nvme: check admin passthru command effects

The NVMe standard provides a command effects log page so the host may
be aware of special requirements it may need to do for a particular
command. For example, the command may need to run with IO quiesced to
prevent timeouts or undefined behavior, or it may change the logical block
formats that determine how the host needs to construct future commands.

This patch saves the nvme command effects log page if the controller
supports it, and performs appropriate actions before and after an admin
passthrough command is completed. If the controller does not support the
command effects log page, the driver will define the effects for known
opcodes. The nvme format and santize are the only commands in this patch
with known effects.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

drivers/nvme/host/core.c

@@ -72,6 +72,9 @@ static DEFINE_IDA(nvme_instance_ida);
 static dev_t nvme_chr_devt;
 static struct class *nvme_class;
 
+static void nvme_ns_remove(struct nvme_ns *ns);
+static int nvme_revalidate_disk(struct gendisk *disk);
+
 static __le32 nvme_get_log_dw10(u8 lid, size_t size)
 {
 	return cpu_to_le32((((size / 4) - 1) << 16) | lid);
@@ -992,12 +995,87 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 			metadata, meta_len, io.slba, NULL, 0);
 }
 
+static u32 nvme_known_admin_effects(u8 opcode)
+{
+	switch (opcode) {
+	case nvme_admin_format_nvm:
+		return NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC |
+					NVME_CMD_EFFECTS_CSE_MASK;
+	case nvme_admin_sanitize_nvm:
+		return NVME_CMD_EFFECTS_CSE_MASK;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
+								u8 opcode)
+{
+	u32 effects = 0;
+
+	if (ns) {
+		if (ctrl->effects)
+			effects = le32_to_cpu(ctrl->effects->iocs[opcode]);
+		if (effects & ~NVME_CMD_EFFECTS_CSUPP)
+			dev_warn(ctrl->device,
+				 "IO command:%02x has unhandled effects:%08x\n",
+				 opcode, effects);
+		return 0;
+	}
+
+	if (ctrl->effects)
+		effects = le32_to_cpu(ctrl->effects->iocs[opcode]);
+	else
+		effects = nvme_known_admin_effects(opcode);
+
+	/*
+	 * For simplicity, IO to all namespaces is quiesced even if the command
+	 * effects say only one namespace is affected.
+	 */
+	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
+		nvme_start_freeze(ctrl);
+		nvme_wait_freeze(ctrl);
+	}
+	return effects;
+}
+
+static void nvme_update_formats(struct nvme_ctrl *ctrl)
+{
+	struct nvme_ns *ns;
+
+	mutex_lock(&ctrl->namespaces_mutex);
+	list_for_each_entry(ns, &ctrl->namespaces, list) {
+		if (ns->disk && nvme_revalidate_disk(ns->disk))
+			nvme_ns_remove(ns);
+	}
+	mutex_unlock(&ctrl->namespaces_mutex);
+}
+
+static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
+{
+	/*
+	 * Revalidate LBA changes prior to unfreezing. This is necessary to
+	 * prevent memory corruption if a logical block size was changed by
+	 * this command.
+	 */
+	if (effects & NVME_CMD_EFFECTS_LBCC)
+		nvme_update_formats(ctrl);
+	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK))
+		nvme_unfreeze(ctrl);
+	if (effects & NVME_CMD_EFFECTS_CCC)
+		nvme_init_identify(ctrl);
+	if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC))
+		nvme_queue_scan(ctrl);
+}
+
 static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 			struct nvme_passthru_cmd __user *ucmd)
 {
 	struct nvme_passthru_cmd cmd;
 	struct nvme_command c;
 	unsigned timeout = 0;
+	u32 effects;
 	int status;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -1023,10 +1101,13 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	if (cmd.timeout_ms)
 		timeout = msecs_to_jiffies(cmd.timeout_ms);
 
+	effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
 			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
 			(void __user *)(uintptr_t)cmd.metadata, cmd.metadata,
 			0, &cmd.result, timeout);
+	nvme_passthru_end(ctrl, effects);
+
 	if (status >= 0) {
 		if (put_user(cmd.result, &ucmd->result))
 			return -EFAULT;
@@ -1759,6 +1840,25 @@ static int nvme_get_log(struct nvme_ctrl *ctrl, u8 log_page, void *log,
 	return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
 }
 
