From cf14c2e987ba0a09a7b09be2ecd55af0bc9c17b4 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Tue, 2 Feb 2010 21:03:50 +0100 Subject: drbd: --dry-run option for drbdsetup net ( drbdadm -- --dry-run connect ) Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- include/linux/drbd.h | 2 +- include/linux/drbd_nl.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 78962272338a..4341b1a97a34 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -56,7 +56,7 @@ extern const char *drbd_buildtag(void); #define REL_VERSION "8.3.7" #define API_VERSION 88 #define PRO_VERSION_MIN 86 -#define PRO_VERSION_MAX 91 +#define PRO_VERSION_MAX 92 enum drbd_io_error_p { diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h index a4d82f895994..b41050e8cc2f 100644 --- a/include/linux/drbd_nl.h +++ b/include/linux/drbd_nl.h @@ -63,6 +63,7 @@ NL_PACKET(net_conf, 5, NL_BIT( 41, T_MAY_IGNORE, always_asbp) NL_BIT( 61, T_MAY_IGNORE, no_cork) NL_BIT( 62, T_MANDATORY, auto_sndbuf_size) + NL_BIT( 70, T_MANDATORY, dry_run) ) NL_PACKET(disconnect, 6, ) -- cgit v1.2.2 From 1f55243024087b56aef0b1e6d9c0ea89c76f0a6b Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Thu, 4 Mar 2010 15:51:01 +0100 Subject: drbd: Renamed overwrite_peer to primary_force Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- include/linux/drbd_nl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h index b41050e8cc2f..f7431a4ca608 100644 --- a/include/linux/drbd_nl.h +++ b/include/linux/drbd_nl.h @@ -12,7 +12,7 @@ #endif NL_PACKET(primary, 1, - NL_BIT( 1, T_MAY_IGNORE, overwrite_peer) + NL_BIT( 1, T_MAY_IGNORE, primary_force) ) NL_PACKET(secondary, 2, ) -- cgit v1.2.2 From f11c9c5c259cb2c3d698548dc3936f773ab1f5b9 Mon Sep 17 00:00:00 2001 From: Edward Shishkin Date: Thu, 11 Mar 2010 14:09:47 -0800 Subject: vfs: improve writeback_inodes_wb() Do not pin/unpin superblock for every inode in writeback_inodes_wb(), pin it for the whole group of inodes which belong to the same superblock and call writeback_sb_inodes() handler for them. Signed-off-by: Edward Shishkin Cc: Jens Axboe Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Jens Axboe --- include/linux/writeback.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 76e8903cd204..36520ded3e06 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -34,6 +34,9 @@ struct writeback_control { enum writeback_sync_modes sync_mode; unsigned long *older_than_this; /* If !NULL, only write back inodes older than this */ + unsigned long wb_start; /* Time writeback_inodes_wb was + called. This is needed to avoid + extra jobs and livelock */ long nr_to_write; /* Write this many pages, and decrement this for each page written */ long pages_skipped; /* Pages which were not written */ -- cgit v1.2.2 From 80a05b9ffa7dc13f6693902dd8999a2b61a3a0d7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 12 Mar 2010 17:34:14 +0100 Subject: clockevents: Sanitize min_delta_ns adjustment and prevent overflows The current logic which handles clock events programming failures can increase min_delta_ns unlimited and even can cause overflows. Sanitize it by: - prevent zero increase when min_delta_ns == 1 - limiting min_delta_ns to a jiffie - bail out if the jiffie limit is hit - add retries stats for /proc/timer_list so we can gather data Reported-by: Uwe Kleine-Koenig Signed-off-by: Thomas Gleixner --- include/linux/clockchips.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 0cf725bdd2a1..fc53492b6ad7 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -73,6 +73,7 @@ enum clock_event_nofitiers { * @list: list head for the management code * @mode: operating mode assigned by the management code * @next_event: local storage for the next event in oneshot mode + * @retries: number of forced programming retries */ struct clock_event_device { const char *name; @@ -93,6 +94,7 @@ struct clock_event_device { struct list_head list; enum clock_event_mode mode; ktime_t next_event; + unsigned long retries; }; /* -- cgit v1.2.2 From 2cda2728aa1c8c006418a24f867b25e5eb7a32e2 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Mon, 15 Mar 2010 12:46:51 +0100 Subject: block: Fix overrun in lcm() and move it to lib lcm() was defined to take integer-sized arguments. The supplied arguments are multiplied, however, causing us to overflow given sufficiently large input. That in turn led to incorrect optimal I/O size reporting in some cases (RAID over RAID). Switch lcm() over to unsigned long similar to gcd() and move the function from blk-settings.c to lib. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/lcm.h | 8 ++++++++ 1 file changed, 8 insertions(+) create mode 100644 include/linux/lcm.h (limited to 'include/linux') diff --git a/include/linux/lcm.h b/include/linux/lcm.h new file mode 100644 index 000000000000..7bf01d779b45 --- /dev/null +++ b/include/linux/lcm.h @@ -0,0 +1,8 @@ +#ifndef _LCM_H +#define _LCM_H + +#include + +unsigned long lcm(unsigned long a, unsigned long b) __attribute_const__; + +#endif /* _LCM_H */ -- cgit v1.2.2 From ee714f2dd33e726346e34f5cda12543162f4753e Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 10 Mar 2010 00:48:32 -0500 Subject: block: Finalize conversion of block limits functions Remove compatibility wrappers and update remaining drivers. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ebd22dbed861..41551c9341b6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -921,26 +921,7 @@ 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_queue_max_hw_sectors(struct request_queue *, unsigned int); - -/* Temporary compatibility wrapper */ -static inline void blk_queue_max_sectors(struct request_queue *q, unsigned int max) -{ - blk_queue_max_hw_sectors(q, max); -} - extern void blk_queue_max_segments(struct request_queue *, unsigned short); - -static inline void blk_queue_max_phys_segments(struct request_queue *q, unsigned short max) -{ - blk_queue_max_segments(q, max); -} - -static inline void blk_queue_max_hw_segments(struct request_queue *q, unsigned short max) -{ - blk_queue_max_segments(q, max); -} - - extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); @@ -1030,11 +1011,6 @@ static inline int sb_issue_discard(struct super_block *sb, extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); -#define MAX_PHYS_SEGMENTS 128 -#define MAX_HW_SEGMENTS 128 -#define SAFE_MAX_SECTORS 255 -#define MAX_SEGMENT_SIZE 65536 - enum blk_default_limits { BLK_MAX_SEGMENTS = 128, BLK_SAFE_MAX_SECTORS = 255, -- cgit v1.2.2 From 97fedbbe1046b3118f49df249840ca21041eefe4 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 16 Mar 2010 08:55:32 +0100 Subject: Remove GENHD_FL_DRIVERFS This flag is not used, so best discarded. Signed-off-by: NeilBrown -- Hi Jens, I came across this recently - these are the only two occurances of "GENHD_FL_DRIVERFS" in the kernel, so it cannot be needed. NeilBrown Signed-off-by: Jens Axboe --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 56b50514ab25..5f2f4c4d8fb0 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -109,7 +109,7 @@ struct hd_struct { }; #define GENHD_FL_REMOVABLE 1 -#define GENHD_FL_DRIVERFS 2 +/* 2 is unused */ #define GENHD_FL_MEDIA_CHANGE_NOTIFY 4 #define GENHD_FL_CD 8 #define GENHD_FL_UP 16 -- cgit v1.2.2 From e3818b8dce2a934cd1521dbc4827e5238d8f45d8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 15 Mar 2010 17:03:43 -0700 Subject: rcu: Make rcu_read_lock_bh_held() allow for disabled BH Disabling BH can stand in for rcu_read_lock_bh(), and this patch updates rcu_read_lock_bh_held() to allow for this. In order to avoid include-file hell, this function is moved out of line to kernel/rcupdate.c. This fixes a false positive RCU warning. Reported-by: Arnd Bergmann Reported-by: Eric Dumazet Signed-off-by: Paul E. McKenney Acked-by: Lai Jiangshan Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <20100316000343.GA25857@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- include/linux/rcupdate.h | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 3024050c82a1..e1bdc4bfd275 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -123,22 +123,11 @@ static inline int rcu_read_lock_held(void) return lock_is_held(&rcu_lock_map); } -/** - * rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section? - * - * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in - * an RCU-bh read-side critical section. In absence of CONFIG_PROVE_LOCKING, - * this assumes we are in an RCU-bh read-side critical section unless it can - * prove otherwise. - * - * Check rcu_scheduler_active to prevent false positives during boot. +/* + * rcu_read_lock_bh_held() is defined out of line to avoid #include-file + * hell. */ -static inline int rcu_read_lock_bh_held(void) -{ - if (!debug_lockdep_rcu_enabled()) - return 1; - return lock_is_held(&rcu_bh_lock_map); -} +extern int rcu_read_lock_bh_held(void); /** * rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section? -- cgit v1.2.2 From 7f5b774275df8c76a959eae7488128b637fcbfc8 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 16 Mar 2010 17:00:29 +0800 Subject: rcu: Fix tracepoints & lockdep false positive tracepoint.h uses rcu_dereference(), which triggers this warning: [ 0.701161] =================================================== [ 0.702211] [ INFO: suspicious rcu_dereference_check() usage. ] [ 0.702716] --------------------------------------------------- [ 0.703203] include/trace/events/workqueue.h:68 invoked rcu_dereference_check() without protection! [ 0.703971] [ 0.703990] other info that might help us debug this: [ 0.703993] [ 0.705590] [ 0.705604] rcu_scheduler_active = 1, debug_locks = 0 [ 0.706712] 1 lock held by swapper/1: [ 0.707229] #0: (cpu_add_remove_lock){+.+.+.}, at: [] cpu_maps_update_begin+0x14/0x20 [ 0.710097] [ 0.710106] stack backtrace: [ 0.712602] Pid: 1, comm: swapper Not tainted 2.6.34-rc1-tip-01613-g72662bb #168 [ 0.713231] Call Trace: [ 0.713997] [] lockdep_rcu_dereference+0x9d/0xb0 [ 0.714746] [] create_workqueue_thread+0x107/0x110 [ 0.715353] [] ? worker_thread+0x0/0x340 [ 0.715845] [] __create_workqueue_key+0x138/0x240 [ 0.716427] [] ? cpu_maps_update_done+0x12/0x20 [ 0.717012] [] init_workqueues+0x6f/0x80 [ 0.717530] [] kernel_init+0x102/0x1f0 [ 0.717570] [] ? kernel_init+0x0/0x1f0 [ 0.718944] [] kernel_thread_helper+0x6/0x10 Signed-off-by: Lai Jiangshan Cc: Paul E. McKenney Cc: Mathieu Desnoyers Cc: Steven Rostedt Cc: Frederic Weisbecker LKML-Reference: <4B9F48AD.4000404@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- include/linux/tracepoint.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index f59604ed0ec6..78b4bd3be496 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -49,7 +49,7 @@ struct tracepoint { void **it_func; \ \ rcu_read_lock_sched_notrace(); \ - it_func = rcu_dereference((tp)->funcs); \ + it_func = rcu_dereference_sched((tp)->funcs); \ if (it_func) { \ do { \ ((void(*)(proto))(*it_func))(args); \ -- cgit v1.2.2 From 0cff810f54b3b52075c27f7a7021d5b195264b6c Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 18 Mar 2010 12:25:33 -0700 Subject: rcu: Fix local_irq_disable() CONFIG_PROVE_RCU=y false positives It is documented that local_irq_disable() also delimits RCU_SCHED read-site critical sections. See the document of synchronize_sched() or Documentation/RCU/whatisRCU.txt. So we have to test irqs_disabled() in rcu_read_lock_sched_held(). Otherwise rcu-lockdep brings incorrect complaint. Signed-off-by: Lai Jiangshan Signed-off-by: Paul E. McKenney Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com Cc: eric.dumazet@gmail.com LKML-Reference: <1268940334-10892-1-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- include/linux/rcupdate.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e1bdc4bfd275..872a98e13d6a 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -149,7 +149,7 @@ static inline int rcu_read_lock_sched_held(void) return 1; if (debug_locks) lockdep_opinion = lock_is_held(&rcu_sched_lock_map); - return lockdep_opinion || preempt_count() != 0; + return lockdep_opinion || preempt_count() != 0 || irqs_disabled(); } #else /* #ifdef CONFIG_PREEMPT */ static inline int rcu_read_lock_sched_held(void) @@ -180,7 +180,7 @@ static inline int rcu_read_lock_bh_held(void) #ifdef CONFIG_PREEMPT static inline int rcu_read_lock_sched_held(void) { - return !rcu_scheduler_active || preempt_count() != 0; + return !rcu_scheduler_active || preempt_count() != 0 || irqs_disabled(); } #else /* #ifdef CONFIG_PREEMPT */ static inline int rcu_read_lock_sched_held(void) -- cgit v1.2.2 From 181fdde3b4268cb7b4af76ba6337e7ec8accbb36 Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Fri, 19 Mar 2010 08:58:16 +0100 Subject: block: remove 16 bytes of padding from struct request on 64bits Remove alignment padding to shrink struct request from 336 to 320 bytes so needing one fewer cacheline and therefore removing 48 bytes from struct request_queue. Signed-off-by: Richard Kennedy Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 41551c9341b6..6690e8bae7bb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -158,7 +158,6 @@ enum rq_flag_bits { struct request { struct list_head queuelist; struct call_single_data csd; - int cpu; struct request_queue *q; @@ -166,9 +165,11 @@ struct request { enum rq_cmd_type_bits cmd_type; unsigned long atomic_flags; + int cpu; + /* the following two fields are internal, NEVER access directly */ - sector_t __sector; /* sector cursor */ unsigned int __data_len; /* total data len */ + sector_t __sector; /* sector cursor */ struct bio *bio; struct bio *biotail; @@ -201,20 +202,20 @@ struct request { unsigned short ioprio; + int ref_count; + void *special; /* opaque pointer available for LLD use */ char *buffer; /* kaddr of the current segment if available */ int tag; int errors; - int ref_count; - /* * when request is used as a packet command carrier */ - unsigned short cmd_len; unsigned char __cmd[BLK_MAX_CDB]; unsigned char *cmd; + unsigned short cmd_len; unsigned int extra_len; /* length of alignment and padding */ unsigned int sense_len; -- cgit v1.2.2 From c9acb42ef1904d15d0fb315061cefbe638f67f3a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 19 Mar 2010 15:36:22 -0400 Subject: SUNRPC: Fix a use after free bug with the NFSv4.1 backchannel The ->release_request() callback was designed to allow the transport layer to do housekeeping after the RPC call is done. It cannot be used to free the request itself, and doing so leads to a use-after-free bug in xprt_release(). Signed-off-by: Trond Myklebust --- include/linux/sunrpc/bc_xprt.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index d7152b451e21..7c91260c44a9 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -36,7 +36,6 @@ struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt); void xprt_free_bc_request(struct rpc_rqst *req); int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs); void xprt_destroy_backchannel(struct rpc_xprt *, int max_reqs); -void bc_release_request(struct rpc_task *); int bc_send(struct rpc_rqst *req); /* @@ -59,6 +58,10 @@ static inline int svc_is_backchannel(const struct svc_rqst *rqstp) { return 0; } + +static inline void xprt_free_bc_request(struct rpc_rqst *req) +{ +} #endif /* CONFIG_NFS_V4_1 */ #endif /* _LINUX_SUNRPC_BC_XPRT_H */ -- cgit v1.2.2 From 66f1207bce10fd80ee8ce99b67d617644612f05e Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 11 Mar 2010 17:01:09 -0700 Subject: resources: add interfaces that return conflict information request_resource() and insert_resource() only return success or failure, which no information about what existing resource conflicted with the proposed new reservation. This patch adds request_resource_conflict() and insert_resource_conflict(), which return the conflicting resource. Callers may use this for better error messages or to adjust the new resource and retry the request. Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- include/linux/ioport.