Merge branches 'x86/urgent' and 'core/urgent' into x86/boot, to pick up fixes and avoid conflicts

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

arch/x86/kernel/acpi/boot.c

@@ -215,6 +215,10 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
 	apic_id = processor->local_apic_id;
 	enabled = processor->lapic_flags & ACPI_MADT_ENABLED;
 
+	/* Ignore invalid ID */
+	if (apic_id == 0xffffffff)
+		return 0;
+
 	/*
 	 * We need to register disabled CPU as well to permit
 	 * counting disabled CPUs. This allows us to size

arch/x86/kernel/apic/x2apic_cluster.c

@@ -116,6 +116,7 @@ static void init_x2apic_ldr(void)
 			goto update;
 	}
 	cmsk = cluster_hotplug_mask;
+	cmsk->clusterid = cluster;
 	cluster_hotplug_mask = NULL;
 update:
 	this_cpu_write(cluster_masks, cmsk);

arch/x86/kernel/cpu/common.c

@@ -868,6 +868,11 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_power = edx;
 	}
 
+	if (c->extended_cpuid_level >= 0x80000008) {
+		cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
+		c->x86_capability[CPUID_8000_0008_EBX] = ebx;
+	}
+
 	if (c->extended_cpuid_level >= 0x8000000a)
 		c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
 
@@ -891,7 +896,6 @@ static void get_cpu_address_sizes(struct cpuinfo_x86 *c)
 
 		c->x86_virt_bits = (eax >> 8) & 0xff;
 		c->x86_phys_bits = eax & 0xff;
-		c->x86_capability[CPUID_8000_0008_EBX] = ebx;
 	}
 #ifdef CONFIG_X86_32
 	else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))

arch/x86/kernel/cpu/intel.c

@@ -811,6 +811,9 @@ static const struct _tlb_table intel_tlb_table[] = {
 	{ 0x5d, TLB_DATA_4K_4M,		256,	" TLB_DATA 4 KByte and 4 MByte pages" },
 	{ 0x61, TLB_INST_4K,		48,	" TLB_INST 4 KByte pages, full associative" },
 	{ 0x63, TLB_DATA_1G,		4,	" TLB_DATA 1 GByte pages, 4-way set associative" },
+	{ 0x6b, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 8-way associative" },
+	{ 0x6c, TLB_DATA_2M_4M,		128,	" TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" },
+	{ 0x6d, TLB_DATA_1G,		16,	" TLB_DATA 1 GByte pages, fully associative" },
 	{ 0x76, TLB_INST_2M_4M,		8,	" TLB_INST 2-MByte or 4-MByte pages, fully associative" },
 	{ 0xb0, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 4-way set associative" },
 	{ 0xb1, TLB_INST_2M_4M,		4,	" TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },

arch/x86/kernel/cpu/microcode/core.c

@@ -564,14 +564,12 @@ static int __reload_late(void *info)
 	apply_microcode_local(&err);
 	spin_unlock(&update_lock);
 
+	/* siblings return UCODE_OK because their engine got updated already */
 	if (err > UCODE_NFOUND) {
 		pr_warn("Error reloading microcode on CPU %d\n", cpu);
-		return -1;
-	/* siblings return UCODE_OK because their engine got updated already */
+		ret = -1;
 	} else if (err == UCODE_UPDATED || err == UCODE_OK) {
 		ret = 1;
-	} else {
-		return ret;
 	}
 
 	/*

arch/x86/kernel/cpu/microcode/intel.c

@@ -485,7 +485,6 @@ static void show_saved_mc(void)
  */
 static void save_mc_for_early(u8 *mc, unsigned int size)
 {
-#ifdef CONFIG_HOTPLUG_CPU
 	/* Synchronization during CPU hotplug. */
 	static DEFINE_MUTEX(x86_cpu_microcode_mutex);
 
@@ -495,7 +494,6 @@ static void save_mc_for_early(u8 *mc, unsigned int size)
 	show_saved_mc();
 
 	mutex_unlock(&x86_cpu_microcode_mutex);
-#endif
 }
 
 static bool load_builtin_intel_microcode(struct cpio_data *cp)

arch/x86/kernel/head64.c

@@ -104,6 +104,12 @@ static bool __head check_la57_support(unsigned long physaddr)
 }
 #endif
 
