From 8e29da69feade64ec7fe9e1a2824b967c5183a21 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 18 Apr 2022 10:44:00 -0600 Subject: io_uring: add support for IORING_ASYNC_CANCEL_ALL The current cancelation will lookup and cancel the first request it finds based on the key passed in. Add a flag that allows to cancel any request that matches they key. It completes with the number of requests found and canceled, or res < 0 if an error occured. Signed-off-by: Jens Axboe Link: https://lore.kernel.org/r/20220418164402.75259-4-axboe@kernel.dk --- include/uapi/linux/io_uring.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 1845cf7c80ba..476e58a2837f 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -187,6 +187,13 @@ enum { #define IORING_POLL_UPDATE_EVENTS (1U << 1) #define IORING_POLL_UPDATE_USER_DATA (1U << 2) +/* + * ASYNC_CANCEL flags. + * + * IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key + */ +#define IORING_ASYNC_CANCEL_ALL (1U << 0) + /* * IO completion data structure (Completion Queue Entry) */ -- cgit v1.2.3-59-g8ed1b From 4bf94615b8886305199ed5755cb72fea88258d15 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 18 Apr 2022 10:44:01 -0600 Subject: io_uring: allow IORING_OP_ASYNC_CANCEL with 'fd' key Currently sqe->addr must contain the user_data of the request being canceled. Introduce the IORING_ASYNC_CANCEL_FD flag, which tells the kernel that we're keying off the file fd instead for cancelation. This allows canceling any request that a) uses a file, and b) was assigned the file based on the value being passed in. Signed-off-by: Jens Axboe Link: https://lore.kernel.org/r/20220418164402.75259-5-axboe@kernel.dk --- fs/io_uring.c | 67 ++++++++++++++++++++++++++++++++++++++----- include/uapi/linux/io_uring.h | 3 ++ 2 files changed, 63 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index b43cdf1a4555..cf0d5437b77d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -587,6 +587,7 @@ struct io_cancel { struct file *file; u64 addr; u32 flags; + s32 fd; }; struct io_timeout { @@ -992,7 +993,10 @@ struct io_defer_entry { struct io_cancel_data { struct io_ring_ctx *ctx; - u64 data; + union { + u64 data; + struct file *file; + }; u32 flags; int seq; }; @@ -6332,6 +6336,29 @@ static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, bool poll_only, return NULL; } +static struct io_kiocb *io_poll_file_find(struct io_ring_ctx *ctx, + struct io_cancel_data *cd) + __must_hold(&ctx->completion_lock) +{ + struct io_kiocb *req; + int i; + + for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { + struct hlist_head *list; + + list = &ctx->cancel_hash[i]; + hlist_for_each_entry(req, list, hash_node) { + if (req->file != cd->file) + continue; + if (cd->seq == req->work.cancel_seq) + continue; + req->work.cancel_seq = cd->seq; + return req; + } + } + return NULL; +} + static bool io_poll_disarm(struct io_kiocb *req) __must_hold(&ctx->completion_lock) { @@ -6345,8 +6372,12 @@ static bool io_poll_disarm(struct io_kiocb *req) static int io_poll_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd) __must_hold(&ctx->completion_lock) { - struct io_kiocb *req = io_poll_find(ctx, false, cd); + struct io_kiocb *req; + if (cd->flags & IORING_ASYNC_CANCEL_FD) + req = io_poll_file_find(ctx, cd); + else + req = io_poll_find(ctx, false, cd); if (!req) return -ENOENT; io_poll_cancel_req(req); @@ -6796,8 +6827,13 @@ static bool io_cancel_cb(struct io_wq_work *work, void *data) if (req->ctx != cd->ctx) return false; - if (req->cqe.user_data != cd->data) - return false; + if (cd->flags & IORING_ASYNC_CANCEL_FD) { + if (req->file != cd->file) + return false; + } else { + if (req->cqe.user_data != cd->data) + return false; + } if (cd->flags & IORING_ASYNC_CANCEL_ALL) { if (cd->seq == req->work.cancel_seq) return false; @@ -6851,7 +6887,8 @@ static int io_try_cancel(struct io_kiocb *req, struct io_cancel_data *cd) ret = io_poll_cancel(ctx, cd); if (ret != -ENOENT) goto out; - ret = io_timeout_cancel(ctx, cd); + if (!