1 files changed, 100 insertions, 82 deletions

diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 7f12d931fe7c..6e4112143c76 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -149,6 +149,8 @@ struct hv_fc_wwn_packet {
 */
 static int vmstor_proto_version;
 
+static bool hv_dev_is_fc(struct hv_device *hv_dev);
+
 #define STORVSC_LOGGING_NONE	0
 #define STORVSC_LOGGING_ERROR	1
 #define STORVSC_LOGGING_WARN	2
@@ -169,6 +171,12 @@ do {								\
 		dev_warn(&(dev)->device, fmt, ##__VA_ARGS__);	\
 } while (0)
 
+#define storvsc_log_ratelimited(dev, level, fmt, ...)				\
+do {										\
+	if (do_logging(level))							\
+		dev_warn_ratelimited(&(dev)->device, fmt, ##__VA_ARGS__);	\
+} while (0)
+
 struct vmscsi_request {
 	u16 length;
 	u8 srb_status;
@@ -316,6 +324,9 @@ enum storvsc_request_type {
 #define SRB_STATUS_ABORTED		0x02
 #define SRB_STATUS_ERROR		0x04
 #define SRB_STATUS_INVALID_REQUEST	0x06
+#define SRB_STATUS_TIMEOUT		0x09
+#define SRB_STATUS_SELECTION_TIMEOUT	0x0A
+#define SRB_STATUS_BUS_RESET		0x0E
 #define SRB_STATUS_DATA_OVERRUN		0x12
 #define SRB_STATUS_INVALID_LUN		0x20
 #define SRB_STATUS_INTERNAL_ERROR	0x30
@@ -327,6 +338,7 @@ enum storvsc_request_type {
  */
 
 static int storvsc_ringbuffer_size = (128 * 1024);
+static int aligned_ringbuffer_size;
 static u32 max_outstanding_req_per_channel;
 static int storvsc_change_queue_depth(struct scsi_device *sdev, int queue_depth);
 
@@ -350,7 +362,7 @@ MODULE_PARM_DESC(ring_avail_percent_lowater,
 /*
  * Timeout in seconds for all devices managed by this driver.
  */
-static int storvsc_timeout = 180;
+static const int storvsc_timeout = 180;
 
 #if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
 static struct scsi_transport_template *fc_transport_template;
@@ -366,6 +378,7 @@ static void storvsc_on_channel_callback(void *context);
 #define STORVSC_FC_MAX_LUNS_PER_TARGET			255
 #define STORVSC_FC_MAX_TARGETS				128
 #define STORVSC_FC_MAX_CHANNELS				8
+#define STORVSC_FC_MAX_XFER_SIZE			((u32)(512 * 1024))
 
 #define STORVSC_IDE_MAX_LUNS_PER_TARGET			64
 #define STORVSC_IDE_MAX_TARGETS				1
@@ -471,7 +484,7 @@ static void storvsc_device_scan(struct work_struct *work)
 	sdev = scsi_device_lookup(wrk->host, 0, wrk->tgt_id, wrk->lun);
 	if (!sdev)
 		goto done;
-	scsi_rescan_device(&sdev->sdev_gendev);
+	scsi_rescan_device(sdev);
 	scsi_device_put(sdev);
 
 done:
@@ -683,8 +696,8 @@ static void handle_sc_creation(struct vmbus_channel *new_sc)
 	new_sc->next_request_id_callback = storvsc_next_request_id;
 
 	ret = vmbus_open(new_sc,
-			 storvsc_ringbuffer_size,
-			 storvsc_ringbuffer_size,
+			 aligned_ringbuffer_size,
+			 aligned_ringbuffer_size,
 			 (void *)&props,
 			 sizeof(struct vmstorage_channel_properties),
 			 storvsc_on_channel_callback, new_sc);
@@ -755,7 +768,7 @@ static void  handle_multichannel_storage(struct hv_device *device, int max_chns)
 		return;
 	}
 
-	t = wait_for_completion_timeout(&request->wait_event, 10*HZ);
+	t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ);
 	if (t == 0) {
 		dev_err(dev, "Failed to create sub-channel: timed out\n");
 		return;
@@ -763,7 +776,7 @@ static void  handle_multichannel_storage(struct hv_device *device, int max_chns)
 
 	if (vstor_packet->operation != VSTOR_OPERATION_COMPLETE_IO ||
 	    vstor_packet->status != 0) {
-		dev_err(dev, "Failed to create sub-channel: op=%d, sts=%d\n",
+		dev_err(dev, "Failed to create sub-channel: op=%d, host=0x%x\n",
 			vstor_packet->operation, vstor_packet->status);
 		return;
 	}
@@ -820,7 +833,7 @@ static int storvsc_execute_vstor_op(struct hv_device *device,
 	if (ret != 0)
 		return ret;
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
+	t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ);
 	if (t == 0)
 		return -ETIMEDOUT;
 
