1 files changed, 77 insertions, 28 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 807a463fd5ed..3277f3b23524 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -9,7 +9,6 @@
  * most "normal" filesystems (but you don't /have/ to use this:
  * the NFS filesystem used to do this differently, for example)
  */
-#include <linux/config.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/compiler.h>
@@ -120,7 +119,7 @@ void __remove_from_page_cache(struct page *page)
         radix_tree_delete(&mapping->page_tree, page->index);
         page->mapping = NULL;
         mapping->nrpages--;
-        pagecache_acct(-1);
+        __dec_zone_page_state(page, NR_FILE_PAGES);
 }
 
 void remove_from_page_cache(struct page *page)
@@ -449,7 +448,7 @@ int add_to_page_cache(struct page *page, struct address_space *mapping,
                         page->mapping = mapping;
                         page->index = offset;
                         mapping->nrpages++;
-                        pagecache_acct(1);
+                        __inc_zone_page_state(page, NR_FILE_PAGES);
                 }
                 write_unlock_irq(&mapping->tree_lock);
                 radix_tree_preload_end();
@@ -489,6 +488,12 @@ struct page *page_cache_alloc_cold(struct address_space *x)
 EXPORT_SYMBOL(page_cache_alloc_cold);
 #endif
 
+static int __sleep_on_page_lock(void *word)
+{
+        io_schedule();
+        return 0;
+}
+
 /*
  * In order to wait for pages to become available there must be
  * waitqueues associated with pages. By using a hash table of
@@ -578,13 +583,24 @@ void fastcall __lock_page(struct page *page)
 }
 EXPORT_SYMBOL(__lock_page);
 
+/*
+ * Variant of lock_page that does not require the caller to hold a reference
+ * on the page's mapping.
+ */
+void fastcall __lock_page_nosync(struct page *page)
+{
+        DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
+        __wait_on_bit_lock(page_waitqueue(page), &wait, __sleep_on_page_lock,
+                                                        TASK_UNINTERRUPTIBLE);
+}
+
 /**
  * find_get_page - find and get a page reference
  * @mapping: the address_space to search
  * @offset: the page index
  *
- * A rather lightweight function, finding and getting a reference to a
- * hashed page atomically.
+ * Is there a pagecache struct page at the given (mapping, offset) tuple?
+ * If yes, increment its refcount and return it; if no, return NULL.
  */
 struct page * find_get_page(struct address_space *mapping, unsigned long offset)
 {
@@ -828,6 +844,30 @@ grab_cache_page_nowait(struct address_space *mapping, unsigned long index)
 }
 EXPORT_SYMBOL(grab_cache_page_nowait);
 
+/*
+ * CD/DVDs are error prone. When a medium error occurs, the driver may fail
+ * a _large_ part of the i/o request. Imagine the worst scenario:
+ *
+ *      ---R__________________________________________B__________
+ *         ^ reading here                             ^ bad block(assume 4k)
+ *
+ * read(R) => miss => readahead(R...B) => media error => frustrating retries
+ * => failing the whole request => read(R) => read(R+1) =>
+ * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) =>
+ * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) =>
+ * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ......
+ *
+ * It is going insane. Fix it by quickly scaling down the readahead size.
+ */
+static void shrink_readahead_size_eio(struct file *filp,
+                                        struct file_ra_state *ra)
+{
+        if (!ra->ra_pages)
+                return;
+
+        ra->ra_pages /= 4;
+}
+
 /**
  * do_generic_mapping_read - generic file read routine
  * @mapping:    address_space to be read
@@ -947,7 +987,7 @@ page_not_up_to_date:
                 /* Get exclusive access to the page ... */
                 lock_page(page);
 
-                /* Did it get unhashed before we got the lock? */
+                /* Did it get truncated before we got the lock? */
                 if (!page->mapping) {
                         unlock_page(page);
                         page_cache_release(page);
@@ -985,6 +1025,7 @@ readpage:
                                 }
                                 unlock_page(page);
                                 error = -EIO;
+                                shrink_readahead_size_eio(filp, &ra);
                                 goto readpage_error;
                         }
                         unlock_page(page);
@@ -1389,7 +1430,7 @@ retry_find:
                  */
                 if (!did_readaround) {
                         majmin = VM_FAULT_MAJOR;
-                        inc_page_state(pgmajfault);
+                        count_vm_event(PGMAJFAULT);
                 }
                 did_readaround = 1;
                 ra_pages = max_sane_readahead(file->f_ra.ra_pages);
@@ -1430,7 +1471,7 @@ outside_data_content:
          * accessible..
          */
         if (area->vm_mm == current->mm)
-                return NULL;
+                return NOPAGE_SIGBUS;
         /* Fall through to the non-read-ahead case */
 no_cached_page:
         /*
@@ -1455,12 +1496,12 @@ no_cached_page:
          */
         if (error == -ENOMEM)
                 return NOPAGE_OOM;
-        return NULL;
+        return NOPAGE_SIGBUS;
 
 page_not_uptodate:
         if (!did_readaround) {
                 majmin = VM_FAULT_MAJOR;
-                inc_page_state(pgmajfault);
+                count_vm_event(PGMAJFAULT);
         }
         lock_page(page);
 
