Merge remote-tracking branch 'tip/auto-latest'

112 files changed, 2053 insertions, 2167 deletions

diff --git a/Documentation/IRQ-domain.txt b/Documentation/IRQ-domain.txt
index 82001a25a14b..1f246eb25ca5 100644
--- a/Documentation/IRQ-domain.txt
+++ b/Documentation/IRQ-domain.txt
@@ -231,5 +231,42 @@ needs to:
 4) No need to implement irq_domain_ops.map and irq_domain_ops.unmap,
    they are unused with hierarchy irq_domain.
 
-Hierarchy irq_domain may also be used to support other architectures,
-such as ARM, ARM64 etc.
+Hierarchy irq_domain is in no way x86 specific, and is heavily used to
+support other architectures, such as ARM, ARM64 etc.
+
+=== Debugging ===
+
+If you switch on CONFIG_IRQ_DOMAIN_DEBUG (which depends on
+CONFIG_IRQ_DOMAIN and CONFIG_DEBUG_FS), you will find a new file in
+your debugfs mount point, called irq_domain_mapping. This file
+contains a live snapshot of all the IRQ domains in the system:
+
+ name              mapped  linear-max  direct-max  devtree-node
+ pl061                  8           8           0  /smb/gpio@e0080000
+ pl061                  8           8           0  /smb/gpio@e1050000
+ pMSI                   0           0           0  /interrupt-controller@e1101000/v2m@e0080000
+ MSI                   37           0           0  /interrupt-controller@e1101000/v2m@e0080000
+ GICv2m                37           0           0  /interrupt-controller@e1101000/v2m@e0080000
+ GICv2                448         448           0  /interrupt-controller@e1101000
+
+it also iterates over the interrupts to display their mapping in the
+domains, and makes the domain stacking visible:
+
+
+irq    hwirq    chip name        chip data           active  type            domain
+    1  0x00019  GICv2            0xffff00000916bfd8     *    LINEAR          GICv2
+    2  0x0001d  GICv2            0xffff00000916bfd8          LINEAR          GICv2
+    3  0x0001e  GICv2            0xffff00000916bfd8     *    LINEAR          GICv2
+    4  0x0001b  GICv2            0xffff00000916bfd8     *    LINEAR          GICv2
+    5  0x0001a  GICv2            0xffff00000916bfd8          LINEAR          GICv2
+[...]
+   96  0x81808  MSI              0x          (null)           RADIX          MSI
+   96+ 0x00063  GICv2m           0xffff8003ee116980           RADIX          GICv2m
+   96+ 0x00063  GICv2            0xffff00000916bfd8          LINEAR          GICv2
+   97  0x08800  MSI              0x          (null)     *     RADIX          MSI
+   97+ 0x00064  GICv2m           0xffff8003ee116980     *     RADIX          GICv2m
+   97+ 0x00064  GICv2            0xffff00000916bfd8     *    LINEAR          GICv2
+
+Here, interrupts 1-5 are only using a single domain, while 96 and 97
+are build out of a stack of three domain, each level performing a
+particular function.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 15f79c27748d..4e4c3402412e 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2127,6 +2127,12 @@
 	memmap=nn[KMG]@ss[KMG]
 			[KNL] Force usage of a specific region of memory.
 			Region of memory to be used is from ss to ss+nn.
+			If @ss[KMG] is omitted, it is equivalent to mem=nn[KMG],
+			which limits max address to nn[KMG].
+			Multiple different regions can be specified,
+			comma delimited.
+			Example:
+				memmap=100M@2G,100M#3G,1G!1024G
 
 	memmap=nn[KMG]#ss[KMG]
 			[KNL,ACPI] Mark specific memory as ACPI data.
@@ -2139,6 +2145,9 @@
 			         memmap=64K$0x18690000
 			         or
 			         memmap=0x10000$0x18690000
+			Some bootloaders may need an escape character before '$',
+			like Grub2, otherwise '$' and the following number
+			will be eaten.
 
 	memmap=nn[KMG]!ss[KMG]
 			[KNL,X86] Mark specific memory as protected.
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index be3b3fbd382f..63cb4c7c6593 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -1090,7 +1090,7 @@ static int __init arch_hw_breakpoint_init(void)
 	 * driven low on this core and there isn't an architected way to
 	 * determine that.
 	 */
-	get_online_cpus();
+	cpus_read_lock();
 	register_undef_hook(&debug_reg_hook);
 
 	/*
@@ -1098,15 +1098,16 @@ static int __init arch_hw_breakpoint_init(void)
 	 * assume that a halting debugger will leave the world in a nice state
 	 * for us.
 	 */
-	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "arm/hw_breakpoint:online",
-				dbg_reset_online, NULL);
+	ret = cpuhp_setup_state_cpuslocked(CPUHP_AP_ONLINE_DYN,
+					   "arm/hw_breakpoint:online",
+					   dbg_reset_online, NULL);
 	unregister_undef_hook(&debug_reg_hook);
 	if (WARN_ON(ret < 0) || !cpumask_empty(&debug_err_mask)) {
 		core_num_brps = 0;
 		core_num_wrps = 0;
 		if (ret > 0)
 			cpuhp_remove_state_nocalls(ret);
-		put_online_cpus();
+		cpus_read_unlock();
 		return 0;
 	}
 
@@ -1124,7 +1125,7 @@ static int __init arch_hw_breakpoint_init(void)
 			TRAP_HWBKPT, "watchpoint debug exception");
 	hook_ifault_code(FAULT_CODE_DEBUG, hw_breakpoint_pending, SIGTRAP,
 			TRAP_HWBKPT, "breakpoint debug exception");
-	put_online_cpus();
+	cpus_read_unlock();
 
 	/* Register PM notifiers. */
 	pm_init();
diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c
index 020560b2dcb7..a1a34722c655 100644
--- a/arch/arm/kernel/patch.c
+++ b/arch/arm/kernel/patch.c
@@ -124,5 +124,5 @@ void __kprobes patch_text(void *addr, unsigned int insn)
 		.insn = insn,
 	};
 
-	stop_machine(patch_text_stop_machine, &patch, NULL);
+	stop_machine_cpuslocked(patch_text_stop_machine, &patch, NULL);
 }
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 572a8df1b766..c9a0a5299827 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -555,8 +555,7 @@ static DEFINE_RAW_SPINLOCK(stop_lock);
  */
 static void ipi_cpu_stop(unsigned int cpu)
 {
-	if (system_state == SYSTEM_BOOTING ||
-	    system_state == SYSTEM_RUNNING) {
+	if (system_state <= SYSTEM_RUNNING) {
 		raw_spin_lock(&stop_lock);
 		pr_crit("CPU%u: stopping\n", cpu);
 		dump_stack();
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index ad1f4e6a9e33..52d1cd14fda4 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -182,7 +182,8 @@ void __kprobes kprobes_remove_breakpoint(void *addr, unsigned int insn)
 		.addr = addr,
 		.insn = insn,
 	};
-	stop_machine(__kprobes_remove_breakpoint, &p, cpu_online_mask);
+	stop_machine_cpuslocked(__kprobes_remove_breakpoint, &p,
+				cpu_online_mask);
 }
 
 void __kprobes arch_disarm_kprobe(struct kprobe *p)
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 29cb2ca756f6..4214c38d016b 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -433,7 +433,6 @@ u32 aarch64_set_branch_offset(u32 insn, s32 offset);
 bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn);
 
 int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
-int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt);
 int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
 
 s32 aarch64_insn_adrp_get_offset(u32 insn);
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index b884a926a632..cd872133e88e 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -255,6 +255,7 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)
 	return ret;
 }
 
+static
 int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt)
 {
 	struct aarch64_insn_patch patch = {
@@ -267,8 +268,8 @@ int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt)
 	if (cnt <= 0)
 		return -EINVAL;
 
-	return stop_machine(aarch64_insn_patch_text_cb, &patch,
-			    cpu_online_mask);
+	return stop_machine_cpuslocked(aarch64_insn_patch_text_cb, &patch,
+				       cpu_online_mask);
 }
 
 int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 6e0e16a3a7d4..321119881abf 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -961,8 +961,7 @@ void smp_send_stop(void)
 		cpumask_copy(&mask, cpu_online_mask);
 		cpumask_clear_cpu(smp_processor_id(), &mask);
 
-		if (system_state == SYSTEM_BOOTING ||
-		    system_state == SYSTEM_RUNNING)
+		if (system_state <= SYSTEM_RUNNING)
 			pr_crit("SMP: stopping secondary CPUs\n");
 		smp_cross_call(&mask, IPI_CPU_STOP);
 	}
diff --git a/arch/metag/kernel/smp.c b/arch/metag/kernel/smp.c
index 232a12bf3f99..2dbbb7c66043 100644
--- a/arch/metag/kernel/smp.c
+++ b/arch/metag/kernel/smp.c
@@ -567,8 +567,7 @@ static void stop_this_cpu(void *data)
 {
 	unsigned int cpu = smp_processor_id();
 
-	if (system_state == SYSTEM_BOOTING ||
-	    system_state == SYSTEM_RUNNING) {
+	if (system_state <= SYSTEM_RUNNING) {
 		spin_lock(&stop_lock);
 		pr_crit("CPU%u: stopping\n", cpu);
 		dump_stack();
diff --git a/arch/mips/kernel/jump_label.c b/arch/mips/kernel/jump_label.c
index 3e586daa3a32..32e3168316cd 100644
--- a/arch/mips/kernel/jump_label.c
+++ b/arch/mips/kernel/jump_label.c
@@ -58,7 +58,6 @@ void arch_jump_label_transform(struct jump_entry *e,
 		insn.word = 0; /* nop */
 	}
 
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 	if (IS_ENABLED(CONFIG_CPU_MICROMIPS)) {
 		insn_p->halfword[0] = insn.word >> 16;
@@ -70,7 +69,6 @@ void arch_jump_label_transform(struct jump_entry *e,
 			   (unsigned long)insn_p + sizeof(*insn_p));
 
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 #endif /* HAVE_JUMP_LABEL */
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index df2a41647d8e..1069f74fca47 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -97,7 +97,7 @@ int smp_generic_cpu_bootable(unsigned int nr)
 	/* Special case - we inhibit secondary thread startup
 	 * during boot if the user requests it.
 	 */
-	if (system_state == SYSTEM_BOOTING && cpu_has_feature(CPU_FTR_SMT)) {
+	if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) {
 		if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
 			return 0;
 		if (smt_enabled_at_boot
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 42b7a4fd57d9..48a6bd160011 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3317,7 +3317,7 @@ void kvmppc_alloc_host_rm_ops(void)
 		return;
 	}
 
-	get_online_cpus();
+	cpus_read_lock();
 
 	for (cpu = 0; cpu < nr_cpu_ids; cpu += threads_per_core) {
 		if (!cpu_online(cpu))
@@ -3339,17 +3339,17 @@ void kvmppc_alloc_host_rm_ops(void)
 	l_ops = (unsigned long) ops;
 
 	if (cmpxchg64((unsigned long *)&kvmppc_host_rm_ops_hv, 0, l_ops)) {
-		put_online_cpus();
+		cpus_read_unlock();
 		kfree(ops->rm_core);
 		kfree(ops);
 		return;
 	}
 
-	cpuhp_setup_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE,
-				  "ppc/kvm_book3s:prepare",
-				  kvmppc_set_host_core,
-				  kvmppc_clear_host_core);
-	put_online_cpus();
+	cpuhp_setup_state_nocalls_cpuslocked(CPUHP_KVM_PPC_BOOK3S_PREPARE,
+					     "ppc/kvm_book3s:prepare",
+					     kvmppc_set_host_core,
+					     kvmppc_clear_host_core);
+	cpus_read_unlock();
 }
 
 void kvmppc_free_host_rm_ops(void)
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index 0babef11136f..e6230f104dd9 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -348,7 +348,7 @@ static int set_subcores_per_core(int new_mode)
 		state->master = 0;
 	}
 
-	get_online_cpus();
+	cpus_read_lock();
 
 	/* This cpu will update the globals before exiting stop machine */
 	this_cpu_ptr(&split_state)->master = 1;
@@ -356,9 +356,10 @@ static int set_subcores_per_core(int new_mode)
 	/* Ensure state is consistent before we call the other cpus */
 	mb();
 
-	stop_machine(cpu_update_split_mode, &new_mode, cpu_online_mask);
+	stop_machine_cpuslocked(cpu_update_split_mode, &new_mode,
+				cpu_online_mask);
 
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return 0;
 }
diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c
index 6aa630a8d24f..262506cee4c3 100644
--- a/arch/s390/kernel/jump_label.c
+++ b/arch/s390/kernel/jump_label.c
@@ -93,7 +93,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
 	args.entry = entry;
 	args.type = type;
 
