This is a note to let you know that I've just added the patch titled
rtmutex: Fix PI chain order integrity
to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git%3Ba=su...
The filename of the patch is: rtmutex-fix-pi-chain-order-integrity.patch and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree, please let stable@vger.kernel.org know about it.
From foo@baz Sun Mar 18 16:55:33 CET 2018
From: Peter Zijlstra peterz@infradead.org Date: Thu, 23 Mar 2017 15:56:13 +0100 Subject: rtmutex: Fix PI chain order integrity
From: Peter Zijlstra peterz@infradead.org
[ Upstream commit e0aad5b44ff5d28ac1d6ae70cdf84ca228e889dc ]
rt_mutex_waiter::prio is a copy of task_struct::prio which is updated during the PI chain walk, such that the PI chain order isn't messed up by (asynchronous) task state updates.
Currently rt_mutex_waiter_less() uses task state for deadline tasks; this is broken, since the task state can, as said above, change asynchronously, causing the RB tree order to change without actual tree update -> FAIL.
Fix this by also copying the deadline into the rt_mutex_waiter state and updating it along with its prio field.
Ideally we would also force PI chain updates whenever DL tasks update their deadline parameter, but for first approximation this is less broken than it was.
Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: juri.lelli@arm.com Cc: bigeasy@linutronix.de Cc: xlpang@redhat.com Cc: rostedt@goodmis.org Cc: mathieu.desnoyers@efficios.com Cc: jdesfossez@efficios.com Cc: bristot@redhat.com Link: http://lkml.kernel.org/r/20170323150216.403992539@infradead.org Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Sasha Levin alexander.levin@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/locking/rtmutex.c | 29 +++++++++++++++++++++++++++-- kernel/locking/rtmutex_common.h | 1 + 2 files changed, 28 insertions(+), 2 deletions(-)
--- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -236,8 +236,7 @@ rt_mutex_waiter_less(struct rt_mutex_wai * then right waiter has a dl_prio() too. */ if (dl_prio(left->prio)) - return dl_time_before(left->task->dl.deadline, - right->task->dl.deadline); + return dl_time_before(left->deadline, right->deadline);
return 0; } @@ -704,7 +703,26 @@ static int rt_mutex_adjust_prio_chain(st
/* [7] Requeue the waiter in the lock waiter tree. */ rt_mutex_dequeue(lock, waiter); + + /* + * Update the waiter prio fields now that we're dequeued. + * + * These values can have changed through either: + * + * sys_sched_set_scheduler() / sys_sched_setattr() + * + * or + * + * DL CBS enforcement advancing the effective deadline. + * + * Even though pi_waiters also uses these fields, and that tree is only + * updated in [11], we can do this here, since we hold [L], which + * serializes all pi_waiters access and rb_erase() does not care about + * the values of the node being removed. + */ waiter->prio = task->prio; + waiter->deadline = task->dl.deadline; + rt_mutex_enqueue(lock, waiter);
/* [8] Release the task */ @@ -831,6 +849,8 @@ static int rt_mutex_adjust_prio_chain(st static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, struct rt_mutex_waiter *waiter) { + lockdep_assert_held(&lock->wait_lock); + /* * Before testing whether we can acquire @lock, we set the * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all @@ -958,6 +978,8 @@ static int task_blocks_on_rt_mutex(struc struct rt_mutex *next_lock; int chain_walk = 0, res;
+ lockdep_assert_held(&lock->wait_lock); + /* * Early deadlock detection. We really don't want the task to * enqueue on itself just to untangle the mess later. It's not @@ -975,6 +997,7 @@ static int task_blocks_on_rt_mutex(struc waiter->task = task; waiter->lock = lock; waiter->prio = task->prio; + waiter->deadline = task->dl.deadline;
/* Get the top priority waiter on the lock */ if (rt_mutex_has_waiters(lock)) @@ -1080,6 +1103,8 @@ static void remove_waiter(struct rt_mute struct task_struct *owner = rt_mutex_owner(lock); struct rt_mutex *next_lock;
+ lockdep_assert_held(&lock->wait_lock); + raw_spin_lock(¤t->pi_lock); rt_mutex_dequeue(lock, waiter); current->pi_blocked_on = NULL; --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -33,6 +33,7 @@ struct rt_mutex_waiter { struct rt_mutex *deadlock_lock; #endif int prio; + u64 deadline; };
/*
Patches currently in stable-queue which might be from peterz@infradead.org are
queue-4.9/sched-stop-resched_cpu-from-sending-ipis-to-offline-cpus.patch queue-4.9/perf-buildid-do-not-assume-that-readlink-returns-a-null-terminated-string.patch queue-4.9/printk-correctly-handle-preemption-in-console_unlock.patch queue-4.9/sched-stop-switched_to_rt-from-sending-ipis-to-offline-cpus.patch queue-4.9/perf-session-don-t-rely-on-evlist-in-pipe-mode.patch queue-4.9/rtmutex-fix-pi-chain-order-integrity.patch queue-4.9/perf-tools-make-perf_event__synthesize_mmap_events-scale.patch queue-4.9/perf-annotate-fix-a-bug-following-symbolic-link-of-a-build-id-file.patch queue-4.9/mm-fix-false-positive-vm_bug_on-in-page_cache_-get-add-_speculative.patch queue-4.9/kprobes-x86-set-kprobes-pages-read-only.patch queue-4.9/perf-stat-issue-a-hw-watchdog-disable-hint.patch queue-4.9/kprobes-x86-fix-kprobe-booster-not-to-boost-far-call-instructions.patch queue-4.9/perf-sort-fix-segfault-with-basic-block-cycles-sort-dimension.patch queue-4.9/perf-probe-fix-concat_probe_trace_events.patch queue-4.9/x86-boot-32-defer-resyncing-initial_page_table-until-per-cpu-is-set-up.patch queue-4.9/perf-inject-copy-events-when-reordering-events-in-pipe-mode.patch queue-4.9/perf-probe-return-errno-when-not-hitting-any-event.patch queue-4.9/perf-evsel-return-exact-sub-event-which-failed-with-eperm-for-wildcards.patch queue-4.9/perf-stat-fix-bug-in-handling-events-in-error-state.patch