The number of outstanding kiocbs is one of the few shared things left that
has to be touched for every kiocb - it'd be nice to make it percpu.
We can make it per cpu by treating it like an allocation problem: we have
a maximum number of kiocbs that can be outstanding (i.e. slots) - then we
just allocate and free slots, and we know how to write per cpu allocators.
So as prep work for that, we convert reqs_active to reqs_available.
Signed-off-by: Kent Overstreet <koverstreet@xxxxxxxxxx>
Cc: Zach Brown <zab@xxxxxxxxxx>
Cc: Felipe Balbi <balbi@xxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: Mark Fasheh <mfasheh@xxxxxxxx>
Cc: Joel Becker <jlbec@xxxxxxxxxxxx>
Cc: Rusty Russell <rusty@xxxxxxxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Asai Thambi S P <asamymuthupa@xxxxxxxxxx>
Cc: Selvan Mani <smani@xxxxxxxxxx>
Cc: Sam Bradshaw <sbradshaw@xxxxxxxxxx>
Cc: Jeff Moyer <jmoyer@xxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Benjamin LaHaise <bcrl@xxxxxxxxx>
Reviewed-by: "Theodore Ts'o" <tytso@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/aio.c | 35 ++++++++++++++++++++---------------
1 file changed, 20 insertions(+), 15 deletions(-)
diff --git a/fs/aio.c b/fs/aio.c
index fe794af..bde41c1 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -89,7 +89,13 @@ struct kioctx {
struct work_struct rcu_work;
struct {
- atomic_t reqs_active;
+ /*
+ * This counts the number of available slots in the ringbuffer,
+ * so we avoid overflowing it: it's decremented (if positive)
+ * when allocating a kiocb and incremented when the resulting
+ * io_event is pulled off the ringbuffer.
+ */
+ atomic_t reqs_available;
} ____cacheline_aligned_in_smp;
struct {
@@ -306,19 +312,19 @@ static void free_ioctx(struct kioctx *ctx)
head = ring->head;
kunmap_atomic(ring);
- while (atomic_read(&ctx->reqs_active) > 0) {
+ while (atomic_read(&ctx->reqs_available) < ctx->nr_events - 1) {
wait_event(ctx->wait,
(head != ctx->tail) ||
- (atomic_read(&ctx->reqs_active) <= 0);
+ (atomic_read(&ctx->reqs_available) >= ctx->nr_events - 1));
avail = (head <= ctx->tail ? ctx->tail : ctx->nr_events) - head;
- atomic_sub(avail, &ctx->reqs_active);
+ atomic_add(avail, &ctx->reqs_available);
head += avail;
head %= ctx->nr_events;
}
- WARN_ON(atomic_read(&ctx->reqs_active) < 0);
+ WARN_ON(atomic_read(&ctx->reqs_available) > ctx->nr_events - 1);
aio_free_ring(ctx);
@@ -382,6 +388,8 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
if (aio_setup_ring(ctx) < 0)
goto out_freectx;
+ atomic_set(&ctx->reqs_available, ctx->nr_events - 1);
+
/* limit the number of system wide aios */
spin_lock(&aio_nr_lock);
if (aio_nr + nr_events > aio_max_nr ||
@@ -484,7 +492,7 @@ void exit_aio(struct mm_struct *mm)
"exit_aio:ioctx still alive: %d %d %d\n",
atomic_read(&ctx->users),
atomic_read(&ctx->dead),
- atomic_read(&ctx->reqs_active));
+ atomic_read(&ctx->reqs_available));
/*
* We don't need to bother with munmap() here -
* exit_mmap(mm) is coming and it'll unmap everything.
@@ -516,12 +524,9 @@ static inline struct kiocb *aio_get_req(struct kioctx *ctx)
{
struct kiocb *req;
- if (atomic_read(&ctx->reqs_active) >= ctx->nr_events)
+ if (atomic_dec_if_positive(&ctx->reqs_available) <= 0)
return NULL;
- if (atomic_inc_return(&ctx->reqs_active) > ctx->nr_events - 1)
- goto out_put;
-
req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL|__GFP_ZERO);
if (unlikely(!req))
goto out_put;
@@ -531,7 +536,7 @@ static inline struct kiocb *aio_get_req(struct kioctx *ctx)
return req;
out_put:
- atomic_dec(&ctx->reqs_active);
+ atomic_inc(&ctx->reqs_available);
return NULL;
}
@@ -602,7 +607,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
/*
* Take rcu_read_lock() in case the kioctx is being destroyed, as we
- * need to issue a wakeup after decrementing reqs_active.
+ * need to issue a wakeup after incrementing reqs_available.
*/
rcu_read_lock();
@@ -620,7 +625,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
*/
if (unlikely(xchg(&iocb->ki_cancel,
KIOCB_CANCELLED) == KIOCB_CANCELLED)) {
- atomic_dec(&ctx->reqs_active);
+ atomic_inc(&ctx->reqs_available);
/* Still need the wake_up in case free_ioctx is waiting */
goto put_rq;
}
@@ -758,7 +763,7 @@ static long aio_read_events_ring(struct kioctx *ctx,
pr_debug("%li h%u t%u\n", ret, head, ctx->tail);
- atomic_sub(ret, &ctx->reqs_active);
+ atomic_add(ret, &ctx->reqs_available);
out:
mutex_unlock(&ctx->ring_lock);
@@ -1142,7 +1147,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
aio_put_req(req); /* drop extra ref to req */
return 0;
out_put_req:
- atomic_dec(&ctx->reqs_active);
+ atomic_inc(&ctx->reqs_available);
aio_put_req(req); /* drop extra ref to req */
aio_put_req(req); /* drop i/o ref to req */
return ret;
--
1.8.2.1
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
