Merge tag 'v5.8-rc6' into x86/cpu, to refresh the branch before adding new commits

Signed-off-by: Ingo Molnar <mingo@kernel.org>

15 files changed, 94 insertions, 52 deletions

diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 35460fef39b8..0367efdc5b7a 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -201,12 +201,8 @@ arch_test_and_change_bit(long nr, volatile unsigned long *addr)
 	return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr);
 }
 
-static __no_kcsan_or_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
+static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
 {
-	/*
-	 * Because this is a plain access, we need to disable KCSAN here to
-	 * avoid double instrumentation via instrumented bitops.
-	 */
 	return ((1UL << (nr & (BITS_PER_LONG-1))) &
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index fb34ff641e0a..028189575560 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -75,6 +75,12 @@ do {								\
 	unreachable();						\
 } while (0)
 
+/*
+ * This instrumentation_begin() is strictly speaking incorrect; but it
+ * suppresses the complaints from WARN()s in noinstr code. If such a WARN()
+ * were to trigger, we'd rather wreck the machine in an attempt to get the
+ * message out than not know about it.
+ */
 #define __WARN_FLAGS(flags)					\
 do {								\
 	instrumentation_begin();				\
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index dd17c2da1af5..da78ccbd493b 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -58,4 +58,9 @@ static inline bool handle_guest_split_lock(unsigned long ip)
 	return false;
 }
 #endif
+#ifdef CONFIG_IA32_FEAT_CTL
+void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
+#else
+static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {}
+#endif
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
index 6722ffcef2e6..3afa990d756b 100644
--- a/arch/x86/include/asm/cpumask.h
+++ b/arch/x86/include/asm/cpumask.h
@@ -11,5 +11,23 @@ extern cpumask_var_t cpu_sibling_setup_mask;
 
 extern void setup_cpu_local_masks(void);
 
+/*
+ * NMI and MCE exceptions need cpu_is_offline() _really_ early,
+ * provide an arch_ special for them to avoid instrumentation.
+ */
+#if NR_CPUS > 1
+static __always_inline bool arch_cpu_online(int cpu)
+{
+	return arch_test_bit(cpu, cpumask_bits(cpu_online_mask));
+}
+#else
+static __always_inline bool arch_cpu_online(int cpu)
+{
+	return cpu == 0;
+}
+#endif
+
+#define arch_cpu_is_offline(cpu)	unlikely(!arch_cpu_online(cpu))
+
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_CPUMASK_H */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 42159f45bf9c..845e7481ab77 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -623,6 +623,11 @@ static inline void switch_fpu_finish(struct fpu *new_fpu)
  * MXCSR and XCR definitions:
  */
 
+static inline void ldmxcsr(u32 mxcsr)
+{
+	asm volatile("ldmxcsr %0" :: "m" (mxcsr));
+}
+
 extern unsigned int mxcsr_feature_mask;
 
 #define XCR_XFEATURE_ENABLED_MASK	0x00000000
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index cf51c50eb356..80d3b30d3ee3 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -353,10 +353,6 @@ static __always_inline void __##func(struct pt_regs *regs)
 
 #else	/* CONFIG_X86_64 */
 
-/* Maps to a regular IDTENTRY on 32bit for now */
-# define DECLARE_IDTENTRY_IST		DECLARE_IDTENTRY
-# define DEFINE_IDTENTRY_IST		DEFINE_IDTENTRY
-
 /**
  * DECLARE_IDTENTRY_DF - Declare functions for double fault 32bit variant
  * @vector:	Vector number (ignored for C)
@@ -387,28 +383,18 @@ __visible noinstr void func(struct pt_regs *regs,			\
 #endif	/* !CONFIG_X86_64 */
 
 /* C-Code mapping */
+#define DECLARE_IDTENTRY_NMI		DECLARE_IDTENTRY_RAW
+#define DEFINE_IDTENTRY_NMI		DEFINE_IDTENTRY_RAW
+
+#ifdef CONFIG_X86_64
 #define DECLARE_IDTENTRY_MCE		DECLARE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_MCE		DEFINE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_MCE_USER	DEFINE_IDTENTRY_NOIST
 
-#define DECLARE_IDTENTRY_NMI		DECLARE_IDTENTRY_RAW
-#define DEFINE_IDTENTRY_NMI		DEFINE_IDTENTRY_RAW
-
 #define DECLARE_IDTENTRY_DEBUG		DECLARE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_DEBUG		DEFINE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_DEBUG_USER	DEFINE_IDTENTRY_NOIST
-
-/**
- * DECLARE_IDTENTRY_XEN - Declare functions for XEN redirect IDT entry points
- * @vector:	Vector number (ignored for C)
- * @func:	Function name of the entry point
- *
- * Used for xennmi and xendebug redirections. No DEFINE as this is all ASM
- * indirection magic.
- */
-#define DECLARE_IDTENTRY_XEN(vector, func)				\
-	asmlinkage void xen_asm_exc_xen##func(void);			\
-	asmlinkage void asm_exc_xen##func(void)
+#endif
 
 #else /* !__ASSEMBLY__ */
 
@@ -455,9 +441,6 @@ __visible noinstr void func(struct pt_regs *regs,			\
 # define DECLARE_IDTENTRY_MCE(vector, func)				\
 	DECLARE_IDTENTRY(vector, func)
 
-# define DECLARE_IDTENTRY_DEBUG(vector, func)				\
-	DECLARE_IDTENTRY(vector, func)
-
 /* No ASM emitted for DF as this goes through a C shim */
 # define DECLARE_IDTENTRY_DF(vector, func)
 
@@ -469,10 +452,6 @@ __visible noinstr void func(struct pt_regs *regs,			\
 /* No ASM code emitted for NMI */
 #define DECLARE_IDTENTRY_NMI(vector, func)
 
-/* XEN NMI and DB wrapper */
-#define DECLARE_IDTENTRY_XEN(vector, func)				\
-	idtentry vector asm_exc_xen##func exc_##func has_error_code=0
-
 /*
  * ASM code to emit the common vector entry stubs where each stub is
  * packed into 8 bytes.
@@ -490,16 +469,15 @@ __visible noinstr void func(struct pt_regs *regs,			\
 	.align 8
 SYM_CODE_START(irq_entries_start)
     vector=FIRST_EXTERNAL_VECTOR
-    pos = .
     .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
 	UNWIND_HINT_IRET_REGS
+0 :
 	.byte	0x6a, vector
 	jmp	asm_common_interrupt
 	nop
 	/* Ensure that the above is 8 bytes max */
-	. = pos + 8
-    pos=pos+8
-    vector=vector+1
+	. = 0b + 8
+	vector = vector+1
     .endr
 SYM_CODE_END(irq_entries_start)
 
@@ -507,16 +485,15 @@ SYM_CODE_END(irq_entries_start)
 	.align 8
 SYM_CODE_START(spurious_entries_start)
     vector=FIRST_SYSTEM_VECTOR
-    pos = .
     .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR)
 	UNWIND_HINT_IRET_REGS
+0 :
 	.byte	0x6a, vector
 	jmp	asm_spurious_interrupt
 	nop
 	/* Ensure that the above is 8 bytes max */
-	. = pos + 8
-    pos=pos+8
-    vector=vector+1
+	. = 0b + 8
+	vector = vector+1
     .endr
 SYM_CODE_END(spurious_entries_start)
 #endif
@@ -565,16 +542,28 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_BP,		exc_int3);
 DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_PF,	exc_page_fault);
 
 #ifdef CONFIG_X86_MCE
+#ifdef CONFIG_X86_64
 DECLARE_IDTENTRY_MCE(X86_TRAP_MC,	exc_machine_check);
+#else
+DECLARE_IDTENTRY_RAW(X86_TRAP_MC,	exc_machine_check);
+#endif
 #endif
 
 /* NMI */
 DECLARE_IDTENTRY_NMI(X86_TRAP_NMI,	exc_nmi);
-DECLARE_IDTENTRY_XEN(X86_TRAP_NMI,	nmi);
+#if defined(CONFIG_XEN_PV) && defined(CONFIG_X86_64)
+DECLARE_IDTENTRY_RAW(X86_TRAP_NMI,	xenpv_exc_nmi);
+#endif
 
