From owner-freebsd-net@FreeBSD.ORG Sun Jan 25 09:39:29 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id E485F87D for ; Sun, 25 Jan 2015 09:39:29 +0000 (UTC) Received: from mwork.nabble.com (mwork.nabble.com [162.253.133.43]) by mx1.freebsd.org (Postfix) with ESMTP id CDB4EDC4 for ; Sun, 25 Jan 2015 09:39:29 +0000 (UTC) Received: from msam.nabble.com (unknown [162.253.133.85]) by mwork.nabble.com (Postfix) with ESMTP id 6D6D911A5F92 for ; Sun, 25 Jan 2015 01:39:24 -0800 (PST) Date: Sun, 25 Jan 2015 02:39:22 -0700 (MST) From: schaman To: freebsd-net@freebsd.org Message-ID: <1422178762964-5983448.post@n5.nabble.com> In-Reply-To: References: Subject: Re: [Bug 185967] [lagg] [patch] Link Aggregation LAGG: LACP not working in 10.0 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 25 Jan 2015 09:39:30 -0000 Try to change juniper settings to /periodic slow;/ -- View this message in context: http://freebsd.1045724.n5.nabble.com/Bug-185967-lagg-patch-Link-Aggregation-LAGG-LACP-not-working-in-10-0-tp5952851p5983448.html Sent from the freebsd-net mailing list archive at Nabble.com. From owner-freebsd-net@FreeBSD.ORG Sun Jan 25 19:46:13 2015 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 0EB0C742 for ; Sun, 25 Jan 2015 19:46:13 +0000 (UTC) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id E983CEAA for ; Sun, 25 Jan 2015 19:46:12 +0000 (UTC) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.14.9/8.14.9) with ESMTP id t0PJkCji078942 for ; Sun, 25 Jan 2015 19:46:12 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 172675] [netinet] [patch] sysctl_tcp_hc_list (net.inet.tcp.hostcache.list) race condition causing memory corruption Date: Sun, 25 Jan 2015 19:46:12 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 8.3-RELEASE X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: commit-hook@freebsd.org X-Bugzilla-Status: In Progress X-Bugzilla-Priority: Normal X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 25 Jan 2015 19:46:13 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=172675 --- Comment #7 from commit-hook@freebsd.org --- A commit references this bug: Author: jhb Date: Sun Jan 25 19:45:45 UTC 2015 New revision: 277709 URL: https://svnweb.freebsd.org/changeset/base/277709 Log: Use an sbuf to generate the output of the net.inet.tcp.hostcache.list sysctl to avoid a possible buffer overflow if the cache grows while the text is being generated. PR: 172675 MFC after: 2 weeks Changes: head/sys/netinet/tcp_hostcache.c -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@FreeBSD.ORG Sun Jan 25 20:11:36 2015 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id CEA45EA9 for ; Sun, 25 Jan 2015 20:11:36 +0000 (UTC) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 9BB031E4 for ; Sun, 25 Jan 2015 20:11:36 +0000 (UTC) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.14.9/8.14.9) with ESMTP id t0PKBaSc070990 for ; Sun, 25 Jan 2015 20:11:36 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 188897] [dc] dc ethernet driver seems to prevent the detection of other NIC chipsets Date: Sun, 25 Jan 2015 20:11:36 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.0-RELEASE X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: jhb@FreeBSD.org X-Bugzilla-Status: In Progress X-Bugzilla-Priority: Normal X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 25 Jan 2015 20:11:36 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=188897 --- Comment #8 from John Baldwin --- So I had missed that you had tried hint.agp.0.disabled=1 before and it fixed this when I re-read this recently. I suspect the re hint would also workaround this. The bug here is the same as one reported recently on net@ and I believe your other PR is a dupe. The problem is that when agp0 goes to allocate a random page of memory, it allocates a resource range that conflicts with the memory I/O windows already claimed by the PCI-PCI bridges on PCI bus 0. We move the window down for the first PCI-PCI bridge that re0 lives behind, but when we do, we move it such that it overlaps the window that the second bridge the quad-port card lives behind. As a result, I believe that some of the memory requests destined for re0 end up getting routed to one of the ports on the quad-port card instead confusing the driver. The second PCI-PCI bridge then probes and notices it is busted, so it moves its window down. If you were to force the re0 device to reattach at that point it would actually work fine, but there's currently not an easy way to do that. The real bug is that the PCI-PCI bridge I/O windows need to be accounted for and not conflicted with. There are a couple of ways to fix this, most of which aren't quite trivial: 1) Reserve the resources assigned to I/O windows just as we do for firmware-assigned BARs before probing any devices. This is probably what I would prefer, but it is unfortunately a bit messy because of the ISA-enable bit (the existing pci_pci driver has quite a bit of code to deal with this already and it would be a shame to duplicate). Also, the PCI bus driver doesn't currently "know" about the resources backing an I/O window the same way it knows about BARs. 1a) Like 1) but sidestep the ISA-enable ickiness by just applying this to memory windows. 2) Flesh out new-bus multipass for x86. This would cause the the PCI-PCI bridge drivers to probe and claim any resources before drivers like agp0 got a chance. This is not a small amount of work however. For now, hint.agp.0.disabled=1 should serve as a workaround for you for all of your cases I believe until I have time to develop and test a better fix. -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@FreeBSD.ORG Mon Jan 26 11:57:43 2015 Return-Path: Delivered-To: net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 932A0C2D for ; Mon, 26 Jan 2015 11:57:43 +0000 (UTC) Received: from shelob.oktetlabs.ru (shelob.oktetlabs.ru [84.52.89.53]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id BAE77805 for ; Mon, 26 Jan 2015 11:57:42 +0000 (UTC) Received: from [192.168.38.17] (aros.oktetlabs.ru [192.168.38.17]) (using TLSv1 with cipher DHE-RSA-AES128-SHA (128/128 bits)) (No client certificate requested) by shelob.oktetlabs.ru (Postfix) with ESMTPSA id 0B4CD7F488; Mon, 26 Jan 2015 14:47:32 +0300 (MSK) X-DKIM: Sendmail DKIM Filter v2.8.2 shelob.oktetlabs.ru 0B4CD7F488 DKIM-Signature: v=1; a=rsa-sha256; c=simple/simple; d=oktetlabs.ru; s=default; t=1422272852; bh=wbeQ5OF+8YoLh056PYkPg9ZGyFeCu76HdRyfWEbp2H0=; l=51960; h=Message-ID:Date:From:MIME-Version:To:CC:Subject:Content-Type; b=bmHRoWncm9YPCU8VZhxtf9cM3T7puhK+qoVWWQT4FvKm1jq+/Qz437jwfEuFFEngO Khxy4BTuIQqve7NaEbxwOG5tww58F2zlizlkx00KbatXEUKNXWeouFgmQvyBMwrJUI XbTf+RdGuMTlRYIt847beYdnyUfLmR/PtIZBtLlU= Message-ID: <54C62954.5030004@oktetlabs.ru> Date: Mon, 26 Jan 2015 14:47:32 +0300 From: Andrew Rybchenko Organization: OKTET Labs User-Agent: Mozilla/5.0 (X11; Linux i686 on x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.4.0 MIME-Version: 1.0 To: net@FreeBSD.org Subject: [PATCH] sfxge improvements and bug fixes Content-Type: multipart/mixed; boundary="------------050201000503010305030302" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 26 Jan 2015 11:57:43 -0000 This is a multi-part message in MIME format. --------------050201000503010305030302 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Hello, my colleagues and me have a number of patches to sfxge driver including: - performance optimizations - fix TSO to work fine when VLAN is used (IPv6 does not work yet, to be fixed in the nearest time) - add tunable to control maximum number of RSS channels - improve software Tx queue to have separate limits for TCP and non-TCP traffic and more granular overflow statistics - cleanup Patches are attached. The goal of the submission is to get feedback and review notes (including mentor). Best regards, Andrew. --------------050201000503010305030302 Content-Type: text/x-patch; name="01-64bit.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="01-64bit.patch" sfxge: using 64-bit access for x86-64 Submitted by: Artem V. Andreev Sponsored by: Solarflare Communications, Inc. Index: sys/dev/sfxge/common/efsys.h =================================================================== --- sys/dev/sfxge/common/efsys.h (revision 277726) +++ sys/dev/sfxge/common/efsys.h (working copy) @@ -51,7 +51,11 @@ #include #define EFSYS_HAS_UINT64 1 +#if defined(__x86_64__) +#define EFSYS_USE_UINT64 1 +#else #define EFSYS_USE_UINT64 0 +#endif #if _BYTE_ORDER == _BIG_ENDIAN #define EFSYS_IS_BIG_ENDIAN 1 #define EFSYS_IS_LITTLE_ENDIAN 0 @@ -399,8 +403,28 @@ _NOTE(CONSTANTCONDITION) \ } while (B_FALSE) +#if defined(__x86_64__) #define EFSYS_MEM_READQ(_esmp, _offset, _eqp) \ do { \ + uint64_t *addr; \ + \ + _NOTE(CONSTANTCONDITION) \ + KASSERT(IS_P2ALIGNED(_offset, sizeof (efx_qword_t)), \ + ("not power of 2 aligned")); \ + \ + addr = (void *)((_esmp)->esm_base + (_offset)); \ + \ + (_eqp)->eq_u64[0] = *addr; \ + \ + EFSYS_PROBE3(mem_readq, unsigned int, (_offset), \ + uint32_t, (_eqp)->eq_u32[1], \ + uint32_t, (_eqp)->eq_u32[0]); \ + \ + _NOTE(CONSTANTCONDITION) \ + } while (B_FALSE) +#else +#define EFSYS_MEM_READQ(_esmp, _offset, _eqp) \ + do { \ uint32_t *addr; \ \ _NOTE(CONSTANTCONDITION) \ @@ -418,9 +442,33 @@ \ _NOTE(CONSTANTCONDITION) \ } while (B_FALSE) +#endif +#if defined(__x86_64__) #define EFSYS_MEM_READO(_esmp, _offset, _eop) \ do { \ + uint64_t *addr; \ + \ + _NOTE(CONSTANTCONDITION) \ + KASSERT(IS_P2ALIGNED(_offset, sizeof (efx_oword_t)), \ + ("not power of 2 aligned")); \ + \ + addr = (void *)((_esmp)->esm_base + (_offset)); \ + \ + (_eop)->eo_u64[0] = *addr++; \ + (_eop)->eo_u64[1] = *addr; \ + \ + EFSYS_PROBE5(mem_reado, unsigned int, (_offset), \ + uint32_t, (_eop)->eo_u32[3], \ + uint32_t, (_eop)->eo_u32[2], \ + uint32_t, (_eop)->eo_u32[1], \ + uint32_t, (_eop)->eo_u32[0]); \ + \ + _NOTE(CONSTANTCONDITION) \ + } while (B_FALSE) +#else +#define EFSYS_MEM_READO(_esmp, _offset, _eop) \ + do { \ uint32_t *addr; \ \ _NOTE(CONSTANTCONDITION) \ @@ -442,6 +490,7 @@ \ _NOTE(CONSTANTCONDITION) \ } while (B_FALSE) +#endif #define EFSYS_MEM_WRITED(_esmp, _offset, _edp) \ do { \ @@ -461,8 +510,29 @@ _NOTE(CONSTANTCONDITION) \ } while (B_FALSE) +#if defined(__x86_64__) #define EFSYS_MEM_WRITEQ(_esmp, _offset, _eqp) \ do { \ + uint64_t *addr; \ + \ + _NOTE(CONSTANTCONDITION) \ + KASSERT(IS_P2ALIGNED(_offset, sizeof (efx_qword_t)), \ + ("not power of 2 aligned")); \ + \ + EFSYS_PROBE3(mem_writeq, unsigned int, (_offset), \ + uint32_t, (_eqp)->eq_u32[1], \ + uint32_t, (_eqp)->eq_u32[0]); \ + \ + addr = (void *)((_esmp)->esm_base + (_offset)); \ + \ + *addr = (_eqp)->eq_u64[0]; \ + \ + _NOTE(CONSTANTCONDITION) \ + } while (B_FALSE) + +#else +#define EFSYS_MEM_WRITEQ(_esmp, _offset, _eqp) \ + do { \ uint32_t *addr; \ \ _NOTE(CONSTANTCONDITION) \ @@ -480,9 +550,33 @@ \ _NOTE(CONSTANTCONDITION) \ } while (B_FALSE) +#endif +#if defined(__x86_64__) #define EFSYS_MEM_WRITEO(_esmp, _offset, _eop) \ do { \ + uint64_t *addr; \ + \ + _NOTE(CONSTANTCONDITION) \ + KASSERT(IS_P2ALIGNED(_offset, sizeof (efx_oword_t)), \ + ("not power of 2 aligned")); \ + \ + EFSYS_PROBE5(mem_writeo, unsigned int, (_offset), \ + uint32_t, (_eop)->eo_u32[3], \ + uint32_t, (_eop)->eo_u32[2], \ + uint32_t, (_eop)->eo_u32[1], \ + uint32_t, (_eop)->eo_u32[0]); \ + \ + addr = (void *)((_esmp)->esm_base + (_offset)); \ + \ + *addr++ = (_eop)->eo_u64[0]; \ + *addr = (_eop)->eo_u64[1]; \ + \ + _NOTE(CONSTANTCONDITION) \ + } while (B_FALSE) +#else +#define EFSYS_MEM_WRITEO(_esmp, _offset, _eop) \ + do { \ uint32_t *addr; \ \ _NOTE(CONSTANTCONDITION) \ @@ -504,6 +598,7 @@ \ _NOTE(CONSTANTCONDITION) \ } while (B_FALSE) +#endif #define EFSYS_MEM_ADDR(_esmp) \ ((_esmp)->esm_addr) @@ -540,6 +635,7 @@ _NOTE(CONSTANTCONDITION) \ } while (B_FALSE) +#if defined(__x86_64__) #define EFSYS_BAR_READQ(_esbp, _offset, _eqp) \ do { \ _NOTE(CONSTANTCONDITION) \ @@ -548,6 +644,53 @@ \ mtx_lock(&((_esbp)->esb_lock)); \ \ + (_eqp)->eq_u64[0] = bus_space_read_8((_esbp)->esb_tag, \ + (_esbp)->esb_handle, (_offset)); \ + \ + EFSYS_PROBE3(bar_readq, unsigned int, (_offset), \ + uint32_t, (_eqp)->eq_u32[1], \ + uint32_t, (_eqp)->eq_u32[0]); \ + \ + mtx_unlock(&((_esbp)->esb_lock)); \ + _NOTE(CONSTANTCONDITION) \ + } while (B_FALSE) + +#define EFSYS_BAR_READO(_esbp, _offset, _eop, _lock) \ + do { \ + _NOTE(CONSTANTCONDITION) \ + KASSERT(IS_P2ALIGNED(_offset, sizeof (efx_oword_t)), \ + ("not power of 2 aligned")); \ + \ + _NOTE(CONSTANTCONDITION) \ + if (_lock) \ + mtx_lock(&((_esbp)->esb_lock)); \ + \ + (_eop)->eo_u64[0] = bus_space_read_8((_esbp)->esb_tag, \ + (_esbp)->esb_handle, (_offset)); \ + (_eop)->eo_u64[1] = bus_space_read_8((_esbp)->esb_tag, \ + (_esbp)->esb_handle, (_offset+8)); \ + \ + EFSYS_PROBE5(bar_reado, unsigned int, (_offset), \ + uint32_t, (_eop)->eo_u32[3], \ + uint32_t, (_eop)->eo_u32[2], \ + uint32_t, (_eop)->eo_u32[1], \ + uint32_t, (_eop)->eo_u32[0]); \ + \ + _NOTE(CONSTANTCONDITION) \ + if (_lock) \ + mtx_unlock(&((_esbp)->esb_lock)); \ + _NOTE(CONSTANTCONDITION) \ + } while (B_FALSE) + +#else +#define EFSYS_BAR_READQ(_esbp, _offset, _eqp) \ + do { \ + _NOTE(CONSTANTCONDITION) \ + KASSERT(IS_P2ALIGNED(_offset, sizeof (efx_qword_t)), \ + ("not power of 2 aligned")); \ + \ + mtx_lock(&((_esbp)->esb_lock)); \ + \ (_eqp)->eq_u32[0] = bus_space_read_4((_esbp)->esb_tag, \ (_esbp)->esb_handle, (_offset)); \ (_eqp)->eq_u32[1] = bus_space_read_4((_esbp)->esb_tag, \ @@ -591,6 +734,7 @@ mtx_unlock(&((_esbp)->esb_lock)); \ _NOTE(CONSTANTCONDITION) \ } while (B_FALSE) +#endif #define EFSYS_BAR_WRITED(_esbp, _offset, _edp, _lock) \ do { \ @@ -614,6 +758,7 @@ _NOTE(CONSTANTCONDITION) \ } while (B_FALSE) +#if defined(__x86_64__) #define EFSYS_BAR_WRITEQ(_esbp, _offset, _eqp) \ do { \ _NOTE(CONSTANTCONDITION) \ @@ -626,6 +771,25 @@ uint32_t, (_eqp)->eq_u32[1], \ uint32_t, (_eqp)->eq_u32[0]); \ \ + bus_space_write_8((_esbp)->esb_tag, (_esbp)->esb_handle,\ + (_offset), (_eqp)->eq_u64[0]); \ + \ + mtx_unlock(&((_esbp)->esb_lock)); \ + _NOTE(CONSTANTCONDITION) \ + } while (B_FALSE) +#else +#define EFSYS_BAR_WRITEQ(_esbp, _offset, _eqp) \ + do { \ + _NOTE(CONSTANTCONDITION) \ + KASSERT(IS_P2ALIGNED(_offset, sizeof (efx_qword_t)), \ + ("not power of 2 aligned")); \ + \ + mtx_lock(&((_esbp)->esb_lock)); \ + \ + EFSYS_PROBE3(bar_writeq, unsigned int, (_offset), \ + uint32_t, (_eqp)->eq_u32[1], \ + uint32_t, (_eqp)->eq_u32[0]); \ + \ bus_space_write_4((_esbp)->esb_tag, (_esbp)->esb_handle,\ (_offset), (_eqp)->eq_u32[0]); \ bus_space_write_4((_esbp)->esb_tag, (_esbp)->esb_handle,\ @@ -634,7 +798,9 @@ mtx_unlock(&((_esbp)->esb_lock)); \ _NOTE(CONSTANTCONDITION) \ } while (B_FALSE) +#endif +#if defined(__x86_64__) #define EFSYS_BAR_WRITEO(_esbp, _offset, _eop, _lock) \ do { \ _NOTE(CONSTANTCONDITION) \ @@ -651,6 +817,34 @@ uint32_t, (_eop)->eo_u32[1], \ uint32_t, (_eop)->eo_u32[0]); \ \ + bus_space_write_8((_esbp)->esb_tag, (_esbp)->esb_handle,\ + (_offset), (_eop)->eo_u64[0]); \ + bus_space_write_8((_esbp)->esb_tag, (_esbp)->esb_handle,\ + (_offset+8), (_eop)->eo_u64[1]); \ + \ + _NOTE(CONSTANTCONDITION) \ + if (_lock) \ + mtx_unlock(&((_esbp)->esb_lock)); \ + _NOTE(CONSTANTCONDITION) \ + } while (B_FALSE) + +#else +#define EFSYS_BAR_WRITEO(_esbp, _offset, _eop, _lock) \ + do { \ + _NOTE(CONSTANTCONDITION) \ + KASSERT(IS_P2ALIGNED(_offset, sizeof (efx_oword_t)), \ + ("not power of 2 aligned")); \ + \ + _NOTE(CONSTANTCONDITION) \ + if (_lock) \ + mtx_lock(&((_esbp)->esb_lock)); \ + \ + EFSYS_PROBE5(bar_writeo, unsigned int, (_offset), \ + uint32_t, (_eop)->eo_u32[3], \ + uint32_t, (_eop)->eo_u32[2], \ + uint32_t, (_eop)->eo_u32[1], \ + uint32_t, (_eop)->eo_u32[0]); \ + \ bus_space_write_4((_esbp)->esb_tag, (_esbp)->esb_handle,\ (_offset), (_eop)->eo_u32[0]); \ bus_space_write_4((_esbp)->esb_tag, (_esbp)->esb_handle,\ @@ -665,6 +859,7 @@ mtx_unlock(&((_esbp)->esb_lock)); \ _NOTE(CONSTANTCONDITION) \ } while (B_FALSE) +#endif /* SPIN */ --------------050201000503010305030302 Content-Type: text/x-patch; name="02-sfxge_ev_qpoll.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="02-sfxge_ev_qpoll.patch" sfxge: Change sfxge_ev_qpoll() proto to avoid EVQ pointers array access It was the only place on data path where sc->evq array is accessed. Sponsored by: Solarflare Communications, Inc. Index: sys/dev/sfxge/sfxge_intr.c =================================================================== --- sys/dev/sfxge/sfxge_intr.c (revision 277726) +++ sys/dev/sfxge/sfxge_intr.c (working copy) @@ -110,9 +110,8 @@ sfxge_intr_line(void *arg) { struct sfxge_evq *evq = arg; - struct sfxge_softc *sc = evq->sc; - (void)sfxge_ev_qpoll(sc, 0); + (void)sfxge_ev_qpoll(evq); } static void @@ -146,7 +145,7 @@ return; } - (void)sfxge_ev_qpoll(sc, index); + (void)sfxge_ev_qpoll(evq); } static int Index: sys/dev/sfxge/sfxge.h =================================================================== --- sys/dev/sfxge/sfxge.h (revision 277726) +++ sys/dev/sfxge/sfxge.h (working copy) @@ -281,7 +281,7 @@ extern void sfxge_ev_fini(struct sfxge_softc *sc); extern int sfxge_ev_start(struct sfxge_softc *sc); extern void sfxge_ev_stop(struct sfxge_softc *sc); -extern int sfxge_ev_qpoll(struct sfxge_softc *sc, unsigned int index); +extern int sfxge_ev_qpoll(struct sfxge_evq *evq); /* * From sfxge_intr.c. Index: sys/dev/sfxge/sfxge_ev.c =================================================================== --- sys/dev/sfxge/sfxge_ev.c (revision 277726) +++ sys/dev/sfxge/sfxge_ev.c (working copy) @@ -569,13 +569,10 @@ int -sfxge_ev_qpoll(struct sfxge_softc *sc, unsigned int index) +sfxge_ev_qpoll(struct sfxge_evq *evq) { - struct sfxge_evq *evq; int rc; - evq = sc->evq[index]; - mtx_lock(&evq->lock); if (evq->init_state != SFXGE_EVQ_STARTING && --------------050201000503010305030302 Content-Type: text/x-patch; name="03-txq_next.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="03-txq_next.patch" sfxge: Move txq->next pointer to part writable on completion path In fact the pointer is used only if more than one TXQ is processed in one interrupt. It is used (read-write) on completion path only. Also it makes the first part of the structure smaller and it fits now into one 128byte cache line. So, TXQ structure becomes 128 bytes smaller. Sponsored by: Solarflare Communications, Inc. Index: sys/dev/sfxge/sfxge_tx.h =================================================================== --- sys/dev/sfxge/sfxge_tx.h (revision 277726) +++ sys/dev/sfxge/sfxge_tx.h (working copy) @@ -139,7 +139,6 @@ bus_dma_tag_t packet_dma_tag; efx_buffer_t *pend_desc; efx_txq_t *common; - struct sfxge_txq *next; efsys_mem_t *tsoh_buffer; @@ -173,6 +172,7 @@ */ unsigned int pending __aligned(CACHE_LINE_SIZE); unsigned int completed; + struct sfxge_txq *next; }; extern int sfxge_tx_packet_add(struct sfxge_txq *, struct mbuf *); --------------050201000503010305030302 Content-Type: text/x-patch; name="04-expect_init_state.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="04-expect_init_state.patch" sfxge: Expect required init_state on data path and in periodic calls Sponsored by: Solarflare Communications, Inc. Index: sys/dev/sfxge/sfxge_port.c =================================================================== --- sys/dev/sfxge/sfxge_port.c (revision 277726) +++ sys/dev/sfxge/sfxge_port.c (working copy) @@ -50,7 +50,7 @@ mtx_lock(&port->lock); - if (port->init_state != SFXGE_PORT_STARTED) { + if (__predict_false(port->init_state != SFXGE_PORT_STARTED)) { rc = 0; goto out; } @@ -181,7 +181,7 @@ port->wanted_fc = fcntl; - if (port->init_state != SFXGE_PORT_STARTED) + if (__predict_false(port->init_state != SFXGE_PORT_STARTED)) goto out; error = efx_mac_fcntl_set(sc->enp, port->wanted_fc, B_TRUE); @@ -208,7 +208,8 @@ port = &sc->port; mtx_lock(&port->lock); - if (port->init_state == SFXGE_PORT_STARTED && SFXGE_LINK_UP(sc)) + if (__predict_true(port->init_state == SFXGE_PORT_STARTED) && + SFXGE_LINK_UP(sc)) efx_mac_fcntl_get(sc->enp, &wanted_fc, &link_fc); else link_fc = 0; @@ -264,7 +265,7 @@ mtx_lock(&port->lock); - if (port->init_state != SFXGE_PORT_STARTED) + if (__predict_false(port->init_state != SFXGE_PORT_STARTED)) goto done; /* This may sleep waiting for MCDI completion */ @@ -331,7 +332,7 @@ * lock is held in sleeping thread. Both problems are repeatable * on LAG with LACP proto bring up. */ - if (port->init_state == SFXGE_PORT_STARTED) + if (__predict_true(port->init_state == SFXGE_PORT_STARTED)) rc = sfxge_mac_filter_set_locked(sc); else rc = 0; @@ -455,7 +456,7 @@ mtx_lock(&port->lock); - if (port->init_state != SFXGE_PORT_STARTED) { + if (__predict_false(port->init_state != SFXGE_PORT_STARTED)) { rc = 0; goto out; } Index: sys/dev/sfxge/sfxge_rx.c =================================================================== --- sys/dev/sfxge/sfxge_rx.c (revision 277726) +++ sys/dev/sfxge/sfxge_rx.c (working copy) @@ -209,7 +209,7 @@ mtx_assert(&evq->lock, MA_OWNED); - if (rxq->init_state != SFXGE_RXQ_STARTED) + if (__predict_false(rxq->init_state != SFXGE_RXQ_STARTED)) return; rxfill = rxq->added - rxq->completed; @@ -269,7 +269,7 @@ sfxge_rx_qrefill(struct sfxge_rxq *rxq) { - if (rxq->init_state != SFXGE_RXQ_STARTED) + if (__predict_false(rxq->init_state != SFXGE_RXQ_STARTED)) return; /* Make sure the queue is full */ @@ -760,7 +760,7 @@ rx_desc = &rxq->queue[id]; m = rx_desc->mbuf; - if (rxq->init_state != SFXGE_RXQ_STARTED) + if (__predict_false(rxq->init_state != SFXGE_RXQ_STARTED)) goto discard; if (rx_desc->flags & (EFX_ADDR_MISMATCH | EFX_DISCARD)) Index: sys/dev/sfxge/sfxge_ev.c =================================================================== --- sys/dev/sfxge/sfxge_ev.c (revision 277726) +++ sys/dev/sfxge/sfxge_ev.c (working copy) @@ -99,7 +99,7 @@ KASSERT(evq->index == rxq->index, ("evq->index != rxq->index")); - if (rxq->init_state != SFXGE_RXQ_STARTED) + if (__predict_false(rxq->init_state != SFXGE_RXQ_STARTED)) goto done; expected = rxq->pending++ & rxq->ptr_mask; @@ -244,7 +244,7 @@ KASSERT(evq->index == txq->evq_index, ("evq->index != txq->evq_index")); - if (txq->init_state != SFXGE_TXQ_STARTED) + if (__predict_false(txq->init_state != SFXGE_TXQ_STARTED)) goto done; stop = (id + 1) & txq->ptr_mask; @@ -415,7 +415,7 @@ sx_xlock(&sc->softc_lock); - if (sc->evq[0]->init_state != SFXGE_EVQ_STARTED) + if (__predict_false(sc->evq[0]->init_state != SFXGE_EVQ_STARTED)) goto out; now = ticks; @@ -578,8 +578,8 @@ mtx_lock(&evq->lock); - if (evq->init_state != SFXGE_EVQ_STARTING && - evq->init_state != SFXGE_EVQ_STARTED) { + if (__predict_false(evq->init_state != SFXGE_EVQ_STARTING && + evq->init_state != SFXGE_EVQ_STARTED)) { rc = EINVAL; goto fail; } Index: sys/dev/sfxge/sfxge_tx.c =================================================================== --- sys/dev/sfxge/sfxge_tx.c (revision 277726) +++ sys/dev/sfxge/sfxge_tx.c (working copy) @@ -285,7 +285,7 @@ if (mbuf->m_pkthdr.csum_flags & CSUM_TSO) prefetch_read_many(mbuf->m_data); - if (txq->init_state != SFXGE_TXQ_STARTED) { + if (__predict_false(txq->init_state != SFXGE_TXQ_STARTED)) { rc = EINTR; goto reject; } @@ -1084,7 +1084,7 @@ mtx_assert(&evq->lock, MA_OWNED); - if (txq->init_state != SFXGE_TXQ_STARTED) + if (__predict_false(txq->init_state != SFXGE_TXQ_STARTED)) return; mtx_lock(SFXGE_TXQ_LOCK(txq)); Index: sys/dev/sfxge/sfxge_intr.c =================================================================== --- sys/dev/sfxge/sfxge_intr.c (revision 277726) +++ sys/dev/sfxge/sfxge_intr.c (working copy) @@ -135,7 +135,7 @@ KASSERT(intr->type == EFX_INTR_MESSAGE, ("intr->type != EFX_INTR_MESSAGE")); - if (intr->state != SFXGE_INTR_STARTED) + if (__predict_false(intr->state != SFXGE_INTR_STARTED)) return; (void)efx_intr_status_message(enp, index, &fatal); --------------050201000503010305030302 Content-Type: text/x-patch; name="05-bus_stream.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="05-bus_stream.patch" sfxge: Using bus_space_*_stream_* API for better portability Submitted by: Artem V. Andreev Sponsored by: Solarflare Communications, Inc. Index: sys/dev/sfxge/common/efsys.h =================================================================== --- sys/dev/sfxge/common/efsys.h +++ sys/dev/sfxge/common/efsys.h @@ -95,6 +95,13 @@ #define ISP2(x) (((x) & ((x) - 1)) == 0) #endif +#if defined(__x86_64__) +#if !defined(bus_space_read_stream_8) +#define bus_space_read_stream_8(t, h, o) bus_space_read_8((t), (h), (o)) +#define bus_space_write_stream_8(t, h, o) bus_space_write_8((t), (h), (o)) +#endif +#endif + #define ENOTACTIVE EINVAL /* Memory type to use on FreeBSD */ @@ -624,7 +631,7 @@ if (_lock) \ mtx_lock(&((_esbp)->esb_lock)); \ \ - (_edp)->ed_u32[0] = bus_space_read_4((_esbp)->esb_tag, \ + (_edp)->ed_u32[0] = bus_space_read_stream_4((_esbp)->esb_tag, \ (_esbp)->esb_handle, (_offset)); \ \ EFSYS_PROBE2(bar_readd, unsigned int, (_offset), \ @@ -645,7 +652,7 @@ \ mtx_lock(&((_esbp)->esb_lock)); \ \ - (_eqp)->eq_u64[0] = bus_space_read_8((_esbp)->esb_tag, \ + (_eqp)->eq_u64[0] = bus_space_read_stream_8((_esbp)->esb_tag, \ (_esbp)->esb_handle, (_offset)); \ \ EFSYS_PROBE3(bar_readq, unsigned int, (_offset), \ @@ -666,9 +673,9 @@ if (_lock) \ mtx_lock(&((_esbp)->esb_lock)); \ \ - (_eop)->eo_u64[0] = bus_space_read_8((_esbp)->esb_tag, \ + (_eop)->eo_u64[0] = bus_space_read_stream_8((_esbp)->esb_tag, \ (_esbp)->esb_handle, (_offset)); \ - (_eop)->eo_u64[1] = bus_space_read_8((_esbp)->esb_tag, \ + (_eop)->eo_u64[1] = bus_space_read_stream_8((_esbp)->esb_tag, \ (_esbp)->esb_handle, (_offset+8)); \ \ EFSYS_PROBE5(bar_reado, unsigned int, (_offset), \ @@ -692,9 +699,9 @@ \ mtx_lock(&((_esbp)->esb_lock)); \ \ - (_eqp)->eq_u32[0] = bus_space_read_4((_esbp)->esb_tag, \ + (_eqp)->eq_u32[0] = bus_space_read_stream_4((_esbp)->esb_tag, \ (_esbp)->esb_handle, (_offset)); \ - (_eqp)->eq_u32[1] = bus_space_read_4((_esbp)->esb_tag, \ + (_eqp)->eq_u32[1] = bus_space_read_stream_4((_esbp)->esb_tag, \ (_esbp)->esb_handle, (_offset+4)); \ \ EFSYS_PROBE3(bar_readq, unsigned int, (_offset), \ @@ -715,13 +722,13 @@ if (_lock) \ mtx_lock(&((_esbp)->esb_lock)); \ \ - (_eop)->eo_u32[0] = bus_space_read_4((_esbp)->esb_tag, \ + (_eop)->eo_u32[0] = bus_space_read_stream_4((_esbp)->esb_tag, \ (_esbp)->esb_handle, (_offset)); \ - (_eop)->eo_u32[1] = bus_space_read_4((_esbp)->esb_tag, \ + (_eop)->eo_u32[1] = bus_space_read_stream_4((_esbp)->esb_tag, \ (_esbp)->esb_handle, (_offset+4)); \ - (_eop)->eo_u32[2] = bus_space_read_4((_esbp)->esb_tag, \ + (_eop)->eo_u32[2] = bus_space_read_stream_4((_esbp)->esb_tag, \ (_esbp)->esb_handle, (_offset+8)); \ - (_eop)->eo_u32[3] = bus_space_read_4((_esbp)->esb_tag, \ + (_eop)->eo_u32[3] = bus_space_read_stream_4((_esbp)->esb_tag, \ (_esbp)->esb_handle, (_offset+12)); \ \ EFSYS_PROBE5(bar_reado, unsigned int, (_offset), \ --------------050201000503010305030302 Content-Type: text/x-patch; name="06-no_evq_stats_build.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="06-no_evq_stats_build.patch" sfxge: Make it possible to build without EVQ statistics Sponsored by: Solarflare Communications, Inc. Index: sys/dev/sfxge/sfxge.h =================================================================== --- sys/dev/sfxge/sfxge.h (revision 277726) +++ sys/dev/sfxge/sfxge.h (working copy) @@ -225,8 +225,10 @@ struct sfxge_evq *evq[SFXGE_RX_SCALE_MAX]; unsigned int ev_moderation; +#if EFSYS_OPT_QSTATS clock_t ev_stats_update_time; uint64_t ev_stats[EV_NQSTATS]; +#endif uma_zone_t rxq_cache; struct sfxge_rxq *rxq[SFXGE_RX_SCALE_MAX]; Index: sys/dev/sfxge/sfxge_ev.c =================================================================== --- sys/dev/sfxge/sfxge_ev.c (revision 277726) +++ sys/dev/sfxge/sfxge_ev.c (working copy) @@ -406,6 +406,8 @@ return (B_FALSE); } +#if EFSYS_OPT_QSTATS + static void sfxge_ev_stat_update(struct sfxge_softc *sc) { @@ -467,6 +469,8 @@ } } +#endif /* EFSYS_OPT_QSTATS */ + static void sfxge_ev_qmoderate(struct sfxge_softc *sc, unsigned int idx, unsigned int us) { @@ -630,8 +634,10 @@ evq->read_ptr = 0; evq->exception = B_FALSE; +#if EFSYS_OPT_QSTATS /* Add event counts before discarding the common evq state */ efx_ev_qstats_update(evq->common, sc->ev_stats); +#endif efx_ev_qdestroy(evq->common); efx_sram_buf_tbl_clear(sc->enp, evq->buf_base_id, @@ -886,7 +892,9 @@ goto fail; } +#if EFSYS_OPT_QSTATS sfxge_ev_stat_init(sc); +#endif return (0); Index: sys/dev/sfxge/common/efx_tx.c =================================================================== --- sys/dev/sfxge/common/efx_tx.c (revision 277726) +++ sys/dev/sfxge/common/efx_tx.c (working copy) @@ -358,6 +358,7 @@ return (rc); } +#if EFSYS_OPT_QSTATS #if EFSYS_OPT_NAMES /* START MKCONFIG GENERATED EfxTransmitQueueStatNamesBlock 78ca9ab00287fffb */ static const char __cs * __cs __efx_tx_qstat_name[] = { @@ -378,6 +379,7 @@ return (__efx_tx_qstat_name[id]); } #endif /* EFSYS_OPT_NAMES */ +#endif /* EFSYS_OPT_QSTATS */ #if EFSYS_OPT_QSTATS void Index: sys/dev/sfxge/common/efx_ev.c =================================================================== --- sys/dev/sfxge/common/efx_ev.c (revision 277726) +++ sys/dev/sfxge/common/efx_ev.c (working copy) @@ -995,6 +995,7 @@ return (rc); } +#if EFSYS_OPT_QSTATS #if EFSYS_OPT_NAMES /* START MKCONFIG GENERATED EfxEventQueueStatNamesBlock 67e9bdcd920059bd */ static const char __cs * __cs __efx_ev_qstat_name[] = { @@ -1052,6 +1053,7 @@ return (__efx_ev_qstat_name[id]); } #endif /* EFSYS_OPT_NAMES */ +#endif /* EFSYS_OPT_QSTATS */ #if EFSYS_OPT_QSTATS void --------------050201000503010305030302 Content-Type: text/x-patch; name="07-sfxge_evq.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="07-sfxge_evq.patch" sfxge: Remove extra cache-line alignment and reorder sfxge_evq_t Remove the first member alignment to cacheline since it is nop. Use __aligned() for the whole structure to make sure that the structure size is cacheline aligned. Remove lock alignment to make the structure smaller and fit all members used on event queue processing into one cacheline (128 bytes) on x86-64. The lock is obtained as well from different context when event queue statistics are retrived from sysctl context, but it is infrequent. Reorder members to avoid padding and go in usage order on event processing. As the result all structure members used on event queue processing fit into exactly one cacheline (128 byte) now. Sponsored by: Solarflare Communications, Inc. Index: sys/dev/sfxge/sfxge.h =================================================================== --- sys/dev/sfxge/sfxge.h (revision 277726) +++ sys/dev/sfxge/sfxge.h (working copy) @@ -103,27 +103,27 @@ #define SFXGE_EV_BATCH 16384 struct sfxge_evq { - struct sfxge_softc *sc __aligned(CACHE_LINE_SIZE); - struct mtx lock __aligned(CACHE_LINE_SIZE); - + /* Structure members below are sorted by usage order */ + struct sfxge_softc *sc; + struct mtx lock; + unsigned int index; enum sfxge_evq_state init_state; - unsigned int index; - unsigned int entries; efsys_mem_t mem; - unsigned int buf_base_id; - - boolean_t exception; - efx_evq_t *common; unsigned int read_ptr; + boolean_t exception; unsigned int rx_done; unsigned int tx_done; /* Linked list of TX queues with completions to process */ struct sfxge_txq *txq; struct sfxge_txq **txqs; -}; + /* Structure members not used on event processing path */ + unsigned int buf_base_id; + unsigned int entries; +} __aligned(CACHE_LINE_SIZE); + #define SFXGE_NDESCS 1024 #define SFXGE_MODERATION 30 --------------050201000503010305030302 Content-Type: text/x-patch; name="08-tso_vs_vlan.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="08-tso_vs_vlan.patch" sfxge: fixed TSO code to cope with VLAN headers Submitted by: Artem V. Andreev Sponsored by: Solarflare Communications, Inc. Index: sys/dev/sfxge/sfxge_tx.c =================================================================== --- sys/dev/sfxge/sfxge_tx.c (revision 277726) +++ sys/dev/sfxge/sfxge_tx.c (working copy) @@ -855,9 +855,7 @@ tso->tcph_off = tso->nh_off + sizeof(struct ip6_hdr); } - /* We assume all headers are linear in the head mbuf */ tso->header_len = tso->tcph_off + 4 * tso_tcph(tso)->th_off; - KASSERT(tso->header_len <= mbuf->m_len, ("packet headers fragmented")); tso->full_packet_size = tso->header_len + mbuf->m_pkthdr.tso_segsz; tso->seqnum = ntohl(tso_tcph(tso)->th_seq); @@ -972,7 +970,7 @@ tsoh_th = (struct tcphdr *)(header + tso->tcph_off); /* Copy and update the headers. */ - memcpy(header, tso->mbuf->m_data, tso->header_len); + m_copydata(tso->mbuf, 0, tso->header_len, header); tsoh_th->th_seq = htonl(tso->seqnum); tso->seqnum += tso->mbuf->m_pkthdr.tso_segsz; @@ -1018,20 +1016,18 @@ { struct sfxge_tso_state tso; unsigned int id, next_id; + unsigned skipped = 0; tso_start(&tso, mbuf); - /* Grab the first payload fragment. */ - if (dma_seg->ds_len == tso.header_len) { + while (dma_seg->ds_len + skipped <= tso.header_len) { + skipped += dma_seg->ds_len; --n_dma_seg; KASSERT(n_dma_seg, ("no payload found in TSO packet")); ++dma_seg; - tso.in_len = dma_seg->ds_len; - tso.dma_addr = dma_seg->ds_addr; - } else { - tso.in_len = dma_seg->ds_len - tso.header_len; - tso.dma_addr = dma_seg->ds_addr + tso.header_len; } + tso.in_len = dma_seg->ds_len + (tso.header_len - skipped); + tso.dma_addr = dma_seg->ds_addr + (tso.header_len - skipped); id = txq->added & txq->ptr_mask; if (__predict_false(tso_start_new_packet(txq, &tso, id))) --------------050201000503010305030302 Content-Type: text/x-patch; name="09-sfxge_tx_qcomplete.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="09-sfxge_tx_qcomplete.patch" sfxge: Add evq argument to sfxge_tx_qcomplete() It removes necessity to get evq pointer by its index in soft context. Sponsored by: Solarflare Communications, Inc. Index: sys/dev/sfxge/sfxge_tx.h =================================================================== --- sys/dev/sfxge/sfxge_tx.h (revision 277726) +++ sys/dev/sfxge/sfxge_tx.h (working copy) @@ -175,13 +175,15 @@ unsigned int completed; }; +struct sfxge_evq; + extern int sfxge_tx_packet_add(struct sfxge_txq *, struct mbuf *); extern int sfxge_tx_init(struct sfxge_softc *sc); extern void sfxge_tx_fini(struct sfxge_softc *sc); extern int sfxge_tx_start(struct sfxge_softc *sc); extern void sfxge_tx_stop(struct sfxge_softc *sc); -extern void sfxge_tx_qcomplete(struct sfxge_txq *txq); +extern void sfxge_tx_qcomplete(struct sfxge_txq *txq, struct sfxge_evq *evq); extern void sfxge_tx_qflush_done(struct sfxge_txq *txq); #ifdef SFXGE_HAVE_MQ extern void sfxge_if_qflush(struct ifnet *ifp); Index: sys/dev/sfxge/sfxge_ev.c =================================================================== --- sys/dev/sfxge/sfxge_ev.c (revision 277726) +++ sys/dev/sfxge/sfxge_ev.c (working copy) @@ -68,7 +68,7 @@ ("txq->evq_index != index")); if (txq->pending != txq->completed) - sfxge_tx_qcomplete(txq); + sfxge_tx_qcomplete(txq, evq); txq = next; } while (txq != NULL); @@ -262,7 +262,7 @@ } if (txq->pending - txq->completed >= SFXGE_TX_BATCH) - sfxge_tx_qcomplete(txq); + sfxge_tx_qcomplete(txq, evq); done: return (evq->tx_done >= SFXGE_EV_BATCH); Index: sys/dev/sfxge/sfxge_tx.c =================================================================== --- sys/dev/sfxge/sfxge_tx.c (revision 277726) +++ sys/dev/sfxge/sfxge_tx.c (working copy) @@ -105,15 +105,10 @@ const bus_dma_segment_t *dma_seg, int n_dma_seg); void -sfxge_tx_qcomplete(struct sfxge_txq *txq) +sfxge_tx_qcomplete(struct sfxge_txq *txq, struct sfxge_evq *evq) { - struct sfxge_softc *sc; - struct sfxge_evq *evq; unsigned int completed; - sc = txq->sc; - evq = sc->evq[txq->evq_index]; - mtx_assert(&evq->lock, MA_OWNED); completed = txq->completed; @@ -1151,7 +1146,7 @@ txq->blocked = 0; txq->pending = txq->added; - sfxge_tx_qcomplete(txq); + sfxge_tx_qcomplete(txq, evq); KASSERT(txq->completed == txq->added, ("txq->completed != txq->added")); --------------050201000503010305030302 Content-Type: text/x-patch; name="10-no_extra_bzero.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="10-no_extra_bzero.patch" sfxge: Do not bzero() DMA allocated memory once again sfxge_dma_alloc() calls bus_dmamem_alloc() with BUS_DMA_ZERO flag, so allocated memory is already filled in by zeros Sponsored by: Solarflare Communications, Inc. Index: sys/dev/sfxge/sfxge_port.c =================================================================== --- sys/dev/sfxge/sfxge_port.c (revision 277726) +++ sys/dev/sfxge/sfxge_port.c (working copy) @@ -583,7 +583,6 @@ M_SFXGE, M_WAITOK | M_ZERO); if ((rc = sfxge_dma_alloc(sc, EFX_PHY_STATS_SIZE, phy_stats_buf)) != 0) goto fail; - bzero(phy_stats_buf->esm_base, phy_stats_buf->esm_size); sfxge_phy_stat_init(sc); sysctl_ctx = device_get_sysctl_ctx(sc->dev); @@ -605,7 +604,6 @@ M_SFXGE, M_WAITOK | M_ZERO); if ((rc = sfxge_dma_alloc(sc, EFX_MAC_STATS_SIZE, mac_stats_buf)) != 0) goto fail2; - bzero(mac_stats_buf->esm_base, mac_stats_buf->esm_size); sfxge_mac_stat_init(sc); port->init_state = SFXGE_PORT_INITIALIZED; --------------050201000503010305030302 Content-Type: text/x-patch; name="11-no_esm_size.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="11-no_esm_size.patch" sfxge: Remove unused esm_size member of the efsys_mem_t structure esm_size is not even initialized properly when memory is allocated. Sponsored by: Solarflare Communications, Inc. Index: sys/dev/sfxge/common/efsys.h =================================================================== --- sys/dev/sfxge/common/efsys.h (revision 277726) +++ sys/dev/sfxge/common/efsys.h (working copy) @@ -370,7 +370,6 @@ bus_dmamap_t esm_map; caddr_t esm_base; efsys_dma_addr_t esm_addr; - size_t esm_size; } efsys_mem_t; --------------050201000503010305030302 Content-Type: text/x-patch; name="12-free_vaddr.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="12-free_vaddr.patch" sfxge: Pass correct address to free allocated memory in the case of load error Most likely is was just memory leak on the error handling path since typically efsys_mem_t is filled in by zeros on allocation. Sponsored by: Solarflare Communications, Inc. Index: sys/dev/sfxge/sfxge_dma.c =================================================================== --- sys/dev/sfxge/sfxge_dma.c (revision 277726) +++ sys/dev/sfxge/sfxge_dma.c (working copy) @@ -157,7 +157,7 @@ if (bus_dmamap_load(esmp->esm_tag, esmp->esm_map, vaddr, len, sfxge_dma_cb, &esmp->esm_addr, 0) != 0) { device_printf(sc->dev, "Couldn't load DMA mapping\n"); - bus_dmamem_free(esmp->esm_tag, esmp->esm_base, esmp->esm_map); + bus_dmamem_free(esmp->esm_tag, vaddr, esmp->esm_map); bus_dma_tag_destroy(esmp->esm_tag); return (ENOMEM); } --------------050201000503010305030302 Content-Type: text/x-patch; name="13-evq_moderation_init.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="13-evq_moderation_init.patch" sfxge: Use SFXGE_MODERATION to initialize event moderation Sponsored by: Solarflare Communications, Inc. Index: sys/dev/sfxge/sfxge_ev.c =================================================================== --- sys/dev/sfxge/sfxge_ev.c (revision 277726) +++ sys/dev/sfxge/sfxge_ev.c (working copy) @@ -872,7 +872,7 @@ /* Set default interrupt moderation; add a sysctl to * read and change it. */ - sc->ev_moderation = 30; + sc->ev_moderation = SFXGE_MODERATION; SYSCTL_ADD_PROC(sysctl_ctx, SYSCTL_CHILDREN(sysctl_tree), OID_AUTO, "int_mod", CTLTYPE_UINT|CTLFLAG_RW, sc, 0, sfxge_int_mod_handler, "IU", --------------050201000503010305030302 Content-Type: text/x-patch; name="14-max_rss_channels.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="14-max_rss_channels.patch" sfxge: implemented parameter to restrict RSS channels Submitted by: Artem V. Andreev Sponsored by: Solarflare Communications, Inc. Index: sys/dev/sfxge/sfxge.h =================================================================== --- sys/dev/sfxge/sfxge.h (revision 277726) +++ sys/dev/sfxge/sfxge.h (working copy) @@ -228,6 +228,7 @@ clock_t ev_stats_update_time; uint64_t ev_stats[EV_NQSTATS]; + unsigned int max_rss_channels; uma_zone_t rxq_cache; struct sfxge_rxq *rxq[SFXGE_RX_SCALE_MAX]; unsigned int rx_indir_table[SFXGE_RX_SCALE_MAX]; Index: sys/dev/sfxge/sfxge_intr.c =================================================================== --- sys/dev/sfxge/sfxge_intr.c (revision 277726) +++ sys/dev/sfxge/sfxge_intr.c (working copy) @@ -303,6 +303,9 @@ if (count > EFX_MAXRSS) count = EFX_MAXRSS; + if (sc->max_rss_channels > 0 && count > sc->max_rss_channels) + count = sc->max_rss_channels; + rid = PCIR_BAR(4); resp = bus_alloc_resource_any(dev, SYS_RES_MEMORY, &rid, RF_ACTIVE); if (resp == NULL) Index: sys/dev/sfxge/sfxge.c =================================================================== --- sys/dev/sfxge/sfxge.c (revision 277726) +++ sys/dev/sfxge/sfxge.c (working copy) @@ -397,11 +397,18 @@ device_t dev; efx_nic_t *enp; int error; + char rss_param_name[sizeof(SFXGE_PARAM(%d.max_rss_channels))]; dev = sc->dev; sx_init(&sc->softc_lock, "sfxge_softc"); + sc->max_rss_channels = 0; + snprintf(rss_param_name, sizeof(rss_param_name), + SFXGE_PARAM(%d.max_rss_channels), + (int)device_get_unit(dev)); + TUNABLE_INT_FETCH(rss_param_name, &sc->max_rss_channels); + sc->stats_node = SYSCTL_ADD_NODE( device_get_sysctl_ctx(dev), SYSCTL_CHILDREN(device_get_sysctl_tree(dev)), Index: share/man/man4/sfxge.4 =================================================================== --- share/man/man4/sfxge.4 (revision 277726) +++ share/man/man4/sfxge.4 (working copy) @@ -108,6 +108,10 @@ .Va tx_early_drops counter is incremented and the local sender receives ENOBUFS. The value must be greater than or equal to 0. +.It Va hw.sfxge.N.max_rss_channels +The maximum number of allocated RSS channels for the Nth adapter. +If set to 0 or unset, the number of channels is determined by the number +of CPU cores. .El .Sh SUPPORT For general information and support, --------------050201000503010305030302 Content-Type: text/x-patch; name="15-stats_port_lock.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="15-stats_port_lock.patch" sfxge: access statistics buffers under port lock Allow access to statistics data not only from sysctl handlers. Submitted by: Boris Misenov Sponsored by: Solarflare Communications, Inc. Index: sys/dev/sfxge/sfxge_port.c =================================================================== --- sys/dev/sfxge/sfxge_port.c (revision 277726) +++ sys/dev/sfxge/sfxge_port.c (working copy) @@ -48,7 +48,7 @@ unsigned int count; int rc; - mtx_lock(&port->lock); + mtx_assert(&port->lock, MA_OWNED); if (port->init_state != SFXGE_PORT_STARTED) { rc = 0; @@ -82,7 +82,6 @@ rc = ETIMEDOUT; out: - mtx_unlock(&port->lock); return (rc); } @@ -93,12 +92,16 @@ unsigned int id = arg2; int rc; + mtx_lock(&sc->port.lock); if ((rc = sfxge_mac_stat_update(sc)) != 0) - return (rc); + goto out; - return (SYSCTL_OUT(req, - (uint64_t *)sc->port.mac_stats.decode_buf + id, - sizeof(uint64_t))); + rc = SYSCTL_OUT(req, + (uint64_t *)sc->port.mac_stats.decode_buf + id, + sizeof(uint64_t)); +out: + mtx_unlock(&sc->port.lock); + return (rc); } static void @@ -453,7 +456,7 @@ unsigned int count; int rc; - mtx_lock(&port->lock); + mtx_assert(&port->lock, MA_OWNED); if (port->init_state != SFXGE_PORT_STARTED) { rc = 0; @@ -487,7 +490,6 @@ rc = ETIMEDOUT; out: - mtx_unlock(&port->lock); return (rc); } @@ -498,12 +500,16 @@ unsigned int id = arg2; int rc; + mtx_lock(&sc->port.lock); if ((rc = sfxge_phy_stat_update(sc)) != 0) - return (rc); + goto out; - return (SYSCTL_OUT(req, - (uint32_t *)sc->port.phy_stats.decode_buf + id, - sizeof(uint32_t))); + rc = SYSCTL_OUT(req, + (uint32_t *)sc->port.phy_stats.decode_buf + id, + sizeof(uint32_t)); +out: + mtx_unlock(&sc->port.lock); + return (rc); } static void --------------050201000503010305030302 Content-Type: text/x-patch; name="17-non_tcp_get_list.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename="17-non_tcp_get_list.patch" sfxge: Separate software Tx queue limit for non-TCP traffic Add separate software Tx queue limit for non-TCP traffic to make total limit higher and avoid local drops of TCP packets because of no backpressure. There is no point to make non-TCP limit high since without backpressure UDP stream easily overflows any sensible limit. Split early drops statistics since it is better to have separate counter for each drop reason to make it unabmiguous. Add software Tx queue high watermark. The information is very useful to understand how big queues grow under traffic load. Sponsored by: Solarflare Communications, Inc. Index: share/man/man4/sfxge.4 =================================================================== --- share/man/man4/sfxge.4 (revision 277737) +++ share/man/man4/sfxge.4 (working copy) @@ -93,19 +93,27 @@ .It Va hw.sfxge.tx_dpl_get_max The maximum length of the deferred packet .Dq get-list -for queued transmit -packets, used only if the transmit queue lock can be acquired. +for queued transmit packets (TCP and non-TCP), used only if the transmit +queue lock can be acquired. If a packet is dropped, the -.Va tx_early_drops +.Va tx_get_overflow counter is incremented and the local sender receives ENOBUFS. The value must be greater than 0. +.It Va hw.sfxge.tx_dpl_get_non_tcp_max +The maximum number of non-TCP packets in the deferred packet +.Dq get-list +, used only if the transmit queue lock can be acquired. +If packet is dropped, the +.Va tx_get_non_tcp_overflow +counter is incremented and the local sender receives ENOBUFS. +The value must be greater than 0. .It Va hw.sfxge.tx_dpl_put_max The maximum length of the deferred packet .Dq put-list for queued transmit packets, used if the transmit queue lock cannot be acquired. If a packet is dropped, the -.Va tx_early_drops +.Va tx_put_overflow counter is incremented and the local sender receives ENOBUFS. The value must be greater than or equal to 0. .El Index: sys/dev/sfxge/sfxge_tx.c =================================================================== --- sys/dev/sfxge/sfxge_tx.c (revision 277737) +++ sys/dev/sfxge/sfxge_tx.c (working copy) @@ -85,14 +85,23 @@ TUNABLE_INT(SFXGE_PARAM_TX_DPL_GET_MAX, &sfxge_tx_dpl_get_max); SYSCTL_INT(_hw_sfxge, OID_AUTO, tx_dpl_get_max, CTLFLAG_RDTUN, &sfxge_tx_dpl_get_max, 0, - "Maximum number of packets in deferred packet get-list"); + "Maximum number of any packets in deferred packet get-list"); +#define SFXGE_PARAM_TX_DPL_GET_NON_TCP_MAX \ + SFXGE_PARAM(tx_dpl_get_non_tcp_max) +static int sfxge_tx_dpl_get_non_tcp_max = + SFXGE_TX_DPL_GET_NON_TCP_PKT_LIMIT_DEFAULT; +TUNABLE_INT(SFXGE_PARAM_TX_DPL_GET_NON_TCP_MAX, &sfxge_tx_dpl_get_non_tcp_max); +SYSCTL_INT(_hw_sfxge, OID_AUTO, tx_dpl_get_non_tcp_max, CTLFLAG_RDTUN, + &sfxge_tx_dpl_get_non_tcp_max, 0, + "Maximum number of non-TCP packets in deferred packet get-list"); + #define SFXGE_PARAM_TX_DPL_PUT_MAX SFXGE_PARAM(tx_dpl_put_max) static int sfxge_tx_dpl_put_max = SFXGE_TX_DPL_PUT_PKT_LIMIT_DEFAULT; TUNABLE_INT(SFXGE_PARAM_TX_DPL_PUT_MAX, &sfxge_tx_dpl_put_max); SYSCTL_INT(_hw_sfxge, OID_AUTO, tx_dpl_put_max, CTLFLAG_RDTUN, &sfxge_tx_dpl_put_max, 0, - "Maximum number of packets in deferred packet put-list"); + "Maximum number of any packets in deferred packet put-list"); #endif @@ -152,6 +161,15 @@ #ifdef SFXGE_HAVE_MQ +static inline unsigned int +sfxge_is_mbuf_non_tcp(struct mbuf *mbuf) +{ + /* Absense of TCP checksum flags does not mean that it is non-TCP + * but it should be true if user wants to achieve high throughput. + */ + return (!