Merge branch 'sched/urgent' into sched/core to pick up fixes

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

20 files changed, 127 insertions, 41 deletions

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 86a9bec18dab..bd3e8421b57c 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -115,7 +115,7 @@ static __initconst const u64 amd_hw_cache_event_ids
 /*
  * AMD Performance Monitor K7 and later.
  */
-static const u64 amd_perfmon_event_map[] =
+static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
 {
   [PERF_COUNT_HW_CPU_CYCLES]			= 0x0076,
   [PERF_COUNT_HW_INSTRUCTIONS]			= 0x00c0,
diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c
index 40625ca7a190..6011a573dd64 100644
--- a/arch/x86/events/amd/iommu.c
+++ b/arch/x86/events/amd/iommu.c
@@ -474,6 +474,7 @@ static __init int _init_perf_amd_iommu(
 
 static struct perf_amd_iommu __perf_iommu = {
 	.pmu = {
+		.task_ctx_nr    = perf_invalid_context,
 		.event_init	= perf_iommu_event_init,
 		.add		= perf_iommu_add,
 		.del		= perf_iommu_del,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 68fa55b4d42e..a6fd4dbcf820 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3637,8 +3637,11 @@ __init int intel_pmu_init(void)
 		pr_cont("Knights Landing events, ");
 		break;
 
+	case 142: /* 14nm Kabylake Mobile */
+	case 158: /* 14nm Kabylake Desktop */
 	case 78: /* 14nm Skylake Mobile */
 	case 94: /* 14nm Skylake Desktop */
+	case 85: /* 14nm Skylake Server */
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 6c3b7c1780c9..1ca5d1e7d4f2 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -63,7 +63,7 @@ static enum {
 
 #define LBR_PLM (LBR_KERNEL | LBR_USER)
 
-#define LBR_SEL_MASK	0x1ff	/* valid bits in LBR_SELECT */
+#define LBR_SEL_MASK	0x3ff	/* valid bits in LBR_SELECT */
 #define LBR_NOT_SUPP	-1	/* LBR filter not supported */
 #define LBR_IGN		0	/* ignored */
 
@@ -610,8 +610,10 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
 	 * The first 9 bits (LBR_SEL_MASK) in LBR_SELECT operate
 	 * in suppress mode. So LBR_SELECT should be set to
 	 * (~mask & LBR_SEL_MASK) | (mask & ~LBR_SEL_MASK)
+	 * But the 10th bit LBR_CALL_STACK does not operate
+	 * in suppress mode.
 	 */
-	reg->config = mask ^ x86_pmu.lbr_sel_mask;
+	reg->config = mask ^ (x86_pmu.lbr_sel_mask & ~LBR_CALL_STACK);
 
 	if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) &&
 	    (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) &&
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 6af7cf71d6b2..09a77dbc73c9 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -136,9 +136,21 @@ static int __init pt_pmu_hw_init(void)
 	struct dev_ext_attribute *de_attrs;
 	struct attribute **attrs;
 	size_t size;
+	u64 reg;
 	int ret;
 	long i;
 
+	if (boot_cpu_has(X86_FEATURE_VMX)) {
+		/*
+		 * Intel SDM, 36.5 "Tracing post-VMXON" says that
+		 * "IA32_VMX_MISC[bit 14]" being 1 means PT can trace
+		 * post-VMXON.
+		 */
+		rdmsrl(MSR_IA32_VMX_MISC, reg);
+		if (reg & BIT(14))
+			pt_pmu.vmx = true;
+	}
+
 	attrs = NULL;
 
 	for (i = 0; i < PT_CPUID_LEAVES; i++) {
@@ -269,20 +281,23 @@ static void pt_config(struct perf_event *event)
 
 	reg |= (event->attr.config & PT_CONFIG_MASK);
 
+	event->hw.config = reg;
 	wrmsrl(MSR_IA32_RTIT_CTL, reg);
 }
 
-static void pt_config_start(bool start)
+static void pt_config_stop(struct perf_event *event)
 {
-	u64 ctl;
+	u64 ctl = READ_ONCE(event->hw.config);
+
+	/* may be already stopped by a PMI */
+	if (!(ctl & RTIT_CTL_TRACEEN))
+		return;
 
-	rdmsrl(MSR_IA32_RTIT_CTL, ctl);
-	if (start)
-		ctl |= RTIT_CTL_TRACEEN;
-	else
-		ctl &= ~RTIT_CTL_TRACEEN;
+	ctl &= ~RTIT_CTL_TRACEEN;
 	wrmsrl(MSR_IA32_RTIT_CTL, ctl);
 
