From: Jens Axboe <axboe@kernel.dk>
To: linux-aio@kvack.org, linux-block@vger.kernel.org,
linux-api@vger.kernel.org
Cc: hch@lst.de, jmoyer@redhat.com, avi@scylladb.com,
jannh@google.com, viro@ZenIV.linux.org.uk,
Jens Axboe <axboe@kernel.dk>
Subject: [PATCH 14/19] io_uring: add file set registration
Date: Sat, 9 Feb 2019 14:13:41 -0700 [thread overview]
Message-ID: <20190209211346.26060-15-axboe@kernel.dk> (raw)
In-Reply-To: <20190209211346.26060-1-axboe@kernel.dk>
We normally have to fget/fput for each IO we do on a file. Even with
the batching we do, the cost of the atomic inc/dec of the file usage
count adds up.
This adds IORING_REGISTER_FILES, and IORING_UNREGISTER_FILES opcodes
for the io_uring_register(2) system call. The arguments passed in must
be an array of __s32 holding file descriptors, and nr_args should hold
the number of file descriptors the application wishes to pin for the
duration of the io_uring instance (or until IORING_UNREGISTER_FILES is
called).
When used, the application must set IOSQE_FIXED_FILE in the sqe->flags
member. Then, instead of setting sqe->fd to the real fd, it sets sqe->fd
to the index in the array passed in to IORING_REGISTER_FILES.
Files are automatically unregistered when the io_uring instance is torn
down. An application need only unregister if it wishes to register a new
set of fds.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/io_uring.c | 269 ++++++++++++++++++++++++++++++----
include/uapi/linux/io_uring.h | 9 +-
2 files changed, 245 insertions(+), 33 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 09a3122b3b6c..c40a7ed2edd5 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -29,6 +29,7 @@
#include <linux/net.h>
#include <net/sock.h>
#include <net/af_unix.h>
+#include <net/scm.h>
#include <linux/anon_inodes.h>
#include <linux/sched/mm.h>
#include <linux/uaccess.h>
@@ -41,6 +42,7 @@
#include "internal.h"
#define IORING_MAX_ENTRIES 4096
+#define IORING_MAX_FIXED_FILES 1024
struct io_uring {
u32 head ____cacheline_aligned_in_smp;
@@ -103,6 +105,14 @@ struct io_ring_ctx {
struct fasync_struct *cq_fasync;
} ____cacheline_aligned_in_smp;
+ /*
+ * If used, fixed file set. Writers must ensure that ->refs is dead,
+ * readers must ensure that ->refs is alive as long as the file* is
+ * used. Only updated through io_uring_register(2).
+ */
+ struct file **user_files;
+ unsigned nr_user_files;
+
/* if used, fixed mapped user buffers */
unsigned nr_user_bufs;
struct io_mapped_ubuf *user_bufs;
@@ -150,6 +160,7 @@ struct io_kiocb {
unsigned int flags;
#define REQ_F_FORCE_NONBLOCK 1 /* inline submission attempt */
#define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */
+#define REQ_F_FIXED_FILE 4 /* ctx owns file */
u64 user_data;
u64 error;
@@ -380,15 +391,17 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
* Batched puts of the same file, to avoid dirtying the
* file usage count multiple times, if avoidable.
