<feed xmlns='http://www.w3.org/2005/Atom'>
<title>src/sys/dev/liquidio, branch releng/12.4</title>
<subtitle>FreeBSD source tree</subtitle>
<id>https://cgit-dev.freebsd.org/src/atom?h=releng%2F12.4</id>
<link rel='self' href='https://cgit-dev.freebsd.org/src/atom?h=releng%2F12.4'/>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/'/>
<updated>2022-04-10T04:16:24Z</updated>
<entry>
<title>Unify zlib instances into one.</title>
<updated>2022-04-10T04:16:24Z</updated>
<author>
<name>Xin LI</name>
<email>delphij@FreeBSD.org</email>
</author>
<published>2019-08-25T17:13:00Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=254a1740cde85300587fcf4e3ad3b91453fa5d09'/>
<id>urn:sha1:254a1740cde85300587fcf4e3ad3b91453fa5d09</id>
<content type='text'>
This is a cumulative update that consists 14 commits on main by
Yoshihiro Ota and myself to stable/12:

Remove gzip'ed a.out support.

(cherry picked from commit d4565741c6b4b256bd30aea8eb74e8a267cf6b60)

Delete unneeded #include &lt;sys/inflate.h&gt; from sys/mips.

(cherry picked from commit 880c6c1b06d203fd6b628d313b5b2658fb7135cb)

cryptodeflate: Drop z_stream zbuf.state-&gt;dummy from SDT probe.

(cherry picked from commit a49818787d7cff34b9ea9878e37c1c1ba221f081)

Remove kgzip and kgzldr.

(cherry picked from commit 5e86bd6073a2fb107318691aaa27b7e19bd45c24)

Separate kernel crc32() implementation to its own header (gsb_crc32.h) and
rename the source to gsb_crc32.c.

(cherry picked from commit f89d2072795407d7c3afff865b988e021c1451a2)

Allow Kernel to link in both legacy libkern/zlib and new sys/contrib/zlib.

(cherry picked from commit 0ed1d6fb00b8f22c82c3f9054c6dd16eb12469d2)

if_mxge: update zlib version 1.0.4 to 1.2.12.

(cherry picked from commit 1dbf944a91cfccba2c18fa273f69985cd15a5081)

Expose zlib's utility functions in Z_SOLO library when building kernel.
This allows kernel code to reuse zlib's implementation.

(cherry picked from commit a15cb219c6f2b8ed16179c2fce882a2ff327b753)

Update geom_uzip to use new zlib.

(cherry picked from commit 2b0cabbdaeac61bdb07909cb0ec995aba36e06b0)

Update bxe(4) to use new zlib.

(cherry picked from commit 92e9c0608bf161df04d14160084da2d50bcad30e)

Convert DDB_CTF to use newer version of ZLIB.

(cherry picked from commit 22bbc4b24270ec55c267a5b4ca4530991c3da408)

Convert ng_deflate to use new zlib.

(cherry picked from commit 34ff55b662d62adea206cb2b77bb064110f68e6d)

GZIO: Update to use zlib 1.2.12.

(cherry picked from commit 4e8671dd78cc77b31c598e83354fa6722acd4e3f)

Remove zlib 1.0.4 from kernel.

(cherry picked from commit 21aae72489aba9f1711c51672b3003cf8d54965d)

PR:		205822
PR:		229763
</content>
</entry>
<entry>
<title>Fix some common typos in source code comments</title>
<updated>2021-08-19T07:35:05Z</updated>
<author>
<name>Gordon Bergling</name>
<email>gbe@FreeBSD.org</email>
</author>
<published>2021-08-14T06:55:58Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=54e111ec0c74dc7ae50758aaaa8d34571a3bc3b0'/>
<id>urn:sha1:54e111ec0c74dc7ae50758aaaa8d34571a3bc3b0</id>
<content type='text'>
- s/struture/structure/
- s/structre/structure/

(cherry picked from commit 17db4b52fb41aeabeb945c68c1b5edd4db4eac31)
</content>
</entry>
<entry>
<title>Eliminate the arena parameter to kmem_free().  Implicitly this corrects an</title>
<updated>2018-08-25T19:38:08Z</updated>
<author>
<name>Alan Cox</name>
<email>alc@FreeBSD.org</email>
</author>
<published>2018-08-25T19:38:08Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=49bfa624ac861d7fafc87f06dc2cdf4972aed854'/>
<id>urn:sha1:49bfa624ac861d7fafc87f06dc2cdf4972aed854</id>
<content type='text'>
error in the function hypercall_memfree(), where the wrong arena was being
passed to kmem_free().

