Merge branch '5.11/scsi-fixes' into 5.12/scsi-queue

Pull in the 5.11 SCSI fixes branch to provide an updated baseline for
megaraid and hisi_sas. Both drivers received core changes in
v5.11-rc3.
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/hisi_sas/hisi_sas.h

@@ -14,6 +14,7 @@
 #include <linux/debugfs.h>
 #include <linux/dmapool.h>
 #include <linux/iopoll.h>
+#include <linux/irq.h>
 #include <linux/lcm.h>
 #include <linux/libata.h>
 #include <linux/mfd/syscon.h>
@@ -294,6 +295,7 @@ enum {
 
 struct hisi_sas_hw {
 	int (*hw_init)(struct hisi_hba *hisi_hba);
+	int (*interrupt_preinit)(struct hisi_hba *hisi_hba);
 	void (*setup_itct)(struct hisi_hba *hisi_hba,
 			   struct hisi_sas_device *device);
 	int (*slot_index_alloc)(struct hisi_hba *hisi_hba,
@@ -393,6 +395,8 @@ struct hisi_hba {
 	u32 refclk_frequency_mhz;
 	u8 sas_addr[SAS_ADDR_SIZE];
 
+	int *irq_map; /* v2 hw */
+
 	int n_phy;
 	spinlock_t lock;
 	struct semaphore sem;

drivers/scsi/hisi_sas/hisi_sas_main.c

@@ -2614,6 +2614,13 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
 	return NULL;
 }
 
+static int hisi_sas_interrupt_preinit(struct hisi_hba *hisi_hba)
+{
+	if (hisi_hba->hw->interrupt_preinit)
+		return hisi_hba->hw->interrupt_preinit(hisi_hba);
+	return 0;
+}
+
 int hisi_sas_probe(struct platform_device *pdev,
 		   const struct hisi_sas_hw *hw)
 {
@@ -2671,6 +2678,10 @@ int hisi_sas_probe(struct platform_device *pdev,
 		sha->sas_port[i] = &hisi_hba->port[i].sas_port;
 	}
 
+	rc = hisi_sas_interrupt_preinit(hisi_hba);
+	if (rc)
+		goto err_out_ha;
+
 	rc = scsi_add_host(shost, &pdev->dev);
 	if (rc)
 		goto err_out_ha;

drivers/scsi/hisi_sas/hisi_sas_v2_hw.c

@@ -3302,6 +3302,28 @@ static irq_handler_t fatal_interrupts[HISI_SAS_FATAL_INT_NR] = {
 	fatal_axi_int_v2_hw
 };
 
+#define CQ0_IRQ_INDEX (96)
+
+static int hisi_sas_v2_interrupt_preinit(struct hisi_hba *hisi_hba)
+{
+	struct platform_device *pdev = hisi_hba->platform_dev;
+	struct Scsi_Host *shost = hisi_hba->shost;
+	struct irq_affinity desc = {
+		.pre_vectors = CQ0_IRQ_INDEX,
+		.post_vectors = 16,
+	};
+	int resv = desc.pre_vectors + desc.post_vectors, minvec = resv + 1, nvec;
+
+	nvec = devm_platform_get_irqs_affinity(pdev, &desc, minvec, 128,
+					       &hisi_hba->irq_map);
+	if (nvec < 0)
+		return nvec;
+
+	shost->nr_hw_queues = hisi_hba->cq_nvecs = nvec - resv;
+
+	return 0;
+}
+
 /*
  * There is a limitation in the hip06 chipset that we need
  * to map in all mbigen interrupts, even if they are not used.
@@ -3310,14 +3332,11 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 {
 	struct platform_device *pdev = hisi_hba->platform_dev;
 	struct device *dev = &pdev->dev;
-	int irq, rc = 0, irq_map[128];
+	int irq, rc = 0;
 	int i, phy_no, fatal_no, queue_no;
 
-	for (i = 0; i < 128; i++)
-		irq_map[i] = platform_get_irq(pdev, i);
-
 	for (i = 0; i < HISI_SAS_PHY_INT_NR; i++) {
-		irq = irq_map[i + 1]; /* Phy up/down is irq1 */
+		irq = hisi_hba->irq_map[i + 1]; /* Phy up/down is irq1 */
 		rc = devm_request_irq(dev, irq, phy_interrupts[i], 0,
 				      DRV_NAME " phy", hisi_hba);
 		if (rc) {
@@ -3331,7 +3350,7 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 	for (phy_no = 0; phy_no < hisi_hba->n_phy; phy_no++) {
 		struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
 
-		irq = irq_map[phy_no + 72];
+		irq = hisi_hba->irq_map[phy_no + 72];
 		rc = devm_request_irq(dev, irq, sata_int_v2_hw, 0,
 				      DRV_NAME " sata", phy);
 		if (rc) {
@@ -3343,7 +3362,7 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 	}
 
 	for (fatal_no = 0; fatal_no < HISI_SAS_FATAL_INT_NR; fatal_no++) {
-		irq = irq_map[fatal_no + 81];
+		irq = hisi_hba->irq_map[fatal_no + 81];
 		rc = devm_request_irq(dev, irq, fatal_interrupts[fatal_no], 0,
 				      DRV_NAME " fatal", hisi_hba);
 		if (rc) {
@@ -3354,24 +3373,22 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 		}
 	}
 
-	for (queue_no = 0; queue_no < hisi_hba->queue_count; queue_no++) {
+	for (queue_no = 0; queue_no < hisi_hba->cq_nvecs; queue_no++) {
 		struct hisi_sas_cq *cq = &hisi_hba->cq[queue_no];
 
-		cq->irq_no = irq_map[queue_no + 96];
+		cq->irq_no = hisi_hba->irq_map[queue_no + 96];
 		rc = devm_request_threaded_irq(dev, cq->irq_no,
 					       cq_interrupt_v2_hw,
 					       cq_thread_v2_hw, IRQF_ONESHOT,
 					       DRV_NAME " cq", cq);
 		if (rc) {
 			dev_err(dev, "irq init: could not request cq interrupt %d, rc=%d\n",
-				irq, rc);
+					cq->irq_no, rc);
 			rc = -ENOENT;
 			goto err_out;
 		}
+		cq->irq_mask = irq_get_affinity_mask(cq->irq_no);
 	}
-
-	hisi_hba->cq_nvecs = hisi_hba->queue_count;
-
 err_out:
 	return rc;
 }
@@ -3529,6 +3546,26 @@ static struct device_attribute *host_attrs_v2_hw[] = {
 	NULL
 };
 
+static int map_queues_v2_hw(struct Scsi_Host *shost)
+{
+	struct hisi_hba *hisi_hba = shost_priv(shost);
+	struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
+	const struct cpumask *mask;
+	unsigned int queue, cpu;
+
+	for (queue = 0; queue < qmap->nr_queues; queue++) {
+		mask = irq_get_affinity_mask(hisi_hba->irq_map[96 + queue]);
+		if (!mask)
+			continue;
+
+		for_each_cpu(cpu, mask)
+			qmap->mq_map[cpu] = qmap->queue_offset + queue;
+	}
+
+	return 0;
+
+}
+
 static struct scsi_host_template sht_v2_hw = {
 	.name			= DRV_NAME,
 	.proc_name		= DRV_NAME,
@@ -3553,10 +3590,13 @@ static struct scsi_host_template sht_v2_hw = {
 #endif
 	.shost_attrs		= host_attrs_v2_hw,
 	.host_reset		= hisi_sas_host_reset,
+	.map_queues		= map_queues_v2_hw,
+	.host_tagset		= 1,
 };
 
 static const struct hisi_sas_hw hisi_sas_v2_hw = {
 	.hw_init = hisi_sas_v2_init,
+	.interrupt_preinit = hisi_sas_v2_interrupt_preinit,
 	.setup_itct = setup_itct_v2_hw,
 	.slot_index_alloc = slot_index_alloc_quirk_v2_hw,
 	.alloc_dev = alloc_dev_quirk_v2_hw,

