On Thu, Jun 16, 2022 at 09:03:52AM +0100, John Garry wrote:
> On 15/06/2022 22:00, Bart Van Assche wrote:
> > This patch prevents that test nvme/004 triggers the following:
> >
> > UBSAN: array-index-out-of-bounds in block/blk-mq.h:135:9
> > index 512 is out of range for type 'long unsigned int [512]'
> > Call Trace:
> > show_stack+0x52/0x58
> > dump_stack_lvl+0x49/0x5e
> > dump_stack+0x10/0x12
> > ubsan_epilogue+0x9/0x3b
> > __ubsan_handle_out_of_bounds.cold+0x44/0x49
> > blk_mq_alloc_request_hctx+0x304/0x310
> > __nvme_submit_sync_cmd+0x70/0x200 [nvme_core]
> > nvmf_connect_io_queue+0x23e/0x2a0 [nvme_fabrics]
> > nvme_loop_connect_io_queues+0x8d/0xb0 [nvme_loop]
> > nvme_loop_create_ctrl+0x58e/0x7d0 [nvme_loop]
> > nvmf_create_ctrl+0x1d7/0x4d0 [nvme_fabrics]
> > nvmf_dev_write+0xae/0x111 [nvme_fabrics]
> > vfs_write+0x144/0x560
> > ksys_write+0xb7/0x140
> > __x64_sys_write+0x42/0x50
> > do_syscall_64+0x35/0x80
> > entry_SYSCALL_64_after_hwframe+0x44/0xae
> >
> > Cc: Christoph Hellwig <hch@xxxxxx>
> > Cc: Ming Lei <ming.lei@xxxxxxxxxx>
> > Fixes: 20e4d8139319 ("blk-mq: simplify queue mapping & schedule with each possisble CPU")
> > Signed-off-by: Bart Van Assche <bvanassche@xxxxxxx>
> > ---
> > block/blk-mq.c | 2 ++
> > 1 file changed, 2 insertions(+)
> >
> > diff --git a/block/blk-mq.c b/block/blk-mq.c
> > index 7a5558bbc7f6..1c09c6017ea9 100644
> > --- a/block/blk-mq.c
> > +++ b/block/blk-mq.c
> > @@ -579,6 +579,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
> > if (!blk_mq_hw_queue_mapped(data.hctx))
> > goto out_queue_exit;
> > cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask);
> > + if (cpu >= nr_cpu_ids)
> > + goto out_queue_exit;
>
> Ming, Did you give up on this:
>
> https://lore.kernel.org/linux-block/20210818144428.896216-1-ming.lei@xxxxxxxxxx/
Yeah, this approach has some big problem, see
https://lore.kernel.org/linux-block/20210722160654.GA8344@xxxxxx/#t
Thanks,
Ming
