From 879aa24d6394aa04b690a600a41ff500441ad384 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 26 Nov 2010 06:47:28 -0300 Subject: [media] V4L: improve the BKL replacement heuristic The BKL replacement mutex had some serious performance side-effects on V4L drivers. It is replaced by a better heuristic that works around the worst of the side-effects. Read the v4l2-dev.c comments for the whole sorry story. This is a temporary measure only until we can convert all v4l drivers to use unlocked_ioctl. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-device.h b/include/media/v4l2-device.h index 6648036b728..b16f307d471 100644 --- a/include/media/v4l2-device.h +++ b/include/media/v4l2-device.h @@ -51,6 +51,8 @@ struct v4l2_device { unsigned int notification, void *arg); /* The control handler. May be NULL. */ struct v4l2_ctrl_handler *ctrl_handler; + /* BKL replacement mutex. Temporary solution only. */ + struct mutex ioctl_lock; }; /* Initialize v4l2_dev and make dev->driver_data point to v4l2_dev. -- cgit v1.2.3-18-g5258 From a757ee2216211278680dd8ac869aabe7b4a9970d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 2 Dec 2010 01:57:03 -0200 Subject: [media] Don't export format_by_forcc on two different drivers Drivers should append their name on exported symbols, to avoid conflicts with allyesconfig: drivers/staging/built-in.o: In function `format_by_fourcc': /home/v4l/work_trees/linus/drivers/staging/cx25821/cx25821-video.c:96: multiple definition of `format_by_fourcc' drivers/media/built-in.o:/home/v4l/work_trees/linus/drivers/media/common/saa7146_video.c:88: first defined here Let's rename both occurences with a small shellscript: for i in drivers/staging/cx25821/*.[ch]; do sed s,format_by_fourcc,cx25821_format_by_fourcc,g <$i >a && mv a $i; done for i in drivers/media/common/saa7146*.[ch]; do sed s,format_by_fourcc,saa7146_format_by_fourcc,g <$i >a && mv a $i; done for i in include/media/saa7146*.[ch]; do sed s,format_by_fourcc,saa7146_format_by_fourcc,g <$i >a && mv a $i; done Signed-off-by: Mauro Carvalho Chehab --- include/media/saa7146.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/saa7146.h b/include/media/saa7146.h index 7a9f76ecbbb..ac7ce00f39c 100644 --- a/include/media/saa7146.h +++ b/include/media/saa7146.h @@ -161,7 +161,7 @@ extern struct list_head saa7146_devices; extern struct mutex saa7146_devices_lock; int saa7146_register_extension(struct saa7146_extension*); int saa7146_unregister_extension(struct saa7146_extension*); -struct saa7146_format* format_by_fourcc(struct saa7146_dev *dev, int fourcc); +struct saa7146_format* saa7146_format_by_fourcc(struct saa7146_dev *dev, int fourcc); int saa7146_pgtable_alloc(struct pci_dev *pci, struct saa7146_pgtable *pt); void saa7146_pgtable_free(struct pci_dev *pci, struct saa7146_pgtable *pt); int saa7146_pgtable_build_single(struct pci_dev *pci, struct saa7146_pgtable *pt, struct scatterlist *list, int length ); -- cgit v1.2.3-18-g5258 From 88d60c32765716289abeb362c44adf6c35c6824c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Mon, 8 Nov 2010 18:19:22 -0500 Subject: fanotify: remove packed from access response message Since fanotify has decided to be careful about alignment and packing rather than rely on __attribute__((packed)) for multiarch support. Since this attribute isn't doing anything on fanotify_response we just drop it. This does not break API/ABI. Suggested-by: Tvrtko Ursulin Signed-off-by: Eric Paris --- include/linux/fanotify.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 0f0121467fc..bdbf9bb29b5 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -96,7 +96,7 @@ struct fanotify_event_metadata { struct fanotify_response { __s32 fd; __u32 response; -} __attribute__ ((packed)); +}; /* Legit userspace responses to a _PERM event */ #define FAN_ALLOW 0x01 -- cgit v1.2.3-18-g5258 From b1085ba80cd2784400a7beec3fda5099198ed01c Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Fri, 5 Nov 2010 17:05:27 +0100 Subject: fanotify: if set by user unset FMODE_NONOTIFY before fsnotify_perm() is called Unsetting FMODE_NONOTIFY in fsnotify_open() is too late, since fsnotify_perm() is called before. If FMODE_NONOTIFY is set fsnotify_perm() will skip permission checks, so a user can still disable permission checks by setting this flag in an open() call. This patch corrects this by unsetting the flag before fsnotify_perm is called. Signed-off-by: Lino Sanfilippo Signed-off-by: Eric Paris --- include/linux/fsnotify.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 5c185fa2708..b10bcdeaef7 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -235,9 +235,6 @@ static inline void fsnotify_open(struct file *file) if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; - /* FMODE_NONOTIFY must never be set from user */ - file->f_mode &= ~FMODE_NONOTIFY; - fsnotify_parent(path, NULL, mask); fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } -- cgit v1.2.3-18-g5258 From 09e5f14e57c70f9d357862bb56e57026c51092a1 Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Fri, 19 Nov 2010 10:58:07 +0100 Subject: fanotify: on group destroy allow all waiters to bypass permission check When fanotify_release() is called, there may still be processes waiting for access permission. Currently only processes for which an event has already been queued into the groups access list will be woken up. Processes for which no event has been queued will continue to sleep and thus cause a deadlock when fsnotify_put_group() is called. Furthermore there is a race allowing further processes to be waiting on the access wait queue after wake_up (if they arrive before clear_marks_by_group() is called). This patch corrects this by setting a flag to inform processes that the group is about to be destroyed and thus not to wait for access permission. [additional changelog from eparis] Lets think about the 4 relevant code paths from the PoV of the 'operator' 'listener' 'responder' and 'closer'. Where operator is the process doing an action (like open/read) which could require permission. Listener is the task (or in this case thread) slated with reading from the fanotify file descriptor. The 'responder' is the thread responsible for responding to access requests. 