linux-btrfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Qu Wenruo <wqu@suse.com>
To: linux-btrfs@vger.kernel.org
Subject: [PATCH 27/32] btrfs: scrub: use flexible array for scrub_page::csums
Date: Tue,  3 Nov 2020 21:31:03 +0800	[thread overview]
Message-ID: <20201103133108.148112-28-wqu@suse.com> (raw)
In-Reply-To: <20201103133108.148112-1-wqu@suse.com>

There are several factors affecting how many checksum bytes are needed
for one scrub_page:

- Sector size and page size
  For subpage case, one page can contain several sectors, thus the csum
  size will differ.

- Checksum size
  Since btrfs supports different csum size now, which can vary from 4
  bytes for CRC32 to 32 bytes for SHA256.

So instead of using fixed BTRFS_CSUM_SIZE, now use flexible array for
scrub_page::csums, and determine the size at scrub_page allocation time.

This does not only provide the basis for later subpage scrub support,
but also reduce the memory usage for default btrfs on x86_64.
As the default CRC32 only uses 4 bytes, thus we can save 28 bytes for
each scrub page.

Signed-off-by: Qu Wenruo <wqu@suse.com>
---
 fs/btrfs/scrub.c | 41 ++++++++++++++++++++++++++++++-----------
 1 file changed, 30 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 7e6ed0b79006..cabc030d4bf9 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -76,9 +76,14 @@ struct scrub_page {
 		unsigned int	have_csum:1;
 		unsigned int	io_error:1;
 	};
-	u8			csum[BTRFS_CSUM_SIZE];
-
 	struct scrub_recover	*recover;
+
+	/*
+	 * The csums size for the page is deteremined by page size,
+	 * sector size and csum size.
+	 * Thus the length has to be determined at runtime.
+	 */
+	u8			csums[];
 };
 
 struct scrub_bio {
@@ -206,6 +211,19 @@ struct full_stripe_lock {
 	struct mutex mutex;
 };
 
+static struct scrub_page *alloc_scrub_page(struct scrub_ctx *sctx, gfp_t mask)
+{
+	u32 sectorsize = sctx->fs_info->sectorsize;
+	size_t size;
+
+	/* No support for multi-page sector size yet */
+	ASSERT(PAGE_SIZE >= sectorsize && IS_ALIGNED(PAGE_SIZE, sectorsize));
+
+	size = sizeof(struct scrub_page);
+	size += (PAGE_SIZE / sectorsize) * sctx->fs_info->csum_size;
+	return kzalloc(size, mask);
+}
+
 static void scrub_pending_bio_inc(struct scrub_ctx *sctx);
 static void scrub_pending_bio_dec(struct scrub_ctx *sctx);
 static int scrub_handle_errored_block(struct scrub_block *sblock_to_check);
@@ -1328,7 +1346,7 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 			sblock = sblocks_for_recheck + mirror_index;
 			sblock->sctx = sctx;
 
-			spage = kzalloc(sizeof(*spage), GFP_NOFS);
+			spage = alloc_scrub_page(sctx, GFP_NOFS);
 			if (!spage) {
 leave_nomem:
 				spin_lock(&sctx->stat_lock);
@@ -1345,8 +1363,8 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 			spage->logical = logical;
 			spage->have_csum = have_csum;
 			if (have_csum)
-				memcpy(spage->csum,
-				       original_sblock->pagev[0]->csum,
+				memcpy(spage->csums,
+				       original_sblock->pagev[0]->csums,
 				       sctx->fs_info->csum_size);
 
 			scrub_stripe_index_and_offset(logical,
@@ -1798,7 +1816,7 @@ static int scrub_checksum_data(struct scrub_block *sblock)
 	crypto_shash_init(shash);
 	crypto_shash_digest(shash, kaddr, PAGE_SIZE, csum);
 
-	if (memcmp(csum, spage->csum, sctx->fs_info->csum_size))
+	if (memcmp(csum, spage->csums, sctx->fs_info->csum_size))
 		sblock->checksum_error = 1;
 
 	return sblock->checksum_error;
@@ -2178,7 +2196,7 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
 		struct scrub_page *spage;
 		u64 l = min_t(u64, len, PAGE_SIZE);
 
-		spage = kzalloc(sizeof(*spage), GFP_KERNEL);
+		spage = alloc_scrub_page(sctx, GFP_KERNEL);
 		if (!spage) {
 leave_nomem:
 			spin_lock(&sctx->stat_lock);
@@ -2200,7 +2218,7 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
 		spage->mirror_num = mirror_num;
 		if (csum) {
 			spage->have_csum = 1;
-			memcpy(spage->csum, csum, sctx->fs_info->csum_size);
+			memcpy(spage->csums, csum, sctx->fs_info->csum_size);
 		} else {
 			spage->have_csum = 0;
 		}
@@ -2486,7 +2504,9 @@ static int scrub_pages_for_parity(struct scrub_parity *sparity,
 		struct scrub_page *spage;
 		u64 l = min_t(u64, len, PAGE_SIZE);
 
