Merge branch 'next' into for-linus

Prepare first round of input updates for 3.20.

1 files changed, 58 insertions, 65 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 3588a80854b2..20805db2c987 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -128,21 +128,15 @@ __clear_page_buffers(struct page *page)
         page_cache_release(page);
 }
 
-
-static int quiet_error(struct buffer_head *bh)
-{
-        if (!test_bit(BH_Quiet, &bh->b_state) && printk_ratelimit())
-                return 0;
-        return 1;
-}
-
-
-static void buffer_io_error(struct buffer_head *bh)
+static void buffer_io_error(struct buffer_head *bh, char *msg)
 {
         char b[BDEVNAME_SIZE];
-        printk(KERN_ERR "Buffer I/O error on device %s, logical block %Lu\n",
+
+        if (!test_bit(BH_Quiet, &bh->b_state))
+                printk_ratelimited(KERN_ERR
+                        "Buffer I/O error on dev %s, logical block %llu%s\n",
                         bdevname(bh->b_bdev, b),
-                        (unsigned long long)bh->b_blocknr);
+                        (unsigned long long)bh->b_blocknr, msg);
 }
 
 /*
@@ -177,17 +171,10 @@ EXPORT_SYMBOL(end_buffer_read_sync);
 
 void end_buffer_write_sync(struct buffer_head *bh, int uptodate)
 {
-        char b[BDEVNAME_SIZE];
-
         if (uptodate) {
                 set_buffer_uptodate(bh);
         } else {
-                if (!quiet_error(bh)) {
-                        buffer_io_error(bh);
-                        printk(KERN_WARNING "lost page write due to "
-                                        "I/O error on %s\n",
-                                       bdevname(bh->b_bdev, b));
-                }
+                buffer_io_error(bh, ", lost sync page write");
                 set_buffer_write_io_error(bh);
                 clear_buffer_uptodate(bh);
         }
@@ -304,8 +291,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
                 set_buffer_uptodate(bh);
         } else {
                 clear_buffer_uptodate(bh);
-                if (!quiet_error(bh))
-                        buffer_io_error(bh);
+                buffer_io_error(bh, ", async page read");
                 SetPageError(page);
         }
 
@@ -353,7 +339,6 @@ still_busy:
  */
 void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 {
-        char b[BDEVNAME_SIZE];
         unsigned long flags;
         struct buffer_head *first;
         struct buffer_head *tmp;
@@ -365,12 +350,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
         if (uptodate) {
                 set_buffer_uptodate(bh);
         } else {
-                if (!quiet_error(bh)) {
-                        buffer_io_error(bh);
-                        printk(KERN_WARNING "lost page write due to "
-                                        "I/O error on %s\n",
-                               bdevname(bh->b_bdev, b));
-                }
+                buffer_io_error(bh, ", lost async page write");
                 set_bit(AS_EIO, &page->mapping->flags);
                 set_buffer_write_io_error(bh);
                 clear_buffer_uptodate(bh);
@@ -993,7 +973,7 @@ init_page_buffers(struct page *page, struct block_device *bdev,
  */
 static int
 grow_dev_page(struct block_device *bdev, sector_t block,
-                pgoff_t index, int size, int sizebits)
+              pgoff_t index, int size, int sizebits, gfp_t gfp)
 {
         struct inode *inode = bdev->bd_inode;
         struct page *page;
@@ -1002,8 +982,8 @@ grow_dev_page(struct block_device *bdev, sector_t block,
         int ret = 0;            /* Will call free_more_memory() */
         gfp_t gfp_mask;
 
-        gfp_mask = mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS;
-        gfp_mask |= __GFP_MOVABLE;
+        gfp_mask = (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS) | gfp;
+
         /*
          * XXX: __getblk_slow() can not really deal with failure and
          * will endlessly loop on improvised global reclaim.  Prefer
@@ -1060,7 +1040,7 @@ failed:
  * that page was dirty, the buffers are set dirty also.
  */
 static int
-grow_buffers(struct block_device *bdev, sector_t block, int size)
+grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp)
 {
         pgoff_t index;
         int sizebits;
@@ -1087,11 +1067,12 @@ grow_buffers(struct block_device *bdev, sector_t block, int size)
         }
 
