nvme: add support for TP4084 - Time-to-Ready Enhancements

Add support for using longer timeouts during controller initialization
and letting the controller come up with namespaces that are not ready
for I/O yet.  We skip these not ready namespaces during scanning and
only bring them online once anoter scan is kicked off by the AEN that
is set when the NRDY bit gets set in the  I/O Command Set Independent
Identify Namespace Data Structure.   This asynchronous probing avoids
blocking the kernel boot when controllers take a very long time to
recover after unclean shutdowns (up to minutes).

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>

2 files changed, 71 insertions, 6 deletions

diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c
index 1dd1d78de295..4910543f00ff 100644
--- a/drivers/nvme/host/constants.c
+++ b/drivers/nvme/host/constants.c
@@ -91,6 +91,7 @@ static const char * const nvme_statuses[] = {
 	[NVME_SC_NS_WRITE_PROTECTED] = "Namespace is Write Protected",
 	[NVME_SC_CMD_INTERRUPTED] = "Command Interrupted",
 	[NVME_SC_TRANSIENT_TR_ERR] = "Transient Transport Error",
+	[NVME_SC_ADMIN_COMMAND_MEDIA_NOT_READY] = "Admin Command Media Not Ready",
 	[NVME_SC_INVALID_IO_CMD_SET] = "Invalid IO Command Set",
 	[NVME_SC_LBA_RANGE] = "LBA Out of Range",
 	[NVME_SC_CAP_EXCEEDED] = "Capacity Exceeded",
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 42f9772abc4d..faeb03271913 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1427,6 +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)
 {
@@ -2103,10 +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;
 
@@ -2119,7 +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);
@@ -2150,13 +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);
@@ -2177,6 +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;
@@ -2185,7 +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);
 
@@ -4092,11 +4139,26 @@ 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);
@@ -4841,6 +4903,8 @@ 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);