[PATCH bpf-next] bpf: x86: use kvmalloc_array instead kmalloc_array in bpf_jit_comp

[PATCH bpf-next] bpf: x86: use kvmalloc_array instead kmalloc_array in bpf_jit_comp

[Yonghong Song]

x86 bpf_jit_comp.c used kmalloc_array to store jited addresses
for each bpf insn. With a large bpf program, we have see the
following allocation failures in our production server:
    page allocation failure: order:5, mode:0x40cc0(GFP_KERNEL|__GFP_COMP),
                             nodemask=(null),cpuset=/,mems_allowed=0"
    Call Trace:
    dump_stack+0x50/0x70
    warn_alloc.cold.120+0x72/0xd2
    ? __alloc_pages_direct_compact+0x157/0x160
    __alloc_pages_slowpath+0xcdb/0xd00
    ? get_page_from_freelist+0xe44/0x1600
    ? vunmap_page_range+0x1ba/0x340
    __alloc_pages_nodemask+0x2c9/0x320
    kmalloc_order+0x18/0x80
    kmalloc_order_trace+0x1d/0xa0
    bpf_int_jit_compile+0x1e2/0x484
    ? kmalloc_order_trace+0x1d/0xa0
    bpf_prog_select_runtime+0xc3/0x150
    bpf_prog_load+0x480/0x720
    ? __mod_memcg_lruvec_state+0x21/0x100
    __do_sys_bpf+0xc31/0x2040
    ? close_pdeo+0x86/0xe0
    do_syscall_64+0x42/0x110
    entry_SYSCALL_64_after_hwframe+0x44/0xa9
    RIP: 0033:0x7f2f300f7fa9
    Code: Bad RIP value.

Dumped assembly:
    ffffffff810b6d70 <bpf_int_jit_compile>:
    ; {
    ffffffff810b6d70: e8 eb a5 b4 00        callq   0xffffffff81c01360 <__fentry__>
    ffffffff810b6d75: 41 57                 pushq   %r15
    ...
    ffffffff810b6f39: e9 72 fe ff ff        jmp     0xffffffff810b6db0 <bpf_int_jit_compile+0x40>
    ;       addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
    ffffffff810b6f3e: 8b 45 0c              movl    12(%rbp), %eax
    ;       return __kmalloc(bytes, flags);
    ffffffff810b6f41: be c0 0c 00 00        movl    $3264, %esi
    ;       addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
    ffffffff810b6f46: 8d 78 01              leal    1(%rax), %edi
    ;       if (unlikely(check_mul_overflow(n, size, &bytes)))
    ffffffff810b6f49: 48 c1 e7 02           shlq    $2, %rdi
    ;       return __kmalloc(bytes, flags);
    ffffffff810b6f4d: e8 8e 0c 1d 00        callq   0xffffffff81287be0 <__kmalloc>
    ;       if (!addrs) {
    ffffffff810b6f52: 48 85 c0              testq   %rax, %rax

Change kmalloc_array() to kvmalloc_array() to avoid potential
allocation error for big bpf programs.

Signed-off-by: Yonghong Song <yhs@fb.com>
---
 arch/x86/net/bpf_jit_comp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

Note: I labelled this patch as bpf-next as I cannot find a proper
      fix tag. The previous commit which touched the same code is
        7c2e988f400e ("bpf: fix x64 JIT code generation for jmp to 1st insn")
      which is not this patch intending to fix.

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 79e7a0ec1da5..487de2d5fdd9 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -2221,7 +2221,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		padding = true;
 		goto skip_init_addrs;
 	}
-	addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
+	addrs = kvmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
 	if (!addrs) {
 		prog = orig_prog;
 		goto out_addrs;
@@ -2313,7 +2313,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		if (image)
 			bpf_prog_fill_jited_linfo(prog, addrs + 1);
 out_addrs:
-		kfree(addrs);
+		kvfree(addrs);
 		kfree(jit_data);
 		prog->aux->jit_data = NULL;
 	}
-- 
2.24.1