15 files changed, 89 insertions, 156 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 4bf9e77f3e05..f4fb8f5b0be4 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -304,7 +304,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 	int cpu = smp_processor_id();
 
 	/* get information required for multi-node processors */
-	if (cpu_has_topoext) {
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
 		u32 eax, ebx, ecx, edx;
 
 		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
@@ -954,7 +954,7 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 
 void set_dr_addr_mask(unsigned long mask, int dr)
 {
-	if (!cpu_has_bpext)
+	if (!boot_cpu_has(X86_FEATURE_BPEXT))
 		return;
 
 	switch (dr) {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8eabbafff213..0498ad3702f5 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1539,7 +1539,9 @@ void cpu_init(void)
 
 	printk(KERN_INFO "Initializing CPU#%d\n", cpu);
 
-	if (cpu_feature_enabled(X86_FEATURE_VME) || cpu_has_tsc || cpu_has_de)
+	if (cpu_feature_enabled(X86_FEATURE_VME) ||
+	    cpu_has_tsc ||
+	    boot_cpu_has(X86_FEATURE_DE))
 		cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
 
 	load_current_idt();
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 209ac1e7d1f0..565648bc1a0a 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -445,7 +445,8 @@ static void init_intel(struct cpuinfo_x86 *c)
 
 	if (cpu_has_xmm2)
 		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
-	if (cpu_has_ds) {
+
+	if (boot_cpu_has(X86_FEATURE_DS)) {
 		unsigned int l1;
 		rdmsr(MSR_IA32_MISC_ENABLE, l1, l2);
 		if (!(l1 & (1<<11)))
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index b4ca91cf55b0..3fa72317ad78 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -591,7 +591,7 @@ cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf)
 	unsigned		edx;
 
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
-		if (cpu_has_topoext)
+		if (boot_cpu_has(X86_FEATURE_TOPOEXT))
 			cpuid_count(0x8000001d, index, &eax.full,
 				    &ebx.full, &ecx.full, &edx);
 		else
@@ -637,7 +637,7 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c)
 void init_amd_cacheinfo(struct cpuinfo_x86 *c)
 {
 
-	if (cpu_has_topoext) {
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
 		num_cache_leaves = find_num_cache_leaves(c);
 	} else if (c->extended_cpuid_level >= 0x80000006) {
 		if (cpuid_edx(0x80000006) & 0xf000)
@@ -809,7 +809,7 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
 	struct cacheinfo *this_leaf;
 	int i, sibling;
 
-	if (cpu_has_topoext) {
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
 		unsigned int apicid, nshared, first, last;
 
 		this_leaf = this_cpu_ci->info_list + index;
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index b5624fafa44a..136ae86f4f5f 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -349,7 +349,7 @@ static void get_fixed_ranges(mtrr_type *frs)
 
 void mtrr_save_fixed_ranges(void *info)
 {
-	if (cpu_has_mtrr)
+	if (boot_cpu_has(X86_FEATURE_MTRR))
 		get_fixed_ranges(mtrr_state.fixed_ranges);
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index fa77ac8291f0..f924f41af89a 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -682,7 +682,7 @@ void __init mtrr_bp_init(void)
 
 	phys_addr = 32;
 
-	if (cpu_has_mtrr) {
+	if (boot_cpu_has(X86_FEATURE_MTRR)) {
 		mtrr_if = &generic_mtrr_ops;
 		size_or_mask = SIZE_OR_MASK_BITS(36);
 		size_and_mask = 0x00f00000;
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 1cee5d2d7ece..3ea177cb7366 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -160,7 +160,7 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel)
 	if (offset)
 		return offset;
 
-	if (!cpu_has_perfctr_core)
+	if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
 		offset = index;
 	else
 		offset = index << 1;
@@ -652,7 +652,7 @@ static __initconst const struct x86_pmu amd_pmu = {
 
 static int __init amd_core_pmu_init(void)
 {
-	if (!cpu_has_perfctr_core)
+	if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
 		return 0;
 
 	switch (boot_cpu_data.x86) {
diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
index cc6cedb8f25d..49742746a6c9 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
@@ -523,10 +523,10 @@ static int __init amd_uncore_init(void)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
 		goto fail_nodev;
 
-	if (!cpu_has_topoext)
+	if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
 		goto fail_nodev;
 
-	if (cpu_has_perfctr_nb) {
+	if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) {
 		amd_uncore_nb = alloc_percpu(struct amd_uncore *);
 		if (!amd_uncore_nb) {
 			ret = -ENOMEM;
@@ -540,7 +540,7 @@ static int __init amd_uncore_init(void)
 		ret = 0;
 	}
 
