mm: bdi: add separate writeback accounting capability

[linux-2.6-omap-h63xx.git] / mm / page-writeback.c

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3d3848fa6324ee30c8bfa4f39ac867808af84627..bbcb916190c992596e81c88b7a3f38a7d68f7fea 100644 (file)
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -68,6 +68,12 @@ static inline long sync_writeback_pages(void)
  */
 int dirty_background_ratio = 5;
 
+/*
+ * free highmem will not be subtracted from the total free memory
+ * for calculating free ratios if vm_highmem_is_dirtyable is true
+ */
+int vm_highmem_is_dirtyable;
+
 /*
  * The generator of dirty data starts writeback at this percentage
  */
@@ -158,7 +164,8 @@ int dirty_ratio_handler(struct ctl_table *table, int write,
  */
 static inline void __bdi_writeout_inc(struct backing_dev_info *bdi)
 {
-       __prop_inc_percpu(&vm_completions, &bdi->completions);
+       __prop_inc_percpu_max(&vm_completions, &bdi->completions,
+                             bdi->max_prop_frac);
 }
 
 static inline void task_dirty_inc(struct task_struct *tsk)
@@ -219,7 +226,7 @@ static inline void task_dirties_fraction(struct task_struct *tsk,
  *
  *   dirty -= (dirty/8) * p_{t}
  */
-void task_dirty_limit(struct task_struct *tsk, long *pdirty)
+static void task_dirty_limit(struct task_struct *tsk, long *pdirty)
 {
        long numerator, denominator;
        long dirty = *pdirty;
@@ -236,6 +243,55 @@ void task_dirty_limit(struct task_struct *tsk, long *pdirty)
        *pdirty = dirty;
 }
 
+/*
+ *
+ */
+static DEFINE_SPINLOCK(bdi_lock);
+static unsigned int bdi_min_ratio;
+
+int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
+{
+       int ret = 0;
+       unsigned long flags;
+
+       spin_lock_irqsave(&bdi_lock, flags);
+       if (min_ratio > bdi->max_ratio) {
+               ret = -EINVAL;
+       } else {
+               min_ratio -= bdi->min_ratio;
+               if (bdi_min_ratio + min_ratio < 100) {
+                       bdi_min_ratio += min_ratio;
+                       bdi->min_ratio += min_ratio;
+               } else {
+                       ret = -EINVAL;
+               }
+       }
+       spin_unlock_irqrestore(&bdi_lock, flags);
+
+       return ret;
+}
+
+int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
+{
+       unsigned long flags;
+       int ret = 0;
+
+       if (max_ratio > 100)
+               return -EINVAL;
+
+       spin_lock_irqsave(&bdi_lock, flags);
+       if (bdi->min_ratio > max_ratio) {
+               ret = -EINVAL;
+       } else {
+               bdi->max_ratio = max_ratio;
+               bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
+       }
+       spin_unlock_irqrestore(&bdi_lock, flags);
+
+       return ret;
+}
+EXPORT_SYMBOL(bdi_set_max_ratio);
+
 /*
  * Work out the current dirty-memory clamping and background writeout
  * thresholds.
@@ -287,11 +343,14 @@ static unsigned long determine_dirtyable_memory(void)
        x = global_page_state(NR_FREE_PAGES)
                + global_page_state(NR_INACTIVE)
                + global_page_state(NR_ACTIVE);
-       x -= highmem_dirtyable_memory(x);
+
+       if (!vm_highmem_is_dirtyable)
+               x -= highmem_dirtyable_memory(x);
+
        return x + 1;   /* Ensure that we never return 0 */
 }
 
-static void
+void
 get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
                 struct backing_dev_info *bdi)
 {
@@ -321,7 +380,7 @@ get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
        *pdirty = dirty;
 
        if (bdi) {
-               u64 bdi_dirty = dirty;
+               u64 bdi_dirty;
                long numerator, denominator;
 
                /*
@@ -329,8 +388,12 @@ get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
                 */
                bdi_writeout_fraction(bdi, &numerator, &denominator);
 
+               bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100;
                bdi_dirty *= numerator;
                do_div(bdi_dirty, denominator);
+               bdi_dirty += (dirty * bdi->min_ratio) / 100;
+               if (bdi_dirty > (dirty * bdi->max_ratio) / 100)
+                       bdi_dirty = dirty * bdi->max_ratio / 100;
 
                *pbdi_dirty = bdi_dirty;
                clip_bdi_dirty_limit(bdi, dirty, pbdi_dirty);
@@ -558,6 +621,7 @@ static void background_writeout(unsigned long _min_pages)
                        global_page_state(NR_UNSTABLE_NFS) < background_thresh
                                && min_pages <= 0)
                        break;
+               wbc.more_io = 0;
                wbc.encountered_congestion = 0;
                wbc.nr_to_write = MAX_WRITEBACK_PAGES;
                wbc.pages_skipped = 0;
@@ -565,8 +629,9 @@ static void background_writeout(unsigned long _min_pages)
                min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
                if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
                        /* Wrote less than expected */
-                       congestion_wait(WRITE, HZ/10);
-                       if (!wbc.encountered_congestion)
+                       if (wbc.encountered_congestion || wbc.more_io)
+                               congestion_wait(WRITE, HZ/10);
+                       else
                                break;
                }
        }
@@ -631,11 +696,12 @@ static void wb_kupdate(unsigned long arg)
                        global_page_state(NR_UNSTABLE_NFS) +
                        (inodes_stat.nr_inodes - inodes_stat.nr_unused);
        while (nr_to_write > 0) {
+               wbc.more_io = 0;
                wbc.encountered_congestion = 0;
                wbc.nr_to_write = MAX_WRITEBACK_PAGES;
                writeback_inodes(&wbc);
                if (wbc.nr_to_write > 0) {
-                       if (wbc.encountered_congestion)
+                       if (wbc.encountered_congestion || wbc.more_io)
                                congestion_wait(WRITE, HZ/10);
                        else
                                break;  /* All the old data is written */
@@ -1064,7 +1130,7 @@ static int __set_page_dirty(struct page *page)
        return 0;
 }
 
-int fastcall set_page_dirty(struct page *page)
+int set_page_dirty(struct page *page)
 {
        int ret = __set_page_dirty(page);
        if (ret)
@@ -1180,7 +1246,7 @@ int test_clear_page_writeback(struct page *page)
                        radix_tree_tag_clear(&mapping->page_tree,
                                                page_index(page),
                                                PAGECACHE_TAG_WRITEBACK);
-                       if (bdi_cap_writeback_dirty(bdi)) {
+                       if (bdi_cap_account_writeback(bdi)) {
                                __dec_bdi_stat(bdi, BDI_WRITEBACK);
                                __bdi_writeout_inc(bdi);
                        }
@@ -1209,7 +1275,7 @@ int test_set_page_writeback(struct page *page)
                        radix_tree_tag_set(&mapping->page_tree,
                                                page_index(page),
                                                PAGECACHE_TAG_WRITEBACK);
-                       if (bdi_cap_writeback_dirty(bdi))
+                       if (bdi_cap_account_writeback(bdi))
                                __inc_bdi_stat(bdi, BDI_WRITEBACK);
                }
                if (!PageDirty(page))