* [PATCH 06/30] aio: simplify cancellation
From: Christoph Hellwig @ 2018-03-28 7:29 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180328072926.17131-1-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 | 34 ++--------------------------------
1 file changed, 2 insertions(+), 32 deletions(-)
diff --git a/fs/aio.c b/fs/aio.c
index 0df07d399a05..c36eec8b0879 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -162,19 +162,6 @@ 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;
@@ -574,23 +561,8 @@ 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);
+ list_del_init(&kiocb->ki_list);
+ return kiocb->ki_cancel(&kiocb->rw);
}
static void free_ioctx(struct work_struct *work)
@@ -633,8 +605,6 @@ 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);
}
--
2.14.2
--
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 05/30] fs: introduce new ->get_poll_head and ->poll_mask methods
From: Christoph Hellwig @ 2018-03-28 7:29 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180328072926.17131-1-hch@lst.de>
->get_poll_head returns the waitqueue that the poll operation is going
to sleep on. Note that this means we can only use a single waitqueue
for the poll, unlike some current drivers that use two waitqueues for
different events. But now that we have keyed wakeups and heavily use
those for poll there aren't that many good reason left to keep the
multiple waitqueues, and if there are any ->poll is still around, the
driver just won't support aio poll.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
---
Documentation/filesystems/Locking | 7 ++++++-
Documentation/filesystems/vfs.txt | 13 +++++++++++++
fs/select.c | 28 ++++++++++++++++++++++++++++
include/linux/fs.h | 2 ++
include/linux/poll.h | 27 +++++++++++++++++++++++----
5 files changed, 72 insertions(+), 5 deletions(-)
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 220bba28f72b..6d227f9d7bd9 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -440,6 +440,8 @@ prototypes:
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
int (*iterate) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
+ struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
+ __poll_t (*poll_mask) (struct file *, __poll_t);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
@@ -470,7 +472,7 @@ prototypes:
};
locking rules:
- All may block.
+ All except for ->poll_mask may block.
->llseek() locking has moved from llseek to the individual llseek
implementations. If your fs is not using generic_file_llseek, you
@@ -498,6 +500,9 @@ in sys_read() and friends.
the lease within the individual filesystem to record the result of the
operation
+->poll_mask can be called with or without the waitqueue lock for the waitqueue
+returned from ->get_poll_head.
+
--------------------------- dquot_operations -------------------------------
prototypes:
int (*write_dquot) (struct dquot *);
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index f608180ad59d..50ee13563271 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -857,6 +857,8 @@ struct file_operations {
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
int (*iterate) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
+ struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
+ __poll_t (*poll_mask) (struct file *, __poll_t);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
@@ -901,6 +903,17 @@ otherwise noted.
activity on this file and (optionally) go to sleep until there
is activity. Called by the select(2) and poll(2) system calls
+ get_poll_head: Returns the struct wait_queue_head that poll, select,
+ epoll or aio poll should wait on in case this instance only has single
+ waitqueue. Can return NULL to indicate polling is not supported,
+ or a POLL* value using the POLL_TO_PTR helper in case a grave error
+ occured and ->poll_mask shall not be called.
+
+ poll_mask: return the mask of POLL* values describing the file descriptor
+ state. Called either before going to sleep on the waitqueue returned by
+ get_poll_head, or after it has been woken. If ->get_poll_head and
+ ->poll_mask are implemented ->poll does not need to be implement.
+
unlocked_ioctl: called by the ioctl(2) system call.
compat_ioctl: called by the ioctl(2) system call when 32 bit system calls
diff --git a/fs/select.c b/fs/select.c
index ba91103707ea..cc270d7f6192 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -34,6 +34,34 @@
#include <linux/uaccess.h>
+__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
+{
+ unsigned int events = poll_requested_events(pt);
+ struct wait_queue_head *head;
+
+ if (unlikely(!file_can_poll(file)))
+ return DEFAULT_POLLMASK;
+
+ if (file->f_op->poll)
+ return file->f_op->poll(file, pt);
+
+ /*
+ * Only get the poll head and do the first mask check if we are actually
+ * going to sleep on this file:
+ */
+ if (pt && pt->_qproc) {
+ head = vfs_get_poll_head(file, events);
+ if (!head)
+ return DEFAULT_POLLMASK;
+ if (IS_ERR(head))
+ return PTR_TO_POLL(head);
+
+ pt->_qproc(file, head, pt);
+ }
+
+ return file->f_op->poll_mask(file, events);
+}
+EXPORT_SYMBOL_GPL(vfs_poll);
/*
* Estimate expected accuracy in ns from a timeval.
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 79c413985305..6ea2c0843bb1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1708,6 +1708,8 @@ struct file_operations {
int (*iterate) (struct file *, struct dir_context *);
int (*iterate_shared) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
+ struct wait_queue_head * (*get_poll_head)(struct file *, __poll_t);
+ __poll_t (*poll_mask) (struct file *, __poll_t);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
diff --git a/include/linux/poll.h b/include/linux/poll.h
index 7e0fdcf905d2..42e8e8665fb0 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -74,18 +74,37 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
pt->_key = ~(__poll_t)0; /* all events enabled */
}
+/*
+ * ->get_poll_head can return a __poll_t in the PTR_ERR, use these macros
+ * to return the value and recover it. It takes care of the negation as
+ * well as off the annotations.
+ */
+#define POLL_TO_PTR(mask) (ERR_PTR(-(__force int)(mask)))
+#define PTR_TO_POLL(ptr) ((__force __poll_t)-PTR_ERR((ptr)))
+
static inline bool file_can_poll(struct file *file)
{
- return file->f_op->poll;
+ return file->f_op->poll ||
+ (file->f_op->get_poll_head && file->f_op->poll_mask);
}
-static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
+static inline struct wait_queue_head *vfs_get_poll_head(struct file *file,
+ __poll_t events)
{
- if (unlikely(!file->f_op->poll))
+ if (unlikely(!file->f_op->get_poll_head || !file->f_op->poll_mask))
+ return NULL;
+ return file->f_op->get_poll_head(file, events);
+}
+
+static inline __poll_t vfs_poll_mask(struct file *file, __poll_t events)
+{
+ if (unlikely(!file->f_op->poll_mask))
return DEFAULT_POLLMASK;
- return file->f_op->poll(file, pt);
+ return file->f_op->poll_mask(file, events) & events;
}
+__poll_t vfs_poll(struct file *file, struct poll_table_struct *pt);
+
struct poll_table_entry {
struct file *filp;
__poll_t key;
--
2.14.2
--
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 04/30] fs: add new vfs_poll and file_can_poll helpers
From: Christoph Hellwig @ 2018-03-28 7:29 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180328072926.17131-1-hch@lst.de>
These abstract out calls to the poll method in preparation for changes
in how we poll.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
---
drivers/staging/comedi/drivers/serial2002.c | 4 ++--
drivers/vfio/virqfd.c | 2 +-
drivers/vhost/vhost.c | 2 +-
fs/eventpoll.c | 5 ++---
fs/select.c | 23 ++++++++---------------
include/linux/poll.h | 12 ++++++++++++
mm/memcontrol.c | 2 +-
net/9p/trans_fd.c | 18 ++++--------------
virt/kvm/eventfd.c | 2 +-
9 files changed, 32 insertions(+), 38 deletions(-)
diff --git a/drivers/staging/comedi/drivers/serial2002.c b/drivers/staging/comedi/drivers/serial2002.c
index b3f3b4a201af..5471b2212a62 100644
--- a/drivers/staging/comedi/drivers/serial2002.c
+++ b/drivers/staging/comedi/drivers/serial2002.c
@@ -113,7 +113,7 @@ static void serial2002_tty_read_poll_wait(struct file *f, int timeout)
long elapsed;
__poll_t mask;
- mask = f->f_op->poll(f, &table.pt);
+ mask = vfs_poll(f, &table.pt);
if (mask & (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN |
EPOLLHUP | EPOLLERR)) {
break;
@@ -136,7 +136,7 @@ static int serial2002_tty_read(struct file *f, int timeout)
result = -1;
if (!IS_ERR(f)) {
- if (f->f_op->poll) {
+ if (file_can_poll(f)) {
serial2002_tty_read_poll_wait(f, timeout);
if (kernel_read(f, &ch, 1, &pos) == 1)
diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c
index 085700f1be10..2a1be859ee71 100644
--- a/drivers/vfio/virqfd.c
+++ b/drivers/vfio/virqfd.c
@@ -166,7 +166,7 @@ int vfio_virqfd_enable(void *opaque,
init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup);
init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc);
- events = irqfd.file->f_op->poll(irqfd.file, &virqfd->pt);
+ events = vfs_poll(irqfd.file, &virqfd->pt);
/*
* Check if there was an event already pending on the eventfd
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 1b3e8d2d5c8b..4d27e288bb1d 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -208,7 +208,7 @@ int vhost_poll_start(struct vhost_poll *poll, struct file *file)
if (poll->wqh)
return 0;
- mask = file->f_op->poll(file, &poll->table);
+ mask = vfs_poll(file, &poll->table);
if (mask)
vhost_poll_wakeup(&poll->wait, 0, 0, poll_to_key(mask));
if (mask & EPOLLERR) {
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 0f3494ed3ed0..2bebae5a38cf 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -884,8 +884,7 @@ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt,
pt->_key = epi->event.events;
if (!is_file_epoll(epi->ffd.file))
- return epi->ffd.file->f_op->poll(epi->ffd.file, pt) &
- epi->event.events;
+ return vfs_poll(epi->ffd.file, pt) & epi->event.events;
ep = epi->ffd.file->private_data;
poll_wait(epi->ffd.file, &ep->poll_wait, pt);
@@ -2020,7 +2019,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
/* The target file descriptor must support poll */
error = -EPERM;
- if (!tf.file->f_op->poll)
+ if (!file_can_poll(tf.file))
goto error_tgt_fput;
/* Check if EPOLLWAKEUP is allowed */
diff --git a/fs/select.c b/fs/select.c
index c6c504a814f9..ba91103707ea 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -502,14 +502,10 @@ static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
continue;
f = fdget(i);
if (f.file) {
- const struct file_operations *f_op;
- f_op = f.file->f_op;
- mask = DEFAULT_POLLMASK;
- if (f_op->poll) {
- wait_key_set(wait, in, out,
- bit, busy_flag);
- mask = (*f_op->poll)(f.file, wait);
- }
+ wait_key_set(wait, in, out, bit,
+ busy_flag);
+ mask = vfs_poll(f.file, wait);
+
fdput(f);
if ((mask & POLLIN_SET) && (in & bit)) {
res_in |= bit;
@@ -819,13 +815,10 @@ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait,
/* userland u16 ->events contains POLL... bitmap */
filter = demangle_poll(pollfd->events) | EPOLLERR | EPOLLHUP;
- mask = DEFAULT_POLLMASK;
- if (f.file->f_op->poll) {
- pwait->_key = filter | busy_flag;
- mask = f.file->f_op->poll(f.file, pwait);
- if (mask & busy_flag)
- *can_busy_poll = true;
- }
+ pwait->_key = filter | busy_flag;
+ mask = vfs_poll(f.file, pwait);
+ if (mask & busy_flag)
+ *can_busy_poll = true;
mask &= filter; /* Mask out unneeded events. */
fdput(f);
diff --git a/include/linux/poll.h b/include/linux/poll.h
index a3576da63377..7e0fdcf905d2 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -74,6 +74,18 @@ static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
pt->_key = ~(__poll_t)0; /* all events enabled */
}
+static inline bool file_can_poll(struct file *file)
+{
+ return file->f_op->poll;
+}
+
+static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt)
+{
+ if (unlikely(!file->f_op->poll))
+ return DEFAULT_POLLMASK;
+ return file->f_op->poll(file, pt);
+}
+
struct poll_table_entry {
struct file *filp;
__poll_t key;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 670e99b68aa6..8774ece5c3c3 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3849,7 +3849,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
if (ret)
goto out_put_css;
- efile.file->f_op->poll(efile.file, &event->pt);
+ vfs_poll(efile.file, &event->pt);
spin_lock(&memcg->event_list_lock);
list_add(&event->list, &memcg->event_list);
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 0cfba919d167..3811775692d0 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -231,7 +231,7 @@ static void p9_conn_cancel(struct p9_conn *m, int err)
static __poll_t
p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt, int *err)
{
- __poll_t ret, n;
+ __poll_t ret;
struct p9_trans_fd *ts = NULL;
if (client && client->status == Connected)
@@ -243,19 +243,9 @@ p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt, int *err)
return EPOLLERR;
}
- if (!ts->rd->f_op->poll)
- ret = DEFAULT_POLLMASK;
- else
- ret = ts->rd->f_op->poll(ts->rd, pt);
-
- if (ts->rd != ts->wr) {
- if (!ts->wr->f_op->poll)
- n = DEFAULT_POLLMASK;
- else
- n = ts->wr->f_op->poll(ts->wr, pt);
- ret = (ret & ~EPOLLOUT) | (n & ~EPOLLIN);
- }
-
+ ret = vfs_poll(ts->rd, pt);
+ if (ts->rd != ts->wr)
+ ret = (ret & ~EPOLLOUT) | (vfs_poll(ts->wr, pt) & ~EPOLLIN);
return ret;
}
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 6e865e8b5b10..90d30fbe95ae 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -397,7 +397,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
* Check if there was an event already pending on the eventfd
* before we registered, and trigger it as if we didn't miss it.