-	if (cpu_has_perfctr_l2) {
+	if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) {
 		amd_uncore_l2 = alloc_percpu(struct amd_uncore *);
 		if (!amd_uncore_l2) {
 			ret = -ENOMEM;
@@ -583,10 +583,11 @@ fail_online:
 
 	/* amd_uncore_nb/l2 should have been freed by cleanup_cpu_online */
 	amd_uncore_nb = amd_uncore_l2 = NULL;
-	if (cpu_has_perfctr_l2)
+
+	if (boot_cpu_has(X86_FEATURE_PERFCTR_L2))
 		perf_pmu_unregister(&amd_l2_pmu);
 fail_l2:
-	if (cpu_has_perfctr_nb)
+	if (boot_cpu_has(X86_FEATURE_PERFCTR_NB))
 		perf_pmu_unregister(&amd_nb_pmu);
 	if (amd_uncore_l2)
 		free_percpu(amd_uncore_l2);
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index d25097c3fc1d..6aa0b519c851 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -114,6 +114,10 @@ void __kernel_fpu_begin(void)
 	kernel_fpu_disable();
 
 	if (fpu->fpregs_active) {
+		/*
+		 * Ignore return value -- we don't care if reg state
+		 * is clobbered.
+		 */
 		copy_fpregs_to_fpstate(fpu);
 	} else {
 		this_cpu_write(fpu_fpregs_owner_ctx, NULL);
@@ -189,8 +193,12 @@ void fpu__save(struct fpu *fpu)
 
 	preempt_disable();
 	if (fpu->fpregs_active) {
-		if (!copy_fpregs_to_fpstate(fpu))
-			fpregs_deactivate(fpu);
+		if (!copy_fpregs_to_fpstate(fpu)) {
+			if (use_eager_fpu())
+				copy_kernel_to_fpregs(&fpu->state);
+			else
+				fpregs_deactivate(fpu);
+		}
 	}
 	preempt_enable();
 }
@@ -259,7 +267,11 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	preempt_disable();
 	if (!copy_fpregs_to_fpstate(dst_fpu)) {
 		memcpy(&src_fpu->state, &dst_fpu->state, xstate_size);
-		fpregs_deactivate(src_fpu);
+
+		if (use_eager_fpu())
+			copy_kernel_to_fpregs(&src_fpu->state);
+		else
+			fpregs_deactivate(src_fpu);
 	}
 	preempt_enable();
 }
@@ -409,8 +421,10 @@ static inline void copy_init_fpstate_to_fpregs(void)
 {
 	if (use_xsave())
 		copy_kernel_to_xregs(&init_fpstate.xsave, -1);
-	else
+	else if (static_cpu_has(X86_FEATURE_FXSR))
 		copy_kernel_to_fxregs(&init_fpstate.fxsave);
+	else
+		copy_kernel_to_fregs(&init_fpstate.fsave);
 }
 
 /*
@@ -423,7 +437,7 @@ void fpu__clear(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
 
-	if (!use_eager_fpu()) {
+	if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) {
 		/* FPU state will be reallocated lazily at the first use. */
 		fpu__drop(fpu);
 	} else {
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 1011c05b1bd5..954517285fa2 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -3,8 +3,11 @@
  */
 #include <asm/fpu/internal.h>
 #include <asm/tlbflush.h>
+#include <asm/setup.h>
+#include <asm/cmdline.h>
 
 #include <linux/sched.h>
+#include <linux/init.h>
 
 /*
  * Initialize the TS bit in CR0 according to the style of context-switches
@@ -12,10 +15,7 @@
  */
 static void fpu__init_cpu_ctx_switch(void)
 {
-	if (!cpu_has_eager_fpu)
-		stts();
-	else
-		clts();
+	clts();
 }
 
 /*
@@ -75,13 +75,15 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
 	cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
 	write_cr0(cr0);
 
-	asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
-		     : "+m" (fsw), "+m" (fcw));
+	if (!test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
+		asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
+			     : "+m" (fsw), "+m" (fcw));
 
-	if (fsw == 0 && (fcw & 0x103f) == 0x003f)
-		set_cpu_cap(c, X86_FEATURE_FPU);
-	else
-		clear_cpu_cap(c, X86_FEATURE_FPU);
+		if (fsw == 0 && (fcw & 0x103f) == 0x003f)
+			set_cpu_cap(c, X86_FEATURE_FPU);
+		else
+			clear_cpu_cap(c, X86_FEATURE_FPU);
+	}
 