-	stop_machine(__sm_arch_jump_label_transform, &args, NULL);
+	stop_machine_cpuslocked(__sm_arch_jump_label_transform, &args, NULL);
 }
 
 void arch_jump_label_transform_static(struct jump_entry *entry,
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 3d6a99746454..6842e4501e2e 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -196,7 +196,7 @@ void arch_arm_kprobe(struct kprobe *p)
 {
 	struct swap_insn_args args = {.p = p, .arm_kprobe = 1};
 
-	stop_machine(swap_instruction, &args, NULL);
+	stop_machine_cpuslocked(swap_instruction, &args, NULL);
 }
 NOKPROBE_SYMBOL(arch_arm_kprobe);
 
@@ -204,7 +204,7 @@ void arch_disarm_kprobe(struct kprobe *p)
 {
 	struct swap_insn_args args = {.p = p, .arm_kprobe = 0};
 
-	stop_machine(swap_instruction, &args, NULL);
+	stop_machine_cpuslocked(swap_instruction, &args, NULL);
 }
 NOKPROBE_SYMBOL(arch_disarm_kprobe);
 
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index c3a52f9a69a0..192efdfac918 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -636,10 +636,10 @@ static void stp_work_fn(struct work_struct *work)
 		goto out_unlock;
 
 	memset(&stp_sync, 0, sizeof(stp_sync));
-	get_online_cpus();
+	cpus_read_lock();
 	atomic_set(&stp_sync.cpus, num_online_cpus() - 1);
-	stop_machine(stp_sync_clock, &stp_sync, cpu_online_mask);
-	put_online_cpus();
+	stop_machine_cpuslocked(stp_sync_clock, &stp_sync, cpu_online_mask);
+	cpus_read_unlock();
 
 	if (!check_sync_clock())
 		/*
diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c
index 07933b9e9ce0..93adde1ac166 100644
--- a/arch/sparc/kernel/jump_label.c
+++ b/arch/sparc/kernel/jump_label.c
@@ -41,12 +41,10 @@ void arch_jump_label_transform(struct jump_entry *entry,
 		val = 0x01000000;
 	}
 
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 	*insn = val;
 	flushi(insn);
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 #endif
diff --git a/arch/tile/kernel/jump_label.c b/arch/tile/kernel/jump_label.c
index 07802d586988..93931a46625b 100644
--- a/arch/tile/kernel/jump_label.c
+++ b/arch/tile/kernel/jump_label.c
@@ -45,14 +45,12 @@ static void __jump_label_transform(struct jump_entry *e,
 void arch_jump_label_transform(struct jump_entry *e,
 				enum jump_label_type type)
 {
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 
 	__jump_label_transform(e, type);
 	flush_icache_range(e->code, e->code + sizeof(tilegx_bundle_bits));
 
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 __init_or_module void arch_jump_label_transform_static(struct jump_entry *e,
diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c
index 73ccf63b0f48..9dc1ce6ba3c0 100644
--- a/arch/x86/boot/compressed/cmdline.c
+++ b/arch/x86/boot/compressed/cmdline.c
@@ -13,7 +13,7 @@ static inline char rdfs8(addr_t addr)
 	return *((char *)(fs + addr));
 }
 #include "../cmdline.c"
-static unsigned long get_cmd_line_ptr(void)
+unsigned long get_cmd_line_ptr(void)
 {
 	unsigned long cmd_line_ptr = boot_params->hdr.cmd_line_ptr;
 
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index 54c24f0a43d3..e0eba12bffe7 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -9,16 +9,41 @@
  * contain the entire properly aligned running kernel image.
  *
  */
+
+/*
+ * isspace() in linux/ctype.h is expected by next_args() to filter
+ * out "space/lf/tab". While boot/ctype.h conflicts with linux/ctype.h,
+ * since isdigit() is implemented in both of them. Hence disable it
+ * here.
+ */
+#define BOOT_CTYPE_H
+
+/*
+ * _ctype[] in lib/ctype.c is needed by isspace() of linux/ctype.h.
+ * While both lib/ctype.c and lib/cmdline.c will bring EXPORT_SYMBOL
+ * which is meaningless and will cause compiling error in some cases.
+ * So do not include linux/export.h and define EXPORT_SYMBOL(sym)
+ * as empty.
+ */
+#define _LINUX_EXPORT_H
+#define EXPORT_SYMBOL(sym)
+
 #include "misc.h"
 #include "error.h"
-#include "../boot.h"
 
 #include <generated/compile.h>
 #include <linux/module.h>
 #include <linux/uts.h>
 #include <linux/utsname.h>
+#include <linux/ctype.h>
 #include <generated/utsrelease.h>
 
+/* Macros used by the included decompressor code below. */
+#define STATIC
+#include <linux/decompress/mm.h>
+
+extern unsigned long get_cmd_line_ptr(void);
+
 /* Simplified build-specific string for starting entropy. */
 static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
 		LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
@@ -62,6 +87,11 @@ struct mem_vector {
 
 static bool memmap_too_large;
 
+
+/* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */
+unsigned long long mem_limit = ULLONG_MAX;
+
+
 enum mem_avoid_index {
 	MEM_AVOID_ZO_RANGE = 0,
 	MEM_AVOID_INITRD,
@@ -85,49 +115,14 @@ static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two)
 	return true;
 }
 
-/**
- *	_memparse - Parse a string with mem suffixes into a number
- *	@ptr: Where parse begins
- *	@retptr: (output) Optional pointer to next char after parse completes
- *
- *	Parses a string into a number.  The number stored at @ptr is
- *	potentially suffixed with K, M, G, T, P, E.
- */
-static unsigned long long _memparse(const char *ptr, char **retptr)
+char *skip_spaces(const char *str)
 {
-	char *endptr;	/* Local pointer to end of parsed string */
-
-	unsigned long long ret = simple_strtoull(ptr, &endptr, 0);
-
-	switch (*endptr) {
-	case 'E':
-	case 'e':
-		ret <<= 10;
-	case 'P':
-	case 'p':
-		ret <<= 10;
-	case 'T':
-	case 't':
-		ret <<= 10;
-	case 'G':
-	case 'g':
-		ret <<= 10;
-	case 'M':
-	case 'm':
-		ret <<= 10;
-	case 'K':
-	case 'k':
-		ret <<= 10;
-		endptr++;
-	default:
-		break;
-	}
-
-	if (retptr)
-		*retptr = endptr;
-
-	return ret;
+	while (isspace(*str))
+		++str;
+	return (char *)str;
 }
+#include "../../../../lib/ctype.c"
+#include "../../../../lib/cmdline.c"
 
 static int
 parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
@@ -142,40 +137,41 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
 		return -EINVAL;
 
 	oldp = p;
-	*size = _memparse(p, &p);
+	*size = memparse(p, &p);
 	if (p == oldp)
 		return -EINVAL;
 
 	switch (*p) {
-	case '@':
-		/* Skip this region, usable */
-		*start = 0;
-		*size = 0;
-		return 0;
 	case '#':
 	case '$':
 	case '!':
-		*start = _memparse(p + 1, &p);
+		*start = memparse(p + 1, &p);
+		return 0;
+	case '@':
+		/* memmap=nn@ss specifies usable region, should be skipped */
+		*size = 0;
+		/* Fall through */
+	default:
+		/*
+		 * If w/o offset, only size specified, memmap=nn[KMG] has the
+		 * same behaviour as mem=nn[KMG]. It limits the max address
+		 * system can use. Region above the limit should be avoided.
+		 */
+		*start = 0;
 		return 0;
 	}
 
 	return -EINVAL;
 }
 
-static void mem_avoid_memmap(void)
+static void mem_avoid_memmap(char *str)
 {
-	char arg[128];
+	static int i;
 	int rc;
-	int i;
-	char *str;
 
-	/* See if we have any memmap areas */
-	rc = cmdline_find_option("memmap", arg, sizeof(arg));
-	if (rc <= 0)
+	if (i >= MAX_MEMMAP_REGIONS)
 		return;
 
-	i = 0;
-	str = arg;
 	while (str && (i < MAX_MEMMAP_REGIONS)) {
 		int rc;
 		unsigned long long start, size;
@@ -188,9 +184,14 @@ static void mem_avoid_memmap(void)
 		if (rc < 0)
 			break;
 		str = k;
-		/* A usable region that should not be skipped */
-		if (size == 0)
+
+		if (start == 0) {
+			/* Store the specified memory limit if size > 0 */
+			if (size > 0)
+				mem_limit = size;
+
 			continue;
+		}
 
 		mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].start = start;
 		mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].size = size;
@@ -202,6 +203,57 @@ static void mem_avoid_memmap(void)
 		memmap_too_large = true;
 }
 
+static int handle_mem_memmap(void)
+{
+	char *args = (char *)get_cmd_line_ptr();
+	size_t len = strlen((char *)args);
+	char *tmp_cmdline;
+	char *param, *val;
+	u64 mem_size;
+
+	if (!strstr(args, "memmap=") && !strstr(args, "mem="))
+		return 0;
+
+	tmp_cmdline = malloc(len + 1);
+	if (!tmp_cmdline )
+		error("Failed to allocate space for tmp_cmdline");
+
+	memcpy(tmp_cmdline, args, len);
+	tmp_cmdline[len] = 0;
+	args = tmp_cmdline;
+
+	/* Chew leading spaces */
+	args = skip_spaces(args);
+
+	while (*args) {
+		args = next_arg(args, &param, &val);
+		/* Stop at -- */
+		if (!val && strcmp(param, "--") == 0) {
+			warn("Only '--' specified in cmdline");
+			free(tmp_cmdline);
+			return -1;
+		}
+
+		if (!strcmp(param, "memmap")) {
+			mem_avoid_memmap(val);
+		} else if (!strcmp(param, "mem")) {
+			char *p = val;
+
+			if (!strcmp(p, "nopentium"))
+				continue;
+			mem_size = memparse(p, &p);
+			if (mem_size == 0) {
+				free(tmp_cmdline);
+				return -EINVAL;
+			}
+			mem_limit = mem_size;
+		}
+	}
+
+	free(tmp_cmdline);
+	return 0;
+}
+
 /*
  * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T).
  * The mem_avoid array is used to store the ranges that need to be avoided
@@ -323,7 +375,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 	/* We don't need to set a mapping for setup_data. */
 
 	/* Mark the memmap regions we need to avoid */
-	mem_avoid_memmap();
+	handle_mem_memmap();
 
 #ifdef CONFIG_X86_VERBOSE_BOOTUP
 	/* Make sure video RAM can be used. */
@@ -432,7 +484,8 @@ static void process_e820_entry(struct boot_e820_entry *entry,
 {
 	struct mem_vector region, overlap;
 	struct slot_area slot_area;
-	unsigned long start_orig;
+	unsigned long start_orig, end;
+	struct boot_e820_entry cur_entry;
 
 	/* Skip non-RAM entries. */
 	if (entry->type != E820_TYPE_RAM)
@@ -446,8 +499,15 @@ static void process_e820_entry(struct boot_e820_entry *entry,
 	if (entry->addr + entry->size < minimum)
 		return;
 
-	region.start = entry->addr;
-	region.size = entry->size;
+	/* Ignore entries above memory limit */
+	end = min(entry->size + entry->addr, mem_limit);
+	if (entry->addr >= end)
+		return;
+	cur_entry.addr = entry->addr;
+	cur_entry.size = end - entry->addr;
+
+	region.start = cur_entry.addr;
+	region.size = cur_entry.size;
 
 	/* Give up if slot area array is full. */
 	while (slot_area_index < MAX_SLOT_AREA) {
@@ -461,7 +521,7 @@ static void process_e820_entry(struct boot_e820_entry *entry,
 		region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);
 
 		/* Did we raise the address above this e820 region? */
-		if (region.start > entry->addr + entry->size)
+		if (region.start > cur_entry.addr + cur_entry.size)
 			return;
 
 		/* Reduce size by any delta from the original address. */
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 5457b02fc050..630e3664906b 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -122,6 +122,14 @@ unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int bas
 	return result;
 }
 
+long simple_strtol(const char *cp, char **endp, unsigned int base)
+{
+	if (*cp == '-')
+		return -simple_strtoull(cp + 1, endp, base);
+
+	return simple_strtoull(cp, endp, base);
+}
+
 /**
  * strlen - Find the length of a string
  * @s: The string to be sized
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 580b60f5ac83..637feed9a594 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1750,6 +1750,8 @@ ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event)
 	return ret;
 }
 
+static struct attribute_group x86_pmu_attr_group;
+
 static int __init init_hw_perf_events(void)
 {
 	struct x86_pmu_quirk *quirk;
@@ -1813,6 +1815,14 @@ static int __init init_hw_perf_events(void)
 			x86_pmu_events_group.attrs = tmp;
 	}
 
