From 70cc08c44fb55b587c7485a15549e9f9a12c9405 Mon Sep 17 00:00:00 2001 From: Prateek Sood Date: Thu, 7 Sep 2017 20:00:58 +0530 Subject: locking/rwsem-xadd: Fix missed wakeup due to reordering of load commit 9c29c31830a4eca724e137a9339137204bbb31be upstream. If a spinner is present, there is a chance that the load of rwsem_has_spinner() in rwsem_wake() can be reordered with respect to decrement of rwsem count in __up_write() leading to wakeup being missed: spinning writer up_write caller --------------- ----------------------- [S] osq_unlock() [L] osq spin_lock(wait_lock) sem->count=0xFFFFFFFF00000001 +0xFFFFFFFF00000000 count=sem->count MB sem->count=0xFFFFFFFE00000001 -0xFFFFFFFF00000001 spin_trylock(wait_lock) return rwsem_try_write_lock(count) spin_unlock(wait_lock) schedule() Reordering of atomic_long_sub_return_release() in __up_write() and rwsem_has_spinner() in rwsem_wake() can cause missing of wakeup in up_write() context. In spinning writer, sem->count and local variable count is 0XFFFFFFFE00000001. It would result in rwsem_try_write_lock() failing to acquire rwsem and spinning writer going to sleep in rwsem_down_write_failed(). The smp_rmb() will make sure that the spinner state is consulted after sem->count is updated in up_write context. Signed-off-by: Prateek Sood Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dave@stgolabs.net Cc: longman@redhat.com Cc: parri.andrea@gmail.com Cc: sramana@codeaurora.org Link: http://lkml.kernel.org/r/1504794658-15397-1-git-send-email-prsood@codeaurora.org Signed-off-by: Ingo Molnar Signed-off-by: Amit Pundir Signed-off-by: Greg Kroah-Hartman --- kernel/locking/rwsem-xadd.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'kernel/locking') diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index a4d4de05b2d1..1be33caf157d 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -510,6 +510,33 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) { unsigned long flags; + /* + * __rwsem_down_write_failed_common(sem) + * rwsem_optimistic_spin(sem) + * osq_unlock(sem->osq) + * ... + * atomic_long_add_return(&sem->count) + * + * - VS - + * + * __up_write() + * if (atomic_long_sub_return_release(&sem->count) < 0) + * rwsem_wake(sem) + * osq_is_locked(&sem->osq) + * + * And __up_write() must observe !osq_is_locked() when it observes the + * atomic_long_add_return() in order to not miss a wakeup. + * + * This boils down to: + * + * [S.rel] X = 1 [RmW] r0 = (Y += 0) + * MB RMB + * [RmW] Y += 1 [L] r1 = X + * + * exists (r0=1 /\ r1=0) + */ + smp_rmb(); + /* * If a spinner is present, it is not necessary to do the wakeup. * Try to do wakeup only if the trylock succeeds to minimize -- cgit v1.2.3 From d914882c936d9c3a1fa4c10d5950c5f0a7d32d79 Mon Sep 17 00:00:00 2001 From: Prateek Sood Date: Fri, 14 Jul 2017 19:17:56 +0530 Subject: locking/osq_lock: Fix osq_lock queue corruption commit 50972fe78f24f1cd0b9d7bbf1f87d2be9e4f412e upstream. Fix ordering of link creation between node->prev and prev->next in osq_lock(). A case in which the status of optimistic spin queue is CPU6->CPU2 in which CPU6 has acquired the lock. tail v ,-. <- ,-. |6| |2| `-' -> `-' At this point if CPU0 comes in to acquire osq_lock, it will update the tail count. CPU2 CPU0 ---------------------------------- tail v ,-. <- ,-. ,-. |6| |2| |0| `-' -> `-' `-' After tail count update if CPU2 starts to unqueue itself from optimistic spin queue, it will find an updated tail count with CPU0 and update CPU2 node->next to NULL in osq_wait_next(). unqueue-A tail v ,-. <- ,-. ,-. |6| |2| |0| `-' `-' `-' unqueue-B ->tail != curr && !node->next If reordering of following stores happen then prev->next where prev being CPU2 would be updated to point to CPU0 node: tail v ,-. <- ,-. ,-. |6| |2| |0| `-' `-' -> `-' osq_wait_next() node->next <- 0 xchg(node->next, NULL) tail v ,-. <- ,-. ,-. |6| |2| |0| `-' `-' `-' unqueue-C At this point if next instruction WRITE_ONCE(next->prev, prev); in CPU2 path is committed before the update of CPU0 node->prev = prev then CPU0 node->prev will point to CPU6 node. tail v----------. v ,-. <- ,-. ,-. |6| |2| |0| `-' `-' `-' `----------^ At this point if CPU0 path's node->prev = prev is committed resulting in change of CPU0 prev back to CPU2 node. CPU2 node->next is NULL currently, tail v ,-. <- ,-. <- ,-. |6| |2| |0| `-' `-' `-' `----------^ so if CPU0 gets into unqueue path of osq_lock it will keep spinning in infinite loop as condition prev->next == node will never be true. Signed-off-by: Prateek Sood [ Added pictures, rewrote comments. ] Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: sramana@codeaurora.org Link: http://lkml.kernel.org/r/1500040076-27626-1-git-send-email-prsood@codeaurora.org Signed-off-by: Ingo Molnar Signed-off-by: Amit Pundir Signed-off-by: Greg Kroah-Hartman --- kernel/locking/osq_lock.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'kernel/locking') diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index 05a37857ab55..8d7047ecef4e 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -104,6 +104,19 @@ bool osq_lock(struct optimistic_spin_queue *lock) prev = decode_cpu(old); node->prev = prev; + + /* + * osq_lock() unqueue + * + * node->prev = prev osq_wait_next() + * WMB MB + * prev->next = node next->prev = prev // unqueue-C + * + * Here 'node->prev' and 'next->prev' are the same variable and we need + * to ensure these stores happen in-order to avoid corrupting the list. + */ + smp_wmb(); + WRITE_ONCE(prev->next, node); /* -- cgit v1.2.3