 #ifndef CONFIG_MATH_EMULATION
 	if (!cpu_has_fpu) {
@@ -130,7 +132,7 @@ static void __init fpu__init_system_generic(void)
 	 * Set up the legacy init FPU context. (xstate init might overwrite this
 	 * with a more modern format, if the CPU supports it.)
 	 */
-	fpstate_init_fxstate(&init_fpstate.fxsave);
+	fpstate_init(&init_fpstate);
 
 	fpu__init_system_mxcsr();
 }
@@ -230,53 +232,16 @@ static void __init fpu__init_system_xstate_size_legacy(void)
 }
 
 /*
- * FPU context switching strategies:
- *
- * Against popular belief, we don't do lazy FPU saves, due to the
- * task migration complications it brings on SMP - we only do
- * lazy FPU restores.
- *
- * 'lazy' is the traditional strategy, which is based on setting
- * CR0::TS to 1 during context-switch (instead of doing a full
- * restore of the FPU state), which causes the first FPU instruction
- * after the context switch (whenever it is executed) to fault - at
- * which point we lazily restore the FPU state into FPU registers.
- *
- * Tasks are of course under no obligation to execute FPU instructions,
- * so it can easily happen that another context-switch occurs without
- * a single FPU instruction being executed. If we eventually switch
- * back to the original task (that still owns the FPU) then we have
- * not only saved the restores along the way, but we also have the
- * FPU ready to be used for the original task.
- *
- * 'eager' switching is used on modern CPUs, there we switch the FPU
- * state during every context switch, regardless of whether the task
- * has used FPU instructions in that time slice or not. This is done
- * because modern FPU context saving instructions are able to optimize
- * state saving and restoration in hardware: they can detect both
- * unused and untouched FPU state and optimize accordingly.
- *
- * [ Note that even in 'lazy' mode we might optimize context switches
- *   to use 'eager' restores, if we detect that a task is using the FPU
- *   frequently. See the fpu->counter logic in fpu/internal.h for that. ]
+ * Find supported xfeatures based on cpu features and command-line input.
+ * This must be called after fpu__init_parse_early_param() is called and
+ * xfeatures_mask is enumerated.
  */
-static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
-
-static int __init eager_fpu_setup(char *s)
+u64 __init fpu__get_supported_xfeatures_mask(void)
 {
-	if (!strcmp(s, "on"))
-		eagerfpu = ENABLE;
-	else if (!strcmp(s, "off"))
-		eagerfpu = DISABLE;
-	else if (!strcmp(s, "auto"))
-		eagerfpu = AUTO;
-	return 1;
+	return XCNTXT_MASK;
 }
-__setup("eagerfpu=", eager_fpu_setup);
 
-/*
- * Pick the FPU context switching strategy:
- */
+/* Legacy code to initialize eager fpu mode. */
 static void __init fpu__init_system_ctx_switch(void)
 {
 	static bool on_boot_cpu = 1;
@@ -286,25 +251,31 @@ static void __init fpu__init_system_ctx_switch(void)
 
 	WARN_ON_FPU(current->thread.fpu.fpstate_active);
 	current_thread_info()->status = 0;
+}
 
-	/* Auto enable eagerfpu for xsaveopt */
-	if (cpu_has_xsaveopt && eagerfpu != DISABLE)
-		eagerfpu = ENABLE;
-
-	if (xfeatures_mask & XFEATURE_MASK_EAGER) {
-		if (eagerfpu == DISABLE) {
-			pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n",
-			       xfeatures_mask & XFEATURE_MASK_EAGER);
-			xfeatures_mask &= ~XFEATURE_MASK_EAGER;
-		} else {
-			eagerfpu = ENABLE;
-		}
+/*
+ * We parse fpu parameters early because fpu__init_system() is executed
+ * before parse_early_param().
+ */
+static void __init fpu__init_parse_early_param(void)
+{
+	if (cmdline_find_option_bool(boot_command_line, "no387"))
+		setup_clear_cpu_cap(X86_FEATURE_FPU);
+
+	if (cmdline_find_option_bool(boot_command_line, "nofxsr")) {
+		setup_clear_cpu_cap(X86_FEATURE_FXSR);
+		setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT);
+		setup_clear_cpu_cap(X86_FEATURE_XMM);
 	}
 
-	if (eagerfpu == ENABLE)
-		setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
+	if (cmdline_find_option_bool(boot_command_line, "noxsave"))
+		fpu__xstate_clear_all_cpu_caps();
+
+	if (cmdline_find_option_bool(boot_command_line, "noxsaveopt"))
+		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
 
