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

Pull x86 CPU feature updates from Thomas Gleixner:
 "Updates for x86 CPU features:

   - Support for UMWAIT/UMONITOR, which allows to use MWAIT and MONITOR
     instructions in user space to save power e.g. in HPC workloads
     which spin wait on synchronization points.

     The maximum time a MWAIT can halt in userspace is controlled by the
     kernel and can be adjusted by the sysadmin.

   - Speed up the MTRR handling code on CPUs which support cache
     self-snooping correctly.

     On those CPUs the wbinvd() invocations can be omitted which speeds
     up the MTRR setup by a factor of 50.

   - Support for the new x86 vendor Zhaoxin who develops processors
     based on the VIA Centaur technology.

   - Prevent 'cat /proc/cpuinfo' from affecting isolated NOHZ_FULL CPUs
     by sending IPIs to retrieve the CPU frequency and use the cached
     values instead.

   - The addition and late revert of the FSGSBASE support. The revert
     was required as it turned out that the code still has hard to
     diagnose issues. Yet another engineering trainwreck...

   - Small fixes, cleanups, improvements and the usual new Intel CPU
     family/model addons"

* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
  x86/fsgsbase: Revert FSGSBASE support
  selftests/x86/fsgsbase: Fix some test case bugs
  x86/entry/64: Fix and clean up paranoid_exit
  x86/entry/64: Don't compile ignore_sysret if 32-bit emulation is enabled
  selftests/x86: Test SYSCALL and SYSENTER manually with TF set
  x86/mtrr: Skip cache flushes on CPUs with cache self-snooping
  x86/cpu/intel: Clear cache self-snoop capability in CPUs with known errata
  Documentation/ABI: Document umwait control sysfs interfaces
  x86/umwait: Add sysfs interface to control umwait maximum time
  x86/umwait: Add sysfs interface to control umwait C0.2 state
  x86/umwait: Initialize umwait control values
  x86/cpufeatures: Enumerate user wait instructions
  x86/cpu: Disable frequency requests via aperfmperf IPI for nohz_full CPUs
  x86/acpi/cstate: Add Zhaoxin processors support for cache flush policy in C3
  ACPI, x86: Add Zhaoxin processors support for NONSTOP TSC
  x86/cpu: Create Zhaoxin processors architecture support file
  x86/cpu: Split Tremont based Atoms from the rest
  Documentation/x86/64: Add documentation for GS/FS addressing mode
  x86/elf: Enumerate kernel FSGSBASE capability in AT_HWCAP2
  x86/cpu: Enable FSGSBASE on 64bit by default and add a chicken bit
  ...

10 files changed, 460 insertions, 32 deletions

diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 5102bf7c8192..4b4eb06e117c 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -24,6 +24,7 @@ obj-y			+= match.o
 obj-y			+= bugs.o
 obj-y			+= aperfmperf.o
 obj-y			+= cpuid-deps.o
+obj-y			+= umwait.o
 
 obj-$(CONFIG_PROC_FS)	+= proc.o
 obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
@@ -38,6 +39,7 @@ obj-$(CONFIG_CPU_SUP_CYRIX_32)		+= cyrix.o
 obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
 obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
+obj-$(CONFIG_CPU_SUP_ZHAOXIN)		+= zhaoxin.o
 
 obj-$(CONFIG_X86_MCE)			+= mce/
 obj-$(CONFIG_MTRR)			+= mtrr/
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index e71a6ff8a67e..e2f319dc992d 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -13,6 +13,7 @@
 #include <linux/percpu.h>
 #include <linux/cpufreq.h>
 #include <linux/smp.h>
+#include <linux/sched/isolation.h>
 
 #include "cpu.h"
 
@@ -85,6 +86,9 @@ unsigned int aperfmperf_get_khz(int cpu)
 	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
+	if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+		return 0;
+
 	aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
 	return per_cpu(samples.khz, cpu);
 }
@@ -101,9 +105,12 @@ void arch_freq_prepare_all(void)
 	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return;
 
