message we receive is of + * the form "complete all TX events up to this index". + */ +static void +efx_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) +{ + unsigned int tx_ev_desc_ptr; + unsigned int tx_ev_q_label; + struct efx_tx_queue *tx_queue; + struct efx_nic *efx = channel->efx; + + if (likely(EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_COMP))) { + /* Transmit completion */ + tx_ev_desc_ptr = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_DESC_PTR); + tx_ev_q_label = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_Q_LABEL); + tx_queue = &efx->tx_queue[tx_ev_q_label]; + channel->irq_mod_score += + (tx_ev_desc_ptr - tx_queue->read_count) & + EFX_TXQ_MASK; + efx_xmit_done(tx_queue, tx_ev_desc_ptr); + } else if (EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_WQ_FF_FULL)) { + /* Rewrite the FIFO write pointer */ + tx_ev_q_label = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_Q_LABEL); + tx_queue = &efx->tx_queue[tx_ev_q_label]; + + if (efx_dev_registered(efx)) + netif_tx_lock(efx->net_dev); + efx_notify_tx_desc(tx_queue); + if (efx_dev_registered(efx)) + netif_tx_unlock(efx->net_dev); + } else if (EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_PKT_ERR) && + EFX_WORKAROUND_10727(efx)) { + efx_schedule_reset(efx, RESET_TYPE_TX_DESC_FETCH); + } else { + EFX_ERR(efx, "channel %d unexpected TX event " + EFX_QWORD_FMT"\n", channel->channel, + EFX_QWORD_VAL(*event)); + } +} + +/* Detect errors included in the rx_evt_pkt_ok bit. */ +static void efx_handle_rx_not_ok(struct efx_rx_queue *rx_queue, + const efx_qword_t *event, + bool *rx_ev_pkt_ok, + bool *discard) +{ + struct efx_nic *efx = rx_queue->efx; + bool rx_ev_buf_owner_id_err, rx_ev_ip_hdr_chksum_err; + bool rx_ev_tcp_udp_chksum_err, rx_ev_eth_crc_err; + bool rx_ev_frm_trunc, rx_ev_drib_nib, rx_ev_tobe_disc; + bool rx_ev_other_err, rx_ev_pause_frm; + bool rx_ev_hdr_type, rx_ev_mcast_pkt; + unsigned rx_ev_pkt_type; + + rx_ev_hdr_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_HDR_TYPE); + rx_ev_mcast_pkt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_PKT); + rx_ev_tobe_disc = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_TOBE_DISC); + rx_ev_pkt_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PKT_TYPE); + rx_ev_buf_owner_id_err = EFX_QWORD_FIELD(*event, + FSF_AZ_RX_EV_BUF_OWNER_ID_ERR); + rx_ev_ip_hdr_chksum_err = EFX_QWORD_FIELD(*event, + FSF_AZ_RX_EV_IP_HDR_CHKSUM_ERR); + rx_ev_tcp_udp_chksum_err = EFX_QWORD_FIELD(*event, + FSF_AZ_RX_EV_TCP_UDP_CHKSUM_ERR); + rx_ev_eth_crc_err = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_ETH_CRC_ERR); + rx_ev_frm_trunc = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_FRM_TRUNC); + rx_ev_drib_nib = ((efx_nic_rev(efx) >= EFX_REV_FALCON_B0) ? + 0 : EFX_QWORD_FIELD(*event, FSF_AA_RX_EV_DRIB_NIB)); + rx_ev_pause_frm = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PAUSE_FRM_ERR); + + /* Every error apart from tobe_disc and pause_frm */ + rx_ev_other_err = (rx_ev_drib_nib | rx_ev_tcp_udp_chksum_err | + rx_ev_buf_owner_id_err | rx_ev_eth_crc_err | + rx_ev_frm_trunc | rx_ev_ip_hdr_chksum_err); + + /* Count errors that are not in MAC stats. Ignore expected + * checksum errors during self-test. */ + if (rx_ev_frm_trunc) + ++rx_queue->channel->n_rx_frm_trunc; + else if (rx_ev_tobe_disc) + ++rx_queue->channel->n_rx_tobe_disc; + else if (!efx->loopback_selftest) { + if (rx_ev_ip_hdr_chksum_err) + ++rx_queue->channel->n_rx_ip_hdr_chksum_err; + else if (rx_ev_tcp_udp_chksum_err) + ++rx_queue->channel->n_rx_tcp_udp_chksum_err; + } + + /* The frame must be discarded if any of these are true. */ + *discard = (rx_ev_eth_crc_err | rx_ev_frm_trunc | rx_ev_drib_nib | + rx_ev_tobe_disc | rx_ev_pause_frm); + + /* TOBE_DISC is expected on unicast mismatches; don't print out an + * error message. FRM_TRUNC indicates RXDP dropped the packet due + * to a FIFO overflow. + */ +#ifdef EFX_ENABLE_DEBUG + if (rx_ev_other_err) { + EFX_INFO_RL(efx, " RX queue %d unexpected RX event " + EFX_QWORD_FMT "%s%s%s%s%s%s%s%s\n", + rx_queue->queue, EFX_QWORD_VAL(*event), + rx_ev_buf_owner_id_err ? " [OWNER_ID_ERR]" : "", + rx_ev_ip_hdr_chksum_err ? + " [IP_HDR_CHKSUM_ERR]" : "", + rx_ev_tcp_udp_chksum_err ? + " [TCP_UDP_CHKSUM_ERR]" : "", + rx_ev_eth_crc_err ? " [ETH_CRC_ERR]" : "", + rx_ev_frm_trunc ? " [FRM_TRUNC]" : "", + rx_ev_drib_nib ? " [DRIB_NIB]" : "", + rx_ev_tobe_disc ? " [TOBE_DISC]" : "", + rx_ev_pause_frm ? " [PAUSE]" : ""); + } +#endif +} + +/* Handle receive events that are not in-order. */ +static void +efx_handle_rx_bad_index(struct efx_rx_queue *rx_queue, unsigned index) +{ + struct efx_nic *efx = rx_queue->efx; + unsigned expected, dropped; + + expected = rx_queue->removed_count & EFX_RXQ_MASK; + dropped = (index - expected) & EFX_RXQ_MASK; + EFX_INFO(efx, "dropped %d events (index=%d expected=%d)\n", + dropped, index, expected); + + efx_schedule_reset(efx, EFX_WORKAROUND_5676(efx) ? + RESET_TYPE_RX_RECOVERY : RESET_TYPE_DISABLE); +} + +/* Handle a packet received event + * + * The NIC gives a "discard" flag if it's a unicast packet with the + * wrong destination address + * Also "is multicast" and "matches multicast filter" flags can be used to + * discard non-matching multicast packets. + */ +static void +efx_handle_rx_event(struct efx_channel *channel, const efx_qword_t *event) +{ + unsigned int rx_ev_desc_ptr, rx_ev_byte_cnt; + unsigned int rx_ev_hdr_type, rx_ev_mcast_pkt; + unsigned expected_ptr; + bool rx_ev_pkt_ok, discard = false, checksummed; + struct efx_rx_queue *rx_queue; + struct efx_nic *efx = channel->efx; + + /* Basic packet information */ + rx_ev_byte_cnt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_BYTE_CNT); + rx_ev_pkt_ok = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PKT_OK); + rx_ev_hdr_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_HDR_TYPE); + WARN_ON(EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_JUMBO_CONT)); + WARN_ON(EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_SOP) != 1); + WARN_ON(EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_Q_LABEL) != + channel->channel); + + rx_queue = &efx->rx_queue[channel->channel]; + + rx_ev_desc_ptr = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_DESC_PTR); + expected_ptr = rx_queue->removed_count & EFX_RXQ_MASK; + if (unlikely(rx_ev_desc_ptr != expected_ptr)) + efx_handle_rx_bad_index(rx_queue, rx_ev_desc_ptr); + + if (likely(rx_ev_pkt_ok)) { + /* If packet is marked as OK and packet type is TCP/IP or + * UDP/IP, then we can rely on the hardware checksum. + */ + checksummed = + likely(efx->rx_checksum_enabled) && + (rx_ev_hdr_type == FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_TCP || + rx_ev_hdr_type == FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_UDP); + } else { + efx_handle_rx_not_ok(rx_queue, event, &rx_ev_pkt_ok, &discard); + checksummed = false; + } + + /* Detect multicast packets that didn't match the filter */ + rx_ev_mcast_pkt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_PKT); + if (rx_ev_mcast_pkt) { + unsigned int rx_ev_mcast_hash_match = + EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_HASH_MATCH); + + if (unlikely(!rx_ev_mcast_hash_match)) { + ++channel->n_rx_mcast_mismatch; + discard = true; + } + } + + channel->irq_mod_score += 2; + + /* Handle received packet */ + efx_rx_packet(rx_queue, rx_ev_desc_ptr, rx_ev_byte_cnt, + checksummed, discard); +} + +/* Global events are basically PHY events */ +static void +efx_handle_global_event(struct efx_channel *channel, efx_qword_t *event) +{ + struct efx_nic *efx = channel->efx; + bool handled = false; + + if (EFX_QWORD_FIELD(*event, FSF_AB_GLB_EV_G_PHY0_INTR) || + EFX_QWORD_FIELD(*event, FSF_AB_GLB_EV_XG_PHY0_INTR) || + EFX_QWORD_FIELD(*event, FSF_AB_GLB_EV_XFP_PHY0_INTR)) { + /* Ignored */ + handled = true; + } + + if ((efx_nic_rev(efx) >= EFX_REV_FALCON_B0) && + EFX_QWORD_FIELD(*event, FSF_BB_GLB_EV_XG_MGT_INTR)) { + efx->xmac_poll_required = true; + handled = true; + } + + if (efx_nic_rev(efx) <= EFX_REV_FALCON_A1 ? + EFX_QWORD_FIELD(*event, FSF_AA_GLB_EV_RX_RECOVERY) : + EFX_QWORD_FIELD(*event, FSF_BB_GLB_EV_RX_RECOVERY)) { + EFX_ERR(efx, "channel %d seen global RX_RESET " + "event. Resetting.\n", channel->channel); + + atomic_inc(&efx->rx_reset); + efx_schedule_reset(efx, EFX_WORKAROUND_6555(efx) ? + RESET_TYPE_RX_RECOVERY : RESET_TYPE_DISABLE); + handled = true; + } + + if (!handled) + EFX_ERR(efx, "channel %d unknown global event " + EFX_QWORD_FMT "\n", channel->channel, + EFX_QWORD_VAL(*event)); +} + +static void +efx_handle_driver_event(struct efx_channel *channel, efx_qword_t *event) +{ + struct efx_nic *efx = channel->efx; + unsigned int ev_sub_code; + unsigned int ev_sub_data; + + ev_sub_code = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_SUBCODE); + ev_sub_data = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_SUBDATA); + + switch (ev_sub_code) { + case FSE_AZ_TX_DESCQ_FLS_DONE_EV: + EFX_TRACE(efx, "channel %d TXQ %d flushed\n", + channel->channel, ev_sub_data); + break; + case FSE_AZ_RX_DESCQ_FLS_DONE_EV: + EFX_TRACE(efx, "channel %d RXQ %d flushed\n", + channel->channel, ev_sub_data); + break; + case FSE_AZ_EVQ_INIT_DONE_EV: + EFX_LOG(efx, "channel %d EVQ %d initialised\n", + channel->channel, ev_sub_data); + break; + case FSE_AZ_SRM_UPD_DONE_EV: + EFX_TRACE(efx, "channel %d SRAM update done\n", + channel->channel); + break; + case FSE_AZ_WAKE_UP_EV: + EFX_TRACE(efx, "channel %d RXQ %d wakeup event\n", + channel->channel, ev_sub_data); + break; + case FSE_AZ_TIMER_EV: + EFX_TRACE(efx, "channel %d RX queue %d timer expired\n", + channel->channel, ev_sub_data); + break; + case FSE_AA_RX_RECOVER_EV: + EFX_ERR(efx, "channel %d seen DRIVER RX_RESET event. " + "Resetting.\n", channel->channel); + atomic_inc(&efx->rx_reset); + efx_schedule_reset(efx, + EFX_WORKAROUND_6555(efx) ? + RESET_TYPE_RX_RECOVERY : + RESET_TYPE_DISABLE); + break; + case FSE_BZ_RX_DSC_ERROR_EV: + EFX_ERR(efx, "RX DMA Q %d reports descriptor fetch error." + " RX Q %d is disabled.\n", ev_sub_data, ev_sub_data); + efx_schedule_reset(efx, RESET_TYPE_RX_DESC_FETCH); + break; + case FSE_BZ_TX_DSC_ERROR_EV: + EFX_ERR(efx, "TX DMA Q %d reports descriptor fetch error." + " TX Q %d is disabled.\n", ev_sub_data, ev_sub_data); + efx_schedule_reset(efx, RESET_TYPE_TX_DESC_FETCH); + break; + default: + EFX_TRACE(efx, "channel %d unknown driver event code %d " + "data %04x\n", channel->channel, ev_sub_code, + ev_sub_data); + break; + } +} + +int efx_nic_process_eventq(struct efx_channel *channel, int rx_quota) +{ + unsigned int read_ptr; + efx_qword_t event, *p_event; + int ev_code; + int rx_packets = 0; + + read_ptr = channel->eventq_read_ptr; + + do { + p_event = efx_event(channel, read_ptr); + event = *p_event; + + if (!efx_event_present(&event)) + /* End of events */ + break; + + EFX_TRACE(channel->efx, "channel %d event is "EFX_QWORD_FMT"\n", + channel->channel, EFX_QWORD_VAL(event)); + + /* Clear this event by marking it all ones */ + EFX_SET_QWORD(*p_event); + + ev_code = EFX_QWORD_FIELD(event, FSF_AZ_EV_CODE); + + switch (ev_code) { + case FSE_AZ_EV_CODE_RX_EV: + efx_handle_rx_event(channel, &event); + ++rx_packets; + break; + case FSE_AZ_EV_CODE_TX_EV: + efx_handle_tx_event(channel, &event); + break; + case FSE_AZ_EV_CODE_DRV_GEN_EV: + channel->eventq_magic = EFX_QWORD_FIELD( + event, FSF_AZ_DRV_GEN_EV_MAGIC); + EFX_LOG(channel->efx, "channel %d received generated " + "event "EFX_QWORD_FMT"\n", channel->channel, + EFX_QWORD_VAL(event)); + break; + case FSE_AZ_EV_CODE_GLOBAL_EV: + efx_handle_global_event(channel, &event); + break; + case FSE_AZ_EV_CODE_DRIVER_EV: + efx_handle_driver_event(channel, &event); + break; + case FSE_CZ_EV_CODE_MCDI_EV: + efx_mcdi_process_event(channel, &event); + break; + default: + EFX_ERR(channel->efx, "channel %d unknown event type %d" + " (data " EFX_QWORD_FMT ")\n", channel->channel, + ev_code, EFX_QWORD_VAL(event)); + } + + /* Increment read pointer */ + read_ptr = (read_ptr + 1) & EFX_EVQ_MASK; + + } while (rx_packets < rx_quota); + + channel->eventq_read_ptr = read_ptr; + return rx_packets; +} + + +/* Allocate buffer table entries for event queue */ +int efx_nic_probe_eventq(struct efx_channel *channel) +{ + struct efx_nic *efx = channel->efx; + BUILD_BUG_ON(EFX_EVQ_SIZE < 512 || EFX_EVQ_SIZE > 32768 || + EFX_EVQ_SIZE & EFX_EVQ_MASK); + return efx_alloc_special_buffer(efx, &channel->eventq, + EFX_EVQ_SIZE * sizeof(efx_qword_t)); +} + +void efx_nic_init_eventq(struct efx_channel *channel) +{ + efx_oword_t reg; + struct efx_nic *efx = channel->efx; + + EFX_LOG(efx, "channel %d event queue in special buffers %d-%d\n", + channel->channel, channel->eventq.index, + channel->eventq.index + channel->eventq.entries - 1); + + if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0) { + EFX_POPULATE_OWORD_3(reg, + FRF_CZ_TIMER_Q_EN, 1, + FRF_CZ_HOST_NOTIFY_MODE, 0, + FRF_CZ_TIMER_MODE, FFE_CZ_TIMER_MODE_DIS); + efx_writeo_table(efx, ®, FR_BZ_TIMER_TBL, channel->channel); + } + + /* Pin event queue buffer */ + efx_init_special_buffer(efx, &channel->eventq); + + /* Fill event queue with all ones (i.e. empty events) */ + memset(channel->eventq.addr, 0xff, channel->eventq.len); + + /* Push event queue to card */ + EFX_POPULATE_OWORD_3(reg, + FRF_AZ_EVQ_EN, 1, + FRF_AZ_EVQ_SIZE, __ffs(channel->eventq.entries), + FRF_AZ_EVQ_BUF_BASE_ID, channel->eventq.index); + efx_writeo_table(efx, ®, efx->type->evq_ptr_tbl_base, + channel->channel); + + efx->type->push_irq_moderation(channel); +} + +void efx_nic_fini_eventq(struct efx_channel *channel) +{ + efx_oword_t reg; + struct efx_nic *efx = channel->efx; + + /* Remove event queue from card */ + EFX_ZERO_OWORD(reg); + efx_writeo_table(efx, ®, efx->type->evq_ptr_tbl_base, + channel->channel); + if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0) + efx_writeo_table(efx, ®, FR_BZ_TIMER_TBL, channel->channel); + + /* Unpin event queue */ + efx_fini_special_buffer(efx, &channel->eventq); +} + +/* Free buffers backing event queue */ +void efx_nic_remove_eventq(struct efx_channel *channel) +{ + efx_free_special_buffer(channel->efx, &channel->eventq); +} + + +/* Generates a test event on the event queue. A subsequent call to + * process_eventq() should pick up the event and place the value of + * "magic" into channel->eventq_magic; + */ +void efx_nic_generate_test_event(struct efx_channel *channel, unsigned int magic) +{ + efx_qword_t test_event; + + EFX_POPULATE_QWORD_2(test_event, FSF_AZ_EV_CODE, + FSE_AZ_EV_CODE_DRV_GEN_EV, + FSF_AZ_DRV_GEN_EV_MAGIC, magic); + efx_generate_event(channel, &test_event); +} + +/************************************************************************** + * + * Flush handling + * + **************************************************************************/ + + +static void efx_poll_flush_events(struct efx_nic *efx) +{ + struct efx_channel *channel = &efx->channel[0]; + struct efx_tx_queue *tx_queue; + struct efx_rx_queue *rx_queue; + unsigned int read_ptr = channel->eventq_read_ptr; + unsigned int end_ptr = (read_ptr - 1) & EFX_EVQ_MASK; + + do { + efx_qword_t *event = efx_event(channel, read_ptr); + int ev_code, ev_sub_code, ev_queue; + bool ev_failed; + + if (!efx_event_present(event)) + break; + + ev_code = EFX_QWORD_FIELD(*event, FSF_AZ_EV_CODE); + ev_sub_code = EFX_QWORD_FIELD(*event, + FSF_AZ_DRIVER_EV_SUBCODE); + if (ev_code == FSE_AZ_EV_CODE_DRIVER_EV && + ev_sub_code == FSE_AZ_TX_DESCQ_FLS_DONE_EV) { + ev_queue = EFX_QWORD_FIELD(*event, + FSF_AZ_DRIVER_EV_SUBDATA); + if (ev_queue < EFX_TX_QUEUE_COUNT) { + tx_queue = efx->tx_queue + ev_queue; + tx_queue->flushed = FLUSH_DONE; + } + } else if (ev_code == FSE_AZ_EV_CODE_DRIVER_EV && + ev_sub_code == FSE_AZ_RX_DESCQ_FLS_DONE_EV) { + ev_queue = EFX_QWORD_FIELD( + *event, FSF_AZ_DRIVER_EV_RX_DESCQ_ID); + ev_failed = EFX_QWORD_FIELD( + *event, FSF_AZ_DRIVER_EV_RX_FLUSH_FAIL); + if (ev_queue < efx->n_rx_queues) { + rx_queue = efx->rx_queue + ev_queue; + rx_queue->flushed = + ev_failed ? FLUSH_FAILED : FLUSH_DONE; + } + } + + /* We're about to destroy the queue anyway, so + * it's ok to throw away every non-flush event */ + EFX_SET_QWORD(*event); + + read_ptr = (read_ptr + 1) & EFX_EVQ_MASK; + } while (read_ptr != end_ptr); + + channel->eventq_read_ptr = read_ptr; +} + +/* Handle tx and rx flushes at the same time, since they run in + * parallel in the hardware and there's no reason for us to + * serialise them */ +int efx_nic_flush_queues(struct efx_nic *efx) +{ + struct efx_rx_queue *rx_queue; + struct efx_tx_queue *tx_queue; + int i, tx_pending, rx_pending; + + /* If necessary prepare the hardware for flushing */ + efx->type->prepare_flush(efx); + + /* Flush all tx queues in parallel */ + efx_for_each_tx_queue(tx_queue, efx) + efx_flush_tx_queue(tx_queue); + + /* The hardware supports four concurrent rx flushes, each of which may + * need to be retried if there is an outstanding descriptor fetch */ + for (i = 0; i < EFX_FLUSH_POLL_COUNT; ++i) { + rx_pending = tx_pending = 0; + efx_for_each_rx_queue(rx_queue, efx) { + if (rx_queue->flushed == FLUSH_PENDING) + ++rx_pending; + } + efx_for_each_rx_queue(rx_queue, efx) { + if (rx_pending == EFX_RX_FLUSH_COUNT) + break; + if (rx_queue->flushed == FLUSH_FAILED || + rx_queue->flushed == FLUSH_NONE) { + efx_flush_rx_queue(rx_queue); + ++rx_pending; + } + } + efx_for_each_tx_queue(tx_queue, efx) { + if (tx_queue->flushed != FLUSH_DONE) + ++tx_pending; + } + + if (rx_pending == 0 && tx_pending == 0) + return 0; + + msleep(EFX_FLUSH_INTERVAL); + efx_poll_flush_events(efx); + } + + /* Mark the queues as all flushed. We're going to return failure + * leading to a reset, or fake up success anyway */ + efx_for_each_tx_queue(tx_queue, efx) { + if (tx_queue->flushed != FLUSH_DONE) + EFX_ERR(efx, "tx queue %d flush command timed out\n", + tx_queue->queue); + tx_queue->flushed = FLUSH_DONE; + } + efx_for_each_rx_queue(rx_queue, efx) { + if (rx_queue->flushed != FLUSH_DONE) + EFX_ERR(efx, "rx queue %d flush command timed out\n", + rx_queue->queue); + rx_queue->flushed = FLUSH_DONE; + } + + if (EFX_WORKAROUND_7803(efx)) + return 0; + + return -ETIMEDOUT; +} + +/************************************************************************** + * + * Hardware interrupts + * The hardware interrupt handler does very little work; all the event + * queue processing is carried out by per-channel tasklets. + * + **************************************************************************/ + +/* Enable/disable/generate interrupts */ +static inline void efx_nic_interrupts(struct efx_nic *efx, + bool enabled, bool force) +{ + efx_oword_t int_en_reg_ker; + unsigned int level = 0; + + if (EFX_WORKAROUND_17213(efx) && !EFX_INT_MODE_USE_MSI(efx)) + /* Set the level always even if we're generating a test + * interrupt, because our legacy interrupt handler is safe */ + level = 0x1f; + + EFX_POPULATE_OWORD_3(int_en_reg_ker, + FRF_AZ_KER_INT_LEVE_SEL, level, + FRF_AZ_KER_INT_KER, force, + FRF_AZ_DRV_INT_EN_KER, enabled); + efx_writeo(efx, &int_en_reg_ker, FR_AZ_INT_EN_KER); +} + +void efx_nic_enable_interrupts(struct efx_nic *efx) +{ + struct efx_channel *channel; + + EFX_ZERO_OWORD(*((efx_oword_t *) efx->irq_status.addr)); + wmb(); /* Ensure interrupt vector is clear before interrupts enabled */ + + /* Enable interrupts */ + efx_nic_interrupts(efx, true, false); + + /* Force processing of all the channels to get the EVQ RPTRs up to + date */ + efx_for_each_channel(channel, efx) + efx_schedule_channel(channel); +} + +void efx_nic_disable_interrupts(struct efx_nic *efx) +{ + /* Disable interrupts */ + efx_nic_interrupts(efx, false, false); +} + +/* Generate a test interrupt + * Interrupt must already have been enabled, otherwise nasty things + * may happen. + */ +void efx_nic_generate_interrupt(struct efx_nic *efx) +{ + efx_nic_interrupts(efx, true, true); +} + +/* Process a fatal interrupt + * Disable bus mastering ASAP and schedule a reset + */ +irqreturn_t efx_nic_fatal_interrupt(struct efx_nic *efx) +{ + struct falcon_nic_data *nic_data = efx->nic_data; + efx_oword_t *int_ker = efx->irq_status.addr; + efx_oword_t fatal_intr; + int error, mem_perr; + + efx_reado(efx, &fatal_intr, FR_AZ_FATAL_INTR_KER); + error = EFX_OWORD_FIELD(fatal_intr, FRF_AZ_FATAL_INTR); + + EFX_ERR(efx, "SYSTEM ERROR " EFX_OWORD_FMT " status " + EFX_OWORD_FMT ": %s\n", EFX_OWORD_VAL(*int_ker), + EFX_OWORD_VAL(fatal_intr), + error ? "disabling bus mastering" : "no recognised error"); + if (error == 0) + goto out; + + /* If this is a memory parity error dump which blocks are offending */ + mem_perr = EFX_OWORD_FIELD(fatal_intr, FRF_AZ_MEM_PERR_INT_KER); + if (mem_perr) { + efx_oword_t reg; + efx_reado(efx, ®, FR_AZ_MEM_STAT); + EFX_ERR(efx, "SYSTEM ERROR: memory parity error " + EFX_OWORD_FMT "\n", EFX_OWORD_VAL(reg)); + } + + /* Disable both devices */ + pci_clear_master(efx->pci_dev); + if (efx_nic_is_dual_func(efx)) + pci_clear_master(nic_data->pci_dev2); + efx_nic_disable_interrupts(efx); + + /* Count errors and reset or disable the NIC accordingly */ + if (efx->int_error_count == 0 || + time_after(jiffies, efx->int_error_expire)) { + efx->int_error_count = 0; + efx->int_error_expire = + jiffies + EFX_INT_ERROR_EXPIRE * HZ; + } + if (++efx->int_error_count < EFX_MAX_INT_ERRORS) { + EFX_ERR(efx, "SYSTEM ERROR - reset scheduled\n"); + efx_schedule_reset(efx, RESET_TYPE_INT_ERROR); + } else { + EFX_ERR(efx, "SYSTEM ERROR - max number of errors seen." + "NIC will be disabled\n"); + efx_schedule_reset(efx, RESET_TYPE_DISABLE); + } +out: + return IRQ_HANDLED; +} + +/* Handle a legacy interrupt + * Acknowledges the interrupt and schedule event queue processing. + */ +static irqreturn_t efx_legacy_interrupt(int irq, void *dev_id) +{ + struct efx_nic *efx = dev_id; + efx_oword_t *int_ker = efx->irq_status.addr; + irqreturn_t result = IRQ_NONE; + struct efx_channel *channel; + efx_dword_t reg; + u32 queues; + int syserr; + + /* Read the ISR which also ACKs the interrupts */ + efx_readd(efx, ®, FR_BZ_INT_ISR0); + queues = EFX_EXTRACT_DWORD(reg, 0, 31); + + /* Check to see if we have a serious error condition */ + syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT); + if (unlikely(syserr)) + return efx_nic_fatal_interrupt(efx); + + if (queues != 0) { + if (EFX_WORKAROUND_15783(efx)) + efx->irq_zero_count = 0; + + /* Schedule processing of any interrupting queues */ + efx_for_each_channel(channel, efx) { + if (queues & 1) + efx_schedule_channel(channel); + queues >>= 1; + } + result = IRQ_HANDLED; + + } else if (EFX_WORKAROUND_15783(efx) && + efx->irq_zero_count++ == 0) { + efx_qword_t *event; + + /* Ensure we rearm all event queues */ + efx_for_each_channel(channel, efx) { + event = efx_event(channel, channel->eventq_read_ptr); + if (efx_event_present(event)) + efx_schedule_channel(channel); + } + + result = IRQ_HANDLED; + } + + if (result == IRQ_HANDLED) { + efx->last_irq_cpu = raw_smp_processor_id(); + EFX_TRACE(efx, "IRQ %d on CPU %d status " EFX_DWORD_FMT "\n", + irq, raw_smp_processor_id(), EFX_DWORD_VAL(reg)); + } + + return result; +} + +/* Handle an MSI interrupt + * + * Handle an MSI hardware interrupt. This routine schedules event + * queue processing. No interrupt acknowledgement cycle is necessary. + * Also, we never need to check that the interrupt is for us, since + * MSI interrupts cannot be shared. + */ +static irqreturn_t efx_msi_interrupt(int irq, void *dev_id) +{ + struct efx_channel *channel = dev_id; + struct efx_nic *efx = channel->efx; + efx_oword_t *int_ker = efx->irq_status.addr; + int syserr; + + efx->last_irq_cpu = raw_smp_processor_id(); + EFX_TRACE(efx, "IRQ %d on CPU %d status " EFX_OWORD_FMT "\n", + irq, raw_smp_processor_id(), EFX_OWORD_VAL(*int_ker)); + + /* Check to see if we have a serious error condition */ + syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT); + if (unlikely(syserr)) + return efx_nic_fatal_interrupt(efx); + + /* Schedule processing of the channel */ + efx_schedule_channel(channel); + + return IRQ_HANDLED; +} + + +/* Setup RSS indirection table. + * This maps from the hash value of the packet to RXQ + */ +static void efx_setup_rss_indir_table(struct efx_nic *efx) +{ + int i = 0; + unsigned long offset; + efx_dword_t dword; + + if (efx_nic_rev(efx) < EFX_REV_FALCON_B0) + return; + + for (offset = FR_BZ_RX_INDIRECTION_TBL; + offset < FR_BZ_RX_INDIRECTION_TBL + 0x800; + offset += 0x10) { + EFX_POPULATE_DWORD_1(dword, FRF_BZ_IT_QUEUE, + i % efx->n_rx_queues); + efx_writed(efx, &dword, offset); + i++; + } +} + +/* Hook interrupt handler(s) + * Try MSI and then legacy interrupts. + */ +int efx_nic_init_interrupt(struct efx_nic *efx) +{ + struct efx_channel *channel; + int rc; + + if (!EFX_INT_MODE_USE_MSI(efx)) { + irq_handler_t handler; + if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) + handler = efx_legacy_interrupt; + else + handler = falcon_legacy_interrupt_a1; + + rc = request_irq(efx->legacy_irq, handler, IRQF_SHARED, + efx->name, efx); + if (rc) { + EFX_ERR(efx, "failed to hook legacy IRQ %d\n", + efx->pci_dev->irq); + goto fail1; + } + return 0; + } + + /* Hook MSI or MSI-X interrupt */ + efx_for_each_channel(channel, efx) { + rc = request_irq(channel->irq, efx_msi_interrupt, + IRQF_PROBE_SHARED, /* Not shared */ + channel->name, channel); + if (rc) { + EFX_ERR(efx, "failed to hook IRQ %d\n", channel->irq); + goto fail2; + } + } + + return 0; + + fail2: + efx_for_each_channel(channel, efx) + free_irq(channel->irq, channel); + fail1: + return rc; +} + +void efx_nic_fini_interrupt(struct efx_nic *efx) +{ + struct efx_channel *channel; + efx_oword_t reg; + + /* Disable MSI/MSI-X interrupts */ + efx_for_each_channel(channel, efx) { + if (channel->irq) + free_irq(channel->irq, channel); + } + + /* ACK legacy interrupt */ + if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) + efx_reado(efx, ®, FR_BZ_INT_ISR0); + else + falcon_irq_ack_a1(efx); + + /* Disable legacy interrupt */ + if (efx->legacy_irq) + free_irq(efx->legacy_irq, efx); +} + +u32 efx_nic_fpga_ver(struct efx_nic *efx) +{ + efx_oword_t altera_build; + efx_reado(efx, &altera_build, FR_AZ_ALTERA_BUILD); + return EFX_OWORD_FIELD(altera_build, FRF_AZ_ALTERA_BUILD_VER); +} + +void efx_nic_init_common(struct efx_nic *efx) +{ + efx_oword_t temp; + + /* Set positions of descriptor caches in SRAM. */ + EFX_POPULATE_OWORD_1(temp, FRF_AZ_SRM_TX_DC_BASE_ADR, + efx->type->tx_dc_base / 8); + efx_writeo(efx, &temp, FR_AZ_SRM_TX_DC_CFG); + EFX_POPULATE_OWORD_1(temp, FRF_AZ_SRM_RX_DC_BASE_ADR, + efx->type->rx_dc_base / 8); + efx_writeo(efx, &temp, FR_AZ_SRM_RX_DC_CFG); + + /* Set TX descriptor cache size. */ + BUILD_BUG_ON(TX_DC_ENTRIES != (8 << TX_DC_ENTRIES_ORDER)); + EFX_POPULATE_OWORD_1(temp, FRF_AZ_TX_DC_SIZE, TX_DC_ENTRIES_ORDER); + efx_writeo(efx, &temp, FR_AZ_TX_DC_CFG); + + /* Set RX descriptor cache size. Set low watermark to size-8, as + * this allows most efficient prefetching. + */ + BUILD_BUG_ON(RX_DC_ENTRIES != (8 << RX_DC_ENTRIES_ORDER)); + EFX_POPULATE_OWORD_1(temp, FRF_AZ_RX_DC_SIZE, RX_DC_ENTRIES_ORDER); + efx_writeo(efx, &temp, FR_AZ_RX_DC_CFG); + EFX_POPULATE_OWORD_1(temp, FRF_AZ_RX_DC_PF_LWM, RX_DC_ENTRIES - 8); + efx_writeo(efx, &temp, FR_AZ_RX_DC_PF_WM); + + /* Program INT_KER address */ + EFX_POPULATE_OWORD_2(temp, + FRF_AZ_NORM_INT_VEC_DIS_KER, + EFX_INT_MODE_USE_MSI(efx), + FRF_AZ_INT_ADR_KER, efx->irq_status.dma_addr); + efx_writeo(efx, &temp, FR_AZ_INT_ADR_KER); + + /* Enable all the genuinely fatal interrupts. (They are still + * masked by the overall interrupt mask, controlled by + * falcon_interrupts()). + * + * Note: All other fatal interrupts are enabled + */ + EFX_POPULATE_OWORD_3(temp, + FRF_AZ_ILL_ADR_INT_KER_EN, 1, + FRF_AZ_RBUF_OWN_INT_KER_EN, 1, + FRF_AZ_TBUF_OWN_INT_KER_EN, 1); + EFX_INVERT_OWORD(temp); + efx_writeo(efx, &temp, FR_AZ_FATAL_INTR_KER); + + efx_setup_rss_indir_table(efx); + + /* Disable the ugly timer-based TX DMA backoff and allow TX DMA to be + * controlled by the RX FIFO fill level. Set arbitration to one pkt/Q. + */ + efx_reado(efx, &temp, FR_AZ_TX_RESERVED); + EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_RX_SPACER, 0xfe); + EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_RX_SPACER_EN, 1); + EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_ONE_PKT_PER_Q, 1); + EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_PUSH_EN, 0); + EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_DIS_NON_IP_EV, 1); + /* Enable SW_EV to inherit in char driver - assume harmless here */ + EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_SOFT_EVT_EN, 1); + /* Prefetch threshold 2 => fetch when descriptor cache half empty */ + EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_PREF_THRESHOLD, 2); + /* Squash TX of packets of 16 bytes or less */ + if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) + EFX_SET_OWORD_FIELD(temp, FRF_BZ_TX_FLUSH_MIN_LEN_EN, 1); + efx_writeo(efx, &temp, FR_AZ_TX_RESERVED); +} diff --git a/drivers/net/sfc/nic.h b/drivers/net/sfc/nic.h new file mode 100644 index 000000000000..9351c0331a47 --- /dev/null +++ b/drivers/net/sfc/nic.h @@ -0,0 +1,261 @@ +/**************************************************************************** + * Driver for Solarflare Solarstorm network controllers and boards + * Copyright 2005-2006 Fen Systems Ltd. + * Copyright 2006-2009 Solarflare Communications Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +#ifndef EFX_NIC_H +#define EFX_NIC_H + +#include <linux/i2c-algo-bit.h> +#include "net_driver.h" +#include "efx.h" +#include "mcdi.h" + +/* + * Falcon hardware control + */ + +enum { + EFX_REV_FALCON_A0 = 0, + EFX_REV_FALCON_A1 = 1, + EFX_REV_FALCON_B0 = 2, + EFX_REV_SIENA_A0 = 3, +}; + +static inline int efx_nic_rev(struct efx_nic *efx) +{ + return efx->type->revision; +} + +extern u32 efx_nic_fpga_ver(struct efx_nic *efx); + +static inline bool efx_nic_has_mc(struct efx_nic *efx) +{ + return efx_nic_rev(efx) >= EFX_REV_SIENA_A0; +} +/* NIC has two interlinked PCI functions for the same port. */ +static inline bool efx_nic_is_dual_func(struct efx_nic *efx) +{ + return efx_nic_rev(efx) < EFX_REV_FALCON_B0; +} + +enum { + PHY_TYPE_NONE = 0, + PHY_TYPE_TXC43128 = 1, + PHY_TYPE_88E1111 = 2, + PHY_TYPE_SFX7101 = 3, + PHY_TYPE_QT2022C2 = 4, + PHY_TYPE_PM8358 = 6, + PHY_TYPE_SFT9001A = 8, + PHY_TYPE_QT2025C = 9, + PHY_TYPE_SFT9001B = 10, +}; + +#define FALCON_XMAC_LOOPBACKS \ + ((1 << LOOPBACK_XGMII) | \ + (1 << LOOPBACK_XGXS) | \ + (1 << LOOPBACK_XAUI)) + +#define FALCON_GMAC_LOOPBACKS \ + (1 << LOOPBACK_GMAC) + +/** + * struct falcon_board_type - board operations and type information + * @id: Board type id, as found in NVRAM + * @ref_model: Model number of Solarflare reference design + * @gen_type: Generic board type description + * @init: Allocate resources and initialise peripheral hardware + * @init_phy: Do board-specific PHY initialisation + * @fini: Shut down hardware and free resources + * @set_id_led: Set state of identifying LED or revert to automatic function + * @monitor: Board-specific health check function + */ +struct falcon_board_type { + u8 id; + const char *ref_model; + const char *gen_type; + int (*init) (struct efx_nic *nic); + void (*init_phy) (struct efx_nic *efx); + void (*fini) (struct efx_nic *nic); + void (*set_id_led) (struct efx_nic *efx, enum efx_led_mode mode); + int (*monitor) (struct efx_nic *nic); +}; + +/** + * struct falcon_board - board information + * @type: Type of board + * @major: Major rev. ('A', 'B' ...) + * @minor: Minor rev. (0, 1, ...) + * @i2c_adap: I2C adapter for on-board peripherals + * @i2c_data: Data for bit-banging algorithm + * @hwmon_client: I2C client for hardware monitor + * @ioexp_client: I2C client for power/port control + */ +struct falcon_board { + const struct falcon_board_type *type; + int major; + int minor; + struct i2c_adapter i2c_adap; + struct i2c_algo_bit_data i2c_data; + struct i2c_client *hwmon_client, *ioexp_client; +}; + +/** + * struct falcon_nic_data - Falcon NIC state + * @pci_dev2: Secondary function of Falcon A + * @board: Board state and functions + * @stats_disable_count: Nest count for disabling statistics fetches + * @stats_pending: Is there a pending DMA of MAC statistics. + * @stats_timer: A timer for regularly fetching MAC statistics. + * @stats_dma_done: Pointer to the flag which indicates DMA completion. + */ +struct falcon_nic_data { + struct pci_dev *pci_dev2; + struct falcon_board board; + unsigned int stats_disable_count; + bool stats_pending; + struct timer_list stats_timer; + u32 *stats_dma_done; +}; + +static inline struct falcon_board *falcon_board(struct efx_nic *efx) +{ + struct falcon_nic_data *data = efx->nic_data; + return &data->board; +} + +/** + * struct siena_nic_data - Siena NIC state + * @fw_version: Management controller firmware version + * @fw_build: Firmware build number + * @mcdi: Management-Controller-to-Driver Interface + * @wol_filter_id: Wake-on-LAN packet filter id + */ +struct siena_nic_data { + u64 fw_version; + u32 fw_build; + struct efx_mcdi_iface mcdi; + int wol_filter_id; +}; + +extern void siena_print_fwver(struct efx_nic *efx, char *buf, size_t len); + +extern struct efx_nic_type falcon_a1_nic_type; +extern struct efx_nic_type falcon_b0_nic_type; +extern struct efx_nic_type siena_a0_nic_type; + +/************************************************************************** + * + * Externs + * + ************************************************************************** + */ + +extern void falcon_probe_board(struct efx_nic *efx, u16 revision_info); + +/* TX data path */ +extern int efx_nic_probe_tx(struct efx_tx_queue *tx_queue); +extern void efx_nic_init_tx(struct efx_tx_queue *tx_queue); +extern void efx_nic_fini_tx(struct efx_tx_queue *tx_queue); +extern void efx_nic_remove_tx(struct efx_tx_queue *tx_queue); +extern void efx_nic_push_buffers(struct efx_tx_queue *tx_queue); + +/* RX data path */ +extern int efx_nic_probe_rx(struct efx_rx_queue *rx_queue); +extern void efx_nic_init_rx(struct efx_rx_queue *rx_queue); +extern void efx_nic_fini_rx(struct efx_rx_queue *rx_queue); +extern void efx_nic_remove_rx(struct efx_rx_queue *rx_queue); +extern void efx_nic_notify_rx_desc(struct efx_rx_queue *rx_queue); + +/* Event data path */ +extern int efx_nic_probe_eventq(struct efx_channel *channel); +extern void efx_nic_init_eventq(struct efx_channel *channel); +extern void efx_nic_fini_eventq(struct efx_channel *channel); +extern void efx_nic_remove_eventq(struct efx_channel *channel); +extern int efx_nic_process_eventq(struct efx_channel *channel, int rx_quota); +extern void efx_nic_eventq_read_ack(struct efx_channel *channel); + +/* MAC/PHY */ +extern void falcon_drain_tx_fifo(struct efx_nic *efx); +extern void falcon_reconfigure_mac_wrapper(struct efx_nic *efx); +extern int efx_nic_rx_xoff_thresh, efx_nic_rx_xon_thresh; + +/* Interrupts and test events */ +extern int efx_nic_init_interrupt(struct efx_nic *efx); +extern void efx_nic_enable_interrupts(struct efx_nic *efx); +extern void efx_nic_generate_test_event(struct efx_channel *channel, + unsigned int magic); +extern void efx_nic_generate_interrupt(struct efx_nic *efx); +extern void efx_nic_disable_interrupts(struct efx_nic *efx); +extern void efx_nic_fini_interrupt(struct efx_nic *efx); +extern irqreturn_t efx_nic_fatal_interrupt(struct efx_nic *efx); +extern irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id); +extern void falcon_irq_ack_a1(struct efx_nic *efx); + +#define EFX_IRQ_MOD_RESOLUTION 5 + +/* Global Resources */ +extern int efx_nic_flush_queues(struct efx_nic *efx); +extern void falcon_start_nic_stats(struct efx_nic *efx); +extern void falcon_stop_nic_stats(struct efx_nic *efx); +extern int falcon_reset_xaui(struct efx_nic *efx); +extern void efx_nic_init_common(struct efx_nic *efx); + +int efx_nic_alloc_buffer(struct efx_nic *efx, struct efx_buffer *buffer, + unsigned int len); +void efx_nic_free_buffer(struct efx_nic *efx, struct efx_buffer *buffer); + +/* Tests */ +struct efx_nic_register_test { + unsigned address; + efx_oword_t mask; +}; +extern int efx_nic_test_registers(struct efx_nic *efx, + const struct efx_nic_register_test *regs, + size_t n_regs); + +/************************************************************************** + * + * Falcon MAC stats + * + ************************************************************************** + */ + +#define FALCON_STAT_OFFSET(falcon_stat) EFX_VAL(falcon_stat, offset) +#define FALCON_STAT_WIDTH(falcon_stat) EFX_VAL(falcon_stat, WIDTH) + +/* Retrieve statistic from statistics block */ +#define FALCON_STAT(efx, falcon_stat, efx_stat) do { \ + if (FALCON_STAT_WIDTH(falcon_stat) == 16) \ + (efx)->mac_stats.efx_stat += le16_to_cpu( \ + *((__force __le16 *) \ + (efx->stats_buffer.addr + \ + FALCON_STAT_OFFSET(falcon_stat)))); \ + else if (FALCON_STAT_WIDTH(falcon_stat) == 32) \ + (efx)->mac_stats.efx_stat += le32_to_cpu( \ + *((__force __le32 *) \ + (efx->stats_buffer.addr + \ + FALCON_STAT_OFFSET(falcon_stat)))); \ + else \ + (efx)->mac_stats.efx_stat += le64_to_cpu( \ + *((__force __le64 *) \ + (efx->stats_buffer.addr + \ + FALCON_STAT_OFFSET(falcon_stat)))); \ + } while (0) + +#define FALCON_MAC_STATS_SIZE 0x100 + +#define MAC_DATA_LBN 0 +#define MAC_DATA_WIDTH 32 + +extern void efx_nic_generate_event(struct efx_channel *channel, + efx_qword_t *event); + +extern void falcon_poll_xmac(struct efx_nic *efx); + +#endif /* EFX_NIC_H */ diff --git a/drivers/net/sfc/phy.h b/drivers/net/sfc/phy.h index 2ad1cec2c720..5bc26137257b 100644 --- a/drivers/net/sfc/phy.h +++ b/drivers/net/sfc/phy.h @@ -1,6 +1,6 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards - * Copyright 2007-2008 Solarflare Communications Inc. + * Copyright 2007-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -41,4 +41,21 @@ extern struct efx_phy_operations falcon_qt202x_phy_ops; extern void falcon_qt202x_set_led(struct efx_nic *p, int led, int state); +/**************************************************************************** + * Siena managed PHYs + */ +extern struct efx_phy_operations efx_mcdi_phy_ops; + +extern int efx_mcdi_mdio_read(struct efx_nic *efx, unsigned int bus, + unsigned int prtad, unsigned int devad, + u16 addr, u16 *value_out, u32 *status_out); +extern int efx_mcdi_mdio_write(struct efx_nic *efx, unsigned int bus, + unsigned int prtad, unsigned int devad, + u16 addr, u16 value, u32 *status_out); +extern void efx_mcdi_phy_decode_link(struct efx_nic *efx, + struct efx_link_state *link_state, + u32 speed, u32 flags, u32 fcntl); +extern int efx_mcdi_phy_reconfigure(struct efx_nic *efx); +extern void efx_mcdi_phy_check_fcntl(struct efx_nic *efx, u32 lpa); + #endif diff --git a/drivers/net/sfc/qt202x_phy.c b/drivers/net/sfc/qt202x_phy.c index 8208ac0ffad7..3800fc791b2f 100644 --- a/drivers/net/sfc/qt202x_phy.c +++ b/drivers/net/sfc/qt202x_phy.c @@ -1,6 +1,6 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards - * Copyright 2006-2008 Solarflare Communications Inc. + * Copyright 2006-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -15,7 +15,7 @@ #include "efx.h" #include "mdio_10g.h" #include "phy.h" -#include "falcon.h" +#include "nic.h" #define QT202X_REQUIRED_DEVS (MDIO_DEVS_PCS | \ MDIO_DEVS_PMAPMD | \ @@ -23,7 +23,7 @@ #define QT202X_LOOPBACKS ((1 << LOOPBACK_PCS) | \ (1 << LOOPBACK_PMAPMD) | \ - (1 << LOOPBACK_NETWORK)) + (1 << LOOPBACK_PHYXS_WS)) /****************************************************************************/ /* Quake-specific MDIO registers */ @@ -126,7 +126,7 @@ static int qt202x_reset_phy(struct efx_nic *efx) if (rc < 0) goto fail; - falcon_board(efx)->init_phy(efx); + falcon_board(efx)->type->init_phy(efx); return rc; @@ -135,42 +135,38 @@ static int qt202x_reset_phy(struct efx_nic *efx) return rc; } +static int qt202x_phy_probe(struct efx_nic *efx) +{ + efx->mdio.mmds = QT202X_REQUIRED_DEVS; + efx->mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22; + efx->loopback_modes = QT202X_LOOPBACKS | FALCON_XMAC_LOOPBACKS; + return 0; +} + static int qt202x_phy_init(struct efx_nic *efx) { struct qt202x_phy_data *phy_data; - u32 devid = efx_mdio_read_id(efx, MDIO_MMD_PHYXS); + u32 devid; int rc; + rc = qt202x_reset_phy(efx); + if (rc) { + EFX_ERR(efx, "PHY init failed\n"); + return rc; + } + phy_data = kzalloc(sizeof(struct qt202x_phy_data), GFP_KERNEL); if (!phy_data) return -ENOMEM; efx->phy_data = phy_data; + devid = efx_mdio_read_id(efx, MDIO_MMD_PHYXS); EFX_INFO(efx, "PHY ID reg %x (OUI %06x model %02x revision %x)\n", devid, efx_mdio_id_oui(devid), efx_mdio_id_model(devid), efx_mdio_id_rev(devid)); phy_data->phy_mode = efx->phy_mode; - - rc = qt202x_reset_phy(efx); - - EFX_INFO(efx, "PHY init %s.\n", - rc ? "failed" : "successful"); - if (rc < 0) - goto fail; - return 0; - - fail: - kfree(efx->phy_data); - efx->phy_data = NULL; - return rc; -} - -static void qt202x_phy_clear_interrupt(struct efx_nic *efx) -{ - /* Read to clear link status alarm */ - efx_mdio_read(efx, MDIO_MMD_PMAPMD, MDIO_PMA_LASI_STAT); } static int qt202x_link_ok(struct efx_nic *efx) @@ -178,18 +174,21 @@ static int qt202x_link_ok(struct efx_nic *efx) return efx_mdio_links_ok(efx, QT202X_REQUIRED_DEVS); } -static void qt202x_phy_poll(struct efx_nic *efx) +static bool qt202x_phy_poll(struct efx_nic *efx) { - int link_up = qt202x_link_ok(efx); - /* Simulate a PHY event if link state has changed */ - if (link_up != efx->link_state.up) - falcon_sim_phy_event(efx); + bool was_up = efx->link_state.up; + + efx->link_state.up = qt202x_link_ok(efx); + efx->link_state.speed = 10000; + efx->link_state.fd = true; + efx->link_state.fc = efx->wanted_fc; + + return efx->link_state.up != was_up; } -static void qt202x_phy_reconfigure(struct efx_nic *efx) +static int qt202x_phy_reconfigure(struct efx_nic *efx) { struct qt202x_phy_data *phy_data = efx->phy_data; - struct efx_link_state *link_state = &efx->link_state; if (efx->phy_type == PHY_TYPE_QT2025C) { /* There are several different register bits which can @@ -216,10 +215,8 @@ static void qt202x_phy_reconfigure(struct efx_nic *efx) efx_mdio_phy_reconfigure(efx); phy_data->phy_mode = efx->phy_mode; - link_state->up = qt202x_link_ok(efx); - link_state->speed = 10000; - link_state->fd = true; - link_state->fc = efx->wanted_fc; + + return 0; } static void qt202x_phy_get_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd) @@ -235,14 +232,11 @@ static void qt202x_phy_fini(struct efx_nic *efx) } struct efx_phy_operations falcon_qt202x_phy_ops = { - .macs = EFX_XMAC, + .probe = qt202x_phy_probe, .init = qt202x_phy_init, .reconfigure = qt202x_phy_reconfigure, .poll = qt202x_phy_poll, .fini = qt202x_phy_fini, - .clear_interrupt = qt202x_phy_clear_interrupt, .get_settings = qt202x_phy_get_settings, .set_settings = efx_mdio_set_settings, - .mmds = QT202X_REQUIRED_DEVS, - .loopbacks = QT202X_LOOPBACKS, }; diff --git a/drivers/net/sfc/regs.h b/drivers/net/sfc/regs.h index f336d83d5fa0..89d606fe9248 100644 --- a/drivers/net/sfc/regs.h +++ b/drivers/net/sfc/regs.h @@ -3106,18 +3106,6 @@ #define FALCON_STATS_NOT_DONE 0x00000000 #define FALCON_STATS_DONE 0xffffffff -/* Interrupt status register bits */ -#define FATAL_INT_LBN 64 -#define FATAL_INT_WIDTH 1 -#define INT_EVQS_LBN 40 -#define INT_EVQS_WIDTH 4 -#define INT_FLAG_LBN 32 -#define INT_FLAG_WIDTH 1 -#define EVQ_FIFO_HF_LBN 1 -#define EVQ_FIFO_HF_WIDTH 1 -#define EVQ_FIFO_AF_LBN 0 -#define EVQ_FIFO_AF_WIDTH 1 - /************************************************************************** * * Falcon non-volatile configuration diff --git a/drivers/net/sfc/rx.c b/drivers/net/sfc/rx.c index accf055ff89d..a97c923b560c 100644 --- a/drivers/net/sfc/rx.c +++ b/drivers/net/sfc/rx.c @@ -1,7 +1,7 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards * Copyright 2005-2006 Fen Systems Ltd. - * Copyright 2005-2008 Solarflare Communications Inc. + * Copyright 2005-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -17,7 +17,7 @@ #include <net/checksum.h> #include "net_driver.h" #include "efx.h" -#include "falcon.h" +#include "nic.h" #include "selftest.h" #include "workarounds.h" @@ -341,7 +341,7 @@ static int __efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue, out: /* Send write pointer to card. */ - falcon_notify_rx_desc(rx_queue); + efx_nic_notify_rx_desc(rx_queue); /* If the fast fill is running inside from the refill tasklet, then * for SMP systems it may be running on a different CPU to @@ -640,7 +640,7 @@ int efx_probe_rx_queue(struct efx_rx_queue *rx_queue) if (!rx_queue->buffer) return -ENOMEM; - rc = falcon_probe_rx(rx_queue); + rc = efx_nic_probe_rx(rx_queue); if (rc) { kfree(rx_queue->buffer); rx_queue->buffer = NULL; @@ -671,7 +671,7 @@ void efx_init_rx_queue(struct efx_rx_queue *rx_queue) rx_queue->fast_fill_limit = limit; /* Set up RX descriptor ring */ - falcon_init_rx(rx_queue); + efx_nic_init_rx(rx_queue); } void efx_fini_rx_queue(struct efx_rx_queue *rx_queue) @@ -681,7 +681,7 @@ void efx_fini_rx_queue(struct efx_rx_queue *rx_queue) EFX_LOG(rx_queue->efx, "shutting down RX queue %d\n", rx_queue->queue); - falcon_fini_rx(rx_queue); + efx_nic_fini_rx(rx_queue); /* Release RX buffers NB start at index 0 not current HW ptr */ if (rx_queue->buffer) { @@ -706,7 +706,7 @@ void efx_remove_rx_queue(struct efx_rx_queue *rx_queue) { EFX_LOG(rx_queue->efx, "destroying RX queue %d\n", rx_queue->queue); - falcon_remove_rx(rx_queue); + efx_nic_remove_rx(rx_queue); kfree(rx_queue->buffer); rx_queue->buffer = NULL; diff --git a/drivers/net/sfc/selftest.c b/drivers/net/sfc/selftest.c index 63ff295334e4..14949bb303a0 100644 --- a/drivers/net/sfc/selftest.c +++ b/drivers/net/sfc/selftest.c @@ -1,7 +1,7 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards * Copyright 2005-2006 Fen Systems Ltd. - * Copyright 2006-2008 Solarflare Communications Inc. + * Copyright 2006-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -21,7 +21,7 @@ #include <asm/io.h> #include "net_driver.h" #include "efx.h" -#include "falcon.h" +#include "nic.h" #include "selftest.h" #include "workarounds.h" #include "spi.h" @@ -55,6 +55,7 @@ static const char *payload_msg = * @flush: Drop all packets in efx_loopback_rx_packet * @packet_count: Number of packets being used in this test * @skbs: An array of skbs transmitted + * @offload_csum: Checksums are being offloaded * @rx_good: RX good packet count * @rx_bad: RX bad packet count * @payload: Payload used in tests @@ -63,10 +64,7 @@ struct efx_loopback_state { bool flush; int packet_count; struct sk_buff **skbs; - - /* Checksums are being offloaded */ bool offload_csum; - atomic_t rx_good; atomic_t rx_bad; struct efx_loopback_payload payload; @@ -102,7 +100,7 @@ static int efx_test_mdio(struct efx_nic *efx, struct efx_self_tests *tests) } if (EFX_IS10G(efx)) { - rc = efx_mdio_check_mmds(efx, efx->phy_op->mmds, 0); + rc = efx_mdio_check_mmds(efx, efx->mdio.mmds, 0); if (rc) goto out; } @@ -115,23 +113,26 @@ out: static int efx_test_nvram(struct efx_nic *efx, struct efx_self_tests *tests) { - int rc; + int rc = 0; + + if (efx->type->test_nvram) { + rc = efx->type->test_nvram(efx); + tests->nvram = rc ? -1 : 1; + } - rc = falcon_read_nvram(efx, NULL); - tests->nvram = rc ? -1 : 1; return rc; } static int efx_test_chip(struct efx_nic *efx, struct efx_self_tests *tests) { - int rc; + int rc = 0; - /* Not supported on A-series silicon */ - if (falcon_rev(efx) < FALCON_REV_B0) - return 0; + /* Test register access */ + if (efx->type->test_registers) { + rc = efx->type->test_registers(efx); + tests->registers = rc ? -1 : 1; + } - rc = falcon_test_registers(efx); - tests->registers = rc ? -1 : 1; return rc; } @@ -163,7 +164,7 @@ static int efx_test_interrupts(struct efx_nic *efx, goto success; } - falcon_generate_interrupt(efx); + efx_nic_generate_interrupt(efx); /* Wait for arrival of test interrupt. */ EFX_LOG(efx, "waiting for test interrupt\n"); @@ -201,7 +202,7 @@ static int efx_test_eventq_irq(struct efx_channel *channel, channel->eventq_magic = 0; smp_wmb(); - falcon_generate_test_event(channel, magic); + efx_nic_generate_test_event(channel, magic); /* Wait for arrival of interrupt */ count = 0; @@ -252,9 +253,6 @@ static int efx_test_phy(struct efx_nic *efx, struct efx_self_tests *tests, if (!efx->phy_op->run_tests) return 0; - EFX_BUG_ON_PARANOID(efx->phy_op->num_tests == 0 || - efx->phy_op->num_tests > EFX_MAX_PHY_TESTS); - mutex_lock(&efx->mac_lock); rc = efx->phy_op->run_tests(efx, tests->phy, flags); mutex_unlock(&efx->mac_lock); @@ -437,7 +435,6 @@ static int efx_begin_loopback(struct efx_tx_queue *tx_queue) kfree_skb(skb); return -EPIPE; } - efx->net_dev->trans_start = jiffies; } return 0; @@ -566,14 +563,49 @@ efx_test_loopback(struct efx_tx_queue *tx_queue, return 0; } +/* Wait for link up. On Falcon, we would prefer to rely on efx_monitor, but + * any contention on the mac lock (via e.g. efx_mac_mcast_work) causes it + * to delay and retry. Therefore, it's safer to just poll directly. Wait + * for link up and any faults to dissipate. */ +static int efx_wait_for_link(struct efx_nic *efx) +{ + struct efx_link_state *link_state = &efx->link_state; + int count; + bool link_up; + + for (count = 0; count < 40; count++) { + schedule_timeout_uninterruptible(HZ / 10); + + if (efx->type->monitor != NULL) { + mutex_lock(&efx->mac_lock); + efx->type->monitor(efx); + mutex_unlock(&efx->mac_lock); + } else { + struct efx_channel *channel = &efx->channel[0]; + if (channel->work_pending) + efx_process_channel_now(channel); + } + + mutex_lock(&efx->mac_lock); + link_up = link_state->up; + if (link_up) + link_up = !efx->mac_op->check_fault(efx); + mutex_unlock(&efx->mac_lock); + + if (link_up) + return 0; + } + + return -ETIMEDOUT; +} + static int efx_test_loopbacks(struct efx_nic *efx, struct efx_self_tests *tests, unsigned int loopback_modes) { enum efx_loopback_mode mode; struct efx_loopback_state *state; struct efx_tx_queue *tx_queue; - bool link_up; - int count, rc = 0; + int rc = 0; /* Set the port loopback_selftest member. From this point on * all received packets will be dropped. Mark the state as @@ -592,46 +624,23 @@ static int efx_test_loopbacks(struct efx_nic *efx, struct efx_self_tests *tests, /* Move the port into the specified loopback mode. */ state->flush = true; + mutex_lock(&efx->mac_lock); efx->loopback_mode = mode; - efx_reconfigure_port(efx); - - /* Wait for the PHY to signal the link is up. Interrupts - * are enabled for PHY's using LASI, otherwise we poll() - * quickly */ - count = 0; - do { - struct efx_channel *channel = &efx->channel[0]; + rc = __efx_reconfigure_port(efx); + mutex_unlock(&efx->mac_lock); + if (rc) { + EFX_ERR(efx, "unable to move into %s loopback\n", + LOOPBACK_MODE(efx)); + goto out; + } - efx->phy_op->poll(efx); - schedule_timeout_uninterruptible(HZ / 10); - if (channel->work_pending) - efx_process_channel_now(channel); - /* Wait for PHY events to be processed */ - flush_workqueue(efx->workqueue); - rmb(); - - /* We need both the phy and xaui links to be ok. - * rather than relying on the falcon_xmac irq/poll - * regime, just poll xaui directly */ - link_up = efx->link_state.up; - if (link_up && EFX_IS10G(efx) && - !falcon_xaui_link_ok(efx)) - link_up = false; - - } while ((++count < 20) && !link_up); - - /* The link should now be up. If it isn't, there is no point - * in attempting a loopback test */ - if (!link_up) { + rc = efx_wait_for_link(efx); + if (rc) { EFX_ERR(efx, "loopback %s never came up\n", LOOPBACK_MODE(efx)); - rc = -EIO; goto out; } - EFX_LOG(efx, "link came up in %s loopback in %d iterations\n", - LOOPBACK_MODE(efx), count); - /* Test every TX queue */ efx_for_each_tx_queue(tx_queue, efx) { state->offload_csum = (tx_queue->queue == @@ -665,7 +674,6 @@ int efx_selftest(struct efx_nic *efx, struct efx_self_tests *tests, enum efx_loopback_mode loopback_mode = efx->loopback_mode; int phy_mode = efx->phy_mode; enum reset_type reset_method = RESET_TYPE_INVISIBLE; - struct ethtool_cmd ecmd; struct efx_channel *channel; int rc_test = 0, rc_reset = 0, rc; @@ -718,21 +726,21 @@ int efx_selftest(struct efx_nic *efx, struct efx_self_tests *tests, mutex_unlock(&efx->mac_lock); /* free up all consumers of SRAM (including all the queues) */ - efx_reset_down(efx, reset_method, &ecmd); + efx_reset_down(efx, reset_method); rc = efx_test_chip(efx, tests); if (rc && !rc_test) rc_test = rc; /* reset the chip to recover from the register test */ - rc_reset = falcon_reset_hw(efx, reset_method); + rc_reset = efx->type->reset(efx, reset_method); /* Ensure that the phy is powered and out of loopback * for the bist and loopback tests */ efx->phy_mode &= ~PHY_MODE_LOW_POWER; efx->loopback_mode = LOOPBACK_NONE; - rc = efx_reset_up(efx, reset_method, &ecmd, rc_reset == 0); + rc = efx_reset_up(efx, reset_method, rc_reset == 0); if (rc && !rc_reset) rc_reset = rc; @@ -751,10 +759,12 @@ int efx_selftest(struct efx_nic *efx, struct efx_self_tests *tests, rc_test = rc; /* restore the PHY to the previous state */ - efx->loopback_mode = loopback_mode; + mutex_lock(&efx->mac_lock); efx->phy_mode = phy_mode; efx->port_inhibited = false; - efx_ethtool_set_settings(efx->net_dev, &ecmd); + efx->loopback_mode = loopback_mode; + __efx_reconfigure_port(efx); + mutex_unlock(&efx->mac_lock); return rc_test; } diff --git a/drivers/net/sfc/siena.c b/drivers/net/sfc/siena.c new file mode 100644 index 000000000000..de07a4f031b2 --- /dev/null +++ b/drivers/net/sfc/siena.c @@ -0,0 +1,604 @@ +/**************************************************************************** + * Driver for Solarflare Solarstorm network controllers and boards + * Copyright 2005-2006 Fen Systems Ltd. + * Copyright 2006-2009 Solarflare Communications Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation, incorporated herein by reference. + */ + +#include <linux/bitops.h> +#include <linux/delay.h> +#include <linux/pci.h> +#include <linux/module.h> +#include "net_driver.h" +#include "bitfield.h" +#include "efx.h" +#include "nic.h" +#include "mac.h" +#include "spi.h" +#include "regs.h" +#include "io.h" +#include "phy.h" +#include "workarounds.h" +#include "mcdi.h" +#include "mcdi_pcol.h" + +/* Hardware control for SFC9000 family including SFL9021 (aka Siena). */ + +static void siena_init_wol(struct efx_nic *efx); + + +static void siena_push_irq_moderation(struct efx_channel *channel) +{ + efx_dword_t timer_cmd; + + if (channel->irq_moderation) + EFX_POPULATE_DWORD_2(timer_cmd, + FRF_CZ_TC_TIMER_MODE, + FFE_CZ_TIMER_MODE_INT_HLDOFF, + FRF_CZ_TC_TIMER_VAL, + channel->irq_moderation - 1); + else + EFX_POPULATE_DWORD_2(timer_cmd, + FRF_CZ_TC_TIMER_MODE, + FFE_CZ_TIMER_MODE_DIS, + FRF_CZ_TC_TIMER_VAL, 0); + efx_writed_page_locked(channel->efx, &timer_cmd, FR_BZ_TIMER_COMMAND_P0, + channel->channel); +} + +static void siena_push_multicast_hash(struct efx_nic *efx) +{ + WARN_ON(!mutex_is_locked(&efx->mac_lock)); + + efx_mcdi_rpc(efx, MC_CMD_SET_MCAST_HASH, + efx->multicast_hash.byte, sizeof(efx->multicast_hash), + NULL, 0, NULL); +} + +static int siena_mdio_write(struct net_device *net_dev, + int prtad, int devad, u16 addr, u16 value) +{ + struct efx_nic *efx = netdev_priv(net_dev); + uint32_t status; + int rc; + + rc = efx_mcdi_mdio_write(efx, efx->mdio_bus, prtad, devad, + addr, value, &status); + if (rc) + return rc; + if (status != MC_CMD_MDIO_STATUS_GOOD) + return -EIO; + + return 0; +} + +static int siena_mdio_read(struct net_device *net_dev, + int prtad, int devad, u16 addr) +{ + struct efx_nic *efx = netdev_priv(net_dev); + uint16_t value; + uint32_t status; + int rc; + + rc = efx_mcdi_mdio_read(efx, efx->mdio_bus, prtad, devad, + addr, &value, &status); + if (rc) + return rc; + if (status != MC_CMD_MDIO_STATUS_GOOD) + return -EIO; + + return (int)value; +} + +/* This call is responsible for hooking in the MAC and PHY operations */ +static int siena_probe_port(struct efx_nic *efx) +{ + int rc; + + /* Hook in PHY operations table */ + efx->phy_op = &efx_mcdi_phy_ops; + + /* Set up MDIO structure for PHY */ + efx->mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22; + efx->mdio.mdio_read = siena_mdio_read; + efx->mdio.mdio_write = siena_mdio_write; + + /* Fill out MDIO structure and loopback modes */ + rc = efx->phy_op->probe(efx); + if (rc != 0) + return rc; + + /* Initial assumption */ + efx->link_state.speed = 10000; + efx->link_state.fd = true; + efx->wanted_fc = EFX_FC_RX | EFX_FC_TX; + + /* Allocate buffer for stats */ + rc = efx_nic_alloc_buffer(efx, &efx->stats_buffer, + MC_CMD_MAC_NSTATS * sizeof(u64)); + if (rc) + return rc; + EFX_LOG(efx, "stats buffer at %llx (virt %p phys %llx)\n", + (u64)efx->stats_buffer.dma_addr, + efx->stats_buffer.addr, + (u64)virt_to_phys(efx->stats_buffer.addr)); + + efx_mcdi_mac_stats(efx, efx->stats_buffer.dma_addr, 0, 0, 1); + + return 0; +} + +void siena_remove_port(struct efx_nic *efx) +{ + efx_nic_free_buffer(efx, &efx->stats_buffer); +} + +static const struct efx_nic_register_test siena_register_tests[] = { + { FR_AZ_ADR_REGION, + EFX_OWORD32(0x0001FFFF, 0x0001FFFF, 0x0001FFFF, 0x0001FFFF) }, + { FR_CZ_USR_EV_CFG, + EFX_OWORD32(0x000103FF, 0x00000000, 0x00000000, 0x00000000) }, + { FR_AZ_RX_CFG, + EFX_OWORD32(0xFFFFFFFE, 0xFFFFFFFF, 0x0003FFFF, 0x00000000) }, + { FR_AZ_TX_CFG, + EFX_OWORD32(0x7FFF0037, 0xFFFF8000, 0xFFFFFFFF, 0x03FFFFFF) }, + { FR_AZ_TX_RESERVED, + EFX_OWORD32(0xFFFEFE80, 0x1FFFFFFF, 0x020000FE, 0x007FFFFF) }, + { FR_AZ_SRM_TX_DC_CFG, + EFX_OWORD32(0x001FFFFF, 0x00000000, 0x00000000, 0x00000000) }, + { FR_AZ_RX_DC_CFG, + EFX_OWORD32(0x00000003, 0x00000000, 0x00000000, 0x00000000) }, + { FR_AZ_RX_DC_PF_WM, + EFX_OWORD32(0x000003FF, 0x00000000, 0x00000000, 0x00000000) }, + { FR_BZ_DP_CTRL, + EFX_OWORD32(0x00000FFF, 0x00000000, 0x00000000, 0x00000000) }, + { FR_BZ_RX_RSS_TKEY, + EFX_OWORD32(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF) }, + { FR_CZ_RX_RSS_IPV6_REG1, + EFX_OWORD32(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF) }, + { FR_CZ_RX_RSS_IPV6_REG2, + EFX_OWORD32(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF) }, + { FR_CZ_RX_RSS_IPV6_REG3, + EFX_OWORD32(0xFFFFFFFF, 0xFFFFFFFF, 0x00000007, 0x00000000) }, +}; + +static int siena_test_registers(struct efx_nic *efx) +{ + return efx_nic_test_registers(efx, siena_register_tests, + ARRAY_SIZE(siena_register_tests)); +} + +/************************************************************************** + * + * Device reset + * + ************************************************************************** + */ + +static int siena_reset_hw(struct efx_nic *efx, enum reset_type method) +{ + + if (method == RESET_TYPE_WORLD) + return efx_mcdi_reset_mc(efx); + else + return efx_mcdi_reset_port(efx); +} + +static int siena_probe_nvconfig(struct efx_nic *efx) +{ + int rc; + + rc = efx_mcdi_get_board_cfg(efx, efx->mac_address, NULL); + if (rc) + return rc; + + return 0; +} + +static int siena_probe_nic(struct efx_nic *efx) +{ + struct siena_nic_data *nic_data; + bool already_attached = 0; + int rc; + + /* Allocate storage for hardware specific data */ + nic_data = kzalloc(sizeof(struct siena_nic_data), GFP_KERNEL); + if (!nic_data) + return -ENOMEM; + efx->nic_data = nic_data; + + if (efx_nic_fpga_ver(efx) != 0) { + EFX_ERR(efx, "Siena FPGA not supported\n"); + rc = -ENODEV; + goto fail1; + } + + efx_mcdi_init(efx); + + /* Recover from a failed assertion before probing */ + rc = efx_mcdi_handle_assertion(efx); + if (rc) + goto fail1; + + rc = efx_mcdi_fwver(efx, &nic_data->fw_version, &nic_data->fw_build); + if (rc) { + EFX_ERR(efx, "Failed to read MCPU firmware version - " + "rc %d\n", rc); + goto fail1; /* MCPU absent? */ + } + + /* Let the BMC know that the driver is now in charge of link and + * filter settings. We must do this before we reset the NIC */ + rc = efx_mcdi_drv_attach(efx, true, &already_attached); + if (rc) { + EFX_ERR(efx, "Unable to register driver with MCPU\n"); + goto fail2; + } + if (already_attached) + /* Not a fatal error */ + EFX_ERR(efx, "Host already registered with MCPU\n"); + + /* Now we can reset the NIC */ + rc = siena_reset_hw(efx, RESET_TYPE_ALL); + if (rc) { + EFX_ERR(efx, "failed to reset NIC\n"); + goto fail3; + } + + siena_init_wol(efx); + + /* Allocate memory for INT_KER */ + rc = efx_nic_alloc_buffer(efx, &efx->irq_status, sizeof(efx_oword_t)); + if (rc) + goto fail4; + BUG_ON(efx->irq_status.dma_addr & 0x0f); + + EFX_LOG(efx, "INT_KER at %llx (virt %p phys %llx)\n", + (unsigned long long)efx->irq_status.dma_addr, + efx->irq_status.addr, + (unsigned long long)virt_to_phys(efx->irq_status.addr)); + + /* Read in the non-volatile configuration */ + rc = siena_probe_nvconfig(efx); + if (rc == -EINVAL) { + EFX_ERR(efx, "NVRAM is invalid therefore using defaults\n"); + efx->phy_type = PHY_TYPE_NONE; + efx->mdio.prtad = MDIO_PRTAD_NONE; + } else if (rc) { + goto fail5; + } + + return 0; + +fail5: + efx_nic_free_buffer(efx, &efx->irq_status); +fail4: +fail3: + efx_mcdi_drv_attach(efx, false, NULL); +fail2: +fail1: + kfree(efx->nic_data); + return rc; +} + +/* This call performs hardware-specific global initialisation, such as + * defining the descriptor cache sizes and number of RSS channels. + * It does not set up any buffers, descriptor rings or event queues. + */ +static int siena_init_nic(struct efx_nic *efx) +{ + efx_oword_t temp; + int rc; + + /* Recover from a failed assertion post-reset */ + rc = efx_mcdi_handle_assertion(efx); + if (rc) + return rc; + + /* Squash TX of packets of 16 bytes or less */ + efx_reado(efx, &temp, FR_AZ_TX_RESERVED); + EFX_SET_OWORD_FIELD(temp, FRF_BZ_TX_FLUSH_MIN_LEN_EN, 1); + efx_writeo(efx, &temp, FR_AZ_TX_RESERVED); + + /* Do not enable TX_NO_EOP_DISC_EN, since it limits packets to 16 + * descriptors (which is bad). + */ + efx_reado(efx, &temp, FR_AZ_TX_CFG); + EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_NO_EOP_DISC_EN, 0); + EFX_SET_OWORD_FIELD(temp, FRF_CZ_TX_FILTER_EN_BIT, 1); + efx_writeo(efx, &temp, FR_AZ_TX_CFG); + + efx_reado(efx, &temp, FR_AZ_RX_CFG); + EFX_SET_OWORD_FIELD(temp, FRF_BZ_RX_DESC_PUSH_EN, 0); + EFX_SET_OWORD_FIELD(temp, FRF_BZ_RX_INGR_EN, 1); + efx_writeo(efx, &temp, FR_AZ_RX_CFG); + + if (efx_nic_rx_xoff_thresh >= 0 || efx_nic_rx_xon_thresh >= 0) + /* No MCDI operation has been defined to set thresholds */ + EFX_ERR(efx, "ignoring RX flow control thresholds\n"); + + /* Enable event logging */ + rc = efx_mcdi_log_ctrl(efx, true, false, 0); + if (rc) + return rc; + + /* Set destination of both TX and RX Flush events */ + EFX_POPULATE_OWORD_1(temp, FRF_BZ_FLS_EVQ_ID, 0); + efx_writeo(efx, &temp, FR_BZ_DP_CTRL); + + EFX_POPULATE_OWORD_1(temp, FRF_CZ_USREV_DIS, 1); + efx_writeo(efx, &temp, FR_CZ_USR_EV_CFG); + + efx_nic_init_common(efx); + return 0; +} + +static void siena_remove_nic(struct efx_nic *efx) +{ + efx_nic_free_buffer(efx, &efx->irq_status); + + siena_reset_hw(efx, RESET_TYPE_ALL); + + /* Relinquish the device back to the BMC */ + if (efx_nic_has_mc(efx)) + efx_mcdi_drv_attach(efx, false, NULL); + + /* Tear down the private nic state */ + kfree(efx->nic_data); + efx->nic_data = NULL; +} + +#define STATS_GENERATION_INVALID ((u64)(-1)) + +static int siena_try_update_nic_stats(struct efx_nic *efx) +{ + u64 *dma_stats; + struct efx_mac_stats *mac_stats; + u64 generation_start; + u64 generation_end; + + mac_stats = &efx->mac_stats; + dma_stats = (u64 *)efx->stats_buffer.addr; + + generation_end = dma_stats[MC_CMD_MAC_GENERATION_END]; + if (generation_end == STATS_GENERATION_INVALID) + return 0; + rmb(); + +#define MAC_STAT(M, D) \ + mac_stats->M = dma_stats[MC_CMD_MAC_ ## D] + + MAC_STAT(tx_bytes, TX_BYTES); + MAC_STAT(tx_bad_bytes, TX_BAD_BYTES); + mac_stats->tx_good_bytes = (mac_stats->tx_bytes - + mac_stats->tx_bad_bytes); + MAC_STAT(tx_packets, TX_PKTS); + MAC_STAT(tx_bad, TX_BAD_FCS_PKTS); + MAC_STAT(tx_pause, TX_PAUSE_PKTS); + MAC_STAT(tx_control, TX_CONTROL_PKTS); + MAC_STAT(tx_unicast, TX_UNICAST_PKTS); + MAC_STAT(tx_multicast, TX_MULTICAST_PKTS); + MAC_STAT(tx_broadcast, TX_BROADCAST_PKTS); + MAC_STAT(tx_lt64, TX_LT64_PKTS); + MAC_STAT(tx_64, TX_64_PKTS); + MAC_STAT(tx_65_to_127, TX_65_TO_127_PKTS); + MAC_STAT(tx_128_to_255, TX_128_TO_255_PKTS); + MAC_STAT(tx_256_to_511, TX_256_TO_511_PKTS); + MAC_STAT(tx_512_to_1023, TX_512_TO_1023_PKTS); + MAC_STAT(tx_1024_to_15xx, TX_1024_TO_15XX_PKTS); + MAC_STAT(tx_15xx_to_jumbo, TX_15XX_TO_JUMBO_PKTS); + MAC_STAT(tx_gtjumbo, TX_GTJUMBO_PKTS); + mac_stats->tx_collision = 0; + MAC_STAT(tx_single_collision, TX_SINGLE_COLLISION_PKTS); + MAC_STAT(tx_multiple_collision, TX_MULTIPLE_COLLISION_PKTS); + MAC_STAT(tx_excessive_collision, TX_EXCESSIVE_COLLISION_PKTS); + MAC_STAT(tx_deferred, TX_DEFERRED_PKTS); + MAC_STAT(tx_late_collision, TX_LATE_COLLISION_PKTS); + mac_stats->tx_collision = (mac_stats->tx_single_collision + + mac_stats->tx_multiple_collision + + mac_stats->tx_excessive_collision + + mac_stats->tx_late_collision); + MAC_STAT(tx_excessive_deferred, TX_EXCESSIVE_DEFERRED_PKTS); + MAC_STAT(tx_non_tcpudp, TX_NON_TCPUDP_PKTS); + MAC_STAT(tx_mac_src_error, TX_MAC_SRC_ERR_PKTS); + MAC_STAT(tx_ip_src_error, TX_IP_SRC_ERR_PKTS); + MAC_STAT(rx_bytes, RX_BYTES); + MAC_STAT(rx_bad_bytes, RX_BAD_BYTES); + mac_stats->rx_good_bytes = (mac_stats->rx_bytes - + mac_stats->rx_bad_bytes); + MAC_STAT(rx_packets, RX_PKTS); + MAC_STAT(rx_good, RX_GOOD_PKTS); + mac_stats->rx_bad = mac_stats->rx_packets - mac_stats->rx_good; + MAC_STAT(rx_pause, RX_PAUSE_PKTS); + MAC_STAT(rx_control, RX_CONTROL_PKTS); + MAC_STAT(rx_unicast, RX_UNICAST_PKTS); + MAC_STAT(rx_multicast, RX_MULTICAST_PKTS); + MAC_STAT(rx_broadcast, RX_BROADCAST_PKTS); + MAC_STAT(rx_lt64, RX_UNDERSIZE_PKTS); + MAC_STAT(rx_64, RX_64_PKTS); + MAC_STAT(rx_65_to_127, RX_65_TO_127_PKTS); + MAC_STAT(rx_128_to_255, RX_128_TO_255_PKTS); + MAC_STAT(rx_256_to_511, RX_256_TO_511_PKTS); + MAC_STAT(rx_512_to_1023, RX_512_TO_1023_PKTS); + MAC_STAT(rx_1024_to_15xx, RX_1024_TO_15XX_PKTS); + MAC_STAT(rx_15xx_to_jumbo, RX_15XX_TO_JUMBO_PKTS); + MAC_STAT(rx_gtjumbo, RX_GTJUMBO_PKTS); + mac_stats->rx_bad_lt64 = 0; + mac_stats->rx_bad_64_to_15xx = 0; + mac_stats->rx_bad_15xx_to_jumbo = 0; + MAC_STAT(rx_bad_gtjumbo, RX_JABBER_PKTS); + MAC_STAT(rx_overflow, RX_OVERFLOW_PKTS); + mac_stats->rx_missed = 0; + MAC_STAT(rx_false_carrier, RX_FALSE_CARRIER_PKTS); + MAC_STAT(rx_symbol_error, RX_SYMBOL_ERROR_PKTS); + MAC_STAT(rx_align_error, RX_ALIGN_ERROR_PKTS); + MAC_STAT(rx_length_error, RX_LENGTH_ERROR_PKTS); + MAC_STAT(rx_internal_error, RX_INTERNAL_ERROR_PKTS); + mac_stats->rx_good_lt64 = 0; + + efx->n_rx_nodesc_drop_cnt = dma_stats[MC_CMD_MAC_RX_NODESC_DROPS]; + +#undef MAC_STAT + + rmb(); + generation_start = dma_stats[MC_CMD_MAC_GENERATION_START]; + if (generation_end != generation_start) + return -EAGAIN; + + return 0; +} + +static void siena_update_nic_stats(struct efx_nic *efx) +{ + while (siena_try_update_nic_stats(efx) == -EAGAIN) + cpu_relax(); +} + +static void siena_start_nic_stats(struct efx_nic *efx) +{ + u64 *dma_stats = (u64 *)efx->stats_buffer.addr; + + dma_stats[MC_CMD_MAC_GENERATION_END] = STATS_GENERATION_INVALID; + + efx_mcdi_mac_stats(efx, efx->stats_buffer.dma_addr, + MC_CMD_MAC_NSTATS * sizeof(u64), 1, 0); +} + +static void siena_stop_nic_stats(struct efx_nic *efx) +{ + efx_mcdi_mac_stats(efx, efx->stats_buffer.dma_addr, 0, 0, 0); +} + +void siena_print_fwver(struct efx_nic *efx, char *buf, size_t len) +{ + struct siena_nic_data *nic_data = efx->nic_data; + snprintf(buf, len, "%u.%u.%u.%u", + (unsigned int)(nic_data->fw_version >> 48), + (unsigned int)(nic_data->fw_version >> 32 & 0xffff), + (unsigned int)(nic_data->fw_version >> 16 & 0xffff), + (unsigned int)(nic_data->fw_version & 0xffff)); +} + +/************************************************************************** + * + * Wake on LAN + * + ************************************************************************** + */ + +static void siena_get_wol(struct efx_nic *efx, struct ethtool_wolinfo *wol) +{ + struct siena_nic_data *nic_data = efx->nic_data; + + wol->supported = WAKE_MAGIC; + if (nic_data->wol_filter_id != -1) + wol->wolopts = WAKE_MAGIC; + else + wol->wolopts = 0; + memset(&wol->sopass, 0, sizeof(wol->sopass)); +} + + +static int siena_set_wol(struct efx_nic *efx, u32 type) +{ + struct siena_nic_data *nic_data = efx->nic_data; + int rc; + + if (type & ~WAKE_MAGIC) + return -EINVAL; + + if (type & WAKE_MAGIC) { + if (nic_data->wol_filter_id != -1) + efx_mcdi_wol_filter_remove(efx, + nic_data->wol_filter_id); + rc = efx_mcdi_wol_filter_set_magic(efx, efx->mac_address, + &nic_data->wol_filter_id); + if (rc) + goto fail; + + pci_wake_from_d3(efx->pci_dev, true); + } else { + rc = efx_mcdi_wol_filter_reset(efx); + nic_data->wol_filter_id = -1; + pci_wake_from_d3(efx->pci_dev, false); + if (rc) + goto fail; + } + + return 0; + fail: + EFX_ERR(efx, "%s failed: type=%d rc=%d\n", __func__, type, rc); + return rc; +} + + +static void siena_init_wol(struct efx_nic *efx) +{ + struct siena_nic_data *nic_data = efx->nic_data; + int rc; + + rc = efx_mcdi_wol_filter_get_magic(efx, &nic_data->wol_filter_id); + + if (rc != 0) { + /* If it failed, attempt to get into a synchronised + * state with MC by resetting any set WoL filters */ + efx_mcdi_wol_filter_reset(efx); + nic_data->wol_filter_id = -1; + } else if (nic_data->wol_filter_id != -1) { + pci_wake_from_d3(efx->pci_dev, true); + } +} + + +/************************************************************************** + * + * Revision-dependent attributes used by efx.c and nic.c + * + ************************************************************************** + */ + +struct efx_nic_type siena_a0_nic_type = { + .probe = siena_probe_nic, + .remove = siena_remove_nic, + .init = siena_init_nic, + .fini = efx_port_dummy_op_void, + .monitor = NULL, + .reset = siena_reset_hw, + .probe_port = siena_probe_port, + .remove_port = siena_remove_port, + .prepare_flush = efx_port_dummy_op_void, + .update_stats = siena_update_nic_stats, + .start_stats = siena_start_nic_stats, + .stop_stats = siena_stop_nic_stats, + .set_id_led = efx_mcdi_set_id_led, + .push_irq_moderation = siena_push_irq_moderation, + .push_multicast_hash = siena_push_multicast_hash, + .reconfigure_port = efx_mcdi_phy_reconfigure, + .get_wol = siena_get_wol, + .set_wol = siena_set_wol, + .resume_wol = siena_init_wol, + .test_registers = siena_test_registers, + .default_mac_ops = &efx_mcdi_mac_operations, + + .revision = EFX_REV_SIENA_A0, + .mem_map_size = (FR_CZ_MC_TREG_SMEM + + FR_CZ_MC_TREG_SMEM_STEP * FR_CZ_MC_TREG_SMEM_ROWS), + .txd_ptr_tbl_base = FR_BZ_TX_DESC_PTR_TBL, + .rxd_ptr_tbl_base = FR_BZ_RX_DESC_PTR_TBL, + .buf_tbl_base = FR_BZ_BUF_FULL_TBL, + .evq_ptr_tbl_base = FR_BZ_EVQ_PTR_TBL, + .evq_rptr_tbl_base = FR_BZ_EVQ_RPTR, + .max_dma_mask = DMA_BIT_MASK(FSF_AZ_TX_KER_BUF_ADDR_WIDTH), + .rx_buffer_padding = 0, + .max_interrupt_mode = EFX_INT_MODE_MSIX, + .phys_addr_channels = 32, /* Hardware limit is 64, but the legacy + * interrupt handler only supports 32 + * channels */ + .tx_dc_base = 0x88000, + .rx_dc_base = 0x68000, + .offload_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM, + .reset_world_flags = ETH_RESET_MGMT << ETH_RESET_SHARED_SHIFT, +}; diff --git a/drivers/net/sfc/spi.h b/drivers/net/sfc/spi.h index 1b1ceb411671..8bf4fce0813a 100644 --- a/drivers/net/sfc/spi.h +++ b/drivers/net/sfc/spi.h @@ -36,8 +36,6 @@ /** * struct efx_spi_device - an Efx SPI (Serial Peripheral Interface) device - * @efx: The Efx controller that owns this device - * @mtd: MTD state * @device_id: Controller's id for the device * @size: Size (in bytes) * @addr_len: Number of address bytes in read/write commands @@ -54,10 +52,6 @@ * Write commands are limited to blocks with this size and alignment. */ struct efx_spi_device { - struct efx_nic *efx; -#ifdef CONFIG_SFC_MTD - void *mtd; -#endif int device_id; unsigned int size; unsigned int addr_len; @@ -67,12 +61,16 @@ struct efx_spi_device { unsigned int block_size; }; -int falcon_spi_cmd(const struct efx_spi_device *spi, unsigned int command, +int falcon_spi_cmd(struct efx_nic *efx, + const struct efx_spi_device *spi, unsigned int command, int address, const void* in, void *out, size_t len); -int falcon_spi_wait_write(const struct efx_spi_device *spi); -int falcon_spi_read(const struct efx_spi_device *spi, loff_t start, +int falcon_spi_wait_write(struct efx_nic *efx, + const struct efx_spi_device *spi); +int falcon_spi_read(struct efx_nic *efx, + const struct efx_spi_device *spi, loff_t start, size_t len, size_t *retlen, u8 *buffer); -int falcon_spi_write(const struct efx_spi_device *spi, loff_t start, +int falcon_spi_write(struct efx_nic *efx, + const struct efx_spi_device *spi, loff_t start, size_t len, size_t *retlen, const u8 *buffer); /* diff --git a/drivers/net/sfc/tenxpress.c b/drivers/net/sfc/tenxpress.c index b001f38524f7..ca11572a49a9 100644 --- a/drivers/net/sfc/tenxpress.c +++ b/drivers/net/sfc/tenxpress.c @@ -1,6 +1,6 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards - * Copyright 2007-2008 Solarflare Communications Inc. + * Copyright 2007-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -12,7 +12,7 @@ #include <linux/seq_file.h> #include "efx.h" #include "mdio_10g.h" -#include "falcon.h" +#include "nic.h" #include "phy.h" #include "regs.h" #include "workarounds.h" @@ -30,13 +30,13 @@ #define SFX7101_LOOPBACKS ((1 << LOOPBACK_PHYXS) | \ (1 << LOOPBACK_PCS) | \ (1 << LOOPBACK_PMAPMD) | \ - (1 << LOOPBACK_NETWORK)) + (1 << LOOPBACK_PHYXS_WS)) #define SFT9001_LOOPBACKS ((1 << LOOPBACK_GPHY) | \ (1 << LOOPBACK_PHYXS) | \ (1 << LOOPBACK_PCS) | \ (1 << LOOPBACK_PMAPMD) | \ - (1 << LOOPBACK_NETWORK)) + (1 << LOOPBACK_PHYXS_WS)) /* We complain if we fail to see the link partner as 10G capable this many * times in a row (must be > 1 as sampling the autoneg. registers is racy) @@ -199,15 +199,16 @@ static ssize_t set_phy_short_reach(struct device *dev, const char *buf, size_t count) { struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + int rc; rtnl_lock(); efx_mdio_set_flag(efx, MDIO_MMD_PMAPMD, MDIO_PMA_10GBT_TXPWR, MDIO_PMA_10GBT_TXPWR_SHORT, count != 0 && *buf != '0'); - efx_reconfigure_port(efx); + rc = efx_reconfigure_port(efx); rtnl_unlock(); - return count; + return rc < 0 ? rc : (ssize_t)count; } static DEVICE_ATTR(phy_short_reach, 0644, show_phy_short_reach, @@ -297,13 +298,29 @@ static int tenxpress_init(struct efx_nic *efx) return 0; } +static int sfx7101_phy_probe(struct efx_nic *efx) +{ + efx->mdio.mmds = TENXPRESS_REQUIRED_DEVS; + efx->mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22; + efx->loopback_modes = SFX7101_LOOPBACKS | FALCON_XMAC_LOOPBACKS; + return 0; +} + +static int sft9001_phy_probe(struct efx_nic *efx) +{ + efx->mdio.mmds = TENXPRESS_REQUIRED_DEVS; + efx->mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22; + efx->loopback_modes = (SFT9001_LOOPBACKS | FALCON_XMAC_LOOPBACKS | + FALCON_GMAC_LOOPBACKS); + return 0; +} + static int tenxpress_phy_init(struct efx_nic *efx) { struct tenxpress_phy_data *phy_data; - u16 old_adv, adv; int rc = 0; - falcon_board(efx)->init_phy(efx); + falcon_board(efx)->type->init_phy(efx); phy_data = kzalloc(sizeof(*phy_data), GFP_KERNEL); if (!phy_data) @@ -335,14 +352,14 @@ static int tenxpress_phy_init(struct efx_nic *efx) if (rc < 0) goto fail; - /* Set pause advertising */ - old_adv = efx_mdio_read(efx, MDIO_MMD_AN, MDIO_AN_ADVERTISE); - adv = ((old_adv & ~(ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM)) | - mii_advertise_flowctrl(efx->wanted_fc)); - if (adv != old_adv) { - efx_mdio_write(efx, MDIO_MMD_AN, MDIO_AN_ADVERTISE, adv); - mdio45_nway_restart(&efx->mdio); - } + /* Initialise advertising flags */ + efx->link_advertising = (ADVERTISED_TP | ADVERTISED_Autoneg | + ADVERTISED_10000baseT_Full); + if (efx->phy_type != PHY_TYPE_SFX7101) + efx->link_advertising |= (ADVERTISED_1000baseT_Full | + ADVERTISED_100baseT_Full); + efx_link_set_wanted_fc(efx, efx->wanted_fc); + efx_mdio_an_reconfigure(efx); if (efx->phy_type == PHY_TYPE_SFT9001B) { rc = device_create_file(&efx->pci_dev->dev, @@ -374,7 +391,7 @@ static int tenxpress_special_reset(struct efx_nic *efx) /* The XGMAC clock is driven from the SFC7101/SFT9001 312MHz clock, so * a special software reset can glitch the XGMAC sufficiently for stats * requests to fail. */ - efx_stats_disable(efx); + falcon_stop_nic_stats(efx); /* Initiate reset */ reg = efx_mdio_read(efx, MDIO_MMD_PMAPMD, PMA_PMD_XCONTROL_REG); @@ -396,7 +413,7 @@ static int tenxpress_special_reset(struct efx_nic *efx) /* Wait for the XGXS state machine to churn */ mdelay(10); out: - efx_stats_enable(efx); + falcon_start_nic_stats(efx); return rc; } @@ -500,97 +517,76 @@ static void tenxpress_low_power(struct efx_nic *efx) !!(efx->phy_mode & PHY_MODE_LOW_POWER)); } -static void tenxpress_phy_reconfigure(struct efx_nic *efx) +static int tenxpress_phy_reconfigure(struct efx_nic *efx) { struct tenxpress_phy_data *phy_data = efx->phy_data; - struct efx_link_state *link_state = &efx->link_state; - struct ethtool_cmd ecmd; bool phy_mode_change, loop_reset; if (efx->phy_mode & (PHY_MODE_OFF | PHY_MODE_SPECIAL)) { phy_data->phy_mode = efx->phy_mode; - return; + return 0; } - tenxpress_low_power(efx); - phy_mode_change = (efx->phy_mode == PHY_MODE_NORMAL && phy_data->phy_mode != PHY_MODE_NORMAL); - loop_reset = (LOOPBACK_OUT_OF(phy_data, efx, efx->phy_op->loopbacks) || + loop_reset = (LOOPBACK_OUT_OF(phy_data, efx, LOOPBACKS_EXTERNAL(efx)) || LOOPBACK_CHANGED(phy_data, efx, 1 << LOOPBACK_GPHY)); if (loop_reset || phy_mode_change) { - int rc; + tenxpress_special_reset(efx); - efx->phy_op->get_settings(efx, &ecmd); - - if (loop_reset || phy_mode_change) { - tenxpress_special_reset(efx); - - /* Reset XAUI if we were in 10G, and are staying - * in 10G. If we're moving into and out of 10G - * then xaui will be reset anyway */ - if (EFX_IS10G(efx)) - falcon_reset_xaui(efx); - } - - rc = efx->phy_op->set_settings(efx, &ecmd); - WARN_ON(rc); + /* Reset XAUI if we were in 10G, and are staying + * in 10G. If we're moving into and out of 10G + * then xaui will be reset anyway */ + if (EFX_IS10G(efx)) + falcon_reset_xaui(efx); } + tenxpress_low_power(efx); efx_mdio_transmit_disable(efx); efx_mdio_phy_reconfigure(efx); tenxpress_ext_loopback(efx); + efx_mdio_an_reconfigure(efx); phy_data->loopback_mode = efx->loopback_mode; phy_data->phy_mode = efx->phy_mode; - if (efx->phy_type == PHY_TYPE_SFX7101) { - link_state->speed = 10000; - link_state->fd = true; - link_state->up = sfx7101_link_ok(efx); - } else { - efx->phy_op->get_settings(efx, &ecmd); - link_state->speed = ecmd.speed; - link_state->fd = ecmd.duplex == DUPLEX_FULL; - link_state->up = sft9001_link_ok(efx, &ecmd); - } - link_state->fc = efx_mdio_get_pause(efx); + return 0; } -/* Poll PHY for interrupt */ -static void tenxpress_phy_poll(struct efx_nic *efx) +static void +tenxpress_get_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd); + +/* Poll for link state changes */ +static bool tenxpress_phy_poll(struct efx_nic *efx) { - struct tenxpress_phy_data *phy_data = efx->phy_data; - struct efx_link_state *link_state = &efx->link_state; - bool change = false; + struct efx_link_state old_state = efx->link_state; if (efx->phy_type == PHY_TYPE_SFX7101) { - bool link_ok = sfx7101_link_ok(efx); - if (link_ok != link_state->up) { - change = true; - } else { - unsigned int link_fc = efx_mdio_get_pause(efx); - if (link_fc != link_state->fc) - change = true; - } - sfx7101_check_bad_lp(efx, link_ok); - } else if (efx->loopback_mode) { - bool link_ok = sft9001_link_ok(efx, NULL); - if (link_ok != link_state->up) - change = true; + efx->link_state.up = sfx7101_link_ok(efx); + efx->link_state.speed = 10000; + efx->link_state.fd = true; + efx->link_state.fc = efx_mdio_get_pause(efx); + + sfx7101_check_bad_lp(efx, efx->link_state.up); } else { - int status = efx_mdio_read(efx, MDIO_MMD_PMAPMD, - MDIO_PMA_LASI_STAT); - if (status & MDIO_PMA_LASI_LSALARM) - change = true; - } + struct ethtool_cmd ecmd; - if (change) - falcon_sim_phy_event(efx); + /* Check the LASI alarm first */ + if (efx->loopback_mode == LOOPBACK_NONE && + !(efx_mdio_read(efx, MDIO_MMD_PMAPMD, MDIO_PMA_LASI_STAT) & + MDIO_PMA_LASI_LSALARM)) + return false; - if (phy_data->phy_mode != PHY_MODE_NORMAL) - return; + tenxpress_get_settings(efx, &ecmd); + + efx->link_state.up = sft9001_link_ok(efx, &ecmd); + efx->link_state.speed = ecmd.speed; + efx->link_state.fd = (ecmd.duplex == DUPLEX_FULL); + efx->link_state.fc = efx_mdio_get_pause(efx); + } + + return !efx_link_state_equal(&efx->link_state, &old_state); } static void tenxpress_phy_fini(struct efx_nic *efx) @@ -648,6 +644,13 @@ static const char *const sfx7101_test_names[] = { "bist" }; +static const char *sfx7101_test_name(struct efx_nic *efx, unsigned int index) +{ + if (index < ARRAY_SIZE(sfx7101_test_names)) + return sfx7101_test_names[index]; + return NULL; +} + static int sfx7101_run_tests(struct efx_nic *efx, int *results, unsigned flags) { @@ -659,6 +662,9 @@ sfx7101_run_tests(struct efx_nic *efx, int *results, unsigned flags) /* BIST is automatically run after a special software reset */ rc = tenxpress_special_reset(efx); results[0] = rc ? -1 : 1; + + efx_mdio_an_reconfigure(efx); + return rc; } @@ -674,14 +680,17 @@ static const char *const sft9001_test_names[] = { "cable.pairD.length", }; +static const char *sft9001_test_name(struct efx_nic *efx, unsigned int index) +{ + if (index < ARRAY_SIZE(sft9001_test_names)) + return sft9001_test_names[index]; + return NULL; +} + static int sft9001_run_tests(struct efx_nic *efx, int *results, unsigned flags) { - struct ethtool_cmd ecmd; int rc = 0, rc2, i, ctrl_reg, res_reg; - if (flags & ETH_TEST_FL_OFFLINE) - efx->phy_op->get_settings(efx, &ecmd); - /* Initialise cable diagnostic results to unknown failure */ for (i = 1; i < 9; ++i) results[i] = -1; @@ -733,9 +742,7 @@ out: if (!rc) rc = rc2; - rc2 = efx->phy_op->set_settings(efx, &ecmd); - if (!rc) - rc = rc2; + efx_mdio_an_reconfigure(efx); } return rc; @@ -766,7 +773,6 @@ tenxpress_get_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd) mdio45_ethtool_gset_npage(&efx->mdio, ecmd, adv, lpa); - ecmd->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; if (efx->phy_type != PHY_TYPE_SFX7101) { ecmd->supported |= (SUPPORTED_100baseT_Full | SUPPORTED_1000baseT_Full); @@ -783,7 +789,7 @@ tenxpress_get_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd) * but doesn't advertise the correct speed. So override it */ if (efx->loopback_mode == LOOPBACK_GPHY) ecmd->speed = SPEED_1000; - else if (LOOPBACK_MASK(efx) & efx->phy_op->loopbacks) + else if (LOOPBACK_EXTERNAL(efx)) ecmd->speed = SPEED_10000; } @@ -813,35 +819,27 @@ static void sft9001_set_npage_adv(struct efx_nic *efx, u32 advertising) } struct efx_phy_operations falcon_sfx7101_phy_ops = { - .macs = EFX_XMAC, + .probe = sfx7101_phy_probe, .init = tenxpress_phy_init, .reconfigure = tenxpress_phy_reconfigure, .poll = tenxpress_phy_poll, .fini = tenxpress_phy_fini, - .clear_interrupt = efx_port_dummy_op_void, .get_settings = tenxpress_get_settings, .set_settings = tenxpress_set_settings, .set_npage_adv = sfx7101_set_npage_adv, - .num_tests = ARRAY_SIZE(sfx7101_test_names), - .test_names = sfx7101_test_names, + .test_name = sfx7101_test_name, .run_tests = sfx7101_run_tests, - .mmds = TENXPRESS_REQUIRED_DEVS, - .loopbacks = SFX7101_LOOPBACKS, }; struct efx_phy_operations falcon_sft9001_phy_ops = { - .macs = EFX_GMAC | EFX_XMAC, + .probe = sft9001_phy_probe, .init = tenxpress_phy_init, .reconfigure = tenxpress_phy_reconfigure, .poll = tenxpress_phy_poll, .fini = tenxpress_phy_fini, - .clear_interrupt = efx_port_dummy_op_void, .get_settings = tenxpress_get_settings, .set_settings = tenxpress_set_settings, .set_npage_adv = sft9001_set_npage_adv, - .num_tests = ARRAY_SIZE(sft9001_test_names), - .test_names = sft9001_test_names, + .test_name = sft9001_test_name, .run_tests = sft9001_run_tests, - .mmds = TENXPRESS_REQUIRED_DEVS, - .loopbacks = SFT9001_LOOPBACKS, }; diff --git a/drivers/net/sfc/tx.c b/drivers/net/sfc/tx.c index c54fa30e6277..e669f94e821b 100644 --- a/drivers/net/sfc/tx.c +++ b/drivers/net/sfc/tx.c @@ -1,7 +1,7 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards * Copyright 2005-2006 Fen Systems Ltd. - * Copyright 2005-2008 Solarflare Communications Inc. + * Copyright 2005-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -12,11 +12,13 @@ #include <linux/tcp.h> #include <linux/ip.h> #include <linux/in.h> +#include <linux/ipv6.h> +#include <net/ipv6.h> #include <linux/if_ether.h> #include <linux/highmem.h> #include "net_driver.h" #include "efx.h" -#include "falcon.h" +#include "nic.h" #include "workarounds.h" /* @@ -278,7 +280,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) buffer->continuation = false; /* Pass off to hardware */ - falcon_push_buffers(tx_queue); + efx_nic_push_buffers(tx_queue); return NETDEV_TX_OK; @@ -426,7 +428,7 @@ int efx_probe_tx_queue(struct efx_tx_queue *tx_queue) tx_queue->buffer[i].continuation = true; /* Allocate hardware ring */ - rc = falcon_probe_tx(tx_queue); + rc = efx_nic_probe_tx(tx_queue); if (rc) goto fail; @@ -449,7 +451,7 @@ void efx_init_tx_queue(struct efx_tx_queue *tx_queue) BUG_ON(tx_queue->stopped); /* Set up TX descriptor ring */ - falcon_init_tx(tx_queue); + efx_nic_init_tx(tx_queue); } void efx_release_tx_buffers(struct efx_tx_queue *tx_queue) @@ -475,7 +477,7 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue) EFX_LOG(tx_queue->efx, "shutting down TX queue %d\n", tx_queue->queue); /* Flush TX queue, remove descriptor ring */ - falcon_fini_tx(tx_queue); + efx_nic_fini_tx(tx_queue); efx_release_tx_buffers(tx_queue); @@ -492,7 +494,7 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue) void efx_remove_tx_queue(struct efx_tx_queue *tx_queue) { EFX_LOG(tx_queue->efx, "destroying TX queue %d\n", tx_queue->queue); - falcon_remove_tx(tx_queue); + efx_nic_remove_tx(tx_queue); kfree(tx_queue->buffer); tx_queue->buffer = NULL; @@ -531,6 +533,7 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue) #define ETH_HDR_LEN(skb) (skb_network_header(skb) - (skb)->data) #define SKB_TCP_OFF(skb) PTR_DIFF(tcp_hdr(skb), (skb)->data) #define SKB_IPV4_OFF(skb) PTR_DIFF(ip_hdr(skb), (skb)->data) +#define SKB_IPV6_OFF(skb) PTR_DIFF(ipv6_hdr(skb), (skb)->data) /** * struct tso_state - TSO state for an SKB @@ -543,6 +546,7 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue) * @unmap_len: Length of SKB fragment * @unmap_addr: DMA address of SKB fragment * @unmap_single: DMA single vs page mapping flag + * @protocol: Network protocol (after any VLAN header) * @header_len: Number of bytes of header * @full_packet_size: Number of bytes to put in each outgoing segment * @@ -563,6 +567,7 @@ struct tso_state { dma_addr_t unmap_addr; bool unmap_single; + __be16 protocol; unsigned header_len; int full_packet_size; }; @@ -570,9 +575,9 @@ struct tso_state { /* * Verify that our various assumptions about sk_buffs and the conditions - * under which TSO will be attempted hold true. + * under which TSO will be attempted hold true. Return the protocol number. */ -static void efx_tso_check_safe(struct sk_buff *skb) +static __be16 efx_tso_check_protocol(struct sk_buff *skb) { __be16 protocol = skb->protocol; @@ -587,13 +592,22 @@ static void efx_tso_check_safe(struct sk_buff *skb) if (protocol == htons(ETH_P_IP)) skb_set_transport_header(skb, sizeof(*veh) + 4 * ip_hdr(skb)->ihl); + else if (protocol == htons(ETH_P_IPV6)) + skb_set_transport_header(skb, sizeof(*veh) + + sizeof(struct ipv6hdr)); } - EFX_BUG_ON_PARANOID(protocol != htons(ETH_P_IP)); - EFX_BUG_ON_PARANOID(ip_hdr(skb)->protocol != IPPROTO_TCP); + if (protocol == htons(ETH_P_IP)) { + EFX_BUG_ON_PARANOID(ip_hdr(skb)->protocol != IPPROTO_TCP); + } else { + EFX_BUG_ON_PARANOID(protocol != htons(ETH_P_IPV6)); + EFX_BUG_ON_PARANOID(ipv6_hdr(skb)->nexthdr != NEXTHDR_TCP); + } EFX_BUG_ON_PARANOID((PTR_DIFF(tcp_hdr(skb), skb->data) + (tcp_hdr(skb)->doff << 2u)) > skb_headlen(skb)); + + return protocol; } @@ -836,7 +850,10 @@ static void tso_start(struct tso_state *st, const struct sk_buff *skb) + PTR_DIFF(tcp_hdr(skb), skb->data)); st->full_packet_size = st->header_len + skb_shinfo(skb)->gso_size; - st->ipv4_id = ntohs(ip_hdr(skb)->id); + if (st->protocol == htons(ETH_P_IP)) + st->ipv4_id = ntohs(ip_hdr(skb)->id); + else + st->ipv4_id = 0; st->seqnum = ntohl(tcp_hdr(skb)->seq); EFX_BUG_ON_PARANOID(tcp_hdr(skb)->urg); @@ -951,7 +968,6 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue, struct tso_state *st) { struct efx_tso_header *tsoh; - struct iphdr *tsoh_iph; struct tcphdr *tsoh_th; unsigned ip_length; u8 *header; @@ -975,7 +991,6 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue, header = TSOH_BUFFER(tsoh); tsoh_th = (struct tcphdr *)(header + SKB_TCP_OFF(skb)); - tsoh_iph = (struct iphdr *)(header + SKB_IPV4_OFF(skb)); /* Copy and update the headers. */ memcpy(header, skb->data, st->header_len); @@ -993,11 +1008,22 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue, tsoh_th->fin = tcp_hdr(skb)->fin; tsoh_th->psh = tcp_hdr(skb)->psh; } - tsoh_iph->tot_len = htons(ip_length); - /* Linux leaves suitable gaps in the IP ID space for us to fill. */ - tsoh_iph->id = htons(st->ipv4_id); - st->ipv4_id++; + if (st->protocol == htons(ETH_P_IP)) { + struct iphdr *tsoh_iph = + (struct iphdr *)(header + SKB_IPV4_OFF(skb)); + + tsoh_iph->tot_len = htons(ip_length); + + /* Linux leaves suitable gaps in the IP ID space for us to fill. */ + tsoh_iph->id = htons(st->ipv4_id); + st->ipv4_id++; + } else { + struct ipv6hdr *tsoh_iph = + (struct ipv6hdr *)(header + SKB_IPV6_OFF(skb)); + + tsoh_iph->payload_len = htons(ip_length - sizeof(*tsoh_iph)); + } st->packet_space = skb_shinfo(skb)->gso_size; ++tx_queue->tso_packets; @@ -1027,8 +1053,8 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, int frag_i, rc, rc2 = NETDEV_TX_OK; struct tso_state state; - /* Verify TSO is safe - these checks should never fail. */ - efx_tso_check_safe(skb); + /* Find the packet protocol and sanity-check it */ + state.protocol = efx_tso_check_protocol(skb); EFX_BUG_ON_PARANOID(tx_queue->write_count != tx_queue->insert_count); @@ -1078,7 +1104,7 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, } /* Pass off to hardware */ - falcon_push_buffers(tx_queue); + efx_nic_push_buffers(tx_queue); tx_queue->tso_bursts++; return NETDEV_TX_OK; diff --git a/drivers/net/sfc/workarounds.h b/drivers/net/sfc/workarounds.h index 325029949488..acd9c734e483 100644 --- a/drivers/net/sfc/workarounds.h +++ b/drivers/net/sfc/workarounds.h @@ -1,6 +1,6 @@ /**************************************************************************** * Driver for Solarflare Solarstorm network controllers and boards - * Copyright 2006-2008 Solarflare Communications Inc. + * Copyright 2006-2009 Solarflare Communications Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as published @@ -16,7 +16,9 @@ */ #define EFX_WORKAROUND_ALWAYS(efx) 1 -#define EFX_WORKAROUND_FALCON_A(efx) (falcon_rev(efx) <= FALCON_REV_A1) +#define EFX_WORKAROUND_FALCON_A(efx) (efx_nic_rev(efx) <= EFX_REV_FALCON_A1) +#define EFX_WORKAROUND_FALCON_AB(efx) (efx_nic_rev(efx) <= EFX_REV_FALCON_B0) +#define EFX_WORKAROUND_SIENA(efx) (efx_nic_rev(efx) == EFX_REV_SIENA_A0) #define EFX_WORKAROUND_10G(efx) EFX_IS10G(efx) #define EFX_WORKAROUND_SFT9001(efx) ((efx)->phy_type == PHY_TYPE_SFT9001A || \ (efx)->phy_type == PHY_TYPE_SFT9001B) @@ -27,17 +29,17 @@ #define EFX_WORKAROUND_7575 EFX_WORKAROUND_ALWAYS /* Bit-bashed I2C reads cause performance drop */ #define EFX_WORKAROUND_7884 EFX_WORKAROUND_10G -/* TX pkt parser problem with <= 16 byte TXes */ -#define EFX_WORKAROUND_9141 EFX_WORKAROUND_ALWAYS /* TX_EV_PKT_ERR can be caused by a dangling TX descriptor * or a PCIe error (bug 11028) */ #define EFX_WORKAROUND_10727 EFX_WORKAROUND_ALWAYS /* Transmit flow control may get disabled */ -#define EFX_WORKAROUND_11482 EFX_WORKAROUND_ALWAYS -/* Flush events can take a very long time to appear */ -#define EFX_WORKAROUND_11557 EFX_WORKAROUND_ALWAYS +#define EFX_WORKAROUND_11482 EFX_WORKAROUND_FALCON_AB /* Truncated IPv4 packets can confuse the TX packet parser */ -#define EFX_WORKAROUND_15592 EFX_WORKAROUND_ALWAYS +#define EFX_WORKAROUND_15592 EFX_WORKAROUND_FALCON_AB +/* Legacy ISR read can return zero once */ +#define EFX_WORKAROUND_15783 EFX_WORKAROUND_SIENA +/* Legacy interrupt storm when interrupt fifo fills */ +#define EFX_WORKAROUND_17213 EFX_WORKAROUND_SIENA /* Spurious parity errors in TSORT buffers */ #define EFX_WORKAROUND_5129 EFX_WORKAROUND_FALCON_A diff --git a/drivers/net/skge.c b/drivers/net/skge.c index 34b4e7d500da..379a3dc00163 100644 --- a/drivers/net/skge.c +++ b/drivers/net/skge.c @@ -238,8 +238,8 @@ static int skge_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) struct skge_port *skge = netdev_priv(dev); struct skge_hw *hw = skge->hw; - if ((wol->wolopts & ~wol_supported(hw)) - || !device_can_wakeup(&hw->pdev->dev)) + if ((wol->wolopts & ~wol_supported(hw)) || + !device_can_wakeup(&hw->pdev->dev)) return -EOPNOTSUPP; skge->wol = wol->wolopts; @@ -576,9 +576,10 @@ static void skge_get_pauseparam(struct net_device *dev, { struct skge_port *skge = netdev_priv(dev); - ecmd->rx_pause = (skge->flow_control == FLOW_MODE_SYMMETRIC) - || (skge->flow_control == FLOW_MODE_SYM_OR_REM); - ecmd->tx_pause = ecmd->rx_pause || (skge->flow_control == FLOW_MODE_LOC_SEND); + ecmd->rx_pause = ((skge->flow_control == FLOW_MODE_SYMMETRIC) || + (skge->flow_control == FLOW_MODE_SYM_OR_REM)); + ecmd->tx_pause = (ecmd->rx_pause || + (skge->flow_control == FLOW_MODE_LOC_SEND)); ecmd->autoneg = ecmd->rx_pause || ecmd->tx_pause; } @@ -2779,8 +2780,8 @@ static netdev_tx_t skge_xmit_frame(struct sk_buff *skb, /* This seems backwards, but it is what the sk98lin * does. Looks like hardware is wrong? */ - if (ipip_hdr(skb)->protocol == IPPROTO_UDP - && hw->chip_rev == 0 && hw->chip_id == CHIP_ID_YUKON) + if (ipip_hdr(skb)->protocol == IPPROTO_UDP && + hw->chip_rev == 0 && hw->chip_id == CHIP_ID_YUKON) control = BMU_TCP_CHECK; else control = BMU_UDP_CHECK; @@ -2948,8 +2949,8 @@ static void genesis_set_multicast(struct net_device *dev) else { memset(filter, 0, sizeof(filter)); - if (skge->flow_status == FLOW_STAT_REM_SEND - || skge->flow_status == FLOW_STAT_SYMMETRIC) + if (skge->flow_status == FLOW_STAT_REM_SEND || + skge->flow_status == FLOW_STAT_SYMMETRIC) genesis_add_filter(filter, pause_mc_addr); for (i = 0; list && i < count; i++, list = list->next) @@ -2972,8 +2973,8 @@ static void yukon_set_multicast(struct net_device *dev) struct skge_hw *hw = skge->hw; int port = skge->port; struct dev_mc_list *list = dev->mc_list; - int rx_pause = (skge->flow_status == FLOW_STAT_REM_SEND - || skge->flow_status == FLOW_STAT_SYMMETRIC); + int rx_pause = (skge->flow_status == FLOW_STAT_REM_SEND || + skge->flow_status == FLOW_STAT_SYMMETRIC); u16 reg; u8 filter[8]; diff --git a/drivers/net/sky2.c b/drivers/net/sky2.c index a3d99913f184..3943d89afb2b 100644 --- a/drivers/net/sky2.c +++ b/drivers/net/sky2.c @@ -374,8 +374,8 @@ static void sky2_phy_init(struct sky2_hw *hw, unsigned port) ctrl |= PHY_M_PC_MDI_XMODE(PHY_M_PC_ENA_AUTO); /* downshift on PHY 88E1112 and 88E1149 is changed */ - if ( (sky2->flags & SKY2_FLAG_AUTO_SPEED) - && (hw->flags & SKY2_HW_NEWER_PHY)) { + if ( (sky2->flags & SKY2_FLAG_AUTO_SPEED) && + (hw->flags & SKY2_HW_NEWER_PHY)) { /* set downshift counter to 3x and enable downshift */ ctrl &= ~PHY_M_PC_DSC_MSK; ctrl |= PHY_M_PC_DSC(2) | PHY_M_PC_DOWN_S_ENA; @@ -619,8 +619,8 @@ static void sky2_phy_init(struct sky2_hw *hw, unsigned port) /* no effect on Yukon-XL */ gm_phy_write(hw, port, PHY_MARV_LED_CTRL, ledctrl); - if ( !