dio: don't zero out the pages array inside struct dio

[linux-beck.git] / fs / direct-io.c

diff --git a/fs/direct-io.c b/fs/direct-io.c
index 3af761c8c5cc49241e63b2f27d419844a97f3c90..9f34bb9b1ecb1ee919fddd5ad63fa768948a215b 100644 (file)
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -104,6 +104,18 @@ struct dio {
        unsigned cur_page_len;          /* Nr of bytes at cur_page_offset */
        sector_t cur_page_block;        /* Where it starts */
 
+       /* BIO completion state */
+       spinlock_t bio_lock;            /* protects BIO fields below */
+       unsigned long refcount;         /* direct_io_worker() and bios */
+       struct bio *bio_list;           /* singly linked via bi_private */
+       struct task_struct *waiter;     /* waiting task (NULL if none) */
+
+       /* AIO related stuff */
+       struct kiocb *iocb;             /* kiocb */
+       int is_async;                   /* is IO async ? */
+       int io_error;                   /* IO error in completion path */
+       ssize_t result;                 /* IO result */
+
        /*
         * Page fetching state. These variables belong to dio_refill_pages().
         */
@@ -115,22 +127,16 @@ struct dio {
         * Page queue.  These variables belong to dio_refill_pages() and
         * dio_get_page().
         */
-       struct page *pages[DIO_PAGES];  /* page buffer */
        unsigned head;                  /* next page to process */
        unsigned tail;                  /* last valid page + 1 */
        int page_errors;                /* errno from get_user_pages() */
 
-       /* BIO completion state */
-       spinlock_t bio_lock;            /* protects BIO fields below */
-       unsigned long refcount;         /* direct_io_worker() and bios */
-       struct bio *bio_list;           /* singly linked via bi_private */
-       struct task_struct *waiter;     /* waiting task (NULL if none) */
-
-       /* AIO related stuff */
-       struct kiocb *iocb;             /* kiocb */
-       int is_async;                   /* is IO async ? */
-       int io_error;                   /* IO error in completion path */
-       ssize_t result;                 /* IO result */
+       /*
+        * pages[] (and any fields placed after it) are not zeroed out at
+        * allocation time.  Don't add new fields after pages[] unless you
+        * wish that they not be zeroed.
+        */
+       struct page *pages[DIO_PAGES];  /* page buffer */
 };
 
 /*
@@ -1124,7 +1130,7 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
        int acquire_i_mutex = 0;
 
        if (rw & WRITE)
-               rw = WRITE_SYNC_PLUG;
+               rw = WRITE_ODIRECT_PLUG;
 
        if (bdev)
                bdev_blkbits = blksize_bits(bdev_logical_block_size(bdev));
@@ -1151,10 +1157,16 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
                }
        }
 
-       dio = kzalloc(sizeof(*dio), GFP_KERNEL);
+       dio = kmalloc(sizeof(*dio), GFP_KERNEL);
        retval = -ENOMEM;
        if (!dio)
                goto out;
+       /*
+        * Believe it or not, zeroing out the page array caused a .5%
+        * performance regression in a database benchmark.  So, we take
+        * care to only zero out what's needed.
+        */
+       memset(dio, 0, offsetof(struct dio, pages));
 
        /*
         * For block device access DIO_NO_LOCKING is used,