diff options
Diffstat (limited to 'fs/io_uring.c')
-rw-r--r-- | fs/io_uring.c | 690 |
1 files changed, 355 insertions, 335 deletions
diff --git a/fs/io_uring.c b/fs/io_uring.c index 6f084e3cf835..562e3a1a1bf9 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -330,6 +330,26 @@ struct io_timeout { struct file *file; u64 addr; int flags; + unsigned count; +}; + +struct io_rw { + /* NOTE: kiocb has the file as the first member, so don't do it here */ + struct kiocb kiocb; + u64 addr; + u64 len; +}; + +struct io_connect { + struct file *file; + struct sockaddr __user *addr; + int addr_len; +}; + +struct io_sr_msg { + struct file *file; + struct user_msghdr __user *msg; + int msg_flags; }; struct io_async_connect { @@ -351,7 +371,6 @@ struct io_async_rw { }; struct io_async_ctx { - struct io_uring_sqe sqe; union { struct io_async_rw rw; struct io_async_msghdr msg; @@ -369,15 +388,16 @@ struct io_async_ctx { struct io_kiocb { union { struct file *file; - struct kiocb rw; + struct io_rw rw; struct io_poll_iocb poll; struct io_accept accept; struct io_sync sync; struct io_cancel cancel; struct io_timeout timeout; + struct io_connect connect; + struct io_sr_msg sr_msg; }; - const struct io_uring_sqe *sqe; struct io_async_ctx *io; struct file *ring_file; int ring_fd; @@ -411,7 +431,6 @@ struct io_kiocb { #define REQ_F_INFLIGHT 16384 /* on inflight list */ #define REQ_F_COMP_LOCKED 32768 /* completion under lock */ #define REQ_F_HARDLINK 65536 /* doesn't sever on completion < 0 */ -#define REQ_F_PREPPED 131072 /* request already opcode prepared */ u64 user_data; u32 result; u32 sequence; @@ -609,33 +628,31 @@ static inline bool io_prep_async_work(struct io_kiocb *req, { bool do_hashed = false; - if (req->sqe) { - switch (req->opcode) { - case IORING_OP_WRITEV: - case IORING_OP_WRITE_FIXED: - /* only regular files should be hashed for writes */ - if (req->flags & REQ_F_ISREG) - do_hashed = true; - /* fall-through */ - case IORING_OP_READV: - case IORING_OP_READ_FIXED: - case IORING_OP_SENDMSG: - case IORING_OP_RECVMSG: - case IORING_OP_ACCEPT: - case IORING_OP_POLL_ADD: - case IORING_OP_CONNECT: - /* - * We know REQ_F_ISREG is not set on some of these - * opcodes, but this enables us to keep the check in - * just one place. - */ - if (!(req->flags & REQ_F_ISREG)) - req->work.flags |= IO_WQ_WORK_UNBOUND; - break; - } - if (io_req_needs_user(req)) - req->work.flags |= IO_WQ_WORK_NEEDS_USER; + switch (req->opcode) { + case IORING_OP_WRITEV: + case IORING_OP_WRITE_FIXED: + /* only regular files should be hashed for writes */ + if (req->flags & REQ_F_ISREG) + do_hashed = true; + /* fall-through */ + case IORING_OP_READV: + case IORING_OP_READ_FIXED: + case IORING_OP_SENDMSG: + case IORING_OP_RECVMSG: + case IORING_OP_ACCEPT: + case IORING_OP_POLL_ADD: + case IORING_OP_CONNECT: + /* + * We know REQ_F_ISREG is not set on some of these + * opcodes, but this enables us to keep the check in + * just one place. + */ + if (!(req->flags & REQ_F_ISREG)) + req->work.flags |= IO_WQ_WORK_UNBOUND; + break; } + if (io_req_needs_user(req)) + req->work.flags |= IO_WQ_WORK_NEEDS_USER; *link = io_prep_linked_timeout(req); return do_hashed; @@ -1180,7 +1197,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, ret = 0; list_for_each_entry_safe(req, tmp, &ctx->poll_list, list) { - struct kiocb *kiocb = &req->rw; + struct kiocb *kiocb = &req->rw.kiocb; /* * Move completed entries to our local list. If we find a @@ -1335,7 +1352,7 @@ static inline void req_set_fail_links(struct io_kiocb *req) static void io_complete_rw_common(struct kiocb *kiocb, long res) { - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); if (kiocb->ki_flags & IOCB_WRITE) kiocb_end_write(req); @@ -1347,7 +1364,7 @@ static void io_complete_rw_common(struct kiocb *kiocb, long res) static void io_complete_rw(struct kiocb *kiocb, long res, long res2) { - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); io_complete_rw_common(kiocb, res); io_put_req(req); @@ -1355,7 +1372,7 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2) static struct io_kiocb *__io_complete_rw(struct kiocb *kiocb, long res) { - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); struct io_kiocb *nxt = NULL; io_complete_rw_common(kiocb, res); @@ -1366,7 +1383,7 @@ static struct io_kiocb *__io_complete_rw(struct kiocb *kiocb, long res) static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) { - struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); + struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); if (kiocb->ki_flags & IOCB_WRITE) kiocb_end_write(req); @@ -1400,7 +1417,7 @@ static void io_iopoll_req_issued(struct io_kiocb *req) list_req = list_first_entry(&ctx->poll_list, struct io_kiocb, list); - if (list_req->rw.ki_filp != req->rw.ki_filp) + if (list_req->file != req->file) ctx->poll_multi_file = true; } @@ -1471,11 +1488,11 @@ static bool io_file_supports_async(struct file *file) return false; } -static int io_prep_rw(struct io_kiocb *req, bool force_nonblock) +static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, + bool force_nonblock) { - const struct io_uring_sqe *sqe = req->sqe; struct io_ring_ctx *ctx = req->ctx; - struct kiocb *kiocb = &req->rw; + struct kiocb *kiocb = &req->rw.kiocb; unsigned ioprio; int ret; @@ -1524,6 +1541,12 @@ static int io_prep_rw(struct io_kiocb *req, bool force_nonblock) return -EINVAL; kiocb->ki_complete = io_complete_rw; } + + req->rw.addr = READ_ONCE(sqe->addr); + req->rw.len = READ_ONCE(sqe->len); + /* we own ->private, reuse it for the buffer index */ + req->rw.kiocb.private = (void *) (unsigned long) + READ_ONCE(sqe->buf_index); return 0; } @@ -1557,11 +1580,11 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, struct io_kiocb **nxt, io_rw_done(kiocb, ret); } -static ssize_t io_import_fixed(struct io_ring_ctx *ctx, int rw, - const struct io_uring_sqe *sqe, +static ssize_t io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) { - size_t len = READ_ONCE(sqe->len); + struct io_ring_ctx *ctx = req->ctx; + size_t len = req->rw.len; struct io_mapped_ubuf *imu; unsigned index, buf_index; size_t offset; @@ -1571,13 +1594,13 @@ static ssize_t io_import_fixed(struct io_ring_ctx *ctx, int rw, if (unlikely(!ctx->user_bufs)) return -EFAULT; - buf_index = READ_ONCE(sqe->buf_index); + buf_index = (unsigned long) req->rw.kiocb.private; 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]; - buf_addr = READ_ONCE(sqe->addr); + buf_addr = req->rw.addr; /* overflow */ if (buf_addr + len < buf_addr) @@ -1634,25 +1657,20 @@ static ssize_t io_import_fixed(struct io_ring_ctx *ctx, int rw, static ssize_t io_import_iovec(int rw, struct io_kiocb *req, struct iovec **iovec, struct iov_iter *iter) { - const struct io_uring_sqe *sqe = req->sqe; - void __user *buf = u64_to_user_ptr(READ_ONCE(sqe->addr)); - size_t sqe_len = READ_ONCE(sqe->len); + void __user *buf = u64_to_user_ptr(req->rw.addr); + size_t sqe_len = req->rw.len; u8 opcode; - /* - * We're reading ->opcode for the second time, but the first read - * doesn't care whether it's _FIXED or not, so it doesn't matter - * whether ->opcode changes concurrently. The first read does care - * about whether it is a READ or a WRITE, so we don't trust this read - * for that purpose and instead let the caller pass in the read/write - * flag. - */ opcode = req->opcode; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { *iovec = NULL; - return io_import_fixed(req->ctx, rw, sqe, iter); + return