*/
- events = f.file->f_op->poll(f.file, &irqfd->pt);
+ events = vfs_poll(f.file, &irqfd->pt);
if (events & EPOLLIN)
schedule_work(&irqfd->inject);
--
2.14.2
--
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 03/30] fs: update documentation to mention __poll_t and match the code
From: Christoph Hellwig @ 2018-03-28 7:28 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180328072926.17131-1-hch@lst.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
Documentation/filesystems/Locking | 2 +-
Documentation/filesystems/vfs.txt | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 75d2d57e2c44..220bba28f72b 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -439,7 +439,7 @@ prototypes:
ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
int (*iterate) (struct file *, struct dir_context *);
- unsigned int (*poll) (struct file *, struct poll_table_struct *);
+ __poll_t (*poll) (struct file *, struct poll_table_struct *);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 5fd325df59e2..f608180ad59d 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -856,7 +856,7 @@ struct file_operations {
ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
int (*iterate) (struct file *, struct dir_context *);
- unsigned int (*poll) (struct file *, struct poll_table_struct *);
+ __poll_t (*poll) (struct file *, struct poll_table_struct *);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
--
2.14.2
--
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 02/30] fs: cleanup do_pollfd
From: Christoph Hellwig @ 2018-03-28 7:28 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180328072926.17131-1-hch@lst.de>
Use straightline code with failure handling gotos instead of a lot
of nested conditionals.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
---
fs/select.c | 48 +++++++++++++++++++++++-------------------------
1 file changed, 23 insertions(+), 25 deletions(-)
diff --git a/fs/select.c b/fs/select.c
index 686de7b3a1db..c6c504a814f9 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -806,34 +806,32 @@ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait,
bool *can_busy_poll,
__poll_t busy_flag)
{
- __poll_t mask;
- int fd;
-
- mask = 0;
- fd = pollfd->fd;
- if (fd >= 0) {
- struct fd f = fdget(fd);
- mask = EPOLLNVAL;
- if (f.file) {
- /* userland u16 ->events contains POLL... bitmap */
- __poll_t filter = demangle_poll(pollfd->events) |
- EPOLLERR | EPOLLHUP;
- mask = DEFAULT_POLLMASK;
- if (f.file->f_op->poll) {
- pwait->_key = filter;
- pwait->_key |= busy_flag;
- mask = f.file->f_op->poll(f.file, pwait);
- if (mask & busy_flag)
- *can_busy_poll = true;
- }
- /* Mask out unneeded events. */
- mask &= filter;
- fdput(f);
- }
+ int fd = pollfd->fd;
+ __poll_t mask = 0, filter;
+ struct fd f;
+
+ if (fd < 0)
+ goto out;
+ mask = EPOLLNVAL;
+ f = fdget(fd);
+ if (!f.file)
+ goto out;
+
+ /* userland u16 ->events contains POLL... bitmap */
+ filter = demangle_poll(pollfd->events) | EPOLLERR | EPOLLHUP;
+ mask = DEFAULT_POLLMASK;
+ if (f.file->f_op->poll) {
+ pwait->_key = filter | busy_flag;
+ mask = f.file->f_op->poll(f.file, pwait);
+ if (mask & busy_flag)
+ *can_busy_poll = true;
}
+ mask &= filter; /* Mask out unneeded events. */
+ fdput(f);
+
+out:
/* ... and so does ->revents */
pollfd->revents = mangle_poll(mask);
-
return mask;
}
--
2.14.2
--
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 01/30] fs: unexport poll_schedule_timeout
From: Christoph Hellwig @ 2018-03-28 7:28 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
In-Reply-To: <20180328072926.17131-1-hch@lst.de>
No users outside of select.c.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
---
fs/select.c | 3 +--
include/linux/poll.h | 2 --
2 files changed, 1 insertion(+), 4 deletions(-)
diff --git a/fs/select.c b/fs/select.c
index b6c36254028a..686de7b3a1db 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -233,7 +233,7 @@ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
add_wait_queue(wait_address, &entry->wait);
}
-int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
+static int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
ktime_t *expires, unsigned long slack)
{
int rc = -EINTR;
@@ -258,7 +258,6 @@ int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
return rc;
}
-EXPORT_SYMBOL(poll_schedule_timeout);
/**
* poll_select_set_timeout - helper function to setup the timeout value
diff --git a/include/linux/poll.h b/include/linux/poll.h
index f45ebd017eaa..a3576da63377 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -96,8 +96,6 @@ struct poll_wqueues {
extern void poll_initwait(struct poll_wqueues *pwq);
extern void poll_freewait(struct poll_wqueues *pwq);
-extern int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
- ktime_t *expires, unsigned long slack);
extern u64 select_estimate_accuracy(struct timespec64 *tv);
#define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1)
--
2.14.2
--
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
* aio poll and a new in-kernel poll API V7
From: Christoph Hellwig @ 2018-03-28 7:28 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, netdev, linux-api,
linux-kernel
Hi all,
this series adds support for the IOCB_CMD_POLL operation to poll for the
readyness of file descriptors using the aio subsystem. The API is based
on patches that existed in RHAS2.1 and RHEL3, which means it already is
supported by libaio. To implement the poll support efficiently new
methods to poll are introduced in struct file_operations: get_poll_head
and poll_mask. The first one returns a wait_queue_head to wait on
(lifetime is bound by the file), and the second does a non-blocking
check for the POLL* events. This allows aio poll to work without
any additional context switches, unlike epoll.
This series sits on top of the aio-fsync series that also includes
support for io_pgetevents.
The changes were sponsored by Scylladb, and improve performance
of the seastar framework up to 10%, while also removing the need
for a privileged SCHED_FIFO epoll listener thread.
git://git.infradead.org/users/hch/vfs.git aio-poll.7
Gitweb:
http://git.infradead.org/users/hch/vfs.git/shortlog/refs/heads/aio-poll.7
Libaio changes:
https://pagure.io/libaio.git io-poll
Seastar changes (not updated for the new io_pgetevens ABI yet):
https://github.com/avikivity/seastar/commits/aio
Changes since V7:
- reworked cancellation
Changes since V6:
- small changelog updates
- rebased on top of the aio-fsync changes
Changes since V4:
- rebased ontop of Linux 4.16-rc4
Changes since V3:
- remove the pre-sleep ->poll_mask call in vfs_poll,
allow ->get_poll_head to return POLL* values.
Changes since V2:
- removed a double initialization
- new vfs_get_poll_head helper
- document that ->get_poll_head can return NULL
- call ->poll_mask before sleeping
- various ACKs
- add conversion of random to ->poll_mask
- add conversion of af_alg to ->poll_mask
- lacking ->poll_mask support now returns -EINVAL for IOCB_CMD_POLL
- reshuffled the series so that prep patches and everything not
requiring the new in-kernel poll API is in the beginning
Changes since V1:
- handle the NULL ->poll case in vfs_poll
- dropped the file argument to the ->poll_mask socket operation
- replace the ->pre_poll socket operation with ->get_poll_head as
in the file operations
--
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
* [PATCH 6/6] aio: implement io_pgetevents
From: Christoph Hellwig @ 2018-03-28 7:26 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, linux-api, linux-kernel
In-Reply-To: <20180328072639.16885-1-hch@lst.de>
This is the io_getevents equivalent of ppoll/pselect and allows to
properly mix signals and aio completions (especially with IOCB_CMD_POLL)
and atomically executes the following sequence:
sigset_t origmask;
pthread_sigmask(SIG_SETMASK, &sigmask, &origmask);
ret = io_getevents(ctx, min_nr, nr, events, timeout);
pthread_sigmask(SIG_SETMASK, &origmask, NULL);
Note that unlike many other signal related calls we do not pass a sigmask
size, as that would get us to 7 arguments, which aren't easily supported
by the syscall infrastructure. It seems a lot less painful to just add a
new syscall variant in the unlikely case we're going to increase the
sigset size.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
---
arch/x86/entry/syscalls/syscall_32.tbl | 1 +
arch/x86/entry/syscalls/syscall_64.tbl | 1 +
fs/aio.c | 114 ++++++++++++++++++++++++++++++---
include/linux/compat.h | 7 ++
include/linux/syscalls.h | 6 ++
include/uapi/asm-generic/unistd.h | 4 +-
include/uapi/linux/aio_abi.h | 6 ++
kernel/sys_ni.c | 2 +
8 files changed, 130 insertions(+), 11 deletions(-)
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 2a5e99cff859..c1018580ddaa 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -391,3 +391,4 @@
382 i386 pkey_free sys_pkey_free
383 i386 statx sys_statx
384 i386 arch_prctl sys_arch_prctl compat_sys_arch_prctl
+385 i386 io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 5aef183e2f85..e995cd2b4e65 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -339,6 +339,7 @@
330 common pkey_alloc sys_pkey_alloc
331 common pkey_free sys_pkey_free
332 common statx sys_statx
+333 common io_pgetevents sys_io_pgetevents
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/fs/aio.c b/fs/aio.c
index fd6c72918a8e..0df07d399a05 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1296,10 +1296,6 @@ static long read_events(struct kioctx *ctx, long min_nr, long nr,
wait_event_interruptible_hrtimeout(ctx->wait,
aio_read_events(ctx, min_nr, nr, event, &ret),
until);
-
- if (!ret && signal_pending(current))
- ret = -EINTR;
-
return ret;
}
@@ -1914,13 +1910,60 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id,
struct timespec __user *, timeout)
{
struct timespec64 ts;
+ int ret;
+
+ if (timeout && unlikely(get_timespec64(&ts, timeout)))
+ return -EFAULT;
+
+ ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+ if (!ret && signal_pending(current))
+ ret = -EINTR;
+ return ret;
+}
- if (timeout) {
- if (unlikely(get_timespec64(&ts, timeout)))
+SYSCALL_DEFINE6(io_pgetevents,
+ aio_context_t, ctx_id,
+ long, min_nr,
+ long, nr,
+ struct io_event __user *, events,
+ struct timespec __user *, timeout,
+ const struct __aio_sigset __user *, usig)
+{
+ struct __aio_sigset ksig = { NULL, };
+ sigset_t ksigmask, sigsaved;
+ struct timespec64 ts;
+ int ret;
+
+ if (timeout && unlikely(get_timespec64(&ts, timeout)))
+ return -EFAULT;
+
+ if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
+ return -EFAULT;
+
+ if (ksig.sigmask) {
+ if (ksig.sigsetsize != sizeof(sigset_t))
+ return -EINVAL;
+ if (copy_from_user(&ksigmask, ksig.sigmask, sizeof(ksigmask)))
return -EFAULT;
+ sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+ sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+ }
+
+ ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+ if (signal_pending(current)) {
+ if (ksig.sigmask) {
+ current->saved_sigmask = sigsaved;
+ set_restore_sigmask();
+ }
+
+ if (!ret)
+ ret = -ERESTARTNOHAND;
+ } else {
+ if (ksig.sigmask)
+ sigprocmask(SIG_SETMASK, &sigsaved, NULL);
}
- return do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
+ return ret;
}
#ifdef CONFIG_COMPAT
@@ -1931,13 +1974,64 @@ COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id,
struct compat_timespec __user *, timeout)
{
struct timespec64 t;
+ int ret;
+
+ if (timeout && compat_get_timespec64(&t, timeout))
+ return -EFAULT;
+
+ ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+ if (!ret && signal_pending(current))
+ ret = -EINTR;
+ return ret;
+}
+
- if (timeout) {
- if (compat_get_timespec64(&t, timeout))
+struct __compat_aio_sigset {
+ compat_sigset_t __user *sigmask;
+ compat_size_t sigsetsize;
+};
+
+COMPAT_SYSCALL_DEFINE6(io_pgetevents,
+ compat_aio_context_t, ctx_id,
+ compat_long_t, min_nr,
+ compat_long_t, nr,
+ struct io_event __user *, events,
+ struct compat_timespec __user *, timeout,
+ const struct __compat_aio_sigset __user *, usig)
+{
+ struct __compat_aio_sigset ksig = { NULL, };
+ sigset_t ksigmask, sigsaved;
+ struct timespec64 t;
+ int ret;
+
+ if (timeout && compat_get_timespec64(&t, timeout))
+ return -EFAULT;
+
+ if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
+ return -EFAULT;
+
+ if (ksig.sigmask) {
+ if (ksig.sigsetsize != sizeof(compat_sigset_t))
+ return -EINVAL;
+ if (get_compat_sigset(&ksigmask, ksig.sigmask))
return -EFAULT;
+ sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+ sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+ }
+ ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+ if (signal_pending(current)) {
+ if (ksig.sigmask) {
+ current->saved_sigmask = sigsaved;
+ set_restore_sigmask();
+ }
+ if (!ret)
+ ret = -ERESTARTNOHAND;
+ } else {
+ if (ksig.sigmask)
+ sigprocmask(SIG_SETMASK, &sigsaved, NULL);
}
- return do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
+ return ret;
}
#endif
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 16c3027074a2..d80cda61eafd 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -304,6 +304,7 @@ extern int put_compat_rusage(const struct rusage *,
struct compat_rusage __user *);
struct compat_siginfo;
+struct __compat_aio_sigset;
extern asmlinkage long compat_sys_waitid(int, compat_pid_t,
struct compat_siginfo __user *, int,
@@ -656,6 +657,12 @@ asmlinkage long compat_sys_io_getevents(compat_aio_context_t ctx_id,
compat_long_t nr,
struct io_event __user *events,
