hugetlbfs read() support

Support for reading from hugetlbfs files.  libhugetlbfs lets application
text/data to be placed in large pages.  When we do that, oprofile doesn't
work - since libbfd tries to read from it.

This code is very similar to what do_generic_mapping_read() does, but I
can't use it since it has PAGE_CACHE_SIZE assumptions.

[akpm@linux-foundation.org: cleanups, fix leak]
[bunk@stusta.de: make hugetlbfs_read() static]
Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com>
Acked-by: William Irwin <bill.irwin@oracle.com>
Tested-by: Nishanth Aravamudan <nacc@us.ibm.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 8f8e13385e961809486e401bd17300c4f9a452dc..04598e12c489ebd20ee6bb9b81217dc2f954d74b 100644 (file)
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -179,6 +179,130 @@ full_search:
 }
 #endif
 
+static int
+hugetlbfs_read_actor(struct page *page, unsigned long offset,
+                       char __user *buf, unsigned long count,
+                       unsigned long size)
+{
+       char *kaddr;
+       unsigned long left, copied = 0;
+       int i, chunksize;
+
+       if (size > count)
+               size = count;
+
+       /* Find which 4k chunk and offset with in that chunk */
+       i = offset >> PAGE_CACHE_SHIFT;
+       offset = offset & ~PAGE_CACHE_MASK;
+
+       while (size) {
+               chunksize = PAGE_CACHE_SIZE;
+               if (offset)
+                       chunksize -= offset;
+               if (chunksize > size)
+                       chunksize = size;
+               kaddr = kmap(&page[i]);
+               left = __copy_to_user(buf, kaddr + offset, chunksize);
+               kunmap(&page[i]);
+               if (left) {
+                       copied += (chunksize - left);
+                       break;
+               }
+               offset = 0;
+               size -= chunksize;
+               buf += chunksize;
+               copied += chunksize;
+               i++;
+       }
+       return copied ? copied : -EFAULT;
+}
+
+/*
+ * Support for read() - Find the page attached to f_mapping and copy out the
+ * data. Its *very* similar to do_generic_mapping_read(), we can't use that
+ * since it has PAGE_CACHE_SIZE assumptions.
+ */
+static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
+                             size_t len, loff_t *ppos)
+{
+       struct address_space *mapping = filp->f_mapping;
+       struct inode *inode = mapping->host;
+       unsigned long index = *ppos >> HPAGE_SHIFT;
+       unsigned long offset = *ppos & ~HPAGE_MASK;
+       unsigned long end_index;
+       loff_t isize;
+       ssize_t retval = 0;
+
+       mutex_lock(&inode->i_mutex);
+
+       /* validate length */
+       if (len == 0)
+               goto out;
+
+       isize = i_size_read(inode);
+       if (!isize)
+               goto out;
+
+       end_index = (isize - 1) >> HPAGE_SHIFT;
+       for (;;) {
+               struct page *page;
+               int nr, ret;
+
+               /* nr is the maximum number of bytes to copy from this page */
+               nr = HPAGE_SIZE;
+               if (index >= end_index) {
+                       if (index > end_index)
+                               goto out;
+                       nr = ((isize - 1) & ~HPAGE_MASK) + 1;
+                       if (nr <= offset) {
+                               goto out;
+                       }
+               }
+               nr = nr - offset;
+
+               /* Find the page */
+               page = find_get_page(mapping, index);
+               if (unlikely(page == NULL)) {
+                       /*
+                        * We have a HOLE, zero out the user-buffer for the
+                        * length of the hole or request.
+                        */
+                       ret = len < nr ? len : nr;
+                       if (clear_user(buf, ret))
+                               ret = -EFAULT;
+               } else {
+                       /*
+                        * We have the page, copy it to user space buffer.
+                        */
+                       ret = hugetlbfs_read_actor(page, offset, buf, len, nr);
+               }
+               if (ret < 0) {
+                       if (retval == 0)
+                               retval = ret;
+                       if (page)
+                               page_cache_release(page);
+                       goto out;
+               }
+
+               offset += ret;
+               retval += ret;
+               len -= ret;
+               index += offset >> HPAGE_SHIFT;
+               offset &= ~HPAGE_MASK;
+
+               if (page)
+                       page_cache_release(page);
+
+               /* short read or no more work */
+               if ((ret != nr) || (len == 0))
+                       break;
+       }
+out:
+       *ppos = ((loff_t)index << HPAGE_SHIFT) + offset;
+       mutex_unlock(&inode->i_mutex);
+       return retval;
+}
+
 /*
  * Read a page. Again trivial. If it didn't already exist
  * in the page cache, it is zero-filled.
@@ -581,6 +705,7 @@ static void init_once(void *foo, struct kmem_cache *cachep, unsigned long flags)
 }
 
 const struct file_operations hugetlbfs_file_operations = {
+       .read                   = hugetlbfs_read,
        .mmap                   = hugetlbfs_file_mmap,
        .fsync                  = simple_sync_file,
        .get_unmapped_area      = hugetlb_get_unmapped_area,