@@ -910,14 +923,13 @@ static int storvsc_channel_init(struct hv_device *device, bool is_fc)
 
 	/*
 	 * Allocate state to manage the sub-channels.
-	 * We allocate an array based on the numbers of possible CPUs
-	 * (Hyper-V does not support cpu online/offline).
-	 * This Array will be sparseley populated with unique
-	 * channels - primary + sub-channels.
-	 * We will however populate all the slots to evenly distribute
-	 * the load.
+	 * We allocate an array based on the number of CPU ids. This array
+	 * is initially sparsely populated for the CPUs assigned to channels:
+	 * primary + sub-channels. As I/Os are initiated by different CPUs,
+	 * the slots for all online CPUs are populated to evenly distribute
+	 * the load across all channels.
 	 */
-	stor_device->stor_chns = kcalloc(num_possible_cpus(), sizeof(void *),
+	stor_device->stor_chns = kcalloc(nr_cpu_ids, sizeof(void *),
 					 GFP_KERNEL);
 	if (stor_device->stor_chns == NULL)
 		return -ENOMEM;
@@ -980,6 +992,10 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb,
 	case SRB_STATUS_ABORTED:
 	case SRB_STATUS_INVALID_REQUEST:
 	case SRB_STATUS_INTERNAL_ERROR:
+	case SRB_STATUS_TIMEOUT:
+	case SRB_STATUS_SELECTION_TIMEOUT:
+	case SRB_STATUS_BUS_RESET:
+	case SRB_STATUS_DATA_OVERRUN:
 		if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID) {
 			/* Check for capacity change */
 			if ((asc == 0x2a) && (ascq == 0x9)) {
@@ -1129,6 +1145,7 @@ static void storvsc_on_io_completion(struct storvsc_device *stor_device,
 	 * not correctly handle:
 	 * INQUIRY command with page code parameter set to 0x80
 	 * MODE_SENSE command with cmd[2] == 0x1c
+	 * MAINTENANCE_IN is not supported by HyperV FC passthrough
 	 *
 	 * Setup srb and scsi status so this won't be fatal.
 	 * We do this so we can distinguish truly fatal failues
@@ -1136,7 +1153,9 @@ static void storvsc_on_io_completion(struct storvsc_device *stor_device,
 	 */
 
 	if ((stor_pkt->vm_srb.cdb[0] == INQUIRY) ||
-	   (stor_pkt->vm_srb.cdb[0] == MODE_SENSE)) {
+	   (stor_pkt->vm_srb.cdb[0] == MODE_SENSE) ||
+	   (stor_pkt->vm_srb.cdb[0] == MAINTENANCE_IN &&
+	   hv_dev_is_fc(device))) {
 		vstor_packet->vm_srb.scsi_status = 0;
 		vstor_packet->vm_srb.srb_status = SRB_STATUS_SUCCESS;
 	}
@@ -1163,8 +1182,8 @@ static void storvsc_on_io_completion(struct storvsc_device *stor_device,
 		int loglevel = (stor_pkt->vm_srb.cdb[0] == TEST_UNIT_READY) ?
 			STORVSC_LOGGING_WARN : STORVSC_LOGGING_ERROR;
 
-		storvsc_log(device, loglevel,
-			"tag#%d cmd 0x%x status: scsi 0x%x srb 0x%x hv 0x%x\n",
+		storvsc_log_ratelimited(device, loglevel,
+			"tag#%d cmd 0x%x status: scsi 0x%x srb 0x%x host 0x%x\n",
 			scsi_cmd_to_rq(request->cmd)->tag,
 			stor_pkt->vm_srb.cdb[0],
 			vstor_packet->vm_srb.scsi_status,
@@ -1331,6 +1350,8 @@ static int storvsc_connect_to_vsp(struct hv_device *device, u32 ring_size,
 		return ret;
 
 	ret = storvsc_channel_init(device, is_fc);
+	if (ret)
+		vmbus_close(device->channel);
 
 	return ret;
 }
@@ -1385,14 +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;
@@ -1448,59 +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];
@@ -1565,7 +1580,8 @@ static int storvsc_device_alloc(struct scsi_device *sdevice)
 	return 0;
 }
 
-static int storvsc_device_configure(struct scsi_device *sdevice)
+static int storvsc_sdev_configure(struct scsi_device *sdevice,
+				  struct queue_limits *lim)
 {
 	blk_queue_rq_timeout(sdevice->request_queue, (storvsc_timeout * HZ));
 
@@ -1593,7 +1609,7 @@ static int storvsc_device_configure(struct scsi_device *sdevice)
 	return 0;
 }
 
