[PATCH v4 1/5] add io_uring with IOPOLL support in scsi layer

[PATCH v4 1/5] add io_uring with IOPOLL support in scsi layer

[Kashyap Desai]

[-- Attachment #1: Type: text/plain, Size: 3424 bytes --]

io_uring with IOPOLL is not currently supported in scsi mid layer.
Outside of that everything else should work and no extra support
in the driver is needed.

Currently io_uring with IOPOLL support is only available in block layer.
This patch is to extend support of mq_poll in scsi layer.

Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: John Garry <john.garry@huawei.com>

Cc: sumit.saxena@broadcom.com
Cc: chandrakanth.patil@broadcom.com
Cc: linux-block@vger.kernel.org
---
 drivers/scsi/scsi_lib.c  | 16 ++++++++++++++++
 include/scsi/scsi_cmnd.h |  1 +
 include/scsi/scsi_host.h | 11 +++++++++++
 3 files changed, 28 insertions(+)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index d0ae586565f8..8c29bf0e4cfd 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1789,6 +1789,19 @@ static void scsi_mq_exit_request(struct blk_mq_tag_set *set, struct request *rq,
 			       cmd->sense_buffer);
 }
 
+
+static int scsi_mq_poll(struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
+	struct scsi_device *sdev = q->queuedata;
+	struct Scsi_Host *shost = sdev->host;
+
+	if (shost->hostt->mq_poll)
+		return shost->hostt->mq_poll(shost, hctx->queue_num);
+
+	return 0;
+}
+
 static int scsi_map_queues(struct blk_mq_tag_set *set)
 {
 	struct Scsi_Host *shost = container_of(set, struct Scsi_Host, tag_set);
@@ -1856,6 +1869,7 @@ static const struct blk_mq_ops scsi_mq_ops_no_commit = {
 	.cleanup_rq	= scsi_cleanup_rq,
 	.busy		= scsi_mq_lld_busy,
 	.map_queues	= scsi_map_queues,
+	.poll		= scsi_mq_poll,
 };
 
 
@@ -1884,6 +1898,7 @@ static const struct blk_mq_ops scsi_mq_ops = {
 	.cleanup_rq	= scsi_cleanup_rq,
 	.busy		= scsi_mq_lld_busy,
 	.map_queues	= scsi_map_queues,
+	.poll		= scsi_mq_poll,
 };
 
 struct request_queue *scsi_mq_alloc_queue(struct scsi_device *sdev)
@@ -1916,6 +1931,7 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost)
 	else
 		tag_set->ops = &scsi_mq_ops_no_commit;
 	tag_set->nr_hw_queues = shost->nr_hw_queues ? : 1;
+	tag_set->nr_maps = shost->nr_maps ? : 1;
 	tag_set->queue_depth = shost->can_queue;
 	tag_set->cmd_size = cmd_size;
 	tag_set->numa_node = NUMA_NO_NODE;
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index ace15b5dc956..1d8a0f6ea8c5 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -10,6 +10,7 @@
 #include <linux/timer.h>
 #include <linux/scatterlist.h>
 #include <scsi/scsi_device.h>
+#include <scsi/scsi_host.h>
 #include <scsi/scsi_request.h>
 
 struct Scsi_Host;
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index e30fd963b97d..3d627bf7b951 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -270,6 +270,16 @@ struct scsi_host_template {
 	 */
 	int (* map_queues)(struct Scsi_Host *shost);
 
+	/*
+	 * SCSI interface of blk_poll - poll for IO completions.
+	 * Possible interface only if scsi LLD expose multiple h/w queues.
+	 *
+	 * Return value: Number of completed entries found.
+	 *
+	 * Status: OPTIONAL
+	 */
+	int (* mq_poll)(struct Scsi_Host *shost, unsigned int queue_num);
+
 	/*
 	 * Check if scatterlists need to be padded for DMA draining.
 	 *
@@ -616,6 +626,7 @@ struct Scsi_Host {
 	 * the total queue depth is can_queue.
 	 */
 	unsigned nr_hw_queues;
+	unsigned nr_maps;
 	unsigned active_mode:2;
 	unsigned unchecked_isa_dma:1;
 
-- 
2.18.1


[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4169 bytes --]

[PATCH v4 2/5] megaraid_sas: iouring iopoll support

[Kashyap Desai]

[-- Attachment #1: Type: text/plain, Size: 12799 bytes --]

Add support of iouring iopoll interface. This feature requires shared
hosttag support in kernel and driver.

Driver will work in non-IRQ mode = There will not be any msix vector
associated for poll_queues and h/w can still work in this mode.
MegaRaid h/w is single submission queue and multiple reply queue, but
using shared host tagset support it will enable simulated multiple hw queue.

Driver allocates some extra reply queues and it will be marked as poll_queue.
These poll_queues will not have associated msix vectors. All the IO
completion on this queue will be done from IOPOLL interface.

megaraid_sas driver having 8 poll_queues and using io_uring hiprio=1 settings,
It can reach 3.2M IOPs and there is zero interrupt generated by h/w.

This feature can be enabled using module parameter poll_queues.

Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Cc: sumit.saxena@broadcom.com
Cc: chandrakanth.patil@broadcom.com
Cc: linux-block@vger.kernel.org
---
 drivers/scsi/megaraid/megaraid_sas.h        |  3 +
 drivers/scsi/megaraid/megaraid_sas_base.c   | 87 ++++++++++++++++++---
 drivers/scsi/megaraid/megaraid_sas_fusion.c | 42 +++++++++-
 drivers/scsi/megaraid/megaraid_sas_fusion.h |  2 +
 4 files changed, 123 insertions(+), 11 deletions(-)

diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index 0f808d63580e..d8b1797e2768 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -2212,6 +2212,7 @@ struct megasas_irq_context {
 	struct irq_poll irqpoll;
 	bool irq_poll_scheduled;
 	bool irq_line_enable;
+	atomic_t   in_used;
 };
 
 struct MR_DRV_SYSTEM_INFO {
@@ -2446,6 +2447,7 @@ struct megasas_instance {
 	bool support_pci_lane_margining;
 	u8  low_latency_index_start;
 	int perf_mode;
+	int iopoll_q_count;
 };
 
 struct MR_LD_VF_MAP {
@@ -2726,5 +2728,6 @@ void megasas_init_debugfs(void);
 void megasas_exit_debugfs(void);
 void megasas_setup_debugfs(struct megasas_instance *instance);
 void megasas_destroy_debugfs(struct megasas_instance *instance);
+int megasas_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num);
 
 #endif				/*LSI_MEGARAID_SAS_H */
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 63a4f48bdc75..25673d0ee524 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -114,6 +114,15 @@ unsigned int enable_sdev_max_qd;
 module_param(enable_sdev_max_qd, int, 0444);
 MODULE_PARM_DESC(enable_sdev_max_qd, "Enable sdev max qd as can_queue. Default: 0");
 
+int poll_queues;
+module_param(poll_queues, int, 0444);
+MODULE_PARM_DESC(poll_queues, "Number of queues to be use for io_uring poll mode.\n\t\t"
+		"This parameter is effective only if host_tagset_enable=1 &\n\t\t"
+		"It is not applicable for MFI_SERIES. &\n\t\t"
+		"Driver will work in latency mode. &\n\t\t"
+		"High iops queues are not allocated &\n\t\t"
+		);
+
 int host_tagset_enable = 1;
 module_param(host_tagset_enable, int, 0444);
 MODULE_PARM_DESC(host_tagset_enable, "Shared host tagset enable/disable Default: enable(1)");
@@ -207,6 +216,7 @@ static bool support_pci_lane_margining;
 static spinlock_t poll_aen_lock;
 
 extern struct dentry *megasas_debugfs_root;
+extern int megasas_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num);
 
 void
 megasas_complete_cmd(struct megasas_instance *instance, struct megasas_cmd *cmd,
@@ -3127,14 +3137,37 @@ megasas_bios_param(struct scsi_device *sdev, struct block_device *bdev,
 static int megasas_map_queues(struct Scsi_Host *shost)
 {
 	struct megasas_instance *instance;
+	int qoff = 0, offset;
+	struct blk_mq_queue_map *map;
 
 	instance = (struct megasas_instance *)shost->hostdata;
 
 	if (shost->nr_hw_queues == 1)
 		return 0;
 
