[RHEL7,COMMIT] ms/mm: implement ->map_pages for page cache

Submitted by Konstantin Khorenko on Feb. 27, 2020, 4:07 p.m.

Details

Message ID 202002271607.01RG7WBR025914@finist-ce7.sw.ru
State New
Series "Series without cover letter"
Headers show

Commit Message

Konstantin Khorenko Feb. 27, 2020, 4:07 p.m.
The commit is pushed to "branch-rh7-3.10.0-1062.12.1.vz7.131.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-1062.12.1.vz7.131.4
------>
commit b631f7c5c5b317ae54ff825cd2e34b3e7e790a71
Author: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Date:   Thu Feb 27 19:07:32 2020 +0300

    ms/mm: implement ->map_pages for page cache
    
    filemap_map_pages() is generic implementation of ->map_pages() for
    filesystems who uses page cache.
    
    It should be safe to use filemap_map_pages() for ->map_pages() if
    filesystem use filemap_fault() for ->fault().
    
    Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
    Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
    Cc: Mel Gorman <mgorman@suse.de>
    Cc: Rik van Riel <riel@redhat.com>
    Cc: Andi Kleen <ak@linux.intel.com>
    Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
    Cc: Dave Hansen <dave.hansen@linux.intel.com>
    Cc: Alexander Viro <viro@zeniv.linux.org.uk>
    Cc: Dave Chinner <david@fromorbit.com>
    Cc: Ning Qu <quning@gmail.com>
    Cc: Hugh Dickins <hughd@google.com>
    Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
    Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
    
    https://jira.sw.ru/browse/PSBM-101300
    (cherry picked from commit f1820361f83d556a7f0a9f629100f3825e594328)
    Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
---
 fs/9p/vfs_file.c   |  1 +
 fs/btrfs/file.c    |  1 +
 fs/cifs/file.c     |  1 +
 fs/ext4/file.c     |  1 +
 fs/f2fs/file.c     |  1 +
 fs/fuse/file.c     |  1 +
 fs/gfs2/file.c     |  1 +
 fs/nfs/file.c      |  1 +
 fs/nilfs2/file.c   |  1 +
 fs/ubifs/file.c    |  1 +
 fs/xfs/xfs_file.c  |  1 +
 include/linux/mm.h |  1 +
 mm/filemap.c       | 74 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/nommu.c         |  6 +++++
 14 files changed, 92 insertions(+)

Patch hide | download patch | download mbox

diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 1ab222986d8b5..b261bb06cd475 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -734,6 +734,7 @@  v9fs_cached_file_write(struct file *filp, const char __user * data,
 
 static const struct vm_operations_struct v9fs_file_vm_ops = {
 	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = v9fs_vm_page_mkwrite,
 };
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f3199b4d87de4..80dcf423266ce 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2188,6 +2188,7 @@  int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 static const struct vm_operations_struct btrfs_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= btrfs_page_mkwrite,
 };
 
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index ccca9c5d9d0f0..3f5304f5acf0c 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3398,6 +3398,7 @@  cifs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 static struct vm_operations_struct cifs_file_vm_ops = {
 	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = cifs_page_mkwrite,
 };
 
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 5acd8ae38db28..509a4ca6c39db 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -349,6 +349,7 @@  static const struct vm_operations_struct ext4_dax_vm_ops = {
 static const struct vm_operations_struct ext4_file_vm_ops = {
 	.fault		= ext4_filemap_fault,
 	.page_mkwrite   = ext4_page_mkwrite,
+	.map_pages	= filemap_map_pages,
 };
 
 static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 36a8bec3f5ee4..f9b38dc7e8974 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -99,6 +99,7 @@  static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 
 static const struct vm_operations_struct f2fs_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= f2fs_vm_page_mkwrite,
 };
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 2ecccf337b45b..4c58d527ec7e4 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2656,6 +2656,7 @@  static int fuse_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 static const struct vm_operations_struct fuse_file_vm_ops = {
 	.close		= fuse_vma_close,
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= fuse_page_mkwrite,
 };
 
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index a7d368691df0d..53a11f484fb48 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -506,6 +506,7 @@  static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 static const struct vm_operations_struct gfs2_vm_ops = {
 	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = gfs2_page_mkwrite,
 };
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 7fab5b6cbdefa..62ab016234339 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -624,6 +624,7 @@  static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 static const struct vm_operations_struct nfs_file_vm_ops = {
 	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = nfs_vm_page_mkwrite,
 };
 
