diff options
| author | Tony Battersby <tonyb@cybernetics.com> | 2015-02-13 12:10:58 -0500 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2015-03-06 14:57:31 -0800 |
| commit | e1ed769da5d4910885850a104d910d0495738d71 (patch) | |
| tree | 9a0a901986ce492c52848e7a50ed40e83734cd42 /drivers | |
| parent | 09c2814bd63d096180729ade91238b12f975e32f (diff) | |
| download | linux-stable-e1ed769da5d4910885850a104d910d0495738d71.tar.gz linux-stable-e1ed769da5d4910885850a104d910d0495738d71.tar.bz2 linux-stable-e1ed769da5d4910885850a104d910d0495738d71.zip | |
sg: fix EWOULDBLOCK errors with scsi-mq
commit 7772855a996ec6e16944b120ab5ce21050279821 upstream.
With scsi-mq enabled, userspace programs can get unexpected EWOULDBLOCK
(a.k.a. EAGAIN) errors when submitting commands to the SCSI generic
driver. Fix by calling blk_get_request() with GFP_KERNEL instead of
GFP_ATOMIC.
Note: to avoid introducing a potential deadlock, this patch should be
applied after the patch titled "sg: fix unkillable I/O wait deadlock
with scsi-mq".
Signed-off-by: Tony Battersby <tonyb@cybernetics.com>
Acked-by: Douglas Gilbert <dgilbert@interlog.com>
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'drivers')
| -rw-r--r-- | drivers/scsi/sg.c | 17 |
1 files changed, 16 insertions, 1 deletions
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 57178eda815d..763bffe23517 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1695,7 +1695,22 @@ sg_start_req(Sg_request *srp, unsigned char *cmd) return -ENOMEM; } - rq = blk_get_request(q, rw, GFP_ATOMIC); + /* + * NOTE + * + * With scsi-mq enabled, there are a fixed number of preallocated + * requests equal in number to shost->can_queue. If all of the + * preallocated requests are already in use, then using GFP_ATOMIC with + * blk_get_request() will return -EWOULDBLOCK, whereas using GFP_KERNEL + * will cause blk_get_request() to sleep until an active command + * completes, freeing up a request. Neither option is ideal, but + * GFP_KERNEL is the better choice to prevent userspace from getting an + * unexpected EWOULDBLOCK. + * + * With scsi-mq disabled, blk_get_request() with GFP_KERNEL usually + * does not sleep except under memory pressure. + */ + rq = blk_get_request(q, rw, GFP_KERNEL); if (IS_ERR(rq)) { kfree(long_cmdp); return PTR_ERR(rq); |