ublk: followup fixes for SHMEM_ZC

Documentation/block/ublk.rst

@@ -382,17 +382,17 @@ Zero copy
 ---------
 
 ublk zero copy relies on io_uring's fixed kernel buffer, which provides
-two APIs: `io_buffer_register_bvec()` and `io_buffer_unregister_bvec`.
+two APIs: `io_buffer_register_request()` and `io_buffer_unregister`.
 
 ublk adds IO command of `UBLK_IO_REGISTER_IO_BUF` to call
-`io_buffer_register_bvec()` for ublk server to register client request
+`io_buffer_register_request()` for ublk server to register client request
 buffer into io_uring buffer table, then ublk server can submit io_uring
 IOs with the registered buffer index. IO command of `UBLK_IO_UNREGISTER_IO_BUF`
-calls `io_buffer_unregister_bvec()` to unregister the buffer, which is
-guaranteed to be live between calling `io_buffer_register_bvec()` and
-`io_buffer_unregister_bvec()`. Any io_uring operation which supports this
-kind of kernel buffer will grab one reference of the buffer until the
-operation is completed.
+calls `io_buffer_unregister()` to unregister the buffer, which is guaranteed
+to be live between calling `io_buffer_register_request()` and
+`io_buffer_unregister()`. Any io_uring operation which supports this kind of
+kernel buffer will grab one reference of the buffer until the operation is
+completed.
 
 ublk server implementing zero copy or user copy has to be CAP_SYS_ADMIN and
 be trusted, because it is ublk server's responsibility to make sure IO buffer

drivers/block/ublk_drv.c

@@ -1690,8 +1690,8 @@ ublk_auto_buf_register(const struct ublk_queue *ubq, struct request *req,
 {
 	int ret;
 
-	ret = io_buffer_register_bvec(cmd, req, ublk_io_release,
-				      io->buf.auto_reg.index, issue_flags);
+	ret = io_buffer_register_request(cmd, req, ublk_io_release,
+					 io->buf.auto_reg.index, issue_flags);
 	if (ret) {
 		if (io->buf.auto_reg.flags & UBLK_AUTO_BUF_REG_FALLBACK) {
 			ublk_auto_buf_reg_fallback(ubq, req->tag);
@@ -1897,7 +1897,7 @@ static noinline void ublk_batch_dispatch_fail(struct ublk_queue *ubq,
 		ublk_io_unlock(io);
 
 		if (index != -1)
-			io_buffer_unregister_bvec(data->cmd, index,
+			io_buffer_unregister(data->cmd, index,
 					data->issue_flags);
 	}
 
@@ -3171,8 +3171,8 @@ static int ublk_register_io_buf(struct io_uring_cmd *cmd,
 	if (!req)
 		return -EINVAL;
 
-	ret = io_buffer_register_bvec(cmd, req, ublk_io_release, index,
-				      issue_flags);
+	ret = io_buffer_register_request(cmd, req, ublk_io_release, index,
+					 issue_flags);
 	if (ret) {
 		ublk_put_req_ref(io, req);
 		return ret;
@@ -3203,8 +3203,8 @@ ublk_daemon_register_io_buf(struct io_uring_cmd *cmd,
 	if (!ublk_dev_support_zero_copy(ub) || !ublk_rq_has_data(req))
 		return -EINVAL;
 
-	ret = io_buffer_register_bvec(cmd, req, ublk_io_release, index,
-				      issue_flags);
+	ret = io_buffer_register_request(cmd, req, ublk_io_release, index,
+					 issue_flags);
 	if (ret)
 		return ret;
 
@@ -3219,7 +3219,7 @@ static int ublk_unregister_io_buf(struct io_uring_cmd *cmd,
 	if (!(ub->dev_info.flags & UBLK_F_SUPPORT_ZERO_COPY))
 		return -EINVAL;
 
-	return io_buffer_unregister_bvec(cmd, index, issue_flags);
+	return io_buffer_unregister(cmd, index, issue_flags);
 }
 
 static int ublk_check_fetch_buf(const struct ublk_device *ub, __u64 buf_addr)
@@ -3360,7 +3360,7 @@ static int ublk_ch_uring_cmd_local(struct io_uring_cmd *cmd,
 		goto out;
 