(sky2->flags & SKY2_FLAG_AUTO_SPEED) - || sky2->speed == SPEED_100) { + if (!(sky2->flags & SKY2_FLAG_AUTO_SPEED) || + sky2->speed == SPEED_100) { /* turn on 100 Mbps LED (LED_LINK100) */ ledover |= PHY_M_LED_MO_100(MO_LED_ON); } @@ -937,8 +937,8 @@ static void sky2_mac_init(struct sky2_hw *hw, unsigned port) /* On chips without ram buffer, pause is controled by MAC level */ if (!(hw->flags & SKY2_HW_RAM_BUFFER)) { /* Pause threshold is scaled by 8 in bytes */ - if (hw->chip_id == CHIP_ID_YUKON_FE_P - && hw->chip_rev == CHIP_REV_YU_FE2_A0) + if (hw->chip_id == CHIP_ID_YUKON_FE_P && + hw->chip_rev == CHIP_REV_YU_FE2_A0) reg = 1568 / 8; else reg = 1024 / 8; @@ -1353,8 +1353,8 @@ static int sky2_rx_start(struct sky2_port *sky2) /* These chips have no ram buffer? * MAC Rx RAM Read is controlled by hardware */ if (hw->chip_id == CHIP_ID_YUKON_EC_U && - (hw->chip_rev == CHIP_REV_YU_EC_U_A1 - || hw->chip_rev == CHIP_REV_YU_EC_U_B0)) + (hw->chip_rev == CHIP_REV_YU_EC_U_A1 || + hw->chip_rev == CHIP_REV_YU_EC_U_B0)) sky2_write32(hw, Q_ADDR(rxq, Q_TEST), F_M_RX_RAM_DIS); sky2_prefetch_init(hw, rxq, sky2->rx_le_map, RX_LE_SIZE - 1); @@ -1560,8 +1560,8 @@ static int sky2_up(struct net_device *dev) sky2_write32(hw, Q_ADDR(txqaddr[port], Q_TEST), F_TX_CHK_AUTO_OFF); /* Set almost empty threshold */ - if (hw->chip_id == CHIP_ID_YUKON_EC_U - && hw->chip_rev == CHIP_REV_YU_EC_U_A0) + if (hw->chip_id == CHIP_ID_YUKON_EC_U && + hw->chip_rev == CHIP_REV_YU_EC_U_A0) sky2_write16(hw, Q_ADDR(txqaddr[port], Q_AL), ECU_TXFF_LEV); sky2_prefetch_init(hw, txqaddr[port], sky2->tx_le_map, @@ -1907,8 +1907,8 @@ static int sky2_down(struct net_device *dev) sky2_write8(hw, SK_REG(port, GPHY_CTRL), GPC_RST_SET); /* Workaround shared GMAC reset */ - if (!(hw->chip_id == CHIP_ID_YUKON_XL && hw->chip_rev == 0 - && port == 0 && hw->dev[1] && netif_running(hw->dev[1]))) + if (!(hw->chip_id == CHIP_ID_YUKON_XL && hw->chip_rev == 0 && + port == 0 && hw->dev[1] && netif_running(hw->dev[1]))) sky2_write8(hw, SK_REG(port, GMAC_CTRL), GMC_RST_SET); sky2_write8(hw, SK_REG(port, RX_GMF_CTRL_T), GMF_RST_SET); @@ -2085,8 +2085,8 @@ static int sky2_autoneg_done(struct sky2_port *sky2, u16 aux) sky2->flow_status = FC_TX; } - if (sky2->duplex == DUPLEX_HALF && sky2->speed < SPEED_1000 - && !(hw->chip_id == CHIP_ID_YUKON_EC_U || hw->chip_id == CHIP_ID_YUKON_EX)) + if (sky2->duplex == DUPLEX_HALF && sky2->speed < SPEED_1000 && + !(hw->chip_id == CHIP_ID_YUKON_EC_U || hw->chip_id == CHIP_ID_YUKON_EX)) sky2->flow_status = FC_NONE; if (sky2->flow_status & FC_TX) @@ -3244,8 +3244,8 @@ static int sky2_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) struct sky2_port *sky2 = netdev_priv(dev); struct sky2_hw *hw = sky2->hw; - if ((wol->wolopts & ~sky2_wol_supported(sky2->hw)) - || !device_can_wakeup(&hw->pdev->dev)) + if ((wol->wolopts & ~sky2_wol_supported(sky2->hw)) || + !device_can_wakeup(&hw->pdev->dev)) return -EOPNOTSUPP; sky2->wol = wol->wolopts; diff --git a/drivers/net/slip.c b/drivers/net/slip.c index 6640469b5d3b..ba5bbc503446 100644 --- a/drivers/net/slip.c +++ b/drivers/net/slip.c @@ -956,8 +956,8 @@ static void slip_unesc(struct slip *sl, unsigned char s) clear_bit(SLF_KEEPTEST, &sl->flags); #endif - if (!test_and_clear_bit(SLF_ERROR, &sl->flags) - && (sl->rcount > 2)) + if (!test_and_clear_bit(SLF_ERROR, &sl->flags) && + (sl->rcount > 2)) sl_bump(sl); clear_bit(SLF_ESCAPE, &sl->flags); sl->rcount = 0; @@ -1039,8 +1039,8 @@ static void slip_unesc6(struct slip *sl, unsigned char s) clear_bit(SLF_KEEPTEST, &sl->flags); #endif - if (!test_and_clear_bit(SLF_ERROR, &sl->flags) - && (sl->rcount > 2)) + if (!test_and_clear_bit(SLF_ERROR, &sl->flags) && + (sl->rcount > 2)) sl_bump(sl); sl->rcount = 0; sl->xbits = 0; diff --git a/drivers/net/smc-mca.c b/drivers/net/smc-mca.c index c791ef76c1d6..a93f122e9a96 100644 --- a/drivers/net/smc-mca.c +++ b/drivers/net/smc-mca.c @@ -268,9 +268,9 @@ static int __init ultramca_probe(struct device *gen_dev) } } - if(!tirq || !tbase - || (irq && irq != tirq) - || (base_addr && tbase != base_addr)) + if(!tirq || !tbase || + (irq && irq != tirq) || + (base_addr && tbase != base_addr)) /* FIXME: we're trying to force the ordering of the * devices here, there should be a way of getting this * to happen */ diff --git a/drivers/net/smc91x.c b/drivers/net/smc91x.c index 0b56ab468d28..ae4983a5127d 100644 --- a/drivers/net/smc91x.c +++ b/drivers/net/smc91x.c @@ -2283,7 +2283,7 @@ static int __devinit smc_drv_probe(struct platform_device *pdev) ndev->irq = ires->start; - if (ires->flags & IRQF_TRIGGER_MASK) + if (irq_flags == -1 || ires->flags & IRQF_TRIGGER_MASK) irq_flags = ires->flags & IRQF_TRIGGER_MASK; ret = smc_request_attrib(pdev, ndev); @@ -2365,9 +2365,10 @@ static int __devexit smc_drv_remove(struct platform_device *pdev) return 0; } -static int smc_drv_suspend(struct platform_device *dev, pm_message_t state) +static int smc_drv_suspend(struct device *dev) { - struct net_device *ndev = platform_get_drvdata(dev); + struct platform_device *pdev = to_platform_device(dev); + struct net_device *ndev = platform_get_drvdata(pdev); if (ndev) { if (netif_running(ndev)) { @@ -2379,9 +2380,10 @@ static int smc_drv_suspend(struct platform_device *dev, pm_message_t state) return 0; } -static int smc_drv_resume(struct platform_device *dev) +static int smc_drv_resume(struct device *dev) { - struct net_device *ndev = platform_get_drvdata(dev); + struct platform_device *pdev = to_platform_device(dev); + struct net_device *ndev = platform_get_drvdata(pdev); if (ndev) { struct smc_local *lp = netdev_priv(ndev); @@ -2397,14 +2399,18 @@ static int smc_drv_resume(struct platform_device *dev) return 0; } +static struct dev_pm_ops smc_drv_pm_ops = { + .suspend = smc_drv_suspend, + .resume = smc_drv_resume, +}; + static struct platform_driver smc_driver = { .probe = smc_drv_probe, .remove = __devexit_p(smc_drv_remove), - .suspend = smc_drv_suspend, - .resume = smc_drv_resume, .driver = { .name = CARDNAME, .owner = THIS_MODULE, + .pm = &smc_drv_pm_ops, }, }; diff --git a/drivers/net/smc91x.h b/drivers/net/smc91x.h index 3911be7c0cba..7815bfc300f5 100644 --- a/drivers/net/smc91x.h +++ b/drivers/net/smc91x.h @@ -158,8 +158,8 @@ static inline void SMC_outw(u16 val, void __iomem *ioaddr, int reg) #define SMC_outsb(a, r, p, l) writesb((a) + (r), p, (l)) #define SMC_IRQ_FLAGS (-1) /* from resource */ -#elif defined(CONFIG_MACH_LOGICPD_PXA270) \ - || defined(CONFIG_MACH_NOMADIK_8815NHK) +#elif defined(CONFIG_MACH_LOGICPD_PXA270) || \ + defined(CONFIG_MACH_NOMADIK_8815NHK) #define SMC_CAN_USE_8BIT 0 #define SMC_CAN_USE_16BIT 1 @@ -258,9 +258,9 @@ SMC_outw(u16 val, void __iomem *ioaddr, int reg) #define RPC_LSA_DEFAULT RPC_LED_TX_RX #define RPC_LSB_DEFAULT RPC_LED_100_10 -#elif defined(CONFIG_MACH_LPD79520) \ - || defined(CONFIG_MACH_LPD7A400) \ - || defined(CONFIG_MACH_LPD7A404) +#elif defined(CONFIG_MACH_LPD79520) || \ + defined(CONFIG_MACH_LPD7A400) || \ + defined(CONFIG_MACH_LPD7A404) /* The LPD7X_IOBARRIER is necessary to overcome a mismatch between the * way that the CPU handles chip selects and the way that the SMC chip diff --git a/drivers/net/smsc911x.c b/drivers/net/smsc911x.c index 7f01e60d5172..4d0d5c56bed8 100644 --- a/drivers/net/smsc911x.c +++ b/drivers/net/smsc911x.c @@ -748,8 +748,8 @@ static void smsc911x_phy_adjust_link(struct net_device *dev) * usage is 10/100 indicator */ pdata->gpio_setting = smsc911x_reg_read(pdata, GPIO_CFG); - if ((pdata->gpio_setting & GPIO_CFG_LED1_EN_) - && (!pdata->using_extphy)) { + if ((pdata->gpio_setting & GPIO_CFG_LED1_EN_) && + (!pdata->using_extphy)) { /* Force 10/100 LED off, after saving * orginal GPIO configuration */ pdata->gpio_orig_setting = pdata->gpio_setting; diff --git a/drivers/net/smsc9420.c b/drivers/net/smsc9420.c index 92e2bbe6b49b..12f0f5d74e3c 100644 --- a/drivers/net/smsc9420.c +++ b/drivers/net/smsc9420.c @@ -252,6 +252,9 @@ static int smsc9420_ethtool_get_settings(struct net_device *dev, { struct smsc9420_pdata *pd = netdev_priv(dev); + if (!pd->phy_dev) + return -ENODEV; + cmd->maxtxpkt = 1; cmd->maxrxpkt = 1; return phy_ethtool_gset(pd->phy_dev, cmd); @@ -262,6 +265,9 @@ static int smsc9420_ethtool_set_settings(struct net_device *dev, { struct smsc9420_pdata *pd = netdev_priv(dev); + if (!pd->phy_dev) + return -ENODEV; + return phy_ethtool_sset(pd->phy_dev, cmd); } @@ -290,6 +296,10 @@ static void smsc9420_ethtool_set_msglevel(struct net_device *netdev, u32 data) static int smsc9420_ethtool_nway_reset(struct net_device *netdev) { struct smsc9420_pdata *pd = netdev_priv(netdev); + + if (!pd->phy_dev) + return -ENODEV; + return phy_start_aneg(pd->phy_dev); } @@ -312,6 +322,10 @@ smsc9420_ethtool_getregs(struct net_device *dev, struct ethtool_regs *regs, for (i = 0; i < 0x100; i += (sizeof(u32))) data[j++] = smsc9420_reg_read(pd, i); + // cannot read phy registers if the net device is down + if (!phy_dev) + return; + for (i = 0; i <= 31; i++) data[j++] = smsc9420_mii_read(phy_dev->bus, phy_dev->addr, i); } diff --git a/drivers/net/starfire.c b/drivers/net/starfire.c index aa10158adb9e..95db60adde41 100644 --- a/drivers/net/starfire.c +++ b/drivers/net/starfire.c @@ -1482,8 +1482,8 @@ static int __netdev_rx(struct net_device *dev, int *quota) printk(KERN_DEBUG " netdev_rx() normal Rx pkt length %d, quota %d.\n", pkt_len, *quota); /* Check if the packet is long enough to accept without copying to a minimally-sized skbuff. */ - if (pkt_len < rx_copybreak - && (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { + if (pkt_len < rx_copybreak && + (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { skb_reserve(skb, 2); /* 16 byte align the IP header */ pci_dma_sync_single_for_cpu(np->pci_dev, np->rx_info[entry].mapping, @@ -1793,8 +1793,8 @@ static void set_rx_mode(struct net_device *dev) if (dev->flags & IFF_PROMISC) { /* Set promiscuous. */ rx_mode |= AcceptAll; - } else if ((dev->mc_count > multicast_filter_limit) - || (dev->flags & IFF_ALLMULTI)) { + } else if ((dev->mc_count > multicast_filter_limit) || + (dev->flags & IFF_ALLMULTI)) { /* Too many to match, or accept all multicasts. */ rx_mode |= AcceptBroadcast|AcceptAllMulticast|PerfectFilter; } else if (dev->mc_count <= 14) { diff --git a/drivers/net/stmmac/stmmac_main.c b/drivers/net/stmmac/stmmac_main.c index e961e7593c1f..508fba8fa07f 100644 --- a/drivers/net/stmmac/stmmac_main.c +++ b/drivers/net/stmmac/stmmac_main.c @@ -416,13 +416,8 @@ static void init_dma_desc_rings(struct net_device *dev) unsigned int txsize = priv->dma_tx_size; unsigned int rxsize = priv->dma_rx_size; unsigned int bfsize = priv->dma_buf_sz; - int buff2_needed = 0; - int dis_ic = 0; + int buff2_needed = 0, dis_ic = 0; -#ifdef CONFIG_STMMAC_TIMER - /* Using Timers disable interrupts on completion for the reception */ - dis_ic = 1; -#endif /* Set the Buffer size according to the MTU; * indeed, in case of jumbo we need to bump-up the buffer sizes. */ @@ -437,6 +432,11 @@ static void init_dma_desc_rings(struct net_device *dev) else bfsize = DMA_BUFFER_SIZE; +#ifdef CONFIG_STMMAC_TIMER + /* Disable interrupts on completion for the reception if timer is on */ + if (likely(priv->tm->enable)) + dis_ic = 1; +#endif /* If the MTU exceeds 8k so use the second buffer in the chain */ if (bfsize >= BUF_SIZE_8KiB) buff2_needed = 1; @@ -809,20 +809,22 @@ static void stmmac_tx(struct stmmac_priv *priv) static inline void stmmac_enable_irq(struct stmmac_priv *priv) { -#ifndef CONFIG_STMMAC_TIMER - writel(DMA_INTR_DEFAULT_MASK, priv->dev->base_addr + DMA_INTR_ENA); -#else - priv->tm->timer_start(tmrate); +#ifdef CONFIG_STMMAC_TIMER + if (likely(priv->tm->enable)) + priv->tm->timer_start(tmrate); + else #endif + writel(DMA_INTR_DEFAULT_MASK, priv->dev->base_addr + DMA_INTR_ENA); } static inline void stmmac_disable_irq(struct stmmac_priv *priv) { -#ifndef CONFIG_STMMAC_TIMER - writel(0, priv->dev->base_addr + DMA_INTR_ENA); -#else - priv->tm->timer_stop(); +#ifdef CONFIG_STMMAC_TIMER + if (likely(priv->tm->enable)) + priv->tm->timer_stop(); + else #endif + writel(0, priv->dev->base_addr + DMA_INTR_ENA); } static int stmmac_has_work(struct stmmac_priv *priv) @@ -920,8 +922,7 @@ static void stmmac_dma_interrupt(struct net_device *dev) DBG(intr, INFO, "CSR5[15] DMA ABNORMAL IRQ: "); if (unlikely(intr_status & DMA_STATUS_UNF)) { DBG(intr, INFO, "transmit underflow\n"); - if (unlikely(tc != SF_DMA_MODE) - && (tc <= 256)) { + if (unlikely(tc != SF_DMA_MODE) && (tc <= 256)) { /* Try to bump up the threshold */ tc += 64; priv->mac_type->ops->dma_mode(ioaddr, tc, @@ -1031,22 +1032,23 @@ static int stmmac_open(struct net_device *dev) } #ifdef CONFIG_STMMAC_TIMER - priv->tm = kmalloc(sizeof(struct stmmac_timer *), GFP_KERNEL); + priv->tm = kzalloc(sizeof(struct stmmac_timer *), GFP_KERNEL); if (unlikely(priv->tm == NULL)) { pr_err("%s: ERROR: timer memory alloc failed \n", __func__); return -ENOMEM; } priv->tm->freq = tmrate; - /* Test if the HW timer can be actually used. - * In case of failure continue with no timer. */ + /* Test if the external timer can be actually used. + * In case of failure continue without timer. */ if (unlikely((stmmac_open_ext_timer(dev, priv->tm)) < 0)) { - pr_warning("stmmaceth: cannot attach the HW timer\n"); + pr_warning("stmmaceth: cannot attach the external timer.\n"); tmrate = 0; priv->tm->freq = 0; priv->tm->timer_start = stmmac_no_timer_started; priv->tm->timer_stop = stmmac_no_timer_stopped; - } + } else + priv->tm->enable = 1; #endif /* Create and initialize the TX/RX descriptors chains. */ @@ -1322,9 +1324,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) /* Interrupt on completition only for the latest segment */ priv->mac_type->ops->close_tx_desc(desc); + #ifdef CONFIG_STMMAC_TIMER - /* Clean IC while using timers */ - priv->mac_type->ops->clear_tx_ic(desc); + /* Clean IC while using timer */ + if (likely(priv->tm->enable)) + priv->mac_type->ops->clear_tx_ic(desc); #endif /* To avoid raise condition */ priv->mac_type->ops->set_tx_owner(first); @@ -2028,7 +2032,8 @@ static int stmmac_suspend(struct platform_device *pdev, pm_message_t state) #ifdef CONFIG_STMMAC_TIMER priv->tm->timer_stop(); - dis_ic = 1; + if (likely(priv->tm->enable)) + dis_ic = 1; #endif napi_disable(&priv->napi); diff --git a/drivers/net/stmmac/stmmac_timer.c b/drivers/net/stmmac/stmmac_timer.c index b838c6582077..679f61ffb1f8 100644 --- a/drivers/net/stmmac/stmmac_timer.c +++ b/drivers/net/stmmac/stmmac_timer.c @@ -63,7 +63,7 @@ int stmmac_open_ext_timer(struct net_device *dev, struct stmmac_timer *tm) stmmac_rtc = rtc_class_open(CONFIG_RTC_HCTOSYS_DEVICE); if (stmmac_rtc == NULL) { - pr_error("open rtc device failed\n"); + pr_err("open rtc device failed\n"); return -ENODEV; } @@ -71,7 +71,7 @@ int stmmac_open_ext_timer(struct net_device *dev, struct stmmac_timer *tm) /* Periodic mode is not supported */ if ((rtc_irq_set_freq(stmmac_rtc, &stmmac_task, tm->freq) < 0)) { - pr_error("set periodic failed\n"); + pr_err("set periodic failed\n"); rtc_irq_unregister(stmmac_rtc, &stmmac_task); rtc_class_close(stmmac_rtc); return -1; diff --git a/drivers/net/stmmac/stmmac_timer.h b/drivers/net/stmmac/stmmac_timer.h index f795cae33725..6863590d184b 100644 --- a/drivers/net/stmmac/stmmac_timer.h +++ b/drivers/net/stmmac/stmmac_timer.h @@ -26,6 +26,7 @@ struct stmmac_timer { void (*timer_start) (unsigned int new_freq); void (*timer_stop) (void); unsigned int freq; + unsigned int enable; }; /* Open the HW timer device and return 0 in case of success */ diff --git a/drivers/net/sundance.c b/drivers/net/sundance.c index 5c396c2e6e76..d58e1891ca60 100644 --- a/drivers/net/sundance.c +++ b/drivers/net/sundance.c @@ -603,8 +603,8 @@ static int __devinit sundance_probe1 (struct pci_dev *pdev, strcmp (media[card_idx], "4") == 0) { np->speed = 100; np->mii_if.full_duplex = 1; - } else if (strcmp (media[card_idx], "100mbps_hd") == 0 - || strcmp (media[card_idx], "3") == 0) { + } else if (strcmp (media[card_idx], "100mbps_hd") == 0 || + strcmp (media[card_idx], "3") == 0) { np->speed = 100; np->mii_if.full_duplex = 0; } else if (strcmp (media[card_idx], "10mbps_fd") == 0 || @@ -1079,8 +1079,8 @@ start_tx (struct sk_buff *skb, struct net_device *dev) tasklet_schedule(&np->tx_tasklet); /* On some architectures: explicitly flush cache lines here. */ - if (np->cur_tx - np->dirty_tx < TX_QUEUE_LEN - 1 - && !netif_queue_stopped(dev)) { + if (np->cur_tx - np->dirty_tx < TX_QUEUE_LEN - 1 && + !netif_queue_stopped(dev)) { /* do nothing */ } else { netif_stop_queue (dev); @@ -1336,8 +1336,8 @@ static void rx_poll(unsigned long data) #endif /* Check if the packet is long enough to accept without copying to a minimally-sized skbuff. */ - if (pkt_len < rx_copybreak - && (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { + if (pkt_len < rx_copybreak && + (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { skb_reserve(skb, 2); /* 16 byte align the IP header */ pci_dma_sync_single_for_cpu(np->pci_dev, le32_to_cpu(desc->frag[0].addr), @@ -1517,8 +1517,8 @@ static void set_rx_mode(struct net_device *dev) if (dev->flags & IFF_PROMISC) { /* Set promiscuous. */ memset(mc_filter, 0xff, sizeof(mc_filter)); rx_mode = AcceptBroadcast | AcceptMulticast | AcceptAll | AcceptMyPhys; - } else if ((dev->mc_count > multicast_filter_limit) - || (dev->flags & IFF_ALLMULTI)) { + } else if ((dev->mc_count > multicast_filter_limit) || + (dev->flags & IFF_ALLMULTI)) { /* Too many to match, or accept all multicasts. */ memset(mc_filter, 0xff, sizeof(mc_filter)); rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys; diff --git a/drivers/net/sungem.h b/drivers/net/sungem.h index f7a02917ce5e..19905460def6 100644 --- a/drivers/net/sungem.h +++ b/drivers/net/sungem.h @@ -1031,8 +1031,8 @@ struct gem { #endif }; -#define found_mii_phy(gp) ((gp->phy_type == phy_mii_mdio0 || gp->phy_type == phy_mii_mdio1) \ - && gp->phy_mii.def && gp->phy_mii.def->ops) +#define found_mii_phy(gp) ((gp->phy_type == phy_mii_mdio0 || gp->phy_type == phy_mii_mdio1) && \ + gp->phy_mii.def && gp->phy_mii.def->ops) #define ALIGNED_RX_SKB_ADDR(addr) \ ((((unsigned long)(addr) + (64UL - 1UL)) & ~(64UL - 1UL)) - (unsigned long)(addr)) diff --git a/drivers/net/sunhme.c b/drivers/net/sunhme.c index 1f842a78acd1..6762f1c6ec8a 100644 --- a/drivers/net/sunhme.c +++ b/drivers/net/sunhme.c @@ -1226,10 +1226,16 @@ static void happy_meal_clean_rings(struct happy_meal *hp) for (frag = 0; frag <= skb_shinfo(skb)->nr_frags; frag++) { txd = &hp->happy_block->happy_meal_txd[i]; dma_addr = hme_read_desc32(hp, &txd->tx_addr); - dma_unmap_single(hp->dma_dev, dma_addr, - (hme_read_desc32(hp, &txd->tx_flags) - & TXFLAG_SIZE), - DMA_TO_DEVICE); + if (!frag) + dma_unmap_single(hp->dma_dev, dma_addr, + (hme_read_desc32(hp, &txd->tx_flags) + & TXFLAG_SIZE), + DMA_TO_DEVICE); + else + dma_unmap_page(hp->dma_dev, dma_addr, + (hme_read_desc32(hp, &txd->tx_flags) + & TXFLAG_SIZE), + DMA_TO_DEVICE); if (frag != skb_shinfo(skb)->nr_frags) i++; @@ -1953,7 +1959,10 @@ static void happy_meal_tx(struct happy_meal *hp) dma_len = hme_read_desc32(hp, &this->tx_flags); dma_len &= TXFLAG_SIZE; - dma_unmap_single(hp->dma_dev, dma_addr, dma_len, DMA_TO_DEVICE); + if (!frag) + dma_unmap_single(hp->dma_dev, dma_addr, dma_len, DMA_TO_DEVICE); + else + dma_unmap_page(hp->dma_dev, dma_addr, dma_len, DMA_TO_DEVICE); elem = NEXT_TX(elem); this = &txbase[elem]; @@ -3047,9 +3056,9 @@ static int __devinit happy_meal_pci_probe(struct pci_dev *pdev, int len; if (qfe_slot != -1 && - (addr = of_get_property(dp, - "local-mac-address", &len)) != NULL - && len == 6) { + (addr = of_get_property(dp, "local-mac-address", &len)) + != NULL && + len == 6) { memcpy(dev->dev_addr, addr, 6); } else { memcpy(dev->dev_addr, idprom->id_ethaddr, 6); diff --git a/drivers/net/tehuti.c b/drivers/net/tehuti.c index 2fbac31767fa..80b404f2b938 100644 --- a/drivers/net/tehuti.c +++ b/drivers/net/tehuti.c @@ -1784,9 +1784,9 @@ static void bdx_tx_cleanup(struct bdx_priv *priv) } #endif - if (unlikely(netif_queue_stopped(priv->ndev) - && netif_carrier_ok(priv->ndev) - && (priv->tx_level >= BDX_MIN_TX_LEVEL))) { + if (unlikely(netif_queue_stopped(priv->ndev) && + netif_carrier_ok(priv->ndev) && + (priv->tx_level >= BDX_MIN_TX_LEVEL))) { DBG("%s: %s: TX Q WAKE level %d\n", BDX_DRV_NAME, priv->ndev->name, priv->tx_level); netif_wake_queue(priv->ndev); @@ -2273,8 +2273,8 @@ bdx_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ecoal) (((tx_max_coal * BDX_TXF_DESC_SZ) + PCK_TH_MULT - 1) / PCK_TH_MULT); - if ((rx_coal > 0x7FFF) || (tx_coal > 0x7FFF) - || (rx_max_coal > 0xF) || (tx_max_coal > 0xF)) + if ((rx_coal > 0x7FFF) || (tx_coal > 0x7FFF) || + (rx_max_coal > 0xF) || (tx_max_coal > 0xF)) return -EINVAL; rdintcm = INT_REG_VAL(rx_coal, GET_INT_COAL_RC(priv->rdintcm), @@ -2347,8 +2347,8 @@ bdx_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) tx_size = 3; /*Is there anything to do? */ - if ((rx_size == priv->rxf_size) - && (tx_size == priv->txd_size)) + if ((rx_size == priv->rxf_size) && + (tx_size == priv->txd_size)) return 0; priv->rxf_size = rx_size; diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index 6e6db955b4a9..3a74d2168598 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -68,8 +68,8 @@ #define DRV_MODULE_NAME "tg3" #define PFX DRV_MODULE_NAME ": " -#define DRV_MODULE_VERSION "3.104" -#define DRV_MODULE_RELDATE "November 13, 2009" +#define DRV_MODULE_VERSION "3.105" +#define DRV_MODULE_RELDATE "December 2, 2009" #define TG3_DEF_MAC_MODE 0 #define TG3_DEF_RX_MODE 0 @@ -4351,13 +4351,13 @@ static void tg3_tx(struct tg3_napi *tnapi) struct netdev_queue *txq; int index = tnapi - tp->napi; - if (tp->tg3_flags2 & TG3_FLG2_USING_MSIX) + if (tp->tg3_flags3 & TG3_FLG3_ENABLE_TSS) index--; txq = netdev_get_tx_queue(tp->dev, index); while (sw_idx != hw_idx) { - struct tx_ring_info *ri = &tnapi->tx_buffers[sw_idx]; + struct ring_info *ri = &tnapi->tx_buffers[sw_idx]; struct sk_buff *skb = ri->skb; int i, tx_bug = 0; @@ -4366,7 +4366,10 @@ static void tg3_tx(struct tg3_napi *tnapi) return; } - skb_dma_unmap(&tp->pdev->dev, skb, DMA_TO_DEVICE); + pci_unmap_single(tp->pdev, + pci_unmap_addr(ri, mapping), + skb_headlen(skb), + PCI_DMA_TODEVICE); ri->skb = NULL; @@ -4376,6 +4379,11 @@ static void tg3_tx(struct tg3_napi *tnapi) ri = &tnapi->tx_buffers[sw_idx]; if (unlikely(ri->skb != NULL || sw_idx == hw_idx)) tx_bug = 1; + + pci_unmap_page(tp->pdev, + pci_unmap_addr(ri, mapping), + skb_shinfo(skb)->frags[i].size, + PCI_DMA_TODEVICE); sw_idx = NEXT_TX(sw_idx); } @@ -4613,13 +4621,12 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget) len = ((desc->idx_len & RXD_LEN_MASK) >> RXD_LEN_SHIFT) - ETH_FCS_LEN; - if (len > RX_COPY_THRESHOLD - && tp->rx_offset == NET_IP_ALIGN - /* rx_offset will likely not equal NET_IP_ALIGN - * if this is a 5701 card running in PCI-X mode - * [see tg3_get_invariants()] - */ - ) { + if (len > RX_COPY_THRESHOLD && + tp->rx_offset == NET_IP_ALIGN) { + /* rx_offset will likely not equal NET_IP_ALIGN + * if this is a 5701 card running in PCI-X mode + * [see tg3_get_invariants()] + */ int skb_size; skb_size = tg3_alloc_rx_skb(tp, tpr, opaque_key, @@ -5334,17 +5341,21 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi, } else { /* New SKB is guaranteed to be linear. */ entry = *start; - ret = skb_dma_map(&tp->pdev->dev, new_skb, DMA_TO_DEVICE); - new_addr = skb_shinfo(new_skb)->dma_head; + new_addr = pci_map_single(tp->pdev, new_skb->data, new_skb->len, + PCI_DMA_TODEVICE); + /* Make sure the mapping succeeded */ + if (pci_dma_mapping_error(tp->pdev, new_addr)) { + ret = -1; + dev_kfree_skb(new_skb); + new_skb = NULL; /* Make sure new skb does not cross any 4G boundaries. * Drop the packet if it does. */ - if (ret || ((tp->tg3_flags3 & TG3_FLG3_4G_DMA_BNDRY_BUG) && - tg3_4g_overflow_test(new_addr, new_skb->len))) { - if (!ret) - skb_dma_unmap(&tp->pdev->dev, new_skb, - DMA_TO_DEVICE); + } else if ((tp->tg3_flags3 & TG3_FLG3_4G_DMA_BNDRY_BUG) && + tg3_4g_overflow_test(new_addr, new_skb->len)) { + pci_unmap_single(tp->pdev, new_addr, new_skb->len, + PCI_DMA_TODEVICE); ret = -1; dev_kfree_skb(new_skb); new_skb = NULL; @@ -5358,15 +5369,28 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi, /* Now clean up the sw ring entries. */ i = 0; while (entry != last_plus_one) { + int len; + if (i == 0) - tnapi->tx_buffers[entry].skb = new_skb; + len = skb_headlen(skb); else + len = skb_shinfo(skb)->frags[i-1].size; + + pci_unmap_single(tp->pdev, + pci_unmap_addr(&tnapi->tx_buffers[entry], + mapping), + len, PCI_DMA_TODEVICE); + if (i == 0) { + tnapi->tx_buffers[entry].skb = new_skb; + pci_unmap_addr_set(&tnapi->tx_buffers[entry], mapping, + new_addr); + } else { tnapi->tx_buffers[entry].skb = NULL; + } entry = NEXT_TX(entry); i++; } - skb_dma_unmap(&tp->pdev->dev, skb, DMA_TO_DEVICE); dev_kfree_skb(skb); return ret; @@ -5403,14 +5427,15 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, { struct tg3 *tp = netdev_priv(dev); u32 len, entry, base_flags, mss; - struct skb_shared_info *sp; dma_addr_t mapping; struct tg3_napi *tnapi; struct netdev_queue *txq; + unsigned int i, last; + txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); tnapi = &tp->napi[skb_get_queue_mapping(skb)]; - if (tp->tg3_flags2 & TG3_FLG2_USING_MSIX) + if (tp->tg3_flags3 & TG3_FLG3_ENABLE_TSS) tnapi++; /* We are running in BH disabled context with netif_tx_lock @@ -5477,20 +5502,19 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, (vlan_tx_tag_get(skb) << 16)); #endif - if (skb_dma_map(&tp->pdev->dev, skb, DMA_TO_DEVICE)) { + len = skb_headlen(skb); + + /* Queue skb data, a.k.a. the main skb fragment. */ + mapping = pci_map_single(tp->pdev, skb->data, len, PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(tp->pdev, mapping)) { dev_kfree_skb(skb); goto out_unlock; } - sp = skb_shinfo(skb); - - mapping = sp->dma_head; - tnapi->tx_buffers[entry].skb = skb; + pci_unmap_addr_set(&tnapi->tx_buffers[entry], mapping, mapping); - len = skb_headlen(skb); - - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 && + if ((tp->tg3_flags3 & TG3_FLG3_USE_JUMBO_BDFLAG) && !mss && skb->len > ETH_DATA_LEN) base_flags |= TXD_FLAG_JMB_PKT; @@ -5501,15 +5525,21 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, /* Now loop through additional data fragments, and queue them. */ if (skb_shinfo(skb)->nr_frags > 0) { - unsigned int i, last; - last = skb_shinfo(skb)->nr_frags - 1; for (i = 0; i <= last; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; len = frag->size; - mapping = sp->dma_maps[i]; + mapping = pci_map_page(tp->pdev, + frag->page, + frag->page_offset, + len, PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(tp->pdev, mapping)) + goto dma_error; + tnapi->tx_buffers[entry].skb = NULL; + pci_unmap_addr_set(&tnapi->tx_buffers[entry], mapping, + mapping); tg3_set_txd(tnapi, entry, mapping, len, base_flags, (i == last) | (mss << 1)); @@ -5532,6 +5562,27 @@ out_unlock: mmiowb(); return NETDEV_TX_OK; + +dma_error: + last = i; + entry = tnapi->tx_prod; + tnapi->tx_buffers[entry].skb = NULL; + pci_unmap_single(tp->pdev, + pci_unmap_addr(&tnapi->tx_buffers[entry], mapping), + skb_headlen(skb), + PCI_DMA_TODEVICE); + for (i = 0; i <= last; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + entry = NEXT_TX(entry); + + pci_unmap_page(tp->pdev, + pci_unmap_addr(&tnapi->tx_buffers[entry], + mapping), + frag->size, PCI_DMA_TODEVICE); + } + + dev_kfree_skb(skb); + return NETDEV_TX_OK; } static netdev_tx_t tg3_start_xmit_dma_bug(struct sk_buff *, @@ -5579,15 +5630,16 @@ static netdev_tx_t tg3_start_xmit_dma_bug(struct sk_buff *skb, { struct tg3 *tp = netdev_priv(dev); u32 len, entry, base_flags, mss; - struct skb_shared_info *sp; int would_hit_hwbug; dma_addr_t mapping; struct tg3_napi *tnapi; struct netdev_queue *txq; + unsigned int i, last; + txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); tnapi = &tp->napi[skb_get_queue_mapping(skb)]; - if (tp->tg3_flags2 & TG3_FLG2_USING_MSIX) + if (tp->tg3_flags3 & TG3_FLG3_ENABLE_TSS) tnapi++; /* We are running in BH disabled context with netif_tx_lock @@ -5674,25 +5726,23 @@ static netdev_tx_t tg3_start_xmit_dma_bug(struct sk_buff *skb, (vlan_tx_tag_get(skb) << 16)); #endif - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 && + if ((tp->tg3_flags3 & TG3_FLG3_USE_JUMBO_BDFLAG) && !mss && skb->len > ETH_DATA_LEN) base_flags |= TXD_FLAG_JMB_PKT; - if (skb_dma_map(&tp->pdev->dev, skb, DMA_TO_DEVICE)) { + len = skb_headlen(skb); + + mapping = pci_map_single(tp->pdev, skb->data, len, PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(tp->pdev, mapping)) { dev_kfree_skb(skb); goto out_unlock; } - sp = skb_shinfo(skb); - - mapping = sp->dma_head; - tnapi->tx_buffers[entry].skb = skb; + pci_unmap_addr_set(&tnapi->tx_buffers[entry], mapping, mapping); would_hit_hwbug = 0; - len = skb_headlen(skb); - if ((tp->tg3_flags3 & TG3_FLG3_SHORT_DMA_BUG) && len <= 8) would_hit_hwbug = 1; @@ -5714,16 +5764,21 @@ static netdev_tx_t tg3_start_xmit_dma_bug(struct sk_buff *skb, /* Now loop through additional data fragments, and queue them. */ if (skb_shinfo(skb)->nr_frags > 0) { - unsigned int i, last; - last = skb_shinfo(skb)->nr_frags - 1; for (i = 0; i <= last; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; len = frag->size; - mapping = sp->dma_maps[i]; + mapping = pci_map_page(tp->pdev, + frag->page, + frag->page_offset, + len, PCI_DMA_TODEVICE); tnapi->tx_buffers[entry].skb = NULL; + pci_unmap_addr_set(&tnapi->tx_buffers[entry], mapping, + mapping); + if (pci_dma_mapping_error(tp->pdev, mapping)) + goto dma_error; if ((tp->tg3_flags3 & TG3_FLG3_SHORT_DMA_BUG) && len <= 8) @@ -5779,6 +5834,27 @@ out_unlock: mmiowb(); return NETDEV_TX_OK; + +dma_error: + last = i; + entry = tnapi->tx_prod; + tnapi->tx_buffers[entry].skb = NULL; + pci_unmap_single(tp->pdev, + pci_unmap_addr(&tnapi->tx_buffers[entry], mapping), + skb_headlen(skb), + PCI_DMA_TODEVICE); + for (i = 0; i <= last; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + entry = NEXT_TX(entry); + + pci_unmap_page(tp->pdev, + pci_unmap_addr(&tnapi->tx_buffers[entry], + mapping), + frag->size, PCI_DMA_TODEVICE); + } + + dev_kfree_skb(skb); + return NETDEV_TX_OK; } static inline void tg3_set_mtu(struct net_device *dev, struct tg3 *tp, @@ -6046,8 +6122,9 @@ static void tg3_free_rings(struct tg3 *tp) continue; for (i = 0; i < TG3_TX_RING_SIZE; ) { - struct tx_ring_info *txp; + struct ring_info *txp; struct sk_buff *skb; + unsigned int k; txp = &tnapi->tx_buffers[i]; skb = txp->skb; @@ -6057,11 +6134,22 @@ static void tg3_free_rings(struct tg3 *tp) continue; } - skb_dma_unmap(&tp->pdev->dev, skb, DMA_TO_DEVICE); - + pci_unmap_single(tp->pdev, + pci_unmap_addr(txp, mapping), + skb_headlen(skb), + PCI_DMA_TODEVICE); txp->skb = NULL; - i += skb_shinfo(skb)->nr_frags + 1; + i++; + + for (k = 0; k < skb_shinfo(skb)->nr_frags; k++) { + txp = &tnapi->tx_buffers[i & (TG3_TX_RING_SIZE - 1)]; + pci_unmap_page(tp->pdev, + pci_unmap_addr(txp, mapping), + skb_shinfo(skb)->frags[k].size, + PCI_DMA_TODEVICE); + i++; + } dev_kfree_skb_any(skb); } @@ -6190,6 +6278,24 @@ static int tg3_alloc_consistent(struct tg3 *tp) memset(tnapi->hw_status, 0, TG3_HW_STATUS_SIZE); sblk = tnapi->hw_status; + /* If multivector TSS is enabled, vector 0 does not handle + * tx interrupts. Don't allocate any resources for it. + */ + if ((!i && !(tp->tg3_flags3 & TG3_FLG3_ENABLE_TSS)) || + (i && (tp->tg3_flags3 & TG3_FLG3_ENABLE_TSS))) { + tnapi->tx_buffers = kzalloc(sizeof(struct ring_info) * + TG3_TX_RING_SIZE, + GFP_KERNEL); + if (!tnapi->tx_buffers) + goto err_out; + + tnapi->tx_ring = pci_alloc_consistent(tp->pdev, + TG3_TX_RING_BYTES, + &tnapi->tx_desc_mapping); + if (!tnapi->tx_ring) + goto err_out; + } + /* * When RSS is enabled, the status block format changes * slightly. The "rx_jumbo_consumer", "reserved", @@ -6230,17 +6336,6 @@ static int tg3_alloc_consistent(struct tg3 *tp) goto err_out; memset(tnapi->rx_rcb, 0, TG3_RX_RCB_RING_BYTES(tp)); - - tnapi->tx_buffers = kzalloc(sizeof(struct tx_ring_info) * - TG3_TX_RING_SIZE, GFP_KERNEL); - if (!tnapi->tx_buffers) - goto err_out; - - tnapi->tx_ring = pci_alloc_consistent(tp->pdev, - TG3_TX_RING_BYTES, - &tnapi->tx_desc_mapping); - if (!tnapi->tx_ring) - goto err_out; } return 0; @@ -6876,7 +6971,8 @@ static int tg3_chip_reset(struct tg3 *tp) if ((tp->tg3_flags2 & TG3_FLG2_PCI_EXPRESS) && tp->pci_chip_rev_id != CHIPREV_ID_5750_A0 && GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5785 && - GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5717) { + GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5717 && + GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_57765) { val = tr32(0x7c00); tw32(0x7c00, val | (1 << 25)); @@ -7228,19 +7324,21 @@ static void __tg3_set_coalesce(struct tg3 *tp, struct ethtool_coalesce *ec) { int i; - if (!(tp->tg3_flags2 & TG3_FLG2_USING_MSIX)) { + if (!(tp->tg3_flags3 & TG3_FLG3_ENABLE_TSS)) { tw32(HOSTCC_TXCOL_TICKS, ec->tx_coalesce_usecs); tw32(HOSTCC_TXMAX_FRAMES, ec->tx_max_coalesced_frames); tw32(HOSTCC_TXCOAL_MAXF_INT, ec->tx_max_coalesced_frames_irq); - - tw32(HOSTCC_RXCOL_TICKS, ec->rx_coalesce_usecs); - tw32(HOSTCC_RXMAX_FRAMES, ec->rx_max_coalesced_frames); - tw32(HOSTCC_RXCOAL_MAXF_INT, ec->rx_max_coalesced_frames_irq); } else { tw32(HOSTCC_TXCOL_TICKS, 0); tw32(HOSTCC_TXMAX_FRAMES, 0); tw32(HOSTCC_TXCOAL_MAXF_INT, 0); + } + if (!(tp->tg3_flags2 & TG3_FLG2_USING_MSIX)) { + tw32(HOSTCC_RXCOL_TICKS, ec->rx_coalesce_usecs); + tw32(HOSTCC_RXMAX_FRAMES, ec->rx_max_coalesced_frames); + tw32(HOSTCC_RXCOAL_MAXF_INT, ec->rx_max_coalesced_frames_irq); + } else { tw32(HOSTCC_RXCOL_TICKS, 0); tw32(HOSTCC_RXMAX_FRAMES, 0); tw32(HOSTCC_RXCOAL_MAXF_INT, 0); @@ -7263,25 +7361,31 @@ static void __tg3_set_coalesce(struct tg3 *tp, struct ethtool_coalesce *ec) reg = HOSTCC_RXCOL_TICKS_VEC1 + i * 0x18; tw32(reg, ec->rx_coalesce_usecs); - reg = HOSTCC_TXCOL_TICKS_VEC1 + i * 0x18; - tw32(reg, ec->tx_coalesce_usecs); reg = HOSTCC_RXMAX_FRAMES_VEC1 + i * 0x18; tw32(reg, ec->rx_max_coalesced_frames); - reg = HOSTCC_TXMAX_FRAMES_VEC1 + i * 0x18; - tw32(reg, ec->tx_max_coalesced_frames); reg = HOSTCC_RXCOAL_MAXF_INT_VEC1 + i * 0x18; tw32(reg, ec->rx_max_coalesced_frames_irq); - reg = HOSTCC_TXCOAL_MAXF_INT_VEC1 + i * 0x18; - tw32(reg, ec->tx_max_coalesced_frames_irq); + + if (tp->tg3_flags3 & TG3_FLG3_ENABLE_TSS) { + reg = HOSTCC_TXCOL_TICKS_VEC1 + i * 0x18; + tw32(reg, ec->tx_coalesce_usecs); + reg = HOSTCC_TXMAX_FRAMES_VEC1 + i * 0x18; + tw32(reg, ec->tx_max_coalesced_frames); + reg = HOSTCC_TXCOAL_MAXF_INT_VEC1 + i * 0x18; + tw32(reg, ec->tx_max_coalesced_frames_irq); + } } for (; i < tp->irq_max - 1; i++) { tw32(HOSTCC_RXCOL_TICKS_VEC1 + i * 0x18, 0); - tw32(HOSTCC_TXCOL_TICKS_VEC1 + i * 0x18, 0); tw32(HOSTCC_RXMAX_FRAMES_VEC1 + i * 0x18, 0); - tw32(HOSTCC_TXMAX_FRAMES_VEC1 + i * 0x18, 0); tw32(HOSTCC_RXCOAL_MAXF_INT_VEC1 + i * 0x18, 0); - tw32(HOSTCC_TXCOAL_MAXF_INT_VEC1 + i * 0x18, 0); + + if (tp->tg3_flags3 & TG3_FLG3_ENABLE_TSS) { + tw32(HOSTCC_TXCOL_TICKS_VEC1 + i * 0x18, 0); + tw32(HOSTCC_TXMAX_FRAMES_VEC1 + i * 0x18, 0); + tw32(HOSTCC_TXCOAL_MAXF_INT_VEC1 + i * 0x18, 0); + } } } @@ -7295,6 +7399,8 @@ static void tg3_rings_reset(struct tg3 *tp) /* Disable all transmit rings but the first. */ if (!(tp->tg3_flags2 & TG3_FLG2_5705_PLUS)) limit = NIC_SRAM_SEND_RCB + TG3_BDINFO_SIZE * 16; + else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) + limit = NIC_SRAM_SEND_RCB + TG3_BDINFO_SIZE * 2; else limit = NIC_SRAM_SEND_RCB + TG3_BDINFO_SIZE; @@ -7309,7 +7415,8 @@ static void tg3_rings_reset(struct tg3 *tp) limit = NIC_SRAM_RCV_RET_RCB + TG3_BDINFO_SIZE * 17; else if (!(tp->tg3_flags2 & TG3_FLG2_5705_PLUS)) limit = NIC_SRAM_RCV_RET_RCB + TG3_BDINFO_SIZE * 16; - else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5755) + else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5755 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) limit = NIC_SRAM_RCV_RET_RCB + TG3_BDINFO_SIZE * 4; else limit = NIC_SRAM_RCV_RET_RCB + TG3_BDINFO_SIZE; @@ -7382,17 +7489,19 @@ static void tg3_rings_reset(struct tg3 *tp) /* Clear status block in ram. */ memset(tnapi->hw_status, 0, TG3_HW_STATUS_SIZE); - tg3_set_bdinfo(tp, txrcb, tnapi->tx_desc_mapping, - (TG3_TX_RING_SIZE << - BDINFO_FLAGS_MAXLEN_SHIFT), - NIC_SRAM_TX_BUFFER_DESC); + if (tnapi->tx_ring) { + tg3_set_bdinfo(tp, txrcb, tnapi->tx_desc_mapping, + (TG3_TX_RING_SIZE << + BDINFO_FLAGS_MAXLEN_SHIFT), + NIC_SRAM_TX_BUFFER_DESC); + txrcb += TG3_BDINFO_SIZE; + } tg3_set_bdinfo(tp, rxrcb, tnapi->rx_rcb_mapping, (TG3_RX_RCB_RING_SIZE(tp) << BDINFO_FLAGS_MAXLEN_SHIFT), 0); stblk += 8; - txrcb += TG3_BDINFO_SIZE; rxrcb += TG3_BDINFO_SIZE; } } @@ -7504,7 +7613,8 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) if (err) return err; - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717) { + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) { val = tr32(TG3PCI_DMA_RW_CTRL) & ~DMA_RWCTRL_DIS_CACHE_ALIGNMENT; tw32(TG3PCI_DMA_RW_CTRL, val | tp->dma_rwctrl); @@ -7665,7 +7775,8 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) BDINFO_FLAGS_DISABLED); } - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717) + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) val = (RX_STD_MAX_SIZE_5705 << BDINFO_FLAGS_MAXLEN_SHIFT) | (RX_STD_MAX_SIZE << 2); else @@ -7682,7 +7793,8 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) tp->rx_jumbo_pending : 0; tw32_rx_mbox(TG3_RX_JMB_PROD_IDX_REG, tpr->rx_jmb_prod_idx); - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717) { + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) { tw32(STD_REPLENISH_LWM, 32); tw32(JMB_REPLENISH_LWM, 16); } @@ -7935,7 +8047,7 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) if (tp->tg3_flags2 & TG3_FLG2_HW_TSO) tw32(SNDDATAI_MODE, SNDDATAI_MODE_ENABLE | 0x8); val = SNDBDI_MODE_ENABLE | SNDBDI_MODE_ATTN_ENABLE; - if (tp->tg3_flags2 & TG3_FLG2_USING_MSIX) + if (tp->tg3_flags3 & TG3_FLG3_ENABLE_TSS) val |= SNDBDI_MODE_MULTI_TXQ_EN; tw32(SNDBDI_MODE, val); tw32(SNDBDS_MODE, SNDBDS_MODE_ENABLE | SNDBDS_MODE_ATTN_ENABLE); @@ -8359,7 +8471,8 @@ static int tg3_test_interrupt(struct tg3 *tp) * Turn off MSI one shot mode. Otherwise this test has no * observable way to know whether the interrupt was delivered. */ - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 && + if ((GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) && (tp->tg3_flags2 & TG3_FLG2_USING_MSI)) { val = tr32(MSGINT_MODE) | MSGINT_MODE_ONE_SHOT_DISABLE; tw32(MSGINT_MODE, val); @@ -8402,7 +8515,8 @@ static int tg3_test_interrupt(struct tg3 *tp) if (intr_ok) { /* Reenable MSI one shot mode. */ - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 && + if ((GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) && (tp->tg3_flags2 & TG3_FLG2_USING_MSI)) { val = tr32(MSGINT_MODE) & ~MSGINT_MODE_ONE_SHOT_DISABLE; tw32(MSGINT_MODE, val); @@ -8543,7 +8657,11 @@ static bool tg3_enable_msix(struct tg3 *tp) for (i = 0; i < tp->irq_max; i++) tp->napi[i].irq_vec = msix_ent[i].vector; - tp->dev->real_num_tx_queues = tp->irq_cnt - 1; + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717) { + tp->tg3_flags3 |= TG3_FLG3_ENABLE_TSS; + tp->dev->real_num_tx_queues = tp->irq_cnt - 1; + } else + tp->dev->real_num_tx_queues = 1; return true; } @@ -8694,6 +8812,7 @@ static int tg3_open(struct net_device *dev) } if (GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5717 && + GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_57765 && (tp->tg3_flags2 & TG3_FLG2_USING_MSI) && (tp->tg3_flags2 & TG3_FLG2_1SHOT_MSI)) { u32 val = tr32(PCIE_TRANSACTION_CFG); @@ -10637,7 +10756,8 @@ static int tg3_run_loopback(struct tg3 *tp, int loopback_mode) for (i = 14; i < tx_len; i++) tx_data[i] = (u8) (i & 0xff); - if (skb_dma_map(&tp->pdev->dev, skb, DMA_TO_DEVICE)) { + map = pci_map_single(tp->pdev, skb->data, tx_len, PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(tp->pdev, map)) { dev_kfree_skb(skb); return -EIO; } @@ -10651,8 +10771,7 @@ static int tg3_run_loopback(struct tg3 *tp, int loopback_mode) num_pkts = 0; - tg3_set_txd(tnapi, tnapi->tx_prod, - skb_shinfo(skb)->dma_head, tx_len, 0, 1); + tg3_set_txd(tnapi, tnapi->tx_prod, map, tx_len, 0, 1); tnapi->tx_prod++; num_pkts++; @@ -10676,7 +10795,7 @@ static int tg3_run_loopback(struct tg3 *tp, int loopback_mode) break; } - skb_dma_unmap(&tp->pdev->dev, skb, DMA_TO_DEVICE); + pci_unmap_single(tp->pdev, map, tx_len, PCI_DMA_TODEVICE); dev_kfree_skb(skb); if (tx_idx != tnapi->tx_prod) @@ -11588,7 +11707,8 @@ static void __devinit tg3_nvram_init(struct tg3 *tp) tg3_get_5761_nvram_info(tp); else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906) tg3_get_5906_nvram_info(tp); - else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57780) + else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57780 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) tg3_get_57780_nvram_info(tp); else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717) tg3_get_5717_nvram_info(tp); @@ -12313,7 +12433,7 @@ skip_phy_reset: static void __devinit tg3_read_partno(struct tg3 *tp) { - unsigned char vpd_data[256]; /* in little-endian format */ + unsigned char vpd_data[TG3_NVM_VPD_LEN]; /* in little-endian format */ unsigned int i; u32 magic; @@ -12322,48 +12442,37 @@ static void __devinit tg3_read_partno(struct tg3 *tp) goto out_not_found; if (magic == TG3_EEPROM_MAGIC) { - for (i = 0; i < 256; i += 4) { + for (i = 0; i < TG3_NVM_VPD_LEN; i += 4) { u32 tmp; /* The data is in little-endian format in NVRAM. * Use the big-endian read routines to preserve * the byte order as it exists in NVRAM. */ - if (tg3_nvram_read_be32(tp, 0x100 + i, &tmp)) + if (tg3_nvram_read_be32(tp, TG3_NVM_VPD_OFF + i, &tmp)) goto out_not_found; memcpy(&vpd_data[i], &tmp, sizeof(tmp)); } } else { - int vpd_cap; - - vpd_cap = pci_find_capability(tp->pdev, PCI_CAP_ID_VPD); - for (i = 0; i < 256; i += 4) { - u32 tmp, j = 0; - __le32 v; - u16 tmp16; - - pci_write_config_word(tp->pdev, vpd_cap + PCI_VPD_ADDR, - i); - while (j++ < 100) { - pci_read_config_word(tp->pdev, vpd_cap + - PCI_VPD_ADDR, &tmp16); - if (tmp16 & 0x8000) - break; - msleep(1); - } - if (!(tmp16 & 0x8000)) + ssize_t cnt; + unsigned int pos = 0, i = 0; + + for (; pos < TG3_NVM_VPD_LEN && i < 3; i++, pos += cnt) { + cnt = pci_read_vpd(tp->pdev, pos, + TG3_NVM_VPD_LEN - pos, + &vpd_data[pos]); + if (cnt == -ETIMEDOUT || -EINTR) + cnt = 0; + else if (cnt < 0) goto out_not_found; - - pci_read_config_dword(tp->pdev, vpd_cap + PCI_VPD_DATA, - &tmp); - v = cpu_to_le32(tmp); - memcpy(&vpd_data[i], &v, sizeof(v)); } + if (pos != TG3_NVM_VPD_LEN) + goto out_not_found; } /* Now parse and find the part number. */ - for (i = 0; i < 254; ) { + for (i = 0; i < TG3_NVM_VPD_LEN - 2; ) { unsigned char val = vpd_data[i]; unsigned int block_end; @@ -12382,7 +12491,7 @@ static void __devinit tg3_read_partno(struct tg3 *tp) (vpd_data[i + 2] << 8))); i += 3; - if (block_end > 256) + if (block_end > TG3_NVM_VPD_LEN) goto out_not_found; while (i < (block_end - 2)) { @@ -12391,7 +12500,8 @@ static void __devinit tg3_read_partno(struct tg3 *tp) int partno_len = vpd_data[i + 2]; i += 3; - if (partno_len > 24 || (partno_len + i) > 256) + if (partno_len > TG3_BPN_SIZE || + (partno_len + i) > TG3_NVM_VPD_LEN) goto out_not_found; memcpy(tp->board_part_number, @@ -12422,6 +12532,8 @@ out_not_found: else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57780 && tp->pdev->device == TG3PCI_DEVICE_TIGON3_57788) strcpy(tp->board_part_number, "BCM57788"); + else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) + strcpy(tp->board_part_number, "BCM57765"); else strcpy(tp->board_part_number, "none"); } @@ -12711,6 +12823,15 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) pci_read_config_dword(tp->pdev, TG3PCI_GEN2_PRODID_ASICREV, &prod_id_asic_rev); + else if (tp->pdev->device == TG3PCI_DEVICE_TIGON3_57781 || + tp->pdev->device == TG3PCI_DEVICE_TIGON3_57785 || + tp->pdev->device == TG3PCI_DEVICE_TIGON3_57761 || + tp->pdev->device == TG3PCI_DEVICE_TIGON3_57765 || + tp->pdev->device == TG3PCI_DEVICE_TIGON3_57791 || + tp->pdev->device == TG3PCI_DEVICE_TIGON3_57795) + pci_read_config_dword(tp->pdev, + TG3PCI_GEN15_PRODID_ASICREV, + &prod_id_asic_rev); else pci_read_config_dword(tp->pdev, TG3PCI_PRODID_ASICREV, &prod_id_asic_rev); @@ -12864,7 +12985,8 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5761 || GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5785 || GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57780 || - GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717) + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) tp->tg3_flags3 |= TG3_FLG3_5755_PLUS; if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5750 || @@ -12891,7 +13013,8 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) } /* Determine TSO capabilities */ - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717) + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) tp->tg3_flags2 |= TG3_FLG2_HW_TSO_3; else if ((tp->tg3_flags3 & TG3_FLG3_5755_PLUS) || GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906) @@ -12927,7 +13050,8 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) tp->tg3_flags2 |= TG3_FLG2_1SHOT_MSI; } - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717) { + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) { tp->tg3_flags |= TG3_FLAG_SUPPORT_MSIX; tp->irq_max = TG3_IRQ_MAX_VECS; } @@ -12941,9 +13065,13 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) tp->tg3_flags3 |= TG3_FLG3_40BIT_DMA_LIMIT_BUG; } + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) + tp->tg3_flags3 |= TG3_FLG3_USE_JUMBO_BDFLAG; + if (!(tp->tg3_flags2 & TG3_FLG2_5705_PLUS) || (tp->tg3_flags2 & TG3_FLG2_5780_CLASS) || - GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717) + (tp->tg3_flags3 & TG3_FLG3_USE_JUMBO_BDFLAG)) tp->tg3_flags |= TG3_FLAG_JUMBO_CAPABLE; pci_read_config_dword(tp->pdev, TG3PCI_PCISTATE, @@ -13136,7 +13264,8 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5761 || GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5785 || GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57780 || - GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717) + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) tp->tg3_flags |= TG3_FLAG_CPMU_PRESENT; /* Set up tp->grc_local_ctrl before calling tg3_set_power_state(). @@ -13215,7 +13344,8 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) !(tp->tg3_flags3 & TG3_FLG3_PHY_IS_FET) && GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5785 && GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_57780 && - GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5717) { + GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5717 && + GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_57765) { if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5755 || GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5787 || GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5784 || @@ -13539,7 +13669,8 @@ static u32 __devinit tg3_calc_dma_bndry(struct tg3 *tp, u32 val) #endif #endif - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717) { + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) { val = goal ? 0 : DMA_RWCTRL_DIS_CACHE_ALIGNMENT; goto out; } @@ -13751,7 +13882,8 @@ static int __devinit tg3_test_dma(struct tg3 *tp) tp->dma_rwctrl = tg3_calc_dma_bndry(tp, tp->dma_rwctrl); - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717) + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) goto out; if (tp->tg3_flags2 & TG3_FLG2_PCI_EXPRESS) { @@ -13944,7 +14076,8 @@ static void __devinit tg3_init_link_config(struct tg3 *tp) static void __devinit tg3_init_bufmgr_config(struct tg3 *tp) { if (tp->tg3_flags2 & TG3_FLG2_5705_PLUS && - GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5717) { + GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5717 && + GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_57765) { tp->bufmgr_config.mbuf_read_dma_low_water = DEFAULT_MB_RDMA_LOW_WATER_5705; tp->bufmgr_config.mbuf_mac_rx_low_water = @@ -14349,7 +14482,7 @@ static int __devinit tg3_init_one(struct pci_dev *pdev, if (err) { printk(KERN_ERR PFX "Could not obtain valid ethernet address, " "aborting.\n"); - goto err_out_fw; + goto err_out_iounmap; } if (tp->tg3_flags3 & TG3_FLG3_ENABLE_APE) { @@ -14358,7 +14491,7 @@ static int __devinit tg3_init_one(struct pci_dev *pdev, printk(KERN_ERR PFX "Cannot map APE registers, " "aborting.\n"); err = -ENOMEM; - goto err_out_fw; + goto err_out_iounmap; } tg3_ape_lock_init(tp); @@ -14489,10 +14622,6 @@ err_out_apeunmap: tp->aperegs = NULL; } -err_out_fw: - if (tp->fw) - release_firmware(tp->fw); - err_out_iounmap: if (tp->regs) { iounmap(tp->regs); diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h index 453a34fb72b9..cd30889650f8 100644 --- a/drivers/net/tg3.h +++ b/drivers/net/tg3.h @@ -49,6 +49,12 @@ #define TG3PCI_DEVICE_TIGON3_5717 0x1655 #define TG3PCI_DEVICE_TIGON3_5718 0x1656 #define TG3PCI_DEVICE_TIGON3_5724 0x165c +#define TG3PCI_DEVICE_TIGON3_57781 0x16b1 +#define TG3PCI_DEVICE_TIGON3_57785 0x16b5 +#define TG3PCI_DEVICE_TIGON3_57761 0x16b0 +#define TG3PCI_DEVICE_TIGON3_57765 0x16b4 +#define TG3PCI_DEVICE_TIGON3_57791 0x16b2 +#define TG3PCI_DEVICE_TIGON3_57795 0x16b6 /* 0x04 --> 0x64 unused */ #define TG3PCI_MSI_DATA 0x00000064 /* 0x66 --> 0x68 unused */ @@ -122,6 +128,7 @@ #define ASIC_REV_5785 0x5785 #define ASIC_REV_57780 0x57780 #define ASIC_REV_5717 0x5717 +#define ASIC_REV_57765 0x57785 #define GET_CHIP_REV(CHIP_REV_ID) ((CHIP_REV_ID) >> 8) #define CHIPREV_5700_AX 0x70 #define CHIPREV_5700_BX 0x71 @@ -220,6 +227,7 @@ /* 0xc0 --> 0xf4 unused */ #define TG3PCI_GEN2_PRODID_ASICREV 0x000000f4 +#define TG3PCI_GEN15_PRODID_ASICREV 0x000000fc /* 0xf8 --> 0x200 unused */ #define TG3_CORR_ERR_STAT 0x00000110 @@ -1813,6 +1821,11 @@ #define TG3_OTP_DEFAULT 0x286c1640 + +/* Hardware Legacy NVRAM layout */ +#define TG3_NVM_VPD_OFF 0x100 +#define TG3_NVM_VPD_LEN 256 + /* Hardware Selfboot NVRAM layout */ #define TG3_NVM_HWSB_CFG1 0x00000004 #define TG3_NVM_HWSB_CFG1_MAJMSK 0xf8000000 @@ -2441,10 +2454,6 @@ struct ring_info { DECLARE_PCI_UNMAP_ADDR(mapping) }; -struct tx_ring_info { - struct sk_buff *skb; -}; - struct tg3_config_info { u32 flags; }; @@ -2608,7 +2617,7 @@ struct tg3_napi { struct tg3_rx_buffer_desc *rx_rcb; struct tg3_tx_buffer_desc *tx_ring; - struct tx_ring_info *tx_buffers; + struct ring_info *tx_buffers; dma_addr_t status_mapping; dma_addr_t rx_rcb_mapping; @@ -2795,9 +2804,11 @@ struct tg3 { #define TG3_FLG3_NO_NVRAM 0x00004000 #define TG3_FLG3_PHY_IS_FET 0x00010000 #define TG3_FLG3_ENABLE_RSS 0x00020000 +#define TG3_FLG3_ENABLE_TSS 0x00040000 #define TG3_FLG3_4G_DMA_BNDRY_BUG 0x00080000 #define TG3_FLG3_40BIT_DMA_LIMIT_BUG 0x00100000 #define TG3_FLG3_SHORT_DMA_BUG 0x00200000 +#define TG3_FLG3_USE_JUMBO_BDFLAG 0x00400000 struct timer_list timer; u16 timer_counter; @@ -2887,8 +2898,9 @@ struct tg3 { u32 led_ctrl; u32 phy_otp; - char board_part_number[24]; -#define TG3_VER_SIZE 32 +#define TG3_BPN_SIZE 24 + char board_part_number[TG3_BPN_SIZE]; +#define TG3_VER_SIZE ETHTOOL_FWVERS_LEN char fw_ver[TG3_VER_SIZE]; u32 nic_sram_data_cfg; u32 pci_clock_ctrl; diff --git a/drivers/net/tlan.c b/drivers/net/tlan.c index 16f23f84920b..fabaeffb3155 100644 --- a/drivers/net/tlan.c +++ b/drivers/net/tlan.c @@ -1755,8 +1755,8 @@ static u32 TLan_HandleStatusCheck( struct net_device *dev, u16 host_int ) ! ( tlphy_ctl & TLAN_TC_SWAPOL ) ) { tlphy_ctl |= TLAN_TC_SWAPOL; TLan_MiiWriteReg( dev, phy, TLAN_TLPHY_CTL, tlphy_ctl); - } else if ( ( tlphy_sts & TLAN_TS_POLOK ) - && ( tlphy_ctl & TLAN_TC_SWAPOL ) ) { + } else if ( ( tlphy_sts & TLAN_TS_POLOK ) && + ( tlphy_ctl & TLAN_TC_SWAPOL ) ) { tlphy_ctl &= ~TLAN_TC_SWAPOL; TLan_MiiWriteReg( dev, phy, TLAN_TLPHY_CTL, tlphy_ctl); } diff --git a/drivers/net/tokenring/lanstreamer.c b/drivers/net/tokenring/lanstreamer.c index 7b1fe9412b6f..d6ccd59c7d07 100644 --- a/drivers/net/tokenring/lanstreamer.c +++ b/drivers/net/tokenring/lanstreamer.c @@ -712,8 +712,8 @@ static int streamer_open(struct net_device *dev) strcat(open_error, " - "); strcat(open_error, open_min_error[(error_code & 0x0f)]); - if (!streamer_priv->streamer_ring_speed - && ((error_code & 0x0f) == 0x0d)) + if (!streamer_priv->streamer_ring_speed && + ((error_code & 0x0f) == 0x0d)) { printk(KERN_WARNING "%s: Tried to autosense ring speed with no monitors present\n", dev->name); printk(KERN_WARNING "%s: Please try again with a specified ring speed \n", dev->name); @@ -1032,8 +1032,8 @@ static irqreturn_t streamer_interrupt(int irq, void *dev_id) sisr = readw(streamer_mmio + SISR); while((sisr & (SISR_MI | SISR_SRB_REPLY | SISR_ADAPTER_CHECK | SISR_ASB_FREE | - SISR_ARB_CMD | SISR_TRB_REPLY | SISR_PAR_ERR | SISR_SERR_ERR)) - && (max_intr > 0)) { + SISR_ARB_CMD | SISR_TRB_REPLY | SISR_PAR_ERR | SISR_SERR_ERR)) && + (max_intr > 0)) { if(sisr & SISR_PAR_ERR) { writew(~SISR_PAR_ERR, streamer_mmio + SISR_RUM); diff --git a/drivers/net/tokenring/smctr.c b/drivers/net/tokenring/smctr.c index ebda61bc4c2f..427a8970b6fe 100644 --- a/drivers/net/tokenring/smctr.c +++ b/drivers/net/tokenring/smctr.c @@ -2309,9 +2309,9 @@ static irqreturn_t smctr_interrupt(int irq, void *dev_id) else { if((tp->acb_head->cmd - == ACB_CMD_READ_TRC_STATUS) - && (tp->acb_head->subcmd - == RW_TRC_STATUS_BLOCK)) + == ACB_CMD_READ_TRC_STATUS) && + (tp->acb_head->subcmd + == RW_TRC_STATUS_BLOCK)) { if(tp->ptr_bcn_type) { @@ -2331,8 +2331,8 @@ static irqreturn_t smctr_interrupt(int irq, void *dev_id) smctr_disable_16bit(dev); err = smctr_ring_status_chg(dev); smctr_enable_16bit(dev); - if((tp->ring_status & REMOVE_RECEIVED) - && (tp->config_word0 & NO_AUTOREMOVE)) + if((tp->ring_status & REMOVE_RECEIVED) && + (tp->config_word0 & NO_AUTOREMOVE)) { smctr_issue_remove_cmd(dev); } @@ -2511,9 +2511,9 @@ static int smctr_issue_init_timers_cmd(struct net_device *dev) tp->config_word0 = THDREN | DMA_TRIGGER | USETPT | NO_AUTOREMOVE; tp->config_word1 = 0; - if((tp->media_type == MEDIA_STP_16) - || (tp->media_type == MEDIA_UTP_16) - || (tp->media_type == MEDIA_STP_16_UTP_16)) + if((tp->media_type == MEDIA_STP_16) || + (tp->media_type == MEDIA_UTP_16) || + (tp->media_type == MEDIA_STP_16_UTP_16)) { tp->config_word0 |= FREQ_16MB_BIT; } @@ -2556,9 +2556,9 @@ static int smctr_issue_init_timers_cmd(struct net_device *dev) tp->config_word1 &= ~SOURCE_ROUTING_SPANNING_BITS; } - if((tp->media_type == MEDIA_STP_16) - || (tp->media_type == MEDIA_UTP_16) - || (tp->media_type == MEDIA_STP_16_UTP_16)) + if((tp->media_type == MEDIA_STP_16) || + (tp->media_type == MEDIA_UTP_16) || + (tp->media_type == MEDIA_STP_16_UTP_16)) { tp->config_word1 |= INTERFRAME_SPACING_16; } @@ -2568,9 +2568,9 @@ static int smctr_issue_init_timers_cmd(struct net_device *dev) *pTimer_Struc++ = tp->config_word0; *pTimer_Struc++ = tp->config_word1; - if((tp->media_type == MEDIA_STP_4) - || (tp->media_type == MEDIA_UTP_4) - || (tp->media_type == MEDIA_STP_4_UTP_4)) + if((tp->media_type == MEDIA_STP_4) || + (tp->media_type == MEDIA_UTP_4) || + (tp->media_type == MEDIA_STP_4_UTP_4)) { *pTimer_Struc++ = 0x00FA; /* prescale */ *pTimer_Struc++ = 0x2710; /* TPT_limit */ @@ -2990,8 +2990,8 @@ static int smctr_load_firmware(struct net_device *dev) } /* Verify the firmware exists and is there in the right amount. */ - if (!fw->data - || (*(fw->data + UCODE_VERSION_OFFSET) < UCODE_VERSION)) + if (!fw->data || + (*(fw->data + UCODE_VERSION_OFFSET) < UCODE_VERSION)) { err = (UCODE_NOT_PRESENT); goto out; @@ -3010,9 +3010,8 @@ static int smctr_load_firmware(struct net_device *dev) smctr_enable_16bit(dev); smctr_set_page(dev, (__u8 *)tp->ram_access); - if((smctr_checksum_firmware(dev)) - || (*(fw->data + UCODE_VERSION_OFFSET) - > tp->microcode_version)) + if((smctr_checksum_firmware(dev)) || + (*(fw->data + UCODE_VERSION_OFFSET) > tp->microcode_version)) { smctr_enable_adapter_ctrl_store(dev); @@ -3117,9 +3116,9 @@ static int smctr_lobe_media_test(struct net_device *dev) } /* Check if any frames received during test. */ - if((tp->rx_fcb_curr[MAC_QUEUE]->frame_status) - || (tp->rx_fcb_curr[NON_MAC_QUEUE]->frame_status)) - goto err; + if((tp->rx_fcb_curr[MAC_QUEUE]->frame_status) || + (tp->rx_fcb_curr[NON_MAC_QUEUE]->frame_status)) + goto err; /* Set receive mask to "Promisc" mode. */ tp->receive_mask = saved_rcv_mask; @@ -3303,8 +3302,8 @@ static int smctr_make_group_addr(struct net_device *dev, MAC_SUB_VECTOR *tsv) /* Set Group Address Sub-vector to all zeros if only the * Group Address/Functional Address Indicator is set. */ - if(tsv->svv[0] == 0x80 && tsv->svv[1] == 0x00 - && tsv->svv[2] == 0x00 && tsv->svv[3] == 0x00) + if(tsv->svv[0] == 0x80 && tsv->svv[1] == 0x00 && + tsv->svv[2] == 0x00 && tsv->svv[3] == 0x00) tsv->svv[0] = 0x00; return (0); @@ -3876,10 +3875,10 @@ static int smctr_process_rx_packet(MAC_HEADER *rmf, __u16 size, /* NOTE: UNKNOWN MAC frames will NOT be passed up unless * ACCEPT_ATT_MAC_FRAMES is set. */ - if(((tp->receive_mask & ACCEPT_ATT_MAC_FRAMES) - && (xframe == (__u8)0)) - || ((tp->receive_mask & ACCEPT_EXT_MAC_FRAMES) - && (xframe == (__u8)1))) + if(((tp->receive_mask & ACCEPT_ATT_MAC_FRAMES) && + (xframe == (__u8)0)) || + ((tp->receive_mask & ACCEPT_EXT_MAC_FRAMES) && + (xframe == (__u8)1))) { rmf->vl = SWAP_BYTES(rmf->vl); @@ -3934,8 +3933,8 @@ static int smctr_ram_memory_test(struct net_device *dev) word_pattern = start_pattern; - for(j = 1; j < (__u32)(tp->ram_usable * 1024) - 1 - && (~err); j += 2, word_pattern++) + for(j = 1; j < (__u32)(tp->ram_usable * 1024) - 1 && (~err); + j += 2, word_pattern++) { word_read = *(__u16 *)(pword + j); if(word_read != word_pattern) @@ -3959,8 +3958,7 @@ static int smctr_ram_memory_test(struct net_device *dev) for(j = 0; j < (__u32)tp->ram_usable * 1024; j +=2) *(__u16 *)(pword + j) = word_pattern; - for(j =0; j < (__u32)tp->ram_usable * 1024 - && (~err); j += 2) + for(j =0; j < (__u32)tp->ram_usable * 1024 && (~err); j += 2) { word_read = *(__u16 *)(pword + j); if(word_read != word_pattern) @@ -4325,8 +4323,8 @@ static int smctr_restart_tx_chain(struct net_device *dev, short queue) if(smctr_debug > 10) printk(KERN_DEBUG "%s: smctr_restart_tx_chain\n", dev->name); - if(tp->num_tx_fcbs_used[queue] != 0 - && tp->tx_queue_status[queue] == NOT_TRANSMITING) + if(tp->num_tx_fcbs_used[queue] != 0 && + tp->tx_queue_status[queue] == NOT_TRANSMITING) { tp->tx_queue_status[queue] = TRANSMITING; err = smctr_issue_resume_tx_fcb_cmd(dev, queue); @@ -4349,8 +4347,8 @@ static int smctr_ring_status_chg(struct net_device *dev) */ if(tp->ring_status_flags == MONITOR_STATE_CHANGED) { - if((tp->monitor_state == MS_ACTIVE_MONITOR_STATE) - || (tp->monitor_state == MS_STANDBY_MONITOR_STATE)) + if((tp->monitor_state == MS_ACTIVE_MONITOR_STATE) || + (tp->monitor_state == MS_STANDBY_MONITOR_STATE)) { tp->monitor_state_ready = 1; } @@ -4363,8 +4361,8 @@ static int smctr_ring_status_chg(struct net_device *dev) tp->monitor_state_ready = 0; /* Ring speed problem, switching to auto mode. */ - if(tp->monitor_state == MS_MONITOR_FSM_INACTIVE - && !tp->cleanup) + if(tp->monitor_state == MS_MONITOR_FSM_INACTIVE && + !tp->cleanup) { printk(KERN_INFO "%s: Incorrect ring speed switching.\n", dev->name); @@ -4442,8 +4440,8 @@ static int smctr_rx_frame(struct net_device *dev) { err = HARDWARE_FAILED; - if(((status & 0x007f) == 0) - || ((tp->receive_mask & ACCEPT_ERR_PACKETS) != 0)) + if(((status & 0x007f) == 0) || + ((tp->receive_mask & ACCEPT_ERR_PACKETS) != 0)) { /* frame length less the CRC (4 bytes) + FS (1 byte) */ rx_size = tp->rx_fcb_curr[queue]->frame_length - 5; @@ -4538,8 +4536,8 @@ static int smctr_send_dat(struct net_device *dev) } /* Check if GOOD frame Tx'ed. */ - if(!(fcb->frame_status & FCB_COMMAND_DONE) - || fcb->frame_status & (FCB_TX_STATUS_E | FCB_TX_AC_BITS)) + if(!(fcb->frame_status & FCB_COMMAND_DONE) || + fcb->frame_status & (FCB_TX_STATUS_E | FCB_TX_AC_BITS)) { return (INITIALIZE_FAILED); } @@ -4653,8 +4651,8 @@ static int smctr_send_lobe_media_test(struct net_device *dev) } /* Check if GOOD frame Tx'ed */ - if(!(fcb->frame_status & FCB_COMMAND_DONE) - || fcb->frame_status & (FCB_TX_STATUS_E | FCB_TX_AC_BITS)) + if(!(fcb->frame_status & FCB_COMMAND_DONE) || + fcb->frame_status & (FCB_TX_STATUS_E | FCB_TX_AC_BITS)) { return (LOBE_MEDIA_TEST_FAILED); } diff --git a/drivers/net/tokenring/tms380tr.c b/drivers/net/tokenring/tms380tr.c index fa152144aacf..e3c42f5ac4a9 100644 --- a/drivers/net/tokenring/tms380tr.c +++ b/drivers/net/tokenring/tms380tr.c @@ -729,8 +729,8 @@ static void tms380tr_timer_chk(unsigned long data) return; tms380tr_chk_outstanding_cmds(dev); - if(time_before(tp->LastSendTime + SEND_TIMEOUT, jiffies) - && (tp->TplFree != tp->TplBusy)) + if(time_before(tp->LastSendTime + SEND_TIMEOUT, jiffies) && + (tp->TplFree != tp->TplBusy)) { /* Anything to send, but stalled too long */ tp->LastSendTime = jiffies; @@ -830,8 +830,8 @@ irqreturn_t tms380tr_interrupt(int irq, void *dev_id) } /* Reset system interrupt if not already done. */ - if(irq_type != STS_IRQ_TRANSMIT_STATUS - && irq_type != STS_IRQ_RECEIVE_STATUS) { + if(irq_type != STS_IRQ_TRANSMIT_STATUS && + irq_type != STS_IRQ_RECEIVE_STATUS) { tms380tr_reset_interrupt(dev); } @@ -895,10 +895,10 @@ static unsigned char tms380tr_chk_ssb(struct net_local *tp, unsigned short IrqTy /* Check if this interrupt does use the SSB. */ - if(IrqType != STS_IRQ_TRANSMIT_STATUS - && IrqType != STS_IRQ_RECEIVE_STATUS - && IrqType != STS_IRQ_COMMAND_STATUS - && IrqType != STS_IRQ_RING_STATUS) + if(IrqType != STS_IRQ_TRANSMIT_STATUS && + IrqType != STS_IRQ_RECEIVE_STATUS && + IrqType != STS_IRQ_COMMAND_STATUS && + IrqType != STS_IRQ_RING_STATUS) { return (1); /* SSB not involved. */ } @@ -1485,8 +1485,8 @@ static int tms380tr_init_adapter(struct net_device *dev) /* Mask interesting status bits */ Status = SIFREADW(SIFSTS); Status &= STS_MASK; - } while(((Status &(STS_INITIALIZE | STS_ERROR | STS_TEST)) != 0) - && ((Status & STS_ERROR) == 0) && (loop_cnt != 0)); + } while(((Status &(STS_INITIALIZE | STS_ERROR | STS_TEST)) != 0) && + ((Status & STS_ERROR) == 0) && (loop_cnt != 0)); if((Status & (STS_INITIALIZE | STS_ERROR | STS_TEST)) == 0) { @@ -2183,8 +2183,8 @@ static void tms380tr_rcv_status_irq(struct net_device *dev) } } - if(skb && (rpl->SkbStat == SKB_DATA_COPY - || rpl->SkbStat == SKB_DMA_DIRECT)) + if(skb && (rpl->SkbStat == SKB_DATA_COPY || + rpl->SkbStat == SKB_DMA_DIRECT)) { if(rpl->SkbStat == SKB_DATA_COPY) skb_copy_to_linear_data(skb, ReceiveDataPtr, diff --git a/drivers/net/tulip/21142.c b/drivers/net/tulip/21142.c index db7d5e11855d..9f6742fad6ca 100644 --- a/drivers/net/tulip/21142.c +++ b/drivers/net/tulip/21142.c @@ -209,10 +209,10 @@ void t21142_lnk_change(struct net_device *dev, int csr5) printk(KERN_DEBUG "%s: Setting CSR6 %8.8x/%x CSR12 %8.8x.\n", dev->name, tp->csr6, ioread32(ioaddr + CSR6), ioread32(ioaddr + CSR12)); - } else if ((tp->nwayset && (csr5 & 0x08000000) - && (dev->if_port == 3 || dev->if_port == 5) - && (csr12 & 2) == 2) || - (tp->nway && (csr5 & (TPLnkFail)))) { + } else if ((tp->nwayset && (csr5 & 0x08000000) && + (dev->if_port == 3 || dev->if_port == 5) && + (csr12 & 2) == 2) || + (tp->nway && (csr5 & (TPLnkFail)))) { /* Link blew? Maybe restart NWay. */ del_timer_sync(&tp->timer); t21142_start_nway(dev); diff --git a/drivers/net/tulip/de2104x.c b/drivers/net/tulip/de2104x.c index 74e5ba42d38d..d4255d44cb75 100644 --- a/drivers/net/tulip/de2104x.c +++ b/drivers/net/tulip/de2104x.c @@ -62,9 +62,9 @@ module_param (debug, int, 0); MODULE_PARM_DESC (debug, "de2104x bitmapped message enable number"); /* Set the copy breakpoint for the copy-only-tiny-buffer Rx structure. */ -#if defined(__alpha__) || defined(__arm__) || defined(__hppa__) \ - || defined(CONFIG_SPARC) || defined(__ia64__) \ - || defined(__sh__) || defined(__mips__) +#if defined(__alpha__) || defined(__arm__) || defined(__hppa__) || \ + defined(CONFIG_SPARC) || defined(__ia64__) || \ + defined(__sh__) || defined(__mips__) static int rx_copybreak = 1518; #else static int rx_copybreak = 100; diff --git a/drivers/net/tulip/eeprom.c b/drivers/net/tulip/eeprom.c index 391acd32a6a5..889f57aae89b 100644 --- a/drivers/net/tulip/eeprom.c +++ b/drivers/net/tulip/eeprom.c @@ -174,10 +174,10 @@ void __devinit tulip_parse_eeprom(struct net_device *dev) } /* Do a fix-up based on the vendor half of the station address prefix. */ for (i = 0; eeprom_fixups[i].name; i++) { - if (dev->dev_addr[0] == eeprom_fixups[i].addr0 - && dev->dev_addr[1] == eeprom_fixups[i].addr1 - && dev->dev_addr[2] == eeprom_fixups[i].addr2) { - if (dev->dev_addr[2] == 0xE8 && ee_data[0x1a] == 0x55) + if (dev->dev_addr[0] == eeprom_fixups[i].addr0 && + dev->dev_addr[1] == eeprom_fixups[i].addr1 && + dev->dev_addr[2] == eeprom_fixups[i].addr2) { + if (dev->dev_addr[2] == 0xE8 && ee_data[0x1a] == 0x55) i++; /* An Accton EN1207, not an outlaw Maxtech. */ memcpy(ee_data + 26, eeprom_fixups[i].newtable, sizeof(eeprom_fixups[i].newtable)); diff --git a/drivers/net/tulip/interrupt.c b/drivers/net/tulip/interrupt.c index c8d220cf2cce..2e8e8ee893c7 100644 --- a/drivers/net/tulip/interrupt.c +++ b/drivers/net/tulip/interrupt.c @@ -170,8 +170,8 @@ int tulip_poll(struct napi_struct *napi, int budget) RxDescCollisionSeen | RxDescRunt | RxDescDescErr | - RxWholePkt)) != RxWholePkt - || pkt_len > 1518) { + RxWholePkt)) != RxWholePkt || + pkt_len > 1518) { if ((status & (RxLengthOver2047 | RxWholePkt)) != RxWholePkt) { /* Ingore earlier buffers. */ @@ -201,8 +201,8 @@ int tulip_poll(struct napi_struct *napi, int budget) /* Check if the packet is long enough to accept without copying to a minimally-sized skbuff. */ - if (pkt_len < tulip_rx_copybreak - && (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { + if (pkt_len < tulip_rx_copybreak && + (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { skb_reserve(skb, 2); /* 16 byte align the IP header */ pci_dma_sync_single_for_cpu(tp->pdev, tp->rx_buffers[entry].mapping, @@ -395,8 +395,8 @@ static int tulip_rx(struct net_device *dev) RxDescCollisionSeen | RxDescRunt | RxDescDescErr | - RxWholePkt)) != RxWholePkt - || pkt_len > 1518) { + RxWholePkt)) != RxWholePkt || + pkt_len > 1518) { if ((status & (RxLengthOver2047 | RxWholePkt)) != RxWholePkt) { /* Ingore earlier buffers. */ @@ -425,8 +425,8 @@ static int tulip_rx(struct net_device *dev) /* Check if the packet is long enough to accept without copying to a minimally-sized skbuff. */ - if (pkt_len < tulip_rx_copybreak - && (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { + if (pkt_len < tulip_rx_copybreak && + (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { skb_reserve(skb, 2); /* 16 byte align the IP header */ pci_dma_sync_single_for_cpu(tp->pdev, tp->rx_buffers[entry].mapping, diff --git a/drivers/net/tulip/media.c b/drivers/net/tulip/media.c index daddfa51853e..d8fda83705bf 100644 --- a/drivers/net/tulip/media.c +++ b/drivers/net/tulip/media.c @@ -468,8 +468,8 @@ void __devinit tulip_find_mii (struct net_device *dev, int board_idx) int phy = phyn & 0x1f; int mii_status = tulip_mdio_read (dev, phy, MII_BMSR); if ((mii_status & 0x8301) == 0x8001 || - ((mii_status & BMSR_100BASE4) == 0 - && (mii_status & 0x7800) != 0)) { + ((mii_status & BMSR_100BASE4) == 0 && + (mii_status & 0x7800) != 0)) { /* preserve Becker logic, gain indentation level */ } else { continue; diff --git a/drivers/net/tulip/pnic2.c b/drivers/net/tulip/pnic2.c index f49579128fb5..d8418694bf46 100644 --- a/drivers/net/tulip/pnic2.c +++ b/drivers/net/tulip/pnic2.c @@ -316,9 +316,9 @@ void pnic2_lnk_change(struct net_device *dev, int csr5) } } - if ((tp->nwayset && (csr5 & 0x08000000) - && (dev->if_port == 3 || dev->if_port == 5) - && (csr12 & 2) == 2) || (tp->nway && (csr5 & (TPLnkFail)))) { + if ((tp->nwayset && (csr5 & 0x08000000) && + (dev->if_port == 3 || dev->if_port == 5) && + (csr12 & 2) == 2) || (tp->nway && (csr5 & (TPLnkFail)))) { /* Link blew? Maybe restart NWay. */ diff --git a/drivers/net/tulip/tulip_core.c b/drivers/net/tulip/tulip_core.c index 0df983bc03a6..0fa3140d65bf 100644 --- a/drivers/net/tulip/tulip_core.c +++ b/drivers/net/tulip/tulip_core.c @@ -64,9 +64,9 @@ const char * const medianame[32] = { }; /* Set the copy breakpoint for the copy-only-tiny-buffer Rx structure. */ -#if defined(__alpha__) || defined(__arm__) || defined(__hppa__) \ - || defined(CONFIG_SPARC) || defined(__ia64__) \ - || defined(__sh__) || defined(__mips__) +#if defined(__alpha__) || defined(__arm__) || defined(__hppa__) || \ + defined(CONFIG_SPARC) || defined(__ia64__) || \ + defined(__sh__) || defined(__mips__) static int rx_copybreak = 1518; #else static int rx_copybreak = 100; @@ -449,8 +449,8 @@ media_picked: iowrite32(0x0201B078, ioaddr + 0xB8); next_tick = 1*HZ; } - } else if ((tp->chip_id == MX98713 || tp->chip_id == COMPEX9881) - && ! tp->medialock) { + } else if ((tp->chip_id == MX98713 || tp->chip_id == COMPEX9881) && + ! tp->medialock) { dev->if_port = 0; tp->csr6 = 0x01880000 | (tp->full_duplex ? 0x0200 : 0); iowrite32(0x0f370000 | ioread16(ioaddr + 0x80), ioaddr + 0x80); @@ -535,9 +535,9 @@ static void tulip_tx_timeout(struct net_device *dev) if (tulip_debug > 1) printk(KERN_WARNING "%s: Transmit timeout using MII device.\n", dev->name); - } else if (tp->chip_id == DC21140 || tp->chip_id == DC21142 - || tp->chip_id == MX98713 || tp->chip_id == COMPEX9881 - || tp->chip_id == DM910X) { + } else if (tp->chip_id == DC21140 || tp->chip_id == DC21142 || + tp->chip_id == MX98713 || tp->chip_id == COMPEX9881 || + tp->chip_id == DM910X) { printk(KERN_WARNING "%s: 21140 transmit timed out, status %8.8x, " "SIA %8.8x %8.8x %8.8x %8.8x, resetting...\n", dev->name, ioread32(ioaddr + CSR5), ioread32(ioaddr + CSR12), @@ -1538,8 +1538,10 @@ static int __devinit tulip_init_one (struct pci_dev *pdev, } } /* Lite-On boards have the address byte-swapped. */ - if ((dev->dev_addr[0] == 0xA0 || dev->dev_addr[0] == 0xC0 || dev->dev_addr[0] == 0x02) - && dev->dev_addr[1] == 0x00) + if ((dev->dev_addr[0] == 0xA0 || + dev->dev_addr[0] == 0xC0 || + dev->dev_addr[0] == 0x02) && + dev->dev_addr[1] == 0x00) for (i = 0; i < 6; i+=2) { char tmp = dev->dev_addr[i]; dev->dev_addr[i] = dev->dev_addr[i+1]; diff --git a/drivers/net/tulip/winbond-840.c b/drivers/net/tulip/winbond-840.c index 1a52729c9466..869a7a0005f9 100644 --- a/drivers/net/tulip/winbond-840.c +++ b/drivers/net/tulip/winbond-840.c @@ -1230,8 +1230,8 @@ static int netdev_rx(struct net_device *dev) #endif /* Check if the packet is long enough to accept without copying to a minimally-sized skbuff. */ - if (pkt_len < rx_copybreak - && (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { + if (pkt_len < rx_copybreak && + (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { skb_reserve(skb, 2); /* 16 byte align the IP header */ pci_dma_sync_single_for_cpu(np->pci_dev,np->rx_addr[entry], np->rx_skbuff[entry]->len, @@ -1357,8 +1357,8 @@ static u32 __set_rx_mode(struct net_device *dev) memset(mc_filter, 0xff, sizeof(mc_filter)); rx_mode = RxAcceptBroadcast | AcceptMulticast | RxAcceptAllPhys | AcceptMyPhys; - } else if ((dev->mc_count > multicast_filter_limit) - || (dev->flags & IFF_ALLMULTI)) { + } else if ((dev->mc_count > multicast_filter_limit) || + (dev->flags & IFF_ALLMULTI)) { /* Too many to match, or accept all multicasts. */ memset(mc_filter, 0xff, sizeof(mc_filter)); rx_mode = RxAcceptBroadcast | AcceptMulticast | AcceptMyPhys; diff --git a/drivers/net/typhoon.c b/drivers/net/typhoon.c index 079a97000e5b..39f1fc650be6 100644 --- a/drivers/net/typhoon.c +++ b/drivers/net/typhoon.c @@ -1769,8 +1769,8 @@ typhoon_rx(struct typhoon *tp, struct basic_ring *rxRing, volatile __le32 * read csum_bits = rx->rxStatus & (TYPHOON_RX_IP_CHK_GOOD | TYPHOON_RX_UDP_CHK_GOOD | TYPHOON_RX_TCP_CHK_GOOD); if(csum_bits == - (TYPHOON_RX_IP_CHK_GOOD | TYPHOON_RX_TCP_CHK_GOOD) - || csum_bits == + (TYPHOON_RX_IP_CHK_GOOD | TYPHOON_RX_TCP_CHK_GOOD) || + csum_bits == (TYPHOON_RX_IP_CHK_GOOD | TYPHOON_RX_UDP_CHK_GOOD)) { new_skb->ip_summed = CHECKSUM_UNNECESSARY; } else diff --git a/drivers/net/ucc_geth.c b/drivers/net/ucc_geth.c index 4469f2451a6f..9f44c99777a8 100644 --- a/drivers/net/ucc_geth.c +++ b/drivers/net/ucc_geth.c @@ -1306,8 +1306,8 @@ static int init_max_rx_buff_len(u16 max_rx_buf_len, u16 __iomem *mrblr_register) { /* max_rx_buf_len value must be a multiple of 128 */ - if ((max_rx_buf_len == 0) - || (max_rx_buf_len % UCC_GETH_MRBLR_ALIGNMENT)) + if ((max_rx_buf_len == 0) || + (max_rx_buf_len % UCC_GETH_MRBLR_ALIGNMENT)) return -EINVAL; out_be16(mrblr_register, max_rx_buf_len); @@ -2159,8 +2159,8 @@ static int ucc_struct_init(struct ucc_geth_private *ugeth) } if ((ug_info->numStationAddresses != - UCC_GETH_NUM_OF_STATION_ADDRESSES_1) - && ug_info->rxExtendedFiltering) { + UCC_GETH_NUM_OF_STATION_ADDRESSES_1) && + ug_info->rxExtendedFiltering) { if (netif_msg_probe(ugeth)) ugeth_err("%s: Number of station addresses greater than 1 " "not allowed in extended parsing mode.", @@ -2284,9 +2284,9 @@ static int ucc_geth_startup(struct ucc_geth_private *ugeth) UCC_GETH_NUM_OF_STATION_ADDRESSES_1); ugeth->rx_extended_features = ugeth->rx_non_dynamic_extended_features || - (ug_info->vlanOperationTagged != UCC_GETH_VLAN_OPERATION_TAGGED_NOP) - || (ug_info->vlanOperationNonTagged != - UCC_GETH_VLAN_OPERATION_NON_TAGGED_NOP); + (ug_info->vlanOperationTagged != UCC_GETH_VLAN_OPERATION_TAGGED_NOP) || + (ug_info->vlanOperationNonTagged != + UCC_GETH_VLAN_OPERATION_NON_TAGGED_NOP); init_default_reg_vals(&uf_regs->upsmr, &ug_regs->maccfg1, &ug_regs->maccfg2); @@ -2987,11 +2987,11 @@ static int ucc_geth_startup(struct ucc_geth_private *ugeth) ugeth->p_init_enet_param_shadow->rgftgfrxglobal |= ugeth->rx_glbl_pram_offset | ug_info->riscRx; if ((ug_info->largestexternallookupkeysize != - QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_NONE) - && (ug_info->largestexternallookupkeysize != - QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_8_BYTES) - && (ug_info->largestexternallookupkeysize != - QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_16_BYTES)) { + QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_NONE) && + (ug_info->largestexternallookupkeysize != + QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_8_BYTES) && + (ug_info->largestexternallookupkeysize != + QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_16_BYTES)) { if (netif_msg_ifup(ugeth)) ugeth_err("%s: Invalid largest External Lookup Key Size.", __func__); diff --git a/drivers/net/usb/asix.c b/drivers/net/usb/asix.c index 1bef39a60a62..a516185cbc9f 100644 --- a/drivers/net/usb/asix.c +++ b/drivers/net/usb/asix.c @@ -365,8 +365,8 @@ static struct sk_buff *asix_tx_fixup(struct usbnet *dev, struct sk_buff *skb, padlen = ((skb->len + 4) % 512) ? 0 : 4; - if ((!skb_cloned(skb)) - && ((headroom + tailroom) >= (4 + padlen))) { + if ((!skb_cloned(skb)) && + ((headroom + tailroom) >= (4 + padlen))) { if ((headroom < 4) || (tailroom < padlen)) { skb->data = memmove(skb->head + 4, skb->data, skb->len); skb_set_tail_pointer(skb, skb->len); @@ -541,8 +541,8 @@ static void asix_set_multicast(struct net_device *net) if (net->flags & IFF_PROMISC) { rx_ctl |= AX_RX_CTL_PRO; - } else if (net->flags & IFF_ALLMULTI - || net->mc_count > AX_MAX_MCAST) { + } else if (net->flags & IFF_ALLMULTI || + net->mc_count > AX_MAX_MCAST) { rx_ctl |= AX_RX_CTL_AMALL; } else if (net->mc_count == 0) { /* just broadcast and directed */ @@ -753,8 +753,8 @@ static void ax88172_set_multicast(struct net_device *net) if (net->flags & IFF_PROMISC) { rx_ctl |= 0x01; - } else if (net->flags & IFF_ALLMULTI - || net->mc_count > AX_MAX_MCAST) { + } else if (net->flags & IFF_ALLMULTI || + net->mc_count > AX_MAX_MCAST) { rx_ctl |= 0x02; } else if (net->mc_count == 0) { /* just broadcast and directed */ diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index 2bed6b087d16..22b87e64a810 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -436,8 +436,8 @@ static netdev_tx_t catc_start_xmit(struct sk_buff *skb, clear_bit(TX_RUNNING, &catc->flags); } - if ((catc->is_f5u011 && catc->tx_ptr) - || (catc->tx_ptr >= ((TX_MAX_BURST - 1) * (PKT_SZ + 2)))) + if ((catc->is_f5u011 && catc->tx_ptr) || + (catc->tx_ptr >= ((TX_MAX_BURST - 1) * (PKT_SZ + 2)))) netif_stop_queue(netdev); spin_unlock_irqrestore(&catc->tx_lock, flags); diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c index 33d5c579c5ad..6491c9c00c83 100644 --- a/drivers/net/usb/cdc-phonet.c +++ b/drivers/net/usb/cdc-phonet.c @@ -372,12 +372,12 @@ int usbpn_probe(struct usb_interface *intf, const struct usb_device_id *id) /* Data interface has one inactive and one active setting */ if (data_intf->num_altsetting != 2) return -EINVAL; - if (data_intf->altsetting[0].desc.bNumEndpoints == 0 - && data_intf->altsetting[1].desc.bNumEndpoints == 2) + if (data_intf->altsetting[0].desc.bNumEndpoints == 0 && + data_intf->altsetting[1].desc.bNumEndpoints == 2) data_desc = data_intf->altsetting + 1; else - if (data_intf->altsetting[0].desc.bNumEndpoints == 2 - && data_intf->altsetting[1].desc.bNumEndpoints == 0) + if (data_intf->altsetting[0].desc.bNumEndpoints == 2 && + data_intf->altsetting[1].desc.bNumEndpoints == 0) data_desc = data_intf->altsetting; else return -EINVAL; diff --git a/drivers/net/usb/cdc_eem.c b/drivers/net/usb/cdc_eem.c index 23300656c266..c337ffc3304a 100644 --- a/drivers/net/usb/cdc_eem.c +++ b/drivers/net/usb/cdc_eem.c @@ -121,8 +121,8 @@ static struct sk_buff *eem_tx_fixup(struct usbnet *dev, struct sk_buff *skb, int headroom = skb_headroom(skb); int tailroom = skb_tailroom(skb); - if ((tailroom >= ETH_FCS_LEN + padlen) - && (headroom >= EEM_HEAD)) + if ((tailroom >= ETH_FCS_LEN + padlen) && + (headroom >= EEM_HEAD)) goto done; if ((headroom + tailroom) diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 7ec24c9b2535..21e183a83b99 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -37,23 +37,23 @@ static int is_rndis(struct usb_interface_descriptor *desc) { - return desc->bInterfaceClass == USB_CLASS_COMM - && desc->bInterfaceSubClass == 2 - && desc->bInterfaceProtocol == 0xff; + return (desc->bInterfaceClass == USB_CLASS_COMM && + desc->bInterfaceSubClass == 2 && + desc->bInterfaceProtocol == 0xff); } static int is_activesync(struct usb_interface_descriptor *desc) { - return desc->bInterfaceClass == USB_CLASS_MISC - && desc->bInterfaceSubClass == 1 - && desc->bInterfaceProtocol == 1; + return (desc->bInterfaceClass == USB_CLASS_MISC && + desc->bInterfaceSubClass == 1 && + desc->bInterfaceProtocol == 1); } static int is_wireless_rndis(struct usb_interface_descriptor *desc) { - return desc->bInterfaceClass == USB_CLASS_WIRELESS_CONTROLLER - && desc->bInterfaceSubClass == 1 - && desc->bInterfaceProtocol == 3; + return (desc->bInterfaceClass == USB_CLASS_WIRELESS_CONTROLLER && + desc->bInterfaceSubClass == 1 && + desc->bInterfaceProtocol == 3); } #else @@ -116,9 +116,9 @@ int usbnet_generic_cdc_bind(struct usbnet *dev, struct usb_interface *intf) /* this assumes that if there's a non-RNDIS vendor variant * of cdc-acm, it'll fail RNDIS requests cleanly. */ - rndis = is_rndis(&intf->cur_altsetting->desc) - || is_activesync(&intf->cur_altsetting->desc) - || is_wireless_rndis(&intf->cur_altsetting->desc); + rndis = (is_rndis(&intf->cur_altsetting->desc) || + is_activesync(&intf->cur_altsetting->desc) || + is_wireless_rndis(&intf->cur_altsetting->desc)); memset(info, 0, sizeof *info); info->control = intf; @@ -279,10 +279,10 @@ next_desc: dev->status = &info->control->cur_altsetting->endpoint [0]; desc = &dev->status->desc; - if (!usb_endpoint_is_int_in(desc) - || (le16_to_cpu(desc->wMaxPacketSize) - < sizeof(struct usb_cdc_notification)) - || !desc->bInterval) { + if (!usb_endpoint_is_int_in(desc) || + (le16_to_cpu(desc->wMaxPacketSize) + < sizeof(struct usb_cdc_notification)) || + !desc->bInterval) { dev_dbg(&intf->dev, "bad notification endpoint\n"); dev->status = NULL; } @@ -411,6 +411,12 @@ static int cdc_bind(struct usbnet *dev, struct usb_interface *intf) return 0; } +static int cdc_manage_power(struct usbnet *dev, int on) +{ + dev->intf->needs_remote_wakeup = on; + return 0; +} + static const struct driver_info cdc_info = { .description = "CDC Ethernet Device", .flags = FLAG_ETHER | FLAG_LINK_INTR, @@ -418,6 +424,7 @@ static const struct driver_info cdc_info = { .bind = cdc_bind, .unbind = usbnet_cdc_unbind, .status = cdc_status, + .manage_power = cdc_manage_power, }; static const struct driver_info mbm_info = { @@ -618,6 +625,8 @@ static struct usb_driver cdc_driver = { .disconnect = usbnet_disconnect, .suspend = usbnet_suspend, .resume = usbnet_resume, + .reset_resume = usbnet_resume, + .supports_autosuspend = 1, }; diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index fa4e58196c21..f78f0903b073 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -378,7 +378,7 @@ static void dbg_dump(int line_count, const char *func_name, unsigned char *buf, } #define DUMP(buf_, len_) \ - dbg_dump(__LINE__, __func__, buf_, len_) + dbg_dump(__LINE__, __func__, (unsigned char *)buf_, len_) #define DUMP1(buf_, len_) \ do { \ @@ -602,9 +602,9 @@ static struct hso_serial *get_serial_by_shared_int_and_type( port = hso_mux_to_port(mux); for (i = 0; i < HSO_SERIAL_TTY_MINORS; i++) { - if (serial_table[i] - && (dev2ser(serial_table[i])->shared_int == shared_int) - && ((serial_table[i]->port_spec & HSO_PORT_MASK) == port)) { + if (serial_table[i] && + (dev2ser(serial_table[i])->shared_int == shared_int) && + ((serial_table[i]->port_spec & HSO_PORT_MASK) == port)) { return dev2ser(serial_table[i]); } } @@ -846,8 +846,8 @@ static void hso_net_tx_timeout(struct net_device *net) dev_warn(&net->dev, "Tx timed out.\n"); /* Tear the waiting frame off the list */ - if (odev->mux_bulk_tx_urb - && (odev->mux_bulk_tx_urb->status == -EINPROGRESS)) + if (odev->mux_bulk_tx_urb && + (odev->mux_bulk_tx_urb->status == -EINPROGRESS)) usb_unlink_urb(odev->mux_bulk_tx_urb); /* Update statistics */ @@ -1020,9 +1020,9 @@ static void read_bulk_callback(struct urb *urb) u32 rest; u8 crc_check[4] = { 0xDE, 0xAD, 0xBE, 0xEF }; rest = urb->actual_length % odev->in_endp->wMaxPacketSize; - if (((rest == 5) || (rest == 6)) - && !memcmp(((u8 *) urb->transfer_buffer) + - urb->actual_length - 4, crc_check, 4)) { + if (((rest == 5) || (rest == 6)) && + !memcmp(((u8 *) urb->transfer_buffer) + + urb->actual_length - 4, crc_check, 4)) { urb->actual_length -= 4; } } @@ -1226,9 +1226,9 @@ static void hso_std_serial_read_bulk_callback(struct urb *urb) rest = urb->actual_length % serial->in_endp->wMaxPacketSize; - if (((rest == 5) || (rest == 6)) - && !memcmp(((u8 *) urb->transfer_buffer) + - urb->actual_length - 4, crc_check, 4)) { + if (((rest == 5) || (rest == 6)) && + !memcmp(((u8 *) urb->transfer_buffer) + + urb->actual_length - 4, crc_check, 4)) { urb->actual_length -= 4; } } @@ -1363,7 +1363,7 @@ static void hso_serial_close(struct tty_struct *tty, struct file *filp) /* reset the rts and dtr */ /* do the actual close */ serial->open_count--; - kref_put(&serial->parent->ref, hso_serial_ref_free); + if (serial->open_count <= 0) { serial->open_count = 0; spin_lock_irq(&serial->serial_lock); @@ -1383,6 +1383,8 @@ static void hso_serial_close(struct tty_struct *tty, struct file *filp) usb_autopm_put_interface(serial->parent->interface); mutex_unlock(&serial->parent->mutex); + + kref_put(&serial->parent->ref, hso_serial_ref_free); } /* close the requested serial port */ @@ -1527,7 +1529,7 @@ static void tiocmget_intr_callback(struct urb *urb) dev_warn(&usb->dev, "hso received invalid serial state notification\n"); DUMP(serial_state_notification, - sizeof(hso_serial_state_notifation)) + sizeof(struct hso_serial_state_notification)); } else { UART_state_bitmap = le16_to_cpu(serial_state_notification-> @@ -2980,8 +2982,8 @@ static int hso_probe(struct usb_interface *interface, case HSO_INTF_BULK: /* It's a regular bulk interface */ - if (((port_spec & HSO_PORT_MASK) == HSO_PORT_NETWORK) - && !disable_net) + if (((port_spec & HSO_PORT_MASK) == HSO_PORT_NETWORK) && + !disable_net) hso_dev = hso_create_net_device(interface, port_spec); else hso_dev = @@ -3144,8 +3146,8 @@ static void hso_free_interface(struct usb_interface *interface) int i; for (i = 0; i < HSO_SERIAL_TTY_MINORS; i++) { - if (serial_table[i] - && (serial_table[i]->interface == interface)) { + if (serial_table[i] && + (serial_table[i]->interface == interface)) { hso_dev = dev2ser(serial_table[i]); spin_lock_irq(&hso_dev->serial_lock); tty = tty_kref_get(hso_dev->tty); @@ -3161,8 +3163,8 @@ static void hso_free_interface(struct usb_interface *interface) } for (i = 0; i < HSO_MAX_NET_DEVICES; i++) { - if (network_table[i] - && (network_table[i]->interface == interface)) { + if (network_table[i] && + (network_table[i]->interface == interface)) { struct rfkill *rfk = dev2net(network_table[i])->rfkill; /* hso_stop_net_device doesn't stop the net queue since * traffic needs to start it again when suspended */ diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c index 10873d96b2da..87374317f480 100644 --- a/drivers/net/usb/mcs7830.c +++ b/drivers/net/usb/mcs7830.c @@ -391,8 +391,8 @@ static void mcs7830_set_multicast(struct net_device *net) if (net->flags & IFF_PROMISC) { data->config |= HIF_REG_CONFIG_PROMISCIOUS; - } else if (net->flags & IFF_ALLMULTI - || net->mc_count > MCS7830_MAX_MCAST) { + } else if (net->flags & IFF_ALLMULTI || + net->mc_count > MCS7830_MAX_MCAST) { data->config |= HIF_REG_CONFIG_ALLMULTICAST; } else if (net->mc_count == 0) { /* just broadcast and directed */ diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c index f56dec6119c3..490fa8f55424 100644 --- a/drivers/net/usb/rndis_host.c +++ b/drivers/net/usb/rndis_host.c @@ -114,8 +114,8 @@ int rndis_command(struct usbnet *dev, struct rndis_msg_hdr *buf, int buflen) */ /* Issue the request; xid is unique, don't bother byteswapping it */ - if (likely(buf->msg_type != RNDIS_MSG_HALT - && buf->msg_type != RNDIS_MSG_RESET)) { + if (likely(buf->msg_type != RNDIS_MSG_HALT && + buf->msg_type != RNDIS_MSG_RESET)) { xid = dev->xid++; if (!xid) xid = dev->xid++; @@ -493,9 +493,9 @@ int rndis_rx_fixup(struct usbnet *dev, struct sk_buff *skb) data_len = le32_to_cpu(hdr->data_len); /* don't choke if we see oob, per-packet data, etc */ - if (unlikely(hdr->msg_type != RNDIS_MSG_PACKET - || skb->len < msg_len - || (data_offset + data_len + 8) > msg_len)) { + if (unlikely(hdr->msg_type != RNDIS_MSG_PACKET || + skb->len < msg_len || + (data_offset + data_len + 8) > msg_len)) { dev->net->stats.rx_frame_errors++; devdbg(dev, "bad rndis message %d/%d/%d/%d, len %d", le32_to_cpu(hdr->msg_type), diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 04f3f289e87c..035fab04c0a0 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -140,8 +140,8 @@ int usbnet_get_endpoints(struct usbnet *dev, struct usb_interface *intf) if (!alt || !in || !out) return -EINVAL; - if (alt->desc.bAlternateSetting != 0 - || !(dev->driver_info->flags & FLAG_NO_SETINT)) { + if (alt->desc.bAlternateSetting != 0 || + !(dev->driver_info->flags & FLAG_NO_SETINT)) { tmp = usb_set_interface (dev->udev, alt->desc.bInterfaceNumber, alt->desc.bAlternateSetting); if (tmp < 0) @@ -351,9 +351,10 @@ static void rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags) spin_lock_irqsave (&dev->rxq.lock, lockflags); - if (netif_running (dev->net) - && netif_device_present (dev->net) - && !test_bit (EVENT_RX_HALT, &dev->flags)) { + if (netif_running (dev->net) && + netif_device_present (dev->net) && + !test_bit (EVENT_RX_HALT, &dev->flags) && + !test_bit (EVENT_DEV_ASLEEP, &dev->flags)) { switch (retval = usb_submit_urb (urb, GFP_ATOMIC)) { case -EPIPE: usbnet_defer_kevent (dev, EVENT_RX_HALT); @@ -391,8 +392,8 @@ static void rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags) static inline void rx_process (struct usbnet *dev, struct sk_buff *skb) { - if (dev->driver_info->rx_fixup - && !dev->driver_info->rx_fixup (dev, skb)) + if (dev->driver_info->rx_fixup && + !dev->driver_info->rx_fixup (dev, skb)) goto error; // else network stack removes extra byte if we forced a short packet @@ -484,8 +485,8 @@ block: defer_bh(dev, skb, &dev->rxq); if (urb) { - if (netif_running (dev->net) - && !test_bit (EVENT_RX_HALT, &dev->flags)) { + if (netif_running (dev->net) && + !test_bit (EVENT_RX_HALT, &dev->flags)) { rx_submit (dev, urb, GFP_ATOMIC); return; } @@ -611,15 +612,39 @@ EXPORT_SYMBOL_GPL(usbnet_unlink_rx_urbs); /*-------------------------------------------------------------------------*/ // precondition: never called in_interrupt +static void usbnet_terminate_urbs(struct usbnet *dev) +{ + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(unlink_wakeup); + DECLARE_WAITQUEUE(wait, current); + int temp; + + /* ensure there are no more active urbs */ + add_wait_queue(&unlink_wakeup, &wait); + set_current_state(TASK_UNINTERRUPTIBLE); + dev->wait = &unlink_wakeup; + temp = unlink_urbs(dev, &dev->txq) + + unlink_urbs(dev, &dev->rxq); + + /* maybe wait for deletions to finish. */ + while (!skb_queue_empty(&dev->rxq) + && !skb_queue_empty(&dev->txq) + && !skb_queue_empty(&dev->done)) { + schedule_timeout(UNLINK_TIMEOUT_MS); + set_current_state(TASK_UNINTERRUPTIBLE); + if (netif_msg_ifdown(dev)) + devdbg(dev, "waited for %d urb completions", + temp); + } + set_current_state(TASK_RUNNING); + dev->wait = NULL; + remove_wait_queue(&unlink_wakeup, &wait); +} int usbnet_stop (struct net_device *net) { struct usbnet *dev = netdev_priv(net); struct driver_info *info = dev->driver_info; - int temp; int retval; - DECLARE_WAIT_QUEUE_HEAD_ONSTACK (unlink_wakeup); - DECLARE_WAITQUEUE (wait, current); netif_stop_queue (net); @@ -641,25 +666,8 @@ int usbnet_stop (struct net_device *net) info->description); } - if (!