1 files changed, 147 insertions, 13 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 555752907dc3..c0d4ce144dec 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -30,6 +30,8 @@
 #include <linux/sysctl.h>
 #include <linux/cpu.h>
 #include <linux/syscalls.h>
+#include <linux/buffer_head.h>
+#include <linux/pagevec.h>
 
 /*
  * The maximum number of pages to writeout in a single bdflush/kupdate
@@ -46,7 +48,6 @@
  */
 static long ratelimit_pages = 32;
 
-static long total_pages;        /* The total number of pages in the machine. */
 static int dirty_exceeded __cacheline_aligned_in_smp;   /* Dirty mem may be over limit */
 
 /*
@@ -126,7 +127,7 @@ get_dirty_limits(long *pbackground, long *pdirty,
         int unmapped_ratio;
         long background;
         long dirty;
-        unsigned long available_memory = total_pages;
+        unsigned long available_memory = vm_total_pages;
         struct task_struct *tsk;
 
 #ifdef CONFIG_HIGHMEM
@@ -141,7 +142,7 @@ get_dirty_limits(long *pbackground, long *pdirty,
 
         unmapped_ratio = 100 - ((global_page_state(NR_FILE_MAPPED) +
                                 global_page_state(NR_ANON_PAGES)) * 100) /
-                                        total_pages;
+                                        vm_total_pages;
 
         dirty_ratio = vm_dirty_ratio;
         if (dirty_ratio > unmapped_ratio / 2)
@@ -502,9 +503,9 @@ void laptop_sync_completion(void)
  * will write six megabyte chunks, max.
  */
 
-static void set_ratelimit(void)
+void writeback_set_ratelimit(void)
 {
-        ratelimit_pages = total_pages / (num_online_cpus() * 32);
+        ratelimit_pages = vm_total_pages / (num_online_cpus() * 32);
         if (ratelimit_pages < 16)
                 ratelimit_pages = 16;
         if (ratelimit_pages * PAGE_CACHE_SIZE > 4096 * 1024)
@@ -514,7 +515,7 @@ static void set_ratelimit(void)
 static int __cpuinit
 ratelimit_handler(struct notifier_block *self, unsigned long u, void *v)
 {
-        set_ratelimit();
+        writeback_set_ratelimit();
         return 0;
 }
 
@@ -533,9 +534,7 @@ void __init page_writeback_init(void)
         long buffer_pages = nr_free_buffer_pages();
         long correction;
 
-        total_pages = nr_free_pagecache_pages();
-
-        correction = (100 * 4 * buffer_pages) / total_pages;
+        correction = (100 * 4 * buffer_pages) / vm_total_pages;
 
         if (correction < 100) {
                 dirty_background_ratio *= correction;
@@ -549,10 +548,143 @@ void __init page_writeback_init(void)
                         vm_dirty_ratio = 1;
         }
         mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
-        set_ratelimit();
+        writeback_set_ratelimit();
         register_cpu_notifier(&ratelimit_nb);
 }
 
