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
  ...

11 files changed, 109 insertions, 59 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7b76eb6..c343a54 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -565,14 +565,17 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	 * can safely set X86_FEATURE_EXTD_APICID unconditionally for families
 	 * after 16h.
 	 */
-	if (cpu_has_apic && c->x86 > 0x16) {
-		set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
-	} else if (cpu_has_apic && c->x86 >= 0xf) {
-		/* check CPU config space for extended APIC ID */
-		unsigned int val;
-		val = read_pci_config(0, 24, 0, 0x68);
-		if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18)))
+	if (boot_cpu_has(X86_FEATURE_APIC)) {
+		if (c->x86 > 0x16)
 			set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
+		else if (c->x86 >= 0xf) {
+			/* check CPU config space for extended APIC ID */
+			unsigned int val;
+
+			val = read_pci_config(0, 24, 0, 0x68);
+			if ((val >> 17 & 0x3) == 0x3)
+				set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
+		}
 	}
 #endif
 
@@ -628,6 +631,7 @@ static void init_amd_k8(struct cpuinfo_x86 *c)
 	 */
 	msr_set_bit(MSR_K7_HWCR, 6);
 #endif
+	set_cpu_bug(c, X86_BUG_SWAPGS_FENCE);
 }
 
 static void init_amd_gh(struct cpuinfo_x86 *c)
@@ -746,7 +750,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 	if (c->x86 >= 0xf)
 		set_cpu_cap(c, X86_FEATURE_K8);
 
-	if (cpu_has_xmm2) {
+	if (cpu_has(c, X86_FEATURE_XMM2)) {
 		/* MFENCE stops RDTSC speculation */
 		set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
 	}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index dbc6f06..6ef6ed9 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -430,7 +430,7 @@ void load_percpu_segment(int cpu)
 #ifdef CONFIG_X86_32
 	loadsegment(fs, __KERNEL_PERCPU);
 #else
-	loadsegment(gs, 0);
+	__loadsegment_simple(gs, 0);
 	wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu));
 #endif
 	load_stack_canary_segment();
@@ -866,30 +866,34 @@ static void detect_nopl(struct cpuinfo_x86 *c)
 #else
 	set_cpu_cap(c, X86_FEATURE_NOPL);
 #endif
+}
 
+static void detect_null_seg_behavior(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_64
 	/*
-	 * ESPFIX is a strange bug.  All real CPUs have it.  Paravirt
-	 * systems that run Linux at CPL > 0 may or may not have the
-	 * issue, but, even if they have the issue, there's absolutely
-	 * nothing we can do about it because we can't use the real IRET
-	 * instruction.
+	 * Empirically, writing zero to a segment selector on AMD does
+	 * not clear the base, whereas writing zero to a segment
+	 * selector on Intel does clear the base.  Intel's behavior
+	 * allows slightly faster context switches in the common case
+	 * where GS is unused by the prev and next threads.
 	 *
-	 * NB: For the time being, only 32-bit kernels support
-	 * X86_BUG_ESPFIX as such.  64-bit kernels directly choose
-	 * whether to apply espfix using paravirt hooks.  If any
-	 * non-paravirt system ever shows up that does *not* have the
-	 * ESPFIX issue, we can change this.
+	 * Since neither vendor documents this anywhere that I can see,
+	 * detect it directly instead of hardcoding the choice by
+	 * vendor.
+	 *
+	 * I've designated AMD's behavior as the "bug" because it's
+	 * counterintuitive and less friendly.
 	 */
-#ifdef CONFIG_X86_32
-#ifdef CONFIG_PARAVIRT
-	do {
-		extern void native_iret(void);
-		if (pv_cpu_ops.iret == native_iret)
-			set_cpu_bug(c, X86_BUG_ESPFIX);
-	} while (0);
-#else
-	set_cpu_bug(c, X86_BUG_ESPFIX);
-#endif
+
+	unsigned long old_base, tmp;
+	rdmsrl(MSR_FS_BASE, old_base);
+	wrmsrl(MSR_FS_BASE, 1);
+	loadsegment(fs, 0);
+	rdmsrl(MSR_FS_BASE, tmp);
+	if (tmp != 0)
+		set_cpu_bug(c, X86_BUG_NULL_SEG);
+	wrmsrl(MSR_FS_BASE, old_base);
 #endif
 }
 