*/
- if (!file) {
- file = req->rw.ki_filp;
- file_count = 1;
- } else if (file == req->rw.ki_filp) {
- file_count++;
- } else {
- fput_many(file, file_count);
- file = req->rw.ki_filp;
- file_count = 1;
+ if (!(req->flags & REQ_F_FIXED_FILE)) {
+ if (!file) {
+ file = req->rw.ki_filp;
+ file_count = 1;
+ } else if (file == req->rw.ki_filp) {
+ file_count++;
+ } else {
+ fput_many(file, file_count);
+ file = req->rw.ki_filp;
+ file_count = 1;
+ }
}
if (to_free == ARRAY_SIZE(reqs))
@@ -520,13 +533,19 @@ static void kiocb_end_write(struct kiocb *kiocb)
}
}
+static void io_fput(struct io_kiocb *req)
+{
+ if (!(req->flags & REQ_F_FIXED_FILE))
+ fput(req->rw.ki_filp);
+}
+
static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
kiocb_end_write(kiocb);
- fput(kiocb->ki_filp);
+ io_fput(req);
io_cqring_add_event(req->ctx, req->user_data, res, 0);
io_free_req(req);
}
@@ -642,19 +661,29 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
{
struct io_ring_ctx *ctx = req->ctx;
struct kiocb *kiocb = &req->rw;
- unsigned ioprio;
+ unsigned ioprio, flags;
int fd, ret;
/* For -EAGAIN retry, everything is already prepped */
if (kiocb->ki_filp)
return 0;
+ flags = READ_ONCE(sqe->flags);
fd = READ_ONCE(sqe->fd);
- kiocb->ki_filp = io_file_get(state, fd);
- if (unlikely(!kiocb->ki_filp))
- return -EBADF;
- if (force_nonblock && !io_file_supports_async(kiocb->ki_filp))
- force_nonblock = false;
+
+ if (flags & IOSQE_FIXED_FILE) {
+ if (unlikely(!ctx->user_files ||
+ (unsigned) fd >= ctx->nr_user_files))
+ return -EBADF;
+ kiocb->ki_filp = ctx->user_files[fd];
+ req->flags |= REQ_F_FIXED_FILE;
+ } else {
+ kiocb->ki_filp = io_file_get(state, fd);
+ if (unlikely(!kiocb->ki_filp))
+ return -EBADF;
+ if (force_nonblock && !io_file_supports_async(kiocb->ki_filp))
+ force_nonblock = false;
+ }
kiocb->ki_pos = READ_ONCE(sqe->off);
kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp));
@@ -694,10 +723,14 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
}
return 0;
out_fput:
- /* in case of error, we didn't use this file reference. drop it. */
- if (state)
- state->used_refs--;
- io_file_put(state, kiocb->ki_filp);
+ if (!(flags & IOSQE_FIXED_FILE)) {
+ /*
+ * in case of error, we didn't use this file reference. drop it.
+ */
+ if (state)
+ state->used_refs--;
+ io_file_put(state, kiocb->ki_filp);
+ }
return ret;
}
@@ -837,7 +870,7 @@ static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s,
out_fput:
/* Hold on to the file for -EAGAIN */
if (unlikely(ret && ret != -EAGAIN))
- fput(file);
+ io_fput(req);
return ret;
}
@@ -891,7 +924,7 @@ static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s,
kfree(iovec);
out_fput:
if (unlikely(ret))
- fput(file);
+ io_fput(req);
return ret;
}
@@ -914,7 +947,8 @@ static int io_nop(struct io_kiocb *req, u64 user_data)
*/
if (req->rw.ki_filp) {
err = -EBADF;
- fput(req->rw.ki_filp);
+ if (!(req->flags & REQ_F_FIXED_FILE))
+ fput(req->rw.ki_filp);
}
io_cqring_add_event(ctx, user_data, err, 0);
io_free_req(req);
