mjoras (Matt Joras)
User

Projects

User Details

User Since
Mar 18 2016, 8:59 PM (95 w, 5 d)

Recent Activity

Nov 9 2017

mjoras committed rS325622: Correct mistake in manpage..
Correct mistake in manpage.
Nov 9 2017, 11:36 PM
mjoras committed rS325621: Introduce EVENTHANDLER_LIST and some users..
Introduce EVENTHANDLER_LIST and some users.
Nov 9 2017, 10:52 PM
mjoras closed D12814: Introduce EVENTHANDLER_LIST_* and some users..
Nov 9 2017, 10:52 PM
mjoras added a comment to D12973: bnxt: While VLAN TCP Tx is progress, "ifconfig destroy" caused kernel Crash in Iflib code.

First off, please submit future patches with arc diff directly, or with a diff generated with full context.

Nov 9 2017, 8:41 PM

Nov 3 2017

mjoras updated the diff for D12814: Introduce EVENTHANDLER_LIST_* and some users..
  • in order to be MFCable we can't change the eventhandler_list layout.
Nov 3 2017, 4:47 PM

Nov 1 2017

mjoras added inline comments to D12814: Introduce EVENTHANDLER_LIST_* and some users..
Nov 1 2017, 8:41 PM
mjoras updated the diff for D12814: Introduce EVENTHANDLER_LIST_* and some users..
  • style fixups.
Nov 1 2017, 7:01 PM
mjoras updated the diff for D12814: Introduce EVENTHANDLER_LIST_* and some users..
  • manpage style and extraneous use of "relative"
  • remove the flags field as it is not needed.
Nov 1 2017, 6:57 PM
mjoras added inline comments to D12814: Introduce EVENTHANDLER_LIST_* and some users..
Nov 1 2017, 6:50 PM
mjoras updated the diff for D12814: Introduce EVENTHANDLER_LIST_* and some users..
  • style nit
Nov 1 2017, 6:12 PM
mjoras added a reviewer for D12814: Introduce EVENTHANDLER_LIST_* and some users.: ian.
Nov 1 2017, 6:04 PM
mjoras retitled D12814: Introduce EVENTHANDLER_LIST_* and some users. from Introduce EVENTHANDLER_STATIC_* and some users. to Introduce EVENTHANDLER_LIST_* and some users..
Nov 1 2017, 5:57 PM
mjoras updated the diff for D12814: Introduce EVENTHANDLER_LIST_* and some users..
  • use a pointer as the global reference to the pre-defined list, allowing for these lists to be created on-register (e.g. from a module) before they are defined. This was the approach suggested and taken by ian in his revision.
  • refactor API usage to reflect this change. LISTS are now defined and declared separately from the eventhandlers. The corresponding invoke is EVENTHANDLER_DIRECT_INVOKE since I think EVENTHANDLER_LIST_INVOKE is too confusing (whereas DIRECT can reasonably imply direct disaptch-ish semantics).
  • Now you must use EVENTHANDLER_LIST_DEFINE to create the reference to the list. EVENTHANDLER_LIST_DECLARE is only needed to declare the list pointer extern, so for callers of EVENTHANDLER_DIRECT_INVOKE that are not in the same compilation unit as the DEFINE.
  • small change to make the eventhandler list name stored at the end of the struct, since the storage is always allocated at the end of the struct anyway.
  • remove EHL_INITTED since it is no longer a relevant state (the lists are initialized either by the SYSINIT stage for eventhandler or when the first handler is registered).
  • update EVENTHANDLER(9) to reflect the API addition, with the recommendation to use the EVENTHANDLER_LIST/DIRECT macros.
Nov 1 2017, 5:47 PM

Oct 31 2017

mjoras added a comment to D12814: Introduce EVENTHANDLER_LIST_* and some users..

Seems ok to me. Do you plan to update this further in light of Ian's similar patch?

+1 to the man page update.

Oct 31 2017, 3:24 PM

Oct 30 2017

mjoras accepted D12831: bluetooth: Default to discoverable off.

Plz

Oct 30 2017, 4:50 AM

Oct 28 2017

mjoras created D12814: Introduce EVENTHANDLER_LIST_* and some users..
Oct 28 2017, 3:40 AM

Oct 23 2017

mjoras committed rS324921: Move clear_unrhdr to tmpfs_free_tmp..
Move clear_unrhdr to tmpfs_free_tmp.
Oct 23 2017, 3:43 PM
mjoras closed D12749: Move clear_unrhdr to tmpfs_free_tmp..
Oct 23 2017, 3:43 PM

Oct 22 2017

mjoras added inline comments to D12753: kernel macro cleanliness, first pass.
Oct 22 2017, 8:24 PM
mjoras added inline comments to D12753: kernel macro cleanliness, first pass.
Oct 22 2017, 3:48 PM
mjoras accepted D12753: kernel macro cleanliness, first pass.

