1 files changed, 280 insertions, 10 deletions

diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 2277b82902d8..6aa51723b92b 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -36,6 +36,9 @@
 #include <linux/bug.h>
 #include <linux/uaccess.h>
 
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+
 #include "kasan.h"
 #include "../slab.h"
 
@@ -107,6 +110,7 @@ void *memset(void *addr, int c, size_t len)
 	return __memset(addr, c, len);
 }
 
+#ifdef __HAVE_ARCH_MEMMOVE
 #undef memmove
 void *memmove(void *dest, const void *src, size_t len)
 {
@@ -115,6 +119,7 @@ void *memmove(void *dest, const void *src, size_t len)
 
 	return __memmove(dest, src, len);
 }
+#endif
 
 #undef memcpy
 void *memcpy(void *dest, const void *src, size_t len)
@@ -304,7 +309,6 @@ size_t kasan_metadata_size(struct kmem_cache *cache)
 struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache,
 					const void *object)
 {
-	BUILD_BUG_ON(sizeof(struct kasan_alloc_meta) > 32);
 	return (void *)object + cache->kasan_info.alloc_meta_offset;
 }
 
@@ -315,14 +319,31 @@ struct kasan_free_meta *get_free_info(struct kmem_cache *cache,
 	return (void *)object + cache->kasan_info.free_meta_offset;
 }
 
+
+static void kasan_set_free_info(struct kmem_cache *cache,
+		void *object, u8 tag)
+{
+	struct kasan_alloc_meta *alloc_meta;
+	u8 idx = 0;
+
+	alloc_meta = get_alloc_info(cache, object);
+
+#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY
+	idx = alloc_meta->free_track_idx;
+	alloc_meta->free_pointer_tag[idx] = tag;
+	alloc_meta->free_track_idx = (idx + 1) % KASAN_NR_FREE_STACKS;
+#endif
+
+	set_track(&alloc_meta->free_track[idx], GFP_NOWAIT);
+}
+
 void kasan_poison_slab(struct page *page)
 {
 	unsigned long i;
 
-	for (i = 0; i < (1 << compound_order(page)); i++)
+	for (i = 0; i < compound_nr(page); i++)
 		page_kasan_tag_reset(page + i);
-	kasan_poison_shadow(page_address(page),
-			PAGE_SIZE << compound_order(page),
+	kasan_poison_shadow(page_address(page), page_size(page),
 			KASAN_KMALLOC_REDZONE);
 }
 
@@ -407,8 +428,14 @@ static inline bool shadow_invalid(u8 tag, s8 shadow_byte)
 	if (IS_ENABLED(CONFIG_KASAN_GENERIC))
 		return shadow_byte < 0 ||
 			shadow_byte >= KASAN_SHADOW_SCALE_SIZE;
-	else
-		return tag != (u8)shadow_byte;
+
+	/* else CONFIG_KASAN_SW_TAGS: */
+	if ((u8)shadow_byte == KASAN_TAG_INVALID)
+		return true;
+	if ((tag != KASAN_TAG_KERNEL) && (tag != (u8)shadow_byte))
+		return true;
+
+	return false;
 }
 
 static bool __kasan_slab_free(struct kmem_cache *cache, void *object,
@@ -446,7 +473,8 @@ static bool __kasan_slab_free(struct kmem_cache *cache, void *object,
 			unlikely(!(cache->flags & SLAB_KASAN)))
 		return false;
 
-	set_track(&get_alloc_info(cache, object)->free_track, GFP_NOWAIT);
+	kasan_set_free_info(cache, object, tag);
+
 	quarantine_put(get_free_info(cache, object), cache);
 
 	return IS_ENABLED(CONFIG_KASAN_GENERIC);
@@ -518,7 +546,7 @@ void * __must_check kasan_kmalloc_large(const void *ptr, size_t size,
 	page = virt_to_page(ptr);
 	redzone_start = round_up((unsigned long)(ptr + size),
 				KASAN_SHADOW_SCALE_SIZE);
-	redzone_end = (unsigned long)ptr + (PAGE_SIZE << compound_order(page));
+	redzone_end = (unsigned long)ptr + page_size(page);
 
 	kasan_unpoison_shadow(ptr, size);
 	kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start,
@@ -554,8 +582,7 @@ void kasan_poison_kfree(void *ptr, unsigned long ip)
 			kasan_report_invalid_free(ptr, ip);
 			return;
 		}
-		kasan_poison_shadow(ptr, PAGE_SIZE << compound_order(page),
-				KASAN_FREE_PAGE);
+		kasan_poison_shadow(ptr, page_size(page), KASAN_FREE_PAGE);
 	} else {
 		__kasan_slab_free(page->slab_cache, ptr, ip, false);
 	}
@@ -568,6 +595,7 @@ void kasan_kfree_large(void *ptr, unsigned long ip)
 	/* The object will be poisoned by page_alloc. */
 }
 
+#ifndef CONFIG_KASAN_VMALLOC
 int kasan_module_alloc(void *addr, size_t size)
 {
 	void *ret;
@@ -603,6 +631,7 @@ void kasan_free_shadow(const struct vm_struct *vm)
 	if (vm->flags & VM_KASAN)
 		vfree(kasan_mem_to_shadow(vm->addr));
 }
+#endif
 
 extern void __kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip);
 
@@ -722,3 +751,244 @@ static int __init kasan_memhotplug_init(void)
 
 core_initcall(kasan_memhotplug_init);
 #endif
+
+#ifdef CONFIG_KASAN_VMALLOC
+static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr,
+				      void *unused)
+{
+	unsigned long page;
+	pte_t pte;
+
+	if (likely(!pte_none(*ptep)))
+		return 0;
+
+	page = __get_free_page(GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+
+	memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE);
+	pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL);
+
+	spin_lock(&init_mm.page_table_lock);
+	if (likely(pte_none(*ptep))) {
+		set_pte_at(&init_mm, addr, ptep, pte);
+		page = 0;
+	}
+	spin_unlock(&init_mm.page_table_lock);
+	if (page)
+		free_page(page);
+	return 0;
+}
+
+int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
+{
+	unsigned long shadow_start, shadow_end;
+	int ret;
+
+	if (!is_vmalloc_or_module_addr((void *)addr))
+		return 0;
+
+	shadow_start = (unsigned long)kasan_mem_to_shadow((void *)addr);
+	shadow_start = ALIGN_DOWN(shadow_start, PAGE_SIZE);
+	shadow_end = (unsigned long)kasan_mem_to_shadow((void *)addr + size);
+	shadow_end = ALIGN(shadow_end, PAGE_SIZE);
+
+	ret = apply_to_page_range(&init_mm, shadow_start,
+				  shadow_end - shadow_start,
+				  kasan_populate_vmalloc_pte, NULL);
+	if (ret)
+		return ret;
+
+	flush_cache_vmap(shadow_start, shadow_end);
+
+	/*
+	 * We need to be careful about inter-cpu effects here. Consider:
+	 *
+	 *   CPU#0				  CPU#1
+	 * WRITE_ONCE(p, vmalloc(100));		while (x = READ_ONCE(p)) ;
+	 *					p[99] = 1;
+	 *
+	 * With compiler instrumentation, that ends up looking like this:
+	 *
+	 *   CPU#0				  CPU#1
+	 * // vmalloc() allocates memory
+	 * // let a = area->addr
+	 * // we reach kasan_populate_vmalloc
+	 * // and call kasan_unpoison_shadow:
+	 * STORE shadow(a), unpoison_val
+	 * ...
+	 * STORE shadow(a+99), unpoison_val	x = LOAD p
+	 * // rest of vmalloc process		<data dependency>
+	 * STORE p, a				LOAD shadow(x+99)
+	 *
+	 * If there is no barrier between the end of unpoisioning the shadow
+	 * and the store of the result to p, the stores could be committed
+	 * in a different order by CPU#0, and CPU#1 could erroneously observe
+	 * poison in the shadow.
+	 *
+	 * We need some sort of barrier between the stores.
+	 *
+	 * In the vmalloc() case, this is provided by a smp_wmb() in
+	 * clear_vm_uninitialized_flag(). In the per-cpu allocator and in
+	 * get_vm_area() and friends, the caller gets shadow allocated but
+	 * doesn't have any pages mapped into the virtual address space that
+	 * has been reserved. Mapping those pages in will involve taking and
+	 * releasing a page-table lock, which will provide the barrier.
+	 */
+
+	return 0;
+}
+
+/*
+ * Poison the shadow for a vmalloc region. Called as part of the
+ * freeing process at the time the region is freed.
+ */
+void kasan_poison_vmalloc(const void *start, unsigned long size)
+{
+	if (!is_vmalloc_or_module_addr(start))
+		return;
+
+	size = round_up(size, KASAN_SHADOW_SCALE_SIZE);
+	kasan_poison_shadow(start, size, KASAN_VMALLOC_INVALID);
+}
+
+void kasan_unpoison_vmalloc(const void *start, unsigned long size)
+{
+	if (!is_vmalloc_or_module_addr(start))
+		return;
+
+	kasan_unpoison_shadow(start, size);
+}
+
+static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr,
+					void *unused)
+{
+	unsigned long page;
+
+	page = (unsigned long)__va(pte_pfn(*ptep) << PAGE_SHIFT);
+
+	spin_lock(&init_mm.page_table_lock);
+
+	if (likely(!pte_none(*ptep))) {
+		pte_clear(&init_mm, addr, ptep);
+		free_page(page);
+	}
+	spin_unlock(&init_mm.page_table_lock);
+
+	return 0;
+}
+
+/*
+ * Release the backing for the vmalloc region [start, end), which
+ * lies within the free region [free_region_start, free_region_end).
+ *
+ * This can be run lazily, long after the region was freed. It runs
+ * under vmap_area_lock, so it's not safe to interact with the vmalloc/vmap
+ * infrastructure.
+ *
+ * How does this work?
+ * -------------------
+ *
+ * We have a region that is page aligned, labelled as A.
+ * That might not map onto the shadow in a way that is page-aligned:
+ *
+ *                    start                     end