(cd->flags & IORING_ASYNC_CANCEL_FD)) + ret = io_timeout_cancel(ctx, cd); out: spin_unlock(&ctx->completion_lock); return ret; @@ -6862,15 +6899,17 @@ static int io_async_cancel_prep(struct io_kiocb *req, { if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) + if (unlikely(req->flags & REQ_F_BUFFER_SELECT)) return -EINVAL; if (sqe->ioprio || sqe->off || sqe->len || sqe->splice_fd_in) return -EINVAL; req->cancel.addr = READ_ONCE(sqe->addr); req->cancel.flags = READ_ONCE(sqe->cancel_flags); - if (req->cancel.flags & ~IORING_ASYNC_CANCEL_ALL) + if (req->cancel.flags & ~(IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_FD)) return -EINVAL; + if (req->cancel.flags & IORING_ASYNC_CANCEL_FD) + req->cancel.fd = READ_ONCE(sqe->fd); return 0; } @@ -6919,7 +6958,21 @@ static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) }; int ret; + if (cd.flags & IORING_ASYNC_CANCEL_FD) { + if (req->flags & REQ_F_FIXED_FILE) + req->file = io_file_get_fixed(req, req->cancel.fd, + issue_flags); + else + req->file = io_file_get_normal(req, req->cancel.fd); + if (!req->file) { + ret = -EBADF; + goto done; + } + cd.file = req->file; + } + ret = __io_async_cancel(&cd, req, issue_flags); +done: if (ret < 0) req_set_fail(req); io_req_complete_post(req, ret, 0); diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 476e58a2837f..cc7fe82a1798 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -191,8 +191,11 @@ enum { * ASYNC_CANCEL flags. * * IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key + * IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the + * request 'user_data' */ #define IORING_ASYNC_CANCEL_ALL (1U << 0) +#define IORING_ASYNC_CANCEL_FD (1U << 1) /* * IO completion data structure (Completion Queue Entry) -- cgit v1.2.3-59-g8ed1b From 970f256edb8c1259c8ed48d52b38215135396126 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 18 Apr 2022 10:44:02 -0600 Subject: io_uring: add support for IORING_ASYNC_CANCEL_ANY Rather than match on a specific key, be it user_data or file, allow canceling any request that we can lookup. Works like IORING_ASYNC_CANCEL_ALL in that it cancels multiple requests, but it doesn't key off user_data or the file. Can't be set with IORING_ASYNC_CANCEL_FD, as that's a key selector. Only one may be used at the time. Signed-off-by: Jens Axboe Link: https://lore.kernel.org/r/20220418164402.75259-6-axboe@kernel.dk Signed-off-by: Jens Axboe --- fs/io_uring.c | 39 +++++++++++++++++++++++++-------------- include/uapi/linux/io_uring.h | 2 ++ 2 files changed, 27 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index cf0d5437b77d..03134ec070a3 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6348,7 +6348,8 @@ static struct io_kiocb *io_poll_file_find(struct io_ring_ctx *ctx, list = &ctx->cancel_hash[i]; hlist_for_each_entry(req, list, hash_node) { - if (req->file != cd->file) + if (!(cd->flags & IORING_ASYNC_CANCEL_ANY) && + req->file != cd->file) continue; if (cd->seq == req->work.cancel_seq) continue; @@ -6374,7 +6375,7 @@ static int io_poll_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd) { struct io_kiocb *req; - if (cd->flags & IORING_ASYNC_CANCEL_FD) + if (cd->flags & (IORING_ASYNC_CANCEL_FD|IORING_ASYNC_CANCEL_ANY)) req = io_poll_file_find(ctx, cd); else req = io_poll_find(ctx, false, cd); @@ -6543,9 +6544,10 @@ static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx, bool found = false; list_for_each_entry(req, &ctx->timeout_list, timeout.list) { - if (cd->data != req->cqe.user_data) + if (!