[PATCH bpf-next] bpf: Fix kmemleak warnings for percpu hashmap

[Yonghong Song <yonghong.song@linux.dev>]

Vlad Poenaru from Meta reported the following kmemleak issues:

  ...
  unreferenced object 0x606fd7c44ac8 (size 32):
    comm "floodgate_agent", pid 5077, jiffies 4294746072
    hex dump (first 32 bytes on cpu 32):
      00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
      00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    backtrace (crc 0):
      pcpu_alloc_noprof+0x730/0xeb0
      bpf_map_alloc_percpu+0x69/0xc0
      prealloc_init+0x9d/0x1b0
      htab_map_alloc+0x363/0x510
      map_create+0x215/0x3a0
      __sys_bpf+0x16b/0x3e0
      __x64_sys_bpf+0x18/0x20
      do_syscall_64+0x7b/0x150
      entry_SYSCALL_64_after_hwframe+0x4b/0x53
  unreferenced object 0x606fd7c44ae8 (size 32):
    comm "floodgate_agent", pid 5077, jiffies 4294746072
    hex dump (first 32 bytes on cpu 32):
      d3 08 00 00 00 00 00 00 d3 08 00 00 00 00 00 00  ................
      00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    backtrace (crc d197b0fe):
      pcpu_alloc_noprof+0x730/0xeb0
      bpf_map_alloc_percpu+0x69/0xc0
      prealloc_init+0x9d/0x1b0
      htab_map_alloc+0x363/0x510
      map_create+0x215/0x3a0
      __sys_bpf+0x16b/0x3e0
      __x64_sys_bpf+0x18/0x20
      do_syscall_64+0x7b/0x150
      entry_SYSCALL_64_after_hwframe+0x4b/0x53
  ...

Further investigation shows the reason is due to not 8-byte aligned
store of percpu pointer in htab_elem_set_ptr():
  *(void __percpu **)(l->key + key_size) = pptr;

Note that the whole htab_elem alignment is 8 (for x86_64). If the key_size
is 4, that means pptr is stored in a location which is 4 byte aligned but
not 8 byte aligned. In mm/kmemleak.c, scan_block() scans the memory based
on 8 byte stride, so it won't detect above pptr, hence reporting the memory
leak.

In htab_map_alloc(), we already have

        htab->elem_size = sizeof(struct htab_elem) +
                          round_up(htab->map.key_size, 8);
        if (percpu)
                htab->elem_size += sizeof(void *);
        else
                htab->elem_size += round_up(htab->map.value_size, 8);

So storing pptr with 8-byte alignment won't cause any problem and can fix
kmemleak too.

The issue can be reproduced with bpf selftest as well:
  1. Enable CONFIG_DEBUG_KMEMLEAK config
  2. Add a getchar() before skel destroy in test_hash_map() in prog_tests/for_each.c.
     The purpose is to keep map available so kmemleak can be detected.
  3. run './test_progs -t for_each/hash_map &' and a kmemleak should be reported.

     unreferenced object 0x607e08c1fd30 (size 8):
       comm "test_progs", pid 1969, jiffies 4294706961
       hex dump (first 8 bytes on cpu 2):
         03 00 00 00 00 00 00 00                          ........
       backtrace (crc 844a0efa):
         pcpu_alloc_noprof+0xf33/0x14a0
         bpf_map_alloc_percpu+0x9c/0x200
         prealloc_init+0x1e7/0x730
         htab_map_alloc+0x698/0xc70
         map_create+0x489/0xcb0
         __sys_bpf+0x443/0x560
         __x64_sys_bpf+0x7c/0x90
         do_syscall_64+0x58/0xf0
         entry_SYSCALL_64_after_hwframe+0x76/0x7e

cc: Vlad Poenaru <thevlad@meta.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
 kernel/bpf/hashtab.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 4a9eeb7aef85..c308300fc72f 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -198,12 +198,12 @@ static bool htab_is_percpu(const struct bpf_htab *htab)
 static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size,
 				     void __percpu *pptr)
 {
-	*(void __percpu **)(l->key + key_size) = pptr;
+	*(void __percpu **)(l->key + roundup(key_size, 8)) = pptr;
 }
 
 static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size)
 {
-	return *(void __percpu **)(l->key + key_size);
+	return *(void __percpu **)(l->key + roundup(key_size, 8));
 }
 
 static void *fd_htab_map_get_ptr(const struct bpf_map *map, struct htab_elem *l)
@@ -2354,7 +2354,7 @@ static int htab_percpu_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn
 	*insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem);
 	*insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3);
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_0,
-				offsetof(struct htab_elem, key) + map->key_size);
+				offsetof(struct htab_elem, key) + roundup(map->key_size, 8));
 	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0);
 	*insn++ = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0);
 
-- 
2.43.5