From d6ad3e286d2c075a60b9f11075a2c55aeeeca2ad Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Wed, 27 Jan 2010 16:25:22 -0600 Subject: softlockup: Add sched_clock_tick() to avoid kernel warning on kgdb resume When CONFIG_HAVE_UNSTABLE_SCHED_CLOCK is set, sched_clock() gets the time from hardware such as the TSC on x86. In this configuration kgdb will report a softlock warning message on resuming or detaching from a debug session. Sequence of events in the problem case: 1) "cpu sched clock" and "hardware time" are at 100 sec prior to a call to kgdb_handle_exception() 2) Debugger waits in kgdb_handle_exception() for 80 sec and on exit the following is called ... touch_softlockup_watchdog() --> __raw_get_cpu_var(touch_timestamp) = 0; 3) "cpu sched clock" = 100s (it was not updated, because the interrupt was disabled in kgdb) but the "hardware time" = 180 sec 4) The first timer interrupt after resuming from kgdb_handle_exception updates the watchdog from the "cpu sched clock" update_process_times() { ... run_local_timers() --> softlockup_tick() --> check (touch_timestamp == 0) (it is "YES" here, we have set "touch_timestamp = 0" at kgdb) --> __touch_softlockup_watchdog() ***(A)--> reset "touch_timestamp" to "get_timestamp()" (Here, the "touch_timestamp" will still be set to 100s.) ... scheduler_tick() ***(B)--> sched_clock_tick() (update "cpu sched clock" to "hardware time" = 180s) ... } 5) The Second timer interrupt handler appears to have a large jump and trips the softlockup warning. update_process_times() { ... run_local_timers() --> softlockup_tick() --> "cpu sched clock" - "touch_timestamp" = 180s-100s > 60s --> printk "soft lockup error messages" ... } note: ***(A) reset "touch_timestamp" to "get_timestamp(this_cpu)" Why is "touch_timestamp" 100 sec, instead of 180 sec? When CONFIG_HAVE_UNSTABLE_SCHED_CLOCK is set, the call trace of get_timestamp() is: get_timestamp(this_cpu) -->cpu_clock(this_cpu) -->sched_clock_cpu(this_cpu) -->__update_sched_clock(sched_clock_data, now) The __update_sched_clock() function uses the GTOD tick value to create a window to normalize the "now" values. So if "now" value is too big for sched_clock_data, it will be ignored. The fix is to invoke sched_clock_tick() to update "cpu sched clock" in order to recover from this state. This is done by introducing the function touch_softlockup_watchdog_sync(). This allows kgdb to request that the sched clock is updated when the watchdog thread runs the first time after a resume from kgdb. [yong.zhang0@gmail.com: Use per cpu instead of an array] Signed-off-by: Jason Wessel Signed-off-by: Dongdong Deng Cc: kgdb-bugreport@lists.sourceforge.net Cc: peterz@infradead.org LKML-Reference: <1264631124-4837-2-git-send-email-jason.wessel@windriver.com> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6f7bba93929..89232151a9d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -310,6 +310,7 @@ extern void sched_show_task(struct task_struct *p); #ifdef CONFIG_DETECT_SOFTLOCKUP extern void softlockup_tick(void); extern void touch_softlockup_watchdog(void); +extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write, void __user *buffer, @@ -323,6 +324,9 @@ static inline void softlockup_tick(void) static inline void touch_softlockup_watchdog(void) { } +static inline void touch_softlockup_watchdog_sync(void) +{ +} static inline void touch_all_softlockup_watchdogs(void) { } -- cgit v1.2.3 From f98bfbd78c37c5946cc53089da32a5f741efdeb7 Mon Sep 17 00:00:00 2001 From: Evgeniy Polyakov Date: Tue, 2 Feb 2010 15:58:48 -0800 Subject: connector: Delete buggy notification code. On Tue, Feb 02, 2010 at 02:57:14PM -0800, Greg KH (gregkh@suse.de) wrote: > > There are at least two ways to fix it: using a big cannon and a small > > one. The former way is to disable notification registration, since it is > > not used by anyone at all. Second way is to check whether calling > > process is root and its destination group is -1 (kind of priveledged > > one) before command is dispatched to workqueue. > > Well if no one is using it, removing it makes the most sense, right? > > No objection from me, care to make up a patch either way for this? Getting it is not used, let's drop support for notifications about (un)registered events from connector. Another option was to check credentials on receiving, but we can always restore it without bugs if needed, but genetlink has a wider code base and none complained, that userspace can not get notification when some other clients were (un)registered. Kudos for Sebastian Krahmer , who found a bug in the code. Signed-off-by: Evgeniy Polyakov Acked-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- include/linux/connector.h | 32 -------------------------------- 1 file changed, 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index 72ba63eb83c..3a779ffba60 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -24,9 +24,6 @@ #include -#define CN_IDX_CONNECTOR 0xffffffff -#define CN_VAL_CONNECTOR 0xffffffff - /* * Process Events connector unique ids -- used for message routing */ @@ -75,30 +72,6 @@ struct cn_msg { __u8 data[0]; }; -/* - * Notify structure - requests notification about - * registering/unregistering idx/val in range [first, first+range]. - */ -struct cn_notify_req { - __u32 first; - __u32 range; -}; - -/* - * Main notification control message - * *_notify_num - number of appropriate cn_notify_req structures after - * this struct. - * group - notification receiver's idx. - * len - total length of the attached data. - */ -struct cn_ctl_msg { - __u32 idx_notify_num; - __u32 val_notify_num; - __u32 group; - __u32 len; - __u8 data[0]; -}; - #ifdef __KERNEL__ #include @@ -151,11 +124,6 @@ struct cn_callback_entry { u32 seq, group; }; -struct cn_ctl_entry { - struct list_head notify_entry; - struct cn_ctl_msg *msg; -}; - struct cn_dev { struct cb_id id; -- cgit v1.2.3 From cd757645fbdc34a8343c04bb0e74e06fccc2cb10 Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Sat, 30 Jan 2010 10:25:18 +0530 Subject: perf: Make bp_len type to u64 generic across the arch Change 'bp_len' type to __u64 to make it work across archs as the s390 architecture watch point length can be upto 2^64. reference: http://lkml.org/lkml/2010/1/25/212 This is an ABI change that is not backward compatible with the previous hardware breakpoint info layout integrated in this development cycle, a rebuilt of perf tools is necessary for versions based on 2.6.33-rc1 - 2.6.33-rc6 to work with a kernel based on this patch. Signed-off-by: Mahesh Salgaonkar Acked-by: Peter Zijlstra Cc: Ananth N Mavinakayanahalli Cc: "K. Prasad" Cc: Maneesh Soni Cc: Heiko Carstens Cc: Martin LKML-Reference: <20100130045518.GA20776@in.ibm.com> Signed-off-by: Frederic Weisbecker --- include/linux/hw_breakpoint.h | 2 +- include/linux/perf_event.h | 6 ++---- 2 files changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h index 070ba062173..5977b724f7c 100644 --- a/include/linux/hw_breakpoint.h +++ b/include/linux/hw_breakpoint.h @@ -44,7 +44,7 @@ static inline int hw_breakpoint_type(struct perf_event *bp) return bp->attr.bp_type; } -static inline int hw_breakpoint_len(struct perf_event *bp) +static inline unsigned long hw_breakpoint_len(struct perf_event *bp) { return bp->attr.bp_len; } diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 8fa71874113..a177698d95e 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -211,11 +211,9 @@ struct perf_event_attr { __u32 wakeup_watermark; /* bytes before wakeup */ }; - __u32 __reserved_2; - - __u64 bp_addr; __u32 bp_type; - __u32 bp_len; + __u64 bp_addr; + __u64 bp_len; }; /* -- cgit v1.2.3 From f7acede65d6b65919aee5b6a360a17cedb11f2f7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 Jan 2010 13:30:11 +0100 Subject: libata: fix ata_id_logical_per_physical_sectors The value we get from the low byte of the ATA_ID_SECTOR_SIZE word is not not a plain multiple, but the log of it, so fix the helper to give the correct answer. Without this we'll get an incorrect minimal I/O size in the block limits VPD page for 4k sector drives. Also change the return value of ata_id_logical_per_physical_sectors to u16 for the unlikely case of very large logical sectors. Signed-off-by: Christoph Hellwig 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 38a6948ce0c..20f31567cce 