Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm changes from Ingo Molnar: "The main changes are: continued PAT work by Toshi Kani, plus a new boot time warning about insecure RWX kernel mappings, by Stephen Smalley. The new CONFIG_DEBUG_WX=y warning is marked default-y if CONFIG_DEBUG_RODATA=y is already eanbled, as a special exception, as these bugs are hard to notice and this check already found several live bugs" * 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/mm: Warn on W^X mappings x86/mm: Fix no-change case in try_preserve_large_page() x86/mm: Fix __split_large_page() to handle large PAT bit x86/mm: Fix try_preserve_large_page() to handle large PAT bit x86/mm: Fix gup_huge_p?d() to handle large PAT bit x86/mm: Fix slow_virt_to_phys() to handle large PAT bit x86/mm: Fix page table dump to show PAT bit x86/asm: Add pud_pgprot() and pmd_pgprot() x86/asm: Fix pud/pmd interfaces to handle large PAT bit x86/asm: Add pud/pmd mask interfaces to handle large PAT bit x86/asm: Move PUD_PAGE macros to page_types.h x86/vdso32: Define PGTABLE_LEVELS to 32bit VDSO
2015-11-03 21:23:56 -08:00
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_SMP)		+= tlb.o
 obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o

 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
-obj-$(CONFIG_X86_PTDUMP)	+= dump_pagetables.o
+obj-$(CONFIG_X86_PTDUMP_CORE)	+= dump_pagetables.o

 obj-$(CONFIG_HIGHMEM)		+= highmem_32.o

--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -32,6 +32,8 @@ struct pg_state {
 	const struct addr_marker *marker;
 	unsigned long lines;
 	bool to_dmesg;
+	bool check_wx;
+	unsigned long wx_pages;
 };

 struct addr_marker {
@@ -155,7 +157,7 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
 			pt_dump_cont_printf(m, dmsg, "    ");
 		if ((level == 4 && pr & _PAGE_PAT) ||
 		    ((level == 3 || level == 2) && pr & _PAGE_PAT_LARGE))
-			pt_dump_cont_printf(m, dmsg, "pat ");
+			pt_dump_cont_printf(m, dmsg, "PAT ");
 		else
 			pt_dump_cont_printf(m, dmsg, "    ");
 		if (pr & _PAGE_GLOBAL)
@@ -198,8 +200,8 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 	 * we have now. "break" is either changing perms, levels or
 	 * address space marker.
 	 */
-	prot = pgprot_val(new_prot) & PTE_FLAGS_MASK;
-	cur = pgprot_val(st->current_prot) & PTE_FLAGS_MASK;
+	prot = pgprot_val(new_prot);
+	cur = pgprot_val(st->current_prot);

 	if (!st->level) {
 		/* First entry */
@@ -214,6 +216,16 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		const char *unit = units;
 		unsigned long delta;
 		int width = sizeof(unsigned long) * 2;
+		pgprotval_t pr = pgprot_val(st->current_prot);
+
+		if (st->check_wx && (pr & _PAGE_RW) && !(pr & _PAGE_NX)) {
+			WARN_ONCE(1,
+				  "x86/mm: Found insecure W+X mapping at address %p/%pS\n",
+				  (void *)st->start_address,
+				  (void *)st->start_address);
+			st->wx_pages += (st->current_address -
+					 st->start_address) / PAGE_SIZE;
+		}

 		/*
 		 * Now print the actual finished series
@@ -269,13 +281,13 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr,
 {
 	int i;
 	pte_t *start;
+	pgprotval_t prot;

 	start = (pte_t *) pmd_page_vaddr(addr);
 	for (i = 0; i < PTRS_PER_PTE; i++) {
-		pgprot_t prot = pte_pgprot(*start);
-
+		prot = pte_flags(*start);
 		st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT);
-		note_page(m, st, prot, 4);
+		note_page(m, st, __pgprot(prot), 4);
 		start++;
 	}
 }
@@ -287,18 +299,19 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr,
 {
 	int i;
 	pmd_t *start;
+	pgprotval_t prot;

