[PATCH AUTOSEL 5.5 08/75] scsi: lpfc: Fix kasan slab-out-of-bounds error in lpfc_unreg_login

[PATCH AUTOSEL 5.5 08/75] scsi: lpfc: Fix kasan slab-out-of-bounds error in lpfc_unreg_login

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit 38503943c89f0bafd9e3742f63f872301d44cbea ]

The following kasan bug was called out:

 BUG: KASAN: slab-out-of-bounds in lpfc_unreg_login+0x7c/0xc0 [lpfc]
 Read of size 2 at addr ffff889fc7c50a22 by task lpfc_worker_3/6676
 ...
 Call Trace:
 dump_stack+0x96/0xe0
 ? lpfc_unreg_login+0x7c/0xc0 [lpfc]
 print_address_description.constprop.6+0x1b/0x220
 ? lpfc_unreg_login+0x7c/0xc0 [lpfc]
 ? lpfc_unreg_login+0x7c/0xc0 [lpfc]
 __kasan_report.cold.9+0x37/0x7c
 ? lpfc_unreg_login+0x7c/0xc0 [lpfc]
 kasan_report+0xe/0x20
 lpfc_unreg_login+0x7c/0xc0 [lpfc]
 lpfc_sli_def_mbox_cmpl+0x334/0x430 [lpfc]
 ...

When processing the completion of a "Reg Rpi" login mailbox command in
lpfc_sli_def_mbox_cmpl, a call may be made to lpfc_unreg_login. The vpi is
extracted from the completing mailbox context and passed as an input for
the next. However, the vpi stored in the mailbox command context is an
absolute vpi, which for SLI4 represents both base + offset.  When used with
a non-zero base component, (function id > 0) this results in an
out-of-range access beyond the allocated phba->vpi_ids array.

Fix by subtracting the function's base value to get an accurate vpi number.

Link: https://lore.kernel.org/r/20200322181304.37655-2-jsmart2021@gmail.com
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc_sli.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 625c046ac4efa..993b1056beb83 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -2511,6 +2511,8 @@ lpfc_sli_def_mbox_cmpl(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	    !pmb->u.mb.mbxStatus) {
 		rpi = pmb->u.mb.un.varWords[0];
 		vpi = pmb->u.mb.un.varRegLogin.vpi;
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			vpi -= phba->sli4_hba.max_cfg_param.vpi_base;
 		lpfc_unreg_login(phba, vpi, rpi, pmb);
 		pmb->vport = vport;
 		pmb->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
-- 
2.20.1

[PATCH AUTOSEL 5.5 10/75] scsi: lpfc: Fix crash after handling a pci error

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit 4cd70891308dfb875ef31060c4a4aa8872630a2e ]

Injecting EEH on a 32GB card is causing kernel oops

The pci error handler is doing an IO flush and the offline code is also
doing an IO flush. When the 1st flush is complete the hdwq is destroyed
(freed), yet the second flush accesses the hdwq and crashes.

Added a check in lpfc_sli4_fush_io_rings to check both the HBA_IOQ_FLUSH
flag and the hdwq pointer to see if it is already set and not already
freed.

Link: https://lore.kernel.org/r/20200322181304.37655-6-jsmart2021@gmail.com
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc_sli.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 993b1056beb83..909554c7c1273 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -4046,6 +4046,11 @@ lpfc_sli_flush_io_rings(struct lpfc_hba *phba)
 	struct lpfc_iocbq *piocb, *next_iocb;
 
 	spin_lock_irq(&phba->hbalock);
+	if (phba->hba_flag & HBA_IOQ_FLUSH ||
+	    !phba->sli4_hba.hdwq) {
+		spin_unlock_irq(&phba->hbalock);
+		return;
+	}
 	/* Indicate the I/O queues are flushed */
 	phba->hba_flag |= HBA_IOQ_FLUSH;
 	spin_unlock_irq(&phba->hbalock);
-- 
2.20.1

[PATCH AUTOSEL 5.5 11/75] scsi: lpfc: Fix crash in target side cable pulls hitting WAIT_FOR_UNREG

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit 807e7353d8a7105ce884d22b0dbc034993c6679c ]

Kernel is crashing with the following stacktrace:

  BUG: unable to handle kernel NULL pointer dereference at
    00000000000005bc
  IP: lpfc_nvme_register_port+0x1a8/0x3a0 [lpfc]
  ...
  Call Trace:
  lpfc_nlp_state_cleanup+0x2b2/0x500 [lpfc]
  lpfc_nlp_set_state+0xd7/0x1a0 [lpfc]
  lpfc_cmpl_prli_prli_issue+0x1f7/0x450 [lpfc]
  lpfc_disc_state_machine+0x7a/0x1e0 [lpfc]
  lpfc_cmpl_els_prli+0x16f/0x1e0 [lpfc]
  lpfc_sli_sp_handle_rspiocb+0x5b2/0x690 [lpfc]
  lpfc_sli_handle_slow_ring_event_s4+0x182/0x230 [lpfc]
  lpfc_do_work+0x87f/0x1570 [lpfc]
  kthread+0x10d/0x130
  ret_from_fork+0x35/0x40

During target side fault injections, it is possible to hit the
NLP_WAIT_FOR_UNREG case in lpfc_nvme_remoteport_delete. A prior commit
fixed a rebind and delete race condition, but called lpfc_nlp_put
unconditionally. This triggered a deletion and the crash.

Fix by movng nlp_put to inside the NLP_WAIT_FOR_UNREG case, where the nlp
will be being unregistered/removed. Leave the reference if the flag isn't
set.

