From af61bc1e33d2c0ec22612b46050f5b58ac56a962 Mon Sep 17 00:00:00 2001 From: Keita Suzuki Date: Tue, 27 Oct 2020 07:31:24 +0000 Subject: [PATCH 1/3] scsi: hpsa: Fix memory leak in hpsa_init_one() When hpsa_scsi_add_host() fails, h->lastlogicals is leaked since it is missing a free() in the error handler. Fix this by adding free() when hpsa_scsi_add_host() fails. Link: https://lore.kernel.org/r/20201027073125.14229-1-keitasuzuki.park@sslab.ics.keio.ac.jp Tested-by: Don Brace Acked-by: Don Brace Signed-off-by: Keita Suzuki Signed-off-by: Martin K. Petersen --- drivers/scsi/hpsa.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 83ce4f11a589..8df70c92911d 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -8855,7 +8855,7 @@ reinit_after_soft_reset: /* hook into SCSI subsystem */ rc = hpsa_scsi_add_host(h); if (rc) - goto clean7; /* perf, sg, cmd, irq, shost, pci, lu, aer/h */ + goto clean8; /* lastlogicals, perf, sg, cmd, irq, shost, pci, lu, aer/h */ /* Monitor the controller for firmware lockups */ h->heartbeat_sample_interval = HEARTBEAT_SAMPLE_INTERVAL; @@ -8870,6 +8870,8 @@ reinit_after_soft_reset: HPSA_EVENT_MONITOR_INTERVAL); return 0; +clean8: /* lastlogicals, perf, sg, cmd, irq, shost, pci, lu, aer/h */ + kfree(h->lastlogicals); clean7: /* perf, sg, cmd, irq, shost, pci, lu, aer/h */ hpsa_free_performant_mode(h); h->access.set_intr_mask(h, HPSA_INTR_OFF); From 5faf50e9e9fdc2117c61ff7e20da49cd6a29e0ca Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Thu, 24 Sep 2020 12:45:59 +0200 Subject: [PATCH 2/3] scsi: scsi_dh_alua: Avoid crash during alua_bus_detach() alua_bus_detach() might be running concurrently with alua_rtpg_work(), so we might trip over h->sdev == NULL and call BUG_ON(). The correct way of handling it is to not set h->sdev to NULL in alua_bus_detach(), and call rcu_synchronize() before the final delete to ensure that all concurrent threads have left the critical section. Then we can get rid of the BUG_ON() and replace it with a simple if condition. Link: https://lore.kernel.org/r/1600167537-12509-1-git-send-email-jitendra.khasdev@oracle.com Link: https://lore.kernel.org/r/20200924104559.26753-1-hare@suse.de Cc: Brian Bunker Acked-by: Brian Bunker Tested-by: Jitendra Khasdev Reviewed-by: Jitendra Khasdev Signed-off-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/scsi/device_handler/scsi_dh_alua.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index f32da0ca529e..308bda2e9c00 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -658,8 +658,8 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) rcu_read_lock(); list_for_each_entry_rcu(h, &tmp_pg->dh_list, node) { - /* h->sdev should always be valid */ - BUG_ON(!h->sdev); + if (!h->sdev) + continue; h->sdev->access_state = desc[0]; } rcu_read_unlock(); @@ -705,7 +705,8 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) pg->expiry = 0; rcu_read_lock(); list_for_each_entry_rcu(h, &pg->dh_list, node) { - BUG_ON(!h->sdev); + if (!h->sdev) + continue; h->sdev->access_state = (pg->state & SCSI_ACCESS_STATE_MASK); if (pg->pref) @@ -1147,7 +1148,6 @@ static void alua_bus_detach(struct scsi_device *sdev) spin_lock(&h->pg_lock); pg = rcu_dereference_protected(h->pg, lockdep_is_held(&h->pg_lock)); rcu_assign_pointer(h->pg, NULL); - h->sdev = NULL; spin_unlock(&h->pg_lock); if (pg) { spin_lock_irq(&pg->lock); @@ -1156,6 +1156,7 @@ static void alua_bus_detach(struct scsi_device *sdev) kref_put(&pg->kref, release_port_group); } sdev->handler_data = NULL; + synchronize_rcu(); kfree(h); } From 5feed64f9199ff90c4239971733f23f30aeb2484 Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Mon, 2 Nov 2020 12:57:46 +0530 Subject: [PATCH 3/3] scsi: mpt3sas: Fix timeouts observed while reenabling IRQ While reenabling the IRQ after irq poll there may be small time window where HBA firmware has posted some replies and raise the interrupts but driver has not received the interrupts. So we may observe I/O timeouts as the driver has not processed the replies as interrupts got missed while reenabling the IRQ. To fix this issue the driver has to go for one more round of processing the reply descriptors from reply descriptor post queue after enabling the IRQ. Link: https://lore.kernel.org/r/20201102072746.27410-1-sreekanth.reddy@broadcom.com Reported-by: Tomas Henzl Reviewed-by: Tomas Henzl Signed-off-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_base.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 93230cd1982f..e4cc92bc4d94 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -1740,6 +1740,13 @@ _base_irqpoll(struct irq_poll *irqpoll, int budget) reply_q->irq_poll_scheduled = false; reply_q->irq_line_enable = true; enable_irq(reply_q->os_irq); + /* + * Go for one more round of processing the + * reply descriptor post queue incase if HBA + * Firmware has posted some reply descriptors + * while reenabling the IRQ. + */ + _base_process_reply_queue(reply_q); } return num_entries;