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>

2 files changed, 31 insertions, 17 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 5f0d797d33fd..44ef329531c3 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -125,10 +125,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres
 #define pgd_offset_gate(mm, addr)       pgd_offset(mm, addr)
 #endif
 
-#ifndef __HAVE_ARCH_LAZY_MMU_PROT_UPDATE
-#define lazy_mmu_prot_update(pte)       do { } while (0)
-#endif
-
 #ifndef __HAVE_ARCH_MOVE_PTE
 #define move_pte(pte, prot, old_addr, new_addr) (pte)
 #endif
diff --git a/include/asm-ia64/pgtable.h b/include/asm-ia64/pgtable.h
index 6b4216edbb9c..0971ec90807e 100644
--- a/include/asm-ia64/pgtable.h
+++ b/include/asm-ia64/pgtable.h
@@ -223,12 +223,6 @@ ia64_phys_addr_valid (unsigned long addr)
  * page table.
  */
 
-/*
- * On some architectures, special things need to be done when setting
- * the PTE in a page table.  Nothing special needs to be on IA-64.
- */
-#define set_pte(ptep, pteval)   (*(ptep) = (pteval))
-#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
 
 #define VMALLOC_START           (RGN_BASE(RGN_GATE) + 0x200000000UL)
 #ifdef CONFIG_VIRTUAL_MEM_MAP
@@ -321,6 +315,36 @@ ia64_phys_addr_valid (unsigned long addr)
 #define pte_mkhuge(pte)         (__pte(pte_val(pte)))
 
 /*
+ * Because ia64's Icache and Dcache is not coherent (on a cpu), we need to
+ * sync icache and dcache when we insert *new* executable page.
+ *  __ia64_sync_icache_dcache() check Pg_arch_1 bit and flush icache
+ * if necessary.
+ *
+ *  set_pte() is also called by the kernel, but we can expect that the kernel
+ *  flushes icache explicitly if necessary.
+ */
+#define pte_present_exec_user(pte)\
+        ((pte_val(pte) & (_PAGE_P | _PAGE_PL_MASK | _PAGE_AR_RX)) == \
+                (_PAGE_P | _PAGE_PL_3 | _PAGE_AR_RX))
+
+extern void __ia64_sync_icache_dcache(pte_t pteval);
+static inline void set_pte(pte_t *ptep, pte_t pteval)
+{
+        /* page is present && page is user  && page is executable
+         * && (page swapin or new page or page migraton
+         *      || copy_on_write with page copying.)
+         */
+        if (pte_present_exec_user(pteval) &&
+            (!pte_present(*ptep) ||
+                pte_pfn(*ptep) != pte_pfn(pteval)))
+                /* load_module() calles flush_icache_range() explicitly*/
+                __ia64_sync_icache_dcache(pteval);
+        *ptep = pteval;
+}
+
+#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
+
+/*
  * Make page protection values cacheable, uncacheable, or write-
  * combining.  Note that "protection" is really a misnomer here as the
  * protection value contains the memory attribute bits, dirty bits, and
@@ -489,12 +513,6 @@ extern struct page *zero_page_memmap_ptr;
 #define HUGETLB_PGDIR_MASK      (~(HUGETLB_PGDIR_SIZE-1))
 #endif
 
-/*
- * IA-64 doesn't have any external MMU info: the page tables contain all the necessary
- * information.  However, we use this routine to take care of any (delayed) i-cache
- * flushing that may be necessary.
- */
-extern void lazy_mmu_prot_update (pte_t pte);
 
 #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 /*
@@ -584,7 +602,7 @@ extern void lazy_mmu_prot_update (pte_t pte);
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 #define __HAVE_ARCH_PTE_SAME
 #define __HAVE_ARCH_PGD_OFFSET_GATE
-#define __HAVE_ARCH_LAZY_MMU_PROT_UPDATE
+
 
 #ifndef CONFIG_PGTABLE_4
 #include <asm-generic/pgtable-nopud.h>