I'd rather not turn my (perhaps radical) parentheses opinions into a bikeshed. At the least I request not adding new ones that aren't needed, but if kib or someone else prefers they stay I won't get in the way.

Oct 22 2017, 3:37 PM
mjoras added inline comments to D12753: kernel macro cleanliness, first pass.
Oct 22 2017, 3:29 PM
mjoras updated the test plan for D12749: Move clear_unrhdr to tmpfs_free_tmp..
Oct 22 2017, 1:47 AM
mjoras requested changes to D12753: kernel macro cleanliness, first pass.

The superfluous parentheses stuff is sort of nitpicky, but I do feel that at least in the case where the expansion is surrounded by commas then it should be dropped since comma operators / separators have the lowest possible precedence.

Oct 22 2017, 1:19 AM

Oct 20 2017

mjoras updated the diff for D12749: Move clear_unrhdr to tmpfs_free_tmp..
  • whitespace
Oct 20 2017, 10:48 PM
mjoras created D12749: Move clear_unrhdr to tmpfs_free_tmp..
Oct 20 2017, 10:47 PM
mjoras edited P149 Masterwork From Distant Lands.
Oct 20 2017, 2:35 AM
mjoras edited P148 Masterwork From Distant Lands.
Oct 20 2017, 1:47 AM

Oct 19 2017

mjoras edited P147 Masterwork From Distant Lands.
Oct 19 2017, 7:03 PM

Oct 16 2017

mjoras closed D12662: Properly reset fields in clean_unrhdr..
Oct 16 2017, 4:23 PM
mjoras committed rS324666: Properly reset the fields in clean_unrhdr..
Properly reset the fields in clean_unrhdr.
Oct 16 2017, 4:15 PM

Oct 14 2017

mjoras updated the diff for D12662: Properly reset fields in clean_unrhdr..
  • Might as well use TAILQ_FOREACH_SAFE while we are here.
Oct 14 2017, 11:58 PM

Oct 13 2017

mjoras updated the diff for D12662: Properly reset fields in clean_unrhdr..
  • use init_unrhdr instead of duplicating it
Oct 13 2017, 8:30 PM
mjoras created D12662: Properly reset fields in clean_unrhdr..
Oct 13 2017, 5:17 PM

Oct 11 2017

mjoras committed rS324541: Add clearing function for unr(9)..
Add clearing function for unr(9).
Oct 11 2017, 9:54 PM
mjoras committed rS324542: When unmounting a tmpfs, do not call free_unr..
When unmounting a tmpfs, do not call free_unr.
Oct 11 2017, 9:54 PM
mjoras closed D12591: Add clearing function for unr(9), call it from tmpfs..
Oct 11 2017, 9:54 PM

Oct 4 2017

mjoras updated the diff for D12591: Add clearing function for unr(9), call it from tmpfs..
  • Add comment explaining the conditional free_unr
Oct 4 2017, 8:05 PM
mjoras updated the diff for D12591: Add clearing function for unr(9), call it from tmpfs..
  • Fixup manpage.
  • Move KASSERT.
Oct 4 2017, 8:02 PM
mjoras added inline comments to D12591: Add clearing function for unr(9), call it from tmpfs..
Oct 4 2017, 7:43 PM
mjoras updated the summary of D12591: Add clearing function for unr(9), call it from tmpfs..
Oct 4 2017, 7:03 PM
mjoras created D12591: Add clearing function for unr(9), call it from tmpfs..
Oct 4 2017, 6:38 PM
mjoras created P145 (An Untitled Masterwork).
Oct 4 2017, 3:18 PM
mjoras edited P144 Masterwork From Distant Lands.
Oct 4 2017, 3:06 PM

Sep 16 2017

mjoras committed rS323633: MFC r323513:.
MFC r323513:
Sep 16 2017, 2:10 AM

Sep 13 2017

mjoras closed D12191: Allow vlan interfaces to rx through netmap(4).
Sep 13 2017, 12:25 AM
mjoras committed rS323513: Allow vlan interfaces to rx through netmap(4)..
Allow vlan interfaces to rx through netmap(4).
Sep 13 2017, 12:25 AM

Sep 12 2017

mjoras accepted D12267: Fix an infinite loop in tcp_tw_2msl_scan() when an INP_TIMEWAIT inp has been destroyed before its tcptw with INVARIANTS undefined..

For anyone wondering about the history here, see this thread from -net: https://lists.freebsd.org/pipermail/freebsd-net/2017-August/048621.html. TL;DR is this: https://lists.freebsd.org/pipermail/freebsd-net/2017-September/048826.html

Sep 12 2017, 4:41 PM
mjoras committed rS323477: MFC r322548: Rework vlan(4) locking..
MFC r322548: Rework vlan(4) locking.
Sep 12 2017, 3:54 AM

Sep 5 2017

mjoras added a comment to D12217: Add temperature sensor support for AMD Zen processors; two separate commits included this review..

Now, no one needs an amdsmn.
If some module in future will use SMN then it will be easy to share this code into module.

That's true, but what's so offensive about having another module? Why do we need to wait for abundant reasons to have logical code separation as opposed to copy paste code sharing?

Sep 5 2017, 1:00 AM

Sep 4 2017

mjoras added a comment to D12217: Add temperature sensor support for AMD Zen processors; two separate commits included this review..
In D12217#253620, @avg wrote:

I dont know where did you get info about Ryzen thermal interface, but for fam 15h 0x60 named "Miscellaneous Index" and I dont know about any renaming registers before.

Why amdsmn in new driver module?
(I dont think than any one want to do something with SMU or Miscellaneous registers)

Why do you think that there is any direction relation between SMU and Miscellaneous registers in family 15h and SMN in family 17h?
SMN is a completely new thing in family 17h (or so it seems), the only similarity between SMU and SMN is "SM" :-)
Family 17h is a big step from families 10h - 16h and even between those families there were incompatible changes in PCI register definitions (I know that for sure about registers that describe DRAM configuration).

Given the lack of documentation we can resort -- again! -- to using Linux commits by AMD employees as a guidance.
For example, https://patchwork.kernel.org/patch/9432511/

Sep 4 2017, 9:09 PM

Sep 2 2017

mjoras accepted D12217: Add temperature sensor support for AMD Zen processors; two separate commits included this review..
In D12217#253379, @cem wrote:

Yeah, that is an unfortunate problem of AMD's temperature scale. On the threadripper part, the offset is 27°C. I don't know how smart we want this thing to be. Is there a good way of determining specific model numbers? For what it's worth, I believe amdtemp had exactly the same problem on previous CPU generations.

My thought is that this is outside the scope of this revision since it's an existing problem in amdtemp. It's not totally clear to me what the best way to do it since the different parts have different offsets, but it's something someone should probably explore. If we can reliably map the offsets for every known part in every generation it would be a nice convenience feature.

Sep 2 2017, 11:51 PM
mjoras requested changes to D12217: Add temperature sensor support for AMD Zen processors; two separate commits included this review..

Also missing the sys/modules/amdsmn directory, so doesn't work with buildkernel at the moment.

Sep 2 2017, 5:49 PM

Aug 31 2017

mjoras created D12191: Allow vlan interfaces to rx through netmap(4).
Aug 31 2017, 9:35 PM
mjoras added a comment to D12188: Fix LACP with extended media..
In D12188#252958, @np wrote:

When you commit can you be more explicit about why this fixes it with the extended media types? For people not familiar with if_lagg some more specifics in the message would be helpful.

I updated the review summary, which is going to be the commit message.

Aug 31 2017, 9:08 PM
mjoras added a comment to D12188: Fix LACP with extended media..

Also unless I'm mistaken it looks like IF_BRIDGE(4) has the same bug. Should we fix that as well?

Upon further inspection, it doesn't actually matter for bridge interfaces.

Aug 31 2017, 9:02 PM
mjoras accepted D12188: Fix LACP with extended media..

When you commit can you be more explicit about why this fixes it with the extended media types? For people not familiar with if_lagg some more specifics in the message would be helpful.

Aug 31 2017, 8:52 PM

Aug 24 2017

mjoras accepted D12119: Fix 32-bit overflow on latency measurements.

The integer handling looks correct. It is definitely better than the defined-but-bad behavior of truncating the non-fractional bits of sbintime_t on ILP32. Using unsigned values everywhere makes all the operations well-defined and reasonable.

