summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-11-30 14:12:13 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2019-11-30 14:12:13 -0800
commit6a965666b7e7475c2f8c8e724703db58b8a8a445 (patch)
tree0fcd268af15fb52cd32343572f5eaee7bf52e0d8 /kernel
parent32ef9553635ab1236c33951a8bd9b5af1c3b1646 (diff)
parent3c0edea9b29f9be6c093f236f762202b30ac9431 (diff)
downloadlinux-6a965666b7e7475c2f8c8e724703db58b8a8a445.tar.bz2
Merge tag 'notifications-pipe-prep-20191115' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs
Pull pipe rework from David Howells: "This is my set of preparatory patches for building a general notification queue on top of pipes. It makes a number of significant changes: - It removes the nr_exclusive argument from __wake_up_sync_key() as this is always 1. This prepares for the next step: - Adds wake_up_interruptible_sync_poll_locked() so that poll can be woken up from a function that's holding the poll waitqueue spinlock. - Change the pipe buffer ring to be managed in terms of unbounded head and tail indices rather than bounded index and length. This means that reading the pipe only needs to modify one index, not two. - A selection of helper functions are provided to query the state of the pipe buffer, plus a couple to apply updates to the pipe indices. - The pipe ring is allowed to have kernel-reserved slots. This allows many notification messages to be spliced in by the kernel without allowing userspace to pin too many pages if it writes to the same pipe. - Advance the head and tail indices inside the pipe waitqueue lock and use wake_up_interruptible_sync_poll_locked() to poke poll without having to take the lock twice. - Rearrange pipe_write() to preallocate the buffer it is going to write into and then drop the spinlock. This allows kernel notifications to then be added the ring whilst it is filling the buffer it allocated. The read side is stalled because the pipe mutex is still held. - Don't wake up readers on a pipe if there was already data in it when we added more. - Don't wake up writers on a pipe if the ring wasn't full before we removed a buffer" * tag 'notifications-pipe-prep-20191115' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs: pipe: Remove sync on wake_ups pipe: Increase the writer-wakeup threshold to reduce context-switch count pipe: Check for ring full inside of the spinlock in pipe_write() pipe: Remove redundant wakeup from pipe_write() pipe: Rearrange sequence in pipe_write() to preallocate slot pipe: Conditionalise wakeup in pipe_read() pipe: Advance tail pointer inside of wait spinlock in pipe_read() pipe: Allow pipes to have kernel-reserved slots pipe: Use head and tail pointers for the ring, not cursor and length Add wake_up_interruptible_sync_poll_locked() Remove the nr_exclusive argument from __wake_up_sync_key() pipe: Reduce #inclusion of pipe_fs_i.h
Diffstat (limited to 'kernel')
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/sched/wait.c37
2 files changed, 28 insertions, 11 deletions
diff --git a/kernel/exit.c b/kernel/exit.c
index 0bac4b60d5f3..bcbd59888e67 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1409,7 +1409,7 @@ static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode,
void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
{
__wake_up_sync_key(&parent->signal->wait_chldexit,
- TASK_INTERRUPTIBLE, 1, p);
+ TASK_INTERRUPTIBLE, p);
}
static long do_wait(struct wait_opts *wo)
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index c1e566a114ca..ba059fbfc53a 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -169,7 +169,6 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark);
* __wake_up_sync_key - wake up threads blocked on a waitqueue.
* @wq_head: the waitqueue
* @mode: which threads
- * @nr_exclusive: how many wake-one or wake-many threads to wake up
* @key: opaque value to be passed to wakeup targets
*
* The sync wakeup differs that the waker knows that it will schedule
@@ -183,26 +182,44 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark);
* accessing the task state.
*/
void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode,
- int nr_exclusive, void *key)
+ void *key)
{
- int wake_flags = 1; /* XXX WF_SYNC */
-
if (unlikely(!wq_head))
return;
- if (unlikely(nr_exclusive != 1))
- wake_flags = 0;
-
- __wake_up_common_lock(wq_head, mode, nr_exclusive, wake_flags, key);
+ __wake_up_common_lock(wq_head, mode, 1, WF_SYNC, key);
}
EXPORT_SYMBOL_GPL(__wake_up_sync_key);
+/**
+ * __wake_up_locked_sync_key - wake up a thread blocked on a locked waitqueue.
+ * @wq_head: the waitqueue
+ * @mode: which threads
+ * @key: opaque value to be passed to wakeup targets
+ *
+ * The sync wakeup differs in that the waker knows that it will schedule
+ * away soon, so while the target thread will be woken up, it will not
+ * be migrated to another CPU - ie. the two threads are 'synchronized'
+ * with each other. This can prevent needless bouncing between CPUs.
+ *
+ * On UP it can prevent extra preemption.
+ *
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
+ */
+void __wake_up_locked_sync_key(struct wait_queue_head *wq_head,
+ unsigned int mode, void *key)
+{
+ __wake_up_common(wq_head, mode, 1, WF_SYNC, key, NULL);
+}
+EXPORT_SYMBOL_GPL(__wake_up_locked_sync_key);
+
/*
* __wake_up_sync - see __wake_up_sync_key()
*/
-void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive)
+void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode)
{
- __wake_up_sync_key(wq_head, mode, nr_exclusive, NULL);
+ __wake_up_sync_key(wq_head, mode, NULL);
}
EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */