fs: kernfs: add poll file operation

Patch series "psi: pressure stall monitors", v3.

Android is adopting psi to detect and remedy memory pressure that
results in stuttering and decreased responsiveness on mobile devices.

Psi gives us the stall information, but because we're dealing with
latencies in the millisecond range, periodically reading the pressure
files to detect stalls in a timely fashion is not feasible.  Psi also
doesn't aggregate its averages at a high enough frequency right now.

This patch series extends the psi interface such that users can
configure sensitive latency thresholds and use poll() and friends to be
notified when these are breached.

As high-frequency aggregation is costly, it implements an aggregation
method that is optimized for fast, short-interval averaging, and makes
the aggregation frequency adaptive, such that high-frequency updates
only happen while monitored stall events are actively occurring.

With these patches applied, Android can monitor for, and ward off,
mounting memory shortages before they cause problems for the user.  For
example, using memory stall monitors in userspace low memory killer
daemon (lmkd) we can detect mounting pressure and kill less important
processes before device becomes visibly sluggish.

In our memory stress testing psi memory monitors produce roughly 10x
less false positives compared to vmpressure signals.  Having ability to
specify multiple triggers for the same psi metric allows other parts of
Android framework to monitor memory state of the device and act
accordingly.

The new interface is straightforward.  The user opens one of the
pressure files for writing and writes a trigger description into the
file descriptor that defines the stall state - some or full, and the
maximum stall time over a given window of time.  E.g.:

        /* Signal when stall time exceeds 100ms of a 1s window */
        char trigger[] = "full 100000 1000000";
        fd = open("/proc/pressure/memory");
        write(fd, trigger, sizeof(trigger));
        while (poll() >= 0) {
                ...
        }
        close(fd);

When the monitored stall state is entered, psi adapts its aggregation
frequency according to what the configured time window requires in order
to emit event signals in a timely fashion.  Once the stalling subsides,
aggregation reverts back to normal.

The trigger is associated with the open file descriptor.  To stop
monitoring, the user only needs to close the file descriptor and the
trigger is discarded.

Patches 1-4 prepare the psi code for polling support.  Patch 5
implements the adaptive polling logic, the pressure growth detection
optimized for short intervals, and hooks up write() and poll() on the
pressure files.

The patches were developed in collaboration with Johannes Weiner.

This patch (of 5):

Kernfs has a standardized poll/notification mechanism for waking all
pollers on all fds when a filesystem node changes.  To allow polling for
custom events, add a .poll callback that can override the default.

This is in preparation for pollable cgroup pressure files which have
per-fd trigger configurations.

Link: http://lkml.kernel.org/r/20190124211518.244221-2-surenb@google.comSigned-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

fs/kernfs/file.c

@@ -832,26 +832,35 @@ void kernfs_drain_open_files(struct kernfs_node *kn)
  * to see if it supports poll (Neither 'poll' nor 'select' return
  * an appropriate error code).  When in doubt, set a suitable timeout value.
  */
-static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait)
+__poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait)
 {
-	struct kernfs_open_file *of = kernfs_of(filp);
-	struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry);
+	struct kernfs_node *kn = kernfs_dentry_node(of->file->f_path.dentry);
 	struct kernfs_open_node *on = kn->attr.open;
 
-	if (!kernfs_get_active(kn))
-		goto trigger;
-
-	poll_wait(filp, &on->poll, wait);
-
-	kernfs_put_active(kn);
+	poll_wait(of->file, &on->poll, wait);
 
 	if (of->event != atomic_read(&on->event))
-		goto trigger;
+		return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;
 
 	return DEFAULT_POLLMASK;
+}
+
+static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait)
+{
+	struct kernfs_open_file *of = kernfs_of(filp);
+	struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry);
+	__poll_t ret;
 
- trigger:
+	if (!kernfs_get_active(kn))
 		return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;
+
+	if (kn->attr.ops->poll)
+		ret = kn->attr.ops->poll(of, wait);
+	else
+		ret = kernfs_generic_poll(of, wait);
+
+	kernfs_put_active(kn);
+	return ret;
 }
 
 static void kernfs_notify_workfn(struct work_struct *work)

include/linux/kernfs.h

@@ -25,6 +25,7 @@ struct seq_file;
 struct vm_area_struct;
 struct super_block;
 struct file_system_type;
+struct poll_table_struct;
 
 struct kernfs_open_node;
 struct kernfs_iattrs;
@@ -261,6 +262,9 @@ struct kernfs_ops {
 	ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes,
 			 loff_t off);
 
+	__poll_t (*poll)(struct kernfs_open_file *of,
+			 struct poll_table_struct *pt);
+
 	int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -350,6 +354,8 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
 int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 		     const char *new_name, const void *new_ns);
 int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr);
+__poll_t kernfs_generic_poll(struct kernfs_open_file *of,
+			     struct poll_table_struct *pt);
 void kernfs_notify(struct kernfs_node *kn);
 
 const void *kernfs_super_ns(struct super_block *sb);