* [PATCH 07/32] aio: simplify cancellation
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
With the current aio code there is no need for the magic KIOCB_CANCELLED
value, as a cancelation just kicks the driver to queue the completion
ASAP, with all actual completion handling done in another thread. Given
that both the completion path and cancelation take the context lock there
is no need for magic cmpxchg loops either. If we remove iocbs from the
active list before calling ->ki_cancel we can also rely on the invariant
thay anything found on the list has a ->ki_cancel callback and can be
cancelled, further simplifing the code.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
fs/aio.c | 49 ++++++-------------------------------------------
1 file changed, 6 insertions(+), 43 deletions(-)
diff --git a/fs/aio.c b/fs/aio.c
index 2e0bc04f7920..8991baa38d5d 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -164,19 +164,6 @@ struct fsync_iocb {
bool datasync;
};
-/*
- * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either
- * cancelled or completed (this makes a certain amount of sense because
- * successful cancellation - io_cancel() - does deliver the completion to
- * userspace).
- *
- * And since most things don't implement kiocb cancellation and we'd really like
- * kiocb completion to be lockless when possible, we use ki_cancel to
- * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED
- * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel().
- */
-#define KIOCB_CANCELLED ((void *) (~0ULL))
-
struct aio_kiocb {
union {
struct kiocb rw;
@@ -574,27 +561,6 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
}
EXPORT_SYMBOL(kiocb_set_cancel_fn);
-static int kiocb_cancel(struct aio_kiocb *kiocb)
-{
- kiocb_cancel_fn *old, *cancel;
-
- /*
- * Don't want to set kiocb->ki_cancel = KIOCB_CANCELLED unless it
- * actually has a cancel function, hence the cmpxchg()
- */
-
- cancel = READ_ONCE(kiocb->ki_cancel);
- do {
- if (!cancel || cancel == KIOCB_CANCELLED)
- return -EINVAL;
-
- old = cancel;
- cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED);
- } while (cancel != old);
-
- return cancel(&kiocb->rw);
-}
-
/*
* free_ioctx() should be RCU delayed to synchronize against the RCU
* protected lookup_ioctx() and also needs process context to call
@@ -641,9 +607,8 @@ static void free_ioctx_users(struct percpu_ref *ref)
while (!list_empty(&ctx->active_reqs)) {
req = list_first_entry(&ctx->active_reqs,
struct aio_kiocb, ki_list);
-
list_del_init(&req->ki_list);
- kiocb_cancel(req);
+ req->ki_cancel(&req->rw);
}
spin_unlock_irq(&ctx->ctx_lock);
@@ -1843,8 +1808,8 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
{
struct kioctx *ctx;
struct aio_kiocb *kiocb;
+ int ret = -EINVAL;
u32 key;
- int ret;
if (unlikely(get_user(key, &iocb->aio_key)))
return -EFAULT;
@@ -1856,13 +1821,11 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
return -EINVAL;
spin_lock_irq(&ctx->ctx_lock);
-
kiocb = lookup_kiocb(ctx, iocb);
- if (kiocb)
- ret = kiocb_cancel(kiocb);
- else
- ret = -EINVAL;
-
+ if (kiocb) {
+ list_del_init(&kiocb->ki_list);
+ ret = kiocb->ki_cancel(&kiocb->rw);
+ }
spin_unlock_irq(&ctx->ctx_lock);
if (!ret) {
--
2.17.0
--
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 08/32] aio: replace kiocb_set_cancel_fn with a cancel_kiocb file operation
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
The current kiocb_set_cancel_fn implementation assumes the kiocb is
embedded into an aio_kiocb, which is fundamentally unsafe as it might
have been submitted by non-aio callers. Instead add a cancel_kiocb
file operation that replaced the ki_cancel function pointer set by
kiocb_set_cancel_fn, and only adds iocbs to the active list when
the read/write_iter methods return -EIOCBQUEUED and the file has
a cancel_kiocb method.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/usb/gadget/function/f_fs.c | 10 ++--------
drivers/usb/gadget/legacy/inode.c | 5 ++---
fs/aio.c | 31 ++++++++++++------------------
fs/orangefs/orangefs-kernel.h | 1 -
include/linux/aio.h | 7 -------
include/linux/fs.h | 1 +
6 files changed, 17 insertions(+), 38 deletions(-)
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 0294e4f18873..531a7206407b 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -26,7 +26,6 @@
#include <linux/usb/composite.h>
#include <linux/usb/functionfs.h>
-#include <linux/aio.h>
#include <linux/mmu_context.h>
#include <linux/poll.h>
#include <linux/eventfd.h>
@@ -1072,7 +1071,7 @@ ffs_epfile_open(struct inode *inode, struct file *file)
return 0;
}
-static int ffs_aio_cancel(struct kiocb *kiocb)
+static int ffs_epfile_cancel_kiocb(struct kiocb *kiocb)
{
struct ffs_io_data *io_data = kiocb->private;
struct ffs_epfile *epfile = kiocb->ki_filp->private_data;
@@ -1115,9 +1114,6 @@ static ssize_t ffs_epfile_write_iter(struct kiocb *kiocb, struct iov_iter *from)
kiocb->private = p;
- if (p->aio)
- kiocb_set_cancel_fn(kiocb, ffs_aio_cancel);
-
res = ffs_epfile_io(kiocb->ki_filp, p);
if (res == -EIOCBQUEUED)
return res;
@@ -1160,9 +1156,6 @@ static ssize_t ffs_epfile_read_iter(struct kiocb *kiocb, struct iov_iter *to)
kiocb->private = p;
- if (p->aio)
- kiocb_set_cancel_fn(kiocb, ffs_aio_cancel);
-
res = ffs_epfile_io(kiocb->ki_filp, p);
if (res == -EIOCBQUEUED)
return res;
@@ -1274,6 +1267,7 @@ static const struct file_operations ffs_epfile_operations = {
.read_iter = ffs_epfile_read_iter,
.release = ffs_epfile_release,
.unlocked_ioctl = ffs_epfile_ioctl,
+ .cancel_kiocb = ffs_epfile_cancel_kiocb,
};
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 37ca0e669bd8..02ea83c8861a 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -21,7 +21,6 @@
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/mmu_context.h>
-#include <linux/aio.h>
#include <linux/uio.h>
#include <linux/refcount.h>
#include <linux/delay.h>
@@ -435,7 +434,7 @@ struct kiocb_priv {
unsigned actual;
};
-static int ep_aio_cancel(struct kiocb *iocb)
+static int ep_cancel_kiocb(struct kiocb *iocb)
{
struct kiocb_priv *priv = iocb->private;
struct ep_data *epdata;
@@ -528,7 +527,6 @@ static ssize_t ep_aio(struct kiocb *iocb,
iocb->private = priv;
priv->iocb = iocb;
- kiocb_set_cancel_fn(iocb, ep_aio_cancel);
get_ep(epdata);
priv->epdata = epdata;
priv->actual = 0;
@@ -700,6 +698,7 @@ static const struct file_operations ep_io_operations = {
.unlocked_ioctl = ep_ioctl,
.read_iter = ep_read_iter,
.write_iter = ep_write_iter,
+ .cancel_kiocb = ep_cancel_kiocb,
};
/* ENDPOINT INITIALIZATION
diff --git a/fs/aio.c b/fs/aio.c
index 8991baa38d5d..be10dde20c8e 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -171,7 +171,6 @@ struct aio_kiocb {
};
struct kioctx *ki_ctx;
- kiocb_cancel_fn *ki_cancel;
struct iocb __user *ki_user_iocb; /* user's aiocb */
__u64 ki_user_data; /* user's data for completion */
@@ -545,22 +544,6 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events)
#define AIO_EVENTS_FIRST_PAGE ((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event))
#define AIO_EVENTS_OFFSET (AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE)
-void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
-{
- struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw);
- struct kioctx *ctx = req->ki_ctx;
- unsigned long flags;
-
- if (WARN_ON_ONCE(!list_empty(&req->ki_list)))
- return;
-
- spin_lock_irqsave(&ctx->ctx_lock, flags);
- list_add_tail(&req->ki_list, &ctx->active_reqs);
- req->ki_cancel = cancel;
- spin_unlock_irqrestore(&ctx->ctx_lock, flags);
-}
-EXPORT_SYMBOL(kiocb_set_cancel_fn);
-
/*
* free_ioctx() should be RCU delayed to synchronize against the RCU
* protected lookup_ioctx() and also needs process context to call
@@ -608,7 +591,7 @@ static void free_ioctx_users(struct percpu_ref *ref)
req = list_first_entry(&ctx->active_reqs,
struct aio_kiocb, ki_list);
list_del_init(&req->ki_list);
- req->ki_cancel(&req->rw);
+ req->rw.ki_filp->f_op->cancel_kiocb(&req->rw);
}
spin_unlock_irq(&ctx->ctx_lock);
@@ -1447,6 +1430,16 @@ static inline ssize_t aio_rw_ret(struct kiocb *req, ssize_t ret)
{
switch (ret) {
case -EIOCBQUEUED:
+ if (req->ki_filp->f_op->cancel_kiocb) {
+ struct aio_kiocb *iocb =
+ container_of(req, struct aio_kiocb, rw);
+ struct kioctx *ctx = iocb->ki_ctx;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctx->ctx_lock, flags);
+ list_add_tail(&iocb->ki_list, &ctx->active_reqs);
+ spin_unlock_irqrestore(&ctx->ctx_lock, flags);
+ }
return ret;
case -ERESTARTSYS:
case -ERESTARTNOINTR:
@@ -1824,7 +1817,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
kiocb = lookup_kiocb(ctx, iocb);
if (kiocb) {
list_del_init(&kiocb->ki_list);
- ret = kiocb->ki_cancel(&kiocb->rw);
+ ret = kiocb->rw.ki_filp->f_op->cancel_kiocb(&kiocb->rw);
}
spin_unlock_irq(&ctx->ctx_lock);
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index c29bb0ebc6bb..5cd598c59bdc 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -34,7 +34,6 @@
#include <linux/fs.h>
#include <linux/vmalloc.h>
-#include <linux/aio.h>
#include <linux/posix_acl.h>
#include <linux/posix_acl_xattr.h>
#include <linux/compat.h>
diff --git a/include/linux/aio.h b/include/linux/aio.h
index b83e68dd006f..42e3cc953005 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -4,20 +4,13 @@
#include <linux/aio_abi.h>
-struct kioctx;
-struct kiocb;
struct mm_struct;
-typedef int (kiocb_cancel_fn)(struct kiocb *);
-
/* prototypes */
#ifdef CONFIG_AIO
extern void exit_aio(struct mm_struct *mm);
-void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel);
#else
static inline void exit_aio(struct mm_struct *mm) { }
-static inline void kiocb_set_cancel_fn(struct kiocb *req,
- kiocb_cancel_fn *cancel) { }
#endif /* CONFIG_AIO */
/* for sysctl: */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4b6045ebb2f2..7fe64df9eb09 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1742,6 +1742,7 @@ struct file_operations {
u64);
ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *,
u64);
+ int (*cancel_kiocb)(struct kiocb *);
} __randomize_layout;
struct inode_operations {
--
2.17.0
--
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 09/32] aio: add delayed cancel support
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
The upcoming aio poll support would like to be able to complete the iocb
inline from the cancellation context, but that would cause a double lock
of ctx_lock as-is. Add a new delayed_cancel_reqs list of iocbs that
should be cancelled from outside the ctx_lock by calling the (re-)added
ki_cancel callback.