         /* Create a page with the proper size buffers.. */
-        return grow_dev_page(bdev, block, index, size, sizebits);
+        return grow_dev_page(bdev, block, index, size, sizebits, gfp);
 }
 
-static struct buffer_head *
-__getblk_slow(struct block_device *bdev, sector_t block, int size)
+struct buffer_head *
+__getblk_slow(struct block_device *bdev, sector_t block,
+             unsigned size, gfp_t gfp)
 {
         /* Size must be multiple of hard sectorsize */
         if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
@@ -1113,13 +1094,14 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size)
                 if (bh)
                         return bh;
 
-                ret = grow_buffers(bdev, block, size);
+                ret = grow_buffers(bdev, block, size, gfp);
                 if (ret < 0)
                         return NULL;
                 if (ret == 0)
                         free_more_memory();
         }
 }
+EXPORT_SYMBOL(__getblk_slow);
 
 /*
  * The relationship between dirty buffers and dirty pages:
@@ -1253,7 +1235,7 @@ static struct buffer_head *__bread_slow(struct buffer_head *bh)
  * a local interrupt disable for that.
  */
 
-#define BH_LRU_SIZE     8
+#define BH_LRU_SIZE     16
 
 struct bh_lru {
         struct buffer_head *bhs[BH_LRU_SIZE];
@@ -1331,8 +1313,8 @@ lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size)
         for (i = 0; i < BH_LRU_SIZE; i++) {
                 struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]);
 
-                if (bh && bh->b_bdev == bdev &&
-                                bh->b_blocknr == block && bh->b_size == size) {
+                if (bh && bh->b_blocknr == block && bh->b_bdev == bdev &&
+                    bh->b_size == size) {
                         if (i) {
                                 while (i) {
                                         __this_cpu_write(bh_lrus.bhs[i],
@@ -1373,24 +1355,25 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size)
 EXPORT_SYMBOL(__find_get_block);
 
 /*
- * __getblk will locate (and, if necessary, create) the buffer_head
+ * __getblk_gfp() will locate (and, if necessary, create) the buffer_head
  * which corresponds to the passed block_device, block and size. The
  * returned buffer has its reference count incremented.
  *
- * __getblk() will lock up the machine if grow_dev_page's try_to_free_buffers()
- * attempt is failing.  FIXME, perhaps?
+ * __getblk_gfp() will lock up the machine if grow_dev_page's
+ * try_to_free_buffers() attempt is failing.  FIXME, perhaps?
  */
 struct buffer_head *
-__getblk(struct block_device *bdev, sector_t block, unsigned size)
+__getblk_gfp(struct block_device *bdev, sector_t block,
+             unsigned size, gfp_t gfp)
 {
         struct buffer_head *bh = __find_get_block(bdev, block, size);
 
         might_sleep();
         if (bh == NULL)
-                bh = __getblk_slow(bdev, block, size);
+                bh = __getblk_slow(bdev, block, size, gfp);
         return bh;
 }
-EXPORT_SYMBOL(__getblk);
+EXPORT_SYMBOL(__getblk_gfp);
 
 /*
  * Do async read-ahead on a buffer..
@@ -1406,24 +1389,28 @@ void __breadahead(struct block_device *bdev, sector_t block, unsigned size)
 EXPORT_SYMBOL(__breadahead);
 