drivers/scsi/megaraid/megaraid_sas_base.c

@@ -37,6 +37,7 @@
 #include <linux/poll.h>
 #include <linux/vmalloc.h>
 #include <linux/irq_poll.h>
+#include <linux/blk-mq-pci.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
@@ -113,6 +114,10 @@ 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 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)");
+
 MODULE_LICENSE("GPL");
 MODULE_VERSION(MEGASAS_VERSION);
 MODULE_AUTHOR("megaraidlinux.pdl@broadcom.com");
@@ -3119,6 +3124,19 @@ megasas_bios_param(struct scsi_device *sdev, struct block_device *bdev,
 	return 0;
 }
 
+static int megasas_map_queues(struct Scsi_Host *shost)
+{
+	struct megasas_instance *instance;
+
+	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);
+}
+
 static void megasas_aen_polling(struct work_struct *work);
 
 /**
@@ -3427,6 +3445,7 @@ static struct scsi_host_template megasas_template = {
 	.eh_timed_out = megasas_reset_timer,
 	.shost_attrs = megaraid_host_attrs,
 	.bios_param = megasas_bios_param,
+	.map_queues = megasas_map_queues,
 	.change_queue_depth = scsi_change_queue_depth,
 	.max_segment_size = 0xffffffff,
 };
@@ -6808,6 +6827,26 @@ static int megasas_io_attach(struct megasas_instance *instance)
 	host->max_lun = MEGASAS_MAX_LUN;
 	host->max_cmd_len = 16;
 
+	/* Use shared host tagset only for fusion adaptors
+	 * if there are managed interrupts (smp affinity enabled case).
+	 * Single msix_vectors in kdump, so shared host tag is also disabled.
+	 */
+
+	host->host_tagset = 0;
+	host->nr_hw_queues = 1;
+
+	if ((instance->adapter_type != MFI_SERIES) &&
+		(instance->msix_vectors > instance->low_latency_index_start) &&
+		host_tagset_enable &&
+		instance->smp_affinity_enable) {
+		host->host_tagset = 1;
+		host->nr_hw_queues = instance->msix_vectors -
+			instance->low_latency_index_start;
+	}
+
+	dev_info(&instance->pdev->dev,
+		"Max firmware commands: %d shared with nr_hw_queues = %d\n",
+		instance->max_fw_cmds, host->nr_hw_queues);
 	/*
 	 * Notify the mid-layer about the new controller
 	 */

drivers/scsi/megaraid/megaraid_sas_fusion.c

@@ -359,24 +359,29 @@ megasas_get_msix_index(struct megasas_instance *instance,
 {
 	int sdev_busy;
 
-	/* nr_hw_queue = 1 for MegaRAID */
-	struct blk_mq_hw_ctx *hctx =
-		scmd->device->request_queue->queue_hw_ctx[0];
-
-	sdev_busy = atomic_read(&hctx->nr_active);
+	/* TBD - if sml remove device_busy in future, driver
+	 * should track counter in internal structure.
+	 */
+	sdev_busy = atomic_read(&scmd->device->device_busy);
 
 	if (instance->perf_mode == MR_BALANCED_PERF_MODE &&
-	    sdev_busy > (data_arms * MR_DEVICE_HIGH_IOPS_DEPTH))
+	    sdev_busy > (data_arms * MR_DEVICE_HIGH_IOPS_DEPTH)) {
 		cmd->request_desc->SCSIIO.MSIxIndex =
 			mega_mod64((atomic64_add_return(1, &instance->high_iops_outstanding) /
 					MR_HIGH_IOPS_BATCH_COUNT), instance->low_latency_index_start);
-	else if (instance->msix_load_balance)
+	} else if (instance->msix_load_balance) {
 		cmd->request_desc->SCSIIO.MSIxIndex =
 			(mega_mod64(atomic64_add_return(1, &instance->total_io_count),
 				instance->msix_vectors));
-	else
+	} else if (instance->host->nr_hw_queues > 1) {
+		u32 tag = blk_mq_unique_tag(scmd->request);
+
+		cmd->request_desc->SCSIIO.MSIxIndex = blk_mq_unique_tag_to_hwq(tag) +
+			instance->low_latency_index_start;
+	} else {
 		cmd->request_desc->SCSIIO.MSIxIndex =
 			instance->reply_map[raw_smp_processor_id()];
+	}
 }
 
