Merge branch 'for-linus' of git://git.kernel.dk/linux-2.6-block

* 'for-linus' of git://git.kernel.dk/linux-2.6-block:
  Block: use round_jiffies_up()
  Add round_jiffies_up and related routines
  block: fix __blkdev_get() for removable devices
  generic-ipi: fix the smp_mb() placement
  blk: move blk_delete_timer call in end_that_request_last
  block: add timer on blkdev_dequeue_request() not elv_next_request()
  bio: define __BIOVEC_PHYS_MERGEABLE
  block: remove unused ll_new_mergeable()

2 files changed, 111 insertions, 36 deletions

diff --git a/kernel/smp.c b/kernel/smp.c
index f362a8553777..75c8dde58c55 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -51,10 +51,6 @@ static void csd_flag_wait(struct call_single_data *data)
 {
         /* Wait for response */
         do {
-                /*
-                 * We need to see the flags store in the IPI handler
-                 */
-                smp_mb();
                 if (!(data->flags & CSD_FLAG_WAIT))
                         break;
                 cpu_relax();
@@ -76,6 +72,11 @@ static void generic_exec_single(int cpu, struct call_single_data *data)
         list_add_tail(&data->list, &dst->list);
         spin_unlock_irqrestore(&dst->lock, flags);
 
+        /*
+         * Make the list addition visible before sending the ipi.
+         */
+        smp_mb();
+
         if (ipi)
                 arch_send_call_function_single_ipi(cpu);
 
@@ -157,7 +158,7 @@ void generic_smp_call_function_single_interrupt(void)
          * Need to see other stores to list head for checking whether
          * list is empty without holding q->lock
          */
-        smp_mb();
+        smp_read_barrier_depends();
         while (!list_empty(&q->list)) {
                 unsigned int data_flags;
 
@@ -191,7 +192,7 @@ void generic_smp_call_function_single_interrupt(void)
                 /*
                  * See comment on outer loop
                  */
-                smp_mb();
+                smp_read_barrier_depends();
         }
 }
 
@@ -370,6 +371,11 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
         list_add_tail_rcu(&data->csd.list, &call_function_queue);
         spin_unlock_irqrestore(&call_function_lock, flags);
 
+        /*
+         * Make the list addition visible before sending the ipi.
+         */
+        smp_mb();
+
         /* Send a message to all CPUs in the map */
         arch_send_call_function_ipi(mask);
 
diff --git a/kernel/timer.c b/kernel/timer.c
index 56becf373c58..dbd50fabe4c7 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -112,27 +112,8 @@ timer_set_base(struct timer_list *timer, struct tvec_base *new_base)
                                       tbase_get_deferrable(timer->base));
 }
 
-/**
- * __round_jiffies - function to round jiffies to a full second
- * @j: the time in (absolute) jiffies that should be rounded
- * @cpu: the processor number on which the timeout will happen
- *
- * __round_jiffies() rounds an absolute time in the future (in jiffies)
- * up or down to (approximately) full seconds. This is useful for timers
- * for which the exact time they fire does not matter too much, as long as
- * they fire approximately every X seconds.
- *
- * By rounding these timers to whole seconds, all such timers will fire
- * at the same time, rather than at various times spread out. The goal
- * of this is to have the CPU wake up less, which saves power.
- *
- * The exact rounding is skewed for each processor to avoid all
- * processors firing at the exact same time, which could lead
- * to lock contention or spurious cache line bouncing.
- *
- * The return value is the rounded version of the @j parameter.
- */
-unsigned long __round_jiffies(unsigned long j, int cpu)
+static unsigned long round_jiffies_common(unsigned long j, int cpu,
+                bool force_up)
 {
         int rem;
         unsigned long original = j;
@@ -154,8 +135,9 @@ unsigned long __round_jiffies(unsigned long j, int cpu)
          * due to delays of the timer irq, long irq off times etc etc) then
          * we should round down to the whole second, not up. Use 1/4th second
          * as cutoff for this rounding as an extreme upper bound for this.
+         * But never round down if @force_up is set.
          */
-        if (rem < HZ/4) /* round down */
+        if (rem < HZ/4 && !force_up) /* round down */
                 j = j - rem;
         else /* round up */
                 j = j - rem + HZ;
@@ -167,6 +149,31 @@ unsigned long __round_jiffies(unsigned long j, int cpu)
                 return original;
         return j;
 }
+
+/**
+ * __round_jiffies - function to round jiffies to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * __round_jiffies() rounds an absolute time in the future (in jiffies)
+ * up or down to (approximately) full seconds. This is useful for timers
+ * for which the exact time they fire does not matter too much, as long as
+ * they fire approximately every X seconds.
+ *
+ * By rounding these timers to whole seconds, all such timers will fire
+ * at the same time, rather than at various times spread out. The goal
+ * of this is to have the CPU wake up less, which saves power.
+ *
+ * The exact rounding is skewed for each processor to avoid all
+ * processors firing at the exact same time, which could lead
+ * to lock contention or spurious cache line bouncing.
+ *
+ * The return value is the rounded version of the @j parameter.
+ */
+unsigned long __round_jiffies(unsigned long j, int cpu)
+{
+        return round_jiffies_common(j, cpu, false);
+}
 EXPORT_SYMBOL_GPL(__round_jiffies);
 
