* [PATCH 09/18] io_uring: use fget/fput_many() for file references
From: Jens Axboe @ 2019-01-30 21:55 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api; +Cc: hch, jmoyer, avi, jannh, Jens Axboe
In-Reply-To: <20190130215540.20871-1-axboe@kernel.dk>
Add a separate io_submit_state structure, to cache some of the things
we need for IO submission.
One such example is file reference batching. io_submit_state. We get as
many references as the number of sqes we are submitting, and drop
unused ones if we end up switching files. The assumption here is that
we're usually only dealing with one fd, and if there are multiple,
hopefuly they are at least somewhat ordered. Could trivially be extended
to cover multiple fds, if needed.
On the completion side we do the same thing, except this is trivially
done just locally in io_iopoll_reap().
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/io_uring.c | 142 ++++++++++++++++++++++++++++++++++++++++++--------
1 file changed, 121 insertions(+), 21 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 90a745c34e8b..488c57a968af 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -138,6 +138,19 @@ struct io_kiocb {
#define IO_PLUG_THRESHOLD 2
#define IO_IOPOLL_BATCH 8
+struct io_submit_state {
+ struct blk_plug plug;
+
+ /*
+ * 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;
@@ -285,9 +298,11 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
struct list_head *done)
{
void *reqs[IO_IOPOLL_BATCH];
+ int file_count, to_free;
+ struct file *file = NULL;
struct io_kiocb *req;
- int to_free = 0;
+ file_count = to_free = 0;
while (!list_empty(done)) {
req = list_first_entry(done, struct io_kiocb, list);
list_del(&req->list);
@@ -297,12 +312,28 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
reqs[to_free++] = req;
(*nr_events)++;
- fput(req->rw.ki_filp);
+ /*
+ * Batched puts of the same file, to avoid dirtying the
+ * file usage count multiple times, if avoidable.
+ */
+ if (!file) {
+ file = req->rw.ki_filp;
+ file_count = 1;
+ } else if (file == req->rw.ki_filp) {
+ file_count++;
+ } else {
+ fput_many(file, file_count);
+ file = req->rw.ki_filp;
+ file_count = 1;
+ }
+
if (to_free == ARRAY_SIZE(reqs))
io_free_req_many(ctx, reqs, &to_free);
}
io_commit_cqring(ctx);
+ if (file)
+ fput_many(file, file_count);
io_free_req_many(ctx, reqs, &to_free);
}
@@ -483,8 +514,50 @@ static void io_iopoll_req_issued(struct io_kiocb *req)
list_add_tail(&req->list, &ctx->poll_list);
}
+static void io_file_put(struct io_submit_state *state, struct file *file)
+{
+ if (!state) {
+ fput(file);
+ } else if (state->file) {
+ int diff = state->has_refs - state->used_refs;
+
+ if (diff)
+ fput_many(state->file, diff);
+ state->file = NULL;
+ }
+}
+
+/*
+ * Get as many references to a file as we have IOs left in this submission,
+ * assuming most submissions are for one file, or at least that each file
+ * has more than one submission.
+ */
+static struct file *io_file_get(struct io_submit_state *state, int fd)
+{
+ if (!state)
+ return fget(fd);
+
+ if (state->file) {
+ if (state->fd == fd) {
+ state->used_refs++;
+ state->ios_left--;
+ return state->file;
+ }
+ io_file_put(state, NULL);
+ }
+ state->file = fget_many(fd, state->ios_left);
+ if (!state->file)
+ return NULL;
+
+ state->fd = fd;
+ state->has_refs = state->ios_left;
+ state->used_refs = 1;
+ state->ios_left--;
+ return state->file;
+}
+
static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
- bool force_nonblock)
+ bool force_nonblock, struct io_submit_state *state)
{
struct io_ring_ctx *ctx = req->ctx;
struct kiocb *kiocb = &req->rw;
@@ -492,7 +565,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
int fd, ret;
fd = READ_ONCE(sqe->fd);
- kiocb->ki_filp = fget(fd);
+ kiocb->ki_filp = io_file_get(state, fd);
if (unlikely(!kiocb->ki_filp))
return -EBADF;
kiocb->ki_pos = READ_ONCE(sqe->off);
@@ -534,7 +607,10 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
}
return 0;
out_fput:
- fput(kiocb->ki_filp);
+ /* in case of error, we didn't use this file reference. drop it. */
+ if (state)
+ state->used_refs--;
+ io_file_put(state, kiocb->ki_filp);
return ret;
}
@@ -580,7 +656,7 @@ static int io_import_iovec(struct io_ring_ctx *ctx, int rw,
}
static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s,
- bool force_nonblock)
+ bool force_nonblock, struct io_submit_state *state)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct kiocb *kiocb = &req->rw;
@@ -588,7 +664,7 @@ static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s,
struct file *file;
ssize_t ret;
- ret = io_prep_rw(req, s->sqe, force_nonblock);
+ ret = io_prep_rw(req, s->sqe, force_nonblock, state);
if (ret)
return ret;
file = kiocb->ki_filp;
@@ -623,7 +699,7 @@ static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s,
}
static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s,
- bool force_nonblock)
+ bool force_nonblock, struct io_submit_state *state)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct kiocb *kiocb = &req->rw;
@@ -631,7 +707,7 @@ static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s,
struct file *file;
ssize_t ret;
- ret = io_prep_rw(req, s->sqe, force_nonblock);
+ ret = io_prep_rw(req, s->sqe, force_nonblock, state);
if (ret)
return ret;
file = kiocb->ki_filp;
@@ -731,7 +807,8 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
}
static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
- const struct sqe_submit *s, bool force_nonblock)
+ const struct sqe_submit *s, bool force_nonblock,
+ struct io_submit_state *state)
{
ssize_t ret;
int opcode;
@@ -746,10 +823,10 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
ret = io_nop(req, req->user_data);
break;
case IORING_OP_READV:
- ret = io_read(req, s, force_nonblock);
+ ret = io_read(req, s, force_nonblock, state);
break;
case IORING_OP_WRITEV:
- ret = io_write(req, s, force_nonblock);
+ ret = io_write(req, s, force_nonblock, state);
break;
case IORING_OP_FSYNC:
ret = io_fsync(req, s->sqe, force_nonblock);
@@ -798,7 +875,7 @@ static void io_sq_wq_submit_work(struct work_struct *work)
set_fs(USER_DS);
do {
- ret = __io_submit_sqe(ctx, req, s, false);
+ ret = __io_submit_sqe(ctx, req, s, false, NULL);
/*
* We can get EAGAIN for polled IO even though we're forcing
* a sync submission from here, since we can't wait for
@@ -823,7 +900,8 @@ static void io_sq_wq_submit_work(struct work_struct *work)
task_unlock(current);
}
-static int io_submit_sqe(struct io_ring_ctx *ctx, const struct sqe_submit *s)
+static int io_submit_sqe(struct io_ring_ctx *ctx, const struct sqe_submit *s,
+ struct io_submit_state *state)
{
struct io_kiocb *req;
ssize_t ret;
@@ -836,7 +914,7 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, const struct sqe_submit *s)
if (unlikely(!req))
return -EAGAIN;
- ret = __io_submit_sqe(ctx, req, s, true);
+ ret = __io_submit_sqe(ctx, req, s, true, state);
if (ret == -EAGAIN) {
memcpy(&req->submit, s, sizeof(*s));
INIT_WORK(&req->work, io_sq_wq_submit_work);
@@ -849,6 +927,26 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, const struct sqe_submit *s)
return ret;
}
+/*
+ * Batched submission is done, ensure local IO is flushed out.
+ */
+static void io_submit_state_end(struct io_submit_state *state)
+{
+ blk_finish_plug(&state->plug);
+ io_file_put(state, NULL);
+}
+
+/*
+ * Start submission side cache.
+ */
+static void io_submit_state_start(struct io_submit_state *state,
+ struct io_ring_ctx *ctx, unsigned max_ios)
+{
+ blk_start_plug(&state->plug);
+ state->file = NULL;
+ state->ios_left = max_ios;
+}
+
static void io_commit_sqring(struct io_ring_ctx *ctx)
{
struct io_sq_ring *ring = ctx->sq_ring;
@@ -911,11 +1009,13 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
{
+ struct io_submit_state state, *statep = NULL;
int i, ret = 0, submit = 0;
- struct blk_plug plug;
- if (to_submit > IO_PLUG_THRESHOLD)
- blk_start_plug(&plug);
+ if (to_submit > IO_PLUG_THRESHOLD) {
+ io_submit_state_start(&state, ctx, to_submit);
+ statep = &state;
+ }
for (i = 0; i < to_submit; i++) {
struct sqe_submit s;
@@ -924,7 +1024,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
break;
s.has_user = true;
- ret = io_submit_sqe(ctx, &s);
+ ret = io_submit_sqe(ctx, &s, statep);
if (ret) {
io_drop_sqring(ctx);
break;
@@ -934,8 +1034,8 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
}
io_commit_sqring(ctx);
- if (to_submit > IO_PLUG_THRESHOLD)
- blk_finish_plug(&plug);
+ if (statep)
+ io_submit_state_end(statep);
return submit ? submit : ret;
}
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 08/18] fs: add fget_many() and fput_many()
From: Jens Axboe @ 2019-01-30 21:55 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api; +Cc: hch, jmoyer, avi, jannh, Jens Axboe
In-Reply-To: <20190130215540.20871-1-axboe@kernel.dk>
Some uses cases repeatedly get and put references to the same file, but
the only exposed interface is doing these one at the time. As each of
these entail an atomic inc or dec on a shared structure, that cost can
add up.
Add fget_many(), which works just like fget(), except it takes an
argument for how many references to get on the file. Ditto fput_many(),
which can drop an arbitrary number of references to a file.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/file.c | 15 ++++++++++-----
fs/file_table.c | 9 +++++++--
include/linux/file.h | 2 ++
include/linux/fs.h | 4 +++-
4 files changed, 22 insertions(+), 8 deletions(-)
diff --git a/fs/file.c b/fs/file.c
index 3209ee271c41..97df385d6ab0 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -705,7 +705,7 @@ 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;
@@ -720,7 +720,7 @@ static struct file *__fget(unsigned int fd, fmode_t mask)
*/
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();
@@ -728,15 +728,20 @@ static struct file *__fget(unsigned int fd, fmode_t mask)
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);
@@ -767,7 +772,7 @@ 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;
diff --git a/fs/file_table.c b/fs/file_table.c
index 5679e7fcb6b0..155d7514a094 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
diff --git a/include/linux/file.h b/include/linux/file.h
index 6b2fb032416c..3fcddff56bc4 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -13,6 +13,7 @@
struct file;
extern void fput(struct file *);
+extern void fput_many(struct file *, unsigned int);
struct file_operations;
struct vfsmount;
@@ -44,6 +45,7 @@ static inline void fdput(struct fd fd)
}
extern struct file *fget(unsigned int fd);
+extern struct file *fget_many(unsigned int fd, unsigned int refs);
extern struct file *fget_raw(unsigned int fd);
extern unsigned long __fdget(unsigned int fd);
extern unsigned long __fdget_raw(unsigned int fd);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ccb0b7a63aa5..acaad78b6781 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -952,7 +952,9 @@ static inline struct file *get_file(struct file *f)
atomic_long_inc(&f->f_count);
return f;
}
-#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count)
+#define get_file_rcu_many(x, cnt) \
+ atomic_long_add_unless(&(x)->f_count, (cnt), 0)
+#define get_file_rcu(x) get_file_rcu_many((x), 1)
#define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1)
#define file_count(x) atomic_long_read(&(x)->f_count)
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 07/18] io_uring: support for IO polling
From: Jens Axboe @ 2019-01-30 21:55 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api; +Cc: hch, jmoyer, avi, jannh, Jens Axboe
In-Reply-To: <20190130215540.20871-1-axboe@kernel.dk>
Add support for a polled io_uring context. When a read or write is
submitted to a polled context, the application must poll for completions
on the CQ ring through io_uring_enter(2). Polled IO may not generate
IRQ completions, hence they need to be actively found by the application
itself.
To use polling, io_uring_setup() must be used with the
IORING_SETUP_IOPOLL flag being set. It is illegal to mix and match
polled and non-polled IO on an io_uring.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/io_uring.c | 261 ++++++++++++++++++++++++++++++++--
include/uapi/linux/io_uring.h | 5 +
2 files changed, 257 insertions(+), 9 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index bcd3a7c72142..90a745c34e8b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -102,6 +102,14 @@ struct io_ring_ctx {
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;
} ____cacheline_aligned_in_smp;
};
@@ -120,12 +128,15 @@ struct io_kiocb {
struct list_head list;
unsigned int flags;
#define REQ_F_FORCE_NONBLOCK 1 /* inline submission attempt */
+#define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */
u64 user_data;
+ u64 error;
struct work_struct work;
};
#define IO_PLUG_THRESHOLD 2
+#define IO_IOPOLL_BATCH 8
static struct kmem_cache *req_cachep;
@@ -157,6 +168,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
mutex_init(&ctx->uring_lock);
init_waitqueue_head(&ctx->wait);
spin_lock_init(&ctx->completion_lock);
+ INIT_LIST_HEAD(&ctx->poll_list);
return ctx;
}
@@ -251,12 +263,153 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx)
return NULL;
}
+static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr)
+{
+ if (*nr) {
+ kmem_cache_free_bulk(req_cachep, *nr, reqs);
+ io_ring_drop_ctx_refs(ctx, *nr);
+ *nr = 0;
+ }
+}
+
static void io_free_req(struct io_kiocb *req)
{
io_ring_drop_ctx_refs(req->ctx, 1);
kmem_cache_free(req_cachep, req);
}
+/*
+ * Find and free completed poll iocbs
+ */
+static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
+ struct list_head *done)
+{
+ void *reqs[IO_IOPOLL_BATCH];
+ struct io_kiocb *req;
+ int to_free = 0;
+
+ while (!list_empty(done)) {
+ req = list_first_entry(done, struct io_kiocb, list);
+ list_del(&req->list);
+
+ io_cqring_fill_event(ctx, req->user_data, req->error, 0);
+
+ reqs[to_free++] = req;
+ (*nr_events)++;
+
+ fput(req->rw.ki_filp);
+ if (to_free == ARRAY_SIZE(reqs))
+ io_free_req_many(ctx, reqs, &to_free);
+ }
+ io_commit_cqring(ctx);
+
+ io_free_req_many(ctx, reqs, &to_free);
+}
+
+static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
+ long min)
+{
+ struct io_kiocb *req, *tmp;
+ LIST_HEAD(done);
+ bool spin;
+ int ret;
+
+ /*
+ * Only spin for completions if we don't have multiple devices hanging
+ * off our complete list, and we're under the requested amount.
