bpf: Add copy_map_value_long to copy to remote percpu memory

bpf_long_memcpy is used while copying to remote percpu regions from BPF
syscall and helpers, so that the copy is atomic at word size
granularity.

This might not be possible when you copy from map value hosting kptrs
from or to percpu maps, as the alignment or size in disjoint regions may
not be multiple of word size.

Hence, to avoid complicating the copy loop, we only use bpf_long_memcpy
when special fields are not present, otherwise use normal memcpy to copy
the disjoint regions.
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20220904204145.3089-2-memxor@gmail.comSigned-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf.h

@@ -280,13 +280,32 @@ static inline void check_and_init_map_value(struct bpf_map *map, void *dst)
 	}
 }
 
-/* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */
-static inline void copy_map_value(struct bpf_map *map, void *dst, void *src)
+/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
+ * forced to use 'long' read/writes to try to atomically copy long counters.
+ * Best-effort only.  No barriers here, since it _will_ race with concurrent
+ * updates from BPF programs. Called from bpf syscall and mostly used with
+ * size 8 or 16 bytes, so ask compiler to inline it.
+ */
+static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
+{
+	const long *lsrc = src;
+	long *ldst = dst;
+
+	size /= sizeof(long);
+	while (size--)
+		*ldst++ = *lsrc++;
+}
+
+/* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */
+static inline void __copy_map_value(struct bpf_map *map, void *dst, void *src, bool long_memcpy)
 {
 	u32 curr_off = 0;
 	int i;
 
 	if (likely(!map->off_arr)) {
+		if (long_memcpy)
+			bpf_long_memcpy(dst, src, round_up(map->value_size, 8));
+		else
 			memcpy(dst, src, map->value_size);
 		return;
 	}
@@ -299,6 +318,17 @@ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src)
 	}
 	memcpy(dst + curr_off, src + curr_off, map->value_size - curr_off);
 }
+
+static inline void copy_map_value(struct bpf_map *map, void *dst, void *src)
+{
+	__copy_map_value(map, dst, src, false);
+}
+
+static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src)
+{
+	__copy_map_value(map, dst, src, true);
+}
+
 void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
 			   bool lock_src);
 void bpf_timer_cancel_and_free(void *timer);
@@ -1827,22 +1857,6 @@ int bpf_get_file_flag(int flags);
 int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size,
 			     size_t actual_size);
 
-/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
- * forced to use 'long' read/writes to try to atomically copy long counters.
- * Best-effort only.  No barriers here, since it _will_ race with concurrent
- * updates from BPF programs. Called from bpf syscall and mostly used with
- * size 8 or 16 bytes, so ask compiler to inline it.
- */
-static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
-{
-	const long *lsrc = src;
-	long *ldst = dst;
-
-	size /= sizeof(long);
-	while (size--)
-		*ldst++ = *lsrc++;
-}
-
 /* verify correctness of eBPF program */
 int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr);