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>

1 files changed, 102 insertions, 28 deletions

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 1624d528aa1f..5247abe4f266 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -67,6 +67,7 @@
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_ioctl.h>
 #include <scsi/scsicam.h>
+#include <scsi/scsi_common.h>
 
 #include "sd.h"
 #include "scsi_priv.h"
@@ -1691,26 +1692,6 @@ out_unlock:
 	return ret;
 }
 
-static char sd_pr_type(enum pr_type type)
-{
-	switch (type) {
-	case PR_WRITE_EXCLUSIVE:
-		return 0x01;
-	case PR_EXCLUSIVE_ACCESS:
-		return 0x03;
-	case PR_WRITE_EXCLUSIVE_REG_ONLY:
-		return 0x05;
-	case PR_EXCLUSIVE_ACCESS_REG_ONLY:
-		return 0x06;
-	case PR_WRITE_EXCLUSIVE_ALL_REGS:
-		return 0x07;
-	case PR_EXCLUSIVE_ACCESS_ALL_REGS:
-		return 0x08;
-	default:
-		return 0;
-	}
-};
-
 static int sd_scsi_to_pr_err(struct scsi_sense_hdr *sshdr, int result)
 {
 	switch (host_byte(result)) {
@@ -1741,8 +1722,97 @@ static int sd_scsi_to_pr_err(struct scsi_sense_hdr *sshdr, int result)
 	}
 }
 
-static int sd_pr_command(struct block_device *bdev, u8 sa,
-		u64 key, u64 sa_key, u8 type, u8 flags)
+static int sd_pr_in_command(struct block_device *bdev, u8 sa,
+			    unsigned char *data, int data_len)
+{
+	struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk);
+	struct scsi_device *sdev = sdkp->device;
+	struct scsi_sense_hdr sshdr;
+	u8 cmd[10] = { PERSISTENT_RESERVE_IN, sa };
+	const struct scsi_exec_args exec_args = {
+		.sshdr = &sshdr,
+	};
+	int result;
+
+	put_unaligned_be16(data_len, &cmd[7]);
+
+	result = scsi_execute_cmd(sdev, cmd, REQ_OP_DRV_IN, data, data_len,
+				  SD_TIMEOUT, sdkp->max_retries, &exec_args);
+	if (scsi_status_is_check_condition(result) &&
+	    scsi_sense_valid(&sshdr)) {
+		sdev_printk(KERN_INFO, sdev, "PR command failed: %d\n", result);
+		scsi_print_sense_hdr(sdev, NULL, &sshdr);
+	}
+
+	if (result <= 0)
+		return result;
+
+	return sd_scsi_to_pr_err(&sshdr, result);
+}
+
+static int sd_pr_read_keys(struct block_device *bdev, struct pr_keys *keys_info)
+{
+	int result, i, data_offset, num_copy_keys;
+	u32 num_keys = keys_info->num_keys;
+	int data_len = num_keys * 8 + 8;
+	u8 *data;
+
+	data = kzalloc(data_len, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	result = sd_pr_in_command(bdev, READ_KEYS, data, data_len);
+	if (result)
+		goto free_data;
+
+	keys_info->generation = get_unaligned_be32(&data[0]);
+	keys_info->num_keys = get_unaligned_be32(&data[4]) / 8;
+
+	data_offset = 8;
+	num_copy_keys = min(num_keys, keys_info->num_keys);
+
+	for (i = 0; i < num_copy_keys; i++) {
+		keys_info->keys[i] = get_unaligned_be64(&data[data_offset]);
+		data_offset += 8;
+	}
+
+free_data:
+	kfree(data);
+	return result;
+}
+
+static int sd_pr_read_reservation(struct block_device *bdev,
+				  struct pr_held_reservation *rsv)
+{
+	struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk);
+	struct scsi_device *sdev = sdkp->device;
+	u8 data[24] = { };
+	int result, len;
+
+	result = sd_pr_in_command(bdev, READ_RESERVATION, data, sizeof(data));
+	if (result)
+		return result;
+
+	len = get_unaligned_be32(&data[4]);
+	if (!len)
+		return 0;
+
+	/* Make sure we have at least the key and type */
+	if (len < 14) {
+		sdev_printk(KERN_INFO, sdev,
+			    "READ RESERVATION failed due to short return buffer of %d bytes\n",
+			    len);
+		return -EINVAL;
+	}
+
+	rsv->generation = get_unaligned_be32(&data[0]);
+	rsv->key = get_unaligned_be64(&data[8]);
+	rsv->type = scsi_pr_type_to_block(data[21] & 0x0f);
+	return 0;
+}
+
+static int sd_pr_out_command(struct block_device *bdev, u8 sa, u64 key,
+			     u64 sa_key, enum scsi_pr_type type, u8 flags)
 {
 	struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk);
 	struct scsi_device *sdev = sdkp->device;
@@ -1784,7 +1854,7 @@ static int sd_pr_register(struct block_device *bdev, u64 old_key, u64 new_key,
 {
 	if (flags & ~PR_FL_IGNORE_KEY)
 		return -EOPNOTSUPP;
-	return sd_pr_command(bdev, (flags & PR_FL_IGNORE_KEY) ? 0x06 : 0x00,
+	return sd_pr_out_command(bdev, (flags & PR_FL_IGNORE_KEY) ? 0x06 : 0x00,
 			old_key, new_key, 0,
 			(1 << 0) /* APTPL */);
 }
@@ -1794,24 +1864,26 @@ static int sd_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
 {
 	if (flags)
 		return -EOPNOTSUPP;
-	return sd_pr_command(bdev, 0x01, key, 0, sd_pr_type(type), 0);
+	return sd_pr_out_command(bdev, 0x01, key, 0,
+				 block_pr_type_to_scsi(type), 0);
 }
 
 static int sd_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
 {
-	return sd_pr_command(bdev, 0x02, key, 0, sd_pr_type(type), 0);
+	return sd_pr_out_command(bdev, 0x02, key, 0,
+				 block_pr_type_to_scsi(type), 0);
 }
 
 static int sd_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key,
 		enum pr_type type, bool abort)
 {
-	return sd_pr_command(bdev, abort ? 0x05 : 0x04, old_key, new_key,
-			     sd_pr_type(type), 0);
+	return sd_pr_out_command(bdev, abort ? 0x05 : 0x04, old_key, new_key,
+				 block_pr_type_to_scsi(type), 0);
 }
 
 static int sd_pr_clear(struct block_device *bdev, u64 key)
 {
-	return sd_pr_command(bdev, 0x03, key, 0, 0, 0);
+	return sd_pr_out_command(bdev, 0x03, key, 0, 0, 0);
 }
 
 static const struct pr_ops sd_pr_ops = {
@@ -1820,6 +1892,8 @@ static const struct pr_ops sd_pr_ops = {
 	.pr_release	= sd_pr_release,
 	.pr_preempt	= sd_pr_preempt,
 	.pr_clear	= sd_pr_clear,
+	.pr_read_keys	= sd_pr_read_keys,
+	.pr_read_reservation = sd_pr_read_reservation,
 };
 
 static void scsi_disk_free_disk(struct gendisk *disk)