@@ -1522,8 +1563,9 @@ page_not_uptodate:
          * Things didn't work out. Return zero to tell the
          * mm layer so, possibly freeing the page cache page first.
          */
+        shrink_readahead_size_eio(file, ra);
         page_cache_release(page);
-        return NULL;
+        return NOPAGE_SIGBUS;
 }
 EXPORT_SYMBOL(filemap_nopage);
 
@@ -1585,7 +1627,7 @@ no_cached_page:
 page_not_uptodate:
         lock_page(page);
 
-        /* Did it get unhashed while we waited for it? */
+        /* Did it get truncated while we waited for it? */
         if (!page->mapping) {
                 unlock_page(page);
                 goto err;
@@ -1892,7 +1934,7 @@ int remove_suid(struct dentry *dentry)
 EXPORT_SYMBOL(remove_suid);
 
 size_t
-__filemap_copy_from_user_iovec(char *vaddr, 
+__filemap_copy_from_user_iovec_inatomic(char *vaddr,
                         const struct iovec *iov, size_t base, size_t bytes)
 {
         size_t copied = 0, left = 0;
@@ -1908,12 +1950,8 @@ __filemap_copy_from_user_iovec(char *vaddr,
                 vaddr += copy;
                 iov++;
 
-                if (unlikely(left)) {
-                        /* zero the rest of the target like __copy_from_user */
-                        if (bytes)
-                                memset(vaddr, 0, bytes);
+                if (unlikely(left))
                         break;
-                }
         }
         return copied - left;
 }
@@ -2045,7 +2083,7 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 {
         struct file *file = iocb->ki_filp;
         struct address_space * mapping = file->f_mapping;
-        struct address_space_operations *a_ops = mapping->a_ops;
+        const struct address_space_operations *a_ops = mapping->a_ops;
         struct inode    *inode = mapping->host;
         long            status = 0;
         struct page     *page;
@@ -2071,14 +2109,21 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
         do {
                 unsigned long index;
                 unsigned long offset;
-                unsigned long maxlen;
                 size_t copied;
 
                 offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
                 index = pos >> PAGE_CACHE_SHIFT;
                 bytes = PAGE_CACHE_SIZE - offset;
-                if (bytes > count)
-                        bytes = count;
+
+                /* Limit the size of the copy to the caller's write size */
+                bytes = min(bytes, count);
+
+                /*
+                 * Limit the size of the copy to that of the current segment,
+                 * because fault_in_pages_readable() doesn't know how to walk
+                 * segments.
+                 */
+                bytes = min(bytes, cur_iov->iov_len - iov_base);
 
                 /*
                  * Bring in the user page that we will copy from _first_.
@@ -2086,10 +2131,7 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
                  * same page as we're writing to, without it being marked
                  * up-to-date.
                  */
-                maxlen = cur_iov->iov_len - iov_base;
-                if (maxlen > bytes)
-                        maxlen = bytes;
-                fault_in_pages_readable(buf, maxlen);
+                fault_in_pages_readable(buf, bytes);
 
                 page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
                 if (!page) {
@@ -2097,6 +2139,12 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
                         break;
                 }
 
+                if (unlikely(bytes == 0)) {
+                        status = 0;
+                        copied = 0;
+                        goto zero_length_segment;
+                }
+
                 status = a_ops->prepare_write(file, page, offset, offset+bytes);
                 if (unlikely(status)) {
                         loff_t isize = i_size_read(inode);
@@ -2126,7 +2174,8 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
                         page_cache_release(page);
                         continue;
                 }
-                if (likely(copied > 0)) {
+zero_length_segment:
+                if (likely(copied >= 0)) {
                         if (!status)
                                 status = copied;
 
@@ -2191,7 +2240,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
                                 unsigned long nr_segs, loff_t *ppos)
 {
         struct file *file = iocb->ki_filp;
-        struct address_space * mapping = file->f_mapping;
+        const struct address_space * mapping = file->f_mapping;
         size_t ocount;          /* original count */
         size_t count;           /* after file limit checks */
         struct inode    *inode = mapping->host;