On Wed, Jan 09, 2019 at 09:57:59AM -0700, Jens Axboe wrote:
> On 1/9/19 5:13 AM, Christoph Hellwig wrote:
> >> + if (!state)
> >> + req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL);
> >
> > Just return an error here if kmem_cache_alloc fails.
> >
> >> + if (req)
> >> + io_req_init(ctx, req);
> >
> > Because all the other ones can't reached this with a NULL req.
>
> This is different in the current tree, since I properly fixed the
> ctx ref issue.
Your tree does a percpu_ref_tryget very first, and then leaks that if
kmem_cache_alloc_bulk fails, and also is inconsistent for NULL vs
ERR_PTR returns. I think you want something like this on top:
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 35d055dcbc22..6c95749e9601 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -250,14 +250,6 @@ static struct io_uring_event *io_peek_cqring(struct
io_ring_ctx *ctx)
return &ring->events[tail & ctx->cq_ring.ring_mask];
}
-static bool io_req_init(struct io_ring_ctx *ctx, struct io_kiocb *req)
-{
- req->ki_ctx = ctx;
- INIT_LIST_HEAD(&req->ki_list);
- req->ki_flags = 0;
- return true;
-}
-
static void io_ring_drop_ctx_ref(struct io_ring_ctx *ctx, unsigned refs)
{
percpu_ref_put_many(&ctx->refs, refs);
@@ -274,9 +266,11 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
if (!percpu_ref_tryget(&ctx->refs))
return NULL;
- if (!state)
+ if (!state) {
req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL);
- else if (!state->free_iocbs) {
+ if (!req)
+ goto out_drop_ref;
+ } else if (!state->free_iocbs) {
size_t size;
int ret;
@@ -284,7 +278,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
ret = kmem_cache_alloc_bulk(kiocb_cachep, GFP_KERNEL, size,
state->iocbs);
if (ret <= 0)
- return ERR_PTR(-ENOMEM);
+ goto out_drop_ref;
state->free_iocbs = ret - 1;
state->cur_iocb = 1;
req = state->iocbs[0];
@@ -294,11 +288,11 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx
*ctx,
state->cur_iocb++;
}
- if (req) {
- io_req_init(ctx, req);
- return req;
- }
+ req->ki_ctx = ctx;
+ req->ki_flags = 0;
+ return req;
+out_drop_ref:
io_ring_drop_ctx_ref(ctx, 1);
return NULL;
}