-	printk(KERN_INFO "x86/fpu: Using '%s' FPU context switches.\n", eagerfpu == ENABLE ? "eager" : "lazy");
+	if (cmdline_find_option_bool(boot_command_line, "noxsaves"))
+		setup_clear_cpu_cap(X86_FEATURE_XSAVES);
 }
 
 /*
@@ -313,6 +284,7 @@ static void __init fpu__init_system_ctx_switch(void)
  */
 void __init fpu__init_system(struct cpuinfo_x86 *c)
 {
+	fpu__init_parse_early_param();
 	fpu__init_system_early_generic(c);
 
 	/*
@@ -336,62 +308,3 @@ void __init fpu__init_system(struct cpuinfo_x86 *c)
 
 	fpu__init_system_ctx_switch();
 }
-
-/*
- * Boot parameter to turn off FPU support and fall back to math-emu:
- */
-static int __init no_387(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_FPU);
-	return 1;
-}
-__setup("no387", no_387);
-
-/*
- * Disable all xstate CPU features:
- */
-static int __init x86_noxsave_setup(char *s)
-{
-	if (strlen(s))
-		return 0;
-
-	fpu__xstate_clear_all_cpu_caps();
-
-	return 1;
-}
-__setup("noxsave", x86_noxsave_setup);
-
-/*
- * Disable the XSAVEOPT instruction specifically:
- */
-static int __init x86_noxsaveopt_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-
-	return 1;
-}
-__setup("noxsaveopt", x86_noxsaveopt_setup);
-
-/*
- * Disable the XSAVES instruction:
- */
-static int __init x86_noxsaves_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
-
-	return 1;
-}
-__setup("noxsaves", x86_noxsaves_setup);
-
-/*
- * Disable FX save/restore and SSE support:
- */
-static int __init x86_nofxsr_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_FXSR);
-	setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT);
-	setup_clear_cpu_cap(X86_FEATURE_XMM);
-
-	return 1;
-}
-__setup("nofxsr", x86_nofxsr_setup);
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 70fc312221fc..3fa200ecca62 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -632,8 +632,7 @@ void __init fpu__init_system_xstate(void)
 		BUG();
 	}
 
-	/* Support only the state known to the OS: */
-	xfeatures_mask = xfeatures_mask & XCNTXT_MASK;
+	xfeatures_mask &= fpu__get_supported_xfeatures_mask();
 
 	/* Enable xstate instructions to be able to continue with initialization: */
 	fpu__init_cpu_xstate();
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 50a3fad5b89f..2bcfb5f2bc44 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -300,6 +300,10 @@ static int arch_build_bp_info(struct perf_event *bp)
 			return -EINVAL;
 		if (bp->attr.bp_addr & (bp->attr.bp_len - 1))
 			return -EINVAL;
+
+		if (!boot_cpu_has(X86_FEATURE_BPEXT))
+			return -EOPNOTSUPP;
+
 		/*
 		 * It's impossible to use a range breakpoint to fake out
 		 * user vs kernel detection because bp_len - 1 can't
@@ -307,8 +311,6 @@ static int arch_build_bp_info(struct perf_event *bp)
 		 * breakpoints, then we'll have to check for kprobe-blacklisted
 		 * addresses anywhere in the range.
 		 */
-		if (!cpu_has_bpext)
-			return -EOPNOTSUPP;
 		info->mask = bp->attr.bp_len - 1;
 		info->len = X86_BREAKPOINT_LEN_1;
 	}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 48ca93242bfd..1f7aefc7b0b4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -295,7 +295,7 @@ do {									\
 
 static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
-	if (cpu_has_topoext) {
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
 		int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
 
 		if (c->phys_proc_id == o->phys_proc_id &&
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 1fbd2631be60..8c73bf1492b8 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -751,7 +751,6 @@ dotraplinkage void
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
-	BUG_ON(use_eager_fpu());
 
 #ifdef CONFIG_MATH_EMULATION
 	if (read_cr0() & X86_CR0_EM) {
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index af57736a0309..d6d64a519559 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -357,8 +357,10 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 	tss = &per_cpu(cpu_tss, get_cpu());
 	/* make room for real-mode segments */
 	tsk->thread.sp0 += 16;
-	if (cpu_has_sep)
+
+	if (static_cpu_has_safe(X86_FEATURE_SEP))
 		tsk->thread.sysenter_cs = 0;
+
 	load_sp0(tss, &tsk->thread);
 	put_cpu();