kasan, vmalloc: only tag normal vmalloc allocations

The kernel can use to allocate executable memory.  The only supported
way to do that is via __vmalloc_node_range() with the executable bit set
in the prot argument.  (vmap() resets the bit via pgprot_nx()).

Once tag-based KASAN modes start tagging vmalloc allocations, executing
code from such allocations will lead to the PC register getting a tag,
which is not tolerated by the kernel.

Only tag the allocations for normal kernel pages.

[andreyknvl@google.com: pass KASAN_VMALLOC_PROT_NORMAL to kasan_unpoison_vmalloc()]
  Link: https://lkml.kernel.org/r/9230ca3d3e40ffca041c133a524191fd71969a8d.1646233925.git.andreyknvl@google.com
[andreyknvl@google.com: support tagged vmalloc mappings]
  Link: https://lkml.kernel.org/r/2f6605e3a358cf64d73a05710cb3da356886ad29.1646233925.git.andreyknvl@google.com
[andreyknvl@google.com: don't unintentionally disabled poisoning]
  Link: https://lkml.kernel.org/r/de4587d6a719232e83c760113e46ed2d4d8da61e.1646757322.git.andreyknvl@google.com

Link: https://lkml.kernel.org/r/fbfd9939a4dc375923c9a5c6b9e7ab05c26b8c6b.1643047180.git.andreyknvl@google.comSigned-off-by: Andrey Konovalov <andreyknvl@google.com>
Acked-by: Marco Elver <elver@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Collingbourne <pcc@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/kasan.h

@@ -31,6 +31,7 @@ typedef unsigned int __bitwise kasan_vmalloc_flags_t;
 #define KASAN_VMALLOC_NONE		0x00u
 #define KASAN_VMALLOC_INIT		0x01u
 #define KASAN_VMALLOC_VM_ALLOC		0x02u
+#define KASAN_VMALLOC_PROT_NORMAL	0x04u
 
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 

kernel/scs.c

@@ -32,15 +32,19 @@ static void *__scs_alloc(int node)
 	for (i = 0; i < NR_CACHED_SCS; i++) {
 		s = this_cpu_xchg(scs_cache[i], NULL);
 		if (s) {
-			kasan_unpoison_vmalloc(s, SCS_SIZE, KASAN_VMALLOC_NONE);
+			s = kasan_unpoison_vmalloc(s, SCS_SIZE,
+						   KASAN_VMALLOC_PROT_NORMAL);
 			memset(s, 0, SCS_SIZE);
-			return s;
+			goto out;
 		}
 	}
 
-	return __vmalloc_node_range(SCS_SIZE, 1, VMALLOC_START, VMALLOC_END,
+	s = __vmalloc_node_range(SCS_SIZE, 1, VMALLOC_START, VMALLOC_END,
 				    GFP_SCS, PAGE_KERNEL, 0, node,
 				    __builtin_return_address(0));
+
+out:
+	return kasan_reset_tag(s);
 }
 
 void *scs_alloc(int node)
@@ -78,7 +82,7 @@ void scs_free(void *s)
 		if (this_cpu_cmpxchg(scs_cache[i], 0, s) == NULL)
 			return;
 
-	kasan_unpoison_vmalloc(s, SCS_SIZE, KASAN_VMALLOC_NONE);
+	kasan_unpoison_vmalloc(s, SCS_SIZE, KASAN_VMALLOC_PROT_NORMAL);
 	vfree_atomic(s);
 }
 

mm/kasan/hw_tags.c

@@ -247,6 +247,13 @@ void *__kasan_unpoison_vmalloc(const void *start, unsigned long size,
 	if (!(flags & KASAN_VMALLOC_VM_ALLOC))
 		return (void *)start;
 
+	/*
+	 * Don't tag executable memory.
+	 * The kernel doesn't tolerate having the PC register tagged.
+	 */
+	if (!(flags & KASAN_VMALLOC_PROT_NORMAL))
+		return (void *)start;
+
 	tag = kasan_random_tag();
 	start = set_tag(start, tag);
 

mm/kasan/shadow.c

@@ -488,6 +488,14 @@ void *__kasan_unpoison_vmalloc(const void *start, unsigned long size,
 	if (!is_vmalloc_or_module_addr(start))
 		return (void *)start;
 