(cd->flags & IORING_ASYNC_CANCEL_ANY) && + cd->data != req->cqe.user_data) continue; - if (cd->flags & IORING_ASYNC_CANCEL_ALL) { + if (cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY)) { if (cd->seq == req->work.cancel_seq) continue; req->work.cancel_seq = cd->seq; @@ -6827,14 +6829,16 @@ static bool io_cancel_cb(struct io_wq_work *work, void *data) if (req->ctx != cd->ctx) return false; - if (cd->flags & IORING_ASYNC_CANCEL_FD) { + if (cd->flags & IORING_ASYNC_CANCEL_ANY) { + ; + } else if (cd->flags & IORING_ASYNC_CANCEL_FD) { if (req->file != cd->file) return false; } else { if (req->cqe.user_data != cd->data) return false; } - if (cd->flags & IORING_ASYNC_CANCEL_ALL) { + if (cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY)) { if (cd->seq == req->work.cancel_seq) return false; req->work.cancel_seq = cd->seq; @@ -6847,12 +6851,13 @@ static int io_async_cancel_one(struct io_uring_task *tctx, { enum io_wq_cancel cancel_ret; int ret = 0; + bool all; if (!tctx || !tctx->io_wq) return -ENOENT; - cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, cd, - cd->flags & IORING_ASYNC_CANCEL_ALL); + all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); + cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, cd, all); switch (cancel_ret) { case IO_WQ_CANCEL_OK: ret = 0; @@ -6894,6 +6899,9 @@ out: return ret; } +#define CANCEL_FLAGS (IORING_ASYNC_CANCEL_ALL | IORING_ASYNC_CANCEL_FD | \ + IORING_ASYNC_CANCEL_ANY) + static int io_async_cancel_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { @@ -6906,10 +6914,13 @@ static int io_async_cancel_prep(struct io_kiocb *req, req->cancel.addr = READ_ONCE(sqe->addr); req->cancel.flags = READ_ONCE(sqe->cancel_flags); - if (req->cancel.flags & ~(IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_FD)) + if (req->cancel.flags & ~CANCEL_FLAGS) return -EINVAL; - if (req->cancel.flags & IORING_ASYNC_CANCEL_FD) + if (req->cancel.flags & IORING_ASYNC_CANCEL_FD) { + if (req->cancel.flags & IORING_ASYNC_CANCEL_ANY) + return -EINVAL; req->cancel.fd = READ_ONCE(sqe->fd); + } return 0; } @@ -6917,7 +6928,7 @@ static int io_async_cancel_prep(struct io_kiocb *req, static int __io_async_cancel(struct io_cancel_data *cd, struct io_kiocb *req, unsigned int issue_flags) { - bool cancel_all = cd->flags & IORING_ASYNC_CANCEL_ALL; + bool all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY); struct io_ring_ctx *ctx = cd->ctx; struct io_tctx_node *node; int ret, nr = 0; @@ -6926,7 +6937,7 @@ static int __io_async_cancel(struct io_cancel_data *cd, struct io_kiocb *req, ret = io_try_cancel(req, cd); if (ret == -ENOENT) break; - if (!cancel_all) + if (!all) return ret; nr++; } while (1); @@ -6939,13 +6950,13 @@ static int __io_async_cancel(struct io_cancel_data *cd, struct io_kiocb *req, ret = io_async_cancel_one(tctx, cd); if (ret != -ENOENT) { - if (!cancel_all) + if (!all) break; nr++; } } io_ring_submit_unlock(ctx, issue_flags); - return cancel_all ? nr : ret; + return all ? nr : ret; } static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index cc7fe82a1798..980d82eb196e 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -193,9 +193,11 @@ enum { * IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key * IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the * request 'user_data' + * IORING_ASYNC_CANCEL_ANY Match any request */ #define IORING_ASYNC_CANCEL_ALL (1U << 0) #define IORING_ASYNC_CANCEL_FD (1U << 1) +#define IORING_ASYNC_CANCEL_ANY (1U << 2) /* * IO completion data structure (Completion Queue Entry) -- cgit v1.2.3-59-g8ed1b From e9621e2bec80fe63f677a759066a5089b292f43a Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Wed, 23 Mar 2022 08:44:19 -0700 Subject: io_uring: add fsetxattr and setxattr support This adds support to io_uring for the fsetxattr and setxattr API. Signed-off-by: Stefan Roesch Acked-by: Christian Brauner Link: https://lore.kernel.org/r/20220323154420.3301504-4-shr@fb.