netdev - [PATCH bpf v2 2/2] x86/bpf: Fix IP for relocating call depth accounting

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <20240401172157.5717-3-ubizjak@gmail.com>
Date: Mon,  1 Apr 2024 19:19:00 +0200
From: Uros Bizjak <ubizjak@...il.com>
To: x86@...nel.org,
	bpf@...r.kernel.org,
	netdev@...r.kernel.org,
	linux-kernel@...r.kernel.org
Cc: Joan Bruguera Micó <joanbrugueram@...il.com>,
	Uros Bizjak <ubizjak@...il.com>,
	Ingo Molnar <mingo@...nel.org>,
	Alexei Starovoitov <ast@...nel.org>,
	Daniel Borkmann <daniel@...earbox.net>
Subject: [PATCH bpf v2 2/2] x86/bpf: Fix IP for relocating call depth accounting

From: Joan Bruguera Micó <joanbrugueram@...il.com>

The recently introduced support for %rip-relative relocations in the
call thunk template:

  17bce3b2ae2d ("x86/callthunks: Handle %rip-relative relocations in call thunk template")

assumes that the code is being patched in-place, so the destination
of the relocation matches the address of the code. This is not true
for the call depth accounting emitted by the BPF JIT, so the calculated
address is wrong and usually causes a page fault.

Pass the destination IP when the BPF JIT emits call depth accounting.

Fixes: 17bce3b2ae2d ("x86/callthunks: Handle %rip-relative relocations in call thunk template")
Signed-off-by: Joan Bruguera Micó <joanbrugueram@...il.com>
Reviewed-by: Uros Bizjak <ubizjak@...il.com>
Acked-by: Ingo Molnar <mingo@...nel.org>
Cc: Alexei Starovoitov <ast@...nel.org>
Cc: Daniel Borkmann <daniel@...earbox.net>
---
 arch/x86/include/asm/alternative.h |  4 ++--
 arch/x86/kernel/callthunks.c       |  4 ++--
 arch/x86/net/bpf_jit_comp.c        | 19 ++++++++-----------
 3 files changed, 12 insertions(+), 15 deletions(-)

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index fcd20c6dc7f9..67b68d0d17d1 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -117,7 +117,7 @@ extern void callthunks_patch_builtin_calls(void);
 extern void callthunks_patch_module_calls(struct callthunk_sites *sites,
 					  struct module *mod);
 extern void *callthunks_translate_call_dest(void *dest);
-extern int x86_call_depth_emit_accounting(u8 **pprog, void *func);
+extern int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip);
 #else
 static __always_inline void callthunks_patch_builtin_calls(void) {}
 static __always_inline void
@@ -128,7 +128,7 @@ static __always_inline void *callthunks_translate_call_dest(void *dest)
 	return dest;
 }
 static __always_inline int x86_call_depth_emit_accounting(u8 **pprog,
-							  void *func)
+							  void *func, void *ip)
 {
 	return 0;
 }
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 30335182b6b0..e92ff0c11db8 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -314,7 +314,7 @@ static bool is_callthunk(void *addr)
 	return !bcmp(pad, insn_buff, tmpl_size);
 }
 
-int x86_call_depth_emit_accounting(u8 **pprog, void *func)
+int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip)
 {
 	unsigned int tmpl_size = SKL_TMPL_SIZE;
 	u8 insn_buff[MAX_PATCH_LEN];
@@ -327,7 +327,7 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func)
 		return 0;
 
 	memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
-	apply_relocation(insn_buff, tmpl_size, *pprog,
+	apply_relocation(insn_buff, tmpl_size, ip,
 			 skl_call_thunk_template, tmpl_size);
 
 	memcpy(*pprog, insn_buff, tmpl_size);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index e55745f512e1..df5fac428408 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -480,7 +480,7 @@ static int emit_call(u8 **pprog, void *func, void *ip)
 static int emit_rsb_call(u8 **pprog, void *func, void *ip)
 {
 	OPTIMIZER_HIDE_VAR(func);
-	ip += x86_call_depth_emit_accounting(pprog, func);
+	ip += x86_call_depth_emit_accounting(pprog, func, ip);
 	return emit_patch(pprog, func, ip, 0xE8);
 }
 
@@ -1972,20 +1972,17 @@ st:			if (is_imm8(insn->off))
 
 			/* call */
 		case BPF_JMP | BPF_CALL: {
-			int offs;
+			u8 *ip = image + addrs[i - 1];
 
 			func = (u8 *) __bpf_call_base + imm32;
 			if (tail_call_reachable) {
 				RESTORE_TAIL_CALL_CNT(bpf_prog->aux->stack_depth);
-				if (!imm32)
-					return -EINVAL;
-				offs = 7 + x86_call_depth_emit_accounting(&prog, func);
-			} else {
-				if (!imm32)
-					return -EINVAL;
-				offs = x86_call_depth_emit_accounting(&prog, func);
+				ip += 7;
 			}
-			if (emit_call(&prog, func, image + addrs[i - 1] + offs))
+			if (!imm32)
+				return -EINVAL;
+			ip += x86_call_depth_emit_accounting(&prog, func, ip);
+			if (emit_call(&prog, func, ip))
 				return -EINVAL;
 			break;
 		}
@@ -2835,7 +2832,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		 * Direct-call fentry stub, as such it needs accounting for the
 		 * __fentry__ call.
 		 */
-		x86_call_depth_emit_accounting(&prog, NULL);
+		x86_call_depth_emit_accounting(&prog, NULL, image);
 	}
 	EMIT1(0x55);		 /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
-- 
2.42.0