struct compat_timespec __user *timeout);
+asmlinkage long compat_sys_io_pgetevents(compat_aio_context_t ctx_id,
+ compat_long_t min_nr,
+ compat_long_t nr,
+ struct io_event __user *events,
+ struct compat_timespec __user *timeout,
+ const struct __compat_aio_sigset __user *usig);
asmlinkage long compat_sys_io_submit(compat_aio_context_t ctx_id, int nr,
u32 __user *iocb);
asmlinkage long compat_sys_mount(const char __user *dev_name,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a78186d826d7..8515ec53c81b 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -539,6 +539,12 @@ asmlinkage long sys_io_getevents(aio_context_t ctx_id,
long nr,
struct io_event __user *events,
struct timespec __user *timeout);
+asmlinkage long sys_io_pgetevents(aio_context_t ctx_id,
+ long min_nr,
+ long nr,
+ struct io_event __user *events,
+ struct timespec __user *timeout,
+ const struct __aio_sigset *sig);
asmlinkage long sys_io_submit(aio_context_t, long,
struct iocb __user * __user *);
asmlinkage long sys_io_cancel(aio_context_t ctx_id, struct iocb __user *iocb,
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 8b87de067bc7..ce2ebbeece10 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -732,9 +732,11 @@ __SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
__SYSCALL(__NR_pkey_free, sys_pkey_free)
#define __NR_statx 291
__SYSCALL(__NR_statx, sys_statx)
+#define __NR_io_pgetevents 292
+__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
#undef __NR_syscalls
-#define __NR_syscalls 292
+#define __NR_syscalls 293
/*
* All syscalls below here should go away really,
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index a04adbc70ddf..2c0a3415beee 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -29,6 +29,7 @@
#include <linux/types.h>
#include <linux/fs.h>
+#include <linux/signal.h>
#include <asm/byteorder.h>
typedef __kernel_ulong_t aio_context_t;
@@ -108,5 +109,10 @@ struct iocb {
#undef IFBIG
#undef IFLITTLE
+struct __aio_sigset {
+ sigset_t __user *sigmask;
+ size_t sigsetsize;
+};
+
#endif /* __LINUX__AIO_ABI_H */
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index b5189762d275..8f7705559b38 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -151,9 +151,11 @@ cond_syscall(sys_io_destroy);
cond_syscall(sys_io_submit);
cond_syscall(sys_io_cancel);
cond_syscall(sys_io_getevents);
+cond_syscall(sys_io_pgetevents);
cond_syscall(compat_sys_io_setup);
cond_syscall(compat_sys_io_submit);
cond_syscall(compat_sys_io_getevents);
+cond_syscall(compat_sys_io_pgetevents);
cond_syscall(sys_sysfs);
cond_syscall(sys_syslog);
cond_syscall(sys_process_vm_readv);
--
2.14.2
--
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 5/6] aio: implement IOCB_CMD_FSYNC and IOCB_CMD_FDSYNC
From: Christoph Hellwig @ 2018-03-28 7:26 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, linux-api, linux-kernel
In-Reply-To: <20180328072639.16885-1-hch@lst.de>
Simple workqueue offload for now, but prepared for adding a real aio_fsync
method if the need arises. Based on an earlier patch from Dave Chinner.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
---
fs/aio.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 50 insertions(+)
diff --git a/fs/aio.c b/fs/aio.c
index f35801d73e0b..fd6c72918a8e 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -156,6 +156,12 @@ struct kioctx {
unsigned id;
};
+struct fsync_iocb {
+ struct work_struct work;
+ struct file *file;
+ 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
@@ -172,6 +178,7 @@ struct kioctx {
struct aio_kiocb {
union {
struct kiocb rw;
+ struct fsync_iocb fsync;
};
struct kioctx *ki_ctx;
@@ -1565,6 +1572,43 @@ static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
return ret;
}
+static void aio_fsync_work(struct work_struct *work)
+{
+ struct fsync_iocb *req = container_of(work, struct fsync_iocb, work);
+ int ret;
+
+ ret = vfs_fsync(req->file, req->datasync);
+ fput(req->file);
+ aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0);
+}
+
+static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
+{
+ int ret;
+
+ if (iocb->aio_buf)
+ return -EINVAL;
+ if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)
+ return -EINVAL;
+
+ req->file = fget(iocb->aio_fildes);
+ if (unlikely(!req->file))
+ return -EBADF;
+
+ ret = -EINVAL;
+ if (!req->file->f_op->fsync)
+ goto out_fput;
+
+ req->datasync = datasync;
+ INIT_WORK(&req->work, aio_fsync_work);
+ schedule_work(&req->work);
+ return -EIOCBQUEUED;
+out_fput:
+ if (unlikely(ret && ret != -EIOCBQUEUED))
+ fput(req->file);
+ return ret;
+}
+
static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
struct iocb *iocb, bool compat)
{
@@ -1628,6 +1672,12 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
case IOCB_CMD_PWRITEV:
ret = aio_write(&req->rw, iocb, true, compat);
break;
+ case IOCB_CMD_FSYNC:
+ ret = aio_fsync(&req->fsync, iocb, false);
+ break;
+ case IOCB_CMD_FDSYNC:
+ ret = aio_fsync(&req->fsync, iocb, true);
+ break;
default:
pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
ret = -EINVAL;
--
2.14.2
--
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 4/6] aio: sanitize ki_list handling
From: Christoph Hellwig @ 2018-03-28 7:26 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, linux-api, linux-kernel
In-Reply-To: <20180328072639.16885-1-hch@lst.de>
Instead of handcoded non-null checks always initialize ki_list to an
empty list and use list_empty / list_empty_careful on it. While we're
at it also error out on a double call to kiocb_set_cancel_fn instead
of ignoring it.
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 | 13 ++++++-------
1 file changed, 6 insertions(+), 7 deletions(-)
diff --git a/fs/aio.c b/fs/aio.c
index 50c4a0554cc6..f35801d73e0b 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -555,13 +555,12 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
struct kioctx *ctx = req->ki_ctx;
unsigned long flags;
- spin_lock_irqsave(&ctx->ctx_lock, flags);
-
- if (!req->ki_list.next)
- list_add(&req->ki_list, &ctx->active_reqs);
+ 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);
@@ -1034,7 +1033,7 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
goto out_put;
percpu_ref_get(&ctx->reqs);
-
+ INIT_LIST_HEAD(&req->ki_list);
req->ki_ctx = ctx;
return req;
out_put:
@@ -1080,7 +1079,7 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
unsigned tail, pos, head;
unsigned long flags;
- if (iocb->ki_list.next) {
+ if (!list_empty_careful(&iocb->ki_list)) {
unsigned long flags;
spin_lock_irqsave(&ctx->ctx_lock, flags);
--
2.14.2
--
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 3/6] aio: refactor read/write iocb setup
From: Christoph Hellwig @ 2018-03-28 7:26 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, linux-api, linux-kernel
In-Reply-To: <20180328072639.16885-1-hch@lst.de>
Don't reference the kiocb structure from the common aio code, and move
any use of it into helper specific to the read/write path. This is in
preparation for aio_poll support that wants to use the space for different
fields.
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 | 167 ++++++++++++++++++++++++++++++++++++---------------------------
1 file changed, 95 insertions(+), 72 deletions(-)
diff --git a/fs/aio.c b/fs/aio.c
index f536b0f249d4..50c4a0554cc6 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -170,7 +170,9 @@ struct kioctx {
#define KIOCB_CANCELLED ((void *) (~0ULL))
struct aio_kiocb {
- struct kiocb common;
+ union {
+ struct kiocb rw;
+ };
struct kioctx *ki_ctx;
kiocb_cancel_fn *ki_cancel;
@@ -549,7 +551,7 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events)
void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel)
{
- struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, common);
+ struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw);
struct kioctx *ctx = req->ki_ctx;
unsigned long flags;
@@ -582,7 +584,7 @@ static int kiocb_cancel(struct aio_kiocb *kiocb)
cancel = cmpxchg(&kiocb->ki_cancel, old, KIOCB_CANCELLED);
} while (cancel != old);
- return cancel(&kiocb->common);
+ return cancel(&kiocb->rw);
}
static void free_ioctx(struct work_struct *work)
@@ -1040,15 +1042,6 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
return NULL;
}
-static void kiocb_free(struct aio_kiocb *req)
-{
- if (req->common.ki_filp)
- fput(req->common.ki_filp);
- if (req->ki_eventfd != NULL)
- eventfd_ctx_put(req->ki_eventfd);
- kmem_cache_free(kiocb_cachep, req);
-}
-
static struct kioctx *lookup_ioctx(unsigned long ctx_id)
{
struct aio_ring __user *ring = (void __user *)ctx_id;
@@ -1079,27 +1072,14 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
/* aio_complete
* Called when the io request on the given iocb is complete.
*/
-static void aio_complete(struct kiocb *kiocb, long res, long res2)
+static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
{
- struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, common);
struct kioctx *ctx = iocb->ki_ctx;
struct aio_ring *ring;
struct io_event *ev_page, *event;
unsigned tail, pos, head;
unsigned long flags;
- if (kiocb->ki_flags & IOCB_WRITE) {
- struct file *file = kiocb->ki_filp;
-
- /*
- * Tell lockdep we inherited freeze protection from submission
- * thread.
- */
- if (S_ISREG(file_inode(file)->i_mode))
- __sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE);
- file_end_write(file);
- }
-
if (iocb->ki_list.next) {
unsigned long flags;
@@ -1161,11 +1141,12 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
* eventfd. The eventfd_signal() function is safe to be called
* from IRQ context.
*/
- if (iocb->ki_eventfd != NULL)
+ if (iocb->ki_eventfd) {
eventfd_signal(iocb->ki_eventfd, 1);
+ eventfd_ctx_put(iocb->ki_eventfd);
+ }
- /* everything turned out well, dispose of the aiocb. */
- kiocb_free(iocb);
+ kmem_cache_free(kiocb_cachep, iocb);
/*
* We have to order our ring_info tail store above and test
@@ -1428,6 +1409,45 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
return -EINVAL;
}
+static void aio_complete_rw(struct kiocb *kiocb, long res, long res2)
+{
+ struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, rw);
+
+ 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);
+ }
+
+ fput(kiocb->ki_filp);
+ aio_complete(iocb, res, res2);
+}
+
+static int aio_prep_rw(struct kiocb *req, struct iocb *iocb)
+{
+ int ret;
+
+ req->ki_filp = fget(iocb->aio_fildes);
+ if (unlikely(!req->ki_filp))
+ return -EBADF;
+ req->ki_complete = aio_complete_rw;
+ req->ki_pos = iocb->aio_offset;
+ req->ki_flags = iocb_flags(req->ki_filp);
+ if (iocb->aio_flags & IOCB_FLAG_RESFD)
+ req->ki_flags |= IOCB_EVENTFD;
+ req->ki_hint = file_write_hint(req->ki_filp);
+ ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags);
+ if (unlikely(ret))
+ fput(req->ki_filp);
+ return ret;
+}
+
static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec,
bool vectored, bool compat, struct iov_iter *iter)
{
@@ -1447,7 +1467,7 @@ static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec,
return import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter);
}
-static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
+static inline ssize_t aio_rw_ret(struct kiocb *req, ssize_t ret)
{
switch (ret) {
case -EIOCBQUEUED:
@@ -1463,7 +1483,7 @@ static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
ret = -EINTR;
/*FALLTHRU*/
default:
- aio_complete(req, ret, 0);
+ aio_complete_rw(req, ret, 0);
return 0;
}
}
@@ -1471,56 +1491,78 @@ static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret)
static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored,
bool compat)
{
- struct file *file = req->ki_filp;
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct iov_iter iter;
+ struct file *file;
ssize_t ret;
+ ret = aio_prep_rw(req, iocb);
+ if (ret)
+ return ret;
+ file = req->ki_filp;
+
+ ret = -EBADF;
if (unlikely(!(file->f_mode & FMODE_READ)))
- return -EBADF;
+ goto out_fput;
+ ret = -EINVAL;
if (unlikely(!file->f_op->read_iter))
- return -EINVAL;
+ goto out_fput;
ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter);
if (ret)
- return ret;
+ goto out_fput;
ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter));
if (!ret)
- ret = aio_ret(req, call_read_iter(file, req, &iter));
+ ret = aio_rw_ret(req, call_read_iter(file, req, &iter));
kfree(iovec);
+out_fput:
+ if (unlikely(ret && ret != -EIOCBQUEUED))
+ fput(file);
return ret;
}
static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
bool compat)
{
- struct file *file = req->ki_filp;
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct iov_iter iter;
+ struct file *file;
ssize_t ret;
+ ret = aio_prep_rw(req, iocb);
+ if (ret)
+ return ret;
+ file = req->ki_filp;
+
+ ret = -EBADF;
if (unlikely(!(file->f_mode & FMODE_WRITE)))
- return -EBADF;
+ goto out_fput;
+ ret = -EINVAL;
if (unlikely(!file->f_op->write_iter))
- return -EINVAL;
+ goto out_fput;
ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter);
if (ret)
- return ret;
+ goto out_fput;
ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter));
if (!ret) {
+ struct inode *inode = file_inode(file);
+
req->ki_flags |= IOCB_WRITE;
file_start_write(file);
- ret = aio_ret(req, call_write_iter(file, req, &iter));
+ ret = aio_rw_ret(req, call_write_iter(file, req, &iter));
/*
- * We release freeze protection in aio_complete(). Fool lockdep
- * by telling it the lock got released so that it doesn't
- * complain about held lock when we return to userspace.
