Merge tag 'please-pull-cmci_rediscover' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras into x86/ras

Pull clean up of the cmci_rediscover code to fix problems found by Dave Jones,
from Tony Luck.

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

13 files changed, 71 insertions, 80 deletions

diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index d3ddd17405d0..5a6d2873f80e 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -77,6 +77,7 @@ struct arch_specific_insn {
 	 * a post_handler or break_handler).
 	 */
 	int boostable;
+	bool if_modifier;
 };
 
 struct arch_optimized_insn {
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 635a74d22409..4979778cc7fb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -414,8 +414,8 @@ struct kvm_vcpu_arch {
 	gpa_t time;
 	struct pvclock_vcpu_time_info hv_clock;
 	unsigned int hw_tsc_khz;
-	unsigned int time_offset;
-	struct page *time_page;
+	struct gfn_to_hva_cache pv_time;
+	bool pv_time_enabled;
 	/* set guest stopped flag in pvclock flags field */
 	bool pvclock_set_guest_stopped_request;
 
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index f4076af1f4ed..fa5f71e021d5 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -146,13 +146,13 @@ DECLARE_PER_CPU(struct device *, mce_device);
 void mce_intel_feature_init(struct cpuinfo_x86 *c);
 void cmci_clear(void);
 void cmci_reenable(void);
-void cmci_rediscover(int dying);
+void cmci_rediscover(void);
 void cmci_recheck(void);
 #else
 static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
 static inline void cmci_clear(void) {}
 static inline void cmci_reenable(void) {}
-static inline void cmci_rediscover(int dying) {}
+static inline void cmci_rediscover(void) {}
 static inline void cmci_recheck(void) {}
 #endif
 
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index c20d1ce62dc6..e709884d0ef9 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -382,14 +382,14 @@ HYPERVISOR_console_io(int cmd, int count, char *str)
 	return _hypercall3(int, console_io, cmd, count, str);
 }
 
-extern int __must_check HYPERVISOR_physdev_op_compat(int, void *);
+extern int __must_check xen_physdev_op_compat(int, void *);
 
 static inline int
 HYPERVISOR_physdev_op(int cmd, void *arg)
 {
 	int rc = _hypercall2(int, physdev_op, cmd, arg);
 	if (unlikely(rc == -ENOSYS))
-		rc = HYPERVISOR_physdev_op_compat(cmd, arg);
+		rc = xen_physdev_op_compat(cmd, arg);
 	return rc;
 }
 
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index 892ce40a7470..7a060f4b411f 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -44,6 +44,7 @@
 #define SNB_C1_AUTO_UNDEMOTE		(1UL << 27)
 #define SNB_C3_AUTO_UNDEMOTE		(1UL << 28)
 
+#define MSR_PLATFORM_INFO		0x000000ce
 #define MSR_MTRRcap			0x000000fe
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 7bc126346ace..9239504b41cb 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2358,7 +2358,7 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 
 	if (action == CPU_POST_DEAD) {
 		/* intentionally ignoring frozen here */
-		cmci_rediscover(cpu);
+		cmci_rediscover();
 	}
 
 	return NOTIFY_OK;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 402c454fbff0..ae1697c2afe3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -285,39 +285,24 @@ void cmci_clear(void)
 	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
-static long cmci_rediscover_work_func(void *arg)
+static void cmci_rediscover_work_func(void *arg)
 {
 	int banks;
 
 	/* Recheck banks in case CPUs don't all have the same */
 	if (cmci_supported(&banks))
 		cmci_discover(banks);
-
-	return 0;
 }
 
-/*
- * After a CPU went down cycle through all the others and rediscover
- * Must run in process context.
- */
-void cmci_rediscover(int dying)
+/* After a CPU went down cycle through all the others and rediscover */
+void cmci_rediscover(void)
 {
-	int cpu, banks;
+	int banks;
 
 	if (!cmci_supported(&banks))
 		return;
 
-	for_each_online_cpu(cpu) {
-		if (cpu == dying)
-			continue;
-
-		if (cpu == smp_processor_id()) {
-			cmci_rediscover_work_func(NULL);
-			continue;
-		}
-
-		work_on_cpu(cpu, cmci_rediscover_work_func, NULL);
-	}
+	on_each_cpu(cmci_rediscover_work_func, NULL, 1);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 529c8931fc02..dab7580c47ae 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -101,6 +101,10 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly =
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */
+	INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */
+	INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
+	INTEL_UEVENT_CONSTRAINT(0x06a3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
 	INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 3f06e6149981..7bfe318d3d8a 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -375,6 +375,9 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p)
 	else
 		p->ainsn.boostable = -1;
 
