Merge tag 'vfs-6.17-rc1.integrity' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs 'protection info' updates from Christian Brauner:
 "This adds the new FS_IOC_GETLBMD_CAP ioctl() to query metadata and
  protection info (PI) capabilities. This ioctl returns information
  about the files integrity profile. This is useful for userspace
  applications to understand a files end-to-end data protection support
  and configure the I/O accordingly.

  For now this interface is only supported by block devices. However the
  design and placement of this ioctl in generic FS ioctl space allows us
  to extend it to work over files as well. This maybe useful when
  filesystems start supporting PI-aware layouts.

  A new structure struct logical_block_metadata_cap is introduced, which
  contains the following fields:

   - lbmd_flags:
     bitmask of logical block metadata capability flags

   - lbmd_interval:
     the amount of data described by each unit of logical block metadata

   - lbmd_size:
     size in bytes of the logical block metadata associated with each
     interval

   - lbmd_opaque_size:
     size in bytes of the opaque block tag associated with each interval

   - lbmd_opaque_offset:
     offset in bytes of the opaque block tag within the logical block
     metadata

   - lbmd_pi_size:
     size in bytes of the T10 PI tuple associated with each interval

   - lbmd_pi_offset:
     offset in bytes of T10 PI tuple within the logical block metadata

   - lbmd_pi_guard_tag_type:
     T10 PI guard tag type

   - lbmd_pi_app_tag_size:
     size in bytes of the T10 PI application tag

   - lbmd_pi_ref_tag_size:
     size in bytes of the T10 PI reference tag

   - lbmd_pi_storage_tag_size:
     size in bytes of the T10 PI storage tag

  The internal logic to fetch the capability is encapsulated in a helper
  function blk_get_meta_cap(), which uses the blk_integrity profile
  associated with the device. The ioctl returns -EOPNOTSUPP, if
  CONFIG_BLK_DEV_INTEGRITY is not enabled"

* tag 'vfs-6.17-rc1.integrity' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  block: fix lbmd_guard_tag_type assignment in FS_IOC_GETLBMD_CAP
  block: fix FS_IOC_GETLBMD_CAP parsing in blkdev_common_ioctl()
  fs: add ioctl to query metadata and protection info capabilities
  nvme: set pi_offset only when checksum type is not BLK_INTEGRITY_CSUM_NONE
  block: introduce pi_tuple_size field in blk_integrity
  block: rename tuple_size field in blk_integrity to metadata_size

5 files changed, 122 insertions, 15 deletions

diff --git a/block/bio-integrity-auto.c b/block/bio-integrity-auto.c
index 9c6657664792..687952f63bbb 100644
--- a/block/bio-integrity-auto.c
+++ b/block/bio-integrity-auto.c
@@ -54,10 +54,10 @@ static bool bi_offload_capable(struct blk_integrity *bi)
 {
 	switch (bi->csum_type) {
 	case BLK_INTEGRITY_CSUM_CRC64:
-		return bi->tuple_size == sizeof(struct crc64_pi_tuple);
+		return bi->metadata_size == sizeof(struct crc64_pi_tuple);
 	case BLK_INTEGRITY_CSUM_CRC:
 	case BLK_INTEGRITY_CSUM_IP:
-		return bi->tuple_size == sizeof(struct t10_pi_tuple);
+		return bi->metadata_size == sizeof(struct t10_pi_tuple);
 	default:
 		pr_warn_once("%s: unknown integrity checksum type:%d\n",
 			__func__, bi->csum_type);
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index e4e2567061f9..056b8948369d 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -13,6 +13,7 @@
 #include <linux/scatterlist.h>
 #include <linux/export.h>
 #include <linux/slab.h>
+#include <linux/t10-pi.h>
 
 #include "blk.h"
 