+ *                    v                         v
+ * |????????|????????|AAAAAAAA|AA....AA|AAAAAAAA|????????| < vmalloc
+ *  -------- -------- --------          -------- --------
+ *      |        |       |                 |        |
+ *      |        |       |         /-------/        |
+ *      \-------\|/------/         |/---------------/
+ *              |||                ||
+ *             |??AAAAAA|AAAAAAAA|AA??????|                < shadow
+ *                 (1)      (2)      (3)
+ *
+ * First we align the start upwards and the end downwards, so that the
+ * shadow of the region aligns with shadow page boundaries. In the
+ * example, this gives us the shadow page (2). This is the shadow entirely
+ * covered by this allocation.
+ *
+ * Then we have the tricky bits. We want to know if we can free the
+ * partially covered shadow pages - (1) and (3) in the example. For this,
+ * we are given the start and end of the free region that contains this
+ * allocation. Extending our previous example, we could have:
+ *
+ *  free_region_start                                    free_region_end
+ *  |                 start                     end      |
+ *  v                 v                         v        v
+ * |FFFFFFFF|FFFFFFFF|AAAAAAAA|AA....AA|AAAAAAAA|FFFFFFFF| < vmalloc
+ *  -------- -------- --------          -------- --------
+ *      |        |       |                 |        |
+ *      |        |       |         /-------/        |
+ *      \-------\|/------/         |/---------------/
+ *              |||                ||
+ *             |FFAAAAAA|AAAAAAAA|AAF?????|                < shadow
+ *                 (1)      (2)      (3)
+ *
+ * Once again, we align the start of the free region up, and the end of
+ * the free region down so that the shadow is page aligned. So we can free
+ * page (1) - we know no allocation currently uses anything in that page,
+ * because all of it is in the vmalloc free region. But we cannot free
+ * page (3), because we can't be sure that the rest of it is unused.
+ *
+ * We only consider pages that contain part of the original region for
+ * freeing: we don't try to free other pages from the free region or we'd
+ * end up trying to free huge chunks of virtual address space.
+ *
+ * Concurrency
+ * -----------
+ *
+ * How do we know that we're not freeing a page that is simultaneously
+ * being used for a fresh allocation in kasan_populate_vmalloc(_pte)?
+ *
+ * We _can_ have kasan_release_vmalloc and kasan_populate_vmalloc running
+ * at the same time. While we run under free_vmap_area_lock, the population
+ * code does not.
+ *
+ * free_vmap_area_lock instead operates to ensure that the larger range
+ * [free_region_start, free_region_end) is safe: because __alloc_vmap_area and
+ * the per-cpu region-finding algorithm both run under free_vmap_area_lock,
+ * no space identified as free will become used while we are running. This
+ * means that so long as we are careful with alignment and only free shadow
+ * pages entirely covered by the free region, we will not run in to any
+ * trouble - any simultaneous allocations will be for disjoint regions.
+ */
+void kasan_release_vmalloc(unsigned long start, unsigned long end,
+			   unsigned long free_region_start,
+			   unsigned long free_region_end)
+{
+	void *shadow_start, *shadow_end;
+	unsigned long region_start, region_end;
+	unsigned long size;
+
+	region_start = ALIGN(start, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE);
+	region_end = ALIGN_DOWN(end, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE);
+
+	free_region_start = ALIGN(free_region_start,
+				  PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE);
+
+	if (start != region_start &&
+	    free_region_start < region_start)
+		region_start -= PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE;
+
+	free_region_end = ALIGN_DOWN(free_region_end,
+				     PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE);
+
+	if (end != region_end &&
+	    free_region_end > region_end)
+		region_end += PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE;
+
+	shadow_start = kasan_mem_to_shadow((void *)region_start);
+	shadow_end = kasan_mem_to_shadow((void *)region_end);
+
+	if (shadow_end > shadow_start) {
+		size = shadow_end - shadow_start;
+		apply_to_existing_page_range(&init_mm,
+					     (unsigned long)shadow_start,
+					     size, kasan_depopulate_vmalloc_pte,
+					     NULL);
+		flush_tlb_kernel_range((unsigned long)shadow_start,
+				       (unsigned long)shadow_end);
+	}
+}
+#endif