+	WRITE_ONCE(event->hw.config, ctl);
+
 	/*
 	 * A wrmsr that disables trace generation serializes other PT
 	 * registers and causes all data packets to be written to memory,
@@ -291,8 +306,7 @@ static void pt_config_start(bool start)
 	 * The below WMB, separating data store and aux_head store matches
 	 * the consumer's RMB that separates aux_head load and data load.
 	 */
-	if (!start)
-		wmb();
+	wmb();
 }
 
 static void pt_config_buffer(void *buf, unsigned int topa_idx,
@@ -942,11 +956,17 @@ void intel_pt_interrupt(void)
 	if (!ACCESS_ONCE(pt->handle_nmi))
 		return;
 
-	pt_config_start(false);
+	/*
+	 * If VMX is on and PT does not support it, don't touch anything.
+	 */
+	if (READ_ONCE(pt->vmx_on))
+		return;
 
 	if (!event)
 		return;
 
+	pt_config_stop(event);
+
 	buf = perf_get_aux(&pt->handle);
 	if (!buf)
 		return;
@@ -983,6 +1003,35 @@ void intel_pt_interrupt(void)
 	}
 }
 
+void intel_pt_handle_vmx(int on)
+{
+	struct pt *pt = this_cpu_ptr(&pt_ctx);
+	struct perf_event *event;
+	unsigned long flags;
+
+	/* PT plays nice with VMX, do nothing */
+	if (pt_pmu.vmx)
+		return;
+
+	/*
+	 * VMXON will clear RTIT_CTL.TraceEn; we need to make
+	 * sure to not try to set it while VMX is on. Disable
+	 * interrupts to avoid racing with pmu callbacks;
+	 * concurrent PMI should be handled fine.
+	 */
+	local_irq_save(flags);
+	WRITE_ONCE(pt->vmx_on, on);
+
+	if (on) {
+		/* prevent pt_config_stop() from writing RTIT_CTL */
+		event = pt->handle.event;
+		if (event)
+			event->hw.config = 0;
+	}
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(intel_pt_handle_vmx);
+
 /*
  * PMU callbacks
  */
@@ -992,6 +1041,9 @@ static void pt_event_start(struct perf_event *event, int mode)
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
 	struct pt_buffer *buf = perf_get_aux(&pt->handle);
 
+	if (READ_ONCE(pt->vmx_on))
+		return;
+
 	if (!buf || pt_buffer_is_full(buf, pt)) {
 		event->hw.state = PERF_HES_STOPPED;
 		return;
@@ -1014,7 +1066,8 @@ static void pt_event_stop(struct perf_event *event, int mode)
 	 * see comment in intel_pt_interrupt().
 	 */
 	ACCESS_ONCE(pt->handle_nmi) = 0;
-	pt_config_start(false);
+
+	pt_config_stop(event);
 
 	if (event->hw.state == PERF_HES_STOPPED)
 		return;
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index 336878a5d205..3abb5f5cccc8 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -65,6 +65,7 @@ enum pt_capabilities {
 struct pt_pmu {
 	struct pmu		pmu;
 	u32			caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
+	bool			vmx;
 };
 
 /**
@@ -107,10 +108,12 @@ struct pt_buffer {
  * struct pt - per-cpu pt context
  * @handle:	perf output handle
  * @handle_nmi:	do handle PT PMI on this cpu, there's an active event
+ * @vmx_on:	1 if VMX is ON on this cpu
  */
 struct pt {
 	struct perf_output_handle handle;
 	int			handle_nmi;
+	int			vmx_on;
 };
 
 #endif /* __INTEL_PT_H__ */
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 70c93f9b03ac..1705c9d75e44 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -718,6 +718,7 @@ static int __init rapl_pmu_init(void)
 		break;
 	case 60: /* Haswell */
 	case 69: /* Haswell-Celeron */
+	case 70: /* Haswell GT3e */
 	case 61: /* Broadwell */
 	case 71: /* Broadwell-H */
 		rapl_cntr_mask = RAPL_IDX_HSW;
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 5a2ed3ed2f26..f353061bba1d 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -285,6 +285,10 @@ static inline void perf_events_lapic_init(void)	{ }
 static inline void perf_check_microcode(void) { }
 #endif
 
+#ifdef CONFIG_CPU_SUP_INTEL
+ extern void intel_pt_handle_vmx(int on);
+#endif
+
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
  extern void amd_pmu_enable_virt(void);
  extern void amd_pmu_disable_virt(void);
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index ad59d70bcb1a..ef495511f019 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -256,7 +256,8 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data)
 	struct irq_desc *desc;
 	int cpu, vector;
 