Link: https://lore.kernel.org/r/20200322181304.37655-8-jsmart2021@gmail.com
Fixes: b15bd3e6212e ("scsi: lpfc: Fix nvme remoteport registration race conditions")
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc_nvme.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index f6c8963c915d4..32b28651039e0 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -382,13 +382,15 @@ lpfc_nvme_remoteport_delete(struct nvme_fc_remote_port *remoteport)
 	if (ndlp->upcall_flags & NLP_WAIT_FOR_UNREG) {
 		ndlp->nrport = NULL;
 		ndlp->upcall_flags &= ~NLP_WAIT_FOR_UNREG;
-	}
-	spin_unlock_irq(&vport->phba->hbalock);
+		spin_unlock_irq(&vport->phba->hbalock);
 
-	/* Remove original register reference. The host transport
-	 * won't reference this rport/remoteport any further.
-	 */
-	lpfc_nlp_put(ndlp);
+		/* Remove original register reference. The host transport
+		 * won't reference this rport/remoteport any further.
+		 */
+		lpfc_nlp_put(ndlp);
+	} else {
+		spin_unlock_irq(&vport->phba->hbalock);
+	}
 
  rport_err:
 	return;
-- 
2.20.1

[PATCH AUTOSEL 5.5 12/75] scsi: libfc: If PRLI rejected, move rport to PLOGI state

[Sasha Levin]

From: Javed Hasan <jhasan@marvell.com>

[ Upstream commit 45e544bfdab2014d11c7595b8ccc3c4715a09015 ]

If PRLI reject code indicates "rejected status", move rport state machine
back to PLOGI state.

Link: https://lore.kernel.org/r/20200327060208.17104-2-skashyap@marvell.com
Signed-off-by: Javed Hasan <jhasan@marvell.com>
Signed-off-by: Saurav Kashyap <skashyap@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/libfc/fc_rport.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index da6e97d8dc3bb..6bb8917b99a19 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -1208,9 +1208,15 @@ static void fc_rport_prli_resp(struct fc_seq *sp, struct fc_frame *fp,
 		rjt = fc_frame_payload_get(fp, sizeof(*rjt));
 		if (!rjt)
 			FC_RPORT_DBG(rdata, "PRLI bad response\n");
-		else
+		else {
 			FC_RPORT_DBG(rdata, "PRLI ELS rejected, reason %x expl %x\n",
 				     rjt->er_reason, rjt->er_explan);
+			if (rjt->er_reason == ELS_RJT_UNAB &&
+			    rjt->er_explan == ELS_EXPL_PLOGI_REQD) {
+				fc_rport_enter_plogi(rdata);
+				goto out;
+			}
+		}
 		fc_rport_error_retry(rdata, FC_EX_ELS_RJT);
 	}
 
-- 
2.20.1

[PATCH AUTOSEL 5.5 18/75] scsi: iscsi: Report unbind session event when the target has been removed

[Sasha Levin]

From: Wu Bo <wubo40@huawei.com>

[ Upstream commit 13e60d3ba287d96eeaf1deaadba51f71578119a3 ]

If the daemon is restarted or crashes while logging out of a session, the
unbind session event sent by the kernel is not processed and is lost.  When
the daemon starts again, the session can't be unbound because the daemon is
waiting for the event message. However, the kernel has already logged out
and the event will not be resent.

When iscsid restart is complete, logout session reports error:

Logging out of session [sid: 6, target: iqn.xxxxx, portal: xx.xx.xx.xx,3260]
iscsiadm: Could not logout of [sid: 6, target: iscsiadm -m node iqn.xxxxx, portal: xx.xx.xx.xx,3260].
iscsiadm: initiator reported error (9 - internal error)
iscsiadm: Could not logout of all requested sessions

Make sure the unbind event is emitted.

[mkp: commit desc and applied by hand since patch was mangled]

Link: https://lore.kernel.org/r/4eab1771-2cb3-8e79-b31c-923652340e99@huawei.com
Reviewed-by: Lee Duncan <lduncan@suse.com>
Signed-off-by: Wu Bo <wubo40@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/scsi_transport_iscsi.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 271afea654e2b..a5c78b38d3022 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -2012,7 +2012,7 @@ static void __iscsi_unbind_session(struct work_struct *work)
 	if (session->target_id == ISCSI_MAX_TARGET) {
 		spin_unlock_irqrestore(&session->lock, flags);
 		mutex_unlock(&ihost->mutex);
-		return;
+		goto unbind_session_exit;
 	}
 
 	target_id = session->target_id;
@@ -2024,6 +2024,8 @@ static void __iscsi_unbind_session(struct work_struct *work)
 		ida_simple_remove(&iscsi_sess_ida, target_id);
 
 	scsi_remove_target(&session->dev);
+
+unbind_session_exit:
 	iscsi_session_event(session, ISCSI_KEVENT_UNBIND_SESSION);
 	ISCSI_DBG_TRANS_SESSION(session, "Completed target removal\n");
 }
-- 
2.20.1

[PATCH AUTOSEL 5.5 43/75] scsi: lpfc: Fix erroneous cpu limit of 128 on I/O statistics

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit 840eda9602d30342486e85e7e96499f565572e4b ]

The cpu io statistics were capped by a hard define limit of 128. This
effectively was a max number of CPUs, not an actual CPU count, nor actual
CPU numbers which can be even larger than both of those values. This made
stats off/misleading and on large CPU count systems, wrong.

Fix the stats so that all CPUs can have a stats struct.  Fix the looping
such that it loops by hdwq, finds CPUs that used the hdwq, and sum the
stats, then display.

Link: https://lore.kernel.org/r/20200322181304.37655-9-jsmart2021@gmail.com
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc.h         |   9 +-
 drivers/scsi/lpfc/lpfc_debugfs.c | 204 ++++++++++++++++++-------------
 drivers/scsi/lpfc/lpfc_debugfs.h |   1 -
 drivers/scsi/lpfc/lpfc_init.c    |  28 +++++
 drivers/scsi/lpfc/lpfc_nvme.c    |  45 ++++---
 drivers/scsi/lpfc/lpfc_nvmet.c   |  55 ++++-----
 drivers/scsi/lpfc/lpfc_scsi.c    |  23 +---
 drivers/scsi/lpfc/lpfc_sli4.h    |  19 +--
 8 files changed, 215 insertions(+), 169 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 935f988041989..d6a305c4e44ed 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -482,7 +482,7 @@ struct lpfc_vport {
 	struct dentry *debug_nvmestat;
 	struct dentry *debug_scsistat;
 	struct dentry *debug_nvmektime;
-	struct dentry *debug_cpucheck;
+	struct dentry *debug_hdwqstat;
 	struct dentry *vport_debugfs_root;
 	struct lpfc_debugfs_trc *disc_trc;
 	atomic_t disc_trc_cnt;
@@ -1175,12 +1175,11 @@ struct lpfc_hba {
 	uint16_t sfp_warning;
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	uint16_t cpucheck_on;
+	uint16_t hdwqstat_on;
 #define LPFC_CHECK_OFF		0
 #define LPFC_CHECK_NVME_IO	1
-#define LPFC_CHECK_NVMET_RCV	2
-#define LPFC_CHECK_NVMET_IO	4
-#define LPFC_CHECK_SCSI_IO	8
+#define LPFC_CHECK_NVMET_IO	2
+#define LPFC_CHECK_SCSI_IO	4
 	uint16_t ktime_on;
 	uint64_t ktime_data_samples;
 	uint64_t ktime_status_samples;
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index a5ecbce4eda23..7d453047c4b67 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -1603,42 +1603,50 @@ lpfc_debugfs_nvmeio_trc_data(struct lpfc_hba *phba, char *buf, int size)
 }
 