-		spage = kzalloc(sizeof(*spage), GFP_KERNEL);
+		BUG_ON(index >= SCRUB_MAX_PAGES_PER_BLOCK);
+
+		spage = alloc_scrub_page(sctx, GFP_KERNEL);
 		if (!spage) {
 leave_nomem:
 			spin_lock(&sctx->stat_lock);
@@ -2495,7 +2515,6 @@ static int scrub_pages_for_parity(struct scrub_parity *sparity,
 			scrub_block_put(sblock);
 			return -ENOMEM;
 		}
-		BUG_ON(index >= SCRUB_MAX_PAGES_PER_BLOCK);
 		/* For scrub block */
 		scrub_page_get(spage);
 		sblock->pagev[index] = spage;
@@ -2511,7 +2530,7 @@ static int scrub_pages_for_parity(struct scrub_parity *sparity,
 		spage->mirror_num = mirror_num;
 		if (csum) {
 			spage->have_csum = 1;
-			memcpy(spage->csum, csum, sctx->fs_info->csum_size);
+			memcpy(spage->csums, csum, sctx->fs_info->csum_size);
 		} else {
 			spage->have_csum = 0;
 		}
-- 
2.29.2


  parent reply	other threads:[~2020-11-03 13:32 UTC|newest]

Thread overview: 98+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-03 13:30 [PATCH 00/32] btrfs: preparation patches for subpage support Qu Wenruo
2020-11-03 13:30 ` [PATCH 01/32] btrfs: extent_io: remove the extent_start/extent_len for end_bio_extent_readpage() Qu Wenruo
2020-11-05  9:46   ` Nikolay Borisov
2020-11-05 10:15     ` Qu Wenruo
2020-11-05 10:32       ` Nikolay Borisov
2020-11-06  2:01         ` Qu Wenruo
2020-11-06  7:19           ` Qu Wenruo
2020-11-05 19:40   ` Josef Bacik
2020-11-06  1:52     ` Qu Wenruo
2020-11-03 13:30 ` [PATCH 02/32] btrfs: extent_io: integrate page status update into endio_readpage_release_extent() Qu Wenruo
2020-11-05 10:26   ` Nikolay Borisov
2020-11-05 11:15     ` Qu Wenruo
2020-11-05 10:35   ` Nikolay Borisov
2020-11-05 11:25     ` Qu Wenruo
2020-11-05 19:34   ` Josef Bacik
2020-11-03 13:30 ` [PATCH 03/32] btrfs: extent_io: add lockdep_assert_held() for attach_extent_buffer_page() Qu Wenruo
2020-11-03 13:30 ` [PATCH 04/32] btrfs: extent_io: extract the btree page submission code into its own helper function Qu Wenruo
2020-11-05 10:47   ` Nikolay Borisov
2020-11-06 18:11     ` David Sterba
2020-11-03 13:30 ` [PATCH 05/32] btrfs: extent-io-tests: remove invalid tests Qu Wenruo
2020-11-03 13:30 ` [PATCH 06/32] btrfs: extent_io: calculate inline extent buffer page size based on page size Qu Wenruo
2020-11-05 12:54   ` Nikolay Borisov
2020-11-03 13:30 ` [PATCH 07/32] btrfs: extent_io: make btrfs_fs_info::buffer_radix to take sector size devided values Qu Wenruo
2020-11-03 13:30 ` [PATCH 08/32] btrfs: extent_io: sink less common parameters for __set_extent_bit() Qu Wenruo
2020-11-05 13:35   ` Nikolay Borisov
2020-11-05 13:55     ` Qu Wenruo
2020-11-03 13:30 ` [PATCH 09/32] btrfs: extent_io: sink less common parameters for __clear_extent_bit() Qu Wenruo
2020-11-03 13:30 ` [PATCH 10/32] btrfs: disk_io: grab fs_info from extent_buffer::fs_info directly for btrfs_mark_buffer_dirty() Qu Wenruo
2020-11-05 13:45   ` Nikolay Borisov
2020-11-05 13:49   ` Nikolay Borisov
2020-11-03 13:30 ` [PATCH 11/32] btrfs: disk-io: make csum_tree_block() handle sectorsize smaller than page size Qu Wenruo
2020-11-06 18:58   ` David Sterba
2020-11-07  0:04     ` Qu Wenruo
2020-11-10 14:33       ` David Sterba
2020-11-11  0:08         ` Qu Wenruo
2020-11-03 13:30 ` [PATCH 12/32] btrfs: disk-io: extract the extent buffer verification from btrfs_validate_metadata_buffer() Qu Wenruo
2020-11-05 13:57   ` Nikolay Borisov
2020-11-06 19:03     ` David Sterba
2020-11-09  6:44       ` Qu Wenruo
2020-11-10 14:37         ` David Sterba
2020-11-03 13:30 ` [PATCH 13/32] btrfs: disk-io: accept bvec directly for csum_dirty_buffer() Qu Wenruo
2020-11-05 14:13   ` Nikolay Borisov
2020-11-03 13:30 ` [PATCH 14/32] btrfs: inode: make btrfs_readpage_end_io_hook() follow sector size Qu Wenruo