+ */
+ spin = !ctx->poll_multi_file && *nr_events < min;
+
+ ret = 0;
+ list_for_each_entry_safe(req, tmp, &ctx->poll_list, list) {
+ struct kiocb *kiocb = &req->rw;
+
+ /*
+ * Move completed entries to our local list. If we find a
+ * request that requires polling, break out and complete
+ * the done list first, if we have entries there.
+ */
+ if (req->flags & REQ_F_IOPOLL_COMPLETED) {
+ list_move_tail(&req->list, &done);
+ continue;
+ }
+ if (!list_empty(&done))
+ break;
+
+ ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin);
+ if (ret < 0)
+ break;
+
+ if (ret && spin)
+ spin = false;
+ ret = 0;
+ }
+
+ if (!list_empty(&done))
+ io_iopoll_complete(ctx, nr_events, &done);
+
+ return ret;
+}
+
+/*
+ * Poll for a mininum of 'min' events. Note that if min == 0 we consider that a
+ * non-spinning poll check - we'll still enter the driver poll loop, but only
+ * as a non-spinning completion check.
+ */
+static int io_iopoll_getevents(struct io_ring_ctx *ctx, unsigned int *nr_events,
+ long min)
+{
+ while (!list_empty(&ctx->poll_list)) {
+ int ret;
+
+ ret = io_do_iopoll(ctx, nr_events, min);
+ if (ret < 0)
+ return ret;
+ if (!min || *nr_events >= min)
+ return 0;
+ }
+
+ return 1;
+}
+
+/*
+ * We can't just wait for polled events to come to us, we have to actively
+ * find and complete them.
+ */
+static void io_iopoll_reap_events(struct io_ring_ctx *ctx)
+{
+ if (!(ctx->flags & IORING_SETUP_IOPOLL))
+ return;
+
+ mutex_lock(&ctx->uring_lock);
+ while (!list_empty(&ctx->poll_list)) {
+ unsigned int nr_events = 0;
+
+ io_iopoll_getevents(ctx, &nr_events, 1);
+ }
+ mutex_unlock(&ctx->uring_lock);
+}
+
+static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
+ long min)
+{
+ int ret = 0;
+
+ do {
+ int tmin = 0;
+
+ if (*nr_events < min)
+ tmin = min - *nr_events;
+
+ ret = io_iopoll_getevents(ctx, nr_events, tmin);
+ if (ret <= 0)
+ break;
+ ret = 0;
+ } while (!*nr_events || !need_resched());
+
+ return ret;
+}
+
static void kiocb_end_write(struct kiocb *kiocb)
{
if (kiocb->ki_flags & IOCB_WRITE) {
@@ -283,9 +436,57 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
io_free_req(req);
}
+static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
+{
+ struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
+
+ kiocb_end_write(kiocb);
+
+ req->error = res;
+ if (res != -EAGAIN)
+ req->flags |= REQ_F_IOPOLL_COMPLETED;
+}
+
+/*
+ * After the iocb has been issued, it's safe to be found on the poll list.
+ * Adding the kiocb to the list AFTER submission ensures that we don't
+ * find it from a io_iopoll_getevents() thread before the issuer is done
+ * accessing the kiocb cookie.
+ */
+static void io_iopoll_req_issued(struct io_kiocb *req)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+
+ /*
+ * Track whether we have multiple files in our lists. This will impact
+ * how we do polling eventually, not spinning if we're on potentially
+ * different devices.
+ */
+ if (list_empty(&ctx->poll_list)) {
+ ctx->poll_multi_file = false;
+ } else if (!ctx->poll_multi_file) {
+ struct io_kiocb *list_req;
+
+ list_req = list_first_entry(&ctx->poll_list, struct io_kiocb,
+ list);
+ if (list_req->rw.ki_filp != req->rw.ki_filp)
+ ctx->poll_multi_file = true;
+ }
+
+ /*
+ * For fast devices, IO may have already completed. If it has, add
+ * it to the front so we find it first.
+ */
+ if (req->flags & REQ_F_IOPOLL_COMPLETED)
+ list_add(&req->list, &ctx->poll_list);
+ else
+ list_add_tail(&req->list, &ctx->poll_list);
+}
+
static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
bool force_nonblock)
{
+ struct io_ring_ctx *ctx = req->ctx;
struct kiocb *kiocb = &req->rw;
unsigned ioprio;
int fd, ret;
@@ -315,12 +516,22 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
kiocb->ki_flags |= IOCB_NOWAIT;
req->flags |= REQ_F_FORCE_NONBLOCK;
}
- if (kiocb->ki_flags & IOCB_HIPRI) {
- ret = -EINVAL;
- goto out_fput;
- }
+ if (ctx->flags & IORING_SETUP_IOPOLL) {
+ ret = -EOPNOTSUPP;
+ if (!(kiocb->ki_flags & IOCB_DIRECT) ||
+ !kiocb->ki_filp->f_op->iopoll)
+ goto out_fput;
- kiocb->ki_complete = io_complete_rw;
+ req->error = 0;
+ kiocb->ki_flags |= IOCB_HIPRI;
+ kiocb->ki_complete = io_complete_rw_iopoll;
+ } else {
+ if (kiocb->ki_flags & IOCB_HIPRI) {
+ ret = -EINVAL;
+ goto out_fput;
+ }
+ kiocb->ki_complete = io_complete_rw;
+ }
return 0;
out_fput:
fput(kiocb->ki_filp);
@@ -473,6 +684,9 @@ static int io_nop(struct io_kiocb *req, u64 user_data)
{
struct io_ring_ctx *ctx = req->ctx;
+ if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
+ return -EINVAL;
+
io_cqring_add_event(ctx, user_data, 0, 0);
io_free_req(req);
return 0;
@@ -493,6 +707,8 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
if (force_nonblock)
return -EAGAIN;
+ if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ return -EINVAL;
if (unlikely(sqe->addr || sqe->ioprio))
return -EINVAL;
@@ -543,7 +759,16 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
break;
}
- return ret;
+ if (ret)
+ return ret;
+
+ if (ctx->flags & IORING_SETUP_IOPOLL) {
+ if (req->error == -EAGAIN)
+ return -EAGAIN;
+ io_iopoll_req_issued(req);
+ }
+
+ return 0;
}
static void io_sq_wq_submit_work(struct work_struct *work)
@@ -572,7 +797,17 @@ static void io_sq_wq_submit_work(struct work_struct *work)
use_mm(ctx->sqo_mm);
set_fs(USER_DS);
- ret = __io_submit_sqe(ctx, req, s, false);
+ do {
+ ret = __io_submit_sqe(ctx, req, s, false);
+ /*
+ * We can get EAGAIN for polled IO even though we're forcing
+ * a sync submission from here, since we can't wait for
+ * request slots on the block side.
+ */
+ if (ret != -EAGAIN)
+ break;
+ cond_resched();
+ } while (1);
set_fs(old_fs);
unuse_mm(ctx->sqo_mm);
@@ -767,6 +1002,8 @@ static int __io_uring_enter(struct io_ring_ctx *ctx, unsigned to_submit,
return submitted;
}
if (flags & IORING_ENTER_GETEVENTS) {
+ unsigned nr_events = 0;
+
/*
* The application could have included the 'to_submit' count
* in how many events it wanted to wait for. If we failed to
@@ -776,7 +1013,10 @@ static int __io_uring_enter(struct io_ring_ctx *ctx, unsigned to_submit,
if (submitted < to_submit)
min_complete = min_t(unsigned, submitted, min_complete);
- ret = io_cqring_wait(ctx, min_complete, sig, sigsz);
+ if (ctx->flags & IORING_SETUP_IOPOLL)
+ ret = io_iopoll_check(ctx, &nr_events, min_complete);
+ else
+ ret = io_cqring_wait(ctx, min_complete, sig, sigsz);
}
return submitted ? submitted : ret;
@@ -877,6 +1117,8 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
mmdrop(ctx->sqo_mm);
put_files_struct(ctx->sqo_files);
+ io_iopoll_reap_events(ctx);
+
io_mem_free(ctx->sq_ring);
io_mem_free(ctx->sq_sqes);
io_mem_free(ctx->cq_ring);
@@ -914,6 +1156,7 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
percpu_ref_kill(&ctx->refs);
mutex_unlock(&ctx->uring_lock);
+ io_iopoll_reap_events(ctx);
wait_for_completion(&ctx->ctx_done);
io_ring_ctx_free(ctx);
}
@@ -1135,7 +1378,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
return -EINVAL;
}
- if (p.flags)
+ if (p.flags & ~IORING_SETUP_IOPOLL)
return -EINVAL;
ret = io_uring_create(entries, &p);
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 0fca46f8fc37..4952fc921866 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -30,6 +30,11 @@ struct io_uring_sqe {
__u64 __pad2[3];
};
+/*
+ * io_uring_setup() flags
+ */
+#define IORING_SETUP_IOPOLL (1U << 0) /* io_context is polled */
+
#define IORING_OP_NOP 0
#define IORING_OP_READV 1
#define IORING_OP_WRITEV 2
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 06/18] io_uring: add fsync support
From: Jens Axboe @ 2019-01-30 21:55 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api; +Cc: hch, jmoyer, avi, jannh, Jens Axboe
In-Reply-To: <20190130215540.20871-1-axboe@kernel.dk>
From: Christoph Hellwig <hch@lst.de>
Add a new fsync opcode, which either syncs a range if one is passed,
or the whole file if the offset and length fields are both cleared
to zero. A flag is provided to use fdatasync semantics, that is only
force out metadata which is required to retrieve the file data, but
not others like metadata.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/io_uring.c | 40 +++++++++++++++++++++++++++++++++++
include/uapi/linux/io_uring.h | 8 ++++++-
2 files changed, 47 insertions(+), 1 deletion(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 356a697ee21c..bcd3a7c72142 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4,6 +4,7 @@
* supporting fast/efficient IO.
*
* Copyright (C) 2018-2019 Jens Axboe
+ * Copyright (c) 2018-2019 Christoph Hellwig
*/
#include <linux/kernel.h>
#include <linux/init.h>
@@ -477,6 +478,42 @@ static int io_nop(struct io_kiocb *req, u64 user_data)
return 0;
}
+static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+ bool force_nonblock)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ loff_t sqe_off = READ_ONCE(sqe->off);
+ loff_t sqe_len = READ_ONCE(sqe->len);
+ loff_t end = sqe_off + sqe_len;
+ unsigned fsync_flags;
+ struct file *file;
+ int ret, fd;
+
+ /* fsync always requires a blocking context */
+ if (force_nonblock)
+ return -EAGAIN;
+
+ if (unlikely(sqe->addr || sqe->ioprio))
+ return -EINVAL;
+
+ fsync_flags = READ_ONCE(sqe->fsync_flags);
+ if (unlikely(fsync_flags & ~IORING_FSYNC_DATASYNC))
+ return -EINVAL;
+
+ fd = READ_ONCE(sqe->fd);
+ file = fget(fd);
+ if (unlikely(!file))
+ return -EBADF;
+
+ ret = vfs_fsync_range(file, sqe_off, end > 0 ? end : LLONG_MAX,
+ fsync_flags & IORING_FSYNC_DATASYNC);
+
+ fput(file);
+ io_cqring_add_event(ctx, sqe->user_data, ret, 0);
+ io_free_req(req);
+ return 0;
+}
+
static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
const struct sqe_submit *s, bool force_nonblock)
{
@@ -498,6 +535,9 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
case IORING_OP_WRITEV:
ret = io_write(req, s, force_nonblock);
break;
+ case IORING_OP_FSYNC:
+ ret = io_fsync(req, s->sqe, force_nonblock);
+ break;
default:
ret = -EINVAL;
break;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index bd47e86701ea..0fca46f8fc37 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -24,7 +24,7 @@ struct io_uring_sqe {
__u32 len; /* buffer size or number of iovecs */
union {
__kernel_rwf_t rw_flags;
- __u32 __resv;
+ __u32 fsync_flags;
};
__u64 user_data; /* data to be passed back at completion time */
__u64 __pad2[3];
@@ -33,6 +33,12 @@ struct io_uring_sqe {
#define IORING_OP_NOP 0
#define IORING_OP_READV 1
#define IORING_OP_WRITEV 2
+#define IORING_OP_FSYNC 3
+
+/*
+ * sqe->fsync_flags
+ */
+#define IORING_FSYNC_DATASYNC (1U << 0)
/*
* IO completion data structure (Completion Queue Entry)
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 05/18] Add io_uring IO interface
From: Jens Axboe @ 2019-01-30 21:55 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api; +Cc: hch, jmoyer, avi, jannh, Jens Axboe
In-Reply-To: <20190130215540.20871-1-axboe@kernel.dk>
The submission queue (SQ) and completion queue (CQ) rings are shared
between the application and the kernel. This eliminates the need to
copy data back and forth to submit and complete IO.
IO submissions use the io_uring_sqe data structure, and completions
are generated in the form of io_uring_sqe data structures. The SQ
ring is an index into the io_uring_sqe array, which makes it possible
to submit a batch of IOs without them being contiguous in the ring.
