#include <net/sock.h>
#include <net/af_unix.h>
#include <net/scm.h>
-#include <net/busy_poll.h>
#include <linux/anon_inodes.h>
#include <linux/sched/mm.h>
#include <linux/uaccess.h>
#include <linux/io_uring.h>
#include <linux/audit.h>
#include <linux/security.h>
+#include <linux/xattr.h>
#define CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>
#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8
/* only define max */
-#define IORING_MAX_FIXED_FILES (1U << 15)
+#define IORING_MAX_FIXED_FILES (1U << 20)
#define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \
IORING_REGISTER_LAST + IORING_OP_LAST)
REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \
REQ_F_ASYNC_DATA)
+#define IO_REQ_CLEAN_SLOW_FLAGS (REQ_F_REFCOUNT | REQ_F_LINK | REQ_F_HARDLINK |\
+ IO_REQ_CLEAN_FLAGS)
+
+#define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED)
+
#define IO_TCTX_REFS_CACHE_NR (1U << 10)
struct io_uring {
* The application needs a full memory barrier before checking
* for IORING_SQ_NEED_WAKEUP after updating the sq tail.
*/
- u32 sq_flags;
+ atomic_t sq_flags;
/*
* Runtime CQ flags
*
struct io_uring_cqe cqes[] ____cacheline_aligned_in_smp;
};
-enum io_uring_cmd_flags {
- IO_URING_F_COMPLETE_DEFER = 1,
- IO_URING_F_UNLOCKED = 2,
- /* int's last bit, sign checks are usually faster than a bit test */
- IO_URING_F_NONBLOCK = INT_MIN,
-};
-
struct io_mapped_ubuf {
u64 ubuf;
u64 ubuf_end;
struct io_ring_ctx;
struct io_overflow_cqe {
- struct io_uring_cqe cqe;
struct list_head list;
+ struct io_uring_cqe cqe;
};
+/*
+ * FFS_SCM is only available on 64-bit archs, for 32-bit we just define it as 0
+ * and define IO_URING_SCM_ALL. For this case, we use SCM for all files as we
+ * can't safely always dereference the file when the task has exited and ring
+ * cleanup is done. If a file is tracked and part of SCM, then unix gc on
+ * process exit may reap it before __io_sqe_files_unregister() is run.
+ */
+#define FFS_NOWAIT 0x1UL
+#define FFS_ISREG 0x2UL
+#if defined(CONFIG_64BIT)
+#define FFS_SCM 0x4UL
+#else
+#define IO_URING_SCM_ALL
+#define FFS_SCM 0x0UL
+#endif
+#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG|FFS_SCM)
+
struct io_fixed_file {
/* file * with additional FFS_* flags */
unsigned long file_ptr;
struct io_file_table {
struct io_fixed_file *files;
+ unsigned long *bitmap;
+ unsigned int alloc_hint;
};
struct io_rsrc_node {
bool quiesce;
};
+#define IO_BUFFER_LIST_BUF_PER_PAGE (PAGE_SIZE / sizeof(struct io_uring_buf))
struct io_buffer_list {
- struct list_head list;
- struct list_head buf_list;
+ /*
+ * If ->buf_nr_pages is set, then buf_pages/buf_ring are used. If not,
+ * then these are classic provided buffers and ->buf_list is used.
+ */
+ union {
+ struct list_head buf_list;
+ struct {
+ struct page **buf_pages;
+ struct io_uring_buf_ring *buf_ring;
+ };
+ };
__u16 bgid;
+
+ /* below is for ring provided buffers */
+ __u16 buf_nr_pages;
+ __u16 nr_entries;
+ __u32 head;
+ __u32 mask;
};
struct io_buffer {
struct rcu_head rcu;
};
-#define IO_BUFFERS_HASH_BITS 5
+#define BGID_ARRAY 64
struct io_ring_ctx {
/* const or read-mostly hot data */
struct io_rings *rings;
unsigned int flags;
+ enum task_work_notify_mode notify_method;
unsigned int compat: 1;
unsigned int drain_next: 1;
unsigned int restricted: 1;
unsigned int drain_active: 1;
unsigned int drain_disabled: 1;
unsigned int has_evfd: 1;
+ unsigned int syscall_iopoll: 1;
} ____cacheline_aligned_in_smp;
/* submission data */
*/
struct io_rsrc_node *rsrc_node;
int rsrc_cached_refs;
+ atomic_t cancel_seq;
struct io_file_table file_table;
unsigned nr_user_files;
unsigned nr_user_bufs;
struct io_mapped_ubuf **user_bufs;
struct io_submit_state submit_state;
+
+ struct io_buffer_list *io_bl;
+ struct xarray io_bl_xa;
+ struct list_head io_buffers_cache;
+
struct list_head timeout_list;
struct list_head ltimeout_list;
struct list_head cq_overflow_list;
- struct list_head *io_buffers;
- struct list_head io_buffers_cache;
struct list_head apoll_cache;
struct xarray personalities;
u32 pers_next;
struct wait_queue_head sqo_sq_wait;
struct list_head sqd_list;
- unsigned long check_cq_overflow;
-#ifdef CONFIG_NET_RX_BUSY_POLL
- /* used to track busy poll napi_id */
- struct list_head napi_list;
- spinlock_t napi_lock; /* napi_list lock */
-#endif
+ unsigned long check_cq;
struct {
+ /*
+ * We cache a range of free CQEs we can use, once exhausted it
+ * should go through a slower range setup, see __io_get_cqe()
+ */
+ struct io_uring_cqe *cqe_cached;
+ struct io_uring_cqe *cqe_sentinel;
+
unsigned cached_cq_tail;
unsigned cq_entries;
struct io_ev_fd __rcu *io_ev_fd;
spinlock_t task_lock;
struct io_wq_work_list task_list;
- struct io_wq_work_list prior_task_list;
+ struct io_wq_work_list prio_task_list;
struct callback_head task_work;
struct file **registered_rings;
bool task_running;
struct file *file;
int fd;
u32 file_slot;
+ u32 flags;
};
struct io_timeout_data {
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;
struct io_cancel {
struct file *file;
u64 addr;
+ u32 flags;
+ s32 fd;
};
struct io_timeout {
/* NOTE: kiocb has the file as the first member, so don't do it here */
struct kiocb kiocb;
u64 addr;
- u64 len;
+ u32 len;
+ rwf_t flags;
};
struct io_connect {
void __user *buf;
};
int msg_flags;
- int bgid;
size_t len;
size_t done_io;
+ unsigned int flags;
};
struct io_open {
struct io_splice {
struct file *file_out;
- struct file *file_in;
loff_t off_out;
loff_t off_in;
u64 len;
+ int splice_fd_in;
unsigned int flags;
};
u32 len;
};
+struct io_nop {
+ struct file *file;
+ u64 extra1;
+ u64 extra2;
+};
+
struct io_async_connect {
struct sockaddr_storage address;
};
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,
REQ_F_NEED_CLEANUP_BIT,
REQ_F_POLLED_BIT,
REQ_F_BUFFER_SELECTED_BIT,
+ REQ_F_BUFFER_RING_BIT,
REQ_F_COMPLETE_INLINE_BIT,
REQ_F_REISSUE_BIT,
REQ_F_CREDS_BIT,
REQ_F_SINGLE_POLL_BIT,
REQ_F_DOUBLE_POLL_BIT,
REQ_F_PARTIAL_IO_BIT,
+ REQ_F_APOLL_MULTISHOT_BIT,
/* keep async read/write and isreg together and in order */
REQ_F_SUPPORT_NOWAIT_BIT,
REQ_F_ISREG_BIT,
REQ_F_POLLED = BIT(REQ_F_POLLED_BIT),
/* buffer already selected */
REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT),
+ /* buffer selected from ring, needs commit */
+ REQ_F_BUFFER_RING = BIT(REQ_F_BUFFER_RING_BIT),
/* completion is deferred through io_comp_state */
REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT),
/* caller should reissue async */
REQ_F_DOUBLE_POLL = BIT(REQ_F_DOUBLE_POLL_BIT),
/* request has already done partial IO */
REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT),
+ /* fast poll multishot mode */
+ REQ_F_APOLL_MULTISHOT = BIT(REQ_F_APOLL_MULTISHOT_BIT),
};
struct async_poll {
IORING_RSRC_BUFFER = 1,
};
+struct io_cqe {
+ __u64 user_data;
+ __s32 res;
+ /* fd initially, then cflags for completion */
+ union {
+ __u32 flags;
+ int fd;
+ };
+};
+
+enum {
+ IO_CHECK_CQ_OVERFLOW_BIT,
+ IO_CHECK_CQ_DROPPED_BIT,
+};
+
/*
* NOTE! Each of the iocb union members has the file pointer
* as the first entry in their struct definition. So you can
struct io_symlink symlink;
struct io_hardlink hardlink;
struct io_msg msg;
+ struct io_xattr xattr;
+ struct io_socket sock;
+ struct io_nop nop;
+ struct io_uring_cmd uring_cmd;
};
u8 opcode;
/* polled IO has completed */
u8 iopoll_completed;
+ /*
+ * Can be either a fixed buffer index, or used with provided buffers.
+ * For the latter, before issue it points to the buffer group ID,
+ * and after selection it points to the buffer ID itself.
+ */
u16 buf_index;
unsigned int flags;
- u64 user_data;
- u32 result;
- u32 cflags;
+ struct io_cqe cqe;
struct io_ring_ctx *ctx;
struct task_struct *task;
- struct percpu_ref *fixed_rsrc_refs;
- /* store used ubuf, so we can prevent reloading */
- struct io_mapped_ubuf *imu;
+ struct io_rsrc_node *rsrc_node;
+
+ union {
+ /* store used ubuf, so we can prevent reloading */
+ struct io_mapped_ubuf *imu;
+
+ /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */
+ struct io_buffer *kbuf;
+
+ /*
+ * stores buffer ID for ring provided buffers, valid IFF
+ * REQ_F_BUFFER_RING is set.
+ */
+ struct io_buffer_list *buf_list;
+ };
- /* used by request caches, completion batching and iopoll */
- struct io_wq_work_node comp_list;
+ union {
+ /* used by request caches, completion batching and iopoll */
+ struct io_wq_work_node comp_list;
+ /* cache ->apoll->events */
+ __poll_t apoll_events;
+ };
atomic_t refs;
atomic_t poll_refs;
struct io_task_work io_task_work;
/* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
- struct hlist_node hash_node;
+ union {
+ struct hlist_node hash_node;
+ struct {
+ u64 extra1;
+ u64 extra2;
+ };
+ };
/* internal polling, see IORING_FEAT_FAST_POLL */
struct async_poll *apoll;
/* opcode allocated if it needs to store data for async defer */
void *async_data;
- /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */
- struct io_buffer *kbuf;
/* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */
struct io_kiocb *link;
/* custom credentials, valid IFF REQ_F_CREDS is set */
u32 seq;
};
+struct io_cancel_data {
+ struct io_ring_ctx *ctx;
+ union {
+ u64 data;
+ struct file *file;
+ };
+ u32 flags;
+ int seq;
+};
+
+/*
+ * The URING_CMD payload starts at 'cmd' in the first sqe, and continues into
+ * the following sqe if SQE128 is used.
+ */
+#define uring_cmd_pdu_size(is_sqe128) \
+ ((1 + !!(is_sqe128)) * sizeof(struct io_uring_sqe) - \
+ offsetof(struct io_uring_sqe, cmd))
+
struct io_op_def {
/* needs req->file assigned */
unsigned needs_file : 1;
unsigned not_supported : 1;
/* skip auditing */
unsigned audit_skip : 1;
+ /* supports ioprio */
+ unsigned ioprio : 1;
+ /* supports iopoll */
+ unsigned iopoll : 1;
/* size of async data needed, if any */
unsigned short async_size;
};
static const struct io_op_def io_op_defs[] = {
- [IORING_OP_NOP] = {},
+ [IORING_OP_NOP] = {
+ .audit_skip = 1,
+ .iopoll = 1,
+ .buffer_select = 1,
+ },
[IORING_OP_READV] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.needs_async_setup = 1,
.plug = 1,
.audit_skip = 1,
+ .ioprio = 1,
+ .iopoll = 1,
.async_size = sizeof(struct io_async_rw),
},
[IORING_OP_WRITEV] = {
.needs_async_setup = 1,
.plug = 1,
.audit_skip = 1,
+ .ioprio = 1,
+ .iopoll = 1,
.async_size = sizeof(struct io_async_rw),
},
[IORING_OP_FSYNC] = {
.pollin = 1,
.plug = 1,
.audit_skip = 1,
+ .ioprio = 1,
+ .iopoll = 1,
.async_size = sizeof(struct io_async_rw),
},
[IORING_OP_WRITE_FIXED] = {
.pollout = 1,
.plug = 1,
.audit_skip = 1,
+ .ioprio = 1,
+ .iopoll = 1,
.async_size = sizeof(struct io_async_rw),
},
[IORING_OP_POLL_ADD] = {
.unbound_nonreg_file = 1,
.pollin = 1,
.poll_exclusive = 1,
+ .ioprio = 1, /* used for flags */
},
[IORING_OP_ASYNC_CANCEL] = {
.audit_skip = 1,
[IORING_OP_CLOSE] = {},
[IORING_OP_FILES_UPDATE] = {
.audit_skip = 1,
+ .iopoll = 1,
},
[IORING_OP_STATX] = {
.audit_skip = 1,
.buffer_select = 1,
.plug = 1,
.audit_skip = 1,
+ .ioprio = 1,
+ .iopoll = 1,
.async_size = sizeof(struct io_async_rw),
},
[IORING_OP_WRITE] = {
.pollout = 1,
.plug = 1,
.audit_skip = 1,
+ .ioprio = 1,
+ .iopoll = 1,
.async_size = sizeof(struct io_async_rw),
},
[IORING_OP_FADVISE] = {
},
[IORING_OP_PROVIDE_BUFFERS] = {
.audit_skip = 1,
+ .iopoll = 1,
},
[IORING_OP_REMOVE_BUFFERS] = {
.audit_skip = 1,
+ .iopoll = 1,
},
[IORING_OP_TEE] = {
.needs_file = 1,
[IORING_OP_LINKAT] = {},
[IORING_OP_MSG_RING] = {
.needs_file = 1,
+ .iopoll = 1,
+ },
+ [IORING_OP_FSETXATTR] = {
+ .needs_file = 1
+ },
+ [IORING_OP_SETXATTR] = {},
+ [IORING_OP_FGETXATTR] = {
+ .needs_file = 1
+ },
+ [IORING_OP_GETXATTR] = {},
+ [IORING_OP_SOCKET] = {
+ .audit_skip = 1,
+ },
+ [IORING_OP_URING_CMD] = {
+ .needs_file = 1,
+ .plug = 1,
+ .needs_async_setup = 1,
+ .async_size = uring_cmd_pdu_size(1),
},
};
/* requests with any of those set should undergo io_disarm_next() */
#define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL)
+#define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK)
static bool io_disarm_next(struct io_kiocb *req);
static void io_uring_del_tctx_node(unsigned long index);
bool cancel_all);
static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);
-static void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags);
-
-static void io_put_req(struct io_kiocb *req);
-static void io_put_req_deferred(struct io_kiocb *req);
+static void __io_req_complete_post(struct io_kiocb *req, s32 res, u32 cflags);
static void io_dismantle_req(struct io_kiocb *req);
static void io_queue_linked_timeout(struct io_kiocb *req);
static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type,
struct io_uring_rsrc_update2 *up,
unsigned nr_args);
static void io_clean_op(struct io_kiocb *req);
-static struct file *io_file_get(struct io_ring_ctx *ctx,
- struct io_kiocb *req, int fd, bool fixed);
-static void __io_queue_sqe(struct io_kiocb *req);
+static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
+ unsigned issue_flags);
+static struct file *io_file_get_normal(struct io_kiocb *req, int fd);
+static void io_queue_sqe(struct io_kiocb *req);
static void io_rsrc_put_work(struct work_struct *work);
static void io_req_task_queue(struct io_kiocb *req);
static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
unsigned int issue_flags, u32 slot_index);
-static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags);
+static int __io_close_fixed(struct io_kiocb *req, unsigned int issue_flags,
+ unsigned int offset);
+static inline int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags);
static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer);
static void io_eventfd_signal(struct io_ring_ctx *ctx);
+static void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags);
static struct kmem_cache *req_cachep;
static const struct file_operations io_uring_fops;
+const char *io_uring_get_opcode(u8 opcode)
+{
+ switch ((enum io_uring_op)opcode) {
+ case IORING_OP_NOP:
+ return "NOP";
+ case IORING_OP_READV:
+ return "READV";
+ case IORING_OP_WRITEV:
+ return "WRITEV";
+ case IORING_OP_FSYNC:
+ return "FSYNC";
+ case IORING_OP_READ_FIXED:
+ return "READ_FIXED";
+ case IORING_OP_WRITE_FIXED:
+ return "WRITE_FIXED";
+ case IORING_OP_POLL_ADD:
+ return "POLL_ADD";
+ case IORING_OP_POLL_REMOVE:
+ return "POLL_REMOVE";
+ case IORING_OP_SYNC_FILE_RANGE:
+ return "SYNC_FILE_RANGE";
+ case IORING_OP_SENDMSG:
+ return "SENDMSG";
+ case IORING_OP_RECVMSG:
+ return "RECVMSG";
+ case IORING_OP_TIMEOUT:
+ return "TIMEOUT";
+ case IORING_OP_TIMEOUT_REMOVE:
+ return "TIMEOUT_REMOVE";
+ case IORING_OP_ACCEPT:
+ return "ACCEPT";
+ case IORING_OP_ASYNC_CANCEL:
+ return "ASYNC_CANCEL";
+ case IORING_OP_LINK_TIMEOUT:
+ return "LINK_TIMEOUT";
+ case IORING_OP_CONNECT:
+ return "CONNECT";
+ case IORING_OP_FALLOCATE:
+ return "FALLOCATE";
+ case IORING_OP_OPENAT:
+ return "OPENAT";
+ case IORING_OP_CLOSE:
+ return "CLOSE";
+ case IORING_OP_FILES_UPDATE:
+ return "FILES_UPDATE";
+ case IORING_OP_STATX:
+ return "STATX";
+ case IORING_OP_READ:
+ return "READ";
+ case IORING_OP_WRITE:
+ return "WRITE";
+ case IORING_OP_FADVISE:
+ return "FADVISE";
+ case IORING_OP_MADVISE:
+ return "MADVISE";
+ case IORING_OP_SEND:
+ return "SEND";
+ case IORING_OP_RECV:
+ return "RECV";
+ case IORING_OP_OPENAT2:
+ return "OPENAT2";
+ case IORING_OP_EPOLL_CTL:
+ return "EPOLL_CTL";
+ case IORING_OP_SPLICE:
+ return "SPLICE";
+ case IORING_OP_PROVIDE_BUFFERS:
+ return "PROVIDE_BUFFERS";
+ case IORING_OP_REMOVE_BUFFERS:
+ return "REMOVE_BUFFERS";
+ case IORING_OP_TEE:
+ return "TEE";
+ case IORING_OP_SHUTDOWN:
+ return "SHUTDOWN";
+ case IORING_OP_RENAMEAT:
+ return "RENAMEAT";
+ case IORING_OP_UNLINKAT:
+ return "UNLINKAT";
+ case IORING_OP_MKDIRAT:
+ return "MKDIRAT";
+ case IORING_OP_SYMLINKAT:
+ return "SYMLINKAT";
+ case IORING_OP_LINKAT:
+ return "LINKAT";
+ case IORING_OP_MSG_RING:
+ return "MSG_RING";
+ case IORING_OP_FSETXATTR:
+ return "FSETXATTR";
+ case IORING_OP_SETXATTR:
+ return "SETXATTR";
+ case IORING_OP_FGETXATTR:
+ return "FGETXATTR";
+ case IORING_OP_GETXATTR:
+ return "GETXATTR";
+ case IORING_OP_SOCKET:
+ return "SOCKET";
+ case IORING_OP_URING_CMD:
+ return "URING_CMD";
+ case IORING_OP_LAST:
+ return "INVALID";
+ }
+ return "INVALID";
+}
+
struct sock *io_uring_get_socket(struct file *file)
{
#if defined(CONFIG_UNIX)
}
EXPORT_SYMBOL(io_uring_get_socket);
+#if defined(CONFIG_UNIX)
+static inline bool io_file_need_scm(struct file *filp)
+{
+#if defined(IO_URING_SCM_ALL)
+ return true;
+#else
+ return !!unix_get_socket(filp);
+#endif
+}
+#else
+static inline bool io_file_need_scm(struct file *filp)
+{
+ return false;
+}
+#endif
+
+static void io_ring_submit_unlock(struct io_ring_ctx *ctx, unsigned issue_flags)
+{
+ lockdep_assert_held(&ctx->uring_lock);
+ if (issue_flags & IO_URING_F_UNLOCKED)
+ mutex_unlock(&ctx->uring_lock);
+}
+
+static void io_ring_submit_lock(struct io_ring_ctx *ctx, unsigned issue_flags)
+{
+ /*
+ * "Normal" inline submissions always hold the uring_lock, since we
+ * grab it from the system call. Same is true for the SQPOLL offload.
+ * The only exception is when we've detached the request and issue it
+ * from an async worker thread, grab the lock for that case.
+ */
+ if (issue_flags & IO_URING_F_UNLOCKED)
+ mutex_lock(&ctx->uring_lock);
+ lockdep_assert_held(&ctx->uring_lock);
+}
+
static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked)
{
if (!*locked) {
#define IO_RSRC_REF_BATCH 100
+static void io_rsrc_put_node(struct io_rsrc_node *node, int nr)
+{
+ percpu_ref_put_many(&node->refs, nr);
+}
+
static inline void io_req_put_rsrc_locked(struct io_kiocb *req,
struct io_ring_ctx *ctx)
__must_hold(&ctx->uring_lock)
{
- struct percpu_ref *ref = req->fixed_rsrc_refs;
+ struct io_rsrc_node *node = req->rsrc_node;
- if (ref) {
- if (ref == &ctx->rsrc_node->refs)
+ if (node) {
+ if (node == ctx->rsrc_node)
ctx->rsrc_cached_refs++;
else
- percpu_ref_put(ref);
+ io_rsrc_put_node(node, 1);
}
}
-static inline void io_req_put_rsrc(struct io_kiocb *req, struct io_ring_ctx *ctx)
+static inline void io_req_put_rsrc(struct io_kiocb *req)
{
- if (req->fixed_rsrc_refs)
- percpu_ref_put(req->fixed_rsrc_refs);
+ if (req->rsrc_node)
+ io_rsrc_put_node(req->rsrc_node, 1);
}
static __cold void io_rsrc_refs_drop(struct io_ring_ctx *ctx)
__must_hold(&ctx->uring_lock)
{
if (ctx->rsrc_cached_refs) {
- percpu_ref_put_many(&ctx->rsrc_node->refs, ctx->rsrc_cached_refs);
+ io_rsrc_put_node(ctx->rsrc_node, ctx->rsrc_cached_refs);
ctx->rsrc_cached_refs = 0;
}
}
}
static inline void io_req_set_rsrc_node(struct io_kiocb *req,
- struct io_ring_ctx *ctx)
+ struct io_ring_ctx *ctx,
+ unsigned int issue_flags)
{
- if (!req->fixed_rsrc_refs) {
- req->fixed_rsrc_refs = &ctx->rsrc_node->refs;
- ctx->rsrc_cached_refs--;
- if (unlikely(ctx->rsrc_cached_refs < 0))
- io_rsrc_refs_refill(ctx);
+ if (!req->rsrc_node) {
+ req->rsrc_node = ctx->rsrc_node;
+
+ if (!(issue_flags & IO_URING_F_UNLOCKED)) {
+ lockdep_assert_held(&ctx->uring_lock);
+ ctx->rsrc_cached_refs--;
+ if (unlikely(ctx->rsrc_cached_refs < 0))
+ io_rsrc_refs_refill(ctx);
+ } else {
+ percpu_ref_get(&req->rsrc_node->refs);
+ }
}
}
static unsigned int __io_put_kbuf(struct io_kiocb *req, struct list_head *list)
{
- struct io_buffer *kbuf = req->kbuf;
- unsigned int cflags;
+ if (req->flags & REQ_F_BUFFER_RING) {
+ if (req->buf_list)
+ req->buf_list->head++;
+ req->flags &= ~REQ_F_BUFFER_RING;
+ } else {
+ list_add(&req->kbuf->list, list);
+ req->flags &= ~REQ_F_BUFFER_SELECTED;
+ }
- cflags = IORING_CQE_F_BUFFER | (kbuf->bid << IORING_CQE_BUFFER_SHIFT);
- req->flags &= ~REQ_F_BUFFER_SELECTED;
- list_add(&kbuf->list, list);
- req->kbuf = NULL;
- return cflags;
+ return IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
}
static inline unsigned int io_put_kbuf_comp(struct io_kiocb *req)
{
lockdep_assert_held(&req->ctx->completion_lock);
- if (likely(!(req->flags & REQ_F_BUFFER_SELECTED)))
+ if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
return 0;
return __io_put_kbuf(req, &req->ctx->io_buffers_comp);
}
{
unsigned int cflags;
- if (likely(!(req->flags & REQ_F_BUFFER_SELECTED)))
+ if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
return 0;
/*
* We migrate buffers from the comp_list to the issue cache list
* when we need one.
*/
- if (issue_flags & IO_URING_F_UNLOCKED) {
+ if (req->flags & REQ_F_BUFFER_RING) {
+ /* no buffers to recycle for this case */
+ cflags = __io_put_kbuf(req, NULL);
+ } else if (issue_flags & IO_URING_F_UNLOCKED) {
struct io_ring_ctx *ctx = req->ctx;
spin_lock(&ctx->completion_lock);
static struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx,
unsigned int bgid)
{
- struct list_head *hash_list;
- struct io_buffer_list *bl;
+ if (ctx->io_bl && bgid < BGID_ARRAY)
+ return &ctx->io_bl[bgid];
- hash_list = &ctx->io_buffers[hash_32(bgid, IO_BUFFERS_HASH_BITS)];
- list_for_each_entry(bl, hash_list, list)
- if (bl->bgid == bgid || bgid == -1U)
- return bl;
-
- return NULL;
+ return xa_load(&ctx->io_bl_xa, bgid);
}
static void io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
struct io_buffer_list *bl;
struct io_buffer *buf;
- if (likely(!(req->flags & REQ_F_BUFFER_SELECTED)))
+ if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
return;
/* don't recycle if we already did IO to this buffer */
if (req->flags & REQ_F_PARTIAL_IO)
return;
+ /*
+ * We don't need to recycle for REQ_F_BUFFER_RING, we can just clear
+ * the flag and hence ensure that bl->head doesn't get incremented.
+ * If the tail has already been incremented, hang on to it.
+ */
+ if (req->flags & REQ_F_BUFFER_RING) {
+ if (req->buf_list) {
+ req->buf_index = req->buf_list->bgid;
+ req->flags &= ~REQ_F_BUFFER_RING;
+ }
+ return;
+ }
- if (issue_flags & IO_URING_F_UNLOCKED)
- mutex_lock(&ctx->uring_lock);
-
- lockdep_assert_held(&ctx->uring_lock);
+ io_ring_submit_lock(ctx, issue_flags);
buf = req->kbuf;
bl = io_buffer_get_list(ctx, buf->bgid);
list_add(&buf->list, &bl->buf_list);
req->flags &= ~REQ_F_BUFFER_SELECTED;
- req->kbuf = NULL;
+ req->buf_index = buf->bgid;
- if (issue_flags & IO_URING_F_UNLOCKED)
- mutex_unlock(&ctx->uring_lock);
+ io_ring_submit_unlock(ctx, issue_flags);
}
static bool io_match_task(struct io_kiocb *head, struct task_struct *task,
static inline void req_fail_link_node(struct io_kiocb *req, int res)
{
req_set_fail(req);
- req->result = res;
+ req->cqe.res = res;
+}
+
+static inline void io_req_add_to_cache(struct io_kiocb *req, struct io_ring_ctx *ctx)
+{
+ wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list);
}
static __cold void io_ring_ctx_ref_free(struct percpu_ref *ref)
static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
{
struct io_ring_ctx *ctx;
- int i, hash_bits;
+ int hash_bits;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return NULL;
+ xa_init(&ctx->io_bl_xa);
+
/*
* Use 5 bits less than the max cq entries, that should give us around
* 32 entries per hash list if totally full and uniformly spread.
/* set invalid range, so io_import_fixed() fails meeting it */
ctx->dummy_ubuf->ubuf = -1UL;
- ctx->io_buffers = kcalloc(1U << IO_BUFFERS_HASH_BITS,
- sizeof(struct list_head), GFP_KERNEL);
- if (!ctx->io_buffers)
- goto err;
- for (i = 0; i < (1U << IO_BUFFERS_HASH_BITS); i++)
- INIT_LIST_HEAD(&ctx->io_buffers[i]);
-
if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free,
PERCPU_REF_ALLOW_REINIT, GFP_KERNEL))
goto err;
INIT_WQ_LIST(&ctx->locked_free_list);
INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
-#ifdef CONFIG_NET_RX_BUSY_POLL
- INIT_LIST_HEAD(&ctx->napi_list);
- spin_lock_init(&ctx->napi_lock);
-#endif
return ctx;
err:
kfree(ctx->dummy_ubuf);
kfree(ctx->cancel_hash);
- kfree(ctx->io_buffers);
+ kfree(ctx->io_bl);
+ xa_destroy(&ctx->io_bl_xa);
kfree(ctx);
return NULL;
}
return false;
}
-#define FFS_NOWAIT 0x1UL
-#define FFS_ISREG 0x2UL
-#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG)
-
static inline bool io_req_ffs_set(struct io_kiocb *req)
{
return req->flags & REQ_F_FIXED_FILE;
return __io_prep_linked_timeout(req);
}
+static noinline void __io_arm_ltimeout(struct io_kiocb *req)
+{
+ io_queue_linked_timeout(__io_prep_linked_timeout(req));
+}
+
+static inline void io_arm_ltimeout(struct io_kiocb *req)
+{
+ if (unlikely(req->flags & REQ_F_ARM_LTIMEOUT))
+ __io_arm_ltimeout(req);
+}
+
static void io_prep_async_work(struct io_kiocb *req)
{
const struct io_op_def *def = &io_op_defs[req->opcode];
req->work.list.next = NULL;
req->work.flags = 0;
+ req->work.cancel_seq = atomic_read(&ctx->cancel_seq);
if (req->flags & REQ_F_FORCE_ASYNC)
req->work.flags |= IO_WQ_WORK_CONCURRENT;
if (def->unbound_nonreg_file)
req->work.flags |= IO_WQ_WORK_UNBOUND;
}
-
- switch (req->opcode) {
- case IORING_OP_SPLICE:
- case IORING_OP_TEE:
- if (!S_ISREG(file_inode(req->splice.file_in)->i_mode))
- req->work.flags |= IO_WQ_WORK_UNBOUND;
- break;
- }
}
static void io_prep_async_link(struct io_kiocb *req)
static inline void io_req_add_compl_list(struct io_kiocb *req)
{
- struct io_ring_ctx *ctx = req->ctx;
- struct io_submit_state *state = &ctx->submit_state;
+ struct io_submit_state *state = &req->ctx->submit_state;
if (!(req->flags & REQ_F_CQE_SKIP))
- ctx->submit_state.flush_cqes = true;
+ state->flush_cqes = true;
wq_list_add_tail(&req->comp_list, &state->compl_reqs);
}
-static void io_queue_async_work(struct io_kiocb *req, bool *dont_use)
+static void io_queue_iowq(struct io_kiocb *req, bool *dont_use)
{
- struct io_ring_ctx *ctx = req->ctx;
struct io_kiocb *link = io_prep_linked_timeout(req);
struct io_uring_task *tctx = req->task->io_uring;
if (WARN_ON_ONCE(!same_thread_group(req->task, current)))
req->work.flags |= IO_WQ_WORK_CANCEL;
- trace_io_uring_queue_async_work(ctx, req, req->user_data, req->opcode, req->flags,
- &req->work, io_wq_is_hashed(&req->work));
+ trace_io_uring_queue_async_work(req->ctx, req, req->cqe.user_data,
+ req->opcode, req->flags, &req->work,
+ io_wq_is_hashed(&req->work));
io_wq_enqueue(tctx->io_wq, &req->work);
if (link)
io_queue_linked_timeout(link);
atomic_set(&req->ctx->cq_timeouts,
atomic_read(&req->ctx->cq_timeouts) + 1);
list_del_init(&req->timeout.list);
- io_fill_cqe_req(req, status, 0);
- io_put_req_deferred(req);
+ io_req_tw_post_queue(req, status, 0);
}
}
__must_hold(&ctx->completion_lock)
{
u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
+ struct io_kiocb *req, *tmp;
spin_lock_irq(&ctx->timeout_lock);
- while (!list_empty(&ctx->timeout_list)) {
+ list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
u32 events_needed, events_got;
- struct io_kiocb *req = list_first_entry(&ctx->timeout_list,
- struct io_kiocb, timeout.list);
if (io_is_timeout_noseq(req))
break;
if (events_got < events_needed)
break;
- list_del_init(&req->timeout.list);
io_kill_timeout(req, 0);
}
ctx->cq_last_tm_flush = seq;
return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head);
}
-static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx)
+/*
+ * writes to the cq entry need to come after reading head; the
+ * control dependency is enough as we're using WRITE_ONCE to
+ * fill the cq entry
+ */
+static noinline struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx)
{
struct io_rings *rings = ctx->rings;
- unsigned tail, mask = ctx->cq_entries - 1;
-
- /*
- * writes to the cq entry need to come after reading head; the
- * control dependency is enough as we're using WRITE_ONCE to
- * fill the cq entry
- */
- if (__io_cqring_events(ctx) == ctx->cq_entries)
+ unsigned int off = ctx->cached_cq_tail & (ctx->cq_entries - 1);
+ unsigned int shift = 0;
+ unsigned int free, queued, len;
+
+ if (ctx->flags & IORING_SETUP_CQE32)
+ shift = 1;
+
+ /* userspace may cheat modifying the tail, be safe and do min */
+ queued = min(__io_cqring_events(ctx), ctx->cq_entries);
+ free = ctx->cq_entries - queued;
+ /* we need a contiguous range, limit based on the current array offset */
+ len = min(free, ctx->cq_entries - off);
+ if (!len)
return NULL;
- tail = ctx->cached_cq_tail++;
- return &rings->cqes[tail & mask];
+ ctx->cached_cq_tail++;
+ ctx->cqe_cached = &rings->cqes[off];
+ ctx->cqe_sentinel = ctx->cqe_cached + len;
+ ctx->cqe_cached++;
+ return &rings->cqes[off << shift];
+}
+
+static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx)
+{
+ if (likely(ctx->cqe_cached < ctx->cqe_sentinel)) {
+ struct io_uring_cqe *cqe = ctx->cqe_cached;
+
+ if (ctx->flags & IORING_SETUP_CQE32) {
+ unsigned int off = ctx->cqe_cached - ctx->rings->cqes;
+
+ cqe += off;
+ }
+
+ ctx->cached_cq_tail++;
+ ctx->cqe_cached++;
+ return cqe;
+ }
+
+ return __io_get_cqe(ctx);
}
static void io_eventfd_signal(struct io_ring_ctx *ctx)
static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
{
bool all_flushed, posted;
+ size_t cqe_size = sizeof(struct io_uring_cqe);
if (!force && __io_cqring_events(ctx) == ctx->cq_entries)
return false;
+ if (ctx->flags & IORING_SETUP_CQE32)
+ cqe_size <<= 1;
+
posted = false;
spin_lock(&ctx->completion_lock);
while (!list_empty(&ctx->cq_overflow_list)) {
ocqe = list_first_entry(&ctx->cq_overflow_list,
struct io_overflow_cqe, list);
if (cqe)
- memcpy(cqe, &ocqe->cqe, sizeof(*cqe));
+ memcpy(cqe, &ocqe->cqe, cqe_size);
else
io_account_cq_overflow(ctx);
all_flushed = list_empty(&ctx->cq_overflow_list);
if (all_flushed) {
- clear_bit(0, &ctx->check_cq_overflow);
- WRITE_ONCE(ctx->rings->sq_flags,
- ctx->rings->sq_flags & ~IORING_SQ_CQ_OVERFLOW);
+ clear_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq);
+ atomic_andnot(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags);
}
- if (posted)
- io_commit_cqring(ctx);
+ io_commit_cqring(ctx);
spin_unlock(&ctx->completion_lock);
if (posted)
io_cqring_ev_posted(ctx);
{
bool ret = true;
- if (test_bit(0, &ctx->check_cq_overflow)) {
+ if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
/* iopoll syncs against uring_lock, not completion_lock */
if (ctx->flags & IORING_SETUP_IOPOLL)
mutex_lock(&ctx->uring_lock);
return ret;
}
-/* must to be called somewhat shortly after putting a request */
-static inline void io_put_task(struct task_struct *task, int nr)
+static void __io_put_task(struct task_struct *task, int nr)
{
struct io_uring_task *tctx = task->io_uring;
- if (likely(task == current)) {
- tctx->cached_refs += nr;
- } else {
- percpu_counter_sub(&tctx->inflight, nr);
- if (unlikely(atomic_read(&tctx->in_idle)))
- wake_up(&tctx->wait);
- put_task_struct_many(task, nr);
- }
+ percpu_counter_sub(&tctx->inflight, nr);
+ if (unlikely(atomic_read(&tctx->in_idle)))
+ wake_up(&tctx->wait);
+ put_task_struct_many(task, nr);
+}
+
+/* must to be called somewhat shortly after putting a request */
+static inline void io_put_task(struct task_struct *task, int nr)
+{
+ if (likely(task == current))
+ task->io_uring->cached_refs += nr;
+ else
+ __io_put_task(task, nr);
}
static void io_task_refs_refill(struct io_uring_task *tctx)
}
static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
- s32 res, u32 cflags)
+ s32 res, u32 cflags, u64 extra1,
+ u64 extra2)
{
struct io_overflow_cqe *ocqe;
+ size_t ocq_size = sizeof(struct io_overflow_cqe);
+ bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32);
- ocqe = kmalloc(sizeof(*ocqe), GFP_ATOMIC | __GFP_ACCOUNT);
+ if (is_cqe32)
+ ocq_size += sizeof(struct io_uring_cqe);
+
+ ocqe = kmalloc(ocq_size, GFP_ATOMIC | __GFP_ACCOUNT);
+ trace_io_uring_cqe_overflow(ctx, user_data, res, cflags, ocqe);
if (!ocqe) {
/*
* If we're in ring overflow flush mode, or in task cancel mode,
* on the floor.
*/
io_account_cq_overflow(ctx);
+ set_bit(IO_CHECK_CQ_DROPPED_BIT, &ctx->check_cq);
return false;
}
if (list_empty(&ctx->cq_overflow_list)) {
- set_bit(0, &ctx->check_cq_overflow);
- WRITE_ONCE(ctx->rings->sq_flags,
- ctx->rings->sq_flags | IORING_SQ_CQ_OVERFLOW);
+ set_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq);
+ atomic_or(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags);
}
ocqe->cqe.user_data = user_data;
ocqe->cqe.res = res;
ocqe->cqe.flags = cflags;
+ if (is_cqe32) {
+ ocqe->cqe.big_cqe[0] = extra1;
+ ocqe->cqe.big_cqe[1] = extra2;
+ }
list_add_tail(&ocqe->list, &ctx->cq_overflow_list);
return true;
}
WRITE_ONCE(cqe->flags, cflags);
return true;
}
- return io_cqring_event_overflow(ctx, user_data, res, cflags);
+ return io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0);
}
-static inline bool __io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags)
+static inline bool __io_fill_cqe_req_filled(struct io_ring_ctx *ctx,
+ struct io_kiocb *req)
{
- trace_io_uring_complete(req->ctx, req, req->user_data, res, cflags);
- return __io_fill_cqe(req->ctx, req->user_data, res, cflags);
-}
+ struct io_uring_cqe *cqe;
-static noinline void io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags)
-{
- if (!(req->flags & REQ_F_CQE_SKIP))
- __io_fill_cqe_req(req, res, cflags);
+ trace_io_uring_complete(req->ctx, req, req->cqe.user_data,
+ req->cqe.res, req->cqe.flags, 0, 0);
+
+ /*
+ * If we can't get a cq entry, userspace overflowed the
+ * submission (by quite a lot). Increment the overflow count in
+ * the ring.
+ */
+ cqe = io_get_cqe(ctx);
+ if (likely(cqe)) {
+ memcpy(cqe, &req->cqe, sizeof(*cqe));
+ return true;
+ }
+ return io_cqring_event_overflow(ctx, req->cqe.user_data,
+ req->cqe.res, req->cqe.flags, 0, 0);
+}
+
+static inline bool __io_fill_cqe32_req_filled(struct io_ring_ctx *ctx,
+ struct io_kiocb *req)
+{
+ struct io_uring_cqe *cqe;
+ u64 extra1 = req->extra1;
+ u64 extra2 = req->extra2;
+
+ trace_io_uring_complete(req->ctx, req, req->cqe.user_data,
+ req->cqe.res, req->cqe.flags, extra1, extra2);
+
+ /*
+ * If we can't get a cq entry, userspace overflowed the
+ * submission (by quite a lot). Increment the overflow count in
+ * the ring.
+ */
+ cqe = io_get_cqe(ctx);
+ if (likely(cqe)) {
+ memcpy(cqe, &req->cqe, sizeof(struct io_uring_cqe));
+ cqe->big_cqe[0] = extra1;
+ cqe->big_cqe[1] = extra2;
+ return true;
+ }
+
+ return io_cqring_event_overflow(ctx, req->cqe.user_data, req->cqe.res,
+ req->cqe.flags, extra1, extra2);
+}
+
+static inline bool __io_fill_cqe_req(struct io_kiocb *req, s32 res, u32 cflags)
+{
+ trace_io_uring_complete(req->ctx, req, req->cqe.user_data, res, cflags, 0, 0);
+ return __io_fill_cqe(req->ctx, req->cqe.user_data, res, cflags);
+}
+
+static inline void __io_fill_cqe32_req(struct io_kiocb *req, s32 res, u32 cflags,
+ u64 extra1, u64 extra2)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_uring_cqe *cqe;
+
+ if (WARN_ON_ONCE(!(ctx->flags & IORING_SETUP_CQE32)))
+ return;
+ if (req->flags & REQ_F_CQE_SKIP)
+ return;
+
+ trace_io_uring_complete(ctx, req, req->cqe.user_data, res, cflags,
+ extra1, extra2);
+
+ /*
+ * If we can't get a cq entry, userspace overflowed the
+ * submission (by quite a lot). Increment the overflow count in
+ * the ring.
+ */
+ cqe = io_get_cqe(ctx);
+ if (likely(cqe)) {
+ WRITE_ONCE(cqe->user_data, req->cqe.user_data);
+ WRITE_ONCE(cqe->res, res);
+ WRITE_ONCE(cqe->flags, cflags);
+ WRITE_ONCE(cqe->big_cqe[0], extra1);
+ WRITE_ONCE(cqe->big_cqe[1], extra2);
+ return;
+ }
+
+ io_cqring_event_overflow(ctx, req->cqe.user_data, res, cflags, extra1, extra2);
}
static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data,
s32 res, u32 cflags)
{
ctx->cq_extra++;
- trace_io_uring_complete(ctx, NULL, user_data, res, cflags);
+ trace_io_uring_complete(ctx, NULL, user_data, res, cflags, 0, 0);
return __io_fill_cqe(ctx, user_data, res, cflags);
}
-static void __io_req_complete_post(struct io_kiocb *req, s32 res,
- u32 cflags)
+static void __io_req_complete_put(struct io_kiocb *req)
{
- struct io_ring_ctx *ctx = req->ctx;
-
- if (!(req->flags & REQ_F_CQE_SKIP))
- __io_fill_cqe_req(req, res, cflags);
/*
* If we're the last reference to this request, add to our locked
* free_list cache.
*/
if (req_ref_put_and_test(req)) {
- if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) {
+ struct io_ring_ctx *ctx = req->ctx;
+
+ if (req->flags & IO_REQ_LINK_FLAGS) {
if (req->flags & IO_DISARM_MASK)
io_disarm_next(req);
if (req->link) {
req->link = NULL;
}
}
- io_req_put_rsrc(req, ctx);
+ io_req_put_rsrc(req);
/*
* Selected buffer deallocation in io_clean_op() assumes that
* we don't hold ->completion_lock. Clean them here to avoid
}
}
-static void io_req_complete_post(struct io_kiocb *req, s32 res,
- u32 cflags)
+static void __io_req_complete_post(struct io_kiocb *req, s32 res,
+ u32 cflags)
+{
+ if (!(req->flags & REQ_F_CQE_SKIP))
+ __io_fill_cqe_req(req, res, cflags);
+ __io_req_complete_put(req);
+}
+
+static void __io_req_complete_post32(struct io_kiocb *req, s32 res,
+ u32 cflags, u64 extra1, u64 extra2)
+{
+ if (!(req->flags & REQ_F_CQE_SKIP))
+ __io_fill_cqe32_req(req, res, cflags, extra1, extra2);
+ __io_req_complete_put(req);
+}
+
+static void io_req_complete_post(struct io_kiocb *req, s32 res, u32 cflags)
{
struct io_ring_ctx *ctx = req->ctx;
io_cqring_ev_posted(ctx);
}
+static void io_req_complete_post32(struct io_kiocb *req, s32 res,
+ u32 cflags, u64 extra1, u64 extra2)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+
+ spin_lock(&ctx->completion_lock);
+ __io_req_complete_post32(req, res, cflags, extra1, extra2);
+ io_commit_cqring(ctx);
+ spin_unlock(&ctx->completion_lock);
+ io_cqring_ev_posted(ctx);
+}
+
static inline void io_req_complete_state(struct io_kiocb *req, s32 res,
u32 cflags)
{
- req->result = res;
- req->cflags = cflags;
+ req->cqe.res = res;
+ req->cqe.flags = cflags;
req->flags |= REQ_F_COMPLETE_INLINE;
}
io_req_complete_post(req, res, cflags);
}
+static inline void __io_req_complete32(struct io_kiocb *req,
+ unsigned int issue_flags, s32 res,
+ u32 cflags, u64 extra1, u64 extra2)
+{
+ if (issue_flags & IO_URING_F_COMPLETE_DEFER) {
+ io_req_complete_state(req, res, cflags);
+ req->extra1 = extra1;
+ req->extra2 = extra2;
+ } else {
+ io_req_complete_post32(req, res, cflags, extra1, extra2);
+ }
+}
+
static inline void io_req_complete(struct io_kiocb *req, s32 res)
{
+ if (res < 0)
+ req_set_fail(req);
__io_req_complete(req, 0, res, 0);
}
io_req_complete_post(req, res, io_put_kbuf(req, IO_URING_F_UNLOCKED));
}
-static void io_req_complete_fail_submit(struct io_kiocb *req)
-{
- /*
- * We don't submit, fail them all, for that replace hardlinks with
- * normal links. Extra REQ_F_LINK is tolerated.
- */
- req->flags &= ~REQ_F_HARDLINK;
- req->flags |= REQ_F_LINK;
- io_req_complete_failed(req, req->result);
-}
-
/*
* Don't initialise the fields below on every allocation, but do that in
* advance and keep them valid across allocations.
req->link = NULL;
req->async_data = NULL;
/* not necessary, but safer to zero */
- req->result = 0;
+ req->cqe.res = 0;
}
static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx,
spin_unlock(&ctx->completion_lock);
}
-/* Returns true IFF there are requests in the cache */
-static bool io_flush_cached_reqs(struct io_ring_ctx *ctx)
+static inline bool io_req_cache_empty(struct io_ring_ctx *ctx)
{
- struct io_submit_state *state = &ctx->submit_state;
-
- /*
- * If we have more than a batch's worth of requests in our IRQ side
- * locked cache, grab the lock and move them over to our submission
- * side cache.
- */
- if (READ_ONCE(ctx->locked_free_nr) > IO_COMPL_BATCH)
- io_flush_cached_locked_reqs(ctx, state);
- return !!state->free_list.next;
+ return !ctx->submit_state.free_list.next;
}
/*
static __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx)
__must_hold(&ctx->uring_lock)
{
- struct io_submit_state *state = &ctx->submit_state;
gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
void *reqs[IO_REQ_ALLOC_BATCH];
- struct io_kiocb *req;
int ret, i;
- if (likely(state->free_list.next || io_flush_cached_reqs(ctx)))
- return true;
+ /*
+ * If we have more than a batch's worth of requests in our IRQ side
+ * locked cache, grab the lock and move them over to our submission
+ * side cache.
+ */
+ if (data_race(ctx->locked_free_nr) > IO_COMPL_BATCH) {
+ io_flush_cached_locked_reqs(ctx, &ctx->submit_state);
+ if (!io_req_cache_empty(ctx))
+ return true;
+ }
ret = kmem_cache_alloc_bulk(req_cachep, gfp, ARRAY_SIZE(reqs), reqs);
percpu_ref_get_many(&ctx->refs, ret);
for (i = 0; i < ret; i++) {
- req = reqs[i];
+ struct io_kiocb *req = reqs[i];
io_preinit_req(req, ctx);
- wq_stack_add_head(&req->comp_list, &state->free_list);
+ io_req_add_to_cache(req, ctx);
}
return true;
}
static inline bool io_alloc_req_refill(struct io_ring_ctx *ctx)
{
- if (unlikely(!ctx->submit_state.free_list.next))
+ if (unlikely(io_req_cache_empty(ctx)))
return __io_alloc_req_refill(ctx);
return true;
}
io_put_file(req->file);
}
-static __cold void __io_free_req(struct io_kiocb *req)
+static __cold void io_free_req(struct io_kiocb *req)
{
struct io_ring_ctx *ctx = req->ctx;
- io_req_put_rsrc(req, ctx);
+ io_req_put_rsrc(req);
io_dismantle_req(req);
io_put_task(req->task, 1);
nxt->link = NULL;
}
-static bool io_kill_linked_timeout(struct io_kiocb *req)
+static struct io_kiocb *io_disarm_linked_timeout(struct io_kiocb *req)
__must_hold(&req->ctx->completion_lock)
__must_hold(&req->ctx->timeout_lock)
{
link->timeout.head = NULL;
if (hrtimer_try_to_cancel(&io->timer) != -1) {
list_del(&link->timeout.list);
- /* leave REQ_F_CQE_SKIP to io_fill_cqe_req */
- io_fill_cqe_req(link, -ECANCELED, 0);
- io_put_req_deferred(link);
- return true;
+ return link;
}
}
- return false;
+ return NULL;
}
static void io_fail_links(struct io_kiocb *req)
long res = -ECANCELED;
if (link->flags & REQ_F_FAIL)
- res = link->result;
+ res = link->cqe.res;
nxt = link->link;
link->link = NULL;
- trace_io_uring_fail_link(req->ctx, req, req->user_data,
+ trace_io_uring_fail_link(req->ctx, req, req->cqe.user_data,
req->opcode, link);
- if (!ignore_cqes) {
+ if (ignore_cqes)
+ link->flags |= REQ_F_CQE_SKIP;
+ else
link->flags &= ~REQ_F_CQE_SKIP;
- io_fill_cqe_req(link, res, 0);
- }
- io_put_req_deferred(link);
+ __io_req_complete_post(link, res, 0);
link = nxt;
}
}
static bool io_disarm_next(struct io_kiocb *req)
__must_hold(&req->ctx->completion_lock)
{
+ struct io_kiocb *link = NULL;
bool posted = false;
if (req->flags & REQ_F_ARM_LTIMEOUT) {
- struct io_kiocb *link = req->link;
-
+ link = req->link;
req->flags &= ~REQ_F_ARM_LTIMEOUT;
if (link && link->opcode == IORING_OP_LINK_TIMEOUT) {
io_remove_next_linked(req);
- /* leave REQ_F_CQE_SKIP to io_fill_cqe_req */
- io_fill_cqe_req(link, -ECANCELED, 0);
- io_put_req_deferred(link);
+ io_req_tw_post_queue(link, -ECANCELED, 0);
posted = true;
}
} else if (req->flags & REQ_F_LINK_TIMEOUT) {
struct io_ring_ctx *ctx = req->ctx;
spin_lock_irq(&ctx->timeout_lock);
- posted = io_kill_linked_timeout(req);
+ link = io_disarm_linked_timeout(req);
spin_unlock_irq(&ctx->timeout_lock);
+ if (link) {
+ posted = true;
+ io_req_tw_post_queue(link, -ECANCELED, 0);
+ }
}
if (unlikely((req->flags & REQ_F_FAIL) &&
!(req->flags & REQ_F_HARDLINK))) {
spin_lock(&ctx->completion_lock);
posted = io_disarm_next(req);
- if (posted)
- io_commit_cqring(ctx);
+ io_commit_cqring(ctx);
spin_unlock(&ctx->completion_lock);
if (posted)
io_cqring_ev_posted(ctx);
{
struct io_kiocb *nxt;
- if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK))))
- return NULL;
/*
* If LINK is set, we have dependent requests in this chain. If we
* didn't fail this request, queue the first one up, moving any other
{
if (!ctx)
return;
+ if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
+ atomic_andnot(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
if (*locked) {
io_submit_flush_completions(ctx);
mutex_unlock(&ctx->uring_lock);
if (likely(*uring_locked))
req->io_task_work.func(req, uring_locked);
else
- __io_req_complete_post(req, req->result,
+ __io_req_complete_post(req, req->cqe.res,
io_put_kbuf_comp(req));
node = next;
} while (node);
while (1) {
struct io_wq_work_node *node1, *node2;
- if (!tctx->task_list.first &&
- !tctx->prior_task_list.first && uring_locked)
- io_submit_flush_completions(ctx);
-
spin_lock_irq(&tctx->task_lock);
- node1 = tctx->prior_task_list.first;
+ node1 = tctx->prio_task_list.first;
node2 = tctx->task_list.first;
INIT_WQ_LIST(&tctx->task_list);
- INIT_WQ_LIST(&tctx->prior_task_list);
+ INIT_WQ_LIST(&tctx->prio_task_list);
if (!node2 && !node1)
tctx->task_running = false;
spin_unlock_irq(&tctx->task_lock);
if (node1)
handle_prev_tw_list(node1, &ctx, &uring_locked);
-
if (node2)
handle_tw_list(node2, &ctx, &uring_locked);
cond_resched();
+
+ if (data_race(!tctx->task_list.first) &&
+ data_race(!tctx->prio_task_list.first) && uring_locked)
+ io_submit_flush_completions(ctx);
}
ctx_flush_and_put(ctx, &uring_locked);
io_uring_drop_tctx_refs(current);
}
-static void io_req_task_work_add(struct io_kiocb *req, bool priority)
+static void __io_req_task_work_add(struct io_kiocb *req,
+ struct io_uring_task *tctx,
+ struct io_wq_work_list *list)
{
- struct task_struct *tsk = req->task;
- struct io_uring_task *tctx = tsk->io_uring;
- enum task_work_notify_mode notify;
+ struct io_ring_ctx *ctx = req->ctx;
struct io_wq_work_node *node;
unsigned long flags;
bool running;
- WARN_ON_ONCE(!tctx);
-
spin_lock_irqsave(&tctx->task_lock, flags);
- if (priority)
- wq_list_add_tail(&req->io_task_work.node, &tctx->prior_task_list);
- else
- wq_list_add_tail(&req->io_task_work.node, &tctx->task_list);
+ wq_list_add_tail(&req->io_task_work.node, list);
running = tctx->task_running;
if (!running)
tctx->task_running = true;
if (running)
return;
- /*
- * SQPOLL kernel thread doesn't need notification, just a wakeup. For
- * all other cases, use TWA_SIGNAL unconditionally to ensure we're
- * processing task_work. There's no reliable way to tell if TWA_RESUME
- * will do the job.
