From e3818b8dce2a934cd1521dbc4827e5238d8f45d8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 15 Mar 2010 17:03:43 -0700 Subject: [PATCH 1/5] 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 ++++--------------- kernel/rcupdate.c | 23 +++++++++++++++++++++++ 2 files changed, 27 insertions(+), 15 deletions(-) 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? diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index f1125c1a6321..63fe25433980 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -45,6 +45,7 @@ #include #include #include +#include #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key rcu_lock_key; @@ -66,6 +67,28 @@ EXPORT_SYMBOL_GPL(rcu_sched_lock_map); int rcu_scheduler_active __read_mostly; EXPORT_SYMBOL_GPL(rcu_scheduler_active); +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +/** + * rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section? + * + * Check for bottom half being disabled, which covers both the + * CONFIG_PROVE_RCU and not cases. Note that if someone uses + * rcu_read_lock_bh(), but then later enables BH, lockdep (if enabled) + * will show the situation. + * + * Check debug_lockdep_rcu_enabled() to prevent false positives during boot. + */ +int rcu_read_lock_bh_held(void) +{ + if (!debug_lockdep_rcu_enabled()) + return 1; + return in_softirq(); +} +EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); + +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + /* * This function is invoked towards the end of the scheduler's initialization * process. Before this is called, the idle task might contain From 7f5b774275df8c76a959eae7488128b637fcbfc8 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 16 Mar 2010 17:00:29 +0800 Subject: [PATCH 2/5] 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(-) 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); \ From 0cff810f54b3b52075c27f7a7021d5b195264b6c Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 18 Mar 2010 12:25:33 -0700 Subject: [PATCH 3/5] 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(-) 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) From 8c2eb4805d422bdbf60ba00ff233c794d23c3c00 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 19 Mar 2010 10:28:02 +0000 Subject: [PATCH 4/5] softlockup: Stop spurious softlockup messages due to overflow Ensure additions on touch_ts do not overflow. This can occur when the top 32 bits of the TSC reach 0xffffffff causing additions to touch_ts to overflow and this in turn generates spurious softlockup warnings. Signed-off-by: Colin Ian King Cc: Peter Zijlstra Cc: Eric Dumazet Cc: LKML-Reference: <1268994482.1798.6.camel@lenovo> Signed-off-by: Ingo Molnar --- kernel/softlockup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/softlockup.c b/kernel/softlockup.c index 0d4c7898ab80..4b493f67dcb5 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -155,11 +155,11 @@ void softlockup_tick(void) * Wake up the high-prio watchdog task twice per * threshold timespan. */ - if (now > touch_ts + softlockup_thresh/2) + if (time_after(now - softlockup_thresh/2, touch_ts)) wake_up_process(per_cpu(softlockup_watchdog, this_cpu)); /* Warn about unreasonable delays: */ - if (now <= (touch_ts + softlockup_thresh)) + if (time_before_eq(now - softlockup_thresh, touch_ts)) return; per_cpu(softlockup_print_ts, this_cpu) = touch_ts; From c26f91a3df1999ec1b3298372d73f90cbab81106 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Mon, 22 Mar 2010 09:32:26 +0100 Subject: [PATCH 5/5] x86: Remove excessive early_res debug output Commit 08677214e318297 ("x86: Make 64 bit use early_res instead of bootmem before slab") introduced early_res replacement for bootmem, but left code in __free_pages_memory() which dumps all the ranges that are beeing freed, without any additional information, causing some noise in dmesg during bootup. Just remove printing of the ranges, that doesn't provide anything useful anyway. While at it, remove other commented-out KERN_DEBUG messages in the NO_BOOTMEM code as well. Signed-off-by: Jiri Kosina Found-OK-by: Andrew Morton Cc: Johannes Weiner Cc: Yinghai Lu LKML-Reference: Signed-off-by: Ingo Molnar --- mm/bootmem.c | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/mm/bootmem.c b/mm/bootmem.c index d7c791ef0036..9b134460b016 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -180,19 +180,12 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end) end_aligned = end & ~(BITS_PER_LONG - 1); if (end_aligned <= start_aligned) { -#if 1 - printk(KERN_DEBUG " %lx - %lx\n", start, end); -#endif for (i = start; i < end; i++) __free_pages_bootmem(pfn_to_page(i), 0); return; } -#if 1 - printk(KERN_DEBUG " %lx %lx - %lx %lx\n", - start, start_aligned, end_aligned, end); -#endif for (i = start; i < start_aligned; i++) __free_pages_bootmem(pfn_to_page(i), 0); @@ -428,9 +421,6 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, { #ifdef CONFIG_NO_BOOTMEM free_early(physaddr, physaddr + size); -#if 0 - printk(KERN_DEBUG "free %lx %lx\n", physaddr, size); -#endif #else unsigned long start, end; @@ -456,9 +446,6 @@ void __init free_bootmem(unsigned long addr, unsigned long size) { #ifdef CONFIG_NO_BOOTMEM free_early(addr, addr + size); -#if 0 - printk(KERN_DEBUG "free %lx %lx\n", addr, size); -#endif #else unsigned long start, end;