To make this safe aio_complete needs to check if this call should complete
the iocb, and to make that safe without much reordering a struct file
argument to put is padded to aio_complete.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
fs/aio.c | 80 ++++++++++++++++++++++++++++++++++++--------------------
1 file changed, 51 insertions(+), 29 deletions(-)
diff --git a/fs/aio.c b/fs/aio.c
index be10dde20c8e..3afca506c7f0 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -138,7 +138,8 @@ struct kioctx {
struct {
spinlock_t ctx_lock;
- struct list_head active_reqs; /* used for cancellation */
+ struct list_head cancel_reqs;
+ struct list_head delayed_cancel_reqs;
} ____cacheline_aligned_in_smp;
struct {
@@ -171,6 +172,7 @@ struct aio_kiocb {
};
struct kioctx *ki_ctx;
+ int (*ki_cancel)(struct aio_kiocb *iocb);
struct iocb __user *ki_user_iocb; /* user's aiocb */
__u64 ki_user_data; /* user's data for completion */
@@ -178,6 +180,9 @@ struct aio_kiocb {
struct list_head ki_list; /* the aio core uses this
* for cancellation */
+ unsigned int flags; /* protected by ctx->ctx_lock */
+#define AIO_IOCB_CANCELLED (1 << 1)
+
/*
* If the aio_resfd field of the userspace iocb is not zero,
* this is the underlying eventfd context to deliver events to.
@@ -584,18 +589,23 @@ static void free_ioctx_users(struct percpu_ref *ref)
{
struct kioctx *ctx = container_of(ref, struct kioctx, users);
struct aio_kiocb *req;
+ LIST_HEAD(list);
spin_lock_irq(&ctx->ctx_lock);
-
- while (!list_empty(&ctx->active_reqs)) {
- req = list_first_entry(&ctx->active_reqs,
+ while (!list_empty(&ctx->cancel_reqs)) {
+ req = list_first_entry(&ctx->cancel_reqs,
struct aio_kiocb, ki_list);
list_del_init(&req->ki_list);
req->rw.ki_filp->f_op->cancel_kiocb(&req->rw);
}
-
+ list_splice_init(&ctx->delayed_cancel_reqs, &list);
spin_unlock_irq(&ctx->ctx_lock);
+ while (!list_empty(&list)) {
+ req = list_first_entry(&list, struct aio_kiocb, ki_list);
+ req->ki_cancel(req);
+ }
+
percpu_ref_kill(&ctx->reqs);
percpu_ref_put(&ctx->reqs);
}
@@ -715,7 +725,8 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
mutex_lock(&ctx->ring_lock);
init_waitqueue_head(&ctx->wait);
- INIT_LIST_HEAD(&ctx->active_reqs);
+ INIT_LIST_HEAD(&ctx->cancel_reqs);
+ INIT_LIST_HEAD(&ctx->delayed_cancel_reqs);
if (percpu_ref_init(&ctx->users, free_ioctx_users, 0, GFP_KERNEL))
goto err;
@@ -1032,25 +1043,34 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
return ret;
}
+#define AIO_COMPLETE_CANCEL (1 << 0)
+
/* aio_complete
* Called when the io request on the given iocb is complete.
*/
-static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
+static void aio_complete(struct aio_kiocb *iocb, struct file *file, long res,
+ long res2, unsigned complete_flags)
{
struct kioctx *ctx = iocb->ki_ctx;
struct aio_ring *ring;
struct io_event *ev_page, *event;
unsigned tail, pos, head;
- unsigned long flags;
+ unsigned long flags;
if (!list_empty_careful(&iocb->ki_list)) {
- unsigned long flags;
-
spin_lock_irqsave(&ctx->ctx_lock, flags);
+ if (!(complete_flags & AIO_COMPLETE_CANCEL) &&
+ (iocb->flags & AIO_IOCB_CANCELLED)) {
+ spin_unlock_irqrestore(&ctx->ctx_lock, flags);
+ return;
+ }
+
list_del(&iocb->ki_list);
spin_unlock_irqrestore(&ctx->ctx_lock, flags);
}
+ fput(file);
+
/*
* Add a completion event to the ring buffer. Must be done holding
* ctx->completion_lock to prevent other code from messing with the tail
@@ -1384,8 +1404,7 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2)
file_end_write(kiocb->ki_filp);
}
- fput(kiocb->ki_filp);
- aio_complete(iocb, res, res2);
+ aio_complete(iocb, kiocb->ki_filp, res, res2, 0);
}
static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
@@ -1437,7 +1456,7 @@ static inline ssize_t aio_rw_ret(struct kiocb *req, ssize_t ret)
unsigned long flags;
spin_lock_irqsave(&ctx->ctx_lock, flags);
- list_add_tail(&iocb->ki_list, &ctx->active_reqs);
+ list_add_tail(&iocb->ki_list, &ctx->cancel_reqs);
spin_unlock_irqrestore(&ctx->ctx_lock, flags);
}
return ret;
@@ -1539,11 +1558,10 @@ static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
static void aio_fsync_work(struct work_struct *work)
{
struct fsync_iocb *req = container_of(work, struct fsync_iocb, work);
- int ret;
+ struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, fsync);
+ struct file *file = req->file;
- ret = vfs_fsync(req->file, req->datasync);
- fput(req->file);
- aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0);
+ aio_complete(iocb, file, vfs_fsync(file, req->datasync), 0, 0);
}
static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
@@ -1768,18 +1786,12 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
}
#endif
-/* lookup_kiocb
- * Finds a given iocb for cancellation.
- */
static struct aio_kiocb *
-lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb)
+lookup_kiocb(struct list_head *list, struct iocb __user *iocb)
{
struct aio_kiocb *kiocb;
- assert_spin_locked(&ctx->ctx_lock);
-
- /* TODO: use a hash or array, this sucks. */
- list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) {
+ list_for_each_entry(kiocb, list, ki_list) {
if (kiocb->ki_user_iocb == iocb)
return kiocb;
}
@@ -1801,6 +1813,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
{
struct kioctx *ctx;
struct aio_kiocb *kiocb;
+ LIST_HEAD(dummy);
int ret = -EINVAL;
u32 key;
@@ -1814,12 +1827,21 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
return -EINVAL;
spin_lock_irq(&ctx->ctx_lock);
- kiocb = lookup_kiocb(ctx, iocb);
+ kiocb = lookup_kiocb(&ctx->delayed_cancel_reqs, iocb);
if (kiocb) {
- list_del_init(&kiocb->ki_list);
- ret = kiocb->rw.ki_filp->f_op->cancel_kiocb(&kiocb->rw);
+ kiocb->flags |= AIO_IOCB_CANCELLED;
+ list_move_tail(&kiocb->ki_list, &dummy);
+ spin_unlock_irq(&ctx->ctx_lock);
+
+ ret = kiocb->ki_cancel(kiocb);
+ } else {
+ kiocb = lookup_kiocb(&ctx->cancel_reqs, iocb);
+ if (kiocb) {
+ list_del_init(&kiocb->ki_list);
+ ret = kiocb->rw.ki_filp->f_op->cancel_kiocb(&kiocb->rw);
+ }
+ spin_unlock_irq(&ctx->ctx_lock);
}
- spin_unlock_irq(&ctx->ctx_lock);
if (!ret) {
/*
--
2.17.0
--
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 10/32] aio: implement IOCB_CMD_POLL
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Simple one-shot poll through the io_submit() interface. To poll for
a file descriptor the application should submit an iocb of type
IOCB_CMD_POLL. It will poll the fd for the events specified in the
the first 32 bits of the aio_buf field of the iocb.
