From 9161e329ef004343250e3db17b8d12c252af88fc Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 10 May 2010 17:01:30 -0700 Subject: powerpc: remove all rcu head initializations Remove all rcu head inits. We don't care about the RCU head state before passing it to call_rcu() anyway. Only leave the "on_stack" variants so debugobjects can keep track of objects on stack. Signed-off-by: Alexey Dobriyan Signed-off-by: Mathieu Desnoyers Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Signed-off-by: Paul E. McKenney --- arch/powerpc/mm/pgtable.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index ebc2f38eb381..2c7e801ab20b 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -92,7 +92,6 @@ static void pte_free_rcu_callback(struct rcu_head *head) static void pte_free_submit(struct pte_freelist_batch *batch) { - INIT_RCU_HEAD(&batch->rcu); call_rcu(&batch->rcu, pte_free_rcu_callback); } -- cgit v1.2.3 From b97181f24212f4c29197890ce1b2b9100bcc184d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 10 May 2010 17:09:25 -0700 Subject: fs: remove all rcu head initializations, except on_stack initializations Remove all rcu head inits. We don't care about the RCU head state before passing it to call_rcu() anyway. Only leave the "on_stack" variants so debugobjects can keep track of objects on stack. Signed-off-by: Alexey Dobriyan Signed-off-by: Mathieu Desnoyers Signed-off-by: Paul E. McKenney Cc: Alexander Viro Cc: Andries Brouwer --- fs/file.c | 3 --- fs/fs-writeback.c | 31 ++++++++++++++++++++++++++----- fs/partitions/check.c | 1 - 3 files changed, 26 insertions(+), 9 deletions(-) diff --git a/fs/file.c b/fs/file.c index 34bb7f71d994..cccaead962c2 100644 --- a/fs/file.c +++ b/fs/file.c @@ -178,7 +178,6 @@ static struct fdtable * alloc_fdtable(unsigned int nr) fdt->open_fds = (fd_set *)data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = (fd_set *)data; - INIT_RCU_HEAD(&fdt->rcu); fdt->next = NULL; return fdt; @@ -312,7 +311,6 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp) new_fdt->close_on_exec = (fd_set *)&newf->close_on_exec_init; new_fdt->open_fds = (fd_set *)&newf->open_fds_init; new_fdt->fd = &newf->fd_array[0]; - INIT_RCU_HEAD(&new_fdt->rcu); new_fdt->next = NULL; spin_lock(&oldf->file_lock); @@ -430,7 +428,6 @@ struct files_struct init_files = { .fd = &init_files.fd_array[0], .close_on_exec = (fd_set *)&init_files.close_on_exec_init, .open_fds = (fd_set *)&init_files.open_fds_init, - .rcu = RCU_HEAD_INIT, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_task.file_lock), }; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 1d1088f48bc2..af92100a7411 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -75,12 +75,33 @@ static inline bool bdi_work_on_stack(struct bdi_work *work) return test_bit(WS_ONSTACK_B, &work->state); } -static inline void bdi_work_init(struct bdi_work *work, - struct wb_writeback_args *args) +static inline void __bdi_work_init(struct bdi_work *work, + struct wb_writeback_args *args, + int on_stack) { - INIT_RCU_HEAD(&work->rcu_head); work->args = *args; work->state = WS_USED; + if (on_stack) { + work->state |= WS_ONSTACK; + init_rcu_head_on_stack(&work->rcu_head); + } +} + +static inline void bdi_work_init(struct bdi_work *work, + struct wb_writeback_args *args) +{ + __bdi_work_init(work, args, false); +} + +static inline void bdi_work_init_on_stack(struct bdi_work *work, + struct wb_writeback_args *args) +{ + __bdi_work_init(work, args, true); +} + +static inline void bdi_destroy_work_on_stack(struct bdi_work *work) +{ + destroy_rcu_head_on_stack(&work->rcu_head); } /** @@ -233,11 +254,11 @@ static void bdi_sync_writeback(struct backing_dev_info *bdi, }; struct bdi_work work; - bdi_work_init(&work, &args); - work.state |= WS_ONSTACK; + bdi_work_init_on_stack(&work, &args); bdi_queue_work(bdi, &work); bdi_wait_on_work_clear(&work); + bdi_destroy_work_on_stack(&work); } /** diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 5dcd4b0c5533..72c52656dc2e 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -459,7 +459,6 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, } /* everything is up and running, commence */ - INIT_RCU_HEAD(&p->rcu_head); rcu_assign_pointer(ptbl->part[partno], p); /* suppress uevent if the disk supresses it */ -- cgit v1.2.3 From 875352c94224c88f5aa28cb77206f993bd31b7a2 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 10 May 2010 17:14:24 -0700 Subject: mm: remove all rcu head initializations Remove all rcu head inits. We don't care about the RCU head state before passing it to call_rcu() anyway. Only leave the "on_stack" variants so debugobjects can keep track of objects on stack. Signed-off-by: Alexey Dobriyan Signed-off-by: Mathieu Desnoyers Signed-off-by: Paul E. McKenney Cc: Christoph Lameter Cc: Pekka Enberg Cc: Matt Mackall Cc: Andrew Morton --- mm/backing-dev.c | 1 - mm/slob.c | 1 - 2 files changed, 2 deletions(-) diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 660a87a22511..42f6d20358ad 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -668,7 +668,6 @@ int bdi_init(struct backing_dev_info *bdi) bdi->max_ratio = 100; bdi->max_prop_frac = PROP_FRAC_BASE; spin_lock_init(&bdi->wb_lock); - INIT_RCU_HEAD(&bdi->rcu_head); INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->wb_list); INIT_LIST_HEAD(&bdi->work_list); diff --git a/mm/slob.c b/mm/slob.c index 23631e2bb57a..19d2e5d46724 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -639,7 +639,6 @@ void kmem_cache_free(struct kmem_cache *c, void *b) if (unlikely(c->flags & SLAB_DESTROY_BY_RCU)) { struct slob_rcu *slob_rcu; slob_rcu = b + (c->size - sizeof(struct slob_rcu)); - INIT_RCU_HEAD(&slob_rcu->head); slob_rcu->size = c->size; call_rcu(&slob_rcu->head, kmem_rcu_free); } else { -- cgit v1.2.3 From 551d55a944b143ef26fbd482d1c463199d6f65cf Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Sat, 17 Apr 2010 08:48:42 -0400 Subject: tree/tiny rcu: Add debug RCU head objects Helps finding racy users of call_rcu(), which results in hangs because list entries are overwritten and/or skipped. Changelog since v4: - Bissectability is now OK - Now generate a WARN_ON_ONCE() for non-initialized rcu_head passed to call_rcu(). Statically initialized objects are detected with object_is_static(). - Rename rcu_head_init_on_stack to init_rcu_head_on_stack. - Remove init_rcu_head() completely. Changelog since v3: - Include comments from Lai Jiangshan This new patch version is based on the debugobjects with the newly introduced "active state" tracker. Non-initialized entries are all considered as "statically initialized". An activation fixup (triggered by call_rcu()) takes care of performing the debug object initialization without issuing any warning. Since we cannot increase the size of struct rcu_head, I don't see much room to put an identifier for statically initialized rcu_head structures. So for now, we have to live without "activation without explicit init" detection. But the main purpose of this debug option is to detect double-activations (double call_rcu() use of a rcu_head before the callback is executed), which is correctly addressed here. This also detects potential internal RCU callback corruption, which would cause the callbacks to be executed twice. Signed-off-by: Mathieu Desnoyers CC: David S. Miller CC: "Paul E. McKenney" CC: akpm@linux-foundation.org CC: mingo@elte.hu CC: laijs@cn.fujitsu.com CC: dipankar@in.ibm.com CC: josh@joshtriplett.org CC: dvhltc@us.ibm.com CC: niv@us.ibm.com CC: tglx@linutronix.de CC: peterz@infradead.org CC: rostedt@goodmis.org CC: Valdis.Kletnieks@vt.edu CC: dhowells@redhat.com CC: eric.dumazet@gmail.com CC: Alexey Dobriyan Signed-off-by: Paul E. McKenney Reviewed-by: Lai Jiangshan --- include/linux/rcupdate.h | 49 +++++++++++++++ kernel/rcupdate.c | 160 +++++++++++++++++++++++++++++++++++++++++++++++ kernel/rcutiny.c | 2 + kernel/rcutree.c | 2 + lib/Kconfig.debug | 6 ++ 5 files changed, 219 insertions(+) diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index b653b4aaa8a6..2b7fc506e479 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -40,6 +40,7 @@ #include #include #include +#include #ifdef CONFIG_RCU_TORTURE_TEST extern int rcutorture_runnable; /* for sysctl */ @@ -79,6 +80,16 @@ extern void rcu_init(void); (ptr)->next = NULL; (ptr)->func = NULL; \ } while (0) +/* + * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic + * initialization and destruction of rcu_head on the stack. rcu_head structures + * allocated dynamically in the heap or defined statically don't need any + * initialization. + */ +#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD +extern void init_rcu_head_on_stack(struct rcu_head *head); +extern void destroy_rcu_head_on_stack(struct rcu_head *head); +#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ static inline void init_rcu_head_on_stack(struct rcu_head *head) { } @@ -86,6 +97,7 @@ static inline void