io_import_fixed(req, rw, iter); } + /* buffer index only valid with fixed read/write */ + if (req->rw.kiocb.private) + return -EINVAL; + if (req->io) { struct io_async_rw *iorw = &req->io->rw; @@ -1750,13 +1768,7 @@ static void io_req_map_rw(struct io_kiocb *req, ssize_t io_size, static int io_alloc_async_ctx(struct io_kiocb *req) { req->io = kmalloc(sizeof(*req->io), GFP_KERNEL); - if (req->io) { - memcpy(&req->io->sqe, req->sqe, sizeof(req->io->sqe)); - req->sqe = &req->io->sqe; - return 0; - } - - return 1; + return req->io == NULL; } static void io_rw_async(struct io_wq_work **workptr) @@ -1782,46 +1794,52 @@ static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size, return 0; } -static int io_read_prep(struct io_kiocb *req, struct iovec **iovec, - struct iov_iter *iter, bool force_nonblock) +static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, + bool force_nonblock) { + struct io_async_ctx *io; + struct iov_iter iter; ssize_t ret; - ret = io_prep_rw(req, force_nonblock); + ret = io_prep_rw(req, sqe, force_nonblock); if (ret) return ret; if (unlikely(!(req->file->f_mode & FMODE_READ))) return -EBADF; - return io_import_iovec(READ, req, iovec, iter); + if (!req->io) + return 0; + + io = req->io; + io->rw.iov = io->rw.fast_iov; + req->io = NULL; + ret = io_import_iovec(READ, req, &io->rw.iov, &iter); + req->io = io; + if (ret < 0) + return ret; + + io_req_map_rw(req, ret, io->rw.iov, io->rw.fast_iov, &iter); + return 0; } static int io_read(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; - struct kiocb *kiocb = &req->rw; + struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter iter; - struct file *file; size_t iov_count; ssize_t io_size, ret; - if (!req->io) { - ret = io_read_prep(req, &iovec, &iter, force_nonblock); - if (ret < 0) - return ret; - } else { - ret = io_import_iovec(READ, req, &iovec, &iter); - if (ret < 0) - return ret; - } + ret = io_import_iovec(READ, req, &iovec, &iter); + if (ret < 0) + return ret; /* Ensure we clear previously set non-block flag */ if (!force_nonblock) - req->rw.ki_flags &= ~IOCB_NOWAIT; + req->rw.kiocb.ki_flags &= ~IOCB_NOWAIT; - file = req->file; io_size = ret; if (req->flags & REQ_F_LINK) req->result = io_size; @@ -1830,20 +1848,20 @@ static int io_read(struct io_kiocb *req, struct io_kiocb **nxt, * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so * we know to async punt it even if it was opened O_NONBLOCK */ - if (force_nonblock && !io_file_supports_async(file)) { + if (force_nonblock && !io_file_supports_async(req->file)) { req->flags |= REQ_F_MUST_PUNT; goto copy_iov; } iov_count = iov_iter_count(&iter); - ret = rw_verify_area(READ, file, &kiocb->ki_pos, iov_count); + ret = rw_verify_area(READ, req->file, &kiocb->ki_pos, iov_count); if (!ret) { ssize_t ret2; - if (file->f_op->read_iter) - ret2 = call_read_iter(file, kiocb, &iter); + if (req->file->f_op->read_iter) + ret2 = call_read_iter(req->file, kiocb, &iter); else - ret2 = loop_rw_iter(READ, file, kiocb, &iter); + ret2 = loop_rw_iter(READ, req->file, kiocb, &iter); /* * In case of a short read, punt to async. This can happen @@ -1875,46 +1893,52 @@ out_free: return ret; } -static int io_write_prep(struct io_kiocb *req, struct iovec **iovec, - struct iov_iter *iter, bool force_nonblock) +static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, + bool force_nonblock) { + struct io_async_ctx *io; + struct iov_iter iter; ssize_t ret; - ret = io_prep_rw(req, force_nonblock); + ret = io_prep_rw(req, sqe, force_nonblock); if (ret) return ret; if (unlikely(!