From: Peter Zijlstra <peterz@infradead.org>
To: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: x86@kernel.org, joao@overdrivepizza.com, hjl.tools@gmail.com,
andrew.cooper3@citrix.com, linux-kernel@vger.kernel.org,
ndesaulniers@google.com, keescook@chromium.org,
samitolvanen@google.com, mark.rutland@arm.com,
alyssa.milburn@intel.com, mbenes@suse.cz, rostedt@goodmis.org,
mhiramat@kernel.org, alexei.starovoitov@gmail.com
Subject: Re: [PATCH v2 00/39] x86: Kernel IBT
Date: Fri, 25 Feb 2022 16:28:32 +0100 [thread overview]
Message-ID: <Yhj1oFcTl2RnghBz@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20220224202602.3gvz5tnxvwb4maod@treble>
On Thu, Feb 24, 2022 at 12:26:02PM -0800, Josh Poimboeuf wrote:
> Bricked my SPR:
>
> [ 21.602888] jump_label: Fatal kernel bug, unexpected op at sched_clock_stable+0x4/0x20 [0000000074a0db20] (eb 06 b8 01 00 != eb 0a 00 00 00)) size:2 type:0
> ffffffff81120a70 <sched_clock_stable>:
> ffffffff81120a70: f3 0f 1e fa endbr64
> ffffffff81120a74: eb 06 jmp ffffffff81120a7c <sched_clock_stable+0xc>
> ffffffff81120a76: b8 01 00 00 00 mov $0x1,%eax
> ffffffff81120a7b: c3 retq
> ffffffff81120a7c: f3 0f 1e fa endbr64
> ffffffff81120a80: 31 c0 xor %eax,%eax
> ffffffff81120a82: c3 retq
> ffffffff81120a83: 66 66 2e 0f 1f 84 00 data16 nopw %cs:0x0(%rax,%rax,1)
> ffffffff81120a8a: 00 00 00 00
> ffffffff81120a8e: 66 90 xchg %ax,%ax
This is due to you having a very old (and arguably buggy) compiler :-( I
can reproduce with gcc-8.4 and gcc-9.4, my gcc-10.3 compiler no longer
generates daft code like that, nor do any later.
That said, I can fix objtool to also re-write jumps to in-the-middle
ENDBR like this, but then I do get a bunch of:
OBJTOOL vmlinux.o
vmlinux.o: warning: objtool: displacement doesn't fit
vmlinux.o: warning: objtool: ep_insert()+0xbc5: Direct IMM jump to ENDBR; cannot fix
vmlinux.o: warning: objtool: displacement doesn't fit
vmlinux.o: warning: objtool: configfs_depend_prep()+0x76: Direct IMM jump to ENDBR; cannot fix
vmlinux.o: warning: objtool: displacement doesn't fit
vmlinux.o: warning: objtool: request_key_and_link()+0x17b: Direct IMM jump to ENDBR; cannot fix
vmlinux.o: warning: objtool: displacement doesn't fit
vmlinux.o: warning: objtool: blk_mq_poll()+0x2e0: Direct IMM jump to ENDBR; cannot fix
The alternative is only skipping endbr at +0 I suppose, lemme go try
that with the brand spanking new skip_endbr() function.
Yep,.. that seems to cure things. It noaw boats when build with old
crappy compilers too.