+ * We release freeze protection in aio_complete_rw(). Fool
+ * lockdep by telling it the lock got released so that it
+ * doesn't complain about held lock when we return to userspace.
*/
- if (S_ISREG(file_inode(file)->i_mode))
- __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+ if (S_ISREG(inode->i_mode))
+ __sb_writers_release(inode->i_sb, SB_FREEZE_WRITE);
}
kfree(iovec);
+out_fput:
+ if (unlikely(ret && ret != -EIOCBQUEUED))
+ fput(file);
return ret;
}
@@ -1528,7 +1570,6 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
struct iocb *iocb, bool compat)
{
struct aio_kiocb *req;
- struct file *file;
ssize_t ret;
/* enforce forwards compatibility on users */
@@ -1551,16 +1592,6 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
if (unlikely(!req))
return -EAGAIN;
- req->common.ki_filp = file = fget(iocb->aio_fildes);
- if (unlikely(!req->common.ki_filp)) {
- ret = -EBADF;
- goto out_put_req;
- }
- req->common.ki_pos = iocb->aio_offset;
- req->common.ki_complete = aio_complete;
- req->common.ki_flags = iocb_flags(req->common.ki_filp);
- req->common.ki_hint = file_write_hint(file);
-
if (iocb->aio_flags & IOCB_FLAG_RESFD) {
/*
* If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
@@ -1574,14 +1605,6 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
req->ki_eventfd = NULL;
goto out_put_req;
}
-
- req->common.ki_flags |= IOCB_EVENTFD;
- }
-
- ret = kiocb_set_rw_flags(&req->common, iocb->aio_rw_flags);
- if (unlikely(ret)) {
- pr_debug("EINVAL: aio_rw_flags\n");
- goto out_put_req;
}
ret = put_user(KIOCB_KEY, &user_iocb->aio_key);
@@ -1593,26 +1616,24 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
req->ki_user_iocb = user_iocb;
req->ki_user_data = iocb->aio_data;
- get_file(file);
switch (iocb->aio_lio_opcode) {
case IOCB_CMD_PREAD:
- ret = aio_read(&req->common, iocb, false, compat);
+ ret = aio_read(&req->rw, iocb, false, compat);
break;
case IOCB_CMD_PWRITE:
- ret = aio_write(&req->common, iocb, false, compat);
+ ret = aio_write(&req->rw, iocb, false, compat);
break;
case IOCB_CMD_PREADV:
- ret = aio_read(&req->common, iocb, true, compat);
+ ret = aio_read(&req->rw, iocb, true, compat);
break;
case IOCB_CMD_PWRITEV:
- ret = aio_write(&req->common, iocb, true, compat);
+ ret = aio_write(&req->rw, iocb, true, compat);
break;
default:
pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
ret = -EINVAL;
break;
}
- fput(file);
if (ret && ret != -EIOCBQUEUED)
goto out_put_req;
@@ -1620,7 +1641,9 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
out_put_req:
put_reqs_available(ctx, 1);
percpu_ref_put(&ctx->reqs);
- kiocb_free(req);
+ if (req->ki_eventfd)
+ eventfd_ctx_put(req->ki_eventfd);
+ kmem_cache_free(kiocb_cachep, req);
return ret;
}
--
2.14.2
--
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 2/6] aio: remove an outdated comment in aio_complete
From: Christoph Hellwig @ 2018-03-28 7:26 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, linux-api, linux-kernel
In-Reply-To: <20180328072639.16885-1-hch@lst.de>
These days we don't treat sync iocbs special in the aio completion code as
they never use it. Remove the old comment and BUG_ON given that the
current definition of is_sync_kiocb makes it impossible to hit.
iocb to the top of the function.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
fs/aio.c | 9 ---------
1 file changed, 9 deletions(-)
diff --git a/fs/aio.c b/fs/aio.c
index 03d59593912d..f536b0f249d4 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1100,15 +1100,6 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
file_end_write(file);
}
- /*
- * Special case handling for sync iocbs:
- * - events go directly into the iocb for fast handling
- * - the sync task with the iocb in its stack holds the single iocb
- * ref, no other paths have a way to get another ref
- * - the sync task helpfully left a reference to itself in the iocb
- */
- BUG_ON(is_sync_kiocb(kiocb));
-
if (iocb->ki_list.next) {
unsigned long flags;
--
2.14.2
--
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 1/6] aio: don't print the page size at boot time
From: Christoph Hellwig @ 2018-03-28 7:26 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, linux-api, linux-kernel
In-Reply-To: <20180328072639.16885-1-hch@lst.de>
The page size is in no way related to the aio code, and printing it in
the (debug) dmesg at every boot serves no purpose.
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 | 3 ---
1 file changed, 3 deletions(-)
diff --git a/fs/aio.c b/fs/aio.c
index a062d75109cb..03d59593912d 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -264,9 +264,6 @@ static int __init aio_setup(void)
kiocb_cachep = KMEM_CACHE(aio_kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
-
- pr_debug("sizeof(struct page) = %zu\n", sizeof(struct page));
-
return 0;
}
__initcall(aio_setup);
--
2.14.2
--
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
* io_pgetevents & aio fsync V2
From: Christoph Hellwig @ 2018-03-28 7:26 UTC (permalink / raw)
To: viro; +Cc: Avi Kivity, linux-aio, linux-fsdevel, linux-api, linux-kernel
Hi all,
this patch adds workqueue based fsync offload. Version of this
patch have been floating around for a couple years, but we now
have a user with seastar used by ScyllaDB (who sponsored this
work) that really wants this in addition to the aio poll support.
More details are in the patch itself.
Because the iocb types have been defined sine day one (and probably
were supported by RHEL3) libaio already supports these calls as-is.
This also pulls in the aio cleanups and io_pgetevents support previously
submitted and review as part of the aio poll series. The aio poll
series will be resubmitted on top of this series
A git tree is available here:
git://git.infradead.org/users/hch/vfs.git aio-fsync.3
Gitweb:
http://git.infradead.org/users/hch/vfs.git/shortlog/refs/heads/aio-fsync.3
Changes since V1:
- remove a BUG_ON_ONE(is_sync_kiocb(kiocb));
- moved cancellation patches to the poll series
- improve a list_empty check
--
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 for 4.17 02/21] rseq: Introduce restartable sequences system call (v12)
From: Boqun Feng @ 2018-03-28 6:47 UTC (permalink / raw)
To: Mathieu Desnoyers
Cc: Peter Zijlstra, Paul E . McKenney, Andy Lutomirski, Dave Watson,
linux-kernel, linux-api, Paul Turner, Andrew Morton, Russell King,
Thomas Gleixner, Ingo Molnar, H . Peter Anvin, Andrew Hunter,
Andi Kleen, Chris Lameter, Ben Maurer, Steven Rostedt,
Josh Triplett, Linus Torvalds, Catalin Marinas, Will Deacon
In-Reply-To: <20180327160542.28457-3-mathieu.desnoyers@efficios.com>
[-- Attachment #1: Type: text/plain, Size: 2186 bytes --]
On Tue, Mar 27, 2018 at 12:05:23PM -0400, Mathieu Desnoyers wrote:
[...]
> Changes since v11:
>
> - Replace task struct rseq_preempt, rseq_signal, and rseq_migrate
> bool by u32 rseq_event_mask.
[...]
> @@ -979,6 +980,17 @@ struct task_struct {
> unsigned long numa_pages_migrated;
> #endif /* CONFIG_NUMA_BALANCING */
>
> +#ifdef CONFIG_RSEQ
> + struct rseq __user *rseq;
> + u32 rseq_len;
> + u32 rseq_sig;
> + /*
> + * RmW on rseq_event_mask must be performed atomically
> + * with respect to preemption.
> + */
> + unsigned long rseq_event_mask;
s/unsigned long/u32
> +#endif
> +
> struct tlbflush_unmap_batch tlb_ubc;
>
> struct rcu_head rcu;
> @@ -1688,4 +1700,110 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
> #define TASK_SIZE_OF(tsk) TASK_SIZE
> #endif
>
[...]
> +
> +static int rseq_ip_fixup(struct pt_regs *regs)
> +{
> + unsigned long ip = instruction_pointer(regs), start_ip = 0,
> + post_commit_offset = 0, abort_ip = 0;
> + struct task_struct *t = current;
> + uint32_t cs_flags = 0;
> + bool in_rseq_cs = false;
This seems unnecessary? Because..
> + int ret;
> +
> + ret = rseq_get_rseq_cs(t, &start_ip, &post_commit_offset, &abort_ip,
> + &cs_flags);
> + if (ret)
> + return ret;
> +
> + /*
> + * Handle potentially not being within a critical section.
> + * Unsigned comparison will be true when
> + * ip >= start_ip, and when ip < start_ip + post_commit_offset.
> + */
> + if (ip - start_ip < post_commit_offset)
> + in_rseq_cs = true;
> +
> + /*
> + * If not nested over a rseq critical section, restart is
> + * useless. Clear the rseq_cs pointer and return.
> + */
> + if (!in_rseq_cs)
> + return clear_rseq_cs(t);
we can write
if (ip - start_ip >= post_commit_offset)
return clear_rseq_cs(t);
Regards,
Boqun
> + ret = rseq_need_restart(t, cs_flags);
> + if (ret <= 0)
> + return ret;
> + ret = clear_rseq_cs(t);
> + if (ret)
> + return ret;
> + trace_rseq_ip_fixup(ip, start_ip, post_commit_offset, abort_ip);
> + instruction_pointer_set(regs, (unsigned long)abort_ip);
> + return 0;
> +}
> +
[...]
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply
* [PATCH v7 bpf-next 10/10] selftests/bpf: test for bpf_get_stackid() from raw tracepoints
From: Alexei Starovoitov @ 2018-03-28 2:11 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
similar to traditional traceopint test add bpf_get_stackid() test
from raw tracepoints
and reduce verbosity of existing stackmap test
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
tools/testing/selftests/bpf/test_progs.c | 91 ++++++++++++++++++++++++--------
1 file changed, 70 insertions(+), 21 deletions(-)
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index e9df48b306df..faadbe233966 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -877,7 +877,7 @@ static void test_stacktrace_map()
err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
- goto out;
+ return;
/* Get the ID for the sched/sched_switch tracepoint */
snprintf(buf, sizeof(buf),
@@ -888,8 +888,7 @@ static void test_stacktrace_map()
bytes = read(efd, buf, sizeof(buf));
close(efd);
- if (CHECK(bytes <= 0 || bytes >= sizeof(buf),
- "read", "bytes %d errno %d\n", bytes, errno))
+ if (bytes <= 0 || bytes >= sizeof(buf))
goto close_prog;
/* Open the perf event and attach bpf progrram */
@@ -906,29 +905,24 @@ static void test_stacktrace_map()
goto close_prog;
err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
- if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n",
- err, errno))
- goto close_pmu;
+ if (err)
+ goto disable_pmu;
err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
- if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n",
- err, errno))
+ if (err)
goto disable_pmu;
/* find map fds */
control_map_fd = bpf_find_map(__func__, obj, "control_map");
- if (CHECK(control_map_fd < 0, "bpf_find_map control_map",
- "err %d errno %d\n", err, errno))
+ if (control_map_fd < 0)
goto disable_pmu;
stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap");
- if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap",
- "err %d errno %d\n", err, errno))
+ if (stackid_hmap_fd < 0)
goto disable_pmu;
stackmap_fd = bpf_find_map(__func__, obj, "stackmap");
- if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n",
- err, errno))
+ if (stackmap_fd < 0)
goto disable_pmu;
/* give some time for bpf program run */
@@ -945,24 +939,78 @@ static void test_stacktrace_map()
err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
"err %d errno %d\n", err, errno))
- goto disable_pmu;
+ goto disable_pmu_noerr;
err = compare_map_keys(stackmap_fd, stackid_hmap_fd);
if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap",
"err %d errno %d\n", err, errno))
- ; /* fall through */
+ goto disable_pmu_noerr;
+ goto disable_pmu_noerr;
disable_pmu:
+ error_cnt++;
+disable_pmu_noerr:
ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
-
-close_pmu:
close(pmu_fd);
-
close_prog:
bpf_object__close(obj);
+}
-out:
- return;
+static void test_stacktrace_map_raw_tp()
+{
+ int control_map_fd, stackid_hmap_fd, stackmap_fd;
+ const char *file = "./test_stacktrace_map.o";
+ int efd, err, prog_fd;
+ __u32 key, val, duration = 0;
+ struct bpf_object *obj;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd);
+ if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
+ return;
+
+ efd = bpf_raw_tracepoint_open("sched_switch", prog_fd);
+ if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno))
+ goto close_prog;
+
+ /* find map fds */
+ control_map_fd = bpf_find_map(__func__, obj, "control_map");
+ if (control_map_fd < 0)
+ goto close_prog;
+
+ stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap");
+ if (stackid_hmap_fd < 0)
+ goto close_prog;
+
+ stackmap_fd = bpf_find_map(__func__, obj, "stackmap");
+ if (stackmap_fd < 0)
+ goto close_prog;
+
+ /* give some time for bpf program run */
+ sleep(1);
+
+ /* disable stack trace collection */
+ key = 0;
+ val = 1;
+ bpf_map_update_elem(control_map_fd, &key, &val, 0);
+
+ /* for every element in stackid_hmap, we can find a corresponding one
+ * in stackmap, and vise versa.
