lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Date:   Wed, 12 Aug 2020 14:17:11 +0900
From:   Daeho Jeong <daeho43@...il.com>
To:     linux-kernel@...r.kernel.org,
        linux-f2fs-devel@...ts.sourceforge.net, kernel-team@...roid.com
Cc:     Daeho Jeong <daehojeong@...gle.com>
Subject: [PATCH v3] f2fs: change virtual mapping way for compression pages

From: Daeho Jeong <daehojeong@...gle.com>

By profiling f2fs compression works, I've found vmap() callings have
unexpected hikes in the execution time in our test environment and
those are bottlenecks of f2fs decompression path. Changing these with
vm_map_ram(), we can enhance f2fs decompression speed pretty much.

[Verification]
Android Pixel 3(ARM64, 6GB RAM, 128GB UFS)
Turned on only 0-3 little cores(at 1.785GHz)

dd if=/dev/zero of=dummy bs=1m count=1000
echo 3 > /proc/sys/vm/drop_caches
dd if=dummy of=/dev/zero bs=512k

- w/o compression -
1048576000 bytes (0.9 G) copied, 2.082554 s, 480 M/s
1048576000 bytes (0.9 G) copied, 2.081634 s, 480 M/s
1048576000 bytes (0.9 G) copied, 2.090861 s, 478 M/s

- before patch -
1048576000 bytes (0.9 G) copied, 7.407527 s, 135 M/s
1048576000 bytes (0.9 G) copied, 7.283734 s, 137 M/s
1048576000 bytes (0.9 G) copied, 7.291508 s, 137 M/s

- after patch -
1048576000 bytes (0.9 G) copied, 1.998959 s, 500 M/s
1048576000 bytes (0.9 G) copied, 1.987554 s, 503 M/s
1048576000 bytes (0.9 G) copied, 1.986380 s, 503 M/s

Signed-off-by: Daeho Jeong <daehojeong@...gle.com>
---
Changes in v2:
 - Added test environment description.
Changes in v3:
 - Re-tested using only ARM little cores and maximzing cpu clock.
---
 fs/f2fs/compress.c | 42 ++++++++++++++++++++++++++++++++----------
 1 file changed, 32 insertions(+), 10 deletions(-)

diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 6e7db450006c..46b7e359f313 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -554,6 +554,8 @@ static void f2fs_compress_free_page(struct page *page)
 	mempool_free(page, compress_page_pool);
 }
 
+#define MAX_VMAP_RETRIES	3
+
 static int f2fs_compress_pages(struct compress_ctx *cc)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode);
@@ -590,13 +592,23 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 		}
 	}
 
-	cc->rbuf = vmap(cc->rpages, cc->cluster_size, VM_MAP, PAGE_KERNEL_RO);
+	for (i = 0; i < MAX_VMAP_RETRIES; i++) {
+		cc->rbuf = vm_map_ram(cc->rpages, cc->cluster_size, -1);
+		if (cc->rbuf)
+			break;
+		vm_unmap_aliases();
+	}
 	if (!cc->rbuf) {
 		ret = -ENOMEM;
 		goto out_free_cpages;
 	}
 
-	cc->cbuf = vmap(cc->cpages, cc->nr_cpages, VM_MAP, PAGE_KERNEL);
+	for (i = 0; i < MAX_VMAP_RETRIES; i++) {
+		cc->cbuf = vm_map_ram(cc->cpages, cc->nr_cpages, -1);
+		if (cc->cbuf)
+			break;
+		vm_unmap_aliases();
+	}
 	if (!cc->cbuf) {
 		ret = -ENOMEM;
 		goto out_vunmap_rbuf;
@@ -624,8 +636,8 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 	memset(&cc->cbuf->cdata[cc->clen], 0,
 	       (nr_cpages * PAGE_SIZE) - (cc->clen + COMPRESS_HEADER_SIZE));
 
-	vunmap(cc->cbuf);
-	vunmap(cc->rbuf);
+	vm_unmap_ram(cc->cbuf, cc->nr_cpages);
+	vm_unmap_ram(cc->rbuf, cc->cluster_size);
 
 	for (i = nr_cpages; i < cc->nr_cpages; i++) {
 		f2fs_compress_free_page(cc->cpages[i]);
@@ -642,9 +654,9 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 	return 0;
 
 out_vunmap_cbuf:
-	vunmap(cc->cbuf);
+	vm_unmap_ram(cc->cbuf, cc->nr_cpages);
 out_vunmap_rbuf:
-	vunmap(cc->rbuf);
+	vm_unmap_ram(cc->rbuf, cc->cluster_size);
 out_free_cpages:
 	for (i = 0; i < cc->nr_cpages; i++) {
 		if (cc->cpages[i])
@@ -715,13 +727,23 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity)
 			goto out_free_dic;
 	}
 
-	dic->rbuf = vmap(dic->tpages, dic->cluster_size, VM_MAP, PAGE_KERNEL);
+	for (i = 0; i < MAX_VMAP_RETRIES; i++) {
+		dic->rbuf = vm_map_ram(dic->tpages, dic->cluster_size, -1);
+		if (dic->rbuf)
+			break;
+		vm_unmap_aliases();
+	}
 	if (!dic->rbuf) {
 		ret = -ENOMEM;
 		goto destroy_decompress_ctx;
 	}
 
-	dic->cbuf = vmap(dic->cpages, dic->nr_cpages, VM_MAP, PAGE_KERNEL_RO);
+	for (i = 0; i < MAX_VMAP_RETRIES; i++) {
+		dic->cbuf = vm_map_ram(dic->cpages, dic->nr_cpages, -1);
+		if (dic->cbuf)
+			break;
+		vm_unmap_aliases();
+	}
 	if (!dic->cbuf) {
 		ret = -ENOMEM;
 		goto out_vunmap_rbuf;
@@ -738,9 +760,9 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity)
 	ret = cops->decompress_pages(dic);
 
 out_vunmap_cbuf:
-	vunmap(dic->cbuf);
+	vm_unmap_ram(dic->cbuf, dic->nr_cpages);
 out_vunmap_rbuf:
-	vunmap(dic->rbuf);
+	vm_unmap_ram(dic->rbuf, dic->cluster_size);
 destroy_decompress_ctx:
 	if (cops->destroy_decompress_ctx)
 		cops->destroy_decompress_ctx(dic);
-- 
2.28.0.236.gb10cc79966-goog

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