From: Peter Zijlstra <peterz@infradead.org>
To: seanjc@google.com, pbonzini@redhat.com, jpoimboe@redhat.com,
tglx@linutronix.de
Cc: linux-kernel@vger.kernel.org, x86@kernel.org,
kvm@vger.kernel.org, jthoughton@google.com,
andrew.cooper3@citrix.com
Subject: Re: [PATCH v2 12/12] x86/kvm/emulate: Avoid RET for fastops
Date: Mon, 11 Nov 2024 17:27:38 +0100 [thread overview]
Message-ID: <20241111162738.GI22801@noisy.programming.kicks-ass.net> (raw)
In-Reply-To: <20241111125219.361243118@infradead.org>
On Mon, Nov 11, 2024 at 12:59:47PM +0100, Peter Zijlstra wrote:
> +/*
> + * All the FASTOP magic above relies on there being *one* instance of this
> + * so it can JMP back, avoiding RET and it's various thunks.
> + */
> +static noinline int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop)
> {
> ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF;
>
> if (!(ctxt->d & ByteOp))
> fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE;
>
> - asm("push %[flags]; popf; " CALL_NOSPEC " ; pushf; pop %[flags]\n"
> + asm("push %[flags]; popf \n\t"
> + UNWIND_HINT(UNWIND_HINT_TYPE_SAVE, 0, 0, 0)
> + ASM_ANNOTATE(ANNOTYPE_JUMP_TABLE)
> + JMP_NOSPEC
> + "fastop_return: \n\t"
> + UNWIND_HINT(UNWIND_HINT_TYPE_RESTORE, 0, 0, 0)
> + "pushf; pop %[flags]\n"
> : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags),
> [thunk_target]"+S"(fop), ASM_CALL_CONSTRAINT
> : "c"(ctxt->src2.val));
Do Andrew is telling me the compiler is free to mess this up... Notably:
https://github.com/llvm/llvm-project/issues/92161
In lieu of that, I wrote the below hack. It makes objtool sad (it don't
like STT_FUNC calling STT_NOTYPE), but it should work if we ever run
into the compiler being daft like that (it should fail to compile
because of the duplicate fastop_return label, so it's not silent
failure).
Wear protective eye gear before continuing...
---
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -429,9 +429,9 @@ static inline void call_depth_return_thu
#ifdef CONFIG_X86_64
-#define __CS_PREFIX \
+#define __CS_PREFIX(reg) \
".irp rs,r8,r9,r10,r11,r12,r13,r14,r15\n" \
- ".ifc %V[thunk_target],\\rs\n" \
+ ".ifc " reg ",\\rs\n" \
".byte 0x2e\n" \
".endif\n" \
".endr\n"
@@ -441,12 +441,12 @@ static inline void call_depth_return_thu
* which is ensured when CONFIG_MITIGATION_RETPOLINE is defined.
*/
# define CALL_NOSPEC \
- __CS_PREFIX \
+ __CS_PREFIX("%V[thunk_target]") \
"call __x86_indirect_thunk_%V[thunk_target]\n"
-# define JMP_NOSPEC \
- __CS_PREFIX \
- "jmp __x86_indirect_thunk_%V[thunk_target]\n"
+# define __JMP_NOSPEC(reg) \
+ __CS_PREFIX(reg) \
+ "jmp __x86_indirect_thunk_" reg "\n"
# define THUNK_TARGET(addr) [thunk_target] "r" (addr)
@@ -478,10 +478,10 @@ static inline void call_depth_return_thu
"call *%[thunk_target]\n", \
X86_FEATURE_RETPOLINE_LFENCE)
-# define JMP_NOSPEC \
+# define __JMP_NOSPEC(reg) \
ALTERNATIVE_2( \
ANNOTATE_RETPOLINE_SAFE \
- "jmp *%[thunk_target]\n", \
+ "jmp *%%" reg "\n", \
" jmp 901f;\n" \
" .align 16\n" \
"901: call 903f;\n" \
@@ -490,22 +490,25 @@ static inline void call_depth_return_thu
" jmp 902b;\n" \
" .align 16\n" \
"903: lea 4(%%esp), %%esp;\n" \
- " pushl %[thunk_target];\n" \
+ " pushl %%" reg "\n" \
" ret;\n", \
X86_FEATURE_RETPOLINE, \
"lfence;\n" \
ANNOTATE_RETPOLINE_SAFE \
- "jmp *%[thunk_target]\n", \
+ "jmp *%%" reg "\n", \
X86_FEATURE_RETPOLINE_LFENCE)
# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
#endif
+
#else /* No retpoline for C / inline asm */
# define CALL_NOSPEC "call *%[thunk_target]\n"
-# define JMP_NOSPEC "jmp *%[thunk_target]\n"
+# define __JMP_NOSPEC(reg) "jmp *%%" reg "\n"
# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
#endif
+# define JMP_NOSPEC __JMP_NOSPEC("%V[thunk_target]")
+
/* The Spectre V2 mitigation variants */
enum spectre_v2_mitigation {
SPECTRE_V2_NONE,
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -5039,23 +5039,45 @@ static void fetch_possible_mmx_operand(s
}
/*
+ * Stub written in asm in order to ensure GCC doesn't duplicate the
+ * fastop_return: label.
+ *
+ * Custom calling convention.
