scsi: ->queue_rq can't sleep

[ Upstream commit 70a0f2c1898c6abf53670e55642b6e840b003892 ]

The blk-mq ->queue_rq method is always called from process context,
but might have preemption disabled.  This means we still always
have to use GFP_ATOMIC for memory allocations, and thus need to
revert part of commit 3c356bde1 ("scsi: stop passing a gfp_mask
argument down the command setup path").

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Tested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index a11837054d6c880a4e6369158ca13ae8a5f31286..0d5c218b7ad1605c4a702acca63a4930e4470d88 100644 (file)
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -616,7 +616,7 @@ static int scsi_alloc_sgtable(struct scsi_data_buffer *sdb, int nents,
        }
 
        ret = __sg_alloc_table(&sdb->table, nents, SCSI_MAX_SG_SEGMENTS,
-                              first_chunk, gfp_mask, scsi_sg_alloc);
+                              first_chunk, GFP_ATOMIC, scsi_sg_alloc);
        if (unlikely(ret))
                scsi_free_sgtable(sdb, mq);
        return ret;