From: Greg Kroah-Hartman Date: Wed, 27 May 2009 21:59:21 +0000 (-0700) Subject: .27 patch actually added. X-Git-Tag: v2.6.27.25~13 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=030e717a8d5e6b65d388b0507461718d8f3a98c6;p=thirdparty%2Fkernel%2Fstable-queue.git .27 patch actually added. --- diff --git a/queue-2.6.27/x86-work-around-fedora-11-x86-32-kernel-failures-on-intel-atom-cpus.patch b/queue-2.6.27/x86-work-around-fedora-11-x86-32-kernel-failures-on-intel-atom-cpus.patch new file mode 100644 index 00000000000..388f6c98073 --- /dev/null +++ b/queue-2.6.27/x86-work-around-fedora-11-x86-32-kernel-failures-on-intel-atom-cpus.patch @@ -0,0 +1,51 @@ +From stable-bounces@linux.kernel.org Wed May 27 14:53:51 2009 +From: Ingo Molnar +Date: Fri, 22 May 2009 16:30:39 -0400 +Subject: x86: work around Fedora-11 x86-32 kernel failures on Intel Atom CPUs +To: stable@kernel.org +Message-ID: <20090522163039.587176f0@dhcp-100-2-144.bos.redhat.com> + + +From: Ingo Molnar +commit 211b3d03c7400f48a781977a50104c9d12f4e229 upstream + +[Trivial backport to 2.6.27 by cebbert@redhat.com] + +x86: work around Fedora-11 x86-32 kernel failures on Intel Atom CPUs + +Impact: work around boot crash + +Work around Intel Atom erratum AAH41 (probabilistically) - it's triggering +in the field. + +Reported-by: Linus Torvalds +Tested-by: Kyle McMartin +Signed-off-by: Ingo Molnar +Cc: +Signed-off-by: Greg Kroah-Hartman +--- + +--- + arch/x86/mm/pageattr.c | 11 +++++++++++ + 1 file changed, 11 insertions(+) + +--- a/arch/x86/mm/pageattr.c ++++ b/arch/x86/mm/pageattr.c +@@ -565,6 +565,17 @@ static int split_large_page(pte_t *kpte, + ref_prot = pte_pgprot(pte_mkexec(pte_clrhuge(*kpte))); + pgprot_val(ref_prot) |= _PAGE_PRESENT; + __set_pmd_pte(kpte, address, mk_pte(base, ref_prot)); ++ ++ /* ++ * Intel Atom errata AAH41 workaround. ++ * ++ * The real fix should be in hw or in a microcode update, but ++ * we also probabilistically try to reduce the window of having ++ * a large TLB mixed with 4K TLBs while instruction fetches are ++ * going on. ++ */ ++ __flush_tlb_all(); ++ + base = NULL; + + out_unlock: