Merge branch 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 FPU changes from Ingo Molnar:
 "There are two bigger changes in this tree:

   - Add an [early-use-]safe static_cpu_has() variant and other
     robustness improvements, including the new X86_DEBUG_STATIC_CPU_HAS
     configurable debugging facility, motivated by recent obscure FPU
     code bugs, by Borislav Petkov

   - Reimplement FPU detection code in C and drop the old asm code, by
     Peter Anvin."

* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, fpu: Use static_cpu_has_safe before alternatives
  x86: Add a static_cpu_has_safe variant
  x86: Sanity-check static_cpu_has usage
  x86, cpu: Add a synthetic, always true, cpu feature
  x86: Get rid of ->hard_math and all the FPU asm fu

3 files changed, 117 insertions, 8 deletions

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e99ac27f95b2..47538a61c91b 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -92,7 +92,7 @@
 #define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */
 #define X86_FEATURE_11AP	(3*32+19) /* "" Bad local APIC aka 11AP */
 #define X86_FEATURE_NOPL	(3*32+20) /* The NOPL (0F 1F) instructions */
-					  /* 21 available, was AMD_C1E */
+#define X86_FEATURE_ALWAYS	(3*32+21) /* "" Always-present feature */
 #define X86_FEATURE_XTOPOLOGY	(3*32+22) /* cpu topology enum extensions */
 #define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
 #define X86_FEATURE_NONSTOP_TSC	(3*32+24) /* TSC does not stop in C states */
@@ -356,15 +356,36 @@ extern const char * const x86_power_flags[32];
 #endif /* CONFIG_X86_64 */
 
 #if __GNUC__ >= 4
+extern void warn_pre_alternatives(void);
+extern bool __static_cpu_has_safe(u16 bit);
+
 /*
  * Static testing of CPU features.  Used the same as boot_cpu_has().
  * These are only valid after alternatives have run, but will statically
  * patch the target code for additional performance.
- *
  */
 static __always_inline __pure bool __static_cpu_has(u16 bit)
 {
 #if __GNUC__ > 4 || __GNUC_MINOR__ >= 5
+
+#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS
+		/*
+		 * Catch too early usage of this before alternatives
+		 * have run.
+		 */
+		asm goto("1: jmp %l[t_warn]\n"
+			 "2:\n"
+			 ".section .altinstructions,\"a\"\n"
+			 " .long 1b - .\n"
+			 " .long 0\n"		/* no replacement */
+			 " .word %P0\n"		/* 1: do replace */
+			 " .byte 2b - 1b\n"	/* source len */
+			 " .byte 0\n"		/* replacement len */
+			 ".previous\n"
+			 /* skipping size check since replacement size = 0 */
+			 : : "i" (X86_FEATURE_ALWAYS) : : t_warn);
+#endif
+
 		asm goto("1: jmp %l[t_no]\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
@@ -379,7 +400,13 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 		return true;
 	t_no:
 		return false;
-#else
+
+#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS
+	t_warn:
+		warn_pre_alternatives();
+		return false;
+#endif
+#else /* GCC_VERSION >= 40500 */
 		u8 flag;
 		/* Open-coded due to __stringify() in ALTERNATIVE() */
 		asm volatile("1: movb $0,%0\n"
@@ -411,11 +438,94 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 		__static_cpu_has(bit) :				\
 		boot_cpu_has(bit)				\
 )
+
+static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
+{
+#if __GNUC__ > 4 || __GNUC_MINOR__ >= 5
+/*
+ * We need to spell the jumps to the compiler because, depending on the offset,
+ * the replacement jump can be bigger than the original jump, and this we cannot
+ * 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"
+			 "2:\n"
+			 ".section .altinstructions,\"a\"\n"
+			 " .long 1b - .\n"		/* src offset */
+			 " .long 3f - .\n"		/* repl offset */
+			 " .word %P1\n"			/* always replace */
+			 " .byte 2b - 1b\n"		/* src len */
+			 " .byte 4f - 3f\n"		/* repl len */
+			 ".previous\n"
+			 ".section .altinstr_replacement,\"ax\"\n"
+			 "3: .byte 0xe9\n .long %l[t_no] - 2b\n"
+			 "4:\n"
+			 ".previous\n"
+			 ".section .altinstructions,\"a\"\n"
+			 " .long 1b - .\n"		/* src offset */
+			 " .long 0\n"			/* no replacement */
+			 " .word %P0\n"			/* feature bit */
+			 " .byte 2b - 1b\n"		/* src len */
+			 " .byte 0\n"			/* repl len */
+			 ".previous\n"
+			 : : "i" (bit), "i" (X86_FEATURE_ALWAYS)
+			 : : t_dynamic, t_no);
+		return true;
+	t_no:
+		return false;
+	t_dynamic:
+		return __static_cpu_has_safe(bit);
+#else /* GCC_VERSION >= 40500 */
+		u8 flag;
+		/* Open-coded due to __stringify() in ALTERNATIVE() */
+		asm volatile("1: movb $2,%0\n"
+			     "2:\n"
+			     ".section .altinstructions,\"a\"\n"
+			     " .long 1b - .\n"		/* src offset */
+			     " .long 3f - .\n"		/* repl offset */
+			     " .word %P2\n"		/* always replace */
+			     " .byte 2b - 1b\n"		/* source len */
+			     " .byte 4f - 3f\n"		/* replacement len */
+			     ".previous\n"
+			     ".section .discard,\"aw\",@progbits\n"
+			     " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */
+			     ".previous\n"
+			     ".section .altinstr_replacement,\"ax\"\n"
+			     "3: movb $0,%0\n"
+			     "4:\n"
+			     ".previous\n"
+			     ".section .altinstructions,\"a\"\n"
+			     " .long 1b - .\n"		/* src offset */
+			     " .long 5f - .\n"		/* repl offset */
+			     " .word %P1\n"		/* feature bit */
+			     " .byte 4b - 3b\n"		/* src len */
+			     " .byte 6f - 5f\n"		/* repl len */
+			     ".previous\n"
+			     ".section .discard,\"aw\",@progbits\n"
+			     " .byte 0xff + (6f-5f) - (4b-3b)\n" /* size check */
+			     ".previous\n"
+			     ".section .altinstr_replacement,\"ax\"\n"
+			     "5: movb $1,%0\n"
+			     "6:\n"
+			     ".previous\n"
+			     : "=qm" (flag)
+			     : "i" (bit), "i" (X86_FEATURE_ALWAYS));
+		return (flag == 2 ? __static_cpu_has_safe(bit) : flag);
+#endif
+}
+
+#define static_cpu_has_safe(bit)				\
+(								\
+	__builtin_constant_p(boot_cpu_has(bit)) ?		\
+		boot_cpu_has(bit) :				\
+		_static_cpu_has_safe(bit)			\
+)
 #else
 /*
  * gcc 3.x is too stupid to do the static test; fall back to dynamic.
  */
-#define static_cpu_has(bit) boot_cpu_has(bit)
+#define static_cpu_has(bit)		boot_cpu_has(bit)
+#define static_cpu_has_safe(bit)	boot_cpu_has(bit)
 #endif
 