 	/*
-	 * io_buffer_unregister_bvec() doesn't access the ubq or io,
+	 * io_buffer_unregister() doesn't access the ubq or io,
 	 * so no need to validate the q_id, tag, or task
 	 */
 	if (_IOC_NR(cmd_op) == UBLK_IO_UNREGISTER_IO_BUF)
@@ -3427,7 +3427,7 @@ static int ublk_ch_uring_cmd_local(struct io_uring_cmd *cmd,
 		req = ublk_fill_io_cmd(io, cmd);
 		ret = ublk_config_io_buf(ub, io, cmd, addr, &buf_idx);
 		if (buf_idx != UBLK_INVALID_BUF_IDX)
-			io_buffer_unregister_bvec(cmd, buf_idx, issue_flags);
+			io_buffer_unregister(cmd, buf_idx, issue_flags);
 		compl = ublk_need_complete_req(ub, io);
 
 		if (req_op(req) == REQ_OP_ZONE_APPEND)
@@ -3762,7 +3762,7 @@ static int ublk_batch_commit_io(struct ublk_queue *ubq,
 	}
 
 	if (buf_idx != UBLK_INVALID_BUF_IDX)
-		io_buffer_unregister_bvec(data->cmd, buf_idx, data->issue_flags);
+		io_buffer_unregister(data->cmd, buf_idx, data->issue_flags);
 	if (req_op(req) == REQ_OP_ZONE_APPEND)
 		req->__sector = ublk_batch_zone_lba(uc, elem);
 	if (compl)

include/linux/io_uring/cmd.h

@@ -91,6 +91,15 @@ struct io_br_sel io_uring_cmd_buffer_select(struct io_uring_cmd *ioucmd,
 bool io_uring_mshot_cmd_post_cqe(struct io_uring_cmd *ioucmd,
 				 struct io_br_sel *sel, unsigned int issue_flags);
 
+int io_buffer_register_request(struct io_uring_cmd *cmd, struct request *rq,
+			       void (*release)(void *), unsigned int index,
+			       unsigned int issue_flags);
+int io_buffer_register_bvec(struct io_uring_cmd *cmd, const struct bio_vec *bvs,
+			    unsigned int nr_bvecs, void (*release)(void *),
+			    void *priv, u8 dir, unsigned int index,
+			    unsigned int issue_flags);
+int io_buffer_unregister(struct io_uring_cmd *cmd, unsigned int index,
+			 unsigned int issue_flags);
 #else
 static inline int
 io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
@@ -133,6 +142,29 @@ static inline bool io_uring_mshot_cmd_post_cqe(struct io_uring_cmd *ioucmd,
 {
 	return true;
 }
+static inline int io_buffer_register_request(struct io_uring_cmd *cmd,
+					     struct request *rq,
+					     void (*release)(void *),
+					     unsigned int index,
+					     unsigned int issue_flags)
+{
+	return -EOPNOTSUPP;
+}
+static inline int io_buffer_register_bvec(struct io_uring_cmd *cmd,
+					  const struct bio_vec *bvs,
+					  unsigned int nr_bvecs,
+					  void (*release)(void *), void *priv,
+					  u8 dir, unsigned int index,
+					  unsigned int issue_flags)
+{
+	return -EOPNOTSUPP;
+}
+static inline int io_buffer_unregister(struct io_uring_cmd *cmd,
+				       unsigned int index,
+				       unsigned int issue_flags)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 static inline struct io_uring_cmd *io_uring_cmd_from_tw(struct io_tw_req tw_req)
@@ -182,10 +214,4 @@ static inline void io_uring_cmd_done32(struct io_uring_cmd *ioucmd, s32 ret,
 	return __io_uring_cmd_done(ioucmd, ret, res2, issue_flags, true);
 }
 
-int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq,
-			    void (*release)(void *), unsigned int index,
-			    unsigned int issue_flags);
-int io_buffer_unregister_bvec(struct io_uring_cmd *cmd, unsigned int index,
-			      unsigned int issue_flags);
-
 #endif /* _LINUX_IO_URING_CMD_H */

include/linux/io_uring_types.h

@@ -44,6 +44,11 @@ enum io_uring_cmd_flags {
 	IO_URING_F_COMPAT		= (1 << 12),
 };
 
+enum {
+	IO_BUF_DEST	= 1 << ITER_DEST,
+	IO_BUF_SOURCE	= 1 << ITER_SOURCE,
+};
+
 struct iou_loop_params;
 
 struct io_wq_work_node {

io_uring/io_uring.c

@@ -3233,7 +3233,7 @@ static int __init io_uring_init(void)
 	io_uring_optable_init();
 
