From: Keith Busch <kbusch@meta.com>
To: <ming.lei@redhat.com>, <asml.silence@gmail.com>,
<axboe@kernel.dk>, <linux-block@vger.kernel.org>,
<io-uring@vger.kernel.org>
Cc: <bernd@bsbernd.com>, Keith Busch <kbusch@kernel.org>
Subject: [PATCHv2 5/6] io_uring: add abstraction for buf_table rsrc data
Date: Mon, 10 Feb 2025 16:56:45 -0800 [thread overview]
Message-ID: <20250211005646.222452-6-kbusch@meta.com> (raw)
In-Reply-To: <20250211005646.222452-1-kbusch@meta.com>
From: Keith Busch <kbusch@kernel.org>
We'll need to add more fields specific to the registered buffers, so
make a layer for it now. No functional change in this patch.
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
include/linux/io_uring_types.h | 6 +++-
io_uring/fdinfo.c | 8 +++---
io_uring/net.c | 2 +-
io_uring/nop.c | 2 +-
io_uring/register.c | 2 +-
io_uring/rsrc.c | 51 +++++++++++++++++-----------------
io_uring/rw.c | 2 +-
io_uring/uring_cmd.c | 2 +-
8 files changed, 39 insertions(+), 36 deletions(-)
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 99aac2d52fbae..4f4b7ad21500d 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -67,6 +67,10 @@ struct io_file_table {
unsigned int alloc_hint;
};
+struct io_buf_table {
+ struct io_rsrc_data data;
+};
+
struct io_hash_bucket {
struct hlist_head list;
} ____cacheline_aligned_in_smp;
@@ -291,7 +295,7 @@ struct io_ring_ctx {
struct io_wq_work_list iopoll_list;
struct io_file_table file_table;
- struct io_rsrc_data buf_table;
+ struct io_buf_table buf_table;
struct io_submit_state submit_state;
diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index f60d0a9d505e2..d389c06cbce10 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -217,12 +217,12 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
seq_puts(m, "\n");
}
}
- seq_printf(m, "UserBufs:\t%u\n", ctx->buf_table.nr);
- for (i = 0; has_lock && i < ctx->buf_table.nr; i++) {
+ seq_printf(m, "UserBufs:\t%u\n", ctx->buf_table.data.nr);
+ for (i = 0; has_lock && i < ctx->buf_table.data.nr; i++) {
struct io_mapped_ubuf *buf = NULL;
- if (ctx->buf_table.nodes[i])
- buf = ctx->buf_table.nodes[i]->buf;
+ if (ctx->buf_table.data.nodes[i])
+ buf = ctx->buf_table.data.nodes[i]->buf;
if (buf)
seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, buf->len);
else
diff --git a/io_uring/net.c b/io_uring/net.c
index 280d576e89249..c1020c857333d 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -1366,7 +1366,7 @@ static int io_send_zc_import(struct io_kiocb *req, unsigned int issue_flags)
ret = -EFAULT;
io_ring_submit_lock(ctx, issue_flags);
- node = io_rsrc_node_lookup(&ctx->buf_table, sr->buf_index);
+ node = io_rsrc_node_lookup(&ctx->buf_table.data, sr->buf_index);
if (node) {
io_req_assign_buf_node(sr->notif, node);
ret = 0;
diff --git a/io_uring/nop.c b/io_uring/nop.c
index 5e5196df650a1..e3ebe5f019076 100644
--- a/io_uring/nop.c
+++ b/io_uring/nop.c
@@ -69,7 +69,7 @@ int io_nop(struct io_kiocb *req, unsigned int issue_flags)
ret = -EFAULT;
io_ring_submit_lock(ctx, issue_flags);
- node = io_rsrc_node_lookup(&ctx->buf_table, nop->buffer);
+ node = io_rsrc_node_lookup(&ctx->buf_table.data, nop->buffer);
if (node) {
io_req_assign_buf_node(req, node);
ret = 0;
diff --git a/io_uring/register.c b/io_uring/register.c
index 9a4d2fbce4aec..fa922b1b26583 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -919,7 +919,7 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
ret = __io_uring_register(ctx, opcode, arg, nr_args);
trace_io_uring_register(ctx, opcode, ctx->file_table.data.nr,
- ctx->buf_table.nr, ret);
+ ctx->buf_table.data.nr, ret);
mutex_unlock(&ctx->uring_lock);
fput(file);
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 14efec8587888..b3f36f1b2a668 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -232,17 +232,17 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
__u32 done;
int i, err;
- if (!ctx->buf_table.nr)
+ if (!ctx->buf_table.data.nr)
return -ENXIO;
- if (up->offset + nr_args > ctx->buf_table.nr)
+ if (up->offset + nr_args > ctx->buf_table.data.nr)
return -EINVAL;
for (done = 0; done < nr_args; done++) {
struct io_rsrc_node *node;
u64 tag = 0;
- i = array_index_nospec(up->offset + done, ctx->buf_table.nr);
