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

Pull x86 asm updates from Ingo Molnar:
 "The main changes in this cycle were:

   - MSR access API fixes and enhancements (Andy Lutomirski)

   - early exception handling improvements (Andy Lutomirski)

   - user-space FS/GS prctl usage fixes and improvements (Andy
     Lutomirski)

   - Remove the cpu_has_*() APIs and replace them with equivalents
     (Borislav Petkov)

   - task switch micro-optimization (Brian Gerst)

   - 32-bit entry code simplification (Denys Vlasenko)

   - enhance PAT handling in enumated CPUs (Toshi Kani)

  ... and lots of other cleanups/fixlets"

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (70 commits)
  x86/arch_prctl/64: Restore accidentally removed put_cpu() in ARCH_SET_GS
  x86/entry/32: Remove asmlinkage_protect()
  x86/entry/32: Remove GET_THREAD_INFO() from entry code
  x86/entry, sched/x86: Don't save/restore EFLAGS on task switch
  x86/asm/entry/32: Simplify pushes of zeroed pt_regs->REGs
  selftests/x86/ldt_gdt: Test set_thread_area() deletion of an active segment
  x86/tls: Synchronize segment registers in set_thread_area()
  x86/asm/64: Rename thread_struct's fs and gs to fsbase and gsbase
  x86/arch_prctl/64: Remove FSBASE/GSBASE < 4G optimization
  x86/segments/64: When load_gs_index fails, clear the base
  x86/segments/64: When loadsegment(fs, ...) fails, clear the base
  x86/asm: Make asm/alternative.h safe from assembly
  x86/asm: Stop depending on ptrace.h in alternative.h
  x86/entry: Rename is_{ia32,x32}_task() to in_{ia32,x32}_syscall()
  x86/asm: Make sure verify_cpu() has a good stack
  x86/extable: Add a comment about early exception handlers
  x86/msr: Set the return value to zero when native_rdmsr_safe() fails
  x86/paravirt: Make "unsafe" MSR accesses unsafe even if PARAVIRT=y
  x86/paravirt: Add paravirt_{read,write}_msr()
  x86/msr: Carry on after a non-"safe" MSR access fails
  ...

5 files changed, 52 insertions, 73 deletions

diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c
index dd9ca9b60ff3..aad34aafc0e0 100644
--- a/arch/x86/kernel/fpu/bugs.c
+++ b/arch/x86/kernel/fpu/bugs.c
@@ -21,11 +21,15 @@ static double __initdata y = 3145727.0;
  * We should really only care about bugs here
  * anyway. Not features.
  */
-static void __init check_fpu(void)
+void __init fpu__init_check_bugs(void)
 {
 	u32 cr0_saved;
 	s32 fdiv_bug;
 
+	/* kernel_fpu_begin/end() relies on patched alternative instructions. */
+	if (!boot_cpu_has(X86_FEATURE_FPU))
+		return;
+
 	/* We might have CR0::TS set already, clear it: */
 	cr0_saved = read_cr0();
 	write_cr0(cr0_saved & ~X86_CR0_TS);
@@ -59,13 +63,3 @@ static void __init check_fpu(void)
 		pr_warn("Hmm, FPU with FDIV bug\n");
 	}
 }
-
-void __init fpu__init_check_bugs(void)
-{
-	/*
-	 * kernel_fpu_begin/end() in check_fpu() relies on the patched
-	 * alternative instructions.
-	 */
-	if (cpu_has_fpu)
-		check_fpu();
-}
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 8e37cc8a539a..97027545a72d 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -217,14 +217,14 @@ static inline void fpstate_init_fstate(struct fregs_state *fp)
 
 void fpstate_init(union fpregs_state *state)
 {
-	if (!cpu_has_fpu) {
+	if (!static_cpu_has(X86_FEATURE_FPU)) {
 		fpstate_init_soft(&state->soft);
 		return;
 	}
 
 	memset(state, 0, xstate_size);
 
-	if (cpu_has_fxsr)
+	if (static_cpu_has(X86_FEATURE_FXSR))
 		fpstate_init_fxstate(&state->fxsave);
 	else
 		fpstate_init_fstate(&state->fsave);
@@ -237,7 +237,7 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	dst_fpu->fpregs_active = 0;
 	dst_fpu->last_cpu = -1;
 
-	if (!src_fpu->fpstate_active || !cpu_has_fpu)
+	if (!src_fpu->fpstate_active || !static_cpu_has(X86_FEATURE_FPU))
 		return 0;
 
 	WARN_ON_FPU(src_fpu != &current->thread.fpu);
@@ -506,33 +506,6 @@ void fpu__clear(struct fpu *fpu)
  * x87 math exception handling:
  */
 
-static inline unsigned short get_fpu_cwd(struct fpu *fpu)
-{
-	if (cpu_has_fxsr) {
-		return fpu->state.fxsave.cwd;
-	} else {
-		return (unsigned short)fpu->state.fsave.cwd;
-	}
-}
-
-static inline unsigned short get_fpu_swd(struct fpu *fpu)
-{
-	if (cpu_has_fxsr) {
-		return fpu->state.fxsave.swd;
-	} else {
-		return (unsigned short)fpu->state.fsave.swd;
-	}
-}
-
-static inline unsigned short get_fpu_mxcsr(struct fpu *fpu)
-{
-	if (cpu_has_xmm) {
-		return fpu->state.fxsave.mxcsr;
-	} else {
-		return MXCSR_DEFAULT;
-	}
-}
-
 int fpu__exception_code(struct fpu *fpu, int trap_nr)
 {
 	int err;
@@ -547,10 +520,15 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr)
 		 * so if this combination doesn't produce any single exception,
 		 * then we have a bad program that isn't synchronizing its FPU usage
 		 * and it will suffer the consequences since we won't be able to
-		 * fully reproduce the context of the exception
+		 * fully reproduce the context of the exception.
 		 */
-		cwd = get_fpu_cwd(fpu);
-		swd = get_fpu_swd(fpu);
+		if (boot_cpu_has(X86_FEATURE_FXSR)) {
+			cwd = fpu->state.fxsave.cwd;
+			swd = fpu->state.fxsave.swd;
+		} else {
+			cwd = (unsigned short)fpu->state.fsave.cwd;
+			swd = (unsigned short)fpu->state.fsave.swd;
+		}
 
 		err = swd & ~cwd;
 	} else {
@@ -560,7 +538,11 @@ int fpu__exception_code(struct fpu *fpu, int trap_nr)
 		 * unmasked exception was caught we must mask the exception mask bits
 		 * at 0x1f80, and then use these to mask the exception bits at 0x3f.
 		 */
-		unsigned short mxcsr = get_fpu_mxcsr(fpu);
+		unsigned short mxcsr = MXCSR_DEFAULT;
+
+		if (boot_cpu_has(X86_FEATURE_XMM))
+			mxcsr = fpu->state.fxsave.mxcsr;
+
 		err = ~(mxcsr >> 7) & mxcsr;
 	}
 
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 54c86fffbf9f..aacfd7a82cec 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -29,22 +29,22 @@ static void fpu__init_cpu_generic(void)
 	unsigned long cr0;
 	unsigned long cr4_mask = 0;
 
-	if (cpu_has_fxsr)
+	if (boot_cpu_has(X86_FEATURE_FXSR))
 		cr4_mask |= X86_CR4_OSFXSR;
-	if (cpu_has_xmm)
+	if (boot_cpu_has(X86_FEATURE_XMM))
 		cr4_mask |= X86_CR4_OSXMMEXCPT;
 	if (cr4_mask)
 		cr4_set_bits(cr4_mask);
 
 	cr0 = read_cr0();
 	cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
-	if (!cpu_has_fpu)
+	if (!boot_cpu_has(X86_FEATURE_FPU))
 		cr0 |= X86_CR0_EM;
 	write_cr0(cr0);
 