The CQ ring is always contiguous, as completion events are inherently
unordered, and hence any io_uring_cqe entry can point back to an
arbitrary submission.
Two new system calls are added for this:
io_uring_setup(entries, params)
Sets up a context for doing async IO. On success, returns a file
descriptor that the application can mmap to gain access to the
SQ ring, CQ ring, and io_uring_sqes.
io_uring_enter(fd, to_submit, min_complete, flags, sigset, sigsetsize)
Initiates IO against the rings mapped to this fd, or waits for
them to complete, or both. The behavior is controlled by the
parameters passed in. If 'to_submit' is non-zero, then we'll
try and submit new IO. If IORING_ENTER_GETEVENTS is set, the
kernel will wait for 'min_complete' events, if they aren't
already available. It's valid to set IORING_ENTER_GETEVENTS
and 'min_complete' == 0 at the same time, this allows the
kernel to return already completed events without waiting
for them. This is useful only for polling, as for IRQ
driven IO, the application can just check the CQ ring
without entering the kernel.
With this setup, it's possible to do async IO with a single system
call. Future developments will enable polled IO with this interface,
and polled submission as well. The latter will enable an application
to do IO without doing ANY system calls at all.
For IRQ driven IO, an application only needs to enter the kernel for
completions if it wants to wait for them to occur.
Each io_uring is backed by a workqueue, to support buffered async IO
as well. We will only punt to an async context if the command would
need to wait for IO on the device side. Any data that can be accessed
directly in the page cache is done inline. This avoids the slowness
issue of usual threadpools, since cached data is accessed as quickly
as a sync interface.
Sample application: http://git.kernel.dk/cgit/fio/plain/t/io_uring.c
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
arch/x86/entry/syscalls/syscall_32.tbl | 2 +
arch/x86/entry/syscalls/syscall_64.tbl | 2 +
fs/Makefile | 1 +
fs/io_uring.c | 1122 ++++++++++++++++++++++++
include/linux/syscalls.h | 6 +
include/uapi/asm-generic/unistd.h | 6 +-
include/uapi/linux/io_uring.h | 94 ++
init/Kconfig | 9 +
kernel/sys_ni.c | 2 +
9 files changed, 1243 insertions(+), 1 deletion(-)
create mode 100644 fs/io_uring.c
create mode 100644 include/uapi/linux/io_uring.h
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 3cf7b533b3d1..481c126259e9 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -398,3 +398,5 @@
384 i386 arch_prctl sys_arch_prctl __ia32_compat_sys_arch_prctl
385 i386 io_pgetevents sys_io_pgetevents __ia32_compat_sys_io_pgetevents
386 i386 rseq sys_rseq __ia32_sys_rseq
+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
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index f0b1709a5ffb..6a32a430c8e0 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -343,6 +343,8 @@
332 common statx __x64_sys_statx
333 common io_pgetevents __x64_sys_io_pgetevents
334 common rseq __x64_sys_rseq
+425 common io_uring_setup __x64_sys_io_uring_setup
+426 common io_uring_enter __x64_sys_io_uring_enter
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/fs/Makefile b/fs/Makefile
index 293733f61594..8e15d6fc4340 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -30,6 +30,7 @@ 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
diff --git a/fs/io_uring.c b/fs/io_uring.c
new file mode 100644
index 000000000000..356a697ee21c
--- /dev/null
+++ b/fs/io_uring.c
@@ -0,0 +1,1122 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shared application/kernel submission and completion ring pairs, for
+ * supporting fast/efficient IO.
+ *
+ * Copyright (C) 2018-2019 Jens Axboe
+ */
+#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/blkdev.h>
+#include <linux/anon_inodes.h>
+#include <linux/sched/mm.h>
+#include <linux/uaccess.h>
+#include <linux/nospec.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "internal.h"
+
+#define IORING_MAX_ENTRIES 4096
+
+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_ring_ctx {
+ struct {
+ struct percpu_ref refs;
+ } ____cacheline_aligned_in_smp;
+
+ struct {
+ unsigned int flags;
+ bool compat;
+
+ /* SQ ring */
+ struct io_sq_ring *sq_ring;
+ unsigned cached_sq_head;
+ unsigned sq_entries;
+ unsigned sq_mask;
+ unsigned sq_thread_cpu;
+ struct io_uring_sqe *sq_sqes;
+ } ____cacheline_aligned_in_smp;
+
+ /* IO offload */
+ struct workqueue_struct *sqo_wq;
+ struct mm_struct *sqo_mm;
+ struct files_struct *sqo_files;
+
+ 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;
+
+ 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;
+ } ____cacheline_aligned_in_smp;
+};
+
+struct sqe_submit {
+ const struct io_uring_sqe *sqe;
+ unsigned short index;
+ bool has_user;
+};
+
+struct io_kiocb {
+ struct kiocb rw;
+
+ struct sqe_submit submit;
+
+ struct io_ring_ctx *ctx;
+ struct list_head list;
+ unsigned int flags;
+#define REQ_F_FORCE_NONBLOCK 1 /* inline submission attempt */
+ u64 user_data;
+
+ struct work_struct work;
+};
+
+#define IO_PLUG_THRESHOLD 2
+
+static struct kmem_cache *req_cachep;
+
+static const struct file_operations io_uring_fops;
+
+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;
+
+ 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);
+ spin_lock_init(&ctx->completion_lock);
+ 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 != ring->r.tail) {
+ /* order cqe stores with ring update */
+ smp_wmb();
+ WRITE_ONCE(ring->r.tail, ctx->cached_cq_tail);
+ /* write side barrier of tail update, app has read side */
+ 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;
+ 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) {
+ cqe->user_data = ki_user_data;
+ cqe->res = res;
+ cqe->flags = ev_flags;
+ } else
+ ctx->cq_ring->overflow++;
+}
+
+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);
+}
+
+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_kiocb *req;
+
+ if (!percpu_ref_tryget(&ctx->refs))
+ return NULL;
+
+ req = kmem_cache_alloc(req_cachep, __GFP_NOWARN);
+ if (req) {
+ req->ctx = ctx;
+ req->flags = 0;
+ return req;
+ }
+
+ io_ring_drop_ctx_refs(ctx, 1);
+ return NULL;
+}
+
+static void io_free_req(struct io_kiocb *req)
+{
+ io_ring_drop_ctx_refs(req->ctx, 1);
+ kmem_cache_free(req_cachep, req);
+}
+
+static void kiocb_end_write(struct kiocb *kiocb)
+{
+ if (kiocb->ki_flags & IOCB_WRITE) {
+ struct inode *inode = file_inode(kiocb->ki_filp);
+
+ /*
+ * Tell lockdep we inherited freeze protection from submission
+ * thread.
+ */
+ if (S_ISREG(inode->i_mode))
+ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
+ file_end_write(kiocb->ki_filp);
+ }
+}
+
+static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
+{
+ struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
+
+ kiocb_end_write(kiocb);
+
+ fput(kiocb->ki_filp);
+ io_cqring_add_event(req->ctx, req->user_data, res, 0);
+ io_free_req(req);
+}
+
+static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+ bool force_nonblock)
+{
+ struct kiocb *kiocb = &req->rw;
+ unsigned ioprio;
+ int fd, ret;
+
+ fd = READ_ONCE(sqe->fd);
+ kiocb->ki_filp = fget(fd);
+ if (unlikely(!kiocb->ki_filp))
+ return -EBADF;
+ kiocb->ki_pos = READ_ONCE(sqe->off);
+ kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
+ kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp));
+
+ ioprio = READ_ONCE(sqe->ioprio);
+ if (ioprio) {
+ ret = ioprio_check_cap(ioprio);
+ if (ret)
+ goto out_fput;
+
+ kiocb->ki_ioprio = ioprio;
+ } else
+ kiocb->ki_ioprio = get_current_ioprio();
+
+ ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
+ if (unlikely(ret))
+ goto out_fput;
+ if (force_nonblock) {
+ kiocb->ki_flags |= IOCB_NOWAIT;
+ req->flags |= REQ_F_FORCE_NONBLOCK;
+ }
+ if (kiocb->ki_flags & IOCB_HIPRI) {
+ ret = -EINVAL;
+ goto out_fput;
+ }
+
+ kiocb->ki_complete = io_complete_rw;
+ return 0;
+out_fput:
+ fput(kiocb->ki_filp);
+ return ret;
+}
+
+static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
+{
+ switch (ret) {
+ case -EIOCBQUEUED:
+ break;
+ case -ERESTARTSYS:
+ case -ERESTARTNOINTR:
+ case -ERESTARTNOHAND:
+ case -ERESTART_RESTARTBLOCK:
+ /*
+ * We can't just restart the syscall, since previously
+ * submitted sqes may already be in progress. Just fail this
+ * IO with EINTR.
+ */
+ ret = -EINTR;
+ /* fall through */
+ default:
+ kiocb->ki_complete(kiocb, ret, 0);
+ }
+}
+
+static int io_import_iovec(struct io_ring_ctx *ctx, int rw,
+ const struct sqe_submit *s, struct iovec **iovec,
+ struct iov_iter *iter)
+{
+ const struct io_uring_sqe *sqe = s->sqe;
+ void __user *buf = u64_to_user_ptr(READ_ONCE(sqe->addr));
+ size_t sqe_len = READ_ONCE(sqe->len);
+
+ if (!s->has_user)
+ return EFAULT;
+
+#ifdef CONFIG_COMPAT
+ if (ctx->compat)
+ return compat_import_iovec(rw, buf, sqe_len, UIO_FASTIOV,
+ iovec, iter);
+#endif
+
+ return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter);
+}
+
+static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s,
+ bool force_nonblock)
+{
+ struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
+ struct kiocb *kiocb = &req->rw;
+ struct iov_iter iter;
+ struct file *file;
+ ssize_t ret;
+
+ ret = io_prep_rw(req, s->sqe, force_nonblock);
+ if (ret)
+ return ret;
+ file = kiocb->ki_filp;
+
+ ret = -EBADF;
+ if (unlikely(!(file->f_mode & FMODE_READ)))
+ goto out_fput;
+ ret = -EINVAL;
+ if (unlikely(!file->f_op->read_iter))
+ goto out_fput;
+
+ ret = io_import_iovec(req->ctx, READ, s, &iovec, &iter);
+ if (ret)
+ goto out_fput;
+
+ ret = rw_verify_area(READ, file, &kiocb->ki_pos, iov_iter_count(&iter));
+ if (!ret) {
+ ssize_t ret2;
+
+ /* Catch -EAGAIN return for forced non-blocking submission */
+ ret2 = call_read_iter(file, kiocb, &iter);
+ if (!force_nonblock || ret2 != -EAGAIN)
+ io_rw_done(kiocb, ret2);
+ else
+ ret = -EAGAIN;
+ }
+ kfree(iovec);
+out_fput:
+ if (unlikely(ret))
+ fput(file);
+ return ret;
+}
+
+static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s,
+ bool force_nonblock)
+{
+ struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
+ struct kiocb *kiocb = &req->rw;
+ struct iov_iter iter;
+ struct file *file;
+ ssize_t ret;
+
+ ret = io_prep_rw(req, s->sqe, force_nonblock);
+ if (ret)
+ return ret;
+ file = kiocb->ki_filp;
+
+ ret = -EAGAIN;
+ if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT))
+ goto out_fput;
+
+ ret = -EBADF;
+ if (unlikely(!(file->f_mode & FMODE_WRITE)))
+ goto out_fput;
+ ret = -EINVAL;
+ if (unlikely(!file->f_op->write_iter))
+ goto out_fput;
+
+ ret = io_import_iovec(req->ctx, WRITE, s, &iovec, &iter);
+ if (ret)
+ goto out_fput;
+
+ ret = rw_verify_area(WRITE, file, &kiocb->ki_pos,
+ iov_iter_count(&iter));
+ if (!ret) {
+ /*
+ * Open-code file_start_write here to grab freeze protection,
+ * which will be released by another thread in
+ * io_complete_rw(). Fool lockdep by telling it the lock got
+ * released so that it doesn't complain about the held lock when
+ * we return to userspace.
+ */
+ if (S_ISREG(file_inode(file)->i_mode)) {
+ __sb_start_write(file_inode(file)->i_sb,
+ SB_FREEZE_WRITE, true);
+ __sb_writers_release(file_inode(file)->i_sb,
+ SB_FREEZE_WRITE);
+ }
+ kiocb->ki_flags |= IOCB_WRITE;
+ io_rw_done(kiocb, call_write_iter(file, kiocb, &iter));
+ }
+ kfree(iovec);
+out_fput:
+ if (unlikely(ret))
+ fput(file);
+ return ret;
+}
+
+/*
+ * IORING_OP_NOP just posts a completion event, nothing else.
