Merge branch 'nvme-5.8' of git://git.infradead.org/nvme into for-5.8/drivers

Pull NVMe updates from Christoph:

"The second large batch of nvme updates:

 - t10 protection information support for nvme-rdma and nvmet-rdma
   (Israel Rukshin and Max Gurtovoy)
 - target side AEN improvements (Chaitanya Kulkarni)
 - various fixes and minor improvements all over, icluding the nvme part
   of the lpfc driver"

* 'nvme-5.8' of git://git.infradead.org/nvme: (38 commits)
  lpfc: Fix return value in __lpfc_nvme_ls_abort
  lpfc: fix axchg pointer reference after free and double frees
  lpfc: Fix pointer checks and comments in LS receive refactoring
  nvme: set dma alignment to qword
  nvmet: cleanups the loop in nvmet_async_events_process
  nvmet: fix memory leak when removing namespaces and controllers concurrently
  nvmet-rdma: add metadata/T10-PI support
  nvmet: add metadata support for block devices
  nvmet: add metadata/T10-PI support
  nvme: add Metadata Capabilities enumerations
  nvmet: rename nvmet_check_data_len to nvmet_check_transfer_len
  nvmet: rename nvmet_rw_len to nvmet_rw_data_len
  nvmet: add metadata characteristics for a namespace
  nvme-rdma: add metadata/T10-PI support
  nvme-rdma: introduce nvme_rdma_sgl structure
  nvme: introduce NVME_INLINE_METADATA_SG_CNT
  nvme: enforce extended LBA format for fabrics metadata
  nvme: introduce max_integrity_segments ctrl attribute
  nvme: make nvme_ns_has_pi accessible to transports
  nvme: introduce NVME_NS_METADATA_SUPPORTED flag
  ...

Author: axboe

drivers/nvme/host/core.c

@@ -19,7 +19,6 @@
 #include <linux/pr.h>
 #include <linux/ptrace.h>
 #include <linux/nvme_ioctl.h>
-#include <linux/t10-pi.h>
 #include <linux/pm_qos.h>
 #include <asm/unaligned.h>
 
@@ -204,11 +203,6 @@ static void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl)
 	nvme_put_ctrl(ctrl);
 }
 
-static inline bool nvme_ns_has_pi(struct nvme_ns *ns)
-{
-	return ns->pi_type && ns->ms == sizeof(struct t10_pi_tuple);
-}
-
 static blk_status_t nvme_error_status(u16 status)
 {
 	switch (status & 0x7ff) {
@@ -552,19 +546,22 @@ static int nvme_configure_directives(struct nvme_ctrl *ctrl)
 
 	ret = nvme_get_stream_params(ctrl, &s, NVME_NSID_ALL);
 	if (ret)
-		return ret;
+		goto out_disable_stream;
 
 	ctrl->nssa = le16_to_cpu(s.nssa);
 	if (ctrl->nssa < BLK_MAX_WRITE_HINTS - 1) {
 		dev_info(ctrl->device, "too few streams (%u) available\n",
 					ctrl->nssa);
-		nvme_disable_streams(ctrl);
-		return 0;
+		goto out_disable_stream;
 	}
 
 	ctrl->nr_streams = min_t(unsigned, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1);
 	dev_info(ctrl->device, "Using %u streams\n", ctrl->nr_streams);
 	return 0;
+
+out_disable_stream:
+	nvme_disable_streams(ctrl);
+	return ret;
 }
 
 /*
@@ -1302,7 +1299,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	meta_len = (io.nblocks + 1) * ns->ms;
 	metadata = nvme_to_user_ptr(io.metadata);
 
-	if (ns->ext) {
+	if (ns->features & NVME_NS_EXT_LBAS) {
 		length += meta_len;
 		meta_len = 0;
 	} else if (meta_len) {
@@ -1696,7 +1693,8 @@ static int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 }
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
-static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type)
+static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type,
+				u32 max_integrity_segments)
 {
 	struct blk_integrity integrity;
 
@@ -1719,10 +1717,11 @@ static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type)
 	}
 	integrity.tuple_size = ms;
 	blk_integrity_register(disk, &integrity);
-	blk_queue_max_integrity_segments(disk->queue, 1);
+	blk_queue_max_integrity_segments(disk->queue, max_integrity_segments);
 }
 #else
-static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type)
+static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type,
+				u32 max_integrity_segments)
 {
 }
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
@@ -1842,7 +1841,7 @@ static void nvme_update_disk_info(struct gendisk *disk,
 {
 	sector_t capacity = nvme_lba_to_sect(ns, le64_to_cpu(id->nsze));
 	unsigned short bs = 1 << ns->lba_shift;
-	u32 atomic_bs, phys_bs, io_opt;
+	u32 atomic_bs, phys_bs, io_opt = 0;
 
 	if (ns->lba_shift > PAGE_SHIFT) {
 		/* unsupported block size, set capacity to 0 later */
@@ -1851,7 +1850,7 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	blk_mq_freeze_queue(disk->queue);
 	blk_integrity_unregister(disk);
 
