[PATCH] paravirt: lazy mmu mode hooks.patch

Implement lazy MMU update hooks which are SMP safe for both direct and shadow
page tables.  The idea is that PTE updates and page invalidations while in
lazy mode can be batched into a single hypercall.  We use this in VMI for
shadow page table synchronization, and it is a win.  It also can be used by
PPC and for direct page tables on Xen.

For SMP, the enter / leave must happen under protection of the page table
locks for page tables which are being modified.  This is because otherwise,
you end up with stale state in the batched hypercall, which other CPUs can
race ahead of.  Doing this under the protection of the locks guarantees the
synchronization is correct, and also means that spurious faults which are
generated during this window by remote CPUs are properly handled, as the page
fault handler must re-check the PTE under protection of the same lock.

Signed-off-by: Zachary Amsden <zach@vmware.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 12 insertions, 0 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 2e754621d333..9cf3f341a28a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -506,6 +506,7 @@ again:
         src_pte = pte_offset_map_nested(src_pmd, addr);
         src_ptl = pte_lockptr(src_mm, src_pmd);
         spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
+        arch_enter_lazy_mmu_mode();
 
         do {
                 /*
@@ -527,6 +528,7 @@ again:
                 progress += 8;
         } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
 
+        arch_leave_lazy_mmu_mode();
         spin_unlock(src_ptl);
         pte_unmap_nested(src_pte - 1);
         add_mm_rss(dst_mm, rss[0], rss[1]);
@@ -628,6 +630,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
         int anon_rss = 0;
 
         pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+        arch_enter_lazy_mmu_mode();
         do {
                 pte_t ptent = *pte;
                 if (pte_none(ptent)) {
@@ -694,6 +697,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
         } while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0));
 
         add_mm_rss(mm, file_rss, anon_rss);
+        arch_leave_lazy_mmu_mode();
         pte_unmap_unlock(pte - 1, ptl);
 
         return addr;
@@ -1109,6 +1113,7 @@ static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd,
         pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
         if (!pte)
                 return -ENOMEM;
+        arch_enter_lazy_mmu_mode();
         do {
                 struct page *page = ZERO_PAGE(addr);
                 pte_t zero_pte = pte_wrprotect(mk_pte(page, prot));
@@ -1118,6 +1123,7 @@ static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd,
                 BUG_ON(!pte_none(*pte));
                 set_pte_at(mm, addr, pte, zero_pte);
         } while (pte++, addr += PAGE_SIZE, addr != end);
+        arch_leave_lazy_mmu_mode();
         pte_unmap_unlock(pte - 1, ptl);
         return 0;
 }
@@ -1275,11 +1281,13 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
         pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
         if (!pte)
                 return -ENOMEM;
+        arch_enter_lazy_mmu_mode();
         do {
                 BUG_ON(!pte_none(*pte));
                 set_pte_at(mm, addr, pte, pfn_pte(pfn, prot));
                 pfn++;
         } while (pte++, addr += PAGE_SIZE, addr != end);
+        arch_leave_lazy_mmu_mode();
         pte_unmap_unlock(pte - 1, ptl);
         return 0;
 }
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 955f9d0e38aa..3b8f3c0c63f3 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -34,6 +34,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
         spinlock_t *ptl;
 
         pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+        arch_enter_lazy_mmu_mode();
         do {
                 oldpte = *pte;
                 if (pte_present(oldpte)) {
@@ -70,6 +71,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
                 }
 
         } while (pte++, addr += PAGE_SIZE, addr != end);
+        arch_leave_lazy_mmu_mode();
         pte_unmap_unlock(pte - 1, ptl);
 }
 
diff --git a/mm/mremap.c b/mm/mremap.c
index 7c15cf3373ad..9c769fa29f32 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -98,6 +98,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
         new_ptl = pte_lockptr(mm, new_pmd);
         if (new_ptl != old_ptl)
                 spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
+        arch_enter_lazy_mmu_mode();
 
         for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE,
                                    new_pte++, new_addr += PAGE_SIZE) {
@@ -109,6 +110,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
                 set_pte_at(mm, new_addr, new_pte, pte);
         }
 
+        arch_leave_lazy_mmu_mode();
         if (new_ptl != old_ptl)
                 spin_unlock(new_ptl);
         pte_unmap_nested(new_pte - 1);