(info->flags & FLAG_AVOID_UNLINK_URBS)) { - /* ensure there are no more active urbs */ - add_wait_queue(&unlink_wakeup, &wait); - dev->wait = &unlink_wakeup; - temp = unlink_urbs(dev, &dev->txq) + - unlink_urbs(dev, &dev->rxq); - - /* maybe wait for deletions to finish. */ - while (!skb_queue_empty(&dev->rxq) - && !skb_queue_empty(&dev->txq) - && !skb_queue_empty(&dev->done)) { - msleep(UNLINK_TIMEOUT_MS); - if (netif_msg_ifdown(dev)) - devdbg(dev, "waited for %d urb completions", - temp); - } - dev->wait = NULL; - remove_wait_queue(&unlink_wakeup, &wait); - } + if (!(info->flags & FLAG_AVOID_UNLINK_URBS)) + usbnet_terminate_urbs(dev); usb_kill_urb(dev->interrupt); @@ -672,7 +680,10 @@ int usbnet_stop (struct net_device *net) dev->flags = 0; del_timer_sync (&dev->delay); tasklet_kill (&dev->bh); - usb_autopm_put_interface(dev->intf); + if (info->manage_power) + info->manage_power(dev, 0); + else + usb_autopm_put_interface(dev->intf); return 0; } @@ -753,6 +764,12 @@ int usbnet_open (struct net_device *net) // delay posting reads until we're fully open tasklet_schedule (&dev->bh); + if (info->manage_power) { + retval = info->manage_power(dev, 1); + if (retval < 0) + goto done; + usb_autopm_put_interface(dev->intf); + } return retval; done: usb_autopm_put_interface(dev->intf); @@ -881,11 +898,16 @@ kevent (struct work_struct *work) /* usb_clear_halt() needs a thread context */ if (test_bit (EVENT_TX_HALT, &dev->flags)) { unlink_urbs (dev, &dev->txq); + status = usb_autopm_get_interface(dev->intf); + if (status < 0) + goto fail_pipe; status = usb_clear_halt (dev->udev, dev->out); - if (status < 0 - && status != -EPIPE - && status != -ESHUTDOWN) { + usb_autopm_put_interface(dev->intf); + if (status < 0 && + status != -EPIPE && + status != -ESHUTDOWN) { if (netif_msg_tx_err (dev)) +fail_pipe: deverr (dev, "can't clear tx halt, status %d", status); } else { @@ -896,11 +918,16 @@ kevent (struct work_struct *work) } if (test_bit (EVENT_RX_HALT, &dev->flags)) { unlink_urbs (dev, &dev->rxq); + status = usb_autopm_get_interface(dev->intf); + if (status < 0) + goto fail_halt; status = usb_clear_halt (dev->udev, dev->in); - if (status < 0 - && status != -EPIPE - && status != -ESHUTDOWN) { + usb_autopm_put_interface(dev->intf); + if (status < 0 && + status != -EPIPE && + status != -ESHUTDOWN) { if (netif_msg_rx_err (dev)) +fail_halt: deverr (dev, "can't clear rx halt, status %d", status); } else { @@ -919,7 +946,12 @@ kevent (struct work_struct *work) clear_bit (EVENT_RX_MEMORY, &dev->flags); if (urb != NULL) { clear_bit (EVENT_RX_MEMORY, &dev->flags); + status = usb_autopm_get_interface(dev->intf); + if (status < 0) + goto fail_lowmem; rx_submit (dev, urb, GFP_KERNEL); + usb_autopm_put_interface(dev->intf); +fail_lowmem: tasklet_schedule (&dev->bh); } } @@ -929,11 +961,18 @@ kevent (struct work_struct *work) int retval = 0; clear_bit (EVENT_LINK_RESET, &dev->flags); + status = usb_autopm_get_interface(dev->intf); + if (status < 0) + goto skip_reset; if(info->link_reset && (retval = info->link_reset(dev)) < 0) { + usb_autopm_put_interface(dev->intf); +skip_reset: devinfo(dev, "link reset failed (%d) usbnet usb-%s-%s, %s", retval, dev->udev->bus->bus_name, dev->udev->devpath, info->description); + } else { + usb_autopm_put_interface(dev->intf); } } @@ -971,6 +1010,7 @@ static void tx_complete (struct urb *urb) case -EPROTO: case -ETIME: case -EILSEQ: + usb_mark_last_busy(dev->udev); if (!timer_pending (&dev->delay)) { mod_timer (&dev->delay, jiffies + THROTTLE_JIFFIES); @@ -987,6 +1027,7 @@ static void tx_complete (struct urb *urb) } } + usb_autopm_put_interface_async(dev->intf); urb->dev = NULL; entry->state = tx_done; defer_bh(dev, skb, &dev->txq); @@ -1057,14 +1098,34 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, } } - spin_lock_irqsave (&dev->txq.lock, flags); + spin_lock_irqsave(&dev->txq.lock, flags); + retval = usb_autopm_get_interface_async(dev->intf); + if (retval < 0) { + spin_unlock_irqrestore(&dev->txq.lock, flags); + goto drop; + } + +#ifdef CONFIG_PM + /* if this triggers the device is still a sleep */ + if (test_bit(EVENT_DEV_ASLEEP, &dev->flags)) { + /* transmission will be done in resume */ + usb_anchor_urb(urb, &dev->deferred); + /* no use to process more packets */ + netif_stop_queue(net); + spin_unlock_irqrestore(&dev->txq.lock, flags); + devdbg(dev, "Delaying transmission for resumption"); + goto deferred; + } +#endif switch ((retval = usb_submit_urb (urb, GFP_ATOMIC))) { case -EPIPE: netif_stop_queue (net); usbnet_defer_kevent (dev, EVENT_TX_HALT); + usb_autopm_put_interface_async(dev->intf); break; default: + usb_autopm_put_interface_async(dev->intf); if (netif_msg_tx_err (dev)) devdbg (dev, "tx: submit urb err %d", retval); break; @@ -1088,6 +1149,9 @@ drop: devdbg (dev, "> tx, len %d, type 0x%x", length, skb->protocol); } +#ifdef CONFIG_PM +deferred: +#endif return NETDEV_TX_OK; } EXPORT_SYMBOL_GPL(usbnet_start_xmit); @@ -1126,10 +1190,10 @@ static void usbnet_bh (unsigned long param) } // or are we maybe short a few urbs? - } else if (netif_running (dev->net) - && netif_device_present (dev->net) - && !timer_pending (&dev->delay) - && !test_bit (EVENT_RX_HALT, &dev->flags)) { + } else if (netif_running (dev->net) && + netif_device_present (dev->net) && + !timer_pending (&dev->delay) && + !test_bit (EVENT_RX_HALT, &dev->flags)) { int temp = dev->rxq.qlen; int qlen = RX_QLEN (dev); @@ -1263,6 +1327,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) dev->bh.func = usbnet_bh; dev->bh.data = (unsigned long) dev; INIT_WORK (&dev->kevent, kevent); + init_usb_anchor(&dev->deferred); dev->delay.function = usbnet_bh; dev->delay.data = (unsigned long) dev; init_timer (&dev->delay); @@ -1297,8 +1362,8 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) // heuristic: "usb%d" for links we know are two-host, // else "eth%d" when there's reasonable doubt. userspace // can rename the link if it knows better. - if ((dev->driver_info->flags & FLAG_ETHER) != 0 - && (net->dev_addr [0] & 0x02) == 0) + if ((dev->driver_info->flags & FLAG_ETHER) != 0 && + (net->dev_addr [0] & 0x02) == 0) strcpy (net->name, "eth%d"); /* WLAN devices should always be named "wlan%d" */ if ((dev->driver_info->flags & FLAG_WLAN) != 0) @@ -1382,13 +1447,23 @@ int usbnet_suspend (struct usb_interface *intf, pm_message_t message) struct usbnet *dev = usb_get_intfdata(intf); if (!dev->suspend_count++) { + spin_lock_irq(&dev->txq.lock); + /* don't autosuspend while transmitting */ + if (dev->txq.qlen && (message.event & PM_EVENT_AUTO)) { + spin_unlock_irq(&dev->txq.lock); + return -EBUSY; + } else { + set_bit(EVENT_DEV_ASLEEP, &dev->flags); + spin_unlock_irq(&dev->txq.lock); + } /* * accelerate emptying of the rx and queues, to avoid * having everything error out. */ netif_device_detach (dev->net); - (void) unlink_urbs (dev, &dev->rxq); - (void) unlink_urbs (dev, &dev->txq); + usbnet_terminate_urbs(dev); + usb_kill_urb(dev->interrupt); + /* * reattach so runtime management can use and * wake the device @@ -1402,10 +1477,34 @@ EXPORT_SYMBOL_GPL(usbnet_suspend); int usbnet_resume (struct usb_interface *intf) { struct usbnet *dev = usb_get_intfdata(intf); + struct sk_buff *skb; + struct urb *res; + int retval; + + if (!--dev->suspend_count) { + spin_lock_irq(&dev->txq.lock); + while ((res = usb_get_from_anchor(&dev->deferred))) { + + printk(KERN_INFO"%s has delayed data\n", __func__); + skb = (struct sk_buff *)res->context; + retval = usb_submit_urb(res, GFP_ATOMIC); + if (retval < 0) { + dev_kfree_skb_any(skb); + usb_free_urb(res); + usb_autopm_put_interface_async(dev->intf); + } else { + dev->net->trans_start = jiffies; + __skb_queue_tail(&dev->txq, skb); + } + } - if (!--dev->suspend_count) + smp_mb(); + clear_bit(EVENT_DEV_ASLEEP, &dev->flags); + spin_unlock_irq(&dev->txq.lock); + if (!(dev->txq.qlen >= TX_QLEN(dev))) + netif_start_queue(dev->net); tasklet_schedule (&dev->bh); - + } return 0; } EXPORT_SYMBOL_GPL(usbnet_resume); diff --git a/drivers/net/usb/zaurus.c b/drivers/net/usb/zaurus.c index 04882c8f9bf1..3eb0b167b5b4 100644 --- a/drivers/net/usb/zaurus.c +++ b/drivers/net/usb/zaurus.c @@ -174,8 +174,8 @@ static int blan_mdlm_bind(struct usbnet *dev, struct usb_interface *intf) goto bad_desc; } /* expect bcdVersion 1.0, ignore */ - if (memcmp(&desc->bGUID, blan_guid, 16) - && memcmp(&desc->bGUID, safe_guid, 16) ) { + if (memcmp(&desc->bGUID, blan_guid, 16) && + memcmp(&desc->bGUID, safe_guid, 16)) { /* hey, this one might _really_ be MDLM! */ dev_dbg(&intf->dev, "MDLM guid\n"); goto bad_desc; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 2d657f2314cb..63099c58a6dd 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -155,8 +155,6 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) struct veth_net_stats *stats, *rcv_stats; int length, cpu; - skb_orphan(skb); - priv = netdev_priv(dev); rcv = priv->peer; rcv_priv = netdev_priv(rcv); @@ -168,20 +166,12 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) if (!(rcv->flags & IFF_UP)) goto tx_drop; - if (skb->len > (rcv->mtu + MTU_PAD)) - goto rx_drop; - - skb->tstamp.tv64 = 0; - skb->pkt_type = PACKET_HOST; - skb->protocol = eth_type_trans(skb, rcv); if (dev->features & NETIF_F_NO_CSUM) skb->ip_summed = rcv_priv->ip_summed; - skb->mark = 0; - secpath_reset(skb); - nf_reset(skb); - - length = skb->len; + length = skb->len + ETH_HLEN; + if (dev_forward_skb(rcv, skb) != NET_RX_SUCCESS) + goto rx_drop; stats->tx_bytes += length; stats->tx_packets++; @@ -189,7 +179,6 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) rcv_stats->rx_bytes += length; rcv_stats->rx_packets++; - netif_rx(skb); return NETDEV_TX_OK; tx_drop: @@ -210,32 +199,29 @@ rx_drop: static struct net_device_stats *veth_get_stats(struct net_device *dev) { struct veth_priv *priv; - struct net_device_stats *dev_stats; int cpu; - struct veth_net_stats *stats; + struct veth_net_stats *stats, total = {0}; priv = netdev_priv(dev); - dev_stats = &dev->stats; - dev_stats->rx_packets = 0; - dev_stats->tx_packets = 0; - dev_stats->rx_bytes = 0; - dev_stats->tx_bytes = 0; - dev_stats->tx_dropped = 0; - dev_stats->rx_dropped = 0; - - for_each_online_cpu(cpu) { + for_each_possible_cpu(cpu) { stats = per_cpu_ptr(priv->stats, cpu); - dev_stats->rx_packets += stats->rx_packets; - dev_stats->tx_packets += stats->tx_packets; - dev_stats->rx_bytes += stats->rx_bytes; - dev_stats->tx_bytes += stats->tx_bytes; - dev_stats->tx_dropped += stats->tx_dropped; - dev_stats->rx_dropped += stats->rx_dropped; + total.rx_packets += stats->rx_packets; + total.tx_packets += stats->tx_packets; + total.rx_bytes += stats->rx_bytes; + total.tx_bytes += stats->tx_bytes; + total.tx_dropped += stats->tx_dropped; + total.rx_dropped += stats->rx_dropped; } - - return dev_stats; + dev->stats.rx_packets = total.rx_packets; + dev->stats.tx_packets = total.tx_packets; + dev->stats.rx_bytes = total.rx_bytes; + dev->stats.tx_bytes = total.tx_bytes; + dev->stats.tx_dropped = total.tx_dropped; + dev->stats.rx_dropped = total.rx_dropped; + + return &dev->stats; } static int veth_open(struct net_device *dev) diff --git a/drivers/net/via-rhine.c b/drivers/net/via-rhine.c index ec94ddf01f56..593e01f64e9b 100644 --- a/drivers/net/via-rhine.c +++ b/drivers/net/via-rhine.c @@ -42,9 +42,9 @@ static int max_interrupt_work = 20; /* Set the copy breakpoint for the copy-only-tiny-frames scheme. Setting to > 1518 effectively disables this feature. */ -#if defined(__alpha__) || defined(__arm__) || defined(__hppa__) \ - || defined(CONFIG_SPARC) || defined(__ia64__) \ - || defined(__sh__) || defined(__mips__) +#if defined(__alpha__) || defined(__arm__) || defined(__hppa__) || \ + defined(CONFIG_SPARC) || defined(__ia64__) || \ + defined(__sh__) || defined(__mips__) static int rx_copybreak = 1518; #else static int rx_copybreak; @@ -1683,8 +1683,8 @@ static void rhine_set_rx_mode(struct net_device *dev) rx_mode = 0x1C; iowrite32(0xffffffff, ioaddr + MulticastFilter0); iowrite32(0xffffffff, ioaddr + MulticastFilter1); - } else if ((dev->mc_count > multicast_filter_limit) - || (dev->flags & IFF_ALLMULTI)) { + } else if ((dev->mc_count > multicast_filter_limit) || + (dev->flags & IFF_ALLMULTI)) { /* Too many to match, or accept all multicasts. */ iowrite32(0xffffffff, ioaddr + MulticastFilter0); iowrite32(0xffffffff, ioaddr + MulticastFilter1); diff --git a/drivers/net/via-velocity.c b/drivers/net/via-velocity.c index 1e6b395c555f..4ceb441f2687 100644 --- a/drivers/net/via-velocity.c +++ b/drivers/net/via-velocity.c @@ -9,7 +9,6 @@ * * TODO * rx_copybreak/alignment - * Scatter gather * More testing * * The changes are (c) Copyright 2004, Red Hat Inc. <alan@lxorguk.ukuu.org.uk> @@ -275,7 +274,7 @@ VELOCITY_PARAM(rx_thresh, "Receive fifo threshold"); #define DMA_LENGTH_MIN 0 #define DMA_LENGTH_MAX 7 -#define DMA_LENGTH_DEF 0 +#define DMA_LENGTH_DEF 6 /* DMA_length[] is used for controlling the DMA length 0: 8 DWORDs @@ -298,14 +297,6 @@ VELOCITY_PARAM(DMA_length, "DMA length"); */ VELOCITY_PARAM(IP_byte_align, "Enable IP header dword aligned"); -#define TX_CSUM_DEF 1 -/* txcsum_offload[] is used for setting the checksum offload ability of NIC. - (We only support RX checksum offload now) - 0: disable csum_offload[checksum offload - 1: enable checksum offload. (Default) -*/ -VELOCITY_PARAM(txcsum_offload, "Enable transmit packet checksum offload"); - #define FLOW_CNTL_DEF 1 #define FLOW_CNTL_MIN 1 #define FLOW_CNTL_MAX 5 @@ -354,12 +345,6 @@ VELOCITY_PARAM(ValPktLen, "Receiving or Drop invalid 802.3 frame"); */ VELOCITY_PARAM(wol_opts, "Wake On Lan options"); -#define INT_WORKS_DEF 20 -#define INT_WORKS_MIN 10 -#define INT_WORKS_MAX 64 - -VELOCITY_PARAM(int_works, "Number of packets per interrupt services"); - static int rx_copybreak = 200; module_param(rx_copybreak, int, 0644); MODULE_PARM_DESC(rx_copybreak, "Copy breakpoint for copy-only-tiny-frames"); @@ -497,13 +482,11 @@ static void __devinit velocity_get_options(struct velocity_opt *opts, int index, velocity_set_int_opt(&opts->numrx, RxDescriptors[index], RX_DESC_MIN, RX_DESC_MAX, RX_DESC_DEF, "RxDescriptors", devname); velocity_set_int_opt(&opts->numtx, TxDescriptors[index], TX_DESC_MIN, TX_DESC_MAX, TX_DESC_DEF, "TxDescriptors", devname); - velocity_set_bool_opt(&opts->flags, txcsum_offload[index], TX_CSUM_DEF, VELOCITY_FLAGS_TX_CSUM, "txcsum_offload", devname); velocity_set_int_opt(&opts->flow_cntl, flow_control[index], FLOW_CNTL_MIN, FLOW_CNTL_MAX, FLOW_CNTL_DEF, "flow_control", devname); velocity_set_bool_opt(&opts->flags, IP_byte_align[index], IP_ALIG_DEF, VELOCITY_FLAGS_IP_ALIGN, "IP_byte_align", devname); velocity_set_bool_opt(&opts->flags, ValPktLen[index], VAL_PKT_LEN_DEF, VELOCITY_FLAGS_VAL_PKT_LEN, "ValPktLen", devname); velocity_set_int_opt((int *) &opts->spd_dpx, speed_duplex[index], MED_LNK_MIN, MED_LNK_MAX, MED_LNK_DEF, "Media link mode", devname); velocity_set_int_opt((int *) &opts->wol_opts, wol_opts[index], WOL_OPT_MIN, WOL_OPT_MAX, WOL_OPT_DEF, "Wake On Lan options", devname); - velocity_set_int_opt((int *) &opts->int_works, int_works[index], INT_WORKS_MIN, INT_WORKS_MAX, INT_WORKS_DEF, "Interrupt service works", devname); opts->numrx = (opts->numrx & ~3); } @@ -912,8 +895,8 @@ static int velocity_set_media_mode(struct velocity_info *vptr, u32 mii_status) /* Check if new status is consisent with current status - if (((mii_status & curr_status) & VELOCITY_AUTONEG_ENABLE) - || (mii_status==curr_status)) { + if (((mii_status & curr_status) & VELOCITY_AUTONEG_ENABLE) || + (mii_status==curr_status)) { vptr->mii_status=mii_check_media_mode(vptr->mac_regs); vptr->mii_status=check_connection_type(vptr->mac_regs); VELOCITY_PRT(MSG_LEVEL_INFO, "Velocity link no change\n"); @@ -1149,8 +1132,8 @@ static void velocity_set_multi(struct net_device *dev) writel(0xffffffff, ®s->MARCAM[0]); writel(0xffffffff, ®s->MARCAM[4]); rx_mode = (RCR_AM | RCR_AB | RCR_PROM); - } else if ((dev->mc_count > vptr->multicast_limit) - || (dev->flags & IFF_ALLMULTI)) { + } else if ((dev->mc_count > vptr->multicast_limit) || + (dev->flags & IFF_ALLMULTI)) { writel(0xffffffff, ®s->MARCAM[0]); writel(0xffffffff, ®s->MARCAM[4]); rx_mode = (RCR_AM | RCR_AB); @@ -1246,6 +1229,66 @@ static void mii_init(struct velocity_info *vptr, u32 mii_status) } } +/** + * setup_queue_timers - Setup interrupt timers + * + * Setup interrupt frequency during suppression (timeout if the frame + * count isn't filled). + */ +static void setup_queue_timers(struct velocity_info *vptr) +{ + /* Only for newer revisions */ + if (vptr->rev_id >= REV_ID_VT3216_A0) { + u8 txqueue_timer = 0; + u8 rxqueue_timer = 0; + + if (vptr->mii_status & (VELOCITY_SPEED_1000 | + VELOCITY_SPEED_100)) { + txqueue_timer = vptr->options.txqueue_timer; + rxqueue_timer = vptr->options.rxqueue_timer; + } + + writeb(txqueue_timer, &vptr->mac_regs->TQETMR); + writeb(rxqueue_timer, &vptr->mac_regs->RQETMR); + } +} +/** + * setup_adaptive_interrupts - Setup interrupt suppression + * + * @vptr velocity adapter + * + * The velocity is able to suppress interrupt during high interrupt load. + * This function turns on that feature. + */ +static void setup_adaptive_interrupts(struct velocity_info *vptr) +{ + struct mac_regs __iomem *regs = vptr->mac_regs; + u16 tx_intsup = vptr->options.tx_intsup; + u16 rx_intsup = vptr->options.rx_intsup; + + /* Setup default interrupt mask (will be changed below) */ + vptr->int_mask = INT_MASK_DEF; + + /* Set Tx Interrupt Suppression Threshold */ + writeb(CAMCR_PS0, ®s->CAMCR); + if (tx_intsup != 0) { + vptr->int_mask &= ~(ISR_PTXI | ISR_PTX0I | ISR_PTX1I | + ISR_PTX2I | ISR_PTX3I); + writew(tx_intsup, ®s->ISRCTL); + } else + writew(ISRCTL_TSUPDIS, ®s->ISRCTL); + + /* Set Rx Interrupt Suppression Threshold */ + writeb(CAMCR_PS1, ®s->CAMCR); + if (rx_intsup != 0) { + vptr->int_mask &= ~ISR_PRXI; + writew(rx_intsup, ®s->ISRCTL); + } else + writew(ISRCTL_RSUPDIS, ®s->ISRCTL); + + /* Select page to interrupt hold timer */ + writeb(0, ®s->CAMCR); +} /** * velocity_init_registers - initialise MAC registers @@ -1332,7 +1375,7 @@ static void velocity_init_registers(struct velocity_info *vptr, */ enable_mii_autopoll(regs); - vptr->int_mask = INT_MASK_DEF; + setup_adaptive_interrupts(vptr); writel(vptr->rx.pool_dma, ®s->RDBaseLo); writew(vptr->options.numrx - 1, ®s->RDCSize); @@ -1470,7 +1513,8 @@ static int velocity_alloc_rx_buf(struct velocity_info *vptr, int idx) * Do the gymnastics to get the buffer head for data at * 64byte alignment. */ - skb_reserve(rd_info->skb, (unsigned long) rd_info->skb->data & 63); + skb_reserve(rd_info->skb, + 64 - ((unsigned long) rd_info->skb->data & 63)); rd_info->skb_dma = pci_map_single(vptr->pdev, rd_info->skb->data, vptr->rx.buf_sz, PCI_DMA_FROMDEVICE); @@ -1589,12 +1633,10 @@ out: */ static int velocity_init_td_ring(struct velocity_info *vptr) { - dma_addr_t curr; int j; /* Init the TD ring entries */ for (j = 0; j < vptr->tx.numq; j++) { - curr = vptr->tx.pool_dma[j]; vptr->tx.infos[j] = kcalloc(vptr->options.numtx, sizeof(struct velocity_td_info), @@ -1660,21 +1702,27 @@ err_free_dma_rings_0: * Release an transmit buffer. If the buffer was preallocated then * recycle it, if not then unmap the buffer. */ -static void velocity_free_tx_buf(struct velocity_info *vptr, struct velocity_td_info *tdinfo) +static void velocity_free_tx_buf(struct velocity_info *vptr, + struct velocity_td_info *tdinfo, struct tx_desc *td) { struct sk_buff *skb = tdinfo->skb; - int i; - int pktlen; /* * Don't unmap the pre-allocated tx_bufs */ if (tdinfo->skb_dma) { + int i; - pktlen = max_t(unsigned int, skb->len, ETH_ZLEN); for (i = 0; i < tdinfo->nskb_dma; i++) { - pci_unmap_single(vptr->pdev, tdinfo->skb_dma[i], pktlen, PCI_DMA_TODEVICE); - tdinfo->skb_dma[i] = 0; + size_t pktlen = max_t(size_t, skb->len, ETH_ZLEN); + + /* For scatter-gather */ + if (skb_shinfo(skb)->nr_frags > 0) + pktlen = max_t(size_t, pktlen, + td->td_buf[i].size & ~TD_QUEUE); + + pci_unmap_single(vptr->pdev, tdinfo->skb_dma[i], + le16_to_cpu(pktlen), PCI_DMA_TODEVICE); } } dev_kfree_skb_irq(skb); @@ -1788,6 +1836,8 @@ static void velocity_error(struct velocity_info *vptr, int status) BYTE_REG_BITS_OFF(TESTCFG_HBDIS, ®s->TESTCFG); else BYTE_REG_BITS_ON(TESTCFG_HBDIS, ®s->TESTCFG); + + setup_queue_timers(vptr); } /* * Get link status from PHYSR0 @@ -1874,7 +1924,7 @@ static int velocity_tx_srv(struct velocity_info *vptr, u32 status) stats->tx_packets++; stats->tx_bytes += tdinfo->skb->len; } - velocity_free_tx_buf(vptr, tdinfo); + velocity_free_tx_buf(vptr, tdinfo, td); vptr->tx.used[qnum]--; } vptr->tx.tail[qnum] = idx; @@ -1886,8 +1936,8 @@ static int velocity_tx_srv(struct velocity_info *vptr, u32 status) * Look to see if we should kick the transmit network * layer for more work. */ - if (netif_queue_stopped(vptr->dev) && (full == 0) - && (!(vptr->mii_status & VELOCITY_LINK_FAIL))) { + if (netif_queue_stopped(vptr->dev) && (full == 0) && + (!(vptr->mii_status & VELOCITY_LINK_FAIL))) { netif_wake_queue(vptr->dev); } return works; @@ -2046,13 +2096,14 @@ static int velocity_receive_frame(struct velocity_info *vptr, int idx) * any received packets from the receive queue. Hand the ring * slots back to the adapter for reuse. */ -static int velocity_rx_srv(struct velocity_info *vptr, int status) +static int velocity_rx_srv(struct velocity_info *vptr, int status, + int budget_left) { struct net_device_stats *stats = &vptr->dev->stats; int rd_curr = vptr->rx.curr; int works = 0; - do { + while (works < budget_left) { struct rx_desc *rd = vptr->rx.ring + rd_curr; if (!vptr->rx.info[rd_curr].skb) @@ -2083,7 +2134,8 @@ static int velocity_rx_srv(struct velocity_info *vptr, int status) rd_curr++; if (rd_curr >= vptr->options.numrx) rd_curr = 0; - } while (++works <= 15); + works++; + } vptr->rx.curr = rd_curr; @@ -2094,6 +2146,40 @@ static int velocity_rx_srv(struct velocity_info *vptr, int status) return works; } +static int velocity_poll(struct napi_struct *napi, int budget) +{ + struct velocity_info *vptr = container_of(napi, + struct velocity_info, napi); + unsigned int rx_done; + u32 isr_status; + + spin_lock(&vptr->lock); + isr_status = mac_read_isr(vptr->mac_regs); + + /* Ack the interrupt */ + mac_write_isr(vptr->mac_regs, isr_status); + if (isr_status & (~(ISR_PRXI | ISR_PPRXI | ISR_PTXI | ISR_PPTXI))) + velocity_error(vptr, isr_status); + + /* + * Do rx and tx twice for performance (taken from the VIA + * out-of-tree driver). + */ + rx_done = velocity_rx_srv(vptr, isr_status, budget / 2); + velocity_tx_srv(vptr, isr_status); + rx_done += velocity_rx_srv(vptr, isr_status, budget - rx_done); + velocity_tx_srv(vptr, isr_status); + + spin_unlock(&vptr->lock); + + /* If budget not fully consumed, exit the polling mode */ + if (rx_done < budget) { + napi_complete(napi); + mac_enable_int(vptr->mac_regs); + } + + return rx_done; +} /** * velocity_intr - interrupt callback @@ -2110,8 +2196,6 @@ static irqreturn_t velocity_intr(int irq, void *dev_instance) struct net_device *dev = dev_instance; struct velocity_info *vptr = netdev_priv(dev); u32 isr_status; - int max_count = 0; - spin_lock(&vptr->lock); isr_status = mac_read_isr(vptr->mac_regs); @@ -2122,32 +2206,13 @@ static irqreturn_t velocity_intr(int irq, void *dev_instance) return IRQ_NONE; } - mac_disable_int(vptr->mac_regs); - - /* - * Keep processing the ISR until we have completed - * processing and the isr_status becomes zero - */ - - while (isr_status != 0) { - mac_write_isr(vptr->mac_regs, isr_status); - if (isr_status & (~(ISR_PRXI | ISR_PPRXI | ISR_PTXI | ISR_PPTXI))) - velocity_error(vptr, isr_status); - if (isr_status & (ISR_PRXI | ISR_PPRXI)) - max_count += velocity_rx_srv(vptr, isr_status); - if (isr_status & (ISR_PTXI | ISR_PPTXI)) - max_count += velocity_tx_srv(vptr, isr_status); - isr_status = mac_read_isr(vptr->mac_regs); - if (max_count > vptr->options.int_works) { - printk(KERN_WARNING "%s: excessive work at interrupt.\n", - dev->name); - max_count = 0; - } + if (likely(napi_schedule_prep(&vptr->napi))) { + mac_disable_int(vptr->mac_regs); + __napi_schedule(&vptr->napi); } spin_unlock(&vptr->lock); - mac_enable_int(vptr->mac_regs); - return IRQ_HANDLED; + return IRQ_HANDLED; } /** @@ -2187,6 +2252,7 @@ static int velocity_open(struct net_device *dev) mac_enable_int(vptr->mac_regs); netif_start_queue(dev); + napi_enable(&vptr->napi); vptr->flags |= VELOCITY_FLAGS_OPENED; out: return ret; @@ -2422,6 +2488,7 @@ static int velocity_close(struct net_device *dev) { struct velocity_info *vptr = netdev_priv(dev); + napi_disable(&vptr->napi); netif_stop_queue(dev); velocity_shutdown(vptr); @@ -2456,14 +2523,22 @@ static netdev_tx_t velocity_xmit(struct sk_buff *skb, struct velocity_td_info *tdinfo; unsigned long flags; int pktlen; - __le16 len; - int index; + int index, prev; + int i = 0; if (skb_padto(skb, ETH_ZLEN)) goto out; - pktlen = max_t(unsigned int, skb->len, ETH_ZLEN); - len = cpu_to_le16(pktlen); + /* The hardware can handle at most 7 memory segments, so merge + * the skb if there are more */ + if (skb_shinfo(skb)->nr_frags > 6 && __skb_linearize(skb)) { + kfree_skb(skb); + return NETDEV_TX_OK; + } + + pktlen = skb_shinfo(skb)->nr_frags == 0 ? + max_t(unsigned int, skb->len, ETH_ZLEN) : + skb_headlen(skb); spin_lock_irqsave(&vptr->lock, flags); @@ -2480,11 +2555,24 @@ static netdev_tx_t velocity_xmit(struct sk_buff *skb, */ tdinfo->skb = skb; tdinfo->skb_dma[0] = pci_map_single(vptr->pdev, skb->data, pktlen, PCI_DMA_TODEVICE); - td_ptr->tdesc0.len = len; + td_ptr->tdesc0.len = cpu_to_le16(pktlen); td_ptr->td_buf[0].pa_low = cpu_to_le32(tdinfo->skb_dma[0]); td_ptr->td_buf[0].pa_high = 0; - td_ptr->td_buf[0].size = len; - tdinfo->nskb_dma = 1; + td_ptr->td_buf[0].size = cpu_to_le16(pktlen); + + /* Handle fragments */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + tdinfo->skb_dma[i + 1] = pci_map_page(vptr->pdev, frag->page, + frag->page_offset, frag->size, + PCI_DMA_TODEVICE); + + td_ptr->td_buf[i + 1].pa_low = cpu_to_le32(tdinfo->skb_dma[i + 1]); + td_ptr->td_buf[i + 1].pa_high = 0; + td_ptr->td_buf[i + 1].size = cpu_to_le16(frag->size); + } + tdinfo->nskb_dma = i + 1; td_ptr->tdesc1.cmd = TCPLS_NORMAL + (tdinfo->nskb_dma + 1) * 16; @@ -2496,8 +2584,8 @@ static netdev_tx_t velocity_xmit(struct sk_buff *skb, /* * Handle hardware checksum */ - if ((vptr->flags & VELOCITY_FLAGS_TX_CSUM) - && (skb->ip_summed == CHECKSUM_PARTIAL)) { + if ((dev->features & NETIF_F_IP_CSUM) && + (skb->ip_summed == CHECKSUM_PARTIAL)) { const struct iphdr *ip = ip_hdr(skb); if (ip->protocol == IPPROTO_TCP) td_ptr->tdesc1.TCR |= TCR0_TCPCK; @@ -2505,23 +2593,21 @@ static netdev_tx_t velocity_xmit(struct sk_buff *skb, td_ptr->tdesc1.TCR |= (TCR0_UDPCK); td_ptr->tdesc1.TCR |= TCR0_IPCK; } - { - int prev = index - 1; + prev = index - 1; + if (prev < 0) + prev = vptr->options.numtx - 1; + td_ptr->tdesc0.len |= OWNED_BY_NIC; + vptr->tx.used[qnum]++; + vptr->tx.curr[qnum] = (index + 1) % vptr->options.numtx; - if (prev < 0) - prev = vptr->options.numtx - 1; - td_ptr->tdesc0.len |= OWNED_BY_NIC; - vptr->tx.used[qnum]++; - vptr->tx.curr[qnum] = (index + 1) % vptr->options.numtx; + if (AVAIL_TD(vptr, qnum) < 1) + netif_stop_queue(dev); - if (AVAIL_TD(vptr, qnum) < 1) - netif_stop_queue(dev); + td_ptr = &(vptr->tx.rings[qnum][prev]); + td_ptr->td_buf[0].size |= TD_QUEUE; + mac_tx_queue_wake(vptr->mac_regs, qnum); - td_ptr = &(vptr->tx.rings[qnum][prev]); - td_ptr->td_buf[0].size |= TD_QUEUE; - mac_tx_queue_wake(vptr->mac_regs, qnum); - } dev->trans_start = jiffies; spin_unlock_irqrestore(&vptr->lock, flags); out: @@ -2740,12 +2826,10 @@ static int __devinit velocity_found1(struct pci_dev *pdev, const struct pci_devi dev->irq = pdev->irq; dev->netdev_ops = &velocity_netdev_ops; dev->ethtool_ops = &velocity_ethtool_ops; + netif_napi_add(dev, &vptr->napi, velocity_poll, VELOCITY_NAPI_WEIGHT); dev->features |= NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_FILTER | - NETIF_F_HW_VLAN_RX; - - if (vptr->flags & VELOCITY_FLAGS_TX_CSUM) - dev->features |= NETIF_F_IP_CSUM; + NETIF_F_HW_VLAN_RX | NETIF_F_IP_CSUM; ret = register_netdev(dev); if (ret < 0) @@ -3198,15 +3282,114 @@ static void velocity_set_msglevel(struct net_device *dev, u32 value) msglevel = value; } +static int get_pending_timer_val(int val) +{ + int mult_bits = val >> 6; + int mult = 1; + + switch (mult_bits) + { + case 1: + mult = 4; break; + case 2: + mult = 16; break; + case 3: + mult = 64; break; + case 0: + default: + break; + } + + return (val & 0x3f) * mult; +} + +static void set_pending_timer_val(int *val, u32 us) +{ + u8 mult = 0; + u8 shift = 0; + + if (us >= 0x3f) { + mult = 1; /* mult with 4 */ + shift = 2; + } + if (us >= 0x3f * 4) { + mult = 2; /* mult with 16 */ + shift = 4; + } + if (us >= 0x3f * 16) { + mult = 3; /* mult with 64 */ + shift = 6; + } + + *val = (mult << 6) | ((us >> shift) & 0x3f); +} + + +static int velocity_get_coalesce(struct net_device *dev, + struct ethtool_coalesce *ecmd) +{ + struct velocity_info *vptr = netdev_priv(dev); + + ecmd->tx_max_coalesced_frames = vptr->options.tx_intsup; + ecmd->rx_max_coalesced_frames = vptr->options.rx_intsup; + + ecmd->rx_coalesce_usecs = get_pending_timer_val(vptr->options.rxqueue_timer); + ecmd->tx_coalesce_usecs = get_pending_timer_val(vptr->options.txqueue_timer); + + return 0; +} + +static int velocity_set_coalesce(struct net_device *dev, + struct ethtool_coalesce *ecmd) +{ + struct velocity_info *vptr = netdev_priv(dev); + int max_us = 0x3f * 64; + + /* 6 bits of */ + if (ecmd->tx_coalesce_usecs > max_us) + return -EINVAL; + if (ecmd->rx_coalesce_usecs > max_us) + return -EINVAL; + + if (ecmd->tx_max_coalesced_frames > 0xff) + return -EINVAL; + if (ecmd->rx_max_coalesced_frames > 0xff) + return -EINVAL; + + vptr->options.rx_intsup = ecmd->rx_max_coalesced_frames; + vptr->options.tx_intsup = ecmd->tx_max_coalesced_frames; + + set_pending_timer_val(&vptr->options.rxqueue_timer, + ecmd->rx_coalesce_usecs); + set_pending_timer_val(&vptr->options.txqueue_timer, + ecmd->tx_coalesce_usecs); + + /* Setup the interrupt suppression and queue timers */ + mac_disable_int(vptr->mac_regs); + setup_adaptive_interrupts(vptr); + setup_queue_timers(vptr); + + mac_write_int_mask(vptr->int_mask, vptr->mac_regs); + mac_clear_isr(vptr->mac_regs); + mac_enable_int(vptr->mac_regs); + + return 0; +} + static const struct ethtool_ops velocity_ethtool_ops = { .get_settings = velocity_get_settings, .set_settings = velocity_set_settings, .get_drvinfo = velocity_get_drvinfo, + .set_tx_csum = ethtool_op_set_tx_csum, + .get_tx_csum = ethtool_op_get_tx_csum, .get_wol = velocity_ethtool_get_wol, .set_wol = velocity_ethtool_set_wol, .get_msglevel = velocity_get_msglevel, .set_msglevel = velocity_set_msglevel, + .set_sg = ethtool_op_set_sg, .get_link = velocity_get_link, + .get_coalesce = velocity_get_coalesce, + .set_coalesce = velocity_set_coalesce, .begin = velocity_ethtool_up, .complete = velocity_ethtool_down }; diff --git a/drivers/net/via-velocity.h b/drivers/net/via-velocity.h index ce894ffa7c91..ef4a0f64ba16 100644 --- a/drivers/net/via-velocity.h +++ b/drivers/net/via-velocity.h @@ -29,9 +29,10 @@ #define VELOCITY_NAME "via-velocity" #define VELOCITY_FULL_DRV_NAM "VIA Networking Velocity Family Gigabit Ethernet Adapter Driver" -#define VELOCITY_VERSION "1.14" +#define VELOCITY_VERSION "1.15" #define VELOCITY_IO_SIZE 256 +#define VELOCITY_NAPI_WEIGHT 64 #define PKT_BUF_SZ 1540 @@ -1005,7 +1006,8 @@ struct mac_regs { volatile __le32 RDBaseLo; /* 0x38 */ volatile __le16 RDIdx; /* 0x3C */ - volatile __le16 reserved_3E; + volatile u8 TQETMR; /* 0x3E, VT3216 and above only */ + volatile u8 RQETMR; /* 0x3F, VT3216 and above only */ volatile __le32 TDBaseLo[4]; /* 0x40 */ @@ -1421,7 +1423,6 @@ enum velocity_msg_level { */ #define VELOCITY_FLAGS_TAGGING 0x00000001UL -#define VELOCITY_FLAGS_TX_CSUM 0x00000002UL #define VELOCITY_FLAGS_RX_CSUM 0x00000004UL #define VELOCITY_FLAGS_IP_ALIGN 0x00000008UL #define VELOCITY_FLAGS_VAL_PKT_LEN 0x00000010UL @@ -1491,6 +1492,10 @@ struct velocity_opt { int rx_bandwidth_hi; int rx_bandwidth_lo; int rx_bandwidth_en; + int rxqueue_timer; + int txqueue_timer; + int tx_intsup; + int rx_intsup; u32 flags; }; @@ -1557,6 +1562,8 @@ struct velocity_info { u32 ticks; u8 rev_id; + + struct napi_struct napi; }; /** diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 74636c5c41f0..c708ecc3cb2e 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -428,8 +428,8 @@ again: /* Out of packets? */ if (received < budget) { napi_complete(napi); - if (unlikely(!vi->rvq->vq_ops->enable_cb(vi->rvq)) - && napi_schedule_prep(napi)) { + if (unlikely(!vi->rvq->vq_ops->enable_cb(vi->rvq)) && + napi_schedule_prep(napi)) { vi->rvq->vq_ops->disable_cb(vi->rvq); __napi_schedule(napi); goto again; @@ -890,9 +890,9 @@ static int virtnet_probe(struct virtio_device *vdev) INIT_DELAYED_WORK(&vi->refill, refill_work); /* If we can receive ANY GSO packets, we must allocate large ones. */ - if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) - || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) - || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN)) + if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) || + virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) || + virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN)) vi->big_packets = true; if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index a4c97e786ee5..1ceb9d0f8b97 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1780,8 +1780,8 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter) set_flag_le64(&devRead->misc.uptFeatures, UPT1_F_LRO); devRead->misc.maxNumRxSG = cpu_to_le16(1 + MAX_SKB_FRAGS); } - if ((adapter->netdev->features & NETIF_F_HW_VLAN_RX) - && adapter->vlan_grp) { + if ((adapter->netdev->features & NETIF_F_HW_VLAN_RX) && + adapter->vlan_grp) { set_flag_le64(&devRead->misc.uptFeatures, UPT1_F_RXVLAN); } diff --git a/drivers/net/vxge/vxge-main.c b/drivers/net/vxge/vxge-main.c index e21358e82c74..f1c4b2a1e867 100644 --- a/drivers/net/vxge/vxge-main.c +++ b/drivers/net/vxge/vxge-main.c @@ -2510,9 +2510,9 @@ static int vxge_add_isr(struct vxgedev *vdev) } /* Point to next vpath handler */ - if (((intr_idx + 1) % VXGE_HW_VPATH_MSIX_ACTIVE == 0) - && (vp_idx < (vdev->no_of_vpath - 1))) - vp_idx++; + if (((intr_idx + 1) % VXGE_HW_VPATH_MSIX_ACTIVE == 0) && + (vp_idx < (vdev->no_of_vpath - 1))) + vp_idx++; } intr_cnt = vdev->max_vpath_supported * 2; diff --git a/drivers/net/vxge/vxge-traffic.c b/drivers/net/vxge/vxge-traffic.c index 61ce754fa9d0..2c012f4ce465 100644 --- a/drivers/net/vxge/vxge-traffic.c +++ b/drivers/net/vxge/vxge-traffic.c @@ -1963,14 +1963,14 @@ enum vxge_hw_status __vxge_hw_vpath_alarm_process( val64 = readq(&vp_reg->asic_ntwk_vp_err_reg); if (((val64 & - VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_FLT) && - (!(val64 & + VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_FLT) && + (!(val64 & VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_OK))) || ((val64 & - VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_FLT_OCCURR) - && (!(val64 & + VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_FLT_OCCURR) && + (!(val64 & VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_OK_OCCURR) - ))) { + ))) { sw_stats->error_stats.network_sustained_fault++; writeq( @@ -1983,14 +1983,14 @@ enum vxge_hw_status __vxge_hw_vpath_alarm_process( } if (((val64 & - VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_OK) && - (!(val64 & + VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_OK) && + (!(val64 & VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_FLT))) || ((val64 & - VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_OK_OCCURR) - && (!(val64 & + VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_OK_OCCURR) && + (!(val64 & VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_FLT_OCCURR) - ))) { + ))) { sw_stats->error_stats.network_sustained_ok++; diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c index cd8f04afed8f..b36bf96eb502 100644 --- a/drivers/net/wan/cosa.c +++ b/drivers/net/wan/cosa.c @@ -907,6 +907,7 @@ static ssize_t cosa_write(struct file *file, current->state = TASK_RUNNING; chan->tx_status = 1; spin_unlock_irqrestore(&cosa->lock, flags); + up(&chan->wsem); return -ERESTARTSYS; } } diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c index 15d353f268b5..421d0715310e 100644 --- a/drivers/net/wan/dlci.c +++ b/drivers/net/wan/dlci.c @@ -77,7 +77,7 @@ static int dlci_header(struct sk_buff *skb, struct net_device *dev, dlp = netdev_priv(dev); hdr.control = FRAD_I_UI; - switch(type) + switch (type) { case ETH_P_IP: hdr.IP_NLPID = FRAD_P_IP; @@ -130,7 +130,7 @@ static void dlci_receive(struct sk_buff *skb, struct net_device *dev) dev->stats.rx_errors++; } else - switch(hdr->IP_NLPID) + switch (hdr->IP_NLPID) { case FRAD_P_PADDING: if (hdr->NLPID != FRAD_P_SNAP) @@ -208,7 +208,7 @@ static int dlci_config(struct net_device *dev, struct dlci_conf __user *conf, in if (!get) { - if(copy_from_user(&config, conf, sizeof(struct dlci_conf))) + if (copy_from_user(&config, conf, sizeof(struct dlci_conf))) return -EFAULT; if (config.flags & ~DLCI_VALID_FLAGS) return(-EINVAL); @@ -222,7 +222,7 @@ static int dlci_config(struct net_device *dev, struct dlci_conf __user *conf, in if (get) { - if(copy_to_user(conf, &dlp->config, sizeof(struct dlci_conf))) + if (copy_to_user(conf, &dlp->config, sizeof(struct dlci_conf))) return -EFAULT; } @@ -238,7 +238,7 @@ static int dlci_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) dlp = netdev_priv(dev); - switch(cmd) + switch (cmd) { case DLCI_GET_SLAVE: if (!*(short *)(dev->dev_addr)) @@ -417,7 +417,7 @@ static int dlci_ioctl(unsigned int cmd, void __user *arg) if (!capable(CAP_NET_ADMIN)) return(-EPERM); - if(copy_from_user(&add, arg, sizeof(struct dlci_add))) + if (copy_from_user(&add, arg, sizeof(struct dlci_add))) return -EFAULT; switch (cmd) @@ -426,7 +426,7 @@ static int dlci_ioctl(unsigned int cmd, void __user *arg) err = dlci_add(&add); if (!err) - if(copy_to_user(arg, &add, sizeof(struct dlci_add))) + if (copy_to_user(arg, &add, sizeof(struct dlci_add))) return -EFAULT; break; diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c index beda387f2fc7..9bc2e3649157 100644 --- a/drivers/net/wan/farsync.c +++ b/drivers/net/wan/farsync.c @@ -1346,8 +1346,8 @@ do_bottom_half_tx(struct fst_card_info *card) dev = port_to_dev(port); while (!(FST_RDB(card, txDescrRing[pi][port->txpos].bits) & - DMA_OWN) - && !(card->dmatx_in_progress)) { + DMA_OWN) && + !(card->dmatx_in_progress)) { /* * There doesn't seem to be a txdone event per-se * We seem to have to deduce it, by checking the DMA_OWN @@ -1379,8 +1379,8 @@ do_bottom_half_tx(struct fst_card_info *card) */ FST_WRW(card, txDescrRing[pi][port->txpos].bcnt, cnv_bcnt(skb->len)); - if ((skb->len < FST_MIN_DMA_LEN) - || (card->family == FST_FAMILY_TXP)) { + if ((skb->len < FST_MIN_DMA_LEN) || + (card->family == FST_FAMILY_TXP)) { /* Enqueue the packet with normal io */ memcpy_toio(card->mem + BUF_OFFSET(txBuffer[pi] @@ -2030,8 +2030,8 @@ fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /* Sanity check the parameters. We don't support partial writes * when going over the top */ - if (wrthdr.size > FST_MEMSIZE || wrthdr.offset > FST_MEMSIZE - || wrthdr.size + wrthdr.offset > FST_MEMSIZE) { + if (wrthdr.size > FST_MEMSIZE || wrthdr.offset > FST_MEMSIZE || + wrthdr.size + wrthdr.offset > FST_MEMSIZE) { return -ENXIO; } diff --git a/drivers/net/wan/hdlc.c b/drivers/net/wan/hdlc.c index cc07236ea734..9937bbab938d 100644 --- a/drivers/net/wan/hdlc.c +++ b/drivers/net/wan/hdlc.c @@ -57,7 +57,7 @@ static int hdlc_rcv(struct sk_buff *skb, struct net_device *dev, { struct hdlc_device *hdlc = dev_to_hdlc(dev); - if (dev_net(dev) != &init_net) { + if (!net_eq(dev_net(dev), &init_net)) { kfree_skb(skb); return 0; } @@ -102,7 +102,7 @@ static int hdlc_device_event(struct notifier_block *this, unsigned long event, unsigned long flags; int on; - if (dev_net(dev) != &init_net) + if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; if (!(dev->priv_flags & IFF_WAN_HDLC)) diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 840cff72a0f1..a7d4fc1a03a2 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -1214,10 +1214,10 @@ static int fr_ioctl(struct net_device *dev, struct ifreq *ifr) return 0; case IF_PROTO_FR: - if(!capable(CAP_NET_ADMIN)) + if (!capable(CAP_NET_ADMIN)) return -EPERM; - if(dev->flags & IFF_UP) + if (dev->flags & IFF_UP) return -EBUSY; if (copy_from_user(&new_settings, fr_s, size)) @@ -1263,7 +1263,7 @@ static int fr_ioctl(struct net_device *dev, struct ifreq *ifr) if (dev_to_hdlc(dev)->proto != &proto) /* Different proto */ return -EINVAL; - if(!capable(CAP_NET_ADMIN)) + if (!capable(CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&pvc, ifr->ifr_settings.ifs_ifsu.fr_pvc, diff --git a/drivers/net/wan/pc300_drv.c b/drivers/net/wan/pc300_drv.c index 79dabc557bd3..aec4d3955420 100644 --- a/drivers/net/wan/pc300_drv.c +++ b/drivers/net/wan/pc300_drv.c @@ -514,8 +514,8 @@ static int dma_buf_read(pc300_t * card, int ch, struct sk_buff *skb) RX_BD_ADDR(ch, chan->rx_first_bd)); while ((status = cpc_readb(&ptdescr->status)) & DST_OSB) { nchar = cpc_readw(&ptdescr->len); - if ((status & (DST_OVR | DST_CRC | DST_RBIT | DST_SHRT | DST_ABT)) - || (nchar > BD_DEF_LEN)) { + if ((status & (DST_OVR | DST_CRC | DST_RBIT | DST_SHRT | DST_ABT)) || + (nchar > BD_DEF_LEN)) { if (nchar > BD_DEF_LEN) status |= DST_RBIT; @@ -1428,8 +1428,7 @@ static void falc_update_stats(pc300_t * card, int ch) if (((conf->media == IF_IFACE_T1) && (cpc_readb(falcbase + F_REG(FRS1, ch)) & FRS1_LLBAD) && - (!(cpc_readb(falcbase + F_REG(FRS1, ch)) & FRS1_PDEN))) - || + (!(cpc_readb(falcbase + F_REG(FRS1, ch)) & FRS1_PDEN))) || ((conf->media == IF_IFACE_E1) && (cpc_readb(falcbase + F_REG(RSP, ch)) & RSP_LLBAD))) { pfalc->prbs = 2; @@ -2285,8 +2284,8 @@ static void falc_e1_intr(pc300_t * card, int ch) if (gis & GIS_ISR1) { isr1 = cpc_readb(falcbase + F_REG(FISR1, ch)); if (isr1 & FISR1_XMB) { - if ((pfalc->xmb_cause & 2) - && pfalc->multiframe_mode) { + if ((pfalc->xmb_cause & 2) && + pfalc->multiframe_mode) { if (cpc_readb (falcbase + F_REG(FRS0, ch)) & (FRS0_LOS | FRS0_AIS | FRS0_LFA)) { cpc_writeb(falcbase + F_REG(XSP, ch), @@ -2639,9 +2638,9 @@ static int cpc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) !(cpc_readb (scabase + M_REG(CTL, ch)) & CTL_DTR); /* There is no DSR in HD64572 */ } - if (!arg - || copy_to_user(arg, &pc300status, sizeof(pc300status_t))) - return -EINVAL; + if (!arg || + copy_to_user(arg, &pc300status, sizeof(pc300status_t))) + return -EINVAL; return 0; } diff --git a/drivers/net/wan/sbni.c b/drivers/net/wan/sbni.c index 1cc24a45f003..25477b5cde47 100644 --- a/drivers/net/wan/sbni.c +++ b/drivers/net/wan/sbni.c @@ -195,9 +195,9 @@ static unsigned int netcard_portlist[ ] __initdata = { static inline int __init sbni_isa_probe( struct net_device *dev ) { - if( dev->base_addr > 0x1ff - && request_region( dev->base_addr, SBNI_IO_EXTENT, dev->name ) - && sbni_probe1( dev, dev->base_addr, dev->irq ) ) + if( dev->base_addr > 0x1ff && + request_region( dev->base_addr, SBNI_IO_EXTENT, dev->name ) && + sbni_probe1( dev, dev->base_addr, dev->irq ) ) return 0; else { @@ -286,8 +286,8 @@ static int __init sbni_init(struct net_device *dev) for( i = 0; netcard_portlist[ i ]; ++i ) { int ioaddr = netcard_portlist[ i ]; - if( request_region( ioaddr, SBNI_IO_EXTENT, dev->name ) - && sbni_probe1( dev, ioaddr, 0 )) + if( request_region( ioaddr, SBNI_IO_EXTENT, dev->name ) && + sbni_probe1( dev, ioaddr, 0 )) return 0; } @@ -306,9 +306,9 @@ sbni_pci_probe( struct net_device *dev ) unsigned long pci_ioaddr; u16 subsys; - if( pdev->vendor != SBNI_PCI_VENDOR - && pdev->device != SBNI_PCI_DEVICE ) - continue; + if( pdev->vendor != SBNI_PCI_VENDOR && + pdev->device != SBNI_PCI_DEVICE ) + continue; pci_ioaddr = pci_resource_start( pdev, 0 ); pci_irq_line = pdev->irq; @@ -977,8 +977,8 @@ check_fhdr( u32 ioaddr, u32 *framelen, u32 *frameno, u32 *ack, *ack = *framelen & FRAME_ACK_MASK; *is_first = (*framelen & FRAME_FIRST) != 0; - if( (*framelen &= FRAME_LEN_MASK) < 6 - || *framelen > SBNI_MAX_FRAME - 3 ) + if( (*framelen &= FRAME_LEN_MASK) < 6 || + *framelen > SBNI_MAX_FRAME - 3 ) return 0; value = inb( ioaddr + DAT ); @@ -1173,10 +1173,10 @@ sbni_open( struct net_device *dev ) if( dev->base_addr < 0x400 ) { /* ISA only */ struct net_device **p = sbni_cards; for( ; *p && p < sbni_cards + SBNI_MAX_NUM_CARDS; ++p ) - if( (*p)->irq == dev->irq - && ((*p)->base_addr == dev->base_addr + 4 - || (*p)->base_addr == dev->base_addr - 4) - && (*p)->flags & IFF_UP ) { + if( (*p)->irq == dev->irq && + ((*p)->base_addr == dev->base_addr + 4 || + (*p)->base_addr == dev->base_addr - 4) && + (*p)->flags & IFF_UP ) { ((struct net_local *) (netdev_priv(*p))) ->second = dev; diff --git a/drivers/net/wan/sealevel.c b/drivers/net/wan/sealevel.c index 3b3ee05bc462..61249f489e37 100644 --- a/drivers/net/wan/sealevel.c +++ b/drivers/net/wan/sealevel.c @@ -84,8 +84,7 @@ static int sealevel_open(struct net_device *d) * Link layer up. */ - switch (unit) - { + switch (unit) { case 0: err = z8530_sync_dma_open(d, slvl->chan); break; @@ -133,8 +132,7 @@ static int sealevel_close(struct net_device *d) hdlc_close(d); netif_stop_queue(d); - switch (unit) - { + switch (unit) { case 0: z8530_sync_dma_close(d, slvl->chan); break; @@ -342,8 +340,7 @@ static void __exit slvl_shutdown(struct slvl_board *b) z8530_shutdown(&b->board); - for (u = 0; u < 2; u++) - { + for (u = 0; u < 2; u++) { struct net_device *d = b->dev[u].chan->netdevice; unregister_hdlc_device(d); free_netdev(d); @@ -391,7 +388,7 @@ static int __init slvl_init_module(void) static void __exit slvl_cleanup_module(void) { - if(slvl_unit) + if (slvl_unit) slvl_shutdown(slvl_unit); } diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c index 3c325d77939b..b9f520b7db6a 100644 --- a/drivers/net/wan/x25_asy.c +++ b/drivers/net/wan/x25_asy.c @@ -657,8 +657,8 @@ static void x25_asy_unesc(struct x25_asy *sl, unsigned char s) switch (s) { case X25_END: - if (!test_and_clear_bit(SLF_ERROR, &sl->flags) - && sl->rcount > 2) + if (!test_and_clear_bit(SLF_ERROR, &sl->flags) && + sl->rcount > 2) x25_asy_bump(sl); clear_bit(SLF_ESCAPE, &sl->flags); sl->rcount = 0; diff --git a/drivers/net/wireless/iwlwifi/iwl-tx.c b/drivers/net/wireless/iwlwifi/iwl-tx.c index 888a8e9fe9ef..58b132f9cf28 100644 --- a/drivers/net/wireless/iwlwifi/iwl-tx.c +++ b/drivers/net/wireless/iwlwifi/iwl-tx.c @@ -1350,8 +1350,16 @@ int iwl_tx_agg_stop(struct iwl_priv *priv , const u8 *ra, u16 tid) return -ENXIO; } + if (priv->stations[sta_id].tid[tid].agg.state == + IWL_EMPTYING_HW_QUEUE_ADDBA) { + IWL_DEBUG_HT(priv, "AGG stop before setup done\n"); + ieee80211_stop_tx_ba_cb_irqsafe(priv->hw, ra, tid); + priv->stations[sta_id].tid[tid].agg.state = IWL_AGG_OFF; + return 0; + } + if (priv->stations[sta_id].tid[tid].agg.state != IWL_AGG_ON) - IWL_WARN(priv, "Stopping AGG while state not IWL_AGG_ON\n"); + IWL_WARN(priv, "Stopping AGG while state not ON or starting\n"); tid_data = &priv->stations[sta_id].tid[tid]; ssn = (tid_data->seq_number & IEEE80211_SCTL_SEQ) >> 4; diff --git a/drivers/net/yellowfin.c b/drivers/net/yellowfin.c index d831dfca0976..0f773a9a3ff2 100644 --- a/drivers/net/yellowfin.c +++ b/drivers/net/yellowfin.c @@ -944,8 +944,8 @@ static irqreturn_t yellowfin_interrupt(int irq, void *dev_instance) dev_kfree_skb_irq(skb); yp->tx_skbuff[entry] = NULL; } - if (yp->tx_full - && yp->cur_tx - yp->dirty_tx < TX_QUEUE_SIZE - 4) { + if (yp->tx_full && + yp->cur_tx - yp->dirty_tx < TX_QUEUE_SIZE - 4) { /* The ring is no longer full, clear tbusy. */ yp->tx_full = 0; netif_wake_queue(dev); @@ -1014,8 +1014,8 @@ static irqreturn_t yellowfin_interrupt(int irq, void *dev_instance) } #endif - if (yp->tx_full - && yp->cur_tx - dirty_tx < TX_QUEUE_SIZE - 2) { + if (yp->tx_full && + yp->cur_tx - dirty_tx < TX_QUEUE_SIZE - 2) { /* The ring is no longer full, clear tbusy. */ yp->tx_full = 0; netif_wake_queue(dev); diff --git a/drivers/net/znet.c b/drivers/net/znet.c index a97d894d26fb..bc5ae0f6e934 100644 --- a/drivers/net/znet.c +++ b/drivers/net/znet.c @@ -697,8 +697,8 @@ static void znet_rx(struct net_device *dev) the same area of the backwards links we now have. This allows us to pass packets to the upper layers in the order they were received -- important for fast-path sequential operations. */ - while (znet->rx_start + cur_frame_end_offset != znet->rx_cur - && ++boguscount < 5) { + while (znet->rx_start + cur_frame_end_offset != znet->rx_cur && + ++boguscount < 5) { unsigned short hi_cnt, lo_cnt, hi_status, lo_status; int count, status; diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c index e5f8fc164fd3..b952ebc7a78b 100644 --- a/drivers/pci/dmar.c +++ b/drivers/pci/dmar.c @@ -609,6 +609,9 @@ int __init check_zero_address(void) dmi_get_system_info(DMI_BIOS_VENDOR), dmi_get_system_info(DMI_BIOS_VERSION), dmi_get_system_info(DMI_PRODUCT_VERSION)); +#ifdef CONFIG_DMAR + dmar_disabled = 1; +#endif return 0; } break; diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c index 0a8f735f6c4a..ab64522aaa64 100644 --- a/drivers/platform/x86/acerhdf.c +++ b/drivers/platform/x86/acerhdf.c @@ -52,7 +52,7 @@ */ #undef START_IN_KERNEL_MODE -#define DRV_VER "0.5.17" +#define DRV_VER "0.5.18" /* * According to the Atom N270 datasheet, @@ -61,7 +61,7 @@ * measured by the on-die thermal monitor are within 0 <= Tj <= 90. So, * assume 89°C is critical temperature. */ -#define ACERHDF_TEMP_CRIT 89 +#define ACERHDF_TEMP_CRIT 89000 #define ACERHDF_FAN_OFF 0 #define ACERHDF_FAN_AUTO 1 @@ -69,7 +69,7 @@ * No matter what value the user puts into the fanon variable, turn on the fan * at 80 degree Celsius to prevent hardware damage */ -#define ACERHDF_MAX_FANON 80 +#define ACERHDF_MAX_FANON 80000 /* * Maximum interval between two temperature checks is 15 seconds, as the die @@ -85,8 +85,8 @@ static int kernelmode; #endif static unsigned int interval = 10; -static unsigned int fanon = 63; -static unsigned int fanoff = 58; +static unsigned int fanon = 63000; +static unsigned int fanoff = 58000; static unsigned int verbose; static unsigned int fanstate = ACERHDF_FAN_AUTO; static char force_bios[16]; @@ -171,7 +171,7 @@ static int acerhdf_get_temp(int *temp) if (ec_read(bios_cfg->tempreg, &read_temp)) return -EINVAL; - *temp = read_temp; + *temp = read_temp * 1000; return 0; } diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index d93108d148fc..a848c7e20aeb 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -1680,36 +1680,48 @@ static void tpacpi_remove_driver_attributes(struct device_driver *drv) | (__bv1) << 8 | (__bv2) } #define TPV_Q_X(__v, __bid1, __bid2, __bv1, __bv2, \ - __eid1, __eid2, __ev1, __ev2) \ + __eid, __ev1, __ev2) \ { .vendor = (__v), \ .bios = TPID(__bid1, __bid2), \ - .ec = TPID(__eid1, __eid2), \ + .ec = __eid, \ .quirks = (__ev1) << 24 | (__ev2) << 16 \ | (__bv1) << 8 | (__bv2) } #define TPV_QI0(__id1, __id2, __bv1, __bv2) \ TPV_Q(PCI_VENDOR_ID_IBM, __id1, __id2, __bv1, __bv2) +/* Outdated IBM BIOSes often lack the EC id string */ #define TPV_QI1(__id1, __id2, __bv1, __bv2, __ev1, __ev2) \ TPV_Q_X(PCI_VENDOR_ID_IBM, __id1, __id2, \ - __bv1, __bv2, __id1, __id2, __ev1, __ev2) + __bv1, __bv2, TPID(__id1, __id2), \ + __ev1, __ev2), \ + TPV_Q_X(PCI_VENDOR_ID_IBM, __id1, __id2, \ + __bv1, __bv2, TPACPI_MATCH_UNKNOWN, \ + __ev1, __ev2) +/* Outdated IBM BIOSes often lack the EC id string */ #define TPV_QI2(__bid1, __bid2, __bv1, __bv2, \ __eid1, __eid2, __ev1, __ev2) \ TPV_Q_X(PCI_VENDOR_ID_IBM, __bid1, __bid2, \ - __bv1, __bv2, __eid1, __eid2, __ev1, __ev2) + __bv1, __bv2, TPID(__eid1, __eid2), \ + __ev1, __ev2), \ + TPV_Q_X(PCI_VENDOR_ID_IBM, __bid1, __bid2, \ + __bv1, __bv2, TPACPI_MATCH_UNKNOWN, \ + __ev1, __ev2) #define TPV_QL0(__id1, __id2, __bv1, __bv2) \ TPV_Q(PCI_VENDOR_ID_LENOVO, __id1, __id2, __bv1, __bv2) #define TPV_QL1(__id1, __id2, __bv1, __bv2, __ev1, __ev2) \ TPV_Q_X(PCI_VENDOR_ID_LENOVO, __id1, __id2, \ - __bv1, __bv2, __id1, __id2, __ev1, __ev2) + __bv1, __bv2, TPID(__id1, __id2), \ + __ev1, __ev2) #define TPV_QL2(__bid1, __bid2, __bv1, __bv2, \ __eid1, __eid2, __ev1, __ev2) \ TPV_Q_X(PCI_VENDOR_ID_LENOVO, __bid1, __bid2, \ - __bv1, __bv2, __eid1, __eid2, __ev1, __ev2) + __bv1, __bv2, TPID(__eid1, __eid2), \ + __ev1, __ev2) static const struct tpacpi_quirk tpacpi_bios_version_qtable[] __initconst = { /* Numeric models ------------------ */ @@ -6313,7 +6325,7 @@ static int brightness_write(char *buf) * Doing it this way makes the syscall restartable in case of EINTR */ rc = brightness_set(level); - return (rc == -EINTR)? ERESTARTSYS : rc; + return (rc == -EINTR)? -ERESTARTSYS : rc; } static struct ibm_struct brightness_driver_data = { diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 5fd2da494d08..c968cc31cd86 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -164,8 +164,8 @@ void scsi_remove_host(struct Scsi_Host *shost) return; } spin_unlock_irqrestore(shost->host_lock, flags); - mutex_unlock(&shost->scan_mutex); scsi_forget_host(shost); + mutex_unlock(&shost->scan_mutex); scsi_proc_host_rm(shost); spin_lock_irqsave(shost->host_lock, flags); diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 0547a7f44d42..47291bcff0d5 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -952,16 +952,6 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, return SCSI_SCAN_LUN_PRESENT; } -static inline void scsi_destroy_sdev(struct scsi_device *sdev) -{ - scsi_device_set_state(sdev, SDEV_DEL); - if (sdev->host->hostt->slave_destroy) - sdev->host->hostt->slave_destroy(sdev); - transport_destroy_device(&sdev->sdev_gendev); - put_device(&sdev->sdev_dev); - put_device(&sdev->sdev_gendev); -} - #ifdef CONFIG_SCSI_LOGGING /** * scsi_inq_str - print INQUIRY data from min to max index, strip trailing whitespace @@ -1139,7 +1129,7 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget, } } } else - scsi_destroy_sdev(sdev); + __scsi_remove_device(sdev); out: return res; } @@ -1500,7 +1490,7 @@ static int scsi_report_lun_scan(struct scsi_target *starget, int bflags, /* * the sdev we used didn't appear in the report luns scan */ - scsi_destroy_sdev(sdev); + __scsi_remove_device(sdev); return ret; } @@ -1710,7 +1700,7 @@ static void scsi_sysfs_add_devices(struct Scsi_Host *shost) shost_for_each_device(sdev, shost) { if (!scsi_host_scan_allowed(shost) || scsi_sysfs_add_sdev(sdev) != 0) - scsi_destroy_sdev(sdev); + __scsi_remove_device(sdev); } } @@ -1943,7 +1933,7 @@ void scsi_free_host_dev(struct scsi_device *sdev) { BUG_ON(sdev->id != sdev->host->this_id); - scsi_destroy_sdev(sdev); + __scsi_remove_device(sdev); } EXPORT_SYMBOL(scsi_free_host_dev); diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 5c7eb63a19d1..392d8db33905 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -854,82 +854,73 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev) transport_configure_device(&starget->dev); error = device_add(&sdev->sdev_gendev); if (error) { - put_device(sdev->sdev_gendev.parent); printk(KERN_INFO "error 1\n"); - return error; + goto out_remove; } error = device_add(&sdev->sdev_dev); if (error) { printk(KERN_INFO "error 2\n"); - goto clean_device; + device_del(&sdev->sdev_gendev); + goto out_remove; } + transport_add_device(&sdev->sdev_gendev); + sdev->is_visible = 1; /* create queue files, which may be writable, depending on the host */ if (sdev->host->hostt->change_queue_depth) error = device_create_file(&sdev->sdev_gendev, &sdev_attr_queue_depth_rw); else error = device_create_file(&sdev->sdev_gendev, &dev_attr_queue_depth); - if (error) { - __scsi_remove_device(sdev); - goto out; - } + if (error) + goto out_remove; + if (sdev->host->hostt->change_queue_type) error = device_create_file(&sdev->sdev_gendev, &sdev_attr_queue_type_rw); else error = device_create_file(&sdev->sdev_gendev, &dev_attr_queue_type); - if (error) { - __scsi_remove_device(sdev); - goto out; - } + if (error) + goto out_remove; error = bsg_register_queue(rq, &sdev->sdev_gendev, NULL, NULL); if (error) + /* we're treating error on bsg register as non-fatal, + * so pretend nothing went wrong */ sdev_printk(KERN_INFO, sdev, "Failed to register bsg queue, errno=%d\n", error); - /* we're treating error on bsg register as non-fatal, so pretend - * nothing went wrong */ - error = 0; - /* add additional host specific attributes */ if (sdev->host->hostt->sdev_attrs) { for (i = 0; sdev->host->hostt->sdev_attrs[i]; i++) { error = device_create_file(&sdev->sdev_gendev, sdev->host->hostt->sdev_attrs[i]); - if (error) { - __scsi_remove_device(sdev); - goto out; - } + if (error) + goto out_remove; } } - transport_add_device(&sdev->sdev_gendev); - out: - return error; - - clean_device: - scsi_device_set_state(sdev, SDEV_CANCEL); - - device_del(&sdev->sdev_gendev); - transport_destroy_device(&sdev->sdev_gendev); - put_device(&sdev->sdev_dev); - put_device(&sdev->sdev_gendev); + return 0; + out_remove: + __scsi_remove_device(sdev); return error; + } void __scsi_remove_device(struct scsi_device *sdev) { struct device *dev = &sdev->sdev_gendev; - if (scsi_device_set_state(sdev, SDEV_CANCEL) != 0) - return; + if (sdev->is_visible) { + if (scsi_device_set_state(sdev, SDEV_CANCEL) != 0) + return; - bsg_unregister_queue(sdev->request_queue); - device_unregister(&sdev->sdev_dev); - transport_remove_device(dev); - device_del(dev); + bsg_unregister_queue(sdev->request_queue); + device_unregister(&sdev->sdev_dev); + transport_remove_device(dev); + device_del(dev); + } else + put_device(&sdev->sdev_dev); scsi_device_set_state(sdev, SDEV_DEL); if (sdev->host->hostt->slave_destroy) sdev->host->hostt->slave_destroy(sdev); diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c index 88da97745710..84be62149c6c 100644 --- a/drivers/scsi/sd_dif.c +++ b/drivers/scsi/sd_dif.c @@ -418,7 +418,7 @@ error: __func__, virt, phys, be32_to_cpu(sdt->ref_tag), be16_to_cpu(sdt->app_tag)); - return -EIO; + return -EILSEQ; } /* diff --git a/drivers/serial/bcm63xx_uart.c b/drivers/serial/bcm63xx_uart.c index beddaa6e9069..37ad0c449937 100644 --- a/drivers/serial/bcm63xx_uart.c +++ b/drivers/serial/bcm63xx_uart.c @@ -242,7 +242,7 @@ static void bcm_uart_do_rx(struct uart_port *port) * higher than fifo size anyway since we're much faster than * serial port */ max_count = 32; - tty = port->info->port.tty; + tty = port->state->port.tty; do { unsigned int iestat, c, cstat; char flag; @@ -318,7 +318,7 @@ static void bcm_uart_do_tx(struct uart_port *port) return; } - xmit = &port->info->xmit; + xmit = &port->state->xmit; if (uart_circ_empty(xmit)) goto txq_empty; diff --git a/drivers/serial/of_serial.c b/drivers/serial/of_serial.c index 02406ba6da1c..cdf172eda2e3 100644 --- a/drivers/serial/of_serial.c +++ b/drivers/serial/of_serial.c @@ -161,6 +161,7 @@ static int of_platform_serial_remove(struct of_device *ofdev) static struct of_device_id __devinitdata of_platform_serial_table[] = { { .type = "serial", .compatible = "ns8250", .data = (void *)PORT_8250, }, { .type = "serial", .compatible = "ns16450", .data = (void *)PORT_16450, }, + { .type = "serial", .compatible = "ns16550a", .data = (void *)PORT_16550A, }, { .type = "serial", .compatible = "ns16550", .data = (void *)PORT_16550, }, { .type = "serial", .compatible = "ns16750", .data = (void *)PORT_16750, }, { .type = "serial", .compatible = "ns16850", .data = (void *)PORT_16850, }, diff --git a/drivers/serial/suncore.c b/drivers/serial/suncore.c index a2d4a19550ab..ed7d958b0a01 100644 --- a/drivers/serial/suncore.c +++ b/drivers/serial/suncore.c @@ -53,20 +53,21 @@ void sunserial_unregister_minors(struct uart_driver *drv, int count) EXPORT_SYMBOL(sunserial_unregister_minors); int sunserial_console_match(struct console *con, struct device_node *dp, - struct uart_driver *drv, int line) + struct uart_driver *drv, int line, bool ignore_line) { - int off; - if (!con || of_console_device != dp) return 0; - off = 0; - if (of_console_options && - *of_console_options == 'b') - off = 1; + if (!ignore_line) { + int off = 0; - if ((line & 1) != off) - return 0; + if (of_console_options && + *of_console_options == 'b') + off = 1; + + if ((line & 1) != off) + return 0; + } con->index = line; drv->cons = con; @@ -76,23 +77,24 @@ int sunserial_console_match(struct console *con, struct device_node *dp, } EXPORT_SYMBOL(sunserial_console_match); -void -sunserial_console_termios(struct console *con) +void sunserial_console_termios(struct console *con, struct device_node *uart_dp) { - struct device_node *dp; - const char *od, *mode, *s; + const char *mode, *s; char mode_prop[] = "ttyX-mode"; int baud, bits, stop, cflag; char parity; - dp = of_find_node_by_path("/options"); - od = of_get_property(dp, "output-device", NULL); - if (!strcmp(od, "rsc")) { - mode = of_get_property(of_console_device, + if (!strcmp(uart_dp->name, "rsc") || + !strcmp(uart_dp->name, "rsc-console") || + !strcmp(uart_dp->name, "rsc-control")) { + mode = of_get_property(uart_dp, "ssp-console-modes", NULL); if (!mode) mode = "115200,8,n,1,-"; + } else if (!strcmp(uart_dp->name, "lom-console")) { + mode = "9600,8,n,1,-"; } else { + struct device_node *dp; char c; c = 'a'; @@ -101,6 +103,7 @@ sunserial_console_termios(struct console *con) mode_prop[3] = c; + dp = of_find_node_by_path("/options"); mode = of_get_property(dp, mode_prop, NULL); if (!mode) mode = "9600,8,n,1,-"; diff --git a/drivers/serial/suncore.h b/drivers/serial/suncore.h index 042668aa602e..db2057936c31 100644 --- a/drivers/serial/suncore.h +++ b/drivers/serial/suncore.h @@ -26,7 +26,8 @@ extern int sunserial_register_minors(struct uart_driver *, int); extern void sunserial_unregister_minors(struct uart_driver *, int); extern int sunserial_console_match(struct console *, struct device_node *, - struct uart_driver *, int); -extern void sunserial_console_termios(struct console *); + struct uart_driver *, int, bool); +extern void sunserial_console_termios(struct console *, + struct device_node *); #endif /* !(_SERIAL_SUN_H) */ diff --git a/drivers/serial/sunhv.c b/drivers/serial/sunhv.c index d548652dee50..d14cca7fb88d 100644 --- a/drivers/serial/sunhv.c +++ b/drivers/serial/sunhv.c @@ -566,7 +566,7 @@ static int __devinit hv_probe(struct of_device *op, const struct of_device_id *m goto out_free_con_read_page; sunserial_console_match(&sunhv_console, op->node, - &sunhv_reg, port->line); + &sunhv_reg, port->line, false); err = uart_add_one_port(&sunhv_reg, port); if (err) diff --git a/drivers/serial/sunsab.c b/drivers/serial/sunsab.c index d1ad34128635..d514e28d0755 100644 --- a/drivers/serial/sunsab.c +++ b/drivers/serial/sunsab.c @@ -883,7 +883,7 @@ static int sunsab_console_setup(struct console *con, char *options) printk("Console: ttyS%d (SAB82532)\n", (sunsab_reg.minor - 64) + con->index); - sunserial_console_termios(con); + sunserial_console_termios(con, to_of_device(up->port.dev)->node); switch (con->cflag & CBAUD) { case B150: baud = 150; break; @@ -1027,10 +1027,12 @@ static int __devinit sab_probe(struct of_device *op, const struct of_device_id * goto out1; sunserial_console_match(SUNSAB_CONSOLE(), op->node, - &sunsab_reg, up[0].port.line); + &sunsab_reg, up[0].port.line, + false); sunserial_console_match(SUNSAB_CONSOLE(), op->node, - &sunsab_reg, up[1].port.line); + &sunsab_reg, up[1].port.line, + false); err = uart_add_one_port(&sunsab_reg, &up[0].port); if (err) @@ -1116,7 +1118,6 @@ static int __init sunsab_init(void) if (!sunsab_ports) return -ENOMEM; - sunsab_reg.cons = SUNSAB_CONSOLE(); err = sunserial_register_minors(&sunsab_reg, num_channels); if (err) { kfree(sunsab_ports); diff --git a/drivers/serial/sunsu.c b/drivers/serial/sunsu.c index 68d262b15749..170d3d68c8f0 100644 --- a/drivers/serial/sunsu.c +++ b/drivers/serial/sunsu.c @@ -1329,11 +1329,9 @@ static void sunsu_console_write(struct console *co, const char *s, */ static int __init sunsu_console_setup(struct console *co, char *options) { + static struct ktermios dummy; + struct ktermios termios; struct uart_port *port; - int baud = 9600; - int bits = 8; - int parity = 'n'; - int flow = 'n'; printk("Console: ttyS%d (SU)\n", (sunsu_reg.minor - 64) + co->index); @@ -1352,10 +1350,15 @@ static int __init sunsu_console_setup(struct console *co, char *options) */ spin_lock_init(&port->lock); - if (options) - uart_parse_options(options, &baud, &parity, &bits, &flow); + /* Get firmware console settings. */ + sunserial_console_termios(co, to_of_device(port->dev)->node); - return uart_set_options(port, co, baud, parity, bits, flow); + memset(&termios, 0, sizeof(struct ktermios)); + termios.c_cflag = co->cflag; + port->mctrl |= TIOCM_DTR; + port->ops->set_termios(port, &termios, &dummy); + + return 0; } static struct console sunsu_console = { @@ -1409,6 +1412,7 @@ static int __devinit su_probe(struct of_device *op, const struct of_device_id *m struct uart_sunsu_port *up; struct resource *rp; enum su_type type; + bool ignore_line; int err; type = su_get_type(dp); @@ -1467,8 +1471,14 @@ static int __devinit su_probe(struct of_device *op, const struct of_device_id *m up->port.ops = &sunsu_pops; + ignore_line = false; + if (!strcmp(dp->name, "rsc-console") || + !strcmp(dp->name, "lom-console")) + ignore_line = true; + sunserial_console_match(SUNSU_CONSOLE(), dp, - &sunsu_reg, up->port.line); + &sunsu_reg, up->port.line, + ignore_line); err = uart_add_one_port(&sunsu_reg, &up->port); if (err) goto out_unmap; @@ -1517,6 +1527,10 @@ static const struct of_device_id su_match[] = { .name = "serial", .compatible = "su", }, + { + .type = "serial", + .compatible = "su", + }, {}, }; MODULE_DEVICE_TABLE(of, su_match); @@ -1548,6 +1562,12 @@ static int __init sunsu_init(void) num_uart++; } } + for_each_node_by_type(dp, "serial") { + if (of_device_is_compatible(dp, "su")) { + if (su_get_type(dp) == SU_PORT_PORT) + num_uart++; + } + } if (num_uart) { err = sunserial_register_minors(&sunsu_reg, num_uart); diff --git a/drivers/serial/sunzilog.c b/drivers/serial/sunzilog.c index ef693ae22e7f..2c7a66af4f52 100644 --- a/drivers/serial/sunzilog.c +++ b/drivers/serial/sunzilog.c @@ -1180,7 +1180,7 @@ static int __init sunzilog_console_setup(struct console *con, char *options) (sunzilog_reg.minor - 64) + con->index, con->index); /* Get firmware console settings. */ - sunserial_console_termios(con); + sunserial_console_termios(con, to_of_device(up->port.dev)->node); /* Firmware console speed is limited to 150-->38400 baud so * this hackish cflag thing is OK. @@ -1416,7 +1416,8 @@ static int __devinit zs_probe(struct of_device *op, const struct of_device_id *m if (!keyboard_mouse) { if (sunserial_console_match(SUNZILOG_CONSOLE(), op->node, - &sunzilog_reg, up[0].port.line)) + &sunzilog_reg, up[0].port.line, + false)) up->flags |= SUNZILOG_FLAG_IS_CONS; err = uart_add_one_port(&sunzilog_reg, &up[0].port); if (err) { @@ -1425,7 +1426,8 @@ static int __devinit zs_probe(struct of_device *op, const struct of_device_id *m return err; } if (sunserial_console_match(SUNZILOG_CONSOLE(), op->node, - &sunzilog_reg, up[1].port.line)) + &sunzilog_reg, up[1].port.line, + false)) up->flags |= SUNZILOG_FLAG_IS_CONS; err = uart_add_one_port(&sunzilog_reg, &up[1].port); if (err) { diff --git a/drivers/staging/go7007/s2250-board.c b/drivers/staging/go7007/s2250-board.c index 8c85a9c3665a..f4a6541c3e60 100644 --- a/drivers/staging/go7007/s2250-board.c +++ b/drivers/staging/go7007/s2250-board.c @@ -261,7 +261,7 @@ static int read_reg_fp(struct i2c_client *client, u16 addr, u16 *val) memset(buf, 0xcd, 6); usb = go->hpi_context; - if (down_interruptible(&usb->i2c_lock) != 0) { + if (mutex_lock_interruptible(&usb->i2c_lock) != 0) { printk(KERN_INFO "i2c lock failed\n"); kfree(buf); return -EINTR; @@ -270,7 +270,7 @@ static int read_reg_fp(struct i2c_client *client, u16 addr, u16 *val) kfree(buf); return -EFAULT; } - up(&usb->i2c_lock); + mutex_unlock(&usb->i2c_lock); *val = (buf[0] << 8) | buf[1]; kfree(buf); diff --git a/drivers/staging/go7007/s2250-loader.h b/drivers/staging/go7007/s2250-loader.h new file mode 100644 index 000000000000..b7c301af16cc --- /dev/null +++ b/drivers/staging/go7007/s2250-loader.h @@ -0,0 +1,24 @@ +/* + * Copyright (C) 2005-2006 Micronas USA Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (Version 2) as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software Foundation, + * Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. + */ + +#ifndef _S2250_LOADER_H_ +#define _S2250_LOADER_H_ + +extern int s2250loader_init(void); +extern void s2250loader_cleanup(void); + +#endif diff --git a/drivers/staging/hv/BlkVsc.c b/drivers/staging/hv/BlkVsc.c index 51aa861292fc..a48ee3a12646 100644 --- a/drivers/staging/hv/BlkVsc.c +++ b/drivers/staging/hv/BlkVsc.c @@ -16,6 +16,7 @@ * Place - Suite 330, Boston, MA 02111-1307 USA. * * Authors: + * Haiyang Zhang <haiyangz@microsoft.com> * Hank Janssen <hjanssen@microsoft.com> * */ diff --git a/drivers/staging/hv/Channel.c b/drivers/staging/hv/Channel.c index d649ee169d95..746370e82115 100644 --- a/drivers/staging/hv/Channel.c +++ b/drivers/staging/hv/Channel.c @@ -611,7 +611,7 @@ void VmbusChannelClose(struct vmbus_channel *Channel) /* Stop callback and cancel the timer asap */ Channel->OnChannelCallback = NULL; - del_timer(&Channel->poll_timer); + del_timer_sync(&Channel->poll_timer); /* Send a closing message */ info = kmalloc(sizeof(*info) + @@ -978,14 +978,10 @@ void VmbusChannelOnChannelEvent(struct vmbus_channel *Channel) { DumpVmbusChannel(Channel); ASSERT(Channel->OnChannelCallback); -#ifdef ENABLE_POLLING - del_timer(&Channel->poll_timer); - Channel->OnChannelCallback(Channel->ChannelCallbackContext); - channel->poll_timer.expires(jiffies + usecs_to_jiffies(100); - add_timer(&channel->poll_timer); -#else + Channel->OnChannelCallback(Channel->ChannelCallbackContext); -#endif + + mod_timer(&Channel->poll_timer, jiffies + usecs_to_jiffies(100)); } /** @@ -997,10 +993,6 @@ void VmbusChannelOnTimer(unsigned long data) if (channel->OnChannelCallback) { channel->OnChannelCallback(channel->ChannelCallbackContext); -#ifdef ENABLE_POLLING - channel->poll_timer.expires(jiffies + usecs_to_jiffies(100); - add_timer(&channel->poll_timer); -#endif } } diff --git a/drivers/staging/hv/ChannelMgmt.c b/drivers/staging/hv/ChannelMgmt.c index 3db62caedcff..ef38467ed4e2 100644 --- a/drivers/staging/hv/ChannelMgmt.c +++ b/drivers/staging/hv/ChannelMgmt.c @@ -119,7 +119,7 @@ static inline void ReleaseVmbusChannel(void *context) */ void FreeVmbusChannel(struct vmbus_channel *Channel) { - del_timer(&Channel->poll_timer); + del_timer_sync(&Channel->poll_timer); /* * We have to release the channel's workqueue/thread in the vmbus's diff --git a/drivers/staging/hv/NetVsc.c b/drivers/staging/hv/NetVsc.c index d384c0ddf069..1c717f9a554e 100644 --- a/drivers/staging/hv/NetVsc.c +++ b/drivers/staging/hv/NetVsc.c @@ -15,6 +15,7 @@ * Place - Suite 330, Boston, MA 02111-1307 USA. * * Authors: + * Haiyang Zhang <haiyangz@microsoft.com> * Hank Janssen <hjanssen@microsoft.com> */ #include <linux/kernel.h> diff --git a/drivers/staging/hv/NetVsc.h b/drivers/staging/hv/NetVsc.h index 3e7112f7c755..6e0e03494126 100644 --- a/drivers/staging/hv/NetVsc.h +++ b/drivers/staging/hv/NetVsc.h @@ -16,6 +16,7 @@ * Place - Suite 330, Boston, MA 02111-1307 USA. * * Authors: + * Haiyang Zhang <haiyangz@microsoft.com> * Hank Janssen <hjanssen@microsoft.com> * */ diff --git a/drivers/staging/hv/StorVsc.c b/drivers/staging/hv/StorVsc.c index 14015c927940..2f7c425896f7 100644 --- a/drivers/staging/hv/StorVsc.c +++ b/drivers/staging/hv/StorVsc.c @@ -196,7 +196,7 @@ static int StorVscChannelInit(struct hv_device *Device) * Now, initiate the vsc/vsp initialization protocol on the open * channel */ - memset(request, sizeof(struct storvsc_request_extension), 0); + memset(request, 0, sizeof(struct storvsc_request_extension)); request->WaitEvent = osd_WaitEventCreate(); vstorPacket->Operation = VStorOperationBeginInitialization; @@ -233,7 +233,7 @@ static int StorVscChannelInit(struct hv_device *Device) DPRINT_INFO(STORVSC, "QUERY_PROTOCOL_VERSION_OPERATION..."); /* reuse the packet for version range supported */ - memset(vstorPacket, sizeof(struct vstor_packet), 0); + memset(vstorPacket, 0, sizeof(struct vstor_packet)); vstorPacket->Operation = VStorOperationQueryProtocolVersion; vstorPacket->Flags = REQUEST_COMPLETION_FLAG; @@ -266,7 +266,7 @@ static int StorVscChannelInit(struct hv_device *Device) /* Query channel properties */ DPRINT_INFO(STORVSC, "QUERY_PROPERTIES_OPERATION..."); - memset(vstorPacket, sizeof(struct vstor_packet), 0); + memset(vstorPacket, 0, sizeof(struct vstor_packet)); vstorPacket->Operation = VStorOperationQueryProperties; vstorPacket->Flags = REQUEST_COMPLETION_FLAG; vstorPacket->StorageChannelProperties.PortNumber = @@ -305,7 +305,7 @@ static int StorVscChannelInit(struct hv_device *Device) DPRINT_INFO(STORVSC, "END_INITIALIZATION_OPERATION..."); - memset(vstorPacket, sizeof(struct vstor_packet), 0); + memset(vstorPacket, 0, sizeof(struct vstor_packet)); vstorPacket->Operation = VStorOperationEndInitialization; vstorPacket->Flags = REQUEST_COMPLETION_FLAG; @@ -508,7 +508,7 @@ static int StorVscConnectToVsp(struct hv_device *Device) int ret; storDriver = (struct storvsc_driver_object *)Device->Driver; - memset(&props, sizeof(struct vmstorage_channel_properties), 0); + memset(&props, 0, sizeof(struct vmstorage_channel_properties)); /* Open the channel */ ret = Device->Driver->VmbusChannelInterface.Open(Device, diff --git a/drivers/staging/hv/blkvsc_drv.c b/drivers/staging/hv/blkvsc_drv.c index 99c49261a8b4..62b282844a53 100644 --- a/drivers/staging/hv/blkvsc_drv.c +++ b/drivers/staging/hv/blkvsc_drv.c @@ -15,6 +15,7 @@ * Place - Suite 330, Boston, MA 02111-1307 USA. * * Authors: + * Haiyang Zhang <haiyangz@microsoft.com> * Hank Janssen <hjanssen@microsoft.com> */ #include <linux/init.h> diff --git a/drivers/staging/hv/netvsc_drv.c b/drivers/staging/hv/netvsc_drv.c index 3192d50f7251..0d7459e2d036 100644 --- a/drivers/staging/hv/netvsc_drv.c +++ b/drivers/staging/hv/netvsc_drv.c @@ -15,6 +15,7 @@ * Place - Suite 330, Boston, MA 02111-1307 USA. * * Authors: + * Haiyang Zhang <haiyangz@microsoft.com> * Hank Janssen <hjanssen@microsoft.com> */ #include <linux/init.h> diff --git a/drivers/staging/octeon/ethernet-mdio.c b/drivers/staging/octeon/ethernet-mdio.c index 42230e62a222..31a58e508924 100644 --- a/drivers/staging/octeon/ethernet-mdio.c +++ b/drivers/staging/octeon/ethernet-mdio.c @@ -170,7 +170,7 @@ static u32 cvm_oct_get_link(struct net_device *dev) return ret; } -struct const ethtool_ops cvm_oct_ethtool_ops = { +const struct ethtool_ops cvm_oct_ethtool_ops = { .get_drvinfo = cvm_oct_get_drvinfo, .get_settings = cvm_oct_get_settings, .set_settings = cvm_oct_set_settings, diff --git a/drivers/staging/octeon/ethernet-spi.c b/drivers/staging/octeon/ethernet-spi.c index 66190b0cb68f..00dc0f4bad19 100644 --- a/drivers/staging/octeon/ethernet-spi.c +++ b/drivers/staging/octeon/ethernet-spi.c @@ -317,6 +317,6 @@ void cvm_oct_spi_uninit(struct net_device *dev) cvmx_write_csr(CVMX_SPXX_INT_MSK(interface), 0); cvmx_write_csr(CVMX_STXX_INT_MSK(interface), 0); } - free_irq(8 + 46, &number_spi_ports); + free_irq(OCTEON_IRQ_RML, &number_spi_ports); } } diff --git a/drivers/staging/octeon/ethernet.c b/drivers/staging/octeon/ethernet.c index b8479517dce2..492c5029992d 100644 --- a/drivers/staging/octeon/ethernet.c +++ b/drivers/staging/octeon/ethernet.c @@ -111,6 +111,16 @@ MODULE_PARM_DESC(disable_core_queueing, "\n" "\tallows packets to be sent without lock contention in the packet\n" "\tscheduler resulting in some cases in improved throughput.\n"); + +/* + * The offset from mac_addr_base that should be used for the next port + * that is configured. By convention, if any mgmt ports exist on the + * chip, they get the first mac addresses, The ports controlled by + * this driver are numbered sequencially following any mgmt addresses + * that may exist. + */ +static unsigned int cvm_oct_mac_addr_offset; + /** * Periodic timer to check auto negotiation */ @@ -474,16 +484,30 @@ static int cvm_oct_common_set_mac_address(struct net_device *dev, void *addr) */ int cvm_oct_common_init(struct net_device *dev) { - static int count; - char mac[8] = { 0x00, 0x00, - octeon_bootinfo->mac_addr_base[0], - octeon_bootinfo->mac_addr_base[1], - octeon_bootinfo->mac_addr_base[2], - octeon_bootinfo->mac_addr_base[3], - octeon_bootinfo->mac_addr_base[4], - octeon_bootinfo->mac_addr_base[5] + count - }; struct octeon_ethernet *priv = netdev_priv(dev); + struct sockaddr sa; + u64 mac = ((u64)(octeon_bootinfo->mac_addr_base[0] & 0xff) << 40) | + ((u64)(octeon_bootinfo->mac_addr_base[1] & 0xff) << 32) | + ((u64)(octeon_bootinfo->mac_addr_base[2] & 0xff) << 24) | + ((u64)(octeon_bootinfo->mac_addr_base[3] & 0xff) << 16) | + ((u64)(octeon_bootinfo->mac_addr_base[4] & 0xff) << 8) | + (u64)(octeon_bootinfo->mac_addr_base[5] & 0xff); + + mac += cvm_oct_mac_addr_offset; + sa.sa_data[0] = (mac >> 40) & 0xff; + sa.sa_data[1] = (mac >> 32) & 0xff; + sa.sa_data[2] = (mac >> 24) & 0xff; + sa.sa_data[3] = (mac >> 16) & 0xff; + sa.sa_data[4] = (mac >> 8) & 0xff; + sa.sa_data[5] = mac & 0xff; + + if (cvm_oct_mac_addr_offset >= octeon_bootinfo->mac_addr_count) + printk(KERN_DEBUG "%s: Using MAC outside of the assigned range:" + " %02x:%02x:%02x:%02x:%02x:%02x\n", dev->name, + sa.sa_data[0] & 0xff, sa.sa_data[1] & 0xff, + sa.sa_data[2] & 0xff, sa.sa_data[3] & 0xff, + sa.sa_data[4] & 0xff, sa.sa_data[5] & 0xff); + cvm_oct_mac_addr_offset++; /* * Force the interface to use the POW send if always_use_pow @@ -496,14 +520,12 @@ int cvm_oct_common_init(struct net_device *dev) if (priv->queue != -1 && USE_HW_TCPUDP_CHECKSUM) dev->features |= NETIF_F_IP_CSUM; - count++; - /* We do our own locking, Linux doesn't need to */ dev->features |= NETIF_F_LLTX; SET_ETHTOOL_OPS(dev, &cvm_oct_ethtool_ops); cvm_oct_mdio_setup_device(dev); - dev->netdev_ops->ndo_set_mac_address(dev, mac); + dev->netdev_ops->ndo_set_mac_address(dev, &sa); dev->netdev_ops->ndo_change_mtu(dev, dev->mtu); /* @@ -620,6 +642,13 @@ static int __init cvm_oct_init_module(void) pr_notice("cavium-ethernet %s\n", OCTEON_ETHERNET_VERSION); + if (OCTEON_IS_MODEL(OCTEON_CN52XX)) + cvm_oct_mac_addr_offset = 2; /* First two are the mgmt ports. */ + else if (OCTEON_IS_MODEL(OCTEON_CN56XX)) + cvm_oct_mac_addr_offset = 1; /* First one is the mgmt port. */ + else + cvm_oct_mac_addr_offset = 0; + cvm_oct_proc_initialize(); cvm_oct_rx_initialize(); cvm_oct_configure_common_hw(); diff --git a/drivers/staging/rtl8187se/TODO b/drivers/staging/rtl8187se/TODO index c09a9160739d..a762e79873e9 100644 --- a/drivers/staging/rtl8187se/TODO +++ b/drivers/staging/rtl8187se/TODO @@ -11,5 +11,4 @@ TODO: - sparse fixes - integrate with drivers/net/wireless/rtl818x -Please send any patches to Greg Kroah-Hartman <greg@kroah.com> and -Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>. +Please send any patches to Greg Kroah-Hartman <greg@kroah.com>. diff --git a/drivers/staging/rtl8192su/TODO b/drivers/staging/rtl8192su/TODO index b13be9edb278..f11eec700030 100644 --- a/drivers/staging/rtl8192su/TODO +++ b/drivers/staging/rtl8192su/TODO @@ -14,5 +14,4 @@ TODO: - sparse fixes - integrate with drivers/net/wireless/rtl818x -Please send any patches to Greg Kroah-Hartman <greg@kroah.com> and -Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>. +Please send any patches to Greg Kroah-Hartman <greg@kroah.com>. diff --git a/drivers/staging/vt6655/TODO b/drivers/staging/vt6655/TODO index 8462cd17eb61..cb04aaafc46f 100644 --- a/drivers/staging/vt6655/TODO +++ b/drivers/staging/vt6655/TODO @@ -16,6 +16,5 @@ TODO: - sparse fixes - integrate with drivers/net/wireless -Please send any patches to Greg Kroah-Hartman <greg@kroah.com>, -Forest Bond <forest@alittletooquiet.net> and Bartlomiej Zolnierkiewicz -<bzolnier@gmail.com>. +Please send any patches to Greg Kroah-Hartman <greg@kroah.com> +and Forest Bond <forest@alittletooquiet.net>. diff --git a/drivers/staging/vt6656/TODO b/drivers/staging/vt6656/TODO index 17cf50c6735e..a318995ba07f 100644 --- a/drivers/staging/vt6656/TODO +++ b/drivers/staging/vt6656/TODO @@ -15,6 +15,5 @@ TODO: - sparse fixes - integrate with drivers/net/wireless -Please send any patches to Greg Kroah-Hartman <greg@kroah.com>, -Forest Bond <forest@alittletooquiet.net> and Bartlomiej Zolnierkiewicz -<bzolnier@gmail.com>. +Please send any patches to Greg Kroah-Hartman <greg@kroah.com> +and Forest Bond <forest@alittletooquiet.net>. diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 5ce839137ad6..0f857e645058 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -444,7 +444,7 @@ resubmit: static inline int hub_clear_tt_buffer (struct usb_device *hdev, u16 devinfo, u16 tt) { - return usb_control_msg(hdev, usb_rcvctrlpipe(hdev, 0), + return usb_control_msg(hdev, usb_sndctrlpipe(hdev, 0), HUB_CLEAR_TT_BUFFER, USB_RT_PORT, devinfo, tt, NULL, 0, 1000); } diff --git a/drivers/usb/gadget/amd5536udc.c b/drivers/usb/gadget/amd5536udc.c index d5b65962dd36..731150d4b1d9 100644 --- a/drivers/usb/gadget/amd5536udc.c +++ b/drivers/usb/gadget/amd5536udc.c @@ -1213,7 +1213,12 @@ udc_queue(struct usb_ep *usbep, struct usb_request *usbreq, gfp_t gfp) tmp &= AMD_UNMASK_BIT(ep->num); writel(tmp, &dev->regs->ep_irqmsk); } - } + } else if (ep->in) { + /* enable ep irq */ + tmp = readl(&dev->regs->ep_irqmsk); + tmp &= AMD_UNMASK_BIT(ep->num); + writel(tmp, &dev->regs->ep_irqmsk); + } } else if (ep->dma) { @@ -2005,18 +2010,17 @@ __acquires(dev->lock) { int tmp; - /* empty queues and init hardware */ - udc_basic_init(dev); - for (tmp = 0; tmp < UDC_EP_NUM; tmp++) { - empty_req_queue(&dev->ep[tmp]); - } - if (dev->gadget.speed != USB_SPEED_UNKNOWN) { spin_unlock(&dev->lock); driver->disconnect(&dev->gadget); spin_lock(&dev->lock); } - /* init */ + + /* empty queues and init hardware */ + udc_basic_init(dev); + for (tmp = 0; tmp < UDC_EP_NUM; tmp++) + empty_req_queue(&dev->ep[tmp]); + udc_setup_endpoints(dev); } @@ -2472,6 +2476,13 @@ static irqreturn_t udc_data_in_isr(struct udc *dev, int ep_ix) } } + } else if (!use_dma && ep->in) { + /* disable interrupt */ + tmp = readl( + &dev->regs->ep_irqmsk); + tmp |= AMD_BIT(ep->num); + writel(tmp, + &dev->regs->ep_irqmsk); } } /* clear status bits */ @@ -3279,6 +3290,17 @@ static int udc_pci_probe( goto finished; } + spin_lock_init(&dev->lock); + /* udc csr registers base */ + dev->csr = dev->virt_addr + UDC_CSR_ADDR; + /* dev registers base */ + dev->regs = dev->virt_addr + UDC_DEVCFG_ADDR; + /* ep registers base */ + dev->ep_regs = dev->virt_addr + UDC_EPREGS_ADDR; + /* fifo's base */ + dev->rxfifo = (u32 __iomem *)(dev->virt_addr + UDC_RXFIFO_ADDR); + dev->txfifo = (u32 __iomem *)(dev->virt_addr + UDC_TXFIFO_ADDR); + if (request_irq(pdev->irq, udc_irq, IRQF_SHARED, name, dev) != 0) { dev_dbg(&dev->pdev->dev, "request_irq(%d) fail\n", pdev->irq); kfree(dev); @@ -3331,7 +3353,6 @@ static int udc_probe(struct udc *dev) udc_pollstall_timer.data = 0; /* device struct setup */ - spin_lock_init(&dev->lock); dev->gadget.ops = &udc_ops; dev_set_name(&dev->gadget.dev, "gadget"); @@ -3340,16 +3361,6 @@ static int udc_probe(struct udc *dev) dev->gadget.name = name; dev->gadget.is_dualspeed = 1; - /* udc csr registers base */ - dev->csr = dev->virt_addr + UDC_CSR_ADDR; - /* dev registers base */ - dev->regs = dev->virt_addr + UDC_DEVCFG_ADDR; - /* ep registers base */ - dev->ep_regs = dev->virt_addr + UDC_EPREGS_ADDR; - /* fifo's base */ - dev->rxfifo = (u32 __iomem *)(dev->virt_addr + UDC_RXFIFO_ADDR); - dev->txfifo = (u32 __iomem *)(dev->virt_addr + UDC_TXFIFO_ADDR); - /* init registers, interrupts, ... */ startup_registers(dev); diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 9835e0713943..f5f5601701c9 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -28,6 +28,7 @@ #include <linux/errno.h> #include <linux/init.h> #include <linux/timer.h> +#include <linux/ktime.h> #include <linux/list.h> #include <linux/interrupt.h> #include <linux/usb.h> @@ -676,6 +677,7 @@ static int ehci_run (struct usb_hcd *hcd) ehci_readl(ehci, &ehci->regs->command); /* unblock posted writes */ msleep(5); up_write(&ehci_cf_port_reset_rwsem); + ehci->last_periodic_enable = ktime_get_real(); temp = HC_VERSION(ehci_readl(ehci, &ehci->caps->hc_capbase)); ehci_info (ehci, diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c index 378861b9d79a..ead5f4f2aa5a 100644 --- a/drivers/usb/host/ehci-pci.c +++ b/drivers/usb/host/ehci-pci.c @@ -111,6 +111,10 @@ static int ehci_pci_setup(struct usb_hcd *hcd) switch (pdev->vendor) { case PCI_VENDOR_ID_INTEL: ehci->need_io_watchdog = 0; + if (pdev->device == 0x27cc) { + ehci->broken_periodic = 1; + ehci_info(ehci, "using broken periodic workaround\n"); + } break; case PCI_VENDOR_ID_TDI: if (pdev->device == PCI_DEVICE_ID_TDI_EHCI) { diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c index 00ad9ce392ed..139a2cc3f641 100644 --- a/drivers/usb/host/ehci-q.c +++ b/drivers/usb/host/ehci-q.c @@ -487,8 +487,20 @@ halt: * we must clear the TT buffer (11.17.5). */ if (unlikely(last_status != -EINPROGRESS && - last_status != -EREMOTEIO)) - ehci_clear_tt_buffer(ehci, qh, urb, token); + last_status != -EREMOTEIO)) { + /* The TT's in some hubs malfunction when they + * receive this request following a STALL (they + * stop sending isochronous packets). Since a + * STALL can't leave the TT buffer in a busy + * state (if you believe Figures 11-48 - 11-51 + * in the USB 2.0 spec), we won't clear the TT + * buffer in this case. Strictly speaking this + * is a violation of the spec. + */ + if (last_status != -EPIPE) + ehci_clear_tt_buffer(ehci, qh, urb, + token); + } } /* if we're removing something not at the queue head, diff --git a/drivers/usb/host/ehci-sched.c b/drivers/usb/host/ehci-sched.c index b25cdea93a1f..a5535b5e3fe2 100644 --- a/drivers/usb/host/ehci-sched.c +++ b/drivers/usb/host/ehci-sched.c @@ -475,6 +475,8 @@ static int enable_periodic (struct ehci_hcd *ehci) /* make sure ehci_work scans these */ ehci->next_uframe = ehci_readl(ehci, &ehci->regs->frame_index) % (ehci->periodic_size << 3); + if (unlikely(ehci->broken_periodic)) + ehci->last_periodic_enable = ktime_get_real(); return 0; } @@ -486,6 +488,16 @@ static int disable_periodic (struct ehci_hcd *ehci) if (--ehci->periodic_sched) return 0; + if (unlikely(ehci->broken_periodic)) { + /* delay experimentally determined */ + ktime_t safe = ktime_add_us(ehci->last_periodic_enable, 1000); + ktime_t now = ktime_get_real(); + s64 delay = ktime_us_delta(safe, now); + + if (unlikely(delay > 0)) + udelay(delay); + } + /* did setting PSE not take effect yet? * takes effect only at frame boundaries... */ diff --git a/drivers/usb/host/ehci.h b/drivers/usb/host/ehci.h index 064e76821ff5..2d85e21ff282 100644 --- a/drivers/usb/host/ehci.h +++ b/drivers/usb/host/ehci.h @@ -118,6 +118,7 @@ struct ehci_hcd { /* one per controller */ unsigned stamp; unsigned random_frame; unsigned long next_statechange; + ktime_t last_periodic_enable; u32 command; /* SILICON QUIRKS */ @@ -127,6 +128,7 @@ struct ehci_hcd { /* one per controller */ unsigned big_endian_desc:1; unsigned has_amcc_usb23:1; unsigned need_io_watchdog:1; + unsigned broken_periodic:1; /* required for usb32 quirk */ #define OHCI_CTRL_HCFS (3 << 6) diff --git a/drivers/usb/musb/cppi_dma.c b/drivers/usb/musb/cppi_dma.c index c3577bbbae6c..ef2332a9941d 100644 --- a/drivers/usb/musb/cppi_dma.c +++ b/drivers/usb/musb/cppi_dma.c @@ -1442,11 +1442,6 @@ static int cppi_channel_abort(struct dma_channel *channel) musb_writew(regs, MUSB_TXCSR, value); musb_writew(regs, MUSB_TXCSR, value); - /* re-enable interrupt */ - if (enabled) - musb_writel(tibase, DAVINCI_TXCPPI_INTENAB_REG, - (1 << cppi_ch->index)); - /* While we scrub the TX state RAM, ensure that we clean * up any interrupt that's currently asserted: * 1. Write to completion Ptr value 0x1(bit 0 set) @@ -1459,6 +1454,11 @@ static int cppi_channel_abort(struct dma_channel *channel) cppi_reset_tx(tx_ram, 1); musb_writel(&tx_ram->tx_complete, 0, 0); + /* re-enable interrupt */ + if (enabled) + musb_writel(tibase, DAVINCI_TXCPPI_INTENAB_REG, + (1 << cppi_ch->index)); + cppi_dump_tx(5, cppi_ch, " (done teardown)"); /* REVISIT tx side _should_ clean up the same way diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 3a61ddb62bd2..547e0e390726 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -1450,7 +1450,7 @@ static int __init musb_core_init(u16 musb_type, struct musb *musb) #endif if (hw_ep->max_packet_sz_tx) { - printk(KERN_DEBUG + DBG(1, "%s: hw_ep %d%s, %smax %d\n", musb_driver_name, i, hw_ep->is_shared_fifo ? "shared" : "tx", @@ -1459,7 +1459,7 @@ static int __init musb_core_init(u16 musb_type, struct musb *musb) hw_ep->max_packet_sz_tx); } if (hw_ep->max_packet_sz_rx && !hw_ep->is_shared_fifo) { - printk(KERN_DEBUG + DBG(1, "%s: hw_ep %d%s, %smax %d\n", musb_driver_name, i, "rx", diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index 8b3c4e2ed7b8..74073f9a43f0 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -4,6 +4,7 @@ * Copyright 2005 Mentor Graphics Corporation * Copyright (C) 2005-2006 by Texas Instruments * Copyright (C) 2006-2007 Nokia Corporation + * Copyright (C) 2009 MontaVista Software, Inc. <source@mvista.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -436,14 +437,6 @@ void musb_g_tx(struct musb *musb, u8 epnum) csr |= MUSB_TXCSR_P_WZC_BITS; csr &= ~MUSB_TXCSR_P_SENTSTALL; musb_writew(epio, MUSB_TXCSR, csr); - if (dma_channel_status(dma) == MUSB_DMA_STATUS_BUSY) { - dma->status = MUSB_DMA_STATUS_CORE_ABORT; - musb->dma_controller->channel_abort(dma); - } - - if (request) - musb_g_giveback(musb_ep, request, -EPIPE); - break; } @@ -582,15 +575,25 @@ void musb_g_tx(struct musb *musb, u8 epnum) */ static void rxstate(struct musb *musb, struct musb_request *req) { - u16 csr = 0; const u8 epnum = req->epnum; struct usb_request *request = &req->request; struct musb_ep *musb_ep = &musb->endpoints[epnum].ep_out; void __iomem *epio = musb->endpoints[epnum].regs; unsigned fifo_count = 0; u16 len = musb_ep->packet_sz; + u16 csr = musb_readw(epio, MUSB_RXCSR); - csr = musb_readw(epio, MUSB_RXCSR); + /* We shouldn't get here while DMA is active, but we do... */ + if (dma_channel_status(musb_ep->dma) == MUSB_DMA_STATUS_BUSY) { + DBG(4, "DMA pending...\n"); + return; + } + + if (csr & MUSB_RXCSR_P_SENDSTALL) { + DBG(5, "%s stalling, RXCSR %04x\n", + musb_ep->end_point.name, csr); + return; + } if (is_cppi_enabled() && musb_ep->dma) { struct dma_controller *c = musb->dma_controller; @@ -761,19 +764,10 @@ void musb_g_rx(struct musb *musb, u8 epnum) csr, dma ? " (dma)" : "", request); if (csr & MUSB_RXCSR_P_SENTSTALL) { - if (dma_channel_status(dma) == MUSB_DMA_STATUS_BUSY) { - dma->status = MUSB_DMA_STATUS_CORE_ABORT; - (void) musb->dma_controller->channel_abort(dma); - request->actual += musb_ep->dma->actual_len; - } - csr |= MUSB_RXCSR_P_WZC_BITS; csr &= ~MUSB_RXCSR_P_SENTSTALL; musb_writew(epio, MUSB_RXCSR, csr); - - if (request) - musb_g_giveback(musb_ep, request, -EPIPE); - goto done; + return; } if (csr & MUSB_RXCSR_P_OVERRUN) { @@ -795,7 +789,7 @@ void musb_g_rx(struct musb *musb, u8 epnum) DBG((csr & MUSB_RXCSR_DMAENAB) ? 