scsi: Wake up the error handler when final completions race against each other
PATCH 1/1 scsi: Wake up the error handler when final completions race against each other
The fragile ordering between marking commands completed or failed so that the error handler only wakes when the last running command completes or times out has race conditions. These race conditions can cause the scsi layer to fail to wake the error handler, leaving I/O through the scsi host stuck as the error state cannot advance.
First, there is an memory ordering issue within scsi_dec_host_busy. The write which clears SCMD_STATE_INFLIGHT may be reordered with reads counting in scsi_host_busy. While the local CPU will see its own write, reordering can allow other CPUs in scsi_dec_host_busy or scsi_eh_inc_host_failed to see a raised busy count, causing no CPU to see a host busy equal to the host_failed count.
This race condition can be prevented with a memory barrier on the error path to force the write to be visible before counting host busy commands.
Second, there is a general ordering issue with scsi_eh_inc_host_failed. By counting busy commands before incrementing host_failed, it can race with a final command in scsi_dec_host_busy, such that scsi_dec_host_busy does not see host_failed incremented but scsi_eh_inc_host_failed counts busy commands before SCMD_STATE_INFLIGHT is cleared by scsi_dec_host_busy, resulting in neither waking the error handler task.
This needs the call to scsi_host_busy to be moved after host_failed is incremented to close the race condition.
--- drivers/scsi/scsi_error.c | 11 ++++++++++- drivers/scsi/scsi_lib.c | 8 ++++++++ 2 files changed, 18 insertions(+), 1 deletion(-)
drivers/scsi/scsi_error.c +10 -1
@@ -282,11 +282,20 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head) {struct scsi_cmnd *scmd =container_of (head,typeof (*scmd), rcu);struct Scsi_Host *shost = scmd->device->host; -unsigned int busy =scsi_host_busy (shost); +unsigned int busy;unsigned long flags;spin_lock_irqsave (shost->host_lock, flags); shost->host_failed++; +spin_unlock_irqrestore (shost->host_lock, flags); +/* +* The counting of busy requests needs to occur after adding to +* host_failed or after the lock acquire for adding to host_failed +* to prevent a race with host unbusy and missing an eh wakeup. +*/ + busy =scsi_host_busy (shost); + +spin_lock_irqsave (shost->host_lock, flags);scsi_eh_wakeup (shost, busy);spin_unlock_irqrestore (shost->host_lock, flags); }
drivers/scsi/scsi_lib.c +8 -0
@@ -376,6 +376,14 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd)rcu_read_lock ();__clear_bit (SCMD_STATE_INFLIGHT , &cmd->state);if (unlikely (scsi_host_in_recovery (shost))) { +/* +* Ensure the clear of SCMD_STATE_INFLIGHT is visible to +* other CPUs before counting busy requests. Otherwise, +* reordering can cause CPUs to race and miss an eh wakeup +* when no CPU sees all busy requests as done or timed out. +*/ +smp_mb (); +unsigned int busy =scsi_host_busy (shost);spin_lock_irqsave (shost->host_lock, flags);
Signature · 1 line
2.52.0
Quoted 23 lines · David Jeffery
The fragile ordering between marking commands completed or failed so that the error handler only wakes when the last running command completes or times out has race conditions. These race conditions can cause the scsi layer to fail to wake the error handler, leaving I/O through the scsi host stuck as the error state cannot advance.
First, there is an memory ordering issue within
scsi_dec_host_busy. The write which clearsSCMD_STATE_INFLIGHTmay be reordered with reads counting inscsi_host_busy. While the local CPU will see its own write, reordering can allow other CPUs inscsi_dec_host_busyorscsi_eh_inc_host_failedto see a raised busy count, causing no CPU to see a host busy equal to thehost_failedcount.This race condition can be prevented with a memory barrier on the error path to force the write to be visible before counting host busy commands.
Second, there is a general ordering issue with
scsi_eh_inc_host_failed. By counting busy commands before incrementinghost_failed, it can race with a final command inscsi_dec_host_busy, such thatscsi_dec_host_busydoes not seehost_failedincremented butscsi_eh_inc_host_failedcounts busy commands beforeSCMD_STATE_INFLIGHTis cleared byscsi_dec_host_busy, resulting in neither waking the error handler task.
Quoted 2 lines
This needs the call to
scsi_host_busyto be moved afterhost_failedis incremented to close the race condition.
Martin K. Petersen
AppliedQuoted 6 lines · David Jeffery
The fragile ordering between marking commands completed or failed so that the error handler only wakes when the last running command completes or times out has race conditions. These race conditions can cause the scsi layer to fail to wake the error handler, leaving I/O through the scsi host stuck as the error state cannot advance.
Quoted 8 lines
First, there is an memory ordering issue within
scsi_dec_host_busy. The write which clearsSCMD_STATE_INFLIGHTmay be reordered with reads counting inscsi_host_busy. While the local CPU will see its own write, reordering can allow other CPUs inscsi_dec_host_busyorscsi_eh_inc_host_failedto see a raised busy count, causing no CPU to see a host busy equal to thehost_failedcount.[...]
Applied to 6.19/scsi-fixes, thanks!
[1/1] scsi: Wake up the error handler when final completions race against each other
https://git.kernel.org/mkp/scsi/c/fe2f8ad6f099
Signature · 1 line
Martin K. Petersen