linux/fs/erofs/zmap.c

718 lines
18 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2018-2019 HUAWEI, Inc.
* https://www.huawei.com/
*/
#include "internal.h"
#include <asm/unaligned.h>
#include <trace/events/erofs.h>
int z_erofs_fill_inode(struct inode *inode)
{
struct erofs_inode *const vi = EROFS_I(inode);
struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);
if (!erofs_sb_has_big_pcluster(sbi) &&
vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY) {
vi->z_advise = 0;
vi->z_algorithmtype[0] = 0;
vi->z_algorithmtype[1] = 0;
vi->z_logical_clusterbits = LOG_BLOCK_SIZE;
set_bit(EROFS_I_Z_INITED_BIT, &vi->flags);
}
inode->i_mapping->a_ops = &z_erofs_aops;
return 0;
}
static int z_erofs_fill_inode_lazy(struct inode *inode)
{
struct erofs_inode *const vi = EROFS_I(inode);
struct super_block *const sb = inode->i_sb;
int err;
erofs_off_t pos;
struct page *page;
void *kaddr;
struct z_erofs_map_header *h;
if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) {
/*
* paired with smp_mb() at the end of the function to ensure
* fields will only be observed after the bit is set.
*/
smp_mb();
return 0;
}
if (wait_on_bit_lock(&vi->flags, EROFS_I_BL_Z_BIT, TASK_KILLABLE))
return -ERESTARTSYS;
err = 0;
if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags))
goto out_unlock;
DBG_BUGON(!erofs_sb_has_big_pcluster(EROFS_SB(sb)) &&
vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY);
pos = ALIGN(iloc(EROFS_SB(sb), vi->nid) + vi->inode_isize +
vi->xattr_isize, 8);
page = erofs_get_meta_page(sb, erofs_blknr(pos));
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto out_unlock;
}
kaddr = kmap_atomic(page);
h = kaddr + erofs_blkoff(pos);
vi->z_advise = le16_to_cpu(h->h_advise);
vi->z_algorithmtype[0] = h->h_algorithmtype & 15;
vi->z_algorithmtype[1] = h->h_algorithmtype >> 4;
if (vi->z_algorithmtype[0] >= Z_EROFS_COMPRESSION_MAX) {
erofs_err(sb, "unknown compression format %u for nid %llu, please upgrade kernel",
vi->z_algorithmtype[0], vi->nid);
err = -EOPNOTSUPP;
goto unmap_done;
}
vi->z_logical_clusterbits = LOG_BLOCK_SIZE + (h->h_clusterbits & 7);
erofs: support parsing big pcluster compact indexes 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. Link: https://lore.kernel.org/r/20210407043927.10623-9-xiang@kernel.org Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
2021-04-07 12:39:25 +08:00
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);
unmap_done:
kunmap_atomic(kaddr);
unlock_page(page);
put_page(page);
out_unlock:
clear_and_wake_up_bit(EROFS_I_BL_Z_BIT, &vi->flags);
return err;
}
struct z_erofs_maprecorder {
struct inode *inode;
struct erofs_map_blocks *map;
void *kaddr;
unsigned long lcn;
/* compression extent information gathered */
u8 type, headtype;
u16 clusterofs;
u16 delta[2];
erofs_blk_t pblk, compressedlcs;
};
static int z_erofs_reload_indexes(struct z_erofs_maprecorder *m,
erofs_blk_t eblk)
{
struct super_block *const sb = m->inode->i_sb;
struct erofs_map_blocks *const map = m->map;
struct page *mpage = map->mpage;
if (mpage) {
if (mpage->index == eblk) {
if (!m->kaddr)
m->kaddr = kmap_atomic(mpage);
return 0;
}
if (m->kaddr) {
kunmap_atomic(m->kaddr);
m->kaddr = NULL;
}
put_page(mpage);
}
mpage = erofs_get_meta_page(sb, eblk);
if (IS_ERR(mpage)) {
map->mpage = NULL;
return PTR_ERR(mpage);
}
m->kaddr = kmap_atomic(mpage);
unlock_page(mpage);
map->mpage = mpage;
return 0;
}
static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
unsigned long lcn)
{
struct inode *const inode = m->inode;
struct erofs_inode *const vi = EROFS_I(inode);
const erofs_off_t ibase = iloc(EROFS_I_SB(inode), vi->nid);
const erofs_off_t pos =
Z_EROFS_VLE_LEGACY_INDEX_ALIGN(ibase + vi->inode_isize +
vi->xattr_isize) +
lcn * sizeof(struct z_erofs_vle_decompressed_index);
struct z_erofs_vle_decompressed_index *di;
unsigned int advise, type;
int err;
err = z_erofs_reload_indexes(m, erofs_blknr(pos));
if (err)
return err;
m->lcn = lcn;
di = m->kaddr + erofs_blkoff(pos);
advise = le16_to_cpu(di->di_advise);
type = (advise >> Z_EROFS_VLE_DI_CLUSTER_TYPE_BIT) &
((1 << Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS) - 1);
switch (type) {
case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
m->clusterofs = 1 << vi->z_logical_clusterbits;
m->delta[0] = le16_to_cpu(di->di_u.delta[0]);
if (m->delta[0] & Z_EROFS_VLE_DI_D0_CBLKCNT) {
if (!(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1)) {
DBG_BUGON(1);
return -EFSCORRUPTED;
}
m->compressedlcs = m->delta[0] &
~Z_EROFS_VLE_DI_D0_CBLKCNT;
m->delta[0] = 1;
}
m->delta[1] = le16_to_cpu(di->di_u.delta[1]);
break;
case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
case Z_EROFS_VLE_CLUSTER_TYPE_HEAD:
m->clusterofs = le16_to_cpu(di->di_clusterofs);
m->pblk = le32_to_cpu(di->di_u.blkaddr);
break;
default:
DBG_BUGON(1);
return -EOPNOTSUPP;
}
m->type = type;
return 0;
}
static unsigned int decode_compactedbits(unsigned int lobits,
unsigned int lomask,
u8 *in, unsigned int pos, u8 *type)
{
const unsigned int v = get_unaligned_le32(in + pos / 8) >> (pos & 7);
const unsigned int lo = v & lomask;
*type = (v >> lobits) & 3;
return lo;
}
static int get_compacted_la_distance(unsigned int lclusterbits,
unsigned int encodebits,
unsigned int vcnt, u8 *in, int i)
{
const unsigned int lomask = (1 << lclusterbits) - 1;
unsigned int lo, d1 = 0;
u8 type;
DBG_BUGON(i >= vcnt);
do {
lo = decode_compactedbits(lclusterbits, lomask,
in, encodebits * i, &type);
if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
return d1;
++d1;
} while (++i < vcnt);
/* vcnt - 1 (Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) item */
if (!(lo & Z_EROFS_VLE_DI_D0_CBLKCNT))
d1 += lo - 1;
return d1;
}
static int unpack_compacted_index(struct z_erofs_maprecorder *m,
unsigned int amortizedshift,
unsigned int eofs, bool lookahead)
{
struct erofs_inode *const vi = EROFS_I(m->inode);
const unsigned int lclusterbits = vi->z_logical_clusterbits;
const unsigned int lomask = (1 << lclusterbits) - 1;
unsigned int vcnt, base, lo, encodebits, nblk;
int i;
u8 *in, type;
erofs: support parsing big pcluster compact indexes 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. Link: https://lore.kernel.org/r/20210407043927.10623-9-xiang@kernel.org Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
2021-04-07 12:39:25 +08:00
bool big_pcluster;
if (1 << amortizedshift == 4)
vcnt = 2;
else if (1 << amortizedshift == 2 && lclusterbits == 12)
vcnt = 16;
else
return -EOPNOTSUPP;
erofs: support parsing big pcluster compact indexes 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. Link: https://lore.kernel.org/r/20210407043927.10623-9-xiang@kernel.org Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
2021-04-07 12:39:25 +08:00
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;
i = (eofs - base) >> amortizedshift;
lo = decode_compactedbits(lclusterbits, lomask,
in, encodebits * i, &type);
m->type = type;
if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
m->clusterofs = 1 << lclusterbits;
/* figure out lookahead_distance: delta[1] if needed */
if (lookahead)
m->delta[1] = get_compacted_la_distance(lclusterbits,
encodebits, vcnt, in, i);
erofs: support parsing big pcluster compact indexes 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. Link: https://lore.kernel.org/r/20210407043927.10623-9-xiang@kernel.org Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
2021-04-07 12:39:25 +08:00
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;
}
/*
* since the last lcluster in the pack is special,
* of which lo saves delta[1] rather than delta[0].
* Hence, get delta[0] by the previous lcluster indirectly.
