1 files changed, 250 insertions, 7 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 44a1a257e0b5..25ec4e585220 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -26,6 +26,7 @@
 #include <linux/ptrace.h>
 #include <linux/nvme_ioctl.h>
 #include <linux/t10-pi.h>
+#include <linux/pm_qos.h>
 #include <scsi/sg.h>
 #include <asm/unaligned.h>
 
@@ -56,6 +57,11 @@ EXPORT_SYMBOL_GPL(nvme_max_retries);
 static int nvme_char_major;
 module_param(nvme_char_major, int, 0);
 
+static unsigned long default_ps_max_latency_us = 25000;
+module_param(default_ps_max_latency_us, ulong, 0644);
+MODULE_PARM_DESC(default_ps_max_latency_us,
+		 "max power saving latency for new devices; use PM QOS to change per device");
+
 static LIST_HEAD(nvme_ctrl_list);
 static DEFINE_SPINLOCK(dev_list_lock);
 
@@ -560,7 +566,7 @@ int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
 
 	/* gcc-4.4.4 (at least) has issues with initializers and anon unions */
 	c.identify.opcode = nvme_admin_identify;
-	c.identify.cns = cpu_to_le32(NVME_ID_CNS_CTRL);
+	c.identify.cns = NVME_ID_CNS_CTRL;
 
 	*id = kmalloc(sizeof(struct nvme_id_ctrl), GFP_KERNEL);
 	if (!*id)
@@ -578,7 +584,7 @@ static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *n
 	struct nvme_command c = { };
 
 	c.identify.opcode = nvme_admin_identify;
-	c.identify.cns = cpu_to_le32(NVME_ID_CNS_NS_ACTIVE_LIST);
+	c.identify.cns = NVME_ID_CNS_NS_ACTIVE_LIST;
 	c.identify.nsid = cpu_to_le32(nsid);
 	return nvme_submit_sync_cmd(dev->admin_q, &c, ns_list, 0x1000);
 }
@@ -590,8 +596,9 @@ int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid,
 	int error;
 
 	/* gcc-4.4.4 (at least) has issues with initializers and anon unions */
-	c.identify.opcode = nvme_admin_identify,
-	c.identify.nsid = cpu_to_le32(nsid),
+	c.identify.opcode = nvme_admin_identify;
+	c.identify.nsid = cpu_to_le32(nsid);
+	c.identify.cns = NVME_ID_CNS_NS;
 
 	*id = kmalloc(sizeof(struct nvme_id_ns), GFP_KERNEL);
 	if (!*id)
@@ -1251,6 +1258,176 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
 	blk_queue_write_cache(q, vwc, vwc);
 }
 
