Merge tag 'io_uring-2019-03-06' of git://git.kernel.dk/linux-block
Merge commit. Changes below are compared with the first parent: 80201fe1.
Changes
32 files changed · +4783 −146
Only the first 600 diff lines are shown. Download the complete patch.
arch/x86/entry/syscalls/syscall_32.tbl
View filediff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 955ab6a..8da7859 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -429,3 +429,6 @@
421 i386 rt_sigtimedwait_time64 sys_rt_sigtimedwait __ia32_compat_sys_rt_sigtimedwait_time64
422 i386 futex_time64 sys_futex __ia32_sys_futex
423 i386 sched_rr_get_interval_time64 sys_sched_rr_get_interval __ia32_sys_sched_rr_get_interval
+425 i386 io_uring_setup sys_io_uring_setup __ia32_sys_io_uring_setup
+426 i386 io_uring_enter sys_io_uring_enter __ia32_sys_io_uring_enter
+427 i386 io_uring_register sys_io_uring_register __ia32_sys_io_uring_register
arch/x86/entry/syscalls/syscall_64.tbl
View filediff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 2ae92fd..c768447 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -345,6 +345,9 @@
334 common rseq __x64_sys_rseq
# don't use numbers 387 through 423, add new calls after the last
# 'common' entry
+425 common io_uring_setup __x64_sys_io_uring_setup
+426 common io_uring_enter __x64_sys_io_uring_enter
+427 common io_uring_register __x64_sys_io_uring_register
#
# x32-specific system call numbers start at 512 to avoid cache impact
block/bio.c
View filediff --git a/block/bio.c b/block/bio.c
index 83a2dfa..71a78d9 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -836,6 +836,40 @@ int bio_add_page(struct bio *bio, struct page *page,
}
EXPORT_SYMBOL(bio_add_page);
+static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter)
+{
+ const struct bio_vec *bv = iter->bvec;
+ unsigned int len;
+ size_t size;
+
+ if (WARN_ON_ONCE(iter->iov_offset > bv->bv_len))
+ return -EINVAL;
+
+ len = min_t(size_t, bv->bv_len - iter->iov_offset, iter->count);
+ size = bio_add_page(bio, bv->bv_page, len,
+ bv->bv_offset + iter->iov_offset);
+ if (size == len) {
+ struct page *page;
+ int i;
+
+ /*
+ * For the normal O_DIRECT case, we could skip grabbing this
+ * reference and then not have to put them again when IO
+ * completes. But this breaks some in-kernel users, like
+ * splicing to/from a loop device, where we release the pipe
+ * pages unconditionally. If we can fix that case, we can
+ * get rid of the get here and the need to call
+ * bio_release_pages() at IO completion time.
+ */
+ mp_bvec_for_each_page(page, bv, i)
+ get_page(page);
+ iov_iter_advance(iter, size);
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
#define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *))
/**
@@ -884,23 +918,35 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
}
/**
- * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * bio_iov_iter_get_pages - add user or kernel pages to a bio
* @bio: bio to add pages to
- * @iter: iov iterator describing the region to be mapped
+ * @iter: iov iterator describing the region to be added
+ *
+ * This takes either an iterator pointing to user memory, or one pointing to
+ * kernel pages (BVEC iterator). If we're adding user pages, we pin them and
+ * map them into the kernel. On IO completion, the caller should put those
+ * pages. For now, when adding kernel pages, we still grab a reference to the
+ * page. This isn't strictly needed for the common case, but some call paths
+ * end up releasing pages from eg a pipe and we can't easily control these.
+ * See comment in __bio_iov_bvec_add_pages().
*
- * Pins pages from *iter and appends them to @bio's bvec array. The
- * pages will have to be released using put_page() when done.
* The function tries, but does not guarantee, to pin as many pages as
- * fit into the bio, or are requested in *iter, whatever is smaller.
- * If MM encounters an error pinning the requested pages, it stops.
- * Error is returned only if 0 pages could be pinned.
+ * fit into the bio, or are requested in *iter, whatever is smaller. If
+ * MM encounters an error pinning the requested pages, it stops. Error
+ * is returned only if 0 pages could be pinned.
*/
int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
{
+ const bool is_bvec = iov_iter_is_bvec(iter);
unsigned short orig_vcnt = bio->bi_vcnt;
do {
- int ret = __bio_iov_iter_get_pages(bio, iter);
+ int ret;
+
+ if (is_bvec)
+ ret = __bio_iov_bvec_add_pages(bio, iter);
+ else
+ ret = __bio_iov_iter_get_pages(bio, iter);
if (unlikely(ret))
return bio->bi_vcnt > orig_vcnt ? 0 : ret;
fs/Makefile
View filediff --git a/fs/Makefile b/fs/Makefile
index 23fcd8c..ffeaa66 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -31,6 +31,7 @@ obj-$(CONFIG_TIMERFD) += timerfd.o
obj-$(CONFIG_EVENTFD) += eventfd.o
obj-$(CONFIG_USERFAULTFD) += userfaultfd.o
obj-$(CONFIG_AIO) += aio.o
+obj-$(CONFIG_IO_URING) += io_uring.o
obj-$(CONFIG_FS_DAX) += dax.o
obj-$(CONFIG_FS_ENCRYPTION) += crypto/
obj-$(CONFIG_FILE_LOCKING) += locks.o
fs/file.c
View filediff --git a/fs/file.c b/fs/file.c
index a10487a..3da91a1 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -706,7 +706,7 @@ void do_close_on_exec(struct files_struct *files)
spin_unlock(&files->file_lock);
}
-static struct file *__fget(unsigned int fd, fmode_t mask)
+static struct file *__fget(unsigned int fd, fmode_t mask, unsigned int refs)
{
struct files_struct *files = current->files;
struct file *file;
@@ -721,7 +721,7 @@ loop:
*/
if (file->f_mode & mask)
file = NULL;
- else if (!get_file_rcu(file))
+ else if (!get_file_rcu_many(file, refs))
goto loop;
}
rcu_read_unlock();
@@ -729,15 +729,20 @@ loop:
return file;
}
+struct file *fget_many(unsigned int fd, unsigned int refs)
+{
+ return __fget(fd, FMODE_PATH, refs);
+}
+
struct file *fget(unsigned int fd)
{
- return __fget(fd, FMODE_PATH);
+ return __fget(fd, FMODE_PATH, 1);
}
EXPORT_SYMBOL(fget);
struct file *fget_raw(unsigned int fd)
{
- return __fget(fd, 0);
+ return __fget(fd, 0, 1);
}
EXPORT_SYMBOL(fget_raw);
@@ -768,7 +773,7 @@ static unsigned long __fget_light(unsigned int fd, fmode_t mask)
return 0;
return (unsigned long)file;
} else {
- file = __fget(fd, mask);
+ file = __fget(fd, mask, 1);
if (!file)
return 0;
return FDPUT_FPUT | (unsigned long)file;
fs/file_table.c
View filediff --git a/fs/file_table.c b/fs/file_table.c
index 5679e7f..155d751 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -326,9 +326,9 @@ void flush_delayed_fput(void)
static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
-void fput(struct file *file)
+void fput_many(struct file *file, unsigned int refs)
{
- if (atomic_long_dec_and_test(&file->f_count)) {
+ if (atomic_long_sub_and_test(refs, &file->f_count)) {
struct task_struct *task = current;
if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
@@ -347,6 +347,11 @@ void fput(struct file *file)
}
}
+void fput(struct file *file)
+{
+ fput_many(file, 1);
+}
+
/*
* synchronous analog of fput(); for kernel threads that might be needed
* in some umount() (and thus can't use flush_delayed_fput() without
fs/io_uring.c
View filediff --git a/fs/io_uring.c b/fs/io_uring.c
new file mode 100644
index 0000000..5d99376
--- /dev/null
+++ b/fs/io_uring.c
@@ -0,0 +1,2971 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shared application/kernel submission and completion ring pairs, for
+ * supporting fast/efficient IO.
+ *
+ * A note on the read/write ordering memory barriers that are matched between
+ * the application and kernel side. When the application reads the CQ ring
+ * tail, it must use an appropriate smp_rmb() to order with the smp_wmb()
+ * the kernel uses after writing the tail. Failure to do so could cause a
+ * delay in when the application notices that completion events available.