+ */
+ err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
+ if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
+ "err %d errno %d\n", err, errno))
+ goto close_prog;
+
+ err = compare_map_keys(stackmap_fd, stackid_hmap_fd);
+ if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap",
+ "err %d errno %d\n", err, errno))
+ goto close_prog;
+
+ goto close_prog_noerr;
+close_prog:
+ error_cnt++;
+close_prog_noerr:
+ bpf_object__close(obj);
}
static int extract_build_id(char *build_id, size_t size)
@@ -1138,6 +1186,7 @@ int main(void)
test_tp_attach_query();
test_stacktrace_map();
test_stacktrace_build_id();
+ test_stacktrace_map_raw_tp();
printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 09/10] samples/bpf: raw tracepoint test
From: Alexei Starovoitov @ 2018-03-28 2:11 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
add empty raw_tracepoint bpf program to test overhead similar
to kprobe and traditional tracepoint tests
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
samples/bpf/Makefile | 1 +
samples/bpf/bpf_load.c | 14 ++++++++++++++
samples/bpf/test_overhead_raw_tp_kern.c | 17 +++++++++++++++++
samples/bpf/test_overhead_user.c | 12 ++++++++++++
4 files changed, 44 insertions(+)
create mode 100644 samples/bpf/test_overhead_raw_tp_kern.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 2c2a587e0942..4d6a6edd4bf6 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -119,6 +119,7 @@ always += offwaketime_kern.o
always += spintest_kern.o
always += map_perf_test_kern.o
always += test_overhead_tp_kern.o
+always += test_overhead_raw_tp_kern.o
always += test_overhead_kprobe_kern.o
always += parse_varlen.o parse_simple.o parse_ldabs.o
always += test_cgrp2_tc_kern.o
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index b1a310c3ae89..bebe4188b4b3 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -61,6 +61,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
bool is_kprobe = strncmp(event, "kprobe/", 7) == 0;
bool is_kretprobe = strncmp(event, "kretprobe/", 10) == 0;
bool is_tracepoint = strncmp(event, "tracepoint/", 11) == 0;
+ bool is_raw_tracepoint = strncmp(event, "raw_tracepoint/", 15) == 0;
bool is_xdp = strncmp(event, "xdp", 3) == 0;
bool is_perf_event = strncmp(event, "perf_event", 10) == 0;
bool is_cgroup_skb = strncmp(event, "cgroup/skb", 10) == 0;
@@ -85,6 +86,8 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
prog_type = BPF_PROG_TYPE_KPROBE;
} else if (is_tracepoint) {
prog_type = BPF_PROG_TYPE_TRACEPOINT;
+ } else if (is_raw_tracepoint) {
+ prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT;
} else if (is_xdp) {
prog_type = BPF_PROG_TYPE_XDP;
} else if (is_perf_event) {
@@ -131,6 +134,16 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
return populate_prog_array(event, fd);
}
+ if (is_raw_tracepoint) {
+ efd = bpf_raw_tracepoint_open(event + 15, fd);
+ if (efd < 0) {
+ printf("tracepoint %s %s\n", event + 15, strerror(errno));
+ return -1;
+ }
+ event_fd[prog_cnt - 1] = efd;
+ return 0;
+ }
+
if (is_kprobe || is_kretprobe) {
if (is_kprobe)
event += 7;
@@ -587,6 +600,7 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map)
if (memcmp(shname, "kprobe/", 7) == 0 ||
memcmp(shname, "kretprobe/", 10) == 0 ||
memcmp(shname, "tracepoint/", 11) == 0 ||
+ memcmp(shname, "raw_tracepoint/", 15) == 0 ||
memcmp(shname, "xdp", 3) == 0 ||
memcmp(shname, "perf_event", 10) == 0 ||
memcmp(shname, "socket", 6) == 0 ||
diff --git a/samples/bpf/test_overhead_raw_tp_kern.c b/samples/bpf/test_overhead_raw_tp_kern.c
new file mode 100644
index 000000000000..d2af8bc1c805
--- /dev/null
+++ b/samples/bpf/test_overhead_raw_tp_kern.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook */
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+SEC("raw_tracepoint/task_rename")
+int prog(struct bpf_raw_tracepoint_args *ctx)
+{
+ return 0;
+}
+
+SEC("raw_tracepoint/urandom_read")
+int prog2(struct bpf_raw_tracepoint_args *ctx)
+{
+ return 0;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/test_overhead_user.c b/samples/bpf/test_overhead_user.c
index d291167fd3c7..e1d35e07a10e 100644
--- a/samples/bpf/test_overhead_user.c
+++ b/samples/bpf/test_overhead_user.c
@@ -158,5 +158,17 @@ int main(int argc, char **argv)
unload_progs();
}
+ if (test_flags & 0xC0) {
+ snprintf(filename, sizeof(filename),
+ "%s_raw_tp_kern.o", argv[0]);
+ if (load_bpf_file(filename)) {
+ printf("%s", bpf_log_buf);
+ return 1;
+ }
+ printf("w/RAW_TRACEPOINT\n");
+ run_perf_test(num_cpu, test_flags >> 6);
+ unload_progs();
+ }
+
return 0;
}
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 08/10] libbpf: add bpf_raw_tracepoint_open helper
From: Alexei Starovoitov @ 2018-03-28 2:11 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
add bpf_raw_tracepoint_open(const char *name, int prog_fd) api to libbpf
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
tools/include/uapi/linux/bpf.h | 11 +++++++++++
tools/lib/bpf/bpf.c | 11 +++++++++++
tools/lib/bpf/bpf.h | 1 +
3 files changed, 23 insertions(+)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d245c41213ac..58060bec999d 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -94,6 +94,7 @@ enum bpf_cmd {
BPF_MAP_GET_FD_BY_ID,
BPF_OBJ_GET_INFO_BY_FD,
BPF_PROG_QUERY,
+ BPF_RAW_TRACEPOINT_OPEN,
};
enum bpf_map_type {
@@ -134,6 +135,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_SK_SKB,
BPF_PROG_TYPE_CGROUP_DEVICE,
BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_RAW_TRACEPOINT,
};
enum bpf_attach_type {
@@ -344,6 +346,11 @@ union bpf_attr {
__aligned_u64 prog_ids;
__u32 prog_cnt;
} query;
+
+ struct {
+ __u64 name;
+ __u32 prog_fd;
+ } raw_tracepoint;
} __attribute__((aligned(8)));
/* BPF helper function descriptions:
@@ -1151,4 +1158,8 @@ struct bpf_cgroup_dev_ctx {
__u32 minor;
};
+struct bpf_raw_tracepoint_args {
+ __u64 args[0];
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 592a58a2b681..e0500055f1a6 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -428,6 +428,17 @@ int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len)
return err;
}
+int bpf_raw_tracepoint_open(const char *name, int prog_fd)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.raw_tracepoint.name = ptr_to_u64(name);
+ attr.raw_tracepoint.prog_fd = prog_fd;
+
+ return sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
+}
+
int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
{
struct sockaddr_nl sa;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 8d18fb73d7fb..ee59342c6f42 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -79,4 +79,5 @@ int bpf_map_get_fd_by_id(__u32 id);
int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
__u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt);
+int bpf_raw_tracepoint_open(const char *name, int prog_fd);
#endif
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 07/10] bpf: introduce BPF_RAW_TRACEPOINT
From: Alexei Starovoitov @ 2018-03-28 2:11 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
Introduce BPF_PROG_TYPE_RAW_TRACEPOINT bpf program type to access
kernel internal arguments of the tracepoints in their raw form.
>From bpf program point of view the access to the arguments look like:
struct bpf_raw_tracepoint_args {
__u64 args[0];
};
int bpf_prog(struct bpf_raw_tracepoint_args *ctx)
{
// program can read args[N] where N depends on tracepoint
// and statically verified at program load+attach time
}
kprobe+bpf infrastructure allows programs access function arguments.
This feature allows programs access raw tracepoint arguments.
Similar to proposed 'dynamic ftrace events' there are no abi guarantees
to what the tracepoints arguments are and what their meaning is.
The program needs to type cast args properly and use bpf_probe_read()
helper to access struct fields when argument is a pointer.
For every tracepoint __bpf_trace_##call function is prepared.
In assembler it looks like:
(gdb) disassemble __bpf_trace_xdp_exception
Dump of assembler code for function __bpf_trace_xdp_exception:
0xffffffff81132080 <+0>: mov %ecx,%ecx
0xffffffff81132082 <+2>: jmpq 0xffffffff811231f0 <bpf_trace_run3>
where
TRACE_EVENT(xdp_exception,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp, u32 act),
The above assembler snippet is casting 32-bit 'act' field into 'u64'
to pass into bpf_trace_run3(), while 'dev' and 'xdp' args are passed as-is.
All of ~500 of __bpf_trace_*() functions are only 5-10 byte long
and in total this approach adds 7k bytes to .text.
This approach gives the lowest possible overhead
while calling trace_xdp_exception() from kernel C code and
transitioning into bpf land.
Since tracepoint+bpf are used at speeds of 1M+ events per second
this is valuable optimization.
The new BPF_RAW_TRACEPOINT_OPEN sys_bpf command is introduced
that returns anon_inode FD of 'bpf-raw-tracepoint' object.
The user space looks like:
// load bpf prog with BPF_PROG_TYPE_RAW_TRACEPOINT type
prog_fd = bpf_prog_load(...);
// receive anon_inode fd for given bpf_raw_tracepoint with prog attached
raw_tp_fd = bpf_raw_tracepoint_open("xdp_exception", prog_fd);
Ctrl-C of tracing daemon or cmdline tool that uses this feature
will automatically detach bpf program, unload it and
unregister tracepoint probe.
On the kernel side the __bpf_raw_tp_map section of pointers to
tracepoint definition and to __bpf_trace_*() probe function is used
to find a tracepoint with "xdp_exception" name and
corresponding __bpf_trace_xdp_exception() probe function
which are passed to tracepoint_probe_register() to connect probe
with tracepoint.
Addition of bpf_raw_tracepoint doesn't interfere with ftrace and perf
tracepoint mechanisms. perf_event_open() can be used in parallel
on the same tracepoint.
Multiple bpf_raw_tracepoint_open("xdp_exception", prog_fd) are permitted.
Each with its own bpf program. The kernel will execute
all tracepoint probes and all attached bpf programs.
In the future bpf_raw_tracepoints can be extended with
query/introspection logic.
__bpf_raw_tp_map section logic was contributed by Steven Rostedt
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
include/asm-generic/vmlinux.lds.h | 10 +++
include/linux/bpf_types.h | 1 +
include/linux/trace_events.h | 42 +++++++++
include/linux/tracepoint-defs.h | 5 ++
include/trace/bpf_probe.h | 91 +++++++++++++++++++
include/trace/define_trace.h | 1 +
include/uapi/linux/bpf.h | 11 +++
kernel/bpf/syscall.c | 78 ++++++++++++++++
kernel/trace/bpf_trace.c | 183 ++++++++++++++++++++++++++++++++++++++
9 files changed, 422 insertions(+)
create mode 100644 include/trace/bpf_probe.h
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 1ab0e520d6fc..8add3493a202 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -178,6 +178,15 @@
#define TRACE_SYSCALLS()
#endif
+#ifdef CONFIG_BPF_EVENTS
+#define BPF_RAW_TP() STRUCT_ALIGN(); \
+ VMLINUX_SYMBOL(__start__bpf_raw_tp) = .; \
+ KEEP(*(__bpf_raw_tp_map)) \
+ VMLINUX_SYMBOL(__stop__bpf_raw_tp) = .;
+#else
+#define BPF_RAW_TP()
+#endif
+
#ifdef CONFIG_SERIAL_EARLYCON
#define EARLYCON_TABLE() STRUCT_ALIGN(); \
VMLINUX_SYMBOL(__earlycon_table) = .; \
@@ -249,6 +258,7 @@
LIKELY_PROFILE() \
BRANCH_PROFILE() \
TRACE_PRINTKS() \
+ BPF_RAW_TP() \
TRACEPOINT_STR()
/*
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 5e2e8a49fb21..6d7243bfb0ff 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -19,6 +19,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg)
BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe)
BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint)
BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event)
+BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint)
#endif
#ifdef CONFIG_CGROUP_BPF
BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 8a1442c4e513..b0357cd198b0 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -468,6 +468,9 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx);
int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog);
void perf_event_detach_bpf_prog(struct perf_event *event);
int perf_event_query_prog_array(struct perf_event *event, void __user *info);
+int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
+int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
+struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name);
#else
static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx)
{
@@ -487,6 +490,18 @@ perf_event_query_prog_array(struct perf_event *event, void __user *info)
{
return -EOPNOTSUPP;
}
+static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *p)
+{
+ return -EOPNOTSUPP;
+}
+static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *p)
+{
+ return -EOPNOTSUPP;
+}
+static inline struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name)
+{
+ return NULL;
+}
#endif
enum {
@@ -546,6 +561,33 @@ extern void ftrace_profile_free_filter(struct perf_event *event);
void perf_trace_buf_update(void *record, u16 type);
void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp);
+void bpf_trace_run1(struct bpf_prog *prog, u64 arg1);
+void bpf_trace_run2(struct bpf_prog *prog, u64 arg1, u64 arg2);
+void bpf_trace_run3(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3);
+void bpf_trace_run4(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4);
+void bpf_trace_run5(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5);
+void bpf_trace_run6(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5, u64 arg6);
+void bpf_trace_run7(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7);
+void bpf_trace_run8(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
+ u64 arg8);
+void bpf_trace_run9(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
+ u64 arg8, u64 arg9);
+void bpf_trace_run10(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
+ u64 arg8, u64 arg9, u64 arg10);
+void bpf_trace_run11(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
+ u64 arg8, u64 arg9, u64 arg10, u64 arg11);
+void bpf_trace_run12(struct bpf_prog *prog, u64 arg1, u64 arg2,
+ u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7,
+ u64 arg8, u64 arg9, u64 arg10, u64 arg11, u64 arg12);
void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx,
struct trace_event_call *call, u64 count,
struct pt_regs *regs, struct hlist_head *head,
diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h
index 39a283c61c51..35db8dd48c4c 100644
--- a/include/linux/tracepoint-defs.h
+++ b/include/linux/tracepoint-defs.h
@@ -36,4 +36,9 @@ struct tracepoint {
u32 num_args;
};
+struct bpf_raw_event_map {
+ struct tracepoint *tp;
+ void *bpf_func;
+};
+
#endif
diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h
new file mode 100644
index 000000000000..c374ed1f2eee
--- /dev/null
+++ b/include/trace/bpf_probe.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#undef TRACE_SYSTEM_VAR
+
+#ifdef CONFIG_BPF_EVENTS
+
+#undef __entry
+#define __entry entry
+
+#undef __get_dynamic_array
+#define __get_dynamic_array(field) \
+ ((void *)__entry + (__entry->__data_loc_##field & 0xffff))
+
+#undef __get_dynamic_array_len
+#define __get_dynamic_array_len(field) \
+ ((__entry->__data_loc_##field >> 16) & 0xffff)
+
+#undef __get_str
+#define __get_str(field) ((char *)__get_dynamic_array(field))
+
+#undef __get_bitmask
+#define __get_bitmask(field) (char *)__get_dynamic_array(field)
+
+#undef __perf_count
+#define __perf_count(c) (c)
+
+#undef __perf_task
+#define __perf_task(t) (t)
+
+/* cast any integer, pointer, or small struct to u64 */
+#define UINTTYPE(size) \
+ __typeof__(__builtin_choose_expr(size == 1, (u8)1, \
+ __builtin_choose_expr(size == 2, (u16)2, \
+ __builtin_choose_expr(size == 4, (u32)3, \
+ __builtin_choose_expr(size == 8, (u64)4, \
+ (void)5)))))
+#define __CAST_TO_U64(x) ({ \
+ typeof(x) __src = (x); \
+ UINTTYPE(sizeof(x)) __dst; \
+ memcpy(&__dst, &__src, sizeof(__dst)); \
+ (u64)__dst; })
+
+#define __CAST1(a,...) __CAST_TO_U64(a)
+#define __CAST2(a,...) __CAST_TO_U64(a), __CAST1(__VA_ARGS__)
+#define __CAST3(a,...) __CAST_TO_U64(a), __CAST2(__VA_ARGS__)
+#define __CAST4(a,...) __CAST_TO_U64(a), __CAST3(__VA_ARGS__)
+#define __CAST5(a,...) __CAST_TO_U64(a), __CAST4(__VA_ARGS__)
+#define __CAST6(a,...) __CAST_TO_U64(a), __CAST5(__VA_ARGS__)
+#define __CAST7(a,...) __CAST_TO_U64(a), __CAST6(__VA_ARGS__)
+#define __CAST8(a,...) __CAST_TO_U64(a), __CAST7(__VA_ARGS__)
+#define __CAST9(a,...) __CAST_TO_U64(a), __CAST8(__VA_ARGS__)
+#define __CAST10(a,...) __CAST_TO_U64(a), __CAST9(__VA_ARGS__)
+#define __CAST11(a,...) __CAST_TO_U64(a), __CAST10(__VA_ARGS__)
+#define __CAST12(a,...) __CAST_TO_U64(a), __CAST11(__VA_ARGS__)
+/* tracepoints with more than 12 arguments will hit build error */
+#define CAST_TO_U64(...) CONCATENATE(__CAST, COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__)
+
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
+static notrace void \
+__bpf_trace_##call(void *__data, proto) \
+{ \
+ struct bpf_prog *prog = __data; \
+ CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(prog, CAST_TO_U64(args)); \
+}
+
+/*
+ * This part is compiled out, it is only here as a build time check
+ * to make sure that if the tracepoint handling changes, the
+ * bpf probe will fail to compile unless it too is updated.
+ */
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, call, proto, args) \
+static inline void bpf_test_probe_##call(void) \
+{ \
+ check_trace_callback_type_##call(__bpf_trace_##template); \
+} \
+static struct bpf_raw_event_map __used \
+ __attribute__((section("__bpf_raw_tp_map"))) \
+__bpf_trace_tp_map_##call = { \
+ .tp = &__tracepoint_##call, \
+ .bpf_func = (void *)__bpf_trace_##template, \
+};
+
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
+ DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+#endif /* CONFIG_BPF_EVENTS */
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
index 96b22ace9ae7..5f8216bc261f 100644
--- a/include/trace/define_trace.h
+++ b/include/trace/define_trace.h
@@ -95,6 +95,7 @@
#ifdef TRACEPOINTS_ENABLED
#include <trace/trace_events.h>
#include <trace/perf.h>
+#include <trace/bpf_probe.h>
#endif
#undef TRACE_EVENT
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 18b7c510c511..1878201c2d77 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -94,6 +94,7 @@ enum bpf_cmd {
BPF_MAP_GET_FD_BY_ID,
BPF_OBJ_GET_INFO_BY_FD,
BPF_PROG_QUERY,
+ BPF_RAW_TRACEPOINT_OPEN,
};
enum bpf_map_type {
@@ -134,6 +135,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_SK_SKB,
BPF_PROG_TYPE_CGROUP_DEVICE,
BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_RAW_TRACEPOINT,
};
enum bpf_attach_type {
@@ -344,6 +346,11 @@ union bpf_attr {
__aligned_u64 prog_ids;
__u32 prog_cnt;
} query;
+
+ struct {
+ __u64 name;
+ __u32 prog_fd;
+ } raw_tracepoint;
} __attribute__((aligned(8)));
/* BPF helper function descriptions:
@@ -1152,4 +1159,8 @@ struct bpf_cgroup_dev_ctx {
__u32 minor;
};
+struct bpf_raw_tracepoint_args {
+ __u64 args[0];
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 3aeb4ea2a93a..1894537dcada 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1311,6 +1311,81 @@ static int bpf_obj_get(const union bpf_attr *attr)
attr->file_flags);
}
+struct bpf_raw_tracepoint {
+ struct bpf_raw_event_map *btp;
+ struct bpf_prog *prog;
+};
+
+static int bpf_raw_tracepoint_release(struct inode *inode, struct file *filp)
+{
+ struct bpf_raw_tracepoint *raw_tp = filp->private_data;
+
+ if (raw_tp->prog) {
+ bpf_probe_unregister(raw_tp->btp, raw_tp->prog);
+ bpf_prog_put(raw_tp->prog);
+ }
+ kfree(raw_tp);
+ return 0;
+}
+
+static const struct file_operations bpf_raw_tp_fops = {
+ .release = bpf_raw_tracepoint_release,
+ .read = bpf_dummy_read,
+ .write = bpf_dummy_write,
+};
+
+#define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd
+
+static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
+{
+ struct bpf_raw_tracepoint *raw_tp;
+ struct bpf_raw_event_map *btp;
+ struct bpf_prog *prog;
+ char tp_name[128];
+ int tp_fd, err;
+
+ if (strncpy_from_user(tp_name, u64_to_user_ptr(attr->raw_tracepoint.name),
+ sizeof(tp_name) - 1) < 0)
+ return -EFAULT;
+ tp_name[sizeof(tp_name) - 1] = 0;
+
+ btp = bpf_find_raw_tracepoint(tp_name);
+ if (!btp)
+ return -ENOENT;
+
+ raw_tp = kzalloc(sizeof(*raw_tp), GFP_USER);
+ if (!raw_tp)
+ return -ENOMEM;
+ raw_tp->btp = btp;
+
+ prog = bpf_prog_get_type(attr->raw_tracepoint.prog_fd,
+ BPF_PROG_TYPE_RAW_TRACEPOINT);
+ if (IS_ERR(prog)) {
+ err = PTR_ERR(prog);
+ goto out_free_tp;
+ }
+
+ err = bpf_probe_register(raw_tp->btp, prog);
+ if (err)
+ goto out_put_prog;
+
+ raw_tp->prog = prog;
+ tp_fd = anon_inode_getfd("bpf-raw-tracepoint", &bpf_raw_tp_fops, raw_tp,
+ O_CLOEXEC);
+ if (tp_fd < 0) {
+ bpf_probe_unregister(raw_tp->btp, prog);
+ err = tp_fd;
+ goto out_put_prog;
+ }
+ return tp_fd;
+
+out_put_prog:
+ bpf_prog_put(prog);
+out_free_tp:
+ kfree(raw_tp);
+ return err;
+}
+
#ifdef CONFIG_CGROUP_BPF
#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
@@ -1921,6 +1996,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_OBJ_GET_INFO_BY_FD:
err = bpf_obj_get_info_by_fd(&attr, uattr);
break;
+ case BPF_RAW_TRACEPOINT_OPEN:
+ err = bpf_raw_tracepoint_open(&attr);
+ break;
default:
err = -EINVAL;
break;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index c634e093951f..7d0009e712f5 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -723,6 +723,86 @@ const struct bpf_verifier_ops tracepoint_verifier_ops = {
const struct bpf_prog_ops tracepoint_prog_ops = {
};
+/*
+ * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp
+ * to avoid potential recursive reuse issue when/if tracepoints are added
+ * inside bpf_*_event_output and/or bpf_get_stack_id
+ */
+static DEFINE_PER_CPU(struct pt_regs, bpf_raw_tp_regs);
+BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args,
+ struct bpf_map *, map, u64, flags, void *, data, u64, size)
+{
+ struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+
+ perf_fetch_caller_regs(regs);
+ return ____bpf_perf_event_output(regs, map, flags, data, size);
+}
+
+static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
+ .func = bpf_perf_event_output_raw_tp,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_MEM,
+ .arg5_type = ARG_CONST_SIZE_OR_ZERO,
+};
+
+BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
+ struct bpf_map *, map, u64, flags)
+{
+ struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+
+ perf_fetch_caller_regs(regs);
+ /* similar to bpf_perf_event_output_tp, but pt_regs fetched differently */
+ return bpf_get_stackid((unsigned long) regs, (unsigned long) map,
+ flags, 0, 0);
+}
+
+static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = {
+ .func = bpf_get_stackid_raw_tp,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_CONST_MAP_PTR,
+ .arg3_type = ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *raw_tp_prog_func_proto(enum bpf_func_id func_id)
+{
+ switch (func_id) {
+ case BPF_FUNC_perf_event_output:
+ return &bpf_perf_event_output_proto_raw_tp;
+ case BPF_FUNC_get_stackid:
+ return &bpf_get_stackid_proto_raw_tp;
+ default:
+ return tracing_func_proto(func_id);
+ }
+}
+
+static bool raw_tp_prog_is_valid_access(int off, int size,
+ enum bpf_access_type type,
+ struct bpf_insn_access_aux *info)
+{
+ /* largest tracepoint in the kernel has 12 args */
+ if (off < 0 || off >= sizeof(__u64) * 12)
+ return false;
+ if (type != BPF_READ)
+ return false;
+ if (off % size != 0)
+ return false;
+ return true;
+}
+
+const struct bpf_verifier_ops raw_tracepoint_verifier_ops = {
+ .get_func_proto = raw_tp_prog_func_proto,
+ .is_valid_access = raw_tp_prog_is_valid_access,
+};
+
+const struct bpf_prog_ops raw_tracepoint_prog_ops = {
+};
+
static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
@@ -896,3 +976,106 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
return ret;
}
+
+extern struct bpf_raw_event_map __start__bpf_raw_tp[];
+extern struct bpf_raw_event_map __stop__bpf_raw_tp[];
+
+struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name)
+{
+ struct bpf_raw_event_map *btp = __start__bpf_raw_tp;
+
+ for (; btp < __stop__bpf_raw_tp; btp++) {
+ if (!strcmp(btp->tp->name, name))
+ return btp;
+ }
+ return NULL;
+}
+
+static __always_inline
+void __bpf_trace_run(struct bpf_prog *prog, u64 *args)
+{
+ rcu_read_lock();
+ preempt_disable();
+ (void) BPF_PROG_RUN(prog, args);
+ preempt_enable();
+ rcu_read_unlock();
+}
+
+#define UNPACK(...) __VA_ARGS__
+#define REPEAT_1(FN, DL, X, ...) FN(X)
+#define REPEAT_2(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_1(FN, DL, __VA_ARGS__)
+#define REPEAT_3(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_2(FN, DL, __VA_ARGS__)
+#define REPEAT_4(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_3(FN, DL, __VA_ARGS__)
+#define REPEAT_5(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_4(FN, DL, __VA_ARGS__)
+#define REPEAT_6(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_5(FN, DL, __VA_ARGS__)
+#define REPEAT_7(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_6(FN, DL, __VA_ARGS__)
+#define REPEAT_8(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_7(FN, DL, __VA_ARGS__)
+#define REPEAT_9(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_8(FN, DL, __VA_ARGS__)
+#define REPEAT_10(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_9(FN, DL, __VA_ARGS__)
+#define REPEAT_11(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_10(FN, DL, __VA_ARGS__)
+#define REPEAT_12(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_11(FN, DL, __VA_ARGS__)
+#define REPEAT(X, FN, DL, ...) REPEAT_##X(FN, DL, __VA_ARGS__)
+
+#define SARG(X) u64 arg##X
+#define COPY(X) args[X] = arg##X
+
+#define __DL_COM (,)
+#define __DL_SEM (;)
+
+#define __SEQ_0_11 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11
+
+#define BPF_TRACE_DEFN_x(x) \
+ void bpf_trace_run##x(struct bpf_prog *prog, \
+ REPEAT(x, SARG, __DL_COM, __SEQ_0_11)) \
+ { \
+ u64 args[x]; \
+ REPEAT(x, COPY, __DL_SEM, __SEQ_0_11); \
+ __bpf_trace_run(prog, args); \
+ } \
+ EXPORT_SYMBOL_GPL(bpf_trace_run##x)
+BPF_TRACE_DEFN_x(1);
+BPF_TRACE_DEFN_x(2);
+BPF_TRACE_DEFN_x(3);
+BPF_TRACE_DEFN_x(4);
+BPF_TRACE_DEFN_x(5);
+BPF_TRACE_DEFN_x(6);
+BPF_TRACE_DEFN_x(7);
+BPF_TRACE_DEFN_x(8);
+BPF_TRACE_DEFN_x(9);
+BPF_TRACE_DEFN_x(10);
+BPF_TRACE_DEFN_x(11);
+BPF_TRACE_DEFN_x(12);
+
+static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
+{
+ struct tracepoint *tp = btp->tp;
+
+ /*
+ * check that program doesn't access arguments beyond what's
+ * available in this tracepoint
+ */
+ if (prog->aux->max_ctx_offset > tp->num_args * sizeof(u64))
+ return -EINVAL;
+
+ return tracepoint_probe_register(tp, (void *)btp->bpf_func, prog);
+}
+
+int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
+{
+ int err;
+
+ mutex_lock(&bpf_event_mutex);
+ err = __bpf_probe_register(btp, prog);
+ mutex_unlock(&bpf_event_mutex);
+ return err;
+}
+
+int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
+{
+ int err;
+
+ mutex_lock(&bpf_event_mutex);
+ err = tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog);
+ mutex_unlock(&bpf_event_mutex);
+ return err;
+}
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 06/10] tracepoint: compute num_args at build time
From: Alexei Starovoitov @ 2018-03-28 2:11 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
compute number of arguments passed into tracepoint
at compile time and store it as part of 'struct tracepoint'.
The number is necessary to check safety of bpf program access that
is coming in subsequent patch.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
include/linux/tracepoint-defs.h | 1 +
include/linux/tracepoint.h | 12 ++++++------
include/trace/define_trace.h | 14 +++++++-------
3 files changed, 14 insertions(+), 13 deletions(-)
diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h
index 64ed7064f1fa..39a283c61c51 100644
--- a/include/linux/tracepoint-defs.h
+++ b/include/linux/tracepoint-defs.h
@@ -33,6 +33,7 @@ struct tracepoint {
int (*regfunc)(void);
void (*unregfunc)(void);
struct tracepoint_func __rcu *funcs;
+ u32 num_args;
};
#endif
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index c94f466d57ef..c92f4adbc0d7 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -230,18 +230,18 @@ extern void syscall_unregfunc(void);
* structures, so we create an array of pointers that will be used for iteration
* on the tracepoints.
*/
-#define DEFINE_TRACE_FN(name, reg, unreg) \
+#define DEFINE_TRACE_FN(name, reg, unreg, num_args) \
static const char __tpstrtab_##name[] \
__attribute__((section("__tracepoints_strings"))) = #name; \
struct tracepoint __tracepoint_##name \
__attribute__((section("__tracepoints"))) = \
- { __tpstrtab_##name, STATIC_KEY_INIT_FALSE, reg, unreg, NULL };\
+ { __tpstrtab_##name, STATIC_KEY_INIT_FALSE, reg, unreg, NULL, num_args };\
static struct tracepoint * const __tracepoint_ptr_##name __used \
__attribute__((section("__tracepoints_ptrs"))) = \
&__tracepoint_##name;
-#define DEFINE_TRACE(name) \
- DEFINE_TRACE_FN(name, NULL, NULL);
+#define DEFINE_TRACE(name, num_args) \
+ DEFINE_TRACE_FN(name, NULL, NULL, num_args);
#define EXPORT_TRACEPOINT_SYMBOL_GPL(name) \
EXPORT_SYMBOL_GPL(__tracepoint_##name)
@@ -275,8 +275,8 @@ extern void syscall_unregfunc(void);
return false; \
}
-#define DEFINE_TRACE_FN(name, reg, unreg)
-#define DEFINE_TRACE(name)
+#define DEFINE_TRACE_FN(name, reg, unreg, num_args)
+#define DEFINE_TRACE(name, num_args)
#define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
#define EXPORT_TRACEPOINT_SYMBOL(name)
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
index d9e3d4aa3f6e..96b22ace9ae7 100644
--- a/include/trace/define_trace.h
+++ b/include/trace/define_trace.h
@@ -25,7 +25,7 @@
#undef TRACE_EVENT
#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \
- DEFINE_TRACE(name)
+ DEFINE_TRACE(name, COUNT_ARGS(args))
#undef TRACE_EVENT_CONDITION
#define TRACE_EVENT_CONDITION(name, proto, args, cond, tstruct, assign, print) \
@@ -39,24 +39,24 @@
#undef TRACE_EVENT_FN
#define TRACE_EVENT_FN(name, proto, args, tstruct, \
assign, print, reg, unreg) \
- DEFINE_TRACE_FN(name, reg, unreg)
+ DEFINE_TRACE_FN(name, reg, unreg, COUNT_ARGS(args))
#undef TRACE_EVENT_FN_COND
#define TRACE_EVENT_FN_COND(name, proto, args, cond, tstruct, \
assign, print, reg, unreg) \
- DEFINE_TRACE_FN(name, reg, unreg)
+ DEFINE_TRACE_FN(name, reg, unreg, COUNT_ARGS(args))
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args) \
- DEFINE_TRACE(name)
+ DEFINE_TRACE(name, COUNT_ARGS(args))
#undef DEFINE_EVENT_FN
#define DEFINE_EVENT_FN(template, name, proto, args, reg, unreg) \
- DEFINE_TRACE_FN(name, reg, unreg)
+ DEFINE_TRACE_FN(name, reg, unreg, COUNT_ARGS(args))
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
- DEFINE_TRACE(name)
+ DEFINE_TRACE(name, COUNT_ARGS(args))
#undef DEFINE_EVENT_CONDITION
#define DEFINE_EVENT_CONDITION(template, name, proto, args, cond) \
@@ -64,7 +64,7 @@
#undef DECLARE_TRACE
#define DECLARE_TRACE(name, proto, args) \
- DEFINE_TRACE(name)
+ DEFINE_TRACE(name, COUNT_ARGS(args))
#undef TRACE_INCLUDE
#undef __TRACE_INCLUDE
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 05/10] macro: introduce COUNT_ARGS() macro
From: Alexei Starovoitov @ 2018-03-28 2:11 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
move COUNT_ARGS() macro from apparmor to generic header and extend it
to count till twelve.
COUNT() was an alternative name for this logic, but it's used for
different purpose in many other places.
Similarly for CONCATENATE() macro.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
include/linux/kernel.h | 7 +++++++
security/apparmor/include/path.h | 7 +------
2 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 3fd291503576..293fa0677fba 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -919,6 +919,13 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
#define swap(a, b) \
do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
+/* This counts to 12. Any more, it will return 13th argument. */
+#define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _n, X...) _n
+#define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+
+#define __CONCAT(a, b) a ## b
+#define CONCATENATE(a, b) __CONCAT(a, b)
+
/**
* container_of - cast a member of a structure out to the containing structure
* @ptr: the pointer to the member.
diff --git a/security/apparmor/include/path.h b/security/apparmor/include/path.h
index 05fb3305671e..e042b994f2b8 100644
--- a/security/apparmor/include/path.h
+++ b/security/apparmor/include/path.h
@@ -43,15 +43,10 @@ struct aa_buffers {
DECLARE_PER_CPU(struct aa_buffers, aa_buffers);
-#define COUNT_ARGS(X...) COUNT_ARGS_HELPER(, ##X, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
-#define COUNT_ARGS_HELPER(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, n, X...) n
-#define CONCAT(X, Y) X ## Y
-#define CONCAT_AFTER(X, Y) CONCAT(X, Y)
-
#define ASSIGN(FN, X, N) ((X) = FN(N))
#define EVAL1(FN, X) ASSIGN(FN, X, 0) /*X = FN(0)*/
#define EVAL2(FN, X, Y...) do { ASSIGN(FN, X, 1); EVAL1(FN, Y); } while (0)
-#define EVAL(FN, X...) CONCAT_AFTER(EVAL, COUNT_ARGS(X))(FN, X)
+#define EVAL(FN, X...) CONCATENATE(EVAL, COUNT_ARGS(X))(FN, X)
#define for_each_cpu_buffer(I) for ((I) = 0; (I) < MAX_PATH_BUFFERS; (I)++)
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 04/10] net/wireless/iwlwifi: fix iwlwifi_dev_ucode_error tracepoint
From: Alexei Starovoitov @ 2018-03-28 2:10 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
fix iwlwifi_dev_ucode_error tracepoint to pass pointer to a table
instead of all 17 arguments by value.
dvm/main.c and mvm/utils.c have 'struct iwl_error_event_table'
defined with very similar yet subtly different fields and offsets.
tracepoint is still common and using definition of 'struct iwl_error_event_table'
from dvm/commands.h while copying fields.
Long term this tracepoint probably should be split into two.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
drivers/net/wireless/intel/iwlwifi/dvm/main.c | 7 +---
.../wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h | 39 ++++++++++------------
drivers/net/wireless/intel/iwlwifi/iwl-devtrace.c | 1 +
drivers/net/wireless/intel/iwlwifi/mvm/utils.c | 7 +---
4 files changed, 21 insertions(+), 33 deletions(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
index d11d72615de2..e68254e12764 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
@@ -1651,12 +1651,7 @@ static void iwl_dump_nic_error_log(struct iwl_priv *priv)
priv->status, table.valid);
}
- trace_iwlwifi_dev_ucode_error(trans->dev, table.error_id, table.tsf_low,
- table.data1, table.data2, table.line,
- table.blink2, table.ilink1, table.ilink2,
- table.bcon_time, table.gp1, table.gp2,
- table.gp3, table.ucode_ver, table.hw_ver,
- 0, table.brd_ver);
+ trace_iwlwifi_dev_ucode_error(trans->dev, &table, 0, table.brd_ver);
IWL_ERR(priv, "0x%08X | %-28s\n", table.error_id,
desc_lookup(table.error_id));
IWL_ERR(priv, "0x%08X | uPc\n", table.pc);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h
index 9518a82f44c2..27e3e4e96aa2 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace-iwlwifi.h
@@ -126,14 +126,11 @@ TRACE_EVENT(iwlwifi_dev_tx,
__entry->framelen, __entry->skbaddr)
);
+struct iwl_error_event_table;
TRACE_EVENT(iwlwifi_dev_ucode_error,
- TP_PROTO(const struct device *dev, u32 desc, u32 tsf_low,
- u32 data1, u32 data2, u32 line, u32 blink2, u32 ilink1,
- u32 ilink2, u32 bcon_time, u32 gp1, u32 gp2, u32 rev_type,
- u32 major, u32 minor, u32 hw_ver, u32 brd_ver),
- TP_ARGS(dev, desc, tsf_low, data1, data2, line,
- blink2, ilink1, ilink2, bcon_time, gp1, gp2,
- rev_type, major, minor, hw_ver, brd_ver),
+ TP_PROTO(const struct device *dev, const struct iwl_error_event_table *table,
+ u32 hw_ver, u32 brd_ver),
+ TP_ARGS(dev, table, hw_ver, brd_ver),
TP_STRUCT__entry(
DEV_ENTRY
__field(u32, desc)
@@ -155,20 +152,20 @@ TRACE_EVENT(iwlwifi_dev_ucode_error,
),
TP_fast_assign(
DEV_ASSIGN;
- __entry->desc = desc;
- __entry->tsf_low = tsf_low;
- __entry->data1 = data1;
- __entry->data2 = data2;
- __entry->line = line;
- __entry->blink2 = blink2;
- __entry->ilink1 = ilink1;
- __entry->ilink2 = ilink2;
- __entry->bcon_time = bcon_time;
- __entry->gp1 = gp1;
- __entry->gp2 = gp2;
- __entry->rev_type = rev_type;
- __entry->major = major;
- __entry->minor = minor;
+ __entry->desc = table->error_id;
+ __entry->tsf_low = table->tsf_low;
+ __entry->data1 = table->data1;
+ __entry->data2 = table->data2;
+ __entry->line = table->line;
+ __entry->blink2 = table->blink2;
+ __entry->ilink1 = table->ilink1;
+ __entry->ilink2 = table->ilink2;
+ __entry->bcon_time = table->bcon_time;
+ __entry->gp1 = table->gp1;
+ __entry->gp2 = table->gp2;
+ __entry->rev_type = table->gp3;
+ __entry->major = table->ucode_ver;
+ __entry->minor = table->hw_ver;
__entry->hw_ver = hw_ver;
__entry->brd_ver = brd_ver;
),
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.c b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.c
index 50510fb6ab8c..6aa719865a58 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-devtrace.c
@@ -30,6 +30,7 @@
#ifndef __CHECKER__
#include "iwl-trans.h"
+#include "dvm/commands.h"
#define CREATE_TRACE_POINTS
#include "iwl-devtrace.h"
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index d65e1db7c097..5442ead876eb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -549,12 +549,7 @@ static void iwl_mvm_dump_lmac_error_log(struct iwl_mvm *mvm, u32 base)
IWL_ERR(mvm, "Loaded firmware version: %s\n", mvm->fw->fw_version);
- trace_iwlwifi_dev_ucode_error(trans->dev, table.error_id, table.tsf_low,
- table.data1, table.data2, table.data3,
- table.blink2, table.ilink1,
- table.ilink2, table.bcon_time, table.gp1,
- table.gp2, table.fw_rev_type, table.major,
- table.minor, table.hw_ver, table.brd_ver);
+ trace_iwlwifi_dev_ucode_error(trans->dev, &table, table.hw_ver, table.brd_ver);
IWL_ERR(mvm, "0x%08X | %-28s\n", table.error_id,
desc_lookup(table.error_id));
IWL_ERR(mvm, "0x%08X | trm_hw_status0\n", table.trm_hw_status0);
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 03/10] net/mac802154: disambiguate mac80215 vs mac802154 trace events
From: Alexei Starovoitov @ 2018-03-28 2:10 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
two trace events defined with the same name and both unused.
They conflict in allyesconfig build. Rename one of them.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
net/mac802154/trace.h | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/net/mac802154/trace.h b/net/mac802154/trace.h
index 2c8a43d3607f..df855c33daf2 100644
--- a/net/mac802154/trace.h
+++ b/net/mac802154/trace.h
@@ -33,7 +33,7 @@
/* Tracing for driver callbacks */
-DECLARE_EVENT_CLASS(local_only_evt,
+DECLARE_EVENT_CLASS(local_only_evt4,
TP_PROTO(struct ieee802154_local *local),
TP_ARGS(local),
TP_STRUCT__entry(
@@ -45,7 +45,7 @@ DECLARE_EVENT_CLASS(local_only_evt,
TP_printk(LOCAL_PR_FMT, LOCAL_PR_ARG)
);
-DEFINE_EVENT(local_only_evt, 802154_drv_return_void,
+DEFINE_EVENT(local_only_evt4, 802154_drv_return_void,
TP_PROTO(struct ieee802154_local *local),
TP_ARGS(local)
);
@@ -65,12 +65,12 @@ TRACE_EVENT(802154_drv_return_int,
__entry->ret)
);
-DEFINE_EVENT(local_only_evt, 802154_drv_start,
+DEFINE_EVENT(local_only_evt4, 802154_drv_start,
TP_PROTO(struct ieee802154_local *local),
TP_ARGS(local)
);
-DEFINE_EVENT(local_only_evt, 802154_drv_stop,
+DEFINE_EVENT(local_only_evt4, 802154_drv_stop,
TP_PROTO(struct ieee802154_local *local),
TP_ARGS(local)
);
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 02/10] net/mediatek: disambiguate mt76 vs mt7601u trace events
From: Alexei Starovoitov @ 2018-03-28 2:10 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
two trace events defined with the same name and both unused.
They conflict in allyesconfig build. Rename one of them.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
drivers/net/wireless/mediatek/mt7601u/trace.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/wireless/mediatek/mt7601u/trace.h b/drivers/net/wireless/mediatek/mt7601u/trace.h
index 289897300ef0..82c8898b9076 100644
--- a/drivers/net/wireless/mediatek/mt7601u/trace.h
+++ b/drivers/net/wireless/mediatek/mt7601u/trace.h
@@ -34,7 +34,7 @@
#define REG_PR_FMT "%04x=%08x"
#define REG_PR_ARG __entry->reg, __entry->val
-DECLARE_EVENT_CLASS(dev_reg_evt,
+DECLARE_EVENT_CLASS(dev_reg_evtu,
TP_PROTO(struct mt7601u_dev *dev, u32 reg, u32 val),
TP_ARGS(dev, reg, val),
TP_STRUCT__entry(
@@ -51,12 +51,12 @@ DECLARE_EVENT_CLASS(dev_reg_evt,
)
);
-DEFINE_EVENT(dev_reg_evt, reg_read,
+DEFINE_EVENT(dev_reg_evtu, reg_read,
TP_PROTO(struct mt7601u_dev *dev, u32 reg, u32 val),
TP_ARGS(dev, reg, val)
);
-DEFINE_EVENT(dev_reg_evt, reg_write,
+DEFINE_EVENT(dev_reg_evtu, reg_write,
TP_PROTO(struct mt7601u_dev *dev, u32 reg, u32 val),
TP_ARGS(dev, reg, val)
);
--
2.9.5
^ permalink raw reply related
* [PATCH v7 bpf-next 01/10] treewide: remove large struct-pass-by-value from tracepoint arguments
From: Alexei Starovoitov @ 2018-03-28 2:10 UTC (permalink / raw)
To: davem
Cc: daniel, torvalds, peterz, rostedt, mathieu.desnoyers, netdev,
kernel-team, linux-api
In-Reply-To: <20180328021105.4061744-1-ast@fb.com>
From: Alexei Starovoitov <ast@kernel.org>
- fix trace_hfi1_ctxt_info() to pass large struct by reference instead of by value
- convert 'type array[]' tracepoint arguments into 'type *array',
since compiler will warn that sizeof('type array[]') == sizeof('type *array')
and later should be used instead
The CAST_TO_U64 macro in the later patch will enforce that tracepoint
arguments can only be integers, pointers, or less than 8 byte structures.
Larger structures should be passed by reference.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
drivers/infiniband/hw/hfi1/file_ops.c | 2 +-
drivers/infiniband/hw/hfi1/trace_ctxts.h | 12 ++++++------
include/trace/events/f2fs.h | 2 +-
net/wireless/trace.h | 2 +-
sound/firewire/amdtp-stream-trace.h | 2 +-
5 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index 41fafebe3b0d..da4aa1a95b11 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -1153,7 +1153,7 @@ static int get_ctxt_info(struct hfi1_filedata *fd, unsigned long arg, u32 len)
cinfo.sdma_ring_size = fd->cq->nentries;
cinfo.rcvegr_size = uctxt->egrbufs.rcvtid_size;
- trace_hfi1_ctxt_info(uctxt->dd, uctxt->ctxt, fd->subctxt, cinfo);
+ trace_hfi1_ctxt_info(uctxt->dd, uctxt->ctxt, fd->subctxt, &cinfo);
if (copy_to_user((void __user *)arg, &cinfo, len))
return -EFAULT;
diff --git a/drivers/infiniband/hw/hfi1/trace_ctxts.h b/drivers/infiniband/hw/hfi1/trace_ctxts.h
index 4eb4cc798035..e00c8a7d559c 100644
--- a/drivers/infiniband/hw/hfi1/trace_ctxts.h
+++ b/drivers/infiniband/hw/hfi1/trace_ctxts.h
@@ -106,7 +106,7 @@ TRACE_EVENT(hfi1_uctxtdata,
TRACE_EVENT(hfi1_ctxt_info,
TP_PROTO(struct hfi1_devdata *dd, unsigned int ctxt,
unsigned int subctxt,
- struct hfi1_ctxt_info cinfo),
+ struct hfi1_ctxt_info *cinfo),
TP_ARGS(dd, ctxt, subctxt, cinfo),
TP_STRUCT__entry(DD_DEV_ENTRY(dd)
__field(unsigned int, ctxt)
@@ -120,11 +120,11 @@ TRACE_EVENT(hfi1_ctxt_info,
TP_fast_assign(DD_DEV_ASSIGN(dd);
__entry->ctxt = ctxt;
__entry->subctxt = subctxt;
- __entry->egrtids = cinfo.egrtids;
- __entry->rcvhdrq_cnt = cinfo.rcvhdrq_cnt;
- __entry->rcvhdrq_size = cinfo.rcvhdrq_entsize;
- __entry->sdma_ring_size = cinfo.sdma_ring_size;
- __entry->rcvegr_size = cinfo.rcvegr_size;
+ __entry->egrtids = cinfo->egrtids;
+ __entry->rcvhdrq_cnt = cinfo->rcvhdrq_cnt;
+ __entry->rcvhdrq_size = cinfo->rcvhdrq_entsize;
+ __entry->sdma_ring_size = cinfo->sdma_ring_size;
+ __entry->rcvegr_size = cinfo->rcvegr_size;
),
TP_printk("[%s] ctxt %u:%u " CINFO_FMT,
__get_str(dev),
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 06c87f9f720c..795698925d20 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -491,7 +491,7 @@ DEFINE_EVENT(f2fs__truncate_node, f2fs_truncate_node,
TRACE_EVENT(f2fs_truncate_partial_nodes,
- TP_PROTO(struct inode *inode, nid_t nid[], int depth, int err),
+ TP_PROTO(struct inode *inode, nid_t *nid, int depth, int err),
TP_ARGS(inode, nid, depth, err),
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 5152938b358d..018c81fa72fb 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -3137,7 +3137,7 @@ TRACE_EVENT(rdev_start_radar_detection,
TRACE_EVENT(rdev_set_mcast_rate,
TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
- int mcast_rate[NUM_NL80211_BANDS]),
+ int *mcast_rate),
TP_ARGS(wiphy, netdev, mcast_rate),
TP_STRUCT__entry(
WIPHY_ENTRY
diff --git a/sound/firewire/amdtp-stream-trace.h b/sound/firewire/amdtp-stream-trace.h
index ea0d486652c8..54cdd4ffa9ce 100644
--- a/sound/firewire/amdtp-stream-trace.h
+++ b/sound/firewire/amdtp-stream-trace.h
@@ -14,7 +14,7 @@
#include <linux/tracepoint.h>
TRACE_EVENT(in_packet,
- TP_PROTO(const struct amdtp_stream *s, u32 cycles, u32 cip_header[2], unsigned int payload_length, unsigned int index),
+ TP_PROTO(const struct amdtp_stream *s, u32 cycles, u32 *cip_header, unsigned int payload_length, unsigned int index),
TP_ARGS(s, cycles, cip_header, payload_length, index),
TP_STRUCT__entry(
__field(unsigned int, second)
--
2.9.5
^ 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