compiler/gcc4: Add quirk for 'asm goto' miscompilation bug

Fengguang Wu, Oleg Nesterov and Peter Zijlstra tracked down
a kernel crash to a GCC bug: GCC miscompiles certain 'asm goto'
constructs, as outlined here:

  http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670

Implement a workaround suggested by Jakub Jelinek.

Reported-and-tested-by: Fengguang Wu <fengguang.wu@intel.com>
Reported-by: Oleg Nesterov <oleg@redhat.com>
Reported-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Suggested-by: Jakub Jelinek <jakub@redhat.com>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: <stable@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index bfc198c759130109d44b73b4506ea853d01fba28..863c892b4aaa7403c3bde97b7de3b2cd9a75519c 100644 (file)
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -16,7 +16,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-       asm goto("1:\n\t"
+       asm_volatile_goto("1:\n\t"
                 JUMP_LABEL_NOP "\n\t"
                 ".pushsection __jump_table,  \"aw\"\n\t"
                 ".word 1b, %l[l_yes], %c0\n\t"

diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index 4d6d77ed9b9d679cd955e2fafe2dbc16527db65c..e194f957ca8c42a0af82f0621c425308a25e4d53 100644 (file)
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -22,7 +22,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-       asm goto("1:\tnop\n\t"
+       asm_volatile_goto("1:\tnop\n\t"
                "nop\n\t"
                ".pushsection __jump_table,  \"aw\"\n\t"
                WORD_INSN " 1b, %l[l_yes], %0\n\t"

diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index ae098c438f009eb0e312fc8b78a6ce07f4311cc6..f016bb699b5f6200268d3b8e5bf4e2bd003dbbf7 100644 (file)
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -19,7 +19,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-       asm goto("1:\n\t"
+       asm_volatile_goto("1:\n\t"
                 "nop\n\t"
                 ".pushsection __jump_table,  \"aw\"\n\t"
                 JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"

diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 6c32190dc73e880255175049fe36965e647101eb..346b1c85ffb40d890078550dc72c2dedcb275a2e 100644 (file)
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -15,7 +15,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-       asm goto("0:    brcl 0,0\n"
+       asm_volatile_goto("0:   brcl 0,0\n"
                ".pushsection __jump_table, \"aw\"\n"
                ASM_ALIGN "\n"
                ASM_PTR " 0b, %l[label], %0\n"

diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index 5080d16a832ffec0c813b30cf546340e5047a7fd..ec2e2e2aba7d8f15419aa12bc6f790993f8c54d4 100644 (file)
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -9,7 +9,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-               asm goto("1:\n\t"
+               asm_volatile_goto("1:\n\t"
                         "nop\n\t"
                         "nop\n\t"
                         ".pushsection __jump_table,  \"aw\"\n\t"

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index d3f5c63078d812e2f6220cfa5ad322aae920827c..89270b4318db8b97ac467717b38863fa549435ad 100644 (file)
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -374,7 +374,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
                 * Catch too early usage of this before alternatives
                 * have run.
                 */
-               asm goto("1: jmp %l[t_warn]\n"
+               asm_volatile_goto("1: jmp %l[t_warn]\n"
                         "2:\n"
                         ".section .altinstructions,\"a\"\n"
                         " .long 1b - .\n"
@@ -388,7 +388,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 
 #endif
 
-               asm goto("1: jmp %l[t_no]\n"
+               asm_volatile_goto("1: jmp %l[t_no]\n"
                         "2:\n"
                         ".section .altinstructions,\"a\"\n"
                         " .long 1b - .\n"
@@ -453,7 +453,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
  * have. Thus, we force the jump to the widest, 4-byte, signed relative
  * offset even though the last would often fit in less bytes.
  */
-               asm goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
+               asm_volatile_goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
                         "2:\n"
                         ".section .altinstructions,\"a\"\n"
                         " .long 1b - .\n"              /* src offset */

diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 64507f35800ce23e9c867e1c80b5dc3d0a835ec1..6a2cefb4395a4228cce550ef8b231f3e7158d9d1 100644 (file)
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -18,7 +18,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-       asm goto("1:"
+       asm_volatile_goto("1:"
                ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
                ".pushsection __jump_table,  \"aw\" \n\t"
                _ASM_ALIGN "\n\t"

diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h
index e7e6751648edf775ad54a42a5c05b3e6d3c1cff5..07537a44216ec9b2eed302183af7c57d8949a5a0 100644 (file)
--- a/arch/x86/include/asm/mutex_64.h
+++ b/arch/x86/include/asm/mutex_64.h
@@ -20,7 +20,7 @@
 static inline void __mutex_fastpath_lock(atomic_t *v,
                                         void (*fail_fn)(atomic_t *))
 {
-       asm volatile goto(LOCK_PREFIX "   decl %0\n"
+       asm_volatile_goto(LOCK_PREFIX "   decl %0\n"
                          "   jns %l[exit]\n"
                          : : "m" (v->counter)
                          : "memory", "cc"
@@ -75,7 +75,7 @@ static inline int __mutex_fastpath_lock_retval(atomic_t *count)
 static inline void __mutex_fastpath_unlock(atomic_t *v,
                                           void (*fail_fn)(atomic_t *))
 {
-       asm volatile goto(LOCK_PREFIX "   incl %0\n"
+       asm_volatile_goto(LOCK_PREFIX "   incl %0\n"
                          "   jg %l[exit]\n"
                          : : "m" (v->counter)
                          : "memory", "cc"

diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h
index 842de225055fc5b8c769c59ff37e5afa81574f38..ded429966c1f447db9106359b174fb742fd3fe54 100644 (file)
--- a/include/linux/compiler-gcc4.h
+++ b/include/linux/compiler-gcc4.h
@@ -65,6 +65,21 @@
 #define __visible __attribute__((externally_visible))
 #endif
 
+/*
+ * GCC 'asm goto' miscompiles certain code sequences:
+ *
+ *   http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+ *
+ * Work it around via a compiler barrier quirk suggested by Jakub Jelinek.
+ * Fixed in GCC 4.8.2 and later versions.
+ *
+ * (asm goto is automatically volatile - the naming reflects this.)
+ */
+#if GCC_VERSION <= 40801
+# define asm_volatile_goto(x...)       do { asm goto(x); asm (""); } while (0)
+#else
+# define asm_volatile_goto(x...)       do { asm goto(x); } while (0)
+#endif
 
 #ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
 #if GCC_VERSION >= 40400