Merge branch 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cpu updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Add support for the "Dhyana" x86 CPUs by Hygon: these are licensed
     based on the AMD Zen architecture, and are built and sold in China,
     for domestic datacenter use. The code is pretty close to AMD
     support, mostly with a few quirks and enumeration differences. (Pu
     Wen)

   - Enable CPUID support on Cyrix 6x86/6x86L processors"

* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  tools/cpupower: Add Hygon Dhyana support
  cpufreq: Add Hygon Dhyana support
  ACPI: Add Hygon Dhyana support
  x86/xen: Add Hygon Dhyana support to Xen
  x86/kvm: Add Hygon Dhyana support to KVM
  x86/mce: Add Hygon Dhyana support to the MCA infrastructure
  x86/bugs: Add Hygon Dhyana to the respective mitigation machinery
  x86/apic: Add Hygon Dhyana support
  x86/pci, x86/amd_nb: Add Hygon Dhyana support to PCI and northbridge
  x86/amd_nb: Check vendor in AMD-only functions
  x86/alternative: Init ideal_nops for Hygon Dhyana
  x86/events: Add Hygon Dhyana support to PMU infrastructure
  x86/smpboot: Do not use BSP INIT delay and MWAIT to idle on Dhyana
  x86/cpu/mtrr: Support TOP_MEM2 and get MTRR number
  x86/cpu: Get cache info and setup cache cpumap for Hygon Dhyana
  x86/cpu: Create Hygon Dhyana architecture support file
  x86/CPU: Change query logic so CPUID is enabled before testing
  x86/CPU: Use correct macros for Cyrix calls

17 files changed, 525 insertions, 22 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index b9d5e7c9ef43..184e9a06b0ff 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -222,6 +222,10 @@ void __init arch_init_ideal_nops(void)
 		}
 		break;
 
+	case X86_VENDOR_HYGON:
+		ideal_nops = p6_nops;
+		return;
+
 	case X86_VENDOR_AMD:
 		if (boot_cpu_data.x86 > 0xf) {
 			ideal_nops = p6_nops;
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index b481b95bd8f6..a6eca647bc76 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -61,6 +61,21 @@ static const struct pci_device_id amd_nb_link_ids[] = {
 	{}
 };
 
+static const struct pci_device_id hygon_root_ids[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_ROOT) },
+	{}
+};
+
+const struct pci_device_id hygon_nb_misc_ids[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_DF_F3) },
+	{}
+};
+
+static const struct pci_device_id hygon_nb_link_ids[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_DF_F4) },
+	{}
+};
+
 const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[] __initconst = {
 	{ 0x00, 0x18, 0x20 },
 	{ 0xff, 0x00, 0x20 },
@@ -194,15 +209,24 @@ EXPORT_SYMBOL_GPL(amd_df_indirect_read);
 
 int amd_cache_northbridges(void)
 {
-	u16 i = 0;
-	struct amd_northbridge *nb;
+	const struct pci_device_id *misc_ids = amd_nb_misc_ids;
+	const struct pci_device_id *link_ids = amd_nb_link_ids;
+	const struct pci_device_id *root_ids = amd_root_ids;
 	struct pci_dev *root, *misc, *link;
+	struct amd_northbridge *nb;
+	u16 i = 0;
 
 	if (amd_northbridges.num)
 		return 0;
 
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
+		root_ids = hygon_root_ids;
+		misc_ids = hygon_nb_misc_ids;
+		link_ids = hygon_nb_link_ids;
+	}
+
 	misc = NULL;
-	while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL)
+	while ((misc = next_northbridge(misc, misc_ids)) != NULL)
 		i++;
 
 	if (!i)
@@ -218,11 +242,11 @@ int amd_cache_northbridges(void)
 	link = misc = root = NULL;
 	for (i = 0; i != amd_northbridges.num; i++) {
 		node_to_amd_nb(i)->root = root =
-			next_northbridge(root, amd_root_ids);
+			next_northbridge(root, root_ids);
 		node_to_amd_nb(i)->misc = misc =
-			next_northbridge(misc, amd_nb_misc_ids);
+			next_northbridge(misc, misc_ids);
 		node_to_amd_nb(i)->link = link =
-			next_northbridge(link, amd_nb_link_ids);
+			next_northbridge(link, link_ids);
 	}
 
 	if (amd_gart_present())
@@ -261,11 +285,19 @@ EXPORT_SYMBOL_GPL(amd_cache_northbridges);
  */
 bool __init early_is_amd_nb(u32 device)
 {
+	const struct pci_device_id *misc_ids = amd_nb_misc_ids;
 	const struct pci_device_id *id;
 	u32 vendor = device & 0xffff;
 