 /**
- *  __bread() - reads a specified block and returns the bh
+ *  __bread_gfp() - reads a specified block and returns the bh
  *  @bdev: the block_device to read from
  *  @block: number of block
  *  @size: size (in bytes) to read
- * 
+ *  @gfp: page allocation flag
+ *
  *  Reads a specified block, and returns buffer head that contains it.
+ *  The page cache can be allocated from non-movable area
+ *  not to prevent page migration if you set gfp to zero.
  *  It returns NULL if the block was unreadable.
  */
 struct buffer_head *
-__bread(struct block_device *bdev, sector_t block, unsigned size)
+__bread_gfp(struct block_device *bdev, sector_t block,
+                   unsigned size, gfp_t gfp)
 {
-        struct buffer_head *bh = __getblk(bdev, block, size);
+        struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp);
 
         if (likely(bh) && !buffer_uptodate(bh))
                 bh = __bread_slow(bh);
         return bh;
 }
-EXPORT_SYMBOL(__bread);
+EXPORT_SYMBOL(__bread_gfp);
 
 /*
  * invalidate_bh_lrus() is called rarely - but not only at unmount.
@@ -2082,6 +2069,7 @@ int generic_write_end(struct file *file, struct address_space *mapping,
                         struct page *page, void *fsdata)
 {
         struct inode *inode = mapping->host;
+        loff_t old_size = inode->i_size;
         int i_size_changed = 0;
 
         copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
@@ -2101,6 +2089,8 @@ int generic_write_end(struct file *file, struct address_space *mapping,
         unlock_page(page);
         page_cache_release(page);
 
+        if (old_size < pos)
+                pagecache_isize_extended(inode, old_size, pos);
         /*
          * Don't mark the inode dirty under page lock. First, it unnecessarily
          * makes the holding time of page lock longer. Second, it forces lock
@@ -2318,6 +2308,11 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
                 err = 0;
 
                 balance_dirty_pages_ratelimited(mapping);
+
+                if (unlikely(fatal_signal_pending(current))) {
+                        err = -EINTR;
+                        goto out;
+                }
         }
 
         /* page covers the boundary, find the boundary offset */
@@ -2956,7 +2951,7 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
 
 /*
  * This allows us to do IO even on the odd last sectors
- * of a device, even if the bh block size is some multiple
+ * of a device, even if the block size is some multiple
  * of the physical sector size.
  *
  * We'll just truncate the bio to the size of the device,
@@ -2966,10 +2961,11 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
  * errors, this only handles the "we need to be able to
  * do IO at the final sector" case.
  */
-static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
+void guard_bio_eod(int rw, struct bio *bio)
 {
         sector_t maxsector;
-        unsigned bytes;
+        struct bio_vec *bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
+        unsigned truncated_bytes;
 
         maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
         if (!maxsector)
@@ -2984,23 +2980,20 @@ static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
                 return;
 
         maxsector -= bio->bi_iter.bi_sector;
-        bytes = bio->bi_iter.bi_size;
-        if (likely((bytes >> 9) <= maxsector))
+        if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
                 return;
 
-        /* Uhhuh. We've got a bh that straddles the device size! */
-        bytes = maxsector << 9;
+        /* Uhhuh. We've got a bio that straddles the device size! */
+        truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9);
 
         /* Truncate the bio.. */
-        bio->bi_iter.bi_size = bytes;
-        bio->bi_io_vec[0].bv_len = bytes;
+        bio->bi_iter.bi_size -= truncated_bytes;
+        bvec->bv_len -= truncated_bytes;
 
         /* ..and clear the end of the buffer for reads */
         if ((rw & RW_MASK) == READ) {
-                void *kaddr = kmap_atomic(bh->b_page);
-                memset(kaddr + bh_offset(bh) + bytes, 0, bh->b_size - bytes);
-                kunmap_atomic(kaddr);
-                flush_dcache_page(bh->b_page);
+                zero_user(bvec->bv_page, bvec->bv_offset + bvec->bv_len,
+                                truncated_bytes);
         }
 }
 
@@ -3041,7 +3034,7 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
         bio->bi_flags |= bio_flags;
 
         /* Take care of bh's that straddle the end of the device */
-        guard_bh_eod(rw, bio, bh);
+        guard_bio_eod(rw, bio);
 
         if (buffer_meta(bh))
                 rw |= REQ_META;