Merge branch 'linus' into x86/urgent, to pick up dependent commits

We are going to fix a bug introduced by a more recent commit, so
refresh the tree.

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

15 files changed, 1113 insertions, 629 deletions

diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 43955ee6715b..44207b71fee1 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -3,7 +3,7 @@
 #include <linux/sched/clock.h>
 
 #include <asm/cpufeature.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 58094a1f9e9d..8ee32119144d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -448,19 +448,60 @@ void load_percpu_segment(int cpu)
 	load_stack_canary_segment();
 }
 
+/* Setup the fixmap mapping only once per-processor */
+static inline void setup_fixmap_gdt(int cpu)
+{
+#ifdef CONFIG_X86_64
+	/* On 64-bit systems, we use a read-only fixmap GDT. */
+	pgprot_t prot = PAGE_KERNEL_RO;
+#else
+	/*
+	 * On native 32-bit systems, the GDT cannot be read-only because
+	 * our double fault handler uses a task gate, and entering through
+	 * a task gate needs to change an available TSS to busy.  If the GDT
+	 * is read-only, that will triple fault.
+	 *
+	 * On Xen PV, the GDT must be read-only because the hypervisor requires
+	 * it.
+	 */
+	pgprot_t prot = boot_cpu_has(X86_FEATURE_XENPV) ?
+		PAGE_KERNEL_RO : PAGE_KERNEL;
+#endif
+
+	__set_fixmap(get_cpu_gdt_ro_index(cpu), get_cpu_gdt_paddr(cpu), prot);
+}
+
+/* Load the original GDT from the per-cpu structure */
+void load_direct_gdt(int cpu)
+{
+	struct desc_ptr gdt_descr;
+
+	gdt_descr.address = (long)get_cpu_gdt_rw(cpu);
+	gdt_descr.size = GDT_SIZE - 1;
+	load_gdt(&gdt_descr);
+}
+EXPORT_SYMBOL_GPL(load_direct_gdt);
+
+/* Load a fixmap remapping of the per-cpu GDT */
+void load_fixmap_gdt(int cpu)
+{
+	struct desc_ptr gdt_descr;
+
+	gdt_descr.address = (long)get_cpu_gdt_ro(cpu);
+	gdt_descr.size = GDT_SIZE - 1;
+	load_gdt(&gdt_descr);
+}
+EXPORT_SYMBOL_GPL(load_fixmap_gdt);
+
 /*
  * Current gdt points %fs at the "master" per-cpu area: after this,
  * it's on the real one.
  */
 void switch_to_new_gdt(int cpu)
 {
-	struct desc_ptr gdt_descr;
-
-	gdt_descr.address = (long)get_cpu_gdt_table(cpu);
-	gdt_descr.size = GDT_SIZE - 1;
-	load_gdt(&gdt_descr);
+	/* Load the original GDT */
+	load_direct_gdt(cpu);
 	/* Reload the per-cpu base */
-
 	load_percpu_segment(cpu);
 }
 
@@ -1526,6 +1567,9 @@ void cpu_init(void)
 
 	if (is_uv_system())
 		uv_cpu_init();
+
+	setup_fixmap_gdt(cpu);
+	load_fixmap_gdt(cpu);
 }
 
 #else
@@ -1581,6 +1625,9 @@ void cpu_init(void)
 	dbg_restore_debug_regs();
 
 	fpu__init_cpu();
+
+	setup_fixmap_gdt(cpu);
+	load_fixmap_gdt(cpu);
 }
 #endif
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 063197771b8d..dfa90a3a5145 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -90,16 +90,12 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c)
 		return;
 	}
 
-	if (ring3mwait_disabled) {
-		msr_clear_bit(MSR_MISC_FEATURE_ENABLES,
-			      MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT);
+	if (ring3mwait_disabled)
 		return;
-	}
-
-	msr_set_bit(MSR_MISC_FEATURE_ENABLES,
-		    MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT);
 
 	set_cpu_cap(c, X86_FEATURE_RING3MWAIT);
+	this_cpu_or(msr_misc_features_shadow,
+		    1UL << MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT);
 
 	if (c == &boot_cpu_data)
 		ELF_HWCAP2 |= HWCAP2_RING3MWAIT;
@@ -488,6 +484,34 @@ static void intel_bsp_resume(struct cpuinfo_x86 *c)
 	init_intel_energy_perf(c);
 }
 
+static void init_cpuid_fault(struct cpuinfo_x86 *c)
+{
+	u64 msr;
+
+	if (!rdmsrl_safe(MSR_PLATFORM_INFO, &msr)) {
+		if (msr & MSR_PLATFORM_INFO_CPUID_FAULT)
+			set_cpu_cap(c, X86_FEATURE_CPUID_FAULT);
+	}
+}
+
+static void init_intel_misc_features(struct cpuinfo_x86 *c)
+{
+	u64 msr;
+
+	if (rdmsrl_safe(MSR_MISC_FEATURES_ENABLES, &msr))
+		return;
+
+	/* Clear all MISC features */
+	this_cpu_write(msr_misc_features_shadow, 0);
+
+	/* Check features and update capabilities and shadow control bits */
+	init_cpuid_fault(c);
+	probe_xeon_phi_r3mwait(c);
+
+	msr = this_cpu_read(msr_misc_features_shadow);
+	wrmsrl(MSR_MISC_FEATURES_ENABLES, msr);
+}
+
 static void init_intel(struct cpuinfo_x86 *c)
 {
 	unsigned int l2 = 0;
@@ -602,7 +626,7 @@ static void init_intel(struct cpuinfo_x86 *c)
 
 	init_intel_energy_perf(c);
 
-	probe_xeon_phi_r3mwait(c);
+	init_intel_misc_features(c);
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 5a533fefefa0..5b366462f579 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -32,55 +32,98 @@
 #include <asm/intel-family.h>
 #include <asm/intel_rdt.h>
 
+#define MAX_MBA_BW	100u
+#define MBA_IS_LINEAR	0x4
+
 /* Mutex to protect rdtgroup access. */
 DEFINE_MUTEX(rdtgroup_mutex);
 
 DEFINE_PER_CPU_READ_MOSTLY(int, cpu_closid);
 
+/*
+ * Used to store the max resource name width and max resource data width
+ * to display the schemata in a tabular format
+ */
+int max_name_width, max_data_width;
+
+static void
+mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
+static void
+cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
+
 #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains)
 
 struct rdt_resource rdt_resources_all[] = {
 	{
-		.name		= "L3",
-		.domains	= domain_init(RDT_RESOURCE_L3),
-		.msr_base	= IA32_L3_CBM_BASE,
-		.min_cbm_bits	= 1,
-		.cache_level	= 3,
-		.cbm_idx_multi	= 1,
-		.cbm_idx_offset	= 0
+		.name			= "L3",
+		.domains		= domain_init(RDT_RESOURCE_L3),
+		.msr_base		= IA32_L3_CBM_BASE,
+		.msr_update		= cat_wrmsr,
+		.cache_level		= 3,
+		.cache = {
+			.min_cbm_bits	= 1,
+			.cbm_idx_mult	= 1,
+			.cbm_idx_offset	= 0,
+		},
+		.parse_ctrlval		= parse_cbm,
+		.format_str		= "%d=%0*x",
+	},
+	{
+		.name			= "L3DATA",
+		.domains		= domain_init(RDT_RESOURCE_L3DATA),
+		.msr_base		= IA32_L3_CBM_BASE,
+		.msr_update		= cat_wrmsr,
+		.cache_level		= 3,
+		.cache = {
+			.min_cbm_bits	= 1,
+			.cbm_idx_mult	= 2,
+			.cbm_idx_offset	= 0,
+		},
+		.parse_ctrlval		= parse_cbm,
+		.format_str		= "%d=%0*x",
 	},
 	{
-		.name		= "L3DATA",
-		.domains	= domain_init(RDT_RESOURCE_L3DATA),
-		.msr_base	= IA32_L3_CBM_BASE,
-		.min_cbm_bits	= 1,
-		.cache_level	= 3,
-		.cbm_idx_multi	= 2,
-		.cbm_idx_offset	= 0
+		.name			= "L3CODE",
+		.domains		= domain_init(RDT_RESOURCE_L3CODE),
+		.msr_base		= IA32_L3_CBM_BASE,
+		.msr_update		= cat_wrmsr,
+		.cache_level		= 3,
+		.cache = {
+			.min_cbm_bits	= 1,
+			.cbm_idx_mult	= 2,
+			.cbm_idx_offset	= 1,
+		},
+		.parse_ctrlval		= parse_cbm,
+		.format_str		= "%d=%0*x",
 	},
 	{
-		.name		= "L3CODE",
-		.domains	= domain_init(RDT_RESOURCE_L3CODE),
-		.msr_base	= IA32_L3_CBM_BASE,
-		.min_cbm_bits	= 1,
-		.cache_level	= 3,
-		.cbm_idx_multi	= 2,
-		.cbm_idx_offset	= 1
+		.name			= "L2",
+		.domains		= domain_init(RDT_RESOURCE_L2),
+		.msr_base		= IA32_L2_CBM_BASE,
+		.msr_update		= cat_wrmsr,
+		.cache_level		= 2,
+		.cache = {
+			.min_cbm_bits	= 1,
+			.cbm_idx_mult	= 1,
+			.cbm_idx_offset	= 0,
+		},
+		.parse_ctrlval		= parse_cbm,
+		.format_str		= "%d=%0*x",
 	},
 	{
-		.name		= "L2",
-		.domains	= domain_init(RDT_RESOURCE_L2),
-		.msr_base	= IA32_L2_CBM_BASE,
-		.min_cbm_bits	= 1,
-		.cache_level	= 2,
-		.cbm_idx_multi	= 1,
-		.cbm_idx_offset	= 0
+		.name			= "MB",
+		.domains		= domain_init(RDT_RESOURCE_MBA),
+		.msr_base		= IA32_MBA_THRTL_BASE,
+		.msr_update		= mba_wrmsr,
+		.cache_level		= 3,
+		.parse_ctrlval		= parse_bw,
+		.format_str		= "%d=%*d",
 	},
 };
 
