mm: fix page table unmap for stack guard page properly

[net-next-2.6.git] / mm / memory.c

diff --git a/mm/memory.c b/mm/memory.c
index bde42c6d3633f15cfe51b1eae8e3e56833e86955..b6e5fd23cc5a48e13f49b0d824ca3cc9713bd3ab 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -307,7 +307,6 @@ void free_pgd_range(struct mmu_gather *tlb,
 {
        pgd_t *pgd;
        unsigned long next;
-       unsigned long start;
 
        /*
         * The next few lines have given us lots of grief...
@@ -351,7 +350,6 @@ void free_pgd_range(struct mmu_gather *tlb,
        if (addr > end - 1)
                return;
 
-       start = addr;
        pgd = pgd_offset(tlb->mm, addr);
        do {
                next = pgd_addr_end(addr, end);
@@ -2008,11 +2006,10 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 {
        pgd_t *pgd;
        unsigned long next;
-       unsigned long start = addr, end = addr + size;
+       unsigned long end = addr + size;
        int err;
 
        BUG_ON(addr >= end);
-       mmu_notifier_invalidate_range_start(mm, start, end);
        pgd = pgd_offset(mm, addr);
        do {
                next = pgd_addr_end(addr, end);
@@ -2020,7 +2017,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
                if (err)
                        break;
        } while (pgd++, addr = next, addr != end);
-       mmu_notifier_invalidate_range_end(mm, start, end);
+
        return err;
 }
 EXPORT_SYMBOL_GPL(apply_to_page_range);
@@ -2630,6 +2627,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
        swp_entry_t entry;
        pte_t pte;
        struct mem_cgroup *ptr = NULL;
+       int exclusive = 0;
        int ret = 0;
 
        if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
@@ -2724,10 +2722,12 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
        if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) {
                pte = maybe_mkwrite(pte_mkdirty(pte), vma);
                flags &= ~FAULT_FLAG_WRITE;
+               ret |= VM_FAULT_WRITE;
+               exclusive = 1;
        }
        flush_icache_page(vma, page);
        set_pte_at(mm, address, page_table, pte);
-       page_add_anon_rmap(page, vma, address);
+       do_page_add_anon_rmap(page, vma, address, exclusive);
        /* It's better to call commit-charge after rmap is established */
        mem_cgroup_commit_charge_swapin(page, ptr);
 
@@ -2759,6 +2759,26 @@ out_release:
        return ret;
 }
 
+/*
+ * This is like a special single-page "expand_downwards()",
+ * except we must first make sure that 'address-PAGE_SIZE'
+ * doesn't hit another vma.
+ *
+ * The "find_vma()" will do the right thing even if we wrap
+ */
+static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address)
+{
+       address &= PAGE_MASK;
+       if ((vma->vm_flags & VM_GROWSDOWN) && address == vma->vm_start) {
+               address -= PAGE_SIZE;
+               if (find_vma(vma->vm_mm, address) != vma)
+                       return -ENOMEM;
+
+               expand_stack(vma, address);
+       }
+       return 0;
+}
+
 /*
  * We enter with non-exclusive mmap_sem (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
@@ -2772,19 +2792,23 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
        spinlock_t *ptl;
        pte_t entry;
 
+       pte_unmap(page_table);
+
+       /* Check if we need to add a guard page to the stack */
+       if (check_stack_guard_page(vma, address) < 0)
+               return VM_FAULT_SIGBUS;
+
+       /* Use the zero-page for reads */
        if (!(flags & FAULT_FLAG_WRITE)) {
                entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
                                                vma->vm_page_prot));
-               ptl = pte_lockptr(mm, pmd);
-               spin_lock(ptl);
+               page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
                if (!pte_none(*page_table))
                        goto unlock;
                goto setpte;
        }
 
        /* Allocate our own private page. */
-       pte_unmap(page_table);
-
        if (unlikely(anon_vma_prepare(vma)))
                goto oom;
        page = alloc_zeroed_user_highpage_movable(vma, address);