-	return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
-			instance->pdev, instance->low_latency_index_start);
+	offset = instance->low_latency_index_start;
+
+	/* Setup Default hctx */
+	map = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
+	map->nr_queues = instance->msix_vectors - offset;
+	map->queue_offset = 0;
+	blk_mq_pci_map_queues(map, instance->pdev, offset);
+	qoff += map->nr_queues;
+	offset += map->nr_queues;
+
+	/* Setup Poll hctx */
+	map = &shost->tag_set.map[HCTX_TYPE_POLL];
+	map->nr_queues = instance->iopoll_q_count;
+	if (map->nr_queues) {
+		/*
+		 * The poll queue(s) doesn't have an IRQ (and hence IRQ
+		 * affinity), so use the regular blk-mq cpu mapping
+		 */
+		map->queue_offset = qoff;
+		blk_mq_map_queues(map);
+	}
+
+	return 0;
 }
 
 static void megasas_aen_polling(struct work_struct *work);
@@ -3446,6 +3479,7 @@ static struct scsi_host_template megasas_template = {
 	.shost_attrs = megaraid_host_attrs,
 	.bios_param = megasas_bios_param,
 	.map_queues = megasas_map_queues,
+	.mq_poll = megasas_blk_mq_poll,
 	.change_queue_depth = scsi_change_queue_depth,
 	.max_segment_size = 0xffffffff,
 };
@@ -5834,13 +5868,16 @@ __megasas_alloc_irq_vectors(struct megasas_instance *instance)
 	irq_flags = PCI_IRQ_MSIX;
 
 	if (instance->smp_affinity_enable)
-		irq_flags |= PCI_IRQ_AFFINITY;
+		irq_flags |= PCI_IRQ_AFFINITY | PCI_IRQ_ALL_TYPES;
 	else
 		descp = NULL;
 
+	/* Do not allocate msix vectors for poll_queues.
+	 * msix_vectors is always within a range of FW supported reply queue.
+	 */
 	i = pci_alloc_irq_vectors_affinity(instance->pdev,
 		instance->low_latency_index_start,
-		instance->msix_vectors, irq_flags, descp);
+		instance->msix_vectors - instance->iopoll_q_count, irq_flags, descp);
 
 	return i;
 }
@@ -5856,10 +5893,30 @@ megasas_alloc_irq_vectors(struct megasas_instance *instance)
 	int i;
 	unsigned int num_msix_req;
 
+	instance->iopoll_q_count = 0;
+	if ((instance->adapter_type != MFI_SERIES) &&
+		poll_queues) {
+
+		instance->perf_mode = MR_LATENCY_PERF_MODE;
+		instance->low_latency_index_start = 1;
+
+		/* reserve for default and non-mananged pre-vector. */
+		if (instance->msix_vectors > (poll_queues + 2))
+			instance->iopoll_q_count = poll_queues;
+		else
+			instance->iopoll_q_count = 0;
+
+		num_msix_req = num_online_cpus() + instance->low_latency_index_start;
+		instance->msix_vectors = min(num_msix_req,
+				instance->msix_vectors);
+
+	}
+
 	i = __megasas_alloc_irq_vectors(instance);
 
-	if ((instance->perf_mode == MR_BALANCED_PERF_MODE) &&
-	    (i != instance->msix_vectors)) {
+	if (((instance->perf_mode == MR_BALANCED_PERF_MODE)
+		|| instance->iopoll_q_count) &&
+	    (i != (instance->msix_vectors - instance->iopoll_q_count))) {
 		if (instance->msix_vectors)
 			pci_free_irq_vectors(instance->pdev);
 		/* Disable Balanced IOPS mode and try realloc vectors */
@@ -5870,12 +5927,15 @@ megasas_alloc_irq_vectors(struct megasas_instance *instance)
 		instance->msix_vectors = min(num_msix_req,
 				instance->msix_vectors);
 