 	/* imu->dir is u8 */
-	BUILD_BUG_ON((IO_IMU_DEST | IO_IMU_SOURCE) > U8_MAX);
+	BUILD_BUG_ON((IO_BUF_DEST | IO_BUF_SOURCE) > U8_MAX);
 
 	/*
 	 * Allow user copy in the per-command field, which starts after the

io_uring/poll.c

@@ -93,7 +93,7 @@ static bool io_poll_get_ownership_slowpath(struct io_kiocb *req)
  */
 static inline bool io_poll_get_ownership(struct io_kiocb *req)
 {
-	if (unlikely(atomic_read(&req->poll_refs) >= IO_POLL_REF_BIAS))
+	if (unlikely((unsigned int)atomic_read(&req->poll_refs) >= IO_POLL_REF_BIAS))
 		return io_poll_get_ownership_slowpath(req);
 	return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK);
 }

io_uring/rsrc.c

@@ -820,7 +820,7 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx,
 	imu->release = io_release_ubuf;
 	imu->priv = imu;
 	imu->flags = 0;
-	imu->dir = IO_IMU_DEST | IO_IMU_SOURCE;
+	imu->dir = IO_BUF_DEST | IO_BUF_SOURCE;
 	if (coalesced)
 		imu->folio_shift = data.folio_shift;
 	refcount_set(&imu->refs, 1);
@@ -924,72 +924,125 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
 	return ret;
 }
 
-int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq,
-			    void (*release)(void *), unsigned int index,
-			    unsigned int issue_flags)
+static struct io_mapped_ubuf *io_kernel_buffer_init(struct io_ring_ctx *ctx,
+						    unsigned int nr_bvecs,
+						    unsigned int total_bytes,
+						    u8 dir,
+						    void (*release)(void *),
+						    void *priv,
+						    unsigned int index)
 {
-	struct io_ring_ctx *ctx = cmd_to_io_kiocb(cmd)->ctx;
 	struct io_rsrc_data *data = &ctx->buf_table;
-	struct req_iterator rq_iter;
 	struct io_mapped_ubuf *imu;
 	struct io_rsrc_node *node;
-	struct bio_vec bv;
-	unsigned int nr_bvecs = 0;
-	int ret = 0;
 
-	io_ring_submit_lock(ctx, issue_flags);
-	if (index >= data->nr) {
-		ret = -EINVAL;
-		goto unlock;
-	}
+	if (index >= data->nr)
+		return ERR_PTR(-EINVAL);
 	index = array_index_nospec(index, data->nr);
 
-	if (data->nodes[index]) {
-		ret = -EBUSY;
-		goto unlock;
-	}
+	if (data->nodes[index])
+		return ERR_PTR(-EBUSY);
 
 	node = io_rsrc_node_alloc(ctx, IORING_RSRC_BUFFER);
-	if (!node) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	if (!node)
+		return ERR_PTR(-ENOMEM);
 
-	/*
-	 * blk_rq_nr_phys_segments() may overestimate the number of bvecs
-	 * but avoids needing to iterate over the bvecs
-	 */
-	imu = io_alloc_imu(ctx, blk_rq_nr_phys_segments(rq));
+	imu = io_alloc_imu(ctx, nr_bvecs);
 	if (!imu) {
 		io_cache_free(&ctx->node_cache, node);
-		ret = -ENOMEM;
-		goto unlock;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	imu->ubuf = 0;
-	imu->len = blk_rq_bytes(rq);
+	imu->len = total_bytes;
 	imu->acct_pages = 0;
 	imu->folio_shift = PAGE_SHIFT;
+	imu->nr_bvecs = nr_bvecs;
 	refcount_set(&imu->refs, 1);
 	imu->release = release;
-	imu->priv = rq;
+	imu->priv = priv;
+	imu->dir = dir;
 	imu->flags = IO_REGBUF_F_KBUF;
-	imu->dir = 1 << rq_data_dir(rq);
 
+	node->buf = imu;
+	data->nodes[index] = node;
+
+	return imu;
+}
+
+int io_buffer_register_request(struct io_uring_cmd *cmd, struct request *rq,
+			       void (*release)(void *), unsigned int index,
+			       unsigned int issue_flags)
+{
+	struct io_ring_ctx *ctx = cmd_to_io_kiocb(cmd)->ctx;
+	struct req_iterator rq_iter;
+	struct io_mapped_ubuf *imu;
+	struct bio_vec bv;
+	/*
+	 * blk_rq_nr_phys_segments() may overestimate the number of bvecs
+	 * but avoids needing to iterate over the bvecs
+	 */
+	unsigned int nr_bvecs = blk_rq_nr_phys_segments(rq);
+	unsigned int total_bytes = blk_rq_bytes(rq);
+	int ret = 0;
+
+	io_ring_submit_lock(ctx, issue_flags);
+
+	imu = io_kernel_buffer_init(ctx, nr_bvecs, total_bytes,
+				    1 << rq_data_dir(rq), release, rq, index);
+	if (IS_ERR(imu)) {
+		ret = PTR_ERR(imu);
+		goto unlock;
+	}
+
+	nr_bvecs = 0;
 	rq_for_each_bvec(bv, rq, rq_iter)
 		imu->bvec[nr_bvecs++] = bv;
 	imu->nr_bvecs = nr_bvecs;
 
-	node->buf = imu;
-	data->nodes[index] = node;
+unlock:
+	io_ring_submit_unlock(ctx, issue_flags);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(io_buffer_register_request);
+
+/*
+ * bvs is copied internally. caller may free it on return.
+ */
+int io_buffer_register_bvec(struct io_uring_cmd *cmd, const struct bio_vec *bvs,
+			    unsigned int nr_bvecs, void (*release)(void *),
+			    void *priv, u8 dir, unsigned int index,
+			    unsigned int issue_flags)
+{
+	struct io_ring_ctx *ctx = cmd_to_io_kiocb(cmd)->ctx;
+	struct io_mapped_ubuf *imu;
+	struct bio_vec *bvec;
+	unsigned int i, total_bytes = 0;
+	int ret = 0;
+
+	for (i = 0; i < nr_bvecs; i++)
+		total_bytes += bvs[i].bv_len;
+
+	io_ring_submit_lock(ctx, issue_flags);
+	imu = io_kernel_buffer_init(ctx, nr_bvecs, total_bytes, dir, release,
+				    priv, index);
+	if (IS_ERR(imu)) {
+		ret = PTR_ERR(imu);
+		goto unlock;
+	}
+
+	bvec = imu->bvec;
+	for (i = 0; i < nr_bvecs; i++)
+		bvec[i] = bvs[i];
+
 unlock:
 	io_ring_submit_unlock(ctx, issue_flags);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(io_buffer_register_bvec);
 
-int io_buffer_unregister_bvec(struct io_uring_cmd *cmd, unsigned int index,
-			      unsigned int issue_flags)
+int io_buffer_unregister(struct io_uring_cmd *cmd, unsigned int index,
+			 unsigned int issue_flags)
 {
 	struct io_ring_ctx *ctx = cmd_to_io_kiocb(cmd)->ctx;
 	struct io_rsrc_data *data = &ctx->buf_table;
@@ -1019,7 +1072,7 @@ int io_buffer_unregister_bvec(struct io_uring_cmd *cmd, unsigned int index,
 	io_ring_submit_unlock(ctx, issue_flags);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(io_buffer_unregister_bvec);
+EXPORT_SYMBOL_GPL(io_buffer_unregister);
 
 static int validate_fixed_range(u64 buf_addr, size_t len,
 				const struct io_mapped_ubuf *imu)

io_uring/rsrc.h

@@ -23,11 +23,6 @@ struct io_rsrc_node {
 	};
 };
 
-enum {
-	IO_IMU_DEST	= 1 << ITER_DEST,
-	IO_IMU_SOURCE	= 1 << ITER_SOURCE,
-};
-
 enum {
 	IO_REGBUF_F_KBUF		= 1,
 };

io_uring/tctx.c

@@ -171,7 +171,10 @@ int __io_uring_add_tctx_node(struct io_ring_ctx *ctx)
 	}
 	if (!current->io_uring) {
 err_free:
-		io_wq_put_and_exit(tctx->io_wq);
+		if (tctx->io_wq) {
+			io_wq_exit_start(tctx->io_wq);
+			io_wq_put_and_exit(tctx->io_wq);
+		}
 		percpu_counter_destroy(&tctx->inflight);
 		kfree(tctx);
 	}