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 71ab79da7e7f..26fad187d661 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -112,12 +112,14 @@ struct resource_list { extern struct resource ioport_resource; extern struct resource iomem_resource; +extern struct resource *request_resource_conflict(struct resource *root, struct resource *new); extern int request_resource(struct resource *root, struct resource *new); extern int release_resource(struct resource *new); void release_child_resources(struct resource *new); extern void reserve_region_with_split(struct resource *root, resource_size_t start, resource_size_t end, const char *name); +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 int allocate_resource(struct resource *root, struct resource *new, -- cgit v1.2.2 From 8a6d9b149f105f8bdfa8e42dd9753e45a1887a16 Mon Sep 17 00:00:00 2001 From: Ferenc Wagner Date: Wed, 24 Mar 2010 08:20:03 +0100 Subject: i2o: Remove the dangerous kobj_to_i2o_device macro This macro worked only when applied to variables named 'kobj'. While this could have been fixed by simply renaming the macro argument, a more type-safe replacement by an inline function would be preferred. However, nobody uses this macro, so it's simpler to just remove it. Signed-off-by: Ferenc Wagner Signed-off-by: Jens Axboe --- include/linux/i2o.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2o.h b/include/linux/i2o.h index 87018dc5527d..9e7a12d6385d 100644 --- a/include/linux/i2o.h +++ b/include/linux/i2o.h @@ -782,7 +782,6 @@ extern int i2o_exec_lct_get(struct i2o_controller *); #define to_i2o_driver(drv) container_of(drv,struct i2o_driver, driver) #define to_i2o_device(dev) container_of(dev, struct i2o_device, device) #define to_i2o_controller(dev) container_of(dev, struct i2o_controller, device) -#define kobj_to_i2o_device(kobj) to_i2o_device(container_of(kobj, struct device, kobj)) /** * i2o_out_to_virt - Turn an I2O message to a virtual address -- cgit v1.2.2 From 4c87684d32e8f95715d53039dcd2d998dc63d1eb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?David=20H=C3=A4rdeman?= Date: Tue, 23 Mar 2010 13:35:22 -0700 Subject: kfifo: fix KFIFO_INIT in include/linux/kfifo.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit include/linux/kfifo.h first defines and then undefines __kfifo_initializer which is used by INIT_KFIFO (which is also a macro, so building a module which uses INIT_KFIFO will fail). Signed-off-by: David Härdeman Acked-by: Stefani Seibold Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfifo.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index bc0fc795bd35..ece0b1c33816 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -102,8 +102,6 @@ union { \ unsigned char name##kfifo_buffer[size]; \ struct kfifo name = __kfifo_initializer(size, name##kfifo_buffer) -#undef __kfifo_initializer - extern void kfifo_init(struct kfifo *fifo, void *buffer, unsigned int size); extern __must_check int kfifo_alloc(struct kfifo *fifo, unsigned int size, -- cgit v1.2.2 From 6cb4aff0a77cc0e6bae9475d62205319e3ebbf3f Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Tue, 23 Mar 2010 13:35:38 -0700 Subject: reiserfs: fix oops while creating privroot with selinux enabled Commit 57fe60df ("reiserfs: add atomic addition of selinux attributes during inode creation") contains a bug that will cause it to oops when mounting a file system that didn't previously contain extended attributes on a system using security.* xattrs. The issue is that while creating the privroot during mount reiserfs_security_init calls reiserfs_xattr_jcreate_nblocks which dereferences the xattr root. The xattr root doesn't exist, so we get an oops. Addresses http://bugzilla.kernel.org/show_bug.cgi?id=15309 Signed-off-by: Jeff Mahoney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reiserfs_xattr.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index 99928dce37ea..7fa02b4af838 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -70,6 +70,11 @@ int reiserfs_security_write(struct reiserfs_transaction_handle *th, void reiserfs_security_free(struct reiserfs_security_handle *sec); #endif +static inline int reiserfs_xattrs_initialized(struct super_block *sb) +{ + return REISERFS_SB(sb)->priv_root != NULL; +} + #define xattr_size(size) ((size) + sizeof(struct reiserfs_xattr_header)) static inline loff_t reiserfs_xattr_nblocks(struct inode *inode, loff_t size) { -- cgit v1.2.2 From 7198f3c9b13c7aa1e5d9f7ff74c0ea303174feff Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 23 Mar 2010 13:35:40 -0700 Subject: mmc: fix incorrect interpretation of card type bits In the extended CSD register the CARD_TYPE is an 8-bit value of which the upper 6 bits were reserved in JEDEC specifications prior to version 4.4. In version 4.4 two of the reserved bits were designated for identifying support for the newly added High-Speed Dual Data Rate. Unfortunately the mmc_read_ext_csd() function required that the reserved bits be zero instead of ignoring them as it should. This patch makes mmc_read_ext_csd() ignore the CARD_TYPE bits that are reserved or not yet supported. It also stops the function jumping to the end as though an error occurred, when it is only warns that the CARD_TYPE bits (that it does interpret) are invalid. Signed-off-by: Adrian Hunter Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/mmc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index c02c8db73701..8a49cbf0376d 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -268,6 +268,7 @@ struct _mmc_csd { #define EXT_CSD_CARD_TYPE_26 (1<<0) /* Card can run at 26MHz */ #define EXT_CSD_CARD_TYPE_52 (1<<1) /* Card can run at 52MHz */ +#define EXT_CSD_CARD_TYPE_MASK 0x3 /* Mask out reserved and DDR bits */ #define EXT_CSD_BUS_WIDTH_1 0 /* Card is in 1 bit mode */ #define EXT_CSD_BUS_WIDTH_4 1 /* Card is in 4 bit mode */ -- cgit v1.2.2 From 90fddabf5818367c6bd1fe1b256a10e01827862f Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 24 Mar 2010 09:43:00 +0000 Subject: Document Linux's circular buffering capabilities Document the circular buffering capabilities available in Linux. Signed-off-by: David Howells Signed-off-by: Paul E. McKenney Reviewed-by: Randy Dunlap Reviewed-by: Stefan Richter Signed-off-by: Linus Torvalds --- include/linux/circ_buf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/circ_buf.h b/include/linux/circ_buf.h index a2ed0591fb19..90f2471dc6f2 100644 --- a/include/linux/circ_buf.h +++ b/include/linux/circ_buf.h @@ -1,3 +1,7 @@ +/* + * See Documentation/circular-buffers.txt for more information. + */ + #ifndef _LINUX_CIRC_BUF_H #define _LINUX_CIRC_BUF_H 1 -- cgit v1.2.2 From 5a7aadfe2fcb0f69e2acc1fbefe22a096e792fc9 Mon Sep 17 00:00:00 2001 From: Matt Helsley Date: Fri, 26 Mar 2010 23:51:44 +0100 Subject: Freezer: Fix buggy resume test for tasks frozen with cgroup freezer When the cgroup freezer is used to freeze tasks we do not want to thaw those tasks during resume. Currently we test the cgroup freezer state of the resuming tasks to see if the cgroup is FROZEN. If so then we don't thaw the task. However, the FREEZING state also indicates that the task should remain frozen. This also avoids a problem pointed out by Oren Ladaan: the freezer state transition from FREEZING to FROZEN is updated lazily when userspace reads or writes the freezer.state file in the cgroup filesystem. This means that resume will thaw tasks in cgroups which should be in the FROZEN state if there is no read/write of the freezer.state file to trigger this transition before suspend. NOTE: Another "simple" solution would be to always update the cgroup freezer state during resume. However it's a bad choice for several reasons: Updating the cgroup freezer state is somewhat expensive because it requires walking all the tasks in the cgroup and checking if they are each frozen. Worse, this could easily make resume run in N^2 time where N is the number of tasks in the cgroup. Finally, updating the freezer state from this code path requires trickier locking because of the way locks must be ordered. Instead of updating the freezer state we rely on the fact that lazy updates only manage the transition from FREEZING to FROZEN. We know that a cgroup with the FREEZING state may actually be FROZEN so test for that state too. This makes sense in the resume path even for partially-frozen cgroups -- those that really are FREEZING but not FROZEN. Reported-by: Oren Ladaan Signed-off-by: Matt Helsley Cc: stable@kernel.org Signed-off-by: Rafael J. Wysocki --- include/linux/freezer.