-static int cbm_idx(struct rdt_resource *r, int closid)
+static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid)
 {
-	return closid * r->cbm_idx_multi + r->cbm_idx_offset;
+	return closid * r->cache.cbm_idx_mult + r->cache.cbm_idx_offset;
 }
 
 /*
@@ -118,9 +161,9 @@ static inline bool cache_alloc_hsw_probe(void)
 			return false;
 
 		r->num_closid = 4;
-		r->cbm_len = 20;
-		r->max_cbm = max_cbm;
-		r->min_cbm_bits = 2;
+		r->default_ctrl = max_cbm;
+		r->cache.cbm_len = 20;
+		r->cache.min_cbm_bits = 2;
 		r->capable = true;
 		r->enabled = true;
 
@@ -130,16 +173,66 @@ static inline bool cache_alloc_hsw_probe(void)
 	return false;
 }
 
-static void rdt_get_config(int idx, struct rdt_resource *r)
+/*
+ * rdt_get_mb_table() - get a mapping of bandwidth(b/w) percentage values
+ * exposed to user interface and the h/w understandable delay values.
+ *
+ * The non-linear delay values have the granularity of power of two
+ * and also the h/w does not guarantee a curve for configured delay
+ * values vs. actual b/w enforced.
+ * Hence we need a mapping that is pre calibrated so the user can
+ * express the memory b/w as a percentage value.
+ */
+static inline bool rdt_get_mb_table(struct rdt_resource *r)
+{
+	/*
+	 * There are no Intel SKUs as of now to support non-linear delay.
+	 */
+	pr_info("MBA b/w map not implemented for cpu:%d, model:%d",
+		boot_cpu_data.x86, boot_cpu_data.x86_model);
+
+	return false;
+}
+
+static bool rdt_get_mem_config(struct rdt_resource *r)
+{
+	union cpuid_0x10_3_eax eax;
+	union cpuid_0x10_x_edx edx;
+	u32 ebx, ecx;
+
+	cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full);
+	r->num_closid = edx.split.cos_max + 1;
+	r->membw.max_delay = eax.split.max_delay + 1;
+	r->default_ctrl = MAX_MBA_BW;
+	if (ecx & MBA_IS_LINEAR) {
+		r->membw.delay_linear = true;
+		r->membw.min_bw = MAX_MBA_BW - r->membw.max_delay;
+		r->membw.bw_gran = MAX_MBA_BW - r->membw.max_delay;
+	} else {
+		if (!rdt_get_mb_table(r))
+			return false;
+	}
+	r->data_width = 3;
+	rdt_get_mba_infofile(r);
+
+	r->capable = true;
+	r->enabled = true;
+
+	return true;
+}
+
+static void rdt_get_cache_config(int idx, struct rdt_resource *r)
 {
 	union cpuid_0x10_1_eax eax;
-	union cpuid_0x10_1_edx edx;
+	union cpuid_0x10_x_edx edx;
 	u32 ebx, ecx;
 
 	cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full);
 	r->num_closid = edx.split.cos_max + 1;
-	r->cbm_len = eax.split.cbm_len + 1;
-	r->max_cbm = BIT_MASK(eax.split.cbm_len + 1) - 1;
+	r->cache.cbm_len = eax.split.cbm_len + 1;
+	r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1;
+	r->data_width = (r->cache.cbm_len + 3) / 4;
+	rdt_get_cache_infofile(r);
 	r->capable = true;
 	r->enabled = true;
 }
@@ -150,8 +243,9 @@ static void rdt_get_cdp_l3_config(int type)
 	struct rdt_resource *r = &rdt_resources_all[type];
 
 	r->num_closid = r_l3->num_closid / 2;
-	r->cbm_len = r_l3->cbm_len;
-	r->max_cbm = r_l3->max_cbm;
+	r->cache.cbm_len = r_l3->cache.cbm_len;
+	r->default_ctrl = r_l3->default_ctrl;
+	r->data_width = (r->cache.cbm_len + 3) / 4;
 	r->capable = true;
 	/*
 	 * By default, CDP is disabled. CDP can be enabled by mount parameter
@@ -160,33 +254,6 @@ static void rdt_get_cdp_l3_config(int type)
 	r->enabled = false;
 }
 
-static inline bool get_rdt_resources(void)
-{
-	bool ret = false;
-
-	if (cache_alloc_hsw_probe())
-		return true;
-
-	if (!boot_cpu_has(X86_FEATURE_RDT_A))
-		return false;
-
-	if (boot_cpu_has(X86_FEATURE_CAT_L3)) {
-		rdt_get_config(1, &rdt_resources_all[RDT_RESOURCE_L3]);
-		if (boot_cpu_has(X86_FEATURE_CDP_L3)) {
-			rdt_get_cdp_l3_config(RDT_RESOURCE_L3DATA);
-			rdt_get_cdp_l3_config(RDT_RESOURCE_L3CODE);
-		}
-		ret = true;
-	}
-	if (boot_cpu_has(X86_FEATURE_CAT_L2)) {
-		/* CPUID 0x10.2 fields are same format at 0x10.1 */
-		rdt_get_config(2, &rdt_resources_all[RDT_RESOURCE_L2]);
-		ret = true;
-	}
-
-	return ret;
-}
-
 static int get_cache_id(int cpu, int level)
 {
 	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
@@ -200,29 +267,55 @@ static int get_cache_id(int cpu, int level)
 	return -1;
 }
 
-void rdt_cbm_update(void *arg)
+/*
+ * Map the memory b/w percentage value to delay values
+ * that can be written to QOS_MSRs.
+ * There are currently no SKUs which support non linear delay values.
+ */
+static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
 {
-	struct msr_param *m = (struct msr_param *)arg;
+	if (r->membw.delay_linear)
+		return MAX_MBA_BW - bw;
+
+	pr_warn_once("Non Linear delay-bw map not supported but queried\n");
+	return r->default_ctrl;
+}
+
+static void
+mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+{
+	unsigned int i;
+
+	/*  Write the delay values for mba. */
+	for (i = m->low; i < m->high; i++)
+		wrmsrl(r->msr_base + i, delay_bw_map(d->ctrl_val[i], r));
+}
+
+static void
+cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+{
+	unsigned int i;
+
+	for (i = m->low; i < m->high; i++)
+		wrmsrl(r->msr_base + cbm_idx(r, i), d->ctrl_val[i]);
+}
+
+void rdt_ctrl_update(void *arg)
+{
+	struct msr_param *m = arg;
 	struct rdt_resource *r = m->res;
-	int i, cpu = smp_processor_id();
+	int cpu = smp_processor_id();
 	struct rdt_domain *d;
 
 	list_for_each_entry(d, &r->domains, list) {
 		/* Find the domain that contains this CPU */
-		if (cpumask_test_cpu(cpu, &d->cpu_mask))
-			goto found;
+		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
+			r->msr_update(d, m, r);
+			return;
+		}
 	}
-	pr_info_once("cpu %d not found in any domain for resource %s\n",
+	pr_warn_once("cpu %d not found in any domain for resource %s\n",
 		     cpu, r->name);
-
-	return;
-
-found:
-	for (i = m->low; i < m->high; i++) {
-		int idx = cbm_idx(r, i);
-
-		wrmsrl(r->msr_base + idx, d->cbm[i]);
-	}
 }
 
 /*
@@ -258,6 +351,32 @@ static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 	return NULL;
 }
 
+static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
+{
+	struct msr_param m;
+	u32 *dc;
+	int i;
+
+	dc = kmalloc_array(r->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL);
+	if (!dc)
+		return -ENOMEM;
+
+	d->ctrl_val = dc;
+
+	/*
+	 * Initialize the Control MSRs to having no control.
+	 * For Cache Allocation: Set all bits in cbm
+	 * For Memory Allocation: Set b/w requested to 100
+	 */
+	for (i = 0; i < r->num_closid; i++, dc++)
+		*dc = r->default_ctrl;
+
+	m.low = 0;
+	m.high = r->num_closid;
+	r->msr_update(d, &m, r);
+	return 0;
+}
+
 /*
  * domain_add_cpu - Add a cpu to a resource's domain list.
  *
@@ -273,7 +392,7 @@ static struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
  */
 static void domain_add_cpu(int cpu, struct rdt_resource *r)
 {
-	int i, id = get_cache_id(cpu, r->cache_level);
+	int id = get_cache_id(cpu, r->cache_level);
 	struct list_head *add_pos = NULL;
 	struct rdt_domain *d;
 
@@ -294,22 +413,13 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 	d->id = id;
 
-	d->cbm = kmalloc_array(r->num_closid, sizeof(*d->cbm), GFP_KERNEL);
-	if (!d->cbm) {
+	if (domain_setup_ctrlval(r, d)) {
 		kfree(d);
 		return;
 	}
 
