[PATCH] add AOP_TRUNCATED_PAGE, prepend AOP_ to WRITEPAGE_ACTIVATE

readpage(), prepare_write(), and commit_write() callers are updated to
understand the special return code AOP_TRUNCATED_PAGE in the style of
writepage() and WRITEPAGE_ACTIVATE.  AOP_TRUNCATED_PAGE tells the caller that
the callee has unlocked the page and that the operation should be tried again
with a new page.  OCFS2 uses this to detect and work around a lock inversion in
its aop methods.  There should be no change in behaviour for methods that don't
return AOP_TRUNCATED_PAGE.

WRITEPAGE_ACTIVATE is also prepended with AOP_ for consistency and they are
made enums so that kerneldoc can be used to document their semantics.

Signed-off-by: Zach Brown <zach.brown@oracle.com>

4 files changed, 61 insertions, 31 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 33a28bfde158..6e1d08a2b8b9 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -831,8 +831,13 @@ readpage:
                 /* Start the actual read. The read will unlock the page. */
                 error = mapping->a_ops->readpage(filp, page);
 
-                if (unlikely(error))
+                if (unlikely(error)) {
+                        if (error == AOP_TRUNCATED_PAGE) {
+                                page_cache_release(page);
+                                goto find_page;
+                        }
                         goto readpage_error;
+                }
 
                 if (!PageUptodate(page)) {
                         lock_page(page);
@@ -1152,26 +1157,24 @@ static int fastcall page_cache_read(struct file * file, unsigned long offset)
 {
         struct address_space *mapping = file->f_mapping;
         struct page *page; 
-        int error;
+        int ret;
 
-        page = page_cache_alloc_cold(mapping);
-        if (!page)
-                return -ENOMEM;
+        do {
+                page = page_cache_alloc_cold(mapping);
+                if (!page)
+                        return -ENOMEM;
+
+                ret = add_to_page_cache_lru(page, mapping, offset, GFP_KERNEL);
+                if (ret == 0)
+                        ret = mapping->a_ops->readpage(file, page);
+                else if (ret == -EEXIST)
+                        ret = 0; /* losing race to add is OK */
 
-        error = add_to_page_cache_lru(page, mapping, offset, GFP_KERNEL);
-        if (!error) {
-                error = mapping->a_ops->readpage(file, page);
                 page_cache_release(page);
-                return error;
-        }
 
-        /*
-         * We arrive here in the unlikely event that someone 
-         * raced with us and added our page to the cache first
-         * or we are out of memory for radix-tree nodes.
-         */
-        page_cache_release(page);
-        return error == -EEXIST ? 0 : error;
+        } while (ret == AOP_TRUNCATED_PAGE);
+                
+        return ret;
 }
 
 #define MMAP_LOTSAMISS  (100)
@@ -1331,10 +1334,14 @@ page_not_uptodate:
                 goto success;
         }
 
-        if (!mapping->a_ops->readpage(file, page)) {
+        error = mapping->a_ops->readpage(file, page);
+        if (!error) {
                 wait_on_page_locked(page);
                 if (PageUptodate(page))
                         goto success;
+        } else if (error == AOP_TRUNCATED_PAGE) {
+                page_cache_release(page);
+                goto retry_find;
         }
 
         /*
@@ -1358,10 +1365,14 @@ page_not_uptodate:
                 goto success;
         }
         ClearPageError(page);
-        if (!mapping->a_ops->readpage(file, page)) {
+        error = mapping->a_ops->readpage(file, page);
+        if (!error) {
                 wait_on_page_locked(page);
                 if (PageUptodate(page))
                         goto success;
+        } else if (error == AOP_TRUNCATED_PAGE) {
+                page_cache_release(page);
+                goto retry_find;
         }
 
         /*
@@ -1444,10 +1455,14 @@ page_not_uptodate:
                 goto success;
         }
 
-        if (!mapping->a_ops->readpage(file, page)) {
+        error = mapping->a_ops->readpage(file, page);
+        if (!error) {
                 wait_on_page_locked(page);
                 if (PageUptodate(page))
                         goto success;
+        } else if (error == AOP_TRUNCATED_PAGE) {
+                page_cache_release(page);
+                goto retry_find;
         }
 