-	BUG_ON(!data->cfg.vector);
+	if (!data->cfg.vector)
+		return;
 
 	vector = data->cfg.vector;
 	for_each_cpu_and(cpu, data->domain, cpu_online_mask)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 8f4942e2bcbb..d7ce96a7daca 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -891,9 +891,7 @@ void __init uv_system_init(void)
 	}
 	pr_info("UV: Found %s hub\n", hub);
 
-	/* We now only need to map the MMRs on UV1 */
-	if (is_uv1_hub())
-		map_low_mmrs();
+	map_low_mmrs();
 
 	m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR );
 	m_val = m_n_config.s.m_skt;
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 1f7fdb91a818..e4393bfc7f0d 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -336,7 +336,7 @@ static int intel_num_cpu_cores(struct cpuinfo_x86 *c)
 {
 	unsigned int eax, ebx, ecx, edx;
 
-	if (c->cpuid_level < 4)
+	if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4)
 		return 1;
 
 	/* Intel has a non-standard dependency on %ecx for this CPUID level. */
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 54cdbd2003fe..af1112980dd4 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -389,12 +389,6 @@ default_entry:
 	/* Make changes effective */
 	wrmsr
 
-	/*
-	 * And make sure that all the mappings we set up have NX set from
-	 * the beginning.
-	 */
-	orl $(1 << (_PAGE_BIT_NX - 32)), pa(__supported_pte_mask + 4)
-
 enable_paging:
 
 /*
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a2065d3b3b39..0e4329ed91ef 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -332,6 +332,11 @@ static void __init smp_init_package_map(void)
 	 * primary cores.
 	 */
 	ncpus = boot_cpu_data.x86_max_cores;
+	if (!ncpus) {
+		pr_warn("x86_max_cores == zero !?!?");
+		ncpus = 1;
+	}
+
 	__max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus);
 
 	/*
diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c
index b285d4e8c68e..5da924bbf0a0 100644
--- a/arch/x86/kernel/sysfb_efi.c
+++ b/arch/x86/kernel/sysfb_efi.c
@@ -106,14 +106,24 @@ static int __init efifb_set_system(const struct dmi_system_id *id)
 					continue;
 				for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
 					resource_size_t start, end;
+					unsigned long flags;
+
+					flags = pci_resource_flags(dev, i);
+					if (!(flags & IORESOURCE_MEM))
+						continue;
+
+					if (flags & IORESOURCE_UNSET)
+						continue;
+
+					if (pci_resource_len(dev, i) == 0)
+						continue;
 
 					start = pci_resource_start(dev, i);
-					if (start == 0)
-						break;
 					end = pci_resource_end(dev, i);
 					if (screen_info.lfb_base >= start &&
 					    screen_info.lfb_base < end) {
 						found_bar = 1;
+						break;
 					}
 				}
 			}
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 92ae6acac8a7..6aa0f4d9eea6 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -92,7 +92,7 @@ unsigned long try_msr_calibrate_tsc(void)
 
 	if (freq_desc_tables[cpu_index].msr_plat) {
 		rdmsr(MSR_PLATFORM_INFO, lo, hi);
-		ratio = (lo >> 8) & 0x1f;
+		ratio = (lo >> 8) & 0xff;
 	} else {
 		rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
 		ratio = (hi >> 8) & 0x1f;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 1ff4dbb73fb7..b6f50e8b0a39 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2823,7 +2823,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
 	 */
 	if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
 	    level == PT_PAGE_TABLE_LEVEL &&
-	    PageTransCompound(pfn_to_page(pfn)) &&
+	    PageTransCompoundMap(pfn_to_page(pfn)) &&
 	    !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
 		unsigned long mask;
 		/*
@@ -4785,7 +4785,7 @@ restart:
 		 */
 		if (sp->role.direct &&
 			!kvm_is_reserved_pfn(pfn) &&
-			PageTransCompound(pfn_to_page(pfn))) {
+			PageTransCompoundMap(pfn_to_page(pfn))) {
 			drop_spte(kvm, sptep);
 			need_tlb_flush = 1;
 			goto restart;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ee1c8a93871c..133679d520af 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3103,6 +3103,8 @@ static __init int vmx_disabled_by_bios(void)
 