 /* #DB */
+#ifdef CONFIG_X86_64
 DECLARE_IDTENTRY_DEBUG(X86_TRAP_DB,	exc_debug);
-DECLARE_IDTENTRY_XEN(X86_TRAP_DB,	debug);
+#else
+DECLARE_IDTENTRY_RAW(X86_TRAP_DB,	exc_debug);
+#endif
+#if defined(CONFIG_XEN_PV) && defined(CONFIG_X86_64)
+DECLARE_IDTENTRY_RAW(X86_TRAP_DB,	xenpv_exc_debug);
+#endif
 
 /* #DF */
 DECLARE_IDTENTRY_DF(X86_TRAP_DF,	exc_double_fault);
@@ -635,8 +624,8 @@ DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR,	sysvec_kvm_posted_intr_nested
 
 #if IS_ENABLED(CONFIG_HYPERV)
 DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR,	sysvec_hyperv_callback);
-DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_REENLIGHTENMENT_VECTOR,	sysvec_hyperv_reenlightenment);
-DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_STIMER0_VECTOR,	sysvec_hyperv_stimer0);
+DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR,	sysvec_hyperv_reenlightenment);
+DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR,	sysvec_hyperv_stimer0);
 #endif
 
 #if IS_ENABLED(CONFIG_ACRN_GUEST)
diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h
index ac1a99ffbd8d..7f080f5c7def 100644
--- a/arch/x86/include/asm/io_bitmap.h
+++ b/arch/x86/include/asm/io_bitmap.h
@@ -19,12 +19,28 @@ struct task_struct;
 void io_bitmap_share(struct task_struct *tsk);
 void io_bitmap_exit(struct task_struct *tsk);
 
+static inline void native_tss_invalidate_io_bitmap(void)
+{
+	/*
+	 * Invalidate the I/O bitmap by moving io_bitmap_base outside the
+	 * TSS limit so any subsequent I/O access from user space will
+	 * trigger a #GP.
+	 *
+	 * This is correct even when VMEXIT rewrites the TSS limit
+	 * to 0x67 as the only requirement is that the base points
+	 * outside the limit.
+	 */
+	this_cpu_write(cpu_tss_rw.x86_tss.io_bitmap_base,
+		       IO_BITMAP_OFFSET_INVALID);
+}
+
 void native_tss_update_io_bitmap(void);
 
 #ifdef CONFIG_PARAVIRT_XXL
 #include <asm/paravirt.h>
 #else
 #define tss_update_io_bitmap native_tss_update_io_bitmap
+#define tss_invalidate_io_bitmap native_tss_invalidate_io_bitmap
 #endif
 
 #else
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f8998e97457f..be5363b21540 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -943,7 +943,7 @@ struct kvm_arch {
 	atomic_t vapics_in_nmi_mode;
 	struct mutex apic_map_lock;
 	struct kvm_apic_map *apic_map;
-	bool apic_map_dirty;
+	atomic_t apic_map_dirty;
 
 	bool apic_access_page_done;
 	unsigned long apicv_inhibit_reasons;
@@ -1220,7 +1220,7 @@ struct kvm_x86_ops {
 	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
 					   struct kvm_memory_slot *slot,
 					   gfn_t offset, unsigned long mask);
-	int (*write_log_dirty)(struct kvm_vcpu *vcpu);
+	int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 73d997aa2966..e039a933aca3 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -25,8 +25,6 @@
 #define TPAUSE_C01_STATE		1
 #define TPAUSE_C02_STATE		0
 
