Merge branch 'irq/urgent' into x86/apic

Pick up core changes which affect the vector rework.

38 files changed, 561 insertions, 494 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 829e89cfcee2..9fb9a1f1e47b 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4409,10 +4409,9 @@ static __init int fixup_ht_bug(void)
 		return 0;
 	}
 
-	if (lockup_detector_suspend() != 0) {
-		pr_debug("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n");
-		return 0;
-	}
+	cpus_read_lock();
+
+	hardlockup_detector_perf_stop();
 
 	x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED);
 
@@ -4420,9 +4419,7 @@ static __init int fixup_ht_bug(void)
 	x86_pmu.commit_scheduling = NULL;
 	x86_pmu.stop_scheduling = NULL;
 
-	lockup_detector_resume();
-
-	cpus_read_lock();
+	hardlockup_detector_perf_restart();
 
 	for_each_online_cpu(c)
 		free_excl_cntrs(c);
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 4cf100ff2a37..72db0664a53d 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -552,6 +552,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE,  snb_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE,  snb_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
@@ -560,6 +561,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_DENVERTON, glm_cstates),
+
+	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GEMINI_LAKE, glm_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 8e2457cb6b4a..005908ee9333 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -775,6 +775,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init),
 
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_DENVERTON, hsw_rapl_init),
+
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GEMINI_LAKE, hsw_rapl_init),
 	{},
 };
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index db1fe377e6dd..a7196818416a 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3462,7 +3462,7 @@ static struct intel_uncore_ops skx_uncore_iio_ops = {
 static struct intel_uncore_type skx_uncore_iio = {
 	.name			= "iio",
 	.num_counters		= 4,
-	.num_boxes		= 5,
+	.num_boxes		= 6,
 	.perf_ctr_bits		= 48,
 	.event_ctl		= SKX_IIO0_MSR_PMON_CTL0,
 	.perf_ctr		= SKX_IIO0_MSR_PMON_CTR0,
@@ -3492,7 +3492,7 @@ static const struct attribute_group skx_uncore_format_group = {
 static struct intel_uncore_type skx_uncore_irp = {
 	.name			= "irp",
 	.num_counters		= 2,
-	.num_boxes		= 5,
+	.num_boxes		= 6,
 	.perf_ctr_bits		= 48,
 	.event_ctl		= SKX_IRP0_MSR_PMON_CTL0,
 	.perf_ctr		= SKX_IRP0_MSR_PMON_CTR0,
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 4bb3ec69e8ea..06723671ae4e 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -63,6 +63,14 @@ static bool test_intel(int idx)
 	case INTEL_FAM6_ATOM_SILVERMONT1:
 	case INTEL_FAM6_ATOM_SILVERMONT2:
 	case INTEL_FAM6_ATOM_AIRMONT:
+
+	case INTEL_FAM6_ATOM_GOLDMONT:
+	case INTEL_FAM6_ATOM_DENVERTON:
+
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+
+	case INTEL_FAM6_XEON_PHI_KNL:
+	case INTEL_FAM6_XEON_PHI_KNM:
 		if (idx == PERF_MSR_SMI)
 			return true;
 		break;
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index e0bb46c02857..0e2a5edbce00 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -231,7 +231,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 		 ksig->ka.sa.sa_restorer)
 		sp = (unsigned long) ksig->ka.sa.sa_restorer;
 
-	if (fpu->fpstate_active) {
+	if (fpu->initialized) {
 		unsigned long fx_aligned, math_size;
 
 		sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size);
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index c1eadbaf1115..b0dc91f4bedc 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -11,10 +11,12 @@
 # define __ASM_FORM_COMMA(x) " " #x ","
 #endif
 
-#ifdef CONFIG_X86_32
+#ifndef __x86_64__
+/* 32 bit */
 # define __ASM_SEL(a,b) __ASM_FORM(a)
 # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a)
 #else
+/* 64 bit */
 # define __ASM_SEL(a,b) __ASM_FORM(b)
 # define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b)
 #endif
@@ -139,8 +141,8 @@
  * gets set up by the containing function.  If you forget to do this, objtool
  * may print a "call without frame pointer save/setup" warning.
  */
-register unsigned int __asm_call_sp asm("esp");
-#define ASM_CALL_CONSTRAINT "+r" (__asm_call_sp)
+register unsigned long current_stack_pointer asm(_ASM_SP);
+#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
 #endif
 
 #endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 554cdb205d17..e3221ffa304e 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -23,11 +23,9 @@
 /*
  * High level FPU state handling functions:
  */
-extern void fpu__activate_curr(struct fpu *fpu);
-extern void fpu__activate_fpstate_read(struct fpu *fpu);
-extern void fpu__activate_fpstate_write(struct fpu *fpu);
-extern void fpu__current_fpstate_write_begin(void);
-extern void fpu__current_fpstate_write_end(void);
+extern void fpu__initialize(struct fpu *fpu);
+extern void fpu__prepare_read(struct fpu *fpu);
+extern void fpu__prepare_write(struct fpu *fpu);
 extern void fpu__save(struct fpu *fpu);
 extern void fpu__restore(struct fpu *fpu);
 extern int  fpu__restore_sig(void __user *buf, int ia32_frame);
@@ -120,20 +118,11 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu);
 	err;								\
 })
 
-#define check_insn(insn, output, input...)				\
-({									\
-	int err;							\
+#define kernel_insn(insn, output, input...)				\
 	asm volatile("1:" #insn "\n\t"					\
 		     "2:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:  movl $-1,%[err]\n"				\
-		     "    jmp  2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
-		     : [err] "=r" (err), output				\
-		     : "0"(0), input);					\
-	err;								\
-})
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore)	\
+		     : output : input)
 
 static inline int copy_fregs_to_user(struct fregs_state __user *fx)
 {
@@ -153,20 +142,16 @@ static inline int copy_fxregs_to_user(struct fxregs_state __user *fx)
 
 static inline void copy_kernel_to_fxregs(struct fxregs_state *fx)
 {
-	int err;
-
 	if (IS_ENABLED(CONFIG_X86_32)) {
-		err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+		kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
 	} else {
 		if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) {
-			err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+			kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
 		} else {
 			/* See comment in copy_fxregs_to_kernel() below. */
-			err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
+			kernel_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
 		}
 	}
-	/* Copying from a kernel buffer to FPU registers should never fail: */
-	WARN_ON_FPU(err);
 }
 
 static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
@@ -183,9 +168,7 @@ static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
 
 static inline void copy_kernel_to_fregs(struct fregs_state *fx)
 {
-	int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-
-	WARN_ON_FPU(err);
+	kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
 }
 
 static inline int copy_user_to_fregs(struct fregs_state __user *fx)
@@ -281,18 +264,13 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
  * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact
  * XSAVE area format.
  */
-#define XSTATE_XRESTORE(st, lmask, hmask, err)				\
+#define XSTATE_XRESTORE(st, lmask, hmask)				\
 	asm volatile(ALTERNATIVE(XRSTOR,				\
 				 XRSTORS, X86_FEATURE_XSAVES)		\
 		     "\n"						\
-		     "xor %[err], %[err]\n"				\
 		     "3:\n"						\
-		     ".pushsection .fixup,\"ax\"\n"			\
-		     "4: movl $-2, %[err]\n"				\
-		     "jmp 3b\n"						\
-		     ".popsection\n"					\
-		     _ASM_EXTABLE(661b, 4b)				\
-		     : [err] "=r" (err)					\
+		     _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\
+		     :							\
 		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
 		     : "memory")
 
@@ -336,7 +314,10 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
 	else
 		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
 
-	/* We should never fault when copying from a kernel buffer: */
+	/*
+	 * We should never fault when copying from a kernel buffer, and the FPU
+	 * state we set at boot time should be valid.
+	 */
 	WARN_ON_FPU(err);
 }
 
@@ -350,7 +331,7 @@ static inline void copy_xregs_to_kernel(struct xregs_state *xstate)
 	u32 hmask = mask >> 32;
 	int err;
 
-	WARN_ON(!alternatives_patched);
+	WARN_ON_FPU(!alternatives_patched);
 