(req->file->f_mode & FMODE_WRITE))) return -EBADF; - return io_import_iovec(WRITE, req, iovec, iter); + if (!req->io) + return 0; + + io = req->io; + io->rw.iov = io->rw.fast_iov; + req->io = NULL; + ret = io_import_iovec(WRITE, req, &io->rw.iov, &iter); + req->io = io; + if (ret < 0) + return ret; + + io_req_map_rw(req, ret, io->rw.iov, io->rw.fast_iov, &iter); + return 0; } static int io_write(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; - struct kiocb *kiocb = &req->rw; + struct kiocb *kiocb = &req->rw.kiocb; struct iov_iter iter; - struct file *file; size_t iov_count; ssize_t ret, io_size; - if (!req->io) { - ret = io_write_prep(req, &iovec, &iter, force_nonblock); - if (ret < 0) - return ret; - } else { - ret = io_import_iovec(WRITE, req, &iovec, &iter); - if (ret < 0) - return ret; - } + ret = io_import_iovec(WRITE, req, &iovec, &iter); + if (ret < 0) + return ret; /* Ensure we clear previously set non-block flag */ if (!force_nonblock) - req->rw.ki_flags &= ~IOCB_NOWAIT; + req->rw.kiocb.ki_flags &= ~IOCB_NOWAIT; - file = kiocb->ki_filp; io_size = ret; if (req->flags & REQ_F_LINK) req->result = io_size; @@ -1934,7 +1958,7 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt, goto copy_iov; iov_count = iov_iter_count(&iter); - ret = rw_verify_area(WRITE, file, &kiocb->ki_pos, iov_count); + ret = rw_verify_area(WRITE, req->file, &kiocb->ki_pos, iov_count); if (!ret) { ssize_t ret2; @@ -1946,17 +1970,17 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt, * we return to userspace. */ if (req->flags & REQ_F_ISREG) { - __sb_start_write(file_inode(file)->i_sb, + __sb_start_write(file_inode(req->file)->i_sb, SB_FREEZE_WRITE, true); - __sb_writers_release(file_inode(file)->i_sb, + __sb_writers_release(file_inode(req->file)->i_sb, SB_FREEZE_WRITE); } kiocb->ki_flags |= IOCB_WRITE; - if (file->f_op->write_iter) - ret2 = call_write_iter(file, kiocb, &iter); + if (req->file->f_op->write_iter) + ret2 = call_write_iter(req->file, kiocb, &iter); else - ret2 = loop_rw_iter(WRITE, file, kiocb, &iter); + ret2 = loop_rw_iter(WRITE, req->file, kiocb, &iter); if (!force_nonblock || ret2 != -EAGAIN) { kiocb_done(kiocb, ret2, nxt, req->in_async); } else { @@ -1989,13 +2013,10 @@ static int io_nop(struct io_kiocb *req) return 0; } -static int io_prep_fsync(struct io_kiocb *req) +static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - const struct io_uring_sqe *sqe = req->sqe; struct io_ring_ctx *ctx = req->ctx; - if (req->flags & REQ_F_PREPPED) - return 0; if (!req->file) return -EBADF; @@ -2010,7 +2031,6 @@ static int io_prep_fsync(struct io_kiocb *req) req->sync.off = READ_ONCE(sqe->off); req->sync.len = READ_ONCE(sqe->len); - req->flags |= REQ_F_PREPPED; return 0; } @@ -2036,7 +2056,7 @@ static void io_fsync_finish(struct io_wq_work **workptr) if (io_req_cancelled(req)) return; - ret = vfs_fsync_range(req->rw.ki_filp, req->sync.off, + ret = vfs_fsync_range(req->file, req->sync.off, end > 0 ? end : LLONG_MAX, req->sync.flags & IORING_FSYNC_DATASYNC); if (ret < 0) @@ -2051,11 +2071,6 @@ static int io_fsync(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { struct io_wq_work *work, *old_work; - int ret; - - ret = io_prep_fsync(req); - if (ret) - return ret; /* fsync always requires a blocking context */ if (force_nonblock) { @@ -2071,13 +2086,10 @@ static int io_fsync(struct io_kiocb *req, struct io_kiocb **nxt, return 0; } -static int io_prep_sfr(struct io_kiocb *req) +static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - const struct io_uring_sqe *sqe = req->sqe; struct io_ring_ctx *ctx = req->ctx; - if (req->flags & REQ_F_PREPPED) - return 0; if (!req->file) return -EBADF; @@ -2089,7 +2101,6 @@ static int io_prep_sfr(struct io_kiocb *req) req->sync.off = READ_ONCE(sqe->off); req->sync.len = READ_ONCE(sqe->len); req->sync.flags = READ_ONCE(sqe->sync_range_flags); - req->flags |= REQ_F_PREPPED; return 