4 : 1, "%s busy, csr %04x\n", musb_ep->end_point.name, csr); - goto done; + return; } if (dma && (csr & MUSB_RXCSR_DMAENAB)) { @@ -826,22 +820,15 @@ void musb_g_rx(struct musb *musb, u8 epnum) if ((request->actual < request->length) && (musb_ep->dma->actual_len == musb_ep->packet_sz)) - goto done; + return; #endif musb_g_giveback(musb_ep, request, 0); request = next_request(musb_ep); if (!request) - goto done; - - /* don't start more i/o till the stall clears */ - musb_ep_select(mbase, epnum); - csr = musb_readw(epio, MUSB_RXCSR); - if (csr & MUSB_RXCSR_P_SENDSTALL) - goto done; + return; } - /* analyze request if the ep is hot */ if (request) rxstate(musb, to_musb_request(request)); @@ -849,8 +836,6 @@ void musb_g_rx(struct musb *musb, u8 epnum) DBG(3, "packet waiting for %s%s request\n", musb_ep->desc ? "" : "inactive ", musb_ep->end_point.name); - -done: return; } @@ -1244,7 +1229,7 @@ int musb_gadget_set_halt(struct usb_ep *ep, int value) void __iomem *mbase; unsigned long flags; u16 csr; - struct musb_request *request = NULL; + struct musb_request *request; int status = 0; if (!ep) @@ -1260,24 +1245,29 @@ int musb_gadget_set_halt(struct usb_ep *ep, int value) musb_ep_select(mbase, epnum); - /* cannot portably stall with non-empty FIFO */ request = to_musb_request(next_request(musb_ep)); - if (value && musb_ep->is_in) { - csr = musb_readw(epio, MUSB_TXCSR); - if (csr & MUSB_TXCSR_FIFONOTEMPTY) { - DBG(3, "%s fifo busy, cannot halt\n", ep->name); - spin_unlock_irqrestore(&musb->lock, flags); - return -EAGAIN; + if (value) { + if (request) { + DBG(3, "request in progress, cannot halt %s\n", + ep->name); + status = -EAGAIN; + goto done; + } + /* Cannot portably stall with non-empty FIFO */ + if (musb_ep->is_in) { + csr = musb_readw(epio, MUSB_TXCSR); + if (csr & MUSB_TXCSR_FIFONOTEMPTY) { + DBG(3, "FIFO busy, cannot halt %s\n", ep->name); + status = -EAGAIN; + goto done; + } } - } /* set/clear the stall and toggle bits */ DBG(2, "%s: %s stall\n", ep->name, value ? "set" : "clear"); if (musb_ep->is_in) { csr = musb_readw(epio, MUSB_TXCSR); - if (csr & MUSB_TXCSR_FIFONOTEMPTY) - csr |= MUSB_TXCSR_FLUSHFIFO; csr |= MUSB_TXCSR_P_WZC_BITS | MUSB_TXCSR_CLRDATATOG; if (value) @@ -1300,14 +1290,13 @@ int musb_gadget_set_halt(struct usb_ep *ep, int value) musb_writew(epio, MUSB_RXCSR, csr); } -done: - /* maybe start the first request in the queue */ if (!musb_ep->busy && !value && request) { DBG(3, "restarting the request\n"); musb_ep_restart(musb, request); } +done: spin_unlock_irqrestore(&musb->lock, flags); return status; } diff --git a/drivers/usb/musb/musb_gadget_ep0.c b/drivers/usb/musb/musb_gadget_ep0.c index 7a6778675ad3..522efb31b56b 100644 --- a/drivers/usb/musb/musb_gadget_ep0.c +++ b/drivers/usb/musb/musb_gadget_ep0.c @@ -511,7 +511,8 @@ static void ep0_txstate(struct musb *musb) /* update the flags */ if (fifo_count < MUSB_MAX_END0_PACKET - || request->actual == request->length) { + || (request->actual == request->length + && !request->zero)) { musb->ep0_state = MUSB_EP0_STAGE_STATUSOUT; csr |= MUSB_CSR0_P_DATAEND; } else diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index cf94511485f2..e3ab40a966eb 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -1301,8 +1301,11 @@ void musb_host_tx(struct musb *musb, u8 epnum) return; } else if (usb_pipeisoc(pipe) && dma) { if (musb_tx_dma_program(musb->dma_controller, hw_ep, qh, urb, - offset, length)) + offset, length)) { + if (is_cppi_enabled() || tusb_dma_omap()) + musb_h_tx_dma_start(hw_ep); return; + } } else if (tx_csr & MUSB_TXCSR_DMAENAB) { DBG(1, "not complete, but DMA enabled?\n"); return; diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 9c60d6d4908a..ebcc6d0e2e91 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1937,7 +1937,7 @@ static void ftdi_write_bulk_callback(struct urb *urb) return; } /* account for transferred data */ - countback = urb->actual_length; + countback = urb->transfer_buffer_length; data_offset = priv->write_offset; if (data_offset > 0) { /* Subtract the control bytes */ @@ -1950,7 +1950,6 @@ static void ftdi_write_bulk_callback(struct urb *urb) if (status) { dbg("nonzero write bulk status received: %d", status); - return; } usb_serial_port_softint(port); diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 319aaf9725b3..0577e4b61114 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -336,6 +336,10 @@ static int option_resume(struct usb_serial *serial); #define AIRPLUS_VENDOR_ID 0x1011 #define AIRPLUS_PRODUCT_MCD650 0x3198 +/* 4G Systems products */ +#define FOUR_G_SYSTEMS_VENDOR_ID 0x1c9e +#define FOUR_G_SYSTEMS_PRODUCT_W14 0x9603 + static struct usb_device_id option_ids[] = { { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) }, { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) }, @@ -599,6 +603,7 @@ static struct usb_device_id option_ids[] = { { USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S) }, { USB_DEVICE(AIRPLUS_VENDOR_ID, AIRPLUS_PRODUCT_MCD650) }, { USB_DEVICE(TLAYTECH_VENDOR_ID, TLAYTECH_PRODUCT_TEU800) }, + { USB_DEVICE(FOUR_G_SYSTEMS_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_W14) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/watchdog/pnx4008_wdt.c b/drivers/watchdog/pnx4008_wdt.c index f24d04132eda..4d227b152001 100644 --- a/drivers/watchdog/pnx4008_wdt.c +++ b/drivers/watchdog/pnx4008_wdt.c @@ -317,7 +317,7 @@ static int __devexit pnx4008_wdt_remove(struct platform_device *pdev) static struct platform_driver platform_wdt_driver = { .driver = { - .name = "watchdog", + .name = "pnx4008-watchdog", .owner = THIS_MODULE, }, .probe = pnx4008_wdt_probe, @@ -352,4 +352,4 @@ MODULE_PARM_DESC(nowayout, MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR); -MODULE_ALIAS("platform:watchdog"); +MODULE_ALIAS("platform:pnx4008-watchdog"); diff --git a/fs/9p/cache.c b/fs/9p/cache.c index 51c94e26a346..e777961939f3 100644 --- a/fs/9p/cache.c +++ b/fs/9p/cache.c @@ -343,18 +343,7 @@ int __v9fs_fscache_release_page(struct page *page, gfp_t gfp) BUG_ON(!vcookie->fscache); - if (PageFsCache(page)) { - if (fscache_check_page_write(vcookie->fscache, page)) { - if (!(gfp & __GFP_WAIT)) - return 0; - fscache_wait_on_page_write(vcookie->fscache, page); - } - - fscache_uncache_page(vcookie->fscache, page); - ClearPageFsCache(page); - } - - return 1; + return fscache_maybe_release_page(vcookie->fscache, page, gfp); } void __v9fs_fscache_invalidate_page(struct page *page) @@ -368,7 +357,6 @@ void __v9fs_fscache_invalidate_page(struct page *page) fscache_wait_on_page_write(vcookie->fscache, page); BUG_ON(!PageLocked(page)); fscache_uncache_page(vcookie->fscache, page); - ClearPageFsCache(page); } } diff --git a/fs/afs/file.c b/fs/afs/file.c index 681c2a7b013f..39b301662f22 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -315,7 +315,6 @@ static void afs_invalidatepage(struct page *page, unsigned long offset) struct afs_vnode *vnode = AFS_FS_I(page->mapping->host); fscache_wait_on_page_write(vnode->cache, page); fscache_uncache_page(vnode->cache, page); - ClearPageFsCache(page); } #endif @@ -349,17 +348,9 @@ static int afs_releasepage(struct page *page, gfp_t gfp_flags) /* deny if page is being written to the cache and the caller hasn't * elected to wait */ #ifdef CONFIG_AFS_FSCACHE - if (PageFsCache(page)) { - if (fscache_check_page_write(vnode->cache, page)) { - if (!(gfp_flags & __GFP_WAIT)) { - _leave(" = F [cache busy]"); - return 0; - } - fscache_wait_on_page_write(vnode->cache, page); - } - - fscache_uncache_page(vnode->cache, page); - ClearPageFsCache(page); + if (!fscache_maybe_release_page(vnode->cache, page, gfp_flags)) { + _leave(" = F [cache busy]"); + return 0; } #endif diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c index 431accd475a7..27089311fbea 100644 --- a/fs/cachefiles/interface.c +++ b/fs/cachefiles/interface.c @@ -114,8 +114,9 @@ nomem_lookup_data: /* * attempt to look up the nominated node in this cache + * - return -ETIMEDOUT to be scheduled again */ -static void cachefiles_lookup_object(struct fscache_object *_object) +static int cachefiles_lookup_object(struct fscache_object *_object) { struct cachefiles_lookup_data *lookup_data; struct cachefiles_object *parent, *object; @@ -145,13 +146,15 @@ static void cachefiles_lookup_object(struct fscache_object *_object) object->fscache.cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX) cachefiles_attr_changed(&object->fscache); - if (ret < 0) { - printk(KERN_WARNING "CacheFiles: Lookup failed error %d\n", - ret); + if (ret < 0 && ret != -ETIMEDOUT) { + if (ret != -ENOBUFS) + printk(KERN_WARNING + "CacheFiles: Lookup failed error %d\n", ret); fscache_object_lookup_error(&object->fscache); } _leave(" [%d]", ret); + return ret; } /* @@ -331,6 +334,7 @@ static void cachefiles_put_object(struct fscache_object *_object) } cache = object->fscache.cache; + fscache_object_destroy(&object->fscache); kmem_cache_free(cachefiles_object_jar, object); fscache_object_destroyed(cache); } @@ -403,12 +407,26 @@ static int cachefiles_attr_changed(struct fscache_object *_object) if (oi_size == ni_size) return 0; - newattrs.ia_size = ni_size; - newattrs.ia_valid = ATTR_SIZE; - cachefiles_begin_secure(cache, &saved_cred); mutex_lock(&object->backer->d_inode->i_mutex); + + /* if there's an extension to a partial page at the end of the backing + * file, we need to discard the partial page so that we pick up new + * data after it */ + if (oi_size & ~PAGE_MASK && ni_size > oi_size) { + _debug("discard tail %llx", oi_size); + newattrs.ia_valid = ATTR_SIZE; + newattrs.ia_size = oi_size & PAGE_MASK; + ret = notify_change(object->backer, &newattrs); + if (ret < 0) + goto truncate_failed; + } + + newattrs.ia_valid = ATTR_SIZE; + newattrs.ia_size = ni_size; ret = notify_change(object->backer, &newattrs); + +truncate_failed: mutex_unlock(&object->backer->d_inode->i_mutex); cachefiles_end_secure(cache, saved_cred); diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 4ce818ae39ea..14ac4806e291 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -21,17 +21,81 @@ #include <linux/security.h> #include "internal.h" -static int cachefiles_wait_bit(void *flags) +#define CACHEFILES_KEYBUF_SIZE 512 + +/* + * dump debugging info about an object + */ +static noinline +void __cachefiles_printk_object(struct cachefiles_object *object, + const char *prefix, + u8 *keybuf) { - schedule(); - return 0; + struct fscache_cookie *cookie; + unsigned keylen, loop; + + printk(KERN_ERR "%sobject: OBJ%x\n", + prefix, object->fscache.debug_id); + printk(KERN_ERR "%sobjstate=%s fl=%lx swfl=%lx ev=%lx[%lx]\n", + prefix, fscache_object_states[object->fscache.state], + object->fscache.flags, object->fscache.work.flags, + object->fscache.events, + object->fscache.event_mask & FSCACHE_OBJECT_EVENTS_MASK); + printk(KERN_ERR "%sops=%u inp=%u exc=%u\n", + prefix, object->fscache.n_ops, object->fscache.n_in_progress, + object->fscache.n_exclusive); + printk(KERN_ERR "%sparent=%p\n", + prefix, object->fscache.parent); + + spin_lock(&object->fscache.lock); + cookie = object->fscache.cookie; + if (cookie) { + printk(KERN_ERR "%scookie=%p [pr=%p nd=%p fl=%lx]\n", + prefix, + object->fscache.cookie, + object->fscache.cookie->parent, + object->fscache.cookie->netfs_data, + object->fscache.cookie->flags); + if (keybuf) + keylen = cookie->def->get_key(cookie->netfs_data, keybuf, + CACHEFILES_KEYBUF_SIZE); + else + keylen = 0; + } else { + printk(KERN_ERR "%scookie=NULL\n", prefix); + keylen = 0; + } + spin_unlock(&object->fscache.lock); + + if (keylen) { + printk(KERN_ERR "%skey=[%u] '", prefix, keylen); + for (loop = 0; loop < keylen; loop++) + printk("%02x", keybuf[loop]); + printk("'\n"); + } +} + +/* + * dump debugging info about a pair of objects + */ +static noinline void cachefiles_printk_object(struct cachefiles_object *object, + struct cachefiles_object *xobject) +{ + u8 *keybuf; + + keybuf = kmalloc(CACHEFILES_KEYBUF_SIZE, GFP_NOIO); + if (object) + __cachefiles_printk_object(object, "", keybuf); + if (xobject) + __cachefiles_printk_object(xobject, "x", keybuf); + kfree(keybuf); } /* * record the fact that an object is now active */ -static void cachefiles_mark_object_active(struct cachefiles_cache *cache, - struct cachefiles_object *object) +static int cachefiles_mark_object_active(struct cachefiles_cache *cache, + struct cachefiles_object *object) { struct cachefiles_object *xobject; struct rb_node **_p, *_parent = NULL; @@ -42,8 +106,11 @@ static void cachefiles_mark_object_active(struct cachefiles_cache *cache, try_again: write_lock(&cache->active_lock); - if (test_and_set_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) + if (test_and_set_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) { + printk(KERN_ERR "CacheFiles: Error: Object already active\n"); + cachefiles_printk_object(object, NULL); BUG(); + } dentry = object->dentry; _p = &cache->active_nodes.rb_node; @@ -66,8 +133,8 @@ try_again: rb_insert_color(&object->active_node, &cache->active_nodes); write_unlock(&cache->active_lock); - _leave(""); - return; + _leave(" = 0"); + return 0; /* an old object from a previous incarnation is hogging the slot - we * need to wait for it to be destroyed */ @@ -76,44 +143,70 @@ wait_for_old_object: printk(KERN_ERR "\n"); printk(KERN_ERR "CacheFiles: Error:" " Unexpected object collision\n"); - printk(KERN_ERR "xobject: OBJ%x\n", - xobject->fscache.debug_id); - printk(KERN_ERR "xobjstate=%s\n", - fscache_object_states[xobject->fscache.state]); - printk(KERN_ERR "xobjflags=%lx\n", xobject->fscache.flags); - printk(KERN_ERR "xobjevent=%lx [%lx]\n", - xobject->fscache.events, xobject->fscache.event_mask); - printk(KERN_ERR "xops=%u inp=%u exc=%u\n", - xobject->fscache.n_ops, xobject->fscache.n_in_progress, - xobject->fscache.n_exclusive); - printk(KERN_ERR "xcookie=%p [pr=%p nd=%p fl=%lx]\n", - xobject->fscache.cookie, - xobject->fscache.cookie->parent, - xobject->fscache.cookie->netfs_data, - xobject->fscache.cookie->flags); - printk(KERN_ERR "xparent=%p\n", - xobject->fscache.parent); - printk(KERN_ERR "object: OBJ%x\n", - object->fscache.debug_id); - printk(KERN_ERR "cookie=%p [pr=%p nd=%p fl=%lx]\n", - object->fscache.cookie, - object->fscache.cookie->parent, - object->fscache.cookie->netfs_data, - object->fscache.cookie->flags); - printk(KERN_ERR "parent=%p\n", - object->fscache.parent); + cachefiles_printk_object(object, xobject); BUG(); } atomic_inc(&xobject->usage); write_unlock(&cache->active_lock); - _debug(">>> wait"); - wait_on_bit(&xobject->flags, CACHEFILES_OBJECT_ACTIVE, - cachefiles_wait_bit, TASK_UNINTERRUPTIBLE); - _debug("<<< waited"); + if (test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) { + wait_queue_head_t *wq; + + signed long timeout = 60 * HZ; + wait_queue_t wait; + bool requeue; + + /* if the object we're waiting for is queued for processing, + * then just put ourselves on the queue behind it */ + if (slow_work_is_queued(&xobject->fscache.work)) { + _debug("queue OBJ%x behind OBJ%x immediately", + object->fscache.debug_id, + xobject->fscache.debug_id); + goto requeue; + } + + /* otherwise we sleep until either the object we're waiting for + * is done, or the slow-work facility wants the thread back to + * do other work */ + wq = bit_waitqueue(&xobject->flags, CACHEFILES_OBJECT_ACTIVE); + init_wait(&wait); + requeue = false; + do { + prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); + if (!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) + break; + requeue = slow_work_sleep_till_thread_needed( + &object->fscache.work, &timeout); + } while (timeout > 0 && !requeue); + finish_wait(wq, &wait); + + if (requeue && + test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) { + _debug("queue OBJ%x behind OBJ%x after wait", + object->fscache.debug_id, + xobject->fscache.debug_id); + goto requeue; + } + + if (timeout <= 0) { + printk(KERN_ERR "\n"); + printk(KERN_ERR "CacheFiles: Error: Overlong" + " wait for old active object to go away\n"); + cachefiles_printk_object(object, xobject); + goto requeue; + } + } + + ASSERT(!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)); cache->cache.ops->put_object(&xobject->fscache); goto try_again; + +requeue: + clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); + cache->cache.ops->put_object(&xobject->fscache); + _leave(" = -ETIMEDOUT"); + return -ETIMEDOUT; } /* @@ -254,7 +347,7 @@ int cachefiles_delete_object(struct cachefiles_cache *cache, dir = dget_parent(object->dentry); - mutex_lock(&dir->d_inode->i_mutex); + mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT); ret = cachefiles_bury_object(cache, dir, object->dentry); dput(dir); @@ -307,7 +400,7 @@ lookup_again: /* search the current directory for the element name */ _debug("lookup '%s'", name); - mutex_lock(&dir->d_inode->i_mutex); + mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT); start = jiffies; next = lookup_one_len(name, dir, nlen); @@ -418,12 +511,15 @@ lookup_again: } /* note that we're now using this object */ - cachefiles_mark_object_active(cache, object); + ret = cachefiles_mark_object_active(cache, object); mutex_unlock(&dir->d_inode->i_mutex); dput(dir); dir = NULL; + if (ret == -ETIMEDOUT) + goto mark_active_timed_out; + _debug("=== OBTAINED_OBJECT ==="); if (object->new) { @@ -467,6 +563,10 @@ create_error: cachefiles_io_error(cache, "Create/mkdir failed"); goto error; +mark_active_timed_out: + _debug("mark active timed out"); + goto release_dentry; + check_error: _debug("check error %d", ret); write_lock(&cache->active_lock); @@ -474,7 +574,7 @@ check_error: clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE); write_unlock(&cache->active_lock); - +release_dentry: dput(object->dentry); object->dentry = NULL; goto error_out; @@ -495,9 +595,6 @@ error: error_out2: dput(dir); error_out: - if (ret == -ENOSPC) - ret = -ENOBUFS; - _leave(" = error %d", -ret); return ret; } diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index a69787e7dd96..a6c8c6fe8df9 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -11,6 +11,7 @@ #include <linux/mount.h> #include <linux/file.h> +#include <linux/ima.h> #include "internal.h" /* @@ -40,8 +41,10 @@ static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode, _debug("--- monitor %p %lx ---", page, page->flags); - if (!PageUptodate(page) && !PageError(page)) - dump_stack(); + if (!PageUptodate(page) && !PageError(page)) { + /* unlocked, not uptodate and not erronous? */ + _debug("page probably truncated"); + } /* remove from the waitqueue */ list_del(&wait->task_list); @@ -61,6 +64,84 @@ static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode, } /* + * handle a probably truncated page + * - check to see if the page is still relevant and reissue the read if + * possible + * - return -EIO on error, -ENODATA if the page is gone, -EINPROGRESS if we + * must wait again and 0 if successful + */ +static int cachefiles_read_reissue(struct cachefiles_object *object, + struct cachefiles_one_read *monitor) +{ + struct address_space *bmapping = object->backer->d_inode->i_mapping; + struct page *backpage = monitor->back_page, *backpage2; + int ret; + + kenter("{ino=%lx},{%lx,%lx}", + object->backer->d_inode->i_ino, + backpage->index, backpage->flags); + + /* skip if the page was truncated away completely */ + if (backpage->mapping != bmapping) { + kleave(" = -ENODATA [mapping]"); + return -ENODATA; + } + + backpage2 = find_get_page(bmapping, backpage->index); + if (!backpage2) { + kleave(" = -ENODATA [gone]"); + return -ENODATA; + } + + if (backpage != backpage2) { + put_page(backpage2); + kleave(" = -ENODATA [different]"); + return -ENODATA; + } + + /* the page is still there and we already have a ref on it, so we don't + * need a second */ + put_page(backpage2); + + INIT_LIST_HEAD(&monitor->op_link); + add_page_wait_queue(backpage, &monitor->monitor); + + if (trylock_page(backpage)) { + ret = -EIO; + if (PageError(backpage)) + goto unlock_discard; + ret = 0; + if (PageUptodate(backpage)) + goto unlock_discard; + + kdebug("reissue read"); + ret = bmapping->a_ops->readpage(NULL, backpage); + if (ret < 0) + goto unlock_discard; + } + + /* but the page may have been read before the monitor was installed, so + * the monitor may miss the event - so we have to ensure that we do get + * one in such a case */ + if (trylock_page(backpage)) { + _debug("jumpstart %p {%lx}", backpage, backpage->flags); + unlock_page(backpage); + } + + /* it'll reappear on the todo list */ + kleave(" = -EINPROGRESS"); + return -EINPROGRESS; + +unlock_discard: + unlock_page(backpage); + spin_lock_irq(&object->work_lock); + list_del(&monitor->op_link); + spin_unlock_irq(&object->work_lock); + kleave(" = %d", ret); + return ret; +} + +/* * copy data from backing pages to netfs pages to complete a read operation * - driven by FS-Cache's thread pool */ @@ -92,20 +173,26 @@ static void cachefiles_read_copier(struct fscache_operation *_op) _debug("- copy {%lu}", monitor->back_page->index); - error = -EIO; + recheck: if (PageUptodate(monitor->back_page)) { copy_highpage(monitor->netfs_page, monitor->back_page); pagevec_add(&pagevec, monitor->netfs_page); fscache_mark_pages_cached(monitor->op, &pagevec); error = 0; - } - - if (error) + } else if (!PageError(monitor->back_page)) { + /* the page has probably been truncated */ + error = cachefiles_read_reissue(object, monitor); + if (error == -EINPROGRESS) + goto next; + goto recheck; + } else { cachefiles_io_error_obj( object, "Readpage failed on backing file %lx", (unsigned long) monitor->back_page->flags); + error = -EIO; + } page_cache_release(monitor->back_page); @@ -114,6 +201,7 @@ static void cachefiles_read_copier(struct fscache_operation *_op) fscache_put_retrieval(op); kfree(monitor); + next: /* let the thread pool have some air occasionally */ max--; if (max < 0 || need_resched()) { @@ -333,7 +421,8 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op, shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits; - op->op.flags = FSCACHE_OP_FAST; + op->op.flags &= FSCACHE_OP_KEEP_FLAGS; + op->op.flags |= FSCACHE_OP_FAST; op->op.processor = cachefiles_read_copier; pagevec_init(&pagevec, 0); @@ -639,7 +728,8 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op, pagevec_init(&pagevec, 0); - op->op.flags = FSCACHE_OP_FAST; + op->op.flags &= FSCACHE_OP_KEEP_FLAGS; + op->op.flags |= FSCACHE_OP_FAST; op->op.processor = cachefiles_read_copier; INIT_LIST_HEAD(&backpages); @@ -801,7 +891,8 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page) struct cachefiles_cache *cache; mm_segment_t old_fs; struct file *file; - loff_t pos; + loff_t pos, eof; + size_t len; void *data; int ret; @@ -832,18 +923,33 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page) if (IS_ERR(file)) { ret = PTR_ERR(file); } else { + ima_counts_get(file); ret = -EIO; if (file->f_op->write) { pos = (loff_t) page->index << PAGE_SHIFT; + + /* we mustn't write more data than we have, so we have + * to beware of a partial page at EOF */ + eof = object->fscache.store_limit_l; + len = PAGE_SIZE; + if (eof & ~PAGE_MASK) { + ASSERTCMP(pos, <, eof); + if (eof - pos < PAGE_SIZE) { + _debug("cut short %llx to %llx", + pos, eof); + len = eof - pos; + ASSERTCMP(pos + len, ==, eof); + } + } + data = kmap(page); old_fs = get_fs(); set_fs(KERNEL_DS); ret = file->f_op->write( - file, (const void __user *) data, PAGE_SIZE, - &pos); + file, (const void __user *) data, len, &pos); set_fs(old_fs); kunmap(page); - if (ret != PAGE_SIZE) + if (ret != len) ret = -EIO; } fput(file); diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES index 145540a316ab..094ea65afc85 100644 --- a/fs/cifs/CHANGES +++ b/fs/cifs/CHANGES @@ -1,3 +1,12 @@ +Version 1.61 +------------ +Fix append problem to Samba servers (files opened with O_APPEND could +have duplicated data). Fix oops in cifs_lookup. Workaround problem +mounting to OS/400 Netserve. Fix oops in cifs_get_tcp_session. +Disable use of server inode numbers when server only +partially supports them (e.g. for one server querying inode numbers on +FindFirst fails but QPathInfo queries works). + Version 1.60 ------------- Fix memory leak in reconnect. Fix oops in DFS mount error path. diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 9a5e4f5f3122..29f1da761bbf 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1037,7 +1037,7 @@ init_cifs(void) if (rc) goto out_unregister_key_type; #endif - rc = slow_work_register_user(); + rc = slow_work_register_user(THIS_MODULE); if (rc) goto out_unregister_resolver_key; diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 627a60a6c1b1..1f42f772865a 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -214,8 +214,6 @@ int cifs_posix_open(char *full_path, struct inode **pinode, posix_flags |= SMB_O_EXCL; if (oflags & O_TRUNC) posix_flags |= SMB_O_TRUNC; - if (oflags & O_APPEND) - posix_flags |= SMB_O_APPEND; if (oflags & O_SYNC) posix_flags |= SMB_O_SYNC; if (oflags & O_DIRECTORY) @@ -643,9 +641,9 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, * O_EXCL: optimize away the lookup, but don't hash the dentry. Let * the VFS handle the create. */ - if (nd->flags & LOOKUP_EXCL) { + if (nd && (nd->flags & LOOKUP_EXCL)) { d_instantiate(direntry, NULL); - return 0; + return NULL; } /* can not grab the rename sem here since it would @@ -675,7 +673,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, * reduction in network traffic in the other paths. */ if (pTcon->unix_ext) { - if (!(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY)) && + if (nd && !(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY)) && (nd->flags & LOOKUP_OPEN) && !pTcon->broken_posix_open && (nd->intent.open.flags & O_CREAT)) { rc = cifs_posix_open(full_path, &newInode, nd->path.mnt, diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig index 9bbb8ce7bea0..864dac20a242 100644 --- a/fs/fscache/Kconfig +++ b/fs/fscache/Kconfig @@ -54,3 +54,10 @@ config FSCACHE_DEBUG enabled by setting bits in /sys/modules/fscache/parameter/debug. See Documentation/filesystems/caching/fscache.txt for more information. + +config FSCACHE_OBJECT_LIST + bool "Maintain global object list for debugging purposes" + depends on FSCACHE && PROC_FS + help + Maintain a global list of active fscache objects that can be + retrieved through /proc/fs/fscache/objects for debugging purposes diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile index 91571b95aacc..6d561531cb36 100644 --- a/fs/fscache/Makefile +++ b/fs/fscache/Makefile @@ -15,5 +15,6 @@ fscache-y := \ fscache-$(CONFIG_PROC_FS) += proc.o fscache-$(CONFIG_FSCACHE_STATS) += stats.o fscache-$(CONFIG_FSCACHE_HISTOGRAM) += histogram.o +fscache-$(CONFIG_FSCACHE_OBJECT_LIST) += object-list.o obj-$(CONFIG_FSCACHE) := fscache.o diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index e21985bbb1fb..6a3c48abd677 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -263,6 +263,7 @@ int fscache_add_cache(struct fscache_cache *cache, spin_lock(&cache->object_list_lock); list_add_tail(&ifsdef->cache_link, &cache->object_list); spin_unlock(&cache->object_list_lock); + fscache_objlist_add(ifsdef); /* add the cache's netfs definition index object to the top level index * cookie as a known backing object */ @@ -380,11 +381,15 @@ void fscache_withdraw_cache(struct fscache_cache *cache) /* make sure all pages pinned by operations on behalf of the netfs are * written to disk */ + fscache_stat(&fscache_n_cop_sync_cache); cache->ops->sync_cache(cache); + fscache_stat_d(&fscache_n_cop_sync_cache); /* dissociate all the netfs pages backed by this cache from the block * mappings in the cache */ + fscache_stat(&fscache_n_cop_dissociate_pages); cache->ops->dissociate_pages(cache); + fscache_stat_d(&fscache_n_cop_dissociate_pages); /* we now have to destroy all the active objects pertaining to this * cache - which we do by passing them off to thread pool to be diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 72fd18f6c71f..990535071a8a 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -36,6 +36,7 @@ void fscache_cookie_init_once(void *_cookie) memset(cookie, 0, sizeof(*cookie)); spin_lock_init(&cookie->lock); + spin_lock_init(&cookie->stores_lock); INIT_HLIST_HEAD(&cookie->backing_objects); } @@ -102,7 +103,9 @@ struct fscache_cookie *__fscache_acquire_cookie( cookie->netfs_data = netfs_data; cookie->flags = 0; - INIT_RADIX_TREE(&cookie->stores, GFP_NOFS); + /* radix tree insertion won't use the preallocation pool unless it's + * told it may not wait */ + INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_WAIT); switch (cookie->def->type) { case FSCACHE_COOKIE_TYPE_INDEX: @@ -249,7 +252,9 @@ static int fscache_alloc_object(struct fscache_cache *cache, /* ask the cache to allocate an object (we may end up with duplicate * objects at this stage, but we sort that out later) */ + fscache_stat(&fscache_n_cop_alloc_object); object = cache->ops->alloc_object(cache, cookie); + fscache_stat_d(&fscache_n_cop_alloc_object); if (IS_ERR(object)) { fscache_stat(&fscache_n_object_no_alloc); ret = PTR_ERR(object); @@ -270,8 +275,11 @@ static int fscache_alloc_object(struct fscache_cache *cache, /* only attach if we managed to allocate all we needed, otherwise * discard the object we just allocated and instead use the one * attached to the cookie */ - if (fscache_attach_object(cookie, object) < 0) + if (fscache_attach_object(cookie, object) < 0) { + fscache_stat(&fscache_n_cop_put_object); cache->ops->put_object(object); + fscache_stat_d(&fscache_n_cop_put_object); + } _leave(" = 0"); return 0; @@ -287,7 +295,9 @@ object_already_extant: return 0; error_put: + fscache_stat(&fscache_n_cop_put_object); cache->ops->put_object(object); + fscache_stat_d(&fscache_n_cop_put_object); error: _leave(" = %d", ret); return ret; @@ -349,6 +359,8 @@ static int fscache_attach_object(struct fscache_cookie *cookie, object->cookie = cookie; atomic_inc(&cookie->usage); hlist_add_head(&object->cookie_link, &cookie->backing_objects); + + fscache_objlist_add(object); ret = 0; cant_attach_object: @@ -403,6 +415,8 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire) unsigned long event; fscache_stat(&fscache_n_relinquishes); + if (retire) + fscache_stat(&fscache_n_relinquishes_retire); if (!cookie) { fscache_stat(&fscache_n_relinquishes_null); @@ -428,12 +442,8 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire) event = retire ? FSCACHE_OBJECT_EV_RETIRE : FSCACHE_OBJECT_EV_RELEASE; - /* detach pointers back to the netfs */ spin_lock(&cookie->lock); - cookie->netfs_data = NULL; - cookie->def = NULL; - /* break links with all the active objects */ while (!hlist_empty(&cookie->backing_objects)) { object = hlist_entry(cookie->backing_objects.first, @@ -456,6 +466,10 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire) BUG(); } + /* detach pointers back to the netfs */ + cookie->netfs_data = NULL; + cookie->def = NULL; + spin_unlock(&cookie->lock); if (cookie->parent) { diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 1c341304621f..edd7434ab6e5 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -17,6 +17,7 @@ * - cache->object_list_lock * - object->lock * - object->parent->lock + * - cookie->stores_lock * - fscache_thread_lock * */ @@ -88,17 +89,31 @@ extern int fscache_wait_bit_interruptible(void *); /* * object.c */ +extern const char fscache_object_states_short[FSCACHE_OBJECT__NSTATES][5]; + extern void fscache_withdrawing_object(struct fscache_cache *, struct fscache_object *); extern void fscache_enqueue_object(struct fscache_object *); /* + * object-list.c + */ +#ifdef CONFIG_FSCACHE_OBJECT_LIST +extern const struct file_operations fscache_objlist_fops; + +extern void fscache_objlist_add(struct fscache_object *); +#else +#define fscache_objlist_add(object) do {} while(0) +#endif + +/* * operation.c */ extern int fscache_submit_exclusive_op(struct fscache_object *, struct fscache_operation *); extern int fscache_submit_op(struct fscache_object *, struct fscache_operation *); +extern int fscache_cancel_op(struct fscache_operation *); extern void fscache_abort_object(struct fscache_object *); extern void fscache_start_operations(struct fscache_object *); extern void fscache_operation_gc(struct work_struct *); @@ -127,6 +142,8 @@ extern atomic_t fscache_n_op_enqueue; extern atomic_t fscache_n_op_deferred_release; extern atomic_t fscache_n_op_release; extern atomic_t fscache_n_op_gc; +extern atomic_t fscache_n_op_cancelled; +extern atomic_t fscache_n_op_rejected; extern atomic_t fscache_n_attr_changed; extern atomic_t fscache_n_attr_changed_ok; @@ -138,6 +155,8 @@ extern atomic_t fscache_n_allocs; extern atomic_t fscache_n_allocs_ok; extern atomic_t fscache_n_allocs_wait; extern atomic_t fscache_n_allocs_nobufs; +extern atomic_t fscache_n_allocs_intr; +extern atomic_t fscache_n_allocs_object_dead; extern atomic_t fscache_n_alloc_ops; extern atomic_t fscache_n_alloc_op_waits; @@ -148,6 +167,7 @@ extern atomic_t fscache_n_retrievals_nodata; extern atomic_t fscache_n_retrievals_nobufs; extern atomic_t fscache_n_retrievals_intr; extern atomic_t fscache_n_retrievals_nomem; +extern atomic_t fscache_n_retrievals_object_dead; extern atomic_t fscache_n_retrieval_ops; extern atomic_t fscache_n_retrieval_op_waits; @@ -158,6 +178,14 @@ extern atomic_t fscache_n_stores_nobufs; extern atomic_t fscache_n_stores_oom; extern atomic_t fscache_n_store_ops; extern atomic_t fscache_n_store_calls; +extern atomic_t fscache_n_store_pages; +extern atomic_t fscache_n_store_radix_deletes; +extern atomic_t fscache_n_store_pages_over_limit; + +extern atomic_t fscache_n_store_vmscan_not_storing; +extern atomic_t fscache_n_store_vmscan_gone; +extern atomic_t fscache_n_store_vmscan_busy; +extern atomic_t fscache_n_store_vmscan_cancelled; extern atomic_t fscache_n_marks; extern atomic_t fscache_n_uncaches; @@ -176,6 +204,7 @@ extern atomic_t fscache_n_updates_run; extern atomic_t fscache_n_relinquishes; extern atomic_t fscache_n_relinquishes_null; extern atomic_t fscache_n_relinquishes_waitcrt; +extern atomic_t fscache_n_relinquishes_retire; extern atomic_t fscache_n_cookie_index; extern atomic_t fscache_n_cookie_data; @@ -186,6 +215,7 @@ extern atomic_t fscache_n_object_no_alloc; extern atomic_t fscache_n_object_lookups; extern atomic_t fscache_n_object_lookups_negative; extern atomic_t fscache_n_object_lookups_positive; +extern atomic_t fscache_n_object_lookups_timed_out; extern atomic_t fscache_n_object_created; extern atomic_t fscache_n_object_avail; extern atomic_t fscache_n_object_dead; @@ -195,15 +225,41 @@ extern atomic_t fscache_n_checkaux_okay; extern atomic_t fscache_n_checkaux_update; extern atomic_t fscache_n_checkaux_obsolete; +extern atomic_t fscache_n_cop_alloc_object; +extern atomic_t fscache_n_cop_lookup_object; +extern atomic_t fscache_n_cop_lookup_complete; +extern atomic_t fscache_n_cop_grab_object; +extern atomic_t fscache_n_cop_update_object; +extern atomic_t fscache_n_cop_drop_object; +extern atomic_t fscache_n_cop_put_object; +extern atomic_t fscache_n_cop_sync_cache; +extern atomic_t fscache_n_cop_attr_changed; +extern atomic_t fscache_n_cop_read_or_alloc_page; +extern atomic_t fscache_n_cop_read_or_alloc_pages; +extern atomic_t fscache_n_cop_allocate_page; +extern atomic_t fscache_n_cop_allocate_pages; +extern atomic_t fscache_n_cop_write_page; +extern atomic_t fscache_n_cop_uncache_page; +extern atomic_t fscache_n_cop_dissociate_pages; + static inline void fscache_stat(atomic_t *stat) { atomic_inc(stat); } +static inline void fscache_stat_d(atomic_t *stat) +{ + atomic_dec(stat); +} + +#define __fscache_stat(stat) (stat) + extern const struct file_operations fscache_stats_fops; #else +#define __fscache_stat(stat) (NULL) #define fscache_stat(stat) do {} while (0) +#define fscache_stat_d(stat) do {} while (0) #endif /* diff --git a/fs/fscache/main.c b/fs/fscache/main.c index 4de41b597499..add6bdb53f04 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -48,7 +48,7 @@ static int __init fscache_init(void) { int ret; - ret = slow_work_register_user(); + ret = slow_work_register_user(THIS_MODULE); if (ret < 0) goto error_slow_work; @@ -80,7 +80,7 @@ error_kobj: error_cookie_jar: fscache_proc_cleanup(); error_proc: - slow_work_unregister_user(); + slow_work_unregister_user(THIS_MODULE); error_slow_work: return ret; } @@ -97,7 +97,7 @@ static void __exit fscache_exit(void) kobject_put(fscache_root); kmem_cache_destroy(fscache_cookie_jar); fscache_proc_cleanup(); - slow_work_unregister_user(); + slow_work_unregister_user(THIS_MODULE); printk(KERN_NOTICE "FS-Cache: Unloaded\n"); } diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c new file mode 100644 index 000000000000..e590242fa41a --- /dev/null +++ b/fs/fscache/object-list.c @@ -0,0 +1,432 @@ +/* Global fscache object list maintainer and viewer + * + * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#define FSCACHE_DEBUG_LEVEL COOKIE +#include <linux/module.h> +#include <linux/seq_file.h> +#include <linux/key.h> +#include <keys/user-type.h> +#include "internal.h" + +static struct rb_root fscache_object_list; +static DEFINE_RWLOCK(fscache_object_list_lock); + +struct fscache_objlist_data { + unsigned long config; /* display configuration */ +#define FSCACHE_OBJLIST_CONFIG_KEY 0x00000001 /* show object keys */ +#define FSCACHE_OBJLIST_CONFIG_AUX 0x00000002 /* show object auxdata */ +#define FSCACHE_OBJLIST_CONFIG_COOKIE 0x00000004 /* show objects with cookies */ +#define FSCACHE_OBJLIST_CONFIG_NOCOOKIE 0x00000008 /* show objects without cookies */ +#define FSCACHE_OBJLIST_CONFIG_BUSY 0x00000010 /* show busy objects */ +#define FSCACHE_OBJLIST_CONFIG_IDLE 0x00000020 /* show idle objects */ +#define FSCACHE_OBJLIST_CONFIG_PENDWR 0x00000040 /* show objects with pending writes */ +#define FSCACHE_OBJLIST_CONFIG_NOPENDWR 0x00000080 /* show objects without pending writes */ +#define FSCACHE_OBJLIST_CONFIG_READS 0x00000100 /* show objects with active reads */ +#define FSCACHE_OBJLIST_CONFIG_NOREADS 0x00000200 /* show objects without active reads */ +#define FSCACHE_OBJLIST_CONFIG_EVENTS 0x00000400 /* show objects with events */ +#define FSCACHE_OBJLIST_CONFIG_NOEVENTS 0x00000800 /* show objects without no events */ +#define FSCACHE_OBJLIST_CONFIG_WORK 0x00001000 /* show objects with slow work */ +#define FSCACHE_OBJLIST_CONFIG_NOWORK 0x00002000 /* show objects without slow work */ + + u8 buf[512]; /* key and aux data buffer */ +}; + +/* + * Add an object to the object list + * - we use the address of the fscache_object structure as the key into the + * tree + */ +void fscache_objlist_add(struct fscache_object *obj) +{ + struct fscache_object *xobj; + struct rb_node **p = &fscache_object_list.rb_node, *parent = NULL; + + write_lock(&fscache_object_list_lock); + + while (*p) { + parent = *p; + xobj = rb_entry(parent, struct fscache_object, objlist_link); + + if (obj < xobj) + p = &(*p)->rb_left; + else if (obj > xobj) + p = &(*p)->rb_right; + else + BUG(); + } + + rb_link_node(&obj->objlist_link, parent, p); + rb_insert_color(&obj->objlist_link, &fscache_object_list); + + write_unlock(&fscache_object_list_lock); +} + +/** + * fscache_object_destroy - Note that a cache object is about to be destroyed + * @object: The object to be destroyed + * + * Note the imminent destruction and deallocation of a cache object record. + */ +void fscache_object_destroy(struct fscache_object *obj) +{ + write_lock(&fscache_object_list_lock); + + BUG_ON(RB_EMPTY_ROOT(&fscache_object_list)); + rb_erase(&obj->objlist_link, &fscache_object_list); + + write_unlock(&fscache_object_list_lock); +} +EXPORT_SYMBOL(fscache_object_destroy); + +/* + * find the object in the tree on or after the specified index + */ +static struct fscache_object *fscache_objlist_lookup(loff_t *_pos) +{ + struct fscache_object *pobj, *obj, *minobj = NULL; + struct rb_node *p; + unsigned long pos; + + if (*_pos >= (unsigned long) ERR_PTR(-ENOENT)) + return NULL; + pos = *_pos; + + /* banners (can't represent line 0 by pos 0 as that would involve + * returning a NULL pointer) */ + if (pos == 0) + return (struct fscache_object *) ++(*_pos); + if (pos < 3) + return (struct fscache_object *)pos; + + pobj = (struct fscache_object *)pos; + p = fscache_object_list.rb_node; + while (p) { + obj = rb_entry(p, struct fscache_object, objlist_link); + if (pobj < obj) { + if (!minobj || minobj > obj) + minobj = obj; + p = p->rb_left; + } else if (pobj > obj) { + p = p->rb_right; + } else { + minobj = obj; + break; + } + obj = NULL; + } + + if (!minobj) + *_pos = (unsigned long) ERR_PTR(-ENOENT); + else if (minobj != obj) + *_pos = (unsigned long) minobj; + return minobj; +} + +/* + * set up the iterator to start reading from the first line + */ +static void *fscache_objlist_start(struct seq_file *m, loff_t *_pos) + __acquires(&fscache_object_list_lock) +{ + read_lock(&fscache_object_list_lock); + return fscache_objlist_lookup(_pos); +} + +/* + * move to the next line + */ +static void *fscache_objlist_next(struct seq_file *m, void *v, loff_t *_pos) +{ + (*_pos)++; + return fscache_objlist_lookup(_pos); +} + +/* + * clean up after reading + */ +static void fscache_objlist_stop(struct seq_file *m, void *v) + __releases(&fscache_object_list_lock) +{ + read_unlock(&fscache_object_list_lock); +} + +/* + * display an object + */ +static int fscache_objlist_show(struct seq_file *m, void *v) +{ + struct fscache_objlist_data *data = m->private; + struct fscache_object *obj = v; + unsigned long config = data->config; + uint16_t keylen, auxlen; + char _type[3], *type; + bool no_cookie; + u8 *buf = data->buf, *p; + + if ((unsigned long) v == 1) { + seq_puts(m, "OBJECT PARENT STAT CHLDN OPS OOP IPR EX READS" + " EM EV F S" + " | NETFS_COOKIE_DEF TY FL NETFS_DATA"); + if (config & (FSCACHE_OBJLIST_CONFIG_KEY | + FSCACHE_OBJLIST_CONFIG_AUX)) + seq_puts(m, " "); + if (config & FSCACHE_OBJLIST_CONFIG_KEY) + seq_puts(m, "OBJECT_KEY"); + if ((config & (FSCACHE_OBJLIST_CONFIG_KEY | + FSCACHE_OBJLIST_CONFIG_AUX)) == + (FSCACHE_OBJLIST_CONFIG_KEY | FSCACHE_OBJLIST_CONFIG_AUX)) + seq_puts(m, ", "); + if (config & FSCACHE_OBJLIST_CONFIG_AUX) + seq_puts(m, "AUX_DATA"); + seq_puts(m, "\n"); + return 0; + } + + if ((unsigned long) v == 2) { + seq_puts(m, "======== ======== ==== ===== === === === == =====" + " == == = =" + " | ================ == == ================"); + if (config & (FSCACHE_OBJLIST_CONFIG_KEY | + FSCACHE_OBJLIST_CONFIG_AUX)) + seq_puts(m, " ================"); + seq_puts(m, "\n"); + return 0; + } + + /* filter out any unwanted objects */ +#define FILTER(criterion, _yes, _no) \ + do { \ + unsigned long yes = FSCACHE_OBJLIST_CONFIG_##_yes; \ + unsigned long no = FSCACHE_OBJLIST_CONFIG_##_no; \ + if (criterion) { \ + if (!(config & yes)) \ + return 0; \ + } else { \ + if (!(config & no)) \ + return 0; \ + } \ + } while(0) + + if (~config) { + FILTER(obj->cookie, + COOKIE, NOCOOKIE); + FILTER(obj->state != FSCACHE_OBJECT_ACTIVE || + obj->n_ops != 0 || + obj->n_obj_ops != 0 || + obj->flags || + !list_empty(&obj->dependents), + BUSY, IDLE); + FILTER(test_bit(FSCACHE_OBJECT_PENDING_WRITE, &obj->flags), + PENDWR, NOPENDWR); + FILTER(atomic_read(&obj->n_reads), + READS, NOREADS); + FILTER(obj->events & obj->event_mask, + EVENTS, NOEVENTS); + FILTER(obj->work.flags & ~(1UL << SLOW_WORK_VERY_SLOW), + WORK, NOWORK); + } + + seq_printf(m, + "%8x %8x %s %5u %3u %3u %3u %2u %5u %2lx %2lx %1lx %1lx | ", + obj->debug_id, + obj->parent ? obj->parent->debug_id : -1, + fscache_object_states_short[obj->state], + obj->n_children, + obj->n_ops, + obj->n_obj_ops, + obj->n_in_progress, + obj->n_exclusive, + atomic_read(&obj->n_reads), + obj->event_mask & FSCACHE_OBJECT_EVENTS_MASK, + obj->events, + obj->flags, + obj->work.flags); + + no_cookie = true; + keylen = auxlen = 0; + if (obj->cookie) { + spin_lock(&obj->lock); + if (obj->cookie) { + switch (obj->cookie->def->type) { + case 0: + type = "IX"; + break; + case 1: + type = "DT"; + break; + default: + sprintf(_type, "%02u", + obj->cookie->def->type); + type = _type; + break; + } + + seq_printf(m, "%-16s %s %2lx %16p", + obj->cookie->def->name, + type, + obj->cookie->flags, + obj->cookie->netfs_data); + + if (obj->cookie->def->get_key && + config & FSCACHE_OBJLIST_CONFIG_KEY) + keylen = obj->cookie->def->get_key( + obj->cookie->netfs_data, + buf, 400); + + if (obj->cookie->def->get_aux && + config & FSCACHE_OBJLIST_CONFIG_AUX) + auxlen = obj->cookie->def->get_aux( + obj->cookie->netfs_data, + buf + keylen, 512 - keylen); + + no_cookie = false; + } + spin_unlock(&obj->lock); + + if (!no_cookie && (keylen > 0 || auxlen > 0)) { + seq_printf(m, " "); + for (p = buf; keylen > 0; keylen--) + seq_printf(m, "%02x", *p++); + if (auxlen > 0) { + if (config & FSCACHE_OBJLIST_CONFIG_KEY) + seq_printf(m, ", "); + for (; auxlen > 0; auxlen--) + seq_printf(m, "%02x", *p++); + } + } + } + + if (no_cookie) + seq_printf(m, "<no_cookie>\n"); + else + seq_printf(m, "\n"); + return 0; +} + +static const struct seq_operations fscache_objlist_ops = { + .start = fscache_objlist_start, + .stop = fscache_objlist_stop, + .next = fscache_objlist_next, + .show = fscache_objlist_show, +}; + +/* + * get the configuration for filtering the list + */ +static void fscache_objlist_config(struct fscache_objlist_data *data) +{ +#ifdef CONFIG_KEYS + struct user_key_payload *confkey; + unsigned long config; + struct key *key; + const char *buf; + int len; + + key = request_key(&key_type_user, "fscache:objlist", NULL); + if (IS_ERR(key)) + goto no_config; + + config = 0; + rcu_read_lock(); + + confkey = key->payload.data; + buf = confkey->data; + + for (len = confkey->datalen - 1; len >= 0; len--) { + switch (buf[len]) { + case 'K': config |= FSCACHE_OBJLIST_CONFIG_KEY; break; + case 'A': config |= FSCACHE_OBJLIST_CONFIG_AUX; break; + case 'C': config |= FSCACHE_OBJLIST_CONFIG_COOKIE; break; + case 'c': config |= FSCACHE_OBJLIST_CONFIG_NOCOOKIE; break; + case 'B': config |= FSCACHE_OBJLIST_CONFIG_BUSY; break; + case 'b': config |= FSCACHE_OBJLIST_CONFIG_IDLE; break; + case 'W': config |= FSCACHE_OBJLIST_CONFIG_PENDWR; break; + case 'w': config |= FSCACHE_OBJLIST_CONFIG_NOPENDWR; break; + case 'R': config |= FSCACHE_OBJLIST_CONFIG_READS; break; + case 'r': config |= FSCACHE_OBJLIST_CONFIG_NOREADS; break; + case 'S': config |= FSCACHE_OBJLIST_CONFIG_WORK; break; + case 's': config |= FSCACHE_OBJLIST_CONFIG_NOWORK; break; + } + } + + rcu_read_unlock(); + key_put(key); + + if (!(config & (FSCACHE_OBJLIST_CONFIG_COOKIE | FSCACHE_OBJLIST_CONFIG_NOCOOKIE))) + config |= FSCACHE_OBJLIST_CONFIG_COOKIE | FSCACHE_OBJLIST_CONFIG_NOCOOKIE; + if (!(config & (FSCACHE_OBJLIST_CONFIG_BUSY | FSCACHE_OBJLIST_CONFIG_IDLE))) + config |= FSCACHE_OBJLIST_CONFIG_BUSY | FSCACHE_OBJLIST_CONFIG_IDLE; + if (!(config & (FSCACHE_OBJLIST_CONFIG_PENDWR | FSCACHE_OBJLIST_CONFIG_NOPENDWR))) + config |= FSCACHE_OBJLIST_CONFIG_PENDWR | FSCACHE_OBJLIST_CONFIG_NOPENDWR; + if (!(config & (FSCACHE_OBJLIST_CONFIG_READS | FSCACHE_OBJLIST_CONFIG_NOREADS))) + config |= FSCACHE_OBJLIST_CONFIG_READS | FSCACHE_OBJLIST_CONFIG_NOREADS; + if (!(config & (FSCACHE_OBJLIST_CONFIG_EVENTS | FSCACHE_OBJLIST_CONFIG_NOEVENTS))) + config |= FSCACHE_OBJLIST_CONFIG_EVENTS | FSCACHE_OBJLIST_CONFIG_NOEVENTS; + if (!(config & (FSCACHE_OBJLIST_CONFIG_WORK | FSCACHE_OBJLIST_CONFIG_NOWORK))) + config |= FSCACHE_OBJLIST_CONFIG_WORK | FSCACHE_OBJLIST_CONFIG_NOWORK; + + data->config = config; + return; + +no_config: +#endif + data->config = ULONG_MAX; +} + +/* + * open "/proc/fs/fscache/objects" to provide a list of active objects + * - can be configured by a user-defined key added to the caller's keyrings + */ +static int fscache_objlist_open(struct inode *inode, struct file *file) +{ + struct fscache_objlist_data *data; + struct seq_file *m; + int ret; + + ret = seq_open(file, &fscache_objlist_ops); + if (ret < 0) + return ret; + + m = file->private_data; + + /* buffer for key extraction */ + data = kmalloc(sizeof(struct fscache_objlist_data), GFP_KERNEL); + if (!data) { + seq_release(inode, file); + return -ENOMEM; + } + + /* get the configuration key */ + fscache_objlist_config(data); + + m->private = data; + return 0; +} + +/* + * clean up on close + */ +static int fscache_objlist_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + + kfree(m->private); + m->private = NULL; + return seq_release(inode, file); +} + +const struct file_operations fscache_objlist_fops = { + .owner = THIS_MODULE, + .open = fscache_objlist_open, + .read = seq_read, + .llseek = seq_lseek, + .release = fscache_objlist_release, +}; diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 392a41b1b79d..e513ac599c8e 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -14,9 +14,10 @@ #define FSCACHE_DEBUG_LEVEL COOKIE #include <linux/module.h> +#include <linux/seq_file.h> #include "internal.h" -const char *fscache_object_states[] = { +const char *fscache_object_states[FSCACHE_OBJECT__NSTATES] = { [FSCACHE_OBJECT_INIT] = "OBJECT_INIT", [FSCACHE_OBJECT_LOOKING_UP] = "OBJECT_LOOKING_UP", [FSCACHE_OBJECT_CREATING] = "OBJECT_CREATING", @@ -33,9 +34,28 @@ const char *fscache_object_states[] = { }; EXPORT_SYMBOL(fscache_object_states); +const char fscache_object_states_short[FSCACHE_OBJECT__NSTATES][5] = { + [FSCACHE_OBJECT_INIT] = "INIT", + [FSCACHE_OBJECT_LOOKING_UP] = "LOOK", + [FSCACHE_OBJECT_CREATING] = "CRTN", + [FSCACHE_OBJECT_AVAILABLE] = "AVBL", + [FSCACHE_OBJECT_ACTIVE] = "ACTV", + [FSCACHE_OBJECT_UPDATING] = "UPDT", + [FSCACHE_OBJECT_DYING] = "DYNG", + [FSCACHE_OBJECT_LC_DYING] = "LCDY", + [FSCACHE_OBJECT_ABORT_INIT] = "ABTI", + [FSCACHE_OBJECT_RELEASING] = "RELS", + [FSCACHE_OBJECT_RECYCLING] = "RCYC", + [FSCACHE_OBJECT_WITHDRAWING] = "WTHD", + [FSCACHE_OBJECT_DEAD] = "DEAD", +}; + static void fscache_object_slow_work_put_ref(struct slow_work *); static int fscache_object_slow_work_get_ref(struct slow_work *); static void fscache_object_slow_work_execute(struct slow_work *); +#ifdef CONFIG_SLOW_WORK_PROC +static void fscache_object_slow_work_desc(struct slow_work *, struct seq_file *); +#endif static void fscache_initialise_object(struct fscache_object *); static void fscache_lookup_object(struct fscache_object *); static void fscache_object_available(struct fscache_object *); @@ -45,9 +65,13 @@ static void fscache_enqueue_dependents(struct fscache_object *); static void fscache_dequeue_object(struct fscache_object *); const struct slow_work_ops fscache_object_slow_work_ops = { + .owner = THIS_MODULE, .get_ref = fscache_object_slow_work_get_ref, .put_ref = fscache_object_slow_work_put_ref, .execute = fscache_object_slow_work_execute, +#ifdef CONFIG_SLOW_WORK_PROC + .desc = fscache_object_slow_work_desc, +#endif }; EXPORT_SYMBOL(fscache_object_slow_work_ops); @@ -81,6 +105,7 @@ static inline void fscache_done_parent_op(struct fscache_object *object) static void fscache_object_state_machine(struct fscache_object *object) { enum fscache_object_state new_state; + struct fscache_cookie *cookie; ASSERT(object != NULL); @@ -120,20 +145,31 @@ static void fscache_object_state_machine(struct fscache_object *object) case FSCACHE_OBJECT_UPDATING: clear_bit(FSCACHE_OBJECT_EV_UPDATE, &object->events); fscache_stat(&fscache_n_updates_run); + fscache_stat(&fscache_n_cop_update_object); object->cache->ops->update_object(object); + fscache_stat_d(&fscache_n_cop_update_object); goto active_transit; /* handle an object dying during lookup or creation */ case FSCACHE_OBJECT_LC_DYING: object->event_mask &= ~(1 << FSCACHE_OBJECT_EV_UPDATE); + fscache_stat(&fscache_n_cop_lookup_complete); object->cache->ops->lookup_complete(object); + fscache_stat_d(&fscache_n_cop_lookup_complete); spin_lock(&object->lock); object->state = FSCACHE_OBJECT_DYING; - if (test_and_clear_bit(FSCACHE_COOKIE_CREATING, - &object->cookie->flags)) - wake_up_bit(&object->cookie->flags, - FSCACHE_COOKIE_CREATING); + cookie = object->cookie; + if (cookie) { + if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, + &cookie->flags)) + wake_up_bit(&cookie->flags, + FSCACHE_COOKIE_LOOKING_UP); + if (test_and_clear_bit(FSCACHE_COOKIE_CREATING, + &cookie->flags)) + wake_up_bit(&cookie->flags, + FSCACHE_COOKIE_CREATING); + } spin_unlock(&object->lock); fscache_done_parent_op(object); @@ -165,6 +201,7 @@ static void fscache_object_state_machine(struct fscache_object *object) } spin_unlock(&object->lock); fscache_enqueue_dependents(object); + fscache_start_operations(object); goto terminal_transit; /* handle an abort during initialisation */ @@ -316,14 +353,29 @@ static void fscache_object_slow_work_execute(struct slow_work *work) _enter("{OBJ%x}", object->debug_id); - clear_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events); - start = jiffies; fscache_object_state_machine(object); fscache_hist(fscache_objs_histogram, start); if (object->events & object->event_mask) fscache_enqueue_object(object); + clear_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events); +} + +/* + * describe an object for slow-work debugging + */ +#ifdef CONFIG_SLOW_WORK_PROC +static void fscache_object_slow_work_desc(struct slow_work *work, + struct seq_file *m) +{ + struct fscache_object *object = + container_of(work, struct fscache_object, work); + + seq_printf(m, "FSC: OBJ%x: %s", + object->debug_id, + fscache_object_states_short[object->state]); } +#endif /* * initialise an object @@ -376,7 +428,9 @@ static void fscache_initialise_object(struct fscache_object *object) * binding on to us, so we need to make sure we don't * add ourself to the list multiple times */ if (list_empty(&object->dep_link)) { + fscache_stat(&fscache_n_cop_grab_object); object->cache->ops->grab_object(object); + fscache_stat_d(&fscache_n_cop_grab_object); list_add(&object->dep_link, &parent->dependents); @@ -414,6 +468,7 @@ static void fscache_lookup_object(struct fscache_object *object) { struct fscache_cookie *cookie = object->cookie; struct fscache_object *parent; + int ret; _enter(""); @@ -438,11 +493,20 @@ static void fscache_lookup_object(struct fscache_object *object) object->cache->tag->name); fscache_stat(&fscache_n_object_lookups); - object->cache->ops->lookup_object(object); + fscache_stat(&fscache_n_cop_lookup_object); + ret = object->cache->ops->lookup_object(object); + fscache_stat_d(&fscache_n_cop_lookup_object); if (test_bit(FSCACHE_OBJECT_EV_ERROR, &object->events)) set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags); + if (ret == -ETIMEDOUT) { + /* probably stuck behind another object, so move this one to + * the back of the queue */ + fscache_stat(&fscache_n_object_lookups_timed_out); + set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events); + } + _leave(""); } @@ -546,7 +610,8 @@ static void fscache_object_available(struct fscache_object *object) spin_lock(&object->lock); - if (test_and_clear_bit(FSCACHE_COOKIE_CREATING, &object->cookie->flags)) + if (object->cookie && + test_and_clear_bit(FSCACHE_COOKIE_CREATING, &object->cookie->flags)) wake_up_bit(&object->cookie->flags, FSCACHE_COOKIE_CREATING); fscache_done_parent_op(object); @@ -562,7 +627,9 @@ static void fscache_object_available(struct fscache_object *object) } spin_unlock(&object->lock); + fscache_stat(&fscache_n_cop_lookup_complete); object->cache->ops->lookup_complete(object); + fscache_stat_d(&fscache_n_cop_lookup_complete); fscache_enqueue_dependents(object); fscache_hist(fscache_obj_instantiate_histogram, object->lookup_jif); @@ -581,11 +648,16 @@ static void fscache_drop_object(struct fscache_object *object) _enter("{OBJ%x,%d}", object->debug_id, object->n_children); + ASSERTCMP(object->cookie, ==, NULL); + ASSERT(hlist_unhashed(&object->cookie_link)); + spin_lock(&cache->object_list_lock); list_del_init(&object->cache_link); spin_unlock(&cache->object_list_lock); + fscache_stat(&fscache_n_cop_drop_object); cache->ops->drop_object(object); + fscache_stat_d(&fscache_n_cop_drop_object); if (parent) { _debug("release parent OBJ%x {%d}", @@ -600,7 +672,9 @@ static void fscache_drop_object(struct fscache_object *object) } /* this just shifts the object release to the slow work processor */ + fscache_stat(&fscache_n_cop_put_object); object->cache->ops->put_object(object); + fscache_stat_d(&fscache_n_cop_put_object); _leave(""); } @@ -690,8 +764,12 @@ static int fscache_object_slow_work_get_ref(struct slow_work *work) { struct fscache_object *object = container_of(work, struct fscache_object, work); + int ret; - return object->cache->ops->grab_object(object) ? 0 : -EAGAIN; + fscache_stat(&fscache_n_cop_grab_object); + ret = object->cache->ops->grab_object(object) ? 0 : -EAGAIN; + fscache_stat_d(&fscache_n_cop_grab_object); + return ret; } /* @@ -702,7 +780,9 @@ static void fscache_object_slow_work_put_ref(struct slow_work *work) struct fscache_object *object = container_of(work, struct fscache_object, work); - return object->cache->ops->put_object(object); + fscache_stat(&fscache_n_cop_put_object); + object->cache->ops->put_object(object); + fscache_stat_d(&fscache_n_cop_put_object); } /* @@ -739,7 +819,9 @@ static void fscache_enqueue_dependents(struct fscache_object *object) /* sort onto appropriate lists */ fscache_enqueue_object(dep); + fscache_stat(&fscache_n_cop_put_object); dep->cache->ops->put_object(dep); + fscache_stat_d(&fscache_n_cop_put_object); if (!list_empty(&object->dependents)) cond_resched_lock(&object->lock); diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c index e7f8d53b8b6b..313e79a14266 100644 --- a/fs/fscache/operation.c +++ b/fs/fscache/operation.c @@ -13,6 +13,7 @@ #define FSCACHE_DEBUG_LEVEL OPERATION #include <linux/module.h> +#include <linux/seq_file.h> #include "internal.h" atomic_t fscache_op_debug_id; @@ -31,32 +32,33 @@ void fscache_enqueue_operation(struct fscache_operation *op) _enter("{OBJ%x OP%x,%u}", op->object->debug_id, op->debug_id, atomic_read(&op->usage)); + fscache_set_op_state(op, "EnQ"); + + ASSERT(list_empty(&op->pend_link)); ASSERT(op->processor != NULL); ASSERTCMP(op->object->state, >=, FSCACHE_OBJECT_AVAILABLE); ASSERTCMP(atomic_read(&op->usage), >, 0); - if (list_empty(&op->pend_link)) { - switch (op->flags & FSCACHE_OP_TYPE) { - case FSCACHE_OP_FAST: - _debug("queue fast"); - atomic_inc(&op->usage); - if (!schedule_work(&op->fast_work)) - fscache_put_operation(op); - break; - case FSCACHE_OP_SLOW: - _debug("queue slow"); - slow_work_enqueue(&op->slow_work); - break; - case FSCACHE_OP_MYTHREAD: - _debug("queue for caller's attention"); - break; - default: - printk(KERN_ERR "FS-Cache: Unexpected op type %lx", - op->flags); - BUG(); - break; - } - fscache_stat(&fscache_n_op_enqueue); + fscache_stat(&fscache_n_op_enqueue); + switch (op->flags & FSCACHE_OP_TYPE) { + case FSCACHE_OP_FAST: + _debug("queue fast"); + atomic_inc(&op->usage); + if (!schedule_work(&op->fast_work)) + fscache_put_operation(op); + break; + case FSCACHE_OP_SLOW: + _debug("queue slow"); + slow_work_enqueue(&op->slow_work); + break; + case FSCACHE_OP_MYTHREAD: + _debug("queue for caller's attention"); + break; + default: + printk(KERN_ERR "FS-Cache: Unexpected op type %lx", + op->flags); + BUG(); + break; } } EXPORT_SYMBOL(fscache_enqueue_operation); @@ -67,6 +69,8 @@ EXPORT_SYMBOL(fscache_enqueue_operation); static void fscache_run_op(struct fscache_object *object, struct fscache_operation *op) { + fscache_set_op_state(op, "Run"); + object->n_in_progress++; if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags)) wake_up_bit(&op->flags, FSCACHE_OP_WAITING); @@ -87,9 +91,12 @@ int fscache_submit_exclusive_op(struct fscache_object *object, _enter("{OBJ%x OP%x},", object->debug_id, op->debug_id); + fscache_set_op_state(op, "SubmitX"); + spin_lock(&object->lock); ASSERTCMP(object->n_ops, >=, object->n_in_progress); ASSERTCMP(object->n_ops, >=, object->n_exclusive); + ASSERT(list_empty(&op->pend_link)); ret = -ENOBUFS; if (fscache_object_is_active(object)) { @@ -190,9 +197,12 @@ int fscache_submit_op(struct fscache_object *object, ASSERTCMP(atomic_read(&op->usage), >, 0); + fscache_set_op_state(op, "Submit"); + spin_lock(&object->lock); ASSERTCMP(object->n_ops, >=, object->n_in_progress); ASSERTCMP(object->n_ops, >=, object->n_exclusive); + ASSERT(list_empty(&op->pend_link)); ostate = object->state; smp_rmb(); @@ -222,6 +232,11 @@ int fscache_submit_op(struct fscache_object *object, list_add_tail(&op->pend_link, &object->pending_ops); fscache_stat(&fscache_n_op_pend); ret = 0; + } else if (object->state == FSCACHE_OBJECT_DYING || + object->state == FSCACHE_OBJECT_LC_DYING || + object->state == FSCACHE_OBJECT_WITHDRAWING) { + fscache_stat(&fscache_n_op_rejected); + ret = -ENOBUFS; } else if (!test_bit(FSCACHE_IOERROR, &object->cache->flags)) { fscache_report_unexpected_submission(object, op, ostate); ASSERT(!fscache_object_is_active(object)); @@ -264,12 +279,7 @@ void fscache_start_operations(struct fscache_object *object) stop = true; } list_del_init(&op->pend_link); - object->n_in_progress++; - - if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags)) - wake_up_bit(&op->flags, FSCACHE_OP_WAITING); - if (op->processor) - fscache_enqueue_operation(op); + fscache_run_op(object, op); /* the pending queue was holding a ref on the object */ fscache_put_operation(op); @@ -282,6 +292,36 @@ void fscache_start_operations(struct fscache_object *object) } /* + * cancel an operation that's pending on an object + */ +int fscache_cancel_op(struct fscache_operation *op) +{ + struct fscache_object *object = op->object; + int ret; + + _enter("OBJ%x OP%x}", op->object->debug_id, op->debug_id); + + spin_lock(&object->lock); + + ret = -EBUSY; + if (!list_empty(&op->pend_link)) { + fscache_stat(&fscache_n_op_cancelled); + list_del_init(&op->pend_link); + object->n_ops--; + if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) + object->n_exclusive--; + if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags)) + wake_up_bit(&op->flags, FSCACHE_OP_WAITING); + fscache_put_operation(op); + ret = 0; + } + + spin_unlock(&object->lock); + _leave(" = %d", ret); + return ret; +} + +/* * release an operation * - queues pending ops if this is the last in-progress op */ @@ -298,6 +338,8 @@ void fscache_put_operation(struct fscache_operation *op) if (!atomic_dec_and_test(&op->usage)) return; + fscache_set_op_state(op, "Put"); + _debug("PUT OP"); if (test_and_set_bit(FSCACHE_OP_DEAD, &op->flags)) BUG(); @@ -311,6 +353,9 @@ void fscache_put_operation(struct fscache_operation *op) object = op->object; + if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags)) + atomic_dec(&object->n_reads); + /* now... we may get called with the object spinlock held, so we * complete the cleanup here only if we can immediately acquire the * lock, and defer it otherwise */ @@ -452,8 +497,27 @@ static void fscache_op_execute(struct slow_work *work) _leave(""); } +/* + * describe an operation for slow-work debugging + */ +#ifdef CONFIG_SLOW_WORK_PROC +static void fscache_op_desc(struct slow_work *work, struct seq_file *m) +{ + struct fscache_operation *op = + container_of(work, struct fscache_operation, slow_work); + + seq_printf(m, "FSC: OBJ%x OP%x: %s/%s fl=%lx", + op->object->debug_id, op->debug_id, + op->name, op->state, op->flags); +} +#endif + const struct slow_work_ops fscache_op_slow_work_ops = { + .owner = THIS_MODULE, .get_ref = fscache_op_get_ref, .put_ref = fscache_op_put_ref, .execute = fscache_op_execute, +#ifdef CONFIG_SLOW_WORK_PROC + .desc = fscache_op_desc, +#endif }; diff --git a/fs/fscache/page.c b/fs/fscache/page.c index 2568e0eb644f..c598ea4c4e7d 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -43,18 +43,102 @@ void __fscache_wait_on_page_write(struct fscache_cookie *cookie, struct page *pa EXPORT_SYMBOL(__fscache_wait_on_page_write); /* - * note that a page has finished being written to the cache + * decide whether a page can be released, possibly by cancelling a store to it + * - we're allowed to sleep if __GFP_WAIT is flagged */ -static void fscache_end_page_write(struct fscache_cookie *cookie, struct page *page) +bool __fscache_maybe_release_page(struct fscache_cookie *cookie, + struct page *page, + gfp_t gfp) { struct page *xpage; + void *val; + + _enter("%p,%p,%x", cookie, page, gfp); + + rcu_read_lock(); + val = radix_tree_lookup(&cookie->stores, page->index); + if (!val) { + rcu_read_unlock(); + fscache_stat(&fscache_n_store_vmscan_not_storing); + __fscache_uncache_page(cookie, page); + return true; + } + + /* see if the page is actually undergoing storage - if so we can't get + * rid of it till the cache has finished with it */ + if (radix_tree_tag_get(&cookie->stores, page->index, + FSCACHE_COOKIE_STORING_TAG)) { + rcu_read_unlock(); + goto page_busy; + } + + /* the page is pending storage, so we attempt to cancel the store and + * discard the store request so that the page can be reclaimed */ + spin_lock(&cookie->stores_lock); + rcu_read_unlock(); + + if (radix_tree_tag_get(&cookie->stores, page->index, + FSCACHE_COOKIE_STORING_TAG)) { + /* the page started to undergo storage whilst we were looking, + * so now we can only wait or return */ + spin_unlock(&cookie->stores_lock); + goto page_busy; + } - spin_lock(&cookie->lock); xpage = radix_tree_delete(&cookie->stores, page->index); - spin_unlock(&cookie->lock); - ASSERT(xpage != NULL); + spin_unlock(&cookie->stores_lock); + + if (xpage) { + fscache_stat(&fscache_n_store_vmscan_cancelled); + fscache_stat(&fscache_n_store_radix_deletes); + ASSERTCMP(xpage, ==, page); + } else { + fscache_stat(&fscache_n_store_vmscan_gone); + } wake_up_bit(&cookie->flags, 0); + if (xpage) + page_cache_release(xpage); + __fscache_uncache_page(cookie, page); + return true; + +page_busy: + /* we might want to wait here, but that could deadlock the allocator as + * the slow-work threads writing to the cache may all end up sleeping + * on memory allocation */ + fscache_stat(&fscache_n_store_vmscan_busy); + return false; +} +EXPORT_SYMBOL(__fscache_maybe_release_page); + +/* + * note that a page has finished being written to the cache + */ +static void fscache_end_page_write(struct fscache_object *object, + struct page *page) +{ + struct fscache_cookie *cookie; + struct page *xpage = NULL; + + spin_lock(&object->lock); + cookie = object->cookie; + if (cookie) { + /* delete the page from the tree if it is now no longer + * pending */ + spin_lock(&cookie->stores_lock); + radix_tree_tag_clear(&cookie->stores, page->index, + FSCACHE_COOKIE_STORING_TAG); + if (!radix_tree_tag_get(&cookie->stores, page->index, + FSCACHE_COOKIE_PENDING_TAG)) { + fscache_stat(&fscache_n_store_radix_deletes); + xpage = radix_tree_delete(&cookie->stores, page->index); + } + spin_unlock(&cookie->stores_lock); + wake_up_bit(&cookie->flags, 0); + } + spin_unlock(&object->lock); + if (xpage) + page_cache_release(xpage); } /* @@ -63,14 +147,21 @@ static void fscache_end_page_write(struct fscache_cookie *cookie, struct page *p static void fscache_attr_changed_op(struct fscache_operation *op) { struct fscache_object *object = op->object; + int ret; _enter("{OBJ%x OP%x}", object->debug_id, op->debug_id); fscache_stat(&fscache_n_attr_changed_calls); - if (fscache_object_is_active(object) && - object->cache->ops->attr_changed(object) < 0) - fscache_abort_object(object); + if (fscache_object_is_active(object)) { + fscache_set_op_state(op, "CallFS"); + fscache_stat(&fscache_n_cop_attr_changed); + ret = object->cache->ops->attr_changed(object); + fscache_stat_d(&fscache_n_cop_attr_changed); + fscache_set_op_state(op, "Done"); + if (ret < 0) + fscache_abort_object(object); + } _leave(""); } @@ -99,6 +190,7 @@ int __fscache_attr_changed(struct fscache_cookie *cookie) fscache_operation_init(op, NULL); fscache_operation_init_slow(op, fscache_attr_changed_op); op->flags = FSCACHE_OP_SLOW | (1 << FSCACHE_OP_EXCLUSIVE); + fscache_set_op_name(op, "Attr"); spin_lock(&cookie->lock); @@ -184,6 +276,7 @@ static struct fscache_retrieval *fscache_alloc_retrieval( op->start_time = jiffies; INIT_WORK(&op->op.fast_work, fscache_retrieval_work); INIT_LIST_HEAD(&op->to_do); + fscache_set_op_name(&op->op, "Retr"); return op; } @@ -221,6 +314,43 @@ static int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie) } /* + * wait for an object to become active (or dead) + */ +static int fscache_wait_for_retrieval_activation(struct fscache_object *object, + struct fscache_retrieval *op, + atomic_t *stat_op_waits, + atomic_t *stat_object_dead) +{ + int ret; + + if (!test_bit(FSCACHE_OP_WAITING, &op->op.flags)) + goto check_if_dead; + + _debug(">>> WT"); + fscache_stat(stat_op_waits); + if (wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING, + fscache_wait_bit_interruptible, + TASK_INTERRUPTIBLE) < 0) { + ret = fscache_cancel_op(&op->op); + if (ret == 0) + return -ERESTARTSYS; + + /* it's been removed from the pending queue by another party, + * so we should get to run shortly */ + wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING, + fscache_wait_bit, TASK_UNINTERRUPTIBLE); + } + _debug("<<< GO"); + +check_if_dead: + if (unlikely(fscache_object_is_dead(object))) { + fscache_stat(stat_object_dead); + return -ENOBUFS; + } + return 0; +} + +/* * read a page from the cache or allocate a block in which to store it * - we return: * -ENOMEM - out of memory, nothing done @@ -257,6 +387,7 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie, _leave(" = -ENOMEM"); return -ENOMEM; } + fscache_set_op_name(&op->op, "RetrRA1"); spin_lock(&cookie->lock); @@ -267,6 +398,9 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie, ASSERTCMP(object->state, >, FSCACHE_OBJECT_LOOKING_UP); + atomic_inc(&object->n_reads); + set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags); + if (fscache_submit_op(object, &op->op) < 0) goto nobufs_unlock; spin_unlock(&cookie->lock); @@ -279,23 +413,27 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie, /* we wait for the operation to become active, and then process it * *here*, in this thread, and not in the thread pool */ - if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) { - _debug(">>> WT"); - fscache_stat(&fscache_n_retrieval_op_waits); - wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); - _debug("<<< GO"); - } + ret = fscache_wait_for_retrieval_activation( + object, op, + __fscache_stat(&fscache_n_retrieval_op_waits), + __fscache_stat(&fscache_n_retrievals_object_dead)); + if (ret < 0) + goto error; /* ask the cache to honour the operation */ if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) { + fscache_stat(&fscache_n_cop_allocate_page); ret = object->cache->ops->allocate_page(op, page, gfp); + fscache_stat_d(&fscache_n_cop_allocate_page); if (ret == 0) ret = -ENODATA; } else { + fscache_stat(&fscache_n_cop_read_or_alloc_page); ret = object->cache->ops->read_or_alloc_page(op, page, gfp); + fscache_stat_d(&fscache_n_cop_read_or_alloc_page); } +error: if (ret == -ENOMEM) fscache_stat(&fscache_n_retrievals_nomem); else if (ret == -ERESTARTSYS) @@ -347,7 +485,6 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie, void *context, gfp_t gfp) { - fscache_pages_retrieval_func_t func; struct fscache_retrieval *op; struct fscache_object *object; int ret; @@ -369,6 +506,7 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie, op = fscache_alloc_retrieval(mapping, end_io_func, context); if (!op) return -ENOMEM; + fscache_set_op_name(&op->op, "RetrRAN"); spin_lock(&cookie->lock); @@ -377,6 +515,9 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie, object = hlist_entry(cookie->backing_objects.first, struct fscache_object, cookie_link); + atomic_inc(&object->n_reads); + set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags); + if (fscache_submit_op(object, &op->op) < 0) goto nobufs_unlock; spin_unlock(&cookie->lock); @@ -389,21 +530,27 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie, /* we wait for the operation to become active, and then process it * *here*, in this thread, and not in the thread pool */ - if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) { - _debug(">>> WT"); - fscache_stat(&fscache_n_retrieval_op_waits); - wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); - _debug("<<< GO"); - } + ret = fscache_wait_for_retrieval_activation( + object, op, + __fscache_stat(&fscache_n_retrieval_op_waits), + __fscache_stat(&fscache_n_retrievals_object_dead)); + if (ret < 0) + goto error; /* ask the cache to honour the operation */ - if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) - func = object->cache->ops->allocate_pages; - else - func = object->cache->ops->read_or_alloc_pages; - ret = func(op, pages, nr_pages, gfp); + if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) { + fscache_stat(&fscache_n_cop_allocate_pages); + ret = object->cache->ops->allocate_pages( + op, pages, nr_pages, gfp); + fscache_stat_d(&fscache_n_cop_allocate_pages); + } else { + fscache_stat(&fscache_n_cop_read_or_alloc_pages); + ret = object->cache->ops->read_or_alloc_pages( + op, pages, nr_pages, gfp); + fscache_stat_d(&fscache_n_cop_read_or_alloc_pages); + } +error: if (ret == -ENOMEM) fscache_stat(&fscache_n_retrievals_nomem); else if (ret == -ERESTARTSYS) @@ -461,6 +608,7 @@ int __fscache_alloc_page(struct fscache_cookie *cookie, op = fscache_alloc_retrieval(page->mapping, NULL, NULL); if (!op) return -ENOMEM; + fscache_set_op_name(&op->op, "RetrAL1"); spin_lock(&cookie->lock); @@ -475,18 +623,22 @@ int __fscache_alloc_page(struct fscache_cookie *cookie, fscache_stat(&fscache_n_alloc_ops); - if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) { - _debug(">>> WT"); - fscache_stat(&fscache_n_alloc_op_waits); - wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING, - fscache_wait_bit, TASK_UNINTERRUPTIBLE); - _debug("<<< GO"); - } + ret = fscache_wait_for_retrieval_activation( + object, op, + __fscache_stat(&fscache_n_alloc_op_waits), + __fscache_stat(&fscache_n_allocs_object_dead)); + if (ret < 0) + goto error; /* ask the cache to honour the operation */ + fscache_stat(&fscache_n_cop_allocate_page); ret = object->cache->ops->allocate_page(op, page, gfp); + fscache_stat_d(&fscache_n_cop_allocate_page); - if (ret < 0) +error: + if (ret == -ERESTARTSYS) + fscache_stat(&fscache_n_allocs_intr); + else if (ret < 0) fscache_stat(&fscache_n_allocs_nobufs); else fscache_stat(&fscache_n_allocs_ok); @@ -521,7 +673,7 @@ static void fscache_write_op(struct fscache_operation *_op) struct fscache_storage *op = container_of(_op, struct fscache_storage, op); struct fscache_object *object = op->op.object; - struct fscache_cookie *cookie = object->cookie; + struct fscache_cookie *cookie; struct page *page; unsigned n; void *results[1]; @@ -529,16 +681,19 @@ static void fscache_write_op(struct fscache_operation *_op) _enter("{OP%x,%d}", op->op.debug_id, atomic_read(&op->op.usage)); - spin_lock(&cookie->lock); + fscache_set_op_state(&op->op, "GetPage"); + spin_lock(&object->lock); + cookie = object->cookie; - if (!fscache_object_is_active(object)) { + if (!fscache_object_is_active(object) || !cookie) { spin_unlock(&object->lock); - spin_unlock(&cookie->lock); _leave(""); return; } + spin_lock(&cookie->stores_lock); + fscache_stat(&fscache_n_store_calls); /* find a page to store */ @@ -549,23 +704,35 @@ static void fscache_write_op(struct fscache_operation *_op) goto superseded; page = results[0]; _debug("gang %d [%lx]", n, page->index); - if (page->index > op->store_limit) + if (page->index > op->store_limit) { + fscache_stat(&fscache_n_store_pages_over_limit); goto superseded; + } - radix_tree_tag_clear(&cookie->stores, page->index, - FSCACHE_COOKIE_PENDING_TAG); + if (page) { + radix_tree_tag_set(&cookie->stores, page->index, + FSCACHE_COOKIE_STORING_TAG); + radix_tree_tag_clear(&cookie->stores, page->index, + FSCACHE_COOKIE_PENDING_TAG); + } + spin_unlock(&cookie->stores_lock); spin_unlock(&object->lock); - spin_unlock(&cookie->lock); if (page) { + fscache_set_op_state(&op->op, "Store"); + fscache_stat(&fscache_n_store_pages); + fscache_stat(&fscache_n_cop_write_page); ret = object->cache->ops->write_page(op, page); - fscache_end_page_write(cookie, page); - page_cache_release(page); - if (ret < 0) + fscache_stat_d(&fscache_n_cop_write_page); + fscache_set_op_state(&op->op, "EndWrite"); + fscache_end_page_write(object, page); + if (ret < 0) { + fscache_set_op_state(&op->op, "Abort"); fscache_abort_object(object); - else + } else { fscache_enqueue_operation(&op->op); + } } _leave(""); @@ -575,9 +742,9 @@ superseded: /* this writer is going away and there aren't any more things to * write */ _debug("cease"); + spin_unlock(&cookie->stores_lock); clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags); spin_unlock(&object->lock); - spin_unlock(&cookie->lock); _leave(""); } @@ -634,6 +801,7 @@ int __fscache_write_page(struct fscache_cookie *cookie, fscache_operation_init(&op->op, fscache_release_write_op); fscache_operation_init_slow(&op->op, fscache_write_op); op->op.flags = FSCACHE_OP_SLOW | (1 << FSCACHE_OP_WAITING); + fscache_set_op_name(&op->op, "Write1"); ret = radix_tree_preload(gfp & ~__GFP_HIGHMEM); if (ret < 0) @@ -652,6 +820,7 @@ int __fscache_write_page(struct fscache_cookie *cookie, /* add the page to the pending-storage radix tree on the backing * object */ spin_lock(&object->lock); + spin_lock(&cookie->stores_lock); _debug("store limit %llx", (unsigned long long) object->store_limit); @@ -672,6 +841,7 @@ int __fscache_write_page(struct fscache_cookie *cookie, if (test_and_set_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags)) goto already_pending; + spin_unlock(&cookie->stores_lock); spin_unlock(&object->lock); op->op.debug_id = atomic_inc_return(&fscache_op_debug_id); @@ -693,6 +863,7 @@ int __fscache_write_page(struct fscache_cookie *cookie, already_queued: fscache_stat(&fscache_n_stores_again); already_pending: + spin_unlock(&cookie->stores_lock); spin_unlock(&object->lock); spin_unlock(&cookie->lock); radix_tree_preload_end(); @@ -702,7 +873,9 @@ already_pending: return 0; submit_failed: + spin_lock(&cookie->stores_lock); radix_tree_delete(&cookie->stores, page->index); + spin_unlock(&cookie->stores_lock); page_cache_release(page); ret = -ENOBUFS; goto nobufs; @@ -763,7 +936,9 @@ void __fscache_uncache_page(struct fscache_cookie *cookie, struct page *page) if (TestClearPageFsCache(page) && object->cache->ops->uncache_page) { /* the cache backend releases the cookie lock */ + fscache_stat(&fscache_n_cop_uncache_page); object->cache->ops->uncache_page(object, page); + fscache_stat_d(&fscache_n_cop_uncache_page); goto done; } diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c index beeab44bc31a..1d9e4951a597 100644 --- a/fs/fscache/proc.c +++ b/fs/fscache/proc.c @@ -37,10 +37,20 @@ int __init fscache_proc_init(void) goto error_histogram; #endif +#ifdef CONFIG_FSCACHE_OBJECT_LIST + if (!proc_create("fs/fscache/objects", S_IFREG | 0444, NULL, + &fscache_objlist_fops)) + goto error_objects; +#endif + _leave(" = 0"); return 0; +#ifdef CONFIG_FSCACHE_OBJECT_LIST +error_objects: +#endif #ifdef CONFIG_FSCACHE_HISTOGRAM + remove_proc_entry("fs/fscache/histogram", NULL); error_histogram: #endif #ifdef CONFIG_FSCACHE_STATS @@ -58,6 +68,9 @@ error_dir: */ void fscache_proc_cleanup(void) { +#ifdef CONFIG_FSCACHE_OBJECT_LIST + remove_proc_entry("fs/fscache/objects", NULL); +#endif #ifdef CONFIG_FSCACHE_HISTOGRAM remove_proc_entry("fs/fscache/histogram", NULL); #endif diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index 65deb99e756b..46435f3aae68 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -25,6 +25,8 @@ atomic_t fscache_n_op_requeue; atomic_t fscache_n_op_deferred_release; atomic_t fscache_n_op_release; atomic_t fscache_n_op_gc; +atomic_t fscache_n_op_cancelled; +atomic_t fscache_n_op_rejected; atomic_t fscache_n_attr_changed; atomic_t fscache_n_attr_changed_ok; @@ -36,6 +38,8 @@ atomic_t fscache_n_allocs; atomic_t fscache_n_allocs_ok; atomic_t fscache_n_allocs_wait; atomic_t fscache_n_allocs_nobufs; +atomic_t fscache_n_allocs_intr; +atomic_t fscache_n_allocs_object_dead; atomic_t fscache_n_alloc_ops; atomic_t fscache_n_alloc_op_waits; @@ -46,6 +50,7 @@ atomic_t fscache_n_retrievals_nodata; atomic_t fscache_n_retrievals_nobufs; atomic_t fscache_n_retrievals_intr; atomic_t fscache_n_retrievals_nomem; +atomic_t fscache_n_retrievals_object_dead; atomic_t fscache_n_retrieval_ops; atomic_t fscache_n_retrieval_op_waits; @@ -56,6 +61,14 @@ atomic_t fscache_n_stores_nobufs; atomic_t fscache_n_stores_oom; atomic_t fscache_n_store_ops; atomic_t fscache_n_store_calls; +atomic_t fscache_n_store_pages; +atomic_t fscache_n_store_radix_deletes; +atomic_t fscache_n_store_pages_over_limit; + +atomic_t fscache_n_store_vmscan_not_storing; +atomic_t fscache_n_store_vmscan_gone; +atomic_t fscache_n_store_vmscan_busy; +atomic_t fscache_n_store_vmscan_cancelled; atomic_t fscache_n_marks; atomic_t fscache_n_uncaches; @@ -74,6 +87,7 @@ atomic_t fscache_n_updates_run; atomic_t fscache_n_relinquishes; atomic_t fscache_n_relinquishes_null; atomic_t fscache_n_relinquishes_waitcrt; +atomic_t fscache_n_relinquishes_retire; atomic_t fscache_n_cookie_index; atomic_t fscache_n_cookie_data; @@ -84,6 +98,7 @@ atomic_t fscache_n_object_no_alloc; atomic_t fscache_n_object_lookups; atomic_t fscache_n_object_lookups_negative; atomic_t fscache_n_object_lookups_positive; +atomic_t fscache_n_object_lookups_timed_out; atomic_t fscache_n_object_created; atomic_t fscache_n_object_avail; atomic_t fscache_n_object_dead; @@ -93,6 +108,23 @@ atomic_t fscache_n_checkaux_okay; atomic_t fscache_n_checkaux_update; atomic_t fscache_n_checkaux_obsolete; +atomic_t fscache_n_cop_alloc_object; +atomic_t fscache_n_cop_lookup_object; +atomic_t fscache_n_cop_lookup_complete; +atomic_t fscache_n_cop_grab_object; +atomic_t fscache_n_cop_update_object; +atomic_t fscache_n_cop_drop_object; +atomic_t fscache_n_cop_put_object; +atomic_t fscache_n_cop_sync_cache; +atomic_t fscache_n_cop_attr_changed; +atomic_t fscache_n_cop_read_or_alloc_page; +atomic_t fscache_n_cop_read_or_alloc_pages; +atomic_t fscache_n_cop_allocate_page; +atomic_t fscache_n_cop_allocate_pages; +atomic_t fscache_n_cop_write_page; +atomic_t fscache_n_cop_uncache_page; +atomic_t fscache_n_cop_dissociate_pages; + /* * display the general statistics */ @@ -129,10 +161,11 @@ static int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_acquires_nobufs), atomic_read(&fscache_n_acquires_oom)); - seq_printf(m, "Lookups: n=%u neg=%u pos=%u crt=%u\n", + seq_printf(m, "Lookups: n=%u neg=%u pos=%u crt=%u tmo=%u\n", atomic_read(&fscache_n_object_lookups), atomic_read(&fscache_n_object_lookups_negative), atomic_read(&fscache_n_object_lookups_positive), + atomic_read(&fscache_n_object_lookups_timed_out), atomic_read(&fscache_n_object_created)); seq_printf(m, "Updates: n=%u nul=%u run=%u\n", @@ -140,10 +173,11 @@ static int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_updates_null), atomic_read(&fscache_n_updates_run)); - seq_printf(m, "Relinqs: n=%u nul=%u wcr=%u\n", + seq_printf(m, "Relinqs: n=%u nul=%u wcr=%u rtr=%u\n", atomic_read(&fscache_n_relinquishes), atomic_read(&fscache_n_relinquishes_null), - atomic_read(&fscache_n_relinquishes_waitcrt)); + atomic_read(&fscache_n_relinquishes_waitcrt), + atomic_read(&fscache_n_relinquishes_retire)); seq_printf(m, "AttrChg: n=%u ok=%u nbf=%u oom=%u run=%u\n", atomic_read(&fscache_n_attr_changed), @@ -152,14 +186,16 @@ static int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_attr_changed_nomem), atomic_read(&fscache_n_attr_changed_calls)); - seq_printf(m, "Allocs : n=%u ok=%u wt=%u nbf=%u\n", + seq_printf(m, "Allocs : n=%u ok=%u wt=%u nbf=%u int=%u\n", atomic_read(&fscache_n_allocs), atomic_read(&fscache_n_allocs_ok), atomic_read(&fscache_n_allocs_wait), - atomic_read(&fscache_n_allocs_nobufs)); - seq_printf(m, "Allocs : ops=%u owt=%u\n", + atomic_read(&fscache_n_allocs_nobufs), + atomic_read(&fscache_n_allocs_intr)); + seq_printf(m, "Allocs : ops=%u owt=%u abt=%u\n", atomic_read(&fscache_n_alloc_ops), - atomic_read(&fscache_n_alloc_op_waits)); + atomic_read(&fscache_n_alloc_op_waits), + atomic_read(&fscache_n_allocs_object_dead)); seq_printf(m, "Retrvls: n=%u ok=%u wt=%u nod=%u nbf=%u" " int=%u oom=%u\n", @@ -170,9 +206,10 @@ static int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_retrievals_nobufs), atomic_read(&fscache_n_retrievals_intr), atomic_read(&fscache_n_retrievals_nomem)); - seq_printf(m, "Retrvls: ops=%u owt=%u\n", + seq_printf(m, "Retrvls: ops=%u owt=%u abt=%u\n", atomic_read(&fscache_n_retrieval_ops), - atomic_read(&fscache_n_retrieval_op_waits)); + atomic_read(&fscache_n_retrieval_op_waits), + atomic_read(&fscache_n_retrievals_object_dead)); seq_printf(m, "Stores : n=%u ok=%u agn=%u nbf=%u oom=%u\n", atomic_read(&fscache_n_stores), @@ -180,18 +217,49 @@ static int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_stores_again), atomic_read(&fscache_n_stores_nobufs), atomic_read(&fscache_n_stores_oom)); - seq_printf(m, "Stores : ops=%u run=%u\n", + seq_printf(m, "Stores : ops=%u run=%u pgs=%u rxd=%u olm=%u\n", atomic_read(&fscache_n_store_ops), - atomic_read(&fscache_n_store_calls)); + atomic_read(&fscache_n_store_calls), + atomic_read(&fscache_n_store_pages), + atomic_read(&fscache_n_store_radix_deletes), + atomic_read(&fscache_n_store_pages_over_limit)); - seq_printf(m, "Ops : pend=%u run=%u enq=%u\n", + seq_printf(m, "VmScan : nos=%u gon=%u bsy=%u can=%u\n", + atomic_read(&fscache_n_store_vmscan_not_storing), + atomic_read(&fscache_n_store_vmscan_gone), + atomic_read(&fscache_n_store_vmscan_busy), + atomic_read(&fscache_n_store_vmscan_cancelled)); + + seq_printf(m, "Ops : pend=%u run=%u enq=%u can=%u rej=%u\n", atomic_read(&fscache_n_op_pend), atomic_read(&fscache_n_op_run), - atomic_read(&fscache_n_op_enqueue)); + atomic_read(&fscache_n_op_enqueue), + atomic_read(&fscache_n_op_cancelled), + atomic_read(&fscache_n_op_rejected)); seq_printf(m, "Ops : dfr=%u rel=%u gc=%u\n", atomic_read(&fscache_n_op_deferred_release), atomic_read(&fscache_n_op_release), atomic_read(&fscache_n_op_gc)); + + seq_printf(m, "CacheOp: alo=%d luo=%d luc=%d gro=%d\n", + atomic_read(&fscache_n_cop_alloc_object), + atomic_read(&fscache_n_cop_lookup_object), + atomic_read(&fscache_n_cop_lookup_complete), + atomic_read(&fscache_n_cop_grab_object)); + seq_printf(m, "CacheOp: upo=%d dro=%d pto=%d atc=%d syn=%d\n", + atomic_read(&fscache_n_cop_update_object), + atomic_read(&fscache_n_cop_drop_object), + atomic_read(&fscache_n_cop_put_object), + atomic_read(&fscache_n_cop_attr_changed), + atomic_read(&fscache_n_cop_sync_cache)); + seq_printf(m, "CacheOp: rap=%d ras=%d alp=%d als=%d wrp=%d ucp=%d dsp=%d\n", + atomic_read(&fscache_n_cop_read_or_alloc_page), + atomic_read(&fscache_n_cop_read_or_alloc_pages), + atomic_read(&fscache_n_cop_allocate_page), + atomic_read(&fscache_n_cop_allocate_pages), + atomic_read(&fscache_n_cop_write_page), + atomic_read(&fscache_n_cop_uncache_page), + atomic_read(&fscache_n_cop_dissociate_pages)); return 0; } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 8ada78aade58..4787ae6c5c1c 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -385,6 +385,9 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, if (fc->no_create) return -ENOSYS; + if (flags & O_DIRECT) + return -EINVAL; + forget_req = fuse_get_req(fc); if (IS_ERR(forget_req)) return PTR_ERR(forget_req); diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index eacd78a5d082..5b31f7741a8f 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -114,7 +114,7 @@ static int __init init_gfs2_fs(void) if (error) goto fail_unregister; - error = slow_work_register_user(); + error = slow_work_register_user(THIS_MODULE); if (error) goto fail_slow; @@ -163,7 +163,7 @@ static void __exit exit_gfs2_fs(void) gfs2_unregister_debugfs(); unregister_filesystem(&gfs2_fs_type); unregister_filesystem(&gfs2meta_fs_type); - slow_work_unregister_user(); + slow_work_unregister_user(THIS_MODULE); kmem_cache_destroy(gfs2_quotad_cachep); kmem_cache_destroy(gfs2_rgrpd_cachep); diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 59d2695509d3..09fa31965576 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -7,6 +7,7 @@ * of the GNU General Public License version 2. */ +#include <linux/module.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/completion.h> @@ -593,6 +594,7 @@ fail: } struct slow_work_ops gfs2_recover_ops = { + .owner = THIS_MODULE, .get_ref = gfs2_recover_get_ref, .put_ref = gfs2_recover_put_ref, .execute = gfs2_recover_work, diff --git a/fs/jffs2/read.c b/fs/jffs2/read.c index cfe05c1966a5..3f39be1b0455 100644 --- a/fs/jffs2/read.c +++ b/fs/jffs2/read.c @@ -164,12 +164,15 @@ int jffs2_read_inode_range(struct jffs2_sb_info *c, struct jffs2_inode_info *f, /* XXX FIXME: Where a single physical node actually shows up in two frags, we read it twice. Don't do that. */ - /* Now we're pointing at the first frag which overlaps our page */ + /* Now we're pointing at the first frag which overlaps our page + * (or perhaps is before it, if we've been asked to read off the + * end of the file). */ while(offset < end) { D2(printk(KERN_DEBUG "jffs2_read_inode_range: offset %d, end %d\n", offset, end)); - if (unlikely(!frag || frag->ofs > offset)) { + if (unlikely(!frag || frag->ofs > offset || + frag->ofs + frag->size <= offset)) { uint32_t holesize = end - offset; - if (frag) { + if (frag && frag->ofs > offset) { D1(printk(KERN_NOTICE "Eep. Hole in ino #%u fraglist. frag->ofs = 0x%08x, offset = 0x%08x\n", f->inocache->ino, frag->ofs, offset)); holesize = min(holesize, frag->ofs - offset); } diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 70fad69eb959..fa588006588d 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -359,17 +359,13 @@ int nfs_fscache_release_page(struct page *page, gfp_t gfp) BUG_ON(!cookie); - if (fscache_check_page_write(cookie, page)) { - if (!(gfp & __GFP_WAIT)) - return 0; - fscache_wait_on_page_write(cookie, page); - } - if (PageFsCache(page)) { dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n", cookie, page, nfsi); - fscache_uncache_page(cookie, page); + if (!fscache_maybe_release_page(cookie, page, gfp)) + return 0; + nfs_add_fscache_stats(page->mapping->host, NFSIOS_FSCACHE_PAGES_UNCACHED, 1); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ff37454fa783..741a562177fc 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2767,7 +2767,7 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, .pages = &page, .pgbase = 0, .count = count, - .bitmask = NFS_SERVER(dentry->d_inode)->cache_consistency_bitmask, + .bitmask = NFS_SERVER(dentry->d_inode)->attr_bitmask, }; struct nfs4_readdir_res res; struct rpc_message msg = { diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 89fc8ee1f5a5..de059f490586 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1712,7 +1712,8 @@ int ocfs2_check_range_for_refcount(struct inode *inode, loff_t pos, struct super_block *sb = inode->i_sb; if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb)) || - !(OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL)) + !(OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL) || + OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) return 0; cpos = pos >> OCFS2_SB(sb)->s_clustersize_bits; diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index eae404602424..d963d8638709 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -35,12 +35,7 @@ #include <linux/kref.h> #include <linux/mutex.h> #include <linux/lockdep.h> -#ifndef CONFIG_OCFS2_COMPAT_JBD -# include <linux/jbd2.h> -#else -# include <linux/jbd.h> -# include "ocfs2_jbd_compat.h" -#endif +#include <linux/jbd2.h> /* For union ocfs2_dlm_lksb */ #include "stackglue.h" diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 60287fc56bcb..3a0df7a1b810 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -3743,6 +3743,9 @@ static int ocfs2_attach_refcount_tree(struct inode *inode, goto out; } + if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) + goto attach_xattr; + ocfs2_init_dinode_extent_tree(&di_et, INODE_CACHE(inode), di_bh); size = i_size_read(inode); @@ -3769,6 +3772,7 @@ static int ocfs2_attach_refcount_tree(struct inode *inode, cpos += num_clusters; } +attach_xattr: if (oi->ip_dyn_features & OCFS2_HAS_XATTR_FL) { ret = ocfs2_xattr_attach_refcount_tree(inode, di_bh, &ref_tree->rf_ci, @@ -3858,6 +3862,49 @@ out: return ret; } +static int ocfs2_duplicate_inline_data(struct inode *s_inode, + struct buffer_head *s_bh, + struct inode *t_inode, + struct buffer_head *t_bh) +{ + int ret; + handle_t *handle; + struct ocfs2_super *osb = OCFS2_SB(s_inode->i_sb); + struct ocfs2_dinode *s_di = (struct ocfs2_dinode *)s_bh->b_data; + struct ocfs2_dinode *t_di = (struct ocfs2_dinode *)t_bh->b_data; + + BUG_ON(!