Merge branch 'dev' of github.com:facebook/zstd into dev

dev
Yann Collet 2017-04-11 14:42:46 -07:00
commit 324c2cd908
6 changed files with 1840 additions and 573 deletions

View File

@ -1,8 +1,7 @@
# Linux Kernel Patch
There are two pieces, the `zstd_compress` and `zstd_decompress` kernel modules, and the BtrFS patch.
The patches are based off of the linux kernel version 4.9.
The BtrFS patch is not present in its entirety yet.
The patches are based off of the linux kernel master branch (version 4.10).
## Zstd Kernel modules
@ -21,6 +20,33 @@ The BtrFS patch is not present in its entirety yet.
## BtrFS
* `fs/btrfs/zstd.c` is provided.
* Some more glue is required to integrate it with BtrFS, but I haven't included the patches yet.
In the meantime see https://github.com/terrelln/linux/commit/1914f7d4ca6c539369c84853eafa4ac104883047 if you're interested.
* The patch is located in `btrfs.diff`.
* Additionally `fs/btrfs/zstd.c` is provided as a source for convenience.
* The patch seems to be working, it doesn't crash the kernel, and compresses at speeds and ratios athat are expected.
It can still use some more testing for fringe features, like printing options.
### Benchmarks
Benchmarks run on a Ubuntu 14.04 with 2 cores and 4 GiB of RAM.
The VM is running on a Macbook Pro with a 3.1 GHz Intel Core i7 processor,
16 GB of ram, and a SSD.
The compression benchmark is copying 10 copies of the
unzipped [silesia corpus](http://mattmahoney.net/dc/silesia.html) into a BtrFS
filesystem mounted with `-o compress-force={none, lzo, zlib, zstd}`.
The decompression benchmark is timing how long it takes to `tar` all 10 copies
into `/dev/null`.
The compression ratio is measured by comparing the output of `df` and `du`.
See `btrfs-benchmark.sh` for details.
| Algorithm | Compression ratio | Compression speed | Decompression speed |
|-----------|-------------------|-------------------|---------------------|
| None | 0.99 | 504 MB/s | 686 MB/s |
| lzo | 1.66 | 398 MB/s | 442 MB/s |
| zlib | 2.58 | 65 MB/s | 241 MB/s |
| zstd 1 | 2.57 | 260 MB/s | 383 MB/s |
| zstd 3 | 2.71 | 174 MB/s | 408 MB/s |
| zstd 6 | 2.87 | 70 MB/s | 398 MB/s |
| zstd 9 | 2.92 | 43 MB/s | 406 MB/s |
| zstd 12 | 2.93 | 21 MB/s | 408 MB/s |
| zstd 15 | 3.01 | 11 MB/s | 354 MB/s |

View File

@ -0,0 +1,104 @@
# !/bin/sh
set -e
# Benchmarks run on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM.
# The VM is running on a Macbook Pro with a 3.1 GHz Intel Core i7 processor and
# 16 GB of RAM and an SSD.
# silesia is a directory that can be downloaded from
# http://mattmahoney.net/dc/silesia.html
# ls -l silesia/
# total 203M
# -rwxr-xr-x 1 terrelln 9.8M Apr 12 2002 dickens
# -rwxr-xr-x 1 terrelln 49M May 31 2002 mozilla
# -rwxr-xr-x 1 terrelln 9.6M Mar 20 2003 mr
# -rwxr-xr-x 1 terrelln 32M Apr 2 2002 nci
# -rwxr-xr-x 1 terrelln 5.9M Jul 4 2002 ooffice
# -rwxr-xr-x 1 terrelln 9.7M Apr 11 2002 osdb
# -rwxr-xr-x 1 terrelln 6.4M Apr 2 2002 reymont
# -rwxr-xr-x 1 terrelln 21M Mar 25 2002 samba
# -rwxr-xr-x 1 terrelln 7.0M Mar 24 2002 sao
# -rwxr-xr-x 1 terrelln 40M Mar 25 2002 webster
# -rwxr-xr-x 1 terrelln 8.1M Apr 4 2002 x-ray
# -rwxr-xr-x 1 terrelln 5.1M Nov 30 2000 xml
# $HOME is on a ext4 filesystem
BENCHMARK_DIR="$HOME/silesia/"
N=10
# Normalize the environment
sudo umount /mnt/btrfs 2> /dev/null > /dev/null || true
sudo mount -t btrfs $@ /dev/sda3 /mnt/btrfs
sudo rm -rf /mnt/btrfs/*
sync
sudo umount /mnt/btrfs
sudo mount -t btrfs $@ /dev/sda3 /mnt/btrfs
# Run the benchmark
echo "Compression"
time sh -c "for i in \$(seq $N); do sudo cp -r $BENCHMARK_DIR /mnt/btrfs/\$i; done; sync"
echo "Approximate compression ratio"
printf "%d / %d\n" \
$(df /mnt/btrfs --output=used -B 1 | tail -n 1) \
$(sudo du /mnt/btrfs -b -d 0 | tr '\t' '\n' | head -n 1);
# Unmount and remount to avoid any caching
sudo umount /mnt/btrfs
sudo mount -t btrfs $@ /dev/sda3 /mnt/btrfs
echo "Decompression"
