kasan, page_alloc: allow skipping unpoisoning for HW_TAGS

Add a new GFP flag __GFP_SKIP_KASAN_UNPOISON that allows skipping KASAN
poisoning for page_alloc allocations.  The flag is only effective with
HW_TAGS KASAN.

This flag will be used by vmalloc code for page_alloc allocations backing
vmalloc() mappings in a following patch.  The reason to skip KASAN
poisoning for these pages in page_alloc is because vmalloc code will be
poisoning them instead.

Also reword the comment for __GFP_SKIP_KASAN_POISON.

Link: https://lkml.kernel.org/r/35c97d77a704f6ff971dd3bfe4be95855744108e.1643047180.git.andreyknvl@google.com
Signed-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>

3 files changed, 38 insertions, 19 deletions

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 75abf8d5bc9bc9..688a39fde43eb0 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -55,12 +55,14 @@ struct vm_area_struct;
 #define ___GFP_ACCOUNT		0x400000u
 #define ___GFP_ZEROTAGS		0x800000u
 #ifdef CONFIG_KASAN_HW_TAGS
-#define ___GFP_SKIP_KASAN_POISON	0x1000000u
+#define ___GFP_SKIP_KASAN_UNPOISON	0x1000000u
+#define ___GFP_SKIP_KASAN_POISON	0x2000000u
 #else
+#define ___GFP_SKIP_KASAN_UNPOISON	0
 #define ___GFP_SKIP_KASAN_POISON	0
 #endif
 #ifdef CONFIG_LOCKDEP
-#define ___GFP_NOLOCKDEP	0x2000000u
+#define ___GFP_NOLOCKDEP	0x4000000u
 #else
 #define ___GFP_NOLOCKDEP	0
 #endif
@@ -241,22 +243,25 @@ struct vm_area_struct;
  * intended for optimization: setting memory tags at the same time as zeroing
  * memory has minimal additional performace impact.
  *
- * %__GFP_SKIP_KASAN_POISON returns a page which does not need to be poisoned
- * on deallocation. Typically used for userspace pages. Currently only has an
- * effect in HW tags mode.
+ * %__GFP_SKIP_KASAN_UNPOISON makes KASAN skip unpoisoning on page allocation.
+ * Only effective in HW_TAGS mode.
+ *
+ * %__GFP_SKIP_KASAN_POISON makes KASAN skip poisoning on page deallocation.
+ * Typically, used for userspace pages. Only effective in HW_TAGS mode.
  */
 #define __GFP_NOWARN	((__force gfp_t)___GFP_NOWARN)
 #define __GFP_COMP	((__force gfp_t)___GFP_COMP)
 #define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)
 #define __GFP_ZEROTAGS	((__force gfp_t)___GFP_ZEROTAGS)
-#define __GFP_SKIP_KASAN_POISON	((__force gfp_t)___GFP_SKIP_KASAN_POISON)
+#define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON)
+#define __GFP_SKIP_KASAN_POISON   ((__force gfp_t)___GFP_SKIP_KASAN_POISON)
 
 /* Disable lockdep for GFP context tracking */
 #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
 
 /* Room for N __GFP_FOO bits */
-#define __GFP_BITS_SHIFT (24 +					\
-			  IS_ENABLED(CONFIG_KASAN_HW_TAGS) +	\
+#define __GFP_BITS_SHIFT (24 +						\
+			  2 * IS_ENABLED(CONFIG_KASAN_HW_TAGS) +	\
 			  IS_ENABLED(CONFIG_LOCKDEP))
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index cb4520374e2c87..134c45e62d9181 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -52,8 +52,9 @@
 	{(unsigned long)__GFP_ZEROTAGS,		"__GFP_ZEROTAGS"}	\
 
 #ifdef CONFIG_KASAN_HW_TAGS
-#define __def_gfpflag_names_kasan					      \
-	, {(unsigned long)__GFP_SKIP_KASAN_POISON, "__GFP_SKIP_KASAN_POISON"}
+#define __def_gfpflag_names_kasan ,					       \
+	{(unsigned long)__GFP_SKIP_KASAN_POISON,   "__GFP_SKIP_KASAN_POISON"}, \
+	{(unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"}
 #else
 #define __def_gfpflag_names_kasan
 #endif
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 350bb27dc4bb61..59a9408e1e7d47 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2343,6 +2343,26 @@ static inline bool check_new_pcp(struct page *page, unsigned int order)
 }
 #endif /* CONFIG_DEBUG_VM */
 
+static inline bool should_skip_kasan_unpoison(gfp_t flags, bool init_tags)
+{
+	/* Don't skip if a software KASAN mode is enabled. */
+	if (IS_ENABLED(CONFIG_KASAN_GENERIC) ||
+	    IS_ENABLED(CONFIG_KASAN_SW_TAGS))
+		return false;
+
+	/* Skip, if hardware tag-based KASAN is not enabled. */
+	if (!kasan_hw_tags_enabled())
+		return true;
+
+	/*
+	 * With hardware tag-based KASAN enabled, skip if either:
+	 *
+	 * 1. Memory tags have already been cleared via tag_clear_highpage().
+	 * 2. Skipping has been requested via __GFP_SKIP_KASAN_UNPOISON.
+	 */
+	return init_tags || (flags & __GFP_SKIP_KASAN_UNPOISON);
+}
+
 inline void post_alloc_hook(struct page *page, unsigned int order,
 				gfp_t gfp_flags)
 {
@@ -2382,15 +2402,8 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 		/* Note that memory is already initialized by the loop above. */
 		init = false;
 	}
-	/*
-	 * If either a software KASAN mode is enabled, or,
-	 * in the case of hardware tag-based KASAN,
-	 * if memory tags have not been cleared via tag_clear_highpage().
-	 */
-	if (IS_ENABLED(CONFIG_KASAN_GENERIC) ||
-	    IS_ENABLED(CONFIG_KASAN_SW_TAGS) ||
-	    kasan_hw_tags_enabled() && !init_tags) {
-		/* Mark shadow memory or set memory tags. */
+	if (!should_skip_kasan_unpoison(gfp_flags, init_tags)) {
+		/* Unpoison shadow memory or set memory tags. */
 		kasan_unpoison_pages(page, order, init);
 
 		/* Note that memory is already initialized by KASAN. */