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 5a361f85cfec..da7e52b099f3 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -64,9 +64,12 @@ extern bool freeze_task(struct task_struct *p, bool sig_only); extern void cancel_freezing(struct task_struct *p); #ifdef CONFIG_CGROUP_FREEZER -extern int cgroup_frozen(struct task_struct *task); +extern int cgroup_freezing_or_frozen(struct task_struct *task); #else /* !CONFIG_CGROUP_FREEZER */ -static inline int cgroup_frozen(struct task_struct *task) { return 0; } +static inline int cgroup_freezing_or_frozen(struct task_struct *task) +{ + return 0; +} #endif /* !CONFIG_CGROUP_FREEZER */ /* -- cgit v1.2.2 From 259354deaaf03d49a02dbb9975d6ec2a54675672 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 10 Mar 2010 18:56:10 +0900 Subject: module: encapsulate percpu handling better and record percpu_size Better encapsulate module static percpu area handling so that code outsidef of CONFIG_SMP ifdef doesn't deal with mod->percpu directly and add mod->percpu_size and record percpu_size in it. Both percpu fields are compiled out on UP. While at it, mark mod->percpu w/ __percpu. This is to prepare for is_module_percpu_address(). Signed-off-by: Tejun Heo Acked-by: Rusty Russell --- include/linux/module.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 5e869ffd34aa..87d247ac6761 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -330,8 +330,11 @@ struct module struct module_notes_attrs *notes_attrs; #endif +#ifdef CONFIG_SMP /* Per-cpu data. */ - void *percpu; + void __percpu *percpu; + unsigned int percpu_size; +#endif /* The command line arguments (may be mangled). People like keeping pointers to this stuff */ -- cgit v1.2.2 From 10fad5e46f6c7bdfb01b1a012380a38e3c6ab346 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 10 Mar 2010 18:57:54 +0900 Subject: percpu, module: implement and use is_kernel/module_percpu_address() lockdep has custom code to check whether a pointer belongs to static percpu area which is somewhat broken. Implement proper is_kernel/module_percpu_address() and replace the custom code. On UP, percpu variables are regular static variables and can't be distinguished from them. Always return %false on UP. Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra Cc: Rusty Russell Cc: Ingo Molnar --- include/linux/module.h | 1 + include/linux/percpu.h | 7 +++++++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 87d247ac6761..f0e2659f4e3e 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -395,6 +395,7 @@ static inline int module_is_live(struct module *mod) struct module *__module_text_address(unsigned long addr); struct module *__module_address(unsigned long addr); bool is_module_address(unsigned long addr); +bool is_module_percpu_address(unsigned long addr); bool is_module_text_address(unsigned long addr); static inline int within_module_core(unsigned long addr, struct module *mod) diff --git a/include/linux/percpu.h b/include/linux/percpu.h index a93e5bfdccb8..11d5f834b54a 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -137,6 +137,7 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align); extern void __percpu *__alloc_percpu(size_t size, size_t align); extern void free_percpu(void __percpu *__pdata); +extern bool is_kernel_percpu_address(unsigned long addr); extern phys_addr_t per_cpu_ptr_to_phys(void *addr); #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA @@ -163,6 +164,12 @@ static inline void free_percpu(void __percpu *p) kfree(p); } +/* can't distinguish from other static vars, always false */ +static inline bool is_kernel_percpu_address(unsigned long addr) +{ + return false; +} + static inline phys_addr_t per_cpu_ptr_to_phys(void *addr) { return __pa(addr); -- cgit v1.2.2 From a53f4f9efaeb1d87cfae066346979d4d70e1abe9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 29 Mar 2010 13:08:52 +0100 Subject: SLOW_WORK: CONFIG_SLOW_WORK_PROC should be CONFIG_SLOW_WORK_DEBUG CONFIG_SLOW_WORK_PROC was changed to CONFIG_SLOW_WORK_DEBUG, but not in all instances. Change the remaining instances. This makes the debugfs file display the time mark and the owner's description again. Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- include/linux/fscache-cache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 7be0c6fbe880..c57db27ac861 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -105,7 +105,7 @@ struct fscache_operation { /* operation releaser */ fscache_operation_release_t release; -#ifdef CONFIG_SLOW_WORK_PROC +#ifdef CONFIG_SLOW_WORK_DEBUG const char *name; /* operation name */ const char *state; /* operation state */ #define fscache_set_op_name(OP, N) do { (OP)->name = (N); } while(0) -- cgit v1.2.2 From c36207a4624f15020f2918324405c1c88a5d4cbc Mon Sep 17 00:00:00 2001 From: viresh kumar Date: Mon, 29 Mar 2010 05:28:32 +0100 Subject: ARM: 5999/1: Including device.h and resource.h header files in linux/amba/bus.h linux/amba/bus.h have dependencies on linux/device.h and linux/resource.h, but it doesn't include them. We get compilation errors in our files which include bus.h but doesn't include device.h and resource.h. This patch includes device.h and resource.h in linux/amba/bus.h file. Signed-off-by: Viresh Kumar Acked-by: Linux Walleij Signed-off-by: Russell King --- include/linux/amba/bus.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 6816be6c3f77..8b1038607831 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -14,6 +14,9 @@ #ifndef ASMARM_AMBA_H #define ASMARM_AMBA_H +#include +#include + #define AMBA_NR_IRQS 2 struct amba_device { -- cgit v1.2.2 From 367d6acceaacff1adc44f121543effb9c060e575 Mon Sep 17 00:00:00 2001 From: viresh kumar Date: Mon, 29 Mar 2010 05:29:56 +0100 Subject: ARM: 6003/1: removing compilation warning from pl061.h pl061.h is using u8 type. including in pl061.h to avoid warning. Signed-off-by: Viresh Kumar Acked-by: Baruch Siach Signed-off-by: Russell King --- include/linux/amba/pl061.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/amba/pl061.h b/include/linux/amba/pl061.h index b4fbd9862606..5ddd9ad4b19c 100644 --- a/include/linux/amba/pl061.h +++ b/include/linux/amba/pl061.h @@ -1,3 +1,5 @@ +#include + /* platform data for the PL061 GPIO driver */ struct pl061_platform_data { -- cgit v1.2.2 From de329820e920cd9cfbc2127cad26a37026260cce Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 29 Mar 2010 14:30:19 -0700 Subject: ext3: fix broken handling of EXT3_STATE_NEW In commit 9df93939b735 ("ext3: Use bitops to read/modify EXT3_I(inode)->i_state") ext3 changed its internal 'i_state' variable to use bitops for its state handling. However, unline the same ext4 change, it didn't actually change the name of the field when it changed the semantics of it. As a result, an old use of 'i_state' remained in fs/ext3/ialloc.c that initialized the field to EXT3_STATE_NEW. And that does not work _at_all_ when we're now working with individually named bits rather than values that get masked. So the code tried to mark the state to be new, but in actual fact set the field to EXT3_STATE_JDATA. Which makes no sense at all, and screws up all the code that checks whether the inode was newly allocated. In particular, it made the xattr code unhappy, and caused various random behavior, like apparently https://bugzilla.redhat.com/show_bug.cgi?id=577911 So fix the initialization, and rename the field to match ext4 so that we don't have this happen again. Cc: James Morris Cc: Stephen Smalley Cc: Daniel J Walsh Cc: Eric Paris Cc: Jan Kara Signed-off-by: Linus Torvalds --- include/linux/ext3_fs.h | 6 +++--- include/linux/ext3_fs_i.