selftests/bpf: Cope with 512 bytes limit with bpf_global_percpu_ma

In the previous patch, the maximum data size for bpf_global_percpu_ma
is 512 bytes. This breaks selftest test_bpf_ma. The test is adjusted
in two aspects:
  - Since the maximum allowed data size for bpf_global_percpu_ma is
    512, remove all tests beyond that, names sizes 1024, 2048 and 4096.
  - Previously the percpu data size is bucket_size - 8 in order to
    avoid percpu allocation into the next bucket. This patch removed
    such data size adjustment thanks to Patch 1.

Also, a better way to generate BTF type is used than adding
a member to the value struct.

Acked-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20231222031807.1292853-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 33 insertions, 33 deletions

diff --git a/tools/testing/selftests/bpf/progs/test_bpf_ma.c b/tools/testing/selftests/bpf/progs/test_bpf_ma.c
index b78f4f702ae0..3494ca30fa7f 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_ma.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_ma.c
@@ -20,6 +20,9 @@ char _license[] SEC("license") = "GPL";
 const unsigned int data_sizes[] = {16, 32, 64, 96, 128, 192, 256, 512, 1024, 2048, 4096};
 const volatile unsigned int data_btf_ids[ARRAY_SIZE(data_sizes)] = {};
 
+const unsigned int percpu_data_sizes[] = {8, 16, 32, 64, 96, 128, 192, 256, 512};
+const volatile unsigned int percpu_data_btf_ids[ARRAY_SIZE(data_sizes)] = {};
+
 int err = 0;
 u32 pid = 0;
 
@@ -27,10 +30,10 @@ u32 pid = 0;
 	struct bin_data_##_size { \
 		char data[_size - sizeof(void *)]; \
 	}; \
+	/* See Commit 5d8d6634ccc, force btf generation for type bin_data_##_size */	\
+	struct bin_data_##_size *__bin_data_##_size; \
 	struct map_value_##_size { \
 		struct bin_data_##_size __kptr * data; \
-		/* To emit BTF info for bin_data_xx */ \
-		struct bin_data_##_size not_used; \
 	}; \
 	struct { \
 		__uint(type, BPF_MAP_TYPE_ARRAY); \
@@ -40,8 +43,12 @@ u32 pid = 0;
 	} array_##_size SEC(".maps")
 
 #define DEFINE_ARRAY_WITH_PERCPU_KPTR(_size) \
+	struct percpu_bin_data_##_size { \
+		char data[_size]; \
+	}; \
+	struct percpu_bin_data_##_size *__percpu_bin_data_##_size; \
 	struct map_value_percpu_##_size { \
-		struct bin_data_##_size __percpu_kptr * data; \
+		struct percpu_bin_data_##_size __percpu_kptr * data; \
 	}; \
 	struct { \
 		__uint(type, BPF_MAP_TYPE_ARRAY); \
@@ -114,7 +121,7 @@ static __always_inline void batch_percpu_alloc(struct bpf_map *map, unsigned int
 			return;
 		}
 		/* per-cpu allocator may not be able to refill in time */
-		new = bpf_percpu_obj_new_impl(data_btf_ids[idx], NULL);
+		new = bpf_percpu_obj_new_impl(percpu_data_btf_ids[idx], NULL);
 		if (!new)
 			continue;
 
@@ -179,7 +186,7 @@ DEFINE_ARRAY_WITH_KPTR(1024);
 DEFINE_ARRAY_WITH_KPTR(2048);
 DEFINE_ARRAY_WITH_KPTR(4096);
 
-/* per-cpu kptr doesn't support bin_data_8 which is a zero-sized array */
+DEFINE_ARRAY_WITH_PERCPU_KPTR(8);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(16);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(32);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(64);
@@ -188,9 +195,6 @@ DEFINE_ARRAY_WITH_PERCPU_KPTR(128);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(192);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(256);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(512);
-DEFINE_ARRAY_WITH_PERCPU_KPTR(1024);
-DEFINE_ARRAY_WITH_PERCPU_KPTR(2048);
-DEFINE_ARRAY_WITH_PERCPU_KPTR(4096);
 
 SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
 int test_batch_alloc_free(void *ctx)
@@ -246,20 +250,18 @@ int test_batch_percpu_alloc_free(void *ctx)
 	if ((u32)bpf_get_current_pid_tgid() != pid)
 		return 0;
 
