Skip to contentSkip to conversation

btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine

PATCH New Qu Wenruo 1 participant 1 message Jan 4, 2022 Btrfs file system

lore
Share & tools
lore

Qu Wenruo

author
#0 lore raw

PATCH 1/1 btrfs: make nodesize >= PAGE_SIZE case to reuse the non-subpage routine

The reason why we only support 64K page size for subpage is, for 64K page size we can ensure no matter what the nodesize is, we can fit it into one page.

When other page size comes, especially like 16K, the limitation is a bit blockage.

To remove such limitation, we allow nodesize >= PAGE_SIZE case to go the non-subpage routine.
By this, we can allow 4K sectorsize on 16K page size.

Although this introduces another smaller limitation, the metadata can not cross page boundary, which is already met by most recent mkfs.

Another small improvement is, we can avoid the overhead for metadata if nodesize >= PAGE_SIZE.
For 4K sector size and 64K page size/node size, or 4K sector size and 16K page size/node size, we don't need to allocate extra memory for the metadata pages.

Please note that, this patch will not yet enable other page size support yet.

---
Reason for RFC:

I have tried my best to create btrfs_is_subpage() wrapper to handle both data and metadata pages.

But the truth is, there is always some odd balls for that function.

We have no way to determine if a unmapped page is data or metadata. As compression/DIO have unammped data page, while metadata can have cloned extent mapped.

Thus we have some open nodesize >= PAGE_SIZE check in metadata paths, to handle unmapped extent buffer.

I'm still not super happy with the solution, thus any idea to remove the several open nodesize check would be welcomed.

---
 fs/btrfs/disk-io.c   |  4 +--
 fs/btrfs/extent_io.c | 80 ++++++++++++++++++++++++++------------------
 fs/btrfs/inode.c     |  2 +-
 fs/btrfs/subpage.c   | 31 ++++++++---------
 fs/btrfs/subpage.h   | 25 ++++++++++++++
 5 files changed, 92 insertions(+), 50 deletions(-)
fs/btrfs/disk-io.c +2 -2
index 87a5addbedf6..884e0b543136 100644
@@ -505,7 +505,7 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec
 	u64 found_start;
 	struct extent_buffer *eb;
 
-	if (fs_info->sectorsize < PAGE_SIZE)
+	if (fs_info->nodesize < PAGE_SIZE)
 		return csum_dirty_subpage_buffers(fs_info, bvec);
 
 	eb = (struct extent_buffer *)page->private;
@@ -690,7 +690,7 @@ int btrfs_validate_metadata_buffer(struct btrfs_bio *bbio,
 
 	ASSERT(page->private);
 
-	if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE)
+	if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE)
 		return validate_subpage_buffer(page, start, end, mirror);
 
 	eb = (struct extent_buffer *)page->private;
fs/btrfs/extent_io.c +48 -32

225 lines not on this page · raw message

fs/btrfs/inode.c +1 -1
index 3b2403b6127f..89e888409609 100644
@@ -8129,7 +8129,7 @@ static void wait_subpage_spinlock(struct page *page)
 	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
 	struct btrfs_subpage *subpage;
 
-	if (fs_info->sectorsize == PAGE_SIZE)
+	if (!btrfs_is_subpage(fs_info, page))
 		return;
 
 	ASSERT(PagePrivate(page) && page->private);
fs/btrfs/subpage.c +16 -15
index 29bd8c7a7706..17c0bda3ab12 100644
@@ -107,7 +107,7 @@ int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info,
 		ASSERT(PageLocked(page));
 
 	/* Either not subpage, or the page already has private attached */
-	if (fs_info->sectorsize == PAGE_SIZE || PagePrivate(page))
+	if (!btrfs_is_subpage(fs_info, page) || PagePrivate(page))
 		return 0;
 
 	subpage = btrfs_alloc_subpage(fs_info, type);
@@ -124,7 +124,7 @@ void btrfs_detach_subpage(const struct btrfs_fs_info *fs_info,
 	struct btrfs_subpage *subpage;
 
 	/* Either not subpage, or already detached */
-	if (fs_info->sectorsize == PAGE_SIZE || !PagePrivate(page))
+	if (!btrfs_is_subpage(fs_info, page) || !PagePrivate(page))
 		return;
 
 	subpage = (struct btrfs_subpage *)detach_page_private(page);
@@ -175,7 +175,7 @@ void btrfs_page_inc_eb_refs(const struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_subpage *subpage;
 
-	if (fs_info->sectorsize == PAGE_SIZE)
+	if (!btrfs_is_subpage(fs_info, page))
 		return;
 
 	ASSERT(PagePrivate(page) && page->mapping);
@@ -190,7 +190,7 @@ void btrfs_page_dec_eb_refs(const struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_subpage *subpage;
 
-	if (fs_info->sectorsize == PAGE_SIZE)
+	if (!btrfs_is_subpage(fs_info, page))
 		return;
 
 	ASSERT(PagePrivate(page) && page->mapping);
@@ -208,6 +208,7 @@ static void btrfs_subpage_assert(const struct btrfs_fs_info *fs_info,
 	ASSERT(PagePrivate(page) && page->private);
 	ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
 	       IS_ALIGNED(len, fs_info->sectorsize));
+	ASSERT(btrfs_is_subpage(fs_info, page));
 	/*
 	 * The range check only works for mapped page, we can still have
 	 * unmapped page like dummy extent buffer pages.
@@ -319,7 +320,7 @@ bool btrfs_subpage_end_and_test_writer(const struct btrfs_fs_info *fs_info,
 int btrfs_page_start_writer_lock(const struct btrfs_fs_info *fs_info,
 		struct page *page, u64 start, u32 len)
 {
-	if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) {
+	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) {
 		lock_page(page);
 		return 0;
 	}
@@ -336,7 +337,7 @@ int btrfs_page_start_writer_lock(const struct btrfs_fs_info *fs_info,
 void btrfs_page_end_writer_lock(const struct btrfs_fs_info *fs_info,
 		struct page *page, u64 start, u32 len)
 {
-	if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE)
+	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page))
 		return unlock_page(page);
 	btrfs_subpage_clamp_range(page, &start, &len);
 	if (btrfs_subpage_end_and_test_writer(fs_info, page, start, len))
@@ -620,7 +621,7 @@ IMPLEMENT_BTRFS_SUBPAGE_TEST_OP(checked);
 void btrfs_page_set_##name(const struct btrfs_fs_info *fs_info,		\
 		struct page *page, u64 start, u32 len)			\
 {									\
-	if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) {	\
+	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) {	\
 		set_page_func(page);					\
 		return;							\
 	}								\
@@ -629,7 +630,7 @@ void btrfs_page_set_##name(const struct btrfs_fs_info *fs_info,		\
 void btrfs_page_clear_##name(const struct btrfs_fs_info *fs_info,	\
 		struct page *page, u64 start, u32 len)			\
 {									\
-	if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) {	\
+	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) {	\
 		clear_page_func(page);					\
 		return;							\
 	}								\
@@ -638,14 +639,14 @@ void btrfs_page_clear_##name(const struct btrfs_fs_info *fs_info,	\
 bool btrfs_page_test_##name(const struct btrfs_fs_info *fs_info,	\
 		struct page *page, u64 start, u32 len)			\
 {									\
-	if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE)	\
+	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page))	\
 		return test_page_func(page);				\
 	return btrfs_subpage_test_##name(fs_info, page, start, len);	\
 }									\
 void btrfs_page_clamp_set_##name(const struct btrfs_fs_info *fs_info,	\
 		struct page *page, u64 start, u32 len)			\
 {									\
-	if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) {	\
+	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) {	\
 		set_page_func(page);					\
 		return;							\
 	}								\
@@ -655,7 +656,7 @@ void btrfs_page_clamp_set_##name(const struct btrfs_fs_info *fs_info,	\
 void btrfs_page_clamp_clear_##name(const struct btrfs_fs_info *fs_info, \
 		struct page *page, u64 start, u32 len)			\
 {									\
-	if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE) {	\
+	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page)) {	\
 		clear_page_func(page);					\
 		return;							\
 	}								\
@@ -665,7 +666,7 @@ void btrfs_page_clamp_clear_##name(const struct btrfs_fs_info *fs_info, \
 bool btrfs_page_clamp_test_##name(const struct btrfs_fs_info *fs_info,	\
 		struct page *page, u64 start, u32 len)			\
 {									\
-	if (unlikely(!fs_info) || fs_info->sectorsize == PAGE_SIZE)	\
+	if (unlikely(!fs_info) || !btrfs_is_subpage(fs_info, page))	\
 		return test_page_func(page);				\
 	btrfs_subpage_clamp_range(page, &start, &len);			\
 	return btrfs_subpage_test_##name(fs_info, page, start, len);	\
@@ -694,7 +695,7 @@ void btrfs_page_assert_not_dirty(const struct btrfs_fs_info *fs_info,
 		return;
 
 	ASSERT(!PageDirty(page));
-	if (fs_info->sectorsize == PAGE_SIZE)
+	if (!btrfs_is_subpage(fs_info, page))
 		return;
 
 	ASSERT(PagePrivate(page) && page->private);
@@ -722,8 +723,8 @@ void btrfs_page_unlock_writer(struct btrfs_fs_info *fs_info, struct page *page,
 	struct btrfs_subpage *subpage;
 
 	ASSERT(PageLocked(page));
-	/* For regular page size case, we just unlock the page */
-	if (fs_info->sectorsize == PAGE_SIZE)
+	/* For non-subpage case, we just unlock the page */
+	if (!btrfs_is_subpage(fs_info, page))
 		return unlock_page(page);
 
 	ASSERT(PagePrivate(page) && page->private);
fs/btrfs/subpage.h +25 -0
index 7accb5c40d33..a87e53e8c24c 100644
@@ -4,6 +4,7 @@
 #define BTRFS_SUBPAGE_H
 
 #include <linux/spinlock.h>
+#include "btrfs_inode.h"
 
 /*
  * Extra info for subpapge bitmap.
@@ -74,6 +75,30 @@ enum btrfs_subpage_type {
 	BTRFS_SUBPAGE_DATA,
 };
 
+static inline bool btrfs_is_subpage(const struct btrfs_fs_info *fs_info,
+				    struct page *page)
+{
+	if (fs_info->sectorsize >= PAGE_SIZE)
+		return false;
+
+	/*
+	 * Only data pages (either through DIO or compression) can have no
+	 * mapping. And if page->mapping->host is data inode, it's subpage.
+	 * As we have ruled our sectorsize >= PAGE_SIZE case already.
+	 */
+	if (!page->mapping || !page->mapping->host ||
+	    is_data_inode(page->mapping->host))
+		return true;
+
+	/*
+	 * Now the only remaining case is metadata, which we only go subpage
+	 * routine if nodesize < PAGE_SIZE.
+	 */
+	if (fs_info->nodesize < PAGE_SIZE)
+		return true;
+	return false;
+}
+
 void btrfs_init_subpage_info(struct btrfs_subpage_info *subpage_info, u32 sectorsize);
 int btrfs_attach_subpage(const struct btrfs_fs_info *fs_info,
 			 struct page *page, enum btrfs_subpage_type type);
Signature · 1 line
2.34.1