From 8c9ebb735a1d9ec8d2cffcfdc39bb6b8fc2b056a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 10 Jul 2020 09:13:34 -0600 Subject: [PATCH 1709/2944] io_uring: account user memory freed when exit has been queued to #29276773 commit 309fc03a3284af62eb6082fb60327045a1dabf57 upstream. We currently account the memory after the exit work has been run, but that leaves a gap where a process has closed its ring and until the memory has been accounted as freed. If the memlocked ulimit is borderline, then that can introduce spurious setup errors returning -ENOMEM because the free work hasn't been run yet. Account this as freed when we close the ring, as not to expose a tiny gap where setting up a new ring can fail. Fixes: 85faa7b8346e ("io_uring: punt final io_ring_ctx wait-and-free to workqueue") Cc: stable@vger.kernel.org # v5.7 Signed-off-by: Jens Axboe Signed-off-by: Jiufei Xue Reviewed-by: Joseph Qi --- fs/io_uring.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 69a53c9..b652e7f 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -7290,9 +7290,6 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) io_mem_free(ctx->sq_sqes); percpu_ref_exit(&ctx->refs); - if (ctx->account_mem) - io_unaccount_mem(ctx->user, - ring_pages(ctx->sq_entries, ctx->cq_entries)); free_uid(ctx->user); put_cred(ctx->creds); kfree(ctx->cancel_hash); @@ -7377,6 +7374,16 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) if (ctx->rings) io_cqring_overflow_flush(ctx, true); idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx); + + /* + * Do this upfront, so we won't have a grace period where the ring + * is closed but resources aren't reaped yet. This can cause + * spurious failure in setting up a new ring. + */ + if (ctx->account_mem) + io_unaccount_mem(ctx->user, + ring_pages(ctx->sq_entries, ctx->cq_entries)); + INIT_WORK(&ctx->exit_work, io_ring_exit_work); queue_work(system_wq, &ctx->exit_work); } -- 1.8.3.1