Aug 24 2017, 8:04 PM
mjoras edited P137 Masterwork From Distant Lands.
Aug 24 2017, 7:35 PM
mjoras created P136 (An Untitled Masterwork).
Aug 24 2017, 7:33 PM
mjoras edited P135 Masterwork From Distant Lands.
Aug 24 2017, 7:30 PM
mjoras added inline comments to D12119: Fix 32-bit overflow on latency measurements.
Aug 24 2017, 7:01 PM

Aug 23 2017

mjoras edited P133 Masterwork From Distant Lands.
Aug 23 2017, 5:01 PM
mjoras edited P132 Masterwork From Distant Lands.
Aug 23 2017, 12:15 AM
mjoras edited P131 Masterwork From Distant Lands.
Aug 23 2017, 12:13 AM

Aug 22 2017

mjoras edited P130 Masterwork From Distant Lands.
Aug 22 2017, 11:42 PM

Aug 20 2017

mjoras accepted D12019: subr_smp: Clean up topology analysis, add additional layers.
mjoras@icarium ~> sysctl hw.model
hw.model: AMD Ryzen Threadripper 1950X 16-Core Processor
Aug 20 2017, 5:08 AM
mjoras accepted D12082: Add powerd(8) support for AMD family 17h (Zen) CPUs.

So I will note that on my system hwpstate ends up opting to get these from acpi_perf:

kernel: hwpstate0: going to fetch info from acpi_perf
...
mjoras@icarium ~> sysctl dev.hwpstate.0.freq_settings
dev.hwpstate.0.freq_settings: 3400/3825 2800/2765 2200/1952
Aug 20 2017, 12:32 AM

Aug 16 2017

mjoras updated the diff for D12050: Fix mlx5en(4) to properly call m_defrag..
  • braces
Aug 16 2017, 7:37 PM
mjoras added inline comments to D12050: Fix mlx5en(4) to properly call m_defrag..
Aug 16 2017, 7:36 PM
mjoras created D12050: Fix mlx5en(4) to properly call m_defrag..
Aug 16 2017, 7:01 PM

Aug 15 2017

mjoras committed rS322548: Rework vlan(4) locking..
Rework vlan(4) locking.
Aug 15 2017, 5:53 PM
mjoras closed D11370: Rework vlan(4) locking. by committing rS322548: Rework vlan(4) locking..
Aug 15 2017, 5:53 PM
mjoras added a member for transport: mjoras.
Aug 15 2017, 4:52 PM
mjoras added a member for network: mjoras.
Aug 15 2017, 4:48 PM
mjoras added a comment to D11370: Rework vlan(4) locking..
In D11370#249572, @ae wrote:

I also did the same test with vlans created on top of lagg with 2x25G mellanox adapters.
I didn't see measurable performance drop there. It is able to forward 14Mpps with our RX direct vlan handling patch.

I think it is acceptable.

Aug 15 2017, 4:14 PM
mjoras added a comment to D11370: Rework vlan(4) locking..
In D11370#249511, @ae wrote:

I have tested your patch in our test environment against forwarding performance.
[packet generator] -> [ switch ] -> [ix.10 -> ix.100]

So, the FreeBSD 12 receives tagged by vlan10 packets on ixgbe(4) and then sends them into vlan100 through the same interface.
With used traffic distribution this test machine is able to forward about 1.3Mpps with and without your patch.
Then I applied our local patch to reduce RX overhead using direct vlan handling in the ixgbe(4). With this patch the same machine is able to forward 3Mpps without packet loss. With your patch this value is lowered to 2.9Mpps. Thus the locking overhead cost is about ~100kpps.
Also I think the possible panic in the vlan_input() due to the race now fixed.

Aug 15 2017, 3:15 PM

Aug 4 2017

mjoras committed rS322062: Selectively print "hwaddr" from ifconfig(8)..
Selectively print "hwaddr" from ifconfig(8).
Aug 4 2017, 9:07 PM
mjoras closed D11777: Selectively print "hwaddr" from ifconfig(8). by committing rS322062: Selectively print "hwaddr" from ifconfig(8)..
Aug 4 2017, 9:06 PM

Aug 3 2017

mjoras added inline comments to D11683: Fix mlx4en(4) to properly call m_defrag..
Aug 3 2017, 10:54 PM
mjoras added a comment to D11725: Add optional TCP logging on sonewconn failures..
In D11725#245735, @ae wrote:

I proposed this patch for the discussed problem:
https://lists.freebsd.org/pipermail/freebsd-net/2016-December/046650.html

But glebius@ said that he will have better solution after "listening sockets revamp".