'Closer' is the thread attempting to close the fanotify file descriptor. The 'operator' is going to end up in: fanotify_handle_event() get_response_from_access() (THIS BLOCKS WAITING ON USERSPACE) The 'listener' interesting code path fanotify_read() copy_event_to_user() prepare_for_access_response() (THIS CREATES AN fanotify_response_event) The 'responder' code path: fanotify_write() process_access_response() (REMOVE A fanotify_response_event, SET RESPONSE, WAKE UP 'operator') The 'closer': fanotify_release() (SUPPOSED TO CLEAN UP THE REST OF THIS MESS) What we have today is that in the closer we remove all of the fanotify_response_events and set a bit so no more response events are ever created in prepare_for_access_response(). The bug is that we never wake all of the operators up and tell them to move along. You fix that in fanotify_get_response_from_access(). You also fix other operators which haven't gotten there yet. So I agree that's a good fix. [/additional changelog from eparis] [remove additional changes to minimize patch size] [move initialization so it was inside CONFIG_FANOTIFY_PERMISSION] Signed-off-by: Lino Sanfilippo Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 0a68f924f06..7380763595d 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -166,7 +166,7 @@ struct fsnotify_group { struct mutex access_mutex; struct list_head access_list; wait_queue_head_t access_waitq; - bool bypass_perm; /* protected by access_mutex */ + atomic_t bypass_perm; #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */ int f_flags; unsigned int max_marks; -- cgit v1.2.3-18-g5258 From e9a3854fd4ff3907e6c200a3980e19365ee695e9 Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Wed, 24 Nov 2010 18:22:09 +0100 Subject: fanotify: Introduce FAN_NOFD FAN_NOFD is used in fanotify events that do not provide an open file descriptor (like the overflow_event). Signed-off-by: Lino Sanfilippo Signed-off-by: Eric Paris --- include/linux/fanotify.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index bdbf9bb29b5..c73224315ae 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -101,6 +101,8 @@ struct fanotify_response { /* Legit userspace responses to a _PERM event */ #define FAN_ALLOW 0x01 #define FAN_DENY 0x02 +/* No fd set in event */ +#define FAN_NOFD -1 /* Helper functions to deal with fanotify_event_metadata buffers */ #define FAN_EVENT_METADATA_LEN (sizeof(struct fanotify_event_metadata)) -- cgit v1.2.3-18-g5258 From 5167695753c63444a9e6cbbef136200a16c7a225 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 7 Dec 2010 14:18:20 +0100 Subject: perf: Fix duplicate events with multiple-pmu vs software events Because the multi-pmu bits can share contexts between struct pmu instances we could get duplicate events by iterating the pmu list. Signed-off-by: Peter Zijlstra Signed-off-by: Thomas Gleixner LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index de2c41758e2..4f1279e105e 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -887,6 +887,7 @@ struct perf_cpu_context { int exclusive; struct list_head rotation_list; int jiffies_interval; + struct pmu *active_pmu; }; struct perf_output_handle { -- cgit v1.2.3-18-g5258 From 0f004f5a696a9434b7214d0d3cbd0525ee77d428 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 30 Nov 2010 19:48:45 +0100 Subject: sched: Cure more NO_HZ load average woes There's a long-running regression that proved difficult to fix and which is hitting certain people and is rather annoying in its effects. Damien reported that after 74f5187ac8 (sched: Cure load average vs NO_HZ woes) his load average is unnaturally high, he also noted that even with that patch reverted the load avgerage numbers are not correct. The problem is that the previous patch only solved half the NO_HZ problem, it addressed the part of going into NO_HZ mode, not of comming out of NO_HZ mode. This patch implements that missing half. When comming out of NO_HZ mode there are two important things to take care of: - Folding the pending idle delta into the global active count. - Correctly aging the averages for the idle-duration. So with this patch the NO_HZ interaction should be complete and behaviour between CONFIG_NO_HZ=[yn] should be equivalent. Furthermore, this patch slightly changes the load average computation by adding a rounding term to the fixed point multiplication. Reported-by: Damien Wyart Reported-by: Tim McGrath Tested-by: Damien Wyart Tested-by: Orion Poplawski Tested-by: Kyle McMartin Signed-off-by: Peter Zijlstra Cc: stable@kernel.org Cc: Chase Douglas LKML-Reference: <1291129145.32004.874.camel@laptop> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c79e921a68..223874538b3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -143,7 +143,7 @@ extern unsigned long nr_iowait_cpu(int cpu); extern unsigned long this_cpu_load(void); -extern void calc_global_load(void); +extern void calc_global_load(unsigned long ticks); extern unsigned long get_parent_ip(unsigned long addr); -- cgit v1.2.3-18-g5258 From 53dde5f385bc56e312f78b7cb25ffaf8efd4735d Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Tue, 16 Nov 2010 13:23:50 -0800 Subject: bootmem: Add alloc_bootmem_align() Add an alloc_bootmem_align() interface to allocate bootmem with specified alignment. This is necessary to be able to allocate the xsave area in a subsequent patch. Signed-off-by: Suresh Siddha LKML-Reference: <20101116212441.977574826@sbsiddha-MOBL3.sc.intel.com> Acked-by: H. Peter Anvin Signed-off-by: H. Peter Anvin Cc: --- include/linux/bootmem.