+ */
+static int io_nop(struct io_kiocb *req, u64 user_data)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+
+ io_cqring_add_event(ctx, user_data, 0, 0);
+ io_free_req(req);
+ return 0;
+}
+
+static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
+ const struct sqe_submit *s, bool force_nonblock)
+{
+ ssize_t ret;
+ int opcode;
+
+ if (unlikely(s->index >= ctx->sq_entries))
+ return -EINVAL;
+ req->user_data = READ_ONCE(s->sqe->user_data);
+
+ opcode = READ_ONCE(s->sqe->opcode);
+ switch (opcode) {
+ case IORING_OP_NOP:
+ ret = io_nop(req, req->user_data);
+ break;
+ case IORING_OP_READV:
+ ret = io_read(req, s, force_nonblock);
+ break;
+ case IORING_OP_WRITEV:
+ ret = io_write(req, s, force_nonblock);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+static void io_sq_wq_submit_work(struct work_struct *work)
+{
+ struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+ struct sqe_submit *s = &req->submit;
+ u64 user_data = READ_ONCE(s->sqe->user_data);
+ struct io_ring_ctx *ctx = req->ctx;
+ mm_segment_t old_fs = get_fs();
+ struct files_struct *old_files;
+ int ret;
+
+ /* Ensure we clear previously set forced non-block flag */
+ req->flags &= ~REQ_F_FORCE_NONBLOCK;
+
+ task_lock(current);
+ old_files = current->files;
+ current->files = ctx->sqo_files;
+ task_unlock(current);
+
+ if (!mmget_not_zero(ctx->sqo_mm)) {
+ ret = -EFAULT;
+ goto err;
+ }
+
+ use_mm(ctx->sqo_mm);
+ set_fs(USER_DS);
+
+ ret = __io_submit_sqe(ctx, req, s, false);
+
+ set_fs(old_fs);
+ unuse_mm(ctx->sqo_mm);
+ mmput(ctx->sqo_mm);
+err:
+ if (ret) {
+ io_cqring_add_event(ctx, user_data, ret, 0);
+ io_free_req(req);
+ }
+
+ task_lock(current);
+ current->files = old_files;
+ task_unlock(current);
+}
+
+static int io_submit_sqe(struct io_ring_ctx *ctx, const struct sqe_submit *s)
+{
+ struct io_kiocb *req;
+ ssize_t ret;
+
+ /* enforce forwards compatibility on users */
+ if (unlikely(s->sqe->flags))
+ return -EINVAL;
+
+ req = io_get_req(ctx);
+ if (unlikely(!req))
+ return -EAGAIN;
+
+ ret = __io_submit_sqe(ctx, req, s, true);
+ if (ret == -EAGAIN) {
+ memcpy(&req->submit, s, sizeof(*s));
+ INIT_WORK(&req->work, io_sq_wq_submit_work);
+ queue_work(ctx->sqo_wq, &req->work);
+ ret = 0;
+ }
+ if (ret)
+ io_free_req(req);
+
+ return ret;
+}
+
+static void io_commit_sqring(struct io_ring_ctx *ctx)
+{
+ struct io_sq_ring *ring = ctx->sq_ring;
+
+ if (ctx->cached_sq_head != ring->r.head) {
+ WRITE_ONCE(ring->r.head, ctx->cached_sq_head);
+ /* write side barrier of head update, app has read side */
+ smp_wmb();
+ }
+}
+
+/*
+ * Undo last io_get_sqring()
+ */
+static void io_drop_sqring(struct io_ring_ctx *ctx)
+{
+ ctx->cached_sq_head--;
+}
+
+/*
+ * Fetch an sqe, if one is available. Note that s->sqe will point to memory
+ * that is mapped by userspace. This means that care needs to be taken to
+ * ensure that reads are stable, as we cannot rely on userspace always
+ * being a good citizen. If members of the sqe are validated and then later
+ * used, it's important that those reads are done through READ_ONCE() to
+ * prevent a re-load down the line.
+ */
+static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
+{
+ struct io_sq_ring *ring = ctx->sq_ring;
+ unsigned head;
+
+ /*
+ * The cached sq head (or cq tail) serves two purposes:
+ *
+ * 1) allows us to batch the cost of updating the user visible
+ * head updates.
+ * 2) allows the kernel side to track the head on its own, even
+ * though the application is the one updating it.
+ */
+ head = ctx->cached_sq_head;
+ smp_rmb();
+ if (head == READ_ONCE(ring->r.tail))
+ return false;
+
+ head = READ_ONCE(ring->array[head & ctx->sq_mask]);
+ if (head < ctx->sq_entries) {
+ s->index = head;
+ s->sqe = &ctx->sq_sqes[head];
+ ctx->cached_sq_head++;
+ return true;
+ }
+
+ /* drop invalid entries */
+ ctx->cached_sq_head++;
+ ring->dropped++;
+ smp_wmb();
+ return false;
+}
+
+static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
+{
+ int i, ret = 0, submit = 0;
+ struct blk_plug plug;
+
+ if (to_submit > IO_PLUG_THRESHOLD)
+ blk_start_plug(&plug);
+
+ for (i = 0; i < to_submit; i++) {
+ struct sqe_submit s;
+
+ if (!io_get_sqring(ctx, &s))
+ break;
+
+ s.has_user = true;
+ ret = io_submit_sqe(ctx, &s);
+ if (ret) {
+ io_drop_sqring(ctx);
+ break;
+ }
+
+ submit++;
+ }
+ io_commit_sqring(ctx);
+
+ if (to_submit > IO_PLUG_THRESHOLD)
+ blk_finish_plug(&plug);
+
+ return submit ? submit : ret;
+}
+
+/*
+ * 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.
+ */
+static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
+ const sigset_t __user *sig, size_t sigsz)
+{
+ struct io_cq_ring *ring = ctx->cq_ring;
+ sigset_t ksigmask, sigsaved;
+ DEFINE_WAIT(wait);
+ int ret = 0;
+
+ smp_rmb();
+ if (ring->r.head != ring->r.tail)
+ return 0;
+ if (!min_events)
+ return 0;
+
+ if (sig) {
+ ret = set_user_sigmask(sig, &ksigmask, &sigsaved, sigsz);
+ if (ret)
+ return ret;
+ }
+
+ do {
+ prepare_to_wait(&ctx->wait, &wait, TASK_INTERRUPTIBLE);
+
+ ret = 0;
+ smp_rmb();
+ if (ring->r.head != ring->r.tail)
+ break;
+
+ schedule();
+
+ ret = -EINTR;
+ if (signal_pending(current))
+ break;
+ } while (1);
+
+ finish_wait(&ctx->wait, &wait);
+
+ if (sig)
+ restore_user_sigmask(sig, &sigsaved);
+
+ return ring->r.head == ring->r.tail ? ret : 0;
+}
+
+static int __io_uring_enter(struct io_ring_ctx *ctx, unsigned to_submit,
+ unsigned min_complete, unsigned flags,
+ const sigset_t __user *sig, size_t sigsz)
+{
+ int submitted, ret;
+
+ submitted = ret = 0;
+ if (to_submit) {
+ to_submit = min(to_submit, ctx->sq_entries);
+
+ submitted = io_ring_submit(ctx, to_submit);
+ if (submitted < 0)
+ return submitted;
+ }
+ if (flags & IORING_ENTER_GETEVENTS) {
+ /*
+ * The application could have included the 'to_submit' count
+ * in how many events it wanted to wait for. If we failed to
+ * submit the desired count, we may need to adjust the number
+ * of events to poll/wait for.
+ */
+ if (submitted < to_submit)
+ min_complete = min_t(unsigned, submitted, min_complete);
+
+ ret = io_cqring_wait(ctx, min_complete, sig, sigsz);
+ }
+
+ return submitted ? submitted : ret;
+}
+
+static int io_sq_offload_start(struct io_ring_ctx *ctx)
+{
+ int ret;
+
+ mmgrab(current->mm);
+ ctx->sqo_mm = current->mm;
+
+ ret = -EBADF;
+ ctx->sqo_files = get_files_struct(current);
+ if (!ctx->sqo_files)
+ goto err;
+
+ /* Do QD, or 2 * CPUS, whatever is smallest */
+ ctx->sqo_wq = alloc_workqueue("io_ring-wq", WQ_UNBOUND | WQ_FREEZABLE,
+ min(ctx->sq_entries - 1, 2 * num_online_cpus()));
+ if (!ctx->sqo_wq) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ return 0;
+err:
+ if (ctx->sqo_files) {
+ put_files_struct(ctx->sqo_files);
+ ctx->sqo_files = NULL;
+ }
+ mmdrop(ctx->sqo_mm);
+ ctx->sqo_mm = NULL;
+ return ret;
+}
+
+static void __io_unaccount_mem(struct user_struct *user, unsigned long nr_pages)
+{
+ atomic_long_sub(nr_pages, &user->locked_vm);
+}
+
+static void io_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages)
+{
+ if (ctx->user)
+ __io_unaccount_mem(ctx->user, nr_pages);
+}
+
+static int __io_account_mem(struct user_struct *user, unsigned long nr_pages)
+{
+ unsigned long page_limit, cur_pages, new_pages;
+
+ /* Don't allow more pages than we can safely lock */
+ page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+
+ do {
+ cur_pages = atomic_long_read(&user->locked_vm);
+ new_pages = cur_pages + nr_pages;
+ if (new_pages > page_limit)
+ return -ENOMEM;
+ } while (atomic_long_cmpxchg(&user->locked_vm, cur_pages,
+ new_pages) != cur_pages);
+
+ return 0;
+}
+
+static void io_mem_free(void *ptr)
+{
+ struct page *page = virt_to_head_page(ptr);
+
+ if (put_page_testzero(page))
+ free_compound_page(page);
+}
+
+static void *io_mem_alloc(size_t size)
+{
+ gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP |
+ __GFP_NORETRY;
+
+ return (void *) __get_free_pages(gfp_flags, get_order(size));
+}
+
+static unsigned long ring_pages(unsigned sq_entries, unsigned cq_entries)
+{
+ struct io_sq_ring *sq_ring;
+ struct io_cq_ring *cq_ring;
+ size_t bytes;
+
+ bytes = struct_size(sq_ring, array, sq_entries);
+ bytes += array_size(sizeof(struct io_uring_sqe), sq_entries);
+ bytes += struct_size(cq_ring, cqes, cq_entries);
+
+ return (bytes + PAGE_SIZE - 1) / PAGE_SIZE;
+}
+
+static void io_ring_ctx_free(struct io_ring_ctx *ctx)
+{
+ destroy_workqueue(ctx->sqo_wq);
+ mmdrop(ctx->sqo_mm);
+ put_files_struct(ctx->sqo_files);
+
+ io_mem_free(ctx->sq_ring);
+ io_mem_free(ctx->sq_sqes);
+ io_mem_free(ctx->cq_ring);
+
+ percpu_ref_exit(&ctx->refs);
+ io_unaccount_mem(ctx, ring_pages(ctx->sq_entries, ctx->cq_entries));
+ kfree(ctx);
+}
+
+static __poll_t io_uring_poll(struct file *file, poll_table *wait)
+{
+ struct io_ring_ctx *ctx = file->private_data;
+ __poll_t mask = 0;
+
+ poll_wait(file, &ctx->cq_wait, wait);
+ smp_rmb();
+ if (ctx->sq_ring->r.tail + 1 != ctx->cached_sq_head)
+ mask |= EPOLLOUT | EPOLLWRNORM;
+ if (ctx->cq_ring->r.head != ctx->cached_cq_tail)
+ mask |= EPOLLIN | EPOLLRDNORM;
+
+ return mask;
+}
+
+static int io_uring_fasync(int fd, struct file *file, int on)
+{
+ struct io_ring_ctx *ctx = file->private_data;
+
+ return fasync_helper(fd, file, on, &ctx->cq_fasync);
+}
+
+static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
+{
+ mutex_lock(&ctx->uring_lock);
+ percpu_ref_kill(&ctx->refs);
+ mutex_unlock(&ctx->uring_lock);
+
+ wait_for_completion(&ctx->ctx_done);
+ io_ring_ctx_free(ctx);
+}
+
+static int io_uring_release(struct inode *inode, struct file *file)
+{
+ struct io_ring_ctx *ctx = file->private_data;
+
+ file->private_data = NULL;
+ io_ring_ctx_wait_and_kill(ctx);
+ return 0;
+}
+
+static int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ loff_t offset = (loff_t) vma->vm_pgoff << PAGE_SHIFT;
+ unsigned long sz = vma->vm_end - vma->vm_start;
+ struct io_ring_ctx *ctx = file->private_data;
+ unsigned long pfn;
+ struct page *page;
+ void *ptr;
+
+ switch (offset) {
+ case IORING_OFF_SQ_RING:
+ ptr = ctx->sq_ring;
+ break;
+ case IORING_OFF_SQES:
+ ptr = ctx->sq_sqes;
+ break;
+ case IORING_OFF_CQ_RING:
+ ptr = ctx->cq_ring;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ page = virt_to_head_page(ptr);
+ if (sz > (PAGE_SIZE << compound_order(page)))
+ return -EINVAL;
+
+ pfn = virt_to_phys(ptr) >> PAGE_SHIFT;
+ return remap_pfn_range(vma, vma->vm_start, pfn, sz, vma->vm_page_prot);
+}
+
+SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
+ u32, min_complete, u32, flags, const sigset_t __user *, sig,
+ size_t, sigsz)
+{
+ struct io_ring_ctx *ctx;
+ long ret = -EBADF;
+ struct fd f;
+
+ if (flags & ~IORING_ENTER_GETEVENTS)
+ return -EINVAL;
+
+ f = fdget(fd);
+ if (!f.file)
+ return -EBADF;
+
+ ret = -EOPNOTSUPP;
+ if (f.file->f_op != &io_uring_fops)
+ goto out_fput;
+
+ ret = -ENXIO;
+ ctx = f.file->private_data;
+ if (!percpu_ref_tryget(&ctx->refs))
+ goto out_fput;
+
+ ret = -EBUSY;
+ if (!mutex_trylock(&ctx->uring_lock))
+ goto out_ctx;
+
+ ret = __io_uring_enter(ctx, to_submit, min_complete, flags, sig, sigsz);
+ mutex_unlock(&ctx->uring_lock);
+out_ctx:
+ io_ring_drop_ctx_refs(ctx, 1);
+out_fput:
+ fdput(f);
+ return ret;
+}
+
+static const struct file_operations io_uring_fops = {
+ .release = io_uring_release,
+ .mmap = io_uring_mmap,
+ .poll = io_uring_poll,
+ .fasync = io_uring_fasync,
+};
+
+static int io_allocate_scq_urings(struct io_ring_ctx *ctx,
+ struct io_uring_params *p)
+{
+ struct io_sq_ring *sq_ring;
+ struct io_cq_ring *cq_ring;
+ size_t size;
+
+ sq_ring = io_mem_alloc(struct_size(sq_ring, array, p->sq_entries));
+ if (!sq_ring)
+ return -ENOMEM;
+
+ ctx->sq_ring = sq_ring;
+ sq_ring->ring_mask = p->sq_entries - 1;
+ sq_ring->ring_entries = p->sq_entries;
+ ctx->sq_mask = sq_ring->ring_mask;
+ ctx->sq_entries = sq_ring->ring_entries;
+
+ size = array_size(sizeof(struct io_uring_sqe), p->sq_entries);
+ if (size == SIZE_MAX)
+ return -EOVERFLOW;
+
+ ctx->sq_sqes = io_mem_alloc(size);
+ if (!ctx->sq_sqes) {
+ io_mem_free(ctx->sq_ring);
+ return -ENOMEM;
+ }
+
+ cq_ring = io_mem_alloc(struct_size(cq_ring, cqes, p->cq_entries));
+ if (!cq_ring) {
+ io_mem_free(ctx->sq_ring);
+ io_mem_free(ctx->sq_sqes);
+ return -ENOMEM;
+ }
+
+ ctx->cq_ring = cq_ring;
+ cq_ring->ring_mask = p->cq_entries - 1;
+ cq_ring->ring_entries = p->cq_entries;
+ ctx->cq_mask = cq_ring->ring_mask;
+ ctx->cq_entries = cq_ring->ring_entries;
+ return 0;
+}
+
+static int io_uring_create(unsigned entries, struct io_uring_params *p)
+{
+ struct user_struct *user = NULL;
+ struct io_ring_ctx *ctx;
+ int ret;
+
+ if (!entries || entries > IORING_MAX_ENTRIES)
+ return -EINVAL;
+
+ /*
+ * Use twice as many entries for the CQ ring. It's possible for the
+ * application to drive a higher depth than the size of the SQ ring,
+ * since the sqes are only used at submission time. This allows for
+ * some flexibility in overcommitting a bit.