+ * This isn't a fatal condition. Likewise, the application must use an
+ * appropriate smp_wmb() both before writing the SQ tail, and after writing
+ * the SQ tail. The first one orders the sqe writes with the tail write, and
+ * the latter is paired with the smp_rmb() the kernel will issue before
+ * reading the SQ tail on submission.
+ *
+ * Also see the examples in the liburing library:
+ *
+ * git://git.kernel.dk/liburing
+ *
+ * io_uring also uses READ/WRITE_ONCE() for _any_ store or load that happens
+ * from data shared between the kernel and application. This is done both
+ * for ordering purposes, but also to ensure that once a value is loaded from
+ * data that the application could potentially modify, it remains stable.
+ *
+ * Copyright (C) 2018-2019 Jens Axboe
+ * Copyright (c) 2018-2019 Christoph Hellwig
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/syscalls.h>
+#include <linux/compat.h>
+#include <linux/refcount.h>
+#include <linux/uio.h>
+
+#include <linux/sched/signal.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/fdtable.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/mmu_context.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <linux/kthread.h>
+#include <linux/blkdev.h>
+#include <linux/bvec.h>
+#include <linux/net.h>
+#include <net/sock.h>
+#include <net/af_unix.h>
+#include <net/scm.h>
+#include <linux/anon_inodes.h>
+#include <linux/sched/mm.h>
+#include <linux/uaccess.h>
+#include <linux/nospec.h>
+#include <linux/sizes.h>
+#include <linux/hugetlb.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "internal.h"
+
+#define IORING_MAX_ENTRIES 4096
+#define IORING_MAX_FIXED_FILES 1024
+
+struct io_uring {
+ u32 head ____cacheline_aligned_in_smp;
+ u32 tail ____cacheline_aligned_in_smp;
+};
+
+struct io_sq_ring {
+ struct io_uring r;
+ u32 ring_mask;
+ u32 ring_entries;
+ u32 dropped;
+ u32 flags;
+ u32 array[];
+};
+
+struct io_cq_ring {
+ struct io_uring r;
+ u32 ring_mask;
+ u32 ring_entries;
+ u32 overflow;
+ struct io_uring_cqe cqes[];
+};
+
+struct io_mapped_ubuf {
+ u64 ubuf;
+ size_t len;
+ struct bio_vec *bvec;
+ unsigned int nr_bvecs;
+};
+
+struct async_list {
+ spinlock_t lock;
+ atomic_t cnt;
+ struct list_head list;
+
+ struct file *file;
+ off_t io_end;
+ size_t io_pages;
+};
+
+struct io_ring_ctx {
+ struct {
+ struct percpu_ref refs;
+ } ____cacheline_aligned_in_smp;
+
+ struct {
+ unsigned int flags;
+ bool compat;
+ bool account_mem;
+
+ /* SQ ring */
+ struct io_sq_ring *sq_ring;
+ unsigned cached_sq_head;
+ unsigned sq_entries;
+ unsigned sq_mask;
+ unsigned sq_thread_idle;
+ struct io_uring_sqe *sq_sqes;
+ } ____cacheline_aligned_in_smp;
+
+ /* IO offload */
+ struct workqueue_struct *sqo_wq;
+ struct task_struct *sqo_thread; /* if using sq thread polling */
+ struct mm_struct *sqo_mm;
+ wait_queue_head_t sqo_wait;
+ unsigned sqo_stop;
+
+ struct {
+ /* CQ ring */
+ struct io_cq_ring *cq_ring;
+ unsigned cached_cq_tail;
+ unsigned cq_entries;
+ unsigned cq_mask;
+ struct wait_queue_head cq_wait;
+ struct fasync_struct *cq_fasync;
+ } ____cacheline_aligned_in_smp;
+
+ /*
+ * If used, fixed file set. Writers must ensure that ->refs is dead,
+ * readers must ensure that ->refs is alive as long as the file* is
+ * used. Only updated through io_uring_register(2).
+ */
+ struct file **user_files;
+ unsigned nr_user_files;
+
+ /* if used, fixed mapped user buffers */
+ unsigned nr_user_bufs;
+ struct io_mapped_ubuf *user_bufs;
+
+ struct user_struct *user;
+
+ struct completion ctx_done;
+
+ struct {
+ struct mutex uring_lock;
+ wait_queue_head_t wait;
+ } ____cacheline_aligned_in_smp;
+
+ struct {
+ spinlock_t completion_lock;
+ bool poll_multi_file;
+ /*
+ * ->poll_list is protected by the ctx->uring_lock for
+ * io_uring instances that don't use IORING_SETUP_SQPOLL.
+ * For SQPOLL, only the single threaded io_sq_thread() will
+ * manipulate the list, hence no extra locking is needed there.
+ */
+ struct list_head poll_list;
+ struct list_head cancel_list;
+ } ____cacheline_aligned_in_smp;
+
+ struct async_list pending_async[2];
+
+#if defined(CONFIG_UNIX)
+ struct socket *ring_sock;
+#endif
+};
+
+struct sqe_submit {
+ const struct io_uring_sqe *sqe;
+ unsigned short index;
+ bool has_user;
+ bool needs_lock;
+ bool needs_fixed_file;
+};
+
+struct io_poll_iocb {
+ struct file *file;
+ struct wait_queue_head *head;
+ __poll_t events;
+ bool woken;
+ bool canceled;
+ struct wait_queue_entry wait;
+};
+
+struct io_kiocb {
+ union {
+ struct kiocb rw;
+ struct io_poll_iocb poll;
+ };
+
+ struct sqe_submit submit;
+
+ struct io_ring_ctx *ctx;
+ struct list_head list;
+ unsigned int flags;
+ refcount_t refs;
+#define REQ_F_FORCE_NONBLOCK 1 /* inline submission attempt */
+#define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */
+#define REQ_F_FIXED_FILE 4 /* ctx owns file */
+#define REQ_F_SEQ_PREV 8 /* sequential with previous */
+ u64 user_data;
+ u64 error;
+
+ struct work_struct work;
+};
+
+#define IO_PLUG_THRESHOLD 2
+#define IO_IOPOLL_BATCH 8
+
+struct io_submit_state {
+ struct blk_plug plug;
+
+ /*
+ * io_kiocb alloc cache
+ */
+ void *reqs[IO_IOPOLL_BATCH];
+ unsigned int free_reqs;
+ unsigned int cur_req;
+
+ /*
+ * File reference cache
+ */
+ struct file *file;
+ unsigned int fd;
+ unsigned int has_refs;
+ unsigned int used_refs;
+ unsigned int ios_left;
+};
+
+static struct kmem_cache *req_cachep;
+
+static const struct file_operations io_uring_fops;
+
+struct sock *io_uring_get_socket(struct file *file)
+{
+#if defined(CONFIG_UNIX)
+ if (file->f_op == &io_uring_fops) {
+ struct io_ring_ctx *ctx = file->private_data;
+
+ return ctx->ring_sock->sk;
+ }
+#endif
+ return NULL;
+}
+EXPORT_SYMBOL(io_uring_get_socket);
+
+static void io_ring_ctx_ref_free(struct percpu_ref *ref)
+{
+ struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs);
+
+ complete(&ctx->ctx_done);
+}
+
+static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
+{
+ struct io_ring_ctx *ctx;
+ int i;
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return NULL;
+
+ if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free, 0, GFP_KERNEL)) {
+ kfree(ctx);
+ return NULL;
+ }
+
+ ctx->flags = p->flags;
+ init_waitqueue_head(&ctx->cq_wait);
+ init_completion(&ctx->ctx_done);
+ mutex_init(&ctx->uring_lock);
+ init_waitqueue_head(&ctx->wait);
+ for (i = 0; i < ARRAY_SIZE(ctx->pending_async); i++) {
+ spin_lock_init(&ctx->pending_async[i].lock);
+ INIT_LIST_HEAD(&ctx->pending_async[i].list);
+ atomic_set(&ctx->pending_async[i].cnt, 0);
+ }
+ spin_lock_init(&ctx->completion_lock);
+ INIT_LIST_HEAD(&ctx->poll_list);
+ INIT_LIST_HEAD(&ctx->cancel_list);
+ return ctx;
+}
+
+static void io_commit_cqring(struct io_ring_ctx *ctx)
+{
+ struct io_cq_ring *ring = ctx->cq_ring;
+
+ if (ctx->cached_cq_tail != READ_ONCE(ring->r.tail)) {
+ /* order cqe stores with ring update */
+ smp_store_release(&ring->r.tail, ctx->cached_cq_tail);
+
+ /*
+ * Write sider barrier of tail update, app has read side. See
+ * comment at the top of this file.