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 165 ++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/io_uring.h | 6 +- 2 files changed, 170 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index e57d47a23682..bb812d007d30 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -80,6 +80,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -779,6 +780,12 @@ struct io_async_rw { struct wait_page_queue wpq; }; +struct io_xattr { + struct file *file; + struct xattr_ctx ctx; + struct filename *filename; +}; + enum { REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT, REQ_F_IO_DRAIN_BIT = IOSQE_IO_DRAIN_BIT, @@ -943,6 +950,7 @@ struct io_kiocb { struct io_symlink symlink; struct io_hardlink hardlink; struct io_msg msg; + struct io_xattr xattr; }; u8 opcode; @@ -1211,6 +1219,10 @@ static const struct io_op_def io_op_defs[] = { [IORING_OP_MSG_RING] = { .needs_file = 1, }, + [IORING_OP_FSETXATTR] = { + .needs_file = 1 + }, + [IORING_OP_SETXATTR] = {}, }; /* requests with any of those set should undergo io_disarm_next() */ @@ -4190,6 +4202,144 @@ static int io_renameat(struct io_kiocb *req, unsigned int issue_flags) return 0; } +static inline void __io_xattr_finish(struct io_kiocb *req) +{ + struct io_xattr *ix = &req->xattr; + + if (ix->filename) + putname(ix->filename); + + kfree(ix->ctx.kname); + kvfree(ix->ctx.kvalue); +} + +static void io_xattr_finish(struct io_kiocb *req, int ret) +{ + req->flags &= ~REQ_F_NEED_CLEANUP; + + __io_xattr_finish(req); + if (ret < 0) + req_set_fail(req); + + io_req_complete(req, ret); +} + +static int __io_setxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = &req->xattr; + const char __user *name; + int ret; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(sqe->ioprio)) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + ix->filename = NULL; + name = u64_to_user_ptr(READ_ONCE(sqe->addr)); + ix->ctx.cvalue = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + ix->ctx.kvalue = NULL; + ix->ctx.size = READ_ONCE(sqe->len); + ix->ctx.flags = READ_ONCE(sqe->xattr_flags); + + ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL); + if (!ix->ctx.kname) + return -ENOMEM; + + ret = setxattr_copy(name, &ix->ctx); + if (ret) { + kfree(ix->ctx.kname); + return ret; + } + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +static int io_setxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = &req->xattr; + const char __user *path; + int ret; + + ret = __io_setxattr_prep(req, sqe); + if (ret) + return ret; + + path = u64_to_user_ptr(READ_ONCE(sqe->addr3)); + + ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL); + if (IS_ERR(ix->filename)) { + ret = PTR_ERR(ix->filename); + ix->filename = NULL; + } + + return ret; +} + +static int io_fsetxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + return __io_setxattr_prep(req, sqe); +} + +static int __io_setxattr(struct io_kiocb *req, unsigned int issue_flags, + struct path *path) +{ + struct io_xattr *ix = &req->xattr; + int ret; + + ret = mnt_want_write(path->mnt); + if (!ret) { + ret = do_setxattr(mnt_user_ns(path->mnt), path->dentry, &ix->ctx); + mnt_drop_write(path->mnt); + } + + return ret; +} + +static int io_fsetxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = __io_setxattr(req, issue_flags, &req->file->f_path); + io_xattr_finish(req, ret); + + return 0; +} + +static int io_setxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_xattr *ix = &req->xattr; + unsigned int lookup_flags = LOOKUP_FOLLOW; + struct path path; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + +retry: + ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL); + if (!ret) { + ret = __io_setxattr(req, issue_flags, &path); + path_put(&path); + if (retry_estale(ret, lookup_flags)) { + lookup_flags |= LOOKUP_REVAL; + goto retry; + } + } + + io_xattr_finish(req, ret); + return 0; +} + static int