@@ -925,6 +929,33 @@ static void generic_identify(struct cpuinfo_x86 *c)
 	get_model_name(c); /* Default name */
 
 	detect_nopl(c);
+
+	detect_null_seg_behavior(c);
+
+	/*
+	 * ESPFIX is a strange bug.  All real CPUs have it.  Paravirt
+	 * systems that run Linux at CPL > 0 may or may not have the
+	 * issue, but, even if they have the issue, there's absolutely
+	 * nothing we can do about it because we can't use the real IRET
+	 * instruction.
+	 *
+	 * NB: For the time being, only 32-bit kernels support
+	 * X86_BUG_ESPFIX as such.  64-bit kernels directly choose
+	 * whether to apply espfix using paravirt hooks.  If any
+	 * non-paravirt system ever shows up that does *not* have the
+	 * ESPFIX issue, we can change this.
+	 */
+#ifdef CONFIG_X86_32
+# ifdef CONFIG_PARAVIRT
+	do {
+		extern void native_iret(void);
+		if (pv_cpu_ops.iret == native_iret)
+			set_cpu_bug(c, X86_BUG_ESPFIX);
+	} while (0);
+# else
+	set_cpu_bug(c, X86_BUG_ESPFIX);
+# endif
+#endif
 }
 
 static void x86_init_cache_qos(struct cpuinfo_x86 *c)
@@ -1080,12 +1111,12 @@ void enable_sep_cpu(void)
 	struct tss_struct *tss;
 	int cpu;
 
+	if (!boot_cpu_has(X86_FEATURE_SEP))
+		return;
+
 	cpu = get_cpu();
 	tss = &per_cpu(cpu_tss, cpu);
 
-	if (!boot_cpu_has(X86_FEATURE_SEP))
-		goto out;
-
 	/*
 	 * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field --
 	 * see the big comment in struct x86_hw_tss's definition.
@@ -1100,7 +1131,6 @@ void enable_sep_cpu(void)
 
 	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
 
-out:
 	put_cpu();
 }
 #endif
@@ -1532,7 +1562,7 @@ void cpu_init(void)
 	pr_info("Initializing CPU#%d\n", cpu);
 
 	if (cpu_feature_enabled(X86_FEATURE_VME) ||
-	    cpu_has_tsc ||
+	    boot_cpu_has(X86_FEATURE_TSC) ||
 	    boot_cpu_has(X86_FEATURE_DE))
 		cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
 
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 6adef9c..bd9dcd6 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -333,7 +333,7 @@ static void init_cyrix(struct cpuinfo_x86 *c)
 		switch (dir0_lsn) {
 		case 0xd:  /* either a 486SLC or DLC w/o DEVID */
 			dir0_msn = 0;
-			p = Cx486_name[(cpu_has_fpu ? 1 : 0)];
+			p = Cx486_name[!!boot_cpu_has(X86_FEATURE_FPU)];
 			break;
 
 		case 0xe:  /* a 486S A step */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index e4393bf..b18f470 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -152,9 +152,9 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	 *  the TLB when any changes are made to any of the page table entries.
 	 *  The operating system must reload CR3 to cause the TLB to be flushed"
 	 *
-	 * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should
-	 * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
-	 * to be modified
+	 * As a result, boot_cpu_has(X86_FEATURE_PGE) in arch/x86/include/asm/tlbflush.h
+	 * should be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
+	 * to be modified.
 	 */
 	if (c->x86 == 5 && c->x86_model == 9) {
 		pr_info("Disabling PGE capability bit\n");
@@ -281,7 +281,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * integrated APIC (see 11AP erratum in "Pentium Processor
 	 * Specification Update").
 	 */
-	if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
+	if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
 	    (c->x86_mask < 0x6 || c->x86_mask == 0xb))
 		set_cpu_bug(c, X86_BUG_11AP);
 
@@ -456,7 +456,7 @@ static void init_intel(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
 	}
 
-	if (cpu_has_xmm2)
+	if (cpu_has(c, X86_FEATURE_XMM2))
 		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
 
 	if (boot_cpu_has(X86_FEATURE_DS)) {
@@ -468,7 +468,7 @@ static void init_intel(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_PEBS);
 	}
 
-	if (c->x86 == 6 && cpu_has_clflush &&
+	if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_CLFLUSH) &&
 	    (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
 		set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR);
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 1e8bb6c..1defb8e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -84,7 +84,7 @@ static int cmci_supported(int *banks)
 	 */
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return 0;
-	if (!cpu_has_apic || lapic_get_maxlvt() < 6)
+	if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6)
 		return 0;
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 	*banks = min_t(unsigned, MAX_NR_BANKS, cap & 0xff);
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index ac780ca..6b9dc4d 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -450,7 +450,7 @@ asmlinkage __visible void smp_trace_thermal_interrupt(struct pt_regs *regs)
 /* Thermal monitoring depends on APIC, ACPI and clock modulation */
 static int intel_thermal_supported(struct cpuinfo_x86 *c)
 {
-	if (!cpu_has_apic)
+	if (!boot_cpu_has(X86_FEATURE_APIC))
 		return 0;
 	if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC))
 		return 0;
diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c
index f8c81ba..b1086f7 100644
--- a/arch/x86/kernel/cpu/mtrr/cyrix.c
+++ b/arch/x86/kernel/cpu/mtrr/cyrix.c
@@ -137,7 +137,7 @@ static void prepare_set(void)
 	u32 cr0;
 