(OCFS2_I(s_inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)); + + handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + mlog_errno(ret); + goto out; + } + + ret = ocfs2_journal_access_di(handle, INODE_CACHE(t_inode), t_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + t_di->id2.i_data.id_count = s_di->id2.i_data.id_count; + memcpy(t_di->id2.i_data.id_data, s_di->id2.i_data.id_data, + le16_to_cpu(s_di->id2.i_data.id_count)); + spin_lock(&OCFS2_I(t_inode)->ip_lock); + OCFS2_I(t_inode)->ip_dyn_features |= OCFS2_INLINE_DATA_FL; + t_di->i_dyn_features = cpu_to_le16(OCFS2_I(t_inode)->ip_dyn_features); + spin_unlock(&OCFS2_I(t_inode)->ip_lock); + + ocfs2_journal_dirty(handle, t_bh); + +out_commit: + ocfs2_commit_trans(osb, handle); +out: + return ret; +} + static int ocfs2_duplicate_extent_list(struct inode *s_inode, struct inode *t_inode, struct buffer_head *t_bh, @@ -3997,6 +4044,14 @@ static int ocfs2_create_reflink_node(struct inode *s_inode, goto out; } + if (OCFS2_I(s_inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + ret = ocfs2_duplicate_inline_data(s_inode, s_bh, + t_inode, t_bh); + if (ret) + mlog_errno(ret); + goto out; + } + ret = ocfs2_lock_refcount_tree(osb, le64_to_cpu(di->i_refcount_loc), 1, &ref_tree, &ref_root_bh); if (ret) { @@ -4013,10 +4068,6 @@ static int ocfs2_create_reflink_node(struct inode *s_inode, goto out_unlock_refcount; } - ret = ocfs2_complete_reflink(s_inode, s_bh, t_inode, t_bh, preserve); - if (ret) - mlog_errno(ret); - out_unlock_refcount: ocfs2_unlock_refcount_tree(osb, ref_tree, 1); brelse(ref_root_bh); @@ -4068,9 +4119,17 @@ static int __ocfs2_reflink(struct dentry *old_dentry, ret = ocfs2_reflink_xattrs(inode, old_bh, new_inode, new_bh, preserve); - if (ret) + if (ret) { mlog_errno(ret); + goto inode_unlock; + } } + + ret = ocfs2_complete_reflink(inode, old_bh, + new_inode, new_bh, preserve); + if (ret) + mlog_errno(ret); + inode_unlock: ocfs2_inode_unlock(new_inode, 1); brelse(new_bh); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index c0e48aeebb1c..14f47d2bfe02 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -773,18 +773,20 @@ static int ocfs2_sb_probe(struct super_block *sb, if (tmpstat < 0) { status = tmpstat; mlog_errno(status); - goto bail; + break; } di = (struct ocfs2_dinode *) (*bh)->b_data; memset(stats, 0, sizeof(struct ocfs2_blockcheck_stats)); spin_lock_init(&stats->b_lock); - status = ocfs2_verify_volume(di, *bh, blksize, stats); - if (status >= 0) - goto bail; - brelse(*bh); - *bh = NULL; - if (status != -EAGAIN) + tmpstat = ocfs2_verify_volume(di, *bh, blksize, stats); + if (tmpstat < 0) { + brelse(*bh); + *bh = NULL; + } + if (tmpstat != -EAGAIN) { + status = tmpstat; break; + } } bail: @@ -1645,6 +1647,10 @@ static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bavail = buf->f_bfree; buf->f_files = numbits; buf->f_ffree = freebits; + buf->f_fsid.val[0] = crc32_le(0, osb->uuid_str, OCFS2_VOL_UUID_LEN) + & 0xFFFFFFFFUL; + buf->f_fsid.val[1] = crc32_le(0, osb->uuid_str + OCFS2_VOL_UUID_LEN, + OCFS2_VOL_UUID_LEN) & 0xFFFFFFFFUL; brelse(bh); diff --git a/fs/ocfs2/uptodate.c b/fs/ocfs2/uptodate.c index b6284f235d2f..c61369342a27 100644 --- a/fs/ocfs2/uptodate.c +++ b/fs/ocfs2/uptodate.c @@ -53,11 +53,6 @@ #include <linux/highmem.h> #include <linux/buffer_head.h> #include <linux/rbtree.h> -#ifndef CONFIG_OCFS2_COMPAT_JBD -# include <linux/jbd2.h> -#else -# include <linux/jbd.h> -#endif #define MLOG_MASK_PREFIX ML_UPTODATE diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h index c118b2ad9807..ec78a4bbe1d5 100644 --- a/include/linux/cryptohash.h +++ b/include/linux/cryptohash.h @@ -2,6 +2,7 @@ #define __CRYPTOHASH_H #define SHA_DIGEST_WORDS 5 +#define SHA_MESSAGE_BYTES (512 /*bits*/ / 8) #define SHA_WORKSPACE_WORDS 80 void sha_init(__u32 *buf); diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index edd03b79e8f8..ef4a2d84d922 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -49,13 +49,14 @@ static inline __u32 ethtool_cmd_speed(struct ethtool_cmd *ep) return (ep->speed_hi << 16) | ep->speed; } +#define ETHTOOL_FWVERS_LEN 32 #define ETHTOOL_BUSINFO_LEN 32 /* these strings are set to whatever the driver author decides... */ struct ethtool_drvinfo { __u32 cmd; char driver[32]; /* driver short name, "tulip", "eepro100" */ char version[32]; /* driver version string */ - char fw_version[32]; /* firmware version string, if applicable */ + char fw_version[ETHTOOL_FWVERS_LEN]; /* firmware version string */ char bus_info[ETHTOOL_BUSINFO_LEN]; /* Bus info for this IF. */ /* For PCI devices, use pci_name(pci_dev). */ char reserved1[32]; @@ -631,6 +632,8 @@ struct ethtool_ops { #define PORT_MII 0x02 #define PORT_FIBRE 0x03 #define PORT_BNC 0x04 +#define PORT_DA 0x05 +#define PORT_NONE 0xef #define PORT_OTHER 0xff /* Which transceiver to use. */ diff --git a/include/linux/fib_rules.h b/include/linux/fib_rules.h index c7e5b700bb91..51da65b68b85 100644 --- a/include/linux/fib_rules.h +++ b/include/linux/fib_rules.h @@ -8,7 +8,9 @@ #define FIB_RULE_PERMANENT 0x00000001 #define FIB_RULE_INVERT 0x00000002 #define FIB_RULE_UNRESOLVED 0x00000004 -#define FIB_RULE_DEV_DETACHED 0x00000008 +#define FIB_RULE_IIF_DETACHED 0x00000008 +#define FIB_RULE_DEV_DETACHED FIB_RULE_IIF_DETACHED +#define FIB_RULE_OIF_DETACHED 0x00000010 /* try to find source address in routing lookups */ #define FIB_RULE_FIND_SADDR 0x00010000 @@ -31,7 +33,8 @@ enum { FRA_UNSPEC, FRA_DST, /* destination address */ FRA_SRC, /* source address */ - FRA_IFNAME, /* interface name */ + FRA_IIFNAME, /* interface name */ +#define FRA_IFNAME FRA_IIFNAME FRA_GOTO, /* target to jump to (FR_ACT_GOTO) */ FRA_UNUSED2, FRA_PRIORITY, /* priority/preference */ @@ -45,6 +48,7 @@ enum { FRA_UNUSED8, FRA_TABLE, /* Extended table id */ FRA_FWMASK, /* mask for netfilter mark */ + FRA_OIFNAME, __FRA_MAX }; diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 84d3532dd3ea..7be0c6fbe880 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -91,6 +91,8 @@ struct fscache_operation { #define FSCACHE_OP_WAITING 4 /* cleared when op is woken */ #define FSCACHE_OP_EXCLUSIVE 5 /* exclusive op, other ops must wait */ #define FSCACHE_OP_DEAD 6 /* op is now dead */ +#define FSCACHE_OP_DEC_READ_CNT 7 /* decrement object->n_reads on destruction */ +#define FSCACHE_OP_KEEP_FLAGS 0xc0 /* flags to keep when repurposing an op */ atomic_t usage; unsigned debug_id; /* debugging ID */ @@ -102,6 +104,16 @@ struct fscache_operation { /* operation releaser */ fscache_operation_release_t release; + +#ifdef CONFIG_SLOW_WORK_PROC + const char *name; /* operation name */ + const char *state; /* operation state */ +#define fscache_set_op_name(OP, N) do { (OP)->name = (N); } while(0) +#define fscache_set_op_state(OP, S) do { (OP)->state = (S); } while(0) +#else +#define fscache_set_op_name(OP, N) do { } while(0) +#define fscache_set_op_state(OP, S) do { } while(0) +#endif }; extern atomic_t fscache_op_debug_id; @@ -125,6 +137,7 @@ static inline void fscache_operation_init(struct fscache_operation *op, op->debug_id = atomic_inc_return(&fscache_op_debug_id); op->release = release; INIT_LIST_HEAD(&op->pend_link); + fscache_set_op_state(op, "Init"); } /** @@ -221,8 +234,10 @@ struct fscache_cache_ops { struct fscache_object *(*alloc_object)(struct fscache_cache *cache, struct fscache_cookie *cookie); - /* look up the object for a cookie */ - void (*lookup_object)(struct fscache_object *object); + /* look up the object for a cookie + * - return -ETIMEDOUT to be requeued + */ + int (*lookup_object)(struct fscache_object *object); /* finished looking up */ void (*lookup_complete)(struct fscache_object *object); @@ -297,12 +312,14 @@ struct fscache_cookie { atomic_t usage; /* number of users of this cookie */ atomic_t n_children; /* number of children of this cookie */ spinlock_t lock; + spinlock_t stores_lock; /* lock on page store tree */ struct hlist_head backing_objects; /* object(s) backing this file/index */ const struct fscache_cookie_def *def; /* definition */ struct fscache_cookie *parent; /* parent of this entry */ void *netfs_data; /* back pointer to netfs */ struct radix_tree_root stores; /* pages to be stored on this cookie */ #define FSCACHE_COOKIE_PENDING_TAG 0 /* pages tag: pending write to cache */ +#define FSCACHE_COOKIE_STORING_TAG 1 /* pages tag: writing to cache */ unsigned long flags; #define FSCACHE_COOKIE_LOOKING_UP 0 /* T if non-index cookie being looked up still */ @@ -337,6 +354,7 @@ struct fscache_object { FSCACHE_OBJECT_RECYCLING, /* retiring object */ FSCACHE_OBJECT_WITHDRAWING, /* withdrawing object */ FSCACHE_OBJECT_DEAD, /* object is now dead */ + FSCACHE_OBJECT__NSTATES } state; int debug_id; /* debugging ID */ @@ -345,6 +363,7 @@ struct fscache_object { int n_obj_ops; /* number of object ops outstanding on object */ int n_in_progress; /* number of ops in progress */ int n_exclusive; /* number of exclusive ops queued */ + atomic_t n_reads; /* number of read ops in progress */ spinlock_t lock; /* state and operations lock */ unsigned long lookup_jif; /* time at which lookup started */ @@ -358,6 +377,7 @@ struct fscache_object { #define FSCACHE_OBJECT_EV_RELEASE 4 /* T if netfs requested object release */ #define FSCACHE_OBJECT_EV_RETIRE 5 /* T if netfs requested object retirement */ #define FSCACHE_OBJECT_EV_WITHDRAW 6 /* T if cache requested object withdrawal */ +#define FSCACHE_OBJECT_EVENTS_MASK 0x7f /* mask of all events*/ unsigned long flags; #define FSCACHE_OBJECT_LOCK 0 /* T if object is busy being processed */ @@ -373,7 +393,11 @@ struct fscache_object { struct list_head dependents; /* FIFO of dependent objects */ struct list_head dep_link; /* link in parent's dependents list */ struct list_head pending_ops; /* unstarted operations on this object */ +#ifdef CONFIG_FSCACHE_OBJECT_LIST + struct rb_node objlist_link; /* link in global object list */ +#endif pgoff_t store_limit; /* current storage limit */ + loff_t store_limit_l; /* current storage limit */ }; extern const char *fscache_object_states[]; @@ -383,6 +407,10 @@ extern const char *fscache_object_states[]; (obj)->state >= FSCACHE_OBJECT_AVAILABLE && \ (obj)->state < FSCACHE_OBJECT_DYING) +#define fscache_object_is_dead(obj) \ + (test_bit(FSCACHE_IOERROR, &(obj)->cache->flags) && \ + (obj)->state >= FSCACHE_OBJECT_DYING) + extern const struct slow_work_ops fscache_object_slow_work_ops; /** @@ -414,6 +442,7 @@ void fscache_object_init(struct fscache_object *object, object->events = object->event_mask = 0; object->flags = 0; object->store_limit = 0; + object->store_limit_l = 0; object->cache = cache; object->cookie = cookie; object->parent = NULL; @@ -422,6 +451,12 @@ void fscache_object_init(struct fscache_object *object, extern void fscache_object_lookup_negative(struct fscache_object *object); extern void fscache_obtained_object(struct fscache_object *object); +#ifdef CONFIG_FSCACHE_OBJECT_LIST +extern void fscache_object_destroy(struct fscache_object *object); +#else +#define fscache_object_destroy(object) do {} while(0) +#endif + /** * fscache_object_destroyed - Note destruction of an object in a cache * @cache: The cache from which the object came @@ -460,6 +495,7 @@ static inline void fscache_object_lookup_error(struct fscache_object *object) static inline void fscache_set_store_limit(struct fscache_object *object, loff_t i_size) { + object->store_limit_l = i_size; object->store_limit = i_size >> PAGE_SHIFT; if (i_size & ~PAGE_MASK) object->store_limit++; diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 6d8ee466e0a0..595ce49288b7 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -202,6 +202,8 @@ extern int __fscache_write_page(struct fscache_cookie *, struct page *, gfp_t); extern void __fscache_uncache_page(struct fscache_cookie *, struct page *); extern bool __fscache_check_page_write(struct fscache_cookie *, struct page *); extern void __fscache_wait_on_page_write(struct fscache_cookie *, struct page *); +extern bool __fscache_maybe_release_page(struct fscache_cookie *, struct page *, + gfp_t); /** * fscache_register_netfs - Register a filesystem as desiring caching services @@ -615,4 +617,29 @@ void fscache_wait_on_page_write(struct fscache_cookie *cookie, __fscache_wait_on_page_write(cookie, page); } +/** + * fscache_maybe_release_page - Consider releasing a page, cancelling a store + * @cookie: The cookie representing the cache object + * @page: The netfs page that is being cached. + * @gfp: The gfp flags passed to releasepage() + * + * Consider releasing a page for the vmscan algorithm, on behalf of the netfs's + * releasepage() call. A storage request on the page may cancelled if it is + * not currently being processed. + * + * The function returns true if the page no longer has a storage request on it, + * and false if a storage request is left in place. If true is returned, the + * page will have been passed to fscache_uncache_page(). If false is returned + * the page cannot be freed yet. + */ +static inline +bool fscache_maybe_release_page(struct fscache_cookie *cookie, + struct page *page, + gfp_t gfp) +{ + if (fscache_cookie_valid(cookie) && PageFsCache(page)) + return __fscache_maybe_release_page(cookie, page, gfp); + return false; +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/linux/i2c-pnx.h b/include/linux/i2c-pnx.h index f13255e06406..9eb07bbc6522 100644 --- a/include/linux/i2c-pnx.h +++ b/include/linux/i2c-pnx.h @@ -21,7 +21,7 @@ struct i2c_pnx_mif { int mode; /* Interface mode */ struct completion complete; /* I/O completion */ struct timer_list timer; /* Timeout */ - char * buf; /* Data buffer */ + u8 * buf; /* Data buffer */ int len; /* Length of data buffer */ }; diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 1d3b2425f661..6674791622ca 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -181,4 +181,19 @@ struct ifla_vlan_qos_mapping { __u32 to; }; +/* MACVLAN section */ +enum { + IFLA_MACVLAN_UNSPEC, + IFLA_MACVLAN_MODE, + __IFLA_MACVLAN_MAX, +}; + +#define IFLA_MACVLAN_MAX (__IFLA_MACVLAN_MAX - 1) + +enum macvlan_mode { + MACVLAN_MODE_PRIVATE = 1, /* don't talk to other macvlans */ + MACVLAN_MODE_VEPA = 2, /* talk to other ports through ext bridge */ + MACVLAN_MODE_BRIDGE = 4, /* talk to bridge ports directly */ +}; + #endif /* _LINUX_IF_LINK_H */ diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 153f6b9e722c..3d870fda8c4f 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -339,6 +339,7 @@ enum vlan_ioctl_cmds { enum vlan_flags { VLAN_FLAG_REORDER_HDR = 0x1, VLAN_FLAG_GVRP = 0x2, + VLAN_FLAG_LOOSE_BINDING = 0x4, }; enum vlan_name_types { diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index eecfa559bfb4..699e85c01a4d 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -83,6 +83,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ ACCEPT_SOURCE_ROUTE) +#define IN_DEV_ACCEPT_LOCAL(in_dev) IN_DEV_ORCONF((in_dev), ACCEPT_LOCAL) #define IN_DEV_BOOTP_RELAY(in_dev) IN_DEV_ANDCONF((in_dev), BOOTP_RELAY) #define IN_DEV_LOG_MARTIANS(in_dev) IN_DEV_ORCONF((in_dev), LOG_MARTIANS) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 97873e31661c..a3fccc85b1a0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1112,6 +1112,8 @@ extern rwlock_t dev_base_lock; /* Device list lock */ #define for_each_netdev(net, d) \ list_for_each_entry(d, &(net)->dev_base_head, dev_list) +#define for_each_netdev_reverse(net, d) \ + list_for_each_entry_reverse(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_rcu(net, d) \ list_for_each_entry_rcu(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_safe(net, d, n) \ @@ -1562,6 +1564,8 @@ extern int dev_set_mac_address(struct net_device *, extern int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq); +extern int dev_forward_skb(struct net_device *dev, + struct sk_buff *skb); extern int netdev_budget; @@ -1977,6 +1981,9 @@ unsigned long netdev_increment_features(unsigned long all, unsigned long one, unsigned long mask); unsigned long netdev_fix_features(unsigned long features, const char *name); +void netif_stacked_transfer_operstate(const struct net_device *rootdev, + struct net_device *dev); + static inline int net_gso_ok(int features, int gso_type) { int feature = gso_type << NETIF_F_GSO_SHIFT; diff --git a/include/linux/netfilter/nf_conntrack_tcp.h b/include/linux/netfilter/nf_conntrack_tcp.h index f6d97f64d7a0..6e135f97e59a 100644 --- a/include/linux/netfilter/nf_conntrack_tcp.h +++ b/include/linux/netfilter/nf_conntrack_tcp.h @@ -66,6 +66,9 @@ struct ip_ct_tcp { u_int32_t last_ack; /* Last sequence number seen in opposite dir */ u_int32_t last_end; /* Last seq + len */ u_int16_t last_win; /* Last window advertisement seen in dir */ + /* For SYN packets while we may be out-of-sync */ + u_int8_t last_wscale; /* Last window scaling factor seen */ + u_int8_t last_flags; /* Last flags set */ }; #endif /* __KERNEL__ */ diff --git a/include/linux/notifier.h b/include/linux/notifier.h index b0c3671d463c..fee6c2f68075 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -202,7 +202,7 @@ static inline int notifier_to_errno(int ret) #define NETDEV_BONDING_OLDTYPE 0x000E #define NETDEV_BONDING_NEWTYPE 0x000F #define NETDEV_POST_INIT 0x0010 -#define NETDEV_UNREGISTER_PERNET 0x0011 +#define NETDEV_UNREGISTER_BATCH 0x0011 #define SYS_DOWN 0x0001 /* Notify of system down */ #define SYS_RESTART SYS_DOWN diff --git a/include/linux/sctp.h b/include/linux/sctp.h index b464b9d3d242..c20d3ce673c0 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -242,6 +242,7 @@ enum { SCTP_DATA_FIRST_FRAG = 0x02, SCTP_DATA_NOT_FRAG = 0x03, SCTP_DATA_UNORDERED = 0x04, + SCTP_DATA_SACK_IMM = 0x08, }; enum { SCTP_DATA_FRAG_MASK = 0x03, }; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 89eed8cdd318..ae836fded530 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -416,14 +416,6 @@ struct sk_buff { #include <asm/system.h> -#ifdef CONFIG_HAS_DMA -#include <linux/dma-mapping.h> -extern int skb_dma_map(struct device *dev, struct sk_buff *skb, - enum dma_data_direction dir); -extern void skb_dma_unmap(struct device *dev, struct sk_buff *skb, - enum dma_data_direction dir); -#endif - static inline struct dst_entry *skb_dst(const struct sk_buff *skb) { return (struct dst_entry *)skb->_skb_dst; diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h index b65c8881f07a..13337bf6c3f5 100644 --- a/include/linux/slow-work.h +++ b/include/linux/slow-work.h @@ -17,13 +17,20 @@ #ifdef CONFIG_SLOW_WORK #include <linux/sysctl.h> +#include <linux/timer.h> struct slow_work; +#ifdef CONFIG_SLOW_WORK_DEBUG +struct seq_file; +#endif /* * The operations used to support slow work items */ struct slow_work_ops { + /* owner */ + struct module *owner; + /* get a ref on a work item * - return 0 if successful, -ve if not */ @@ -34,6 +41,11 @@ struct slow_work_ops { /* execute a work item */ void (*execute)(struct slow_work *work); + +#ifdef CONFIG_SLOW_WORK_DEBUG + /* describe a work item for debugfs */ + void (*desc)(struct slow_work *work, struct seq_file *m); +#endif }; /* @@ -42,13 +54,24 @@ struct slow_work_ops { * queued */ struct slow_work { + struct module *owner; /* the owning module */ unsigned long flags; #define SLOW_WORK_PENDING 0 /* item pending (further) execution */ #define SLOW_WORK_EXECUTING 1 /* item currently executing */ #define SLOW_WORK_ENQ_DEFERRED 2 /* item enqueue deferred */ #define SLOW_WORK_VERY_SLOW 3 /* item is very slow */ +#define SLOW_WORK_CANCELLING 4 /* item is being cancelled, don't enqueue */ +#define SLOW_WORK_DELAYED 5 /* item is struct delayed_slow_work with active timer */ const struct slow_work_ops *ops; /* operations table for this item */ struct list_head link; /* link in queue */ +#ifdef CONFIG_SLOW_WORK_DEBUG + struct timespec mark; /* jiffies at which queued or exec begun */ +#endif +}; + +struct delayed_slow_work { + struct slow_work work; + struct timer_list timer; }; /** @@ -67,6 +90,20 @@ static inline void slow_work_init(struct slow_work *work, } /** + * slow_work_init - Initialise a delayed slow work item + * @work: The work item to initialise + * @ops: The operations to use to handle the slow work item + * + * Initialise a delayed slow work item. + */ +static inline void delayed_slow_work_init(struct delayed_slow_work *dwork, + const struct slow_work_ops *ops) +{ + init_timer(&dwork->timer); + slow_work_init(&dwork->work, ops); +} + +/** * vslow_work_init - Initialise a very slow work item * @work: The work item to initialise * @ops: The operations to use to handle the slow work item @@ -83,9 +120,40 @@ static inline void vslow_work_init(struct slow_work *work, INIT_LIST_HEAD(&work->link); } +/** + * slow_work_is_queued - Determine if a slow work item is on the work queue + * work: The work item to test + * + * Determine if the specified slow-work item is on the work queue. This + * returns true if it is actually on the queue. + * + * If the item is executing and has been marked for requeue when execution + * finishes, then false will be returned. + * + * Anyone wishing to wait for completion of execution can wait on the + * SLOW_WORK_EXECUTING bit. + */ +static inline bool slow_work_is_queued(struct slow_work *work) +{ + unsigned long flags = work->flags; + return flags & SLOW_WORK_PENDING && !(flags & SLOW_WORK_EXECUTING); +} + extern int slow_work_enqueue(struct slow_work *work); -extern int slow_work_register_user(void); -extern void slow_work_unregister_user(void); +extern void slow_work_cancel(struct slow_work *work); +extern int slow_work_register_user(struct module *owner); +extern void slow_work_unregister_user(struct module *owner); + +extern int delayed_slow_work_enqueue(struct delayed_slow_work *dwork, + unsigned long delay); + +static inline void delayed_slow_work_cancel(struct delayed_slow_work *dwork) +{ + slow_work_cancel(&dwork->work); +} + +extern bool slow_work_sleep_till_thread_needed(struct slow_work *work, + signed long *_timeout); #ifdef CONFIG_SYSCTL extern ctl_table slow_work_sysctls[]; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 1e4743ee6831..9f047d73a216 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -490,6 +490,7 @@ enum NET_IPV4_CONF_PROMOTE_SECONDARIES=20, NET_IPV4_CONF_ARP_ACCEPT=21, NET_IPV4_CONF_ARP_NOTIFY=22, + NET_IPV4_CONF_ACCEPT_LOCAL=23, __NET_IPV4_CONF_MAX }; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 32d7d77b4a01..7fee8a4df931 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -102,7 +102,9 @@ enum { #define TCP_QUICKACK 12 /* Block/reenable quick acks */ #define TCP_CONGESTION 13 /* Congestion control algorithm */ #define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */ +#define TCP_COOKIE_TRANSACTIONS 15 /* TCP Cookie Transactions */ +/* for TCP_INFO socket option */ #define TCPI_OPT_TIMESTAMPS 1 #define TCPI_OPT_SACK 2 #define TCPI_OPT_WSCALE 4 @@ -174,6 +176,30 @@ struct tcp_md5sig { __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; /* key (binary) */ }; +/* for TCP_COOKIE_TRANSACTIONS (TCPCT) socket option */ +#define TCP_COOKIE_MIN 8 /* 64-bits */ +#define TCP_COOKIE_MAX 16 /* 128-bits */ +#define TCP_COOKIE_PAIR_SIZE (2*TCP_COOKIE_MAX) + +/* Flags for both getsockopt and setsockopt */ +#define TCP_COOKIE_IN_ALWAYS (1 << 0) /* Discard SYN without cookie */ +#define TCP_COOKIE_OUT_NEVER (1 << 1) /* Prohibit outgoing cookies, + * supercedes everything. */ + +/* Flags for getsockopt */ +#define TCP_S_DATA_IN (1 << 2) /* Was data received? */ +#define TCP_S_DATA_OUT (1 << 3) /* Was data sent? */ + +/* TCP_COOKIE_TRANSACTIONS data */ +struct tcp_cookie_transactions { + __u16 tcpct_flags; /* see above */ + __u8 __tcpct_pad1; /* zero */ + __u8 tcpct_cookie_desired; /* bytes */ + __u16 tcpct_s_data_desired; /* bytes of variable data */ + __u16 tcpct_used; /* bytes in value */ + __u8 tcpct_value[TCP_MSS_DEFAULT]; +}; + #ifdef __KERNEL__ #include <linux/skbuff.h> @@ -221,26 +247,38 @@ struct tcp_options_received { sack_ok : 4, /* SACK seen on SYN packet */ snd_wscale : 4, /* Window scaling received from sender */ rcv_wscale : 4; /* Window scaling to send to receiver */ -/* SACKs data */ + u8 cookie_plus:6, /* bytes in authenticator/cookie option */ + cookie_out_never:1, + cookie_in_always:1; u8 num_sacks; /* Number of SACK blocks */ - u16 user_mss; /* mss requested by user in ioctl */ + u16 user_mss; /* mss requested by user in ioctl */ u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ }; +static inline void tcp_clear_options(struct tcp_options_received *rx_opt) +{ + rx_opt->tstamp_ok = rx_opt->sack_ok = 0; + rx_opt->wscale_ok = rx_opt->snd_wscale = 0; + rx_opt->cookie_plus = 0; +} + /* This is the max number of SACKS that we'll generate and process. It's safe - * to increse this, although since: + * to increase this, although since: * size = TCPOLEN_SACK_BASE_ALIGNED (4) + n * TCPOLEN_SACK_PERBLOCK (8) * only four options will fit in a standard TCP header */ #define TCP_NUM_SACKS 4 +struct tcp_cookie_values; +struct tcp_request_sock_ops; + struct tcp_request_sock { struct inet_request_sock req; #ifdef CONFIG_TCP_MD5SIG /* Only used by TCP MD5 Signature so far. */ const struct tcp_request_sock_ops *af_specific; #endif - u32 rcv_isn; - u32 snt_isn; + u32 rcv_isn; + u32 snt_isn; }; static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) @@ -410,6 +448,12 @@ struct tcp_sock { /* TCP MD5 Signature Option information */ struct tcp_md5sig_info *md5sig_info; #endif + + /* When the cookie options are generated and exchanged, then this + * object holds a reference to them (cookie_values->kref). Also + * contains related tcp_cookie_transactions fields. + */ + struct tcp_cookie_values *cookie_values; }; static inline struct tcp_sock *tcp_sk(const struct sock *sk) @@ -428,6 +472,10 @@ struct tcp_timewait_sock { u16 tw_md5_keylen; u8 tw_md5_key[TCP_MD5SIG_MAXKEYLEN]; #endif + /* Few sockets in timewait have cookies; in that case, then this + * object holds a reference to them (tw_cookie_values->kref). + */ + struct tcp_cookie_values *tw_cookie_values; }; static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) @@ -435,6 +483,6 @@ static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) return (struct tcp_timewait_sock *)sk; } -#endif +#endif /* __KERNEL__ */ #endif /* _LINUX_TCP_H */ diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 8c84881f8478..8ce61359bf73 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -55,6 +55,7 @@ struct usbnet { struct sk_buff_head done; struct sk_buff_head rxq_pause; struct urb *interrupt; + struct usb_anchor deferred; struct tasklet_struct bh; struct work_struct kevent; @@ -65,6 +66,8 @@ struct usbnet { # define EVENT_STS_SPLIT 3 # define EVENT_LINK_RESET 4 # define EVENT_RX_PAUSED 5 +# define EVENT_DEV_WAKING 6 +# define EVENT_DEV_ASLEEP 7 }; static inline struct usb_driver *driver_of(struct usb_interface *intf) @@ -109,6 +112,9 @@ struct driver_info { /* see if peer is connected ... can sleep */ int (*check_connect)(struct usbnet *); + /* (dis)activate runtime power management */ + int (*manage_power)(struct usbnet *, int); + /* for status polling */ void (*status)(struct usbnet *, struct urb *); diff --git a/include/linux/vt.h b/include/linux/vt.h index 7afca0d72139..7ffa11f06232 100644 --- a/include/linux/vt.h +++ b/include/linux/vt.h @@ -70,8 +70,8 @@ struct vt_event { #define VT_EVENT_UNBLANK 0x0004 /* Screen unblank */ #define VT_EVENT_RESIZE 0x0008 /* Resize display */ #define VT_MAX_EVENT 0x000F - unsigned int old; /* Old console */ - unsigned int new; /* New console (if changing) */ + unsigned int oldev; /* Old console */ + unsigned int newev; /* New console (if changing) */ unsigned int pad[4]; /* Padding for expansion */ }; diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 3246f0e66bcc..29e04beb1fc9 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -90,6 +90,13 @@ struct xfrm_algo { char alg_key[0]; }; +struct xfrm_algo_auth { + char alg_name[64]; + unsigned int alg_key_len; /* in bits */ + unsigned int alg_trunc_len; /* in bits */ + char alg_key[0]; +}; + struct xfrm_algo_aead { char alg_name[64]; unsigned int alg_key_len; /* in bits */ @@ -274,6 +281,7 @@ enum xfrm_attr_type_t { XFRMA_MIGRATE, XFRMA_ALG_AEAD, /* struct xfrm_algo_aead */ XFRMA_KMADDRESS, /* struct xfrm_user_kmaddress */ + XFRMA_ALG_AUTH_TRUNC, /* struct xfrm_algo_auth */ __XFRMA_MAX #define XFRMA_MAX (__XFRMA_MAX - 1) diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 7b640aeddb64..7b86094a894b 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -367,22 +367,6 @@ static inline void hci_conn_put(struct hci_conn *conn) } } -/* ----- HCI tasks ----- */ -static inline void hci_sched_cmd(struct hci_dev *hdev) -{ - tasklet_schedule(&hdev->cmd_task); -} - -static inline void hci_sched_rx(struct hci_dev *hdev) -{ - tasklet_schedule(&hdev->rx_task); -} - -static inline void hci_sched_tx(struct hci_dev *hdev) -{ - tasklet_schedule(&hdev->tx_task); -} - /* ----- HCI Devices ----- */ static inline void __hci_dev_put(struct hci_dev *d) { @@ -437,28 +421,7 @@ int hci_inquiry(void __user *arg); void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); -/* Receive frame from HCI drivers */ -static inline int hci_recv_frame(struct sk_buff *skb) -{ - struct hci_dev *hdev = (struct hci_dev *) skb->dev; - if (!hdev || (!test_bit(HCI_UP, &hdev->flags) - && !test_bit(HCI_INIT, &hdev->flags))) { - kfree_skb(skb); - return -ENXIO; - } - - /* Incomming skb */ - bt_cb(skb)->incoming = 1; - - /* Time stamp */ - __net_timestamp(skb); - - /* Queue frame for rx task */ - skb_queue_tail(&hdev->rx_q, skb); - hci_sched_rx(hdev); - return 0; -} - +int hci_recv_frame(struct sk_buff *skb); int hci_recv_fragment(struct hci_dev *hdev, int type, void *data, int count); int hci_register_sysfs(struct hci_dev *hdev); diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 9516f4b4a3c2..17a689f27a6a 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -324,7 +324,6 @@ struct l2cap_pinfo { __u8 next_tx_seq; __u8 expected_ack_seq; - __u8 req_seq; __u8 expected_tx_seq; __u8 buffer_seq; __u8 buffer_seq_srej; @@ -375,6 +374,7 @@ struct l2cap_pinfo { #define L2CAP_CONN_SEND_PBIT 0x10 #define L2CAP_CONN_REMOTE_BUSY 0x20 #define L2CAP_CONN_LOCAL_BUSY 0x40 +#define L2CAP_CONN_REJ_ACT 0x80 #define __mod_retrans_timer() mod_timer(&l2cap_pi(sk)->retrans_timer, \ jiffies + msecs_to_jiffies(L2CAP_DEFAULT_RETRANS_TO)); diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 2cd707b15d59..c07ac9650ebc 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -10,8 +10,8 @@ struct fib_rule { struct list_head list; atomic_t refcnt; - int ifindex; - char ifname[IFNAMSIZ]; + int iifindex; + int oifindex; u32 mark; u32 mark_mask; u32 pref; @@ -20,6 +20,8 @@ struct fib_rule { u8 action; u32 target; struct fib_rule * ctarget; + char iifname[IFNAMSIZ]; + char oifname[IFNAMSIZ]; struct rcu_head rcu; struct net * fr_net; }; @@ -64,10 +66,12 @@ struct fib_rules_ops { struct list_head rules_list; struct module *owner; struct net *fro_net; + struct rcu_head rcu; }; #define FRA_GENERIC_POLICY \ - [FRA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ + [FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ + [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ [FRA_PRIORITY] = { .type = NLA_U32 }, \ [FRA_FWMARK] = { .type = NLA_U32 }, \ [FRA_FWMASK] = { .type = NLA_U32 }, \ @@ -99,7 +103,7 @@ static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla) return frh->table; } -extern int fib_rules_register(struct fib_rules_ops *); +extern struct fib_rules_ops *fib_rules_register(struct fib_rules_ops *, struct net *); extern void fib_rules_unregister(struct fib_rules_ops *); extern void fib_rules_cleanup_ops(struct fib_rules_ops *); diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 773b10fa38e4..b801ade2295e 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -199,6 +199,8 @@ static inline __be32 inet_rcv_saddr(const struct sock *sk) extern void inet_twsk_put(struct inet_timewait_sock *tw); +extern int inet_twsk_unhash(struct inet_timewait_sock *tw); + extern struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int state); @@ -212,14 +214,14 @@ extern void inet_twsk_schedule(struct inet_timewait_sock *tw, extern void inet_twsk_deschedule(struct inet_timewait_sock *tw, struct inet_timewait_death_row *twdr); -extern void inet_twsk_purge(struct net *net, struct inet_hashinfo *hashinfo, +extern void inet_twsk_purge(struct inet_hashinfo *hashinfo, struct inet_timewait_death_row *twdr, int family); static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) { #ifdef CONFIG_NET_NS - return twsk->tw_net; + return rcu_dereference(twsk->tw_net); #else return &init_net; #endif @@ -229,7 +231,7 @@ static inline void twsk_net_set(struct inet_timewait_sock *twsk, struct net *net) { #ifdef CONFIG_NET_NS - twsk->tw_net = net; + rcu_assign_pointer(twsk->tw_net, net); #endif } #endif /* _INET_TIMEWAIT_SOCK_ */ diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 1d75b960da06..2aff4906b2ae 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1304,6 +1304,12 @@ enum ieee80211_filter_flags { * * These flags are used with the ampdu_action() callback in * &struct ieee80211_ops to indicate which action is needed. + * + * Note that drivers MUST be able to deal with a TX aggregation + * session being stopped even before they OK'ed starting it by + * calling ieee80211_start_tx_ba_cb(_irqsafe), because the peer + * might receive the addBA frame and send a delBA right away! + * * @IEEE80211_AMPDU_RX_START: start Rx aggregation * @IEEE80211_AMPDU_RX_STOP: stop Rx aggregation * @IEEE80211_AMPDU_TX_START: start Tx aggregation diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 0addd45038ac..f307e133d14c 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -42,7 +42,8 @@ struct net { */ #endif struct list_head list; /* list of network namespaces */ - struct work_struct work; /* work struct for freeing */ + struct list_head cleanup_list; /* namespaces on death row */ + struct list_head exit_list; /* Use only net_mutex */ struct proc_dir_entry *proc_net; struct proc_dir_entry *proc_net_stat; @@ -236,6 +237,9 @@ struct pernet_operations { struct list_head list; int (*init)(struct net *net); void (*exit)(struct net *net); + void (*exit_batch)(struct list_head *net_exit_list); + int *id; + size_t size; }; /* @@ -259,12 +263,8 @@ struct pernet_operations { */ extern int register_pernet_subsys(struct pernet_operations *); extern void unregister_pernet_subsys(struct pernet_operations *); -extern int register_pernet_gen_subsys(int *id, struct pernet_operations *); -extern void unregister_pernet_gen_subsys(int id, struct pernet_operations *); extern int register_pernet_device(struct pernet_operations *); extern void unregister_pernet_device(struct pernet_operations *); -extern int register_pernet_gen_device(int *id, struct pernet_operations *); -extern void unregister_pernet_gen_device(int id, struct pernet_operations *); struct ctl_path; struct ctl_table; diff --git a/include/net/netns/generic.h b/include/net/netns/generic.h index 0c04fd2a700b..ff4982ab84b6 100644 --- a/include/net/netns/generic.h +++ b/include/net/netns/generic.h @@ -12,9 +12,11 @@ * stuff on the struct net without explicit struct net modification * * The rules are simple: - * 1. register the ops with register_pernet_gen_device to get the id - * of your private pointer; - * 2. call net_assign_generic() to put the private data on the struct + * 1. set pernet_operations->id. After register_pernet_device you + * will have the id of your private pointer. + * 2. Either set pernet_operations->size (to have the code allocate and + * free a private structure pointed to from struct net ) or + * call net_assign_generic() to put the private data on the struct * net (most preferably this should be done in the ->init callback * of the ops registered); * 3. do not change this pointer while the net is alive; diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 1ba912749caa..56f8e5585df7 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -43,6 +43,7 @@ struct netns_xfrm { struct work_struct policy_hash_work; struct sock *nlsk; + struct sock *nlsk_stash; u32 sysctl_aevent_etime; u32 sysctl_aevent_rseqth; diff --git a/include/net/request_sock.h b/include/net/request_sock.h index c7190846e128..c9b50ebd9ce9 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -27,13 +27,19 @@ struct sk_buff; struct dst_entry; struct proto; +/* empty to "strongly type" an otherwise void parameter. + */ +struct request_values { +}; + struct request_sock_ops { int family; int obj_size; struct kmem_cache *slab; char *slab_name; int (*rtx_syn_ack)(struct sock *sk, - struct request_sock *req); + struct request_sock *req, + struct request_values *rvp); void (*send_ack)(struct sock *sk, struct sk_buff *skb, struct request_sock *req); void (*send_reset)(struct sock *sk, diff --git a/include/net/route.h b/include/net/route.h index cfb4c071a136..bce6dd68d27b 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -108,6 +108,7 @@ extern int ip_rt_init(void); extern void ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw, __be32 src, struct net_device *dev); extern void rt_cache_flush(struct net *net, int how); +extern void rt_cache_flush_batch(void); extern int __ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp); extern int ip_route_output_key(struct net *, struct rtable **, struct flowi *flp); extern int ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, int flags); diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 58f714a3b670..63908840eef0 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -308,6 +308,10 @@ enum { SCTP_MAX_GABS = 16 }; #define SCTP_DEFAULT_MINWINDOW 1500 /* default minimum rwnd size */ #define SCTP_DEFAULT_MAXWINDOW 65535 /* default rwnd size */ +#define SCTP_DEFAULT_RWND_SHIFT 4 /* by default, update on 1/16 of + * rcvbuf, which is 1/8 of initial + * window + */ #define SCTP_DEFAULT_MAXSEGMENT 1500 /* MTU size, this is the limit * to which we will raise the P-MTU. */ diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index c1dd89365833..851c813adb3a 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -243,7 +243,8 @@ struct sctp_chunk *sctp_make_op_error(const struct sctp_association *, const struct sctp_chunk *chunk, __be16 cause_code, const void *payload, - size_t paylen); + size_t paylen, + size_t reserve_tail); struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *, union sctp_addr *, diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index cd2e18778f81..7571e32723bf 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -231,6 +231,11 @@ extern struct sctp_globals { /* Flag to indicate whether computing and verifying checksum * is disabled. */ int checksum_disable; + + /* Threshold for rwnd update SACKS. Receive buffer shifted this many + * bits is an indicator of when to send and window update SACK. + */ + int rwnd_update_shift; } sctp_globals; #define sctp_rto_initial (sctp_globals.rto_initial) @@ -267,6 +272,7 @@ extern struct sctp_globals { #define sctp_prsctp_enable (sctp_globals.prsctp_enable) #define sctp_auth_enable (sctp_globals.auth_enable) #define sctp_checksum_disable (sctp_globals.checksum_disable) +#define sctp_rwnd_upd_shift (sctp_globals.rwnd_update_shift) /* SCTP Socket type: UDP or TCP style. */ typedef enum { @@ -893,7 +899,6 @@ struct sctp_transport { */ /* RTO : The current retransmission timeout value. */ unsigned long rto; - unsigned long last_rto; __u32 rtt; /* This is the most recent RTT. */ @@ -936,6 +941,8 @@ struct sctp_transport { /* Data that has been sent, but not acknowledged. */ __u32 flight_size; + __u32 burst_limited; /* Holds old cwnd when max.burst is applied */ + /* TSN marking the fast recovery exit point */ __u32 fast_recovery_exit; @@ -944,12 +951,6 @@ struct sctp_transport { /* Source address. */ union sctp_addr saddr; - /* When was the last time(in jiffies) that a data packet was sent on - * this transport? This is used to adjust the cwnd when the transport - * becomes inactive. - */ - unsigned long last_time_used; - /* Heartbeat interval: The endpoint sends out a Heartbeat chunk to * the destination address every heartbeat interval. */ @@ -1070,6 +1071,8 @@ void sctp_transport_put(struct sctp_transport *); void sctp_transport_update_rto(struct sctp_transport *, __u32); void sctp_transport_raise_cwnd(struct sctp_transport *, __u32, __u32); void sctp_transport_lower_cwnd(struct sctp_transport *, sctp_lower_cwnd_t); +void sctp_transport_burst_limited(struct sctp_transport *); +void sctp_transport_burst_reset(struct sctp_transport *); unsigned long sctp_transport_timeout(struct sctp_transport *); void sctp_transport_reset(struct sctp_transport *); void sctp_transport_update_pmtu(struct sctp_transport *, u32); diff --git a/include/net/sctp/user.h b/include/net/sctp/user.h index be2334aaf52e..2b2769c5ca9f 100644 --- a/include/net/sctp/user.h +++ b/include/net/sctp/user.h @@ -60,96 +60,49 @@ typedef __s32 sctp_assoc_t; /* The following symbols come from the Sockets API Extensions for * SCTP <draft-ietf-tsvwg-sctpsocket-07.txt>. */ -enum sctp_optname { - SCTP_RTOINFO, -#define SCTP_RTOINFO SCTP_RTOINFO - SCTP_ASSOCINFO, -#define SCTP_ASSOCINFO SCTP_ASSOCINFO - SCTP_INITMSG, -#define SCTP_INITMSG SCTP_INITMSG - SCTP_NODELAY, /* Get/set nodelay option. */ -#define SCTP_NODELAY SCTP_NODELAY - SCTP_AUTOCLOSE, -#define SCTP_AUTOCLOSE SCTP_AUTOCLOSE - SCTP_SET_PEER_PRIMARY_ADDR, -#define SCTP_SET_PEER_PRIMARY_ADDR SCTP_SET_PEER_PRIMARY_ADDR - SCTP_PRIMARY_ADDR, -#define SCTP_PRIMARY_ADDR SCTP_PRIMARY_ADDR - SCTP_ADAPTATION_LAYER, -#define SCTP_ADAPTATION_LAYER SCTP_ADAPTATION_LAYER - SCTP_DISABLE_FRAGMENTS, -#define SCTP_DISABLE_FRAGMENTS SCTP_DISABLE_FRAGMENTS - SCTP_PEER_ADDR_PARAMS, -#define SCTP_PEER_ADDR_PARAMS SCTP_PEER_ADDR_PARAMS - SCTP_DEFAULT_SEND_PARAM, -#define SCTP_DEFAULT_SEND_PARAM SCTP_DEFAULT_SEND_PARAM - SCTP_EVENTS, -#define SCTP_EVENTS SCTP_EVENTS - SCTP_I_WANT_MAPPED_V4_ADDR, /* Turn on/off mapped v4 addresses */ -#define SCTP_I_WANT_MAPPED_V4_ADDR SCTP_I_WANT_MAPPED_V4_ADDR - SCTP_MAXSEG, /* Get/set maximum fragment. */ -#define SCTP_MAXSEG SCTP_MAXSEG - SCTP_STATUS, -#define SCTP_STATUS SCTP_STATUS - SCTP_GET_PEER_ADDR_INFO, -#define SCTP_GET_PEER_ADDR_INFO SCTP_GET_PEER_ADDR_INFO - SCTP_DELAYED_ACK, -#define SCTP_DELAYED_ACK_TIME SCTP_DELAYED_ACK -#define SCTP_DELAYED_ACK SCTP_DELAYED_ACK - SCTP_CONTEXT, /* Receive Context */ -#define SCTP_CONTEXT SCTP_CONTEXT - SCTP_FRAGMENT_INTERLEAVE, -#define SCTP_FRAGMENT_INTERLEAVE SCTP_FRAGMENT_INTERLEAVE - SCTP_PARTIAL_DELIVERY_POINT, /* Set/Get partial delivery point */ -#define SCTP_PARTIAL_DELIVERY_POINT SCTP_PARTIAL_DELIVERY_POINT - SCTP_MAX_BURST, /* Set/Get max burst */ -#define SCTP_MAX_BURST SCTP_MAX_BURST - SCTP_AUTH_CHUNK, /* Set only: add a chunk type to authenticat */ -#define SCTP_AUTH_CHUNK SCTP_AUTH_CHUNK - SCTP_HMAC_IDENT, -#define SCTP_HMAC_IDENT SCTP_HMAC_IDENT - SCTP_AUTH_KEY, -#define SCTP_AUTH_KEY SCTP_AUTH_KEY - SCTP_AUTH_ACTIVE_KEY, -#define SCTP_AUTH_ACTIVE_KEY SCTP_AUTH_ACTIVE_KEY - SCTP_AUTH_DELETE_KEY, -#define SCTP_AUTH_DELETE_KEY SCTP_AUTH_DELETE_KEY - SCTP_PEER_AUTH_CHUNKS, /* Read only */ -#define SCTP_PEER_AUTH_CHUNKS SCTP_PEER_AUTH_CHUNKS - SCTP_LOCAL_AUTH_CHUNKS, /* Read only */ -#define SCTP_LOCAL_AUTH_CHUNKS SCTP_LOCAL_AUTH_CHUNKS - SCTP_GET_ASSOC_NUMBER, /* Read only */ -#define SCTP_GET_ASSOC_NUMBER SCTP_GET_ASSOC_NUMBER - - - /* Internal Socket Options. Some of the sctp library functions are - * implemented using these socket options. - */ - SCTP_SOCKOPT_BINDX_ADD = 100,/* BINDX requests for adding addresses. */ -#define SCTP_SOCKOPT_BINDX_ADD SCTP_SOCKOPT_BINDX_ADD - SCTP_SOCKOPT_BINDX_REM, /* BINDX requests for removing addresses. */ -#define SCTP_SOCKOPT_BINDX_REM SCTP_SOCKOPT_BINDX_REM - SCTP_SOCKOPT_PEELOFF, /* peel off association. */ -#define SCTP_SOCKOPT_PEELOFF SCTP_SOCKOPT_PEELOFF - SCTP_GET_PEER_ADDRS_NUM_OLD, /* Get number of peer addresss. */ -#define SCTP_GET_PEER_ADDRS_NUM_OLD SCTP_GET_PEER_ADDRS_NUM_OLD - SCTP_GET_PEER_ADDRS_OLD, /* Get all peer addresss. */ -#define SCTP_GET_PEER_ADDRS_OLD SCTP_GET_PEER_ADDRS_OLD - SCTP_GET_LOCAL_ADDRS_NUM_OLD, /* Get number of local addresss. */ -#define SCTP_GET_LOCAL_ADDRS_NUM_OLD SCTP_GET_LOCAL_ADDRS_NUM_OLD - SCTP_GET_LOCAL_ADDRS_OLD, /* Get all local addresss. */ -#define SCTP_GET_LOCAL_ADDRS_OLD SCTP_GET_LOCAL_ADDRS_OLD - SCTP_SOCKOPT_CONNECTX_OLD, /* CONNECTX old requests. */ -#define SCTP_SOCKOPT_CONNECTX_OLD SCTP_SOCKOPT_CONNECTX_OLD - SCTP_GET_PEER_ADDRS, /* Get all peer addresss. */ -#define SCTP_GET_PEER_ADDRS SCTP_GET_PEER_ADDRS - SCTP_GET_LOCAL_ADDRS, /* Get all local addresss. */ -#define SCTP_GET_LOCAL_ADDRS SCTP_GET_LOCAL_ADDRS - SCTP_SOCKOPT_CONNECTX, /* CONNECTX requests. */ -#define SCTP_SOCKOPT_CONNECTX SCTP_SOCKOPT_CONNECTX - SCTP_SOCKOPT_CONNECTX3, /* CONNECTX requests. (new implementation) */ -#define SCTP_SOCKOPT_CONNECTX3 SCTP_SOCKOPT_CONNECTX3 -}; +#define SCTP_RTOINFO 0 +#define SCTP_ASSOCINFO 1 +#define SCTP_INITMSG 2 +#define SCTP_NODELAY 3 /* Get/set nodelay option. */ +#define SCTP_AUTOCLOSE 4 +#define SCTP_SET_PEER_PRIMARY_ADDR 5 +#define SCTP_PRIMARY_ADDR 6 +#define SCTP_ADAPTATION_LAYER 7 +#define SCTP_DISABLE_FRAGMENTS 8 +#define SCTP_PEER_ADDR_PARAMS 9 +#define SCTP_DEFAULT_SEND_PARAM 10 +#define SCTP_EVENTS 11 +#define SCTP_I_WANT_MAPPED_V4_ADDR 12 /* Turn on/off mapped v4 addresses */ +#define SCTP_MAXSEG 13 /* Get/set maximum fragment. */ +#define SCTP_STATUS 14 +#define SCTP_GET_PEER_ADDR_INFO 15 +#define SCTP_DELAYED_ACK_TIME 16 +#define SCTP_DELAYED_ACK SCTP_DELAYED_ACK_TIME +#define SCTP_CONTEXT 17 +#define SCTP_FRAGMENT_INTERLEAVE 18 +#define SCTP_PARTIAL_DELIVERY_POINT 19 /* Set/Get partial delivery point */ +#define SCTP_MAX_BURST 20 /* Set/Get max burst */ +#define SCTP_AUTH_CHUNK 21 /* Set only: add a chunk type to authenticate */ +#define SCTP_HMAC_IDENT 22 +#define SCTP_AUTH_KEY 23 +#define SCTP_AUTH_ACTIVE_KEY 24 +#define SCTP_AUTH_DELETE_KEY 25 +#define SCTP_PEER_AUTH_CHUNKS 26 /* Read only */ +#define SCTP_LOCAL_AUTH_CHUNKS 27 /* Read only */ +#define SCTP_GET_ASSOC_NUMBER 28 /* Read only */ + +/* Internal Socket Options. Some of the sctp library functions are + * implemented using these socket options. + */ +#define SCTP_SOCKOPT_BINDX_ADD 100 /* BINDX requests for adding addrs */ +#define SCTP_SOCKOPT_BINDX_REM 101 /* BINDX requests for removing addrs. */ +#define SCTP_SOCKOPT_PEELOFF 102 /* peel off association. */ +/* Options 104-106 are deprecated and removed. Do not use this space */ +#define SCTP_SOCKOPT_CONNECTX_OLD 107 /* CONNECTX old requests. */ +#define SCTP_GET_PEER_ADDRS 108 /* Get all peer addresss. */ +#define SCTP_GET_LOCAL_ADDRS 109 /* Get all local addresss. */ +#define SCTP_SOCKOPT_CONNECTX 110 /* CONNECTX requests. */ +#define SCTP_SOCKOPT_CONNECTX3 111 /* CONNECTX requests (updated) */ /* * 5.2.1 SCTP Initiation Structure (SCTP_INIT) @@ -206,6 +159,7 @@ enum sctp_sinfo_flags { SCTP_UNORDERED = 1, /* Send/receive message unordered. */ SCTP_ADDR_OVER = 2, /* Override the primary destination. */ SCTP_ABORT=4, /* Send an ABORT message to the peer. */ + SCTP_SACK_IMMEDIATELY = 8, /* SACK should be sent without delay */ SCTP_EOF=MSG_FIN, /* Initiate graceful shutdown process. */ }; diff --git a/include/net/tcp.h b/include/net/tcp.h index 325bfcf5c934..e2d2ca2509be 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -30,6 +30,7 @@ #include <linux/dmaengine.h> #include <linux/crypto.h> #include <linux/cryptohash.h> +#include <linux/kref.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> @@ -164,6 +165,7 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOPT_SACK 5 /* SACK Block */ #define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */ #define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */ +#define TCPOPT_COOKIE 253 /* Cookie extension (experimental) */ /* * TCP option lengths @@ -174,6 +176,10 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOLEN_SACK_PERM 2 #define TCPOLEN_TIMESTAMP 10 #define TCPOLEN_MD5SIG 18 +#define TCPOLEN_COOKIE_BASE 2 /* Cookie-less header extension */ +#define TCPOLEN_COOKIE_PAIR 3 /* Cookie pair header extension */ +#define TCPOLEN_COOKIE_MIN (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MIN) +#define TCPOLEN_COOKIE_MAX (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MAX) /* But this is what stacks really send out. */ #define TCPOLEN_TSTAMP_ALIGNED 12 @@ -234,6 +240,7 @@ extern int sysctl_tcp_base_mss; extern int sysctl_tcp_workaround_signed_windows; extern int sysctl_tcp_slow_start_after_idle; extern int sysctl_tcp_max_ssthresh; +extern int sysctl_tcp_cookie_size; extern atomic_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; @@ -340,11 +347,6 @@ static inline void tcp_dec_quickack_mode(struct sock *sk, extern void tcp_enter_quickack_mode(struct sock *sk); -static inline void tcp_clear_options(struct tcp_options_received *rx_opt) -{ - rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0; -} - #define TCP_ECN_OK 1 #define TCP_ECN_QUEUE_CWR 2 #define TCP_ECN_DEMAND_CWR 4 @@ -405,6 +407,7 @@ extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, extern void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, + u8 **hvpp, int estab, struct dst_entry *dst); @@ -440,7 +443,8 @@ extern int tcp_connect(struct sock *sk); extern struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst, - struct request_sock *req); + struct request_sock *req, + struct request_values *rvp); extern int tcp_disconnect(struct sock *sk, int flags); @@ -1225,6 +1229,7 @@ static inline void tcp_write_queue_purge(struct sock *sk) while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) sk_wmem_free_skb(sk, skb); sk_mem_reclaim(sk); + tcp_clear_all_retrans_hints(tcp_sk(sk)); } static inline struct sk_buff *tcp_write_queue_head(struct sock *sk) @@ -1477,6 +1482,91 @@ struct tcp_request_sock_ops { #endif }; +/* Using SHA1 for now, define some constants. + */ +#define COOKIE_DIGEST_WORDS (SHA_DIGEST_WORDS) +#define COOKIE_MESSAGE_WORDS (SHA_MESSAGE_BYTES / 4) +#define COOKIE_WORKSPACE_WORDS (COOKIE_DIGEST_WORDS + COOKIE_MESSAGE_WORDS) + +extern int tcp_cookie_generator(u32 *bakery); + +/** + * struct tcp_cookie_values - each socket needs extra space for the + * cookies, together with (optional) space for any SYN data. + * + * A tcp_sock contains a pointer to the current value, and this is + * cloned to the tcp_timewait_sock. + * + * @cookie_pair: variable data from the option exchange. + * + * @cookie_desired: user specified tcpct_cookie_desired. Zero + * indicates default (sysctl_tcp_cookie_size). + * After cookie sent, remembers size of cookie. + * Range 0, TCP_COOKIE_MIN to TCP_COOKIE_MAX. + * + * @s_data_desired: user specified tcpct_s_data_desired. When the + * constant payload is specified (@s_data_constant), + * holds its length instead. + * Range 0 to TCP_MSS_DESIRED. + * + * @s_data_payload: constant data that is to be included in the + * payload of SYN or SYNACK segments when the + * cookie option is present. + */ +struct tcp_cookie_values { + struct kref kref; + u8 cookie_pair[TCP_COOKIE_PAIR_SIZE]; + u8 cookie_pair_size; + u8 cookie_desired; + u16 s_data_desired:11, + s_data_constant:1, + s_data_in:1, + s_data_out:1, + s_data_unused:2; + u8 s_data_payload[0]; +}; + +static inline void tcp_cookie_values_release(struct kref *kref) +{ + kfree(container_of(kref, struct tcp_cookie_values, kref)); +} + +/* The length of constant payload data. Note that s_data_desired is + * overloaded, depending on s_data_constant: either the length of constant + * data (returned here) or the limit on variable data. + */ +static inline int tcp_s_data_size(const struct tcp_sock *tp) +{ + return (tp->cookie_values != NULL && tp->cookie_values->s_data_constant) + ? tp->cookie_values->s_data_desired + : 0; +} + +/** + * struct tcp_extend_values - tcp_ipv?.c to tcp_output.c workspace. + * + * As tcp_request_sock has already been extended in other places, the + * only remaining method is to pass stack values along as function + * parameters. These parameters are not needed after sending SYNACK. + * + * @cookie_bakery: cryptographic secret and message workspace. + * + * @cookie_plus: bytes in authenticator/cookie option, copied from + * struct tcp_options_received (above). + */ +struct tcp_extend_values { + struct request_values rv; + u32 cookie_bakery[COOKIE_WORKSPACE_WORDS]; + u8 cookie_plus:6, + cookie_out_never:1, + cookie_in_always:1; +}; + +static inline struct tcp_extend_values *tcp_xv(struct request_values *rvp) +{ + return (struct tcp_extend_values *)rvp; +} + extern void tcp_v4_init(void); extern void tcp_init(void); diff --git a/include/net/x25.h b/include/net/x25.h index 2cda04011568..9baa07dc7d17 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -287,8 +287,14 @@ extern unsigned long x25_display_timer(struct sock *); extern void x25_check_rbuf(struct sock *); /* sysctl_net_x25.c */ +#ifdef CONFIG_SYSCTL extern void x25_register_sysctl(void); extern void x25_unregister_sysctl(void); +#else +static inline void x25_register_sysctl(void) {}; +static inline void x25_unregister_sysctl(void) {}; +#endif /* CONFIG_SYSCTL */ + struct x25_skb_cb { unsigned flags; }; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 93d184b91a8c..6d85861ab990 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -162,7 +162,7 @@ struct xfrm_state { struct xfrm_lifetime_cfg lft; /* Data for transformer */ - struct xfrm_algo *aalg; + struct xfrm_algo_auth *aalg; struct xfrm_algo *ealg; struct xfrm_algo *calg; struct xfrm_algo_aead *aead; @@ -1532,12 +1532,22 @@ static inline int xfrm_alg_len(struct xfrm_algo *alg) return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); } +static inline int xfrm_alg_auth_len(struct xfrm_algo_auth *alg) +{ + return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); +} + #ifdef CONFIG_XFRM_MIGRATE static inline struct xfrm_algo *xfrm_algo_clone(struct xfrm_algo *orig) { return kmemdup(orig, xfrm_alg_len(orig), GFP_KERNEL); } +static inline struct xfrm_algo_auth *xfrm_algo_auth_clone(struct xfrm_algo_auth *orig) +{ + return kmemdup(orig, xfrm_alg_auth_len(orig), GFP_KERNEL); +} + static inline void xfrm_states_put(struct xfrm_state **states, int n) { int i; diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 9af48cbf0036..f097ae340bc1 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -145,6 +145,7 @@ struct scsi_device { unsigned retry_hwerror:1; /* Retry HARDWARE_ERROR */ unsigned last_sector_bug:1; /* do not use multisector accesses on SD_LAST_BUGGY_SECTORS */ + unsigned is_visible:1; /* is the device visible in sysfs */ DECLARE_BITMAP(supported_events, SDEV_EVT_MAXBITS); /* supported events */ struct list_head event_list; /* asserted events */ diff --git a/init/Kconfig b/init/Kconfig index 9e03ef8b311e..39923ccc287b 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1098,6 +1098,16 @@ config SLOW_WORK See Documentation/slow-work.txt. +config SLOW_WORK_DEBUG + bool "Slow work debugging through debugfs" + default n + depends on SLOW_WORK && DEBUG_FS + help + Display the contents of the slow work run queue through debugfs, + including items currently executing. + + See Documentation/slow-work.txt. + endmenu # General setup config HAVE_GENERIC_DMA_COHERENT diff --git a/kernel/Makefile b/kernel/Makefile index b8d4cd8ac0b9..d7c13d249b2d 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -94,6 +94,7 @@ obj-$(CONFIG_X86_DS) += trace/ obj-$(CONFIG_RING_BUFFER) += trace/ obj-$(CONFIG_SMP) += sched_cpupri.o obj-$(CONFIG_SLOW_WORK) += slow-work.o +obj-$(CONFIG_SLOW_WORK_DEBUG) += slow-work-debugfs.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) diff --git a/kernel/slow-work-debugfs.c b/kernel/slow-work-debugfs.c new file mode 100644 index 000000000000..e45c43645298 --- /dev/null +++ b/kernel/slow-work-debugfs.c @@ -0,0 +1,227 @@ +/* Slow work debugging + * + * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/slow-work.h> +#include <linux/fs.h> +#include <linux/time.h> +#include <linux/seq_file.h> +#include "slow-work.h" + +#define ITERATOR_SHIFT (BITS_PER_LONG - 4) +#define ITERATOR_SELECTOR (0xfUL << ITERATOR_SHIFT) +#define ITERATOR_COUNTER (~ITERATOR_SELECTOR) + +void slow_work_new_thread_desc(struct slow_work *work, struct seq_file *m) +{ + seq_puts(m, "Slow-work: New thread"); +} + +/* + * Render the time mark field on a work item into a 5-char time with units plus + * a space + */ +static void slow_work_print_mark(struct seq_file *m, struct slow_work *work) +{ + struct timespec now, diff; + + now = CURRENT_TIME; + diff = timespec_sub(now, work->mark); + + if (diff.tv_sec < 0) + seq_puts(m, " -ve "); + else if (diff.tv_sec == 0 && diff.tv_nsec < 1000) + seq_printf(m, "%3luns ", diff.tv_nsec); + else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000) + seq_printf(m, "%3luus ", diff.tv_nsec / 1000); + else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000000) + seq_printf(m, "%3lums ", diff.tv_nsec / 1000000); + else if (diff.tv_sec <= 1) + seq_puts(m, " 1s "); + else if (diff.tv_sec < 60) + seq_printf(m, "%4lus ", diff.tv_sec); + else if (diff.tv_sec < 60 * 60) + seq_printf(m, "%4lum ", diff.tv_sec / 60); + else if (diff.tv_sec < 60 * 60 * 24) + seq_printf(m, "%4luh ", diff.tv_sec / 3600); + else + seq_puts(m, "exces "); +} + +/* + * Describe a slow work item for debugfs + */ +static int slow_work_runqueue_show(struct seq_file *m, void *v) +{ + struct slow_work *work; + struct list_head *p = v; + unsigned long id; + + switch ((unsigned long) v) { + case 1: + seq_puts(m, "THR PID ITEM ADDR FL MARK DESC\n"); + return 0; + case 2: + seq_puts(m, "=== ===== ================ == ===== ==========\n"); + return 0; + + case 3 ... 3 + SLOW_WORK_THREAD_LIMIT - 1: + id = (unsigned long) v - 3; + + read_lock(&slow_work_execs_lock); + work = slow_work_execs[id]; + if (work) { + smp_read_barrier_depends(); + + seq_printf(m, "%3lu %5d %16p %2lx ", + id, slow_work_pids[id], work, work->flags); + slow_work_print_mark(m, work); + + if (work->ops->desc) + work->ops->desc(work, m); + seq_putc(m, '\n'); + } + read_unlock(&slow_work_execs_lock); + return 0; + + default: + work = list_entry(p, struct slow_work, link); + seq_printf(m, "%3s - %16p %2lx ", + work->flags & SLOW_WORK_VERY_SLOW ? "vsq" : "sq", + work, work->flags); + slow_work_print_mark(m, work); + + if (work->ops->desc) + work->ops->desc(work, m); + seq_putc(m, '\n'); + return 0; + } +} + +/* + * map the iterator to a work item + */ +static void *slow_work_runqueue_index(struct seq_file *m, loff_t *_pos) +{ + struct list_head *p; + unsigned long count, id; + + switch (*_pos >> ITERATOR_SHIFT) { + case 0x0: + if (*_pos == 0) + *_pos = 1; + if (*_pos < 3) + return (void *)(unsigned long) *_pos; + if (*_pos < 3 + SLOW_WORK_THREAD_LIMIT) + for (id = *_pos - 3; + id < SLOW_WORK_THREAD_LIMIT; + id++, (*_pos)++) + if (slow_work_execs[id]) + return (void *)(unsigned long) *_pos; + *_pos = 0x1UL << ITERATOR_SHIFT; + + case 0x1: + count = *_pos & ITERATOR_COUNTER; + list_for_each(p, &slow_work_queue) { + if (count == 0) + return p; + count--; + } + *_pos = 0x2UL << ITERATOR_SHIFT; + + case 0x2: + count = *_pos & ITERATOR_COUNTER; + list_for_each(p, &vslow_work_queue) { + if (count == 0) + return p; + count--; + } + *_pos = 0x3UL << ITERATOR_SHIFT; + + default: + return NULL; + } +} + +/* + * set up the iterator to start reading from the first line + */ +static void *slow_work_runqueue_start(struct seq_file *m, loff_t *_pos) +{ + spin_lock_irq(&slow_work_queue_lock); + return slow_work_runqueue_index(m, _pos); +} + +/* + * move to the next line + */ +static void *slow_work_runqueue_next(struct seq_file *m, void *v, loff_t *_pos) +{ + struct list_head *p = v; + unsigned long selector = *_pos >> ITERATOR_SHIFT; + + (*_pos)++; + switch (selector) { + case 0x0: + return slow_work_runqueue_index(m, _pos); + + case 0x1: + if (*_pos >> ITERATOR_SHIFT == 0x1) { + p = p->next; + if (p != &slow_work_queue) + return p; + } + *_pos = 0x2UL << ITERATOR_SHIFT; + p = &vslow_work_queue; + + case 0x2: + if (*_pos >> ITERATOR_SHIFT == 0x2) { + p = p->next; + if (p != &vslow_work_queue) + return p; + } + *_pos = 0x3UL << ITERATOR_SHIFT; + + default: + return NULL; + } +} + +/* + * clean up after reading + */ +static void slow_work_runqueue_stop(struct seq_file *m, void *v) +{ + spin_unlock_irq(&slow_work_queue_lock); +} + +static const struct seq_operations slow_work_runqueue_ops = { + .start = slow_work_runqueue_start, + .stop = slow_work_runqueue_stop, + .next = slow_work_runqueue_next, + .show = slow_work_runqueue_show, +}; + +/* + * open "/sys/kernel/debug/slow_work/runqueue" to list queue contents + */ +static int slow_work_runqueue_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &slow_work_runqueue_ops); +} + +const struct file_operations slow_work_runqueue_fops = { + .owner = THIS_MODULE, + .open = slow_work_runqueue_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; diff --git a/kernel/slow-work.c b/kernel/slow-work.c index 0d31135efbf4..00889bd3c590 100644 --- a/kernel/slow-work.c +++ b/kernel/slow-work.c @@ -16,11 +16,8 @@ #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/wait.h> - -#define SLOW_WORK_CULL_TIMEOUT (5 * HZ) /* cull threads 5s after running out of - * things to do */ -#define SLOW_WORK_OOM_TIMEOUT (5 * HZ) /* can't start new threads for 5s after - * OOM */ +#include <linux/debugfs.h> +#include "slow-work.h" static void slow_work_cull_timeout(unsigned long); static void slow_work_oom_timeout(unsigned long); @@ -46,7 +43,7 @@ static unsigned vslow_work_proportion = 50; /* % of threads that may process #ifdef CONFIG_SYSCTL static const int slow_work_min_min_threads = 2; -static int slow_work_max_max_threads = 255; +static int slow_work_max_max_threads = SLOW_WORK_THREAD_LIMIT; static const int slow_work_min_vslow = 1; static const int slow_work_max_vslow = 99; @@ -98,6 +95,56 @@ static DEFINE_TIMER(slow_work_oom_timer, slow_work_oom_timeout, 0, 0); static struct slow_work slow_work_new_thread; /* new thread starter */ /* + * slow work ID allocation (use slow_work_queue_lock) + */ +static DECLARE_BITMAP(slow_work_ids, SLOW_WORK_THREAD_LIMIT); + +/* + * Unregistration tracking to prevent put_ref() from disappearing during module + * unload + */ +#ifdef CONFIG_MODULES +static struct module *slow_work_thread_processing[SLOW_WORK_THREAD_LIMIT]; +static struct module *slow_work_unreg_module; +static struct slow_work *slow_work_unreg_work_item; +static DECLARE_WAIT_QUEUE_HEAD(slow_work_unreg_wq); +static DEFINE_MUTEX(slow_work_unreg_sync_lock); + +static void slow_work_set_thread_processing(int id, struct slow_work *work) +{ + if (work) + slow_work_thread_processing[id] = work->owner; +} +static void slow_work_done_thread_processing(int id, struct slow_work *work) +{ + struct module *module = slow_work_thread_processing[id]; + + slow_work_thread_processing[id] = NULL; + smp_mb(); + if (slow_work_unreg_work_item == work || + slow_work_unreg_module == module) + wake_up_all(&slow_work_unreg_wq); +} +static void slow_work_clear_thread_processing(int id) +{ + slow_work_thread_processing[id] = NULL; +} +#else +static void slow_work_set_thread_processing(int id, struct slow_work *work) {} +static void slow_work_done_thread_processing(int id, struct slow_work *work) {} +static void slow_work_clear_thread_processing(int id) {} +#endif + +/* + * Data for tracking currently executing items for indication through /proc + */ +#ifdef CONFIG_SLOW_WORK_DEBUG +struct slow_work *slow_work_execs[SLOW_WORK_THREAD_LIMIT]; +pid_t slow_work_pids[SLOW_WORK_THREAD_LIMIT]; +DEFINE_RWLOCK(slow_work_execs_lock); +#endif + +/* * The queues of work items and the lock governing access to them. These are * shared between all the CPUs. It doesn't make sense to have per-CPU queues * as the number of threads bears no relation to the number of CPUs. @@ -105,9 +152,18 @@ static struct slow_work slow_work_new_thread; /* new thread starter */ * There are two queues of work items: one for slow work items, and one for * very slow work items. */ -static LIST_HEAD(slow_work_queue); -static LIST_HEAD(vslow_work_queue); -static DEFINE_SPINLOCK(slow_work_queue_lock); +LIST_HEAD(slow_work_queue); +LIST_HEAD(vslow_work_queue); +DEFINE_SPINLOCK(slow_work_queue_lock); + +/* + * The following are two wait queues that get pinged when a work item is placed + * on an empty queue. These allow work items that are hogging a thread by + * sleeping in a way that could be deferred to yield their thread and enqueue + * themselves. + */ +static DECLARE_WAIT_QUEUE_HEAD(slow_work_queue_waits_for_occupation); +static DECLARE_WAIT_QUEUE_HEAD(vslow_work_queue_waits_for_occupation); /* * The thread controls. A variable used to signal to the threads that they @@ -126,6 +182,20 @@ static DECLARE_COMPLETION(slow_work_last_thread_exited); static int slow_work_user_count; static DEFINE_MUTEX(slow_work_user_lock); +static inline int slow_work_get_ref(struct slow_work *work) +{ + if (work->ops->get_ref) + return work->ops->get_ref(work); + + return 0; +} + +static inline void slow_work_put_ref(struct slow_work *work) +{ + if (work->ops->put_ref) + work->ops->put_ref(work); +} + /* * Calculate the maximum number of active threads in the pool that are * permitted to process very slow work items. @@ -149,7 +219,7 @@ static unsigned slow_work_calc_vsmax(void) * Attempt to execute stuff queued on a slow thread. Return true if we managed * it, false if there was nothing to do. */ -static bool slow_work_execute(void) +static noinline bool slow_work_execute(int id) { struct slow_work *work = NULL; unsigned vsmax; @@ -186,6 +256,13 @@ static bool slow_work_execute(void) } else { very_slow = false; /* avoid the compiler warning */ } + + slow_work_set_thread_processing(id, work); + if (work) { + slow_work_mark_time(work); + slow_work_begin_exec(id, work); + } + spin_unlock_irq(&slow_work_queue_lock); if (!work) @@ -194,12 +271,19 @@ static bool slow_work_execute(void) if (!test_and_clear_bit(SLOW_WORK_PENDING, &work->flags)) BUG(); - work->ops->execute(work); + /* don't execute if the work is in the process of being cancelled */ + if (!test_bit(SLOW_WORK_CANCELLING, &work->flags)) + work->ops->execute(work); if (very_slow) atomic_dec(&vslow_work_executing_count); clear_bit_unlock(SLOW_WORK_EXECUTING, &work->flags); + /* wake up anyone waiting for this work to be complete */ + wake_up_bit(&work->flags, SLOW_WORK_EXECUTING); + + slow_work_end_exec(id, work); + /* if someone tried to enqueue the item whilst we were executing it, * then it'll be left unenqueued to avoid multiple threads trying to * execute it simultaneously @@ -219,7 +303,10 @@ static bool slow_work_execute(void) spin_unlock_irq(&slow_work_queue_lock); } - work->ops->put_ref(work); + /* sort out the race between module unloading and put_ref() */ + slow_work_put_ref(work); + slow_work_done_thread_processing(id, work); + return true; auto_requeue: @@ -227,15 +314,61 @@ auto_requeue: * - we transfer our ref on the item back to the appropriate queue * - don't wake another thread up as we're awake already */ + slow_work_mark_time(work); if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) list_add_tail(&work->link, &vslow_work_queue); else list_add_tail(&work->link, &slow_work_queue); spin_unlock_irq(&slow_work_queue_lock); + slow_work_clear_thread_processing(id); return true; } /** + * slow_work_sleep_till_thread_needed - Sleep till thread needed by other work + * work: The work item under execution that wants to sleep + * _timeout: Scheduler sleep timeout + * + * Allow a requeueable work item to sleep on a slow-work processor thread until + * that thread is needed to do some other work or the sleep is interrupted by + * some other event. + * + * The caller must set up a wake up event before calling this and must have set + * the appropriate sleep mode (such as TASK_UNINTERRUPTIBLE) and tested its own + * condition before calling this function as no test is made here. + * + * False is returned if there is nothing on the queue; true is returned if the + * work item should be requeued + */ +bool slow_work_sleep_till_thread_needed(struct slow_work *work, + signed long *_timeout) +{ + wait_queue_head_t *wfo_wq; + struct list_head *queue; + + DEFINE_WAIT(wait); + + if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) { + wfo_wq = &vslow_work_queue_waits_for_occupation; + queue = &vslow_work_queue; + } else { + wfo_wq = &slow_work_queue_waits_for_occupation; + queue = &slow_work_queue; + } + + if (!list_empty(queue)) + return true; + + add_wait_queue_exclusive(wfo_wq, &wait); + if (list_empty(queue)) + *_timeout = schedule_timeout(*_timeout); + finish_wait(wfo_wq, &wait); + + return !list_empty(queue); +} +EXPORT_SYMBOL(slow_work_sleep_till_thread_needed); + +/** * slow_work_enqueue - Schedule a slow work item for processing * @work: The work item to queue * @@ -260,16 +393,22 @@ auto_requeue: * allowed to pick items to execute. This ensures that very slow items won't * overly block ones that are just ordinarily slow. * - * Returns 0 if successful, -EAGAIN if not. + * Returns 0 if successful, -EAGAIN if not (or -ECANCELED if cancelled work is + * attempted queued) */ int slow_work_enqueue(struct slow_work *work) { + wait_queue_head_t *wfo_wq; + struct list_head *queue; unsigned long flags; + int ret; + + if (test_bit(SLOW_WORK_CANCELLING, &work->flags)) + return -ECANCELED; BUG_ON(slow_work_user_count <= 0); BUG_ON(!work); BUG_ON(!work->ops); - BUG_ON(!work->ops->get_ref); /* when honouring an enqueue request, we only promise that we will run * the work function in the future; we do not promise to run it once @@ -280,8 +419,19 @@ int slow_work_enqueue(struct slow_work *work) * maintaining our promise */ if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) { + if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) { + wfo_wq = &vslow_work_queue_waits_for_occupation; + queue = &vslow_work_queue; + } else { + wfo_wq = &slow_work_queue_waits_for_occupation; + queue = &slow_work_queue; + } + spin_lock_irqsave(&slow_work_queue_lock, flags); + if (unlikely(test_bit(SLOW_WORK_CANCELLING, &work->flags))) + goto cancelled; + /* we promise that we will not attempt to execute the work * function in more than one thread simultaneously * @@ -299,25 +449,221 @@ int slow_work_enqueue(struct slow_work *work) if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) { set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags); } else { - if (work->ops->get_ref(work) < 0) - goto cant_get_ref; - if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) - list_add_tail(&work->link, &vslow_work_queue); - else - list_add_tail(&work->link, &slow_work_queue); + ret = slow_work_get_ref(work); + if (ret < 0) + goto failed; + slow_work_mark_time(work); + list_add_tail(&work->link, queue); wake_up(&slow_work_thread_wq); + + /* if someone who could be requeued is sleeping on a + * thread, then ask them to yield their thread */ + if (work->link.prev == queue) + wake_up(wfo_wq); } spin_unlock_irqrestore(&slow_work_queue_lock, flags); } return 0; -cant_get_ref: +cancelled: + ret = -ECANCELED; +failed: spin_unlock_irqrestore(&slow_work_queue_lock, flags); - return -EAGAIN; + return ret; } EXPORT_SYMBOL(slow_work_enqueue); +static int slow_work_wait(void *word) +{ + schedule(); + return 0; +} + +/** + * slow_work_cancel - Cancel a slow work item + * @work: The work item to cancel + * + * This function will cancel a previously enqueued work item. If we cannot + * cancel the work item, it is guarenteed to have run when this function + * returns. + */ +void slow_work_cancel(struct slow_work *work) +{ + bool wait = true, put = false; + + set_bit(SLOW_WORK_CANCELLING, &work->flags); + smp_mb(); + + /* if the work item is a delayed work item with an active timer, we + * need to wait for the timer to finish _before_ getting the spinlock, + * lest we deadlock against the timer routine + * + * the timer routine will leave DELAYED set if it notices the + * CANCELLING flag in time + */ + if (test_bit(SLOW_WORK_DELAYED, &work->flags)) { + struct delayed_slow_work *dwork = + container_of(work, struct delayed_slow_work, work); + del_timer_sync(&dwork->timer); + } + + spin_lock_irq(&slow_work_queue_lock); + + if (test_bit(SLOW_WORK_DELAYED, &work->flags)) { + /* the timer routine aborted or never happened, so we are left + * holding the timer's reference on the item and should just + * drop the pending flag and wait for any ongoing execution to + * finish */ + struct delayed_slow_work *dwork = + container_of(work, struct delayed_slow_work, work); + + BUG_ON(timer_pending(&dwork->timer)); + BUG_ON(!list_empty(&work->link)); + + clear_bit(SLOW_WORK_DELAYED, &work->flags); + put = true; + clear_bit(SLOW_WORK_PENDING, &work->flags); + + } else if (test_bit(SLOW_WORK_PENDING, &work->flags) && + !list_empty(&work->link)) { + /* the link in the pending queue holds a reference on the item + * that we will need to release */ + list_del_init(&work->link); + wait = false; + put = true; + clear_bit(SLOW_WORK_PENDING, &work->flags); + + } else if (test_and_clear_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags)) { + /* the executor is holding our only reference on the item, so + * we merely need to wait for it to finish executing */ + clear_bit(SLOW_WORK_PENDING, &work->flags); + } + + spin_unlock_irq(&slow_work_queue_lock); + + /* the EXECUTING flag is set by the executor whilst the spinlock is set + * and before the item is dequeued - so assuming the above doesn't + * actually dequeue it, simply waiting for the EXECUTING flag to be + * released here should be sufficient */ + if (wait) + wait_on_bit(&work->flags, SLOW_WORK_EXECUTING, slow_work_wait, + TASK_UNINTERRUPTIBLE); + + clear_bit(SLOW_WORK_CANCELLING, &work->flags); + if (put) + slow_work_put_ref(work); +} +EXPORT_SYMBOL(slow_work_cancel); + +/* + * Handle expiry of the delay timer, indicating that a delayed slow work item + * should now be queued if not cancelled + */ +static void delayed_slow_work_timer(unsigned long data) +{ + wait_queue_head_t *wfo_wq; + struct list_head *queue; + struct slow_work *work = (struct slow_work *) data; + unsigned long flags; + bool queued = false, put = false, first = false; + + if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) { + wfo_wq = &vslow_work_queue_waits_for_occupation; + queue = &vslow_work_queue; + } else { + wfo_wq = &slow_work_queue_waits_for_occupation; + queue = &slow_work_queue; + } + + spin_lock_irqsave(&slow_work_queue_lock, flags); + if (likely(!test_bit(SLOW_WORK_CANCELLING, &work->flags))) { + clear_bit(SLOW_WORK_DELAYED, &work->flags); + + if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) { + /* we discard the reference the timer was holding in + * favour of the one the executor holds */ + set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags); + put = true; + } else { + slow_work_mark_time(work); + list_add_tail(&work->link, queue); + queued = true; + if (work->link.prev == queue) + first = true; + } + } + + spin_unlock_irqrestore(&slow_work_queue_lock, flags); + if (put) + slow_work_put_ref(work); + if (first) + wake_up(wfo_wq); + if (queued) + wake_up(&slow_work_thread_wq); +} + +/** + * delayed_slow_work_enqueue - Schedule a delayed slow work item for processing + * @dwork: The delayed work item to queue + * @delay: When to start executing the work, in jiffies from now + * + * This is similar to slow_work_enqueue(), but it adds a delay before the work + * is actually queued for processing. + * + * The item can have delayed processing requested on it whilst it is being + * executed. The delay will begin immediately, and if it expires before the + * item finishes executing, the item will be placed back on the queue when it + * has done executing. + */ +int delayed_slow_work_enqueue(struct delayed_slow_work *dwork, + unsigned long delay) +{ + struct slow_work *work = &dwork->work; + unsigned long flags; + int ret; + + if (delay == 0) + return slow_work_enqueue(&dwork->work); + + BUG_ON(slow_work_user_count <= 0); + BUG_ON(!work); + BUG_ON(!work->ops); + + if (test_bit(SLOW_WORK_CANCELLING, &work->flags)) + return -ECANCELED; + + if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) { + spin_lock_irqsave(&slow_work_queue_lock, flags); + + if (test_bit(SLOW_WORK_CANCELLING, &work->flags)) + goto cancelled; + + /* the timer holds a reference whilst it is pending */ + ret = work->ops->get_ref(work); + if (ret < 0) + goto cant_get_ref; + + if (test_and_set_bit(SLOW_WORK_DELAYED, &work->flags)) + BUG(); + dwork->timer.expires = jiffies + delay; + dwork->timer.data = (unsigned long) work; + dwork->timer.function = delayed_slow_work_timer; + add_timer(&dwork->timer); + + spin_unlock_irqrestore(&slow_work_queue_lock, flags); + } + + return 0; + +cancelled: + ret = -ECANCELED; +cant_get_ref: + spin_unlock_irqrestore(&slow_work_queue_lock, flags); + return ret; +} +EXPORT_SYMBOL(delayed_slow_work_enqueue); + /* * Schedule a cull of the thread pool at some time in the near future */ @@ -368,13 +714,23 @@ static inline bool slow_work_available(int vsmax) */ static int slow_work_thread(void *_data) { - int vsmax; + int vsmax, id; DEFINE_WAIT(wait); set_freezable(); set_user_nice(current, -5); + /* allocate ourselves an ID */ + spin_lock_irq(&slow_work_queue_lock); + id = find_first_zero_bit(slow_work_ids, SLOW_WORK_THREAD_LIMIT); + BUG_ON(id < 0 || id >= SLOW_WORK_THREAD_LIMIT); + __set_bit(id, slow_work_ids); + slow_work_set_thread_pid(id, current->pid); + spin_unlock_irq(&slow_work_queue_lock); + + sprintf(current->comm, "kslowd%03u", id); + for (;;) { vsmax = vslow_work_proportion; vsmax *= atomic_read(&slow_work_thread_count); @@ -395,7 +751,7 @@ static int slow_work_thread(void *_data) vsmax *= atomic_read(&slow_work_thread_count); vsmax /= 100; - if (slow_work_available(vsmax) && slow_work_execute()) { + if (slow_work_available(vsmax) && slow_work_execute(id)) { cond_resched(); if (list_empty(&slow_work_queue) && list_empty(&vslow_work_queue) && @@ -412,6 +768,11 @@ static int slow_work_thread(void *_data) break; } + spin_lock_irq(&slow_work_queue_lock); + slow_work_set_thread_pid(id, 0); + __clear_bit(id, slow_work_ids); + spin_unlock_irq(&slow_work_queue_lock); + if (atomic_dec_and_test(&slow_work_thread_count)) complete_and_exit(&slow_work_last_thread_exited, 0); return 0; @@ -427,21 +788,6 @@ static void slow_work_cull_timeout(unsigned long data) } /* - * Get a reference on slow work thread starter - */ -static int slow_work_new_thread_get_ref(struct slow_work *work) -{ - return 0; -} - -/* - * Drop a reference on slow work thread starter - */ -static void slow_work_new_thread_put_ref(struct slow_work *work) -{ -} - -/* * Start a new slow work thread */ static void slow_work_new_thread_execute(struct slow_work *work) @@ -475,9 +821,11 @@ static void slow_work_new_thread_execute(struct slow_work *work) } static const struct slow_work_ops slow_work_new_thread_ops = { - .get_ref = slow_work_new_thread_get_ref, - .put_ref = slow_work_new_thread_put_ref, + .owner = THIS_MODULE, .execute = slow_work_new_thread_execute, +#ifdef CONFIG_SLOW_WORK_DEBUG + .desc = slow_work_new_thread_desc, +#endif }; /* @@ -546,12 +894,13 @@ static int slow_work_max_threads_sysctl(struct ctl_table *table, int write, /** * slow_work_register_user - Register a user of the facility + * @module: The module about to make use of the facility * * Register a user of the facility, starting up the initial threads if there * aren't any other users at this point. This will return 0 if successful, or * an error if not. */ -int slow_work_register_user(void) +int slow_work_register_user(struct module *module) { struct task_struct *p; int loop; @@ -598,14 +947,81 @@ error: } EXPORT_SYMBOL(slow_work_register_user); +/* + * wait for all outstanding items from the calling module to complete + * - note that more items may be queued whilst we're waiting + */ +static void slow_work_wait_for_items(struct module *module) +{ +#ifdef CONFIG_MODULES + DECLARE_WAITQUEUE(myself, current); + struct slow_work *work; + int loop; + + mutex_lock(&slow_work_unreg_sync_lock); + add_wait_queue(&slow_work_unreg_wq, &myself); + + for (;;) { + spin_lock_irq(&slow_work_queue_lock); + + /* first of all, we wait for the last queued item in each list + * to be processed */ + list_for_each_entry_reverse(work, &vslow_work_queue, link) { + if (work->owner == module) { + set_current_state(TASK_UNINTERRUPTIBLE); + slow_work_unreg_work_item = work; + goto do_wait; + } + } + list_for_each_entry_reverse(work, &slow_work_queue, link) { + if (work->owner == module) { + set_current_state(TASK_UNINTERRUPTIBLE); + slow_work_unreg_work_item = work; + goto do_wait; + } + } + + /* then we wait for the items being processed to finish */ + slow_work_unreg_module = module; + smp_mb(); + for (loop = 0; loop < SLOW_WORK_THREAD_LIMIT; loop++) { + if (slow_work_thread_processing[loop] == module) + goto do_wait; + } + spin_unlock_irq(&slow_work_queue_lock); + break; /* okay, we're done */ + + do_wait: + spin_unlock_irq(&slow_work_queue_lock); + schedule(); + slow_work_unreg_work_item = NULL; + slow_work_unreg_module = NULL; + } + + remove_wait_queue(&slow_work_unreg_wq, &myself); + mutex_unlock(&slow_work_unreg_sync_lock); +#endif /* CONFIG_MODULES */ +} + /** * slow_work_unregister_user - Unregister a user of the facility + * @module: The module whose items should be cleared * * Unregister a user of the facility, killing all the threads if this was the * last one. + * + * This waits for all the work items belonging to the nominated module to go + * away before proceeding. */ -void slow_work_unregister_user(void) +void slow_work_unregister_user(struct module *module) { + /* first of all, wait for all outstanding items from the calling module + * to complete */ + if (module) + slow_work_wait_for_items(module); + + /* then we can actually go about shutting down the facility if need + * be */ mutex_lock(&slow_work_user_lock); BUG_ON(slow_work_user_count <= 0); @@ -639,6 +1055,16 @@ static int __init init_slow_work(void) if (slow_work_max_max_threads < nr_cpus * 2) slow_work_max_max_threads = nr_cpus * 2; #endif +#ifdef CONFIG_SLOW_WORK_DEBUG + { + struct dentry *dbdir; + + dbdir = debugfs_create_dir("slow_work", NULL); + if (dbdir && !IS_ERR(dbdir)) + debugfs_create_file("runqueue", S_IFREG | 0400, dbdir, + NULL, &slow_work_runqueue_fops); + } +#endif return 0; } diff --git a/kernel/slow-work.h b/kernel/slow-work.h new file mode 100644 index 000000000000..321f3c59d732 --- /dev/null +++ b/kernel/slow-work.h @@ -0,0 +1,72 @@ +/* Slow work private definitions + * + * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#define SLOW_WORK_CULL_TIMEOUT (5 * HZ) /* cull threads 5s after running out of + * things to do */ +#define SLOW_WORK_OOM_TIMEOUT (5 * HZ) /* can't start new threads for 5s after + * OOM */ + +#define SLOW_WORK_THREAD_LIMIT 255 /* abs maximum number of slow-work threads */ + +/* + * slow-work.c + */ +#ifdef CONFIG_SLOW_WORK_DEBUG +extern struct slow_work *slow_work_execs[]; +extern pid_t slow_work_pids[]; +extern rwlock_t slow_work_execs_lock; +#endif + +extern struct list_head slow_work_queue; +extern struct list_head vslow_work_queue; +extern spinlock_t slow_work_queue_lock; + +/* + * slow-work-debugfs.c + */ +#ifdef CONFIG_SLOW_WORK_DEBUG +extern const struct file_operations slow_work_runqueue_fops; + +extern void slow_work_new_thread_desc(struct slow_work *, struct seq_file *); +#endif + +/* + * Helper functions + */ +static inline void slow_work_set_thread_pid(int id, pid_t pid) +{ +#ifdef CONFIG_SLOW_WORK_PROC + slow_work_pids[id] = pid; +#endif +} + +static inline void slow_work_mark_time(struct slow_work *work) +{ +#ifdef CONFIG_SLOW_WORK_PROC + work->mark = CURRENT_TIME; +#endif +} + +static inline void slow_work_begin_exec(int id, struct slow_work *work) +{ +#ifdef CONFIG_SLOW_WORK_PROC + slow_work_execs[id] = work; +#endif +} + +static inline void slow_work_end_exec(int id, struct slow_work *work) +{ +#ifdef CONFIG_SLOW_WORK_PROC + write_lock(&slow_work_execs_lock); + slow_work_execs[id] = NULL; + write_unlock(&slow_work_execs_lock); +#endif +} diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c index b6e7aaea4604..f1d676e4b368 100644 --- a/kernel/sysctl_check.c +++ b/kernel/sysctl_check.c @@ -220,6 +220,7 @@ static const struct trans_ctl_table trans_net_ipv4_conf_vars_table[] = { { NET_IPV4_CONF_PROMOTE_SECONDARIES, "promote_secondaries" }, { NET_IPV4_CONF_ARP_ACCEPT, "arp_accept" }, { NET_IPV4_CONF_ARP_NOTIFY, "arp_notify" }, + { NET_IPV4_CONF_ACCEPT_LOCAL, "accept_local" }, {} }; diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 23abbd93cae1..92cdd9936e3d 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -200,6 +200,9 @@ radix_tree_node_free(struct radix_tree_node *node) * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. + * + * To make use of this facility, the radix tree must be initialised without + * __GFP_WAIT being passed to INIT_RADIX_TREE(). */ int radix_tree_preload(gfp_t gfp_mask) { @@ -543,7 +546,6 @@ out: } EXPORT_SYMBOL(radix_tree_tag_clear); -#ifndef __KERNEL__ /* Only the test harness uses this at present */ /** * radix_tree_tag_get - get a tag on a radix tree node * @root: radix tree root @@ -606,7 +608,6 @@ int radix_tree_tag_get(struct radix_tree_root *root, } } EXPORT_SYMBOL(radix_tree_tag_get); -#endif /** * radix_tree_next_hole - find the next hole (not-present entry) diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 11aee09dd2a6..67a33a5a1a93 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -604,10 +604,14 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) /* * Finally, kill the kernel threads. We don't need to be RCU - * safe anymore, since the bdi is gone from visibility. + * safe anymore, since the bdi is gone from visibility. Force + * unfreeze of the thread before calling kthread_stop(), otherwise + * it would never exet if it is currently stuck in the refrigerator. */ - list_for_each_entry(wb, &bdi->wb_list, list) + list_for_each_entry(wb, &bdi->wb_list, list) { + wb->task->flags &= ~PF_FROZEN; kthread_stop(wb->task); + } } /* diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 1483243edf14..33f90e7362cc 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -184,27 +184,6 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) dev_put(real_dev); } -static void vlan_transfer_operstate(const struct net_device *dev, - struct net_device *vlandev) -{ - /* Have to respect userspace enforced dormant state - * of real device, also must allow supplicant running - * on VLAN device - */ - if (dev->operstate == IF_OPER_DORMANT) - netif_dormant_on(vlandev); - else - netif_dormant_off(vlandev); - - if (netif_carrier_ok(dev)) { - if (!netif_carrier_ok(vlandev)) - netif_carrier_on(vlandev); - } else { - if (netif_carrier_ok(vlandev)) - netif_carrier_off(vlandev); - } -} - int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id) { const char *name = real_dev->name; @@ -262,7 +241,7 @@ int register_vlan_dev(struct net_device *dev) /* Account for reference in struct vlan_dev_info */ dev_hold(real_dev); - vlan_transfer_operstate(real_dev, dev); + netif_stacked_transfer_operstate(real_dev, dev); linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */ /* So, got the sucker initialized, now lets place @@ -431,6 +410,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, struct vlan_group *grp; int i, flgs; struct net_device *vlandev; + struct vlan_dev_info *vlan; LIST_HEAD(list); if (is_vlan_dev(dev)) @@ -452,7 +432,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, if (!vlandev) continue; - vlan_transfer_operstate(dev, vlandev); + netif_stacked_transfer_operstate(dev, vlandev); } break; @@ -507,8 +487,10 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, if (!(flgs & IFF_UP)) continue; - dev_change_flags(vlandev, flgs & ~IFF_UP); - vlan_transfer_operstate(dev, vlandev); + vlan = vlan_dev_info(vlandev); + if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) + dev_change_flags(vlandev, flgs & ~IFF_UP); + netif_stacked_transfer_operstate(dev, vlandev); } break; @@ -523,8 +505,10 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, if (flgs & IFF_UP) continue; - dev_change_flags(vlandev, flgs | IFF_UP); - vlan_transfer_operstate(dev, vlandev); + vlan = vlan_dev_info(vlandev); + if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) + dev_change_flags(vlandev, flgs | IFF_UP); + netif_stacked_transfer_operstate(dev, vlandev); } break; @@ -681,47 +665,26 @@ out: static int vlan_init_net(struct net *net) { + struct vlan_net *vn = net_generic(net, vlan_net_id); int err; - struct vlan_net *vn; - - err = -ENOMEM; - vn = kzalloc(sizeof(struct vlan_net), GFP_KERNEL); - if (vn == NULL) - goto err_alloc; - - err = net_assign_generic(net, vlan_net_id, vn); - if (err < 0) - goto err_assign; vn->name_type = VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD; err = vlan_proc_init(net); - if (err < 0) - goto err_proc; - return 0; - -err_proc: - /* nothing */ -err_assign: - kfree(vn); -err_alloc: return err; } static void vlan_exit_net(struct net *net) { - struct vlan_net *vn; - - vn = net_generic(net, vlan_net_id); - rtnl_kill_links(net, &vlan_link_ops); vlan_proc_cleanup(net); - kfree(vn); } static struct pernet_operations vlan_net_ops = { .init = vlan_init_net, .exit = vlan_exit_net, + .id = &vlan_net_id, + .size = sizeof(struct vlan_net), }; static int __init vlan_proto_init(void) @@ -731,7 +694,7 @@ static int __init vlan_proto_init(void) pr_info("%s v%s %s\n", vlan_fullname, vlan_version, vlan_copyright); pr_info("All bugs added by %s\n", vlan_buggyright); - err = register_pernet_gen_device(&vlan_net_id, &vlan_net_ops); + err = register_pernet_subsys(&vlan_net_ops); if (err < 0) goto err0; @@ -756,7 +719,7 @@ err4: err3: unregister_netdevice_notifier(&vlan_notifier_block); err2: - unregister_pernet_gen_device(vlan_net_id, &vlan_net_ops); + unregister_pernet_subsys(&vlan_net_ops); err0: return err; } @@ -776,7 +739,7 @@ static void __exit vlan_cleanup_module(void) for (i = 0; i < VLAN_GRP_HASH_SIZE; i++) BUG_ON(!hlist_empty(&vlan_group_hash[i])); - unregister_pernet_gen_device(vlan_net_id, &vlan_net_ops); + unregister_pernet_subsys(&vlan_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ vlan_gvrp_uninit(); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index de0dc6bacbe8..b7889782047e 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -431,7 +431,8 @@ int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask) struct vlan_dev_info *vlan = vlan_dev_info(dev); u32 old_flags = vlan->flags; - if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP)) + if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP | + VLAN_FLAG_LOOSE_BINDING)) return -EINVAL; vlan->flags = (old_flags & ~mask) | (flags & mask); @@ -456,7 +457,8 @@ static int vlan_dev_open(struct net_device *dev) struct net_device *real_dev = vlan->real_dev; int err; - if (!(real_dev->flags & IFF_UP)) + if (!(real_dev->flags & IFF_UP) && + !(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) return -ENETDOWN; if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) { diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 3c9cf6a8e7fb..ddc105734af7 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -60,7 +60,8 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[]) if (data[IFLA_VLAN_FLAGS]) { flags = nla_data(data[IFLA_VLAN_FLAGS]); if ((flags->flags & flags->mask) & - ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP)) + ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP | + VLAN_FLAG_LOOSE_BINDING)) return -EINVAL; } diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 8d934dd7fd54..4dd873e3a1bb 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -633,8 +633,8 @@ static void p9_poll_mux(struct p9_conn *m) if (n & POLLOUT) { set_bit(Wpending, &m->wsched); P9_DPRINTK(P9_DEBUG_TRANS, "mux %p can write\n", m); - if ((m->wsize || !list_empty(&m->unsent_req_list)) - && !test_and_set_bit(Wworksched, &m->wsched)) { + if ((m->wsize || !list_empty(&m->unsent_req_list)) && + !test_and_set_bit(Wworksched, &m->wsched)) { P9_DPRINTK(P9_DEBUG_TRANS, "sched write work %p\n", m); queue_work(p9_mux_wq, &m->wq); } diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 73ca4d524928..9fc4da56fb1d 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1023,7 +1023,7 @@ static int atalk_create(struct net *net, struct socket *sock, int protocol, struct sock *sk; int rc = -ESOCKTNOSUPPORT; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; /* diff --git a/net/atm/svc.c b/net/atm/svc.c index c7395070ee78..66e1d9b3e5de 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -655,7 +655,7 @@ static int svc_create(struct net *net, struct socket *sock, int protocol, { int error; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; sock->ops = &svc_proto_ops; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index d6ddfa4c4471..5588ba69c468 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -805,7 +805,7 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol, struct sock *sk; ax25_cb *ax25; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; switch (sock->type) { diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index cafe9f54d841..29b1b220d6cf 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -230,7 +230,6 @@ static int bnep_rx_control(struct bnep_session *s, void *data, int len) switch (cmd) { case BNEP_CMD_NOT_UNDERSTOOD: - case BNEP_SETUP_CONN_REQ: case BNEP_SETUP_CONN_RSP: case BNEP_FILTER_NET_TYPE_RSP: case BNEP_FILTER_MULTI_ADDR_RSP: @@ -245,6 +244,10 @@ static int bnep_rx_control(struct bnep_session *s, void *data, int len) err = bnep_ctrl_set_mcfilter(s, data, len); break; + case BNEP_SETUP_CONN_REQ: + err = bnep_send_rsp(s, BNEP_SETUP_CONN_RSP, BNEP_CONN_NOT_ALLOWED); + break; + default: { u8 pkt[3]; pkt[0] = BNEP_CONTROL; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index e1da8f68759c..94ba34982021 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -193,8 +193,9 @@ static void hci_init_req(struct hci_dev *hdev, unsigned long opt) while ((skb = skb_dequeue(&hdev->driver_init))) { bt_cb(skb)->pkt_type = HCI_COMMAND_PKT; skb->dev = (void *) hdev; + skb_queue_tail(&hdev->cmd_q, skb); - hci_sched_cmd(hdev); + tasklet_schedule(&hdev->cmd_task); } skb_queue_purge(&hdev->driver_init); @@ -987,6 +988,30 @@ int hci_resume_dev(struct hci_dev *hdev) } EXPORT_SYMBOL(hci_resume_dev); +/* Receive frame from HCI drivers */ +int hci_recv_frame(struct sk_buff *skb) +{ + struct hci_dev *hdev = (struct hci_dev *) skb->dev; + if (!hdev || (!test_bit(HCI_UP, &hdev->flags) + && !test_bit(HCI_INIT, &hdev->flags))) { + kfree_skb(skb); + return -ENXIO; + } + + /* Incomming skb */ + bt_cb(skb)->incoming = 1; + + /* Time stamp */ + __net_timestamp(skb); + + /* Queue frame for rx task */ + skb_queue_tail(&hdev->rx_q, skb); + tasklet_schedule(&hdev->rx_task); + + return 0; +} +EXPORT_SYMBOL(hci_recv_frame); + /* Receive packet type fragment */ #define __reassembly(hdev, type) ((hdev)->reassembly[(type) - 2]) @@ -1193,8 +1218,9 @@ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, void *param) bt_cb(skb)->pkt_type = HCI_COMMAND_PKT; skb->dev = (void *) hdev; + skb_queue_tail(&hdev->cmd_q, skb); - hci_sched_cmd(hdev); + tasklet_schedule(&hdev->cmd_task); return 0; } @@ -1271,7 +1297,8 @@ int hci_send_acl(struct hci_conn *conn, struct sk_buff *skb, __u16 flags) spin_unlock_bh(&conn->data_q.lock); } - hci_sched_tx(hdev); + tasklet_schedule(&hdev->tx_task); + return 0; } EXPORT_SYMBOL(hci_send_acl); @@ -1298,8 +1325,10 @@ int hci_send_sco(struct hci_conn *conn, struct sk_buff *skb) skb->dev = (void *) hdev; bt_cb(skb)->pkt_type = HCI_SCODATA_PKT; + skb_queue_tail(&conn->data_q, skb); - hci_sched_tx(hdev); + tasklet_schedule(&hdev->tx_task); + return 0; } EXPORT_SYMBOL(hci_send_sco); @@ -1612,7 +1641,7 @@ static void hci_cmd_task(unsigned long arg) hdev->cmd_last_tx = jiffies; } else { skb_queue_head(&hdev->cmd_q, skb); - hci_sched_cmd(hdev); + tasklet_schedule(&hdev->cmd_task); } } } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index e99fe385fba2..28517bad796c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1320,7 +1320,7 @@ static inline void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *sk if (ev->ncmd) { atomic_set(&hdev->cmd_cnt, 1); if (!skb_queue_empty(&hdev->cmd_q)) - hci_sched_cmd(hdev); + tasklet_schedule(&hdev->cmd_task); } } @@ -1386,7 +1386,7 @@ static inline void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb) if (ev->ncmd) { atomic_set(&hdev->cmd_cnt, 1); if (!skb_queue_empty(&hdev->cmd_q)) - hci_sched_cmd(hdev); + tasklet_schedule(&hdev->cmd_task); } } @@ -1454,7 +1454,7 @@ static inline void hci_num_comp_pkts_evt(struct hci_dev *hdev, struct sk_buff *s } } - hci_sched_tx(hdev); + tasklet_schedule(&hdev->tx_task); tasklet_enable(&hdev->tx_task); } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 1ca5c7ca9bd4..688cfebfbee0 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -414,6 +414,11 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock, goto done; } + if (!test_bit(HCI_UP, &hdev->flags)) { + err = -ENETDOWN; + goto done; + } + if (!