 	XSTATE_XSAVE(xstate, lmask, hmask, err);
 
@@ -365,12 +346,8 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask)
 {
 	u32 lmask = mask;
 	u32 hmask = mask >> 32;
-	int err;
-
-	XSTATE_XRESTORE(xstate, lmask, hmask, err);
 
-	/* We should never fault when copying from a kernel buffer: */
-	WARN_ON_FPU(err);
+	XSTATE_XRESTORE(xstate, lmask, hmask);
 }
 
 /*
@@ -526,38 +503,17 @@ static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu)
  */
 static inline void fpregs_deactivate(struct fpu *fpu)
 {
-	WARN_ON_FPU(!fpu->fpregs_active);
-
-	fpu->fpregs_active = 0;
 	this_cpu_write(fpu_fpregs_owner_ctx, NULL);
 	trace_x86_fpu_regs_deactivated(fpu);
 }
 
 static inline void fpregs_activate(struct fpu *fpu)
 {
-	WARN_ON_FPU(fpu->fpregs_active);
-
-	fpu->fpregs_active = 1;
 	this_cpu_write(fpu_fpregs_owner_ctx, fpu);
 	trace_x86_fpu_regs_activated(fpu);
 }
 
 /*
- * The question "does this thread have fpu access?"
- * is slightly racy, since preemption could come in
- * and revoke it immediately after the test.
- *
- * However, even in that very unlikely scenario,
- * we can just assume we have FPU access - typically
- * to save the FP state - we'll just take a #NM
- * fault and get the FPU access back.
- */
-static inline int fpregs_active(void)
-{
-	return current->thread.fpu.fpregs_active;
-}
-
-/*
  * FPU state switching for scheduling.
  *
  * This is a two-stage process:
@@ -571,14 +527,13 @@ static inline int fpregs_active(void)
 static inline void
 switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 {
-	if (old_fpu->fpregs_active) {
+	if (old_fpu->initialized) {
 		if (!copy_fpregs_to_fpstate(old_fpu))
 			old_fpu->last_cpu = -1;
 		else
 			old_fpu->last_cpu = cpu;
 
 		/* But leave fpu_fpregs_owner_ctx! */
-		old_fpu->fpregs_active = 0;
 		trace_x86_fpu_regs_deactivated(old_fpu);
 	} else
 		old_fpu->last_cpu = -1;
@@ -595,7 +550,7 @@ switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu)
 {
 	bool preload = static_cpu_has(X86_FEATURE_FPU) &&
-		       new_fpu->fpstate_active;
+		       new_fpu->initialized;
 
 	if (preload) {
 		if (!fpregs_state_valid(new_fpu, cpu))
@@ -617,8 +572,7 @@ static inline void user_fpu_begin(void)
 	struct fpu *fpu = &current->thread.fpu;
 
 	preempt_disable();
-	if (!fpregs_active())
-		fpregs_activate(fpu);
+	fpregs_activate(fpu);
 	preempt_enable();
 }
 
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 3c80f5b9c09d..a1520575d86b 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -68,6 +68,9 @@ struct fxregs_state {
 /* Default value for fxregs_state.mxcsr: */
 #define MXCSR_DEFAULT		0x1f80
 
+/* Copy both mxcsr & mxcsr_flags with a single u64 memcpy: */
+#define MXCSR_AND_FLAGS_SIZE sizeof(u64)
+
 /*
  * Software based FPU emulation state. This is arbitrary really,
  * it matches the x87 format to make it easier to understand:
@@ -290,36 +293,13 @@ struct fpu {
 	unsigned int			last_cpu;
 