0; } @@ -2102,7 +2113,7 @@ static void io_sync_file_range_finish(struct io_wq_work **workptr) if (io_req_cancelled(req)) return; - ret = sync_file_range(req->rw.ki_filp, req->sync.off, req->sync.len, + ret = sync_file_range(req->file, req->sync.off, req->sync.len, req->sync.flags); if (ret < 0) req_set_fail_links(req); @@ -2116,11 +2127,6 @@ static int io_sync_file_range(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { struct io_wq_work *work, *old_work; - int ret; - - ret = io_prep_sfr(req); - if (ret) - return ret; /* sync_file_range always requires a blocking context */ if (force_nonblock) { @@ -2149,19 +2155,23 @@ static void io_sendrecv_async(struct io_wq_work **workptr) } #endif -static int io_sendmsg_prep(struct io_kiocb *req, struct io_async_ctx *io) +static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; - struct user_msghdr __user *msg; - unsigned flags; + struct io_sr_msg *sr = &req->sr_msg; + struct io_async_ctx *io = req->io; + + sr->msg_flags = READ_ONCE(sqe->msg_flags); + sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr)); + + if (!io) + return 0; - flags = READ_ONCE(sqe->msg_flags); - msg = (struct user_msghdr __user *)(unsigned long) READ_ONCE(sqe->addr); io->msg.iov = io->msg.fast_iov; - return sendmsg_copy_msghdr(&io->msg.msg, msg, flags, &io->msg.iov); + return sendmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags, + &io->msg.iov); #else - return 0; + return -EOPNOTSUPP; #endif } @@ -2169,7 +2179,6 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; struct io_async_msghdr *kmsg = NULL; struct socket *sock; int ret; @@ -2183,12 +2192,6 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt, struct sockaddr_storage addr; unsigned flags; - flags = READ_ONCE(sqe->msg_flags); - if (flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) - flags |= MSG_DONTWAIT; - if (req->io) { kmsg = &req->io->msg; kmsg->msg.msg_name = &addr; @@ -2197,13 +2200,24 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt, kmsg->iov = kmsg->fast_iov; kmsg->msg.msg_iter.iov = kmsg->iov; } else { + struct io_sr_msg *sr = &req->sr_msg; + kmsg = &io.msg; kmsg->msg.msg_name = &addr; - ret = io_sendmsg_prep(req, &io); + + io.msg.iov = io.msg.fast_iov; + ret = sendmsg_copy_msghdr(&io.msg.msg, sr->msg, + sr->msg_flags, &io.msg.iov); if (ret) - goto out; + return ret; } + flags = req->sr_msg.msg_flags; + if (flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + else if (force_nonblock) + flags |= MSG_DONTWAIT; + ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags); if (force_nonblock && ret == -EAGAIN) { if (req->io) @@ -2218,7 +2232,6 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt, ret = -EINTR; } -out: if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov) kfree(kmsg->iov); io_cqring_add_event(req, ret); @@ -2231,20 +2244,24 @@ out: #endif } -static int io_recvmsg_prep(struct io_kiocb *req, struct io_async_ctx *io) +static int io_recvmsg_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; - struct user_msghdr __user *msg; - unsigned flags; + struct io_sr_msg *sr = &req->sr_msg; + struct io_async_ctx *io = req->io; + + sr->msg_flags = READ_ONCE(sqe->msg_flags); + sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr)); + + if (!io) + return 0; - flags = READ_ONCE(sqe->msg_flags); - msg = (struct user_msghdr __user *)(unsigned long) READ_ONCE(sqe->addr); io->msg.iov = io->msg.fast_iov; - return recvmsg_copy_msghdr(&io->msg.msg, msg, flags, &io->msg.uaddr, - &io->msg.iov); + return recvmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags, + &io->msg.uaddr, &io->msg.iov); #else - return 0; + return -EOPNOTSUPP; #endif } @@ -2252,7 +2269,6 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; struct