+/* Code in __startup_64() can be relocated during execution, but the compiler
+ * doesn't have to generate PC-relative relocations when accessing globals from
+ * that function. Clang actually does not generate them, which leads to
+ * boot-time crashes. To work around this problem, every global pointer must
+ * be adjusted using fixup_pointer().
+ */
 unsigned long __head __startup_64(unsigned long physaddr,
 				  struct boot_params *bp)
 {
@@ -113,6 +119,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	p4dval_t *p4d;
 	pudval_t *pud;
 	pmdval_t *pmd, pmd_entry;
+	pteval_t *mask_ptr;
 	bool la57;
 	int i;
 	unsigned int *next_pgt_ptr;
@@ -196,7 +203,8 @@ unsigned long __head __startup_64(unsigned long physaddr,
 
 	pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
 	/* Filter out unsupported __PAGE_KERNEL_* bits: */
-	pmd_entry &= __supported_pte_mask;
+	mask_ptr = fixup_pointer(&__supported_pte_mask, physaddr);
+	pmd_entry &= *mask_ptr;
 	pmd_entry += sme_get_me_mask();
 	pmd_entry +=  physaddr;
 

arch/x86/kernel/jailhouse.c

@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL2.0
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Jailhouse paravirt_ops implementation
  *

arch/x86/kernel/kexec-bzimage64.c

@@ -398,11 +398,10 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	 * little bit simple
 	 */
 	efi_map_sz = efi_get_runtime_map_size();
-	efi_map_sz = ALIGN(efi_map_sz, 16);
 	params_cmdline_sz = sizeof(struct boot_params) + cmdline_len +
 				MAX_ELFCOREHDR_STR_LEN;
 	params_cmdline_sz = ALIGN(params_cmdline_sz, 16);
-	kbuf.bufsz = params_cmdline_sz + efi_map_sz +
+	kbuf.bufsz = params_cmdline_sz + ALIGN(efi_map_sz, 16) +
 				sizeof(struct setup_data) +
 				sizeof(struct efi_setup_data);
 
@@ -410,7 +409,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	if (!params)
 		return ERR_PTR(-ENOMEM);
 	efi_map_offset = params_cmdline_sz;
-	efi_setup_data_offset = efi_map_offset + efi_map_sz;
+	efi_setup_data_offset = efi_map_offset + ALIGN(efi_map_sz, 16);
 
 	/* Copy setup header onto bootparams. Documentation/x86/boot.txt */
 	setup_header_size = 0x0202 + kernel[0x0201] - setup_hdr_offset;

arch/x86/kernel/kprobes/core.c

@@ -370,6 +370,10 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
 	if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
 		return 0;
 
+	/* We should not singlestep on the exception masking instructions */
+	if (insn_masking_exception(insn))
+		return 0;
+
 #ifdef CONFIG_X86_64
 	/* Only x86_64 has RIP relative instructions */
 	if (insn_rip_relative(insn)) {

arch/x86/kernel/machine_kexec_32.c

@@ -57,12 +57,17 @@ static void load_segments(void)
 static void machine_kexec_free_page_tables(struct kimage *image)
 {
 	free_page((unsigned long)image->arch.pgd);
+	image->arch.pgd = NULL;
 #ifdef CONFIG_X86_PAE
 	free_page((unsigned long)image->arch.pmd0);
+	image->arch.pmd0 = NULL;
 	free_page((unsigned long)image->arch.pmd1);
+	image->arch.pmd1 = NULL;
 #endif
 	free_page((unsigned long)image->arch.pte0);
+	image->arch.pte0 = NULL;
 	free_page((unsigned long)image->arch.pte1);
+	image->arch.pte1 = NULL;
 }
 
 static int machine_kexec_alloc_page_tables(struct kimage *image)
@@ -79,7 +84,6 @@ static int machine_kexec_alloc_page_tables(struct kimage *image)
 	    !image->arch.pmd0 || !image->arch.pmd1 ||
 #endif
 	    !image->arch.pte0 || !image->arch.pte1) {
-		machine_kexec_free_page_tables(image);
 		return -ENOMEM;
 	}
 	return 0;

arch/x86/kernel/machine_kexec_64.c

@@ -39,9 +39,13 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
 static void free_transition_pgtable(struct kimage *image)
 {
 	free_page((unsigned long)image->arch.p4d);
+	image->arch.p4d = NULL;
 	free_page((unsigned long)image->arch.pud);
+	image->arch.pud = NULL;
 	free_page((unsigned long)image->arch.pmd);
+	image->arch.pmd = NULL;
 	free_page((unsigned long)image->arch.pte);
+	image->arch.pte = NULL;
 }
 
 static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
@@ -91,7 +95,6 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
 	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC));
 	return 0;
 err:
-	free_transition_pgtable(image);
 	return result;
 }
 

