Merge tag 'v4.9.144' into 4.9-2.3.x-imx

This is the 4.9.144 stable release

9 files changed, 12 insertions, 83 deletions

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index fbc1474960e3..c56c24347f15 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -104,7 +104,6 @@
 #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 */
-/* free, was #define X86_FEATURE_EAGER_FPU	( 3*32+29) * "eagerfpu" Non lazy FPU restore */
 #define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
@@ -214,6 +213,7 @@
 #define X86_FEATURE_STIBP	( 7*32+27) /* Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ZEN		( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
 #define X86_FEATURE_L1TF_PTEINV	( 7*32+29) /* "" L1TF workaround PTE inversion */
+#define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 8852e3afa1ad..499d6ed0e376 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -60,11 +60,6 @@ extern u64 fpu__get_supported_xfeatures_mask(void);
 /*
  * FPU related CPU feature flag helper routines:
  */
-static __always_inline __pure bool use_eager_fpu(void)
-{
-	return true;
-}
-
 static __always_inline __pure bool use_xsaveopt(void)
 {
 	return static_cpu_has(X86_FEATURE_XSAVEOPT);
@@ -501,24 +496,6 @@ static inline int fpu_want_lazy_restore(struct fpu *fpu, unsigned int cpu)
 }
 
 
-/*
- * Wrap lazy FPU TS handling in a 'hw fpregs activation/deactivation'
- * idiom, which is then paired with the sw-flag (fpregs_active) later on:
- */
-
-static inline void __fpregs_activate_hw(void)
-{
-	if (!use_eager_fpu())
-		clts();
-}
-
-static inline void __fpregs_deactivate_hw(void)
-{
-	if (!use_eager_fpu())
-		stts();
-}
-
-/* Must be paired with an 'stts' (fpregs_deactivate_hw()) after! */
 static inline void __fpregs_deactivate(struct fpu *fpu)
 {
 	WARN_ON_FPU(!fpu->fpregs_active);
@@ -528,7 +505,6 @@ static inline void __fpregs_deactivate(struct fpu *fpu)
 	trace_x86_fpu_regs_deactivated(fpu);
 }
 
-/* Must be paired with a 'clts' (fpregs_activate_hw()) before! */
 static inline void __fpregs_activate(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu->fpregs_active);
@@ -554,22 +530,17 @@ static inline int fpregs_active(void)
 }
 
 /*
- * Encapsulate the CR0.TS handling together with the
- * software flag.
- *
  * These generally need preemption protection to work,
  * do try to avoid using these on their own.
  */
 static inline void fpregs_activate(struct fpu *fpu)
 {
-	__fpregs_activate_hw();
 	__fpregs_activate(fpu);
 }
 
 static inline void fpregs_deactivate(struct fpu *fpu)
 {
 	__fpregs_deactivate(fpu);
-	__fpregs_deactivate_hw();
 }
 
 /*
@@ -596,8 +567,7 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
 	 * or if the past 5 consecutive context-switches used math.
 	 */
 	fpu.preload = static_cpu_has(X86_FEATURE_FPU) &&
-		      new_fpu->fpstate_active &&
-		      (use_eager_fpu() || new_fpu->counter > 5);
+		      new_fpu->fpstate_active;
 
 	if (old_fpu->fpregs_active) {
 		if (!copy_fpregs_to_fpstate(old_fpu))
@@ -611,18 +581,13 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
 
 		/* Don't change CR0.TS if we just switch! */
 		if (fpu.preload) {
-			new_fpu->counter++;
 			__fpregs_activate(new_fpu);
 			trace_x86_fpu_regs_activated(new_fpu);
 			prefetch(&new_fpu->state);
-		} else {
-			__fpregs_deactivate_hw();
 		}
 	} else {
-		old_fpu->counter = 0;
 		old_fpu->last_cpu = -1;
 		if (fpu.preload) {
-			new_fpu->counter++;
 			if (fpu_want_lazy_restore(new_fpu, cpu))
 				fpu.preload = 0;
 			else
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 48df486b02f9..3c80f5b9c09d 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -322,17 +322,6 @@ struct fpu {
 	unsigned char			fpregs_active;
 
