From 6371c03ee4a95b694f88d1ca4f822e87ee752901 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 11 Sep 2023 13:46:07 -0600 Subject: [PATCH 1/7] io_uring/rw: mark readv/writev as vectored in the opcode definition This is cleaner than gating on the opcode type, particularly as more read/write type opcodes may be added. Then we can use that for the data import, and for __io_read() on whether or not we need to copy state. Reviewed-by: Gabriel Krisman Bertazi Signed-off-by: Jens Axboe Conflicts: io_uring/rw.c [because of ("io_uring: add io_file_can_poll() helper") merged before] (cherry picked from commit d2d778fbf9964e4e5b8d7420eba8ec5ce938e794) Signed-off-by: Wentao Guan --- io_uring/opdef.c | 2 ++ io_uring/opdef.h | 2 ++ io_uring/rw.c | 10 ++++++---- 3 files changed, 10 insertions(+), 4 deletions(-) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 2d0a7db940fdb..d27d9454440be 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -63,6 +63,7 @@ const struct io_issue_def io_issue_defs[] = { .ioprio = 1, .iopoll = 1, .iopoll_queue = 1, + .vectored = 1, .prep = io_prep_rw, .issue = io_read, }, @@ -76,6 +77,7 @@ const struct io_issue_def io_issue_defs[] = { .ioprio = 1, .iopoll = 1, .iopoll_queue = 1, + .vectored = 1, .prep = io_prep_rw, .issue = io_write, }, diff --git a/io_uring/opdef.h b/io_uring/opdef.h index c22c8696e749b..9e5435ec27d00 100644 --- a/io_uring/opdef.h +++ b/io_uring/opdef.h @@ -29,6 +29,8 @@ struct io_issue_def { unsigned iopoll_queue : 1; /* opcode specific path will handle ->async_data allocation if needed */ unsigned manual_alloc : 1; + /* vectored opcode, set if 1) vectored, and 2) handler needs to know */ + unsigned vectored : 1; int (*issue)(struct io_kiocb *, unsigned int); int (*prep)(struct io_kiocb *, const struct io_uring_sqe *); diff --git a/io_uring/rw.c b/io_uring/rw.c index 4ff3442ac2eee..05d30b2cfe4ec 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -392,8 +392,7 @@ static struct iovec *__io_import_iovec(int ddir, struct io_kiocb *req, buf = u64_to_user_ptr(rw->addr); sqe_len = rw->len; - if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE || - (req->flags & REQ_F_BUFFER_SELECT)) { + if (!io_issue_defs[opcode].vectored || req->flags & REQ_F_BUFFER_SELECT) { if (io_do_buffer_select(req)) { buf = io_buffer_select(req, &sqe_len, issue_flags); if (!buf) @@ -792,8 +791,11 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags) if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) { req->flags &= ~REQ_F_REISSUE; - /* if we can poll, just do that */ - if (req->opcode == IORING_OP_READ && io_file_can_poll(req)) + /* + * If we can poll, just do that. For a vectored read, we'll + * need to copy state first. + */ + if (io_file_can_poll(req) && !io_issue_defs[req->opcode].vectored) return -EAGAIN; /* IOPOLL retry should happen for io-wq threads */ if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL)) From 59efbace6a3fc512a02e2976a5a6123f1169863b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 11 Sep 2023 13:35:42 -0600 Subject: [PATCH 2/7] io_uring/rw: add support for IORING_OP_READ_MULTISHOT This behaves like IORING_OP_READ, except: 1) It only supports pollable files (eg pipes, sockets, etc). Note that for sockets, you probably want to use recv/recvmsg with multishot instead. 2) It supports multishot mode, meaning it will repeatedly trigger a read and fill a buffer when data is available. This allows similar use to recv/recvmsg but on non-sockets, where a single request will repeatedly post a CQE whenever data is read from it. 3) Because of #2, it must be used with provided buffers. This is uniformly true across any request type that supports multishot and transfers data, with the reason being that it's obviously not possible to pass in a single buffer for the data, as multiple reads may very well trigger before an application has a chance to process previous CQEs and the data passed from them. Reviewed-by: Gabriel Krisman Bertazi Signed-off-by: Jens Axboe Conflicts: io_uring/rw.c (cherry picked from commit fc68fcda049108478ee4704d8a3ad3e05cc72fd0) Signed-off-by: Wentao Guan --- include/uapi/linux/io_uring.h | 1 + io_uring/opdef.c | 13 ++++++- io_uring/rw.c | 67 +++++++++++++++++++++++++++++++++++ io_uring/rw.h | 2 ++ 4 files changed, 82 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 333769bc6abf0..9d97d0ff1c4f6 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -240,6 +240,7 @@ enum io_uring_op { IORING_OP_URING_CMD, IORING_OP_SEND_ZC, IORING_OP_SENDMSG_ZC, + IORING_OP_READ_MULTISHOT, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/opdef.c b/io_uring/opdef.c index d27d9454440be..c604a72f6467b 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -431,9 +431,17 @@ const struct io_issue_def io_issue_defs[] = { .prep = io_eopnotsupp_prep, #endif }, + [IORING_OP_READ_MULTISHOT] = { + .needs_file = 1, + .unbound_nonreg_file = 1, + .pollin = 1, + .buffer_select = 1, + .audit_skip = 1, + .prep = io_read_mshot_prep, + .issue = io_read_mshot, + }, }; - const struct io_cold_def io_cold_defs[] = { [IORING_OP_NOP] = { .name = "NOP", @@ -651,6 +659,9 @@ const struct io_cold_def io_cold_defs[] = { .fail = io_sendrecv_fail, #endif }, + [IORING_OP_READ_MULTISHOT] = { + .name = "READ_MULTISHOT", + }, }; const char *io_uring_get_opcode(u8 opcode) diff --git a/io_uring/rw.c b/io_uring/rw.c index 05d30b2cfe4ec..6f04458fb82e0 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -133,6 +133,22 @@ int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) return 0; } +/* + * Multishot read is prepared just like a normal read/write request, only + * difference is that we set the MULTISHOT flag. + */ +int io_read_mshot_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + int ret; + + ret = io_prep_rw(req, sqe); + if (unlikely(ret)) + return ret; + + req->flags |= REQ_F_APOLL_MULTISHOT; + return 0; +} + void io_readv_writev_cleanup(struct io_kiocb *req) { struct io_async_rw *io = req->async_data; @@ -890,6 +906,57 @@ int io_read(struct io_kiocb *req, unsigned int issue_flags) return ret; } +int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags) +{ + unsigned int cflags = 0; + int ret; + + /* + * Multishot MUST be used on a pollable file + */ + if (!file_can_poll(req->file)) + return -EBADFD; + + ret = __io_read(req, issue_flags); + + /* + * If we get -EAGAIN, recycle our buffer and just let normal poll + * handling arm it. + */ + if (ret == -EAGAIN) { + io_kbuf_recycle(req, issue_flags); + return -EAGAIN; + } + + /* + * Any successful return value will keep the multishot read armed. + */ + if (ret > 0) { + /* + * Put our buffer and post a CQE. If we fail to post a CQE, then + * jump to the termination path. This request is then done. + */ + cflags = io_put_kbuf(req, issue_flags); + + if (io_fill_cqe_req_aux(req, + issue_flags & IO_URING_F_COMPLETE_DEFER, + ret, cflags | IORING_CQE_F_MORE)) { + if (issue_flags & IO_URING_F_MULTISHOT) + return IOU_ISSUE_SKIP_COMPLETE; + return -EAGAIN; + } + } + + /* + * Either an error, or we've hit overflow posting the CQE. For any + * multishot request, hitting overflow will terminate it. + */ + io_req_set_res(req, ret, cflags); + if (issue_flags & IO_URING_F_MULTISHOT) + return IOU_STOP_MULTISHOT; + return IOU_OK; +} + static bool io_kiocb_start_write(struct io_kiocb *req, struct kiocb *kiocb) { struct inode *inode; diff --git a/io_uring/rw.h b/io_uring/rw.h index 4b89f9659366a..c5aed03d42a4d 100644 --- a/io_uring/rw.h +++ b/io_uring/rw.h @@ -23,3 +23,5 @@ int io_writev_prep_async(struct io_kiocb *req); void io_readv_writev_cleanup(struct io_kiocb *req); void io_rw_fail(struct io_kiocb *req); void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts); +int io_read_mshot_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags); From 50405edfdab0532527c6864c74cbbbe716961b08 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 11 Jul 2023 10:31:10 -0600 Subject: [PATCH 3/7] exit: abstract out should_wake helper for child_wait_callback() Abstract out the helper that decides if we should wake up following a wake_up() callback on our internal waitqueue. No functional changes intended in this patch. Acked-by: Christian Brauner Signed-off-by: Jens Axboe (cherry picked from commit 9d900d4ea352069de8728f11fe4b20051d64cc20) Signed-off-by: Wentao Guan --- kernel/exit.