time sudo tar -c /mnt/btrfs 2> /dev/null | wc -c > /dev/null
sudo rm -rf /mnt/btrfs/*
sudo umount /mnt/btrfs
# Run for each of -o compress-force={none, lzo, zlib, zstd} 5 times and take the
# min time and ratio.
# Ran zstd with compression levels {1, 3, 6, 9, 12, 15}.
# Original size: 2119415342 B (using du /mnt/btrfs)
# none
# compress: 4.205 s
# decompress: 3.090 s
# ratio: 0.99
# lzo
# compress: 5.328 s
# decompress: 4.793 s
# ratio: 1.66
# zlib
# compress: 32.588 s
# decompress: 8.791 s
# ratio : 2.58
# zstd 1
# compress: 8.147 s
# decompress: 5.527 s
# ratio : 2.57
# zstd 3
# compress: 12.207 s
# decompress: 5.195 s
# ratio : 2.71
# zstd 6
# compress: 30.253 s
# decompress: 5.324 s
# ratio : 2.87
# zstd 9
# compress: 49.659 s
# decompress: 5.220 s
# ratio : 2.92
# zstd 12
# compress: 99.245 s
# decompress: 5.193 s
# ratio : 2.93
# zstd 15
# compress: 196.997 s
# decompress: 5.992 s
# ratio : 3.01

View File

@ -0,0 +1,633 @@
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index 80e9c18..a26c63b 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -6,6 +6,8 @@ config BTRFS_FS
select ZLIB_DEFLATE
select LZO_COMPRESS
select LZO_DECOMPRESS
+ select ZSTD_COMPRESS
+ select ZSTD_DECOMPRESS
select RAID6_PQ
select XOR_BLOCKS
select SRCU
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 128ce17..962a95a 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -6,7 +6,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
transaction.o inode.o file.o tree-defrag.o \
extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \
extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
- export.o tree-log.o free-space-cache.o zlib.o lzo.o \
+ export.o tree-log.o free-space-cache.o zlib.o lzo.o zstd.o \
compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
uuid-tree.o props.o hash.o free-space-tree.o
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index c7721a6..66d4ced 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -761,6 +761,7 @@ static struct {
static const struct btrfs_compress_op * const btrfs_compress_op[] = {
&btrfs_zlib_compress,
&btrfs_lzo_compress,
+ &btrfs_zstd_compress,
};
void __init btrfs_init_compress(void)
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 39ec43a..d99fc21 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -60,8 +60,9 @@ enum btrfs_compression_type {
BTRFS_COMPRESS_NONE = 0,
BTRFS_COMPRESS_ZLIB = 1,
BTRFS_COMPRESS_LZO = 2,
- BTRFS_COMPRESS_TYPES = 2,
- BTRFS_COMPRESS_LAST = 3,
+ BTRFS_COMPRESS_ZSTD = 3,
+ BTRFS_COMPRESS_TYPES = 3,
+ BTRFS_COMPRESS_LAST = 4,
};
struct btrfs_compress_op {
@@ -92,5 +93,6 @@ struct btrfs_compress_op {
extern const struct btrfs_compress_op btrfs_zlib_compress;
extern const struct btrfs_compress_op btrfs_lzo_compress;
+extern const struct btrfs_compress_op btrfs_zstd_compress;
#endif
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 29b7fc2..878b23b9 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -270,6 +270,7 @@ struct btrfs_super_block {
BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS | \
BTRFS_FEATURE_INCOMPAT_BIG_METADATA | \
BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO | \
+ BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD | \
BTRFS_FEATURE_INCOMPAT_RAID56 | \
BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF | \
BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 08b74da..0c43e4e 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2853,6 +2853,8 @@ int open_ctree(struct super_block *sb,
features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
if (fs_info->compress_type == BTRFS_COMPRESS_LZO)
features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
+ else if (tree_root->fs_info->compress_type == BTRFS_COMPRESS_ZSTD)
+ features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD;
if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
btrfs_info(fs_info, "has skinny extents");
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index dabfc7a..d8ea727 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -327,8 +327,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
if (fs_info->compress_type == BTRFS_COMPRESS_LZO)
comp = "lzo";
- else
+ else if (fs_info->compress_type == BTRFS_COMPRESS_ZLIB)
comp = "zlib";
+ else
+ comp = "zstd";
ret = btrfs_set_prop(inode, "btrfs.compression",
comp, strlen(comp), 0);
if (ret)
@@ -1463,6 +1465,8 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
if (range->compress_type == BTRFS_COMPRESS_LZO) {
btrfs_set_fs_incompat(fs_info, COMPRESS_LZO);
+ } else if (range->compress_type == BTRFS_COMPRESS_ZSTD) {
+ btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD);
}
ret = defrag_count;
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index d6cb155..162105f 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -383,6 +383,8 @@ static int prop_compression_validate(const char *value, size_t len)
return 0;
else if (!strncmp("zlib", value, len))
return 0;
+ else if (!strncmp("zstd", value, len))
+ return 0;
return -EINVAL;
}
@@ -405,6 +407,8 @@ static int prop_compression_apply(struct inode *inode,
type = BTRFS_COMPRESS_LZO;
else if (!strncmp("zlib", value, len))
type = BTRFS_COMPRESS_ZLIB;
+ else if (!strncmp("zstd", value, len))
+ type = BTRFS_COMPRESS_ZSTD;
else
return -EINVAL;
@@ -422,6 +426,8 @@ static const char *prop_compression_extract(struct inode *inode)
return "zlib";
case BTRFS_COMPRESS_LZO:
return "lzo";
+ case BTRFS_COMPRESS_ZSTD:
+ return "zstd";
}
return NULL;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index da687dc..b064456 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -513,6 +513,14 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
btrfs_clear_opt(info->mount_opt, NODATASUM);
btrfs_set_fs_incompat(info, COMPRESS_LZO);
no_compress = 0;
+ } else if (strcmp(args[0].from, "zstd") == 0) {
+ compress_type = "zstd";
+ info->compress_type = BTRFS_COMPRESS_ZSTD;
+ btrfs_set_opt(info->mount_opt, COMPRESS);
+ btrfs_clear_opt(info->mount_opt, NODATACOW);
+ btrfs_clear_opt(info->mount_opt, NODATASUM);
+ btrfs_set_fs_incompat(info, COMPRESS_ZSTD);
+ no_compress = 0;
} else if (strncmp(args[0].from, "no", 2) == 0) {
compress_type = "no";
btrfs_clear_opt(info->mount_opt, COMPRESS);
@@ -1230,8 +1238,10 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
if (btrfs_test_opt(info, COMPRESS)) {
if (info->compress_type == BTRFS_COMPRESS_ZLIB)
compress_type = "zlib";
- else
+ else if (info->compress_type == BTRFS_COMPRESS_LZO)
compress_type = "lzo";
+ else
+ compress_type = "zstd";
if (btrfs_test_opt(info, FORCE_COMPRESS))
seq_printf(seq, ",compress-force=%s", compress_type);
else
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 1f157fb..b0dec90 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -200,6 +200,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(mixed_backref, MIXED_BACKREF);
BTRFS_FEAT_ATTR_INCOMPAT(default_subvol, DEFAULT_SUBVOL);
BTRFS_FEAT_ATTR_INCOMPAT(mixed_groups, MIXED_GROUPS);
BTRFS_FEAT_ATTR_INCOMPAT(compress_lzo, COMPRESS_LZO);
+BTRFS_FEAT_ATTR_INCOMPAT(compress_zstd, COMPRESS_ZSTD);
BTRFS_FEAT_ATTR_INCOMPAT(big_metadata, BIG_METADATA);
BTRFS_FEAT_ATTR_INCOMPAT(extended_iref, EXTENDED_IREF);
BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56);
@@ -212,6 +213,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = {
BTRFS_FEAT_ATTR_PTR(default_subvol),
BTRFS_FEAT_ATTR_PTR(mixed_groups),
BTRFS_FEAT_ATTR_PTR(compress_lzo),
+ BTRFS_FEAT_ATTR_PTR(compress_zstd),
BTRFS_FEAT_ATTR_PTR(big_metadata),
BTRFS_FEAT_ATTR_PTR(extended_iref),
BTRFS_FEAT_ATTR_PTR(raid56),
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