@@ -54,6 +55,73 @@ new_segment:
 	return segments;
 }
 
+int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd,
+		     struct logical_block_metadata_cap __user *argp)
+{
+	struct blk_integrity *bi = blk_get_integrity(bdev->bd_disk);
+	struct logical_block_metadata_cap meta_cap = {};
+	size_t usize = _IOC_SIZE(cmd);
+
+	if (_IOC_DIR(cmd)  != _IOC_DIR(FS_IOC_GETLBMD_CAP) ||
+	    _IOC_TYPE(cmd) != _IOC_TYPE(FS_IOC_GETLBMD_CAP) ||
+	    _IOC_NR(cmd)   != _IOC_NR(FS_IOC_GETLBMD_CAP) ||
+	    _IOC_SIZE(cmd) < LBMD_SIZE_VER0)
+		return -ENOIOCTLCMD;
+
+	if (!bi)
+		goto out;
+
+	if (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE)
+		meta_cap.lbmd_flags |= LBMD_PI_CAP_INTEGRITY;
+	if (bi->flags & BLK_INTEGRITY_REF_TAG)
+		meta_cap.lbmd_flags |= LBMD_PI_CAP_REFTAG;
+	meta_cap.lbmd_interval = 1 << bi->interval_exp;
+	meta_cap.lbmd_size = bi->metadata_size;
+	meta_cap.lbmd_pi_size = bi->pi_tuple_size;
+	meta_cap.lbmd_pi_offset = bi->pi_offset;
+	meta_cap.lbmd_opaque_size = bi->metadata_size - bi->pi_tuple_size;
+	if (meta_cap.lbmd_opaque_size && !bi->pi_offset)
+		meta_cap.lbmd_opaque_offset = bi->pi_tuple_size;
+
+	switch (bi->csum_type) {
+	case BLK_INTEGRITY_CSUM_NONE:
+		meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_NONE;
+		break;
+	case BLK_INTEGRITY_CSUM_IP:
+		meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_IP;
+		break;
+	case BLK_INTEGRITY_CSUM_CRC:
+		meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_CRC16_T10DIF;
+		break;
+	case BLK_INTEGRITY_CSUM_CRC64:
+		meta_cap.lbmd_guard_tag_type = LBMD_PI_CSUM_CRC64_NVME;
+		break;
+	}
+
+	if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE)
+		meta_cap.lbmd_app_tag_size = 2;
+
+	if (bi->flags & BLK_INTEGRITY_REF_TAG) {
+		switch (bi->csum_type) {
+		case BLK_INTEGRITY_CSUM_CRC64:
+			meta_cap.lbmd_ref_tag_size =
+				sizeof_field(struct crc64_pi_tuple, ref_tag);
+			break;
+		case BLK_INTEGRITY_CSUM_CRC:
+		case BLK_INTEGRITY_CSUM_IP:
+			meta_cap.lbmd_ref_tag_size =
+				sizeof_field(struct t10_pi_tuple, ref_tag);
+			break;
+		default:
+			break;
+		}
+	}
+
+out:
+	return copy_struct_to_user(argp, usize, &meta_cap, sizeof(meta_cap),
+				   NULL);
+}
+
 /**
  * blk_rq_map_integrity_sg - Map integrity metadata into a scatterlist
  * @rq:		request to map
@@ -239,7 +307,7 @@ static ssize_t format_show(struct device *dev, struct device_attribute *attr,
 {
 	struct blk_integrity *bi = dev_to_bi(dev);
 
-	if (!bi->tuple_size)
+	if (!bi->metadata_size)
 		return sysfs_emit(page, "none\n");
 	return sysfs_emit(page, "%s\n", blk_integrity_profile_name(bi));
 }
diff --git a/block/blk-settings.c b/block/blk-settings.c
index b5c75f0ac3e9..e0cc7a1fe4ac 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -14,6 +14,8 @@
 #include <linux/jiffies.h>
 #include <linux/gfp.h>
 #include <linux/dma-mapping.h>
+#include <linux/t10-pi.h>
+#include <linux/crc64.h>
 
 #include "blk.h"
 #include "blk-rq-qos.h"
@@ -116,7 +118,7 @@ static int blk_validate_integrity_limits(struct queue_limits *lim)
 {
 	struct blk_integrity *bi = &lim->integrity;
 
-	if (!bi->tuple_size) {
+	if (!bi->metadata_size) {
 		if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE ||
 		    bi->tag_size || ((bi->flags & BLK_INTEGRITY_REF_TAG))) {
 			pr_warn("invalid PI settings.\n");
@@ -137,6 +139,42 @@ static int blk_validate_integrity_limits(struct queue_limits *lim)
 		return -EINVAL;
 	}
 
+	if (bi->pi_tuple_size > bi->metadata_size) {
+		pr_warn("pi_tuple_size (%u) exceeds metadata_size (%u)\n",
+			 bi->pi_tuple_size,
+			 bi->metadata_size);
+		return -EINVAL;
+	}
+
+	switch (bi->csum_type) {
+	case BLK_INTEGRITY_CSUM_NONE:
+		if (bi->pi_tuple_size) {
+			pr_warn("pi_tuple_size must be 0 when checksum type \
+				 is none\n");
+			return -EINVAL;
+		}
+		break;
+	case BLK_INTEGRITY_CSUM_CRC:
+	case BLK_INTEGRITY_CSUM_IP:
+		if (bi->pi_tuple_size != sizeof(struct t10_pi_tuple)) {
+			pr_warn("pi_tuple_size mismatch for T10 PI: expected \
+				 %zu, got %u\n",
+				 sizeof(struct t10_pi_tuple),
+				 bi->pi_tuple_size);
+			return -EINVAL;
+		}
+		break;
+	case BLK_INTEGRITY_CSUM_CRC64:
+		if (bi->pi_tuple_size != sizeof(struct crc64_pi_tuple)) {
+			pr_warn("pi_tuple_size mismatch for CRC64 PI: \
+				 expected %zu, got %u\n",
+				 sizeof(struct crc64_pi_tuple),
+				 bi->pi_tuple_size);
+			return -EINVAL;
+		}
+		break;
+	}
+
 	if (!bi->interval_exp)
 		bi->interval_exp = ilog2(lim->logical_block_size);
 
@@ -891,7 +929,7 @@ bool queue_limits_stack_integrity(struct queue_limits *t,
 		return true;
 
 	if (ti->flags & BLK_INTEGRITY_STACKED) {
-		if (ti->tuple_size != bi->tuple_size)
+		if (ti->metadata_size != bi->metadata_size)
 			goto incompatible;
 		if (ti->interval_exp != bi->interval_exp)
 			goto incompatible;
@@ -907,7 +945,7 @@ bool queue_limits_stack_integrity(struct queue_limits *t,
 		ti->flags |= (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) |
 			     (bi->flags & BLK_INTEGRITY_REF_TAG);
 		ti->csum_type = bi->csum_type;
-		ti->tuple_size = bi->tuple_size;
+		ti->metadata_size = bi->metadata_size;
 		ti->pi_offset = bi->pi_offset;
 		ti->interval_exp = bi->interval_exp;
 		ti->tag_size = bi->tag_size;
diff --git a/block/ioctl.c b/block/ioctl.c
index e472cc1030c6..f7b0006ca45d 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -13,6 +13,7 @@
 #include <linux/uaccess.h>
 #include <linux/pagemap.h>
 #include <linux/io_uring/cmd.h>
+#include <linux/blk-integrity.h>
 #include <uapi/linux/blkdev.h>
 #include "blk.h"
 #include "blk-crypto-internal.h"
@@ -644,7 +645,7 @@ static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode,
 	case IOC_PR_CLEAR:
 		return blkdev_pr_clear(bdev, mode, argp);
 	default:
-		return -ENOIOCTLCMD;
+		return blk_get_meta_cap(bdev, cmd, argp);
 	}
 }
 
diff --git a/block/t10-pi.c b/block/t10-pi.c
index 851db518ee5e..0c4ed9702146 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -56,7 +56,7 @@ static void t10_pi_generate(struct blk_integrity_iter *iter,
 			pi->ref_tag = 0;
 
 		iter->data_buf += iter->interval;
-		iter->prot_buf += bi->tuple_size;
+		iter->prot_buf += bi->metadata_size;
 		iter->seed++;
 	}
 }
@@ -105,7 +105,7 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 
 next:
 		iter->data_buf += iter->interval;
-		iter->prot_buf += bi->tuple_size;
+		iter->prot_buf += bi->metadata_size;
 		iter->seed++;
 	}
 
@@ -125,7 +125,7 @@ next:
 static void t10_pi_type1_prepare(struct request *rq)
 {
 	struct blk_integrity *bi = &rq->q->limits.integrity;
-	const int tuple_sz = bi->tuple_size;
+	const int tuple_sz = bi->metadata_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
 	struct bio *bio;
@@ -177,7 +177,7 @@ static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
 	struct blk_integrity *bi = &rq->q->limits.integrity;
 	unsigned intervals = nr_bytes >> bi->interval_exp;
-	const int tuple_sz = bi->tuple_size;
+	const int tuple_sz = bi->metadata_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
 	struct bio *bio;
@@ -234,7 +234,7 @@ static void ext_pi_crc64_generate(struct blk_integrity_iter *iter,
 			put_unaligned_be48(0ULL, pi->ref_tag);
 
 		iter->data_buf += iter->interval;
-		iter->prot_buf += bi->tuple_size;
+		iter->prot_buf += bi->metadata_size;
 		iter->seed++;
 	}
 }
@@ -289,7 +289,7 @@ static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
 
 next:
 		iter->data_buf += iter->interval;
-		iter->prot_buf += bi->tuple_size;
+		iter->prot_buf += bi->metadata_size;
 		iter->seed++;
 	}
 
@@ -299,7 +299,7 @@ next:
 static void ext_pi_type1_prepare(struct request *rq)
 {
 	struct blk_integrity *bi = &rq->q->limits.integrity;
-	const int tuple_sz = bi->tuple_size;
+	const int tuple_sz = bi->metadata_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
 	struct bio *bio;
@@ -340,7 +340,7 @@ static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
 	struct blk_integrity *bi = &rq->q->limits.integrity;
 	unsigned intervals = nr_bytes >> bi->interval_exp;
-	const int tuple_sz = bi->tuple_size;
+	const int tuple_sz = bi->metadata_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
 	struct bio *bio;