From 6d5f904904608a9cd32854d7d0a4dd65b27f9935 Mon Sep 17 00:00:00 2001 From: Xiaoguang Wang Date: Thu, 9 Jul 2020 09:15:29 +0800 Subject: [PATCH 1/4] io_uring: export cq overflow status to userspace For those applications which are not willing to use io_uring_enter() to reap and handle cqes, they may completely rely on liburing's io_uring_peek_cqe(), but if cq ring has overflowed, currently because io_uring_peek_cqe() is not aware of this overflow, it won't enter kernel to flush cqes, below test program can reveal this bug: static void test_cq_overflow(struct io_uring *ring) { struct io_uring_cqe *cqe; struct io_uring_sqe *sqe; int issued = 0; int ret = 0; do { sqe = io_uring_get_sqe(ring); if (!sqe) { fprintf(stderr, "get sqe failed\n"); break;; } ret = io_uring_submit(ring); if (ret <= 0) { if (ret != -EBUSY) fprintf(stderr, "sqe submit failed: %d\n", ret); break; } issued++; } while (ret > 0); assert(ret == -EBUSY); printf("issued requests: %d\n", issued); while (issued) { ret = io_uring_peek_cqe(ring, &cqe); if (ret) { if (ret != -EAGAIN) { fprintf(stderr, "peek completion failed: %s\n", strerror(ret)); break; } printf("left requets: %d\n", issued); continue; } io_uring_cqe_seen(ring, cqe); issued--; printf("left requets: %d\n", issued); } } int main(int argc, char *argv[]) { int ret; struct io_uring ring; ret = io_uring_queue_init(16, &ring, 0); if (ret) { fprintf(stderr, "ring setup failed: %d\n", ret); return 1; } test_cq_overflow(&ring); return 0; } To fix this issue, export cq overflow status to userspace by adding new IORING_SQ_CQ_OVERFLOW flag, then helper functions() in liburing, such as io_uring_peek_cqe, can be aware of this cq overflow and do flush accordingly. Signed-off-by: Xiaoguang Wang Signed-off-by: Jens Axboe --- fs/io_uring.c | 11 +++++++++-- include/uapi/linux/io_uring.h | 1 + 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index d37d7ea5ebe5..32e37c38f274 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1274,6 +1274,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) if (cqe) { clear_bit(0, &ctx->sq_check_overflow); clear_bit(0, &ctx->cq_check_overflow); + ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW; } spin_unlock_irqrestore(&ctx->completion_lock, flags); io_cqring_ev_posted(ctx); @@ -1311,6 +1312,7 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags) if (list_empty(&ctx->cq_overflow_list)) { set_bit(0, &ctx->sq_check_overflow); set_bit(0, &ctx->cq_check_overflow); + ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW; } req->flags |= REQ_F_OVERFLOW; refcount_inc(&req->refs); @@ -6080,9 +6082,9 @@ static int io_sq_thread(void *data) } /* Tell userspace we may need a wakeup call */ + spin_lock_irq(&ctx->completion_lock); ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP; - /* make sure to read SQ tail after writing flags */ - smp_mb(); + spin_unlock_irq(&ctx->completion_lock); to_submit = io_sqring_entries(ctx); if (!to_submit || ret == -EBUSY) { @@ -6100,13 +6102,17 @@ static int io_sq_thread(void *data) schedule(); finish_wait(&ctx->sqo_wait, &wait); + spin_lock_irq(&ctx->completion_lock); ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP; + spin_unlock_irq(&ctx->completion_lock); ret = 0; continue; } finish_wait(&ctx->sqo_wait, &wait); + spin_lock_irq(&ctx->completion_lock); ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP; + spin_unlock_irq(&ctx->completion_lock); } mutex_lock(&ctx->uring_lock); @@ -7488,6 +7494,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, if (list_empty(&ctx->cq_overflow_list)) { clear_bit(0, &ctx->sq_check_overflow); clear_bit(0, &ctx->cq_check_overflow); + ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW; } spin_unlock_irq(&ctx->completion_lock); diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 92c22699a5a7..7843742b8b74 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -197,6 +197,7 @@ struct io_sqring_offsets { * sq_ring->flags */ #define IORING_SQ_NEED_WAKEUP (1U << 0) /* needs io_uring_enter wakeup */ +#define IORING_SQ_CQ_OVERFLOW (1U << 1) /* CQ ring is overflown */ struct io_cqring_offsets { __u32 head; From f3bd9dae3708a0ff6b067e766073ffeb853301f9 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 9 Jul 2020 10:11:41 +0000 Subject: [PATCH 2/4] io_uring: fix memleak in __io_sqe_files_update() I got a memleak report when doing some fuzz test: BUG: memory leak unreferenced object 0xffff888113e02300 (size 488): comm "syz-executor401", pid 356, jiffies 4294809529 (age 11.954s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ a0 a4 ce 19 81 88 ff ff 60 ce 09 0d 81 88 ff ff ........