Merge tag 'nvme-5.14-2021-06-22' of git://git.infradead.org/nvme into for-5.14/drivers

Pull NVMe updates from Christoph

"nvme updates for Linux 5.14:

 - move the ACPI StorageD3 code to drivers/acpi/ and add quirks for
   certain AMD CPUs (Mario Limonciello)
 - zoned device support for nvmet (Chaitanya Kulkarni)
 - fix the rules for changing the serial number in nvmet (Noam Gottlieb)
 - various small fixes and cleanups (Dan Carpenter, JK Kim,
   Chaitanya Kulkarni, Hannes Reinecke, Wesley Sheng, Geert Uytterhoeven,
   Daniel Wagner)"

* tag 'nvme-5.14-2021-06-22' of git://git.infradead.org/nvme: (38 commits)
  nvmet: use NVMET_MAX_NAMESPACES to set nn value
  nvme.h: add missing nvme_lba_range_type endianness annotations
  nvme: remove zeroout memset call for struct
  nvme-pci: remove zeroout memset call for struct
  nvmet: remove zeroout memset call for struct
  nvmet: add ZBD over ZNS backend support
  nvmet: add Command Set Identifier support
  nvmet: add nvmet_req_bio put helper for backends
  nvmet: add req cns error complete helper
  block: export blk_next_bio()
  nvmet: remove local variable
  nvmet: use nvme status value directly
  nvmet: use u32 type for the local variable nsid
  nvmet: use u32 for nvmet_subsys max_nsid
  nvmet: use req->cmd directly in file-ns fast path
  nvmet: use req->cmd directly in bdev-ns fast path
  nvmet: make ver stable once connection established
  nvmet: allow mn change if subsys not discovered
  nvmet: make sn stable once connection was established
  nvmet: change sn size and check validity
  ...

Author: axboe

block/blk-lib.c

@@ -21,6 +21,7 @@ struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp)
 
 	return new;
 }
+EXPORT_SYMBOL_GPL(blk_next_bio);
 
 int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, int flags,

drivers/acpi/device_pm.c

@@ -1340,4 +1340,36 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
 	return 1;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_pm_attach);
+
+/**
+ * acpi_storage_d3 - Check if D3 should be used in the suspend path
+ * @dev: Device to check
+ *
+ * Return %true if the platform firmware wants @dev to be programmed
+ * into D3hot or D3cold (if supported) in the suspend path, or %false
+ * when there is no specific preference. On some platforms, if this
+ * hint is ignored, @dev may remain unresponsive after suspending the
+ * platform as a whole.
+ *
+ * Although the property has storage in the name it actually is
+ * applied to the PCIe slot and plugging in a non-storage device the
+ * same platform restrictions will likely apply.
+ */
+bool acpi_storage_d3(struct device *dev)
+{
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+	u8 val;
+
+	if (force_storage_d3())
+		return true;
+
+	if (!adev)
+		return false;
+	if (fwnode_property_read_u8(acpi_fwnode_handle(adev), "StorageD3Enable",
+			&val))
+		return false;
+	return val == 1;
+}
+EXPORT_SYMBOL_GPL(acpi_storage_d3);
+
 #endif /* CONFIG_PM */

drivers/acpi/internal.h

@@ -236,6 +236,15 @@ static inline int suspend_nvs_save(void) { return 0; }
 static inline void suspend_nvs_restore(void) {}
 #endif
 
+#ifdef CONFIG_X86
+bool force_storage_d3(void);
+#else
+static inline bool force_storage_d3(void)
+{
+	return false;
+}
+#endif
+
 /*--------------------------------------------------------------------------
 				Device properties
   -------------------------------------------------------------------------- */

drivers/acpi/x86/utils.c

@@ -135,3 +135,28 @@ bool acpi_device_always_present(struct acpi_device *adev)
 
 	return ret;
 }
+
+/*
+ * AMD systems from Renoir and Lucienne *require* that the NVME controller
+ * is put into D3 over a Modern Standby / suspend-to-idle cycle.
+ *
+ * This is "typically" accomplished using the `StorageD3Enable`
+ * property in the _DSD that is checked via the `acpi_storage_d3` function
+ * but this property was introduced after many of these systems launched
+ * and most OEM systems don't have it in their BIOS.
+ *
+ * The Microsoft documentation for StorageD3Enable mentioned that Windows has
+ * a hardcoded allowlist for D3 support, which was used for these platforms.
+ *
+ * This allows quirking on Linux in a similar fashion.
+ */
+static const struct x86_cpu_id storage_d3_cpu_ids[] = {
+	X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 96, NULL),	/* Renoir */
+	X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 104, NULL),	/* Lucienne */
+	{}
+};
+
+bool force_storage_d3(void)
+{
+	return x86_match_cpu(storage_d3_cpu_ids);
+}

drivers/nvme/host/Kconfig

@@ -21,7 +21,7 @@ config NVME_MULTIPATH
 	help
 	   This option enables support for multipath access to NVMe
 	   subsystems.  If this option is enabled only a single
-	   /dev/nvmeXnY device will show up for each NVMe namespaces,
+	   /dev/nvmeXnY device will show up for each NVMe namespace,
 	   even if it is accessible through multiple controllers.
 
 config NVME_HWMON

drivers/nvme/host/core.c

@@ -721,9 +721,7 @@ EXPORT_SYMBOL_GPL(__nvme_check_ready);
 
 static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable)
 {
-	struct nvme_command c;
-
-	memset(&c, 0, sizeof(c));
+	struct nvme_command c = { };
 
 	c.directive.opcode = nvme_admin_directive_send;
 	c.directive.nsid = cpu_to_le32(NVME_NSID_ALL);
@@ -748,9 +746,8 @@ static int nvme_enable_streams(struct nvme_ctrl *ctrl)
 static int nvme_get_stream_params(struct nvme_ctrl *ctrl,
 				  struct streams_directive_params *s, u32 nsid)
 {
-	struct nvme_command c;
+	struct nvme_command c = { };
 
-	memset(&c, 0, sizeof(c));
 	memset(s, 0, sizeof(*s));
 
 	c.directive.opcode = nvme_admin_directive_recv;
@@ -1460,10 +1457,9 @@ static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid,
 		unsigned int dword11, void *buffer, size_t buflen, u32 *result)
 {
 	union nvme_result res = { 0 };
-	struct nvme_command c;
+	struct nvme_command c = { };
 	int ret;
 
-	memset(&c, 0, sizeof(c));
 	c.features.opcode = op;
 	c.features.fid = cpu_to_le32(fid);
 	c.features.dword11 = cpu_to_le32(dword11);
@@ -1591,9 +1587,8 @@ int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type,
 				u32 max_integrity_segments)
 {
-	struct blk_integrity integrity;
+	struct blk_integrity integrity = { };
 
-	memset(&integrity, 0, sizeof(integrity));
 	switch (pi_type) {
 	case NVME_NS_DPS_PI_TYPE3:
 		integrity.profile = &t10_pi_type3_crc;
@@ -1964,13 +1959,12 @@ static int nvme_send_ns_pr_command(struct nvme_ns *ns, struct nvme_command *c,
 static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
 				u64 key, u64 sa_key, u8 op)
 {
-	struct nvme_command c;
+	struct nvme_command c = { };
 	u8 data[16] = { 0, };
 
 	put_unaligned_le64(key, &data[0]);
 	put_unaligned_le64(sa_key, &data[8]);
 
-	memset(&c, 0, sizeof(c));
 	c.common.opcode = op;
 	c.common.cdw10 = cpu_to_le32(cdw10);
 
@@ -2042,9 +2036,8 @@ int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
 		bool send)
 {
 	struct nvme_ctrl *ctrl = data;
-	struct nvme_command cmd;
+	struct nvme_command cmd = { };
 
-	memset(&cmd, 0, sizeof(cmd));
 	if (send)
 		cmd.common.opcode = nvme_admin_security_send;
 	else

drivers/nvme/host/fabrics.c

@@ -190,11 +190,10 @@ EXPORT_SYMBOL_GPL(nvmf_reg_read32);
  */
 int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
 {
-	struct nvme_command cmd;
+	struct nvme_command cmd = { };
 	union nvme_result res;
 	int ret;
 
-	memset(&cmd, 0, sizeof(cmd));
 	cmd.prop_get.opcode = nvme_fabrics_command;
 	cmd.prop_get.fctype = nvme_fabrics_type_property_get;
 	cmd.prop_get.attrib = 1;
@@ -236,10 +235,9 @@ EXPORT_SYMBOL_GPL(nvmf_reg_read64);
  */
 int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
 {
-	struct nvme_command cmd;
+	struct nvme_command cmd = { };
 	int ret;
 