+ */
+ p->sq_entries = roundup_pow_of_two(entries);
+ p->cq_entries = 2 * p->sq_entries;
+
+ if (!capable(CAP_IPC_LOCK)) {
+ user = get_uid(current_user());
+ ret = __io_account_mem(user, ring_pages(p->sq_entries,
+ p->cq_entries));
+ if (ret) {
+ free_uid(user);
+ return ret;
+ }
+ }
+
+ ctx = io_ring_ctx_alloc(p);
+ if (!ctx) {
+ __io_unaccount_mem(user, ring_pages(p->sq_entries,
+ p->cq_entries));
+ free_uid(user);
+ return -ENOMEM;
+ }
+ ctx->compat = in_compat_syscall();
+ ctx->user = user;
+
+ ret = io_allocate_scq_urings(ctx, p);
+ if (ret)
+ goto err;
+
+ ret = io_sq_offload_start(ctx);
+ if (ret)
+ goto err;
+
+ ret = anon_inode_getfd("[io_uring]", &io_uring_fops, ctx,
+ O_RDWR | O_CLOEXEC);
+ if (ret < 0)
+ goto err;
+
+ memset(&p->sq_off, 0, sizeof(p->sq_off));
+ p->sq_off.head = offsetof(struct io_sq_ring, r.head);
+ p->sq_off.tail = offsetof(struct io_sq_ring, r.tail);
+ p->sq_off.ring_mask = offsetof(struct io_sq_ring, ring_mask);
+ p->sq_off.ring_entries = offsetof(struct io_sq_ring, ring_entries);
+ p->sq_off.flags = offsetof(struct io_sq_ring, flags);
+ p->sq_off.dropped = offsetof(struct io_sq_ring, dropped);
+ p->sq_off.array = offsetof(struct io_sq_ring, array);
+
+ memset(&p->cq_off, 0, sizeof(p->cq_off));
+ p->cq_off.head = offsetof(struct io_cq_ring, r.head);
+ p->cq_off.tail = offsetof(struct io_cq_ring, r.tail);
+ p->cq_off.ring_mask = offsetof(struct io_cq_ring, ring_mask);
+ p->cq_off.ring_entries = offsetof(struct io_cq_ring, ring_entries);
+ p->cq_off.overflow = offsetof(struct io_cq_ring, overflow);
+ p->cq_off.cqes = offsetof(struct io_cq_ring, cqes);
+ return ret;
+err:
+ io_ring_ctx_wait_and_kill(ctx);
+ return ret;
+}
+
+/*
+ * Sets up an aio uring context, and returns the fd. Applications asks for a
+ * ring size, we return the actual sq/cq ring sizes (among other things) in the
+ * params structure passed in.
+ */
+static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
+{
+ struct io_uring_params p;
+ long ret;
+ int i;
+
+ if (copy_from_user(&p, params, sizeof(p)))
+ return -EFAULT;
+ for (i = 0; i < ARRAY_SIZE(p.resv); i++) {
+ if (p.resv[i])
+ return -EINVAL;
+ }
+
+ if (p.flags)
+ return -EINVAL;
+
+ ret = io_uring_create(entries, &p);
+ if (ret < 0)
+ return ret;
+
+ if (copy_to_user(params, &p, sizeof(p)))
+ return -EFAULT;
+
+ return ret;
+}
+
+SYSCALL_DEFINE2(io_uring_setup, u32, entries,
+ struct io_uring_params __user *, params)
+{
+ return io_uring_setup(entries, params);
+}
+
+static int __init io_uring_init(void)
+{
+ req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
+ return 0;
+};
+__initcall(io_uring_init);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 257cccba3062..3072dbaa7869 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -69,6 +69,7 @@ struct file_handle;
struct sigaltstack;
struct rseq;
union bpf_attr;
+struct io_uring_params;
#include <linux/types.h>
#include <linux/aio_abi.h>
@@ -309,6 +310,11 @@ asmlinkage long sys_io_pgetevents_time32(aio_context_t ctx_id,
struct io_event __user *events,
struct old_timespec32 __user *timeout,
const struct __aio_sigset *sig);
+asmlinkage long sys_io_uring_setup(u32 entries,
+ struct io_uring_params __user *p);
+asmlinkage long sys_io_uring_enter(unsigned int fd, u32 to_submit,
+ u32 min_complete, u32 flags,
+ const sigset_t __user *sig, size_t sigsz);
/* fs/xattr.c */
asmlinkage long sys_setxattr(const char __user *path, const char __user *name,
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index d90127298f12..87871e7b7ea7 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -740,9 +740,13 @@ __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
__SYSCALL(__NR_rseq, sys_rseq)
#define __NR_kexec_file_load 294
__SYSCALL(__NR_kexec_file_load, sys_kexec_file_load)
+#define __NR_io_uring_setup 425
+__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
+#define __NR_io_uring_enter 426
+__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
#undef __NR_syscalls
-#define __NR_syscalls 295
+#define __NR_syscalls 427
/*
* 32 bit systems traditionally used different
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
new file mode 100644
index 000000000000..bd47e86701ea
--- /dev/null
+++ b/include/uapi/linux/io_uring.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Header file for the io_uring interface.
+ *
+ * Copyright (C) 2019 Jens Axboe
+ * Copyright (C) 2019 Christoph Hellwig
+ */
+#ifndef LINUX_IO_URING_H
+#define LINUX_IO_URING_H
+
+#include <linux/fs.h>
+#include <linux/types.h>
+
+/*
+ * IO submission data structure (Submission Queue Entry)
+ */
+struct io_uring_sqe {
+ __u8 opcode; /* type of operation for this sqe */
+ __u8 flags; /* as of now unused */
+ __u16 ioprio; /* ioprio for the request */
+ __s32 fd; /* file descriptor to do IO on */
+ __u64 off; /* offset into file */
+ __u64 addr; /* pointer to buffer or iovecs */
+ __u32 len; /* buffer size or number of iovecs */
+ union {
+ __kernel_rwf_t rw_flags;
+ __u32 __resv;
+ };
+ __u64 user_data; /* data to be passed back at completion time */
+ __u64 __pad2[3];
+};
+
+#define IORING_OP_NOP 0
+#define IORING_OP_READV 1
+#define IORING_OP_WRITEV 2
+
+/*
+ * IO completion data structure (Completion Queue Entry)
+ */
+struct io_uring_cqe {
+ __u64 user_data; /* sqe->data submission passed back */
+ __s32 res; /* result code for this event */
+ __u32 flags;
+};
+
+/*
+ * Magic offsets for the application to mmap the data it needs
+ */
+#define IORING_OFF_SQ_RING 0ULL
+#define IORING_OFF_CQ_RING 0x8000000ULL
+#define IORING_OFF_SQES 0x10000000ULL
+
+/*
+ * Filled with the offset for mmap(2)
+ */
+struct io_sqring_offsets {
+ __u32 head;
+ __u32 tail;
+ __u32 ring_mask;
+ __u32 ring_entries;
+ __u32 flags;
+ __u32 dropped;
+ __u32 array;
+ __u32 resv[3];
+};
+
+struct io_cqring_offsets {
+ __u32 head;
+ __u32 tail;
+ __u32 ring_mask;
+ __u32 ring_entries;
+ __u32 overflow;
+ __u32 cqes;
+ __u32 resv[4];
+};
+
+/*
+ * io_uring_enter(2) flags
+ */
+#define IORING_ENTER_GETEVENTS (1U << 0)
+
+/*
+ * Passed in for io_uring_setup(2). Copied back with updated info on success
+ */
+struct io_uring_params {
+ __u32 sq_entries;
+ __u32 cq_entries;
+ __u32 flags;
+ __u32 resv[7];
+ struct io_sqring_offsets sq_off;
+ struct io_cqring_offsets cq_off;
+};
+
+#endif
diff --git a/init/Kconfig b/init/Kconfig
index 513fa544a134..0cf723867e69 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1403,6 +1403,15 @@ config AIO
by some high performance threaded applications. Disabling
this option saves about 7k.
+config IO_URING
+ bool "Enable IO uring support" if EXPERT
+ select ANON_INODES
+ default y
+ help
+ This option enables support for the io_uring interface, enabling
+ applications to submit and completion IO through submission and
+ completion rings that are shared between the kernel and application.
+
config ADVISE_SYSCALLS
bool "Enable madvise/fadvise syscalls" if EXPERT
default y
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index ab9d0e3c6d50..ee5e523564bb 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -46,6 +46,8 @@ COND_SYSCALL(io_getevents);
COND_SYSCALL(io_pgetevents);
COND_SYSCALL_COMPAT(io_getevents);
COND_SYSCALL_COMPAT(io_pgetevents);
+COND_SYSCALL(io_uring_setup);
+COND_SYSCALL(io_uring_enter);
/* fs/xattr.c */
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 04/18] iomap: wire up the iopoll method
From: Jens Axboe @ 2019-01-30 21:55 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api; +Cc: hch, jmoyer, avi, jannh, Jens Axboe
In-Reply-To: <20190130215540.20871-1-axboe@kernel.dk>
From: Christoph Hellwig <hch@lst.de>
Store the request queue the last bio was submitted to in the iocb
private data in addition to the cookie so that we find the right block
device. Also refactor the common direct I/O bio submission code into a
nice little helper.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Modified to use bio_set_polled().
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/gfs2/file.c | 2 ++
fs/iomap.c | 43 ++++++++++++++++++++++++++++---------------
fs/xfs/xfs_file.c | 1 +
include/linux/iomap.h | 1 +
4 files changed, 32 insertions(+), 15 deletions(-)
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index a2dea5bc0427..58a768e59712 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1280,6 +1280,7 @@ const struct file_operations gfs2_file_fops = {
.llseek = gfs2_llseek,
.read_iter = gfs2_file_read_iter,
.write_iter = gfs2_file_write_iter,
+ .iopoll = iomap_dio_iopoll,
.unlocked_ioctl = gfs2_ioctl,
.mmap = gfs2_mmap,
.open = gfs2_open,
@@ -1310,6 +1311,7 @@ const struct file_operations gfs2_file_fops_nolock = {
.llseek = gfs2_llseek,
.read_iter = gfs2_file_read_iter,
.write_iter = gfs2_file_write_iter,
+ .iopoll = iomap_dio_iopoll,
.unlocked_ioctl = gfs2_ioctl,
.mmap = gfs2_mmap,
.open = gfs2_open,
diff --git a/fs/iomap.c b/fs/iomap.c
index a3088fae567b..4ee50b76b4a1 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1454,6 +1454,28 @@ struct iomap_dio {
};
};
+int iomap_dio_iopoll(struct kiocb *kiocb, bool spin)
+{
+ struct request_queue *q = READ_ONCE(kiocb->private);
+
+ if (!q)
+ return 0;
+ return blk_poll(q, READ_ONCE(kiocb->ki_cookie), spin);
+}
+EXPORT_SYMBOL_GPL(iomap_dio_iopoll);
+
+static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
+ struct bio *bio)
+{
+ atomic_inc(&dio->ref);
+
+ if (dio->iocb->ki_flags & IOCB_HIPRI)
+ bio_set_polled(bio, dio->iocb);
+
+ dio->submit.last_queue = bdev_get_queue(iomap->bdev);
+ dio->submit.cookie = submit_bio(bio);
+}
+
static ssize_t iomap_dio_complete(struct iomap_dio *dio)
{
struct kiocb *iocb = dio->iocb;
@@ -1566,7 +1588,7 @@ static void iomap_dio_bio_end_io(struct bio *bio)
}
}
-static blk_qc_t
+static void
iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
unsigned len)
{
@@ -1580,15 +1602,10 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
bio->bi_private = dio;
bio->bi_end_io = iomap_dio_bio_end_io;
- if (dio->iocb->ki_flags & IOCB_HIPRI)
- flags |= REQ_HIPRI;
-
get_page(page);
__bio_add_page(bio, page, len, 0);
bio_set_op_attrs(bio, REQ_OP_WRITE, flags);
-
- atomic_inc(&dio->ref);
- return submit_bio(bio);
+ iomap_dio_submit_bio(dio, iomap, bio);
}
static loff_t
@@ -1691,9 +1708,6 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
bio_set_pages_dirty(bio);
}
- if (dio->iocb->ki_flags & IOCB_HIPRI)
- bio->bi_opf |= REQ_HIPRI;
-
iov_iter_advance(dio->submit.iter, n);
dio->size += n;
@@ -1701,11 +1715,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
copied += n;
nr_pages = iov_iter_npages(&iter, BIO_MAX_PAGES);
-
- atomic_inc(&dio->ref);
-
- dio->submit.last_queue = bdev_get_queue(iomap->bdev);
- dio->submit.cookie = submit_bio(bio);
+ iomap_dio_submit_bio(dio, iomap, bio);
} while (nr_pages);
/*
@@ -1916,6 +1926,9 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (dio->flags & IOMAP_DIO_WRITE_FUA)
dio->flags &= ~IOMAP_DIO_NEED_SYNC;
+ WRITE_ONCE(iocb->ki_cookie, dio->submit.cookie);
+ WRITE_ONCE(iocb->private, dio->submit.last_queue);
+
if (!atomic_dec_and_test(&dio->ref)) {
if (!dio->wait_for_completion)
return -EIOCBQUEUED;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index e47425071e65..60c2da41f0fc 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1203,6 +1203,7 @@ const struct file_operations xfs_file_operations = {
.write_iter = xfs_file_write_iter,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
+ .iopoll = iomap_dio_iopoll,
.unlocked_ioctl = xfs_file_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = xfs_file_compat_ioctl,
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 9a4258154b25..0fefb5455bda 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -162,6 +162,7 @@ typedef int (iomap_dio_end_io_t)(struct kiocb *iocb, ssize_t ret,
unsigned flags);
ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
const struct iomap_ops *ops, iomap_dio_end_io_t end_io);
+int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
#ifdef CONFIG_SWAP
struct file;
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 03/18] block: add bio_set_polled() helper
From: Jens Axboe @ 2019-01-30 21:55 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api; +Cc: hch, jmoyer, avi, jannh, Jens Axboe
In-Reply-To: <20190130215540.20871-1-axboe@kernel.dk>
For the upcoming async polled IO, we can't sleep allocating requests.
