[PATCH v2 20/20] scsi: target: Add block PR support to iblock.

[Mike Christie <michael.christie@oracle.com>]

This adds support for the block PR callouts to target_core_iblock. This
patch doesn't attempt to implement the entire spec because there's no way
support it all like SPEC_I_PT and ALL_TG_PT. This only supports
exporting the iblock device from one path on the local target.

Signed-off-by: Mike Christie <michael.christie@oracle.com>
---
 drivers/target/target_core_iblock.c | 292 +++++++++++++++++++++++++++-
 1 file changed, 287 insertions(+), 5 deletions(-)

diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 5db7318b4822..caf6958dd75d 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -23,13 +23,16 @@
 #include <linux/file.h>
 #include <linux/module.h>
 #include <linux/scatterlist.h>
+#include <linux/pr.h>
 #include <scsi/scsi_proto.h>
+#include <scsi/scsi_block_pr.h>
 #include <asm/unaligned.h>
 
 #include <target/target_core_base.h>
 #include <target/target_core_backend.h>
 
 #include "target_core_iblock.h"
+#include "target_core_pr.h"
 
 #define IBLOCK_MAX_BIO_PER_TASK	 32	/* max # of bios to submit at a time */
 #define IBLOCK_BIO_POOL_SIZE	128
@@ -310,7 +313,7 @@ static unsigned long long iblock_emulate_read_cap_with_block_size(
 	return blocks_long;
 }
 
-static void iblock_complete_cmd(struct se_cmd *cmd)
+static void iblock_complete_cmd(struct se_cmd *cmd, blk_status_t blk_status)
 {
 	struct iblock_req *ibr = cmd->priv;
 	u8 status;
@@ -318,7 +321,9 @@ static void iblock_complete_cmd(struct se_cmd *cmd)
 	if (!refcount_dec_and_test(&ibr->pending))
 		return;
 
-	if (atomic_read(&ibr->ib_bio_err_cnt))
+	if (blk_status == BLK_STS_NEXUS)
+		status = SAM_STAT_RESERVATION_CONFLICT;
+	else if (atomic_read(&ibr->ib_bio_err_cnt))
 		status = SAM_STAT_CHECK_CONDITION;
 	else
 		status = SAM_STAT_GOOD;
@@ -331,6 +336,7 @@ static void iblock_bio_done(struct bio *bio)
 {
 	struct se_cmd *cmd = bio->bi_private;
 	struct iblock_req *ibr = cmd->priv;
+	blk_status_t blk_status = bio->bi_status;
 
 	if (bio->bi_status) {
 		pr_err("bio error: %p,  err: %d\n", bio, bio->bi_status);
@@ -343,7 +349,7 @@ static void iblock_bio_done(struct bio *bio)
 
 	bio_put(bio);
 
-	iblock_complete_cmd(cmd);
+	iblock_complete_cmd(cmd, blk_status);
 }
 
 static struct bio *iblock_get_bio(struct se_cmd *cmd, sector_t lba, u32 sg_num,
@@ -759,7 +765,7 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 
 	if (!sgl_nents) {
 		refcount_set(&ibr->pending, 1);
-		iblock_complete_cmd(cmd);
+		iblock_complete_cmd(cmd, BLK_STS_OK);
 		return 0;
 	}
 
@@ -817,7 +823,7 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	}
 
 	iblock_submit_bios(&list);
-	iblock_complete_cmd(cmd);
+	iblock_complete_cmd(cmd, BLK_STS_OK);
 	return 0;
 
 fail_put_bios:
@@ -829,6 +835,279 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 }
 
+static sense_reason_t iblock_execute_pr_out(struct se_cmd *cmd, u8 sa, u64 key,
+					    u64 sa_key, u8 type, bool aptpl,
+					    bool all_tg_pt, bool spec_i_pt)
+{
+	struct se_device *dev = cmd->se_dev;
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+	struct block_device *bdev = ib_dev->ibd_bd;
+	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+	blk_status_t blk_stat = 0;
+	int ret;
+
+	if (!ops) {
+		pr_err("Block device does not support pr_ops but iblock device has been configured for PR passthrough.\n");
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
+	}
+
+	switch (sa) {
+	case PRO_REGISTER_AND_MOVE:
+		pr_err("PRO_REGISTER_AND_MOVE is not supported by iblock PR passthrough.\n");
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
+	case PRO_REPLACE_LOST_RESERVATION:
+		pr_err("PRO_REPLACE_LOST_RESERVATION is not supported by iblock PR passthrough.\n");
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
+	case PRO_REGISTER:
+	case PRO_REGISTER_AND_IGNORE_EXISTING_KEY:
+		if (!ops->pr_register) {
+			pr_err("block device does not support pr_register.\n");
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
+		}
+
+		/*
+		 * We only support one target port. We don't know the target
+		 * port config at this level and the block layer has a
+		 * different view.
+		 */
+		if (spec_i_pt || all_tg_pt) {
+			pr_err("SPC-3 PR: SPEC_I_PT and ALL_TG_PT are not supported by PR passthrough.\n");
+
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
+		}
+
+		/* The block layer pr ops always enables aptpl */
+		if (!aptpl)
+			pr_info("APTPL not set by initiator, but will be used.\n");
+
+		ret = ops->pr_register(bdev, key, sa_key,
+				sa == PRO_REGISTER ? 0 : PR_FL_IGNORE_KEY,
+				&blk_stat);
+		break;
+	case PRO_RESERVE:
+		if (!ops->pr_reserve) {
+			pr_err("block_device does not support pr_reserve.\n");
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
+		}
+
+		ret = ops->pr_reserve(bdev, key, scsi_pr_type_to_block(type), 0,
+				      &blk_stat);
+		break;
+	case PRO_CLEAR:
+		if (!ops->pr_clear) {
+			pr_err("block_device does not support pr_clear.\n");
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
+		}
+
+		ret = ops->pr_clear(bdev, key, &blk_stat);
+		break;
+	case PRO_PREEMPT:
+	case PRO_PREEMPT_AND_ABORT:
+		if (!ops->pr_clear) {
+			pr_err("block_device does not support pr_preempt.\n");
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
+		}
+
+		ret = ops->pr_preempt(bdev, key, sa_key,
+				      scsi_pr_type_to_block(type),
+				      sa == PRO_PREEMPT ? false : true,
+				      &blk_stat);
+		break;
+	case PRO_RELEASE:
+		if (!ops->pr_clear) {
+			pr_err("block_device does not support pr_pclear.\n");
+			return TCM_UNSUPPORTED_SCSI_OPCODE;
+		}
+
+		ret = ops->pr_release(bdev, key, scsi_pr_type_to_block(type),
+				      &blk_stat);
+		break;
+	default:
+		pr_err("Unknown PERSISTENT_RESERVE_OUT SA: 0x%02x\n", sa);
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
+	}
+
+	if (!ret)
+		return TCM_NO_SENSE;
+	else if (blk_stat == BLK_STS_NEXUS)
+		return TCM_RESERVATION_CONFLICT;
+	else
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+}
+
+static void iblock_pr_report_caps(unsigned char *param_data)
+{
+	u16 len = 8;
+
+	put_unaligned_be16(len, &param_data[0]);
+	/*
+	 * When using the pr_ops passthrough method we only support exporting
+	 * the device through one target port because from the backend module
+	 * level we can't see the target port config. As a result we only
+	 * support registration directly from the I_T nexus the cmd is sent
+	 * through and do not set ATP_C here.
+	 *
+	 * The block layer pr_ops do not support passing in initiators so
+	 * we don't set SIP_C here.
+	 */
+	/* PTPL_C: Persistence across Target Power Loss bit */
+	param_data[2] |= 0x01;
+	/*
+	 * We are filling in the PERSISTENT RESERVATION TYPE MASK below, so
+	 * set the TMV: Task Mask Valid bit.
+	 */
+	param_data[3] |= 0x80;
+	/*
+	 * Change ALLOW COMMANDs to 0x20 or 0x40 later from Table 166
+	 */
+	param_data[3] |= 0x10; /* ALLOW COMMANDs field 001b */
+	/*
+	 * PTPL_A: Persistence across Target Power Loss Active bit. The block
+	 * layer pr ops always enables this so report it active.
+	 */
+	param_data[3] |= 0x01;
+	/*
+	 * Setup the PERSISTENT RESERVATION TYPE MASK from Table 212 spc4r37.
+	 */
+	param_data[4] |= 0x80; /* PR_TYPE_EXCLUSIVE_ACCESS_ALLREG */
+	param_data[4] |= 0x40; /* PR_TYPE_EXCLUSIVE_ACCESS_REGONLY */
+	param_data[4] |= 0x20; /* PR_TYPE_WRITE_EXCLUSIVE_REGONLY */