(skb = bt_skb_send_alloc(sk, len, msg->msg_flags & MSG_DONTWAIT, &err))) goto done; @@ -440,10 +445,10 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock, if (test_bit(HCI_RAW, &hdev->flags) || (ogf == 0x3f)) { skb_queue_tail(&hdev->raw_q, skb); - hci_sched_tx(hdev); + tasklet_schedule(&hdev->tx_task); } else { skb_queue_tail(&hdev->cmd_q, skb); - hci_sched_cmd(hdev); + tasklet_schedule(&hdev->cmd_task); } } else { if (!capable(CAP_NET_RAW)) { @@ -452,7 +457,7 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock, } skb_queue_tail(&hdev->raw_q, skb); - hci_sched_tx(hdev); + tasklet_schedule(&hdev->tx_task); } err = len; diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 49d8495d69be..569750010fd3 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -280,6 +280,13 @@ static int hidp_send_report(struct hidp_session *session, struct hid_report *rep return hidp_queue_report(session, buf, rsize); } +static int hidp_output_raw_report(struct hid_device *hid, unsigned char *data, size_t count) +{ + if (hidp_queue_report(hid->driver_data, data, count)) + return -ENOMEM; + return count; +} + static void hidp_idle_timeout(unsigned long arg) { struct hidp_session *session = (struct hidp_session *) arg; @@ -785,6 +792,8 @@ static int hidp_setup_hid(struct hidp_session *session, hid->dev.parent = hidp_get_device(session); hid->ll_driver = &hidp_hid_driver; + hid->hid_output_raw_report = hidp_output_raw_report; + err = hid_add_device(hid); if (err < 0) goto failed; diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index 80d929842f04..5129b88c8e5b 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -54,6 +54,7 @@ #define VERSION "2.14" static int enable_ertm = 0; +static int max_transmit = L2CAP_DEFAULT_MAX_TX; static u32 l2cap_feat_mask = L2CAP_FEAT_FIXED_CHAN; static u8 l2cap_fixed_chan[8] = { 0x02, }; @@ -373,6 +374,8 @@ static inline int l2cap_send_rr_or_rnr(struct l2cap_pinfo *pi, u16 control) else control |= L2CAP_SUPER_RCV_READY; + control |= pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT; + return l2cap_send_sframe(pi, control); } @@ -1333,7 +1336,7 @@ static int l2cap_retransmit_frame(struct sock *sk, u8 tx_seq) tx_skb = skb_clone(skb, GFP_ATOMIC); bt_cb(skb)->retries++; control = get_unaligned_le16(tx_skb->data + L2CAP_HDR_SIZE); - control |= (pi->req_seq << L2CAP_CTRL_REQSEQ_SHIFT) + control |= (pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT) | (tx_seq << L2CAP_CTRL_TXSEQ_SHIFT); put_unaligned_le16(control, tx_skb->data + L2CAP_HDR_SIZE); @@ -1362,8 +1365,8 @@ static int l2cap_ertm_send(struct sock *sk) if (pi->conn_state & L2CAP_CONN_WAIT_F) return 0; - while ((skb = sk->sk_send_head) && (!l2cap_tx_window_full(sk)) - && !(pi->conn_state & L2CAP_CONN_REMOTE_BUSY)) { + while ((skb = sk->sk_send_head) && (!l2cap_tx_window_full(sk)) && + !(pi->conn_state & L2CAP_CONN_REMOTE_BUSY)) { tx_skb = skb_clone(skb, GFP_ATOMIC); if (pi->remote_max_tx && @@ -1375,7 +1378,7 @@ static int l2cap_ertm_send(struct sock *sk) bt_cb(skb)->retries++; control = get_unaligned_le16(tx_skb->data + L2CAP_HDR_SIZE); - control |= (pi->req_seq << L2CAP_CTRL_REQSEQ_SHIFT) + control |= (pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT) | (pi->next_tx_seq << L2CAP_CTRL_TXSEQ_SHIFT); put_unaligned_le16(control, tx_skb->data + L2CAP_HDR_SIZE); @@ -1604,8 +1607,8 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms return -EOPNOTSUPP; /* Check outgoing MTU */ - if (sk->sk_type == SOCK_SEQPACKET && pi->mode == L2CAP_MODE_BASIC - && len > pi->omtu) + if (sk->sk_type == SOCK_SEQPACKET && pi->mode == L2CAP_MODE_BASIC && + len > pi->omtu) return -EINVAL; lock_sock(sk); @@ -2173,6 +2176,21 @@ static void l2cap_add_conf_opt(void **ptr, u8 type, u8 len, unsigned long val) *ptr += L2CAP_CONF_OPT_SIZE + len; } +static inline void l2cap_ertm_init(struct sock *sk) +{ + l2cap_pi(sk)->expected_ack_seq = 0; + l2cap_pi(sk)->unacked_frames = 0; + l2cap_pi(sk)->buffer_seq = 0; + l2cap_pi(sk)->num_to_ack = 0; + + setup_timer(&l2cap_pi(sk)->retrans_timer, + l2cap_retrans_timeout, (unsigned long) sk); + setup_timer(&l2cap_pi(sk)->monitor_timer, + l2cap_monitor_timeout, (unsigned long) sk); + + __skb_queue_head_init(SREJ_QUEUE(sk)); +} + static int l2cap_mode_supported(__u8 mode, __u32 feat_mask) { u32 local_feat_mask = l2cap_feat_mask; @@ -2236,7 +2254,7 @@ done: case L2CAP_MODE_ERTM: rfc.mode = L2CAP_MODE_ERTM; rfc.txwin_size = L2CAP_DEFAULT_TX_WINDOW; - rfc.max_transmit = L2CAP_DEFAULT_MAX_TX; + rfc.max_transmit = max_transmit; rfc.retrans_timeout = 0; rfc.monitor_timeout = 0; rfc.max_pdu_size = cpu_to_le16(L2CAP_DEFAULT_MAX_PDU_SIZE); @@ -2756,22 +2774,18 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr goto unlock; if (l2cap_pi(sk)->conf_state & L2CAP_CONF_INPUT_DONE) { - if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) - || l2cap_pi(sk)->fcs != L2CAP_FCS_NONE) + if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) || + l2cap_pi(sk)->fcs != L2CAP_FCS_NONE) l2cap_pi(sk)->fcs = L2CAP_FCS_CRC16; sk->sk_state = BT_CONNECTED; - l2cap_pi(sk)->next_tx_seq = 0; - l2cap_pi(sk)->expected_ack_seq = 0; - l2cap_pi(sk)->unacked_frames = 0; - - setup_timer(&l2cap_pi(sk)->retrans_timer, - l2cap_retrans_timeout, (unsigned long) sk); - setup_timer(&l2cap_pi(sk)->monitor_timer, - l2cap_monitor_timeout, (unsigned long) sk); + l2cap_pi(sk)->next_tx_seq = 0; + l2cap_pi(sk)->expected_tx_seq = 0; __skb_queue_head_init(TX_QUEUE(sk)); - __skb_queue_head_init(SREJ_QUEUE(sk)); + if (l2cap_pi(sk)->mode == L2CAP_MODE_ERTM) + l2cap_ertm_init(sk); + l2cap_chan_ready(sk); goto unlock; } @@ -2845,16 +2859,17 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr l2cap_pi(sk)->conf_state |= L2CAP_CONF_INPUT_DONE; if (l2cap_pi(sk)->conf_state & L2CAP_CONF_OUTPUT_DONE) { - if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) - || l2cap_pi(sk)->fcs != L2CAP_FCS_NONE) + if (!(l2cap_pi(sk)->conf_state & L2CAP_CONF_NO_FCS_RECV) || + l2cap_pi(sk)->fcs != L2CAP_FCS_NONE) l2cap_pi(sk)->fcs = L2CAP_FCS_CRC16; sk->sk_state = BT_CONNECTED; + l2cap_pi(sk)->next_tx_seq = 0; l2cap_pi(sk)->expected_tx_seq = 0; - l2cap_pi(sk)->buffer_seq = 0; - l2cap_pi(sk)->num_to_ack = 0; __skb_queue_head_init(TX_QUEUE(sk)); - __skb_queue_head_init(SREJ_QUEUE(sk)); + if (l2cap_pi(sk)->mode == L2CAP_MODE_ERTM) + l2cap_ertm_init(sk); + l2cap_chan_ready(sk); } @@ -2886,9 +2901,12 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, struct l2cap_cmd sk->sk_shutdown = SHUTDOWN_MASK; skb_queue_purge(TX_QUEUE(sk)); - skb_queue_purge(SREJ_QUEUE(sk)); - del_timer(&l2cap_pi(sk)->retrans_timer); - del_timer(&l2cap_pi(sk)->monitor_timer); + + if (l2cap_pi(sk)->mode == L2CAP_MODE_ERTM) { + skb_queue_purge(SREJ_QUEUE(sk)); + del_timer(&l2cap_pi(sk)->retrans_timer); + del_timer(&l2cap_pi(sk)->monitor_timer); + } l2cap_chan_del(sk, ECONNRESET); bh_unlock_sock(sk); @@ -2913,9 +2931,12 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, struct l2cap_cmd return 0; skb_queue_purge(TX_QUEUE(sk)); - skb_queue_purge(SREJ_QUEUE(sk)); - del_timer(&l2cap_pi(sk)->retrans_timer); - del_timer(&l2cap_pi(sk)->monitor_timer); + + if (l2cap_pi(sk)->mode == L2CAP_MODE_ERTM) { + skb_queue_purge(SREJ_QUEUE(sk)); + del_timer(&l2cap_pi(sk)->retrans_timer); + del_timer(&l2cap_pi(sk)->monitor_timer); + } l2cap_chan_del(sk, 0); bh_unlock_sock(sk); @@ -3280,12 +3301,16 @@ static inline int l2cap_data_channel_iframe(struct sock *sk, u16 rx_control, str { struct l2cap_pinfo *pi = l2cap_pi(sk); u8 tx_seq = __get_txseq(rx_control); + u8 req_seq = __get_reqseq(rx_control); u16 tx_control = 0; u8 sar = rx_control >> L2CAP_CTRL_SAR_SHIFT; int err = 0; BT_DBG("sk %p rx_control 0x%4.4x len %d", sk, rx_control, skb->len); + pi->expected_ack_seq = req_seq; + l2cap_drop_acked_frames(sk); + if (tx_seq == pi->expected_tx_seq) goto expected; @@ -3340,6 +3365,16 @@ expected: return 0; } + if (rx_control & L2CAP_CTRL_FINAL) { + if (pi->conn_state & L2CAP_CONN_REJ_ACT) + pi->conn_state &= ~L2CAP_CONN_REJ_ACT; + else { + sk->sk_send_head = TX_QUEUE(sk)->next; + pi->next_tx_seq = pi->expected_ack_seq; + l2cap_ertm_send(sk); + } + } + pi->buffer_seq = (pi->buffer_seq + 1) % 64; err = l2cap_sar_reassembly_sdu(sk, skb, rx_control); @@ -3376,6 +3411,14 @@ static inline int l2cap_data_channel_sframe(struct sock *sk, u16 rx_control, str pi->expected_ack_seq = tx_seq; l2cap_drop_acked_frames(sk); + if (pi->conn_state & L2CAP_CONN_REJ_ACT) + pi->conn_state &= ~L2CAP_CONN_REJ_ACT; + else { + sk->sk_send_head = TX_QUEUE(sk)->next; + pi->next_tx_seq = pi->expected_ack_seq; + l2cap_ertm_send(sk); + } + if (!(pi->conn_state & L2CAP_CONN_WAIT_F)) break; @@ -3388,8 +3431,8 @@ static inline int l2cap_data_channel_sframe(struct sock *sk, u16 rx_control, str pi->expected_ack_seq = tx_seq; l2cap_drop_acked_frames(sk); - if ((pi->conn_state & L2CAP_CONN_REMOTE_BUSY) - && (pi->unacked_frames > 0)) + if ((pi->conn_state & L2CAP_CONN_REMOTE_BUSY) && + (pi->unacked_frames > 0)) __mod_retrans_timer(); l2cap_ertm_send(sk); @@ -3403,10 +3446,24 @@ static inline int l2cap_data_channel_sframe(struct sock *sk, u16 rx_control, str pi->expected_ack_seq = __get_reqseq(rx_control); l2cap_drop_acked_frames(sk); - sk->sk_send_head = TX_QUEUE(sk)->next; - pi->next_tx_seq = pi->expected_ack_seq; + if (rx_control & L2CAP_CTRL_FINAL) { + if (pi->conn_state & L2CAP_CONN_REJ_ACT) + pi->conn_state &= ~L2CAP_CONN_REJ_ACT; + else { + sk->sk_send_head = TX_QUEUE(sk)->next; + pi->next_tx_seq = pi->expected_ack_seq; + l2cap_ertm_send(sk); + } + } else { + sk->sk_send_head = TX_QUEUE(sk)->next; + pi->next_tx_seq = pi->expected_ack_seq; + l2cap_ertm_send(sk); - l2cap_ertm_send(sk); + if (pi->conn_state & L2CAP_CONN_WAIT_F) { + pi->srej_save_reqseq = tx_seq; + pi->conn_state |= L2CAP_CONN_REJ_ACT; + } + } break; @@ -3425,7 +3482,7 @@ static inline int l2cap_data_channel_sframe(struct sock *sk, u16 rx_control, str } else if (rx_control & L2CAP_CTRL_FINAL) { if ((pi->conn_state & L2CAP_CONN_SREJ_ACT) && pi->srej_save_reqseq == tx_seq) - pi->srej_save_reqseq &= ~L2CAP_CONN_SREJ_ACT; + pi->conn_state &= ~L2CAP_CONN_SREJ_ACT; else l2cap_retransmit_frame(sk, tx_seq); } @@ -4004,6 +4061,9 @@ module_exit(l2cap_exit); module_param(enable_ertm, bool, 0644); MODULE_PARM_DESC(enable_ertm, "Enable enhanced retransmission mode"); +module_param(max_transmit, uint, 0644); +MODULE_PARM_DESC(max_transmit, "Max transmit value (default = 3)"); + MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth L2CAP ver " VERSION); MODULE_VERSION(VERSION); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 25692bc0a342..fc5ee3296e22 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -51,6 +51,7 @@ static int disable_cfc = 0; static int channel_mtu = -1; static unsigned int l2cap_mtu = RFCOMM_MAX_L2CAP_MTU; +static int l2cap_ertm = 0; static struct task_struct *rfcomm_thread; @@ -702,6 +703,8 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, bdaddr_t *dst sk = sock->sk; lock_sock(sk); l2cap_pi(sk)->imtu = l2cap_mtu; + if (l2cap_ertm) + l2cap_pi(sk)->mode = L2CAP_MODE_ERTM; release_sock(sk); s = rfcomm_session_add(sock, BT_BOUND); @@ -2185,6 +2188,9 @@ MODULE_PARM_DESC(channel_mtu, "Default MTU for the RFCOMM channel"); module_param(l2cap_mtu, uint, 0644); MODULE_PARM_DESC(l2cap_mtu, "Default MTU for the L2CAP connection"); +module_param(l2cap_ertm, bool, 0644); +MODULE_PARM_DESC(l2cap_ertm, "Use L2CAP ERTM mode for connection"); + MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth RFCOMM ver " VERSION); MODULE_VERSION(VERSION); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 57bf05c353bc..3b8e038ab32c 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -60,8 +60,8 @@ static inline unsigned long hold_time(const struct net_bridge *br) static inline int has_expired(const struct net_bridge *br, const struct net_bridge_fdb_entry *fdb) { - return !fdb->is_static - && time_before_eq(fdb->ageing_timer + hold_time(br), jiffies); + return !fdb->is_static && + time_before_eq(fdb->ageing_timer + hold_time(br), jiffies); } static inline int br_mac_hash(const unsigned char *mac) diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index ee4820aa1843..bee4f300d0c8 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -316,9 +316,9 @@ static ssize_t store_group_addr(struct device *d, if (new_addr[5] & ~0xf) return -EINVAL; - if (new_addr[5] == 1 /* 802.3x Pause address */ - || new_addr[5] == 2 /* 802.3ad Slow protocols */ - || new_addr[5] == 3) /* 802.1X PAE address */ + if (new_addr[5] == 1 || /* 802.3x Pause address */ + new_addr[5] == 2 || /* 802.3ad Slow protocols */ + new_addr[5] == 3) /* 802.1X PAE address */ return -EINVAL; spin_lock_bh(&br->lock); diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c index 48527e621626..75e29a9cebda 100644 --- a/net/bridge/netfilter/ebt_stp.c +++ b/net/bridge/netfilter/ebt_stp.c @@ -135,8 +135,8 @@ ebt_stp_mt(const struct sk_buff *skb, const struct xt_match_param *par) if (memcmp(sp, header, sizeof(header))) return false; - if (info->bitmask & EBT_STP_TYPE - && FWINV(info->type != sp->type, EBT_STP_TYPE)) + if (info->bitmask & EBT_STP_TYPE && + FWINV(info->type != sp->type, EBT_STP_TYPE)) return false; if (sp->type == BPDU_TYPE_CONFIG && diff --git a/net/can/af_can.c b/net/can/af_can.c index 833bd838edc6..51adc4c2b860 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -126,7 +126,7 @@ static int can_create(struct net *net, struct socket *sock, int protocol, if (protocol < 0 || protocol >= CAN_NPROTO) return -EINVAL; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; #ifdef CONFIG_MODULES @@ -375,8 +375,8 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask, return &d->rx[RX_ALL]; /* extra filterlists for the subscription of a single non-RTR can_id */ - if (((*mask & CAN_EFF_RTR_FLAGS) == CAN_EFF_RTR_FLAGS) - && !(*can_id & CAN_RTR_FLAG)) { + if (((*mask & CAN_EFF_RTR_FLAGS) == CAN_EFF_RTR_FLAGS) && + !(*can_id & CAN_RTR_FLAG)) { if (*can_id & CAN_EFF_FLAG) { if (*mask == (CAN_EFF_MASK | CAN_EFF_RTR_FLAGS)) { @@ -525,8 +525,8 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, */ hlist_for_each_entry_rcu(r, next, rl, list) { - if (r->can_id == can_id && r->mask == mask - && r->func == func && r->data == data) + if (r->can_id == can_id && r->mask == mask && + r->func == func && r->data == data) break; } diff --git a/net/compat.c b/net/compat.c index 6a2f75fb3f45..e1a56ade803b 100644 --- a/net/compat.c +++ b/net/compat.c @@ -758,9 +758,13 @@ asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, { int datagrams; struct timespec ktspec; - struct compat_timespec __user *utspec = - (struct compat_timespec __user *)timeout; + struct compat_timespec __user *utspec; + if (timeout == NULL) + return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, + flags | MSG_CMSG_COMPAT, NULL); + + utspec = (struct compat_timespec __user *)timeout; if (get_user(ktspec.tv_sec, &utspec->tv_sec) || get_user(ktspec.tv_nsec, &utspec->tv_nsec)) return -EFAULT; diff --git a/net/core/Makefile b/net/core/Makefile index 796f46eece5f..08791ac3e05a 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -6,7 +6,6 @@ obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ gen_stats.o gen_estimator.o net_namespace.o obj-$(CONFIG_SYSCTL) += sysctl_net_core.o -obj-$(CONFIG_HAS_DMA) += skb_dma_map.o obj-y += dev.o ethtool.o dev_mcast.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o diff --git a/net/core/dev.c b/net/core/dev.c index ccefa2473c39..c36a17aafcf3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -105,6 +105,7 @@ #include <net/dst.h> #include <net/pkt_sched.h> #include <net/checksum.h> +#include <net/xfrm.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/kmod.h> @@ -985,7 +986,7 @@ rollback: /* For now only devices in the initial network namespace * are in sysfs. */ - if (net == &init_net) { + if (net_eq(net, &init_net)) { ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); @@ -1352,7 +1353,7 @@ rollback: nb->notifier_call(nb, NETDEV_DOWN, dev); } nb->notifier_call(nb, NETDEV_UNREGISTER, dev); - nb->notifier_call(nb, NETDEV_UNREGISTER_PERNET, dev); + nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev); } } @@ -1419,6 +1420,45 @@ static inline void net_timestamp(struct sk_buff *skb) skb->tstamp.tv64 = 0; } +/** + * dev_forward_skb - loopback an skb to another netif + * + * @dev: destination network device + * @skb: buffer to forward + * + * return values: + * NET_RX_SUCCESS (no congestion) + * NET_RX_DROP (packet was dropped) + * + * dev_forward_skb can be used for injecting an skb from the + * start_xmit function of one device into the receive queue + * of another device. + * + * The receiving device may be in another namespace, so + * we have to clear all information in the skb that could + * impact namespace isolation. + */ +int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) +{ + skb_orphan(skb); + + if (!(dev->flags & IFF_UP)) + return NET_RX_DROP; + + if (skb->len > (dev->mtu + dev->hard_header_len)) + return NET_RX_DROP; + + skb_dst_drop(skb); + skb->tstamp.tv64 = 0; + skb->pkt_type = PACKET_HOST; + skb->protocol = eth_type_trans(skb, dev); + skb->mark = 0; + secpath_reset(skb); + nf_reset(skb); + return netif_rx(skb); +} +EXPORT_SYMBOL_GPL(dev_forward_skb); + /* * Support routine. Sends outgoing frames to any network * taps currently in use. @@ -2637,9 +2677,10 @@ __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) return GRO_NORMAL; for (p = napi->gro_list; p; p = p->next) { - NAPI_GRO_CB(p)->same_flow = (p->dev == skb->dev) - && !compare_ether_header(skb_mac_header(p), - skb_gro_mac_header(skb)); + NAPI_GRO_CB(p)->same_flow = + (p->dev == skb->dev) && + !compare_ether_header(skb_mac_header(p), + skb_gro_mac_header(skb)); NAPI_GRO_CB(p)->flush = 0; } @@ -4730,8 +4771,7 @@ static void net_set_todo(struct net_device *dev) static void rollback_registered_many(struct list_head *head) { - struct net_device *dev, *aux, *fdev; - LIST_HEAD(pernet_list); + struct net_device *dev; BUG_ON(dev_boot_phase); ASSERT_RTNL(); @@ -4787,26 +4827,14 @@ static void rollback_registered_many(struct list_head *head) netdev_unregister_kobject(dev); } - synchronize_net(); + /* Process any work delayed until the end of the batch */ + dev = list_entry(head->next, struct net_device, unreg_list); + call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); - list_for_each_entry_safe(dev, aux, head, unreg_list) { - int new_net = 1; - list_for_each_entry(fdev, &pernet_list, unreg_list) { - if (dev_net(dev) == dev_net(fdev)) { - new_net = 0; - dev_put(dev); - break; - } - } - if (new_net) - list_move(&dev->unreg_list, &pernet_list); - } + synchronize_net(); - list_for_each_entry_safe(dev, aux, &pernet_list, unreg_list) { - call_netdevice_notifiers(NETDEV_UNREGISTER_PERNET, dev); - list_move(&dev->unreg_list, head); + list_for_each_entry(dev, head, unreg_list) dev_put(dev); - } } static void rollback_registered(struct net_device *dev) @@ -4873,6 +4901,33 @@ unsigned long netdev_fix_features(unsigned long features, const char *name) EXPORT_SYMBOL(netdev_fix_features); /** + * netif_stacked_transfer_operstate - transfer operstate + * @rootdev: the root or lower level device to transfer state from + * @dev: the device to transfer operstate to + * + * Transfer operational state from root to device. This is normally + * called when a stacking relationship exists between the root + * device and the device(a leaf device). + */ +void netif_stacked_transfer_operstate(const struct net_device *rootdev, + struct net_device *dev) +{ + if (rootdev->operstate == IF_OPER_DORMANT) + netif_dormant_on(dev); + else + netif_dormant_off(dev); + + if (netif_carrier_ok(rootdev)) { + if (!netif_carrier_ok(dev)) + netif_carrier_on(dev); + } else { + if (netif_carrier_ok(dev)) + netif_carrier_off(dev); + } +} +EXPORT_SYMBOL(netif_stacked_transfer_operstate); + +/** * register_netdevice - register a network device * @dev: device to register * @@ -5088,7 +5143,7 @@ static void netdev_wait_allrefs(struct net_device *dev) /* Rebroadcast unregister notification */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - /* don't resend NETDEV_UNREGISTER_PERNET, _PERNET users + /* don't resend NETDEV_UNREGISTER_BATCH, _BATCH users * should have already handle it the first time */ if (test_bit(__LINK_STATE_LINKWATCH_PENDING, @@ -5401,11 +5456,6 @@ EXPORT_SYMBOL(unregister_netdevice_queue); /** * unregister_netdevice_many - unregister many devices * @head: list of devices - * - * WARNING: Calling this modifies the given list - * (in rollback_registered_many). It may change the order of the elements - * in the list. However, you can assume it does not add or delete elements - * to/from the list. */ void unregister_netdevice_many(struct list_head *head) { @@ -5514,7 +5564,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char this device. They should clean all the things. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - call_netdevice_notifiers(NETDEV_UNREGISTER_PERNET, dev); + call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); /* * Flush the unicast and multicast chains @@ -5713,14 +5763,13 @@ static struct pernet_operations __net_initdata netdev_net_ops = { static void __net_exit default_device_exit(struct net *net) { - struct net_device *dev; + struct net_device *dev, *aux; /* - * Push all migratable of the network devices back to the + * Push all migratable network devices back to the * initial network namespace */ rtnl_lock(); -restart: - for_each_netdev(net, dev) { + for_each_netdev_safe(net, dev, aux) { int err; char fb_name[IFNAMSIZ]; @@ -5728,11 +5777,9 @@ restart: if (dev->features & NETIF_F_NETNS_LOCAL) continue; - /* Delete virtual devices */ - if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) { - dev->rtnl_link_ops->dellink(dev, NULL); - goto restart; - } + /* Leave virtual devices for the generic cleanup */ + if (dev->rtnl_link_ops) + continue; /* Push remaing network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); @@ -5742,13 +5789,37 @@ restart: __func__, dev->name, err); BUG(); } - goto restart; } rtnl_unlock(); } +static void __net_exit default_device_exit_batch(struct list_head *net_list) +{ + /* At exit all network devices most be removed from a network + * namespace. Do this in the reverse order of registeration. + * Do this across as many network namespaces as possible to + * improve batching efficiency. + */ + struct net_device *dev; + struct net *net; + LIST_HEAD(dev_kill_list); + + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) { + for_each_netdev_reverse(net, dev) { + if (dev->rtnl_link_ops) + dev->rtnl_link_ops->dellink(dev, &dev_kill_list); + else + unregister_netdevice_queue(dev, &dev_kill_list); + } + } + unregister_netdevice_many(&dev_kill_list); + rtnl_unlock(); +} + static struct pernet_operations __net_initdata default_device_ops = { .exit = default_device_exit, + .exit_batch = default_device_exit_batch, }; /* diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index bd309384f8b8..02a3b2c69c1e 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -72,7 +72,7 @@ static void flush_route_cache(struct fib_rules_ops *ops) ops->flush_cache(ops); } -int fib_rules_register(struct fib_rules_ops *ops) +static int __fib_rules_register(struct fib_rules_ops *ops) { int err = -EEXIST; struct fib_rules_ops *o; @@ -102,6 +102,28 @@ errout: return err; } +struct fib_rules_ops * +fib_rules_register(struct fib_rules_ops *tmpl, struct net *net) +{ + struct fib_rules_ops *ops; + int err; + + ops = kmemdup(tmpl, sizeof (*ops), GFP_KERNEL); + if (ops == NULL) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&ops->rules_list); + ops->fro_net = net; + + err = __fib_rules_register(ops); + if (err) { + kfree(ops); + ops = ERR_PTR(err); + } + + return ops; +} + EXPORT_SYMBOL_GPL(fib_rules_register); void fib_rules_cleanup_ops(struct fib_rules_ops *ops) @@ -115,6 +137,15 @@ void fib_rules_cleanup_ops(struct fib_rules_ops *ops) } EXPORT_SYMBOL_GPL(fib_rules_cleanup_ops); +static void fib_rules_put_rcu(struct rcu_head *head) +{ + struct fib_rules_ops *ops = container_of(head, struct fib_rules_ops, rcu); + struct net *net = ops->fro_net; + + release_net(net); + kfree(ops); +} + void fib_rules_unregister(struct fib_rules_ops *ops) { struct net *net = ops->fro_net; @@ -124,8 +155,7 @@ void fib_rules_unregister(struct fib_rules_ops *ops) fib_rules_cleanup_ops(ops); spin_unlock(&net->rules_mod_lock); - synchronize_rcu(); - release_net(net); + call_rcu(&ops->rcu, fib_rules_put_rcu); } EXPORT_SYMBOL_GPL(fib_rules_unregister); @@ -135,7 +165,10 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, { int ret = 0; - if (rule->ifindex && (rule->ifindex != fl->iif)) + if (rule->iifindex && (rule->iifindex != fl->iif)) + goto out; + + if (rule->oifindex && (rule->oifindex != fl->oif)) goto out; if ((rule->mark ^ fl->mark) & rule->mark_mask) @@ -248,14 +281,24 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (tb[FRA_PRIORITY]) rule->pref = nla_get_u32(tb[FRA_PRIORITY]); - if (tb[FRA_IFNAME]) { + if (tb[FRA_IIFNAME]) { + struct net_device *dev; + + rule->iifindex = -1; + nla_strlcpy(rule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, rule->iifname); + if (dev) + rule->iifindex = dev->ifindex; + } + + if (tb[FRA_OIFNAME]) { struct net_device *dev; - rule->ifindex = -1; - nla_strlcpy(rule->ifname, tb[FRA_IFNAME], IFNAMSIZ); - dev = __dev_get_by_name(net, rule->ifname); + rule->oifindex = -1; + nla_strlcpy(rule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, rule->oifname); if (dev) - rule->ifindex = dev->ifindex; + rule->oifindex = dev->ifindex; } if (tb[FRA_FWMARK]) { @@ -274,7 +317,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) rule->flags = frh->flags; rule->table = frh_get_table(frh, tb); - if (!rule->pref && ops->default_pref) + if (!tb[FRA_PRIORITY] && ops->default_pref) rule->pref = ops->default_pref(ops); err = -EINVAL; @@ -388,8 +431,12 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) (rule->pref != nla_get_u32(tb[FRA_PRIORITY]))) continue; - if (tb[FRA_IFNAME] && - nla_strcmp(tb[FRA_IFNAME], rule->ifname)) + if (tb[FRA_IIFNAME] && + nla_strcmp(tb[FRA_IIFNAME], rule->iifname)) + continue; + + if (tb[FRA_OIFNAME] && + nla_strcmp(tb[FRA_OIFNAME], rule->oifname)) continue; if (tb[FRA_FWMARK] && @@ -447,7 +494,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, struct fib_rule *rule) { size_t payload = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)) - + nla_total_size(IFNAMSIZ) /* FRA_IFNAME */ + + nla_total_size(IFNAMSIZ) /* FRA_IIFNAME */ + + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */ + nla_total_size(4) /* FRA_PRIORITY */ + nla_total_size(4) /* FRA_TABLE */ + nla_total_size(4) /* FRA_FWMARK */ @@ -481,11 +529,18 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, if (rule->action == FR_ACT_GOTO && rule->ctarget == NULL) frh->flags |= FIB_RULE_UNRESOLVED; - if (rule->ifname[0]) { - NLA_PUT_STRING(skb, FRA_IFNAME, rule->ifname); + if (rule->iifname[0]) { + NLA_PUT_STRING(skb, FRA_IIFNAME, rule->iifname); - if (rule->ifindex == -1) - frh->flags |= FIB_RULE_DEV_DETACHED; + if (rule->iifindex == -1) + frh->flags |= FIB_RULE_IIF_DETACHED; + } + + if (rule->oifname[0]) { + NLA_PUT_STRING(skb, FRA_OIFNAME, rule->oifname); + + if (rule->oifindex == -1) + frh->flags |= FIB_RULE_OIF_DETACHED; } if (rule->pref) @@ -600,9 +655,12 @@ static void attach_rules(struct list_head *rules, struct net_device *dev) struct fib_rule *rule; list_for_each_entry(rule, rules, list) { - if (rule->ifindex == -1 && - strcmp(dev->name, rule->ifname) == 0) - rule->ifindex = dev->ifindex; + if (rule->iifindex == -1 && + strcmp(dev->name, rule->iifname) == 0) + rule->iifindex = dev->ifindex; + if (rule->oifindex == -1 && + strcmp(dev->name, rule->oifname) == 0) + rule->oifindex = dev->ifindex; } } @@ -610,9 +668,12 @@ static void detach_rules(struct list_head *rules, struct net_device *dev) { struct fib_rule *rule; - list_for_each_entry(rule, rules, list) - if (rule->ifindex == dev->ifindex) - rule->ifindex = -1; + list_for_each_entry(rule, rules, list) { + if (rule->iifindex == dev->ifindex) + rule->iifindex = -1; + if (rule->oifindex == dev->ifindex) + rule->oifindex = -1; + } } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e587e6819698..a08a35bf0a7b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2092,7 +2092,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, if (h > s_h) s_idx = 0; for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next) { - if (dev_net(n->dev) != net) + if (!net_eq(dev_net(n->dev), net)) continue; if (idx < s_idx) goto next; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 157645c0da73..fbc1c7472c5e 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -525,7 +525,7 @@ void netdev_unregister_kobject(struct net_device * net) kobject_get(&dev->kobj); - if (dev_net(net) != &init_net) + if (!net_eq(dev_net(net), &init_net)) return; device_del(dev); @@ -559,7 +559,7 @@ int netdev_register_kobject(struct net_device *net) #endif #endif /* CONFIG_SYSFS */ - if (dev_net(net) != &init_net) + if (!net_eq(dev_net(net), &init_net)) return 0; return device_add(dev); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 1c1af2756f38..bd8c4712ea24 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -27,14 +27,64 @@ EXPORT_SYMBOL(init_net); #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ +static int ops_init(const struct pernet_operations *ops, struct net *net) +{ + int err; + if (ops->id && ops->size) { + void *data = kzalloc(ops->size, GFP_KERNEL); + if (!data) + return -ENOMEM; + + err = net_assign_generic(net, *ops->id, data); + if (err) { + kfree(data); + return err; + } + } + if (ops->init) + return ops->init(net); + return 0; +} + +static void ops_free(const struct pernet_operations *ops, struct net *net) +{ + if (ops->id && ops->size) { + int id = *ops->id; + kfree(net_generic(net, id)); + } +} + +static void ops_exit_list(const struct pernet_operations *ops, + struct list_head *net_exit_list) +{ + struct net *net; + if (ops->exit) { + list_for_each_entry(net, net_exit_list, exit_list) + ops->exit(net); + } + if (ops->exit_batch) + ops->exit_batch(net_exit_list); +} + +static void ops_free_list(const struct pernet_operations *ops, + struct list_head *net_exit_list) +{ + struct net *net; + if (ops->size && ops->id) { + list_for_each_entry(net, net_exit_list, exit_list) + ops_free(ops, net); + } +} + /* * setup_net runs the initializers for the network namespace object. */ static __net_init int setup_net(struct net *net) { /* Must be called with net_mutex held */ - struct pernet_operations *ops; + const struct pernet_operations *ops, *saved_ops; int error = 0; + LIST_HEAD(net_exit_list); atomic_set(&net->count, 1); @@ -43,11 +93,9 @@ static __net_init int setup_net(struct net *net) #endif list_for_each_entry(ops, &pernet_list, list) { - if (ops->init) { - error = ops->init(net); - if (error < 0) - goto out_undo; - } + error = ops_init(ops, net); + if (error < 0) + goto out_undo; } out: return error; @@ -56,10 +104,14 @@ out_undo: /* Walk through the list backwards calling the exit functions * for the pernet modules whose init functions did not fail. */ - list_for_each_entry_continue_reverse(ops, &pernet_list, list) { - if (ops->exit) - ops->exit(net); - } + list_add(&net->exit_list, &net_exit_list); + saved_ops = ops; + list_for_each_entry_continue_reverse(ops, &pernet_list, list) + ops_exit_list(ops, &net_exit_list); + + ops = saved_ops; + list_for_each_entry_continue_reverse(ops, &pernet_list, list) + ops_free_list(ops, &net_exit_list); rcu_barrier(); goto out; @@ -147,18 +199,29 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net) return net_create(); } +static DEFINE_SPINLOCK(cleanup_list_lock); +static LIST_HEAD(cleanup_list); /* Must hold cleanup_list_lock to touch */ + static void cleanup_net(struct work_struct *work) { - struct pernet_operations *ops; - struct net *net; + const struct pernet_operations *ops; + struct net *net, *tmp; + LIST_HEAD(net_kill_list); + LIST_HEAD(net_exit_list); - net = container_of(work, struct net, work); + /* Atomically snapshot the list of namespaces to cleanup */ + spin_lock_irq(&cleanup_list_lock); + list_replace_init(&cleanup_list, &net_kill_list); + spin_unlock_irq(&cleanup_list_lock); mutex_lock(&net_mutex); /* Don't let anyone else find us. */ rtnl_lock(); - list_del_rcu(&net->list); + list_for_each_entry(net, &net_kill_list, cleanup_list) { + list_del_rcu(&net->list); + list_add_tail(&net->exit_list, &net_exit_list); + } rtnl_unlock(); /* @@ -169,10 +232,12 @@ static void cleanup_net(struct work_struct *work) synchronize_rcu(); /* Run all of the network namespace exit methods */ - list_for_each_entry_reverse(ops, &pernet_list, list) { - if (ops->exit) - ops->exit(net); - } + list_for_each_entry_reverse(ops, &pernet_list, list) + ops_exit_list(ops, &net_exit_list); + + /* Free the net generic variables */ + list_for_each_entry_reverse(ops, &pernet_list, list) + ops_free_list(ops, &net_exit_list); mutex_unlock(&net_mutex); @@ -182,14 +247,23 @@ static void cleanup_net(struct work_struct *work) rcu_barrier(); /* Finally it is safe to free my network namespace structure */ - net_free(net); + list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { + list_del_init(&net->exit_list); + net_free(net); + } } +static DECLARE_WORK(net_cleanup_work, cleanup_net); void __put_net(struct net *net) { /* Cleanup the network namespace in process context */ - INIT_WORK(&net->work, cleanup_net); - queue_work(netns_wq, &net->work); + unsigned long flags; + + spin_lock_irqsave(&cleanup_list_lock, flags); + list_add(&net->cleanup_list, &cleanup_list); + spin_unlock_irqrestore(&cleanup_list_lock, flags); + + queue_work(netns_wq, &net_cleanup_work); } EXPORT_SYMBOL_GPL(__put_net); @@ -259,18 +333,20 @@ static int __init net_ns_init(void) pure_initcall(net_ns_init); #ifdef CONFIG_NET_NS -static int register_pernet_operations(struct list_head *list, - struct pernet_operations *ops) +static int __register_pernet_operations(struct list_head *list, + struct pernet_operations *ops) { - struct net *net, *undo_net; + struct net *net; int error; + LIST_HEAD(net_exit_list); list_add_tail(&ops->list, list); - if (ops->init) { + if (ops->init || (ops->id && ops->size)) { for_each_net(net) { - error = ops->init(net); + error = ops_init(ops, net); if (error) goto out_undo; + list_add_tail(&net->exit_list, &net_exit_list); } } return 0; @@ -278,45 +354,82 @@ static int register_pernet_operations(struct list_head *list, out_undo: /* If I have an error cleanup all namespaces I initialized */ list_del(&ops->list); - if (ops->exit) { - for_each_net(undo_net) { - if (undo_net == net) - goto undone; - ops->exit(undo_net); - } - } -undone: + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); return error; } -static void unregister_pernet_operations(struct pernet_operations *ops) +static void __unregister_pernet_operations(struct pernet_operations *ops) { struct net *net; + LIST_HEAD(net_exit_list); list_del(&ops->list); - if (ops->exit) - for_each_net(net) - ops->exit(net); + for_each_net(net) + list_add_tail(&net->exit_list, &net_exit_list); + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); } #else +static int __register_pernet_operations(struct list_head *list, + struct pernet_operations *ops) +{ + int err = 0; + err = ops_init(ops, &init_net); + if (err) + ops_free(ops, &init_net); + return err; + +} + +static void __unregister_pernet_operations(struct pernet_operations *ops) +{ + LIST_HEAD(net_exit_list); + list_add(&init_net.exit_list, &net_exit_list); + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); +} + +#endif /* CONFIG_NET_NS */ + +static DEFINE_IDA(net_generic_ids); + static int register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { - if (ops->init == NULL) - return 0; - return ops->init(&init_net); + int error; + + if (ops->id) { +again: + error = ida_get_new_above(&net_generic_ids, 1, ops->id); + if (error < 0) { + if (error == -EAGAIN) { + ida_pre_get(&net_generic_ids, GFP_KERNEL); + goto again; + } + return error; + } + } + error = __register_pernet_operations(list, ops); + if (error) { + rcu_barrier(); + if (ops->id) + ida_remove(&net_generic_ids, *ops->id); + } + + return error; } static void unregister_pernet_operations(struct pernet_operations *ops) { - if (ops->exit) - ops->exit(&init_net); + + __unregister_pernet_operations(ops); + rcu_barrier(); + if (ops->id) + ida_remove(&net_generic_ids, *ops->id); } -#endif - -static DEFINE_IDA(net_generic_ids); /** * register_pernet_subsys - register a network namespace subsystem @@ -364,38 +477,6 @@ void unregister_pernet_subsys(struct pernet_operations *module) } EXPORT_SYMBOL_GPL(unregister_pernet_subsys); -int register_pernet_gen_subsys(int *id, struct pernet_operations *ops) -{ - int rv; - - mutex_lock(&net_mutex); -again: - rv = ida_get_new_above(&net_generic_ids, 1, id); - if (rv < 0) { - if (rv == -EAGAIN) { - ida_pre_get(&net_generic_ids, GFP_KERNEL); - goto again; - } - goto out; - } - rv = register_pernet_operations(first_device, ops); - if (rv < 0) - ida_remove(&net_generic_ids, *id); -out: - mutex_unlock(&net_mutex); - return rv; -} -EXPORT_SYMBOL_GPL(register_pernet_gen_subsys); - -void unregister_pernet_gen_subsys(int id, struct pernet_operations *ops) -{ - mutex_lock(&net_mutex); - unregister_pernet_operations(ops); - ida_remove(&net_generic_ids, id); - mutex_unlock(&net_mutex); -} -EXPORT_SYMBOL_GPL(unregister_pernet_gen_subsys); - /** * register_pernet_device - register a network namespace device * @ops: pernet operations structure for the subsystem @@ -427,30 +508,6 @@ int register_pernet_device(struct pernet_operations *ops) } EXPORT_SYMBOL_GPL(register_pernet_device); -int register_pernet_gen_device(int *id, struct pernet_operations *ops) -{ - int error; - mutex_lock(&net_mutex); -again: - error = ida_get_new_above(&net_generic_ids, 1, id); - if (error) { - if (error == -EAGAIN) { - ida_pre_get(&net_generic_ids, GFP_KERNEL); - goto again; - } - goto out; - } - error = register_pernet_operations(&pernet_list, ops); - if (error) - ida_remove(&net_generic_ids, *id); - else if (first_device == &pernet_list) - first_device = &ops->list; -out: - mutex_unlock(&net_mutex); - return error; -} -EXPORT_SYMBOL_GPL(register_pernet_gen_device); - /** * unregister_pernet_device - unregister a network namespace netdevice * @ops: pernet operations structure to manipulate @@ -470,17 +527,6 @@ void unregister_pernet_device(struct pernet_operations *ops) } EXPORT_SYMBOL_GPL(unregister_pernet_device); -void unregister_pernet_gen_device(int id, struct pernet_operations *ops) -{ - mutex_lock(&net_mutex); - if (&ops->list == first_device) - first_device = first_device->next; - unregister_pernet_operations(ops); - ida_remove(&net_generic_ids, id); - mutex_unlock(&net_mutex); -} -EXPORT_SYMBOL_GPL(unregister_pernet_gen_device); - static void net_generic_release(struct rcu_head *rcu) { struct net_generic *ng; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index d38470a32792..a23b45f08ec9 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -364,6 +364,7 @@ struct pktgen_dev { * device name (not when the inject is * started as it used to do.) */ + char odevname[32]; struct flow_state *flows; unsigned cflows; /* Concurrent flows (config) */ unsigned lflow; /* Flow length (config) */ @@ -427,7 +428,7 @@ static const char version[] = static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *i); static int pktgen_add_device(struct pktgen_thread *t, const char *ifname); static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, - const char *ifname); + const char *ifname, bool exact); static int pktgen_device_event(struct notifier_block *, unsigned long, void *); static void pktgen_run_all_threads(void); static void pktgen_reset_all_threads(void); @@ -529,7 +530,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) seq_printf(seq, " frags: %d delay: %llu clone_skb: %d ifname: %s\n", pkt_dev->nfrags, (unsigned long long) pkt_dev->delay, - pkt_dev->clone_skb, pkt_dev->odev->name); + pkt_dev->clone_skb, pkt_dev->odevname); seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows, pkt_dev->lflow); @@ -1689,13 +1690,13 @@ static int pktgen_thread_show(struct seq_file *seq, void *v) if_lock(t); list_for_each_entry(pkt_dev, &t->if_list, list) if (pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->odev->name); + seq_printf(seq, "%s ", pkt_dev->odevname); seq_printf(seq, "\nStopped: "); list_for_each_entry(pkt_dev, &t->if_list, list) if (!pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->odev->name); + seq_printf(seq, "%s ", pkt_dev->odevname); if (t->result[0]) seq_printf(seq, "\nResult: %s\n", t->result); @@ -1818,9 +1819,10 @@ static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) { struct pktgen_thread *t; struct pktgen_dev *pkt_dev = NULL; + bool exact = (remove == FIND); list_for_each_entry(t, &pktgen_threads, th_list) { - pkt_dev = pktgen_find_dev(t, ifname); + pkt_dev = pktgen_find_dev(t, ifname, exact); if (pkt_dev) { if (remove) { if_lock(t); @@ -1995,7 +1997,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) "queue_map_min (zero-based) (%d) exceeds valid range " "[0 - %d] for (%d) queues on %s, resetting\n", pkt_dev->queue_map_min, (ntxq ?: 1) - 1, ntxq, - pkt_dev->odev->name); + pkt_dev->odevname); pkt_dev->queue_map_min = ntxq - 1; } if (pkt_dev->queue_map_max >= ntxq) { @@ -2003,7 +2005,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) "queue_map_max (zero-based) (%d) exceeds valid range " "[0 - %d] for (%d) queues on %s, resetting\n", pkt_dev->queue_map_max, (ntxq ?: 1) - 1, ntxq, - pkt_dev->odev->name); + pkt_dev->odevname); pkt_dev->queue_map_max = ntxq - 1; } @@ -2050,9 +2052,8 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) read_lock_bh(&idev->lock); for (ifp = idev->addr_list; ifp; ifp = ifp->if_next) { - if (ifp->scope == IFA_LINK - && !(ifp-> - flags & IFA_F_TENTATIVE)) { + if (ifp->scope == IFA_LINK && + !(ifp->flags & IFA_F_TENTATIVE)) { ipv6_addr_copy(&pkt_dev-> cur_in6_saddr, &ifp->addr); @@ -3263,7 +3264,7 @@ static int pktgen_stop_device(struct pktgen_dev *pkt_dev) if (!pkt_dev->running) { printk(KERN_WARNING "pktgen: interface: %s is already " - "stopped\n", pkt_dev->odev->name); + "stopped\n", pkt_dev->odevname); return -EINVAL; } @@ -3467,7 +3468,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) default: /* Drivers are not supposed to return other values! */ if (net_ratelimit()) pr_info("pktgen: %s xmit error: %d\n", - odev->name, ret); + pkt_dev->odevname, ret); pkt_dev->errors++; /* fallthru */ case NETDEV_TX_LOCKED: @@ -3570,13 +3571,18 @@ static int pktgen_thread_worker(void *arg) } static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, - const char *ifname) + const char *ifname, bool exact) { struct pktgen_dev *p, *pkt_dev = NULL; - if_lock(t); + size_t len = strlen(ifname); + if_lock(t); list_for_each_entry(p, &t->if_list, list) - if (strncmp(p->odev->name, ifname, IFNAMSIZ) == 0) { + if (strncmp(p->odevname, ifname, len) == 0) { + if (p->odevname[len]) { + if (exact || p->odevname[len] != '@') + continue; + } pkt_dev = p; break; } @@ -3619,6 +3625,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) { struct pktgen_dev *pkt_dev; int err; + int node = cpu_to_node(t->cpu); /* We don't allow a device to be on several threads */ @@ -3628,11 +3635,13 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) return -EBUSY; } - pkt_dev = kzalloc(sizeof(struct pktgen_dev), GFP_KERNEL); + pkt_dev = kzalloc_node(sizeof(struct pktgen_dev), GFP_KERNEL, node); if (!pkt_dev) return -ENOMEM; - pkt_dev->flows = vmalloc(MAX_CFLOWS * sizeof(struct flow_state)); + strcpy(pkt_dev->odevname, ifname); + pkt_dev->flows = vmalloc_node(MAX_CFLOWS * sizeof(struct flow_state), + node); if (pkt_dev->flows == NULL) { kfree(pkt_dev); return -ENOMEM; @@ -3694,7 +3703,8 @@ static int __init pktgen_create_thread(int cpu) struct proc_dir_entry *pe; struct task_struct *p; - t = kzalloc(sizeof(struct pktgen_thread), GFP_KERNEL); + t = kzalloc_node(sizeof(struct pktgen_thread), GFP_KERNEL, + cpu_to_node(cpu)); if (!t) { printk(KERN_ERR "pktgen: ERROR: out of memory, can't " "create new thread.\n"); diff --git a/net/core/skb_dma_map.c b/net/core/skb_dma_map.c deleted file mode 100644 index 79687dfd6957..000000000000 --- a/net/core/skb_dma_map.c +++ /dev/null @@ -1,65 +0,0 @@ -/* skb_dma_map.c: DMA mapping helpers for socket buffers. - * - * Copyright (C) David S. Miller <davem@davemloft.net> - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/dma-mapping.h> -#include <linux/skbuff.h> - -int skb_dma_map(struct device *dev, struct sk_buff *skb, - enum dma_data_direction dir) -{ - struct skb_shared_info *sp = skb_shinfo(skb); - dma_addr_t map; - int i; - - map = dma_map_single(dev, skb->data, - skb_headlen(skb), dir); - if (dma_mapping_error(dev, map)) - goto out_err; - - sp->dma_head = map; - for (i = 0; i < sp->nr_frags; i++) { - skb_frag_t *fp = &sp->frags[i]; - - map = dma_map_page(dev, fp->page, fp->page_offset, - fp->size, dir); - if (dma_mapping_error(dev, map)) - goto unwind; - sp->dma_maps[i] = map; - } - - return 0; - -unwind: - while (--i >= 0) { - skb_frag_t *fp = &sp->frags[i]; - - dma_unmap_page(dev, sp->dma_maps[i], - fp->size, dir); - } - dma_unmap_single(dev, sp->dma_head, - skb_headlen(skb), dir); -out_err: - return -ENOMEM; -} -EXPORT_SYMBOL(skb_dma_map); - -void skb_dma_unmap(struct device *dev, struct sk_buff *skb, - enum dma_data_direction dir) -{ - struct skb_shared_info *sp = skb_shinfo(skb); - int i; - - dma_unmap_single(dev, sp->dma_head, - skb_headlen(skb), dir); - for (i = 0; i < sp->nr_frags; i++) { - skb_frag_t *fp = &sp->frags[i]; - - dma_unmap_page(dev, sp->dma_maps[i], - fp->size, dir); - } -} -EXPORT_SYMBOL(skb_dma_unmap); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 7db1de0497c6..fcfc5458c399 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -134,7 +134,7 @@ static __net_init int sysctl_core_net_init(struct net *net) net->core.sysctl_somaxconn = SOMAXCONN; tbl = netns_core_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { tbl = kmemdup(tbl, sizeof(netns_core_table), GFP_KERNEL); if (tbl == NULL) goto err_dup; diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index ac1205df6c86..db9f5b39388f 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1085,8 +1085,8 @@ static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlattr **tb, u8 value_byte; u32 value_int; - if (!tb[DCB_ATTR_BCN] || !netdev->dcbnl_ops->setbcncfg - || !netdev->dcbnl_ops->setbcnrp) + if (!tb[DCB_ATTR_BCN] || !netdev->dcbnl_ops->setbcncfg || + !netdev->dcbnl_ops->setbcnrp) return ret; ret = nla_parse_nested(data, DCB_BCN_ATTR_MAX, @@ -1126,7 +1126,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) u32 pid = skb ? NETLINK_CB(skb).pid : 0; int ret = -EINVAL; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EINVAL; ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX, diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 2423a0866733..efbcfdc12796 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -477,7 +477,8 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, return &rt->u.dst; } -static int dccp_v4_send_response(struct sock *sk, struct request_sock *req) +static int dccp_v4_send_response(struct sock *sk, struct request_sock *req, + struct request_values *rv_unused) { int err = -1; struct sk_buff *skb; @@ -626,7 +627,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) dreq->dreq_iss = dccp_v4_init_sequence(skb); dreq->dreq_service = service; - if (dccp_v4_send_response(sk, req)) + if (dccp_v4_send_response(sk, req, NULL)) goto drop_and_free; inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 50ea91a77705..6574215a1f51 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -241,7 +241,8 @@ out: } -static int dccp_v6_send_response(struct sock *sk, struct request_sock *req) +static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, + struct request_values *rv_unused) { struct inet6_request_sock *ireq6 = inet6_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); @@ -468,7 +469,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) dreq->dreq_iss = dccp_v6_init_sequence(skb); dreq->dreq_service = service; - if (dccp_v6_send_response(sk, req)) + if (dccp_v6_send_response(sk, req, NULL)) goto drop_and_free; inet6_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 5ca49cec95f5..af226a063141 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -184,7 +184,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, * counter (backoff, monitored by dccp_response_timer). */ req->retrans++; - req->rsk_ops->rtx_syn_ack(sk, req); + req->rsk_ops->rtx_syn_ack(sk, req, NULL); } /* Network Duplicate, discard packet */ return NULL; diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 9ade3a6de954..2b494fac9468 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -680,7 +680,7 @@ static int dn_create(struct net *net, struct socket *sock, int protocol, { struct sock *sk; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; switch(sock->type) { diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 6c916e2b8a84..f20dec9cfa06 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -636,7 +636,7 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct dn_ifaddr *ifa, **ifap; int err = -EINVAL; - if (net != &init_net) + if (!net_eq(net, &init_net)) goto errout; err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, dn_ifa_policy); @@ -675,7 +675,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct dn_ifaddr *ifa; int err; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EINVAL; err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, dn_ifa_policy); @@ -789,7 +789,7 @@ static int dn_nl_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) struct dn_dev *dn_db; struct dn_ifaddr *ifa; - if (net != &init_net) + if (!net_eq(net, &init_net)) return 0; skip_ndevs = cb->args[0]; diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index fd641f65e092..e9d48700e83a 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -509,7 +509,7 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void * struct rtattr **rta = arg; struct rtmsg *r = NLMSG_DATA(nlh); - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EINVAL; if (dn_fib_check_attr(r, rta)) @@ -529,7 +529,7 @@ static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void * struct rtattr **rta = arg; struct rtmsg *r = NLMSG_DATA(nlh); - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EINVAL; if (dn_fib_check_attr(r, rta)) diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 860286a3921b..a03284061a31 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1517,7 +1517,7 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void struct sk_buff *skb; struct flowi fl; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EINVAL; memset(&fl, 0, sizeof(fl)); @@ -1602,7 +1602,7 @@ int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb) int h, s_h; int idx, s_idx; - if (net != &init_net) + if (!net_eq(net, &init_net)) return 0; if (NLMSG_PAYLOAD(cb->nlh, 0) < sizeof(struct rtmsg)) diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 72495f25269f..7466c546f286 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -33,7 +33,7 @@ #include <net/dn_dev.h> #include <net/dn_route.h> -static struct fib_rules_ops dn_fib_rules_ops; +static struct fib_rules_ops *dn_fib_rules_ops; struct dn_fib_rule { @@ -56,7 +56,7 @@ int dn_fib_lookup(struct flowi *flp, struct dn_fib_res *res) }; int err; - err = fib_rules_lookup(&dn_fib_rules_ops, flp, 0, &arg); + err = fib_rules_lookup(dn_fib_rules_ops, flp, 0, &arg); res->r = arg.rule; return err; @@ -217,9 +217,9 @@ static u32 dn_fib_rule_default_pref(struct fib_rules_ops *ops) struct list_head *pos; struct fib_rule *rule; - if (!list_empty(&dn_fib_rules_ops.rules_list)) { - pos = dn_fib_rules_ops.rules_list.next; - if (pos->next != &dn_fib_rules_ops.rules_list) { + if (!list_empty(&dn_fib_rules_ops->rules_list)) { + pos = dn_fib_rules_ops->rules_list.next; + if (pos->next != &dn_fib_rules_ops->rules_list) { rule = list_entry(pos->next, struct fib_rule, list); if (rule->pref) return rule->pref - 1; @@ -234,7 +234,7 @@ static void dn_fib_rule_flush_cache(struct fib_rules_ops *ops) dn_rt_cache_flush(-1); } -static struct fib_rules_ops dn_fib_rules_ops = { +static struct fib_rules_ops dn_fib_rules_ops_template = { .family = AF_DECnet, .rule_size = sizeof(struct dn_fib_rule), .addr_size = sizeof(u16), @@ -247,21 +247,23 @@ static struct fib_rules_ops dn_fib_rules_ops = { .flush_cache = dn_fib_rule_flush_cache, .nlgroup = RTNLGRP_DECnet_RULE, .policy = dn_fib_rule_policy, - .rules_list = LIST_HEAD_INIT(dn_fib_rules_ops.rules_list), .owner = THIS_MODULE, .fro_net = &init_net, }; void __init dn_fib_rules_init(void) { - BUG_ON(fib_default_rule_add(&dn_fib_rules_ops, 0x7fff, + dn_fib_rules_ops = + fib_rules_register(&dn_fib_rules_ops_template, &init_net); + BUG_ON(IS_ERR(dn_fib_rules_ops)); + BUG_ON(fib_default_rule_add(dn_fib_rules_ops, 0x7fff, RT_TABLE_MAIN, 0)); - fib_rules_register(&dn_fib_rules_ops); } void __exit dn_fib_rules_cleanup(void) { - fib_rules_unregister(&dn_fib_rules_ops); + fib_rules_unregister(dn_fib_rules_ops); + rcu_barrier(); } diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index 67054b0d550f..b9a33bb5e9cc 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -471,7 +471,7 @@ int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb) struct hlist_node *node; int dumped = 0; - if (net != &init_net) + if (!net_eq(net, &init_net)) return 0; if (NLMSG_PAYLOAD(cb->nlh, 0) >= sizeof(struct rtmsg) && @@ -581,8 +581,9 @@ static int dn_fib_table_insert(struct dn_fib_table *tb, struct rtmsg *r, struct DN_FIB_SCAN_KEY(f, fp, key) { if (fi->fib_priority != DN_FIB_INFO(f)->fib_priority) break; - if (f->fn_type == type && f->fn_scope == r->rtm_scope - && DN_FIB_INFO(f) == fi) + if (f->fn_type == type && + f->fn_scope == r->rtm_scope && + DN_FIB_INFO(f) == fi) goto out; } diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c index 596679803de5..29b4931aae52 100644 --- a/net/econet/af_econet.c +++ b/net/econet/af_econet.c @@ -612,7 +612,7 @@ static int econet_create(struct net *net, struct socket *sock, int protocol, struct econet_sock *eo; int err; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; /* Econet only provides datagram services. */ diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c index de6e34d2a7f8..bad1c49fd960 100644 --- a/net/ieee802154/af_ieee802154.c +++ b/net/ieee802154/af_ieee802154.c @@ -241,7 +241,7 @@ static int ieee802154_create(struct net *net, struct socket *sock, struct proto *proto; const struct proto_ops *ops; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; switch (sock->type) { diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index d07b0c1dd350..7ed3e4ae93ae 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -444,7 +444,7 @@ static int ah_init_state(struct xfrm_state *x) } ahp->icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8; - ahp->icv_trunc_len = aalg_desc->uinfo.auth.icv_truncbits/8; + ahp->icv_trunc_len = x->aalg->alg_trunc_len/8; BUG_ON(ahp->icv_trunc_len > MAX_AH_AUTH_LEN); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 7620382058a0..e3126612fcbb 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1468,6 +1468,7 @@ static struct devinet_sysctl_table { DEVINET_SYSCTL_RW_ENTRY(SEND_REDIRECTS, "send_redirects"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE, "accept_source_route"), + DEVINET_SYSCTL_RW_ENTRY(ACCEPT_LOCAL, "accept_local"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"), DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"), DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"), @@ -1605,7 +1606,7 @@ static __net_init int devinet_init_net(struct net *net) all = &ipv4_devconf; dflt = &ipv4_devconf_dflt; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { all = kmemdup(all, sizeof(ipv4_devconf), GFP_KERNEL); if (all == NULL) goto err_alloc_all; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 12f7287e902d..1948895beb6d 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -530,7 +530,7 @@ static int esp_init_authenc(struct xfrm_state *x) } err = crypto_aead_setauthsize( - aead, aalg_desc->uinfo.auth.icv_truncbits / 8); + aead, x->aalg->alg_trunc_len / 8); if (err) goto free_key; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 6c1e56aef1f4..3323168ee52d 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -241,16 +241,17 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, .iif = oif }; struct fib_result res; - int no_addr, rpf; + int no_addr, rpf, accept_local; int ret; struct net *net; - no_addr = rpf = 0; + no_addr = rpf = accept_local = 0; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) { no_addr = in_dev->ifa_list == NULL; rpf = IN_DEV_RPFILTER(in_dev); + accept_local = IN_DEV_ACCEPT_LOCAL(in_dev); } rcu_read_unlock(); @@ -260,8 +261,10 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, net = dev_net(dev); if (fib_lookup(net, &fl, &res)) goto last_resort; - if (res.type != RTN_UNICAST) - goto e_inval_res; + if (res.type != RTN_UNICAST) { + if (res.type != RTN_LOCAL || !accept_local) + goto e_inval_res; + } *spec_dst = FIB_RES_PREFSRC(res); fib_combine_itag(itag, &res); #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -959,9 +962,11 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo break; case NETDEV_CHANGEMTU: case NETDEV_CHANGE: - case NETDEV_UNREGISTER_PERNET: rt_cache_flush(dev_net(dev), 0); break; + case NETDEV_UNREGISTER_BATCH: + rt_cache_flush_batch(); + break; } return NOTIFY_DONE; } diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 835262c2b867..ca2d07b1c706 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -284,7 +284,7 @@ static int fib_default_rules_init(struct fib_rules_ops *ops) { int err; - err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL, FIB_RULE_PERMANENT); + err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL, 0); if (err < 0) return err; err = fib_default_rule_add(ops, 0x7FFE, RT_TABLE_MAIN, 0); @@ -301,13 +301,9 @@ int __net_init fib4_rules_init(struct net *net) int err; struct fib_rules_ops *ops; - ops = kmemdup(&fib4_rules_ops_template, sizeof(*ops), GFP_KERNEL); - if (ops == NULL) - return -ENOMEM; - INIT_LIST_HEAD(&ops->rules_list); - ops->fro_net = net; - - fib_rules_register(ops); + ops = fib_rules_register(&fib4_rules_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); err = fib_default_rules_init(ops); if (err < 0) @@ -318,12 +314,10 @@ int __net_init fib4_rules_init(struct net *net) fail: /* also cleans all rules already added */ fib_rules_unregister(ops); - kfree(ops); return err; } void __net_exit fib4_rules_exit(struct net *net) { fib_rules_unregister(net->ipv4.rules_ops); - kfree(net->ipv4.rules_ops); } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 9b096d6ff3f2..ed19aa6919c2 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -228,7 +228,7 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi) head = &fib_info_hash[hash]; hlist_for_each_entry(fi, node, head, fib_hash) { - if (fi->fib_net != nfi->fib_net) + if (!net_eq(fi->fib_net, nfi->fib_net)) continue; if (fi->fib_nhs != nfi->fib_nhs) continue; @@ -1047,7 +1047,7 @@ int fib_sync_down_addr(struct net *net, __be32 local) return 0; hlist_for_each_entry(fi, node, head, fib_lhash) { - if (fi->fib_net != net) + if (!net_eq(fi->fib_net, net)) continue; if (fi->fib_prefsrc == local) { fi->fib_flags |= RTNH_F_DEAD; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6110c6d6e613..76c08402c933 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1899,8 +1899,9 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct err = -EADDRNOTAVAIL; for (pmc=inet->mc_list; pmc; pmc=pmc->next) { - if (pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr - && pmc->multi.imr_ifindex == imr.imr_ifindex) + if ((pmc->multi.imr_multiaddr.s_addr == + imr.imr_multiaddr.s_addr) && + (pmc->multi.imr_ifindex == imr.imr_ifindex)) break; } if (!pmc) { /* must have a prior join */ diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 26fb50e91311..ee16475f8fc3 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -112,7 +112,7 @@ again: hashinfo->bhash_size)]; spin_lock(&head->lock); inet_bind_bucket_for_each(tb, node, &head->chain) - if (ib_net(tb) == net && tb->port == rover) { + if (net_eq(ib_net(tb), net) && tb->port == rover) { if (tb->fastreuse > 0 && sk->sk_reuse && sk->sk_state != TCP_LISTEN && @@ -158,7 +158,7 @@ have_snum: hashinfo->bhash_size)]; spin_lock(&head->lock); inet_bind_bucket_for_each(tb, node, &head->chain) - if (ib_net(tb) == net && tb->port == snum) + if (net_eq(ib_net(tb), net) && tb->port == snum) goto tb_found; } tb = NULL; @@ -531,7 +531,7 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, &expire, &resend); if (!expire && (!resend || - !req->rsk_ops->rtx_syn_ack(parent, req) || + !req->rsk_ops->rtx_syn_ack(parent, req, NULL) || inet_rsk(req)->acked)) { unsigned long timeo; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 47ad7aab51e3..21e5e32d8c60 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -286,6 +286,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw; + int twrefcnt = 0; spin_lock(lock); @@ -318,20 +319,23 @@ unique: sk->sk_hash = hash; WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); + if (tw) { + twrefcnt = inet_twsk_unhash(tw); + NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); + } spin_unlock(lock); + if (twrefcnt) + inet_twsk_put(tw); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); if (twp) { *twp = tw; - NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); } else if (tw) { /* Silly. Should hash-dance instead... */ inet_twsk_deschedule(tw, death_row); - NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); inet_twsk_put(tw); } - return 0; not_unique: @@ -454,7 +458,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, * unique enough. */ inet_bind_bucket_for_each(tb, node, &head->chain) { - if (ib_net(tb) == net && tb->port == port) { + if (net_eq(ib_net(tb), net) && + tb->port == port) { if (tb->fastreuse >= 0) goto next_port; WARN_ON(hlist_empty(&tb->owners)); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 1f5d508bb18b..0fdf45e4c90c 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -14,22 +14,33 @@ #include <net/inet_timewait_sock.h> #include <net/ip.h> + +/* + * unhash a timewait socket from established hash + * lock must be hold by caller + */ +int inet_twsk_unhash(struct inet_timewait_sock *tw) +{ + if (hlist_nulls_unhashed(&tw->tw_node)) + return 0; + + hlist_nulls_del_rcu(&tw->tw_node); + sk_nulls_node_init(&tw->tw_node); + return 1; +} + /* Must be called with locally disabled BHs. */ static void __inet_twsk_kill(struct inet_timewait_sock *tw, struct inet_hashinfo *hashinfo) { struct inet_bind_hashbucket *bhead; struct inet_bind_bucket *tb; + int refcnt; /* Unlink from established hashes. */ spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash); spin_lock(lock); - if (hlist_nulls_unhashed(&tw->tw_node)) { - spin_unlock(lock); - return; - } - hlist_nulls_del_rcu(&tw->tw_node); - sk_nulls_node_init(&tw->tw_node); + refcnt = inet_twsk_unhash(tw); spin_unlock(lock); /* Disassociate with bind bucket. */ @@ -37,9 +48,12 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw, hashinfo->bhash_size)]; spin_lock(&bhead->lock); tb = tw->tw_tb; - __hlist_del(&tw->tw_bind_node); - tw->tw_tb = NULL; - inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); + if (tb) { + __hlist_del(&tw->tw_bind_node); + tw->tw_tb = NULL; + inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); + refcnt++; + } spin_unlock(&bhead->lock); #ifdef SOCK_REFCNT_DEBUG if (atomic_read(&tw->tw_refcnt) != 1) { @@ -47,7 +61,10 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw, tw->tw_prot->name, tw, atomic_read(&tw->tw_refcnt)); } #endif - inet_twsk_put(tw); + while (refcnt) { + inet_twsk_put(tw); + refcnt--; + } } static noinline void inet_twsk_free(struct inet_timewait_sock *tw) @@ -101,13 +118,22 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, * Should be done before removing sk from established chain * because readers are lockless and search established first. */ - atomic_inc(&tw->tw_refcnt); inet_twsk_add_node_rcu(tw, &ehead->twchain); /* Step 3: Remove SK from established hash. */ if (__sk_nulls_del_node_init_rcu(sk)) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + /* + * Notes : + * - We initially set tw_refcnt to 0 in inet_twsk_alloc() + * - We add one reference for the bhash link + * - We add one reference for the ehash link + * - We want this refcnt update done before allowing other + * threads to find this tw in ehash chain. + */ + atomic_add(1 + 1 + 1, &tw->tw_refcnt); + spin_unlock(lock); } @@ -139,7 +165,12 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat tw->tw_transparent = inet->transparent; tw->tw_prot = sk->sk_prot_creator; twsk_net_set(tw, hold_net(sock_net(sk))); - atomic_set(&tw->tw_refcnt, 1); + /* + * Because we use RCU lookups, we should not set tw_refcnt + * to a non null value before everything is setup for this + * timewait socket. + */ + atomic_set(&tw->tw_refcnt, 0); inet_twsk_dead_node_init(tw); __module_get(tw->tw_prot->owner); } @@ -421,37 +452,46 @@ out: EXPORT_SYMBOL_GPL(inet_twdr_twcal_tick); -void inet_twsk_purge(struct net *net, struct inet_hashinfo *hashinfo, +void inet_twsk_purge(struct inet_hashinfo *hashinfo, struct inet_timewait_death_row *twdr, int family) { struct inet_timewait_sock *tw; struct sock *sk; struct hlist_nulls_node *node; - int h; + unsigned int slot; - local_bh_disable(); - for (h = 0; h <= hashinfo->ehash_mask; h++) { - struct inet_ehash_bucket *head = - inet_ehash_bucket(hashinfo, h); - spinlock_t *lock = inet_ehash_lockp(hashinfo, h); + for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { + struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; +restart_rcu: + rcu_read_lock(); restart: - spin_lock(lock); - sk_nulls_for_each(sk, node, &head->twchain) { - + sk_nulls_for_each_rcu(sk, node, &head->twchain) { tw = inet_twsk(sk); - if (!net_eq(twsk_net(tw), net) || - tw->tw_family != family) + if ((tw->tw_family != family) || + atomic_read(&twsk_net(tw)->count)) + continue; + + if (unlikely(!atomic_inc_not_zero(&tw->tw_refcnt))) continue; - atomic_inc(&tw->tw_refcnt); - spin_unlock(lock); + if (unlikely((tw->tw_family != family) || + atomic_read(&twsk_net(tw)->count))) { + inet_twsk_put(tw); + goto restart; + } + + rcu_read_unlock(); inet_twsk_deschedule(tw, twdr); inet_twsk_put(tw); - - goto restart; + goto restart_rcu; } - spin_unlock(lock); + /* If the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot) + goto restart; + rcu_read_unlock(); } - local_bh_enable(); } EXPORT_SYMBOL_GPL(inet_twsk_purge); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b007f8af6e1f..c4735310a923 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -564,7 +564,7 @@ out_oversize: printk(KERN_INFO "Oversized IP packet from %pI4.\n", &qp->saddr); out_fail: - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_REASMFAILS); + IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS); return err; } @@ -658,7 +658,7 @@ static int ip4_frags_ns_ctl_register(struct net *net) struct ctl_table_header *hdr; table = ip4_frags_ns_ctl_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL); if (table == NULL) goto err_alloc; @@ -676,7 +676,7 @@ static int ip4_frags_ns_ctl_register(struct net *net) return 0; err_reg: - if (net != &init_net) + if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index c5f6af5d0f34..f36ce156cac6 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1309,17 +1309,8 @@ static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head) static int ipgre_init_net(struct net *net) { + struct ipgre_net *ign = net_generic(net, ipgre_net_id); int err; - struct ipgre_net *ign; - - err = -ENOMEM; - ign = kzalloc(sizeof(struct ipgre_net), GFP_KERNEL); - if (ign == NULL) - goto err_alloc; - - err = net_assign_generic(net, ipgre_net_id, ign); - if (err < 0) - goto err_assign; ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "gre0", ipgre_tunnel_setup); @@ -1340,10 +1331,6 @@ static int ipgre_init_net(struct net *net) err_reg_dev: free_netdev(ign->fb_tunnel_dev); err_alloc_dev: - /* nothing */ -err_assign: - kfree(ign); -err_alloc: return err; } @@ -1357,12 +1344,13 @@ static void ipgre_exit_net(struct net *net) ipgre_destroy_tunnels(ign, &list); unregister_netdevice_many(&list); rtnl_unlock(); - kfree(ign); } static struct pernet_operations ipgre_net_ops = { .init = ipgre_init_net, .exit = ipgre_exit_net, + .id = &ipgre_net_id, + .size = sizeof(struct ipgre_net), }; static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) @@ -1682,7 +1670,7 @@ static int __init ipgre_init(void) return -EAGAIN; } - err = register_pernet_gen_device(&ipgre_net_id, &ipgre_net_ops); + err = register_pernet_device(&ipgre_net_ops); if (err < 0) goto gen_device_failed; @@ -1700,7 +1688,7 @@ out: tap_ops_failed: rtnl_link_unregister(&ipgre_link_ops); rtnl_link_failed: - unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops); + unregister_pernet_device(&ipgre_net_ops); gen_device_failed: inet_del_protocol(&ipgre_protocol, IPPROTO_GRE); goto out; @@ -1710,7 +1698,7 @@ static void __exit ipgre_fini(void) { rtnl_link_unregister(&ipgre_tap_ops); rtnl_link_unregister(&ipgre_link_ops); - unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops); + unregister_pernet_device(&ipgre_net_ops); if (inet_del_protocol(&ipgre_protocol, IPPROTO_GRE) < 0) printk(KERN_INFO "ipgre close: can't remove protocol\n"); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index fdf51badc8e5..c29de9879fda 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -164,7 +164,7 @@ int ip_call_ra_chain(struct sk_buff *skb) if (sk && inet_sk(sk)->inet_num == protocol && (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dev->ifindex) && - sock_net(sk) == dev_net(dev)) { + net_eq(sock_net(sk), dev_net(dev))) { if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN)) { read_unlock(&ip_ra_lock); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b78e61502efe..e34013a78ef4 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -503,8 +503,8 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; - truesizes += frag->truesize; } + truesizes += frag->truesize; } /* Everything is OK. Generate! */ diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 7242ffcc44e5..eda04fed3379 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -775,17 +775,8 @@ static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head) static int ipip_init_net(struct net *net) { + struct ipip_net *ipn = net_generic(net, ipip_net_id); int err; - struct ipip_net *ipn; - - err = -ENOMEM; - ipn = kzalloc(sizeof(struct ipip_net), GFP_KERNEL); - if (ipn == NULL) - goto err_alloc; - - err = net_assign_generic(net, ipip_net_id, ipn); - if (err < 0) - goto err_assign; ipn->tunnels[0] = ipn->tunnels_wc; ipn->tunnels[1] = ipn->tunnels_l; @@ -812,29 +803,26 @@ err_reg_dev: free_netdev(ipn->fb_tunnel_dev); err_alloc_dev: /* nothing */ -err_assign: - kfree(ipn); -err_alloc: return err; } static void ipip_exit_net(struct net *net) { - struct ipip_net *ipn; + struct ipip_net *ipn = net_generic(net, ipip_net_id); LIST_HEAD(list); - ipn = net_generic(net, ipip_net_id); rtnl_lock(); ipip_destroy_tunnels(ipn, &list); unregister_netdevice_queue(ipn->fb_tunnel_dev, &list); unregister_netdevice_many(&list); rtnl_unlock(); - kfree(ipn); } static struct pernet_operations ipip_net_ops = { .init = ipip_init_net, .exit = ipip_exit_net, + .id = &ipip_net_id, + .size = sizeof(struct ipip_net), }; static int __init ipip_init(void) @@ -848,7 +836,7 @@ static int __init ipip_init(void) return -EAGAIN; } - err = register_pernet_gen_device(&ipip_net_id, &ipip_net_ops); + err = register_pernet_device(&ipip_net_ops); if (err) xfrm4_tunnel_deregister(&ipip_handler, AF_INET); @@ -860,7 +848,7 @@ static void __exit ipip_fini(void) if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET)) printk(KERN_INFO "ipip close: can't deregister tunnel\n"); - unregister_pernet_gen_device(ipip_net_id, &ipip_net_ops); + unregister_pernet_device(&ipip_net_ops); } module_init(ipip_init); diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 1725dc0ef688..f53cb8df4182 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -155,10 +155,10 @@ static int nf_ip_reroute(struct sk_buff *skb, if (entry->hook == NF_INET_LOCAL_OUT) { const struct iphdr *iph = ip_hdr(skb); - if (!(iph->tos == rt_info->tos - && skb->mark == rt_info->mark - && iph->daddr == rt_info->daddr - && iph->saddr == rt_info->saddr)) + if (!(iph->tos == rt_info->tos && + skb->mark == rt_info->mark && + iph->daddr == rt_info->daddr && + iph->saddr == rt_info->saddr)) return ip_route_me_harder(skb, RTN_UNSPEC); } return 0; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 27774c99d888..06632762ba5f 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -384,11 +384,11 @@ static int mark_source_chains(struct xt_table_info *newinfo, |= ((1 << hook) | (1 << NF_ARP_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct arpt_entry) - && (strcmp(t->target.u.user.name, - ARPT_STANDARD_TARGET) == 0) - && t->verdict < 0 - && unconditional(&e->arp)) || visited) { + if ((e->target_offset == sizeof(struct arpt_entry) && + (strcmp(t->target.u.user.name, + ARPT_STANDARD_TARGET) == 0) && + t->verdict < 0 && unconditional(&e->arp)) || + visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -427,8 +427,8 @@ static int mark_source_chains(struct xt_table_info *newinfo, int newpos = t->verdict; if (strcmp(t->target.u.user.name, - ARPT_STANDARD_TARGET) == 0 - && newpos >= 0) { + ARPT_STANDARD_TARGET) == 0 && + newpos >= 0) { if (newpos > newinfo->size - sizeof(struct arpt_entry)) { duprintf("mark_source_chains: " @@ -559,8 +559,8 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, { unsigned int h; - if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 - || (unsigned char *)e + sizeof(struct arpt_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 || + (unsigned char *)e + sizeof(struct arpt_entry) >= limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -1251,8 +1251,8 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, int ret, off, h; duprintf("check_compat_entry_size_and_hooks %p\n", e); - if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 - || (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 || + (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index c156db215987..49ad44712f46 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -497,10 +497,9 @@ ipq_rcv_nl_event(struct notifier_block *this, { struct netlink_notify *n = ptr; - if (event == NETLINK_URELEASE && - n->protocol == NETLINK_FIREWALL && n->pid) { + if (event == NETLINK_URELEASE && n->protocol == NETLINK_FIREWALL) { write_lock_bh(&queue_lock); - if ((n->net == &init_net) && (n->pid == peer_pid)) + if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid)) __ipq_reset(); write_unlock_bh(&queue_lock); } @@ -622,7 +621,7 @@ cleanup_netlink_notifier: static void __exit ip_queue_fini(void) { nf_unregister_queue_handlers(&nfqh); - synchronize_net(); + ipq_flush(NULL, 0); #ifdef CONFIG_SYSCTL diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index cde755d5eeab..572330a552ef 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -89,9 +89,9 @@ ip_packet_match(const struct iphdr *ip, #define FWINV(bool, invflg) ((bool) ^ !!(ipinfo->invflags & (invflg))) if (FWINV((ip->saddr&ipinfo->smsk.s_addr) != ipinfo->src.s_addr, - IPT_INV_SRCIP) - || FWINV((ip->daddr&ipinfo->dmsk.s_addr) != ipinfo->dst.s_addr, - IPT_INV_DSTIP)) { + IPT_INV_SRCIP) || + FWINV((ip->daddr&ipinfo->dmsk.s_addr) != ipinfo->dst.s_addr, + IPT_INV_DSTIP)) { dprintf("Source or dest mismatch.\n"); dprintf("SRC: %pI4. Mask: %pI4. Target: %pI4.%s\n", @@ -122,8 +122,8 @@ ip_packet_match(const struct iphdr *ip, } /* Check specific protocol */ - if (ipinfo->proto - && FWINV(ip->protocol != ipinfo->proto, IPT_INV_PROTO)) { + if (ipinfo->proto && + FWINV(ip->protocol != ipinfo->proto, IPT_INV_PROTO)) { dprintf("Packet protocol %hi does not match %hi.%s\n", ip->protocol, ipinfo->proto, ipinfo->invflags&IPT_INV_PROTO ? " (INV)":""); @@ -246,11 +246,11 @@ get_chainname_rulenum(struct ipt_entry *s, struct ipt_entry *e, } else if (s == e) { (*rulenum)++; - if (s->target_offset == sizeof(struct ipt_entry) - && strcmp(t->target.u.kernel.target->name, - IPT_STANDARD_TARGET) == 0 - && t->verdict < 0 - && unconditional(&s->ip)) { + if (s->target_offset == sizeof(struct ipt_entry) && + strcmp(t->target.u.kernel.target->name, + IPT_STANDARD_TARGET) == 0 && + t->verdict < 0 && + unconditional(&s->ip)) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP_TRACE_COMMENT_POLICY] @@ -388,8 +388,8 @@ ipt_do_table(struct sk_buff *skb, back = get_entry(table_base, back->comefrom); continue; } - if (table_base + v != ipt_next_entry(e) - && !(e->ip.flags & IPT_F_GOTO)) { + if (table_base + v != ipt_next_entry(e) && + !(e->ip.flags & IPT_F_GOTO)) { /* Save old back ptr in next entry */ struct ipt_entry *next = ipt_next_entry(e); next->comefrom = (void *)back - table_base; @@ -473,11 +473,11 @@ mark_source_chains(struct xt_table_info *newinfo, e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct ipt_entry) - && (strcmp(t->target.u.user.name, - IPT_STANDARD_TARGET) == 0) - && t->verdict < 0 - && unconditional(&e->ip)) || visited) { + if ((e->target_offset == sizeof(struct ipt_entry) && + (strcmp(t->target.u.user.name, + IPT_STANDARD_TARGET) == 0) && + t->verdict < 0 && unconditional(&e->ip)) || + visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -524,8 +524,8 @@ mark_source_chains(struct xt_table_info *newinfo, int newpos = t->verdict; if (strcmp(t->target.u.user.name, - IPT_STANDARD_TARGET) == 0 - && newpos >= 0) { + IPT_STANDARD_TARGET) == 0 && + newpos >= 0) { if (newpos > newinfo->size - sizeof(struct ipt_entry)) { duprintf("mark_source_chains: " @@ -735,8 +735,8 @@ check_entry_size_and_hooks(struct ipt_entry *e, { unsigned int h; - if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 - || (unsigned char *)e + sizeof(struct ipt_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 || + (unsigned char *)e + sizeof(struct ipt_entry) >= limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -1548,8 +1548,8 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, int ret, off, h; duprintf("check_compat_entry_size_and_hooks %p\n", e); - if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 - || (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 || + (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 2e4f98b85524..40ca2d240abb 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -303,9 +303,9 @@ clusterip_tg(struct sk_buff *skb, const struct xt_target_param *par) /* special case: ICMP error handling. conntrack distinguishes between * error messages (RELATED) and information requests (see below) */ - if (ip_hdr(skb)->protocol == IPPROTO_ICMP - && (ctinfo == IP_CT_RELATED - || ctinfo == IP_CT_RELATED+IP_CT_IS_REPLY)) + if (ip_hdr(skb)->protocol == IPPROTO_ICMP && + (ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)) return XT_CONTINUE; /* ip_conntrack_icmp guarantees us that we only have ICMP_ECHO, @@ -362,8 +362,8 @@ static bool clusterip_tg_check(const struct xt_tgchk_param *par) return false; } - if (e->ip.dmsk.s_addr != htonl(0xffffffff) - || e->ip.dst.s_addr == 0) { + if (e->ip.dmsk.s_addr != htonl(0xffffffff) || + e->ip.dst.s_addr == 0) { printk(KERN_ERR "CLUSTERIP: Please specify destination IP\n"); return false; } @@ -495,14 +495,14 @@ arp_mangle(unsigned int hook, struct clusterip_config *c; /* we don't care about non-ethernet and non-ipv4 ARP */ - if (arp->ar_hrd != htons(ARPHRD_ETHER) - || arp->ar_pro != htons(ETH_P_IP) - || arp->ar_pln != 4 || arp->ar_hln != ETH_ALEN) + if (arp->ar_hrd != htons(ARPHRD_ETHER) || + arp->ar_pro != htons(ETH_P_IP) || + arp->ar_pln != 4 || arp->ar_hln != ETH_ALEN) return NF_ACCEPT; /* we only want to mangle arp requests and replies */ - if (arp->ar_op != htons(ARPOP_REPLY) - && arp->ar_op != htons(ARPOP_REQUEST)) + if (arp->ar_op != htons(ARPOP_REPLY) && + arp->ar_op != htons(ARPOP_REQUEST)) return NF_ACCEPT; payload = (void *)(arp+1); diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index f7e2fa0974dc..549e206cdd42 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -85,8 +85,8 @@ ecn_tg(struct sk_buff *skb, const struct xt_target_param *par) if (!set_ect_ip(skb, einfo)) return NF_DROP; - if (einfo->operation & (IPT_ECN_OP_SET_ECE | IPT_ECN_OP_SET_CWR) - && ip_hdr(skb)->protocol == IPPROTO_TCP) + if (einfo->operation & (IPT_ECN_OP_SET_ECE | IPT_ECN_OP_SET_CWR) && + ip_hdr(skb)->protocol == IPPROTO_TCP) if (!set_ect_tcp(skb, einfo)) return NF_DROP; @@ -108,8 +108,8 @@ static bool ecn_tg_check(const struct xt_tgchk_param *par) einfo->ip_ect); return false; } - if ((einfo->operation & (IPT_ECN_OP_SET_ECE|IPT_ECN_OP_SET_CWR)) - && (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO))) { + if ((einfo->operation & (IPT_ECN_OP_SET_ECE|IPT_ECN_OP_SET_CWR)) && + (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO))) { printk(KERN_WARNING "ECN: cannot use TCP operations on a " "non-tcp rule\n"); return false; diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index acc44c69eb68..ee128efa1c8d 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -74,8 +74,8 @@ static void dump_packet(const struct nf_loginfo *info, if (ntohs(ih->frag_off) & IP_OFFSET) printk("FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); - if ((logflags & IPT_LOG_IPOPT) - && ih->ihl * 4 > sizeof(struct iphdr)) { + if ((logflags & IPT_LOG_IPOPT) && + ih->ihl * 4 > sizeof(struct iphdr)) { const unsigned char *op; unsigned char _opt[4 * 15 - sizeof(struct iphdr)]; unsigned int i, optsize; @@ -146,8 +146,8 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 11 "URGP=65535 " */ printk("URGP=%u ", ntohs(th->urg_ptr)); - if ((logflags & IPT_LOG_TCPOPT) - && th->doff * 4 > sizeof(struct tcphdr)) { + if ((logflags & IPT_LOG_TCPOPT) && + th->doff * 4 > sizeof(struct tcphdr)) { unsigned char _opt[4 * 15 - sizeof(struct tcphdr)]; const unsigned char *op; unsigned int i, optsize; @@ -238,9 +238,9 @@ static void dump_packet(const struct nf_loginfo *info, printk("TYPE=%u CODE=%u ", ich->type, ich->code); /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - if (ich->type <= NR_ICMP_TYPES - && required_len[ich->type] - && skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) { + if (ich->type <= NR_ICMP_TYPES && + required_len[ich->type] && + skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) { printk("INCOMPLETE [%u bytes] ", skb->len - iphoff - ih->ihl*4); break; @@ -276,8 +276,8 @@ static void dump_packet(const struct nf_loginfo *info, } /* Max length: 10 "MTU=65535 " */ - if (ich->type == ICMP_DEST_UNREACH - && ich->code == ICMP_FRAG_NEEDED) + if (ich->type == ICMP_DEST_UNREACH && + ich->code == ICMP_FRAG_NEEDED) printk("MTU=%u ", ntohs(ich->un.frag.mtu)); } break; @@ -407,8 +407,8 @@ ipt_log_packet(u_int8_t pf, if (in && !out) { /* MAC logging for input chain only. */ printk("MAC="); - if (skb->dev && skb->dev->hard_header_len - && skb->mac_header != skb->network_header) { + if (skb->dev && skb->dev->hard_header_len && + skb->mac_header != skb->network_header) { int i; const unsigned char *p = skb_mac_header(skb); for (i = 0; i < skb->dev->hard_header_len; i++,p++) diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index dada0863946d..650b54042b01 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -59,8 +59,8 @@ masquerade_tg(struct sk_buff *skb, const struct xt_target_param *par) ct = nf_ct_get(skb, &ctinfo); nat = nfct_nat(ct); - NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED - || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)); + NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)); /* Source address is 0.0.0.0 - locally generated packet that is * probably not supposed to be masqueraded. diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index c93ae44bff2a..5113b8f1a379 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -184,8 +184,8 @@ static bool reject_tg_check(const struct xt_tgchk_param *par) return false; } else if (rejinfo->with == IPT_TCP_RESET) { /* Must specify that it's a TCP packet */ - if (e->ip.proto != IPPROTO_TCP - || (e->ip.invflags & XT_INV_PROTO)) { + if (e->ip.proto != IPPROTO_TCP || + (e->ip.invflags & XT_INV_PROTO)) { printk("ipt_REJECT: TCP_RESET invalid for non-tcp\n"); return false; } diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index d32cc4bb328a..399061c3fd7d 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -226,9 +226,9 @@ static void ipt_ulog_packet(unsigned int hooknum, else *(pm->prefix) = '\0'; - if (in && in->hard_header_len > 0 - && skb->mac_header != skb->network_header - && in->hard_header_len <= ULOG_MAC_LEN) { + if (in && in->hard_header_len > 0 && + skb->mac_header != skb->network_header && + in->hard_header_len <= ULOG_MAC_LEN) { memcpy(pm->mac, skb_mac_header(skb), in->hard_header_len); pm->mac_len = in->hard_header_len; } else diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c index 6289b64144c6..2a1e56b71908 100644 --- a/net/ipv4/netfilter/ipt_ecn.c +++ b/net/ipv4/netfilter/ipt_ecn.c @@ -96,8 +96,8 @@ static bool ecn_mt_check(const struct xt_mtchk_param *par) if (info->invert & IPT_ECN_OP_MATCH_MASK) return false; - if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR) - && ip->proto != IPPROTO_TCP) { + if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR) && + ip->proto != IPPROTO_TCP) { printk(KERN_WARNING "ipt_ecn: can't match TCP bits in rule for" " non-tcp packets\n"); return false; diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 036047f9b0f2..fae78c3076c4 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -130,8 +130,8 @@ ipt_local_hook(unsigned int hook, u_int32_t mark; /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) - || ip_hdrlen(skb) < sizeof(struct iphdr)) + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; /* Save things which could affect route */ diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 99eb76c65d25..3bd3d6388da5 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -94,8 +94,8 @@ ipt_local_out_hook(unsigned int hook, int (*okfn)(struct sk_buff *)) { /* Somebody is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) - || ip_hdrlen(skb) < sizeof(struct iphdr)) + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; return ipt_do_table(skb, hook, in, out, dev_net(out)->ipv4.iptable_security); diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index d71ba7677344..e3dd93623df8 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -54,8 +54,8 @@ static const u_int8_t invmap[] = { static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig) { - if (orig->dst.u.icmp.type >= sizeof(invmap) - || !invmap[orig->dst.u.icmp.type]) + if (orig->dst.u.icmp.type >= sizeof(invmap) || + !invmap[orig->dst.u.icmp.type]) return false; tuple->src.u.icmp.id = orig->src.u.icmp.id; @@ -101,8 +101,8 @@ static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb, [ICMP_ADDRESS] = 1 }; - if (ct->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) - || !valid_new[ct->tuplehash[0].tuple.dst.u.icmp.type]) { + if (ct->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) || + !valid_new[ct->tuplehash[0].tuple.dst.u.icmp.type]) { /* Can't create a new ICMP `conn' with this. */ pr_debug("icmp: can't create new conn with type %u\n", ct->tuplehash[0].tuple.dst.u.icmp.type); @@ -201,11 +201,11 @@ icmp_error(struct net *net, struct sk_buff *skb, unsigned int dataoff, } /* Need to track icmp error message? */ - if (icmph->type != ICMP_DEST_UNREACH - && icmph->type != ICMP_SOURCE_QUENCH - && icmph->type != ICMP_TIME_EXCEEDED - && icmph->type != ICMP_PARAMETERPROB - && icmph->type != ICMP_REDIRECT) + if (icmph->type != ICMP_DEST_UNREACH && + icmph->type != ICMP_SOURCE_QUENCH && + icmph->type != ICMP_TIME_EXCEEDED && + icmph->type != ICMP_PARAMETERPROB && + icmph->type != ICMP_REDIRECT) return NF_ACCEPT; return icmp_error_message(net, skb, ctinfo, hooknum); @@ -238,17 +238,17 @@ static const struct nla_policy icmp_nla_policy[CTA_PROTO_MAX+1] = { static int icmp_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *tuple) { - if (!tb[CTA_PROTO_ICMP_TYPE] - || !tb[CTA_PROTO_ICMP_CODE] - || !tb[CTA_PROTO_ICMP_ID]) + if (!tb[CTA_PROTO_ICMP_TYPE] || + !tb[CTA_PROTO_ICMP_CODE] || + !tb[CTA_PROTO_ICMP_ID]) return -EINVAL; tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]); tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]); tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]); - if (tuple->dst.u.icmp.type >= sizeof(invmap) - || !invmap[tuple->dst.u.icmp.type]) + if (tuple->dst.u.icmp.type >= sizeof(invmap) || + !invmap[tuple->dst.u.icmp.type]) return -EINVAL; return 0; diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index f9520fa3aba9..7f10a6be0191 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -41,18 +41,14 @@ adjust_tcp_sequence(u32 seq, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - int dir; - struct nf_nat_seq *this_way, *other_way; + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_nat_seq *this_way = &nat->seq[dir]; - pr_debug("adjust_tcp_sequence: seq = %u, sizediff = %d\n", seq, seq); - - dir = CTINFO2DIR(ctinfo); - - this_way = &nat->seq[dir]; - other_way = &nat->seq[!dir]; + pr_debug("adjust_tcp_sequence: seq = %u, sizediff = %d\n", + seq, sizediff); - pr_debug("nf_nat_resize_packet: Seq_offset before: "); + pr_debug("adjust_tcp_sequence: Seq_offset before: "); DUMP_OFFSET(this_way); spin_lock_bh(&nf_nat_seqofs_lock); @@ -63,13 +59,13 @@ adjust_tcp_sequence(u32 seq, * retransmit */ if (this_way->offset_before == this_way->offset_after || before(this_way->correction_pos, seq)) { - this_way->correction_pos = seq; - this_way->offset_before = this_way->offset_after; - this_way->offset_after += sizediff; + this_way->correction_pos = seq; + this_way->offset_before = this_way->offset_after; + this_way->offset_after += sizediff; } spin_unlock_bh(&nf_nat_seqofs_lock); - pr_debug("nf_nat_resize_packet: Seq_offset after: "); + pr_debug("adjust_tcp_sequence: Seq_offset after: "); DUMP_OFFSET(this_way); } diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index 5f41d017ddd8..5678e9562c15 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -197,11 +197,11 @@ nf_nat_out(unsigned int hooknum, (ct = nf_ct_get(skb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - if (ct->tuplehash[dir].tuple.src.u3.ip != - ct->tuplehash[!dir].tuple.dst.u3.ip - || ct->tuplehash[dir].tuple.src.u.all != - ct->tuplehash[!dir].tuple.dst.u.all - ) + if ((ct->tuplehash[dir].tuple.src.u3.ip != + ct->tuplehash[!dir].tuple.dst.u3.ip) || + (ct->tuplehash[dir].tuple.src.u.all != + ct->tuplehash[!dir].tuple.dst.u.all) + ) return ip_xfrm_me_harder(skb) == 0 ? ret : NF_DROP; } #endif diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 7547944ea9bf..90cdcfc32937 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -513,43 +513,42 @@ static const struct file_operations rt_cpu_seq_fops = { }; #ifdef CONFIG_NET_CLS_ROUTE -static int ip_rt_acct_read(char *buffer, char **start, off_t offset, - int length, int *eof, void *data) -{ - unsigned int i; - - if ((offset & 3) || (length & 3)) - return -EIO; - - if (offset >= sizeof(struct ip_rt_acct) * 256) { - *eof = 1; - return 0; - } - - if (offset + length >= sizeof(struct ip_rt_acct) * 256) { - length = sizeof(struct ip_rt_acct) * 256 - offset; - *eof = 1; +static int rt_acct_proc_show(struct seq_file *m, void *v) +{ + struct ip_rt_acct *dst, *src; + unsigned int i, j; + + dst = kcalloc(256, sizeof(struct ip_rt_acct), GFP_KERNEL); + if (!dst) + return -ENOMEM; + + for_each_possible_cpu(i) { + src = (struct ip_rt_acct *)per_cpu_ptr(ip_rt_acct, i); + for (j = 0; j < 256; j++) { + dst[j].o_bytes += src[j].o_bytes; + dst[j].o_packets += src[j].o_packets; + dst[j].i_bytes += src[j].i_bytes; + dst[j].i_packets += src[j].i_packets; + } } - offset /= sizeof(u32); - - if (length > 0) { - u32 *dst = (u32 *) buffer; - - *start = buffer; - memset(dst, 0, length); - - for_each_possible_cpu(i) { - unsigned int j; - u32 *src; + seq_write(m, dst, 256 * sizeof(struct ip_rt_acct)); + kfree(dst); + return 0; +} - src = ((u32 *) per_cpu_ptr(ip_rt_acct, i)) + offset; - for (j = 0; j < length/4; j++) - dst[j] += src[j]; - } - } - return length; +static int rt_acct_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, rt_acct_proc_show, NULL); } + +static const struct file_operations rt_acct_proc_fops = { + .owner = THIS_MODULE, + .open = rt_acct_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; #endif static int __net_init ip_rt_do_proc_init(struct net *net) @@ -567,8 +566,7 @@ static int __net_init ip_rt_do_proc_init(struct net *net) goto err2; #ifdef CONFIG_NET_CLS_ROUTE - pde = create_proc_read_entry("rt_acct", 0, net->proc_net, - ip_rt_acct_read, NULL); + pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops); if (!pde) goto err3; #endif @@ -703,7 +701,7 @@ static inline int compare_keys(struct flowi *fl1, struct flowi *fl2) static inline int compare_netns(struct rtable *rt1, struct rtable *rt2) { - return dev_net(rt1->u.dst.dev) == dev_net(rt2->u.dst.dev); + return net_eq(dev_net(rt1->u.dst.dev), dev_net(rt2->u.dst.dev)); } static inline int rt_is_expired(struct rtable *rth) @@ -902,6 +900,12 @@ void rt_cache_flush(struct net *net, int delay) rt_do_flush(!in_softirq()); } +/* Flush previous cache invalidated entries from the cache */ +void rt_cache_flush_batch(void) +{ + rt_do_flush(!in_softirq()); +} + /* * We change rt_genid and let gc do the cleanup */ @@ -3310,7 +3314,7 @@ static __net_init int sysctl_route_net_init(struct net *net) struct ctl_table *tbl; tbl = ipv4_route_flush_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL); if (tbl == NULL) goto err_dup; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 3146cc401748..26399ad2a289 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -253,6 +253,8 @@ EXPORT_SYMBOL(cookie_check_timestamp); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, struct ip_options *opt) { + struct tcp_options_received tcp_opt; + u8 *hash_location; struct inet_request_sock *ireq; struct tcp_request_sock *treq; struct tcp_sock *tp = tcp_sk(sk); @@ -263,7 +265,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, int mss; struct rtable *rt; __u8 rcv_wscale; - struct tcp_options_received tcp_opt; if (!sysctl_tcp_syncookies || !th->ack) goto out; @@ -341,7 +342,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, 0, &rt->u.dst); + tcp_parse_options(skb, &tcp_opt, &hash_location, 0, &rt->u.dst); if (tcp_opt.saw_tstamp) cookie_check_timestamp(&tcp_opt); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 2dcf04d9b005..13f7ab6ad6a0 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -714,6 +714,14 @@ static struct ctl_table ipv4_table[] = { }, { .ctl_name = CTL_UNNUMBERED, + .procname = "tcp_cookie_size", + .data = &sysctl_tcp_cookie_size, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .ctl_name = CTL_UNNUMBERED, .procname = "udp_mem", .