bpf: Add alignment padding for "map_extra" + consolidate holes

This patch makes 2 changes regarding alignment padding
for the "map_extra" field.

1) In the kernel header, "map_extra" and "btf_value_type_id"
are rearranged to consolidate the hole.

Before:
struct bpf_map {
	...
        u32		max_entries;	/*    36     4	*/
        u32		map_flags;	/*    40     4	*/

        /* XXX 4 bytes hole, try to pack */

        u64		map_extra;	/*    48     8	*/
        int		spin_lock_off;	/*    56     4	*/
        int		timer_off;	/*    60     4	*/
        /* --- cacheline 1 boundary (64 bytes) --- */
        u32		id;		/*    64     4	*/
        int		numa_node;	/*    68     4	*/
	...
        bool		frozen;		/*   117     1	*/

        /* XXX 10 bytes hole, try to pack */

        /* --- cacheline 2 boundary (128 bytes) --- */
	...
        struct work_struct	work;	/*   144    72	*/

        /* --- cacheline 3 boundary (192 bytes) was 24 bytes ago --- */
	struct mutex	freeze_mutex;	/*   216   144 	*/

        /* --- cacheline 5 boundary (320 bytes) was 40 bytes ago --- */
        u64		writecnt; 	/*   360     8	*/

    /* size: 384, cachelines: 6, members: 26 */
    /* sum members: 354, holes: 2, sum holes: 14 */
    /* padding: 16 */
    /* forced alignments: 2, forced holes: 1, sum forced holes: 10 */

} __attribute__((__aligned__(64)));

After:
struct bpf_map {
	...
        u32		max_entries;	/*    36     4	*/
        u64		map_extra;	/*    40     8 	*/
        u32		map_flags;	/*    48     4	*/
        int		spin_lock_off;	/*    52     4	*/
        int		timer_off;	/*    56     4	*/
        u32		id;		/*    60     4	*/

        /* --- cacheline 1 boundary (64 bytes) --- */
        int		numa_node;	/*    64     4	*/
	...
	bool		frozen		/*   113     1  */

        /* XXX 14 bytes hole, try to pack */

        /* --- cacheline 2 boundary (128 bytes) --- */
	...
        struct work_struct	work;	/*   144    72	*/

        /* --- cacheline 3 boundary (192 bytes) was 24 bytes ago --- */
        struct mutex	freeze_mutex;	/*   216   144	*/

        /* --- cacheline 5 boundary (320 bytes) was 40 bytes ago --- */
        u64		writecnt;       /*   360     8	*/

    /* size: 384, cachelines: 6, members: 26 */
    /* sum members: 354, holes: 1, sum holes: 14 */
    /* padding: 16 */
    /* forced alignments: 2, forced holes: 1, sum forced holes: 14 */

} __attribute__((__aligned__(64)));

2) Add alignment padding to the bpf_map_info struct
More details can be found in commit 36f9814a494a ("bpf: fix uapi hole
for 32 bit compat applications")

Signed-off-by: Joanne Koong <joannekoong@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20211029224909.1721024-3-joannekoong@fb.com

include/linux/bpf.h

@@ -168,23 +168,23 @@ struct bpf_map {
 	u32 key_size;
 	u32 value_size;
 	u32 max_entries;
-	u32 map_flags;
 	u64 map_extra; /* any per-map-type extra fields */
+	u32 map_flags;
 	int spin_lock_off; /* >=0 valid offset, <0 error */
 	int timer_off; /* >=0 valid offset, <0 error */
 	u32 id;
 	int numa_node;
 	u32 btf_key_type_id;
 	u32 btf_value_type_id;
+	u32 btf_vmlinux_value_type_id;
 	struct btf *btf;
 #ifdef CONFIG_MEMCG_KMEM
 	struct mem_cgroup *memcg;
 #endif
 	char name[BPF_OBJ_NAME_LEN];
-	u32 btf_vmlinux_value_type_id;
 	bool bypass_spec_v1;
 	bool frozen; /* write-once; write-protected by freeze_mutex */
-	/* 22 bytes hole */
+	/* 14 bytes hole */
 
 	/* The 3rd and 4th cacheline with misc members to avoid false sharing
 	 * particularly with refcounting.

include/uapi/linux/bpf.h

@@ -5662,6 +5662,7 @@ struct bpf_map_info {
 	__u32 btf_id;
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
+	__u32 :32;	/* alignment pad */
 	__u64 map_extra;
 } __attribute__((aligned(8)));
 

tools/include/uapi/linux/bpf.h

@@ -5662,6 +5662,7 @@ struct bpf_map_info {
 	__u32 btf_id;
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
+	__u32 :32;	/* alignment pad */
 	__u64 map_extra;
 } __attribute__((aligned(8)));