page cache: use xa_lock

Remove the address_space ->tree_lock and use the xa_lock newly added to the radix_tree_root. Rename the address_space ->page_tree to ->i_pages, since we don't really care that it's a tree. [willy@infradead.org: fix nds32, fs/dax.c] Link: http://lkml.kernel.org/r/20180406145415.GB20605@bombadil.infradead.orgLink: http://lkml.kernel.org/r/20180313132639.17387-9-willy@infradead.org Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com> Acked-by: Jeff Layton <jlayton@redhat.com> Cc: Darrick J. Wong <darrick.wong@oracle.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Cc: Will Deacon <will.deacon@arm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
LeviMarvin · Apr 11, 2018 · b93b016 · b93b016
1 parent f6bb2a2
commit b93b016
Show file tree

Hide file tree

Showing 39 changed files with 345 additions and 366 deletions.
diff --git a/Documentation/cgroup-v1/memory.txt b/Documentation/cgroup-v1/memory.txt
@@ -262,7 +262,7 @@ When oom event notifier is registered, event will be delivered.
 2.6 Locking
 
    lock_page_cgroup()/unlock_page_cgroup() should not be called under
-   mapping->tree_lock.
+   the i_pages lock.
 
    Other lock order is following:
    PG_locked.

diff --git a/Documentation/vm/page_migration b/Documentation/vm/page_migration
@@ -90,7 +90,7 @@ Steps:
 
 1. Lock the page to be migrated
 
-2. Insure that writeback is complete.
+2. Ensure that writeback is complete.
 
 3. Lock the new page that we want to move to. It is locked so that accesses to
    this (not yet uptodate) page immediately lock while the move is in progress.
@@ -100,8 +100,8 @@ Steps:
    mapcount is not zero then we do not migrate the page. All user space
    processes that attempt to access the page will now wait on the page lock.
 
-5. The radix tree lock is taken. This will cause all processes trying
-   to access the page via the mapping to block on the radix tree spinlock.
+5. The i_pages lock is taken. This will cause all processes trying
+   to access the page via the mapping to block on the spinlock.
 
 6. The refcount of the page is examined and we back out if references remain
    otherwise we know that we are the only one referencing this page.
@@ -114,12 +114,12 @@ Steps:
 
 9. The radix tree is changed to point to the new page.
 
-10. The reference count of the old page is dropped because the radix tree
+10. The reference count of the old page is dropped because the address space
     reference is gone. A reference to the new page is established because
-    the new page is referenced to by the radix tree.
+    the new page is referenced by the address space.
 
-11. The radix tree lock is dropped. With that lookups in the mapping
-    become possible again. Processes will move from spinning on the tree_lock
+11. The i_pages lock is dropped. With that lookups in the mapping
+    become possible again. Processes will move from spinning on the lock
     to sleeping on the locked new page.
 
 12. The page contents are copied to the new page.

diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
@@ -318,10 +318,8 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
 #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
 extern void flush_kernel_dcache_page(struct page *);
 
-#define flush_dcache_mmap_lock(mapping) \
-	spin_lock_irq(&(mapping)->tree_lock)
-#define flush_dcache_mmap_unlock(mapping) \
-	spin_unlock_irq(&(mapping)->tree_lock)
+#define flush_dcache_mmap_lock(mapping)		xa_lock_irq(&mapping->i_pages)
+#define flush_dcache_mmap_unlock(mapping)	xa_unlock_irq(&mapping->i_pages)
 
 #define flush_icache_user_range(vma,page,addr,len) \
 	flush_dcache_page(page)

diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h
@@ -34,8 +34,8 @@ void flush_anon_page(struct vm_area_struct *vma,
 void flush_kernel_dcache_page(struct page *page);
 void flush_icache_range(unsigned long start, unsigned long end);
 void flush_icache_page(struct vm_area_struct *vma, struct page *page);
-#define flush_dcache_mmap_lock(mapping)   spin_lock_irq(&(mapping)->tree_lock)
-#define flush_dcache_mmap_unlock(mapping) spin_unlock_irq(&(mapping)->tree_lock)
+#define flush_dcache_mmap_lock(mapping)   xa_lock_irq(&(mapping)->i_pages)
+#define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&(mapping)->i_pages)
 
