Page MenuHomeFreeBSD

bz (Bjoern A. Zeeb)
User

Projects (8)

User Details

User Since
Aug 29 2014, 12:11 PM (300 w, 4 d)

Recent Activity

Wed, May 27

bz accepted D25031: [net80211] Fix interrupted scan logic and ticks comparison.

Could make the flags bool instead of int but for the sake of minimal change for now, on a quick pass it looks ok.

Wed, May 27, 5:30 PM

Mon, May 25

bz committed rS361444: Release Peter Grehan (grehan) from "mentor ship"..
Release Peter Grehan (grehan) from "mentor ship".
Mon, May 25, 9:53 AM

Apr 28 2020

bz added inline comments to D24598: More re-working of multipage mbufs..
Apr 28 2020, 9:06 AM

Apr 16 2020

bz added inline comments to D24432: bridge: Simplify mac address generation.
Apr 16 2020, 9:33 AM

Apr 15 2020

bz accepted D24432: bridge: Simplify mac address generation.
Apr 15 2020, 8:02 PM
bz added a comment to D24383: ethersubr: Make the mac address generation more robust.

I'd be happy with this. I'd still think there could be a comment saying "If each (vnet) jail would also have a unique hostuuid this would not be necessary." for the getjailname() call.

Apr 15 2020, 7:57 PM
bz abandoned D24033: epair(4): disable per-IF fallback queuing and draining.

I've started on the inevitable try to rewrite epair(4) two weeks ago (need to say it's UBR work) and ridden it of the netisr.
I do have a prototype which seems working; need to figure out how to scale things up to hundreds of epairs or 100(s) of CPU threads.

Apr 15 2020, 1:59 PM

Apr 13 2020

bz updated subscribers of D24383: ethersubr: Make the mac address generation more robust.
In D24383#536488, @kp wrote:
In D24383#536382, @bz wrote:

(1) can we stop assigning locally administered addresses. We have general infrastructure in the FreeBSD OUI. Or is there a reason we cannot do that?

We can, and if_bridge does so, if hostid == 0 (which is the case for jails not created with host=inherit). I'm not clear on why the bridge has these two approaches. We could simplify the code by removing that, and just always calling ether_gen_addr().

Apr 13 2020, 10:15 AM

Apr 12 2020

bz added a comment to D24383: ethersubr: Make the mac address generation more robust.

(1) can we stop assigning locally administered addresses. We have general infrastructure in the FreeBSD OUI. Or is there a reason we cannot do that?
(2) jails have a hostid as well. If they are the same for all of them then maybe we should fix the the jail code to make sure they actually are unique if not set?

Apr 12 2020, 8:39 PM

Apr 7 2020

bz accepted D24272: Print more detail as part of the sonewconn() overflow message.
Apr 7 2020, 8:11 AM

Apr 5 2020

bz added a comment to D24272: Print more detail as part of the sonewconn() overflow message.

I like the idea; I'll wait for the sbuf conversion.

Apr 5 2020, 3:02 PM

Apr 4 2020

bz committed rS359630: Welcome Peter Grehan (grehan) back (see r334992) as a source committer..
Welcome Peter Grehan (grehan) back (see r334992) as a source committer.
Apr 4 2020, 11:11 AM

Mar 23 2020

bz updated the diff for D24135: IPV6_PKTINFO support for v4-mapped IPv6 sockets.

Fix more errors of in-between work.
I should really write that test case which would be simple.

Mar 23 2020, 10:44 AM

Mar 22 2020

bz added inline comments to D24135: IPV6_PKTINFO support for v4-mapped IPv6 sockets.
Mar 22 2020, 2:58 PM
bz updated the diff for D24135: IPV6_PKTINFO support for v4-mapped IPv6 sockets.

Correct logic bug identified by gert.
Factor out the code into its own function as requested my @melifaro.

Mar 22 2020, 2:56 PM

Mar 20 2020

bz updated the diff for D24135: IPV6_PKTINFO support for v4-mapped IPv6 sockets.

Actually check that PRUS_IPV6 is set before accepting the IPv6
control message in IPv4 lands.

Mar 20 2020, 11:10 AM
bz created D24135: IPV6_PKTINFO support for v4-mapped IPv6 sockets.
Mar 20 2020, 9:29 AM

Mar 19 2020

bz accepted D24125: Fix synchronization in the IPV6_2292PKTOPTIONS set handler..
Mar 19 2020, 8:54 PM

Mar 18 2020

bz added a comment to D21163: Make p_vaddr % p_align == p_offset % p_align for TLS segments..

... and on my arm64 boards for 66 days or shorter. Updated to the latest version a few days ago. So far no issues either.

Mar 18 2020, 3:05 PM

Mar 16 2020

bz committed rS359021: MFC r358992:.
MFC r358992:
Mar 16 2020, 9:13 PM
bz committed rS359020: MFC r358992:.
MFC r358992:
Mar 16 2020, 9:12 PM

Mar 14 2020

bz committed rS358992: kern_jail: missing \0 termination check on osrelease parameter.
kern_jail: missing \0 termination check on osrelease parameter
Mar 14 2020, 2:05 PM

Mar 11 2020

bz created D24035: IPv6 neighbour entries resource limits.
Mar 11 2020, 9:23 PM
bz created D24033: epair(4): disable per-IF fallback queuing and draining.
Mar 11 2020, 9:02 PM
bz committed rS358897: Correctly spell TUNABLES..
Correctly spell TUNABLES.
Mar 11 2020, 8:24 PM

Mar 10 2020

bz added a comment to D22003: Add lle_event handler to ARP.

@bz: do I understand correctly that you're okay with the patch but suggesting committing the exact same change but in 2 separate commits?
Both referencing this review, one for if_ether.c and another for nd6.c?

Mar 10 2020, 9:46 PM

Mar 4 2020

bz added a comment to D23145: dwc(4) Ethernet MAC address setting/generating.

ping6? Or else it goes in... which I don't know if it's the best idea ...

Mar 4 2020, 7:19 PM
bz added inline comments to D22712: Add Router and Prefix table limits..
Mar 4 2020, 7:17 PM
bz updated the diff for D22712: Add Router and Prefix table limits..

Update (move sysctls to the top of the file).
Implement excluding dr pref updates from the resource limits as suggested by @melifaro.

Mar 4 2020, 7:17 PM
bz committed rS358625: Implement optional table entry limits for if_llatbl..
Implement optional table entry limits for if_llatbl.
Mar 4 2020, 5:17 PM
bz closed D22713: Implement optional table entry limits of if_llatbl..
Mar 4 2020, 5:17 PM
bz accepted D23957: Use consistent flow labels when using SYN cookies.
Mar 4 2020, 4:29 PM
bz closed D22711: Add new ICMPv6 counters for Anti-DoS limits.
Mar 4 2020, 4:21 PM
bz committed rS358620: Add new ICMPv6 counters for Anti-DoS limits..
Add new ICMPv6 counters for Anti-DoS limits.
Mar 4 2020, 4:21 PM
bz added inline comments to D22711: Add new ICMPv6 counters for Anti-DoS limits.
Mar 4 2020, 4:20 PM

Mar 3 2020

bz committed rS358577: tcp_hpts: make RSS kernel compile again..
tcp_hpts: make RSS kernel compile again.
Mar 3 2020, 2:15 PM
bz closed D23726: Make RSS kernels compile again.
Mar 3 2020, 2:15 PM
bz reopened D23726: Make RSS kernels compile again.

I am re-opening this again as HPTS still needs fixing @rrs . See https://reviews.freebsd.org/D23726?id=68452 for the original diff.

Mar 3 2020, 2:09 PM
bz closed D23726: Make RSS kernels compile again.
Mar 3 2020, 2:08 PM
bz committed rS358576: upic_ktrls: make RSS compile again here.
upic_ktrls: make RSS compile again here
Mar 3 2020, 2:08 PM
bz committed rS358575: ip6: retire in6_selectroute_fib() as promised 8 years ago.
ip6: retire in6_selectroute_fib() as promised 8 years ago
Mar 3 2020, 1:48 PM
bz closed D23886: ip6_output: use new routing KPI when not passed a cached route.
Mar 3 2020, 11:33 AM
bz committed rS358572: ip6_output: use new routing KPI when not passed a cached route.
ip6_output: use new routing KPI when not passed a cached route
Mar 3 2020, 11:32 AM
bz committed rS358569: in6_fib: return nh_ia in the ext interface as we do for IPv4.
in6_fib: return nh_ia in the ext interface as we do for IPv4
Mar 3 2020, 9:50 AM
bz closed D23873: in6_fib: return nh_ia in the ext interface as we do for IPv4.
Mar 3 2020, 9:50 AM
bz committed rS358568: fib6_rte_to_nh_*: return a link-local gw address with scope embedded.
fib6_rte_to_nh_*: return a link-local gw address with scope embedded
Mar 3 2020, 9:45 AM
bz closed D23872: fib6_rte_to_nh_*: correctly return a link-local gw address:.
Mar 3 2020, 9:45 AM
bz committed rS358566: MFC r358297: Fix IPv6 checksums when exthdrs are present..
MFC r358297: Fix IPv6 checksums when exthdrs are present.
Mar 3 2020, 8:24 AM

