[PATCH] x86: ptep_clear optimization

Add a new accessor for PTEs, which passes the full hint from the mmu_gather
struct; this allows architectures with hardware pagetables to optimize away
atomic PTE operations when destroying an address space.  Removing the
locked operation should allow better pipelining of memory access in this
loop.  I measured an average savings of 30-35 cycles per zap_pte_range on
the first 500 destructions on Pentium-M, but I believe the optimization
would win more on older processors which still assert the bus lock on xchg
for an exclusive cacheline.

Update: I made some new measurements, and this saves exactly 26 cycles over
ptep_get_and_clear on Pentium M.  On P4, with a PAE kernel, this saves 180
cycles per ptep_get_and_clear, for a whopping 92160 cycles savings for a
full address space destruction.

pte_clear_full is not yet used, but is provided for future optimizations
(in particular, when running inside of a hypervisor that queues page table
updates, the full hint allows us to avoid queueing unnecessary page table
update for an address space in the process of being destroyed.

This is not a huge win, but it does help a bit, and sets the stage for
further hypervisor optimization of the mm layer on all architectures.

Signed-off-by: Zachary Amsden <zach@vmware.com>
Cc: Christoph Lameter <christoph@lameter.com>
Cc: <linux-mm@kvack.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 32 insertions, 2 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index f40593565173..f86c1e549466 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -101,6 +101,22 @@ do {				  					  \
 })
 #endif
 
+#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
+#define ptep_get_and_clear_full(__mm, __address, __ptep, __full)        \
+({                                                                      \
+        pte_t __pte;                                                    \
+        __pte = ptep_get_and_clear((__mm), (__address), (__ptep));      \
+        __pte;                                                          \
+})
+#endif
+
+#ifndef __HAVE_ARCH_PTE_CLEAR_FULL
+#define pte_clear_full(__mm, __address, __ptep, __full)                 \
+do {                                                                    \
+        pte_clear((__mm), (__address), (__ptep));                       \
+} while (0)
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
 #define ptep_clear_flush(__vma, __address, __ptep)                      \
 ({                                                                      \
diff --git a/include/asm-i386/pgtable.h b/include/asm-i386/pgtable.h
index f51fd2c956bb..d74185aee15b 100644
--- a/include/asm-i386/pgtable.h
+++ b/include/asm-i386/pgtable.h
@@ -260,6 +260,18 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned
         return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte_low);
 }
 
+static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full)
+{
+        pte_t pte;
+        if (full) {
+                pte = *ptep;
+                *ptep = __pte(0);
+        } else {
+                pte = ptep_get_and_clear(mm, addr, ptep);
+        }
+        return pte;
+}
+
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
         clear_bit(_PAGE_BIT_RW, &ptep->pte_low);
@@ -417,6 +429,7 @@ extern void noexec_setup(const char *str);
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 #define __HAVE_ARCH_PTE_SAME
 #include <asm-generic/pgtable.h>
diff --git a/mm/memory.c b/mm/memory.c
index b25f5e58a14c..788a62810340 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -562,7 +562,8 @@ static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
                                      page->index > details->last_index))
                                         continue;
                         }
-                        ptent = ptep_get_and_clear(tlb->mm, addr, pte);
+                        ptent = ptep_get_and_clear_full(tlb->mm, addr, pte,
+                                                        tlb->fullmm);
                         tlb_remove_tlb_entry(tlb, pte, addr);
                         if (unlikely(!page))
                                 continue;
@@ -590,7 +591,7 @@ static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
                         continue;
                 if (!pte_file(ptent))
                         free_swap_and_cache(pte_to_swp_entry(ptent));
-                pte_clear(tlb->mm, addr, pte);
+                pte_clear_full(tlb->mm, addr, pte, tlb->fullmm);
         } while (pte++, addr += PAGE_SIZE, addr != end);
         pte_unmap(pte - 1);
 }