 	/*
-	 * @fpstate_active:
+	 * @initialized:
 	 *
-	 * This flag indicates whether this context is active: if the task
+	 * This flag indicates whether this context is initialized: if the task
 	 * is not running then we can restore from this context, if the task
 	 * is running then we should save into this context.
 	 */
-	unsigned char			fpstate_active;
-
-	/*
-	 * @fpregs_active:
-	 *
-	 * This flag determines whether a given context is actively
-	 * loaded into the FPU's registers and that those registers
-	 * represent the task's current FPU state.
-	 *
-	 * Note the interaction with fpstate_active:
-	 *
-	 *   # task does not use the FPU:
-	 *   fpstate_active == 0
-	 *
-	 *   # task uses the FPU and regs are active:
-	 *   fpstate_active == 1 && fpregs_active == 1
-	 *
-	 *   # the regs are inactive but still match fpstate:
-	 *   fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu
-	 *
-	 * The third state is what we use for the lazy restore optimization
-	 * on lazy-switching CPUs.
-	 */
-	unsigned char			fpregs_active;
+	unsigned char			initialized;
 
 	/*
 	 * @state:
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 1b2799e0699a..83fee2469eb7 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -48,8 +48,12 @@ void fpu__xstate_clear_all_cpu_caps(void);
 void *get_xsave_addr(struct xregs_state *xsave, int xstate);
 const void *get_xsave_field_ptr(int xstate_field);
 int using_compacted_format(void);
-int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
-			void __user *ubuf, struct xregs_state *xsave);
-int copyin_to_xsaves(const void *kbuf, const void __user *ubuf,
-		     struct xregs_state *xsave);
+int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
+int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
+int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf);
+int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf);
+
+/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
+extern int validate_xstate_header(const struct xstate_header *hdr);
+
 #endif
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index bc62e7cbf1b1..59ad3d132353 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -88,7 +88,7 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 bool kvm_para_available(void);
 unsigned int kvm_arch_para_features(void);
 void __init kvm_guest_init(void);
-void kvm_async_pf_task_wait(u32 token);
+void kvm_async_pf_task_wait(u32 token, int interrupt_kernel);
 void kvm_async_pf_task_wake(u32 token);
 u32 kvm_read_and_reset_pf_reason(void);
 extern void kvm_disable_steal_time(void);
@@ -103,7 +103,7 @@ static inline void kvm_spinlock_init(void)
 
 #else /* CONFIG_KVM_GUEST */
 #define kvm_guest_init() do {} while (0)
-#define kvm_async_pf_task_wait(T) do {} while(0)
+#define kvm_async_pf_task_wait(T, I) do {} while(0)
 #define kvm_async_pf_task_wake(T) do {} while(0)
 
 static inline bool kvm_para_available(void)
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 5161da1a0fa0..89e7eeb5cec1 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -158,17 +158,6 @@ struct thread_info {
  */
 #ifndef __ASSEMBLY__
 
-static inline unsigned long current_stack_pointer(void)
-{
-	unsigned long sp;
-#ifdef CONFIG_X86_64
-	asm("mov %%rsp,%0" : "=g" (sp));
-#else
-	asm("mov %%esp,%0" : "=g" (sp));
-#endif
-	return sp;
-}
-
 /*
  * Walks up the stack frames to make sure that the specified object is
  * entirely contained by a single stack frame.
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
index 342e59789fcd..39f7a27bef13 100644
--- a/arch/x86/include/asm/trace/fpu.h
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -12,25 +12,22 @@ DECLARE_EVENT_CLASS(x86_fpu,
 
 	TP_STRUCT__entry(
 		__field(struct fpu *, fpu)
-		__field(bool, fpregs_active)
-		__field(bool, fpstate_active)
+		__field(bool, initialized)
 		__field(u64, xfeatures)
 		__field(u64, xcomp_bv)
 		),
 
 	TP_fast_assign(
 		__entry->fpu		= fpu;
-		__entry->fpregs_active	= fpu->fpregs_active;
-		__entry->fpstate_active	= fpu->fpstate_active;
+		__entry->initialized	= fpu->initialized;
 		if (boot_cpu_has(X86_FEATURE_OSXSAVE)) {
 			__entry->xfeatures = fpu->state.xsave.header.xfeatures;
 			__entry->xcomp_bv  = fpu->state.xsave.header.xcomp_bv;
 		}
 	),
-	TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d xfeatures: %llx xcomp_bv: %llx",
+	TP_printk("x86/fpu: %p initialized: %d xfeatures: %llx xcomp_bv: %llx",
 			__entry->fpu,
-			__entry->fpregs_active,
-			__entry->fpstate_active,
+			__entry->initialized,
 			__entry->xfeatures,
 			__entry->xcomp_bv
 	)
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 78e8fcc87d4c..4b892917edeb 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -337,7 +337,7 @@ do {									\
 		     _ASM_EXTABLE(1b, 4b)				\
 		     _ASM_EXTABLE(2b, 4b)				\
 		     : "=r" (retval), "=&A"(x)				\
-		     : "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1),	\
+		     : "m" (__m(__ptr)), "m" __m(((u32 __user *)(__ptr)) + 1),	\
 		       "i" (errret), "0" (retval));			\
 })
 
