Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer updates from Thomas Gleixner:
 "The timer departement presents:

   - A rather large rework of the hrtimer infrastructure which
     introduces softirq based hrtimers to replace the spread of
     hrtimer/tasklet combos which force the actual callback execution
     into softirq context. The approach is completely different from the
     initial implementation which you cursed at 10 years ago rightfully.

     The softirq based timers have their own queues and there is no
     nasty indirection and list reshuffling in the hard interrupt
     anymore. This comes with conversion of some of the hrtimer/tasklet
     users, the rest and the final removal of that horrible interface
     will come towards the end of the merge window or go through the
     relevant maintainer trees.

     Note: The top commit merged the last minute bugfix for the 10 years
     old CPU hotplug bug as I wanted to make sure that I fatfinger the
     merge conflict resolution myself.

   - The overhaul of the STM32 clocksource/clockevents driver

   - A new driver for the Spreadtrum SC9860 timer

   - A new driver dor the Actions Semi S700 timer

   - The usual set of fixes and updates all over the place"

* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
  usb/gadget/NCM: Replace tasklet with softirq hrtimer
  ALSA/dummy: Replace tasklet with softirq hrtimer
  hrtimer: Implement SOFT/HARD clock base selection
  hrtimer: Implement support for softirq based hrtimers
  hrtimer: Prepare handling of hard and softirq based hrtimers
  hrtimer: Add clock bases and hrtimer mode for softirq context
  hrtimer: Use irqsave/irqrestore around __run_hrtimer()
  hrtimer: Factor out __hrtimer_next_event_base()
  hrtimer: Factor out __hrtimer_start_range_ns()
  hrtimer: Remove the 'base' parameter from hrtimer_reprogram()
  hrtimer: Make remote enqueue decision less restrictive
  hrtimer: Unify remote enqueue handling
  hrtimer: Unify hrtimer removal handling
  hrtimer: Make hrtimer_force_reprogramm() unconditionally available
  hrtimer: Make hrtimer_reprogramm() unconditional
  hrtimer: Make hrtimer_cpu_base.next_timer handling unconditional
  hrtimer: Make the remote enqueue check unconditional
  hrtimer: Use accesor functions instead of direct access
  hrtimer: Make the hrtimer_cpu_base::hres_active field unconditional, to simplify the code
  hrtimer: Make room in 'struct hrtimer_cpu_base'
  ...

3 files changed, 114 insertions, 61 deletions

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 012c37fdb688..c7902ca7c9f4 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -28,13 +28,29 @@ struct hrtimer_cpu_base;
 
 /*
  * Mode arguments of xxx_hrtimer functions:
+ *
+ * HRTIMER_MODE_ABS		- Time value is absolute
+ * HRTIMER_MODE_REL		- Time value is relative to now
+ * HRTIMER_MODE_PINNED		- Timer is bound to CPU (is only considered
+ *				  when starting the timer)
+ * HRTIMER_MODE_SOFT		- Timer callback function will be executed in
+ *				  soft irq context
  */
 enum hrtimer_mode {
-	HRTIMER_MODE_ABS = 0x0,		/* Time value is absolute */
-	HRTIMER_MODE_REL = 0x1,		/* Time value is relative to now */
-	HRTIMER_MODE_PINNED = 0x02,	/* Timer is bound to CPU */
-	HRTIMER_MODE_ABS_PINNED = 0x02,
-	HRTIMER_MODE_REL_PINNED = 0x03,
+	HRTIMER_MODE_ABS	= 0x00,
+	HRTIMER_MODE_REL	= 0x01,
+	HRTIMER_MODE_PINNED	= 0x02,
+	HRTIMER_MODE_SOFT	= 0x04,
+
+	HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED,
+	HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED,
+
+	HRTIMER_MODE_ABS_SOFT	= HRTIMER_MODE_ABS | HRTIMER_MODE_SOFT,
+	HRTIMER_MODE_REL_SOFT	= HRTIMER_MODE_REL | HRTIMER_MODE_SOFT,
+
+	HRTIMER_MODE_ABS_PINNED_SOFT = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_SOFT,
+	HRTIMER_MODE_REL_PINNED_SOFT = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_SOFT,
+
 };
 
 /*
@@ -87,6 +103,7 @@ enum hrtimer_restart {
  * @base:	pointer to the timer base (per cpu and per clock)
  * @state:	state information (See bit values above)
  * @is_rel:	Set if the timer was armed relative
+ * @is_soft:	Set if hrtimer will be expired in soft interrupt context.
  *
  * The hrtimer structure must be initialized by hrtimer_init()
  */
@@ -97,6 +114,7 @@ struct hrtimer {
 	struct hrtimer_clock_base	*base;
 	u8				state;
 	u8				is_rel;
+	u8				is_soft;
 };
 
 /**
@@ -112,9 +130,9 @@ struct hrtimer_sleeper {
 };
 
 #ifdef CONFIG_64BIT
-# define HRTIMER_CLOCK_BASE_ALIGN	64
+# define __hrtimer_clock_base_align	____cacheline_aligned
 #else
-# define HRTIMER_CLOCK_BASE_ALIGN	32
+# define __hrtimer_clock_base_align
 #endif
 
 /**
@@ -123,48 +141,57 @@ struct hrtimer_sleeper {
  * @index:		clock type index for per_cpu support when moving a
  *			timer to a base on another cpu.
  * @clockid:		clock id for per_cpu support
+ * @seq:		seqcount around __run_hrtimer
+ * @running:		pointer to the currently running hrtimer
  * @active:		red black tree root node for the active timers
  * @get_time:		function to retrieve the current time of the clock
  * @offset:		offset of this clock to the monotonic base
  */
 struct hrtimer_clock_base {
 	struct hrtimer_cpu_base	*cpu_base;
-	int			index;
+	unsigned int		index;
 	clockid_t		clockid;
+	seqcount_t		seq;
+	struct hrtimer		*running;
 	struct timerqueue_head	active;
 	ktime_t			(*get_time)(void);
 	ktime_t			offset;
-} __attribute__((__aligned__(HRTIMER_CLOCK_BASE_ALIGN)));
+} __hrtimer_clock_base_align;
 
 enum  hrtimer_base_type {
 	HRTIMER_BASE_MONOTONIC,
 	HRTIMER_BASE_REALTIME,
 	HRTIMER_BASE_BOOTTIME,
 	HRTIMER_BASE_TAI,
+	HRTIMER_BASE_MONOTONIC_SOFT,
+	HRTIMER_BASE_REALTIME_SOFT,
+	HRTIMER_BASE_BOOTTIME_SOFT,
+	HRTIMER_BASE_TAI_SOFT,
 	HRTIMER_MAX_CLOCK_BASES,
 };
 
-/*
+/**
  * struct hrtimer_cpu_base - the per cpu clock bases
  * @lock:		lock protecting the base and associated clock bases
  *			and timers
- * @seq:		seqcount around __run_hrtimer
- * @running:		pointer to the currently running hrtimer
  * @cpu:		cpu number
  * @active_bases:	Bitfield to mark bases with active timers
  * @clock_was_set_seq:	Sequence counter of clock was set events
- * @migration_enabled:	The migration of hrtimers to other cpus is enabled
- * @nohz_active:	The nohz functionality is enabled
- * @expires_next:	absolute time of the next event which was scheduled
- *			via clock_set_next_event()
- * @next_timer:		Pointer to the first expiring timer
- * @in_hrtirq:		hrtimer_interrupt() is currently executing
  * @hres_active:	State of high resolution mode
+ * @in_hrtirq:		hrtimer_interrupt() is currently executing
  * @hang_detected:	The last hrtimer interrupt detected a hang
+ * @softirq_activated:	displays, if the softirq is raised - update of softirq
+ *			related settings is not required then.
  * @nr_events:		Total number of hrtimer interrupt events
  * @nr_retries:		Total number of hrtimer interrupt retries
  * @nr_hangs:		Total number of hrtimer interrupt hangs
  * @max_hang_time:	Maximum time spent in hrtimer_interrupt
+ * @expires_next:	absolute time of the next event, is required for remote
+ *			hrtimer enqueue; it is the total first expiry time (hard
+ *			and soft hrtimer are taken into account)
+ * @next_timer:		Pointer to the first expiring timer
+ * @softirq_expires_next: Time to check, if soft queues needs also to be expired
+ * @softirq_next_timer: Pointer to the first expiring softirq based timer
  * @clock_base:		array of clock bases for this cpu
  *
  * Note: next_timer is just an optimization for __remove_hrtimer().
@@ -173,31 +200,28 @@ enum  hrtimer_base_type {
  */
 struct hrtimer_cpu_base {
 	raw_spinlock_t			lock;
-	seqcount_t			seq;
-	struct hrtimer			*running;
 	unsigned int			cpu;
 	unsigned int			active_bases;
 	unsigned int			clock_was_set_seq;
-	bool				migration_enabled;
-	bool				nohz_active;
+	unsigned int			hres_active		: 1,
+					in_hrtirq		: 1,
+					hang_detected		: 1,
+					softirq_activated       : 1;
 #ifdef CONFIG_HIGH_RES_TIMERS
-	unsigned int			in_hrtirq	: 1,
-					hres_active	: 1,
-					hang_detected	: 1;
-	ktime_t				expires_next;
-	struct hrtimer			*next_timer;
 	unsigned int			nr_events;
-	unsigned int			nr_retries;
-	unsigned int			nr_hangs;
+	unsigned short			nr_retries;
+	unsigned short			nr_hangs;
 	unsigned int			max_hang_time;
 #endif
+	ktime_t				expires_next;
+	struct hrtimer			*next_timer;
+	ktime_t				softirq_expires_next;
+	struct hrtimer			*softirq_next_timer;
 	struct hrtimer_clock_base	clock_base[HRTIMER_MAX_CLOCK_BASES];
 } ____cacheline_aligned;
 
 static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
 {
-	BUILD_BUG_ON(sizeof(struct hrtimer_clock_base) > HRTIMER_CLOCK_BASE_ALIGN);
-
 	timer->node.expires = time;
 	timer->_softexpires = time;
 }
@@ -266,16 +290,17 @@ static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
 	return timer->base->get_time();
 }
 
+static inline int hrtimer_is_hres_active(struct hrtimer *timer)
+{
+	return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ?
+		timer->base->cpu_base->hres_active : 0;
+}
+
 #ifdef CONFIG_HIGH_RES_TIMERS
 struct clock_event_device;
 
 extern void hrtimer_interrupt(struct clock_event_device *dev);
 
-static inline int hrtimer_is_hres_active(struct hrtimer *timer)
-{
-	return timer->base->cpu_base->hres_active;
-}
-
 /*
  * The resolution of the clocks. The resolution value is returned in
  * the clock_getres() system call to give application programmers an
@@ -298,11 +323,6 @@ extern unsigned int hrtimer_resolution;
 
 #define hrtimer_resolution	(unsigned int)LOW_RES_NSEC
 
-static inline int hrtimer_is_hres_active(struct hrtimer *timer)
-{
-	return 0;
-}
-
 static inline void clock_was_set_delayed(void) { }
 
 #endif
@@ -365,11 +385,12 @@ extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 				   u64 range_ns, const enum hrtimer_mode mode);
 
 /**
- * hrtimer_start - (re)start an hrtimer on the current CPU
+ * hrtimer_start - (re)start an hrtimer
  * @timer:	the timer to be added
  * @tim:	expiry time
- * @mode:	expiry mode: absolute (HRTIMER_MODE_ABS) or
- *		relative (HRTIMER_MODE_REL)
+ * @mode:	timer mode: absolute (HRTIMER_MODE_ABS) or
+ *		relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED);
+ *		softirq based mode is considered for debug purpose only!
  */
 static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim,
 				 const enum hrtimer_mode mode)
@@ -422,7 +443,7 @@ static inline int hrtimer_is_queued(struct hrtimer *timer)
  */
 static inline int hrtimer_callback_running(struct hrtimer *timer)
 {
-	return timer->base->cpu_base->running == timer;
+	return timer->base->running == timer;
 }
 
 /* Forward a hrtimer so it expires after now: */
@@ -466,7 +487,7 @@ extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta,
 extern int schedule_hrtimeout_range_clock(ktime_t *expires,
 					  u64 delta,
 					  const enum hrtimer_mode mode,
-					  int clock);
+					  clockid_t clock_id);
 extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
 
 /* Soft interrupt function to run the hrtimer queues: */
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 672c4f32311e..c85704fcdbd2 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -42,13 +42,26 @@ struct cpu_timer_list {
 #define CLOCKFD			CPUCLOCK_MAX
 #define CLOCKFD_MASK		(CPUCLOCK_PERTHREAD_MASK|CPUCLOCK_CLOCK_MASK)
 
-#define MAKE_PROCESS_CPUCLOCK(pid, clock) \
-	((~(clockid_t) (pid) << 3) | (clockid_t) (clock))
-#define MAKE_THREAD_CPUCLOCK(tid, clock) \
-	MAKE_PROCESS_CPUCLOCK((tid), (clock) | CPUCLOCK_PERTHREAD_MASK)
+static inline clockid_t make_process_cpuclock(const unsigned int pid,
+		const clockid_t clock)
+{
+	return ((~pid) << 3) | clock;
+}
+static inline clockid_t make_thread_cpuclock(const unsigned int tid,
+		const clockid_t clock)
+{
+	return make_process_cpuclock(tid, clock | CPUCLOCK_PERTHREAD_MASK);
+}
 
-#define FD_TO_CLOCKID(fd)	((~(clockid_t) (fd) << 3) | CLOCKFD)
-#define CLOCKID_TO_FD(clk)	((unsigned int) ~((clk) >> 3))
+static inline clockid_t fd_to_clockid(const int fd)
+{
+	return make_process_cpuclock((unsigned int) fd, CLOCKFD);
+}
+
+static inline int clockid_to_fd(const clockid_t clk)
+{
+	return ~(clk >> 3);
+}
 
 #define REQUEUE_PENDING 1
 
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index 16e305e69f34..a57e4ee989d6 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -136,6 +136,24 @@ DEFINE_EVENT(timer_class, timer_cancel,
 	TP_ARGS(timer)
 );
 
+#define decode_clockid(type)						\
+	__print_symbolic(type,						\
+		{ CLOCK_REALTIME,	"CLOCK_REALTIME"	},	\
+		{ CLOCK_MONOTONIC,	"CLOCK_MONOTONIC"	},	\
+		{ CLOCK_BOOTTIME,	"CLOCK_BOOTTIME"	},	\
+		{ CLOCK_TAI,		"CLOCK_TAI"		})
+
+#define decode_hrtimer_mode(mode)					\
+	__print_symbolic(mode,						\
+		{ HRTIMER_MODE_ABS,		"ABS"		},	\
+		{ HRTIMER_MODE_REL,		"REL"		},	\
+		{ HRTIMER_MODE_ABS_PINNED,	"ABS|PINNED"	},	\
+		{ HRTIMER_MODE_REL_PINNED,	"REL|PINNED"	},	\
+		{ HRTIMER_MODE_ABS_SOFT,	"ABS|SOFT"	},	\
+		{ HRTIMER_MODE_REL_SOFT,	"REL|SOFT"	},	\
+		{ HRTIMER_MODE_ABS_PINNED_SOFT,	"ABS|PINNED|SOFT" },	\
+		{ HRTIMER_MODE_REL_PINNED_SOFT,	"REL|PINNED|SOFT" })
+
 /**
  * hrtimer_init - called when the hrtimer is initialized
  * @hrtimer:	pointer to struct hrtimer
@@ -162,10 +180,8 @@ TRACE_EVENT(hrtimer_init,
 	),
 
 	TP_printk("hrtimer=%p clockid=%s mode=%s", __entry->hrtimer,
-		  __entry->clockid == CLOCK_REALTIME ?
-			"CLOCK_REALTIME" : "CLOCK_MONOTONIC",
-		  __entry->mode == HRTIMER_MODE_ABS ?
-			"HRTIMER_MODE_ABS" : "HRTIMER_MODE_REL")
+		  decode_clockid(__entry->clockid),
+		  decode_hrtimer_mode(__entry->mode))
 );
 
 /**
@@ -174,15 +190,16 @@ TRACE_EVENT(hrtimer_init,
  */
 TRACE_EVENT(hrtimer_start,
 
-	TP_PROTO(struct hrtimer *hrtimer),
+	TP_PROTO(struct hrtimer *hrtimer, enum hrtimer_mode mode),
 
-	TP_ARGS(hrtimer),
+	TP_ARGS(hrtimer, mode),
 
 	TP_STRUCT__entry(
 		__field( void *,	hrtimer		)
 		__field( void *,	function	)
 		__field( s64,		expires		)
 		__field( s64,		softexpires	)
+		__field( enum hrtimer_mode,	mode	)
 	),
 
 	TP_fast_assign(
@@ -190,12 +207,14 @@ TRACE_EVENT(hrtimer_start,
 		__entry->function	= hrtimer->function;
 		__entry->expires	= hrtimer_get_expires(hrtimer);
 		__entry->softexpires	= hrtimer_get_softexpires(hrtimer);
+		__entry->mode		= mode;
 	),
 
-	TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu",
-		  __entry->hrtimer, __entry->function,
+	TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu "
+		  "mode=%s", __entry->hrtimer, __entry->function,
 		  (unsigned long long) __entry->expires,
-		  (unsigned long long) __entry->softexpires)
+		  (unsigned long long) __entry->softexpires,
+		  decode_hrtimer_mode(__entry->mode))
 );
 
 /**