@@ -923,21 +957,32 @@ static int io_nop(struct io_kiocb *req, u64 user_data)
static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
+ struct io_ring_ctx *ctx = req->ctx;
+ unsigned flags;
int fd;
/* Prep already done */
if (req->rw.ki_filp)
return 0;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index))
return -EINVAL;
fd = READ_ONCE(sqe->fd);
- req->rw.ki_filp = fget(fd);
- if (unlikely(!req->rw.ki_filp))
- return -EBADF;
+ flags = READ_ONCE(sqe->flags);
+
+ if (flags & IOSQE_FIXED_FILE) {
+ if (unlikely(!ctx->user_files || fd >= ctx->nr_user_files))
+ return -EBADF;
+ req->rw.ki_filp = ctx->user_files[fd];
+ req->flags |= REQ_F_FIXED_FILE;
+ } else {
+ req->rw.ki_filp = fget(fd);
+ if (unlikely(!req->rw.ki_filp))
+ return -EBADF;
+ }
return 0;
}
@@ -967,7 +1012,8 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
end > 0 ? end : LLONG_MAX,
fsync_flags & IORING_FSYNC_DATASYNC);
- fput(req->rw.ki_filp);
+ if (!(req->flags & REQ_F_FIXED_FILE))
+ fput(req->rw.ki_filp);
io_cqring_add_event(req->ctx, sqe->user_data, ret, 0);
io_free_req(req);
return 0;
@@ -1104,7 +1150,7 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, const struct sqe_submit *s,
ssize_t ret;
/* enforce forwards compatibility on users */
- if (unlikely(s->sqe->flags))
+ if (unlikely(s->sqe->flags & ~IOSQE_FIXED_FILE))
return -EINVAL;
req = io_get_req(ctx, state);
@@ -1292,6 +1338,154 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
return READ_ONCE(ring->r.head) == READ_ONCE(ring->r.tail) ? ret : 0;
}
+static void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
+{
+#if defined(CONFIG_UNIX)
+ if (ctx->ring_sock) {
+ struct sock *sock = ctx->ring_sock->sk;
+ struct sk_buff *skb;
+
+ while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL)
+ kfree_skb(skb);
+ }
+#else
+ int i;
+
+ for (i = 0; i < ctx->nr_user_files; i++)
+ fput(ctx->user_files[i]);
+#endif
+}
+
+static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
+{
+ if (!ctx->user_files)
+ return -ENXIO;
+
+ __io_sqe_files_unregister(ctx);
+ kfree(ctx->user_files);
+ ctx->user_files = NULL;
+ return 0;
+}
+
+#if defined(CONFIG_UNIX)
+static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset)
+{
+ struct scm_fp_list *fpl;
+ struct sk_buff *skb;
+ int i;
+
+ fpl = kzalloc(sizeof(*fpl), GFP_KERNEL);
+ if (!fpl)
+ return -ENOMEM;
+
+ skb = alloc_skb(0, GFP_KERNEL);
+ if (!skb) {
+ kfree(fpl);
+ return -ENOMEM;
+ }
+
+ skb->sk = ctx->ring_sock->sk;
+ skb->destructor = unix_destruct_scm;
+
+ fpl->user = get_uid(ctx->user);
+ for (i = 0; i < nr; i++) {
+ fpl->fp[i] = get_file(ctx->user_files[i + offset]);
+ unix_inflight(fpl->user, fpl->fp[i]);
+ }
+
+ fpl->max = fpl->count = nr;
+ UNIXCB(skb).fp = fpl;
+ skb_queue_head(&ctx->ring_sock->sk->sk_receive_queue, skb);
+
+ for (i = 0; i < nr; i++)
+ fput(fpl->fp[i]);
+
+ return 0;
+}
+
+/*
+ * If UNIX sockets are enabled, fd passing can cause a reference cycle which
+ * causes regular reference counting to break down. We rely on the UNIX
+ * garbage collection to take care of this problem for us.