 	/*  Save value of CR4 and clear Page Global Enable (bit 7)  */
-	if (cpu_has_pge) {
+	if (boot_cpu_has(X86_FEATURE_PGE)) {
 		cr4 = __read_cr4();
 		__write_cr4(cr4 & ~X86_CR4_PGE);
 	}
@@ -170,7 +170,7 @@ static void post_set(void)
 	write_cr0(read_cr0() & ~X86_CR0_CD);
 
 	/* Restore value of CR4 */
-	if (cpu_has_pge)
+	if (boot_cpu_has(X86_FEATURE_PGE))
 		__write_cr4(cr4);
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 19f5736..16e37a25 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -444,11 +444,24 @@ static void __init print_mtrr_state(void)
 		pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20);
 }
 
+/* PAT setup for BP. We need to go through sync steps here */
+void __init mtrr_bp_pat_init(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	prepare_set();
+
+	pat_init();
+
+	post_set();
+	local_irq_restore(flags);
+}
+
 /* Grab all of the MTRR state for this CPU into *state */
 bool __init get_mtrr_state(void)
 {
 	struct mtrr_var_range *vrs;
-	unsigned long flags;
 	unsigned lo, dummy;
 	unsigned int i;
 
@@ -481,15 +494,6 @@ bool __init get_mtrr_state(void)
 
 	mtrr_state_set = 1;
 
-	/* PAT setup for BP. We need to go through sync steps here */
-	local_irq_save(flags);
-	prepare_set();
-
-	pat_init();
-
-	post_set();
-	local_irq_restore(flags);
-
 	return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED);
 }
 
@@ -741,7 +745,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 	wbinvd();
 
 	/* Save value of CR4 and clear Page Global Enable (bit 7) */
-	if (cpu_has_pge) {
+	if (boot_cpu_has(X86_FEATURE_PGE)) {
 		cr4 = __read_cr4();
 		__write_cr4(cr4 & ~X86_CR4_PGE);
 	}
@@ -771,7 +775,7 @@ static void post_set(void) __releases(set_atomicity_lock)
 	write_cr0(read_cr0() & ~X86_CR0_CD);
 
 	/* Restore value of CR4 */
-	if (cpu_has_pge)
+	if (boot_cpu_has(X86_FEATURE_PGE))
 		__write_cr4(cr4);
 	raw_spin_unlock(&set_atomicity_lock);
 }
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 10f8d47..7d393ec 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -752,6 +752,9 @@ void __init mtrr_bp_init(void)
 			/* BIOS may override */
 			__mtrr_enabled = get_mtrr_state();
 
+			if (mtrr_enabled())
+				mtrr_bp_pat_init();
+
 			if (mtrr_cleanup(phys_addr)) {
 				changed_by_mtrr_cleanup = 1;
 				mtrr_if->set_all();
@@ -759,8 +762,16 @@ void __init mtrr_bp_init(void)
 		}
 	}
 
-	if (!mtrr_enabled())
+	if (!mtrr_enabled()) {
 		pr_info("MTRR: Disabled\n");
+
+		/*
+		 * PAT initialization relies on MTRR's rendezvous handler.
+		 * Skip PAT init until the handler can initialize both
+		 * features independently.
+		 */
+		pat_disable("MTRRs disabled, skipping PAT initialization too.");
+	}
 }
 
 void mtrr_ap_init(void)
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index 951884d..6c7ced0 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -52,6 +52,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt);
 void fill_mtrr_var_range(unsigned int index,
 		u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi);
 bool get_mtrr_state(void);
+void mtrr_bp_pat_init(void);
 
 extern void set_mtrr_ops(const struct mtrr_ops *ops);
 
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 364e583..8cac429 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -94,7 +94,7 @@ static void __init vmware_platform_setup(void)
  */
 static uint32_t __init vmware_platform(void)
 {
-	if (cpu_has_hypervisor) {
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
 		unsigned int eax;
 		unsigned int hyper_vendor_id[3];