Mar 2 2020

bz committed rS358557: MFC r358297: Fix IPv6 checksums when exthdrs are present..
MFC r358297: Fix IPv6 checksums when exthdrs are present.
Mar 2 2020, 10:54 PM
bz committed rS358543: MFC r358427: initialize oifp to avoid bogus results/panics in edge cases.
MFC r358427: initialize oifp to avoid bogus results/panics in edge cases
Mar 2 2020, 1:24 PM
bz committed rS358542: MFC r358427: initialize oifp to avoid bogus results/panics in edge cases.
MFC r358427: initialize oifp to avoid bogus results/panics in edge cases
Mar 2 2020, 1:23 PM
bz committed rS358541: MFC r358167,358311: ip6_output: improve extension header handling.
MFC r358167,358311: ip6_output: improve extension header handling
Mar 2 2020, 1:16 PM
bz committed rS358540: MFC r358167,358311: ip6_output: improve extension header handling.
MFC r358167,358311: ip6_output: improve extension header handling
Mar 2 2020, 1:16 PM
bz committed rS358539: MFC r358071: ip6_output: update comments..
MFC r358071: ip6_output: update comments.
Mar 2 2020, 1:13 PM
bz committed rS358538: MFC r358071: ip6_output: update comments..
MFC r358071: ip6_output: update comments.
Mar 2 2020, 1:13 PM

Mar 1 2020

bz added a comment to D23886: ip6_output: use new routing KPI when not passed a cached route.
Mar 1 2020, 10:50 PM

Feb 28 2020

bz added a comment to D23886: ip6_output: use new routing KPI when not passed a cached route.
In D23886#525161, @bz wrote:

@olivier do you have a non-forwarding TCP test-bed these days?

I have a nginx <=> wrk lab, do you think we could use it in this case ? By serving only very small files, like 16Kb and asking wrk to use large number of clients, something like 2500 or more ?

Feb 28 2020, 11:09 PM
bz added a comment to D23886: ip6_output: use new routing KPI when not passed a cached route.

@olivier do you have a non-forwarding TCP test-bed these days?

Feb 28 2020, 9:09 PM
bz added a comment to D23886: ip6_output: use new routing KPI when not passed a cached route.

I re-run UDP6, min-size packets, pps tests on a multi-user system for all four cases (1-2 is the patched new KPI use when possible, 3-4 is the vanilla kernel runs):

Feb 28 2020, 9:04 PM
bz accepted D23882: Add BSM conversion logic for some jail and setlogin class events.

Not my expertise of code but looks ok to me.

Feb 28 2020, 7:46 PM
bz created D23886: ip6_output: use new routing KPI when not passed a cached route.
Feb 28 2020, 7:32 PM
bz added a reviewer for D23872: fib6_rte_to_nh_*: correctly return a link-local gw address:: ae.
In D23872#524865, @ae wrote:

This code, probably, was written with hope of depreciation of scope embedding into addresses.

Feb 28 2020, 11:54 AM
bz updated the diff for D23872: fib6_rte_to_nh_*: correctly return a link-local gw address:.

Update based on @ae 's comments.

Feb 28 2020, 11:53 AM
bz added a reviewer for D23872: fib6_rte_to_nh_*: correctly return a link-local gw address:: olivier.
Feb 28 2020, 11:27 AM
bz committed rS358427: mld6: initialize oifp to avoid bogus results/panics in edge cases.
mld6: initialize oifp to avoid bogus results/panics in edge cases
Feb 28 2020, 11:16 AM
bz created D23873: in6_fib: return nh_ia in the ext interface as we do for IPv4.
Feb 28 2020, 11:09 AM
bz created D23872: fib6_rte_to_nh_*: correctly return a link-local gw address:.
Feb 28 2020, 10:58 AM

Feb 27 2020

bz accepted D22003: Add lle_event handler to ARP.

I'd probably still commit the nd6 change separately.

Feb 27 2020, 9:28 PM
bz added inline comments to D23726: Make RSS kernels compile again.
Feb 27 2020, 6:32 PM
bz edited reviewers for D23726: Make RSS kernels compile again, added: gallatin, jtl; removed: transport.

Can someone look at the hpts bits please? I know they are not as straight forward as is the ktls case.

