From 8a1116c4e1ab4e54aa2a6be492ac3f62c9705fa0 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 15 Mar 2024 16:58:48 +0800 Subject: [PATCH 1/2] scsi: core: Move scsi_host_busy() out of host lock for waking up EH handler mainline inclusion from mainline-v6.8-rc3 commit 4373534a9850627a2695317944898eb1283a2db0 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I96GXK CVE: CVE-2024-26627 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=4373534a9850627a2695317944898eb1283a2db0 -------------------------------- Inside scsi_eh_wakeup(), scsi_host_busy() is called & checked with host lock every time for deciding if error handler kthread needs to be waken up. This can be too heavy in case of recovery, such as: - N hardware queues - queue depth is M for each hardware queue - each scsi_host_busy() iterates over (N * M) tag/requests If recovery is triggered in case that all requests are in-flight, each scsi_eh_wakeup() is strictly serialized, when scsi_eh_wakeup() is called for the last in-flight request, scsi_host_busy() has been run for (N * M - 1) times, and request has been iterated for (N*M - 1) * (N * M) times. If both N and M are big enough, hard lockup can be triggered on acquiring host lock, and it is observed on mpi3mr(128 hw queues, queue depth 8169). Fix the issue by calling scsi_host_busy() outside the host lock. We don't need the host lock for getting busy count because host the lock never covers that. [mkp: Drop unnecessary 'busy' variables pointed out by Bart] Cc: Ewan Milne Fixes: 6eb045e092ef ("scsi: core: avoid host-wide host_busy counter for scsi_mq") Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20240112070000.4161982-1-ming.lei@redhat.com Reviewed-by: Ewan D. Milne Reviewed-by: Sathya Prakash Veerichetty Tested-by: Sathya Prakash Veerichetty Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen Signed-off-by: Li Nan --- drivers/scsi/scsi_error.c | 8 ++++---- drivers/scsi/scsi_lib.c | 2 +- drivers/scsi/scsi_priv.h | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index c67cdcdc3ba8..48da34b1ebe4 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -61,11 +61,11 @@ static int scsi_eh_try_stu(struct scsi_cmnd *scmd); static enum scsi_disposition scsi_try_to_abort_cmd(const struct scsi_host_template *, struct scsi_cmnd *); -void scsi_eh_wakeup(struct Scsi_Host *shost) +void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy) { lockdep_assert_held(shost->host_lock); - if (scsi_host_busy(shost) == shost->host_failed) { + if (busy == shost->host_failed) { trace_scsi_eh_wakeup(shost); wake_up_process(shost->ehandler); SCSI_LOG_ERROR_RECOVERY(5, shost_printk(KERN_INFO, shost, @@ -88,7 +88,7 @@ void scsi_schedule_eh(struct Scsi_Host *shost) if (scsi_host_set_state(shost, SHOST_RECOVERY) == 0 || scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY) == 0) { shost->host_eh_scheduled++; - scsi_eh_wakeup(shost); + scsi_eh_wakeup(shost, scsi_host_busy(shost)); } spin_unlock_irqrestore(shost->host_lock, flags); @@ -286,7 +286,7 @@ static void scsi_eh_inc_host_failed(struct rcu_head *head) spin_lock_irqsave(shost->host_lock, flags); shost->host_failed++; - scsi_eh_wakeup(shost); + scsi_eh_wakeup(shost, scsi_host_busy(shost)); spin_unlock_irqrestore(shost->host_lock, flags); } diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 53c93c4616bc..60b446f1c779 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -280,7 +280,7 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost, struct scsi_cmnd *cmd) if (unlikely(scsi_host_in_recovery(shost))) { spin_lock_irqsave(shost->host_lock, flags); if (shost->host_failed || shost->host_eh_scheduled) - scsi_eh_wakeup(shost); + scsi_eh_wakeup(shost, scsi_host_busy(shost)); spin_unlock_irqrestore(shost->host_lock, flags); } rcu_read_unlock(); diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h index 3f0dfb97db6b..1fbfe1b52c9f 100644 --- a/drivers/scsi/scsi_priv.h +++ b/drivers/scsi/scsi_priv.h @@ -92,7 +92,7 @@ extern void scmd_eh_abort_handler(struct work_struct *work); extern enum blk_eh_timer_return scsi_timeout(struct request *req); extern int scsi_error_handler(void *host); extern enum scsi_disposition scsi_decide_disposition(struct scsi_cmnd *cmd); -extern void scsi_eh_wakeup(struct Scsi_Host *shost); +extern void scsi_eh_wakeup(struct Scsi_Host *shost, unsigned int busy); extern void scsi_eh_scmd_add(struct scsi_cmnd *); void scsi_eh_ready_devs(struct Scsi_Host *shost, struct list_head *work_q, -- Gitee From fda19376057bb6b534ac2104bd19e1283c6238fd Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 15 Mar 2024 16:58:49 +0800 Subject: [PATCH 2/2] scsi: core: Move scsi_host_busy() out of host lock if it is for per-command mainline inclusion from mainline-v6.8-rc4 commit 4e6c9011990726f4d175e2cdfebe5b0b8cce4839 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I96GXK CVE: CVE-2024-26627 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=4e6c9011990726f4d175e2cdfebe5b0b8cce4839 -------------------------------- Commit 4373534a9850 ("scsi: core: Move scsi_host_busy() out of host lock for waking up EH handler") intended to fix a hard lockup issue triggered by EH. The core idea was to move scsi_host_busy() out of the host lock when processing individual commands for EH. However, a suggested style change inadvertently caused scsi_host_busy() to remain under the host lock. Fix this by calling scsi_host_busy() outside the lock. Fixes: 4373534a9850 ("scsi: core: Move scsi_host_busy() out of host lock for waking up EH handler") Cc: Sathya Prakash Veerichetty Cc: Bart Van Assche Cc: Ewan D. Milne Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20240203024521.2006455-1-ming.lei@redhat.com Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen Signed-off-by: Li Nan --- drivers/scsi/scsi_error.c | 3 ++- drivers/scsi/scsi_lib.c | 4 +++- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 48da34b1ebe4..65e644328584 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -282,11 +282,12 @@ 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 long flags; spin_lock_irqsave(shost->host_lock, flags); shost->host_failed++; - scsi_eh_wakeup(shost, scsi_host_busy(shost)); + scsi_eh_wakeup(shost, busy); spin_unlock_irqrestore(shost->host_lock, flags); } diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 60b446f1c779..5dda11a5ff10 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -278,9 +278,11 @@ 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))) { + unsigned int busy = scsi_host_busy(shost); + spin_lock_irqsave(shost->host_lock, flags); if (shost->host_failed || shost->host_eh_scheduled) - scsi_eh_wakeup(shost, scsi_host_busy(shost)); + scsi_eh_wakeup(shost, busy); spin_unlock_irqrestore(shost->host_lock, flags); } rcu_read_unlock(); -- Gitee