Unlike poll or epoll without EPOLLONESHOT this interface always works
in one shot mode, that is once the iocb is completed, it will have to be
resubmitted.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Jeff Moyer <jmoyer@redhat.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
---
fs/aio.c | 92 +++++++++++++++++++++++++++++++++++-
include/uapi/linux/aio_abi.h | 6 +--
2 files changed, 93 insertions(+), 5 deletions(-)
diff --git a/fs/aio.c b/fs/aio.c
index 3afca506c7f0..f2c7674e2151 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -5,6 +5,7 @@
* Implements an efficient asynchronous io interface.
*
* Copyright 2000, 2001, 2002 Red Hat, Inc. All Rights Reserved.
+ * Copyright 2018 Christoph Hellwig.
*
* See ../COPYING for licensing terms.
*/
@@ -165,10 +166,18 @@ struct fsync_iocb {
bool datasync;
};
+struct poll_iocb {
+ struct file *file;
+ __poll_t events;
+ struct wait_queue_head *head;
+ struct wait_queue_entry wait;
+};
+
struct aio_kiocb {
union {
struct kiocb rw;
struct fsync_iocb fsync;
+ struct poll_iocb poll;
};
struct kioctx *ki_ctx;
@@ -1569,7 +1578,6 @@ static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes ||
iocb->aio_rw_flags))
return -EINVAL;
-
req->file = fget(iocb->aio_fildes);
if (unlikely(!req->file))
return -EBADF;
@@ -1584,6 +1592,86 @@ static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
return -EIOCBQUEUED;
}
+static int aio_poll_cancel(struct aio_kiocb *iocb)
+{
+ remove_wait_queue(iocb->poll.head, &iocb->poll.wait);
+ aio_complete(iocb, iocb->poll.file, 0, 0, AIO_COMPLETE_CANCEL);
+ return 0;
+}
+
+static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
+ void *key)
+{
+ struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
+ struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
+ struct file *file = req->file;
+ __poll_t mask = key_to_poll(key);
+
+ assert_spin_locked(&req->head->lock);
+
+ /* for instances that support it check for an event match first: */
+ if (mask && !(mask & req->events))
+ return 0;
+
+ mask = file->f_op->poll_mask(file, req->events);
+ if (!mask)
+ return 0;
+
+ __remove_wait_queue(req->head, &req->wait);
+ aio_complete(iocb, req->file, mangle_poll(mask), 0, 0);
+ return 1;
+}
+
+static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
+{
+ struct kioctx *ctx = aiocb->ki_ctx;
+ struct poll_iocb *req = &aiocb->poll;
+ unsigned long flags;
+ __poll_t mask;
+
+ /* reject any unknown events outside the normal event mask. */
+ if ((u16)iocb->aio_buf != iocb->aio_buf)
+ return -EINVAL;
+ /* reject fields that are not defined for poll */
+ if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)
+ return -EINVAL;
+
+ req->events = demangle_poll(iocb->aio_buf) | POLLERR | POLLHUP;
+ req->file = fget(iocb->aio_fildes);
+ if (unlikely(!req->file))
+ return -EBADF;
+ if (!file_has_poll_mask(req->file))
+ goto out_fail;
+
+ req->head = req->file->f_op->get_poll_head(req->file, req->events);
+ if (!req->head)
+ goto out_fail;
+ if (IS_ERR(req->head)) {
+ mask = EPOLLERR;
+ goto done;
+ }
+
+ init_waitqueue_func_entry(&req->wait, aio_poll_wake);
+ aiocb->ki_cancel = aio_poll_cancel;
+
+ spin_lock_irqsave(&ctx->ctx_lock, flags);
+ list_add_tail(&aiocb->ki_list, &ctx->delayed_cancel_reqs);
+ spin_unlock(&ctx->ctx_lock);
+
+ spin_lock(&req->head->lock);
+ mask = req->file->f_op->poll_mask(req->file, req->events);
+ if (!mask)
+ __add_wait_queue(req->head, &req->wait);
+ spin_unlock_irqrestore(&req->head->lock, flags);
+done:
+ if (mask)
+ aio_complete(aiocb, req->file, mangle_poll(mask), 0, 0);
+ return -EIOCBQUEUED;
+out_fail:
+ fput(req->file);
+ return -EINVAL; /* same as no support for IOCB_CMD_POLL */
+}
+
static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
struct iocb *iocb, bool compat)
{
@@ -1652,6 +1740,8 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
break;
case IOCB_CMD_FDSYNC:
ret = aio_fsync(&req->fsync, iocb, true);
+ case IOCB_CMD_POLL:
+ ret = aio_poll(req, iocb);
break;
default:
pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index 2c0a3415beee..ed0185945bb2 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -39,10 +39,8 @@ enum {
IOCB_CMD_PWRITE = 1,
IOCB_CMD_FSYNC = 2,
IOCB_CMD_FDSYNC = 3,
- /* These two are experimental.
- * IOCB_CMD_PREADX = 4,
- * IOCB_CMD_POLL = 5,
- */
+ /* 4 was the experimental IOCB_CMD_PREADX */
+ IOCB_CMD_POLL = 5,
IOCB_CMD_NOOP = 6,
IOCB_CMD_PREADV = 7,
IOCB_CMD_PWRITEV = 8,
--
2.17.0
--
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 11/32] net: refactor socket_poll
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Factor out two busy poll related helpers for late reuse, and remove
a command that isn't very helpful, especially with the __poll_t
annotations in place.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
include/net/busy_poll.h | 15 +++++++++++++++
net/socket.c | 21 ++++-----------------
2 files changed, 19 insertions(+), 17 deletions(-)
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 71c72a939bf8..c5187438af38 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -121,6 +121,21 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock)
#endif
}
+static inline void sock_poll_busy_loop(struct socket *sock, __poll_t events)
+{
+ if (sk_can_busy_loop(sock->sk) &&
+ events && (events & POLL_BUSY_LOOP)) {
+ /* once, only if requested by syscall */
+ sk_busy_loop(sock->sk, 1);
+ }
+}
+
+/* if this socket can poll_ll, tell the system call */
+static inline __poll_t sock_poll_busy_flag(struct socket *sock)
+{
+ return sk_can_busy_loop(sock->sk) ? POLL_BUSY_LOOP : 0;
+}
+
/* used in the NIC receive handler to mark the skb */
static inline void skb_mark_napi_id(struct sk_buff *skb,
struct napi_struct *napi)
diff --git a/net/socket.c b/net/socket.c
index f10f1d947c78..571ee4005192 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1117,24 +1117,11 @@ EXPORT_SYMBOL(sock_create_lite);
/* No kernel lock held - perfect */
static __poll_t sock_poll(struct file *file, poll_table *wait)
{
- __poll_t busy_flag = 0;
- struct socket *sock;
-
- /*
- * We can't return errors to poll, so it's either yes or no.
- */
- sock = file->private_data;
-
- if (sk_can_busy_loop(sock->sk)) {
- /* this socket can poll_ll so tell the system call */
- busy_flag = POLL_BUSY_LOOP;
-
- /* once, only if requested by syscall */
- if (wait && (wait->_key & POLL_BUSY_LOOP))
- sk_busy_loop(sock->sk, 1);
- }
+ struct socket *sock = file->private_data;
+ __poll_t events = poll_requested_events(wait);
- return busy_flag | sock->ops->poll(file, sock, wait);
+ sock_poll_busy_loop(sock, events);
+ return sock->ops->poll(file, sock, wait) | sock_poll_busy_flag(sock);
}
static int sock_mmap(struct file *file, struct vm_area_struct *vma)
--
2.17.0
--
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 12/32] net: add support for ->poll_mask in proto_ops
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
The socket file operations still implement ->poll until all protocols are
switched over.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
include/linux/net.h | 3 +++
net/socket.c | 51 ++++++++++++++++++++++++++++++++++++++++-----
2 files changed, 49 insertions(+), 5 deletions(-)
diff --git a/include/linux/net.h b/include/linux/net.h
index 2248a052061d..804413cf1c72 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -147,6 +147,9 @@ struct proto_ops {
int (*getname) (struct socket *sock,
struct sockaddr *addr,
int peer);
+ struct wait_queue_head *(*get_poll_head)(struct socket *sock,
+ __poll_t events);
+ __poll_t (*poll_mask) (struct socket *sock, __poll_t events);
__poll_t (*poll) (struct file *file, struct socket *sock,
struct poll_table_struct *wait);
int (*ioctl) (struct socket *sock, unsigned int cmd,
diff --git a/net/socket.c b/net/socket.c
index 571ee4005192..3c4544ee0a16 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -117,8 +117,10 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from);
static int sock_mmap(struct file *file, struct vm_area_struct *vma);
static int sock_close(struct inode *inode, struct file *file);
-static __poll_t sock_poll(struct file *file,
- struct poll_table_struct *wait);
+static struct wait_queue_head *sock_get_poll_head(struct file *file,
+ __poll_t events);
+static __poll_t sock_poll_mask(struct file *file, __poll_t);
+static __poll_t sock_poll(struct file *file, struct poll_table_struct *wait);
static long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
#ifdef CONFIG_COMPAT
static long compat_sock_ioctl(struct file *file,
@@ -141,6 +143,8 @@ static const struct file_operations socket_file_ops = {
.llseek = no_llseek,
.read_iter = sock_read_iter,
.write_iter = sock_write_iter,
+ .get_poll_head = sock_get_poll_head,
+ .poll_mask = sock_poll_mask,
.poll = sock_poll,
.unlocked_ioctl = sock_ioctl,
#ifdef CONFIG_COMPAT
@@ -1114,14 +1118,51 @@ int sock_create_lite(int family, int type, int protocol, struct socket **res)
}
EXPORT_SYMBOL(sock_create_lite);
+static struct wait_queue_head *sock_get_poll_head(struct file *file,
+ __poll_t events)
+{
+ struct socket *sock = file->private_data;
+
+ if (!sock->ops->poll_mask)
+ return NULL;
+ if (sock->ops->get_poll_head)
+ return sock->ops->get_poll_head(sock, events);
+
+ sock_poll_busy_loop(sock, events);
+ return sk_sleep(sock->sk);
+}
+
+static __poll_t sock_poll_mask(struct file *file, __poll_t events)
+{
+ struct socket *sock = file->private_data;
+
+ /*
+ * We need to be sure we are in sync with the socket flags modification.
+ *
+ * This memory barrier is paired in the wq_has_sleeper.
+ */
+ smp_mb();
+
+ /* this socket can poll_ll so tell the system call */
+ return sock->ops->poll_mask(sock, events) |
+ (sk_can_busy_loop(sock->sk) ? POLL_BUSY_LOOP : 0);
+}
+
/* No kernel lock held - perfect */
static __poll_t sock_poll(struct file *file, poll_table *wait)
{
struct socket *sock = file->private_data;
- __poll_t events = poll_requested_events(wait);
+ __poll_t events = poll_requested_events(wait), mask = 0;
- sock_poll_busy_loop(sock, events);
- return sock->ops->poll(file, sock, wait) | sock_poll_busy_flag(sock);
+ if (sock->ops->poll) {
+ sock_poll_busy_loop(sock, events);
+ mask = sock->ops->poll(file, sock, wait);
+ } else if (sock->ops->poll_mask) {
+ sock_poll_wait(file, sock_get_poll_head(file, events), wait);
+ mask = sock->ops->poll_mask(sock, events);
+ }
+
+ return mask | sock_poll_busy_flag(sock);
}
static int sock_mmap(struct file *file, struct vm_area_struct *vma)
--
2.17.0
--
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 13/32] net: remove sock_no_poll
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Now that sock_poll handles a NULL ->poll or ->poll_mask there is no need
for a stub.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
crypto/af_alg.c | 1 -
crypto/algif_hash.c | 2 --
crypto/algif_rng.c | 1 -
drivers/isdn/mISDN/socket.c | 1 -
drivers/net/ppp/pptp.c | 1 -
include/net/sock.h | 2 --
net/bluetooth/bnep/sock.c | 1 -
net/bluetooth/cmtp/sock.c | 1 -
net/bluetooth/hidp/sock.c | 1 -
net/core/sock.c | 6 ------
10 files changed, 17 deletions(-)
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 7846c0c20cfe..80838c1cef94 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -347,7 +347,6 @@ static const struct proto_ops alg_proto_ops = {
.sendpage = sock_no_sendpage,
.sendmsg = sock_no_sendmsg,
.recvmsg = sock_no_recvmsg,
- .poll = sock_no_poll,
.bind = alg_bind,
.release = af_alg_release,
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 6c9b1927a520..bfcf595fd8f9 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -288,7 +288,6 @@ static struct proto_ops algif_hash_ops = {
.mmap = sock_no_mmap,
.bind = sock_no_bind,
.setsockopt = sock_no_setsockopt,
- .poll = sock_no_poll,
.release = af_alg_release,
.sendmsg = hash_sendmsg,
@@ -396,7 +395,6 @@ static struct proto_ops algif_hash_ops_nokey = {
.mmap = sock_no_mmap,
.bind = sock_no_bind,
.setsockopt = sock_no_setsockopt,
- .poll = sock_no_poll,
.release = af_alg_release,
.sendmsg = hash_sendmsg_nokey,
diff --git a/crypto/algif_rng.c b/crypto/algif_rng.c
index 150c2b6480ed..22df3799a17b 100644
--- a/crypto/algif_rng.c
+++ b/crypto/algif_rng.c
@@ -106,7 +106,6 @@ static struct proto_ops algif_rng_ops = {
.bind = sock_no_bind,
.accept = sock_no_accept,
.setsockopt = sock_no_setsockopt,
- .poll = sock_no_poll,
.sendmsg = sock_no_sendmsg,
.sendpage = sock_no_sendpage,
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index 1f8f489b4167..18c0a1281914 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -745,7 +745,6 @@ static const struct proto_ops base_sock_ops = {
.getname = sock_no_getname,
.sendmsg = sock_no_sendmsg,
.recvmsg = sock_no_recvmsg,
- .poll = sock_no_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index c4267ecefd85..157b67c1bf8e 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -624,7 +624,6 @@ static const struct proto_ops pptp_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = pptp_getname,
- .poll = sock_no_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
diff --git a/include/net/sock.h b/include/net/sock.h
index 74d725fdbe0f..4d2e8ad98985 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1591,8 +1591,6 @@ int sock_no_connect(struct socket *, struct sockaddr *, int, int);
int sock_no_socketpair(struct socket *, struct socket *);
int sock_no_accept(struct socket *, struct socket *, int, bool);
int sock_no_getname(struct socket *, struct sockaddr *, int);
-__poll_t sock_no_poll(struct file *, struct socket *,
- struct poll_table_struct *);
int sock_no_ioctl(struct socket *, unsigned int, unsigned long);
int sock_no_listen(struct socket *, int);
int sock_no_shutdown(struct socket *, int);
diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c
index b5116fa9835e..00deacdcb51c 100644
--- a/net/bluetooth/bnep/sock.c
+++ b/net/bluetooth/bnep/sock.c
@@ -175,7 +175,6 @@ static const struct proto_ops bnep_sock_ops = {
.getname = sock_no_getname,
.sendmsg = sock_no_sendmsg,
.recvmsg = sock_no_recvmsg,
- .poll = sock_no_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
diff --git a/net/bluetooth/cmtp/sock.c b/net/bluetooth/cmtp/sock.c
index ce86a7bae844..e08f28fadd65 100644
--- a/net/bluetooth/cmtp/sock.c
+++ b/net/bluetooth/cmtp/sock.c
@@ -178,7 +178,6 @@ static const struct proto_ops cmtp_sock_ops = {
.getname = sock_no_getname,
.sendmsg = sock_no_sendmsg,
.recvmsg = sock_no_recvmsg,
- .poll = sock_no_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c
index 008ba439bd62..1eaac01f85de 100644
--- a/net/bluetooth/hidp/sock.c
+++ b/net/bluetooth/hidp/sock.c
@@ -208,7 +208,6 @@ static const struct proto_ops hidp_sock_ops = {
.getname = sock_no_getname,
.sendmsg = sock_no_sendmsg,
.recvmsg = sock_no_recvmsg,
- .poll = sock_no_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.setsockopt = sock_no_setsockopt,
diff --git a/net/core/sock.c b/net/core/sock.c
index 6444525f610c..d471aa524b62 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2567,12 +2567,6 @@ int sock_no_getname(struct socket *sock, struct sockaddr *saddr,
}
EXPORT_SYMBOL(sock_no_getname);
-__poll_t sock_no_poll(struct file *file, struct socket *sock, poll_table *pt)
-{
- return 0;
-}
-EXPORT_SYMBOL(sock_no_poll);
-
int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
return -EOPNOTSUPP;
--
2.17.0
--
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 14/32] net/tcp: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
include/net/tcp.h | 4 ++--
net/ipv4/af_inet.c | 3 ++-
net/ipv4/tcp.c | 31 ++++++++++++++-----------------
net/ipv6/af_inet6.c | 3 ++-
4 files changed, 20 insertions(+), 21 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9c9b3768b350..d4d72ea9128d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -388,8 +388,8 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
void tcp_close(struct sock *sk, long timeout);
void tcp_init_sock(struct sock *sk);
void tcp_init_transfer(struct sock *sk, int bpf_op);
-__poll_t tcp_poll(struct file *file, struct socket *sock,
- struct poll_table_struct *wait);
+struct wait_queue_head *tcp_get_poll_head(struct socket *sock, __poll_t events);
+__poll_t tcp_poll_mask(struct socket *sock, __poll_t events);
int tcp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
int tcp_setsockopt(struct sock *sk, int level, int optname,
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index eaed0367e669..220b51347526 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -986,7 +986,8 @@ const struct proto_ops inet_stream_ops = {
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet_getname,
- .poll = tcp_poll,
+ .get_poll_head = tcp_get_poll_head,
+ .poll_mask = tcp_poll_mask,
.ioctl = inet_ioctl,
.listen = inet_listen,
.shutdown = inet_shutdown,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9ce1c726185e..6ec0e7a13581 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -493,33 +493,30 @@ static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
sk->sk_prot->stream_memory_read(sk) : false);
}
+struct wait_queue_head *tcp_get_poll_head(struct socket *sock, __poll_t events)
+{
+ sock_poll_busy_loop(sock, events);
+ sock_rps_record_flow(sock->sk);
+ return sk_sleep(sock->sk);
+}
+EXPORT_SYMBOL(tcp_get_poll_head);
+
/*
- * Wait for a TCP event.
- *
- * Note that we don't need to lock the socket, as the upper poll layers
- * take care of normal races (between the test and the event) and we don't
- * go look at any of the socket buffers directly.
+ * Socket is not locked. We are protected from async events by poll logic and
+ * correct handling of state changes made by other threads is impossible in
+ * any case.
*/
-__poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t tcp_poll_mask(struct socket *sock, __poll_t events)
{
- __poll_t mask;
struct sock *sk = sock->sk;
const struct tcp_sock *tp = tcp_sk(sk);
+ __poll_t mask = 0;
int state;
- sock_poll_wait(file, sk_sleep(sk), wait);
-
state = inet_sk_state_load(sk);
if (state == TCP_LISTEN)
return inet_csk_listen_poll(sk);
- /* Socket is not locked. We are protected from async events
- * by poll logic and correct handling of state changes
- * made by other threads is impossible in any case.
- */
-
- mask = 0;
-
/*
* EPOLLHUP is certainly not done right. But poll() doesn't
* have a notion of HUP in just one direction, and for a
@@ -600,7 +597,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
return mask;
}
-EXPORT_SYMBOL(tcp_poll);
+EXPORT_SYMBOL(tcp_poll_mask);
int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 8da0b513f188..a43d967eeca5 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -571,7 +571,8 @@ const struct proto_ops inet6_stream_ops = {
.socketpair = sock_no_socketpair, /* a do nothing */
.accept = inet_accept, /* ok */
.getname = inet6_getname,
- .poll = tcp_poll, /* ok */
+ .get_poll_head = tcp_get_poll_head,
+ .poll_mask = tcp_poll_mask, /* ok */
.ioctl = inet6_ioctl, /* must change */
.listen = inet_listen, /* ok */
.shutdown = inet_shutdown, /* ok */
--
2.17.0
^ permalink raw reply related
* [PATCH 15/32] net/unix: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
net/unix/af_unix.c | 30 +++++++++++-------------------
1 file changed, 11 insertions(+), 19 deletions(-)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 68bb70a62afe..1a9cdad4ab82 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -638,9 +638,8 @@ static int unix_stream_connect(struct socket *, struct sockaddr *,
static int unix_socketpair(struct socket *, struct socket *);
static int unix_accept(struct socket *, struct socket *, int, bool);
static int unix_getname(struct socket *, struct sockaddr *, int);
-static __poll_t unix_poll(struct file *, struct socket *, poll_table *);
-static __poll_t unix_dgram_poll(struct file *, struct socket *,
- poll_table *);
+static __poll_t unix_poll_mask(struct socket *, __poll_t);
+static __poll_t unix_dgram_poll_mask(struct socket *, __poll_t);
static int unix_ioctl(struct socket *, unsigned int, unsigned long);
static int unix_shutdown(struct socket *, int);
static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t);
@@ -681,7 +680,7 @@ static const struct proto_ops unix_stream_ops = {
.socketpair = unix_socketpair,
.accept = unix_accept,
.getname = unix_getname,
- .poll = unix_poll,
+ .poll_mask = unix_poll_mask,
.ioctl = unix_ioctl,
.listen = unix_listen,
.shutdown = unix_shutdown,
@@ -704,7 +703,7 @@ static const struct proto_ops unix_dgram_ops = {
.socketpair = unix_socketpair,
.accept = sock_no_accept,
.getname = unix_getname,
- .poll = unix_dgram_poll,
+ .poll_mask = unix_dgram_poll_mask,
.ioctl = unix_ioctl,
.listen = sock_no_listen,
.shutdown = unix_shutdown,
@@ -726,7 +725,7 @@ static const struct proto_ops unix_seqpacket_ops = {
.socketpair = unix_socketpair,
.accept = unix_accept,
.getname = unix_getname,
- .poll = unix_dgram_poll,
+ .poll_mask = unix_dgram_poll_mask,
.ioctl = unix_ioctl,
.listen = unix_listen,
.shutdown = unix_shutdown,
@@ -2630,13 +2629,10 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
return err;
}
-static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait)
+static __poll_t unix_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
- __poll_t mask;
-
- sock_poll_wait(file, sk_sleep(sk), wait);
- mask = 0;
+ __poll_t mask = 0;
/* exceptional events? */
if (sk->sk_err)
@@ -2665,15 +2661,11 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
return mask;
}
-static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static __poll_t unix_dgram_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk, *other;
- unsigned int writable;
- __poll_t mask;
-
- sock_poll_wait(file, sk_sleep(sk), wait);
- mask = 0;
+ int writable;
+ __poll_t mask = 0;
/* exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
@@ -2699,7 +2691,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
}
/* No write status requested, avoid expensive OUT tests. */
- if (!(poll_requested_events(wait) & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
+ if (!(events & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
return mask;
writable = unix_writable(sk);
--
2.17.0
^ permalink raw reply related
* [PATCH 17/32] net/dccp: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
net/dccp/dccp.h | 3 +--
net/dccp/ipv4.c | 2 +-
net/dccp/ipv6.c | 2 +-
net/dccp/proto.c | 13 ++-----------
4 files changed, 5 insertions(+), 15 deletions(-)
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index f91e3816806b..0ea2ee56ac1b 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -316,8 +316,7 @@ int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
int flags, int *addr_len);
void dccp_shutdown(struct sock *sk, int how);
int inet_dccp_listen(struct socket *sock, int backlog);
-__poll_t dccp_poll(struct file *file, struct socket *sock,
- poll_table *wait);
+__poll_t dccp_poll_mask(struct socket *sock, __poll_t events);
int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
void dccp_req_err(struct sock *sk, u64 seq);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index b08feb219b44..a9e478cd3787 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -984,7 +984,7 @@ static const struct proto_ops inet_dccp_ops = {
.accept = inet_accept,
.getname = inet_getname,
/* FIXME: work on tcp_poll to rename it to inet_csk_poll */
- .poll = dccp_poll,
+ .poll_mask = dccp_poll_mask,
.ioctl = inet_ioctl,
/* FIXME: work on inet_listen to rename it to sock_common_listen */
.listen = inet_dccp_listen,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 6344f1b18a6a..17fc4e0166ba 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -1070,7 +1070,7 @@ static const struct proto_ops inet6_dccp_ops = {
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet6_getname,
- .poll = dccp_poll,
+ .poll_mask = dccp_poll_mask,
.ioctl = inet6_ioctl,
.listen = inet_dccp_listen,
.shutdown = inet_shutdown,
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 84cd4e3fd01b..88b668db244b 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -314,20 +314,11 @@ int dccp_disconnect(struct sock *sk, int flags)
EXPORT_SYMBOL_GPL(dccp_disconnect);
-/*
- * Wait for a DCCP event.
- *
- * Note that we don't need to lock the socket, as the upper poll layers
- * take care of normal races (between the test and the event) and we don't
- * go look at any of the socket buffers directly.