If we do, then we introduce a deadlock where the submitter already
has async polled IO in-flight, but can't wait for them to complete
since polled requests must be active found and reaped.
Utilize the helper in the blockdev DIRECT_IO code.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/block_dev.c | 4 ++--
include/linux/bio.h | 14 ++++++++++++++
2 files changed, 16 insertions(+), 2 deletions(-)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index f18d076a2596..392e2bfb636f 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -247,7 +247,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
task_io_account_write(ret);
}
if (iocb->ki_flags & IOCB_HIPRI)
- bio.bi_opf |= REQ_HIPRI;
+ bio_set_polled(&bio, iocb);
qc = submit_bio(&bio);
for (;;) {
@@ -415,7 +415,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES);
if (!nr_pages) {
if (iocb->ki_flags & IOCB_HIPRI)
- bio->bi_opf |= REQ_HIPRI;
+ bio_set_polled(bio, iocb);
qc = submit_bio(bio);
WRITE_ONCE(iocb->ki_cookie, qc);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 7380b094dcca..f6f0a2b3cbc8 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -823,5 +823,19 @@ static inline int bio_integrity_add_page(struct bio *bio, struct page *page,
#endif /* CONFIG_BLK_DEV_INTEGRITY */
+/*
+ * Mark a bio as polled. Note that for async polled IO, the caller must
+ * expect -EWOULDBLOCK if we cannot allocate a request (or other resources).
+ * We cannot block waiting for requests on polled IO, as those completions
+ * must be found by the caller. This is different than IRQ driven IO, where
+ * it's safe to wait for IO to complete.
+ */
+static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
+{
+ bio->bi_opf |= REQ_HIPRI;
+ if (!is_sync_kiocb(kiocb))
+ bio->bi_opf |= REQ_NOWAIT;
+}
+
#endif /* CONFIG_BLOCK */
#endif /* __LINUX_BIO_H */
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 02/18] block: wire up block device iopoll method
From: Jens Axboe @ 2019-01-30 21:55 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api; +Cc: hch, jmoyer, avi, jannh, Jens Axboe
In-Reply-To: <20190130215540.20871-1-axboe@kernel.dk>
From: Christoph Hellwig <hch@lst.de>
Just call blk_poll on the iocb cookie, we can derive the block device
from the inode trivially.
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/block_dev.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 58a4c1217fa8..f18d076a2596 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -293,6 +293,14 @@ struct blkdev_dio {
static struct bio_set blkdev_dio_pool;
+static int blkdev_iopoll(struct kiocb *kiocb, bool wait)
+{
+ struct block_device *bdev = I_BDEV(kiocb->ki_filp->f_mapping->host);
+ struct request_queue *q = bdev_get_queue(bdev);
+
+ return blk_poll(q, READ_ONCE(kiocb->ki_cookie), wait);
+}
+
static void blkdev_bio_end_io(struct bio *bio)
{
struct blkdev_dio *dio = bio->bi_private;
@@ -410,6 +418,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
bio->bi_opf |= REQ_HIPRI;
qc = submit_bio(bio);
+ WRITE_ONCE(iocb->ki_cookie, qc);
break;
}
@@ -2076,6 +2085,7 @@ const struct file_operations def_blk_fops = {
.llseek = block_llseek,
.read_iter = blkdev_read_iter,
.write_iter = blkdev_write_iter,
+ .iopoll = blkdev_iopoll,
.mmap = generic_file_mmap,
.fsync = blkdev_fsync,
.unlocked_ioctl = block_ioctl,
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 01/18] fs: add an iopoll method to struct file_operations
From: Jens Axboe @ 2019-01-30 21:55 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api; +Cc: hch, jmoyer, avi, jannh, Jens Axboe
In-Reply-To: <20190130215540.20871-1-axboe@kernel.dk>
From: Christoph Hellwig <hch@lst.de>
This new methods is used to explicitly poll for I/O completion for an
iocb. It must be called for any iocb submitted asynchronously (that
is with a non-null ki_complete) which has the IOCB_HIPRI flag set.
The method is assisted by a new ki_cookie field in struct iocb to store
the polling cookie.
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
Documentation/filesystems/vfs.txt | 3 +++
include/linux/fs.h | 2 ++
2 files changed, 5 insertions(+)
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 8dc8e9c2913f..761c6fd24a53 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -857,6 +857,7 @@ struct file_operations {
ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
+ int (*iopoll)(struct kiocb *kiocb, bool spin);
int (*iterate) (struct file *, struct dir_context *);
int (*iterate_shared) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
@@ -902,6 +903,8 @@ otherwise noted.
write_iter: possibly asynchronous write with iov_iter as source
+ iopoll: called when aio wants to poll for completions on HIPRI iocbs
+
iterate: called when the VFS needs to read the directory contents
iterate_shared: called when the VFS needs to read the directory contents
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 811c77743dad..ccb0b7a63aa5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -310,6 +310,7 @@ struct kiocb {
int ki_flags;
u16 ki_hint;
u16 ki_ioprio; /* See linux/ioprio.h */
+ unsigned int ki_cookie; /* for ->iopoll */
} __randomize_layout;
static inline bool is_sync_kiocb(struct kiocb *kiocb)
@@ -1786,6 +1787,7 @@ struct file_operations {
ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
+ int (*iopoll)(struct kiocb *kiocb, bool spin);
int (*iterate) (struct file *, struct dir_context *);
int (*iterate_shared) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCHSET v10] io_uring IO interface
From: Jens Axboe @ 2019-01-30 21:55 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api; +Cc: hch, jmoyer, avi, jannh
Keeping the review train hot, this has all review comments addressed
from v9, with a few other fixes on top.
Outside of review comments, this fixes a few annoyances with the
SQPOLL thread. We now shut it down quick, regardless of idle setting,
and I got rid of the silly need to park it for exit.
Also fixed a case with SQPOLL where we'd get -EAGAIN due to request
shortage in the block layer, and we didn't handle that properly. Now
we do.
The liburing git repo now has a io_uring_setup(2) man page, but
otherwise no changes. You can clone that here:
git://git.kernel.dk/liburing
Patches are against 5.0-rc4, and can also be found in my io_uring branch
here:
git://git.kernel.dk/linux-block io_uring
Since v9:
- Use FOLL_ANON instead of checking vmas for file backing
- Fix bad nospec index limiter
- Address various minor review comments
- Fix drop extra file reference in case of submission error
- Fix race with sqe->opcode and "needs mm" checks without sqe copy
- Un-unionize io_kiocb->submit, from the async path it's almost
impossible to do this safely.
- Clear io_kiocb->error for polled IO
- Fix EAGAIN for polled IO and SQPOLL for the !force_nonblock case of
running out of block requests
- Remove need for kthread parking
- Ensure sqo thread exits as quickly as possible
Documentation/filesystems/vfs.txt | 3 +
arch/x86/entry/syscalls/syscall_32.tbl | 3 +
arch/x86/entry/syscalls/syscall_64.tbl | 3 +
block/bio.c | 59 +-
fs/Makefile | 1 +
fs/block_dev.c | 19 +-
fs/file.c | 15 +-
fs/file_table.c | 9 +-
fs/gfs2/file.c | 2 +
fs/io_uring.c | 2611 ++++++++++++++++++++++++
fs/iomap.c | 48 +-
fs/xfs/xfs_file.c | 1 +
include/linux/bio.h | 14 +
include/linux/blk_types.h | 1 +
include/linux/file.h | 2 +
include/linux/fs.h | 6 +-
include/linux/iomap.h | 1 +
include/linux/sched/user.h | 2 +-
include/linux/syscalls.h | 8 +
include/uapi/asm-generic/unistd.h | 8 +-
include/uapi/linux/io_uring.h | 141 ++
init/Kconfig | 9 +
kernel/sys_ni.c | 3 +
23 files changed, 2928 insertions(+), 41 deletions(-)
--
Jens Axboe
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply
* Re: [RFC PATCH glibc 1/4] glibc: Perform rseq(2) registration at C startup and thread creation (v6)
From: Joseph Myers @ 2019-01-30 21:10 UTC (permalink / raw)
To: Mathieu Desnoyers
Cc: carlos, Florian Weimer, Szabolcs Nagy, libc-alpha,
Thomas Gleixner, Ben Maurer, Peter Zijlstra, Paul E. McKenney,
Boqun Feng, Will Deacon, Dave Watson, Paul Turner, Rich Felker,
linux-kernel, linux-api
In-Reply-To: <1832200535.4162.1548871426959.JavaMail.zimbra@efficios.com>
On Wed, 30 Jan 2019, Mathieu Desnoyers wrote:
> #if defined (__NR_rseq) && !defined (RSEQ_SIG)
> # error "UAPI headers support rseq system call, but glibc does not define RSEQ_SIG."
> #endif
>
> Would that take care of your concerns ?
That would of course need appropriate conditionals based on the most
recent kernel version for which a given glibc version has been updated, so
that using new kernel headers with an existing glibc release does not make
the build fail (cf. the test of syscall-names.list). And being able to
write such a test only solves one half of the problem - it needs to be
easy to determine what value to put in that header in glibc for an
architecture that's newly gained support in the kernel, *without* needing
any architecture expertise.
--
Joseph S. Myers
joseph@codesourcery.com
^ permalink raw reply
* Re: [RFC PATCH glibc 1/4] glibc: Perform rseq(2) registration at C startup and thread creation (v6)
From: Mathieu Desnoyers @ 2019-01-30 18:03 UTC (permalink / raw)
To: Joseph Myers
Cc: carlos, Florian Weimer, Szabolcs Nagy, libc-alpha,
Thomas Gleixner, Ben Maurer, Peter Zijlstra, Paul E. McKenney,
Boqun Feng, Will Deacon, Dave Watson, Paul Turner, Rich Felker,
linux-kernel, linux-api
In-Reply-To: <alpine.DEB.2.21.1901300231210.24454@digraph.polyomino.org.uk>
----- On Jan 29, 2019, at 9:40 PM, Joseph Myers joseph@codesourcery.com wrote:
> On Tue, 29 Jan 2019, Mathieu Desnoyers wrote:
>
>> My thinking was to put the #error in the generic header, so architectures that
>> are not supported yet cannot build against rseq.h at all, so we don't end up
>> in a broken upgrade scenario. I'm open to alternative ways to do it though, as
>> long as we don't let not-yet-supported architectures build broken code.
>
> Any case with #error in installed glibc headers needs special-casing in
> check-installed-headers.sh (and, thus, such errors are to be discouraged).
One alternative to #error would be to have an empty generic bits/rseq.h
that does _not_ define RSEQ_SIG. This way, it would be possible to
include sys/rseq.h from an architecture that does not define RSEQ_SIG
yet, but it would not cause any build failure. It's only if the code
try to use RSEQ_SIG that it would fail to compile because undefined.
> Cases where architectures commonly need their own bits/ headers,
> especially where those are likely to need updating for new kernel
> versions, are also discouraged.
The per-arch bits/rseq.h headers, once they define a specific value for
RSEQ_SIG, should never ever change that value.
> Furthermore, a normal check for glibc
> headers updates needed for a new kernel version would only involve
> examining uapi headers (and the non-uapi linux/socket.h for new address
> families, an unfortunate existing wart in this area). As far as I can
> see, this value isn't defined in any uapi header, which makes it
> especially likely to be missed in such a check. Furthermore, I'm hoping
> to add more glibc tests for consistency of such constants between glibc
> and the kernel, to ensure any such updates missing are caught
> automatically through test failures - but that doesn't work if the
> constants in question aren't in a uapi header.
>
> If this constant were in a uapi header, the glibc header could just
> include that - is the issue that it's not actually an interface between
> glibc and the kernel at all, but some kind of purely-userspace interface?