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
+		return false;
+
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+		misc_ids = hygon_nb_misc_ids;
+
 	device >>= 16;
-	for (id = amd_nb_misc_ids; id->vendor; id++)
+	for (id = misc_ids; id->vendor; id++)
 		if (vendor == id->vendor && device == id->device)
 			return true;
 	return false;
@@ -277,7 +309,8 @@ struct resource *amd_get_mmconfig_range(struct resource *res)
 	u64 base, msr;
 	unsigned int segn_busn_bits;
 
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
 		return NULL;
 
 	/* assume all cpus from fam10h have mmconfig */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 84132eddb5a8..ab731ab09f06 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -224,6 +224,11 @@ static int modern_apic(void)
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
 	    boot_cpu_data.x86 >= 0xf)
 		return 1;
+
+	/* Hygon systems use modern APIC */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+		return 1;
+
 	return lapic_get_version() >= 0x14;
 }
 
@@ -1912,6 +1917,8 @@ static int __init detect_init_APIC(void)
 		    (boot_cpu_data.x86 >= 15))
 			break;
 		goto no_apic;
+	case X86_VENDOR_HYGON:
+		break;
 	case X86_VENDOR_INTEL:
 		if (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15 ||
 		    (boot_cpu_data.x86 == 5 && boot_cpu_has(X86_FEATURE_APIC)))
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 02e8acb134f8..47ff2976c292 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -185,6 +185,7 @@ void __init default_setup_apic_routing(void)
 				break;
 			}
 			/* If P4 and above fall through */
+		case X86_VENDOR_HYGON:
 		case X86_VENDOR_AMD:
 			def_to_bigsmp = 1;
 		}
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 347137e80bf5..1f5d2291c31e 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -30,6 +30,7 @@ obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
 
 obj-$(CONFIG_CPU_SUP_INTEL)		+= intel.o intel_pconfig.o
 obj-$(CONFIG_CPU_SUP_AMD)		+= amd.o
+obj-$(CONFIG_CPU_SUP_HYGON)		+= hygon.o
 obj-$(CONFIG_CPU_SUP_CYRIX_32)		+= cyrix.o
 obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 40bdaea97fe7..b810cc239375 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -312,6 +312,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 	}
 
 	if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON &&
 	    boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
 		pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n");
 		return SPECTRE_V2_CMD_AUTO;
@@ -371,7 +372,8 @@ static void __init spectre_v2_select_mitigation(void)
 	return;
 
 retpoline_auto:
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
 	retpoline_amd:
 		if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
 			pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n");
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 0c5fcbd998cf..dc1b9342e9c4 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -602,6 +602,10 @@ cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf)
 		else
 			amd_cpuid4(index, &eax, &ebx, &ecx);
 		amd_init_l3_cache(this_leaf, index);
+	} else if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
+		cpuid_count(0x8000001d, index, &eax.full,
+			    &ebx.full, &ecx.full, &edx);
+		amd_init_l3_cache(this_leaf, index);
 	} else {
 		cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
 	}
@@ -625,7 +629,8 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c)
 	union _cpuid4_leaf_eax	cache_eax;
 	int 			i = -1;
 
-	if (c->x86_vendor == X86_VENDOR_AMD)
+	if (c->x86_vendor == X86_VENDOR_AMD ||
+	    c->x86_vendor == X86_VENDOR_HYGON)
 		op = 0x8000001d;
 	else
 		op = 4;
@@ -678,6 +683,22 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
 	}
 }
 