Introduce a per-page flag, VPO_KMEM_EXEC, to mark physical pages that are
mapped in kmem with execute permissions.  Use this flag to determine which
arena the kmem virtual addresses are returned to.

Eliminate UMA_SLAB_KRWX.  The introduction of VPO_KMEM_EXEC makes it
redundant.

Update the nearby comment for UMA_SLAB_KERNEL.

Reviewed by:	kib, markj
Discussed with:	jeff
Approved by:	re (marius)
Differential Revision:	https://reviews.freebsd.org/D16845
</content>
</entry>
<entry>
<title>Eliminate kmem_alloc_contig()'s unused arena parameter.</title>
<updated>2018-08-20T15:57:27Z</updated>
<author>
<name>Alan Cox</name>
<email>alc@FreeBSD.org</email>
</author>
<published>2018-08-20T15:57:27Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=44d0efb2154d884c85919229f28b31d50d25a350'/>
<id>urn:sha1:44d0efb2154d884c85919229f28b31d50d25a350</id>
<content type='text'>
Reviewed by:	hselasky, kib, markj
Discussed with:	jeff
Differential Revision:	https://reviews.freebsd.org/D16799
</content>
</entry>
<entry>
<title>Fix build of liquidio with base gcc on i386</title>
<updated>2018-06-13T07:55:57Z</updated>
<author>
<name>Dimitry Andric</name>
<email>dim@FreeBSD.org</email>
</author>
<published>2018-06-13T07:55:57Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=2b6fe1b2da8fcf8e8b075c4e653ab2c65bdc00a8'/>
<id>urn:sha1:2b6fe1b2da8fcf8e8b075c4e653ab2c65bdc00a8</id>
<content type='text'>
Some casts from pointers to uint64_t and back in lio_main.c cause base
gcc on i386 to warn "cast from pointer to integer of different size",
and vice versa.  Add additional casts to uintptr_t to suppress these.

Reviewed by:	sbruno
MFC after:	3 days
Differential Revision: https://reviews.freebsd.org/D15754
</content>
</entry>
<entry>
<title>tcp_lro.h requires &lt;netinet/in.h&gt;, include it directly instead of</title>
<updated>2018-06-05T19:23:23Z</updated>
<author>
<name>Andrey V. Elsukov</name>
<email>ae@FreeBSD.org</email>
</author>
<published>2018-06-05T19:23:23Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=9f855fb282de1e5fa854b737dec66fb11aaf51e2'/>
<id>urn:sha1:9f855fb282de1e5fa854b737dec66fb11aaf51e2</id>
<content type='text'>
indirect inclusion trough if_gif.h
</content>
</entry>
<entry>
<title>ifnet: Replace if_addr_lock rwlock with epoch + mutex</title>
<updated>2018-05-18T20:13:34Z</updated>
<author>
<name>Matt Macy</name>
<email>mmacy@FreeBSD.org</email>
</author>
<published>2018-05-18T20:13:34Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=d7c5a620e2b99e914f1770abde956cf0d0a970b7'/>
<id>urn:sha1:d7c5a620e2b99e914f1770abde956cf0d0a970b7</id>
<content type='text'>
Run on LLNW canaries and tested by pho@

gallatin:
Using a 14-core, 28-HTT single socket E5-2697 v3 with a 40GbE MLX5
based ConnectX 4-LX NIC, I see an almost 12% improvement in received
packet rate, and a larger improvement in bytes delivered all the way
to userspace.