- */
-__poll_t dccp_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+__poll_t dccp_poll_mask(struct socket *sock, __poll_t events)
{
__poll_t mask;
struct sock *sk = sock->sk;
- sock_poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_state == DCCP_LISTEN)
return inet_csk_listen_poll(sk);
@@ -369,7 +360,7 @@ __poll_t dccp_poll(struct file *file, struct socket *sock,
return mask;
}
-EXPORT_SYMBOL_GPL(dccp_poll);
+EXPORT_SYMBOL_GPL(dccp_poll_mask);
int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
--
2.17.0
^ permalink raw reply related
* [PATCH 18/32] net/atm: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
net/atm/common.c | 11 +++--------
net/atm/common.h | 2 +-
net/atm/pvc.c | 2 +-
net/atm/svc.c | 2 +-
4 files changed, 6 insertions(+), 11 deletions(-)
diff --git a/net/atm/common.c b/net/atm/common.c
index fc78a0508ae1..1f2af59935db 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -648,16 +648,11 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
return error;
}
-__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t vcc_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
- struct atm_vcc *vcc;
- __poll_t mask;
-
- sock_poll_wait(file, sk_sleep(sk), wait);
- mask = 0;
-
- vcc = ATM_SD(sock);
+ struct atm_vcc *vcc = ATM_SD(sock);
+ __poll_t mask = 0;
/* exceptional events */
if (sk->sk_err)
diff --git a/net/atm/common.h b/net/atm/common.h
index 5850649068bb..526796ad230f 100644
--- a/net/atm/common.h
+++ b/net/atm/common.h
@@ -17,7 +17,7 @@ int vcc_connect(struct socket *sock, int itf, short vpi, int vci);
int vcc_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int flags);
int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len);
-__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait);
+__poll_t vcc_poll_mask(struct socket *sock, __poll_t events);
int vcc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
int vcc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
int vcc_setsockopt(struct socket *sock, int level, int optname,
diff --git a/net/atm/pvc.c b/net/atm/pvc.c
index 2cb10af16afc..9f75092fe778 100644
--- a/net/atm/pvc.c
+++ b/net/atm/pvc.c
@@ -113,7 +113,7 @@ static const struct proto_ops pvc_proto_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = pvc_getname,
- .poll = vcc_poll,
+ .poll_mask = vcc_poll_mask,
.ioctl = vcc_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = vcc_compat_ioctl,
diff --git a/net/atm/svc.c b/net/atm/svc.c
index 2f91b766ac42..53f4ad7087b1 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -636,7 +636,7 @@ static const struct proto_ops svc_proto_ops = {
.socketpair = sock_no_socketpair,
.accept = svc_accept,
.getname = svc_getname,
- .poll = vcc_poll,
+ .poll_mask = vcc_poll_mask,
.ioctl = svc_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = svc_compat_ioctl,
--
2.17.0
^ permalink raw reply related
* [PATCH 19/32] net/vmw_vsock: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
net/vmw_vsock/af_vsock.c | 19 ++++++-------------
1 file changed, 6 insertions(+), 13 deletions(-)
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index c1076c19b858..bb5d5fa68c35 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -850,18 +850,11 @@ static int vsock_shutdown(struct socket *sock, int mode)
return err;
}
-static __poll_t vsock_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static __poll_t vsock_poll_mask(struct socket *sock, __poll_t events)
{
- struct sock *sk;
- __poll_t mask;
- struct vsock_sock *vsk;
-
- sk = sock->sk;
- vsk = vsock_sk(sk);
-
- poll_wait(file, sk_sleep(sk), wait);
- mask = 0;
+ struct sock *sk = sock->sk;
+ struct vsock_sock *vsk = vsock_sk(sk);
+ __poll_t mask = 0;
if (sk->sk_err)
/* Signify that there has been an error on this socket. */
@@ -1091,7 +1084,7 @@ static const struct proto_ops vsock_dgram_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = vsock_getname,
- .poll = vsock_poll,
+ .poll_mask = vsock_poll_mask,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = vsock_shutdown,
@@ -1849,7 +1842,7 @@ static const struct proto_ops vsock_stream_ops = {
.socketpair = sock_no_socketpair,
.accept = vsock_accept,
.getname = vsock_getname,
- .poll = vsock_poll,
+ .poll_mask = vsock_poll_mask,
.ioctl = sock_no_ioctl,
.listen = vsock_listen,
.shutdown = vsock_shutdown,
--
2.17.0
^ permalink raw reply related
* [PATCH 20/32] net/tipc: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
net/tipc/socket.c | 14 +++++---------
1 file changed, 5 insertions(+), 9 deletions(-)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 252a52ae0893..58549338582a 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -692,10 +692,9 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
}
/**
- * tipc_poll - read and possibly block on pollmask
+ * tipc_poll - read pollmask
* @file: file structure associated with the socket
* @sock: socket for which to calculate the poll bits
- * @wait: ???
*
* Returns pollmask value
*
@@ -709,15 +708,12 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
* imply that the operation will succeed, merely that it should be performed
* and will not block.
*/
-static __poll_t tipc_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static __poll_t tipc_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
__poll_t revents = 0;
- sock_poll_wait(file, sk_sleep(sk), wait);
-
if (sk->sk_shutdown & RCV_SHUTDOWN)
revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
@@ -3027,7 +3023,7 @@ static const struct proto_ops msg_ops = {
.socketpair = tipc_socketpair,
.accept = sock_no_accept,
.getname = tipc_getname,
- .poll = tipc_poll,
+ .poll_mask = tipc_poll_mask,
.ioctl = tipc_ioctl,
.listen = sock_no_listen,
.shutdown = tipc_shutdown,
@@ -3048,7 +3044,7 @@ static const struct proto_ops packet_ops = {
.socketpair = tipc_socketpair,
.accept = tipc_accept,
.getname = tipc_getname,
- .poll = tipc_poll,
+ .poll_mask = tipc_poll_mask,
.ioctl = tipc_ioctl,
.listen = tipc_listen,
.shutdown = tipc_shutdown,
@@ -3069,7 +3065,7 @@ static const struct proto_ops stream_ops = {
.socketpair = tipc_socketpair,
.accept = tipc_accept,
.getname = tipc_getname,
- .poll = tipc_poll,
+ .poll_mask = tipc_poll_mask,
.ioctl = tipc_ioctl,
.listen = tipc_listen,
.shutdown = tipc_shutdown,
--
2.17.0
--
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 21/32] net/sctp: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
include/net/sctp/sctp.h | 3 +--
net/sctp/ipv6.c | 2 +-
net/sctp/protocol.c | 2 +-
net/sctp/socket.c | 4 +---
4 files changed, 4 insertions(+), 7 deletions(-)
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 28b996d63490..206100cc665b 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -107,8 +107,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb);
int sctp_inet_listen(struct socket *sock, int backlog);
void sctp_write_space(struct sock *sk);
void sctp_data_ready(struct sock *sk);
-__poll_t sctp_poll(struct file *file, struct socket *sock,
- poll_table *wait);
+__poll_t sctp_poll_mask(struct socket *sock, __poll_t events);
void sctp_sock_rfree(struct sk_buff *skb);
void sctp_copy_sock(struct sock *newsk, struct sock *sk,
struct sctp_association *asoc);
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 2e3f7b75a8ec..d52eaf1881af 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -1007,7 +1007,7 @@ static const struct proto_ops inet6_seqpacket_ops = {
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = sctp_getname,
- .poll = sctp_poll,
+ .poll_mask = sctp_poll_mask,
.ioctl = inet6_ioctl,
.listen = sctp_inet_listen,
.shutdown = inet_shutdown,
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index d685f8456762..a1d2ea3ff4c9 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1016,7 +1016,7 @@ static const struct proto_ops inet_seqpacket_ops = {
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet_getname, /* Semantics are different. */
- .poll = sctp_poll,
+ .poll_mask = sctp_poll_mask,
.ioctl = inet_ioctl,
.listen = sctp_inet_listen,
.shutdown = inet_shutdown, /* Looks harmless. */
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 80835ac26d2c..f6bb1b89525c 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7701,14 +7701,12 @@ int sctp_inet_listen(struct socket *sock, int backlog)
* here, again, by modeling the current TCP/UDP code. We don't have
* a good way to test with it yet.
*/
-__poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
+__poll_t sctp_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
struct sctp_sock *sp = sctp_sk(sk);
__poll_t mask;
- poll_wait(file, sk_sleep(sk), wait);
-
sock_rps_record_flow(sk);
/* A TCP-style listening socket becomes readable when the accept queue
--
2.17.0
--
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 22/32] net/bluetooth: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
include/net/bluetooth/bluetooth.h | 2 +-
net/bluetooth/af_bluetooth.c | 7 ++-----
net/bluetooth/l2cap_sock.c | 2 +-
net/bluetooth/rfcomm/sock.c | 2 +-
net/bluetooth/sco.c | 2 +-
5 files changed, 6 insertions(+), 9 deletions(-)
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index ec9d6bc65855..53ce8176c313 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -271,7 +271,7 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
int flags);
int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg,
size_t len, int flags);
-__poll_t bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait);
+__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events);
int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo);
int bt_sock_wait_ready(struct sock *sk, unsigned long flags);
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 84d92a077834..80033a7e1de2 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -437,16 +437,13 @@ static inline __poll_t bt_accept_poll(struct sock *parent)
return 0;
}