--- a/arch/x86/include/asm/ibt.h
+++ b/arch/x86/include/asm/ibt.h
@@ -47,6 +47,8 @@ static inline bool is_endbr(unsigned int
return val == gen_endbr();
}
+extern void *skip_endbr(void *);
+
extern __noendbr u64 ibt_save(void);
extern __noendbr void ibt_restore(u64 save);
@@ -71,6 +73,7 @@ extern __noendbr void ibt_restore(u64 sa
#define __noendbr
static inline bool is_endbr(unsigned int val) { return false; }
+static inline void *skip_endbr(void *addr) { return addr; }
static inline u64 ibt_save(void) { return 0; }
static inline void ibt_restore(u64 save) { }
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -112,10 +112,7 @@ void __text_gen_insn(void *buf, u8 opcod
OPTIMIZER_HIDE_VAR(addr);
OPTIMIZER_HIDE_VAR(dest);
-#ifdef CONFIG_X86_KERNEL_IBT
- if (is_endbr(*(u32 *)dest))
- dest += 4;
-#endif
+ dest = skip_endbr((void *)dest);
insn->opcode = opcode;
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -620,6 +620,19 @@ __noendbr void ibt_restore(u64 save)
}
}
+
+void *skip_endbr(void *addr)
+{
+ unsigned long size, offset;
+
+ if (is_endbr(*(unsigned int *)addr) &&
+ kallsyms_lookup_size_offset((unsigned long)addr, &size, &offset) &&
+ !offset)
+ addr += 4;
+
+ return addr;
+}
+
#endif
static __always_inline void setup_cet(struct cpuinfo_x86 *c)
@@ -636,7 +649,10 @@ static __always_inline void setup_cet(st
if (!ibt_selftest()) {
pr_err("IBT selftest: Failed!\n");
setup_clear_cpu_cap(X86_FEATURE_IBT);
+ return;
}
+
+ pr_info("CET detected: Indirect Branch Tracking enabled\n");
}
__noendbr void cet_disable(void)
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -350,18 +350,12 @@ static int __bpf_arch_text_poke(void *ip
u8 *prog;
int ret;
-#ifdef CONFIG_X86_KERNEL_IBT
- if (is_endbr(*(u32 *)ip))
- ip += 4;
-#endif
+ ip = skip_endbr(ip);
memcpy(old_insn, nop_insn, X86_PATCH_SIZE);
if (old_addr) {
prog = old_insn;
-#ifdef CONFIG_X86_KERNEL_IBT
- if (is_endbr(*(u32 *)old_addr))
- old_addr += 4;
-#endif
+ old_addr = skip_endbr(old_addr);
ret = t == BPF_MOD_CALL ?
emit_call(&prog, old_addr, ip) :
emit_jump(&prog, old_addr, ip);
@@ -372,10 +366,7 @@ static int __bpf_arch_text_poke(void *ip
memcpy(new_insn, nop_insn, X86_PATCH_SIZE);
if (new_addr) {
prog = new_insn;
-#ifdef CONFIG_X86_KERNEL_IBT
- if (is_endbr(*(u32 *)new_addr))
- new_addr += 4;
-#endif
+ new_addr = skip_endbr(new_addr);
ret = t == BPF_MOD_CALL ?
emit_call(&prog, new_addr, ip) :
emit_jump(&prog, new_addr, ip);
next prev parent reply other threads:[~2022-02-25 15:29 UTC|newest]
Thread overview: 183+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-24 14:51 [PATCH v2 00/39] x86: Kernel IBT Peter Zijlstra
2022-02-24 14:51 ` [PATCH v2 01/39] kbuild: Fix clang build Peter Zijlstra
2022-02-25 0:11 ` Kees Cook
2022-03-01 21:16 ` Nick Desaulniers
2022-03-02 0:47 ` Kees Cook
2022-03-02 0:53 ` Fangrui Song
2022-03-02 16:37 ` Nathan Chancellor
2022-03-02 18:40 ` Kees Cook
