]> git.karo-electronics.de Git - karo-tx-linux.git/commit
x86: Flush TLB if PGD entry is changed in i386 PAE mode
authorShaohua Li <shaohua.li@intel.com>
Wed, 16 Mar 2011 03:37:29 +0000 (11:37 +0800)
committerWilly Tarreau <w@1wt.eu>
Sat, 30 Apr 2011 14:53:19 +0000 (16:53 +0200)
commit89296f1f0b4ad37daa78859155708f1cbb568d15
treeef3ce7034038afe0ee573466caebe000830e8013
parent451d692b122af43b68fb75466d8f94cf35ad9680
x86: Flush TLB if PGD entry is changed in i386 PAE mode

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<y-goto@jp.fujitsu.com>
Tested-by: Yasunori Goto<y-goto@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Shaohua Li<shaohua.li@intel.com>
Cc: Mallick Asit K <asit.k.mallick@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm <linux-mm@kvack.org>
LKML-Reference: <1300246649.2337.95.camel@sli10-conroe>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
arch/x86/mm/pgtable.c
include/asm-x86/pgtable-3level.h