(mbuf->m_pkthdr.csum_flags & (CSUM_IP_TCP | CSUM_IP6_TCP))); +} + /* * Reorder the put list and append it to the get list. */ @@ -163,6 +181,7 @@ volatile uintptr_t *putp; uintptr_t put; unsigned int count; + unsigned int non_tcp_count; mtx_assert(&txq->lock, MA_OWNED); @@ -181,9 +200,11 @@ get_next = NULL; count = 0; + non_tcp_count = 0; do { struct mbuf *put_next; + non_tcp_count += sfxge_is_mbuf_non_tcp(mbuf); put_next = mbuf->m_nextpkt; mbuf->m_nextpkt = get_next; get_next = mbuf; @@ -197,6 +218,7 @@ *stdp->std_getp = get_next; stdp->std_getp = get_tailp; stdp->std_get_count += count; + stdp->std_get_non_tcp_count += non_tcp_count; } #endif /* SFXGE_HAVE_MQ */ @@ -387,6 +409,7 @@ struct sfxge_tx_dpl *stdp; struct mbuf *mbuf, *next; unsigned int count; + unsigned int non_tcp_count; unsigned int pushed; int rc; @@ -401,7 +424,11 @@ mbuf = stdp->std_get; count = stdp->std_get_count; + non_tcp_count = stdp->std_get_non_tcp_count; + if (count > stdp->std_get_hiwat) + stdp->std_get_hiwat = count; + while (count != 0) { KASSERT(mbuf != NULL, ("mbuf == NULL")); @@ -415,6 +442,7 @@ rc = sfxge_tx_queue_mbuf(txq, mbuf); --count; + non_tcp_count -= sfxge_is_mbuf_non_tcp(mbuf); mbuf = next; if (rc != 0) continue; @@ -431,12 +459,16 @@ if (count == 0) { KASSERT(mbuf == NULL, ("mbuf != NULL")); + KASSERT(non_tcp_count == 0, + ("inconsistent TCP/non-TCP detection")); stdp->std_get = NULL; stdp->std_get_count = 0; + stdp->std_get_non_tcp_count = 0; stdp->std_getp = &stdp->std_get; } else { stdp->std_get = mbuf; stdp->std_get_count = count; + stdp->std_get_non_tcp_count = non_tcp_count; } if (txq->added != pushed) @@ -496,8 +528,18 @@ sfxge_tx_qdpl_swizzle(txq); - if (stdp->std_get_count >= stdp->std_get_max) + if (stdp->std_get_count >= stdp->std_get_max) { + txq->get_overflow++; return (ENOBUFS); + } + if (sfxge_is_mbuf_non_tcp(mbuf)) { + if (stdp->std_get_non_tcp_count >= + stdp->std_get_non_tcp_max) { + txq->get_non_tcp_overflow++; + return (ENOBUFS); + } + stdp->std_get_non_tcp_count++; + } *(stdp->std_getp) = mbuf; stdp->std_getp = &mbuf->m_nextpkt; @@ -518,8 +560,10 @@ old_len = mp->m_pkthdr.csum_data; } else old_len = 0; - if (old_len >= stdp->std_put_max) + if (old_len >= stdp->std_put_max) { + atomic_add_long(&txq->put_overflow, 1); return (ENOBUFS); + } mbuf->m_pkthdr.csum_data = old_len + 1; mbuf->m_nextpkt = (void *)old; } while (atomic_cmpset_ptr(putp, old, new) == 0); @@ -540,6 +584,7 @@ if (!SFXGE_LINK_UP(txq->sc)) { rc = ENETDOWN; + atomic_add_long(&txq->netdown_drops, 1); goto fail; } @@ -577,7 +622,6 @@ fail: m_freem(m); - atomic_add_long(&txq->early_drops, 1); return (rc); } @@ -596,6 +640,7 @@ } stdp->std_get = NULL; stdp->std_get_count = 0; + stdp->std_get_non_tcp_count = 0; stdp->std_getp = &stdp->std_get; mtx_unlock(&txq->lock); @@ -1411,6 +1456,13 @@ rc = EINVAL; goto fail_tx_dpl_get_max; } + if (sfxge_tx_dpl_get_non_tcp_max <= 0) { + log(LOG_ERR, "%s=%d must be greater than 0", + SFXGE_PARAM_TX_DPL_GET_NON_TCP_MAX, + sfxge_tx_dpl_get_non_tcp_max); + rc = EINVAL; + goto fail_tx_dpl_get_max; + } if (sfxge_tx_dpl_put_max < 0) { log(LOG_ERR, "%s=%d must be greater or equal to 0", SFXGE_PARAM_TX_DPL_PUT_MAX, sfxge_tx_dpl_put_max); @@ -1422,6 +1474,7 @@ stdp = &txq->dpl; stdp->std_put_max = sfxge_tx_dpl_put_max; stdp->std_get_max = sfxge_tx_dpl_get_max; + stdp->std_get_non_tcp_max = sfxge_tx_dpl_get_non_tcp_max; stdp->std_getp = &stdp->std_get; mtx_init(&txq->lock, "txq", NULL, MTX_DEF); @@ -1430,6 +1483,14 @@ SYSCTL_CHILDREN(txq_node), OID_AUTO, "dpl_get_count", CTLFLAG_RD | CTLFLAG_STATS, &stdp->std_get_count, 0, ""); + SYSCTL_ADD_UINT(device_get_sysctl_ctx(sc->dev), + SYSCTL_CHILDREN(txq_node), OID_AUTO, + "dpl_get_non_tcp_count", CTLFLAG_RD | CTLFLAG_STATS, + &stdp->std_get_non_tcp_count, 0, ""); + SYSCTL_ADD_UINT(device_get_sysctl_ctx(sc->dev), + SYSCTL_CHILDREN(txq_node), OID_AUTO, + "dpl_get_hiwat", CTLFLAG_RD | CTLFLAG_STATS, + &stdp->std_get_hiwat, 0, ""); #endif txq->type = type; @@ -1467,7 +1528,10 @@ SFXGE_TX_STAT(tso_long_headers, tso_long_headers), SFXGE_TX_STAT(tx_collapses, collapses), SFXGE_TX_STAT(tx_drops, drops), - SFXGE_TX_STAT(tx_early_drops, early_drops), + SFXGE_TX_STAT(tx_get_overflow, get_overflow), + SFXGE_TX_STAT(tx_get_non_tcp_overflow, get_non_tcp_overflow), + SFXGE_TX_STAT(tx_put_overflow, put_overflow), + SFXGE_TX_STAT(tx_netdown_drops, netdown_drops), }; static int Index: sys/dev/sfxge/sfxge_tx.h =================================================================== --- sys/dev/sfxge/sfxge_tx.h (revision 277737) +++ sys/dev/sfxge/sfxge_tx.h (working copy) @@ -75,21 +75,29 @@ enum sfxge_tx_buf_flags flags; }; -#define SFXGE_TX_DPL_GET_PKT_LIMIT_DEFAULT 1024 -#define SFXGE_TX_DPL_PUT_PKT_LIMIT_DEFAULT 64 +#define SFXGE_TX_DPL_GET_PKT_LIMIT_DEFAULT (64 * 1024) +#define SFXGE_TX_DPL_GET_NON_TCP_PKT_LIMIT_DEFAULT 1024 +#define SFXGE_TX_DPL_PUT_PKT_LIMIT_DEFAULT 64 /* * Deferred packet list. */ struct sfxge_tx_dpl { - unsigned int std_get_max; /* Maximum number of packets + unsigned int std_get_max; /* Maximum number of packets * in get list */ - unsigned int std_put_max; /* Maximum number of packets + unsigned int std_get_non_tcp_max; /* Maximum number + * of non-TCP packets + * in get list */ + unsigned int std_put_max; /* Maximum number of packets * in put list */ - uintptr_t std_put; /* Head of put list. */ - struct mbuf *std_get; /* Head of get list. */ - struct mbuf **std_getp; /* Tail of get list. */ - unsigned int std_get_count; /* Packets in get list. */ + uintptr_t std_put; /* Head of put list. */ + struct mbuf *std_get; /* Head of get list. */ + struct mbuf **std_getp; /* Tail of get list. */ + unsigned int std_get_count; /* Packets in get list. */ + unsigned int std_get_non_tcp_count; /* Non-TCP packets + * in get list */ + unsigned int std_get_hiwat; /* Packets in get list + * high watermark */ }; @@ -166,7 +174,10 @@ unsigned long tso_long_headers; unsigned long collapses; unsigned long drops; - unsigned long early_drops; + unsigned long get_overflow; + unsigned long get_non_tcp_overflow; + unsigned long put_overflow; + unsigned long netdown_drops; /* The following fields change more often, and are used mostly * on the completion path --------------050201000503010305030302-- From owner-freebsd-net@FreeBSD.ORG Mon Jan 26 13:11:05 2015 Return-Path: Delivered-To: net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 13BF9929 for ; Mon, 26 Jan 2015 13:11:05 +0000 (UTC) Received: from mail-qc0-x233.google.com (mail-qc0-x233.google.com [IPv6:2607:f8b0:400d:c01::233]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id BE954ED2 for ; Mon, 26 Jan 2015 13:11:04 +0000 (UTC) Received: by mail-qc0-f179.google.com with SMTP id w7so6645531qcr.10 for ; Mon, 26 Jan 2015 05:11:03 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=sender:content-type:mime-version:subject:from:in-reply-to:date:cc :content-transfer-encoding:message-id:references:to; bh=LW1ZcEW3w0wGS3vSk+CaB38siKI0xZTwxmPUDV1AjH8=; b=redfrLv6yFBNxua+qX6XSx+CSRbQIFuHsKyXOdhP+dGhUe6daj2MT/VoNcMhJwcLMY cKgF5r21yczptiffqLppHOX1PTiH13n/JcZ1TCVg7HrVc1EF9g0EdVEd58X2TdhuLb6L 3Do1DalY8fudiuCejQqEvvb/Fr5ISX2H9XdfJ7RDxwVKauTB3dZp/FKe6xjEc9zF0BJ8 3jV/BPE1m4M6WCphIxXchoqxb1DFaKWqTlQ62gWOr765KHaalZPtSop0mxsYS+MmgpAD 9tC86yHPoUfQ6G2E3vcuu12yc2gi+l6Dd4xHnvf9qGWFxMNZXSWYX1tgD8oj7+f7H8Wy KXlg== X-Received: by 10.140.37.39 with SMTP id q36mr39258095qgq.89.1422277863579; Mon, 26 Jan 2015 05:11:03 -0800 (PST) Received: from mbp.home ([177.131.83.121]) by mx.google.com with ESMTPSA id q78sm9891184qgq.5.2015.01.26.05.11.01 (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Mon, 26 Jan 2015 05:11:02 -0800 (PST) Sender: Renato Botelho Content-Type: text/plain; charset=us-ascii Mime-Version: 1.0 (Mac OS X Mail 8.1 \(1993\)) Subject: Re: [PATCH] sfxge improvements and bug fixes From: Renato Botelho In-Reply-To: <54C62954.5030004@oktetlabs.ru> Date: Mon, 26 Jan 2015 11:10:57 -0200 Content-Transfer-Encoding: quoted-printable Message-Id: <1241FC5F-46B9-4D62-8EF7-E107EE4D3F66@FreeBSD.org> References: <54C62954.5030004@oktetlabs.ru> To: Andrew Rybchenko X-Mailer: Apple Mail (2.1993) Cc: net@FreeBSD.org X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 26 Jan 2015 13:11:05 -0000 > On Jan 26, 2015, at 09:47, Andrew Rybchenko = wrote: >=20 > Hello, >=20 > my colleagues and me have a number of patches to sfxge driver = including: > - performance optimizations > - fix TSO to work fine when VLAN is used (IPv6 does not work yet, to = be fixed in the nearest time) > - add tunable to control maximum number of RSS channels > - improve software Tx queue to have separate limits for TCP and = non-TCP traffic and more granular overflow statistics > - cleanup >=20 > Patches are attached. >=20 > The goal of the submission is to get feedback and review notes = (including mentor). Hello Andrew, Did you consider to add them to Phabricator [1]? [1] https://reviews.freebsd.org Regards -- Renato Botelho From owner-freebsd-net@FreeBSD.ORG Mon Jan 26 21:21:08 2015 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 134BB3A2 for ; Mon, 26 Jan 2015 21:21:08 +0000 (UTC) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id EDDDEF44 for ; Mon, 26 Jan 2015 21:21:07 +0000 (UTC) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.14.9/8.14.9) with ESMTP id t0QLL7DW056457 for ; Mon, 26 Jan 2015 21:21:07 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 193053] ixgbe(4) IXGBE_LEGACY_TX + ALTQ path broken Date: Mon, 26 Jan 2015 21:21:07 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.1-STABLE X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Some People X-Bugzilla-Who: ncrogers@gmail.com X-Bugzilla-Status: New X-Bugzilla-Priority: Normal X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: version Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 26 Jan 2015 21:21:08 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=193053 ncrogers@gmail.com changed: What |Removed |Added ---------------------------------------------------------------------------- Version|10.1-RC2 |10.1-STABLE -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 00:34:33 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 36CAFAF3 for ; Tue, 27 Jan 2015 00:34:33 +0000 (UTC) Received: from na01-bl2-obe.outbound.protection.outlook.com (mail-bl2on0133.outbound.protection.outlook.com [65.55.169.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-SHA384 (256/256 bits)) (Client CN "mail.protection.outlook.com", Issuer "MSIT Machine Auth CA 2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id B1874AAA for ; Tue, 27 Jan 2015 00:34:32 +0000 (UTC) Received: from CO2PR05MB761.namprd05.prod.outlook.com (10.141.227.13) by CO2PR05MB763.namprd05.prod.outlook.com (10.141.227.15) with Microsoft SMTP Server (TLS) id 15.1.65.19; Tue, 27 Jan 2015 00:00:19 +0000 Received: from CO2PR05MB761.namprd05.prod.outlook.com ([10.141.227.13]) by CO2PR05MB761.namprd05.prod.outlook.com ([10.141.227.13]) with mapi id 15.01.0065.013; Tue, 27 Jan 2015 00:00:19 +0000 From: Sreekanth Rupavatharam To: "freebsd-net@freebsd.org" Subject: Double cleanup in igb_attach Thread-Topic: Double cleanup in igb_attach Thread-Index: AQHQOcQ8M6DG1/D37kKlfeofCj44QA== Date: Tue, 27 Jan 2015 00:00:19 +0000 Message-ID: Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: user-agent: Microsoft-MacOutlook/14.4.7.141117 x-originating-ip: [66.129.239.14] authentication-results: freebsd.org; dkim=none (message not signed) header.d=none;freebsd.org; dmarc=none action=none header.from=juniper.net; x-dmarcaction-test: None x-microsoft-antispam: BCL:0;PCL:0;RULEID:(3005004);SRVR:CO2PR05MB763; x-exchange-antispam-report-test: UriScan:; x-exchange-antispam-report-cfa-test: BCL:0;PCL:0;RULEID:;SRVR:CO2PR05MB763; x-forefront-prvs: 046985391D x-forefront-antispam-report: SFV:NSPM; SFS:(10019020)(6009001)(164054003)(92566002)(110136001)(62966003)(2656002)(77156002)(77096005)(40100003)(2900100001)(122556002)(102836002)(66066001)(46102003)(2351001)(107886001)(229853001)(83506001)(106116001)(50986999)(99286002)(36756003)(16236675004)(450100001)(87936001)(86362001)(54356999); DIR:OUT; SFP:1102; SCL:1; SRVR:CO2PR05MB763; H:CO2PR05MB761.namprd05.prod.outlook.com; FPR:; SPF:None; MLV:sfv; LANG:en; MIME-Version: 1.0 X-OriginatorOrg: juniper.net X-MS-Exchange-CrossTenant-originalarrivaltime: 27 Jan 2015 00:00:19.1605 (UTC) X-MS-Exchange-CrossTenant-fromentityheader: Hosted X-MS-Exchange-CrossTenant-id: bea78b3c-4cdb-4130-854a-1d193232e5f4 X-MS-Exchange-Transport-CrossTenantHeadersStamped: CO2PR05MB763 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: base64 X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 00:34:33 -0000 QXBvbG9naWVzIGlmIHRoaXMgaXMgbm90IHRoZSByaWdodCBmb3J1bS4gSW4gaWdiX2F0dGFjaCBm dW5jdGlvbiwgd2UgaGF2ZSB0aGlzIGNvZGUuDQplcnJfbGF0ZToNCmlnYl9kZXRhY2goZGV2KTsN CiAgICAgICAgaWdiX2ZyZWVfdHJhbnNtaXRfc3RydWN0dXJlcyhhZGFwdGVyKTsNCiAgICAgICAg aWdiX2ZyZWVfcmVjZWl2ZV9zdHJ1Y3R1cmVzKGFkYXB0ZXIpOw0KICAgICAgICBpZ2JfcmVsZWFz ZV9od19jb250cm9sKGFkYXB0ZXIpOw0KZXJyX3BjaToNCiAgICAgICAgaWdiX2ZyZWVfcGNpX3Jl c291cmNlcyhhZGFwdGVyKTsNCiAgICAgICAgaWYgKGFkYXB0ZXItPmlmcCAhPSBOVUxMKQ0KICAg ICAgICAgICAgICAgIGlmX2ZyZWUoYWRhcHRlci0+aWZwKTsNCiAgICAgICAgZnJlZShhZGFwdGVy LT5tdGEsIE1fREVWQlVGKTsNCiAgICAgICAgSUdCX0NPUkVfTE9DS19ERVNUUk9ZKGFkYXB0ZXIp Ow0KDQpUaGUgcHJvYmxlbSBpcyB0aGF0IGlnYl9kZXRhY2ggYWxzbyBkb2VzIHRoZSBzYW1lIGNs ZWFudXAgaW4gaXTigJlzIGJvZHkuIE9ubHkgZXhjZXB0aW9uIGlzIHRoaXMgY2FzZSB3aGVyZSBp dCBqdXN0IHJldHVybnMgRUJVU1kNCiAgICAgICAgLyogTWFrZSBzdXJlIFZMQU5TIGFyZSBub3Qg dXNpbmcgZHJpdmVyICovDQppZiAoaWZfdmxhbnRydW5raW51c2UoaWZwKSkgew0KZGV2aWNlX3By aW50ZihkZXYsIlZsYW4gaW4gdXNlLCBkZXRhY2ggZmlyc3RcbiIpOw0KcmV0dXJuIChFQlVTWSk7 DQp9DQoNCkkgdGhpbmsgdGhlIGNvZGUgaW4gaWdiX2F0dGFjaCBzaG91bGQgYmUgY2hhbmdlZCB0 byBmcmVlIHVwIHJlc291cmNlcyBvbmx5IGlmIHRoZSBpZ2JfZGV0YWNoIHJldHVybnMgYW4gZXJy b3IuIEhlcmXigJlzIHRoZSBwYXRjaCBmb3IgaXQuDQoNCg0KSW5kZXg6IGlmX2lnYi5jDQoNCj09 PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09 PT09PT09PT0NCg0KLS0tIGlmX2lnYi5jIChyZXZpc2lvbiAyOTgwMjUpDQoNCisrKyBpZl9pZ2Iu YyAod29ya2luZyBjb3B5KQ0KDQpAQCAtNzIzLDcgKzcyMyw4IEBAIGlnYl9hdHRhY2goZGV2aWNl X3QgZGV2KQ0KDQogIHJldHVybiAoMCk7DQoNCg0KDQogZXJyX2xhdGU6DQoNCi0gaWdiX2RldGFj aChkZXYpOw0KDQorIGlmKGlnYl9kZXRhY2goZGV2KSA9PSAwKSAvKiBpZ2JfZGV0YWNoIGRpZCB0 aGUgY2xlYW51cCAqLw0KDQorIHJldHVybjsNCg0KICBpZ2JfZnJlZV90cmFuc21pdF9zdHJ1Y3R1 cmVzKGFkYXB0ZXIpOw0KDQogQ2FuIGFueW9uZSBjb21tZW50IG9uIGl0IGFuZCB0ZWxsIG1lIGlm IG15IHVuZGVyc3RhbmRpbmcgaXMgaW5jb3JyZWN0Pw0KDQotLSBUaGFua3MsDQoNClNyZWVrYW50 aA0KDQoNCg== From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 10:59:38 2015 Return-Path: Delivered-To: net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 66AE7245 for ; Tue, 27 Jan 2015 10:59:38 +0000 (UTC) Received: from onlyone.friendlyhosting.spb.ru (onlyone.friendlyhosting.spb.ru [IPv6:2a01:4f8:131:60a2::2]) by mx1.freebsd.org (Postfix) with ESMTP id 2B96E401 for ; Tue, 27 Jan 2015 10:59:38 +0000 (UTC) Received: from [127.0.0.1] (nat.in.devexperts.com [89.113.128.63]) (Authenticated sender: lev@serebryakov.spb.ru) by onlyone.friendlyhosting.spb.ru (Postfix) with ESMTPSA id 208DF5C003 for ; Tue, 27 Jan 2015 13:59:25 +0300 (MSK) Message-ID: <54C76F8A.4070104@FreeBSD.org> Date: Tue, 27 Jan 2015 13:59:22 +0300 From: Lev Serebryakov Reply-To: lev@FreeBSD.org Organization: FreeBSD User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:31.0) Gecko/20100101 Thunderbird/31.4.0 MIME-Version: 1.0 To: net@FreeBSD.org Subject: ipfw, source-based routing, "forward" action and unknown GW address Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 8bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 10:59:38 -0000 -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA512 I have typical task at hands: two providers, no AS, no real IPv4 addresses in network, IPv4 NAT for both connections. Typical solution for this task is two NATs, "global" rule for outgoing packets and two "forward" rules based on source address after "nat global", am I right? But here is problem: "forward" rule uses "next hop IP". And one of my providers change this IP from time to time. It assigns same IP for me (I'm paying for "fixed IP") via DHCP, but "default router" option could be different (looks like load-balancing). Is here any way to solve this "source based routing" problem without changing rules in firewall on each DHCP lease re-acquisition? - -- // Lev Serebryakov -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (MingW32) iQJ8BAEBCgBmBQJUx2+KXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRGOTZEMUNBMEI1RjQzMThCNjc0QjMzMEFF QUIwM0M1OEJGREM0NzhGAAoJEOqwPFi/3EePCPAQAKVXGb9QmahvGNvTAwWp1gDj AxWNnEkBQau209kkUFGma55VtLe5vjXwmjnxyC66zAec2Je44TAF1vYtr0GAevVp nRnLznsb+mN3tqI5Y5nlqugJyBzJiJWE6p5uFHsDxmYXmyA0/kQoLUt3JjlyZfLg JDpMUrJ6KIqwgVmq8gASVQhMzsLkreBItht20tFjEdUxcVnXISkpLfTbXJXZb0yi SntAwsrVaMhwpuSskiz26TTersVDHppKILGaJTSCYff6Tm0tLFeHwRKneK+KqBRk YCgCsD3gT8yPpRjqdBSawSapVpl1J2eRHSiZ+fo4DpAt3XHUkZD+HAFdWwszrD2X fdwAnHP94scjK//mV6MZXSS7sp8iAgGmm+sTeVl9N4F43hYazSyANwXjdcNm/Sc2 kZnYrWJInJUfP+6w+jWG7YaYMhC4hdxlEyeMoh37x6roUMWCUxraqQ/HUKlPiwtV EhEPhRnUr6ZQv2Qv5WhjjaRYnLgNUb/M//EVftOsYdmek/uScunz5KCa9IM6SR+m T6aa6YmJ7vAI12b04muG6/niknKavbmvn1bSvzDhxax/CivPp+paJkiPlq4MvNcv uEClqKQ28GcC3vOmx3ILjtOFXaqqBGqh7rj2EkPMSaOvw+7tVK5JaWBGy9WqQTLY 2GsVhcwZUT7xrjoa9tyX =LJQo -----END PGP SIGNATURE----- From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 17:28:50 2015 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id E1FCA821 for ; Tue, 27 Jan 2015 17:28:50 +0000 (UTC) Received: from marcos.anarc.at (mail.orangeseeds.org [72.0.72.144]) by mx1.freebsd.org (Postfix) with ESMTP id 8E947A6C for ; Tue, 27 Jan 2015 17:28:47 +0000 (UTC) Received: by marcos.anarc.at (Postfix, from userid 1000) id DC2CF1A006C; Tue, 27 Jan 2015 12:28:46 -0500 (EST) From: Antoine =?utf-8?Q?Beaupr=C3=A9?= To: freebsd-net@FreeBSD.org Subject: is polling still a thing? User-Agent: Notmuch/0.18.2 (http://notmuchmail.org) Emacs/24.4.1 (x86_64-pc-linux-gnu) Date: Tue, 27 Jan 2015 12:28:46 -0500 Message-ID: <871tmgceup.fsf@marcos.anarc.at> MIME-Version: 1.0 Content-Type: text/plain X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 17:28:51 -0000 (Please CC, as i am not on the list.) I was surprised to read this article in the pfSense blog: https://blog.pfsense.org/?p=115 TLDR: "At this time, polling is not recommended at all." Is that true? I am trying to tweak a Supermicro machine as a router to survive major DDOS attacks on a 1gbps link. So far, I can't get far beyond the 100kpps and 50mbps mark. The hardware is: * 2xIntel E1G44HTBLK NICs * 1xIntel 1220LV2 CPU More detailed specs here: https://wiki.koumbit.net/rtr1.koumbit.net We are using a stateful pf firewall and polling on the network interfaces. We got around 100kpps during the DDOS, with 700kpps dropped (or at least 700k/s errors) on the NIC. The DDOS was apparently 5.5gbps but around 400mbps reached our port from upstream's point of view. The kernel interfaces counted around 50mbps: https://redmine.koumbit.net/attachments/download/7706 https://redmine.koumbit.net/attachments/download/7707 https://redmine.koumbit.net/attachments/download/7708 https://redmine.koumbit.net/attachments/download/7709 The load on the router was fine during the DDOS, but of course packet loss was endemic. At this point, I'm considering the following options: * switching to an Intel IGB nic * enabling fastforwarding * tweak the number of IGB queues Any recommendations would be welcome. Thanks! A. -- feature, n: a documented bug | bug, n: an undocumented feature - Mario S F Ferreira From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 18:03:20 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id D10FF2C8 for ; Tue, 27 Jan 2015 18:03:20 +0000 (UTC) Received: from mail-oi0-f49.google.com (mail-oi0-f49.google.com [209.85.218.49]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 94D99E92 for ; Tue, 27 Jan 2015 18:03:20 +0000 (UTC) Received: by mail-oi0-f49.google.com with SMTP id a3so13580526oib.8 for ; Tue, 27 Jan 2015 10:03:19 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:content-type:mime-version:subject:from :in-reply-to:date:cc:message-id:references:to; bh=dCYi+c1YUh6f49YmmgghummPgvLd3qyI69uNNzG1K4E=; b=jQ+sVnaxmWNH0srHm80Cnp1m4e9Kh5VNGyD8XNmkFvNtdbdOANhvTfZDkwPc4Qt9LJ kkLFJU4u3KNEEMCbPd9gQJaEiVuVlaGUMBE8B4oEDHZYGPasmy4nWGgyoPqQH6V/3d2O nNXsbMH3ul9W5xQ7VtS4J2Cu2GHJ9rse3fNGMig3Aw83L54iTJxfnPA/tebTpyk2coJd rABqI/0vnGo+LN4/bc+z4tJlrxuT4e1cY927F0zmpL8RiWztE29N2Hy18viSyJqjAuPJ I7rejbrGhDhjBlq6hrzc+MFQ5X/lMau7Mw6JgIcyy3W/3jqQ1uERlm8xt643RPSs85oJ O6kw== X-Gm-Message-State: ALoCoQlA4EXWFoY6x+OmIfR42chNE6QwKI65VU+cBsW5x+656q+f9p0zV87f3He4S50Sxp+I3kMk X-Received: by 10.202.90.139 with SMTP id o133mr1403033oib.99.1422381799042; Tue, 27 Jan 2015 10:03:19 -0800 (PST) Received: from ?IPv6:2610:160:11:33:956e:9562:4694:6bbf? ([2610:160:11:33:956e:9562:4694:6bbf]) by mx.google.com with ESMTPSA id r9sm940909obi.29.2015.01.27.10.03.18 (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Tue, 27 Jan 2015 10:03:18 -0800 (PST) Mime-Version: 1.0 (Mac OS X Mail 8.2 \(2070.1\)) Subject: Re: is polling still a thing? From: Jim Thompson In-Reply-To: <871tmgceup.fsf@marcos.anarc.at> Date: Tue, 27 Jan 2015 12:03:19 -0600 Message-Id: References: <871tmgceup.fsf@marcos.anarc.at> To: =?utf-8?Q?Antoine_Beaupr=C3=A9?= X-Mailer: Apple Mail (2.2070.1) Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: freebsd-net@FreeBSD.org X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 18:03:20 -0000 > On Jan 27, 2015, at 11:28 AM, Antoine Beaupr=C3=A9 = wrote: >=20 > (Please CC, as i am not on the list.) >=20 > I was surprised to read this article in the pfSense blog: >=20 > https://blog.pfsense.org/?p=3D115 That article is from June 2007. It=E2=80=99s over seven years old. = Times change. > TLDR: "At this time, polling is not recommended at all.=E2=80=9D There are situations which warrant polling. > Is that true? I am trying to tweak a Supermicro machine as a router to > survive major DDOS attacks on a 1gbps link. So far, I can't get far > beyond the 100kpps and 50mbps mark. >=20 > The hardware is: >=20 > * 2xIntel E1G44HTBLK NICs Quad port i340 PCIe Nic (igb(4) driver) > * 1xIntel 1220LV2 CPU 2 core Ivy Bridge @ 2.3GHz > More detailed specs here: >=20 > https://wiki.koumbit.net/rtr1.koumbit.net = Says you=E2=80=99re running 9.3 The pf in 9.3 is single-threaded. > We are using a stateful pf firewall and polling on the network > interfaces. We got around 100kpps during the DDOS, with 700kpps = dropped > (or at least 700k/s errors) on the NIC. The DDOS was apparently = 5.5gbps > but around 400mbps reached our port from upstream's point of view. The > kernel interfaces counted around 50mbps: >=20 > https://redmine.koumbit.net/attachments/download/7706 > https://redmine.koumbit.net/attachments/download/7707 > https://redmine.koumbit.net/attachments/download/7708 > https://redmine.koumbit.net/attachments/download/7709 = These want a login/password to access. >=20 > The load on the router was fine during the DDOS, but of course packet > loss was endemic. >=20 > At this point, I'm considering the following options: >=20 > * switching to an Intel IGB nic You already have one. > * enabling fastforwarding typically a good idea. > * tweak the number of IGB queues >=20 > Any recommendations would be welcome. Have you considered FreeBSD 10.1? > Thanks! >=20 > A. >=20 > --=20 > feature, n: a documented bug | bug, n: an undocumented feature > - Mario S F Ferreira > _______________________________________________ > freebsd-net@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 18:19:24 2015 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id E30B1811 for ; Tue, 27 Jan 2015 18:19:24 +0000 (UTC) Received: from marcos.anarc.at (mail.orangeseeds.org [72.0.72.144]) by mx1.freebsd.org (Postfix) with ESMTP id 720F8BD for ; Tue, 27 Jan 2015 18:19:24 +0000 (UTC) Received: by marcos.anarc.at (Postfix, from userid 1000) id BADE91A006C; Tue, 27 Jan 2015 13:19:21 -0500 (EST) From: Antoine =?utf-8?Q?Beaupr=C3=A9?= To: Jim Thompson Subject: Re: is polling still a thing? In-Reply-To: References: <871tmgceup.fsf@marcos.anarc.at> User-Agent: Notmuch/0.18.2 (http://notmuchmail.org) Emacs/24.4.1 (x86_64-pc-linux-gnu) Date: Tue, 27 Jan 2015 13:19:21 -0500 Message-ID: <87vbjsaxxy.fsf@marcos.anarc.at> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Cc: freebsd-net@FreeBSD.org X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 18:19:25 -0000 On 2015-01-27 13:03:19, Jim Thompson wrote: >> On Jan 27, 2015, at 11:28 AM, Antoine Beaupr=C3=A9 = wrote: >>=20 >> (Please CC, as i am not on the list.) >>=20 >> I was surprised to read this article in the pfSense blog: >>=20 >> https://blog.pfsense.org/?p=3D115 > > That article is from June 2007. It=E2=80=99s over seven years old. Time= s change. Oh, i got confused by the last comment, which dates from 2013: >> TLDR: "At this time, polling is not recommended at all.=E2=80=9D > > There are situations which warrant polling. > >> Is that true? I am trying to tweak a Supermicro machine as a router to >> survive major DDOS attacks on a 1gbps link. So far, I can't get far >> beyond the 100kpps and 50mbps mark. >>=20 >> The hardware is: >>=20 >> * 2xIntel E1G44HTBLK NICs > > Quad port i340 PCIe Nic (igb(4) driver) > >> * 1xIntel 1220LV2 CPU > > 2 core Ivy Bridge @ 2.3GHz > >> More detailed specs here: >>=20 >> https://wiki.koumbit.net/rtr1.koumbit.net > > Says you=E2=80=99re running 9.3 That is correct, we just upgraded. > The pf in 9.3 is single-threaded. Is that changed in later versions? >> We are using a stateful pf firewall and polling on the network >> interfaces. We got around 100kpps during the DDOS, with 700kpps dropped >> (or at least 700k/s errors) on the NIC. The DDOS was apparently 5.5gbps >> but around 400mbps reached our port from upstream's point of view. The >> kernel interfaces counted around 50mbps: >>=20 >> https://redmine.koumbit.net/attachments/download/7706 >> https://redmine.koumbit.net/attachments/download/7707 >> https://redmine.koumbit.net/attachments/download/7708 >> https://redmine.koumbit.net/attachments/download/7709 > > These want a login/password to access. Ah, crap. Here: http://shell.koumbit.net/~anarcat/ddos-snaps-2015-01-27/ >> The load on the router was fine during the DDOS, but of course packet >> loss was endemic. >>=20 >> At this point, I'm considering the following options: >>=20 >> * switching to an Intel IGB nic > You already have one. Yeah, but the public interface is using some em driver, for some reason. I think it may be the builtin NIC on the X9SPU-F motherboard. >> * enabling fastforwarding > typically a good idea. Understood. >> * tweak the number of IGB queues >>=20 >> Any recommendations would be welcome. > > Have you considered FreeBSD 10.1? Not yet. What should i expect from the upgrade? We just barely made it to 9.3 at this point... A. --=20 Conformity-the natural instinct to passively yield to that vague something recognized as authority. - Mark Twain From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 18:46:34 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 34EE4D5A for ; Tue, 27 Jan 2015 18:46:34 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 17A5B3F8 for ; Tue, 27 Jan 2015 18:46:34 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0RIkXth070574 for ; Tue, 27 Jan 2015 18:46:33 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0RIkXVu070573; Tue, 27 Jan 2015 18:46:33 GMT (envelope-from mat) Date: Tue, 27 Jan 2015 18:46:33 +0000 To: freebsd-net@freebsd.org From: "rstone (Ryan Stone)" Subject: [Differential] [Updated, 281 lines] D1640: Refactor network stack state separate from VSI state Message-ID: <9391b5d30cf5272e786a979937b01b56@localhost.localdomain> X-Priority: 3 Thread-Topic: D1640: Refactor network stack state separate from VSI state X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: N2JmNDRjOWRkY2RlYmQ2NjRjZDUxYzYxNjBmIFTH3Qk= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 18:46:34 -0000 rstone updated this revision to Diff 3458. rstone added a comment. Remove the ifx/vsi separation and just refactor out the necessary functions CHANGES SINCE LAST UPDATE https://reviews.freebsd.org/D1640?vs=3393&id=3458 BRANCH review_D1640 REVISION DETAIL https://reviews.freebsd.org/D1640 AFFECTED FILES sys/dev/ixl/if_ixl.c sys/dev/ixl/if_ixlv.c sys/dev/ixl/ixl.h sys/dev/ixl/ixl_pf.h sys/dev/ixl/ixl_txrx.c sys/dev/ixl/ixlvc.c To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 19:23:05 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id BE53E6D6 for ; Tue, 27 Jan 2015 19:23:05 +0000 (UTC) Received: from frv191.fwdcdn.com (frv191.fwdcdn.com [212.42.77.191]) (using TLSv1.2 with cipher DHE-RSA-AES128-SHA (128/128 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 7927D9F7 for ; Tue, 27 Jan 2015 19:23:04 +0000 (UTC) Received: from [10.10.1.26] (helo=frv197.fwdcdn.com) by frv191.fwdcdn.com with esmtp ID 1YGBKJ-0009Ki-I9 for freebsd-net@freebsd.org; Tue, 27 Jan 2015 20:57:27 +0200 DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=ukr.net; s=ffe; h=Content-Transfer-Encoding:Content-Type:MIME-Version:References:In-Reply-To:Message-Id:Cc:To:Subject:From:Date; bh=66g/xxyGXhdI9Iv6tCph95da/vhIV8Z6fJBNBsk6e5U=; b=MzsATvCxkSV8SxleFl57Y3wJNrVZQpwRzuSmlXQ/j+1GrmL7NcZ51FH1kaHqnUYBwL4LuJ58qzHGYJ/E9cwWB8ibPa0VNgptJ9YdU7WFHKjmUe0ItKNI8/zK7U5+o5GJ3uHCIV7XWNMFIT5fBSp+vGsN9pLf7xFajz/2sJBj86A=; Received: from [10.10.10.34] (helo=frv34.fwdcdn.com) by frv197.fwdcdn.com with smtp ID 1YGBKC-0001yB-Kr for freebsd-net@freebsd.org; Tue, 27 Jan 2015 20:57:20 +0200 Date: Tue, 27 Jan 2015 20:57:20 +0200 From: wishmaster Subject: Re: is polling still a thing? To: anarcat@koumbit.org X-Mailer: mail.ukr.net 5.0 Message-Id: <1422384769.867067950.y2iiuu53@frv34.fwdcdn.com> In-Reply-To: <871tmgceup.fsf@marcos.anarc.at> References: <871tmgceup.fsf@marcos.anarc.at> MIME-Version: 1.0 Received: from artemrts@ukr.net by frv34.fwdcdn.com; Tue, 27 Jan 2015 20:57:20 +0200 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: binary Content-Disposition: inline X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: freebsd-net@freebsd.org X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 19:23:05 -0000 Have you consider to use netmap-based ipfw instead pf in DDoS mitigation? I think you should. And without any network ''haks'' like polling. Cheers, Vitaly --- Original Message --- From: "Antoine Beaupré" Date: 27 January 2015, 19:28:55 > (Please CC, as i am not on the list.) > > I was surprised to read this article in the pfSense blog: > > https://blog.pfsense.org/?p=115 > > TLDR: "At this time, polling is not recommended at all." > > Is that true? I am trying to tweak a Supermicro machine as a router to > survive major DDOS attacks on a 1gbps link. So far, I can't get far > beyond the 100kpps and 50mbps mark. > > The hardware is: > > * 2xIntel E1G44HTBLK NICs > * 1xIntel 1220LV2 CPU > > More detailed specs here: > > https://wiki.koumbit.net/rtr1.koumbit.net > > We are using a stateful pf firewall and polling on the network > interfaces. We got around 100kpps during the DDOS, with 700kpps dropped > (or at least 700k/s errors) on the NIC. The DDOS was apparently 5.5gbps > but around 400mbps reached our port from upstream's point of view. The > kernel interfaces counted around 50mbps: > > https://redmine.koumbit.net/attachments/download/7706 > https://redmine.koumbit.net/attachments/download/7707 > https://redmine.koumbit.net/attachments/download/7708 > https://redmine.koumbit.net/attachments/download/7709 > > The load on the router was fine during the DDOS, but of course packet > loss was endemic. > > At this point, I'm considering the following options: > > * switching to an Intel IGB nic > * enabling fastforwarding > * tweak the number of IGB queues > > Any recommendations would be welcome. > > Thanks! > > A. > > -- > feature, n: a documented bug | bug, n: an undocumented feature > - Mario S F Ferreira > _______________________________________________ > freebsd-net@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" > From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 19:36:26 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 3DFFE249; Tue, 27 Jan 2015 19:36:26 +0000 (UTC) Received: from mail.strugglingcoder.info (strugglingcoder.info [65.19.130.35]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 0F87CB1E; Tue, 27 Jan 2015 19:36:25 +0000 (UTC) Received: from localhost (unknown [10.1.1.3]) (Authenticated sender: hiren@strugglingcoder.info) by mail.strugglingcoder.info (Postfix) with ESMTPSA id E99BECB062; Tue, 27 Jan 2015 11:28:14 -0800 (PST) Date: Tue, 27 Jan 2015 11:28:14 -0800 From: hiren panchasara To: Sreekanth Rupavatharam Subject: Re: Double cleanup in igb_attach Message-ID: <20150127192814.GA63990@strugglingcoder.info> References: MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha512; protocol="application/pgp-signature"; boundary="XsQoSWH+UP9D9v3l" Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.23 (2014-03-12) Cc: jfv@freebsd.org, "freebsd-net@freebsd.org" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 19:36:26 -0000 --XsQoSWH+UP9D9v3l Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable + Jack On Tue, Jan 27, 2015 at 12:00:19AM +0000, Sreekanth Rupavatharam wrote: > Apologies if this is not the right forum. In igb_attach function, we have= this code. > err_late: > igb_detach(dev); > igb_free_transmit_structures(adapter); > igb_free_receive_structures(adapter); > igb_release_hw_control(adapter); > err_pci: > igb_free_pci_resources(adapter); > if (adapter->ifp !=3D NULL) > if_free(adapter->ifp); > free(adapter->mta, M_DEVBUF); > IGB_CORE_LOCK_DESTROY(adapter); >=20 > The problem is that igb_detach also does the same cleanup in it?s body. O= nly exception is this case where it just returns EBUSY > /* Make sure VLANS are not using driver */ > if (if_vlantrunkinuse(ifp)) { > device_printf(dev,"Vlan in use, detach first\n"); > return (EBUSY); > } >=20 > I think the code in igb_attach should be changed to free up resources onl= y if the igb_detach returns an error. Here?s the patch for it. >=20 >=20 > Index: if_igb.c >=20 > =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D >=20 > --- if_igb.c (revision 298025) >=20 > +++ if_igb.c (working copy) >=20 > @@ -723,7 +723,8 @@ igb_attach(device_t dev) >=20 > return (0); >=20 >=20 >=20 > err_late: >=20 > - igb_detach(dev); >=20 > + if(igb_detach(dev) =3D=3D 0) /* igb_detach did the cleanup */ >=20 > + return; >=20 > igb_free_transmit_structures(adapter); >=20 > Can anyone comment on it and tell me if my understanding is incorrect? > Seems reasonable to me at the first glance. We need to call IGB_CORE_LOCK_DESTROY(adapter) before returning though. cheers, Hiren --XsQoSWH+UP9D9v3l Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (FreeBSD) iQF8BAEBCgBmBQJUx+bOXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRBNEUyMEZBMUQ4Nzg4RjNGMTdFNjZGMDI4 QjkyNTBFMTU2M0VERkU1AAoJEIuSUOFWPt/lObUH/0Hx97ALe1Q7eUgQKTMH2fYU gqfI89/WZ4TII5/xZPGCpMFooBUNYCRDe4hvCLaf6kfPawWSQLs2j4cWjM854T8h bux/k9KlAkwzCv2ZpiwYQQ1Fm/VLA411La21BmyKPv0rwoF3RosYI6C5XHNC/AT2 6IlePuvKBvaZJT0KYkZ2VDGQUFIr/A3kHKF/DUiTNMGrsVtqcEkMvZp+KBt6IKZs v5coe/wsgfCnFUtxuxf5HXMY2ReJYsgvsbVrwyLKVgomTDHvw1LKVGq7fuzJMsUi 2XbTrOgv+5Ho3BwtDAVIBkU4Jgr8trYl7YejNAZEVJa1Xl0xr4AuirU90pRwZUE= =IUyh -----END PGP SIGNATURE----- --XsQoSWH+UP9D9v3l-- From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 19:36:28 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 636AB24E; Tue, 27 Jan 2015 19:36:28 +0000 (UTC) Received: from na01-bn1-obe.outbound.protection.outlook.com (mail-bn1bon0142.outbound.protection.outlook.com [157.56.111.142]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-SHA384 (256/256 bits)) (Client CN "mail.protection.outlook.com", Issuer "MSIT Machine Auth CA 2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id C2643B22; Tue, 27 Jan 2015 19:36:27 +0000 (UTC) Received: from CO2PR05MB764.namprd05.prod.outlook.com (10.141.227.19) by CO2PR05MB780.namprd05.prod.outlook.com (10.141.226.156) with Microsoft SMTP Server (TLS) id 15.1.65.19; Tue, 27 Jan 2015 19:36:20 +0000 Received: from CO2PR05MB761.namprd05.prod.outlook.com (10.141.227.13) by CO2PR05MB764.namprd05.prod.outlook.com (10.141.227.19) with Microsoft SMTP Server (TLS) id 15.1.65.19; Tue, 27 Jan 2015 19:36:17 +0000 Received: from CO2PR05MB761.namprd05.prod.outlook.com ([10.141.227.13]) by CO2PR05MB761.namprd05.prod.outlook.com ([10.141.227.13]) with mapi id 15.01.0065.013; Tue, 27 Jan 2015 19:36:17 +0000 From: Sreekanth Rupavatharam To: hiren panchasara Subject: Re: Double cleanup in igb_attach Thread-Topic: Double cleanup in igb_attach Thread-Index: AQHQOcQ8M6DG1/D37kKlfeofCj44QJzUW0EA//98HwA= Date: Tue, 27 Jan 2015 19:36:17 +0000 Message-ID: References: <20150127192814.GA63990@strugglingcoder.info> In-Reply-To: <20150127192814.GA63990@strugglingcoder.info> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: user-agent: Microsoft-MacOutlook/14.4.7.141117 x-originating-ip: [66.129.239.13] authentication-results: strugglingcoder.info; dkim=none (message not signed) header.d=none;strugglingcoder.info; dmarc=none action=none header.from=juniper.net; x-dmarcaction-test: None x-microsoft-antispam: BCL:0; PCL:0; RULEID:(3005004); SRVR:CO2PR05MB764; UriScan:; x-exchange-antispam-report-test: UriScan:; x-exchange-antispam-report-cfa-test: BCL:0;PCL:0;RULEID:;SRVR:CO2PR05MB764; x-forefront-prvs: 046985391D x-forefront-antispam-report: SFV:NSPM; SFS:(10019020)(6009001)(51704005)(36756003)(122556002)(110136001)(46102003)(99286002)(54356999)(86362001)(66066001)(76176999)(50986999)(558084003)(77096005)(87936001)(40100003)(77156002)(83506001)(2900100001)(62966003)(2656002)(102836002)(2950100001)(106116001)(92566002); DIR:OUT; SFP:1102; SCL:1; SRVR:CO2PR05MB764; H:CO2PR05MB761.namprd05.prod.outlook.com; FPR:; SPF:None; MLV:sfv; LANG:en; Content-Type: text/plain; charset="us-ascii" Content-ID: Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 X-MS-Exchange-CrossTenant-originalarrivaltime: 27 Jan 2015 19:36:17.3426 (UTC) X-MS-Exchange-CrossTenant-fromentityheader: Hosted X-MS-Exchange-CrossTenant-id: bea78b3c-4cdb-4130-854a-1d193232e5f4 X-MS-Exchange-Transport-CrossTenantHeadersStamped: CO2PR05MB764 X-Microsoft-Antispam: BCL:0;PCL:0;RULEID:;SRVR:CO2PR05MB780; X-OriginatorOrg: juniper.net Cc: "jfv@freebsd.org" , "freebsd-net@freebsd.org" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 19:36:28 -0000 > >Seems reasonable to me at the first glance. > >We need to call IGB_CORE_LOCK_DESTROY(adapter) before returning though. > Not necessary. igb_detach does that. From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 19:50:27 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 8FE0DA53; Tue, 27 Jan 2015 19:50:27 +0000 (UTC) Received: from mail.strugglingcoder.info (strugglingcoder.info [65.19.130.35]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 788D0C74; Tue, 27 Jan 2015 19:50:27 +0000 (UTC) Received: from localhost (unknown [10.1.1.3]) (Authenticated sender: hiren@strugglingcoder.info) by mail.strugglingcoder.info (Postfix) with ESMTPSA id 254B6CB360; Tue, 27 Jan 2015 11:50:27 -0800 (PST) Date: Tue, 27 Jan 2015 11:50:27 -0800 From: hiren panchasara To: Sreekanth Rupavatharam Subject: Re: Double cleanup in igb_attach Message-ID: <20150127195027.GB63990@strugglingcoder.info> References: <20150127192814.GA63990@strugglingcoder.info> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha512; protocol="application/pgp-signature"; boundary="NMuMz9nt05w80d4+" Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.23 (2014-03-12) Cc: "jfv@freebsd.org" , "freebsd-net@freebsd.org" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 19:50:27 -0000 --NMuMz9nt05w80d4+ Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Tue, Jan 27, 2015 at 07:36:17PM +0000, Sreekanth Rupavatharam wrote: > > > >Seems reasonable to me at the first glance. > > > >We need to call IGB_CORE_LOCK_DESTROY(adapter) before returning though. > > > Not necessary. igb_detach does that. Bah, I read that call inside detach as UNLOCK. Yeah, you are right.=20 cheers, Hiren --NMuMz9nt05w80d4+ Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (FreeBSD) iQF8BAEBCgBmBQJUx+wCXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRBNEUyMEZBMUQ4Nzg4RjNGMTdFNjZGMDI4 QjkyNTBFMTU2M0VERkU1AAoJEIuSUOFWPt/lrFQIAKY7yW//68Wa3mw7vp4nH4p9 BqtJEe57mOnCC5jwC1U4V+y8Mpivc/ZG1VwJ7uvmVVK5IjLwp8xWqgh4ub8/vXpb qTQe99g3j/1kNjNuklGtuaB2sWTZ0qYTnQA8I645Ns2CrTMEuJ6B1r5JnKNYAlEE 8J/f8gfraCjtKFT/1CXedxiXodvNHcvv4s/4D6xJiPuYMFFz0wIN63McVGJK0027 bA35fkIm9TuCgpFZaIpPAe48R7VVni3mnWGnw5SGBwp6G3JQQLb8ZxnB4VjjLk3Q jvjJLdVc3+e1CWSCV4XauqQsbmTCbRbym9INB4KhvbFIVYoL+GyFAJtBriYObtw= =065L -----END PGP SIGNATURE----- --NMuMz9nt05w80d4+-- From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 20:00:41 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 35769933 for ; Tue, 27 Jan 2015 20:00:41 +0000 (UTC) Received: from mail-wi0-x234.google.com (mail-wi0-x234.google.com [IPv6:2a00:1450:400c:c05::234]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id B909DF6C for ; Tue, 27 Jan 2015 20:00:40 +0000 (UTC) Received: by mail-wi0-f180.google.com with SMTP id h11so7426048wiw.1 for ; Tue, 27 Jan 2015 12:00:39 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:from:date:message-id :subject:to:cc:content-type; bh=mX6iNwdLsyHUCKV1kFT8DNR1QXK5URAy1bb70bUVIvA=; b=yfNeYuCVdcBLfsOo9idpbi+mNHYaarrt7Q5FBHOHxocnDKJO13O/M//6kgMpR47K+9 tDtTOVAF6HVkZ9qW6I0Eht+1vIu6jYF98XawxLCbXR9gt8RfeJjmxpEleex72nOfzj+w +1UTXBMZ1PsqwKpzelIjWjgAgqsg4EzswaFoM0OUxZlZz7RpKDNcafzDITajk0+3MNMo aGB2nS1wtbyhgdVW3hC6s5BZIVAeLpy1Qtw2KU7l8Q2OzcOi/bdGm8/NxgvYPpkQOkY3 kHYpR0eLEJpCpb76BysP4FR3BiRB26X4tYnKe0Gc/N6K9fiOp9qOzupaug5I9upG++e0 M9eg== X-Received: by 10.180.78.99 with SMTP id a3mr9296877wix.2.1422388839214; Tue, 27 Jan 2015 12:00:39 -0800 (PST) MIME-Version: 1.0 Sender: cochard@gmail.com Received: by 10.194.61.1 with HTTP; Tue, 27 Jan 2015 12:00:18 -0800 (PST) In-Reply-To: <87vbjsaxxy.fsf@marcos.anarc.at> References: <871tmgceup.fsf@marcos.anarc.at> <87vbjsaxxy.fsf@marcos.anarc.at> From: =?ISO-8859-1?Q?Olivier_Cochard=2DLabb=E9?= Date: Tue, 27 Jan 2015 21:00:18 +0100 X-Google-Sender-Auth: QS-QAomedgUriFyOrqm5vgzr2xc Message-ID: Subject: Re: is polling still a thing? To: =?ISO-8859-1?Q?Antoine_Beaupr=E9?= Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: "freebsd-net@freebsd.org" , Jim Thompson X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 20:00:41 -0000 On Tue, Jan 27, 2015 at 7:19 PM, Antoine Beaupr=E9 wrote: > On 2015-01-27 13:03:19, Jim Thompson wrote: > > > > > Have you considered FreeBSD 10.1? > > Not yet. What should i expect from the upgrade? We just barely made it > to 9.3 at this point... > Here is an old bench comparing pf improvement since fbsd 10.0: http://dev.bsdrp.net/benchs/BSD.network.performance.TenGig.png But I don't know what kind of specific patches regarding pf are used on pfSense: I didn't find them on the pfsense github account. From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 20:06:16 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 9C1E2BA3; Tue, 27 Jan 2015 20:06:16 +0000 (UTC) Received: from na01-bn1-obe.outbound.protection.outlook.com (mail-bn1on0147.outbound.protection.outlook.com [157.56.110.147]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-SHA384 (256/256 bits)) (Client CN "mail.protection.outlook.com", Issuer "MSIT Machine Auth CA 2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 093CEED; Tue, 27 Jan 2015 20:06:15 +0000 (UTC) Received: from CO2PR05MB762.namprd05.prod.outlook.com (10.141.227.14) by CO2PR05MB634.namprd05.prod.outlook.com (10.141.199.17) with Microsoft SMTP Server (TLS) id 15.1.65.19; Tue, 27 Jan 2015 19:51:51 +0000 Received: from CO2PR05MB761.namprd05.prod.outlook.com (10.141.227.13) by CO2PR05MB762.namprd05.prod.outlook.com (10.141.227.14) with Microsoft SMTP Server (TLS) id 15.1.65.19; Tue, 27 Jan 2015 19:51:49 +0000 Received: from CO2PR05MB761.namprd05.prod.outlook.com ([10.141.227.13]) by CO2PR05MB761.namprd05.prod.outlook.com ([10.141.227.13]) with mapi id 15.01.0065.013; Tue, 27 Jan 2015 19:51:49 +0000 From: Sreekanth Rupavatharam To: hiren panchasara Subject: Re: Double cleanup in igb_attach Thread-Topic: Double cleanup in igb_attach Thread-Index: AQHQOcQ8M6DG1/D37kKlfeofCj44QJzUW0EA//+AdgA= Date: Tue, 27 Jan 2015 19:51:49 +0000 Message-ID: References: <20150127192814.GA63990@strugglingcoder.info> In-Reply-To: <20150127192814.GA63990@strugglingcoder.info> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: user-agent: Microsoft-MacOutlook/14.4.7.141117 x-originating-ip: [66.129.239.13] authentication-results: strugglingcoder.info; dkim=none (message not signed) header.d=none;strugglingcoder.info; dmarc=none action=none header.from=juniper.net; x-dmarcaction-test: None x-microsoft-antispam: BCL:0; PCL:0; RULEID:(3005004); SRVR:CO2PR05MB762; UriScan:; x-exchange-antispam-report-test: UriScan:; x-exchange-antispam-report-cfa-test: BCL:0;PCL:0;RULEID:;SRVR:CO2PR05MB762; x-forefront-prvs: 046985391D x-forefront-antispam-report: SFV:NSPM; SFS:(10019020)(164054003)(377454003)(479174004)(24454002)(46102003)(110136001)(92566002)(2656002)(19580395003)(54356999)(76176999)(62966003)(77156002)(102836002)(19580405001)(83506001)(66066001)(50986999)(77096005)(2950100001)(2900100001)(40100003)(122556002)(16236675004)(106116001)(86362001)(99286002)(36756003)(87936001)(6606295002); DIR:OUT; SFP:1102; SCL:1; SRVR:CO2PR05MB762; H:CO2PR05MB761.namprd05.prod.outlook.com; FPR:; SPF:None; MLV:sfv; LANG:en; MIME-Version: 1.0 X-MS-Exchange-CrossTenant-originalarrivaltime: 27 Jan 2015 19:51:49.5982 (UTC) X-MS-Exchange-CrossTenant-fromentityheader: Hosted X-MS-Exchange-CrossTenant-id: bea78b3c-4cdb-4130-854a-1d193232e5f4 X-MS-Exchange-Transport-CrossTenantHeadersStamped: CO2PR05MB762 X-Microsoft-Antispam: BCL:0;PCL:0;RULEID:;SRVR:CO2PR05MB634; X-OriginatorOrg: juniper.net Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: "jfv@freebsd.org" , "freebsd-net@freebsd.org" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 20:06:16 -0000 Hiren, Can you help commit this? Index: if_igb.c =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D --- if_igb.c (revision 298053) +++ if_igb.c (working copy) @@ -723,7 +723,8 @@ igb_attach(device_t dev) return (0); err_late: - igb_detach(dev); + if(igb_detach(dev) =3D=3D 0) /* igb_detach did the cleanup */ + return(error); igb_free_transmit_structures(adapter); igb_free_receive_structures(adapter); igb_release_hw_control(adapter); -- Thanks, Sreekanth On 1/27/15, 11:28 AM, "hiren panchasara" > wrote: + Jack On Tue, Jan 27, 2015 at 12:00:19AM +0000, Sreekanth Rupavatharam wrote: Apologies if this is not the right forum. In igb_attach function, we have t= his code. err_late: igb_detach(dev); igb_free_transmit_structures(adapter); igb_free_receive_structures(adapter); igb_release_hw_control(adapter); err_pci: igb_free_pci_resources(adapter); if (adapter->ifp !