+	/*
+	 * Don't tag executable memory with the tag-based mode.
+	 * The kernel doesn't tolerate having the PC register tagged.
+	 */
+	if (IS_ENABLED(CONFIG_KASAN_SW_TAGS) &&
+	    !(flags & KASAN_VMALLOC_PROT_NORMAL))
+		return (void *)start;
+
 	start = set_tag(start, kasan_random_tag());
 	kasan_unpoison(start, size, false);
 	return (void *)start;

mm/vmalloc.c

@@ -2242,7 +2242,7 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node)
 	 * With hardware tag-based KASAN, marking is skipped for
 	 * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc().
 	 */
-	mem = kasan_unpoison_vmalloc(mem, size, KASAN_VMALLOC_NONE);
+	mem = kasan_unpoison_vmalloc(mem, size, KASAN_VMALLOC_PROT_NORMAL);
 
 	return mem;
 }
@@ -2481,7 +2481,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
 	 */
 	if (!(flags & VM_ALLOC))
 		area->addr = kasan_unpoison_vmalloc(area->addr, requested_size,
-							KASAN_VMALLOC_NONE);
+						    KASAN_VMALLOC_PROT_NORMAL);
 
 	return area;
 }
@@ -3091,7 +3091,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 {
 	struct vm_struct *area;
 	void *ret;
-	kasan_vmalloc_flags_t kasan_flags;
+	kasan_vmalloc_flags_t kasan_flags = KASAN_VMALLOC_NONE;
 	unsigned long real_size = size;
 	unsigned long real_align = align;
 	unsigned int shift = PAGE_SHIFT;
@@ -3144,23 +3144,30 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 		goto fail;
 	}
 
-	/* Prepare arguments for __vmalloc_area_node(). */
-	if (kasan_hw_tags_enabled() &&
-	    pgprot_val(prot) == pgprot_val(PAGE_KERNEL)) {
+	/*
+	 * Prepare arguments for __vmalloc_area_node() and
+	 * kasan_unpoison_vmalloc().
+	 */
+	if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL)) {
+		if (kasan_hw_tags_enabled()) {
 			/*
 			 * Modify protection bits to allow tagging.
-		 * This must be done before mapping in __vmalloc_area_node().
+			 * This must be done before mapping.
 			 */
 			prot = arch_vmap_pgprot_tagged(prot);
 
 			/*
-		 * Skip page_alloc poisoning and zeroing for physical pages
-		 * backing VM_ALLOC mapping. Memory is instead poisoned and
-		 * zeroed by kasan_unpoison_vmalloc().
+			 * Skip page_alloc poisoning and zeroing for physical
+			 * pages backing VM_ALLOC mapping. Memory is instead
+			 * poisoned and zeroed by kasan_unpoison_vmalloc().
 			 */
 			gfp_mask |= __GFP_SKIP_KASAN_UNPOISON | __GFP_SKIP_ZERO;
 		}
 
+		/* Take note that the mapping is PAGE_KERNEL. */
+		kasan_flags |= KASAN_VMALLOC_PROT_NORMAL;
+	}
+
 	/* Allocate physical pages and map them into vmalloc space. */
 	ret = __vmalloc_area_node(area, gfp_mask, prot, shift, node);
 	if (!ret)
@@ -3172,10 +3179,13 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	 * (except for the should_skip_init() check) to make sure that memory
 	 * is initialized under the same conditions regardless of the enabled
 	 * KASAN mode.
+	 * Tag-based KASAN modes only assign tags to normal non-executable
+	 * allocations, see __kasan_unpoison_vmalloc().
 	 */
-	kasan_flags = KASAN_VMALLOC_VM_ALLOC;
+	kasan_flags |= KASAN_VMALLOC_VM_ALLOC;
 	if (!want_init_on_free() && want_init_on_alloc(gfp_mask))
 		kasan_flags |= KASAN_VMALLOC_INIT;
+	/* KASAN_VMALLOC_PROT_NORMAL already set if required. */
 	area->addr = kasan_unpoison_vmalloc(area->addr, real_size, kasan_flags);
 
 	/*
@@ -3881,8 +3891,7 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
 	 */
 	for (area = 0; area < nr_vms; area++)
 		vms[area]->addr = kasan_unpoison_vmalloc(vms[area]->addr,
-							 vms[area]->size,
-							 KASAN_VMALLOC_NONE);
+				vms[area]->size, KASAN_VMALLOC_PROT_NORMAL);
 
 	kfree(vas);
 	return vms;