From 5f2962401c6e195222f320d12b3a55377b2d4653 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Thu, 10 Dec 2020 11:15:00 +0100 Subject: [PATCH] locking/lockdep: Exclude local_lock_t from IRQ inversions The purpose of local_lock_t is to abstract: preempt_disable() / local_bh_disable() / local_irq_disable(). These are the traditional means of gaining access to per-cpu data, but are fundamentally non-preemptible. local_lock_t provides a per-cpu lock, that on !PREEMPT_RT reduces to no-ops, just like regular spinlocks do on UP. This gives rise to: CPU0 CPU1 local_lock(B) spin_lock_irq(A) spin_lock(A) local_lock(B) Where lockdep then figures things will lock up; which would be true if B were any other kind of lock. However this is a false positive, no such deadlock actually exists. For !RT the above local_lock(B) is preempt_disable(), and there's obviously no deadlock; alternatively, CPU0's B != CPU1's B. For RT the argument is that since local_lock() nests inside spin_lock(), it cannot be used in hardirq context, and therefore CPU0 cannot in fact happen. Even though B is a real lock, it is a preemptible lock and any threaded-irq would simply schedule out and let the preempted task (which holds B) continue such that the task on CPU1 can make progress, after which the threaded-irq resumes and can finish. This means that we can never form an IRQ inversion on a local_lock dependency, so terminate the graph walk when looking for IRQ inversions when we encounter one. One consequence is that (for LOCKDEP_SMALL) when we look for redundant dependencies, A -> B is not redundant in the presence of A -> L -> B. Signed-off-by: Boqun Feng [peterz: Changelog] Signed-off-by: Peter Zijlstra (Intel) --- kernel/locking/lockdep.c | 57 +++++++++++++++++++++++++++++++++++++--- 1 file changed, 53 insertions(+), 4 deletions(-) diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index f2ae8a65f667..ad9afd8c7eb9 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2200,6 +2200,44 @@ static inline bool usage_match(struct lock_list *entry, void *mask) return !!((entry->class->usage_mask & LOCKF_IRQ) & *(unsigned long *)mask); } +static inline bool usage_skip(struct lock_list *entry, void *mask) +{ + /* + * Skip local_lock() for irq inversion detection. + * + * For !RT, local_lock() is not a real lock, so it won't carry any + * dependency. + * + * For RT, an irq inversion happens when we have lock A and B, and on + * some CPU we can have: + * + * lock(A); + * + * lock(B); + * + * where lock(B) cannot sleep, and we have a dependency B -> ... -> A. + * + * Now we prove local_lock() cannot exist in that dependency. First we + * have the observation for any lock chain L1 -> ... -> Ln, for any + * 1 <= i <= n, Li.inner_wait_type <= L1.inner_wait_type, otherwise + * wait context check will complain. And since B is not a sleep lock, + * therefore B.inner_wait_type >= 2, and since the inner_wait_type of + * local_lock() is 3, which is greater than 2, therefore there is no + * way the local_lock() exists in the dependency B -> ... -> A. + * + * As a result, we will skip local_lock(), when we search for irq + * inversion bugs. + */ + if (entry->class->lock_type == LD_LOCK_PERCPU) { + if (DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG)) + return false; + + return true; + } + + return false; +} + /* * Find a node in the forwards-direction dependency sub-graph starting * at @root->class that matches @bit. @@ -2215,7 +2253,7 @@ find_usage_forwards(struct lock_list *root, unsigned long usage_mask, debug_atomic_inc(nr_find_usage_forwards_checks); - result = __bfs_forwards(root, &usage_mask, usage_match, NULL, target_entry); + result = __bfs_forwards(root, &usage_mask, usage_match, usage_skip, target_entry); return result; } @@ -2232,7 +2270,7 @@ find_usage_backwards(struct lock_list *root, unsigned long usage_mask, debug_atomic_inc(nr_find_usage_backwards_checks); - result = __bfs_backwards(root, &usage_mask, usage_match, NULL, target_entry); + result = __bfs_backwards(root, &usage_mask, usage_match, usage_skip, target_entry); return result; } @@ -2597,7 +2635,7 @@ static int check_irq_usage(struct task_struct *curr, struct held_lock *prev, */ bfs_init_rootb(&this, prev); - ret = __bfs_backwards(&this, &usage_mask, usage_accumulate, NULL, NULL); + ret = __bfs_backwards(&this, &usage_mask, usage_accumulate, usage_skip, NULL); if (bfs_error(ret)) { print_bfs_bug(ret); return 0; @@ -2664,6 +2702,12 @@ static inline int check_irq_usage(struct task_struct *curr, { return 1; } + +static inline bool usage_skip(struct lock_list *entry, void *mask) +{ + return false; +} + #endif /* CONFIG_TRACE_IRQFLAGS */ #ifdef CONFIG_LOCKDEP_SMALL @@ -2697,7 +2741,12 @@ check_redundant(struct held_lock *src, struct held_lock *target) debug_atomic_inc(nr_redundant_checks); - ret = check_path(target, &src_entry, hlock_equal, NULL, &target_entry); + /* + * Note: we skip local_lock() for redundant check, because as the + * comment in usage_skip(), A -> local_lock() -> B and A -> B are not + * the same. + */ + ret = check_path(target, &src_entry, hlock_equal, usage_skip, &target_entry); if (ret == BFS_RMATCH) debug_atomic_inc(nr_redundant);