=3D NULL) if_free(adapter->ifp); free(adapter->mta, M_DEVBUF); IGB_CORE_LOCK_DESTROY(adapter); The problem is that igb_detach also does the same cleanup in it?s body. Onl= y exception is this case where it just returns EBUSY /* Make sure VLANS are not using driver */ if (if_vlantrunkinuse(ifp)) { device_printf(dev,"Vlan in use, detach first\n"); return (EBUSY); } I think the code in igb_attach should be changed to free up resources only = if the igb_detach returns an error. Here?s the patch for it. Index: if_igb.c =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D --- if_igb.c (revision 298025) +++ if_igb.c (working copy) @@ -723,7 +723,8 @@ igb_attach(device_t dev) return (0); err_late: - igb_detach(dev); + if(igb_detach(dev) =3D=3D 0) /* igb_detach did the cleanup */ + return; igb_free_transmit_structures(adapter); Can anyone comment on it and tell me if my understanding is incorrect? Seems reasonable to me at the first glance. We need to call IGB_CORE_LOCK_DESTROY(adapter) before returning though. cheers, Hiren From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 20:15:30 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id AC403FE1 for ; Tue, 27 Jan 2015 20:15:30 +0000 (UTC) Received: from mail-ob0-f176.google.com (mail-ob0-f176.google.com [209.85.214.176]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 72BD524F for ; Tue, 27 Jan 2015 20:15:30 +0000 (UTC) Received: by mail-ob0-f176.google.com with SMTP id va2so15588503obc.7 for ; Tue, 27 Jan 2015 12:15:23 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:mime-version:in-reply-to:references:date :message-id:subject:from:to:cc:content-type; bh=JNXkdJOgLHqzLrM1W4RW1nr7eZghgRxjXyFZWOsvNRw=; b=L3QGwsLeweHVQ5t1q2wkZ9SqibMj0rKGWjpM+geWDpjs75fJwwGRCimHyKFz3Ph6n+ JhLwLOHQWMAF4vgL2VWxKWOeB8VuU2Uq0BMlXddJE/e68SEI2ryAyE6E60f9PmvMLqKA igzv7cTdLR2ig3/lrrrZbAsbaGX0LgpmpLeCFyoAb7z5sih8v8ypzf7yevTLnPpMZXW7 z3jbCBBTTDG0tvaBgKzfb3kjzgyTG19kCGLv6Pbm1fuIuSLBPu6kBeIiSqF8qYWzw8px Yepo8Z+a3905BgJuBXO4vE0RQ2rCB1O2MP4DRC3MvJvJVa0tgG2wVjUGzeVeSts7NhhA NcIQ== X-Gm-Message-State: ALoCoQkLZWKXo5X1pgRXbmbp9SV8la9onZCV66zG8/BLLonEeFwH52sHKENyOf6melHChZejtggl MIME-Version: 1.0 X-Received: by 10.60.124.194 with SMTP id mk2mr1858374oeb.79.1422389723654; Tue, 27 Jan 2015 12:15:23 -0800 (PST) Received: by 10.60.92.195 with HTTP; Tue, 27 Jan 2015 12:15:23 -0800 (PST) In-Reply-To: References: <871tmgceup.fsf@marcos.anarc.at> <87vbjsaxxy.fsf@marcos.anarc.at> Date: Tue, 27 Jan 2015 12:15:23 -0800 Message-ID: Subject: Re: is polling still a thing? From: Michael Sierchio To: =?UTF-8?Q?Olivier_Cochard=2DLabb=C3=A9?= Content-Type: text/plain; charset=UTF-8 X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: "freebsd-net@freebsd.org" , Jim Thompson , =?UTF-8?Q?Antoine_Beaupr=C3=A9?= X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 20:15:30 -0000 On small, embedded computers running ipfw w/kernel nat and device polling enabled (on em ether adapters), I observed the *reported* system load grow very high. When disabling polling on the interfaces, it went back to something normal. My impression is that the consensus among the core developers concerned with networking is that device polling is an ancient hack and is deprecated. In the case of a DDoS attack, there may be many other things to try - at the infrastructure level - traffic diversion techniques like BGP flowspec, use anycast, etc. On the individual server level, use stateful rules with GRED enabled, dropping most new tcp or udp traffic based on load. That's a topic of its own... - M From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 20:15:49 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id EC473E7; Tue, 27 Jan 2015 20:15:49 +0000 (UTC) Received: from mail-wi0-x235.google.com (mail-wi0-x235.google.com [IPv6:2a00:1450:400c:c05::235]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 725DA25B; Tue, 27 Jan 2015 20:15:49 +0000 (UTC) Received: by mail-wi0-f181.google.com with SMTP id fb4so7530703wid.2; Tue, 27 Jan 2015 12:15:47 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=EkHU9iaE90NvKIpvOVO/esllh24KrWgZGiVnXzxwseY=; b=oKlq8aL0A4m3yxt9BzQsTK14Cy6RK5etyXmageBLhU8PSsd5yE596G18NxtN9413t+ lEE4+5VDlP2XAIXkmjYnpXjc+lVg70jXFEGn2vJL+0ghlJQ7qEKzxvc5YibDpNsp/Rp2 z/lqvKK1mn2BN5C0VWb8t35/ZFoRXI2Qjr0CNaEP8nBbnewYIYwcRY22dxs1RDb3k/Ha 1HochiPI7w74XcY4qRmkIJeWGij+3eE/ad423Ua+ZtMvlf1yKyh6g/8lFh+44OFCiG2W RPWCUkiTbELynCSueejGRPodneUKZG1hIphyME7ouATc+s2aUySpAi/CA7wPp1/3win4 NyKA== MIME-Version: 1.0 X-Received: by 10.180.218.39 with SMTP id pd7mr357007wic.21.1422389747395; Tue, 27 Jan 2015 12:15:47 -0800 (PST) Received: by 10.194.101.106 with HTTP; Tue, 27 Jan 2015 12:15:47 -0800 (PST) In-Reply-To: References: <20150127192814.GA63990@strugglingcoder.info> Date: Tue, 27 Jan 2015 12:15:47 -0800 Message-ID: Subject: Re: Double cleanup in igb_attach From: Jack Vogel To: Sreekanth Rupavatharam Content-Type: text/plain; charset=ISO-8859-1 X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: "jfv@freebsd.org" , "freebsd-net@freebsd.org" , hiren panchasara X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 20:15:50 -0000 If you want something committed to an Intel driver, asking Intel might be the courteous thing to do, don't you think? Jack On Tue, Jan 27, 2015 at 11:51 AM, Sreekanth Rupavatharam < rupavath@juniper.net> wrote: > Hiren, > Can you help commit this? > > Index: if_igb.c > > =================================================================== > > --- if_igb.c (revision 298053) > > +++ if_igb.c (working copy) > > @@ -723,7 +723,8 @@ igb_attach(device_t dev) > > return (0); > > > > err_late: > > - igb_detach(dev); > > + if(igb_detach(dev) == 0) /* igb_detach did the cleanup */ > > + return(error); > > igb_free_transmit_structures(adapter); > > igb_free_receive_structures(adapter); > > igb_release_hw_control(adapter); > > -- Thanks, > > Sreekanth > > > > > > > On 1/27/15, 11:28 AM, "hiren panchasara" > wrote: > > + Jack > On Tue, Jan 27, 2015 at 12:00:19AM +0000, Sreekanth Rupavatharam wrote: > > Apologies if this is not the right forum. In igb_attach function, we have > this code. > err_late: > igb_detach(dev); > igb_free_transmit_structures(adapter); > igb_free_receive_structures(adapter); > igb_release_hw_control(adapter); > err_pci: > igb_free_pci_resources(adapter); > if (adapter->ifp != NULL) > if_free(adapter->ifp); > free(adapter->mta, M_DEVBUF); > IGB_CORE_LOCK_DESTROY(adapter); > The problem is that igb_detach also does the same cleanup in it?s body. > Only exception is this case where it just returns EBUSY > /* Make sure VLANS are not using driver */ > if (if_vlantrunkinuse(ifp)) { > device_printf(dev,"Vlan in use, detach first\n"); > return (EBUSY); > } > I think the code in igb_attach should be changed to free up resources > only if the igb_detach returns an error. Here?s the patch for it. > Index: if_igb.c > =================================================================== > --- if_igb.c (revision 298025) > +++ if_igb.c (working copy) > @@ -723,7 +723,8 @@ igb_attach(device_t dev) > return (0); > err_late: > - igb_detach(dev); > + if(igb_detach(dev) == 0) /* igb_detach did the cleanup */ > + return; > igb_free_transmit_structures(adapter); > Can anyone comment on it and tell me if my understanding is incorrect? > > > Seems reasonable to me at the first glance. > > We need to call IGB_CORE_LOCK_DESTROY(adapter) before returning though. > > cheers, > Hiren > > From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 20:21:17 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 33E61227; Tue, 27 Jan 2015 20:21:17 +0000 (UTC) Received: from na01-bl2-obe.outbound.protection.outlook.com (mail-bl2on0121.outbound.protection.outlook.com [65.55.169.121]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-SHA384 (256/256 bits)) (Client CN "mail.protection.outlook.com", Issuer "MSIT Machine Auth CA 2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 99D3E37E; Tue, 27 Jan 2015 20:21:16 +0000 (UTC) Received: from CO2PR05MB761.namprd05.prod.outlook.com (10.141.227.13) by CO2PR05MB761.namprd05.prod.outlook.com (10.141.227.13) with Microsoft SMTP Server (TLS) id 15.1.65.19; Tue, 27 Jan 2015 20:21:09 +0000 Received: from CO2PR05MB761.namprd05.prod.outlook.com ([10.141.227.13]) by CO2PR05MB761.namprd05.prod.outlook.com ([10.141.227.13]) with mapi id 15.01.0065.013; Tue, 27 Jan 2015 20:21:09 +0000 From: Sreekanth Rupavatharam To: Jack Vogel Subject: Re: Double cleanup in igb_attach Thread-Topic: Double cleanup in igb_attach Thread-Index: AQHQOcQ8M6DG1/D37kKlfeofCj44QJzUW0EA//+AdgCAAIzTgIAAAX8Y Date: Tue, 27 Jan 2015 20:21:08 +0000 Message-ID: <26266AD2-4743-4A7B-A87D-F68E2E2425A0@juniper.net> References: <20150127192814.GA63990@strugglingcoder.info> , In-Reply-To: Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [66.129.246.4] authentication-results: gmail.com; dkim=none (message not signed) header.d=none;gmail.com; dmarc=none action=none header.from=juniper.net; x-dmarcaction-test: None x-microsoft-antispam: BCL:0;PCL:0;RULEID:(3005004);SRVR:CO2PR05MB761; x-exchange-antispam-report-test: UriScan:; x-exchange-antispam-report-cfa-test: BCL:0;PCL:0;RULEID:;SRVR:CO2PR05MB761; x-forefront-prvs: 046985391D x-forefront-antispam-report: SFV:NSPM; SFS:(10019020)(479174004)(377454003)(24454002)(164054003)(76176999)(2950100001)(36756003)(54356999)(50986999)(122556002)(1411001)(92566002)(40100003)(66066001)(2900100001)(33656002)(2656002)(83716003)(46102003)(110136001)(16236675004)(106116001)(62966003)(77156002)(86362001)(77096005)(99286002)(82746002)(87936001)(19580405001)(102836002)(19580395003)(93886004)(104396002)(567454003)(6606295002); DIR:OUT; SFP:1102; SCL:1; SRVR:CO2PR05MB761; H:CO2PR05MB761.namprd05.prod.outlook.com; FPR:; SPF:None; MLV:sfv; LANG:en; MIME-Version: 1.0 X-OriginatorOrg: juniper.net X-MS-Exchange-CrossTenant-originalarrivaltime: 27 Jan 2015 20:21:08.8498 (UTC) X-MS-Exchange-CrossTenant-fromentityheader: Hosted X-MS-Exchange-CrossTenant-id: bea78b3c-4cdb-4130-854a-1d193232e5f4 X-MS-Exchange-Transport-CrossTenantHeadersStamped: CO2PR05MB761 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: "jfv@freebsd.org" , "freebsd-net@freebsd.org" , hiren panchasara X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 20:21:17 -0000 Definitely, but I didn't have the contact info of those people. Thanks, -Sreekanth On Jan 27, 2015, at 12:15 PM, "Jack Vogel" > wrote: If you want something committed to an Intel driver, asking Intel might be t= he courteous thing to do, don't you think? Jack On Tue, Jan 27, 2015 at 11:51 AM, Sreekanth Rupavatharam > wrote: Hiren, Can you help commit this? Index: if_igb.c =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D --- if_igb.c (revision 298053) +++ if_igb.c (working copy) @@ -723,7 +723,8 @@ igb_attach(device_t dev) return (0); err_late: - igb_detach(dev); + if(igb_detach(dev) =3D=3D 0) /* igb_detach did the cleanup */ + return(error); igb_free_transmit_structures(adapter); igb_free_receive_structures(adapter); igb_release_hw_control(adapter); -- Thanks, Sreekanth On 1/27/15, 11:28 AM, "hiren panchasara" > wrote: + Jack On Tue, Jan 27, 2015 at 12:00:19AM +0000, Sreekanth Rupavatharam wrote: Apologies if this is not the right forum. In igb_attach function, we have t= his code. err_late: igb_detach(dev); igb_free_transmit_structures(adapter); igb_free_receive_structures(adapter); igb_release_hw_control(adapter); err_pci: igb_free_pci_resources(adapter); if (adapter->ifp !=3D NULL) if_free(adapter->ifp); free(adapter->mta, M_DEVBUF); IGB_CORE_LOCK_DESTROY(adapter); The problem is that igb_detach also does the same cleanup in it?s body. Onl= y exception is this case where it just returns EBUSY /* Make sure VLANS are not using driver */ if (if_vlantrunkinuse(ifp)) { device_printf(dev,"Vlan in use, detach first\n"); return (EBUSY); } I think the code in igb_attach should be changed to free up resources only = if the igb_detach returns an error. Here?s the patch for it. Index: if_igb.c =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D --- if_igb.c (revision 298025) +++ if_igb.c (working copy) @@ -723,7 +723,8 @@ igb_attach(device_t dev) return (0); err_late: - igb_detach(dev); + if(igb_detach(dev) =3D=3D 0) /* igb_detach did the cleanup */ + return; igb_free_transmit_structures(adapter); Can anyone comment on it and tell me if my understanding is incorrect? Seems reasonable to me at the first glance. We need to call IGB_CORE_LOCK_DESTROY(adapter) before returning though. cheers, Hiren From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 20:24:19 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 952EE497; Tue, 27 Jan 2015 20:24:19 +0000 (UTC) Received: from mail-we0-x231.google.com (mail-we0-x231.google.com [IPv6:2a00:1450:400c:c03::231]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 2B0D43D8; Tue, 27 Jan 2015 20:24:19 +0000 (UTC) Received: by mail-we0-f177.google.com with SMTP id l61so16983723wev.8; Tue, 27 Jan 2015 12:24:17 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=pbMbzLEDi6JhHG4gY0NsQBqmUXi8ZkQ1X+Sz1RlGO/s=; b=l4WqMvo1miz96ejKWFQzpVG+2NsNQoqVyqJuSnPRcha/9mQ3qx9r8iNWhVngzmrVX0 sFNFNnOaMGHHqRP2T6TMs3mXaI0PjpRBd3kx1gTKzm3BGw1oLch7YJydwO0queV0h/qT kGYvq0qughOfrYjb06fPOY56xHUbJE93VT1jJvHFqODie4gLzcxjzyc3tu14CXFIu9Lr g+4qK8LhJnlSuOHjNLheR5IU8rSpEz5riOZ5ON1FW1lL5fnL2TmCMb5o869qL2JGUqHj QCxsWyY4paO982M6owwOaLrXqvSjyuN3xoSqob07mGUBBjI3UTP3SEh+mqF2YZ0YGoIj Ci0w== MIME-Version: 1.0 X-Received: by 10.180.74.114 with SMTP id s18mr9585769wiv.29.1422390257550; Tue, 27 Jan 2015 12:24:17 -0800 (PST) Received: by 10.194.101.106 with HTTP; Tue, 27 Jan 2015 12:24:17 -0800 (PST) In-Reply-To: <26266AD2-4743-4A7B-A87D-F68E2E2425A0@juniper.net> References: <20150127192814.GA63990@strugglingcoder.info> <26266AD2-4743-4A7B-A87D-F68E2E2425A0@juniper.net> Date: Tue, 27 Jan 2015 12:24:17 -0800 Message-ID: Subject: Re: Double cleanup in igb_attach From: Jack Vogel To: Sreekanth Rupavatharam Content-Type: text/plain; charset=ISO-8859-1 X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: "jfv@freebsd.org" , "freebsd-net@freebsd.org" , hiren panchasara X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 20:24:19 -0000 Errrr, I am one of those people :) (jack.vogel@intel.com) Jack On Tue, Jan 27, 2015 at 12:21 PM, Sreekanth Rupavatharam < rupavath@juniper.net> wrote: > Definitely, but I didn't have the contact info of those people. > > Thanks, > > -Sreekanth > > On Jan 27, 2015, at 12:15 PM, "Jack Vogel" wrote: > > If you want something committed to an Intel driver, asking Intel might > be the > courteous thing to do, don't you think? > > Jack > > > On Tue, Jan 27, 2015 at 11:51 AM, Sreekanth Rupavatharam < > rupavath@juniper.net> wrote: > >> Hiren, >> Can you help commit this? >> >> Index: if_igb.c >> >> =================================================================== >> >> --- if_igb.c (revision 298053) >> >> +++ if_igb.c (working copy) >> >> @@ -723,7 +723,8 @@ igb_attach(device_t dev) >> >> return (0); >> >> >> >> err_late: >> >> - igb_detach(dev); >> >> + if(igb_detach(dev) == 0) /* igb_detach did the cleanup */ >> >> + return(error); >> >> igb_free_transmit_structures(adapter); >> >> igb_free_receive_structures(adapter); >> >> igb_release_hw_control(adapter); >> >> -- Thanks, >> >> Sreekanth >> >> >> >> >> >> >> On 1/27/15, 11:28 AM, "hiren panchasara" >> wrote: >> >> + Jack >> On Tue, Jan 27, 2015 at 12:00:19AM +0000, Sreekanth Rupavatharam wrote: >> >> Apologies if this is not the right forum. In igb_attach function, we have >> this code. >> err_late: >> igb_detach(dev); >> igb_free_transmit_structures(adapter); >> igb_free_receive_structures(adapter); >> igb_release_hw_control(adapter); >> err_pci: >> igb_free_pci_resources(adapter); >> if (adapter->ifp != NULL) >> if_free(adapter->ifp); >> free(adapter->mta, M_DEVBUF); >> IGB_CORE_LOCK_DESTROY(adapter); >> The problem is that igb_detach also does the same cleanup in it?s body. >> Only exception is this case where it just returns EBUSY >> /* Make sure VLANS are not using driver */ >> if (if_vlantrunkinuse(ifp)) { >> device_printf(dev,"Vlan in use, detach first\n"); >> return (EBUSY); >> } >> I think the code in igb_attach should be changed to free up resources >> only if the igb_detach returns an error. Here?s the patch for it. >> Index: if_igb.c >> =================================================================== >> --- if_igb.c (revision 298025) >> +++ if_igb.c (working copy) >> @@ -723,7 +723,8 @@ igb_attach(device_t dev) >> return (0); >> err_late: >> - igb_detach(dev); >> + if(igb_detach(dev) == 0) /* igb_detach did the cleanup */ >> + return; >> igb_free_transmit_structures(adapter); >> Can anyone comment on it and tell me if my understanding is incorrect? >> >> >> Seems reasonable to me at the first glance. >> >> We need to call IGB_CORE_LOCK_DESTROY(adapter) before returning though. >> >> cheers, >> Hiren >> >> > From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 20:28:41 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 450D8585 for ; Tue, 27 Jan 2015 20:28:41 +0000 (UTC) Received: from mail-we0-x22a.google.com (mail-we0-x22a.google.com [IPv6:2a00:1450:400c:c03::22a]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id D04005F2 for ; Tue, 27 Jan 2015 20:28:40 +0000 (UTC) Received: by mail-we0-f170.google.com with SMTP id w55so11608474wes.1 for ; Tue, 27 Jan 2015 12:28:39 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:from:date:message-id :subject:to:cc:content-type; bh=XUoEfOqDFbfwJ2RerLlAbMnv0hOCYTueqJpLo7NH+7A=; b=H3IS0vRpHOo1UvJysYe50yqJP5vaAu7jO3OEAuQwduFpOOfLodVGfsQuE8QVs1J4ir EvOFPugk3q3/78cVqvsXh0aLtesDS0abMiGNsikx/8lGYm8eY2GQ5aWGs5lCKk6gkxlV hI03F8R+/5LJSIj0xS9byOhlMdTMhCIOY6cyuXXXo9/LebDTYJ3zprgV+Ar1g+Dr3ON/ VJg2SC8PhPWeR7ffs851blTTwgu4m7ncvbLez2k509XaO6tSoqi/ESF3ScOMOWel8cpE tLMWJ1JfppkmCMnIdO8k8bi0Md+PODYMy7YUodGqDCNDJHBWZRgtFv5415QiAWLbjpzr dFag== X-Received: by 10.194.192.98 with SMTP id hf2mr6736681wjc.52.1422390519260; Tue, 27 Jan 2015 12:28:39 -0800 (PST) MIME-Version: 1.0 Sender: cochard@gmail.com Received: by 10.194.61.1 with HTTP; Tue, 27 Jan 2015 12:28:19 -0800 (PST) In-Reply-To: References: <871tmgceup.fsf@marcos.anarc.at> <87vbjsaxxy.fsf@marcos.anarc.at> From: =?ISO-8859-1?Q?Olivier_Cochard=2DLabb=E9?= Date: Tue, 27 Jan 2015 21:28:19 +0100 X-Google-Sender-Auth: M0Rg9GiKyAHLPlqyNdgkwjsTP2Y Message-ID: Subject: Re: is polling still a thing? To: Michael Sierchio Content-Type: text/plain; charset=ISO-8859-1 X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: "freebsd-net@freebsd.org" , Jim Thompson , =?ISO-8859-1?Q?Antoine_Beaupr=E9?= X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 20:28:41 -0000 On Tue, Jan 27, 2015 at 9:15 PM, Michael Sierchio wrote: > > > On small, embedded computers running ipfw w/kernel nat and device polling > enabled (on em ether adapters), I observed the *reported* system load grow > very high. When disabling polling on the interfaces, it went back to > something normal. > > My impression is that the consensus among the core developers concerned > with networking is that device polling is an ancient hack and is > deprecated. In the case of a DDoS attack, there may be many other things to > try - at the infrastructure level - traffic diversion techniques like BGP > flowspec, use anycast, etc. On the individual server level, use stateful > rules with GRED enabled, dropping most new tcp or udp traffic based on load. > > > If I remember well, Luigi had a surprise regarding the advantage of using polling inside a VM: https://lists.freebsd.org/pipermail/freebsd-net/2013-May/035626.html But on real hardware, since the introduction of interrupt moderation on NIC, polling is not more useful. From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 20:39:00 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 5C67AA86; Tue, 27 Jan 2015 20:39:00 +0000 (UTC) Received: from na01-by2-obe.outbound.protection.outlook.com (mail-by2on0129.outbound.protection.outlook.com [207.46.100.129]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-SHA384 (256/256 bits)) (Client CN "mail.protection.outlook.com", Issuer "MSIT Machine Auth CA 2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 0048077B; Tue, 27 Jan 2015 20:38:59 +0000 (UTC) Received: from CO2PR05MB761.namprd05.prod.outlook.com (10.141.227.13) by CO2PR05MB763.namprd05.prod.outlook.com (10.141.227.15) with Microsoft SMTP Server (TLS) id 15.1.65.19; Tue, 27 Jan 2015 20:38:53 +0000 Received: from CO2PR05MB761.namprd05.prod.outlook.com ([10.141.227.13]) by CO2PR05MB761.namprd05.prod.outlook.com ([10.141.227.13]) with mapi id 15.01.0065.013; Tue, 27 Jan 2015 20:38:53 +0000 From: Sreekanth Rupavatharam To: Jack Vogel Subject: Re: Double cleanup in igb_attach Thread-Topic: Double cleanup in igb_attach Thread-Index: AQHQOcQ8M6DG1/D37kKlfeofCj44QJzUW0EA//+AdgCAAIzTgIAAAX8YgAAA4YCAAAQUEw== Date: Tue, 27 Jan 2015 20:38:52 +0000 Message-ID: References: <20150127192814.GA63990@strugglingcoder.info> <26266AD2-4743-4A7B-A87D-F68E2E2425A0@juniper.net>, In-Reply-To: Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [66.129.246.4] authentication-results: gmail.com; dkim=none (message not signed) header.d=none;gmail.com; dmarc=none action=none header.from=juniper.net; x-dmarcaction-test: None x-microsoft-antispam: BCL:0;PCL:0;RULEID:(3005004);SRVR:CO2PR05MB763; x-exchange-antispam-report-test: UriScan:; x-exchange-antispam-report-cfa-test: BCL:0;PCL:0;RULEID:;SRVR:CO2PR05MB763; x-forefront-prvs: 046985391D x-forefront-antispam-report: SFV:NSPM; SFS:(10019020)(479174004)(24454002)(164054003)(377454003)(50986999)(19580395003)(46102003)(66066001)(36756003)(16236675004)(99286002)(87936001)(76176999)(1411001)(19580405001)(86362001)(54356999)(106116001)(82746002)(110136001)(93886004)(83716003)(92566002)(2950100001)(2900100001)(102836002)(33656002)(77096005)(122556002)(2656002)(77156002)(40100003)(62966003)(104396002)(6606295002); DIR:OUT; SFP:1102; SCL:1; SRVR:CO2PR05MB763; H:CO2PR05MB761.namprd05.prod.outlook.com; FPR:; SPF:None; MLV:sfv; LANG:en; MIME-Version: 1.0 X-OriginatorOrg: juniper.net X-MS-Exchange-CrossTenant-originalarrivaltime: 27 Jan 2015 20:38:52.9900 (UTC) X-MS-Exchange-CrossTenant-fromentityheader: Hosted X-MS-Exchange-CrossTenant-id: bea78b3c-4cdb-4130-854a-1d193232e5f4 X-MS-Exchange-Transport-CrossTenantHeadersStamped: CO2PR05MB763 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: "jfv@freebsd.org" , "freebsd-net@freebsd.org" , hiren panchasara X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 20:39:00 -0000 Thanks jack, Now, can you please review these changes? And commit if you deem it fi= t? Thanks, -Sreekanth On Jan 27, 2015, at 12:24 PM, "Jack Vogel" > wrote: Errrr, I am one of those people :) (jack.vogel@intel.com) Jack On Tue, Jan 27, 2015 at 12:21 PM, Sreekanth Rupavatharam > wrote: Definitely, but I didn't have the contact info of those people. Thanks, -Sreekanth On Jan 27, 2015, at 12:15 PM, "Jack Vogel" > wrote: If you want something committed to an Intel driver, asking Intel might be t= he courteous thing to do, don't you think? Jack On Tue, Jan 27, 2015 at 11:51 AM, Sreekanth Rupavatharam > wrote: Hiren, Can you help commit this? Index: if_igb.c =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D --- if_igb.c (revision 298053) +++ if_igb.c (working copy) @@ -723,7 +723,8 @@ igb_attach(device_t dev) return (0); err_late: - igb_detach(dev); + if(igb_detach(dev) =3D=3D 0) /* igb_detach did the cleanup */ + return(error); igb_free_transmit_structures(adapter); igb_free_receive_structures(adapter); igb_release_hw_control(adapter); -- Thanks, Sreekanth On 1/27/15, 11:28 AM, "hiren panchasara" > wrote: + Jack On Tue, Jan 27, 2015 at 12:00:19AM +0000, Sreekanth Rupavatharam wrote: Apologies if this is not the right forum. In igb_attach function, we have t= his code. err_late: igb_detach(dev); igb_free_transmit_structures(adapter); igb_free_receive_structures(adapter); igb_release_hw_control(adapter); err_pci: igb_free_pci_resources(adapter); if (adapter->ifp !=3D NULL) if_free(adapter->ifp); free(adapter->mta, M_DEVBUF); IGB_CORE_LOCK_DESTROY(adapter); The problem is that igb_detach also does the same cleanup in it?s body. Onl= y exception is this case where it just returns EBUSY /* Make sure VLANS are not using driver */ if (if_vlantrunkinuse(ifp)) { device_printf(dev,"Vlan in use, detach first\n"); return (EBUSY); } I think the code in igb_attach should be changed to free up resources only = if the igb_detach returns an error. Here?s the patch for it. Index: if_igb.c =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D --- if_igb.c (revision 298025) +++ if_igb.c (working copy) @@ -723,7 +723,8 @@ igb_attach(device_t dev) return (0); err_late: - igb_detach(dev); + if(igb_detach(dev) =3D=3D 0) /* igb_detach did the cleanup */ + return; igb_free_transmit_structures(adapter); Can anyone comment on it and tell me if my understanding is incorrect? Seems reasonable to me at the first glance. We need to call IGB_CORE_LOCK_DESTROY(adapter) before returning though. cheers, Hiren From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 20:42:24 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 9DC9AD15; Tue, 27 Jan 2015 20:42:24 +0000 (UTC) Received: from mail-we0-x231.google.com (mail-we0-x231.google.com [IPv6:2a00:1450:400c:c03::231]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 35B61843; Tue, 27 Jan 2015 20:42:24 +0000 (UTC) Received: by mail-we0-f177.google.com with SMTP id l61so17059382wev.8; Tue, 27 Jan 2015 12:42:22 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=+gnTg0ciSd9tyUnf1D0zY9t6mp1Sz6BsCDkAIBrZuMg=; b=s/pwAVy5aaqj6PiOt0+34dsp5nz3LEdFCJl96AjilGGfmiXnWbCoJyo1SaHS70q8yp EF/nq0VlnSV5nMr5L7G7I+jwQWy9+G1KFnFvWMcBpzHEQbimk6BwMDRykq3ziA0KoPSQ 4HjTIFLrQRaZivliEhv1l7l8IEQUwtHiJaO4vkg3okSaT0UG+bKuwJHQ+YRZrkwsE8kb q+9pnWhs/RX6P57h6xgYwZ/gCXVNqwTrzWDdCutMGOPj/9eFWqfSkL44wbvNmTA47/sq pgEPnYMPsv5+XGvw9Vk7QltujVqJvVkKiwnQaSl2+saj3S35Ndsz6r5fiQRDZt3UTlFA pIrw== MIME-Version: 1.0 X-Received: by 10.194.219.68 with SMTP id pm4mr2663079wjc.71.1422391342735; Tue, 27 Jan 2015 12:42:22 -0800 (PST) Received: by 10.194.101.106 with HTTP; Tue, 27 Jan 2015 12:42:22 -0800 (PST) In-Reply-To: References: <20150127192814.GA63990@strugglingcoder.info> <26266AD2-4743-4A7B-A87D-F68E2E2425A0@juniper.net> Date: Tue, 27 Jan 2015 12:42:22 -0800 Message-ID: Subject: Re: Double cleanup in igb_attach From: Jack Vogel To: Sreekanth Rupavatharam Content-Type: text/plain; charset=ISO-8859-1 X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: "jfv@freebsd.org" , "freebsd-net@freebsd.org" , hiren panchasara X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 20:42:24 -0000 Yes, I will look them over. Jack On Tue, Jan 27, 2015 at 12:38 PM, Sreekanth Rupavatharam < rupavath@juniper.net> wrote: > Thanks jack, > Now, can you please review these changes? And commit if you deem it > fit? > > Thanks, > > -Sreekanth > > On Jan 27, 2015, at 12:24 PM, "Jack Vogel" wrote: > > Errrr, I am one of those people :) (jack.vogel@intel.com) > > Jack > > > On Tue, Jan 27, 2015 at 12:21 PM, Sreekanth Rupavatharam < > rupavath@juniper.net> wrote: > >> Definitely, but I didn't have the contact info of those people. >> >> Thanks, >> >> -Sreekanth >> >> On Jan 27, 2015, at 12:15 PM, "Jack Vogel" wrote: >> >> If you want something committed to an Intel driver, asking Intel might >> be the >> courteous thing to do, don't you think? >> >> Jack >> >> >> On Tue, Jan 27, 2015 at 11:51 AM, Sreekanth Rupavatharam < >> rupavath@juniper.net> wrote: >> >>> Hiren, >>> Can you help commit this? >>> >>> Index: if_igb.c >>> >>> =================================================================== >>> >>> --- if_igb.c (revision 298053) >>> >>> +++ if_igb.c (working copy) >>> >>> @@ -723,7 +723,8 @@ igb_attach(device_t dev) >>> >>> return (0); >>> >>> >>> >>> err_late: >>> >>> - igb_detach(dev); >>> >>> + if(igb_detach(dev) == 0) /* igb_detach did the cleanup */ >>> >>> + return(error); >>> >>> igb_free_transmit_structures(adapter); >>> >>> igb_free_receive_structures(adapter); >>> >>> igb_release_hw_control(adapter); >>> >>> -- Thanks, >>> >>> Sreekanth >>> >>> >>> >>> >>> >>> >>> On 1/27/15, 11:28 AM, "hiren panchasara" >>> wrote: >>> >>> + Jack >>> On Tue, Jan 27, 2015 at 12:00:19AM +0000, Sreekanth Rupavatharam wrote: >>> >>> Apologies if this is not the right forum. In igb_attach function, we >>> have this code. >>> err_late: >>> igb_detach(dev); >>> igb_free_transmit_structures(adapter); >>> igb_free_receive_structures(adapter); >>> igb_release_hw_control(adapter); >>> err_pci: >>> igb_free_pci_resources(adapter); >>> if (adapter->ifp != NULL) >>> if_free(adapter->ifp); >>> free(adapter->mta, M_DEVBUF); >>> IGB_CORE_LOCK_DESTROY(adapter); >>> The problem is that igb_detach also does the same cleanup in it?s >>> body. Only exception is this case where it just returns EBUSY >>> /* Make sure VLANS are not using driver */ >>> if (if_vlantrunkinuse(ifp)) { >>> device_printf(dev,"Vlan in use, detach first\n"); >>> return (EBUSY); >>> } >>> I think the code in igb_attach should be changed to free up resources >>> only if the igb_detach returns an error. Here?s the patch for it. >>> Index: if_igb.c >>> =================================================================== >>> --- if_igb.c (revision 298025) >>> +++ if_igb.c (working copy) >>> @@ -723,7 +723,8 @@ igb_attach(device_t dev) >>> return (0); >>> err_late: >>> - igb_detach(dev); >>> + if(igb_detach(dev) == 0) /* igb_detach did the cleanup */ >>> + return; >>> igb_free_transmit_structures(adapter); >>> Can anyone comment on it and tell me if my understanding is >>> incorrect? >>> >>> >>> Seems reasonable to me at the first glance. >>> >>> We need to call IGB_CORE_LOCK_DESTROY(adapter) before returning though. >>> >>> cheers, >>> Hiren >>> >>> >> > From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 20:54:09 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 20D8B2A2; Tue, 27 Jan 2015 20:54:09 +0000 (UTC) Received: from mail-ig0-x232.google.com (mail-ig0-x232.google.com [IPv6:2607:f8b0:4001:c05::232]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id DB4B0960; Tue, 27 Jan 2015 20:54:08 +0000 (UTC) Received: by mail-ig0-f178.google.com with SMTP id hl2so7186542igb.5; Tue, 27 Jan 2015 12:54:08 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date:message-id:subject :from:to:cc:content-type; bh=AtJpnTOPi9tqb+rQvd4pytR/cqGpyOFnLjAGvuMO+Fs=; b=gdkSNZTHgdv4WoYcB3+rmRgIAbXyINNH4Z4eyNbZty9ZI634YLDdBvRY4fDqY7/lNS ymSyWMsUqpgPA9nFPZGXDeauOc15cscIFj6EWxCBhdLePoE0BbBIyYOCRyoEA/PuxsPI G5sduqlTpUGl+ZULP+bjhCORDq8+FJJeNJ6uhu2HEHXCwLddhK9Y3s26zaaoGiQ69XRy cuWO56055hvHtPpn0HJPYyQIBhll4C3gyEfiX0LXq5Ph9MgDX0Xz5T7eOTEBXoWiYLcW XHGVIznOLKvQ2K9+bWkMwsuAtPFh2dcUHfNuxTc3wuc2fiRuCvDG38UOsO/w0FjtUBG6 tdxw== MIME-Version: 1.0 X-Received: by 10.42.62.71 with SMTP id x7mr4329871ich.61.1422392048335; Tue, 27 Jan 2015 12:54:08 -0800 (PST) Sender: adrian.chadd@gmail.com Received: by 10.36.78.14 with HTTP; Tue, 27 Jan 2015 12:54:08 -0800 (PST) In-Reply-To: References: <20150127192814.GA63990@strugglingcoder.info> <26266AD2-4743-4A7B-A87D-F68E2E2425A0@juniper.net> Date: Tue, 27 Jan 2015 12:54:08 -0800 X-Google-Sender-Auth: MEDbf5ev9z7Fe8xrAaE86EjPNvY Message-ID: Subject: Re: Double cleanup in igb_attach From: Adrian Chadd To: Jack Vogel Content-Type: text/plain; charset=UTF-8 Cc: "jfv@freebsd.org" , "freebsd-net@freebsd.org" , Sreekanth Rupavatharam , hiren panchasara X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 20:54:09 -0000 Hi! Sreekanth - this does look like it is valid and needs fixing. Just file a FreeBSD PR (bugs.freebsd.org/submit/) and we'll assign it to the intel team. Thanks! -a On 27 January 2015 at 12:42, Jack Vogel wrote: > Yes, I will look them over. > > Jack > > > On Tue, Jan 27, 2015 at 12:38 PM, Sreekanth Rupavatharam < > rupavath@juniper.net> wrote: > >> Thanks jack, >> Now, can you please review these changes? And commit if you deem it >> fit? >> >> Thanks, >> >> -Sreekanth >> >> On Jan 27, 2015, at 12:24 PM, "Jack Vogel" wrote: >> >> Errrr, I am one of those people :) (jack.vogel@intel.com) >> >> Jack >> >> >> On Tue, Jan 27, 2015 at 12:21 PM, Sreekanth Rupavatharam < >> rupavath@juniper.net> wrote: >> >>> Definitely, but I didn't have the contact info of those people. >>> >>> Thanks, >>> >>> -Sreekanth >>> >>> On Jan 27, 2015, at 12:15 PM, "Jack Vogel" wrote: >>> >>> If you want something committed to an Intel driver, asking Intel might >>> be the >>> courteous thing to do, don't you think? >>> >>> Jack >>> >>> >>> On Tue, Jan 27, 2015 at 11:51 AM, Sreekanth Rupavatharam < >>> rupavath@juniper.net> wrote: >>> >>>> Hiren, >>>> Can you help commit this? >>>> >>>> Index: if_igb.c >>>> >>>> =================================================================== >>>> >>>> --- if_igb.c (revision 298053) >>>> >>>> +++ if_igb.c (working copy) >>>> >>>> @@ -723,7 +723,8 @@ igb_attach(device_t dev) >>>> >>>> return (0); >>>> >>>> >>>> >>>> err_late: >>>> >>>> - igb_detach(dev); >>>> >>>> + if(igb_detach(dev) == 0) /* igb_detach did the cleanup */ >>>> >>>> + return(error); >>>> >>>> igb_free_transmit_structures(adapter); >>>> >>>> igb_free_receive_structures(adapter); >>>> >>>> igb_release_hw_control(adapter); >>>> >>>> -- Thanks, >>>> >>>> Sreekanth >>>> >>>> >>>> >>>> >>>> >>>> >>>> On 1/27/15, 11:28 AM, "hiren panchasara" >>>> wrote: >>>> >>>> + Jack >>>> On Tue, Jan 27, 2015 at 12:00:19AM +0000, Sreekanth Rupavatharam wrote: >>>> >>>> Apologies if this is not the right forum. In igb_attach function, we >>>> have this code. >>>> err_late: >>>> igb_detach(dev); >>>> igb_free_transmit_structures(adapter); >>>> igb_free_receive_structures(adapter); >>>> igb_release_hw_control(adapter); >>>> err_pci: >>>> igb_free_pci_resources(adapter); >>>> if (adapter->ifp != NULL) >>>> if_free(adapter->ifp); >>>> free(adapter->mta, M_DEVBUF); >>>> IGB_CORE_LOCK_DESTROY(adapter); >>>> The problem is that igb_detach also does the same cleanup in it?s >>>> body. Only exception is this case where it just returns EBUSY >>>> /* Make sure VLANS are not using driver */ >>>> if (if_vlantrunkinuse(ifp)) { >>>> device_printf(dev,"Vlan in use, detach first\n"); >>>> return (EBUSY); >>>> } >>>> I think the code in igb_attach should be changed to free up resources >>>> only if the igb_detach returns an error. Here?s the patch for it. >>>> Index: if_igb.c >>>> =================================================================== >>>> --- if_igb.c (revision 298025) >>>> +++ if_igb.c (working copy) >>>> @@ -723,7 +723,8 @@ igb_attach(device_t dev) >>>> return (0); >>>> err_late: >>>> - igb_detach(dev); >>>> + if(igb_detach(dev) == 0) /* igb_detach did the cleanup */ >>>> + return; >>>> igb_free_transmit_structures(adapter); >>>> Can anyone comment on it and tell me if my understanding is >>>> incorrect? >>>> >>>> >>>> Seems reasonable to me at the first glance. >>>> >>>> We need to call IGB_CORE_LOCK_DESTROY(adapter) before returning though. >>>> >>>> cheers, >>>> Hiren >>>> >>>> >>> >> > _______________________________________________ > freebsd-net@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 22:09:01 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id C7D6CC56 for ; Tue, 27 Jan 2015 22:09:01 +0000 (UTC) Received: from marcos.anarc.at (mail.orangeseeds.org [72.0.72.144]) by mx1.freebsd.org (Postfix) with ESMTP id 727F91BC for ; Tue, 27 Jan 2015 22:08:59 +0000 (UTC) Received: by marcos.anarc.at (Postfix, from userid 1000) id 23F9B1A006C; Tue, 27 Jan 2015 17:08:27 -0500 (EST) From: Antoine =?utf-8?Q?Beaupr=C3=A9?= To: wishmaster Subject: Re: is polling still a thing? In-Reply-To: <1422384769.867067950.y2iiuu53@frv34.fwdcdn.com> References: <871tmgceup.fsf@marcos.anarc.at> <1422384769.867067950.y2iiuu53@frv34.fwdcdn.com> User-Agent: Notmuch/0.18.2 (http://notmuchmail.org) Emacs/24.4.1 (x86_64-pc-linux-gnu) Date: Tue, 27 Jan 2015 17:08:27 -0500 Message-ID: <87pp9zc1wk.fsf@marcos.anarc.at> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Cc: freebsd-net@freebsd.org X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 22:09:01 -0000 On 2015-01-27 13:57:20, wishmaster wrote: > Have you consider to use netmap-based ipfw instead pf in DDoS mitigation?= I think you should. And without any network ''haks'' like polling. My understanding of netmap was that it wasn't useful for packet forwarding, because its design is for transmitting packets directly to userland faster, whereas routers dataflow stay mostly in the router... I'm hesitant in switching back to ipfw, considering how nice the featureset and syntax of pf is. But if that's what's needed to restore sanity... a. --=20 Celui qui sait jouir du peu qu'il a est toujours assez riche. - D=C3=A9mocrite From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 22:34:08 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 146E0FD7 for ; Tue, 27 Jan 2015 22:34:08 +0000 (UTC) Received: from onelab2.iet.unipi.it (onelab2.iet.unipi.it [131.114.59.238]) by mx1.freebsd.org (Postfix) with ESMTP id C9BEE693 for ; Tue, 27 Jan 2015 22:34:07 +0000 (UTC) Received: by onelab2.iet.unipi.it (Postfix, from userid 275) id 4EED57300A; Tue, 27 Jan 2015 23:39:17 +0100 (CET) Date: Tue, 27 Jan 2015 23:39:17 +0100 From: Luigi Rizzo To: Antoine Beaupr? Subject: Re: is polling still a thing? Message-ID: <20150127223917.GA21883@onelab2.iet.unipi.it> References: <871tmgceup.fsf@marcos.anarc.at> <1422384769.867067950.y2iiuu53@frv34.fwdcdn.com> <87pp9zc1wk.fsf@marcos.anarc.at> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <87pp9zc1wk.fsf@marcos.anarc.at> User-Agent: Mutt/1.5.20 (2009-06-14) Cc: freebsd-net@freebsd.org, wishmaster X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 22:34:08 -0000 On Tue, Jan 27, 2015 at 05:08:27PM -0500, Antoine Beaupr? wrote: > On 2015-01-27 13:57:20, wishmaster wrote: > > Have you consider to use netmap-based ipfw instead pf in DDoS mitigation? I think you should. And without any network ''haks'' like polling. > > My understanding of netmap was that it wasn't useful for packet > forwarding, because its design is for transmitting packets directly to > userland faster, whereas routers dataflow stay mostly in the router... i think the suggestion was to have let netmap-ipfw drop the traffic you don't want to deal with, and then inject the remaining ones into the kernel where the processing occurs -- possibly even using pf or a different firewall There are people using netmap-ipfw on external physical boxes exactly in this way -- as a "bump in the wire", but it is trivial to run it on the same machine. cheers luigi > I'm hesitant in switching back to ipfw, considering how nice the > featureset and syntax of pf is. But if that's what's needed to restore > sanity... > > a. > > -- > Celui qui sait jouir du peu qu'il a est toujours assez riche. > - Démocrite > _______________________________________________ > freebsd-net@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 22:36:02 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 5AF5E30A; Tue, 27 Jan 2015 22:36:02 +0000 (UTC) Received: from na01-bn1-obe.outbound.protection.outlook.com (mail-bn1bon0136.outbound.protection.outlook.com [157.56.111.136]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-SHA384 (256/256 bits)) (Client CN "mail.protection.outlook.com", Issuer "MSIT Machine Auth CA 2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id B650D6C6; Tue, 27 Jan 2015 22:36:01 +0000 (UTC) Received: from CO2PR05MB761.namprd05.prod.outlook.com (10.141.227.13) by CO2PR05MB761.namprd05.prod.outlook.com (10.141.227.13) with Microsoft SMTP Server (TLS) id 15.1.65.19; Tue, 27 Jan 2015 21:03:10 +0000 Received: from CO2PR05MB761.namprd05.prod.outlook.com ([10.141.227.13]) by CO2PR05MB761.namprd05.prod.outlook.com ([10.141.227.13]) with mapi id 15.01.0065.013; Tue, 27 Jan 2015 21:03:10 +0000 From: Sreekanth Rupavatharam To: Adrian Chadd , Jack Vogel Subject: Re: Double cleanup in igb_attach Thread-Topic: Double cleanup in igb_attach Thread-Index: AQHQOcQ8M6DG1/D37kKlfeofCj44QJzUW0EA//+AdgCAAIzTgIAAAX8YgAAA4YCAAAQUE4AAAPkAgAADSgD//3xmgA== Date: Tue, 27 Jan 2015 21:03:10 +0000 Message-ID: References: <20150127192814.GA63990@strugglingcoder.info> <26266AD2-4743-4A7B-A87D-F68E2E2425A0@juniper.net> In-Reply-To: Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: user-agent: Microsoft-MacOutlook/14.4.7.141117 x-originating-ip: [66.129.239.13] authentication-results: freebsd.org; dkim=none (message not signed) header.d=none;freebsd.org; dmarc=none action=none header.from=juniper.net; x-dmarcaction-test: None x-microsoft-antispam: BCL:0;PCL:0;RULEID:(3005004);SRVR:CO2PR05MB761; x-exchange-antispam-report-test: UriScan:; x-exchange-antispam-report-cfa-test: BCL:0;PCL:0;RULEID:;SRVR:CO2PR05MB761; x-forefront-prvs: 046985391D x-forefront-antispam-report: SFV:NSPM; SFS:(10019020)(6009001)(41574002)(51704005)(479174004)(164054003)(24454002)(377454003)(106116001)(83506001)(2656002)(46102003)(99286002)(19580395003)(93886004)(87936001)(19580405001)(15975445007)(102836002)(77156002)(1720100001)(62966003)(86362001)(77096005)(2950100001)(76176999)(50986999)(54356999)(36756003)(40100003)(66066001)(2900100001)(122556002)(92566002)(6606295002); DIR:OUT; SFP:1102; SCL:1; SRVR:CO2PR05MB761; H:CO2PR05MB761.namprd05.prod.outlook.com; FPR:; SPF:None; MLV:sfv; LANG:en; Content-Type: text/plain; charset="us-ascii" Content-ID: Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 X-OriginatorOrg: juniper.net X-MS-Exchange-CrossTenant-originalarrivaltime: 27 Jan 2015 21:03:10.3126 (UTC) X-MS-Exchange-CrossTenant-fromentityheader: Hosted X-MS-Exchange-CrossTenant-id: bea78b3c-4cdb-4130-854a-1d193232e5f4 X-MS-Exchange-Transport-CrossTenantHeadersStamped: CO2PR05MB761 Cc: "jfv@freebsd.org" , "freebsd-net@freebsd.org" , hiren panchasara X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 22:36:02 -0000 Done, I have also attached the patch in the bug report. -- Thanks, Sreekanth On 1/27/15, 12:54 PM, "Adrian Chadd" wrote: >Hi! > >Sreekanth - this does look like it is valid and needs fixing. Just >file a FreeBSD PR (bugs.freebsd.org/submit/) and we'll assign it to >the intel team. > >Thanks! > > >-a > > >On 27 January 2015 at 12:42, Jack Vogel wrote: >> Yes, I will look them over. >> >> Jack >> >> >> On Tue, Jan 27, 2015 at 12:38 PM, Sreekanth Rupavatharam < >> rupavath@juniper.net> wrote: >> >>> Thanks jack, >>> Now, can you please review these changes? And commit if you deem >>>it >>> fit? >>> >>> Thanks, >>> >>> -Sreekanth >>> >>> On Jan 27, 2015, at 12:24 PM, "Jack Vogel" wrote: >>> >>> Errrr, I am one of those people :) (jack.vogel@intel.com) >>> >>> Jack >>> >>> >>> On Tue, Jan 27, 2015 at 12:21 PM, Sreekanth Rupavatharam < >>> rupavath@juniper.net> wrote: >>> >>>> Definitely, but I didn't have the contact info of those people. >>>> >>>> Thanks, >>>> >>>> -Sreekanth >>>> >>>> On Jan 27, 2015, at 12:15 PM, "Jack Vogel" wrote: >>>> >>>> If you want something committed to an Intel driver, asking Intel >>>>might >>>> be the >>>> courteous thing to do, don't you think? >>>> >>>> Jack >>>> >>>> >>>> On Tue, Jan 27, 2015 at 11:51 AM, Sreekanth Rupavatharam < >>>> rupavath@juniper.net> wrote: >>>> >>>>> Hiren, >>>>> Can you help commit this? >>>>> >>>>> Index: if_igb.c >>>>> >>>>> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D >>>>> >>>>> --- if_igb.c (revision 298053) >>>>> >>>>> +++ if_igb.c (working copy) >>>>> >>>>> @@ -723,7 +723,8 @@ igb_attach(device_t dev) >>>>> >>>>> return (0); >>>>> >>>>> >>>>> >>>>> err_late: >>>>> >>>>> - igb_detach(dev); >>>>> >>>>> + if(igb_detach(dev) =3D=3D 0) /* igb_detach did the cleanup */ >>>>> >>>>> + return(error); >>>>> >>>>> igb_free_transmit_structures(adapter); >>>>> >>>>> igb_free_receive_structures(adapter); >>>>> >>>>> igb_release_hw_control(adapter); >>>>> >>>>> -- Thanks, >>>>> >>>>> Sreekanth >>>>> >>>>> >>>>> >>>>> >>>>> >>>>> >>>>> On 1/27/15, 11:28 AM, "hiren panchasara" >>>>> >>>>> wrote: >>>>> >>>>> + Jack >>>>> On Tue, Jan 27, 2015 at 12:00:19AM +0000, Sreekanth Rupavatharam >>>>>wrote: >>>>> >>>>> Apologies if this is not the right forum. In igb_attach function, we >>>>> have this code. >>>>> err_late: >>>>> igb_detach(dev); >>>>> igb_free_transmit_structures(adapter); >>>>> igb_free_receive_structures(adapter); >>>>> igb_release_hw_control(adapter); >>>>> err_pci: >>>>> igb_free_pci_resources(adapter); >>>>> if (adapter->ifp !