1 files changed, 95 insertions, 16 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index e1846d04817f..72f7c955c707 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1207,6 +1207,7 @@ static void nvme_keep_alive_work(struct work_struct *work)
 
 	rq->timeout = ctrl->kato * HZ;
 	rq->end_io_data = ctrl;
+	rq->rq_flags |= RQF_QUIET;
 	blk_execute_rq_nowait(rq, false, nvme_keep_alive_end_io);
 }
 
@@ -1426,6 +1427,32 @@ out_free_id:
 	return error;
 }
 
+static int nvme_identify_ns_cs_indep(struct nvme_ctrl *ctrl, unsigned nsid,
+			struct nvme_id_ns_cs_indep **id)
+{
+	struct nvme_command c = {
+		.identify.opcode	= nvme_admin_identify,
+		.identify.nsid		= cpu_to_le32(nsid),
+		.identify.cns		= NVME_ID_CNS_NS_CS_INDEP,
+	};
+	int ret;
+
+	*id = kmalloc(sizeof(**id), GFP_KERNEL);
+	if (!*id)
+		return -ENOMEM;
+
+	ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, *id, sizeof(**id));
+	if (ret) {
+		dev_warn(ctrl->device,
+			 "Identify namespace (CS independent) failed (%d)\n",
+			 ret);
+		kfree(*id);
+		return ret;
+	}
+
+	return 0;
+}
+
 static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid,
 		unsigned int dword11, void *buffer, size_t buflen, u32 *result)
 {
@@ -1621,20 +1648,22 @@ static void nvme_config_discard(struct gendisk *disk, struct nvme_ns *ns)
 	u32 size = queue_logical_block_size(queue);
 
 	if (ctrl->max_discard_sectors == 0) {
-		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, queue);
+		blk_queue_max_discard_sectors(queue, 0);
 		return;
 	}
 
 	BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
 			NVME_DSM_MAX_RANGES);
 
-	queue->limits.discard_alignment = 0;
 	queue->limits.discard_granularity = size;
 
 	/* If discard is already enabled, don't reset queue limits */
-	if (blk_queue_flag_test_and_set(QUEUE_FLAG_DISCARD, queue))
+	if (queue->limits.max_discard_sectors)
 		return;
 
+	if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns, UINT_MAX))
+		ctrl->max_discard_sectors = nvme_lba_to_sect(ns, ctrl->dmrsl);
+
 	blk_queue_max_discard_sectors(queue, ctrl->max_discard_sectors);
 	blk_queue_max_discard_segments(queue, ctrl->max_discard_segments);
 
@@ -1771,7 +1800,7 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
 		blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
 	}
 	blk_queue_virt_boundary(q, NVME_CTRL_PAGE_SIZE - 1);
-	blk_queue_dma_alignment(q, 7);
+	blk_queue_dma_alignment(q, 3);
 	blk_queue_write_cache(q, vwc, vwc);
 }
 
@@ -2100,10 +2129,9 @@ static const struct block_device_operations nvme_bdev_ops = {
 	.pr_ops		= &nvme_pr_ops,
 };
 
-static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled)
+static int nvme_wait_ready(struct nvme_ctrl *ctrl, u32 timeout, bool enabled)
 {
-	unsigned long timeout =
-		((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies;
+	unsigned long timeout_jiffies = ((timeout + 1) * HZ / 2) + jiffies;
 	u32 csts, bit = enabled ? NVME_CSTS_RDY : 0;
 	int ret;
 
@@ -2116,7 +2144,7 @@ static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled)
 		usleep_range(1000, 2000);
 		if (fatal_signal_pending(current))
 			return -EINTR;
-		if (time_after(jiffies, timeout)) {
+		if (time_after(jiffies, timeout_jiffies)) {
 			dev_err(ctrl->device,
 				"Device not ready; aborting %s, CSTS=0x%x\n",
 				enabled ? "initialisation" : "reset", csts);
@@ -2147,13 +2175,14 @@ int nvme_disable_ctrl(struct nvme_ctrl *ctrl)
 	if (ctrl->quirks & NVME_QUIRK_DELAY_BEFORE_CHK_RDY)
 		msleep(NVME_QUIRK_DELAY_AMOUNT);
 
-	return nvme_wait_ready(ctrl, ctrl->cap, false);
+	return nvme_wait_ready(ctrl, NVME_CAP_TIMEOUT(ctrl->cap), false);
 }
 EXPORT_SYMBOL_GPL(nvme_disable_ctrl);
 
 int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
 {
 	unsigned dev_page_min;
+	u32 timeout;
 	int ret;
 
 	ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &ctrl->cap);
@@ -2174,6 +2203,27 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
 		ctrl->ctrl_config = NVME_CC_CSS_CSI;
 	else
 		ctrl->ctrl_config = NVME_CC_CSS_NVM;
+
+	if (ctrl->cap & NVME_CAP_CRMS_CRWMS) {
+		u32 crto;
+
+		ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CRTO, &crto);
+		if (ret) {
+			dev_err(ctrl->device, "Reading CRTO failed (%d)\n",
+				ret);
+			return ret;
+		}
+
+		if (ctrl->cap & NVME_CAP_CRMS_CRIMS) {
+			ctrl->ctrl_config |= NVME_CC_CRIME;
+			timeout = NVME_CRTO_CRIMT(crto);
+		} else {
+			timeout = NVME_CRTO_CRWMT(crto);
+		}
+	} else {
+		timeout = NVME_CAP_TIMEOUT(ctrl->cap);
+	}
+
 	ctrl->ctrl_config |= (NVME_CTRL_PAGE_SHIFT - 12) << NVME_CC_MPS_SHIFT;
 	ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE;
 	ctrl->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES;
@@ -2182,7 +2232,7 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
 	ret = ctrl->ops->reg_write32(ctrl, NVME_REG_CC, ctrl->ctrl_config);
 	if (ret)
 		return ret;
-	return nvme_wait_ready(ctrl, ctrl->cap, true);
+	return nvme_wait_ready(ctrl, timeout, true);
 }
 EXPORT_SYMBOL_GPL(nvme_enable_ctrl);
 
@@ -2894,8 +2944,7 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl)
 
 	if (id->dmrl)
 		ctrl->max_discard_segments = id->dmrl;
-	if (id->dmrsl)
-		ctrl->max_discard_sectors = le32_to_cpu(id->dmrsl);
+	ctrl->dmrsl = le32_to_cpu(id->dmrsl);
 	if (id->wzsl)
 		ctrl->max_zeroes_sectors = nvme_mps_to_sectors(ctrl, id->wzsl);
 
@@ -3080,10 +3129,6 @@ int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl)
 	if (ret)
 		return ret;
 
-	ret = nvme_init_non_mdts_limits(ctrl);
-	if (ret < 0)
-		return ret;
-
 	ret = nvme_configure_apst(ctrl);
 	if (ret < 0)
 		return ret;
@@ -3146,6 +3191,7 @@ static const struct file_operations nvme_dev_fops = {
 	.release	= nvme_dev_release,
 	.unlocked_ioctl	= nvme_dev_ioctl,
 	.compat_ioctl	= compat_ptr_ioctl,
+	.uring_cmd	= nvme_dev_uring_cmd,
 };
 
 static ssize_t nvme_sysfs_reset(struct device *dev,
@@ -3699,6 +3745,7 @@ static const struct file_operations nvme_ns_chr_fops = {
 	.release	= nvme_ns_chr_release,
 	.unlocked_ioctl	= nvme_ns_chr_ioctl,
 	.compat_ioctl	= compat_ptr_ioctl,
+	.uring_cmd	= nvme_ns_chr_uring_cmd,
 };
 
 static int nvme_add_ns_cdev(struct nvme_ns *ns)
@@ -4090,11 +4137,26 @@ out:
 static void nvme_validate_or_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 {
 	struct nvme_ns_ids ids = { };
+	struct nvme_id_ns_cs_indep *id;
 	struct nvme_ns *ns;
+	bool ready = true;
 
 	if (nvme_identify_ns_descs(ctrl, nsid, &ids))
 		return;
 
+	/*
+	 * Check if the namespace is ready.  If not ignore it, we will get an
+	 * AEN once it becomes ready and restart the scan.
+	 */
+	if ((ctrl->cap & NVME_CAP_CRMS_CRIMS) &&
+	    !nvme_identify_ns_cs_indep(ctrl, nsid, &id)) {
+		ready = id->nstat & NVME_NSTAT_NRDY;
+		kfree(id);
+	}
+
+	if (!ready)
+		return;
+
 	ns = nvme_find_get_ns(ctrl, nsid);
 	if (ns) {
 		nvme_validate_ns(ns, &ids);
@@ -4237,11 +4299,26 @@ static void nvme_scan_work(struct work_struct *work)
 {
 	struct nvme_ctrl *ctrl =
 		container_of(work, struct nvme_ctrl, scan_work);
+	int ret;
 
 	/* No tagset on a live ctrl means IO queues could not created */
 	if (ctrl->state != NVME_CTRL_LIVE || !ctrl->tagset)
 		return;
 
+	/*
+	 * Identify controller limits can change at controller reset due to
+	 * new firmware download, even though it is not common we cannot ignore
+	 * such scenario. Controller's non-mdts limits are reported in the unit
+	 * of logical blocks that is dependent on the format of attached
+	 * namespace. Hence re-read the limits at the time of ns allocation.
+	 */
+	ret = nvme_init_non_mdts_limits(ctrl);
+	if (ret < 0) {
+		dev_warn(ctrl->device,
+			"reading non-mdts-limits failed: %d\n", ret);
+		return;
+	}
+
 	if (test_and_clear_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) {
 		dev_info(ctrl->device, "rescanning namespaces.\n");
 		nvme_clear_changed_ns_log(ctrl);
@@ -4839,6 +4916,8 @@ static inline void _nvme_check_size(void)
 	BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE);
+	BUILD_BUG_ON(sizeof(struct nvme_id_ns_cs_indep) !=
+			NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ns_zns) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ns_nvm) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_zns) != NVME_IDENTIFY_DATA_SIZE);