ublk: add support for integrity data

include/linux/blk-integrity.h

@@ -91,7 +91,7 @@ static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
 	return bio_integrity_intervals(bi, sectors) * bi->metadata_size;
 }
 
-static inline bool blk_integrity_rq(struct request *rq)
+static inline bool blk_integrity_rq(const struct request *rq)
 {
 	return rq->cmd_flags & REQ_INTEGRITY;
 }
@@ -168,9 +168,9 @@ static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
 {
 	return 0;
 }
-static inline int blk_integrity_rq(struct request *rq)
+static inline bool blk_integrity_rq(const struct request *rq)
 {
-	return 0;
+	return false;
 }
 
 static inline struct bio_vec rq_integrity_vec(struct request *rq)

include/uapi/linux/ublk_cmd.h

@@ -134,6 +134,10 @@
 #define UBLKSRV_IO_BUF_TOTAL_BITS	(UBLK_QID_OFF + UBLK_QID_BITS)
 #define UBLKSRV_IO_BUF_TOTAL_SIZE	(1ULL << UBLKSRV_IO_BUF_TOTAL_BITS)
 
+/* Copy to/from request integrity buffer instead of data buffer */
+#define UBLK_INTEGRITY_FLAG_OFF 62
+#define UBLKSRV_IO_INTEGRITY_FLAG (1ULL << UBLK_INTEGRITY_FLAG_OFF)
+
 /*
  * ublk server can register data buffers for incoming I/O requests with a sparse
  * io_uring buffer table. The request buffer can then be used as the data buffer
@@ -311,6 +315,12 @@
  */
 #define UBLK_F_BUF_REG_OFF_DAEMON (1ULL << 14)
 
+/*
+ * ublk device supports requests with integrity/metadata buffer.
+ * Requires UBLK_F_USER_COPY.
+ */
+#define UBLK_F_INTEGRITY (1ULL << 16)
+
 /* device state */
 #define UBLK_S_DEV_DEAD	0
 #define UBLK_S_DEV_LIVE	1
@@ -408,6 +418,8 @@ struct ublksrv_ctrl_dev_info {
  * passed in.
  */
 #define		UBLK_IO_F_NEED_REG_BUF		(1U << 17)
+/* Request has an integrity data buffer */
+#define		UBLK_IO_F_INTEGRITY		(1UL << 18)
 
 /*
  * io cmd is described by this structure, and stored in share memory, indexed
@@ -600,6 +612,17 @@ struct ublk_param_segment {
 	__u8	pad[2];
 };
 
+struct ublk_param_integrity {
+	__u32	flags; /* LBMD_PI_CAP_* from linux/fs.h */
+	__u16	max_integrity_segments; /* 0 means no limit */
+	__u8	interval_exp;
+	__u8	metadata_size; /* UBLK_PARAM_TYPE_INTEGRITY requires nonzero */
+	__u8	pi_offset;
+	__u8	csum_type; /* LBMD_PI_CSUM_* from linux/fs.h */
+	__u8	tag_size;
+	__u8	pad[5];
+};
+
 struct ublk_params {
 	/*
 	 * Total length of parameters, userspace has to set 'len' for both
@@ -614,6 +637,7 @@ struct ublk_params {
 #define UBLK_PARAM_TYPE_ZONED           (1 << 3)
 #define UBLK_PARAM_TYPE_DMA_ALIGN       (1 << 4)
 #define UBLK_PARAM_TYPE_SEGMENT         (1 << 5)
+#define UBLK_PARAM_TYPE_INTEGRITY       (1 << 6) /* requires UBLK_F_INTEGRITY */
 	__u32	types;			/* types of parameter included */
 
 	struct ublk_param_basic		basic;
@@ -622,6 +646,7 @@ struct ublk_params {
 	struct ublk_param_zoned	zoned;
 	struct ublk_param_dma_align	dma;
 	struct ublk_param_segment	seg;
+	struct ublk_param_integrity	integrity;
 };
 
 #endif

tools/testing/selftests/ublk/Makefile

@@ -27,13 +27,15 @@ TEST_PROGS += test_generic_15.sh
 TEST_PROGS += test_null_01.sh
 TEST_PROGS += test_null_02.sh
 TEST_PROGS += test_null_03.sh
+TEST_PROGS += test_null_04.sh
 TEST_PROGS += test_loop_01.sh
 TEST_PROGS += test_loop_02.sh
 TEST_PROGS += test_loop_03.sh
 TEST_PROGS += test_loop_04.sh
 TEST_PROGS += test_loop_05.sh
 TEST_PROGS += test_loop_06.sh
 TEST_PROGS += test_loop_07.sh
+TEST_PROGS += test_loop_08.sh
 TEST_PROGS += test_stripe_01.sh
 TEST_PROGS += test_stripe_02.sh
 TEST_PROGS += test_stripe_03.sh
@@ -49,12 +51,13 @@ TEST_PROGS += test_stress_05.sh
 TEST_PROGS += test_stress_06.sh
 TEST_PROGS += test_stress_07.sh
 