+void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
+{
+	/*
+	 * We may have multiple LLCs if L3 caches exist, so check if we
+	 * have an L3 cache by looking at the L3 cache CPUID leaf.
+	 */
+	if (!cpuid_edx(0x80000006))
+		return;
+
+	/*
+	 * LLC is at the core complex level.
+	 * Core complex ID is ApicId[3] for these processors.
+	 */
+	per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
+}
+
 void init_amd_cacheinfo(struct cpuinfo_x86 *c)
 {
 
@@ -691,6 +712,11 @@ void init_amd_cacheinfo(struct cpuinfo_x86 *c)
 	}
 }
 
+void init_hygon_cacheinfo(struct cpuinfo_x86 *c)
+{
+	num_cache_leaves = find_num_cache_leaves(c);
+}
+
 void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 {
 	/* Cache sizes */
@@ -913,7 +939,8 @@ static void __cache_cpumap_setup(unsigned int cpu, int index,
 	int index_msb, i;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	if (c->x86_vendor == X86_VENDOR_AMD) {
+	if (c->x86_vendor == X86_VENDOR_AMD ||
+	    c->x86_vendor == X86_VENDOR_HYGON) {
 		if (__cache_amd_cpumap_setup(cpu, index, base))
 			return;
 	}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0b99a7fae6be..c519a079b3d5 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -963,6 +963,7 @@ static const __initconst struct x86_cpu_id cpu_no_speculation[] = {
 
 static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
 	{ X86_VENDOR_AMD },
+	{ X86_VENDOR_HYGON },
 	{}
 };
 
@@ -1076,6 +1077,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	memset(&c->x86_capability, 0, sizeof c->x86_capability);
 	c->extended_cpuid_level = 0;
 
+	if (!have_cpuid_p())
+		identify_cpu_without_cpuid(c);
+
 	/* cyrix could have cpuid enabled via c_identify()*/
 	if (have_cpuid_p()) {
 		cpu_detect(c);
@@ -1093,7 +1097,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 		if (this_cpu->c_bsp_init)
 			this_cpu->c_bsp_init(c);
 	} else {
-		identify_cpu_without_cpuid(c);
 		setup_clear_cpu_cap(X86_FEATURE_CPUID);
 	}
 
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 7b229afa0a37..da5446acc241 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -54,6 +54,7 @@ extern u32 get_scattered_cpuid_leaf(unsigned int level,
 				    enum cpuid_regs_idx reg);
 extern void init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
+extern void init_hygon_cacheinfo(struct cpuinfo_x86 *c);
 
 extern void detect_num_cpu_cores(struct cpuinfo_x86 *c);
 extern int detect_extended_topology_early(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 8949b7ae6d92..d12226f60168 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -437,7 +437,7 @@ static void cyrix_identify(struct cpuinfo_x86 *c)
 			/* enable MAPEN  */
 			setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);
 			/* enable cpuid  */
-			setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x80);
+			setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x80);
 			/* disable MAPEN */
 			setCx86(CX86_CCR3, ccr3);
 			local_irq_restore(flags);
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
new file mode 100644
index 000000000000..cf25405444ab
--- /dev/null
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -0,0 +1,408 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Hygon Processor Support for Linux
+ *
+ * Copyright (C) 2018 Chengdu Haiguang IC Design Co., Ltd.
+ *
+ * Author: Pu Wen <puwen@hygon.cn>
+ */
+#include <linux/io.h>
+
+#include <asm/cpu.h>
+#include <asm/smp.h>
+#include <asm/cacheinfo.h>
+#include <asm/spec-ctrl.h>
+#include <asm/delay.h>
+#ifdef CONFIG_X86_64
+# include <asm/set_memory.h>
+#endif
+
+#include "cpu.h"
+
+/*
+ * nodes_per_socket: Stores the number of nodes per socket.
+ * Refer to CPUID Fn8000_001E_ECX Node Identifiers[10:8]
+ */
+static u32 nodes_per_socket = 1;
+
+#ifdef CONFIG_NUMA
+/*
+ * To workaround broken NUMA config.  Read the comment in
+ * srat_detect_node().
+ */
+static int nearby_node(int apicid)
+{
+	int i, node;
+
+	for (i = apicid - 1; i >= 0; i--) {
+		node = __apicid_to_node[i];
+		if (node != NUMA_NO_NODE && node_online(node))
+			return node;
+	}
+	for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
+		node = __apicid_to_node[i];
+		if (node != NUMA_NO_NODE && node_online(node))
+			return node;
+	}
+	return first_node(node_online_map); /* Shouldn't happen */
+}
+#endif
+
+static void hygon_get_topology_early(struct cpuinfo_x86 *c)
+{
+	if (cpu_has(c, X86_FEATURE_TOPOEXT))
+		smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1;
+}
+
+/*
+ * Fixup core topology information for
+ * (1) Hygon multi-node processors
+ *     Assumption: Number of cores in each internal node is the same.
+ * (2) Hygon processors supporting compute units
+ */
+static void hygon_get_topology(struct cpuinfo_x86 *c)
+{
+	u8 node_id;
+	int cpu = smp_processor_id();
+
+	/* get information required for multi-node processors */
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+		int err;
+		u32 eax, ebx, ecx, edx;
+
+		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+
+		node_id  = ecx & 0xff;
+
+		c->cpu_core_id = ebx & 0xff;
+
+		if (smp_num_siblings > 1)
+			c->x86_max_cores /= smp_num_siblings;
+
+		/*
+		 * In case leaf B is available, use it to derive
+		 * topology information.
+		 */
+		err = detect_extended_topology(c);
+		if (!err)
+			c->x86_coreid_bits = get_count_order(c->x86_max_cores);
+
+		cacheinfo_hygon_init_llc_id(c, cpu, node_id);
+	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
+		u64 value;
+
+		rdmsrl(MSR_FAM10H_NODE_ID, value);
+		node_id = value & 7;
+
+		per_cpu(cpu_llc_id, cpu) = node_id;
+	} else
+		return;
+
+	if (nodes_per_socket > 1)
+		set_cpu_cap(c, X86_FEATURE_AMD_DCM);
+}
+
+/*
+ * On Hygon setup the lower bits of the APIC id distinguish the cores.
+ * Assumes number of cores is a power of two.
+ */
+static void hygon_detect_cmp(struct cpuinfo_x86 *c)
+{
+	unsigned int bits;
+	int cpu = smp_processor_id();
+
+	bits = c->x86_coreid_bits;
+	/* Low order bits define the core id (index of core in socket) */
+	c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
+	/* Convert the initial APIC ID into the socket ID */
+	c->phys_proc_id = c->initial_apicid >> bits;
+	/* use socket ID also for last level cache */
+	per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
+}
+
+static void srat_detect_node(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_NUMA
+	int cpu = smp_processor_id();
+	int node;
+	unsigned int apicid = c->apicid;
+
+	node = numa_cpu_node(cpu);
+	if (node == NUMA_NO_NODE)
+		node = per_cpu(cpu_llc_id, cpu);
+
+	/*
+	 * On multi-fabric platform (e.g. Numascale NumaChip) a
+	 * platform-specific handler needs to be called to fixup some
+	 * IDs of the CPU.
+	 */
+	if (x86_cpuinit.fixup_cpu_id)
+		x86_cpuinit.fixup_cpu_id(c, node);
+
+	if (!node_online(node)) {
+		/*
+		 * Two possibilities here:
+		 *
+		 * - The CPU is missing memory and no node was created.  In
+		 *   that case try picking one from a nearby CPU.
+		 *
+		 * - The APIC IDs differ from the HyperTransport node IDs.
+		 *   Assume they are all increased by a constant offset, but
+		 *   in the same order as the HT nodeids.  If that doesn't
+		 *   result in a usable node fall back to the path for the
+		 *   previous case.
+		 *
+		 * This workaround operates directly on the mapping between
+		 * APIC ID and NUMA node, assuming certain relationship
+		 * between APIC ID, HT node ID and NUMA topology.  As going
+		 * through CPU mapping may alter the outcome, directly
+		 * access __apicid_to_node[].
+		 */
+		int ht_nodeid = c->initial_apicid;
+
+		if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
+			node = __apicid_to_node[ht_nodeid];
+		/* Pick a nearby node */
+		if (!node_online(node))
+			node = nearby_node(apicid);
+	}
+	numa_set_node(cpu, node);
+#endif
+}
+
+static void early_init_hygon_mc(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	unsigned int bits, ecx;
+
+	/* Multi core CPU? */
+	if (c->extended_cpuid_level < 0x80000008)
+		return;
+
+	ecx = cpuid_ecx(0x80000008);
+
+	c->x86_max_cores = (ecx & 0xff) + 1;
+
+	/* CPU telling us the core id bits shift? */
+	bits = (ecx >> 12) & 0xF;
+
+	/* Otherwise recompute */
+	if (bits == 0) {
+		while ((1 << bits) < c->x86_max_cores)
+			bits++;
+	}
+
+	c->x86_coreid_bits = bits;
+#endif
+}
+
+static void bsp_init_hygon(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_64
+	unsigned long long tseg;
+
+	/*
+	 * Split up direct mapping around the TSEG SMM area.
+	 * Don't do it for gbpages because there seems very little
+	 * benefit in doing so.
+	 */
+	if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
+		unsigned long pfn = tseg >> PAGE_SHIFT;
+
+		pr_debug("tseg: %010llx\n", tseg);
+		if (pfn_range_is_mapped(pfn, pfn + 1))
+			set_memory_4k((unsigned long)__va(tseg), 1);
+	}
+#endif
+
+	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
+		u64 val;
+
+		rdmsrl(MSR_K7_HWCR, val);
+		if (!(val & BIT(24)))
+			pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n");
+	}
+
+	if (cpu_has(c, X86_FEATURE_MWAITX))
+		use_mwaitx_delay();
+
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+		u32 ecx;
+
+		ecx = cpuid_ecx(0x8000001e);
+		nodes_per_socket = ((ecx >> 8) & 7) + 1;
+	} else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
+		u64 value;
+
+		rdmsrl(MSR_FAM10H_NODE_ID, value);
+		nodes_per_socket = ((value >> 3) & 7) + 1;
+	}
+
+	if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) &&
+	    !boot_cpu_has(X86_FEATURE_VIRT_SSBD)) {
+		/*
+		 * Try to cache the base value so further operations can
+		 * avoid RMW. If that faults, do not enable SSBD.
+		 */
+		if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+			setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD);
+			setup_force_cpu_cap(X86_FEATURE_SSBD);
+			x86_amd_ls_cfg_ssbd_mask = 1ULL << 10;
+		}
+	}
+}
+
+static void early_init_hygon(struct cpuinfo_x86 *c)
+{
+	u32 dummy;
+
+	early_init_hygon_mc(c);
+
+	set_cpu_cap(c, X86_FEATURE_K8);
+
+	rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
+
+	/*
+	 * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate
+	 * with P/T states and does not stop in deep C-states
+	 */
+	if (c->x86_power & (1 << 8)) {
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+	}
+
+	/* Bit 12 of 8000_0007 edx is accumulated power mechanism. */
+	if (c->x86_power & BIT(12))