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/kernel/exit.c b/kernel/exit.c index 78ddb76f203c6..e2ac44bb64670 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1529,6 +1529,17 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk) return 0; } +static bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p) +{ + if (!eligible_pid(wo, p)) + return false; + + if ((wo->wo_flags & __WNOTHREAD) && wo->child_wait.private != p->parent) + return false; + + return true; +} + static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { @@ -1536,13 +1547,10 @@ static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode, child_wait); struct task_struct *p = key; - if (!eligible_pid(wo, p)) - return 0; + if (pid_child_should_wake(wo, p)) + return default_wake_function(wait, mode, sync, key); - if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent) - return 0; - - return default_wake_function(wait, mode, sync, key); + return 0; } void __wake_up_parent(struct task_struct *p, struct task_struct *parent) From e94462432893735b84417413baaf2d314d2d5cf4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 11 Jul 2023 10:34:37 -0600 Subject: [PATCH 4/7] exit: move core of do_wait() into helper Rather than have a maze of gotos, put the actual logic in __do_wait() and have do_wait() loop deal with waitqueue setup/teardown and whether to call __do_wait() again. No functional changes intended in this patch. Acked-by: Christian Brauner Signed-off-by: Jens Axboe (cherry picked from commit 06a101ca45b296fe951692620b0bc49abf90c368) Signed-off-by: Wentao Guan --- kernel/exit.c | 51 +++++++++++++++++++++++++++++++-------------------- 1 file changed, 31 insertions(+), 20 deletions(-) diff --git a/kernel/exit.c b/kernel/exit.c index e2ac44bb64670..67f334ac5a922 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1599,16 +1599,10 @@ static int do_wait_pid(struct wait_opts *wo) return 0; } -static long do_wait(struct wait_opts *wo) +static long __do_wait(struct wait_opts *wo) { - int retval; - - trace_sched_process_wait(wo->wo_pid); + long retval; - init_waitqueue_func_entry(&wo->child_wait, child_wait_callback); - wo->child_wait.private = current; - add_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); -repeat: /* * If there is nothing that can match our criteria, just get out. * We will clear ->notask_error to zero if we see any child that @@ -1620,24 +1614,23 @@ static long do_wait(struct wait_opts *wo) (!wo->wo_pid || !pid_has_task(wo->wo_pid, wo->wo_type))) goto notask; - set_current_state(TASK_INTERRUPTIBLE); read_lock(&tasklist_lock); if (wo->wo_type == PIDTYPE_PID) { retval = do_wait_pid(wo); if (retval) - goto end; + return retval; } else { struct task_struct *tsk = current; do { retval = do_wait_thread(wo, tsk); if (retval) - goto end; + return retval; retval = ptrace_do_wait(wo, tsk); if (retval) - goto end; + return retval; if (wo->wo_flags & __WNOTHREAD) break; @@ -1647,14 +1640,32 @@ static long do_wait(struct wait_opts *wo) notask: retval = wo->notask_error; - if (!retval && !(wo->wo_flags & WNOHANG)) { - retval = -ERESTARTSYS; - if (!signal_pending(current)) { - schedule(); - goto repeat; - } - } -end: + if (!retval && !(wo->wo_flags & WNOHANG)) + return -ERESTARTSYS; + + return retval; +} + +static long do_wait(struct wait_opts *wo) +{ + int retval; + + trace_sched_process_wait(wo->wo_pid); + + init_waitqueue_func_entry(&wo->child_wait, child_wait_callback); + wo->child_wait.private = current; + add_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); + + do { + set_current_state(TASK_INTERRUPTIBLE); + retval = __do_wait(wo); + if (retval != -ERESTARTSYS) + break; + if (signal_pending(current)) + break; + schedule(); + } while (1); + __set_current_state(TASK_RUNNING); remove_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); return retval; From d83c8b4fe3ee4585b7488ad09dc5cac1eecffb9e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 11 Jul 2023 10:38:23 -0600 Subject: [PATCH 5/7] exit: add