-__poll_t bt_sock_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+__poll_t bt_sock_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
__poll_t mask = 0;
BT_DBG("sock %p, sk %p", sock, sk);
- poll_wait(file, sk_sleep(sk), wait);
-
if (sk->sk_state == BT_LISTEN)
return bt_accept_poll(sk);
@@ -478,7 +475,7 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock,
return mask;
}
-EXPORT_SYMBOL(bt_sock_poll);
+EXPORT_SYMBOL(bt_sock_poll_mask);
int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 686bdc6b35b0..742a190034e6 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1653,7 +1653,7 @@ static const struct proto_ops l2cap_sock_ops = {
.getname = l2cap_sock_getname,
.sendmsg = l2cap_sock_sendmsg,
.recvmsg = l2cap_sock_recvmsg,
- .poll = bt_sock_poll,
+ .poll_mask = bt_sock_poll_mask,
.ioctl = bt_sock_ioctl,
.mmap = sock_no_mmap,
.socketpair = sock_no_socketpair,
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index d606e9212291..1cf57622473a 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -1049,7 +1049,7 @@ static const struct proto_ops rfcomm_sock_ops = {
.setsockopt = rfcomm_sock_setsockopt,
.getsockopt = rfcomm_sock_getsockopt,
.ioctl = rfcomm_sock_ioctl,
- .poll = bt_sock_poll,
+ .poll_mask = bt_sock_poll_mask,
.socketpair = sock_no_socketpair,
.mmap = sock_no_mmap
};
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 413b8ee49fec..d60dbc61d170 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -1197,7 +1197,7 @@ static const struct proto_ops sco_sock_ops = {
.getname = sco_sock_getname,
.sendmsg = sco_sock_sendmsg,
.recvmsg = sco_sock_recvmsg,
- .poll = bt_sock_poll,
+ .poll_mask = bt_sock_poll_mask,
.ioctl = bt_sock_ioctl,
.mmap = sock_no_mmap,
.socketpair = sock_no_socketpair,
--
2.17.0
--
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 23/32] net/caif: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
net/caif/caif_socket.c | 12 ++++--------
1 file changed, 4 insertions(+), 8 deletions(-)
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index a6fb1b3bcad9..c7991867d622 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -934,15 +934,11 @@ static int caif_release(struct socket *sock)
}
/* Copied from af_unix.c:unix_poll(), added CAIF tx_flow handling */
-static __poll_t caif_poll(struct file *file,
- struct socket *sock, poll_table *wait)
+static __poll_t caif_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
- __poll_t mask;
struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
-
- sock_poll_wait(file, sk_sleep(sk), wait);
- mask = 0;
+ __poll_t mask = 0;
/* exceptional events? */
if (sk->sk_err)
@@ -976,7 +972,7 @@ static const struct proto_ops caif_seqpacket_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll = caif_poll,
+ .poll_mask = caif_poll_mask,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
@@ -997,7 +993,7 @@ static const struct proto_ops caif_stream_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll = caif_poll,
+ .poll_mask = caif_poll_mask,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
--
2.17.0
^ permalink raw reply related
* [PATCH 24/32] net/nfc: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
net/nfc/llcp_sock.c | 9 +++------
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index ea0c0c6f1874..ab5bb14b49af 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -548,16 +548,13 @@ static inline __poll_t llcp_accept_poll(struct sock *parent)
return 0;
}
-static __poll_t llcp_sock_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static __poll_t llcp_sock_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
__poll_t mask = 0;
pr_debug("%p\n", sk);
- sock_poll_wait(file, sk_sleep(sk), wait);
-
if (sk->sk_state == LLCP_LISTEN)
return llcp_accept_poll(sk);
@@ -899,7 +896,7 @@ static const struct proto_ops llcp_sock_ops = {
.socketpair = sock_no_socketpair,
.accept = llcp_sock_accept,
.getname = llcp_sock_getname,
- .poll = llcp_sock_poll,
+ .poll_mask = llcp_sock_poll_mask,
.ioctl = sock_no_ioctl,
.listen = llcp_sock_listen,
.shutdown = sock_no_shutdown,
@@ -919,7 +916,7 @@ static const struct proto_ops llcp_rawsock_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = llcp_sock_getname,
- .poll = llcp_sock_poll,
+ .poll_mask = llcp_sock_poll_mask,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
--
2.17.0
--
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 25/32] net/phonet: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
net/phonet/socket.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index 9ecf02def928..ea2bfc3aafb9 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -340,15 +340,12 @@ static int pn_socket_getname(struct socket *sock, struct sockaddr *addr,
return sizeof(struct sockaddr_pn);
}
-static __poll_t pn_socket_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static __poll_t pn_socket_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
struct pep_sock *pn = pep_sk(sk);
__poll_t mask = 0;
- poll_wait(file, sk_sleep(sk), wait);
-
if (sk->sk_state == TCP_CLOSE)
return EPOLLERR;
if (!skb_queue_empty(&sk->sk_receive_queue))
@@ -473,7 +470,7 @@ const struct proto_ops phonet_stream_ops = {
.socketpair = sock_no_socketpair,
.accept = pn_socket_accept,
.getname = pn_socket_getname,
- .poll = pn_socket_poll,
+ .poll_mask = pn_socket_poll_mask,
.ioctl = pn_socket_ioctl,
.listen = pn_socket_listen,
.shutdown = sock_no_shutdown,
--
2.17.0
^ permalink raw reply related
* [PATCH 26/32] net/iucv: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
include/net/iucv/af_iucv.h | 2 --
net/iucv/af_iucv.c | 7 ++-----
2 files changed, 2 insertions(+), 7 deletions(-)
diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h
index f4c21b5a1242..b0eaeb02d46d 100644
--- a/include/net/iucv/af_iucv.h
+++ b/include/net/iucv/af_iucv.h
@@ -153,8 +153,6 @@ struct iucv_sock_list {
atomic_t autobind_name;
};
-__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
- poll_table *wait);
void iucv_sock_link(struct iucv_sock_list *l, struct sock *s);
void iucv_sock_unlink(struct iucv_sock_list *l, struct sock *s);
void iucv_accept_enqueue(struct sock *parent, struct sock *sk);
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 893a022f9620..68e86257a549 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1488,14 +1488,11 @@ static inline __poll_t iucv_accept_poll(struct sock *parent)
return 0;
}
-__poll_t iucv_sock_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static __poll_t iucv_sock_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
__poll_t mask = 0;
- sock_poll_wait(file, sk_sleep(sk), wait);
-
if (sk->sk_state == IUCV_LISTEN)
return iucv_accept_poll(sk);
@@ -2388,7 +2385,7 @@ static const struct proto_ops iucv_sock_ops = {
.getname = iucv_sock_getname,
.sendmsg = iucv_sock_sendmsg,
.recvmsg = iucv_sock_recvmsg,
- .poll = iucv_sock_poll,
+ .poll_mask = iucv_sock_poll_mask,
.ioctl = sock_no_ioctl,
.mmap = sock_no_mmap,
.socketpair = sock_no_socketpair,
--
2.17.0
^ permalink raw reply related
* [PATCH 27/32] net/rxrpc: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
net/rxrpc/af_rxrpc.c | 10 +++-------
1 file changed, 3 insertions(+), 7 deletions(-)
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 9a2c8e7c000e..6b170f2e47f2 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -734,15 +734,11 @@ static int rxrpc_getsockopt(struct socket *sock, int level, int optname,
/*
* permit an RxRPC socket to be polled
*/
-static __poll_t rxrpc_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+static __poll_t rxrpc_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
struct rxrpc_sock *rx = rxrpc_sk(sk);
- __poll_t mask;
-
- sock_poll_wait(file, sk_sleep(sk), wait);
- mask = 0;
+ __poll_t mask = 0;
/* the socket is readable if there are any messages waiting on the Rx
* queue */
@@ -949,7 +945,7 @@ static const struct proto_ops rxrpc_rpc_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = sock_no_getname,
- .poll = rxrpc_poll,
+ .poll_mask = rxrpc_poll_mask,
.ioctl = sock_no_ioctl,
.listen = rxrpc_listen,
.shutdown = rxrpc_shutdown,
--
2.17.0
^ permalink raw reply related
* [PATCH 28/32] crypto: af_alg: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:07 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
crypto/af_alg.c | 13 +++----------
crypto/algif_aead.c | 4 ++--
crypto/algif_skcipher.c | 4 ++--
include/crypto/if_alg.h | 3 +--
4 files changed, 8 insertions(+), 16 deletions(-)
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 80838c1cef94..89ed613c017e 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -1060,19 +1060,12 @@ void af_alg_async_cb(struct crypto_async_request *_req, int err)
}
EXPORT_SYMBOL_GPL(af_alg_async_cb);
-/**
- * af_alg_poll - poll system call handler
- */
-__poll_t af_alg_poll(struct file *file, struct socket *sock,
- poll_table *wait)
+__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events)
{
struct sock *sk = sock->sk;
struct alg_sock *ask = alg_sk(sk);
struct af_alg_ctx *ctx = ask->private;
- __poll_t mask;
-
- sock_poll_wait(file, sk_sleep(sk), wait);
- mask = 0;
+ __poll_t mask = 0;
if (!ctx->more || ctx->used)
mask |= EPOLLIN | EPOLLRDNORM;
@@ -1082,7 +1075,7 @@ __poll_t af_alg_poll(struct file *file, struct socket *sock,
return mask;
}
-EXPORT_SYMBOL_GPL(af_alg_poll);
+EXPORT_SYMBOL_GPL(af_alg_poll_mask);
/**
* af_alg_alloc_areq - allocate struct af_alg_async_req
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 4b07edd5a9ff..330cf9f2b767 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -375,7 +375,7 @@ static struct proto_ops algif_aead_ops = {
.sendmsg = aead_sendmsg,
.sendpage = af_alg_sendpage,
.recvmsg = aead_recvmsg,
- .poll = af_alg_poll,
+ .poll_mask = af_alg_poll_mask,
};
static int aead_check_key(struct socket *sock)
@@ -471,7 +471,7 @@ static struct proto_ops algif_aead_ops_nokey = {
.sendmsg = aead_sendmsg_nokey,
.sendpage = aead_sendpage_nokey,
.recvmsg = aead_recvmsg_nokey,