+	if (x86_pmu.attrs) {
+		struct attribute **tmp;
+
+		tmp = merge_attr(x86_pmu_attr_group.attrs, x86_pmu.attrs);
+		if (!WARN_ON(!tmp))
+			x86_pmu_attr_group.attrs = tmp;
+	}
+
 	pr_info("... version:                %d\n",     x86_pmu.version);
 	pr_info("... bit width:              %d\n",     x86_pmu.cntval_bits);
 	pr_info("... generic registers:      %d\n",     x86_pmu.num_counters);
@@ -2224,7 +2234,6 @@ void perf_check_microcode(void)
 	if (x86_pmu.check_microcode)
 		x86_pmu.check_microcode();
 }
-EXPORT_SYMBOL_GPL(perf_check_microcode);
 
 static struct pmu pmu = {
 	.pmu_enable		= x86_pmu_enable,
@@ -2255,7 +2264,7 @@ static struct pmu pmu = {
 void arch_perf_update_userpage(struct perf_event *event,
 			       struct perf_event_mmap_page *userpg, u64 now)
 {
-	struct cyc2ns_data *data;
+	struct cyc2ns_data data;
 	u64 offset;
 
 	userpg->cap_user_time = 0;
@@ -2267,17 +2276,17 @@ void arch_perf_update_userpage(struct perf_event *event,
 	if (!using_native_sched_clock() || !sched_clock_stable())
 		return;
 
-	data = cyc2ns_read_begin();
+	cyc2ns_read_begin(&data);
 
-	offset = data->cyc2ns_offset + __sched_clock_offset;
+	offset = data.cyc2ns_offset + __sched_clock_offset;
 
 	/*
 	 * Internal timekeeping for enabled/running/stopped times
 	 * is always in the local_clock domain.
 	 */
 	userpg->cap_user_time = 1;
-	userpg->time_mult = data->cyc2ns_mul;
-	userpg->time_shift = data->cyc2ns_shift;
+	userpg->time_mult = data.cyc2ns_mul;
+	userpg->time_shift = data.cyc2ns_shift;
 	userpg->time_offset = offset - now;
 
 	/*
@@ -2289,7 +2298,7 @@ void arch_perf_update_userpage(struct perf_event *event,
 		userpg->time_zero = offset;
 	}
 
-	cyc2ns_read_end(data);
+	cyc2ns_read_end();
 }
 
 void
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a6d91d4e37a1..de26a370176f 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3160,6 +3160,19 @@ err:
 	return -ENOMEM;
 }
 
+static void flip_smm_bit(void *data)
+{
+	unsigned long set = *(unsigned long *)data;
+
+	if (set > 0) {
+		msr_set_bit(MSR_IA32_DEBUGCTLMSR,
+			    DEBUGCTLMSR_FREEZE_IN_SMM_BIT);
+	} else {
+		msr_clear_bit(MSR_IA32_DEBUGCTLMSR,
+			      DEBUGCTLMSR_FREEZE_IN_SMM_BIT);
+	}
+}
+
 static void intel_pmu_cpu_starting(int cpu)
 {
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
@@ -3174,6 +3187,8 @@ static void intel_pmu_cpu_starting(int cpu)
 
 	cpuc->lbr_sel = NULL;
 
+	flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
+
 	if (!cpuc->shared_regs)
 		return;
 
@@ -3410,12 +3425,10 @@ static void intel_snb_check_microcode(void)
 	int pebs_broken = 0;
 	int cpu;
 
-	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		if ((pebs_broken = intel_snb_pebs_broken(cpu)))
 			break;
 	}
-	put_online_cpus();
 
 	if (pebs_broken == x86_pmu.pebs_broken)
 		return;
@@ -3488,7 +3501,9 @@ static bool check_msr(unsigned long msr, u64 mask)
 static __init void intel_sandybridge_quirk(void)
 {
 	x86_pmu.check_microcode = intel_snb_check_microcode;
+	cpus_read_lock();
 	intel_snb_check_microcode();
+	cpus_read_unlock();
 }
 
 static const struct { int id; char *name; } intel_arch_events_map[] __initconst = {
@@ -3595,6 +3610,52 @@ static struct attribute *hsw_events_attrs[] = {
 	NULL
 };
 
+static ssize_t freeze_on_smi_show(struct device *cdev,
+				  struct device_attribute *attr,
+				  char *buf)
+{
+	return sprintf(buf, "%lu\n", x86_pmu.attr_freeze_on_smi);
+}
+
+static DEFINE_MUTEX(freeze_on_smi_mutex);
+
+static ssize_t freeze_on_smi_store(struct device *cdev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t count)
+{
+	unsigned long val;
+	ssize_t ret;
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (val > 1)
+		return -EINVAL;
+
+	mutex_lock(&freeze_on_smi_mutex);
+
+	if (x86_pmu.attr_freeze_on_smi == val)
+		goto done;
+
+	x86_pmu.attr_freeze_on_smi = val;
+
+	get_online_cpus();
+	on_each_cpu(flip_smm_bit, &val, 1);
+	put_online_cpus();
+done:
+	mutex_unlock(&freeze_on_smi_mutex);
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(freeze_on_smi);
+
+static struct attribute *intel_pmu_attrs[] = {
+	&dev_attr_freeze_on_smi.attr,
+	NULL,
+};
+
 __init int intel_pmu_init(void)
 {
 	union cpuid10_edx edx;
@@ -3641,6 +3702,8 @@ __init int intel_pmu_init(void)
 
 	x86_pmu.max_pebs_events		= min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters);
 
+
+	x86_pmu.attrs			= intel_pmu_attrs;
 	/*
 	 * Quirk: v2 perfmon does not report fixed-purpose events, so
 	 * assume at least 3 events, when not running in a hypervisor:
@@ -4112,13 +4175,12 @@ static __init int fixup_ht_bug(void)
 
 	lockup_detector_resume();
 
-	get_online_cpus();
+	cpus_read_lock();
 
-	for_each_online_cpu(c) {
+	for_each_online_cpu(c)
 		free_excl_cntrs(c);
-	}
 
-	put_online_cpus();
+	cpus_read_unlock();
 	pr_info("PMU erratum BJ122, BV98, HSD29 workaround disabled, HT off\n");
 	return 0;
 }
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 8c00dc09a5d2..2521f771f2f5 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -1682,7 +1682,7 @@ static int __init intel_cqm_init(void)
 	 *
 	 * Also, check that the scales match on all cpus.
 	 */
-	get_online_cpus();
+	cpus_read_lock();
 	for_each_online_cpu(cpu) {
 		struct cpuinfo_x86 *c = &cpu_data(cpu);
 
@@ -1746,14 +1746,14 @@ static int __init intel_cqm_init(void)
 	 * Setup the hot cpu notifier once we are sure cqm
 	 * is enabled to avoid notifier leak.
 	 */
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_STARTING,
-			  "perf/x86/cqm:starting",
-			  intel_cqm_cpu_starting, NULL);
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "perf/x86/cqm:online",
-			  NULL, intel_cqm_cpu_exit);
-
+	cpuhp_setup_state_cpuslocked(CPUHP_AP_PERF_X86_CQM_STARTING,
+				     "perf/x86/cqm:starting",
+				     intel_cqm_cpu_starting, NULL);
+	cpuhp_setup_state_cpuslocked(CPUHP_AP_PERF_X86_CQM_ONLINE,
+				     "perf/x86/cqm:online",
+				     NULL, intel_cqm_cpu_exit);
 out:
-	put_online_cpus();
+	cpus_read_unlock();
 
 	if (ret) {
 		kfree(str);
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index be3d36254040..53728eea1bed 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -562,6 +562,9 @@ struct x86_pmu {
 	ssize_t		(*events_sysfs_show)(char *page, u64 config);
 	struct attribute **cpu_events;
 
+	unsigned long	attr_freeze_on_smi;
+	struct attribute **attrs;
+
 	/*
 	 * CPU Hotplug hooks
 	 */
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 00c88a01301d..da181ad1d5f8 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -3,6 +3,7 @@
 
 #include <linux/ioport.h>
 #include <linux/pci.h>
+#include <linux/refcount.h>
 
 struct amd_nb_bus_dev_range {
 	u8 bus;
@@ -55,7 +56,7 @@ struct threshold_bank {
 	struct threshold_block	*blocks;
 
 	/* initialized to the number of CPUs on the node sharing this bank */
-	atomic_t		cpus;
+	refcount_t		cpus;
 };
 
 struct amd_northbridge {
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index d8638e2419cc..d406894cd9a2 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -137,6 +137,8 @@
 #define DEBUGCTLMSR_BTS_OFF_OS		(1UL <<  9)
 #define DEBUGCTLMSR_BTS_OFF_USR		(1UL << 10)
 #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI	(1UL << 11)
+#define DEBUGCTLMSR_FREEZE_IN_SMM_BIT	14
+#define DEBUGCTLMSR_FREEZE_IN_SMM	(1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT)
 
 #define MSR_PEBS_FRONTEND		0x000003f7
 
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index 27e9f9d769b8..2016962103df 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -29,11 +29,9 @@ struct cyc2ns_data {
 	u32 cyc2ns_mul;
 	u32 cyc2ns_shift;
 	u64 cyc2ns_offset;
-	u32 __count;
-	/* u32 hole */
-}; /* 24 bytes -- do not grow */
+}; /* 16 bytes */
 
-extern struct cyc2ns_data *cyc2ns_read_begin(void);
-extern void cyc2ns_read_end(struct cyc2ns_data *);
+extern void cyc2ns_read_begin(struct cyc2ns_data *);
+extern void cyc2ns_read_end(void);
 
 #endif /* _ASM_X86_TIMER_H */
diff --git a/arch/x86/include/asm/tlbbatch.h b/arch/x86/include/asm/tlbbatch.h
new file mode 100644
index 000000000000..01a6de16fb96
--- /dev/null
+++ b/arch/x86/include/asm/tlbbatch.h
@@ -0,0 +1,16 @@
+#ifndef _ARCH_X86_TLBBATCH_H
+#define _ARCH_X86_TLBBATCH_H
+
+#include <linux/cpumask.h>
+
+#ifdef CONFIG_SMP
+struct arch_tlbflush_unmap_batch {
+	/*
+	 * Each bit set is a CPU that potentially has a TLB entry for one of
+	 * the PFNs being flushed..
+	 */
+	struct cpumask cpumask;
+};
+#endif
+
+#endif /* _ARCH_X86_TLBBATCH_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6ed9ea469b48..8f6e2f87511b 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -307,11 +307,15 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 		flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags)
 
 extern void flush_tlb_all(void);
-extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
 extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				unsigned long end, unsigned long vmflag);
 extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
+static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
+{
+	flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, VM_NONE);
+}
+
 void native_flush_tlb_others(const struct cpumask *cpumask,
 				struct mm_struct *mm,
 				unsigned long start, unsigned long end);
@@ -325,6 +329,14 @@ static inline void reset_lazy_tlbstate(void)
 	this_cpu_write(cpu_tlbstate.active_mm, &init_mm);
 }
 
+static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
+					struct mm_struct *mm)
+{
+	cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
+}
+
+extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
+
 #endif	/* SMP */
 
 #ifndef CONFIG_PARAVIRT
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 347bb9f65737..247880fc29f9 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1200,28 +1200,6 @@ EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
 
 static struct irq_chip ioapic_chip, ioapic_ir_chip;
 
-#ifdef CONFIG_X86_32
-static inline int IO_APIC_irq_trigger(int irq)
-{
-	int apic, idx, pin;
-
-	for_each_ioapic_pin(apic, pin) {
-		idx = find_irq_entry(apic, pin, mp_INT);
-		if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin, 0)))
-			return irq_trigger(idx);
-	}
-	/*
-         * nonexistent IRQs are edge default
-         */
-	return 0;
-}
-#else
-static inline int IO_APIC_irq_trigger(int irq)
-{
-	return 1;
-}
-#endif
-
 static void __init setup_IO_APIC_irqs(void)
 {
 	unsigned int ioapic, pin;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 6e4a047e4b68..d00f299f2ada 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -164,17 +164,48 @@ static void default_deferred_error_interrupt(void)
 }
 void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt;
 