+ */
+ smp_wmb();
+
+ if (wq_has_sleeper(&ctx->cq_wait)) {
+ wake_up_interruptible(&ctx->cq_wait);
+ kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
+ }
+ }
+}
+
+static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
+{
+ struct io_cq_ring *ring = ctx->cq_ring;
+ unsigned tail;
+
+ tail = ctx->cached_cq_tail;
+ /* See comment at the top of the file */
+ smp_rmb();
+ if (tail + 1 == READ_ONCE(ring->r.head))
+ return NULL;
+
+ ctx->cached_cq_tail++;
+ return &ring->cqes[tail & ctx->cq_mask];
+}
+
+static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data,
+ long res, unsigned ev_flags)
+{
+ struct io_uring_cqe *cqe;
+
+ /*
+ * 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_cqring(ctx);
+ if (cqe) {
+ WRITE_ONCE(cqe->user_data, ki_user_data);
+ WRITE_ONCE(cqe->res, res);
+ WRITE_ONCE(cqe->flags, ev_flags);
+ } else {
+ unsigned overflow = READ_ONCE(ctx->cq_ring->overflow);
+
+ WRITE_ONCE(ctx->cq_ring->overflow, overflow + 1);
+ }
+}
+
+static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 ki_user_data,
+ long res, unsigned ev_flags)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+ io_cqring_fill_event(ctx, ki_user_data, res, ev_flags);
+ io_commit_cqring(ctx);
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+
+ if (waitqueue_active(&ctx->wait))
+ wake_up(&ctx->wait);
+ if (waitqueue_active(&ctx->sqo_wait))
+ wake_up(&ctx->sqo_wait);
+}
+
+static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs)
+{
+ percpu_ref_put_many(&ctx->refs, refs);
+
+ if (waitqueue_active(&ctx->wait))
+ wake_up(&ctx->wait);
+}
+
+static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
+ struct io_submit_state *state)
+{
+ struct io_kiocb *req;
+
This diff is incomplete. Download the complete patch.
include/linux/file.h
View fileThis diff is incomplete. Download the complete patch.
include/linux/fs.h
View fileThis diff is incomplete. Download the complete patch.
include/linux/sched/user.h
View fileThis diff is incomplete. Download the complete patch.
include/linux/syscalls.h
View fileThis diff is incomplete. Download the complete patch.
include/net/af_unix.h
View fileThis diff is incomplete. Download the complete patch.
include/uapi/asm-generic/unistd.h
View fileThis diff is incomplete. Download the complete patch.
include/uapi/linux/io_uring.h
View fileThis diff is incomplete. Download the complete patch.
init/Kconfig
View fileThis diff is incomplete. Download the complete patch.
kernel/sys_ni.c
View fileThis diff is incomplete. Download the complete patch.
net/Makefile
View fileThis diff is incomplete. Download the complete patch.
net/unix/Kconfig
View fileThis diff is incomplete. Download the complete patch.
net/unix/Makefile
View fileThis diff is incomplete. Download the complete patch.
net/unix/af_unix.c
View fileThis diff is incomplete. Download the complete patch.
net/unix/garbage.c
View fileThis diff is incomplete. Download the complete patch.
net/unix/scm.c
View fileThis diff is incomplete. Download the complete patch.
net/unix/scm.h
View fileThis diff is incomplete. Download the complete patch.
tools/io_uring/Makefile
View fileThis diff is incomplete. Download the complete patch.
tools/io_uring/README
View fileThis diff is incomplete. Download the complete patch.
tools/io_uring/barrier.h
View fileThis diff is incomplete. Download the complete patch.
tools/io_uring/io_uring-bench.c
View fileThis diff is incomplete. Download the complete patch.
tools/io_uring/io_uring-cp.c
View fileThis diff is incomplete. Download the complete patch.
tools/io_uring/liburing.h
View fileThis diff is incomplete. Download the complete patch.
tools/io_uring/queue.c
View fileThis diff is incomplete. Download the complete patch.
tools/io_uring/setup.c
View fileThis diff is incomplete. Download the complete patch.
tools/io_uring/syscall.c
View fileThis diff is incomplete. Download the complete patch.