[PATCH v6 2/5] io_uring: implement fixed buffers registration similar to fixed files

[Bijan Mottahedeh <bijan.mottahedeh@oracle.com>]

Apply fixed_rsrc functionality for fixed buffers support.

Signed-off-by: Bijan Mottahedeh <bijan.mottahedeh@oracle.com>
---
 fs/io_uring.c | 221 ++++++++++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 183 insertions(+), 38 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 416c350..2f02e11 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -104,6 +104,14 @@
 #define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
 				 IORING_REGISTER_LAST + IORING_OP_LAST)
 
+/*
+ * Shift of 7 is 128 entries, or exactly one page on 64-bit archs
+ */
+#define IORING_BUF_TABLE_SHIFT	7	/* struct io_mapped_ubuf */
+#define IORING_MAX_BUFS_TABLE	(1U << IORING_BUF_TABLE_SHIFT)
+#define IORING_BUF_TABLE_MASK	(IORING_MAX_BUFS_TABLE - 1)
+#define IORING_MAX_FIXED_BUFS	UIO_MAXIOV
+
 struct io_uring {
 	u32 head ____cacheline_aligned_in_smp;
 	u32 tail ____cacheline_aligned_in_smp;
@@ -202,11 +210,15 @@ struct io_rsrc_put {
 	union {
 		void *rsrc;
 		struct file *file;
+		struct io_mapped_ubuf *buf;
 	};
 };
 
 struct fixed_rsrc_table {
-	struct file		**files;
+	union {
+		struct file		**files;
+		struct io_mapped_ubuf	*bufs;
+	};
 };
 
 struct fixed_rsrc_ref_node {
@@ -333,8 +345,8 @@ struct io_ring_ctx {
 	unsigned		nr_user_files;
 
 	/* if used, fixed mapped user buffers */
+	struct fixed_rsrc_data	*buf_data;
 	unsigned		nr_user_bufs;
-	struct io_mapped_ubuf	*user_bufs;
 
 	struct user_struct	*user;
 
@@ -1015,6 +1027,8 @@ static struct fixed_rsrc_ref_node *alloc_fixed_rsrc_ref_node(
 			struct io_ring_ctx *ctx);
 static void init_fixed_file_ref_node(struct io_ring_ctx *ctx,
 				     struct fixed_rsrc_ref_node *ref_node);
+static void init_fixed_buf_ref_node(struct io_ring_ctx *ctx,
+				    struct fixed_rsrc_ref_node *ref_node);
 
 static void __io_complete_rw(struct io_kiocb *req, long res, long res2,
 			     struct io_comp_state *cs);
@@ -2988,6 +3002,15 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
 		io_rw_done(kiocb, ret);
 }
 
+static inline struct io_mapped_ubuf *io_buf_from_index(struct io_ring_ctx *ctx,
+						       int index)
+{
+	struct fixed_rsrc_table *table;
+
+	table = &ctx->buf_data->table[index >> IORING_BUF_TABLE_SHIFT];
+	return &table->bufs[index & IORING_BUF_TABLE_MASK];
+}
+
 static ssize_t io_import_fixed(struct io_kiocb *req, int rw,
 			       struct iov_iter *iter)
 {
@@ -3001,7 +3024,7 @@ static ssize_t io_import_fixed(struct io_kiocb *req, int rw,
 	if (unlikely(buf_index >= ctx->nr_user_bufs))
 		return -EFAULT;
 	index = array_index_nospec(buf_index, ctx->nr_user_bufs);
-	imu = &ctx->user_bufs[index];
+	imu = io_buf_from_index(ctx, index);
 	buf_addr = req->rw.addr;
 
 	/* overflow */
@@ -6086,7 +6109,7 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 
 	printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
 			req->opcode);
-	return-EINVAL;
+	return -EINVAL;
 }
 
 static int io_req_defer_prep(struct io_kiocb *req,
@@ -8391,28 +8414,66 @@ static unsigned long ring_pages(unsigned sq_entries, unsigned cq_entries)
 	return pages;
 }
 
-static int io_sqe_buffers_unregister(struct io_ring_ctx *ctx)
+static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf *imu)
 {
-	int i, j;
+	unsigned int i;
 
-	if (!ctx->user_bufs)
-		return -ENXIO;
+	for (i = 0; i < imu->nr_bvecs; i++)
+		unpin_user_page(imu->bvec[i].bv_page);
 