Aug 3 2017, 6:57 PM
mjoras added a comment to D11683: Fix mlx4en(4) to properly call m_defrag..

Hi,

We are currently testing this patch internally. Testing will be done by Monday. Do you mind if I push it, so I can have it my MFC queue?

--HPS

Aug 3 2017, 3:22 PM

Aug 2 2017

mjoras updated the diff for D11683: Fix mlx4en(4) to properly call m_defrag..
  • add per-ring sysctl for defrag_attempts
Aug 2 2017, 3:01 PM

Aug 1 2017

mjoras added a comment to D11683: Fix mlx4en(4) to properly call m_defrag..

Here's an older test output that shows defrag_attempts and oversized_packets:

durinf004-1: hw.mlxen1.stat.tx_oversized_packets: 0
durinf004-1: hw.mlxen1.stat.defrag_attempts: 117
durinf004-2: hw.mlxen1.stat.tx_oversized_packets: 0
durinf004-2: hw.mlxen1.stat.defrag_attempts: 1
Fri Jul 21 18:46:25 PDT 2017
durinf004-1: hw.mlxen1.stat.tx_oversized_packets: 0
durinf004-1: hw.mlxen1.stat.defrag_attempts: 121
durinf004-2: hw.mlxen1.stat.tx_oversized_packets: 0
durinf004-2: hw.mlxen1.stat.defrag_attempts: 1
durinf004-1# tail -n 10 logfile
Sun Jul 23 23:00:25 PDT 2017
durinf004-1: hw.mlxen1.stat.tx_oversized_packets: 0
durinf004-1: hw.mlxen1.stat.defrag_attempts: 9306
durinf004-2: hw.mlxen1.stat.tx_oversized_packets: 0
durinf004-2: hw.mlxen1.stat.defrag_attempts: 47
Sun Jul 23 23:00:55 PDT 2017
durinf004-1: hw.mlxen1.stat.tx_oversized_packets: 0
durinf004-1: hw.mlxen1.stat.defrag_attempts: 9306
durinf004-2: hw.mlxen1.stat.tx_oversized_packets: 0
durinf004-2: hw.mlxen1.stat.defrag_attempts: 47
Aug 1 2017, 8:43 PM
mjoras updated the test plan for D11683: Fix mlx4en(4) to properly call m_defrag..
Aug 1 2017, 7:11 PM
mjoras added a comment to D11683: Fix mlx4en(4) to properly call m_defrag..

Have you tested this patch?

Aug 1 2017, 5:49 PM
mjoras updated the diff for D11683: Fix mlx4en(4) to properly call m_defrag..
  • add per-ring sysctl node for tso_packets
Aug 1 2017, 5:34 PM
mjoras added inline comments to D11683: Fix mlx4en(4) to properly call m_defrag..
Aug 1 2017, 5:27 PM
mjoras added a comment to D11683: Fix mlx4en(4) to properly call m_defrag..

BTW: I think the same issue exists for mlx5en.

Would you like me to make a separate revision for mlx5en or combine it into this one?

Aug 1 2017, 5:15 PM
mjoras added inline comments to D11683: Fix mlx4en(4) to properly call m_defrag..
Aug 1 2017, 4:58 PM
mjoras added inline comments to D11683: Fix mlx4en(4) to properly call m_defrag..
Aug 1 2017, 4:06 PM
mjoras updated the diff for D11683: Fix mlx4en(4) to properly call m_defrag..
  • unload / free the mbuf if everything was inlined
Aug 1 2017, 4:05 PM
mjoras updated the diff for D11683: Fix mlx4en(4) to properly call m_defrag..
  • Forgot to add the sysctl for defrag_attempts.
Aug 1 2017, 3:12 PM

Jul 31 2017

mjoras updated the diff for D11683: Fix mlx4en(4) to properly call m_defrag..

Rebasing on HEAD.

Jul 31 2017, 7:29 PM
mjoras edited P129 Masterwork From Distant Lands.
Jul 31 2017, 6:27 PM
mjoras edited P128 Masterwork From Distant Lands.
Jul 31 2017, 6:26 PM
mjoras edited P127 Masterwork From Distant Lands.
Jul 31 2017, 6:25 PM
mjoras closed D11797: Add myself to the calendar. by committing rS321804: Add myself to the calendar..
Jul 31 2017, 6:10 PM
mjoras committed rS321804: Add myself to the calendar..
Add myself to the calendar.
Jul 31 2017, 6:10 PM
mjoras created D11797: Add myself to the calendar..
Jul 31 2017, 5:16 PM