Feb 27 2020, 8:32 AM

Feb 26 2020

bz added inline comments to D23726: Make RSS kernels compile again.
Feb 26 2020, 11:26 PM

Feb 25 2020

bz committed rS358311: ip6_output: fix regression introduced in r358167 for ipv6 fragmentation.
ip6_output: fix regression introduced in r358167 for ipv6 fragmentation
Feb 25 2020, 3:03 PM
bz added a comment to D23775: buffer pager: deref ucred immediately after read..

add myself to keep track of it

Feb 25 2020, 12:12 PM
bz added a comment to D23145: dwc(4) Ethernet MAC address setting/generating.

Anyone else any comments?

Feb 25 2020, 11:57 AM

Feb 24 2020

bz added a comment to D23726: Make RSS kernels compile again.

Anyone any comment on this? Otherwise I'll commit it the next two days.

Feb 24 2020, 7:17 PM
bz committed rS358297: Fix IPv6 checksums when exthdrs are present..
Fix IPv6 checksums when exthdrs are present.
Feb 24 2020, 7:12 PM
bz closed D23760: Fix IPv6 checksums when exthdrs are present..
Feb 24 2020, 7:12 PM
bz added a comment to D23760: Fix IPv6 checksums when exthdrs are present..

@gallatin I hope this makes sense ..

Feb 24 2020, 6:26 PM

Feb 20 2020

bz added a comment to D23760: Fix IPv6 checksums when exthdrs are present..

Seems all sorted now. Thanks especially to @gallatin for bearing with me.

Feb 20 2020, 6:56 PM
bz updated the diff for D23760: Fix IPv6 checksums when exthdrs are present..

Pass the proper csum flags into the 2nd call of ip6_output_delayed_csum().

Feb 20 2020, 6:53 PM
bz added inline comments to D23760: Fix IPv6 checksums when exthdrs are present..
Feb 20 2020, 3:00 PM
bz added inline comments to D23760: Fix IPv6 checksums when exthdrs are present..
Feb 20 2020, 2:14 PM
bz added inline comments to D23760: Fix IPv6 checksums when exthdrs are present..
Feb 20 2020, 11:28 AM
bz updated the diff for D23760: Fix IPv6 checksums when exthdrs are present..

Add KASSERT as suggested by @markj .
Remove hlen variable which always matches unfragpartlen as suggested by @markj.
Fix a case where we possibly do not update the ip6 pointer.
Leave a comment about an unclear header clearing line for future contemplation (which was removed in the previous revision).

Feb 20 2020, 11:27 AM
bz added a comment to D23760: Fix IPv6 checksums when exthdrs are present..

Leave comments and questions (and another possible bugfix comment for later).

Feb 20 2020, 11:08 AM
bz closed D23740: ip6_output: improve extension header handling.
Feb 20 2020, 10:56 AM
bz committed rS358167: ip6_output: improve extension header handling.
ip6_output: improve extension header handling
Feb 20 2020, 10:56 AM

Feb 19 2020

bz added a comment to D23760: Fix IPv6 checksums when exthdrs are present..

I'm 1/2 joking, but what would you think about not supporting extension headers at all? They are the worst part of IPv6 and make everything complicated and add lots of hairy cases. What benefit are they?
(I'm legitimately curious)

Feb 19 2020, 10:28 PM
bz added inline comments to D23760: Fix IPv6 checksums when exthdrs are present..
Feb 19 2020, 6:42 PM
bz created D23760: Fix IPv6 checksums when exthdrs are present..
Feb 19 2020, 6:41 PM
bz added inline comments to D23740: ip6_output: improve extension header handling.
Feb 19 2020, 5:50 PM
bz updated the diff for D23740: ip6_output: improve extension header handling.

Correct changes based on the comments from @markj and make hdrsplit
a bool as it is used as such.

Feb 19 2020, 5:48 PM

Feb 18 2020

bz created D23740: ip6_output: improve extension header handling.
Feb 18 2020, 12:05 PM
bz committed rS358071: ip6_output: update comments..
ip6_output: update comments.
Feb 18 2020, 11:28 AM

Feb 17 2020

bz added inline comments to D23726: Make RSS kernels compile again.
Feb 17 2020, 4:05 PM
bz added inline comments to D23726: Make RSS kernels compile again.
Feb 17 2020, 11:52 AM
bz created D23726: Make RSS kernels compile again.
Feb 17 2020, 11:49 AM
bz committed rD53908: Update for __FreeBSD_version 1300078 after src r358020 changing.
Update for __FreeBSD_version 1300078 after src r358020 changing
Feb 17 2020, 11:15 AM
bz closed D23097: Revert VNET change and expand VNET structure..
Feb 17 2020, 11:09 AM
bz committed rS358020: Partially revert VNET change and expand VNET structure..
Partially revert VNET change and expand VNET structure.
Feb 17 2020, 11:09 AM