+static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
+{
+	int ret;
+
+	if (!ctrl->effects)
+		ctrl->effects = kzalloc(sizeof(*ctrl->effects), GFP_KERNEL);
+
+	if (!ctrl->effects)
+		return 0;
+
+	ret = nvme_get_log(ctrl, NVME_LOG_CMD_EFFECTS, ctrl->effects,
+					sizeof(*ctrl->effects));
+	if (ret) {
+		kfree(ctrl->effects);
+		ctrl->effects = NULL;
+	}
+	return ret;
+}
+
 /*
  * Initialize the cached copies of the Identify data and various controller
  * register in our nvme_ctrl structure.  This should be called as soon as
@@ -1794,6 +1894,12 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		return -EIO;
 	}
 
+	if (id->lpa & NVME_CTRL_LPA_CMD_EFFECTS_LOG) {
+		ret = nvme_get_effects_log(ctrl);
+		if (ret < 0)
+			return ret;
+	}
+
 	nvme_init_subnqn(ctrl, id);
 
 	if (!ctrl->identified) {
@@ -2713,6 +2819,7 @@ static void nvme_free_ctrl(struct device *dev)
 
 	ida_simple_remove(&nvme_instance_ida, ctrl->instance);
 	ida_destroy(&ctrl->ns_ida);
+	kfree(ctrl->effects);
 
 	ctrl->ops->free_ctrl(ctrl);
 }

drivers/nvme/host/nvme.h

@@ -174,6 +174,7 @@ struct nvme_ctrl {
 	bool subsystem;
 	unsigned long quirks;
 	struct nvme_id_power_state psd[32];
+	struct nvme_effects_log *effects;
 	struct work_struct scan_work;
 	struct work_struct async_event_work;
 	struct delayed_work ka_work;

include/linux/nvme.h

@@ -267,6 +267,7 @@ enum {
 	NVME_CTRL_OACS_SEC_SUPP                 = 1 << 0,
 	NVME_CTRL_OACS_DIRECTIVES		= 1 << 5,
 	NVME_CTRL_OACS_DBBUF_SUPP		= 1 << 8,
+	NVME_CTRL_LPA_CMD_EFFECTS_LOG		= 1 << 1,
 };
 
 struct nvme_lbaf {
@@ -395,6 +396,21 @@ struct nvme_fw_slot_info_log {
 	__u8			rsvd64[448];
 };
 
+enum {
+	NVME_CMD_EFFECTS_CSUPP		= 1 << 0,
+	NVME_CMD_EFFECTS_LBCC		= 1 << 1,
+	NVME_CMD_EFFECTS_NCC		= 1 << 2,
+	NVME_CMD_EFFECTS_NIC		= 1 << 3,
+	NVME_CMD_EFFECTS_CCC		= 1 << 4,
+	NVME_CMD_EFFECTS_CSE_MASK	= 3 << 16,
+};
+
+struct nvme_effects_log {
+	__le32 acs[256];
+	__le32 iocs[256];
+	__u8   resv[2048];
+};
+
 enum {
 	NVME_SMART_CRIT_SPARE		= 1 << 0,
 	NVME_SMART_CRIT_TEMPERATURE	= 1 << 1,
@@ -681,6 +697,7 @@ enum nvme_admin_opcode {
 	nvme_admin_format_nvm		= 0x80,
 	nvme_admin_security_send	= 0x81,
 	nvme_admin_security_recv	= 0x82,
+	nvme_admin_sanitize_nvm		= 0x84,
 };
 
 enum {
@@ -712,6 +729,7 @@ enum {
 	NVME_LOG_ERROR		= 0x01,
 	NVME_LOG_SMART		= 0x02,
 	NVME_LOG_FW_SLOT	= 0x03,
+	NVME_LOG_CMD_EFFECTS	= 0x05,
 	NVME_LOG_DISC		= 0x70,
 	NVME_LOG_RESERVATION	= 0x80,
 	NVME_FWACT_REPL		= (0 << 3),