[PATCH 07/12] mm: Add support for direct_IO to highmem pages

[Mel Gorman <mgorman@suse.de>]

The patch "mm: Add support for a filesystem to activate swap files and
use direct_IO for writing swap pages" added support for using direct_IO
to write swap pages but it is insufficient for highmem pages.

To support highmem pages, this patch kmaps() the page before calling the
direct_IO() handler. As direct_IO deals with virtual addresses an
additional helper is necessary for get_kernel_pages() to lookup the
struct page for a kmap virtual address.

Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/highmem.h |    7 +++++++
 mm/highmem.c            |   12 ++++++++++++
 mm/memory.c             |    3 +--
 mm/page_io.c            |    3 ++-
 4 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index d3999b4..e186e3c 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -39,10 +39,17 @@ extern unsigned long totalhigh_pages;
 
 void kmap_flush_unused(void);
 
+struct page *kmap_to_page(void *addr);
+
 #else /* CONFIG_HIGHMEM */
 
 static inline unsigned int nr_free_highpages(void) { return 0; }
 
+static inline struct page *kmap_to_page(void *addr)
+{
+	return virt_to_page(addr);
+}
+
 #define totalhigh_pages 0UL
 
 #ifndef ARCH_HAS_KMAP
diff --git a/mm/highmem.c b/mm/highmem.c
index 57d82c6..d517cd1 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -94,6 +94,18 @@ static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait);
 		do { spin_unlock(&kmap_lock); (void)(flags); } while (0)
 #endif
 
+struct page *kmap_to_page(void *vaddr)
+{
+	unsigned long addr = (unsigned long)vaddr;
+
+	if (addr >= PKMAP_ADDR(0) && addr <= PKMAP_ADDR(LAST_PKMAP)) {
+		int i = (addr - PKMAP_ADDR(0)) >> PAGE_SHIFT;
+		return pte_page(pkmap_page_table[i]);
+	}
+
+	return virt_to_page(addr);
+}
+
 static void flush_all_zero_pkmaps(void)
 {
 	int i;
diff --git a/mm/memory.c b/mm/memory.c
index 0bc990e7..fd32a1a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1858,8 +1858,7 @@ int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write,
 		if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE))
 			return seg;
 
-		/* virt_to_page sanity checks the PFN */
-		pages[seg] = virt_to_page(kiov[seg].iov_base);
+		pages[seg] = kmap_to_page(kiov[seg].iov_base);
 		page_cache_get(pages[seg]);
 	}
 
diff --git a/mm/page_io.c b/mm/page_io.c
index f363261..1e39e88 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -198,7 +198,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
 		struct file *swap_file = sis->swap_file;
 		struct address_space *mapping = swap_file->f_mapping;
 		struct iovec iov = {
-			.iov_base = page_address(page),
+			.iov_base = kmap(page),
 			.iov_len  = PAGE_SIZE,
 		};
 
@@ -211,6 +211,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
 		ret = mapping->a_ops->direct_IO(KERNEL_WRITE,
 						&kiocb, &iov,
 						kiocb.ki_pos, 1);
+		kunmap(page);
 		if (ret == PAGE_SIZE) {
 			count_vm_event(PSWPOUT);
 			ret = 0;
-- 
1.7.9.2

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>