-	atomic_bs = phys_bs = io_opt = bs;
+	atomic_bs = phys_bs = bs;
 	nvme_setup_streams_ns(ns->ctrl, ns, &phys_bs, &io_opt);
 	if (id->nabo == 0) {
 		/*
@@ -1882,13 +1881,28 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	blk_queue_io_min(disk->queue, phys_bs);
 	blk_queue_io_opt(disk->queue, io_opt);
 
-	if (ns->ms && !ns->ext &&
-	    (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
-		nvme_init_integrity(disk, ns->ms, ns->pi_type);
-	if ((ns->ms && !nvme_ns_has_pi(ns) && !blk_get_integrity(disk)) ||
-	    ns->lba_shift > PAGE_SHIFT)
+	/*
+	 * The block layer can't support LBA sizes larger than the page size
+	 * yet, so catch this early and don't allow block I/O.
+	 */
+	if (ns->lba_shift > PAGE_SHIFT)
 		capacity = 0;
 
+	/*
+	 * Register a metadata profile for PI, or the plain non-integrity NVMe
+	 * metadata masquerading as Type 0 if supported, otherwise reject block
+	 * I/O to namespaces with metadata except when the namespace supports
+	 * PI, as it can strip/insert in that case.
+	 */
+	if (ns->ms) {
+		if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
+		    (ns->features & NVME_NS_METADATA_SUPPORTED))
+			nvme_init_integrity(disk, ns->ms, ns->pi_type,
+					    ns->ctrl->max_integrity_segments);
+		else if (!nvme_ns_has_pi(ns))
+			capacity = 0;
+	}
+
 	set_capacity_revalidate_and_notify(disk, capacity, false);
 
 	nvme_config_discard(disk, ns);
@@ -1902,9 +1916,10 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	blk_mq_unfreeze_queue(disk->queue);
 }
 
-static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
+static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 {
 	struct nvme_ns *ns = disk->private_data;
+	struct nvme_ctrl *ctrl = ns->ctrl;
 	u32 iob;
 
 	/*
@@ -1915,20 +1930,43 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	if (ns->lba_shift == 0)
 		ns->lba_shift = 9;
 
-	if ((ns->ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
-	    is_power_of_2(ns->ctrl->max_hw_sectors))
-		iob = ns->ctrl->max_hw_sectors;
+	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
+	    is_power_of_2(ctrl->max_hw_sectors))
+		iob = ctrl->max_hw_sectors;
 	else
 		iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));
 
+	ns->features = 0;
 	ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
-	ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
 	/* the PI implementation requires metadata equal t10 pi tuple size */
 	if (ns->ms == sizeof(struct t10_pi_tuple))
 		ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
 	else
 		ns->pi_type = 0;
 
+	if (ns->ms) {
+		/*
+		 * For PCIe only the separate metadata pointer is supported,
+		 * as the block layer supplies metadata in a separate bio_vec
+		 * chain. For Fabrics, only metadata as part of extended data
+		 * LBA is supported on the wire per the Fabrics specification,
+		 * but the HBA/HCA will do the remapping from the separate
+		 * metadata buffers for us.
+		 */
+		if (id->flbas & NVME_NS_FLBAS_META_EXT) {
+			ns->features |= NVME_NS_EXT_LBAS;
+			if ((ctrl->ops->flags & NVME_F_FABRICS) &&
+			    (ctrl->ops->flags & NVME_F_METADATA_SUPPORTED) &&
+			    ctrl->max_integrity_segments)
+				ns->features |= NVME_NS_METADATA_SUPPORTED;
+		} else {
+			if (WARN_ON_ONCE(ctrl->ops->flags & NVME_F_FABRICS))
+				return -EINVAL;
+			if (ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)
+				ns->features |= NVME_NS_METADATA_SUPPORTED;
+		}
+	}
+
 	if (iob)
 		blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(iob));
 	nvme_update_disk_info(disk, ns, id);
@@ -1939,6 +1977,7 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		revalidate_disk(ns->head->disk);
 	}
 #endif
+	return 0;
 }
 
 static int nvme_revalidate_disk(struct gendisk *disk)
@@ -1974,7 +2013,7 @@ static int nvme_revalidate_disk(struct gendisk *disk)
 		goto free_id;
 	}
 
-	__nvme_revalidate_disk(disk, id);
+	ret = __nvme_revalidate_disk(disk, id);
 free_id:
 	kfree(id);
 out:
@@ -2283,6 +2322,7 @@ 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, ctrl->page_size - 1);
+	blk_queue_dma_alignment(q, 7);
 	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
 		vwc = true;
 	blk_queue_write_cache(q, vwc, vwc);
@@ -3628,7 +3668,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	memcpy(disk->disk_name, disk_name, DISK_NAME_LEN);
 	ns->disk = disk;
 