- node = io_rsrc_node_lookup(&ctx->buf_table, i);
+ i = array_index_nospec(up->offset + done, ctx->buf_table.data.nr);
+ node = io_rsrc_node_lookup(&ctx->buf_table.data, i);
if (node && node->type != IORING_RSRC_BUFFER) {
err = -EBUSY;
break;
@@ -273,8 +273,8 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
}
node->tag = tag;
}
- io_reset_rsrc_node(ctx, &ctx->buf_table, i);
- ctx->buf_table.nodes[i] = node;
+ io_reset_rsrc_node(ctx, &ctx->buf_table.data, i);
+ ctx->buf_table.data.nodes[i] = node;
if (ctx->compat)
user_data += sizeof(struct compat_iovec);
else
@@ -555,9 +555,9 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
int io_sqe_buffers_unregister(struct io_ring_ctx *ctx)
{
- if (!ctx->buf_table.nr)
+ if (!ctx->buf_table.data.nr)
return -ENXIO;
- io_rsrc_data_free(ctx, &ctx->buf_table);
+ io_rsrc_data_free(ctx, &ctx->buf_table.data);
return 0;
}
@@ -584,8 +584,8 @@ static bool headpage_already_acct(struct io_ring_ctx *ctx, struct page **pages,
}
/* check previously registered pages */
- for (i = 0; i < ctx->buf_table.nr; i++) {
- struct io_rsrc_node *node = ctx->buf_table.nodes[i];
+ for (i = 0; i < ctx->buf_table.data.nr; i++) {
+ struct io_rsrc_node *node = ctx->buf_table.data.nodes[i];
struct io_mapped_ubuf *imu;
if (!node)
@@ -811,7 +811,7 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
BUILD_BUG_ON(IORING_MAX_REG_BUFFERS >= (1u << 16));
- if (ctx->buf_table.nr)
+ if (ctx->buf_table.data.nr)
return -EBUSY;
if (!nr_args || nr_args > IORING_MAX_REG_BUFFERS)
return -EINVAL;
@@ -864,7 +864,7 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
data.nodes[i] = node;
}
- ctx->buf_table = data;
+ ctx->buf_table.data = data;
if (ret)
io_sqe_buffers_unregister(ctx);
return ret;
@@ -873,7 +873,7 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
int io_buffer_register_bvec(struct io_ring_ctx *ctx, struct request *rq,
void (*release)(void *), unsigned int index)
{
- struct io_rsrc_data *data = &ctx->buf_table;
+ struct io_rsrc_data *data = &ctx->buf_table.data;
struct req_iterator rq_iter;
struct io_mapped_ubuf *imu;
struct io_rsrc_node *node;
@@ -924,7 +924,7 @@ EXPORT_SYMBOL_GPL(io_buffer_register_bvec);
void io_buffer_unregister_bvec(struct io_ring_ctx *ctx, unsigned int index)
{
- struct io_rsrc_data *data = &ctx->buf_table;
+ struct io_rsrc_data *data = &ctx->buf_table.data;
struct io_rsrc_node *node;
lockdep_assert_held(&ctx->uring_lock);
@@ -1040,10 +1040,10 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
if (!arg->nr && (arg->dst_off || arg->src_off))
return -EINVAL;
/* not allowed unless REPLACE is set */
- if (ctx->buf_table.nr && !(arg->flags & IORING_REGISTER_DST_REPLACE))
+ if (ctx->buf_table.data.nr && !(arg->flags & IORING_REGISTER_DST_REPLACE))
return -EBUSY;
- nbufs = src_ctx->buf_table.nr;
+ nbufs = src_ctx->buf_table.data.nr;
if (!arg->nr)
arg->nr = nbufs;
else if (arg->nr > nbufs)
@@ -1053,13 +1053,13 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
if (check_add_overflow(arg->nr, arg->dst_off, &nbufs))
return -EOVERFLOW;
- ret = io_rsrc_data_alloc(&data, max(nbufs, ctx->buf_table.nr));
+ ret = io_rsrc_data_alloc(&data, max(nbufs, ctx->buf_table.data.nr));
if (ret)
return ret;
/* Fill entries in data from dst that won't overlap with src */
- for (i = 0; i < min(arg->dst_off, ctx->buf_table.nr); i++) {
- struct io_rsrc_node *src_node = ctx->buf_table.nodes[i];
+ for (i = 0; i < min(arg->dst_off, ctx->buf_table.data.nr); i++) {
+ struct io_rsrc_node *src_node = ctx->buf_table.data.nodes[i];
if (src_node) {
data.nodes[i] = src_node;
@@ -1068,7 +1068,7 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
}
ret = -ENXIO;
- nbufs = src_ctx->buf_table.nr;
+ nbufs = src_ctx->buf_table.data.nr;
if (!nbufs)
goto out_free;
ret = -EINVAL;
@@ -1088,7 +1088,7 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
while (nr--) {
struct io_rsrc_node *dst_node, *src_node;
- src_node = io_rsrc_node_lookup(&src_ctx->buf_table, i);
+ src_node = io_rsrc_node_lookup(&src_ctx->buf_table.data, i);
if (!src_node) {
dst_node = NULL;
} else {
@@ -1110,7 +1110,7 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
* old and new nodes at this point.