 /**
- * lpfc_debugfs_cpucheck_data - Dump target node list to a buffer
+ * lpfc_debugfs_hdwqstat_data - Dump I/O stats to a buffer
  * @vport: The vport to gather target node info from.
  * @buf: The buffer to dump log into.
  * @size: The maximum amount of data to process.
  *
  * Description:
- * This routine dumps the NVME statistics associated with @vport
+ * This routine dumps the NVME + SCSI statistics associated with @vport
  *
  * Return Value:
  * This routine returns the amount of bytes that were dumped into @buf and will
  * not exceed @size.
  **/
 static int
-lpfc_debugfs_cpucheck_data(struct lpfc_vport *vport, char *buf, int size)
+lpfc_debugfs_hdwqstat_data(struct lpfc_vport *vport, char *buf, int size)
 {
 	struct lpfc_hba   *phba = vport->phba;
 	struct lpfc_sli4_hdw_queue *qp;
-	int i, j, max_cnt;
-	int len = 0;
+	struct lpfc_hdwq_stat *c_stat;
+	int i, j, len;
 	uint32_t tot_xmt;
 	uint32_t tot_rcv;
 	uint32_t tot_cmpl;
+	char tmp[LPFC_MAX_SCSI_INFO_TMP_LEN] = {0};
 
-	len += scnprintf(buf + len, PAGE_SIZE - len,
-			"CPUcheck %s ",
-			(phba->cpucheck_on & LPFC_CHECK_NVME_IO ?
-				"Enabled" : "Disabled"));
-	if (phba->nvmet_support) {
-		len += scnprintf(buf + len, PAGE_SIZE - len,
-				"%s\n",
-				(phba->cpucheck_on & LPFC_CHECK_NVMET_RCV ?
-					"Rcv Enabled\n" : "Rcv Disabled\n"));
-	} else {
-		len += scnprintf(buf + len, PAGE_SIZE - len, "\n");
-	}
-	max_cnt = size - LPFC_DEBUG_OUT_LINE_SZ;
+	scnprintf(tmp, sizeof(tmp), "HDWQ Stats:\n\n");
+	if (strlcat(buf, tmp, size) >= size)
+		goto buffer_done;
+
+	scnprintf(tmp, sizeof(tmp), "(NVME Accounting: %s) ",
+		  (phba->hdwqstat_on &
+		  (LPFC_CHECK_NVME_IO | LPFC_CHECK_NVMET_IO) ?
+		  "Enabled" : "Disabled"));
+	if (strlcat(buf, tmp, size) >= size)
+		goto buffer_done;
+
+	scnprintf(tmp, sizeof(tmp), "(SCSI Accounting: %s) ",
+		  (phba->hdwqstat_on & LPFC_CHECK_SCSI_IO ?
+		  "Enabled" : "Disabled"));
+	if (strlcat(buf, tmp, size) >= size)
+		goto buffer_done;
+
+	scnprintf(tmp, sizeof(tmp), "\n\n");
+	if (strlcat(buf, tmp, size) >= size)
+		goto buffer_done;
 
 	for (i = 0; i < phba->cfg_hdw_queue; i++) {
 		qp = &phba->sli4_hba.hdwq[i];
@@ -1646,46 +1654,76 @@ lpfc_debugfs_cpucheck_data(struct lpfc_vport *vport, char *buf, int size)
 		tot_rcv = 0;
 		tot_xmt = 0;
 		tot_cmpl = 0;
-		for (j = 0; j < LPFC_CHECK_CPU_CNT; j++) {
-			tot_xmt += qp->cpucheck_xmt_io[j];
-			tot_cmpl += qp->cpucheck_cmpl_io[j];
-			if (phba->nvmet_support)
-				tot_rcv += qp->cpucheck_rcv_io[j];
-		}
 
-		/* Only display Hardware Qs with something */
-		if (!tot_xmt && !tot_cmpl && !tot_rcv)
-			continue;
+		for_each_present_cpu(j) {
+			c_stat = per_cpu_ptr(phba->sli4_hba.c_stat, j);
+
+			/* Only display for this HDWQ */
+			if (i != c_stat->hdwq_no)
+				continue;
 
