[PATCH] Enable mprotect on huge pages

2.6.16-rc3 uses hugetlb on-demand paging, but it doesn_t support hugetlb
mprotect.

From: David Gibson <david@gibson.dropbear.id.au>

  Remove a test from the mprotect() path which checks that the mprotect()ed
  range on a hugepage VMA is hugepage aligned (yes, really, the sense of
  is_aligned_hugepage_range() is the opposite of what you'd guess :-/).

  In fact, we don't need this test.  If the given addresses match the
  beginning/end of a hugepage VMA they must already be suitably aligned.  If
  they don't, then mprotect_fixup() will attempt to split the VMA.  The very
  first test in split_vma() will check for a badly aligned address on a
  hugepage VMA and return -EINVAL if necessary.

From: "Chen, Kenneth W" <kenneth.w.chen@intel.com>

  On i386 and x86-64, pte flag _PAGE_PSE collides with _PAGE_PROTNONE.  The
  identify of hugetlb pte is lost when changing page protection via mprotect.
  A page fault occurs later will trigger a bug check in huge_pte_alloc().

  The fix is to always make new pte a hugetlb pte and also to clean up
  legacy code where _PAGE_PRESENT is forced on in the pre-faulting day.
Signed-off-by: Zhang Yanmin <yanmin.zhang@intel.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: William Lee Irwin III <wli@holomorphy.com>
Signed-off-by: Ken Chen <kenneth.w.chen@intel.com>
Signed-off-by: Nishanth Aravamudan <nacc@us.ibm.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

include/asm-i386/pgtable.h

@@ -219,13 +219,12 @@ extern unsigned long pg0[];
  * The following only work if pte_present() is true.
  * Undefined behaviour if not..
  */
-#define __LARGE_PTE (_PAGE_PSE | _PAGE_PRESENT)
 static inline int pte_user(pte_t pte)		{ return (pte).pte_low & _PAGE_USER; }
 static inline int pte_read(pte_t pte)		{ return (pte).pte_low & _PAGE_USER; }
 static inline int pte_dirty(pte_t pte)		{ return (pte).pte_low & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return (pte).pte_low & _PAGE_ACCESSED; }
 static inline int pte_write(pte_t pte)		{ return (pte).pte_low & _PAGE_RW; }
-static inline int pte_huge(pte_t pte)		{ return ((pte).pte_low & __LARGE_PTE) == __LARGE_PTE; }
+static inline int pte_huge(pte_t pte)		{ return (pte).pte_low & _PAGE_PSE; }
 
 /*
  * The following only works if pte_present() is not true.
@@ -242,7 +241,7 @@ static inline pte_t pte_mkexec(pte_t pte)	{ (pte).pte_low |= _PAGE_USER; return
 static inline pte_t pte_mkdirty(pte_t pte)	{ (pte).pte_low |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte)	{ (pte).pte_low |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)	{ (pte).pte_low |= _PAGE_RW; return pte; }
-static inline pte_t pte_mkhuge(pte_t pte)	{ (pte).pte_low |= __LARGE_PTE; return pte; }
+static inline pte_t pte_mkhuge(pte_t pte)	{ (pte).pte_low |= _PAGE_PSE; return pte; }
 
 #ifdef CONFIG_X86_PAE
 # include <asm/pgtable-3level.h>

include/asm-ia64/pgtable.h

@@ -314,7 +314,7 @@ ia64_phys_addr_valid (unsigned long addr)
 #define pte_mkyoung(pte)	(__pte(pte_val(pte) | _PAGE_A))
 #define pte_mkclean(pte)	(__pte(pte_val(pte) & ~_PAGE_D))
 #define pte_mkdirty(pte)	(__pte(pte_val(pte) | _PAGE_D))
-#define pte_mkhuge(pte)		(__pte(pte_val(pte) | _PAGE_P))
+#define pte_mkhuge(pte)		(__pte(pte_val(pte)))
 