-	for (i = 0; i < r->num_closid; i++) {
-		int idx = cbm_idx(r, i);
-
-		d->cbm[i] = r->max_cbm;
-		wrmsrl(r->msr_base + idx, d->cbm[i]);
-	}
-
 	cpumask_set_cpu(cpu, &d->cpu_mask);
 	list_add_tail(&d->list, add_pos);
-	r->num_domains++;
 }
 
 static void domain_remove_cpu(int cpu, struct rdt_resource *r)
@@ -325,8 +435,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 
 	cpumask_clear_cpu(cpu, &d->cpu_mask);
 	if (cpumask_empty(&d->cpu_mask)) {
-		r->num_domains--;
-		kfree(d->cbm);
+		kfree(d->ctrl_val);
 		list_del(&d->list);
 		kfree(d);
 	}
@@ -374,6 +483,57 @@ static int intel_rdt_offline_cpu(unsigned int cpu)
 	return 0;
 }
 
+/*
+ * Choose a width for the resource name and resource data based on the
+ * resource that has widest name and cbm.
+ */
+static __init void rdt_init_padding(void)
+{
+	struct rdt_resource *r;
+	int cl;
+
+	for_each_capable_rdt_resource(r) {
+		cl = strlen(r->name);
+		if (cl > max_name_width)
+			max_name_width = cl;
+
+		if (r->data_width > max_data_width)
+			max_data_width = r->data_width;
+	}
+}
+
+static __init bool get_rdt_resources(void)
+{
+	bool ret = false;
+
+	if (cache_alloc_hsw_probe())
+		return true;
+
+	if (!boot_cpu_has(X86_FEATURE_RDT_A))
+		return false;
+
+	if (boot_cpu_has(X86_FEATURE_CAT_L3)) {
+		rdt_get_cache_config(1, &rdt_resources_all[RDT_RESOURCE_L3]);
+		if (boot_cpu_has(X86_FEATURE_CDP_L3)) {
+			rdt_get_cdp_l3_config(RDT_RESOURCE_L3DATA);
+			rdt_get_cdp_l3_config(RDT_RESOURCE_L3CODE);
+		}
+		ret = true;
+	}
+	if (boot_cpu_has(X86_FEATURE_CAT_L2)) {
+		/* CPUID 0x10.2 fields are same format at 0x10.1 */
+		rdt_get_cache_config(2, &rdt_resources_all[RDT_RESOURCE_L2]);
+		ret = true;
+	}
+
+	if (boot_cpu_has(X86_FEATURE_MBA)) {
+		if (rdt_get_mem_config(&rdt_resources_all[RDT_RESOURCE_MBA]))
+			ret = true;
+	}
+
+	return ret;
+}
+
 static int __init intel_rdt_late_init(void)
 {
 	struct rdt_resource *r;
@@ -382,6 +542,8 @@ static int __init intel_rdt_late_init(void)
 	if (!get_rdt_resources())
 		return -ENODEV;
 
+	rdt_init_padding();
+
 	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
 				  "x86/rdt/cat:online:",
 				  intel_rdt_online_cpu, intel_rdt_offline_cpu);
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 9ac2a5cdd9c2..f5af0cc7eb0d 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -174,6 +174,13 @@ static struct kernfs_ops rdtgroup_kf_single_ops = {
 	.seq_show		= rdtgroup_seqfile_show,
 };
 
+static bool is_cpu_list(struct kernfs_open_file *of)
+{
+	struct rftype *rft = of->kn->priv;
+
+	return rft->flags & RFTYPE_FLAGS_CPUS_LIST;
+}
+
 static int rdtgroup_cpus_show(struct kernfs_open_file *of,
 			      struct seq_file *s, void *v)
 {
@@ -182,10 +189,12 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 
-	if (rdtgrp)
-		seq_printf(s, "%*pb\n", cpumask_pr_args(&rdtgrp->cpu_mask));
-	else
+	if (rdtgrp) {
+		seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
+			   cpumask_pr_args(&rdtgrp->cpu_mask));
+	} else {
 		ret = -ENOENT;
+	}
 	rdtgroup_kn_unlock(of->kn);
 
 	return ret;
@@ -252,7 +261,11 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 		goto unlock;
 	}
 
-	ret = cpumask_parse(buf, newmask);
+	if (is_cpu_list(of))
+		ret = cpulist_parse(buf, newmask);
+	else
+		ret = cpumask_parse(buf, newmask);
+
 	if (ret)
 		goto unlock;
 
@@ -473,6 +486,14 @@ static struct rftype rdtgroup_base_files[] = {
 		.seq_show	= rdtgroup_cpus_show,
 	},
 	{
+		.name		= "cpus_list",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_cpus_write,
+		.seq_show	= rdtgroup_cpus_show,
+		.flags		= RFTYPE_FLAGS_CPUS_LIST,
+	},
+	{
 		.name		= "tasks",
 		.mode		= 0644,
 		.kf_ops		= &rdtgroup_kf_single_ops,
@@ -494,32 +515,56 @@ static int rdt_num_closids_show(struct kernfs_open_file *of,
 	struct rdt_resource *r = of->kn->parent->priv;
 
 	seq_printf(seq, "%d\n", r->num_closid);
+	return 0;
+}
+
+static int rdt_default_ctrl_show(struct kernfs_open_file *of,
+			     struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
 
+	seq_printf(seq, "%x\n", r->default_ctrl);
 	return 0;
 }
 
-static int rdt_cbm_mask_show(struct kernfs_open_file *of,
+static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
 	struct rdt_resource *r = of->kn->parent->priv;
 
-	seq_printf(seq, "%x\n", r->max_cbm);
+	seq_printf(seq, "%u\n", r->cache.min_cbm_bits);
+	return 0;
+}
+
+static int rdt_min_bw_show(struct kernfs_open_file *of,
+			     struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
 
+	seq_printf(seq, "%u\n", r->membw.min_bw);
 	return 0;
 }
 
-static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
+static int rdt_bw_gran_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
 	struct rdt_resource *r = of->kn->parent->priv;
 
-	seq_printf(seq, "%d\n", r->min_cbm_bits);
+	seq_printf(seq, "%u\n", r->membw.bw_gran);
+	return 0;
+}
+
+static int rdt_delay_linear_show(struct kernfs_open_file *of,
+			     struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
 
+	seq_printf(seq, "%u\n", r->membw.delay_linear);
 	return 0;
 }
 
 /* rdtgroup information files for one cache resource. */
-static struct rftype res_info_files[] = {
+static struct rftype res_cache_info_files[] = {
 	{
 		.name		= "num_closids",
 		.mode		= 0444,
@@ -530,7 +575,7 @@ static struct rftype res_info_files[] = {
 		.name		= "cbm_mask",
 		.mode		= 0444,
 		.kf_ops		= &rdtgroup_kf_single_ops,
-		.seq_show	= rdt_cbm_mask_show,
+		.seq_show	= rdt_default_ctrl_show,
 	},
 	{
 		.name		= "min_cbm_bits",
@@ -540,11 +585,52 @@ static struct rftype res_info_files[] = {
 	},
 };
 
+/* rdtgroup information files for memory bandwidth. */
+static struct rftype res_mba_info_files[] = {
+	{
+		.name		= "num_closids",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_num_closids_show,
+	},
+	{
+		.name		= "min_bandwidth",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_min_bw_show,
+	},
+	{
+		.name		= "bandwidth_gran",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_bw_gran_show,
+	},
+	{
+		.name		= "delay_linear",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_delay_linear_show,
+	},
+};
+
+void rdt_get_mba_infofile(struct rdt_resource *r)
+{
+	r->info_files = res_mba_info_files;
+	r->nr_info_files = ARRAY_SIZE(res_mba_info_files);
+}
+
+void rdt_get_cache_infofile(struct rdt_resource *r)
+{
+	r->info_files = res_cache_info_files;
+	r->nr_info_files = ARRAY_SIZE(res_cache_info_files);
+}
+
 static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 {
 	struct kernfs_node *kn_subdir;
+	struct rftype *res_info_files;
 	struct rdt_resource *r;
-	int ret;
+	int ret, len;
 
 	/* create the directory */
 	kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL);
@@ -563,8 +649,11 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 		ret = rdtgroup_kn_set_ugid(kn_subdir);
 		if (ret)
 			goto out_destroy;
-		ret = rdtgroup_add_files(kn_subdir, res_info_files,
-					 ARRAY_SIZE(res_info_files));
+
+		res_info_files = r->info_files;
+		len = r->nr_info_files;
+
+		ret = rdtgroup_add_files(kn_subdir, res_info_files, len);
 		if (ret)
 			goto out_destroy;
 		kernfs_activate(kn_subdir);
@@ -780,7 +869,7 @@ out:
 	return dentry;
 }
 
-static int reset_all_cbms(struct rdt_resource *r)
+static int reset_all_ctrls(struct rdt_resource *r)
 {
 	struct msr_param msr_param;
 	cpumask_var_t cpu_mask;
@@ -803,14 +892,14 @@ static int reset_all_cbms(struct rdt_resource *r)
 		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
 
 		for (i = 0; i < r->num_closid; i++)
-			d->cbm[i] = r->max_cbm;
+			d->ctrl_val[i] = r->default_ctrl;
 	}
 	cpu = get_cpu();
 	/* Update CBM on this cpu if it's in cpu_mask. */
 	if (cpumask_test_cpu(cpu, cpu_mask))
-		rdt_cbm_update(&msr_param);
+		rdt_ctrl_update(&msr_param);
 	/* Update CBM on all other cpus in cpu_mask. */
-	smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1);
+	smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
 	put_cpu();
 
 	free_cpumask_var(cpu_mask);
@@ -896,7 +985,7 @@ static void rdt_kill_sb(struct super_block *sb)
 