 	/*
-	 * @counter:
-	 *
-	 * This counter contains the number of consecutive context switches
-	 * during which the FPU stays used. If this is over a threshold, the
-	 * lazy FPU restore logic becomes eager, to save the trap overhead.
-	 * This is an unsigned char so that after 256 iterations the counter
-	 * wraps and the context switch behavior turns lazy again; this is to
-	 * deal with bursty apps that only use the FPU for a short time:
-	 */
-	unsigned char			counter;
-	/*
 	 * @state:
 	 *
 	 * In-memory copy of all FPU registers that we save/restore
@@ -340,29 +329,6 @@ struct fpu {
 	 * the registers in the FPU are more recent than this state
 	 * copy. If the task context-switches away then they get
 	 * saved here and represent the FPU state.
-	 *
-	 * After context switches there may be a (short) time period
-	 * during which the in-FPU hardware registers are unchanged
-	 * and still perfectly match this state, if the tasks
-	 * scheduled afterwards are not using the FPU.
-	 *
-	 * This is the 'lazy restore' window of optimization, which
-	 * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'.
-	 *
-	 * We detect whether a subsequent task uses the FPU via setting
-	 * CR0::TS to 1, which causes any FPU use to raise a #NM fault.
-	 *
-	 * During this window, if the task gets scheduled again, we
-	 * might be able to skip having to do a restore from this
-	 * memory buffer to the hardware registers - at the cost of
-	 * incurring the overhead of #NM fault traps.
-	 *
-	 * Note that on modern CPUs that support the XSAVEOPT (or other
-	 * optimized XSAVE instructions), we don't use #NM traps anymore,
-	 * as the hardware can track whether FPU registers need saving
-	 * or not. On such CPUs we activate the non-lazy ('eagerfpu')
-	 * logic, which unconditionally saves/restores all FPU state
-	 * across context switches. (if FPU state exists.)
 	 */
 	union fpregs_state		state;
 	/*
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 8b38df98548e..1b4132161c1f 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -215,6 +215,7 @@ enum spectre_v2_mitigation {
 	SPECTRE_V2_RETPOLINE_GENERIC,
 	SPECTRE_V2_RETPOLINE_AMD,
 	SPECTRE_V2_IBRS,
+	SPECTRE_V2_IBRS_ENHANCED,
 };
 
 /* The Speculative Store Bypass disable variants */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 84f58de08c2b..2cb5d0f13641 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -184,22 +184,22 @@ do {									\
 	typeof(var) pfo_ret__;				\
 	switch (sizeof(var)) {				\
 	case 1:						\
-		asm(op "b "__percpu_arg(1)",%0"		\
+		asm volatile(op "b "__percpu_arg(1)",%0"\
 		    : "=q" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 2:						\
-		asm(op "w "__percpu_arg(1)",%0"		\
+		asm volatile(op "w "__percpu_arg(1)",%0"\
 		    : "=r" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 4:						\
-		asm(op "l "__percpu_arg(1)",%0"		\
+		asm volatile(op "l "__percpu_arg(1)",%0"\
 		    : "=r" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 8:						\
-		asm(op "q "__percpu_arg(1)",%0"		\
+		asm volatile(op "q "__percpu_arg(1)",%0"\
 		    : "=r" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index dfdb7e21ba56..93d089c9509a 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -134,7 +134,7 @@
  */
 #define _PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |		\
 			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |	\
-			 _PAGE_SOFT_DIRTY)
+			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
 #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
 
 /* The ASID is the lower 12 bits of CR3 */
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 6136a18152af..2bd96b4df140 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -42,8 +42,7 @@ struct saved_context {
 	set_debugreg((thread)->debugreg##register, register)
 
 /* routines for saving/restoring kernel state */
-extern int acpi_save_state_mem(void);
-extern char core_restore_code;
-extern char restore_registers;
+extern char core_restore_code[];
+extern char restore_registers[];
 
 #endif /* _ASM_X86_SUSPEND_64_H */
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
index 9217ab1f5bf6..342e59789fcd 100644
--- a/arch/x86/include/asm/trace/fpu.h
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -14,7 +14,6 @@ DECLARE_EVENT_CLASS(x86_fpu,
 		__field(struct fpu *, fpu)
 		__field(bool, fpregs_active)
 		__field(bool, fpstate_active)
-		__field(int, counter)
 		__field(u64, xfeatures)
 		__field(u64, xcomp_bv)
 		),
@@ -23,17 +22,15 @@ DECLARE_EVENT_CLASS(x86_fpu,
 		__entry->fpu		= fpu;
 		__entry->fpregs_active	= fpu->fpregs_active;
 		__entry->fpstate_active	= fpu->fpstate_active;
-		__entry->counter	= fpu->counter;
 		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 counter: %d xfeatures: %llx xcomp_bv: %llx",
+	TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d xfeatures: %llx xcomp_bv: %llx",
 			__entry->fpu,
 			__entry->fpregs_active,
 			__entry->fpstate_active,
-			__entry->counter,
 			__entry->xfeatures,
 			__entry->xcomp_bv
 	)
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 739c0c594022..1bb90fafcdc3 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -356,5 +356,6 @@ struct kvm_sync_regs {
 
 #define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
 #define KVM_X86_QUIRK_CD_NW_CLEARED	(1 << 1)
+#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE	(1 << 2)
 
 #endif /* _ASM_X86_KVM_H */