-static void get_smca_bank_info(unsigned int bank)
+static void smca_configure(unsigned int bank, unsigned int cpu)
 {
-	unsigned int i, hwid_mcatype, cpu = smp_processor_id();
+	unsigned int i, hwid_mcatype;
 	struct smca_hwid *s_hwid;
-	u32 high, instance_id;
+	u32 high, low;
+	u32 smca_config = MSR_AMD64_SMCA_MCx_CONFIG(bank);
+
+	/* Set appropriate bits in MCA_CONFIG */
+	if (!rdmsr_safe(smca_config, &low, &high)) {
+		/*
+		 * OS is required to set the MCAX bit to acknowledge that it is
+		 * now using the new MSR ranges and new registers under each
+		 * bank. It also means that the OS will configure deferred
+		 * errors in the new MCx_CONFIG register. If the bit is not set,
+		 * uncorrectable errors will cause a system panic.
+		 *
+		 * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.)
+		 */
+		high |= BIT(0);
+
+		/*
+		 * SMCA sets the Deferred Error Interrupt type per bank.
+		 *
+		 * MCA_CONFIG[DeferredIntTypeSupported] is bit 5, and tells us
+		 * if the DeferredIntType bit field is available.
+		 *
+		 * MCA_CONFIG[DeferredIntType] is bits [38:37] ([6:5] in the
+		 * high portion of the MSR). OS should set this to 0x1 to enable
+		 * APIC based interrupt. First, check that no interrupt has been
+		 * set.
+		 */
+		if ((low & BIT(5)) && !((high >> 5) & 0x3))
+			high |= BIT(5);
+
+		wrmsr(smca_config, low, high);
+	}
 
 	/* Collect bank_info using CPU 0 for now. */
 	if (cpu)
 		return;
 
-	if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &instance_id, &high)) {
+	if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) {
 		pr_warn("Failed to read MCA_IPID for bank %d\n", bank);
 		return;
 	}
@@ -191,7 +222,7 @@ static void get_smca_bank_info(unsigned int bank)
 			     smca_get_name(s_hwid->bank_type));
 
 			smca_banks[bank].hwid = s_hwid;
-			smca_banks[bank].id = instance_id;
+			smca_banks[bank].id = low;
 			smca_banks[bank].sysfs_id = s_hwid->count++;
 			break;
 		}
@@ -433,7 +464,7 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
 			int offset, u32 misc_high)
 {
 	unsigned int cpu = smp_processor_id();
-	u32 smca_low, smca_high, smca_addr;
+	u32 smca_low, smca_high;
 	struct threshold_block b;
 	int new;
 
@@ -457,51 +488,6 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
 		goto set_offset;
 	}
 
-	smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank);
-
-	if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) {
-		/*
-		 * OS is required to set the MCAX bit to acknowledge that it is
-		 * now using the new MSR ranges and new registers under each
-		 * bank. It also means that the OS will configure deferred
-		 * errors in the new MCx_CONFIG register. If the bit is not set,
-		 * uncorrectable errors will cause a system panic.
-		 *
-		 * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.)
-		 */
-		smca_high |= BIT(0);
-
-		/*
-		 * SMCA logs Deferred Error information in MCA_DE{STAT,ADDR}
-		 * registers with the option of additionally logging to
-		 * MCA_{STATUS,ADDR} if MCA_CONFIG[LogDeferredInMcaStat] is set.
-		 *
-		 * This bit is usually set by BIOS to retain the old behavior
-		 * for OSes that don't use the new registers. Linux supports the
-		 * new registers so let's disable that additional logging here.
-		 *
-		 * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in the high
-		 * portion of the MSR).
-		 */
-		smca_high &= ~BIT(2);
-
-		/*
-		 * SMCA sets the Deferred Error Interrupt type per bank.
-		 *
-		 * MCA_CONFIG[DeferredIntTypeSupported] is bit 5, and tells us
-		 * if the DeferredIntType bit field is available.
-		 *
-		 * MCA_CONFIG[DeferredIntType] is bits [38:37] ([6:5] in the
-		 * high portion of the MSR). OS should set this to 0x1 to enable
-		 * APIC based interrupt. First, check that no interrupt has been
-		 * set.
-		 */
-		if ((smca_low & BIT(5)) && !((smca_high >> 5) & 0x3))
-			smca_high |= BIT(5);
-
-		wrmsr(smca_addr, smca_low, smca_high);
-	}
-
 	/* Gather LVT offset for thresholding: */
 	if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high))
 		goto out;
@@ -530,7 +516,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
 		if (mce_flags.smca)
-			get_smca_bank_info(bank);
+			smca_configure(bank, cpu);
 
 		for (block = 0; block < NR_BLOCKS; ++block) {
 			address = get_block_address(cpu, address, low, high, bank, block);
@@ -755,37 +741,19 @@ out_err:
 }
 EXPORT_SYMBOL_GPL(umc_normaddr_to_sysaddr);
 
-static void
-__log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc)
+static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
 {
-	u32 msr_status = msr_ops.status(bank);
-	u32 msr_addr = msr_ops.addr(bank);
 	struct mce m;
-	u64 status;
-
-	WARN_ON_ONCE(deferred_err && threshold_err);
-
-	if (deferred_err && mce_flags.smca) {
-		msr_status = MSR_AMD64_SMCA_MCx_DESTAT(bank);
-		msr_addr = MSR_AMD64_SMCA_MCx_DEADDR(bank);
-	}
-
-	rdmsrl(msr_status, status);
-
-	if (!(status & MCI_STATUS_VAL))
-		return;
 
 	mce_setup(&m);
 
 	m.status = status;
+	m.misc   = misc;
 	m.bank   = bank;
 	m.tsc	 = rdtsc();
 
-	if (threshold_err)
-		m.misc = misc;
-
 	if (m.status & MCI_STATUS_ADDRV) {
-		rdmsrl(msr_addr, m.addr);
+		m.addr = addr;
 
 		/*
 		 * Extract [55:<lsb>] where lsb is the least significant
@@ -806,8 +774,6 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc)
 	}
 
 	mce_log(&m);
-
-	wrmsrl(msr_status, 0);
 }
 
 static inline void __smp_deferred_error_interrupt(void)
@@ -832,45 +798,85 @@ asmlinkage __visible void __irq_entry smp_trace_deferred_error_interrupt(void)
 	exiting_ack_irq();
 }
 
-/* APIC interrupt handler for deferred errors */
-static void amd_deferred_error_interrupt(void)
+/*
+ * Returns true if the logged error is deferred. False, otherwise.
+ */
+static inline bool
+_log_error_bank(unsigned int bank, u32 msr_stat, u32 msr_addr, u64 misc)
 {
-	unsigned int bank;
-	u32 msr_status;
-	u64 status;
+	u64 status, addr = 0;
 
-	for (bank = 0; bank < mca_cfg.banks; ++bank) {
-		msr_status = (mce_flags.smca) ? MSR_AMD64_SMCA_MCx_DESTAT(bank)
-					      : msr_ops.status(bank);
+	rdmsrl(msr_stat, status);
+	if (!(status & MCI_STATUS_VAL))
+		return false;
 
-		rdmsrl(msr_status, status);
+	if (status & MCI_STATUS_ADDRV)
+		rdmsrl(msr_addr, addr);
 
-		if (!(status & MCI_STATUS_VAL) ||
-		    !(status & MCI_STATUS_DEFERRED))
-			continue;
+	__log_error(bank, status, addr, misc);
 
-		__log_error(bank, true, false, 0);
-		break;
-	}
+	wrmsrl(status, 0);
+
+	return status & MCI_STATUS_DEFERRED;
 }
 
 /*
- * APIC Interrupt Handler
+ * We have three scenarios for checking for Deferred errors:
+ *
+ * 1) Non-SMCA systems check MCA_STATUS and log error if found.
+ * 2) SMCA systems check MCA_STATUS. If error is found then log it and also
+ *    clear MCA_DESTAT.
+ * 3) SMCA systems check MCA_DESTAT, if error was not found in MCA_STATUS, and
+ *    log it.
  */
+static void log_error_deferred(unsigned int bank)
+{
+	bool defrd;
+
+	defrd = _log_error_bank(bank, msr_ops.status(bank),
+					msr_ops.addr(bank), 0);
+
+	if (!mce_flags.smca)
+		return;
+
+	/* Clear MCA_DESTAT if we logged the deferred error from MCA_STATUS. */
+	if (defrd) {
+		wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0);
+		return;
+	}
+
+	/*
+	 * Only deferred errors are logged in MCA_DE{STAT,ADDR} so just check
+	 * for a valid error.
+	 */
+	_log_error_bank(bank, MSR_AMD64_SMCA_MCx_DESTAT(bank),
+			      MSR_AMD64_SMCA_MCx_DEADDR(bank), 0);
+}
+
+/* APIC interrupt handler for deferred errors */
+static void amd_deferred_error_interrupt(void)
+{
+	unsigned int bank;
+
+	for (bank = 0; bank < mca_cfg.banks; ++bank)
+		log_error_deferred(bank);
+}
+
+static void log_error_thresholding(unsigned int bank, u64 misc)
+{
+	_log_error_bank(bank, msr_ops.status(bank), msr_ops.addr(bank), misc);
+}
 
 /*
- * threshold interrupt handler will service THRESHOLD_APIC_VECTOR.
- * the interrupt goes off when error_count reaches threshold_limit.
- * the handler will simply log mcelog w/ software defined bank number.
+ * Threshold interrupt handler will service THRESHOLD_APIC_VECTOR. The interrupt
+ * goes off when error_count reaches threshold_limit.
  */
-
 static void amd_threshold_interrupt(void)
 {
 	u32 low = 0, high = 0, address = 0;
 	unsigned int bank, block, cpu = smp_processor_id();
 	struct thresh_restart tr;
 
-	/* assume first bank caused it */
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
@@ -893,23 +899,18 @@ static void amd_threshold_interrupt(void)
 			     (high & MASK_LOCKED_HI))
 				continue;
 
-			/*
-			 * Log the machine check that caused the threshold
-			 * event.
-			 */
-			if (high & MASK_OVERFLOW_HI)
-				goto log;
-		}
-	}
-	return;
+			if (!(high & MASK_OVERFLOW_HI))
+				continue;
 
-log:
-	__log_error(bank, false, true, ((u64)high << 32) | low);
+			/* Log the MCE which caused the threshold event. */
+			log_error_thresholding(bank, ((u64)high << 32) | low);
 
-	/* Reset threshold block after logging error. */
-	memset(&tr, 0, sizeof(tr));
-	tr.b = &per_cpu(threshold_banks, cpu)[bank]->blocks[block];
-	threshold_restart_bank(&tr);
+			/* Reset threshold block after logging error. */
+			memset(&tr, 0, sizeof(tr));
+			tr.b = &per_cpu(threshold_banks, cpu)[bank]->blocks[block];
+			threshold_restart_bank(&tr);
+		}
+	}
 }
 
 /*
@@ -1202,7 +1203,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 				goto out;
 
 			per_cpu(threshold_banks, cpu)[bank] = b;
-			atomic_inc(&b->cpus);
+			refcount_inc(&b->cpus);
 
 			err = __threshold_add_blocks(b);
 
@@ -1225,7 +1226,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 	per_cpu(threshold_banks, cpu)[bank] = b;
 
 	if (is_shared_bank(bank)) {
-		atomic_set(&b->cpus, 1);
+		refcount_set(&b->cpus, 1);
 
 		/* nb is already initialized, see above */
 		if (nb) {
@@ -1289,7 +1290,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank)
 		goto free_out;
 
 	if (is_shared_bank(bank)) {
-		if (!atomic_dec_and_test(&b->cpus)) {
+		if (!refcount_dec_and_test(&b->cpus)) {
 			__threshold_remove_blocks(b);
 			per_cpu(threshold_banks, cpu)[bank] = NULL;
 			return;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 45db4d2ebd01..e9f4d762aa5b 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -320,7 +320,7 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax)
 }
 
 static enum ucode_state
-load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size);
+load_microcode_amd(bool save, u8 family, const u8 *data, size_t size);
 
 int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 {
@@ -338,8 +338,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 	if (!desc.mc)
 		return -EINVAL;
 
-	ret = load_microcode_amd(smp_processor_id(), x86_family(cpuid_1_eax),
-				 desc.data, desc.size);
+	ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size);
 	if (ret != UCODE_OK)
 		return -EINVAL;
 
@@ -675,7 +674,7 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
 }
 
 static enum ucode_state
-load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size)
+load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
 {
 	enum ucode_state ret;
 
@@ -689,8 +688,8 @@ load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size)
 
 #ifdef CONFIG_X86_32
 	/* save BSP's matching patch for early load */
-	if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) {
-		struct ucode_patch *p = find_patch(cpu);
+	if (save) {
+		struct ucode_patch *p = find_patch(0);
 		if (p) {
 			memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
 			memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
@@ -722,11 +721,12 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 {
 	char fw_name[36] = "amd-ucode/microcode_amd.bin";
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
 	enum ucode_state ret = UCODE_NFOUND;
 	const struct firmware *fw;
 
 	/* reload ucode container only on the boot cpu */
-	if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index)
+	if (!refresh_fw || !bsp)
 		return UCODE_OK;
 
 	if (c->x86 >= 0x15)
@@ -743,7 +743,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 		goto fw_release;
 	}
 
-	ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size);
+	ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size);
 
  fw_release:
 	release_firmware(fw);
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 2bce84d91c2b..c5bb63be4ba1 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -807,10 +807,8 @@ void mtrr_save_state(void)
 	if (!mtrr_enabled())
 		return;
 