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), @@ -818,7 +826,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) struct ctl_table *table; table = ipv4_net_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(ipv4_net_table), GFP_KERNEL); if (table == NULL) goto err_alloc; @@ -849,7 +857,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) return 0; err_reg: - if (net != &init_net) + if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 524f9760193b..c8666b70cde0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -264,6 +264,7 @@ #include <linux/cache.h> #include <linux/err.h> #include <linux/crypto.h> +#include <linux/time.h> #include <net/icmp.h> #include <net/tcp.h> @@ -2059,6 +2060,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; tp->bytes_acked = 0; + tp->window_clamp = 0; tcp_set_ca_state(sk, TCP_CA_Open); tcp_clear_retrans(tp); inet_csk_delack_init(sk); @@ -2083,8 +2085,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int val; int err = 0; - /* This is a string value all the others are int's */ - if (optname == TCP_CONGESTION) { + /* These are data/string values, all the others are ints */ + switch (optname) { + case TCP_CONGESTION: { char name[TCP_CA_NAME_MAX]; if (optlen < 1) @@ -2101,6 +2104,93 @@ static int do_tcp_setsockopt(struct sock *sk, int level, release_sock(sk); return err; } + case TCP_COOKIE_TRANSACTIONS: { + struct tcp_cookie_transactions ctd; + struct tcp_cookie_values *cvp = NULL; + + if (sizeof(ctd) > optlen) + return -EINVAL; + if (copy_from_user(&ctd, optval, sizeof(ctd))) + return -EFAULT; + + if (ctd.tcpct_used > sizeof(ctd.tcpct_value) || + ctd.tcpct_s_data_desired > TCP_MSS_DESIRED) + return -EINVAL; + + if (ctd.tcpct_cookie_desired == 0) { + /* default to global value */ + } else if ((0x1 & ctd.tcpct_cookie_desired) || + ctd.tcpct_cookie_desired > TCP_COOKIE_MAX || + ctd.tcpct_cookie_desired < TCP_COOKIE_MIN) { + return -EINVAL; + } + + if (TCP_COOKIE_OUT_NEVER & ctd.tcpct_flags) { + /* Supercedes all other values */ + lock_sock(sk); + if (tp->cookie_values != NULL) { + kref_put(&tp->cookie_values->kref, + tcp_cookie_values_release); + tp->cookie_values = NULL; + } + tp->rx_opt.cookie_in_always = 0; /* false */ + tp->rx_opt.cookie_out_never = 1; /* true */ + release_sock(sk); + return err; + } + + /* Allocate ancillary memory before locking. + */ + if (ctd.tcpct_used > 0 || + (tp->cookie_values == NULL && + (sysctl_tcp_cookie_size > 0 || + ctd.tcpct_cookie_desired > 0 || + ctd.tcpct_s_data_desired > 0))) { + cvp = kzalloc(sizeof(*cvp) + ctd.tcpct_used, + GFP_KERNEL); + if (cvp == NULL) + return -ENOMEM; + } + lock_sock(sk); + tp->rx_opt.cookie_in_always = + (TCP_COOKIE_IN_ALWAYS & ctd.tcpct_flags); + tp->rx_opt.cookie_out_never = 0; /* false */ + + if (tp->cookie_values != NULL) { + if (cvp != NULL) { + /* Changed values are recorded by a changed + * pointer, ensuring the cookie will differ, + * without separately hashing each value later. + */ + kref_put(&tp->cookie_values->kref, + tcp_cookie_values_release); + kref_init(&cvp->kref); + tp->cookie_values = cvp; + } else { + cvp = tp->cookie_values; + } + } + if (cvp != NULL) { + cvp->cookie_desired = ctd.tcpct_cookie_desired; + + if (ctd.tcpct_used > 0) { + memcpy(cvp->s_data_payload, ctd.tcpct_value, + ctd.tcpct_used); + cvp->s_data_desired = ctd.tcpct_used; + cvp->s_data_constant = 1; /* true */ + } else { + /* No constant payload data. */ + cvp->s_data_desired = ctd.tcpct_s_data_desired; + cvp->s_data_constant = 0; /* false */ + } + } + release_sock(sk); + return err; + } + default: + /* fallthru */ + break; + }; if (optlen < sizeof(int)) return -EINVAL; @@ -2425,6 +2515,47 @@ static int do_tcp_getsockopt(struct sock *sk, int level, if (copy_to_user(optval, icsk->icsk_ca_ops->name, len)) return -EFAULT; return 0; + + case TCP_COOKIE_TRANSACTIONS: { + struct tcp_cookie_transactions ctd; + struct tcp_cookie_values *cvp = tp->cookie_values; + + if (get_user(len, optlen)) + return -EFAULT; + if (len < sizeof(ctd)) + return -EINVAL; + + memset(&ctd, 0, sizeof(ctd)); + ctd.tcpct_flags = (tp->rx_opt.cookie_in_always ? + TCP_COOKIE_IN_ALWAYS : 0) + | (tp->rx_opt.cookie_out_never ? + TCP_COOKIE_OUT_NEVER : 0); + + if (cvp != NULL) { + ctd.tcpct_flags |= (cvp->s_data_in ? + TCP_S_DATA_IN : 0) + | (cvp->s_data_out ? + TCP_S_DATA_OUT : 0); + + ctd.tcpct_cookie_desired = cvp->cookie_desired; + ctd.tcpct_s_data_desired = cvp->s_data_desired; + + /* Cookie(s) saved, return as nonce */ + if (sizeof(ctd.tcpct_value) < cvp->cookie_pair_size) { + /* impossible? */ + return -EINVAL; + } + memcpy(&ctd.tcpct_value[0], &cvp->cookie_pair[0], + cvp->cookie_pair_size); + ctd.tcpct_used = cvp->cookie_pair_size; + } + + if (put_user(sizeof(ctd), optlen)) + return -EFAULT; + if (copy_to_user(optval, &ctd, sizeof(ctd))) + return -EFAULT; + return 0; + } default: return -ENOPROTOOPT; } @@ -2847,6 +2978,135 @@ EXPORT_SYMBOL(tcp_md5_hash_key); #endif +/** + * Each Responder maintains up to two secret values concurrently for + * efficient secret rollover. Each secret value has 4 states: + * + * Generating. (tcp_secret_generating != tcp_secret_primary) + * Generates new Responder-Cookies, but not yet used for primary + * verification. This is a short-term state, typically lasting only + * one round trip time (RTT). + * + * Primary. (tcp_secret_generating == tcp_secret_primary) + * Used both for generation and primary verification. + * + * Retiring. (tcp_secret_retiring != tcp_secret_secondary) + * Used for verification, until the first failure that can be + * verified by the newer Generating secret. At that time, this + * cookie's state is changed to Secondary, and the Generating + * cookie's state is changed to Primary. This is a short-term state, + * typically lasting only one round trip time (RTT). + * + * Secondary. (tcp_secret_retiring == tcp_secret_secondary) + * Used for secondary verification, after primary verification + * failures. This state lasts no more than twice the Maximum Segment + * Lifetime (2MSL). Then, the secret is discarded. + */ +struct tcp_cookie_secret { + /* The secret is divided into two parts. The digest part is the + * equivalent of previously hashing a secret and saving the state, + * and serves as an initialization vector (IV). The message part + * serves as the trailing secret. + */ + u32 secrets[COOKIE_WORKSPACE_WORDS]; + unsigned long expires; +}; + +#define TCP_SECRET_1MSL (HZ * TCP_PAWS_MSL) +#define TCP_SECRET_2MSL (HZ * TCP_PAWS_MSL * 2) +#define TCP_SECRET_LIFE (HZ * 600) + +static struct tcp_cookie_secret tcp_secret_one; +static struct tcp_cookie_secret tcp_secret_two; + +/* Essentially a circular list, without dynamic allocation. */ +static struct tcp_cookie_secret *tcp_secret_generating; +static struct tcp_cookie_secret *tcp_secret_primary; +static struct tcp_cookie_secret *tcp_secret_retiring; +static struct tcp_cookie_secret *tcp_secret_secondary; + +static DEFINE_SPINLOCK(tcp_secret_locker); + +/* Select a pseudo-random word in the cookie workspace. + */ +static inline u32 tcp_cookie_work(const u32 *ws, const int n) +{ + return ws[COOKIE_DIGEST_WORDS + ((COOKIE_MESSAGE_WORDS-1) & ws[n])]; +} + +/* Fill bakery[COOKIE_WORKSPACE_WORDS] with generator, updating as needed. + * Called in softirq context. + * Returns: 0 for success. + */ +int tcp_cookie_generator(u32 *bakery) +{ + unsigned long jiffy = jiffies; + + if (unlikely(time_after_eq(jiffy, tcp_secret_generating->expires))) { + spin_lock_bh(&tcp_secret_locker); + if (!time_after_eq(jiffy, tcp_secret_generating->expires)) { + /* refreshed by another */ + memcpy(bakery, + &tcp_secret_generating->secrets[0], + COOKIE_WORKSPACE_WORDS); + } else { + /* still needs refreshing */ + get_random_bytes(bakery, COOKIE_WORKSPACE_WORDS); + + /* The first time, paranoia assumes that the + * randomization function isn't as strong. But, + * this secret initialization is delayed until + * the last possible moment (packet arrival). + * Although that time is observable, it is + * unpredictably variable. Mash in the most + * volatile clock bits available, and expire the + * secret extra quickly. + */ + if (unlikely(tcp_secret_primary->expires == + tcp_secret_secondary->expires)) { + struct timespec tv; + + getnstimeofday(&tv); + bakery[COOKIE_DIGEST_WORDS+0] ^= + (u32)tv.tv_nsec; + + tcp_secret_secondary->expires = jiffy + + TCP_SECRET_1MSL + + (0x0f & tcp_cookie_work(bakery, 0)); + } else { + tcp_secret_secondary->expires = jiffy + + TCP_SECRET_LIFE + + (0xff & tcp_cookie_work(bakery, 1)); + tcp_secret_primary->expires = jiffy + + TCP_SECRET_2MSL + + (0x1f & tcp_cookie_work(bakery, 2)); + } + memcpy(&tcp_secret_secondary->secrets[0], + bakery, COOKIE_WORKSPACE_WORDS); + + rcu_assign_pointer(tcp_secret_generating, + tcp_secret_secondary); + rcu_assign_pointer(tcp_secret_retiring, + tcp_secret_primary); + /* + * Neither call_rcu() nor synchronize_rcu() needed. + * Retiring data is not freed. It is replaced after + * further (locked) pointer updates, and a quiet time + * (minimum 1MSL, maximum LIFE - 2MSL). + */ + } + spin_unlock_bh(&tcp_secret_locker); + } else { + rcu_read_lock_bh(); + memcpy(bakery, + &rcu_dereference(tcp_secret_generating)->secrets[0], + COOKIE_WORKSPACE_WORDS); + rcu_read_unlock_bh(); + } + return 0; +} +EXPORT_SYMBOL(tcp_cookie_generator); + void tcp_done(struct sock *sk) { if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) @@ -2881,6 +3141,7 @@ void __init tcp_init(void) struct sk_buff *skb = NULL; unsigned long nr_pages, limit; int order, i, max_share; + unsigned long jiffy = jiffies; BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb)); @@ -2974,6 +3235,15 @@ void __init tcp_init(void) tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size); tcp_register_congestion_control(&tcp_reno); + + memset(&tcp_secret_one.secrets[0], 0, sizeof(tcp_secret_one.secrets)); + memset(&tcp_secret_two.secrets[0], 0, sizeof(tcp_secret_two.secrets)); + tcp_secret_one.expires = jiffy; /* past due */ + tcp_secret_two.expires = jiffy; /* past due */ + tcp_secret_generating = &tcp_secret_one; + tcp_secret_primary = &tcp_secret_one; + tcp_secret_retiring = &tcp_secret_two; + tcp_secret_secondary = &tcp_secret_two; } EXPORT_SYMBOL(tcp_close); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index fcbcd4ff6c5f..939edb3b8e4d 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -27,7 +27,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, r->idiag_rqueue = sk->sk_ack_backlog; r->idiag_wqueue = sk->sk_max_ack_backlog; } else { - r->idiag_rqueue = tp->rcv_nxt - tp->copied_seq; + r->idiag_rqueue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); r->idiag_wqueue = tp->write_seq - tp->snd_una; } if (info != NULL) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index be166e0e11c5..57ae96a04220 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3698,7 +3698,7 @@ old_ack: * the fast version below fails. */ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, - int estab, struct dst_entry *dst) + u8 **hvpp, int estab, struct dst_entry *dst) { unsigned char *ptr; struct tcphdr *th = tcp_hdr(skb); @@ -3785,7 +3785,30 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, */ break; #endif - } + case TCPOPT_COOKIE: + /* This option is variable length. + */ + switch (opsize) { + case TCPOLEN_COOKIE_BASE: + /* not yet implemented */ + break; + case TCPOLEN_COOKIE_PAIR: + /* not yet implemented */ + break; + case TCPOLEN_COOKIE_MIN+0: + case TCPOLEN_COOKIE_MIN+2: + case TCPOLEN_COOKIE_MIN+4: + case TCPOLEN_COOKIE_MIN+6: + case TCPOLEN_COOKIE_MAX: + /* 16-bit multiple */ + opt_rx->cookie_plus = opsize; + *hvpp = ptr; + default: + /* ignore option */ + break; + }; + break; + }; ptr += opsize-2; length -= opsize; @@ -3813,17 +3836,20 @@ static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th) * If it is wrong it falls back on tcp_parse_options(). */ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th, - struct tcp_sock *tp) + struct tcp_sock *tp, u8 **hvpp) { - if (th->doff == sizeof(struct tcphdr) >> 2) { + /* In the spirit of fast parsing, compare doff directly to constant + * values. Because equality is used, short doff can be ignored here. + */ + if (th->doff == (sizeof(*th) / 4)) { tp->rx_opt.saw_tstamp = 0; return 0; } else if (tp->rx_opt.tstamp_ok && - th->doff == (sizeof(struct tcphdr)>>2)+(TCPOLEN_TSTAMP_ALIGNED>>2)) { + th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) { if (tcp_parse_aligned_timestamp(tp, th)) return 1; } - tcp_parse_options(skb, &tp->rx_opt, 1, NULL); + tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL); return 1; } @@ -5077,10 +5103,12 @@ out: static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, struct tcphdr *th, int syn_inerr) { + u8 *hash_location; struct tcp_sock *tp = tcp_sk(sk); /* RFC1323: H1. Apply PAWS check first. */ - if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp && + if (tcp_fast_parse_options(skb, th, tp, &hash_location) && + tp->rx_opt.saw_tstamp && tcp_paws_discard(sk, skb)) { if (!th->rst) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); @@ -5368,12 +5396,14 @@ discard: static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, struct tcphdr *th, unsigned len) { - struct tcp_sock *tp = tcp_sk(sk); + u8 *hash_location; struct inet_connection_sock *icsk = inet_csk(sk); - int saved_clamp = tp->rx_opt.mss_clamp; + struct tcp_sock *tp = tcp_sk(sk); struct dst_entry *dst = __sk_dst_get(sk); + struct tcp_cookie_values *cvp = tp->cookie_values; + int saved_clamp = tp->rx_opt.mss_clamp; - tcp_parse_options(skb, &tp->rx_opt, 0, dst); + tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, dst); if (th->ack) { /* rfc793: @@ -5470,6 +5500,31 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, * Change state from SYN-SENT only after copied_seq * is initialized. */ tp->copied_seq = tp->rcv_nxt; + + if (cvp != NULL && + cvp->cookie_pair_size > 0 && + tp->rx_opt.cookie_plus > 0) { + int cookie_size = tp->rx_opt.cookie_plus + - TCPOLEN_COOKIE_BASE; + int cookie_pair_size = cookie_size + + cvp->cookie_desired; + + /* A cookie extension option was sent and returned. + * Note that each incoming SYNACK replaces the + * Responder cookie. The initial exchange is most + * fragile, as protection against spoofing relies + * entirely upon the sequence and timestamp (above). + * This replacement strategy allows the correct pair to + * pass through, while any others will be filtered via + * Responder verification later. + */ + if (sizeof(cvp->cookie_pair) >= cookie_pair_size) { + memcpy(&cvp->cookie_pair[cvp->cookie_desired], + hash_location, cookie_size); + cvp->cookie_pair_size = cookie_pair_size; + } + } + smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index df18ce04f41e..29002ab26e0d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -742,8 +742,9 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, * This still operates on a request_sock only, not on a big * socket. */ -static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req, - struct dst_entry *dst) +static int __tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, + struct request_sock *req, + struct request_values *rvp) { const struct inet_request_sock *ireq = inet_rsk(req); int err = -1; @@ -753,7 +754,7 @@ static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req, if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL) return -1; - skb = tcp_make_synack(sk, dst, req); + skb = tcp_make_synack(sk, dst, req, rvp); if (skb) { struct tcphdr *th = tcp_hdr(skb); @@ -774,9 +775,10 @@ static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req, return err; } -static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req) +static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req, + struct request_values *rvp) { - return __tcp_v4_send_synack(sk, req, NULL); + return __tcp_v4_send_synack(sk, NULL, req, rvp); } /* @@ -1211,13 +1213,16 @@ static struct timewait_sock_ops tcp_timewait_sock_ops = { int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { - struct inet_request_sock *ireq; + struct tcp_extend_values tmp_ext; struct tcp_options_received tmp_opt; + u8 *hash_location; struct request_sock *req; + struct inet_request_sock *ireq; + struct tcp_sock *tp = tcp_sk(sk); + struct dst_entry *dst = NULL; __be32 saddr = ip_hdr(skb)->saddr; __be32 daddr = ip_hdr(skb)->daddr; __u32 isn = TCP_SKB_CB(skb)->when; - struct dst_entry *dst = NULL; #ifdef CONFIG_SYN_COOKIES int want_cookie = 0; #else @@ -1269,15 +1274,49 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = TCP_MSS_DEFAULT; - tmp_opt.user_mss = tcp_sk(sk)->rx_opt.user_mss; + tmp_opt.user_mss = tp->rx_opt.user_mss; + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, dst); + + if (tmp_opt.cookie_plus > 0 && + tmp_opt.saw_tstamp && + !tp->rx_opt.cookie_out_never && + (sysctl_tcp_cookie_size > 0 || + (tp->cookie_values != NULL && + tp->cookie_values->cookie_desired > 0))) { + u8 *c; + u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS]; + int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE; + + if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0) + goto drop_and_release; - tcp_parse_options(skb, &tmp_opt, 0, dst); + /* Secret recipe starts with IP addresses */ + *mess++ ^= daddr; + *mess++ ^= saddr; + + /* plus variable length Initiator Cookie */ + c = (u8 *)mess; + while (l-- > 0) + *c++ ^= *hash_location++; + +#ifdef CONFIG_SYN_COOKIES + want_cookie = 0; /* not our kind of cookie */ +#endif + tmp_ext.cookie_out_never = 0; /* false */ + tmp_ext.cookie_plus = tmp_opt.cookie_plus; + } else if (!tp->rx_opt.cookie_in_always) { + /* redundant indications, but ensure initialization. */ + tmp_ext.cookie_out_never = 1; /* true */ + tmp_ext.cookie_plus = 0; + } else { + goto drop_and_release; + } + tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always; if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; - tcp_openreq_init(req, &tmp_opt, skb); if (security_inet_conn_request(sk, skb, req)) @@ -1337,7 +1376,9 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) } tcp_rsk(req)->snt_isn = isn; - if (__tcp_v4_send_synack(sk, req, dst) || want_cookie) + if (__tcp_v4_send_synack(sk, dst, req, + (struct request_values *)&tmp_ext) || + want_cookie) goto drop_and_free; inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); @@ -1831,6 +1872,19 @@ static int tcp_v4_init_sock(struct sock *sk) tp->af_specific = &tcp_sock_ipv4_specific; #endif + /* TCP Cookie Transactions */ + if (sysctl_tcp_cookie_size > 0) { + /* Default, cookies without s_data_payload. */ + tp->cookie_values = + kzalloc(sizeof(*tp->cookie_values), + sk->sk_allocation); + if (tp->cookie_values != NULL) + kref_init(&tp->cookie_values->kref); + } + /* Presumed zeroed, in order of appearance: + * cookie_in_always, cookie_out_never, + * s_data_constant, s_data_in, s_data_out + */ sk->sk_sndbuf = sysctl_tcp_wmem[1]; sk->sk_rcvbuf = sysctl_tcp_rmem[1]; @@ -1884,6 +1938,13 @@ void tcp_v4_destroy_sock(struct sock *sk) sk->sk_sndmsg_page = NULL; } + /* TCP Cookie Transactions */ + if (tp->cookie_values != NULL) { + kref_put(&tp->cookie_values->kref, + tcp_cookie_values_release); + tp->cookie_values = NULL; + } + percpu_counter_dec(&tcp_sockets_allocated); } @@ -2257,6 +2318,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) __be32 src = inet->inet_rcv_saddr; __u16 destp = ntohs(inet->inet_dport); __u16 srcp = ntohs(inet->inet_sport); + int rx_queue; if (icsk->icsk_pending == ICSK_TIME_RETRANS) { timer_active = 1; @@ -2272,12 +2334,19 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) timer_expires = jiffies; } + if (sk->sk_state == TCP_LISTEN) + rx_queue = sk->sk_ack_backlog; + else + /* + * because we dont lock socket, we might find a transient negative value + */ + rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5d %8d %lu %d %p %lu %lu %u %u %d%n", i, src, srcp, dest, destp, sk->sk_state, tp->write_seq - tp->snd_una, - sk->sk_state == TCP_LISTEN ? sk->sk_ack_backlog : - (tp->rcv_nxt - tp->copied_seq), + rx_queue, timer_active, jiffies_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, @@ -2468,12 +2537,17 @@ static int __net_init tcp_sk_init(struct net *net) static void __net_exit tcp_sk_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv4.tcp_sock); - inet_twsk_purge(net, &tcp_hashinfo, &tcp_death_row, AF_INET); +} + +static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET); } static struct pernet_operations __net_initdata tcp_sk_ops = { - .init = tcp_sk_init, - .exit = tcp_sk_exit, + .init = tcp_sk_init, + .exit = tcp_sk_exit, + .exit_batch = tcp_sk_exit_batch, }; void __init tcp_v4_init(void) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ab32c181f749..87accec8d097 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -90,13 +90,14 @@ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th) { - struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); struct tcp_options_received tmp_opt; + u8 *hash_location; + struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); int paws_reject = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { tmp_opt.tstamp_ok = 1; - tcp_parse_options(skb, &tmp_opt, 1, NULL); + tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = tcptw->tw_ts_recent; @@ -383,14 +384,43 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, const struct inet_request_sock *ireq = inet_rsk(req); struct tcp_request_sock *treq = tcp_rsk(req); struct inet_connection_sock *newicsk = inet_csk(newsk); - struct tcp_sock *newtp; + struct tcp_sock *newtp = tcp_sk(newsk); + struct tcp_sock *oldtp = tcp_sk(sk); + struct tcp_cookie_values *oldcvp = oldtp->cookie_values; + + /* TCP Cookie Transactions require space for the cookie pair, + * as it differs for each connection. There is no need to + * copy any s_data_payload stored at the original socket. + * Failure will prevent resuming the connection. + * + * Presumed copied, in order of appearance: + * cookie_in_always, cookie_out_never + */ + if (oldcvp != NULL) { + struct tcp_cookie_values *newcvp = + kzalloc(sizeof(*newtp->cookie_values), + GFP_ATOMIC); + + if (newcvp != NULL) { + kref_init(&newcvp->kref); + newcvp->cookie_desired = + oldcvp->cookie_desired; + newtp->cookie_values = newcvp; + } else { + /* Not Yet Implemented */ + newtp->cookie_values = NULL; + } + } /* Now setup tcp_sock */ - newtp = tcp_sk(newsk); newtp->pred_flags = 0; - newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1; - newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = treq->snt_isn + 1; - newtp->snd_up = treq->snt_isn + 1; + + newtp->rcv_wup = newtp->copied_seq = + newtp->rcv_nxt = treq->rcv_isn + 1; + + newtp->snd_sml = newtp->snd_una = + newtp->snd_nxt = newtp->snd_up = + treq->snt_isn + 1 + tcp_s_data_size(oldtp); tcp_prequeue_init(newtp); @@ -423,8 +453,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, tcp_set_ca_state(newsk, TCP_CA_Open); tcp_init_xmit_timers(newsk); skb_queue_head_init(&newtp->out_of_order_queue); - newtp->write_seq = treq->snt_isn + 1; - newtp->pushed_seq = newtp->write_seq; + newtp->write_seq = newtp->pushed_seq = + treq->snt_isn + 1 + tcp_s_data_size(oldtp); newtp->rx_opt.saw_tstamp = 0; @@ -489,15 +519,16 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct request_sock **prev) { + struct tcp_options_received tmp_opt; + u8 *hash_location; + struct sock *child; const struct tcphdr *th = tcp_hdr(skb); __be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK); int paws_reject = 0; - struct tcp_options_received tmp_opt; - struct sock *child; - if ((th->doff > (sizeof(struct tcphdr)>>2)) && (req->ts_recent)) { + if ((th->doff > (sizeof(*th) >> 2)) && (req->ts_recent)) { tmp_opt.tstamp_ok = 1; - tcp_parse_options(skb, &tmp_opt, 1, NULL); + tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = req->ts_recent; @@ -531,7 +562,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * Enforce "SYN-ACK" according to figure 8, figure 6 * of RFC793, fixed by RFC1122. */ - req->rsk_ops->rtx_syn_ack(sk, req); + req->rsk_ops->rtx_syn_ack(sk, req, NULL); return NULL; } @@ -590,7 +621,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * Invalid ACK: reset will be sent by listening socket */ if ((flg & TCP_FLAG_ACK) && - (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1)) + (TCP_SKB_CB(skb)->ack_seq != + tcp_rsk(req)->snt_isn + 1 + tcp_s_data_size(tcp_sk(sk)))) return sk; /* Also, it would be not so bad idea to check rcv_tsecr, which diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 875bc6dcd920..93316a96d820 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -59,6 +59,10 @@ int sysctl_tcp_base_mss __read_mostly = 512; /* By default, RFC2861 behavior. */ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; +int sysctl_tcp_cookie_size __read_mostly = 0; /* TCP_COOKIE_MAX */ +EXPORT_SYMBOL_GPL(sysctl_tcp_cookie_size); + + /* Account for new data that has been sent to the network. */ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) { @@ -362,15 +366,45 @@ static inline int tcp_urg_mode(const struct tcp_sock *tp) #define OPTION_TS (1 << 1) #define OPTION_MD5 (1 << 2) #define OPTION_WSCALE (1 << 3) +#define OPTION_COOKIE_EXTENSION (1 << 4) struct tcp_out_options { u8 options; /* bit field of OPTION_* */ u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ + u8 hash_size; /* bytes in hash_location */ u16 mss; /* 0 to disable */ __u32 tsval, tsecr; /* need to include OPTION_TS */ + __u8 *hash_location; /* temporary pointer, overloaded */ }; +/* The sysctl int routines are generic, so check consistency here. + */ +static u8 tcp_cookie_size_check(u8 desired) +{ + if (desired > 0) { + /* previously specified */ + return desired; + } + if (sysctl_tcp_cookie_size <= 0) { + /* no default specified */ + return 0; + } + if (sysctl_tcp_cookie_size <= TCP_COOKIE_MIN) { + /* value too small, specify minimum */ + return TCP_COOKIE_MIN; + } + if (sysctl_tcp_cookie_size >= TCP_COOKIE_MAX) { + /* value too large, specify maximum */ + return TCP_COOKIE_MAX; + } + if (0x1 & sysctl_tcp_cookie_size) { + /* 8-bit multiple, illegal, fix it */ + return (u8)(sysctl_tcp_cookie_size + 0x1); + } + return (u8)sysctl_tcp_cookie_size; +} + /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of @@ -385,17 +419,34 @@ struct tcp_out_options { * (but it may well be that other scenarios fail similarly). */ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, - const struct tcp_out_options *opts, - __u8 **md5_hash) { - if (unlikely(OPTION_MD5 & opts->options)) { - *ptr++ = htonl((TCPOPT_NOP << 24) | - (TCPOPT_NOP << 16) | - (TCPOPT_MD5SIG << 8) | - TCPOLEN_MD5SIG); - *md5_hash = (__u8 *)ptr; + struct tcp_out_options *opts) +{ + u8 options = opts->options; /* mungable copy */ + + /* Having both authentication and cookies for security is redundant, + * and there's certainly not enough room. Instead, the cookie-less + * extension variant is proposed. + * + * Consider the pessimal case with authentication. The options + * could look like: + * COOKIE|MD5(20) + MSS(4) + SACK|TS(12) + WSCALE(4) == 40 + */ + if (unlikely(OPTION_MD5 & options)) { + if (unlikely(OPTION_COOKIE_EXTENSION & options)) { + *ptr++ = htonl((TCPOPT_COOKIE << 24) | + (TCPOLEN_COOKIE_BASE << 16) | + (TCPOPT_MD5SIG << 8) | + TCPOLEN_MD5SIG); + } else { + *ptr++ = htonl((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_MD5SIG << 8) | + TCPOLEN_MD5SIG); + } + options &= ~OPTION_COOKIE_EXTENSION; + /* overload cookie hash location */ + opts->hash_location = (__u8 *)ptr; ptr += 4; - } else { - *md5_hash = NULL; } if (unlikely(opts->mss)) { @@ -404,12 +455,13 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, opts->mss); } - if (likely(OPTION_TS & opts->options)) { - if (unlikely(OPTION_SACK_ADVERTISE & opts->options)) { + if (likely(OPTION_TS & options)) { + if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_SACK_PERM << 24) | (TCPOLEN_SACK_PERM << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); + options &= ~OPTION_SACK_ADVERTISE; } else { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | @@ -420,15 +472,52 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, *ptr++ = htonl(opts->tsecr); } - if (unlikely(OPTION_SACK_ADVERTISE & opts->options && - !(OPTION_TS & opts->options))) { + /* Specification requires after timestamp, so do it now. + * + * Consider the pessimal case without authentication. The options + * could look like: + * MSS(4) + SACK|TS(12) + COOKIE(20) + WSCALE(4) == 40 + */ + if (unlikely(OPTION_COOKIE_EXTENSION & options)) { + __u8 *cookie_copy = opts->hash_location; + u8 cookie_size = opts->hash_size; + + /* 8-bit multiple handled in tcp_cookie_size_check() above, + * and elsewhere. + */ + if (0x2 & cookie_size) { + __u8 *p = (__u8 *)ptr; + + /* 16-bit multiple */ + *p++ = TCPOPT_COOKIE; + *p++ = TCPOLEN_COOKIE_BASE + cookie_size; + *p++ = *cookie_copy++; + *p++ = *cookie_copy++; + ptr++; + cookie_size -= 2; + } else { + /* 32-bit multiple */ + *ptr++ = htonl(((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_COOKIE << 8) | + TCPOLEN_COOKIE_BASE) + + cookie_size); + } + + if (cookie_size > 0) { + memcpy(ptr, cookie_copy, cookie_size); + ptr += (cookie_size / 4); + } + } + + if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM); } - if (unlikely(OPTION_WSCALE & opts->options)) { + if (unlikely(OPTION_WSCALE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | @@ -463,14 +552,18 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { struct tcp_sock *tp = tcp_sk(sk); - unsigned size = 0; + struct tcp_cookie_values *cvp = tp->cookie_values; struct dst_entry *dst = __sk_dst_get(sk); + unsigned remaining = MAX_TCP_OPTION_SPACE; + u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ? + tcp_cookie_size_check(cvp->cookie_desired) : + 0; #ifdef CONFIG_TCP_MD5SIG *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { opts->options |= OPTION_MD5; - size += TCPOLEN_MD5SIG_ALIGNED; + remaining -= TCPOLEN_MD5SIG_ALIGNED; } #else *md5 = NULL; @@ -486,7 +579,7 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, * SACKs don't matter, we never delay an ACK when we have any of those * going out. */ opts->mss = tcp_advertise_mss(sk); - size += TCPOLEN_MSS_ALIGNED; + remaining -= TCPOLEN_MSS_ALIGNED; if (likely(sysctl_tcp_timestamps && !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) && @@ -494,22 +587,68 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->options |= OPTION_TS; opts->tsval = TCP_SKB_CB(skb)->when; opts->tsecr = tp->rx_opt.ts_recent; - size += TCPOLEN_TSTAMP_ALIGNED; + remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(sysctl_tcp_window_scaling && !dst_feature(dst, RTAX_FEATURE_NO_WSCALE))) { opts->ws = tp->rx_opt.rcv_wscale; opts->options |= OPTION_WSCALE; - size += TCPOLEN_WSCALE_ALIGNED; + remaining -= TCPOLEN_WSCALE_ALIGNED; } if (likely(sysctl_tcp_sack && !dst_feature(dst, RTAX_FEATURE_NO_SACK))) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) - size += TCPOLEN_SACKPERM_ALIGNED; + remaining -= TCPOLEN_SACKPERM_ALIGNED; } - return size; + /* Note that timestamps are required by the specification. + * + * Odd numbers of bytes are prohibited by the specification, ensuring + * that the cookie is 16-bit aligned, and the resulting cookie pair is + * 32-bit aligned. + */ + if (*md5 == NULL && + (OPTION_TS & opts->options) && + cookie_size > 0) { + int need = TCPOLEN_COOKIE_BASE + cookie_size; + + if (0x2 & need) { + /* 32-bit multiple */ + need += 2; /* NOPs */ + + if (need > remaining) { + /* try shrinking cookie to fit */ + cookie_size -= 2; + need -= 4; + } + } + while (need > remaining && TCP_COOKIE_MIN <= cookie_size) { + cookie_size -= 4; + need -= 4; + } + if (TCP_COOKIE_MIN <= cookie_size) { + opts->options |= OPTION_COOKIE_EXTENSION; + opts->hash_location = (__u8 *)&cvp->cookie_pair[0]; + opts->hash_size = cookie_size; + + /* Remember for future incarnations. */ + cvp->cookie_desired = cookie_size; + + if (cvp->cookie_desired != cvp->cookie_pair_size) { + /* Currently use random bytes as a nonce, + * assuming these are completely unpredictable + * by hostile users of the same system. + */ + get_random_bytes(&cvp->cookie_pair[0], + cookie_size); + cvp->cookie_pair_size = cookie_size; + } + + remaining -= need; + } + } + return MAX_TCP_OPTION_SPACE - remaining; } /* Set up TCP options for SYN-ACKs. */ @@ -517,48 +656,77 @@ static unsigned tcp_synack_options(struct sock *sk, struct request_sock *req, unsigned mss, struct sk_buff *skb, struct tcp_out_options *opts, - struct tcp_md5sig_key **md5) { - unsigned size = 0; + struct tcp_md5sig_key **md5, + struct tcp_extend_values *xvp) +{ struct inet_request_sock *ireq = inet_rsk(req); - char doing_ts; + unsigned remaining = MAX_TCP_OPTION_SPACE; + u8 cookie_plus = (xvp != NULL && !xvp->cookie_out_never) ? + xvp->cookie_plus : + 0; + bool doing_ts = ireq->tstamp_ok; #ifdef CONFIG_TCP_MD5SIG *md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req); if (*md5) { opts->options |= OPTION_MD5; - size += TCPOLEN_MD5SIG_ALIGNED; + remaining -= TCPOLEN_MD5SIG_ALIGNED; + + /* We can't fit any SACK blocks in a packet with MD5 + TS + * options. There was discussion about disabling SACK + * rather than TS in order to fit in better with old, + * buggy kernels, but that was deemed to be unnecessary. + */ + doing_ts &= !ireq->sack_ok; } #else *md5 = NULL; #endif - /* we can't fit any SACK blocks in a packet with MD5 + TS - options. There was discussion about disabling SACK rather than TS in - order to fit in better with old, buggy kernels, but that was deemed - to be unnecessary. */ - doing_ts = ireq->tstamp_ok && !(*md5 && ireq->sack_ok); - + /* We always send an MSS option. */ opts->mss = mss; - size += TCPOLEN_MSS_ALIGNED; + remaining -= TCPOLEN_MSS_ALIGNED; if (likely(ireq->wscale_ok)) { opts->ws = ireq->rcv_wscale; opts->options |= OPTION_WSCALE; - size += TCPOLEN_WSCALE_ALIGNED; + remaining -= TCPOLEN_WSCALE_ALIGNED; } if (likely(doing_ts)) { opts->options |= OPTION_TS; opts->tsval = TCP_SKB_CB(skb)->when; opts->tsecr = req->ts_recent; - size += TCPOLEN_TSTAMP_ALIGNED; + remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(ireq->sack_ok)) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!doing_ts)) - size += TCPOLEN_SACKPERM_ALIGNED; + remaining -= TCPOLEN_SACKPERM_ALIGNED; } - return size; + /* Similar rationale to tcp_syn_options() applies here, too. + * If the <SYN> options fit, the same options should fit now! + */ + if (*md5 == NULL && + doing_ts && + cookie_plus > TCPOLEN_COOKIE_BASE) { + int need = cookie_plus; /* has TCPOLEN_COOKIE_BASE */ + + if (0x2 & need) { + /* 32-bit multiple */ + need += 2; /* NOPs */ + } + if (need <= remaining) { + opts->options |= OPTION_COOKIE_EXTENSION; + opts->hash_size = cookie_plus - TCPOLEN_COOKIE_BASE; + remaining -= need; + } else { + /* There's no error return, so flag it. */ + xvp->cookie_out_never = 1; /* true */ + opts->hash_size = 0; + } + } + return MAX_TCP_OPTION_SPACE - remaining; } /* Compute TCP options for ESTABLISHED sockets. This is not the @@ -624,7 +792,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, struct tcp_out_options opts; unsigned tcp_options_size, tcp_header_size; struct tcp_md5sig_key *md5; - __u8 *md5_hash_location; struct tcphdr *th; int err; @@ -695,7 +862,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, } } - tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location); + tcp_options_write((__be32 *)(th + 1), tp, &opts); if (likely((tcb->flags & TCPCB_FLAG_SYN) == 0)) TCP_ECN_send(sk, skb, tcp_header_size); @@ -703,7 +870,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, /* Calculate the MD5 hash, as we have all we need now */ if (md5) { sk->sk_route_caps &= ~NETIF_F_GSO_MASK; - tp->af_specific->calc_md5_hash(md5_hash_location, + tp->af_specific->calc_md5_hash(opts.hash_location, md5, sk, NULL, skb); } #endif @@ -2224,16 +2391,17 @@ int tcp_send_synack(struct sock *sk) /* Prepare a SYN-ACK. */ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, - struct request_sock *req) + struct request_sock *req, + struct request_values *rvp) { + struct tcp_out_options opts; + struct tcp_extend_values *xvp = tcp_xv(rvp); struct inet_request_sock *ireq = inet_rsk(req); struct tcp_sock *tp = tcp_sk(sk); struct tcphdr *th; - int tcp_header_size; - struct tcp_out_options opts; struct sk_buff *skb; struct tcp_md5sig_key *md5; - __u8 *md5_hash_location; + int tcp_header_size; int mss; skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC); @@ -2271,8 +2439,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, #endif TCP_SKB_CB(skb)->when = tcp_time_stamp; tcp_header_size = tcp_synack_options(sk, req, mss, - skb, &opts, &md5) + - sizeof(struct tcphdr); + skb, &opts, &md5, xvp) + + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); @@ -2289,19 +2457,58 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, */ tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn, TCPCB_FLAG_SYN | TCPCB_FLAG_ACK); + + if (OPTION_COOKIE_EXTENSION & opts.options) { + const struct tcp_cookie_values *cvp = tp->cookie_values; + + if (cvp != NULL && + cvp->s_data_constant && + cvp->s_data_desired > 0) { + u8 *buf = skb_put(skb, cvp->s_data_desired); + + /* copy data directly from the listening socket. */ + memcpy(buf, cvp->s_data_payload, cvp->s_data_desired); + TCP_SKB_CB(skb)->end_seq += cvp->s_data_desired; + } + + if (opts.hash_size > 0) { + __u32 workspace[SHA_WORKSPACE_WORDS]; + u32 *mess = &xvp->cookie_bakery[COOKIE_DIGEST_WORDS]; + u32 *tail = &mess[COOKIE_MESSAGE_WORDS-1]; + + /* Secret recipe depends on the Timestamp, (future) + * Sequence and Acknowledgment Numbers, Initiator + * Cookie, and others handled by IP variant caller. + */ + *tail-- ^= opts.tsval; + *tail-- ^= tcp_rsk(req)->rcv_isn + 1; + *tail-- ^= TCP_SKB_CB(skb)->seq + 1; + + /* recommended */ + *tail-- ^= ((th->dest << 16) | th->source); + *tail-- ^= (u32)(unsigned long)cvp; /* per sockopt */ + + sha_transform((__u32 *)&xvp->cookie_bakery[0], + (char *)mess, + &workspace[0]); + opts.hash_location = + (__u8 *)&xvp->cookie_bakery[0]; + } + } + th->seq = htonl(TCP_SKB_CB(skb)->seq); th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1); /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rcv_wnd, 65535U)); - tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location); + tcp_options_write((__be32 *)(th + 1), tp, &opts); th->doff = (tcp_header_size >> 2); TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ if (md5) { - tcp_rsk(req)->af_specific->calc_md5_hash(md5_hash_location, + tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location, md5, NULL, req, skb); } #endif diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 522bdc77206c..b1ce8fc62049 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4498,7 +4498,7 @@ static int addrconf_init_net(struct net *net) all = &ipv6_devconf; dflt = &ipv6_devconf_dflt; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { all = kmemdup(all, sizeof(ipv6_devconf), GFP_KERNEL); if (all == NULL) goto err_alloc_all; @@ -4546,7 +4546,7 @@ static void addrconf_exit_net(struct net *net) __addrconf_sysctl_unregister(net->ipv6.devconf_dflt); __addrconf_sysctl_unregister(net->ipv6.devconf_all); #endif - if (net != &init_net) { + if (!net_eq(net, &init_net)) { kfree(net->ipv6.devconf_dflt); kfree(net->ipv6.devconf_all); } diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 0f526f8ea518..c2f300c314be 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -667,7 +667,7 @@ static int ah6_init_state(struct xfrm_state *x) } ahp->icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8; - ahp->icv_trunc_len = aalg_desc->uinfo.auth.icv_truncbits/8; + ahp->icv_trunc_len = x->aalg->alg_trunc_len/8; BUG_ON(ahp->icv_trunc_len > MAX_AH_AUTH_LEN); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index af597c73ebe9..668a46b655e6 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -473,7 +473,7 @@ static int esp_init_authenc(struct xfrm_state *x) } err = crypto_aead_setauthsize( - aead, aalg_desc->uinfo.auth.icv_truncbits / 8); + aead, x->aalg->alg_trunc_len / 8); if (err) goto free_key; } diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 00a7a5e4ac97..b7aa7c64cc4a 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -264,44 +264,36 @@ static struct fib_rules_ops fib6_rules_ops_template = { static int fib6_rules_net_init(struct net *net) { + struct fib_rules_ops *ops; int err = -ENOMEM; - net->ipv6.fib6_rules_ops = kmemdup(&fib6_rules_ops_template, - sizeof(*net->ipv6.fib6_rules_ops), - GFP_KERNEL); - if (!net->ipv6.fib6_rules_ops) - goto out; + ops = fib_rules_register(&fib6_rules_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + net->ipv6.fib6_rules_ops = ops; - net->ipv6.fib6_rules_ops->fro_net = net; - INIT_LIST_HEAD(&net->ipv6.fib6_rules_ops->rules_list); err = fib_default_rule_add(net->ipv6.fib6_rules_ops, 0, - RT6_TABLE_LOCAL, FIB_RULE_PERMANENT); + RT6_TABLE_LOCAL, 0); if (err) goto out_fib6_rules_ops; err = fib_default_rule_add(net->ipv6.fib6_rules_ops, 0x7FFE, RT6_TABLE_MAIN, 0); if (err) - goto out_fib6_default_rule_add; + goto out_fib6_rules_ops; - err = fib_rules_register(net->ipv6.fib6_rules_ops); - if (err) - goto out_fib6_default_rule_add; out: return err; -out_fib6_default_rule_add: - fib_rules_cleanup_ops(net->ipv6.fib6_rules_ops); out_fib6_rules_ops: - kfree(net->ipv6.fib6_rules_ops); + fib_rules_unregister(ops); goto out; } static void fib6_rules_net_exit(struct net *net) { fib_rules_unregister(net->ipv6.fib6_rules_ops); - kfree(net->ipv6.fib6_rules_ops); } static struct pernet_operations fib6_rules_net_ops = { diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 00c6a3e6cddf..c813e294ec0c 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -223,6 +223,7 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw; + int twrefcnt = 0; spin_lock(lock); @@ -250,19 +251,23 @@ unique: * in hash table socket with a funny identity. */ inet->inet_num = lport; inet->inet_sport = htons(lport); + sk->sk_hash = hash; WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); - sk->sk_hash = hash; + if (tw) { + twrefcnt = inet_twsk_unhash(tw); + NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); + } spin_unlock(lock); + if (twrefcnt) + inet_twsk_put(tw); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - if (twp != NULL) { + if (twp) { *twp = tw; - NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); - } else if (tw != NULL) { + } else if (tw) { /* Silly. Should hash-dance instead... */ inet_twsk_deschedule(tw, death_row); - NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); inet_twsk_put(tw); } diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 593a67e8d3f6..6e7bffa2205e 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -67,7 +67,7 @@ static inline struct ip6_flowlabel *__fl_lookup(struct net *net, __be32 label) struct ip6_flowlabel *fl; for (fl=fl_ht[FL_HASH(label)]; fl; fl = fl->next) { - if (fl->label == label && fl->fl_net == net) + if (fl->label == label && net_eq(fl->fl_net, net)) return fl; } return NULL; @@ -163,7 +163,8 @@ static void ip6_fl_purge(struct net *net) struct ip6_flowlabel *fl, **flp; flp = &fl_ht[i]; while ((fl = *flp) != NULL) { - if (fl->fl_net == net && atomic_read(&fl->users) == 0) { + if (net_eq(fl->fl_net, net) && + atomic_read(&fl->users) == 0) { *flp = fl->next; fl_free(fl); atomic_dec(&fl_size); @@ -630,7 +631,7 @@ static struct ip6_flowlabel *ip6fl_get_first(struct seq_file *seq) for (state->bucket = 0; state->bucket <= FL_HASH_MASK; ++state->bucket) { fl = fl_ht[state->bucket]; - while (fl && fl->fl_net != net) + while (fl && !net_eq(fl->fl_net, net)) fl = fl->next; if (fl) break; @@ -645,7 +646,7 @@ static struct ip6_flowlabel *ip6fl_get_next(struct seq_file *seq, struct ip6_flo fl = fl->next; try_again: - while (fl && fl->fl_net != net) + while (fl && !net_eq(fl->fl_net, net)) fl = fl->next; while (!fl) { diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index e5c0f6bb8314..d453d07b0dfe 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1409,17 +1409,8 @@ static void ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) static int ip6_tnl_init_net(struct net *net) { + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); int err; - struct ip6_tnl_net *ip6n; - - err = -ENOMEM; - ip6n = kzalloc(sizeof(struct ip6_tnl_net), GFP_KERNEL); - if (ip6n == NULL) - goto err_alloc; - - err = net_assign_generic(net, ip6_tnl_net_id, ip6n); - if (err < 0) - goto err_assign; ip6n->tnls[0] = ip6n->tnls_wc; ip6n->tnls[1] = ip6n->tnls_r_l; @@ -1442,27 +1433,23 @@ static int ip6_tnl_init_net(struct net *net) err_register: free_netdev(ip6n->fb_tnl_dev); err_alloc_dev: - /* nothing */ -err_assign: - kfree(ip6n); -err_alloc: return err; } static void ip6_tnl_exit_net(struct net *net) { - struct ip6_tnl_net *ip6n; + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - ip6n = net_generic(net, ip6_tnl_net_id); rtnl_lock(); ip6_tnl_destroy_tunnels(ip6n); rtnl_unlock(); - kfree(ip6n); } static struct pernet_operations ip6_tnl_net_ops = { .init = ip6_tnl_init_net, .exit = ip6_tnl_exit_net, + .id = &ip6_tnl_net_id, + .size = sizeof(struct ip6_tnl_net), }; /** @@ -1487,7 +1474,7 @@ static int __init ip6_tunnel_init(void) goto unreg_ip4ip6; } - err = register_pernet_gen_device(&ip6_tnl_net_id, &ip6_tnl_net_ops); + err = register_pernet_device(&ip6_tnl_net_ops); if (err < 0) goto err_pernet; return 0; @@ -1511,7 +1498,7 @@ static void __exit ip6_tunnel_cleanup(void) if (xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6)) printk(KERN_INFO "ip6_tunnel close: can't deregister ip6ip6\n"); - unregister_pernet_gen_device(ip6_tnl_net_id, &ip6_tnl_net_ops); + unregister_pernet_device(&ip6_tnl_net_ops); } module_init(ip6_tunnel_init); diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index 1cf3f0c6a959..db4d5725cce8 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -499,10 +499,9 @@ ipq_rcv_nl_event(struct notifier_block *this, { struct netlink_notify *n = ptr; - if (event == NETLINK_URELEASE && - n->protocol == NETLINK_IP6_FW && n->pid) { + if (event == NETLINK_URELEASE && n->protocol == NETLINK_IP6_FW) { write_lock_bh(&queue_lock); - if ((n->net == &init_net) && (n->pid == peer_pid)) + if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid)) __ipq_reset(); write_unlock_bh(&queue_lock); } @@ -625,7 +624,7 @@ cleanup_netlink_notifier: static void __exit ip6_queue_fini(void) { nf_unregister_queue_handlers(&nfqh); - synchronize_net(); + ipq_flush(NULL, 0); #ifdef CONFIG_SYSCTL diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index cc9f8ef303fd..480d7f8c9802 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -105,9 +105,9 @@ ip6_packet_match(const struct sk_buff *skb, #define FWINV(bool, invflg) ((bool) ^ !!(ip6info->invflags & (invflg))) if (FWINV(ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk, - &ip6info->src), IP6T_INV_SRCIP) - || FWINV(ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk, - &ip6info->dst), IP6T_INV_DSTIP)) { + &ip6info->src), IP6T_INV_SRCIP) || + FWINV(ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk, + &ip6info->dst), IP6T_INV_DSTIP)) { dprintf("Source or dest mismatch.\n"); /* dprintf("SRC: %u. Mask: %u. Target: %u.%s\n", ip->saddr, @@ -277,11 +277,11 @@ get_chainname_rulenum(struct ip6t_entry *s, struct ip6t_entry *e, } else if (s == e) { (*rulenum)++; - if (s->target_offset == sizeof(struct ip6t_entry) - && strcmp(t->target.u.kernel.target->name, - IP6T_STANDARD_TARGET) == 0 - && t->verdict < 0 - && unconditional(&s->ipv6)) { + if (s->target_offset == sizeof(struct ip6t_entry) && + strcmp(t->target.u.kernel.target->name, + IP6T_STANDARD_TARGET) == 0 && + t->verdict < 0 && + unconditional(&s->ipv6)) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP6_TRACE_COMMENT_POLICY] @@ -418,8 +418,8 @@ ip6t_do_table(struct sk_buff *skb, back = get_entry(table_base, back->comefrom); continue; } - if (table_base + v != ip6t_next_entry(e) - && !(e->ipv6.flags & IP6T_F_GOTO)) { + if (table_base + v != ip6t_next_entry(e) && + !(e->ipv6.flags & IP6T_F_GOTO)) { /* Save old back ptr in next entry */ struct ip6t_entry *next = ip6t_next_entry(e); next->comefrom = (void *)back - table_base; @@ -505,11 +505,11 @@ mark_source_chains(struct xt_table_info *newinfo, e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct ip6t_entry) - && (strcmp(t->target.u.user.name, - IP6T_STANDARD_TARGET) == 0) - && t->verdict < 0 - && unconditional(&e->ipv6)) || visited) { + if ((e->target_offset == sizeof(struct ip6t_entry) && + (strcmp(t->target.u.user.name, + IP6T_STANDARD_TARGET) == 0) && + t->verdict < 0 && + unconditional(&e->ipv6)) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -556,8 +556,8 @@ mark_source_chains(struct xt_table_info *newinfo, int newpos = t->verdict; if (strcmp(t->target.u.user.name, - IP6T_STANDARD_TARGET) == 0 - && newpos >= 0) { + IP6T_STANDARD_TARGET) == 0 && + newpos >= 0) { if (newpos > newinfo->size - sizeof(struct ip6t_entry)) { duprintf("mark_source_chains: " @@ -767,8 +767,8 @@ check_entry_size_and_hooks(struct ip6t_entry *e, { unsigned int h; - if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 - || (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 || + (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -1584,8 +1584,8 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, int ret, off, h; duprintf("check_compat_entry_size_and_hooks %p\n", e); - if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 - || (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 || + (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index 7018cac4fddc..b285fdf19050 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -249,8 +249,8 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 11 "URGP=65535 " */ printk("URGP=%u ", ntohs(th->urg_ptr)); - if ((logflags & IP6T_LOG_TCPOPT) - && th->doff * 4 > sizeof(struct tcphdr)) { + if ((logflags & IP6T_LOG_TCPOPT) && + th->doff * 4 > sizeof(struct tcphdr)) { u_int8_t _opt[60 - sizeof(struct tcphdr)]; const u_int8_t *op; unsigned int i; diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 5a7f00cd15ce..8311ca31816a 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -223,8 +223,8 @@ static bool reject_tg6_check(const struct xt_tgchk_param *par) return false; } else if (rejinfo->with == IP6T_TCP_RESET) { /* Must specify that it's a TCP packet */ - if (e->ipv6.proto != IPPROTO_TCP - || (e->ipv6.invflags & XT_INV_PROTO)) { + if (e->ipv6.proto != IPPROTO_TCP || + (e->ipv6.invflags & XT_INV_PROTO)) { printk("ip6t_REJECT: TCP_RESET illegal for non-tcp\n"); return false; } diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c index 3a82f24746b9..ac0b7c629d78 100644 --- a/net/ipv6/netfilter/ip6t_ah.c +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -77,17 +77,14 @@ static bool ah_mt6(const struct sk_buff *skb, const struct xt_match_param *par) ahinfo->hdrres, ah->reserved, !(ahinfo->hdrres && ah->reserved)); - return (ah != NULL) - && - spi_match(ahinfo->spis[0], ahinfo->spis[1], - ntohl(ah->spi), - !!(ahinfo->invflags & IP6T_AH_INV_SPI)) - && - (!ahinfo->hdrlen || - (ahinfo->hdrlen == hdrlen) ^ - !!(ahinfo->invflags & IP6T_AH_INV_LEN)) - && - !(ahinfo->hdrres && ah->reserved); + return (ah != NULL) && + spi_match(ahinfo->spis[0], ahinfo->spis[1], + ntohl(ah->spi), + !!(ahinfo->invflags & IP6T_AH_INV_SPI)) && + (!ahinfo->hdrlen || + (ahinfo->hdrlen == hdrlen) ^ + !!(ahinfo->invflags & IP6T_AH_INV_LEN)) && + !(ahinfo->hdrres && ah->reserved); } static bool ah_mt6_check(const struct xt_mtchk_param *par) diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c index 673aa0a5084e..7b91c2598ed5 100644 --- a/net/ipv6/netfilter/ip6t_frag.c +++ b/net/ipv6/netfilter/ip6t_frag.c @@ -70,41 +70,36 @@ frag_mt6(const struct sk_buff *skb, const struct xt_match_param *par) pr_debug("res %02X %02X%04X %02X ", fraginfo->flags & IP6T_FRAG_RES, fh->reserved, ntohs(fh->frag_off) & 0x6, - !((fraginfo->flags & IP6T_FRAG_RES) - && (fh->reserved || (ntohs(fh->frag_off) & 0x06)))); + !((fraginfo->flags & IP6T_FRAG_RES) && + (fh->reserved || (ntohs(fh->frag_off) & 0x06)))); pr_debug("first %02X %02X %02X ", fraginfo->flags & IP6T_FRAG_FST, ntohs(fh->frag_off) & ~0x7, - !((fraginfo->flags & IP6T_FRAG_FST) - && (ntohs(fh->frag_off) & ~0x7))); + !((fraginfo->flags & IP6T_FRAG_FST) && + (ntohs(fh->frag_off) & ~0x7))); pr_debug("mf %02X %02X %02X ", fraginfo->flags & IP6T_FRAG_MF, ntohs(fh->frag_off) & IP6_MF, - !((fraginfo->flags & IP6T_FRAG_MF) - && !((ntohs(fh->frag_off) & IP6_MF)))); + !((fraginfo->flags & IP6T_FRAG_MF) && + !((ntohs(fh->frag_off) & IP6_MF)))); pr_debug("last %02X %02X %02X\n", fraginfo->flags & IP6T_FRAG_NMF, ntohs(fh->frag_off) & IP6_MF, - !((fraginfo->flags & IP6T_FRAG_NMF) - && (ntohs(fh->frag_off) & IP6_MF))); - - return (fh != NULL) - && - id_match(fraginfo->ids[0], fraginfo->ids[1], - ntohl(fh->identification), - !!(fraginfo->invflags & IP6T_FRAG_INV_IDS)) - && - !((fraginfo->flags & IP6T_FRAG_RES) - && (fh->reserved || (ntohs(fh->frag_off) & 0x6))) - && - !((fraginfo->flags & IP6T_FRAG_FST) - && (ntohs(fh->frag_off) & ~0x7)) - && - !((fraginfo->flags & IP6T_FRAG_MF) - && !(ntohs(fh->frag_off) & IP6_MF)) - && - !((fraginfo->flags & IP6T_FRAG_NMF) - && (ntohs(fh->frag_off) & IP6_MF)); + !((fraginfo->flags & IP6T_FRAG_NMF) && + (ntohs(fh->frag_off) & IP6_MF))); + + return (fh != NULL) && + id_match(fraginfo->ids[0], fraginfo->ids[1], + ntohl(fh->identification), + !!(fraginfo->invflags & IP6T_FRAG_INV_IDS)) && + !((fraginfo->flags & IP6T_FRAG_RES) && + (fh->reserved || (ntohs(fh->frag_off) & 0x6))) && + !((fraginfo->flags & IP6T_FRAG_FST) && + (ntohs(fh->frag_off) & ~0x7)) && + !((fraginfo->flags & IP6T_FRAG_MF) && + !(ntohs(fh->frag_off) & IP6_MF)) && + !((fraginfo->flags & IP6T_FRAG_NMF) && + (ntohs(fh->frag_off) & IP6_MF)); } static bool frag_mt6_check(const struct xt_mtchk_param *par) diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index 356b8d6f6baa..b77307fc8743 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -92,16 +92,13 @@ static bool rt_mt6(const struct sk_buff *skb, const struct xt_match_param *par) !((rtinfo->flags & IP6T_RT_RES) && (((const struct rt0_hdr *)rh)->reserved))); - ret = (rh != NULL) - && + ret = (rh != NULL) && (segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1], rh->segments_left, - !!(rtinfo->invflags & IP6T_RT_INV_SGS))) - && + !!(rtinfo->invflags & IP6T_RT_INV_SGS))) && (!(rtinfo->flags & IP6T_RT_LEN) || ((rtinfo->hdrlen == hdrlen) ^ - !!(rtinfo->invflags & IP6T_RT_INV_LEN))) - && + !!(rtinfo->invflags & IP6T_RT_INV_LEN))) && (!(rtinfo->flags & IP6T_RT_TYP) || ((rtinfo->rt_type == rh->type) ^ !!(rtinfo->invflags & IP6T_RT_INV_TYP))); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 6f4383ad86f9..ad378efd0eb8 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -79,8 +79,8 @@ ip6t_local_out_hook(unsigned int hook, { #if 0 /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) - || ip_hdrlen(skb) < sizeof(struct iphdr)) { + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) { if (net_ratelimit()) printk("ip6t_hook: happy cracking.\n"); return NF_ACCEPT; diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 0ad91433ed61..a929c19d30e3 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -102,8 +102,8 @@ ip6t_local_out_hook(unsigned int hook, #if 0 /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) - || ip_hdrlen(skb) < sizeof(struct iphdr)) { + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) { if (net_ratelimit()) printk("ip6t_hook: happy cracking.\n"); return NF_ACCEPT; @@ -122,11 +122,11 @@ ip6t_local_out_hook(unsigned int hook, ret = ip6t_do_table(skb, hook, in, out, dev_net(out)->ipv6.ip6table_mangle); - if (ret != NF_DROP && ret != NF_STOLEN - && (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) - || memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) - || skb->mark != mark - || ipv6_hdr(skb)->hop_limit != hop_limit)) + if (ret != NF_DROP && ret != NF_STOLEN && + (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) || + memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) || + skb->mark != mark || + ipv6_hdr(skb)->hop_limit != hop_limit)) return ip6_route_me_harder(skb) == 0 ? ret : NF_DROP; return ret; diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 642dcb127bab..0f3df45718ac 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -244,18 +244,18 @@ static const struct nla_policy icmpv6_nla_policy[CTA_PROTO_MAX+1] = { static int icmpv6_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *tuple) { - if (!tb[CTA_PROTO_ICMPV6_TYPE] - || !tb[CTA_PROTO_ICMPV6_CODE] - || !tb[CTA_PROTO_ICMPV6_ID]) + if (!tb[CTA_PROTO_ICMPV6_TYPE] || + !tb[CTA_PROTO_ICMPV6_CODE] || + !tb[CTA_PROTO_ICMPV6_ID]) return -EINVAL; tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]); tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]); tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]); - if (tuple->dst.u.icmp.type < 128 - || tuple->dst.u.icmp.type - 128 >= sizeof(invmap) - || !invmap[tuple->dst.u.icmp.type - 128]) + if (tuple->dst.u.icmp.type < 128 || + tuple->dst.u.icmp.type - 128 >= sizeof(invmap) || + !invmap[tuple->dst.u.icmp.type - 128]) return -EINVAL; return 0; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index dce699fb2672..45efc39753e2 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -681,7 +681,7 @@ static int ip6_frags_ns_sysctl_register(struct net *net) struct ctl_table_header *hdr; table = ip6_frags_ns_ctl_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(ip6_frags_ns_ctl_table), GFP_KERNEL); if (table == NULL) goto err_alloc; @@ -699,7 +699,7 @@ static int ip6_frags_ns_sysctl_register(struct net *net) return 0; err_reg: - if (net != &init_net) + if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index d9deaa7753ef..976e68244b99 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1164,17 +1164,8 @@ static void sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head) static int sit_init_net(struct net *net) { + struct sit_net *sitn = net_generic(net, sit_net_id); int err; - struct sit_net *sitn; - - err = -ENOMEM; - sitn = kzalloc(sizeof(struct sit_net), GFP_KERNEL); - if (sitn == NULL) - goto err_alloc; - - err = net_assign_generic(net, sit_net_id, sitn); - if (err < 0) - goto err_assign; sitn->tunnels[0] = sitn->tunnels_wc; sitn->tunnels[1] = sitn->tunnels_l; @@ -1201,37 +1192,33 @@ err_reg_dev: dev_put(sitn->fb_tunnel_dev); free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: - /* nothing */ -err_assign: - kfree(sitn); -err_alloc: return err; } static void sit_exit_net(struct net *net) { - struct sit_net *sitn; + struct sit_net *sitn = net_generic(net, sit_net_id); LIST_HEAD(list); - sitn = net_generic(net, sit_net_id); rtnl_lock(); sit_destroy_tunnels(sitn, &list); unregister_netdevice_queue(sitn->fb_tunnel_dev, &list); unregister_netdevice_many(&list); rtnl_unlock(); - kfree(sitn); } static struct pernet_operations sit_net_ops = { .init = sit_init_net, .exit = sit_exit_net, + .id = &sit_net_id, + .size = sizeof(struct sit_net), }; static void __exit sit_cleanup(void) { xfrm4_tunnel_deregister(&sit_handler, AF_INET6); - unregister_pernet_gen_device(sit_net_id, &sit_net_ops); + unregister_pernet_device(&sit_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ } @@ -1246,7 +1233,7 @@ static int __init sit_init(void) return -EAGAIN; } - err = register_pernet_gen_device(&sit_net_id, &sit_net_ops); + err = register_pernet_device(&sit_net_ops); if (err < 0) xfrm4_tunnel_deregister(&sit_handler, AF_INET6); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 612fc53e0bb9..5b9af508b8f2 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -159,6 +159,8 @@ static inline int cookie_check(struct sk_buff *skb, __u32 cookie) struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) { + struct tcp_options_received tcp_opt; + u8 *hash_location; struct inet_request_sock *ireq; struct inet6_request_sock *ireq6; struct tcp_request_sock *treq; @@ -171,7 +173,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) int mss; struct dst_entry *dst; __u8 rcv_wscale; - struct tcp_options_received tcp_opt; if (!sysctl_tcp_syncookies || !th->ack) goto out; @@ -254,7 +255,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, 0, dst); + tcp_parse_options(skb, &tcp_opt, &hash_location, 0, dst); if (tcp_opt.saw_tstamp) cookie_check_timestamp(&tcp_opt); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index de709091b26d..aadd7cef73b3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -461,7 +461,8 @@ out: } -static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req) +static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, + struct request_values *rvp) { struct inet6_request_sock *treq = inet6_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); @@ -499,7 +500,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req) if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) goto done; - skb = tcp_make_synack(sk, dst, req); + skb = tcp_make_synack(sk, dst, req, rvp); if (skb) { struct tcphdr *th = tcp_hdr(skb); @@ -1161,13 +1162,15 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) */ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { + struct tcp_extend_values tmp_ext; + struct tcp_options_received tmp_opt; + u8 *hash_location; + struct request_sock *req; struct inet6_request_sock *treq; struct ipv6_pinfo *np = inet6_sk(sk); - struct tcp_options_received tmp_opt; struct tcp_sock *tp = tcp_sk(sk); - struct request_sock *req = NULL; - __u32 isn = TCP_SKB_CB(skb)->when; struct dst_entry *dst = __sk_dst_get(sk); + __u32 isn = TCP_SKB_CB(skb)->when; #ifdef CONFIG_SYN_COOKIES int want_cookie = 0; #else @@ -1205,8 +1208,52 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); tmp_opt.user_mss = tp->rx_opt.user_mss; + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, dst); + + if (tmp_opt.cookie_plus > 0 && + tmp_opt.saw_tstamp && + !tp->rx_opt.cookie_out_never && + (sysctl_tcp_cookie_size > 0 || + (tp->cookie_values != NULL && + tp->cookie_values->cookie_desired > 0))) { + u8 *c; + u32 *d; + u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS]; + int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE; + + if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0) + goto drop_and_free; + + /* Secret recipe starts with IP addresses */ + d = &ipv6_hdr(skb)->daddr.s6_addr32[0]; + *mess++ ^= *d++; + *mess++ ^= *d++; + *mess++ ^= *d++; + *mess++ ^= *d++; + d = &ipv6_hdr(skb)->saddr.s6_addr32[0]; + *mess++ ^= *d++; + *mess++ ^= *d++; + *mess++ ^= *d++; + *mess++ ^= *d++; + + /* plus variable length Initiator Cookie */ + c = (u8 *)mess; + while (l-- > 0) + *c++ ^= *hash_location++; - tcp_parse_options(skb, &tmp_opt, 0, dst); +#ifdef CONFIG_SYN_COOKIES + want_cookie = 0; /* not our kind of cookie */ +#endif + tmp_ext.cookie_out_never = 0; /* false */ + tmp_ext.cookie_plus = tmp_opt.cookie_plus; + } else if (!tp->rx_opt.cookie_in_always) { + /* redundant indications, but ensure initialization. */ + tmp_ext.cookie_out_never = 1; /* true */ + tmp_ext.cookie_plus = 0; + } else { + goto drop_and_free; + } + tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always; if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); @@ -1239,23 +1286,21 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) isn = tcp_v6_init_sequence(skb); } - tcp_rsk(req)->snt_isn = isn; security_inet_conn_request(sk, skb, req); - if (tcp_v6_send_synack(sk, req)) - goto drop; + if (tcp_v6_send_synack(sk, req, + (struct request_values *)&tmp_ext) || + want_cookie) + goto drop_and_free; - if (!want_cookie) { - inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); - return 0; - } + inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); + return 0; +drop_and_free: + reqsk_free(req); drop: - if (req) - reqsk_free(req); - return 0; /* don't send reset */ } @@ -1867,6 +1912,19 @@ static int tcp_v6_init_sock(struct sock *sk) tp->af_specific = &tcp_sock_ipv6_specific; #endif + /* TCP Cookie Transactions */ + if (sysctl_tcp_cookie_size > 0) { + /* Default, cookies without s_data_payload. */ + tp->cookie_values = + kzalloc(sizeof(*tp->cookie_values), + sk->sk_allocation); + if (tp->cookie_values != NULL) + kref_init(&tp->cookie_values->kref); + } + /* Presumed zeroed, in order of appearance: + * cookie_in_always, cookie_out_never, + * s_data_constant, s_data_in, s_data_out + */ sk->sk_sndbuf = sysctl_tcp_wmem[1]; sk->sk_rcvbuf = sysctl_tcp_rmem[1]; @@ -2126,12 +2184,17 @@ static int tcpv6_net_init(struct net *net) static void tcpv6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.tcp_sk); - inet_twsk_purge(net, &tcp_hashinfo, &tcp_death_row, AF_INET6); +} + +static void tcpv6_net_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET6); } static struct pernet_operations tcpv6_net_ops = { - .init = tcpv6_net_init, - .exit = tcpv6_net_exit, + .init = tcpv6_net_init, + .exit = tcpv6_net_exit, + .exit_batch = tcpv6_net_exit_batch, }; int __init tcpv6_init(void) diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 975c5a366e55..f9759b54a6de 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1362,7 +1362,7 @@ static int ipx_create(struct net *net, struct socket *sock, int protocol, int rc = -ESOCKTNOSUPPORT; struct sock *sk; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; /* diff --git a/net/irda/irnet/irnet_irda.c b/net/irda/irnet/irnet_irda.c index cccc2e93234f..b26dee784aba 100644 --- a/net/irda/irnet/irnet_irda.c +++ b/net/irda/irnet/irnet_irda.c @@ -1403,8 +1403,8 @@ irnet_connect_indication(void * instance, /* Socket already connecting ? On primary ? */ if(0 #ifdef ALLOW_SIMULT_CONNECT - || ((irttp_is_primary(server->tsap) == 1) /* primary */ - && (test_and_clear_bit(0, &new->ttp_connect))) + || ((irttp_is_primary(server->tsap) == 1) && /* primary */ + (test_and_clear_bit(0, &new->ttp_connect))) #endif /* ALLOW_SIMULT_CONNECT */ ) { diff --git a/net/key/af_key.c b/net/key/af_key.c index 478c8b32a5fb..84209fbbeb17 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3765,28 +3765,14 @@ static struct xfrm_mgr pfkeyv2_mgr = static int __net_init pfkey_net_init(struct net *net) { - struct netns_pfkey *net_pfkey; + struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); int rv; - net_pfkey = kmalloc(sizeof(struct netns_pfkey), GFP_KERNEL); - if (!net_pfkey) { - rv = -ENOMEM; - goto out_kmalloc; - } INIT_HLIST_HEAD(&net_pfkey->table); atomic_set(&net_pfkey->socks_nr, 0); - rv = net_assign_generic(net, pfkey_net_id, net_pfkey); - if (rv < 0) - goto out_assign; + rv = pfkey_init_proc(net); - if (rv < 0) - goto out_proc; - return 0; -out_proc: -out_assign: - kfree(net_pfkey); -out_kmalloc: return rv; } @@ -3796,17 +3782,18 @@ static void __net_exit pfkey_net_exit(struct net *net) pfkey_exit_proc(net); BUG_ON(!hlist_empty(&net_pfkey->table)); - kfree(net_pfkey); } static struct pernet_operations pfkey_net_ops = { .init = pfkey_net_init, .exit = pfkey_net_exit, + .id = &pfkey_net_id, + .size = sizeof(struct netns_pfkey), }; static void __exit ipsec_pfkey_exit(void) { - unregister_pernet_gen_subsys(pfkey_net_id, &pfkey_net_ops); + unregister_pernet_subsys(&pfkey_net_ops); xfrm_unregister_km(&pfkeyv2_mgr); sock_unregister(PF_KEY); proto_unregister(&key_proto); @@ -3825,7 +3812,7 @@ static int __init ipsec_pfkey_init(void) err = xfrm_register_km(&pfkeyv2_mgr); if (err != 0) goto out_sock_unregister; - err = register_pernet_gen_subsys(&pfkey_net_id, &pfkey_net_ops); + err = register_pernet_subsys(&pfkey_net_ops); if (err != 0) goto out_xfrm_unregister_km; out: diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 5266c286b260..3a66546cad06 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -158,7 +158,7 @@ static int llc_ui_create(struct net *net, struct socket *sock, int protocol, if (!capable(CAP_NET_RAW)) return -EPERM; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; if (likely(sock->type == SOCK_DGRAM || sock->type == SOCK_STREAM)) { diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 7ed5fe664732..51c7dc3c4c3b 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -86,10 +86,6 @@ void ieee80211_sta_stop_rx_ba_session(struct ieee80211_sub_if_data *sdata, u8 *r struct ieee80211_local *local = sdata->local; struct sta_info *sta; - /* stop HW Rx aggregation. ampdu_action existence - * already verified in session init so we add the BUG_ON */ - BUG_ON(!local->ops->ampdu_action); - rcu_read_lock(); sta = sta_info_get(local, ra); @@ -211,9 +207,9 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, * check if configuration can support the BA policy * and if buffer size does not exceeds max value */ /* XXX: check own ht delayed BA capability?? */ - if (((ba_policy != 1) - && (!(sta->sta.ht_cap.cap & IEEE80211_HT_CAP_DELAY_BA))) - || (buf_size > IEEE80211_MAX_AMPDU_BUF)) { + if (((ba_policy != 1) && + (!(sta->sta.ht_cap.cap & IEEE80211_HT_CAP_DELAY_BA))) || + (buf_size > IEEE80211_MAX_AMPDU_BUF)) { status = WLAN_STATUS_INVALID_QOS_PARAM; #ifdef CONFIG_MAC80211_HT_DEBUG if (net_ratelimit()) diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index b50b2bc3b8c5..5e3a7eccef5a 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -124,13 +124,18 @@ void ieee80211_send_bar(struct ieee80211_sub_if_data *sdata, u8 *ra, u16 tid, u1 ieee80211_tx_skb(sdata, skb); } -static int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, - enum ieee80211_back_parties initiator) +int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, + enum ieee80211_back_parties initiator) { struct ieee80211_local *local = sta->local; int ret; u8 *state; +#ifdef CONFIG_MAC80211_HT_DEBUG + printk(KERN_DEBUG "Tx BA session stop requested for %pM tid %u\n", + sta->sta.addr, tid); +#endif /* CONFIG_MAC80211_HT_DEBUG */ + state = &sta->ampdu_mlme.tid_state_tx[tid]; if (*state == HT_AGG_STATE_OPERATIONAL) @@ -145,7 +150,6 @@ static int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, /* HW shall not deny going back to legacy */ if (WARN_ON(ret)) { - *state = HT_AGG_STATE_OPERATIONAL; /* * We may have pending packets get stuck in this case... * Not bothering with a workaround for now. @@ -175,12 +179,14 @@ static void sta_addba_resp_timer_expired(unsigned long data) /* check if the TID waits for addBA response */ spin_lock_bh(&sta->lock); - if (!(*state & HT_ADDBA_REQUESTED_MSK)) { + if ((*state & (HT_ADDBA_REQUESTED_MSK | HT_ADDBA_RECEIVED_MSK)) != + HT_ADDBA_REQUESTED_MSK) { spin_unlock_bh(&sta->lock); *state = HT_AGG_STATE_IDLE; #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "timer expired on tid %d but we are not " - "expecting addBA response there", tid); + "(or no longer) expecting addBA response there", + tid); #endif return; } @@ -513,11 +519,6 @@ int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, goto unlock; } -#ifdef CONFIG_MAC80211_HT_DEBUG - printk(KERN_DEBUG "Tx BA session stop requested for %pM tid %u\n", - sta->sta.addr, tid); -#endif /* CONFIG_MAC80211_HT_DEBUG */ - ret = ___ieee80211_stop_tx_ba_session(sta, tid, initiator); unlock: @@ -532,7 +533,7 @@ int ieee80211_stop_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; - if (WARN_ON(!local->ops->ampdu_action)) + if (!local->ops->ampdu_action) return -EINVAL; if (tid >= STA_TID_NUM) @@ -649,21 +650,21 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, state = &sta->ampdu_mlme.tid_state_tx[tid]; - del_timer_sync(&sta->ampdu_mlme.tid_tx[tid]->addba_resp_timer); - spin_lock_bh(&sta->lock); if (!(*state & HT_ADDBA_REQUESTED_MSK)) - goto timer_still_needed; + goto out; if (mgmt->u.action.u.addba_resp.dialog_token != sta->ampdu_mlme.tid_tx[tid]->dialog_token) { #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "wrong addBA response token, tid %d\n", tid); #endif /* CONFIG_MAC80211_HT_DEBUG */ - goto timer_still_needed; + goto out; } + del_timer(&sta->ampdu_mlme.tid_tx[tid]->addba_resp_timer); + #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "switched off addBA timer for tid %d \n", tid); #endif /* CONFIG_MAC80211_HT_DEBUG */ @@ -682,10 +683,6 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, ___ieee80211_stop_tx_ba_session(sta, tid, WLAN_BACK_INITIATOR); } - goto out; - - timer_still_needed: - add_timer(&sta->ampdu_mlme.tid_tx[tid]->addba_resp_timer); out: spin_unlock_bh(&sta->lock); } diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 15c9d4f94cee..3787455fb696 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -160,10 +160,9 @@ void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, WLAN_BACK_INITIATOR, 0); else { /* WLAN_BACK_RECIPIENT */ spin_lock_bh(&sta->lock); - sta->ampdu_mlme.tid_state_tx[tid] = - HT_AGG_STATE_OPERATIONAL; + if (sta->ampdu_mlme.tid_state_tx[tid] & HT_ADDBA_REQUESTED_MSK) + ___ieee80211_stop_tx_ba_session(sta, tid, + WLAN_BACK_RECIPIENT); spin_unlock_bh(&sta->lock); - ieee80211_stop_tx_ba_session(&sta->sta, tid, - WLAN_BACK_RECIPIENT); } } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 7d3178f1b443..419f186cfcf0 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -601,6 +601,14 @@ struct ieee80211_local { bool suspended; /* + * Resuming is true while suspended, but when we're reprogramming the + * hardware -- at that time it's allowed to use ieee80211_queue_work() + * again even though some other parts of the stack are still suspended + * and we still drop received frames to avoid waking the stack. + */ + bool resuming; + + /* * quiescing is true during the suspend process _only_ to * ease timer cancelling etc. */ @@ -987,6 +995,8 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, enum ieee80211_back_parties initiator); +int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, + enum ieee80211_back_parties initiator); /* Spectrum management */ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/main.c b/net/mac80211/main.c index dd8ec8d5e8b2..8116d1a96a4a 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -631,8 +631,8 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) sta_info_stop(local); rate_control_deinitialize(local); - if (skb_queue_len(&local->skb_queue) - || skb_queue_len(&local->skb_queue_unreliable)) + if (skb_queue_len(&local->skb_queue) || + skb_queue_len(&local->skb_queue_unreliable)) printk(KERN_WARNING "%s: skb_queue not empty\n", wiphy_name(local->hw.wiphy)); skb_queue_purge(&local->skb_queue); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 51adb1115215..c0fe46493f71 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -195,8 +195,8 @@ int mesh_rmc_check(u8 *sa, struct ieee80211s_hdr *mesh_hdr, list_del(&p->list); kmem_cache_free(rm_cache, p); --entries; - } else if ((seqnum == p->seqnum) - && (memcmp(sa, p->sa, ETH_ALEN) == 0)) + } else if ((seqnum == p->seqnum) && + (memcmp(sa, p->sa, ETH_ALEN) == 0)) return -1; } diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 9aecf0207afc..833b2f3670c5 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -936,17 +936,16 @@ int mesh_nexthop_lookup(struct sk_buff *skb, } if (mpath->flags & MESH_PATH_ACTIVE) { - if (time_after(jiffies, mpath->exp_time + - msecs_to_jiffies(sdata->u.mesh.mshcfg.path_refresh_time)) - && !memcmp(sdata->dev->dev_addr, hdr->addr4, - ETH_ALEN) - && !(mpath->flags & MESH_PATH_RESOLVING) - && !(mpath->flags & MESH_PATH_FIXED)) { + if (time_after(jiffies, + mpath->exp_time + + msecs_to_jiffies(sdata->u.mesh.mshcfg.path_refresh_time)) && + !memcmp(sdata->dev->dev_addr, hdr->addr4, ETH_ALEN) && + !(mpath->flags & MESH_PATH_RESOLVING) && + !(mpath->flags & MESH_PATH_FIXED)) { mesh_queue_preq(mpath, PREQ_Q_F_START | PREQ_Q_F_REFRESH); } - memcpy(hdr->addr1, mpath->next_hop->sta.addr, - ETH_ALEN); + memcpy(hdr->addr1, mpath->next_hop->sta.addr, ETH_ALEN); } else { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); if (!(mpath->flags & MESH_PATH_RESOLVING)) { diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 57b8a0a42776..4ed60ae81b99 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1403,8 +1403,8 @@ ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) rx->key)) return -EACCES; /* BIP does not use Protected field, so need to check MMIE */ - if (unlikely(ieee80211_is_multicast_robust_mgmt_frame(rx->skb) - && ieee80211_get_mmie_keyidx(rx->skb) < 0 && + if (unlikely(ieee80211_is_multicast_robust_mgmt_frame(rx->skb) && + ieee80211_get_mmie_keyidx(rx->skb) < 0 && rx->key)) return -EACCES; /* diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 943def2b07df..8834cc93c716 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -366,10 +366,11 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx) struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; u32 staflags; - if (unlikely(!sta || ieee80211_is_probe_resp(hdr->frame_control) - || ieee80211_is_auth(hdr->frame_control) - || ieee80211_is_assoc_resp(hdr->frame_control) - || ieee80211_is_reassoc_resp(hdr->frame_control))) + if (unlikely(!sta || + ieee80211_is_probe_resp(hdr->frame_control) || + ieee80211_is_auth(hdr->frame_control) || + ieee80211_is_assoc_resp(hdr->frame_control) || + ieee80211_is_reassoc_resp(hdr->frame_control))) return TX_CONTINUE; staflags = get_sta_flags(sta); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 2fb0432ac830..d09f78bb2442 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -520,9 +520,9 @@ EXPORT_SYMBOL_GPL(ieee80211_iterate_active_interfaces_atomic); */ static bool ieee80211_can_queue_work(struct ieee80211_local *local) { - if (WARN(local->suspended, "queueing ieee80211 work while " - "going to suspend\n")) - return false; + if (WARN(local->suspended && !local->resuming, + "queueing ieee80211 work while going to suspend\n")) + return false; return true; } @@ -1033,13 +1033,9 @@ int ieee80211_reconfig(struct ieee80211_local *local) struct sta_info *sta; unsigned long flags; int res; - bool from_suspend = local->suspended; - /* - * We're going to start the hardware, at that point - * we are no longer suspended and can RX frames. - */ - local->suspended = false; + if (local->suspended) + local->resuming = true; /* restart hardware */ if (local->open_count) { @@ -1137,11 +1133,14 @@ int ieee80211_reconfig(struct ieee80211_local *local) * If this is for hw restart things are still running. * We may want to change that later, however. */ - if (!from_suspend) + if (!local->suspended) return 0; #ifdef CONFIG_PM + /* first set suspended false, then resuming */ local->suspended = false; + mb(); + local->resuming = false; list_for_each_entry(sdata, &local->interfaces, list) { switch(sdata->vif.type) { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index b9168c1864ca..0e98c3282d42 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -512,11 +512,17 @@ static noinline int early_drop(struct net *net, unsigned int hash) cnt++; } - if (ct && unlikely(nf_ct_is_dying(ct) || - !atomic_inc_not_zero(&ct->ct_general.use))) - ct = NULL; - if (ct || cnt >= NF_CT_EVICTION_RANGE) + if (ct != NULL) { + if (likely(!nf_ct_is_dying(ct) && + atomic_inc_not_zero(&ct->ct_general.use))) + break; + else + ct = NULL; + } + + if (cnt >= NF_CT_EVICTION_RANGE) break; + hash = (hash + 1) % nf_conntrack_htable_size; } rcu_read_unlock(); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 2032dfe25ca8..fdf5d2a1d9b4 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -202,9 +202,9 @@ static inline int expect_clash(const struct nf_conntrack_expect *a, static inline int expect_matches(const struct nf_conntrack_expect *a, const struct nf_conntrack_expect *b) { - return a->master == b->master && a->class == b->class - && nf_ct_tuple_equal(&a->tuple, &b->tuple) - && nf_ct_tuple_mask_equal(&a->mask, &b->mask); + return a->master == b->master && a->class == b->class && + nf_ct_tuple_equal(&a->tuple, &b->tuple) && + nf_ct_tuple_mask_equal(&a->mask, &b->mask); } /* Generally a bad idea to call this: could have matched already. */ diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 5509dd1f14cf..38ea7ef3ccd2 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -243,8 +243,8 @@ static int try_epsv_response(const char *data, size_t dlen, /* Three delimiters. */ if (dlen <= 3) return 0; delim = data[0]; - if (isdigit(delim) || delim < 33 || delim > 126 - || data[1] != delim || data[2] != delim) + if (isdigit(delim) || delim < 33 || delim > 126 || + data[1] != delim || data[2] != delim) return 0; return get_port(data, 3, dlen, delim, &cmd->u.tcp.port); @@ -366,8 +366,8 @@ static int help(struct sk_buff *skb, typeof(nf_nat_ftp_hook) nf_nat_ftp; /* Until there's been traffic both ways, don't look in packets. */ - if (ctinfo != IP_CT_ESTABLISHED - && ctinfo != IP_CT_ESTABLISHED+IP_CT_IS_REPLY) { + if (ctinfo != IP_CT_ESTABLISHED && + ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) { pr_debug("ftp: Conntrackinfo = %u\n", ctinfo); return NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 80abdf297b36..98916ef26f5d 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -810,12 +810,7 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = { static __net_init int dccp_net_init(struct net *net) { - struct dccp_net *dn; - int err; - - dn = kmalloc(sizeof(*dn), GFP_KERNEL); - if (!dn) - return -ENOMEM; + struct dccp_net *dn = dccp_pernet(net); /* default values */ dn->dccp_loose = 1; @@ -827,16 +822,11 @@ static __net_init int dccp_net_init(struct net *net) dn->dccp_timeout[CT_DCCP_CLOSING] = 64 * HZ; dn->dccp_timeout[CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL; - err = net_assign_generic(net, dccp_net_id, dn); - if (err) - goto out; - #ifdef CONFIG_SYSCTL - err = -ENOMEM; dn->sysctl_table = kmemdup(dccp_sysctl_table, sizeof(dccp_sysctl_table), GFP_KERNEL); if (!dn->sysctl_table) - goto out; + return -ENOMEM; dn->sysctl_table[0].data = &dn->dccp_timeout[CT_DCCP_REQUEST]; dn->sysctl_table[1].data = &dn->dccp_timeout[CT_DCCP_RESPOND]; @@ -851,15 +841,11 @@ static __net_init int dccp_net_init(struct net *net) nf_net_netfilter_sysctl_path, dn->sysctl_table); if (!dn->sysctl_header) { kfree(dn->sysctl_table); - goto out; + return -ENOMEM; } #endif return 0; - -out: - kfree(dn); - return err; } static __net_exit void dccp_net_exit(struct net *net) @@ -869,21 +855,20 @@ static __net_exit void dccp_net_exit(struct net *net) unregister_net_sysctl_table(dn->sysctl_header); kfree(dn->sysctl_table); #endif - kfree(dn); - - net_assign_generic(net, dccp_net_id, NULL); } static struct pernet_operations dccp_net_ops = { .init = dccp_net_init, .exit = dccp_net_exit, + .id = &dccp_net_id, + .size = sizeof(struct dccp_net), }; static int __init nf_conntrack_proto_dccp_init(void) { int err; - err = register_pernet_gen_subsys(&dccp_net_id, &dccp_net_ops); + err = register_pernet_subsys(&dccp_net_ops); if (err < 0) goto err1; @@ -899,14 +884,14 @@ static int __init nf_conntrack_proto_dccp_init(void) err3: nf_conntrack_l4proto_unregister(&dccp_proto4); err2: - unregister_pernet_gen_subsys(dccp_net_id, &dccp_net_ops); + unregister_pernet_subsys(&dccp_net_ops); err1: return err; } static void __exit nf_conntrack_proto_dccp_fini(void) { - unregister_pernet_gen_subsys(dccp_net_id, &dccp_net_ops); + unregister_pernet_subsys(&dccp_net_ops); nf_conntrack_l4proto_unregister(&dccp_proto6); nf_conntrack_l4proto_unregister(&dccp_proto4); } diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 91d0e719d67c..c99cfba64ddc 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -300,32 +300,24 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = { static int proto_gre_net_init(struct net *net) { - struct netns_proto_gre *net_gre; - int rv; + struct netns_proto_gre *net_gre = net_generic(net, proto_gre_net_id); - net_gre = kmalloc(sizeof(struct netns_proto_gre), GFP_KERNEL); - if (!net_gre) - return -ENOMEM; rwlock_init(&net_gre->keymap_lock); INIT_LIST_HEAD(&net_gre->keymap_list); - rv = net_assign_generic(net, proto_gre_net_id, net_gre); - if (rv < 0) - kfree(net_gre); - return rv; + return 0; } static void proto_gre_net_exit(struct net *net) { - struct netns_proto_gre *net_gre = net_generic(net, proto_gre_net_id); - nf_ct_gre_keymap_flush(net); - kfree(net_gre); } static struct pernet_operations proto_gre_net_ops = { .init = proto_gre_net_init, .exit = proto_gre_net_exit, + .id = &proto_gre_net_id, + .size = sizeof(struct netns_proto_gre), }; static int __init nf_ct_proto_gre_init(void) @@ -335,7 +327,7 @@ static int __init nf_ct_proto_gre_init(void) rv = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_gre4); if (rv < 0) return rv; - rv = register_pernet_gen_subsys(&proto_gre_net_id, &proto_gre_net_ops); + rv = register_pernet_subsys(&proto_gre_net_ops); if (rv < 0) nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_gre4); return rv; @@ -344,7 +336,7 @@ static int __init nf_ct_proto_gre_init(void) static void __exit nf_ct_proto_gre_fini(void) { nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_gre4); - unregister_pernet_gen_subsys(proto_gre_net_id, &proto_gre_net_ops); + unregister_pernet_subsys(&proto_gre_net_ops); } module_init(nf_ct_proto_gre_init); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index ba2b76937283..37a8c74be619 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -896,23 +896,54 @@ static int tcp_packet(struct nf_conn *ct, /* b) This SYN/ACK acknowledges a SYN that we earlier * ignored as invalid. This means that the client and * the server are both in sync, while the firewall is - * not. We kill this session and block the SYN/ACK so - * that the client cannot but retransmit its SYN and - * thus initiate a clean new session. + * not. We get in sync from the previously annotated + * values. */ - spin_unlock_bh(&ct->lock); - if (LOG_INVALID(net, IPPROTO_TCP)) - nf_log_packet(pf, 0, skb, NULL, NULL, NULL, - "nf_ct_tcp: killing out of sync session "); - nf_ct_kill(ct); - return NF_DROP; + old_state = TCP_CONNTRACK_SYN_SENT; + new_state = TCP_CONNTRACK_SYN_RECV; + ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_end = + ct->proto.tcp.last_end; + ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxend = + ct->proto.tcp.last_end; + ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_maxwin = + ct->proto.tcp.last_win == 0 ? + 1 : ct->proto.tcp.last_win; + ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_scale = + ct->proto.tcp.last_wscale; + ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags = + ct->proto.tcp.last_flags; + memset(&ct->proto.tcp.seen[dir], 0, + sizeof(struct ip_ct_tcp_state)); + break; } ct->proto.tcp.last_index = index; ct->proto.tcp.last_dir = dir; ct->proto.tcp.last_seq = ntohl(th->seq); ct->proto.tcp.last_end = segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th); - + ct->proto.tcp.last_win = ntohs(th->window); + + /* a) This is a SYN in ORIGINAL. The client and the server + * may be in sync but we are not. In that case, we annotate + * the TCP options and let the packet go through. If it is a + * valid SYN packet, the server will reply with a SYN/ACK, and + * then we'll get in sync. Otherwise, the server ignores it. */ + if (index == TCP_SYN_SET && dir == IP_CT_DIR_ORIGINAL) { + struct ip_ct_tcp_state seen = {}; + + ct->proto.tcp.last_flags = + ct->proto.tcp.last_wscale = 0; + tcp_options(skb, dataoff, th, &seen); + if (seen.flags & IP_CT_TCP_FLAG_WINDOW_SCALE) { + ct->proto.tcp.last_flags |= + IP_CT_TCP_FLAG_WINDOW_SCALE; + ct->proto.tcp.last_wscale = seen.td_scale; + } + if (seen.flags & IP_CT_TCP_FLAG_SACK_PERM) { + ct->proto.tcp.last_flags |= + IP_CT_TCP_FLAG_SACK_PERM; + } + } spin_unlock_bh(&ct->lock); if (LOG_INVALID(net, IPPROTO_TCP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index c93494fef8ef..d65d3481919c 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -128,9 +128,8 @@ EXPORT_SYMBOL(nf_log_packet); #ifdef CONFIG_PROC_FS static void *seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) { - rcu_read_lock(); + mutex_lock(&nf_log_mutex); if (*pos >= ARRAY_SIZE(nf_loggers)) return NULL; @@ -149,9 +148,8 @@ static void *seq_next(struct seq_file *s, void *v, loff_t *pos) } static void seq_stop(struct seq_file *s, void *v) - __releases(RCU) { - rcu_read_unlock(); + mutex_unlock(&nf_log_mutex); } static int seq_show(struct seq_file *s, void *v) @@ -161,7 +159,7 @@ static int seq_show(struct seq_file *s, void *v) struct nf_logger *t; int ret; - logger = rcu_dereference(nf_loggers[*pos]); + logger = nf_loggers[*pos]; if (!logger) ret = seq_printf(s, "%2lld NONE (", *pos); @@ -171,22 +169,16 @@ static int seq_show(struct seq_file *s, void *v) if (ret < 0) return ret; - mutex_lock(&nf_log_mutex); list_for_each_entry(t, &nf_loggers_l[*pos], list[*pos]) { ret = seq_printf(s, "%s", t->name); - if (ret < 0) { - mutex_unlock(&nf_log_mutex); + if (ret < 0) return ret; - } if (&t->list[*pos] != nf_loggers_l[*pos].prev) { ret = seq_printf(s, ","); - if (ret < 0) { - mutex_unlock(&nf_log_mutex); + if (ret < 0) return ret; - } } } - mutex_unlock(&nf_log_mutex); return seq_printf(s, ")\n"); } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index f900dc3194af..9de0470d557e 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -666,8 +666,7 @@ nfulnl_rcv_nl_event(struct notifier_block *this, { struct netlink_notify *n = ptr; - if (event == NETLINK_URELEASE && - n->protocol == NETLINK_NETFILTER && n->pid) { + if (event == NETLINK_URELEASE && n->protocol == NETLINK_NETFILTER) { int i; /* destroy all instances for this pid */ @@ -678,7 +677,7 @@ nfulnl_rcv_nl_event(struct notifier_block *this, struct hlist_head *head = &instance_table[i]; hlist_for_each_entry_safe(inst, tmp, t2, head, hlist) { - if ((n->net == &init_net) && + if ((net_eq(n->net, &init_net)) && (n->pid == inst->peer_pid)) __instance_destroy(inst); } diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 7a9dec9fb822..7e3fa410641e 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -574,8 +574,7 @@ nfqnl_rcv_nl_event(struct notifier_block *this, { struct netlink_notify *n = ptr; - if (event == NETLINK_URELEASE && - n->protocol == NETLINK_NETFILTER && n->pid) { + if (event == NETLINK_URELEASE && n->protocol == NETLINK_NETFILTER) { int i; /* destroy all instances for this pid */ diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index 6dc4652f2fe8..ae66305f0fe5 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -113,7 +113,8 @@ ct_proto_port_check(const struct xt_conntrack_mtinfo2 *info, } static bool -conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par) +conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par, + u16 state_mask, u16 status_mask) { const struct xt_conntrack_mtinfo2 *info = par->matchinfo; enum ip_conntrack_info ctinfo; @@ -136,7 +137,7 @@ conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par) if (test_bit(IPS_DST_NAT_BIT, &ct->status)) statebit |= XT_CONNTRACK_STATE_DNAT; } - if (!!