kernel_waitid_prepare() helper Move the setup logic out of kernel_waitid(), and into a separate helper. No functional changes intended in this patch. Signed-off-by: Jens Axboe (cherry picked from commit eda7e9d409ce16960d5ed28bedf8a33b2667a93c) Signed-off-by: Wentao Guan --- kernel/exit.c | 38 +++++++++++++++++++++++++------------- 1 file changed, 25 insertions(+), 13 deletions(-) diff --git a/kernel/exit.c b/kernel/exit.c index 67f334ac5a922..ced2be79dbcc8 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1671,14 +1671,13 @@ static long do_wait(struct wait_opts *wo) return retval; } -static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop, - int options, struct rusage *ru) +static int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid, + struct waitid_info *infop, int options, + struct rusage *ru) { - struct wait_opts wo; + unsigned int f_flags = 0; struct pid *pid = NULL; enum pid_type type; - long ret; - unsigned int f_flags = 0; if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED| __WNOTHREAD|__WCLONE|__WALL)) @@ -1721,19 +1720,32 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop, return -EINVAL; } - wo.wo_type = type; - wo.wo_pid = pid; - wo.wo_flags = options; - wo.wo_info = infop; - wo.wo_rusage = ru; + wo->wo_type = type; + wo->wo_pid = pid; + wo->wo_flags = options; + wo->wo_info = infop; + wo->wo_rusage = ru; if (f_flags & O_NONBLOCK) - wo.wo_flags |= WNOHANG; + wo->wo_flags |= WNOHANG; + + return 0; +} + +static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop, + int options, struct rusage *ru) +{ + struct wait_opts wo; + long ret; + + ret = kernel_waitid_prepare(&wo, which, upid, infop, options, ru); + if (ret) + return ret; ret = do_wait(&wo); - if (!ret && !(options & WNOHANG) && (f_flags & O_NONBLOCK)) + if (!ret && !(options & WNOHANG) && (wo.wo_flags & WNOHANG)) ret = -EAGAIN; - put_pid(pid); + put_pid(wo.wo_pid); return ret; } From daccbf33220d121a64b9feffd334b20dc9a53c59 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 11 Jul 2023 10:40:31 -0600 Subject: [PATCH 6/7] exit: add internal include file with helpers Move struct wait_opts and waitid_info into kernel/exit.h, and include function declarations for the recently added helpers. Make them non-static as well. This is in preparation for adding a waitid operation through io_uring. With the abtracted helpers, this is now possible. Signed-off-by: Jens Axboe (cherry picked from commit 2e521a2064bf8b26cf178c0f7644a70ed1a512fa) Signed-off-by: Wentao Guan --- kernel/exit.c | 32 +++++++------------------------- kernel/exit.h | 30 ++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 25 deletions(-) create mode 100644 kernel/exit.h diff --git a/kernel/exit.c b/kernel/exit.c index ced2be79dbcc8..882361f4fbca8 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -77,6 +77,8 @@ #include #endif +#include "exit.h" + /* * The default value should be high enough to not crash a system that randomly * crashes its kernel from time to time, but low enough to at least not permit @@ -1046,26 +1048,6 @@ SYSCALL_DEFINE1(exit_group, int, error_code) return 0; } -struct waitid_info { - pid_t pid; - uid_t uid; - int status; - int cause; -}; - -struct wait_opts { - enum pid_type wo_type; - int wo_flags; - struct pid *wo_pid; - - struct waitid_info *wo_info; - int wo_stat; - struct rusage *wo_rusage; - - wait_queue_entry_t child_wait; - int notask_error; -}; - static int eligible_pid(struct wait_opts *wo, struct task_struct *p) { return wo->wo_type == PIDTYPE_MAX || @@ -1529,7 +1511,7 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk) return 0; } -static bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p) +bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p) { if (!eligible_pid(wo, p)) return false; @@ -1599,7 +1581,7 @@ static int do_wait_pid(struct wait_opts *wo) return 0; } -static long __do_wait(struct wait_opts *wo) +long __do_wait(struct wait_opts *wo) { long retval; @@ -1671,9 +1653,9 @@ static long do_wait(struct wait_opts *wo) return retval; } -static int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid, - struct waitid_info *infop, int options, - struct rusage *ru) +int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid, + struct waitid_info *infop, int options, + struct rusage *ru) { unsigned int f_flags = 0; struct pid *pid = NULL; diff --git a/kernel/exit.h b/kernel/exit.h new file mode 100644 index 0000000000000..278faa26a6532 --- /dev/null +++ b/kernel/exit.h @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef LINUX_WAITID_H +#define LINUX_WAITID_H + +struct waitid_info { + pid_t pid; + uid_t uid; + int status; + int cause; +}; + +struct wait_opts { + enum pid_type wo_type; + int wo_flags; + struct pid *wo_pid; + + struct waitid_info *wo_info; + int wo_stat; + struct rusage *wo_rusage; + + wait_queue_entry_t child_wait; + int notask_error; +}; + +bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p); +long __do_wait(struct wait_opts *wo); +int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid, + struct waitid_info *infop, int options, + struct rusage *ru); +#endif From b6407e61bf460bb50e93d0483e67f4c82e3a10a8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 10 Jul 2023 16:14:37 -0600 Subject: [PATCH 7/7] io_uring: add IORING_OP_WAITID support This adds support for an async version of waitid(2), in a fully async version. If an event isn't immediately available, wait for a callback to trigger a retry. The format of the sqe is as follows: sqe->len The 'which', the idtype being queried/waited for. sqe->fd The 'pid' (or id) being waited for. sqe->file_index The 'options' being set. sqe->addr2 A pointer to siginfo_t, if any, being filled in. buf_index, add3, and waitid_flags are reserved/unused for now. waitid_flags will be used for options for this request type. One interesting use case may be to add multi-shot support, so that the request stays armed and posts a notification every time a monitored process state change occurs. Note that this does not support rusage, on Arnd's recommendation. See the waitid(2) man page for details on the arguments. Signed-off-by: Jens Axboe (cherry picked from commit f31ecf671ddc498f20219453395794ff2383e06b) Signed-off-by: Wentao Guan --- include/linux/io_uring_types.h | 2 + include/uapi/linux/io_uring.h | 2 + io_uring/Makefile | 3 +- io_uring/cancel.c | 5 + io_uring/io_uring.c | 3 + io_uring/opdef.c | 9 + io_uring/waitid.c | 372 +++++++++++++++++++++++++++++++++ io_uring/waitid.h | 15 ++ 8 files changed, 410 insertions(+), 1 deletion(-) create mode 100644 io_uring/waitid.c create mode 100644 io_uring/waitid.h diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index dad2f9e4d53d6..85dbb3b6baa2a 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -312,6 +312,8 @@ struct io_ring_ctx { struct list_head cq_overflow_list; struct io_hash_table cancel_table; + struct hlist_head waitid_list; + const struct cred *sq_creds; /* cred used for __io_sq_thread() */ struct io_sq_data *sq_data; /* if using sq thread polling */ diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 9d97d0ff1c4f6..55a71c7178a81 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -65,6 +65,7 @@ struct io_uring_sqe { __u32 xattr_flags; __u32 msg_ring_flags; __u32 uring_cmd_flags; + __u32 waitid_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -241,6 +242,7 @@ enum io_uring_op { IORING_OP_SEND_ZC, IORING_OP_SENDMSG_ZC, IORING_OP_READ_MULTISHOT, + IORING_OP_WAITID, /* this goes last, obviously */ IORING_OP_LAST, diff --git a/io_uring/Makefile b/io_uring/Makefile index 8cc8e5387a75e..7bd64e4425673 100644 --- a/io_uring/Makefile +++ b/io_uring/Makefile @@ -7,5 +7,6 @@ obj-$(CONFIG_IO_URING) += io_uring.o xattr.o nop.o fs.o splice.o \ openclose.o uring_cmd.o epoll.o \ statx.o net.o msg_ring.o timeout.o \ sqpoll.o fdinfo.o tctx.o poll.o \ - cancel.o kbuf.o rsrc.o rw.o opdef.o notif.o + cancel.o kbuf.o rsrc.o rw.o opdef.o \ + notif.o waitid.o obj-$(CONFIG_IO_WQ) += io-wq.o diff --git a/io_uring/cancel.c b/io_uring/cancel.c index a5d51471feebb..0b7d91e706a3a 100644 --- a/io_uring/cancel.c +++ b/io_uring/cancel.c @@ -15,6 +15,7 @@ #include "tctx.h" #include "poll.h" #include "timeout.h" +#include "waitid.h" #include "cancel.h" struct io_cancel { @@ -119,6 +120,10 @@ int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd, if (ret != -ENOENT) return ret; + ret = io_waitid_cancel(ctx, cd, issue_flags); + if (ret != -ENOENT) + return ret; + spin_lock(&ctx->completion_lock); if (!