-TEST_GEN_PROGS_EXTENDED = kublk
+TEST_GEN_PROGS_EXTENDED = kublk metadata_size
+STANDALONE_UTILS := metadata_size.c
 
 LOCAL_HDRS += $(wildcard *.h)
 include ../lib.mk
 
-$(TEST_GEN_PROGS_EXTENDED): $(wildcard *.c)
+$(OUTPUT)/kublk: $(filter-out $(STANDALONE_UTILS),$(wildcard *.c))
 
 check:
 	shellcheck -x -f gcc *.sh

tools/testing/selftests/ublk/common.c

@@ -12,7 +12,7 @@ void backing_file_tgt_deinit(struct ublk_dev *dev)
 	}
 }
 
-int backing_file_tgt_init(struct ublk_dev *dev)
+int backing_file_tgt_init(struct ublk_dev *dev, unsigned int nr_direct)
 {
 	int fd, i;
 
@@ -25,7 +25,7 @@ int backing_file_tgt_init(struct ublk_dev *dev)
 
 		ublk_dbg(UBLK_DBG_DEV, "%s: file %d: %s\n", __func__, i, file);
 
-		fd = open(file, O_RDWR | O_DIRECT);
+		fd = open(file, O_RDWR | (i < nr_direct ? O_DIRECT : 0));
 		if (fd < 0) {
 			ublk_err("%s: backing file %s can't be opened: %s\n",
 					__func__, file, strerror(errno));

tools/testing/selftests/ublk/fault_inject.c

@@ -33,6 +33,7 @@ static int ublk_fault_inject_tgt_init(const struct dev_ctx *ctx,
 			.dev_sectors		= dev_size >> 9,
 		},
 	};
+	ublk_set_integrity_params(ctx, &dev->tgt.params);
 
 	dev->private_data = (void *)(unsigned long)(ctx->fault_inject.delay_us * 1000);
 	return 0;

tools/testing/selftests/ublk/file_backed.c

@@ -35,24 +35,38 @@ static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q,
 	unsigned auto_zc = ublk_queue_use_auto_zc(q);
 	enum io_uring_op op = ublk_to_uring_op(iod, zc | auto_zc);
 	struct ublk_io *io = ublk_get_io(q, tag);
+	__u64 offset = iod->start_sector << 9;
+	__u32 len = iod->nr_sectors << 9;
 	struct io_uring_sqe *sqe[3];
 	void *addr = io->buf_addr;
 
+	if (iod->op_flags & UBLK_IO_F_INTEGRITY) {
+		ublk_io_alloc_sqes(t, sqe, 1);
+		/* Use second backing file for integrity data */
+		io_uring_prep_rw(op, sqe[0], ublk_get_registered_fd(q, 2),
+				 io->integrity_buf,
+				 ublk_integrity_len(q, len),
+				 ublk_integrity_len(q, offset));
+		sqe[0]->flags = IOSQE_FIXED_FILE;
+		/* tgt_data = 1 indicates integrity I/O */
+		sqe[0]->user_data = build_user_data(tag, ublk_op, 1, q->q_id, 1);
+	}
+
 	if (!zc || auto_zc) {
 		ublk_io_alloc_sqes(t, sqe, 1);
 		if (!sqe[0])
 			return -ENOMEM;
 
 		io_uring_prep_rw(op, sqe[0], ublk_get_registered_fd(q, 1) /*fds[1]*/,
 				addr,
-				iod->nr_sectors << 9,
-				iod->start_sector << 9);
+				len,
+				offset);
 		if (auto_zc)
 			sqe[0]->buf_index = tag;
 		io_uring_sqe_set_flags(sqe[0], IOSQE_FIXED_FILE);
 		/* bit63 marks us as tgt io */
 		sqe[0]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1);
-		return 1;
+		return !!(iod->op_flags & UBLK_IO_F_INTEGRITY) + 1;
 	}
 
 	ublk_io_alloc_sqes(t, sqe, 3);
@@ -63,16 +77,16 @@ static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q,
 			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
 
 	io_uring_prep_rw(op, sqe[1], ublk_get_registered_fd(q, 1) /*fds[1]*/, 0,
-		iod->nr_sectors << 9,
-		iod->start_sector << 9);
+			len,
+			offset);
 	sqe[1]->buf_index = tag;
 	sqe[1]->flags |= IOSQE_FIXED_FILE | IOSQE_IO_HARDLINK;
 	sqe[1]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1);
 
 	io_uring_prep_buf_unregister(sqe[2], q, tag, q->q_id, io->buf_index);
 	sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1);
 