 	/*Put everything back to default values. */
 	for_each_enabled_rdt_resource(r)
-		reset_all_cbms(r);
+		reset_all_ctrls(r);
 	cdp_disable();
 	rmdir_all_sub();
 	static_branch_disable(&rdt_enable_key);
diff --git a/arch/x86/kernel/cpu/intel_rdt_schemata.c b/arch/x86/kernel/cpu/intel_rdt_schemata.c
index badd2b31a560..406d7a6532f9 100644
--- a/arch/x86/kernel/cpu/intel_rdt_schemata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_schemata.c
@@ -29,26 +29,77 @@
 #include <asm/intel_rdt.h>
 
 /*
+ * Check whether MBA bandwidth percentage value is correct. The value is
+ * checked against the minimum and max bandwidth values specified by the
+ * hardware. The allocated bandwidth percentage is rounded to the next
+ * control step available on the hardware.
+ */
+static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
+{
+	unsigned long bw;
+	int ret;
+
+	/*
+	 * Only linear delay values is supported for current Intel SKUs.
+	 */
+	if (!r->membw.delay_linear)
+		return false;
+
+	ret = kstrtoul(buf, 10, &bw);
+	if (ret)
+		return false;
+
+	if (bw < r->membw.min_bw || bw > r->default_ctrl)
+		return false;
+
+	*data = roundup(bw, (unsigned long)r->membw.bw_gran);
+	return true;
+}
+
+int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d)
+{
+	unsigned long data;
+
+	if (d->have_new_ctrl)
+		return -EINVAL;
+
+	if (!bw_validate(buf, &data, r))
+		return -EINVAL;
+	d->new_ctrl = data;
+	d->have_new_ctrl = true;
+
+	return 0;
+}
+
+/*
  * Check whether a cache bit mask is valid. The SDM says:
  *	Please note that all (and only) contiguous '1' combinations
  *	are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
  * Additionally Haswell requires at least two bits set.
  */
-static bool cbm_validate(unsigned long var, struct rdt_resource *r)
+static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 {
-	unsigned long first_bit, zero_bit;
+	unsigned long first_bit, zero_bit, val;
+	unsigned int cbm_len = r->cache.cbm_len;
+	int ret;
+
+	ret = kstrtoul(buf, 16, &val);
+	if (ret)
+		return false;
 
-	if (var == 0 || var > r->max_cbm)
+	if (val == 0 || val > r->default_ctrl)
 		return false;
 
-	first_bit = find_first_bit(&var, r->cbm_len);
-	zero_bit = find_next_zero_bit(&var, r->cbm_len, first_bit);
+	first_bit = find_first_bit(&val, cbm_len);
+	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
 
-	if (find_next_bit(&var, r->cbm_len, zero_bit) < r->cbm_len)
+	if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)
 		return false;
 
-	if ((zero_bit - first_bit) < r->min_cbm_bits)
+	if ((zero_bit - first_bit) < r->cache.min_cbm_bits)
 		return false;
+
+	*data = val;
 	return true;
 }
 
@@ -56,17 +107,17 @@ static bool cbm_validate(unsigned long var, struct rdt_resource *r)
  * Read one cache bit mask (hex). Check that it is valid for the current
  * resource type.
  */
-static int parse_cbm(char *buf, struct rdt_resource *r)
+int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d)
 {
 	unsigned long data;
-	int ret;
 
-	ret = kstrtoul(buf, 16, &data);
-	if (ret)
-		return ret;
-	if (!cbm_validate(data, r))
+	if (d->have_new_ctrl)
 		return -EINVAL;
-	r->tmp_cbms[r->num_tmp_cbms++] = data;
+
+	if(!cbm_validate(buf, &data, r))
+		return -EINVAL;
+	d->new_ctrl = data;
+	d->have_new_ctrl = true;
 
 	return 0;
 }
@@ -74,8 +125,8 @@ static int parse_cbm(char *buf, struct rdt_resource *r)
 /*
  * For each domain in this resource we expect to find a series of:
  *	id=mask
- * separated by ";". The "id" is in decimal, and must appear in the
- * right order.
+ * separated by ";". The "id" is in decimal, and must match one of
+ * the "id"s for this resource.
  */
 static int parse_line(char *line, struct rdt_resource *r)
 {
@@ -83,21 +134,22 @@ static int parse_line(char *line, struct rdt_resource *r)
 	struct rdt_domain *d;
 	unsigned long dom_id;
 
+next:
+	if (!line || line[0] == '\0')
+		return 0;
+	dom = strsep(&line, ";");
+	id = strsep(&dom, "=");
+	if (!dom || kstrtoul(id, 10, &dom_id))
+		return -EINVAL;
+	dom = strim(dom);
 	list_for_each_entry(d, &r->domains, list) {
-		dom = strsep(&line, ";");
-		if (!dom)
-			return -EINVAL;
-		id = strsep(&dom, "=");
-		if (kstrtoul(id, 10, &dom_id) || dom_id != d->id)
-			return -EINVAL;
-		if (parse_cbm(dom, r))
-			return -EINVAL;
+		if (d->id == dom_id) {
+			if (r->parse_ctrlval(dom, r, d))
+				return -EINVAL;
+			goto next;
+		}
 	}
-
-	/* Any garbage at the end of the line? */
-	if (line && line[0])
-		return -EINVAL;
-	return 0;
+	return -EINVAL;
 }
 
 static int update_domains(struct rdt_resource *r, int closid)
@@ -105,7 +157,7 @@ static int update_domains(struct rdt_resource *r, int closid)
 	struct msr_param msr_param;
 	cpumask_var_t cpu_mask;
 	struct rdt_domain *d;
-	int cpu, idx = 0;
+	int cpu;
 
 	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
 		return -ENOMEM;
@@ -115,30 +167,46 @@ static int update_domains(struct rdt_resource *r, int closid)
 	msr_param.res = r;
 
 	list_for_each_entry(d, &r->domains, list) {
-		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
-		d->cbm[msr_param.low] = r->tmp_cbms[idx++];
+		if (d->have_new_ctrl && d->new_ctrl != d->ctrl_val[closid]) {
+			cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+			d->ctrl_val[closid] = d->new_ctrl;
+		}
 	}
+	if (cpumask_empty(cpu_mask))
+		goto done;
 	cpu = get_cpu();
 	/* Update CBM on this cpu if it's in cpu_mask. */
 	if (cpumask_test_cpu(cpu, cpu_mask))
-		rdt_cbm_update(&msr_param);
+		rdt_ctrl_update(&msr_param);
 	/* Update CBM on other cpus. */
-	smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1);
+	smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
 	put_cpu();
 
+done:
 	free_cpumask_var(cpu_mask);
 
 	return 0;
 }
 
+static int rdtgroup_parse_resource(char *resname, char *tok, int closid)
+{
+	struct rdt_resource *r;
+
+	for_each_enabled_rdt_resource(r) {
+		if (!strcmp(resname, r->name) && closid < r->num_closid)
+			return parse_line(tok, r);
+	}
+	return -EINVAL;
+}
+
 ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off)
 {
 	struct rdtgroup *rdtgrp;
+	struct rdt_domain *dom;
 	struct rdt_resource *r;
 	char *tok, *resname;
 	int closid, ret = 0;
-	u32 *l3_cbms = NULL;
 
 	/* Valid input requires a trailing newline */
 	if (nbytes == 0 || buf[nbytes - 1] != '\n')
@@ -153,44 +221,20 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 
 	closid = rdtgrp->closid;
 
-	/* get scratch space to save all the masks while we validate input */
 	for_each_enabled_rdt_resource(r) {
-		r->tmp_cbms = kcalloc(r->num_domains, sizeof(*l3_cbms),
-				      GFP_KERNEL);
-		if (!r->tmp_cbms) {
-			ret = -ENOMEM;
-			goto out;
-		}
-		r->num_tmp_cbms = 0;
+		list_for_each_entry(dom, &r->domains, list)
+			dom->have_new_ctrl = false;
 	}
 
 	while ((tok = strsep(&buf, "\n")) != NULL) {
-		resname = strsep(&tok, ":");
+		resname = strim(strsep(&tok, ":"));
 		if (!tok) {
 			ret = -EINVAL;
 			goto out;
 		}
-		for_each_enabled_rdt_resource(r) {
-			if (!strcmp(resname, r->name) &&
-			    closid < r->num_closid) {
-				ret = parse_line(tok, r);
-				if (ret)
-					goto out;
-				break;
-			}
-		}
-		if (!r->name) {
-			ret = -EINVAL;
-			goto out;
-		}
-	}
-
-	/* Did the parser find all the masks we need? */
-	for_each_enabled_rdt_resource(r) {
-		if (r->num_tmp_cbms != r->num_domains) {
-			ret = -EINVAL;
+		ret = rdtgroup_parse_resource(resname, tok, closid);
+		if (ret)
 			goto out;
-		}
 	}
 
 	for_each_enabled_rdt_resource(r) {
@@ -200,10 +244,6 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	}
 
 out:
-	for_each_enabled_rdt_resource(r) {
-		kfree(r->tmp_cbms);
-		r->tmp_cbms = NULL;
-	}
 	rdtgroup_kn_unlock(of->kn);
 	return ret ?: nbytes;
 }
@@ -213,11 +253,12 @@ static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid)
 	struct rdt_domain *dom;
 	bool sep = false;
 