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index cac84b006667..5f494b465097 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -565,17 +565,17 @@ enum { static inline int ext3_test_inode_state(struct inode *inode, int bit) { - return test_bit(bit, &EXT3_I(inode)->i_state); + return test_bit(bit, &EXT3_I(inode)->i_state_flags); } static inline void ext3_set_inode_state(struct inode *inode, int bit) { - set_bit(bit, &EXT3_I(inode)->i_state); + set_bit(bit, &EXT3_I(inode)->i_state_flags); } static inline void ext3_clear_inode_state(struct inode *inode, int bit) { - clear_bit(bit, &EXT3_I(inode)->i_state); + clear_bit(bit, &EXT3_I(inode)->i_state_flags); } #else /* Assume that user mode programs are passing in an ext3fs superblock, not diff --git a/include/linux/ext3_fs_i.h b/include/linux/ext3_fs_i.h index 7679acdb519a..f42c098aed8d 100644 --- a/include/linux/ext3_fs_i.h +++ b/include/linux/ext3_fs_i.h @@ -87,7 +87,7 @@ struct ext3_inode_info { * near to their parent directory's inode. */ __u32 i_block_group; - unsigned long i_state; /* Dynamic state flags for ext3 */ + unsigned long i_state_flags; /* Dynamic state flags for ext3 */ /* block reservation info */ struct ext3_block_alloc_info *i_block_alloc_info; -- cgit v1.2.2 From 5a0e3ad6af8660be21ca98a971cd00f331318c05 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 24 Mar 2010 17:04:11 +0900 Subject: include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo Guess-its-ok-by: Christoph Lameter Cc: Ingo Molnar Cc: Lee Schermerhorn --- include/linux/delayacct.h | 1 + include/linux/fsnotify.h | 1 + include/linux/gameport.h | 1 + include/linux/io-mapping.h | 1 + include/linux/jbd.h | 1 + include/linux/jbd2.h | 1 + include/linux/security.h | 2 +- include/linux/spi/spi.h | 1 + include/linux/taskstats_kern.h | 1 + include/linux/usb/gadget.h | 2 ++ include/linux/wimax/debug.h | 1 + 11 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 5076fe0c8a96..6cee17c22313 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -18,6 +18,7 @@ #define _LINUX_DELAYACCT_H #include +#include /* * Per-task flags relevant to delay accounting diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index df8fd9a3b214..01755909ce81 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -15,6 +15,7 @@ #include #include #include +#include /* * fsnotify_d_instantiate - instantiate a dentry for inode diff --git a/include/linux/gameport.h b/include/linux/gameport.h index 48e68da097f6..361d1cc288d0 100644 --- a/include/linux/gameport.h +++ b/include/linux/gameport.h @@ -16,6 +16,7 @@ #include #include #include +#include struct gameport { diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 97eb928b4924..25085ddd955f 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -19,6 +19,7 @@ #define _LINUX_IO_MAPPING_H #include +#include #include #include #include diff --git a/include/linux/jbd.h b/include/linux/jbd.h index f3aa59cb675d..516a2a27e87a 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -31,6 +31,7 @@ #include #include #include +#include #define journal_oom_retry 1 diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 1ec876358180..a4d2e9f7088a 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -30,6 +30,7 @@ #include #include #include +#include #endif #define journal_oom_retry 1 diff --git a/include/linux/security.h b/include/linux/security.h index 233d20b52c1b..3158dd982d27 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include /* Maximum number of letters for an LSM name string */ diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 97b60b37f445..af56071b06f9 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -21,6 +21,7 @@ #include #include +#include /* * INTERFACES between SPI master-side drivers and SPI infrastructure. diff --git a/include/linux/taskstats_kern.h b/include/linux/taskstats_kern.h index b6523c1427ce..58de6edf751f 100644 --- a/include/linux/taskstats_kern.h +++ b/include/linux/taskstats_kern.h @@ -9,6 +9,7 @@ #include #include +#include #ifdef CONFIG_TASKSTATS extern struct kmem_cache *taskstats_cache; diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index bbf45d500b6d..f4b7ca516cdd 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -15,6 +15,8 @@ #ifndef __LINUX_USB_GADGET_H #define __LINUX_USB_GADGET_H +#include + struct usb_ep; /** diff --git a/include/linux/wimax/debug.h b/include/linux/wimax/debug.h index db8096e88533..57031b4d12f2 100644 --- a/include/linux/wimax/debug.h +++ b/include/linux/wimax/debug.h @@ -155,6 +155,7 @@ #include #include +#include /* Backend stuff */ -- cgit v1.2.2 From de380b55f92986c1a84198149cb71b7228d15fbd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 24 Mar 2010 17:06:43 +0900 Subject: percpu: don't implicitly include slab.h from percpu.h percpu.h has always been including slab.h to get k[mz]alloc/free() for UP inline implementation. percpu.h being used by very low level headers including module.h and sched.h, this meant that a lot files unintentionally got slab.h inclusion. Lee Schermerhorn was trying to make topology.h use percpu.h and got bitten by this implicit inclusion. The right thing to do is break this ultimately unnecessary dependency. The previous patch added explicit inclusion of either gfp.h or slab.h to the source files using them. This patch updates percpu.h such that slab.h is no longer included from percpu.h. Signed-off-by: Tejun Heo Reviewed-by: Christoph Lameter Cc: Ingo Molnar Cc: Lee Schermerhorn --- include/linux/percpu.h | 30 +++++------------------------- 1 file changed, 5 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index a93e5bfdccb8..c7845130bfdf 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -2,10 +2,10 @@ #define __LINUX_PERCPU_H #include -#include /* For kmalloc() */ #include #include #include +#include #include @@ -135,9 +135,6 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, #define per_cpu_ptr(ptr, cpu) SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu))) extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align); -extern void __percpu *__alloc_percpu(size_t size, size_t align); -extern void free_percpu(void __percpu *__pdata); -extern phys_addr_t per_cpu_ptr_to_phys(void *addr); #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA extern void __init setup_per_cpu_areas(void); @@ -147,27 +144,6 @@ extern void __init setup_per_cpu_areas(void); #define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) -static inline void __percpu *__alloc_percpu(size_t size, size_t align) -{ - /* - * Can't easily make larger alignment work with kmalloc. WARN - * on it. Larger alignment should only be used for module - * percpu sections on SMP for which this path isn't used. - */ - WARN_ON_ONCE(align > SMP_CACHE_BYTES); - return kzalloc(size, GFP_KERNEL); -} - -static inline void free_percpu(void __percpu *p) -{ - kfree(p); -} - -static inline phys_addr_t per_cpu_ptr_to_phys(void *addr) -{ - return __pa(addr); -} - static inline void __init setup_per_cpu_areas(void) { } static inline void *pcpu_lpage_remapped(void *kaddr) @@ -177,6 +153,10 @@ static inline void *pcpu_lpage_remapped(void *kaddr) #endif /* CONFIG_SMP */ +extern void __percpu *__alloc_percpu(size_t size, size_t align); +extern void free_percpu(void __percpu *__pdata); +extern phys_addr_t per_cpu_ptr_to_phys(void *addr); + #define alloc_percpu(type) \ (typeof(type) __percpu *)__alloc_percpu(sizeof(type), __alignof__(type)) -- cgit v1.2.2 From d5e50daf92df8afcb701fd717b301985691e802f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 31 Mar 2010 11:33:42 +0900 Subject: module: add stub for is_module_percpu_address Fix build for CONFIG_MODULES not enabled by providing a stub for is_module_percpu_address(). kernel/lockdep.c:605: error: implicit declaration of function 'is_module_percpu_address' Signed-off-by: Randy Dunlap Signed-off-by: Tejun Heo --- include/linux/module.