linux-kernel - [PATCH 10/29] x86/bpf: Add ENDBR instructions to prologue

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

Message-ID: <20220218171409.160786220@infradead.org>
Date:   Fri, 18 Feb 2022 17:49:12 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     x86@...nel.org, joao@...rdrivepizza.com, hjl.tools@...il.com,
        jpoimboe@...hat.com, andrew.cooper3@...rix.com
Cc:     linux-kernel@...r.kernel.org, peterz@...radead.org,
        ndesaulniers@...gle.com, keescook@...omium.org,
        samitolvanen@...gle.com, mark.rutland@....com,
        alyssa.milburn@...el.com
Subject: [PATCH 10/29] x86/bpf: Add ENDBR instructions to prologue

With IBT enabled builds we need ENDBR instructions at indirect jump
target sites, since we start execution of the JIT'ed code through an
indirect jump, the very first instruction needs to be ENDBR.

Similarly, since eBPF tail-calls use indirect branches, their landing
site needs to be an ENDBR too.

Note: this shifts the trampoline patch site by 5 bytes but I've not
yet figured out where this is used.

Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
---
 arch/x86/net/bpf_jit_comp.c |   13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -46,6 +46,12 @@ static u8 *emit_code(u8 *ptr, u32 bytes,
 #define EMIT4_off32(b1, b2, b3, b4, off) \
 	do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
 
+#ifdef CONFIG_X86_IBT
+#define EMIT_ENDBR() EMIT4(0xf3, 0x0f, 0x1e, 0xfa)
+#else
+#define EMIT_ENDBR()
+#endif
+
 static bool is_imm8(int value)
 {
 	return value <= 127 && value >= -128;
@@ -241,7 +247,7 @@ struct jit_context {
 /* Number of bytes emit_patch() needs to generate instructions */
 #define X86_PATCH_SIZE		5
 /* Number of bytes that will be skipped on tailcall */
-#define X86_TAIL_CALL_OFFSET	11
+#define X86_TAIL_CALL_OFFSET	(11 + 4*IS_ENABLED(CONFIG_X86_IBT))
 
 static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
 {
@@ -286,6 +292,7 @@ static void emit_prologue(u8 **pprog, u3
 	/* BPF trampoline can be made to work without these nops,
 	 * but let's waste 5 bytes for now and optimize later
 	 */
+	EMIT_ENDBR();
 	memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
 	prog += X86_PATCH_SIZE;
 	if (!ebpf_from_cbpf) {
@@ -296,6 +303,10 @@ static void emit_prologue(u8 **pprog, u3
 	}
 	EMIT1(0x55);             /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+
+	/* X86_TAIL_CALL_OFFSET is here */
+	EMIT_ENDBR();
+
 	/* sub rsp, rounded_stack_depth */
 	if (stack_depth)
 		EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));