Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:

 - a couple of hotfixes

 - almost all of the rest of MM

 - lib/ updates

 - binfmt_elf updates

 - autofs updates

 - quite a lot of misc fixes and updates
    - reiserfs, fatfs
    - signals
    - exec
    - cpumask
    - rapidio
    - sysctl
    - pids
    - eventfd
    - gcov
    - panic
    - pps

 - gdb script updates

 - ipc updates

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (126 commits)
  mm: memcontrol: fix NUMA round-robin reclaim at intermediate level
  mm: memcontrol: fix recursive statistics correctness & scalabilty
  mm: memcontrol: move stat/event counting functions out-of-line
  mm: memcontrol: make cgroup stats and events query API explicitly local
  drivers/virt/fsl_hypervisor.c: prevent integer overflow in ioctl
  drivers/virt/fsl_hypervisor.c: dereferencing error pointers in ioctl
  mm, memcg: rename ambiguously named memory.stat counters and functions
  arch: remove <asm/sizes.h> and <asm-generic/sizes.h>
  treewide: replace #include <asm/sizes.h> with #include <linux/sizes.h>
  fs/block_dev.c: Remove duplicate header
  fs/cachefiles/namei.c: remove duplicate header
  include/linux/sched/signal.h: replace `tsk' with `task'
  fs/coda/psdev.c: remove duplicate header
  ipc: do cyclic id allocation for the ipc object.
  ipc: conserve sequence numbers in ipcmni_extend mode
  ipc: allow boot time extension of IPCMNI from 32k to 16M
  ipc/mqueue: optimize msg_get()
  ipc/mqueue: remove redundant wq task assignment
  ipc: prevent lockup on alloc_msg and free_msg
  scripts/gdb: print cached rate in lx-clk-summary
  ...

1 files changed, 93 insertions, 12 deletions

diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index 2cf422db5d18..07aaf9b82241 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -1,8 +1,11 @@
 #ifndef _LINUX_PSI_TYPES_H
 #define _LINUX_PSI_TYPES_H
 
+#include <linux/kthread.h>
 #include <linux/seqlock.h>
 #include <linux/types.h>
+#include <linux/kref.h>
+#include <linux/wait.h>
 
 #ifdef CONFIG_PSI
 
@@ -11,7 +14,7 @@ enum psi_task_count {
 	NR_IOWAIT,
 	NR_MEMSTALL,
 	NR_RUNNING,
-	NR_PSI_TASK_COUNTS,
+	NR_PSI_TASK_COUNTS = 3,
 };
 
 /* Task state bitmasks */
@@ -24,7 +27,7 @@ enum psi_res {
 	PSI_IO,
 	PSI_MEM,
 	PSI_CPU,
-	NR_PSI_RESOURCES,
+	NR_PSI_RESOURCES = 3,
 };
 
 /*
@@ -41,7 +44,13 @@ enum psi_states {
 	PSI_CPU_SOME,
 	/* Only per-CPU, to weigh the CPU in the global average: */
 	PSI_NONIDLE,
-	NR_PSI_STATES,
+	NR_PSI_STATES = 6,
+};
+
+enum psi_aggregators {
+	PSI_AVGS = 0,
+	PSI_POLL,
+	NR_PSI_AGGREGATORS,
 };
 
 struct psi_group_cpu {
@@ -53,6 +62,9 @@ struct psi_group_cpu {
 	/* States of the tasks belonging to this group */
 	unsigned int tasks[NR_PSI_TASK_COUNTS];
 
+	/* Aggregate pressure state derived from the tasks */
+	u32 state_mask;
+
 	/* Period time sampling buckets for each state of interest (ns) */
 	u32 times[NR_PSI_STATES];
 
@@ -62,25 +74,94 @@ struct psi_group_cpu {
 	/* 2nd cacheline updated by the aggregator */
 
 	/* Delta detection against the sampling buckets */
-	u32 times_prev[NR_PSI_STATES] ____cacheline_aligned_in_smp;
+	u32 times_prev[NR_PSI_AGGREGATORS][NR_PSI_STATES]
+			____cacheline_aligned_in_smp;
+};
+
+/* PSI growth tracking window */
+struct psi_window {
+	/* Window size in ns */
+	u64 size;
+
+	/* Start time of the current window in ns */
+	u64 start_time;
+
+	/* Value at the start of the window */
+	u64 start_value;
+
+	/* Value growth in the previous window */
+	u64 prev_growth;
+};
+
+struct psi_trigger {
+	/* PSI state being monitored by the trigger */
+	enum psi_states state;
+
+	/* User-spacified threshold in ns */
+	u64 threshold;
+
+	/* List node inside triggers list */
+	struct list_head node;
+
+	/* Backpointer needed during trigger destruction */
+	struct psi_group *group;
+
+	/* Wait queue for polling */
+	wait_queue_head_t event_wait;
+
+	/* Pending event flag */
+	int event;
+
+	/* Tracking window */
+	struct psi_window win;
+
+	/*
+	 * Time last event was generated. Used for rate-limiting
+	 * events to one per window
+	 */
+	u64 last_event_time;
+
+	/* Refcounting to prevent premature destruction */
+	struct kref refcount;
 };
 
 struct psi_group {
-	/* Protects data updated during an aggregation */
-	struct mutex stat_lock;
+	/* Protects data used by the aggregator */
+	struct mutex avgs_lock;
 
 	/* Per-cpu task state & time tracking */
 	struct psi_group_cpu __percpu *pcpu;
 
-	/* Periodic aggregation state */
-	u64 total_prev[NR_PSI_STATES - 1];
-	u64 last_update;
-	u64 next_update;
-	struct delayed_work clock_work;
+	/* Running pressure averages */
+	u64 avg_total[NR_PSI_STATES - 1];
+	u64 avg_last_update;
+	u64 avg_next_update;
+
+	/* Aggregator work control */
+	struct delayed_work avgs_work;
 
 	/* Total stall times and sampled pressure averages */
-	u64 total[NR_PSI_STATES - 1];
+	u64 total[NR_PSI_AGGREGATORS][NR_PSI_STATES - 1];
 	unsigned long avg[NR_PSI_STATES - 1][3];
+
+	/* Monitor work control */
+	atomic_t poll_scheduled;
+	struct kthread_worker __rcu *poll_kworker;
+	struct kthread_delayed_work poll_work;
+
+	/* Protects data used by the monitor */
+	struct mutex trigger_lock;
+
+	/* Configured polling triggers */
+	struct list_head triggers;
+	u32 nr_triggers[NR_PSI_STATES - 1];
+	u32 poll_states;
+	u64 poll_min_period;
+
+	/* Total stall times at the start of monitor activation */
+	u64 polling_total[NR_PSI_STATES - 1];
+	u64 polling_next_update;
+	u64 polling_until;
 };
 
 #else /* CONFIG_PSI */