-	get_online_cpus();
 	first_cpu = cpumask_first(cpu_online_mask);
 	smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1);
-	put_online_cpus();
 }
 
 void set_mtrr_aps_delayed_init(void)
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index c37bd0f39c70..ab4f491da2a9 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -105,11 +105,9 @@ static void __jump_label_transform(struct jump_entry *entry,
 void arch_jump_label_transform(struct jump_entry *entry,
 			       enum jump_label_type type)
 {
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 	__jump_label_transform(entry, type, NULL, 0);
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 static enum {
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index ff40e74c9181..ffeae818aa7a 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -78,7 +78,7 @@ void __show_regs(struct pt_regs *regs, int all)
 
 	printk(KERN_DEFAULT "EIP: %pS\n", (void *)regs->ip);
 	printk(KERN_DEFAULT "EFLAGS: %08lx CPU: %d\n", regs->flags,
-		smp_processor_id());
+		raw_smp_processor_id());
 
 	printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
 		regs->ax, regs->bx, regs->cx, regs->dx);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f04479a8f74f..045e4f993bd2 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -863,7 +863,7 @@ static void announce_cpu(int cpu, int apicid)
 	if (cpu == 1)
 		printk(KERN_INFO "x86: Booting SMP configuration:\n");
 
-	if (system_state == SYSTEM_BOOTING) {
+	if (system_state < SYSTEM_RUNNING) {
 		if (node != current_node) {
 			if (current_node > (-1))
 				pr_cont("\n");
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 714dfba6a1e7..5270fc0c2df6 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -51,115 +51,34 @@ static u32 art_to_tsc_denominator;
 static u64 art_to_tsc_offset;
 struct clocksource *art_related_clocksource;
 
-/*
- * Use a ring-buffer like data structure, where a writer advances the head by
- * writing a new data entry and a reader advances the tail when it observes a
- * new entry.
- *
- * Writers are made to wait on readers until there's space to write a new
- * entry.
- *
- * This means that we can always use an {offset, mul} pair to compute a ns
- * value that is 'roughly' in the right direction, even if we're writing a new
- * {offset, mul} pair during the clock read.
- *
- * The down-side is that we can no longer guarantee strict monotonicity anymore
- * (assuming the TSC was that to begin with), because while we compute the
- * intersection point of the two clock slopes and make sure the time is
- * continuous at the point of switching; we can no longer guarantee a reader is
- * strictly before or after the switch point.
- *
- * It does mean a reader no longer needs to disable IRQs in order to avoid
- * CPU-Freq updates messing with his times, and similarly an NMI reader will
- * no longer run the risk of hitting half-written state.
- */
-
 struct cyc2ns {
-	struct cyc2ns_data data[2];	/*  0 + 2*24 = 48 */
-	struct cyc2ns_data *head;	/* 48 + 8    = 56 */
-	struct cyc2ns_data *tail;	/* 56 + 8    = 64 */
-}; /* exactly fits one cacheline */
-
-static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns);
-
-struct cyc2ns_data *cyc2ns_read_begin(void)
-{
-	struct cyc2ns_data *head;
-
-	preempt_disable();
-
-	head = this_cpu_read(cyc2ns.head);
-	/*
-	 * Ensure we observe the entry when we observe the pointer to it.
-	 * matches the wmb from cyc2ns_write_end().
-	 */
-	smp_read_barrier_depends();
-	head->__count++;
-	barrier();
+	struct cyc2ns_data data[2];	/*  0 + 2*16 = 32 */
+	seqcount_t	   seq;		/* 32 + 4    = 36 */
 
-	return head;
-}
+}; /* fits one cacheline */
 
-void cyc2ns_read_end(struct cyc2ns_data *head)
-{
-	barrier();
-	/*
-	 * If we're the outer most nested read; update the tail pointer
-	 * when we're done. This notifies possible pending writers
-	 * that we've observed the head pointer and that the other
-	 * entry is now free.
-	 */
-	if (!--head->__count) {
-		/*
-		 * x86-TSO does not reorder writes with older reads;
-		 * therefore once this write becomes visible to another
-		 * cpu, we must be finished reading the cyc2ns_data.
-		 *
-		 * matches with cyc2ns_write_begin().
-		 */
-		this_cpu_write(cyc2ns.tail, head);
-	}
-	preempt_enable();
-}
+static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns);
 
-/*
- * Begin writing a new @data entry for @cpu.
- *
- * Assumes some sort of write side lock; currently 'provided' by the assumption
- * that cpufreq will call its notifiers sequentially.
- */
-static struct cyc2ns_data *cyc2ns_write_begin(int cpu)
+void cyc2ns_read_begin(struct cyc2ns_data *data)
 {
-	struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
-	struct cyc2ns_data *data = c2n->data;
+	int seq, idx;
 
-	if (data == c2n->head)
-		data++;
+	preempt_disable_notrace();
 
-	/* XXX send an IPI to @cpu in order to guarantee a read? */
+	do {
+		seq = this_cpu_read(cyc2ns.seq.sequence);
+		idx = seq & 1;
 
-	/*
-	 * When we observe the tail write from cyc2ns_read_end(),
-	 * the cpu must be done with that entry and its safe
-	 * to start writing to it.
-	 */
-	while (c2n->tail == data)
-		cpu_relax();
+		data->cyc2ns_offset = this_cpu_read(cyc2ns.data[idx].cyc2ns_offset);
+		data->cyc2ns_mul    = this_cpu_read(cyc2ns.data[idx].cyc2ns_mul);
+		data->cyc2ns_shift  = this_cpu_read(cyc2ns.data[idx].cyc2ns_shift);
 
-	return data;
+	} while (unlikely(seq != this_cpu_read(cyc2ns.seq.sequence)));
 }
 
-static void cyc2ns_write_end(int cpu, struct cyc2ns_data *data)
+void cyc2ns_read_end(void)
 {
-	struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
-
-	/*
-	 * Ensure the @data writes are visible before we publish the
-	 * entry. Matches the data-depencency in cyc2ns_read_begin().
-	 */
-	smp_wmb();
-
-	ACCESS_ONCE(c2n->head) = data;
+	preempt_enable_notrace();
 }
 
 /*
@@ -191,7 +110,6 @@ static void cyc2ns_data_init(struct cyc2ns_data *data)
 	data->cyc2ns_mul = 0;
 	data->cyc2ns_shift = 0;
 	data->cyc2ns_offset = 0;
-	data->__count = 0;
 }
 
 static void cyc2ns_init(int cpu)
@@ -201,51 +119,29 @@ static void cyc2ns_init(int cpu)
 	cyc2ns_data_init(&c2n->data[0]);
 	cyc2ns_data_init(&c2n->data[1]);
 
-	c2n->head = c2n->data;
-	c2n->tail = c2n->data;
+	seqcount_init(&c2n->seq);
 }
 
 static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 {
-	struct cyc2ns_data *data, *tail;
+	struct cyc2ns_data data;
 	unsigned long long ns;
 
-	/*
-	 * See cyc2ns_read_*() for details; replicated in order to avoid
-	 * an extra few instructions that came with the abstraction.
-	 * Notable, it allows us to only do the __count and tail update
-	 * dance when its actually needed.
-	 */
-
-	preempt_disable_notrace();
-	data = this_cpu_read(cyc2ns.head);
-	tail = this_cpu_read(cyc2ns.tail);
-
-	if (likely(data == tail)) {
-		ns = data->cyc2ns_offset;
-		ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift);
-	} else {
-		data->__count++;
-
-		barrier();
-
-		ns = data->cyc2ns_offset;
-		ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift);
+	cyc2ns_read_begin(&data);
 
-		barrier();
+	ns = data.cyc2ns_offset;
+	ns += mul_u64_u32_shr(cyc, data.cyc2ns_mul, data.cyc2ns_shift);
 
-		if (!--data->__count)
-			this_cpu_write(cyc2ns.tail, data);
-	}
-	preempt_enable_notrace();
+	cyc2ns_read_end();
 
 	return ns;
 }
 
-static void set_cyc2ns_scale(unsigned long khz, int cpu)
+static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
 {
-	unsigned long long tsc_now, ns_now;
-	struct cyc2ns_data *data;
+	unsigned long long ns_now;
+	struct cyc2ns_data data;
+	struct cyc2ns *c2n;
 	unsigned long flags;
 
 	local_irq_save(flags);
@@ -254,9 +150,6 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu)
 	if (!khz)
 		goto done;
 
-	data = cyc2ns_write_begin(cpu);
-
-	tsc_now = rdtsc();
 	ns_now = cycles_2_ns(tsc_now);
 
 	/*
@@ -264,7 +157,7 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu)
 	 * time function is continuous; see the comment near struct
 	 * cyc2ns_data.
 	 */
-	clocks_calc_mult_shift(&data->cyc2ns_mul, &data->cyc2ns_shift, khz,
+	clocks_calc_mult_shift(&data.cyc2ns_mul, &data.cyc2ns_shift, khz,
 			       NSEC_PER_MSEC, 0);
 
 	/*
@@ -273,20 +166,26 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu)
 	 * conversion algorithm shifting a 32-bit value (now specifies a 64-bit
 	 * value) - refer perf_event_mmap_page documentation in perf_event.h.
 	 */
-	if (data->cyc2ns_shift == 32) {
-		data->cyc2ns_shift = 31;
-		data->cyc2ns_mul >>= 1;
+	if (data.cyc2ns_shift == 32) {
+		data.cyc2ns_shift = 31;
+		data.cyc2ns_mul >>= 1;
 	}
 
-	data->cyc2ns_offset = ns_now -
-		mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, data->cyc2ns_shift);
+	data.cyc2ns_offset = ns_now -
+		mul_u64_u32_shr(tsc_now, data.cyc2ns_mul, data.cyc2ns_shift);
+
+	c2n = per_cpu_ptr(&cyc2ns, cpu);
 
-	cyc2ns_write_end(cpu, data);
+	raw_write_seqcount_latch(&c2n->seq);
+	c2n->data[0] = data;
+	raw_write_seqcount_latch(&c2n->seq);
+	c2n->data[1] = data;
 
 done:
-	sched_clock_idle_wakeup_event(0);
+	sched_clock_idle_wakeup_event();
 	local_irq_restore(flags);
 }
+
 /*
  * Scheduler clock - returns current time in nanosec units.
  */
@@ -374,6 +273,8 @@ static int __init tsc_setup(char *str)
 		tsc_clocksource_reliable = 1;
 	if (!strncmp(str, "noirqtime", 9))
 		no_sched_irq_time = 1;
+	if (!strcmp(str, "unstable"))
+		mark_tsc_unstable("boot parameter");
 	return 1;
 }
 
@@ -986,7 +887,6 @@ void tsc_restore_sched_clock_state(void)
 }
 
 #ifdef CONFIG_CPU_FREQ
-
 /* Frequency scaling support. Adjust the TSC based timer when the cpu frequency
  * changes.
  *
@@ -1027,7 +927,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 		if (!(freq->flags & CPUFREQ_CONST_LOOPS))
 			mark_tsc_unstable("cpufreq changes");
 
-		set_cyc2ns_scale(tsc_khz, freq->cpu);
+		set_cyc2ns_scale(tsc_khz, freq->cpu, rdtsc());
 	}
 
 	return 0;
@@ -1127,6 +1027,15 @@ static void tsc_cs_mark_unstable(struct clocksource *cs)
 	pr_info("Marking TSC unstable due to clocksource watchdog\n");
 }
 
+static void tsc_cs_tick_stable(struct clocksource *cs)
+{
+	if (tsc_unstable)
+		return;
+
+	if (using_native_sched_clock())
+		sched_clock_tick_stable();
+}
+
 /*
  * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc()
  */
@@ -1140,6 +1049,7 @@ static struct clocksource clocksource_tsc = {
 	.archdata               = { .vclock_mode = VCLOCK_TSC },
 	.resume			= tsc_resume,
 	.mark_unstable		= tsc_cs_mark_unstable,
+	.tick_stable		= tsc_cs_tick_stable,
 };
 
 void mark_tsc_unstable(char *reason)
@@ -1255,6 +1165,7 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 	static int hpet;
 	u64 tsc_stop, ref_stop, delta;
 	unsigned long freq;
+	int cpu;
 
 	/* Don't bother refining TSC on unstable systems */
 	if (check_tsc_unstable())
@@ -1305,6 +1216,10 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 	/* Inform the TSC deadline clockevent devices about the recalibration */
 	lapic_update_tsc_freq();
 
+	/* Update the sched_clock() rate to match the clocksource one */
+	for_each_possible_cpu(cpu)
+		set_cyc2ns_scale(tsc_khz, cpu, tsc_stop);
+
 out:
 	if (boot_cpu_has(X86_FEATURE_ART))
 		art_related_clocksource = &clocksource_tsc;
@@ -1350,7 +1265,7 @@ device_initcall(init_tsc_clocksource);
 
 void __init tsc_init(void)
 {
-	u64 lpj;
+	u64 lpj, cyc;
 	int cpu;
 
 	if (!boot_cpu_has(X86_FEATURE_TSC)) {
@@ -1390,9 +1305,10 @@ void __init tsc_init(void)
 	 * speed as the bootup CPU. (cpufreq notifiers will fix this
 	 * up if their speed diverges)
 	 */
+	cyc = rdtsc();
 	for_each_possible_cpu(cpu) {
 		cyc2ns_init(cpu);
-		set_cyc2ns_scale(tsc_khz, cpu);
+		set_cyc2ns_scale(tsc_khz, cpu, cyc);
 	}
 
 	if (tsc_disabled > 0)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6e7bedf69af7..743e4c6b4529 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -237,24 +237,26 @@ static void flush_tlb_func(void *info)
 		return;
 
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
-	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
-		if (f->flush_end == TLB_FLUSH_ALL) {
-			local_flush_tlb();
-			trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, TLB_FLUSH_ALL);
-		} else {
-			unsigned long addr;
-			unsigned long nr_pages =
-				(f->flush_end - f->flush_start) / PAGE_SIZE;
-			addr = f->flush_start;
-			while (addr < f->flush_end) {
-				__flush_tlb_single(addr);
-				addr += PAGE_SIZE;
-			}
-			trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, nr_pages);
-		}
-	} else
+
+	if (this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK) {
 		leave_mm(smp_processor_id());
+		return;
+	}
 
+	if (f->flush_end == TLB_FLUSH_ALL) {
+		local_flush_tlb();
+		trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, TLB_FLUSH_ALL);
+	} else {
+		unsigned long addr;
+		unsigned long nr_pages =
+			(f->flush_end - f->flush_start) / PAGE_SIZE;
+		addr = f->flush_start;
+		while (addr < f->flush_end) {
+			__flush_tlb_single(addr);
+			addr += PAGE_SIZE;
+		}
+		trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, nr_pages);
+	}
 }
 
 void native_flush_tlb_others(const struct cpumask *cpumask,
@@ -354,33 +356,6 @@ out:
 	preempt_enable();
 }
 
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
-{
-	struct mm_struct *mm = vma->vm_mm;
-
-	preempt_disable();
-
-	if (current->active_mm == mm) {
-		if (current->mm) {
-			/*
-			 * Implicit full barrier (INVLPG) that synchronizes
-			 * with switch_mm.
-			 */
-			__flush_tlb_one(start);
-		} else {
-			leave_mm(smp_processor_id());
-
-			/* Synchronize with switch_mm. */
-			smp_mb();
-		}
-	}
-
-	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE);
-
-	preempt_enable();
-}
-
 static void do_flush_tlb_all(void *info)
 {
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
@@ -420,6 +395,23 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 	}
 }
 
+void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
+{
+	int cpu = get_cpu();
+
+	if (cpumask_test_cpu(cpu, &batch->cpumask)) {
+		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
+		local_flush_tlb();
+		trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL);
+	}
+
+	if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids)
+		flush_tlb_others(&batch->cpumask, NULL, 0, TLB_FLUSH_ALL);
+	cpumask_clear(&batch->cpumask);
+
+	put_cpu();
+}
+
 static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf,
 			     size_t count, loff_t *ppos)
 {
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 7e76a4d8304b..43b96f5f78ba 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -828,9 +828,11 @@ static void __init kexec_enter_virtual_mode(void)
 
 	/*
 	 * We don't do virtual mode, since we don't do runtime services, on
-	 * non-native EFI
+	 * non-native EFI. With efi=old_map, we don't do runtime services in
+	 * kexec kernel because in the initial boot something else might
+	 * have been mapped at these virtual addresses.
 	 */
-	if (!efi_is_native()) {
+	if (!efi_is_native() || efi_enabled(EFI_OLD_MEMMAP)) {
 		efi_memmap_unmap();
 		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 		return;
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index c488625c9712..eb8dff15a7f6 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -71,11 +71,13 @@ static void __init early_code_mapping_set_exec(int executable)
 
 pgd_t * __init efi_call_phys_prolog(void)
 {
-	unsigned long vaddress;
-	pgd_t *save_pgd;
+	unsigned long vaddr, addr_pgd, addr_p4d, addr_pud;
+	pgd_t *save_pgd, *pgd_k, *pgd_efi;
+	p4d_t *p4d, *p4d_k, *p4d_efi;
+	pud_t *pud;
 
 	int pgd;
-	int n_pgds;
+	int n_pgds, i, j;
 
 	if (!efi_enabled(EFI_OLD_MEMMAP)) {
 		save_pgd = (pgd_t *)read_cr3();
@@ -88,10 +90,49 @@ pgd_t * __init efi_call_phys_prolog(void)
 	n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
 	save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL);
 
+	/*
+	 * Build 1:1 identity mapping for efi=old_map usage. Note that
+	 * PAGE_OFFSET is PGDIR_SIZE aligned when KASLR is disabled, while
+	 * it is PUD_SIZE ALIGNED with KASLR enabled. So for a given physical
+	 * address X, the pud_index(X) != pud_index(__va(X)), we can only copy
+	 * PUD entry of __va(X) to fill in pud entry of X to build 1:1 mapping.
+	 * This means here we can only reuse the PMD tables of the direct mapping.
+	 */
 	for (pgd = 0; pgd < n_pgds; pgd++) {
-		save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
-		vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
-		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
+		addr_pgd = (unsigned long)(pgd * PGDIR_SIZE);
+		vaddr = (unsigned long)__va(pgd * PGDIR_SIZE);
+		pgd_efi = pgd_offset_k(addr_pgd);
+		save_pgd[pgd] = *pgd_efi;
+
+		p4d = p4d_alloc(&init_mm, pgd_efi, addr_pgd);
+		if (!p4d) {
+			pr_err("Failed to allocate p4d table!\n");
+			goto out;
+		}
+
+		for (i = 0; i < PTRS_PER_P4D; i++) {
+			addr_p4d = addr_pgd + i * P4D_SIZE;
+			p4d_efi = p4d + p4d_index(addr_p4d);
+
+			pud = pud_alloc(&init_mm, p4d_efi, addr_p4d);
+			if (!pud) {
+				pr_err("Failed to allocate pud table!\n");
+				goto out;
+			}
+
+			for (j = 0; j < PTRS_PER_PUD; j++) {
+				addr_pud = addr_p4d + j * PUD_SIZE;
+
+				if (addr_pud > (max_pfn << PAGE_SHIFT))
+					break;
+
+				vaddr = (unsigned long)__va(addr_pud);
+
+				pgd_k = pgd_offset_k(vaddr);
+				p4d_k = p4d_offset(pgd_k, vaddr);
+				pud[j] = *pud_offset(p4d_k, vaddr);
+			}
+		}
 	}
 out:
 	__flush_tlb_all();
@@ -104,8 +145,11 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 	/*
 	 * After the lock is released, the original page table is restored.
 	 */
-	int pgd_idx;
+	int pgd_idx, i;
 	int nr_pgds;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
 
 	if (!efi_enabled(EFI_OLD_MEMMAP)) {
 		write_cr3((unsigned long)save_pgd);
@@ -115,9 +159,28 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 
 	nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
 
-	for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++)
+	for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) {
+		pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE);
 		set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]);
 
+		if (!(pgd_val(*pgd) & _PAGE_PRESENT))
+			continue;
+
+		for (i = 0; i < PTRS_PER_P4D; i++) {
+			p4d = p4d_offset(pgd,
+					 pgd_idx * PGDIR_SIZE + i * P4D_SIZE);
+
+			if (!(p4d_val(*p4d) & _PAGE_PRESENT))
+				continue;
+
+			pud = (pud_t *)p4d_page_vaddr(*p4d);
+			pud_free(&init_mm, pud);
+		}
+
+		p4d = (p4d_t *)pgd_page_vaddr(*pgd);
+		p4d_free(&init_mm, p4d);
+	}
+
 	kfree(save_pgd);
 
 	__flush_tlb_all();
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 26615991d69c..e0cf95a83f3f 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -360,6 +360,9 @@ void __init efi_free_boot_services(void)
 		free_bootmem_late(start, size);
 	}
 
+	if (!num_entries)
+		return;
+
 	new_size = efi.memmap.desc_size * num_entries;
 	new_phys = efi_memmap_alloc(num_entries);
 	if (!new_phys) {
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 42e65fee5673..795671593528 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -456,12 +456,13 @@ static void reset_with_ipi(struct pnmask *distribution, struct bau_control *bcp)
  */
 static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 {
-	struct cyc2ns_data *data = cyc2ns_read_begin();
+	struct cyc2ns_data data;
 	unsigned long long ns;
 
-	ns = mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift);
+	cyc2ns_read_begin(&data);
+	ns = mul_u64_u32_shr(cyc, data.cyc2ns_mul, data.cyc2ns_shift);
+	cyc2ns_read_end();
 
-	cyc2ns_read_end(data);
 	return ns;
 }
 
@@ -470,12 +471,13 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
  */
 static inline unsigned long long ns_2_cycles(unsigned long long ns)
 {
-	struct cyc2ns_data *data = cyc2ns_read_begin();
+	struct cyc2ns_data data;
 	unsigned long long cyc;
 
-	cyc = (ns << data->cyc2ns_shift) / data->cyc2ns_mul;
+	cyc2ns_read_begin(&data);
+	cyc = (ns << data.cyc2ns_shift) / data.cyc2ns_mul;
+	cyc2ns_read_end();
 
-	cyc2ns_read_end(data);
 	return cyc;
 }
 
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index d0855c09f32f..d2c8a9286fa8 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -89,14 +89,14 @@ bool ghes_disable;
 module_param_named(disable, ghes_disable, bool, 0);
 
 /*
- * All error sources notified with SCI shares one notifier function,
- * so they need to be linked and checked one by one.  This is applied
- * to NMI too.
+ * All error sources notified with HED (Hardware Error Device) share a
+ * single notifier callback, so they need to be linked and checked one
+ * by one. This holds true for NMI too.
  *
  * RCU is used for these lists, so ghes_list_mutex is only used for
  * list changing, not for traversing.
  */
-static LIST_HEAD(ghes_sci);
+static LIST_HEAD(ghes_hed);
 static DEFINE_MUTEX(ghes_list_mutex);
 
 /*
@@ -702,14 +702,14 @@ static irqreturn_t ghes_irq_func(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int ghes_notify_sci(struct notifier_block *this,
-				  unsigned long event, void *data)
+static int ghes_notify_hed(struct notifier_block *this, unsigned long event,
+			   void *data)
 {
 	struct ghes *ghes;
 	int ret = NOTIFY_DONE;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(ghes, &ghes_sci, list) {
+	list_for_each_entry_rcu(ghes, &ghes_hed, list) {
 		if (!ghes_proc(ghes))
 			ret = NOTIFY_OK;
 	}
@@ -718,8 +718,8 @@ static int ghes_notify_sci(struct notifier_block *this,
 	return ret;
 }
 
-static struct notifier_block ghes_notifier_sci = {
-	.notifier_call = ghes_notify_sci,
+static struct notifier_block ghes_notifier_hed = {
+	.notifier_call = ghes_notify_hed,
 };
 