-	for_each_online_cpu(cpu)
+	for_each_online_cpu(cpu) {
+		if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+			continue;
 		if (!aperfmperf_snapshot_cpu(cpu, now, false))
 			wait = true;
+	}
 
 	if (wait)
 		msleep(APERFMPERF_REFRESH_DELAY_MS);
@@ -117,6 +124,9 @@ unsigned int arch_freq_get_on_cpu(int cpu)
 	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
+	if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+		return 0;
+
 	if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
 		return per_cpu(samples.khz, cpu);
 
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 395d46f78582..c7503be92f35 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -658,8 +658,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
 	if (c->x86 < 0x17) {
 		/* LLC is at the node level. */
 		per_cpu(cpu_llc_id, cpu) = node_id;
-	} else if (c->x86 == 0x17 &&
-		   c->x86_model >= 0 && c->x86_model <= 0x1F) {
+	} else if (c->x86 == 0x17 && c->x86_model <= 0x1F) {
 		/*
 		 * LLC is at the core complex level.
 		 * Core complex ID is ApicId[3] for these processors.
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2c57fffebf9b..dad20bc891d5 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -801,6 +801,30 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
 	}
 }
 
+static void init_cqm(struct cpuinfo_x86 *c)
+{
+	if (!cpu_has(c, X86_FEATURE_CQM_LLC)) {
+		c->x86_cache_max_rmid  = -1;
+		c->x86_cache_occ_scale = -1;
+		return;
+	}
+
+	/* will be overridden if occupancy monitoring exists */
+	c->x86_cache_max_rmid = cpuid_ebx(0xf);
+
+	if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) ||
+	    cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) ||
+	    cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) {
+		u32 eax, ebx, ecx, edx;
+
+		/* QoS sub-leaf, EAX=0Fh, ECX=1 */
+		cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx);
+
+		c->x86_cache_max_rmid  = ecx;
+		c->x86_cache_occ_scale = ebx;
+	}
+}
+
 void get_cpu_cap(struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
@@ -823,6 +847,12 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_7_0_EBX] = ebx;
 		c->x86_capability[CPUID_7_ECX] = ecx;
 		c->x86_capability[CPUID_7_EDX] = edx;
+
+		/* Check valid sub-leaf index before accessing it */
+		if (eax >= 1) {
+			cpuid_count(0x00000007, 1, &eax, &ebx, &ecx, &edx);
+			c->x86_capability[CPUID_7_1_EAX] = eax;
+		}
 	}
 
 	/* Extended state features: level 0x0000000d */
@@ -832,33 +862,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_D_1_EAX] = eax;
 	}
 
-	/* Additional Intel-defined flags: level 0x0000000F */
-	if (c->cpuid_level >= 0x0000000F) {
-
-		/* QoS sub-leaf, EAX=0Fh, ECX=0 */
-		cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
-		c->x86_capability[CPUID_F_0_EDX] = edx;
-
-		if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
-			/* will be overridden if occupancy monitoring exists */
-			c->x86_cache_max_rmid = ebx;
-
-			/* QoS sub-leaf, EAX=0Fh, ECX=1 */
-			cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
-			c->x86_capability[CPUID_F_1_EDX] = edx;
-
-			if ((cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) ||
-			      ((cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL)) ||
-			       (cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)))) {
-				c->x86_cache_max_rmid = ecx;
-				c->x86_cache_occ_scale = ebx;
-			}
-		} else {
-			c->x86_cache_max_rmid = -1;
-			c->x86_cache_occ_scale = -1;
-		}
-	}
-
 	/* AMD-defined flags: level 0x80000001 */
 	eax = cpuid_eax(0x80000000);
 	c->extended_cpuid_level = eax;
@@ -889,6 +892,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 
 	init_scattered_cpuid_features(c);
 	init_speculation_control(c);
+	init_cqm(c);
 