-	memset(&cmd, 0, sizeof(cmd));
 	cmd.prop_set.opcode = nvme_fabrics_command;
 	cmd.prop_set.fctype = nvme_fabrics_type_property_set;
 	cmd.prop_set.attrib = 0;
@@ -364,12 +362,11 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl,
  */
 int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
 {
-	struct nvme_command cmd;
+	struct nvme_command cmd = { };
 	union nvme_result res;
 	struct nvmf_connect_data *data;
 	int ret;
 
-	memset(&cmd, 0, sizeof(cmd));
 	cmd.connect.opcode = nvme_fabrics_command;
 	cmd.connect.fctype = nvme_fabrics_type_connect;
 	cmd.connect.qid = 0;
@@ -432,12 +429,11 @@ EXPORT_SYMBOL_GPL(nvmf_connect_admin_queue);
  */
 int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid, bool poll)
 {
-	struct nvme_command cmd;
+	struct nvme_command cmd = { };
 	struct nvmf_connect_data *data;
 	union nvme_result res;
 	int ret;
 
-	memset(&cmd, 0, sizeof(cmd));
 	cmd.connect.opcode = nvme_fabrics_command;
 	cmd.connect.fctype = nvme_fabrics_type_connect;
 	cmd.connect.qid = cpu_to_le16(qid);

drivers/nvme/host/fc.c

@@ -3111,7 +3111,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	}
 
 	/* FC-NVME supports normal SGL Data Block Descriptors */
-	if (!(ctrl->ctrl.sgls & ((1 << 0) | (1 << 1)))) {
+	if (!nvme_ctrl_sgl_supported(&ctrl->ctrl)) {
 		dev_err(ctrl->ctrl.device,
 			"Mandatory sgls are not supported!\n");
 		goto out_disconnect_admin_queue;

drivers/nvme/host/ioctl.c

@@ -177,6 +177,20 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 			metadata, meta_len, lower_32_bits(io.slba), NULL, 0);
 }
 
+static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
+					struct nvme_ns *ns, __u32 nsid)
+{
+	if (ns && nsid != ns->head->ns_id) {
+		dev_err(ctrl->device,
+			"%s: nsid (%u) in cmd does not match nsid (%u)"
+			"of namespace\n",
+			current->comm, nsid, ns->head->ns_id);
+		return false;
+	}
+
+	return true;
+}
+
 static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 			struct nvme_passthru_cmd __user *ucmd)
 {
@@ -192,12 +206,8 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 		return -EFAULT;
 	if (cmd.flags)
 		return -EINVAL;
-	if (ns && cmd.nsid != ns->head->ns_id) {
-		dev_err(ctrl->device,
-			"%s: nsid (%u) in cmd does not match nsid (%u) of namespace\n",
-			current->comm, cmd.nsid, ns->head->ns_id);
+	if (!nvme_validate_passthru_nsid(ctrl, ns, cmd.nsid))
 		return -EINVAL;
-	}
 
 	memset(&c, 0, sizeof(c));
 	c.common.opcode = cmd.opcode;
@@ -242,12 +252,8 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 		return -EFAULT;
 	if (cmd.flags)
 		return -EINVAL;
-	if (ns && cmd.nsid != ns->head->ns_id) {
-		dev_err(ctrl->device,
-			"%s: nsid (%u) in cmd does not match nsid (%u) of namespace\n",
-			current->comm, cmd.nsid, ns->head->ns_id);
+	if (!nvme_validate_passthru_nsid(ctrl, ns, cmd.nsid))
 		return -EINVAL;
-	}
 
 	memset(&c, 0, sizeof(c));
 	c.common.opcode = cmd.opcode;

drivers/nvme/host/multipath.c

@@ -435,11 +435,6 @@ static void nvme_requeue_work(struct work_struct *work)
 		next = bio->bi_next;
 		bio->bi_next = NULL;
 
-		/*
-		 * Reset disk to the mpath node and resubmit to select a new
-		 * path.
-		 */
-		bio_set_dev(bio, head->disk->part0);
 		submit_bio_noacct(bio);
 	}
 }
@@ -818,6 +813,13 @@ int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	    !(ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA))
 		return 0;
 
+	if (!ctrl->max_namespaces ||
+	    ctrl->max_namespaces > le32_to_cpu(id->nn)) {
+		dev_err(ctrl->device,
+			"Invalid MNAN value %u\n", ctrl->max_namespaces);
+		return -EINVAL;
+	}
+
 	ctrl->anacap = id->anacap;
 	ctrl->anatt = id->anatt;
 	ctrl->nanagrpid = le32_to_cpu(id->nanagrpid);