 static void kvm_cpu_vmxon(u64 addr)
 {
+	intel_pt_handle_vmx(1);
+
 	asm volatile (ASM_VMX_VMXON_RAX
 			: : "a"(&addr), "m"(addr)
 			: "memory", "cc");
@@ -3172,6 +3174,8 @@ static void vmclear_local_loaded_vmcss(void)
 static void kvm_cpu_vmxoff(void)
 {
 	asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
+
+	intel_pt_handle_vmx(0);
 }
 
 static void hardware_disable(void)
diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c
index 8bea84724a7d..f65a33f505b6 100644
--- a/arch/x86/mm/setup_nx.c
+++ b/arch/x86/mm/setup_nx.c
@@ -32,8 +32,9 @@ early_param("noexec", noexec_setup);
 
 void x86_configure_nx(void)
 {
-	/* If disable_nx is set, clear NX on all new mappings going forward. */
-	if (disable_nx)
+	if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx)
+		__supported_pte_mask |= _PAGE_NX;
+	else
 		__supported_pte_mask &= ~_PAGE_NX;
 }
 
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c
index a2433817c987..6a2f5691b1ab 100644
--- a/arch/x86/platform/efi/efi-bgrt.c
+++ b/arch/x86/platform/efi/efi-bgrt.c
@@ -43,40 +43,40 @@ void __init efi_bgrt_init(void)
 		return;
 
 	if (bgrt_tab->header.length < sizeof(*bgrt_tab)) {
-		pr_err("Ignoring BGRT: invalid length %u (expected %zu)\n",
+		pr_notice("Ignoring BGRT: invalid length %u (expected %zu)\n",
 		       bgrt_tab->header.length, sizeof(*bgrt_tab));
 		return;
 	}
 	if (bgrt_tab->version != 1) {
-		pr_err("Ignoring BGRT: invalid version %u (expected 1)\n",
+		pr_notice("Ignoring BGRT: invalid version %u (expected 1)\n",
 		       bgrt_tab->version);
 		return;
 	}
 	if (bgrt_tab->status & 0xfe) {
-		pr_err("Ignoring BGRT: reserved status bits are non-zero %u\n",
+		pr_notice("Ignoring BGRT: reserved status bits are non-zero %u\n",
 		       bgrt_tab->status);
 		return;
 	}
 	if (bgrt_tab->image_type != 0) {
-		pr_err("Ignoring BGRT: invalid image type %u (expected 0)\n",
+		pr_notice("Ignoring BGRT: invalid image type %u (expected 0)\n",
 		       bgrt_tab->image_type);
 		return;
 	}
 	if (!bgrt_tab->image_address) {
-		pr_err("Ignoring BGRT: null image address\n");
+		pr_notice("Ignoring BGRT: null image address\n");
 		return;
 	}
 
 	image = memremap(bgrt_tab->image_address, sizeof(bmp_header), MEMREMAP_WB);
 	if (!image) {
-		pr_err("Ignoring BGRT: failed to map image header memory\n");
+		pr_notice("Ignoring BGRT: failed to map image header memory\n");
 		return;
 	}
 
 	memcpy(&bmp_header, image, sizeof(bmp_header));
 	memunmap(image);
 	if (bmp_header.id != 0x4d42) {
-		pr_err("Ignoring BGRT: Incorrect BMP magic number 0x%x (expected 0x4d42)\n",
+		pr_notice("Ignoring BGRT: Incorrect BMP magic number 0x%x (expected 0x4d42)\n",
 			bmp_header.id);
 		return;
 	}
@@ -84,14 +84,14 @@ void __init efi_bgrt_init(void)
 
 	bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL | __GFP_NOWARN);
 	if (!bgrt_image) {
-		pr_err("Ignoring BGRT: failed to allocate memory for image (wanted %zu bytes)\n",
+		pr_notice("Ignoring BGRT: failed to allocate memory for image (wanted %zu bytes)\n",
 		       bgrt_image_size);
 		return;
 	}
 
 	image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB);
 	if (!image) {
-		pr_err("Ignoring BGRT: failed to map image memory\n");
+		pr_notice("Ignoring BGRT: failed to map image memory\n");
 		kfree(bgrt_image);
 		bgrt_image = NULL;
 		return;
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 9e2ba5c6e1dd..f42e78de1e10 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -27,6 +27,12 @@ static bool xen_pvspin = true;
 
 static void xen_qlock_kick(int cpu)
 {
+	int irq = per_cpu(lock_kicker_irq, cpu);
+
+	/* Don't kick if the target's kicker interrupt is not initialized. */
+	if (irq == -1)
+		return;
+
 	xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
 }