-	__nvme_revalidate_disk(disk, id);
+	if (__nvme_revalidate_disk(disk, id))
+		goto out_free_disk;
 
 	if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
 		ret = nvme_nvm_register(ns, disk_name, node);
@@ -3655,6 +3696,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	/* prevent double queue cleanup */
 	ns->disk->queue = NULL;
 	put_disk(ns->disk);
+ out_free_disk:
+	del_gendisk(ns->disk);
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
 	list_del_rcu(&ns->siblings);

drivers/nvme/host/fc.c

@@ -108,7 +108,7 @@ struct nvme_fc_fcp_op {
 struct nvme_fcp_op_w_sgl {
 	struct nvme_fc_fcp_op	op;
 	struct scatterlist	sgl[NVME_INLINE_SG_CNT];
-	uint8_t			priv[0];
+	uint8_t			priv[];
 };
 
 struct nvme_fc_lport {
@@ -3246,7 +3246,9 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
 			dev_warn(ctrl->ctrl.device,
 				"NVME-FC{%d}: dev_loss_tmo (%d) expired "
 				"while waiting for remoteport connectivity.\n",
-				ctrl->cnum, portptr->dev_loss_tmo);
+				ctrl->cnum, min_t(int, portptr->dev_loss_tmo,
+					(ctrl->ctrl.opts->max_reconnects *
+					 ctrl->ctrl.opts->reconnect_delay)));
 		WARN_ON(nvme_delete_ctrl(&ctrl->ctrl));
 	}
 }

drivers/nvme/host/lightnvm.c

@@ -171,7 +171,7 @@ struct nvme_nvm_bb_tbl {
 	__le32	tdresv;
 	__le32	thresv;
 	__le32	rsvd2[8];
-	__u8	blk[0];
+	__u8	blk[];
 };
 
 struct nvme_nvm_id20_addrf {
@@ -961,7 +961,10 @@ int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node)
 	geo = &dev->geo;
 	geo->csecs = 1 << ns->lba_shift;
 	geo->sos = ns->ms;
-	geo->ext = ns->ext;
+	if (ns->features & NVME_NS_EXT_LBAS)
+		geo->ext = true;
+	else
+		geo->ext = false;
 	geo->mdts = ns->ctrl->max_hw_sectors;
 
 	dev->q = q;

drivers/nvme/host/nvme.h

@@ -16,6 +16,7 @@
 #include <linux/fault-inject.h>
 #include <linux/rcupdate.h>
 #include <linux/wait.h>
+#include <linux/t10-pi.h>
 
 #include <trace/events/block.h>
 
@@ -30,8 +31,10 @@ extern unsigned int admin_timeout;
 
 #ifdef CONFIG_ARCH_NO_SG_CHAIN
 #define  NVME_INLINE_SG_CNT  0
+#define  NVME_INLINE_METADATA_SG_CNT  0
 #else
 #define  NVME_INLINE_SG_CNT  2
+#define  NVME_INLINE_METADATA_SG_CNT  1
 #endif
 
 extern struct workqueue_struct *nvme_wq;
@@ -228,6 +231,7 @@ struct nvme_ctrl {
 	u32 page_size;
 	u32 max_hw_sectors;
 	u32 max_segments;
+	u32 max_integrity_segments;
 	u16 crdt[3];
 	u16 oncs;
 	u16 oacs;
@@ -364,6 +368,11 @@ struct nvme_ns_head {
 #endif
 };
 
+enum nvme_ns_features {
+	NVME_NS_EXT_LBAS = 1 << 0, /* support extended LBA format */
+	NVME_NS_METADATA_SUPPORTED = 1 << 1, /* support getting generated md */
+};
+
 struct nvme_ns {
 	struct list_head list;
 
@@ -383,8 +392,8 @@ struct nvme_ns {
 	u16 ms;
 	u16 sgs;
 	u32 sws;
-	bool ext;
 	u8 pi_type;
+	unsigned long features;
 	unsigned long flags;
 #define NVME_NS_REMOVING	0
 #define NVME_NS_DEAD     	1
@@ -394,6 +403,12 @@ struct nvme_ns {
 
 };
 
+/* NVMe ns supports metadata actions by the controller (generate/strip) */
+static inline bool nvme_ns_has_pi(struct nvme_ns *ns)
+{
+	return ns->pi_type && ns->ms == sizeof(struct t10_pi_tuple);
+}
+
 struct nvme_ctrl_ops {
 	const char *name;
 	struct module *module;
@@ -497,7 +512,6 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 void nvme_uninit_ctrl(struct nvme_ctrl *ctrl);
 void nvme_start_ctrl(struct nvme_ctrl *ctrl);
 void nvme_stop_ctrl(struct nvme_ctrl *ctrl);
-void nvme_put_ctrl(struct nvme_ctrl *ctrl);
 int nvme_init_identify(struct nvme_ctrl *ctrl);
 
 void nvme_remove_namespaces(struct nvme_ctrl *ctrl);