All of lore.kernel.org
 help / color / mirror / Atom feed
From: Gao Xiang <xiang@kernel.org>
To: linux-erofs@lists.ozlabs.org, Chao Yu <yuchao0@huawei.com>,
	Chao Yu <chao@kernel.org>
Cc: LKML <linux-kernel@vger.kernel.org>, Gao Xiang <hsiangkao@redhat.com>
Subject: [PATCH v3 08/10] erofs: support parsing big pcluster compact indexes
Date: Wed,  7 Apr 2021 12:39:25 +0800	[thread overview]
Message-ID: <20210407043927.10623-9-xiang@kernel.org> (raw)
In-Reply-To: <20210407043927.10623-1-xiang@kernel.org>

From: Gao Xiang <hsiangkao@redhat.com>

Different from non-compact indexes, several lclusters are packed
as the compact form at once and an unique base blkaddr is stored for
each pack, so each lcluster index would take less space on avarage
(e.g. 2 bytes for COMPACT_2B.) btw, that is also why BIG_PCLUSTER
switch should be consistent for compact head0/1.

Prior to big pcluster, the size of all pclusters was 1 lcluster.
Therefore, when a new HEAD lcluster was scanned, blkaddr would be
bumped by 1 lcluster. However, that way doesn't work anymore for
big pcluster since we actually don't know the compressed size of
pclusters in advance (before reading CBLKCNT lcluster).

So, instead, let blkaddr of each pack be the first pcluster blkaddr
with a valid CBLKCNT, in detail,

 1) if CBLKCNT starts at the pack, this first valid pcluster is
    itself, e.g.
  _____________________________________________________________
 |_CBLKCNT0_|_NONHEAD_| .. |_HEAD_|_CBLKCNT1_| ... |_HEAD_| ...
 ^ = blkaddr base          ^ += CBLKCNT0           ^ += CBLKCNT1

 2) if CBLKCNT doesn't start at the pack, the first valid pcluster
    is the next pcluster, e.g.
  _________________________________________________________
 | NONHEAD_| .. |_HEAD_|_CBLKCNT0_| ... |_HEAD_|_HEAD_| ...
                ^ = blkaddr base        ^ += CBLKCNT0
                                               ^ += 1

When a CBLKCNT is found, blkaddr will be increased by CBLKCNT
lclusters, or a new HEAD is found immediately, bump blkaddr by 1
instead (see the picture above.)

Also noted if CBLKCNT is the end of the pack, instead of storing
delta1 (distance of the next HEAD lcluster) as normal NONHEADs,
it still uses the compressed block count (delta0) since delta1
can be calculated indirectly but the block count can't.

Adjust decoding logic to fit big pcluster compact indexes as well.

Acked-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
---
 fs/erofs/zmap.c | 72 ++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 62 insertions(+), 10 deletions(-)

diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 6c0c47f68b75..e62d813756f2 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -77,6 +77,22 @@ static int z_erofs_fill_inode_lazy(struct inode *inode)
 	}
 
 	vi->z_logical_clusterbits = LOG_BLOCK_SIZE + (h->h_clusterbits & 7);
+	if (!erofs_sb_has_big_pcluster(EROFS_SB(sb)) &&
+	    vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 |
+			    Z_EROFS_ADVISE_BIG_PCLUSTER_2)) {
+		erofs_err(sb, "per-inode big pcluster without sb feature for nid %llu",
+			  vi->nid);
+		err = -EFSCORRUPTED;
+		goto unmap_done;
+	}
+	if (vi->datalayout == EROFS_INODE_FLAT_COMPRESSION &&
+	    !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1) ^
+	    !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2)) {
+		erofs_err(sb, "big pcluster head1/2 of compact indexes should be consistent for nid %llu",
+			  vi->nid);
+		err = -EFSCORRUPTED;
+		goto unmap_done;
+	}
 	/* paired with smp_mb() at the beginning of the function */
 	smp_mb();
 	set_bit(EROFS_I_Z_INITED_BIT, &vi->flags);
@@ -207,6 +223,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 	unsigned int vcnt, base, lo, encodebits, nblk;
 	int i;
 	u8 *in, type;
+	bool big_pcluster;
 
 	if (1 << amortizedshift == 4)
 		vcnt = 2;
@@ -215,6 +232,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 	else
 		return -EOPNOTSUPP;
 