2020-11-05 14:28   ` Nikolay Borisov
2020-11-06 19:16     ` David Sterba
2020-11-06 19:20       ` David Sterba
2020-11-06 19:28   ` David Sterba
2020-11-03 13:30 ` [PATCH 15/32] btrfs: introduce a helper to determine if the sectorsize is smaller than PAGE_SIZE Qu Wenruo
2020-11-05 15:01   ` Nikolay Borisov
2020-11-05 22:52     ` Qu Wenruo
2020-11-06 17:28       ` David Sterba
2020-11-07  0:00         ` Qu Wenruo
2020-11-10 14:53           ` David Sterba
2020-11-11  1:34             ` Qu Wenruo
2020-11-11  2:21               ` Qu Wenruo
2020-11-03 13:30 ` [PATCH 16/32] btrfs: extent_io: allow find_first_extent_bit() to find a range with exact bits match Qu Wenruo
2020-11-05 15:03   ` Nikolay Borisov
2020-11-05 22:55     ` Qu Wenruo
2020-11-03 13:30 ` [PATCH 17/32] btrfs: extent_io: don't allow tree block to cross page boundary for subpage support Qu Wenruo
2020-11-06 11:54   ` Nikolay Borisov
2020-11-06 12:03     ` Nikolay Borisov
2020-11-06 13:25     ` Qu Wenruo
2020-11-06 14:04       ` Nikolay Borisov
2020-11-06 23:56         ` Qu Wenruo
2020-11-03 13:30 ` [PATCH 18/32] btrfs: extent_io: update num_extent_pages() to support subpage sized extent buffer Qu Wenruo
2020-11-06 12:09   ` Nikolay Borisov
2020-11-03 13:30 ` [PATCH 19/32] btrfs: handle sectorsize < PAGE_SIZE case for extent buffer accessors Qu Wenruo
2020-11-06 12:51   ` Nikolay Borisov
2020-11-09  5:49     ` Qu Wenruo
2020-11-03 13:30 ` [PATCH 20/32] btrfs: disk-io: only clear EXTENT_LOCK bit for extent_invalidatepage() Qu Wenruo
2020-11-06 13:17   ` Nikolay Borisov
2020-11-03 13:30 ` [PATCH 21/32] btrfs: extent-io: make type of extent_state::state to be at least 32 bits Qu Wenruo
2020-11-06 13:38   ` Nikolay Borisov
2020-11-03 13:30 ` [PATCH 22/32] btrfs: file-item: use nodesize to determine whether we need readahead for btrfs_lookup_bio_sums() Qu Wenruo
2020-11-06 13:55   ` Nikolay Borisov
2020-11-03 13:30 ` [PATCH 23/32] btrfs: file-item: remove the btrfs_find_ordered_sum() call in btrfs_lookup_bio_sums() Qu Wenruo
2020-11-06 14:28   ` Nikolay Borisov
2020-11-03 13:31 ` [PATCH 24/32] btrfs: file-item: refactor btrfs_lookup_bio_sums() to handle out-of-order bvecs Qu Wenruo
2020-11-06 15:22   ` Nikolay Borisov
2020-11-03 13:31 ` [PATCH 25/32] btrfs: scrub: distinguish scrub_page from regular page Qu Wenruo
2020-11-03 13:31 ` [PATCH 26/32] btrfs: scrub: remove the @force parameter of scrub_pages() Qu Wenruo
2020-11-03 13:31 ` Qu Wenruo [this message]
2020-11-09 17:44   ` [PATCH 27/32] btrfs: scrub: use flexible array for scrub_page::csums David Sterba
2020-11-10  0:53     ` Qu Wenruo
2020-11-10 14:22       ` David Sterba
2020-11-03 13:31 ` [PATCH 28/32] btrfs: scrub: refactor scrub_find_csum() Qu Wenruo
2020-11-03 13:31 ` [PATCH 29/32] btrfs: scrub: introduce scrub_page::page_len for subpage support Qu Wenruo
2020-11-09 18:17   ` David Sterba
2020-11-10  0:54     ` Qu Wenruo
2020-11-09 18:25   ` David Sterba
2020-11-10  0:56     ` Qu Wenruo
2020-11-10 14:27       ` David Sterba
2020-11-03 13:31 ` [PATCH 30/32] btrfs: scrub: always allocate one full page for one sector for RAID56 Qu Wenruo
2020-11-03 13:31 ` [PATCH 31/32] btrfs: scrub: support subpage tree block scrub Qu Wenruo
2020-11-09 18:31   ` David Sterba
2020-11-03 13:31 ` [PATCH 32/32] btrfs: scrub: support subpage data scrub Qu Wenruo
2020-11-05 19:28 ` [PATCH 00/32] btrfs: preparation patches for subpage support Josef Bacik
2020-11-06  0:02   ` Qu Wenruo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20201103133108.148112-28-wqu@suse.com \
    --to=wqu@suse.com \
    --cc=linux-btrfs@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).