block: add pi for extended integrity

The NVMe specification defines new data integrity formats beyond the
t10 tuple. Add support for the specification defined CRC64 formats,
assuming the reference tag does not need to be split with the "storage
tag".

Cc: Hannes Reinecke <hare@suse.de>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20220303201312.3255347-8-kbusch@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/Kconfig b/block/Kconfig
index 7eb5d6d53b3fc51c9d977d9536c54c1731aa9fbd..50b17e260fa26d54a77c7315576c6810fb4ad707 100644 (file)
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -73,6 +73,7 @@ config BLK_DEV_INTEGRITY_T10
        tristate
        depends on BLK_DEV_INTEGRITY
        select CRC_T10DIF
+       select CRC64_ROCKSOFT
 
 config BLK_DEV_ZONED
        bool "Zoned block device support"

diff --git a/block/t10-pi.c b/block/t10-pi.c
index 758a7651885462ba700fb2ad9b5cb3d1a87a2f94..914d8cddd43a92ebc65c02c0b92d7e7825cdc3d0 100644 (file)
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -7,8 +7,10 @@
 #include <linux/t10-pi.h>
 #include <linux/blk-integrity.h>
 #include <linux/crc-t10dif.h>
+#include <linux/crc64.h>
 #include <linux/module.h>
 #include <net/checksum.h>
+#include <asm/unaligned.h>
 
 typedef __be16 (csum_fn) (void *, unsigned int);
 
@@ -278,4 +280,196 @@ const struct blk_integrity_profile t10_pi_type3_ip = {
 };
 EXPORT_SYMBOL(t10_pi_type3_ip);
 