-	seq_printf(s, "%s:", r->name);
+	seq_printf(s, "%*s:", max_name_width, r->name);
 	list_for_each_entry(dom, &r->domains, list) {
 		if (sep)
 			seq_puts(s, ";");
-		seq_printf(s, "%d=%x", dom->id, dom->cbm[closid]);
+		seq_printf(s, r->format_str, dom->id, max_data_width,
+			   dom->ctrl_val[closid]);
 		sep = true;
 	}
 	seq_puts(s, "\n");
diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile
index a3311c886194..43051f0777d4 100644
--- a/arch/x86/kernel/cpu/mcheck/Makefile
+++ b/arch/x86/kernel/cpu/mcheck/Makefile
@@ -9,3 +9,5 @@ obj-$(CONFIG_X86_MCE_INJECT)	+= mce-inject.o
 obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o
 
 obj-$(CONFIG_ACPI_APEI)		+= mce-apei.o
+
+obj-$(CONFIG_X86_MCELOG_LEGACY)	+= dev-mcelog.o
diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
new file mode 100644
index 000000000000..9c632cb88546
--- /dev/null
+++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
@@ -0,0 +1,397 @@
+/*
+ * /dev/mcelog driver
+ *
+ * K8 parts Copyright 2002,2003 Andi Kleen, SuSE Labs.
+ * Rest from unknown author(s).
+ * 2004 Andi Kleen. Rewrote most of it.
+ * Copyright 2008 Intel Corporation
+ * Author: Andi Kleen
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/miscdevice.h>
+#include <linux/slab.h>
+#include <linux/kmod.h>
+#include <linux/poll.h>
+
+#include "mce-internal.h"
+
+static DEFINE_MUTEX(mce_chrdev_read_mutex);
+
+static char mce_helper[128];
+static char *mce_helper_argv[2] = { mce_helper, NULL };
+
+#define mce_log_get_idx_check(p) \
+({ \
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
+			 !lockdep_is_held(&mce_chrdev_read_mutex), \
+			 "suspicious mce_log_get_idx_check() usage"); \
+	smp_load_acquire(&(p)); \
+})
+
+/*
+ * Lockless MCE logging infrastructure.
+ * This avoids deadlocks on printk locks without having to break locks. Also
+ * 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 DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
+
+/* User mode helper program triggered by machine check event */
+extern char			mce_helper[128];
+
+static int dev_mce_log(struct notifier_block *nb, unsigned long val,
+				void *data)
+{
+	struct mce *mce = (struct mce *)data;
+	unsigned int next, entry;
+
+	wmb();
+	for (;;) {
+		entry = mce_log_get_idx_check(mcelog.next);
+		for (;;) {
+
+			/*
+			 * 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);
+				return NOTIFY_OK;
+			}
+			/* Old left over entry. Skip: */
+			if (mcelog.entry[entry].finished) {
+				entry++;
+				continue;
+			}
+			break;
+		}
+		smp_rmb();
+		next = entry + 1;
+		if (cmpxchg(&mcelog.next, entry, next) == entry)
+			break;
+	}
+	memcpy(mcelog.entry + entry, mce, sizeof(struct mce));
+	wmb();
+	mcelog.entry[entry].finished = 1;
+	wmb();
+
+	/* wake processes polling /dev/mcelog */
+	wake_up_interruptible(&mce_chrdev_wait);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block dev_mcelog_nb = {
+	.notifier_call	= dev_mce_log,
+	.priority	= MCE_PRIO_MCELOG,
+};
+
+static void mce_do_trigger(struct work_struct *work)
+{
+	call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT);
+}
+
+static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
+
+
+void mce_work_trigger(void)
+{
+	if (mce_helper[0])
+		schedule_work(&mce_trigger_work);
+}
+
+static ssize_t
+show_trigger(struct device *s, struct device_attribute *attr, char *buf)
+{
+	strcpy(buf, mce_helper);
+	strcat(buf, "\n");
+	return strlen(mce_helper) + 1;
+}
+
+static ssize_t set_trigger(struct device *s, struct device_attribute *attr,
+				const char *buf, size_t siz)
+{
+	char *p;
+
+	strncpy(mce_helper, buf, sizeof(mce_helper));
+	mce_helper[sizeof(mce_helper)-1] = 0;
+	p = strchr(mce_helper, '\n');
+
+	if (p)
+		*p = 0;
+
+	return strlen(mce_helper) + !!p;
+}
+
+DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger);
+
+/*
+ * mce_chrdev: Character device /dev/mcelog to read and clear the MCE log.
+ */
+
+static DEFINE_SPINLOCK(mce_chrdev_state_lock);
+static int mce_chrdev_open_count;	/* #times opened */
+static int mce_chrdev_open_exclu;	/* already open exclusive? */
+
+static int mce_chrdev_open(struct inode *inode, struct file *file)
+{
+	spin_lock(&mce_chrdev_state_lock);
+
+	if (mce_chrdev_open_exclu ||
+	    (mce_chrdev_open_count && (file->f_flags & O_EXCL))) {
+		spin_unlock(&mce_chrdev_state_lock);
+
+		return -EBUSY;
+	}
+
+	if (file->f_flags & O_EXCL)
+		mce_chrdev_open_exclu = 1;
+	mce_chrdev_open_count++;
+
+	spin_unlock(&mce_chrdev_state_lock);
+
+	return nonseekable_open(inode, file);
+}
+
+static int mce_chrdev_release(struct inode *inode, struct file *file)
+{
+	spin_lock(&mce_chrdev_state_lock);
+
+	mce_chrdev_open_count--;
+	mce_chrdev_open_exclu = 0;
+
+	spin_unlock(&mce_chrdev_state_lock);
+
+	return 0;
+}
+
+static void collect_tscs(void *data)
+{
+	unsigned long *cpu_tsc = (unsigned long *)data;
+
+	cpu_tsc[smp_processor_id()] = rdtsc();
+}
+
+static int mce_apei_read_done;
+
+/* Collect MCE record of previous boot in persistent storage via APEI ERST. */
+static int __mce_read_apei(char __user **ubuf, size_t usize)
+{
+	int rc;
+	u64 record_id;
+	struct mce m;
+
+	if (usize < sizeof(struct mce))
+		return -EINVAL;
+
+	rc = apei_read_mce(&m, &record_id);
+	/* Error or no more MCE record */
+	if (rc <= 0) {
+		mce_apei_read_done = 1;
+		/*
+		 * When ERST is disabled, mce_chrdev_read() should return
+		 * "no record" instead of "no device."
+		 */
+		if (rc == -ENODEV)
+			return 0;
+		return rc;
+	}
+	rc = -EFAULT;
+	if (copy_to_user(*ubuf, &m, sizeof(struct mce)))
+		return rc;
+	/*
+	 * In fact, we should have cleared the record after that has
+	 * been flushed to the disk or sent to network in
+	 * /sbin/mcelog, but we have no interface to support that now,
+	 * so just clear it to avoid duplication.
+	 */
+	rc = apei_clear_mce(record_id);
+	if (rc) {
+		mce_apei_read_done = 1;
+		return rc;
+	}
+	*ubuf += sizeof(struct mce);
+
+	return 0;
+}
+
+static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
+				size_t usize, loff_t *off)
+{
+	char __user *buf = ubuf;
+	unsigned long *cpu_tsc;
+	unsigned prev, next;
+	int i, err;
+
+	cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL);
+	if (!cpu_tsc)
+		return -ENOMEM;
+
+	mutex_lock(&mce_chrdev_read_mutex);
+
+	if (!mce_apei_read_done) {
+		err = __mce_read_apei(&buf, usize);
+		if (err || buf != ubuf)
+			goto out;
+	}
+
+	next = mce_log_get_idx_check(mcelog.next);
+
+	/* Only supports full reads right now */
+	err = -EINVAL;
+	if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
+		goto out;
+
+	err = 0;
+	prev = 0;
+	do {
+		for (i = prev; i < next; i++) {
+			unsigned long start = jiffies;
+			struct mce *m = &mcelog.entry[i];
+
+			while (!m->finished) {
+				if (time_after_eq(jiffies, start + 2)) {
+					memset(m, 0, sizeof(*m));
+					goto timeout;
+				}
+				cpu_relax();
+			}
+			smp_rmb();
+			err |= copy_to_user(buf, m, sizeof(*m));
+			buf += sizeof(*m);
+timeout:
+			;
+		}
+
+		memset(mcelog.entry + prev, 0,
+		       (next - prev) * sizeof(struct mce));
+		prev = next;
+		next = cmpxchg(&mcelog.next, prev, 0);
+	} while (next != prev);
+
+	synchronize_sched();
+
+	/*
+	 * Collect entries that were still getting written before the
+	 * synchronize.
+	 */
+	on_each_cpu(collect_tscs, cpu_tsc, 1);
+
+	for (i = next; i < MCE_LOG_LEN; i++) {
+		struct mce *m = &mcelog.entry[i];
+
+		if (m->finished && m->tsc < cpu_tsc[m->cpu]) {
+			err |= copy_to_user(buf, m, sizeof(*m));
+			smp_rmb();
+			buf += sizeof(*m);
+			memset(m, 0, sizeof(*m));
+		}
+	}
+
+	if (err)
+		err = -EFAULT;
+
+out:
+	mutex_unlock(&mce_chrdev_read_mutex);
+	kfree(cpu_tsc);
+
+	return err ? err : buf - ubuf;
+}
+
+static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
+{
+	poll_wait(file, &mce_chrdev_wait, wait);
+	if (READ_ONCE(mcelog.next))
+		return POLLIN | POLLRDNORM;
+	if (!mce_apei_read_done && apei_check_mce())
+		return POLLIN | POLLRDNORM;
+	return 0;
+}
+
+static long mce_chrdev_ioctl(struct file *f, unsigned int cmd,
+				unsigned long arg)
+{
+	int __user *p = (int __user *)arg;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	switch (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);
+	case MCE_GETCLEAR_FLAGS: {
+		unsigned flags;
+
+		do {
+			flags = mcelog.flags;
+		} while (cmpxchg(&mcelog.flags, flags, 0) != flags);
+
+		return put_user(flags, p);
+	}
+	default:
+		return -ENOTTY;
+	}
+}
+
+static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf,
+			    size_t usize, loff_t *off);
+
+void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
+			     const char __user *ubuf,
+			     size_t usize, loff_t *off))
+{
+	mce_write = fn;
+}
+EXPORT_SYMBOL_GPL(register_mce_write_callback);
+
+static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
+				size_t usize, loff_t *off)
+{
+	if (mce_write)
+		return mce_write(filp, ubuf, usize, off);
+	else
+		return -EINVAL;
+}
+
+static const struct file_operations mce_chrdev_ops = {
+	.open			= mce_chrdev_open,
+	.release		= mce_chrdev_release,
+	.read			= mce_chrdev_read,
+	.write			= mce_chrdev_write,
+	.poll			= mce_chrdev_poll,
+	.unlocked_ioctl		= mce_chrdev_ioctl,
+	.llseek			= no_llseek,
+};
+
+static struct miscdevice mce_chrdev_device = {
+	MISC_MCELOG_MINOR,
+	"mcelog",
+	&mce_chrdev_ops,
+};
+
+static __init int dev_mcelog_init_device(void)
+{
+	int err;
+
+	/* register character device /dev/mcelog */
+	err = misc_register(&mce_chrdev_device);
+	if (err) {
+		pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err);
+		return err;
+	}
+	mce_register_decode_chain(&dev_mcelog_nb);
+	return 0;
+}
+device_initcall_sync(dev_mcelog_init_device);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index 19592ba1a320..654ad0668d72 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -96,3 +96,11 @@ static inline bool mce_cmp(struct mce *m1, struct mce *m2)
 		m1->addr != m2->addr ||
 		m1->misc != m2->misc;
 }
+
+extern struct device_attribute dev_attr_trigger;
+
+#ifdef CONFIG_X86_MCELOG_LEGACY
+extern void mce_work_trigger(void);
+#else
+static inline void mce_work_trigger(void)	{ }
+#endif
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index af44ebeb593f..5abd4bf73d6e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -35,6 +35,7 @@
 #include <linux/poll.h>
 #include <linux/nmi.h>
 #include <linux/cpu.h>
+#include <linux/ras.h>
 #include <linux/smp.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
@@ -49,20 +50,11 @@
 #include <asm/tlbflush.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
+#include <asm/reboot.h>
 