=3D NULL) >>>>> if_free(adapter->ifp); >>>>> free(adapter->mta, M_DEVBUF); >>>>> IGB_CORE_LOCK_DESTROY(adapter); >>>>> The problem is that igb_detach also does the same cleanup in it?s >>>>> body. Only exception is this case where it just returns EBUSY >>>>> /* Make sure VLANS are not using driver */ >>>>> if (if_vlantrunkinuse(ifp)) { >>>>> device_printf(dev,"Vlan in use, detach first\n"); >>>>> return (EBUSY); >>>>> } >>>>> I think the code in igb_attach should be changed to free up >>>>>resources >>>>> only if the igb_detach returns an error. Here?s the patch for it. >>>>> Index: if_igb.c >>>>> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D >>>>> --- if_igb.c (revision 298025) >>>>> +++ if_igb.c (working copy) >>>>> @@ -723,7 +723,8 @@ igb_attach(device_t dev) >>>>> return (0); >>>>> err_late: >>>>> - igb_detach(dev); >>>>> + if(igb_detach(dev) =3D=3D 0) /* igb_detach did the cleanup */ >>>>> + return; >>>>> igb_free_transmit_structures(adapter); >>>>> Can anyone comment on it and tell me if my understanding is >>>>> incorrect? >>>>> >>>>> >>>>> Seems reasonable to me at the first glance. >>>>> >>>>> We need to call IGB_CORE_LOCK_DESTROY(adapter) before returning >>>>>though. >>>>> >>>>> cheers, >>>>> Hiren >>>>> >>>>> >>>> >>> >> _______________________________________________ >> freebsd-net@freebsd.org mailing list >> http://lists.freebsd.org/mailman/listinfo/freebsd-net >> To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 22:44:37 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 2D666812 for ; Tue, 27 Jan 2015 22:44:37 +0000 (UTC) Received: from mail-ob0-f180.google.com (mail-ob0-f180.google.com [209.85.214.180]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id E1D21828 for ; Tue, 27 Jan 2015 22:44:36 +0000 (UTC) Received: by mail-ob0-f180.google.com with SMTP id uz6so16202311obc.11 for ; Tue, 27 Jan 2015 14:44:30 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:content-type:mime-version:subject:from :in-reply-to:date:cc:message-id:references:to; bh=a0Qp1M6s/TtSn7aqI93hrt7EdDajGmEQpr0WZ3hZELo=; b=UaDoDg1tZHJH+60DoGReq1GwJPpI6oZjOxq7d4K5rztgypoTEN1td99dU1hgmP9W96 sNMaPBEqaz0elD4uxAoSlNQ1c1fIhUKjMUtN1QnBi923cgHQUGtVhVKfQdBTNaJG1GtS fR0CdCZOW0KRpKtTnQWMkHGsypczjgRfC15pKWzDCU6XgXJmpw4cRUJZyPegs8LWWWkr 4iiuW32LBxY3gKirCSwuVrC6Jbm/st4qAJGKY6SkIjqKCRXeq+fZ3TPOEZQ9TB9o4OvP m7kMWvb5UcTeyLq4Oaqjq5b69NfTcHEKTKGUW5jhdnVZsS8/eyQV+JUfQGyTSozPtCBV XT7g== X-Gm-Message-State: ALoCoQkKGgaIoZ3w99ViD/kJZX/9IK2yPak6sFODx4/U8uP1SXfc7s4VAw+UXDQ2W6dgTR3yxIR1 X-Received: by 10.182.191.6 with SMTP id gu6mr275095obc.36.1422398670482; Tue, 27 Jan 2015 14:44:30 -0800 (PST) Received: from ?IPv6:2610:160:11:33:956e:9562:4694:6bbf? ([2610:160:11:33:956e:9562:4694:6bbf]) by mx.google.com with ESMTPSA id mp3sm1344065obb.25.2015.01.27.14.44.29 (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Tue, 27 Jan 2015 14:44:29 -0800 (PST) Mime-Version: 1.0 (Mac OS X Mail 8.2 \(2070.1\)) Subject: Re: is polling still a thing? From: Jim Thompson In-Reply-To: Date: Tue, 27 Jan 2015 16:44:30 -0600 Message-Id: References: <871tmgceup.fsf@marcos.anarc.at> <87vbjsaxxy.fsf@marcos.anarc.at> To: =?utf-8?Q?Olivier_Cochard-Labb=C3=A9?= X-Mailer: Apple Mail (2.2070.1) Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: "freebsd-net@freebsd.org" , Michael Sierchio , =?utf-8?Q?Antoine_Beaupr=C3=A9?= X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 22:44:37 -0000 > On Jan 27, 2015, at 2:28 PM, Olivier Cochard-Labb=E9 = wrote: >=20 > On Tue, Jan 27, 2015 at 9:15 PM, Michael Sierchio > wrote: >=20 >=20 > On small, embedded computers running ipfw w/kernel nat and device = polling enabled (on em ether adapters), I observed the *reported* system = load grow very high. When disabling polling on the interfaces, it went = back to something normal. >=20 > My impression is that the consensus among the core developers = concerned with networking is that device polling is an ancient hack and = is deprecated. In the case of a DDoS attack, there may be many other = things to try - at the infrastructure level - traffic diversion = techniques like BGP flowspec, use anycast, etc. On the individual = server level, use stateful rules with GRED enabled, dropping most new = tcp or udp traffic based on load. >=20 >=20 >=20 > If I remember well, Luigi had a surprise regarding the advantage of = using polling inside a VM: > https://lists.freebsd.org/pipermail/freebsd-net/2013-May/035626.html = >=20 > But on real hardware, since the introduction of interrupt moderation = on NIC, polling is not more useful. The DPDK guys disagree. From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 23:03:17 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 87608C8D for ; Tue, 27 Jan 2015 23:03:17 +0000 (UTC) Received: from marcos.anarc.at (mail.orangeseeds.org [72.0.72.144]) by mx1.freebsd.org (Postfix) with ESMTP id 1C9A0A0F for ; Tue, 27 Jan 2015 23:03:16 +0000 (UTC) Received: by marcos.anarc.at (Postfix, from userid 1000) id 1590D1A006E; Tue, 27 Jan 2015 18:02:46 -0500 (EST) From: Antoine =?utf-8?Q?Beaupr=C3=A9?= To: Luigi Rizzo Subject: Re: is polling still a thing? In-Reply-To: <20150127223917.GA21883@onelab2.iet.unipi.it> References: <871tmgceup.fsf@marcos.anarc.at> <1422384769.867067950.y2iiuu53@frv34.fwdcdn.com> <87pp9zc1wk.fsf@marcos.anarc.at> <20150127223917.GA21883@onelab2.iet.unipi.it> User-Agent: Notmuch/0.18.2 (http://notmuchmail.org) Emacs/24.4.1 (x86_64-pc-linux-gnu) Date: Tue, 27 Jan 2015 18:02:46 -0500 Message-ID: <87h9vbbze1.fsf@marcos.anarc.at> MIME-Version: 1.0 Content-Type: text/plain Cc: freebsd-net@freebsd.org, wishmaster X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 23:03:17 -0000 On 2015-01-27 17:39:17, Luigi Rizzo wrote: > On Tue, Jan 27, 2015 at 05:08:27PM -0500, Antoine Beaupr? wrote: >> On 2015-01-27 13:57:20, wishmaster wrote: >> > Have you consider to use netmap-based ipfw instead pf in DDoS mitigation? I think you should. And without any network ''haks'' like polling. >> >> My understanding of netmap was that it wasn't useful for packet >> forwarding, because its design is for transmitting packets directly to >> userland faster, whereas routers dataflow stay mostly in the router... > > i think the suggestion was to have let netmap-ipfw > drop the traffic you don't want to deal with, and then > inject the remaining ones into the kernel where > the processing occurs -- possibly even using pf or > a different firewall > > There are people using netmap-ipfw on external physical > boxes exactly in this way -- as a "bump in the wire", > but it is trivial to run it on the same machine. hmmm... i *was* using pf to drop a significant amount of the traffic, I am not sure I understand how using netmap/ipfw would help here. my understanding of the problem, at this stage, is not so much pf processing the packets as the kernel having trouble extracting the packets from the NIC fast enough. but my analysis may be incorrect. A. -- Travail, du latin Tri Palium trois pieux, instrument de torture. From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 23:27:25 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 16985295 for ; Tue, 27 Jan 2015 23:27:25 +0000 (UTC) Received: from onelab2.iet.unipi.it (onelab2.iet.unipi.it [131.114.59.238]) by mx1.freebsd.org (Postfix) with ESMTP id CBACCC50 for ; Tue, 27 Jan 2015 23:27:24 +0000 (UTC) Received: by onelab2.iet.unipi.it (Postfix, from userid 275) id D321F7300A; Wed, 28 Jan 2015 00:32:40 +0100 (CET) Date: Wed, 28 Jan 2015 00:32:40 +0100 From: Luigi Rizzo To: Antoine Beaupr? Subject: Re: is polling still a thing? Message-ID: <20150127233240.GA22364@onelab2.iet.unipi.it> References: <871tmgceup.fsf@marcos.anarc.at> <1422384769.867067950.y2iiuu53@frv34.fwdcdn.com> <87pp9zc1wk.fsf@marcos.anarc.at> <20150127223917.GA21883@onelab2.iet.unipi.it> <87h9vbbze1.fsf@marcos.anarc.at> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <87h9vbbze1.fsf@marcos.anarc.at> User-Agent: Mutt/1.5.20 (2009-06-14) Cc: freebsd-net@freebsd.org, wishmaster X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 23:27:25 -0000 On Tue, Jan 27, 2015 at 06:02:46PM -0500, Antoine Beaupr? wrote: > On 2015-01-27 17:39:17, Luigi Rizzo wrote: > > On Tue, Jan 27, 2015 at 05:08:27PM -0500, Antoine Beaupr? wrote: > >> On 2015-01-27 13:57:20, wishmaster wrote: > >> > Have you consider to use netmap-based ipfw instead pf in DDoS mitigation? I think you should. And without any network ''haks'' like polling. > >> > >> My understanding of netmap was that it wasn't useful for packet > >> forwarding, because its design is for transmitting packets directly to > >> userland faster, whereas routers dataflow stay mostly in the router... > > > > i think the suggestion was to have let netmap-ipfw > > drop the traffic you don't want to deal with, and then > > inject the remaining ones into the kernel where > > the processing occurs -- possibly even using pf or > > a different firewall > > > > There are people using netmap-ipfw on external physical > > boxes exactly in this way -- as a "bump in the wire", > > but it is trivial to run it on the same machine. > > hmmm... i *was* using pf to drop a significant amount of the traffic, I > am not sure I understand how using netmap/ipfw would help here. > > my understanding of the problem, at this stage, is not so much pf > processing the packets as the kernel having trouble extracting the > packets from the NIC fast enough. The arrangement is as in the picture below (use a fixed size font). +------------------+ | netmap-ipfw | +-[HHH-------[HHH]-+ HHH H HHH H +-----[HHH]------[HHH]-----------------------+ | HHH H +-----------+ | | HHH H | host | | | HHH o=======| network | | | +--[HHH]--+ | stack | | | | netmap | +-----------+ | | | enabled | | | | NIC | | +--+---------+-------------------------------+ A netmap-aware NIC has no problem dealing with high PPS rates, deliver them through the fat pipe HHH to netmap-ipfw in userspace, which does the filtering and drops the junk. The remaining part is reinjected through another netmap port into the host stack, which is the actual bottleneck. Presumably at this point the amount of residual traffic is sustainable by the kernel. netmap-ipfw is simmetric so it supports traffic in the other direction too. another host netmap port. Presumably at thi cheers luigi From owner-freebsd-net@FreeBSD.ORG Tue Jan 27 23:38:18 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 3A7AC525 for ; Tue, 27 Jan 2015 23:38:18 +0000 (UTC) Received: from mail-oi0-f42.google.com (mail-oi0-f42.google.com [209.85.218.42]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id F193AD3F for ; Tue, 27 Jan 2015 23:38:17 +0000 (UTC) Received: by mail-oi0-f42.google.com with SMTP id i138so14967080oig.1 for ; Tue, 27 Jan 2015 15:38:11 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:content-type:mime-version:subject:from :in-reply-to:date:cc:message-id:references:to; bh=BEAYc7JPF23sGEHKBeJ0nibwraz1ddBiEvjKzhfal5o=; b=UlYe/4OMyIkvobRqy4vOG5FSxfCN4Tx4rk9fMZQ1n/zF4kOqHGjWNa/fCF1ckdIsht 5cCvTb9uaDCcttjL55GfGkvKYzGxaVX3ETeCR5/zdANUIWkwEHxIdSR5BrwXf0xjoENH 3vWaDJeGDD2CUi2fBYCLdbXf1wlnxqpj65DZJGLICVqCIotX3ZFR48+4PsTzPBluSCmw 3otGSsLvPLkhIGGcbvclLXdwyJ9Ok9+s/lS9Te5YY+xoehc62inUPdXDf3XFkvrunN2/ yXqKLu1DWEqLvCaqALyu6DvPs3ygYXxB4oPL0ATj61kRqwZIlyXAGZ+hxCeIiRCqSIsQ E00w== X-Gm-Message-State: ALoCoQmwkEax5kHFkC7u7kHQrWjbgqQfIw542QFXLz+ICoOK7NuVLeFP6C/tKPQUrd2YEuMGX16u X-Received: by 10.202.68.6 with SMTP id r6mr269186oia.69.1422401891715; Tue, 27 Jan 2015 15:38:11 -0800 (PST) Received: from ?IPv6:2610:160:11:33:956e:9562:4694:6bbf? ([2610:160:11:33:956e:9562:4694:6bbf]) by mx.google.com with ESMTPSA id cr2sm1377160oec.15.2015.01.27.15.38.11 (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Tue, 27 Jan 2015 15:38:11 -0800 (PST) Mime-Version: 1.0 (Mac OS X Mail 8.2 \(2070.1\)) Subject: Re: is polling still a thing? From: Jim Thompson In-Reply-To: <87pp9zc1wk.fsf@marcos.anarc.at> Date: Tue, 27 Jan 2015 17:38:11 -0600 Message-Id: <6BB47230-9AB8-4F0B-843B-7C51330F8306@netgate.com> References: <871tmgceup.fsf@marcos.anarc.at> <1422384769.867067950.y2iiuu53@frv34.fwdcdn.com> <87pp9zc1wk.fsf@marcos.anarc.at> To: =?utf-8?Q?Antoine_Beaupr=C3=A9?= X-Mailer: Apple Mail (2.2070.1) Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: freebsd-net@freebsd.org, wishmaster X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Jan 2015 23:38:18 -0000 > On Jan 27, 2015, at 4:08 PM, Antoine Beaupr=C3=A9 = wrote: >=20 > On 2015-01-27 13:57:20, wishmaster wrote: >> Have you consider to use netmap-based ipfw instead pf in DDoS = mitigation? I think you should. And without any network ''haks'' like = polling. >=20 > My understanding of netmap was that it wasn't useful for packet > forwarding, because its design is for transmitting packets directly to > userland faster, whereas routers dataflow stay mostly in the router=E2=80= =A6 the problem is that the =E2=80=9Cdata flow=E2=80=9D in freebsd isn=E2=80=99= t very fast. (I=E2=80=99d go so far to say, =E2=80=9Cbroken=E2=80=9D, = but that=E2=80=99s throwing rocks.) But as long as the window is already broken: the rtentry locking is a good example of how the stack is broken. the lack of FIB caching is another issue and the packet-at-a-time-to-completion is another. (no batching) So =E2=80=99N=E2=80=99 packets worth of address lookups, (ACLs, =E2=80=A6,= etc) at a time. Just like =E2=80=9CClick=E2=80=9D showed a decade ago = (and where the polling mode was of use). But it=E2=80=99s trivial to build a packet forwarder (more L2 than L3, = but all things are possible) using netmap (or dpdk) that smacks the = freebsd (and linux) stacks with a large stick. The netmap code comes with a =E2=80=9Cbridge.c=E2=80=9D example that is = just that, a dead-simple bridge. Another example, =E2=80=9Cnetmap-fwd=E2=80= =9D runs at 14.88Mpps between two 10Gbps interfaces. (Neither pf or the kernel-resident ipfw will come close, both are more = than an order of magnitude slower.) Here=E2=80=99s something a bit more than =E2=80=9Cdead simple=E2=80=9D: = https://github.com/caladri/brilter This would be even faster if Juli would use one of the Lua JITs, e.g.: = http://wingolog.org/archives/2014/09/02/high-performance-packet-filtering-= with-pflua And if you want to go =E2=80=98full tilt=E2=80=99, Click runs on top of = netmap since 2012: https://github.com/kohler/click/commits/netmap = (the code is in the = master branch, too. use master.) As for the netmap-ipfw code, it=E2=80=99s 6.5Mpps to 10Mpps (later = editions of the code: = http://freebsd.1045724.n5.nabble.com/ipfw-meets-netmap-6-5-Mpps-in-userspa= ce-td5734014.html = > I'm hesitant in switching back to ipfw, considering how nice the > featureset and syntax of pf is. But if that's what's needed to restore > sanity=E2=80=A6 pf is sane? No, I don=E2=80=99t think so. (yes, it does say =E2=80=9Cpf=E2=80=9D at the front of =E2=80=9CpfSense=E2= =80=9D. so what? I mean, have you looked at the code?) Turn off polling, unless you know you need it. You=E2=80=99ll know you = =E2=80=98need it=E2=80=9D if you start making changes to the stack. There is a lot of =E2=80=9Cmystery meat=E2=80=9D in most fields, and the = field of computers / operating systems contains it=E2=80=99s share. As a somewhat associated example, Intel says, "hyperthreading helps = (networking) performance!=E2=80=9D 6wind says this too. freebsd = developers say, "hyperthreading hurts performance=E2=80=9D. In the end, it depends what is stalling the CPU. Hyper-threading is a = trick to share the write pipes on the core, and traditional = implementations of memcpy() will fill these pipes (call them buffers if = you like.) And the stack does a lot of =E2=80=9Cmemcpy()=E2=80=9D (I=E2=80=99m = waiting for the yowls of =E2=80=9Cwe zero-copy!=E2=80=9D, because anyone = who asserts this just hasn=E2=80=99t looked at the stack.) There are = tricks (if your code is interleaving access to the write pipes well, = you=E2=80=99ll see more benefit. This really wants cache-aligned data = structures, etc.) So, that=E2=80=99s just a long-winded =E2=80=9CYMMV=E2=80=9D. Jim From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 00:14:30 2015 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id DC39E13D for ; Wed, 28 Jan 2015 00:14:30 +0000 (UTC) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id C3792160 for ; Wed, 28 Jan 2015 00:14:30 +0000 (UTC) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S0EUU1056209 for ; Wed, 28 Jan 2015 00:14:30 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 188897] [dc] dc ethernet driver seems to prevent the detection of other NIC chipsets Date: Wed, 28 Jan 2015 00:14:30 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.0-RELEASE X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: clif@eugeneweb.com X-Bugzilla-Status: In Progress X-Bugzilla-Priority: Normal X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 00:14:30 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=188897 --- Comment #9 from clif@eugeneweb.com --- Greetings, I just tried the hint.agp.0.disabled=1 again, and not surprisingly, I got the same results as before. Though I had also forgten what those where. ;-) to wit: Yes it does bring back the re0 interface, but the dc ports fail in exactly the same way as I described above. ie, about two of them work, sometimes only one. The patch seems to have fixed just the mac addresses and the link active sensing, and even though these work for all ports some (most?) ports still fail to get a dhcp lease. The bottom line is I can't use this as a workaround, sorry. At least it seems like you have a good understanding of the problem, too bad it's so hard to fix. Clif -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 00:17:18 2015 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 0022B235 for ; Wed, 28 Jan 2015 00:17:17 +0000 (UTC) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id DB94718C for ; Wed, 28 Jan 2015 00:17:17 +0000 (UTC) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S0HH3E057379 for ; Wed, 28 Jan 2015 00:17:17 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 194314] [ixgbe] driver makes some dangerous assumptions with struct mbuf sizing with IXGBE_RX_COPY_LEN Date: Wed, 28 Jan 2015 00:17:18 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 11.0-CURRENT X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Many People X-Bugzilla-Who: ricera10@gmail.com X-Bugzilla-Status: New X-Bugzilla-Priority: Normal X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 00:17:18 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=194314 --- Comment #13 from Eric Joyner --- Has this error gone away with the code change, or did something else happen? -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 00:29:19 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 05D6C54C for ; Wed, 28 Jan 2015 00:29:19 +0000 (UTC) Received: from marcos.anarc.at (mail.orangeseeds.org [72.0.72.144]) by mx1.freebsd.org (Postfix) with ESMTP id 9865A2B1 for ; Wed, 28 Jan 2015 00:29:18 +0000 (UTC) Received: by marcos.anarc.at (Postfix, from userid 1000) id 224791A0070; Tue, 27 Jan 2015 19:29:14 -0500 (EST) From: Antoine =?utf-8?Q?Beaupr=C3=A9?= To: Luigi Rizzo Subject: Re: is polling still a thing? In-Reply-To: <20150127233240.GA22364@onelab2.iet.unipi.it> References: <871tmgceup.fsf@marcos.anarc.at> <1422384769.867067950.y2iiuu53@frv34.fwdcdn.com> <87pp9zc1wk.fsf@marcos.anarc.at> <20150127223917.GA21883@onelab2.iet.unipi.it> <87h9vbbze1.fsf@marcos.anarc.at> <20150127233240.GA22364@onelab2.iet.unipi.it> User-Agent: Notmuch/0.18.2 (http://notmuchmail.org) Emacs/24.4.1 (x86_64-pc-linux-gnu) Date: Tue, 27 Jan 2015 19:29:14 -0500 Message-ID: <87bnljbvdx.fsf@marcos.anarc.at> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Cc: freebsd-net@freebsd.org, wishmaster X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 00:29:19 -0000 On 2015-01-27 18:32:40, Luigi Rizzo wrote: > A netmap-aware NIC has no problem dealing with high PPS rates, > deliver them through the fat pipe HHH to netmap-ipfw in userspace, > which does the filtering and drops the junk. The remaining part > is reinjected through another netmap port into the host stack, > which is the actual bottleneck. Presumably at this point the amount > of residual traffic is sustainable by the kernel. netmap-ipfw is > simmetric so it supports traffic in the other direction too. > another host netmap port. Presumably at thi [trimmed?] uh! so that's pretty amazing. :) is there some tutorial that's available for this somewhere? i looked briefly at the netmap-ipfw README, and couldn't quite figure it out. thanks! a. --=20 Au nom de l'=C3=A9tat, la force s'appelle droit. Au main de l'individu, elle s'appelle crime. - Max Stirner From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 00:42:25 2015 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id DA8D688A for ; Wed, 28 Jan 2015 00:42:25 +0000 (UTC) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id C1D79636 for ; Wed, 28 Jan 2015 00:42:25 +0000 (UTC) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S0gPjh012198 for ; Wed, 28 Jan 2015 00:42:25 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 194314] [ixgbe] driver makes some dangerous assumptions with struct mbuf sizing with IXGBE_RX_COPY_LEN Date: Wed, 28 Jan 2015 00:42:26 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 11.0-CURRENT X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Many People X-Bugzilla-Who: ngie@FreeBSD.org X-Bugzilla-Status: New X-Bugzilla-Priority: Normal X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 00:42:25 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=194314 --- Comment #14 from Garrett Cooper,425-314-3911 --- (In reply to Eric Joyner from comment #13) I haven't tested the change yet, but thanks for the reminder (I'll verify it this week). If it works, do I have Intel's blessing for committing the fix, or should jfv do the commit? -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 00:49:20 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 62B1DA83 for ; Wed, 28 Jan 2015 00:49:20 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 44B2467C for ; Wed, 28 Jan 2015 00:49:20 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S0nJkM038193 for ; Wed, 28 Jan 2015 00:49:19 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S0nJ8R038192; Wed, 28 Jan 2015 00:49:19 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 00:49:19 +0000 To: freebsd-net@freebsd.org From: "rstone (Ryan Stone)" Subject: [Differential] [Updated, 227 lines] D1641: Implement PCI SR-IOV initialization methods Message-ID: <2f573b157042c65f163146abe4a4e72a@localhost.localdomain> X-Priority: 3 Thread-Topic: D1641: Implement PCI SR-IOV initialization methods X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: ZWFiODdhYWU0YTRhNWFiMzk2YmRlMzA0YTZlIFTIMg8= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 00:49:20 -0000 rstone updated this revision to Diff 3461. rstone added a comment. Undo ifx/vsi split CHANGES SINCE LAST UPDATE https://reviews.freebsd.org/D1641?vs=3394&id=3461 BRANCH review_D1641 REVISION DETAIL https://reviews.freebsd.org/D1641 AFFECTED FILES sys/dev/ixl/if_ixl.c sys/dev/ixl/ixl.h sys/dev/ixl/ixl_pf.h To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 00:50:03 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 47AA5B23 for ; Wed, 28 Jan 2015 00:50:03 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 21BC268D for ; Wed, 28 Jan 2015 00:50:03 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S0o2RV038867 for ; Wed, 28 Jan 2015 00:50:02 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S0o24E038866; Wed, 28 Jan 2015 00:50:02 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 00:50:02 +0000 To: freebsd-net@freebsd.org From: "rstone (Ryan Stone)" Subject: [Differential] [Updated, 161 lines] D1652: Add support for ADD/DEL_ETHER_ADDRESS VC messages Message-ID: <72b6bca7a43064ec380973bbae0051d6@localhost.localdomain> X-Priority: 3 Thread-Topic: D1652: Add support for ADD/DEL_ETHER_ADDRESS VC messages X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: MzM5Y2U0ZjQwMTJmYWViOTFkMDMyZmM4NGIzIFTIMjo= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 00:50:03 -0000 rstone updated this revision to Diff 3462. rstone added a comment. Revert vsi/ifx split CHANGES SINCE LAST UPDATE https://reviews.freebsd.org/D1652?vs=3405&id=3462 BRANCH review_D1652 REVISION DETAIL https://reviews.freebsd.org/D1652 AFFECTED FILES sys/dev/ixl/if_ixl.c sys/dev/ixl/ixl.h sys/dev/ixl/ixl_pf.h To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 00:50:49 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 201F1BBA for ; Wed, 28 Jan 2015 00:50:49 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 02F1C781 for ; Wed, 28 Jan 2015 00:50:49 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S0omJn040243 for ; Wed, 28 Jan 2015 00:50:48 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S0omFw040242; Wed, 28 Jan 2015 00:50:48 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 00:50:48 +0000 To: freebsd-net@freebsd.org From: "rstone (Ryan Stone)" Subject: [Differential] [Updated, 36 lines] D1657: Allow VFs to run while the PF is admin down Message-ID: X-Priority: 3 Thread-Topic: D1657: Allow VFs to run while the PF is admin down X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2EyNmJlZTU5MWYxMjQxNTNiNmRlMzQzYjQxIFTIMmg= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 00:50:49 -0000 rstone updated this revision to Diff 3463. rstone added a comment. Revert ifx/vsi split CHANGES SINCE LAST UPDATE https://reviews.freebsd.org/D1657?vs=3410&id=3463 BRANCH review_D1657 REVISION DETAIL https://reviews.freebsd.org/D1657 AFFECTED FILES sys/dev/ixl/if_ixl.c To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 00:54:00 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id B54C6CA7 for ; Wed, 28 Jan 2015 00:54:00 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 9839A7BC for ; Wed, 28 Jan 2015 00:54:00 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S0s0Bt044468 for ; Wed, 28 Jan 2015 00:54:00 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S0s0ia044465; Wed, 28 Jan 2015 00:54:00 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 00:54:00 +0000 To: freebsd-net@freebsd.org From: "rstone (Ryan Stone)" Subject: [Differential] [Updated, 34 lines] D1658: Add sysctls for per-VF hardware counters Message-ID: <74da713b9a478b64dc40e551d0dae277@localhost.localdomain> X-Priority: 3 Thread-Topic: D1658: Add sysctls for per-VF hardware counters X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: OWE0YzQwMmZkYjZmN2FjNjA4MWQ1MGYxZmY1IFTIMyg= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 00:54:00 -0000 rstone updated this revision to Diff 3464. rstone added a comment. Revert ifx/vsi split CHANGES SINCE LAST UPDATE https://reviews.freebsd.org/D1658?vs=3411&id=3464 BRANCH review_D1658 REVISION DETAIL https://reviews.freebsd.org/D1658 AFFECTED FILES sys/dev/ixl/if_ixl.c sys/dev/ixl/ixl_pf.h To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 00:55:06 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 5BD8ED4A for ; Wed, 28 Jan 2015 00:55:06 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 3EDAF7CF for ; Wed, 28 Jan 2015 00:55:06 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S0t5ZP045346 for ; Wed, 28 Jan 2015 00:55:05 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S0t5Vb045345; Wed, 28 Jan 2015 00:55:05 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 00:55:05 +0000 To: freebsd-net@freebsd.org From: "rstone (Ryan Stone)" Subject: [Differential] [Updated, 41 lines] D1655: Add support for GET_STATS VC message Message-ID: X-Priority: 3 Thread-Topic: D1655: Add support for GET_STATS VC message X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: M2VlZmI5Nzk5ZGE5MDQ2YzE4OWMyZjdiMDU1IFTIM2k= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 00:55:06 -0000 rstone updated this revision to Diff 3465. rstone added a comment. revert ifx/vsi split CHANGES SINCE LAST UPDATE https://reviews.freebsd.org/D1655?vs=3408&id=3465 BRANCH review_D1655 REVISION DETAIL https://reviews.freebsd.org/D1655 AFFECTED FILES sys/dev/ixl/if_ixl.c To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 00:56:01 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id C0009DE2 for ; Wed, 28 Jan 2015 00:56:01 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id A25757DF for ; Wed, 28 Jan 2015 00:56:01 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S0u1b4046291 for ; Wed, 28 Jan 2015 00:56:01 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S0u1u0046290; Wed, 28 Jan 2015 00:56:01 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 00:56:01 +0000 To: freebsd-net@freebsd.org From: "rstone (Ryan Stone)" Subject: [Differential] [Updated, 118 lines] D1642: Implement PCI SR-IOV method to initialize individual VFs Message-ID: <92d36ed37dec496a3f811081721735ce@localhost.localdomain> X-Priority: 3 Thread-Topic: D1642: Implement PCI SR-IOV method to initialize individual VFs X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: ZmZlNzY0OTVkYmNlM2JkOWFhZWQ3MjBhMjA1IFTIM6E= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 00:56:01 -0000 rstone updated this revision to Diff 3466. rstone added a comment. revert ifx/vsi split CHANGES SINCE LAST UPDATE https://reviews.freebsd.org/D1642?vs=3395&id=3466 BRANCH review_D1642 REVISION DETAIL https://reviews.freebsd.org/D1642 AFFECTED FILES sys/dev/ixl/if_ixl.c sys/dev/ixl/ixl.h sys/dev/ixl/ixl_pf.h sys/dev/ixl/ixlv.h To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 00:57:06 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 90CE0EBD for ; Wed, 28 Jan 2015 00:57:06 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 732257EF for ; Wed, 28 Jan 2015 00:57:06 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S0v6vK046950 for ; Wed, 28 Jan 2015 00:57:06 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S0v6WZ046949; Wed, 28 Jan 2015 00:57:06 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 00:57:06 +0000 To: freebsd-net@freebsd.org From: "rstone (Ryan Stone)" Subject: [Differential] [Updated, 36 lines] D1657: Allow VFs to run while the PF is admin down Message-ID: <027382d581fce8cbb0718419ae922a5e@localhost.localdomain> X-Priority: 3 Thread-Topic: D1657: Allow VFs to run while the PF is admin down X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2EyNmJlZTU5MWYxMjQxNTNiNmRlMzQzYjQxIFTIM+I= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 00:57:06 -0000 rstone updated this revision to Diff 3467. rstone added a comment. Missed part of the ifx/vsi split CHANGES SINCE LAST UPDATE https://reviews.freebsd.org/D1657?vs=3463&id=3467 BRANCH review_D1657 REVISION DETAIL https://reviews.freebsd.org/D1657 AFFECTED FILES sys/dev/ixl/if_ixl.c To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 01:15:09 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 50461863 for ; Wed, 28 Jan 2015 01:15:09 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 325E99F4 for ; Wed, 28 Jan 2015 01:15:09 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S1F8GC067095 for ; Wed, 28 Jan 2015 01:15:08 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S1F8jx067094; Wed, 28 Jan 2015 01:15:08 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 01:15:08 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1640: Refactor network stack state separate from VSI state Message-ID: <4771d5f6012773a29d7ff70c2f0a34c9@localhost.localdomain> X-Priority: 3 Thread-Topic: D1640: Refactor network stack state separate from VSI state X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: N2JmNDRjOWRkY2RlYmQ2NjRjZDUxYzYxNjBmIFTIOBw= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 01:15:09 -0000 jfvogel accepted this revision. jfvogel added a comment. This revision is now accepted and ready to land. Thanks Ryan, am happier with this. BRANCH review_D1640 REVISION DETAIL https://reviews.freebsd.org/D1640 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 01:38:56 2015 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 2E582D9D for ; Wed, 28 Jan 2015 01:38:56 +0000 (UTC) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 16608C14 for ; Wed, 28 Jan 2015 01:38:56 +0000 (UTC) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S1ctB3086201 for ; Wed, 28 Jan 2015 01:38:55 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 194234] [ixgbe] Update ixgbe to 2.5.27 Date: Wed, 28 Jan 2015 01:38:55 +0000 X-Bugzilla-Reason: CC AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 11.0-CURRENT X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: ricera10@gmail.com X-Bugzilla-Status: Closed X-Bugzilla-Priority: Normal X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: bug_status resolution Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 01:38:56 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=194234 Eric Joyner changed: What |Removed |Added ---------------------------------------------------------------------------- Status|New |Closed Resolution|--- |Overcome By Events --- Comment #8 from Eric Joyner --- A newer patch to update ixgbe (that obsoletes this one) has been posted in phabricator: https://reviews.freebsd.org/D1580 -- You are receiving this mail because: You are on the CC list for the bug. You are the assignee for the bug. From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 07:20:48 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 166D3ABC for ; Wed, 28 Jan 2015 07:20:48 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id EED2D68E for ; Wed, 28 Jan 2015 07:20:47 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S7KlJX079548 for ; Wed, 28 Jan 2015 07:20:47 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S7KlmE079547; Wed, 28 Jan 2015 07:20:47 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 07:20:47 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Request, 195 lines] D1691: sfxge: using 64-bit access for x86-64 Message-ID: X-Priority: 3 Thread-Topic: D1691: sfxge: using 64-bit access for x86-64 X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: Y2Y0Y2ViOWM0MzVmZDk3ZmY2NmFhNTJmMTY1 X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 07:20:48 -0000 arybchik created this revision. arybchik added a reviewer: gnn. arybchik added a subscriber: freebsd-net. arybchik set the repository for this revision to rS (FreeBSD src repository). REVISION SUMMARY Submitted by: Artem V. Andreev Sponsored by: Solarflare Communications, Inc. REVISION DETAIL https://reviews.freebsd.org/D1691 AFFECTED FILES sys/dev/sfxge/common/efsys.h To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 07:26:39 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 83032D0E for ; Wed, 28 Jan 2015 07:26:39 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 65CB87B7 for ; Wed, 28 Jan 2015 07:26:39 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S7QdT8085135 for ; Wed, 28 Jan 2015 07:26:39 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S7QdAr085134; Wed, 28 Jan 2015 07:26:39 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 07:26:39 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Request, 12 lines] D1692: sfxge: Change sfxge_ev_qpoll() proto to avoid EVQ pointers array access Message-ID: X-Priority: 3 Thread-Topic: D1692: sfxge: Change sfxge_ev_qpoll() proto to avoid EVQ pointers array access X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: M2JhMDFjOGZmMjEwY2M2YjkyOWY2NzZhZTVl X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 07:26:39 -0000 arybchik created this revision. arybchik added a reviewer: gnn. arybchik added a subscriber: freebsd-net. arybchik set the repository for this revision to rS (FreeBSD src repository). REVISION SUMMARY It was the only place on data path where sc->evq array is accessed. Sponsored by: Solarflare Communications, Inc. TEST PLAN L1D_REPLACEMENT events are measured using pmcstat under high traffic load (many streams). The patch decreases number of events. REVISION DETAIL https://reviews.freebsd.org/D1692 AFFECTED FILES sys/dev/sfxge/sfxge.h sys/dev/sfxge/sfxge_ev.c sys/dev/sfxge/sfxge_intr.c To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 08:00:25 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 26CF98CF for ; Wed, 28 Jan 2015 08:00:25 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 0476BACE for ; Wed, 28 Jan 2015 08:00:25 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S80Ot7086498 for ; Wed, 28 Jan 2015 08:00:24 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S80OrV086497; Wed, 28 Jan 2015 08:00:24 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 08:00:24 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Request, 2 lines] D1694: sfxge: Move txq->next pointer to part writable on completion path Message-ID: X-Priority: 3 Thread-Topic: D1694: sfxge: Move txq->next pointer to part writable on completion path X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: YTIzODBmY2JlMjNhMDRmNDFmNmQzOTU2NTVk X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 08:00:25 -0000 arybchik created this revision. arybchik added a reviewer: gnn. arybchik added a subscriber: freebsd-net. REVISION SUMMARY In fact the pointer is used only if more than one TXQ is processed in one interrupt. It is used (read-write) on completion path only. Also it makes the first part of the structure smaller and it fits now into one 128byte cache line. So, TXQ structure becomes 128 bytes smaller. Sponsored by: Solarflare Communications, Inc. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1694 AFFECTED FILES sys/dev/sfxge/sfxge_tx.h To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 08:14:25 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 76678C53 for ; Wed, 28 Jan 2015 08:14:25 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 59235C8F for ; Wed, 28 Jan 2015 08:14:25 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S8EP2N001965 for ; Wed, 28 Jan 2015 08:14:25 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S8EPI1001964; Wed, 28 Jan 2015 08:14:25 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 08:14:25 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Request, 35 lines] D1697: sfxge: Expect required init_state on data path and in periodic calls Message-ID: X-Priority: 3 Thread-Topic: D1697: sfxge: Expect required init_state on data path and in periodic calls X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: MTVmZWRhZmFiZTk2YzBiOTY0NjE3OTVjNDBk X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 08:14:25 -0000 arybchik created this revision. arybchik added a reviewer: gnn. arybchik added a subscriber: freebsd-net. REVISION SUMMARY Sponsored by: Solarflare Communications, Inc. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1697 AFFECTED FILES sys/dev/sfxge/sfxge_ev.c sys/dev/sfxge/sfxge_intr.c sys/dev/sfxge/sfxge_port.c sys/dev/sfxge/sfxge_rx.c sys/dev/sfxge/sfxge_tx.c To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 08:27:41 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id CC738DB0 for ; Wed, 28 Jan 2015 08:27:41 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id AFFBFD99 for ; Wed, 28 Jan 2015 08:27:41 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S8Rf3l014574 for ; Wed, 28 Jan 2015 08:27:41 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S8RfWA014573; Wed, 28 Jan 2015 08:27:41 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 08:27:41 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Request, 14 lines] D1698: sfxge: Make it possible to build without EVQ statistics Message-ID: X-Priority: 3 Thread-Topic: D1698: sfxge: Make it possible to build without EVQ statistics X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: N2FjZjRiMTcyNjhlNjBkNjJlNGQ0MjNmYTk1 X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 08:27:41 -0000 arybchik created this revision. arybchik added a reviewer: gnn. arybchik added a subscriber: freebsd-net. REVISION SUMMARY Sponsored by: Solarflare Communications, Inc. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1698 AFFECTED FILES sys/dev/sfxge/common/efx_ev.c sys/dev/sfxge/common/efx_tx.c sys/dev/sfxge/sfxge.h sys/dev/sfxge/sfxge_ev.c To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 08:31:22 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id B09E2AD for ; Wed, 28 Jan 2015 08:31:22 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 93BF9E4F for ; Wed, 28 Jan 2015 08:31:22 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S8VMB0019577 for ; Wed, 28 Jan 2015 08:31:22 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S8VMvu019576; Wed, 28 Jan 2015 08:31:22 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 08:31:22 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Request, 20 lines] D1699: sfxge: Remove extra cache-line alignment and reorder sfxge_evq_t Message-ID: X-Priority: 3 Thread-Topic: D1699: sfxge: Remove extra cache-line alignment and reorder sfxge_evq_t X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: NTEwZjA3ZGJmNDI3MWUzMTM4NTAyOTUxODg2 X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 08:31:22 -0000 arybchik created this revision. arybchik added a reviewer: gnn. arybchik added a subscriber: freebsd-net. REVISION SUMMARY Remove the first member alignment to cacheline since it is nop. Use __aligned() for the whole structure to make sure that the structure size is cacheline aligned. Remove lock alignment to make the structure smaller and fit all members used on event queue processing into one cacheline (128 bytes) on x86-64. The lock is obtained as well from different context when event queue statistics are retrived from sysctl context, but it is infrequent. Reorder members to avoid padding and go in usage order on event processing. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1699 AFFECTED FILES sys/dev/sfxge/sfxge.h To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 08:38:27 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id E61E141A for ; Wed, 28 Jan 2015 08:38:27 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id C981EEBE for ; Wed, 28 Jan 2015 08:38:27 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S8cRGi025400 for ; Wed, 28 Jan 2015 08:38:27 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S8cR5X025399; Wed, 28 Jan 2015 08:38:27 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 08:38:27 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Request, 16 lines] D1700: sfxge: fixed TSO code to cope with VLAN headers Message-ID: X-Priority: 3 Thread-Topic: D1700: sfxge: fixed TSO code to cope with VLAN headers X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: ZGMyYWRlNDljMGY2NDEzMjkzZjgzNGExNGM4 X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 08:38:28 -0000 arybchik created this revision. arybchik added a reviewer: gnn. arybchik added a subscriber: freebsd-net. REVISION SUMMARY Submitted by: Artem V. Andreev Sponsored by: Solarflare Communications, Inc. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1700 AFFECTED FILES sys/dev/sfxge/sfxge_tx.c To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 08:41:06 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id F32705C9 for ; Wed, 28 Jan 2015 08:41:06 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id D5013EE3 for ; Wed, 28 Jan 2015 08:41:06 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S8f6M9029408 for ; Wed, 28 Jan 2015 08:41:06 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S8f6w6029407; Wed, 28 Jan 2015 08:41:06 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 08:41:06 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Updated] D1692: sfxge: Change sfxge_ev_qpoll() proto to avoid EVQ pointers array access Message-ID: X-Priority: 3 Thread-Topic: D1692: sfxge: Change sfxge_ev_qpoll() proto to avoid EVQ pointers array access X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: M2JhMDFjOGZmMjEwY2M2YjkyOWY2NzZhZTVlIFTIoKI= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 08:41:07 -0000 arybchik set the repository for this revision to rS (FreeBSD src repository). REVISION DETAIL https://reviews.freebsd.org/D1692 To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 08:42:17 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 4394789D for ; Wed, 28 Jan 2015 08:42:17 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 257DEF8E for ; Wed, 28 Jan 2015 08:42:17 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S8gGkE031373 for ; Wed, 28 Jan 2015 08:42:16 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S8gGnr031372; Wed, 28 Jan 2015 08:42:16 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 08:42:16 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Request, 17 lines] D1701: sfxge: Add evq argument to sfxge_tx_qcomplete() Message-ID: X-Priority: 3 Thread-Topic: D1701: sfxge: Add evq argument to sfxge_tx_qcomplete() X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: ZmRkNjdiMWY1YTE1NTE2MDQzZDA3Y2U3MTM2 X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 08:42:17 -0000 arybchik created this revision. arybchik added a reviewer: gnn. arybchik added a subscriber: freebsd-net. REVISION SUMMARY It removes necessity to get evq pointer by its index in soft context. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1701 AFFECTED FILES sys/dev/sfxge/sfxge_ev.c sys/dev/sfxge/sfxge_tx.c sys/dev/sfxge/sfxge_tx.h To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 08:45:07 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 24A30A22 for ; Wed, 28 Jan 2015 08:45:07 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 08446FCA for ; Wed, 28 Jan 2015 08:45:07 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S8j6hK034225 for ; Wed, 28 Jan 2015 08:45:06 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S8j63v034224; Wed, 28 Jan 2015 08:45:06 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 08:45:06 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Request, 2 lines] D1702: sfxge: Do not bzero() DMA allocated memory once again Message-ID: X-Priority: 3 Thread-Topic: D1702: sfxge: Do not bzero() DMA allocated memory once again X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: NjMxMmJlOThhNGY4NzdkYmQzMTVhYzdmMTg2 X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 08:45:07 -0000 arybchik created this revision. arybchik added a reviewer: gnn. arybchik added a subscriber: freebsd-net. REVISION SUMMARY sfxge_dma_alloc() calls bus_dmamem_alloc() with BUS_DMA_ZERO flag, so allocated memory is already filled in by zeros BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1702 AFFECTED FILES sys/dev/sfxge/sfxge_port.c To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 08:48:38 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id B5A10C0F for ; Wed, 28 Jan 2015 08:48:38 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 9449B72 for ; Wed, 28 Jan 2015 08:48:38 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S8mbmZ036805 for ; Wed, 28 Jan 2015 08:48:37 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S8mbZJ036802; Wed, 28 Jan 2015 08:48:37 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 08:48:37 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Request, 1 lines] D1703: sfxge: Remove unused esm_size member of the efsys_mem_t structure Message-ID: X-Priority: 3 Thread-Topic: D1703: sfxge: Remove unused esm_size member of the efsys_mem_t structure X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: OWVkM2NjY2YxZDEzNDJlODFhNGI3MTJjMGJh X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 08:48:38 -0000 arybchik created this revision. arybchik added a reviewer: gnn. arybchik added a subscriber: freebsd-net. REVISION SUMMARY esm_size is not even initialized properly when memory is allocated. Sponsored by: Solarflare Communications, Inc. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1703 AFFECTED FILES sys/dev/sfxge/common/efsys.h To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 08:52:07 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id ACC01CDF for ; Wed, 28 Jan 2015 08:52:07 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 8ECE014E for ; Wed, 28 Jan 2015 08:52:07 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S8q72f042865 for ; Wed, 28 Jan 2015 08:52:07 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S8q7jB042864; Wed, 28 Jan 2015 08:52:07 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 08:52:07 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Request, 2 lines] D1704: sfxge: Pass correct address to free allocated memory in the case of load error Message-ID: X-Priority: 3 Thread-Topic: D1704: sfxge: Pass correct address to free allocated memory in the case of load error X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: YTAwZjJhNTVjYzUxYTk4MzVhNDlmMDRkNDA1 X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 08:52:07 -0000 arybchik created this revision. arybchik added a reviewer: gnn. arybchik added a subscriber: freebsd-net. REVISION SUMMARY Most likely is was just memory leak on the error handling path since typically efsys_mem_t is filled in by zeros on allocation. Sponsored by: Solarflare Communications, Inc. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1704 AFFECTED FILES sys/dev/sfxge/sfxge_dma.c To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 08:55:25 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 6E2B1D9E for ; Wed, 28 Jan 2015 08:55:25 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 51B5C16F for ; Wed, 28 Jan 2015 08:55:25 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S8tPfY045172 for ; Wed, 28 Jan 2015 08:55:25 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S8tPN0045171; Wed, 28 Jan 2015 08:55:25 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 08:55:25 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Request, 2 lines] D1705: sfxge: Use SFXGE_MODERATION to initialize event moderation Message-ID: X-Priority: 3 Thread-Topic: D1705: sfxge: Use SFXGE_MODERATION to initialize event moderation X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: ZjQyOTAwZTc1YjQ5ZTljNTMxYTVkMzE2ZDk4 X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 08:55:25 -0000 arybchik created this revision. arybchik added a reviewer: gnn. arybchik added a subscriber: freebsd-net. REVISION SUMMARY Sponsored by: Solarflare Communications, Inc. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1705 AFFECTED FILES sys/dev/sfxge/sfxge_ev.c To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 09:08:12 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 352162EB for ; Wed, 28 Jan 2015 09:08:12 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 15D9429B for ; Wed, 28 Jan 2015 09:08:12 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S98BDe079488 for ; Wed, 28 Jan 2015 09:08:11 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S98BDP079487; Wed, 28 Jan 2015 09:08:11 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 09:08:11 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Request, 15 lines] D1706: sfxge: implemented parameter to restrict RSS channels Message-ID: X-Priority: 3 Thread-Topic: D1706: sfxge: implemented parameter to restrict RSS channels X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: ZTZjNzc1NjJhMjcwMWI3YzZjZTkzMDg4ZDNl X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 09:08:12 -0000 arybchik created this revision. arybchik added a reviewer: gnn. arybchik added a subscriber: freebsd-net. REVISION SUMMARY Submitted by: Artem V. Andreev Sponsored by: Solarflare Communications, Inc. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1706 AFFECTED FILES share/man/man4/sfxge.4 sys/dev/sfxge/sfxge.c sys/dev/sfxge/sfxge.h sys/dev/sfxge/sfxge_intr.c To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 09:12:42 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 9566F511 for ; Wed, 28 Jan 2015 09:12:42 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 78A4738F for ; Wed, 28 Jan 2015 09:12:42 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S9CgEs091283 for ; Wed, 28 Jan 2015 09:12:42 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S9Cg0W091282; Wed, 28 Jan 2015 09:12:42 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 09:12:42 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Request, 30 lines] D1707: sfxge: access statistics buffers under port lock Message-ID: X-Priority: 3 Thread-Topic: D1707: sfxge: access statistics buffers under port lock X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: MmFkY2EyODhjMzI1YWNkNjhmYWJmNzczN2Qy X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 09:12:42 -0000 arybchik created this revision. arybchik added a reviewer: gnn. arybchik added a subscriber: freebsd-net. REVISION SUMMARY Allow access to statistics data not only from sysctl handlers. Submitted by: Boris Misenov Sponsored by: Solarflare Communications, Inc. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1707 AFFECTED FILES sys/dev/sfxge/sfxge_port.c To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 09:19:17 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id B311B600; Wed, 28 Jan 2015 09:19:17 +0000 (UTC) Received: from ms-10.1blu.de (ms-10.1blu.de [178.254.4.101]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 736663DC; Wed, 28 Jan 2015 09:19:14 +0000 (UTC) Received: from [89.204.139.95] (helo=c720-r276659) by ms-10.1blu.de with esmtpsa (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.76) (envelope-from ) id 1YGOmE-0000nU-4X; Wed, 28 Jan 2015 10:19:10 +0100 Date: Wed, 28 Jan 2015 10:19:07 +0100 From: Matthias Apitz To: "arybchik (Andrew Rybchenko)" Subject: Re: [Differential] [Request, 30 lines] D1707: sfxge: access statistics buffers under port lock Message-ID: <20150128091907.GA1912@c720-r276659> Reply-To: Matthias Apitz Mail-Followup-To: Matthias Apitz , "arybchik (Andrew Rybchenko)" , freebsd-net@freebsd.org References: MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: X-Operating-System: FreeBSD 11.0-CURRENT r269739 (i386) User-Agent: Mutt/1.5.23 (2014-03-12) X-Con-Id: 51246 X-Con-U: 0-guru X-Originating-IP: 89.204.139.95 Cc: freebsd-net@freebsd.org X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 09:19:17 -0000 El día Wednesday, January 28, 2015 a las 09:12:42AM +0000, arybchik (Andrew Rybchenko) escribió: > arybchik created this revision. > arybchik added a reviewer: gnn. > arybchik added a subscriber: freebsd-net. > > REVISION SUMMARY > Allow access to statistics data not only from sysctl handlers. > > Submitted by: Boris Misenov > Sponsored by: Solarflare Communications, Inc. > > BRANCH > /head > ... Hello, My I kindly opt to move such state message to another list, or create one for this purpose? This list, freebsd-net@, is more a discussion list as it says: About freebsd-net English (USA) Discussions of networking in general and TCP/IP source code in particular. Thanks in advance matthias -- Matthias Apitz, guru@unixarea.de, http://www.unixarea.de/ +49-170-4527211 1989-2014: The Wall was torn down so that we go to war together again. El Muro ha sido derribado para que nos unimos en ir a la guerra otra vez. Diese Grenze wurde aufgehoben damit wir gemeinsam wieder in den Krieg ziehen. From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 09:30:00 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 57D20942 for ; Wed, 28 Jan 2015 09:30:00 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 3AB536AB for ; Wed, 28 Jan 2015 09:30:00 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0S9Tx6h050733 for ; Wed, 28 Jan 2015 09:29:59 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0S9TxBg050732; Wed, 28 Jan 2015 09:29:59 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 09:29:59 +0000 To: freebsd-net@freebsd.org From: "arybchik (Andrew Rybchenko)" Subject: [Differential] [Request, 151 lines] D1708: sfxge: Separate software Tx queue limit for non-TCP traffic Message-ID: X-Priority: 3 Thread-Topic: D1708: sfxge: Separate software Tx queue limit for non-TCP traffic X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: YjIwYzkzODE4ZTFiNjc4ZjI3YjRiMDJhNWJj X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 09:30:00 -0000 arybchik created this revision. arybchik added a reviewer: gnn. arybchik added a subscriber: freebsd-net. REVISION SUMMARY Add separate software Tx queue limit for non-TCP traffic to make total limit higher and avoid local drops of TCP packets because of no backpressure. There is no point to make non-TCP limit high since without backpressure UDP stream easily overflows any sensible limit. Split early drops statistics since it is better to have separate counter for each drop reason to make it unabmiguous. Sponsored by: Solarflare Communications, Inc. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1708 AFFECTED FILES share/man/man4/sfxge.4 sys/dev/sfxge/sfxge_port.c sys/dev/sfxge/sfxge_tx.c sys/dev/sfxge/sfxge_tx.h To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 13:00:37 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 327BB5E4 for ; Wed, 28 Jan 2015 13:00:37 +0000 (UTC) Received: from dragon.rutgers.edu (dragon.rutgers.edu [128.6.4.3]) by mx1.freebsd.org (Postfix) with ESMTP id EB0BAE7B for ; Wed, 28 Jan 2015 13:00:36 +0000 (UTC) X-ExtScanner: Niversoft's Regex Matcher X-Virus-Scanned: by dragon-cgpav-clamav-v1.3b Received: by dragon.rutgers.edu (CommuniGate Pro PIPE 6.0.11) with PIPE id 118667108; Wed, 28 Jan 2015 08:00:30 -0500 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on spamfilter4.cs.rutgers.edu X-Spam-ASN: X-Spam-Status: No, score=-32.4 required=5.0 tests=ALL_TRUSTED, BAYES_00, RUMAILX, RUMAILX2,RUMAILX3 shortcircuit=no autolearn=disabled version=3.3.1 X-Spam-Relay-Country: X-Spam-Language: en X-Spam-Level: Received: from [47.16.180.189] (account wkatsak@dragon.rutgers.edu HELO [172.30.1.5]) by dragon.rutgers.edu (CommuniGate Pro SMTP 6.0.11) with ESMTPSA id 118667104 for freebsd-net@freebsd.org; Wed, 28 Jan 2015 08:00:18 -0500 Message-ID: <54C8DD61.9040307@cs.rutgers.edu> Date: Wed, 28 Jan 2015 08:00:17 -0500 From: William Katsak User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.3.0 MIME-Version: 1.0 To: freebsd-net@freebsd.org Subject: Jails, VIMAGE, and VLANs Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 13:00:37 -0000 Hello, I am having a very frustrating issue with VIMAGE jails using VLANs on 10.1-RELEASE. I posted this earlier to the FreeBSD forum, then realized that this is probably a better place. Let me tell you about my issue: If I set up my jails using a regular ethernet interface (em0), a bridge, and epairs, everything works beautifully. All networking works as expected. However, if I try to do the exact same thing using a VLAN interface, everything ALMOST works, except for one thing: I cannot communicate between the host and the jail. I can ping in both directions, but nothing else. No TCP traffic seems to pass. To make it weirder, the jail can communicate perfectly with other machines on the VLAN, so the bridge itself seems to be (partially) working. I've checked routing tables, firewalls, everything. Nothing seems to make sense, except that something is broken either inside the bridge or the VIMAGE code. Again, if I keep the config exactly the same, but use em0 instead of em0.100, everything works. Does anyone have any ideas? Thanks in advance. -Bill -------------------------------------------------- Here is the offending bridge config: bridge1: flags=8843 metric 0 mtu 1500 ether 02:f1:2d:eb:f9:01 nd6 options=1 id 00:00:00:00:00:00 priority 32768 hellotime 2 fwddelay 15 maxage 20 holdcnt 6 proto rstp maxaddr 2000 timeout 1200 root id 00:00:00:00:00:00 priority 32768 ifcost 0 port 0 member: epair5a flags=143 ifmaxaddr 0 port 13 priority 128 path cost 2000 member: epair4a flags=143 ifmaxaddr 0 port 12 priority 128 path cost 2000 member: em0.100 flags=143 ifmaxaddr 0 port 4 priority 128 path cost 20000 -- **************************************** William Katsak Ph.D. Student Rutgers University Department of Computer Science **************************************** From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 17:07:20 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id ACAE216B for ; Wed, 28 Jan 2015 17:07:20 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 8A6F6E39 for ; Wed, 28 Jan 2015 17:07:20 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SH7K7d081075 for ; Wed, 28 Jan 2015 17:07:20 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SH7Kcp081074; Wed, 28 Jan 2015 17:07:20 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 17:07:20 +0000 To: freebsd-net@freebsd.org From: "rrs (Randall Stewart)" Subject: [Differential] [Request, 895 lines] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlk X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 17:07:20 -0000 rrs created this revision. rrs added reviewers: gnn, rwatson, imp, hselasky, adrian, sbruno, lstewart. rrs added a subscriber: freebsd-net. REVISION SUMMARY The callout code had two specific bugs within it after the new CPU migration feature was added. 1) The callout_active() call at times could lie to the KPI user, this is because during a migration the ACTIVE flag would have been removed so that the semantics were broken. This could cause problems for KPI users since the active flag is a key feature used by those declaring themselves MPSAFE and using there own lock (think TCP). 2) There was a bug in the callout code where if a migration was going on and two calls were made to callout_reset (the first starting the migration) the second call would possibly corrupt the linked list (if it was the active callout about to execute) and thus we would spin forever in soft clock and this would result in a panic, spin lock held to long. TEST PLAN I have added the kernel test framework and a callout_test module. This allows us to pound on the callout code with multiple threads resetting, draining and stopping callouts all at about the same time. This test without the fixes would lock up and panic with a spin lock held to long vs now it does not. I have also begun testing this on Netflix Caches to further validate that it does no harm and instead gets rid of a panic or two ;-) REVISION DETAIL https://reviews.freebsd.org/D1711 AFFECTED FILES sys/amd64/conf/GENERIC sys/conf/files sys/conf/options sys/kern/kern_testfrwk.c sys/kern/kern_timeout.c sys/modules/Makefile sys/modules/callout_test/Makefile sys/modules/callout_test/callout_test.c sys/sys/callout.h sys/sys/callout_test.h sys/sys/kern_testfrwk.h To: rrs, gnn, rwatson, imp, hselasky, adrian, sbruno, lstewart Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 17:14:11 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 7F110337 for ; Wed, 28 Jan 2015 17:14:11 +0000 (UTC) Received: from onlyone.friendlyhosting.spb.ru (onlyone.friendlyhosting.spb.ru [IPv6:2a01:4f8:131:60a2::2]) by mx1.freebsd.org (Postfix) with ESMTP id 46E91EF9 for ; Wed, 28 Jan 2015 17:14:11 +0000 (UTC) Received: from [127.0.0.1] (nat.in.devexperts.com [89.113.128.63]) (Authenticated sender: lev@serebryakov.spb.ru) by onlyone.friendlyhosting.spb.ru (Postfix) with ESMTPSA id F21165C002 for ; Wed, 28 Jan 2015 20:13:54 +0300 (MSK) Message-ID: <54C918D2.7090805@FreeBSD.org> Date: Wed, 28 Jan 2015 20:13:54 +0300 From: Lev Serebryakov Reply-To: lev@FreeBSD.org Organization: FreeBSD User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:31.0) Gecko/20100101 Thunderbird/31.4.0 MIME-Version: 1.0 To: freebsd-net@freebsd.org Subject: Problems with DNSSEC -- answer in fragmented UDP doesn't work Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 8bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 17:14:11 -0000 -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA512 I could not resolve names with DNSSEC (for example, in freebsd.org domain) on two of my installations, one with FreeBSD 11 and other with FreeBSD 9.3. Symptoms are the same: answer is sent as fragmented IP/UDP packet and second part of answer is never arrived. For example, this doesn't work for me ("timeout" and only first part of fragmented packet on wire according to tcpdump): % dig +dnssec www.freebsd.org @72.52.71.1 ; <<>> DiG 9.9.5 <<>> +dnssec www.freebsd.org @72.52.71.1 ;; global options: +cmd ;; connection timed out; no servers could be reached % Problem is, latest bind (9.9 from ports) send such requests over UDP, not TCP. Is it Ok? Is it misconfiguration of my networks (I have such problem in tow different installations) or something? - -- // Lev Serebryakov -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (MingW32) iQJ8BAEBCgBmBQJUyRjSXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRGOTZEMUNBMEI1RjQzMThCNjc0QjMzMEFF QUIwM0M1OEJGREM0NzhGAAoJEOqwPFi/3EePWP8P/Rnxgs5mAXzYTlYqa5S0e8H/ 22bKyBIzqGiv6Ha33/qWLSl+bjVbMfYYJU8DHMv0kHp00JK1W5ezmq9GRm1OeDWS EP/03Etrm2BInQM486GOXFsp2k1MGR/+GbrzXfCs/WZj1zbrNIZ6aqQ9WOOlnukJ eEsTO7rBUiuW6PbCAHSvzw7BBWDX59+Mj2KgjEesL+E/CxMGQy2iskB8eLSDrgpJ EXqB5mGYEgyTDRcQ+EZnYGowMUEU5ZWoS2uKJkH5M+9ok9uj/58z3hYxUy0Yr93K VNaSfjZcvKB+Yfj/mOG+WbrBgz/kJmryyh676WBI0BvIEBKEo+3gcPJVZBnCxsed fUvZxC/ARDHOljIQHglax1GWMRT1RR8idpAZoGvVxDEtygyfYLFhwIWITdffyR6G CUY16Sjp1tWa6wADjal+pz1tE9V8n67tkNbGtZcwF7N2bAMfAmMTVG0LuOyWZWgC DU2kOEX6lU6/Y/M+oY73yXzMf/fGdO6RI1SpVhBOiIBeRK7901JXng/IXAcV3k9D tjw8C8lHoClU0gbNJuiEXFwWXIB6cUg0/55V4cuBFdHhqShBWdaVaLE/N5HSDhrp ISoD+mcoBZs+QlP7gF2w+G+qvOq5BZB2Np/5WETs5Sk8HlFaWz2pseGN2t8AetvZ iAvOQuKF2Kq+dg3dzOGj =83vn -----END PGP SIGNATURE----- From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 17:37:46 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id E714EAE0 for ; Wed, 28 Jan 2015 17:37:46 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id C2FAC18D for ; Wed, 28 Jan 2015 17:37:46 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SHbkVm013358 for ; Wed, 28 Jan 2015 17:37:46 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SHbkNq013357; Wed, 28 Jan 2015 17:37:46 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 17:37:46 +0000 To: freebsd-net@freebsd.org From: "erj (Eric Joyner)" Subject: [Differential] [Changed Subscribers] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTJHmo= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 17:37:47 -0000 erj added a subscriber: erj. REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, imp, hselasky, adrian, sbruno, lstewart Cc: erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 17:38:23 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 5C409B7F for ; Wed, 28 Jan 2015 17:38:23 +0000 (UTC) Received: from smtp.infracaninophile.co.uk (smtp6.infracaninophile.co.uk [IPv6:2001:8b0:151:1:3cd3:cd67:fafa:3d78]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "smtp.infracaninophile.co.uk", Issuer "ca.infracaninophile.co.uk" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id DB17B19E for ; Wed, 28 Jan 2015 17:38:22 +0000 (UTC) Received: from ox-dell39.ox.adestra.com (no-reverse-dns.metronet-uk.com [85.199.232.226] (may be forged)) (authenticated bits=0) by smtp.infracaninophile.co.uk (8.15.1/8.15.1) with ESMTPSA id t0SHcEZh004890 (version=TLSv1.2 cipher=DHE-RSA-AES128-SHA bits=128 verify=NO) for ; Wed, 28 Jan 2015 17:38:15 GMT (envelope-from m.seaman@infracaninophile.co.uk) Authentication-Results: smtp.infracaninophile.co.uk; dmarc=none header.from=infracaninophile.co.uk DKIM-Filter: OpenDKIM Filter v2.9.2 smtp.infracaninophile.co.uk t0SHcEZh004890 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=infracaninophile.co.uk; s=201001-infracaninophile; t=1422466695; bh=v1M/FV+E/QhMWkFFiAp4rp7eyaieSnR+ld5bDqeEekE=; h=Date:From:To:Subject:References:In-Reply-To; z=Date:=20Wed,=2028=20Jan=202015=2017:38:08=20+0000|From:=20Matthew =20Seaman=20|To:=20freebsd-net@fr eebsd.org|Subject:=20Re:=20Problems=20with=20DNSSEC=20--=20answer= 20in=20fragmented=20UDP=20doesn't=20work|References:=20<54C918D2.7 090805@FreeBSD.org>|In-Reply-To:=20<54C918D2.7090805@FreeBSD.org>; b=NWSTLz9cKJzXTJ0/gryMvcBa6YLvnSbTy28wyknse5evTKKxmC1OrnBbMPBrTiAVe QAHP1b4ylpab2EWfp8qelginjsqZd+E15yfNKHCA/P0uarwZt8Gwz1PuhRGB8z9ZGj x3mcXDD47AVTN7izcWN/LhhY+xDZWhfuEUvhoGas= X-Authentication-Warning: lucid-nonsense.infracaninophile.co.uk: Host no-reverse-dns.metronet-uk.com [85.199.232.226] (may be forged) claimed to be ox-dell39.ox.adestra.com Message-ID: <54C91E80.7020407@infracaninophile.co.uk> Date: Wed, 28 Jan 2015 17:38:08 +0000 From: Matthew Seaman User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:31.0) Gecko/20100101 Thunderbird/31.4.0 MIME-Version: 1.0 To: freebsd-net@freebsd.org Subject: Re: Problems with DNSSEC -- answer in fragmented UDP doesn't work References: <54C918D2.7090805@FreeBSD.org> In-Reply-To: <54C918D2.7090805@FreeBSD.org> Content-Type: multipart/signed; micalg=pgp-sha512; protocol="application/pgp-signature"; boundary="UsdSLQO7RCcdO38OShMpnRSwqHll9H7L2" X-Virus-Scanned: clamav-milter 0.98.5 at lucid-nonsense.infracaninophile.co.uk X-Virus-Status: Clean X-Spam-Status: No, score=-2.5 required=5.0 tests=ALL_TRUSTED,AWL,BAYES_00, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,URIBL_BLOCKED autolearn=ham autolearn_force=no version=3.4.0 X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on lucid-nonsense.infracaninophile.co.uk X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 17:38:23 -0000 This is an OpenPGP/MIME signed message (RFC 4880 and 3156) --UsdSLQO7RCcdO38OShMpnRSwqHll9H7L2 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable On 01/28/15 17:13, Lev Serebryakov wrote: >=20 > I could not resolve names with DNSSEC (for example, in freebsd.org > domain) on two of my installations, one with FreeBSD 11 and other with > FreeBSD 9.3. >=20 > Symptoms are the same: answer is sent as fragmented IP/UDP packet and > second part of answer is never arrived. For example, this doesn't work > for me ("timeout" and only first part of fragmented packet on wire > according to tcpdump): >=20 > % dig +dnssec www.freebsd.org @72.52.71.1 >=20 > ; <<>> DiG 9.9.5 <<>> +dnssec www.freebsd.org @72.52.71.1 > ;; global options: +cmd > ;; connection timed out; no servers could be reached > % >=20 > Problem is, latest bind (9.9 from ports) send such requests over UDP, > not TCP. >=20 > Is it Ok? Is it misconfiguration of my networks (I have such problem > in tow different installations) or something? What do you get if you run the reply size test at DNS-OARC ? https://www.dns-oarc.net/oarc/services/replysizetest This should help you eliminate restrictions on the size of DNS responses, rather than it being a DNSSEC specific problem. Most queries nowadays are expected to run over UDP, even if the response is too big to fit into a single UDP packet, by means of the EDNS mechanism. The old 'try UDP, and failing that, try again using TCP' style should still work though, although TCP is only used routinely for AXFR or IXFR type queries -- meaning that certain people may forget to allow TCP queries via port 53 when setting up firewalls... If you're on 10.x or above, try enabling local_unbound -- beware that there's a bug that prevents resolution of RFC1918 and other special IP ranges on 10.0, fixed in 10.1. Using a local unbound as a forwarder should give you the ability to tweak exactly how it talks to your upstream DNSes so that the answers get through more reliably. Cheers, Matthew --UsdSLQO7RCcdO38OShMpnRSwqHll9H7L2 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQJ8BAEBCgBmBQJUyR6AXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXQxOUYxNTRFQ0JGMTEyRTUwNTQ0RTNGMzAw MDUxM0YxMEUwQTlFNEU3AAoJEABRPxDgqeTnFGoQAJoiCEbPkw4R17L4k4xkYjjS /AS25Je57wVkpguV56fhSXIlYV/V/q7YiNBLL5Y7bjiIvSJNE4aExiGIlorlcyf9 xkt+at29NzgyBj2xBC5eESHBpX/rBqL4xVob10Lzio79yUzq95itcTM3nkZflsT8 ihvZ7q5xZmP7iSb+nnJB2aF2n/nOF0Kka9EnMw+IPp7XzFTy8/+v0iAyUY9eRW8N UgOv3TPF67P3WjMAqAWpavWB2MJ79UvNP+bshtDi8ni9XGv2wSJlCxsyXu2txnSy +3NVPdbIg4y4VbicR2O71oYeXV6jwN6c1zDDKKADe9YRo38cfnyZ+VmKnPHrLk4e Pkv6l9/66XoeuN2t6Ogm4mVu/fr4rRdsBeTMZ6K5P+grZ66f8djtdkLGE5O035yx OArn9rT9IuaNsjnLEme6wB8z0zO6CIePwqhnpKvAeOZQHY4vJ0Xt1R2jlRoZhkEl wcWF1ly4pZsP3My8O3h+rRYt98VcDud8HKhXVhQya3cnL6JeczJn23CVlyLzeLAu nh4O1EoSQ7juYIyEpQPAeNRIqR7PUlVdeYV4FGJNRQeVtbIyrscwC61XBDB3cyG6 AWjaQKBrE8owogsrElFz0T9EyZg/f+AsUhTCDOLKrGdghU3tmEmiPfZoRWOxqBIf zdvuV3oQGXyu3JqV73vC =cawr -----END PGP SIGNATURE----- --UsdSLQO7RCcdO38OShMpnRSwqHll9H7L2-- From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 17:53:55 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 10878228 for ; Wed, 28 Jan 2015 17:53:55 +0000 (UTC) Received: from onlyone.friendlyhosting.spb.ru (onlyone.friendlyhosting.spb.ru [46.4.40.135]) by mx1.freebsd.org (Postfix) with ESMTP id C53EE389 for ; Wed, 28 Jan 2015 17:53:54 +0000 (UTC) Received: from [127.0.0.1] (nat.in.devexperts.com [89.113.128.63]) (Authenticated sender: lev@serebryakov.spb.ru) by onlyone.friendlyhosting.spb.ru (Postfix) with ESMTPSA id 3462F5C002; Wed, 28 Jan 2015 20:53:38 +0300 (MSK) Message-ID: <54C92222.6000201@FreeBSD.org> Date: Wed, 28 Jan 2015 20:53:38 +0300 From: Lev Serebryakov Reply-To: lev@FreeBSD.org Organization: FreeBSD User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:31.0) Gecko/20100101 Thunderbird/31.4.0 MIME-Version: 1.0 To: Matthew Seaman , freebsd-net@freebsd.org Subject: Problems with IP fragments (was: Problems with DNSSEC -- answer in fragmented UDP doesn't work) References: <54C918D2.7090805@FreeBSD.org> <54C91E80.7020407@infracaninophile.co.uk> In-Reply-To: <54C91E80.7020407@infracaninophile.co.uk> Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 8bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 17:53:55 -0000 -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA512 On 28.01.2015 20:38, Matthew Seaman wrote: > What do you get if you run the reply size test at DNS-OARC ? > > https://www.dns-oarc.net/oarc/services/replysizetest 0 lines (empty answer) at CURRENT, only "rst.x1013.rs.dns-oarc.net." on 9.3. Looks like "IP Fragments Filtered", but I don't understand — why and where?! I'm using ipfw on both hosts, but I don't have any special rules about IP fragments at all! And as these systems are in completely different networks, with different uplinks and FreeBSD versions! > This should help you eliminate restrictions on the size of DNS > responses, rather than it being a DNSSEC specific problem. Yes, it is EDNS more-than-one-UDP-dataggram problem, not DNSSEC-specific one. > If you're on 10.x or above, try enabling local_unbound -- beware > that there's a bug that prevents resolution of RFC1918 and other > special IP ranges on 10.0, fixed in 10.1. Using a local unbound as > a forwarder should give you the ability to tweak exactly how it > talks to your upstream DNSes so that the answers get through more > reliably. Unfortunately, I need recursive resolver for my network and authoritative server (with views!) on one host. unbound could not do that, so I'm using bind from ports on CURRENT. - -- // Lev Serebryakov -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (MingW32) iQJ8BAEBCgBmBQJUySIiXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRGOTZEMUNBMEI1RjQzMThCNjc0QjMzMEFF QUIwM0M1OEJGREM0NzhGAAoJEOqwPFi/3EePUt4P/3Ubd77zLlazBQ8ZiQ/hS/O6 Y/t8lAMmRW2OiNO4FU0EuakSj3WxvEITTjVcX46o/K7ZBYGxa6r5Zq5OWw1rVlii KfDesQQHZzCV9WyJI4bp84FyaxFlKzEsBVTbVU8YNvKrBtJqhfL7iGr1aM5Xgvag j6KffsfVkozC8c/WKLHDKriFbR9NzTO1t1DWcWymS3a2PT/Ih1USycb+bZ+xDqFB TXICX0+OZ9h956RP2gGsSdpEvJAP5OTW+daoaDfvHjTdrx77SyfAxHQop7ROEy7n 5blMTVMHBs1iK/hfAfuiXkCAVpAssqOrLEk5mb+SdX5OgwOR79kshE/hyYeN28gg wUjX6FuAnb8HRvv4HNGqe82ptevammeWUSYrFuM2xzQqdfJOElTF3VDfk6FN+iT5 yCdVv2Oqsg6ZPB2dosWK5aWMUeVn5BYdwWD6Z3jrRFGONJ3V1pS17TpLL/bEd4Ta u8A/tIbCLvfzNSrmrs4iXCRRfx1wDpFE+cvL5PXTlS3A8qf4Nm2EgOgv92Oz9862 0TJ/WvxvXn6QdSMXDvgMmk2DhclU3/L7aJy/of4QR1zwdJFwjuQSuhCjek/w1vw0 9wB8mjnVu0kIXa9z1FigI0X2fYF9rIB6YLca0N3SsGydm5p6zHFqIXNcYwTjHUg+ WOu4W9yfm0X10XHI3VdV =+8Zi -----END PGP SIGNATURE----- From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 17:55:12 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id ADFE42DC for ; Wed, 28 Jan 2015 17:55:12 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 8965A3B1 for ; Wed, 28 Jan 2015 17:55:12 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SHtCBT033106 for ; Wed, 28 Jan 2015 17:55:12 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SHtCHd033101; Wed, 28 Jan 2015 17:55:12 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 17:55:12 +0000 To: freebsd-net@freebsd.org From: "neel (Neel Natu)" Subject: [Differential] [Changed Subscribers] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTJIoA= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 17:55:12 -0000 neel added a subscriber: neel. REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, imp, hselasky, adrian, sbruno, lstewart Cc: neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 18:04:58 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 5745A432; Wed, 28 Jan 2015 18:04:58 +0000 (UTC) Received: from mail-yh0-x22c.google.com (mail-yh0-x22c.google.com [IPv6:2607:f8b0:4002:c01::22c]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 1199A690; Wed, 28 Jan 2015 18:04:58 +0000 (UTC) Received: by mail-yh0-f44.google.com with SMTP id i57so9387751yha.3; Wed, 28 Jan 2015 10:04:57 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=nXvSr9I+E2x5/OQGVo/fO9qJTHOXjR+RQhHtcqaGx28=; b=Uy9HXMc0MsyQO5fR9xMMNCb7qN7pPbhUB/L74M0muqZhXJhzMI5Y2IQ1bQQUsNeN2B ZJsDVrt5Vt/yYLjMZqCQ1kNl/SnKuVrScPMX0nsrykTXe0NezdOG9hPg8wnwZSxClmR7 Lu1a7jUFPTEHvR47ZqYk5f7dzXbeGfp8ZiYJQtRByeQ+j5Qf2WrnZiZpJ5PWI151r03X 1MSXu0UZXRCyGvLDSLyTcEE6eR+sfD/S7OstnldwT2BmLPe9OiFcJVIgDNvDOb16j1WJ dDMFluGHoJTrNz+PV7rJrqstzix4vFr18HgaeGzp2cuiWiicOdj5kXgksm90odiDKxod VqBA== MIME-Version: 1.0 X-Received: by 10.236.40.116 with SMTP id e80mr1755286yhb.186.1422468297121; Wed, 28 Jan 2015 10:04:57 -0800 (PST) Received: by 10.170.79.87 with HTTP; Wed, 28 Jan 2015 10:04:57 -0800 (PST) In-Reply-To: <54C92222.6000201@FreeBSD.org> References: <54C918D2.7090805@FreeBSD.org> <54C91E80.7020407@infracaninophile.co.uk> <54C92222.6000201@FreeBSD.org> Date: Wed, 28 Jan 2015 10:04:57 -0800 Message-ID: Subject: Re: Problems with IP fragments (was: Problems with DNSSEC -- answer in fragmented UDP doesn't work) From: Freddie Cash To: lev@freebsd.org Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: freebsd-net , Matthew Seaman X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 18:04:58 -0000 On Wed, Jan 28, 2015 at 9:53 AM, Lev Serebryakov wrote: > -----BEGIN PGP SIGNED MESSAGE----- > Hash: SHA512 > > On 28.01.2015 20:38, Matthew Seaman wrote: > > > What do you get if you run the reply size test at DNS-OARC ? > > > > https://www.dns-oarc.net/oarc/services/replysizetest > 0 lines (empty answer) at CURRENT, only "rst.x1013.rs.dns-oarc.net." > on 9.3. > > Looks like "IP Fragments Filtered", but I don't understand =E2=80=94 why= and > where?! > > I'm using ipfw on both hosts, but I don't have any special rules > about IP fragments at all! And as these systems are in completely > different networks, with different uplinks and FreeBSD versions! > =E2=80=8BIPFW doesn't deal with IP fragment reassembly by default. You can add something like the following to the start of the IPFW ruleset to work around it (one for each NIC): =E2=80=8B$IPFW add reass ip from any to any in recv $NIC0 =E2=80=8B$IPFW add reass ip from any to any in recv $NIC1 ... --=20 Freddie Cash fjwcash@gmail.com From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 18:08:39 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 324D5508 for ; Wed, 28 Jan 2015 18:08:39 +0000 (UTC) Received: from onlyone.friendlyhosting.spb.ru (onlyone.friendlyhosting.spb.ru [IPv6:2a01:4f8:131:60a2::2]) by mx1.freebsd.org (Postfix) with ESMTP id E82B96C1 for ; Wed, 28 Jan 2015 18:08:38 +0000 (UTC) Received: from [127.0.0.1] (nat.in.devexperts.com [89.113.128.63]) (Authenticated sender: lev@serebryakov.spb.ru) by onlyone.friendlyhosting.spb.ru (Postfix) with ESMTPSA id 6E1DA5C002; Wed, 28 Jan 2015 21:08:27 +0300 (MSK) Message-ID: <54C9259B.4030508@FreeBSD.org> Date: Wed, 28 Jan 2015 21:08:27 +0300 From: Lev Serebryakov Reply-To: lev@FreeBSD.org Organization: FreeBSD User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:31.0) Gecko/20100101 Thunderbird/31.4.0 MIME-Version: 1.0 To: Freddie Cash Subject: Re: Problems with IP fragments References: <54C918D2.7090805@FreeBSD.org> <54C91E80.7020407@infracaninophile.co.uk> <54C92222.6000201@FreeBSD.org> In-Reply-To: Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 8bit Cc: freebsd-net , Matthew Seaman X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 18:08:39 -0000 -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA512 On 28.01.2015 21:04, Freddie Cash wrote: >> Looks like "IP Fragments Filtered", but I don't understand — why >> and where?! >> >> I'm using ipfw on both hosts, but I don't have any special rules >> about IP fragments at all! And as these systems are in >> completely different networks, with different uplinks and FreeBSD >> versions! >> > > ​IPFW doesn't deal with IP fragment reassembly by default. Oh, I see. And as second fragment is not "UDP" (it doesn't have UDP header!), it doesn't pass through stateful firewall... I see now. Thank you. > You can add something like the following to the start of the IPFW > ruleset to work around it (one for each NIC): > > ​$IPFW add reass ip from any to any in recv $NIC0 ​$IPFW add reass > ip from any to any in recv $NIC1 ... > - -- // Lev Serebryakov -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (MingW32) iQJ8BAEBCgBmBQJUySWbXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRGOTZEMUNBMEI1RjQzMThCNjc0QjMzMEFF QUIwM0M1OEJGREM0NzhGAAoJEOqwPFi/3EeP/WUP/RJUv19sCqjt3/a/TNH/b6vs 8IcjQA3rD4i1NgUWn1w0Olro4SlzkbqDFzv/ShvNA5TSH6NbhJpaBkO9dno8nwDB 8K1GuTqYnDqAIexHw+br/dkcTLrah4h80tiucn0fSs12qOFaN5zJGchLDpxeEEg5 Okncf/0Ef20ooaUfRXwcD+C0gmaYkiWZ2+VcmbqsZvT3gvdAiEXpPJjqp3agUr/4 aTGriLZwo6OHTZdW7FQuKIV+4KO2piga+pF1lZKb78VOwgEYhw3yISuFzddIdaUd T+Uj/qDjYgjqyxt+cSXIpnsY4jKQ6fR3EOoERgv5VXtRdunHC/6i9vygp6cga3rj EZNAFlc+6ecmX9yPCdV5ScCvjh8lYZKuQivYNMauwI8o+Jud3dHJTCtl3zaVl18C b2Y7+6gNY/oM78H1b63R79DVf+ohSmlLHW+hSqXfYcrqmT+ocCfOK13ybEoV93N1 nTMEDom83lvMhbDm9HHSBYbMyDKKPf6bX4VX2aZbjL+3u5VBclgKHMIS2U5VUBm/ h7fWIPys/XVs+eHNACkye0qh/7bHQ0GarMhJ27nHA+qrkbnmzqT1Ush7bQXyrgVJ MfzU/JI/1u5Dw558innRMLP+3FnjjiITth/ZQCVzNXndVai4vpVXfzNdCRhNGQgV kIJ0H5+AoXwiL5qLYR1x =MY36 -----END PGP SIGNATURE----- From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 18:47:03 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 25FAB617 for ; Wed, 28 Jan 2015 18:47:03 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 011FCB56 for ; Wed, 28 Jan 2015 18:47:03 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SIl2ct070884 for ; Wed, 28 Jan 2015 18:47:02 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SIl2uV070883; Wed, 28 Jan 2015 18:47:02 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 18:47:02 +0000 To: freebsd-net@freebsd.org From: "hselasky (Hans Petter Selasky)" Subject: [Differential] [Updated] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: <9bc554086756e04f34eef3d7813ddc2e@localhost.localdomain> X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTJLqY= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 18:47:03 -0000 hselasky added a comment. Hi, Should the callout_test module be put in a separate directory? sys/modules/test_frwk sys/modules/test_frwk/callout When more tests are added that makes it easy exclude them from the build. --HPS REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, imp, adrian, sbruno, lstewart, hselasky Cc: neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 18:55:20 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 91D24802 for ; Wed, 28 Jan 2015 18:55:20 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 5319BC28 for ; Wed, 28 Jan 2015 18:55:20 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SItKrV079856 for ; Wed, 28 Jan 2015 18:55:20 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SItKBC079854; Wed, 28 Jan 2015 18:55:20 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 18:55:20 +0000 To: freebsd-net@freebsd.org From: "hselasky (Hans Petter Selasky)" Subject: [Differential] [Requested Changes To] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTJMJg= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 18:55:20 -0000 hselasky requested changes to this revision. hselasky added a comment. This revision now requires changes to proceed. See comments given. INLINE COMMENTS sys/kern/kern_timeout.c:674 cc_exec_cancel(cc, direct) should be true when c_lock == NULL, because the callback cannot be stopped then. sys/kern/kern_timeout.c:1059 Is this comment be properly formatted with regard to filling lines till end of line? ALT+Q in emacs?? sys/modules/callout_test/callout_test.c:58 Should these variables all be static? sys/modules/callout_test/callout_test.c:69 Possibly this define is redundant. sys/modules/callout_test/callout_test.c:254 Is this check really needed? sys/sys/callout_test.h:1 Upper case inclusion guard. sys/sys/callout_test.h:1 Missing copyright for header file. sys/sys/kern_testfrwk.h:43 Should this function be typedefed: typedef void (kern_testframework_func_t)(struct kern_test *); REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, imp, adrian, sbruno, lstewart, hselasky Cc: neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 19:13:27 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 728FA230 for ; Wed, 28 Jan 2015 19:13:27 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 357A7E3C for ; Wed, 28 Jan 2015 19:13:27 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SJDQbj064779 for ; Wed, 28 Jan 2015 19:13:26 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SJDQlr064778; Wed, 28 Jan 2015 19:13:26 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 19:13:26 +0000 To: freebsd-net@freebsd.org From: "rrs (Randall Stewart)" Subject: [Differential] [Commented On] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTJNNY= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 19:13:27 -0000 rrs added a comment. Moving the tests to a sub-dir sounds like a good idea as well.. Thanks Hans.. INLINE COMMENTS sys/kern/kern_timeout.c:674 Hans, no *you must* set it to false here in the soft clock so you can recognize if it is requested to be stopped (if possible). The return codes are all correct if the c_lock is set or not. sys/kern/kern_timeout.c:1059 Sure I can do that.. I will ALT-Q it and see if I can get it better formatted sys/modules/callout_test/callout_test.c:58 Sure thats a good ideas since they are only used in the module. sys/modules/callout_test/callout_test.c:69 ahh yes, it surely is. I had been testing it in a branch that did not have the define in callout.h and it must have slipped in.. good catch! sys/modules/callout_test/callout_test.c:254 Yes it is, since the MOD_QUIESCE may unload the model.. or it may not. sys/sys/callout_test.h:1 Good catch I will fix it ;-) sys/sys/kern_testfrwk.h:43 That sounds fine.. I was just copying how the callout code did it (which was without typedef) but we can do that too ;-) REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, imp, adrian, sbruno, lstewart, hselasky Cc: neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 19:48:23 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 12CDC649; Wed, 28 Jan 2015 19:48:23 +0000 (UTC) Received: from na01-bn1-obe.outbound.protection.outlook.com (mail-bn1bn0105.outbound.protection.outlook.com [157.56.110.105]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-SHA384 (256/256 bits)) (Client CN "mail.protection.outlook.com", Issuer "MSIT Machine Auth CA 2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 9CA0027A; Wed, 28 Jan 2015 19:48:22 +0000 (UTC) Received: from BN1AFFO11FD033.protection.gbl (10.58.52.31) by BN1AFFO11HUB020.protection.gbl (10.58.52.130) with Microsoft SMTP Server (TLS) id 15.1.75.11; Wed, 28 Jan 2015 18:14:03 +0000 Received: from cio-krc-pf03.osuad.osu.edu (164.107.81.210) by BN1AFFO11FD033.mail.protection.outlook.com (10.58.52.246) with Microsoft SMTP Server (TLS) id 15.1.75.11 via Frontend Transport; Wed, 28 Jan 2015 18:14:03 +0000 Received: from CIO-TNC-HT06.osuad.osu.edu (cio-tnc-ht06.osuad.osu.edu [164.107.81.171]) (using TLSv1 with cipher AES128-SHA (128/128 bits)) (No client certificate requested) by cio-krc-pf03.osuad.osu.edu (Postfix) with ESMTPS id 9C9F0201D6; Wed, 28 Jan 2015 13:14:02 -0500 (EST) Received: from CIO-KRC-D2MBX11.osuad.osu.edu ([fe80::6158:b059:ab30:6627]) by CIO-TNC-HT06.osuad.osu.edu ([fe80::3d16:84bd:8d88:7cfd%12]) with mapi id 14.03.0174.001; Wed, 28 Jan 2015 13:14:01 -0500 From: "Wolff, Nicholas (Nick)" To: "lev@FreeBSD.org" , Freddie Cash Subject: Re: Problems with IP fragments Thread-Topic: Problems with IP fragments Thread-Index: AQHQOyWCB9jirW7jGUqcnBu3PUIfCJzV1hKA Date: Wed, 28 Jan 2015 18:14:00 +0000 Message-ID: References: <54C918D2.7090805@FreeBSD.org> <54C91E80.7020407@infracaninophile.co.uk> <54C92222.6000201@FreeBSD.org> <54C9259B.4030508@FreeBSD.org> In-Reply-To: <54C9259B.4030508@FreeBSD.org> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [199.18.249.24] Content-Type: text/plain; charset="utf-8" Content-ID: Content-Transfer-Encoding: base64 MIME-Version: 1.0 X-EOPAttributedMessage: 0 Received-SPF: Pass (protection.outlook.com: domain of oar.net designates 164.107.81.210 as permitted sender) receiver=protection.outlook.com; client-ip=164.107.81.210; helo=cio-krc-pf03.osuad.osu.edu; Authentication-Results: spf=pass (sender IP is 164.107.81.210) smtp.mailfrom=nwolff@oar.net; freebsd.org; dkim=none (message not signed) header.d=none; X-Forefront-Antispam-Report: CIP:164.107.81.210; CTRY:US; IPV:NLI; EFV:NLI; SFV:NSPM; SFS:(10019020)(6009001)(51704005)(54524002)(377454003)(24454002)(479174004)(15975445007)(87936001)(2656002)(46102003)(2950100001)(23676002)(50986999)(93886004)(2501002)(102836002)(1720100001)(62966003)(47776003)(2900100001)(92566002)(93346002)(6806004)(19580395003)(106116001)(36756003)(19580405001)(66066001)(54356999)(77156002)(106466001)(575784001)(76176999)(50466002)(86362001)(109096001); DIR:OUT; SFP:1102; SCL:1; SRVR:BN1AFFO11HUB020; H:cio-krc-pf03.osuad.osu.edu; FPR:; SPF:None; MLV:sfv; LANG:en; X-Microsoft-Antispam: UriScan:; X-Microsoft-Antispam: BCL:0;PCL:0;RULEID:;SRVR:BN1AFFO11HUB020; X-Exchange-Antispam-Report-Test: UriScan:; X-Exchange-Antispam-Report-CFA-Test: BCL:0; PCL:0; RULEID:(601004); SRVR:BN1AFFO11HUB020; X-Forefront-PRVS: 047001DADA X-Exchange-Antispam-Report-CFA-Test: BCL:0; PCL:0; RULEID:; SRVR:BN1AFFO11HUB020; X-OriginatorOrg: oar.net X-MS-Exchange-CrossTenant-OriginalArrivalTime: 28 Jan 2015 18:14:03.8407 (UTC) X-MS-Exchange-CrossTenant-Id: b4d138ca-1815-4a9b-a3a7-130a33b1e692 X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=b4d138ca-1815-4a9b-a3a7-130a33b1e692; Ip=[164.107.81.210] X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem X-MS-Exchange-Transport-CrossTenantHeadersStamped: BN1AFFO11HUB020 Cc: freebsd-net , Matthew Seaman X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 19:48:23 -0000 V2UgdXNlIHRoZSBmb2xsb3dpbmcgZm9yIHVkcCBmcmFnbWVudHMgc3BlY2lmaWNhbGx5IHRoaXMg aXNzdWUgYWN0dWFsbHkuDQoNCiMgdWRwIGZyYWdzIChsYXJnZSBkbnNzZWMgcmVzcG9uc2VzKQ0K YWRkIDAyMDMwIGFsbG93IHVkcCBmcm9tIGFueSB0byBtZSBmcmFnDQoNCg0KDQpPbiAxLzI4LzE1 LCAxOjA4IFBNLCAiTGV2IFNlcmVicnlha292IiA8bGV2QEZyZWVCU0Qub3JnPiB3cm90ZToNCg0K Pi0tLS0tQkVHSU4gUEdQIFNJR05FRCBNRVNTQUdFLS0tLS0NCj5IYXNoOiBTSEE1MTINCj4NCj5P biAyOC4wMS4yMDE1IDIxOjA0LCBGcmVkZGllIENhc2ggd3JvdGU6DQo+DQo+Pj4gTG9va3MgbGlr ZSAiSVAgRnJhZ21lbnRzIEZpbHRlcmVkIiwgYnV0IEkgZG9uJ3QgdW5kZXJzdGFuZCDigJQgd2h5 DQo+Pj4gYW5kIHdoZXJlPyENCj4+PiANCj4+PiBJJ20gdXNpbmcgaXBmdyBvbiBib3RoIGhvc3Rz LCBidXQgSSBkb24ndCBoYXZlIGFueSBzcGVjaWFsIHJ1bGVzDQo+Pj4gYWJvdXQgSVAgZnJhZ21l