-static int storvsc_get_chs(struct scsi_device *sdev, struct block_device * bdev,
+static int storvsc_get_chs(struct scsi_device *sdev, struct gendisk *unused,
 			   sector_t capacity, int *info)
 {
 	sector_t nsect = capacity;
@@ -1648,7 +1664,7 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd)
 	if (ret != 0)
 		return FAILED;
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
+	t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ);
 	if (t == 0)
 		return TIMEOUT_ERROR;
 
@@ -1673,10 +1689,6 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd)
  */
 static enum scsi_timeout_action storvsc_eh_timed_out(struct scsi_cmnd *scmnd)
 {
-#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
-	if (scmnd->device->host->transportt == fc_transport_template)
-		return fc_eh_timed_out(scmnd);
-#endif
 	return SCSI_EH_RESET_TIMER;
 }
 
@@ -1784,6 +1796,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 
 	length = scsi_bufflen(scmnd);
 	payload = (struct vmbus_packet_mpb_array *)&cmd_request->mpb;
+	payload->range.len = 0;
 	payload_sz = 0;
 
 	if (scsi_sg_count(scmnd)) {
@@ -1802,6 +1815,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 				return SCSI_MLQUEUE_DEVICE_BUSY;
 		}
 
+		payload->rangecount = 1;
 		payload->range.len = length;
 		payload->range.offset = offset_in_hvpg;
 
@@ -1870,8 +1884,8 @@ static struct scsi_host_template scsi_driver = {
 	.eh_host_reset_handler =	storvsc_host_reset_handler,
 	.proc_name =		"storvsc_host",
 	.eh_timed_out =		storvsc_eh_timed_out,
-	.slave_alloc =		storvsc_device_alloc,
-	.slave_configure =	storvsc_device_configure,
+	.sdev_init =		storvsc_device_alloc,
+	.sdev_configure =	storvsc_sdev_configure,
 	.cmd_per_lun =		2048,
 	.this_id =		-1,
 	/* Ensure there are no gaps in presented sgls */
@@ -1921,8 +1935,8 @@ static int storvsc_probe(struct hv_device *device,
 	int num_present_cpus = num_present_cpus();
 	struct Scsi_Host *host;
 	struct hv_host_device *host_dev;
-	bool dev_is_ide = ((dev_id->driver_data == IDE_GUID) ? true : false);
-	bool is_fc = ((dev_id->driver_data == SFC_GUID) ? true : false);
+	bool dev_is_ide = dev_id->driver_data == IDE_GUID;
+	bool is_fc = dev_id->driver_data == SFC_GUID;
 	int target = 0;
 	struct storvsc_device *stor_device;
 	int max_sub_channels = 0;
@@ -1969,7 +1983,7 @@ static int storvsc_probe(struct hv_device *device,
 	dma_set_min_align_mask(&device->device, HV_HYP_PAGE_SIZE - 1);
 
 	stor_device->port_number = host->host_no;
-	ret = storvsc_connect_to_vsp(device, storvsc_ringbuffer_size, is_fc);
+	ret = storvsc_connect_to_vsp(device, aligned_ringbuffer_size, is_fc);
 	if (ret)
 		goto err_out1;
 
@@ -2006,6 +2020,9 @@ static int storvsc_probe(struct hv_device *device,
 	 * protecting it from any weird value.
 	 */
 	max_xfer_bytes = round_down(stor_device->max_transfer_bytes, HV_HYP_PAGE_SIZE);
+	if (is_fc)
+		max_xfer_bytes = min(max_xfer_bytes, STORVSC_FC_MAX_XFER_SIZE);
+
 	/* max_hw_sectors_kb */
 	host->max_sectors = max_xfer_bytes >> 9;
 	/*
@@ -2157,7 +2174,7 @@ static int storvsc_resume(struct hv_device *hv_dev)
 {
 	int ret;
 
-	ret = storvsc_connect_to_vsp(hv_dev, storvsc_ringbuffer_size,
+	ret = storvsc_connect_to_vsp(hv_dev, aligned_ringbuffer_size,
 				     hv_dev_is_fc(hv_dev));
 	return ret;
 }
@@ -2191,8 +2208,9 @@ static int __init storvsc_drv_init(void)
 	 * the ring buffer indices) by the max request size (which is
 	 * vmbus_channel_packet_multipage_buffer + struct vstor_packet + u64)
 	 */
+	aligned_ringbuffer_size = VMBUS_RING_SIZE(storvsc_ringbuffer_size);
 	max_outstanding_req_per_channel =
-		((storvsc_ringbuffer_size - PAGE_SIZE) /
+		((aligned_ringbuffer_size - PAGE_SIZE) /
 		ALIGN(MAX_MULTIPAGE_BUFFER_PACKET +
 		sizeof(struct vstor_packet) + sizeof(u64),
 		sizeof(u64)));