arch/x86/kernel/pci-nommu.c

@@ -1,90 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Fallback functions when the main IOMMU code is not compiled in. This
-   code is roughly equivalent to i386. */
-#include <linux/dma-direct.h>
-#include <linux/scatterlist.h>
-#include <linux/string.h>
-#include <linux/gfp.h>
-#include <linux/pci.h>
-#include <linux/mm.h>
-
-#include <asm/processor.h>
-#include <asm/iommu.h>
-#include <asm/dma.h>
-
-#define NOMMU_MAPPING_ERROR		0
-
-static int
-check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size)
-{
-	if (hwdev && !dma_capable(hwdev, bus, size)) {
-		if (*hwdev->dma_mask >= DMA_BIT_MASK(32))
-			printk(KERN_ERR
-			    "nommu_%s: overflow %Lx+%zu of device mask %Lx\n",
-				name, (long long)bus, size,
-				(long long)*hwdev->dma_mask);
-		return 0;
-	}
-	return 1;
-}
-
-static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
-				 unsigned long offset, size_t size,
-				 enum dma_data_direction dir,
-				 unsigned long attrs)
-{
-	dma_addr_t bus = phys_to_dma(dev, page_to_phys(page)) + offset;
-	WARN_ON(size == 0);
-	if (!check_addr("map_single", dev, bus, size))
-		return NOMMU_MAPPING_ERROR;
-	return bus;
-}
-
-/* Map a set of buffers described by scatterlist in streaming
- * mode for DMA.  This is the scatter-gather version of the
- * above pci_map_single interface.  Here the scatter gather list
- * elements are each tagged with the appropriate dma address
- * and length.  They are obtained via sg_dma_{address,length}(SG).
- *
- * NOTE: An implementation may be able to use a smaller number of
- *       DMA address/length pairs than there are SG table elements.
- *       (for example via virtual mapping capabilities)
- *       The routine returns the number of addr/length pairs actually
- *       used, at most nents.
- *
- * Device ownership issues as mentioned above for pci_map_single are
- * the same here.
- */
-static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
-			int nents, enum dma_data_direction dir,
-			unsigned long attrs)
-{
-	struct scatterlist *s;
-	int i;
-
-	WARN_ON(nents == 0 || sg[0].length == 0);
-
-	for_each_sg(sg, s, nents, i) {
-		BUG_ON(!sg_page(s));
-		s->dma_address = sg_phys(s);
-		if (!check_addr("map_sg", hwdev, s->dma_address, s->length))
-			return 0;
-		s->dma_length = s->length;
-	}
-	return nents;
-}
-
-static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == NOMMU_MAPPING_ERROR;
-}
-
-const struct dma_map_ops nommu_dma_ops = {
-	.alloc			= dma_generic_alloc_coherent,
-	.free			= dma_generic_free_coherent,
-	.map_sg			= nommu_map_sg,
-	.map_page		= nommu_map_page,
-	.is_phys		= 1,
-	.mapping_error		= nommu_mapping_error,
-	.dma_supported		= x86_dma_supported,
-};

arch/x86/kernel/setup.c

@@ -50,6 +50,7 @@
 #include <linux/init_ohci1394_dma.h>
 #include <linux/kvm_para.h>
 #include <linux/dma-contiguous.h>
+#include <xen/xen.h>
 
 #include <linux/errno.h>
 #include <linux/kernel.h>
@@ -534,6 +535,11 @@ static void __init reserve_crashkernel(void)
 		high = true;
 	}
 
+	if (xen_pv_domain()) {
+		pr_info("Ignoring crashkernel for a Xen PV domain\n");
+		return;
+	}
+
 	/* 0 means: find the address automatically */
 	if (crash_base <= 0) {
 		/*

arch/x86/kernel/smpboot.c

@@ -77,6 +77,8 @@
 #include <asm/i8259.h>
 #include <asm/misc.h>
 #include <asm/qspinlock.h>
+#include <asm/intel-family.h>
+#include <asm/cpu_device_id.h>
 
 /* representing HT siblings of each logical CPU */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
@@ -383,15 +385,47 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 	return false;
 }
 
+/*
+ * Define snc_cpu[] for SNC (Sub-NUMA Cluster) CPUs.
+ *
+ * These are Intel CPUs that enumerate an LLC that is shared by
+ * multiple NUMA nodes. The LLC on these systems is shared for
+ * off-package data access but private to the NUMA node (half
+ * of the package) for on-package access.
+ *
+ * CPUID (the source of the information about the LLC) can only
+ * enumerate the cache as being shared *or* unshared, but not
+ * this particular configuration. The CPU in this case enumerates
+ * the cache to be shared across the entire package (spanning both
+ * NUMA nodes).
+ */
+
+static const struct x86_cpu_id snc_cpu[] = {
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_X },
+	{}
+};
+
 static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
 	int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
 
-	if (per_cpu(cpu_llc_id, cpu1) != BAD_APICID &&
-	    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2))
-		return topology_sane(c, o, "llc");
+	/* Do not match if we do not have a valid APICID for cpu: */
+	if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID)
+		return false;
 
