sched/fair: Rework sched_fair time accounting

Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This
results in him occasionally seeing time going backwards - which
crashes the scheduler ...

Most of our time accounting can actually handle that except the most
common one; the tick time update of sched_fair.

There is a further problem with that code; previously we assumed that
because we get a tick every TICK_NSEC our time delta could never
exceed 32bits and math was simpler.

However, ever since Frederic managed to get NO_HZ_FULL merged; this is
no longer the case since now a task can run for a long time indeed
without getting a tick. It only takes about ~4.2 seconds to overflow
our u32 in nanoseconds.

This means we not only need to better deal with time going backwards;
but also means we need to be able to deal with large deltas.

This patch reworks the entire code and uses mul_u64_u32_shr() as
proposed by Andy a long while ago.

We express our virtual time scale factor in a u32 multiplier and shift
right and the 32bit mul_u64_u32_shr() implementation reduces to a
single 32x32->64 multiply if the time delta is still short (common
case).

For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128.

Reported-and-Tested-by: Christian Engelmayer <cengelma@gmx.at>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: fweisbec@gmail.com
Cc: Paul Turner <pjt@google.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 64 insertions, 80 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fd773ade1a31..9030da7bcb15 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -178,59 +178,61 @@ void sched_init_granularity(void)
         update_sysctl();
 }
 
-#if BITS_PER_LONG == 32
-# define WMULT_CONST    (~0UL)
-#else
-# define WMULT_CONST    (1UL << 32)
-#endif
-
+#define WMULT_CONST     (~0U)
 #define WMULT_SHIFT     32
 
-/*
- * Shift right and round:
- */
-#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
+static void __update_inv_weight(struct load_weight *lw)
+{
+        unsigned long w;
+
+        if (likely(lw->inv_weight))
+                return;
+
+        w = scale_load_down(lw->weight);
+
+        if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST))
+                lw->inv_weight = 1;
+        else if (unlikely(!w))
+                lw->inv_weight = WMULT_CONST;
+        else
+                lw->inv_weight = WMULT_CONST / w;
+}
 
 /*
- * delta *= weight / lw
+ * delta_exec * weight / lw.weight
+ *   OR
+ * (delta_exec * (weight * lw->inv_weight)) >> WMULT_SHIFT
+ *
+ * Either weight := NICE_0_LOAD and lw \e prio_to_wmult[], in which case
+ * we're guaranteed shift stays positive because inv_weight is guaranteed to
+ * fit 32 bits, and NICE_0_LOAD gives another 10 bits; therefore shift >= 22.
+ *
+ * Or, weight =< lw.weight (because lw.weight is the runqueue weight), thus
+ * weight/lw.weight <= 1, and therefore our shift will also be positive.
  */
-static unsigned long
-calc_delta_mine(unsigned long delta_exec, unsigned long weight,
-                struct load_weight *lw)
+static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw)
 {
-        u64 tmp;
+        u64 fact = scale_load_down(weight);
+        int shift = WMULT_SHIFT;
 
-        /*
-         * weight can be less than 2^SCHED_LOAD_RESOLUTION for task group sched
-         * entities since MIN_SHARES = 2. Treat weight as 1 if less than
-         * 2^SCHED_LOAD_RESOLUTION.
-         */
-        if (likely(weight > (1UL << SCHED_LOAD_RESOLUTION)))
-                tmp = (u64)delta_exec * scale_load_down(weight);
-        else
-                tmp = (u64)delta_exec;
+        __update_inv_weight(lw);
 
-        if (!lw->inv_weight) {
-                unsigned long w = scale_load_down(lw->weight);
-
-                if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST))
-                        lw->inv_weight = 1;
-                else if (unlikely(!w))
-                        lw->inv_weight = WMULT_CONST;
-                else
-                        lw->inv_weight = WMULT_CONST / w;
+        if (unlikely(fact >> 32)) {
+                while (fact >> 32) {
+                        fact >>= 1;
+                        shift--;
+                }
         }
 
-        /*
-         * Check whether we'd overflow the 64-bit multiplication:
-         */
-        if (unlikely(tmp > WMULT_CONST))
-                tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
-                        WMULT_SHIFT/2);
-        else
-                tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT);
+        /* hint to use a 32x32->64 mul */
+        fact = (u64)(u32)fact * lw->inv_weight;
+
+        while (fact >> 32) {
+                fact >>= 1;
+                shift--;
+        }
 
-        return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
+        return mul_u64_u32_shr(delta_exec, fact, shift);
 }
 
 
@@ -443,7 +445,7 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
 #endif  /* CONFIG_FAIR_GROUP_SCHED */
 
 static __always_inline
-void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec);
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec);
 
 /**************************************************************
  * Scheduling class tree data structure manipulation methods:
@@ -612,11 +614,10 @@ int sched_proc_update_handler(struct ctl_table *table, int write,
 /*
  * delta /= w
  */
-static inline unsigned long
-calc_delta_fair(unsigned long delta, struct sched_entity *se)
+static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se)
 {
         if (unlikely(se->load.weight != NICE_0_LOAD))
-                delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load);
+                delta = __calc_delta(delta, NICE_0_LOAD, &se->load);
 
         return delta;
 }
@@ -665,7 +666,7 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
                         update_load_add(&lw, se->load.weight);
                         load = &lw;
                 }
-                slice = calc_delta_mine(slice, se->load.weight, load);
+                slice = __calc_delta(slice, se->load.weight, load);
         }
         return slice;
 }
@@ -703,47 +704,32 @@ void init_task_runnable_average(struct task_struct *p)
 #endif
 
 /*
- * Update the current task's runtime statistics. Skip current tasks that
- * are not in our scheduling class.
+ * Update the current task's runtime statistics.
  */
-static inline void
-__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
-              unsigned long delta_exec)
-{
-        unsigned long delta_exec_weighted;
-
-        schedstat_set(curr->statistics.exec_max,
-                      max((u64)delta_exec, curr->statistics.exec_max));
-
-        curr->sum_exec_runtime += delta_exec;
-        schedstat_add(cfs_rq, exec_clock, delta_exec);
-        delta_exec_weighted = calc_delta_fair(delta_exec, curr);
-
-        curr->vruntime += delta_exec_weighted;
-        update_min_vruntime(cfs_rq);
-}
-
 static void update_curr(struct cfs_rq *cfs_rq)
 {
         struct sched_entity *curr = cfs_rq->curr;
         u64 now = rq_clock_task(rq_of(cfs_rq));
-        unsigned long delta_exec;
+        u64 delta_exec;
 
         if (unlikely(!curr))
                 return;
 
-        /*
-         * Get the amount of time the current task was running
-         * since the last time we changed load (this cannot
-         * overflow on 32 bits):
-         */
-        delta_exec = (unsigned long)(now - curr->exec_start);
-        if (!delta_exec)
+        delta_exec = now - curr->exec_start;
+        if (unlikely((s64)delta_exec <= 0))
                 return;
 
-        __update_curr(cfs_rq, curr, delta_exec);
         curr->exec_start = now;
 
+        schedstat_set(curr->statistics.exec_max,
+                      max(delta_exec, curr->statistics.exec_max));
+
+        curr->sum_exec_runtime += delta_exec;
+        schedstat_add(cfs_rq, exec_clock, delta_exec);
+
+        curr->vruntime += calc_delta_fair(delta_exec, curr);
+        update_min_vruntime(cfs_rq);
+
         if (entity_is_task(curr)) {
                 struct task_struct *curtask = task_of(curr);
 
@@ -3015,8 +3001,7 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
         }
 }
 
-static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
-                                     unsigned long delta_exec)
+static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
 {
         /* dock delta_exec before expiring quota (as it could span periods) */
         cfs_rq->runtime_remaining -= delta_exec;
@@ -3034,7 +3019,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
 }
 
 static __always_inline
-void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec)
+void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
 {
         if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled)
                 return;
@@ -3574,8 +3559,7 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
         return rq_clock_task(rq_of(cfs_rq));
 }
 
-static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
-                                     unsigned long delta_exec) {}
+static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {}
 static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}