init_rcu_head_on_stack(struct rcu_head *head) static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } +#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -517,4 +529,41 @@ extern void call_rcu(struct rcu_head *head, extern void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *head)); +/* + * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally + * by call_rcu() and rcu callback execution, and are therefore not part of the + * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors. + */ + +#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD +# define STATE_RCU_HEAD_READY 0 +# define STATE_RCU_HEAD_QUEUED 1 + +extern struct debug_obj_descr rcuhead_debug_descr; + +static inline void debug_rcu_head_queue(struct rcu_head *head) +{ + debug_object_activate(head, &rcuhead_debug_descr); + debug_object_active_state(head, &rcuhead_debug_descr, + STATE_RCU_HEAD_READY, + STATE_RCU_HEAD_QUEUED); +} + +static inline void debug_rcu_head_unqueue(struct rcu_head *head) +{ + debug_object_active_state(head, &rcuhead_debug_descr, + STATE_RCU_HEAD_QUEUED, + STATE_RCU_HEAD_READY); + debug_object_deactivate(head, &rcuhead_debug_descr); +} +#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +static inline void debug_rcu_head_queue(struct rcu_head *head) +{ +} + +static inline void debug_rcu_head_unqueue(struct rcu_head *head) +{ +} +#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ + #endif /* __LINUX_RCUPDATE_H */ diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 72a8dc9567f5..4d169835fb36 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -114,3 +114,163 @@ int rcu_my_thread_group_empty(void) } EXPORT_SYMBOL_GPL(rcu_my_thread_group_empty); #endif /* #ifdef CONFIG_PROVE_RCU */ + +#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD +static inline void debug_init_rcu_head(struct rcu_head *head) +{ + debug_object_init(head, &rcuhead_debug_descr); +} + +static inline void debug_rcu_head_free(struct rcu_head *head) +{ + debug_object_free(head, &rcuhead_debug_descr); +} + +/* + * fixup_init is called when: + * - an active object is initialized + */ +static int rcuhead_fixup_init(void *addr, enum debug_obj_state state) +{ + struct rcu_head *head = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + /* + * Ensure that queued callbacks are all executed. + * If we detect that we are nested in a RCU read-side critical + * section, we should simply fail, otherwise we would deadlock. + */ + if (rcu_preempt_depth() != 0 || preempt_count() != 0 || + irqs_disabled()) { + WARN_ON(1); + return 0; + } + rcu_barrier(); + rcu_barrier_sched(); + rcu_barrier_bh(); + debug_object_init(head, &rcuhead_debug_descr); + return 1; + default: + return 0; + } +} + +/* + * fixup_activate is called when: + * - an active object is activated + * - an unknown object is activated (might be a statically initialized object) + * Activation is performed internally by call_rcu(). + */ +static int rcuhead_fixup_activate(void *addr, enum debug_obj_state state) +{ + struct rcu_head *head = addr; + + switch (state) { + + case ODEBUG_STATE_NOTAVAILABLE: + /* + * This is not really a fixup. We just make sure that it is + * tracked in the object tracker. + */ + debug_object_init(head, &rcuhead_debug_descr); + debug_object_activate(head, &rcuhead_debug_descr); + return 0; + + case ODEBUG_STATE_ACTIVE: + /* + * Ensure that queued callbacks are all executed. + * If we detect that we are nested in a RCU read-side critical + * section, we should simply fail, otherwise we would deadlock. + */ + if (rcu_preempt_depth() != 0 || preempt_count() != 0 || + irqs_disabled()) { + WARN_ON(1); + return 0; + } + rcu_barrier(); + rcu_barrier_sched(); + rcu_barrier_bh(); + debug_object_activate(head, &rcuhead_debug_descr); + return 1; + default: + return 0; + } +} + +/* + * fixup_free is called when: + * - an active object is freed + */ +static int rcuhead_fixup_free(void *addr, enum debug_obj_state state) +{ + struct rcu_head *head = addr; + + switch (state) { + case ODEBUG_STATE_ACTIVE: + /* + * Ensure that queued callbacks are all executed. + * If we detect that we are nested in a RCU read-side critical + * section, we should simply fail, otherwise we would deadlock. + */ +#ifndef CONFIG_PREEMPT + WARN_ON(1); + return 0; +#else + if (rcu_preempt_depth() != 0 || preempt_count() != 0 || + irqs_disabled()) { + WARN_ON(1); + return 0; + } + rcu_barrier(); + rcu_barrier_sched(); + rcu_barrier_bh(); + debug_object_free(head, &rcuhead_debug_descr); + return 1; +#endif + default: + return 0; + } +} + +/** + * init_rcu_head_on_stack() - initialize on-stack rcu_head for debugobjects + * @head: pointer to rcu_head structure to be initialized + * + * This function informs debugobjects of a new rcu_head structure that + * has been allocated as an auto variable on the stack. This function + * is not required for rcu_head structures that are statically defined or + * that are dynamically allocated on the heap. This function has no + * effect for !CONFIG_DEBUG_OBJECTS_RCU_HEAD kernel builds. + */ +void init_rcu_head_on_stack(struct rcu_head *head) +{ + debug_object_init_on_stack(head, &rcuhead_debug_descr); +} +EXPORT_SYMBOL_GPL(init_rcu_head_on_stack); + +/** + * destroy_rcu_head_on_stack() - destroy on-stack rcu_head for debugobjects + * @head: pointer to rcu_head structure to be initialized + * + * This function informs debugobjects that an on-stack rcu_head structure + * is about to go out of scope. As with init_rcu_head_on_stack(), this + * function is not required for rcu_head structures that are statically + * defined or that are dynamically allocated on the heap. Also as with + * init_rcu_head_on_stack(), this function has no effect for + * !CONFIG_DEBUG_OBJECTS_RCU_HEAD kernel builds. + */ +void destroy_rcu_head_on_stack(struct rcu_head *head) +{ + debug_object_free(head, &rcuhead_debug_descr); +} +EXPORT_SYMBOL_GPL(destroy_rcu_head_on_stack); + +struct debug_obj_descr rcuhead_debug_descr = { + .name = "rcu_head", + .fixup_init = rcuhead_fixup_init, + .fixup_activate = rcuhead_fixup_activate, + .fixup_free = rcuhead_fixup_free, +}; +EXPORT_SYMBOL_GPL(rcuhead_debug_descr); +#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */ diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 38729d3cd236..196ec02f8be0 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -169,6 +169,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) while (list) { next = list->next; prefetch(next); + debug_rcu_head_unqueue(list); list->func(list); list = next; } @@ -211,6 +212,7 @@ static void __call_rcu(struct rcu_head *head, { unsigned long flags; + debug_rcu_head_queue(head); head->func = func; head->next = NULL; diff --git a/kernel/rcutree.c b/kernel/rcutree.c index d4437345706f..d5bc43976c5a 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1112,6 +1112,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) while (list) { next = list->next; prefetch(next); + debug_rcu_head_unqueue(list); list->func(list); list = next; if (++count >= rdp->blimit) @@ -1388,6 +1389,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), unsigned long flags; struct rcu_data *rdp; + debug_rcu_head_queue(head); head->func = func; head->next = NULL; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index e722e9d62221..142faa2ec665 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -307,6 +307,12 @@ config DEBUG_OBJECTS_WORK work queue routines to track the life time of work objects and validate the work operations. +config DEBUG_OBJECTS_RCU_HEAD + bool "Debug RCU callbacks objects" + depends on DEBUG_OBJECTS && PREEMPT + help + Enable this to turn on debugging of RCU list heads (call_rcu() usage). + config DEBUG_OBJECTS_ENABLE_DEFAULT int "debug_objects bootup default value (0-1)" range 0 1 -- cgit v1.2.3 From f5155b33277c9678041a27869165619bb34f722f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 30 Apr 2010 06:42:01 -0700 Subject: rcu: add an rcu_dereference_index_check() The sparse RCU-pointer checking relies on type magic that dereferences the pointer in question. This does not work if the pointer is in fact an array index. This commit therefore supplies a new RCU API that omits the sparse checking to continue to support rcu_dereference() on integers. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 2b7fc506e479..9fbc54a2585d 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -566,4 +566,37 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head) } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +#ifndef CONFIG_PROVE_RCU +#define __do_rcu_dereference_check(c) do { } while (0) +#endif /* #ifdef CONFIG_PROVE_RCU */ + +#define __rcu_dereference_index_check(p, c) \ + ({ \ + typeof(p) _________p1 = ACCESS_ONCE(p); \ + __do_rcu_dereference_check(c); \ + smp_read_barrier_depends(); \ + (_________p1); \ + }) + +/** + * rcu_dereference_index_check() - rcu_dereference for indices with debug checking + * @p: The pointer to read, prior to dereferencing + * @c: The conditions under which the dereference will take place + * + * Similar to rcu_dereference_check(), but omits the sparse checking. + * This allows rcu_dereference_index_check() to be used on integers, + * which can then be used as array indices. Attempting to use + * rcu_dereference_check() on an integer will give compiler warnings + * because the sparse address-space mechanism relies on dereferencing + * the RCU-protected pointer. Dereferencing integers is not something + * that even gcc will put up with. + * + * Note that this function does not implicitly check for RCU read-side + * critical sections. If this function gains lots of uses, it might + * make sense to provide versions for each flavor of RCU, but it does + * not make sense as of early 2010. + */ +#define rcu_dereference_index_check(p, c) \ + __rcu_dereference_index_check((p), (c)) + #endif /* __LINUX_RCUPDATE_H */ -- cgit v1.2.3 From 71d1d5c722db9ae3b3f9c08ef7ddcd7759fbb1e0 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 11 May 2010 16:13:14 -0700 Subject: rcu: add __rcu API for later sparse checking This commit defines an __rcu API, but provides only vacuous definitions for it. This breaks dependencies among most of the subsequent patches, allowing them to reach mainline asynchronously via whatever trees are appropriate. Signed-off-by: Arnd Bergmann Signed-off-by: Paul E. McKenney Cc: Christopher Li Cc: Josh Triplett --- include/linux/compiler.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index a5a472b10746..c1a62c56a660 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -16,6 +16,7 @@ # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) # define __percpu __attribute__((noderef, address_space(3))) +# define __rcu extern void __chk_user_ptr(const volatile void __user *); extern void __chk_io_ptr(const volatile void __iomem *); #else @@ -34,6 +35,7 @@ extern void __chk_io_ptr(const volatile void __iomem *); # define __release(x) (void)0 # define __cond_lock(x,c) (c) # define __percpu +# define __rcu #endif #ifdef __KERNEL__ -- cgit v1.2.3 From a25909a4d4a29e272f953e12595bf2f04a292dbd Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 13 May 2010 12:32:28 -0700 Subject: lockdep: Add an in_workqueue_context() lockdep-based test function Some recent uses of RCU make use of workqueues. In these uses, execution within the context of a specific workqueue takes the place of the usual RCU read-side primitives such as rcu_read_lock(), and flushing of workqueues takes the place of the usual RCU grace-period primitives. Checking for correct use of rcu_dereference() in such cases requires a test of whether the code is executing in the context of a particular workqueue. This commit adds an in_workqueue_context() function that provides this test. This new function is only defined when lockdep is enabled, which allows it to be used as the second argument of rcu_dereference_check(). Signed-off-by: Paul E. McKenney --- include/linux/workqueue.h | 4 ++++ kernel/workqueue.c | 15 +++++++++++++++ 2 files changed, 19 insertions(+) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 9466e860d8c2..d0f7c8178498 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -297,4 +297,8 @@ static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) #else long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg); #endif /* CONFIG_SMP */ + +#ifdef CONFIG_LOCKDEP +int in_workqueue_context(struct workqueue_struct *wq); +#endif #endif diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 327d2deb4451..59fef1531dd2 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -68,6 +68,21 @@ struct workqueue_struct { #endif }; +#ifdef CONFIG_LOCKDEP +/** + * in_workqueue_context() - in context of specified workqueue? + * @wq: the workqueue of interest + * + * Checks lockdep state to see if the current task is executing from + * within a workqueue item. This function exists only if lockdep is + * enabled. + */ +int in_workqueue_context(struct workqueue_struct *wq) +{ + return lock_is_held(&wq->lockdep_map); +} +#endif + #ifdef CONFIG_DEBUG_OBJECTS_WORK static struct debug_obj_descr work_debug_descr; -- cgit v1.2.3 From 2c666df80764389886110c942a7916ba9622583d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 29 Apr 2010 20:48:47 -0700 Subject: vfs: add fs.h to define struct file The sparse RCU-pointer annotations require definition of the underlying type of any pointer passed to rcu_dereference() and friends. So fcheck_files() needs "struct file" to be defined, so include fs.h. Signed-off-by: Arnd Bergmann Signed-off-by: Paul E. McKenney Cc: Al Viro --- include/linux/fdtable.