(cd->flags & IORING_ASYNC_CANCEL_FD)) ret = io_timeout_cancel(ctx, cd); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 712c724a7444c..d1d19b9bde2bf 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -91,6 +91,7 @@ #include "cancel.h" #include "net.h" #include "notif.h" +#include "waitid.h" #include "timeout.h" #include "poll.h" @@ -337,6 +338,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_LIST_HEAD(&ctx->tctx_list); ctx->submit_state.free_list.next = NULL; INIT_WQ_LIST(&ctx->locked_free_list); + INIT_HLIST_HEAD(&ctx->waitid_list); INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); INIT_WQ_LIST(&ctx->submit_state.compl_reqs); return ctx; @@ -3416,6 +3418,7 @@ static __cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx, ret |= io_cancel_defer_files(ctx, task, cancel_all); mutex_lock(&ctx->uring_lock); ret |= io_poll_remove_all(ctx, task, cancel_all); + ret |= io_waitid_remove_all(ctx, task, cancel_all); mutex_unlock(&ctx->uring_lock); ret |= io_kill_timeouts(ctx, task, cancel_all); if (task) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index c604a72f6467b..3bb473314d26b 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -33,6 +33,7 @@ #include "poll.h" #include "cancel.h" #include "rw.h" +#include "waitid.h" static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags) { @@ -440,6 +441,10 @@ const struct io_issue_def io_issue_defs[] = { .prep = io_read_mshot_prep, .issue = io_read_mshot, }, + [IORING_OP_WAITID] = { + .prep = io_waitid_prep, + .issue = io_waitid, + }, }; const struct io_cold_def io_cold_defs[] = { @@ -662,6 +667,10 @@ const struct io_cold_def io_cold_defs[] = { [IORING_OP_READ_MULTISHOT] = { .name = "READ_MULTISHOT", }, + [IORING_OP_WAITID] = { + .name = "WAITID", + .async_size = sizeof(struct io_waitid_async), + }, }; const char *io_uring_get_opcode(u8 opcode) diff --git a/io_uring/waitid.c b/io_uring/waitid.c new file mode 100644 index 0000000000000..6f851978606d9 --- /dev/null +++ b/io_uring/waitid.c @@ -0,0 +1,372 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Support for async notification of waitid + */ +#include +#include +#include +#include +#include +#include + +#include + +#include "io_uring.h" +#include "cancel.h" +#include "waitid.h" +#include "../kernel/exit.h" + +static void io_waitid_cb(struct io_kiocb *req, struct io_tw_state *ts); + +#define IO_WAITID_CANCEL_FLAG BIT(31) +#define IO_WAITID_REF_MASK GENMASK(30, 0) + +struct io_waitid { + struct file *file; + int which; + pid_t upid; + int options; + atomic_t refs; + struct wait_queue_head *head; + struct siginfo __user *infop; + struct waitid_info info; +}; + +static void io_waitid_free(struct io_kiocb *req) +{ + struct io_waitid_async *iwa = req->async_data; + + put_pid(iwa->wo.wo_pid); + kfree(req->async_data); + req->async_data = NULL; + req->flags &= ~REQ_F_ASYNC_DATA; +} + +#ifdef CONFIG_COMPAT +static bool io_waitid_compat_copy_si(struct io_waitid *iw, int signo) +{ + struct compat_siginfo __user *infop; + bool ret; + + infop = (struct compat_siginfo __user *) iw->infop; + + if (!user_write_access_begin(infop, sizeof(*infop))) + return false; + + unsafe_put_user(signo, &infop->si_signo, Efault); + unsafe_put_user(0, &infop->si_errno, Efault); + unsafe_put_user(iw->info.cause, &infop->si_code, Efault); + unsafe_put_user(iw->info.pid, &infop->si_pid, Efault); + unsafe_put_user(iw->info.uid, &infop->si_uid, Efault); + unsafe_put_user(iw->info.status, &infop->si_status, Efault); + ret = true; +done: + user_write_access_end(); + return ret; +Efault: + ret = false; + goto done; +} +#endif + +static bool io_waitid_copy_si(struct io_kiocb *req, int signo) +{ + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + bool ret; + + if (!iw->infop) + return true; + +#ifdef CONFIG_COMPAT + if (req->ctx->compat) + return io_waitid_compat_copy_si(iw, signo); +#endif + + if (!user_write_access_begin(iw->infop, sizeof(*iw->infop))) + return false; + + unsafe_put_user(signo, &iw->infop->si_signo, Efault); + unsafe_put_user(0, &iw->infop->si_errno, Efault); + unsafe_put_user(iw->info.cause, &iw->infop->si_code, Efault); + unsafe_put_user(iw->info.pid, &iw->infop->si_pid, Efault); + unsafe_put_user(iw->info.uid, &iw->infop->si_uid, Efault); + unsafe_put_user(iw->info.status, &iw->infop->si_status, Efault); + ret = true; +done: + user_write_access_end(); + return ret; +Efault: + ret = false; + goto done; +} + +static int io_waitid_finish(struct io_kiocb *req, int ret) +{ + int signo = 0; + + if (ret > 0) { + signo = SIGCHLD; + ret = 0; + } + + if (!io_waitid_copy_si(req, signo)) + ret = -EFAULT; + io_waitid_free(req); + return ret; +} + +static void io_waitid_complete(struct io_kiocb *req, int ret) +{ + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + struct io_tw_state ts = { .locked = true }; + + /* anyone completing better be holding a reference */ + WARN_ON_ONCE(!(atomic_read(&iw->refs) & IO_WAITID_REF_MASK)); + + lockdep_assert_held(&req->ctx->uring_lock); + + /* + * Did cancel find it meanwhile? + */ + if (hlist_unhashed(&req->hash_node)) + return; + + hlist_del_init(&req->hash_node); + + ret = io_waitid_finish(req, ret); + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + io_req_task_complete(req, &ts); +} + +static bool __io_waitid_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) +{ + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + struct io_waitid_async *iwa = req->async_data; + + /* + * Mark us canceled regardless of ownership. This will prevent a + * potential retry from a spurious wakeup. + */ + atomic_or(IO_WAITID_CANCEL_FLAG, &iw->refs); + + /* claim ownership */ + if (atomic_fetch_inc(&iw->refs) & IO_WAITID_REF_MASK) + return false; + + spin_lock_irq(&iw->head->lock); + list_del_init(&iwa->wo.child_wait.entry); + spin_unlock_irq(&iw->head->lock); + io_waitid_complete(req, -ECANCELED); + return true; +} + +int io_waitid_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd, + unsigned int issue_flags) +{ + struct hlist_node *tmp; + struct io_kiocb *req; + int nr = 0; + + if (cd->flags & (IORING_ASYNC_CANCEL_FD|IORING_ASYNC_CANCEL_FD_FIXED)) + return -ENOENT; + + io_ring_submit_lock(ctx, issue_flags); + hlist_for_each_entry_safe(req, tmp, &ctx->waitid_list, hash_node) { + if (req->cqe.user_data != cd->data && + !(cd->flags & IORING_ASYNC_CANCEL_ANY)) + continue; + if (__io_waitid_cancel(ctx, req)) + nr++; + if (!(cd->flags & IORING_ASYNC_CANCEL_ALL)) + break; + } + io_ring_submit_unlock(ctx, issue_flags); + + if (nr) + return nr; + + return -ENOENT; +} + +bool io_waitid_remove_all(struct io_ring_ctx *ctx, struct task_struct *task, + bool cancel_all) +{ + struct hlist_node *tmp; + struct io_kiocb *req; + bool found = false; + + lockdep_assert_held(&ctx->uring_lock); + + hlist_for_each_entry_safe(req, tmp, &ctx->waitid_list, hash_node) { + if (!io_match_task_safe(req, task, cancel_all)) + continue; + __io_waitid_cancel(ctx, req); + found = true; + } + + return found; +} + +static inline bool io_waitid_drop_issue_ref(struct io_kiocb *req) +{ + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + struct io_waitid_async *iwa = req->async_data; + + if (!atomic_sub_return(1, &iw->refs)) + return false; + + /* + * Wakeup triggered, racing with us. It was prevented from + * completing because of that, queue up the tw to do that. + */ + req->io_task_work.func = io_waitid_cb; + io_req_task_work_add(req); + remove_wait_queue(iw->head, &iwa->wo.child_wait); + return true; +} + +static void io_waitid_cb(struct io_kiocb *req, struct io_tw_state *ts) +{ + struct io_waitid_async *iwa = req->async_data; + struct io_ring_ctx *ctx = req->ctx; + int ret; + + io_tw_lock(ctx, ts); + + ret = __do_wait(&iwa->wo); + + /* + * If we get -ERESTARTSYS here, we need to re-arm and check again + * to ensure we get another callback. If the retry works, then we can + * just remove ourselves from the waitqueue again and finish the + * request. + */ + if (unlikely(ret == -ERESTARTSYS)) { + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + + /* Don't retry if cancel found it meanwhile */ + ret = -ECANCELED; + if (!(atomic_read(&iw->refs) & IO_WAITID_CANCEL_FLAG)) { + iw->head = ¤t->signal->wait_chldexit; + add_wait_queue(iw->head, &iwa->wo.child_wait); + ret = __do_wait(&iwa->wo); + if (ret == -ERESTARTSYS) { + /* retry armed, drop our ref */ + io_waitid_drop_issue_ref(req); + return; + } + + remove_wait_queue(iw->head, &iwa->wo.child_wait); + } + } + + io_waitid_complete(req, ret); +} + +static int io_waitid_wait(struct wait_queue_entry *wait, unsigned mode, + int sync, void *key) +{ + struct wait_opts *wo = container_of(wait, struct wait_opts, child_wait); + struct io_waitid_async *iwa = container_of(wo, struct io_waitid_async, wo); + struct io_kiocb *req = iwa->req; + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + struct task_struct *p = key; + + if (!pid_child_should_wake(wo, p)) + return 0; + + /* cancel is in progress */ + if (atomic_fetch_inc(&iw->refs) & IO_WAITID_REF_MASK) + return 1; + + req->io_task_work.func = io_waitid_cb; + io_req_task_work_add(req); + list_del_init(&wait->entry); + return 1; +} + +int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) +{ + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + + if (sqe->addr || sqe->buf_index || sqe->addr3 || sqe->waitid_flags) + return -EINVAL; + + iw->which = READ_ONCE(sqe->len); + iw->upid = READ_ONCE(sqe->fd); + iw->options = READ_ONCE(sqe->file_index); + iw->infop = u64_to_user_ptr(READ_ONCE(sqe->addr2)); + return 0; +} + +int io_waitid(struct io_kiocb *req, unsigned int issue_flags) +{ + struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + struct io_ring_ctx *ctx = req->ctx; + struct io_waitid_async *iwa; + int ret; + + if (io_alloc_async_data(req)) + return -ENOMEM; + + iwa = req->async_data; + iwa->req = req; + + ret = kernel_waitid_prepare(&iwa->wo, iw->which, iw->upid, &iw->info, + iw->options, NULL); + if (ret) + goto done; + + /* + * Mark the request as busy upfront, in case we're racing with the + * wakeup. If we are, then we'll notice when we drop this initial + * reference again after arming. + */ + atomic_set(&iw->refs, 1); + + /* + * Cancel must hold the ctx lock, so there's no risk of cancelation + * finding us until a) we remain on the list, and b) the lock is + * dropped. We only need to worry about racing with the wakeup + * callback. + */ + io_ring_submit_lock(ctx, issue_flags); + hlist_add_head(&req->hash_node, &ctx->waitid_list); + + init_waitqueue_func_entry(&iwa->wo.child_wait, io_waitid_wait); + iwa->wo.child_wait.private = req->task; + iw->head = ¤t->signal->wait_chldexit; + add_wait_queue(iw->head, &iwa->wo.child_wait); + + ret = __do_wait(&iwa->wo); + if (ret == -ERESTARTSYS) { + /* + * Nobody else grabbed a reference, it'll complete when we get + * a waitqueue callback, or if someone cancels it. + */ + if (!io_waitid_drop_issue_ref(req)) { + io_ring_submit_unlock(ctx, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; + } + + /* + * Wakeup triggered, racing with us. It was prevented from + * completing because of that, queue up the tw to do that. + */ + io_ring_submit_unlock(ctx, issue_flags); + return IOU_ISSUE_SKIP_COMPLETE; + } + + hlist_del_init(&req->hash_node); + remove_wait_queue(iw->head, &iwa->wo.child_wait); + ret = io_waitid_finish(req, ret); + + io_ring_submit_unlock(ctx, issue_flags); +done: + if (ret < 0) + req_set_fail(req); + io_req_set_res(req, ret, 0); + return IOU_OK; +} diff --git a/io_uring/waitid.h b/io_uring/waitid.h new file mode 100644 index 0000000000000..956a8adafe8c0 --- /dev/null +++ b/io_uring/waitid.h @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "../kernel/exit.h" + +struct io_waitid_async { + struct io_kiocb *req; + struct wait_opts wo; +}; + +int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_waitid(struct io_kiocb *req, unsigned int issue_flags); +int io_waitid_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd, + unsigned int issue_flags); +bool io_waitid_remove_all(struct io_ring_ctx *ctx, struct task_struct *task, + bool cancel_all);