-u32 get_umwait_control_msr(void);
-
 static inline void __monitor(const void *eax, unsigned long ecx,
 			     unsigned long edx)
 {
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 5ca5d297df75..3d2afecde50c 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -302,6 +302,11 @@ static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g)
 }
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+static inline void tss_invalidate_io_bitmap(void)
+{
+	PVOP_VCALL0(cpu.invalidate_io_bitmap);
+}
+
 static inline void tss_update_io_bitmap(void)
 {
 	PVOP_VCALL0(cpu.update_io_bitmap);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 732f62e04ddb..8dfcb2508e6d 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -141,6 +141,7 @@ struct pv_cpu_ops {
 	void (*load_sp0)(unsigned long sp0);
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+	void (*invalidate_io_bitmap)(void);
 	void (*update_io_bitmap)(void);
 #endif
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 2da1f95b88d7..816b31c68550 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -194,6 +194,7 @@ enum page_cache_mode {
 #define _PAGE_TABLE_NOENC	 (__PP|__RW|_USR|___A|   0|___D|   0|   0)
 #define _PAGE_TABLE		 (__PP|__RW|_USR|___A|   0|___D|   0|   0| _ENC)
 #define __PAGE_KERNEL_RO	 (__PP|   0|   0|___A|__NX|___D|   0|___G)
+#define __PAGE_KERNEL_ROX	 (__PP|   0|   0|___A|   0|___D|   0|___G)
 #define __PAGE_KERNEL_NOCACHE	 (__PP|__RW|   0|___A|__NX|___D|   0|___G| __NC)
 #define __PAGE_KERNEL_VVAR	 (__PP|   0|_USR|___A|__NX|___D|   0|___G)
 #define __PAGE_KERNEL_LARGE	 (__PP|__RW|   0|___A|__NX|___D|_PSE|___G)
@@ -219,6 +220,7 @@ enum page_cache_mode {
 #define PAGE_KERNEL_RO		__pgprot_mask(__PAGE_KERNEL_RO         | _ENC)
 #define PAGE_KERNEL_EXEC	__pgprot_mask(__PAGE_KERNEL_EXEC       | _ENC)
 #define PAGE_KERNEL_EXEC_NOENC	__pgprot_mask(__PAGE_KERNEL_EXEC       |    0)
+#define PAGE_KERNEL_ROX		__pgprot_mask(__PAGE_KERNEL_ROX        | _ENC)
 #define PAGE_KERNEL_NOCACHE	__pgprot_mask(__PAGE_KERNEL_NOCACHE    | _ENC)
 #define PAGE_KERNEL_LARGE	__pgprot_mask(__PAGE_KERNEL_LARGE      | _ENC)
 #define PAGE_KERNEL_LARGE_EXEC	__pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 42cd333616c4..03b7c4ca425a 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -370,7 +370,7 @@ struct x86_hw_tss {
 #define IO_BITMAP_OFFSET_INVALID	(__KERNEL_TSS_LIMIT + 1)
 
 struct entry_stack {
-	unsigned long		words[64];
+	char	stack[PAGE_SIZE];
 };
 
 struct entry_stack_page {
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index ebedeab48704..255b2dde2c1b 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -278,7 +278,7 @@ static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs
 }
 
 /* To avoid include hell, we can't include uaccess.h */
-extern long probe_kernel_read(void *dst, const void *src, size_t size);
+extern long copy_from_kernel_nofault(void *dst, const void *src, size_t size);
 
 /**
  * regs_get_kernel_stack_nth() - get Nth entry of the stack
@@ -298,7 +298,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 
 	addr = regs_get_kernel_stack_nth_addr(regs, n);
 	if (addr) {
-		ret = probe_kernel_read(&val, addr, sizeof(val));
+		ret = copy_from_kernel_nofault(&val, addr, sizeof(val));
 		if (!ret)
 			return val;
 	}
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 17c5a038f42d..0780f97c1850 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -408,14 +408,15 @@ struct kvm_vmx_nested_state_data {
 };
 
 struct kvm_vmx_nested_state_hdr {
-	__u32 flags;
 	__u64 vmxon_pa;
 	__u64 vmcs12_pa;
-	__u64 preemption_timer_deadline;
 
 	struct {
 		__u16 flags;
 	} smm;
+
+	__u32 flags;
+	__u64 preemption_timer_deadline;
 };
 
 struct kvm_svm_nested_state_data {