Merge branch 'mpi-master' into wip-k-fmlpwip-k-fmlp

Conflicts:
	litmus/sched_cedf.c

1 files changed, 75 insertions, 19 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 65d420499a61..f032e6e1e09a 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -14,17 +14,11 @@
 
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
-void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
-}
-EXPORT_SYMBOL(default_unplug_io_fn);
-
 struct backing_dev_info default_backing_dev_info = {
         .name           = "default",
         .ra_pages       = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
         .state          = 0,
         .capabilities   = BDI_CAP_MAP_COPY,
-        .unplug_io_fn   = default_unplug_io_fn,
 };
 EXPORT_SYMBOL_GPL(default_backing_dev_info);
 
@@ -69,18 +63,18 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
         unsigned long background_thresh;
         unsigned long dirty_thresh;
         unsigned long bdi_thresh;
-        unsigned long nr_dirty, nr_io, nr_more_io, nr_wb;
+        unsigned long nr_dirty, nr_io, nr_more_io;
         struct inode *inode;
 
-        nr_wb = nr_dirty = nr_io = nr_more_io = 0;
-        spin_lock(&inode_lock);
-        list_for_each_entry(inode, &wb->b_dirty, i_list)
+        nr_dirty = nr_io = nr_more_io = 0;
+        spin_lock(&inode_wb_list_lock);
+        list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
                 nr_dirty++;
-        list_for_each_entry(inode, &wb->b_io, i_list)
+        list_for_each_entry(inode, &wb->b_io, i_wb_list)
                 nr_io++;
-        list_for_each_entry(inode, &wb->b_more_io, i_list)
+        list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
                 nr_more_io++;
-        spin_unlock(&inode_lock);
+        spin_unlock(&inode_wb_list_lock);
 
         global_dirty_limits(&background_thresh, &dirty_thresh);
         bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
@@ -362,7 +356,7 @@ static int bdi_forker_thread(void *ptr)
 {
         struct bdi_writeback *me = ptr;
 
-        current->flags |= PF_FLUSHER | PF_SWAPWRITE;
+        current->flags |= PF_SWAPWRITE;
         set_freezable();
 
         /*
@@ -604,7 +598,7 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
         spin_lock(&sb_lock);
         list_for_each_entry(sb, &super_blocks, s_list) {
                 if (sb->s_bdi == bdi)
-                        sb->s_bdi = NULL;
+                        sb->s_bdi = &default_backing_dev_info;
         }
         spin_unlock(&sb_lock);
 }
@@ -682,11 +676,11 @@ void bdi_destroy(struct backing_dev_info *bdi)
         if (bdi_has_dirty_io(bdi)) {
                 struct bdi_writeback *dst = &default_backing_dev_info.wb;
 
-                spin_lock(&inode_lock);
+                spin_lock(&inode_wb_list_lock);
                 list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
                 list_splice(&bdi->wb.b_io, &dst->b_io);
                 list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
-                spin_unlock(&inode_lock);
+                spin_unlock(&inode_wb_list_lock);
         }
 
         bdi_unregister(bdi);
@@ -729,6 +723,7 @@ static wait_queue_head_t congestion_wqh[2] = {
                 __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
                 __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
         };
+static atomic_t nr_bdi_congested[2];
 
 void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
@@ -736,7 +731,8 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
         wait_queue_head_t *wqh = &congestion_wqh[sync];
 
         bit = sync ? BDI_sync_congested : BDI_async_congested;
-        clear_bit(bit, &bdi->state);
+        if (test_and_clear_bit(bit, &bdi->state))
+                atomic_dec(&nr_bdi_congested[sync]);
         smp_mb__after_clear_bit();
         if (waitqueue_active(wqh))
                 wake_up(wqh);
@@ -748,7 +744,8 @@ void set_bdi_congested(struct backing_dev_info *bdi, int sync)
         enum bdi_state bit;
 
         bit = sync ? BDI_sync_congested : BDI_async_congested;
-        set_bit(bit, &bdi->state);
+        if (!test_and_set_bit(bit, &bdi->state))
+                atomic_inc(&nr_bdi_congested[sync]);
 }
 EXPORT_SYMBOL(set_bdi_congested);
 
@@ -764,13 +761,72 @@ EXPORT_SYMBOL(set_bdi_congested);
 long congestion_wait(int sync, long timeout)
 {
         long ret;
+        unsigned long start = jiffies;
         DEFINE_WAIT(wait);
         wait_queue_head_t *wqh = &congestion_wqh[sync];
 
         prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
         ret = io_schedule_timeout(timeout);
         finish_wait(wqh, &wait);
+
+        trace_writeback_congestion_wait(jiffies_to_usecs(timeout),
+                                        jiffies_to_usecs(jiffies - start));
+
         return ret;
 }
 EXPORT_SYMBOL(congestion_wait);
 
+/**
+ * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a zone to complete writes
+ * @zone: A zone to check if it is heavily congested
+ * @sync: SYNC or ASYNC IO
+ * @timeout: timeout in jiffies
+ *
+ * In the event of a congested backing_dev (any backing_dev) and the given
+ * @zone has experienced recent congestion, this waits for up to @timeout
+ * jiffies for either a BDI to exit congestion of the given @sync queue
+ * or a write to complete.
+ *
+ * In the absence of zone congestion, cond_resched() is called to yield
+ * the processor if necessary but otherwise does not sleep.
+ *
+ * The return value is 0 if the sleep is for the full timeout. Otherwise,
+ * it is the number of jiffies that were still remaining when the function
+ * returned. return_value == timeout implies the function did not sleep.
+ */
+long wait_iff_congested(struct zone *zone, int sync, long timeout)
+{
+        long ret;
+        unsigned long start = jiffies;
+        DEFINE_WAIT(wait);
+        wait_queue_head_t *wqh = &congestion_wqh[sync];
+
+        /*
+         * If there is no congestion, or heavy congestion is not being
+         * encountered in the current zone, yield if necessary instead
+         * of sleeping on the congestion queue
+         */
+        if (atomic_read(&nr_bdi_congested[sync]) == 0 ||
+                        !zone_is_reclaim_congested(zone)) {
+                cond_resched();
+
+                /* In case we scheduled, work out time remaining */
+                ret = timeout - (jiffies - start);
+                if (ret < 0)
+                        ret = 0;
+
+                goto out;
+        }
+
+        /* Sleep until uncongested or a write happens */
+        prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
+        ret = io_schedule_timeout(timeout);
+        finish_wait(wqh, &wait);
+
+out:
+        trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout),
+                                        jiffies_to_usecs(jiffies - start));
+
+        return ret;
+}
+EXPORT_SYMBOL(wait_iff_congested);