 	/* Flush out any pending x87 state: */
 #ifdef CONFIG_MATH_EMULATION
-	if (!cpu_has_fpu)
+	if (!boot_cpu_has(X86_FEATURE_FPU))
 		fpstate_init_soft(&current->thread.fpu.state.soft);
 	else
 #endif
@@ -89,7 +89,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
 	}
 
 #ifndef CONFIG_MATH_EMULATION
-	if (!cpu_has_fpu) {
+	if (!boot_cpu_has(X86_FEATURE_FPU)) {
 		pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n");
 		for (;;)
 			asm volatile("hlt");
@@ -106,7 +106,7 @@ static void __init fpu__init_system_mxcsr(void)
 {
 	unsigned int mask = 0;
 
-	if (cpu_has_fxsr) {
+	if (boot_cpu_has(X86_FEATURE_FXSR)) {
 		/* Static because GCC does not get 16-byte stack alignment right: */
 		static struct fxregs_state fxregs __initdata;
 
@@ -212,7 +212,7 @@ static void __init fpu__init_system_xstate_size_legacy(void)
 	 * fpu__init_system_xstate().
 	 */
 
-	if (!cpu_has_fpu) {
+	if (!boot_cpu_has(X86_FEATURE_FPU)) {
 		/*
 		 * Disable xsave as we do not support it if i387
 		 * emulation is enabled.
@@ -221,7 +221,7 @@ static void __init fpu__init_system_xstate_size_legacy(void)
 		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
 		xstate_size = sizeof(struct swregs_state);
 	} else {
-		if (cpu_has_fxsr)
+		if (boot_cpu_has(X86_FEATURE_FXSR))
 			xstate_size = sizeof(struct fxregs_state);
 		else
 			xstate_size = sizeof(struct fregs_state);
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 8bd1c003942a..81422dfb152b 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -21,7 +21,10 @@ int regset_xregset_fpregs_active(struct task_struct *target, const struct user_r
 {
 	struct fpu *target_fpu = &target->thread.fpu;
 
-	return (cpu_has_fxsr && target_fpu->fpstate_active) ? regset->n : 0;
+	if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->fpstate_active)
+		return regset->n;
+	else
+		return 0;
 }
 
 int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
@@ -30,7 +33,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
 {
 	struct fpu *fpu = &target->thread.fpu;
 
-	if (!cpu_has_fxsr)
+	if (!boot_cpu_has(X86_FEATURE_FXSR))
 		return -ENODEV;
 
 	fpu__activate_fpstate_read(fpu);
@@ -47,7 +50,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
 	struct fpu *fpu = &target->thread.fpu;
 	int ret;
 
-	if (!cpu_has_fxsr)
+	if (!boot_cpu_has(X86_FEATURE_FXSR))
 		return -ENODEV;
 
 	fpu__activate_fpstate_write(fpu);
@@ -65,7 +68,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
 	 * update the header bits in the xsave header, indicating the
 	 * presence of FP and SSE state.
 	 */
-	if (cpu_has_xsave)
+	if (boot_cpu_has(X86_FEATURE_XSAVE))
 		fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE;
 
 	return ret;
@@ -79,7 +82,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
 	struct xregs_state *xsave;
 	int ret;
 
-	if (!cpu_has_xsave)
+	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return -ENODEV;
 
 	fpu__activate_fpstate_read(fpu);
@@ -108,7 +111,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
 	struct xregs_state *xsave;
 	int ret;
 
-	if (!cpu_has_xsave)
+	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return -ENODEV;
 
 	fpu__activate_fpstate_write(fpu);
@@ -275,10 +278,10 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset,
 
 	fpu__activate_fpstate_read(fpu);
 