-		len += scnprintf(buf + len, PAGE_SIZE - len,
-				"HDWQ %03d: ", i);
-		for (j = 0; j < LPFC_CHECK_CPU_CNT; j++) {
 			/* Only display non-zero counters */
-			if (!qp->cpucheck_xmt_io[j] &&
-			    !qp->cpucheck_cmpl_io[j] &&
-			    !qp->cpucheck_rcv_io[j])
+			if (!c_stat->xmt_io && !c_stat->cmpl_io &&
+			    !c_stat->rcv_io)
 				continue;
+
+			if (!tot_xmt && !tot_cmpl && !tot_rcv) {
+				/* Print HDWQ string only the first time */
+				scnprintf(tmp, sizeof(tmp), "[HDWQ %d]:\t", i);
+				if (strlcat(buf, tmp, size) >= size)
+					goto buffer_done;
+			}
+
+			tot_xmt += c_stat->xmt_io;
+			tot_cmpl += c_stat->cmpl_io;
+			if (phba->nvmet_support)
+				tot_rcv += c_stat->rcv_io;
+
+			scnprintf(tmp, sizeof(tmp), "| [CPU %d]: ", j);
+			if (strlcat(buf, tmp, size) >= size)
+				goto buffer_done;
+
 			if (phba->nvmet_support) {
-				len += scnprintf(buf + len, PAGE_SIZE - len,
-						"CPU %03d: %x/%x/%x ", j,
-						qp->cpucheck_rcv_io[j],
-						qp->cpucheck_xmt_io[j],
-						qp->cpucheck_cmpl_io[j]);
+				scnprintf(tmp, sizeof(tmp),
+					  "XMT 0x%x CMPL 0x%x RCV 0x%x |",
+					  c_stat->xmt_io, c_stat->cmpl_io,
+					  c_stat->rcv_io);
+				if (strlcat(buf, tmp, size) >= size)
+					goto buffer_done;
 			} else {
-				len += scnprintf(buf + len, PAGE_SIZE - len,
-						"CPU %03d: %x/%x ", j,
-						qp->cpucheck_xmt_io[j],
-						qp->cpucheck_cmpl_io[j]);
+				scnprintf(tmp, sizeof(tmp),
+					  "XMT 0x%x CMPL 0x%x |",
+					  c_stat->xmt_io, c_stat->cmpl_io);
+				if (strlcat(buf, tmp, size) >= size)
+					goto buffer_done;
 			}
 		}
-		len += scnprintf(buf + len, PAGE_SIZE - len,
-				"Total: %x\n", tot_xmt);
-		if (len >= max_cnt) {
-			len += scnprintf(buf + len, PAGE_SIZE - len,
-					"Truncated ...\n");
-			return len;
+
+		/* Check if nothing to display */
+		if (!tot_xmt && !tot_cmpl && !tot_rcv)
+			continue;
+
+		scnprintf(tmp, sizeof(tmp), "\t->\t[HDWQ Total: ");
+		if (strlcat(buf, tmp, size) >= size)
+			goto buffer_done;
+
+		if (phba->nvmet_support) {
+			scnprintf(tmp, sizeof(tmp),
+				  "XMT 0x%x CMPL 0x%x RCV 0x%x]\n\n",
+				  tot_xmt, tot_cmpl, tot_rcv);
+			if (strlcat(buf, tmp, size) >= size)
+				goto buffer_done;
+		} else {
+			scnprintf(tmp, sizeof(tmp),
+				  "XMT 0x%x CMPL 0x%x]\n\n",
+				  tot_xmt, tot_cmpl);
+			if (strlcat(buf, tmp, size) >= size)
+				goto buffer_done;
 		}
 	}
+
+buffer_done:
+	len = strnlen(buf, size);
 	return len;
 }
 
@@ -2914,7 +2952,7 @@ lpfc_debugfs_nvmeio_trc_write(struct file *file, const char __user *buf,
 }
 
 static int
-lpfc_debugfs_cpucheck_open(struct inode *inode, struct file *file)
+lpfc_debugfs_hdwqstat_open(struct inode *inode, struct file *file)
 {
 	struct lpfc_vport *vport = inode->i_private;
 	struct lpfc_debug *debug;
@@ -2925,14 +2963,14 @@ lpfc_debugfs_cpucheck_open(struct inode *inode, struct file *file)
 		goto out;
 
 	 /* Round to page boundary */
-	debug->buffer = kmalloc(LPFC_CPUCHECK_SIZE, GFP_KERNEL);
+	debug->buffer = kcalloc(1, LPFC_SCSISTAT_SIZE, GFP_KERNEL);
 	if (!debug->buffer) {
 		kfree(debug);
 		goto out;
 	}
 
-	debug->len = lpfc_debugfs_cpucheck_data(vport, debug->buffer,
-		LPFC_CPUCHECK_SIZE);
+	debug->len = lpfc_debugfs_hdwqstat_data(vport, debug->buffer,
+						LPFC_SCSISTAT_SIZE);
 
 	debug->i_private = inode->i_private;
 	file->private_data = debug;
@@ -2943,16 +2981,16 @@ lpfc_debugfs_cpucheck_open(struct inode *inode, struct file *file)
 }
 
 static ssize_t
-lpfc_debugfs_cpucheck_write(struct file *file, const char __user *buf,
+lpfc_debugfs_hdwqstat_write(struct file *file, const char __user *buf,
 			    size_t nbytes, loff_t *ppos)
 {
 	struct lpfc_debug *debug = file->private_data;
 	struct lpfc_vport *vport = (struct lpfc_vport *)debug->i_private;
 	struct lpfc_hba   *phba = vport->phba;
-	struct lpfc_sli4_hdw_queue *qp;
+	struct lpfc_hdwq_stat *c_stat;
 	char mybuf[64];
 	char *pbuf;
-	int i, j;
+	int i;
 
 	if (nbytes > 64)
 		nbytes = 64;
@@ -2965,41 +3003,39 @@ lpfc_debugfs_cpucheck_write(struct file *file, const char __user *buf,
 