+	big_pcluster = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1;
 	encodebits = ((vcnt << amortizedshift) - sizeof(__le32)) * 8 / vcnt;
 	base = round_down(eofs, vcnt << amortizedshift);
 	in = m->kaddr + base;
@@ -226,7 +244,15 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 	m->type = type;
 	if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
 		m->clusterofs = 1 << lclusterbits;
-		if (i + 1 != vcnt) {
+		if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) {
+			if (!big_pcluster) {
+				DBG_BUGON(1);
+				return -EFSCORRUPTED;
+			}
+			m->compressedlcs = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT;
+			m->delta[0] = 1;
+			return 0;
+		} else if (i + 1 != (int)vcnt) {
 			m->delta[0] = lo;
 			return 0;
 		}
@@ -239,22 +265,48 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 					  in, encodebits * (i - 1), &type);
 		if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
 			lo = 0;
+		else if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT)
+			lo = 1;
 		m->delta[0] = lo + 1;
 		return 0;
 	}
 	m->clusterofs = lo;
 	m->delta[0] = 0;
 	/* figout out blkaddr (pblk) for HEAD lclusters */
-	nblk = 1;
-	while (i > 0) {
-		--i;
-		lo = decode_compactedbits(lclusterbits, lomask,
-					  in, encodebits * i, &type);
-		if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
-			i -= lo;
-
-		if (i >= 0)
+	if (!big_pcluster) {
+		nblk = 1;
+		while (i > 0) {
+			--i;
+			lo = decode_compactedbits(lclusterbits, lomask,
+						  in, encodebits * i, &type);
+			if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
+				i -= lo;
+
+			if (i >= 0)
+				++nblk;
+		}
+	} else {
+		nblk = 0;
+		while (i > 0) {
+			--i;
+			lo = decode_compactedbits(lclusterbits, lomask,
+						  in, encodebits * i, &type);
+			if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
+				if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) {
+					--i;
+					nblk += lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT;
+					continue;
+				}
+				/* bigpcluster shouldn't have plain d0 == 1 */
+				if (lo <= 1) {
+					DBG_BUGON(1);
+					return -EFSCORRUPTED;
+				}
+				i -= lo - 2;
+				continue;
+			}
 			++nblk;
+		}
 	}
 	in += (vcnt << amortizedshift) - sizeof(__le32);
 	m->pblk = le32_to_cpu(*(__le32 *)in) + nblk;
-- 
2.20.1


WARNING: multiple messages have this Message-ID (diff)
From: Gao Xiang <xiang@kernel.org>
To: linux-erofs@lists.ozlabs.org, Chao Yu <yuchao0@huawei.com>,
	Chao Yu <chao@kernel.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH v3 08/10] erofs: support parsing big pcluster compact indexes
Date: Wed,  7 Apr 2021 12:39:25 +0800	[thread overview]
Message-ID: <20210407043927.10623-9-xiang@kernel.org> (raw)
In-Reply-To: <20210407043927.10623-1-xiang@kernel.org>

From: Gao Xiang <hsiangkao@redhat.com>

Different from non-compact indexes, several lclusters are packed
as the compact form at once and an unique base blkaddr is stored for
each pack, so each lcluster index would take less space on avarage
(e.g. 2 bytes for COMPACT_2B.) btw, that is also why BIG_PCLUSTER
switch should be consistent for compact head0/1.

Prior to big pcluster, the size of all pclusters was 1 lcluster.
Therefore, when a new HEAD lcluster was scanned, blkaddr would be
bumped by 1 lcluster. However, that way doesn't work anymore for
big pcluster since we actually don't know the compressed size of
pclusters in advance (before reading CBLKCNT lcluster).