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 266ab929123..499dfe982a0 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -105,6 +105,8 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, #define alloc_bootmem(x) \ __alloc_bootmem(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) +#define alloc_bootmem_align(x, align) \ + __alloc_bootmem(x, align, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_nopanic(x) \ __alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_pages(x) \ -- cgit v1.2.3-18-g5258 From 62731fa0c893515dc6cbc3e0a2879a92793c735f Mon Sep 17 00:00:00 2001 From: Alexey Zaytsev Date: Mon, 22 Nov 2010 00:33:03 +0000 Subject: fanotify: split version into version and metadata_len To implement per event type optional headers we are interested in knowing how long the metadata structure is. This patch slits the __u32 version field into a __u8 version and a __u16 metadata_len field (with __u8 left over). This should allow for backwards compat ABI. Signed-off-by: Alexey Zaytsev [rewrote descrtion and changed object sizes and ordering - eparis] Signed-off-by: Eric Paris --- include/linux/fanotify.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index c73224315ae..6c6133f76e1 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -83,11 +83,13 @@ FAN_ALL_PERM_EVENTS |\ FAN_Q_OVERFLOW) -#define FANOTIFY_METADATA_VERSION 2 +#define FANOTIFY_METADATA_VERSION 3 struct fanotify_event_metadata { __u32 event_len; - __u32 vers; + __u8 vers; + __u8 reserved; + __u16 metadata_len; __aligned_u64 mask; __s32 fd; __s32 pid; -- cgit v1.2.3-18-g5258 From f08f5a0add20834d3f3d876dfe08005a5df656db Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 16 Dec 2010 17:11:58 +0100 Subject: PM / Runtime: Fix pm_runtime_suspended() There are some situations (e.g. in __pm_generic_call()), where pm_runtime_suspended() is used to decide whether or not to execute a device's (system) ->suspend() callback. The callback is not executed if pm_runtime_suspended() returns true, but it does so for devices that don't even support runtime PM, because the power.disable_depth device field is ignored by it. This leads to problems (i.e. devices are not suspened when they should), so rework pm_runtime_suspended() so that it returns false if the device's power.disable_depth field is different from zero. Signed-off-by: Rafael J. Wysocki Cc: stable@kernel.org --- include/linux/pm_runtime.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 3ec2358f869..d19f1cca7f7 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -77,7 +77,8 @@ static inline void device_set_run_wake(struct device *dev, bool enable) static inline bool pm_runtime_suspended(struct device *dev) { - return dev->power.runtime_status == RPM_SUSPENDED; + return dev->power.runtime_status == RPM_SUSPENDED + && !dev->power.disable_depth; } static inline void pm_runtime_mark_last_busy(struct device *dev) -- cgit v1.2.3-18-g5258 From 3f84622d7c7818077f5e6cf4b8a0d1b10dc65147 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Sat, 27 Nov 2010 19:26:32 +0100 Subject: SSB: Fix nvram_get on BCM47xx platform The nvram_get function was never in the mainline kernel, it only existed in an external OpenWrt patch. Use nvram_getenv function, which is in mainline and use an include instead of an extra function declaration. et0macaddr contains the mac address in text from like 00:11:22:33:44:55. We have to parse it before adding it into macaddr. nvram_parse_macaddr will be merged into asm/mach-bcm47xx/nvram.h through the MIPS git tree and will be available soon. It will not build now without nvram_parse_macaddr, but it hasn't before either. Signed-off-by: Hauke Mehrtens To: linux-mips@linux-mips.org Cc: mb@bu3sch.de Cc: netdev@vger.kernel.org Cc: Hauke Mehrtens Acked-by: Michael Buesch Patchwork: https://patchwork.linux-mips.org/patch/1849/ Signed-off-by: Ralf Baechle --- include/linux/ssb/ssb_driver_gige.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/ssb/ssb_driver_gige.h b/include/linux/ssb/ssb_driver_gige.h index 942e3873690..eba52a10053 100644 --- a/include/linux/ssb/ssb_driver_gige.h +++ b/include/linux/ssb/ssb_driver_gige.h @@ -96,16 +96,21 @@ static inline bool ssb_gige_must_flush_posted_writes(struct pci_dev *pdev) return 0; } -extern char * nvram_get(const char *name); +#ifdef CONFIG_BCM47XX +#include /* Get the device MAC address */ static inline void ssb_gige_get_macaddr(struct pci_dev *pdev, u8 *macaddr) { -#ifdef CONFIG_BCM47XX - char *res = nvram_get("et0macaddr"); - if (res) - memcpy(macaddr, res, 6); -#endif + char buf[20]; + if (nvram_getenv("et0macaddr", buf, sizeof(buf)) < 0) + return; + nvram_parse_macaddr(buf, macaddr); } +#else +static inline void ssb_gige_get_macaddr(struct pci_dev *pdev, u8 *macaddr) +{ +} +#endif extern int ssb_gige_pcibios_plat_dev_init(struct ssb_device *sdev, struct pci_dev *pdev); -- cgit v1.2.3-18-g5258 From fcbdf09d9652c8919dcf47072e3ae7dcb4eb98ac Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Thu, 16 Dec 2010 14:26:56 -0800 Subject: net: fix nulls list corruptions in sk_prot_alloc Special care is taken inside sk_port_alloc to avoid overwriting skc_node/skc_nulls_node. We should also avoid overwriting skc_bind_node/skc_portaddr_node. The patch fixes the following crash: BUG: unable to handle kernel paging request at fffffffffffffff0 IP: [] udp4_lib_lookup2+0xad/0x370 [] __udp4_lib_lookup+0x282/0x360 [] __udp4_lib_rcv+0x31e/0x700 [] ? ip_local_deliver_finish+0x65/0x190 [] ? ip_local_deliver+0x88/0xa0 [] udp_rcv+0x15/0x20 [] ip_local_deliver_finish+0x65/0x190 [] ip_local_deliver+0x88/0xa0 [] ip_rcv_finish+0x32d/0x6f0 [] ? netif_receive_skb+0x99c/0x11c0 [] ip_rcv+0x2bb/0x350 [] netif_receive_skb+0x99c/0x11c0 Signed-off-by: Leonard Crestez Signed-off-by: Octavian Purdila Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 659d968d95c..7d3f7ce239b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -754,6 +754,7 @@ struct proto { void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); + void (*clear_sk)(struct sock *sk, int size); /* Keeping track of sockets in use */ #ifdef CONFIG_PROC_FS @@ -852,6 +853,8 @@ static inline void __sk_prot_rehash(struct sock *sk) sk->sk_prot->hash(sk); } +void sk_prot_clear_portaddr_nulls(struct sock *sk, int size); + /* About 10 seconds */ #define SOCK_DESTROY_TIME (10*HZ) -- cgit v1.2.3-18-g5258 From e692cb668fdd5a712c6ed2a2d6f2a36ee83997b4 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 1 Dec 2010 19:41:49 +0100 Subject: block: Deprecate QUEUE_FLAG_CLUSTER and use queue_limits instead When stacking devices, a request_queue is not always available. This forced us to have a no_cluster flag in the queue_limits that could be used as a carrier until the request_queue had been set up for a metadevice. There were several problems with that approach. First of all it was up to the stacking device to remember to set queue flag after stacking had completed. Also, the queue flag and the queue limits had to be kept in sync at all times. We got that wrong, which could lead to us issuing commands that went beyond the max scatterlist limit set by the driver. The proper fix is to avoid having two flags for tracking the same thing. We deprecate QUEUE_FLAG_CLUSTER and use the queue limit directly in the block layer merging functions. The queue_limit 'no_cluster' is turned into 'cluster' to avoid double negatives and to ease stacking. Clustering defaults to being enabled as before. The queue flag logic is removed from the stacking function, and explicitly setting the cluster flag is no longer necessary in DM and MD. Reported-by: Ed Lin Signed-off-by: Martin K. Petersen Acked-by: Mike Snitzer Cc: stable@kernel.org Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index aae86fd10c4..95aeeeb49e8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -250,7 +250,7 @@ struct queue_limits { unsigned char misaligned; unsigned char discard_misaligned; - unsigned char no_cluster; + unsigned char cluster; signed char discard_zeroes_data; }; @@ -380,7 +380,6 @@ struct request_queue #endif }; -#define QUEUE_FLAG_CLUSTER 0 /* cluster several segments into 1 */ #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ #define QUEUE_FLAG_STOPPED 2 /* queue is stopped */ #define QUEUE_FLAG_SYNCFULL 3 /* read queue has been filled */ @@ -403,7 +402,6 @@ struct request_queue #define QUEUE_FLAG_SECDISCARD 19 /* supports SECDISCARD */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_CLUSTER) | \ (1 << QUEUE_FLAG_STACKABLE) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_ADD_RANDOM)) @@ -510,6 +508,11 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define rq_data_dir(rq) ((rq)->cmd_flags & 1) +static inline unsigned int blk_queue_cluster(struct request_queue *q) +{ + return q->limits.cluster; +} + /* * We regard a request as sync, if either a read or a sync write */ -- cgit v1.2.3-18-g5258 From 72d4cd9f38b5ed96b75df4c622be25e1c2648dd3 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 17 Dec 2010 08:34:20 +0100 Subject: block: max hardware sectors limit wrapper Implement blk_limits_max_hw_sectors() and make blk_queue_max_hw_sectors() a wrapper around it. DM needs this to avoid setting queue_limits' max_hw_sectors and max_sectors directly. dm_set_device_limits() now leverages blk_limits_max_hw_sectors() logic to establish the appropriate max_hw_sectors minimum (PAGE_SIZE). Fixes issue where DM was incorrectly setting max_sectors rather than max_hw_sectors (which caused dm_merge_bvec()'s max_hw_sectors check to be ineffective). Signed-off-by: Mike Snitzer Cc: stable@kernel.org Acked-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 95aeeeb49e8..36ab42c9bb9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -808,6 +808,7 @@ extern struct request_queue *blk_init_allocated_queue(struct request_queue *, extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); +extern void blk_limits_max_hw_sectors(struct queue_limits *, unsigned int); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); -- cgit v1.2.3-18-g5258 From b6aa5901c7a2bd90d0b6b9866300d2648b2568f3 Mon Sep 17 00:00:00 2001 From: Henry C Chang Date: Wed, 15 Dec 2010 20:45:41 -0800 Subject: ceph: mark user pages dirty on direct-io reads For read operation, we have to set the argument _write_ of get_user_pages to 1 since we will write data to pages. Also, we need to SetPageDirty before releasing these pages. Signed-off-by: Henry C Chang Signed-off-by: Sage Weil --- include/linux/ceph/libceph.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 9e76d35670d..72c72bfccb8 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -227,8 +227,10 @@ extern int ceph_open_session(struct ceph_client *client); extern void ceph_release_page_vector(struct page **pages, int num_pages); extern struct page **ceph_get_direct_page_vector(const char __user *data, - int num_pages); -extern void ceph_put_page_vector(struct page **pages, int num_pages); + int num_pages, + bool write_page); +extern void ceph_put_page_vector(struct page **pages, int num_pages, + bool dirty); extern void ceph_release_page_vector(struct page **pages, int num_pages); extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); extern int ceph_copy_user_to_page_vector(struct page **pages, -- cgit v1.2.3-18-g5258 From c0f5ac5426f7fd82b23dd5c6a1e633b290294a08 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 16 Dec 2010 10:38:41 -0700 Subject: Revert "resources: support allocating space within a region from the top down" This reverts commit e7f8567db9a7f6b3151b0b275e245c1cef0d9c70. Acked-by: H. Peter Anvin Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- include/linux/ioport.