This is a note to let you know that I've just added the patch titled
scsi: hisi_sas: Prevent parallel FLR and controller reset
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
scsi-hisi_sas-prevent-parallel-flr-and-controller-re.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 8dc18255f53f0bcaa39174b78e4e1502b42a7fbd
Author: Qi Liu <liuqi115@xxxxxxxxxx>
Date: Wed Dec 15 22:37:39 2021 +0800
scsi: hisi_sas: Prevent parallel FLR and controller reset
[ Upstream commit 16775db613c2bdea09705dcb876942c0641a1098 ]
If we issue a controller reset command during executing a FLR a hung task
may be found:
Call trace:
__switch_to+0x158/0x1cc
__schedule+0x2e8/0x85c
schedule+0x7c/0x110
schedule_timeout+0x190/0x1cc
__down+0x7c/0xd4
down+0x5c/0x7c
hisi_sas_task_exec+0x510/0x680 [hisi_sas_main]
hisi_sas_queue_command+0x24/0x30 [hisi_sas_main]
smp_execute_task_sg+0xf4/0x23c [libsas]
sas_smp_phy_control+0x110/0x1e0 [libsas]
transport_sas_phy_reset+0xc8/0x190 [libsas]
phy_reset_work+0x2c/0x40 [libsas]
process_one_work+0x1dc/0x48c
worker_thread+0x15c/0x464
kthread+0x160/0x170
ret_from_fork+0x10/0x18
This is a race condition which occurs when the FLR completes first.
Here the host HISI_SAS_RESETTING_BIT flag out gets of sync as
HISI_SAS_RESETTING_BIT is not always cleared with the hisi_hba.sem held, so
now only set/unset HISI_SAS_RESETTING_BIT under hisi_hba.sem .
Link: https://lore.kernel.org/r/1639579061-179473-7-git-send-email-john.garry@xxxxxxxxxx
Signed-off-by: Qi Liu <liuqi115@xxxxxxxxxx>
Signed-off-by: John Garry <john.garry@xxxxxxxxxx>
Signed-off-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx>
Stable-dep-of: d34ee535705e ("scsi: hisi_sas: Replace with standard error code return value")
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 7744594cd3e3..19081790f011 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1548,7 +1548,6 @@ void hisi_sas_controller_reset_prepare(struct hisi_hba *hisi_hba)
{
struct Scsi_Host *shost = hisi_hba->shost;
- down(&hisi_hba->sem);
hisi_hba->phy_state = hisi_hba->hw->get_phys_state(hisi_hba);
scsi_block_requests(shost);
@@ -1574,9 +1573,9 @@ void hisi_sas_controller_reset_done(struct hisi_hba *hisi_hba)
if (hisi_hba->reject_stp_links_msk)
hisi_sas_terminate_stp_reject(hisi_hba);
hisi_sas_reset_init_all_devices(hisi_hba);
- up(&hisi_hba->sem);
scsi_unblock_requests(shost);
clear_bit(HISI_SAS_RESETTING_BIT, &hisi_hba->flags);
+ up(&hisi_hba->sem);
hisi_sas_rescan_topology(hisi_hba, hisi_hba->phy_state);
}
@@ -1587,8 +1586,11 @@ static int hisi_sas_controller_prereset(struct hisi_hba *hisi_hba)
if (!hisi_hba->hw->soft_reset)
return -1;
- if (test_and_set_bit(HISI_SAS_RESETTING_BIT, &hisi_hba->flags))
+ down(&hisi_hba->sem);
+ if (test_and_set_bit(HISI_SAS_RESETTING_BIT, &hisi_hba->flags)) {
+ up(&hisi_hba->sem);
return -1;
+ }
if (hisi_sas_debugfs_enable && hisi_hba->debugfs_itct[0].itct)
hisi_hba->hw->debugfs_snapshot_regs(hisi_hba);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 2ed787956fa8..0e57381121d5 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -4935,6 +4935,7 @@ static void hisi_sas_reset_prepare_v3_hw(struct pci_dev *pdev)
int rc;
dev_info(dev, "FLR prepare\n");
+ down(&hisi_hba->sem);
set_bit(HISI_SAS_RESETTING_BIT, &hisi_hba->flags);
hisi_sas_controller_reset_prepare(hisi_hba);
