simple_readpage() and simple_write_end() are modified to handle huge
pages.
simple_thp_write_begin() is introduced to allocate huge pages on write.
Signed-off-by: Kirill A. Shutemov <kirill.shute...@linux.intel.com>
---
fs/libfs.c | 58 +++++++++++++++++++++++++++++++++++++++++++++----
include/linux/fs.h | 7 ++++++
include/linux/pagemap.h | 8 +++++++
3 files changed, 69 insertions(+), 4 deletions(-)
diff --git a/fs/libfs.c b/fs/libfs.c
index 3a3a9b53bf..807f66098e 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -364,7 +364,7 @@ EXPORT_SYMBOL(simple_setattr);
int simple_readpage(struct file *file, struct page *page)
{
- clear_highpage(page);
+ clear_pagecache_page(page);
flush_dcache_page(page);
SetPageUptodate(page);
unlock_page(page);
@@ -424,9 +424,14 @@ int simple_write_end(struct file *file, struct
address_space *mapping,
/* zero the stale part of the page if we did a short copy */
if (copied < len) {
- unsigned from = pos & (PAGE_CACHE_SIZE - 1);
-
- zero_user(page, from + copied, len - copied);
+ unsigned from;
+ if (PageTransHugeCache(page)) {
+ from = pos & ~HPAGE_PMD_MASK;
+ zero_huge_user(page, from + copied, len - copied);
+ } else {
+ from = pos & ~PAGE_CACHE_MASK;
+ zero_user(page, from + copied, len - copied);
+ }
}
if (!PageUptodate(page))
@@ -445,6 +450,51 @@ int simple_write_end(struct file *file, struct
address_space *mapping,
return copied;
}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE_PAGECACHE
+int simple_thp_write_begin(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata)
+{
+ struct page *page = NULL;
+ pgoff_t index;
+
+ index = pos >> PAGE_CACHE_SHIFT;
+
+ /*
+ * Do not allocate a huge page in the first huge page range in page
+ * cache. This way we can avoid most small files overhead.
+ */
+ if (mapping_can_have_hugepages(mapping) &&
+ pos >= HPAGE_PMD_SIZE) {
+ page = grab_cache_page_write_begin(mapping,
+ index & ~HPAGE_CACHE_INDEX_MASK,
+ flags | AOP_FLAG_TRANSHUGE);
+ /* fallback to small page */
+ if (!page) {
+ unsigned long offset;
+ offset = pos & ~PAGE_CACHE_MASK;
+ /* adjust the len to not cross small page boundary */
+ len = min_t(unsigned long,
+ len, PAGE_CACHE_SIZE - offset);
+ }
+ BUG_ON(page && !PageTransHuge(page));
+ }
+ if (!page)
+ return simple_write_begin(file, mapping, pos, len, flags,
+ pagep, fsdata);
+
+ *pagep = page;
+
+ if (!PageUptodate(page) && len != HPAGE_PMD_SIZE) {
+ unsigned from = pos & ~HPAGE_PMD_MASK;
+
+ zero_huge_user_segment(page, 0, from);
+ zero_huge_user_segment(page, from + len, HPAGE_PMD_SIZE);
+ }
+ return 0;
+}
+#endif
+
/*
* the inodes created here are not hashed. If you use iunique to generate
* unique inode values later for this filesystem, then you must take care
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 42ccdeddd9..71a5ce4472 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2566,6 +2566,13 @@ extern int simple_write_begin(struct file *file, struct
address_space *mapping,
extern int simple_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE_PAGECACHE
+extern int simple_thp_write_begin(struct file *file,
+ struct address_space *mapping, loff_t pos, unsigned len,
+ unsigned flags, struct page **pagep, void **fsdata);
+#else
+#define simple_thp_write_begin simple_write_begin
+#endif
extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned
int flags);
extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t
*);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index ad60dcc50e..967aadbc5e 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -572,4 +572,12 @@ static inline int add_to_page_cache(struct page *page,
return error;
}
+static inline void clear_pagecache_page(struct page *page)
+{
+ if (PageTransHuge(page))
+ zero_huge_user(page, 0, HPAGE_PMD_SIZE);
+ else
+ clear_highpage(page);
+}
+
#endif /* _LINUX_PAGEMAP_H */
--
1.8.4.rc3
--
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/