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index d377ea815d4..b22790268b6 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -112,7 +112,6 @@ struct resource_list { /* PC/ISA/whatever - the normal PC address spaces: IO and memory */ extern struct resource ioport_resource; extern struct resource iomem_resource; -extern int resource_alloc_from_bottom; extern struct resource *request_resource_conflict(struct resource *root, struct resource *new); extern int request_resource(struct resource *root, struct resource *new); -- cgit v1.2.3-18-g5258 From fcb119183c73bf0781009713f303e28b1fb13d3e Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 16 Dec 2010 10:38:46 -0700 Subject: resources: add arch hook for preventing allocation in reserved areas This adds arch_remove_reservations(), which an arch can implement if it needs to protect part of the address space from allocation. Sometimes that can be done by just putting a region in the resource tree, but there are cases where that doesn't work well. For example, x86 BIOS E820 reservations are not related to devices, so they may overlap part of, all of, or more than a device resource, so they may not end up at the correct spot in the resource tree. Acked-by: H. Peter Anvin Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- include/linux/ioport.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index b22790268b6..e9bb22cba76 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -123,6 +123,7 @@ extern void reserve_region_with_split(struct resource *root, extern struct resource *insert_resource_conflict(struct resource *parent, struct resource *new); extern int insert_resource(struct resource *parent, struct resource *new); extern void insert_resource_expand_to_fit(struct resource *root, struct resource *new); +extern void arch_remove_reservations(struct resource *avail); extern int allocate_resource(struct resource *root, struct resource *new, resource_size_t size, resource_size_t min, resource_size_t max, resource_size_t align, -- cgit v1.2.3-18-g5258 From 4b8fe66300acb2fba8b16d62606e0d30204022fc Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Fri, 17 Dec 2010 12:03:14 -0800 Subject: netlink: fix gcc -Wconversion compilation warning $ cat << EOF | gcc -Wconversion -xc -S -o/dev/null - unsigned f(void) {return NLMSG_HDRLEN;} EOF : In function 'f': :3:26: warning: negative integer implicitly converted to unsigned type Signed-off-by: Dmitry V. Levin Signed-off-by: Kirill A. Shutemov Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 123566912d7..e2b9e63afa6 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -70,7 +70,7 @@ struct nlmsghdr { Check NLM_F_EXCL */ -#define NLMSG_ALIGNTO 4 +#define NLMSG_ALIGNTO 4U #define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) ) #define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr))) #define NLMSG_LENGTH(len) ((len)+NLMSG_ALIGN(NLMSG_HDRLEN)) -- cgit v1.2.3-18-g5258 From ad0081e43af6de3fecf308b0d098f9611835766b Mon Sep 17 00:00:00 2001 From: David Stevens Date: Fri, 17 Dec 2010 11:42:42 +0000 Subject: ipv6: Fragment locally generated tunnel-mode IPSec6 packets as needed. This patch modifies IPsec6 to fragment IPv6 packets that are locally generated as needed. This version of the patch only fragments in tunnel mode, so that fragment headers will not be obscured by ESP in transport mode. Signed-off-by: David L Stevens Acked-by: Herbert Xu Signed-off-by: David S. Miller --- include/net/ip6_route.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 278312c95f9..2ab926860cd 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -164,5 +164,15 @@ static inline int ipv6_unicast_destination(struct sk_buff *skb) return rt->rt6i_flags & RTF_LOCAL; } +int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); + +static inline int ip6_skb_dst_mtu(struct sk_buff *skb) +{ + struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; + + return (np && np->pmtudisc == IPV6_PMTUDISC_PROBE) ? + skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); +} + #endif #endif -- cgit v1.2.3-18-g5258 From b8da46d3d55807037b58f14621a0949f18053bde Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Mon, 20 Dec 2010 00:29:32 -0500 Subject: clarify a usage constraint for cnt32_to_63() The cnt32_to_63 algorithm relies on proper counter data evaluation ordering to work properly. This was missing from the provided documentation. Let's augment the documentation with the missing usage constraint and fix the only instance that got it wrong. Signed-off-by: Nicolas Pitre Acked-by: David Howells Signed-off-by: Linus Torvalds --- include/linux/cnt32_to_63.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cnt32_to_63.h b/include/linux/cnt32_to_63.h index 7605fdd1eb6..e3d8bf26e5e 100644 --- a/include/linux/cnt32_to_63.h +++ b/include/linux/cnt32_to_63.h @@ -61,13 +61,31 @@ union cnt32_to_63 { * * 2) this code must not be preempted for a duration longer than the * 32-bit counter half period minus the longest period between two - * calls to this code. + * calls to this code; * * Those requirements ensure proper update to the state bit in memory. * This is usually not a problem in practice, but if it is then a kernel * timer should be scheduled to manage for this code to be executed often * enough. * + * And finally: + * + * 3) the cnt_lo argument must be seen as a globally incrementing value, + * meaning that it should be a direct reference to the counter data which + * can be evaluated according to a specific ordering within the macro, + * and not the result of a previous evaluation stored in a variable. + * + * For example, this is wrong: + * + * u32 partial = get_hw_count(); + * u64 full = cnt32_to_63(partial); + * return full; + * + * This is fine: + * + * u64 full = cnt32_to_63(get_hw_count()); + * return full; + * * Note that the top bit (bit 63) in the returned value should be considered * as garbage. It is not cleared here because callers are likely to use a * multiplier on the returned value which can get rid of the top bit -- cgit v1.2.3-18-g5258 From 173021072e86a0a5b3d2271347493a3e0d5f68e8 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Mon, 20 Dec 2010 04:35:30 +0000 Subject: net_sched: always clone skbs Pawel reported a panic related to handling shared skbs in ixgbe incorrectly. So we need to revert my previous patch to work around this bug. Instead of reverting the patch completely, I just revert the essential lines, so we can add the previous optimization back more easily in future. commit 3511c9132f8b1e1b5634e41a3331c44b0c13be70 Author: Changli Gao Date: Sat Oct 16 13:04:08 2010 +0000 net_sched: remove the unused parameter of qdisc_create_dflt() Reported-by: Pawel Staszewski Signed-off-by: Changli Gao Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sch_generic.