-	return false;
+	/* Do not match if LLC id does not match: */
+	if (per_cpu(cpu_llc_id, cpu1) != per_cpu(cpu_llc_id, cpu2))
+		return false;
+
+	/*
+	 * Allow the SNC topology without warning. Return of false
+	 * means 'c' does not share the LLC of 'o'. This will be
+	 * reflected to userspace.
+	 */
+	if (!topology_same_node(c, o) && x86_match_cpu(snc_cpu))
+		return false;
+
+	return topology_sane(c, o, "llc");
 }
 
 /*
@@ -449,7 +483,8 @@ static struct sched_domain_topology_level x86_topology[] = {
 
 /*
  * Set if a package/die has multiple NUMA nodes inside.
- * AMD Magny-Cours and Intel Cluster-on-Die have this.
+ * AMD Magny-Cours, Intel Cluster-on-Die, and Intel
+ * Sub-NUMA Clustering have this.
  */
 static bool x86_has_numa_in_package;
 
@@ -1529,6 +1564,8 @@ static inline void mwait_play_dead(void)
 	void *mwait_ptr;
 	int i;
 
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		return;
 	if (!this_cpu_has(X86_FEATURE_MWAIT))
 		return;
 	if (!this_cpu_has(X86_FEATURE_CLFLUSH))

arch/x86/kernel/tsc.c

@@ -317,7 +317,7 @@ static unsigned long calc_hpet_ref(u64 deltatsc, u64 hpet1, u64 hpet2)
 	hpet2 -= hpet1;
 	tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD));
 	do_div(tmp, 1000000);
-	do_div(deltatsc, tmp);
+	deltatsc = div64_u64(deltatsc, tmp);
 
 	return (unsigned long) deltatsc;
 }
@@ -1067,6 +1067,7 @@ static struct clocksource clocksource_tsc_early = {
 	.resume			= tsc_resume,
 	.mark_unstable		= tsc_cs_mark_unstable,
 	.tick_stable		= tsc_cs_tick_stable,
+	.list			= LIST_HEAD_INIT(clocksource_tsc_early.list),
 };
 
 /*
@@ -1086,6 +1087,7 @@ static struct clocksource clocksource_tsc = {
 	.resume			= tsc_resume,
 	.mark_unstable		= tsc_cs_mark_unstable,
 	.tick_stable		= tsc_cs_tick_stable,
+	.list			= LIST_HEAD_INIT(clocksource_tsc.list),
 };
 
 void mark_tsc_unstable(char *reason)
@@ -1098,13 +1100,9 @@ void mark_tsc_unstable(char *reason)
 		clear_sched_clock_stable();
 	disable_sched_clock_irqtime();
 	pr_info("Marking TSC unstable due to %s\n", reason);
-	/* Change only the rating, when not registered */
-	if (clocksource_tsc.mult) {
-		clocksource_mark_unstable(&clocksource_tsc);
-	} else {
-		clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
-		clocksource_tsc.rating = 0;
-	}
+
+	clocksource_mark_unstable(&clocksource_tsc_early);
+	clocksource_mark_unstable(&clocksource_tsc);
 }
 
 EXPORT_SYMBOL_GPL(mark_tsc_unstable);
@@ -1244,7 +1242,7 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 
 	/* Don't bother refining TSC on unstable systems */
 	if (tsc_unstable)
-		return;
+		goto unreg;
 
 	/*
 	 * Since the work is started early in boot, we may be
@@ -1297,11 +1295,12 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 
 out:
 	if (tsc_unstable)
-		return;
+		goto unreg;
 
 	if (boot_cpu_has(X86_FEATURE_ART))
 		art_related_clocksource = &clocksource_tsc;
 	clocksource_register_khz(&clocksource_tsc, tsc_khz);
+unreg:
 	clocksource_unregister(&clocksource_tsc_early);
 }
 
@@ -1311,8 +1310,8 @@ static int __init init_tsc_clocksource(void)
 	if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz)
 		return 0;
 
-	if (check_tsc_unstable())
-		return 0;
+	if (tsc_unstable)
+		goto unreg;
 
 	if (tsc_clocksource_reliable)
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
@@ -1328,6 +1327,7 @@ static int __init init_tsc_clocksource(void)
 		if (boot_cpu_has(X86_FEATURE_ART))
 			art_related_clocksource = &clocksource_tsc;
 		clocksource_register_khz(&clocksource_tsc, tsc_khz);
+unreg:
 		clocksource_unregister(&clocksource_tsc_early);
 		return 0;
 	}

arch/x86/kernel/uprobes.c

@@ -299,6 +299,10 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
 	if (is_prefix_bad(insn))
 		return -ENOTSUPP;
 
+	/* We should not singlestep on the exception masking instructions */
+	if (insn_masking_exception(insn))
+		return -ENOTSUPP;
+
 	if (x86_64)
 		good_insns = good_insns_64;
 	else