*/
lo = decode_compactedbits(lclusterbits, lomask,
in, encodebits * (i - 1), &type);
if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
lo = 0;
erofs: support parsing big pcluster compact indexes 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. Link: https://lore.kernel.org/r/20210407043927.10623-9-xiang@kernel.org Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
2021-04-07 12:39:25 +08:00
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 */
erofs: support parsing big pcluster compact indexes 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. Link: https://lore.kernel.org/r/20210407043927.10623-9-xiang@kernel.org Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
2021-04-07 12:39:25 +08:00
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;
erofs: support parsing big pcluster compact indexes 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. Link: https://lore.kernel.org/r/20210407043927.10623-9-xiang@kernel.org Acked-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Gao Xiang <hsiangkao@redhat.com>
2021-04-07 12:39:25 +08:00
}
}
in += (vcnt << amortizedshift) - sizeof(__le32);
m->pblk = le32_to_cpu(*(__le32 *)in) + nblk;
return 0;
}
static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m,
unsigned long lcn, bool lookahead)
{
struct inode *const inode = m->inode;
struct erofs_inode *const vi = EROFS_I(inode);
const unsigned int lclusterbits = vi->z_logical_clusterbits;
const erofs_off_t ebase = ALIGN(iloc(EROFS_I_SB(inode), vi->nid) +
vi->inode_isize + vi->xattr_isize, 8) +
sizeof(struct z_erofs_map_header);
const unsigned int totalidx = DIV_ROUND_UP(inode->i_size, EROFS_BLKSIZ);
unsigned int compacted_4b_initial, compacted_2b;
unsigned int amortizedshift;
erofs_off_t pos;
int err;
if (lclusterbits != 12)
return -EOPNOTSUPP;
if (lcn >= totalidx)
return -EINVAL;
m->lcn = lcn;
/* used to align to 32-byte (compacted_2b) alignment */
compacted_4b_initial = (32 - ebase % 32) / 4;
if (compacted_4b_initial == 32 / 4)
compacted_4b_initial = 0;
if ((vi->z_advise & Z_EROFS_ADVISE_COMPACTED_2B) &&
compacted_4b_initial < totalidx)
compacted_2b = rounddown(totalidx - compacted_4b_initial, 16);
else
compacted_2b = 0;
pos = ebase;
if (lcn < compacted_4b_initial) {
amortizedshift = 2;
goto out;
}
pos += compacted_4b_initial * 4;
lcn -= compacted_4b_initial;
if (lcn < compacted_2b) {
amortizedshift = 1;
goto out;
}
pos += compacted_2b * 2;
lcn -= compacted_2b;
amortizedshift = 2;
out:
pos += lcn * (1 << amortizedshift);
err = z_erofs_reload_indexes(m, erofs_blknr(pos));
if (err)
return err;
return unpack_compacted_index(m, amortizedshift, erofs_blkoff(pos),
lookahead);
}
static int z_erofs_load_cluster_from_disk(struct z_erofs_maprecorder *m,
unsigned int lcn, bool lookahead)
{
const unsigned int datamode = EROFS_I(m->inode)->datalayout;
if (datamode == EROFS_INODE_FLAT_COMPRESSION_LEGACY)
return legacy_load_cluster_from_disk(m, lcn);
if (datamode == EROFS_INODE_FLAT_COMPRESSION)
return compacted_load_cluster_from_disk(m, lcn, lookahead);
return -EINVAL;
}
static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m,
unsigned int lookback_distance)
{
struct erofs_inode *const vi = EROFS_I(m->inode);
struct erofs_map_blocks *const map = m->map;
const unsigned int lclusterbits = vi->z_logical_clusterbits;
unsigned long lcn = m->lcn;
int err;
if (lcn < lookback_distance) {
erofs_err(m->inode->i_sb,
"bogus lookback distance @ nid %llu", vi->nid);
DBG_BUGON(1);
return -EFSCORRUPTED;
}
/* load extent head logical cluster if needed */
lcn -= lookback_distance;