 #include "mce-internal.h"
 
-static DEFINE_MUTEX(mce_chrdev_read_mutex);
-
-static int mce_chrdev_open_count;	/* #times opened */
-
-#define mce_log_get_idx_check(p) \
-({ \
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
-			 !lockdep_is_held(&mce_chrdev_read_mutex), \
-			 "suspicious mce_log_get_idx_check() usage"); \
-	smp_load_acquire(&(p)); \
-})
+static DEFINE_MUTEX(mce_log_mutex);
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/mce.h>
@@ -87,15 +79,9 @@ struct mca_config mca_cfg __read_mostly = {
 	.monarch_timeout = -1
 };
 
-/* User mode helper program triggered by machine check event */
-static unsigned long		mce_need_notify;
-static char			mce_helper[128];
-static char			*mce_helper_argv[2] = { mce_helper, NULL };
-
-static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
-
 static DEFINE_PER_CPU(struct mce, mces_seen);
-static int			cpu_missing;
+static unsigned long mce_need_notify;
+static int cpu_missing;
 
 /*
  * MCA banks polled by the period polling timer for corrected events.
@@ -145,80 +131,36 @@ void mce_setup(struct mce *m)
 DEFINE_PER_CPU(struct mce, injectm);
 EXPORT_PER_CPU_SYMBOL_GPL(injectm);
 
-/*
- * Lockless MCE logging infrastructure.
- * This avoids deadlocks on printk locks without having to break locks. Also
- * separate MCEs from kernel messages to avoid bogus bug reports.
- */
-
-static struct mce_log mcelog = {
-	.signature	= MCE_LOG_SIGNATURE,
-	.len		= MCE_LOG_LEN,
-	.recordlen	= sizeof(struct mce),
-};
-
-void mce_log(struct mce *mce)
+void mce_log(struct mce *m)
 {
-	unsigned next, entry;
-
-	/* Emit the trace record: */
-	trace_mce_record(mce);
-
-	if (!mce_gen_pool_add(mce))
+	if (!mce_gen_pool_add(m))
 		irq_work_queue(&mce_irq_work);
-
-	wmb();
-	for (;;) {
-		entry = mce_log_get_idx_check(mcelog.next);
-		for (;;) {
-
-			/*
-			 * 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);
-				return;
-			}
-			/* Old left over entry. Skip: */
-			if (mcelog.entry[entry].finished) {
-				entry++;
-				continue;
-			}
-			break;
-		}
-		smp_rmb();
-		next = entry + 1;
-		if (cmpxchg(&mcelog.next, entry, next) == entry)
-			break;
-	}
-	memcpy(mcelog.entry + entry, mce, sizeof(struct mce));
-	wmb();
-	mcelog.entry[entry].finished = 1;
-	wmb();
-
-	set_bit(0, &mce_need_notify);
 }
 
 void mce_inject_log(struct mce *m)
 {
-	mutex_lock(&mce_chrdev_read_mutex);
+	mutex_lock(&mce_log_mutex);
 	mce_log(m);
-	mutex_unlock(&mce_chrdev_read_mutex);
+	mutex_unlock(&mce_log_mutex);
 }
 EXPORT_SYMBOL_GPL(mce_inject_log);
 
 static struct notifier_block mce_srao_nb;
 
+/*
+ * We run the default notifier if we have only the SRAO, the first and the
+ * default notifier registered. I.e., the mandatory NUM_DEFAULT_NOTIFIERS
+ * notifiers registered on the chain.
+ */
+#define NUM_DEFAULT_NOTIFIERS	3
 static atomic_t num_notifiers;
 
 void mce_register_decode_chain(struct notifier_block *nb)
 {
-	atomic_inc(&num_notifiers);
+	if (WARN_ON(nb->priority > MCE_PRIO_MCELOG && nb->priority < MCE_PRIO_EDAC))
+		return;
 
-	WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC);
+	atomic_inc(&num_notifiers);
 
 	blocking_notifier_chain_register(&x86_mce_decoder_chain, nb);
 }
@@ -510,7 +452,6 @@ static void mce_schedule_work(void)
 
 static void mce_irq_work_cb(struct irq_work *entry)
 {
-	mce_notify_irq();
 	mce_schedule_work();
 }
 
@@ -539,20 +480,97 @@ static void mce_report_event(struct pt_regs *regs)
  */
 static int mce_usable_address(struct mce *m)
 {
-	if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV))
+	if (!(m->status & MCI_STATUS_ADDRV))
 		return 0;
 
 	/* Checks after this one are Intel-specific: */
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return 1;
 
+	if (!(m->status & MCI_STATUS_MISCV))
+		return 0;
+
 	if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT)
 		return 0;
+
 	if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS)
 		return 0;
+
 	return 1;
 }
 
+static bool memory_error(struct mce *m)
+{
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	if (c->x86_vendor == X86_VENDOR_AMD) {
+		/* ErrCodeExt[20:16] */
+		u8 xec = (m->status >> 16) & 0x1f;
+
+		return (xec == 0x0 || xec == 0x8);
+	} else if (c->x86_vendor == X86_VENDOR_INTEL) {
+		/*
+		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
+		 *
+		 * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for
+		 * indicating a memory error. Bit 8 is used for indicating a
+		 * cache hierarchy error. The combination of bit 2 and bit 3
+		 * is used for indicating a `generic' cache hierarchy error
+		 * But we can't just blindly check the above bits, because if
+		 * bit 11 is set, then it is a bus/interconnect error - and
+		 * either way the above bits just gives more detail on what
+		 * bus/interconnect error happened. Note that bit 12 can be
+		 * ignored, as it's the "filter" bit.
+		 */
+		return (m->status & 0xef80) == BIT(7) ||
+		       (m->status & 0xef00) == BIT(8) ||
+		       (m->status & 0xeffc) == 0xc;
+	}
+
+	return false;
+}
+
+static bool cec_add_mce(struct mce *m)
+{
+	if (!m)
+		return false;
+
+	/* We eat only correctable DRAM errors with usable addresses. */
+	if (memory_error(m) &&
+	    !(m->status & MCI_STATUS_UC) &&
+	    mce_usable_address(m))
+		if (!cec_add_elem(m->addr >> PAGE_SHIFT))
+			return true;
+
+	return false;
+}
+
+static int mce_first_notifier(struct notifier_block *nb, unsigned long val,
+			      void *data)
+{
+	struct mce *m = (struct mce *)data;
+
+	if (!m)
+		return NOTIFY_DONE;
+
+	if (cec_add_mce(m))
+		return NOTIFY_STOP;
+
+	/* Emit the trace record: */
+	trace_mce_record(m);
+
+	set_bit(0, &mce_need_notify);
+
+	mce_notify_irq();
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block first_nb = {
+	.notifier_call	= mce_first_notifier,
+	.priority	= MCE_PRIO_FIRST,
+};
+
 static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
 				void *data)
 {
@@ -582,15 +600,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
 	if (!m)
 		return NOTIFY_DONE;
 