-	for (i = 0; i < ctx->nr_user_bufs; i++) {
-		struct io_mapped_ubuf *imu = &ctx->user_bufs[i];
+	if (imu->acct_pages)
+		io_unaccount_mem(ctx, imu->nr_bvecs, ACCT_PINNED);
+	kvfree(imu->bvec);
+	imu->nr_bvecs = 0;
+}
 
-		for (j = 0; j < imu->nr_bvecs; j++)
-			unpin_user_page(imu->bvec[j].bv_page);
+static void io_buffers_unmap(struct io_ring_ctx *ctx)
+{
+	unsigned int i;
+	struct io_mapped_ubuf *imu;
 
-		if (imu->acct_pages)
-			io_unaccount_mem(ctx, imu->acct_pages, ACCT_PINNED);
-		kvfree(imu->bvec);
-		imu->nr_bvecs = 0;
+	for (i = 0; i < ctx->nr_user_bufs; i++) {
+		imu = io_buf_from_index(ctx, i);
+		io_buffer_unmap(ctx, imu);
 	}
+}
 
-	kfree(ctx->user_bufs);
-	ctx->user_bufs = NULL;
+static void io_buffers_map_free(struct io_ring_ctx *ctx)
+{
+	struct fixed_rsrc_data *data = ctx->buf_data;
+	unsigned int nr_tables, i;
+
+	if (!data)
+		return;
+
+	nr_tables = DIV_ROUND_UP(ctx->nr_user_bufs, IORING_MAX_BUFS_TABLE);
+	for (i = 0; i < nr_tables; i++)
+		kfree(data->table[i].bufs);
+	free_fixed_rsrc_data(data);
+	ctx->buf_data = NULL;
 	ctx->nr_user_bufs = 0;
+}
+
+static int io_sqe_buffers_unregister(struct io_ring_ctx *ctx)
+{
+	struct fixed_rsrc_data *data = ctx->buf_data;
+	struct fixed_rsrc_ref_node *backup_node;
+	int ret;
+
+	if (!data)
+		return -ENXIO;
+	backup_node = alloc_fixed_rsrc_ref_node(ctx);
+	if (!backup_node)
+		return -ENOMEM;
+	init_fixed_buf_ref_node(ctx, backup_node);
+
+	ret = io_rsrc_ref_quiesce(data, ctx, backup_node);
+	if (ret)
+		return ret;
+
+	io_buffers_unmap(ctx);
+	io_buffers_map_free(ctx);
+
 	return 0;
 }
 
@@ -8465,7 +8526,9 @@ static bool headpage_already_acct(struct io_ring_ctx *ctx, struct page **pages,
 
 	/* check previously registered pages */
 	for (i = 0; i < ctx->nr_user_bufs; i++) {
-		struct io_mapped_ubuf *imu = &ctx->user_bufs[i];
+		struct io_mapped_ubuf *imu;
+
+		imu = io_buf_from_index(ctx, i);
 
 		for (j = 0; j < imu->nr_bvecs; j++) {
 			if (!PageCompound(imu->bvec[j].bv_page))
@@ -8600,19 +8663,66 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
 	return ret;
 }
 
-static int io_buffers_map_alloc(struct io_ring_ctx *ctx, unsigned int nr_args)
+static void io_free_buf_tables(struct fixed_rsrc_data *buf_data,
+			       unsigned int nr_tables)
 {
-	if (ctx->user_bufs)
-		return -EBUSY;
-	if (!nr_args || nr_args > UIO_MAXIOV)
-		return -EINVAL;
+	int i;
 
-	ctx->user_bufs = kcalloc(nr_args, sizeof(struct io_mapped_ubuf),
-					GFP_KERNEL);
-	if (!ctx->user_bufs)
-		return -ENOMEM;
+	for (i = 0; i < nr_tables; i++) {
+		struct fixed_rsrc_table *table = &buf_data->table[i];
 