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 128a1a0b1450..7cb282e9e587 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -551,13 +551,13 @@ static inline void
 MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr,
 			struct desc_struct desc)
 {
-	u32 *p = (u32 *) &desc;
-
 	mcl->op = __HYPERVISOR_update_descriptor;
 	if (sizeof(maddr) == sizeof(long)) {
 		mcl->args[0] = maddr;
 		mcl->args[1] = *(unsigned long *)&desc;
 	} else {
+		u32 *p = (u32 *)&desc;
+
 		mcl->args[0] = maddr;
 		mcl->args[1] = maddr >> 32;
 		mcl->args[2] = *p++;
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index e1114f070c2d..f92a6593de1e 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -100,7 +100,7 @@ void __kernel_fpu_begin(void)
 
 	kernel_fpu_disable();
 
-	if (fpu->fpregs_active) {
+	if (fpu->initialized) {
 		/*
 		 * Ignore return value -- we don't care if reg state
 		 * is clobbered.
@@ -116,7 +116,7 @@ void __kernel_fpu_end(void)
 {
 	struct fpu *fpu = &current->thread.fpu;
 
-	if (fpu->fpregs_active)
+	if (fpu->initialized)
 		copy_kernel_to_fpregs(&fpu->state);
 
 	kernel_fpu_enable();
@@ -148,7 +148,7 @@ void fpu__save(struct fpu *fpu)
 
 	preempt_disable();
 	trace_x86_fpu_before_save(fpu);
-	if (fpu->fpregs_active) {
+	if (fpu->initialized) {
 		if (!copy_fpregs_to_fpstate(fpu)) {
 			copy_kernel_to_fpregs(&fpu->state);
 		}
@@ -189,10 +189,9 @@ EXPORT_SYMBOL_GPL(fpstate_init);
 
 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 || !static_cpu_has(X86_FEATURE_FPU))
+	if (!src_fpu->initialized || !static_cpu_has(X86_FEATURE_FPU))
 		return 0;
 
 	WARN_ON_FPU(src_fpu != &current->thread.fpu);
@@ -206,26 +205,14 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
 	/*
 	 * Save current FPU registers directly into the child
 	 * FPU context, without any memory-to-memory copying.
-	 * In lazy mode, if the FPU context isn't loaded into
-	 * fpregs, CR0.TS will be set and do_device_not_available
-	 * will load the FPU context.
 	 *
-	 * We have to do all this with preemption disabled,
-	 * mostly because of the FNSAVE case, because in that
-	 * case we must not allow preemption in the window
-	 * between the FNSAVE and us marking the context lazy.
-	 *
-	 * It shouldn't be an issue as even FNSAVE is plenty
-	 * fast in terms of critical section length.
+	 * ( The function 'fails' in the FNSAVE case, which destroys
+	 *   register contents so we have to copy them back. )
 	 */
-	preempt_disable();
 	if (!copy_fpregs_to_fpstate(dst_fpu)) {
-		memcpy(&src_fpu->state, &dst_fpu->state,
-		       fpu_kernel_xstate_size);
-
+		memcpy(&src_fpu->state, &dst_fpu->state, fpu_kernel_xstate_size);
 		copy_kernel_to_fpregs(&src_fpu->state);
 	}
-	preempt_enable();
 
 	trace_x86_fpu_copy_src(src_fpu);
 	trace_x86_fpu_copy_dst(dst_fpu);
@@ -237,45 +224,48 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
  * Activate the current task's in-memory FPU context,
  * if it has not been used before:
  */
-void fpu__activate_curr(struct fpu *fpu)
+void fpu__initialize(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu);
 