io_async_msghdr *kmsg = NULL; struct socket *sock; int ret; @@ -2262,19 +2278,10 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt, sock = sock_from_file(req->file, &ret); if (sock) { - struct user_msghdr __user *msg; struct io_async_ctx io; struct sockaddr_storage addr; unsigned flags; - flags = READ_ONCE(sqe->msg_flags); - if (flags & MSG_DONTWAIT) - req->flags |= REQ_F_NOWAIT; - else if (force_nonblock) - flags |= MSG_DONTWAIT; - - msg = (struct user_msghdr __user *) (unsigned long) - READ_ONCE(sqe->addr); if (req->io) { kmsg = &req->io->msg; kmsg->msg.msg_name = &addr; @@ -2283,14 +2290,27 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt, kmsg->iov = kmsg->fast_iov; kmsg->msg.msg_iter.iov = kmsg->iov; } else { + struct io_sr_msg *sr = &req->sr_msg; + kmsg = &io.msg; kmsg->msg.msg_name = &addr; - ret = io_recvmsg_prep(req, &io); + + io.msg.iov = io.msg.fast_iov; + ret = recvmsg_copy_msghdr(&io.msg.msg, sr->msg, + sr->msg_flags, &io.msg.uaddr, + &io.msg.iov); if (ret) - goto out; + return ret; } - ret = __sys_recvmsg_sock(sock, &kmsg->msg, msg, kmsg->uaddr, flags); + flags = req->sr_msg.msg_flags; + if (flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + else if (force_nonblock) + flags |= MSG_DONTWAIT; + + ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.msg, + kmsg->uaddr, flags); if (force_nonblock && ret == -EAGAIN) { if (req->io) return -EAGAIN; @@ -2304,7 +2324,6 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt, ret = -EINTR; } -out: if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov) kfree(kmsg->iov); io_cqring_add_event(req, ret); @@ -2317,25 +2336,19 @@ out: #endif } -static int io_accept_prep(struct io_kiocb *req) +static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; struct io_accept *accept = &req->accept; - if (req->flags & REQ_F_PREPPED) - return 0; - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) return -EINVAL; if (sqe->ioprio || sqe->len || sqe->buf_index) return -EINVAL; - accept->addr = (struct sockaddr __user *) - (unsigned long) READ_ONCE(sqe->addr); - accept->addr_len = (int __user *) (unsigned long) READ_ONCE(sqe->addr2); + accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2)); accept->flags = READ_ONCE(sqe->accept_flags); - req->flags |= REQ_F_PREPPED; return 0; #else return -EOPNOTSUPP; @@ -2383,10 +2396,6 @@ static int io_accept(struct io_kiocb *req, struct io_kiocb **nxt, #if defined(CONFIG_NET) int ret; - ret = io_accept_prep(req); - if (ret) - return ret; - ret = __io_accept(req, nxt, force_nonblock); if (ret == -EAGAIN && force_nonblock) { req->work.func = io_accept_finish; @@ -2400,18 +2409,27 @@ static int io_accept(struct io_kiocb *req, struct io_kiocb **nxt, #endif } -static int io_connect_prep(struct io_kiocb *req, struct io_async_ctx *io) +static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; - struct sockaddr __user *addr; - int addr_len; + struct io_connect *conn = &req->connect; + struct io_async_ctx *io = req->io; + + if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) + return -EINVAL; + if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags) + return -EINVAL; - addr = (struct sockaddr __user *) (unsigned long) READ_ONCE(sqe->addr); - addr_len = READ_ONCE(sqe->addr2); - return move_addr_to_kernel(addr, addr_len, &io->connect.address); + conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); + conn->addr_len = READ_ONCE(sqe->addr2); + + if (!io) + return 0; + + return move_addr_to_kernel(conn->addr, conn->addr_len, + &io->connect.address); #else - return 0; + return -EOPNOTSUPP; #endif } @@ -2419,30 +2437,25 @@ static int io_connect(struct io_kiocb *req, struct io_kiocb **nxt, bool force_nonblock) { #if defined(CONFIG_NET) - const struct