Merge tag 'ronx-next' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux into devel-stable

generic fixmaps
ARM support for CONFIG_DEBUG_RODATA

4 files changed, 211 insertions, 13 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index ae69809a9e47..c9cd9c5bf1e1 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -1008,3 +1008,24 @@ config ARCH_SUPPORTS_BIG_ENDIAN
 	help
 	  This option specifies the architecture can support big endian
 	  operation.
+
+config ARM_KERNMEM_PERMS
+	bool "Restrict kernel memory permissions"
+	help
+	  If this is set, kernel memory other than kernel text (and rodata)
+	  will be made non-executable. The tradeoff is that each region is
+	  padded to section-size (1MiB) boundaries (because their permissions
+	  are different and splitting the 1M pages into 4K ones causes TLB
+	  performance problems), wasting memory.
+
+config DEBUG_RODATA
+	bool "Make kernel text and rodata read-only"
+	depends on ARM_KERNMEM_PERMS
+	default y
+	help
+	  If this is set, kernel text and rodata will be made read-only. This
+	  is to help catch accidental or malicious attempts to change the
+	  kernel's executable code. Additionally splits rodata from kernel
+	  text so it can be made explicitly non-executable. This creates
+	  another section-size padded region, so it can waste more memory
+	  space while gaining the read-only protections.
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index 45aeaaca9052..81061987ac45 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -18,19 +18,20 @@
 #include <asm/tlbflush.h>
 #include "mm.h"
 
-pte_t *fixmap_page_table;
-
 static inline void set_fixmap_pte(int idx, pte_t pte)
 {
 	unsigned long vaddr = __fix_to_virt(idx);
-	set_pte_ext(fixmap_page_table + idx, pte, 0);
+	pte_t *ptep = pte_offset_kernel(pmd_off_k(vaddr), vaddr);
+
+	set_pte_ext(ptep, pte, 0);
 	local_flush_tlb_kernel_page(vaddr);
 }
 
 static inline pte_t get_fixmap_pte(unsigned long vaddr)
 {
-	unsigned long idx = __virt_to_fix(vaddr);
-	return *(fixmap_page_table + idx);
+	pte_t *ptep = pte_offset_kernel(pmd_off_k(vaddr), vaddr);
+
+	return *ptep;
 }
 
 void *kmap(struct page *page)
@@ -84,7 +85,7 @@ void *kmap_atomic(struct page *page)
 	 * With debugging enabled, kunmap_atomic forces that entry to 0.
 	 * Make sure it was indeed properly unmapped.
 	 */
-	BUG_ON(!pte_none(*(fixmap_page_table + idx)));
+	BUG_ON(!pte_none(get_fixmap_pte(vaddr)));
 #endif
 	/*
 	 * When debugging is off, kunmap_atomic leaves the previous mapping
@@ -134,7 +135,7 @@ void *kmap_atomic_pfn(unsigned long pfn)
 	idx = type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
-	BUG_ON(!pte_none(*(fixmap_page_table + idx)));
+	BUG_ON(!pte_none(get_fixmap_pte(vaddr)));
 #endif
 	set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot));
 
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 92bba32d9230..67b15426b9c6 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -29,6 +29,7 @@
 #include <asm/prom.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
+#include <asm/system_info.h>
 #include <asm/tlb.h>
 #include <asm/fixmap.h>
 
@@ -570,7 +571,7 @@ void __init mem_init(void)
 			MLK(DTCM_OFFSET, (unsigned long) dtcm_end),
 			MLK(ITCM_OFFSET, (unsigned long) itcm_end),
 #endif
-			MLK(FIXADDR_START, FIXADDR_TOP),
+			MLK(FIXADDR_START, FIXADDR_END),
 			MLM(VMALLOC_START, VMALLOC_END),
 			MLM(PAGE_OFFSET, (unsigned long)high_memory),
 #ifdef CONFIG_HIGHMEM
@@ -615,7 +616,145 @@ void __init mem_init(void)
 	}
 }
 