new file mode 100644
index 0000000..b7f319e
--- /dev/null
+++ b/fs/btrfs/zstd.c
@@ -0,0 +1,415 @@
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/init.h>
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <linux/pagemap.h>
+#include <linux/bio.h>
+#include <linux/zstd.h>
+#include "compression.h"
+
+#define ZSTD_BTRFS_MAX_WINDOWLOG 17
+#define ZSTD_BTRFS_MAX_INPUT (1 << ZSTD_BTRFS_MAX_WINDOWLOG)
+
+static ZSTD_parameters zstd_get_btrfs_parameters(size_t src_len)
+{
+ ZSTD_parameters params = ZSTD_getParams(3, src_len, 0);
+
+ if (params.cParams.windowLog > ZSTD_BTRFS_MAX_WINDOWLOG)
+ params.cParams.windowLog = ZSTD_BTRFS_MAX_WINDOWLOG;
+ WARN_ON(src_len > ZSTD_BTRFS_MAX_INPUT);
+ return params;
+}
+
+struct workspace {
+ void *mem;
+ size_t size;
+ char *buf;
+ struct list_head list;
+};
+
+static void zstd_free_workspace(struct list_head *ws)
+{
+ struct workspace *workspace = list_entry(ws, struct workspace, list);
+
+ vfree(workspace->mem);
+ kfree(workspace->buf);
+ kfree(workspace);
+}
+
+static struct list_head *zstd_alloc_workspace(void)
+{
+ ZSTD_parameters params =
+ zstd_get_btrfs_parameters(ZSTD_BTRFS_MAX_INPUT);
+ struct workspace *workspace;
+
+ workspace = kzalloc(sizeof(*workspace), GFP_NOFS);
+ if (!workspace)
+ return ERR_PTR(-ENOMEM);
+
+ workspace->size = max_t(size_t,
+ ZSTD_CStreamWorkspaceBound(params.cParams),
+ ZSTD_DStreamWorkspaceBound(ZSTD_BTRFS_MAX_INPUT));
+ workspace->mem = vmalloc(workspace->size);
+ workspace->buf = kmalloc(PAGE_SIZE, GFP_NOFS);
+ if (!workspace->mem || !workspace->buf)
+ goto fail;
+
+ INIT_LIST_HEAD(&workspace->list);
+
+ return &workspace->list;
+fail:
+ zstd_free_workspace(&workspace->list);
+ return ERR_PTR(-ENOMEM);
+}
+
+static int zstd_compress_pages(struct list_head *ws,
+ struct address_space *mapping,
+ u64 start,
+ struct page **pages,
+ unsigned long *out_pages,
+ unsigned long *total_in,
+ unsigned long *total_out)
+{
+ struct workspace *workspace = list_entry(ws, struct workspace, list);
+ ZSTD_CStream *stream;
+ int ret = 0;
+ int nr_pages = 0;
+ struct page *in_page = NULL; /* The current page to read */
+ struct page *out_page = NULL; /* The current page to write to */
+ ZSTD_inBuffer in_buf = { NULL, 0, 0 };
+ ZSTD_outBuffer out_buf = { NULL, 0, 0 };
+ unsigned long tot_in = 0;
+ unsigned long tot_out = 0;
+ unsigned long len = *total_out;
+ const unsigned long nr_dest_pages = *out_pages;
+ unsigned long max_out = nr_dest_pages * PAGE_SIZE;
+ ZSTD_parameters params = zstd_get_btrfs_parameters(len);
+
+ *out_pages = 0;
+ *total_out = 0;
+ *total_in = 0;
+
+ /* Initialize the stream */
+ stream = ZSTD_createCStream(params, len, workspace->mem,
+ workspace->size);
+ if (!stream) {
+ pr_warn("BTRFS: ZSTD_createStream failed\n");
+ ret = -EIO;
+ goto out;
+ }
+
+ /* map in the first page of input data */
+ in_page = find_get_page(mapping, start >> PAGE_SHIFT);
+ in_buf.src = kmap(in_page);
+ in_buf.pos = 0;
+ in_buf.size = min_t(size_t, len, PAGE_SIZE);
+
+
+ /* Allocate and map in the output buffer */
+ out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+ if (out_page == NULL) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ pages[nr_pages++] = out_page;
+ out_buf.dst = kmap(out_page);
+ out_buf.pos = 0;
+ out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
+
+ while (1) {
+ size_t ret2;
+
+ ret2 = ZSTD_compressStream(stream, &out_buf, &in_buf);
+ if (ZSTD_isError(ret2)) {
+ pr_debug("BTRFS: ZSTD_compressStream returned %d\n",
+ ZSTD_getErrorCode(ret2));
+ ret = -EIO;
+ goto out;
+ }
+
+ /* Check to see if we are making it bigger */
+ if (tot_in + in_buf.pos > 8192 &&
+ tot_in + in_buf.pos <
+ tot_out + out_buf.pos) {
+ ret = -E2BIG;
+ goto out;
+ }
+
+ /* We've reached the end of our output range */
+ if (out_buf.pos >= max_out) {
+ tot_out += out_buf.pos;
+ ret = -E2BIG;
+ goto out;
+ }
+
+ /* Check if we need more output space */
+ if (out_buf.pos == out_buf.size) {
+ tot_out += PAGE_SIZE;
+ max_out -= PAGE_SIZE;
+ kunmap(out_page);
+ if (nr_pages == nr_dest_pages) {
+ out_page = NULL;
+ ret = -E2BIG;
+ goto out;
+ }
+ out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+ if (out_page == NULL) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ pages[nr_pages++] = out_page;
+ out_buf.dst = kmap(out_page);
+ out_buf.pos = 0;
+ out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
+ }
+
+ /* We've reached the end of the input */
+ if (in_buf.pos >= len) {
+ tot_in += in_buf.pos;
+ break;
+ }
+
+ /* Check if we need more input */
+ if (in_buf.pos == in_buf.size) {
+ tot_in += PAGE_SIZE;
+ kunmap(in_page);
+ put_page(in_page);
+
+ start += PAGE_SIZE;
+ len -= PAGE_SIZE;
+ in_page = find_get_page(mapping, start >> PAGE_SHIFT);
+ in_buf.src = kmap(in_page);
+ in_buf.pos = 0;
+ in_buf.size = min_t(size_t, len, PAGE_SIZE);
+ }
+ }
+ while (1) {
+ size_t ret2;
+
+ ret2 = ZSTD_endStream(stream, &out_buf);
+ if (ZSTD_isError(ret2)) {
+ pr_debug("BTRFS: ZSTD_endStream returned %d\n",
+ ZSTD_getErrorCode(ret2));
+ ret = -EIO;
+ goto out;
+ }
+ if (ret2 == 0) {
+ tot_out += out_buf.pos;
+ break;
+ }
+ if (out_buf.pos >= max_out) {
+ tot_out += out_buf.pos;
+ ret = -E2BIG;
+ goto out;
+ }
+
+ tot_out += PAGE_SIZE;
+ max_out -= PAGE_SIZE;
+ kunmap(out_page);
+ if (nr_pages == nr_dest_pages) {
+ out_page = NULL;
+ ret = -E2BIG;
+ goto out;
+ }
+ out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+ if (out_page == NULL) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ pages[nr_pages++] = out_page;
+ out_buf.dst = kmap(out_page);
+ out_buf.pos = 0;
+ out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
+ }
+
+ if (tot_out >= tot_in) {
+ ret = -E2BIG;
+ goto out;
+ }
+
+ ret = 0;
+ *total_in = tot_in;
+ *total_out = tot_out;
+out:
+ *out_pages = nr_pages;
+ /* Cleanup */
+ if (in_page) {
+ kunmap(in_page);
+ put_page(in_page);
+ }
+ if (out_page)
+ kunmap(out_page);
+ return ret;
+}
+
+static int zstd_decompress_bio(struct list_head *ws, struct page **pages_in,
+ u64 disk_start,
+ struct bio *orig_bio,
+ size_t srclen)
+{
+ struct workspace *workspace = list_entry(ws, struct workspace, list);
+ ZSTD_DStream *stream;
+ int ret = 0;
+ unsigned long page_in_index = 0;
+ unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
+ unsigned long buf_start;
+ unsigned long total_out = 0;
+ ZSTD_inBuffer in_buf = { NULL, 0, 0 };
+ ZSTD_outBuffer out_buf = { NULL, 0, 0 };
+
+ stream = ZSTD_createDStream(
+ ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size);
+ if (!stream) {
+ pr_debug("BTRFS: ZSTD_createDStream failed\n");
+ ret = -EIO;
+ goto done;
+ }
+
+ in_buf.src = kmap(pages_in[page_in_index]);
+ in_buf.pos = 0;
+ in_buf.size = min_t(size_t, srclen, PAGE_SIZE);
+
+ out_buf.dst = workspace->buf;
+ out_buf.pos = 0;
+ out_buf.size = PAGE_SIZE;
+
+ while (1) {
+ size_t ret2;
+
+ ret2 = ZSTD_decompressStream(stream, &out_buf, &in_buf);
+ if (ZSTD_isError(ret2)) {
+ pr_debug("BTRFS: ZSTD_decompressStream returned %d\n",
+ ZSTD_getErrorCode(ret2));
+ ret = -EIO;
+ goto done;
+ }
+ buf_start = total_out;
+ total_out += out_buf.pos;
+ out_buf.pos = 0;
+
+ ret = btrfs_decompress_buf2page(out_buf.dst, buf_start,
+ total_out, disk_start, orig_bio);
+ if (ret == 0)
+ break;
+
+ if (in_buf.pos >= srclen)
+ break;
+
+ /* Check if we've hit the end of a frame */
+ if (ret2 == 0)
+ break;
+
+ if (in_buf.pos == in_buf.size) {
+ kunmap(pages_in[page_in_index++]);
+ if (page_in_index >= total_pages_in) {
+ in_buf.src = NULL;
+ ret = -EIO;
+ goto done;
+ }
+ srclen -= PAGE_SIZE;
+ in_buf.src = kmap(pages_in[page_in_index]);
+ in_buf.pos = 0;
+ in_buf.size = min_t(size_t, srclen, PAGE_SIZE);
+ }
+ }
+ ret = 0;
+ zero_fill_bio(orig_bio);
+done:
+ if (in_buf.src)
+ kunmap(pages_in[page_in_index]);
+ return ret;
+}
+
+static int zstd_decompress(struct list_head *ws, unsigned char *data_in,
+ struct page *dest_page,
+ unsigned long start_byte,
+ size_t srclen, size_t destlen)
+{
+ struct workspace *workspace = list_entry(ws, struct workspace, list);
+ ZSTD_DStream *stream;
+ int ret = 0;
+ size_t ret2;
+ ZSTD_inBuffer in_buf = { NULL, 0, 0 };
+ ZSTD_outBuffer out_buf = { NULL, 0, 0 };
+ unsigned long total_out = 0;
+ unsigned long pg_offset = 0;
+ char *kaddr;
+
+ stream = ZSTD_createDStream(
+ ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size);
+ if (!stream) {
+ pr_warn("BTRFS: ZSTD_createDStream failed\n");
+ ret = -EIO;
+ goto finish;
+ }
+
+ destlen = min_t(size_t, destlen, PAGE_SIZE);
+
+ in_buf.src = data_in;
+ in_buf.pos = 0;
+ in_buf.size = srclen;
+
+ out_buf.dst = workspace->buf;
+ out_buf.pos = 0;
+ out_buf.size = PAGE_SIZE;
+
+ ret2 = 1;
+ while (pg_offset < destlen && in_buf.pos < in_buf.size) {
+ unsigned long buf_start;
+ unsigned long buf_offset;
+ unsigned long bytes;
+
+ /* Check if the frame is over and we still need more input */
+ if (ret2 == 0) {
+ pr_debug("BTRFS: ZSTD_decompressStream ended early\n");
+ ret = -EIO;
+ goto finish;
+ }
+ ret2 = ZSTD_decompressStream(stream, &out_buf, &in_buf);
+ if (ZSTD_isError(ret2)) {
+ pr_debug("BTRFS: ZSTD_decompressStream returned %d\n",
+ ZSTD_getErrorCode(ret2));
+ ret = -EIO;
+ goto finish;
+ }
+
+ buf_start = total_out;
+ total_out += out_buf.pos;
+ out_buf.pos = 0;
+
+ if (total_out <= start_byte)
+ continue;
+
+ if (total_out > start_byte && buf_start < start_byte)
+ buf_offset = start_byte - buf_start;
+ else
+ buf_offset = 0;
+
+ bytes = min_t(unsigned long, destlen - pg_offset,
+ out_buf.size - buf_offset);
+
+ kaddr = kmap_atomic(dest_page);
+ memcpy(kaddr + pg_offset, out_buf.dst + buf_offset, bytes);
+ kunmap_atomic(kaddr);
+
+ pg_offset += bytes;
+ }
+ ret = 0;
+finish:
+ if (pg_offset < destlen) {
+ kaddr = kmap_atomic(dest_page);
+ memset(kaddr + pg_offset, 0, destlen - pg_offset);
+ kunmap_atomic(kaddr);
+ }
+ return ret;
+}
+
+const struct btrfs_compress_op btrfs_zstd_compress = {
+ .alloc_workspace = zstd_alloc_workspace,
+ .free_workspace = zstd_free_workspace,
+ .compress_pages = zstd_compress_pages,
+ .decompress_bio = zstd_decompress_bio,
+ .decompress = zstd_decompress,
+};
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index db4c253..f26c34f 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -255,13 +255,7 @@ struct btrfs_ioctl_fs_info_args {
#define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL (1ULL << 1)
#define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS (1ULL << 2)
#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO (1ULL << 3)
-/*
- * some patches floated around with a second compression method
- * lets save that incompat here for when they do get in
- * Note we don't actually support it, we're just reserving the
- * number
- */
-#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZOv2 (1ULL << 4)
+#define BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD (1ULL << 4)
/*
* older kernels tried to do bigger metadata blocks, but the

View File

@ -15,9 +15,10 @@
static ZSTD_parameters zstd_get_btrfs_parameters(size_t src_len)
{
ZSTD_parameters params = ZSTD_getParams(3, src_len, 0);
BUG_ON(src_len > ZSTD_BTRFS_MAX_INPUT);
BUG_ON(params.cParams.windowLog > ZSTD_BTRFS_MAX_WINDOWLOG);
params.fParams.checksumFlag = 1;
if (params.cParams.windowLog > ZSTD_BTRFS_MAX_WINDOWLOG)
params.cParams.windowLog = ZSTD_BTRFS_MAX_WINDOWLOG;
WARN_ON(src_len > ZSTD_BTRFS_MAX_INPUT);
return params;
}
@ -39,17 +40,21 @@ static void zstd_free_workspace(struct list_head *ws)