+	/* Check whether the instruction modifies Interrupt Flag or not */
+	p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn);
+
 	/* Also, displacement change doesn't affect the first byte */
 	p->opcode = p->ainsn.insn[0];
 }
@@ -434,7 +437,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 	__this_cpu_write(current_kprobe, p);
 	kcb->kprobe_saved_flags = kcb->kprobe_old_flags
 		= (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
-	if (is_IF_modifier(p->ainsn.insn))
+	if (p->ainsn.if_modifier)
 		kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF;
 }
 
diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c
index 7890bc838952..d893e8ed8ac9 100644
--- a/arch/x86/kernel/microcode_intel_early.c
+++ b/arch/x86/kernel/microcode_intel_early.c
@@ -90,13 +90,13 @@ microcode_phys(struct microcode_intel **mc_saved_tmp,
 	struct microcode_intel ***mc_saved;
 
 	mc_saved = (struct microcode_intel ***)
-		   __pa_symbol(&mc_saved_data->mc_saved);
+		   __pa_nodebug(&mc_saved_data->mc_saved);
 	for (i = 0; i < mc_saved_data->mc_saved_count; i++) {
 		struct microcode_intel *p;
 
 		p = *(struct microcode_intel **)
-			__pa(mc_saved_data->mc_saved + i);
-		mc_saved_tmp[i] = (struct microcode_intel *)__pa(p);
+			__pa_nodebug(mc_saved_data->mc_saved + i);
+		mc_saved_tmp[i] = (struct microcode_intel *)__pa_nodebug(p);
 	}
 }
 #endif
@@ -562,7 +562,7 @@ scan_microcode(unsigned long start, unsigned long end,
 	struct cpio_data cd;
 	long offset = 0;
 #ifdef CONFIG_X86_32
-	char *p = (char *)__pa_symbol(ucode_name);
+	char *p = (char *)__pa_nodebug(ucode_name);
 #else
 	char *p = ucode_name;
 #endif
@@ -630,8 +630,8 @@ static void __cpuinit print_ucode(struct ucode_cpu_info *uci)
 	if (mc_intel == NULL)
 		return;
 
-	delay_ucode_info_p = (int *)__pa_symbol(&delay_ucode_info);
-	current_mc_date_p = (int *)__pa_symbol(&current_mc_date);
+	delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info);
+	current_mc_date_p = (int *)__pa_nodebug(&current_mc_date);
 
 	*delay_ucode_info_p = 1;
 	*current_mc_date_p = mc_intel->hdr.date;
@@ -659,8 +659,8 @@ static inline void __cpuinit print_ucode(struct ucode_cpu_info *uci)
 }
 #endif
 
-static int apply_microcode_early(struct mc_saved_data *mc_saved_data,
-				 struct ucode_cpu_info *uci)
+static int __cpuinit apply_microcode_early(struct mc_saved_data *mc_saved_data,
+					   struct ucode_cpu_info *uci)
 {
 	struct microcode_intel *mc_intel;
 	unsigned int val[2];
@@ -741,15 +741,15 @@ load_ucode_intel_bsp(void)
 #ifdef CONFIG_X86_32
 	struct boot_params *boot_params_p;
 
-	boot_params_p = (struct boot_params *)__pa_symbol(&boot_params);
+	boot_params_p = (struct boot_params *)__pa_nodebug(&boot_params);
 	ramdisk_image = boot_params_p->hdr.ramdisk_image;
 	ramdisk_size  = boot_params_p->hdr.ramdisk_size;
 	initrd_start_early = ramdisk_image;
 	initrd_end_early = initrd_start_early + ramdisk_size;
 
 	_load_ucode_intel_bsp(
-		(struct mc_saved_data *)__pa_symbol(&mc_saved_data),
-		(unsigned long *)__pa_symbol(&mc_saved_in_initrd),
+		(struct mc_saved_data *)__pa_nodebug(&mc_saved_data),
+		(unsigned long *)__pa_nodebug(&mc_saved_in_initrd),
 		initrd_start_early, initrd_end_early, &uci);
 #else
 	ramdisk_image = boot_params.hdr.ramdisk_image;
@@ -772,10 +772,10 @@ void __cpuinit load_ucode_intel_ap(void)
 	unsigned long *initrd_start_p;
 
 	mc_saved_in_initrd_p =
-		(unsigned long *)__pa_symbol(mc_saved_in_initrd);
-	mc_saved_data_p = (struct mc_saved_data *)__pa_symbol(&mc_saved_data);
-	initrd_start_p = (unsigned long *)__pa_symbol(&initrd_start);
-	initrd_start_addr = (unsigned long)__pa_symbol(*initrd_start_p);
+		(unsigned long *)__pa_nodebug(mc_saved_in_initrd);
+	mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data);
+	initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
+	initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p);
 #else
 	mc_saved_data_p = &mc_saved_data;
 	mc_saved_in_initrd_p = mc_saved_in_initrd;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f71500af1f81..f19ac0aca60d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1406,25 +1406,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	unsigned long flags, this_tsc_khz;
 	struct kvm_vcpu_arch *vcpu = &v->arch;
 	struct kvm_arch *ka = &v->kvm->arch;
-	void *shared_kaddr;
 	s64 kernel_ns, max_kernel_ns;
 	u64 tsc_timestamp, host_tsc;
-	struct pvclock_vcpu_time_info *guest_hv_clock;
+	struct pvclock_vcpu_time_info guest_hv_clock;
 	u8 pvclock_flags;
 	bool use_master_clock;
 
 	kernel_ns = 0;
 	host_tsc = 0;
 
