[PATCH v3] scsi: core: pair EH runtime PM get and put

[Hongjie Fang]

shost->eh_noresume is currently consulted twice in one error handling
iteration: once before scsi_autopm_get_host() and once again before
scsi_autopm_put_host().

That is racy when a PM-triggered error path flips shost->eh_noresume while
the SCSI EH thread is still running.

The problem flow looks like this:
PM path
  ufshcd_set_dev_pwr_mode()
    shost->eh_noresume = 1
    ufshcd_execute_start_stop  <-- trigger EH
    ...
    shost->eh_noresume = 0

EH path
  scsi_error_handler()
    if (!shost->eh_noresume)
      scsi_autopm_get_host()  <-- skipped
    ...
    if (!shost->eh_noresume)
       scsi_autopm_put_host()  <-- executed later

In that case one EH iteration can skip autoresume on entry and still drop
a runtime PM reference on exit. That leaves an unmatched runtime PM put
and can trigger a runtime PM usage count underflow.

Fix this by making eh_noresume a regular bool so it can be accessed with
READ_ONCE() and WRITE_ONCE(). Snapshot it once per EH iteration and use
that snapshot for both runtime PM get and put decisions.

Fixes: ae0751ffc77e ("[SCSI] add flag to skip the runtime PM calls on the host")
Signed-off-by: Hongjie Fang <hongjiefang@xxxxxxxxxxxx>
---

v3:
- Use READ_ONCE() and WRITE_ONCE() for eh_noresume.
- Make eh_noresume a regular bool since READ_ONCE() cannot be used on
  bitfields.

v2:
- Snapshot the shost->eh_noresume once per EH iteration.

 drivers/scsi/scsi_error.c | 6 ++++--
 drivers/ufs/core/ufshcd.c | 4 ++--
 include/scsi/scsi_host.h  | 6 +++---
 3 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 147127fb4db9..72515fa6daf7 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -2342,6 +2342,7 @@ static void scsi_unjam_host(struct Scsi_Host *shost)
 int scsi_error_handler(void *data)
 {
 	struct Scsi_Host *shost = data;
+	bool eh_noresume;
 
 	/*
 	 * We use TASK_INTERRUPTIBLE so that the thread is not
@@ -2383,7 +2384,8 @@ int scsi_error_handler(void *data)
 		 * what we need to do to get it up and online again (if we can).
 		 * If we fail, we end up taking the thing offline.
 		 */
-		if (!shost->eh_noresume && scsi_autopm_get_host(shost) != 0) {
+		eh_noresume = READ_ONCE(shost->eh_noresume);
+		if (!eh_noresume && scsi_autopm_get_host(shost) != 0) {
 			SCSI_LOG_ERROR_RECOVERY(1,
 				shost_printk(KERN_ERR, shost,
 					     "scsi_eh_%d: unable to autoresume\n",
@@ -2407,7 +2409,7 @@ int scsi_error_handler(void *data)
 		 * which are still online.
 		 */
 		scsi_restart_operations(shost);
-		if (!shost->eh_noresume)
+		if (!eh_noresume)
 			scsi_autopm_put_host(shost);
 	}
 	__set_current_state(TASK_RUNNING);
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index c3f08957d179..9e2ae37340c9 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -9995,7 +9995,7 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 	 * we are functional while we are here, skip host resume in error
 	 * handling context.
 	 */
-	hba->host->eh_noresume = 1;
+	WRITE_ONCE(hba->host->eh_noresume, 1);
 
 	/*
 	 * Current function would be generally called from the power management
@@ -10017,7 +10017,7 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 	}
 
 	scsi_device_put(sdp);
-	hba->host->eh_noresume = 0;
+	WRITE_ONCE(hba->host->eh_noresume, 0);
 	return ret;
 }
 
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 7e2011830ba4..857f955f08cf 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -664,6 +664,9 @@ struct Scsi_Host {
 	/* Asynchronous scan in progress */
 	bool async_scan __guarded_by(&scan_mutex);
 
+	/* Don't resume host in EH */
+	bool eh_noresume;
+
 	unsigned active_mode:2;
 
 	/*
@@ -682,9 +685,6 @@ struct Scsi_Host {
 	/* Task mgmt function in progress */
 	unsigned tmf_in_progress:1;
 
-	/* Don't resume host in EH */
-	unsigned eh_noresume:1;
-
 	/* The controller does not support WRITE SAME */
 	unsigned no_write_same:1;
 
-- 
2.25.1