 /*
  * Macro to a page protection value as "uncacheable".  Note that "protection" is really a

include/asm-x86_64/pgtable.h

@@ -273,7 +273,7 @@ static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
 static inline int pte_write(pte_t pte)		{ return pte_val(pte) & _PAGE_RW; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
-static inline int pte_huge(pte_t pte)		{ return (pte_val(pte) & __LARGE_PTE) == __LARGE_PTE; }
+static inline int pte_huge(pte_t pte)		{ return pte_val(pte) & _PAGE_PSE; }
 
 static inline pte_t pte_rdprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
 static inline pte_t pte_exprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
@@ -285,7 +285,7 @@ static inline pte_t pte_mkexec(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _
 static inline pte_t pte_mkdirty(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
 static inline pte_t pte_mkyoung(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }
-static inline pte_t pte_mkhuge(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | __LARGE_PTE)); return pte; }
+static inline pte_t pte_mkhuge(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_PSE)); return pte; }
 
 struct vm_area_struct;
 

include/linux/hugetlb.h

@@ -41,6 +41,8 @@ struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 				pmd_t *pmd, int write);
 int is_aligned_hugepage_range(unsigned long addr, unsigned long len);
 int pmd_huge(pmd_t pmd);
+void hugetlb_change_protection(struct vm_area_struct *vma,
+		unsigned long address, unsigned long end, pgprot_t newprot);
 
 #ifndef ARCH_HAS_HUGEPAGE_ONLY_RANGE
 #define is_hugepage_only_range(mm, addr, len)	0
@@ -101,6 +103,8 @@ static inline unsigned long hugetlb_total_pages(void)
 #define free_huge_page(p)			({ (void)(p); BUG(); })
 #define hugetlb_fault(mm, vma, addr, write)	({ BUG(); 0; })
 
+#define hugetlb_change_protection(vma, address, end, newprot)
+
 #ifndef HPAGE_MASK
 #define HPAGE_MASK	PAGE_MASK		/* Keep the compiler happy */
 #define HPAGE_SIZE	PAGE_SIZE

mm/hugetlb.c

@@ -565,3 +565,32 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	return i;
 }
+
+void hugetlb_change_protection(struct vm_area_struct *vma,
+		unsigned long address, unsigned long end, pgprot_t newprot)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long start = address;
+	pte_t *ptep;
+	pte_t pte;
+
+	BUG_ON(address >= end);
+	flush_cache_range(vma, address, end);
+
+	spin_lock(&mm->page_table_lock);
+	for (; address < end; address += HPAGE_SIZE) {
+		ptep = huge_pte_offset(mm, address);
+		if (!ptep)
+			continue;
+		if (!pte_none(*ptep)) {
+			pte = huge_ptep_get_and_clear(mm, address, ptep);
+			pte = pte_mkhuge(pte_modify(pte, newprot));
+			set_huge_pte_at(mm, address, ptep, pte);
+			lazy_mmu_prot_update(pte);
+		}
+	}
+	spin_unlock(&mm->page_table_lock);
+
+	flush_tlb_range(vma, start, end);
+}
+

mm/mprotect.c

@@ -124,7 +124,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	 * a MAP_NORESERVE private mapping to writable will now reserve.
 	 */
 	if (newflags & VM_WRITE) {
-		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_SHARED|VM_HUGETLB))) {
+		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_SHARED))) {
 			charged = nrpages;
 			if (security_vm_enough_memory(charged))
 				return -ENOMEM;
@@ -166,7 +166,10 @@ success:
 	 */
 	vma->vm_flags = newflags;
 	vma->vm_page_prot = newprot;
-	change_protection(vma, start, end, newprot);
+	if (is_vm_hugetlb_page(vma))
+		hugetlb_change_protection(vma, start, end, newprot);
+	else
+		change_protection(vma, start, end, newprot);
 	vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
 	vm_stat_account(mm, newflags, vma->vm_file, nrpages);
 	return 0;
@@ -240,11 +243,6 @@ sys_mprotect(unsigned long start, size_t len, unsigned long prot)
 
 		/* Here we know that  vma->vm_start <= nstart < vma->vm_end. */
 
-		if (is_vm_hugetlb_page(vma)) {
-			error = -EACCES;
-			goto out;
-		}
-
 		newflags = vm_flags | (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
 
 		/* newflags >> 4 shift VM_MAY% in place of VM_% */