From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ben Hutchings Subject: Re: [PATCH stable v3.2 v3.4] ipv4: disable bh while doing route gc Date: Tue, 21 Oct 2014 20:32:51 +0100 Message-ID: <1413919971.31953.39.camel@decadent.org.uk> References: <6c3d6eca5d6a15c01393b010f2116bd169477c5a.1413215324.git.mleitner@redhat.com> <20141013.135127.1915115817707962111.davem@davemloft.net> <1413774581.31953.12.camel@decadent.org.uk> <5446AF2A.1030508@redhat.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg="pgp-sha512"; protocol="application/pgp-signature"; boundary="=-zvb7HOHc3Xa+e3qr8dMb" Cc: David Miller , stable@vger.kernel.org, netdev@vger.kernel.org, hannes@stressinduktion.org To: Marcelo Ricardo Leitner Return-path: In-Reply-To: <5446AF2A.1030508@redhat.com> Sender: stable-owner@vger.kernel.org List-Id: netdev.vger.kernel.org --=-zvb7HOHc3Xa+e3qr8dMb Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Tue, 2014-10-21 at 17:08 -0200, Marcelo Ricardo Leitner wrote: > On 20-10-2014 01:09, Ben Hutchings wrote: > > On Mon, 2014-10-13 at 13:51 -0400, David Miller wrote: > >> From: Marcelo Ricardo Leitner > >> Date: Mon, 13 Oct 2014 14:03:30 -0300 > >> > >>> Further tests revealed that after moving the garbage collector to a w= ork > >>> queue and protecting it with a spinlock may leave the system prone to > >>> soft lockups if bottom half gets very busy. > >>> > >>> It was reproced with a set of firewall rules that REJECTed packets. I= f > >>> the NIC bottom half handler ends up running on the same CPU that is > >>> running the garbage collector on a very large cache, the garbage > >>> collector will not be able to do its job due to the amount of work > >>> needed for handling the REJECTs and also won't reschedule. > >>> > >>> The fix is to disable bottom half during the garbage collecting, as i= t > >>> already was in the first place (most calls to it came from softirqs). > >>> > >>> Signed-off-by: Marcelo Ricardo Leitner > >>> Acked-by: Hannes Frederic Sowa > >>> Acked-by: David S. Miller > >>> Cc: stable@vger.kernel.org > >> > >> -stable folks, please integrate this directly, thanks! > > > > I've appplied this and the previous two patches mentioned ('ipv4: move > > route garbage collector to work queue' and 'ipv4: avoid parallel route > > cache gc executions'). But I didn't get the other two from you. The > > last batch of networking fixes I received and applied was dated > > 2014-08-07, and the next one I've seen is dated 2014-10-11 and has > > nothing for 3.2 or 3.4. Did I miss one between these? >=20 > Sorry to ask Ben but, where did you apply them? I'm not seeing the commit= s on=20 > linux-stable.git and couldn't find their summaries anywhere else. They're in a patch queue that I've just pushed to: git://git.kernel.org/pub/scm/linux/kernel/git/bwh/linux-3.2.y-queue.git Ben. --=20 Ben Hutchings Reality is just a crutch for people who can't handle science fiction. --=-zvb7HOHc3Xa+e3qr8dMb Content-Type: application/pgp-signature; name="signature.asc" Content-Description: This is a digitally signed message part -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQIVAwUAVEa06Oe/yOyVhhEJAQqNKQ//dTLrv5sZOSW44DQ36MyC9M5I8Df/gLMN 7IlFlLhR+XUpA3UvrDAIeKqOU9PbbEf3ky+DuAw9uQVjkGAUlr7mEnxP2qa9RfkV mUdkVuO6vJ+JN2CtkOph9IvTn3zt3OXCMtmeW40c98iEwH4/aLuajjFYII+pPp39 oc2BkALNwaCVjLkXM7jXYqJrk62LCM8oSGpxCptaqK4q3MevOE4O32rAZ5d2Sohy ZcnPlhkGg2uTNLBRxqFbJXLxTPJ+QuPLA6hpkR3audwk9c/wMSsPLZ7bMkMeVQRO 3iIXFaY3s/CXTRHyTW5L0WvqWJnRLLw1ed6tnZwI6f7T7A1rZuRn+doX5X1JZxi0 XTorgfaTttFhzaqTqNM3GO/N4HBErA8zuGusnW3/qOpmflpVOrfigIlFVSBG+/4W ouGTz9C9Drz0zM1yoUQkKaJzI1tdCpUo5KG0c/Is74LSu4d6/7MX/oKu2UxWG6uS PKJ7KI3GvyIDimEJdJrLXUIG+ilA9X1E+c9Bxu4pCP6OE16e1RwBqMx4mJigsg6t aDumc+Cj0UWff1OFBXunb+0K+2IHuOOBb8nDY5X0Av4b5Fp/mATcNEqU7gu8njMV hfQWrJynEqllvkRLagzAtkESMfNJtOA0ehsMsIifSyrtIzUFTEO2h5L7sZG2HHba 6A0X0qAMxjI= =c5Bi -----END PGP SIGNATURE----- --=-zvb7HOHc3Xa+e3qr8dMb--