-	return 0;
+		kfree(table->bufs);
+	}
+}
+
+static int io_alloc_buf_tables(struct fixed_rsrc_data *buf_data,
+			       unsigned int nr_tables, unsigned int nr_bufs)
+{
+	int i;
+
+	for (i = 0; i < nr_tables; i++) {
+		struct fixed_rsrc_table *table = &buf_data->table[i];
+		unsigned int this_bufs;
+
+		this_bufs = min(nr_bufs, IORING_MAX_BUFS_TABLE);
+		table->bufs = kcalloc(this_bufs, sizeof(struct io_mapped_ubuf),
+				      GFP_KERNEL);
+		if (!table->bufs)
+			break;
+		nr_bufs -= this_bufs;
+	}
+
+	if (i == nr_tables)
+		return 0;
+
+	io_free_buf_tables(buf_data, i);
+	return 1;
+}
+
+static struct fixed_rsrc_data *io_buffers_map_alloc(struct io_ring_ctx *ctx,
+						    unsigned int nr_args)
+{
+	unsigned int nr_tables;
+	struct fixed_rsrc_data *buf_data;
+
+	buf_data = alloc_fixed_rsrc_data(ctx);
+	if (!buf_data)
+		return NULL;
+
+	nr_tables = DIV_ROUND_UP(nr_args, IORING_MAX_BUFS_TABLE);
+	buf_data->table = kcalloc(nr_tables, sizeof(*buf_data->table),
+				  GFP_KERNEL);
+	if (!buf_data->table)
+		goto out;
+
+	if (io_alloc_buf_tables(buf_data, nr_tables, nr_args))
+		goto out;
+
+	return buf_data;
+out:
+	free_fixed_rsrc_data(ctx->buf_data);
+	ctx->buf_data = NULL;
+	return NULL;
 }
 
 static int io_buffer_validate(struct iovec *iov)
@@ -8632,39 +8742,73 @@ static int io_buffer_validate(struct iovec *iov)
 	return 0;
 }
 
+static void io_ring_buf_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
+{
+	io_buffer_unmap(ctx, prsrc->buf);
+}
+
+static void init_fixed_buf_ref_node(struct io_ring_ctx *ctx,
+				    struct fixed_rsrc_ref_node *ref_node)
+{
+	ref_node->rsrc_data = ctx->buf_data;
+	ref_node->rsrc_put = io_ring_buf_put;
+}
+
 static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
 				   unsigned int nr_args)
 {
 	int i, ret;
 	struct iovec iov;
 	struct page *last_hpage = NULL;
+	struct fixed_rsrc_ref_node *ref_node;
+	struct fixed_rsrc_data *buf_data;
 
-	ret = io_buffers_map_alloc(ctx, nr_args);
-	if (ret)
-		return ret;
+	if (ctx->buf_data)
+		return -EBUSY;
+	if (!nr_args || nr_args > IORING_MAX_FIXED_BUFS)
+		return -EINVAL;
 
-	for (i = 0; i < nr_args; i++) {
-		struct io_mapped_ubuf *imu = &ctx->user_bufs[i];
+	buf_data = io_buffers_map_alloc(ctx, nr_args);
+	if (!buf_data)
+		return -ENOMEM;
+	ctx->buf_data = buf_data;
+
+	for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) {
+		struct io_mapped_ubuf *imu;
 
 		ret = io_copy_iov(ctx, &iov, arg, i);
 		if (ret)
 			break;
 
+		/* allow sparse sets */
+		if (!iov.iov_base && !iov.iov_len)
+			continue;
+
 		ret = io_buffer_validate(&iov);
 		if (ret)
 			break;
 
+		imu = io_buf_from_index(ctx, i);
+
 		ret = io_sqe_buffer_register(ctx, &iov, imu, &last_hpage);
 		if (ret)
 			break;
+	}
 
-		ctx->nr_user_bufs++;
+	if (ret) {
+		io_sqe_buffers_unregister(ctx);
+		return ret;
 	}
 
-	if (ret)
+	ref_node = alloc_fixed_rsrc_ref_node(ctx);
+	if (!ref_node) {
 		io_sqe_buffers_unregister(ctx);
+		return -ENOMEM;
+	}
+	init_fixed_buf_ref_node(ctx, ref_node);
 
-	return ret;
+	io_sqe_rsrc_set_node(ctx, buf_data, ref_node);
+	return 0;
 }
 
 static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg)
@@ -9508,7 +9652,7 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 	}
 	seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs);
 	for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) {
-		struct io_mapped_ubuf *buf = &ctx->user_bufs[i];
+		struct io_mapped_ubuf *buf = io_buf_from_index(ctx, i);
 
 		seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf,
 						(unsigned int) buf->len);
@@ -10025,6 +10169,7 @@ static bool io_register_op_must_quiesce(int op)
 	switch (op) {
 	case IORING_UNREGISTER_FILES:
 	case IORING_REGISTER_FILES_UPDATE:
+	case IORING_UNREGISTER_BUFFERS:
 	case IORING_REGISTER_PROBE:
 	case IORING_REGISTER_PERSONALITY:
 	case IORING_UNREGISTER_PERSONALITY:
-- 
1.8.3.1