- */
- notify = (req->ctx->flags & IORING_SETUP_SQPOLL) ? TWA_NONE : TWA_SIGNAL;
- if (likely(!task_work_add(tsk, &tctx->task_work, notify))) {
- if (notify == TWA_NONE)
- wake_up_process(tsk);
+ if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
+ atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
+
+ if (likely(!task_work_add(req->task, &tctx->task_work, ctx->notify_method)))
return;
- }
spin_lock_irqsave(&tctx->task_lock, flags);
tctx->task_running = false;
- node = wq_list_merge(&tctx->prior_task_list, &tctx->task_list);
+ node = wq_list_merge(&tctx->prio_task_list, &tctx->task_list);
spin_unlock_irqrestore(&tctx->task_lock, flags);
while (node) {
}
}
-static void io_req_task_cancel(struct io_kiocb *req, bool *locked)
+static void io_req_task_work_add(struct io_kiocb *req)
{
- struct io_ring_ctx *ctx = req->ctx;
+ struct io_uring_task *tctx = req->task->io_uring;
+
+ __io_req_task_work_add(req, tctx, &tctx->task_list);
+}
+
+static void io_req_task_prio_work_add(struct io_kiocb *req)
+{
+ struct io_uring_task *tctx = req->task->io_uring;
+ if (req->ctx->flags & IORING_SETUP_SQPOLL)
+ __io_req_task_work_add(req, tctx, &tctx->prio_task_list);
+ else
+ __io_req_task_work_add(req, tctx, &tctx->task_list);
+}
+
+static void io_req_tw_post(struct io_kiocb *req, bool *locked)
+{
+ io_req_complete_post(req, req->cqe.res, req->cqe.flags);
+}
+
+static void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags)
+{
+ req->cqe.res = res;
+ req->cqe.flags = cflags;
+ req->io_task_work.func = io_req_tw_post;
+ io_req_task_work_add(req);
+}
+
+static void io_req_task_cancel(struct io_kiocb *req, bool *locked)
+{
/* not needed for normal modes, but SQPOLL depends on it */
- io_tw_lock(ctx, locked);
- io_req_complete_failed(req, req->result);
+ io_tw_lock(req->ctx, locked);
+ io_req_complete_failed(req, req->cqe.res);
}
static void io_req_task_submit(struct io_kiocb *req, bool *locked)
{
- struct io_ring_ctx *ctx = req->ctx;
-
- io_tw_lock(ctx, locked);
+ io_tw_lock(req->ctx, locked);
/* req->task == current here, checking PF_EXITING is safe */
if (likely(!(req->task->flags & PF_EXITING)))
- __io_queue_sqe(req);
+ io_queue_sqe(req);
else
io_req_complete_failed(req, -EFAULT);
}
static void io_req_task_queue_fail(struct io_kiocb *req, int ret)
{
- req->result = ret;
+ req->cqe.res = ret;
req->io_task_work.func = io_req_task_cancel;
- io_req_task_work_add(req, false);
+ io_req_task_work_add(req);
}
static void io_req_task_queue(struct io_kiocb *req)
{
req->io_task_work.func = io_req_task_submit;
- io_req_task_work_add(req, false);
+ io_req_task_work_add(req);
}
static void io_req_task_queue_reissue(struct io_kiocb *req)
{
- req->io_task_work.func = io_queue_async_work;
- io_req_task_work_add(req, false);
+ req->io_task_work.func = io_queue_iowq;
+ io_req_task_work_add(req);
}
-static inline void io_queue_next(struct io_kiocb *req)
+static void io_queue_next(struct io_kiocb *req)
{
struct io_kiocb *nxt = io_req_find_next(req);
io_req_task_queue(nxt);
}
-static void io_free_req(struct io_kiocb *req)
-{
- io_queue_next(req);
- __io_free_req(req);
-}
-
-static void io_free_req_work(struct io_kiocb *req, bool *locked)
-{
- io_free_req(req);
-}
-
static void io_free_batch_list(struct io_ring_ctx *ctx,
struct io_wq_work_node *node)
__must_hold(&ctx->uring_lock)
struct io_kiocb *req = container_of(node, struct io_kiocb,
comp_list);
- if (unlikely(req->flags & REQ_F_REFCOUNT)) {
- node = req->comp_list.next;
- if (!req_ref_put_and_test(req))
- continue;
+ if (unlikely(req->flags & IO_REQ_CLEAN_SLOW_FLAGS)) {
+ if (req->flags & REQ_F_REFCOUNT) {
+ node = req->comp_list.next;
+ if (!req_ref_put_and_test(req))
+ continue;
+ }
+ if ((req->flags & REQ_F_POLLED) && req->apoll) {
+ struct async_poll *apoll = req->apoll;
+
+ if (apoll->double_poll)
+ kfree(apoll->double_poll);
+ list_add(&apoll->poll.wait.entry,
+ &ctx->apoll_cache);
+ req->flags &= ~REQ_F_POLLED;
+ }
+ if (req->flags & IO_REQ_LINK_FLAGS)
+ io_queue_next(req);
+ if (unlikely(req->flags & IO_REQ_CLEAN_FLAGS))
+ io_clean_op(req);
}
+ if (!(req->flags & REQ_F_FIXED_FILE))
+ io_put_file(req->file);
io_req_put_rsrc_locked(req, ctx);
- io_queue_next(req);
- io_dismantle_req(req);
if (req->task != task) {
if (task)
}
task_refs++;
node = req->comp_list.next;
- wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list);
+ io_req_add_to_cache(req, ctx);
} while (node);
if (task)
struct io_kiocb *req = container_of(node, struct io_kiocb,
comp_list);
- if (!(req->flags & REQ_F_CQE_SKIP))
- __io_fill_cqe_req(req, req->result, req->cflags);
- if ((req->flags & REQ_F_POLLED) && req->apoll) {
- struct async_poll *apoll = req->apoll;
-
- if (apoll->double_poll)
- kfree(apoll->double_poll);
- list_add(&apoll->poll.wait.entry,
- &ctx->apoll_cache);
- req->flags &= ~REQ_F_POLLED;
+ if (!(req->flags & REQ_F_CQE_SKIP)) {
+ if (!(ctx->flags & IORING_SETUP_CQE32))
+ __io_fill_cqe_req_filled(ctx, req);
+ else
+ __io_fill_cqe32_req_filled(ctx, req);
}
}
struct io_kiocb *nxt = NULL;
if (req_ref_put_and_test(req)) {
- nxt = io_req_find_next(req);
- __io_free_req(req);
+ if (unlikely(req->flags & IO_REQ_LINK_FLAGS))
+ nxt = io_req_find_next(req);
+ io_free_req(req);
}
return nxt;
}
static inline void io_put_req(struct io_kiocb *req)
-{
- if (req_ref_put_and_test(req))
- io_free_req(req);
-}
-
-static inline void io_put_req_deferred(struct io_kiocb *req)
{
if (req_ref_put_and_test(req)) {
- req->io_task_work.func = io_free_req_work;
- io_req_task_work_add(req, false);
+ io_queue_next(req);
+ io_free_req(req);
}
}
/* order with io_complete_rw_iopoll(), e.g. ->result updates */
if (!smp_load_acquire(&req->iopoll_completed))
break;
+ nr_events++;
if (unlikely(req->flags & REQ_F_CQE_SKIP))
continue;
-
- __io_fill_cqe_req(req, req->result, io_put_kbuf(req, 0));
- nr_events++;
+ __io_fill_cqe_req(req, req->cqe.res, io_put_kbuf(req, 0));
}
if (unlikely(!nr_events))
{
unsigned int nr_events = 0;
int ret = 0;
+ unsigned long check_cq;
- /*
- * We disallow the app entering submit/complete with polling, but we
- * still need to lock the ring to prevent racing with polled issue
- * that got punted to a workqueue.
- */
- mutex_lock(&ctx->uring_lock);
/*
* Don't enter poll loop if we already have events pending.
* If we do, we can potentially be spinning for commands that
* already triggered a CQE (eg in error).
*/
- if (test_bit(0, &ctx->check_cq_overflow))
+ check_cq = READ_ONCE(ctx->check_cq);
+ if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT))
__io_cqring_overflow_flush(ctx, false);
if (io_cqring_events(ctx))
- goto out;
+ return 0;
+
+ /*
+ * Similarly do not spin if we have not informed the user of any
+ * dropped CQE.
+ */
+ if (unlikely(check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT)))
+ return -EBADR;
+
do {
/*
* If a submit got punted to a workqueue, we can have the
nr_events += ret;
ret = 0;
} while (nr_events < min && !need_resched());
-out:
- mutex_unlock(&ctx->uring_lock);
+
return ret;
}
} else {
fsnotify_access(req->file);
}
- if (unlikely(res != req->result)) {
+ if (unlikely(res != req->cqe.res)) {
if ((res == -EAGAIN || res == -EOPNOTSUPP) &&
io_rw_should_reissue(req)) {
req->flags |= REQ_F_REISSUE;
return true;
}
req_set_fail(req);
- req->result = res;
+ req->cqe.res = res;
}
return false;
}
static inline void io_req_task_complete(struct io_kiocb *req, bool *locked)
{
- int res = req->result;
+ int res = req->cqe.res;
if (*locked) {
io_req_complete_state(req, res, io_put_kbuf(req, 0));
{
if (__io_complete_rw_common(req, res))
return;
- __io_req_complete(req, issue_flags, req->result,
+ __io_req_complete(req, issue_flags, req->cqe.res,
io_put_kbuf(req, issue_flags));
}
if (__io_complete_rw_common(req, res))
return;
- req->result = res;
+ req->cqe.res = res;
req->io_task_work.func = io_req_task_complete;
- io_req_task_work_add(req, !!(req->ctx->flags & IORING_SETUP_SQPOLL));
+ io_req_task_prio_work_add(req);
}
static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
if (kiocb->ki_flags & IOCB_WRITE)
kiocb_end_write(req);
- if (unlikely(res != req->result)) {
+ if (unlikely(res != req->cqe.res)) {
if (res == -EAGAIN && io_rw_should_reissue(req)) {
req->flags |= REQ_F_REISSUE;
return;
}
- req->result = res;
+ req->cqe.res = res;
}
/* order with io_iopoll_complete() checking ->iopoll_completed */
res |= FFS_ISREG;
if (__io_file_supports_nowait(file, mode))
res |= FFS_NOWAIT;
+ if (io_file_need_scm(file))
+ res |= FFS_SCM;
return res;
}
static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- struct io_ring_ctx *ctx = req->ctx;
struct kiocb *kiocb = &req->rw.kiocb;
- struct file *file = req->file;
unsigned ioprio;
int ret;
- if (!io_req_ffs_set(req))
- req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;
-
kiocb->ki_pos = READ_ONCE(sqe->off);
- kiocb->ki_flags = iocb_flags(file);
- ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
- if (unlikely(ret))
- return ret;
-
- /*
- * If the file is marked O_NONBLOCK, still allow retry for it if it
- * supports async. Otherwise it's impossible to use O_NONBLOCK files
- * reliably. If not, or it IOCB_NOWAIT is set, don't retry.
- */
- if ((kiocb->ki_flags & IOCB_NOWAIT) ||
- ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
- req->flags |= REQ_F_NOWAIT;
-
- if (ctx->flags & IORING_SETUP_IOPOLL) {
- if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
- return -EOPNOTSUPP;
-
- kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE;
- kiocb->ki_complete = io_complete_rw_iopoll;
- req->iopoll_completed = 0;
- } else {
- if (kiocb->ki_flags & IOCB_HIPRI)
- return -EINVAL;
- kiocb->ki_complete = io_complete_rw;
- }
ioprio = READ_ONCE(sqe->ioprio);
if (ioprio) {
req->imu = NULL;
req->rw.addr = READ_ONCE(sqe->addr);
req->rw.len = READ_ONCE(sqe->len);
+ req->rw.flags = READ_ONCE(sqe->rw_flags);
+ /* used for fixed read/write too - just read unconditionally */
req->buf_index = READ_ONCE(sqe->buf_index);
return 0;
}
static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req)
{
struct kiocb *kiocb = &req->rw.kiocb;
- bool is_stream = req->file->f_mode & FMODE_STREAM;
- if (kiocb->ki_pos == -1) {
- if (!is_stream) {
- req->flags |= REQ_F_CUR_POS;
- kiocb->ki_pos = req->file->f_pos;
- return &kiocb->ki_pos;
- } else {
- kiocb->ki_pos = 0;
- return NULL;
- }
+ if (kiocb->ki_pos != -1)
+ return &kiocb->ki_pos;
+
+ if (!(req->file->f_mode & FMODE_STREAM)) {
+ req->flags |= REQ_F_CUR_POS;
+ kiocb->ki_pos = req->file->f_pos;
+ return &kiocb->ki_pos;
}
- return is_stream ? NULL : &kiocb->ki_pos;
+
+ kiocb->ki_pos = 0;
+ return NULL;
}
static void kiocb_done(struct io_kiocb *req, ssize_t ret,
return 0;
}
-static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
+static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter,
+ unsigned int issue_flags)
{
struct io_mapped_ubuf *imu = req->imu;
u16 index, buf_index = req->buf_index;
if (unlikely(buf_index >= ctx->nr_user_bufs))
return -EFAULT;
- io_req_set_rsrc_node(req, ctx);
+ io_req_set_rsrc_node(req, ctx, issue_flags);
index = array_index_nospec(buf_index, ctx->nr_user_bufs);
imu = READ_ONCE(ctx->user_bufs[index]);
req->imu = imu;
return __io_import_fixed(req, rw, iter, imu);
}
-static void io_ring_submit_unlock(struct io_ring_ctx *ctx, bool needs_lock)
+static int io_buffer_add_list(struct io_ring_ctx *ctx,
+ struct io_buffer_list *bl, unsigned int bgid)
{
- if (needs_lock)
- mutex_unlock(&ctx->uring_lock);
-}
+ bl->bgid = bgid;
+ if (bgid < BGID_ARRAY)
+ return 0;
-static void io_ring_submit_lock(struct io_ring_ctx *ctx, bool needs_lock)
-{
- /*
- * "Normal" inline submissions always hold the uring_lock, since we
- * grab it from the system call. Same is true for the SQPOLL offload.
- * The only exception is when we've detached the request and issue it
- * from an async worker thread, grab the lock for that case.
- */
- if (needs_lock)
- mutex_lock(&ctx->uring_lock);
+ return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL));
}
-static void io_buffer_add_list(struct io_ring_ctx *ctx,
- struct io_buffer_list *bl, unsigned int bgid)
+static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len,
+ struct io_buffer_list *bl)
{
- struct list_head *list;
+ if (!list_empty(&bl->buf_list)) {
+ struct io_buffer *kbuf;
- list = &ctx->io_buffers[hash_32(bgid, IO_BUFFERS_HASH_BITS)];
- INIT_LIST_HEAD(&bl->buf_list);
- bl->bgid = bgid;
- list_add(&bl->list, list);
-}
-
-static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len,
- int bgid, unsigned int issue_flags)
-{
- struct io_buffer *kbuf = req->kbuf;
- bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
- struct io_ring_ctx *ctx = req->ctx;
- struct io_buffer_list *bl;
-
- if (req->flags & REQ_F_BUFFER_SELECTED)
- return kbuf;
-
- io_ring_submit_lock(ctx, needs_lock);
-
- lockdep_assert_held(&ctx->uring_lock);
-
- bl = io_buffer_get_list(ctx, bgid);
- if (bl && !list_empty(&bl->buf_list)) {
kbuf = list_first_entry(&bl->buf_list, struct io_buffer, list);
list_del(&kbuf->list);
if (*len > kbuf->len)
*len = kbuf->len;
req->flags |= REQ_F_BUFFER_SELECTED;
req->kbuf = kbuf;
+ req->buf_index = kbuf->bid;
+ return u64_to_user_ptr(kbuf->addr);
+ }
+ return NULL;
+}
+
+static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
+ struct io_buffer_list *bl,
+ unsigned int issue_flags)
+{
+ struct io_uring_buf_ring *br = bl->buf_ring;
+ struct io_uring_buf *buf;
+ __u32 head = bl->head;
+
+ if (unlikely(smp_load_acquire(&br->tail) == head)) {
+ io_ring_submit_unlock(req->ctx, issue_flags);
+ return NULL;
+ }
+
+ head &= bl->mask;
+ if (head < IO_BUFFER_LIST_BUF_PER_PAGE) {
+ buf = &br->bufs[head];
} else {
- kbuf = ERR_PTR(-ENOBUFS);
+ int off = head & (IO_BUFFER_LIST_BUF_PER_PAGE - 1);
+ int index = head / IO_BUFFER_LIST_BUF_PER_PAGE - 1;
+ buf = page_address(bl->buf_pages[index]);
+ buf += off;
}
+ if (*len > buf->len)
+ *len = buf->len;
+ req->flags |= REQ_F_BUFFER_RING;
+ req->buf_list = bl;
+ req->buf_index = buf->bid;
- io_ring_submit_unlock(req->ctx, needs_lock);
- return kbuf;
+ if (issue_flags & IO_URING_F_UNLOCKED) {
+ /*
+ * If we came in unlocked, we have no choice but to consume the
+ * buffer here. This does mean it'll be pinned until the IO
+ * completes. But coming in unlocked means we're in io-wq
+ * context, hence there should be no further retry. For the
+ * locked case, the caller must ensure to call the commit when
+ * the transfer completes (or if we get -EAGAIN and must poll
+ * or retry).
+ */
+ req->buf_list = NULL;
+ bl->head++;
+ }
+ return u64_to_user_ptr(buf->addr);
}
-static void __user *io_rw_buffer_select(struct io_kiocb *req, size_t *len,
- unsigned int issue_flags)
+static void __user *io_buffer_select(struct io_kiocb *req, size_t *len,
+ unsigned int issue_flags)
{
- struct io_buffer *kbuf;
- u16 bgid;
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_buffer_list *bl;
+ void __user *ret = NULL;
+
+ io_ring_submit_lock(req->ctx, issue_flags);
- bgid = req->buf_index;
- kbuf = io_buffer_select(req, len, bgid, issue_flags);
- if (IS_ERR(kbuf))
- return kbuf;
- return u64_to_user_ptr(kbuf->addr);
+ bl = io_buffer_get_list(ctx, req->buf_index);
+ if (likely(bl)) {
+ if (bl->buf_nr_pages)
+ ret = io_ring_buffer_select(req, len, bl, issue_flags);
+ else
+ ret = io_provided_buffer_select(req, len, bl);
+ }
+ io_ring_submit_unlock(req->ctx, issue_flags);
+ return ret;
}
#ifdef CONFIG_COMPAT
struct compat_iovec __user *uiov;
compat_ssize_t clen;
void __user *buf;
- ssize_t len;
+ size_t len;
uiov = u64_to_user_ptr(req->rw.addr);
if (!access_ok(uiov, sizeof(*uiov)))
return -EINVAL;
len = clen;
- buf = io_rw_buffer_select(req, &len, issue_flags);
- if (IS_ERR(buf))
- return PTR_ERR(buf);
+ buf = io_buffer_select(req, &len, issue_flags);
+ if (!buf)
+ return -ENOBUFS;
+ req->rw.addr = (unsigned long) buf;
iov[0].iov_base = buf;
- iov[0].iov_len = (compat_size_t) len;
+ req->rw.len = iov[0].iov_len = (compat_size_t) len;
return 0;
}
#endif
len = iov[0].iov_len;
if (len < 0)
return -EINVAL;
- buf = io_rw_buffer_select(req, &len, issue_flags);
- if (IS_ERR(buf))
- return PTR_ERR(buf);
+ buf = io_buffer_select(req, &len, issue_flags);
+ if (!buf)
+ return -ENOBUFS;
+ req->rw.addr = (unsigned long) buf;
iov[0].iov_base = buf;
- iov[0].iov_len = len;
+ req->rw.len = iov[0].iov_len = len;
return 0;
}
static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
unsigned int issue_flags)
{
- if (req->flags & REQ_F_BUFFER_SELECTED) {
- struct io_buffer *kbuf = req->kbuf;
-
- iov[0].iov_base = u64_to_user_ptr(kbuf->addr);
- iov[0].iov_len = kbuf->len;
+ if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) {
+ iov[0].iov_base = u64_to_user_ptr(req->rw.addr);
+ iov[0].iov_len = req->rw.len;
return 0;
}
if (req->rw.len != 1)
return __io_iov_buffer_select(req, iov, issue_flags);
}
+static inline bool io_do_buffer_select(struct io_kiocb *req)
+{
+ if (!(req->flags & REQ_F_BUFFER_SELECT))
+ return false;
+ return !(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING));
+}
+
static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req,
struct io_rw_state *s,
unsigned int issue_flags)
ssize_t ret;
if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) {
- ret = io_import_fixed(req, rw, iter);
+ ret = io_import_fixed(req, rw, iter, issue_flags);
if (ret)
return ERR_PTR(ret);
return NULL;
}
- /* buffer index only valid with fixed read/write, or buffer select */
- if (unlikely(req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT)))
- return ERR_PTR(-EINVAL);
-
buf = u64_to_user_ptr(req->rw.addr);
sqe_len = req->rw.len;
if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
- if (req->flags & REQ_F_BUFFER_SELECT) {
- buf = io_rw_buffer_select(req, &sqe_len, issue_flags);
- if (IS_ERR(buf))
- return ERR_CAST(buf);
+ if (io_do_buffer_select(req)) {
+ buf = io_buffer_select(req, &sqe_len, issue_flags);
+ if (!buf)
+ return ERR_PTR(-ENOBUFS);
+ req->rw.addr = (unsigned long) buf;
req->rw.len = sqe_len;
}
return 0;
}
-static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+static int io_readv_prep_async(struct io_kiocb *req)
{
- if (unlikely(!(req->file->f_mode & FMODE_READ)))
- return -EBADF;
- return io_prep_rw(req, sqe);
+ return io_rw_prep_async(req, READ);
+}
+
+static int io_writev_prep_async(struct io_kiocb *req)
+{
+ return io_rw_prep_async(req, WRITE);
}
/*
S_ISBLK(file_inode(req->file)->i_mode);
}
+static int io_rw_init_file(struct io_kiocb *req, fmode_t mode)
+{
+ struct kiocb *kiocb = &req->rw.kiocb;
+ struct io_ring_ctx *ctx = req->ctx;
+ struct file *file = req->file;
+ int ret;
+
+ if (unlikely(!file || !(file->f_mode & mode)))
+ return -EBADF;
+
+ if (!io_req_ffs_set(req))
+ req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;
+
+ kiocb->ki_flags = iocb_flags(file);
+ ret = kiocb_set_rw_flags(kiocb, req->rw.flags);
+ if (unlikely(ret))
+ return ret;
+
+ /*
+ * If the file is marked O_NONBLOCK, still allow retry for it if it
+ * supports async. Otherwise it's impossible to use O_NONBLOCK files
+ * reliably. If not, or it IOCB_NOWAIT is set, don't retry.