+static void nvme_configure_apst(struct nvme_ctrl *ctrl)
+{
+	/*
+	 * APST (Autonomous Power State Transition) lets us program a
+	 * table of power state transitions that the controller will
+	 * perform automatically.  We configure it with a simple
+	 * heuristic: we are willing to spend at most 2% of the time
+	 * transitioning between power states.  Therefore, when running
+	 * in any given state, we will enter the next lower-power
+	 * non-operational state after waiting 100 * (enlat + exlat)
+	 * microseconds, as long as that state's total latency is under
+	 * the requested maximum latency.
+	 *
+	 * We will not autonomously enter any non-operational state for
+	 * which the total latency exceeds ps_max_latency_us.  Users
+	 * can set ps_max_latency_us to zero to turn off APST.
+	 */
+
+	unsigned apste;
+	struct nvme_feat_auto_pst *table;
+	int ret;
+
+	/*
+	 * If APST isn't supported or if we haven't been initialized yet,
+	 * then don't do anything.
+	 */
+	if (!ctrl->apsta)
+		return;
+
+	if (ctrl->npss > 31) {
+		dev_warn(ctrl->device, "NPSS is invalid; not using APST\n");
+		return;
+	}
+
+	table = kzalloc(sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return;
+
+	if (ctrl->ps_max_latency_us == 0) {
+		/* Turn off APST. */
+		apste = 0;
+	} else {
+		__le64 target = cpu_to_le64(0);
+		int state;
+
+		/*
+		 * Walk through all states from lowest- to highest-power.
+		 * According to the spec, lower-numbered states use more
+		 * power.  NPSS, despite the name, is the index of the
+		 * lowest-power state, not the number of states.
+		 */
+		for (state = (int)ctrl->npss; state >= 0; state--) {
+			u64 total_latency_us, transition_ms;
+
+			if (target)
+				table->entries[state] = target;
+
+			/*
+			 * Is this state a useful non-operational state for
+			 * higher-power states to autonomously transition to?
+			 */
+			if (!(ctrl->psd[state].flags &
+			      NVME_PS_FLAGS_NON_OP_STATE))
+				continue;
+
+			total_latency_us =
+				(u64)le32_to_cpu(ctrl->psd[state].entry_lat) +
+				+ le32_to_cpu(ctrl->psd[state].exit_lat);
+			if (total_latency_us > ctrl->ps_max_latency_us)
+				continue;
+
+			/*
+			 * This state is good.  Use it as the APST idle
+			 * target for higher power states.
+			 */
+			transition_ms = total_latency_us + 19;
+			do_div(transition_ms, 20);
+			if (transition_ms > (1 << 24) - 1)
+				transition_ms = (1 << 24) - 1;
+
+			target = cpu_to_le64((state << 3) |
+					     (transition_ms << 8));
+		}
+
+		apste = 1;
+	}
+
+	ret = nvme_set_features(ctrl, NVME_FEAT_AUTO_PST, apste,
+				table, sizeof(*table), NULL);
+	if (ret)
+		dev_err(ctrl->device, "failed to set APST feature (%d)\n", ret);
+
+	kfree(table);
+}
+
+static void nvme_set_latency_tolerance(struct device *dev, s32 val)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	u64 latency;
+
+	switch (val) {
+	case PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT:
+	case PM_QOS_LATENCY_ANY:
+		latency = U64_MAX;
+		break;
+
+	default:
+		latency = val;
+	}
+
+	if (ctrl->ps_max_latency_us != latency) {
+		ctrl->ps_max_latency_us = latency;
+		nvme_configure_apst(ctrl);
+	}
+}
+
+struct nvme_core_quirk_entry {
+	/*
+	 * NVMe model and firmware strings are padded with spaces.  For
+	 * simplicity, strings in the quirk table are padded with NULLs
+	 * instead.
+	 */
+	u16 vid;
+	const char *mn;
+	const char *fr;
+	unsigned long quirks;
+};
+
+static const struct nvme_core_quirk_entry core_quirks[] = {
+	/*
+	 * Seen on a Samsung "SM951 NVMe SAMSUNG 256GB": using APST causes
+	 * the controller to go out to lunch.  It dies when the watchdog
+	 * timer reads CSTS and gets 0xffffffff.
+	 */
+	{
+		.vid = 0x144d,
+		.fr = "BXW75D0Q",
+		.quirks = NVME_QUIRK_NO_APST,
+	},
+};
+
+/* match is null-terminated but idstr is space-padded. */
+static bool string_matches(const char *idstr, const char *match, size_t len)
+{
+	size_t matchlen;
+
+	if (!match)
+		return true;
+
+	matchlen = strlen(match);
+	WARN_ON_ONCE(matchlen > len);
+
+	if (memcmp(idstr, match, matchlen))
+		return false;
+
+	for (; matchlen < len; matchlen++)
+		if (idstr[matchlen] != ' ')
+			return false;
+
+	return true;
+}
+
+static bool quirk_matches(const struct nvme_id_ctrl *id,
+			  const struct nvme_core_quirk_entry *q)
+{
+	return q->vid == le16_to_cpu(id->vid) &&
+		string_matches(id->mn, q->mn, sizeof(id->mn)) &&
+		string_matches(id->fr, q->fr, sizeof(id->fr));
+}
+
 /*
  * Initialize the cached copies of the Identify data and various controller
  * register in our nvme_ctrl structure.  This should be called as soon as
@@ -1262,6 +1439,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	u64 cap;
 	int ret, page_shift;
 	u32 max_hw_sectors;
+	u8 prev_apsta;
 
 	ret = ctrl->ops->reg_read32(ctrl, NVME_REG_VS, &ctrl->vs);
 	if (ret) {
@@ -1285,6 +1463,24 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		return -EIO;
 	}
 