 #else
 #include <asm-generic/cacheflush.h>

diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h
@@ -46,9 +46,7 @@ extern void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
 extern void flush_dcache_range(unsigned long start, unsigned long end);
 extern void invalidate_dcache_range(unsigned long start, unsigned long end);
 
-#define flush_dcache_mmap_lock(mapping) \
-	spin_lock_irq(&(mapping)->tree_lock)
-#define flush_dcache_mmap_unlock(mapping) \
-	spin_unlock_irq(&(mapping)->tree_lock)
+#define flush_dcache_mmap_lock(mapping)		xa_lock_irq(&mapping->i_pages)
+#define flush_dcache_mmap_unlock(mapping)	xa_unlock_irq(&mapping->i_pages)
 
 #endif /* _ASM_NIOS2_CACHEFLUSH_H */
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
@@ -55,10 +55,8 @@ void invalidate_kernel_vmap_range(void *vaddr, int size);
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *page);
 
-#define flush_dcache_mmap_lock(mapping) \
-	spin_lock_irq(&(mapping)->tree_lock)
-#define flush_dcache_mmap_unlock(mapping) \
-	spin_unlock_irq(&(mapping)->tree_lock)
+#define flush_dcache_mmap_lock(mapping)		xa_lock_irq(&mapping->i_pages)
+#define flush_dcache_mmap_unlock(mapping)	xa_unlock_irq(&mapping->i_pages)
 
 #define flush_icache_page(vma,page)	do { 		\
 	flush_kernel_dcache_page(page);			\

diff --git a/drivers/staging/lustre/lustre/llite/glimpse.c b/drivers/staging/lustre/lustre/llite/glimpse.c
@@ -69,7 +69,7 @@ blkcnt_t dirty_cnt(struct inode *inode)
 	void	      *results[1];
 
 	if (inode->i_mapping)
-		cnt += radix_tree_gang_lookup_tag(&inode->i_mapping->page_tree,
+		cnt += radix_tree_gang_lookup_tag(&inode->i_mapping->i_pages,
 						  results, 0, 1,
 						  PAGECACHE_TAG_DIRTY);
 	if (cnt == 0 && atomic_read(&vob->vob_mmap_cnt) > 0)

diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c b/drivers/staging/lustre/lustre/mdc/mdc_request.c
@@ -934,14 +934,14 @@ static struct page *mdc_page_locate(struct address_space *mapping, __u64 *hash,
 	struct page *page;
 	int found;
 
-	spin_lock_irq(&mapping->tree_lock);
-	found = radix_tree_gang_lookup(&mapping->page_tree,
+	xa_lock_irq(&mapping->i_pages);
+	found = radix_tree_gang_lookup(&mapping->i_pages,
 				       (void **)&page, offset, 1);
 	if (found > 0 && !radix_tree_exceptional_entry(page)) {
 		struct lu_dirpage *dp;
 
 		get_page(page);
-		spin_unlock_irq(&mapping->tree_lock);
+		xa_unlock_irq(&mapping->i_pages);
 		/*
 		 * In contrast to find_lock_page() we are sure that directory
 		 * page cannot be truncated (while DLM lock is held) and,
@@ -989,7 +989,7 @@ static struct page *mdc_page_locate(struct address_space *mapping, __u64 *hash,
 			page = ERR_PTR(-EIO);
 		}
 	} else {
-		spin_unlock_irq(&mapping->tree_lock);
+		xa_unlock_irq(&mapping->i_pages);
 		page = NULL;
 	}
 	return page;

diff --git a/fs/afs/write.c b/fs/afs/write.c
@@ -570,10 +570,11 @@ static int afs_writepages_region(struct address_space *mapping,
 
 		_debug("wback %lx", page->index);
 
-		/* at this point we hold neither mapping->tree_lock nor lock on
-		 * the page itself: the page may be truncated or invalidated
-		 * (changing page->mapping to NULL), or even swizzled back from
-		 * swapper_space to tmpfs file mapping
+		/*
+		 * at this point we hold neither the i_pages lock nor the
+		 * page lock: the page may be truncated or invalidated
+		 * (changing page->mapping to NULL), or even swizzled
+		 * back from swapper_space to tmpfs file mapping
 		 */
 		ret = lock_page_killable(page);
 		if (ret < 0) {

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
@@ -458,7 +458,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 			break;
 
 		rcu_read_lock();
-		page = radix_tree_lookup(&mapping->page_tree, pg_index);
+		page = radix_tree_lookup(&mapping->i_pages, pg_index);
 		rcu_read_unlock();
 		if (page && !radix_tree_exceptional_entry(page)) {
 			misses++;