`....... backtrace: [<00000000129a84ec>] kmem_cache_zalloc include/linux/slab.h:659 [inline] [<00000000129a84ec>] __alloc_file+0x25/0x310 fs/file_table.c:101 [<000000003050ad84>] alloc_empty_file+0x4f/0x120 fs/file_table.c:151 [<000000004d0a41a3>] alloc_file+0x5e/0x550 fs/file_table.c:193 [<000000002cb242f0>] alloc_file_pseudo+0x16a/0x240 fs/file_table.c:233 [<00000000046a4baa>] anon_inode_getfile fs/anon_inodes.c:91 [inline] [<00000000046a4baa>] anon_inode_getfile+0xac/0x1c0 fs/anon_inodes.c:74 [<0000000035beb745>] __do_sys_perf_event_open+0xd4a/0x2680 kernel/events/core.c:11720 [<0000000049009dc7>] do_syscall_64+0x56/0xa0 arch/x86/entry/common.c:359 [<00000000353731ca>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 BUG: memory leak unreferenced object 0xffff8881152dd5e0 (size 16): comm "syz-executor401", pid 356, jiffies 4294809529 (age 11.954s) hex dump (first 16 bytes): 01 00 00 00 01 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<0000000074caa794>] kmem_cache_zalloc include/linux/slab.h:659 [inline] [<0000000074caa794>] lsm_file_alloc security/security.c:567 [inline] [<0000000074caa794>] security_file_alloc+0x32/0x160 security/security.c:1440 [<00000000c6745ea3>] __alloc_file+0xba/0x310 fs/file_table.c:106 [<000000003050ad84>] alloc_empty_file+0x4f/0x120 fs/file_table.c:151 [<000000004d0a41a3>] alloc_file+0x5e/0x550 fs/file_table.c:193 [<000000002cb242f0>] alloc_file_pseudo+0x16a/0x240 fs/file_table.c:233 [<00000000046a4baa>] anon_inode_getfile fs/anon_inodes.c:91 [inline] [<00000000046a4baa>] anon_inode_getfile+0xac/0x1c0 fs/anon_inodes.c:74 [<0000000035beb745>] __do_sys_perf_event_open+0xd4a/0x2680 kernel/events/core.c:11720 [<0000000049009dc7>] do_syscall_64+0x56/0xa0 arch/x86/entry/common.c:359 [<00000000353731ca>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 If io_sqe_file_register() failed, we need put the file that get by fget() to avoid the memleak. Fixes: c3a31e605620 ("io_uring: add support for IORING_REGISTER_FILES_UPDATE") Cc: stable@vger.kernel.org Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Signed-off-by: Jens Axboe --- fs/io_uring.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 32e37c38f274..a9ce2e6f03dd 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6851,8 +6851,10 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, } table->files[index] = file; err = io_sqe_file_register(ctx, file, i); - if (err) + if (err) { + fput(file); break; + } } nr_args--; done++; From 667e57da358f61b6966e12e925a69e42d912e8bb Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 10 Jul 2020 14:14:20 +0000 Subject: [PATCH 3/4] io_uring: fix memleak in io_sqe_files_register() I got a memleak report when doing some fuzz test: BUG: memory leak unreferenced object 0x607eeac06e78 (size 8): comm "test", pid 295, jiffies 4294735835 (age 31.745s) hex dump (first 8 bytes): 00 00 00 00 00 00 00 00 ........ backtrace: [<00000000932632e6>] percpu_ref_init+0x2a/0x1b0 [<0000000092ddb796>] __io_uring_register+0x111d/0x22a0 [<00000000eadd6c77>] __x64_sys_io_uring_register+0x17b/0x480 [<00000000591b89a6>] do_syscall_64+0x56/0xa0 [<00000000864a281d>] entry_SYSCALL_64_after_hwframe+0x44/0xa9 Call percpu_ref_exit() on error path to avoid refcount memleak. Fixes: 05f3fb3c5397 ("io_uring: avoid ring quiesce for fixed file set unregister and update") Cc: stable@vger.kernel.org Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Signed-off-by: Jens Axboe --- fs/io_uring.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/io_uring.c b/fs/io_uring.c index a9ce2e6f03dd..fc07baf4392a 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6699,6 +6699,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, for (i = 0; i < nr_tables; i++) kfree(ctx->file_data->table[i].files); + percpu_ref_exit(&ctx->file_data->refs); kfree(ctx->file_data->table); kfree(ctx->file_data); ctx->file_data = NULL; From 309fc03a3284af62eb6082fb60327045a1dabf57 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 10 Jul 2020 09:13:34 -0600 Subject: [PATCH 4/4] io_uring: account user memory freed when exit has been queued 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 --- 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 fc07baf4392a..ca8abde48b6c 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -7351,9 +7351,6 @@ 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); @@ -7438,6 +7435,16 @@ 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); }