+	if (!ctrl->identified) {
+		/*
+		 * Check for quirks.  Quirk can depend on firmware version,
+		 * so, in principle, the set of quirks present can change
+		 * across a reset.  As a possible future enhancement, we
+		 * could re-scan for quirks every time we reinitialize
+		 * the device, but we'd have to make sure that the driver
+		 * behaves intelligently if the quirks change.
+		 */
+
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(core_quirks); i++) {
+			if (quirk_matches(id, &core_quirks[i]))
+				ctrl->quirks |= core_quirks[i].quirks;
+		}
+	}
+
 	ctrl->oacs = le16_to_cpu(id->oacs);
 	ctrl->vid = le16_to_cpu(id->vid);
 	ctrl->oncs = le16_to_cpup(&id->oncs);
@@ -1305,6 +1501,11 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	ctrl->sgls = le32_to_cpu(id->sgls);
 	ctrl->kas = le16_to_cpu(id->kas);
 
+	ctrl->npss = id->npss;
+	prev_apsta = ctrl->apsta;
+	ctrl->apsta = (ctrl->quirks & NVME_QUIRK_NO_APST) ? 0 : id->apsta;
+	memcpy(ctrl->psd, id->psd, sizeof(ctrl->psd));
+
 	if (ctrl->ops->is_fabrics) {
 		ctrl->icdoff = le16_to_cpu(id->icdoff);
 		ctrl->ioccsz = le32_to_cpu(id->ioccsz);
@@ -1328,6 +1529,16 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	}
 
 	kfree(id);
+
+	if (ctrl->apsta && !prev_apsta)
+		dev_pm_qos_expose_latency_tolerance(ctrl->device);
+	else if (!ctrl->apsta && prev_apsta)
+		dev_pm_qos_hide_latency_tolerance(ctrl->device);
+
+	nvme_configure_apst(ctrl);
+
+	ctrl->identified = true;
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nvme_init_identify);
@@ -1577,6 +1788,29 @@ static ssize_t nvme_sysfs_show_transport(struct device *dev,
 }
 static DEVICE_ATTR(transport, S_IRUGO, nvme_sysfs_show_transport, NULL);
 
+static ssize_t nvme_sysfs_show_state(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	static const char *const state_name[] = {
+		[NVME_CTRL_NEW]		= "new",
+		[NVME_CTRL_LIVE]	= "live",
+		[NVME_CTRL_RESETTING]	= "resetting",
+		[NVME_CTRL_RECONNECTING]= "reconnecting",
+		[NVME_CTRL_DELETING]	= "deleting",
+		[NVME_CTRL_DEAD]	= "dead",
+	};
+
+	if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) &&
+	    state_name[ctrl->state])
+		return sprintf(buf, "%s\n", state_name[ctrl->state]);
+
+	return sprintf(buf, "unknown state\n");
+}
+
+static DEVICE_ATTR(state, S_IRUGO, nvme_sysfs_show_state, NULL);
+
 static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
@@ -1609,6 +1843,7 @@ static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_transport.attr,
 	&dev_attr_subsysnqn.attr,
 	&dev_attr_address.attr,
+	&dev_attr_state.attr,
 	NULL
 };
 
@@ -2065,6 +2300,14 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	list_add_tail(&ctrl->node, &nvme_ctrl_list);
 	spin_unlock(&dev_list_lock);
 
+	/*
+	 * Initialize latency tolerance controls.  The sysfs files won't
+	 * be visible to userspace unless the device actually supports APST.
+	 */
+	ctrl->device->power.set_latency_tolerance = nvme_set_latency_tolerance;
+	dev_pm_qos_update_user_latency_tolerance(ctrl->device,
+		min(default_ps_max_latency_us, (unsigned long)S32_MAX));
+
 	return 0;
 out_release_instance:
 	nvme_release_instance(ctrl);
@@ -2090,9 +2333,9 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
 		 * Revalidating a dead namespace sets capacity to 0. This will
 		 * end buffered writers dirtying pages that can't be synced.
 		 */
-		if (ns->disk && !test_and_set_bit(NVME_NS_DEAD, &ns->flags))
-			revalidate_disk(ns->disk);
-
+		if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+			continue;
+		revalidate_disk(ns->disk);
 		blk_set_queue_dying(ns->queue);
 		blk_mq_abort_requeue_list(ns->queue);
 		blk_mq_start_stopped_hw_queues(ns->queue, true);