+		set_cpu_cap(c, X86_FEATURE_ACC_POWER);
+
+#ifdef CONFIG_X86_64
+	set_cpu_cap(c, X86_FEATURE_SYSCALL32);
+#endif
+
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI)
+	/*
+	 * ApicID can always be treated as an 8-bit value for Hygon APIC So, we
+	 * can safely set X86_FEATURE_EXTD_APICID unconditionally.
+	 */
+	if (boot_cpu_has(X86_FEATURE_APIC))
+		set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
+#endif
+
+	/*
+	 * This is only needed to tell the kernel whether to use VMCALL
+	 * and VMMCALL.  VMMCALL is never executed except under virt, so
+	 * we can set it unconditionally.
+	 */
+	set_cpu_cap(c, X86_FEATURE_VMMCALL);
+
+	hygon_get_topology_early(c);
+}
+
+static void init_hygon(struct cpuinfo_x86 *c)
+{
+	early_init_hygon(c);
+
+	/*
+	 * Bit 31 in normal CPUID used for nonstandard 3DNow ID;
+	 * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway
+	 */
+	clear_cpu_cap(c, 0*32+31);
+
+	set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+	/* get apicid instead of initial apic id from cpuid */
+	c->apicid = hard_smp_processor_id();
+
+	set_cpu_cap(c, X86_FEATURE_ZEN);
+	set_cpu_cap(c, X86_FEATURE_CPB);
+
+	cpu_detect_cache_sizes(c);
+
+	hygon_detect_cmp(c);
+	hygon_get_topology(c);
+	srat_detect_node(c);
+
+	init_hygon_cacheinfo(c);
+
+	if (cpu_has(c, X86_FEATURE_XMM2)) {
+		unsigned long long val;
+		int ret;
+
+		/*
+		 * A serializing LFENCE has less overhead than MFENCE, so
+		 * use it for execution serialization.  On families which
+		 * don't have that MSR, LFENCE is already serializing.
+		 * msr_set_bit() uses the safe accessors, too, even if the MSR
+		 * is not present.
+		 */
+		msr_set_bit(MSR_F10H_DECFG,
+			    MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
+
+		/*
+		 * Verify that the MSR write was successful (could be running
+		 * under a hypervisor) and only then assume that LFENCE is
+		 * serializing.
+		 */
+		ret = rdmsrl_safe(MSR_F10H_DECFG, &val);
+		if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) {
+			/* A serializing LFENCE stops RDTSC speculation */
+			set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+		} else {
+			/* MFENCE stops RDTSC speculation */
+			set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+		}
+	}
+
+	/*
+	 * Hygon processors have APIC timer running in deep C states.
+	 */
+	set_cpu_cap(c, X86_FEATURE_ARAT);
+
+	/* Hygon CPUs don't reset SS attributes on SYSRET, Xen does. */
+	if (!cpu_has(c, X86_FEATURE_XENPV))
+		set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+}
+
+static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c)
+{
+	u32 ebx, eax, ecx, edx;
+	u16 mask = 0xfff;
+
+	if (c->extended_cpuid_level < 0x80000006)
+		return;
+
+	cpuid(0x80000006, &eax, &ebx, &ecx, &edx);
+
+	tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask;
+	tlb_lli_4k[ENTRIES] = ebx & mask;
+
+	/* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
+	if (!((eax >> 16) & mask))
+		tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff;
+	else
+		tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
+
+	/* a 4M entry uses two 2M entries */
+	tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
+
+	/* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
+	if (!(eax & mask)) {
+		cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
+		tlb_lli_2m[ENTRIES] = eax & 0xff;
+	} else
+		tlb_lli_2m[ENTRIES] = eax & mask;
+
+	tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+}
+
+static const struct cpu_dev hygon_cpu_dev = {
+	.c_vendor	= "Hygon",
+	.c_ident	= { "HygonGenuine" },
+	.c_early_init   = early_init_hygon,
+	.c_detect_tlb	= cpu_detect_tlb_hygon,
+	.c_bsp_init	= bsp_init_hygon,
+	.c_init		= init_hygon,
+	.c_x86_vendor	= X86_VENDOR_HYGON,
+};
+
+cpu_dev_register(hygon_cpu_dev);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index f34d89c01edc..44396d521987 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -336,7 +336,8 @@ int (*mce_severity)(struct mce *m, int tolerant, char **msg, bool is_excp) =
 