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
@@ -3963,11 +3963,11 @@ static int extent_write_cache_pages(struct address_space *mapping,
 
 			done_index = page->index;
 			/*
-			 * At this point we hold neither mapping->tree_lock nor
-			 * lock on the page itself: the page may be truncated or
-			 * invalidated (changing page->mapping to NULL), or even
-			 * swizzled back from swapper_space to tmpfs file
-			 * mapping
+			 * At this point we hold neither the i_pages lock nor
+			 * the page lock: the page may be truncated or
+			 * invalidated (changing page->mapping to NULL),
+			 * or even swizzled back from swapper_space to
+			 * tmpfs file mapping
 			 */
 			if (!trylock_page(page)) {
 				flush_write_bio(epd);
@@ -5174,13 +5174,13 @@ void clear_extent_buffer_dirty(struct extent_buffer *eb)
 		WARN_ON(!PagePrivate(page));
 
 		clear_page_dirty_for_io(page);
-		spin_lock_irq(&page->mapping->tree_lock);
+		xa_lock_irq(&page->mapping->i_pages);
 		if (!PageDirty(page)) {
-			radix_tree_tag_clear(&page->mapping->page_tree,
+			radix_tree_tag_clear(&page->mapping->i_pages,
 						page_index(page),
 						PAGECACHE_TAG_DIRTY);
 		}
-		spin_unlock_irq(&page->mapping->tree_lock);
+		xa_unlock_irq(&page->mapping->i_pages);
 		ClearPageError(page);
 		unlock_page(page);
 	}

diff --git a/fs/buffer.c b/fs/buffer.c
@@ -185,10 +185,9 @@ EXPORT_SYMBOL(end_buffer_write_sync);
  * we get exclusion from try_to_free_buffers with the blockdev mapping's
  * private_lock.
  *
- * Hack idea: for the blockdev mapping, i_bufferlist_lock contention
+ * Hack idea: for the blockdev mapping, private_lock contention
  * may be quite high.  This code could TryLock the page, and if that
- * succeeds, there is no need to take private_lock. (But if
- * private_lock is contended then so is mapping->tree_lock).
+ * succeeds, there is no need to take private_lock.
  */
 static struct buffer_head *
 __find_get_block_slow(struct block_device *bdev, sector_t block)
@@ -599,14 +598,14 @@ void __set_page_dirty(struct page *page, struct address_space *mapping,
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&mapping->tree_lock, flags);
+	xa_lock_irqsave(&mapping->i_pages, flags);
 	if (page->mapping) {	/* Race with truncate? */
 		WARN_ON_ONCE(warn && !PageUptodate(page));
 		account_page_dirtied(page, mapping);
-		radix_tree_tag_set(&mapping->page_tree,
+		radix_tree_tag_set(&mapping->i_pages,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 	}
-	spin_unlock_irqrestore(&mapping->tree_lock, flags);
+	xa_unlock_irqrestore(&mapping->i_pages, flags);
 }
 EXPORT_SYMBOL_GPL(__set_page_dirty);
 
@@ -1096,7 +1095,7 @@ __getblk_slow(struct block_device *bdev, sector_t block,
  * inode list.
  *
  * mark_buffer_dirty() is atomic.  It takes bh->b_page->mapping->private_lock,
- * mapping->tree_lock and mapping->host->i_lock.
+ * i_pages lock and mapping->host->i_lock.
  */
 void mark_buffer_dirty(struct buffer_head *bh)
 {

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
@@ -1987,11 +1987,10 @@ wdata_prepare_pages(struct cifs_writedata *wdata, unsigned int found_pages,
 	for (i = 0; i < found_pages; i++) {
 		page = wdata->pages[i];
 		/*
-		 * At this point we hold neither mapping->tree_lock nor
-		 * lock on the page itself: the page may be truncated or
-		 * invalidated (changing page->mapping to NULL), or even
-		 * swizzled back from swapper_space to tmpfs file
-		 * mapping
+		 * At this point we hold neither the i_pages lock nor the
+		 * page lock: the page may be truncated or invalidated
+		 * (changing page->mapping to NULL), or even swizzled
+		 * back from swapper_space to tmpfs file mapping
 		 */
 
 		if (nr_pages == 0)