-	return 2;
+	return !!(iod->op_flags & UBLK_IO_F_INTEGRITY) + 2;
 }
 
 static int loop_queue_tgt_io(struct ublk_thread *t, struct ublk_queue *q, int tag)
@@ -119,12 +133,17 @@ static void ublk_loop_io_done(struct ublk_thread *t, struct ublk_queue *q,
 	unsigned op = user_data_to_op(cqe->user_data);
 	struct ublk_io *io = ublk_get_io(q, tag);
 
-	if (cqe->res < 0 || op != ublk_cmd_op_nr(UBLK_U_IO_UNREGISTER_IO_BUF)) {
-		if (!io->result)
-			io->result = cqe->res;
-		if (cqe->res < 0)
-			ublk_err("%s: io failed op %x user_data %lx\n",
-					__func__, op, cqe->user_data);
+	if (cqe->res < 0) {
+		io->result = cqe->res;
+		ublk_err("%s: io failed op %x user_data %lx\n",
+				__func__, op, cqe->user_data);
+	} else if (op != ublk_cmd_op_nr(UBLK_U_IO_UNREGISTER_IO_BUF)) {
+		__s32 data_len = user_data_to_tgt_data(cqe->user_data)
+			? ublk_integrity_data_len(q, cqe->res)
+			: cqe->res;
+
+		if (!io->result || data_len < io->result)
+			io->result = data_len;
 	}
 
 	/* buffer register op is IOSQE_CQE_SKIP_SUCCESS */
@@ -135,9 +154,30 @@ static void ublk_loop_io_done(struct ublk_thread *t, struct ublk_queue *q,
 		ublk_complete_io(t, q, tag, io->result);
 }
 
+static int ublk_loop_memset_file(int fd, __u8 byte, size_t len)
+{
+	off_t offset = 0;
+	__u8 buf[4096];
+
+	memset(buf, byte, sizeof(buf));
+	while (len) {
+		int ret = pwrite(fd, buf, min(len, sizeof(buf)), offset);
+
+		if (ret < 0)
+			return -errno;
+		if (!ret)
+			return -EIO;
+
+		len -= ret;
+		offset += ret;
+	}
+	return 0;
+}
+
 static int ublk_loop_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
 {
 	unsigned long long bytes;
+	unsigned long blocks;
 	int ret;
 	struct ublk_params p = {
 		.types = UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DMA_ALIGN,
@@ -154,19 +194,39 @@ static int ublk_loop_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
 		},
 	};
 
+	ublk_set_integrity_params(ctx, &p);
 	if (ctx->auto_zc_fallback) {
 		ublk_err("%s: not support auto_zc_fallback\n", __func__);
 		return -EINVAL;
 	}
 
-	ret = backing_file_tgt_init(dev);
+	/* Use O_DIRECT only for data file */
+	ret = backing_file_tgt_init(dev, 1);
 	if (ret)
 		return ret;
 
-	if (dev->tgt.nr_backing_files != 1)
+	/* Expect a second file for integrity data */
+	if (dev->tgt.nr_backing_files != 1 + !!ctx->metadata_size)
 		return -EINVAL;
 
-	bytes = dev->tgt.backing_file_size[0];
+	blocks = dev->tgt.backing_file_size[0] >> p.basic.logical_bs_shift;
+	if (ctx->metadata_size) {
+		unsigned long metadata_blocks =
+			dev->tgt.backing_file_size[1] / ctx->metadata_size;
+		unsigned long integrity_len;
+
+		/* Ensure both data and integrity data fit in backing files */
+		blocks = min(blocks, metadata_blocks);
+		integrity_len = blocks * ctx->metadata_size;
+		/*
+		 * Initialize PI app tag and ref tag to 0xFF
+		 * to disable bio-integrity-auto checks
+		 */
+		ret = ublk_loop_memset_file(dev->fds[2], 0xFF, integrity_len);
+		if (ret)
+			return ret;
+	}
+	bytes = blocks << p.basic.logical_bs_shift;
 	dev->tgt.dev_size = bytes;
 	p.basic.dev_sectors = bytes >> 9;
 	dev->tgt.params = p;