 	start = (pmd_t *) pud_page_vaddr(addr);
 	for (i = 0; i < PTRS_PER_PMD; i++) {
 		st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT);
 		if (!pmd_none(*start)) {
-			pgprotval_t prot = pmd_val(*start) & PTE_FLAGS_MASK;
-
-			if (pmd_large(*start) || !pmd_present(*start))
+			if (pmd_large(*start) || !pmd_present(*start)) {
+				prot = pmd_flags(*start);
 				note_page(m, st, __pgprot(prot), 3);
-			else
+			} else {
 				walk_pte_level(m, st, *start,
 					       P + i * PMD_LEVEL_MULT);
+			}
 		} else
 			note_page(m, st, __pgprot(0), 3);
 		start++;
@@ -318,19 +331,20 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
 {
 	int i;
 	pud_t *start;
+	pgprotval_t prot;

 	start = (pud_t *) pgd_page_vaddr(addr);

 	for (i = 0; i < PTRS_PER_PUD; i++) {
 		st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT);
 		if (!pud_none(*start)) {
-			pgprotval_t prot = pud_val(*start) & PTE_FLAGS_MASK;
-
-			if (pud_large(*start) || !pud_present(*start))
+			if (pud_large(*start) || !pud_present(*start)) {
+				prot = pud_flags(*start);
 				note_page(m, st, __pgprot(prot), 2);
-			else
+			} else {
 				walk_pmd_level(m, st, *start,
 					       P + i * PUD_LEVEL_MULT);
+			}
 		} else
 			note_page(m, st, __pgprot(0), 2);

@@ -344,13 +358,15 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
 #define pgd_none(a)  pud_none(__pud(pgd_val(a)))
 #endif

-void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
+static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
+				       bool checkwx)
 {
 #ifdef CONFIG_X86_64
 	pgd_t *start = (pgd_t *) &init_level4_pgt;
 #else
 	pgd_t *start = swapper_pg_dir;
 #endif
+	pgprotval_t prot;
 	int i;
 	struct pg_state st = {};

@@ -359,16 +375,20 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
 		st.to_dmesg = true;
 	}

+	st.check_wx = checkwx;
+	if (checkwx)
+		st.wx_pages = 0;
+
 	for (i = 0; i < PTRS_PER_PGD; i++) {
 		st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
 		if (!pgd_none(*start)) {
-			pgprotval_t prot = pgd_val(*start) & PTE_FLAGS_MASK;
-
-			if (pgd_large(*start) || !pgd_present(*start))
+			if (pgd_large(*start) || !pgd_present(*start)) {
+				prot = pgd_flags(*start);
 				note_page(m, &st, __pgprot(prot), 1);
-			else
+			} else {
 				walk_pud_level(m, &st, *start,
 					       i * PGD_LEVEL_MULT);
+			}
 		} else
 			note_page(m, &st, __pgprot(0), 1);

@@ -378,8 +398,26 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
 	/* Flush out the last page */
 	st.current_address = normalize_addr(PTRS_PER_PGD*PGD_LEVEL_MULT);
 	note_page(m, &st, __pgprot(0), 0);
+	if (!checkwx)
+		return;
+	if (st.wx_pages)
+		pr_info("x86/mm: Checked W+X mappings: FAILED, %lu W+X pages found.\n",
+			st.wx_pages);
+	else
+		pr_info("x86/mm: Checked W+X mappings: passed, no W+X pages found.\n");
 }

+void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
+{
+	ptdump_walk_pgd_level_core(m, pgd, false);
+}
+
+void ptdump_walk_pgd_level_checkwx(void)
+{
+	ptdump_walk_pgd_level_core(NULL, NULL, true);
+}
+
+#ifdef CONFIG_X86_PTDUMP
 static int ptdump_show(struct seq_file *m, void *v)
 {
 	ptdump_walk_pgd_level(m, NULL);
@@ -397,10 +435,13 @@ static const struct file_operations ptdump_fops = {
 	.llseek		= seq_lseek,
 	.release	= single_release,
 };
+#endif

 static int pt_dump_init(void)
 {
+#ifdef CONFIG_X86_PTDUMP
 	struct dentry *pe;
+#endif

 #ifdef CONFIG_X86_32
 	/* Not a compile-time constant on x86-32 */
@@ -412,10 +453,12 @@ static int pt_dump_init(void)
 	address_markers[FIXADDR_START_NR].start_address = FIXADDR_START;
 #endif