 /**
@@ -956,9 +961,6 @@ megasas_alloc_cmds_fusion(struct megasas_instance *instance)
 	if (megasas_alloc_cmdlist_fusion(instance))
 		goto fail_exit;
 
-	dev_info(&instance->pdev->dev, "Configured max firmware commands: %d\n",
-		 instance->max_fw_cmds);
-
 	/* The first 256 bytes (SMID 0) is not used. Don't add to the cmd list */
 	io_req_base = fusion->io_request_frames + MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE;
 	io_req_base_phys = fusion->io_request_frames_phys + MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE;
@@ -1102,8 +1104,9 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 		MR_HIGH_IOPS_QUEUE_COUNT) && cur_intr_coalescing)
 		instance->perf_mode = MR_BALANCED_PERF_MODE;
 
-	dev_info(&instance->pdev->dev, "Performance mode :%s\n",
-		MEGASAS_PERF_MODE_2STR(instance->perf_mode));
+	dev_info(&instance->pdev->dev, "Performance mode :%s (latency index = %d)\n",
+		MEGASAS_PERF_MODE_2STR(instance->perf_mode),
+		instance->low_latency_index_start);
 
 	instance->fw_sync_cache_support = (scratch_pad_1 &
 		MR_CAN_HANDLE_SYNC_CACHE_OFFSET) ? 1 : 0;

drivers/scsi/mpt3sas/Kconfig

@@ -79,5 +79,5 @@ config SCSI_MPT2SAS
 	select SCSI_MPT3SAS
 	depends on PCI && SCSI
 	help
-	Dummy config option for backwards compatiblity: configure the MPT3SAS
+	Dummy config option for backwards compatibility: configure the MPT3SAS
 	driver instead.

drivers/scsi/qedi/qedi_main.c

@@ -2245,7 +2245,7 @@ qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type,
 			     chap_name);
 		break;
 	case ISCSI_BOOT_TGT_CHAP_SECRET:
-		rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN,
+		rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN,
 			     chap_secret);
 		break;
 	case ISCSI_BOOT_TGT_REV_CHAP_NAME:
@@ -2253,7 +2253,7 @@ qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type,
 			     mchap_name);
 		break;
 	case ISCSI_BOOT_TGT_REV_CHAP_SECRET:
-		rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN,
+		rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN,
 			     mchap_secret);
 		break;
 	case ISCSI_BOOT_TGT_FLAGS:

drivers/scsi/scsi_debug.c

@@ -6740,7 +6740,7 @@ static int __init scsi_debug_init(void)
 		k = sdeb_zbc_model_str(sdeb_zbc_model_s);
 		if (k < 0) {
 			ret = k;
-			goto free_vm;
+			goto free_q_arr;
 		}
 		sdeb_zbc_model = k;
 		switch (sdeb_zbc_model) {
@@ -6753,7 +6753,8 @@ static int __init scsi_debug_init(void)
 			break;
 		default:
 			pr_err("Invalid ZBC model\n");
-			return -EINVAL;
+			ret = -EINVAL;
+			goto free_q_arr;
 		}
 	}
 	if (sdeb_zbc_model != BLK_ZONED_NONE) {

drivers/scsi/sd.c

@@ -984,8 +984,10 @@ static blk_status_t sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd)
 		}
 	}
 