So, instead, let blkaddr of each pack be the first pcluster blkaddr
with a valid CBLKCNT, in detail,

 1) if CBLKCNT starts at the pack, this first valid pcluster is
    itself, e.g.
  _____________________________________________________________
 |_CBLKCNT0_|_NONHEAD_| .. |_HEAD_|_CBLKCNT1_| ... |_HEAD_| ...
 ^ = blkaddr base          ^ += CBLKCNT0           ^ += CBLKCNT1

 2) if CBLKCNT doesn't start at the pack, the first valid pcluster
    is the next pcluster, e.g.
  _________________________________________________________
 | NONHEAD_| .. |_HEAD_|_CBLKCNT0_| ... |_HEAD_|_HEAD_| ...
                ^ = blkaddr base        ^ += CBLKCNT0
                                               ^ += 1

When a CBLKCNT is found, blkaddr will be increased by CBLKCNT
lclusters, or a new HEAD is found immediately, bump blkaddr by 1
instead (see the picture above.)

Also noted if CBLKCNT is the end of the pack, instead of storing
delta1 (distance of the next HEAD lcluster) as normal NONHEADs,
it still uses the compressed block count (delta0) since delta1
can be calculated indirectly but the block count can't.

Adjust decoding logic to fit big pcluster compact indexes as well.

Acked-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
---
 fs/erofs/zmap.c | 72 ++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 62 insertions(+), 10 deletions(-)

diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 6c0c47f68b75..e62d813756f2 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -77,6 +77,22 @@ static int z_erofs_fill_inode_lazy(struct inode *inode)
 	}
 
 	vi->z_logical_clusterbits = LOG_BLOCK_SIZE + (h->h_clusterbits & 7);
+	if (!erofs_sb_has_big_pcluster(EROFS_SB(sb)) &&
+	    vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 |
+			    Z_EROFS_ADVISE_BIG_PCLUSTER_2)) {
+		erofs_err(sb, "per-inode big pcluster without sb feature for nid %llu",
+			  vi->nid);
+		err = -EFSCORRUPTED;
+		goto unmap_done;
+	}
+	if (vi->datalayout == EROFS_INODE_FLAT_COMPRESSION &&
+	    !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1) ^
+	    !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2)) {
+		erofs_err(sb, "big pcluster head1/2 of compact indexes should be consistent for nid %llu",
+			  vi->nid);
+		err = -EFSCORRUPTED;
+		goto unmap_done;
+	}
 	/* paired with smp_mb() at the beginning of the function */
 	smp_mb();
 	set_bit(EROFS_I_Z_INITED_BIT, &vi->flags);
@@ -207,6 +223,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 	unsigned int vcnt, base, lo, encodebits, nblk;
 	int i;
 	u8 *in, type;
+	bool big_pcluster;
 
 	if (1 << amortizedshift == 4)
 		vcnt = 2;
@@ -215,6 +232,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 	else
 		return -EOPNOTSUPP;
 
+	big_pcluster = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1;
 	encodebits = ((vcnt << amortizedshift) - sizeof(__le32)) * 8 / vcnt;
 	base = round_down(eofs, vcnt << amortizedshift);
 	in = m->kaddr + base;
@@ -226,7 +244,15 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 	m->type = type;
 	if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
 		m->clusterofs = 1 << lclusterbits;
-		if (i + 1 != vcnt) {
+		if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) {
+			if (!big_pcluster) {
+				DBG_BUGON(1);
+				return -EFSCORRUPTED;
+			}
+			m->compressedlcs = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT;
+			m->delta[0] = 1;
+			return 0;
+		} else if (i + 1 != (int)vcnt) {
 			m->delta[0] = lo;
 			return 0;
 		}
@@ -239,22 +265,48 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 					  in, encodebits * (i - 1), &type);
 		if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
 			lo = 0;
+		else if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT)
+			lo = 1;
 		m->delta[0] = lo + 1;
 		return 0;
 	}
 	m->clusterofs = lo;
 	m->delta[0] = 0;
 	/* figout out blkaddr (pblk) for HEAD lclusters */
-	nblk = 1;
-	while (i > 0) {
-		--i;
-		lo = decode_compactedbits(lclusterbits, lomask,
-					  in, encodebits * i, &type);
-		if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
-			i -= lo;
-
-		if (i >= 0)
+	if (!big_pcluster) {
+		nblk = 1;
+		while (i > 0) {
+			--i;
+			lo = decode_compactedbits(lclusterbits, lomask,
+						  in, encodebits * i, &type);
+			if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
+				i -= lo;
+
+			if (i >= 0)
+				++nblk;
+		}
+	} else {
+		nblk = 0;
+		while (i > 0) {
+			--i;
+			lo = decode_compactedbits(lclusterbits, lomask,
+						  in, encodebits * i, &type);
+			if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
+				if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) {
+					--i;
+					nblk += lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT;
+					continue;
+				}
+				/* bigpcluster shouldn't have plain d0 == 1 */
+				if (lo <= 1) {
+					DBG_BUGON(1);
+					return -EFSCORRUPTED;
+				}
+				i -= lo - 2;
+				continue;
+			}
 			++nblk;
+		}
 	}
 	in += (vcnt << amortizedshift) - sizeof(__le32);
 	m->pblk = le32_to_cpu(*(__le32 *)in) + nblk;
-- 
2.20.1


  parent reply	other threads:[~2021-04-07  4:40 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-07  4:39 [PATCH v3 00/10] erofs: add big pcluster compression support Gao Xiang
2021-04-07  4:39 ` Gao Xiang
2021-04-07  4:39 ` [PATCH v3 01/10] erofs: reserve physical_clusterbits[] Gao Xiang
2021-04-07  4:39   ` Gao Xiang
2021-04-07  4:39 ` [PATCH v3 02/10] erofs: introduce multipage per-CPU buffers Gao Xiang
2021-04-07  4:39   ` Gao Xiang
2021-04-09 10:53   ` [PATCH v3.1 " Gao Xiang
2021-04-09 10:53     ` Gao Xiang
2021-04-09 19:06   ` [PATCH v3.2 " Gao Xiang
2021-04-09 19:06     ` Gao Xiang
2021-04-07  4:39 ` [PATCH v3 03/10] erofs: introduce physical cluster slab pools Gao Xiang
2021-04-07  4:39   ` Gao Xiang
2021-04-07  4:39 ` [PATCH v3 04/10] erofs: fix up inplace I/O pointer for big pcluster Gao Xiang
2021-04-07  4:39   ` Gao Xiang
2021-04-07  4:39 ` [PATCH v3 05/10] erofs: add big physical cluster definition Gao Xiang
2021-04-07  4:39   ` Gao Xiang
2021-04-07  4:39 ` [PATCH v3 06/10] erofs: adjust per-CPU buffers according to max_pclusterblks Gao Xiang
2021-04-07  4:39   ` Gao Xiang
2021-04-07  4:39 ` [PATCH v3 07/10] erofs: support parsing big pcluster compress indexes Gao Xiang
2021-04-07  4:39   ` Gao Xiang
2021-04-07  4:39 ` Gao Xiang [this message]
2021-04-07  4:39   ` [PATCH v3 08/10] erofs: support parsing big pcluster compact indexes Gao Xiang
2021-04-07  4:39 ` [PATCH v3 09/10] erofs: support decompress big pcluster for lz4 backend Gao Xiang
2021-04-07  4:39   ` Gao Xiang
2021-04-07  4:39 ` [PATCH v3 10/10] erofs: enable big pcluster feature Gao Xiang
2021-04-07  4:39   ` 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=20210407043927.10623-9-xiang@kernel.org \
    --to=xiang@kernel.org \
    --cc=chao@kernel.org \
    --cc=hsiangkao@redhat.com \
    --cc=linux-erofs@lists.ozlabs.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=yuchao0@huawei.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.