1 files changed, 38 insertions, 28 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 561e63a14966..6cbfceabd95d 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -40,6 +40,7 @@
 #include <linux/cpu.h>
 #include <linux/bitops.h>
 #include <linux/mpage.h>
+#include <linux/bit_spinlock.h>
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
 static void invalidate_bh_lrus(void);
@@ -513,8 +514,8 @@ static void free_more_memory(void)
  */
 static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 {
-        static DEFINE_SPINLOCK(page_uptodate_lock);
         unsigned long flags;
+        struct buffer_head *first;
         struct buffer_head *tmp;
         struct page *page;
         int page_uptodate = 1;
@@ -536,7 +537,9 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
          * two buffer heads end IO at almost the same time and both
          * decide that the page is now completely done.
          */
-        spin_lock_irqsave(&page_uptodate_lock, flags);
+        first = page_buffers(page);
+        local_irq_save(flags);
+        bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
         clear_buffer_async_read(bh);
         unlock_buffer(bh);
         tmp = bh;
@@ -549,7 +552,8 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
                 }
                 tmp = tmp->b_this_page;
         } while (tmp != bh);
-        spin_unlock_irqrestore(&page_uptodate_lock, flags);
+        bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+        local_irq_restore(flags);
 
         /*
          * If none of the buffers had errors and they are all
@@ -561,7 +565,8 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
         return;
 
 still_busy:
-        spin_unlock_irqrestore(&page_uptodate_lock, flags);
+        bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+        local_irq_restore(flags);
         return;
 }
 
@@ -572,8 +577,8 @@ still_busy:
 void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 {
         char b[BDEVNAME_SIZE];
-        static DEFINE_SPINLOCK(page_uptodate_lock);
         unsigned long flags;
+        struct buffer_head *first;
         struct buffer_head *tmp;
         struct page *page;
 
@@ -594,7 +599,10 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
                 SetPageError(page);
         }
 
-        spin_lock_irqsave(&page_uptodate_lock, flags);
+        first = page_buffers(page);
+        local_irq_save(flags);
+        bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+
         clear_buffer_async_write(bh);
         unlock_buffer(bh);
         tmp = bh->b_this_page;
@@ -605,12 +613,14 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
                 }
                 tmp = tmp->b_this_page;
         }
-        spin_unlock_irqrestore(&page_uptodate_lock, flags);
+        bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+        local_irq_restore(flags);
         end_page_writeback(page);
         return;
 
 still_busy:
-        spin_unlock_irqrestore(&page_uptodate_lock, flags);
+        bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+        local_irq_restore(flags);
         return;
 }
 
@@ -908,8 +918,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
                                  * contents - it is a noop if I/O is still in
                                  * flight on potentially older contents.
                                  */
-                                wait_on_buffer(bh);
-                                ll_rw_block(WRITE, 1, &bh);
+                                ll_rw_block(SWRITE, 1, &bh);
                                 brelse(bh);
                                 spin_lock(lock);
                         }
@@ -2784,21 +2793,22 @@ int submit_bh(int rw, struct buffer_head * bh)
 
 /**
  * ll_rw_block: low-level access to block devices (DEPRECATED)
- * @rw: whether to %READ or %WRITE or maybe %READA (readahead)
+ * @rw: whether to %READ or %WRITE or %SWRITE or maybe %READA (readahead)
  * @nr: number of &struct buffer_heads in the array
  * @bhs: array of pointers to &struct buffer_head
  *
- * ll_rw_block() takes an array of pointers to &struct buffer_heads,
- * and requests an I/O operation on them, either a %READ or a %WRITE.
- * The third %READA option is described in the documentation for
- * generic_make_request() which ll_rw_block() calls.
+ * ll_rw_block() takes an array of pointers to &struct buffer_heads, and
+ * requests an I/O operation on them, either a %READ or a %WRITE.  The third
+ * %SWRITE is like %WRITE only we make sure that the *current* data in buffers
+ * are sent to disk. The fourth %READA option is described in the documentation
+ * for generic_make_request() which ll_rw_block() calls.
  *
  * This function drops any buffer that it cannot get a lock on (with the
- * BH_Lock state bit), any buffer that appears to be clean when doing a
- * write request, and any buffer that appears to be up-to-date when doing
- * read request.  Further it marks as clean buffers that are processed for
- * writing (the buffer cache won't assume that they are actually clean until
- * the buffer gets unlocked).
+ * BH_Lock state bit) unless SWRITE is required, any buffer that appears to be
+ * clean when doing a write request, and any buffer that appears to be
+ * up-to-date when doing read request.  Further it marks as clean buffers that
+ * are processed for writing (the buffer cache won't assume that they are
+ * actually clean until the buffer gets unlocked).
  *
  * ll_rw_block sets b_end_io to simple completion handler that marks
  * the buffer up-to-date (if approriate), unlocks the buffer and wakes
@@ -2814,11 +2824,13 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[])
         for (i = 0; i < nr; i++) {
                 struct buffer_head *bh = bhs[i];
 
-                if (test_set_buffer_locked(bh))
+                if (rw == SWRITE)
+                        lock_buffer(bh);
+                else if (test_set_buffer_locked(bh))
                         continue;
 
                 get_bh(bh);
-                if (rw == WRITE) {
+                if (rw == WRITE || rw == SWRITE) {
                         if (test_clear_buffer_dirty(bh)) {
                                 bh->b_end_io = end_buffer_write_sync;
                                 submit_bh(WRITE, bh);
@@ -3037,10 +3049,9 @@ struct buffer_head *alloc_buffer_head(unsigned int __nocast gfp_flags)
 {
         struct buffer_head *ret = kmem_cache_alloc(bh_cachep, gfp_flags);
         if (ret) {
-                preempt_disable();
-                __get_cpu_var(bh_accounting).nr++;
+                get_cpu_var(bh_accounting).nr++;
                 recalc_bh_state();
-                preempt_enable();
+                put_cpu_var(bh_accounting);
         }
         return ret;
 }
@@ -3050,10 +3061,9 @@ void free_buffer_head(struct buffer_head *bh)
 {
         BUG_ON(!list_empty(&bh->b_assoc_buffers));
         kmem_cache_free(bh_cachep, bh);
-        preempt_disable();
-        __get_cpu_var(bh_accounting).nr--;
+        get_cpu_var(bh_accounting).nr--;
         recalc_bh_state();
-        preempt_enable();
+        put_cpu_var(bh_accounting);
 }
 EXPORT_SYMBOL(free_buffer_head);