+		instance->iopoll_q_count = 0;
 		i = __megasas_alloc_irq_vectors(instance);
 
 	}
 
 	dev_info(&instance->pdev->dev,
-		"requested/available msix %d/%d\n", instance->msix_vectors, i);
+		"requested/available msix %d/%d poll_queue %d\n",
+			instance->msix_vectors - instance->iopoll_q_count,
+			i, instance->iopoll_q_count);
 
 	if (i > 0)
 		instance->msix_vectors = i;
@@ -6841,12 +6901,18 @@ static int megasas_io_attach(struct megasas_instance *instance)
 		instance->smp_affinity_enable) {
 		host->host_tagset = 1;
 		host->nr_hw_queues = instance->msix_vectors -
-			instance->low_latency_index_start;
+			instance->low_latency_index_start + instance->iopoll_q_count;
+		if (instance->iopoll_q_count)
+			host->nr_maps = 3;
+	} else {
+		instance->iopoll_q_count = 0;
 	}
 
 	dev_info(&instance->pdev->dev,
-		"Max firmware commands: %d shared with nr_hw_queues = %d\n",
-		instance->max_fw_cmds, host->nr_hw_queues);
+		"Max firmware commands: %d shared with default "
+		"hw_queues = %d poll_queues %d\n", instance->max_fw_cmds,
+		host->nr_hw_queues - instance->iopoll_q_count,
+		instance->iopoll_q_count);
 	/*
 	 * Notify the mid-layer about the new controller
 	 */
@@ -8859,6 +8925,7 @@ static int __init megasas_init(void)
 		msix_vectors = 1;
 		rdpq_enable = 0;
 		dual_qdepth_disable = 1;
+		poll_queues = 0;
 	}
 
 	/*
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 38fc9467c625..10b8157044bb 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -685,6 +685,8 @@ megasas_alloc_reply_fusion(struct megasas_instance *instance)
 	fusion = instance->ctrl_context;
 
 	count = instance->msix_vectors > 0 ? instance->msix_vectors : 1;
+	count += instance->iopoll_q_count;
+
 	fusion->reply_frames_desc_pool =
 			dma_pool_create("mr_reply", &instance->pdev->dev,
 				fusion->reply_alloc_sz * count, 16, 0);
@@ -779,6 +781,7 @@ megasas_alloc_rdpq_fusion(struct megasas_instance *instance)
 	}
 
 	msix_count = instance->msix_vectors > 0 ? instance->msix_vectors : 1;
+	msix_count += instance->iopoll_q_count;
 
 	fusion->reply_frames_desc_pool = dma_pool_create("mr_rdpq",
 							 &instance->pdev->dev,
@@ -1129,7 +1132,7 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 			MPI2_IOCINIT_MSGFLAG_RDPQ_ARRAY_MODE : 0;
 	IOCInitMessage->SystemRequestFrameBaseAddress = cpu_to_le64(fusion->io_request_frames_phys);
 	IOCInitMessage->SenseBufferAddressHigh = cpu_to_le32(upper_32_bits(fusion->sense_phys_addr));
-	IOCInitMessage->HostMSIxVectors = instance->msix_vectors;
+	IOCInitMessage->HostMSIxVectors = instance->msix_vectors + instance->iopoll_q_count;
 	IOCInitMessage->HostPageSize = MR_DEFAULT_NVME_PAGE_SHIFT;
 
 	time = ktime_get_real();
@@ -1823,6 +1826,8 @@ megasas_init_adapter_fusion(struct megasas_instance *instance)
 		 sizeof(union MPI2_SGE_IO_UNION))/16;
 
 	count = instance->msix_vectors > 0 ? instance->msix_vectors : 1;
+	count += instance->iopoll_q_count;
+
 	for (i = 0 ; i < count; i++)
 		fusion->last_reply_idx[i] = 0;
 
@@ -1835,6 +1840,9 @@ megasas_init_adapter_fusion(struct megasas_instance *instance)
 				MEGASAS_FUSION_IOCTL_CMDS);
 	sema_init(&instance->ioctl_sem, MEGASAS_FUSION_IOCTL_CMDS);
 