 #ifdef CONFIG_HAVE_ACPI_APEI_NMI
@@ -966,7 +966,10 @@ static int ghes_probe(struct platform_device *ghes_dev)
 	case ACPI_HEST_NOTIFY_POLLED:
 	case ACPI_HEST_NOTIFY_EXTERNAL:
 	case ACPI_HEST_NOTIFY_SCI:
+	case ACPI_HEST_NOTIFY_GSIV:
+	case ACPI_HEST_NOTIFY_GPIO:
 		break;
+
 	case ACPI_HEST_NOTIFY_NMI:
 		if (!IS_ENABLED(CONFIG_HAVE_ACPI_APEI_NMI)) {
 			pr_warn(GHES_PFX "Generic hardware error source: %d notified via NMI interrupt is not supported!\n",
@@ -1024,13 +1027,17 @@ static int ghes_probe(struct platform_device *ghes_dev)
 			goto err_edac_unreg;
 		}
 		break;
+
 	case ACPI_HEST_NOTIFY_SCI:
+	case ACPI_HEST_NOTIFY_GSIV:
+	case ACPI_HEST_NOTIFY_GPIO:
 		mutex_lock(&ghes_list_mutex);
-		if (list_empty(&ghes_sci))
-			register_acpi_hed_notifier(&ghes_notifier_sci);
-		list_add_rcu(&ghes->list, &ghes_sci);
+		if (list_empty(&ghes_hed))
+			register_acpi_hed_notifier(&ghes_notifier_hed);
+		list_add_rcu(&ghes->list, &ghes_hed);
 		mutex_unlock(&ghes_list_mutex);
 		break;
+
 	case ACPI_HEST_NOTIFY_NMI:
 		ghes_nmi_add(ghes);
 		break;
@@ -1066,14 +1073,18 @@ static int ghes_remove(struct platform_device *ghes_dev)
 	case ACPI_HEST_NOTIFY_EXTERNAL:
 		free_irq(ghes->irq, ghes);
 		break;
+
 	case ACPI_HEST_NOTIFY_SCI:
+	case ACPI_HEST_NOTIFY_GSIV:
+	case ACPI_HEST_NOTIFY_GPIO:
 		mutex_lock(&ghes_list_mutex);
 		list_del_rcu(&ghes->list);
-		if (list_empty(&ghes_sci))
-			unregister_acpi_hed_notifier(&ghes_notifier_sci);
+		if (list_empty(&ghes_hed))
+			unregister_acpi_hed_notifier(&ghes_notifier_hed);
 		mutex_unlock(&ghes_list_mutex);
 		synchronize_rcu();
 		break;
+
 	case ACPI_HEST_NOTIFY_NMI:
 		ghes_nmi_remove(ghes);
 		break;
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 919be0aa2578..240544253ccd 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -523,7 +523,7 @@ static int acpi_pci_root_add(struct acpi_device *device,
 	struct acpi_pci_root *root;
 	acpi_handle handle = device->handle;
 	int no_aspm = 0;
-	bool hotadd = system_state != SYSTEM_BOOTING;
+	bool hotadd = system_state == SYSTEM_RUNNING;
 
 	root = kzalloc(sizeof(struct acpi_pci_root), GFP_KERNEL);
 	if (!root)
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 8697a82bd465..591d1dd3f04e 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -268,9 +268,9 @@ static int acpi_processor_start(struct device *dev)
 		return -ENODEV;
 
 	/* Protect against concurrent CPU hotplug operations */
-	get_online_cpus();
+	cpu_hotplug_disable();
 	ret = __acpi_processor_start(device);
-	put_online_cpus();
+	cpu_hotplug_enable();
 	return ret;
 }
 
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index 3de34633f7f9..7f9aff4b8d62 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -909,6 +909,13 @@ static long __acpi_processor_get_throttling(void *data)
 	return pr->throttling.acpi_processor_get_throttling(pr);
 }
 
+static int call_on_cpu(int cpu, long (*fn)(void *), void *arg, bool direct)
+{
+	if (direct || (is_percpu_thread() && cpu == smp_processor_id()))
+		return fn(arg);
+	return work_on_cpu(cpu, fn, arg);
+}
+
 static int acpi_processor_get_throttling(struct acpi_processor *pr)
 {
 	if (!pr)
@@ -926,7 +933,7 @@ static int acpi_processor_get_throttling(struct acpi_processor *pr)
 	if (!cpu_online(pr->id))
 		return -ENODEV;
 
-	return work_on_cpu(pr->id, __acpi_processor_get_throttling, pr);
+	return call_on_cpu(pr->id, __acpi_processor_get_throttling, pr, false);
 }
 
 static int acpi_processor_get_fadt_info(struct acpi_processor *pr)
@@ -1076,13 +1083,6 @@ static long acpi_processor_throttling_fn(void *data)
 			arg->target_state, arg->force);
 }
 
-static int call_on_cpu(int cpu, long (*fn)(void *), void *arg, bool direct)
-{
-	if (direct)
-		return fn(arg);
-	return work_on_cpu(cpu, fn, arg);
-}
-
 static int __acpi_processor_set_throttling(struct acpi_processor *pr,
 					   int state, bool force, bool direct)
 {
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 5548f9686016..0440d95c9b5b 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -377,7 +377,7 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
 	if (!pfn_valid_within(pfn))
 		return -1;
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-	if (system_state == SYSTEM_BOOTING)
+	if (system_state < SYSTEM_RUNNING)
 		return early_pfn_to_nid(pfn);
 #endif
 	page = pfn_to_page(pfn);
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index 31adbebf812e..2af70014ee5a 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -539,15 +539,6 @@ config HANGCHECK_TIMER
 	  out to lunch past a certain margin.  It can reboot the system
 	  or merely print a warning.
 