 	if ((strncmp(pbuf, "on", sizeof("on") - 1) == 0)) {
 		if (phba->nvmet_support)
-			phba->cpucheck_on |= LPFC_CHECK_NVMET_IO;
+			phba->hdwqstat_on |= LPFC_CHECK_NVMET_IO;
 		else
-			phba->cpucheck_on |= (LPFC_CHECK_NVME_IO |
+			phba->hdwqstat_on |= (LPFC_CHECK_NVME_IO |
 				LPFC_CHECK_SCSI_IO);
 		return strlen(pbuf);
 	} else if ((strncmp(pbuf, "nvme_on", sizeof("nvme_on") - 1) == 0)) {
 		if (phba->nvmet_support)
-			phba->cpucheck_on |= LPFC_CHECK_NVMET_IO;
+			phba->hdwqstat_on |= LPFC_CHECK_NVMET_IO;
 		else
-			phba->cpucheck_on |= LPFC_CHECK_NVME_IO;
+			phba->hdwqstat_on |= LPFC_CHECK_NVME_IO;
 		return strlen(pbuf);
 	} else if ((strncmp(pbuf, "scsi_on", sizeof("scsi_on") - 1) == 0)) {
-		phba->cpucheck_on |= LPFC_CHECK_SCSI_IO;
+		if (!phba->nvmet_support)
+			phba->hdwqstat_on |= LPFC_CHECK_SCSI_IO;
 		return strlen(pbuf);
-	} else if ((strncmp(pbuf, "rcv",
-		   sizeof("rcv") - 1) == 0)) {
-		if (phba->nvmet_support)
-			phba->cpucheck_on |= LPFC_CHECK_NVMET_RCV;
-		else
-			return -EINVAL;
+	} else if ((strncmp(pbuf, "nvme_off", sizeof("nvme_off") - 1) == 0)) {
+		phba->hdwqstat_on &= ~(LPFC_CHECK_NVME_IO |
+				       LPFC_CHECK_NVMET_IO);
+		return strlen(pbuf);
+	} else if ((strncmp(pbuf, "scsi_off", sizeof("scsi_off") - 1) == 0)) {
+		phba->hdwqstat_on &= ~LPFC_CHECK_SCSI_IO;
 		return strlen(pbuf);
 	} else if ((strncmp(pbuf, "off",
 		   sizeof("off") - 1) == 0)) {
-		phba->cpucheck_on = LPFC_CHECK_OFF;
+		phba->hdwqstat_on = LPFC_CHECK_OFF;
 		return strlen(pbuf);
 	} else if ((strncmp(pbuf, "zero",
 		   sizeof("zero") - 1) == 0)) {
-		for (i = 0; i < phba->cfg_hdw_queue; i++) {
-			qp = &phba->sli4_hba.hdwq[i];
-
-			for (j = 0; j < LPFC_CHECK_CPU_CNT; j++) {
-				qp->cpucheck_rcv_io[j] = 0;
-				qp->cpucheck_xmt_io[j] = 0;
-				qp->cpucheck_cmpl_io[j] = 0;
-			}
+		for_each_present_cpu(i) {
+			c_stat = per_cpu_ptr(phba->sli4_hba.c_stat, i);
+			c_stat->xmt_io = 0;
+			c_stat->cmpl_io = 0;
+			c_stat->rcv_io = 0;
 		}
 		return strlen(pbuf);
 	}
@@ -5444,13 +5480,13 @@ static const struct file_operations lpfc_debugfs_op_nvmeio_trc = {
 	.release =      lpfc_debugfs_release,
 };
 
-#undef lpfc_debugfs_op_cpucheck
-static const struct file_operations lpfc_debugfs_op_cpucheck = {
+#undef lpfc_debugfs_op_hdwqstat
+static const struct file_operations lpfc_debugfs_op_hdwqstat = {
 	.owner =        THIS_MODULE,
-	.open =         lpfc_debugfs_cpucheck_open,
+	.open =         lpfc_debugfs_hdwqstat_open,
 	.llseek =       lpfc_debugfs_lseek,
 	.read =         lpfc_debugfs_read,
-	.write =	lpfc_debugfs_cpucheck_write,
+	.write =	lpfc_debugfs_hdwqstat_write,
 	.release =      lpfc_debugfs_release,
 };
 
@@ -6074,11 +6110,11 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport)
 				    vport->vport_debugfs_root,
 				    vport, &lpfc_debugfs_op_nvmektime);
 
-	snprintf(name, sizeof(name), "cpucheck");
-	vport->debug_cpucheck =
+	snprintf(name, sizeof(name), "hdwqstat");
+	vport->debug_hdwqstat =
 		debugfs_create_file(name, 0644,
 				    vport->vport_debugfs_root,
-				    vport, &lpfc_debugfs_op_cpucheck);
+				    vport, &lpfc_debugfs_op_hdwqstat);
 
 	/*
 	 * The following section is for additional directories/files for the
@@ -6212,8 +6248,8 @@ lpfc_debugfs_terminate(struct lpfc_vport *vport)
 	debugfs_remove(vport->debug_nvmektime); /* nvmektime */
 	vport->debug_nvmektime = NULL;
 
-	debugfs_remove(vport->debug_cpucheck); /* cpucheck */
-	vport->debug_cpucheck = NULL;
+	debugfs_remove(vport->debug_hdwqstat); /* hdwqstat */
+	vport->debug_hdwqstat = NULL;
 
 	if (vport->vport_debugfs_root) {
 		debugfs_remove(vport->vport_debugfs_root); /* vportX */
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.h b/drivers/scsi/lpfc/lpfc_debugfs.h
index 20f2537af511c..6643b9bfd4f39 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.h
+++ b/drivers/scsi/lpfc/lpfc_debugfs.h
@@ -47,7 +47,6 @@
 /* nvmestat output buffer size */
 #define LPFC_NVMESTAT_SIZE 8192
 #define LPFC_NVMEKTIME_SIZE 8192
-#define LPFC_CPUCHECK_SIZE 8192
 #define LPFC_NVMEIO_TRC_SIZE 8192
 
 /* scsistat output buffer size */
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 6a04fdb3fbf21..d4a90bec93899 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -6935,6 +6935,17 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		rc = -ENOMEM;
 		goto out_free_hba_cpu_map;
 	}
+
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	phba->sli4_hba.c_stat = alloc_percpu(struct lpfc_hdwq_stat);
+	if (!phba->sli4_hba.c_stat) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+				"3332 Failed allocating per cpu hdwq stats\n");
+		rc = -ENOMEM;
+		goto out_free_hba_eq_info;
+	}
+#endif
+
 	/*
 	 * Enable sr-iov virtual functions if supported and configured
 	 * through the module parameter.
@@ -6954,6 +6965,10 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 
 	return 0;
 
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+out_free_hba_eq_info:
+	free_percpu(phba->sli4_hba.eq_info);
+#endif
 out_free_hba_cpu_map:
 	kfree(phba->sli4_hba.cpu_map);
 out_free_hba_eq_hdl:
@@ -6992,6 +7007,9 @@ lpfc_sli4_driver_resource_unset(struct lpfc_hba *phba)
 	struct lpfc_fcf_conn_entry *conn_entry, *next_conn_entry;
 
 	free_percpu(phba->sli4_hba.eq_info);
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	free_percpu(phba->sli4_hba.c_stat);
+#endif
 
 	/* Free memory allocated for msi-x interrupt vector to CPU mapping */
 	kfree(phba->sli4_hba.cpu_map);
@@ -10837,6 +10855,9 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors)
 #ifdef CONFIG_X86
 	struct cpuinfo_x86 *cpuinfo;
 #endif
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	struct lpfc_hdwq_stat *c_stat;
+#endif
 
 	max_phys_id = 0;
 	min_phys_id = LPFC_VECTOR_MAP_EMPTY;
@@ -11088,10 +11109,17 @@ lpfc_cpu_affinity_check(struct lpfc_hba *phba, int vectors)
 	idx = 0;
 	for_each_possible_cpu(cpu) {
 		cpup = &phba->sli4_hba.cpu_map[cpu];
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+		c_stat = per_cpu_ptr(phba->sli4_hba.c_stat, cpu);
+		c_stat->hdwq_no = cpup->hdwq;
+#endif
 		if (cpup->hdwq != LPFC_VECTOR_MAP_EMPTY)
 			continue;
 
 		cpup->hdwq = idx++ % phba->cfg_hdw_queue;
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+		c_stat->hdwq_no = cpup->hdwq;
+#endif
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 				"3340 Set Affinity: not present "
 				"CPU %d hdwq %d\n",
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 32b28651039e0..38936b7ce043f 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -1012,6 +1012,9 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 	uint32_t code, status, idx;
 	uint16_t cid, sqhd, data;
 	uint32_t *ptr;
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	int cpu;
+#endif
 
 	/* Sanity check on return of outstanding command */
 	if (!lpfc_ncmd) {
@@ -1184,19 +1187,15 @@ lpfc_nvme_io_cmd_wqe_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pwqeIn,
 		phba->ktime_last_cmd = lpfc_ncmd->ts_data_nvme;
 		lpfc_nvme_ktime(phba, lpfc_ncmd);
 	}
-	if (unlikely(phba->cpucheck_on & LPFC_CHECK_NVME_IO)) {
-		uint32_t cpu;
-		idx = lpfc_ncmd->cur_iocbq.hba_wqidx;
+	if (unlikely(phba->hdwqstat_on & LPFC_CHECK_NVME_IO)) {
 		cpu = raw_smp_processor_id();
-		if (cpu < LPFC_CHECK_CPU_CNT) {
-			if (lpfc_ncmd->cpu != cpu)
-				lpfc_printf_vlog(vport,
-						 KERN_INFO, LOG_NVME_IOERR,
-						 "6701 CPU Check cmpl: "
-						 "cpu %d expect %d\n",
-						 cpu, lpfc_ncmd->cpu);
-			phba->sli4_hba.hdwq[idx].cpucheck_cmpl_io[cpu]++;
-		}
+		this_cpu_inc(phba->sli4_hba.c_stat->cmpl_io);
+		if (lpfc_ncmd->cpu != cpu)
+			lpfc_printf_vlog(vport,
+					 KERN_INFO, LOG_NVME_IOERR,
+					 "6701 CPU Check cmpl: "
+					 "cpu %d expect %d\n",
+					 cpu, lpfc_ncmd->cpu);
 	}
 #endif
 
@@ -1745,19 +1744,17 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 	if (lpfc_ncmd->ts_cmd_start)
 		lpfc_ncmd->ts_cmd_wqput = ktime_get_ns();
 
-	if (phba->cpucheck_on & LPFC_CHECK_NVME_IO) {
+	if (phba->hdwqstat_on & LPFC_CHECK_NVME_IO) {
 		cpu = raw_smp_processor_id();
-		if (cpu < LPFC_CHECK_CPU_CNT) {
-			lpfc_ncmd->cpu = cpu;
-			if (idx != cpu)
-				lpfc_printf_vlog(vport,
-						 KERN_INFO, LOG_NVME_IOERR,
-						"6702 CPU Check cmd: "
-						"cpu %d wq %d\n",
-						lpfc_ncmd->cpu,
-						lpfc_queue_info->index);
-			phba->sli4_hba.hdwq[idx].cpucheck_xmt_io[cpu]++;
-		}
+		this_cpu_inc(phba->sli4_hba.c_stat->xmt_io);
+		lpfc_ncmd->cpu = cpu;
+		if (idx != cpu)
+			lpfc_printf_vlog(vport,
+					 KERN_INFO, LOG_NVME_IOERR,
+					"6702 CPU Check cmd: "
+					"cpu %d wq %d\n",
+					lpfc_ncmd->cpu,
+					lpfc_queue_info->index);
 	}
 #endif
 	return 0;
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 9dc9afe1c2550..f3760a4827d82 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -707,7 +707,7 @@ lpfc_nvmet_xmt_fcp_op_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 	struct lpfc_nvmet_rcv_ctx *ctxp;
 	uint32_t status, result, op, start_clean, logerr;
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	uint32_t id;
+	int id;
 #endif
 
 	ctxp = cmdwqe->context2;
@@ -814,16 +814,14 @@ lpfc_nvmet_xmt_fcp_op_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
 		rsp->done(rsp);
 	}
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	if (phba->cpucheck_on & LPFC_CHECK_NVMET_IO) {
+	if (phba->hdwqstat_on & LPFC_CHECK_NVMET_IO) {
 		id = raw_smp_processor_id();
-		if (id < LPFC_CHECK_CPU_CNT) {
-			if (ctxp->cpu != id)
-				lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
-						"6704 CPU Check cmdcmpl: "
-						"cpu %d expect %d\n",
-						id, ctxp->cpu);
-			phba->sli4_hba.hdwq[rsp->hwqid].cpucheck_cmpl_io[id]++;
-		}
+		this_cpu_inc(phba->sli4_hba.c_stat->cmpl_io);
+		if (ctxp->cpu != id)
+			lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
+					"6704 CPU Check cmdcmpl: "
+					"cpu %d expect %d\n",
+					id, ctxp->cpu);
 	}
 #endif
 }
@@ -931,6 +929,9 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
 	struct lpfc_sli_ring *pring;
 	unsigned long iflags;
 	int rc;
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	int id;
+#endif
 
 	if (phba->pport->load_flag & FC_UNLOADING) {
 		rc = -ENODEV;
@@ -954,16 +955,14 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
 	if (!ctxp->hdwq)
 		ctxp->hdwq = &phba->sli4_hba.hdwq[rsp->hwqid];
 