-	/*
-	 * Run the default notifier if we have only the SRAO
-	 * notifier and us registered.
-	 */
-	if (atomic_read(&num_notifiers) > 2)
-		return NOTIFY_DONE;
-
-	/* Don't print when mcelog is running */
-	if (mce_chrdev_open_count > 0)
+	if (atomic_read(&num_notifiers) > NUM_DEFAULT_NOTIFIERS)
 		return NOTIFY_DONE;
 
 	__print_mce(m);
@@ -643,37 +653,6 @@ static void mce_read_aux(struct mce *m, int i)
 	}
 }
 
-static bool memory_error(struct mce *m)
-{
-	struct cpuinfo_x86 *c = &boot_cpu_data;
-
-	if (c->x86_vendor == X86_VENDOR_AMD) {
-		/* ErrCodeExt[20:16] */
-		u8 xec = (m->status >> 16) & 0x1f;
-
-		return (xec == 0x0 || xec == 0x8);
-	} else if (c->x86_vendor == X86_VENDOR_INTEL) {
-		/*
-		 * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
-		 *
-		 * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for
-		 * indicating a memory error. Bit 8 is used for indicating a
-		 * cache hierarchy error. The combination of bit 2 and bit 3
-		 * is used for indicating a `generic' cache hierarchy error
-		 * But we can't just blindly check the above bits, because if
-		 * bit 11 is set, then it is a bus/interconnect error - and
-		 * either way the above bits just gives more detail on what
-		 * bus/interconnect error happened. Note that bit 12 can be
-		 * ignored, as it's the "filter" bit.
-		 */
-		return (m->status & 0xef80) == BIT(7) ||
-		       (m->status & 0xef00) == BIT(8) ||
-		       (m->status & 0xeffc) == 0xc;
-	}
-
-	return false;
-}
-
 DEFINE_PER_CPU(unsigned, mce_poll_count);
 
 /*
@@ -1122,9 +1101,22 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	 * on Intel.
 	 */
 	int lmce = 1;
+	int cpu = smp_processor_id();
 
-	/* If this CPU is offline, just bail out. */
-	if (cpu_is_offline(smp_processor_id())) {
+	/*
+	 * Cases where we avoid rendezvous handler timeout:
+	 * 1) If this CPU is offline.
+	 *
+	 * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to
+	 *  skip those CPUs which remain looping in the 1st kernel - see
+	 *  crash_nmi_callback().
+	 *
+	 * Note: there still is a small window between kexec-ing and the new,
+	 * kdump kernel establishing a new #MC handler where a broadcasted MCE
+	 * might not get handled properly.
+	 */
+	if (cpu_is_offline(cpu) ||
+	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
 		u64 mcgstatus;
 
 		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
@@ -1394,13 +1386,6 @@ static void mce_timer_delete_all(void)
 		del_timer_sync(&per_cpu(mce_timer, cpu));
 }
 
-static void mce_do_trigger(struct work_struct *work)
-{
-	call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT);
-}
-
-static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
-
 /*
  * Notify the user(s) about new machine check events.
  * Can be called from interrupt context, but not from machine check/NMI
@@ -1412,11 +1397,7 @@ int mce_notify_irq(void)
 	static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);
 
 	if (test_and_clear_bit(0, &mce_need_notify)) {
-		/* wake processes polling /dev/mcelog */
-		wake_up_interruptible(&mce_chrdev_wait);
-
-		if (mce_helper[0])
-			schedule_work(&mce_trigger_work);
+		mce_work_trigger();
 
 		if (__ratelimit(&ratelimit))
 			pr_info(HW_ERR "Machine check events logged\n");
@@ -1683,30 +1664,35 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
 	return 0;
 }
 
-static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
+/*
+ * Init basic CPU features needed for early decoding of MCEs.
+ */
+static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
 {
-	switch (c->x86_vendor) {
-	case X86_VENDOR_INTEL:
-		mce_intel_feature_init(c);
-		mce_adjust_timer = cmci_intel_adjust_timer;
-		break;
-
-	case X86_VENDOR_AMD: {
+	if (c->x86_vendor == X86_VENDOR_AMD) {
 		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);
 
-		/*
-		 * Install proper ops for Scalable MCA enabled processors
-		 */
 		if (mce_flags.smca) {
 			msr_ops.ctl	= smca_ctl_reg;
 			msr_ops.status	= smca_status_reg;
 			msr_ops.addr	= smca_addr_reg;
 			msr_ops.misc	= smca_misc_reg;
 		}
-		mce_amd_feature_init(c);
+	}
+}
+
+static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
+{
+	switch (c->x86_vendor) {
+	case X86_VENDOR_INTEL:
+		mce_intel_feature_init(c);
+		mce_adjust_timer = cmci_intel_adjust_timer;
+		break;
 
+	case X86_VENDOR_AMD: {
+		mce_amd_feature_init(c);
 		break;
 		}
 
@@ -1793,6 +1779,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 
 	machine_check_vector = do_machine_check;
 
+	__mcheck_cpu_init_early(c);
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
 	__mcheck_cpu_init_clear_banks();
@@ -1818,251 +1805,6 @@ void mcheck_cpu_clear(struct cpuinfo_x86 *c)
 