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 013dc529e95f..551671e87927 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -11,6 +11,7 @@ #include #include #include +#include #include -- cgit v1.2.3 From 81bdf5bd7349bd4523538cbd7878f334bc2bfe14 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 2 May 2010 18:10:06 -0700 Subject: net: Make accesses to ->br_port safe for sparse RCU The new versions of the rcu_dereference() APIs requires that any pointers passed to one of these APIs be fully defined. The ->br_port field in struct net_device points to a struct net_bridge_port, which is an incomplete type. This commit therefore changes ->br_port to be a void*, and introduces a br_port() helper function to convert the type to struct net_bridge_port, and applies this new helper function where required. Signed-off-by: Arnd Bergmann Signed-off-by: Paul E. McKenney Cc: David Miller Cc: Stephen Hemminger Cc: Eric Dumazet --- include/linux/if_bridge.h | 3 +++ net/bridge/br_fdb.c | 2 +- net/bridge/br_private.h | 5 +++++ net/bridge/netfilter/ebt_redirect.c | 2 +- net/bridge/netfilter/ebt_ulog.c | 4 ++-- net/bridge/netfilter/ebtables.c | 4 ++-- net/netfilter/nfnetlink_log.c | 4 ++-- net/netfilter/nfnetlink_queue.c | 4 ++-- 8 files changed, 18 insertions(+), 10 deletions(-) diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 938b7e81df95..d001d782922d 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -101,6 +101,9 @@ struct __fdb_entry { #include +/* br_handle_frame_hook() needs the following forward declaration. */ +struct net_bridge_port; + extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); extern struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p, struct sk_buff *skb); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 26637439965b..845710bca49c 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -246,7 +246,7 @@ int br_fdb_test_addr(struct net_device *dev, unsigned char *addr) return 0; rcu_read_lock(); - fdb = __br_fdb_get(dev->br_port->br, addr); + fdb = __br_fdb_get(br_port(dev)->br, addr); ret = fdb && fdb->dst->dev != dev && fdb->dst->state == BR_STATE_FORWARDING; rcu_read_unlock(); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 0f4a74bc6a9b..3255188355b5 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -268,6 +268,11 @@ static inline int br_is_root_bridge(const struct net_bridge *br) return !memcmp(&br->bridge_id, &br->designated_root, 8); } +static inline struct net_bridge_port *br_port(const struct net_device *dev) +{ + return rcu_dereference(dev->br_port); +} + /* br_device.c */ extern void br_dev_setup(struct net_device *dev); extern netdev_tx_t br_dev_xmit(struct sk_buff *skb, diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c index 9e19166ba453..a39df0ae0f81 100644 --- a/net/bridge/netfilter/ebt_redirect.c +++ b/net/bridge/netfilter/ebt_redirect.c @@ -25,7 +25,7 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) if (par->hooknum != NF_BR_BROUTING) memcpy(eth_hdr(skb)->h_dest, - par->in->br_port->br->dev->dev_addr, ETH_ALEN); + br_port(par->in)->br->dev->dev_addr, ETH_ALEN); else memcpy(eth_hdr(skb)->h_dest, par->in->dev_addr, ETH_ALEN); skb->pkt_type = PACKET_HOST; diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index ae3c7cef1484..5a4996bbb090 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -178,7 +178,7 @@ static void ebt_ulog_packet(unsigned int hooknr, const struct sk_buff *skb, strcpy(pm->physindev, in->name); /* If in isn't a bridge, then physindev==indev */ if (in->br_port) - strcpy(pm->indev, in->br_port->br->dev->name); + strcpy(pm->indev, br_port(in)->br->dev->name); else strcpy(pm->indev, in->name); } else @@ -187,7 +187,7 @@ static void ebt_ulog_packet(unsigned int hooknr, const struct sk_buff *skb, if (out) { /* If out exists, then out is a bridge port */ strcpy(pm->physoutdev, out->name); - strcpy(pm->outdev, out->br_port->br->dev->name); + strcpy(pm->outdev, br_port(out)->br->dev->name); } else pm->outdev[0] = pm->physoutdev[0] = '\0'; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 59ca00e40dec..4c2aab8cbfc7 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -141,10 +141,10 @@ ebt_basic_match(const struct ebt_entry *e, const struct ethhdr *h, if (FWINV2(ebt_dev_check(e->out, out), EBT_IOUT)) return 1; if ((!in || !in->br_port) ? 0 : FWINV2(ebt_dev_check( - e->logical_in, in->br_port->br->dev), EBT_ILOGICALIN)) + e->logical_in, br_port(in)->br->dev), EBT_ILOGICALIN)) return 1; if ((!out || !out->br_port) ? 0 : FWINV2(ebt_dev_check( - e->logical_out, out->br_port->br->dev), EBT_ILOGICALOUT)) + e->logical_out, br_port(out)->br->dev), EBT_ILOGICALOUT)) return 1; if (e->bitmask & EBT_SOURCEMAC) { diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index fc9a211e629e..78957cfa3bdd 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -404,7 +404,7 @@ __build_packet_message(struct nfulnl_instance *inst, htonl(indev->ifindex)); /* this is the bridge group "brX" */ NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_INDEV, - htonl(indev->br_port->br->dev->ifindex)); + htonl(br_port(indev)->br->dev->ifindex)); } else { /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ @@ -431,7 +431,7 @@ __build_packet_message(struct nfulnl_instance *inst, htonl(outdev->ifindex)); /* this is the bridge group "brX" */ NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_OUTDEV, - htonl(outdev->br_port->br->dev->ifindex)); + htonl(br_port(outdev)->br->dev->ifindex)); } else { /* Case 2: indev is a bridge group, we need to look * for physical device (when called from ipv4) */ diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 12e1ab37fcd8..c3c17498298e 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -297,7 +297,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, htonl(indev->ifindex)); /* this is the bridge group "brX" */ NLA_PUT_BE32(skb, NFQA_IFINDEX_INDEV, - htonl(indev->br_port->br->dev->ifindex)); + htonl(br_port(indev)->br->dev->ifindex)); } else { /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ @@ -322,7 +322,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, htonl(outdev->ifindex)); /* this is the bridge group "brX" */ NLA_PUT_BE32(skb, NFQA_IFINDEX_OUTDEV, - htonl(outdev->br_port->br->dev->ifindex)); + htonl(br_port(outdev)->br->dev->ifindex)); } else { /* Case 2: outdev is bridge group, we need to look for * physical output device (when called from ipv4) */ -- cgit v1.2.3 From ec8c27e04f89a7575ca2c4facb99152e03d6a99c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 30 Apr 2010 06:45:36 -0700 Subject: mce: convert to rcu_dereference_index_check() The mce processing applies rcu_dereference_check() to integers used as array indices. This patch therefore moves mce to the new RCU API rcu_dereference_index_check() that avoids the sparse processing that would otherwise result in compiler errors. Signed-off-by: Paul E. McKenney Cc: Andi Kleen Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" --- arch/x86/kernel/cpu/mcheck/mce.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 18cc42562250..0e78657e29c5 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -51,7 +51,7 @@ static DEFINE_MUTEX(mce_read_mutex); #define rcu_dereference_check_mce(p) \ - rcu_dereference_check((p), \ + rcu_dereference_index_check((p), \ rcu_read_lock_sched_held() || \ lockdep_is_held(&mce_read_mutex)) -- cgit v1.2.3 From a53f4b61a76a7e95139b8e8abba02e9bfe87a58a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 1 Jul 2010 12:45:34 -0700 Subject: Revert "net: Make accesses to ->br_port safe for sparse RCU" This reverts commit 81bdf5bd7349bd4523538cbd7878f334bc2bfe14, which is obsoleted by commit f350a0a87374 from the net tree. --- include/linux/if_bridge.h | 3 --- net/bridge/br_fdb.c | 2 +- net/bridge/br_private.h | 5 ----- net/bridge/netfilter/ebt_redirect.c | 2 +- net/bridge/netfilter/ebt_ulog.c | 4 ++-- net/bridge/netfilter/ebtables.c | 4 ++-- net/netfilter/nfnetlink_log.c | 4 ++-- net/netfilter/nfnetlink_queue.c | 4 ++-- 8 files changed, 10 insertions(+), 18 deletions(-) diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index d001d782922d..938b7e81df95 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -101,9 +101,6 @@ struct __fdb_entry { #include -/* br_handle_frame_hook() needs the following forward declaration. */ -struct net_bridge_port; - extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); extern struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p, struct sk_buff *skb); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 09c479e05623..b01dde35a69e 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -244,7 +244,7 @@ int br_fdb_test_addr(struct net_device *dev, unsigned char *addr) return 