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index f0e2659f4e3e..8bd399a00343 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -567,6 +567,11 @@ static inline bool is_module_address(unsigned long addr) return false; } +static inline bool is_module_percpu_address(unsigned long addr) +{ + return false; +} + static inline bool is_module_text_address(unsigned long addr) { return false; -- cgit v1.2.2 From e49a5bd38159dfb1928fd25b173bc9de4bbadb21 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 22 Mar 2010 19:40:03 +0100 Subject: perf: Use hot regs with software sched switch/migrate events Scheduler's task migration events don't work because they always pass NULL regs perf_sw_event(). The event hence gets filtered in perf_swevent_add(). Scheduler's context switches events use task_pt_regs() to get the context when the event occured which is a wrong thing to do as this won't give us the place in the kernel where we went to sleep but the place where we left userspace. The result is even more wrong if we switch from a kernel thread. Use the hot regs snapshot for both events as they belong to the non-interrupt/exception based events family. Unlike page faults or so that provide the regs matching the exact origin of the event, we need to save the current context. This makes the task migration event working and fix the context switch callchains and origin ip. Example: perf record -a -e cs Before: 10.91% ksoftirqd/0 0 [k] 0000000000000000 | --- (nil) perf_callchain perf_prepare_sample __perf_event_overflow perf_swevent_overflow perf_swevent_add perf_swevent_ctx_event do_perf_sw_event __perf_sw_event perf_event_task_sched_out schedule run_ksoftirqd kthread kernel_thread_helper After: 23.77% hald-addon-stor [kernel.kallsyms] [k] schedule | --- schedule | |--60.00%-- schedule_timeout | wait_for_common | wait_for_completion | blk_execute_rq | scsi_execute | scsi_execute_req | sr_test_unit_ready | | | |--66.67%-- sr_media_change | | media_changed | | cdrom_media_changed | | sr_block_media_changed | | check_disk_change | | cdrom_open v2: Always build perf_arch_fetch_caller_regs() now that software events need that too. They don't need it from modules, unlike trace events, so we keep the EXPORT_SYMBOL in trace_event_perf.c Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Paul Mackerras Cc: Ingo Molnar Cc: David Miller --- include/linux/perf_event.h | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 95477038a72a..c8e375440403 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -842,13 +842,6 @@ extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64); -static inline void -perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) -{ - if (atomic_read(&perf_swevent_enabled[event_id])) - __perf_sw_event(event_id, nr, nmi, regs, addr); -} - extern void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip); @@ -887,6 +880,20 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip) return perf_arch_fetch_caller_regs(regs, ip, skip); } +static inline void +perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) +{ + if (atomic_read(&perf_swevent_enabled[event_id])) { + struct pt_regs hot_regs; + + if (!regs) { + perf_fetch_caller_regs(&hot_regs, 1); + regs = &hot_regs; + } + __perf_sw_event(event_id, nr, nmi, regs, addr); + } +} + extern void __perf_event_mmap(struct vm_area_struct *vma); static inline void perf_event_mmap(struct vm_area_struct *vma) -- cgit v1.2.2 From 6072f7491f5ef391a575e18a1165e72a3eef1601 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 31 Mar 2010 20:11:59 +0000 Subject: ide: Requeue request after DMA timeout I noticed that my KVM virtual machines were experiencing IDE issues resulting in processes stuck on waiting for buffers to complete. The root cause is of course race conditions in the ancient qemu backend that I'm using. However, the fact that the guest isn't recovering is a bug. I've tracked it down to the change made last year to dequeue requests at the start rather than at the end in the IDE layer. commit 8f6205cd572fece673da0255d74843680f67f879 Author: Tejun Heo Date: Fri May 8 11:53:59 2009 +0900 ide: dequeue in-flight request The problem is that the function ide_dma_timeout_retry does not requeue the current request, causing one request to be lost for each DMA timeout. This patch fixes this by requeueing the request. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/ide.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index 97e6ab435184..3239d1c10acb 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -1169,6 +1169,7 @@ extern void ide_stall_queue(ide_drive_t *drive, unsigned long timeout); extern void ide_timer_expiry(unsigned long); extern irqreturn_t ide_intr(int irq, void *dev_id); extern void do_ide_request(struct request_queue *); +extern void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq); void ide_init_disk(struct gendisk *, ide_drive_t *); -- cgit v1.2.2 From 042be38e6106ed70b42d096ab4a1ed4187e510e6 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 1 Apr 2010 14:32:43 -0700 Subject: ibft, x86: Change reserve_ibft_region() to find_ibft_region() This allows arch code could decide the way to reserve the ibft. And we should reserve ibft as early as possible, instead of BOOTMEM stage, in case the table is in RAM range and is not reserved by BIOS (this will often be the case.) Move to just after find_smp_config(). Also when CONFIG_NO_BOOTMEM=y, We will not have reserve_bootmem() anymore. -v2: fix typo about ibft pointed by Konrad Rzeszutek Wilk Signed-off-by: Yinghai Lu LKML-Reference: <4BB510FB.80601@kernel.org> Cc: Pekka Enberg Cc: Peter Jones Cc: Konrad Rzeszutek Wilk CC: Jan Beulich Signed-off-by: H. Peter Anvin --- include/linux/iscsi_ibft.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iscsi_ibft.h b/include/linux/iscsi_ibft.h index 6092487e2950..d2e4042f8f5e 100644 --- a/include/linux/iscsi_ibft.h +++ b/include/linux/iscsi_ibft.h @@ -42,9 +42,13 @@ extern struct ibft_table_header *ibft_addr; * mapped address is set in the ibft_addr variable. */ #ifdef CONFIG_ISCSI_IBFT_FIND -extern void __init reserve_ibft_region(void); +unsigned long find_ibft_region(unsigned long *sizep); #else -static inline void reserve_ibft_region(void) { } +static inline unsigned long find_ibft_region(unsigned long *sizep) +{ + *sizep = 0; + return 0; +} #endif #endif /* ISCSI_IBFT_H */ -- cgit v1.2.2 From 5fbfb18d7a5b846946d52c4a10e3aaa213ec31b6 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Thu, 1 Apr 2010 19:09:40 +1100 Subject: Fix up possibly racy module refcounting Module refcounting is implemented with a per-cpu counter for speed. However there is a race when tallying the counter where a reference may be taken by one CPU and released by another. Reference count summation may then see the decrement without having seen the previous increment, leading to lower than expected count. A module which never has its actual reference drop below 1 may return a reference count of 0 due to this race. Module removal generally runs under stop_machine, which prevents this race causing bugs due to removal of in-use modules. However there are other real bugs in module.c code and driver code (module_refcount is exported) where the callers do not run under stop_machine. Fix this by maintaining running per-cpu counters for the number of module refcount increments and the number of refcount decrements. The increments are tallied after the decrements, so any decrement seen will always have its corresponding increment counted. The final refcount is the difference of the total increments and decrements, preventing a low-refcount from being returned. Signed-off-by: Nick Piggin Acked-by: Rusty Russell Signed-off-by: Linus Torvalds --- include/linux/module.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 8bd399a00343..515d53ae6a79 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -368,7 +368,8 @@ struct module void (*exit)(void); struct module_ref { - int count; + unsigned int incs; + unsigned int decs; } __percpu *refptr; #endif @@ -463,9 +464,9 @@ static inline void __module_get(struct module *module) { if (module) { preempt_disable(); - __this_cpu_inc(module->refptr->count); + __this_cpu_inc(module->refptr->incs); trace_module_get(module, _THIS_IP_, - __this_cpu_read(module->refptr->count)); + __this_cpu_read(module->refptr->incs)); preempt_enable(); } } @@ -478,11 +479,10 @@ static inline int try_module_get(struct module *module) preempt_disable(); if (likely(module_is_live(module))) { - __this_cpu_inc(module->refptr->count); + __this_cpu_inc(module->refptr->incs); trace_module_get(module, _THIS_IP_, - __this_cpu_read(module->refptr->count)); - } - else + __this_cpu_read(module->refptr->incs)); + } else ret = 0; preempt_enable(); -- cgit v1.2.2 From 445d211b0da4e9a6e6d576edff85085c2aaf53df Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 5 Apr 2010 10:33:13 +0900 Subject: libata: unlock HPA if device shrunk Some BIOSes don't configure HPA during boot but do so while resuming. This causes harddrives to shrink during resume making libata detach and reattach them. This can be worked around by unlocking HPA if old size equals native size. Add ATA_DFLAG_UNLOCK_HPA so that HPA unlocking can be controlled per-device and update ata_dev_revalidate() such that it sets ATA_DFLAG_UNLOCK_HPA and fails with -EIO when the above condition is detected. This patch fixes the following bug. https://bugzilla.kernel.org/show_bug.cgi?id=15396 Signed-off-by: Tejun Heo Reported-by: Oleksandr Yermolenko Signed-off-by: Jeff Garzik --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index f8ea71e6d0e2..b2f2003b92e5 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -146,6 +146,7 @@ enum { ATA_DFLAG_SLEEPING = (1 << 15), /* device is sleeping */ ATA_DFLAG_DUBIOUS_XFER = (1 << 16), /* data transfer not verified */ ATA_DFLAG_NO_UNLOAD = (1 << 17), /* device doesn't support unload */ + ATA_DFLAG_UNLOCK_HPA = (1 << 18), /* unlock HPA */ ATA_DFLAG_INIT_MASK = (1 << 24) - 1, ATA_DFLAG_DETACH = (1 << 24), -- cgit v1.2.2 From b01d0942c2b7a3026d2b7d38b5773d3d00420e06 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 6 Apr 2010 14:34:41 -0700 Subject: bitops: remove temporary for_each_bit() Migration has been completed so remove this now. There's one straggler in linux-next's drivers/mtd/sm_ftl.c. A patch has been sent. Cc: Akinobu Mita Cc: Stephen Rothwell Cc: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitops.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index b79389879238..b796eab5ca75 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -21,9 +21,6 @@ (bit) < (size); \ (bit) = find_next_bit((addr), (size), (bit) + 1)) -/* Temporary */ -#define for_each_bit(bit, addr, size) for_each_set_bit(bit, addr, size) - static __inline__ int get_bitmask_order(unsigned int count) { int order; -- cgit v1.2.2 From 530cd330dc3865e3107304a6e84fdc332aa72f7d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?David=20H=C3=A4rdeman?= Date: Tue, 6 Apr 2010 14:34:43 -0700 Subject: include/linux/kfifo.h: fix INIT_KFIFO() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit DECLARE_KFIFO creates a union with a struct kfifo and a buffer array with size [size + sizeof(struct kfifo)]. INIT_KFIFO then sets the buffer pointer in struct kfifo to point to the beginning of the buffer array which means that the first call to kfifo_in will overwrite members of the struct kfifo. Signed-off-by: David Härdeman Acked-by: Stefani Seibold Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfifo.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index ece0b1c33816..e117b1aee69c 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -86,7 +86,8 @@ union { \ */ #define INIT_KFIFO(name) \ name = __kfifo_initializer(sizeof(name##kfifo_buffer) - \ - sizeof(struct kfifo), name##kfifo_buffer) + sizeof(struct kfifo), \ + name##kfifo_buffer + sizeof(struct kfifo)) /** * DEFINE_KFIFO - macro to define and initialize a kfifo -- cgit v1.2.2 From 55ab3a1ff843e3f0e24d2da44e71bffa5d853010 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 6 Apr 2010 14:34:58 -0700 Subject: raw: fsync method is now required Commit 148f948ba877f4d3cdef036b1ff6d9f68986706a (vfs: Introduce new helpers for syncing after writing to O_SYNC file or IS_SYNC inode) broke the raw driver. We now call through generic_file_aio_write -> generic_write_sync -> vfs_fsync_range. vfs_fsync_range has: if (!fop || !fop->fsync) { ret = -EINVAL; goto out; } But drivers/char/raw.c doesn't set an fsync method. We have two options: fix it or remove the raw driver completely. I'm happy to do either, the fact this has been broken for so long suggests it is rarely used. The patch below adds an fsync method to the raw driver. My knowledge of the block layer is pretty sketchy so this could do with a once over. If we instead decide to remove the raw driver, this patch might still be useful as a backport to 2.6.33 and 2.6.32. Signed-off-by: Anton Blanchard Reviewed-by: Jan Kara Cc: Christoph Hellwig Cc: Alexander Viro Cc: Jens Axboe Reviewed-by: Jeff Moyer Tested-by: Jeff Moyer Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 10b8dedcd18b..5d9c7e27c5a4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2212,6 +2212,7 @@ extern int generic_segment_checks(const struct iovec *iov, /* fs/block_dev.c */ extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos); +extern int block_fsync(struct file *filp, struct dentry *dentry, int datasync); /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, -- cgit v1.2.2 From b1dd3b2843b3b73b7fc2ee47d96310cd1c051371 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 6 Apr 2010 14:35:00 -0700 Subject: vfs: rename block_fsync() to blkdev_fsync() Requested by hch, for consistency now it is exported. Cc: Alexander Viro Cc: Anton Blanchard Cc: Christoph Hellwig Cc: Jan Kara Cc: Jeff Moyer Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5d9c7e27c5a4..39d57bc6cc71 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2212,7 +2212,7 @@ extern int generic_segment_checks(const struct iovec *iov, /* fs/block_dev.c */ extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos); -extern int block_fsync(struct file *filp, struct dentry *dentry, int datasync); +extern int blkdev_fsync(struct file *filp, struct dentry *dentry, int datasync); /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, -- cgit v1.2.2 From bb1dc0bacb8ddd7ba6a5906c678a5a5a110cf695 Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Tue, 6 Apr 2010 14:35:02 -0700 Subject: kernel.h: fix wrong usage of __ratelimit() When __ratelimit() returns 1 this means that we can go ahead. Signed-off-by: Yong Zhang Cc: Ingo Molnar Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7f0707463360..9365227dbaf6 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -426,7 +426,7 @@ static inline char *pack_hex_byte(char *buf, u8 byte) .burst = DEFAULT_RATELIMIT_BURST, \ }; \ \ - if (!__ratelimit(&_rs)) \ + if (__ratelimit(&_rs)) \ printk(fmt, ##__VA_ARGS__); \ }) #else -- cgit v1.2.2 From 116354d177ba2da37e91cf884e3d11e67f825efd Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Tue, 6 Apr 2010 14:35:04 -0700 Subject: pagemap: fix pfn calculation for hugepage When we look into pagemap using page-types with option -p, the value of pfn for hugepages looks wrong (see below.) This is because pte was evaluated only once for one vma although it should be updated for each hugepage. This patch fixes it. $ page-types -p 3277 -Nl -b huge voffset offset len flags 7f21e8a00 11e400 1 ___U___________H_G________________ 7f21e8a01 11e401 1ff ________________TG________________ ^^^ 7f21e8c00 11e400 1 ___U___________H_G________________ 7f21e8c01 11e401 1ff ________________TG________________ ^^^ One hugepage contains 1 head page and 511 tail pages in x86_64 and each two lines represent each hugepage. Voffset and offset mean virtual address and physical address in the page unit, respectively. The different hugepages should not have the same offset value. With this patch applied: $ page-types -p 3386 -Nl -b huge voffset offset len flags 7fec7a600 112c00 1 ___UD__________H_G________________ 7fec7a601 112c01 1ff ________________TG________________ ^^^ 7fec7a800 113200 1 ___UD__________H_G________________ 7fec7a801 113201 1ff ________________TG________________ ^^^ OK More info: - This patch modifies walk_page_range()'s hugepage walker. But the change only affects pagemap_read(), which is the only caller of hugepage callback. - Without this patch, hugetlb_entry() callback is called per vma, that doesn't match the natural expectation from its name. - With this patch, hugetlb_entry() is called per hugepte entry and the callback can become much simpler. Signed-off-by: Naoya Horiguchi Signed-off-by: KAMEZAWA Hiroyuki Acked-by: Matt Mackall Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e70f21beb4b4..462acaf36f3a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -783,8 +783,8 @@ struct mm_walk { int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *); int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *); int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *); - int (*hugetlb_entry)(pte_t *, unsigned long, unsigned long, - struct mm_walk *); + int (*hugetlb_entry)(pte_t *, unsigned long, + unsigned long, unsigned long, struct mm_walk *); struct mm_struct *mm; void *private; }; -- cgit v1.2.2 From 8725d5416213a145ccc9c236dbd26830ba409e00 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 6 Apr 2010 14:35:05 -0700 Subject: memcg: fix race in file_mapped accounting Presently, memcg's FILE_MAPPED accounting has following race with move_account (happens at rmdir()). increment page->mapcount (rmap.c) mem_cgroup_update_file_mapped() move_account() lock_page_cgroup() check page_mapped() if page_mapped(page)>1 { FILE_MAPPED -1 from old memcg FILE_MAPPED +1 to old memcg } ..... overwrite pc->mem_cgroup unlock_page_cgroup() lock_page_cgroup() FILE_MAPPED + 1 to pc->mem_cgroup unlock_page_cgroup() Then, old memcg (-1 file mapped) new memcg (+2 file mapped) This happens because move_account see page_mapped() which is not guarded by lock_page_cgroup(). This patch adds FILE_MAPPED flag to page_cgroup and move account information based on it. Now, all checks are synchronous with lock_page_cgroup(). Signed-off-by: KAMEZAWA Hiroyuki Reviewed-by: Balbir Singh Reviewed-by: Daisuke Nishimura Cc: Andrea Righi Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_cgroup.