err = z_erofs_load_cluster_from_disk(m, lcn, false);
if (err)
return err;
switch (m->type) {
case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
if (!m->delta[0]) {
erofs_err(m->inode->i_sb,
"invalid lookback distance 0 @ nid %llu",
vi->nid);
DBG_BUGON(1);
return -EFSCORRUPTED;
}
return z_erofs_extent_lookback(m, m->delta[0]);
case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
case Z_EROFS_VLE_CLUSTER_TYPE_HEAD:
m->headtype = m->type;
map->m_la = (lcn << lclusterbits) | m->clusterofs;
break;
default:
erofs_err(m->inode->i_sb,
"unknown type %u @ lcn %lu of nid %llu",
m->type, lcn, vi->nid);
DBG_BUGON(1);
return -EOPNOTSUPP;
}
return 0;
}
static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
unsigned int initial_lcn)
{
struct erofs_inode *const vi = EROFS_I(m->inode);
struct erofs_map_blocks *const map = m->map;
const unsigned int lclusterbits = vi->z_logical_clusterbits;
unsigned long lcn;
int err;
DBG_BUGON(m->type != Z_EROFS_VLE_CLUSTER_TYPE_PLAIN &&
m->type != Z_EROFS_VLE_CLUSTER_TYPE_HEAD);
if (m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN ||
!(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1)) {
map->m_plen = 1 << lclusterbits;
return 0;
}
lcn = m->lcn + 1;
if (m->compressedlcs)
goto out;
err = z_erofs_load_cluster_from_disk(m, lcn, false);
if (err)
return err;
/*
* If the 1st NONHEAD lcluster has already been handled initially w/o
* valid compressedlcs, which means at least it mustn't be CBLKCNT, or
* an internal implemenatation error is detected.
*
* The following code can also handle it properly anyway, but let's
* BUG_ON in the debugging mode only for developers to notice that.
*/
DBG_BUGON(lcn == initial_lcn &&
m->type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD);
switch (m->type) {
case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
case Z_EROFS_VLE_CLUSTER_TYPE_HEAD:
/*
* if the 1st NONHEAD lcluster is actually PLAIN or HEAD type
* rather than CBLKCNT, it's a 1 lcluster-sized pcluster.
*/
m->compressedlcs = 1;
break;
case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
if (m->delta[0] != 1)
goto err_bonus_cblkcnt;
if (m->compressedlcs)
break;
fallthrough;
default:
erofs_err(m->inode->i_sb,
"cannot found CBLKCNT @ lcn %lu of nid %llu",
lcn, vi->nid);
DBG_BUGON(1);
return -EFSCORRUPTED;
}
out:
map->m_plen = m->compressedlcs << lclusterbits;
return 0;
err_bonus_cblkcnt:
erofs_err(m->inode->i_sb,
"bogus CBLKCNT @ lcn %lu of nid %llu",
lcn, vi->nid);
DBG_BUGON(1);
return -EFSCORRUPTED;
}
static int z_erofs_get_extent_decompressedlen(struct z_erofs_maprecorder *m)
{
struct inode *inode = m->inode;
struct erofs_inode *vi = EROFS_I(inode);
struct erofs_map_blocks *map = m->map;
unsigned int lclusterbits = vi->z_logical_clusterbits;
u64 lcn = m->lcn, headlcn = map->m_la >> lclusterbits;
int err;
do {
/* handle the last EOF pcluster (no next HEAD lcluster) */
if ((lcn << lclusterbits) >= inode->i_size) {
map->m_llen = inode->i_size - map->m_la;
return 0;
}
err = z_erofs_load_cluster_from_disk(m, lcn, true);
if (err)
return err;
if (m->type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
DBG_BUGON(!m->delta[1] &&
m->clusterofs != 1 << lclusterbits);
} else if (m->type == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN ||
m->type == Z_EROFS_VLE_CLUSTER_TYPE_HEAD) {
/* go on until the next HEAD lcluster */
if (lcn != headlcn)
break;
m->delta[1] = 1;
} else {
erofs_err(inode->i_sb, "unknown type %u @ lcn %llu of nid %llu",
m->type, lcn, vi->nid);
DBG_BUGON(1);
return -EOPNOTSUPP;
}
lcn += m->delta[1];
} while (m->delta[1]);
map->m_llen = (lcn << lclusterbits) + m->clusterofs - map->m_la;
return 0;
}
int z_erofs_map_blocks_iter(struct inode *inode,
struct erofs_map_blocks *map,
int flags)
{
struct erofs_inode *const vi = EROFS_I(inode);
struct z_erofs_maprecorder m = {
.inode = inode,
.map = map,
};
int err = 0;
unsigned int lclusterbits, endoff;
unsigned long initial_lcn;
unsigned long long ofs, end;
trace_z_erofs_map_blocks_iter_enter(inode, map, flags);
/* when trying to read beyond EOF, leave it unmapped */
if (map->m_la >= inode->i_size) {
map->m_llen = map->m_la + 1 - inode->i_size;
map->m_la = inode->i_size;
map->m_flags = 0;
goto out;
}
err = z_erofs_fill_inode_lazy(inode);
if (err)
goto out;
lclusterbits = vi->z_logical_clusterbits;
ofs = map->m_la;
initial_lcn = ofs >> lclusterbits;
endoff = ofs & ((1 << lclusterbits) - 1);
err = z_erofs_load_cluster_from_disk(&m, initial_lcn, false);
if (err)
goto unmap_out;
map->m_flags = EROFS_MAP_MAPPED | EROFS_MAP_ENCODED;
end = (m.lcn + 1ULL) << lclusterbits;
switch (m.type) {
case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
case Z_EROFS_VLE_CLUSTER_TYPE_HEAD:
if (endoff >= m.clusterofs) {
m.headtype = m.type;
map->m_la = (m.lcn << lclusterbits) | m.clusterofs;
break;
}
/* m.lcn should be >= 1 if endoff < m.clusterofs */
if (!m.lcn) {
erofs_err(inode->i_sb,
"invalid logical cluster 0 at nid %llu",
vi->nid);
err = -EFSCORRUPTED;
goto unmap_out;
}
end = (m.lcn << lclusterbits) | m.clusterofs;
map->m_flags |= EROFS_MAP_FULL_MAPPED;
m.delta[0] = 1;
fallthrough;
case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
/* get the corresponding first chunk */
err = z_erofs_extent_lookback(&m, m.delta[0]);
if (err)
goto unmap_out;
break;
default:
erofs_err(inode->i_sb,
"unknown type %u @ offset %llu of nid %llu",
m.type, ofs, vi->nid);
err = -EOPNOTSUPP;
goto unmap_out;
}
map->m_llen = end - map->m_la;
map->m_pa = blknr_to_addr(m.pblk);
err = z_erofs_get_extent_compressedlen(&m, initial_lcn);
if (err)
goto out;
if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN)
map->m_algorithmformat = Z_EROFS_COMPRESSION_SHIFTED;
else
map->m_algorithmformat = vi->z_algorithmtype[0];
if (flags & EROFS_GET_BLOCKS_FIEMAP) {
err = z_erofs_get_extent_decompressedlen(&m);
if (!err)
map->m_flags |= EROFS_MAP_FULL_MAPPED;
}
unmap_out:
if (m.kaddr)
kunmap_atomic(m.kaddr);
out:
erofs_dbg("%s, m_la %llu m_pa %llu m_llen %llu m_plen %llu m_flags 0%o",
__func__, map->m_la, map->m_pa,
map->m_llen, map->m_plen, map->m_flags);
trace_z_erofs_map_blocks_iter_exit(inode, map, flags, err);
/* aggressively BUG_ON iff CONFIG_EROFS_FS_DEBUG is on */
DBG_BUGON(err < 0 && err != -ENOMEM);
return err;
}
static int z_erofs_iomap_begin_report(struct inode *inode, loff_t offset,
loff_t length, unsigned int flags,
struct iomap *iomap, struct iomap *srcmap)
{
int ret;
struct erofs_map_blocks map = { .m_la = offset };
ret = z_erofs_map_blocks_iter(inode, &map, EROFS_GET_BLOCKS_FIEMAP);
if (map.mpage)
put_page(map.mpage);
if (ret < 0)
return ret;
iomap->bdev = inode->i_sb->s_bdev;
iomap->offset = map.m_la;
iomap->length = map.m_llen;
if (map.m_flags & EROFS_MAP_MAPPED) {
iomap->type = IOMAP_MAPPED;
iomap->addr = map.m_pa;
} else {
iomap->type = IOMAP_HOLE;
iomap->addr = IOMAP_NULL_ADDR;
/*
* No strict rule how to describe extents for post EOF, yet
* we need do like below. Otherwise, iomap itself will get
* into an endless loop on post EOF.
*/
if (iomap->offset >= inode->i_size)
iomap->length = length + map.m_la - offset;
}
iomap->flags = 0;
return 0;
}
const struct iomap_ops z_erofs_iomap_report_ops = {
.iomap_begin = z_erofs_iomap_begin_report,
};