Merge tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsiHEADmaster

Pull SCSI fixes from James Bottomley:
 "All driver fixes. The big change is the storvsc one to rejig the
  hyper-v channel handling to be more efficient for SMP virtual
  machines"

* tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi:
  scsi: ufs: phy: dt-bindings: Add QMP UFS PHY compatible for Kaanapali
  scsi: ufs: qcom: dt-bindings: Document the Kaanapali UFS controller
  scsi: libfc: Prevent integer overflow in fc_fcp_recv_data()
  scsi: qla4xxx: Fix typos in comments
  scsi: storvsc: Prefer returning channel with the same CPU as on the I/O issuing CPU

3 files changed, 50 insertions, 56 deletions

diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c
index 16d0f02af1e4..31d08c115521 100644
--- a/drivers/scsi/libfc/fc_fcp.c
+++ b/drivers/scsi/libfc/fc_fcp.c
@@ -503,7 +503,7 @@ static void fc_fcp_recv_data(struct fc_fcp_pkt *fsp, struct fc_frame *fp)
 		host_bcode = FC_ERROR;
 		goto err;
 	}
-	if (offset + len > fsp->data_len) {
+	if (size_add(offset, len) > fsp->data_len) {
 		/* this should never happen */
 		if ((fr_flags(fp) & FCPHF_CRC_UNCHECKED) &&
 		    fc_frame_crc_check(fp))
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index a761c0aa5127..83ff66f954e6 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -4104,7 +4104,7 @@ void qla4xxx_srb_compl(struct kref *ref)
  * The mid-level driver tries to ensure that queuecommand never gets
  * invoked concurrently with itself or the interrupt handler (although
  * the interrupt handler may call this routine as part of request-
- * completion handling).   Unfortunely, it sometimes calls the scheduler
+ * completion handling). Unfortunately, it sometimes calls the scheduler
  * in interrupt context which is a big NO! NO!.
  **/
 static int qla4xxx_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
@@ -4647,7 +4647,7 @@ static int qla4xxx_cmd_wait(struct scsi_qla_host *ha)
 			cmd = scsi_host_find_tag(ha->host, index);
 			/*
 			 * We cannot just check if the index is valid,
-			 * becase if we are run from the scsi eh, then
+			 * because if we are run from the scsi eh, then
 			 * the scsi/block layer is going to prevent
 			 * the tag from being released.
 			 */
@@ -4952,7 +4952,7 @@ recover_ha_init_adapter:
 	/* Upon successful firmware/chip reset, re-initialize the adapter */
 	if (status == QLA_SUCCESS) {
 		/* For ISP-4xxx, force function 1 to always initialize
-		 * before function 3 to prevent both funcions from
+		 * before function 3 to prevent both functions from
 		 * stepping on top of the other */
 		if (is_qla40XX(ha) && (ha->mac_index == 3))
 			ssleep(6);
@@ -6914,7 +6914,7 @@ static int qla4xxx_sess_conn_setup(struct scsi_qla_host *ha,
 	struct ddb_entry *ddb_entry = NULL;
 
 	/* Create session object, with INVALID_ENTRY,
-	 * the targer_id would get set when we issue the login
+	 * the target_id would get set when we issue the login
 	 */
 	cls_sess = iscsi_session_setup(&qla4xxx_iscsi_transport, ha->host,
 				       cmds_max, sizeof(struct ddb_entry),
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 567f9cd29102..6e4112143c76 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1406,14 +1406,19 @@ static struct vmbus_channel *get_og_chn(struct storvsc_device *stor_device,
 	}
 
 	/*
-	 * Our channel array is sparsley populated and we
+	 * Our channel array could be sparsley populated and we
 	 * initiated I/O on a processor/hw-q that does not
 	 * currently have a designated channel. Fix this.
 	 * The strategy is simple:
-	 * I. Ensure NUMA locality
-	 * II. Distribute evenly (best effort)
+	 * I. Prefer the channel associated with the current CPU
+	 * II. Ensure NUMA locality
+	 * III. Distribute evenly (best effort)
 	 */
 