The rseq uapi headers do not enforce the value of RSEQ_SIG. The role of the
kernel wrt signature is to receive it as sys_rseq argument, and then validate
that abort targets are prefixed with the signature before moving the
instruction pointer there.
Therefore, it's up to user-space to agree on the RSEQ_SIG value across
all code using rseq within a process. Since glibc will be registering
rseq and exposing public headers, it appears that glibc would be the
appropriate project to define the RSEQ_SIG value for each architecture.
>
> We very definitely wish to keep to a minimum the cases where updates need
> to be done separately in glibc by each architecture maintainer (that's
> just a recipe for some updates getting missed accidentally) - meaning that
> there needs to be a clear way in which someone can tell, globally for all
> architectures, whether the set of such architecture-specific headers for
> this constant in glibc is complete and current, and when it needs updating
> (and this should be as similar to possible to such checks for any other
> header constant).
Currently, I use #ifdef __NR_rseq from uapi unistd.h to check whether the
kernel headers implement the rseq system call for the target architecture.
With the approach of having an empty bits/rseq.h for architecture not yet
supporting rseq in glibc, one way to check that glibc implements RSEQ_SIG
for all architectures that have the rseq system call wired up in uapi would
be:
#include <unistd.h>
#include <sys/rseq.h>
#if defined (__NR_rseq) && !defined (RSEQ_SIG)
# error "UAPI headers support rseq system call, but glibc does not define RSEQ_SIG."
#endif
Would that take care of your concerns ?
Thanks,
Mathieu
--
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com
^ permalink raw reply
* Re: [RFD] A mount api that notices previous mounts
From: Karel Zak @ 2019-01-30 18:00 UTC (permalink / raw)
To: Eric W. Biederman
Cc: David Howells, linux-api, linux-fsdevel, linux-kernel, Al Viro,
Miklos Szeredi, Linus Torvalds, util-linux, Andy Lutomirski
In-Reply-To: <87h8dqs1xw.fsf@xmission.com>
On Wed, Jan 30, 2019 at 07:35:39AM -0600, Eric W. Biederman wrote:
> I suspect that as long as userspace supports /etc/fstab and we in turn
> support /proc/mounts there is going to be a lot of pressure to keep
> the majority of options so they can be encoded in a string separated by
> commas.
Well, we're doing many crazy things in userspace ;-) For example we do
not distinguish between VFS flags (MS_*), FS specific mount options
and userspace mount options (loop=) in our config files.
You already need to parse fstab/command line before you can use the
strings for mount(2) syscall. It's already not straightforward, see
all the code in libmount...
/proc/mounts is only for backward compatibility, /proc/self/mountinfo
is better way, because it allows to see VFS and FS, etc.
IMHO it would be better to not care about way how we use mount options
strings now (in userspace) when you think about the new API design.
Karel
--
Karel Zak <kzak@redhat.com>
http://karelzak.blogspot.com
^ permalink raw reply
* Re: [RFD] A mount api that notices previous mounts
From: Karel Zak @ 2019-01-30 17:43 UTC (permalink / raw)
To: David Howells
Cc: Eric W. Biederman, linux-api, linux-fsdevel, linux-kernel,
Al Viro, Miklos Szeredi, Linus Torvalds, util-linux,
Andy Lutomirski
In-Reply-To: <9871.1548853314@warthog.procyon.org.uk>
On Wed, Jan 30, 2019 at 01:01:54PM +0000, David Howells wrote:
> Karel Zak <kzak@redhat.com> wrote:
>
> > It seems more elegant is to ask for Nth option as expected by fsinfo().
>
> More elegant yes, but there's an issue with atomiticity[*]. I'm in the
> process of switching to something that returns you a single buffer with all
> the options in, but each key and each value is preceded by a length count.
Sounds good, for me is important to avoid all the split/join
operations with the strings.
> The reasons for not using separator characters are:
>
> (1) There's no separator char that cannot validly occur within an option[**].
Yes, it's pretty common for selinux mount options where "," is
used within an option, so mount options string looks like
'context="system_u:object_r:tmp_t:s0:c127,c456",noexec'
and I have doubts all the parses in userspace are compatible with this
use case...
> (2) Makes it possible to return binary values if we need to.
Yes.
> [**] Oh, and look at cifs where you can *change* the separator char during
> option parsing ("sep=<char>").
No comment :-)
Karel
--
Karel Zak <kzak@redhat.com>
http://karelzak.blogspot.com
^ permalink raw reply
* Re: [RFD] A mount api that notices previous mounts
From: Casey Schaufler @ 2019-01-30 16:19 UTC (permalink / raw)
To: Eric W. Biederman
Cc: linux-api-u79uwXL29TY76Z2rM5mHXA,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, Al Viro, David Howells,
Miklos Szeredi, Linus Torvalds, Karel Zak,
util-linux-u79uwXL29TY76Z2rM5mHXA, Andy Lutomirski, LSM,
SMACK-discuss-hn68Rpc1hR1g9hUCZPvPmw@public.gmane.org
In-Reply-To: <8736pawbw2.fsf-aS9lmoZGLiVWk0Htik3J/w@public.gmane.org>
On 1/30/2019 4:47 AM, Eric W. Biederman wrote:
> ebiederm-aS9lmoZGLiVWk0Htik3J/w@public.gmane.org (Eric W. Biederman) writes:
>
>> ebiederm-aS9lmoZGLiVWk0Htik3J/w@public.gmane.org (Eric W. Biederman) writes:
>>
>>> Casey Schaufler <casey-iSGtlc1asvQWG2LlvL+J4A@public.gmane.org> writes:
>>>> Are you taking the LSM specific mount options into account?
>>> In the design yes, and I allow setting them. It appears in the code
>>> to retrieve the mount options I forgot to call security_sb_show_options.
>>>
>>> For finding the super block that you are going to mount the LSM mount
>>> options are not relevant. Even nfs will not want to set those early as
>>> they do not help determine the nfs super block. So the only place where
>>> there is anything interesting in my api is in reading back the security
>>> options so they can be compared to the options the mounter is setting.
>>>
>>> I will add the missing call to security_sb_show_options which is enough
>>> to fix selinux. Unfortunately smack does not currently implement
>>> .sb_show_options. Not implementing smack_sb_show_options means
>>> /proc/mounts fails to match /etc/mtab which is a bug and it is likely
>>> a real workd bug for the people who use smack and don't want to depend
>>> on /etc/mtab, or are transitioning away from it.
>>>
>>> Casey do you want to implement smack_sb_show_options or should I put it
>>> on my todo list?
>> Oh. I should add that I am always parsing the LSM mount options out so
>> that there is not a chance of the individual filesystems implementing
>> comflicting options even when there are no LSMs active. Without that I
>> am afraid we run the risk of having LSM mount otions in conflict with
>> ordinary filesystems options at some point and by the time we discover
>> it it would start introducing filesystem regressions.
>>
>> That does help with stack though as there is no fundamental reason only
>> one LSM could process mount options.
> Sigh. I just realized that there is a smack variant of the bug I am
> working to fix.
>
> smack on remount does not fail if you change the smack mount options.
> It just silently ignores the smack mount options. Which is exactly the
> same poor interaction with userspace that has surprised user space
> and caused CVEs.
>
> How much do you think the smack users will care if you start verifying
> that if smack options are present in remount that they are unchanged
> from mount?
I've added the smack-discuss list to the conversation.
> I suspect the smack userbase is small enough, and the corner case is
> crazy enough we can fix this poor communication by smack. Otherwise it
> looks like there needs to be a new security hook so old and new remounts
> can be distinguished by the LSMs, and smack can be fixed in the new
> version.
I fear that it may be worse than that. It's not enough to distinguish
a mount from a remount. On remount you need an LSM specific way to
compare mount options. Smack may decide that it's OK to remount a
filesystem with more restrictive smackfshat values, for example. Or,
it may allow smackfsroot=Pop for one and smackfstransmute=Pop on
the other. I'm not sure about the 2nd case, but you should get the idea.
>
> Eric
>
>
^ permalink raw reply
* Re: [PATCH 13/18] io_uring: add file set registration
From: Jens Axboe @ 2019-01-30 15:35 UTC (permalink / raw)
To: Jann Horn
Cc: linux-aio, linux-block, Linux API, hch, jmoyer, avi, Al Viro,
linux-fsdevel
In-Reply-To: <CAG48ez2kLWUEambWesQQaeVn_u=PtjuMeDUc49yamhYspfd7Sg@mail.gmail.com>
On 1/29/19 6:29 PM, Jann Horn wrote:
> On Tue, Jan 29, 2019 at 8:27 PM Jens Axboe <axboe@kernel.dk> wrote:
>> We normally have to fget/fput for each IO we do on a file. Even with
>> the batching we do, the cost of the atomic inc/dec of the file usage
>> count adds up.
>>
>> This adds IORING_REGISTER_FILES, and IORING_UNREGISTER_FILES opcodes
>> for the io_uring_register(2) system call. The arguments passed in must
>> be an array of __s32 holding file descriptors, and nr_args should hold
>> the number of file descriptors the application wishes to pin for the
>> duration of the io_uring context (or until IORING_UNREGISTER_FILES is
>> called).
>>
>> When used, the application must set IOSQE_FIXED_FILE in the sqe->flags
>> member. Then, instead of setting sqe->fd to the real fd, it sets sqe->fd
>> to the index in the array passed in to IORING_REGISTER_FILES.
>>
>> Files are automatically unregistered when the io_uring context is
>> torn down. An application need only unregister if it wishes to
>> register a new set of fds.
>
> Crazy idea:
>
> Taking a step back, at a high level, basically this patch creates sort
> of the same difference that you get when you compare the following
> scenarios for normal multithreaded I/O in userspace:
>
> ===========================================================
> ~/tests/fdget_perf$ cat fdget_perf.c
> #define _GNU_SOURCE
> #include <sys/wait.h>
> #include <sched.h>
> #include <unistd.h>
> #include <stdbool.h>
> #include <string.h>
> #include <err.h>
> #include <signal.h>
> #include <sys/eventfd.h>
> #include <stdio.h>
>
> // two different physical processors on my machine
> #define CORE_A 0
> #define CORE_B 14
>
> static void pin_to_core(int coreid) {
> cpu_set_t set;
> CPU_ZERO(&set);
> CPU_SET(coreid, &set);
> if (sched_setaffinity(0, sizeof(cpu_set_t), &set))
> err(1, "sched_setaffinity");
> }
>
> static int fd = -1;
>
> static volatile int time_over = 0;
> static void alarm_handler(int sig) { time_over = 1; }
> static void run_stuff(void) {
> unsigned long long iterations = 0;
> if (signal(SIGALRM, alarm_handler) == SIG_ERR) err(1, "signal");
> alarm(10);
> while (1) {
> uint64_t val;
> read(fd, &val, sizeof(val));
> if (time_over) {
> printf("iterations = 0x%llx\n", iterations);
> return;
> }
> iterations++;
> }
> }
>
> static int child_fn(void *dummy) {
> pin_to_core(CORE_B);
> run_stuff();
> return 0;
> }
>
> static char child_stack[1024*1024];
>
> int main(int argc, char **argv) {
> fd = eventfd(0, EFD_NONBLOCK);
> if (fd == -1) err(1, "eventfd");
>
> if (argc != 2) errx(1, "bad usage");
> int flags = SIGCHLD;
> if (strcmp(argv[1], "shared") == 0) {
> flags |= CLONE_FILES;
> } else if (strcmp(argv[1], "cloned") == 0) {
> /* nothing */
> } else {
> errx(1, "bad usage");
> }
> pid_t child = clone(child_fn, child_stack+sizeof(child_stack), flags, NULL);
> if (child == -1) err(1, "clone");
>
> pin_to_core(CORE_A);
> run_stuff();
> int status;
> if (wait(&status) != child) err(1, "wait");
> return 0;
> }
> ~/tests/fdget_perf$ gcc -Wall -o fdget_perf fdget_perf.c
> ~/tests/fdget_perf$ ./fdget_perf shared
> iterations = 0x8d3010
> iterations = 0x92d894
> ~/tests/fdget_perf$ ./fdget_perf cloned
> iterations = 0xad3bbd
> iterations = 0xb08838
> ~/tests/fdget_perf$ ./fdget_perf shared
> iterations = 0x8cc340
> iterations = 0x8e4e64
> ~/tests/fdget_perf$ ./fdget_perf cloned
> iterations = 0xada5f3
> iterations = 0xb04b6f
> ===========================================================
>
> This kinda makes me wonder whether this is really something that
> should be implemented specifically for the io_uring API, or whether it
> would make sense to somehow handle part of this in the generic VFS
> code and give the user the ability to prepare a new files_struct that
> can then be transferred to the worker thread, or something like
> that... I'm not sure whether there's a particularly clean way to do
> that though.
>
> Or perhaps you could add a userspace API for marking file descriptor
> table entries as "has percpu refcounting" somehow, with one percpu
> refcount per files_struct and one bit per fd, allocated when percpu
> refcounting is activated for the files_struct the first time, or
> something like that...
There's undoubtedly a win by NOT sharing, obviously. Not sure how to do
this in a generalized fashion, cleanly, it's easier (and a better fit)
to do it for specific cases, like io_uring here. If others want to go
down that path, io_uring could always be adapted to use that
infrastructure.
--
Jens Axboe
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply
* Re: [PATCH 09/18] io_uring: use fget/fput_many() for file references
From: Jens Axboe @ 2019-01-30 15:33 UTC (permalink / raw)
To: Jann Horn; +Cc: linux-aio, linux-block, Linux API, hch, jmoyer, Avi Kivity
In-Reply-To: <bceb5e2b-9634-1296-a2a9-ed521f0e31d4@kernel.dk>
On 1/29/19 4:44 PM, Jens Axboe wrote:
> On 1/29/19 4:31 PM, Jann Horn wrote:
>> On Tue, Jan 29, 2019 at 8:27 PM Jens Axboe <axboe@kernel.dk> wrote:
>>> Add a separate io_submit_state structure, to cache some of the things
>>> we need for IO submission.
>>>
>>> One such example is file reference batching. io_submit_state. We get as
>>> many references as the number of sqes we are submitting, and drop
>>> unused ones if we end up switching files. The assumption here is that
>>> we're usually only dealing with one fd, and if there are multiple,
>>> hopefuly they are at least somewhat ordered. Could trivially be extended
>>> to cover multiple fds, if needed.
>>>
>>> On the completion side we do the same thing, except this is trivially
>>> done just locally in io_iopoll_reap().
>> [...]
>>> +static void io_file_put(struct io_submit_state *state, struct file *file)
>>> +{
>>> + if (!state) {
>>> + fput(file);
>>> + } else if (state->file) {
>>> + int diff = state->has_refs - state->used_refs;
>>> +
>>> + if (diff)
>>> + fput_many(state->file, diff);
>>> + state->file = NULL;
>>> + }
>>> +}
>>
>> Hmm, this function confuses me.
>> The state==NULL path works as I'd expect, it calls fput() on the file.
>> But if `state!=NULL && state->file==NULL`, it does nothing, it never
>> uses `file`.
>> And if `state->file!=NULL`, it drops the excess bias on the file's
>> refcount, but it doesn't drop the current reference - and again
>> without even looking at `file`.
>>
>> So when io_prep_rw() uses io_file_get() to grab a reference on a file
>> it hasn't seen before, it will acquire `ios_left` references and
>> actually use one of them; then if it goes through the out_fput error
>> path, it goes through the path for `state->file!=NULL`, drops
>> `ios_left-1` references (leaving the refcount elevated by 1), and
>> forgets about the file?
>
> I'll take a look, it's not impossible there's an off-by-one there.
Fixed it!
--
Jens Axboe
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply
* Re: [PATCH 2/3] mm/filemap: initiate readahead even if IOCB_NOWAIT is set for the I/O
From: Jiri Kosina @ 2019-01-30 15:15 UTC (permalink / raw)
To: Florian Weimer
Cc: Vlastimil Babka, Andrew Morton, Linus Torvalds, linux-kernel,
linux-mm, linux-api, Peter Zijlstra, Greg KH, Jann Horn,
Dominique Martinet, Andy Lutomirski, Dave Chinner, Kevin Easton,
Matthew Wilcox, Cyril Hrubis, Tejun Heo, Kirill A . Shutemov,
Daniel Gruss
In-Reply-To: <87munii3uj.fsf@oldenburg2.str.redhat.com>
On Wed, 30 Jan 2019, Florian Weimer wrote:
> > preadv2(RWF_NOWAIT) can be used to open a side-channel to pagecache
> > contents, as it reveals metadata about residency of pages in
> > pagecache.
> >
> > If preadv2(RWF_NOWAIT) returns immediately, it provides a clear "page
> > not resident" information, and vice versa.
> >
> > Close that sidechannel by always initiating readahead on the cache if
> > we encounter a cache miss for preadv2(RWF_NOWAIT); with that in place,
> > probing the pagecache residency itself will actually populate the
> > cache, making the sidechannel useless.
>
> I think this needs to use a different flag because the semantics are so
> much different. If I understand this change correctly, previously,
> RWF_NOWAIT essentially avoided any I/O, and now it does not.
It still avoid synchronous I/O, due to this code still being in place:
if (!PageUptodate(page)) {
if (iocb->ki_flags & IOCB_NOWAIT) {
put_page(page);
goto would_block;
}
but goes the would_block path only after initiating asynchronous
readahead.
--
Jiri Kosina
SUSE Labs
^ permalink raw reply
* Re: [PATCH 2/3] mm/filemap: initiate readahead even if IOCB_NOWAIT is set for the I/O
From: Florian Weimer @ 2019-01-30 15:04 UTC (permalink / raw)
To: Vlastimil Babka
Cc: Andrew Morton, Linus Torvalds, linux-kernel, linux-mm, linux-api,
Peter Zijlstra, Greg KH, Jann Horn, Jiri Kosina,
Dominique Martinet, Andy Lutomirski, Dave Chinner, Kevin Easton,
Matthew Wilcox, Cyril Hrubis, Tejun Heo, Kirill A . Shutemov,
Daniel Gruss, Jiri Kosina
In-Reply-To: <20190130124420.1834-3-vbabka@suse.cz>
* Vlastimil Babka:
> preadv2(RWF_NOWAIT) can be used to open a side-channel to pagecache
> contents, as it reveals metadata about residency of pages in
> pagecache.
>
> If preadv2(RWF_NOWAIT) returns immediately, it provides a clear "page
> not resident" information, and vice versa.
>
> Close that sidechannel by always initiating readahead on the cache if
> we encounter a cache miss for preadv2(RWF_NOWAIT); with that in place,
> probing the pagecache residency itself will actually populate the
> cache, making the sidechannel useless.
I think this needs to use a different flag because the semantics are so
much different. If I understand this change correctly, previously,
RWF_NOWAIT essentially avoided any I/O, and now it does not.
Thanks,
Florian
^ permalink raw reply
* Re: [RFD] A mount api that notices previous mounts
From: Eric W. Biederman @ 2019-01-30 13:45 UTC (permalink / raw)
To: Karel Zak
Cc: linux-api, linux-fsdevel, linux-kernel, Al Viro, David Howells,
Miklos Szeredi, Linus Torvalds, util-linux, Andy Lutomirski
In-Reply-To: <20190130120654.q5zqcexquca7u337@ws.net.home>
Karel Zak <kzak@redhat.com> writes:
> On Tue, Jan 29, 2019 at 03:44:22PM -0600, Eric W. Biederman wrote:
>> so I am proposing we change this in the new mount api.
>
> Well, this forces me to ask what the new API is? :-)
>
> It seems that David uses fsconfig() and fsinfo() to set and get
> mount options, and your patch introduces fsset() and fsoptions().
>
> IMHO differentiate between FS driver and FS instance is a good idea it
> makes things more extendable. The sequence number in the instance is a
> good example.
>
> But for me David's fsinfo() seems better that fsoptions() and
> fsspecifier(). I'm not sure about "all mount options as one string"
> From your example is pretty obvious how much energy is necessary to
> split and join the strings.
>
> It seems more elegant is to ask for Nth option as expected by fsinfo().
> It also seems that fsinfo() is able to replace fsname() and fstype().
>
> It would be better to extend David's fsinfo() to work with FS instance
> and to return specifiers. And use fsconfig() rather than fsset().
As David has pointed out with cifs having a sep= option we need a better
story of parsing the options in the kernel.
What my branch does is demonstrate there is at least one way we can
avoid mount options being silently different from what userspace
expects.
Which means my branch is fine for looking at semantics and possible
system calls, but not much else.
I actually used multiple system calls just so I could avoid dealing
with multi-plexor systems calls.
Eric
^ permalink raw reply
* Re: [RFD] A mount api that notices previous mounts
From: Eric W. Biederman @ 2019-01-30 13:35 UTC (permalink / raw)
To: David Howells
Cc: Karel Zak, linux-api-u79uwXL29TY76Z2rM5mHXA,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, Al Viro, Miklos Szeredi,
Linus Torvalds, util-linux-u79uwXL29TY76Z2rM5mHXA,
Andy Lutomirski
In-Reply-To: <9871.1548853314-S6HVgzuS8uM4Awkfq6JHfwNdhmdF6hFW@public.gmane.org>
David Howells <dhowells-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> writes:
> Karel Zak <kzak-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> wrote:
>
>> It seems more elegant is to ask for Nth option as expected by fsinfo().
>
> More elegant yes, but there's an issue with atomiticity[*]. I'm in the
> process of switching to something that returns you a single buffer with all
> the options in, but each key and each value is preceded by a length count.
>
> The reasons for not using separator characters are:
>
> (1) There's no separator char that cannot validly occur within an option[**].
*Blink* I had missed the cifs issue. So yes we certainly need
a better way to encode things in the buffer. I just used a single
string as an easy way to place everything in a buffer.
> (2) Makes it possible to return binary values if we need to.
I don't totally disagree with this. But I will point out that
except for coda passing a file descriptor there are no filesystems
that currently take or need binary options.
I suspect that as long as userspace supports /etc/fstab and we in turn
support /proc/mounts there is going to be a lot of pressure to keep
the majority of options so they can be encoded in a string separated by
commas.
> David
>
> [*] Atomic with respect to remount calls, that is.
There are also mount options that depend on each other and whose order
matters with respect to other mount options extN's ("sb=<NNNN>") for
example.
> [**] Oh, and look at cifs where you can *change* the separator char during
> option parsing ("sep=<char>").
^ permalink raw reply
* Re: [RFD] A mount api that notices previous mounts
From: Eric W. Biederman @ 2019-01-30 13:24 UTC (permalink / raw)
To: David Howells
Cc: linux-api-u79uwXL29TY76Z2rM5mHXA,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA, Al Viro, Miklos Szeredi,
Linus Torvalds, Karel Zak, util-linux-u79uwXL29TY76Z2rM5mHXA,
Andy Lutomirski
In-Reply-To: <9151.1548852654-S6HVgzuS8uM4Awkfq6JHfwNdhmdF6hFW@public.gmane.org>
David Howells <dhowells-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> writes:
> You need to rebase on linus/master. A bunch of your patches are obsoleted by
> Al's security changes there.
Before anything is merged definitely.
Al dealt with mount options from the LSMs in a slightly different way
than I did. At a practical level Als version of the changes to the LSMs
and mine are you say po-tae-toe I say po-tah-toe differences so I don't
see that influencing semantics up at the api level.
For purposes of disucssing an API (not of merging one) I chose to start
with code I had a reasonable amount of testing against, so that other
people could play with it without expecting trouble.
Eric
^ permalink raw reply
* Re: [RFD] A mount api that notices previous mounts
From: David Howells @ 2019-01-30 13:01 UTC (permalink / raw)
To: Karel Zak
Cc: dhowells, Eric W. Biederman, linux-api, linux-fsdevel,
linux-kernel, Al Viro, Miklos Szeredi, Linus Torvalds, util-linux,
Andy Lutomirski
In-Reply-To: <20190130120654.q5zqcexquca7u337@ws.net.home>
Karel Zak <kzak@redhat.com> wrote:
> It seems more elegant is to ask for Nth option as expected by fsinfo().
More elegant yes, but there's an issue with atomiticity[*]. I'm in the
process of switching to something that returns you a single buffer with all
the options in, but each key and each value is preceded by a length count.
The reasons for not using separator characters are:
(1) There's no separator char that cannot validly occur within an option[**].
(2) Makes it possible to return binary values if we need to.
David
[*] Atomic with respect to remount calls, that is.
[**] Oh, and look at cifs where you can *change* the separator char during
option parsing ("sep=<char>").
^ permalink raw reply
* Re: [RFD] A mount api that notices previous mounts
From: David Howells @ 2019-01-30 12:50 UTC (permalink / raw)
To: Eric W. Biederman
Cc: dhowells, linux-api, linux-fsdevel, linux-kernel, Al Viro,
Miklos Szeredi, Linus Torvalds, Karel Zak, util-linux,
Andy Lutomirski
In-Reply-To: <87va2716mh.fsf@xmission.com>
You need to rebase on linus/master. A bunch of your patches are obsoleted by
Al's security changes there.
David
^ permalink raw reply
* Re: [RFD] A mount api that notices previous mounts
From: Eric W. Biederman @ 2019-01-30 12:47 UTC (permalink / raw)
To: Casey Schaufler
Cc: linux-api, linux-fsdevel, linux-kernel, Al Viro, David Howells,
Miklos Szeredi, Linus Torvalds, Karel Zak, util-linux,
Andy Lutomirski, LSM
In-Reply-To: <87ef8vx7jz.fsf@xmission.com>
ebiederm@xmission.com (Eric W. Biederman) writes:
> ebiederm@xmission.com (Eric W. Biederman) writes:
>
>> Casey Schaufler <casey@schaufler-ca.com> writes:
>>> Are you taking the LSM specific mount options into account?
>>
>> In the design yes, and I allow setting them. It appears in the code
>> to retrieve the mount options I forgot to call security_sb_show_options.
>>
>> For finding the super block that you are going to mount the LSM mount
>> options are not relevant. Even nfs will not want to set those early as
>> they do not help determine the nfs super block. So the only place where
>> there is anything interesting in my api is in reading back the security
>> options so they can be compared to the options the mounter is setting.
>>
>> I will add the missing call to security_sb_show_options which is enough
>> to fix selinux. Unfortunately smack does not currently implement
>> .sb_show_options. Not implementing smack_sb_show_options means
>> /proc/mounts fails to match /etc/mtab which is a bug and it is likely
>> a real workd bug for the people who use smack and don't want to depend
>> on /etc/mtab, or are transitioning away from it.
>>
>> Casey do you want to implement smack_sb_show_options or should I put it
>> on my todo list?
>
> Oh. I should add that I am always parsing the LSM mount options out so
> that there is not a chance of the individual filesystems implementing
> comflicting options even when there are no LSMs active. Without that I
> am afraid we run the risk of having LSM mount otions in conflict with
> ordinary filesystems options at some point and by the time we discover
> it it would start introducing filesystem regressions.
>
> That does help with stack though as there is no fundamental reason only
> one LSM could process mount options.
Sigh. I just realized that there is a smack variant of the bug I am
working to fix.
smack on remount does not fail if you change the smack mount options.
It just silently ignores the smack mount options. Which is exactly the
same poor interaction with userspace that has surprised user space
and caused CVEs.
How much do you think the smack users will care if you start verifying
that if smack options are present in remount that they are unchanged
from mount?
I suspect the smack userbase is small enough, and the corner case is
crazy enough we can fix this poor communication by smack. Otherwise it
looks like there needs to be a new security hook so old and new remounts
can be distinguished by the LSMs, and smack can be fixed in the new
version.
Eric
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox