mm: kfence: improve the performance of __kfence_alloc() and __kfence_free()

In __kfence_alloc() and __kfence_free(), we will set and check canary. 
Assuming that the size of the object is close to 0, nearly 4k memory
accesses are required because setting and checking canary is executed byte
by byte.

canary is now defined like this:
KFENCE_CANARY_PATTERN(addr) ((u8)0xaa ^ (u8)((unsigned long)(addr) & 0x7))

Observe that canary is only related to the lower three bits of the
address, so every 8 bytes of canary are the same.  We can access 8-byte
canary each time instead of byte-by-byte, thereby optimizing nearly 4k
memory accesses to 4k/8 times.

Use the bcc tool funclatency to measure the latency of __kfence_alloc()
and __kfence_free(), the numbers (deleted the distribution of latency) is
posted below.  Though different object sizes will have an impact on the
measurement, we ignore it for now and assume the average object size is
roughly equal.

Before patching:
__kfence_alloc:
avg = 5055 nsecs, total: 5515252 nsecs, count: 1091
__kfence_free:
avg = 5319 nsecs, total: 9735130 nsecs, count: 1830

After patching:
__kfence_alloc:
avg = 3597 nsecs, total: 6428491 nsecs, count: 1787
__kfence_free:
avg = 3046 nsecs, total: 3415390 nsecs, count: 1121

The numbers indicate that there is ~30% - ~40% performance improvement.

Link: https://lkml.kernel.org/r/20230403122738.6006-1-zhangpeng.00@bytedance.com
Signed-off-by: Peng Zhang <zhangpeng.00@bytedance.com>
Reviewed-by: Marco Elver <elver@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 49 insertions, 21 deletions

diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 1065e0568d05..d085ac7c8ae0 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -297,20 +297,13 @@ metadata_update_state(struct kfence_metadata *meta, enum kfence_object_state nex
 	WRITE_ONCE(meta->state, next);
 }
 
-/* Write canary byte to @addr. */
-static inline bool set_canary_byte(u8 *addr)
-{
-	*addr = KFENCE_CANARY_PATTERN(addr);
-	return true;
-}
-
 /* Check canary byte at @addr. */
 static inline bool check_canary_byte(u8 *addr)
 {
 	struct kfence_metadata *meta;
 	unsigned long flags;
 
-	if (likely(*addr == KFENCE_CANARY_PATTERN(addr)))
+	if (likely(*addr == KFENCE_CANARY_PATTERN_U8(addr)))
 		return true;
 
 	atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]);
@@ -323,15 +316,31 @@ static inline bool check_canary_byte(u8 *addr)
 	return false;
 }
 
-/* __always_inline this to ensure we won't do an indirect call to fn. */
-static __always_inline void for_each_canary(const struct kfence_metadata *meta, bool (*fn)(u8 *))
+static inline void set_canary(const struct kfence_metadata *meta)
 {
 	const unsigned long pageaddr = ALIGN_DOWN(meta->addr, PAGE_SIZE);
-	unsigned long addr;
+	unsigned long addr = pageaddr;
+
+	/*
+	 * The canary may be written to part of the object memory, but it does
+	 * not affect it. The user should initialize the object before using it.
+	 */
+	for (; addr < meta->addr; addr += sizeof(u64))
+		*((u64 *)addr) = KFENCE_CANARY_PATTERN_U64;
+
+	addr = ALIGN_DOWN(meta->addr + meta->size, sizeof(u64));
+	for (; addr - pageaddr < PAGE_SIZE; addr += sizeof(u64))
+		*((u64 *)addr) = KFENCE_CANARY_PATTERN_U64;
+}
+
+static inline void check_canary(const struct kfence_metadata *meta)
+{
+	const unsigned long pageaddr = ALIGN_DOWN(meta->addr, PAGE_SIZE);
+	unsigned long addr = pageaddr;
 
 	/*
-	 * We'll iterate over each canary byte per-side until fn() returns
-	 * false. However, we'll still iterate over the canary bytes to the
+	 * We'll iterate over each canary byte per-side until a corrupted byte
+	 * is found. However, we'll still iterate over the canary bytes to the
 	 * right of the object even if there was an error in the canary bytes to
 	 * the left of the object. Specifically, if check_canary_byte()
 	 * generates an error, showing both sides might give more clues as to
@@ -339,16 +348,35 @@ static __always_inline void for_each_canary(const struct kfence_metadata *meta,
 	 */
 
 	/* Apply to left of object. */
-	for (addr = pageaddr; addr < meta->addr; addr++) {
-		if (!fn((u8 *)addr))
+	for (; meta->addr - addr >= sizeof(u64); addr += sizeof(u64)) {
+		if (unlikely(*((u64 *)addr) != KFENCE_CANARY_PATTERN_U64))
 			break;
 	}
 
-	/* Apply to right of object. */
-	for (addr = meta->addr + meta->size; addr < pageaddr + PAGE_SIZE; addr++) {
-		if (!fn((u8 *)addr))
+	/*
+	 * If the canary is corrupted in a certain 64 bytes, or the canary
+	 * memory cannot be completely covered by multiple consecutive 64 bytes,
+	 * it needs to be checked one by one.
+	 */
+	for (; addr < meta->addr; addr++) {
+		if (unlikely(!check_canary_byte((u8 *)addr)))
 			break;
 	}
+
+	/* Apply to right of object. */
+	for (addr = meta->addr + meta->size; addr % sizeof(u64) != 0; addr++) {
+		if (unlikely(!check_canary_byte((u8 *)addr)))
+			return;
+	}
+	for (; addr - pageaddr < PAGE_SIZE; addr += sizeof(u64)) {
+		if (unlikely(*((u64 *)addr) != KFENCE_CANARY_PATTERN_U64)) {
+
+			for (; addr - pageaddr < PAGE_SIZE; addr++) {
+				if (!check_canary_byte((u8 *)addr))
+					return;
+			}
+		}
+	}
 }
 
 static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t gfp,
@@ -434,7 +462,7 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g
 #endif
 
 	/* Memory initialization. */
-	for_each_canary(meta, set_canary_byte);
+	set_canary(meta);
 
 	/*
 	 * We check slab_want_init_on_alloc() ourselves, rather than letting
@@ -495,7 +523,7 @@ static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool z
 	alloc_covered_add(meta->alloc_stack_hash, -1);
 
 	/* Check canary bytes for memory corruption. */
-	for_each_canary(meta, check_canary_byte);
+	check_canary(meta);
 
 	/*
 	 * Clear memory if init-on-free is set. While we protect the page, the
@@ -751,7 +779,7 @@ static void kfence_check_all_canary(void)
 		struct kfence_metadata *meta = &kfence_metadata[i];
 
 		if (meta->state == KFENCE_OBJECT_ALLOCATED)
-			for_each_canary(meta, check_canary_byte);
+			check_canary(meta);
 	}
 }