+ */
+ if ((kiocb->ki_flags & IOCB_NOWAIT) ||
+ ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
+ req->flags |= REQ_F_NOWAIT;
+
+ if (ctx->flags & IORING_SETUP_IOPOLL) {
+ if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
+ return -EOPNOTSUPP;
+
+ kiocb->private = NULL;
+ kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE;
+ kiocb->ki_complete = io_complete_rw_iopoll;
+ req->iopoll_completed = 0;
+ } else {
+ if (kiocb->ki_flags & IOCB_HIPRI)
+ return -EINVAL;
+ kiocb->ki_complete = io_complete_rw;
+ }
+
+ return 0;
+}
+
static int io_read(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_rw_state __s, *s = &__s;
iov_iter_restore(&s->iter, &s->iter_state);
iovec = NULL;
}
- req->result = iov_iter_count(&s->iter);
+ ret = io_rw_init_file(req, FMODE_READ);
+ if (unlikely(ret)) {
+ kfree(iovec);
+ return ret;
+ }
+ req->cqe.res = iov_iter_count(&s->iter);
if (force_nonblock) {
/* If the file doesn't support async, just async punt */
ppos = io_kiocb_update_pos(req);
- ret = rw_verify_area(READ, req->file, ppos, req->result);
+ ret = rw_verify_area(READ, req->file, ppos, req->cqe.res);
if (unlikely(ret)) {
kfree(iovec);
return ret;
ret = 0;
} else if (ret == -EIOCBQUEUED) {
goto out_free;
- } else if (ret == req->result || ret <= 0 || !force_nonblock ||
+ } else if (ret == req->cqe.res || ret <= 0 || !force_nonblock ||
(req->flags & REQ_F_NOWAIT) || !need_read_all(req)) {
/* read all, failed, already did sync or don't want to retry */
goto done;
return 0;
}
-static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- if (unlikely(!(req->file->f_mode & FMODE_WRITE)))
- return -EBADF;
- return io_prep_rw(req, sqe);
-}
-
static int io_write(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_rw_state __s, *s = &__s;
iov_iter_restore(&s->iter, &s->iter_state);
iovec = NULL;
}
- req->result = iov_iter_count(&s->iter);
+ ret = io_rw_init_file(req, FMODE_WRITE);
+ if (unlikely(ret)) {
+ kfree(iovec);
+ return ret;
+ }
+ req->cqe.res = iov_iter_count(&s->iter);
if (force_nonblock) {
/* If the file doesn't support async, just async punt */
ppos = io_kiocb_update_pos(req);
- ret = rw_verify_area(WRITE, req->file, ppos, req->result);
+ ret = rw_verify_area(WRITE, req->file, ppos, req->cqe.res);
if (unlikely(ret))
goto out_free;
struct io_rename *ren = &req->rename;
const char __user *oldf, *newf;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in)
+ if (sqe->buf_index || sqe->splice_fd_in)
return -EINVAL;
if (unlikely(req->flags & REQ_F_FIXED_FILE))
return -EBADF;
ren->newpath, ren->flags);
req->flags &= ~REQ_F_NEED_CLEANUP;
- if (ret < 0)
- req_set_fail(req);
io_req_complete(req, ret);
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);
+ 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->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)
+{
+ struct io_xattr *ix = &req->xattr;
+ const char __user *name;
+ int ret;
+
+ 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)
{
struct io_unlink *un = &req->unlink;
const char __user *fname;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index ||
- sqe->splice_fd_in)
+ if (sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in)
return -EINVAL;
if (unlikely(req->flags & REQ_F_FIXED_FILE))
return -EBADF;
ret = do_unlinkat(un->dfd, un->filename);
req->flags &= ~REQ_F_NEED_CLEANUP;
- if (ret < 0)
- req_set_fail(req);
io_req_complete(req, ret);
return 0;
}
struct io_mkdir *mkd = &req->mkdir;
const char __user *fname;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (sqe->ioprio || sqe->off || sqe->rw_flags || sqe->buf_index ||
- sqe->splice_fd_in)
+ if (sqe->off || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
return -EINVAL;
if (unlikely(req->flags & REQ_F_FIXED_FILE))
return -EBADF;
ret = do_mkdirat(mkd->dfd, mkd->filename, mkd->mode);
req->flags &= ~REQ_F_NEED_CLEANUP;
- if (ret < 0)
- req_set_fail(req);
io_req_complete(req, ret);
return 0;
}
struct io_symlink *sl = &req->symlink;
const char __user *oldpath, *newpath;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (sqe->ioprio || sqe->len || sqe->rw_flags || sqe->buf_index ||
- sqe->splice_fd_in)
+ if (sqe->len || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
return -EINVAL;
if (unlikely(req->flags & REQ_F_FIXED_FILE))
return -EBADF;
ret = do_symlinkat(sl->oldpath, sl->new_dfd, sl->newpath);
req->flags &= ~REQ_F_NEED_CLEANUP;
- if (ret < 0)
- req_set_fail(req);
io_req_complete(req, ret);
return 0;
}
struct io_hardlink *lnk = &req->hardlink;
const char __user *oldf, *newf;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (sqe->ioprio || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
+ if (sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
return -EINVAL;
if (unlikely(req->flags & REQ_F_FIXED_FILE))
return -EBADF;
lnk->newpath, lnk->flags);
req->flags &= ~REQ_F_NEED_CLEANUP;
+ io_req_complete(req, ret);
+ return 0;
+}
+
+static void io_uring_cmd_work(struct io_kiocb *req, bool *locked)
+{
+ req->uring_cmd.task_work_cb(&req->uring_cmd);
+}
+
+void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
+ void (*task_work_cb)(struct io_uring_cmd *))
+{
+ struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd);
+
+ req->uring_cmd.task_work_cb = task_work_cb;
+ req->io_task_work.func = io_uring_cmd_work;
+ io_req_task_prio_work_add(req);
+}
+EXPORT_SYMBOL_GPL(io_uring_cmd_complete_in_task);
+
+/*
+ * Called by consumers of io_uring_cmd, if they originally returned
+ * -EIOCBQUEUED upon receiving the command.
+ */
+void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2)
+{
+ struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd);
+
if (ret < 0)
req_set_fail(req);
- io_req_complete(req, ret);
+ if (req->ctx->flags & IORING_SETUP_CQE32)
+ __io_req_complete32(req, 0, ret, 0, res2, 0);
+ else
+ io_req_complete(req, ret);
+}
+EXPORT_SYMBOL_GPL(io_uring_cmd_done);
+
+static int io_uring_cmd_prep_async(struct io_kiocb *req)
+{
+ size_t cmd_size;
+
+ cmd_size = uring_cmd_pdu_size(req->ctx->flags & IORING_SETUP_SQE128);
+
+ memcpy(req->async_data, req->uring_cmd.cmd, cmd_size);
return 0;
}
-static int io_shutdown_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
+static int io_uring_cmd_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
{
-#if defined(CONFIG_NET)
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (unlikely(sqe->ioprio || sqe->off || sqe->addr || sqe->rw_flags ||
- sqe->buf_index || sqe->splice_fd_in))
- return -EINVAL;
+ struct io_uring_cmd *ioucmd = &req->uring_cmd;
- req->shutdown.how = READ_ONCE(sqe->len);
+ if (sqe->rw_flags)
+ return -EINVAL;
+ ioucmd->cmd = sqe->cmd;
+ ioucmd->cmd_op = READ_ONCE(sqe->cmd_op);
return 0;
-#else
- return -EOPNOTSUPP;
-#endif
}
-static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags)
+static int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
{
-#if defined(CONFIG_NET)
- struct socket *sock;
+ struct io_uring_cmd *ioucmd = &req->uring_cmd;
+ struct io_ring_ctx *ctx = req->ctx;
+ struct file *file = req->file;
int ret;
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
+ if (!req->file->f_op->uring_cmd)
+ return -EOPNOTSUPP;
- sock = sock_from_file(req->file);
- if (unlikely(!sock))
- return -ENOTSOCK;
+ if (ctx->flags & IORING_SETUP_SQE128)
+ issue_flags |= IO_URING_F_SQE128;
+ if (ctx->flags & IORING_SETUP_CQE32)
+ issue_flags |= IO_URING_F_CQE32;
+ if (ctx->flags & IORING_SETUP_IOPOLL)
+ issue_flags |= IO_URING_F_IOPOLL;
+
+ if (req_has_async_data(req))
+ ioucmd->cmd = req->async_data;
+
+ ret = file->f_op->uring_cmd(ioucmd, issue_flags);
+ if (ret == -EAGAIN) {
+ if (!req_has_async_data(req)) {
+ if (io_alloc_async_data(req))
+ return -ENOMEM;
+ io_uring_cmd_prep_async(req);
+ }
+ return -EAGAIN;
+ }
- ret = __sys_shutdown_sock(sock, req->shutdown.how);
- if (ret < 0)
- req_set_fail(req);
- io_req_complete(req, ret);
+ if (ret != -EIOCBQUEUED)
+ io_uring_cmd_done(ioucmd, ret, 0);
return 0;
-#else
- return -EOPNOTSUPP;
-#endif
}
static int __io_splice_prep(struct io_kiocb *req,
struct io_splice *sp = &req->splice;
unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
-
- sp->file_in = NULL;
sp->len = READ_ONCE(sqe->len);
sp->flags = READ_ONCE(sqe->splice_flags);
-
if (unlikely(sp->flags & ~valid_flags))
return -EINVAL;
-
- sp->file_in = io_file_get(req->ctx, req, READ_ONCE(sqe->splice_fd_in),
- (sp->flags & SPLICE_F_FD_IN_FIXED));
- if (!sp->file_in)
- return -EBADF;
- req->flags |= REQ_F_NEED_CLEANUP;
+ sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in);
return 0;
}
static int io_tee(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_splice *sp = &req->splice;
- struct file *in = sp->file_in;
struct file *out = sp->file_out;
unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
+ struct file *in;
long ret = 0;
if (issue_flags & IO_URING_F_NONBLOCK)
return -EAGAIN;
+
+ if (sp->flags & SPLICE_F_FD_IN_FIXED)
+ in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags);
+ else
+ in = io_file_get_normal(req, sp->splice_fd_in);
+ if (!in) {
+ ret = -EBADF;
+ goto done;
+ }
+
if (sp->len)
ret = do_tee(in, out, sp->len, flags);
if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
io_put_file(in);
- req->flags &= ~REQ_F_NEED_CLEANUP;
-
+done:
if (ret != sp->len)
req_set_fail(req);
- io_req_complete(req, ret);
+ __io_req_complete(req, 0, ret, 0);
return 0;
}
static int io_splice(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_splice *sp = &req->splice;
- struct file *in = sp->file_in;
struct file *out = sp->file_out;
unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
loff_t *poff_in, *poff_out;
+ struct file *in;
long ret = 0;
if (issue_flags & IO_URING_F_NONBLOCK)
return -EAGAIN;
+ if (sp->flags & SPLICE_F_FD_IN_FIXED)
+ in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags);
+ else
+ in = io_file_get_normal(req, sp->splice_fd_in);
+ if (!in) {
+ ret = -EBADF;
+ goto done;
+ }
+
poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;
if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
io_put_file(in);
- req->flags &= ~REQ_F_NEED_CLEANUP;
-
+done:
if (ret != sp->len)
req_set_fail(req);
- io_req_complete(req, ret);
+ __io_req_complete(req, 0, ret, 0);
+ return 0;
+}
+
+static int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ /*
+ * If the ring is setup with CQE32, relay back addr/addr
+ */
+ if (req->ctx->flags & IORING_SETUP_CQE32) {
+ req->nop.extra1 = READ_ONCE(sqe->addr);
+ req->nop.extra2 = READ_ONCE(sqe->addr2);
+ }
+
return 0;
}
*/
static int io_nop(struct io_kiocb *req, unsigned int issue_flags)
{
- struct io_ring_ctx *ctx = req->ctx;
+ unsigned int cflags;
+ void __user *buf;
- if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
+ if (req->flags & REQ_F_BUFFER_SELECT) {
+ size_t len = 1;
+
+ buf = io_buffer_select(req, &len, issue_flags);
+ if (!buf)
+ return -ENOBUFS;
+ }
- __io_req_complete(req, issue_flags, 0, 0);
+ cflags = io_put_kbuf(req, issue_flags);
+ if (!(req->ctx->flags & IORING_SETUP_CQE32))
+ __io_req_complete(req, issue_flags, 0, cflags);
+ else
+ __io_req_complete32(req, issue_flags, 0, cflags,
+ req->nop.extra1, req->nop.extra2);
return 0;
}
static int io_msg_ring_prep(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
- if (unlikely(sqe->addr || sqe->ioprio || sqe->rw_flags ||
- sqe->splice_fd_in || sqe->buf_index || sqe->personality))
+ if (unlikely(sqe->addr || sqe->rw_flags || sqe->splice_fd_in ||
+ sqe->buf_index || sqe->personality))
return -EINVAL;
req->msg.user_data = READ_ONCE(sqe->off);
if (ret < 0)
req_set_fail(req);
__io_req_complete(req, issue_flags, ret, 0);
+ /* put file to avoid an attempt to IOPOLL the req */
+ io_put_file(req->file);
+ req->file = NULL;
return 0;
}
static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- struct io_ring_ctx *ctx = req->ctx;
-
- if (!req->file)
- return -EBADF;
-
- if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index ||
- sqe->splice_fd_in))
+ if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in))
return -EINVAL;
req->sync.flags = READ_ONCE(sqe->fsync_flags);
ret = vfs_fsync_range(req->file, req->sync.off,
end > 0 ? end : LLONG_MAX,
req->sync.flags & IORING_FSYNC_DATASYNC);
- if (ret < 0)
- req_set_fail(req);
io_req_complete(req, ret);
return 0;
}
static int io_fallocate_prep(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
- if (sqe->ioprio || sqe->buf_index || sqe->rw_flags ||
- sqe->splice_fd_in)
- return -EINVAL;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ if (sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in)
return -EINVAL;
req->sync.off = READ_ONCE(sqe->off);
return -EAGAIN;
ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off,
req->sync.len);
- if (ret < 0)
- req_set_fail(req);
- else
+ if (ret >= 0)
fsnotify_modify(req->file);
io_req_complete(req, ret);
return 0;
const char __user *fname;
int ret;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (unlikely(sqe->ioprio || sqe->buf_index))
+ if (unlikely(sqe->buf_index))
return -EINVAL;
if (unlikely(req->flags & REQ_F_FIXED_FILE))
return -EBADF;
return __io_openat_prep(req, sqe);
}
+static int io_file_bitmap_get(struct io_ring_ctx *ctx)
+{
+ struct io_file_table *table = &ctx->file_table;
+ unsigned long nr = ctx->nr_user_files;
+ int ret;
+
+ do {
+ ret = find_next_zero_bit(table->bitmap, nr, table->alloc_hint);
+ if (ret != nr)
+ return ret;
+
+ if (!table->alloc_hint)
+ break;
+
+ nr = table->alloc_hint;
+ table->alloc_hint = 0;
+ } while (1);
+
+ return -ENFILE;
+}
+
+/*
+ * Note when io_fixed_fd_install() returns error value, it will ensure
+ * fput() is called correspondingly.
+ */
+static int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags,
+ struct file *file, unsigned int file_slot)
+{
+ bool alloc_slot = file_slot == IORING_FILE_INDEX_ALLOC;
+ struct io_ring_ctx *ctx = req->ctx;
+ int ret;
+
+ io_ring_submit_lock(ctx, issue_flags);
+
+ if (alloc_slot) {
+ ret = io_file_bitmap_get(ctx);
+ if (unlikely(ret < 0))
+ goto err;
+ file_slot = ret;
+ } else {
+ file_slot--;
+ }
+
+ ret = io_install_fixed_file(req, file, issue_flags, file_slot);
+ if (!ret && alloc_slot)
+ ret = file_slot;
+err:
+ io_ring_submit_unlock(ctx, issue_flags);
+ if (unlikely(ret < 0))
+ fput(file);
+ return ret;
+}
+
static int io_openat2(struct io_kiocb *req, unsigned int issue_flags)
{
struct open_flags op;
if (!fixed)
fd_install(ret, file);
else
- ret = io_install_fixed_file(req, file, issue_flags,
- req->open.file_slot - 1);
+ ret = io_fixed_fd_install(req, issue_flags, file,
+ req->open.file_slot);
err:
putname(req->open.filename);
req->flags &= ~REQ_F_NEED_CLEANUP;
struct io_provide_buf *p = &req->pbuf;
u64 tmp;
- if (sqe->ioprio || sqe->rw_flags || sqe->addr || sqe->len || sqe->off ||
+ if (sqe->rw_flags || sqe->addr || sqe->len || sqe->off ||
sqe->splice_fd_in)
return -EINVAL;
if (!nbufs)
return 0;
+ if (bl->buf_nr_pages) {
+ int j;
+
+ i = bl->buf_ring->tail - bl->head;
+ for (j = 0; j < bl->buf_nr_pages; j++)
+ unpin_user_page(bl->buf_pages[j]);
+ kvfree(bl->buf_pages);
+ bl->buf_pages = NULL;
+ bl->buf_nr_pages = 0;
+ /* make sure it's seen as empty */
+ INIT_LIST_HEAD(&bl->buf_list);
+ return i;
+ }
+
/* the head kbuf is the list itself */
while (!list_empty(&bl->buf_list)) {
struct io_buffer *nxt;
struct io_ring_ctx *ctx = req->ctx;
struct io_buffer_list *bl;
int ret = 0;
- bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
- io_ring_submit_lock(ctx, needs_lock);
-
- lockdep_assert_held(&ctx->uring_lock);
+ io_ring_submit_lock(ctx, issue_flags);
ret = -ENOENT;
bl = io_buffer_get_list(ctx, p->bgid);
- if (bl)
- ret = __io_remove_buffers(ctx, bl, p->nbufs);
+ if (bl) {
+ ret = -EINVAL;
+ /* can't use provide/remove buffers command on mapped buffers */
+ if (!bl->buf_nr_pages)
+ ret = __io_remove_buffers(ctx, bl, p->nbufs);
+ }
if (ret < 0)
req_set_fail(req);
/* complete before unlock, IOPOLL may need the lock */
__io_req_complete(req, issue_flags, ret, 0);
- io_ring_submit_unlock(ctx, needs_lock);
+ io_ring_submit_unlock(ctx, issue_flags);
return 0;
}
struct io_provide_buf *p = &req->pbuf;
u64 tmp;
- if (sqe->ioprio || sqe->rw_flags || sqe->splice_fd_in)
+ if (sqe->rw_flags || sqe->splice_fd_in)
return -EINVAL;
tmp = READ_ONCE(sqe->fd);
return i ? 0 : -ENOMEM;
}
+static __cold int io_init_bl_list(struct io_ring_ctx *ctx)
+{
+ int i;
+
+ ctx->io_bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list),
+ GFP_KERNEL);
+ if (!ctx->io_bl)
+ return -ENOMEM;
+
+ for (i = 0; i < BGID_ARRAY; i++) {
+ INIT_LIST_HEAD(&ctx->io_bl[i].buf_list);
+ ctx->io_bl[i].bgid = i;
+ }
+
+ return 0;
+}
+
static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_provide_buf *p = &req->pbuf;
struct io_ring_ctx *ctx = req->ctx;
struct io_buffer_list *bl;
int ret = 0;
- bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
- io_ring_submit_lock(ctx, needs_lock);
+ io_ring_submit_lock(ctx, issue_flags);
- lockdep_assert_held(&ctx->uring_lock);
+ if (unlikely(p->bgid < BGID_ARRAY && !ctx->io_bl)) {
+ ret = io_init_bl_list(ctx);
+ if (ret)
+ goto err;
+ }
bl = io_buffer_get_list(ctx, p->bgid);
if (unlikely(!bl)) {
- bl = kmalloc(sizeof(*bl), GFP_KERNEL);
+ bl = kzalloc(sizeof(*bl), GFP_KERNEL);
if (!bl) {
ret = -ENOMEM;
goto err;
}
- io_buffer_add_list(ctx, bl, p->bgid);
+ INIT_LIST_HEAD(&bl->buf_list);
+ ret = io_buffer_add_list(ctx, bl, p->bgid);
+ if (ret) {
+ kfree(bl);
+ goto err;
+ }
+ }
+ /* can't add buffers via this command for a mapped buffer ring */
+ if (bl->buf_nr_pages) {
+ ret = -EINVAL;
+ goto err;
}
ret = io_add_buffers(ctx, p, bl);
req_set_fail(req);
/* complete before unlock, IOPOLL may need the lock */
__io_req_complete(req, issue_flags, ret, 0);
- io_ring_submit_unlock(ctx, needs_lock);
+ io_ring_submit_unlock(ctx, issue_flags);
return 0;
}
const struct io_uring_sqe *sqe)
{
#if defined(CONFIG_EPOLL)
- if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in)
- return -EINVAL;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ if (sqe->buf_index || sqe->splice_fd_in)
return -EINVAL;
req->epoll.epfd = READ_ONCE(sqe->fd);
static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
- if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->splice_fd_in)
- return -EINVAL;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ if (sqe->buf_index || sqe->off || sqe->splice_fd_in)
return -EINVAL;
req->madvise.addr = READ_ONCE(sqe->addr);
return -EAGAIN;
ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice);
- if (ret < 0)
- req_set_fail(req);
io_req_complete(req, ret);
return 0;
#else
static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- if (sqe->ioprio || sqe->buf_index || sqe->addr || sqe->splice_fd_in)
- return -EINVAL;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ if (sqe->buf_index || sqe->addr || sqe->splice_fd_in)
return -EINVAL;
req->fadvise.offset = READ_ONCE(sqe->off);
{
const char __user *path;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in)
+ if (sqe->buf_index || sqe->splice_fd_in)
return -EINVAL;
if (req->flags & REQ_F_FIXED_FILE)
return -EBADF;
ret = do_statx(ctx->dfd, ctx->filename, ctx->flags, ctx->mask,
ctx->buffer);
-
- if (ret < 0)
- req_set_fail(req);
io_req_complete(req, ret);
return 0;
}
static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (sqe->ioprio || sqe->off || sqe->addr || sqe->len ||
- sqe->rw_flags || sqe->buf_index)
+ if (sqe->off || sqe->addr || sqe->len || sqe->buf_index)
return -EINVAL;
if (req->flags & REQ_F_FIXED_FILE)
return -EBADF;
req->close.fd = READ_ONCE(sqe->fd);
req->close.file_slot = READ_ONCE(sqe->file_index);
- if (req->close.file_slot && req->close.fd)
+ req->close.flags = READ_ONCE(sqe->close_flags);
+ if (req->close.flags & ~IORING_CLOSE_FD_AND_FILE_SLOT)
+ return -EINVAL;
+ if (!(req->close.flags & IORING_CLOSE_FD_AND_FILE_SLOT) &&
+ req->close.file_slot && req->close.fd)
return -EINVAL;
return 0;
if (req->close.file_slot) {
ret = io_close_fixed(req, issue_flags);
- goto err;
+ if (ret || !(req->close.flags & IORING_CLOSE_FD_AND_FILE_SLOT))
+ goto err;
}
spin_lock(&files->file_lock);
spin_unlock(&files->file_lock);
goto err;
}
- file = fdt->fd[close->fd];
+ file = rcu_dereference_protected(fdt->fd[close->fd],
+ lockdep_is_held(&files->file_lock));
if (!file || file->f_op == &io_uring_fops) {
spin_unlock(&files->file_lock);
file = NULL;
static int io_sfr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- struct io_ring_ctx *ctx = req->ctx;
-
- if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index ||
- sqe->splice_fd_in))
+ if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in))
return -EINVAL;
req->sync.off = READ_ONCE(sqe->off);
ret = sync_file_range(req->file, req->sync.off, req->sync.len,
req->sync.flags);
- if (ret < 0)
- req_set_fail(req);
io_req_complete(req, ret);
return 0;
}
#if defined(CONFIG_NET)
+static int io_shutdown_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+ if (unlikely(sqe->off || sqe->addr || sqe->rw_flags ||
+ sqe->buf_index || sqe->splice_fd_in))
+ return -EINVAL;
+
+ req->shutdown.how = READ_ONCE(sqe->len);
+ return 0;
+}
+
+static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags)
+{
+ struct socket *sock;
+ int ret;
+
+ if (issue_flags & IO_URING_F_NONBLOCK)
+ return -EAGAIN;
+
+ sock = sock_from_file(req->file);
+ if (unlikely(!sock))
+ return -ENOTSOCK;
+
+ ret = __sys_shutdown_sock(sock, req->shutdown.how);
+ io_req_complete(req, ret);
+ return 0;
+}
+
+static bool io_net_retry(struct socket *sock, int flags)
+{
+ if (!(flags & MSG_WAITALL))
+ return false;
+ return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET;
+}
+
static int io_setup_async_msg(struct io_kiocb *req,
struct io_async_msghdr *kmsg)
{
{
struct io_sr_msg *sr = &req->sr_msg;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ if (unlikely(sqe->file_index))
+ return -EINVAL;
+ if (unlikely(sqe->addr2 || sqe->file_index))
return -EINVAL;
sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
sr->len = READ_ONCE(sqe->len);
+ sr->flags = READ_ONCE(sqe->addr2);
+ if (sr->flags & ~IORING_RECVSEND_POLL_FIRST)
+ return -EINVAL;
sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
if (sr->msg_flags & MSG_DONTWAIT)
req->flags |= REQ_F_NOWAIT;
if (req->ctx->compat)
sr->msg_flags |= MSG_CMSG_COMPAT;
#endif
+ sr->done_io = 0;
return 0;
}
static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_async_msghdr iomsg, *kmsg;
+ struct io_sr_msg *sr = &req->sr_msg;
struct socket *sock;
unsigned flags;
int min_ret = 0;
kmsg = &iomsg;
}
- flags = req->sr_msg.msg_flags;
+ if (!(req->flags & REQ_F_POLLED) &&
+ (sr->flags & IORING_RECVSEND_POLL_FIRST))
+ return io_setup_async_msg(req, kmsg);
+
+ flags = sr->msg_flags;
if (issue_flags & IO_URING_F_NONBLOCK)
flags |= MSG_DONTWAIT;
if (flags & MSG_WAITALL)
return io_setup_async_msg(req, kmsg);
if (ret == -ERESTARTSYS)
ret = -EINTR;
+ if (ret > 0 && io_net_retry(sock, flags)) {
+ sr->done_io += ret;
+ req->flags |= REQ_F_PARTIAL_IO;
+ return io_setup_async_msg(req, kmsg);
+ }
req_set_fail(req);
}
/* fast path, check for non-NULL to avoid function call */
if (kmsg->free_iov)
kfree(kmsg->free_iov);
req->flags &= ~REQ_F_NEED_CLEANUP;
+ if (ret >= 0)
+ ret += sr->done_io;
+ else if (sr->done_io)
+ ret = sr->done_io;
__io_req_complete(req, issue_flags, ret, 0);
return 0;
}
int min_ret = 0;
int ret;
+ if (!(req->flags & REQ_F_POLLED) &&
+ (sr->flags & IORING_RECVSEND_POLL_FIRST))
+ return -EAGAIN;
+
sock = sock_from_file(req->file);
if (unlikely(!sock))
return -ENOTSOCK;
msg.msg_controllen = 0;
msg.msg_namelen = 0;
- flags = req->sr_msg.msg_flags;
+ flags = sr->msg_flags;
if (issue_flags & IO_URING_F_NONBLOCK)
flags |= MSG_DONTWAIT;
if (flags & MSG_WAITALL)
return -EAGAIN;
if (ret == -ERESTARTSYS)
ret = -EINTR;
+ if (ret > 0 && io_net_retry(sock, flags)) {
+ sr->len -= ret;
+ sr->buf += ret;
+ sr->done_io += ret;
+ req->flags |= REQ_F_PARTIAL_IO;
+ return -EAGAIN;
+ }
req_set_fail(req);
}
+ if (ret >= 0)
+ ret += sr->done_io;
+ else if (sr->done_io)
+ ret = sr->done_io;
__io_req_complete(req, issue_flags, ret, 0);
return 0;
}
return __io_recvmsg_copy_hdr(req, iomsg);
}
-static struct io_buffer *io_recv_buffer_select(struct io_kiocb *req,
- unsigned int issue_flags)
-{
- struct io_sr_msg *sr = &req->sr_msg;
-
- return io_buffer_select(req, &sr->len, sr->bgid, issue_flags);
-}
-
static int io_recvmsg_prep_async(struct io_kiocb *req)
{
int ret;
{
struct io_sr_msg *sr = &req->sr_msg;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ if (unlikely(sqe->file_index))
+ return -EINVAL;
+ if (unlikely(sqe->addr2 || sqe->file_index))
return -EINVAL;
sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
sr->len = READ_ONCE(sqe->len);
- sr->bgid = READ_ONCE(sqe->buf_group);
+ sr->flags = READ_ONCE(sqe->addr2);
+ if (sr->flags & ~IORING_RECVSEND_POLL_FIRST)
+ return -EINVAL;
sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
if (sr->msg_flags & MSG_DONTWAIT)
req->flags |= REQ_F_NOWAIT;
return 0;
}
-static bool io_net_retry(struct socket *sock, int flags)
-{
- if (!(flags & MSG_WAITALL))
- return false;
- return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET;
-}
-
static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_async_msghdr iomsg, *kmsg;
struct io_sr_msg *sr = &req->sr_msg;
struct socket *sock;
- struct io_buffer *kbuf;
+ unsigned int cflags;
unsigned flags;
int ret, min_ret = 0;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
kmsg = &iomsg;
}
- if (req->flags & REQ_F_BUFFER_SELECT) {
- kbuf = io_recv_buffer_select(req, issue_flags);
- if (IS_ERR(kbuf))
- return PTR_ERR(kbuf);
- kmsg->fast_iov[0].iov_base = u64_to_user_ptr(kbuf->addr);
- kmsg->fast_iov[0].iov_len = req->sr_msg.len;
- iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov,
- 1, req->sr_msg.len);
+ if (!(req->flags & REQ_F_POLLED) &&
+ (sr->flags & IORING_RECVSEND_POLL_FIRST))
+ return io_setup_async_msg(req, kmsg);
+
+ if (io_do_buffer_select(req)) {
+ void __user *buf;
+
+ buf = io_buffer_select(req, &sr->len, issue_flags);
+ if (!buf)
+ return -ENOBUFS;
+ kmsg->fast_iov[0].iov_base = buf;
+ kmsg->fast_iov[0].iov_len = sr->len;
+ iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1,
+ sr->len);
}
- flags = req->sr_msg.msg_flags;
+ flags = sr->msg_flags;
if (force_nonblock)
flags |= MSG_DONTWAIT;
if (flags & MSG_WAITALL)
min_ret = iov_iter_count(&kmsg->msg.msg_iter);
- ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.umsg,
- kmsg->uaddr, flags);
+ kmsg->msg.msg_get_inq = 1;
+ ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags);
if (ret < min_ret) {
if (ret == -EAGAIN && force_nonblock)
return io_setup_async_msg(req, kmsg);
ret += sr->done_io;
else if (sr->done_io)
ret = sr->done_io;
- __io_req_complete(req, issue_flags, ret, io_put_kbuf(req, issue_flags));
+ cflags = io_put_kbuf(req, issue_flags);
+ if (kmsg->msg.msg_inq)
+ cflags |= IORING_CQE_F_SOCK_NONEMPTY;
+ __io_req_complete(req, issue_flags, ret, cflags);
return 0;
}
static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
{
- struct io_buffer *kbuf;
struct io_sr_msg *sr = &req->sr_msg;
struct msghdr msg;
- void __user *buf = sr->buf;
struct socket *sock;
struct iovec iov;
+ unsigned int cflags;
unsigned flags;
int ret, min_ret = 0;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
+ if (!(req->flags & REQ_F_POLLED) &&
+ (sr->flags & IORING_RECVSEND_POLL_FIRST))
+ return -EAGAIN;
+
sock = sock_from_file(req->file);
if (unlikely(!sock))
return -ENOTSOCK;
- if (req->flags & REQ_F_BUFFER_SELECT) {
- kbuf = io_recv_buffer_select(req, issue_flags);
- if (IS_ERR(kbuf))
- return PTR_ERR(kbuf);
- buf = u64_to_user_ptr(kbuf->addr);
+ if (io_do_buffer_select(req)) {
+ void __user *buf;
+
+ buf = io_buffer_select(req, &sr->len, issue_flags);
+ if (!buf)
+ return -ENOBUFS;
+ sr->buf = buf;
}
- ret = import_single_range(READ, buf, sr->len, &iov, &msg.msg_iter);
+ ret = import_single_range(READ, sr->buf, sr->len, &iov, &msg.msg_iter);
if (unlikely(ret))
goto out_free;
msg.msg_name = NULL;
+ msg.msg_namelen = 0;
msg.msg_control = NULL;
+ msg.msg_get_inq = 1;
+ msg.msg_flags = 0;
msg.msg_controllen = 0;
- msg.msg_namelen = 0;
msg.msg_iocb = NULL;
- msg.msg_flags = 0;
- flags = req->sr_msg.msg_flags;
+ flags = sr->msg_flags;
if (force_nonblock)
flags |= MSG_DONTWAIT;
if (flags & MSG_WAITALL)
return -EAGAIN;
if (ret == -ERESTARTSYS)
ret = -EINTR;
- if (ret > 0 && io_net_retry(sock, flags)) {
- sr->len -= ret;
- sr->buf += ret;
- sr->done_io += ret;
- req->flags |= REQ_F_PARTIAL_IO;
- return -EAGAIN;
- }
- req_set_fail(req);
- } else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) {
-out_free:
+ if (ret > 0 && io_net_retry(sock, flags)) {
+ sr->len -= ret;
+ sr->buf += ret;
+ sr->done_io += ret;
+ req->flags |= REQ_F_PARTIAL_IO;
+ return -EAGAIN;
+ }
+ req_set_fail(req);
+ } else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) {
+out_free:
+ req_set_fail(req);
+ }
+
+ if (ret >= 0)
+ ret += sr->done_io;
+ else if (sr->done_io)
+ ret = sr->done_io;
+ cflags = io_put_kbuf(req, issue_flags);
+ if (msg.msg_inq)
+ cflags |= IORING_CQE_F_SOCK_NONEMPTY;
+ __io_req_complete(req, issue_flags, ret, cflags);
+ return 0;
+}
+
+static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ struct io_accept *accept = &req->accept;
+ unsigned flags;
+
+ if (sqe->len || sqe->buf_index)
+ return -EINVAL;
+
+ 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);
+ accept->nofile = rlimit(RLIMIT_NOFILE);
+ flags = READ_ONCE(sqe->ioprio);
+ if (flags & ~IORING_ACCEPT_MULTISHOT)
+ return -EINVAL;
+
+ accept->file_slot = READ_ONCE(sqe->file_index);
+ if (accept->file_slot) {
+ if (accept->flags & SOCK_CLOEXEC)
+ return -EINVAL;
+ if (flags & IORING_ACCEPT_MULTISHOT &&
+ accept->file_slot != IORING_FILE_INDEX_ALLOC)
+ return -EINVAL;
+ }
+ if (accept->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
+ return -EINVAL;
+ if (SOCK_NONBLOCK != O_NONBLOCK && (accept->flags & SOCK_NONBLOCK))
+ accept->flags = (accept->flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
+ if (flags & IORING_ACCEPT_MULTISHOT)
+ req->flags |= REQ_F_APOLL_MULTISHOT;
+ return 0;
+}
+
+static int io_accept(struct io_kiocb *req, unsigned int issue_flags)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_accept *accept = &req->accept;
+ bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
+ unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0;
+ bool fixed = !!accept->file_slot;
+ struct file *file;
+ int ret, fd;
+
+retry:
+ if (!fixed) {
+ fd = __get_unused_fd_flags(accept->flags, accept->nofile);
+ if (unlikely(fd < 0))
+ return fd;
+ }
+ file = do_accept(req->file, file_flags, accept->addr, accept->addr_len,
+ accept->flags);
+ if (IS_ERR(file)) {
+ if (!fixed)
+ put_unused_fd(fd);
+ ret = PTR_ERR(file);
+ if (ret == -EAGAIN && force_nonblock) {
+ /*
+ * if it's multishot and polled, we don't need to
+ * return EAGAIN to arm the poll infra since it
+ * has already been done
+ */
+ if ((req->flags & IO_APOLL_MULTI_POLLED) ==
+ IO_APOLL_MULTI_POLLED)
+ ret = 0;
+ return ret;
+ }
+ if (ret == -ERESTARTSYS)
+ ret = -EINTR;
req_set_fail(req);
+ } else if (!fixed) {
+ fd_install(fd, file);
+ ret = fd;
+ } else {
+ ret = io_fixed_fd_install(req, issue_flags, file,
+ accept->file_slot);
}
- if (ret >= 0)
- ret += sr->done_io;
- else if (sr->done_io)
- ret = sr->done_io;
- __io_req_complete(req, issue_flags, ret, io_put_kbuf(req, issue_flags));
- return 0;
+ if (!(req->flags & REQ_F_APOLL_MULTISHOT)) {
+ __io_req_complete(req, issue_flags, ret, 0);
+ return 0;
+ }
+ if (ret >= 0) {
+ bool filled;
+
+ spin_lock(&ctx->completion_lock);
+ filled = io_fill_cqe_aux(ctx, req->cqe.user_data, ret,
+ IORING_CQE_F_MORE);
+ io_commit_cqring(ctx);
+ spin_unlock(&ctx->completion_lock);
+ if (filled) {
+ io_cqring_ev_posted(ctx);
+ goto retry;
+ }
+ ret = -ECANCELED;
+ }
+
+ return ret;
}
-static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+static int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- struct io_accept *accept = &req->accept;
+ struct io_socket *sock = &req->sock;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (sqe->ioprio || sqe->len || sqe->buf_index)
+ if (sqe->addr || sqe->rw_flags || sqe->buf_index)
return -EINVAL;
- 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);
- accept->nofile = rlimit(RLIMIT_NOFILE);
+ 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);
- accept->file_slot = READ_ONCE(sqe->file_index);
- if (accept->file_slot && (accept->flags & SOCK_CLOEXEC))
+ sock->flags = sock->type & ~SOCK_TYPE_MASK;
+ if (sock->file_slot && (sock->flags & SOCK_CLOEXEC))
return -EINVAL;
- if (accept->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
+ if (sock->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
return -EINVAL;
- if (SOCK_NONBLOCK != O_NONBLOCK && (accept->flags & SOCK_NONBLOCK))
- accept->flags = (accept->flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
return 0;
}
-static int io_accept(struct io_kiocb *req, unsigned int issue_flags)
+static int io_socket(struct io_kiocb *req, unsigned int issue_flags)
{
- struct io_accept *accept = &req->accept;
- bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
- unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0;
- bool fixed = !!accept->file_slot;
+ struct io_socket *sock = &req->sock;
+ bool fixed = !!sock->file_slot;
struct file *file;
int ret, fd;
if (!fixed) {
- fd = __get_unused_fd_flags(accept->flags, accept->nofile);
+ fd = __get_unused_fd_flags(sock->flags, sock->nofile);
if (unlikely(fd < 0))
return fd;
}
- file = do_accept(req->file, file_flags, accept->addr, accept->addr_len,
- accept->flags);
+ 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 && force_nonblock)
+ if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
return -EAGAIN;
if (ret == -ERESTARTSYS)
ret = -EINTR;
fd_install(fd, file);
ret = fd;
} else {
- ret = io_install_fixed_file(req, file, issue_flags,
- accept->file_slot - 1);
+ ret = io_fixed_fd_install(req, issue_flags, file,
+ sock->file_slot);
}
__io_req_complete(req, issue_flags, ret, 0);
return 0;
{
struct io_connect *conn = &req->connect;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags ||
- sqe->splice_fd_in)
+ if (sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in)
return -EINVAL;
conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr));
IO_NETOP_PREP_ASYNC(recvmsg);
IO_NETOP_PREP_ASYNC(connect);
IO_NETOP_PREP(accept);
+IO_NETOP_PREP(socket);
+IO_NETOP_PREP(shutdown);
IO_NETOP_FN(send);
IO_NETOP_FN(recv);
#endif /* CONFIG_NET */
-#ifdef CONFIG_NET_RX_BUSY_POLL
-
-#define NAPI_TIMEOUT (60 * SEC_CONVERSION)
-
-struct napi_entry {
- struct list_head list;
- unsigned int napi_id;
- unsigned long timeout;
-};
-
-/*
- * Add busy poll NAPI ID from sk.
- */
-static void io_add_napi(struct file *file, struct io_ring_ctx *ctx)
-{
- unsigned int napi_id;
- struct socket *sock;
- struct sock *sk;
- struct napi_entry *ne;
-
- if (!net_busy_loop_on())
- return;
-
- sock = sock_from_file(file);
- if (!sock)
- return;
-
- sk = sock->sk;
- if (!sk)
- return;
-
- napi_id = READ_ONCE(sk->sk_napi_id);
-
- /* Non-NAPI IDs can be rejected */
- if (napi_id < MIN_NAPI_ID)
- return;
-
- spin_lock(&ctx->napi_lock);
- list_for_each_entry(ne, &ctx->napi_list, list) {
- if (ne->napi_id == napi_id) {
- ne->timeout = jiffies + NAPI_TIMEOUT;
- goto out;
- }
- }
-
- ne = kmalloc(sizeof(*ne), GFP_NOWAIT);
- if (!ne)
- goto out;
-
- ne->napi_id = napi_id;
- ne->timeout = jiffies + NAPI_TIMEOUT;
- list_add_tail(&ne->list, &ctx->napi_list);
-out:
- spin_unlock(&ctx->napi_lock);
-}
-
-static inline void io_check_napi_entry_timeout(struct napi_entry *ne)
-{
- if (time_after(jiffies, ne->timeout)) {
- list_del(&ne->list);
- kfree(ne);
- }
-}
-
-/*
- * Busy poll if globally on and supporting sockets found
- */
-static bool io_napi_busy_loop(struct list_head *napi_list)
-{
- struct napi_entry *ne, *n;
-
- list_for_each_entry_safe(ne, n, napi_list, list) {
- napi_busy_loop(ne->napi_id, NULL, NULL, true,
- BUSY_POLL_BUDGET);
- io_check_napi_entry_timeout(ne);
- }
- return !list_empty(napi_list);
-}
-
-static void io_free_napi_list(struct io_ring_ctx *ctx)
-{
- spin_lock(&ctx->napi_lock);
- while (!list_empty(&ctx->napi_list)) {
- struct napi_entry *ne =
- list_first_entry(&ctx->napi_list, struct napi_entry,
- list);
-
- list_del(&ne->list);
- kfree(ne);
- }
- spin_unlock(&ctx->napi_lock);
-}
-#else
-static inline void io_add_napi(struct file *file, struct io_ring_ctx *ctx)
-{
-}
-
-static inline void io_free_napi_list(struct io_ring_ctx *ctx)
-{
-}
-#endif /* CONFIG_NET_RX_BUSY_POLL */
-
struct io_poll_table {
struct poll_table_struct pt;
struct io_kiocb *req;
struct io_ring_ctx *ctx = req->ctx;
struct hlist_head *list;
- list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)];
+ list = &ctx->cancel_hash[hash_long(req->cqe.user_data, ctx->cancel_hash_bits)];
hlist_add_head(&req->hash_node, list);
}
rcu_read_unlock();
}
+static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags);
/*
* All poll tw should go through this. Checks for poll events, manages
* references, does rewait, etc.
*
* Returns a negative error on failure. >0 when no action require, which is
* either spurious wakeup or multishot CQE is served. 0 when it's done with
- * the request, then the mask is stored in req->result.
+ * the request, then the mask is stored in req->cqe.res.
*/
-static int io_poll_check_events(struct io_kiocb *req)
+static int io_poll_check_events(struct io_kiocb *req, bool *locked)
{
struct io_ring_ctx *ctx = req->ctx;
- struct io_poll_iocb *poll = io_poll_get_single(req);
- int v;
+ int v, ret;
/* req->task == current here, checking PF_EXITING is safe */
if (unlikely(req->task->flags & PF_EXITING))
- io_poll_mark_cancelled(req);
+ return -ECANCELED;
do {
v = atomic_read(&req->poll_refs);
if (v & IO_POLL_CANCEL_FLAG)
return -ECANCELED;
- if (!req->result) {
- struct poll_table_struct pt = { ._key = req->cflags };
-
- req->result = vfs_poll(req->file, &pt) & req->cflags;
+ if (!req->cqe.res) {
+ struct poll_table_struct pt = { ._key = req->apoll_events };
+ req->cqe.res = vfs_poll(req->file, &pt) & req->apoll_events;
}
- /* multishot, just fill an CQE and proceed */
- if (req->result && !(req->cflags & EPOLLONESHOT)) {
- __poll_t mask = mangle_poll(req->result & poll->events);
+ if ((unlikely(!req->cqe.res)))
+ continue;
+ if (req->apoll_events & EPOLLONESHOT)
+ return 0;
+
+ /* multishot, just fill a CQE and proceed */
+ if (!(req->flags & REQ_F_APOLL_MULTISHOT)) {
+ __poll_t mask = mangle_poll(req->cqe.res &
+ req->apoll_events);
bool filled;
spin_lock(&ctx->completion_lock);
- filled = io_fill_cqe_aux(ctx, req->user_data, mask,
- IORING_CQE_F_MORE);
+ filled = io_fill_cqe_aux(ctx, req->cqe.user_data,
+ mask, IORING_CQE_F_MORE);
io_commit_cqring(ctx);
spin_unlock(&ctx->completion_lock);
- if (unlikely(!filled))
- return -ECANCELED;
- io_cqring_ev_posted(ctx);
- io_add_napi(req->file, ctx);
- } else if (req->result) {
- return 0;
+ if (filled) {
+ io_cqring_ev_posted(ctx);
+ continue;
+ }
+ return -ECANCELED;
}
+ io_tw_lock(req->ctx, locked);
+ if (unlikely(req->task->flags & PF_EXITING))
+ return -EFAULT;
+ ret = io_issue_sqe(req,
+ IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER);
+ if (ret)
+ return ret;
+
/*
* Release all references, retry if someone tried to restart
* task_work while we were executing it.
struct io_ring_ctx *ctx = req->ctx;
int ret;
- ret = io_poll_check_events(req);
+ ret = io_poll_check_events(req, locked);
if (ret > 0)
return;
if (!ret) {
- req->result = mangle_poll(req->result & req->poll.events);
+ req->cqe.res = mangle_poll(req->cqe.res & req->poll.events);
} else {
- req->result = ret;
+ req->cqe.res = ret;
req_set_fail(req);
}
io_poll_remove_entries(req);
spin_lock(&ctx->completion_lock);
hash_del(&req->hash_node);
- __io_req_complete_post(req, req->result, 0);
+ __io_req_complete_post(req, req->cqe.res, 0);
io_commit_cqring(ctx);
spin_unlock(&ctx->completion_lock);
io_cqring_ev_posted(ctx);
struct io_ring_ctx *ctx = req->ctx;
int ret;
- ret = io_poll_check_events(req);
+ ret = io_poll_check_events(req, locked);
if (ret > 0)
return;
io_req_complete_failed(req, ret);
}
-static void __io_poll_execute(struct io_kiocb *req, int mask, int events)
+static void __io_poll_execute(struct io_kiocb *req, int mask, __poll_t events)
{
- req->result = mask;
+ req->cqe.res = mask;
/*
* This is useful for poll that is armed on behalf of another
* request, and where the wakeup path could be on a different
* CPU. We want to avoid pulling in req->apoll->events for that
* case.
*/
- req->cflags = events;
+ req->apoll_events = events;
if (req->opcode == IORING_OP_POLL_ADD)
req->io_task_work.func = io_poll_task_func;
else
req->io_task_work.func = io_apoll_task_func;
- trace_io_uring_task_add(req->ctx, req, req->user_data, req->opcode, mask);
- io_req_task_work_add(req, false);
+ trace_io_uring_task_add(req->ctx, req, req->cqe.user_data, req->opcode, mask);
+ io_req_task_work_add(req);
}
-static inline void io_poll_execute(struct io_kiocb *req, int res, int events)
+static inline void io_poll_execute(struct io_kiocb *req, int res,
+ __poll_t events)
{
if (io_poll_get_ownership(req))
__io_poll_execute(req, res, events);
#define wqe_to_req(wait) ((void *)((unsigned long) (wait)->private & ~1))
#define wqe_is_double(wait) ((unsigned long) (wait)->private & 1)
+#define IO_ASYNC_POLL_COMMON (EPOLLONESHOT | EPOLLPRI)
static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
void *key)
}
/* for instances that support it check for an event match first */
- if (mask && !(mask & poll->events))
+ if (mask && !(mask & (poll->events & ~IO_ASYNC_POLL_COMMON)))
return 0;
if (io_poll_get_ownership(req)) {
int v;
INIT_HLIST_NODE(&req->hash_node);
+ req->work.cancel_seq = atomic_read(&ctx->cancel_seq);
io_init_poll_iocb(poll, mask, io_poll_wake);
poll->file = req->file;
__io_poll_execute(req, mask, poll->events);
return 0;
}
- io_add_napi(req->file, req->ctx);
/*
* Release ownership. If someone tried to queue a tw while it was
struct io_ring_ctx *ctx = req->ctx;
struct async_poll *apoll;
struct io_poll_table ipt;
- __poll_t mask = EPOLLONESHOT | POLLERR | POLLPRI;
+ __poll_t mask = POLLPRI | POLLERR;
int ret;
if (!def->pollin && !def->pollout)
return IO_APOLL_ABORTED;
- if (!file_can_poll(req->file) || (req->flags & REQ_F_POLLED))
+ if (!file_can_poll(req->file))
+ return IO_APOLL_ABORTED;
+ if ((req->flags & (REQ_F_POLLED|REQ_F_PARTIAL_IO)) == REQ_F_POLLED)
return IO_APOLL_ABORTED;
+ if (!(req->flags & REQ_F_APOLL_MULTISHOT))
+ mask |= EPOLLONESHOT;
if (def->pollin) {
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
/* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */
if ((req->opcode == IORING_OP_RECVMSG) &&
(req->sr_msg.msg_flags & MSG_ERRQUEUE))
- mask &= ~POLLIN;
+ mask &= ~EPOLLIN;
} else {
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
if (def->poll_exclusive)
mask |= EPOLLEXCLUSIVE;
- if (!(issue_flags & IO_URING_F_UNLOCKED) &&
- !list_empty(&ctx->apoll_cache)) {
+ if (req->flags & REQ_F_POLLED) {
+ apoll = req->apoll;
+ } else if (!(issue_flags & IO_URING_F_UNLOCKED) &&
+ !list_empty(&ctx->apoll_cache)) {
apoll = list_first_entry(&ctx->apoll_cache, struct async_poll,
poll.wait.entry);
list_del_init(&apoll->poll.wait.entry);
if (ret || ipt.error)
return ret ? IO_APOLL_READY : IO_APOLL_ABORTED;
- trace_io_uring_poll_arm(ctx, req, req->user_data, req->opcode,
+ trace_io_uring_poll_arm(ctx, req, req->cqe.user_data, req->opcode,
mask, apoll->poll.events);
return IO_APOLL_OK;
}
return found;
}
-static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, __u64 sqe_addr,
- bool poll_only)
+static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, bool poll_only,
+ struct io_cancel_data *cd)
__must_hold(&ctx->completion_lock)
{
struct hlist_head *list;
struct io_kiocb *req;
- list = &ctx->cancel_hash[hash_long(sqe_addr, ctx->cancel_hash_bits)];
+ list = &ctx->cancel_hash[hash_long(cd->data, ctx->cancel_hash_bits)];
hlist_for_each_entry(req, list, hash_node) {
- if (sqe_addr != req->user_data)
+ if (cd->data != req->cqe.user_data)
continue;
if (poll_only && req->opcode != IORING_OP_POLL_ADD)
continue;
+ if (cd->flags & IORING_ASYNC_CANCEL_ALL) {
+ if (cd->seq == req->work.cancel_seq)
+ continue;
+ req->work.cancel_seq = cd->seq;
+ }
return req;
}
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 (!(cd->flags & IORING_ASYNC_CANCEL_ANY) &&
+ 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)
{
return true;
}
-static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr,
- bool poll_only)
+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, sqe_addr, poll_only);
+ struct io_kiocb *req;
+ 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);
if (!req)
return -ENOENT;
io_poll_cancel_req(req);
return demangle_poll(events) | (events & (EPOLLEXCLUSIVE|EPOLLONESHOT));
}
-static int io_poll_update_prep(struct io_kiocb *req,
+static int io_poll_remove_prep(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
struct io_poll_update *upd = &req->poll_update;
u32 flags;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (sqe->ioprio || sqe->buf_index || sqe->splice_fd_in)
+ if (sqe->buf_index || sqe->splice_fd_in)
return -EINVAL;
flags = READ_ONCE(sqe->len);
if (flags & ~(IORING_POLL_UPDATE_EVENTS | IORING_POLL_UPDATE_USER_DATA |
struct io_poll_iocb *poll = &req->poll;
u32 flags;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (sqe->ioprio || sqe->buf_index || sqe->off || sqe->addr)
+ if (sqe->buf_index || sqe->off || sqe->addr)
return -EINVAL;
flags = READ_ONCE(sqe->len);
if (flags & ~IORING_POLL_ADD_MULTI)
return -EINVAL;
io_req_set_refcount(req);
- req->cflags = poll->events = io_poll_parse_events(sqe, flags);
+ req->apoll_events = poll->events = io_poll_parse_events(sqe, flags);
return 0;
}
return 0;
}
-static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags)
+static int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags)
{
+ struct io_cancel_data cd = { .data = req->poll_update.old_user_data, };
struct io_ring_ctx *ctx = req->ctx;
struct io_kiocb *preq;
int ret2, ret = 0;
bool locked;
spin_lock(&ctx->completion_lock);
- preq = io_poll_find(ctx, req->poll_update.old_user_data, true);
+ preq = io_poll_find(ctx, true, &cd);
if (!preq || !io_poll_disarm(preq)) {
spin_unlock(&ctx->completion_lock);
ret = preq ? -EALREADY : -ENOENT;
preq->poll.events |= IO_POLL_UNMASK;
}
if (req->poll_update.update_user_data)
- preq->user_data = req->poll_update.new_user_data;
+ preq->cqe.user_data = req->poll_update.new_user_data;
ret2 = io_poll_add(preq, issue_flags);
/* successfully updated, don't complete poll request */
}
req_set_fail(preq);
- preq->result = -ECANCELED;
+ preq->cqe.res = -ECANCELED;
locked = !(issue_flags & IO_URING_F_UNLOCKED);
io_req_task_complete(preq, &locked);
out:
if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS))
req_set_fail(req);
- req->result = -ETIME;
+ req->cqe.res = -ETIME;
req->io_task_work.func = io_req_task_complete;
- io_req_task_work_add(req, false);
+ io_req_task_work_add(req);
return HRTIMER_NORESTART;
}
static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx,
- __u64 user_data)
+ struct io_cancel_data *cd)
__must_hold(&ctx->timeout_lock)
{
struct io_timeout_data *io;
bool found = false;
list_for_each_entry(req, &ctx->timeout_list, timeout.list) {
- found = user_data == req->user_data;
- if (found)
- break;
+ if (!(cd->flags & IORING_ASYNC_CANCEL_ANY) &&
+ cd->data != req->cqe.user_data)
+ continue;
+ 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;
+ }
+ found = true;
+ break;
}
if (!found)
return ERR_PTR(-ENOENT);
return req;
}
-static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data)
+static int io_timeout_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd)
__must_hold(&ctx->completion_lock)
- __must_hold(&ctx->timeout_lock)
{
- struct io_kiocb *req = io_timeout_extract(ctx, user_data);
+ struct io_kiocb *req;
+
+ spin_lock_irq(&ctx->timeout_lock);
+ req = io_timeout_extract(ctx, cd);
+ spin_unlock_irq(&ctx->timeout_lock);
if (IS_ERR(req))
return PTR_ERR(req);
bool found = false;
list_for_each_entry(req, &ctx->ltimeout_list, timeout.list) {
- found = user_data == req->user_data;
+ found = user_data == req->cqe.user_data;
if (found)
break;
}
struct timespec64 *ts, enum hrtimer_mode mode)
__must_hold(&ctx->timeout_lock)
{
- struct io_kiocb *req = io_timeout_extract(ctx, user_data);
+ struct io_cancel_data cd = { .data = user_data, };
+ struct io_kiocb *req = io_timeout_extract(ctx, &cd);
struct io_timeout_data *data;
if (IS_ERR(req))
{
struct io_timeout_rem *tr = &req->timeout_rem;
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
return -EINVAL;
- if (sqe->ioprio || sqe->buf_index || sqe->len || sqe->splice_fd_in)
+ if (sqe->buf_index || sqe->len || sqe->splice_fd_in)
return -EINVAL;
tr->ltimeout = false;
int ret;
if (!(req->timeout_rem.flags & IORING_TIMEOUT_UPDATE)) {
+ struct io_cancel_data cd = { .data = tr->addr, };
+
spin_lock(&ctx->completion_lock);
- spin_lock_irq(&ctx->timeout_lock);
- ret = io_timeout_cancel(ctx, tr->addr);
- spin_unlock_irq(&ctx->timeout_lock);
+ ret = io_timeout_cancel(ctx, &cd);
spin_unlock(&ctx->completion_lock);
} else {
enum hrtimer_mode mode = io_translate_timeout_mode(tr->flags);
return 0;
}
-static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
- bool is_timeout_link)
+static int __io_timeout_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe,
+ bool is_timeout_link)
{
struct io_timeout_data *data;
unsigned flags;
u32 off = READ_ONCE(sqe->off);
- if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
- if (sqe->ioprio || sqe->buf_index || sqe->len != 1 ||
- sqe->splice_fd_in)
+ if (sqe->buf_index || sqe->len != 1 || sqe->splice_fd_in)
return -EINVAL;
if (off && is_timeout_link)
return -EINVAL;
if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0)
return -EINVAL;
+ INIT_LIST_HEAD(&req->timeout.list);
data->mode = io_translate_timeout_mode(flags);
hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode);
return 0;
}
+static int io_timeout_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+ return __io_timeout_prep(req, sqe, false);
+}
+
+static int io_link_timeout_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+ return __io_timeout_prep(req, sqe, true);
+}
+
static int io_timeout(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
return 0;
}
-struct io_cancel_data {
- struct io_ring_ctx *ctx;
- u64 user_data;
-};
-
static bool io_cancel_cb(struct io_wq_work *work, void *data)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
struct io_cancel_data *cd = data;
- return req->ctx == cd->ctx && req->user_data == cd->user_data;
+ if (req->ctx != cd->ctx)
+ return false;
+ 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|IORING_ASYNC_CANCEL_ANY)) {
+ if (cd->seq == req->work.cancel_seq)
+ return false;
+ req->work.cancel_seq = cd->seq;
+ }
+ return true;
}
-static int io_async_cancel_one(struct io_uring_task *tctx, u64 user_data,
- struct io_ring_ctx *ctx)
+static int io_async_cancel_one(struct io_uring_task *tctx,
+ struct io_cancel_data *cd)
{
- struct io_cancel_data data = { .ctx = ctx, .user_data = user_data, };
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, &data, false);
+ 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;
return ret;
}
-static int io_try_cancel_userdata(struct io_kiocb *req, u64 sqe_addr)
+static int io_try_cancel(struct io_kiocb *req, struct io_cancel_data *cd)
{
struct io_ring_ctx *ctx = req->ctx;
int ret;
WARN_ON_ONCE(!io_wq_current_is_worker() && req->task != current);
- ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx);
+ ret = io_async_cancel_one(req->task->io_uring, cd);
/*
* Fall-through even for -EALREADY, as we may have poll armed
* that need unarming.
return 0;
spin_lock(&ctx->completion_lock);
- ret = io_poll_cancel(ctx, sqe_addr, false);
+ ret = io_poll_cancel(ctx, cd);
if (ret != -ENOENT)
goto out;
-
- spin_lock_irq(&ctx->timeout_lock);
- ret = io_timeout_cancel(ctx, sqe_addr);
- spin_unlock_irq(&ctx->timeout_lock);
+ if (!(cd->flags & IORING_ASYNC_CANCEL_FD))
+ ret = io_timeout_cancel(ctx, cd);
out:
spin_unlock(&ctx->completion_lock);
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)
{
- 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->cancel_flags ||
- sqe->splice_fd_in)
+ if (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 & ~CANCEL_FLAGS)
+ return -EINVAL;
+ 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;
}
-static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
+static int __io_async_cancel(struct io_cancel_data *cd, struct io_kiocb *req,
+ unsigned int issue_flags)
{
- struct io_ring_ctx *ctx = req->ctx;
- u64 sqe_addr = req->cancel.addr;
- bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
+ 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;
+ int ret, nr = 0;
- ret = io_try_cancel_userdata(req, sqe_addr);
- if (ret != -ENOENT)
- goto done;
+ do {
+ ret = io_try_cancel(req, cd);
+ if (ret == -ENOENT)
+ break;
+ if (!all)
+ return ret;
+ nr++;
+ } while (1);
/* slow path, try all io-wq's */
- io_ring_submit_lock(ctx, needs_lock);
+ io_ring_submit_lock(ctx, issue_flags);
ret = -ENOENT;
list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
struct io_uring_task *tctx = node->task->io_uring;
- ret = io_async_cancel_one(tctx, req->cancel.addr, ctx);
- if (ret != -ENOENT)
- break;
+ ret = io_async_cancel_one(tctx, cd);
+ if (ret != -ENOENT) {
+ if (!all)
+ break;
+ nr++;
+ }
}
- io_ring_submit_unlock(ctx, needs_lock);
+ io_ring_submit_unlock(ctx, issue_flags);
+ return all ? nr : ret;
+}
+
+static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
+{
+ struct io_cancel_data cd = {
+ .ctx = req->ctx,
+ .data = req->cancel.addr,
+ .flags = req->cancel.flags,
+ .seq = atomic_inc_return(&req->ctx->cancel_seq),
+ };
+ 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);
return 0;
}
-static int io_rsrc_update_prep(struct io_kiocb *req,
+static int io_files_update_prep(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
return -EINVAL;
- if (sqe->ioprio || sqe->rw_flags || sqe->splice_fd_in)
+ if (sqe->rw_flags || sqe->splice_fd_in)
return -EINVAL;
req->rsrc_update.offset = READ_ONCE(sqe->off);
return 0;
}
+static int io_files_update_with_index_alloc(struct io_kiocb *req,
+ unsigned int issue_flags)
+{
+ __s32 __user *fds = u64_to_user_ptr(req->rsrc_update.arg);
+ unsigned int done;
+ struct file *file;
+ int ret, fd;
+
+ for (done = 0; done < req->rsrc_update.nr_args; done++) {
+ if (copy_from_user(&fd, &fds[done], sizeof(fd))) {
+ ret = -EFAULT;
+ break;
+ }
+
+ file = fget(fd);
+ if (!file) {
+ ret = -EBADF;
+ break;
+ }
+ ret = io_fixed_fd_install(req, issue_flags, file,
+ IORING_FILE_INDEX_ALLOC);
+ if (ret < 0)
+ break;
+ if (copy_to_user(&fds[done], &ret, sizeof(ret))) {
+ ret = -EFAULT;
+ __io_close_fixed(req, issue_flags, ret);
+ break;
+ }
+ }
+
+ if (done)
+ return done;
+ return ret;
+}
+
static int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
- bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
struct io_uring_rsrc_update2 up;
int ret;
up.nr = 0;
up.tags = 0;
up.resv = 0;
+ up.resv2 = 0;
- io_ring_submit_lock(ctx, needs_lock);
- ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE,
- &up, req->rsrc_update.nr_args);
- io_ring_submit_unlock(ctx, needs_lock);
+ if (req->rsrc_update.offset == IORING_FILE_INDEX_ALLOC) {
+ ret = io_files_update_with_index_alloc(req, issue_flags);
+ } else {
+ io_ring_submit_lock(ctx, issue_flags);
+ ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE,
+ &up, req->rsrc_update.nr_args);
+ io_ring_submit_unlock(ctx, issue_flags);
+ }
if (ret < 0)
req_set_fail(req);
{
switch (req->opcode) {
case IORING_OP_NOP:
- return 0;
+ return io_nop_prep(req, sqe);
case IORING_OP_READV:
case IORING_OP_READ_FIXED:
case IORING_OP_READ:
- return io_read_prep(req, sqe);
case IORING_OP_WRITEV:
case IORING_OP_WRITE_FIXED:
case IORING_OP_WRITE:
- return io_write_prep(req, sqe);
+ return io_prep_rw(req, sqe);
case IORING_OP_POLL_ADD:
return io_poll_add_prep(req, sqe);
case IORING_OP_POLL_REMOVE:
- return io_poll_update_prep(req, sqe);
+ return io_poll_remove_prep(req, sqe);
case IORING_OP_FSYNC:
return io_fsync_prep(req, sqe);
case IORING_OP_SYNC_FILE_RANGE:
case IORING_OP_CONNECT:
return io_connect_prep(req, sqe);
case IORING_OP_TIMEOUT:
- return io_timeout_prep(req, sqe, false);
+ return io_timeout_prep(req, sqe);
case IORING_OP_TIMEOUT_REMOVE:
return io_timeout_remove_prep(req, sqe);
case IORING_OP_ASYNC_CANCEL:
return io_async_cancel_prep(req, sqe);
case IORING_OP_LINK_TIMEOUT:
- return io_timeout_prep(req, sqe, true);
+ return io_link_timeout_prep(req, sqe);
case IORING_OP_ACCEPT:
return io_accept_prep(req, sqe);
case IORING_OP_FALLOCATE:
case IORING_OP_CLOSE:
return io_close_prep(req, sqe);
case IORING_OP_FILES_UPDATE:
- return io_rsrc_update_prep(req, sqe);
+ return io_files_update_prep(req, sqe);
case IORING_OP_STATX:
return io_statx_prep(req, sqe);
case IORING_OP_FADVISE:
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);
+ case IORING_OP_FGETXATTR:
+ 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);
+ case IORING_OP_URING_CMD:
+ return io_uring_cmd_prep(req, sqe);
}
printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
static int io_req_prep_async(struct io_kiocb *req)
{
- if (!io_op_defs[req->opcode].needs_async_setup)
+ const struct io_op_def *def = &io_op_defs[req->opcode];
+
+ /* assign early for deferred execution for non-fixed file */
+ if (def->needs_file && !(req->flags & REQ_F_FIXED_FILE))
+ req->file = io_file_get_normal(req, req->cqe.fd);
+ if (!def->needs_async_setup)
return 0;
if (WARN_ON_ONCE(req_has_async_data(req)))
return -EFAULT;
switch (req->opcode) {
case IORING_OP_READV:
- return io_rw_prep_async(req, READ);
+ return io_readv_prep_async(req);
case IORING_OP_WRITEV:
- return io_rw_prep_async(req, WRITE);
+ return io_writev_prep_async(req);
case IORING_OP_SENDMSG:
return io_sendmsg_prep_async(req);
case IORING_OP_RECVMSG:
return io_recvmsg_prep_async(req);
case IORING_OP_CONNECT:
return io_connect_prep_async(req);
+ case IORING_OP_URING_CMD:
+ return io_uring_cmd_prep_async(req);
}
printk_once(KERN_WARNING "io_uring: prep_async() bad opcode %d\n",
req->opcode);
static u32 io_get_sequence(struct io_kiocb *req)
{
u32 seq = req->ctx->cached_sq_head;
+ struct io_kiocb *cur;
/* need original cached_sq_head, but it was increased for each req */
- io_for_each_link(req, req)
+ io_for_each_link(cur, req)
seq--;
return seq;
}
goto queue;
}
- trace_io_uring_defer(ctx, req, req->user_data, req->opcode);
+ trace_io_uring_defer(ctx, req, req->cqe.user_data, req->opcode);
de->req = req;
de->seq = seq;
list_add_tail(&de->list, &ctx->defer_list);
kfree(io->free_iov);
break;
}
- case IORING_OP_SPLICE:
- case IORING_OP_TEE:
- if (!(req->splice.flags & SPLICE_F_FD_IN_FIXED))
- io_put_file(req->splice.file_in);
- break;
case IORING_OP_OPENAT:
case IORING_OP_OPENAT2:
if (req->open.filename)
if (req->statx.filename)
putname(req->statx.filename);
break;
+ case IORING_OP_SETXATTR:
+ case IORING_OP_FSETXATTR:
+ case IORING_OP_GETXATTR:
+ case IORING_OP_FGETXATTR:
+ __io_xattr_finish(req);
+ break;
}
}
if ((req->flags & REQ_F_POLLED) && req->apoll) {
req->flags &= ~IO_REQ_CLEAN_FLAGS;
}
+static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags)
+{
+ if (req->file || !io_op_defs[req->opcode].needs_file)
+ return true;
+
+ if (req->flags & REQ_F_FIXED_FILE)
+ req->file = io_file_get_fixed(req, req->cqe.fd, issue_flags);
+ else
+ req->file = io_file_get_normal(req, req->cqe.fd);
+
+ return !!req->file;
+}
+
static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
{
+ const struct io_op_def *def = &io_op_defs[req->opcode];
const struct cred *creds = NULL;
int ret;
+ if (unlikely(!io_assign_file(req, issue_flags)))
+ return -EBADF;
+
if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred()))
creds = override_creds(req->creds);
- if (!io_op_defs[req->opcode].audit_skip)
+ if (!def->audit_skip)
audit_uring_entry(req->opcode);
switch (req->opcode) {
ret = io_poll_add(req, issue_flags);
break;
case IORING_OP_POLL_REMOVE:
- ret = io_poll_update(req, issue_flags);
+ ret = io_poll_remove(req, issue_flags);
break;
case IORING_OP_SYNC_FILE_RANGE:
ret = io_sync_file_range(req, 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;
+ case IORING_OP_FGETXATTR:
+ ret = io_fgetxattr(req, issue_flags);
+ break;
+ case IORING_OP_GETXATTR:
+ ret = io_getxattr(req, issue_flags);
+ break;
+ case IORING_OP_SOCKET:
+ ret = io_socket(req, issue_flags);
+ break;
+ case IORING_OP_URING_CMD:
+ ret = io_uring_cmd(req, issue_flags);
+ break;
default:
ret = -EINVAL;
break;
}
- if (!io_op_defs[req->opcode].audit_skip)
+ if (!def->audit_skip)
audit_uring_exit(!ret, ret);
if (creds)
static void io_wq_submit_work(struct io_wq_work *work)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+ const struct io_op_def *def = &io_op_defs[req->opcode];
unsigned int issue_flags = IO_URING_F_UNLOCKED;
bool needs_poll = false;
- struct io_kiocb *timeout;
- int ret = 0;
+ int ret = 0, err = -ECANCELED;
/* one will be dropped by ->io_free_work() after returning to io-wq */
if (!(req->flags & REQ_F_REFCOUNT))
else
req_ref_get(req);
- timeout = io_prep_linked_timeout(req);
- if (timeout)
- io_queue_linked_timeout(timeout);
+ io_arm_ltimeout(req);
/* either cancelled or io-wq is dying, so don't touch tctx->iowq */
if (work->flags & IO_WQ_WORK_CANCEL) {
- io_req_task_queue_fail(req, -ECANCELED);
+fail:
+ io_req_task_queue_fail(req, err);
return;
}
+ if (!io_assign_file(req, issue_flags)) {
+ err = -EBADF;
+ work->flags |= IO_WQ_WORK_CANCEL;
+ goto fail;
+ }
if (req->flags & REQ_F_FORCE_ASYNC) {
- const struct io_op_def *def = &io_op_defs[req->opcode];
bool opcode_poll = def->pollin || def->pollout;
if (opcode_poll && file_can_poll(req->file)) {
* wait for request slots on the block side.
*/
if (!needs_poll) {
+ if (!(req->ctx->flags & IORING_SETUP_IOPOLL))
+ break;
cond_resched();
continue;
}
file_slot->file_ptr = file_ptr;
}
-static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx,
- struct io_kiocb *req, int fd)
+static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
+ unsigned int issue_flags)
{
- struct file *file;
+ struct io_ring_ctx *ctx = req->ctx;
+ struct file *file = NULL;
unsigned long file_ptr;
+ io_ring_submit_lock(ctx, issue_flags);
+
if (unlikely((unsigned int)fd >= ctx->nr_user_files))
- return NULL;
+ goto out;
fd = array_index_nospec(fd, ctx->nr_user_files);
file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr;
file = (struct file *) (file_ptr & FFS_MASK);
file_ptr &= ~FFS_MASK;
/* mask in overlapping REQ_F and FFS bits */
req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT);
- io_req_set_rsrc_node(req, ctx);
+ io_req_set_rsrc_node(req, ctx, 0);
+ WARN_ON_ONCE(file && !test_bit(fd, ctx->file_table.bitmap));
+out:
+ io_ring_submit_unlock(ctx, issue_flags);
return file;
}
-static struct file *io_file_get_normal(struct io_ring_ctx *ctx,
- struct io_kiocb *req, int fd)
+static struct file *io_file_get_normal(struct io_kiocb *req, int fd)
{
struct file *file = fget(fd);
- trace_io_uring_file_get(ctx, req, req->user_data, fd);
+ trace_io_uring_file_get(req->ctx, req, req->cqe.user_data, fd);
/* we don't allow fixed io_uring files */
- if (file && unlikely(file->f_op == &io_uring_fops))
+ if (file && file->f_op == &io_uring_fops)
io_req_track_inflight(req);
return file;
}
-static inline struct file *io_file_get(struct io_ring_ctx *ctx,
- struct io_kiocb *req, int fd, bool fixed)
-{
- if (fixed)
- return io_file_get_fixed(ctx, req, fd);
- else
- return io_file_get_normal(ctx, req, fd);
-}
-
static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked)
{
struct io_kiocb *prev = req->timeout.prev;
int ret = -ENOENT;
if (prev) {
- if (!(req->task->flags & PF_EXITING))
- ret = io_try_cancel_userdata(req, prev->user_data);
+ if (!(req->task->flags & PF_EXITING)) {
+ struct io_cancel_data cd = {
+ .ctx = req->ctx,
+ .data = prev->cqe.user_data,
+ };
+
+ ret = io_try_cancel(req, &cd);
+ }
io_req_complete_post(req, ret ?: -ETIME, 0);
io_put_req(prev);
} else {
spin_unlock_irqrestore(&ctx->timeout_lock, flags);
req->io_task_work.func = io_req_task_link_timeout;
- io_req_task_work_add(req, false);
+ io_req_task_work_add(req);
return HRTIMER_NORESTART;
}
io_put_req(req);
}
-static void io_queue_sqe_arm_apoll(struct io_kiocb *req)
+static void io_queue_async(struct io_kiocb *req, int ret)
__must_hold(&req->ctx->uring_lock)
{
- struct io_kiocb *linked_timeout = io_prep_linked_timeout(req);
+ struct io_kiocb *linked_timeout;
+
+ if (ret != -EAGAIN || (req->flags & REQ_F_NOWAIT)) {
+ io_req_complete_failed(req, ret);
+ return;
+ }
+
+ linked_timeout = io_prep_linked_timeout(req);
switch (io_arm_poll_handler(req, 0)) {
case IO_APOLL_READY:
* Queued up for async execution, worker will release
* submit reference when the iocb is actually submitted.
*/
- io_queue_async_work(req, NULL);
+ io_queue_iowq(req, NULL);
break;
case IO_APOLL_OK:
break;
io_queue_linked_timeout(linked_timeout);
}
-static inline void __io_queue_sqe(struct io_kiocb *req)
+static inline void io_queue_sqe(struct io_kiocb *req)
__must_hold(&req->ctx->uring_lock)
{
- struct io_kiocb *linked_timeout;
int ret;
ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER);
* We async punt it if the file wasn't marked NOWAIT, or if the file
* doesn't support non-blocking read/write attempts
*/
- if (likely(!ret)) {
- linked_timeout = io_prep_linked_timeout(req);
- if (linked_timeout)
- io_queue_linked_timeout(linked_timeout);
- } else if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
- io_queue_sqe_arm_apoll(req);
- } else {
- io_req_complete_failed(req, ret);
- }
+ if (likely(!ret))
+ io_arm_ltimeout(req);
+ else
+ io_queue_async(req, ret);
}
static void io_queue_sqe_fallback(struct io_kiocb *req)
__must_hold(&req->ctx->uring_lock)
{
- if (req->flags & REQ_F_FAIL) {
- io_req_complete_fail_submit(req);
+ if (unlikely(req->flags & REQ_F_FAIL)) {
+ /*
+ * We don't submit, fail them all, for that replace hardlinks
+ * with normal links. Extra REQ_F_LINK is tolerated.
+ */
+ req->flags &= ~REQ_F_HARDLINK;
+ req->flags |= REQ_F_LINK;
+ io_req_complete_failed(req, req->cqe.res);
} else if (unlikely(req->ctx->drain_active)) {
io_drain_req(req);
} else {
if (unlikely(ret))
io_req_complete_failed(req, ret);
else
- io_queue_async_work(req, NULL);
+ io_queue_iowq(req, NULL);
}
}
-static inline void io_queue_sqe(struct io_kiocb *req)
- __must_hold(&req->ctx->uring_lock)
-{
- if (likely(!(req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL))))
- __io_queue_sqe(req);
- else
- io_queue_sqe_fallback(req);
-}
-
/*
* Check SQE restrictions (opcode and flags).
*
const struct io_uring_sqe *sqe)
__must_hold(&ctx->uring_lock)
{
+ const struct io_op_def *def;
unsigned int sqe_flags;
int personality;
u8 opcode;
req->opcode = opcode = READ_ONCE(sqe->opcode);
/* same numerical values with corresponding REQ_F_*, safe to copy */
req->flags = sqe_flags = READ_ONCE(sqe->flags);
- req->user_data = READ_ONCE(sqe->user_data);
+ req->cqe.user_data = READ_ONCE(sqe->user_data);
req->file = NULL;
- req->fixed_rsrc_refs = NULL;
+ req->rsrc_node = NULL;
req->task = current;
if (unlikely(opcode >= IORING_OP_LAST)) {
req->opcode = 0;
return -EINVAL;
}
+ def = &io_op_defs[opcode];
if (unlikely(sqe_flags & ~SQE_COMMON_FLAGS)) {
/* enforce forwards compatibility on users */
if (sqe_flags & ~SQE_VALID_FLAGS)
return -EINVAL;
- if ((sqe_flags & IOSQE_BUFFER_SELECT) &&
- !io_op_defs[opcode].buffer_select)
- return -EOPNOTSUPP;
+ if (sqe_flags & IOSQE_BUFFER_SELECT) {
+ if (!def->buffer_select)
+ return -EOPNOTSUPP;
+ req->buf_index = READ_ONCE(sqe->buf_group);
+ }
if (sqe_flags & IOSQE_CQE_SKIP_SUCCESS)
ctx->drain_disabled = true;
if (sqe_flags & IOSQE_IO_DRAIN) {
}
}
- if (io_op_defs[opcode].needs_file) {
+ if (!def->ioprio && sqe->ioprio)
+ return -EINVAL;
+ if (!def->iopoll && (ctx->flags & IORING_SETUP_IOPOLL))
+ return -EINVAL;
+
+ if (def->needs_file) {
struct io_submit_state *state = &ctx->submit_state;
+ req->cqe.fd = READ_ONCE(sqe->fd);
+
/*
* Plug now if we have more than 2 IO left after this, and the
* target is potentially a read/write to block based storage.
*/
- if (state->need_plug && io_op_defs[opcode].plug) {
+ if (state->need_plug && def->plug) {
state->plug_started = true;
state->need_plug = false;
blk_start_plug_nr_ios(&state->plug, state->submit_nr);
}
-
- req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd),
- (sqe_flags & IOSQE_FIXED_FILE));
- if (unlikely(!req->file))
- return -EBADF;
}
personality = READ_ONCE(sqe->personality);
return io_req_prep(req, sqe);
}
-static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
+static __cold int io_submit_fail_init(const struct io_uring_sqe *sqe,
+ struct io_kiocb *req, int ret)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_submit_link *link = &ctx->submit_state.link;
+ struct io_kiocb *head = link->head;
+
+ trace_io_uring_req_failed(sqe, ctx, req, ret);
+
+ /*
+ * Avoid breaking links in the middle as it renders links with SQPOLL
+ * unusable. Instead of failing eagerly, continue assembling the link if
+ * applicable and mark the head with REQ_F_FAIL. The link flushing code
+ * should find the flag and handle the rest.
+ */
+ req_fail_link_node(req, ret);
+ if (head && !(head->flags & REQ_F_FAIL))
+ req_fail_link_node(head, -ECANCELED);
+
+ if (!(req->flags & IO_REQ_LINK_FLAGS)) {
+ if (head) {
+ link->last->link = req;
+ link->head = NULL;
+ req = head;
+ }
+ io_queue_sqe_fallback(req);
+ return ret;
+ }
+
+ if (head)
+ link->last->link = req;
+ else
+ link->head = req;
+ link->last = req;
+ return 0;
+}
+
+static inline int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
const struct io_uring_sqe *sqe)
__must_hold(&ctx->uring_lock)
{
int ret;
ret = io_init_req(ctx, req, sqe);
- if (unlikely(ret)) {
- trace_io_uring_req_failed(sqe, ctx, req, ret);
-
- /* fail even hard links since we don't submit */
- if (link->head) {
- /*
- * we can judge a link req is failed or cancelled by if
- * REQ_F_FAIL is set, but the head is an exception since
- * it may be set REQ_F_FAIL because of other req's failure
- * so let's leverage req->result to distinguish if a head
- * is set REQ_F_FAIL because of its failure or other req's
- * failure so that we can set the correct ret code for it.
- * init result here to avoid affecting the normal path.
- */
- if (!(link->head->flags & REQ_F_FAIL))
- req_fail_link_node(link->head, -ECANCELED);
- } else if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) {
- /*
- * the current req is a normal req, we should return
- * error and thus break the submittion loop.
- */
- io_req_complete_failed(req, ret);
- return ret;
- }
- req_fail_link_node(req, ret);
- }
+ if (unlikely(ret))
+ return io_submit_fail_init(sqe, req, ret);
/* don't need @sqe from now on */
- trace_io_uring_submit_sqe(ctx, req, req->user_data, req->opcode,
+ trace_io_uring_submit_sqe(ctx, req, req->cqe.user_data, req->opcode,
req->flags, true,
ctx->flags & IORING_SETUP_SQPOLL);
* submitted sync once the chain is complete. If none of those
* conditions are true (normal request), then just queue it.
*/
- if (link->head) {
- struct io_kiocb *head = link->head;
-
- if (!(req->flags & REQ_F_FAIL)) {
- ret = io_req_prep_async(req);
- if (unlikely(ret)) {
- req_fail_link_node(req, ret);
- if (!(head->flags & REQ_F_FAIL))
- req_fail_link_node(head, -ECANCELED);
- }
- }
- trace_io_uring_link(ctx, req, head);
+ if (unlikely(link->head)) {
+ ret = io_req_prep_async(req);
+ if (unlikely(ret))
+ return io_submit_fail_init(sqe, req, ret);
+
+ trace_io_uring_link(ctx, req, link->head);
link->last->link = req;
link->last = req;
- if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK))
+ if (req->flags & IO_REQ_LINK_FLAGS)
return 0;
- /* last request of a link, enqueue the link */
+ /* last request of the link, flush it */
+ req = link->head;
link->head = NULL;
- req = head;
- } else if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) {
- link->head = req;
- link->last = req;
+ if (req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL))
+ goto fallback;
+
+ } else if (unlikely(req->flags & (IO_REQ_LINK_FLAGS |
+ REQ_F_FORCE_ASYNC | REQ_F_FAIL))) {
+ if (req->flags & IO_REQ_LINK_FLAGS) {
+ link->head = req;
+ link->last = req;
+ } else {
+fallback:
+ io_queue_sqe_fallback(req);
+ }
return 0;
}
{
struct io_submit_state *state = &ctx->submit_state;
- if (state->link.head)
- io_queue_sqe(state->link.head);
+ if (unlikely(state->link.head))
+ io_queue_sqe_fallback(state->link.head);
/* flush only after queuing links as they can generate completions */
io_submit_flush_completions(ctx);
if (state->plug_started)
* though the application is the one updating it.
*/
head = READ_ONCE(ctx->sq_array[sq_idx]);
- if (likely(head < ctx->sq_entries))
+ if (likely(head < ctx->sq_entries)) {
+ /* double index for 128-byte SQEs, twice as long */
+ if (ctx->flags & IORING_SETUP_SQE128)
+ head <<= 1;
return &ctx->sq_sqes[head];
+ }
/* drop invalid entries */
ctx->cq_extra--;
__must_hold(&ctx->uring_lock)
{
unsigned int entries = io_sqring_entries(ctx);
- int submitted = 0;
+ unsigned int left;
+ int ret;
if (unlikely(!entries))
return 0;
/* make sure SQ entry isn't read before tail */
- nr = min3(nr, ctx->sq_entries, entries);
- io_get_task_refs(nr);
+ ret = left = min3(nr, ctx->sq_entries, entries);
+ io_get_task_refs(left);
+ io_submit_state_start(&ctx->submit_state, left);
- io_submit_state_start(&ctx->submit_state, nr);
do {
const struct io_uring_sqe *sqe;
struct io_kiocb *req;
- if (unlikely(!io_alloc_req_refill(ctx))) {
- if (!submitted)
- submitted = -EAGAIN;
+ if (unlikely(!io_alloc_req_refill(ctx)))
break;
- }
req = io_alloc_req(ctx);
sqe = io_get_sqe(ctx);
if (unlikely(!sqe)) {
- wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list);
+ io_req_add_to_cache(req, ctx);
break;
}
- /* will complete beyond this point, count as submitted */
- submitted++;
- if (io_submit_sqe(ctx, req, sqe)) {
- /*
- * Continue submitting even for sqe failure if the
- * ring was setup with IORING_SETUP_SUBMIT_ALL
- */
- if (!(ctx->flags & IORING_SETUP_SUBMIT_ALL))
- break;
- }
- } while (submitted < nr);
- if (unlikely(submitted != nr)) {
- int ref_used = (submitted == -EAGAIN) ? 0 : submitted;
- int unused = nr - ref_used;
+ /*
+ * Continue submitting even for sqe failure if the
+ * ring was setup with IORING_SETUP_SUBMIT_ALL
+ */
+ if (unlikely(io_submit_sqe(ctx, req, sqe)) &&
+ !(ctx->flags & IORING_SETUP_SUBMIT_ALL)) {
+ left--;
+ break;
+ }
+ } while (--left);
- current->io_uring->cached_refs += unused;
+ if (unlikely(left)) {
+ ret -= left;
+ /* try again if it submitted nothing and can't allocate a req */
+ if (!ret && io_req_cache_empty(ctx))
+ ret = -EAGAIN;
+ current->io_uring->cached_refs += left;
}
io_submit_state_end(ctx);
/* Commit SQ ring head once we've consumed and submitted all SQEs */
io_commit_sqring(ctx);
-
- return submitted;
+ return ret;
}
static inline bool io_sqd_events_pending(struct io_sq_data *sqd)
return READ_ONCE(sqd->state);
}
-static inline void io_ring_set_wakeup_flag(struct io_ring_ctx *ctx)
-{
- /* Tell userspace we may need a wakeup call */
- spin_lock(&ctx->completion_lock);
- WRITE_ONCE(ctx->rings->sq_flags,
- ctx->rings->sq_flags | IORING_SQ_NEED_WAKEUP);
- spin_unlock(&ctx->completion_lock);
-}
-
-static inline void io_ring_clear_wakeup_flag(struct io_ring_ctx *ctx)
-{
- spin_lock(&ctx->completion_lock);
- WRITE_ONCE(ctx->rings->sq_flags,
- ctx->rings->sq_flags & ~IORING_SQ_NEED_WAKEUP);
- spin_unlock(&ctx->completion_lock);
-}
-
static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
{
unsigned int to_submit;
!(ctx->flags & IORING_SETUP_R_DISABLED))
ret = io_submit_sqes(ctx, to_submit);
mutex_unlock(&ctx->uring_lock);
-#ifdef CONFIG_NET_RX_BUSY_POLL
- spin_lock(&ctx->napi_lock);
- if (!list_empty(&ctx->napi_list) &&
- io_napi_busy_loop(&ctx->napi_list))
- ++ret;
- spin_unlock(&ctx->napi_lock);
-#endif
+
if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait))
wake_up(&ctx->sqo_sq_wait);
if (creds)
bool needs_sched = true;
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
- io_ring_set_wakeup_flag(ctx);
-
+ atomic_or(IORING_SQ_NEED_WAKEUP,
+ &ctx->rings->sq_flags);
if ((ctx->flags & IORING_SETUP_IOPOLL) &&
!wq_list_empty(&ctx->iopoll_list)) {
needs_sched = false;
* Ensure the store of the wakeup flag is not
* reordered with the load of the SQ tail
*/
- smp_mb();
+ smp_mb__after_atomic();
if (io_sqring_entries(ctx)) {
needs_sched = false;
mutex_lock(&sqd->lock);
}
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
- io_ring_clear_wakeup_flag(ctx);
+ atomic_andnot(IORING_SQ_NEED_WAKEUP,
+ &ctx->rings->sq_flags);
}
finish_wait(&sqd->wait, &wait);
io_uring_cancel_generic(true, sqd);
sqd->thread = NULL;
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
- io_ring_set_wakeup_flag(ctx);
+ atomic_or(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags);
io_run_task_work();
mutex_unlock(&sqd->lock);
struct io_ring_ctx *ctx;
unsigned cq_tail;
unsigned nr_timeouts;
-#ifdef CONFIG_NET_RX_BUSY_POLL
- unsigned busy_poll_to;
-#endif
};
static inline bool io_should_wake(struct io_wait_queue *iowq)
* Cannot safely flush overflowed CQEs from here, ensure we wake up
* the task, and the next invocation will do it.
*/
- if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->check_cq_overflow))
+ if (io_should_wake(iowq) ||
+ test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &iowq->ctx->check_cq))
return autoremove_wake_function(curr, mode, wake_flags, key);
return -1;
}
ktime_t timeout)
{
int ret;
+ unsigned long check_cq;
/* make sure we run task_work before checking for signals */
ret = io_run_task_work_sig();
if (ret || io_should_wake(iowq))
return ret;
+ check_cq = READ_ONCE(ctx->check_cq);
/* let the caller flush overflows, retry */
- if (test_bit(0, &ctx->check_cq_overflow))
+ if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT))
return 1;
-
+ if (unlikely(check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT)))
+ return -EBADR;
if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS))
return -ETIME;
return 1;
}
-#ifdef CONFIG_NET_RX_BUSY_POLL
-static void io_adjust_busy_loop_timeout(struct timespec64 *ts,
- struct io_wait_queue *iowq)
-{
- unsigned busy_poll_to = READ_ONCE(sysctl_net_busy_poll);
- struct timespec64 pollto = ns_to_timespec64(1000 * (s64)busy_poll_to);
-
- if (timespec64_compare(ts, &pollto) > 0) {
- *ts = timespec64_sub(*ts, pollto);
- iowq->busy_poll_to = busy_poll_to;
- } else {
- u64 to = timespec64_to_ns(ts);
-
- do_div(to, 1000);
- iowq->busy_poll_to = to;
- ts->tv_sec = 0;
- ts->tv_nsec = 0;
- }
-}
-
-static inline bool io_busy_loop_timeout(unsigned long start_time,
- unsigned long bp_usec)
-{
- if (bp_usec) {
- unsigned long end_time = start_time + bp_usec;
- unsigned long now = busy_loop_current_time();
-
- return time_after(now, end_time);
- }
- return true;
-}
-
-static bool io_busy_loop_end(void *p, unsigned long start_time)
-{
- struct io_wait_queue *iowq = p;
-
- return signal_pending(current) ||
- io_should_wake(iowq) ||
- io_busy_loop_timeout(start_time, iowq->busy_poll_to);
-}
-
-static void io_blocking_napi_busy_loop(struct list_head *napi_list,
- struct io_wait_queue *iowq)
-{
- unsigned long start_time =
- list_is_singular(napi_list) ? 0 :
- busy_loop_current_time();
-
- do {
- if (list_is_singular(napi_list)) {
- struct napi_entry *ne =
- list_first_entry(napi_list,
- struct napi_entry, list);
-
- napi_busy_loop(ne->napi_id, io_busy_loop_end, iowq,
- true, BUSY_POLL_BUDGET);
- io_check_napi_entry_timeout(ne);
- break;
- }
- } while (io_napi_busy_loop(napi_list) &&
- !io_busy_loop_end(iowq, start_time));
-}
-
-static void io_putback_napi_list(struct io_ring_ctx *ctx,
- struct list_head *napi_list)
-{
- struct napi_entry *cne, *lne;
-
- spin_lock(&ctx->napi_lock);
- list_for_each_entry(cne, &ctx->napi_list, list)
- list_for_each_entry(lne, napi_list, list)
- if (cne->napi_id == lne->napi_id) {
- list_del(&lne->list);
- kfree(lne);
- break;
- }
- list_splice(napi_list, &ctx->napi_list);
- spin_unlock(&ctx->napi_lock);
-}
-#endif /* CONFIG_NET_RX_BUSY_POLL */
-
/*
* Wait until events become available, if we don't already have some. The
* application must reap them itself, as they reside on the shared cq ring.
struct io_rings *rings = ctx->rings;
ktime_t timeout = KTIME_MAX;
int ret;
-#ifdef CONFIG_NET_RX_BUSY_POLL
- LIST_HEAD(local_napi_list);
-#endif
do {
io_cqring_overflow_flush(ctx);
return ret;
}
-#ifdef CONFIG_NET_RX_BUSY_POLL
- iowq.busy_poll_to = 0;
- if (!(ctx->flags & IORING_SETUP_SQPOLL)) {
- spin_lock(&ctx->napi_lock);
- list_splice_init(&ctx->napi_list, &local_napi_list);
- spin_unlock(&ctx->napi_lock);
- }
-#endif
if (uts) {
struct timespec64 ts;
if (get_timespec64(&ts, uts))
return -EFAULT;
-#ifdef CONFIG_NET_RX_BUSY_POLL
- if (!list_empty(&local_napi_list))
- io_adjust_busy_loop_timeout(&ts, &iowq);
-#endif
timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns());
}
-#ifdef CONFIG_NET_RX_BUSY_POLL
- else if (!list_empty(&local_napi_list))
- iowq.busy_poll_to = READ_ONCE(sysctl_net_busy_poll);
-#endif
init_waitqueue_func_entry(&iowq.wq, io_wake_function);
iowq.wq.private = current;
iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events;
trace_io_uring_cqring_wait(ctx, min_events);
-#ifdef CONFIG_NET_RX_BUSY_POLL
- if (iowq.busy_poll_to)
- io_blocking_napi_busy_loop(&local_napi_list, &iowq);
- if (!list_empty(&local_napi_list))
- io_putback_napi_list(ctx, &local_napi_list);
-#endif
do {
/* if we can't even flush overflow, don't wait for more */
if (!io_cqring_overflow_flush(ctx)) {
prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
TASK_INTERRUPTIBLE);
ret = io_cqring_wait_schedule(ctx, &iowq, timeout);
- finish_wait(&ctx->cq_wait, &iowq.wq);
cond_resched();
} while (ret > 0);
+ finish_wait(&ctx->cq_wait, &iowq.wq);
restore_saved_sigmask_unless(ret == -EINTR);
return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0;
{
table->files = kvcalloc(nr_files, sizeof(table->files[0]),
GFP_KERNEL_ACCOUNT);
- return !!table->files;
+ if (unlikely(!table->files))
+ return false;
+
+ table->bitmap = bitmap_zalloc(nr_files, GFP_KERNEL_ACCOUNT);
+ if (unlikely(!table->bitmap)) {
+ kvfree(table->files);
+ return false;
+ }
+
+ return true;
}
static void io_free_file_tables(struct io_file_table *table)
{
kvfree(table->files);
+ bitmap_free(table->bitmap);
table->files = NULL;
+ table->bitmap = NULL;
+}
+
+static inline void io_file_bitmap_set(struct io_file_table *table, int bit)
+{
+ WARN_ON_ONCE(test_bit(bit, table->bitmap));
+ __set_bit(bit, table->bitmap);
+ table->alloc_hint = bit + 1;
+}
+
+static inline void io_file_bitmap_clear(struct io_file_table *table, int bit)
+{
+ __clear_bit(bit, table->bitmap);
+ table->alloc_hint = bit;
}
static void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
{
+#if !defined(IO_URING_SCM_ALL)
+ int i;
+
+ for (i = 0; i < ctx->nr_user_files; i++) {
+ struct file *file = io_file_from_index(ctx, i);
+
+ if (!file)
+ continue;
+ if (io_fixed_file_slot(&ctx->file_table, i)->file_ptr & FFS_SCM)
+ continue;
+ io_file_bitmap_clear(&ctx->file_table, i);
+ fput(file);
+ }
+#endif
+
#if defined(CONFIG_UNIX)
if (ctx->ring_sock) {
struct sock *sock = ctx->ring_sock->sk;
while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL)
kfree_skb(skb);
}
-#else
- int i;
-
- for (i = 0; i < ctx->nr_user_files; i++) {
- struct file *file;
-
- file = io_file_from_index(ctx, i);
- if (file)
- fput(file);
- }
#endif
io_free_file_tables(&ctx->file_table);
io_rsrc_data_free(ctx->file_data);
return sqd;
}
-#if defined(CONFIG_UNIX)
/*
* Ensure the UNIX gc is aware of our file set, so we are certain that
* the io_uring can be safely unregistered on process exit, even if we have
- * loops in the file referencing.
+ * loops in the file referencing. We account only files that can hold other
+ * files because otherwise they can't form a loop and so are not interesting
+ * for GC.
*/
-static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset)
+static int io_scm_file_account(struct io_ring_ctx *ctx, struct file *file)
{
+#if defined(CONFIG_UNIX)
struct sock *sk = ctx->ring_sock->sk;
+ struct sk_buff_head *head = &sk->sk_receive_queue;
struct scm_fp_list *fpl;
struct sk_buff *skb;
- int i, nr_files;
-
- fpl = kzalloc(sizeof(*fpl), GFP_KERNEL);
- if (!fpl)
- return -ENOMEM;
- skb = alloc_skb(0, GFP_KERNEL);
- if (!skb) {
- kfree(fpl);
- return -ENOMEM;
- }
+ if (likely(!io_file_need_scm(file)))
+ return 0;
- skb->sk = sk;
+ /*
+ * See if we can merge this file into an existing skb SCM_RIGHTS
+ * file set. If there's no room, fall back to allocating a new skb
+ * and filling it in.
+ */
+ spin_lock_irq(&head->lock);
+ skb = skb_peek(head);
+ if (skb && UNIXCB(skb).fp->count < SCM_MAX_FD)
+ __skb_unlink(skb, head);
+ else
+ skb = NULL;
+ spin_unlock_irq(&head->lock);
- nr_files = 0;
- fpl->user = get_uid(current_user());
- for (i = 0; i < nr; i++) {
- struct file *file = io_file_from_index(ctx, i + offset);
+ if (!skb) {
+ fpl = kzalloc(sizeof(*fpl), GFP_KERNEL);
+ if (!fpl)
+ return -ENOMEM;
- if (!file)
- continue;
- fpl->fp[nr_files] = get_file(file);
- unix_inflight(fpl->user, fpl->fp[nr_files]);
- nr_files++;
- }
+ skb = alloc_skb(0, GFP_KERNEL);
+ if (!skb) {
+ kfree(fpl);
+ return -ENOMEM;
+ }
- if (nr_files) {
+ fpl->user = get_uid(current_user());
fpl->max = SCM_MAX_FD;
- fpl->count = nr_files;
+ fpl->count = 0;
+
UNIXCB(skb).fp = fpl;
+ skb->sk = sk;
skb->destructor = unix_destruct_scm;
refcount_add(skb->truesize, &sk->sk_wmem_alloc);
- skb_queue_head(&sk->sk_receive_queue, skb);
-
- for (i = 0; i < nr_files; i++)
- fput(fpl->fp[i]);
- } else {
- kfree_skb(skb);
- free_uid(fpl->user);
- kfree(fpl);
- }
-
- return 0;
-}
-
-/*
- * If UNIX sockets are enabled, fd passing can cause a reference cycle which
- * causes regular reference counting to break down. We rely on the UNIX
- * garbage collection to take care of this problem for us.
- */
-static int io_sqe_files_scm(struct io_ring_ctx *ctx)
-{
- unsigned left, total;
- int ret = 0;
-
- total = 0;
- left = ctx->nr_user_files;
- while (left) {
- unsigned this_files = min_t(unsigned, left, SCM_MAX_FD);
-
- ret = __io_sqe_files_scm(ctx, this_files, total);
- if (ret)
- break;
- left -= this_files;
- total += this_files;
- }
-
- if (!ret)
- return 0;
-
- while (total < ctx->nr_user_files) {
- struct file *file = io_file_from_index(ctx, total);
-
- if (file)
- fput(file);
- total++;
}
- return ret;
-}
-#else
-static int io_sqe_files_scm(struct io_ring_ctx *ctx)
-{
+ fpl = UNIXCB(skb).fp;
+ fpl->fp[fpl->count++] = get_file(file);
+ unix_inflight(fpl->user, file);
+ skb_queue_head(head, skb);
+ fput(file);
+#endif
return 0;
}
-#endif
static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
{
struct sk_buff *skb;
int i;
+ if (!io_file_need_scm(file)) {
+ fput(file);
+ return;
+ }
+
__skb_queue_head_init(&list);
/*
list_del(&prsrc->list);
if (prsrc->tag) {
- bool lock_ring = ctx->flags & IORING_SETUP_IOPOLL;
+ if (ctx->flags & IORING_SETUP_IOPOLL)
+ mutex_lock(&ctx->uring_lock);
- io_ring_submit_lock(ctx, lock_ring);
spin_lock(&ctx->completion_lock);
io_fill_cqe_aux(ctx, prsrc->tag, 0, 0);
io_commit_cqring(ctx);
spin_unlock(&ctx->completion_lock);
io_cqring_ev_posted(ctx);
- io_ring_submit_unlock(ctx, lock_ring);
+
+ if (ctx->flags & IORING_SETUP_IOPOLL)
+ mutex_unlock(&ctx->uring_lock);
}
rsrc_data->do_put(ctx, prsrc);
if (ret)
return ret;
- ret = -ENOMEM;
- if (!io_alloc_file_tables(&ctx->file_table, nr_args))
- goto out_free;
+ if (!io_alloc_file_tables(&ctx->file_table, nr_args)) {
+ io_rsrc_data_free(ctx->file_data);
+ ctx->file_data = NULL;
+ return -ENOMEM;
+ }
for (i = 0; i < nr_args; i++, ctx->nr_user_files++) {
- if (copy_from_user(&fd, &fds[i], sizeof(fd))) {
+ struct io_fixed_file *file_slot;
+
+ if (fds && copy_from_user(&fd, &fds[i], sizeof(fd))) {
ret = -EFAULT;
- goto out_fput;
+ goto fail;
}
/* allow sparse sets */
- if (fd == -1) {
+ if (!fds || fd == -1) {
ret = -EINVAL;
if (unlikely(*io_get_tag_slot(ctx->file_data, i)))
- goto out_fput;
+ goto fail;
continue;
}
file = fget(fd);
ret = -EBADF;
if (unlikely(!file))
- goto out_fput;
+ goto fail;
/*
* Don't allow io_uring instances to be registered. If UNIX
*/
if (file->f_op == &io_uring_fops) {
fput(file);
- goto out_fput;
+ goto fail;
}
- io_fixed_file_set(io_fixed_file_slot(&ctx->file_table, i), file);
- }
-
- ret = io_sqe_files_scm(ctx);
- if (ret) {
- __io_sqe_files_unregister(ctx);
- return ret;
- }
-
- io_rsrc_node_switch(ctx, NULL);
- return ret;
-out_fput:
- for (i = 0; i < ctx->nr_user_files; i++) {
- file = io_file_from_index(ctx, i);
- if (file)
+ ret = io_scm_file_account(ctx, file);
+ if (ret) {
fput(file);
- }
- io_free_file_tables(&ctx->file_table);
- ctx->nr_user_files = 0;
-out_free:
- io_rsrc_data_free(ctx->file_data);
- ctx->file_data = NULL;
- return ret;
-}
-
-static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file,
- int index)
-{
-#if defined(CONFIG_UNIX)
- struct sock *sock = ctx->ring_sock->sk;
- struct sk_buff_head *head = &sock->sk_receive_queue;
- struct sk_buff *skb;
-
- /*
- * See if we can merge this file into an existing skb SCM_RIGHTS
- * file set. If there's no room, fall back to allocating a new skb
- * and filling it in.
- */
- spin_lock_irq(&head->lock);
- skb = skb_peek(head);
- if (skb) {
- struct scm_fp_list *fpl = UNIXCB(skb).fp;
-
- if (fpl->count < SCM_MAX_FD) {
- __skb_unlink(skb, head);
- spin_unlock_irq(&head->lock);
- fpl->fp[fpl->count] = get_file(file);
- unix_inflight(fpl->user, fpl->fp[fpl->count]);
- fpl->count++;
- spin_lock_irq(&head->lock);
- __skb_queue_head(head, skb);
- } else {
- skb = NULL;
+ goto fail;
}
- }
- spin_unlock_irq(&head->lock);
-
- if (skb) {
- fput(file);
- return 0;
+ file_slot = io_fixed_file_slot(&ctx->file_table, i);
+ io_fixed_file_set(file_slot, file);
+ io_file_bitmap_set(&ctx->file_table, i);
}
- return __io_sqe_files_scm(ctx, 1, index);
-#else
+ io_rsrc_node_switch(ctx, NULL);
return 0;
-#endif
+fail:
+ __io_sqe_files_unregister(ctx);
+ return ret;
}
static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx,
struct io_rsrc_node *node, void *rsrc)
{
+ u64 *tag_slot = io_get_tag_slot(data, idx);
struct io_rsrc_put *prsrc;
prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL);
if (!prsrc)
return -ENOMEM;
- prsrc->tag = *io_get_tag_slot(data, idx);
+ prsrc->tag = *tag_slot;
+ *tag_slot = 0;
prsrc->rsrc = rsrc;
list_add(&prsrc->list, &node->rsrc_list);
return 0;
static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
unsigned int issue_flags, u32 slot_index)
+ __must_hold(&req->ctx->uring_lock)
{
struct io_ring_ctx *ctx = req->ctx;
- bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
bool needs_switch = false;
struct io_fixed_file *file_slot;
- int ret = -EBADF;
+ int ret;
- io_ring_submit_lock(ctx, needs_lock);
if (file->f_op == &io_uring_fops)
- goto err;
- ret = -ENXIO;
+ return -EBADF;
if (!ctx->file_data)
- goto err;
- ret = -EINVAL;
+ return -ENXIO;
if (slot_index >= ctx->nr_user_files)
- goto err;
+ return -EINVAL;
slot_index = array_index_nospec(slot_index, ctx->nr_user_files);
file_slot = io_fixed_file_slot(&ctx->file_table, slot_index);
if (ret)
goto err;
file_slot->file_ptr = 0;
+ io_file_bitmap_clear(&ctx->file_table, slot_index);
needs_switch = true;
}
- *io_get_tag_slot(ctx->file_data, slot_index) = 0;
- io_fixed_file_set(file_slot, file);
- ret = io_sqe_file_register(ctx, file, slot_index);
- if (ret) {
- file_slot->file_ptr = 0;
- goto err;
+ ret = io_scm_file_account(ctx, file);
+ if (!ret) {
+ *io_get_tag_slot(ctx->file_data, slot_index) = 0;
+ io_fixed_file_set(file_slot, file);
+ io_file_bitmap_set(&ctx->file_table, slot_index);
}
-
- ret = 0;
err:
if (needs_switch)
io_rsrc_node_switch(ctx, ctx->file_data);
- io_ring_submit_unlock(ctx, needs_lock);
if (ret)
fput(file);
return ret;
}
-static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags)
+static int __io_close_fixed(struct io_kiocb *req, unsigned int issue_flags,
+ unsigned int offset)
{
- unsigned int offset = req->close.file_slot - 1;
struct io_ring_ctx *ctx = req->ctx;
- bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
struct io_fixed_file *file_slot;
struct file *file;
- int ret, i;
+ int ret;
- io_ring_submit_lock(ctx, needs_lock);
+ io_ring_submit_lock(ctx, issue_flags);
ret = -ENXIO;
if (unlikely(!ctx->file_data))
goto out;
if (ret)
goto out;
- i = array_index_nospec(offset, ctx->nr_user_files);
- file_slot = io_fixed_file_slot(&ctx->file_table, i);
+ offset = array_index_nospec(offset, ctx->nr_user_files);
+ file_slot = io_fixed_file_slot(&ctx->file_table, offset);
ret = -EBADF;
if (!file_slot->file_ptr)
goto out;
goto out;
file_slot->file_ptr = 0;
+ io_file_bitmap_clear(&ctx->file_table, offset);
io_rsrc_node_switch(ctx, ctx->file_data);
ret = 0;
out:
- io_ring_submit_unlock(ctx, needs_lock);
+ io_ring_submit_unlock(ctx, issue_flags);
return ret;
}
+static inline int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags)
+{
+ return __io_close_fixed(req, issue_flags, req->close.file_slot - 1);
+}
+
static int __io_sqe_files_update(struct io_ring_ctx *ctx,
struct io_uring_rsrc_update2 *up,
unsigned nr_args)
if (file_slot->file_ptr) {
file = (struct file *)(file_slot->file_ptr & FFS_MASK);
- err = io_queue_rsrc_removal(data, up->offset + done,
- ctx->rsrc_node, file);
+ err = io_queue_rsrc_removal(data, i, ctx->rsrc_node, file);
if (err)
break;
file_slot->file_ptr = 0;
+ io_file_bitmap_clear(&ctx->file_table, i);
needs_switch = true;
}
if (fd != -1) {
err = -EBADF;
break;
}
- *io_get_tag_slot(data, up->offset + done) = tag;
- io_fixed_file_set(file_slot, file);
- err = io_sqe_file_register(ctx, file, i);
+ err = io_scm_file_account(ctx, file);
if (err) {
- file_slot->file_ptr = 0;
fput(file);
break;
}
+ *io_get_tag_slot(data, i) = tag;
+ io_fixed_file_set(file_slot, file);
+ io_file_bitmap_set(&ctx->file_table, i);
}
}
task->io_uring = tctx;
spin_lock_init(&tctx->task_lock);
INIT_WQ_LIST(&tctx->task_list);
- INIT_WQ_LIST(&tctx->prior_task_list);
+ INIT_WQ_LIST(&tctx->prio_task_list);
init_task_work(&tctx->task_work, tctx_task_work);
return 0;
}
return (void *) __get_free_pages(gfp, get_order(size));
}
-static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries,
- size_t *sq_offset)
+static unsigned long rings_size(struct io_ring_ctx *ctx, unsigned int sq_entries,
+ unsigned int cq_entries, size_t *sq_offset)
{
struct io_rings *rings;
size_t off, sq_array_size;
off = struct_size(rings, cqes, cq_entries);
if (off == SIZE_MAX)
return SIZE_MAX;
+ if (ctx->flags & IORING_SETUP_CQE32) {
+ if (check_shl_overflow(off, 1, &off))
+ return SIZE_MAX;
+ }
#ifdef CONFIG_SMP
off = ALIGN(off, SMP_CACHE_BYTES);
return ret;
}
-static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
- struct io_mapped_ubuf **pimu,
- struct page **last_hpage)
+static struct page **io_pin_pages(unsigned long ubuf, unsigned long len,
+ int *npages)
{
- struct io_mapped_ubuf *imu = NULL;
+ unsigned long start, end, nr_pages;
struct vm_area_struct **vmas = NULL;
struct page **pages = NULL;
- unsigned long off, start, end, ubuf;
- size_t size;
- int ret, pret, nr_pages, i;
-
- if (!iov->iov_base) {
- *pimu = ctx->dummy_ubuf;
- return 0;
- }
+ int i, pret, ret = -ENOMEM;
- ubuf = (unsigned long) iov->iov_base;
- end = (ubuf + iov->iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ end = (ubuf + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
start = ubuf >> PAGE_SHIFT;
nr_pages = end - start;
- *pimu = NULL;
- ret = -ENOMEM;
-
pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL);
if (!pages)
goto done;
if (!vmas)
goto done;
- imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL);
- if (!imu)
- goto done;
-
ret = 0;
mmap_read_lock(current->mm);
pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM,
break;
}
}
+ *npages = nr_pages;
} else {
ret = pret < 0 ? pret : -EFAULT;
}
unpin_user_pages(pages, pret);
goto done;
}
+ ret = 0;
+done:
+ kvfree(vmas);
+ if (ret < 0) {
+ kvfree(pages);
+ pages = ERR_PTR(ret);
+ }
+ return pages;
+}
+
+static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
+ struct io_mapped_ubuf **pimu,
+ struct page **last_hpage)
+{
+ struct io_mapped_ubuf *imu = NULL;
+ struct page **pages = NULL;
+ unsigned long off;
+ size_t size;
+ int ret, nr_pages, i;
+
+ if (!iov->iov_base) {
+ *pimu = ctx->dummy_ubuf;
+ return 0;
+ }
+
+ *pimu = NULL;
+ ret = -ENOMEM;
+
+ pages = io_pin_pages((unsigned long) iov->iov_base, iov->iov_len,
+ &nr_pages);
+ if (IS_ERR(pages)) {
+ ret = PTR_ERR(pages);
+ pages = NULL;
+ goto done;
+ }
+
+ imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL);
+ if (!imu)
+ goto done;
- ret = io_buffer_account_pin(ctx, pages, pret, imu, last_hpage);
+ ret = io_buffer_account_pin(ctx, pages, nr_pages, imu, last_hpage);
if (ret) {
- unpin_user_pages(pages, pret);
+ unpin_user_pages(pages, nr_pages);
goto done;
}
- off = ubuf & ~PAGE_MASK;
+ off = (unsigned long) iov->iov_base & ~PAGE_MASK;
size = iov->iov_len;
for (i = 0; i < nr_pages; i++) {
size_t vec_len;
size -= vec_len;
}
/* store original address for later verification */
- imu->ubuf = ubuf;
- imu->ubuf_end = ubuf + iov->iov_len;
+ imu->ubuf = (unsigned long) iov->iov_base;
+ imu->ubuf_end = imu->ubuf + iov->iov_len;
imu->nr_bvecs = nr_pages;
*pimu = imu;
ret = 0;
if (ret)
kvfree(imu);
kvfree(pages);
- kvfree(vmas);
return ret;
}
}
for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) {
- ret = io_copy_iov(ctx, &iov, arg, i);
- if (ret)
- break;
- ret = io_buffer_validate(&iov);
- if (ret)
- break;
+ if (arg) {
+ ret = io_copy_iov(ctx, &iov, arg, i);
+ if (ret)
+ break;
+ ret = io_buffer_validate(&iov);
+ if (ret)
+ break;
+ } else {
+ memset(&iov, 0, sizeof(iov));
+ }
+
if (!iov.iov_base && *io_get_tag_slot(data, i)) {
ret = -EINVAL;
break;
i = array_index_nospec(offset, ctx->nr_user_bufs);
if (ctx->user_bufs[i] != ctx->dummy_ubuf) {
- err = io_queue_rsrc_removal(ctx->buf_data, offset,
+ err = io_queue_rsrc_removal(ctx->buf_data, i,
ctx->rsrc_node, ctx->user_bufs[i]);
if (unlikely(err)) {
io_buffer_unmap(ctx, &imu);
static void io_destroy_buffers(struct io_ring_ctx *ctx)
{
+ struct io_buffer_list *bl;
+ unsigned long index;
int i;
- for (i = 0; i < (1U << IO_BUFFERS_HASH_BITS); i++) {
- struct list_head *list = &ctx->io_buffers[i];
-
- while (!list_empty(list)) {
- struct io_buffer_list *bl;
+ for (i = 0; i < BGID_ARRAY; i++) {
+ if (!ctx->io_bl)
+ break;
+ __io_remove_buffers(ctx, &ctx->io_bl[i], -1U);
+ }
- bl = list_first_entry(list, struct io_buffer_list, list);
- __io_remove_buffers(ctx, bl, -1U);
- list_del(&bl->list);
- kfree(bl);
- }
+ xa_for_each(&ctx->io_bl_xa, index, bl) {
+ xa_erase(&ctx->io_bl_xa, bl->bgid);
+ __io_remove_buffers(ctx, bl, -1U);
+ kfree(bl);
}
while (!list_empty(&ctx->io_buffers_pages)) {
mutex_lock(&ctx->uring_lock);
io_flush_cached_locked_reqs(ctx, state);
- while (state->free_list.next) {
+ while (!io_req_cache_empty(ctx)) {
struct io_wq_work_node *node;
struct io_kiocb *req;
io_req_caches_free(ctx);
if (ctx->hash_map)
io_wq_put_hash(ctx->hash_map);
- io_free_napi_list(ctx);
kfree(ctx->cancel_hash);
kfree(ctx->dummy_ubuf);
- kfree(ctx->io_buffers);
+ kfree(ctx->io_bl);
+ xa_destroy(&ctx->io_bl_xa);
kfree(ctx);
}
* Users may get EPOLLIN meanwhile seeing nothing in cqring, this
* pushs them to do the flush.
*/
- if (io_cqring_events(ctx) || test_bit(0, &ctx->check_cq_overflow))
+ if (io_cqring_events(ctx) ||
+ test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq))
mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
}
spin_unlock_irq(&ctx->timeout_lock);
- if (canceled != 0)
- io_commit_cqring(ctx);
+ io_commit_cqring(ctx);
spin_unlock(&ctx->completion_lock);
if (canceled != 0)
io_cqring_ev_posted(ctx);
io_unregister_personality(ctx, index);
mutex_unlock(&ctx->uring_lock);
- io_kill_timeouts(ctx, NULL, true);
- io_poll_remove_all(ctx, NULL, true);
-
- /* if we failed setting up the ctx, we might not have any rings */
- io_iopoll_try_reap_events(ctx);
+ /* failed during ring init, it couldn't have issued any requests */
+ if (ctx->rings) {
+ io_kill_timeouts(ctx, NULL, true);
+ io_poll_remove_all(ctx, NULL, true);
+ /* if we failed setting up the ctx, we might not have any rings */
+ io_iopoll_try_reap_events(ctx);
+ }
INIT_WORK(&ctx->exit_work, io_ring_exit_work);
/*
struct io_task_cancel cancel = { .task = task, .all = cancel_all, };
struct io_uring_task *tctx = task ? task->io_uring : NULL;
+ /* failed during ring init, it couldn't have issued any requests */
+ if (!ctx->rings)
+ return;
+
while (1) {
enum io_wq_cancel cret;
bool ret = false;
break;
}
+ if (reg.resv) {
+ ret = -EINVAL;
+ break;
+ }
+
if (reg.offset == -1U) {
start = 0;
end = IO_RINGFD_REG_MAX;
ret = -EFAULT;
break;
}
- if (reg.offset >= IO_RINGFD_REG_MAX) {
+ if (reg.resv || reg.data || reg.offset >= IO_RINGFD_REG_MAX) {
ret = -EINVAL;
break;
}
return 0;
}
+static int io_validate_ext_arg(unsigned flags, const void __user *argp, size_t argsz)
+{
+ if (flags & IORING_ENTER_EXT_ARG) {
+ struct io_uring_getevents_arg arg;
+
+ if (argsz != sizeof(arg))
+ return -EINVAL;
+ if (copy_from_user(&arg, argp, sizeof(arg)))
+ return -EFAULT;
+ }
+ return 0;
+}
+
static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz,
struct __kernel_timespec __user **ts,
const sigset_t __user **sig)
return -EINVAL;
if (copy_from_user(&arg, argp, sizeof(arg)))
return -EFAULT;
+ if (arg.pad)
+ return -EINVAL;
*sig = u64_to_user_ptr(arg.sigmask);
*argsz = arg.sigmask_sz;
*ts = u64_to_user_ptr(arg.ts);
size_t, argsz)
{
struct io_ring_ctx *ctx;
- int submitted = 0;
struct fd f;
long ret;
if (ret)
goto out;
}
- submitted = to_submit;
+ ret = to_submit;
} else if (to_submit) {
ret = io_uring_add_tctx_node(ctx);
if (unlikely(ret))
goto out;
- mutex_lock(&ctx->uring_lock);
- submitted = io_submit_sqes(ctx, to_submit);
- mutex_unlock(&ctx->uring_lock);
- if (submitted != to_submit)
+ mutex_lock(&ctx->uring_lock);
+ ret = io_submit_sqes(ctx, to_submit);
+ if (ret != to_submit) {
+ mutex_unlock(&ctx->uring_lock);
goto out;
+ }
+ if ((flags & IORING_ENTER_GETEVENTS) && ctx->syscall_iopoll)
+ goto iopoll_locked;
+ mutex_unlock(&ctx->uring_lock);
}
if (flags & IORING_ENTER_GETEVENTS) {
- const sigset_t __user *sig;
- struct __kernel_timespec __user *ts;
-
- ret = io_get_ext_arg(flags, argp, &argsz, &ts, &sig);
- if (unlikely(ret))
- goto out;
+ int ret2;
+ if (ctx->syscall_iopoll) {
+ /*
+ * We disallow the app entering submit/complete with
+ * polling, but we still need to lock the ring to
+ * prevent racing with polled issue that got punted to
+ * a workqueue.
+ */
+ mutex_lock(&ctx->uring_lock);
+iopoll_locked:
+ ret2 = io_validate_ext_arg(flags, argp, argsz);
+ if (likely(!ret2)) {
+ min_complete = min(min_complete,
+ ctx->cq_entries);
+ ret2 = io_iopoll_check(ctx, min_complete);
+ }
+ mutex_unlock(&ctx->uring_lock);
+ } else {
+ const sigset_t __user *sig;
+ struct __kernel_timespec __user *ts;
+
+ ret2 = io_get_ext_arg(flags, argp, &argsz, &ts, &sig);
+ if (likely(!ret2)) {
+ min_complete = min(min_complete,
+ ctx->cq_entries);
+ ret2 = io_cqring_wait(ctx, min_complete, sig,
+ argsz, ts);
+ }
+ }
- min_complete = min(min_complete, ctx->cq_entries);
+ if (!ret) {
+ ret = ret2;
- /*
- * When SETUP_IOPOLL and SETUP_SQPOLL are both enabled, user
- * space applications don't need to do io completion events
- * polling again, they can rely on io_sq_thread to do polling
- * work, which can reduce cpu usage and uring_lock contention.
- */
- if (ctx->flags & IORING_SETUP_IOPOLL &&
- !(ctx->flags & IORING_SETUP_SQPOLL)) {
- ret = io_iopoll_check(ctx, min_complete);
- } else {
- ret = io_cqring_wait(ctx, min_complete, sig, argsz, ts);
+ /*
+ * EBADR indicates that one or more CQE were dropped.
+ * Once the user has been informed we can clear the bit
+ * as they are obviously ok with those drops.
+ */
+ if (unlikely(ret2 == -EBADR))
+ clear_bit(IO_CHECK_CQ_DROPPED_BIT,
+ &ctx->check_cq);
}
}
percpu_ref_put(&ctx->refs);
out_fput:
fdput(f);
- return submitted ? submitted : ret;
+ return ret;
}
#ifdef CONFIG_PROC_FS
unsigned int sq_tail = READ_ONCE(r->sq.tail);
unsigned int cq_head = READ_ONCE(r->cq.head);
unsigned int cq_tail = READ_ONCE(r->cq.tail);
+ unsigned int cq_shift = 0;
unsigned int sq_entries, cq_entries;
bool has_lock;
+ bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32);
unsigned int i;
+ if (is_cqe32)
+ cq_shift = 1;
+
/*
* we may get imprecise sqe and cqe info if uring is actively running
* since we get cached_sq_head and cached_cq_tail without uring_lock
cq_entries = min(cq_tail - cq_head, ctx->cq_entries);
for (i = 0; i < cq_entries; i++) {
unsigned int entry = i + cq_head;
- struct io_uring_cqe *cqe = &r->cqes[entry & cq_mask];
+ struct io_uring_cqe *cqe = &r->cqes[(entry & cq_mask) << cq_shift];
- seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x\n",
+ if (!is_cqe32) {
+ seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x\n",
entry & cq_mask, cqe->user_data, cqe->res,
cqe->flags);
+ } else {
+ seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x, "
+ "extra1:%llu, extra2:%llu\n",
+ entry & cq_mask, cqe->user_data, cqe->res,
+ cqe->flags, cqe->big_cqe[0], cqe->big_cqe[1]);
+ }
}
/*
ctx->sq_entries = p->sq_entries;
ctx->cq_entries = p->cq_entries;
- size = rings_size(p->sq_entries, p->cq_entries, &sq_array_offset);
+ size = rings_size(ctx, p->sq_entries, p->cq_entries, &sq_array_offset);
if (size == SIZE_MAX)
return -EOVERFLOW;
rings->sq_ring_entries = p->sq_entries;
rings->cq_ring_entries = p->cq_entries;
- size = array_size(sizeof(struct io_uring_sqe), p->sq_entries);
+ if (p->flags & IORING_SETUP_SQE128)
+ size = array_size(2 * sizeof(struct io_uring_sqe), p->sq_entries);
+ else
+ size = array_size(sizeof(struct io_uring_sqe), p->sq_entries);
if (size == SIZE_MAX) {
io_mem_free(ctx->rings);
ctx->rings = NULL;
ctx = io_ring_ctx_alloc(p);
if (!ctx)
return -ENOMEM;
+
+ /*
+ * When SETUP_IOPOLL and SETUP_SQPOLL are both enabled, user
+ * space applications don't need to do io completion events
+ * polling again, they can rely on io_sq_thread to do polling
+ * work, which can reduce cpu usage and uring_lock contention.
+ */
+ if (ctx->flags & IORING_SETUP_IOPOLL &&
+ !(ctx->flags & IORING_SETUP_SQPOLL))
+ ctx->syscall_iopoll = 1;
+
ctx->compat = in_compat_syscall();
if (!capable(CAP_IPC_LOCK))
ctx->user = get_uid(current_user());
+ /*
+ * For SQPOLL, we just need a wakeup, always. For !SQPOLL, if
+ * COOP_TASKRUN is set, then IPIs are never needed by the app.
+ */
+ ret = -EINVAL;
+ if (ctx->flags & IORING_SETUP_SQPOLL) {
+ /* IPI related flags don't make sense with SQPOLL */
+ if (ctx->flags & (IORING_SETUP_COOP_TASKRUN |
+ IORING_SETUP_TASKRUN_FLAG))
+ goto err;
+ ctx->notify_method = TWA_SIGNAL_NO_IPI;
+ } else if (ctx->flags & IORING_SETUP_COOP_TASKRUN) {
+ ctx->notify_method = TWA_SIGNAL_NO_IPI;
+ } else {
+ if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
+ goto err;
+ ctx->notify_method = TWA_SIGNAL;
+ }
+
/*
* This is just grabbed for accounting purposes. When a process exits,
* the mm is exited and dropped before the files, hence we need to hang
IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL |
IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED |
IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS |
- IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP;
+ IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP |
+ IORING_FEAT_LINKED_FILE;
if (copy_to_user(params, p, sizeof(*p))) {
ret = -EFAULT;
if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL |
IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE |
IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ |
- IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL))
+ IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL |
+ IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG |
+ IORING_SETUP_SQE128 | IORING_SETUP_CQE32))
return -EINVAL;
- return io_uring_create(entries, &p, params);
+ return io_uring_create(entries, &p, params);
}
SYSCALL_DEFINE2(io_uring_setup, u32, entries,
__u32 tmp;
int err;
- if (up->resv)
- return -EINVAL;
if (check_add_overflow(up->offset, nr_args, &tmp))
return -EOVERFLOW;
err = io_rsrc_node_switch_start(ctx);
memset(&up, 0, sizeof(up));
if (copy_from_user(&up, arg, sizeof(struct io_uring_rsrc_update)))
return -EFAULT;
+ if (up.resv || up.resv2)
+ return -EINVAL;
return __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, nr_args);
}
return -EINVAL;
if (copy_from_user(&up, arg, sizeof(up)))
return -EFAULT;
- if (!up.nr || up.resv)
+ if (!up.nr || up.resv || up.resv2)
return -EINVAL;
return __io_register_rsrc_update(ctx, type, &up, up.nr);
}
memset(&rr, 0, sizeof(rr));
if (copy_from_user(&rr, arg, size))
return -EFAULT;
- if (!rr.nr || rr.resv || rr.resv2)
+ if (!rr.nr || rr.resv2)
+ return -EINVAL;
+ if (rr.flags & ~IORING_RSRC_REGISTER_SPARSE)
return -EINVAL;
switch (type) {
case IORING_RSRC_FILE:
+ if (rr.flags & IORING_RSRC_REGISTER_SPARSE && rr.data)
+ break;
return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data),
rr.nr, u64_to_user_ptr(rr.tags));
case IORING_RSRC_BUFFER:
+ if (rr.flags & IORING_RSRC_REGISTER_SPARSE && rr.data)
+ break;
return io_sqe_buffers_register(ctx, u64_to_user_ptr(rr.data),
rr.nr, u64_to_user_ptr(rr.tags));
}
if (len > cpumask_size())
len = cpumask_size();
- if (copy_from_user(new_mask, arg, len)) {
+ if (in_compat_syscall()) {
+ ret = compat_get_bitmap(cpumask_bits(new_mask),
+ (const compat_ulong_t __user *)arg,
+ len * 8 /* CHAR_BIT */);
+ } else {
+ ret = copy_from_user(new_mask, arg, len);
+ }
+
+ if (ret) {
free_cpumask_var(new_mask);
return -EFAULT;
}
return ret;
}
+static int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
+{
+ struct io_uring_buf_ring *br;
+ struct io_uring_buf_reg reg;
+ struct io_buffer_list *bl;
+ struct page **pages;
+ int nr_pages;
+
+ if (copy_from_user(®, arg, sizeof(reg)))
+ return -EFAULT;
+
+ if (reg.pad || reg.resv[0] || reg.resv[1] || reg.resv[2])
+ return -EINVAL;
+ if (!reg.ring_addr)
+ return -EFAULT;
+ if (reg.ring_addr & ~PAGE_MASK)
+ return -EINVAL;
+ if (!is_power_of_2(reg.ring_entries))
+ return -EINVAL;
+
+ if (unlikely(reg.bgid < BGID_ARRAY && !ctx->io_bl)) {
+ int ret = io_init_bl_list(ctx);
+ if (ret)
+ return ret;
+ }
+
+ bl = io_buffer_get_list(ctx, reg.bgid);
+ if (bl) {
+ /* if mapped buffer ring OR classic exists, don't allow */
+ if (bl->buf_nr_pages || !list_empty(&bl->buf_list))
+ return -EEXIST;
+ } else {
+ bl = kzalloc(sizeof(*bl), GFP_KERNEL);
+ if (!bl)
+ return -ENOMEM;
+ }
+
+ pages = io_pin_pages(reg.ring_addr,
+ struct_size(br, bufs, reg.ring_entries),
+ &nr_pages);
+ if (IS_ERR(pages)) {
+ kfree(bl);
+ return PTR_ERR(pages);
+ }
+
+ br = page_address(pages[0]);
+ bl->buf_pages = pages;
+ bl->buf_nr_pages = nr_pages;
+ bl->nr_entries = reg.ring_entries;
+ bl->buf_ring = br;
+ bl->mask = reg.ring_entries - 1;
+ io_buffer_add_list(ctx, bl, reg.bgid);
+ return 0;
+}
+
+static int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
+{
+ struct io_uring_buf_reg reg;
+ struct io_buffer_list *bl;
+
+ if (copy_from_user(®, arg, sizeof(reg)))
+ return -EFAULT;
+ if (reg.pad || reg.resv[0] || reg.resv[1] || reg.resv[2])
+ return -EINVAL;
+
+ bl = io_buffer_get_list(ctx, reg.bgid);
+ if (!bl)
+ return -ENOENT;
+ if (!bl->buf_nr_pages)
+ return -EINVAL;
+
+ __io_remove_buffers(ctx, bl, -1U);
+ if (bl->bgid >= BGID_ARRAY) {
+ xa_erase(&ctx->io_bl_xa, bl->bgid);
+ kfree(bl);
+ }
+ return 0;
+}
+
static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
void __user *arg, unsigned nr_args)
__releases(ctx->uring_lock)
switch (opcode) {
case IORING_REGISTER_BUFFERS:
+ ret = -EFAULT;
+ if (!arg)
+ break;
ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL);
break;
case IORING_UNREGISTER_BUFFERS:
ret = io_sqe_buffers_unregister(ctx);
break;
case IORING_REGISTER_FILES:
+ ret = -EFAULT;
+ if (!arg)
+ break;
ret = io_sqe_files_register(ctx, arg, nr_args, NULL);
break;
case IORING_UNREGISTER_FILES:
case IORING_UNREGISTER_RING_FDS:
ret = io_ringfd_unregister(ctx, arg, nr_args);
break;
+ case IORING_REGISTER_PBUF_RING:
+ ret = -EINVAL;
+ if (!arg || nr_args != 1)
+ break;
+ ret = io_register_pbuf_ring(ctx, arg);
+ break;
+ case IORING_UNREGISTER_PBUF_RING:
+ ret = -EINVAL;
+ if (!arg || nr_args != 1)
+ break;
+ ret = io_unregister_pbuf_ring(ctx, arg);
+ break;
default:
ret = -EINVAL;
break;
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));
/* ->buf_index is u16 */
BUILD_BUG_ON(IORING_MAX_REG_BUFFERS >= (1u << 16));
+ BUILD_BUG_ON(BGID_ARRAY * sizeof(struct io_buffer_list) > PAGE_SIZE);
+ BUILD_BUG_ON(offsetof(struct io_uring_buf_ring, bufs) != 0);
+ BUILD_BUG_ON(offsetof(struct io_uring_buf, resv) !=
+ offsetof(struct io_uring_buf_ring, tail));
/* should fit into one byte */
BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8));
BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int));
+ BUILD_BUG_ON(sizeof(atomic_t) != sizeof(u32));
+
+ BUILD_BUG_ON(sizeof(struct io_uring_cmd) > 64);
+
req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC |
SLAB_ACCOUNT);
return 0;
git.samba.org / sfrench / cifs-2.6.git / blobdiff