From 4c54005ca438a8b46dd542b497d4f0dc2ca375e8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 14 Jan 2010 16:10:57 -0800 Subject: rcu: 1Q2010 update for RCU documentation Add expedited functions. Review documentation and update obsolete verbiage. Also fix the advice for the RCU CPU-stall kernel configuration parameter, and document RCU CPU-stall warnings. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com 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: <12635142581866-git-send-email-> Signed-off-by: Ingo Molnar --- lib/Kconfig.debug | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'lib/Kconfig.debug') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 25c3ed594c54..6bf97d176326 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -765,9 +765,9 @@ config RCU_CPU_STALL_DETECTOR CPUs are delaying the current grace period, but only when the grace period extends for excessive time periods. - Say Y if you want RCU to perform such checks. + Say N if you want to disable such checks. - Say N if you are unsure. + Say Y if you are unsure. config KPROBES_SANITY_TEST bool "Kprobes sanity tests" -- cgit v1.2.3 From 660e2acad81c19b404f7d7d06e57a6d5e6ce7426 Mon Sep 17 00:00:00 2001 From: Chris Smith Date: Wed, 27 Jan 2010 22:03:11 +0900 Subject: sh: kmemleak support. Enables support for kmemleak on sh. Signed-off-by: Chris Smith Signed-off-by: Paul Mundt --- arch/sh/kernel/vmlinux.lds.S | 6 +++--- lib/Kconfig.debug | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'lib/Kconfig.debug') diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S index 93e9b25a1811..f0bc6b886eed 100644 --- a/arch/sh/kernel/vmlinux.lds.S +++ b/arch/sh/kernel/vmlinux.lds.S @@ -50,12 +50,12 @@ SECTIONS } = 0x0009 EXCEPTION_TABLE(16) - NOTES + + _sdata = .; RO_DATA(PAGE_SIZE) RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) - - _edata = .; /* End of data section */ + _edata = .; DWARF_EH_FRAME diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 25c3ed594c54..d62e3cdab357 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -355,7 +355,7 @@ config SLUB_STATS config DEBUG_KMEMLEAK bool "Kernel memory leak detector" depends on DEBUG_KERNEL && EXPERIMENTAL && !MEMORY_HOTPLUG && \ - (X86 || ARM || PPC || S390) + (X86 || ARM || PPC || S390 || SUPERH) select DEBUG_FS if SYSFS select STACKTRACE if STACKTRACE_SUPPORT -- cgit v1.2.3 From 632ee200130899252508c478ad0e808222573fbc Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 22 Feb 2010 17:04:45 -0800 Subject: rcu: Introduce lockdep-based checking to RCU read-side primitives Inspection is proving insufficient to catch all RCU misuses, which is understandable given that rcu_dereference() might be protected by any of four different flavors of RCU (RCU, RCU-bh, RCU-sched, and SRCU), and might also/instead be protected by any of a number of locking primitives. It is therefore time to enlist the aid of lockdep. This set of patches is inspired by earlier work by Peter Zijlstra and Thomas Gleixner, and takes the following approach: o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched. o Set up separate lockdep classes for each instance of SRCU. o Create primitives that check for being in an RCU read-side critical section. These return exact answers if lockdep is fully enabled, but if unsure, report being in an RCU read-side critical section. (We want to avoid false positives!) The primitives are: For RCU: rcu_read_lock_held(void) For RCU-bh: rcu_read_lock_bh_held(void) For RCU-sched: rcu_read_lock_sched_held(void) For SRCU: srcu_read_lock_held(struct srcu_struct *sp) o Add rcu_dereference_check(), which takes a second argument in which one places a boolean expression based on the above primitives and/or lockdep_is_held(). o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING, and should be quite helpful during the transition period while CONFIG_PROVE_RCU-unaware patches are in flight. The existing rcu_dereference() primitive does no checking, but upcoming patches will change that. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com 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: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- include/linux/rcupdate.h | 126 +++++++++++++++++++++++++++++++++++++++++++---- include/linux/srcu.h | 87 +++++++++++++++++++++++++++++++- kernel/rcupdate.c | 10 ++++ kernel/rcutorture.c | 12 ++++- kernel/srcu.c | 50 ++++++++++++------- lib/Kconfig.debug | 12 +++++ lib/debug_locks.c | 1 + 7 files changed, 267 insertions(+), 31 deletions(-) (limited to 'lib/Kconfig.debug') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 24440f4bf476..e3d37efe2703 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -78,14 +78,120 @@ extern void rcu_init(void); } while (0) #ifdef CONFIG_DEBUG_LOCK_ALLOC + extern struct lockdep_map rcu_lock_map; -# define rcu_read_acquire() \ - lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_) +# define rcu_read_acquire() \ + lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_) # define rcu_read_release() lock_release(&rcu_lock_map, 1, _THIS_IP_) -#else -# define rcu_read_acquire() do { } while (0) -# define rcu_read_release() do { } while (0) -#endif + +extern struct lockdep_map rcu_bh_lock_map; +# define rcu_read_acquire_bh() \ + lock_acquire(&rcu_bh_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_) +# define rcu_read_release_bh() lock_release(&rcu_bh_lock_map, 1, _THIS_IP_) + +extern struct lockdep_map rcu_sched_lock_map; +# define rcu_read_acquire_sched() \ + lock_acquire(&rcu_sched_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_) +# define rcu_read_release_sched() \ + lock_release(&rcu_sched_lock_map, 1, _THIS_IP_) + +/** + * rcu_read_lock_held - might we be in RCU read-side critical section? + * + * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in + * an