| Message ID | 20190208173423.27014-15-axboe@kernel.dk (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [01/19] fs: add an iopoll method to struct file_operations | expand |
On Fri, Feb 8, 2019 at 6:35 PM Jens Axboe <axboe@kernel.dk> wrote: > 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. I think the overall concept here is still broken: You're giving the user_files to the GC, and I think the GC can drop their refcounts, but I don't see you actually getting feedback from the GC anywhere that would let the GC break your references? E.g. in io_prep_rw() you grab file pointers from ctx->user_files after simply checking ctx->nr_user_files, and there is no path from the GC that touches those fields. As far as I can tell, the GC is just going to go through unix_destruct_scm() and drop references on your files, causing use-after-free. But the unix GC is complicated, and maybe I'm just missing something... > +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]); > + fput(fpl->fp[i]); This pattern is almost always superfluous. You increment the file's refcount, maybe insert the file into a list (essentially), and drop the file's refcount back down. You're already holding a stable reference, and you're not temporarily lending that to anyone else. > + } > + > + fpl->max = fpl->count = nr; > + UNIXCB(skb).fp = fpl; > + skb_queue_head(&ctx->ring_sock->sk->sk_receive_queue, skb); > + 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 suppor regular read/write anyway. nit: support > + */ > + 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; > @@ -1521,14 +1708,16 @@ 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);
On 2/8/19 1:26 PM, Jann Horn wrote: > On Fri, Feb 8, 2019 at 6:35 PM Jens Axboe <axboe@kernel.dk> wrote: >> 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. > > I think the overall concept here is still broken: You're giving the > user_files to the GC, and I think the GC can drop their refcounts, but > I don't see you actually getting feedback from the GC anywhere that > would let the GC break your references? E.g. in io_prep_rw() you grab > file pointers from ctx->user_files after simply checking > ctx->nr_user_files, and there is no path from the GC that touches > those fields. As far as I can tell, the GC is just going to go through > unix_destruct_scm() and drop references on your files, causing > use-after-free. > > But the unix GC is complicated, and maybe I'm just missing something... Only when the skb is released, which is either done when the io_uring is torn down (and then definitely safe), or if the socket is released, which is again also at a safe time. >> +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]); >> + fput(fpl->fp[i]); > > This pattern is almost always superfluous. You increment the file's > refcount, maybe insert the file into a list (essentially), and drop > the file's refcount back down. You're already holding a stable > reference, and you're not temporarily lending that to anyone else. Actually, this is me messing up. The fput() should be done AFTER adding to the socket. I'll fix that.
On 2/8/19 6:34 PM, Jens Axboe wrote: > 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. > > Signed-off-by: Jens Axboe <axboe@kernel.dk> > --- > fs/io_uring.c | 256 ++++++++++++++++++++++++++++++---- > include/uapi/linux/io_uring.h | 9 +- > 2 files changed, 235 insertions(+), 30 deletions(-) > Reviewed-by: Hannes Reinecke <hare@suse.com> Cheers, Hannes
diff --git a/fs/io_uring.c b/fs/io_uring.c index 50c48e43d56e..244fb71e3424 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; @@ -102,6 +104,14 @@ 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; @@ -149,6 +159,7 @@ 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; @@ -376,15 +387,17 @@ 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)) @@ -516,13 +529,19 @@ 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); } @@ -638,19 +657,29 @@ 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)); @@ -690,10 +719,14 @@ 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; } @@ -825,7 +858,7 @@ 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; } @@ -879,7 +912,7 @@ 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; } @@ -905,7 +938,7 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, loff_t sqe_off = READ_ONCE(sqe->off); loff_t sqe_len = READ_ONCE(sqe->len); loff_t end = sqe_off + sqe_len; - unsigned fsync_flags; + unsigned fsync_flags, flags; struct file *file; int ret, fd; @@ -923,14 +956,23 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, return -EINVAL; fd = READ_ONCE(sqe->fd); - file = fget(fd); + flags = READ_ONCE(sqe->flags); + + if (flags & IOSQE_FIXED_FILE) { + if (unlikely(!ctx->user_files || fd >= ctx->nr_user_files)) + return -EBADF; + file = ctx->user_files[fd]; + } else { + file = fget(fd); + } if (unlikely(!file)) return -EBADF; ret = vfs_fsync_range(file, sqe_off, end > 0 ? end : LLONG_MAX, fsync_flags & IORING_FSYNC_DATASYNC); - fput(file); + if (!(flags & IOSQE_FIXED_FILE)) + fput(file); io_cqring_add_event(ctx, sqe->user_data, ret, 0); io_free_req(req); return 0; @@ -1067,7 +1109,7 @@ 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); @@ -1255,6 +1297,151 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return ring->r.head == 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]); + fput(fpl->fp[i]); + } + + fpl->max = fpl->count = nr; + UNIXCB(skb).fp = fpl; + skb_queue_head(&ctx->ring_sock->sk->sk_receive_queue, skb); + 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 suppor 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; @@ -1521,14 +1708,16 @@ 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); @@ -1886,6 +2075,15 @@ 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
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. Signed-off-by: Jens Axboe <axboe@kernel.dk> --- fs/io_uring.c | 256 ++++++++++++++++++++++++++++++---- include/uapi/linux/io_uring.h | 9 +- 2 files changed, 235 insertions(+), 30 deletions(-)