public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: x86@kernel.org, jpoimboe@redhat.com, andrew.cooper3@citrix.com
Cc: linux-kernel@vger.kernel.org, peterz@infradead.org,
	alexei.starovoitov@gmail.com, ndesaulniers@google.com
Subject: [PATCH 6/9] x86/alternative: Try inline spectre_v2=retpoline,amd
Date: Wed, 13 Oct 2021 14:22:23 +0200	[thread overview]
Message-ID: <20211013123645.245747489@infradead.org> (raw)
In-Reply-To: 20211013122217.304265366@infradead.org

Try and replace retpoline thunk calls with:

  lfence
  call    *%\reg

for spectre_v2=retpoline,amd.

Specifically, the sequence above is 5 bytes for the low 8 registers,
but 6 bytes for the high 8 registers. This means that unless the
compilers prefix stuff the call with higher registers this replacement
will fail.

Luckily GCC strongly favours RAX for the indirect calls and most (95%+
for defconfig-x86_64) will be converted. OTOH clang strongly favours
R11 and almost nothing gets converted.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/kernel/alternative.c |   24 +++++++++++++++++++-----
 1 file changed, 19 insertions(+), 5 deletions(-)

--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -389,15 +389,13 @@ static int emit_indirect(int op, int reg
  *
  *   CALL *%\reg
  *
+ * It also tries to inline spectre_v2=retpoline,amd when size permits.
  */
 static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 {
+	u8 cc, op = insn->opcode.bytes[0];
 	void (*target)(void);
 	int reg, ret, i = 0;
-	u8 op, cc;
-
-	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE))
-		return -1;
 
 	target = addr + insn->length + insn->immediate.value;
 	reg = (target - &__x86_indirect_thunk_rax) /
@@ -406,7 +404,22 @@ static int patch_retpoline(void *addr, s
 	if (WARN_ON_ONCE(reg & ~0xf))
 		return -1;
 
-	op = insn->opcode.bytes[0];
+	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) {
+		/*
+		 * Can't do nothing about the Jcc case here.
+		 */
+		if (op != JMP32_INSN_OPCODE && op != CALL_INSN_OPCODE)
+			return -1;
+
+		bytes[i++] = 0x0f;
+		bytes[i++] = 0xae;
+		bytes[i++] = 0xe8; /* lfence */
+
+		goto indirect;
+	}
+
+	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE))
+		return -1;
 
 	/*
 	 * Convert:
@@ -430,6 +443,7 @@ static int patch_retpoline(void *addr, s
 		op = JMP32_INSN_OPCODE;
 	}
 
+indirect:
 	ret = emit_indirect(op, reg, bytes + i);
 	if (ret < 0)
 		return ret;



  parent reply	other threads:[~2021-10-13 12:40 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-13 12:22 [PATCH 0/9] x86: Rewrite the retpoline rewrite logic Peter Zijlstra
2021-10-13 12:22 ` [PATCH 1/9] objtool,x86: Replace alternatives with .retpoline_sites Peter Zijlstra
2021-10-13 13:29   ` Borislav Petkov
2021-10-13 20:11   ` Josh Poimboeuf
2021-10-14 15:43     ` Peter Zijlstra
2021-10-13 12:22 ` [PATCH 2/9] x86/retpoline: Remove unused replacement symbols Peter Zijlstra
2021-10-13 12:22 ` [PATCH 3/9] x86/asm: Fix register order Peter Zijlstra
2021-10-13 20:15   ` Josh Poimboeuf
2021-10-13 12:22 ` [PATCH 4/9] x86/alternative: Implement .retpoline_sites support Peter Zijlstra
2021-10-13 14:38   ` Andrew Cooper
2021-10-13 15:12     ` Peter Zijlstra
2021-10-13 17:11       ` Andrew Cooper
2021-10-14 10:05       ` Peter Zijlstra
2021-10-13 20:39   ` Josh Poimboeuf
2021-10-13 21:20     ` Peter Zijlstra
2021-10-13 21:49       ` Josh Poimboeuf
2021-10-13 21:52         ` Josh Poimboeuf
2021-10-13 22:10         ` Peter Zijlstra
2021-10-13 22:47           ` Andrew Cooper
2021-10-13 20:52   ` Josh Poimboeuf
2021-10-13 21:00     ` Peter Zijlstra
2021-10-19 11:37     ` Peter Zijlstra
2021-10-19 16:46       ` Josh Poimboeuf
2021-10-19 16:49         ` Josh Poimboeuf
2021-10-20  8:25           ` Peter Zijlstra
2021-10-20  8:30           ` Peter Zijlstra
2021-10-13 21:11   ` Josh Poimboeuf
2021-10-13 21:43     ` Peter Zijlstra
2021-10-13 22:05       ` Josh Poimboeuf
2021-10-13 22:14         ` Peter Zijlstra
2021-10-15 14:24   ` Borislav Petkov
2021-10-15 16:56     ` Peter Zijlstra
2021-10-18 23:06       ` Alexander Lobakin
2021-10-19  0:25         ` Alexander Lobakin
2021-10-19  9:47           ` Alexander Lobakin
2021-10-19 10:16             ` Peter Zijlstra
2021-10-19 15:37               ` Sami Tolvanen
2021-10-19 18:00                 ` Alexander Lobakin
2021-10-19  9:40         ` Peter Zijlstra
2021-10-19 10:02           ` Peter Zijlstra
2021-10-13 12:22 ` [PATCH 5/9] x86/alternative: Handle Jcc __x86_indirect_thunk_\reg Peter Zijlstra
2021-10-13 20:11   ` Nick Desaulniers
2021-10-13 21:08     ` Peter Zijlstra
2021-10-13 12:22 ` Peter Zijlstra [this message]
2021-10-13 12:22 ` [PATCH 7/9] x86/alternative: Add debug prints to apply_retpolines() Peter Zijlstra
2021-10-13 12:22 ` [PATCH 8/9] x86,bugs: Unconditionally allow spectre_v2=retpoline,amd Peter Zijlstra
2021-10-13 12:22 ` [PATCH 9/9] bpf,x86: Respect X86_FEATURE_RETPOLINE* Peter Zijlstra
2021-10-13 21:06   ` Josh Poimboeuf
2021-10-13 21:54     ` Peter Zijlstra
2021-10-14  9:46       ` Peter Zijlstra
2021-10-14  9:48         ` Peter Zijlstra
2021-10-20  7:34         ` 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=20211013123645.245747489@infradead.org \
    --to=peterz@infradead.org \
    --cc=alexei.starovoitov@gmail.com \
    --cc=andrew.cooper3@citrix.com \
    --cc=jpoimboe@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ndesaulniers@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