1 files changed, 113 insertions, 32 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index b5f044283edb..ec0aca8ba6bf 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -911,6 +911,18 @@ link_dev_buffers(struct page *page, struct buffer_head *head)
         attach_page_buffers(page, head);
 }
 
+static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size)
+{
+        sector_t retval = ~((sector_t)0);
+        loff_t sz = i_size_read(bdev->bd_inode);
+
+        if (sz) {
+                unsigned int sizebits = blksize_bits(size);
+                retval = (sz >> sizebits);
+        }
+        return retval;
+}
+
 /*
  * Initialise the state of a blockdev page's buffers.
  */ 
@@ -921,7 +933,7 @@ init_page_buffers(struct page *page, struct block_device *bdev,
         struct buffer_head *head = page_buffers(page);
         struct buffer_head *bh = head;
         int uptodate = PageUptodate(page);
-        sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode));
+        sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode), size);
 
         do {
                 if (!buffer_mapped(bh)) {
@@ -1553,6 +1565,28 @@ void unmap_underlying_metadata(struct block_device *bdev, sector_t block)
 EXPORT_SYMBOL(unmap_underlying_metadata);
 
 /*
+ * Size is a power-of-two in the range 512..PAGE_SIZE,
+ * and the case we care about most is PAGE_SIZE.
+ *
+ * So this *could* possibly be written with those
+ * constraints in mind (relevant mostly if some
+ * architecture has a slow bit-scan instruction)
+ */
+static inline int block_size_bits(unsigned int blocksize)
+{
+        return ilog2(blocksize);
+}
+
+static struct buffer_head *create_page_buffers(struct page *page, struct inode *inode, unsigned int b_state)
+{
+        BUG_ON(!PageLocked(page));
+
+        if (!page_has_buffers(page))
+                create_empty_buffers(page, 1 << ACCESS_ONCE(inode->i_blkbits), b_state);
+        return page_buffers(page);
+}
+
+/*
  * NOTE! All mapped/uptodate combinations are valid:
  *
  *      Mapped  Uptodate        Meaning
@@ -1589,19 +1623,13 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
         sector_t block;
         sector_t last_block;
         struct buffer_head *bh, *head;
-        const unsigned blocksize = 1 << inode->i_blkbits;
+        unsigned int blocksize, bbits;
         int nr_underway = 0;
         int write_op = (wbc->sync_mode == WB_SYNC_ALL ?
                         WRITE_SYNC : WRITE);
 
-        BUG_ON(!PageLocked(page));
-
-        last_block = (i_size_read(inode) - 1) >> inode->i_blkbits;
-
-        if (!page_has_buffers(page)) {
-                create_empty_buffers(page, blocksize,
+        head = create_page_buffers(page, inode,
                                         (1 << BH_Dirty)|(1 << BH_Uptodate));
-        }
 
         /*
          * Be very careful.  We have no exclusion from __set_page_dirty_buffers
@@ -1613,9 +1641,12 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
          * handle that here by just cleaning them.
          */
 
-        block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
-        head = page_buffers(page);
         bh = head;
+        blocksize = bh->b_size;
+        bbits = block_size_bits(blocksize);
+
+        block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits);
+        last_block = (i_size_read(inode) - 1) >> bbits;
 
         /*
          * Get all the dirty buffers mapped to disk addresses and
@@ -1806,12 +1837,10 @@ int __block_write_begin(struct page *page, loff_t pos, unsigned len,
         BUG_ON(to > PAGE_CACHE_SIZE);
         BUG_ON(from > to);
 
-        blocksize = 1 << inode->i_blkbits;
-        if (!page_has_buffers(page))
-                create_empty_buffers(page, blocksize, 0);
-        head = page_buffers(page);
+        head = create_page_buffers(page, inode, 0);
+        blocksize = head->b_size;
+        bbits = block_size_bits(blocksize);
 
-        bbits = inode->i_blkbits;
         block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits);
 
         for(bh = head, block_start = 0; bh != head || !block_start;
@@ -1881,11 +1910,11 @@ static int __block_commit_write(struct inode *inode, struct page *page,
         unsigned blocksize;
         struct buffer_head *bh, *head;
 