+	param_data[4] |= 0x08; /* PR_TYPE_EXCLUSIVE_ACCESS */
+	param_data[4] |= 0x02; /* PR_TYPE_WRITE_EXCLUSIVE */
+	param_data[5] |= 0x01; /* PR_TYPE_EXCLUSIVE_ACCESS_ALLREG */
+}
+
+static int iblock_pr_read_keys(struct se_cmd *cmd, unsigned char *param_data)
+{
+	struct se_device *dev = cmd->se_dev;
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+	struct block_device *bdev = ib_dev->ibd_bd;
+	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+	int i, ret, len, paths, data_offset;
+	struct pr_keys *keys;
+
+	if (!ops) {
+		pr_err("Block device does not support pr_ops but iblock device has been configured for PR passthrough.\n");
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
+	}
+
+	if (!ops->pr_read_keys) {
+		pr_err("Block device does not support read_keys.\n");
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
+	}
+
+	/*
+	 * We don't know what's under us, but dm-multipath will register every
+	 * path with the same key, so start off with enough space for 16 paths.
+	 */
+	paths = 16;
+retry:
+	len = 8 * paths;
+	keys = kzalloc(sizeof(*keys) + len, GFP_KERNEL);
+	if (!keys)
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
+	ret = ops->pr_read_keys(bdev, keys, len, NULL);
+	if (!ret) {
+		if (keys->num_keys > paths) {
+			kfree(keys);
+			paths *= 2;
+			goto retry;
+		}
+	} else if (ret) {
+		ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+		goto free_keys;
+	}
+
+	ret = TCM_NO_SENSE;
+
+	put_unaligned_be32(keys->generation, &param_data[0]);
+	if (!keys->num_keys) {
+		put_unaligned_be32(0, &param_data[4]);
+		goto free_keys;
+	}
+
+	put_unaligned_be32(8 * keys->num_keys, &param_data[4]);
+
+	data_offset = 8;
+	for (i = 0; i < keys->num_keys; i++) {
+		if (data_offset + 8 > cmd->data_length)
+			break;
+
+		put_unaligned_be64(keys->keys[i], &param_data[data_offset]);
+		data_offset += 8;
+	}
+
+free_keys:
+	kfree(keys);
+	return ret;
+}
+
+static int iblock_pr_read_reservation(struct se_cmd *cmd,
+				      unsigned char *param_data)
+{
+	struct se_device *dev = cmd->se_dev;
+	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+	struct block_device *bdev = ib_dev->ibd_bd;
+	const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops;
+	struct pr_held_reservation rsv;
+
+	if (!ops) {
+		pr_err("Block device does not support pr_ops but iblock device has been configured for PR passthrough.\n");
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
+	}
+
+	if (!ops->pr_read_reservation) {
+		pr_err("Block device does not support read_keys.\n");
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
+	}
+
+	if (ops->pr_read_reservation(bdev, &rsv, NULL))
+		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+
+	put_unaligned_be32(rsv.generation, &param_data[0]);
+	if (!block_pr_type_to_scsi(rsv.type)) {
+		put_unaligned_be32(0, &param_data[4]);
+		return TCM_NO_SENSE;
+	}
+
+	put_unaligned_be32(16, &param_data[4]);
+
+	if (cmd->data_length < 16)
+		return TCM_NO_SENSE;
+	put_unaligned_be64(rsv.key, &param_data[8]);
+
+	if (cmd->data_length < 22)
+		return TCM_NO_SENSE;
+	param_data[21] = block_pr_type_to_scsi(rsv.type);
+
+	return TCM_NO_SENSE;
+}
+
+static sense_reason_t iblock_execute_pr_in(struct se_cmd *cmd, u8 sa,
+					   unsigned char *param_data)
+{
+	sense_reason_t ret = TCM_NO_SENSE;
+
+	switch (sa) {
+	case PRI_REPORT_CAPABILITIES:
+		iblock_pr_report_caps(param_data);
+		break;
+	case PRI_READ_KEYS:
+		ret = iblock_pr_read_keys(cmd, param_data);
+		break;
+	case PRI_READ_RESERVATION:
+		ret = iblock_pr_read_reservation(cmd, param_data);
+		break;
+	case PRI_READ_FULL_STATUS:
+	default:
+		pr_err("Unknown PERSISTENT_RESERVE_IN SA: 0x%02x\n", sa);
+		return TCM_UNSUPPORTED_SCSI_OPCODE;
+	}
+
+	return ret;
+}
+
 static sector_t iblock_get_blocks(struct se_device *dev)
 {
 	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
@@ -883,6 +1162,8 @@ static struct exec_cmd_ops iblock_exec_cmd_ops = {
 	.execute_sync_cache	= iblock_execute_sync_cache,
 	.execute_write_same	= iblock_execute_write_same,
 	.execute_unmap		= iblock_execute_unmap,
+	.execute_pr_out		= iblock_execute_pr_out,
+	.execute_pr_in		= iblock_execute_pr_in,
 };
 
 static sense_reason_t
@@ -899,6 +1180,7 @@ static bool iblock_get_write_cache(struct se_device *dev)
 static const struct target_backend_ops iblock_ops = {
 	.name			= "iblock",
 	.inquiry_prod		= "IBLOCK",
+	.transport_flags_changeable = TRANSPORT_FLAG_PASSTHROUGH_PGR,
 	.inquiry_rev		= IBLOCK_VERSION,
 	.owner			= THIS_MODULE,
 	.attach_hba		= iblock_attach_hba,
-- 
2.18.2