(info->state_mask & statebit) ^ + if (!!(state_mask & statebit) ^ !(info->invert_flags & XT_CONNTRACK_STATE)) return false; } @@ -172,7 +173,7 @@ conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par) return false; if ((info->match_flags & XT_CONNTRACK_STATUS) && - (!!(info->status_mask & ct->status) ^ + (!!(status_mask & ct->status) ^ !(info->invert_flags & XT_CONNTRACK_STATUS))) return false; @@ -192,11 +193,17 @@ conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par) static bool conntrack_mt_v1(const struct sk_buff *skb, const struct xt_match_param *par) { - const struct xt_conntrack_mtinfo2 *const *info = par->matchinfo; - struct xt_match_param newpar = *par; + const struct xt_conntrack_mtinfo1 *info = par->matchinfo; - newpar.matchinfo = *info; - return conntrack_mt(skb, &newpar); + return conntrack_mt(skb, par, info->state_mask, info->status_mask); +} + +static bool +conntrack_mt_v2(const struct sk_buff *skb, const struct xt_match_param *par) +{ + const struct xt_conntrack_mtinfo2 *info = par->matchinfo; + + return conntrack_mt(skb, par, info->state_mask, info->status_mask); } static bool conntrack_mt_check(const struct xt_mtchk_param *par) @@ -209,45 +216,11 @@ static bool conntrack_mt_check(const struct xt_mtchk_param *par) return true; } -static bool conntrack_mt_check_v1(const struct xt_mtchk_param *par) -{ - struct xt_conntrack_mtinfo1 *info = par->matchinfo; - struct xt_conntrack_mtinfo2 *up; - int ret = conntrack_mt_check(par); - - if (ret < 0) - return ret; - - up = kmalloc(sizeof(*up), GFP_KERNEL); - if (up == NULL) { - nf_ct_l3proto_module_put(par->family); - return -ENOMEM; - } - - /* - * The strategy here is to minimize the overhead of v1 matching, - * by prebuilding a v2 struct and putting the pointer into the - * v1 dataspace. - */ - memcpy(up, info, offsetof(typeof(*info), state_mask)); - up->state_mask = info->state_mask; - up->status_mask = info->status_mask; - *(void **)info = up; - return true; -} - static void conntrack_mt_destroy(const struct xt_mtdtor_param *par) { nf_ct_l3proto_module_put(par->family); } -static void conntrack_mt_destroy_v1(const struct xt_mtdtor_param *par) -{ - struct xt_conntrack_mtinfo2 **info = par->matchinfo; - kfree(*info); - conntrack_mt_destroy(par); -} - static struct xt_match conntrack_mt_reg[] __read_mostly = { { .name = "conntrack", @@ -255,8 +228,8 @@ static struct xt_match conntrack_mt_reg[] __read_mostly = { .family = NFPROTO_UNSPEC, .matchsize = sizeof(struct xt_conntrack_mtinfo1), .match = conntrack_mt_v1, - .checkentry = conntrack_mt_check_v1, - .destroy = conntrack_mt_destroy_v1, + .checkentry = conntrack_mt_check, + .destroy = conntrack_mt_destroy, .me = THIS_MODULE, }, { @@ -264,7 +237,7 @@ static struct xt_match conntrack_mt_reg[] __read_mostly = { .revision = 2, .family = NFPROTO_UNSPEC, .matchsize = sizeof(struct xt_conntrack_mtinfo2), - .match = conntrack_mt, + .match = conntrack_mt_v2, .checkentry = conntrack_mt_check, .destroy = conntrack_mt_destroy, .me = THIS_MODULE, diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index 2e8089ecd0af..2773be6a71dd 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -112,7 +112,7 @@ static bool limit_mt_check(const struct xt_mtchk_param *par) priv = kmalloc(sizeof(*priv), GFP_KERNEL); if (priv == NULL) - return -ENOMEM; + return false; /* For SMP, we only want to use one set of state. */ r->master = priv; diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 63e190504656..4d1a41bbd5d7 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -118,7 +118,7 @@ static int xt_osf_remove_callback(struct sock *ctnl, struct sk_buff *skb, { struct xt_osf_user_finger *f; struct xt_osf_finger *sf; - int err = ENOENT; + int err = -ENOENT; if (!osf_attrs[OSF_ATTR_FINGER]) return -EINVAL; diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 362afbd60a96..6a902564d24f 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -192,7 +192,8 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .revision = 0, .family = NFPROTO_IPV4, .match = socket_mt_v0, - .hooks = 1 << NF_INET_PRE_ROUTING, + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, { @@ -201,7 +202,8 @@ static struct xt_match socket_mt_reg[] __read_mostly = { .family = NFPROTO_IPV4, .match = socket_mt_v1, .matchsize = sizeof(struct xt_socket_mtinfo1), - .hooks = 1 << NF_INET_PRE_ROUTING, + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN), .me = THIS_MODULE, }, }; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index eff5b0ddc5ca..a4957bf2ca60 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1092,7 +1092,7 @@ static inline int do_one_set_err(struct sock *sk, if (sk == p->exclude_sk) goto out; - if (sock_net(sk) != sock_net(p->exclude_sk)) + if (!net_eq(sock_net(sk), sock_net(p->exclude_sk))) goto out; if (nlk->pid == p->pid || p->group - 1 >= nlk->ngroups || diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 4bdd5697f63b..71604c6613b5 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -431,7 +431,7 @@ static int nr_create(struct net *net, struct socket *sock, int protocol, struct sock *sk; struct nr_sock *nr; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; if (sock->type != SOCK_SEQPACKET || protocol != 0) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c620bd9ae3de..020562164b56 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -365,7 +365,7 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, if (skb->pkt_type == PACKET_LOOPBACK) goto out; - if (dev_net(dev) != sock_net(sk)) + if (!net_eq(dev_net(dev), sock_net(sk))) goto out; skb = skb_share_check(skb, GFP_ATOMIC); @@ -553,7 +553,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, sk = pt->af_packet_priv; po = pkt_sk(sk); - if (dev_net(dev) != sock_net(sk)) + if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; skb->dev = dev; @@ -674,7 +674,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, sk = pt->af_packet_priv; po = pkt_sk(sk); - if (dev_net(dev) != sock_net(sk)) + if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; if (dev->header_ops) { @@ -1034,9 +1034,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto out_xmit; packet_increment_head(&po->tx_ring); len_sum += tp_len; - } while (likely((ph != NULL) || ((!(msg->msg_flags & MSG_DONTWAIT)) - && (atomic_read(&po->tx_ring.pending)))) - ); + } while (likely((ph != NULL) || + ((!(msg->msg_flags & MSG_DONTWAIT)) && + (atomic_read(&po->tx_ring.pending)))) + ); err = len_sum; goto out_put; diff --git a/net/phonet/pep.c b/net/phonet/pep.c index bdc17bdad366..b6356f3832f6 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -714,8 +714,8 @@ static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg) return -EINVAL; lock_sock(sk); - if (sock_flag(sk, SOCK_URGINLINE) - && !skb_queue_empty(&pn->ctrlreq_queue)) + if (sock_flag(sk, SOCK_URGINLINE) && + !skb_queue_empty(&pn->ctrlreq_queue)) answ = skb_peek(&pn->ctrlreq_queue)->len; else if (!skb_queue_empty(&sk->sk_receive_queue)) answ = skb_peek(&sk->sk_receive_queue)->len; diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index d87388c94b00..bc4a33bf2d3d 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -313,19 +313,14 @@ static struct notifier_block phonet_device_notifier = { /* Per-namespace Phonet devices handling */ static int phonet_init_net(struct net *net) { - struct phonet_net *pnn = kzalloc(sizeof(*pnn), GFP_KERNEL); - if (!pnn) - return -ENOMEM; + struct phonet_net *pnn = net_generic(net, phonet_net_id); - if (!proc_net_fops_create(net, "phonet", 0, &pn_sock_seq_fops)) { - kfree(pnn); + if (!proc_net_fops_create(net, "phonet", 0, &pn_sock_seq_fops)) return -ENOMEM; - } INIT_LIST_HEAD(&pnn->pndevs.list); mutex_init(&pnn->pndevs.lock); mutex_init(&pnn->routes.lock); - net_assign_generic(net, phonet_net_id, pnn); return 0; } @@ -349,18 +344,19 @@ static void phonet_exit_net(struct net *net) rtnl_unlock(); proc_net_remove(net, "phonet"); - kfree(pnn); } static struct pernet_operations phonet_net_ops = { .init = phonet_init_net, .exit = phonet_exit_net, + .id = &phonet_net_id, + .size = sizeof(struct phonet_net), }; /* Initialize Phonet devices list */ int __init phonet_device_init(void) { - int err = register_pernet_gen_device(&phonet_net_id, &phonet_net_ops); + int err = register_pernet_device(&phonet_net_ops); if (err) return err; @@ -375,7 +371,7 @@ void phonet_device_exit(void) { rtnl_unregister_all(PF_PHONET); unregister_netdevice_notifier(&phonet_device_notifier); - unregister_pernet_gen_device(phonet_net_id, &phonet_net_ops); + unregister_pernet_device(&phonet_net_ops); } int phonet_route_add(struct net_device *dev, u8 daddr) diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 4112b6e1c48a..69c8b826a0ce 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -98,8 +98,8 @@ struct sock *pn_find_sock_by_sa(struct net *net, const struct sockaddr_pn *spn) if (pn->resource != res) continue; } - if (pn_addr(pn->sobject) - && pn_addr(pn->sobject) != pn_addr(obj)) + if (pn_addr(pn->sobject) && + pn_addr(pn->sobject) != pn_addr(obj)) continue; rval = sknode; diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index e25d8d5ce8df..853c52be781f 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -174,8 +174,8 @@ static unsigned int rds_poll(struct file *file, struct socket *sock, mask |= (POLLIN | POLLRDNORM); spin_unlock(&rs->rs_lock); } - if (!list_empty(&rs->rs_recv_queue) - || !list_empty(&rs->rs_notify_queue)) + if (!list_empty(&rs->rs_recv_queue) || + !list_empty(&rs->rs_notify_queue)) mask |= (POLLIN | POLLRDNORM); if (rs->rs_snd_bytes < rds_sk_sndbuf(rs)) mask |= (POLLOUT | POLLWRNORM); @@ -308,8 +308,8 @@ static int rds_getsockopt(struct socket *sock, int level, int optname, if (len < sizeof(int)) ret = -EINVAL; else - if (put_user(rs->rs_recverr, (int __user *) optval) - || put_user(sizeof(int), optlen)) + if (put_user(rs->rs_recverr, (int __user *) optval) || + put_user(sizeof(int), optlen)) ret = -EFAULT; else ret = 0; diff --git a/net/rds/connection.c b/net/rds/connection.c index cc8b568c0c84..278f607ab603 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -133,10 +133,8 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr, spin_lock_irqsave(&rds_conn_lock, flags); conn = rds_conn_lookup(head, laddr, faddr, trans); - if (conn - && conn->c_loopback - && conn->c_trans != &rds_loop_transport - && !is_outgoing) { + if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport && + !is_outgoing) { /* This is a looped back IB connection, and we're * called by the code handling the incoming connect. * We need a second connection object into which we diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 9d320692a4fc..647cb8ffc39b 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -377,8 +377,8 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event) } /* Even if len is crap *now* I still want to check it. -ASG */ - if (event->param.conn.private_data_len < sizeof (*dp) - || dp->dp_protocol_major == 0) + if (event->param.conn.private_data_len < sizeof (*dp) || + dp->dp_protocol_major == 0) return RDS_PROTOCOL_3_0; common = be16_to_cpu(dp->dp_protocol_minor_mask) & RDS_IB_SUPPORTED_PROTOCOLS; diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index c5e916598c14..4b0da865a72c 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -570,8 +570,8 @@ void rds_ib_free_mr(void *trans_private, int invalidate) spin_unlock_irqrestore(&pool->list_lock, flags); /* If we've pinned too many pages, request a flush */ - if (atomic_read(&pool->free_pinned) >= pool->max_free_pinned - || atomic_read(&pool->dirty_count) >= pool->max_items / 10) + if (atomic_read(&pool->free_pinned) >= pool->max_free_pinned || + atomic_read(&pool->dirty_count) >= pool->max_items / 10) queue_work(rds_wq, &pool->flush_worker); if (invalidate) { diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index fe5ab8c6b964..04dc0d3f3c95 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -230,8 +230,8 @@ int rds_ib_recv_refill(struct rds_connection *conn, gfp_t kptr_gfp, int ret = 0; u32 pos; - while ((prefill || rds_conn_up(conn)) - && rds_ib_ring_alloc(&ic->i_recv_ring, 1, &pos)) { + while ((prefill || rds_conn_up(conn)) && + rds_ib_ring_alloc(&ic->i_recv_ring, 1, &pos)) { if (pos >= ic->i_recv_ring.w_nr) { printk(KERN_NOTICE "Argh - ring alloc returned pos=%u\n", pos); @@ -771,10 +771,10 @@ static void rds_ib_process_recv(struct rds_connection *conn, hdr = &ibinc->ii_inc.i_hdr; /* We can't just use memcmp here; fragments of a * single message may carry different ACKs */ - if (hdr->h_sequence != ihdr->h_sequence - || hdr->h_len != ihdr->h_len - || hdr->h_sport != ihdr->h_sport - || hdr->h_dport != ihdr->h_dport) { + if (hdr->h_sequence != ihdr->h_sequence || + hdr->h_len != ihdr->h_len || + hdr->h_sport != ihdr->h_sport || + hdr->h_dport != ihdr->h_dport) { rds_ib_conn_error(conn, "fragment header mismatch; forcing reconnect\n"); return; diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index 23bf830db2d5..a10fab6886d1 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -252,8 +252,8 @@ void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context) rds_ib_ring_free(&ic->i_send_ring, completed); - if (test_and_clear_bit(RDS_LL_SEND_FULL, &conn->c_flags) - || test_bit(0, &conn->c_map_queued)) + if (test_and_clear_bit(RDS_LL_SEND_FULL, &conn->c_flags) || + test_bit(0, &conn->c_map_queued)) queue_delayed_work(rds_wq, &conn->c_send_w, 0); /* We expect errors as the qp is drained during shutdown */ diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index b25d785e49fc..9eda11cca956 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -573,8 +573,8 @@ void rds_iw_free_mr(void *trans_private, int invalidate) rds_iw_free_fastreg(pool, ibmr); /* If we've pinned too many pages, request a flush */ - if (atomic_read(&pool->free_pinned) >= pool->max_free_pinned - || atomic_read(&pool->dirty_count) >= pool->max_items / 10) + if (atomic_read(&pool->free_pinned) >= pool->max_free_pinned || + atomic_read(&pool->dirty_count) >= pool->max_items / 10) queue_work(rds_wq, &pool->flush_worker); if (invalidate) { diff --git a/net/rds/iw_recv.c b/net/rds/iw_recv.c index 24fc53f03833..54af7d6b92da 100644 --- a/net/rds/iw_recv.c +++ b/net/rds/iw_recv.c @@ -230,8 +230,8 @@ int rds_iw_recv_refill(struct rds_connection *conn, gfp_t kptr_gfp, int ret = 0; u32 pos; - while ((prefill || rds_conn_up(conn)) - && rds_iw_ring_alloc(&ic->i_recv_ring, 1, &pos)) { + while ((prefill || rds_conn_up(conn)) && + rds_iw_ring_alloc(&ic->i_recv_ring, 1, &pos)) { if (pos >= ic->i_recv_ring.w_nr) { printk(KERN_NOTICE "Argh - ring alloc returned pos=%u\n", pos); @@ -730,10 +730,10 @@ static void rds_iw_process_recv(struct rds_connection *conn, hdr = &iwinc->ii_inc.i_hdr; /* We can't just use memcmp here; fragments of a * single message may carry different ACKs */ - if (hdr->h_sequence != ihdr->h_sequence - || hdr->h_len != ihdr->h_len - || hdr->h_sport != ihdr->h_sport - || hdr->h_dport != ihdr->h_dport) { + if (hdr->h_sequence != ihdr->h_sequence || + hdr->h_len != ihdr->h_len || + hdr->h_sport != ihdr->h_sport || + hdr->h_dport != ihdr->h_dport) { rds_iw_conn_error(conn, "fragment header mismatch; forcing reconnect\n"); return; diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c index 1f5abe3cf2b4..1379e9d66a78 100644 --- a/net/rds/iw_send.c +++ b/net/rds/iw_send.c @@ -288,8 +288,8 @@ void rds_iw_send_cq_comp_handler(struct ib_cq *cq, void *context) rds_iw_ring_free(&ic->i_send_ring, completed); - if (test_and_clear_bit(RDS_LL_SEND_FULL, &conn->c_flags) - || test_bit(0, &conn->c_map_queued)) + if (test_and_clear_bit(RDS_LL_SEND_FULL, &conn->c_flags) || + test_bit(0, &conn->c_map_queued)) queue_delayed_work(rds_wq, &conn->c_send_w, 0); /* We expect errors as the qp is drained during shutdown */ @@ -519,8 +519,7 @@ int rds_iw_xmit(struct rds_connection *conn, struct rds_message *rm, BUG_ON(hdr_off != 0 && hdr_off != sizeof(struct rds_header)); /* Fastreg support */ - if (rds_rdma_cookie_key(rm->m_rdma_cookie) - && !ic->i_fastreg_posted) { + if (rds_rdma_cookie_key(rm->m_rdma_cookie) && !ic->i_fastreg_posted) { ret = -EAGAIN; goto out; } diff --git a/net/rds/message.c b/net/rds/message.c index ca50a8ec9742..73e600ffd87f 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -122,8 +122,7 @@ int rds_message_add_extension(struct rds_header *hdr, if (hdr->h_exthdr[0] != RDS_EXTHDR_NONE) return 0; - if (type >= __RDS_EXTHDR_MAX - || len != rds_exthdr_size[type]) + if (type >= __RDS_EXTHDR_MAX || len != rds_exthdr_size[type]) return 0; if (ext_len >= RDS_HEADER_EXT_SPACE) diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 971b5a668458..4c64daa1f5d5 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -631,8 +631,8 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, { struct rds_rdma_op *op; - if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_rdma_args)) - || rm->m_rdma_op != NULL) + if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_rdma_args)) || + rm->m_rdma_op != NULL) return -EINVAL; op = rds_rdma_prepare(rs, CMSG_DATA(cmsg)); @@ -655,8 +655,8 @@ int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm, u32 r_key; int err = 0; - if (cmsg->cmsg_len < CMSG_LEN(sizeof(rds_rdma_cookie_t)) - || rm->m_rdma_cookie != 0) + if (cmsg->cmsg_len < CMSG_LEN(sizeof(rds_rdma_cookie_t)) || + rm->m_rdma_cookie != 0) return -EINVAL; memcpy(&rm->m_rdma_cookie, CMSG_DATA(cmsg), sizeof(rm->m_rdma_cookie)); @@ -692,8 +692,8 @@ int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm, int rds_cmsg_rdma_map(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { - if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_get_mr_args)) - || rm->m_rdma_cookie != 0) + if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_get_mr_args)) || + rm->m_rdma_cookie != 0) return -EINVAL; return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, &rm->m_rdma_mr); diff --git a/net/rds/recv.c b/net/rds/recv.c index fdff33c7b432..b426d67f760c 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -195,8 +195,8 @@ void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr, * XXX we could spend more on the wire to get more robust failure * detection, arguably worth it to avoid data corruption. */ - if (be64_to_cpu(inc->i_hdr.h_sequence) < conn->c_next_rx_seq - && (inc->i_hdr.h_flags & RDS_FLAG_RETRANSMITTED)) { + if (be64_to_cpu(inc->i_hdr.h_sequence) < conn->c_next_rx_seq && + (inc->i_hdr.h_flags & RDS_FLAG_RETRANSMITTED)) { rds_stats_inc(s_recv_drop_old_seq); goto out; } @@ -432,10 +432,9 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, } timeo = wait_event_interruptible_timeout(*sk->sk_sleep, - (!list_empty(&rs->rs_notify_queue) - || rs->rs_cong_notify - || rds_next_incoming(rs, &inc)), - timeo); + (!list_empty(&rs->rs_notify_queue) || + rs->rs_cong_notify || + rds_next_incoming(rs, &inc)), timeo); rdsdebug("recvmsg woke inc %p timeo %ld\n", inc, timeo); if (timeo > 0 || timeo == MAX_SCHEDULE_TIMEOUT) diff --git a/net/rds/send.c b/net/rds/send.c index 28c88ff3d038..b2fccfc20769 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -235,8 +235,8 @@ int rds_send_xmit(struct rds_connection *conn) * connection. * Therefore, we never retransmit messages with RDMA ops. */ - if (rm->m_rdma_op - && test_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags)) { + if (rm->m_rdma_op && + test_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags)) { spin_lock_irqsave(&conn->c_lock, flags); if (test_and_clear_bit(RDS_MSG_ON_CONN, &rm->m_flags)) list_move(&rm->m_conn_item, &to_be_dropped); @@ -247,8 +247,8 @@ int rds_send_xmit(struct rds_connection *conn) /* Require an ACK every once in a while */ len = ntohl(rm->m_inc.i_hdr.h_len); - if (conn->c_unacked_packets == 0 - || conn->c_unacked_bytes < len) { + if (conn->c_unacked_packets == 0 || + conn->c_unacked_bytes < len) { __set_bit(RDS_MSG_ACK_REQUIRED, &rm->m_flags); conn->c_unacked_packets = rds_sysctl_max_unacked_packets; @@ -418,8 +418,8 @@ void rds_rdma_send_complete(struct rds_message *rm, int status) spin_lock(&rm->m_rs_lock); ro = rm->m_rdma_op; - if (test_bit(RDS_MSG_ON_SOCK, &rm->m_flags) - && ro && ro->r_notify && ro->r_notifier) { + if (test_bit(RDS_MSG_ON_SOCK, &rm->m_flags) && + ro && ro->r_notify && ro->r_notifier) { notifier = ro->r_notifier; rs = rm->m_rs; sock_hold(rds_rs_to_sk(rs)); @@ -549,8 +549,7 @@ void rds_send_remove_from_sock(struct list_head *messages, int status) list_del_init(&rm->m_sock_item); rds_send_sndbuf_remove(rs, rm); - if (ro && ro->r_notifier - && (status || ro->r_notify)) { + if (ro && ro->r_notifier && (status || ro->r_notify)) { notifier = ro->r_notifier; list_add_tail(¬ifier->n_list, &rs->rs_notify_queue); @@ -877,8 +876,8 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, if (ret) goto out; - if ((rm->m_rdma_cookie || rm->m_rdma_op) - && conn->c_trans->xmit_rdma == NULL) { + if ((rm->m_rdma_cookie || rm->m_rdma_op) && + conn->c_trans->xmit_rdma == NULL) { if (printk_ratelimit()) printk(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n", rm->m_rdma_op, conn->c_trans->xmit_rdma); @@ -890,8 +889,8 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, * have scheduled a delayed reconnect however - in this case * we should not interfere. */ - if (rds_conn_state(conn) == RDS_CONN_DOWN - && !test_and_set_bit(RDS_RECONNECT_PENDING, &conn->c_flags)) + if (rds_conn_state(conn) == RDS_CONN_DOWN && + !test_and_set_bit(RDS_RECONNECT_PENDING, &conn->c_flags)) queue_delayed_work(rds_wq, &conn->c_conn_w, 0); ret = rds_cong_wait(conn->c_fcong, dport, nonblock, rs); @@ -973,8 +972,8 @@ rds_send_pong(struct rds_connection *conn, __be16 dport) * have scheduled a delayed reconnect however - in this case * we should not interfere. */ - if (rds_conn_state(conn) == RDS_CONN_DOWN - && !test_and_set_bit(RDS_RECONNECT_PENDING, &conn->c_flags)) + if (rds_conn_state(conn) == RDS_CONN_DOWN && + !test_and_set_bit(RDS_RECONNECT_PENDING, &conn->c_flags)) queue_delayed_work(rds_wq, &conn->c_conn_w, 0); ret = rds_cong_wait(conn->c_fcong, dport, 1, NULL); diff --git a/net/rds/threads.c b/net/rds/threads.c index dd7e0cad1e7c..00fa10e59af8 100644 --- a/net/rds/threads.c +++ b/net/rds/threads.c @@ -170,8 +170,8 @@ void rds_shutdown_worker(struct work_struct *work) * handler is supposed to check for state DISCONNECTING */ mutex_lock(&conn->c_cm_lock); - if (!rds_conn_transition(conn, RDS_CONN_UP, RDS_CONN_DISCONNECTING) - && !rds_conn_transition(conn, RDS_CONN_ERROR, RDS_CONN_DISCONNECTING)) { + if (!rds_conn_transition(conn, RDS_CONN_UP, RDS_CONN_DISCONNECTING) && + !rds_conn_transition(conn, RDS_CONN_ERROR, RDS_CONN_DISCONNECTING)) { rds_conn_error(conn, "shutdown called in state %d\n", atomic_read(&conn->c_state)); mutex_unlock(&conn->c_cm_lock); diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 09f4e161799b..448e5a0fcc2e 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1191,6 +1191,7 @@ static long rfkill_fop_ioctl(struct file *file, unsigned int cmd, #endif static const struct file_operations rfkill_fops = { + .owner = THIS_MODULE, .open = rfkill_fop_open, .read = rfkill_fop_read, .write = rfkill_fop_write, diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 4de4287fec37..8feb9e5d6623 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -518,7 +518,7 @@ static int rose_create(struct net *net, struct socket *sock, int protocol, struct sock *sk; struct rose_sock *rose; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; if (sock->type != SOCK_SEQPACKET || protocol != 0) diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index ea2e72337e2f..795c4b025e31 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -77,8 +77,9 @@ static int __must_check rose_add_node(struct rose_route_struct *rose_route, rose_neigh = rose_neigh_list; while (rose_neigh != NULL) { - if (ax25cmp(&rose_route->neighbour, &rose_neigh->callsign) == 0 - && rose_neigh->dev == dev) + if (ax25cmp(&rose_route->neighbour, + &rose_neigh->callsign) == 0 && + rose_neigh->dev == dev) break; rose_neigh = rose_neigh->next; } @@ -311,8 +312,9 @@ static int rose_del_node(struct rose_route_struct *rose_route, rose_neigh = rose_neigh_list; while (rose_neigh != NULL) { - if (ax25cmp(&rose_route->neighbour, &rose_neigh->callsign) == 0 - && rose_neigh->dev == dev) + if (ax25cmp(&rose_route->neighbour, + &rose_neigh->callsign) == 0 && + rose_neigh->dev == dev) break; rose_neigh = rose_neigh->next; } diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index f978d02a248a..287b1415cee9 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -616,7 +616,7 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol, _enter("%p,%d", sock, protocol); - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; /* we support transport protocol UDP only */ diff --git a/net/sched/act_api.c b/net/sched/act_api.c index ca2e1fd2bf69..2a740035aa6b 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -969,7 +969,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg) u32 pid = skb ? NETLINK_CB(skb).pid : 0; int ret = 0, ovr = 0; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EINVAL; ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL); @@ -1052,7 +1052,7 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) struct tcamsg *t = (struct tcamsg *) NLMSG_DATA(cb->nlh); struct nlattr *kind = find_dump_kind(cb->nlh); - if (net != &init_net) + if (!net_eq(net, &init_net)) return 0; if (kind == NULL) { diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index c024da77824f..3725d8fa29db 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -137,7 +137,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, void *arg) int err; int tp_created = 0; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EINVAL; replay: @@ -418,7 +418,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) const struct Qdisc_class_ops *cops; struct tcf_dump_args arg; - if (net != &init_net) + if (!net_eq(net, &init_net)) return 0; if (cb->nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*tcm))) diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 7034ea4530e5..dd9414e44200 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -170,21 +170,23 @@ restart: for (s = sht[h1]; s; s = s->next) { if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] && protocol == s->protocol && - !(s->dpi.mask & (*(u32*)(xprt+s->dpi.offset)^s->dpi.key)) + !(s->dpi.mask & + (*(u32*)(xprt+s->dpi.offset)^s->dpi.key)) && #if RSVP_DST_LEN == 4 - && dst[0] == s->dst[0] - && dst[1] == s->dst[1] - && dst[2] == s->dst[2] + dst[0] == s->dst[0] && + dst[1] == s->dst[1] && + dst[2] == s->dst[2] && #endif - && tunnelid == s->tunnelid) { + tunnelid == s->tunnelid) { for (f = s->ht[h2]; f; f = f->next) { if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN-1] && !(f->spi.mask & (*(u32*)(xprt+f->spi.offset)^f->spi.key)) #if RSVP_DST_LEN == 4 - && src[0] == f->src[0] - && src[1] == f->src[1] - && src[2] == f->src[2] + && + src[0] == f->src[0] && + src[1] == f->src[1] && + src[2] == f->src[2] #endif ) { *res = f->res; @@ -493,13 +495,13 @@ static int rsvp_change(struct tcf_proto *tp, unsigned long base, for (sp = &data->ht[h1]; (s=*sp) != NULL; sp = &s->next) { if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] && pinfo && pinfo->protocol == s->protocol && - memcmp(&pinfo->dpi, &s->dpi, sizeof(s->dpi)) == 0 + memcmp(&pinfo->dpi, &s->dpi, sizeof(s->dpi)) == 0 && #if RSVP_DST_LEN == 4 - && dst[0] == s->dst[0] - && dst[1] == s->dst[1] - && dst[2] == s->dst[2] + dst[0] == s->dst[0] && + dst[1] == s->dst[1] && + dst[2] == s->dst[2] && #endif - && pinfo->tunnelid == s->tunnelid) { + pinfo->tunnelid == s->tunnelid) { insert: /* OK, we found appropriate session */ diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 876ba4bb6ae9..75fd1c672c61 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -947,7 +947,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) struct Qdisc *p = NULL; int err; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EINVAL; if ((dev = __dev_get_by_index(&init_net, tcm->tcm_ifindex)) == NULL) @@ -1009,7 +1009,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) struct Qdisc *q, *p; int err; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EINVAL; replay: @@ -1274,7 +1274,7 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) int s_idx, s_q_idx; struct net_device *dev; - if (net != &init_net) + if (!net_eq(net, &init_net)) return 0; s_idx = cb->args[0]; @@ -1334,7 +1334,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) u32 qid = TC_H_MAJ(clid); int err; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EINVAL; if ((dev = __dev_get_by_index(&init_net, tcm->tcm_ifindex)) == NULL) @@ -1576,7 +1576,7 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) struct net_device *dev; int t, s_t; - if (net != &init_net) + if (!net_eq(net, &init_net)) return 0; if (cb->nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*tcm))) diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 2e38d1abd830..508cf5f3a6d5 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1344,8 +1344,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, }; /* check for valid classid */ - if (!classid || TC_H_MAJ(classid ^ sch->handle) - || htb_find(classid, sch)) + if (!classid || TC_H_MAJ(classid ^ sch->handle) || + htb_find(classid, sch)) goto failure; /* check maximal depth */ diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 2b88295cb7b7..d8b10e054627 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -199,9 +199,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) * do it now in software before we mangle it. */ if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) { - if (!(skb = skb_unshare(skb, GFP_ATOMIC)) - || (skb->ip_summed == CHECKSUM_PARTIAL - && skb_checksum_help(skb))) { + if (!(skb = skb_unshare(skb, GFP_ATOMIC)) || + (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_help(skb))) { sch->qstats.drops++; return NET_XMIT_DROP; } @@ -210,9 +210,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) } cb = netem_skb_cb(skb); - if (q->gap == 0 /* not doing reordering */ - || q->counter < q->gap /* inside last reordering gap */ - || q->reorder < get_crandom(&q->reorder_cor)) { + if (q->gap == 0 || /* not doing reordering */ + q->counter < q->gap || /* inside last reordering gap */ + q->reorder < get_crandom(&q->reorder_cor)) { psched_time_t now; psched_tdiff_t delay; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 5a002c247231..db69637069c4 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -190,10 +190,13 @@ static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt) if (m->slaves) { if (m->dev->flags & IFF_UP) { - if ((m->dev->flags&IFF_POINTOPOINT && !(dev->flags&IFF_POINTOPOINT)) - || (m->dev->flags&IFF_BROADCAST && !(dev->flags&IFF_BROADCAST)) - || (m->dev->flags&IFF_MULTICAST && !(dev->flags&IFF_MULTICAST)) - || dev->mtu < m->dev->mtu) + if ((m->dev->flags & IFF_POINTOPOINT && + !(dev->flags & IFF_POINTOPOINT)) || + (m->dev->flags & IFF_BROADCAST && + !(dev->flags & IFF_BROADCAST)) || + (m->dev->flags & IFF_MULTICAST && + !(dev->flags & IFF_MULTICAST)) || + dev->mtu < m->dev->mtu) return -EINVAL; } else { if (!(dev->flags&IFF_POINTOPOINT)) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 7eed77a39d0d..df5abbff63e2 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -63,6 +63,12 @@ static void sctp_assoc_bh_rcv(struct work_struct *work); static void sctp_assoc_free_asconf_acks(struct sctp_association *asoc); +/* Keep track of the new idr low so that we don't re-use association id + * numbers too fast. It is protected by they idr spin lock is in the + * range of 1 - INT_MAX. + */ +static u32 idr_low = 1; + /* 1st Level Abstractions. */ @@ -167,7 +173,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->timeouts[SCTP_EVENT_TIMEOUT_HEARTBEAT] = 0; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = - sp->autoclose * HZ; + (unsigned long)sp->autoclose * HZ; /* Initilizes the timers */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) @@ -512,7 +518,13 @@ void sctp_assoc_set_primary(struct sctp_association *asoc, * to this destination address earlier. The sender MUST set * CYCLING_CHANGEOVER to indicate that this switch is a * double switch to the same destination address. + * + * Really, only bother is we have data queued or outstanding on + * the association. */ + if (!asoc->outqueue.outstanding_bytes && !asoc->outqueue.out_qlen) + return; + if (transport->cacc.changeover_active) transport->cacc.cycling_changeover = changeover; @@ -732,6 +744,7 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, peer->partial_bytes_acked = 0; peer->flight_size = 0; + peer->burst_limited = 0; /* Set the transport's RTO.initial value */ peer->rto = asoc->rto_initial; @@ -1377,8 +1390,9 @@ static inline int sctp_peer_needs_update(struct sctp_association *asoc) case SCTP_STATE_SHUTDOWN_RECEIVED: case SCTP_STATE_SHUTDOWN_SENT: if ((asoc->rwnd > asoc->a_rwnd) && - ((asoc->rwnd - asoc->a_rwnd) >= - min_t(__u32, (asoc->base.sk->sk_rcvbuf >> 1), asoc->pathmtu))) + ((asoc->rwnd - asoc->a_rwnd) >= max_t(__u32, + (asoc->base.sk->sk_rcvbuf >> sctp_rwnd_upd_shift), + asoc->pathmtu))) return 1; break; default: @@ -1545,7 +1559,12 @@ retry: spin_lock_bh(&sctp_assocs_id_lock); error = idr_get_new_above(&sctp_assocs_id, (void *)asoc, - 1, &assoc_id); + idr_low, &assoc_id); + if (!error) { + idr_low = assoc_id + 1; + if (idr_low == INT_MAX) + idr_low = 1; + } spin_unlock_bh(&sctp_assocs_id_lock); if (error == -EAGAIN) goto retry; diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index acf7c4d128f7..8e4320040f05 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -263,9 +263,18 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, if (0 == i) frag |= SCTP_DATA_FIRST_FRAG; - if ((i == (whole - 1)) && !over) + if ((i == (whole - 1)) && !over) { frag |= SCTP_DATA_LAST_FRAG; + /* The application requests to set the I-bit of the + * last DATA chunk of a user message when providing + * the user message to the SCTP implementation. + */ + if ((sinfo->sinfo_flags & SCTP_EOF) || + (sinfo->sinfo_flags & SCTP_SACK_IMMEDIATELY)) + frag |= SCTP_DATA_SACK_IMM; + } + chunk = sctp_make_datafrag_empty(asoc, sinfo, len, frag, 0); if (!chunk) @@ -297,6 +306,10 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, else frag = SCTP_DATA_LAST_FRAG; + if ((sinfo->sinfo_flags & SCTP_EOF) || + (sinfo->sinfo_flags & SCTP_SACK_IMMEDIATELY)) + frag |= SCTP_DATA_SACK_IMM; + chunk = sctp_make_datafrag_empty(asoc, sinfo, over, frag, 0); if (!chunk) diff --git a/net/sctp/output.c b/net/sctp/output.c index 5cbda8f1ddfd..7c5589363433 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -429,23 +429,22 @@ int sctp_packet_transmit(struct sctp_packet *packet) list_del_init(&chunk->list); if (sctp_chunk_is_data(chunk)) { - if (!chunk->has_tsn) { - sctp_chunk_assign_ssn(chunk); - sctp_chunk_assign_tsn(chunk); - - /* 6.3.1 C4) When data is in flight and when allowed - * by rule C5, a new RTT measurement MUST be made each - * round trip. Furthermore, new RTT measurements - * SHOULD be made no more than once per round-trip - * for a given destination transport address. - */ + if (!chunk->resent) { + + /* 6.3.1 C4) When data is in flight and when allowed + * by rule C5, a new RTT measurement MUST be made each + * round trip. Furthermore, new RTT measurements + * SHOULD be made no more than once per round-trip + * for a given destination transport address. + */ if (!tp->rto_pending) { chunk->rtt_in_progress = 1; tp->rto_pending = 1; } - } else - chunk->resent = 1; + } + + chunk->resent = 1; has_data = 1; } @@ -557,8 +556,6 @@ int sctp_packet_transmit(struct sctp_packet *packet) struct timer_list *timer; unsigned long timeout; - tp->last_time_used = jiffies; - /* Restart the AUTOCLOSE timer when sending data. */ if (sctp_state(asoc, ESTABLISHED) && asoc->autoclose) { timer = &asoc->timers[SCTP_EVENT_TIMEOUT_AUTOCLOSE]; @@ -617,7 +614,6 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, sctp_xmit_t retval = SCTP_XMIT_OK; size_t datasize, rwnd, inflight, flight_size; struct sctp_transport *transport = packet->transport; - __u32 max_burst_bytes; struct sctp_association *asoc = transport->asoc; struct sctp_outq *q = &asoc->outqueue; @@ -650,28 +646,6 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, } } - /* sctpimpguide-05 2.14.2 - * D) When the time comes for the sender to - * transmit new DATA chunks, the protocol parameter Max.Burst MUST - * first be applied to limit how many new DATA chunks may be sent. - * The limit is applied by adjusting cwnd as follows: - * if ((flightsize + Max.Burst * MTU) < cwnd) - * cwnd = flightsize + Max.Burst * MTU - */ - max_burst_bytes = asoc->max_burst * asoc->pathmtu; - if ((flight_size + max_burst_bytes) < transport->cwnd) { - transport->cwnd = flight_size + max_burst_bytes; - SCTP_DEBUG_PRINTK("%s: cwnd limited by max_burst: " - "transport: %p, cwnd: %d, " - "ssthresh: %d, flight_size: %d, " - "pba: %d\n", - __func__, transport, - transport->cwnd, - transport->ssthresh, - transport->flight_size, - transport->partial_bytes_acked); - } - /* RFC 2960 6.1 Transmission of DATA Chunks * * B) At any given time, the sender MUST NOT transmit new data @@ -747,6 +721,8 @@ static void sctp_packet_append_data(struct sctp_packet *packet, /* Has been accepted for transmission. */ if (!asoc->peer.prsctp_capable) chunk->msg->can_abandon = 0; + sctp_chunk_assign_tsn(chunk); + sctp_chunk_assign_ssn(chunk); } static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet, diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index c9f20e28521b..229690f02a1d 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -191,8 +191,8 @@ static inline int sctp_cacc_skip(struct sctp_transport *primary, __u32 tsn) { if (primary->cacc.changeover_active && - (sctp_cacc_skip_3_1(primary, transport, count_of_newacks) - || sctp_cacc_skip_3_2(primary, tsn))) + (sctp_cacc_skip_3_1(primary, transport, count_of_newacks) || + sctp_cacc_skip_3_2(primary, tsn))) return 1; return 0; } @@ -423,16 +423,6 @@ void sctp_retransmit_mark(struct sctp_outq *q, if ((reason == SCTP_RTXR_FAST_RTX && (chunk->fast_retransmit == SCTP_NEED_FRTX)) || (reason != SCTP_RTXR_FAST_RTX && !chunk->tsn_gap_acked)) { - /* If this chunk was sent less then 1 rto ago, do not - * retransmit this chunk, but give the peer time - * to acknowlege it. Do this only when - * retransmitting due to T3 timeout. - */ - if (reason == SCTP_RTXR_T3_RTX && - time_before(jiffies, chunk->sent_at + - transport->last_rto)) - continue; - /* RFC 2960 6.2.1 Processing a Received SACK * * C) Any time a DATA chunk is marked for @@ -931,6 +921,14 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) goto sctp_flush_out; } + /* Apply Max.Burst limitation to the current transport in + * case it will be used for new data. We are going to + * rest it before we return, but we want to apply the limit + * to the currently queued data. + */ + if (transport) + sctp_transport_burst_limited(transport); + /* Finally, transmit new packets. */ while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { /* RFC 2960 6.5 Every DATA chunk MUST carry a valid @@ -976,6 +974,10 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) packet = &transport->packet; sctp_packet_config(packet, vtag, asoc->peer.ecn_capable); + /* We've switched transports, so apply the + * Burst limit to the new transport. + */ + sctp_transport_burst_limited(transport); } SCTP_DEBUG_PRINTK("sctp_outq_flush(%p, %p[%s]), ", @@ -1011,6 +1013,13 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) break; case SCTP_XMIT_OK: + /* The sender is in the SHUTDOWN-PENDING state, + * The sender MAY set the I-bit in the DATA + * chunk header. + */ + if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING) + chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM; + break; default: @@ -1063,6 +1072,9 @@ sctp_flush_out: packet = &t->packet; if (!sctp_packet_empty(packet)) error = sctp_packet_transmit(packet); + + /* Clear the burst limited state, if any */ + sctp_transport_burst_reset(t); } return error; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 08ef203d36ac..a3c8988758b1 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1258,6 +1258,9 @@ SCTP_STATIC __init int sctp_init(void) /* Set SCOPE policy to enabled */ sctp_scope_policy = SCTP_SCOPE_POLICY_ENABLE; + /* Set the default rwnd update threshold */ + sctp_rwnd_upd_shift = SCTP_DEFAULT_RWND_SHIFT; + sctp_sysctl_register(); INIT_LIST_HEAD(&sctp_address_families); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 9d881a61ac02..9e732916b671 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -987,7 +987,10 @@ static void *sctp_addto_param(struct sctp_chunk *chunk, int len, target = skb_put(chunk->skb, len); - memcpy(target, data, len); + if (data) + memcpy(target, data, len); + else + memset(target, 0, len); /* Adjust the chunk length field. */ chunk->chunk_hdr->length = htons(chunklen + len); @@ -1129,16 +1132,18 @@ nodata: struct sctp_chunk *sctp_make_op_error(const struct sctp_association *asoc, const struct sctp_chunk *chunk, __be16 cause_code, const void *payload, - size_t paylen) + size_t paylen, size_t reserve_tail) { struct sctp_chunk *retval; - retval = sctp_make_op_error_space(asoc, chunk, paylen); + retval = sctp_make_op_error_space(asoc, chunk, paylen + reserve_tail); if (!retval) goto nodata; - sctp_init_cause(retval, cause_code, paylen); + sctp_init_cause(retval, cause_code, paylen + reserve_tail); sctp_addto_chunk(retval, paylen, payload); + if (reserve_tail) + sctp_addto_param(retval, reserve_tail, NULL); nodata: return retval; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 8674d4919556..d771cc1b777a 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -217,8 +217,7 @@ static int sctp_gen_sack(struct sctp_association *asoc, int force, sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_SACK)); } else { - if (asoc->a_rwnd > asoc->rwnd) - asoc->a_rwnd = asoc->rwnd; + asoc->a_rwnd = asoc->rwnd; sack = sctp_make_sack(asoc); if (!sack) goto nomem; @@ -480,7 +479,6 @@ static void sctp_do_8_2_transport_strike(struct sctp_association *asoc, * that indicates that we have an outstanding HB. */ if (!is_hb || transport->hb_sent) { - transport->last_rto = transport->rto; transport->rto = min((transport->rto * 2), transport->asoc->rto_max); } } @@ -1418,6 +1416,8 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, asoc->init_last_sent_to = t; chunk->transport = t; t->init_sent_count++; + /* Set the new transport as primary */ + sctp_assoc_set_primary(asoc, t); break; case SCTP_CMD_INIT_RESTART: diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index d4df45022ffa..1ef9de9bbae9 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -996,14 +996,15 @@ sctp_disposition_t sctp_sf_sendbeat_8_3(const struct sctp_endpoint *ep, sctp_sf_heartbeat(ep, asoc, type, arg, commands)) return SCTP_DISPOSITION_NOMEM; + /* Set transport error counter and association error counter * when sending heartbeat. */ - sctp_add_cmd_sf(commands, SCTP_CMD_TRANSPORT_IDLE, - SCTP_TRANSPORT(transport)); sctp_add_cmd_sf(commands, SCTP_CMD_TRANSPORT_HB_SENT, SCTP_TRANSPORT(transport)); } + sctp_add_cmd_sf(commands, SCTP_CMD_TRANSPORT_IDLE, + SCTP_TRANSPORT(transport)); sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMER_UPDATE, SCTP_TRANSPORT(transport)); @@ -1720,7 +1721,7 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(const struct sctp_endpoint *ep, err = sctp_make_op_error(asoc, chunk, SCTP_ERROR_COOKIE_IN_SHUTDOWN, - NULL, 0); + NULL, 0, 0); if (err) sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err)); @@ -2868,6 +2869,7 @@ sctp_disposition_t sctp_sf_eat_data_6_2(const struct sctp_endpoint *ep, sctp_cmd_seq_t *commands) { struct sctp_chunk *chunk = arg; + sctp_arg_t force = SCTP_NOFORCE(); int error; if (!sctp_vtag_verify(chunk, asoc)) { @@ -2901,6 +2903,9 @@ sctp_disposition_t sctp_sf_eat_data_6_2(const struct sctp_endpoint *ep, BUG(); } + if (chunk->chunk_hdr->flags & SCTP_DATA_SACK_IMM) + force = SCTP_FORCE(); + if (asoc->autoclose) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_AUTOCLOSE)); @@ -2929,7 +2934,7 @@ sctp_disposition_t sctp_sf_eat_data_6_2(const struct sctp_endpoint *ep, * more aggressive than the following algorithms allow. */ if (chunk->end_of_packet) - sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, SCTP_NOFORCE()); + sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, force); return SCTP_DISPOSITION_CONSUME; @@ -2954,7 +2959,7 @@ discard_force: discard_noforce: if (chunk->end_of_packet) - sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, SCTP_NOFORCE()); + sctp_add_cmd_sf(commands, SCTP_CMD_GEN_SACK, force); return SCTP_DISPOSITION_DISCARD; consume: @@ -3973,7 +3978,7 @@ sctp_disposition_t sctp_sf_eat_auth(const struct sctp_endpoint *ep, err_chunk = sctp_make_op_error(asoc, chunk, SCTP_ERROR_UNSUP_HMAC, &auth_hdr->hmac_id, - sizeof(__u16)); + sizeof(__u16), 0); if (err_chunk) { sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err_chunk)); @@ -4065,7 +4070,8 @@ sctp_disposition_t sctp_sf_unk_chunk(const struct sctp_endpoint *ep, hdr = unk_chunk->chunk_hdr; err_chunk = sctp_make_op_error(asoc, unk_chunk, SCTP_ERROR_UNKNOWN_CHUNK, hdr, - WORD_ROUND(ntohs(hdr->length))); + WORD_ROUND(ntohs(hdr->length)), + 0); if (err_chunk) { sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err_chunk)); @@ -4084,7 +4090,8 @@ sctp_disposition_t sctp_sf_unk_chunk(const struct sctp_endpoint *ep, hdr = unk_chunk->chunk_hdr; err_chunk = sctp_make_op_error(asoc, unk_chunk, SCTP_ERROR_UNKNOWN_CHUNK, hdr, - WORD_ROUND(ntohs(hdr->length))); + WORD_ROUND(ntohs(hdr->length)), + 0); if (err_chunk) { sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err_chunk)); @@ -6048,7 +6055,8 @@ static int sctp_eat_data(const struct sctp_association *asoc, err = sctp_make_op_error(asoc, chunk, SCTP_ERROR_INV_STRM, &data_hdr->stream, - sizeof(data_hdr->stream)); + sizeof(data_hdr->stream), + sizeof(u16)); if (err) sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(err)); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 66b1f02b17ba..89ab66e54740 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2086,6 +2086,9 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, return -EINVAL; if (copy_from_user(&sp->autoclose, optval, optlen)) return -EFAULT; + /* make sure it won't exceed MAX_SCHEDULE_TIMEOUT */ + if (sp->autoclose > (MAX_SCHEDULE_TIMEOUT / HZ) ) + sp->autoclose = (__u32)(MAX_SCHEDULE_TIMEOUT / HZ) ; return 0; } @@ -2311,11 +2314,10 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, } } - /* Note that unless the spp_flag is set to SPP_PMTUD_ENABLE the value - * of this field is ignored. Note also that a value of zero - * indicates the current setting should be left unchanged. + /* Note that a value of zero indicates the current setting should be + left unchanged. */ - if ((params->spp_flags & SPP_PMTUD_ENABLE) && params->spp_pathmaxrxt) { + if (params->spp_pathmaxrxt) { if (trans) { trans->pathmaxrxt = params->spp_pathmaxrxt; } else if (asoc) { @@ -2354,8 +2356,8 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk, pmtud_change == SPP_PMTUD || sackdelay_change == SPP_SACKDELAY || params.spp_sackdelay > 500 || - (params.spp_pathmtu - && params.spp_pathmtu < SCTP_DEFAULT_MINSEGMENT)) + (params.spp_pathmtu && + params.spp_pathmtu < SCTP_DEFAULT_MINSEGMENT)) return -EINVAL; /* If an address other than INADDR_ANY is specified, and @@ -4349,90 +4351,6 @@ static int sctp_getsockopt_initmsg(struct sock *sk, int len, char __user *optval return 0; } -static int sctp_getsockopt_peer_addrs_num_old(struct sock *sk, int len, - char __user *optval, - int __user *optlen) -{ - sctp_assoc_t id; - struct sctp_association *asoc; - struct list_head *pos; - int cnt = 0; - - if (len < sizeof(sctp_assoc_t)) - return -EINVAL; - - if (copy_from_user(&id, optval, sizeof(sctp_assoc_t))) - return -EFAULT; - - printk(KERN_WARNING "SCTP: Use of SCTP_GET_PEER_ADDRS_NUM_OLD " - "socket option deprecated\n"); - /* For UDP-style sockets, id specifies the association to query. */ - asoc = sctp_id2assoc(sk, id); - if (!asoc) - return -EINVAL; - - list_for_each(pos, &asoc->peer.transport_addr_list) { - cnt ++; - } - - return cnt; -} - -/* - * Old API for getting list of peer addresses. Does not work for 32-bit - * programs running on a 64-bit kernel - */ -static int sctp_getsockopt_peer_addrs_old(struct sock *sk, int len, - char __user *optval, - int __user *optlen) -{ - struct sctp_association *asoc; - int cnt = 0; - struct sctp_getaddrs_old getaddrs; - struct sctp_transport *from; - void __user *to; - union sctp_addr temp; - struct sctp_sock *sp = sctp_sk(sk); - int addrlen; - - if (len < sizeof(struct sctp_getaddrs_old)) - return -EINVAL; - - len = sizeof(struct sctp_getaddrs_old); - - if (copy_from_user(&getaddrs, optval, len)) - return -EFAULT; - - if (getaddrs.addr_num <= 0) return -EINVAL; - - printk(KERN_WARNING "SCTP: Use of SCTP_GET_PEER_ADDRS_OLD " - "socket option deprecated\n"); - - /* For UDP-style sockets, id specifies the association to query. */ - asoc = sctp_id2assoc(sk, getaddrs.assoc_id); - if (!asoc) - return -EINVAL; - - to = (void __user *)getaddrs.addrs; - list_for_each_entry(from, &asoc->peer.transport_addr_list, - transports) { - memcpy(&temp, &from->ipaddr, sizeof(temp)); - sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp); - addrlen = sctp_get_af_specific(sk->sk_family)->sockaddr_len; - if (copy_to_user(to, &temp, addrlen)) - return -EFAULT; - to += addrlen ; - cnt ++; - if (cnt >= getaddrs.addr_num) break; - } - getaddrs.addr_num = cnt; - if (put_user(len, optlen)) - return -EFAULT; - if (copy_to_user(optval, &getaddrs, len)) - return -EFAULT; - - return 0; -} static int sctp_getsockopt_peer_addrs(struct sock *sk, int len, char __user *optval, int __user *optlen) @@ -4485,125 +4403,6 @@ static int sctp_getsockopt_peer_addrs(struct sock *sk, int len, return 0; } -static int sctp_getsockopt_local_addrs_num_old(struct sock *sk, int len, - char __user *optval, - int __user *optlen) -{ - sctp_assoc_t id; - struct sctp_bind_addr *bp; - struct sctp_association *asoc; - struct sctp_sockaddr_entry *addr; - int cnt = 0; - - if (len < sizeof(sctp_assoc_t)) - return -EINVAL; - - if (copy_from_user(&id, optval, sizeof(sctp_assoc_t))) - return -EFAULT; - - printk(KERN_WARNING "SCTP: Use of SCTP_GET_LOCAL_ADDRS_NUM_OLD " - "socket option deprecated\n"); - - /* - * For UDP-style sockets, id specifies the association to query. - * If the id field is set to the value '0' then the locally bound - * addresses are returned without regard to any particular - * association. - */ - if (0 == id) { - bp = &sctp_sk(sk)->ep->base.bind_addr; - } else { - asoc = sctp_id2assoc(sk, id); - if (!asoc) - return -EINVAL; - bp = &asoc->base.bind_addr; - } - - /* If the endpoint is bound to 0.0.0.0 or ::0, count the valid - * addresses from the global local address list. - */ - if (sctp_list_single_entry(&bp->address_list)) { - addr = list_entry(bp->address_list.next, - struct sctp_sockaddr_entry, list); - if (sctp_is_any(sk, &addr->a)) { - rcu_read_lock(); - list_for_each_entry_rcu(addr, - &sctp_local_addr_list, list) { - if (!addr->valid) - continue; - - if ((PF_INET == sk->sk_family) && - (AF_INET6 == addr->a.sa.sa_family)) - continue; - - if ((PF_INET6 == sk->sk_family) && - inet_v6_ipv6only(sk) && - (AF_INET == addr->a.sa.sa_family)) - continue; - - cnt++; - } - rcu_read_unlock(); - } else { - cnt = 1; - } - goto done; - } - - /* Protection on the bound address list is not needed, - * since in the socket option context we hold the socket lock, - * so there is no way that the bound address list can change. - */ - list_for_each_entry(addr, &bp->address_list, list) { - cnt ++; - } -done: - return cnt; -} - -/* Helper function that copies local addresses to user and returns the number - * of addresses copied. - */ -static int sctp_copy_laddrs_old(struct sock *sk, __u16 port, - int max_addrs, void *to, - int *bytes_copied) -{ - struct sctp_sockaddr_entry *addr; - union sctp_addr temp; - int cnt = 0; - int addrlen; - - rcu_read_lock(); - list_for_each_entry_rcu(addr, &sctp_local_addr_list, list) { - if (!addr->valid) - continue; - - if ((PF_INET == sk->sk_family) && - (AF_INET6 == addr->a.sa.sa_family)) - continue; - if ((PF_INET6 == sk->sk_family) && - inet_v6_ipv6only(sk) && - (AF_INET == addr->a.sa.sa_family)) - continue; - memcpy(&temp, &addr->a, sizeof(temp)); - if (!temp.v4.sin_port) - temp.v4.sin_port = htons(port); - - sctp_get_pf_specific(sk->sk_family)->addr_v4map(sctp_sk(sk), - &temp); - addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len; - memcpy(to, &temp, addrlen); - - to += addrlen; - *bytes_copied += addrlen; - cnt ++; - if (cnt >= max_addrs) break; - } - rcu_read_unlock(); - - return cnt; -} - static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to, size_t space_left, int *bytes_copied) { @@ -4647,112 +4446,6 @@ static int sctp_copy_laddrs(struct sock *sk, __u16 port, void *to, return cnt; } -/* Old API for getting list of local addresses. Does not work for 32-bit - * programs running on a 64-bit kernel - */ -static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len, - char __user *optval, int __user *optlen) -{ - struct sctp_bind_addr *bp; - struct sctp_association *asoc; - int cnt = 0; - struct sctp_getaddrs_old getaddrs; - struct sctp_sockaddr_entry *addr; - void __user *to; - union sctp_addr temp; - struct sctp_sock *sp = sctp_sk(sk); - int addrlen; - int err = 0; - void *addrs; - void *buf; - int bytes_copied = 0; - - if (len < sizeof(struct sctp_getaddrs_old)) - return -EINVAL; - - len = sizeof(struct sctp_getaddrs_old); - if (copy_from_user(&getaddrs, optval, len)) - return -EFAULT; - - if (getaddrs.addr_num <= 0 || - getaddrs.addr_num >= (INT_MAX / sizeof(union sctp_addr))) - return -EINVAL; - - printk(KERN_WARNING "SCTP: Use of SCTP_GET_LOCAL_ADDRS_OLD " - "socket option deprecated\n"); - - /* - * For UDP-style sockets, id specifies the association to query. - * If the id field is set to the value '0' then the locally bound - * addresses are returned without regard to any particular - * association. - */ - if (0 == getaddrs.assoc_id) { - bp = &sctp_sk(sk)->ep->base.bind_addr; - } else { - asoc = sctp_id2assoc(sk, getaddrs.assoc_id); - if (!asoc) - return -EINVAL; - bp = &asoc->base.bind_addr; - } - - to = getaddrs.addrs; - - /* Allocate space for a local instance of packed array to hold all - * the data. We store addresses here first and then put write them - * to the user in one shot. - */ - addrs = kmalloc(sizeof(union sctp_addr) * getaddrs.addr_num, - GFP_KERNEL); - if (!addrs) - return -ENOMEM; - - /* If the endpoint is bound to 0.0.0.0 or ::0, get the valid - * addresses from the global local address list. - */ - if (sctp_list_single_entry(&bp->address_list)) { - addr = list_entry(bp->address_list.next, - struct sctp_sockaddr_entry, list); - if (sctp_is_any(sk, &addr->a)) { - cnt = sctp_copy_laddrs_old(sk, bp->port, - getaddrs.addr_num, - addrs, &bytes_copied); - goto copy_getaddrs; - } - } - - buf = addrs; - /* Protection on the bound address list is not needed since - * in the socket option context we hold a socket lock and - * thus the bound address list can't change. - */ - list_for_each_entry(addr, &bp->address_list, list) { - memcpy(&temp, &addr->a, sizeof(temp)); - sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp); - addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len; - memcpy(buf, &temp, addrlen); - buf += addrlen; - bytes_copied += addrlen; - cnt ++; - if (cnt >= getaddrs.addr_num) break; - } - -copy_getaddrs: - /* copy the entire address list into the user provided space */ - if (copy_to_user(to, addrs, bytes_copied)) { - err = -EFAULT; - goto error; - } - - /* copy the leading structure back to user */ - getaddrs.addr_num = cnt; - if (copy_to_user(optval, &getaddrs, len)) - err = -EFAULT; - -error: - kfree(addrs); - return err; -} static int sctp_getsockopt_local_addrs(struct sock *sk, int len, char __user *optval, int __user *optlen) @@ -5603,22 +5296,6 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname, case SCTP_INITMSG: retval = sctp_getsockopt_initmsg(sk, len, optval, optlen); break; - case SCTP_GET_PEER_ADDRS_NUM_OLD: - retval = sctp_getsockopt_peer_addrs_num_old(sk, len, optval, - optlen); - break; - case SCTP_GET_LOCAL_ADDRS_NUM_OLD: - retval = sctp_getsockopt_local_addrs_num_old(sk, len, optval, - optlen); - break; - case SCTP_GET_PEER_ADDRS_OLD: - retval = sctp_getsockopt_peer_addrs_old(sk, len, optval, - optlen); - break; - case SCTP_GET_LOCAL_ADDRS_OLD: - retval = sctp_getsockopt_local_addrs_old(sk, len, optval, - optlen); - break; case SCTP_GET_PEER_ADDRS: retval = sctp_getsockopt_peer_addrs(sk, len, optval, optlen); diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index ab7151da120f..ae03ded2bf1a 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -52,6 +52,7 @@ static int int_max = INT_MAX; static int sack_timer_min = 1; static int sack_timer_max = 500; static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */ +static int rwnd_scale_max = 16; extern int sysctl_sctp_mem[3]; extern int sysctl_sctp_rmem[3]; @@ -284,6 +285,18 @@ static ctl_table sctp_table[] = { .extra1 = &zero, .extra2 = &addr_scope_max, }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "rwnd_update_shift", + .data = &sctp_rwnd_upd_shift, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &one, + .extra2 = &rwnd_scale_max, + }, + { .ctl_name = 0 } }; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 3b141bb32faf..b827d21dbe54 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -74,7 +74,7 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, * given destination transport address, set RTO to the protocol * parameter 'RTO.Initial'. */ - peer->last_rto = peer->rto = msecs_to_jiffies(sctp_rto_initial); + peer->rto = msecs_to_jiffies(sctp_rto_initial); peer->rtt = 0; peer->rttvar = 0; peer->srtt = 0; @@ -83,7 +83,6 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, peer->fast_recovery = 0; peer->last_time_heard = jiffies; - peer->last_time_used = jiffies; peer->last_time_ecne_reduced = jiffies; peer->init_sent_count = 0; @@ -386,7 +385,6 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) tp->rto = tp->asoc->rto_max; tp->rtt = rtt; - tp->last_rto = tp->rto; /* Reset rto_pending so that a new RTT measurement is started when a * new data chunk is sent. @@ -565,10 +563,8 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport, * to be done every RTO interval, we do it every hearbeat * interval. */ - if (time_after(jiffies, transport->last_time_used + - transport->rto)) - transport->cwnd = max(transport->cwnd/2, - 4*transport->asoc->pathmtu); + transport->cwnd = max(transport->cwnd/2, + 4*transport->asoc->pathmtu); break; } @@ -579,6 +575,43 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport, transport->cwnd, transport->ssthresh); } +/* Apply Max.Burst limit to the congestion window: + * sctpimpguide-05 2.14.2 + * D) When the time comes for the sender to + * transmit new DATA chunks, the protocol parameter Max.Burst MUST + * first be applied to limit how many new DATA chunks may be sent. + * The limit is applied by adjusting cwnd as follows: + * if ((flightsize+ Max.Burst * MTU) < cwnd) + * cwnd = flightsize + Max.Burst * MTU + */ + +void sctp_transport_burst_limited(struct sctp_transport *t) +{ + struct sctp_association *asoc = t->asoc; + u32 old_cwnd = t->cwnd; + u32 max_burst_bytes; + + if (t->burst_limited) + return; + + max_burst_bytes = t->flight_size + (asoc->max_burst * asoc->pathmtu); + if (max_burst_bytes < old_cwnd) { + t->cwnd = max_burst_bytes; + t->burst_limited = old_cwnd; + } +} + +/* Restore the old cwnd congestion window, after the burst had it's + * desired effect. + */ +void sctp_transport_burst_reset(struct sctp_transport *t) +{ + if (t->burst_limited) { + t->cwnd = t->burst_limited; + t->burst_limited = 0; + } +} + /* What is the next timeout value for this transport? */ unsigned long sctp_transport_timeout(struct sctp_transport *t) { @@ -601,8 +634,9 @@ void sctp_transport_reset(struct sctp_transport *t) * (see Section 6.2.1) */ t->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380)); + t->burst_limited = 0; t->ssthresh = asoc->peer.i.a_rwnd; - t->last_rto = t->rto = asoc->rto_initial; + t->rto = asoc->rto_initial; t->rtt = 0; t->srtt = 0; t->rttvar = 0; diff --git a/net/socket.c b/net/socket.c index 402abb39cbfe..b94c3dd71015 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2144,6 +2144,7 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, int fput_needed, err, datagrams; struct socket *sock; struct mmsghdr __user *entry; + struct compat_mmsghdr __user *compat_entry; struct msghdr msg_sys; struct timespec end_time; @@ -2163,19 +2164,30 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, goto out_put; entry = mmsg; + compat_entry = (struct compat_mmsghdr __user *)mmsg; while (datagrams < vlen) { /* * No need to ask LSM for more than the first datagram. */ - err = __sys_recvmsg(sock, (struct msghdr __user *)entry, - &msg_sys, flags, datagrams); - if (err < 0) - break; - err = put_user(err, &entry->msg_len); + if (MSG_CMSG_COMPAT & flags) { + err = __sys_recvmsg(sock, (struct msghdr __user *)compat_entry, + &msg_sys, flags, datagrams); + if (err < 0) + break; + err = __put_user(err, &compat_entry->msg_len); + ++compat_entry; + } else { + err = __sys_recvmsg(sock, (struct msghdr __user *)entry, + &msg_sys, flags, datagrams); + if (err < 0) + break; + err = put_user(err, &entry->msg_len); + ++entry; + } + if (err) break; - ++entry; ++datagrams; if (timeout) { diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c index 22e8fd89477f..c7450c8f0a7c 100644 --- a/net/sunrpc/addr.c +++ b/net/sunrpc/addr.c @@ -306,24 +306,25 @@ EXPORT_SYMBOL_GPL(rpc_sockaddr2uaddr); * @sap: buffer into which to plant socket address * @salen: size of buffer * + * @uaddr does not have to be '\0'-terminated, but strict_strtoul() and + * rpc_pton() require proper string termination to be successful. + * * Returns the size of the socket address if successful; otherwise * zero is returned. */ size_t rpc_uaddr2sockaddr(const char *uaddr, const size_t uaddr_len, struct sockaddr *sap, const size_t salen) { - char *c, buf[RPCBIND_MAXUADDRLEN]; + char *c, buf[RPCBIND_MAXUADDRLEN + sizeof('\0')]; unsigned long portlo, porthi; unsigned short port; - if (uaddr_len > sizeof(buf)) + if (uaddr_len > RPCBIND_MAXUADDRLEN) return 0; memcpy(buf, uaddr, uaddr_len); - buf[uaddr_len] = '\n'; - buf[uaddr_len + 1] = '\0'; - + buf[uaddr_len] = '\0'; c = strrchr(buf, '.'); if (unlikely(c == NULL)) return 0; @@ -332,9 +333,7 @@ size_t rpc_uaddr2sockaddr(const char *uaddr, const size_t uaddr_len, if (unlikely(portlo > 255)) return 0; - c[0] = '\n'; - c[1] = '\0'; - + *c = '\0'; c = strrchr(buf, '.'); if (unlikely(c == NULL)) return 0; @@ -345,8 +344,7 @@ size_t rpc_uaddr2sockaddr(const char *uaddr, const size_t uaddr_len, port = (unsigned short)((porthi << 8) | portlo); - c[0] = '\0'; - + *c = '\0'; if (rpc_pton(buf, strlen(buf), sap, salen) == 0) return 0; diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 54a4e042f104..7535a7bed2fa 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -332,9 +332,9 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, list_add_tail(&new->cr_lru, &free); spin_unlock(&cache->lock); found: - if (test_bit(RPCAUTH_CRED_NEW, &cred->cr_flags) - && cred->cr_ops->cr_init != NULL - && !(flags & RPCAUTH_LOOKUP_NEW)) { + if (test_bit(RPCAUTH_CRED_NEW, &cred->cr_flags) && + cred->cr_ops->cr_init != NULL && + !(flags & RPCAUTH_LOOKUP_NEW)) { int res = cred->cr_ops->cr_init(auth, cred); if (res < 0) { put_rpccred(cred); diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c index f160be6c1a46..17562b4c35f6 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c +++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c @@ -75,8 +75,8 @@ krb5_get_seq_num(struct crypto_blkcipher *key, if ((code = krb5_decrypt(key, cksum, buf, plain, 8))) return code; - if ((plain[4] != plain[5]) || (plain[4] != plain[6]) - || (plain[4] != plain[7])) + if ((plain[4] != plain[5]) || (plain[4] != plain[6]) || + (plain[4] != plain[7])) return (s32)KG_BAD_SEQ; *direction = plain[4]; diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index f6c51e562a02..e34bc531fcb9 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -105,8 +105,8 @@ static int rsi_match(struct cache_head *a, struct cache_head *b) { struct rsi *item = container_of(a, struct rsi, h); struct rsi *tmp = container_of(b, struct rsi, h); - return netobj_equal(&item->in_handle, &tmp->in_handle) - && netobj_equal(&item->in_token, &tmp->in_token); + return netobj_equal(&item->in_handle, &tmp->in_handle) && + netobj_equal(&item->in_token, &tmp->in_token); } static int dup_to_netobj(struct xdr_netobj *dst, char *src, int len) diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index d6eee291a0e2..39bddba53ba1 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -401,9 +401,8 @@ static int cache_clean(void) for (; ch; cp= & ch->next, ch= *cp) { if (current_detail->nextcheck > ch->expiry_time) current_detail->nextcheck = ch->expiry_time+1; - if (ch->expiry_time >= get_seconds() - && ch->last_refresh >= current_detail->flush_time - ) + if (ch->expiry_time >= get_seconds() && + ch->last_refresh >= current_detail->flush_time) continue; if (test_and_clear_bit(CACHE_PENDING, &ch->flags)) cache_dequeue(current_detail, ch); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 952f206ff307..538ca433a56c 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1103,8 +1103,9 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) procp->pc_release(rqstp, NULL, rqstp->rq_resp); goto dropit; } - if (*statp == rpc_success && (xdr = procp->pc_encode) - && !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) { + if (*statp == rpc_success && + (xdr = procp->pc_encode) && + !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) { dprintk("svc: failed to encode reply\n"); /* serv->sv_stats->rpcsystemerr++; */ *statp = rpc_system_err; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index df124f78ee48..b845e2293dfe 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -129,8 +129,8 @@ static void svc_xprt_free(struct kref *kref) struct svc_xprt *xprt = container_of(kref, struct svc_xprt, xpt_ref); struct module *owner = xprt->xpt_class->xcl_owner; - if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags) - && xprt->xpt_auth_cache != NULL) + if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags) && + xprt->xpt_auth_cache != NULL) svcauth_unix_info_release(xprt->xpt_auth_cache); xprt->xpt_ops->xpo_free(xprt); module_put(owner); @@ -846,8 +846,8 @@ static void svc_age_temp_xprts(unsigned long closure) * through, close it. */ if (!test_and_set_bit(XPT_OLD, &xprt->xpt_flags)) continue; - if (atomic_read(&xprt->xpt_ref.refcount) > 1 - || test_bit(XPT_BUSY, &xprt->xpt_flags)) + if (atomic_read(&xprt->xpt_ref.refcount) > 1 || + test_bit(XPT_BUSY, &xprt->xpt_flags)) continue; svc_xprt_get(xprt); list_move(le, &to_be_aged); diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index e64109b02aee..4e9393c24687 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -46,8 +46,8 @@ svc_authenticate(struct svc_rqst *rqstp, __be32 *authp) dprintk("svc: svc_authenticate (%d)\n", flavor); spin_lock(&authtab_lock); - if (flavor >= RPC_AUTH_MAXFLAVOR || !(aops = authtab[flavor]) - || !try_module_get(aops->owner)) { + if (flavor >= RPC_AUTH_MAXFLAVOR || !(aops = authtab[flavor]) || + !try_module_get(aops->owner)) { spin_unlock(&authtab_lock); *authp = rpc_autherr_badcred; return SVC_DENIED; diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index f4c7ff3a53e6..4a8f6558718a 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -125,8 +125,8 @@ static int ip_map_match(struct cache_head *corig, struct cache_head *cnew) { struct ip_map *orig = container_of(corig, struct ip_map, h); struct ip_map *new = container_of(cnew, struct ip_map, h); - return strcmp(orig->m_class, new->m_class) == 0 - && ipv6_addr_equal(&orig->m_addr, &new->m_addr); + return strcmp(orig->m_class, new->m_class) == 0 && + ipv6_addr_equal(&orig->m_addr, &new->m_addr); } static void ip_map_init(struct cache_head *cnew, struct cache_head *citem) { diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 9e884383134f..f92e37eb413c 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -337,10 +337,9 @@ static int rdma_set_ctxt_sge(struct svcxprt_rdma *xprt, static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count) { - if ((RDMA_TRANSPORT_IWARP == - rdma_node_get_transport(xprt->sc_cm_id-> - device->node_type)) - && sge_count > 1) + if ((rdma_node_get_transport(xprt->sc_cm_id->device->node_type) == + RDMA_TRANSPORT_IWARP) && + sge_count > 1) return 1; else return min_t(int, sge_count, xprt->sc_max_sge); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 465aafc2007f..2209aa87d899 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -878,8 +878,8 @@ if (strnicmp(ia->ri_id->device->dma_device->bus->name, "pci", 3) == 0) { * others indicate a transport condition which has already * undergone a best-effort. */ - if (ep->rep_connected == -ECONNREFUSED - && ++retry_count <= RDMA_CONNECT_RETRY_MAX) { + if (ep->rep_connected == -ECONNREFUSED && + ++retry_count <= RDMA_CONNECT_RETRY_MAX) { dprintk("RPC: %s: non-peer_reject, retry\n", __func__); goto retry; } diff --git a/net/tipc/cluster.c b/net/tipc/cluster.c index 689fdefe9d04..a7eac00cd363 100644 --- a/net/tipc/cluster.c +++ b/net/tipc/cluster.c @@ -437,11 +437,11 @@ void tipc_cltr_recv_routing_table(struct sk_buff *buf) break; case ROUTE_ADDITION: if (!is_slave(tipc_own_addr)) { - assert(!in_own_cluster(c_ptr->addr) - || is_slave(rem_node)); + assert(!in_own_cluster(c_ptr->addr) || + is_slave(rem_node)); } else { - assert(in_own_cluster(c_ptr->addr) - && !is_slave(rem_node)); + assert(in_own_cluster(c_ptr->addr) && + !is_slave(rem_node)); } n_ptr = c_ptr->nodes[tipc_node(rem_node)]; if (!n_ptr) @@ -451,11 +451,11 @@ void tipc_cltr_recv_routing_table(struct sk_buff *buf) break; case ROUTE_REMOVAL: if (!is_slave(tipc_own_addr)) { - assert(!in_own_cluster(c_ptr->addr) - || is_slave(rem_node)); + assert(!in_own_cluster(c_ptr->addr) || + is_slave(rem_node)); } else { - assert(in_own_cluster(c_ptr->addr) - && !is_slave(rem_node)); + assert(in_own_cluster(c_ptr->addr) && + !is_slave(rem_node)); } n_ptr = c_ptr->nodes[tipc_node(rem_node)]; if (n_ptr) diff --git a/net/tipc/link.c b/net/tipc/link.c index dd4c18b9a35b..6f50f6423f63 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -378,8 +378,8 @@ static void link_timeout(struct link *l_ptr) struct tipc_msg *msg = buf_msg(l_ptr->first_out); u32 length = msg_size(msg); - if ((msg_user(msg) == MSG_FRAGMENTER) - && (msg_type(msg) == FIRST_FRAGMENT)) { + if ((msg_user(msg) == MSG_FRAGMENTER) && + (msg_type(msg) == FIRST_FRAGMENT)) { length = msg_size(msg_get_wrapped(msg)); } if (length) { @@ -2788,8 +2788,8 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, /* Is there an incomplete message waiting for this fragment? */ - while (pbuf && ((msg_seqno(buf_msg(pbuf)) != long_msg_seq_no) - || (msg_orignode(fragm) != msg_orignode(buf_msg(pbuf))))) { + while (pbuf && ((msg_seqno(buf_msg(pbuf)) != long_msg_seq_no) || + (msg_orignode(fragm) != msg_orignode(buf_msg(pbuf))))) { prev = pbuf; pbuf = pbuf->next; } @@ -3325,8 +3325,8 @@ static void link_print(struct link *l_ptr, struct print_buf *buf, (l_ptr->last_out)), l_ptr->out_queue_size); if ((mod(msg_seqno(buf_msg(l_ptr->last_out)) - msg_seqno(buf_msg(l_ptr->first_out))) - != (l_ptr->out_queue_size - 1)) - || (l_ptr->last_out->next != NULL)) { + != (l_ptr->out_queue_size - 1)) || + (l_ptr->last_out->next != NULL)) { tipc_printf(buf, "\nSend queue inconsistency\n"); tipc_printf(buf, "first_out= %x ", l_ptr->first_out); tipc_printf(buf, "next_out= %x ", l_ptr->next_out); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index d00c2119faf3..1ea64f09cc45 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -195,7 +195,7 @@ static int tipc_create(struct net *net, struct socket *sock, int protocol, /* Validate arguments */ - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; if (unlikely(protocol != 0)) @@ -1136,13 +1136,11 @@ restart: /* Loop around if more data is required */ - if ((sz_copied < buf_len) /* didn't get all requested data */ - && (!skb_queue_empty(&sk->sk_receive_queue) || - (flags & MSG_WAITALL)) - /* ... and more is ready or required */ - && (!(flags & MSG_PEEK)) /* ... and aren't just peeking at data */ - && (!err) /* ... and haven't reached a FIN */ - ) + if ((sz_copied < buf_len) && /* didn't get all requested data */ + (!skb_queue_empty(&sk->sk_receive_queue) || + (flags & MSG_WAITALL)) && /* and more is ready or required */ + (!(flags & MSG_PEEK)) && /* and aren't just peeking at data */ + (!err)) /* and haven't reached a FIN */ goto restart; exit: diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 0747d8a9232f..ac91f0dfa144 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -364,9 +364,9 @@ static struct subscription *subscr_subscribe(struct tipc_subscr *s, sub->seq.upper = htohl(s->seq.upper, swap); sub->timeout = htohl(s->timeout, swap); sub->filter = htohl(s->filter, swap); - if ((!(sub->filter & TIPC_SUB_PORTS) - == !(sub->filter & TIPC_SUB_SERVICE)) - || (sub->seq.lower > sub->seq.upper)) { + if ((!(sub->filter & TIPC_SUB_PORTS) == + !(sub->filter & TIPC_SUB_SERVICE)) || + (sub->seq.lower > sub->seq.upper)) { warn("Subscription rejected, illegal request\n"); kfree(sub); subscr_terminate(subscriber); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 7553ea6edd8f..f25511903115 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1033,8 +1033,8 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, goto out; addr_len = err; - if (test_bit(SOCK_PASSCRED, &sock->flags) - && !u->addr && (err = unix_autobind(sock)) != 0) + if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr && + (err = unix_autobind(sock)) != 0) goto out; timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); @@ -1378,8 +1378,8 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, goto out; } - if (test_bit(SOCK_PASSCRED, &sock->flags) - && !u->addr && (err = unix_autobind(sock)) != 0) + if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr + && (err = unix_autobind(sock)) != 0) goto out; err = -EMSGSIZE; diff --git a/net/wimax/op-rfkill.c b/net/wimax/op-rfkill.c index 94d339c345d2..ae752a64d920 100644 --- a/net/wimax/op-rfkill.c +++ b/net/wimax/op-rfkill.c @@ -107,8 +107,8 @@ void wimax_report_rfkill_hw(struct wimax_dev *wimax_dev, if (state != wimax_dev->rf_hw) { wimax_dev->rf_hw = state; - if (wimax_dev->rf_hw == WIMAX_RF_ON - && wimax_dev->rf_sw == WIMAX_RF_ON) + if (wimax_dev->rf_hw == WIMAX_RF_ON && + wimax_dev->rf_sw == WIMAX_RF_ON) wimax_state = WIMAX_ST_READY; else wimax_state = WIMAX_ST_RADIO_OFF; @@ -163,8 +163,8 @@ void wimax_report_rfkill_sw(struct wimax_dev *wimax_dev, if (state != wimax_dev->rf_sw) { wimax_dev->rf_sw = state; - if (wimax_dev->rf_hw == WIMAX_RF_ON - && wimax_dev->rf_sw == WIMAX_RF_ON) + if (wimax_dev->rf_hw == WIMAX_RF_ON && + wimax_dev->rf_sw == WIMAX_RF_ON) wimax_state = WIMAX_ST_READY; else wimax_state = WIMAX_ST_RADIO_OFF; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index df26228db1b3..12dfa62aad18 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -937,8 +937,8 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info, ie += ie[1] + 2; } - if (bss->pub.capability & (WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_IBSS) - || ismesh) { + if (bss->pub.capability & (WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_IBSS) || + ismesh) { memset(&iwe, 0, sizeof(iwe)); iwe.cmd = SIOCGIWMODE; if (ismesh) diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 6033785f56c5..5e1656bdf23b 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -912,8 +912,9 @@ static int wireless_process_ioctl(struct net *net, struct ifreq *ifr, */ static int wext_permission_check(unsigned int cmd) { - if ((IW_IS_SET(cmd) || cmd == SIOCGIWENCODE || cmd == SIOCGIWENCODEEXT) - && !capable(CAP_NET_ADMIN)) + if ((IW_IS_SET(cmd) || cmd == SIOCGIWENCODE || + cmd == SIOCGIWENCODEEXT) && + !capable(CAP_NET_ADMIN)) return -EPERM; return 0; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index ac7dba46fa33..e3219e4cd044 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -514,7 +514,7 @@ static int x25_create(struct net *net, struct socket *sock, int protocol, struct x25_sock *x25; int rc = -ESOCKTNOSUPPORT; - if (net != &init_net) + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; if (sock->type != SOCK_SEQPACKET || protocol) @@ -1721,20 +1721,31 @@ static int __init x25_init(void) if (rc != 0) goto out; - sock_register(&x25_family_ops); + rc = sock_register(&x25_family_ops); + if (rc != 0) + goto out_proto; dev_add_pack(&x25_packet_type); - register_netdevice_notifier(&x25_dev_notifier); + rc = register_netdevice_notifier(&x25_dev_notifier); + if (rc != 0) + goto out_sock; printk(KERN_INFO "X.25 for Linux Version 0.2\n"); -#ifdef CONFIG_SYSCTL x25_register_sysctl(); -#endif - x25_proc_init(); + rc = x25_proc_init(); + if (rc != 0) + goto out_dev; out: return rc; +out_dev: + unregister_netdevice_notifier(&x25_dev_notifier); +out_sock: + sock_unregister(AF_X25); +out_proto: + proto_unregister(&x25_proto); + goto out; } module_init(x25_init); @@ -1744,9 +1755,7 @@ static void __exit x25_exit(void) x25_link_free(); x25_route_free(); -#ifdef CONFIG_SYSCTL x25_unregister_sysctl(); -#endif unregister_netdevice_notifier(&x25_dev_notifier); diff --git a/net/x25/x25_route.c b/net/x25/x25_route.c index 66961ea28c91..b95fae9ab393 100644 --- a/net/x25/x25_route.c +++ b/net/x25/x25_route.c @@ -136,8 +136,10 @@ struct net_device *x25_dev_get(char *devname) #if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE) && dev->type != ARPHRD_ETHER #endif - ))) + ))){ dev_put(dev); + dev = NULL; + } return dev; } diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index b39341072aa6..743c0134a6a9 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -200,6 +200,40 @@ static struct xfrm_algo_desc aalg_list[] = { } }, { + .name = "hmac(sha384)", + + .uinfo = { + .auth = { + .icv_truncbits = 192, + .icv_fullbits = 384, + } + }, + + .desc = { + .sadb_alg_id = SADB_X_AALG_SHA2_384HMAC, + .sadb_alg_ivlen = 0, + .sadb_alg_minbits = 384, + .sadb_alg_maxbits = 384 + } +}, +{ + .name = "hmac(sha512)", + + .uinfo = { + .auth = { + .icv_truncbits = 256, + .icv_fullbits = 512, + } + }, + + .desc = { + .sadb_alg_id = SADB_X_AALG_SHA2_512HMAC, + .sadb_alg_ivlen = 0, + .sadb_alg_minbits = 512, + .sadb_alg_maxbits = 512 + } +}, +{ .name = "hmac(rmd160)", .compat = "rmd160", @@ -365,6 +399,7 @@ static struct xfrm_algo_desc ealg_list[] = { }, { .name = "cbc(camellia)", + .compat = "camellia", .uinfo = { .encr = { diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index e9ac0cec0877..d847f1a52b44 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1114,7 +1114,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) x->props.saddr = orig->props.saddr; if (orig->aalg) { - x->aalg = xfrm_algo_clone(orig->aalg); + x->aalg = xfrm_algo_auth_clone(orig->aalg); if (!x->aalg) goto error; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index b95a2d64eb59..1ada6186933c 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -62,6 +62,22 @@ static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type) return 0; } +static int verify_auth_trunc(struct nlattr **attrs) +{ + struct nlattr *rt = attrs[XFRMA_ALG_AUTH_TRUNC]; + struct xfrm_algo_auth *algp; + + if (!rt) + return 0; + + algp = nla_data(rt); + if (nla_len(rt) < xfrm_alg_auth_len(algp)) + return -EINVAL; + + algp->alg_name[CRYPTO_MAX_ALG_NAME - 1] = '\0'; + return 0; +} + static int verify_aead(struct nlattr **attrs) { struct nlattr *rt = attrs[XFRMA_ALG_AEAD]; @@ -128,7 +144,8 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, err = -EINVAL; switch (p->id.proto) { case IPPROTO_AH: - if (!attrs[XFRMA_ALG_AUTH] || + if ((!attrs[XFRMA_ALG_AUTH] && + !attrs[XFRMA_ALG_AUTH_TRUNC]) || attrs[XFRMA_ALG_AEAD] || attrs[XFRMA_ALG_CRYPT] || attrs[XFRMA_ALG_COMP]) @@ -139,10 +156,12 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, if (attrs[XFRMA_ALG_COMP]) goto out; if (!attrs[XFRMA_ALG_AUTH] && + !attrs[XFRMA_ALG_AUTH_TRUNC] && !attrs[XFRMA_ALG_CRYPT] && !attrs[XFRMA_ALG_AEAD]) goto out; if ((attrs[XFRMA_ALG_AUTH] || + attrs[XFRMA_ALG_AUTH_TRUNC] || attrs[XFRMA_ALG_CRYPT]) && attrs[XFRMA_ALG_AEAD]) goto out; @@ -152,6 +171,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, if (!attrs[XFRMA_ALG_COMP] || attrs[XFRMA_ALG_AEAD] || attrs[XFRMA_ALG_AUTH] || + attrs[XFRMA_ALG_AUTH_TRUNC] || attrs[XFRMA_ALG_CRYPT]) goto out; break; @@ -161,6 +181,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, case IPPROTO_ROUTING: if (attrs[XFRMA_ALG_COMP] || attrs[XFRMA_ALG_AUTH] || + attrs[XFRMA_ALG_AUTH_TRUNC] || attrs[XFRMA_ALG_AEAD] || attrs[XFRMA_ALG_CRYPT] || attrs[XFRMA_ENCAP] || @@ -176,6 +197,8 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, if ((err = verify_aead(attrs))) goto out; + if ((err = verify_auth_trunc(attrs))) + goto out; if ((err = verify_one_alg(attrs, XFRMA_ALG_AUTH))) goto out; if ((err = verify_one_alg(attrs, XFRMA_ALG_CRYPT))) @@ -229,6 +252,66 @@ static int attach_one_algo(struct xfrm_algo **algpp, u8 *props, return 0; } +static int attach_auth(struct xfrm_algo_auth **algpp, u8 *props, + struct nlattr *rta) +{ + struct xfrm_algo *ualg; + struct xfrm_algo_auth *p; + struct xfrm_algo_desc *algo; + + if (!rta) + return 0; + + ualg = nla_data(rta); + + algo = xfrm_aalg_get_byname(ualg->alg_name, 1); + if (!algo) + return -ENOSYS; + *props = algo->desc.sadb_alg_id; + + p = kmalloc(sizeof(*p) + (ualg->alg_key_len + 7) / 8, GFP_KERNEL); + if (!p) + return -ENOMEM; + + strcpy(p->alg_name, algo->name); + p->alg_key_len = ualg->alg_key_len; + p->alg_trunc_len = algo->uinfo.auth.icv_truncbits; + memcpy(p->alg_key, ualg->alg_key, (ualg->alg_key_len + 7) / 8); + + *algpp = p; + return 0; +} + +static int attach_auth_trunc(struct xfrm_algo_auth **algpp, u8 *props, + struct nlattr *rta) +{ + struct xfrm_algo_auth *p, *ualg; + struct xfrm_algo_desc *algo; + + if (!rta) + return 0; + + ualg = nla_data(rta); + + algo = xfrm_aalg_get_byname(ualg->alg_name, 1); + if (!algo) + return -ENOSYS; + if (ualg->alg_trunc_len > algo->uinfo.auth.icv_fullbits) + return -EINVAL; + *props = algo->desc.sadb_alg_id; + + p = kmemdup(ualg, xfrm_alg_auth_len(ualg), GFP_KERNEL); + if (!p) + return -ENOMEM; + + strcpy(p->alg_name, algo->name); + if (!p->alg_trunc_len) + p->alg_trunc_len = algo->uinfo.auth.icv_truncbits; + + *algpp = p; + return 0; +} + static int attach_aead(struct xfrm_algo_aead **algpp, u8 *props, struct nlattr *rta) { @@ -332,10 +415,14 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, if ((err = attach_aead(&x->aead, &x->props.ealgo, attrs[XFRMA_ALG_AEAD]))) goto error; - if ((err = attach_one_algo(&x->aalg, &x->props.aalgo, - xfrm_aalg_get_byname, - attrs[XFRMA_ALG_AUTH]))) + if ((err = attach_auth_trunc(&x->aalg, &x->props.aalgo, + attrs[XFRMA_ALG_AUTH_TRUNC]))) goto error; + if (!x->props.aalgo) { + if ((err = attach_auth(&x->aalg, &x->props.aalgo, + attrs[XFRMA_ALG_AUTH]))) + goto error; + } if ((err = attach_one_algo(&x->ealg, &x->props.ealgo, xfrm_ealg_get_byname, attrs[XFRMA_ALG_CRYPT]))) @@ -548,6 +635,24 @@ static int copy_sec_ctx(struct xfrm_sec_ctx *s, struct sk_buff *skb) return 0; } +static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb) +{ + struct xfrm_algo *algo; + struct nlattr *nla; + + nla = nla_reserve(skb, XFRMA_ALG_AUTH, + sizeof(*algo) + (auth->alg_key_len + 7) / 8); + if (!nla) + return -EMSGSIZE; + + algo = nla_data(nla); + strcpy(algo->alg_name, auth->alg_name); + memcpy(algo->alg_key, auth->alg_key, (auth->alg_key_len + 7) / 8); + algo->alg_key_len = auth->alg_key_len; + + return 0; +} + /* Don't change this without updating xfrm_sa_len! */ static int copy_to_user_state_extra(struct xfrm_state *x, struct xfrm_usersa_info *p, @@ -563,8 +668,13 @@ static int copy_to_user_state_extra(struct xfrm_state *x, if (x->aead) NLA_PUT(skb, XFRMA_ALG_AEAD, aead_len(x->aead), x->aead); - if (x->aalg) - NLA_PUT(skb, XFRMA_ALG_AUTH, xfrm_alg_len(x->aalg), x->aalg); + if (x->aalg) { + if (copy_to_user_auth(x->aalg, skb)) + goto nla_put_failure; + + NLA_PUT(skb, XFRMA_ALG_AUTH_TRUNC, + xfrm_alg_auth_len(x->aalg), x->aalg); + } if (x->ealg) NLA_PUT(skb, XFRMA_ALG_CRYPT, xfrm_alg_len(x->ealg), x->ealg); if (x->calg) @@ -2117,8 +2227,11 @@ static inline size_t xfrm_sa_len(struct xfrm_state *x) size_t l = 0; if (x->aead) l += nla_total_size(aead_len(x->aead)); - if (x->aalg) - l += nla_total_size(xfrm_alg_len(x->aalg)); + if (x->aalg) { + l += nla_total_size(sizeof(struct xfrm_algo) + + (x->aalg->alg_key_len + 7) / 8); + l += nla_total_size(xfrm_alg_auth_len(x->aalg)); + } if (x->ealg) l += nla_total_size(xfrm_alg_len(x->ealg)); if (x->calg) @@ -2608,22 +2721,24 @@ static int __net_init xfrm_user_net_init(struct net *net) xfrm_netlink_rcv, NULL, THIS_MODULE); if (nlsk == NULL) return -ENOMEM; + net->xfrm.nlsk_stash = nlsk; /* Don't set to NULL */ rcu_assign_pointer(net->xfrm.nlsk, nlsk); return 0; } -static void __net_exit xfrm_user_net_exit(struct net *net) +static void __net_exit xfrm_user_net_exit(struct list_head *net_exit_list) { - struct sock *nlsk = net->xfrm.nlsk; - - rcu_assign_pointer(net->xfrm.nlsk, NULL); - synchronize_rcu(); - netlink_kernel_release(nlsk); + struct net *net; + list_for_each_entry(net, net_exit_list, exit_list) + rcu_assign_pointer(net->xfrm.nlsk, NULL); + synchronize_net(); + list_for_each_entry(net, net_exit_list, exit_list) + netlink_kernel_release(net->xfrm.nlsk_stash); } static struct pernet_operations xfrm_user_net_ops = { - .init = xfrm_user_net_init, - .exit = xfrm_user_net_exit, + .init = xfrm_user_net_init, + .exit_batch = xfrm_user_net_exit, }; static int __init xfrm_user_init(void) diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index 6d69c7ccdcc7..80599e3a7994 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -30,7 +30,7 @@ silentoldconfig: $(obj)/conf $< -s $(Kconfig) localmodconfig: $(obj)/streamline_config.pl $(obj)/conf - $(Q)perl $< $(Kconfig) > .tmp.config + $(Q)perl $< $(srctree) $(Kconfig) > .tmp.config $(Q)if [ -f .config ]; then \ cmp -s .tmp.config .config || \ (mv -f .config .config.old.1; \ @@ -44,7 +44,7 @@ localmodconfig: $(obj)/streamline_config.pl $(obj)/conf $(Q)rm -f .tmp.config localyesconfig: $(obj)/streamline_config.pl $(obj)/conf - $(Q)perl $< $(Kconfig) > .tmp.config + $(Q)perl $< $(srctree) $(Kconfig) > .tmp.config $(Q)sed -i s/=m/=y/ .tmp.config $(Q)if [ -f .config ]; then \ cmp -s .tmp.config .config || \ diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl index 95984db8e1e0..0d800820c3cd 100644 --- a/scripts/kconfig/streamline_config.pl +++ b/scripts/kconfig/streamline_config.pl @@ -43,7 +43,6 @@ # make oldconfig # my $config = ".config"; -my $linuxpath = "."; my $uname = `uname -r`; chomp $uname; @@ -111,7 +110,11 @@ sub find_config { find_config; -my @makefiles = `find $linuxpath -name Makefile`; +# Get the build source and top level Kconfig file (passed in) +my $ksource = $ARGV[0]; +my $kconfig = $ARGV[1]; + +my @makefiles = `find $ksource -name Makefile`; my %depends; my %selects; my %prompts; @@ -119,9 +122,6 @@ my %objects; my $var; my $cont = 0; -# Get the top level Kconfig file (passed in) -my $kconfig = $ARGV[0]; - # prevent recursion my %read_kconfigs; @@ -132,7 +132,7 @@ sub read_kconfig { my $config; my @kconfigs; - open(KIN, $kconfig) || die "Can't open $kconfig"; + open(KIN, "$ksource/$kconfig") || die "Can't open $kconfig"; while (<KIN>) { chomp; diff --git a/sound/arm/aaci.c b/sound/arm/aaci.c index 1f0f8213e2d5..6c160a038b23 100644 --- a/sound/arm/aaci.c +++ b/sound/arm/aaci.c @@ -504,6 +504,10 @@ static int aaci_pcm_hw_params(struct snd_pcm_substream *substream, int err; aaci_pcm_hw_free(substream); + if (aacirun->pcm_open) { + snd_ac97_pcm_close(aacirun->pcm); + aacirun->pcm_open = 0; + } err = devdma_hw_alloc(NULL, substream, params_buffer_bytes(params)); @@ -517,7 +521,7 @@ static int aaci_pcm_hw_params(struct snd_pcm_substream *substream, else err = snd_ac97_pcm_open(aacirun->pcm, params_rate(params), params_channels(params), - aacirun->pcm->r[1].slots); + aacirun->pcm->r[0].slots); if (err) goto out; diff --git a/sound/soc/codecs/tlv320aic23.c b/sound/soc/codecs/tlv320aic23.c index 6b24d8bb02bb..90a0264f7538 100644 --- a/sound/soc/codecs/tlv320aic23.c +++ b/sound/soc/codecs/tlv320aic23.c @@ -625,11 +625,10 @@ static int tlv320aic23_resume(struct platform_device *pdev) { struct snd_soc_device *socdev = platform_get_drvdata(pdev); struct snd_soc_codec *codec = socdev->card->codec; - int i; u16 reg; /* Sync reg_cache with the hardware */ - for (reg = 0; reg < ARRAY_SIZE(tlv320aic23_reg); i++) { + for (reg = 0; reg < TLV320AIC23_RESET; reg++) { u16 val = tlv320aic23_read_reg_cache(codec, reg); tlv320aic23_write(codec, reg, val); } diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index d89f6dc00908..66d4c165f99b 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -973,9 +973,19 @@ static int dapm_power_widgets(struct snd_soc_codec *codec, int event) if (!w->power_check) continue; - power = w->power_check(w); - if (power) - sys_power = 1; + /* If we're suspending then pull down all the + * power. */ + switch (event) { + case SND_SOC_DAPM_STREAM_SUSPEND: + power = 0; + break; + + default: + power = w->power_check(w); + if (power) + sys_power = 1; + break; + } if (w->power == power) continue; @@ -999,8 +1009,12 @@ static int dapm_power_widgets(struct snd_soc_codec *codec, int event) case SND_SOC_DAPM_STREAM_RESUME: sys_power = 1; break; + case SND_SOC_DAPM_STREAM_SUSPEND: + sys_power = 0; + break; case SND_SOC_DAPM_STREAM_NOP: sys_power = codec->bias_level != SND_SOC_BIAS_STANDBY; + break; default: break; } |