From 6687659568e2ec5b3ac24b39c5d26ce8b9d90434 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Sun, 17 Apr 2016 23:31:41 -0700 Subject: locking/pvqspinlock: Fix division by zero in qstat_read() While playing with the qstat statistics (in /qlockstat/) I ran into the following splat on a VM when opening pv_hash_hops: divide error: 0000 [#1] SMP ... RIP: 0010:[] [] qstat_read+0x12e/0x1e0 ... Call Trace: [] ? mem_cgroup_commit_charge+0x6c/0xd0 [] ? page_add_new_anon_rmap+0x8c/0xd0 [] ? handle_mm_fault+0x1439/0x1b40 [] ? do_mmap+0x449/0x550 [] ? __vfs_read+0x23/0xd0 [] ? rw_verify_area+0x52/0xd0 [] ? vfs_read+0x81/0x120 [] ? SyS_read+0x42/0xa0 [] ? entry_SYSCALL_64_fastpath+0x1e/0xa8 Fix this by verifying that qstat_pv_kick_unlock is in fact non-zero, similarly to what the qstat_pv_latency_wake case does, as if nothing else, this can come from resetting the statistics, thus having 0 kicks should be quite valid in this context. Signed-off-by: Davidlohr Bueso Reviewed-by: Waiman Long Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dave@stgolabs.net Cc: waiman.long@hpe.com Link: http://lkml.kernel.org/r/1460961103-24953-1-git-send-email-dave@stgolabs.net Signed-off-by: Ingo Molnar --- kernel/locking/qspinlock_stat.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h index eb2a2c9bc3fc..d734b7502001 100644 --- a/kernel/locking/qspinlock_stat.h +++ b/kernel/locking/qspinlock_stat.h @@ -136,10 +136,12 @@ static ssize_t qstat_read(struct file *file, char __user *user_buf, } if (counter == qstat_pv_hash_hops) { - u64 frac; + u64 frac = 0; - frac = 100ULL * do_div(stat, kicks); - frac = DIV_ROUND_CLOSEST_ULL(frac, kicks); + if (kicks) { + frac = 100ULL * do_div(stat, kicks); + frac = DIV_ROUND_CLOSEST_ULL(frac, kicks); + } /* * Return a X.XX decimal number -- cgit v1.2.3 From c24697566298df04cac9913e0601501b5ee2b3f5 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Tue, 16 Feb 2016 13:57:40 +0800 Subject: locking/lockdep: Fix ->irq_context calculation task_irq_context() returns the encoded irq_context of the task, the return value is encoded in the same as ->irq_context of held_lock. Always return 0 if !(CONFIG_TRACE_IRQFLAGS && CONFIG_PROVE_LOCKING) Signed-off-by: Boqun Feng Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Josh Triplett Cc: Lai Jiangshan Cc: Linus Torvalds Cc: Mathieu Desnoyers Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Cc: sasha.levin@oracle.com Link: http://lkml.kernel.org/r/1455602265-16490-2-git-send-email-boqun.feng@gmail.com Signed-off-by: Ingo Molnar --- kernel/locking/lockdep.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index ed9410936a22..beb06f604420 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2932,6 +2932,11 @@ static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock) return 1; } +static inline unsigned int task_irq_context(struct task_struct *task) +{ + return 2 * !!task->hardirq_context + !!task->softirq_context; +} + static int separate_irq_context(struct task_struct *curr, struct held_lock *hlock) { @@ -2940,8 +2945,6 @@ static int separate_irq_context(struct task_struct *curr, /* * Keep track of points where we cross into an interrupt context: */ - hlock->irq_context = 2*(curr->hardirq_context ? 1 : 0) + - curr->softirq_context; if (depth) { struct held_lock *prev_hlock; @@ -2973,6 +2976,11 @@ static inline int mark_irqflags(struct task_struct *curr, return 1; } +static inline unsigned int task_irq_context(struct task_struct *task) +{ + return 0; +} + static inline int separate_irq_context(struct task_struct *curr, struct held_lock *hlock) { @@ -3241,6 +3249,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, hlock->acquire_ip = ip; hlock->instance = lock; hlock->nest_lock = nest_lock; + hlock->irq_context = task_irq_context(curr); hlock->trylock = trylock; hlock->read = read; hlock->check = check; -- cgit v1.2.3 From 75dd602a5198a6e5f75534db52b6e6fbaabb33d1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 30 Mar 2016 11:36:59 +0200 Subject: lockdep: Fix lock_chain::base size lock_chain::base is used to store an index into the chain_hlocks[] array, however that array contains more elements than can be indexed using the u16. Change the lock_chain structure to use a bitfield to encode the data it needs and add BUILD_BUG_ON() assertions to check the fields are wide enough. Also, for DEBUG_LOCKDEP, assert that we don't run out of elements of that array; as that would wreck the collision detectoring. Signed-off-by: Peter Zijlstra (Intel) Cc: Alfredo Alvarez Fernandez Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Sedat Dilek Cc: Theodore Ts'o Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20160330093659.GS3408@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 8 +++++--- kernel/locking/lockdep.c | 24 +++++++++++++++++++++++- kernel/locking/lockdep_proc.c | 2 ++ 3 files changed, 30 insertions(+), 4 deletions(-) (limited to 'kernel/locking') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index d026b190c530..d10ef06971b5 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -196,9 +196,11 @@ struct lock_list { * We record lock dependency chains, so that we can cache them: */ struct lock_chain { - u8 irq_context; - u8 depth; - u16 base; + /* see BUILD_BUG_ON()s in lookup_chain_cache() */ + unsigned int irq_context : 2, + depth : 6, + base : 24; + /* 4 byte hole */ struct hlist_node entry; u64 chain_key; }; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index beb06f604420..78c1c0ee6dc1 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2176,15 +2176,37 @@ cache_hit: chain->irq_context = hlock->irq_context; i = get_first_held_lock(curr, hlock); chain->depth = curr->lockdep_depth + 1 - i; + + BUILD_BUG_ON((1UL << 24) <= ARRAY_SIZE(chain_hlocks)); + BUILD_BUG_ON((1UL << 6) <= ARRAY_SIZE(curr->held_locks)); + BUILD_BUG_ON((1UL << 8*sizeof(chain_hlocks[0])) <= ARRAY_SIZE(lock_classes)); + if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) { chain->base = nr_chain_hlocks; - nr_chain_hlocks += chain->depth; for (j = 0; j < chain->depth - 1; j++, i++) { int lock_id = curr->held_locks[i].class_idx - 1; chain_hlocks[chain->base + j] = lock_id; } chain_hlocks[chain->base + j] = class - lock_classes; } + + if (nr_chain_hlocks < MAX_LOCKDEP_CHAIN_HLOCKS) + nr_chain_hlocks += chain->depth; + +#ifdef CONFIG_DEBUG_LOCKDEP + /* + * Important for check_no_collision(). + */ + if (unlikely(nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)) { + if (debug_locks_off_graph_unlock()) + return 0; + + print_lockdep_off("BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!"); + dump_stack(); + return 0; + } +#endif + hlist_add_head_rcu(&chain->entry, hash_head); debug_atomic_inc(chain_lookup_misses); inc_chains(); diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index dbb61a302548..a0f61effad25 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -141,6 +141,8 @@ static int lc_show(struct seq_file *m, void *v) int i; if (v == SEQ_START_TOKEN) { + if (nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS) + seq_printf(m, "(buggered) "); seq_printf(m, "all lock chains:\n"); return 0; } -- cgit v1.2.3