+ */
+static int io_sqe_files_scm(struct io_ring_ctx *ctx)
+{
+ unsigned left, total;
+ int ret = 0;
+
+ total = 0;
+ left = ctx->nr_user_files;
+ while (left) {
+ unsigned this_files = min_t(unsigned, left, SCM_MAX_FD);
+ int ret;
+
+ ret = __io_sqe_files_scm(ctx, this_files, total);
+ if (ret)
+ break;
+ left -= this_files;
+ total += this_files;
+ }
+
+ return ret;
+}
+#else
+static int io_sqe_files_scm(struct io_ring_ctx *ctx)
+{
+ return 0;
+}
+#endif
+
+static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
+ unsigned nr_args)
+{
+ __s32 __user *fds = (__s32 __user *) arg;
+ int fd, ret = 0;
+ unsigned i;
+
+ if (ctx->user_files)
+ return -EBUSY;
+ if (!nr_args)
+ return -EINVAL;
+ if (nr_args > IORING_MAX_FIXED_FILES)
+ return -EMFILE;
+
+ ctx->user_files = kcalloc(nr_args, sizeof(struct file *), GFP_KERNEL);
+ if (!ctx->user_files)
+ return -ENOMEM;
+
+ for (i = 0; i < nr_args; i++) {
+ ret = -EFAULT;
+ if (copy_from_user(&fd, &fds[i], sizeof(fd)))
+ break;
+
+ ctx->user_files[i] = fget(fd);
+
+ ret = -EBADF;
+ if (!ctx->user_files[i])
+ break;
+ /*
+ * Don't allow io_uring instances to be registered. If UNIX
+ * isn't enabled, then this causes a reference cycle and this
+ * instance can never get freed. If UNIX is enabled we'll
+ * handle it just fine, but there's still no point in allowing
+ * a ring fd as it doesn't support regular read/write anyway.
+ */
+ if (ctx->user_files[i]->f_op == &io_uring_fops) {
+ fput(ctx->user_files[i]);
+ break;
+ }
+ ctx->nr_user_files++;
+ ret = 0;
+ }
+
+ if (!ret)
+ ret = io_sqe_files_scm(ctx);
+ if (ret)
+ io_sqe_files_unregister(ctx);
+
+ return ret;
+}
+
static int io_sq_offload_start(struct io_ring_ctx *ctx)
{
int ret;
@@ -1560,14 +1754,16 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
destroy_workqueue(ctx->sqo_wq);
if (ctx->sqo_mm)
mmdrop(ctx->sqo_mm);
+
+ io_iopoll_reap_events(ctx);
+ io_sqe_buffer_unregister(ctx);
+ io_sqe_files_unregister(ctx);
+
#if defined(CONFIG_UNIX)
if (ctx->ring_sock)
sock_release(ctx->ring_sock);
#endif
- io_iopoll_reap_events(ctx);
- io_sqe_buffer_unregister(ctx);
-
io_mem_free(ctx->sq_ring);
io_mem_free(ctx->sq_sqes);
io_mem_free(ctx->cq_ring);
@@ -1934,6 +2130,15 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
break;
ret = io_sqe_buffer_unregister(ctx);
break;
+ case IORING_REGISTER_FILES:
+ ret = io_sqe_files_register(ctx, arg, nr_args);
+ break;
+ case IORING_UNREGISTER_FILES:
+ ret = -EINVAL;
+ if (arg || nr_args)
+ break;
+ ret = io_sqe_files_unregister(ctx);
+ break;
default:
ret = -EINVAL;
break;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index cf28f7a11f12..6257478d55e9 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -16,7 +16,7 @@
*/
struct io_uring_sqe {
__u8 opcode; /* type of operation for this sqe */
- __u8 flags; /* as of now unused */
+ __u8 flags; /* IOSQE_ flags */
__u16 ioprio; /* ioprio for the request */
__s32 fd; /* file descriptor to do IO on */
__u64 off; /* offset into file */
@@ -33,6 +33,11 @@ struct io_uring_sqe {
};
};
+/*
+ * sqe->flags
+ */
+#define IOSQE_FIXED_FILE (1U << 0) /* use fixed fileset */
+
/*
* io_uring_setup() flags
*/
@@ -113,5 +118,7 @@ struct io_uring_params {
*/
#define IORING_REGISTER_BUFFERS 0
#define IORING_UNREGISTER_BUFFERS 1