static struct list_head *zstd_alloc_workspace(void)
{
ZSTD_parameters params = zstd_get_btrfs_parameters(ZSTD_BTRFS_MAX_INPUT);
ZSTD_parameters params =
zstd_get_btrfs_parameters(ZSTD_BTRFS_MAX_INPUT);
struct workspace *workspace;
workspace = kzalloc(sizeof(*workspace), GFP_NOFS);
if (!workspace) return ERR_PTR(-ENOMEM);
if (!workspace)
return ERR_PTR(-ENOMEM);
workspace->size = max_t(size_t, ZSTD_CStreamWorkspaceBound(params.cParams),
workspace->size = max_t(size_t,
ZSTD_CStreamWorkspaceBound(params.cParams),
ZSTD_DStreamWorkspaceBound(ZSTD_BTRFS_MAX_INPUT));
workspace->mem = vmalloc(workspace->size);
workspace->buf = kmalloc(PAGE_SIZE, GFP_NOFS);
if (!workspace->mem || !workspace->buf) goto fail;
if (!workspace->mem || !workspace->buf)
goto fail;
INIT_LIST_HEAD(&workspace->list);
@ -61,16 +66,13 @@ fail:
static int zstd_compress_pages(struct list_head *ws,
struct address_space *mapping,
u64 start, unsigned long len,
u64 start,
struct page **pages,
unsigned long nr_dest_pages,
unsigned long *out_pages,
unsigned long *total_in,
unsigned long *total_out,
unsigned long max_out)
unsigned long *total_out)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
ZSTD_parameters params = zstd_get_btrfs_parameters(len);
ZSTD_CStream *stream;
int ret = 0;
int nr_pages = 0;
@ -80,13 +82,18 @@ static int zstd_compress_pages(struct list_head *ws,
ZSTD_outBuffer out_buf = { NULL, 0, 0 };
unsigned long tot_in = 0;
unsigned long tot_out = 0;
unsigned long len = *total_out;
const unsigned long nr_dest_pages = *out_pages;
unsigned long max_out = nr_dest_pages * PAGE_SIZE;
ZSTD_parameters params = zstd_get_btrfs_parameters(len);
*out_pages = 0;
*total_out = 0;
*total_in = 0;
/* Initialize the stream */
stream = ZSTD_createCStream(params, len, workspace->mem, workspace->size);
stream = ZSTD_createCStream(params, len, workspace->mem,
workspace->size);
if (!stream) {
pr_warn("BTRFS: ZSTD_createStream failed\n");
ret = -EIO;
@ -112,10 +119,12 @@ static int zstd_compress_pages(struct list_head *ws,
out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
while (1) {
const size_t rc = ZSTD_compressStream(stream, &out_buf, &in_buf);
if (ZSTD_isError(rc)) {
size_t ret2;
ret2 = ZSTD_compressStream(stream, &out_buf, &in_buf);
if (ZSTD_isError(ret2)) {
pr_debug("BTRFS: ZSTD_compressStream returned %d\n",
ZSTD_getErrorCode(rc));
ZSTD_getErrorCode(ret2));
ret = -EIO;
goto out;
}
@ -177,14 +186,16 @@ static int zstd_compress_pages(struct list_head *ws,
}
}
while (1) {
const size_t rc = ZSTD_endStream(stream, &out_buf);
if (ZSTD_isError(rc)) {
size_t ret2;
ret2 = ZSTD_endStream(stream, &out_buf);
if (ZSTD_isError(ret2)) {
pr_debug("BTRFS: ZSTD_endStream returned %d\n",
ZSTD_getErrorCode(rc));
ZSTD_getErrorCode(ret2));
ret = -EIO;
goto out;
}
if (rc == 0) {
if (ret2 == 0) {
tot_out += out_buf.pos;
break;
}
@ -228,24 +239,22 @@ out:
kunmap(in_page);
put_page(in_page);
}
if (out_page) { kunmap(out_page); }
if (out_page)
kunmap(out_page);
return ret;
}
static int zstd_decompress_biovec(struct list_head *ws, struct page **pages_in,
static int zstd_decompress_bio(struct list_head *ws, struct page **pages_in,
u64 disk_start,
struct bio_vec *bvec,
int vcnt,
struct bio *orig_bio,
size_t srclen)
{
struct workspace *workspace = list_entry(ws, struct workspace, list);
ZSTD_DStream *stream;
int ret = 0;
unsigned long page_in_index = 0;
unsigned long page_out_index = 0;
unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
unsigned long buf_start;
unsigned long pg_offset;
unsigned long total_out = 0;
ZSTD_inBuffer in_buf = { NULL, 0, 0 };
ZSTD_outBuffer out_buf = { NULL, 0, 0 };
@ -266,13 +275,13 @@ static int zstd_decompress_biovec(struct list_head *ws, struct page **pages_in,
out_buf.pos = 0;
out_buf.size = PAGE_SIZE;
pg_offset = 0;
while (1) {