 	/*
 	 * Clear/Set all flags overridden by options, after probe.
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index e794e3860fc8..b5353244749b 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -64,6 +64,10 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_AVX512_4VNNIW,	X86_FEATURE_AVX512F   },
 	{ X86_FEATURE_AVX512_4FMAPS,	X86_FEATURE_AVX512F   },
 	{ X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F   },
+	{ X86_FEATURE_CQM_OCCUP_LLC,	X86_FEATURE_CQM_LLC   },
+	{ X86_FEATURE_CQM_MBM_TOTAL,	X86_FEATURE_CQM_LLC   },
+	{ X86_FEATURE_CQM_MBM_LOCAL,	X86_FEATURE_CQM_LLC   },
+	{ X86_FEATURE_AVX512_BF16,	X86_FEATURE_AVX512VL  },
 	{}
 };
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index f17c1a714779..8d6d92ebeb54 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -66,6 +66,32 @@ void check_mpx_erratum(struct cpuinfo_x86 *c)
 	}
 }
 
+/*
+ * Processors which have self-snooping capability can handle conflicting
+ * memory type across CPUs by snooping its own cache. However, there exists
+ * CPU models in which having conflicting memory types still leads to
+ * unpredictable behavior, machine check errors, or hangs. Clear this
+ * feature to prevent its use on machines with known erratas.
+ */
+static void check_memory_type_self_snoop_errata(struct cpuinfo_x86 *c)
+{
+	switch (c->x86_model) {
+	case INTEL_FAM6_CORE_YONAH:
+	case INTEL_FAM6_CORE2_MEROM:
+	case INTEL_FAM6_CORE2_MEROM_L:
+	case INTEL_FAM6_CORE2_PENRYN:
+	case INTEL_FAM6_CORE2_DUNNINGTON:
+	case INTEL_FAM6_NEHALEM:
+	case INTEL_FAM6_NEHALEM_G:
+	case INTEL_FAM6_NEHALEM_EP:
+	case INTEL_FAM6_NEHALEM_EX:
+	case INTEL_FAM6_WESTMERE:
+	case INTEL_FAM6_WESTMERE_EP:
+	case INTEL_FAM6_SANDYBRIDGE:
+		setup_clear_cpu_cap(X86_FEATURE_SELFSNOOP);
+	}
+}
+
 static bool ring3mwait_disabled __read_mostly;
 
 static int __init ring3mwait_disable(char *__unused)
@@ -304,6 +330,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	}
 
 	check_mpx_erratum(c);
+	check_memory_type_self_snoop_errata(c);
 
 	/*
 	 * Get the number of SMT siblings early from the extended topology
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 9356c1c9024d..aa5c064a6a22 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -743,7 +743,15 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 	/* Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */
 	cr0 = read_cr0() | X86_CR0_CD;
 	write_cr0(cr0);
-	wbinvd();
+
+	/*
+	 * Cache flushing is the most time-consuming step when programming
+	 * the MTRRs. Fortunately, as per the Intel Software Development
+	 * Manual, we can skip it if the processor supports cache self-
+	 * snooping.
+	 */
+	if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
+		wbinvd();
 
 	/* Save value of CR4 and clear Page Global Enable (bit 7) */
 	if (boot_cpu_has(X86_FEATURE_PGE)) {
@@ -760,7 +768,10 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 
 	/* Disable MTRRs, and set the default type to uncached */
 	mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi);
-	wbinvd();
+
+	/* Again, only flush caches if we have to. */
+	if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
+		wbinvd();
 }
 
 static void post_set(void) __releases(set_atomicity_lock)
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 94aa1c72ca98..adf9b71386ef 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -26,6 +26,10 @@ struct cpuid_bit {
 static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
 	{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
+	{ X86_FEATURE_CQM_LLC,		CPUID_EDX,  1, 0x0000000f, 0 },
+	{ X86_FEATURE_CQM_OCCUP_LLC,	CPUID_EDX,  0, 0x0000000f, 1 },
+	{ X86_FEATURE_CQM_MBM_TOTAL,	CPUID_EDX,  1, 0x0000000f, 1 },
+	{ X86_FEATURE_CQM_MBM_LOCAL,	CPUID_EDX,  2, 0x0000000f, 1 },
 	{ X86_FEATURE_CAT_L3,		CPUID_EBX,  1, 0x00000010, 0 },
 	{ X86_FEATURE_CAT_L2,		CPUID_EBX,  2, 0x00000010, 0 },
 	{ X86_FEATURE_CDP_L3,		CPUID_ECX,  2, 0x00000010, 1 },
diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c
new file mode 100644
index 000000000000..6a204e7336c1
--- /dev/null
+++ b/arch/x86/kernel/cpu/umwait.c
@@ -0,0 +1,200 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/syscore_ops.h>
+#include <linux/suspend.h>
+#include <linux/cpu.h>
+
+#include <asm/msr.h>
+
+#define UMWAIT_C02_ENABLE	0
+
+#define UMWAIT_CTRL_VAL(max_time, c02_disable)				\
+	(((max_time) & MSR_IA32_UMWAIT_CONTROL_TIME_MASK) |		\
+	((c02_disable) & MSR_IA32_UMWAIT_CONTROL_C02_DISABLE))
+
+/*
+ * Cache IA32_UMWAIT_CONTROL MSR. This is a systemwide control. By default,
+ * umwait max time is 100000 in TSC-quanta and C0.2 is enabled
+ */
+static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE);
+
+/*
+ * Serialize access to umwait_control_cached and IA32_UMWAIT_CONTROL MSR in
+ * the sysfs write functions.
+ */
+static DEFINE_MUTEX(umwait_lock);
+
+static void umwait_update_control_msr(void * unused)
+{
+	lockdep_assert_irqs_disabled();
+	wrmsr(MSR_IA32_UMWAIT_CONTROL, READ_ONCE(umwait_control_cached), 0);
+}
+
+/*
+ * The CPU hotplug callback sets the control MSR to the global control
+ * value.
+ *
+ * Disable interrupts so the read of umwait_control_cached and the WRMSR
+ * are protected against a concurrent sysfs write. Otherwise the sysfs
+ * write could update the cached value after it had been read on this CPU
+ * and issue the IPI before the old value had been written. The IPI would
+ * interrupt, write the new value and after return from IPI the previous
+ * value would be written by this CPU.
+ *
+ * With interrupts disabled the upcoming CPU either sees the new control
+ * value or the IPI is updating this CPU to the new control value after
+ * interrupts have been reenabled.
+ */
+static int umwait_cpu_online(unsigned int cpu)
+{
+	local_irq_disable();
+	umwait_update_control_msr(NULL);
+	local_irq_enable();
+	return 0;
+}
+
+/*
+ * On resume, restore IA32_UMWAIT_CONTROL MSR on the boot processor which
+ * is the only active CPU at this time. The MSR is set up on the APs via the
+ * CPU hotplug callback.
+ *
+ * This function is invoked on resume from suspend and hibernation. On
+ * resume from suspend the restore should be not required, but we neither
+ * trust the firmware nor does it matter if the same value is written
+ * again.
+ */
+static void umwait_syscore_resume(void)
+{
+	umwait_update_control_msr(NULL);
+}
+
+static struct syscore_ops umwait_syscore_ops = {
+	.resume	= umwait_syscore_resume,
+};
+
+/* sysfs interface */
+
+/*
+ * When bit 0 in IA32_UMWAIT_CONTROL MSR is 1, C0.2 is disabled.
+ * Otherwise, C0.2 is enabled.
+ */
+static inline bool umwait_ctrl_c02_enabled(u32 ctrl)
+{
+	return !(ctrl & MSR_IA32_UMWAIT_CONTROL_C02_DISABLE);
+}
+
+static inline u32 umwait_ctrl_max_time(u32 ctrl)
+{
+	return ctrl & MSR_IA32_UMWAIT_CONTROL_TIME_MASK;
+}
+
+static inline void umwait_update_control(u32 maxtime, bool c02_enable)
+{
+	u32 ctrl = maxtime & MSR_IA32_UMWAIT_CONTROL_TIME_MASK;
+
+	if (!c02_enable)
+		ctrl |= MSR_IA32_UMWAIT_CONTROL_C02_DISABLE;
+
+	WRITE_ONCE(umwait_control_cached, ctrl);
+	/* Propagate to all CPUs */
+	on_each_cpu(umwait_update_control_msr, NULL, 1);
+}
+
+static ssize_t
+enable_c02_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	u32 ctrl = READ_ONCE(umwait_control_cached);
+
+	return sprintf(buf, "%d\n", umwait_ctrl_c02_enabled(ctrl));
+}
+
+static ssize_t enable_c02_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	bool c02_enable;
+	u32 ctrl;
+	int ret;
+
+	ret = kstrtobool(buf, &c02_enable);
+	if (ret)
+		return ret;
+
+	mutex_lock(&umwait_lock);
+
+	ctrl = READ_ONCE(umwait_control_cached);
+	if (c02_enable != umwait_ctrl_c02_enabled(ctrl))
+		umwait_update_control(ctrl, c02_enable);
+
+	mutex_unlock(&umwait_lock);
+
+	return count;
+}
+static DEVICE_ATTR_RW(enable_c02);
+
+static ssize_t
+max_time_show(struct device *kobj, struct device_attribute *attr, char *buf)
+{
+	u32 ctrl = READ_ONCE(umwait_control_cached);
+
+	return sprintf(buf, "%u\n", umwait_ctrl_max_time(ctrl));
+}
+
+static ssize_t max_time_store(struct device *kobj,
+			      struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	u32 max_time, ctrl;
+	int ret;
+
+	ret = kstrtou32(buf, 0, &max_time);
+	if (ret)
+		return ret;
+
+	/* bits[1:0] must be zero */
+	if (max_time & ~MSR_IA32_UMWAIT_CONTROL_TIME_MASK)
+		return -EINVAL;
+
+	mutex_lock(&umwait_lock);
+
+	ctrl = READ_ONCE(umwait_control_cached);
+	if (max_time != umwait_ctrl_max_time(ctrl))
+		umwait_update_control(max_time, umwait_ctrl_c02_enabled(ctrl));
+
+	mutex_unlock(&umwait_lock);
+
+	return count;
+}
+static DEVICE_ATTR_RW(max_time);
+
+static struct attribute *umwait_attrs[] = {
+	&dev_attr_enable_c02.attr,
+	&dev_attr_max_time.attr,
+	NULL
+};
+
+static struct attribute_group umwait_attr_group = {
+	.attrs = umwait_attrs,
+	.name = "umwait_control",
+};
+
+static int __init umwait_init(void)
+{
+	struct device *dev;
+	int ret;
+
+	if (!boot_cpu_has(X86_FEATURE_WAITPKG))
+		return -ENODEV;
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "umwait:online",
+				umwait_cpu_online, NULL);
+
+	register_syscore_ops(&umwait_syscore_ops);
+
+	/*
+	 * Add umwait control interface. Ignore failure, so at least the
+	 * default values are set up in case the machine manages to boot.
+	 */
+	dev = cpu_subsys.dev_root;
+	return sysfs_create_group(&dev->kobj, &umwait_attr_group);
+}
+device_initcall(umwait_init);
diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c
new file mode 100644
index 000000000000..8e6f2f4b4afe
--- /dev/null
+++ b/arch/x86/kernel/cpu/zhaoxin.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
+
+#include <asm/cpufeature.h>
+
+#include "cpu.h"
+
+#define MSR_ZHAOXIN_FCR57 0x00001257
+
+#define ACE_PRESENT	(1 << 6)
+#define ACE_ENABLED	(1 << 7)
+#define ACE_FCR		(1 << 7)	/* MSR_ZHAOXIN_FCR */
+
+#define RNG_PRESENT	(1 << 2)
+#define RNG_ENABLED	(1 << 3)
+#define RNG_ENABLE	(1 << 8)	/* MSR_ZHAOXIN_RNG */
+
+#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW	0x00200000
+#define X86_VMX_FEATURE_PROC_CTLS_VNMI		0x00400000
+#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS	0x80000000
+#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC	0x00000001
+#define X86_VMX_FEATURE_PROC_CTLS2_EPT		0x00000002
+#define X86_VMX_FEATURE_PROC_CTLS2_VPID		0x00000020
+
+static void init_zhaoxin_cap(struct cpuinfo_x86 *c)
+{
+	u32  lo, hi;
+
+	/* Test for Extended Feature Flags presence */
+	if (cpuid_eax(0xC0000000) >= 0xC0000001) {
+		u32 tmp = cpuid_edx(0xC0000001);
+
+		/* Enable ACE unit, if present and disabled */
+		if ((tmp & (ACE_PRESENT | ACE_ENABLED)) == ACE_PRESENT) {
