Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965239Ab1C3VTr (ORCPT ); Wed, 30 Mar 2011 17:19:47 -0400 Received: from mga01.intel.com ([192.55.52.88]:24598 "EHLO mga01.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S965189Ab1C3VJl (ORCPT ); Wed, 30 Mar 2011 17:09:41 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.63,270,1299484800"; d="scan'208";a="673448624" From: Andi Kleen References: <20110330203.501921634@firstfloor.org> In-Reply-To: <20110330203.501921634@firstfloor.org> To: shaohua.li@intel.com, y-goto@jp.fujitsu.com, ak@linux.intel.com, riel@redhat.com, asit.k.mallick@intel.com, torvalds@linux-foundation.org, akpm@linux-foundation.org, linux-mm@kvack.org, mingo@elte.hu, gregkh@suse.de, linux-kernel@vger.kernel.org, stable@kernel.org, tim.bird@am.sony.com Subject: [PATCH] [214/275] x86: Flush TLB if PGD entry is changed in i386 PAE mode Message-Id: <20110330210739.07D5E3E1A05@tassilo.jf.intel.com> Date: Wed, 30 Mar 2011 14:07:38 -0700 (PDT) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3331 Lines: 88 2.6.35-longterm review patch. If anyone has any objections, please let me know. ------------------ From: Shaohua Li commit 4981d01eada5354d81c8929d5b2836829ba3df7b upstream. According to intel CPU manual, every time PGD entry is changed in i386 PAE mode, we need do a full TLB flush. Current code follows this and there is comment for this too in the code. But current code misses the multi-threaded case. A changed page table might be used by several CPUs, every such CPU should flush TLB. Usually this isn't a problem, because we prepopulate all PGD entries at process fork. But when the process does munmap and follows new mmap, this issue will be triggered. When it happens, some CPUs keep doing page faults: http://marc.info/?l=linux-kernel&m=129915020508238&w=2 Reported-by: Yasunori Goto Tested-by: Yasunori Goto Signed-off-by: Andi Kleen Reviewed-by: Rik van Riel Signed-off-by: Shaohua Li Cc: Mallick Asit K Cc: Linus Torvalds Cc: Andrew Morton Cc: linux-mm LKML-Reference: <1300246649.2337.95.camel@sli10-conroe> Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/pgtable-3level.h | 11 +++-------- arch/x86/mm/pgtable.c | 3 +-- 2 files changed, 4 insertions(+), 10 deletions(-) Index: linux-2.6.35.y/arch/x86/include/asm/pgtable-3level.h =================================================================== --- linux-2.6.35.y.orig/arch/x86/include/asm/pgtable-3level.h 2011-03-29 22:50:32.352430601 -0700 +++ linux-2.6.35.y/arch/x86/include/asm/pgtable-3level.h 2011-03-29 23:03:02.707230900 -0700 @@ -69,8 +69,6 @@ static inline void pud_clear(pud_t *pudp) { - unsigned long pgd; - set_pud(pudp, __pud(0)); /* @@ -79,13 +77,10 @@ * section 8.1: in PAE mode we explicitly have to flush the * TLB via cr3 if the top-level pgd is changed... * - * Make sure the pud entry we're updating is within the - * current pgd to avoid unnecessary TLB flushes. + * Currently all places where pud_clear() is called either have + * flush_tlb_mm() followed or don't need TLB flush (x86_64 code or + * pud_clear_bad()), so we don't need TLB flush here. */ - pgd = read_cr3(); - if (__pa(pudp) >= pgd && __pa(pudp) < - (pgd + sizeof(pgd_t)*PTRS_PER_PGD)) - write_cr3(pgd); } #ifdef CONFIG_SMP Index: linux-2.6.35.y/arch/x86/mm/pgtable.c =================================================================== --- linux-2.6.35.y.orig/arch/x86/mm/pgtable.c 2011-03-29 22:50:32.352430601 -0700 +++ linux-2.6.35.y/arch/x86/mm/pgtable.c 2011-03-29 23:03:02.708230874 -0700 @@ -160,8 +160,7 @@ * section 8.1: in PAE mode we explicitly have to flush the * TLB via cr3 if the top-level pgd is changed... */ - if (mm == current->active_mm) - write_cr3(read_cr3()); + flush_tlb_mm(mm); } #else /* !CONFIG_X86_PAE */ -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/