+#ifdef CONFIG_X86_PTDUMP
 	pe = debugfs_create_file("kernel_page_tables", 0600, NULL, NULL,
 				 &ptdump_fops);
 	if (!pe)
 		return -ENOMEM;
+#endif

 	return 0;
 }
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -118,21 +118,20 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
 	unsigned long mask;
-	pte_t pte = *(pte_t *)&pmd;
 	struct page *head, *page;
 	int refs;

 	mask = _PAGE_PRESENT|_PAGE_USER;
 	if (write)
 		mask |= _PAGE_RW;
-	if ((pte_flags(pte) & mask) != mask)
+	if ((pmd_flags(pmd) & mask) != mask)
 		return 0;
 	/* hugepages are never "special" */
-	VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL);
-	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+	VM_BUG_ON(pmd_flags(pmd) & _PAGE_SPECIAL);
+	VM_BUG_ON(!pfn_valid(pmd_pfn(pmd)));

 	refs = 0;
-	head = pte_page(pte);
+	head = pmd_page(pmd);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
 	do {
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
@@ -195,21 +194,20 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr,
 		unsigned long end, int write, struct page **pages, int *nr)
 {
 	unsigned long mask;
-	pte_t pte = *(pte_t *)&pud;
 	struct page *head, *page;
 	int refs;

 	mask = _PAGE_PRESENT|_PAGE_USER;
 	if (write)
 		mask |= _PAGE_RW;
-	if ((pte_flags(pte) & mask) != mask)
+	if ((pud_flags(pud) & mask) != mask)
 		return 0;
 	/* hugepages are never "special" */
-	VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL);
-	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+	VM_BUG_ON(pud_flags(pud) & _PAGE_SPECIAL);
+	VM_BUG_ON(!pfn_valid(pud_pfn(pud)));

 	refs = 0;
-	head = pte_page(pte);
+	head = pud_page(pud);
 	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
 	do {
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -957,6 +957,8 @@ void mark_rodata_ro(void)
 	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
 #endif
 	mark_nxdata_nx();
+	if (__supported_pte_mask & _PAGE_NX)
+		debug_checkwx();
 }
 #endif

--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1150,6 +1150,8 @@ void mark_rodata_ro(void)
 	free_init_pages("unused kernel",
 			(unsigned long) __va(__pa_symbol(rodata_end)),
 			(unsigned long) __va(__pa_symbol(_sdata)));
+
+	debug_checkwx();
 }

 #endif
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -414,18 +414,28 @@ pmd_t *lookup_pmd_address(unsigned long address)
 phys_addr_t slow_virt_to_phys(void *__virt_addr)
 {
 	unsigned long virt_addr = (unsigned long)__virt_addr;
-	phys_addr_t phys_addr;
-	unsigned long offset;
+	unsigned long phys_addr, offset;
 	enum pg_level level;
-	unsigned long pmask;
 	pte_t *pte;

 	pte = lookup_address(virt_addr, &level);
 	BUG_ON(!pte);
-	pmask = page_level_mask(level);
-	offset = virt_addr & ~pmask;
-	phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
-	return (phys_addr | offset);
+
+	switch (level) {
+	case PG_LEVEL_1G:
+		phys_addr = pud_pfn(*(pud_t *)pte) << PAGE_SHIFT;
+		offset = virt_addr & ~PUD_PAGE_MASK;
+		break;
+	case PG_LEVEL_2M:
+		phys_addr = pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT;
+		offset = virt_addr & ~PMD_PAGE_MASK;
+		break;
+	default:
+		phys_addr = pte_pfn(*pte) << PAGE_SHIFT;
+		offset = virt_addr & ~PAGE_MASK;
+	}
+
+	return (phys_addr_t)(phys_addr | offset);
 }
 EXPORT_SYMBOL_GPL(slow_virt_to_phys);

@@ -458,7 +468,7 @@ static int
 try_preserve_large_page(pte_t *kpte, unsigned long address,
 			struct cpa_data *cpa)
 {
-	unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn;
+	unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn, old_pfn;
 	pte_t new_pte, old_pte, *tmp;
 	pgprot_t old_prot, new_prot, req_prot;
 	int i, do_split = 1;
@@ -478,17 +488,21 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,

 	switch (level) {
 	case PG_LEVEL_2M:
-#ifdef CONFIG_X86_64
+		old_prot = pmd_pgprot(*(pmd_t *)kpte);
+		old_pfn = pmd_pfn(*(pmd_t *)kpte);
+		break;
 	case PG_LEVEL_1G:
-#endif
-		psize = page_level_size(level);
-		pmask = page_level_mask(level);
+		old_prot = pud_pgprot(*(pud_t *)kpte);
+		old_pfn = pud_pfn(*(pud_t *)kpte);
 		break;
 	default:
 		do_split = -EINVAL;
 		goto out_unlock;
 	}

+	psize = page_level_size(level);
+	pmask = page_level_mask(level);
+
 	/*
 	 * Calculate the number of pages, which fit into this large
 	 * page starting at address:
@@ -504,7 +518,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	 * up accordingly.
 	 */
 	old_pte = *kpte;
-	old_prot = req_prot = pgprot_large_2_4k(pte_pgprot(old_pte));
+	req_prot = pgprot_large_2_4k(old_prot);

 	pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr);
 	pgprot_val(req_prot) |= pgprot_val(cpa->mask_set);
@@ -530,10 +544,10 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	req_prot = canon_pgprot(req_prot);

 	/*
-	 * old_pte points to the large page base address. So we need
+	 * old_pfn points to the large page base pfn. So we need
 	 * to add the offset of the virtual address:
 	 */
-	pfn = pte_pfn(old_pte) + ((address & (psize - 1)) >> PAGE_SHIFT);
+	pfn = old_pfn + ((address & (psize - 1)) >> PAGE_SHIFT);
 	cpa->pfn = pfn;

 	new_prot = static_protections(req_prot, address, pfn);
@@ -544,7 +558,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	 * the pages in the range we try to preserve:
 	 */
 	addr = address & pmask;
-	pfn = pte_pfn(old_pte);
+	pfn = old_pfn;
 	for (i = 0; i < (psize >> PAGE_SHIFT); i++, addr += PAGE_SIZE, pfn++) {
 		pgprot_t chk_prot = static_protections(req_prot, addr, pfn);

@@ -574,7 +588,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 		 * The address is aligned and the number of pages
 		 * covers the full page.
 		 */
-		new_pte = pfn_pte(pte_pfn(old_pte), new_prot);
+		new_pte = pfn_pte(old_pfn, new_prot);
 		__set_pmd_pte(kpte, address, new_pte);
 		cpa->flags |= CPA_FLUSHTLB;
 		do_split = 0;
@@ -591,7 +605,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
 		   struct page *base)
 {
 	pte_t *pbase = (pte_t *)page_address(base);
-	unsigned long pfn, pfninc = 1;
+	unsigned long ref_pfn, pfn, pfninc = 1;
 	unsigned int i, level;
 	pte_t *tmp;
 	pgprot_t ref_prot;
@@ -608,26 +622,33 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
 	}

 	paravirt_alloc_pte(&init_mm, page_to_pfn(base));
-	ref_prot = pte_pgprot(pte_clrhuge(*kpte));

-	/* promote PAT bit to correct position */
-	if (level == PG_LEVEL_2M)
+	switch (level) {
+	case PG_LEVEL_2M:
+		ref_prot = pmd_pgprot(*(pmd_t *)kpte);
+		/* clear PSE and promote PAT bit to correct position */
 		ref_prot = pgprot_large_2_4k(ref_prot);
+		ref_pfn = pmd_pfn(*(pmd_t *)kpte);
+		break;

-#ifdef CONFIG_X86_64
-	if (level == PG_LEVEL_1G) {
+	case PG_LEVEL_1G:
+		ref_prot = pud_pgprot(*(pud_t *)kpte);
+		ref_pfn = pud_pfn(*(pud_t *)kpte);
 		pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT;
+
 		/*
-		 * Set the PSE flags only if the PRESENT flag is set
+		 * Clear the PSE flags if the PRESENT flag is not set
 		 * otherwise pmd_present/pmd_huge will return true
 		 * even on a non present pmd.
 		 */
-		if (pgprot_val(ref_prot) & _PAGE_PRESENT)
-			pgprot_val(ref_prot) |= _PAGE_PSE;
-		else
+		if (!(pgprot_val(ref_prot) & _PAGE_PRESENT))
 			pgprot_val(ref_prot) &= ~_PAGE_PSE;
+		break;
+
+	default:
+		spin_unlock(&pgd_lock);
+		return 1;
 	}
-#endif

 	/*
 	 * Set the GLOBAL flags only if the PRESENT flag is set
@@ -643,7 +664,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
 	/*
 	 * Get the target pfn from the original entry:
 	 */
-	pfn = pte_pfn(*kpte);
+	pfn = ref_pfn;
 	for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc)
 		set_pte(&pbase[i], pfn_pte(pfn, canon_pgprot(ref_prot)));