2022-03-02 19:18 ` Nick Desaulniers
2022-03-02 21:15 ` Nathan Chancellor
2022-03-02 22:07 ` Nick Desaulniers
2022-03-02 23:00 ` Kees Cook
2022-03-02 23:10 ` Peter Zijlstra
2022-02-24 14:51 ` [PATCH v2 02/39] static_call: Avoid building empty .static_call_sites Peter Zijlstra
2022-02-24 14:51 ` [PATCH v2 03/39] x86/module: Fix the paravirt vs alternative order Peter Zijlstra
2022-03-01 14:37 ` Miroslav Benes
2022-02-24 14:51 ` [PATCH v2 04/39] objtool: Add --dry-run Peter Zijlstra
2022-02-25 0:27 ` Kees Cook
2022-03-01 14:37 ` Miroslav Benes
2022-02-24 14:51 ` [PATCH v2 05/39] x86: Base IBT bits Peter Zijlstra
2022-02-25 0:35 ` Kees Cook
2022-02-25 0:46 ` Nathan Chancellor
2022-02-25 22:08 ` Nathan Chancellor
2022-02-26 0:29 ` Joao Moreira
2022-02-26 4:58 ` Kees Cook
2022-02-26 4:59 ` Fāng-ruì Sòng
2022-02-26 5:04 ` Kees Cook
2022-02-25 13:41 ` Peter Zijlstra
2022-02-24 14:51 ` [PATCH v2 06/39] x86/ibt: Add ANNOTATE_NOENDBR Peter Zijlstra
2022-02-25 0:36 ` Kees Cook
2022-02-24 14:51 ` [PATCH v2 07/39] x86/entry: Sprinkle ENDBR dust Peter Zijlstra
2022-02-24 22:37 ` Josh Poimboeuf
2022-02-25 0:42 ` Kees Cook
2022-02-25 9:22 ` Andrew Cooper
2022-02-24 14:51 ` [PATCH v2 08/39] x86/linkage: Add ENDBR to SYM_FUNC_START*() Peter Zijlstra
2022-02-25 0:45 ` Kees Cook
2022-02-24 14:51 ` [PATCH v2 09/39] x86/ibt,paravirt: Sprinkle ENDBR Peter Zijlstra
2022-02-25 0:47 ` Kees Cook
2022-02-24 14:51 ` [PATCH v2 10/39] x86/ibt,crypto: Add ENDBR for the jump-table entries Peter Zijlstra
2022-02-24 22:41 ` Josh Poimboeuf
2022-02-25 0:50 ` Kees Cook
2022-02-25 10:22 ` Peter Zijlstra
2022-02-24 14:51 ` [PATCH v2 11/39] x86/ibt,kvm: Add ENDBR to fastops Peter Zijlstra
2022-02-25 0:54 ` Kees Cook
2022-02-25 10:24 ` Peter Zijlstra
2022-02-25 13:09 ` David Laight
2022-02-24 14:51 ` [PATCH v2 12/39] x86/ibt,ftrace: Search for __fentry__ location Peter Zijlstra
2022-02-24 15:55 ` Masami Hiramatsu
2022-02-24 15:58 ` Steven Rostedt
2022-02-24 15:59 ` Steven Rostedt
2022-02-24 16:01 ` Steven Rostedt
2022-02-24 22:46 ` Josh Poimboeuf
2022-02-24 22:51 ` Steven Rostedt
2022-02-25 1:34 ` Masami Hiramatsu
2022-02-25 2:19 ` Steven Rostedt
2022-02-25 10:20 ` Masami Hiramatsu
2022-02-25 13:36 ` Steven Rostedt
2022-03-01 18:57 ` Naveen N. Rao
2022-03-01 19:20 ` Steven Rostedt
2022-03-02 13:20 ` Peter Zijlstra
2022-03-02 16:01 ` Steven Rostedt
2022-03-02 19:47 ` Steven Rostedt
2022-03-02 20:48 ` Steven Rostedt
2022-03-02 20:51 ` Peter Zijlstra
2022-03-03 9:45 ` Naveen N. Rao
2022-03-03 13:04 ` Peter Zijlstra
2022-03-03 14:34 ` Steven Rostedt
2022-03-03 15:59 ` Peter Zijlstra
2022-03-06 3:48 ` Masami Hiramatsu
2022-03-09 11:47 ` Naveen N. Rao
2022-03-03 14:39 ` Naveen N. Rao
2022-02-25 0:55 ` Kees Cook
2022-03-02 16:25 ` Naveen N. Rao
2022-02-24 14:51 ` [PATCH v2 13/39] x86/livepatch: Validate " Peter Zijlstra
2022-02-24 23:02 ` Josh Poimboeuf