const size_t rc = ZSTD_decompressStream(stream, &out_buf, &in_buf);
if (ZSTD_isError(rc)) {
size_t ret2;
ret2 = ZSTD_decompressStream(stream, &out_buf, &in_buf);
if (ZSTD_isError(ret2)) {
pr_debug("BTRFS: ZSTD_decompressStream returned %d\n",
ZSTD_getErrorCode(rc));
ZSTD_getErrorCode(ret2));
ret = -EIO;
goto done;
}
@ -280,23 +289,17 @@ static int zstd_decompress_biovec(struct list_head *ws, struct page **pages_in,
total_out += out_buf.pos;
out_buf.pos = 0;
{
int ret2 = btrfs_decompress_buf2page(out_buf.dst, buf_start,
total_out, disk_start, bvec, vcnt,
&page_out_index, &pg_offset);
if (ret2 == 0) {
break;
}
}
if (in_buf.pos >= srclen) {
ret = btrfs_decompress_buf2page(out_buf.dst, buf_start,
total_out, disk_start, orig_bio);
if (ret == 0)
break;
if (in_buf.pos >= srclen)
break;
}
/* Check if we've hit the end of a frame */
if (rc == 0) {
if (ret2 == 0)
break;
}
if (in_buf.pos == in_buf.size) {
kunmap(pages_in[page_in_index++]);
@ -311,10 +314,11 @@ static int zstd_decompress_biovec(struct list_head *ws, struct page **pages_in,
in_buf.size = min_t(size_t, srclen, PAGE_SIZE);
}
}
btrfs_clear_biovec_end(bvec, vcnt, page_out_index, pg_offset);
ret = 0;
zero_fill_bio(orig_bio);
done:
if (in_buf.src) { kunmap(pages_in[page_in_index]); }
if (in_buf.src)
kunmap(pages_in[page_in_index]);
return ret;
}
@ -326,6 +330,7 @@ static int zstd_decompress(struct list_head *ws, unsigned char *data_in,
struct workspace *workspace = list_entry(ws, struct workspace, list);
ZSTD_DStream *stream;
int ret = 0;
size_t ret2;
ZSTD_inBuffer in_buf = { NULL, 0, 0 };
ZSTD_outBuffer out_buf = { NULL, 0, 0 };
unsigned long total_out = 0;
@ -350,41 +355,37 @@ static int zstd_decompress(struct list_head *ws, unsigned char *data_in,
out_buf.pos = 0;
out_buf.size = PAGE_SIZE;
ret = 1;
ret2 = 1;
while (pg_offset < destlen && in_buf.pos < in_buf.size) {
unsigned long buf_start;
unsigned long buf_offset;
unsigned long bytes;
/* Check if the frame is over and we still need more input */
if (ret == 0) {
pr_debug("BTRFS: ZSTD_decompressStream frame ended to early\n");
if (ret2 == 0) {
pr_debug("BTRFS: ZSTD_decompressStream ended early\n");
ret = -EIO;
goto finish;
}
{
const size_t rc = ZSTD_decompressStream(stream, &out_buf, &in_buf);
if (ZSTD_isError(rc)) {
pr_debug("BTRFS: ZSTD_decompressStream returned %d\n",
ZSTD_getErrorCode(rc));
ret = -EIO;
goto finish;
}
ret = rc > 0;
ret2 = ZSTD_decompressStream(stream, &out_buf, &in_buf);
if (ZSTD_isError(ret2)) {
pr_debug("BTRFS: ZSTD_decompressStream returned %d\n",
ZSTD_getErrorCode(ret2));
ret = -EIO;
goto finish;
}
buf_start = total_out;
total_out += out_buf.pos;
out_buf.pos = 0;
if (total_out <= start_byte) {
if (total_out <= start_byte)
continue;
}
if (total_out > start_byte && buf_start < start_byte) {
if (total_out > start_byte && buf_start < start_byte)
buf_offset = start_byte - buf_start;
} else {
else
buf_offset = 0;
}
bytes = min_t(unsigned long, destlen - pg_offset,
out_buf.size - buf_offset);
@ -409,6 +410,6 @@ const struct btrfs_compress_op btrfs_zstd_compress = {
.alloc_workspace = zstd_alloc_workspace,
.free_workspace = zstd_free_workspace,
.compress_pages = zstd_compress_pages,
.decompress_biovec = zstd_decompress_biovec,
.decompress_bio = zstd_decompress_bio,
.decompress = zstd_decompress,
};

File diff suppressed because it is too large Load Diff

View File

@ -1399,7 +1399,7 @@ size_t ZSTD_decompressBlock(ZSTD_DCtx* dctx,
/** ZSTD_insertBlock() :
insert `src` block into `dctx` history. Useful to track uncompressed blocks. */
ZSTDLIB_API size_t ZSTD_insertBlock(ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize)
size_t ZSTD_insertBlock(ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize)
{
ZSTD_checkContinuity(dctx, blockStart);
dctx->previousDstEnd = (const char*)blockStart + blockSize;