+ *
+ * __fastop:
+ * ax = ctxt->dst.val
+ * dx = ctxt->src.val
+ * cx = ctxt->src.val2
+ * di = flags
+ * si = fop
+ */
+asm (ASM_FUNC_ALIGN
+ "__fastop: \n\t"
+ "push %" _ASM_DI "\n\t"
+ "popf \n\t"
+ UNWIND_HINT(UNWIND_HINT_TYPE_SAVE, 0, 0, 0)
+ ASM_ANNOTATE(ANNOTYPE_JUMP_TABLE)
+ __JMP_NOSPEC(_ASM_SI)
+ "fastop_return: \n\t"
+ UNWIND_HINT(UNWIND_HINT_TYPE_RESTORE, 0, 0, 0)
+ "pushf \n\t"
+ "pop %" _ASM_DI "\n\t"
+ ASM_RET
+ ".type __fastop, @notype \n\t"
+ ".size __fastop, . - __fastop \n\t");
+
+/*
* All the FASTOP magic above relies on there being *one* instance of this
* so it can JMP back, avoiding RET and it's various thunks.
*/
-static noinline int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop)
+static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop)
{
ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF;
if (!(ctxt->d & ByteOp))
fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE;
- asm("push %[flags]; popf \n\t"
- UNWIND_HINT(UNWIND_HINT_TYPE_SAVE, 0, 0, 0)
- ASM_ANNOTATE(ANNOTYPE_JUMP_TABLE)
- JMP_NOSPEC
- "fastop_return: \n\t"
- UNWIND_HINT(UNWIND_HINT_TYPE_RESTORE, 0, 0, 0)
- "pushf; pop %[flags]\n"
+ asm("call __fastop"
: "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags),
[thunk_target]"+S"(fop), ASM_CALL_CONSTRAINT
: "c"(ctxt->src2.val));
next prev parent reply other threads:[~2024-11-11 16:27 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-11 11:59 [PATCH v2 00/12] x86/kvm/emulate: Avoid RET for FASTOPs Peter Zijlstra
2024-11-11 11:59 ` [PATCH v2 01/12] objtool: Generic annotation infrastructure Peter Zijlstra
2024-11-15 18:38 ` Josh Poimboeuf
2024-11-16 9:33 ` Peter Zijlstra
2024-11-20 0:31 ` Josh Poimboeuf
2024-11-20 1:04 ` Josh Poimboeuf
2024-11-20 8:52 ` Peter Zijlstra
2024-11-20 16:03 ` Josh Poimboeuf
2024-11-20 16:03 ` Josh Poimboeuf
2024-11-21 11:46 ` Peter Zijlstra
2024-11-11 11:59 ` [PATCH v2 02/12] objtool: Convert ANNOTATE_NOENDBR to ANNOTATE Peter Zijlstra
2024-11-11 11:59 ` [PATCH v2 03/12] objtool: Convert ANNOTATE_RETPOLINE_SAFE " Peter Zijlstra
2024-11-15 18:39 ` Josh Poimboeuf
2024-11-16 9:34 ` Peter Zijlstra
2024-11-11 11:59 ` [PATCH v2 04/12] objtool: Convert instrumentation_{begin,end}() " Peter Zijlstra
2024-11-15 18:40 ` Josh Poimboeuf
2024-11-16 9:36 ` Peter Zijlstra
2024-11-16 9:51 ` Peter Zijlstra
2024-11-16 10:06 ` Peter Zijlstra
2024-11-11 11:59 ` [PATCH v2 05/12] objtool: Convert VALIDATE_UNRET_BEGIN " Peter Zijlstra
2024-11-11 11:59 ` [PATCH v2 06/12] objtool: Convert ANNOTATE_IGNORE_ALTERNATIVE " Peter Zijlstra
2024-11-11 11:59 ` [PATCH v2 07/12] objtool: Convert ANNOTATE_INTRA_FUNCTION_CALLS " Peter Zijlstra
2024-11-15 18:40 ` Josh Poimboeuf
2024-11-16 9:37 ` Peter Zijlstra
2024-11-11 11:59 ` [PATCH v2 08/12] objtool: Collapse annotate sequences Peter Zijlstra
2024-11-11 11:59 ` [PATCH v2 09/12] x86/nospec: JMP_NOSPEC Peter Zijlstra
2024-11-11 11:59 ` [PATCH v2 10/12] x86,nospec: Simplify {JMP,CALL}_NOSPEC (part 2) Peter Zijlstra
2024-11-15 18:40 ` Josh Poimboeuf
2024-11-16 9:39 ` Peter Zijlstra
2024-11-11 11:59 ` [PATCH v2 11/12] x86/kvm/emulate: Implement test_cc() in C Peter Zijlstra
2024-11-11 17:13 ` Sean Christopherson
2024-11-11 11:59 ` [PATCH v2 12/12] x86/kvm/emulate: Avoid RET for fastops Peter Zijlstra
2024-11-11 16:27 ` Peter Zijlstra [this message]
2024-11-11 17:26 ` Sean Christopherson
2024-11-11 18:28 ` Peter Zijlstra
2024-11-15 18:41 ` Josh Poimboeuf
2024-11-16 9:39 ` Peter Zijlstra
2024-11-11 17:27 ` [PATCH v2 00/12] x86/kvm/emulate: Avoid RET for FASTOPs Sean Christopherson
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=20241111162738.GI22801@noisy.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=andrew.cooper3@citrix.com \
--cc=jpoimboe@redhat.com \
--cc=jthoughton@google.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=seanjc@google.com \
--cc=tglx@linutronix.de \
--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