- .poll = af_alg_poll,
+ .poll_mask = af_alg_poll_mask,
};
static void *aead_bind(const char *name, u32 type, u32 mask)
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index c4e885df4564..15cf3c5222e0 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -205,7 +205,7 @@ static struct proto_ops algif_skcipher_ops = {
.sendmsg = skcipher_sendmsg,
.sendpage = af_alg_sendpage,
.recvmsg = skcipher_recvmsg,
- .poll = af_alg_poll,
+ .poll_mask = af_alg_poll_mask,
};
static int skcipher_check_key(struct socket *sock)
@@ -301,7 +301,7 @@ static struct proto_ops algif_skcipher_ops_nokey = {
.sendmsg = skcipher_sendmsg_nokey,
.sendpage = skcipher_sendpage_nokey,
.recvmsg = skcipher_recvmsg_nokey,
- .poll = af_alg_poll,
+ .poll_mask = af_alg_poll_mask,
};
static void *skcipher_bind(const char *name, u32 type, u32 mask)
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index 482461d8931d..cc414db9da0a 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -245,8 +245,7 @@ ssize_t af_alg_sendpage(struct socket *sock, struct page *page,
int offset, size_t size, int flags);
void af_alg_free_resources(struct af_alg_async_req *areq);
void af_alg_async_cb(struct crypto_async_request *_req, int err);
-__poll_t af_alg_poll(struct file *file, struct socket *sock,
- poll_table *wait);
+__poll_t af_alg_poll_mask(struct socket *sock, __poll_t events);
struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk,
unsigned int areqlen);
int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags,
--
2.17.0
^ permalink raw reply related
* [PATCH 29/32] pipe: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:08 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
fs/pipe.c | 22 +++++++++++++---------
1 file changed, 13 insertions(+), 9 deletions(-)
diff --git a/fs/pipe.c b/fs/pipe.c
index 39d6f431da83..bb0840e234f3 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -509,19 +509,22 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
}
}
-/* No kernel lock held - fine */
-static __poll_t
-pipe_poll(struct file *filp, poll_table *wait)
+static struct wait_queue_head *
+pipe_get_poll_head(struct file *filp, __poll_t events)
{
- __poll_t mask;
struct pipe_inode_info *pipe = filp->private_data;
- int nrbufs;
- poll_wait(filp, &pipe->wait, wait);
+ return &pipe->wait;
+}
+
+/* No kernel lock held - fine */
+static __poll_t pipe_poll_mask(struct file *filp, __poll_t events)
+{
+ struct pipe_inode_info *pipe = filp->private_data;
+ int nrbufs = pipe->nrbufs;
+ __poll_t mask = 0;
/* Reading only -- no need for acquiring the semaphore. */
- nrbufs = pipe->nrbufs;
- mask = 0;
if (filp->f_mode & FMODE_READ) {
mask = (nrbufs > 0) ? EPOLLIN | EPOLLRDNORM : 0;
if (!pipe->writers && filp->f_version != pipe->w_counter)
@@ -1020,7 +1023,8 @@ const struct file_operations pipefifo_fops = {
.llseek = no_llseek,
.read_iter = pipe_read,
.write_iter = pipe_write,
- .poll = pipe_poll,
+ .get_poll_head = pipe_get_poll_head,
+ .poll_mask = pipe_poll_mask,
.unlocked_ioctl = pipe_ioctl,
.release = pipe_release,
.fasync = pipe_fasync,
--
2.17.0
--
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 30/32] eventfd: switch to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:08 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
fs/eventfd.c | 15 +++++++++++----
1 file changed, 11 insertions(+), 4 deletions(-)
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 08d3bd602f73..61c9514da5e9 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -101,14 +101,20 @@ static int eventfd_release(struct inode *inode, struct file *file)
return 0;
}
-static __poll_t eventfd_poll(struct file *file, poll_table *wait)
+static struct wait_queue_head *
+eventfd_get_poll_head(struct file *file, __poll_t events)
+{
+ struct eventfd_ctx *ctx = file->private_data;
+
+ return &ctx->wqh;
+}
+
+static __poll_t eventfd_poll_mask(struct file *file, __poll_t eventmask)
{
struct eventfd_ctx *ctx = file->private_data;
__poll_t events = 0;
u64 count;
- poll_wait(file, &ctx->wqh, wait);
-
/*
* All writes to ctx->count occur within ctx->wqh.lock. This read
* can be done outside ctx->wqh.lock because we know that poll_wait
@@ -305,7 +311,8 @@ static const struct file_operations eventfd_fops = {
.show_fdinfo = eventfd_show_fdinfo,
#endif
.release = eventfd_release,
- .poll = eventfd_poll,
+ .get_poll_head = eventfd_get_poll_head,
+ .poll_mask = eventfd_poll_mask,
.read = eventfd_read,
.write = eventfd_write,
.llseek = noop_llseek,
--
2.17.0
--
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 31/32] timerfd: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:08 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
fs/timerfd.c | 22 +++++++++++-----------
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git a/fs/timerfd.c b/fs/timerfd.c
index cdad49da3ff7..d84a2bee4f82 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -226,21 +226,20 @@ static int timerfd_release(struct inode *inode, struct file *file)
kfree_rcu(ctx, rcu);
return 0;
}
-
-static __poll_t timerfd_poll(struct file *file, poll_table *wait)
+
+static struct wait_queue_head *timerfd_get_poll_head(struct file *file,
+ __poll_t eventmask)
{
struct timerfd_ctx *ctx = file->private_data;
- __poll_t events = 0;
- unsigned long flags;
- poll_wait(file, &ctx->wqh, wait);
+ return &ctx->wqh;
+}
- spin_lock_irqsave(&ctx->wqh.lock, flags);
- if (ctx->ticks)
- events |= EPOLLIN;
- spin_unlock_irqrestore(&ctx->wqh.lock, flags);
+static __poll_t timerfd_poll_mask(struct file *file, __poll_t eventmask)
+{
+ struct timerfd_ctx *ctx = file->private_data;
- return events;
+ return ctx->ticks ? EPOLLIN : 0;
}
static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
@@ -364,7 +363,8 @@ static long timerfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg
static const struct file_operations timerfd_fops = {
.release = timerfd_release,
- .poll = timerfd_poll,
+ .get_poll_head = timerfd_get_poll_head,
+ .poll_mask = timerfd_poll_mask,
.read = timerfd_read,
.llseek = noop_llseek,
.show_fdinfo = timerfd_show,
--
2.17.0
--
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 32/32] random: convert to ->poll_mask
From: Christoph Hellwig @ 2018-05-11 11:08 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180511110803.10910-1-hch@lst.de>
The big change is that random_read_wait and random_write_wait are merged
into a single waitqueue that uses keyed wakeups. Because wait_event_*
doesn't know about that this will lead to occassional spurious wakeups
in _random_read and add_hwgenerator_randomness, but wait_event_* is
designed to handle these and were are not in a a hot path there.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/char/random.c | 29 ++++++++++++++++-------------
1 file changed, 16 insertions(+), 13 deletions(-)
diff --git a/drivers/char/random.c b/drivers/char/random.c
index cd888d4ee605..a8fb0020ba5c 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -402,8 +402,7 @@ static struct poolinfo {
/*
* Static global variables
*/
-static DECLARE_WAIT_QUEUE_HEAD(random_read_wait);
-static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
+static DECLARE_WAIT_QUEUE_HEAD(random_wait);
static struct fasync_struct *fasync;
static DEFINE_SPINLOCK(random_ready_list_lock);
@@ -722,8 +721,8 @@ static void credit_entropy_bits(struct entropy_store *r, int nbits)
/* should we wake readers? */
if (entropy_bits >= random_read_wakeup_bits &&
- wq_has_sleeper(&random_read_wait)) {
- wake_up_interruptible(&random_read_wait);
+ wq_has_sleeper(&random_wait)) {
+ wake_up_interruptible_poll(&random_wait, POLLIN);
kill_fasync(&fasync, SIGIO, POLL_IN);
}
/* If the input pool is getting full, send some
@@ -1397,7 +1396,7 @@ static size_t account(struct entropy_store *r, size_t nbytes, int min,
trace_debit_entropy(r->name, 8 * ibytes);
if (ibytes &&
(r->entropy_count >> ENTROPY_SHIFT) < random_write_wakeup_bits) {
- wake_up_interruptible(&random_write_wait);
+ wake_up_interruptible_poll(&random_wait, POLLOUT);
kill_fasync(&fasync, SIGIO, POLL_OUT);
}
@@ -1839,7 +1838,7 @@ _random_read(int nonblock, char __user *buf, size_t nbytes)
if (nonblock)
return -EAGAIN;
- wait_event_interruptible(random_read_wait,
+ wait_event_interruptible(random_wait,
ENTROPY_BITS(&input_pool) >=
random_read_wakeup_bits);
if (signal_pending(current))
@@ -1876,14 +1875,17 @@ urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
return ret;
}
+static struct wait_queue_head *
+random_get_poll_head(struct file *file, __poll_t events)
+{
+ return &random_wait;
+}
+
static __poll_t
-random_poll(struct file *file, poll_table * wait)
+random_poll_mask(struct file *file, __poll_t events)
{
- __poll_t mask;
+ __poll_t mask = 0;
- poll_wait(file, &random_read_wait, wait);
- poll_wait(file, &random_write_wait, wait);
- mask = 0;
if (ENTROPY_BITS(&input_pool) >= random_read_wakeup_bits)
mask |= EPOLLIN | EPOLLRDNORM;
if (ENTROPY_BITS(&input_pool) < random_write_wakeup_bits)
@@ -1990,7 +1992,8 @@ static int random_fasync(int fd, struct file *filp, int on)
const struct file_operations random_fops = {
.read = random_read,
.write = random_write,
- .poll = random_poll,
+ .get_poll_head = random_get_poll_head,
+ .poll_mask = random_poll_mask,
.unlocked_ioctl = random_ioctl,
.fasync = random_fasync,
.llseek = noop_llseek,
@@ -2323,7 +2326,7 @@ void add_hwgenerator_randomness(const char *buffer, size_t count,
* We'll be woken up again once below random_write_wakeup_thresh,
* or when the calling thread is about to terminate.
*/
- wait_event_interruptible(random_write_wait, kthread_should_stop() ||
+ wait_event_interruptible(random_wait, kthread_should_stop() ||
ENTROPY_BITS(&input_pool) <= random_write_wakeup_bits);
mix_pool_bytes(poolp, buffer, count);
credit_entropy_bits(poolp, entropy);
--
2.17.0
--
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
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