 /**
@@ -191,13 +198,10 @@ EXPORT_SYMBOL_GPL(__round_jiffies);
  */
 unsigned long __round_jiffies_relative(unsigned long j, int cpu)
 {
-        /*
-         * In theory the following code can skip a jiffy in case jiffies
-         * increments right between the addition and the later subtraction.
-         * However since the entire point of this function is to use approximate
-         * timeouts, it's entirely ok to not handle that.
-         */
-        return  __round_jiffies(j + jiffies, cpu) - jiffies;
+        unsigned long j0 = jiffies;
+
+        /* Use j0 because jiffies might change while we run */
+        return round_jiffies_common(j + j0, cpu, false) - j0;
 }
 EXPORT_SYMBOL_GPL(__round_jiffies_relative);
 
@@ -218,7 +222,7 @@ EXPORT_SYMBOL_GPL(__round_jiffies_relative);
  */
 unsigned long round_jiffies(unsigned long j)
 {
-        return __round_jiffies(j, raw_smp_processor_id());
+        return round_jiffies_common(j, raw_smp_processor_id(), false);
 }
 EXPORT_SYMBOL_GPL(round_jiffies);
 
@@ -243,6 +247,71 @@ unsigned long round_jiffies_relative(unsigned long j)
 }
 EXPORT_SYMBOL_GPL(round_jiffies_relative);
 
+/**
+ * __round_jiffies_up - function to round jiffies up to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * This is the same as __round_jiffies() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long __round_jiffies_up(unsigned long j, int cpu)
+{
+        return round_jiffies_common(j, cpu, true);
+}
+EXPORT_SYMBOL_GPL(__round_jiffies_up);
+
+/**
+ * __round_jiffies_up_relative - function to round jiffies up to a full second
+ * @j: the time in (relative) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * This is the same as __round_jiffies_relative() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long __round_jiffies_up_relative(unsigned long j, int cpu)
+{
+        unsigned long j0 = jiffies;
+
+        /* Use j0 because jiffies might change while we run */
+        return round_jiffies_common(j + j0, cpu, true) - j0;
+}
+EXPORT_SYMBOL_GPL(__round_jiffies_up_relative);
+
+/**
+ * round_jiffies_up - function to round jiffies up to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ *
+ * This is the same as round_jiffies() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long round_jiffies_up(unsigned long j)
+{
+        return round_jiffies_common(j, raw_smp_processor_id(), true);
+}
+EXPORT_SYMBOL_GPL(round_jiffies_up);
+
+/**
+ * round_jiffies_up_relative - function to round jiffies up to a full second
+ * @j: the time in (relative) jiffies that should be rounded
+ *
+ * This is the same as round_jiffies_relative() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long round_jiffies_up_relative(unsigned long j)
+{
+        return __round_jiffies_up_relative(j, raw_smp_processor_id());
+}
+EXPORT_SYMBOL_GPL(round_jiffies_up_relative);
+
 
 static inline void set_running_timer(struct tvec_base *base,
                                         struct timer_list *timer)