16 files changed, 586 insertions, 40 deletions
diff --git a/arch/x86/kernel/cpu/.gitignore b/arch/x86/kernel/cpu/.gitignore
index 667df55a4399..0bca7ef7426a 100644
--- a/arch/x86/kernel/cpu/.gitignore
+++ b/arch/x86/kernel/cpu/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 capflags.c
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1f875fbe1384..547ad7bbf0e0 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -394,6 +394,35 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
 	per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
 }
 
+static void amd_detect_ppin(struct cpuinfo_x86 *c)
+{
+	unsigned long long val;
+
+	if (!cpu_has(c, X86_FEATURE_AMD_PPIN))
+		return;
+
+	/* When PPIN is defined in CPUID, still need to check PPIN_CTL MSR */
+	if (rdmsrl_safe(MSR_AMD_PPIN_CTL, &val))
+		goto clear_ppin;
+
+	/* PPIN is locked in disabled mode, clear feature bit */
+	if ((val & 3UL) == 1UL)
+		goto clear_ppin;
+
+	/* If PPIN is disabled, try to enable it */
+	if (!(val & 2UL)) {
+		wrmsrl_safe(MSR_AMD_PPIN_CTL,  val | 2UL);
+		rdmsrl_safe(MSR_AMD_PPIN_CTL, &val);
+	}
+
+	/* If PPIN_EN bit is 1, return from here; otherwise fall through */
+	if (val & 2UL)
+		return;
+
+clear_ppin:
+	clear_cpu_cap(c, X86_FEATURE_AMD_PPIN);
+}
+
 u16 amd_get_nb_id(int cpu)
 {
 	return per_cpu(cpu_llc_id, cpu);
@@ -926,7 +955,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 	case 0x12: init_amd_ln(c); break;
 	case 0x15: init_amd_bd(c); break;
 	case 0x16: init_amd_jg(c); break;
-	case 0x17: init_amd_zn(c); break;
+	case 0x17: fallthrough;
+	case 0x19: init_amd_zn(c); break;
 	}
 
 	/*
@@ -941,6 +971,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 	amd_detect_cmp(c);
 	amd_get_topology(c);
 	srat_detect_node(c);
+	amd_detect_ppin(c);
 
 	init_amd_cacheinfo(c);
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4cdb123ff66a..bed0cb83fe24 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1008,8 +1008,8 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #define NO_ITLB_MULTIHIT	BIT(7)
 #define NO_SPECTRE_V2		BIT(8)
 
-#define VULNWL(_vendor, _family, _model, _whitelist)	\
-	{ X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
+#define VULNWL(vendor, family, model, whitelist)	\
+	X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist)
 
 #define VULNWL_INTEL(model, whitelist)		\
 	VULNWL(INTEL, 6, INTEL_FAM6_##model, whitelist)
@@ -1224,6 +1224,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 
 	cpu_set_bug_bits(c);
 
+	cpu_set_core_cap_bits(c);
+
 	fpu__init_system(c);
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c
index 0268185bef94..29a3bedabd06 100644
--- a/arch/x86/kernel/cpu/feat_ctl.c
+++ b/arch/x86/kernel/cpu/feat_ctl.c
@@ -5,6 +5,7 @@
 #include <asm/msr-index.h>
 #include <asm/processor.h>
 #include <asm/vmx.h>
+#include "cpu.h"
 
 #undef pr_fmt
 #define pr_fmt(fmt)	"x86/cpu: " fmt
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index be82cd5841c3..a19a680542ce 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -19,6 +19,9 @@
 #include <asm/microcode_intel.h>
 #include <asm/hwcap2.h>
 #include <asm/elf.h>
+#include <asm/cpu_device_id.h>
+#include <asm/cmdline.h>
+#include <asm/traps.h>
 
 #ifdef CONFIG_X86_64
 #include <linux/topology.h>
@@ -31,6 +34,20 @@
 #include <asm/apic.h>
 #endif
 
+enum split_lock_detect_state {
+	sld_off = 0,
+	sld_warn,
+	sld_fatal,
+};
+
+/*
+ * Default to sld_off because most systems do not support split lock detection
+ * split_lock_setup() will switch this to sld_warn on systems that support
+ * split lock detect, unless there is a command line override.
+ */
+static enum split_lock_detect_state sld_state __ro_after_init = sld_off;
+static u64 msr_test_ctrl_cache __ro_after_init;
+
 /*
  * Processors which have self-snooping capability can handle conflicting
  * memory type across CPUs by snooping its own cache. However, there exists
@@ -570,6 +587,8 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c)
 	wrmsrl(MSR_MISC_FEATURES_ENABLES, msr);
 }
 
+static void split_lock_init(void);
+
 static void init_intel(struct cpuinfo_x86 *c)
 {
 	early_init_intel(c);
@@ -684,6 +703,8 @@ static void init_intel(struct cpuinfo_x86 *c)
 		tsx_enable();
 	if (tsx_ctrl_state == TSX_CTRL_DISABLE)
 		tsx_disable();
+
+	split_lock_init();
 }
 
 #ifdef CONFIG_X86_32
@@ -945,3 +966,206 @@ static const struct cpu_dev intel_cpu_dev = {
 };
 
 cpu_dev_register(intel_cpu_dev);
+
+#undef pr_fmt
+#define pr_fmt(fmt) "x86/split lock detection: " fmt
+
+static const struct {
+	const char			*option;
+	enum split_lock_detect_state	state;
+} sld_options[] __initconst = {
+	{ "off",	sld_off   },
+	{ "warn",	sld_warn  },
+	{ "fatal",	sld_fatal },
+};
+
+static inline bool match_option(const char *arg, int arglen, const char *opt)
+{
+	int len = strlen(opt);
+
+	return len == arglen && !strncmp(arg, opt, len);
+}
+
+static bool split_lock_verify_msr(bool on)
+{
+	u64 ctrl, tmp;
+
+	if (rdmsrl_safe(MSR_TEST_CTRL, &ctrl))
+		return false;
+	if (on)
+		ctrl |= MSR_TEST_CTRL_SPLIT_LOCK_DETECT;
+	else
+		ctrl &= ~MSR_TEST_CTRL_SPLIT_LOCK_DETECT;
+	if (wrmsrl_safe(MSR_TEST_CTRL, ctrl))
+		return false;
+	rdmsrl(MSR_TEST_CTRL, tmp);
+	return ctrl == tmp;
+}
+
+static void __init split_lock_setup(void)
+{
+	enum split_lock_detect_state state = sld_warn;
+	char arg[20];
+	int i, ret;
+
+	if (!split_lock_verify_msr(false)) {
+		pr_info("MSR access failed: Disabled\n");
+		return;
+	}
+
+	ret = cmdline_find_option(boot_command_line, "split_lock_detect",
+				  arg, sizeof(arg));
+	if (ret >= 0) {
+		for (i = 0; i < ARRAY_SIZE(sld_options); i++) {
+			if (match_option(arg, ret, sld_options[i].option)) {
+				state = sld_options[i].state;
+				break;
+			}
+		}
+	}
+
+	switch (state) {
+	case sld_off:
+		pr_info("disabled\n");
+		return;
+	case sld_warn:
+		pr_info("warning about user-space split_locks\n");
+		break;
+	case sld_fatal:
+		pr_info("sending SIGBUS on user-space split_locks\n");
+		break;
+	}
+
+	rdmsrl(MSR_TEST_CTRL, msr_test_ctrl_cache);
+
+	if (!split_lock_verify_msr(true)) {
+		pr_info("MSR access failed: Disabled\n");
+		return;
+	}
+
+	sld_state = state;
+	setup_force_cpu_cap(X86_FEATURE_SPLIT_LOCK_DETECT);
+}
+
+/*
+ * MSR_TEST_CTRL is per core, but we treat it like a per CPU MSR. Locking
+ * is not implemented as one thread could undo the setting of the other
+ * thread immediately after dropping the lock anyway.
+ */
+static void sld_update_msr(bool on)
+{
+	u64 test_ctrl_val = msr_test_ctrl_cache;
+
+	if (on)
+		test_ctrl_val |= MSR_TEST_CTRL_SPLIT_LOCK_DETECT;
+
+	wrmsrl(MSR_TEST_CTRL, test_ctrl_val);
+}
+
+static void split_lock_init(void)
+{
+	split_lock_verify_msr(sld_state != sld_off);
+}
+
+static void split_lock_warn(unsigned long ip)
+{
+	pr_warn_ratelimited("#AC: %s/%d took a split_lock trap at address: 0x%lx\n",
+			    current->comm, current->pid, ip);
+
+	/*
+	 * Disable the split lock detection for this task so it can make
+	 * progress and set TIF_SLD so the detection is re-enabled via
+	 * switch_to_sld() when the task is scheduled out.
+	 */
+	sld_update_msr(false);
+	set_tsk_thread_flag(current, TIF_SLD);
+}
+
+bool handle_guest_split_lock(unsigned long ip)
+{
+	if (sld_state == sld_warn) {
+		split_lock_warn(ip);
+		return true;
+	}
+
+	pr_warn_once("#AC: %s/%d %s split_lock trap at address: 0x%lx\n",
+		     current->comm, current->pid,
+		     sld_state == sld_fatal ? "fatal" : "bogus", ip);
+
+	current->thread.error_code = 0;
+	current->thread.trap_nr = X86_TRAP_AC;
+	force_sig_fault(SIGBUS, BUS_ADRALN, NULL);
+	return false;
+}
+EXPORT_SYMBOL_GPL(handle_guest_split_lock);
+
+bool handle_user_split_lock(struct pt_regs *regs, long error_code)
+{
+	if ((regs->flags & X86_EFLAGS_AC) || sld_state == sld_fatal)
+		return false;
+	split_lock_warn(regs->ip);
+	return true;
+}
+
+/*
+ * This function is called only when switching between tasks with
+ * different split-lock detection modes. It sets the MSR for the
+ * mode of the new task. This is right most of the time, but since
+ * the MSR is shared by hyperthreads on a physical core there can
+ * be glitches when the two threads need different modes.
+ */
+void switch_to_sld(unsigned long tifn)
+{
+	sld_update_msr(!(tifn & _TIF_SLD));
+}
+
+/*
+ * Bits in the IA32_CORE_CAPABILITIES are not architectural, so they should
+ * only be trusted if it is confirmed that a CPU model implements a
+ * specific feature at a particular bit position.
+ *
+ * The possible driver data field values:
+ *
+ * - 0: CPU models that are known to have the per-core split-lock detection
+ *	feature even though they do not enumerate IA32_CORE_CAPABILITIES.
+ *
+ * - 1: CPU models which may enumerate IA32_CORE_CAPABILITIES and if so use
+ *      bit 5 to enumerate the per-core split-lock detection feature.
+ */
+static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = {
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		0),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		0),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT,	1),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	1),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	1),
+	{}
+};
+
+void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c)
+{
+	const struct x86_cpu_id *m;
+	u64 ia32_core_caps;
+
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return;
+
+	m = x86_match_cpu(split_lock_cpu_ids);
+	if (!m)
+		return;
+
+	switch (m->driver_data) {
+	case 0:
+		break;
+	case 1:
+		if (!cpu_has(c, X86_FEATURE_CORE_CAPABILITIES))
+			return;
+		rdmsrl(MSR_IA32_CORE_CAPS, ia32_core_caps);
+		if (!(ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT))
+			return;
+		break;
+	default:
+		return;
+	}
+
+	split_lock_setup();
+}
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index 6dd78d8235e4..d3482eb43ff3 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -16,12 +16,17 @@
  * respective wildcard entries.
  *
  * A typical table entry would be to match a specific CPU
- * { X86_VENDOR_INTEL, 6, 0x12 }
- * or to match a specific CPU feature
- * { X86_FEATURE_MATCH(X86_FEATURE_FOOBAR) }
+ *
+ * X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_BROADWELL,
+ *				      X86_FEATURE_ANY, NULL);
  *
  * Fields can be wildcarded with %X86_VENDOR_ANY, %X86_FAMILY_ANY,
- * %X86_MODEL_ANY, %X86_FEATURE_ANY or 0 (except for vendor)
+ * %X86_MODEL_ANY, %X86_FEATURE_ANY (except for vendor)
+ *
+ * asm/cpu_device_id.h contains a set of useful macros which are shortcuts
+ * for various common selections. The above can be shortened to:
+ *
+ * X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, NULL);
  *
  * Arrays used to match for this should also be declared using
  * MODULE_DEVICE_TABLE(x86cpu, ...)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 2c4f949611e4..54165f3569e8 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -142,6 +142,8 @@ void mce_setup(struct mce *m)
 
 	if (this_cpu_has(X86_FEATURE_INTEL_PPIN))
 		rdmsrl(MSR_PPIN, m->ppin);
+	else if (this_cpu_has(X86_FEATURE_AMD_PPIN))
+		rdmsrl(MSR_AMD_PPIN, m->ppin);
 
 	m->microcode = boot_cpu_data.microcode;
 }
@@ -1213,8 +1215,14 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
  * On Intel systems this is entered on all CPUs in parallel through
  * MCE broadcast. However some CPUs might be broken beyond repair,
  * so be always careful when synchronizing with others.
+ *
+ * Tracing and kprobes are disabled: if we interrupted a kernel context
+ * with IF=1, we need to minimize stack usage.  There are also recursion
+ * issues: if the machine check was due to a failure of the memory
+ * backing the user stack, tracing that reads the user stack will cause
+ * potentially infinite recursion.
  */
-void do_machine_check(struct pt_regs *regs, long error_code)
+void notrace do_machine_check(struct pt_regs *regs, long error_code)
 {
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
@@ -1360,6 +1368,7 @@ out_ist:
 	ist_exit(regs);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
+NOKPROBE_SYMBOL(do_machine_check);
 
 #ifndef CONFIG_MEMORY_FAILURE
 int memory_failure(unsigned long pfn, int flags)
@@ -1877,6 +1886,8 @@ bool filter_mce(struct mce *m)
 {
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
 		return amd_filter_mce(m);
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		return intel_filter_mce(m);
 
 	return false;
 }
@@ -1892,10 +1903,11 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code)
 void (*machine_check_vector)(struct pt_regs *, long error_code) =
 						unexpected_machine_check;
 
-dotraplinkage void do_mce(struct pt_regs *regs, long error_code)
+dotraplinkage notrace void do_mce(struct pt_regs *regs, long error_code)
 {
 	machine_check_vector(regs, error_code);
 }
+NOKPROBE_SYMBOL(do_mce);
 
 /*
  * Called for each booted CPU to set up machine checks.
diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c
index 7c8958dee103..d089567a9ce8 100644
--- a/arch/x86/kernel/cpu/mce/dev-mcelog.c
+++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c
@@ -29,11 +29,7 @@ static char *mce_helper_argv[2] = { mce_helper, NULL };
  * separate MCEs from kernel messages to avoid bogus bug reports.
  */
 
-static struct mce_log_buffer mcelog = {
-	.signature	= MCE_LOG_SIGNATURE,
-	.len		= MCE_LOG_LEN,
-	.recordlen	= sizeof(struct mce),
-};
+static struct mce_log_buffer *mcelog;
 
 static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
 
@@ -45,21 +41,21 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val,
 
 	mutex_lock(&mce_chrdev_read_mutex);
 
-	entry = mcelog.next;
+	entry = mcelog->next;
 
 	/*
 	 * When the buffer fills up discard new entries. Assume that the
 	 * earlier errors are the more interesting ones:
 	 */
-	if (entry >= MCE_LOG_LEN) {
-		set_bit(MCE_OVERFLOW, (unsigned long *)&mcelog.flags);
+	if (entry >= mcelog->len) {
+		set_bit(MCE_OVERFLOW, (unsigned long *)&mcelog->flags);
 		goto unlock;
 	}
 
-	mcelog.next = entry + 1;
+	mcelog->next = entry + 1;
 
-	memcpy(mcelog.entry + entry, mce, sizeof(struct mce));
-	mcelog.entry[entry].finished = 1;
+	memcpy(mcelog->entry + entry, mce, sizeof(struct mce));
+	mcelog->entry[entry].finished = 1;
 
 	/* wake processes polling /dev/mcelog */
 	wake_up_interruptible(&mce_chrdev_wait);
@@ -214,21 +210,21 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
 
 	/* Only supports full reads right now */
 	err = -EINVAL;
-	if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
+	if (*off != 0 || usize < mcelog->len * sizeof(struct mce))
 		goto out;
 
-	next = mcelog.next;
+	next = mcelog->next;
 	err = 0;
 
 	for (i = 0; i < next; i++) {
-		struct mce *m = &mcelog.entry[i];
+		struct mce *m = &mcelog->entry[i];
 
 		err |= copy_to_user(buf, m, sizeof(*m));
 		buf += sizeof(*m);
 	}
 
-	memset(mcelog.entry, 0, next * sizeof(struct mce));
-	mcelog.next = 0;
+	memset(mcelog->entry, 0, next * sizeof(struct mce));
+	mcelog->next = 0;
 
 	if (err)
 		err = -EFAULT;
@@ -242,7 +238,7 @@ out:
 static __poll_t mce_chrdev_poll(struct file *file, poll_table *wait)
 {
 	poll_wait(file, &mce_chrdev_wait, wait);
-	if (READ_ONCE(mcelog.next))
+	if (READ_ONCE(mcelog->next))
 		return EPOLLIN | EPOLLRDNORM;
 	if (!mce_apei_read_done && apei_check_mce())
 		return EPOLLIN | EPOLLRDNORM;
@@ -261,13 +257,13 @@ static long mce_chrdev_ioctl(struct file *f, unsigned int cmd,
 	case MCE_GET_RECORD_LEN:
 		return put_user(sizeof(struct mce), p);
 	case MCE_GET_LOG_LEN:
-		return put_user(MCE_LOG_LEN, p);
+		return put_user(mcelog->len, p);
 	case MCE_GETCLEAR_FLAGS: {
 		unsigned flags;
 
 		do {
-			flags = mcelog.flags;
-		} while (cmpxchg(&mcelog.flags, flags, 0) != flags);
+			flags = mcelog->flags;
+		} while (cmpxchg(&mcelog->flags, flags, 0) != flags);
 
 		return put_user(flags, p);
 	}
@@ -339,8 +335,18 @@ static struct miscdevice mce_chrdev_device = {
 
 static __init int dev_mcelog_init_device(void)
 {
+	int mce_log_len;
 	int err;
 
+	mce_log_len = max(MCE_LOG_MIN_LEN, num_online_cpus());
+	mcelog = kzalloc(sizeof(*mcelog) + mce_log_len * sizeof(struct mce), GFP_KERNEL);
+	if (!mcelog)
+		return -ENOMEM;
+
+	strncpy(mcelog->signature, MCE_LOG_SIGNATURE, sizeof(mcelog->signature));
+	mcelog->len = mce_log_len;
+	mcelog->recordlen = sizeof(struct mce);
+
 	/* register character device /dev/mcelog */
 	err = misc_register(&mce_chrdev_device);
 	if (err) {
@@ -350,6 +356,7 @@ static __init int dev_mcelog_init_device(void)
 		else
 			pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err);
 
+		kfree(mcelog);
 		return err;
 	}
 
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index f996ffb887bc..d8f9230d2034 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -521,3 +521,20 @@ void mce_intel_feature_clear(struct cpuinfo_x86 *c)
 {
 	intel_clear_lmce();
 }
+
+bool intel_filter_mce(struct mce *m)
+{
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	/* MCE errata HSD131, HSM142, HSW131, BDM48, and HSM142 */
+	if ((c->x86 == 6) &&
+	    ((c->x86_model == INTEL_FAM6_HASWELL) ||
+	     (c->x86_model == INTEL_FAM6_HASWELL_L) ||
+	     (c->x86_model == INTEL_FAM6_BROADWELL) ||
+	     (c->x86_model == INTEL_FAM6_HASWELL_G)) &&
+	    (m->bank == 0) &&
+	    ((m->status & 0xa0000000ffffffff) == 0x80000000000f0005))
+		return true;
+
+	return false;
+}
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index b785c0d0b590..3b008172ad73 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -8,6 +8,9 @@
 #include <linux/device.h>
 #include <asm/mce.h>
 
+/* Pointer to the installed machine check handler for this CPU setup. */
+extern void (*machine_check_vector)(struct pt_regs *, long error_code);
+
 enum severity_level {
 	MCE_NO_SEVERITY,
 	MCE_DEFERRED_SEVERITY,
@@ -48,6 +51,7 @@ void cmci_disable_bank(int bank);
 void intel_init_cmci(void);
 void intel_init_lmce(void);
 void intel_clear_lmce(void);
+bool intel_filter_mce(struct mce *m);
 #else
 # define cmci_intel_adjust_timer mce_adjust_timer_default
 static inline bool mce_intel_cmci_poll(void) { return false; }
@@ -56,6 +60,7 @@ static inline void cmci_disable_bank(int bank) { }
 static inline void intel_init_cmci(void) { }
 static inline void intel_init_lmce(void) { }
 static inline void intel_clear_lmce(void) { }
+static inline bool intel_filter_mce(struct mce *m) { return false; };
 #endif
 
 void mce_timer_kick(unsigned long interval);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index caa032ce3fe3..ebf34c7bc8bc 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -227,8 +227,8 @@ static void __init ms_hyperv_init_platform(void)
 	ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.hints    = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
 
-	pr_info("Hyper-V: features 0x%x, hints 0x%x\n",
-		ms_hyperv.features, ms_hyperv.hints);
+	pr_info("Hyper-V: features 0x%x, hints 0x%x, misc 0x%x\n",
+		ms_hyperv.features, ms_hyperv.hints, ms_hyperv.misc_features);
 
 	ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS);
 	ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS);
@@ -263,6 +263,16 @@ static void __init ms_hyperv_init_platform(void)
 			cpuid_eax(HYPERV_CPUID_NESTED_FEATURES);
 	}
 
+	/*
+	 * Hyper-V expects to get crash register data or kmsg when
+	 * crash enlightment is available and system crashes. Set
+	 * crash_kexec_post_notifiers to be true to make sure that
+	 * calling crash enlightment interface before running kdump
+	 * kernel.
+	 */
+	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE)
+		crash_kexec_post_notifiers = true;
+
 #ifdef CONFIG_X86_LOCAL_APIC
 	if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
 	    ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 89049b343c7a..d8cc5223b7ce 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -578,6 +578,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 	d->id = id;
 	cpumask_set_cpu(cpu, &d->cpu_mask);
 
+	rdt_domain_reconfigure_cdp(r);
+
 	if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
 		kfree(d);
 		return;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 181c992f448c..3dd13f3a8b23 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -601,5 +601,6 @@ bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
 void __check_limbo(struct rdt_domain *d, bool force_free);
 bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r);
 bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r);
+void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 064e9ef44cd6..5a359d9fcc05 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1859,6 +1859,19 @@ static int set_cache_qos_cfg(int level, bool enable)
 	return 0;
 }
 
+/* Restore the qos cfg state when a domain comes online */
+void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
+{
+	if (!r->alloc_capable)
+		return;
+
+	if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA])
+		l2_qos_cfg_update(&r->alloc_enabled);
+
+	if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA])
+		l3_qos_cfg_update(&r->alloc_enabled);
+}
+
 /*
  * Enable or disable the MBA software controller
  * which helps user specify bandwidth in MBps.
@@ -3072,7 +3085,8 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 	 * If the rdtgroup is a mon group and parent directory
 	 * is a valid "mon_groups" directory, remove the mon group.
 	 */
-	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) {
+	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn &&
+	    rdtgrp != &rdtgroup_default) {
 		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
 		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
 			ret = rdtgroup_ctrl_remove(kn, rdtgrp);
diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c
index c222f283b456..300e3fd5ade3 100644
--- a/arch/x86/kernel/cpu/umwait.c
+++ b/arch/x86/kernel/cpu/umwait.c
@@ -4,6 +4,7 @@
 #include <linux/cpu.h>
 
 #include <asm/msr.h>
+#include <asm/mwait.h>
 
 #define UMWAIT_C02_ENABLE	0
 
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 46d732696c1c..9b6fafa69be9 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -25,6 +25,8 @@
 #include <linux/init.h>
 #include <linux/export.h>
 #include <linux/clocksource.h>
+#include <linux/cpu.h>
+#include <linux/reboot.h>
 #include <asm/div64.h>
 #include <asm/x86_init.h>
 #include <asm/hypervisor.h>
@@ -47,6 +49,11 @@
 #define VMWARE_CMD_GETVCPU_INFO  68
 #define VMWARE_CMD_LEGACY_X2APIC  3
 #define VMWARE_CMD_VCPU_RESERVED 31
+#define VMWARE_CMD_STEALCLOCK    91
+
+#define STEALCLOCK_NOT_AVAILABLE (-1)
+#define STEALCLOCK_DISABLED        0
+#define STEALCLOCK_ENABLED         1
 
 #define VMWARE_PORT(cmd, eax, ebx, ecx, edx)				\
 	__asm__("inl (%%dx), %%eax" :					\
@@ -86,6 +93,18 @@
 	}							\
 	} while (0)
 
+struct vmware_steal_time {
+	union {
+		uint64_t clock;	/* stolen time counter in units of vtsc */
+		struct {
+			/* only for little-endian */
+			uint32_t clock_low;
+			uint32_t clock_high;
+		};
+	};
+	uint64_t reserved[7];
+};
+
 static unsigned long vmware_tsc_khz __ro_after_init;
 static u8 vmware_hypercall_mode     __ro_after_init;
 
@@ -103,15 +122,25 @@ static unsigned long vmware_get_tsc_khz(void)
 
 #ifdef CONFIG_PARAVIRT
 static struct cyc2ns_data vmware_cyc2ns __ro_after_init;
-static int vmw_sched_clock __initdata = 1;
+static bool vmw_sched_clock __initdata = true;
+static DEFINE_PER_CPU_DECRYPTED(struct vmware_steal_time, vmw_steal_time) __aligned(64);
+static bool has_steal_clock;
+static bool steal_acc __initdata = true; /* steal time accounting */
 
 static __init int setup_vmw_sched_clock(char *s)
 {
-	vmw_sched_clock = 0;
+	vmw_sched_clock = false;
 	return 0;
 }
 early_param("no-vmw-sched-clock", setup_vmw_sched_clock);
 
+static __init int parse_no_stealacc(char *arg)
+{
+	steal_acc = false;
+	return 0;
+}
+early_param("no-steal-acc", parse_no_stealacc);
+
 static unsigned long long notrace vmware_sched_clock(void)
 {
 	unsigned long long ns;
@@ -122,7 +151,7 @@ static unsigned long long notrace vmware_sched_clock(void)
 	return ns;
 }
 
-static void __init vmware_sched_clock_setup(void)
+static void __init vmware_cyc2ns_setup(void)
 {
 	struct cyc2ns_data *d = &vmware_cyc2ns;
 	unsigned long long tsc_now = rdtsc();
@@ -132,17 +161,201 @@ static void __init vmware_sched_clock_setup(void)
 	d->cyc2ns_offset = mul_u64_u32_shr(tsc_now, d->cyc2ns_mul,
 					   d->cyc2ns_shift);
 
-	pv_ops.time.sched_clock = vmware_sched_clock;
-	pr_info("using sched offset of %llu ns\n", d->cyc2ns_offset);
+	pr_info("using clock offset of %llu ns\n", d->cyc2ns_offset);
+}
+
+static int vmware_cmd_stealclock(uint32_t arg1, uint32_t arg2)
+{
+	uint32_t result, info;
+
+	asm volatile (VMWARE_HYPERCALL :
+		"=a"(result),
+		"=c"(info) :
+		"a"(VMWARE_HYPERVISOR_MAGIC),
+		"b"(0),
+		"c"(VMWARE_CMD_STEALCLOCK),
+		"d"(0),
+		"S"(arg1),
+		"D"(arg2) :
+		"memory");
+	return result;
+}
+
+static bool stealclock_enable(phys_addr_t pa)
+{
+	return vmware_cmd_stealclock(upper_32_bits(pa),
+				     lower_32_bits(pa)) == STEALCLOCK_ENABLED;
+}
+
+static int __stealclock_disable(void)
+{
+	return vmware_cmd_stealclock(0, 1);
+}
+
+static void stealclock_disable(void)
+{
+	__stealclock_disable();
+}
+
+static bool vmware_is_stealclock_available(void)
+{
+	return __stealclock_disable() != STEALCLOCK_NOT_AVAILABLE;
+}
+
+/**
+ * vmware_steal_clock() - read the per-cpu steal clock
+ * @cpu:            the cpu number whose steal clock we want to read
+ *
+ * The function reads the steal clock if we are on a 64-bit system, otherwise
+ * reads it in parts, checking that the high part didn't change in the
+ * meantime.
+ *
+ * Return:
+ *      The steal clock reading in ns.
+ */
+static uint64_t vmware_steal_clock(int cpu)
+{
+	struct vmware_steal_time *steal = &per_cpu(vmw_steal_time, cpu);
+	uint64_t clock;
+
+	if (IS_ENABLED(CONFIG_64BIT))
+		clock = READ_ONCE(steal->clock);
+	else {
+		uint32_t initial_high, low, high;
+
+		do {
+			initial_high = READ_ONCE(steal->clock_high);
+			/* Do not reorder initial_high and high readings */
+			virt_rmb();
+			low = READ_ONCE(steal->clock_low);
+			/* Keep low reading in between */
+			virt_rmb();
+			high = READ_ONCE(steal->clock_high);
+		} while (initial_high != high);
+
+		clock = ((uint64_t)high << 32) | low;
+	}
+
+	return mul_u64_u32_shr(clock, vmware_cyc2ns.cyc2ns_mul,
+			     vmware_cyc2ns.cyc2ns_shift);
+}
+
+static void vmware_register_steal_time(void)
+{
+	int cpu = smp_processor_id();
+	struct vmware_steal_time *st = &per_cpu(vmw_steal_time, cpu);
+
+	if (!has_steal_clock)
+		return;
+
+	if (!stealclock_enable(slow_virt_to_phys(st))) {
+		has_steal_clock = false;
+		return;
+	}
+
+	pr_info("vmware-stealtime: cpu %d, pa %llx\n",
+		cpu, (unsigned long long) slow_virt_to_phys(st));
 }
 