RCU read-side critical section. In absence of CONFIG_PROVE_LOCKING, + * this assumes we are in an RCU read-side critical section unless it can + * prove otherwise. + */ +static inline int rcu_read_lock_held(void) +{ + if (debug_locks) + return lock_is_held(&rcu_lock_map); + return 1; +} + +/** + * 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. + */ +static inline int rcu_read_lock_bh_held(void) +{ + if (debug_locks) + return lock_is_held(&rcu_bh_lock_map); + return 1; +} + +/** + * rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section? + * + * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in an + * RCU-sched read-side critical section. In absence of CONFIG_PROVE_LOCKING, + * this assumes we are in an RCU-sched read-side critical section unless it + * can prove otherwise. Note that disabling of preemption (including + * disabling irqs) counts as an RCU-sched read-side critical section. + */ +static inline int rcu_read_lock_sched_held(void) +{ + int lockdep_opinion = 0; + + if (debug_locks) + lockdep_opinion = lock_is_held(&rcu_sched_lock_map); + return lockdep_opinion || preempt_count() != 0; +} + +#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +# define rcu_read_acquire() do { } while (0) +# define rcu_read_release() do { } while (0) +# define rcu_read_acquire_bh() do { } while (0) +# define rcu_read_release_bh() do { } while (0) +# define rcu_read_acquire_sched() do { } while (0) +# define rcu_read_release_sched() do { } while (0) + +static inline int rcu_read_lock_held(void) +{ + return 1; +} + +static inline int rcu_read_lock_bh_held(void) +{ + return 1; +} + +static inline int rcu_read_lock_sched_held(void) +{ + return preempt_count() != 0; +} + +#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +#ifdef CONFIG_PROVE_RCU + +/** + * rcu_dereference_check - rcu_dereference with debug checking + * + * Do an rcu_dereference(), but check that the context is correct. + * For example, rcu_dereference_check(gp, rcu_read_lock_held()) to + * ensure that the rcu_dereference_check() executes within an RCU + * read-side critical section. It is also possible to check for + * locks being held, for example, by using lockdep_is_held(). + */ +#define rcu_dereference_check(p, c) \ + ({ \ + if (debug_locks) \ + WARN_ON_ONCE(!(c)); \ + rcu_dereference(p); \ + }) + +#else /* #ifdef CONFIG_PROVE_RCU */ + +#define rcu_dereference_check(p, c) rcu_dereference(p) + +#endif /* #else #ifdef CONFIG_PROVE_RCU */ /** * rcu_read_lock - mark the beginning of an RCU read-side critical section. @@ -160,7 +266,7 @@ static inline void rcu_read_lock_bh(void) { __rcu_read_lock_bh(); __acquire(RCU_BH); - rcu_read_acquire(); + rcu_read_acquire_bh(); } /* @@ -170,7 +276,7 @@ static inline void rcu_read_lock_bh(void) */ static inline void rcu_read_unlock_bh(void) { - rcu_read_release(); + rcu_read_release_bh(); __release(RCU_BH); __rcu_read_unlock_bh(); } @@ -188,7 +294,7 @@ static inline void rcu_read_lock_sched(void) { preempt_disable(); __acquire(RCU_SCHED); - rcu_read_acquire(); + rcu_read_acquire_sched(); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ @@ -205,7 +311,7 @@ static inline notrace void rcu_read_lock_sched_notrace(void) */ static inline void rcu_read_unlock_sched(void) { - rcu_read_release(); + rcu_read_release_sched(); __release(RCU_SCHED); preempt_enable(); } diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 4765d97dcafb..adbe1670b366 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -35,6 +35,9 @@ struct srcu_struct { int completed; struct srcu_struct_array *per_cpu_ref; struct mutex mutex; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ }; #ifndef CONFIG_PREEMPT @@ -43,12 +46,92 @@ struct srcu_struct { #define srcu_barrier() #endif /* #else #ifndef CONFIG_PREEMPT */ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +int __init_srcu_struct(struct srcu_struct *sp, const char *name, + struct lock_class_key *key); + +#define init_srcu_struct(sp) \ +({ \ + static struct lock_class_key __srcu_key; \ + \ + __init_srcu_struct((sp), #sp, &__srcu_key); \ +}) + +# define srcu_read_acquire(sp) \ + lock_acquire(&(sp)->dep_map, 0, 0, 2, 1, NULL, _THIS_IP_) +# define srcu_read_release(sp) \ + lock_release(&(sp)->dep_map, 1, _THIS_IP_) + +#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + int init_srcu_struct(struct srcu_struct *sp); + +# define srcu_read_acquire(sp) do { } while (0) +# define srcu_read_release(sp) do { } while (0) + +#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + void cleanup_srcu_struct(struct srcu_struct *sp); -int srcu_read_lock(struct srcu_struct *sp) __acquires(sp); -void srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); +int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp); +void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); void synchronize_srcu(struct srcu_struct *sp); void synchronize_srcu_expedited(struct srcu_struct *sp); long srcu_batches_completed(struct srcu_struct *sp); +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +/** + * srcu_read_lock_held - might we be in SRCU read-side critical section? + * + * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in + * an SRCU read-side critical section. In absence of CONFIG_PROVE_LOCKING, + * this assumes we are in an SRCU read-side critical section unless it can + * prove otherwise. + */ +static inline int srcu_read_lock_held(struct srcu_struct *sp) +{ + if (debug_locks) + return lock_is_held(&sp->dep_map); + return 1; +} + +#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +static inline int srcu_read_lock_held(struct srcu_struct *sp) +{ + return 1; +} + +#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +/** + * srcu_read_lock - register a new reader for an SRCU-protected structure. + * @sp: srcu_struct in which to register the new