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index 30b08136fdf3..aef22ae2af47 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -39,6 +39,7 @@ enum { PCG_CACHE, /* charged as cache */ PCG_USED, /* this object is in use. */ PCG_ACCT_LRU, /* page has been accounted for */ + PCG_FILE_MAPPED, /* page is accounted as "mapped" */ }; #define TESTPCGFLAG(uname, lname) \ @@ -73,6 +74,11 @@ CLEARPCGFLAG(AcctLRU, ACCT_LRU) TESTPCGFLAG(AcctLRU, ACCT_LRU) TESTCLEARPCGFLAG(AcctLRU, ACCT_LRU) + +SETPCGFLAG(FileMapped, FILE_MAPPED) +CLEARPCGFLAG(FileMapped, FILE_MAPPED) +TESTPCGFLAG(FileMapped, FILE_MAPPED) + static inline int page_cgroup_nid(struct page_cgroup *pc) { return page_to_nid(pc->page); -- cgit v1.2.2 From b7a413015d2986edf020fba765c906cc9cbcbfc9 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 31 Mar 2010 21:56:42 +0300 Subject: virtio: disable multiport console support. Move MULTIPORT feature and related config changes out of exported headers, and disable the feature at runtime. At this point, it seems less risky to keep code around until we can enable it than rip it out completely. Signed-off-by: Michael S. Tsirkin Signed-off-by: Rusty Russell --- include/linux/virtio_console.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_console.h b/include/linux/virtio_console.h index ae4f039515b4..92228a8fbcbc 100644 --- a/include/linux/virtio_console.h +++ b/include/linux/virtio_console.h @@ -12,37 +12,14 @@ /* Feature bits */ #define VIRTIO_CONSOLE_F_SIZE 0 /* Does host provide console size? */ -#define VIRTIO_CONSOLE_F_MULTIPORT 1 /* Does host provide multiple ports? */ struct virtio_console_config { /* colums of the screens */ __u16 cols; /* rows of the screens */ __u16 rows; - /* max. number of ports this device can hold */ - __u32 max_nr_ports; - /* number of ports added so far */ - __u32 nr_ports; } __attribute__((packed)); -/* - * A message that's passed between the Host and the Guest for a - * particular port. - */ -struct virtio_console_control { - __u32 id; /* Port number */ - __u16 event; /* The kind of control event (see below) */ - __u16 value; /* Extra information for the key */ -}; - -/* Some events for control messages */ -#define VIRTIO_CONSOLE_PORT_READY 0 -#define VIRTIO_CONSOLE_CONSOLE_PORT 1 -#define VIRTIO_CONSOLE_RESIZE 2 -#define VIRTIO_CONSOLE_PORT_OPEN 3 -#define VIRTIO_CONSOLE_PORT_NAME 4 -#define VIRTIO_CONSOLE_PORT_REMOVE 5 - #ifdef __KERNEL__ int __init virtio_cons_early_init(int (*put_chars)(u32, const char *, int)); #endif /* __KERNEL__ */ -- cgit v1.2.2 From 45c4d015a92f72ec47acd0c7557abdc0c8a6499d Mon Sep 17 00:00:00 2001 From: Mark Lord Date: Wed, 7 Apr 2010 13:52:08 -0400 Subject: libata: Fix accesses at LBA28 boundary (old bug, but nasty) (v2) Most drives from Seagate, Hitachi, and possibly other brands, do not allow LBA28 access to sector number 0x0fffffff (2^28 - 1). So instead use LBA48 for such accesses. This bug could bite a lot of systems, especially when the user has taken care to align partitions to 4KB boundaries. On misaligned systems, it is less likely to be encountered, since a 4KB read would end at 0x10000000 rather than at 0x0fffffff. Signed-off-by: Mark Lord Signed-off-by: Jeff Garzik --- include/linux/ata.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index b4c85e2adef5..700c5b9b3583 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -1025,8 +1025,8 @@ static inline int ata_ok(u8 status) static inline int lba_28_ok(u64 block, u32 n_block) { - /* check the ending block number */ - return ((block + n_block) < ((u64)1 << 28)) && (n_block <= 256); + /* check the ending block number: must be LESS THAN 0x0fffffff */ + return ((block + n_block) < ((1 << 28) - 1)) && (n_block <= 256); } static inline int lba_48_ok(u64 block, u32 n_block) -- cgit v1.2.2 From fc1c183353a113c71675fecd0485e5aa0fe68d72 Mon Sep 17 00:00:00 2001 From: Pekka Enberg Date: Wed, 7 Apr 2010 19:23:40 +0300 Subject: slab: Generify kernel pointer validation As suggested by Linus, introduce a kern_ptr_validate() helper that does some sanity checks to make sure a pointer is a valid kernel pointer. This is a preparational step for fixing SLUB kmem_ptr_validate(). Cc: Andrew Morton Cc: Christoph Lameter Cc: David Rientjes Cc: Ingo Molnar Cc: Matt Mackall Cc: Nick Piggin Signed-off-by: Pekka Enberg Signed-off-by: Linus Torvalds --- include/linux/slab.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 488446289cab..49d1247cd6d9 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -106,6 +106,7 @@ int kmem_cache_shrink(struct kmem_cache *); void kmem_cache_free(struct kmem_cache *, void *); unsigned int kmem_cache_size(struct kmem_cache *); const char *kmem_cache_name(struct kmem_cache *); +int kern_ptr_validate(const void *ptr, unsigned long size); int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr); /* -- cgit v1.2.2 From ce82653d6cfcc95ba88c25908664878459fb1b8d Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 6 Apr 2010 22:36:20 +0100 Subject: radix_tree_tag_get() is not as safe as the docs make out [ver #2] radix_tree_tag_get() is not safe to use concurrently with radix_tree_tag_set() or radix_tree_tag_clear(). The problem is that the double tag_get() in radix_tree_tag_get(): if (!tag_get(node, tag, offset)) saw_unset_tag = 1; if (height == 1) { int ret = tag_get(node, tag, offset); may see the value change due to the action of set/clear. RCU is no protection against this as no pointers are being changed, no nodes are being replaced according to a COW protocol - set/clear alter the node directly. The documentation in linux/radix-tree.h, however, says that radix_tree_tag_get() is an exception to the rule that "any function modifying the tree or tags (...) must exclude other modifications, and exclude any functions reading the tree". The problem is that the next statement in radix_tree_tag_get() checks that the tag doesn't vary over time: BUG_ON(ret && saw_unset_tag); This has been seen happening in FS-Cache: https://www.redhat.com/archives/linux-cachefs/2010-April/msg00013.html To this end, remove the BUG_ON() from radix_tree_tag_get() and note in various comments that the value of the tag may change whilst the RCU read lock is held, and thus that the return value of radix_tree_tag_get() may not be relied upon unless radix_tree_tag_set/clear() and radix_tree_delete() are excluded from running concurrently with it. Reported-by: Romain DEGEZ Signed-off-by: David Howells Acked-by: Nick Piggin Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index c5da74918096..55ca73cf25e5 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -121,6 +121,13 @@ do { \ * (Note, rcu_assign_pointer and rcu_dereference are not needed to control * access to data items when inserting into or looking up from the radix tree) * + * Note that the value returned by radix_tree_tag_get() may not be relied upon + * if only the RCU read lock is held. Functions to set/clear tags and to + * delete nodes running concurrently with it may affect its result such that + * two consecutive reads in the same locked section may return different + * values. If reliability is required, modification functions must also be + * excluded from concurrency. + * * radix_tree_tagged is able to be called without locking or RCU. */ -- cgit v1.2.2