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index e3ce6c9e2a7b8..e0c458b8a1687 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -134,6 +134,7 @@  static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 static const struct vm_operations_struct nilfs_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= nilfs_page_mkwrite,
 };
 
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 2dfae9a054c64..09c7e78ea2fc5 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1537,6 +1537,7 @@  static int ubifs_vm_page_mkwrite(struct vm_area_struct *vma,
 
 static const struct vm_operations_struct ubifs_file_vm_ops = {
 	.fault        = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = ubifs_vm_page_mkwrite,
 };
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 891c37fe39928..5c0d38b82bb10 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1316,6 +1316,7 @@  static const struct vm_operations_struct xfs_file_vm_ops = {
 	.huge_fault	= xfs_filemap_huge_fault,
 	.page_mkwrite	= xfs_filemap_page_mkwrite,
 	.pfn_mkwrite	= xfs_filemap_pfn_mkwrite,
+	.map_pages	= filemap_map_pages,
 };
 
 STATIC int
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bc4536044e7db..701818b16b1b2 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2156,6 +2156,7 @@  extern void truncate_inode_pages_final(struct address_space *);
 
 /* generic vm_area_ops exported for stackable file systems */
 extern int filemap_fault(struct vm_area_struct *, struct vm_fault *);
+extern void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf);
 extern int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 struct path;
diff --git a/mm/filemap.c b/mm/filemap.c
index fd9abfec4b41c..2ba7ef844af67 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -35,6 +35,7 @@ 
 #include <linux/hugetlb.h>
 #include <linux/memcontrol.h>
 #include <linux/cleancache.h>
+#include <linux/rmap.h>
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS
@@ -2408,6 +2409,78 @@  int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 EXPORT_SYMBOL(filemap_fault);
 
+void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct radix_tree_iter iter;
+	void **slot;
+	struct file *file = vma->vm_file;
+	struct address_space *mapping = file->f_mapping;
+	loff_t size;
+	struct page *page;
+	unsigned long address = (unsigned long) vmf->virtual_address;
+	unsigned long addr;
+	pte_t *pte;
+
+	rcu_read_lock();
+	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, vmf->pgoff) {
+		if (iter.index > vmf->max_pgoff)
+			break;
+repeat:
+		page = radix_tree_deref_slot(slot);
+		if (unlikely(!page))
+			goto next;
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page))
+				break;
+			else
+				goto next;
+		}
+
+		if (!page_cache_get_speculative(page))
+			goto repeat;
+
+		/* Has the page moved? */
+		if (unlikely(page != *slot)) {
+			page_cache_release(page);
+			goto repeat;
+		}
+
+		if (!PageUptodate(page) ||
+				PageReadahead(page) ||
+				PageHWPoison(page))
+			goto skip;
+		if (!trylock_page(page))
+			goto skip;
+
+		if (page->mapping != mapping || !PageUptodate(page))
+			goto unlock;
+
+		size = i_size_read(mapping->host) + PAGE_CACHE_SIZE - 1;
+		if (page->index >= size	>> PAGE_CACHE_SHIFT)
+			goto unlock;
+
+		pte = vmf->pte + page->index - vmf->pgoff;
+		if (!pte_none(*pte))
+			goto unlock;
+
+		if (file->f_ra.mmap_miss > 0)
+			file->f_ra.mmap_miss--;
+		addr = address + (page->index - vmf->pgoff) * PAGE_SIZE;
+		do_set_pte(vma, addr, page, pte, false, false);
+		unlock_page(page);
+		goto next;
+unlock:
+		unlock_page(page);
+skip:
+		page_cache_release(page);
+next:
+		if (iter.index == vmf->max_pgoff)
+			break;
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(filemap_map_pages);
+
 int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
@@ -2437,6 +2510,7 @@  EXPORT_SYMBOL(filemap_page_mkwrite);
 
 const struct vm_operations_struct generic_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= filemap_page_mkwrite,
 };
 
diff --git a/mm/nommu.c b/mm/nommu.c
index a1c026a881102..0a3cbe94535af 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -2028,6 +2028,12 @@  int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 EXPORT_SYMBOL(filemap_fault);
 
+void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	BUG();
+}
+EXPORT_SYMBOL(filemap_map_pages);
+
 static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long addr, void *buf, int len, int write)
 {