| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20240424100210.11982-3-puranjay@kernel.org>
Date: Wed, 24 Apr 2024 10:02:09 +0000
From: Puranjay Mohan <puranjay@...nel.org>
To: Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Andrii Nakryiko <andrii@...nel.org>,
Martin KaFai Lau <martin.lau@...ux.dev>,
Eduard Zingerman <eddyz87@...il.com>,
Song Liu <song@...nel.org>,
Yonghong Song <yonghong.song@...ux.dev>,
John Fastabend <john.fastabend@...il.com>,
KP Singh <kpsingh@...nel.org>,
Stanislav Fomichev <sdf@...gle.com>,
Hao Luo <haoluo@...gle.com>,
Jiri Olsa <jolsa@...nel.org>,
bpf@...r.kernel.org,
linux-kernel@...r.kernel.org,
Ilya Leoshkevich <iii@...ux.ibm.com>
Cc: puranjay12@...il.com
Subject: [PATCH bpf v6 2/3] bpf, x86: Fix PROBE_MEM runtime load check
When a load is marked PROBE_MEM - e.g. due to PTR_UNTRUSTED access - the
address being loaded from is not necessarily valid. The BPF jit sets up
exception handlers for each such load which catch page faults and 0 out
the destination register.
If the address for the load is outside kernel address space, the load
will escape the exception handling and crash the kernel. To prevent this
from happening, the emits some instruction to verify that addr is > end
of userspace addresses.
x86 has a legacy vsyscall ABI where a page at address 0xffffffffff600000
is mapped with user accessible permissions. The addresses in this page
are considered userspace addresses by the fault handler. Therefore, a
BPF program accessing this page will crash the kernel.
This patch fixes the runtime checks to also check that the PROBE_MEM
address is below VSYSCALL_ADDR.
Example BPF program:
SEC("fentry/tcp_v4_connect")
int BPF_PROG(fentry_tcp_v4_connect, struct sock *sk)
{
*(volatile unsigned long *)&sk->sk_tsq_flags;
return 0;
}
BPF Assembly:
0: (79) r1 = *(u64 *)(r1 +0)
1: (79) r1 = *(u64 *)(r1 +344)
2: (b7) r0 = 0
3: (95) exit
x86-64 JIT
==========
BEFORE AFTER
------ -----
0: nopl 0x0(%rax,%rax,1) 0: nopl 0x0(%rax,%rax,1)
5: xchg %ax,%ax 5: xchg %ax,%ax
7: push %rbp 7: push %rbp
8: mov %rsp,%rbp 8: mov %rsp,%rbp
b: mov 0x0(%rdi),%rdi b: mov 0x0(%rdi),%rdi
-------------------------------------------------------------------------------
f: movabs $0x100000000000000,%r11 f: movabs $0xffffffffff600000,%r10
19: add $0x2a0,%rdi 19: mov %rdi,%r11
20: cmp %r11,%rdi 1c: add $0x2a0,%r11
23: jae 0x0000000000000029 23: sub %r10,%r11
25: xor %edi,%edi 26: movabs $0x100000000a00000,%r10
27: jmp 0x000000000000002d 30: cmp %r10,%r11
29: mov 0x0(%rdi),%rdi 33: ja 0x0000000000000039
--------------------------------\ 35: xor %edi,%edi
2d: xor %eax,%eax \ 37: jmp 0x0000000000000040
2f: leave \ 39: mov 0x2a0(%rdi),%rdi
30: ret \--------------------------------------------
40: xor %eax,%eax
42: leave
43: ret
Signed-off-by: Puranjay Mohan <puranjay@...nel.org>
---
arch/x86/net/bpf_jit_comp.c | 57 ++++++++++++++++---------------------
1 file changed, 25 insertions(+), 32 deletions(-)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index b520b66ad14b..59cbc94b6e69 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1807,36 +1807,41 @@ st: if (is_imm8(insn->off))
if (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
BPF_MODE(insn->code) == BPF_PROBE_MEMSX) {
/* Conservatively check that src_reg + insn->off is a kernel address:
- * src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE
- * src_reg is used as scratch for src_reg += insn->off and restored
- * after emit_ldx if necessary
+ * src_reg + insn->off > TASK_SIZE_MAX + PAGE_SIZE
+ * and
+ * src_reg + insn->off < VSYSCALL_ADDR
*/
- u64 limit = TASK_SIZE_MAX + PAGE_SIZE;
+ u64 limit = TASK_SIZE_MAX + PAGE_SIZE - VSYSCALL_ADDR;
u8 *end_of_jmp;
- /* At end of these emitted checks, insn->off will have been added
- * to src_reg, so no need to do relative load with insn->off offset
- */
- insn_off = 0;
+ /* movabsq r10, VSYSCALL_ADDR */
+ emit_mov_imm64(&prog, BPF_REG_AX, (long)VSYSCALL_ADDR >> 32,
+ (u32)(long)VSYSCALL_ADDR);
- /* movabsq r11, limit */
- EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG));
- EMIT((u32)limit, 4);
- EMIT(limit >> 32, 4);
+ /* mov src_reg, r11 */
+ EMIT_mov(AUX_REG, src_reg);
if (insn->off) {
- /* add src_reg, insn->off */
- maybe_emit_1mod(&prog, src_reg, true);
- EMIT2_off32(0x81, add_1reg(0xC0, src_reg), insn->off);
+ /* add r11, insn->off */
+ maybe_emit_1mod(&prog, AUX_REG, true);
+ EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off);
}
- /* cmp src_reg, r11 */
- maybe_emit_mod(&prog, src_reg, AUX_REG, true);
- EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG));
+ /* sub r11, r10 */
+ maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true);
+ EMIT2(0x29, add_2reg(0xC0, AUX_REG, BPF_REG_AX));
+
+ /* movabsq r10, limit */
+ emit_mov_imm64(&prog, BPF_REG_AX, (long)limit >> 32,
+ (u32)(long)limit);
+
+ /* cmp r10, r11 */
+ maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true);
+ EMIT2(0x39, add_2reg(0xC0, AUX_REG, BPF_REG_AX));
- /* if unsigned '>=', goto load */
- EMIT2(X86_JAE, 0);
+ /* if unsigned '>', goto load */
+ EMIT2(X86_JA, 0);
end_of_jmp = prog;
/* xor dst_reg, dst_reg */
@@ -1862,18 +1867,6 @@ st: if (is_imm8(insn->off))
/* populate jmp_offset for JMP above */
start_of_ldx[-1] = prog - start_of_ldx;
- if (insn->off && src_reg != dst_reg) {
- /* sub src_reg, insn->off
- * Restore src_reg after "add src_reg, insn->off" in prev
- * if statement. But if src_reg == dst_reg, emit_ldx
- * above already clobbered src_reg, so no need to restore.
- * If add src_reg, insn->off was unnecessary, no need to
- * restore either.
- */
- maybe_emit_1mod(&prog, src_reg, true);
- EMIT2_off32(0x81, add_1reg(0xE8, src_reg), insn->off);
- }
-
if (!bpf_prog->aux->extable)
break;
--
2.40.1
Powered by blists - more mailing lists