2022-02-24 14:51 ` [PATCH v2 14/39] x86/ibt,ftrace: Make function-graph play nice Peter Zijlstra
2022-02-24 15:36 ` Peter Zijlstra
2022-02-24 15:42 ` Steven Rostedt
2022-02-24 23:09 ` Peter Zijlstra
2022-02-24 14:51 ` [PATCH v2 15/39] x86/ibt,kprobes: Fix more +0 assumptions Peter Zijlstra
2022-02-25 0:58 ` Kees Cook
2022-02-25 1:32 ` Masami Hiramatsu
2022-02-25 10:46 ` Peter Zijlstra
2022-02-25 13:42 ` Masami Hiramatsu
2022-02-25 15:41 ` Peter Zijlstra
2022-02-26 2:10 ` Masami Hiramatsu
2022-02-26 11:48 ` Peter Zijlstra
2022-02-25 14:14 ` Steven Rostedt
2022-02-26 7:09 ` Masami Hiramatsu
2022-02-28 6:07 ` Masami Hiramatsu
2022-02-28 23:25 ` Peter Zijlstra
2022-03-01 2:49 ` Masami Hiramatsu
2022-03-01 8:28 ` Peter Zijlstra
2022-03-01 17:19 ` Naveen N. Rao
2022-03-01 19:12 ` Peter Zijlstra
2022-03-01 20:05 ` Peter Zijlstra
2022-03-02 15:59 ` Naveen N. Rao
2022-03-02 16:38 ` Peter Zijlstra
2022-03-02 16:17 ` Naveen N. Rao
2022-03-02 19:32 ` Peter Zijlstra
2022-03-02 19:39 ` Peter Zijlstra
2022-03-03 12:11 ` Naveen N. Rao
2022-03-03 1:54 ` Masami Hiramatsu
2022-03-02 0:11 ` Masami Hiramatsu
2022-03-02 10:25 ` Peter Zijlstra
2022-03-01 17:03 ` Naveen N. Rao
2022-02-24 14:51 ` [PATCH v2 16/39] x86/bpf: Add ENDBR instructions to prologue and trampoline Peter Zijlstra
2022-02-24 23:37 ` Josh Poimboeuf
2022-02-25 0:59 ` Kees Cook
2022-02-25 11:20 ` Peter Zijlstra
2022-02-25 12:24 ` Peter Zijlstra
2022-02-25 22:46 ` Josh Poimboeuf
2022-02-24 14:51 ` [PATCH v2 17/39] x86/ibt,ftrace: Add ENDBR to samples/ftrace Peter Zijlstra
2022-02-24 14:51 ` [PATCH v2 18/39] x86/ibt: Add IBT feature, MSR and #CP handling Peter Zijlstra
2022-02-24 23:55 ` Josh Poimboeuf
2022-02-25 10:51 ` Peter Zijlstra
2022-02-25 11:10 ` Peter Zijlstra
2022-02-25 23:51 ` Josh Poimboeuf
2022-02-26 11:55 ` Peter Zijlstra
2022-02-25 1:09 ` Kees Cook
2022-02-25 19:59 ` Edgecombe, Rick P
2022-03-01 15:14 ` Peter Zijlstra
2022-03-01 21:02 ` Peter Zijlstra
2022-03-01 23:13 ` Josh Poimboeuf
2022-03-02 1:59 ` Edgecombe, Rick P
2022-03-02 13:49 ` Peter Zijlstra
2022-03-02 18:38 ` Kees Cook
2022-02-24 14:51 ` [PATCH v2 19/39] x86: Disable IBT around firmware Peter Zijlstra
2022-02-25 1:10 ` Kees Cook
2022-02-24 14:51 ` [PATCH v2 20/39] x86/bugs: Disable Retpoline when IBT Peter Zijlstra
2022-02-25 1:11 ` Kees Cook
2022-02-25 2:22 ` Josh Poimboeuf
2022-02-25 10:55 ` Peter Zijlstra
2022-02-24 14:51 ` [PATCH v2 21/39] x86/ibt: Annotate text references Peter Zijlstra
2022-02-25 0:47 ` Josh Poimboeuf
2022-02-25 12:57 ` Peter Zijlstra
2022-02-25 13:04 ` Peter Zijlstra
2022-02-24 14:52 ` [PATCH v2 22/39] x86/ibt,ftrace: Annotate ftrace code patching Peter Zijlstra
2022-02-24 14:52 ` [PATCH v2 23/39] x86/ibt,sev: Annotations Peter Zijlstra
2022-02-24 14:52 ` [PATCH v2 24/39] x86/text-patching: Make text_gen_insn() IBT aware Peter Zijlstra
2022-02-25 0:49 ` Josh Poimboeuf
2022-02-24 14:52 ` [PATCH v2 25/39] x86/ibt,paravirt: Use text_gen_insn() for paravirt_patch() Peter Zijlstra