-	if (sdp->no_write_same)
+	if (sdp->no_write_same) {
+		rq->rq_flags |= RQF_QUIET;
 		return BLK_STS_TARGET;
+	}
 
 	if (sdkp->ws16 || lba > 0xffffffff || nr_blocks > 0xffff)
 		return sd_setup_write_same16_cmnd(cmd, false);
@@ -3510,10 +3512,8 @@ static int sd_probe(struct device *dev)
 static int sd_remove(struct device *dev)
 {
 	struct scsi_disk *sdkp;
-	dev_t devt;
 
 	sdkp = dev_get_drvdata(dev);
-	devt = disk_devt(sdkp->disk);
 	scsi_autopm_get_device(sdkp->device);
 
 	async_synchronize_full_domain(&scsi_sd_pm_domain);

drivers/scsi/ufs/ufshcd.c

@@ -292,7 +292,8 @@ static inline void ufshcd_wb_config(struct ufs_hba *hba)
 	if (ret)
 		dev_err(hba->dev, "%s: En WB flush during H8: failed: %d\n",
 			__func__, ret);
-	ufshcd_wb_toggle_flush(hba, true);
+	if (!(hba->quirks & UFSHCI_QUIRK_SKIP_MANUAL_WB_FLUSH_CTRL))
+		ufshcd_wb_toggle_flush(hba, true);
 }
 
 static void ufshcd_scsi_unblock_requests(struct ufs_hba *hba)
@@ -5463,9 +5464,6 @@ static int ufshcd_wb_toggle_flush_during_h8(struct ufs_hba *hba, bool set)
 
 static inline void ufshcd_wb_toggle_flush(struct ufs_hba *hba, bool enable)
 {
-	if (hba->quirks & UFSHCI_QUIRK_SKIP_MANUAL_WB_FLUSH_CTRL)
-		return;
-
 	if (enable)
 		ufshcd_wb_buf_flush_enable(hba);
 	else
@@ -6689,19 +6687,16 @@ static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd)
 {
 	struct Scsi_Host *host;
 	struct ufs_hba *hba;
-	unsigned int tag;
 	u32 pos;
 	int err;
-	u8 resp = 0xF;
-	struct ufshcd_lrb *lrbp;
+	u8 resp = 0xF, lun;
 	unsigned long flags;
 
 	host = cmd->device->host;
 	hba = shost_priv(host);
-	tag = cmd->request->tag;
 
-	lrbp = &hba->lrb[tag];
-	err = ufshcd_issue_tm_cmd(hba, lrbp->lun, 0, UFS_LOGICAL_RESET, &resp);
+	lun = ufshcd_scsi_to_upiu_lun(cmd->device->lun);
+	err = ufshcd_issue_tm_cmd(hba, lun, 0, UFS_LOGICAL_RESET, &resp);
 	if (err || resp != UPIU_TASK_MANAGEMENT_FUNC_COMPL) {
 		if (!err)
 			err = resp;
@@ -6710,7 +6705,7 @@ static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd)
 
 	/* clear the commands that were pending for corresponding LUN */
 	for_each_set_bit(pos, &hba->outstanding_reqs, hba->nutrs) {
-		if (hba->lrb[pos].lun == lrbp->lun) {
+		if (hba->lrb[pos].lun == lun) {
 			err = ufshcd_clear_cmd(hba, pos);
 			if (err)
 				break;
@@ -8729,6 +8724,8 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 			ufshcd_wb_need_flush(hba));
 	}
 
+	flush_work(&hba->eeh_work);
+
 	if (req_dev_pwr_mode != hba->curr_dev_pwr_mode) {
 		if (!ufshcd_is_runtime_pm(pm_op))
 			/* ensure that bkops is disabled */
@@ -8741,8 +8738,6 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 		}
 	}
 
-	flush_work(&hba->eeh_work);
-
 	/*
 	 * In the case of DeepSleep, the device is expected to remain powered
 	 * with the link off, so do not check for bkops.
@@ -8975,7 +8970,8 @@ int ufshcd_system_suspend(struct ufs_hba *hba)
 	if ((ufs_get_pm_lvl_to_dev_pwr_mode(hba->spm_lvl) ==
 	     hba->curr_dev_pwr_mode) &&
 	    (ufs_get_pm_lvl_to_link_pwr_state(hba->spm_lvl) ==
-	     hba->uic_link_state))
+	     hba->uic_link_state) &&
+	     !hba->dev_info.b_rpm_dev_flush_capable)
 		goto out;
 
 	if (pm_runtime_suspended(hba->dev)) {