+	/* Prefer the channel on the I/O issuing processor/hw-q */
+	if (cpumask_test_cpu(q_num, &stor_device->alloced_cpus))
+		return stor_device->stor_chns[q_num];
+
 	node_mask = cpumask_of_node(cpu_to_node(q_num));
 
 	num_channels = 0;
@@ -1469,59 +1474,48 @@ static int storvsc_do_io(struct hv_device *device,
 	/* See storvsc_change_target_cpu(). */
 	outgoing_channel = READ_ONCE(stor_device->stor_chns[q_num]);
 	if (outgoing_channel != NULL) {
-		if (outgoing_channel->target_cpu == q_num) {
-			/*
-			 * Ideally, we want to pick a different channel if
-			 * available on the same NUMA node.
-			 */
-			node_mask = cpumask_of_node(cpu_to_node(q_num));
-			for_each_cpu_wrap(tgt_cpu,
-				 &stor_device->alloced_cpus, q_num + 1) {
-				if (!cpumask_test_cpu(tgt_cpu, node_mask))
-					continue;
-				if (tgt_cpu == q_num)
-					continue;
-				channel = READ_ONCE(
-					stor_device->stor_chns[tgt_cpu]);
-				if (channel == NULL)
-					continue;
-				if (hv_get_avail_to_write_percent(
-							&channel->outbound)
-						> ring_avail_percent_lowater) {
-					outgoing_channel = channel;
-					goto found_channel;
-				}
-			}
+		if (hv_get_avail_to_write_percent(&outgoing_channel->outbound)
+				> ring_avail_percent_lowater)
+			goto found_channel;
 
-			/*
-			 * All the other channels on the same NUMA node are
-			 * busy. Try to use the channel on the current CPU
-			 */
-			if (hv_get_avail_to_write_percent(
-						&outgoing_channel->outbound)
-					> ring_avail_percent_lowater)
+		/*
+		 * Channel is busy, try to find a channel on the same NUMA node
+		 */
+		node_mask = cpumask_of_node(cpu_to_node(q_num));
+		for_each_cpu_wrap(tgt_cpu, &stor_device->alloced_cpus,
+				  q_num + 1) {
+			if (!cpumask_test_cpu(tgt_cpu, node_mask))
+				continue;
+			channel = READ_ONCE(stor_device->stor_chns[tgt_cpu]);
+			if (!channel)
+				continue;
+			if (hv_get_avail_to_write_percent(&channel->outbound)
+					> ring_avail_percent_lowater) {
+				outgoing_channel = channel;
 				goto found_channel;
+			}
+		}
 
-			/*
-			 * If we reach here, all the channels on the current
-			 * NUMA node are busy. Try to find a channel in
-			 * other NUMA nodes
-			 */
-			for_each_cpu(tgt_cpu, &stor_device->alloced_cpus) {
-				if (cpumask_test_cpu(tgt_cpu, node_mask))
-					continue;
-				channel = READ_ONCE(
-					stor_device->stor_chns[tgt_cpu]);
-				if (channel == NULL)
-					continue;
-				if (hv_get_avail_to_write_percent(
-							&channel->outbound)
-						> ring_avail_percent_lowater) {
-					outgoing_channel = channel;
-					goto found_channel;
-				}
+		/*
+		 * If we reach here, all the channels on the current
+		 * NUMA node are busy. Try to find a channel in
+		 * all NUMA nodes
+		 */
+		for_each_cpu_wrap(tgt_cpu, &stor_device->alloced_cpus,
+				  q_num + 1) {
+			channel = READ_ONCE(stor_device->stor_chns[tgt_cpu]);
+			if (!channel)
+				continue;
+			if (hv_get_avail_to_write_percent(&channel->outbound)
+					> ring_avail_percent_lowater) {
+				outgoing_channel = channel;
+				goto found_channel;
 			}
 		}
+		/*
+		 * If we reach here, all the channels are busy. Use the
+		 * original channel found.
+		 */
 	} else {
 		spin_lock_irqsave(&stor_device->lock, flags);
 		outgoing_channel = stor_device->stor_chns[q_num];