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index ea1f8a83160..79f34e2b752 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -610,11 +610,7 @@ static inline struct sk_buff *skb_act_clone(struct sk_buff *skb, gfp_t gfp_mask, { struct sk_buff *n; - if ((action == TC_ACT_STOLEN || action == TC_ACT_QUEUED) && - !skb_shared(skb)) - n = skb_get(skb); - else - n = skb_clone(skb, gfp_mask); + n = skb_clone(skb, gfp_mask); if (n) { n->tc_verd = SET_TC_VERD(n->tc_verd, 0); -- cgit v1.2.3-18-g5258 From 9f333281a7da4c3a59bccc0cb53f7590eb850d93 Mon Sep 17 00:00:00 2001 From: Johannes Stezenbach Date: Tue, 30 Nov 2010 16:49:23 +0100 Subject: mac80211/rt2x00: add ieee80211_tx_status_ni() All rt2x00 drivers except rt2800pci call ieee80211_tx_status() from a workqueue, which causes "NOHZ: local_softirq_pending 08" messages. To fix it, add ieee80211_tx_status_ni() similar to ieee80211_rx_ni() which can be called from process context, and call it from rt2x00lib_txdone(). For the rt2800pci special case a driver flag is introduced. https://bugzilla.kernel.org/show_bug.cgi?id=24892 Signed-off-by: Johannes Stezenbach Signed-off-by: John W. Linville --- include/net/mac80211.h | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 9fdf982d128..365359b2417 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2024,8 +2024,8 @@ static inline void ieee80211_rx_ni(struct ieee80211_hw *hw, * * This function may not be called in IRQ context. Calls to this function * for a single hardware must be synchronized against each other. Calls - * to this function and ieee80211_tx_status_irqsafe() may not be mixed - * for a single hardware. + * to this function, ieee80211_tx_status_ni() and ieee80211_tx_status_irqsafe() + * may not be mixed for a single hardware. * * @hw: the hardware the frame was transmitted by * @skb: the frame that was transmitted, owned by mac80211 after this call @@ -2033,14 +2033,34 @@ static inline void ieee80211_rx_ni(struct ieee80211_hw *hw, void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb); +/** + * ieee80211_tx_status_ni - transmit status callback (in process context) + * + * Like ieee80211_tx_status() but can be called in process context. + * + * Calls to this function, ieee80211_tx_status() and + * ieee80211_tx_status_irqsafe() may not be mixed + * for a single hardware. + * + * @hw: the hardware the frame was transmitted by + * @skb: the frame that was transmitted, owned by mac80211 after this call + */ +static inline void ieee80211_tx_status_ni(struct ieee80211_hw *hw, + struct sk_buff *skb) +{ + local_bh_disable(); + ieee80211_tx_status(hw, skb); + local_bh_enable(); +} + /** * ieee80211_tx_status_irqsafe - IRQ-safe transmit status callback * * Like ieee80211_tx_status() but can be called in IRQ context * (internally defers to a tasklet.) * - * Calls to this function and ieee80211_tx_status() may not be mixed for a - * single hardware. + * Calls to this function, ieee80211_tx_status() and + * ieee80211_tx_status_ni() may not be mixed for a single hardware. * * @hw: the hardware the frame was transmitted by * @skb: the frame that was transmitted, owned by mac80211 after this call -- cgit v1.2.3-18-g5258 From da521b2c4f046383bc8941604174bc0e8bffb430 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 21 Dec 2010 12:43:16 -0800 Subject: net: Fix range checks in tcf_valid_offset(). This function has three bugs: 1) The offset should be valid most of the time, this is just a sanity check, therefore we should use "likely" not "unlikely" 2) This is the only place where we can check for arithmetic overflow of the pointer plus the length. 3) The existing range checks are off by one, the valid range is skb->head to skb_tail_pointer(), inclusive. Based almost entirely upon a patch by Ralph Loader. Reported-by: Ralph Loader Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index dd3031aed9d..9fcc680ab6b 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -323,7 +323,9 @@ static inline unsigned char * tcf_get_base_ptr(struct sk_buff *skb, int layer) static inline int tcf_valid_offset(const struct sk_buff *skb, const unsigned char *ptr, const int len) { - return unlikely((ptr + len) < skb_tail_pointer(skb) && ptr > skb->head); + return likely((ptr + len) <= skb_tail_pointer(skb) && + ptr >= skb->head && + (ptr <= (ptr + len))); } #ifdef CONFIG_NET_CLS_IND -- cgit v1.2.3-18-g5258 From 4f32e9b1f812fd6c00cc85a127583fefbdedaedc Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Wed, 22 Dec 2010 10:27:53 +0100 Subject: kthread_work: make lockdep happy spinlock in kthread_worker and wait_queue_head in kthread_work both should be lockdep sensible, so change the interface to make it suiltable for CONFIG_LOCKDEP. tj: comment update Reported-by: Nicolas Signed-off-by: Yong Zhang Signed-off-by: Andy Walls Tested-by: Andy Walls Cc: Tejun Heo Cc: Andrew Morton Signed-off-by: Tejun Heo --- include/linux/kthread.h | 45 +++++++++++++++++++++++++++++++++++---------- 1 file changed, 35 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 685ea65eb80..ce0775aa64c 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -81,16 +81,41 @@ struct kthread_work { #define DEFINE_KTHREAD_WORK(work, fn) \ struct