From 214f766ea0909e743122966c4617b3a112e405d7 Mon Sep 17 00:00:00 2001 From: Vikram Mulukutla Date: Thu, 4 Oct 2012 17:13:22 -0700 Subject: [PATCH] lib/spinlock_debug: avoid livelock in do_raw_spin_lock() The logic in do_raw_spin_lock() attempts to acquire a spinlock by invoking arch_spin_trylock() in a loop with a delay between each attempt. Now consider the following situation in a 2 CPU system: 1. CPU-0 continually acquires and releases a spinlock in a tight loop; it stays in this loop until some condition X is satisfied. X can only be satisfied by another CPU. 2. CPU-1 tries to acquire the same spinlock, in an attempt to satisfy the aforementioned condition X. However, it never sees the unlocked value of the lock because the debug spinlock code uses trylock instead of just lock; it checks at all the wrong moments - whenever CPU-0 has locked the lock. Now in the absence of debug spinlocks, the architecture specific spinlock code can correctly allow CPU-1 to wait in a "queue" (e.g., ticket spinlocks), ensuring that it acquires the lock at some point. However, with the debug spinlock code, livelock can easily occur due to the use of try_lock, which obviously cannot put the CPU in that "queue". This queueing mechanism is implemented in both x86 and ARM spinlock code. Note that the situation mentioned above is not hypothetical. A real problem was encountered where CPU-0 was running hrtimer_cancel with interrupts disabled, and CPU-1 was attempting to run the hrtimer that CPU-0 was trying to cancel. Address this by actually attempting arch_spin_lock once it is suspected that there is a spinlock lockup. If we're in a situation that is described above, the arch_spin_lock should succeed; otherwise other timeout mechanisms (e.g., watchdog) should alert the system of a lockup. Therefore, if there is a genuine system problem and the spinlock can't be acquired, the end result (irrespective of this change being present) is the same. If there is a livelock caused by the debug code, this change will allow the lock to be acquired, depending on the implementation of the lower level arch specific spinlock code. [akpm@linux-foundation.org: tweak comment] Signed-off-by: Vikram Mulukutla Cc: Thomas Gleixner Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/spinlock_debug.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) diff --git a/lib/spinlock_debug.c b/lib/spinlock_debug.c index eb10578ae05..0374a596cff 100644 --- a/lib/spinlock_debug.c +++ b/lib/spinlock_debug.c @@ -107,23 +107,27 @@ static void __spin_lock_debug(raw_spinlock_t *lock) { u64 i; u64 loops = loops_per_jiffy * HZ; - int print_once = 1; - for (;;) { - for (i = 0; i < loops; i++) { - if (arch_spin_trylock(&lock->raw_lock)) - return; - __delay(1); - } - /* lockup suspected: */ - if (print_once) { - print_once = 0; - spin_dump(lock, "lockup suspected"); + for (i = 0; i < loops; i++) { + if (arch_spin_trylock(&lock->raw_lock)) + return; + __delay(1); + } + /* lockup suspected: */ + spin_dump(lock, "lockup suspected"); #ifdef CONFIG_SMP - trigger_all_cpu_backtrace(); + trigger_all_cpu_backtrace(); #endif - } - } + + /* + * The trylock above was causing a livelock. Give the lower level arch + * specific lock code a chance to acquire the lock. We have already + * printed a warning/backtrace at this point. The non-debug arch + * specific code might actually succeed in acquiring the lock. If it is + * not successful, the end-result is the same - there is no forward + * progress. + */ + arch_spin_lock(&lock->raw_lock); } void do_raw_spin_lock(raw_spinlock_t *lock) -- 2.20.1