As of commit
f8567a3845ac05bb28f3c1b478ef752762bd39ef it is now possible to
have put_reqs_available() called from irq context. While put_reqs_available()
is per cpu, it did not protect itself from interrupts on the same CPU. This
lead to aio_complete() corrupting the available io requests count when run
under a heavy O_DIRECT workloads as reported by Robert Elliott. Fix this by
disabling irq updates around the per cpu batch updates of reqs_available.
Many thanks to Robert and folks for testing and tracking this down.
Reported-by: Robert Elliot <Elliott@hp.com>
Tested-by: Robert Elliot <Elliott@hp.com>
Signed-off-by: Benjamin LaHaise <bcrl@kvack.org>
Cc: Jens Axboe <axboe@kernel.dk>, Christoph Hellwig <hch@infradead.org>
Cc: stable@vger.kenel.org
static void put_reqs_available(struct kioctx *ctx, unsigned nr)
{
struct kioctx_cpu *kcpu;
+ unsigned long flags;
preempt_disable();
kcpu = this_cpu_ptr(ctx->cpu);
+ local_irq_save(flags);
kcpu->reqs_available += nr;
+
while (kcpu->reqs_available >= ctx->req_batch * 2) {
kcpu->reqs_available -= ctx->req_batch;
atomic_add(ctx->req_batch, &ctx->reqs_available);
}
+ local_irq_restore(flags);
preempt_enable();
}
{
struct kioctx_cpu *kcpu;
bool ret = false;
+ unsigned long flags;
preempt_disable();
kcpu = this_cpu_ptr(ctx->cpu);
+ local_irq_save(flags);
if (!kcpu->reqs_available) {
int old, avail = atomic_read(&ctx->reqs_available);
ret = true;
kcpu->reqs_available--;
out:
+ local_irq_restore(flags);
preempt_enable();
return ret;
}