reader. + * + * Enter an SRCU read-side critical section. Note that SRCU read-side + * critical sections may be nested. + */ +static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) +{ + int retval = __srcu_read_lock(sp); + + srcu_read_acquire(sp); + return retval; +} + +/** + * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. + * @sp: srcu_struct in which to unregister the old reader. + * @idx: return value from corresponding srcu_read_lock(). + * + * Exit an SRCU read-side critical section. + */ +static inline void srcu_read_unlock(struct srcu_struct *sp, int idx) + __releases(sp) +{ + srcu_read_release(sp); + __srcu_read_unlock(sp, idx); +} + #endif diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 9b7fd4723878..033cb55c26df 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -50,6 +50,16 @@ static struct lock_class_key rcu_lock_key; struct lockdep_map rcu_lock_map = STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key); EXPORT_SYMBOL_GPL(rcu_lock_map); + +static struct lock_class_key rcu_bh_lock_key; +struct lockdep_map rcu_bh_lock_map = + STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_bh", &rcu_bh_lock_key); +EXPORT_SYMBOL_GPL(rcu_bh_lock_map); + +static struct lock_class_key rcu_sched_lock_key; +struct lockdep_map rcu_sched_lock_map = + STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key); +EXPORT_SYMBOL_GPL(rcu_sched_lock_map); #endif /* diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index adda92bfafac..5f43f30fcd1d 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -796,7 +796,11 @@ static void rcu_torture_timer(unsigned long unused) idx = cur_ops->readlock(); completed = cur_ops->completed(); - p = rcu_dereference(rcu_torture_current); + p = rcu_dereference_check(rcu_torture_current, + rcu_read_lock_held() || + rcu_read_lock_bh_held() || + rcu_read_lock_sched_held() || + srcu_read_lock_held(&srcu_ctl)); if (p == NULL) { /* Leave because rcu_torture_writer is not yet underway */ cur_ops->readunlock(idx); @@ -853,7 +857,11 @@ rcu_torture_reader(void *arg) } idx = cur_ops->readlock(); completed = cur_ops->completed(); - p = rcu_dereference(rcu_torture_current); + p = rcu_dereference_check(rcu_torture_current, + rcu_read_lock_held() || + rcu_read_lock_bh_held() || + rcu_read_lock_sched_held() || + srcu_read_lock_held(&srcu_ctl)); if (p == NULL) { /* Wait for rcu_torture_writer to get underway */ cur_ops->readunlock(idx); diff --git a/kernel/srcu.c b/kernel/srcu.c index 31b275b9c112..bde4295774c8 100644 --- a/kernel/srcu.c +++ b/kernel/srcu.c @@ -34,6 +34,30 @@ #include #include +static int init_srcu_struct_fields(struct srcu_struct *sp) +{ + sp->completed = 0; + mutex_init(&sp->mutex); + sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array); + return sp->per_cpu_ref ? 0 : -ENOMEM; +} + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +int __init_srcu_struct(struct srcu_struct *sp, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* Don't re-initialize a lock while it is held. */ + debug_check_no_locks_freed((void *)sp, sizeof(*sp)); + lockdep_init_map(&sp->dep_map, name, key, 0); +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + return init_srcu_struct_fields(sp); +} +EXPORT_SYMBOL_GPL(__init_srcu_struct); + +#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + /** * init_srcu_struct - initialize a sleep-RCU structure * @sp: structure to initialize. @@ -44,13 +68,12 @@ */ int init_srcu_struct(struct srcu_struct *sp) { - sp->completed = 0; - mutex_init(&sp->mutex); - sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array); - return (sp->per_cpu_ref ? 0 : -ENOMEM); + return init_srcu_struct_fields(sp); } EXPORT_SYMBOL_GPL(init_srcu_struct); +#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + /* * srcu_readers_active_idx -- returns approximate number of readers * active on the specified rank of per-CPU counters. @@ -100,15 +123,12 @@ void cleanup_srcu_struct(struct srcu_struct *sp) } EXPORT_SYMBOL_GPL(cleanup_srcu_struct); -/** - * srcu_read_lock - register a new reader for an SRCU-protected structure. - * @sp: srcu_struct in which to register the new reader. - * +/* * Counts the new reader in the appropriate per-CPU element of the * srcu_struct. Must be called from process context. * Returns an index that must be passed to the matching srcu_read_unlock(). */ -int srcu_read_lock(struct srcu_struct *sp) +int __srcu_read_lock(struct srcu_struct *sp) { int idx; @@ -120,26 +140,22 @@ int srcu_read_lock(struct srcu_struct *sp) preempt_enable(); return idx; } -EXPORT_SYMBOL_GPL(srcu_read_lock); +EXPORT_SYMBOL_GPL(__srcu_read_lock); -/** - * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. - * @sp: srcu_struct in which to unregister the old reader. - * @idx: return value from corresponding srcu_read_lock(). - * +/* * Removes the count for the old reader from the appropriate per-CPU * element of the srcu_struct. Note that this may well be a different * CPU than that which was incremented by the corresponding srcu_read_lock(). * Must be called from process context. */ -void srcu_read_unlock(struct srcu_struct *sp, int idx) +void __srcu_read_unlock(struct srcu_struct *sp, int idx) { preempt_disable(); srcu_barrier(); /* ensure compiler won't misorder critical section. */ per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]--; preempt_enable(); } -EXPORT_SYMBOL_GPL(srcu_read_unlock); +EXPORT_SYMBOL_GPL(__srcu_read_unlock); /* * Helper function for synchronize_srcu() and synchronize_srcu_expedited(). diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 6bf97d176326..6af20a8a0a54 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -499,6 +499,18 @@ config PROVE_LOCKING For more details, see Documentation/lockdep-design.txt. +config PROVE_RCU + bool "RCU debugging: prove RCU correctness" + depends on PROVE_LOCKING + default n + help + This feature enables lockdep extensions that check for correct + use of RCU APIs. This is currently under development. Say Y + if you want to debug RCU usage or help work on the PROVE_RCU + feature. + + Say N if you are unsure. + config LOCKDEP bool depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT diff --git a/lib/debug_locks.c b/lib/debug_locks.c index bc3b11731b9c..5bf0020b9248 100644 --- a/lib/debug_locks.c +++ b/lib/debug_locks.c @@ -23,6 +23,7 @@ * shut up after that. */ int debug_locks = 1; +EXPORT_SYMBOL_GPL(debug_locks); /* * The locking-testsuite uses to get a -- cgit v1.2.3 From 1ed509a225008c9e8c0644fbd22168e09a7383a0 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 22 Feb 2010 17:05:05 -0800 Subject: rcu: Add RCU_CPU_STALL_VERBOSE to dump detailed per-task information When RCU detects a grace-period stall, it currently just prints out the PID of any tasks doing the stalling. This patch adds RCU_CPU_STALL_VERBOSE, which enables the more-verbose reporting from sched_show_task(). Suggested-by: Thomas Gleixner Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com 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: <1266887105-1528-21-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- kernel/rcutree.c | 4 ++++ kernel/rcutree.h | 1 + kernel/rcutree_plugin.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++++ lib/Kconfig.debug | 12 ++++++++++++ 4 files changed, 69 insertions(+) (limited to 'lib/Kconfig.debug') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index b07be37d2aa3..525d39810616 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -489,6 +489,10 @@ static void print_other_cpu_stall(struct rcu_state *rsp) smp_processor_id(), (long)(jiffies - rsp->gp_start)); trigger_all_cpu_backtrace(); + /* If so configured, complain about tasks blocking the grace period. */ + + rcu_print_detail_task_stall(rsp); + force_quiescent_state(rsp, 0); /* Kick them all. */ } diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 6a82c34ce669..2ceb08388582 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -352,6 +352,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ #ifdef CONFIG_RCU_CPU_STALL_DETECTOR +static void rcu_print_detail_task_stall(struct rcu_state *rsp); static void rcu_print_task_stall(struct rcu_node *rnp); #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index aecfe37e0117..3516de7091a1 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -312,6 +312,50 @@ EXPORT_SYMBOL_GPL(__rcu_read_unlock); #ifdef CONFIG_RCU_CPU_STALL_DETECTOR +#ifdef CONFIG_RCU_CPU_STALL_VERBOSE + +/* + * Dump detailed information for all tasks blocking the current RCU + * grace period on the specified rcu_node structure. + */ +static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) +{ + unsigned long flags; + struct list_head *lp; + int phase; + struct task_struct *t; + + if (rcu_preempted_readers(rnp)) { + raw_spin_lock_irqsave(&rnp->lock, flags); + phase = rnp->gpnum & 0x1; + lp = &rnp->blocked_tasks[phase]; + list_for_each_entry(t, lp, rcu_node_entry) + sched_show_task(t); + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } +} + +/* + * Dump detailed information for all tasks blocking the current RCU + * grace period. + */ +static void rcu_print_detail_task_stall(struct rcu_state *rsp) +{ + struct rcu_node *rnp = rcu_get_root(rsp); + + rcu_print_detail_task_stall_rnp(rnp); + rcu_for_each_leaf_node(rsp, rnp) + rcu_print_detail_task_stall_rnp(rnp); +} + +#else /* #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */ + +static void rcu_print_detail_task_stall(struct rcu_state *rsp) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */ + /* * Scan the current list of tasks blocked within RCU read-side critical * sections, printing out the tid of each. @@ -760,6 +804,14 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) #ifdef CONFIG_RCU_CPU_STALL_DETECTOR +/* + * Because preemptable RCU does not exist, we never have to check for + * tasks blocked within RCU read-side critical sections. + */ +static void rcu_print_detail_task_stall(struct rcu_state *rsp) +{ +} + /* * Because preemptable RCU does not exist, we never have to check for * tasks blocked within RCU read-side critical sections. diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 6af20a8a0a54..4cdab452bfe2 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -781,6 +781,18 @@ config RCU_CPU_STALL_DETECTOR Say Y if you are unsure. +config RCU_CPU_STALL_VERBOSE + bool "Print additional per-task information for RCU_CPU_STALL_DETECTOR" + depends on RCU_CPU_STALL_DETECTOR && TREE_PREEMPT_RCU + default n + help + This option causes RCU to printk detailed per-task information + for any tasks that are stalling the current RCU grace period. + + Say N if you are unsure. + + Say Y if you want to enable such checks. + config KPROBES_SANITY_TEST bool "Kprobes sanity tests" depends on DEBUG_KERNEL -- cgit v1.2.3 From 84c6f88fc8265d7a712d7d6ed8fc1a878dfc84d1 Mon Sep 17 00:00:00 2001 From: Hitoshi Mitake Date: Thu, 4 Feb 2010 16:08:15 +0900 Subject: perf lock: Fix and add misc documentally things I've forgot to add 'perf lock' line to command-list.txt, so users of perf could not find perf lock when they type 'perf'. Fixing command-list.txt requires document (tools/perf/Documentation/perf-lock.txt). But perf lock is too much "under construction" to write a stable document, so this is something like pseudo document for now. And I wrote description of perf lock at help section of CONFIG_LOCK_STAT, this will navigate users of lock trace events. Signed-off-by: Hitoshi Mitake Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo LKML-Reference: <1265267295-8388-1-git-send-email-mitake@dcl.info.waseda.ac.jp> Signed-off-by: Frederic Weisbecker --- lib/Kconfig.debug | 6 ++++++ tools/perf/Documentation/perf-lock.txt | 29 +++++++++++++++++++++++++++++ tools/perf/command-list.txt | 1 + 3 files changed, 36 insertions(+) create mode 100644 tools/perf/Documentation/perf-lock.txt (limited to 'lib/Kconfig.debug') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 25c3ed594c54..65f964e7fe78 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -520,6 +520,12 @@ config LOCK_STAT For more details, see Documentation/lockstat.txt + You can analyze lock events with "perf lock", subcommand of perf. + If you want to use "perf lock", you need to turn on CONFIG_EVENT_TRACING. + + CONFIG_LOCK_STAT defines "contended" and "acquired" lock events. + (CONFIG_LOCKDEP defines "acquire" and "release" events.) + config DEBUG_LOCKDEP bool "Lock dependency engine debugging" depends on DEBUG_KERNEL && LOCKDEP diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt new file mode 100644 index 000000000000..b317102138c8 --- /dev/null +++ b/tools/perf/Documentation/perf-lock.txt @@ -0,0 +1,29 @@ +perf-lock(1) +============ + +NAME +---- +perf-lock - Analyze lock events + +SYNOPSIS +-------- +[verse] +'perf lock' {record|report|trace} + +DESCRIPTION +----------- +You can analyze various lock behaviours +and statistics with this 'perf lock' command. + + 'perf lock record ' records lock events + between start and end . And this command + produces the file "perf.data" which contains tracing + results of lock events. + + 'perf lock trace' shows raw lock events. + + 'perf lock report' reports statistical data. + +SEE ALSO +-------- +linkperf:perf[1] diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index 9afcff2e3ae5..db6ee94d4a8e 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -18,3 +18,4 @@ perf-top mainporcelain common perf-trace mainporcelain common perf-probe mainporcelain common perf-kmem mainporcelain common +perf-lock mainporcelain common -- cgit v1.2.3 From dd8b1cf681eab40bc5afb67bdd06b2ca341f5669 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 27 Feb 2010 17:10:39 +0100 Subject: perf: Remove pointless breakpoint union Remove pointless union in the breakpoint field of hw_perf_event. Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Paul Mackerras --- include/linux/perf_event.h | 5 ++--- lib/Kconfig.debug | 8 +++++--- 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'lib/Kconfig.debug') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 7b18b4fd5df7..04f06b4be297 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -487,9 +487,8 @@ struct hw_perf_event { struct hrtimer hrtimer; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT - union { /* breakpoint */ - struct arch_hw_breakpoint info; - }; + /* breakpoint */ + struct arch_hw_breakpoint info; #endif }; atomic64_t prev_count; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 65f964e7fe78..4dc24cc13f5c 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -520,11 +520,13 @@ config LOCK_STAT For more details, see Documentation/lockstat.txt - You can analyze lock events with "perf lock", subcommand of perf. - If you want to use "perf lock", you need to turn on CONFIG_EVENT_TRACING. + This also enables lock events required by "perf lock", + subcommand of perf. + If you want to use "perf lock", you also need to turn on + CONFIG_EVENT_TRACING. CONFIG_LOCK_STAT defines "contended" and "acquired" lock events. - (CONFIG_LOCKDEP defines "acquire" and "release" events.) + (CONFIG_LOCKDEP defines "acquire" and "release" events.) config DEBUG_LOCKDEP bool "Lock dependency engine debugging" -- cgit v1.2.3 From 0347af4ee3922220f6bfe74b87b526aa709a0365 Mon Sep 17 00:00:00 2001 From: Simon Kagstrom Date: Fri, 5 Mar 2010 13:42:49 -0800 Subject: lkdtm: add debugfs access and loosen KPROBE ties Add adds a debugfs interface and additional failure modes to LKDTM to provide similar functionality to the provoke-crash driver submitted here: http://lwn.net/Articles/371208/ Crashes can now be induced either through module parameters (as before) or through the debugfs interface as in provoke-crash. The patch also provides a new "direct" interface, where KPROBES are not used, i.e., the crash is invoked directly upon write to the debugfs file. When built without KPROBES configured, only this mode is available. Signed-off-by: Simon Kagstrom Cc: M. Mohan Kumar Cc: Americo Wang Cc: David Woodhouse Cc: Ingo Molnar Cc: "Eric W. Biederman" , Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/fault-injection/provoke-crashes.txt | 38 ++ drivers/misc/lkdtm.c | 472 ++++++++++++++++++---- lib/Kconfig.debug | 5 +- 3 files changed, 430 insertions(+), 85 deletions(-) create mode 100644 Documentation/fault-injection/provoke-crashes.txt (limited to 'lib/Kconfig.debug') diff --git a/Documentation/fault-injection/provoke-crashes.txt b/Documentation/fault-injection/provoke-crashes.txt new file mode 100644 index 000000000000..7a9d3d81525b --- /dev/null +++ b/Documentation/fault-injection/provoke-crashes.txt @@ -0,0 +1,38 @@ +The lkdtm module provides an interface to crash or injure the kernel at +predefined crashpoints to evaluate the reliability of crash dumps obtained +using different dumping solutions. The module uses KPROBEs to instrument +crashing points, but can also crash the kernel directly without KRPOBE +support. + + +You can provide the way either through module arguments when inserting +the module, or through a debugfs interface. + +Usage: insmod lkdtm.ko [recur_count={>0}] cpoint_name=<> cpoint_type=<> + [cpoint_count={>0}] + + recur_count : Recursion level for the stack overflow test. Default is 10. + + cpoint_name : Crash point where the kernel is to be crashed. It can be + one of INT_HARDWARE_ENTRY, INT_HW_IRQ_EN, INT_TASKLET_ENTRY, + FS_DEVRW, MEM_SWAPOUT, TIMERADD, SCSI_DISPATCH_CMD, + IDE_CORE_CP, DIRECT + + cpoint_type : Indicates the action to be taken