If the symlink has already be been read-in, then
page_follow_link_light can succeed in RCU-walk mode.
page_getlink_rcu() is added to support this.

With this, many filesystems can follow links in RCU-walk
mode when everything is cached.  This includes ext?fs and
others.

If the page is a HighMem page we do *not* try to kmap_atomic,
but simply give up - only page_address() is used.
This is because we need to be able to sleep while holding
the address of the page, particularly over calls to do_last()
which can be quite slow and in particular takes a mutex.

If this were a problem, then copying into a GFP_ATOMIC allocation
might be a workable solution.

This selective calling of kmap requires us to know, in page_put_link,
whether or not kunmap() needs to be called.  Pass this information in
the lsb of the cookie.

The new page_getlink_rcu() needs to be passed the inode rather than
the dentry (as dentry->d_inode is not stable), so change
page_getlink() to behave the same way: it only needed the dentry
to get the inode.

Signed-off-by: NeilBrown <ne...@suse.de>
---
 fs/namei.c |   45 ++++++++++++++++++++++++++++++++++++---------
 1 file changed, 36 insertions(+), 9 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 0f5b627bd78e..d13b4315447f 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4497,24 +4497,48 @@ int generic_readlink(struct dentry *dentry, char __user 
*buffer, int buflen)
 EXPORT_SYMBOL(generic_readlink);
 
 /* get the link contents into pagecache */
-static char *page_getlink(struct dentry * dentry, struct page **ppage)
+static char *page_getlink(struct inode *inode, struct page **ppage)
 {
        char *kaddr;
        struct page *page;
-       struct address_space *mapping = dentry->d_inode->i_mapping;
+       struct address_space *mapping = inode->i_mapping;
        page = read_mapping_page(mapping, 0, NULL);
        if (IS_ERR(page))
                return (char*)page;
        *ppage = page;
        kaddr = kmap(page);
-       nd_terminate_link(kaddr, dentry->d_inode->i_size, PAGE_SIZE - 1);
+       nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1);
+       return kaddr;
+}
+
+/* get the link contents from pagecache under RCU */
+static char *page_getlink_rcu(struct inode *inode, struct page **ppage)
+{
+       char *kaddr;
+       struct page *page;
+       struct address_space *mapping = inode->i_mapping;
+
+       page = find_get_page(mapping, 0);
+       if (page &&
+           (!PageUptodate(page) || PageHighMem(page))) {
+               put_page(page);
+               page = NULL;
+       }
+       if (!page) {
+               *ppage = ERR_PTR(-ECHILD);
+               return NULL;
+       }
+       *ppage = page;
+       kaddr = page_address(page);
+       nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1);
        return kaddr;
 }
 
 int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
        struct page *page = NULL;
-       int res = readlink_copy(buffer, buflen, page_getlink(dentry, &page));
+       int res = readlink_copy(buffer, buflen,
+                               page_getlink(dentry->d_inode, &page));
        if (page) {
                kunmap(page);
                page_cache_release(page);
@@ -4527,19 +4551,22 @@ void *page_follow_link_light(struct dentry *dentry, 
struct inode *inode,
                             int flags)
 {
        struct page *page = NULL;
-       if (flags & LOOKUP_RCU)
-               return ERR_PTR(-ECHILD);
-       nd_set_link(page_getlink(dentry, &page));
+       if (flags & LOOKUP_RCU) {
+               nd_set_link(page_getlink_rcu(inode, &page));
+               page = (void *)((unsigned long)page | 1);
+       } else
+               nd_set_link(page_getlink(inode, &page));
        return page;
 }
 EXPORT_SYMBOL(page_follow_link_light);
 
 void page_put_link(struct dentry *dentry, char *link, void *cookie)
 {
-       struct page *page = cookie;
+       struct page *page = (void *)((unsigned long)cookie & ~1UL);
 
        if (page) {
-               kunmap(page);
+               if (page == cookie)
+                       kunmap(page);
                page_cache_release(page);
        }
 }


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to