From 778b032d96909690c19d84f8d17c13be65ed6f8e Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 29 May 2012 21:30:08 +0200 Subject: uprobes: Kill uprobes_srcu/uprobe_srcu_id Kill the no longer needed uprobes_srcu/uprobe_srcu_id code. It doesn't really work anyway. synchronize_srcu() can only synchronize with the code "inside" the srcu_read_lock/srcu_read_unlock section, while uprobe_pre_sstep_notifier() does srcu_read_lock() _after_ we already hit the breakpoint. I guess this probably works "in practice". synchronize_srcu() is slow and it implies synchronize_sched(), and the probed task enters the non- preemptible section at the start of exception handler. Still this is not right at least in theory, and task->uprobe_srcu_id blows task_struct. Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Cc: Ananth N Mavinakayanahalli Cc: Anton Arapov Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120529193008.GG8057@redhat.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6029d8c54476..6bd19655c1a7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1569,7 +1569,6 @@ struct task_struct { #endif #ifdef CONFIG_UPROBES struct uprobe_task *utask; - int uprobe_srcu_id; #endif }; -- cgit v1.2.3 From cba6d0d64ee53772b285d0c0c288deefbeaf7775 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 2 Jul 2012 07:08:42 -0700 Subject: Revert "rcu: Move PREEMPT_RCU preemption to switch_to() invocation" This reverts commit 616c310e83b872024271c915c1b9ab505b9efad9. (Move PREEMPT_RCU preemption to switch_to() invocation). Testing by Sasha Levin showed that this can result in deadlock due to invoking the scheduler when one of the runqueue locks is held. Because this commit was simply a performance optimization, revert it. Reported-by: Sasha Levin Signed-off-by: Paul E. McKenney Tested-by: Sasha Levin --- include/linux/sched.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4059c0f33f07..06a4c5f4f55c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1871,22 +1871,12 @@ static inline void rcu_copy_process(struct task_struct *p) INIT_LIST_HEAD(&p->rcu_node_entry); } -static inline void rcu_switch_from(struct task_struct *prev) -{ - if (prev->rcu_read_lock_nesting != 0) - rcu_preempt_note_context_switch(); -} - #else static inline void rcu_copy_process(struct task_struct *p) { } -static inline void rcu_switch_from(struct task_struct *prev) -{ -} - #endif #ifdef CONFIG_SMP -- cgit v1.2.3 From 5167e8d5417bf5c322a703d2927daec727ea40dd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Jun 2012 15:52:09 +0200 Subject: sched/nohz: Rewrite and fix load-avg computation -- again Thanks to Charles Wang for spotting the defects in the current code: - If we go idle during the sample window -- after sampling, we get a negative bias because we can negate our own sample. - If we wake up during the sample window we get a positive bias because we push the sample to a known active period. So rewrite the entire nohz load-avg muck once again, now adding copious documentation to the code. Reported-and-tested-by: Doug Smythies Reported-and-tested-by: Charles Wang Signed-off-by: Peter Zijlstra Cc: Linus Torvalds Cc: Andrew Morton Cc: stable@kernel.org Link: http://lkml.kernel.org/r/1340373782.18025.74.camel@twins [ minor edits ] Signed-off-by: Ingo Molnar --- include/linux/sched.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4059c0f33f07..20cb7497c59c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1909,6 +1909,14 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, } #endif +#ifdef CONFIG_NO_HZ +void calc_load_enter_idle(void); +void calc_load_exit_idle(void); +#else +static inline void calc_load_enter_idle(void) { } +static inline void calc_load_exit_idle(void) { } +#endif /* CONFIG_NO_HZ */ + #ifndef CONFIG_CPUMASK_OFFSTACK static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) { -- cgit v1.2.3 From 158e1645e07f3e9f7e4962d7a0997f5c3b98311b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Jun 2012 09:24:13 +0400 Subject: trim task_work: get rid of hlist layout based on Oleg's suggestion; single-linked list, task->task_works points to the last element, forward pointer from said last element points to head. I'd still prefer much more regular scheme with two pointers in task_work, but... Signed-off-by: Al Viro --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4059c0f33f07..b9216ebc2789 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1405,7 +1405,7 @@ struct task_struct { int (*notifier)(void *priv); void *notifier_data; sigset_t *notifier_mask; - struct hlist_head task_works; + void *task_works; struct audit_context *audit_context; #ifdef CONFIG_AUDITSYSCALL -- cgit v1.2.3 From 67d1214551e800f9fe7dc7c47a346d2df0fafed5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 27 Jun 2012 11:07:19 +0400 Subject: merge task_work and rcu_head, get rid of separate allocation for keyring case task_work and rcu_head are identical now; merge them (calling the result struct callback_head, rcu_head #define'd to it), kill separate allocation in security/keys since we can just use cred->rcu now. Signed-off-by: Al Viro --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index b9216ebc2789..af3555cc760f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1405,7 +1405,7 @@ struct task_struct { int (*notifier)(void *priv); void *notifier_data; sigset_t *notifier_mask; - void *task_works; + struct callback_head *task_works; struct audit_context *audit_context; #ifdef CONFIG_AUDITSYSCALL -- cgit v1.2.3 From 6120d3dbb1220792ebea88cd475e1ec8f8620a93 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 24 Jun 2012 10:03:05 +0400 Subject: get rid of ->scm_work_list recursion in __scm_destroy() will be cut by delaying final fput() Signed-off-by: Al Viro --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index af3555cc760f..598ba2da7865 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1546,7 +1546,6 @@ struct task_struct { unsigned long timer_slack_ns; unsigned long default_timer_slack_ns; - struct list_head *scm_work_list; #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack */ int curr_ret_stack; -- cgit v1.2.3 From 970e178985cadbca660feb02f4d2ee3a09f7fdda Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Tue, 12 Jun 2012 05:18:32 +0200 Subject: sched: Improve scalability via 'CPU buddies', which withstand random perturbations Traversing an entire package is not only expensive, it also leads to tasks bouncing all over a partially idle and possible quite large package. Fix that up by assigning a 'buddy' CPU to try to motivate. Each buddy may try to motivate that one other CPU, if it's busy, tough, it may then try its SMT sibling, but that's all this optimization is allowed to cost. Sibling cache buddies are cross-wired to prevent bouncing. 4 socket 40 core + SMT Westmere box, single 30 sec tbench runs, higher is better: clients 1 2 4 8 16 32 64 128 .......................................................................... pre 30 41 118 645 3769 6214 12233 14312 post 299 603 1211 2418 4697 6847 11606 14557 A nice increase in performance. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra Cc: Linus Torvalds Cc: Andrew Morton Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1339471112.7352.32.camel@marge.simpson.net Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4a1f493e0fef..bc9952991710 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -949,6 +949,7 @@ struct sched_domain { unsigned int smt_gain; int flags; /* See SD_* */ int level; + int idle_buddy; /* cpu assigned to select_idle_sibling() */ /* Runtime fields. */ unsigned long last_balance; /* init to jiffies. units in jiffies */ -- cgit v1.2.3 From 8323f26ce3425460769605a6aece7a174edaa7d1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 22 Jun 2012 13:36:05 +0200 Subject: sched: Fix race in task_group() Stefan reported a crash on a kernel before a3e5d1091c1 ("sched: Don't call task_group() too many times in set_task_rq()"), he found the reason to be that the multiple task_group() invocations in set_task_rq() returned different values. Looking at all that I found a lack of serialization and plain wrong comments. The below tries to fix it using an extra pointer which is updated under the appropriate scheduler locks. Its not pretty, but I can't really see another way given how all the cgroup stuff works. Reported-and-tested-by: Stefan Bader Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1340364965.18025.71.camel@twins Signed-off-by: Ingo Molnar --- include/linux/sched.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index bc9952991710..fd9436a3a545 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1245,6 +1245,9 @@ struct task_struct { const struct sched_class *sched_class; struct sched_entity se; struct sched_rt_entity rt; +#ifdef CONFIG_CGROUP_SCHED + struct task_group *sched_task_group; +#endif #ifdef CONFIG_PREEMPT_NOTIFIERS /* list of struct preempt_notifier: */ @@ -2724,7 +2727,7 @@ extern int sched_group_set_rt_period(struct task_group *tg, extern long sched_group_rt_period(struct task_group *tg); extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk); #endif -#endif +#endif /* CONFIG_CGROUP_SCHED */ extern int task_can_switch_user(struct user_struct *up, struct task_struct *tsk); -- cgit v1.2.3 From 54b501992dd2a839e94e76aa392c392b55080ce8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 30 Jul 2012 14:39:18 -0700 Subject: coredump: warn about unsafe suid_dumpable / core_pattern combo When suid_dumpable=2, detect unsafe core_pattern settings and warn when they are seen. Signed-off-by: Kees Cook Suggested-by: Andrew Morton Cc: Alexander Viro Cc: Alan Cox Cc: "Eric W. Biederman" Cc: Doug Ledford Cc: Serge Hallyn Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index a721cef7e2d4..1e26a5e45aa6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -406,6 +406,11 @@ static inline void arch_pick_mmap_layout(struct mm_struct *mm) {} extern void set_dumpable(struct mm_struct *mm, int value); extern int get_dumpable(struct mm_struct *mm); +/* get/set_dumpable() values */ +#define SUID_DUMPABLE_DISABLED 0 +#define SUID_DUMPABLE_ENABLED 1 +#define SUID_DUMPABLE_SAFE 2 + /* mm flags */ /* dumpable bits */ #define MMF_DUMPABLE 0 /* core dump is permitted */ -- cgit v1.2.3 From 45226e944ce071d0231949f2fea90969437cd2dc Mon Sep 17 00:00:00 2001 From: Sameer Nanda Date: Mon, 30 Jul 2012 14:40:00 -0700 Subject: NMI watchdog: fix for lockup detector breakage on resume On the suspend/resume path the boot CPU does not go though an offline->online transition. This breaks the NMI detector post-resume since it depends on PMU state that is lost when the system gets suspended. Fix this by forcing a CPU offline->online transition for the lockup detector on the boot CPU during resume. To provide more context, we enable NMI watchdog on Chrome OS. We have seen several reports of systems freezing up completely which indicated that the NMI watchdog was not firing for some reason. Debugging further, we found a simple way of repro'ing system freezes -- issuing the command 'tasket 1 sh -c "echo nmilockup > /proc/breakme"' after the system has been suspended/resumed one or more times. With this patch in place, the system freeze result in panics, as expected. These panics provide a nice stack trace for us to debug the actual issue causing the freeze. [akpm@linux-foundation.org: fiddle with code comment] [akpm@linux-foundation.org: make lockup_detector_bootcpu_resume() conditional on CONFIG_SUSPEND] [akpm@linux-foundation.org: fix section errors] Signed-off-by: Sameer Nanda Cc: Ingo Molnar Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Don Zickus Cc: Mandeep Singh Baines Cc: Srivatsa S. Bhat Cc: Anshuman Khandual Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 1e26a5e45aa6..68dcffaa62a0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -334,6 +334,14 @@ static inline void lockup_detector_init(void) } #endif +#if defined(CONFIG_LOCKUP_DETECTOR) && defined(CONFIG_SUSPEND) +void lockup_detector_bootcpu_resume(void); +#else +static inline void lockup_detector_bootcpu_resume(void) +{ +} +#endif + #ifdef CONFIG_DETECT_HUNG_TASK extern unsigned int sysctl_hung_task_panic; extern unsigned long sysctl_hung_task_check_count; -- cgit v1.2.3 From c255a458055e459f65eb7b7f51dc5dbdd0caf1d8 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 31 Jul 2012 16:43:02 -0700 Subject: memcg: rename config variables Sanity: CONFIG_CGROUP_MEM_RES_CTLR -> CONFIG_MEMCG CONFIG_CGROUP_MEM_RES_CTLR_SWAP -> CONFIG_MEMCG_SWAP CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED -> CONFIG_MEMCG_SWAP_ENABLED CONFIG_CGROUP_MEM_RES_CTLR_KMEM -> CONFIG_MEMCG_KMEM [mhocko@suse.cz: fix missed bits] Cc: Glauber Costa Acked-by: Michal Hocko Cc: Johannes Weiner Cc: KAMEZAWA Hiroyuki Cc: Hugh Dickins Cc: Tejun Heo Cc: Aneesh Kumar K.V Cc: David Rientjes Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 68dcffaa62a0..865725adb9d3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1584,7 +1584,7 @@ struct task_struct { /* bitmask and counter of trace recursion */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ -#ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */ +#ifdef CONFIG_MEMCG /* memcg uses this to do batch job */ struct memcg_batch_info { int do_batch; /* incremented when batch uncharge started */ struct mem_cgroup *memcg; /* target memcg of uncharge */ -- cgit v1.2.3 From 907aed48f65efeecf91575397e3d79335d93a466 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 31 Jul 2012 16:44:07 -0700 Subject: mm: allow PF_MEMALLOC from softirq context This is needed to allow network softirq packet processing to make use of PF_MEMALLOC. Currently softirq context cannot use PF_MEMALLOC due to it not being associated with a task, and therefore not having task flags to fiddle with - thus the gfp to alloc flag mapping ignores the task flags when in interrupts (hard or soft) context. Allowing softirqs to make use of PF_MEMALLOC therefore requires some trickery. This patch borrows the task flags from whatever process happens to be preempted by the softirq. It then modifies the gfp to alloc flags mapping to not exclude task flags in softirq context, and modify the softirq code to save, clear and restore the PF_MEMALLOC flag. The save and clear, ensures the preempted task's PF_MEMALLOC flag doesn't leak into the softirq. The restore ensures a softirq's PF_MEMALLOC flag cannot leak back into the preempted process. This should be safe due to the following reasons Softirqs can run on multiple CPUs sure but the same task should not be executing the same softirq code. Neither should the softirq handler be preempted by any other softirq handler so the flags should not leak to an unrelated softirq. Softirqs re-enable hardware interrupts in __do_softirq() so can be preempted by hardware interrupts so PF_MEMALLOC is inherited by the hard IRQ. However, this is similar to a process in reclaim being preempted by a hardirq. While PF_MEMALLOC is set, gfp_to_alloc_flags() distinguishes between hard and soft irqs and avoids giving a hardirq the ALLOC_NO_WATERMARKS flag. If the softirq is deferred to ksoftirq then its flags may be used instead of a normal tasks but as the softirq cannot be preempted, the PF_MEMALLOC flag does not leak to other code by accident. [davem@davemloft.net: Document why PF_MEMALLOC is safe] Signed-off-by: Peter Zijlstra Signed-off-by: Mel Gorman Cc: David Miller Cc: Neil Brown Cc: Mike Christie Cc: Eric B Munson Cc: Eric Dumazet Cc: Sebastian Andrzej Siewior Cc: Mel Gorman Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 865725adb9d3..c147e7024f11 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1894,6 +1894,13 @@ static inline void rcu_copy_process(struct task_struct *p) #endif +static inline void tsk_restore_flags(struct task_struct *task, + unsigned long orig_flags, unsigned long flags) +{ + task->flags &= ~flags; + task->flags |= orig_flags & flags; +} + #ifdef CONFIG_SMP extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); -- cgit v1.2.3 From 300d3739e873d50d4c6e3656f89007a217fb1d29 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 7 Aug 2012 13:50:22 +0200 Subject: Revert "NMI watchdog: fix for lockup detector breakage on resume" Revert commit 45226e9 (NMI watchdog: fix for lockup detector breakage on resume) which breaks resume from system suspend on my SH7372 Mackerel board (by causing a NULL pointer dereference to happen) and is generally wrong, because it abuses the CPU hotplug functionality in a shamelessly blatant way. The original issue should be addressed through appropriate syscore resume callback instead. Signed-off-by: Rafael J. Wysocki --- include/linux/sched.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index c147e7024f11..b8c86648a2f9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -334,14 +334,6 @@ static inline void lockup_detector_init(void) } #endif -#if defined(CONFIG_LOCKUP_DETECTOR) && defined(CONFIG_SUSPEND) -void lockup_detector_bootcpu_resume(void); -#else -static inline void lockup_detector_bootcpu_resume(void) -{ -} -#endif - #ifdef CONFIG_DETECT_HUNG_TASK extern unsigned int sysctl_hung_task_panic; extern unsigned long sysctl_hung_task_check_count; -- cgit v1.2.3