-	if (!static_cpu_has(X86_FEATURE_FPU))
+	if (!boot_cpu_has(X86_FEATURE_FPU))
 		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
 
-	if (!cpu_has_fxsr)
+	if (!boot_cpu_has(X86_FEATURE_FXSR))
 		return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 					   &fpu->state.fsave, 0,
 					   -1);
@@ -306,10 +309,10 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 	fpu__activate_fpstate_write(fpu);
 	fpstate_sanitize_xstate(fpu);
 
-	if (!static_cpu_has(X86_FEATURE_FPU))
+	if (!boot_cpu_has(X86_FEATURE_FPU))
 		return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
 
-	if (!cpu_has_fxsr)
+	if (!boot_cpu_has(X86_FEATURE_FXSR))
 		return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 					  &fpu->state.fsave, 0,
 					  -1);
@@ -325,7 +328,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 	 * update the header bit in the xsave header, indicating the
 	 * presence of FP.
 	 */
-	if (cpu_has_xsave)
+	if (boot_cpu_has(X86_FEATURE_XSAVE))
 		fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FP;
 	return ret;
 }
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index b48ef35b28d4..4ea2a59483c7 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -190,7 +190,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
  */
 void fpu__init_cpu_xstate(void)
 {
-	if (!cpu_has_xsave || !xfeatures_mask)
+	if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask)
 		return;
 
 	cr4_set_bits(X86_CR4_OSXSAVE);
@@ -280,7 +280,7 @@ static void __init setup_xstate_comp(void)
 	xstate_comp_offsets[0] = 0;
 	xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space);
 
-	if (!cpu_has_xsaves) {
+	if (!boot_cpu_has(X86_FEATURE_XSAVES)) {
 		for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) {
 			if (xfeature_enabled(i)) {
 				xstate_comp_offsets[i] = xstate_offsets[i];
@@ -316,13 +316,13 @@ static void __init setup_init_fpu_buf(void)
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
 
-	if (!cpu_has_xsave)
+	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return;
 
 	setup_xstate_features();
 	print_xstate_features();
 
-	if (cpu_has_xsaves) {
+	if (boot_cpu_has(X86_FEATURE_XSAVES)) {
 		init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask;
 		init_fpstate.xsave.header.xfeatures = xfeatures_mask;
 	}
@@ -417,7 +417,7 @@ static int xfeature_size(int xfeature_nr)
  */
 static int using_compacted_format(void)
 {
-	return cpu_has_xsaves;
+	return boot_cpu_has(X86_FEATURE_XSAVES);
 }
 
 static void __xstate_dump_leaves(void)
@@ -549,7 +549,7 @@ static unsigned int __init calculate_xstate_size(void)
 	unsigned int eax, ebx, ecx, edx;
 	unsigned int calculated_xstate_size;
 
-	if (!cpu_has_xsaves) {
+	if (!boot_cpu_has(X86_FEATURE_XSAVES)) {
 		/*
 		 * - CPUID function 0DH, sub-function 0:
 		 *    EBX enumerates the size (in bytes) required by
@@ -630,7 +630,7 @@ void __init fpu__init_system_xstate(void)
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
 
-	if (!cpu_has_xsave) {
+	if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
 		pr_info("x86/fpu: Legacy x87 FPU detected.\n");
 		return;
 	}
@@ -667,7 +667,7 @@ void __init fpu__init_system_xstate(void)
 	pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
 		xfeatures_mask,
 		xstate_size,
-		cpu_has_xsaves ? "compacted" : "standard");
+		boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard");
 }
 
 /*
@@ -678,7 +678,7 @@ void fpu__resume_cpu(void)
 	/*
 	 * Restore XCR0 on xsave capable CPUs:
 	 */
-	if (cpu_has_xsave)
+	if (boot_cpu_has(X86_FEATURE_XSAVE))
 		xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
 }