 }
 
-/*
- * mce_chrdev: Character device /dev/mcelog to read and clear the MCE log.
- */
-
-static DEFINE_SPINLOCK(mce_chrdev_state_lock);
-static int mce_chrdev_open_exclu;	/* already open exclusive? */
-
-static int mce_chrdev_open(struct inode *inode, struct file *file)
-{
-	spin_lock(&mce_chrdev_state_lock);
-
-	if (mce_chrdev_open_exclu ||
-	    (mce_chrdev_open_count && (file->f_flags & O_EXCL))) {
-		spin_unlock(&mce_chrdev_state_lock);
-
-		return -EBUSY;
-	}
-
-	if (file->f_flags & O_EXCL)
-		mce_chrdev_open_exclu = 1;
-	mce_chrdev_open_count++;
-
-	spin_unlock(&mce_chrdev_state_lock);
-
-	return nonseekable_open(inode, file);
-}
-
-static int mce_chrdev_release(struct inode *inode, struct file *file)
-{
-	spin_lock(&mce_chrdev_state_lock);
-
-	mce_chrdev_open_count--;
-	mce_chrdev_open_exclu = 0;
-
-	spin_unlock(&mce_chrdev_state_lock);
-
-	return 0;
-}
-
-static void collect_tscs(void *data)
-{
-	unsigned long *cpu_tsc = (unsigned long *)data;
-
-	cpu_tsc[smp_processor_id()] = rdtsc();
-}
-
-static int mce_apei_read_done;
-
-/* Collect MCE record of previous boot in persistent storage via APEI ERST. */
-static int __mce_read_apei(char __user **ubuf, size_t usize)
-{
-	int rc;
-	u64 record_id;
-	struct mce m;
-
-	if (usize < sizeof(struct mce))
-		return -EINVAL;
-
-	rc = apei_read_mce(&m, &record_id);
-	/* Error or no more MCE record */
-	if (rc <= 0) {
-		mce_apei_read_done = 1;
-		/*
-		 * When ERST is disabled, mce_chrdev_read() should return
-		 * "no record" instead of "no device."
-		 */
-		if (rc == -ENODEV)
-			return 0;
-		return rc;
-	}
-	rc = -EFAULT;
-	if (copy_to_user(*ubuf, &m, sizeof(struct mce)))
-		return rc;
-	/*
-	 * In fact, we should have cleared the record after that has
-	 * been flushed to the disk or sent to network in
-	 * /sbin/mcelog, but we have no interface to support that now,
-	 * so just clear it to avoid duplication.
-	 */
-	rc = apei_clear_mce(record_id);
-	if (rc) {
-		mce_apei_read_done = 1;
-		return rc;
-	}
-	*ubuf += sizeof(struct mce);
-
-	return 0;
-}
-
-static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
-				size_t usize, loff_t *off)
-{
-	char __user *buf = ubuf;
-	unsigned long *cpu_tsc;
-	unsigned prev, next;
-	int i, err;
-
-	cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL);
-	if (!cpu_tsc)
-		return -ENOMEM;
-
-	mutex_lock(&mce_chrdev_read_mutex);
-
-	if (!mce_apei_read_done) {
-		err = __mce_read_apei(&buf, usize);
-		if (err || buf != ubuf)
-			goto out;
-	}
-
-	next = mce_log_get_idx_check(mcelog.next);
-
-	/* Only supports full reads right now */
-	err = -EINVAL;
-	if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
-		goto out;
-
-	err = 0;
-	prev = 0;
-	do {
-		for (i = prev; i < next; i++) {
-			unsigned long start = jiffies;
-			struct mce *m = &mcelog.entry[i];
-
-			while (!m->finished) {
-				if (time_after_eq(jiffies, start + 2)) {
-					memset(m, 0, sizeof(*m));
-					goto timeout;
-				}
-				cpu_relax();
-			}
-			smp_rmb();
-			err |= copy_to_user(buf, m, sizeof(*m));
-			buf += sizeof(*m);
-timeout:
-			;
-		}
-
-		memset(mcelog.entry + prev, 0,
-		       (next - prev) * sizeof(struct mce));
-		prev = next;
-		next = cmpxchg(&mcelog.next, prev, 0);
-	} while (next != prev);
-
-	synchronize_sched();
-
-	/*
-	 * Collect entries that were still getting written before the
-	 * synchronize.
-	 */
-	on_each_cpu(collect_tscs, cpu_tsc, 1);
-
-	for (i = next; i < MCE_LOG_LEN; i++) {
-		struct mce *m = &mcelog.entry[i];
-
-		if (m->finished && m->tsc < cpu_tsc[m->cpu]) {
-			err |= copy_to_user(buf, m, sizeof(*m));
-			smp_rmb();
-			buf += sizeof(*m);
-			memset(m, 0, sizeof(*m));
-		}
-	}
-
-	if (err)
-		err = -EFAULT;
-
-out:
-	mutex_unlock(&mce_chrdev_read_mutex);
-	kfree(cpu_tsc);
-
-	return err ? err : buf - ubuf;
-}
-
-static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
-{
-	poll_wait(file, &mce_chrdev_wait, wait);
-	if (READ_ONCE(mcelog.next))
-		return POLLIN | POLLRDNORM;
-	if (!mce_apei_read_done && apei_check_mce())
-		return POLLIN | POLLRDNORM;
-	return 0;
-}
-
-static long mce_chrdev_ioctl(struct file *f, unsigned int cmd,
-				unsigned long arg)
-{
-	int __user *p = (int __user *)arg;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	switch (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);
-	case MCE_GETCLEAR_FLAGS: {
-		unsigned flags;
-
-		do {
-			flags = mcelog.flags;
-		} while (cmpxchg(&mcelog.flags, flags, 0) != flags);
-
-		return put_user(flags, p);
-	}
-	default:
-		return -ENOTTY;
-	}
-}
-
-static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf,
-			    size_t usize, loff_t *off);
-
-void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
-			     const char __user *ubuf,
-			     size_t usize, loff_t *off))
-{
-	mce_write = fn;
-}
-EXPORT_SYMBOL_GPL(register_mce_write_callback);
-
-static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
-				size_t usize, loff_t *off)
-{
-	if (mce_write)
-		return mce_write(filp, ubuf, usize, off);
-	else
-		return -EINVAL;
-}
-
-static const struct file_operations mce_chrdev_ops = {
-	.open			= mce_chrdev_open,
-	.release		= mce_chrdev_release,
-	.read			= mce_chrdev_read,
-	.write			= mce_chrdev_write,
-	.poll			= mce_chrdev_poll,
-	.unlocked_ioctl		= mce_chrdev_ioctl,
-	.llseek			= no_llseek,
-};
-
-static struct miscdevice mce_chrdev_device = {
-	MISC_MCELOG_MINOR,
-	"mcelog",
-	&mce_chrdev_ops,
-};
-
 static void __mce_disable_bank(void *arg)
 {
 	int bank = *((int *)arg);
@@ -2136,6 +1878,7 @@ __setup("mce", mcheck_enable);
 int __init mcheck_init(void)
 {
 	mcheck_intel_therm_init();
+	mce_register_decode_chain(&first_nb);
 	mce_register_decode_chain(&mce_srao_nb);
 	mce_register_decode_chain(&mce_default_nb);
 	mcheck_vendor_init_severity();
@@ -2280,29 +2023,6 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr,
 	return size;
 }
 
-static ssize_t
-show_trigger(struct device *s, struct device_attribute *attr, char *buf)
-{
-	strcpy(buf, mce_helper);
-	strcat(buf, "\n");
-	return strlen(mce_helper) + 1;
-}
-
-static ssize_t set_trigger(struct device *s, struct device_attribute *attr,
-				const char *buf, size_t siz)
-{
-	char *p;
-
-	strncpy(mce_helper, buf, sizeof(mce_helper));
-	mce_helper[sizeof(mce_helper)-1] = 0;
-	p = strchr(mce_helper, '\n');
-
-	if (p)
-		*p = 0;
-
-	return strlen(mce_helper) + !!p;
-}
-
 static ssize_t set_ignore_ce(struct device *s,
 			     struct device_attribute *attr,
 			     const char *buf, size_t size)
@@ -2359,7 +2079,6 @@ static ssize_t store_int_with_restart(struct device *s,
 	return ret;
 }
 
-static DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger);
 static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant);
 static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout);
 static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce);
@@ -2382,7 +2101,9 @@ static struct dev_ext_attribute dev_attr_cmci_disabled = {
 static struct device_attribute *mce_device_attrs[] = {
 	&dev_attr_tolerant.attr,
 	&dev_attr_check_interval.attr,
+#ifdef CONFIG_X86_MCELOG_LEGACY
 	&dev_attr_trigger,
+#endif
 	&dev_attr_monarch_timeout.attr,
 	&dev_attr_dont_log_ce.attr,
 	&dev_attr_ignore_ce.attr,
@@ -2556,7 +2277,6 @@ static __init void mce_init_banks(void)
 
 static __init int mcheck_init_device(void)
 {
-	enum cpuhp_state hp_online;
 	int err;
 
 	if (!mce_available(&boot_cpu_data)) {
@@ -2584,21 +2304,11 @@ static __init int mcheck_init_device(void)
 				mce_cpu_online, mce_cpu_pre_down);
 	if (err < 0)
 		goto err_out_online;
-	hp_online = err;
 
 	register_syscore_ops(&mce_syscore_ops);
 
-	/* register character device /dev/mcelog */
-	err = misc_register(&mce_chrdev_device);
-	if (err)
-		goto err_register;
-
 	return 0;
 
-err_register:
-	unregister_syscore_ops(&mce_syscore_ops);
-	cpuhp_remove_state(hp_online);
-
 err_out_online:
 	cpuhp_remove_state(CPUHP_X86_MCE_DEAD);
 
@@ -2606,7 +2316,7 @@ err_out_mem:
 	free_cpumask_var(mce_device_initialized);
 
 err_out:
-	pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err);
+	pr_err("Unable to init MCE device (rc: %d)\n", err);
 
 	return err;
 }
@@ -2685,6 +2395,7 @@ static int __init mcheck_late_init(void)
 		static_branch_inc(&mcsafe_key);
 
 	mcheck_debugfs_init();
+	cec_init();
 
 	/*
 	 * Flush out everything that has been logged during early boot, now that
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 190b3e6cef4d..e84db79ef272 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -481,6 +481,9 @@ static void intel_ppin_init(struct cpuinfo_x86 *c)
 	case INTEL_FAM6_BROADWELL_XEON_D:
 	case INTEL_FAM6_BROADWELL_X:
 	case INTEL_FAM6_SKYLAKE_X:
+	case INTEL_FAM6_XEON_PHI_KNL:
+	case INTEL_FAM6_XEON_PHI_KNM:
+
 		if (rdmsrl_safe(MSR_PPIN_CTL, &val))
 			return;
 
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 3b442b64c72d..765afd599039 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -27,7 +27,7 @@
 #include <linux/range.h>
 
 #include <asm/processor.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
 
@@ -860,7 +860,7 @@ real_trim_memory(unsigned long start_pfn, unsigned long limit_pfn)
 	trim_size <<= PAGE_SHIFT;
 	trim_size -= trim_start;
 
-	return e820_update_range(trim_start, trim_size, E820_RAM, E820_RESERVED);
+	return e820__range_update(trim_start, trim_size, E820_TYPE_RAM, E820_TYPE_RESERVED);
 }
 
 /**
@@ -978,7 +978,7 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 			WARN_ON(1);
 
 		pr_info("update e820 for mtrr\n");
-		update_e820();
+		e820__update_table_print();
 
 		return 1;
 	}
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 24e87e74990d..2bce84d91c2b 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -48,7 +48,7 @@
 #include <linux/syscore_ops.h>
 
 #include <asm/cpufeature.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
 #include <asm/pat.h>
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 18ca99f2798b..6df621ae62a7 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -31,14 +31,13 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c)
 		   "fpu\t\t: %s\n"
 		   "fpu_exception\t: %s\n"
 		   "cpuid level\t: %d\n"
-		   "wp\t\t: %s\n",
+		   "wp\t\t: yes\n",
 		   static_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
 		   static_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
 		   static_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
 		   static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
 		   static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
-		   c->cpuid_level,
-		   c->wp_works_ok ? "yes" : "no");
+		   c->cpuid_level);
 }
 #else
 static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index d9794060fe22..23c23508c012 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -27,6 +27,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ 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 },
+	{ X86_FEATURE_MBA,		CPUID_EBX,  3, 0x00000010, 0 },
 	{ X86_FEATURE_HW_PSTATE,	CPUID_EDX,  7, 0x80000007, 0 },
 	{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
 	{ X86_FEATURE_PROC_FEEDBACK,    CPUID_EDX, 11, 0x80000007, 0 },