summaryrefslogtreecommitdiff
blob: 62de15ae66fcfacc03d292bc8e7fb1788b02930d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
From 00aa5c93d14c6561a69fe204cbe29f7519830782 Mon Sep 17 00:00:00 2001
From: Andrew Cooper <andrew.cooper3@citrix.com>
Date: Fri, 31 Mar 2023 08:31:20 +0200
Subject: [PATCH 78/89] x86/nospec: Fix evaluate_nospec() code generation under
 Clang
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It turns out that evaluate_nospec() code generation is not safe under Clang.
Given:

  void eval_nospec_test(int x)
  {
      if ( evaluate_nospec(x) )
          asm volatile ("nop #true" ::: "memory");
      else
          asm volatile ("nop #false" ::: "memory");
  }

Clang emits:

  <eval_nospec_test>:
         0f ae e8                lfence
         85 ff                   test   %edi,%edi
         74 02                   je     <eval_nospec_test+0x9>
         90                      nop
         c3                      ret
         90                      nop
         c3                      ret

which is not safe because the lfence has been hoisted above the conditional
jump.  Clang concludes that both barrier_nospec_true()'s have identical side
effects and can safely be merged.

Clang can be persuaded that the side effects are different if there are
different comments in the asm blocks.  This is fragile, but no more fragile
that other aspects of this construct.

Introduce barrier_nospec_false() with a separate internal comment to prevent
Clang merging it with barrier_nospec_true() despite the otherwise-identical
content.  The generated code now becomes:

  <eval_nospec_test>:
         85 ff                   test   %edi,%edi
         74 05                   je     <eval_nospec_test+0x9>
         0f ae e8                lfence
         90                      nop
         c3                      ret
         0f ae e8                lfence
         90                      nop
         c3                      ret

which has the correct number of lfence's, and in the correct place.

Link: https://github.com/llvm/llvm-project/issues/55084
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
master commit: bc3c133841435829ba5c0a48427e2a77633502ab
master date: 2023-03-24 12:16:31 +0000
---
 xen/arch/x86/include/asm/nospec.h | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/xen/arch/x86/include/asm/nospec.h b/xen/arch/x86/include/asm/nospec.h
index 5312ae4c6f..7150e76b87 100644
--- a/xen/arch/x86/include/asm/nospec.h
+++ b/xen/arch/x86/include/asm/nospec.h
@@ -10,15 +10,26 @@
 static always_inline bool barrier_nospec_true(void)
 {
 #ifdef CONFIG_SPECULATIVE_HARDEN_BRANCH
-    alternative("lfence", "", X86_FEATURE_SC_NO_BRANCH_HARDEN);
+    alternative("lfence #nospec-true", "", X86_FEATURE_SC_NO_BRANCH_HARDEN);
 #endif
     return true;
 }
 
+static always_inline bool barrier_nospec_false(void)
+{
+#ifdef CONFIG_SPECULATIVE_HARDEN_BRANCH
+    alternative("lfence #nospec-false", "", X86_FEATURE_SC_NO_BRANCH_HARDEN);
+#endif
+    return false;
+}
+
 /* Allow to protect evaluation of conditionals with respect to speculation */
 static always_inline bool evaluate_nospec(bool condition)
 {
-    return condition ? barrier_nospec_true() : !barrier_nospec_true();
+    if ( condition )
+        return barrier_nospec_true();
+    else
+        return barrier_nospec_false();
 }
 
 /* Allow to block speculative execution in generic code */
-- 
2.40.0