<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux-toradex.git/drivers/block/zram/backend_zstd.c, branch v6.13-rc2</title>
<subtitle>Linux kernel for Apalis and Colibri modules</subtitle>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/'/>
<entry>
<title>zram: add dictionary support to zstd backend</title>
<updated>2024-09-09T23:39:11+00:00</updated>
<author>
<name>Sergey Senozhatsky</name>
<email>senozhatsky@chromium.org</email>
</author>
<published>2024-09-02T10:56:10+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=6a559ecd6e7ec26b691add74eab8ee3eb5dd2a87'/>
<id>6a559ecd6e7ec26b691add74eab8ee3eb5dd2a87</id>
<content type='text'>
This adds support for pre-trained zstd dictionaries [1] Dictionary is
setup in params once (per-comp) and loaded to Cctx and Dctx by reference,
so we don't allocate extra memory.

TEST
====

*** zstd
/sys/block/zram0/mm_stat
1750654976 504565092 514203648        0 514203648        1        0    34204    34204

*** zstd dict=/etc/zstd-dict-amd64
/sys/block/zram0/mm_stat
1750638592 465851259 475373568        0 475373568        1        0    34185    34185

*** zstd level=8 dict=/etc/zstd-dict-amd64
/sys/block/zram0/mm_stat
1750642688 430765171 439955456        0 439955456        1        0    34185    34185

[1] https://github.com/facebook/zstd/blob/dev/programs/zstd.1.md#dictionary-builder

Link: https://lkml.kernel.org/r/20240902105656.1383858-23-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This adds support for pre-trained zstd dictionaries [1] Dictionary is
setup in params once (per-comp) and loaded to Cctx and Dctx by reference,
so we don't allocate extra memory.

TEST
====

*** zstd
/sys/block/zram0/mm_stat
1750654976 504565092 514203648        0 514203648        1        0    34204    34204

*** zstd dict=/etc/zstd-dict-amd64
/sys/block/zram0/mm_stat
1750638592 465851259 475373568        0 475373568        1        0    34185    34185

*** zstd level=8 dict=/etc/zstd-dict-amd64
/sys/block/zram0/mm_stat
1750642688 430765171 439955456        0 439955456        1        0    34185    34185

[1] https://github.com/facebook/zstd/blob/dev/programs/zstd.1.md#dictionary-builder

Link: https://lkml.kernel.org/r/20240902105656.1383858-23-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>zram: move immutable comp params away from per-CPU context</title>
<updated>2024-09-09T23:39:10+00:00</updated>
<author>
<name>Sergey Senozhatsky</name>
<email>senozhatsky@chromium.org</email>
</author>
<published>2024-09-02T10:56:07+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=b8f03cb703a160e14f87a467a4443adc5d940087'/>
<id>b8f03cb703a160e14f87a467a4443adc5d940087</id>
<content type='text'>
Immutable params never change once comp has been allocated and setup, so
we don't need to store multiple copies of them in each per-CPU backend
context.  Move those to per-comp zcomp_params and pass it to backends
callbacks for requests execution.  Basically, this means parameters
sharing between different contexts.

Also introduce two new backends callbacks: setup_params() and
release_params().  First, we need to validate params in a driver-specific
way; second, driver may want to allocate its specific representation of
the params which is needed to execute requests.

Link: https://lkml.kernel.org/r/20240902105656.1383858-20-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Immutable params never change once comp has been allocated and setup, so
we don't need to store multiple copies of them in each per-CPU backend
context.  Move those to per-comp zcomp_params and pass it to backends
callbacks for requests execution.  Basically, this means parameters
sharing between different contexts.

Also introduce two new backends callbacks: setup_params() and
release_params().  First, we need to validate params in a driver-specific
way; second, driver may want to allocate its specific representation of
the params which is needed to execute requests.

Link: https://lkml.kernel.org/r/20240902105656.1383858-20-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>zram: introduce zcomp_ctx structure</title>
<updated>2024-09-09T23:39:10+00:00</updated>
<author>
<name>Sergey Senozhatsky</name>
<email>senozhatsky@chromium.org</email>
</author>
<published>2024-09-02T10:56:06+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=6a81bdfeb35094c3097650306a5fda9a990d8a97'/>
<id>6a81bdfeb35094c3097650306a5fda9a990d8a97</id>
<content type='text'>
Keep run-time driver data (scratch buffers, etc.) in zcomp_ctx structure. 
This structure is allocated per-CPU because drivers (backends) need to
modify its content during requests execution.

We will split mutable and immutable driver data, this is a preparation
path.

Link: https://lkml.kernel.org/r/20240902105656.1383858-19-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Keep run-time driver data (scratch buffers, etc.) in zcomp_ctx structure. 
This structure is allocated per-CPU because drivers (backends) need to
modify its content during requests execution.

We will split mutable and immutable driver data, this is a preparation
path.

Link: https://lkml.kernel.org/r/20240902105656.1383858-19-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>zram: introduce zcomp_req structure</title>
<updated>2024-09-09T23:39:10+00:00</updated>
<author>
<name>Sergey Senozhatsky</name>
<email>senozhatsky@chromium.org</email>
</author>
<published>2024-09-02T10:56:05+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=52c7b4e2ba508a924c991e681db534e66a851adf'/>
<id>52c7b4e2ba508a924c991e681db534e66a851adf</id>
<content type='text'>
Encapsulate compression/decompression data in zcomp_req structure.

Link: https://lkml.kernel.org/r/20240902105656.1383858-18-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Encapsulate compression/decompression data in zcomp_req structure.

Link: https://lkml.kernel.org/r/20240902105656.1383858-18-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>zram: recalculate zstd compression params once</title>
<updated>2024-09-09T23:39:09+00:00</updated>
<author>
<name>Sergey Senozhatsky</name>
<email>senozhatsky@chromium.org</email>
</author>
<published>2024-09-02T10:56:02+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=eb826a01909a2d39660ed5a486ebc43e831254bc'/>
<id>eb826a01909a2d39660ed5a486ebc43e831254bc</id>
<content type='text'>
zstd compression params depends on level, but are constant for a given
instance of zstd compression backend.  Calculate once (during ctx
creation).

Link: https://lkml.kernel.org/r/20240902105656.1383858-15-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
zstd compression params depends on level, but are constant for a given
instance of zstd compression backend.  Calculate once (during ctx
creation).

Link: https://lkml.kernel.org/r/20240902105656.1383858-15-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>zram: introduce zcomp_params structure</title>
<updated>2024-09-09T23:39:09+00:00</updated>
<author>
<name>Sergey Senozhatsky</name>
<email>senozhatsky@chromium.org</email>
</author>
<published>2024-09-02T10:56:01+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=f2bac7ad187d77e2a053d3cd04b158a06b683d26'/>
<id>f2bac7ad187d77e2a053d3cd04b158a06b683d26</id>
<content type='text'>
We will store a per-algorithm parameters there (compression level,
dictionary, dictionary size, etc.).

Link: https://lkml.kernel.org/r/20240902105656.1383858-14-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
We will store a per-algorithm parameters there (compression level,
dictionary, dictionary size, etc.).

Link: https://lkml.kernel.org/r/20240902105656.1383858-14-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>zram: pass estimated src size hint to zstd</title>
<updated>2024-09-09T23:39:08+00:00</updated>
<author>
<name>Sergey Senozhatsky</name>
<email>senozhatsky@chromium.org</email>
</author>
<published>2024-09-02T10:55:57+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=dbf2763cec21f4e56420c3a31bf6f0ebf81b5ab7'/>
<id>dbf2763cec21f4e56420c3a31bf6f0ebf81b5ab7</id>
<content type='text'>
zram works with PAGE_SIZE buffers, so we always know exact size of the
source buffer and hence can pass estimated_src_size to zstd_get_params().

This hint on x86_64, for example, reduces the size of the work memory
buffer from 1303520 bytes down to 90080 bytes.  Given that compression
streams are per-CPU that's quite some memory saving.

Link: https://lkml.kernel.org/r/20240902105656.1383858-10-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
zram works with PAGE_SIZE buffers, so we always know exact size of the
source buffer and hence can pass estimated_src_size to zstd_get_params().

This hint on x86_64, for example, reduces the size of the work memory
buffer from 1303520 bytes down to 90080 bytes.  Given that compression
streams are per-CPU that's quite some memory saving.

Link: https://lkml.kernel.org/r/20240902105656.1383858-10-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>zram: add zstd compression backend support</title>
<updated>2024-09-09T23:39:08+00:00</updated>
<author>
<name>Sergey Senozhatsky</name>
<email>senozhatsky@chromium.org</email>
</author>
<published>2024-09-02T10:55:56+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=73e7d81abbc80b04595cc7da09dcaa05a3a92602'/>
<id>73e7d81abbc80b04595cc7da09dcaa05a3a92602</id>
<content type='text'>
Add s/w zstd compression.

Link: https://lkml.kernel.org/r/20240902105656.1383858-9-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add s/w zstd compression.

Link: https://lkml.kernel.org/r/20240902105656.1383858-9-senozhatsky@chromium.org
Signed-off-by: Sergey Senozhatsky &lt;senozhatsky@chromium.org&gt;
Cc: Minchan Kim &lt;minchan@kernel.org&gt;
Cc: Nick Terrell &lt;terrelln@fb.com&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
</pre>
</div>
</content>
</entry>
</feed>
