X-Git-Url: http://git.rot13.org/?a=blobdiff_plain;ds=sidebyside;f=mm%2Fmremap.c;h=1903bdf65e428d88e5bf124243d99ee7ab7c51e3;hb=253aa11578c1b89757282430891bb66ae5300092;hp=318eea5467a05bac295b8723cf6e0b216becef02;hpb=d0de32d9b71e11cc51618c2045086e9694093d01;p=powerpc.git

diff --git a/mm/mremap.c b/mm/mremap.c
index 318eea5467..1903bdf65e 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -13,6 +13,7 @@
 #include <linux/shm.h>
 #include <linux/mman.h>
 #include <linux/swap.h>
+#include <linux/capability.h>
 #include <linux/fs.h>
 #include <linux/highmem.h>
 #include <linux/security.h>
@@ -28,9 +29,6 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
 	pud_t *pud;
 	pmd_t *pmd;
 
-	/*
-	 * We don't need page_table_lock: we have mmap_sem exclusively.
-	 */
 	pgd = pgd_offset(mm, addr);
 	if (pgd_none_or_clear_bad(pgd))
 		return NULL;
@@ -50,30 +48,20 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
 	pud_t *pud;
-	pmd_t *pmd = NULL;
-	pte_t *pte;
+	pmd_t *pmd;
 
-	/*
-	 * We do need page_table_lock: because allocators expect that.
-	 */
-	spin_lock(&mm->page_table_lock);
 	pgd = pgd_offset(mm, addr);
 	pud = pud_alloc(mm, pgd, addr);
 	if (!pud)
-		goto out;
+		return NULL;
 
 	pmd = pmd_alloc(mm, pud, addr);
 	if (!pmd)
-		goto out;
+		return NULL;
+
+	if (!pmd_present(*pmd) && __pte_alloc(mm, pmd, addr))
+		return NULL;
 
-	pte = pte_alloc_map(mm, pmd, addr);
-	if (!pte) {
-		pmd = NULL;
-		goto out;
-	}
-	pte_unmap(pte);
-out:
-	spin_unlock(&mm->page_table_lock);
 	return pmd;
 }
 
@@ -85,6 +73,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	struct address_space *mapping = NULL;
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *old_pte, *new_pte, pte;
+	spinlock_t *old_ptl, *new_ptl;
 
 	if (vma->vm_file) {
 		/*
@@ -100,9 +89,15 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 			new_vma->vm_truncate_count = 0;
 	}
 
-	spin_lock(&mm->page_table_lock);
-	old_pte = pte_offset_map(old_pmd, old_addr);
-	new_pte = pte_offset_map_nested(new_pmd, new_addr);
+	/*
+	 * We don't have to worry about the ordering of src and dst
+	 * pte locks because exclusive mmap_sem prevents deadlock.
+	 */
+	old_pte = pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl);
+ 	new_pte = pte_offset_map_nested(new_pmd, new_addr);
+	new_ptl = pte_lockptr(mm, new_pmd);
+	if (new_ptl != old_ptl)
+		spin_lock(new_ptl);
 
 	for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE,
 				   new_pte++, new_addr += PAGE_SIZE) {
@@ -114,9 +109,10 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 		set_pte_at(mm, new_addr, new_pte, pte);
 	}
 
+	if (new_ptl != old_ptl)
+		spin_unlock(new_ptl);
 	pte_unmap_nested(new_pte - 1);
-	pte_unmap(old_pte - 1);
-	spin_unlock(&mm->page_table_lock);
+	pte_unmap_unlock(old_pte - 1, old_ptl);
 	if (mapping)
 		spin_unlock(&mapping->i_mmap_lock);
 }
@@ -167,6 +163,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	unsigned long new_pgoff;
 	unsigned long moved_len;
 	unsigned long excess = 0;
+	unsigned long hiwater_vm;
 	int split = 0;
 
 	/*
@@ -205,9 +202,15 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	}
 
 	/*
-	 * if we failed to move page tables we still do total_vm increment
-	 * since do_munmap() will decrement it by old_len == new_len
+	 * If we failed to move page tables we still do total_vm increment
+	 * since do_munmap() will decrement it by old_len == new_len.
+	 *
+	 * Since total_vm is about to be raised artificially high for a
+	 * moment, we need to restore high watermark afterwards: if stats
+	 * are taken meanwhile, total_vm and hiwater_vm appear too high.
+	 * If this were a serious issue, we'd add a flag to do_munmap().
 	 */
+	hiwater_vm = mm->hiwater_vm;
 	mm->total_vm += new_len >> PAGE_SHIFT;
 	vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT);
 
@@ -216,6 +219,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 		vm_unacct_memory(excess >> PAGE_SHIFT);
 		excess = 0;
 	}
+	mm->hiwater_vm = hiwater_vm;
 
 	/* Restore VM_ACCOUNT if one or two pieces of vma left */
 	if (excess) {
@@ -320,7 +324,7 @@ unsigned long do_mremap(unsigned long addr,
 	/* We can't remap across vm area boundaries */
 	if (old_len > vma->vm_end - addr)
 		goto out;
-	if (vma->vm_flags & VM_DONTEXPAND) {
+	if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) {
 		if (new_len > old_len)
 			goto out;
 	}