+static __be64 ext_pi_crc64(void *data, unsigned int len)
+{
+       return cpu_to_be64(crc64_rocksoft(data, len));
+}
+
+static blk_status_t ext_pi_crc64_generate(struct blk_integrity_iter *iter,
+                                       enum t10_dif_type type)
+{
+       unsigned int i;
+
+       for (i = 0 ; i < iter->data_size ; i += iter->interval) {
+               struct crc64_pi_tuple *pi = iter->prot_buf;
+
+               pi->guard_tag = ext_pi_crc64(iter->data_buf, iter->interval);
+               pi->app_tag = 0;
+
+               if (type == T10_PI_TYPE1_PROTECTION)
+                       put_unaligned_be48(iter->seed, pi->ref_tag);
+               else
+                       put_unaligned_be48(0ULL, pi->ref_tag);
+
+               iter->data_buf += iter->interval;
+               iter->prot_buf += iter->tuple_size;
+               iter->seed++;
+       }
+
+       return BLK_STS_OK;
+}
+
+static bool ext_pi_ref_escape(u8 *ref_tag)
+{
+       static u8 ref_escape[6] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+
+       return memcmp(ref_tag, ref_escape, sizeof(ref_escape)) == 0;
+}
+
+static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
+                                     enum t10_dif_type type)
+{
+       unsigned int i;
+
+       for (i = 0; i < iter->data_size; i += iter->interval) {
+               struct crc64_pi_tuple *pi = iter->prot_buf;
+               u64 ref, seed;
+               __be64 csum;
+
+               if (type == T10_PI_TYPE1_PROTECTION) {
+                       if (pi->app_tag == T10_PI_APP_ESCAPE)
+                               goto next;
+
+                       ref = get_unaligned_be48(pi->ref_tag);
+                       seed = lower_48_bits(iter->seed);
+                       if (ref != seed) {
+                               pr_err("%s: ref tag error at location %llu (rcvd %llu)\n",
+                                       iter->disk_name, seed, ref);
+                               return BLK_STS_PROTECTION;
+                       }
+               } else if (type == T10_PI_TYPE3_PROTECTION) {
+                       if (pi->app_tag == T10_PI_APP_ESCAPE &&
+                           ext_pi_ref_escape(pi->ref_tag))
+                               goto next;
+               }
+
+               csum = ext_pi_crc64(iter->data_buf, iter->interval);
+               if (pi->guard_tag != csum) {
+                       pr_err("%s: guard tag error at sector %llu " \
+                              "(rcvd %016llx, want %016llx)\n",
+                               iter->disk_name, (unsigned long long)iter->seed,
+                               be64_to_cpu(pi->guard_tag), be64_to_cpu(csum));
+                       return BLK_STS_PROTECTION;
+               }
+
+next:
+               iter->data_buf += iter->interval;
+               iter->prot_buf += iter->tuple_size;
+               iter->seed++;
+       }
+
+       return BLK_STS_OK;
+}
+
+static blk_status_t ext_pi_type1_verify_crc64(struct blk_integrity_iter *iter)
+{
+       return ext_pi_crc64_verify(iter, T10_PI_TYPE1_PROTECTION);
+}
+
+static blk_status_t ext_pi_type1_generate_crc64(struct blk_integrity_iter *iter)
+{
+       return ext_pi_crc64_generate(iter, T10_PI_TYPE1_PROTECTION);
+}
+
+static void ext_pi_type1_prepare(struct request *rq)
+{
+       const int tuple_sz = rq->q->integrity.tuple_size;
+       u64 ref_tag = ext_pi_ref_tag(rq);
+       struct bio *bio;
+
+       __rq_for_each_bio(bio, rq) {
+               struct bio_integrity_payload *bip = bio_integrity(bio);
+               u64 virt = lower_48_bits(bip_get_seed(bip));
+               struct bio_vec iv;
+               struct bvec_iter iter;
+
+               /* Already remapped? */
+               if (bip->bip_flags & BIP_MAPPED_INTEGRITY)
+                       break;
+
+               bip_for_each_vec(iv, bip, iter) {
+                       unsigned int j;
+                       void *p;
+
+                       p = bvec_kmap_local(&iv);
+                       for (j = 0; j < iv.bv_len; j += tuple_sz) {
+                               struct crc64_pi_tuple *pi = p;
+                               u64 ref = get_unaligned_be48(pi->ref_tag);
+
+                               if (ref == virt)
+                                       put_unaligned_be48(ref_tag, pi->ref_tag);
+                               virt++;
+                               ref_tag++;
+                               p += tuple_sz;
+                       }
+                       kunmap_local(p);
+               }
+
+               bip->bip_flags |= BIP_MAPPED_INTEGRITY;
+       }
+}
+
+static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
+{
+       unsigned intervals = nr_bytes >> rq->q->integrity.interval_exp;
+       const int tuple_sz = rq->q->integrity.tuple_size;
+       u64 ref_tag = ext_pi_ref_tag(rq);
+       struct bio *bio;
+
+       __rq_for_each_bio(bio, rq) {
+               struct bio_integrity_payload *bip = bio_integrity(bio);
+               u64 virt = lower_48_bits(bip_get_seed(bip));
+               struct bio_vec iv;
+               struct bvec_iter iter;
+
+               bip_for_each_vec(iv, bip, iter) {
+                       unsigned int j;
+                       void *p;
+
+                       p = bvec_kmap_local(&iv);
+                       for (j = 0; j < iv.bv_len && intervals; j += tuple_sz) {
+                               struct crc64_pi_tuple *pi = p;
+                               u64 ref = get_unaligned_be48(pi->ref_tag);
+
+                               if (ref == ref_tag)
+                                       put_unaligned_be48(virt, pi->ref_tag);
+                               virt++;
+                               ref_tag++;
+                               intervals--;
+                               p += tuple_sz;
+                       }
+                       kunmap_local(p);
+               }
+       }
+}
+
+static blk_status_t ext_pi_type3_verify_crc64(struct blk_integrity_iter *iter)
+{
+       return ext_pi_crc64_verify(iter, T10_PI_TYPE3_PROTECTION);
+}
+
+static blk_status_t ext_pi_type3_generate_crc64(struct blk_integrity_iter *iter)
+{
+       return ext_pi_crc64_generate(iter, T10_PI_TYPE3_PROTECTION);
+}
+
+const struct blk_integrity_profile ext_pi_type1_crc64 = {
+       .name                   = "EXT-DIF-TYPE1-CRC64",
+       .generate_fn            = ext_pi_type1_generate_crc64,
+       .verify_fn              = ext_pi_type1_verify_crc64,
+       .prepare_fn             = ext_pi_type1_prepare,
+       .complete_fn            = ext_pi_type1_complete,
+};
+EXPORT_SYMBOL_GPL(ext_pi_type1_crc64);
+
+const struct blk_integrity_profile ext_pi_type3_crc64 = {
+       .name                   = "EXT-DIF-TYPE3-CRC64",
+       .generate_fn            = ext_pi_type3_generate_crc64,
+       .verify_fn              = ext_pi_type3_verify_crc64,
+       .prepare_fn             = t10_pi_type3_prepare,
+       .complete_fn            = t10_pi_type3_complete,
+};
+EXPORT_SYMBOL_GPL(ext_pi_type3_crc64);
+
+MODULE_LICENSE("GPL");
 MODULE_LICENSE("GPL");

diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h
index c635c2e014e3d4e6ca81fde407531eb552cd094e..a4b1af581f69ec055fbc0828765fad10bfd62a8e 100644 (file)
--- a/include/linux/t10-pi.h
+++ b/include/linux/t10-pi.h
@@ -53,4 +53,24 @@ extern const struct blk_integrity_profile t10_pi_type1_ip;
 extern const struct blk_integrity_profile t10_pi_type3_crc;
 extern const struct blk_integrity_profile t10_pi_type3_ip;
 
+struct crc64_pi_tuple {
+       __be64 guard_tag;
+       __be16 app_tag;
+       __u8   ref_tag[6];
+};
+
+static inline u64 ext_pi_ref_tag(struct request *rq)
+{
+       unsigned int shift = ilog2(queue_logical_block_size(rq->q));
+
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+       if (rq->q->integrity.interval_exp)
+               shift = rq->q->integrity.interval_exp;
+#endif
+       return lower_48_bits(blk_rq_pos(rq) >> (shift - SECTOR_SHIFT));
+}
+
+extern const struct blk_integrity_profile ext_pi_type1_crc64;
+extern const struct blk_integrity_profile ext_pi_type3_crc64;
+
 #endif