bnRzIGF0IGFsbCEgQW5kIGFzIHRoZXNlIHN5c3RlbXMgYXJlIGluDQo+Pj4gY29tcGxldGVseSBk aWZmZXJlbnQgbmV0d29ya3MsIHdpdGggZGlmZmVyZW50IHVwbGlua3MgYW5kIEZyZWVCU0QNCj4+ PiB2ZXJzaW9ucyENCj4+PiANCj4+IA0KPj4g4oCLSVBGVyBkb2Vzbid0IGRlYWwgd2l0aCBJUCBm cmFnbWVudCByZWFzc2VtYmx5IGJ5IGRlZmF1bHQuDQo+ICBPaCwgSSBzZWUuIEFuZCBhcyBzZWNv bmQgZnJhZ21lbnQgaXMgbm90ICJVRFAiIChpdCBkb2Vzbid0IGhhdmUgVURQDQo+aGVhZGVyISks IGl0IGRvZXNuJ3QgcGFzcyB0aHJvdWdoIHN0YXRlZnVsIGZpcmV3YWxsLi4uIEkgc2VlIG5vdy4N Cj5UaGFuayB5b3UuDQo+DQo+PiBZb3UgY2FuIGFkZCBzb21ldGhpbmcgbGlrZSB0aGUgZm9sbG93 aW5nIHRvIHRoZSBzdGFydCBvZiB0aGUgSVBGVw0KPj4gcnVsZXNldCB0byB3b3JrIGFyb3VuZCBp dCAob25lIGZvciBlYWNoIE5JQyk6DQo+PiANCj4+IOKAiyRJUEZXIGFkZCByZWFzcyBpcCBmcm9t IGFueSB0byBhbnkgaW4gcmVjdiAkTklDMCDigIskSVBGVyBhZGQgcmVhc3MNCj4+IGlwIGZyb20g YW55IHRvIGFueSBpbiByZWN2ICROSUMxIC4uLg0KPj4gDQo+DQo+DQo+LSAtLSANCj4vLyBMZXYg U2VyZWJyeWFrb3YNCj4tLS0tLUJFR0lOIFBHUCBTSUdOQVRVUkUtLS0tLQ0KPlZlcnNpb246IEdu dVBHIHYyLjAuMjIgKE1pbmdXMzIpDQo+DQo+aVFKOEJBRUJDZ0JtQlFKVXlTV2JYeFNBQUFBQUFD NEFLR2x6YzNWbGNpMW1jSEpBYm05MFlYUnBiMjV6TG05dw0KPlpXNXdaM0F1Wm1sbWRHaG9iM0p6 WlcxaGJpNXVaWFJHT1RaRU1VTkJNRUkxUmpRek1UaENOamMwUWpNek1FRkYNCj5RVUl3TTBNMU9F SkdSRU0wTnpoR0FBb0pFT3F3UEZpLzNFZVAvV1VQL1JKVXYxOXNDcWp0My9hL1ROSC9iNnZzDQo+ OEljalFBM3JENGkxTmdVV24xdzBPbHJvNFNsemticURGenYvU2h2TkE1VFNINk5iaEpwYUJrTzlk bm84bndEQg0KPjhLMUd1VHFZbkRxQUlleEh3K2JyL2RrY1RMcmFoNGg4MHRpdWNuMGZTczEycU9G YU41ekpHY2hMRHB4ZUVFZzUNCj5Pa25jZi8wRWYyMG9vYVVmUlh3Y0QrQzBnbWFZa2lXWjIrVmNt YnFzWnZUM2d2ZEFpRVhwUEpqcXAzYWdVci80DQo+YVRHcmlMWndvNk9IVFpkVzdGUXVLSVYrNEtP MnBpZ2ErcEYxbFpLYjc4Vk93Z0VZaHczeUlTdUZ6ZGRJZGFVZA0KPlQrVWovcURqWWdqcXl4dCtj U1hJcG5zWTRqS1E2ZlIzRU9vRVJndjVWWHRSZHVuSEMvNmk5dnlncDZjZ2EzcmoNCj5FWk5BRmxj KzZlY21YOXlQQ2RWNVNjQ3ZqaDhsWVpLdVFpdllOTWF1d0k4bytKdWQzZEhKVEN0bDN6YVZsMThD DQo+YjJZNys2Z05ZL29NNzhIMWI2M1I3OURWZitvaFNtbExIVytoU3FYZlljcnFtVCtvY0NmT0sx M3liRW9WOTNOMQ0KPm5UTUVEb204M2x2TWhiRG05SEhTQlliTXlES0tQZjZiWDRWWDJhWmJqTCsz dTVWQmNsZ0tITUlTMlU1VlVCbS8NCj5oN2ZXSVB5cy9YVnMrZUhOQUNreWUwcWgvN2JIUTBHYXJN aEoyN25IQStxcmtibm16cVQxVXNoN2JRWHlyZ1ZKDQo+TWZ6VS9KSS8xdTVEdzU1OGlublJNTFAr M0ZuamppSVR0aC9aUUNWek5YbmRWYWk0dnBWWGZ6TmRDUmhOR1FnVg0KPmtJSjBINStBb1h3aUw1 cUxZUjF4DQo+PU1ZMzYNCj4tLS0tLUVORCBQR1AgU0lHTkFUVVJFLS0tLS0NCj5fX19fX19fX19f X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fXw0KPmZyZWVic2QtbmV0QGZyZWVi c2Qub3JnIG1haWxpbmcgbGlzdA0KPmh0dHA6Ly9saXN0cy5mcmVlYnNkLm9yZy9tYWlsbWFuL2xp c3RpbmZvL2ZyZWVic2QtbmV0DQo+VG8gdW5zdWJzY3JpYmUsIHNlbmQgYW55IG1haWwgdG8gImZy ZWVic2QtbmV0LXVuc3Vic2NyaWJlQGZyZWVic2Qub3JnIg0KDQo= From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 20:40:17 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 63AA6D18; Wed, 28 Jan 2015 20:40:17 +0000 (UTC) Received: from mail-qg0-x22c.google.com (mail-qg0-x22c.google.com [IPv6:2607:f8b0:400d:c04::22c]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 1FC70B12; Wed, 28 Jan 2015 20:40:17 +0000 (UTC) Received: by mail-qg0-f44.google.com with SMTP id l89so19218216qgf.3; Wed, 28 Jan 2015 12:40:16 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:date:message-id:subject:from:to:content-type; bh=WyTcjkcss4RPfC5hhHrgHxw00vIWjMgd0mARYRNMLYY=; b=wLGkYPpcOke0wr1vJi3El4L3K3AETwrd2Zz04/WH0nSQbmmZsyu4z47oMBW3MF0uTT k7ooMNMJvHe0KL879IFaASJrZMwPv2l21gPWexdyO4EIMFJbiWULxeOxqYj/iMxmGvxd xpXS1dbVAmDLB4e/dBOJQvX34WDr0rpykv7/ySOAUmb+HEmu9y+BDYckuZO26ENygdlH 8NuwEvYeTQb8sMndNV0/Y5cxQyrH85mvXPgB8s+Gg3JO1l1nDcYyTyYna9LjeBTPkHWV sl+g1Ua70cExGXo6z8J47LSlCDJOuasnooCcNs+wC4bNsJRlAzhTJskwSILpJybb8Qgk +mOw== MIME-Version: 1.0 X-Received: by 10.224.23.6 with SMTP id p6mr527747qab.55.1422477616225; Wed, 28 Jan 2015 12:40:16 -0800 (PST) Received: by 10.96.65.69 with HTTP; Wed, 28 Jan 2015 12:40:16 -0800 (PST) Date: Wed, 28 Jan 2015 18:40:16 -0200 Message-ID: Subject: FreeBSD & Netmap Advocacy on Nanog From: Eduardo Meyer To: freebsd-advocacy@freebsd.org, "freebsd-net@freebsd.org" Content-Type: text/plain; charset=UTF-8 X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 20:40:17 -0000 Hello, I don't know who follows NANOG, but a recent discussion raised a positive position much likely suitable to the advocacy mailing list, concerning FreeBSD Netmap vs Intel DPDK and so on. I believe it's worth sharing this guy's point of view and case: http://mailman.nanog.org/pipermail/nanog/2015-January/072864.html I quite agre with those statements, and I specially agree with this excerpts: "I honestly hope a fraction of this million dollar donated to FreeBSD Foundation from WhatsApp founder goes on research and enhancements for Netmap technology. It's the most promising networking technology I have seen in the last years, and it goes straight to what FreeBSD does best: networking performance. It's not a coincidence that since the beginning of Internet, top Internet traffic servers, from Yahoo! to WhatsApp and Netflix, run FreeBSD. I don't know how important decisions can be addressed concerning adding to a Netmap stack a superset of full forwarding capability along with lagg(4), vlan(4), Q-in-Q, maybe carp(4) and other lightweight but still very kernel-path choppy features. But I hope FreeBSD engineers take good decisions on assigning those issues. And address time, funds and goals to Netmap. For now, however, if you really want a relatively new and innovative technology with actual code to use and run, ready and available, this is my suggestion: FreeBSD+Netmap." I completely agree Netmap is promising, innovative and adds incomparable potentials for FreeBSD in the future and hope FreeBSD (Foundation & Project) gives some extra attention future netmap enhancements. I also agree Netmap has proven itself with more usable code, utilities and samples provided by Professor Luigi Rizzo than Intel DPDK and Linux stuff (aka DNA). -- =========== Eduardo Meyer pessoal: dudu.meyer@gmail.com profissional: ddm.farmaciap@saude.gov.br From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 20:56:20 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id C7E421E9 for ; Wed, 28 Jan 2015 20:56:20 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 882C9D3A for ; Wed, 28 Jan 2015 20:56:20 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SKuK2D072224 for ; Wed, 28 Jan 2015 20:56:20 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SKuKEH072222; Wed, 28 Jan 2015 20:56:20 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 20:56:20 +0000 To: freebsd-net@freebsd.org From: "rrs (Randall Stewart)" Subject: [Differential] [Updated, 895 lines] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: <327b589b689fe5234bdcb3d8157d469d@localhost.localdomain> X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTJTPQ= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 20:56:20 -0000 rrs updated this revision to Diff 3503. rrs added a comment. This addresses all of the concerns of Hans. I still need help with getting MK_TESTKERN to properly be placed in the /mk infrastructure, I have pending queries to GNN and JHB on this... CHANGES SINCE LAST UPDATE https://reviews.freebsd.org/D1711?vs=3498&id=3503 REVISION DETAIL https://reviews.freebsd.org/D1711 AFFECTED FILES sys/amd64/conf/GENERIC sys/conf/files sys/conf/options sys/kern/kern_testfrwk.c sys/kern/kern_timeout.c sys/modules/Makefile sys/modules/callout_test/Makefile sys/modules/callout_test/callout_test.c sys/sys/callout.h sys/sys/callout_test.h sys/sys/kern_testfrwk.h To: rrs, gnn, rwatson, imp, adrian, sbruno, lstewart, hselasky Cc: neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 21:19:56 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 3D0CDF25 for ; Wed, 28 Jan 2015 21:19:56 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id F2E9099 for ; Wed, 28 Jan 2015 21:19:55 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SLJtp0096896 for ; Wed, 28 Jan 2015 21:19:55 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SLJtCq096894; Wed, 28 Jan 2015 21:19:55 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 21:19:55 +0000 To: freebsd-net@freebsd.org From: "hselasky (Hans Petter Selasky)" Subject: [Differential] [Commented On] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: <4f6927867f192f15826ff36ed897df80@localhost.localdomain> X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTJUns= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 21:19:56 -0000 hselasky added a comment. Did you upload the correct patch? INLINE COMMENTS sys/kern/kern_timeout.c:674 I don't mean inside the if (c_lock != NULL) { } There should be an else case after it. if (c_lock != NULL) { ... } else { /* The callout cannot be stopped now */ cc_exec_cancel(cc, direct) = true; /* XXX this piece is missing */ } Because else callout_stop() will return (1) when cancel() == false, which is a lie. It cannot stop the MPSAFE callout in this case and has to let it run ??? REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, imp, adrian, sbruno, lstewart, hselasky Cc: neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 21:25:32 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id D43BF255 for ; Wed, 28 Jan 2015 21:25:32 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id AC3A41BF for ; Wed, 28 Jan 2015 21:25:32 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SLPWNO004415 for ; Wed, 28 Jan 2015 21:25:32 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SLPWeS004413; Wed, 28 Jan 2015 21:25:32 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 21:25:32 +0000 To: freebsd-net@freebsd.org From: "delphij (Xin Li)" Subject: [Differential] [Changed Subscribers] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: <8e4a58861d2e74bffbcdc98f8b4f8c21@localhost.localdomain> X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTJU8w= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 21:25:32 -0000 delphij added a subscriber: delphij. REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, imp, adrian, sbruno, lstewart, hselasky Cc: delphij, neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 22:58:57 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id A768D893 for ; Wed, 28 Jan 2015 22:58:57 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 83FCAF1A for ; Wed, 28 Jan 2015 22:58:57 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SMwvD0072217 for ; Wed, 28 Jan 2015 22:58:57 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SMwv8u072216; Wed, 28 Jan 2015 22:58:57 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 22:58:57 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1643: Implement resetting a VF Message-ID: X-Priority: 3 Thread-Topic: D1643: Implement resetting a VF X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: MDJmMjIzMGI5NWVmMGNmNjI3NTcwNmNhOWQ0IFTJabE= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 22:58:57 -0000 jfvogel accepted this revision. jfvogel added a comment. This revision is now accepted and ready to land. See no problems. REVISION DETAIL https://reviews.freebsd.org/D1643 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 23:00:42 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id ECB40A66 for ; Wed, 28 Jan 2015 23:00:42 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id CE4F1FCC for ; Wed, 28 Jan 2015 23:00:42 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SN0gB8075004 for ; Wed, 28 Jan 2015 23:00:42 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SN0ghD075003; Wed, 28 Jan 2015 23:00:42 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 23:00:42 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1642: Implement PCI SR-IOV method to initialize individual VFs Message-ID: X-Priority: 3 Thread-Topic: D1642: Implement PCI SR-IOV method to initialize individual VFs X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: ZmZlNzY0OTVkYmNlM2JkOWFhZWQ3MjBhMjA1IFTJaho= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 23:00:43 -0000 jfvogel accepted this revision. This revision is now accepted and ready to land. BRANCH review_D1642 REVISION DETAIL https://reviews.freebsd.org/D1642 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 23:02:20 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 48180B0E for ; Wed, 28 Jan 2015 23:02:20 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 298FDFE3 for ; Wed, 28 Jan 2015 23:02:20 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SN2Jtf077328 for ; Wed, 28 Jan 2015 23:02:19 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SN2JoM077327; Wed, 28 Jan 2015 23:02:19 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 23:02:19 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1641: Implement PCI SR-IOV initialization methods Message-ID: X-Priority: 3 Thread-Topic: D1641: Implement PCI SR-IOV initialization methods X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: ZWFiODdhYWU0YTRhNWFiMzk2YmRlMzA0YTZlIFTJans= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 23:02:20 -0000 jfvogel accepted this revision. jfvogel added a comment. This revision is now accepted and ready to land. Don't see any issues, of course the proof will come in the actual use when we have the infrastructure :) BRANCH review_D1641 REVISION DETAIL https://reviews.freebsd.org/D1641 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 23:04:15 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 3F6ABBB4 for ; Wed, 28 Jan 2015 23:04:15 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 20816FF7 for ; Wed, 28 Jan 2015 23:04:15 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SN4ENK079000 for ; Wed, 28 Jan 2015 23:04:14 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SN4EDk078999; Wed, 28 Jan 2015 23:04:14 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 23:04:14 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1644: Add infrastructure for handling the VC msg channel from VFs Message-ID: <5bda65d023501569516ad83a1ca53f74@localhost.localdomain> X-Priority: 3 Thread-Topic: D1644: Add infrastructure for handling the VC msg channel from VFs X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: NWFiMWUzZDU0ODgxNGJiOTVkN2EzZDdiZjI3IFTJau4= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 23:04:15 -0000 jfvogel accepted this revision. jfvogel added a comment. This revision is now accepted and ready to land. Fine REVISION DETAIL https://reviews.freebsd.org/D1644 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 23:13:44 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id DEC2BE78 for ; Wed, 28 Jan 2015 23:13:44 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id BBDDA17A for ; Wed, 28 Jan 2015 23:13:44 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SNDiB5088791 for ; Wed, 28 Jan 2015 23:13:44 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SNDiNo088790; Wed, 28 Jan 2015 23:13:44 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 23:13:44 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1645: Add support for VERSION VC message Message-ID: <1f31bd36b5dc73e6f07063fbb6b890ea@localhost.localdomain> X-Priority: 3 Thread-Topic: D1645: Add support for VERSION VC message X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: MjYzNzUyNDQxYTA3Y2RhZGM3M2FmMDUwYmQwIFTJbSg= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 23:13:45 -0000 jfvogel accepted this revision. This revision is now accepted and ready to land. REVISION DETAIL https://reviews.freebsd.org/D1645 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 23:52:40 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 5DB71992 for ; Wed, 28 Jan 2015 23:52:40 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 3DE05797 for ; Wed, 28 Jan 2015 23:52:40 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SNqdIN042594 for ; Wed, 28 Jan 2015 23:52:39 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SNqdrS042593; Wed, 28 Jan 2015 23:52:39 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 23:52:39 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1646: Add support for RESET_VF VC message Message-ID: <716f5d2addb3baeb14381470738759f4@localhost.localdomain> X-Priority: 3 Thread-Topic: D1646: Add support for RESET_VF VC message X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: ZTA1MzIxZDNjN2MzMDRiYzg0ZWYwMDZjYmQwIFTJdkc= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 23:52:40 -0000 jfvogel accepted this revision. This revision is now accepted and ready to land. REVISION DETAIL https://reviews.freebsd.org/D1646 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 23:54:26 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 79591A47 for ; Wed, 28 Jan 2015 23:54:26 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 586F57AE for ; Wed, 28 Jan 2015 23:54:26 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SNsQED043919 for ; Wed, 28 Jan 2015 23:54:26 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SNsQkU043918; Wed, 28 Jan 2015 23:54:26 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 23:54:26 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1647: Add support for GET_VF_RESOURCES VC message Message-ID: <1a5338612074258d5e6ce1589522d784@localhost.localdomain> X-Priority: 3 Thread-Topic: D1647: Add support for GET_VF_RESOURCES VC message X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: YmFkOTJjNjIzYWI1MTUxNDE0ZGM3MmQ2MTc0IFTJdrI= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 23:54:26 -0000 jfvogel accepted this revision. jfvogel added a comment. This revision is now accepted and ready to land. seems fine REVISION DETAIL https://reviews.freebsd.org/D1647 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Wed Jan 28 23:59:43 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 94154B36 for ; Wed, 28 Jan 2015 23:59:43 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 75BD47DC for ; Wed, 28 Jan 2015 23:59:43 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0SNxhNE048183 for ; Wed, 28 Jan 2015 23:59:43 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0SNxh34048182; Wed, 28 Jan 2015 23:59:43 GMT (envelope-from mat) Date: Wed, 28 Jan 2015 23:59:43 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Requested Changes To] D1648: Add stubs for deprecated VC messages Message-ID: <343520ceb86776d9b4cd47f37fb8189b@localhost.localdomain> X-Priority: 3 Thread-Topic: D1648: Add stubs for deprecated VC messages X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2MyNjI4YjVjODUwMDVhYzYxNTNkMjEyYzRlIFTJd+8= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Jan 2015 23:59:43 -0000 jfvogel requested changes to this revision. jfvogel added a comment. This revision now requires changes to proceed. Let's not mention Linux in our comments, either say nothing or think of something else :) REVISION DETAIL https://reviews.freebsd.org/D1648 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 00:15:14 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 62F05235 for ; Thu, 29 Jan 2015 00:15:14 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 4432B9AF for ; Thu, 29 Jan 2015 00:15:14 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T0FDtA062487 for ; Thu, 29 Jan 2015 00:15:13 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T0FDmR062486; Thu, 29 Jan 2015 00:15:13 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 00:15:13 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1649: Add support for CONFIG_VSI_QUEUES VC message Message-ID: <6700c289472cc4efe0c00a9f4903d7fe@localhost.localdomain> X-Priority: 3 Thread-Topic: D1649: Add support for CONFIG_VSI_QUEUES VC message X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: NzBjMzdhMjA1NGRjOGJkMTFiY2ViZGYyMDRkIFTJe5E= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 00:15:14 -0000 jfvogel accepted this revision. jfvogel added a comment. This revision is now accepted and ready to land. Don't see any problems. REVISION DETAIL https://reviews.freebsd.org/D1649 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 00:20:30 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id AC5F53A6 for ; Thu, 29 Jan 2015 00:20:30 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 8E53D9F2 for ; Thu, 29 Jan 2015 00:20:30 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T0KU5u066608 for ; Thu, 29 Jan 2015 00:20:30 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T0KULR066603; Thu, 29 Jan 2015 00:20:30 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 00:20:30 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1650: Add support for CONFIG_IRQ_MAP VC message Message-ID: <07c0061ebf267523b09ae7829684c6e9@localhost.localdomain> X-Priority: 3 Thread-Topic: D1650: Add support for CONFIG_IRQ_MAP VC message X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: OGIzNWI2MTYxYWRjMTI0NjU4YTJkZTYwY2Q2IFTJfM4= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 00:20:30 -0000 jfvogel accepted this revision. This revision is now accepted and ready to land. REVISION DETAIL https://reviews.freebsd.org/D1650 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 00:21:16 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 662E843D for ; Thu, 29 Jan 2015 00:21:16 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 4826FA04 for ; Thu, 29 Jan 2015 00:21:16 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T0LG4n069423 for ; Thu, 29 Jan 2015 00:21:16 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T0LGZN069422; Thu, 29 Jan 2015 00:21:16 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 00:21:16 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1651: Add support for ENABLE/DISABLE_QUEUES VC messages Message-ID: <0ce26d5da963332cd6459b008bb29855@localhost.localdomain> X-Priority: 3 Thread-Topic: D1651: Add support for ENABLE/DISABLE_QUEUES VC messages X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: NzRiMTE2MzFlMGU1Yzg4ZDYyZDE0NWY0ZTZlIFTJfPw= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 00:21:16 -0000 jfvogel accepted this revision. This revision is now accepted and ready to land. REVISION DETAIL https://reviews.freebsd.org/D1651 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 00:23:23 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 586BC509 for ; Thu, 29 Jan 2015 00:23:23 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 39EAAAB4 for ; Thu, 29 Jan 2015 00:23:23 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T0NMFv084292 for ; Thu, 29 Jan 2015 00:23:22 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T0NMfC084291; Thu, 29 Jan 2015 00:23:22 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 00:23:22 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1652: Add support for ADD/DEL_ETHER_ADDRESS VC messages Message-ID: X-Priority: 3 Thread-Topic: D1652: Add support for ADD/DEL_ETHER_ADDRESS VC messages X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: MzM5Y2U0ZjQwMTJmYWViOTFkMDMyZmM4NGIzIFTJfXo= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 00:23:23 -0000 jfvogel accepted this revision. jfvogel added a comment. This revision is now accepted and ready to land. Good. BRANCH review_D1652 REVISION DETAIL https://reviews.freebsd.org/D1652 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 00:54:12 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 2059BCF7 for ; Thu, 29 Jan 2015 00:54:12 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id F292DD79 for ; Thu, 29 Jan 2015 00:54:11 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T0sBvU016990 for ; Thu, 29 Jan 2015 00:54:11 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T0sB0Q016987; Thu, 29 Jan 2015 00:54:11 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 00:54:11 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1653: Add support for ADD/DEL_VLAN VC messages Message-ID: <67789c37d0dcb6f46e7b368e13e9975d@localhost.localdomain> X-Priority: 3 Thread-Topic: D1653: Add support for ADD/DEL_VLAN VC messages X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2ZkZmUyNmRjYTBlOGYyYTlmNjY4MTQyOTZlIFTJhLM= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 00:54:12 -0000 jfvogel accepted this revision. jfvogel added a comment. This revision is now accepted and ready to land. No issues. REVISION DETAIL https://reviews.freebsd.org/D1653 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 00:59:35 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 626ADF6 for ; Thu, 29 Jan 2015 00:59:35 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 42E3EDC9 for ; Thu, 29 Jan 2015 00:59:35 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T0xY6g021568 for ; Thu, 29 Jan 2015 00:59:34 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T0xY9C021567; Thu, 29 Jan 2015 00:59:34 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 00:59:34 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1654: Add support for CONFIG_PROMISCUOUS_MODE VC message Message-ID: <2fb85519fb4472855206162e1c9f0eb9@localhost.localdomain> X-Priority: 3 Thread-Topic: D1654: Add support for CONFIG_PROMISCUOUS_MODE VC message X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: ODZlMGNmMmIwNjllNDI3NzNjZDY5MDBlOTFhIFTJhfY= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 00:59:35 -0000 jfvogel accepted this revision. jfvogel added a comment. This revision is now accepted and ready to land. No problems REVISION DETAIL https://reviews.freebsd.org/D1654 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 01:02:20 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 81461291 for ; Thu, 29 Jan 2015 01:02:20 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 6331AE8B for ; Thu, 29 Jan 2015 01:02:20 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T12Kt0026471 for ; Thu, 29 Jan 2015 01:02:20 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T12Kvn026470; Thu, 29 Jan 2015 01:02:20 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 01:02:20 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1655: Add support for GET_STATS VC message Message-ID: X-Priority: 3 Thread-Topic: D1655: Add support for GET_STATS VC message X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: M2VlZmI5Nzk5ZGE5MDQ2YzE4OWMyZjdiMDU1IFTJhpw= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 01:02:20 -0000 jfvogel accepted this revision. This revision is now accepted and ready to land. BRANCH review_D1655 REVISION DETAIL https://reviews.freebsd.org/D1655 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 01:06:13 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 0D44D3D4 for ; Thu, 29 Jan 2015 01:06:13 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id E3964EBC for ; Thu, 29 Jan 2015 01:06:12 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T16CB3029422 for ; Thu, 29 Jan 2015 01:06:12 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T16CE5029421; Thu, 29 Jan 2015 01:06:12 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 01:06:12 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1656: Handle VFLR events from VFs Message-ID: <5eb7b070e1164731e2f26299c7fa8762@localhost.localdomain> X-Priority: 3 Thread-Topic: D1656: Handle VFLR events from VFs X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: MjAxYmVkMTcyNjY3NDZhMmYxYWVkM2NmMGRiIFTJh4Q= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 01:06:13 -0000 jfvogel accepted this revision. jfvogel added a comment. This revision is now accepted and ready to land. Looks good. Again, will need real world testing when we have infrastructure. REVISION DETAIL https://reviews.freebsd.org/D1656 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 01:08:21 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id DDEF148A for ; Thu, 29 Jan 2015 01:08:21 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id BF9E3ED7 for ; Thu, 29 Jan 2015 01:08:21 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T18LNA031272 for ; Thu, 29 Jan 2015 01:08:21 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T18L2v031271; Thu, 29 Jan 2015 01:08:21 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 01:08:21 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1657: Allow VFs to run while the PF is admin down Message-ID: X-Priority: 3 Thread-Topic: D1657: Allow VFs to run while the PF is admin down X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2EyNmJlZTU5MWYxMjQxNTNiNmRlMzQzYjQxIFTJiAU= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 01:08:22 -0000 jfvogel accepted this revision. This revision is now accepted and ready to land. BRANCH review_D1657 REVISION DETAIL https://reviews.freebsd.org/D1657 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 01:11:18 2015 Return-Path: Delivered-To: net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 7505755A for ; Thu, 29 Jan 2015 01:11:18 +0000 (UTC) Received: from mail-oi0-f45.google.com (mail-oi0-f45.google.com [209.85.218.45]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 3D1E7F89 for ; Thu, 29 Jan 2015 01:11:17 +0000 (UTC) Received: by mail-oi0-f45.google.com with SMTP id g201so21964185oib.4 for ; Wed, 28 Jan 2015 17:11:10 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:from:content-type:subject:date:message-id:cc:to :mime-version; bh=/1XcOL1X5GABBy8GTAI8G/5kdhUI9ToOnGyvFq1qWoo=; b=IBfB5ZuPbV87roy3XCa8nQz7YflY3pa4DocsbcIlt/S6L0exDo+OvAmrAIHfwG70ae CHfjgmq/QJfSdkWY5PF7e3H3ft8CvoX9tMDY5rWWah63kXqBCyem9/p1fe0kF29NYzkM Vy2aq7L8K+9dSt/CdY2EXFYFA8jcAB3qQnSgrYL0oNM7vb6D1PPGDf93/ERV9PEU5xQZ C7fJpao6JRUrNH4wGZ1ylEYJLD6MjiBvP3r4tQ1eQK1/MdpfOWNaRVI4cxpOsshsTBDO WwDcXrbrB/XRhPhfdgnmWMQJNykIKQVtGRVlzGTkyBItaa3ly9rtYFFMiNp4/01npWw4 S5Dw== X-Gm-Message-State: ALoCoQm9zNLH1eLQjGIWR4ziyHHyiRPyOCsFHUxzgn2mf/FvPHqX6RGWvDUNRHO+czjWZCct8k2z X-Received: by 10.60.57.42 with SMTP id f10mr4003607oeq.29.1422493870881; Wed, 28 Jan 2015 17:11:10 -0800 (PST) Received: from [10.0.1.4] (werc-dhcp-1949.tamu.edu. [165.91.215.157]) by mx.google.com with ESMTPSA id cr2sm3006174oec.15.2015.01.28.17.11.09 (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Wed, 28 Jan 2015 17:11:09 -0800 (PST) From: Luke McHale Subject: Netmap support for Linux Containers (veth) Date: Wed, 28 Jan 2015 19:11:08 -0600 Message-Id: <1FDC0E90-F9A3-457D-B5CC-640FF66BB48F@tamu.edu> To: net@freebsd.org Mime-Version: 1.0 (Mac OS X Mail 8.1 \(1993\)) X-Mailer: Apple Mail (2.1993) Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: rizzo@iet.unipi.it X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 01:11:18 -0000 Hello Dr. Luigi Rizzo and netmap contributors, I am looking to integrate netmap capabilities into linux=E2=80=99s veth = (Virtual Ethernet device) for netmap support within linux containers. = Does a patch currently exist? If not, do you have any intuition as to = what it would take to add netmap capability? I am new to the netmap = framework and I would appreciate any help you can provide toward = patching veth for netmap. http://lxr.free-electrons.com/source/drivers/net/veth.c = Thank you, Luke McHale= From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 01:20:29 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 736F46A8 for ; Thu, 29 Jan 2015 01:20:29 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 515AFFED for ; Thu, 29 Jan 2015 01:20:29 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T1KSvr043931 for ; Thu, 29 Jan 2015 01:20:28 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T1KS2P043930; Thu, 29 Jan 2015 01:20:28 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 01:20:28 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1658: Add sysctls for per-VF hardware counters Message-ID: <1f710d6ca2c12769efe5723d47df3d07@localhost.localdomain> X-Priority: 3 Thread-Topic: D1658: Add sysctls for per-VF hardware counters X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: OWE0YzQwMmZkYjZmN2FjNjA4MWQ1MGYxZmY1IFTJitw= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 01:20:29 -0000 jfvogel accepted this revision. This revision is now accepted and ready to land. BRANCH review_D1658 REVISION DETAIL https://reviews.freebsd.org/D1658 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 01:21:19 2015 Return-Path: Delivered-To: net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 250AB744 for ; Thu, 29 Jan 2015 01:21:19 +0000 (UTC) Received: from mail-lb0-x22c.google.com (mail-lb0-x22c.google.com [IPv6:2a00:1450:4010:c04::22c]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 99B68F8 for ; Thu, 29 Jan 2015 01:21:18 +0000 (UTC) Received: by mail-lb0-f172.google.com with SMTP id l4so23117875lbv.3 for ; Wed, 28 Jan 2015 17:21:16 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date:message-id:subject :from:to:cc:content-type:content-transfer-encoding; bh=RZG8Twm1pQ6144lI6yxPds0Hx1FsMwroUZJQhYjarZ8=; b=Q9PuRuEfDladqtnpfLmcHCo3ITeWUK9Vjef8PevCYvDtynzglvBigcR2KgP94H5JcE SQ4qnwtLkNwVQSlv/hQvw/WBbboUsfcpREOG/XZUMFb108HaR/fX88520uTQ1hCnfl1T k+x+SsDqRQjMfEQj0QEFr0EFcUa9S4MTnB955wM/Wz1HxR2xP0Qw1yNRrr5DsRJcwYoX F5fRM8irszEx8gioLv40TecgqOfaQcseuLZbjQ5N0rfSdPkCAHacfyhw+vEIDi5aVzwR MeqphWPBLcfDo2APVODY4wra+YTFVrZGK2fdL+ayZ3HJm6ga6fy/HLuzA9se9xASDQQg KGOg== MIME-Version: 1.0 X-Received: by 10.112.12.134 with SMTP id y6mr11678737lbb.34.1422494476698; Wed, 28 Jan 2015 17:21:16 -0800 (PST) Sender: rizzo.unipi@gmail.com Received: by 10.114.19.206 with HTTP; Wed, 28 Jan 2015 17:21:16 -0800 (PST) In-Reply-To: <1FDC0E90-F9A3-457D-B5CC-640FF66BB48F@tamu.edu> References: <1FDC0E90-F9A3-457D-B5CC-640FF66BB48F@tamu.edu> Date: Wed, 28 Jan 2015 17:21:16 -0800 X-Google-Sender-Auth: PVq26h-8mRNMcJBGXnvojKZ_ask Message-ID: Subject: Re: Netmap support for Linux Containers (veth) From: Luigi Rizzo To: Luke McHale Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Cc: "freebsd-net@freebsd.org" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 01:21:19 -0000 On Wed, Jan 28, 2015 at 5:11 PM, Luke McHale wrote: > Hello Dr. Luigi Rizzo and netmap contributors, > > I am looking to integrate netmap capabilities into linux=E2=80=99s veth (= Virtual > Ethernet device) for netmap support within linux containers. Does a patc= h > currently exist? If not, do you have any intuition as to what it would t= ake > to add netmap capability? I am new to the netmap framework and I would > appreciate any help you can provide toward patching veth for netmap. > we do have an initial version of netmap support for veth (Linux; in FreeBSD would be epair), Hopefully we will be able to complete and distribute the veth code shortly. If you are not familiar with netmap internals it may be easier to wait for our code than start developing your own. As a temporary workaround you can surely use VALE switches or netmap pipes to connect different containers. cheers luigi From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 01:25:00 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 4E26789C for ; Thu, 29 Jan 2015 01:25:00 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 2F64B125 for ; Thu, 29 Jan 2015 01:25:00 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T1OxVJ049869 for ; Thu, 29 Jan 2015 01:24:59 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T1OxOA049868; Thu, 29 Jan 2015 01:24:59 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 01:24:59 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1659: Register ixl as an SR-IOV-capable driver during attach Message-ID: <78c9c364fb8f92a0242d937daed859b9@localhost.localdomain> X-Priority: 3 Thread-Topic: D1659: Register ixl as an SR-IOV-capable driver during attach X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: MWEzYTlmNjM0ZjU1ZjZiMTRhYzdkZDlmYjZkIFTJi+s= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 01:25:00 -0000 jfvogel accepted this revision. jfvogel added a comment. This revision is now accepted and ready to land. can't wait to see the infrastructure in place :) REVISION DETAIL https://reviews.freebsd.org/D1659 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 01:25:56 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 41F8C95F for ; Thu, 29 Jan 2015 01:25:56 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 23F6C15C for ; Thu, 29 Jan 2015 01:25:56 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T1PtsT050659 for ; Thu, 29 Jan 2015 01:25:55 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T1Ptpl050658; Thu, 29 Jan 2015 01:25:55 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 01:25:55 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1660: Add support for mac-addr parameter Message-ID: X-Priority: 3 Thread-Topic: D1660: Add support for mac-addr parameter X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: ZWE5ZGNjNWRmODc2N2E5NGNhNGQwMTExOWMxIFTJjCM= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 01:25:56 -0000 jfvogel accepted this revision. This revision is now accepted and ready to land. REVISION DETAIL https://reviews.freebsd.org/D1660 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 01:27:25 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 3183BB51 for ; Thu, 29 Jan 2015 01:27:25 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 13C9A17E for ; Thu, 29 Jan 2015 01:27:25 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T1RORW051790 for ; Thu, 29 Jan 2015 01:27:24 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T1RO4u051789; Thu, 29 Jan 2015 01:27:24 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 01:27:24 +0000 To: freebsd-net@freebsd.org From: "jfvogel (Jack Vogel)" Subject: [Differential] [Accepted] D1661: Add some security-related config parameters Message-ID: X-Priority: 3 Thread-Topic: D1661: Add some security-related config parameters X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: MjUxNWUxN2JmMmRmYzQ5MzQyZmZlNzZlOTY2IFTJjHw= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 01:27:25 -0000 jfvogel accepted this revision. This revision is now accepted and ready to land. REVISION DETAIL https://reviews.freebsd.org/D1661 To: rstone, jfvogel Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 01:48:48 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id A7D14F1C for ; Thu, 29 Jan 2015 01:48:48 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 816F73F4 for ; Thu, 29 Jan 2015 01:48:48 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T1mmDq074175 for ; Thu, 29 Jan 2015 01:48:48 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T1mmgL074174; Thu, 29 Jan 2015 01:48:48 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 01:48:48 +0000 To: freebsd-net@freebsd.org From: "imp (Warner Losh)" Subject: [Differential] [Updated] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: <2bb3e330c245394280ea27e0c697c9c7@localhost.localdomain> X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTJkYA= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 01:48:48 -0000 imp added a comment. For the commit, I'd separate out the timeout fix from the kernel testframework. REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, adrian, sbruno, lstewart, hselasky, imp Cc: delphij, neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 02:17:45 2015 Return-Path: Delivered-To: net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 532BC8CD for ; Thu, 29 Jan 2015 02:17:45 +0000 (UTC) Received: from mail-oi0-f43.google.com (mail-oi0-f43.google.com [209.85.218.43]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 19021993 for ; Thu, 29 Jan 2015 02:17:44 +0000 (UTC) Received: by mail-oi0-f43.google.com with SMTP id z81so22407184oif.2 for ; Wed, 28 Jan 2015 18:17:43 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:content-type:mime-version:subject:from :in-reply-to:date:cc:content-transfer-encoding:message-id:references :to; bh=Nr0HkZcgqxvk7FB3KCu/vHalLNrINcE9Y469Ypk2Zkk=; b=ZGpwZRyF88alXS/MbO8vdbUXZzAwy6Wxh3EWMDaE8lkTyzeq65j/1dSu49s/79gJLY xYNO+E7WI6tVoCuPAL3+XGf70h+LYCDmLnkYoGuxFa9qzkJJClOjkHjbKOTD8wZg4kiO cXYvXZHDOt8I7KFlh8jHJkpSeQQlyO4EDgVS/otrMIFlYaco/h885UTY3dHnKwGSAXqv VNXh0lKmv5ybWuCfZoKRiU2X48ISN2r0/g/RgNUImEawDnObxR8MbY4agFiCH0A2ps5a Rtn2/CQX/IXlG6YLfx3XURQXG/V7qY83DjNpbn0KjjFAZSYTnNwiZZKodlMBmmIIWG/7 gBew== X-Gm-Message-State: ALoCoQmzHR6YM4U7IbCJGjCIUOEDIOU1YD9U+jWooqoCVmO3nVTclB6+sPe+zljENZgaiJ6zPN93 X-Received: by 10.60.145.145 with SMTP id su17mr980731oeb.59.1422497863529; Wed, 28 Jan 2015 18:17:43 -0800 (PST) Received: from [10.0.1.4] (werc-dhcp-1949.tamu.edu. [165.91.215.157]) by mx.google.com with ESMTPSA id ur1sm3189137obc.3.2015.01.28.18.17.42 (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Wed, 28 Jan 2015 18:17:42 -0800 (PST) Content-Type: text/plain; charset=utf-8 Mime-Version: 1.0 (Mac OS X Mail 8.1 \(1993\)) Subject: Re: Netmap support for Linux Containers (veth) From: Luke McHale In-Reply-To: Date: Wed, 28 Jan 2015 20:17:40 -0600 Content-Transfer-Encoding: quoted-printable Message-Id: <21E9D568-F421-4BFD-90B7-656A36475091@tamu.edu> References: <1FDC0E90-F9A3-457D-B5CC-640FF66BB48F@tamu.edu> To: Luigi Rizzo X-Mailer: Apple Mail (2.1993) Cc: net@freebsd.org X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 02:17:45 -0000 Hello Dr. Luigi Rizzo, Thank you for your quick reply! I=E2=80=99m glad to see veth is already = in the works. While I am new to netmap, we are aiming to utilize it in = several of our projects. I currently have two tasks, including: - patch veth - patch eTSEC (gianfar) controller Since these tasks are gating our current work, we would really = appreciate any insight/pointers you may have and if possible, access to = a repository with preliminary veth modifications. Any assistance you = can provide in jump-starting our efforts would be greatly appreciated! Thank you, Luke > On Jan 28, 2015, at 7:21 PM, Luigi Rizzo wrote: >=20 > On Wed, Jan 28, 2015 at 5:11 PM, Luke McHale wrote: >> Hello Dr. Luigi Rizzo and netmap contributors, >>=20 >> I am looking to integrate netmap capabilities into linux=E2=80=99s = veth (Virtual >> Ethernet device) for netmap support within linux containers. Does a = patch >> currently exist? If not, do you have any intuition as to what it = would take >> to add netmap capability? I am new to the netmap framework and I = would >> appreciate any help you can provide toward patching veth for netmap. >>=20 >=20 > we do have an initial version of netmap support for veth (Linux; in > FreeBSD would be epair), >=20 >=20 > Hopefully we will be able to complete and distribute the veth code = shortly. >=20 > If you are not familiar with netmap internals it may be easier to wait > for our code than start developing your own. >=20 > As a temporary workaround you can surely use VALE switches or > netmap pipes to connect different containers. >=20 > cheers > luigi From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 02:23:44 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id A69A4B3C for ; Thu, 29 Jan 2015 02:23:44 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 67DC6A6E for ; Thu, 29 Jan 2015 02:23:44 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T2NivJ011765 for ; Thu, 29 Jan 2015 02:23:44 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T2NiOG011764; Thu, 29 Jan 2015 02:23:44 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 02:23:44 +0000 To: freebsd-net@freebsd.org From: "rrs (Randall Stewart)" Subject: [Differential] [Commented On] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: <03037b55642e637b0123a296025a5ab8@localhost.localdomain> X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTJmbA= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 02:23:44 -0000 rrs added a comment. Hans: We have discussed that, and *no* it will *not* return the incorrect thing once it can't be stopped. There is code in the callout_reset_sbt_on() that makes sure zero is returned. The only way that zero will *not* be returned is if the PENDING flag is set. That won't happen if the callout is the one waiting on a lock. So the answer will be 0, and the new callout will be scheduled at the end of the current one. However if before that can return (the callout) yes you will get a 1, since the rescheduled callout from the first one that set the migration will see the subsequent migration flag and return one since that *was* rescheduled. The exec_cancel flag is only valid or looked at in the case where the lock is set on the callout. REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, adrian, sbruno, lstewart, hselasky, imp Cc: delphij, neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 03:50:09 2015 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id B5C6CA9C for ; Thu, 29 Jan 2015 03:50:09 +0000 (UTC) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 9CF3B6BD for ; Thu, 29 Jan 2015 03:50:09 +0000 (UTC) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T3o94q052625 for ; Thu, 29 Jan 2015 03:50:09 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 137089] [lagg] lagg falsely triggers IPv6 duplicate address detection Date: Thu, 29 Jan 2015 03:50:09 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: unspecified X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: hiren@FreeBSD.org X-Bugzilla-Status: In Progress X-Bugzilla-Priority: Normal X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: cc Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 03:50:09 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=137089 Hiren Panchasara changed: What |Removed |Added ---------------------------------------------------------------------------- CC| |hiren@FreeBSD.org --- Comment #2 from Hiren Panchasara --- Is this still an issue? Is anybody running into this? -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 04:10:42 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 45951D81 for ; Thu, 29 Jan 2015 04:10:42 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 1F3AE853 for ; Thu, 29 Jan 2015 04:10:42 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T4Af2R020272 for ; Thu, 29 Jan 2015 04:10:41 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T4AfHn020271; Thu, 29 Jan 2015 04:10:41 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 04:10:41 +0000 To: freebsd-net@freebsd.org From: "emaste (Ed Maste)" Subject: [Differential] [Changed Subscribers] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTJssE= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 04:10:42 -0000 emaste added a subscriber: emaste. REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, adrian, sbruno, lstewart, hselasky, imp Cc: emaste, delphij, neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 07:29:32 