io_unlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { @@ -7151,6 +7301,10 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return io_linkat_prep(req, sqe); case IORING_OP_MSG_RING: return io_msg_ring_prep(req, sqe); + case IORING_OP_FSETXATTR: + return io_fsetxattr_prep(req, sqe); + case IORING_OP_SETXATTR: + return io_setxattr_prep(req, sqe); } printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n", @@ -7295,6 +7449,10 @@ static void io_clean_op(struct io_kiocb *req) if (req->statx.filename) putname(req->statx.filename); break; + case IORING_OP_SETXATTR: + case IORING_OP_FSETXATTR: + __io_xattr_finish(req); + break; } } if ((req->flags & REQ_F_POLLED) && req->apoll) { @@ -7451,6 +7609,12 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) case IORING_OP_MSG_RING: ret = io_msg_ring(req, issue_flags); break; + case IORING_OP_FSETXATTR: + ret = io_fsetxattr(req, issue_flags); + break; + case IORING_OP_SETXATTR: + ret = io_setxattr(req, issue_flags); + break; default: ret = -EINVAL; break; @@ -12012,6 +12176,7 @@ static int __init io_uring_init(void) BUILD_BUG_SQE_ELEM(42, __u16, personality); BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in); BUILD_BUG_SQE_ELEM(44, __u32, file_index); + BUILD_BUG_SQE_ELEM(48, __u64, addr3); BUILD_BUG_ON(sizeof(struct io_uring_files_update) != sizeof(struct io_uring_rsrc_update)); diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 980d82eb196e..864bd6a4d4ff 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -45,6 +45,7 @@ struct io_uring_sqe { __u32 rename_flags; __u32 unlink_flags; __u32 hardlink_flags; + __u32 xattr_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -60,7 +61,8 @@ struct io_uring_sqe { __s32 splice_fd_in; __u32 file_index; }; - __u64 __pad2[2]; + __u64 addr3; + __u64 __pad2[1]; }; enum { @@ -145,6 +147,8 @@ enum { IORING_OP_SYMLINKAT, IORING_OP_LINKAT, IORING_OP_MSG_RING, + IORING_OP_FSETXATTR, + IORING_OP_SETXATTR, /* this goes last, obviously */ IORING_OP_LAST, -- cgit v1.2.3-59-g8ed1b From a56834e0fafe0adf7f22a28a5dbec3e8c3031a0e Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Wed, 23 Mar 2022 08:44:20 -0700 Subject: io_uring: add fgetxattr and getxattr support This adds support to io_uring for the fgetxattr and getxattr API. Signed-off-by: Stefan Roesch Acked-by: Christian Brauner Link: https://lore.kernel.org/r/20220323154420.3301504-5-shr@fb.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 129 ++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/io_uring.h | 2 + 2 files changed, 131 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index bb812d007d30..2221fe01b1c4 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1223,6 +1223,10 @@ static const struct io_op_def io_op_defs[] = { .needs_file = 1 }, [IORING_OP_SETXATTR] = {}, + [IORING_OP_FGETXATTR] = { + .needs_file = 1 + }, + [IORING_OP_GETXATTR] = {}, }; /* requests with any of those set should undergo io_disarm_next() */ @@ -4224,6 +4228,119 @@ static void io_xattr_finish(struct io_kiocb *req, int ret) io_req_complete(req, ret); } +static int __io_getxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = &req->xattr; + const char __user *name; + int ret; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (unlikely(sqe->ioprio)) + return -EINVAL; + if (unlikely(req->flags & REQ_F_FIXED_FILE)) + return -EBADF; + + ix->filename = NULL; + ix->ctx.kvalue = NULL; + name = u64_to_user_ptr(READ_ONCE(sqe->addr)); + ix->ctx.cvalue = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + ix->ctx.size = READ_ONCE(sqe->len); + ix->ctx.flags = READ_ONCE(sqe->xattr_flags); + + if (ix->ctx.flags) + return -EINVAL; + + ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL); + if (!ix->ctx.kname) + return -ENOMEM; + + ret = strncpy_from_user(ix->ctx.kname->name, name, + sizeof(ix->ctx.kname->name)); + if (!ret || ret == sizeof(ix->ctx.kname->name)) + ret = -ERANGE; + if (ret < 0) { + kfree(ix->ctx.kname); + return ret; + } + + req->flags |= REQ_F_NEED_CLEANUP; + return 0; +} + +static int io_fgetxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + return __io_getxattr_prep(req, sqe); +} + +static int io_getxattr_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) +{ + struct io_xattr *ix = &req->xattr; + const char __user *path; + int ret; + + ret = __io_getxattr_prep(req, sqe); + if (ret) + return ret; + + path = u64_to_user_ptr(READ_ONCE(sqe->addr3)); + + ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL); + if (IS_ERR(ix->filename)) { + ret = PTR_ERR(ix->filename); + ix->filename = NULL; + } + + return ret; +} + +static int io_fgetxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_xattr *ix = &req->xattr; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + + ret = do_getxattr(mnt_user_ns(req->file->f_path.mnt), + req->file->f_path.dentry, + &ix->ctx); + + io_xattr_finish(req, ret); + return 0; +} + +static int io_getxattr(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_xattr *ix = &req->xattr; + unsigned int lookup_flags = LOOKUP_FOLLOW; + struct path path; + int ret; + + if (issue_flags & IO_URING_F_NONBLOCK) + return -EAGAIN; + +retry: + ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL); + if (!ret) { + ret = do_getxattr(mnt_user_ns(path.mnt), + path.dentry, + &ix->ctx); + + path_put(&path); + if (retry_estale(ret, lookup_flags)) { + lookup_flags |= LOOKUP_REVAL; + goto retry; + } + } + + io_xattr_finish(req, ret); + return 0; +} + static int __io_setxattr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { @@ -7305,6 +7422,10 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return io_fsetxattr_prep(req, sqe); case IORING_OP_SETXATTR: return io_setxattr_prep(req, sqe); + case IORING_OP_FGETXATTR: + return io_fgetxattr_prep(req, sqe); + case IORING_OP_GETXATTR: + return io_getxattr_prep(req, sqe); } printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n", @@ -7451,6 +7572,8 @@ static void io_clean_op(struct io_kiocb *req) break; case IORING_OP_SETXATTR: case IORING_OP_FSETXATTR: + case IORING_OP_GETXATTR: + case IORING_OP_FGETXATTR: __io_xattr_finish(req); break; } @@ -7615,6 +7738,12 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) case IORING_OP_SETXATTR: ret = io_setxattr(req, issue_flags); break; + case IORING_OP_FGETXATTR: + ret = io_fgetxattr(req, issue_flags); + break; + case IORING_OP_GETXATTR: + ret = io_getxattr(req, issue_flags); + break; default: ret = -EINVAL; break; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 864bd6a4d4ff..8ca1d9ae56d6 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -149,6 +149,8 @@ enum { IORING_OP_MSG_RING, IORING_OP_FSETXATTR, IORING_OP_SETXATTR, + IORING_OP_FGETXATTR, + IORING_OP_GETXATTR, /* this goes last, obviously */ IORING_OP_LAST, -- cgit v1.2.3-59-g8ed1b From 1374e08e2d44863c931910797852589803997668 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 12 Apr 2022 14:22:40 -0600 Subject: io_uring: add socket(2) support Supports both regular socket(2) where a normal file descriptor is instantiated when called, or direct descriptors. Link: https://lore.kernel.org/r/20220412202240.234207-3-axboe@kernel.dk Signed-off-by: Jens Axboe --- fs/io_uring.c | 76 +++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/io_uring.h | 1 + 2 files changed, 77 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 2221fe01b1c4..bf95ef9240e5 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -576,6 +576,16 @@ struct io_accept { unsigned long nofile; }; +struct io_socket { + struct file *file; + int domain; + int type; + int protocol; + int flags; + u32 file_slot; + unsigned long nofile; +}; + struct io_sync { struct file *file; loff_t len; @@ -951,6 +961,7 @@ struct io_kiocb { struct