-	if (phba->cpucheck_on & LPFC_CHECK_NVMET_IO) {
-		int id = raw_smp_processor_id();
-		if (id < LPFC_CHECK_CPU_CNT) {
-			if (rsp->hwqid != id)
-				lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
-						"6705 CPU Check OP: "
-						"cpu %d expect %d\n",
-						id, rsp->hwqid);
-			phba->sli4_hba.hdwq[rsp->hwqid].cpucheck_xmt_io[id]++;
-		}
+	if (phba->hdwqstat_on & LPFC_CHECK_NVMET_IO) {
+		id = raw_smp_processor_id();
+		this_cpu_inc(phba->sli4_hba.c_stat->xmt_io);
+		if (rsp->hwqid != id)
+			lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
+					"6705 CPU Check OP: "
+					"cpu %d expect %d\n",
+					id, rsp->hwqid);
 		ctxp->cpu = id; /* Setup cpu for cmpl check */
 	}
 #endif
@@ -2270,15 +2269,13 @@ lpfc_nvmet_unsol_fcp_buffer(struct lpfc_hba *phba,
 	size = nvmebuf->bytes_recv;
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	if (phba->cpucheck_on & LPFC_CHECK_NVMET_RCV) {
-		if (current_cpu < LPFC_CHECK_CPU_CNT) {
-			if (idx != current_cpu)
-				lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
-						"6703 CPU Check rcv: "
-						"cpu %d expect %d\n",
-						current_cpu, idx);
-			phba->sli4_hba.hdwq[idx].cpucheck_rcv_io[current_cpu]++;
-		}
+	if (phba->hdwqstat_on & LPFC_CHECK_NVMET_IO) {
+		this_cpu_inc(phba->sli4_hba.c_stat->rcv_io);
+		if (idx != current_cpu)
+			lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
+					"6703 CPU Check rcv: "
+					"cpu %d expect %d\n",
+					current_cpu, idx);
 	}
 #endif
 
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index b138d9fee6757..328e000f1b109 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -3803,9 +3803,6 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 	struct Scsi_Host *shost;
 	int idx;
 	uint32_t logit = LOG_FCP;
-#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	int cpu;
-#endif
 
 	/* Guard against abort handler being called at same time */
 	spin_lock(&lpfc_cmd->buf_lock);
@@ -3824,11 +3821,8 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 		phba->sli4_hba.hdwq[idx].scsi_cstat.io_cmpls++;
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	if (unlikely(phba->cpucheck_on & LPFC_CHECK_SCSI_IO)) {
-		cpu = raw_smp_processor_id();
-		if (cpu < LPFC_CHECK_CPU_CNT && phba->sli4_hba.hdwq)
-			phba->sli4_hba.hdwq[idx].cpucheck_cmpl_io[cpu]++;
-	}
+	if (unlikely(phba->hdwqstat_on & LPFC_CHECK_SCSI_IO))
+		this_cpu_inc(phba->sli4_hba.c_stat->cmpl_io);
 #endif
 	shost = cmd->device->host;
 
@@ -4501,9 +4495,6 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	struct lpfc_io_buf *lpfc_cmd;
 	struct fc_rport *rport = starget_to_rport(scsi_target(cmnd->device));
 	int err, idx;
-#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	int cpu;
-#endif
 
 	rdata = lpfc_rport_data_from_scsi_device(cmnd->device);
 
@@ -4624,14 +4615,8 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	lpfc_scsi_prep_cmnd(vport, lpfc_cmd, ndlp);
 
 #ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-	if (unlikely(phba->cpucheck_on & LPFC_CHECK_SCSI_IO)) {
-		cpu = raw_smp_processor_id();
-		if (cpu < LPFC_CHECK_CPU_CNT) {
-			struct lpfc_sli4_hdw_queue *hdwq =
-					&phba->sli4_hba.hdwq[lpfc_cmd->hdwq_no];
-			hdwq->cpucheck_xmt_io[cpu]++;
-		}
-	}
+	if (unlikely(phba->hdwqstat_on & LPFC_CHECK_SCSI_IO))
+		this_cpu_inc(phba->sli4_hba.c_stat->xmt_io);
 #endif
 	err = lpfc_sli_issue_iocb(phba, LPFC_FCP_RING,
 				  &lpfc_cmd->cur_iocbq, SLI_IOCB_RET_IOCB);
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index d963ca8713833..8da7429e385a5 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -697,13 +697,6 @@ struct lpfc_sli4_hdw_queue {
 	struct lpfc_lock_stat lock_conflict;
 #endif
 
-#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
-#define LPFC_CHECK_CPU_CNT    128
-	uint32_t cpucheck_rcv_io[LPFC_CHECK_CPU_CNT];
-	uint32_t cpucheck_xmt_io[LPFC_CHECK_CPU_CNT];
-	uint32_t cpucheck_cmpl_io[LPFC_CHECK_CPU_CNT];
-#endif
-
 	/* Per HDWQ pool resources */
 	struct list_head sgl_list;
 	struct list_head cmd_rsp_buf_list;
@@ -740,6 +733,15 @@ struct lpfc_sli4_hdw_queue {
 #define lpfc_qp_spin_lock(lock, qp, lstat) spin_lock(lock)
 #endif
 
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+struct lpfc_hdwq_stat {
+	u32 hdwq_no;
+	u32 rcv_io;
+	u32 xmt_io;
+	u32 cmpl_io;
+};
+#endif
+
 struct lpfc_sli4_hba {
 	void __iomem *conf_regs_memmap_p; /* Kernel memory mapped address for
 					   * config space registers
@@ -921,6 +923,9 @@ struct lpfc_sli4_hba {
 	struct cpumask numa_mask;
 	uint16_t curr_disp_cpu;
 	struct lpfc_eq_intr_info __percpu *eq_info;
+#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
+	struct lpfc_hdwq_stat __percpu *c_stat;
+#endif
 	uint32_t conf_trunk;
 #define lpfc_conf_trunk_port0_WORD	conf_trunk
 #define lpfc_conf_trunk_port0_SHIFT	0
-- 
2.20.1

[PATCH AUTOSEL 5.5 46/75] scsi: lpfc: Fix lockdep error - register non-static key

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit f861f596714bed06069f1109b89e51f3855c4ddf ]