-void free_initmem(void)
+#ifdef CONFIG_ARM_KERNMEM_PERMS
+struct section_perm {
+	unsigned long start;
+	unsigned long end;
+	pmdval_t mask;
+	pmdval_t prot;
+	pmdval_t clear;
+};
+
+static struct section_perm nx_perms[] = {
+	/* Make pages tables, etc before _stext RW (set NX). */
+	{
+		.start	= PAGE_OFFSET,
+		.end	= (unsigned long)_stext,
+		.mask	= ~PMD_SECT_XN,
+		.prot	= PMD_SECT_XN,
+	},
+	/* Make init RW (set NX). */
+	{
+		.start	= (unsigned long)__init_begin,
+		.end	= (unsigned long)_sdata,
+		.mask	= ~PMD_SECT_XN,
+		.prot	= PMD_SECT_XN,
+	},
+#ifdef CONFIG_DEBUG_RODATA
+	/* Make rodata NX (set RO in ro_perms below). */
+	{
+		.start  = (unsigned long)__start_rodata,
+		.end    = (unsigned long)__init_begin,
+		.mask   = ~PMD_SECT_XN,
+		.prot   = PMD_SECT_XN,
+	},
+#endif
+};
+
+#ifdef CONFIG_DEBUG_RODATA
+static struct section_perm ro_perms[] = {
+	/* Make kernel code and rodata RX (set RO). */
+	{
+		.start  = (unsigned long)_stext,
+		.end    = (unsigned long)__init_begin,
+#ifdef CONFIG_ARM_LPAE
+		.mask   = ~PMD_SECT_RDONLY,
+		.prot   = PMD_SECT_RDONLY,
+#else
+		.mask   = ~(PMD_SECT_APX | PMD_SECT_AP_WRITE),
+		.prot   = PMD_SECT_APX | PMD_SECT_AP_WRITE,
+		.clear  = PMD_SECT_AP_WRITE,
+#endif
+	},
+};
+#endif
+
+/*
+ * Updates section permissions only for the current mm (sections are
+ * copied into each mm). During startup, this is the init_mm. Is only
+ * safe to be called with preemption disabled, as under stop_machine().
+ */
+static inline void section_update(unsigned long addr, pmdval_t mask,
+				  pmdval_t prot)
+{
+	struct mm_struct *mm;
+	pmd_t *pmd;
+
+	mm = current->active_mm;
+	pmd = pmd_offset(pud_offset(pgd_offset(mm, addr), addr), addr);
+
+#ifdef CONFIG_ARM_LPAE
+	pmd[0] = __pmd((pmd_val(pmd[0]) & mask) | prot);
+#else
+	if (addr & SECTION_SIZE)
+		pmd[1] = __pmd((pmd_val(pmd[1]) & mask) | prot);
+	else
+		pmd[0] = __pmd((pmd_val(pmd[0]) & mask) | prot);
+#endif
+	flush_pmd_entry(pmd);
+	local_flush_tlb_kernel_range(addr, addr + SECTION_SIZE);
+}
+
+/* Make sure extended page tables are in use. */
+static inline bool arch_has_strict_perms(void)
+{
+	if (cpu_architecture() < CPU_ARCH_ARMv6)
+		return false;
+
+	return !!(get_cr() & CR_XP);
+}
+
+#define set_section_perms(perms, field)	{				\
+	size_t i;							\
+	unsigned long addr;						\
+									\
+	if (!arch_has_strict_perms())					\
+		return;							\
+									\
+	for (i = 0; i < ARRAY_SIZE(perms); i++) {			\
+		if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) ||	\
+		    !IS_ALIGNED(perms[i].end, SECTION_SIZE)) {		\
+			pr_err("BUG: section %lx-%lx not aligned to %lx\n", \
+				perms[i].start, perms[i].end,		\
+				SECTION_SIZE);				\
+			continue;					\
+		}							\
+									\
+		for (addr = perms[i].start;				\
+		     addr < perms[i].end;				\
+		     addr += SECTION_SIZE)				\
+			section_update(addr, perms[i].mask,		\
+				       perms[i].field);			\
+	}								\
+}
+
+static inline void fix_kernmem_perms(void)
+{
+	set_section_perms(nx_perms, prot);
+}
+
+#ifdef CONFIG_DEBUG_RODATA
+void mark_rodata_ro(void)
+{
+	set_section_perms(ro_perms, prot);
+}
+
+void set_kernel_text_rw(void)
+{
+	set_section_perms(ro_perms, clear);
+}
+
+void set_kernel_text_ro(void)
+{
+	set_section_perms(ro_perms, prot);
+}
+#endif /* CONFIG_DEBUG_RODATA */
+
+#else
+static inline void fix_kernmem_perms(void) { }
+#endif /* CONFIG_ARM_KERNMEM_PERMS */
+
+void free_tcmmem(void)
 {
 #ifdef CONFIG_HAVE_TCM
 	extern char __tcm_start, __tcm_end;
@@ -623,6 +762,12 @@ void free_initmem(void)
 	poison_init_mem(&__tcm_start, &__tcm_end - &__tcm_start);
 	free_reserved_area(&__tcm_start, &__tcm_end, -1, "TCM link");
 #endif
+}
+
+void free_initmem(void)
+{
+	fix_kernmem_perms();
+	free_tcmmem();
 