         /*
@@ -1470,10 +1485,14 @@ page_not_uptodate:
         }
 
         ClearPageError(page);
-        if (!mapping->a_ops->readpage(file, page)) {
+        error = mapping->a_ops->readpage(file, page);
+        if (!error) {
                 wait_on_page_locked(page);
                 if (PageUptodate(page))
                         goto success;
+        } else if (error == AOP_TRUNCATED_PAGE) {
+                page_cache_release(page);
+                goto retry_find;
         }
 
         /*
@@ -1934,12 +1953,16 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
                 status = a_ops->prepare_write(file, page, offset, offset+bytes);
                 if (unlikely(status)) {
                         loff_t isize = i_size_read(inode);
+
+                        if (status != AOP_TRUNCATED_PAGE)
+                                unlock_page(page);
+                        page_cache_release(page);
+                        if (status == AOP_TRUNCATED_PAGE)
+                                continue;
                         /*
                          * prepare_write() may have instantiated a few blocks
                          * outside i_size.  Trim these off again.
                          */
-                        unlock_page(page);
-                        page_cache_release(page);
                         if (pos + bytes > isize)
                                 vmtruncate(inode, isize);
                         break;
@@ -1952,6 +1975,10 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
                                                 cur_iov, iov_base, bytes);
                 flush_dcache_page(page);
                 status = a_ops->commit_write(file, page, offset, offset+bytes);
+                if (status == AOP_TRUNCATED_PAGE) {
+                        page_cache_release(page);
+                        continue;
+                }
                 if (likely(copied > 0)) {
                         if (!status)
                                 status = copied;
diff --git a/mm/readahead.c b/mm/readahead.c
index 72e7adbb87c7..8d6eeaaa6296 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -158,7 +158,7 @@ static int read_pages(struct address_space *mapping, struct file *filp,
 {
         unsigned page_idx;
         struct pagevec lru_pvec;
-        int ret = 0;
+        int ret;
 
         if (mapping->a_ops->readpages) {
                 ret = mapping->a_ops->readpages(filp, mapping, pages, nr_pages);
@@ -171,14 +171,17 @@ static int read_pages(struct address_space *mapping, struct file *filp,
                 list_del(&page->lru);
                 if (!add_to_page_cache(page, mapping,
                                         page->index, GFP_KERNEL)) {
-                        mapping->a_ops->readpage(filp, page);
-                        if (!pagevec_add(&lru_pvec, page))
-                                __pagevec_lru_add(&lru_pvec);
-                } else {
-                        page_cache_release(page);
+                        ret = mapping->a_ops->readpage(filp, page);
+                        if (ret != AOP_TRUNCATED_PAGE) {
+                                if (!pagevec_add(&lru_pvec, page))
+                                        __pagevec_lru_add(&lru_pvec);
+                                continue;
+                        } /* else fall through to release */
                 }
+                page_cache_release(page);
         }
         pagevec_lru_add(&lru_pvec);
+        ret = 0;
 out:
         return ret;
 }
diff --git a/mm/shmem.c b/mm/shmem.c
index dc25565a61e9..d9fc277940da 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -855,7 +855,7 @@ unlock:
         swap_free(swap);
 redirty:
         set_page_dirty(page);
-        return WRITEPAGE_ACTIVATE;      /* Return with the page locked */
+        return AOP_WRITEPAGE_ACTIVATE;  /* Return with the page locked */
 }
 
 #ifdef CONFIG_NUMA
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b0cd81c32de6..795a050fe471 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -367,7 +367,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping)
                 res = mapping->a_ops->writepage(page, &wbc);
                 if (res < 0)
                         handle_write_error(mapping, page, res);
-                if (res == WRITEPAGE_ACTIVATE) {
+                if (res == AOP_WRITEPAGE_ACTIVATE) {
                         ClearPageReclaim(page);
                         return PAGE_ACTIVATE;
                 }