+static void vmware_disable_steal_time(void)
+{
+	if (!has_steal_clock)
+		return;
+
+	stealclock_disable();
+}
+
+static void vmware_guest_cpu_init(void)
+{
+	if (has_steal_clock)
+		vmware_register_steal_time();
+}
+
+static void vmware_pv_guest_cpu_reboot(void *unused)
+{
+	vmware_disable_steal_time();
+}
+
+static int vmware_pv_reboot_notify(struct notifier_block *nb,
+				unsigned long code, void *unused)
+{
+	if (code == SYS_RESTART)
+		on_each_cpu(vmware_pv_guest_cpu_reboot, NULL, 1);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block vmware_pv_reboot_nb = {
+	.notifier_call = vmware_pv_reboot_notify,
+};
+
+#ifdef CONFIG_SMP
+static void __init vmware_smp_prepare_boot_cpu(void)
+{
+	vmware_guest_cpu_init();
+	native_smp_prepare_boot_cpu();
+}
+
+static int vmware_cpu_online(unsigned int cpu)
+{
+	local_irq_disable();
+	vmware_guest_cpu_init();
+	local_irq_enable();
+	return 0;
+}
+
+static int vmware_cpu_down_prepare(unsigned int cpu)
+{
+	local_irq_disable();
+	vmware_disable_steal_time();
+	local_irq_enable();
+	return 0;
+}
+#endif
+
+static __init int activate_jump_labels(void)
+{
+	if (has_steal_clock) {
+		static_key_slow_inc(&paravirt_steal_enabled);
+		if (steal_acc)
+			static_key_slow_inc(&paravirt_steal_rq_enabled);
+	}
+
+	return 0;
+}
+arch_initcall(activate_jump_labels);
+
 static void __init vmware_paravirt_ops_setup(void)
 {
 	pv_info.name = "VMware hypervisor";
 	pv_ops.cpu.io_delay = paravirt_nop;
 
-	if (vmware_tsc_khz && vmw_sched_clock)
-		vmware_sched_clock_setup();
+	if (vmware_tsc_khz == 0)
+		return;
+
+	vmware_cyc2ns_setup();
+
+	if (vmw_sched_clock)
+		pv_ops.time.sched_clock = vmware_sched_clock;
+
+	if (vmware_is_stealclock_available()) {
+		has_steal_clock = true;
+		pv_ops.time.steal_clock = vmware_steal_clock;
+
+		/* We use reboot notifier only to disable steal clock */
+		register_reboot_notifier(&vmware_pv_reboot_nb);
+
+#ifdef CONFIG_SMP
+		smp_ops.smp_prepare_boot_cpu =
+			vmware_smp_prepare_boot_cpu;
+		if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					      "x86/vmware:online",
+					      vmware_cpu_online,
+					      vmware_cpu_down_prepare) < 0)
+			pr_err("vmware_guest: Failed to install cpu hotplug callbacks\n");
+#else
+		vmware_guest_cpu_init();
+#endif
+	}
 }
 #else
 #define vmware_paravirt_ops_setup() do {} while (0)
@@ -213,7 +426,7 @@ static void __init vmware_platform_setup(void)
 	vmware_set_capabilities();
 }
 
-static u8 vmware_select_hypercall(void)
+static u8 __init vmware_select_hypercall(void)
 {
 	int eax, ebx, ecx, edx;