The following lockdep error was reported when unloading the lpfc driver:

  INFO: trying to register non-static key.
  the code is fine but needs lockdep annotation.
  turning off the locking correctness validator.
  ...
  Call Trace:
  dump_stack+0x96/0xe0
  register_lock_class+0x8b8/0x8c0
  ? lockdep_hardirqs_on+0x190/0x280
  ? is_dynamic_key+0x150/0x150
  ? wait_for_completion_interruptible+0x2a0/0x2a0
  ? wake_up_q+0xd0/0xd0
  __lock_acquire+0xda/0x21a0
  ? register_lock_class+0x8c0/0x8c0
  ? synchronize_rcu_expedited+0x500/0x500
  ? __call_rcu+0x850/0x850
  lock_acquire+0xf3/0x1f0
  ? del_timer_sync+0x5/0xb0
  del_timer_sync+0x3c/0xb0
  ? del_timer_sync+0x5/0xb0
  lpfc_pci_remove_one.cold.102+0x8b7/0x935 [lpfc]
  ...

Unloading the driver resulted in a call to del_timer_sync for the
cpuhp_poll_timer. However the call to setup the timer had never been made,
so the timer structures used by lockdep checking were not initialized.

Unconditionally call setup_timer for the cpuhp_poll_timer during driver
initialization. Calls to start the timer remain "as needed".

Link: https://lore.kernel.org/r/20200322181304.37655-3-jsmart2021@gmail.com
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc_init.c | 5 ++---
 drivers/scsi/lpfc/lpfc_sli.c  | 6 ++----
 2 files changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index d4a90bec93899..42ce31a8fb3c1 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -11209,11 +11209,9 @@ static void lpfc_cpuhp_add(struct lpfc_hba *phba)
 
 	rcu_read_lock();
 
-	if (!list_empty(&phba->poll_list)) {
-		timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0);
+	if (!list_empty(&phba->poll_list))
 		mod_timer(&phba->cpuhp_poll_timer,
 			  jiffies + msecs_to_jiffies(LPFC_POLL_HB));
-	}
 
 	rcu_read_unlock();
 
@@ -13179,6 +13177,7 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid)
 	lpfc_sli4_ras_setup(phba);
 
 	INIT_LIST_HEAD(&phba->poll_list);
+	timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0);
 	cpuhp_state_add_instance_nocalls(lpfc_cpuhp_state, &phba->cpuhp);
 
 	return 0;
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 909554c7c1273..409d54e05302f 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -14448,12 +14448,10 @@ static inline void lpfc_sli4_add_to_poll_list(struct lpfc_queue *eq)
 {
 	struct lpfc_hba *phba = eq->phba;
 
-	if (list_empty(&phba->poll_list)) {
-		timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0);
-		/* kickstart slowpath processing for this eq */
+	/* kickstart slowpath processing if needed */
+	if (list_empty(&phba->poll_list))
 		mod_timer(&phba->cpuhp_poll_timer,
 			  jiffies + msecs_to_jiffies(LPFC_POLL_HB));
-	}
 
 	list_add_rcu(&eq->_poll_list, &phba->poll_list);
 	synchronize_rcu();
-- 
2.20.1

[PATCH AUTOSEL 5.5 65/75] scsi: mpt3sas: Fix kernel panic observed on soft HBA unplug

[Sasha Levin]

From: Sreekanth Reddy <sreekanth.reddy@broadcom.com>

[ Upstream commit cc41f11a21a51d6869d71e525a7264c748d7c0d7 ]

Generic protection fault type kernel panic is observed when user performs
soft (ordered) HBA unplug operation while IOs are running on drives
connected to HBA.

When user performs ordered HBA removal operation, the kernel calls PCI
device's .remove() call back function where driver is flushing out all the
outstanding SCSI IO commands with DID_NO_CONNECT host byte and also unmaps
sg buffers allocated for these IO commands.

However, in the ordered HBA removal case (unlike of real HBA hot removal),
HBA device is still alive and hence HBA hardware is performing the DMA
operations to those buffers on the system memory which are already unmapped
while flushing out the outstanding SCSI IO commands and this leads to
kernel panic.

Don't flush out the outstanding IOs from .remove() path in case of ordered
removal since HBA will be still alive in this case and it can complete the
outstanding IOs. Flush out the outstanding IOs only in case of 'physical
HBA hot unplug' where there won't be any communication with the HBA.

During shutdown also it is possible that HBA hardware can perform DMA
operations on those outstanding IO buffers which are completed with
DID_NO_CONNECT by the driver from .shutdown(). So same above fix is applied
in shutdown path as well.

It is safe to drop the outstanding commands when HBA is inaccessible such
as when permanent PCI failure happens, when HBA is in non-operational
state, or when someone does a real HBA hot unplug operation. Since driver
knows that HBA is inaccessible during these cases, it is safe to drop the
outstanding commands instead of waiting for SCSI error recovery to kick in
and clear these outstanding commands.

Link: https://lore.kernel.org/r/1585302763-23007-1-git-send-email-sreekanth.reddy@broadcom.com
Fixes: c666d3be99c0 ("scsi: mpt3sas: wait for and flush running commands on shutdown/unload")
Cc: stable@vger.kernel.org #v4.14.174+
Signed-off-by: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/mpt3sas/mpt3sas_scsih.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index a038be8a0e905..c919cb7ad5248 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -9747,8 +9747,8 @@ static void scsih_remove(struct pci_dev *pdev)
 
 	ioc->remove_host = 1;
 
-	mpt3sas_wait_for_commands_to_complete(ioc);
-	_scsih_flush_running_cmds(ioc);
+	if (!pci_device_is_present(pdev))
+		_scsih_flush_running_cmds(ioc);
 
 	_scsih_fw_event_cleanup_queue(ioc);
 
@@ -9831,8 +9831,8 @@ scsih_shutdown(struct pci_dev *pdev)
 
 	ioc->remove_host = 1;
 
-	mpt3sas_wait_for_commands_to_complete(ioc);
-	_scsih_flush_running_cmds(ioc);
+	if (!pci_device_is_present(pdev))
+		_scsih_flush_running_cmds(ioc);
 
 	_scsih_fw_event_cleanup_queue(ioc);
 
-- 
2.20.1