+#define IORING_REGISTER_FILES 2
+#define IORING_UNREGISTER_FILES 3
#endif
--
2.17.1
next prev parent reply other threads:[~2019-02-09 21:14 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-02-09 21:13 [PATCHSET v14] io_uring IO interface Jens Axboe
2019-02-09 21:13 ` [PATCH 01/19] fs: add an iopoll method to struct file_operations Jens Axboe
2019-02-09 21:13 ` [PATCH 02/19] block: wire up block device iopoll method Jens Axboe
2019-02-09 21:13 ` [PATCH 03/19] block: add bio_set_polled() helper Jens Axboe
2019-02-09 21:13 ` [PATCH 04/19] iomap: wire up the iopoll method Jens Axboe
2019-02-09 21:13 ` [PATCH 05/19] Add io_uring IO interface Jens Axboe
2019-02-10 12:03 ` Thomas Gleixner
2019-02-10 14:19 ` Jens Axboe
2019-02-09 21:13 ` [PATCH 06/19] io_uring: add fsync support Jens Axboe
2019-02-09 21:13 ` [PATCH 07/19] io_uring: support for IO polling Jens Axboe
2019-02-09 21:13 ` [PATCH 08/19] fs: add fget_many() and fput_many() Jens Axboe
2019-02-09 21:13 ` [PATCH 09/19] io_uring: use fget/fput_many() for file references Jens Axboe
2019-02-09 21:13 ` [PATCH 10/19] io_uring: batch io_kiocb allocation Jens Axboe
2019-02-09 21:13 ` [PATCH 11/19] block: implement bio helper to add iter bvec pages to bio Jens Axboe
2019-02-09 21:13 ` [PATCH 12/19] io_uring: add support for pre-mapped user IO buffers Jens Axboe
2019-02-09 21:13 ` [PATCH 13/19] net: split out functions related to registering inflight socket files Jens Axboe
2019-02-09 21:13 ` Jens Axboe [this message]
2019-02-09 23:52 ` [PATCH 14/19] io_uring: add file set registration Matt Mullins
2019-02-10 0:47 ` Jens Axboe
[not found] ` <60e4c6a489549daad1fb2c5e8eee5496c668d79a.camel@fb.com>
2019-02-10 2:34 ` Jens Axboe
2019-02-10 2:57 ` Jens Axboe
2019-02-10 19:55 ` Matt Mullins
2019-02-09 21:13 ` [PATCH 15/19] io_uring: add submission polling Jens Axboe
2019-02-09 21:13 ` [PATCH 16/19] io_uring: add io_kiocb ref count Jens Axboe
2019-02-10 9:19 ` Hannes Reinecke
2019-02-09 21:13 ` [PATCH 17/19] io_uring: add support for IORING_OP_POLL Jens Axboe
2019-02-10 9:28 ` Hannes Reinecke
2019-02-09 21:13 ` [PATCH 18/19] io_uring: allow workqueue item to handle multiple buffered requests Jens Axboe
2019-02-10 9:31 ` Hannes Reinecke
2019-02-09 21:13 ` [PATCH 19/19] io_uring: add io_uring_event cache hit information Jens Axboe
2019-02-10 9:36 ` Hannes Reinecke
2019-02-10 13:39 ` Jens Axboe
-- strict thread matches above, loose matches on Subject: below --
2019-02-11 19:00 [PATCHSET v15] io_uring IO interface Jens Axboe
2019-02-11 19:00 ` [PATCH 14/19] io_uring: add file set registration Jens Axboe
2019-02-19 16:12 ` Jann Horn
2019-02-22 22:29 ` Jens Axboe
2019-02-08 17:34 [PATCHSET v13] io_uring IO interface Jens Axboe
2019-02-08 17:34 ` [PATCH 14/19] io_uring: add file set registration Jens Axboe
2019-02-08 20:26 ` Jann Horn
2019-02-09 0:16 ` Jens Axboe
2019-02-09 9:50 ` Hannes Reinecke
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=20190209211346.26060-15-axboe@kernel.dk \
--to=axboe@kernel.dk \
--cc=avi@scylladb.com \
--cc=hch@lst.de \
--cc=jannh@google.com \
--cc=jmoyer@redhat.com \
--cc=linux-aio@kvack.org \
--cc=linux-api@vger.kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=viro@ZenIV.linux.org.uk \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).