Merge patch series "Use block pr_ops in LIO"

Mike Christie <michael.christie@oracle.com> says:

The patches in this thread allow us to use the block pr_ops with LIO's
target_core_iblock module to support cluster applications in VMs. They
were built over Linus's tree. They also apply over linux-next and
Martin's tree and Jens's trees.

Currently, to use windows clustering or linux clustering (pacemaker +
cluster labs scsi fence agents) in VMs with LIO and vhost-scsi, you
have to use tcmu or pscsi or use a cluster aware FS/framework for the
LIO pr file. Setting up a cluster FS/framework is pain and waste when
your real backend device is already a distributed device, and pscsi
and tcmu are nice for specific use cases, but iblock gives you the
best performance and allows you to use stacked devices like
dm-multipath. So these patches allow iblock to work like pscsi/tcmu
where they can pass a PR command to the backend module. And then
iblock will use the pr_ops to pass the PR command to the real devices
similar to what we do for unmap today.

The patches are separated in the following groups:

Patch 1 - 2:

 - Add block layer callouts for reading reservations and rename reservation
   error code.

Patch 3 - 5:

 - SCSI support for new callouts.

Patch 6:

 - DM support for new callouts.

Patch 7 - 13:

 - NVMe support for new callouts.

Patch 14 - 18:

 - LIO support for new callouts.

This patchset has been tested with the libiscsi PGR ops and with
window's failover cluster verification test. Note that for scsi
backend devices we need this patchset:

https://lore.kernel.org/linux-scsi/20230123221046.125483-1-michael.christie@oracle.com/T/#m4834a643ffb5bac2529d65d40906d3cfbdd9b1b7

to handle UAs. To reduce the size of this patchset that's being done
separately to make reviewing easier. And to make merging easier this
patchset and the one above do not have any conflicts so can be merged
in different trees.

Link: https://lore.kernel.org/r/20230407200551.12660-1-michael.christie@oracle.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

3 files changed, 70 insertions, 10 deletions

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 740afe80f297..936e898016f8 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -101,7 +101,7 @@ typedef u16 blk_short_t;
 #define BLK_STS_NOSPC		((__force blk_status_t)3)
 #define BLK_STS_TRANSPORT	((__force blk_status_t)4)
 #define BLK_STS_TARGET		((__force blk_status_t)5)
-#define BLK_STS_NEXUS		((__force blk_status_t)6)
+#define BLK_STS_RESV_CONFLICT	((__force blk_status_t)6)
 #define BLK_STS_MEDIUM		((__force blk_status_t)7)
 #define BLK_STS_PROTECTION	((__force blk_status_t)8)
 #define BLK_STS_RESOURCE	((__force blk_status_t)9)
@@ -189,7 +189,7 @@ static inline bool blk_path_error(blk_status_t error)
 	case BLK_STS_NOTSUPP:
 	case BLK_STS_NOSPC:
 	case BLK_STS_TARGET:
-	case BLK_STS_NEXUS:
+	case BLK_STS_RESV_CONFLICT:
 	case BLK_STS_MEDIUM:
 	case BLK_STS_PROTECTION:
 		return false;
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 779507ac750b..182b6d614eb1 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -759,20 +759,55 @@ enum {
 	NVME_LBART_ATTRIB_HIDE	= 1 << 1,
 };
 
+enum nvme_pr_type {
+	NVME_PR_WRITE_EXCLUSIVE			= 1,
+	NVME_PR_EXCLUSIVE_ACCESS		= 2,
+	NVME_PR_WRITE_EXCLUSIVE_REG_ONLY	= 3,
+	NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY	= 4,
+	NVME_PR_WRITE_EXCLUSIVE_ALL_REGS	= 5,
+	NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS	= 6,
+};
+
+enum nvme_eds {
+	NVME_EXTENDED_DATA_STRUCT	= 0x1,
+};
+
+struct nvme_registered_ctrl {
+	__le16	cntlid;
+	__u8	rcsts;
+	__u8	rsvd3[5];
+	__le64	hostid;
+	__le64	rkey;
+};
+
 struct nvme_reservation_status {
 	__le32	gen;
 	__u8	rtype;
 	__u8	regctl[2];
 	__u8	resv5[2];
 	__u8	ptpls;
-	__u8	resv10[13];
-	struct {
-		__le16	cntlid;
-		__u8	rcsts;
-		__u8	resv3[5];
-		__le64	hostid;
-		__le64	rkey;
-	} regctl_ds[];
+	__u8	resv10[14];
+	struct nvme_registered_ctrl regctl_ds[];
+};
+
+struct nvme_registered_ctrl_ext {
+	__le16	cntlid;
+	__u8	rcsts;
+	__u8	rsvd3[5];
+	__le64	rkey;
+	__u8	hostid[16];
+	__u8	rsvd32[32];
+};
+
+struct nvme_reservation_status_ext {
+	__le32	gen;
+	__u8	rtype;
+	__u8	regctl[2];
+	__u8	resv5[2];
+	__u8	ptpls;
+	__u8	resv10[14];
+	__u8	rsvd24[40];
+	struct nvme_registered_ctrl_ext regctl_eds[];
 };
 
 enum nvme_async_event_type {
diff --git a/include/linux/pr.h b/include/linux/pr.h
index 94ceec713afe..3003daec28a5 100644
--- a/include/linux/pr.h
+++ b/include/linux/pr.h
@@ -4,6 +4,18 @@
 
 #include <uapi/linux/pr.h>
 
+struct pr_keys {
+	u32	generation;
+	u32	num_keys;
+	u64	keys[];
+};
+
+struct pr_held_reservation {
+	u64		key;
+	u32		generation;
+	enum pr_type	type;
+};
+
 struct pr_ops {
 	int (*pr_register)(struct block_device *bdev, u64 old_key, u64 new_key,
 			u32 flags);
@@ -14,6 +26,19 @@ struct pr_ops {
 	int (*pr_preempt)(struct block_device *bdev, u64 old_key, u64 new_key,
 			enum pr_type type, bool abort);
 	int (*pr_clear)(struct block_device *bdev, u64 key);
+	/*
+	 * pr_read_keys - Read the registered keys and return them in the
+	 * pr_keys->keys array. The keys array will have been allocated at the
+	 * end of the pr_keys struct, and pr_keys->num_keys must be set to the
+	 * number of keys the array can hold. If there are more than can fit
+	 * in the array, success will still be returned and pr_keys->num_keys
+	 * will reflect the total number of keys the device contains, so the
+	 * caller can retry with a larger array.
+	 */
+	int (*pr_read_keys)(struct block_device *bdev,
+			struct pr_keys *keys_info);
+	int (*pr_read_reservation)(struct block_device *bdev,
+			struct pr_held_reservation *rsv);
 };
 
 #endif /* LINUX_PR_H */