linux-erofs.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Yue Hu <zbestahu@gmail.com>
To: xiang@kernel.org, chao@kernel.org
Cc: Yue Hu <huyue2@coolpad.com>,
	linux-erofs@lists.ozlabs.org, linux-kernel@vger.kernel.org,
	zhangwen@coolpad.com
Subject: [PATCH v6 1/2] erofs: support interlaced uncompressed data for compressed files
Date: Fri, 23 Sep 2022 10:11:21 +0800	[thread overview]
Message-ID: <8369112678604fdf4ef796626d59b1fdd0745a53.1663898962.git.huyue2@coolpad.com> (raw)
In-Reply-To: <cover.1663898962.git.huyue2@coolpad.com>

From: Yue Hu <huyue2@coolpad.com>

Currently, uncompressed data is all handled in the shifted way, which
means we have to shift the whole on-disk plain pcluster to get the
logical data.   However, since we are also using in-place I/O for
uncompressed data, data copy will be reduced a lot if pcluster is
recorded in the interlaced way as illustrated below:
 _______________________________________________________________
|               |    |               |_ tail part |_ head part _|
|<-   blk0    ->| .. |<-   blkn-2  ->|<-         blkn-1       ->|

The logical data then becomes:
 ________________________________________________________
|_ head part _|_  blk0  _| .. |_  blkn-2  _|_ tail part _|

In addition, non-4k plain pclusters are also survived by the
interlaced way, which can be used for non-4k lclusters as well.

However, it's almost impossible to de-duplicate uncompressed data
in the interlaced way, therefore shifted uncompressed data is still
useful.

Signed-off-by: Yue Hu <huyue2@coolpad.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/decompressor.c | 47 ++++++++++++++++++++++++-----------------
 fs/erofs/erofs_fs.h     |  2 ++
 fs/erofs/internal.h     |  1 +
 fs/erofs/zmap.c         | 14 ++++++++----
 4 files changed, 41 insertions(+), 23 deletions(-)

diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 2d55569f96ac..51b7ac7166d9 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -317,52 +317,61 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq,
 	return ret;
 }
 
-static int z_erofs_shifted_transform(struct z_erofs_decompress_req *rq,
-				     struct page **pagepool)
+static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq,
+				   struct page **pagepool)
 {
-	const unsigned int nrpages_out =
+	const unsigned int inpages = PAGE_ALIGN(rq->inputsize) >> PAGE_SHIFT;
+	const unsigned int outpages =
 		PAGE_ALIGN(rq->pageofs_out + rq->outputsize) >> PAGE_SHIFT;
 	const unsigned int righthalf = min_t(unsigned int, rq->outputsize,
 					     PAGE_SIZE - rq->pageofs_out);
 	const unsigned int lefthalf = rq->outputsize - righthalf;
+	const unsigned int interlaced_offset =
+		rq->alg == Z_EROFS_COMPRESSION_SHIFTED ? 0 : rq->pageofs_out;
 	unsigned char *src, *dst;
 
-	if (nrpages_out > 2) {
+	if (outpages > 2 && rq->alg == Z_EROFS_COMPRESSION_SHIFTED) {
 		DBG_BUGON(1);
-		return -EIO;
+		return -EFSCORRUPTED;
 	}
 
 	if (rq->out[0] == *rq->in) {
-		DBG_BUGON(nrpages_out != 1);
+		DBG_BUGON(rq->pageofs_out);
 		return 0;
 	}
 
-	src = kmap_atomic(*rq->in) + rq->pageofs_in;
+	src = kmap_local_page(rq->in[inpages - 1]) + rq->pageofs_in;
 	if (rq->out[0]) {
-		dst = kmap_atomic(rq->out[0]);
-		memcpy(dst + rq->pageofs_out, src, righthalf);
-		kunmap_atomic(dst);
+		dst = kmap_local_page(rq->out[0]);
+		memcpy(dst + rq->pageofs_out, src + interlaced_offset,
+		       righthalf);
+		kunmap_local(dst);
 	}
 
-	if (nrpages_out == 2) {
-		DBG_BUGON(!rq->out[1]);
-		if (rq->out[1] == *rq->in) {
+	if (outpages > inpages) {
+		DBG_BUGON(!rq->out[outpages - 1]);
+		if (rq->out[outpages - 1] != rq->in[inpages - 1]) {
+			dst = kmap_local_page(rq->out[outpages - 1]);
+			memcpy(dst, interlaced_offset ? src :
+					(src + righthalf), lefthalf);
+			kunmap_local(dst);
+		} else if (!interlaced_offset) {
 			memmove(src, src + righthalf, lefthalf);
-		} else {
-			dst = kmap_atomic(rq->out[1]);
-			memcpy(dst, src + righthalf, lefthalf);
-			kunmap_atomic(dst);
 		}
 	}
-	kunmap_atomic(src);
+	kunmap_local(src);
 	return 0;
 }
 
 static struct z_erofs_decompressor decompressors[] = {
 	[Z_EROFS_COMPRESSION_SHIFTED] = {
-		.decompress = z_erofs_shifted_transform,
+		.decompress = z_erofs_transform_plain,
 		.name = "shifted"
 	},
+	[Z_EROFS_COMPRESSION_INTERLACED] = {
+		.decompress = z_erofs_transform_plain,
+		.name = "interlaced"
+	},
 	[Z_EROFS_COMPRESSION_LZ4] = {
 		.decompress = z_erofs_lz4_decompress,
 		.name = "lz4"
diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index 2b48373f690b..5c1de6d7ad71 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -295,11 +295,13 @@ struct z_erofs_lzma_cfgs {
  * bit 1 : HEAD1 big pcluster (0 - off; 1 - on)
  * bit 2 : HEAD2 big pcluster (0 - off; 1 - on)
  * bit 3 : tailpacking inline pcluster (0 - off; 1 - on)
+ * bit 4 : interlaced plain pcluster (0 - off; 1 - on)
  */
 #define Z_EROFS_ADVISE_COMPACTED_2B		0x0001
 #define Z_EROFS_ADVISE_BIG_PCLUSTER_1		0x0002
 #define Z_EROFS_ADVISE_BIG_PCLUSTER_2		0x0004
 #define Z_EROFS_ADVISE_INLINE_PCLUSTER		0x0008
+#define Z_EROFS_ADVISE_INTERLACED_PCLUSTER	0x0010
 
 struct z_erofs_map_header {
 	__le16	h_reserved1;
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index cfee49d33b95..f3ed36445d73 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -436,6 +436,7 @@ struct erofs_map_blocks {
 
 enum {
 	Z_EROFS_COMPRESSION_SHIFTED = Z_EROFS_COMPRESSION_MAX,
+	Z_EROFS_COMPRESSION_INTERLACED,
 	Z_EROFS_COMPRESSION_RUNTIME_MAX
 };
 
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index d58549ca1df9..7196235a441c 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -679,12 +679,18 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 			goto out;
 	}
 
-	if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN)
-		map->m_algorithmformat = Z_EROFS_COMPRESSION_SHIFTED;
-	else if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2)
+	if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN) {
+		if (vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER)
+			map->m_algorithmformat =
+				Z_EROFS_COMPRESSION_INTERLACED;
+		else
+			map->m_algorithmformat =
+				Z_EROFS_COMPRESSION_SHIFTED;
+	} else if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) {
 		map->m_algorithmformat = vi->z_algorithmtype[1];
-	else
+	} else {
 		map->m_algorithmformat = vi->z_algorithmtype[0];
+	}
 
 	if ((flags & EROFS_GET_BLOCKS_FIEMAP) ||
 	    ((flags & EROFS_GET_BLOCKS_READMORE) &&
-- 
2.17.1


       reply	other threads:[~2022-09-23  2:12 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <cover.1663898962.git.huyue2@coolpad.com>
2022-09-23  2:11 ` Yue Hu [this message]
2022-09-23  2:11 ` [PATCH v6 2/2] erofs: support on-disk compressed fragments data Yue Hu
2022-09-26 15:52   ` Gao Xiang

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=8369112678604fdf4ef796626d59b1fdd0745a53.1663898962.git.huyue2@coolpad.com \
    --to=zbestahu@gmail.com \
    --cc=chao@kernel.org \
    --cc=huyue2@coolpad.com \
    --cc=linux-erofs@lists.ozlabs.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=xiang@kernel.org \
    --cc=zhangwen@coolpad.com \
    /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).