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

Pull x86 fpu updates from Ingo Molnar:
 "The main changes relate to fixes between (lack of) CPUID and FPU
  detection that should only affect old or weird CPUs, by Andy
  Lutomirski"

* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu: Fix the "Giving up, no FPU found" test
  x86/fpu: Fix CPUID-less FPU detection
  x86/fpu: Fix "x86/fpu: Legacy x87 FPU detected" message
  x86/cpu: Re-apply forced caps every time CPU caps are re-read
  x86/cpu: Factor out application of forced CPU caps
  x86/cpu: Add X86_FEATURE_CPUID
  x86/fpu/xstate: Move XSAVES state init to a function

Author: torvalds

arch/x86/include/asm/cpufeatures.h

@@ -100,7 +100,7 @@
 #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 */
-/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */
+#define X86_FEATURE_CPUID	( 3*32+25) /* CPU has CPUID instruction itself */
 #define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
 #define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
 #define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */

arch/x86/include/asm/fpu/internal.h

@@ -87,6 +87,16 @@ extern void fpstate_init_soft(struct swregs_state *soft);
 #else
 static inline void fpstate_init_soft(struct swregs_state *soft) {}
 #endif
+
+static inline void fpstate_init_xstate(struct xregs_state *xsave)
+{
+	/*
+	 * XRSTORS requires these bits set in xcomp_bv, or it will
+	 * trigger #GP:
+	 */
+	xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask;
+}
+
 static inline void fpstate_init_fxstate(struct fxregs_state *fx)
 {
 	fx->cwd = 0x37f;

arch/x86/kernel/cpu/common.c

@@ -659,6 +659,16 @@ void cpu_detect(struct cpuinfo_x86 *c)
 	}
 }
 
+static void apply_forced_caps(struct cpuinfo_x86 *c)
+{
+	int i;
+
+	for (i = 0; i < NCAPINTS; i++) {
+		c->x86_capability[i] &= ~cpu_caps_cleared[i];
+		c->x86_capability[i] |= cpu_caps_set[i];
+	}
+}
+
 void get_cpu_cap(struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
@@ -752,6 +762,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
 
 	init_scattered_cpuid_features(c);
+
+	/*
+	 * Clear/Set all flags overridden by options, after probe.
+	 * This needs to happen each time we re-probe, which may happen
+	 * several times during CPU initialization.
+	 */
+	apply_forced_caps(c);
 }
 
 static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
@@ -805,14 +822,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	memset(&c->x86_capability, 0, sizeof c->x86_capability);
 	c->extended_cpuid_level = 0;
 
-	if (!have_cpuid_p())
-		identify_cpu_without_cpuid(c);
-
 	/* cyrix could have cpuid enabled via c_identify()*/
 	if (have_cpuid_p()) {
 		cpu_detect(c);
 		get_cpu_vendor(c);
 		get_cpu_cap(c);
+		setup_force_cpu_cap(X86_FEATURE_CPUID);
 
 		if (this_cpu->c_early_init)
 			this_cpu->c_early_init(c);
@@ -822,6 +837,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 
 		if (this_cpu->c_bsp_init)
 			this_cpu->c_bsp_init(c);
+	} else {
+		identify_cpu_without_cpuid(c);
+		setup_clear_cpu_cap(X86_FEATURE_CPUID);
 	}
 
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
@@ -1039,10 +1057,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 		this_cpu->c_identify(c);
 
 	/* Clear/Set all flags overridden by options, after probe */
-	for (i = 0; i < NCAPINTS; i++) {
-		c->x86_capability[i] &= ~cpu_caps_cleared[i];
-		c->x86_capability[i] |= cpu_caps_set[i];
-	}
+	apply_forced_caps(c);
 
 #ifdef CONFIG_X86_64
 	c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
@@ -1103,10 +1118,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	 * Clear/Set all flags overridden by options, need do it
 	 * before following smp all cpus cap AND.
 	 */
-	for (i = 0; i < NCAPINTS; i++) {
-		c->x86_capability[i] &= ~cpu_caps_cleared[i];
-		c->x86_capability[i] |= cpu_caps_set[i];
-	}
+	apply_forced_caps(c);
 
 	/*
 	 * On SMP, boot_cpu_data holds the common feature set between

arch/x86/kernel/fpu/core.c

@@ -9,7 +9,6 @@
 #include <asm/fpu/regset.h>
 #include <asm/fpu/signal.h>
 #include <asm/fpu/types.h>
-#include <asm/fpu/xstate.h>
 #include <asm/traps.h>
 
 #include <linux/hardirq.h>
@@ -179,14 +178,8 @@ void fpstate_init(union fpregs_state *state)
 
 	memset(state, 0, fpu_kernel_xstate_size);
 
-	/*
-	 * XRSTORS requires that this bit is set in xcomp_bv, or
-	 * it will #GP. Make sure it is replaced after the memset().
-	 */
 	if (static_cpu_has(X86_FEATURE_XSAVES))
-		state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT |
-					       xfeatures_mask;
-
+		fpstate_init_xstate(&state->xsave);
 	if (static_cpu_has(X86_FEATURE_FXSR))
 		fpstate_init_fxstate(&state->fxsave);
 	else

arch/x86/kernel/fpu/init.c

@@ -48,13 +48,7 @@ void fpu__init_cpu(void)
 	fpu__init_cpu_xstate();
 }
 
-/*
- * The earliest FPU detection code.
- *
- * Set the X86_FEATURE_FPU CPU-capability bit based on
- * trying to execute an actual sequence of FPU instructions:
- */
-static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
+static bool fpu__probe_without_cpuid(void)
 {
 	unsigned long cr0;
 	u16 fsw, fcw;
@@ -65,18 +59,25 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
 	cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
 	write_cr0(cr0);
 
-	if (!test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
-		asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
-			     : "+m" (fsw), "+m" (fcw));
+	asm volatile("fninit ; fnstsw %0 ; fnstcw %1" : "+m" (fsw), "+m" (fcw));
+
+	pr_info("x86/fpu: Probing for FPU: FSW=0x%04hx FCW=0x%04hx\n", fsw, fcw);
 
-		if (fsw == 0 && (fcw & 0x103f) == 0x003f)
-			set_cpu_cap(c, X86_FEATURE_FPU);
+	return fsw == 0 && (fcw & 0x103f) == 0x003f;
+}
+
+static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
+{
+	if (!boot_cpu_has(X86_FEATURE_CPUID) &&
+	    !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
+		if (fpu__probe_without_cpuid())
+			setup_force_cpu_cap(X86_FEATURE_FPU);
 		else
-			clear_cpu_cap(c, X86_FEATURE_FPU);
+			setup_clear_cpu_cap(X86_FEATURE_FPU);
 	}
 
 #ifndef CONFIG_MATH_EMULATION
-	if (!boot_cpu_has(X86_FEATURE_FPU)) {
+	if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_FPU)) {
 		pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n");
 		for (;;)
 			asm volatile("hlt");

arch/x86/kernel/fpu/xstate.c

@@ -706,8 +706,14 @@ void __init fpu__init_system_xstate(void)
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
 
+	if (!boot_cpu_has(X86_FEATURE_FPU)) {
+		pr_info("x86/fpu: No FPU detected\n");
+		return;
+	}
+
 	if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
-		pr_info("x86/fpu: Legacy x87 FPU detected.\n");
+		pr_info("x86/fpu: x87 FPU will use %s\n",
+			boot_cpu_has(X86_FEATURE_FXSR) ? "FXSAVE" : "FSAVE");
 		return;
 	}