kthread_work work = KTHREAD_WORK_INIT(work, fn) -static inline void init_kthread_worker(struct kthread_worker *worker) -{ - *worker = (struct kthread_worker)KTHREAD_WORKER_INIT(*worker); -} - -static inline void init_kthread_work(struct kthread_work *work, - kthread_work_func_t fn) -{ - *work = (struct kthread_work)KTHREAD_WORK_INIT(*work, fn); -} +/* + * kthread_worker.lock and kthread_work.done need their own lockdep class + * keys if they are defined on stack with lockdep enabled. Use the + * following macros when defining them on stack. + */ +#ifdef CONFIG_LOCKDEP +# define KTHREAD_WORKER_INIT_ONSTACK(worker) \ + ({ init_kthread_worker(&worker); worker; }) +# define DEFINE_KTHREAD_WORKER_ONSTACK(worker) \ + struct kthread_worker worker = KTHREAD_WORKER_INIT_ONSTACK(worker) +# define KTHREAD_WORK_INIT_ONSTACK(work, fn) \ + ({ init_kthread_work((&work), fn); work; }) +# define DEFINE_KTHREAD_WORK_ONSTACK(work, fn) \ + struct kthread_work work = KTHREAD_WORK_INIT_ONSTACK(work, fn) +#else +# define DEFINE_KTHREAD_WORKER_ONSTACK(worker) DEFINE_KTHREAD_WORKER(worker) +# define DEFINE_KTHREAD_WORK_ONSTACK(work, fn) DEFINE_KTHREAD_WORK(work, fn) +#endif + +extern void __init_kthread_worker(struct kthread_worker *worker, + const char *name, struct lock_class_key *key); + +#define init_kthread_worker(worker) \ + do { \ + static struct lock_class_key __key; \ + __init_kthread_worker((worker), "("#worker")->lock", &__key); \ + } while (0) + +#define init_kthread_work(work, fn) \ + do { \ + memset((work), 0, sizeof(struct kthread_work)); \ + INIT_LIST_HEAD(&(work)->node); \ + (work)->func = (fn); \ + init_waitqueue_head(&(work)->done); \ + } while (0) int kthread_worker_fn(void *worker_ptr); -- cgit v1.2.3-18-g5258 From 4e06fd14d5fa78826397c891654a37e5a36ee827 Mon Sep 17 00:00:00 2001 From: Will Newton Date: Tue, 21 Dec 2010 17:24:29 -0800 Subject: include/linux/unaligned: pack the whole struct rather than just the field The current packed struct implementation of unaligned access adds the packed attribute only to the field within the unaligned struct rather than to the struct as a whole. This is not sufficient to enforce proper behaviour on architectures with a default struct alignment of more than one byte. For example, the current implementation of __get_unaligned_cpu16 when compiled for arm with gcc -O1 -mstructure-size-boundary=32 assumes the struct is on a 4 byte boundary so performs the load of the 16bit packed field as if it were on a 4 byte boundary: __get_unaligned_cpu16: ldrh r0, [r0, #0] bx lr Moving the packed attribute to the struct rather than the field causes the proper unaligned access code to be generated: __get_unaligned_cpu16: ldrb r3, [r0, #0] @ zero_extendqisi2 ldrb r0, [r0, #1] @ zero_extendqisi2 orr r0, r3, r0, asl #8 bx lr Signed-off-by: Will Newton Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/unaligned/packed_struct.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/unaligned/packed_struct.h b/include/linux/unaligned/packed_struct.h index 2498bb9fe00..c9a6abd972a 100644 --- a/include/linux/unaligned/packed_struct.h +++ b/include/linux/unaligned/packed_struct.h @@ -3,9 +3,9 @@ #include -struct __una_u16 { u16 x __attribute__((packed)); }; -struct __una_u32 { u32 x __attribute__((packed)); }; -struct __una_u64 { u64 x __attribute__((packed)); }; +struct __una_u16 { u16 x; } __attribute__((packed)); +struct __una_u32 { u32 x; } __attribute__((packed)); +struct __una_u64 { u64 x; } __attribute__((packed)); static inline u16 __get_unaligned_cpu16(const void *p) { -- cgit v1.2.3-18-g5258 From 4be2c95d1f7706ca0e74499f2bd118e1cee19669 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Tue, 21 Dec 2010 17:24:30 -0800 Subject: taskstats: pad taskstats netlink response for aligment issues on ia64 The taskstats structure is internally aligned on 8 byte boundaries but the layout of the aggregrate reply, with two NLA headers and the pid (each 4 bytes), actually force the entire structure to be unaligned. This causes the kernel to issue unaligned access warnings on some architectures like ia64. Unfortunately, some software out there doesn't properly unroll the NLA packet and assumes that the start of the taskstats structure will always be 20 bytes from the start of the netlink payload. Aligning the start of the taskstats structure breaks this software, which we don't want. So, for now the alignment only happens on architectures that require it and those users will have to update to fixed versions of those packages. Space is reserved in the packet only when needed. This ifdef should be removed in several years e.g. 2012 once we can be confident that fixed versions are installed on most systems. We add the padding before the aggregate since the aggregate is already a defined type. Commit 85893120 ("delayacct: align to 8 byte boundary on 64-bit systems") previously addressed the alignment issues by padding out the pid field. This was supposed to be a compatible change but the circumstances described above mean that it wasn't. This patch backs out that change, since it was a hack, and introduces a new NULL attribute type to provide the padding. Padding the response with 4 bytes avoids allocating an aligned taskstats structure and copying it back. Since the structure weighs in at 328 bytes, it's too big to do it on the stack. Signed-off-by: Jeff Mahoney Reported-by: Brian Rogers Cc: Jeff Mahoney Cc: Guillaume Chazarain Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/taskstats.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h index 341dddb5509..2466e550a41 100644 --- a/include/linux/taskstats.h +++ b/include/linux/taskstats.h @@ -33,7 +33,7 @@ */ -#define TASKSTATS_VERSION 7 +#define TASKSTATS_VERSION 8 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -188,6 +188,7 @@ enum { TASKSTATS_TYPE_STATS, /* taskstats structure */ TASKSTATS_TYPE_AGGR_PID, /* contains pid + stats */ TASKSTATS_TYPE_AGGR_TGID, /* contains tgid + stats */ + TASKSTATS_TYPE_NULL, /* contains nothing */ __TASKSTATS_TYPE_MAX, }; -- cgit v1.2.3-18-g5258 From e058464990c2ef1f3ecd6b83a154913c3c06f02a Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 23 Dec 2010 12:03:57 -0800 Subject: Revert "ipv4: Allow configuring subnets as local addresses" This reverts commit 4465b469008bc03b98a1b8df4e9ae501b6c69d4b. Conflicts: net/ipv4/fib_frontend.c As reported by Ben Greear, this causes regressions: > Change 4465b469008bc03b98a1b8df4e9ae501b6c69d4b caused rules > to stop matching the input device properly because the > FLOWI_FLAG_MATCH_ANY_IIF is always defined in ip_dev_find(). > > This breaks rules such as: > > ip rule add pref 512 lookup local > ip rule del pref 0 lookup local > ip link set eth2 up > ip -4 addr add 172.16.0.102/24 broadcast 172.16.0.255 dev eth2 > ip rule add to 172.16.0.102 iif eth2 lookup local pref 10 > ip rule add iif eth2 lookup 10001 pref 20 > ip route add 172.16.0.0/24 dev eth2 table 10001 > ip route add unreachable 0/0 table 10001 > > If you had a second interface 'eth0' that was on a different > subnet, pinging a system on that interface would fail: > > [root@ct503-60 ~]# ping 192.168.100.1 > connect: Invalid argument Reported-by: Ben Greear Signed-off-by: David S. Miller --- include/net/flow.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/flow.h b/include/net/flow.h index 0ac3fb5e097..bb08692a20b 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -49,7 +49,6 @@ struct flowi { __u8 proto; __u8 flags; #define FLOWI_FLAG_ANYSRC 0x01 -#define FLOWI_FLAG_MATCH_ANY_IIF 0x02 union { struct { __be16 sport; -- cgit v1.2.3-18-g5258 From 8f33d5277fada0291ea495f7fd44a3e7b7aa41d3 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 22 Dec 2010 14:46:46 +0100 Subject: dmaengine: provide dummy functions for DMA_ENGINE=n This lets drivers, optionally using the dmaengine, build with DMA_ENGINE unselected. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 9d8688b92d8..8cd00ad98d3 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -824,6 +824,8 @@ enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie); #ifdef CONFIG_DMA_ENGINE enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx); void dma_issue_pending_all(void); +struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param); +void dma_release_channel(struct dma_chan *chan); #else static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx) { @@ -831,7 +833,14 @@ static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descript } static inline void dma_issue_pending_all(void) { - do { } while (0); +} +static inline struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, + dma_filter_fn fn, void *fn_param) +{ + return NULL; +} +static inline void dma_release_channel(struct dma_chan *chan) +{ } #endif @@ -842,8 +851,6 @@ void dma_async_device_unregister(struct dma_device *device); void dma_run_dependencies(struct dma_async_tx_descriptor *tx); struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type); #define dma_request_channel(mask, x, y) __dma_request_channel(&(mask), x, y) -struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param); -void dma_release_channel(struct dma_chan *chan); /* --- Helper iov-locking functions --- */ -- cgit v1.2.3-18-g5258 From 46e67acd5d4cacda758e871eebd15cef4e2c2665 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 3 Jan 2011 09:09:56 -0200 Subject: [media] wm8775: Revert changeset fcb9757333 to avoid a regression It seems that cx88 and ivtv use wm8775 on some different modes. The patch that added support for a board with wm8775 broke ivtv boards with this device. As we're too close to release 2.6.37, let's just revert it. Reported-by: Andy Walls Reported-by: Eric Sharkey Reported-by: Auric Reported by: David Gesswein Signed-off-by: Mauro Carvalho Chehab --- include/media/wm8775.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/media/wm8775.h b/include/media/wm8775.h index a1c4d417dfa..60739c5a23a 100644 --- a/include/media/wm8775.h +++ b/include/media/wm8775.h @@ -32,7 +32,4 @@ #define WM8775_AIN3 4 #define WM8775_AIN4 8 -/* subdev group ID */ -#define WM8775_GID (1 << 0) - #endif -- cgit v1.2.3-18-g5258 From 6650239a4b01077e80d5a4468562756d77afaa59 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 8 Jan 2011 17:45:38 -0500 Subject: NFS: Don't use vm_map_ram() in readdir vm_map_ram() is not available on NOMMU platforms, and causes trouble on incoherrent architectures such as ARM when we access the page data through both the direct and the virtual mapping. The alternative is to use the direct mapping to access page data for the case when we are not crossing a page boundary, but to copy the data into a linear scratch buffer when we are accessing data that spans page boundaries. Signed-off-by: Trond Myklebust Tested-by: Marc Kleine-Budde Cc: stable@kernel.org [2.6.37] --- include/linux/sunrpc/xdr.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 498ab93a81e..7783c687c77 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -201,6 +201,8 @@ struct xdr_stream { __be32 *end; /* end of available buffer space */ struct kvec *iov; /* pointer to the current kvec */ + struct kvec scratch; /* Scratch buffer */ + struct page **page_ptr; /* pointer to the current page */ }; extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); @@ -208,7 +210,7 @@ extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int base, unsigned int len); extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); -extern __be32 *xdr_inline_peek(struct xdr_stream *xdr, size_t nbytes); +extern void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen); extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes); extern void xdr_read_pages(struct xdr_stream *xdr, unsigned int len); extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len); -- cgit v1.2.3-18-g5258