 	poison_init_mem(__init_begin, __init_end - __init_begin);
 	if (!machine_is_integrator() && !machine_is_cintegrator())
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 9f98cec7fe1e..a7b12cb21e81 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -22,6 +22,7 @@
 #include <asm/cputype.h>
 #include <asm/sections.h>
 #include <asm/cachetype.h>
+#include <asm/fixmap.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp_plat.h>
@@ -393,6 +394,29 @@ SET_MEMORY_FN(x, pte_set_x)
 SET_MEMORY_FN(nx, pte_set_nx)
 
 /*
+ * To avoid TLB flush broadcasts, this uses local_flush_tlb_kernel_range().
+ * As a result, this can only be called with preemption disabled, as under
+ * stop_machine().
+ */
+void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
+{
+	unsigned long vaddr = __fix_to_virt(idx);
+	pte_t *pte = pte_offset_kernel(pmd_off_k(vaddr), vaddr);
+
+	/* Make sure fixmap region does not exceed available allocation. */
+	BUILD_BUG_ON(FIXADDR_START + (__end_of_fixed_addresses * PAGE_SIZE) >
+		     FIXADDR_END);
+	BUG_ON(idx >= __end_of_fixed_addresses);
+
+	if (pgprot_val(prot))
+		set_pte_at(NULL, vaddr, pte,
+			pfn_pte(phys >> PAGE_SHIFT, prot));
+	else
+		pte_clear(NULL, vaddr, pte);
+	local_flush_tlb_kernel_range(vaddr, vaddr + PAGE_SIZE);
+}
+
+/*
  * Adjust the PMD section entries according to the CPU in use.
  */
 static void __init build_mem_type_table(void)
@@ -1326,10 +1350,10 @@ static void __init kmap_init(void)
 #ifdef CONFIG_HIGHMEM
 	pkmap_page_table = early_pte_alloc(pmd_off_k(PKMAP_BASE),
 		PKMAP_BASE, _PAGE_KERNEL_TABLE);
-
-	fixmap_page_table = early_pte_alloc(pmd_off_k(FIXADDR_START),
-		FIXADDR_START, _PAGE_KERNEL_TABLE);
 #endif
+
+	early_pte_alloc(pmd_off_k(FIXADDR_START), FIXADDR_START,
+			_PAGE_KERNEL_TABLE);
 }
 
 static void __init map_lowmem(void)
@@ -1349,13 +1373,20 @@ static void __init map_lowmem(void)
 		if (start >= end)
 			break;
 
-		if (end < kernel_x_start || start >= kernel_x_end) {
+		if (end < kernel_x_start) {
 			map.pfn = __phys_to_pfn(start);
 			map.virtual = __phys_to_virt(start);
 			map.length = end - start;
 			map.type = MT_MEMORY_RWX;
 
 			create_mapping(&map);
+		} else if (start >= kernel_x_end) {
+			map.pfn = __phys_to_pfn(start);
+			map.virtual = __phys_to_virt(start);
+			map.length = end - start;
+			map.type = MT_MEMORY_RW;
+
+			create_mapping(&map);
 		} else {
 			/* This better cover the entire kernel */
 			if (start < kernel_x_start) {