2022-02-24 14:52 ` [PATCH v2 26/39] x86/entry: Cleanup PARAVIRT Peter Zijlstra
2022-02-24 14:52 ` [PATCH v2 27/39] x86/entry,xen: Early rewrite of restore_regs_and_return_to_kernel() Peter Zijlstra
2022-02-24 17:51 ` Andrew Cooper
2022-02-24 14:52 ` [PATCH v2 28/39] x86/ibt,xen: Sprinkle the ENDBR Peter Zijlstra
2022-02-25 0:54 ` Josh Poimboeuf
2022-02-25 13:16 ` Peter Zijlstra
2022-02-24 14:52 ` [PATCH v2 29/39] objtool: Rename --duplicate to --lto Peter Zijlstra
2022-02-24 14:52 ` [PATCH v2 30/39] Kbuild: Allow whole module objtool runs Peter Zijlstra
2022-02-24 14:52 ` [PATCH v2 31/39] objtool: Read the NOENDBR annotation Peter Zijlstra
2022-02-24 14:52 ` [PATCH v2 32/39] x86/ibt: Dont generate ENDBR in .discard.text Peter Zijlstra
2022-02-24 14:52 ` [PATCH v2 33/39] objtool: Add IBT/ENDBR decoding Peter Zijlstra
2022-03-03 10:53 ` Miroslav Benes
2022-03-03 11:06 ` Andrew Cooper
2022-03-03 12:33 ` Miroslav Benes
2022-03-03 14:13 ` Peter Zijlstra
2022-02-24 14:52 ` [PATCH v2 34/39] objtool: Validate IBT assumptions Peter Zijlstra
2022-02-27 3:13 ` Josh Poimboeuf
2022-02-27 17:00 ` Peter Zijlstra
2022-02-27 22:20 ` Josh Poimboeuf
2022-02-28 9:47 ` Peter Zijlstra
2022-02-28 18:36 ` Josh Poimboeuf
2022-02-28 20:10 ` Peter Zijlstra
2022-02-28 9:26 ` Peter Zijlstra
2022-02-28 18:39 ` Josh Poimboeuf
2022-02-24 14:52 ` [PATCH v2 35/39] objtool: IBT fix direct JMP/CALL Peter Zijlstra
2022-02-24 14:52 ` [PATCH v2 36/39] objtool: Find unused ENDBR instructions Peter Zijlstra
2022-02-27 3:46 ` Josh Poimboeuf
2022-02-28 12:41 ` Peter Zijlstra
2022-02-28 17:36 ` Josh Poimboeuf
2022-02-24 14:52 ` [PATCH v2 37/39] x86/ibt: Finish --ibt-fix-direct on module loading Peter Zijlstra
2022-02-24 14:52 ` [PATCH v2 38/39] x86/ibt: Ensure module init/exit points have references Peter Zijlstra
2022-02-24 14:52 ` [PATCH v2 39/39] x86/alternative: Use .ibt_endbr_sites to seal indirect calls Peter Zijlstra
2022-02-24 20:26 ` [PATCH v2 00/39] x86: Kernel IBT Josh Poimboeuf
2022-02-25 15:28 ` Peter Zijlstra [this message]
2022-02-25 15:43 ` Peter Zijlstra
2022-02-25 17:26 ` Josh Poimboeuf
2022-02-25 17:32 ` Steven Rostedt
2022-02-25 19:53 ` Peter Zijlstra
2022-02-25 20:15 ` Josh Poimboeuf
2022-03-01 23:10 ` Josh Poimboeuf
2022-03-02 10:20 ` Peter Zijlstra
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=Yhj1oFcTl2RnghBz@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=alexei.starovoitov@gmail.com \
--cc=alyssa.milburn@intel.com \
--cc=andrew.cooper3@citrix.com \
--cc=hjl.tools@gmail.com \
--cc=joao@overdrivepizza.com \
--cc=jpoimboe@redhat.com \
--cc=keescook@chromium.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=mbenes@suse.cz \
--cc=mhiramat@kernel.org \
--cc=ndesaulniers@google.com \
--cc=rostedt@goodmis.org \
--cc=samitolvanen@google.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).