When the host receiving 64 streams of netperf -H $DUT -t UDP_STREAM -- -m 1,
I see, using nstat -I mce0 1 before the patch:

InMpps OMpps  InGbs  OGbs err TCP Est %CPU syscalls csw     irq GBfree
4.98   0.00   4.42   0.00 4235592     33   83.80 4720653 2149771   1235 247.32
4.73   0.00   4.20   0.00 4025260     33   82.99 4724900 2139833   1204 247.32
4.72   0.00   4.20   0.00 4035252     33   82.14 4719162 2132023   1264 247.32
4.71   0.00   4.21   0.00 4073206     33   83.68 4744973 2123317   1347 247.32
4.72   0.00   4.21   0.00 4061118     33   80.82 4713615 2188091   1490 247.32
4.72   0.00   4.21   0.00 4051675     33   85.29 4727399 2109011   1205 247.32
4.73   0.00   4.21   0.00 4039056     33   84.65 4724735 2102603   1053 247.32

After the patch

InMpps OMpps  InGbs  OGbs err TCP Est %CPU syscalls csw     irq GBfree
5.43   0.00   4.20   0.00 3313143     33   84.96 5434214 1900162   2656 245.51
5.43   0.00   4.20   0.00 3308527     33   85.24 5439695 1809382   2521 245.51
5.42   0.00   4.19   0.00 3316778     33   87.54 5416028 1805835   2256 245.51
5.42   0.00   4.19   0.00 3317673     33   90.44 5426044 1763056   2332 245.51
5.42   0.00   4.19   0.00 3314839     33   88.11 5435732 1792218   2499 245.52
5.44   0.00   4.19   0.00 3293228     33   91.84 5426301 1668597   2121 245.52

Similarly, netperf reports 230Mb/s before the patch, and 270Mb/s after the patch

Reviewed by:	gallatin
Sponsored by:	Limelight Networks
Differential Revision:	https://reviews.freebsd.org/D15366
</content>
</entry>
<entry>
<title>Revert r327828, r327949, r327953, r328016-r328026, r328041:</title>
<updated>2018-01-21T15:42:36Z</updated>
<author>
<name>Pedro F. Giffuni</name>
<email>pfg@FreeBSD.org</email>
</author>
<published>2018-01-21T15:42:36Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=ac2fffa4b74cd83963f0d462c379c7f50eeabf20'/>
<id>urn:sha1:ac2fffa4b74cd83963f0d462c379c7f50eeabf20</id>
<content type='text'>
Uses of mallocarray(9).

The use of mallocarray(9) has rocketed the required swap to build FreeBSD.
This is likely caused by the allocation size attributes which put extra pressure
on the compiler.

Given that most of these checks are superfluous we have to choose better
where to use mallocarray(9). We still have more uses of mallocarray(9) but
hopefully this is enough to bring swap usage to a reasonable level.

Reported by:	wosch
PR:		225197
</content>
</entry>
<entry>
<title>dev: make some use of mallocarray(9).</title>
<updated>2018-01-13T22:30:30Z</updated>
<author>
<name>Pedro F. Giffuni</name>
<email>pfg@FreeBSD.org</email>
</author>
<published>2018-01-13T22:30:30Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=26c1d774b55c4db79bca772941883244986e6f44'/>
<id>urn:sha1:26c1d774b55c4db79bca772941883244986e6f44</id>
<content type='text'>
Focus on code where we are doing multiplications within malloc(9). None of
these is likely to overflow, however the change is still useful as some
static checkers can benefit from the allocation attributes we use for
mallocarray.

This initial sweep only covers malloc(9) calls with M_NOWAIT. No good
reason but I started doing the changes before r327796 and at that time it
was convenient to make sure the sorrounding code could handle NULL values.
</content>
</entry>
<entry>
<title>Enable i386 build of the Cavium LiquidIO driver (lio) module.</title>
<updated>2017-10-25T17:49:17Z</updated>
<author>
<name>Sean Bruno</name>
<email>sbruno@FreeBSD.org</email>
</author>
<published>2017-10-25T17:49:17Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=3de0952fba9607fbcad3009366bc9c4d9c899b27'/>
<id>urn:sha1:3de0952fba9607fbcad3009366bc9c4d9c899b27</id>
<content type='text'>
Submitted by:	pkanneganti@cavium.com (Prasad V Kanneganti)
MFC after:	1 week
Sponsored by:	Cavium Networks
Differential Revision:	https://reviews.freebsd.org/D12415
</content>
</entry>
</feed>