on hitting the crash point. + It can be one of PANIC, BUG, EXCEPTION, LOOP, OVERFLOW, + CORRUPT_STACK, UNALIGNED_LOAD_STORE_WRITE, OVERWRITE_ALLOCATION, + WRITE_AFTER_FREE, + + cpoint_count : Indicates the number of times the crash point is to be hit + to trigger an action. The default is 10. + +You can also induce failures by mounting debugfs and writing the type to +/provoke-crash/. E.g., + + mount -t debugfs debugfs /mnt + echo EXCEPTION > /mnt/provoke-crash/INT_HARDWARE_ENTRY + + +A special file is `DIRECT' which will induce the crash directly without +KPROBE instrumentation. This mode is the only one available when the module +is built on a kernel without KPROBEs support. diff --git a/drivers/misc/lkdtm.c b/drivers/misc/lkdtm.c index 3648b23d5c92..4a0648301fdf 100644 --- a/drivers/misc/lkdtm.c +++ b/drivers/misc/lkdtm.c @@ -26,21 +26,9 @@ * It is adapted from the Linux Kernel Dump Test Tool by * Fernando Luis Vazquez Cao * - * Usage : insmod lkdtm.ko [recur_count={>0}] cpoint_name=<> cpoint_type=<> - * [cpoint_count={>0}] + * Debugfs support added by Simon Kagstrom * - * recur_count : Recursion level for the stack overflow test. Default is 10. - * - * cpoint_name : Crash point where the kernel is to be crashed. It can be - * one of INT_HARDWARE_ENTRY, INT_HW_IRQ_EN, INT_TASKLET_ENTRY, - * FS_DEVRW, MEM_SWAPOUT, TIMERADD, SCSI_DISPATCH_CMD, - * IDE_CORE_CP - * - * cpoint_type : Indicates the action to be taken on hitting the crash point. - * It can be one of PANIC, BUG, EXCEPTION, LOOP, OVERFLOW - * - * cpoint_count : Indicates the number of times the crash point is to be hit - * to trigger an action. The default is 10. + * See Documentation/fault-injection/provoke-crashes.txt for instructions */ #include @@ -53,13 +41,12 @@ #include #include #include +#include #ifdef CONFIG_IDE #include #endif -#define NUM_CPOINTS 8 -#define NUM_CPOINT_TYPES 5 #define DEFAULT_COUNT 10 #define REC_NUM_DEFAULT 10 @@ -72,7 +59,8 @@ enum cname { MEM_SWAPOUT, TIMERADD, SCSI_DISPATCH_CMD, - IDE_CORE_CP + IDE_CORE_CP, + DIRECT, }; enum ctype { @@ -81,7 +69,11 @@ enum ctype { BUG, EXCEPTION, LOOP, - OVERFLOW + OVERFLOW, + CORRUPT_STACK, + UNALIGNED_LOAD_STORE_WRITE, + OVERWRITE_ALLOCATION, + WRITE_AFTER_FREE, }; static char* cp_name[] = { @@ -92,7 +84,8 @@ static char* cp_name[] = { "MEM_SWAPOUT", "TIMERADD", "SCSI_DISPATCH_CMD", - "IDE_CORE_CP" + "IDE_CORE_CP", + "DIRECT", }; static char* cp_type[] = { @@ -100,7 +93,11 @@ static char* cp_type[] = { "BUG", "EXCEPTION", "LOOP", - "OVERFLOW" + "OVERFLOW", + "CORRUPT_STACK", + "UNALIGNED_LOAD_STORE_WRITE", + "OVERWRITE_ALLOCATION", + "WRITE_AFTER_FREE", }; static struct jprobe lkdtm; @@ -193,34 +190,66 @@ int jp_generic_ide_ioctl(ide_drive_t *drive, struct file *file, } #endif +/* Return the crashpoint number or NONE if the name is invalid */ +static enum ctype parse_cp_type(const char *what, size_t count) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cp_type); i++) { + if (!strcmp(what, cp_type[i])) + return i + 1; + } + + return NONE; +} + +static const char *cp_type_to_str(enum ctype type) +{ + if (type == NONE || type < 0 || type > ARRAY_SIZE(cp_type)) + return "None"; + + return cp_type[type - 1]; +} + +static const char *cp_name_to_str(enum cname name) +{ + if (name == INVALID || name < 0 || name > ARRAY_SIZE(cp_name)) + return "INVALID"; + + return cp_name[name - 1]; +} + + static int lkdtm_parse_commandline(void) { int i; - if (cpoint_name == NULL || cpoint_type == NULL || - cpoint_count < 1 || recur_count < 1) + if (cpoint_count < 1 || recur_count < 1) return -EINVAL; - for (i = 0; i < NUM_CPOINTS; ++i) { + count = cpoint_count; + + /* No special parameters */ + if (!cpoint_type && !cpoint_name) + return 0; + + /* Neither or both of these need to be set */ + if (!cpoint_type || !cpoint_name) + return -EINVAL; + + cptype = parse_cp_type(cpoint_type, strlen(cpoint_type)); + if (cptype == NONE) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(cp_name); i++) { if (!strcmp(cpoint_name, cp_name[i])) { cpoint = i + 1; - break; - } - } - - for (i = 0; i < NUM_CPOINT_TYPES; ++i) { - if (!strcmp(cpoint_type, cp_type[i])) { - cptype = i + 1; - break; + return 0; } } - if (cpoint == INVALID || cptype == NONE) - return -EINVAL; - - count = cpoint_count; - - return 0; + /* Could not find a valid crash point */ + return -EINVAL; } static int recursive_loop(int a) @@ -235,53 +264,92 @@ static int recursive_loop(int a) return recursive_loop(a); } -void lkdtm_handler(void) +static void lkdtm_do_action(enum ctype which) { - printk(KERN_INFO "lkdtm : Crash point %s of type %s hit\n", - cpoint_name, cpoint_type); - --count; + switch (which) { + case PANIC: + panic("dumptest"); + break; + case BUG: + BUG(); + break; + case EXCEPTION: + *((int *) 0) = 0; + break; + case LOOP: + for (;;) + ; + break; + case OVERFLOW: + (void) recursive_loop(0); + break; + case CORRUPT_STACK: { + volatile u32 data[8]; + volatile u32 *p = data; + + p[12] = 0x12345678; + break; + } + case UNALIGNED_LOAD_STORE_WRITE: { + static u8 data[5] __attribute__((aligned(4))) = {1, 2, + 3, 4, 5}; + u32 *p; + u32 val = 0x12345678; + + p = (u32 *)(data + 1); + if (*p == 0) + val = 0x87654321; + *p = val; + break; + } + case OVERWRITE_ALLOCATION: { + size_t len = 1020; + u32 *data = kmalloc(len, GFP_KERNEL); + + data[1024 / sizeof(u32)] = 0x12345678; + kfree(data); + break; + } + case WRITE_AFTER_FREE: { + size_t len = 1024; + u32 *data = kmalloc(len, GFP_KERNEL); + + kfree(data); + schedule(); + memset(data, 0x78, len); + break; + } + case NONE: + default: + break; + } + +} + +static void lkdtm_handler(void) +{ + count--; + printk(KERN_INFO "lkdtm: Crash point %s of type %s hit, trigger in %d rounds\n", + cp_name_to_str(cpoint), cp_type_to_str(cptype), count); if (count == 0) { - switch (cptype) { - case