summaryrefslogtreecommitdiff
path: root/drivers/scsi/cxlflash
diff options
context:
space:
mode:
authorManoj Kumar <manoj@linux.vnet.ibm.com>2015-12-14 15:07:02 -0600
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2016-09-15 08:27:41 +0200
commit284555fc7f5d2d4aab34dbf2b5766c6f8da84873 (patch)
tree98456e2409d19f89c51d1cc77631a092fada4b0c /drivers/scsi/cxlflash
parente66e0a249d9dacb9fda4135d0e38ba8ae9af9cac (diff)
cxlflash: Fix to resolve cmd leak after host reset
[ Upstream commit ee91e332a6e6e9b939f60f6e1bd72fb2def5290d ] After a few iterations of resetting the card, either during EEH recovery, or a host_reset the following is seen in the logs. cxlflash 0008:00: cxlflash_queuecommand: could not get a free command At every reset of the card, the commands that are outstanding are being leaked. No effort is being made to reap these commands. A few more resets later, the above error message floods the logs and the card is rendered totally unusable as no free commands are available. Iterated through the 'cmd' queue and printed out the 'free' counter and found that on each reset certain commands were in-use and stayed in-use through subsequent resets. To resolve this issue, when the card is reset, reap all the commands that are active/outstanding. Signed-off-by: Manoj N. Kumar <manoj@linux.vnet.ibm.com> Acked-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Sasha Levin <alexander.levin@verizon.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'drivers/scsi/cxlflash')
-rw-r--r--drivers/scsi/cxlflash/main.c19
1 files changed, 17 insertions, 2 deletions
diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c
index 1e5bf0ca81da..3fb0e1ca6809 100644
--- a/drivers/scsi/cxlflash/main.c
+++ b/drivers/scsi/cxlflash/main.c
@@ -632,15 +632,30 @@ static void free_mem(struct cxlflash_cfg *cfg)
* @cfg: Internal structure associated with the host.
*
* Safe to call with AFU in a partially allocated/initialized state.
+ *
+ * Cleans up all state associated with the command queue, and unmaps
+ * the MMIO space.
+ *
+ * - complete() will take care of commands we initiated (they'll be checked
+ * in as part of the cleanup that occurs after the completion)
+ *
+ * - cmd_checkin() will take care of entries that we did not initiate and that
+ * have not (and will not) complete because they are sitting on a [now stale]
+ * hardware queue
*/
static void stop_afu(struct cxlflash_cfg *cfg)
{
int i;
struct afu *afu = cfg->afu;
+ struct afu_cmd *cmd;
if (likely(afu)) {
- for (i = 0; i < CXLFLASH_NUM_CMDS; i++)
- complete(&afu->cmd[i].cevent);
+ for (i = 0; i < CXLFLASH_NUM_CMDS; i++) {
+ cmd = &afu->cmd[i];
+ complete(&cmd->cevent);
+ if (!atomic_read(&cmd->free))
+ cmd_checkin(cmd);
+ }
if (likely(afu->afu_map)) {
cxl_psa_unmap((void __iomem *)afu->afu_map);