io_hardlink hardlink; struct io_msg msg; struct io_xattr xattr; + struct io_socket sock; }; u8 opcode; @@ -1227,6 +1238,9 @@ static const struct io_op_def io_op_defs[] = { .needs_file = 1 }, [IORING_OP_GETXATTR] = {}, + [IORING_OP_SOCKET] = { + .audit_skip = 1, + }, }; /* requests with any of those set should undergo io_disarm_next() */ @@ -6017,6 +6031,62 @@ static int io_accept(struct io_kiocb *req, unsigned int issue_flags) return 0; } +static int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_socket *sock = &req->sock; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->addr || sqe->rw_flags || sqe->buf_index) + return -EINVAL; + + sock->domain = READ_ONCE(sqe->fd); + sock->type = READ_ONCE(sqe->off); + sock->protocol = READ_ONCE(sqe->len); + sock->file_slot = READ_ONCE(sqe->file_index); + sock->nofile = rlimit(RLIMIT_NOFILE); + + sock->flags = sock->type & ~SOCK_TYPE_MASK; + if (sock->file_slot && (sock->flags & SOCK_CLOEXEC)) + return -EINVAL; + if (sock->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) + return -EINVAL; + return 0; +} + +static int io_socket(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_socket *sock = &req->sock; + bool fixed = !!sock->file_slot; + struct file *file; + int ret, fd; + + if (!fixed) { + fd = __get_unused_fd_flags(sock->flags, sock->nofile); + if (unlikely(fd < 0)) + return fd; + } + file = __sys_socket_file(sock->domain, sock->type, sock->protocol); + if (IS_ERR(file)) { + if (!fixed) + put_unused_fd(fd); + ret = PTR_ERR(file); + if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK)) + return -EAGAIN; + if (ret == -ERESTARTSYS) + ret = -EINTR; + req_set_fail(req); + } else if (!fixed) { + fd_install(fd, file); + ret = fd; + } else { + ret = io_install_fixed_file(req, file, issue_flags, + sock->file_slot - 1); + } + __io_req_complete(req, issue_flags, ret, 0); + return 0; +} + static int io_connect_prep_async(struct io_kiocb *req) { struct io_async_connect *io = req->async_data; @@ -6105,6 +6175,7 @@ IO_NETOP_PREP_ASYNC(sendmsg); IO_NETOP_PREP_ASYNC(recvmsg); IO_NETOP_PREP_ASYNC(connect); IO_NETOP_PREP(accept); +IO_NETOP_PREP(socket); IO_NETOP_FN(send); IO_NETOP_FN(recv); #endif /* CONFIG_NET */ @@ -7426,6 +7497,8 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) return io_fgetxattr_prep(req, sqe); case IORING_OP_GETXATTR: return io_getxattr_prep(req, sqe); + case IORING_OP_SOCKET: + return io_socket_prep(req, sqe); } printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n", @@ -7744,6 +7817,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) case IORING_OP_GETXATTR: ret = io_getxattr(req, issue_flags); break; + case IORING_OP_SOCKET: + ret = io_socket(req, issue_flags); + break; default: ret = -EINVAL; break; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 8ca1d9ae56d6..5fb52bf32435 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -151,6 +151,7 @@ enum { IORING_OP_SETXATTR, IORING_OP_FGETXATTR, IORING_OP_GETXATTR, + IORING_OP_SOCKET, /* this goes last, obviously */ IORING_OP_LAST, -- cgit v1.2.3-59-g8ed1b From cc51eaa8b530bf070e76847a717adcbf603469b7 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 26 Apr 2022 01:29:04 -0700 Subject: io_uring: add type to op enum It is useful to have a type enum for opcodes, to allow the compiler to assert that every value is used in a switch statement. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220426082907.3600028-2-dylany@fb.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 5fb52bf32435..49d1f3994f8d 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -105,7 +105,7 @@ enum { #define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */ #define IORING_SETUP_SUBMIT_ALL (1U << 7) /* continue submit on error */ -enum { +enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, IORING_OP_WRITEV, -- cgit v1.2.3-59-g8ed1b