-	/* Keep irq disabled to prevent changes to the clock */
-	local_irq_save(flags);
-	this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
-	if (unlikely(this_tsc_khz == 0)) {
-		local_irq_restore(flags);
-		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
-		return 1;
-	}
-
 	/*
 	 * If the host uses TSC clock, then passthrough TSC as stable
 	 * to the guest.
@@ -1436,6 +1426,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 		kernel_ns = ka->master_kernel_ns;
 	}
 	spin_unlock(&ka->pvclock_gtod_sync_lock);
+
+	/* Keep irq disabled to prevent changes to the clock */
+	local_irq_save(flags);
+	this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
+	if (unlikely(this_tsc_khz == 0)) {
+		local_irq_restore(flags);
+		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
+		return 1;
+	}
 	if (!use_master_clock) {
 		host_tsc = native_read_tsc();
 		kernel_ns = get_kernel_ns();
@@ -1463,7 +1462,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	local_irq_restore(flags);
 
-	if (!vcpu->time_page)
+	if (!vcpu->pv_time_enabled)
 		return 0;
 
 	/*
@@ -1525,12 +1524,12 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	 */
 	vcpu->hv_clock.version += 2;
 
-	shared_kaddr = kmap_atomic(vcpu->time_page);
-
-	guest_hv_clock = shared_kaddr + vcpu->time_offset;
+	if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
+		&guest_hv_clock, sizeof(guest_hv_clock))))
+		return 0;
 
 	/* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
-	pvclock_flags = (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED);
+	pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
 
 	if (vcpu->pvclock_set_guest_stopped_request) {
 		pvclock_flags |= PVCLOCK_GUEST_STOPPED;
@@ -1543,12 +1542,9 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	vcpu->hv_clock.flags = pvclock_flags;
 
-	memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
-	       sizeof(vcpu->hv_clock));
-
-	kunmap_atomic(shared_kaddr);
-
-	mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
+	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+				&vcpu->hv_clock,
+				sizeof(vcpu->hv_clock));
 	return 0;
 }
 
@@ -1837,10 +1833,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 
 static void kvmclock_reset(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.time_page) {
-		kvm_release_page_dirty(vcpu->arch.time_page);
-		vcpu->arch.time_page = NULL;
-	}
+	vcpu->arch.pv_time_enabled = false;
 }
 
 static void accumulate_steal_time(struct kvm_vcpu *vcpu)
@@ -1947,6 +1940,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_KVM_SYSTEM_TIME_NEW:
 	case MSR_KVM_SYSTEM_TIME: {
+		u64 gpa_offset;
 		kvmclock_reset(vcpu);
 
 		vcpu->arch.time = data;
@@ -1956,14 +1950,17 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!(data & 1))
 			break;
 
-		/* ...but clean it before doing the actual write */
-		vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
+		gpa_offset = data & ~(PAGE_MASK | 1);
 
-		vcpu->arch.time_page =
-				gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
+		/* Check that the address is 32-byte aligned. */
+		if (gpa_offset & (sizeof(struct pvclock_vcpu_time_info) - 1))
+			break;
 
-		if (is_error_page(vcpu->arch.time_page))
-			vcpu->arch.time_page = NULL;
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+		     &vcpu->arch.pv_time, data & ~1ULL))
+			vcpu->arch.pv_time_enabled = false;
+		else
+			vcpu->arch.pv_time_enabled = true;
 
 		break;
 	}
@@ -2967,7 +2964,7 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
  */
 static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->arch.time_page)
+	if (!vcpu->arch.pv_time_enabled)
 		return -EINVAL;
 	vcpu->arch.pvclock_set_guest_stopped_request = true;
 	kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -6718,6 +6715,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 		goto fail_free_wbinvd_dirty_mask;
 
 	vcpu->arch.ia32_tsc_adjust_msr = 0x0;
+	vcpu->arch.pv_time_enabled = false;
 	kvm_async_pf_hash_reset(vcpu);
 	kvm_pmu_init(vcpu);
 
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 05928aae911e..906fea315791 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -74,10 +74,10 @@ copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest)
 	char c;
 	unsigned zero_len;
 
-	for (; len; --len) {
+	for (; len; --len, to++) {
 		if (__get_user_nocheck(c, from++, sizeof(char)))
 			break;
-		if (__put_user_nocheck(c, to++, sizeof(char)))
+		if (__put_user_nocheck(c, to, sizeof(char)))
 			break;
 	}
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index e8e34938c57d..6afbb2ca9a0a 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1467,8 +1467,6 @@ static void __init xen_write_cr3_init(unsigned long cr3)
 	__xen_write_cr3(true, cr3);
 
 	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
-
-	pv_mmu_ops.write_cr3 = &xen_write_cr3;
 }
 #endif
 
@@ -2122,6 +2120,7 @@ static void __init xen_post_allocator_init(void)
 #endif
 
 #ifdef CONFIG_X86_64
+	pv_mmu_ops.write_cr3 = &xen_write_cr3;
 	SetPagePinned(virt_to_page(level3_user_vsyscall));
 #endif
 	xen_mark_init_mm_pinned();