+/**
+ * generic_writepages - walk the list of dirty pages of the given
+ *                      address space and writepage() all of them.
+ *
+ * @mapping: address space structure to write
+ * @wbc: subtract the number of written pages from *@wbc->nr_to_write
+ *
+ * This is a library function, which implements the writepages()
+ * address_space_operation.
+ *
+ * If a page is already under I/O, generic_writepages() skips it, even
+ * if it's dirty.  This is desirable behaviour for memory-cleaning writeback,
+ * but it is INCORRECT for data-integrity system calls such as fsync().  fsync()
+ * and msync() need to guarantee that all the data which was dirty at the time
+ * the call was made get new I/O started against them.  If wbc->sync_mode is
+ * WB_SYNC_ALL then we were called for data integrity and we must wait for
+ * existing IO to complete.
+ *
+ * Derived from mpage_writepages() - if you fix this you should check that
+ * also!
+ */
+int generic_writepages(struct address_space *mapping,
+                       struct writeback_control *wbc)
+{
+        struct backing_dev_info *bdi = mapping->backing_dev_info;
+        int ret = 0;
+        int done = 0;
+        int (*writepage)(struct page *page, struct writeback_control *wbc);
+        struct pagevec pvec;
+        int nr_pages;
+        pgoff_t index;
+        pgoff_t end;            /* Inclusive */
+        int scanned = 0;
+        int range_whole = 0;
+
+        if (wbc->nonblocking && bdi_write_congested(bdi)) {
+                wbc->encountered_congestion = 1;
+                return 0;
+        }
+
+        writepage = mapping->a_ops->writepage;
+
+        /* deal with chardevs and other special file */
+        if (!writepage)
+                return 0;
+
+        pagevec_init(&pvec, 0);
+        if (wbc->range_cyclic) {
+                index = mapping->writeback_index; /* Start from prev offset */
+                end = -1;
+        } else {
+                index = wbc->range_start >> PAGE_CACHE_SHIFT;
+                end = wbc->range_end >> PAGE_CACHE_SHIFT;
+                if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+                        range_whole = 1;
+                scanned = 1;
+        }
+retry:
+        while (!done && (index <= end) &&
+               (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+                                              PAGECACHE_TAG_DIRTY,
+                                              min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
+                unsigned i;
+
+                scanned = 1;
+                for (i = 0; i < nr_pages; i++) {
+                        struct page *page = pvec.pages[i];
+
+                        /*
+                         * At this point we hold neither mapping->tree_lock nor
+                         * lock on the page itself: the page may be truncated or
+                         * invalidated (changing page->mapping to NULL), or even
+                         * swizzled back from swapper_space to tmpfs file
+                         * mapping
+                         */
+                        lock_page(page);
+
+                        if (unlikely(page->mapping != mapping)) {
+                                unlock_page(page);
+                                continue;
+                        }
+
+                        if (!wbc->range_cyclic && page->index > end) {
+                                done = 1;
+                                unlock_page(page);
+                                continue;
+                        }
+
+                        if (wbc->sync_mode != WB_SYNC_NONE)
+                                wait_on_page_writeback(page);
+
+                        if (PageWriteback(page) ||
+                            !clear_page_dirty_for_io(page)) {
+                                unlock_page(page);
+                                continue;
+                        }
+
+                        ret = (*writepage)(page, wbc);
+                        if (ret) {
+                                if (ret == -ENOSPC)
+                                        set_bit(AS_ENOSPC, &mapping->flags);
+                                else
+                                        set_bit(AS_EIO, &mapping->flags);
+                        }
+
+                        if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE))
+                                unlock_page(page);
+                        if (ret || (--(wbc->nr_to_write) <= 0))
+                                done = 1;
+                        if (wbc->nonblocking && bdi_write_congested(bdi)) {
+                                wbc->encountered_congestion = 1;
+                                done = 1;
+                        }
+                }
+                pagevec_release(&pvec);
+                cond_resched();
+        }
+        if (!scanned && !done) {
+                /*
+                 * We hit the last page and there is more work to be done: wrap
+                 * back to the start of the file
+                 */
+                scanned = 1;
+                index = 0;
+                goto retry;
+        }
+        if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+                mapping->writeback_index = index;
+        return ret;
+}
+
+EXPORT_SYMBOL(generic_writepages);
+
 int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
         int ret;
@@ -675,9 +807,11 @@ int fastcall set_page_dirty(struct page *page)
 
         if (likely(mapping)) {
                 int (*spd)(struct page *) = mapping->a_ops->set_page_dirty;
-                if (spd)
-                        return (*spd)(page);
-                return __set_page_dirty_buffers(page);
+#ifdef CONFIG_BLOCK
+                if (!spd)
+                        spd = __set_page_dirty_buffers;
+#endif
+                return (*spd)(page);
         }
         if (!PageDirty(page)) {
                 if (!TestSetPageDirty(page))