+	for (i = 0; i < MAX_MSIX_QUEUES_FUSION; i++)
+		atomic_set(&fusion->busy_mq_poll[i], 0);
+
 	if (megasas_alloc_ioc_init_frame(instance))
 		return 1;
 
@@ -3500,6 +3508,9 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex,
 	if (reply_descript_type == MPI2_RPY_DESCRIPT_FLAGS_UNUSED)
 		return IRQ_NONE;
 
+	if (irq_context && !atomic_add_unless(&irq_context->in_used, 1, 1))
+		return 0;
+
 	num_completed = 0;
 
 	while (d_val.u.low != cpu_to_le32(UINT_MAX) &&
@@ -3613,6 +3624,7 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex,
 					irq_context->irq_line_enable = true;
 					irq_poll_sched(&irq_context->irqpoll);
 				}
+				atomic_dec(&irq_context->in_used);
 				return num_completed;
 			}
 		}
@@ -3630,9 +3642,35 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex,
 				instance->reply_post_host_index_addr[0]);
 		megasas_check_and_restore_queue_depth(instance);
 	}
+
+	if (irq_context)
+		atomic_dec(&irq_context->in_used);
+
 	return num_completed;
 }
 
+int megasas_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num)
+{
+
+	struct megasas_instance *instance;
+	int num_entries = 0;
+	struct fusion_context *fusion;
+
+	instance = (struct megasas_instance *)shost->hostdata;
+
+	fusion = instance->ctrl_context;
+
+	queue_num = queue_num + instance->low_latency_index_start;
+
+	if (!atomic_add_unless(&fusion->busy_mq_poll[queue_num], 1, 1))
+		return 0;
+
+	num_entries = complete_cmd_fusion(instance, queue_num, NULL);
+	atomic_dec(&fusion->busy_mq_poll[queue_num]);
+
+	return num_entries;
+}
+
 /**
  * megasas_enable_irq_poll() - enable irqpoll
  * @instance:			Adapter soft state
@@ -4163,6 +4201,8 @@ void  megasas_reset_reply_desc(struct megasas_instance *instance)
 
 	fusion = instance->ctrl_context;
 	count = instance->msix_vectors > 0 ? instance->msix_vectors : 1;
+	count += instance->iopoll_q_count;
+
 	for (i = 0 ; i < count ; i++) {
 		fusion->last_reply_idx[i] = 0;
 		reply_desc = fusion->reply_frames_desc[i];
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.h b/drivers/scsi/megaraid/megaraid_sas_fusion.h
index 30de4b01f703..ce84f811e5e1 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.h
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.h
@@ -1303,6 +1303,8 @@ struct fusion_context {
 	u8 *sense;
 	dma_addr_t sense_phys_addr;
 
+	atomic_t   busy_mq_poll[MAX_MSIX_QUEUES_FUSION];
+
 	dma_addr_t reply_frames_desc_phys[MAX_MSIX_QUEUES_FUSION];
 	union MPI2_REPLY_DESCRIPTORS_UNION *reply_frames_desc[MAX_MSIX_QUEUES_FUSION];
 	struct rdpq_alloc_detail rdpq_tracker[RDPQ_MAX_CHUNK_COUNT];
-- 
2.18.1


[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4169 bytes --]

[PATCH v4 3/5] scsi_debug : iouring iopoll support

[Kashyap Desai]

[-- Attachment #1: Type: text/plain, Size: 6838 bytes --]

Add support of iouring iopoll interface in scsi_debug.
This feature requires shared hosttag support in kernel and driver.

Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Acked-by: Douglas Gilbert <dgilbert@interlog.com>
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>