+			rdmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+			/* Enable ACE unit */
+			lo |= ACE_FCR;
+			wrmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+			pr_info("CPU: Enabled ACE h/w crypto\n");
+		}
+
+		/* Enable RNG unit, if present and disabled */
+		if ((tmp & (RNG_PRESENT | RNG_ENABLED)) == RNG_PRESENT) {
+			rdmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+			/* Enable RNG unit */
+			lo |= RNG_ENABLE;
+			wrmsr(MSR_ZHAOXIN_FCR57, lo, hi);
+			pr_info("CPU: Enabled h/w RNG\n");
+		}
+
+		/*
+		 * Store Extended Feature Flags as word 5 of the CPU
+		 * capability bit array
+		 */
+		c->x86_capability[CPUID_C000_0001_EDX] = cpuid_edx(0xC0000001);
+	}
+
+	if (c->x86 >= 0x6)
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+	cpu_detect_cache_sizes(c);
+}
+
+static void early_init_zhaoxin(struct cpuinfo_x86 *c)
+{
+	if (c->x86 >= 0x6)
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+#ifdef CONFIG_X86_64
+	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
+#endif
+	if (c->x86_power & (1 << 8)) {
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+	}
+
+	if (c->cpuid_level >= 0x00000001) {
+		u32 eax, ebx, ecx, edx;
+
+		cpuid(0x00000001, &eax, &ebx, &ecx, &edx);
+		/*
+		 * If HTT (EDX[28]) is set EBX[16:23] contain the number of
+		 * apicids which are reserved per package. Store the resulting
+		 * shift value for the package management code.
+		 */
+		if (edx & (1U << 28))
+			c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff);
+	}
+
+}
+
+static void zhaoxin_detect_vmx_virtcap(struct cpuinfo_x86 *c)
+{
+	u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
+
+	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
+	msr_ctl = vmx_msr_high | vmx_msr_low;
+
+	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)
+		set_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
+	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI)
+		set_cpu_cap(c, X86_FEATURE_VNMI);
+	if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) {
+		rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
+		      vmx_msr_low, vmx_msr_high);
+		msr_ctl2 = vmx_msr_high | vmx_msr_low;
+		if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
+		    (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
+			set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
+		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
+			set_cpu_cap(c, X86_FEATURE_EPT);
+		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
+			set_cpu_cap(c, X86_FEATURE_VPID);
+	}
+}
+
+static void init_zhaoxin(struct cpuinfo_x86 *c)
+{
+	early_init_zhaoxin(c);
+	init_intel_cacheinfo(c);
+	detect_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+	detect_ht(c);
+#endif
+
+	if (c->cpuid_level > 9) {
+		unsigned int eax = cpuid_eax(10);
+
+		/*
+		 * Check for version and the number of counters
+		 * Version(eax[7:0]) can't be 0;
+		 * Counters(eax[15:8]) should be greater than 1;
+		 */
+		if ((eax & 0xff) && (((eax >> 8) & 0xff) > 1))
+			set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
+	}
+
+	if (c->x86 >= 0x6)
+		init_zhaoxin_cap(c);
+#ifdef CONFIG_X86_64
+	set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+#endif
+
+	if (cpu_has(c, X86_FEATURE_VMX))
+		zhaoxin_detect_vmx_virtcap(c);
+}
+
+#ifdef CONFIG_X86_32
+static unsigned int
+zhaoxin_size_cache(struct cpuinfo_x86 *c, unsigned int size)
+{
+	return size;
+}
+#endif
+
+static const struct cpu_dev zhaoxin_cpu_dev = {
+	.c_vendor	= "zhaoxin",
+	.c_ident	= { "  Shanghai  " },
+	.c_early_init	= early_init_zhaoxin,
+	.c_init		= init_zhaoxin,
+#ifdef CONFIG_X86_32
+	.legacy_cache_size = zhaoxin_size_cache,
+#endif
+	.c_x86_vendor	= X86_VENDOR_ZHAOXIN,
+};
+
+cpu_dev_register(zhaoxin_cpu_dev);