 #define cpu_has_bug(c, bit)	cpu_has(c, (bit))
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index e25cc33ec54d..4d0bda7b11e3 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -62,10 +62,8 @@ extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
 #define xstateregs_active	fpregs_active
 
 #ifdef CONFIG_MATH_EMULATION
-# define HAVE_HWFP		(boot_cpu_data.hard_math)
 extern void finit_soft_fpu(struct i387_soft_struct *soft);
 #else
-# define HAVE_HWFP		1
 static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
 #endif
 
@@ -345,7 +343,7 @@ static inline void __thread_fpu_end(struct task_struct *tsk)
 
 static inline void __thread_fpu_begin(struct task_struct *tsk)
 {
-	if (!use_eager_fpu())
+	if (!static_cpu_has_safe(X86_FEATURE_EAGER_FPU))
 		clts();
 	__thread_set_has_fpu(tsk);
 }
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 5b87d52eed0b..29937c4f6ff8 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -89,9 +89,9 @@ struct cpuinfo_x86 {
 	char			wp_works_ok;	/* It doesn't on 386's */
 
 	/* Problems on some 486Dx4's and old 386's: */
-	char			hard_math;
 	char			rfu;
 	char			pad0;
+	char			pad1;
 #else
 	/* Number of 4K pages in DTLB/ITLB combined(in pages): */
 	int			x86_tlbsize;
@@ -164,6 +164,7 @@ extern const struct seq_operations cpuinfo_op;
 #define cache_line_size()	(boot_cpu_data.x86_cache_alignment)
 
 extern void cpu_detect(struct cpuinfo_x86 *c);
+extern void __cpuinit fpu_detect(struct cpuinfo_x86 *c);
 
 extern void early_cpu_init(void);
 extern void identify_boot_cpu(void);