-        blocksize = 1 << inode->i_blkbits;
+        bh = head = page_buffers(page);
+        blocksize = bh->b_size;
 
-        for(bh = head = page_buffers(page), block_start = 0;
-            bh != head || !block_start;
-            block_start=block_end, bh = bh->b_this_page) {
+        block_start = 0;
+        do {
                 block_end = block_start + blocksize;
                 if (block_end <= from || block_start >= to) {
                         if (!buffer_uptodate(bh))
@@ -1895,7 +1924,10 @@ static int __block_commit_write(struct inode *inode, struct page *page,
                         mark_buffer_dirty(bh);
                 }
                 clear_buffer_new(bh);
-        }
+
+                block_start = block_end;
+                bh = bh->b_this_page;
+        } while (bh != head);
 
         /*
          * If this is a partial write which happened to make all buffers
@@ -2020,7 +2052,6 @@ EXPORT_SYMBOL(generic_write_end);
 int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
                                         unsigned long from)
 {
-        struct inode *inode = page->mapping->host;
         unsigned block_start, block_end, blocksize;
         unsigned to;
         struct buffer_head *bh, *head;
@@ -2029,13 +2060,13 @@ int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
         if (!page_has_buffers(page))
                 return 0;
 
-        blocksize = 1 << inode->i_blkbits;
+        head = page_buffers(page);
+        blocksize = head->b_size;
         to = min_t(unsigned, PAGE_CACHE_SIZE - from, desc->count);
         to = from + to;
         if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize)
                 return 0;
 
-        head = page_buffers(page);
         bh = head;
         block_start = 0;
         do {
@@ -2068,18 +2099,16 @@ int block_read_full_page(struct page *page, get_block_t *get_block)
         struct inode *inode = page->mapping->host;
         sector_t iblock, lblock;
         struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
-        unsigned int blocksize;
+        unsigned int blocksize, bbits;
         int nr, i;
         int fully_mapped = 1;
 
-        BUG_ON(!PageLocked(page));
-        blocksize = 1 << inode->i_blkbits;
-        if (!page_has_buffers(page))
-                create_empty_buffers(page, blocksize, 0);
-        head = page_buffers(page);
+        head = create_page_buffers(page, inode, 0);
+        blocksize = head->b_size;
+        bbits = block_size_bits(blocksize);
 
-        iblock = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
-        lblock = (i_size_read(inode)+blocksize-1) >> inode->i_blkbits;
+        iblock = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits);
+        lblock = (i_size_read(inode)+blocksize-1) >> bbits;
         bh = head;
         nr = 0;
         i = 0;
@@ -2864,6 +2893,55 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
         bio_put(bio);
 }
 
+/*
+ * 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 the physical sector size.
+ *
+ * We'll just truncate the bio to the size of the device,
+ * and clear the end of the buffer head manually.
+ *
+ * Truly out-of-range accesses will turn into actual IO
+ * 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)
+{
+        sector_t maxsector;
+        unsigned bytes;
+
+        maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
+        if (!maxsector)
+                return;
+
+        /*
+         * If the *whole* IO is past the end of the device,
+         * let it through, and the IO layer will turn it into
+         * an EIO.
+         */
+        if (unlikely(bio->bi_sector >= maxsector))
+                return;
+
+        maxsector -= bio->bi_sector;
+        bytes = bio->bi_size;
+        if (likely((bytes >> 9) <= maxsector))
+                return;
+
+        /* Uhhuh. We've got a bh that straddles the device size! */
+        bytes = maxsector << 9;
+
+        /* Truncate the bio.. */
+        bio->bi_size = bytes;
+        bio->bi_io_vec[0].bv_len = 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);
+        }
+}
+
 int submit_bh(int rw, struct buffer_head * bh)
 {
         struct bio *bio;
@@ -2900,6 +2978,9 @@ int submit_bh(int rw, struct buffer_head * bh)
         bio->bi_end_io = end_bio_bh_io_sync;
         bio->bi_private = bh;
 
+        /* Take care of bh's that straddle the end of the device */
+        guard_bh_eod(rw, bio, bh);
+
         bio_get(bio);
         submit_bio(rw, bio);