-	if (!fpu->fpstate_active) {
+	if (!fpu->initialized) {
 		fpstate_init(&fpu->state);
 		trace_x86_fpu_init_state(fpu);
 
 		trace_x86_fpu_activate_state(fpu);
 		/* Safe to do for the current task: */
-		fpu->fpstate_active = 1;
+		fpu->initialized = 1;
 	}
 }
-EXPORT_SYMBOL_GPL(fpu__activate_curr);
+EXPORT_SYMBOL_GPL(fpu__initialize);
 
 /*
  * This function must be called before we read a task's fpstate.
  *
- * If the task has not used the FPU before then initialize its
- * fpstate.
+ * There's two cases where this gets called:
+ *
+ * - for the current task (when coredumping), in which case we have
+ *   to save the latest FPU registers into the fpstate,
+ *
+ * - or it's called for stopped tasks (ptrace), in which case the
+ *   registers were already saved by the context-switch code when
+ *   the task scheduled out - we only have to initialize the registers
+ *   if they've never been initialized.
  *
  * If the task has used the FPU before then save it.
  */
-void fpu__activate_fpstate_read(struct fpu *fpu)
+void fpu__prepare_read(struct fpu *fpu)
 {
-	/*
-	 * If fpregs are active (in the current CPU), then
-	 * copy them to the fpstate:
-	 */
-	if (fpu->fpregs_active) {
+	if (fpu == &current->thread.fpu) {
 		fpu__save(fpu);
 	} else {
-		if (!fpu->fpstate_active) {
+		if (!fpu->initialized) {
 			fpstate_init(&fpu->state);
 			trace_x86_fpu_init_state(fpu);
 
 			trace_x86_fpu_activate_state(fpu);
 			/* Safe to do for current and for stopped child tasks: */
-			fpu->fpstate_active = 1;
+			fpu->initialized = 1;
 		}
 	}
 }
@@ -283,17 +273,17 @@ void fpu__activate_fpstate_read(struct fpu *fpu)
 /*
  * This function must be called before we write a task's fpstate.
  *
- * If the task has used the FPU before then unlazy it.
+ * If the task has used the FPU before then invalidate any cached FPU registers.
  * If the task has not used the FPU before then initialize its fpstate.
  *
  * After this function call, after registers in the fpstate are
  * modified and the child task has woken up, the child task will
  * restore the modified FPU state from the modified context. If we
- * didn't clear its lazy status here then the lazy in-registers
+ * didn't clear its cached status here then the cached in-registers
  * state pending on its former CPU could be restored, corrupting
  * the modifications.
  */
-void fpu__activate_fpstate_write(struct fpu *fpu)
+void fpu__prepare_write(struct fpu *fpu)
 {
 	/*
 	 * Only stopped child tasks can be used to modify the FPU
@@ -301,8 +291,8 @@ void fpu__activate_fpstate_write(struct fpu *fpu)
 	 */
 	WARN_ON_FPU(fpu == &current->thread.fpu);
 
-	if (fpu->fpstate_active) {
-		/* Invalidate any lazy state: */
+	if (fpu->initialized) {
+		/* Invalidate any cached state: */
 		__fpu_invalidate_fpregs_state(fpu);
 	} else {
 		fpstate_init(&fpu->state);
@@ -310,74 +300,11 @@ void fpu__activate_fpstate_write(struct fpu *fpu)
 
 		trace_x86_fpu_activate_state(fpu);
 		/* Safe to do for stopped child tasks: */
-		fpu->fpstate_active = 1;
+		fpu->initialized = 1;
 	}
 }
 
 /*
- * This function must be called before we write the current
- * task's fpstate.
- *
- * This call gets the current FPU register state and moves
- * it in to the 'fpstate'.  Preemption is disabled so that
- * no writes to the 'fpstate' can occur from context
- * swiches.
- *
- * Must be followed by a fpu__current_fpstate_write_end().
- */
-void fpu__current_fpstate_write_begin(void)
-{
-	struct fpu *fpu = &current->thread.fpu;
-