 void __init mcheck_vendor_init_severity(void)
 {
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
 		mce_severity = mce_severity_amd;
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index ef8fd1f2ede0..8cb3c02980cf 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -270,7 +270,7 @@ static void print_mce(struct mce *m)
 {
 	__print_mce(m);
 
-	if (m->cpuvendor != X86_VENDOR_AMD)
+	if (m->cpuvendor != X86_VENDOR_AMD && m->cpuvendor != X86_VENDOR_HYGON)
 		pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
 }
 
@@ -508,9 +508,9 @@ static int mce_usable_address(struct mce *m)
 
 bool mce_is_memory_error(struct mce *m)
 {
-	if (m->cpuvendor == X86_VENDOR_AMD) {
+	if (m->cpuvendor == X86_VENDOR_AMD ||
+	    m->cpuvendor == X86_VENDOR_HYGON) {
 		return amd_mce_is_memory_error(m);
-
 	} else if (m->cpuvendor == X86_VENDOR_INTEL) {
 		/*
 		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
@@ -539,6 +539,9 @@ static bool mce_is_correctable(struct mce *m)
 	if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
 		return false;
 
+	if (m->cpuvendor == X86_VENDOR_HYGON && m->status & MCI_STATUS_DEFERRED)
+		return false;
+
 	if (m->status & MCI_STATUS_UC)
 		return false;
 
@@ -1705,7 +1708,7 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
  */
 static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
 {
-	if (c->x86_vendor == X86_VENDOR_AMD) {
+	if (c->x86_vendor == X86_VENDOR_AMD || c->x86_vendor == X86_VENDOR_HYGON) {
 		mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV);
 		mce_flags.succor	 = !!cpu_has(c, X86_FEATURE_SUCCOR);
 		mce_flags.smca		 = !!cpu_has(c, X86_FEATURE_SMCA);
@@ -1746,6 +1749,11 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 		mce_amd_feature_init(c);
 		break;
 		}
+
+	case X86_VENDOR_HYGON:
+		mce_hygon_feature_init(c);
+		break;
+
 	case X86_VENDOR_CENTAUR:
 		mce_centaur_feature_init(c);
 		break;
@@ -1971,12 +1979,14 @@ static void mce_disable_error_reporting(void)
 static void vendor_disable_error_reporting(void)
 {
 	/*
-	 * Don't clear on Intel or AMD CPUs. Some of these MSRs are socket-wide.
+	 * Don't clear on Intel or AMD or Hygon CPUs. Some of these MSRs
+	 * are socket-wide.
 	 * Disabling them for just a single offlined CPU is bad, since it will
 	 * inhibit reporting for all shared resources on the socket like the
 	 * last level cache (LLC), the integrated memory controller (iMC), etc.
 	 */
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL ||
+	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ||
 	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
 		return;
 
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 765afd599039..3668c5df90c6 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -831,7 +831,8 @@ int __init amd_special_default_mtrr(void)
 {
 	u32 l, h;
 
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
 		return 0;
 	if (boot_cpu_data.x86 < 0xf)
 		return 0;
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c
index 9a19c800fe40..507039c20128 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.c
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.c
@@ -127,7 +127,7 @@ static void __init set_num_var_ranges(void)
 
 	if (use_intel())
 		rdmsr(MSR_MTRRcap, config, dummy);
-	else if (is_cpu(AMD))
+	else if (is_cpu(AMD) || is_cpu(HYGON))
 		config = 2;
 	else if (is_cpu(CYRIX) || is_cpu(CENTAUR))
 		config = 8;
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index d389083330c5..9556930cd8c1 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -46,6 +46,7 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
 {
 	/* returns the bit offset of the performance counter register */
 	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_HYGON:
 	case X86_VENDOR_AMD:
 		if (msr >= MSR_F15H_PERF_CTR)
 			return (msr - MSR_F15H_PERF_CTR) >> 1;
@@ -74,6 +75,7 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
 {
 	/* returns the bit offset of the event selection register */
 	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_HYGON:
 	case X86_VENDOR_AMD:
 		if (msr >= MSR_F15H_PERF_CTL)
 			return (msr - MSR_F15H_PERF_CTL) >> 1;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f02ecaf97904..5369d7fac797 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -676,6 +676,7 @@ static void __init smp_quirk_init_udelay(void)
 
 	/* if modern processor, use no delay */
 	if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
+	    ((boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) && (boot_cpu_data.x86 >= 0x18)) ||
 	    ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) {
 		init_udelay = 0;
 		return;
@@ -1592,7 +1593,8 @@ static inline void mwait_play_dead(void)
 	void *mwait_ptr;
 	int i;
 
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
 		return;
 	if (!this_cpu_has(X86_FEATURE_MWAIT))
 		return;