*/
if (arg->flags & IORING_REGISTER_DST_REPLACE)
- io_rsrc_data_free(ctx, &ctx->buf_table);
+ io_sqe_buffers_unregister(ctx);
/*
* ctx->buf_table must be empty now - either the contents are being
@@ -1118,10 +1118,9 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
* copied to a ring that does not have buffers yet (checked at function
* entry).
*/
- WARN_ON_ONCE(ctx->buf_table.nr);
- ctx->buf_table = data;
+ WARN_ON_ONCE(ctx->buf_table.data.nr);
+ ctx->buf_table.data = data;
return 0;
-
out_free:
io_rsrc_data_free(ctx, &data);
return ret;
@@ -1146,7 +1145,7 @@ int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg)
return -EFAULT;
if (buf.flags & ~(IORING_REGISTER_SRC_REGISTERED|IORING_REGISTER_DST_REPLACE))
return -EINVAL;
- if (!(buf.flags & IORING_REGISTER_DST_REPLACE) && ctx->buf_table.nr)
+ if (!(buf.flags & IORING_REGISTER_DST_REPLACE) && ctx->buf_table.data.nr)
return -EBUSY;
if (memchr_inv(buf.pad, 0, sizeof(buf.pad)))
return -EINVAL;
diff --git a/io_uring/rw.c b/io_uring/rw.c
index c25e0ab5c996b..38ec32401a558 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -363,7 +363,7 @@ static int io_prep_rw_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe
if (unlikely(ret))
return ret;
- node = io_rsrc_node_lookup(&ctx->buf_table, req->buf_index);
+ node = io_rsrc_node_lookup(&ctx->buf_table.data, req->buf_index);
if (!node)
return -EFAULT;
io_req_assign_buf_node(req, node);
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index aebbe2a4c7183..5d9719402b49b 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -206,7 +206,7 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
struct io_rsrc_node *node;
u16 index = READ_ONCE(sqe->buf_index);
- node = io_rsrc_node_lookup(&ctx->buf_table, index);
+ node = io_rsrc_node_lookup(&ctx->buf_table.data, index);
if (unlikely(!node))
return -EFAULT;
/*
--
2.43.5
next prev parent reply other threads:[~2025-02-11 0:57 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-11 0:56 [PATCHv2 0/6] ublk zero-copy support Keith Busch
2025-02-11 0:56 ` [PATCHv2 1/6] io_uring: use node for import Keith Busch
2025-02-11 0:56 ` [PATCHv2 2/6] io_uring: create resource release callback Keith Busch
2025-02-13 1:31 ` Pavel Begunkov
2025-02-13 1:58 ` Keith Busch
2025-02-13 13:06 ` Pavel Begunkov
2025-02-11 0:56 ` [PATCHv2 3/6] io_uring: add support for kernel registered bvecs Keith Busch
2025-02-13 1:33 ` Pavel Begunkov
2025-02-14 3:30 ` Ming Lei
2025-02-14 15:26 ` Keith Busch
2025-02-15 1:34 ` Ming Lei
2025-02-18 20:34 ` Keith Busch
2025-02-11 0:56 ` [PATCHv2 4/6] ublk: zc register/unregister bvec Keith Busch
2025-02-12 2:49 ` Ming Lei
2025-02-12 4:11 ` Keith Busch
2025-02-12 9:24 ` Ming Lei
2025-02-12 14:59 ` Keith Busch
2025-02-13 2:12 ` Pavel Begunkov
2025-02-11 0:56 ` Keith Busch [this message]
2025-02-11 0:56 ` [PATCHv2 6/6] io_uring: cache nodes and mapped buffers Keith Busch
2025-02-11 15:17 ` kernel test robot
2025-02-11 16:47 ` Keith Busch
2025-02-12 1:42 ` kernel test robot
2025-02-12 2:29 ` [PATCHv2 0/6] ublk zero-copy support Ming Lei
2025-02-12 15:28 ` Keith Busch
2025-02-12 16:06 ` Pavel Begunkov
2025-02-13 1:52 ` Ming Lei
2025-02-13 15:12 ` lizetao
2025-02-13 16:06 ` Keith Busch
2025-02-14 3:39 ` lizetao
2025-02-14 2:41 ` Ming Lei
2025-02-14 4:21 ` lizetao
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250211005646.222452-6-kbusch@meta.com \
--to=kbusch@meta.com \
--cc=asml.silence@gmail.com \
--cc=axboe@kernel.dk \
--cc=bernd@bsbernd.com \
--cc=io-uring@vger.kernel.org \
--cc=kbusch@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=ming.lei@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.