flush icache before set_pte() on ia64: flush icache at set_pte
authorKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Tue, 16 Oct 2007 08:25:44 +0000 (01:25 -0700)
committerLinus Torvalds <torvalds@woody.linux-foundation.org>
Tue, 16 Oct 2007 16:42:59 +0000 (09:42 -0700)
commit954ffcb35f5aca428661d29b96c4eee82b3c19cd
tree2dd8aaf26a8ae81b461b6d5d824ae8744690e483
parent97ee052461446526e1de7236497e6f1b1ffedf8c
flush icache before set_pte() on ia64: flush icache at set_pte

Current ia64 kernel flushes icache by lazy_mmu_prot_update() *after*
set_pte().  This is too late.  This patch removes lazy_mmu_prot_update and
add modfied set_pte() for flushing if necessary.

This patch flush icache of a page when
new pte has exec bit.
&& new pte has present bit
&& new pte is user's page.
&& (old *ptep is not present
            || new pte's pfn is not same to old *ptep's ptn)
&& new pte's page has no Pg_arch_1 bit.
   Pg_arch_1 is set when a page is cache consistent.

I think this condition checks are much easier to understand than considering
"Where sync_icache_dcache() should be inserted ?".

pte_user() for ia64 was removed by http://lkml.org/lkml/2007/6/12/67 as
clean-up. So, I added it again.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Documentation/cachetlb.txt
arch/ia64/mm/init.c
include/asm-generic/pgtable.h
include/asm-ia64/pgtable.h
mm/hugetlb.c
mm/memory.c
mm/migrate.c
mm/mprotect.c
mm/rmap.c