-	/* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling,
-	 * then free 128 16-bytes per-cpu objects in batch to trigger freeing.
+	/* Alloc 128 8-bytes per-cpu objects in batch to trigger refilling,
+	 * then free 128 8-bytes per-cpu objects in batch to trigger freeing.
 	 */
-	CALL_BATCH_PERCPU_ALLOC_FREE(16, 128, 0);
-	CALL_BATCH_PERCPU_ALLOC_FREE(32, 128, 1);
-	CALL_BATCH_PERCPU_ALLOC_FREE(64, 128, 2);
-	CALL_BATCH_PERCPU_ALLOC_FREE(96, 128, 3);
-	CALL_BATCH_PERCPU_ALLOC_FREE(128, 128, 4);
-	CALL_BATCH_PERCPU_ALLOC_FREE(192, 128, 5);
-	CALL_BATCH_PERCPU_ALLOC_FREE(256, 128, 6);
-	CALL_BATCH_PERCPU_ALLOC_FREE(512, 64, 7);
-	CALL_BATCH_PERCPU_ALLOC_FREE(1024, 32, 8);
-	CALL_BATCH_PERCPU_ALLOC_FREE(2048, 16, 9);
-	CALL_BATCH_PERCPU_ALLOC_FREE(4096, 8, 10);
+	CALL_BATCH_PERCPU_ALLOC_FREE(8, 128, 0);
+	CALL_BATCH_PERCPU_ALLOC_FREE(16, 128, 1);
+	CALL_BATCH_PERCPU_ALLOC_FREE(32, 128, 2);
+	CALL_BATCH_PERCPU_ALLOC_FREE(64, 128, 3);
+	CALL_BATCH_PERCPU_ALLOC_FREE(96, 128, 4);
+	CALL_BATCH_PERCPU_ALLOC_FREE(128, 128, 5);
+	CALL_BATCH_PERCPU_ALLOC_FREE(192, 128, 6);
+	CALL_BATCH_PERCPU_ALLOC_FREE(256, 128, 7);
+	CALL_BATCH_PERCPU_ALLOC_FREE(512, 64, 8);
 
 	return 0;
 }
@@ -270,20 +272,18 @@ int test_percpu_free_through_map_free(void *ctx)
 	if ((u32)bpf_get_current_pid_tgid() != pid)
 		return 0;
 
-	/* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling,
+	/* Alloc 128 8-bytes per-cpu objects in batch to trigger refilling,
 	 * then free these object through map free.
 	 */
-	CALL_BATCH_PERCPU_ALLOC(16, 128, 0);
-	CALL_BATCH_PERCPU_ALLOC(32, 128, 1);
-	CALL_BATCH_PERCPU_ALLOC(64, 128, 2);
-	CALL_BATCH_PERCPU_ALLOC(96, 128, 3);
-	CALL_BATCH_PERCPU_ALLOC(128, 128, 4);
-	CALL_BATCH_PERCPU_ALLOC(192, 128, 5);
-	CALL_BATCH_PERCPU_ALLOC(256, 128, 6);
-	CALL_BATCH_PERCPU_ALLOC(512, 64, 7);
-	CALL_BATCH_PERCPU_ALLOC(1024, 32, 8);
-	CALL_BATCH_PERCPU_ALLOC(2048, 16, 9);
-	CALL_BATCH_PERCPU_ALLOC(4096, 8, 10);
+	CALL_BATCH_PERCPU_ALLOC(8, 128, 0);
+	CALL_BATCH_PERCPU_ALLOC(16, 128, 1);
+	CALL_BATCH_PERCPU_ALLOC(32, 128, 2);
+	CALL_BATCH_PERCPU_ALLOC(64, 128, 3);
+	CALL_BATCH_PERCPU_ALLOC(96, 128, 4);
+	CALL_BATCH_PERCPU_ALLOC(128, 128, 5);
+	CALL_BATCH_PERCPU_ALLOC(192, 128, 6);
+	CALL_BATCH_PERCPU_ALLOC(256, 128, 7);
+	CALL_BATCH_PERCPU_ALLOC(512, 64, 8);
 
 	return 0;
 }