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -647,9 +647,9 @@ static inline int ata_id_has_large_logical_sectors(const u16 *id) return id[ATA_ID_SECTOR_SIZE] & (1 << 13); } -static inline u8 ata_id_logical_per_physical_sectors(const u16 *id) +static inline u16 ata_id_logical_per_physical_sectors(const u16 *id) { - return id[ATA_ID_SECTOR_SIZE] & 0xf; + return 1 << (id[ATA_ID_SECTOR_SIZE] & 0xf); } static inline int ata_id_has_lba48(const u16 *id) -- cgit v1.2.3 From 2938429501b73f6aeb312236eac7ed0416a07cd5 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Fri, 5 Feb 2010 16:09:11 +1100 Subject: percpu: add __percpu for sparse This is to make the annotation of percpu variables during the next merge window less painfull. Extracted from a patch by Rusty Russell. Signed-off-by: Stephen Rothwell Acked-by: Tejun Heo Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 5be3dab4a69..188fcae10a9 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -15,6 +15,7 @@ # define __acquire(x) __context__(x,1) # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) +# define __percpu __attribute__((noderef, address_space(3))) extern void __chk_user_ptr(const volatile void __user *); extern void __chk_io_ptr(const volatile void __iomem *); #else @@ -32,6 +33,7 @@ extern void __chk_io_ptr(const volatile void __iomem *); # define __acquire(x) (void)0 # define __release(x) (void)0 # define __cond_lock(x,c) (c) +# define __percpu #endif #ifdef __KERNEL__ -- cgit v1.2.3 From 8eb988c70e7709b7bd1a69f0ec53d19ac20dea84 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Wed, 20 Jan 2010 15:35:41 -0500 Subject: fix ima breakage The "Untangling ima mess, part 2 with counters" patch messed up the counters. Based on conversations with Al Viro, this patch streamlines ima_path_check() by removing the counter maintaince. The counters are now updated independently, from measuring the file, in __dentry_open() and alloc_file() by calling ima_counts_get(). ima_path_check() is called from nfsd and do_filp_open(). It also did not measure all files that should have been measured. Reason: ima_path_check() got bogus value passed as mask. [AV: mea culpa] [AV: add missing nfsd bits] Signed-off-by: Mimi Zohar Signed-off-by: Al Viro --- include/linux/ima.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 99dc6d5cf7e..aa55a8f1f5b 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -17,7 +17,7 @@ struct linux_binprm; extern int ima_bprm_check(struct linux_binprm *bprm); extern int ima_inode_alloc(struct inode *inode); extern void ima_inode_free(struct inode *inode); -extern int ima_path_check(struct path *path, int mask); +extern int ima_path_check(struct file *file, int mask); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); extern void ima_counts_get(struct file *file); @@ -38,7 +38,7 @@ static inline void ima_inode_free(struct inode *inode) return; } -static inline int ima_path_check(struct path *path, int mask) +static inline int ima_path_check(struct file *file, int mask) { return 0; } -- cgit v1.2.3 From 9bbb6cad0173e6220f3ac609e26beb48dab3b7cd Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Tue, 26 Jan 2010 17:02:40 -0500 Subject: ima: rename ima_path_check to ima_file_check ima_path_check actually deals with files! call it ima_file_check instead. Signed-off-by: Eric Paris Acked-by: Mimi Zohar Signed-off-by: Al Viro --- include/linux/ima.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index aa55a8f1f5b..975837e7d6c 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -17,7 +17,7 @@ struct linux_binprm; extern int ima_bprm_check(struct linux_binprm *bprm); extern int ima_inode_alloc(struct inode *inode); extern void ima_inode_free(struct inode *inode); -extern int ima_path_check(struct file *file, int mask); +extern int ima_file_check(struct file *file, int mask); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); extern void ima_counts_get(struct file *file); @@ -38,7 +38,7 @@ static inline void ima_inode_free(struct inode *inode) return; } -static inline int ima_path_check(struct file *file, int mask) +static inline int ima_file_check(struct file *file, int mask) { return 0; } -- cgit v1.2.3