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 516C3D8D for ; Thu, 29 Jan 2015 07:29:32 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 2A412BDE for ; Thu, 29 Jan 2015 07:29:32 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T7TV1X072573 for ; Thu, 29 Jan 2015 07:29:31 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0T7TV0j072572; Thu, 29 Jan 2015 07:29:31 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 07:29:31 +0000 To: freebsd-net@freebsd.org From: "hselasky (Hans Petter Selasky)" Subject: [Differential] [Accepted] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: <8b7aeb3cf87ddec73fefae9dcac4178c@localhost.localdomain> X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTJ4Vs= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 07:29:32 -0000 hselasky accepted this revision. hselasky added a comment. This revision is now accepted and ready to land. This looks usable. REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, adrian, sbruno, lstewart, imp, hselasky Cc: emaste, delphij, neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 08:54:10 2015 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 67125CC2 for ; Thu, 29 Jan 2015 08:54:10 +0000 (UTC) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 4EA6D823 for ; Thu, 29 Jan 2015 08:54:10 +0000 (UTC) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.14.9/8.14.9) with ESMTP id t0T8sASs046300 for ; Thu, 29 Jan 2015 08:54:10 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 137089] [lagg] lagg falsely triggers IPv6 duplicate address detection Date: Thu, 29 Jan 2015 08:54:10 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: unspecified X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: xelah-freebsdpr@xelah.com X-Bugzilla-Status: In Progress X-Bugzilla-Priority: Normal X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 08:54:10 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=137089 --- Comment #3 from xelah-freebsdpr@xelah.com --- (In reply to Hiren Panchasara from comment #2) The servers involved have long since been retired, so I no longer have a way to test if it still happens. -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 09:48:22 2015 Return-Path: Delivered-To: net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id C1BDAE09 for ; Thu, 29 Jan 2015 09:48:22 +0000 (UTC) Received: from mail-wi0-x230.google.com (mail-wi0-x230.google.com [IPv6:2a00:1450:400c:c05::230]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 3423DDDB for ; Thu, 29 Jan 2015 09:48:22 +0000 (UTC) Received: by mail-wi0-f176.google.com with SMTP id bs8so15045312wib.3 for ; Thu, 29 Jan 2015 01:48:19 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=message-id:date:from:user-agent:mime-version:cc:subject:references :in-reply-to:content-type:content-transfer-encoding; bh=ZVlSEHhp9oCBNn4l3fjN8iFlyRivtaJOkGP+oEeXcqc=; b=KYMwqjb+2ySDgDBxQNFAxx19OC65PrJ2rx2iIZl95LVhLfbvF8hFn5zZLGiYcgBrrw Un2Wj+6vBlXEqg8Z/0lUzn4smRKl4ErpEb1Yl9Mf6v5j5uOjBMSE7hRrxbc1692KikYb mpVJV4nkxh22UjrSBdf9hIikY3QwPibC+hAnwjdG9fA69ZDGjPEWAa0wJvkx5zewTTzQ KC7C+9OAFSjg9qUpato7lGp7Y0ZJdtCS1wCjqq20ByViOiG1KJz640MywCltTxc0QTvZ SBu//DLP5Mng2psQsYqsjgTG3Jdx8HUviR7TuAtQry9stwZjkd0pgQMWYTGQeNFoglp0 aNLg== X-Received: by 10.194.170.161 with SMTP id an1mr16031683wjc.126.1422524899207; Thu, 29 Jan 2015 01:48:19 -0800 (PST) Received: from t510.bsoft-company.ro (remote.ezwim.com. [193.239.202.173]) by mx.google.com with ESMTPSA id v7sm1729605wib.5.2015.01.29.01.48.18 for (version=TLSv1.2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Thu, 29 Jan 2015 01:48:18 -0800 (PST) Message-ID: <54CA01E2.2040404@gmail.com> Date: Thu, 29 Jan 2015 10:48:18 +0100 From: Andrei Brezan User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:31.0) Gecko/20100101 Thunderbird/31.4.0 MIME-Version: 1.0 Subject: Re: IPSEC MTU routing issue References: <54BFB4B5.3070705@gmail.com> <20150123141337.GA13989@zeninc.net> In-Reply-To: <20150123141337.GA13989@zeninc.net> Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit Cc: net@freebsd.org X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 09:48:22 -0000 On 01/23/15 15:13, VANHULLEBUS Yvan wrote: > Hi. > > On Wed, Jan 21, 2015 at 03:16:21PM +0100, Andrei Brezan wrote: >> Weird subject, maybe. >> >> I'm running FreeBSD-10.0-RELEASE with PF as firewall and racoon for >> IPSEC. The IPSEC tunnel is between the FreeBSD box and a Fortinet >> appliance. >> >> The IPSEC tunnel comes up and on a quick test it seems to be >> working, icmp between networks is ok, you can successfully telnet on >> services on the other side. However when you need to transfer some >> data strange things happen. I'm really trying to wrap my head around >> it and I still don't understand why it happens >> (http://pastebin.com/NAspcM9w). The packets smaller than 1260 and >> larger than 1417 are delivered to vlan103, the ones in between are >> not. > > I'm not sure why do you have this strange issue. > Having a look at your IPsec/ESP related kernel stats may give a first > idea. > > > But I know that, even if you find a fix for this, you'll have very > poor performances as soon as packets start to be fragmented, and your > data transferts may just stall forever. > > So, the usual way of solving that is to change the TCPMSS "low enough" > on the fly for all IPsec related trafic. > 1300 is a common value, low enough to avoid fragmentation, and high > enough to keep good throughput. > > Of course, this will only works for TCP, but most big packets / long > flows are done on TCP. > Thanks Yvan, The ICMP started working at some point, most likely when I changed something in my config or the other side did, wasn't able to identify it. I still had the issues specified in this thread https://forums.freebsd.org/threads/ipsec-racoon-gif-packet-routing-issues-transfer-stall-fail.50085/ I managed to resolve the problems with an update from Release 10.0 to 10.1 -- Andrei From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 10:51:36 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id ECC6AB5D for ; Thu, 29 Jan 2015 10:51:36 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id AB65374B for ; Thu, 29 Jan 2015 10:51:36 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TApaGv028599 for ; Thu, 29 Jan 2015 10:51:36 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TApaxA028598; Thu, 29 Jan 2015 10:51:36 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 10:51:36 +0000 To: freebsd-net@freebsd.org From: "kostikbel (Konstantin Belousov)" Subject: [Differential] [Changed Subscribers] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTKELg= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 10:51:37 -0000 kostikbel added a subscriber: kostikbel. kostikbel added a comment. Also would be nice to further split the patch into the mechanical change of the cc_exec/cc_migration macros, and the real fix(es). From what I read, the patch is correct, but it is currently noisy, which makes reading harder and less convincing. What about previous Hans' patch ? Is this one a replacement, i.e. is it believed that the same bugs are fixed there without rewriting and without modifying the callout KPI ? INLINE COMMENTS sys/conf/files:3006 The kern_testfrwk.c should be optional, with the possibility to be built as module. I do support the request to split the patch into the callout fix proper and everything else. REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, adrian, sbruno, lstewart, imp, hselasky Cc: kostikbel, emaste, delphij, neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 11:25:28 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 90218251 for ; Thu, 29 Jan 2015 11:25:28 +0000 (UTC) Received: from smtp-out.sentor.se (smtp-out.sentor.se [176.124.225.2]) (using TLSv1 with cipher DHE-RSA-CAMELLIA256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 50B75ADA for ; Thu, 29 Jan 2015 11:25:27 +0000 (UTC) Received: from localhost (localhost [127.0.0.1]) by farmermaggot.shire.sentor.se (Postfix) with ESMTP id 70F61B61D250; Thu, 29 Jan 2015 12:25:25 +0100 (CET) Date: Thu, 29 Jan 2015 12:25:25 +0100 (CET) From: elof2@sentor.se To: freebsd-net Subject: Zerocopy bpf Message-ID: User-Agent: Alpine 2.00 (BSF 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; format=flowed; charset=US-ASCII X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 11:25:28 -0000 Hi! q1) I assume that libpcap has builtin support for checking if sysctl net.bpf.zerocopy_enable is set to 1, and if so uses zerocopy. Correct? q2) This should mean that all normal sniffing tools like tcpdump, tshark, ngrep, argus, etc do NOT need any specific options in order to use zerocopy. Correct? q3) How do I see if zerocopy is used or not? 'netstat -B' don't tell me much, and the tool 'bpfstat' don't seem to exist any more. q4) When activating zerocopy, should I immediately see a performance boost on the machine? (like less drops on a heavily loaded sniffer NIC (running in monitor mode)) /Elof From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 14:58:37 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 4E66CA62 for ; Thu, 29 Jan 2015 14:58:37 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 0C25165B for ; Thu, 29 Jan 2015 14:58:37 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TEwaxH017428 for ; Thu, 29 Jan 2015 14:58:36 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TEwaFO017424; Thu, 29 Jan 2015 14:58:36 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 14:58:36 +0000 To: freebsd-net@freebsd.org From: "jhb (John Baldwin)" Subject: [Differential] [Changed Subscribers] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: <7a833ed117edb84f9e178b55201dff2b@localhost.localdomain> X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTKSpw= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 14:58:37 -0000 jhb added a subscriber: jhb. jhb added a comment. Hmm, I do think the idea of a kernel test framework should be discussed in its own right. I have implemented a much simpler one on my own for unit tests of locking primitives that you can see here. These worked by declaring tests in linker sets in a kernel module. Loading the module implicitly runs the tests. I have other changes in this branch to allow "catching" panics like exceptions and similar changes for witness as well. The test framework (much simpler) can be found at: http://p4db.freebsd.org/fileDownLoad.cgi?FSPC=//depot/user/jhb/lock/kern/subr_test.c&REV=6 http://p4db.freebsd.org/fileDownLoad.cgi?FSPC=//depot/user/jhb/lock/sys/unittest.h&REV=2 Sample test modules can be found here: http://p4db.freebsd.org/depotTreeBrowser.cgi?FSPC=//depot/user/jhb/lock/modules/test&HIDEDEL=NO I think "test" is probably a better name for a subdir of test modules as it is more consistent with what we are doing in userland with kyua. REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, adrian, sbruno, lstewart, imp, hselasky Cc: jhb, kostikbel, emaste, delphij, neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 15:07:23 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 28D66CD6 for ; Thu, 29 Jan 2015 15:07:23 +0000 (UTC) Received: from udns.ultimatedns.net (ultimatedns.net [209.180.214.225]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id F076C7DB for ; Thu, 29 Jan 2015 15:07:22 +0000 (UTC) Received: from ultimatedns.net (localhost [127.0.0.1]) by udns.ultimatedns.net (8.14.9/8.14.9) with ESMTP id t0TF7AeY036698 for ; Thu, 29 Jan 2015 07:07:10 -0800 (PST) (envelope-from bsd-lists@bsdforge.com) To: In-Reply-To: References: From: "Chris H" Subject: Re: Zerocopy bpf Date: Thu, 29 Jan 2015 07:07:10 -0800 Content-Type: text/plain; charset=UTF-8; format=fixed MIME-Version: 1.0 Message-id: <8c11690ac977550b52e3494351a44c78@ultimatedns.net> Content-Transfer-Encoding: 8bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 15:07:23 -0000 On Thu, 29 Jan 2015 12:25:25 +0100 (CET) elof2@sentor.se wrote > Hi! > > q1) > I assume that libpcap has builtin support for checking if sysctl > net.bpf.zerocopy_enable is set to 1, and if so uses zerocopy. > Correct? > > q2) > This should mean that all normal sniffing tools like tcpdump, tshark, > ngrep, argus, etc do NOT need any specific options in order to use > zerocopy. > Correct? > > q3) > How do I see if zerocopy is used or not? 'netstat -B' don't tell me > much, and the tool 'bpfstat' don't seem to exist any more. I can't speak from personal experience to the rest. But as to bpfstat(8); it was merged into netstat(1) ~RELENG_7. --Chris > > q4) > When activating zerocopy, should I immediately see a performance boost on > the machine? (like less drops on a heavily loaded sniffer NIC (running in > monitor mode)) > > /Elof > _______________________________________________ > freebsd-net@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org" From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 15:41:09 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id A57C6BC5 for ; Thu, 29 Jan 2015 15:41:09 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 7E3B8BD9 for ; Thu, 29 Jan 2015 15:41:09 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TFf9vn066563 for ; Thu, 29 Jan 2015 15:41:09 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TFf9Vs066562; Thu, 29 Jan 2015 15:41:09 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 15:41:09 +0000 To: freebsd-net@freebsd.org From: "rrs (Randall Stewart)" Subject: [Differential] [Commented On] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: <6b9877fabfc054b3bce9c3a97f7e0455@localhost.localdomain> X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTKVJU= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 15:41:09 -0000 rrs added a comment. To answer jhb and kostikbel 1) Yes this does address the two issues that Hans re-write of the callout system did without changing the KPI. There may be other bugs as well, but with the test framework and the old code I could reproduce both issues (spin lock held to long and broken callout_active() semantic). The spin lock held to long I was able to get a vmcore and actually pinpoint *exactly* why it happened and *exactly* how the patch fixes it (as Gleb would say, no mystery ...) 2) Yes, its a good idea to split the test framework out as imp suggested, which I will do into test framework and callout changes. 3) As to simpler testing, yes we originally were running the test out of the kldload, but this causes at least two problems. It appears that the GIANT lock is held during kldload, any test that needs to do locking can experience LOR's and other fun stuff with Witness on. Second it becomes *much* harder to do multi-threaded testing. This is/was essential to find the bugs and reproduce them in the callout system. Basically you just put num_threads = 2 and you have two kthreads running the tests which helps located nasty races more easily ;-) 4) Imp, in an early version of the patch, complained I was not using the macros and what he had complained about was just code that I cut and paste. Thats what prompted me to fix and use the macro's properly throughout the code. Backing that out would be painful at this point so I see no need to split it out except to do a *lot* of extra work. REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, adrian, sbruno, lstewart, imp, hselasky Cc: jhb, kostikbel, emaste, delphij, neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 15:50:56 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id CF255EDE for ; Thu, 29 Jan 2015 15:50:56 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id AE303D0A for ; Thu, 29 Jan 2015 15:50:56 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TFou8F076682 for ; Thu, 29 Jan 2015 15:50:56 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TFoub3076681; Thu, 29 Jan 2015 15:50:56 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 15:50:56 +0000 To: freebsd-net@freebsd.org From: "gnn (George Neville-Neil)" Subject: [Differential] [Accepted] D1705: sfxge: Use SFXGE_MODERATION to initialize event moderation Message-ID: <8ef0e830f13ac8048ff69ef7dde77f08@localhost.localdomain> X-Priority: 3 Thread-Topic: D1705: sfxge: Use SFXGE_MODERATION to initialize event moderation X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: ZjQyOTAwZTc1YjQ5ZTljNTMxYTVkMzE2ZDk4IFTKVuA= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 15:50:56 -0000 gnn accepted this revision. gnn added a comment. This revision is now accepted and ready to land. Remember to add Approved by: gnn to your commit message. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1705 To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 15:51:27 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id F0723F7B for ; Thu, 29 Jan 2015 15:51:27 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id D178ADA6 for ; Thu, 29 Jan 2015 15:51:27 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TFpRB0077481 for ; Thu, 29 Jan 2015 15:51:27 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TFpRGs077439; Thu, 29 Jan 2015 15:51:27 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 15:51:27 +0000 To: freebsd-net@freebsd.org From: "gnn (George Neville-Neil)" Subject: [Differential] [Accepted] D1704: sfxge: Pass correct address to free allocated memory in the case of load error Message-ID: X-Priority: 3 Thread-Topic: D1704: sfxge: Pass correct address to free allocated memory in the case of load error X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: YTAwZjJhNTVjYzUxYTk4MzVhNDlmMDRkNDA1IFTKVv8= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 15:51:28 -0000 gnn accepted this revision. gnn added a comment. This revision is now accepted and ready to land. Remember to add Approved by: gnn (mentor) to your commit message. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1704 To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 15:51:49 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 80D8E106 for ; Thu, 29 Jan 2015 15:51:49 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 633DEDB2 for ; Thu, 29 Jan 2015 15:51:49 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TFpneG078434 for ; Thu, 29 Jan 2015 15:51:49 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TFpnIg078433; Thu, 29 Jan 2015 15:51:49 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 15:51:49 +0000 To: freebsd-net@freebsd.org From: "gnn (George Neville-Neil)" Subject: [Differential] [Accepted] D1703: sfxge: Remove unused esm_size member of the efsys_mem_t structure Message-ID: <3a516f1aa85a19bc324957a31c915de9@localhost.localdomain> X-Priority: 3 Thread-Topic: D1703: sfxge: Remove unused esm_size member of the efsys_mem_t structure X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: OWVkM2NjY2YxZDEzNDJlODFhNGI3MTJjMGJhIFTKVxU= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 15:51:49 -0000 gnn accepted this revision. gnn added a comment. This revision is now accepted and ready to land. Remember to add Approved by: gnn (mentor) to your commit message. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1703 To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 15:52:11 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 437111E5 for ; Thu, 29 Jan 2015 15:52:11 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 258B5DC7 for ; Thu, 29 Jan 2015 15:52:11 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TFqA5j078719 for ; Thu, 29 Jan 2015 15:52:10 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TFqAIM078718; Thu, 29 Jan 2015 15:52:10 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 15:52:10 +0000 To: freebsd-net@freebsd.org From: "gnn (George Neville-Neil)" Subject: [Differential] [Accepted] D1702: sfxge: Do not bzero() DMA allocated memory once again Message-ID: X-Priority: 3 Thread-Topic: D1702: sfxge: Do not bzero() DMA allocated memory once again X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: NjMxMmJlOThhNGY4NzdkYmQzMTVhYzdmMTg2IFTKVyo= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 15:52:11 -0000 gnn accepted this revision. gnn added a comment. This revision is now accepted and ready to land. Remember to add Approved by: gnn (mentor) to your commit message. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1702 To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 15:52:56 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 647BD293 for ; Thu, 29 Jan 2015 15:52:56 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 46746DE3 for ; Thu, 29 Jan 2015 15:52:56 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TFquAL079308 for ; Thu, 29 Jan 2015 15:52:56 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TFquTo079307; Thu, 29 Jan 2015 15:52:56 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 15:52:55 +0000 To: freebsd-net@freebsd.org From: "gnn (George Neville-Neil)" Subject: [Differential] [Accepted] D1706: sfxge: implemented parameter to restrict RSS channels Message-ID: X-Priority: 3 Thread-Topic: D1706: sfxge: implemented parameter to restrict RSS channels X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: ZTZjNzc1NjJhMjcwMWI3YzZjZTkzMDg4ZDNlIFTKV1c= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 15:52:56 -0000 gnn accepted this revision. gnn added a comment. This revision is now accepted and ready to land. Remember to add Approved by: gnn (mentor) to your commit message. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1706 To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 15:53:49 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 0470B333 for ; Thu, 29 Jan 2015 15:53:49 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id DA8E6DF7 for ; Thu, 29 Jan 2015 15:53:48 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TFrm6D079811 for ; Thu, 29 Jan 2015 15:53:48 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TFrmuD079810; Thu, 29 Jan 2015 15:53:48 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 15:53:48 +0000 To: freebsd-net@freebsd.org From: "gnn (George Neville-Neil)" Subject: [Differential] [Accepted] D1701: sfxge: Add evq argument to sfxge_tx_qcomplete() Message-ID: X-Priority: 3 Thread-Topic: D1701: sfxge: Add evq argument to sfxge_tx_qcomplete() X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: ZmRkNjdiMWY1YTE1NTE2MDQzZDA3Y2U3MTM2IFTKV4w= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 15:53:49 -0000 gnn accepted this revision. gnn added a comment. This revision is now accepted and ready to land. Remember to add Approved by: gnn (mentor) to your commit message. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1701 To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 15:54:26 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 0DFD63CF for ; Thu, 29 Jan 2015 15:54:26 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id E2B9BE04 for ; Thu, 29 Jan 2015 15:54:25 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TFsPkN080378 for ; Thu, 29 Jan 2015 15:54:25 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TFsPEI080377; Thu, 29 Jan 2015 15:54:25 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 15:54:25 +0000 To: freebsd-net@freebsd.org From: "gnn (George Neville-Neil)" Subject: [Differential] [Accepted] D1692: sfxge: Change sfxge_ev_qpoll() proto to avoid EVQ pointers array access Message-ID: X-Priority: 3 Thread-Topic: D1692: sfxge: Change sfxge_ev_qpoll() proto to avoid EVQ pointers array access X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: M2JhMDFjOGZmMjEwY2M2YjkyOWY2NzZhZTVlIFTKV7E= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 15:54:26 -0000 gnn accepted this revision. gnn added a comment. This revision is now accepted and ready to land. Remember to add Approved by: gnn (mentor) to your commit message. REVISION DETAIL https://reviews.freebsd.org/D1692 To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 15:55:11 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id E5CA947D for ; Thu, 29 Jan 2015 15:55:11 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id C7997E17 for ; Thu, 29 Jan 2015 15:55:11 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TFtBNx080954 for ; Thu, 29 Jan 2015 15:55:11 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TFtBHE080953; Thu, 29 Jan 2015 15:55:11 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 15:55:11 +0000 To: freebsd-net@freebsd.org From: "gnn (George Neville-Neil)" Subject: [Differential] [Accepted] D1700: sfxge: fixed TSO code to cope with VLAN headers Message-ID: <734732cf754a3f28ed118e1a1397bc8e@localhost.localdomain> X-Priority: 3 Thread-Topic: D1700: sfxge: fixed TSO code to cope with VLAN headers X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: ZGMyYWRlNDljMGY2NDEzMjkzZjgzNGExNGM4IFTKV98= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 15:55:12 -0000 gnn accepted this revision. gnn added a comment. This revision is now accepted and ready to land. Remember to add Approved by: gnn (mentor) to your commit message. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1700 To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 15:57:28 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id E78E553B for ; Thu, 29 Jan 2015 15:57:28 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id C9791E41 for ; Thu, 29 Jan 2015 15:57:28 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TFvSJK082856 for ; Thu, 29 Jan 2015 15:57:28 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TFvSeG082855; Thu, 29 Jan 2015 15:57:28 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 15:57:28 +0000 To: freebsd-net@freebsd.org From: "gnn (George Neville-Neil)" Subject: [Differential] [Requested Changes To] D1707: sfxge: access statistics buffers under port lock Message-ID: <63958787bd31353ba613da583e4e4b19@localhost.localdomain> X-Priority: 3 Thread-Topic: D1707: sfxge: access statistics buffers under port lock X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: MmFkY2EyODhjMzI1YWNkNjhmYWJmNzczN2QyIFTKWGg= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 15:57:29 -0000 gnn requested changes to this revision. gnn added a comment. This revision now requires changes to proceed. If you look at other drivers you'll see they have #define'd macros for the locks, rather than direct calls. This allows us to name the lock in the macro. See, for instance, this example from cxgbe/adapter.h: #define ADAPTER_LOCK(sc) mtx_lock(&(sc)->sc_lock) #define ADAPTER_UNLOCK(sc) mtx_unlock(&(sc)->sc_lock) #define ADAPTER_LOCK_ASSERT_OWNED(sc) mtx_assert(&(sc)->sc_lock, MA_OWNED) #define ADAPTER_LOCK_ASSERT_NOTOWNED(sc) mtx_assert(&(sc)->sc_lock, MA_NOTOWNED) You should move to this model and then update the patch. REVISION DETAIL https://reviews.freebsd.org/D1707 To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 15:58:15 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 030615DA for ; Thu, 29 Jan 2015 15:58:15 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id D8BEBE51 for ; Thu, 29 Jan 2015 15:58:14 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TFwEcx083462 for ; Thu, 29 Jan 2015 15:58:14 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TFwEVH083461; Thu, 29 Jan 2015 15:58:14 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 15:58:14 +0000 To: freebsd-net@freebsd.org From: "gnn (George Neville-Neil)" Subject: [Differential] [Accepted] D1699: sfxge: Remove extra cache-line alignment and reorder sfxge_evq_t Message-ID: <878297c7c712441fa0ddb4562c3acaee@localhost.localdomain> X-Priority: 3 Thread-Topic: D1699: sfxge: Remove extra cache-line alignment and reorder sfxge_evq_t X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: NTEwZjA3ZGJmNDI3MWUzMTM4NTAyOTUxODg2IFTKWJY= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 15:58:15 -0000 gnn accepted this revision. gnn added a comment. This revision is now accepted and ready to land. Remember to put Approved by: gnn (mentor) in the commit message. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1699 To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 15:58:49 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 5F1FD683 for ; Thu, 29 Jan 2015 15:58:49 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 31CF6E61 for ; Thu, 29 Jan 2015 15:58:49 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TFwmNj083731 for ; Thu, 29 Jan 2015 15:58:48 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TFwm9E083730; Thu, 29 Jan 2015 15:58:48 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 15:58:48 +0000 To: freebsd-net@freebsd.org From: "gnn (George Neville-Neil)" Subject: [Differential] [Accepted] D1698: sfxge: Make it possible to build without EVQ statistics Message-ID: X-Priority: 3 Thread-Topic: D1698: sfxge: Make it possible to build without EVQ statistics X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: N2FjZjRiMTcyNjhlNjBkNjJlNGQ0MjNmYTk1IFTKWLg= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 15:58:49 -0000 gnn accepted this revision. gnn added a comment. This revision is now accepted and ready to land. Remember to put Approved by: gnn (mentor) in the commit message. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1698 To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 15:59:22 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 208C7729 for ; Thu, 29 Jan 2015 15:59:22 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 02267E74 for ; Thu, 29 Jan 2015 15:59:22 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TFxLwV084274 for ; Thu, 29 Jan 2015 15:59:21 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TFxLtI084273; Thu, 29 Jan 2015 15:59:21 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 15:59:21 +0000 To: freebsd-net@freebsd.org From: "gnn (George Neville-Neil)" Subject: [Differential] [Accepted] D1708: sfxge: Separate software Tx queue limit for non-TCP traffic Message-ID: <1a88e03029583685e1846313cfd67923@localhost.localdomain> X-Priority: 3 Thread-Topic: D1708: sfxge: Separate software Tx queue limit for non-TCP traffic X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: YjIwYzkzODE4ZTFiNjc4ZjI3YjRiMDJhNWJjIFTKWNk= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 15:59:22 -0000 gnn accepted this revision. gnn added a comment. This revision is now accepted and ready to land. Remember to put Approved by: gnn (mentor) in the commit message. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1708 To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 16:00:08 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 33491917 for ; Thu, 29 Jan 2015 16:00:08 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 147E4E8C for ; Thu, 29 Jan 2015 16:00:08 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TG07jp084754 for ; Thu, 29 Jan 2015 16:00:07 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TG07Dc084753; Thu, 29 Jan 2015 16:00:07 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 16:00:07 +0000 To: freebsd-net@freebsd.org From: "gnn (George Neville-Neil)" Subject: [Differential] [Requested Changes To] D1697: sfxge: Expect required init_state on data path and in periodic calls Message-ID: X-Priority: 3 Thread-Topic: D1697: sfxge: Expect required init_state on data path and in periodic calls X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: MTVmZWRhZmFiZTk2YzBiOTY0NjE3OTVjNDBkIFTKWQc= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 16:00:08 -0000 gnn requested changes to this revision. gnn added a comment. This revision now requires changes to proceed. __predict_false rarely, if ever, does the right thing. Have you run any benchmarks to show that this improves performance? REVISION DETAIL https://reviews.freebsd.org/D1697 To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 16:00:58 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 0CA419BD for ; Thu, 29 Jan 2015 16:00:58 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id E23D6EA2 for ; Thu, 29 Jan 2015 16:00:57 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TG0vsw086122 for ; Thu, 29 Jan 2015 16:00:57 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TG0vN0086121; Thu, 29 Jan 2015 16:00:57 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 16:00:57 +0000 To: freebsd-net@freebsd.org From: "gnn (George Neville-Neil)" Subject: [Differential] [Accepted] D1694: sfxge: Move txq->next pointer to part writable on completion path Message-ID: X-Priority: 3 Thread-Topic: D1694: sfxge: Move txq->next pointer to part writable on completion path X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: YTIzODBmY2JlMjNhMDRmNDFmNmQzOTU2NTVkIFTKWTk= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: , , MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 16:00:58 -0000 gnn accepted this revision. gnn added a comment. This revision is now accepted and ready to land. Remember to put Approved by: gnn (mentor) in the commit message. BRANCH /head REVISION DETAIL https://reviews.freebsd.org/D1694 To: arybchik, gnn Cc: freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 16:15:08 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 43515E9F for ; Thu, 29 Jan 2015 16:15:08 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 017F4FF for ; Thu, 29 Jan 2015 16:15:08 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TGF7aO062095 for ; Thu, 29 Jan 2015 16:15:07 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TGF7dE062094; Thu, 29 Jan 2015 16:15:07 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 16:15:07 +0000 To: freebsd-net@freebsd.org From: "imp (Warner Losh)" Subject: [Differential] [Commented On] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: <3b02c5ed4b2e51f0d66edcc2bfc95549@localhost.localdomain> X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTKXIs= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 16:15:08 -0000 imp added a comment. I agree that the kernel test framework should be done differently as well. I didn't realize the number of mechanical changes my request to use the macros produced :( INLINE COMMENTS sys/sys/callout_test.h:1 I'm not sure that the callout_test.h belong in sys. Seems like needless pollution. sys/sys/kern_testfrwk.h:1 Does this need to live in sys as well? REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, adrian, sbruno, lstewart, imp, hselasky Cc: jhb, kostikbel, emaste, delphij, neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 16:59:24 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id B26B5C8F for ; Thu, 29 Jan 2015 16:59:24 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 72354830 for ; Thu, 29 Jan 2015 16:59:24 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TGxOho007144 for ; Thu, 29 Jan 2015 16:59:24 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TGxOGE007143; Thu, 29 Jan 2015 16:59:24 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 16:59:24 +0000 To: freebsd-net@freebsd.org From: "jhb (John Baldwin)" Subject: [Differential] [Commented On] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTKZuw= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 16:59:24 -0000 jhb added a comment. To be clear, I'm fine with updating my tests to a different framework, but I think it's worth discussing what that looked like. I also had to explicitly drop Giant in my test module handler. I do think it's probably better to explicitly ask tests to run instead of having kldload do them, that just seemed like less hassle to implement. REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, adrian, sbruno, lstewart, imp, hselasky Cc: jhb, kostikbel, emaste, delphij, neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 18:39:07 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 9BED78CB for ; Thu, 29 Jan 2015 18:39:07 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 710F333B for ; Thu, 29 Jan 2015 18:39:07 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TId7m5008241 for ; Thu, 29 Jan 2015 18:39:07 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TId7V0008240; Thu, 29 Jan 2015 18:39:07 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 18:39:07 +0000 To: freebsd-net@freebsd.org From: "rrs (Randall Stewart)" Subject: [Differential] [Commented On] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTKfks= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 18:39:07 -0000 rrs added a comment. Imp: I can see how we can easily move callout_test.h out of sys. That really should be in the module/tests/callout_test/ dir. But where would you suggest the global framework file go if not sys? REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, adrian, sbruno, lstewart, imp, hselasky Cc: jhb, kostikbel, emaste, delphij, neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 18:41:26 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id A8C5E999 for ; Thu, 29 Jan 2015 18:41:26 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [IPv6:2001:4f8:3:ffe0:406a:0:50:2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 66C115E2 for ; Thu, 29 Jan 2015 18:41:26 +0000 (UTC) Received: from phabric-backend.isc.freebsd.org (phabric-backend.isc.freebsd.org [127.0.1.5]) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TIfQY0011859 for ; Thu, 29 Jan 2015 18:41:26 GMT (envelope-from mat@phabric-backend.isc.freebsd.org) Received: (from root@localhost) by phabric-backend.isc.freebsd.org (8.14.9/8.14.9/Submit) id t0TIfQs1011858; Thu, 29 Jan 2015 18:41:26 GMT (envelope-from mat) Date: Thu, 29 Jan 2015 18:41:26 +0000 To: freebsd-net@freebsd.org From: "rrs (Randall Stewart)" Subject: [Differential] [Commented On] D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate thecallout code (and potentially for use by other tests). Message-ID: <7194910b547a82a82fbce45c2fdb156c@localhost.localdomain> X-Priority: 3 Thread-Topic: D1711: Changes to the callout code to restore active semantics and also add a test-framework and test to validate the callout code (and potentially for use by other tests). X-Herald-Rules: none X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-To: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: X-Phabricator-Cc: In-Reply-To: References: Thread-Index: Y2JjMTcyODJkYzgxM2NkZDFjY2RhOGRmMTlkIFTKftY= X-Phabricator-Sent-This-Message: Yes X-Mail-Transport-Agent: MetaMTA X-Auto-Response-Suppress: All X-Phabricator-Mail-Tags: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="utf-8" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 18:41:26 -0000 rrs added a comment. jhb The only reason I put the test stuff in this patch is its the only way to validate the patch, and that is something we really need in the callout system is a way to validate that its working correctly since this stuff tends to be very subtle and a bit of a head banger ;-) I can easily split this patch in two, and move the test framework into a second patch. The callout stuff is definitely not dependent on it other than for validation.. REVISION DETAIL https://reviews.freebsd.org/D1711 To: rrs, gnn, rwatson, adrian, sbruno, lstewart, imp, hselasky Cc: jhb, kostikbel, emaste, delphij, neel, erj, freebsd-net From owner-freebsd-net@FreeBSD.ORG Thu Jan 29 22:12:53 2015 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 860698D7 for ; Thu, 29 Jan 2015 22:12:53 +0000 (UTC) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 53ACCD7 for ; Thu, 29 Jan 2015 22:12:53 +0000 (UTC) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.14.9/8.14.9) with ESMTP id t0TMCrwT002344 for ; Thu, 29 Jan 2015 22:12:53 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 194314] [ixgbe] driver makes some dangerous assumptions with struct mbuf sizing with IXGBE_RX_COPY_LEN Date: Thu, 29 Jan 2015 22:12:53 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 11.0-CURRENT X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Many People X-Bugzilla-Who: ngie@FreeBSD.org X-Bugzilla-Status: New X-Bugzilla-Priority: Normal X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: cc Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 29 Jan 2015 22:12:53 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=194314 Garrett Cooper,425-314-3911 changed: What |Removed |Added ---------------------------------------------------------------------------- CC| |rrs@FreeBSD.org --- Comment #15 from Garrett Cooper,425-314-3911 --- (In reply to Garrett Cooper,425-314-3911 from comment #14) Hi Eric! I confirmed that the fix you provided worked for our environment. Unfortunately struct mbuf lacks some of the fields we have in it so it doesn't work with FreeBSD proper. I believe this patch would work for CURRENT, based on my basic C program: $ clang -Wall -Wno-c++1z-extensions -std=c11 -o ~/test_ixgbe_defines ~/test_ixgbe_defines.c $ cat ~/test_ixgbe_defines.c #include #include #include #include #ifndef offsetof #define offsetof __offsetof #endif #define IXGBE_RX_COPY_HDR_PADDED ((((MPKTHSIZE - 1) / 32) + 1) * 32) #define IXGBE_RX_COPY_LEN (MSIZE - IXGBE_RX_COPY_HDR_PADDED) #define IXGBE_RX_COPY_ALIGN (IXGBE_RX_COPY_HDR_PADDED - MPKTHSIZE) static_assert(IXGBE_RX_COPY_LEN == 160); static_assert(IXGBE_RX_COPY_ALIGN == (MHLEN - IXGBE_RX_COPY_LEN)); int main(void) { return (0); } I'm going to try this out internally, but could you and Adrian (or Randall, because Netflix runs CURRENT-ish and I believe uses ixgbe in some cases) please look at this as well to make sure that it works accordingly? diff --git a/sys/dev/ixgbe/ixgbe.h b/sys/dev/ixgbe/ixgbe.h index f7e9efa..1ddeebb 100644 --- a/sys/dev/ixgbe/ixgbe.h +++ b/sys/dev/ixgbe/ixgbe.h @@ -162,8 +162,10 @@ * modern Intel CPUs, results in 40 bytes wasted and a significant drop * in observed efficiency of the optimization, 97.9% -> 81.8%. */ -#define IXGBE_RX_COPY_LEN 160 -#define IXGBE_RX_COPY_ALIGN (MHLEN - IXGBE_RX_COPY_LEN) + +#define IXGBE_RX_COPY_HDR_PADDED ((((MPKTHSIZE - 1) / 32) + 1) * 32) +#define IXGBE_RX_COPY_LEN (MSIZE - IXGBE_RX_COPY_HDR_PADDED) +#define IXGBE_RX_COPY_ALIGN (IXGBE_RX_COPY_HDR_PADDED - MPKTHSIZE) /* Keep older OS drivers building... */ #if !defined(SYSCTL_ADD_UQUAD) -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@FreeBSD.ORG Fri Jan 30 00:37:46 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 288CF1BA for ; Fri, 30 Jan 2015 00:37:46 +0000 (UTC) Received: from onlyone.friendlyhosting.spb.ru (onlyone.friendlyhosting.spb.ru [46.4.40.135]) by mx1.freebsd.org (Postfix) with ESMTP id DE2F6195 for ; Fri, 30 Jan 2015 00:37:45 +0000 (UTC) Received: from [192.168.135.70] (unknown [94.19.235.70]) (Authenticated sender: lev@serebryakov.spb.ru) by onlyone.friendlyhosting.spb.ru (Postfix) with ESMTPSA id 897B15C002 for ; Fri, 30 Jan 2015 03:36:56 +0300 (MSK) Message-ID: <54CAD234.3020407@FreeBSD.org> Date: Fri, 30 Jan 2015 03:37:08 +0300 From: Lev Serebryakov Reply-To: lev@FreeBSD.org Organization: FreeBSD User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:31.0) Gecko/20100101 Thunderbird/31.4.0 MIME-Version: 1.0 To: freebsd-net@freebsd.org Subject: ipfw, nat and stateful firewall: why "keep-state" on "skipto" works at all and how do this properly? Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 8bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 30 Jan 2015 00:37:46 -0000 -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA512 I have problems to understand how combination of nat and stateful ruleset for ipfw should work. There is no good guides, and most guides uses old "divert" which is different from in-kernel nat, as far as I understand. Problem is, if we want to allow only incoming packets which are belong to already established connections, we need to create state in "allow" out rule for outbound packet BEFORE nat rule and then pass it to nat, which looks impossible, as "allow" stop processing. Or we could pass it to nat and then "allow keep-state", but then there will be same problem for inbound packets: "check-state" should go before "nat" rule, but packet should be passed to nat after that! Now I have old ruleset which I don't quite understand. It works, but WHY? Now I have such rules for outbound packets: 12700 skipto 12900 ip from any to any keep-state 12800 deny ip from any to any 12900 nat 1 ip from any to any out 12999 allow ip from any to any And rules for inbound ones are: 11000 deny ip from any to not me 11500 nat 1 ip from any to any 11510 check-state 11600 allow tcp from any to me ssh,http setup keep-state 11999 deny ip from any to any It was migrated from old copy'n'pasted "divert" variant (created before "nat" action was created!). Looks like, it does not what I want at all! It works only by accident, as "check-state" becomes "skipto 12900" and it is works only because 12999 is "allow ip from any to any" and not some other filtration! Is here better way to have nat and stateful ruleset? BTW, if I add second outbound link and "nat global" + two "fwd" rules, thing become even worse, as rul 12700 doesn't see second outbound packet (because it is intercepted by "nat global") and TTL of dynamic rule becomes 10 seconds! I don't see any way to achieve my goal with "nat global", exactly because "skipto keep-state" should be placed almost before "allow" and "nat global" adds second way through ruleset. - -- // Lev Serebryakov AKA Black Lion -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (MingW32) iQJ8BAEBCgBmBQJUytIzXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRGOTZEMUNBMEI1RjQzMThCNjc0QjMzMEFF QUIwM0M1OEJGREM0NzhGAAoJEOqwPFi/3EeP5R4P/jiZlkbm5boUI5n6JOCuFK7F g2rkiRtJacS+r5D2AVka7v1MPpNh7EU1n+YWjFo+oFz1yZPuLVMPjm9na2Y2CkKE NwBjO4m4z5crjvFK8nP/p/KFjHujDGRsA+EMxUs0UjEIw5GtaGSURqozliKqQReb dSInAOFPXOElka7n1IGQaFh/C0JYU/V86pHYM0axRSJfVA5QNMNImCPjUF6ESO1/ Nn/TRbI5nu/F0MFp6+Wsq/44n59ehJDF/sRIAKXzvF0BMBC4W/i76RGdjDZEEPhn w1P5TvHiOimnBkgegtS5J1HZuF2a6JbNTnv9FrtE1wZqppWAUeCzrJKfV5NNlOWw kR2v1oEjP00Mrsst10jZOyWVrNduGQsBMb4JK1LB3S8+v9hCg0oYipXdWmOEq+V3 tShc714b1kcY5zciyKqA7b8DLIGmrIECKVgj4mwaNCT3Qrs23JE0/3SPVX4hUiJN z9DwLGEJxiQTguh0+1PbwAJXWsmkBRBdytjyiKbNZtjU97foDIutndugBE9INTpV qIFIVB8310y/GOikiSDbftK/Xvea1vwWvPV5VoH/DF3wkWb0Gs9t2fKAbsQ53Rvx ACINd5zCShCQpV6d9NzgtjSWOfN7au6mmU2o+1TuUbQzBMyhdpVX0XA2vxFBwCTk 9W6wHQC2NZLiSqFxq1Xd =Agj5 -----END PGP SIGNATURE----- From owner-freebsd-net@FreeBSD.ORG Fri Jan 30 00:52:27 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 2B32E2EE for ; Fri, 30 Jan 2015 00:52:27 +0000 (UTC) Received: from onlyone.friendlyhosting.spb.ru (onlyone.friendlyhosting.spb.ru [46.4.40.135]) by mx1.freebsd.org (Postfix) with ESMTP id DF862345 for ; Fri, 30 Jan 2015 00:52:26 +0000 (UTC) Received: from [192.168.135.70] (unknown [94.19.235.70]) (Authenticated sender: lev@serebryakov.spb.ru) by onlyone.friendlyhosting.spb.ru (Postfix) with ESMTPSA id 82AA45C002 for ; Fri, 30 Jan 2015 03:52:10 +0300 (MSK) Message-ID: <54CAD5C8.3080904@FreeBSD.org> Date: Fri, 30 Jan 2015 03:52:24 +0300 From: Lev Serebryakov Reply-To: lev@FreeBSD.org Organization: FreeBSD User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:31.0) Gecko/20100101 Thunderbird/31.4.0 MIME-Version: 1.0 To: freebsd-net@freebsd.org Subject: Re: ipfw, nat and stateful firewall: why "keep-state" on "skipto" works at all and how do this properly? References: <54CAD234.3020407@FreeBSD.org> In-Reply-To: <54CAD234.3020407@FreeBSD.org> Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 30 Jan 2015 00:52:27 -0000 -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA512 On 30.01.2015 03:37, Lev Serebryakov wrote: > Is here better way to have nat and stateful ruleset? Actions like "create-dyn-allow" and "create-dyn-deny" will be very nice, BTW :) But looks like it is hard to add, as now dynamic rules are "replaced" by parents, and could not be easily replaced by other rules. - -- // Lev Serebryakov AKA Black Lion -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (MingW32) iQJ8BAEBCgBmBQJUytXHXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRGOTZEMUNBMEI1RjQzMThCNjc0QjMzMEFF QUIwM0M1OEJGREM0NzhGAAoJEOqwPFi/3EePkT8QAK9ypvFIG0jQnCquIp0DFxf3 POEh0e3SgFgzJ8z98bSY36/8XGHJp+yOV3lJeDPNfFhyxojMYSnJB2Dcjf/hVx/O EzJa+FJZce6uh3H4uidEcv0u4CA3WaNceDdQb+Z+VqhNRKx5e4LVcu4rWmdDLMkb MGqE3gT/6mOgPUTiZNtZUBTT39AyiUCoCWF9gfTJbFOUBkl2c21sRjAnAmYS5ien ASXfnaP5HULdDx6CIy+YP6oCZH1O1DFxGOKse7hJVMtS7H2YlX9kk8eoC8g8YPVN C1ng9Pahxy8FIS/lhtnOW25v3wLHZ+H5nHBA7EhSTEQPR7JZE13zIUKELHkpJt/j MdK/mNL3mldWdc4M4FzZCmGEDpbIYH9guuzEU0M48xUesrvenP6iBRloqX5tzduM yb1Fl4p1wAg/OMkBYdTExoyJF7X0WGAA9x8dYG7HuPuVzZb3AKaFQeaC1WU3mln5 d8TN6LbydEI+QxnrFDpivWz6cGy4WrYSHVP7A4/3AzFLlHXsjOvYNBEXUsh0+FJ/ Rg5wTfYeV7N+YnwyvtHItt482V9MekXz1egD4nIAB1Ae0TENVijdvb41eX+rJ3Yj XcsNKX5cAguenEB34BsEiBrF0cxB+H6PryUUaQ6MtwwW31BZZkG8HaoUWjkNigOo eYukYDv6a7b4bGoXNKJ7 =OMB1 -----END PGP SIGNATURE----- From owner-freebsd-net@FreeBSD.ORG Fri Jan 30 02:33:32 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id D93B7FC; Fri, 30 Jan 2015 02:33:31 +0000 (UTC) Received: from vps1.elischer.org (vps1.elischer.org [204.109.63.16]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "vps1.elischer.org", Issuer "CA Cert Signing Authority" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id B7BBBE2E; Fri, 30 Jan 2015 02:33:31 +0000 (UTC) Received: from Julian-MBP3.local (ppp121-45-239-189.lns20.per1.internode.on.net [121.45.239.189]) (authenticated bits=0) by vps1.elischer.org (8.14.9/8.14.9) with ESMTP id t0U2XQYR016464 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES128-SHA bits=128 verify=NO); Thu, 29 Jan 2015 18:33:29 -0800 (PST) (envelope-from julian@freebsd.org) Message-ID: <54CAED70.1080501@freebsd.org> Date: Fri, 30 Jan 2015 10:33:20 +0800 From: Julian Elischer User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:31.0) Gecko/20100101 Thunderbird/31.4.0 MIME-Version: 1.0 To: lev@FreeBSD.org, freebsd-net@freebsd.org Subject: Re: ipfw, nat and stateful firewall: why "keep-state" on "skipto" works at all and how do this properly? References: <54CAD234.3020407@FreeBSD.org> In-Reply-To: <54CAD234.3020407@FreeBSD.org> Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 30 Jan 2015 02:33:32 -0000 On 1/30/15 8:37 AM, Lev Serebryakov wrote: > -----BEGIN PGP SIGNED MESSAGE----- > Hash: SHA512 > > > I have problems to understand how combination of nat and stateful > ruleset for ipfw should work. There is no good guides, and most guides > uses old "divert" which is different from in-kernel nat, as far as I > understand. > > Problem is, if we want to allow only incoming packets which are > belong to already established connections, we need to create state in > "allow" out rule for outbound packet BEFORE nat rule and then pass it > to nat, which looks impossible, as "allow" stop processing. Or we > could pass it to nat and then "allow keep-state", but then there will > be same problem for inbound packets: "check-state" should go before > "nat" rule, but packet should be passed to nat after that! > > Now I have old ruleset which I don't quite understand. It works, but > WHY? Now I have such rules for outbound packets: > > 12700 skipto 12900 ip from any to any keep-state > 12800 deny ip from any to any > 12900 nat 1 ip from any to any out > 12999 allow ip from any to any > > And rules for inbound ones are: > > 11000 deny ip from any to not me > 11500 nat 1 ip from any to any > 11510 check-state > 11600 allow tcp from any to me ssh,http setup keep-state > 11999 deny ip from any to any ok so the dynamic rule is created on the outgoing packet, and associated with skipto 12900 which sets up a NAT session. on a later incoming packet, the rule 11500 is hit first so the packets are NAT'd back, and then their state is compared to that stored in the outgoing path, and if they match, they go to 12900 where they are not checked again becasue they are not 'out' packets. so it falls through to 12999 and is allowed in. (in its changed form). packets that are not in a known session fall through teh check-state and are dropped. it all looks ok to me. kinda cute actually. > It was migrated from old copy'n'pasted "divert" variant (created > before "nat" action was created!). > > Looks like, it does not what I want at all! It works only by > accident, as "check-state" becomes "skipto 12900" and it is works only > because 12999 is "allow ip from any to any" and not some other filtration! > > Is here better way to have nat and stateful ruleset? It would be really cool if state could hold the NAT'd form of the packets as well. but what you have above is really kinda cute, and seems to work as far as I can read. what "other filtration" do you want? I always do what is done here and separate inwards and outwards packets for the external interface into two different sets of rules (and another set for other interfaces). I find it helps to draw a packet flow with two chains, in and out.. with samples of what the packets look like for each flow at each point. From owner-freebsd-net@FreeBSD.ORG Fri Jan 30 09:05:39 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 6C430210; Fri, 30 Jan 2015 09:05:39 +0000 (UTC) Received: from onlyone.friendlyhosting.spb.ru (onlyone.friendlyhosting.spb.ru [46.4.40.135]) by mx1.freebsd.org (Postfix) with ESMTP id 2D705A3B; Fri, 30 Jan 2015 09:05:39 +0000 (UTC) Received: from [192.168.135.70] (unknown [94.19.235.70]) (Authenticated sender: lev@serebryakov.spb.ru) by onlyone.friendlyhosting.spb.ru (Postfix) with ESMTPSA id F3EF35C002; Fri, 30 Jan 2015 12:04:52 +0300 (MSK) Message-ID: <54CB4943.4050104@FreeBSD.org> Date: Fri, 30 Jan 2015 12:05:07 +0300 From: Lev Serebryakov Reply-To: lev@FreeBSD.org Organization: FreeBSD User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:31.0) Gecko/20100101 Thunderbird/31.4.0 MIME-Version: 1.0 To: Julian Elischer , freebsd-net@freebsd.org Subject: Re: ipfw, nat and stateful firewall: why "keep-state" on "skipto" works at all and how do this properly? References: <54CAD234.3020407@FreeBSD.org> <54CAED70.1080501@freebsd.org> In-Reply-To: <54CAED70.1080501@freebsd.org> Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 8bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 30 Jan 2015 09:05:39 -0000 -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA512 On 30.01.2015 05:33, Julian Elischer wrote: >> 12700 skipto 12900 ip from any to any keep-state 12800 deny ip >> from any to any 12900 nat 1 ip from any to any out 12999 allow ip >> from any to any >> >> And rules for inbound ones are: >> >> 11000 deny ip from any to not me 11500 nat 1 ip from any to any >> 11510 check-state 11600 allow tcp from any to me ssh,http setup >> keep-state 11999 deny ip from any to any > ok so the dynamic rule is created on the outgoing packet, and > associated with skipto 12900 which sets up a NAT session. > > on a later incoming packet, the rule 11500 is hit first so the > packets are NAT'd back, and then their state is compared to that > stored in the outgoing path, and if they match, they go to 12900 > where they are not checked again becasue they are not 'out' > packets. so it falls through to 12999 and is allowed in. (in its > changed form). packets that are not in a known session fall through > teh check-state and are dropped. > > it all looks ok to me. kinda cute actually. Not cute at all for me, as 12900 needs "out" (it is already in "out" group of rules!) and incoming packet is jumped to outbound section :) > It would be really cool if state could hold the NAT'd form of the > packets as well. but what you have above is really kinda cute, and > seems to work as far as I can read. what "other filtration" do you > want? Other filtration is hypothetical now, but I don't like this "skip -> nat with additional "redundant" check -> allow" pattern. > I always do what is done here and separate inwards and outwards > packets for the external interface into two different sets of > rules (and another set for other interfaces). Yep, it is exactly what I do, these two groups of rules are not only rules, of course. - -- // Lev Serebryakov AKA Black Lion -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (MingW32) iQJ8BAEBCgBmBQJUy0lDXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRGOTZEMUNBMEI1RjQzMThCNjc0QjMzMEFF QUIwM0M1OEJGREM0NzhGAAoJEOqwPFi/3EePgH4P+wWTLKxIhvRk1oD3GJqs4GHH d7vf+JoY1S2RDOJHBvNGfyc42YSBn6ubtIs2+dG/si9QzzmO57LFMPwiWFKRbPn4 rzJJ6qox91VMwfFnaDe1sceN072Dw5lbzrZN/AcTUZHBRpkGyKY6XHGamyZhMQzy pDlE0z1tYmnUwJXk7uQa5CitqKkVRozS2DWxpTPhTyfJbYASja68+h1aoRw7vobV mfKYOQpC+m2NHt8O2kT5S9XROAbDsTVtz9tXwqveJjsoBgAKgSamqp/u2YuLbZIy +ioYUHUbuJI1cfHEvpUvcnsZnx83TrIllDTso9WvWK7WRVzTkKnZEakMu3cMqW9S rVnFxRRklMwpbI+VoRY5BSjjdQ25iZlW0AGCgvgMdWstY/dM8Kv1xIdk92b2mAHR 6KlsnVaYPzf5R4gdjFlA6GVgiPhVW2o1/l9ynMZn53wETAHQGWm5pVbTmKWQqp3T ng6SxU7loZNIXHFFEnY+4Gk5e/Fg9qEOKFiKexPQBFD0mSlX0jMCAx/sMIiJPNm7 iU9Ip+MxGQSm7FgJ+GaRGXh3eSsX9/hphVewl6swyrjLkqVQayLRo+UrgwlA2jhw Ii4/XtktupWHMLmZPKXgGDDcRzXQ+PVQsLSdNHDnlNwIFS6Ss0ma+sPoBJM3wQKg SjHn11Rs6CpoHzRfn0oF =NXsa -----END PGP SIGNATURE----- From owner-freebsd-net@FreeBSD.ORG Fri Jan 30 09:42:38 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 7CE3FAC2 for ; Fri, 30 Jan 2015 09:42:38 +0000 (UTC) Received: from frv190.fwdcdn.com (frv190.fwdcdn.com [212.42.77.190]) (using TLSv1.2 with cipher DHE-RSA-AES128-SHA (128/128 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 3AFADE14 for ; Fri, 30 Jan 2015 09:42:37 +0000 (UTC) Received: from [10.10.1.23] (helo=frv199.fwdcdn.com) by frv190.fwdcdn.com with esmtp ID 1YH7n0-000Pyb-Mo for freebsd-net@freebsd.org; Fri, 30 Jan 2015 11:22:58 +0200 DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=ukr.net; s=ffe; h=Content-Transfer-Encoding:Content-Type:MIME-Version:References:In-Reply-To:Message-Id:Cc:To:Subject:From:Date; bh=hrSBIY9vz5gCx9KA+/8W1Soxoo88ppxiK5Lwoa78UII=; b=dmMvWIN78BTmsBcgNrOxGzTI5swudLQr1sO668BG0xyLaq3WknyL/VyZh9Ja7Yzbsuo9Me4ZnTDXxsq6zB59E43JbnGjd9O4ABuvJiK54E+jFl9UIrINMNTDpSL3NSp4NTzaJjfq5RD0nmfOIhZMKq5l3jzrodvgj3Egp8p7uxI=; Received: from [10.10.10.34] (helo=frv34.fwdcdn.com) by frv199.fwdcdn.com with smtp ID 1YH7mo-000Pib-Is for freebsd-net@freebsd.org; Fri, 30 Jan 2015 11:22:46 +0200 Date: Fri, 30 Jan 2015 11:22:46 +0200 From: wishmaster Subject: Re: ipfw, nat and stateful firewall: why "keep-state" on "skipto" works at all and how do this properly? To: lev@freebsd.org X-Mailer: mail.ukr.net 5.0 Message-Id: <1422608336.828476401.wghnslia@frv34.fwdcdn.com> In-Reply-To: <54CAD234.3020407@FreeBSD.org> References: <54CAD234.3020407@FreeBSD.org> MIME-Version: 1.0 Received: from artemrts@ukr.net by frv34.fwdcdn.com; Fri, 30 Jan 2015 11:22:46 +0200 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: binary Content-Disposition: inline Cc: freebsd-net@freebsd.org X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 30 Jan 2015 09:42:38 -0000 Hi, below my experience. --- Original message --- From: "Lev Serebryakov" Date: 30 January 2015, 02:37:54 > -----BEGIN PGP SIGNED MESSAGE----- > Hash: SHA512 > > > I have problems to understand how combination of nat and stateful > ruleset for ipfw should work. There is no good guides, and most guides > uses old "divert" which is different from in-kernel nat, as far as I > understand. > > Problem is, if we want to allow only incoming packets which are > belong to already established connections, we need to create state in > "allow" out rule for outbound packet BEFORE nat rule and then pass it > to nat, which looks impossible, as "allow" stop processing. Or we > could pass it to nat and then "allow keep-state", but then there will > be same problem for inbound packets: "check-state" should go before > "nat" rule, but packet should be passed to nat after that! > > Now I have old ruleset which I don't quite understand. It works, but > WHY? Now I have such rules for outbound packets: > > 12700 skipto 12900 ip from any to any keep-state > 12800 deny ip from any to any > 12900 nat 1 ip from any to any out > 12999 allow ip from any to any > > And rules for inbound ones are: > > 11000 deny ip from any to not me > 11500 nat 1 ip from any to any > 11510 check-state > 11600 allow tcp from any to me ssh,http setup keep-state > 11999 deny ip from any to any At first, i think you should move keep-state from skipto to explicit allow rule. Some explaining where check-state is useful for me. Packets, coming from LAN allow by rule 3205 and create keep-state rule; on ext_if nat and allow rule without keep-state (15000,15010) as it is already exists. On incoming on ext_if nat and keep-state rules and packets goes to the kernel. Any other packets from outside will be blocked. Traffic from server itself allows by 15150 rule with keep-state and will be checked on incoming interface by rule 5020. So in my case it is no need to have explicit allow rule after 'nat' rule on incoming direction on external interface. This is behavior like pf. For my case with 4 ISP link I use something like this example, but more complex, though. ### IN int_if nfe0 $cmd 3000 check-state log $cmd 3205 allow log ip4 from any to not me not 25 $ks # allow to wild world to not 25 port only $cmd 3210 allow log ip4 from any to me 22,21,20,80,81,3306,2112,5060,49000-65535 $ks $cmd 3212 allow log ip4 from any 68 to me 67 $cmd 3215 allow log icmp from any to me icmptypes 0,3,4,8,11 $cmd 3499 deny log all from any to any ### OUT ext_if sk0 $cmd 15000 nat 1 log ip4 from not me to not me recv "*" # for LAN only $cmd 15010 allow log ip4 from me to not me recv "*" # for LAN only $cmd 15150 allow log ip4 from me to any $ks # for server's traffic only $cmd 15999 deny log all from any to any ### IN ext_if sk0 $cmd 5000 nat 1 log ip4 from any to me $cmd 5020 check-state log $cmd 5100 allow log tcp from any to me 22 setup limit src-addr 3 # to server itself $cmd 5200 allow log tcp from any to "table(12)" 80,81,443,5555 setup limit src-addr 20 # to jails $cmd 5310 allow log icmp from any to any icmptypes 0,3,4,8,11 $cmd 5999 deny log all from any to any Cheers, Vitaly From owner-freebsd-net@FreeBSD.ORG Fri Jan 30 09:56:43 2015 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 932AD106 for ; Fri, 30 Jan 2015 09:56:43 +0000 (UTC) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 7B7FDF39 for ; Fri, 30 Jan 2015 09:56:43 +0000 (UTC) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.14.9/8.14.9) with ESMTP id t0U9uhoT045654 for ; Fri, 30 Jan 2015 09:56:43 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 197059] network locks up with IPv6 udp traffic Date: Fri, 30 Jan 2015 09:56:43 +0000 X-Bugzilla-Reason: CC X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.0-STABLE X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: demon@FreeBSD.org X-Bugzilla-Status: New X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: freebsd-bugs@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 30 Jan 2015 09:56:43 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=197059 --- Comment #1 from Dmitry Sivachenko --- For us this is rather severe problem (it take about 10 seconds to leave machine without working network). If these LORs are not enough to debug this issue, I am more than willing to provide any necessary info, please ask. -- You are receiving this mail because: You are on the CC list for the bug. From owner-freebsd-net@FreeBSD.ORG Fri Jan 30 10:50:20 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 2FE3CC3D; Fri, 30 Jan 2015 10:50:20 +0000 (UTC) Received: from sola.nimnet.asn.au (paqi.nimnet.asn.au [115.70.110.159]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 87D54791; Fri, 30 Jan 2015 10:50:18 +0000 (UTC) Received: from localhost (localhost [127.0.0.1]) by sola.nimnet.asn.au (8.14.2/8.14.2) with ESMTP id t0UAoFP4078570; Fri, 30 Jan 2015 21:50:15 +1100 (EST) (envelope-from smithi@nimnet.asn.au) Date: Fri, 30 Jan 2015 21:50:14 +1100 (EST) From: Ian Smith To: Lev Serebryakov Subject: Re: ipfw, nat and stateful firewall: why "keep-state" on "skipto" works at all and how do this properly? In-Reply-To: <54CB4943.4050104@FreeBSD.org> Message-ID: <20150130211405.Q66172@sola.nimnet.asn.au> References: <54CAD234.3020407@FreeBSD.org> <54CAED70.1080501@freebsd.org> <54CB4943.4050104@FreeBSD.org> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Cc: freebsd-net@freebsd.org X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 30 Jan 2015 10:50:20 -0000 On Fri, 30 Jan 2015 12:05:07 +0300, Lev Serebryakov wrote: > On 30.01.2015 05:33, Julian Elischer wrote: > > >> 12700 skipto 12900 ip from any to any keep-state 12800 deny ip > >> from any to any 12900 nat 1 ip from any to any out 12999 allow ip > >> from any to any > >> > >> And rules for inbound ones are: > >> > >> 11000 deny ip from any to not me 11500 nat 1 ip from any to any > >> 11510 check-state 11600 allow tcp from any to me ssh,http setup > >> keep-state 11999 deny ip from any to any > > ok so the dynamic rule is created on the outgoing packet, and > > associated with skipto 12900 which sets up a NAT session. > > > > on a later incoming packet, the rule 11500 is hit first so the > > packets are NAT'd back, and then their state is compared to that > > stored in the outgoing path, and if they match, they go to 12900 > > where they are not checked again becasue they are not 'out' > > packets. so it falls through to 12999 and is allowed in. (in its > > changed form). packets that are not in a known session fall through > > teh check-state and are dropped. > > > > it all looks ok to me. kinda cute actually. > Not cute at all for me, as 12900 needs "out" (it is already in "out" > group of rules!) and incoming packet is jumped to outbound section :) So, don't do it that way. I've also always found skipto .. keep-state rules confusing, so I'll reinforce wishmaster's initial comment: : At first, i think you should move keep-state from skipto to explicit : allow rule. Use skipto to distinguish inbound from outbound packets, on both/all of inside and outside interfaces, then use keep-state in the appropriate sections to avoid confusion. > Other filtration is hypothetical now, but I don't like this "skip -> > nat with additional "redundant" check -> allow" pattern. Frankly the examples in the IPFW handbook section still suck, despite some recent good work in cleaning up that document. I would suggest basing a ruleset on one of those - probably 'simple' in this case - in /etc/rc.firewall, adding whatever stateful rules you want there. I failed in several attempts to get the newer kernel nat code used in 'client' and 'open' rulesets into 'simple', but it's straightforward. Even then, I extend the _structure_ of that example to split inbound from outbound flows as described below, rather than just nat everything. > > I always do what is done here and separate inwards and outwards > > packets for the external interface into two different sets of > > rules (and another set for other interfaces). > Yep, it is exactly what I do, these two groups of rules are not only > rules, of course. Something else I learned from Julian a long time ago regarding natd - though it applies equally well to kernel nat: "Don't waste natd's time with packets it doesn't care about". You need to nat all inbound packets from the outside - well, those to the $nat_if address anyway, if you have multiple IPs - but you only need to nat outbound packets on the outside interface that have earlier been accepted in from the inside interface from an internal address: $fwadd skipto $NATIN ip4 from any to ${ext_ip} in recv ${ext_if} [..] $fwadd skipto $NATOUT ip4 from any to any out xmit $ext_if recv $int_if [..] $fwadd $NATIN divert natd ip4 from any to any in recv ${nat_if} [..] $fwadd $NATOUT divert natd ip4 from any to any out xmit ${nat_if} Simply replacing 'divert natd' with 'nat N' of course. If you can't follow your own ruleset a year later, it's just not clear enough .. speaking from bitter experience :) cheers, Ian From owner-freebsd-net@FreeBSD.ORG Fri Jan 30 11:23:26 2015 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id BB8B719B for ; Fri, 30 Jan 2015 11:23:26 +0000 (UTC) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id A325DAF7 for ; Fri, 30 Jan 2015 11:23:26 +0000 (UTC) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.14.9/8.14.9) with ESMTP id t0UBNQE9017388 for ; Fri, 30 Jan 2015 11:23:26 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 197059] network locks up with IPv6 udp traffic Date: Fri, 30 Jan 2015 11:23:26 +0000 X-Bugzilla-Reason: CC X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.0-STABLE X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: ae@FreeBSD.org X-Bugzilla-Status: New X-Bugzilla-Priority: --- X-Bugzilla-Assigned-To: ae@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: assigned_to cc Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 30 Jan 2015 11:23:26 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=197059 Andrey V. Elsukov changed: What |Removed |Added ---------------------------------------------------------------------------- Assignee|freebsd-bugs@FreeBSD.org |ae@FreeBSD.org CC| |ae@FreeBSD.org -- You are receiving this mail because: You are on the CC list for the bug. From owner-freebsd-net@FreeBSD.ORG Fri Jan 30 15:39:23 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 880E3AF8 for ; Fri, 30 Jan 2015 15:39:23 +0000 (UTC) Received: from onlyone.friendlyhosting.spb.ru (onlyone.friendlyhosting.spb.ru [46.4.40.135]) by mx1.freebsd.org (Postfix) with ESMTP id 48415BBE for ; Fri, 30 Jan 2015 15:39:23 +0000 (UTC) Received: from [127.0.0.1] (nat.in.devexperts.com [89.113.128.63]) (Authenticated sender: lev@serebryakov.spb.ru) by onlyone.friendlyhosting.spb.ru (Postfix) with ESMTPSA id 776655C002; Fri, 30 Jan 2015 18:39:11 +0300 (MSK) Message-ID: <54CBA599.8030904@FreeBSD.org> Date: Fri, 30 Jan 2015 18:39:05 +0300 From: Lev Serebryakov Reply-To: lev@FreeBSD.org Organization: FreeBSD User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:31.0) Gecko/20100101 Thunderbird/31.4.0 MIME-Version: 1.0 To: wishmaster Subject: Re: ipfw, nat and stateful firewall: why "keep-state" on "skipto" works at all and how do this properly? References: <54CAD234.3020407@FreeBSD.org> <1422608336.828476401.wghnslia@frv34.fwdcdn.com> In-Reply-To: <1422608336.828476401.wghnslia@frv34.fwdcdn.com> Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Cc: freebsd-net@freebsd.org X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 30 Jan 2015 15:39:23 -0000 -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA512 On 30.01.2015 12:22, wishmaster wrote: > At first, i think you should move keep-state from skipto to > explicit allow rule. Yep! I like it TOO! > For my case with 4 ISP link I use something like this example, but > more complex, though. Could you please show variant for 4 ISP links? :) - -- // Lev Serebryakov -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (MingW32) iQJ8BAEBCgBmBQJUy6WZXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRGOTZEMUNBMEI1RjQzMThCNjc0QjMzMEFF QUIwM0M1OEJGREM0NzhGAAoJEOqwPFi/3EePXUEQAKF33zboObfY2QwHXkMniPP6 tDIRTH5uDYvj84L/90MhdA0eEZXLuoPUW34p57ipmSSiH0uBYvtvdQAR0WLe+0+Q XvmajOt5Gve6ANlgxr4PS//nOXte9dWp4ZtdvR44/BAZPM+jSeKVkWRsz/YLTS6x FrSGYAMgQYXTBSR/RpBz/dseqwTrY0Qcv9WJpU+oigHKpReZkVJ7tJmDgCAO8+rE X7YTyLwVPYXBw4Y77yZVox/P2oBEdMQ1Z6Eb/qvQXCNkszS4QmbMXj81Uu0x3Zdt BzvJoucnNSUeQivYDbZGY+521RBXtyLXfaWGyRHLFmFiNFz6iT+TdF/S93PBdhY6 1rPx9PIkdystxin44n87HBzYOn3XxiH+O4DcQjkwKfA/+3xGCQDY4FY9GdV+mlBQ nhxrmrmauhSAOUz3BoRDk1k/gcke3Kgcn06dBqNW/bShoJ7fjceK87jUK4OPYm5G JG6z1tVVRPBYmA2WFwGfmx6e60Qfq0dM8DVeffpf22UowNxx+t+JqpnRLFDyS7M+ iUuEnPWQL74/9WRmYREC1CBZWPAHiBm7HlhUz01lVu5uwH1PjdZzG+Z2n3VyWjas t3E/W4/+7ZKgCFS2jwBjiXoa16LunwdJUxH3feFYkLFrYgVoc4edHtsafUKyGsy+ ZrkOl05x9PavJtCTMr7W =3dsG -----END PGP SIGNATURE----- From owner-freebsd-net@FreeBSD.ORG Fri Jan 30 21:11:52 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 26637BEC; Fri, 30 Jan 2015 21:11:52 +0000 (UTC) Received: from mail.ignoranthack.me (ignoranthack.me [199.102.79.106]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 08F3895E; Fri, 30 Jan 2015 21:11:51 +0000 (UTC) Received: from [192.168.200.212] (unknown [50.136.155.142]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) (Authenticated sender: sbruno@ignoranthack.me) by mail.ignoranthack.me (Postfix) with ESMTPSA id 3B0B31941DD; Fri, 30 Jan 2015 21:11:51 +0000 (UTC) Message-ID: <54CBF396.3090903@ignoranthack.me> Date: Fri, 30 Jan 2015 13:11:50 -0800 From: Sean Bruno Reply-To: sbruno@freebsd.org User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:31.0) Gecko/20100101 Thunderbird/31.4.0 MIME-Version: 1.0 To: freebsd-net@freebsd.org Subject: Intel 82574L (em) Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 30 Jan 2015 21:11:52 -0000 -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA512 http://www.intel.com/content/dam/doc/datasheet/82574l-gbe-controller-datasheet.pdf According to 7.1.11, this device does indeed have 2 queues for stuff and or things. So, basic RSS would be possible in something like an Atom box. I note that the em(4) driver intentionally disables this on initialization. I'm up for some science on my new shiny, soon to be router box. Any reason not to default to 1 queue and allow loader.conf to raise it to 2? sean bcc Intel Domination team -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQF8BAEBCgBmBQJUy/OTXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRCQUFENDYzMkU3MTIxREU4RDIwOTk3REQx MjAxRUZDQTFFNzI3RTY0AAoJEBIB78oecn5k600IAKpunQhI/hWNE42I+WYW7V1u ry2zsNWjBayJe/fYZYHXQSRBmbiC9VGkGWRqYKMflnC6GSz6LuNJWCnZ46mnNOSK SUKRe8eXLJ+ERQrUO75r8xsYl3D+FXA3bRqVAzCfV7U5kyeRlfGqNypanWXbVKXB 8mTMLKvzi3KSD1oACZC5eMVwGQXVD9u/+999yiWI7KQRg3GnxAYjWrjHuluJzBgl 7vVLbJuG1Ezs7CYl2JnKaWM8Z6kUpkRvNuuka9z8csp1lMlefk2Ta/xMmGTZN9x6 ucc436V3m8qr+fSRs5R9yvkltDeVx/Nu4bLL8BkvQ9nqQuQ3KHGuqvLzhsAkHCk= =8hTG -----END PGP SIGNATURE----- From owner-freebsd-net@FreeBSD.ORG Fri Jan 30 23:07:42 2015 Return-Path: Delivered-To: freebsd-net@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 849FBF82 for ; Fri, 30 Jan 2015 23:07:42 +0000 (UTC) Received: from kenobi.freebsd.org (kenobi.freebsd.org [IPv6:2001:1900:2254:206a::16:76]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 6B0F03DE for ; Fri, 30 Jan 2015 23:07:42 +0000 (UTC) Received: from bugs.freebsd.org ([127.0.1.118]) by kenobi.freebsd.org (8.14.9/8.14.9) with ESMTP id t0UN7gpi041647 for ; Fri, 30 Jan 2015 23:07:42 GMT (envelope-from bugzilla-noreply@freebsd.org) From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 165622] [ndis][panic][patch] Unregistered use of FPU in kernel on amd64 Date: Fri, 30 Jan 2015 23:07:42 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: Base System X-Bugzilla-Component: kern X-Bugzilla-Version: 10.0-CURRENT X-Bugzilla-Keywords: X-Bugzilla-Severity: Affects Only Me X-Bugzilla-Who: AWilcox@Wilcox-Tech.com X-Bugzilla-Status: In Progress X-Bugzilla-Priority: Normal X-Bugzilla-Assigned-To: freebsd-net@FreeBSD.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: cc Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit X-Bugzilla-URL: https://bugs.freebsd.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 30 Jan 2015 23:07:42 -0000 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=165622 Andrew Wilcox changed: What |Removed |Added ---------------------------------------------------------------------------- CC| |AWilcox@Wilcox-Tech.com --- Comment #3 from Andrew Wilcox --- This patch still applies cleanly to 11.0-CURRENT and is still needed for at least the bcm43xx 5.100.235.19 NDIS 5 driver. -- You are receiving this mail because: You are the assignee for the bug. From owner-freebsd-net@FreeBSD.ORG Sat Jan 31 00:57:28 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id B4204BC1; Sat, 31 Jan 2015 00:57:28 +0000 (UTC) Received: from mail-pa0-x22e.google.com (mail-pa0-x22e.google.com [IPv6:2607:f8b0:400e:c03::22e]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 81827AF; Sat, 31 Jan 2015 00:57:28 +0000 (UTC) Received: by mail-pa0-f46.google.com with SMTP id lj1so58522550pab.5; Fri, 30 Jan 2015 16:57:28 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date:message-id:subject :from:to:cc:content-type; bh=O1yB3/wSq7kd7zGOSkuTL9A8BGWCEj0xS47V7IjOcQE=; b=VZtta781tlUsuPNP8GzRrOccxE10Jkg5AEAnScUWs9syADTGPMf7cIBYByAdPFwvto kkJxoyXVUkYxYvRXWgeXhvfrci8W57NKsupjG0tsDjzlHTC5r7U/qRLPQmrkRWIIAR25 TJt0m/8Q9cqx+8TbANrgk5Mr2TTRNC5BnLKmmwaoC6EE+BHBqmdhPbmubair+AVvUqT9 rhnJJmKAwftiyaPQDszJ/WrclrDIZd+pEY7mmQOul/begTmFUN3W2JcvZcVpbAd/mEPB KFkw/JgXEyf8J4Ol4O2C3Z+tQzdUWy21DD33yqPaqF7agoJA4VaKpGfz9Oy9UzObM7Yr a4YA== MIME-Version: 1.0 X-Received: by 10.68.197.10 with SMTP id iq10mr12519032pbc.143.1422665848066; Fri, 30 Jan 2015 16:57:28 -0800 (PST) Sender: kob6558@gmail.com Received: by 10.67.22.231 with HTTP; Fri, 30 Jan 2015 16:57:28 -0800 (PST) In-Reply-To: <54C918D2.7090805@FreeBSD.org> References: <54C918D2.7090805@FreeBSD.org> Date: Fri, 30 Jan 2015 16:57:28 -0800 X-Google-Sender-Auth: NSSG4MfyAmDxX4MH3uTj6hCDUw0 Message-ID: Subject: Re: Problems with DNSSEC -- answer in fragmented UDP doesn't work From: Kevin Oberman To: Lev Serebryakov Content-Type: text/plain; charset=UTF-8 X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: "freebsd-net@freebsd.org" X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 31 Jan 2015 00:57:28 -0000 On Wed, Jan 28, 2015 at 9:13 AM, Lev Serebryakov wrote: > -----BEGIN PGP SIGNED MESSAGE----- > Hash: SHA512 > > > I could not resolve names with DNSSEC (for example, in freebsd.org > domain) on two of my installations, one with FreeBSD 11 and other with > FreeBSD 9.3. > > Symptoms are the same: answer is sent as fragmented IP/UDP packet and > second part of answer is never arrived. For example, this doesn't work > for me ("timeout" and only first part of fragmented packet on wire > according to tcpdump): > > % dig +dnssec www.freebsd.org @72.52.71.1 > > ; <<>> DiG 9.9.5 <<>> +dnssec www.freebsd.org @72.52.71.1 > ;; global options: +cmd > ;; connection timed out; no servers could be reached > % > > Problem is, latest bind (9.9 from ports) send such requests over UDP, > not TCP. > > Is it Ok? Is it misconfiguration of my networks (I have such problem > in tow different installations) or something? > > - -- > // Lev Serebryakov > Does the system have a firewall? If so, is it configured to allow fragments? For ipfw you need something like "allow ip from any to me frag". If you want to restrict this to DNS, restrict it to dst-port 53. -- Kevin Oberman, Network Engineer, Retired E-mail: rkoberman@gmail.com From owner-freebsd-net@FreeBSD.ORG Sat Jan 31 01:00:21 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 468C5C6E; Sat, 31 Jan 2015 01:00:21 +0000 (UTC) Received: from mail.strugglingcoder.info (strugglingcoder.info [65.19.130.35]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 31AD2D0; Sat, 31 Jan 2015 01:00:20 +0000 (UTC) Received: from localhost (unknown [10.1.1.3]) (Authenticated sender: hiren@strugglingcoder.info) by mail.strugglingcoder.info (Postfix) with ESMTPSA id 843DDCE400; Fri, 30 Jan 2015 17:00:14 -0800 (PST) Date: Fri, 30 Jan 2015 17:00:14 -0800 From: hiren panchasara To: sbruno@freebsd.org Subject: Re: Intel 82574L (em) Message-ID: <20150131010014.GB19333@strugglingcoder.info> References: <54CBF396.3090903@ignoranthack.me> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha512; protocol="application/pgp-signature"; boundary="hQiwHBbRI9kgIhsi" Content-Disposition: inline In-Reply-To: <54CBF396.3090903@ignoranthack.me> User-Agent: Mutt/1.5.23 (2014-03-12) Cc: freebsd-net@freebsd.org X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 31 Jan 2015 01:00:21 -0000 --hQiwHBbRI9kgIhsi Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Fri, Jan 30, 2015 at 01:11:50PM -0800, Sean Bruno wrote: >=20 > -----BEGIN PGP SIGNED MESSAGE----- > Hash: SHA512 >=20 > http://www.intel.com/content/dam/doc/datasheet/82574l-gbe-controller-data= sheet.pdf >=20 > According to 7.1.11, this device does indeed have 2 queues for stuff and > or things. So, basic RSS would be possible in something like an Atom box. >=20 > I note that the em(4) driver intentionally disables this on > initialization. I'm up for some science on my new shiny, soon to be > router box. Any reason not to default to 1 queue and allow loader.conf > to raise it to 2? Intel folks know better but it seems this is hartwell. em_setup_msix() in very start says: /* ** Setup MSI/X for Hartwell: tests have shown ** use of two queues to be unstable, and to ** provide no great gain anyway, so we simply ** seperate the interrupts and use a single queue. */ Things may have changed now. I guess you can try enabling it and find out := -) cheers, Hiren --hQiwHBbRI9kgIhsi Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (FreeBSD) iQF8BAEBCgBmBQJUzCkeXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRBNEUyMEZBMUQ4Nzg4RjNGMTdFNjZGMDI4 QjkyNTBFMTU2M0VERkU1AAoJEIuSUOFWPt/lOEoH/3DL/joxvDlITP12IY6rGJZn dAzkJT7AIUlu3YgJmO518v1RvtqUnT+zWLkwd5b096WSpV9KI9WJs685rINNa4ab 8K8ou/RMbtdTwi9V6EYrysUZm+w8kcn7LE0BgiH3wTCsZIHAiyuqKjrFMhOlcw28 Ti4d+tcjB/hWxHUMo4qjrenTD6jh1iTE80uLY9wEh6LP1//ASnVrSFEhPJPcro+4 BchDFVs0I8YIW4aS5TUxUNZR5MxnghAu4Q1DpGEOCscqi4GToeVTIoBsYqO+9EpO RRY1ag4nALDIGVptu3K7QURFWZ5/GsoaWEv04uoBMJ1G/wpioIyo9eIeMrzjbDU= =n/u8 -----END PGP SIGNATURE----- --hQiwHBbRI9kgIhsi-- From owner-freebsd-net@FreeBSD.ORG Sat Jan 31 03:50:20 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 8A3E3394; Sat, 31 Jan 2015 03:50:20 +0000 (UTC) Received: from sola.nimnet.asn.au (paqi.nimnet.asn.au [115.70.110.159]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 0109022F; Sat, 31 Jan 2015 03:50:19 +0000 (UTC) Received: from localhost (localhost [127.0.0.1]) by sola.nimnet.asn.au (8.14.2/8.14.2) with ESMTP id t0V3o8VW013109; Sat, 31 Jan 2015 14:50:08 +1100 (EST) (envelope-from smithi@nimnet.asn.au) Date: Sat, 31 Jan 2015 14:50:08 +1100 (EST) From: Ian Smith To: Kevin Oberman Subject: Re: Problems with DNSSEC -- answer in fragmented UDP doesn't work In-Reply-To: Message-ID: <20150131143014.F66172@sola.nimnet.asn.au> References: <54C918D2.7090805@FreeBSD.org> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Cc: "freebsd-net@freebsd.org" , Lev Serebryakov X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 31 Jan 2015 03:50:20 -0000 On Fri, 30 Jan 2015 16:57:28 -0800, Kevin Oberman wrote: > On Wed, Jan 28, 2015 at 9:13 AM, Lev Serebryakov wrote: > > I could not resolve names with DNSSEC (for example, in freebsd.org > > domain) on two of my installations, one with FreeBSD 11 and other with > > FreeBSD 9.3. > > > > Symptoms are the same: answer is sent as fragmented IP/UDP packet and > > second part of answer is never arrived. For example, this doesn't work > > for me ("timeout" and only first part of fragmented packet on wire > > according to tcpdump): > > > > % dig +dnssec www.freebsd.org @72.52.71.1 > > > > ; <<>> DiG 9.9.5 <<>> +dnssec www.freebsd.org @72.52.71.1 > > ;; global options: +cmd > > ;; connection timed out; no servers could be reached > > % > > > > Problem is, latest bind (9.9 from ports) send such requests over UDP, > > not TCP. That's normal for bind, and nothing new. > > Is it Ok? Is it misconfiguration of my networks (I have such problem > > in tow different installations) or something? > > > > - -- > > // Lev Serebryakov > > > > Does the system have a firewall? If so, is it configured to allow > fragments? > > For ipfw you need something like "allow ip from any to me frag". If you > want to restrict this to DNS, restrict it to dst-port 53. Indeed. Same has long applied if using (eg) zen.spamhaus.org lookups against spam, which responses can have up to two fragments. If also serving DNSSEC you'd need to allow frags outbound as well. Another example, perhaps, of damage due to the mistake-ridden IPFW handbook example rulesets, all of which gratuitously deny all frags. cheers, Ian From owner-freebsd-net@FreeBSD.ORG Sat Jan 31 04:30:05 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 75A1E940; Sat, 31 Jan 2015 04:30:05 +0000 (UTC) Received: from mail-we0-x234.google.com (mail-we0-x234.google.com [IPv6:2a00:1450:400c:c03::234]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 09FAF893; Sat, 31 Jan 2015 04:30:05 +0000 (UTC) Received: by mail-we0-f180.google.com with SMTP id m14so30374174wev.11; Fri, 30 Jan 2015 20:30:02 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=OkfFmupbNiOYfyiLjw2XWdxfsA89O//BPKYcI/OFVwc=; b=nAII8QZrqgb9RzPVvTrmqzJ41ByNf0f7XbYJWkCd2npWZDX0dpiA+8DLzBPz949ota 2nHS7uwoPR1Zf7c6+5OJulYNg2woEEdIAs9wTX/Nxa29qrpySYNhcyq9IfMgxL+Zy2fv CRpFR5D7zIBlG6a30h84258Gx+e+N1UcWdl4wII8h8wmA2IVsnQP85LdNnkkVIXYdAjN /PLvQflsDAbQxGkZjjyLe3dhILtO0jvwLlpqF4LXT9sHtlrBWLMOTCxzCCaOkQfM6vwt pvh94Zl9/fK5+AmQxMemybdDdSDz43X5q7QIzc5aVESiMLdQKR0oOjVMqAVhunT60Mgv vsDA== MIME-Version: 1.0 X-Received: by 10.194.77.201 with SMTP id u9mr19138993wjw.41.1422678602604; Fri, 30 Jan 2015 20:30:02 -0800 (PST) Received: by 10.194.101.106 with HTTP; Fri, 30 Jan 2015 20:30:02 -0800 (PST) In-Reply-To: <20150131010014.GB19333@strugglingcoder.info> References: <54CBF396.3090903@ignoranthack.me> <20150131010014.GB19333@strugglingcoder.info> Date: Fri, 30 Jan 2015 20:30:02 -0800 Message-ID: Subject: Re: Intel 82574L (em) From: Jack Vogel To: hiren panchasara Content-Type: text/plain; charset=ISO-8859-1 X-Content-Filtered-By: Mailman/MimeDel 2.1.18-1 Cc: FreeBSD Net X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 31 Jan 2015 04:30:05 -0000 Yup, I wrote that :) Sean, I will check around to see if anything may have changed in that regard. Jack On Fri, Jan 30, 2015 at 5:00 PM, hiren panchasara < hiren@strugglingcoder.info> wrote: > On Fri, Jan 30, 2015 at 01:11:50PM -0800, Sean Bruno wrote: > > > > -----BEGIN PGP SIGNED MESSAGE----- > > Hash: SHA512 > > > > > http://www.intel.com/content/dam/doc/datasheet/82574l-gbe-controller-datasheet.pdf > > > > According to 7.1.11, this device does indeed have 2 queues for stuff and > > or things. So, basic RSS would be possible in something like an Atom > box. > > > > I note that the em(4) driver intentionally disables this on > > initialization. I'm up for some science on my new shiny, soon to be > > router box. Any reason not to default to 1 queue and allow loader.conf > > to raise it to 2? > > Intel folks know better but it seems this is hartwell. > > em_setup_msix() in very start says: > > /* > ** Setup MSI/X for Hartwell: tests have shown > ** use of two queues to be unstable, and to > ** provide no great gain anyway, so we simply > ** seperate the interrupts and use a single queue. > */ > > Things may have changed now. I guess you can try enabling it and find out > :-) > > cheers, > Hiren > From owner-freebsd-net@FreeBSD.ORG Sat Jan 31 06:11:19 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id AE64F208 for ; Sat, 31 Jan 2015 06:11:19 +0000 (UTC) Received: from na01-by2-obe.outbound.protection.outlook.com (mail-by2on0082.outbound.protection.outlook.com [207.46.100.82]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-SHA384 (256/256 bits)) (Client CN "mail.protection.outlook.com", Issuer "MSIT Machine Auth CA 2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 65C59E9 for ; Sat, 31 Jan 2015 06:11:18 +0000 (UTC) Received: from BLUPR0801MB674.namprd08.prod.outlook.com (10.141.255.11) by BLUPR0801MB674.namprd08.prod.outlook.com (10.141.255.11) with Microsoft SMTP Server (TLS) id 15.1.75.20; Sat, 31 Jan 2015 06:11:11 +0000 Received: from BLUPR0801MB674.namprd08.prod.outlook.com ([10.141.255.11]) by BLUPR0801MB674.namprd08.prod.outlook.com ([10.141.255.11]) with mapi id 15.01.0075.002; Sat, 31 Jan 2015 06:11:11 +0000 From: David DeSimone To: "freebsd-net@freebsd.org" Subject: RE: Problems with DNSSEC -- answer in fragmented UDP doesn't work Thread-Topic: Problems with DNSSEC -- answer in fragmented UDP doesn't work Thread-Index: AQHQOx3aTKtmAUOfCkCczkjPsBAgBJzZa4gAgABW7YA= Date: Sat, 31 Jan 2015 06:11:11 +0000 Message-ID: References: <54C918D2.7090805@FreeBSD.org> In-Reply-To: Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [173.74.95.3] authentication-results: freebsd.org; dkim=none (message not signed) header.d=none; x-microsoft-antispam: BCL:0;PCL:0;RULEID:;SRVR:BLUPR0801MB674; x-exchange-antispam-report-test: UriScan:; x-exchange-antispam-report-cfa-test: BCL:0;PCL:0;RULEID:;SRVR:BLUPR0801MB674; x-forefront-prvs: 0473A03F3F x-forefront-antispam-report: SFV:NSPM; SFS:(10009020)(6009001)(51704005)(24454002)(46102003)(230673001)(99286002)(92566002)(74316001)(40100003)(19580395003)(77156002)(450100001)(106116001)(50986999)(87936001)(122556002)(76176999)(62966003)(54356999)(2656002)(107886001)(2351001)(2950100001)(2900100001)(102836002)(33656002)(66066001)(19580405001)(110136001)(86362001)(76576001)(77096005); DIR:OUT; SFP:1101; SCL:1; SRVR:BLUPR0801MB674; H:BLUPR0801MB674.namprd08.prod.outlook.com; FPR:; SPF:None; MLV:sfv; LANG:en; Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 X-OriginatorOrg: verio.net X-MS-Exchange-CrossTenant-originalarrivaltime: 31 Jan 2015 06:11:11.2560 (UTC) X-MS-Exchange-CrossTenant-fromentityheader: Hosted X-MS-Exchange-CrossTenant-id: 281c3918-264a-4db4-ab20-2dafa1dca324 X-MS-Exchange-Transport-CrossTenantHeadersStamped: BLUPR0801MB674 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 31 Jan 2015 06:11:19 -0000 Kevin Oberman wrote: > > For ipfw you need something like "allow ip from any to me frag". If you > want to restrict this to DNS, restrict it to dst-port 53. Unfortunately, UDP fragments only contain the port number in the very first= fragment. So you will not be able to forward the later fragments based on= port number. You can only see the Src/Dest IP and Protocol number in the = fragment. -- David DeSimone =3D=3D fox@verio.net =3D=3D Network Admin "I don't like spinach, and I'm glad I don't, because if I liked it I'd eat it, and I just hate it." -- Clarence Darrow This email message is intended for the use of the person to whom it has bee= n sent, and may contain information that is confidential or legally protect= ed. If you are not the intended recipient or have received this message in = error, you are not authorized to copy, distribute, or otherwise use this me= ssage or its attachments. Please notify the sender immediately by return e-= mail and permanently delete this message and any attachments. Verio Inc. ma= kes no warranty that this email is error or virus free. Thank you. From owner-freebsd-net@FreeBSD.ORG Sat Jan 31 17:03:23 2015 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id E9A172D3 for ; Sat, 31 Jan 2015 17:03:23 +0000 (UTC) Received: from mail.ignoranthack.me (ignoranthack.me [199.102.79.106]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id C918026D for ; Sat, 31 Jan 2015 17:03:23 +0000 (UTC) Received: from [192.168.200.211] (unknown [50.136.155.142]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) (Authenticated sender: sbruno@ignoranthack.me) by mail.ignoranthack.me (Postfix) with ESMTPSA id BAF601941DD; Sat, 31 Jan 2015 17:03:15 +0000 (UTC) Message-ID: <54CD0AD2.3090903@ignoranthack.me> Date: Sat, 31 Jan 2015 09:03:14 -0800 From: Sean Bruno Reply-To: sbruno@freebsd.org User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:31.0) Gecko/20100101 Thunderbird/31.4.0 MIME-Version: 1.0 To: Jack Vogel Subject: Re: Intel 82574L (em) References: <54CBF396.3090903@ignoranthack.me> <20150131010014.GB19333@strugglingcoder.info> In-Reply-To: Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit Cc: FreeBSD Net X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 31 Jan 2015 17:03:24 -0000 -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA512 On 01/30/15 20:30, Jack Vogel wrote: > Yup, I wrote that :) > > Sean, I will check around to see if anything may have changed in > that regard. > > Jack Maybe, but the linux driver has the same limitation and does not enable multiple queues either. sean https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/tree/drivers/net/ethernet/intel/e1000/e1000_main.c?id=refs/tags/v3.19-rc6#n1300 -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQF8BAEBCgBmBQJUzQrPXxSAAAAAAC4AKGlzc3Vlci1mcHJAbm90YXRpb25zLm9w ZW5wZ3AuZmlmdGhob3JzZW1hbi5uZXRCQUFENDYzMkU3MTIxREU4RDIwOTk3REQx MjAxRUZDQTFFNzI3RTY0AAoJEBIB78oecn5kkrAH/jtCsVpeM1CkZnUFkX7DRHzt Lk/YBulBUEGbZy7uo1hop/cUsf6i9XO4uKxKQM4dZZ8TU/Op2GiKwkgFPcEoa5XP rnnG3H16cScSrICpLdoJqFT0BmFy+ocYl4IGKV299XPb/14+34vubfkORFn+RURa 2RfThLSwYagKnbLQzNfdv+HP4bU1o+7rhfLAmFRj3yi1BHBu+Ha82IlX9tfpG6zd fR9tXDtTfA5izpHKS4hfpi96a1BfuU1PYmemDrWQOrXUdXLu24yyXsqkow+rw9Zi BBBfPX+Sq+MfqVkR2UJZl3wORiPhBX6hKrpkhPrN5F0+PQ6MrSmS64cM4Km5kYU= =LHBt -----END PGP SIGNATURE-----