NONE: - break; - case PANIC: - printk(KERN_INFO "lkdtm : PANIC\n"); - panic("dumptest"); - break; - case BUG: - printk(KERN_INFO "lkdtm : BUG\n"); - BUG(); - break; - case EXCEPTION: - printk(KERN_INFO "lkdtm : EXCEPTION\n"); - *((int *) 0) = 0; - break; - case LOOP: - printk(KERN_INFO "lkdtm : LOOP\n"); - for (;;); - break; - case OVERFLOW: - printk(KERN_INFO "lkdtm : OVERFLOW\n"); - (void) recursive_loop(0); - break; - default: - break; - } + lkdtm_do_action(cptype); count = cpoint_count; } } -static int __init lkdtm_module_init(void) +static int lkdtm_register_cpoint(enum cname which) { int ret; - if (lkdtm_parse_commandline() == -EINVAL) { - printk(KERN_INFO "lkdtm : Invalid command\n"); - return -EINVAL; - } + cpoint = INVALID; + if (lkdtm.entry != NULL) + unregister_jprobe(&lkdtm); - switch (cpoint) { + switch (which) { + case DIRECT: + lkdtm_do_action(cptype); + return 0; case INT_HARDWARE_ENTRY: lkdtm.kp.symbol_name = "do_IRQ"; lkdtm.entry = (kprobe_opcode_t*) jp_do_irq; @@ -315,28 +383,268 @@ static int __init lkdtm_module_init(void) lkdtm.kp.symbol_name = "generic_ide_ioctl"; lkdtm.entry = (kprobe_opcode_t*) jp_generic_ide_ioctl; #else - printk(KERN_INFO "lkdtm : Crash point not available\n"); + printk(KERN_INFO "lkdtm: Crash point not available\n"); + return -EINVAL; #endif break; default: - printk(KERN_INFO "lkdtm : Invalid Crash Point\n"); - break; + printk(KERN_INFO "lkdtm: Invalid Crash Point\n"); + return -EINVAL; } + cpoint = which; if ((ret = register_jprobe(&lkdtm)) < 0) { - printk(KERN_INFO "lkdtm : Couldn't register jprobe\n"); - return ret; + printk(KERN_INFO "lkdtm: Couldn't register jprobe\n"); + cpoint = INVALID; + } + + return ret; +} + +static ssize_t do_register_entry(enum cname which, struct file *f, + const char __user *user_buf, size_t count, loff_t *off) +{ + char *buf; + int err; + + if (count >= PAGE_SIZE) + return -EINVAL; + + buf = (char *)__get_free_page(GFP_KERNEL); + if (!buf) + return -ENOMEM; + if (copy_from_user(buf, user_buf, count)) { + free_page((unsigned long) buf); + return -EFAULT; + } + /* NULL-terminate and remove enter */ + buf[count] = '\0'; + strim(buf); + + cptype = parse_cp_type(buf, count); + free_page((unsigned long) buf); + + if (cptype == NONE) + return -EINVAL; + + err = lkdtm_register_cpoint(which); + if (err < 0) + return err; + + *off += count; + + return count; +} + +/* Generic read callback that just prints out the available crash types */ +static ssize_t lkdtm_debugfs_read(struct file *f, char __user *user_buf, + size_t count, loff_t *off) +{ + char *buf; + int i, n, out; + + buf = (char *)__get_free_page(GFP_KERNEL); + + n = snprintf(buf, PAGE_SIZE, "Available crash types:\n"); + for (i = 0; i < ARRAY_SIZE(cp_type); i++) + n += snprintf(buf + n, PAGE_SIZE - n, "%s\n", cp_type[i]); + buf[n] = '\0'; + + out = simple_read_from_buffer(user_buf, count, off, + buf, n); + free_page((unsigned long) buf); + + return out; +} + +static int lkdtm_debugfs_open(struct inode *inode, struct file *file) +{ + return 0; +} + + +static ssize_t int_hardware_entry(struct file *f, const char __user *buf, + size_t count, loff_t *off) +{ + return do_register_entry(INT_HARDWARE_ENTRY, f, buf, count, off); +} + +static ssize_t int_hw_irq_en(struct file *f, const char __user *buf, + size_t count, loff_t *off) +{ + return do_register_entry(INT_HW_IRQ_EN, f, buf, count, off); +} + +static ssize_t int_tasklet_entry(struct file *f, const char __user *buf, + size_t count, loff_t *off) +{ + return do_register_entry(INT_TASKLET_ENTRY, f, buf, count, off); +} + +static ssize_t fs_devrw_entry(struct file *f, const char __user *buf, + size_t count, loff_t *off) +{ + return do_register_entry(FS_DEVRW, f, buf, count, off); +} + +static ssize_t mem_swapout_entry(struct file *f, const char __user *buf, + size_t count, loff_t *off) +{ + return do_register_entry(MEM_SWAPOUT, f, buf, count, off); +} + +static ssize_t timeradd_entry(struct file *f, const char __user *buf, + size_t count, loff_t *off) +{ + return do_register_entry(TIMERADD, f, buf, count, off); +} + +static ssize_t scsi_dispatch_cmd_entry(struct file *f, + const char __user *buf, size_t count, loff_t *off) +{ + return do_register_entry(SCSI_DISPATCH_CMD, f, buf, count, off); +} + +static ssize_t ide_core_cp_entry(struct file *f, const char __user *buf, + size_t count, loff_t *off) +{ + return do_register_entry(IDE_CORE_CP, f, buf, count, off); +} + +/* Special entry to just crash directly. Available without KPROBEs */ +static ssize_t direct_entry(struct file *f, const char __user *user_buf, + size_t count, loff_t *off) +{ + enum ctype type; + char *buf; + + if (count >= PAGE_SIZE) + return -EINVAL; + if (count < 1) + return -EINVAL; + + buf = (char *)__get_free_page(GFP_KERNEL); + if (!buf) + return -ENOMEM; + if (copy_from_user(buf, user_buf, count)) { + free_page((unsigned long) buf); + return -EFAULT; + } + /* NULL-terminate and remove enter */ + buf[count] = '\0'; + strim(buf); + + type = parse_cp_type(buf, count); + free_page((unsigned long) buf); + if (type == NONE) + return -EINVAL; + + printk(KERN_INFO "lkdtm: Performing direct entry %s\n", + cp_type_to_str(type)); + lkdtm_do_action(type); + *off += count; + + return count; +} + +struct crash_entry { + const char *name; + const struct file_operations fops; +}; + +static const struct crash_entry crash_entries[] = { + {"DIRECT", {.read = lkdtm_debugfs_read, + .open = lkdtm_debugfs_open, + .write = direct_entry} }, + {"INT_HARDWARE_ENTRY", {.read = lkdtm_debugfs_read, + .open = lkdtm_debugfs_open, + .write = int_hardware_entry} }, + {"INT_HW_IRQ_EN", {.read = lkdtm_debugfs_read, + .open = lkdtm_debugfs_open, + .write = int_hw_irq_en} }, + {"INT_TASKLET_ENTRY", {.read = lkdtm_debugfs_read, + .open = lkdtm_debugfs_open, + .write = int_tasklet_entry} }, + {"FS_DEVRW", {.read = lkdtm_debugfs_read, + .open = lkdtm_debugfs_open, + .write = fs_devrw_entry} }, + {"MEM_SWAPOUT", {.read = lkdtm_debugfs_read, + .open = lkdtm_debugfs_open, + .write = mem_swapout_entry} }, + {"TIMERADD", {.read = lkdtm_debugfs_read, + .open = lkdtm_debugfs_open, + .write = timeradd_entry} }, + {"SCSI_DISPATCH_CMD", {.read = lkdtm_debugfs_read, + .open = lkdtm_debugfs_open, + .write = scsi_dispatch_cmd_entry} }, + {"IDE_CORE_CP", {.read = lkdtm_debugfs_read, + .open = lkdtm_debugfs_open, + .write = ide_core_cp_entry} }, +}; + +static struct dentry *lkdtm_debugfs_root; + +static int __init lkdtm_module_init(void) +{ + int ret = -EINVAL; + int n_debugfs_entries = 1; /* Assume only the direct entry */ + int i; + + /* Register debugfs interface */ + lkdtm_debugfs_root = debugfs_create_dir("provoke-crash", NULL); + if (!lkdtm_debugfs_root) { + printk(KERN_ERR "lkdtm: creating root dir failed\n"); + return -ENODEV; + } + +#ifdef CONFIG_KPROBES + n_debugfs_entries = ARRAY_SIZE(crash_entries); +#endif + + for (i = 0; i < n_debugfs_entries; i++) { + const struct crash_entry *cur = &crash_entries[i]; + struct dentry *de; + + de = debugfs_create_file(cur->name, 0644, lkdtm_debugfs_root, + NULL, &cur->fops); + if (de == NULL) { + printk(KERN_ERR "lkdtm: could not create %s\n", + cur->name); + goto out_err; + } + } + + if (lkdtm_parse_commandline() == -EINVAL) { + printk(KERN_INFO "lkdtm: Invalid command\n"); + goto out_err; + } + + if (cpoint != INVALID && cptype != NONE) { + ret = lkdtm_register_cpoint(cpoint); + if (ret < 0) { + printk(KERN_INFO "lkdtm: Invalid crash point %d\n", + cpoint); + goto out_err; + } + printk(KERN_INFO "lkdtm: Crash point %s of type %s registered\n", + cpoint_name, cpoint_type); + } else { + printk(KERN_INFO "lkdtm: No crash points registered, enable through debugfs\n"); } - printk(KERN_INFO "lkdtm : Crash point %s of type %s registered\n", - cpoint_name, cpoint_type); return 0; + +out_err: + debugfs_remove_recursive(lkdtm_debugfs_root); + return ret; } static void __exit lkdtm_module_exit(void) { - unregister_jprobe(&lkdtm); - printk(KERN_INFO "lkdtm : Crash point unregistered\n"); + debugfs_remove_recursive(lkdtm_debugfs_root); + + unregister_jprobe(&lkdtm); + printk(KERN_INFO "lkdtm: Crash point unregistered\n"); } module_init(lkdtm_module_init); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 5e3407d997b2..b520ec1f33c5 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -864,8 +864,7 @@ config DEBUG_FORCE_WEAK_PER_CPU config LKDTM tristate "Linux Kernel Dump Test Tool Module" - depends on DEBUG_KERNEL - depends on KPROBES + depends on DEBUG_FS depends on BLOCK default n help @@ -876,7 +875,7 @@ config LKDTM called lkdtm. Documentation on how to use the module can be found in - drivers/misc/lkdtm.c + Documentation/fault-injection/provoke-crashes.txt config FAULT_INJECTION bool "Fault-injection framework" -- cgit v1.2.3 From 1d53661d26aa779dcd74f8a1c5a94e181cc101d8 Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Tue, 23 Mar 2010 13:35:17 -0700 Subject: blackfin: enable DEBUG_SECTION_MISMATCH We see only one section mismatch now after thousands of randconfigs, and a bug has been filed about that one. Signed-off-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Kconfig.debug | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'lib/Kconfig.debug') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 8e5ec5e1ab91..1fafb4b99c9b 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -103,7 +103,8 @@ config HEADERS_CHECK config DEBUG_SECTION_MISMATCH bool "Enable full Section mismatch analysis" - depends on UNDEFINED + depends on UNDEFINED || (BLACKFIN) + default y # This option is on purpose disabled for now. # It will be enabled when we are down to a reasonable number # of section mismatch warnings (< 10 for an allyesconfig build) -- cgit v1.2.3 From 47c4c864af60d14926f4017d23968a8341b8ab9f Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Tue, 6 Apr 2010 10:19:30 +0200 Subject: microblaze: Enable memory leak detector Enable DEBUG_KMEMLEAK for microblaze Signed-off-by: Michal Simek --- lib/Kconfig.debug | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib/Kconfig.debug') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 1fafb4b99c9b..ff017108700d 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -356,7 +356,7 @@ config SLUB_STATS config DEBUG_KMEMLEAK bool "Kernel memory leak detector" depends on DEBUG_KERNEL && EXPERIMENTAL && !MEMORY_HOTPLUG && \ - (X86 || ARM || PPC || S390 || SUPERH) + (X86 || ARM || PPC || S390 || SUPERH || MICROBLAZE) select DEBUG_FS if SYSFS select STACKTRACE if STACKTRACE_SUPPORT -- cgit v1.2.3 From 8b8d8e2840a440d62e8dc0ef36ba433b26f70d32 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 9 Apr 2010 00:14:35 -0700 Subject: sparc64: Support kmemleak. Only missing thing was an _sdata marker in vmlinux.lds.S Signed-off-by: David S. Miller --- arch/sparc/kernel/vmlinux.lds.S | 4 ++++ lib/Kconfig.debug | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'lib/Kconfig.debug') diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index c4f5758c9dc7..0c1e6783657f 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -52,6 +52,10 @@ SECTIONS _etext = .; RO_DATA(PAGE_SIZE) + + /* Start of data section */ + _sdata = .; + .data1 : { *(.data1) } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 1fafb4b99c9b..6c2be6089559 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -356,7 +356,7 @@ config SLUB_STATS config DEBUG_KMEMLEAK bool "Kernel memory leak detector" depends on DEBUG_KERNEL && EXPERIMENTAL && !MEMORY_HOTPLUG && \ - (X86 || ARM || PPC || S390 || SUPERH) + (X86 || ARM || PPC || S390 || SPARC64 || SUPERH) select DEBUG_FS if SYSFS select STACKTRACE if STACKTRACE_SUPPORT -- cgit v1.2.3