Cc: dgilbert@interlog.com
Cc: linux-block@vger.kernel.org
---
 drivers/scsi/scsi_debug.c | 130 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 130 insertions(+)

diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index d1b0cbe1b5f1..746eec521f79 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -829,6 +829,7 @@ static int sdeb_zbc_max_open = DEF_ZBC_MAX_OPEN_ZONES;
 static int sdeb_zbc_nr_conv = DEF_ZBC_NR_CONV_ZONES;
 
 static int submit_queues = DEF_SUBMIT_QUEUES;  /* > 1 for multi-queue (mq) */
+static int poll_queues; /* iouring iopoll interface.*/
 static struct sdebug_queue *sdebug_q_arr;  /* ptr to array of submit queues */
 
 static DEFINE_RWLOCK(atomic_rw);
@@ -5432,6 +5433,14 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
 	cmnd->host_scribble = (unsigned char *)sqcp;
 	sd_dp = sqcp->sd_dp;
 	spin_unlock_irqrestore(&sqp->qc_lock, iflags);
+
+	/* Do not complete IO from default completion path.
+	 * Let it to be on queue.
+	 * Completion should happen from mq_poll interface.
+	 */
+	if ((sqp - sdebug_q_arr) >= (submit_queues - poll_queues))
+		return 0;
+
 	if (!sd_dp) {
 		sd_dp = kzalloc(sizeof(*sd_dp), GFP_ATOMIC);
 		if (!sd_dp) {
@@ -5615,6 +5624,7 @@ module_param_named(sector_size, sdebug_sector_size, int, S_IRUGO);
 module_param_named(statistics, sdebug_statistics, bool, S_IRUGO | S_IWUSR);
 module_param_named(strict, sdebug_strict, bool, S_IRUGO | S_IWUSR);
 module_param_named(submit_queues, submit_queues, int, S_IRUGO);
+module_param_named(poll_queues, poll_queues, int, S_IRUGO);
 module_param_named(tur_ms_to_ready, sdeb_tur_ms_to_ready, int, S_IRUGO);
 module_param_named(unmap_alignment, sdebug_unmap_alignment, int, S_IRUGO);
 module_param_named(unmap_granularity, sdebug_unmap_granularity, int, S_IRUGO);
@@ -5677,6 +5687,7 @@ MODULE_PARM_DESC(opt_xferlen_exp, "optimal transfer length granularity exponent
 MODULE_PARM_DESC(opts, "1->noise, 2->medium_err, 4->timeout, 8->recovered_err... (def=0)");
 MODULE_PARM_DESC(per_host_store, "If set, next positive add_host will get new store (def=0)");
 MODULE_PARM_DESC(physblk_exp, "physical block exponent (def=0)");
+MODULE_PARM_DESC(poll_queues, "support for iouring iopoll queues (1 to max(submit_queues - 1)");
 MODULE_PARM_DESC(ptype, "SCSI peripheral type(def=0[disk])");
 MODULE_PARM_DESC(random, "If set, uniformly randomize command duration between 0 and delay_in_ns");
 MODULE_PARM_DESC(removable, "claim to have removable media (def=0)");
@@ -7201,6 +7212,104 @@ static int resp_not_ready(struct scsi_cmnd *scp, struct sdebug_dev_info *devip)
 	return check_condition_result;
 }
 
