io_uring: avoid page allocation warnings [Linux 5.1]

io_uring: avoid page allocation warnings [Linux 5.1]

This Linux kernel change "io_uring: avoid page allocation warnings" is included in the Linux 5.1 release. This change is authored by Mark Rutland <mark.rutland [at]> on Wed May 1 16:59:16 2019 +0100. The commit for this change in Linux stable tree is d4ef647 (patch).

io_uring: avoid page allocation warnings

In io_sqe_buffer_register() we allocate a number of arrays based on the
iov_len from the user-provided iov. While we limit iov_len to SZ_1G,
we can still attempt to allocate arrays exceeding MAX_ORDER.

On a 64-bit system with 4KiB pages, for an iov where iov_base = 0x10 and
iov_len = SZ_1G, we'll calculate that nr_pages = 262145. When we try to
allocate a corresponding array of (16-byte) bio_vecs, requiring 4194320
bytes, which is greater than 4MiB. This results in SLUB warning that
we're trying to allocate greater than MAX_ORDER, and failing the

Avoid this by using kvmalloc() for allocations dependent on the
user-provided iov_len. At the same time, fix a leak of imu->bvec when
registration fails.

Full splat from before this patch:

WARNING: CPU: 1 PID: 2314 at mm/page_alloc.c:4595 __alloc_pages_nodemask+0x7ac/0x2938 mm/page_alloc.c:4595
Kernel panic - not syncing: panic_on_warn set ...
CPU: 1 PID: 2314 Comm: syz-executor326 Not tainted 5.1.0-rc7-dirty #4
Hardware name: linux,dummy-virt (DT)
Call trace:
 dump_backtrace+0x0/0x2f0 include/linux/compiler.h:193
 show_stack+0x20/0x30 arch/arm64/kernel/traps.c:158
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x110/0x190 lib/dump_stack.c:113
 panic+0x384/0x68c kernel/panic.c:214
 __warn+0x2bc/0x2c0 kernel/panic.c:571
 report_bug+0x228/0x2d8 lib/bug.c:186
 bug_handler+0xa0/0x1a0 arch/arm64/kernel/traps.c:956
 call_break_hook arch/arm64/kernel/debug-monitors.c:301 [inline]
 brk_handler+0x1d4/0x388 arch/arm64/kernel/debug-monitors.c:316
 do_debug_exception+0x1a0/0x468 arch/arm64/mm/fault.c:831
 __alloc_pages_nodemask+0x7ac/0x2938 mm/page_alloc.c:4595
 alloc_pages_current+0x164/0x278 mm/mempolicy.c:2132
 alloc_pages include/linux/gfp.h:509 [inline]
 kmalloc_order+0x20/0x50 mm/slab_common.c:1231
 kmalloc_order_trace+0x30/0x2b0 mm/slab_common.c:1243
 kmalloc_large include/linux/slab.h:480 [inline]
 __kmalloc+0x3dc/0x4f0 mm/slub.c:3791
 kmalloc_array include/linux/slab.h:670 [inline]
 io_sqe_buffer_register fs/io_uring.c:2472 [inline]
 __io_uring_register fs/io_uring.c:2962 [inline]
 __do_sys_io_uring_register fs/io_uring.c:3008 [inline]
 __se_sys_io_uring_register fs/io_uring.c:2990 [inline]
 __arm64_sys_io_uring_register+0x9e0/0x1bc8 fs/io_uring.c:2990
 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline]
 invoke_syscall arch/arm64/kernel/syscall.c:47 [inline]
 el0_svc_common.constprop.0+0x148/0x2e0 arch/arm64/kernel/syscall.c:83
 el0_svc_handler+0xdc/0x100 arch/arm64/kernel/syscall.c:129
 el0_svc+0x8/0xc arch/arm64/kernel/entry.S:948
SMP: stopping secondary CPUs
Dumping ftrace buffer:
   (ftrace buffer empty)
Kernel Offset: disabled
CPU features: 0x002,23000438
Memory Limit: none
Rebooting in 1 seconds..

Fixes: edafccee56ff3167 ("io_uring: add support for pre-mapped user IO buffers")
Signed-off-by: Mark Rutland <>
Cc: Alexander Viro <>
Cc: Jens Axboe <>
Signed-off-by: Jens Axboe <>

There are 17 lines of Linux source code added/deleted in this change. Code changes to Linux kernel are as follows.

 fs/io_uring.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 18cecb6..84efb89 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2443,7 +2443,7 @@ static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx)

        if (ctx->account_mem)
            io_unaccount_mem(ctx->user, imu->nr_bvecs);
-       kfree(imu->bvec);
+       kvfree(imu->bvec);
        imu->nr_bvecs = 0;

@@ -2535,9 +2535,9 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
        if (!pages || nr_pages > got_pages) {
-           pages = kmalloc_array(nr_pages, sizeof(struct page *),
+           pages = kvmalloc_array(nr_pages, sizeof(struct page *),
-           vmas = kmalloc_array(nr_pages,
+           vmas = kvmalloc_array(nr_pages,
                    sizeof(struct vm_area_struct *),
            if (!pages || !vmas) {
@@ -2549,7 +2549,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
            got_pages = nr_pages;

-       imu->bvec = kmalloc_array(nr_pages, sizeof(struct bio_vec),
+       imu->bvec = kvmalloc_array(nr_pages, sizeof(struct bio_vec),
        ret = -ENOMEM;
        if (!imu->bvec) {
@@ -2588,6 +2588,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
            if (ctx->account_mem)
                io_unaccount_mem(ctx->user, nr_pages);
+           kvfree(imu->bvec);
            goto err;

@@ -2610,12 +2611,12 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,

-   kfree(pages);
-   kfree(vmas);
+   kvfree(pages);
+   kvfree(vmas);
    return 0;
-   kfree(pages);
-   kfree(vmas);
+   kvfree(pages);
+   kvfree(vmas);
    return ret;

Leave a Reply

Your email address will not be published. Required fields are marked *