io_uring_sqe *sqe = req->sqe; struct io_async_ctx __io, *io; unsigned file_flags; - int addr_len, ret; - - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) - return -EINVAL; - if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags) - return -EINVAL; - - addr_len = READ_ONCE(sqe->addr2); - file_flags = force_nonblock ? O_NONBLOCK : 0; + int ret; if (req->io) { io = req->io; } else { - ret = io_connect_prep(req, &__io); + ret = move_addr_to_kernel(req->connect.addr, + req->connect.addr_len, + &__io.connect.address); if (ret) goto out; io = &__io; } - ret = __sys_connect_file(req->file, &io->connect.address, addr_len, - file_flags); + file_flags = force_nonblock ? O_NONBLOCK : 0; + + ret = __sys_connect_file(req->file, &io->connect.address, + req->connect.addr_len, file_flags); if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) { if (req->io) return -EAGAIN; @@ -2513,12 +2526,9 @@ static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr) return -ENOENT; } -static int io_poll_remove_prep(struct io_kiocb *req) +static int io_poll_remove_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) { - const struct io_uring_sqe *sqe = req->sqe; - - if (req->flags & REQ_F_PREPPED) - return 0; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index || @@ -2526,7 +2536,6 @@ static int io_poll_remove_prep(struct io_kiocb *req) return -EINVAL; req->poll.addr = READ_ONCE(sqe->addr); - req->flags |= REQ_F_PREPPED; return 0; } @@ -2540,10 +2549,6 @@ static int io_poll_remove(struct io_kiocb *req) u64 addr; int ret; - ret = io_poll_remove_prep(req); - if (ret) - return ret; - addr = req->poll.addr; spin_lock_irq(&ctx->completion_lock); ret = io_poll_cancel(ctx, addr); @@ -2681,14 +2686,11 @@ static void io_poll_req_insert(struct io_kiocb *req) hlist_add_head(&req->hash_node, list); } -static int io_poll_add_prep(struct io_kiocb *req) +static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - const struct io_uring_sqe *sqe = req->sqe; struct io_poll_iocb *poll = &req->poll; u16 events; - if (req->flags & REQ_F_PREPPED) - return 0; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->addr || sqe->ioprio || sqe->off || sqe->len || sqe->buf_index) @@ -2696,7 +2698,6 @@ static int io_poll_add_prep(struct io_kiocb *req) if (!poll->file) return -EBADF; - req->flags |= REQ_F_PREPPED; events = READ_ONCE(sqe->poll_events); poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP; return 0; @@ -2709,11 +2710,6 @@ static int io_poll_add(struct io_kiocb *req, struct io_kiocb **nxt) struct io_poll_table ipt; bool cancel = false; __poll_t mask; - int ret; - - ret = io_poll_add_prep(req); - if (ret) - return ret; INIT_IO_WORK(&req->work, io_poll_complete_work); INIT_HLIST_NODE(&req->hash_node); @@ -2832,12 +2828,9 @@ static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) return 0; } -static int io_timeout_remove_prep(struct io_kiocb *req) +static int io_timeout_remove_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) { - const struct io_uring_sqe *sqe = req->sqe; - - if (req->flags & REQ_F_PREPPED) - return 0; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->len) @@ -2848,7 +2841,6 @@ static int io_timeout_remove_prep(struct io_kiocb *req) if (req->timeout.flags) return -EINVAL; - req->flags |= REQ_F_PREPPED; return 0; } @@ -2860,10 +2852,6 @@ static int io_timeout_remove(struct io_kiocb *req) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_timeout_remove_prep(req); - if (ret) - return ret; - spin_lock_irq(&ctx->completion_lock); ret = io_timeout_cancel(ctx, req->timeout.addr); @@ -2877,10 +2865,9 @@ static int io_timeout_remove(struct io_kiocb *req) return 0; } -static int io_timeout_prep(struct io_kiocb *req, struct io_async_ctx *io, +static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, bool is_timeout_link) { - const struct io_uring_sqe *sqe = req->sqe; struct io_timeout_data *data; unsigned flags; @@ -2894,7 +2881,12 @@ static int io_timeout_prep(struct io_kiocb *req, struct io_async_ctx *io, if (flags & ~IORING_TIMEOUT_ABS) return -EINVAL; - data = &io->timeout; + req->timeout.count = READ_ONCE(sqe->off); + + if (!req->io && io_alloc_async_ctx(req)) + return -ENOMEM; + + data = &req->io->timeout; data->req = req; req->flags |= REQ_F_TIMEOUT; @@ -2912,21 +2904,12 @@ static int io_timeout_prep(struct io_kiocb *req, struct io_async_ctx *io, static int io_timeout(struct io_kiocb *req) { - const struct io_uring_sqe *sqe = req->sqe; unsigned count; struct io_ring_ctx *ctx = req->ctx; struct io_timeout_data *data; struct list_head *entry; unsigned span = 0; - int ret; - if (!req->io) { - if (io_alloc_async_ctx(req)) - return -ENOMEM; - ret = io_timeout_prep(req, req->io, false); - if (ret) - return ret; - } data = &req->io->timeout; /* @@ -2934,7 +2917,7 @@ static int io_timeout(struct io_kiocb *req) * timeout event to be satisfied. If it isn't set, then this is * a pure timeout request, sequence isn't used. */ - count = READ_ONCE(sqe->off); + count = req->timeout.count; if (!count) { req->flags |= REQ_F_TIMEOUT_NOSEQ; spin_lock_irq(&ctx->completion_lock); @@ -3052,19 +3035,15 @@ done: io_put_req_find_next(req, nxt); } -static int io_async_cancel_prep(struct io_kiocb *req) +static int io_async_cancel_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) { - const struct io_uring_sqe *sqe = req->sqe; - - if (req->flags & REQ_F_PREPPED) - return 0; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->flags || sqe->ioprio || sqe->off || sqe->len || sqe->cancel_flags) return -EINVAL; - req->flags |= REQ_F_PREPPED; req->cancel.addr = READ_ONCE(sqe->addr); return 0; } @@ -3072,21 +3051,14 @@ static int io_async_cancel_prep(struct io_kiocb *req) static int io_async_cancel(struct io_kiocb *req, struct io_kiocb **nxt) { struct io_ring_ctx *ctx = req->ctx; - int ret; - - ret = io_async_cancel_prep(req); - if (ret) - return ret; io_async_find_and_cancel(ctx, req, req->cancel.addr, nxt, 0); return 0; } -static int io_req_defer_prep(struct io_kiocb *req) +static int io_req_defer_prep(struct io_kiocb *req, + const struct io_uring_sqe *sqe) { - struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; - struct io_async_ctx *io = req->io; - struct iov_iter iter; ssize_t ret = 0; switch (req->opcode) { @@ -3094,61 +3066,47 @@ static int io_req_defer_prep(struct io_kiocb *req) break; case IORING_OP_READV: case IORING_OP_READ_FIXED: - /* ensure prep does right import */ - req->io = NULL; - ret = io_read_prep(req, &iovec, &iter, true); - req->io = io; - if (ret < 0) - break; - io_req_map_rw(req, ret, iovec, inline_vecs, &iter); - ret = 0; + ret = io_read_prep(req, sqe, true); break; case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: - /* ensure prep does right import */ - req->io = NULL; - ret = io_write_prep(req, &iovec, &iter, true); - req->io = io; - if (ret < 0) - break; - io_req_map_rw(req, ret, iovec, inline_vecs, &iter); - ret = 0; + ret = io_write_prep(req, sqe, true); break; case IORING_OP_POLL_ADD: - ret = io_poll_add_prep(req); + ret = io_poll_add_prep(req, sqe); break; case IORING_OP_POLL_REMOVE: - ret = io_poll_remove_prep(req); + ret = io_poll_remove_prep(req, sqe); break; case IORING_OP_FSYNC: - ret = io_prep_fsync(req); + ret = io_prep_fsync(req, sqe); break; case IORING_OP_SYNC_FILE_RANGE: - ret = io_prep_sfr(req); + ret = io_prep_sfr(req, sqe); break; case IORING_OP_SENDMSG: - ret = io_sendmsg_prep(req, io); + ret = io_sendmsg_prep(req, sqe); break; case IORING_OP_RECVMSG: - ret = |