+static int sdebug_map_queues(struct Scsi_Host *shost)
+{
+	int i, qoff;
+
+	if (shost->nr_hw_queues == 1)
+		return 0;
+
+	for (i = 0, qoff = 0; i < HCTX_MAX_TYPES; i++) {
+		struct blk_mq_queue_map *map = &shost->tag_set.map[i];
+
+		map->nr_queues  = 0;
+
+		if (i == HCTX_TYPE_DEFAULT)
+			map->nr_queues = submit_queues - poll_queues;
+		else if (i == HCTX_TYPE_POLL)
+			map->nr_queues = poll_queues;
+
+		if (!map->nr_queues) {
+			BUG_ON(i == HCTX_TYPE_DEFAULT);
+			continue;
+		}
+
+		map->queue_offset = qoff;
+		blk_mq_map_queues(map);
+
+		qoff += map->nr_queues;
+	}
+
+	return 0;
+
+}
+
+static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num)
+{
+	int qc_idx;
+	int retiring = 0;
+	unsigned long iflags;
+	struct sdebug_queue *sqp;
+	struct sdebug_queued_cmd *sqcp;
+	struct scsi_cmnd *scp;
+	struct sdebug_dev_info *devip;
+	int num_entries = 0;
+
+	sqp = sdebug_q_arr + queue_num;
+
+	do {
+		spin_lock_irqsave(&sqp->qc_lock, iflags);
+		qc_idx = find_first_bit(sqp->in_use_bm, sdebug_max_queue);
+		if (unlikely((qc_idx < 0) || (qc_idx >= sdebug_max_queue)))
+			goto out;
+
+		sqcp = &sqp->qc_arr[qc_idx];
+		scp = sqcp->a_cmnd;
+		if (unlikely(scp == NULL)) {
+			pr_err("scp is NULL, queue_num=%d, qc_idx=%d from %s\n",
+			       queue_num, qc_idx, __func__);
+			goto out;
+		}
+		devip = (struct sdebug_dev_info *)scp->device->hostdata;
+		if (likely(devip))
+			atomic_dec(&devip->num_in_q);
+		else
+			pr_err("devip=NULL from %s\n", __func__);
+		if (unlikely(atomic_read(&retired_max_queue) > 0))
+			retiring = 1;
+
+		sqcp->a_cmnd = NULL;
+		if (unlikely(!test_and_clear_bit(qc_idx, sqp->in_use_bm))) {
+			pr_err("Unexpected completion sqp %p queue_num=%d qc_idx=%d from %s\n",
+				sqp, queue_num, qc_idx, __func__);
+			goto out;
+		}
+
+		if (unlikely(retiring)) {	/* user has reduced max_queue */
+			int k, retval;
+
+			retval = atomic_read(&retired_max_queue);
+			if (qc_idx >= retval) {
+				pr_err("index %d too large\n", retval);
+				goto out;
+			}
+			k = find_last_bit(sqp->in_use_bm, retval);
+			if ((k < sdebug_max_queue) || (k == retval))
+				atomic_set(&retired_max_queue, 0);
+			else
+				atomic_set(&retired_max_queue, k + 1);
+		}
+		spin_unlock_irqrestore(&sqp->qc_lock, iflags);
+		scp->scsi_done(scp); /* callback to mid level */
+		num_entries++;
+	} while (1);
+
+out:
+	spin_unlock_irqrestore(&sqp->qc_lock, iflags);
+	return num_entries;
+}
+
+
 static int scsi_debug_queuecommand(struct Scsi_Host *shost,
 				   struct scsi_cmnd *scp)
 {
@@ -7380,6 +7489,8 @@ static struct scsi_host_template sdebug_driver_template = {
 	.ioctl =		scsi_debug_ioctl,
 	.queuecommand =		scsi_debug_queuecommand,
 	.change_queue_depth =	sdebug_change_qdepth,
+	.map_queues =		sdebug_map_queues,
+	.mq_poll =		sdebug_blk_mq_poll,
 	.eh_abort_handler =	scsi_debug_abort,
 	.eh_device_reset_handler = scsi_debug_device_reset,
 	.eh_target_reset_handler = scsi_debug_target_reset,
@@ -7427,6 +7538,25 @@ static int sdebug_driver_probe(struct device *dev)
 	if (sdebug_host_max_queue)
 		hpnt->host_tagset = 1;
 
+	/* poll queues are possible for nr_hw_queues > 1 */
+	if (hpnt->nr_hw_queues == 1 || (poll_queues < 1)) {
+		pr_warn("%s: trim poll_queues to 0. poll_q/nr_hw = (%d/%d)\n",
+			 my_name, poll_queues, hpnt->nr_hw_queues);
+		poll_queues = 0;
+	}
+
+	/*
+	 * Poll queues don't need interrupts, but we need at least one I/O queue
+	 * left over for non-polled I/O.
+	 * If condition not met, trim poll_queues to 1 (just for simplicity).
+	 */
+	if (poll_queues >= submit_queues) {
+		pr_warn("%s: trim poll_queues to 1\n", my_name);
+		poll_queues = 1;
+	}
+	if (poll_queues)
+		hpnt->nr_maps = 3;
+
 	sdbg_host->shost = hpnt;
 	*((struct sdebug_host_info **)hpnt->hostdata) = sdbg_host;
 	if ((hpnt->this_id >= 0) && (sdebug_num_tgts > hpnt->this_id))
-- 
2.18.1


[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4169 bytes --]