0; rcu_read_lock(); - fdb = __br_fdb_get(br_port(dev)->br, addr); + fdb = __br_fdb_get(dev->br_port->br, addr); ret = fdb && fdb->dst->dev != dev && fdb->dst->state == BR_STATE_FORWARDING; rcu_read_unlock(); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 3255188355b5..0f4a74bc6a9b 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -268,11 +268,6 @@ static inline int br_is_root_bridge(const struct net_bridge *br) return !memcmp(&br->bridge_id, &br->designated_root, 8); } -static inline struct net_bridge_port *br_port(const struct net_device *dev) -{ - return rcu_dereference(dev->br_port); -} - /* br_device.c */ extern void br_dev_setup(struct net_device *dev); extern netdev_tx_t br_dev_xmit(struct sk_buff *skb, diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c index a39df0ae0f81..9e19166ba453 100644 --- a/net/bridge/netfilter/ebt_redirect.c +++ b/net/bridge/netfilter/ebt_redirect.c @@ -25,7 +25,7 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) if (par->hooknum != NF_BR_BROUTING) memcpy(eth_hdr(skb)->h_dest, - br_port(par->in)->br->dev->dev_addr, ETH_ALEN); + par->in->br_port->br->dev->dev_addr, ETH_ALEN); else memcpy(eth_hdr(skb)->h_dest, par->in->dev_addr, ETH_ALEN); skb->pkt_type = PACKET_HOST; diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index 5a4996bbb090..ae3c7cef1484 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -178,7 +178,7 @@ static void ebt_ulog_packet(unsigned int hooknr, const struct sk_buff *skb, strcpy(pm->physindev, in->name); /* If in isn't a bridge, then physindev==indev */ if (in->br_port) - strcpy(pm->indev, br_port(in)->br->dev->name); + strcpy(pm->indev, in->br_port->br->dev->name); else strcpy(pm->indev, in->name); } else @@ -187,7 +187,7 @@ static void ebt_ulog_packet(unsigned int hooknr, const struct sk_buff *skb, if (out) { /* If out exists, then out is a bridge port */ strcpy(pm->physoutdev, out->name); - strcpy(pm->outdev, br_port(out)->br->dev->name); + strcpy(pm->outdev, out->br_port->br->dev->name); } else pm->outdev[0] = pm->physoutdev[0] = '\0'; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 4c2aab8cbfc7..59ca00e40dec 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -141,10 +141,10 @@ ebt_basic_match(const struct ebt_entry *e, const struct ethhdr *h, if (FWINV2(ebt_dev_check(e->out, out), EBT_IOUT)) return 1; if ((!in || !in->br_port) ? 0 : FWINV2(ebt_dev_check( - e->logical_in, br_port(in)->br->dev), EBT_ILOGICALIN)) + e->logical_in, in->br_port->br->dev), EBT_ILOGICALIN)) return 1; if ((!out || !out->br_port) ? 0 : FWINV2(ebt_dev_check( - e->logical_out, br_port(out)->br->dev), EBT_ILOGICALOUT)) + e->logical_out, out->br_port->br->dev), EBT_ILOGICALOUT)) return 1; if (e->bitmask & EBT_SOURCEMAC) { diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 78957cfa3bdd..fc9a211e629e 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -404,7 +404,7 @@ __build_packet_message(struct nfulnl_instance *inst, htonl(indev->ifindex)); /* this is the bridge group "brX" */ NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_INDEV, - htonl(br_port(indev)->br->dev->ifindex)); + htonl(indev->br_port->br->dev->ifindex)); } else { /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ @@ -431,7 +431,7 @@ __build_packet_message(struct nfulnl_instance *inst, htonl(outdev->ifindex)); /* this is the bridge group "brX" */ NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_OUTDEV, - htonl(br_port(outdev)->br->dev->ifindex)); + htonl(outdev->br_port->br->dev->ifindex)); } else { /* Case 2: indev is a bridge group, we need to look * for physical device (when called from ipv4) */ diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index c3c17498298e..12e1ab37fcd8 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -297,7 +297,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, htonl(indev->ifindex)); /* this is the bridge group "brX" */ NLA_PUT_BE32(skb, NFQA_IFINDEX_INDEV, - htonl(br_port(indev)->br->dev->ifindex)); + htonl(indev->br_port->br->dev->ifindex)); } else { /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ @@ -322,7 +322,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, htonl(outdev->ifindex)); /* this is the bridge group "brX" */ NLA_PUT_BE32(skb, NFQA_IFINDEX_OUTDEV, - htonl(br_port(outdev)->br->dev->ifindex)); + htonl(outdev->br_port->br->dev->ifindex)); } else { /* Case 2: outdev is bridge group, we need to look for * physical output device (when called from ipv4) */ -- cgit v1.2.3