-config MMTIMER
-	tristate "MMTIMER Memory mapped RTC for SGI Altix"
-	depends on IA64_GENERIC || IA64_SGI_SN2
-	depends on POSIX_TIMERS
-	default y
-	help
-	  The mmtimer device allows direct userspace access to the
-	  Altix system timer.
-
 config UV_MMTIMER
 	tristate "UV_MMTIMER Memory mapped RTC for SGI UV"
 	depends on X86_UV
diff --git a/drivers/char/Makefile b/drivers/char/Makefile
index 6e6c244a66a0..53e33720818c 100644
--- a/drivers/char/Makefile
+++ b/drivers/char/Makefile
@@ -10,7 +10,6 @@ obj-$(CONFIG_VIRTIO_CONSOLE)	+= virtio_console.o
 obj-$(CONFIG_RAW_DRIVER)	+= raw.o
 obj-$(CONFIG_SGI_SNSC)		+= snsc.o snsc_event.o
 obj-$(CONFIG_MSPEC)		+= mspec.o
-obj-$(CONFIG_MMTIMER)		+= mmtimer.o
 obj-$(CONFIG_UV_MMTIMER)	+= uv_mmtimer.o
 obj-$(CONFIG_IBM_BSR)		+= bsr.o
 obj-$(CONFIG_SGI_MBCS)		+= mbcs.o
diff --git a/drivers/char/mmtimer.c b/drivers/char/mmtimer.c
deleted file mode 100644
index 0e7fcb04f01e..000000000000
--- a/drivers/char/mmtimer.c
+++ /dev/null
@@ -1,858 +0,0 @@
-/*
- * Timer device implementation for SGI SN platforms.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (c) 2001-2006 Silicon Graphics, Inc.  All rights reserved.
- *
- * This driver exports an API that should be supportable by any HPET or IA-PC
- * multimedia timer.  The code below is currently specific to the SGI Altix
- * SHub RTC, however.
- *
- * 11/01/01 - jbarnes - initial revision
- * 9/10/04 - Christoph Lameter - remove interrupt support for kernel inclusion
- * 10/1/04 - Christoph Lameter - provide posix clock CLOCK_SGI_CYCLE
- * 10/13/04 - Christoph Lameter, Dimitri Sivanich - provide timer interrupt
- *		support via the posix timer interface
- */
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/ioctl.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/errno.h>
-#include <linux/mm.h>
-#include <linux/fs.h>
-#include <linux/mmtimer.h>
-#include <linux/miscdevice.h>
-#include <linux/posix-timers.h>
-#include <linux/interrupt.h>
-#include <linux/time.h>
-#include <linux/math64.h>
-#include <linux/mutex.h>
-#include <linux/slab.h>
-
-#include <linux/uaccess.h>
-#include <asm/sn/addrs.h>
-#include <asm/sn/intr.h>
-#include <asm/sn/shub_mmr.h>
-#include <asm/sn/nodepda.h>
-#include <asm/sn/shubio.h>
-
-MODULE_AUTHOR("Jesse Barnes <jbarnes@sgi.com>");
-MODULE_DESCRIPTION("SGI Altix RTC Timer");
-MODULE_LICENSE("GPL");
-
-/* name of the device, usually in /dev */
-#define MMTIMER_NAME "mmtimer"
-#define MMTIMER_DESC "SGI Altix RTC Timer"
-#define MMTIMER_VERSION "2.1"
-
-#define RTC_BITS 55 /* 55 bits for this implementation */
-
-static struct k_clock sgi_clock;
-
-extern unsigned long sn_rtc_cycles_per_second;
-
-#define RTC_COUNTER_ADDR        ((long *)LOCAL_MMR_ADDR(SH_RTC))
-
-#define rtc_time()              (*RTC_COUNTER_ADDR)
-
-static DEFINE_MUTEX(mmtimer_mutex);
-static long mmtimer_ioctl(struct file *file, unsigned int cmd,
-						unsigned long arg);
-static int mmtimer_mmap(struct file *file, struct vm_area_struct *vma);
-
-/*
- * Period in femtoseconds (10^-15 s)
- */
-static unsigned long mmtimer_femtoperiod = 0;
-
-static const struct file_operations mmtimer_fops = {
-	.owner = THIS_MODULE,
-	.mmap =	mmtimer_mmap,
-	.unlocked_ioctl = mmtimer_ioctl,
-	.llseek = noop_llseek,
-};
-
-/*
- * We only have comparison registers RTC1-4 currently available per
- * node.  RTC0 is used by SAL.
- */
-/* Check for an RTC interrupt pending */
-static int mmtimer_int_pending(int comparator)
-{
-	if (HUB_L((unsigned long *)LOCAL_MMR_ADDR(SH_EVENT_OCCURRED)) &
-			SH_EVENT_OCCURRED_RTC1_INT_MASK << comparator)
-		return 1;
-	else
-		return 0;
-}
-
-/* Clear the RTC interrupt pending bit */
-static void mmtimer_clr_int_pending(int comparator)
-{
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_EVENT_OCCURRED_ALIAS),
-		SH_EVENT_OCCURRED_RTC1_INT_MASK << comparator);
-}
-
-/* Setup timer on comparator RTC1 */
-static void mmtimer_setup_int_0(int cpu, u64 expires)
-{
-	u64 val;
-
-	/* Disable interrupt */
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC1_INT_ENABLE), 0UL);
-
-	/* Initialize comparator value */
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPB), -1L);
-
-	/* Clear pending bit */
-	mmtimer_clr_int_pending(0);
-
-	val = ((u64)SGI_MMTIMER_VECTOR << SH_RTC1_INT_CONFIG_IDX_SHFT) |
-		((u64)cpu_physical_id(cpu) <<
-			SH_RTC1_INT_CONFIG_PID_SHFT);
-
-	/* Set configuration */
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC1_INT_CONFIG), val);
-
-	/* Enable RTC interrupts */
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC1_INT_ENABLE), 1UL);
-
-	/* Initialize comparator value */
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPB), expires);
-
-
-}
-
-/* Setup timer on comparator RTC2 */
-static void mmtimer_setup_int_1(int cpu, u64 expires)
-{
-	u64 val;
-
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC2_INT_ENABLE), 0UL);
-
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPC), -1L);
-
-	mmtimer_clr_int_pending(1);
-
-	val = ((u64)SGI_MMTIMER_VECTOR << SH_RTC2_INT_CONFIG_IDX_SHFT) |
-		((u64)cpu_physical_id(cpu) <<
-			SH_RTC2_INT_CONFIG_PID_SHFT);
-
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC2_INT_CONFIG), val);
-
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC2_INT_ENABLE), 1UL);
-
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPC), expires);
-}
-
-/* Setup timer on comparator RTC3 */
-static void mmtimer_setup_int_2(int cpu, u64 expires)
-{
-	u64 val;
-
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC3_INT_ENABLE), 0UL);
-
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPD), -1L);
-
-	mmtimer_clr_int_pending(2);
-
-	val = ((u64)SGI_MMTIMER_VECTOR << SH_RTC3_INT_CONFIG_IDX_SHFT) |
-		((u64)cpu_physical_id(cpu) <<
-			SH_RTC3_INT_CONFIG_PID_SHFT);
-
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC3_INT_CONFIG), val);
-
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC3_INT_ENABLE), 1UL);
-
-	HUB_S((u64 *)LOCAL_MMR_ADDR(SH_INT_CMPD), expires);
-}
-
-/*
- * This function must be called with interrupts disabled and preemption off
- * in order to insure that the setup succeeds in a deterministic time frame.
- * It will check if the interrupt setup succeeded.
- */
-static int mmtimer_setup(int cpu, int comparator, unsigned long expires,
-	u64 *set_completion_time)
-{
-	switch (comparator) {
-	case 0:
-		mmtimer_setup_int_0(cpu, expires);
-		break;
-	case 1:
-		mmtimer_setup_int_1(cpu, expires);
-		break;
-	case 2:
-		mmtimer_setup_int_2(cpu, expires);
-		break;
-	}
-	/* We might've missed our expiration time */
-	*set_completion_time = rtc_time();
-	if (*set_completion_time <= expires)
-		return 1;
-
-	/*
-	 * If an interrupt is already pending then its okay
-	 * if not then we failed
-	 */
-	return mmtimer_int_pending(comparator);
-}
-
-static int mmtimer_disable_int(long nasid, int comparator)
-{
-	switch (comparator) {
-	case 0:
-		nasid == -1 ? HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC1_INT_ENABLE),
-			0UL) : REMOTE_HUB_S(nasid, SH_RTC1_INT_ENABLE, 0UL);
-		break;
-	case 1:
-		nasid == -1 ? HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC2_INT_ENABLE),
-			0UL) : REMOTE_HUB_S(nasid, SH_RTC2_INT_ENABLE, 0UL);
-		break;
-	case 2:
-		nasid == -1 ? HUB_S((u64 *)LOCAL_MMR_ADDR(SH_RTC3_INT_ENABLE),
-			0UL) : REMOTE_HUB_S(nasid, SH_RTC3_INT_ENABLE, 0UL);
-		break;
-	default:
-		return -EFAULT;
-	}
-	return 0;
-}
-
-#define COMPARATOR	1		/* The comparator to use */
-
-#define TIMER_OFF	0xbadcabLL	/* Timer is not setup */
-#define TIMER_SET	0		/* Comparator is set for this timer */
-
-#define MMTIMER_INTERVAL_RETRY_INCREMENT_DEFAULT 40
-
-/* There is one of these for each timer */
-struct mmtimer {
-	struct rb_node list;
-	struct k_itimer *timer;
-	int cpu;
-};
-
-struct mmtimer_node {
-	spinlock_t lock ____cacheline_aligned;
-	struct rb_root timer_head;
-	struct rb_node *next;
-	struct tasklet_struct tasklet;
-};
-static struct mmtimer_node *timers;
-
-static unsigned mmtimer_interval_retry_increment =
-	MMTIMER_INTERVAL_RETRY_INCREMENT_DEFAULT;
-module_param(mmtimer_interval_retry_increment, uint, 0644);
-MODULE_PARM_DESC(mmtimer_interval_retry_increment,
-	"RTC ticks to add to expiration on interval retry (default 40)");
-
-/*
- * Add a new mmtimer struct to the node's mmtimer list.
- * This function assumes the struct mmtimer_node is locked.
- */
-static void mmtimer_add_list(struct mmtimer *n)
-{
-	int nodeid = n->timer->it.mmtimer.node;
-	unsigned long expires = n->timer->it.mmtimer.expires;
-	struct rb_node **link = &timers[nodeid].timer_head.rb_node;
-	struct rb_node *parent = NULL;
-	struct mmtimer *x;
-
-	/*
-	 * Find the right place in the rbtree:
-	 */
-	while (*link) {
-		parent = *link;
-		x = rb_entry(parent, struct mmtimer, list);
-
-		if (expires < x->timer->it.mmtimer.expires)
-			link = &(*link)->rb_left;
-		else
-			link = &(*link)->rb_right;
-	}
-
-	/*
-	 * Insert the timer to the rbtree and check whether it
-	 * replaces the first pending timer
-	 */
-	rb_link_node(&n->list, parent, link);
-	rb_insert_color(&n->list, &timers[nodeid].timer_head);
-
-	if (!timers[nodeid].next || expires < rb_entry(timers[nodeid].next,
-			struct mmtimer, list)->timer->it.mmtimer.expires)
-		timers[nodeid].next = &n->list;
-}
-
-/*
- * Set the comparator for the next timer.
- * This function assumes the struct mmtimer_node is locked.
- */
-static void mmtimer_set_next_timer(int nodeid)
-{
-	struct mmtimer_node *n = &timers[nodeid];
-	struct mmtimer *x;
-	struct k_itimer *t;
-	u64 expires, exp, set_completion_time;
-	int i;
-
-restart:
-	if (n->next == NULL)
-		return;
-
-	x = rb_entry(n->next, struct mmtimer, list);
-	t = x->timer;
-	if (!t->it.mmtimer.incr) {
-		/* Not an interval timer */
-		if (!mmtimer_setup(x->cpu, COMPARATOR,
-					t->it.mmtimer.expires,
-					&set_completion_time)) {
-			/* Late setup, fire now */
-			tasklet_schedule(&n->tasklet);
-		}
-		return;
-	}
-
-	/* Interval timer */
-	i = 0;
-	expires = exp = t->it.mmtimer.expires;
-	while (!mmtimer_setup(x->cpu, COMPARATOR, expires,
-				&set_completion_time)) {
-		int to;
-
-		i++;
-		expires = set_completion_time +
-				mmtimer_interval_retry_increment + (1 << i);
-		/* Calculate overruns as we go. */
-		to = ((u64)(expires - exp) / t->it.mmtimer.incr);
-		if (to) {
-			t->it_overrun += to;
-			t->it.mmtimer.expires += t->it.mmtimer.incr * to;
-			exp = t->it.mmtimer.expires;
-		}
-		if (i > 20) {
-			printk(KERN_ALERT "mmtimer: cannot reschedule timer\n");
-			t->it.mmtimer.clock = TIMER_OFF;
-			n->next = rb_next(&x->list);
-			rb_erase(&x->list, &n->timer_head);
-			kfree(x);
-			goto restart;
-		}
-	}
-}
-
-/**
- * mmtimer_ioctl - ioctl interface for /dev/mmtimer
- * @file: file structure for the device
- * @cmd: command to execute
- * @arg: optional argument to command
- *
- * Executes the command specified by @cmd.  Returns 0 for success, < 0 for
- * failure.
- *
- * Valid commands:
- *
- * %MMTIMER_GETOFFSET - Should return the offset (relative to the start
- * of the page where the registers are mapped) for the counter in question.
- *
- * %MMTIMER_GETRES - Returns the resolution of the clock in femto (10^-15)
- * seconds
- *
- * %MMTIMER_GETFREQ - Copies the frequency of the clock in Hz to the address
- * specified by @arg
- *
- * %MMTIMER_GETBITS - Returns the number of bits in the clock's counter
- *
- * %MMTIMER_MMAPAVAIL - Returns 1 if the registers can be mmap'd into userspace
- *
- * %MMTIMER_GETCOUNTER - Gets the current value in the counter and places it
- * in the address specified by @arg.
- */
-static long mmtimer_ioctl(struct file *file, unsigned int cmd,
-						unsigned long arg)
-{
-	int ret = 0;
-
-	mutex_lock(&mmtimer_mutex);
-
-	switch (cmd) {
-	case MMTIMER_GETOFFSET:	/* offset of the counter */
-		/*
-		 * SN RTC registers are on their own 64k page
-		 */
-		if(PAGE_SIZE <= (1 << 16))
-			ret = (((long)RTC_COUNTER_ADDR) & (PAGE_SIZE-1)) / 8;
-		else
-			ret = -ENOSYS;
-		break;
-
-	case MMTIMER_GETRES: /* resolution of the clock in 10^-15 s */
-		if(copy_to_user((unsigned long __user *)arg,
-				&mmtimer_femtoperiod, sizeof(unsigned long)))
-			ret = -EFAULT;
-		break;
-
-	case MMTIMER_GETFREQ: /* frequency in Hz */
-		if(copy_to_user((unsigned long __user *)arg,
-				&sn_rtc_cycles_per_second,
-				sizeof(unsigned long)))
-			ret = -EFAULT;
-		break;
-
-	case MMTIMER_GETBITS: /* number of bits in the clock */
-		ret = RTC_BITS;
-		break;
-
-	case MMTIMER_MMAPAVAIL: /* can we mmap the clock into userspace? */
-		ret = (PAGE_SIZE <= (1 << 16)) ? 1 : 0;
-		break;
-
-	case MMTIMER_GETCOUNTER:
-		if(copy_to_user((unsigned long __user *)arg,
-				RTC_COUNTER_ADDR, sizeof(unsigned long)))
-			ret = -EFAULT;
-		break;
-	default:
-		ret = -ENOTTY;
-		break;
-	}
-	mutex_unlock(&mmtimer_mutex);
-	return ret;
-}
-
-/**
- * mmtimer_mmap - maps the clock's registers into userspace
- * @file: file structure for the device
- * @vma: VMA to map the registers into
- *
- * Calls remap_pfn_range() to map the clock's registers into
- * the calling process' address space.
- */
-static int mmtimer_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	unsigned long mmtimer_addr;
-
-	if (vma->vm_end - vma->vm_start != PAGE_SIZE)
-		return -EINVAL;
-
-	if (vma->vm_flags & VM_WRITE)
-		return -EPERM;
-
-	if (PAGE_SIZE > (1 << 16))
-		return -ENOSYS;
-
-	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-
-	mmtimer_addr = __pa(RTC_COUNTER_ADDR);
-	mmtimer_addr &= ~(PAGE_SIZE - 1);
-	mmtimer_addr &= 0xfffffffffffffffUL;
-
-	if (remap_pfn_range(vma, vma->vm_start, mmtimer_addr >> PAGE_SHIFT,
-					PAGE_SIZE, vma->vm_page_prot)) {
-		printk(KERN_ERR "remap_pfn_range failed in mmtimer.c\n");
-		return -EAGAIN;
-	}
-
-	return 0;
-}
-
-static struct miscdevice mmtimer_miscdev = {
-	.minor = SGI_MMTIMER,
-	.name = MMTIMER_NAME,
-	.fops = &mmtimer_fops
-};
-
-static struct timespec sgi_clock_offset;
-static int sgi_clock_period;
-
-/*
- * Posix Timer Interface
- */
-
-static struct timespec sgi_clock_offset;
-static int sgi_clock_period;
-
-static int sgi_clock_get(clockid_t clockid, struct timespec64 *tp)
-{
-	u64 nsec;
-
-	nsec = rtc_time() * sgi_clock_period
-			+ sgi_clock_offset.tv_nsec;
-	*tp = ns_to_timespec64(nsec);
-	tp->tv_sec += sgi_clock_offset.tv_sec;
-	return 0;
-};
-
-static int sgi_clock_set(const clockid_t clockid, const struct timespec64 *tp)
-{
-
-	u64 nsec;
-	u32 rem;
-
-	nsec = rtc_time() * sgi_clock_period;
-
-	sgi_clock_offset.tv_sec = tp->tv_sec - div_u64_rem(nsec, NSEC_PER_SEC, &rem);
-
-	if (rem <= tp->tv_nsec)
-		sgi_clock_offset.tv_nsec = tp->tv_sec - rem;
-	else {
-		sgi_clock_offset.tv_nsec = tp->tv_sec + NSEC_PER_SEC - rem;
-		sgi_clock_offset.tv_sec--;
-	}
-	return 0;
-}
-
-/**
- * mmtimer_interrupt - timer interrupt handler
- * @irq: irq received
- * @dev_id: device the irq came from
- *
- * Called when one of the comarators matches the counter, This
- * routine will send signals to processes that have requested
- * them.
- *
- * This interrupt is run in an interrupt context
- * by the SHUB. It is therefore safe to locally access SHub
- * registers.
- */
-static irqreturn_t
-mmtimer_interrupt(int irq, void *dev_id)
-{
-	unsigned long expires = 0;
-	int result = IRQ_NONE;
-	unsigned indx = cpu_to_node(smp_processor_id());
-	struct mmtimer *base;
-
-	spin_lock(&timers[indx].lock);
-	base = rb_entry(timers[indx].next, struct mmtimer, list);
-	if (base == NULL) {
-		spin_unlock(&timers[indx].lock);
-		return result;
-	}
-
-	if (base->cpu == smp_processor_id()) {
-		if (base->timer)
-			expires = base->timer->it.mmtimer.expires;
-		/* expires test won't work with shared irqs */
-		if ((mmtimer_int_pending(COMPARATOR) > 0) ||
-			(expires && (expires <= rtc_time()))) {
-			mmtimer_clr_int_pending(COMPARATOR);
-			tasklet_schedule(&timers[indx].tasklet);
-			result = IRQ_HANDLED;
-		}
-	}
-	spin_unlock(&timers[indx].lock);
-	return result;
-}
-
-static void mmtimer_tasklet(unsigned long data)
-{
-	int nodeid = data;
-	struct mmtimer_node *mn = &timers[nodeid];
-	struct mmtimer *x;
-	struct k_itimer *t;
-	unsigned long flags;
-
-	/* Send signal and deal with periodic signals */
-	spin_lock_irqsave(&mn->lock, flags);
-	if (!mn->next)
-		goto out;
-
-	x = rb_entry(mn->next, struct mmtimer, list);
-	t = x->timer;
-
-	if (t->it.mmtimer.clock == TIMER_OFF)
-		goto out;
-
-	t->it_overrun = 0;
-
-	mn->next = rb_next(&x->list);
-	rb_erase(&x->list, &mn->timer_head);
-
-	if (posix_timer_event(t, 0) != 0)
-		t->it_overrun++;
-
-	if(t->it.mmtimer.incr) {
-		t->it.mmtimer.expires += t->it.mmtimer.incr;
-		mmtimer_add_list(x);
-	} else {
-		/* Ensure we don't false trigger in mmtimer_interrupt */
-		t->it.mmtimer.clock = TIMER_OFF;
-		t->it.mmtimer.expires = 0;
-		kfree(x);
-	}
-	/* Set comparator for next timer, if there is one */
-	mmtimer_set_next_timer(nodeid);
-
-	t->it_overrun_last = t->it_overrun;
-out:
-	spin_unlock_irqrestore(&mn->lock, flags);
-}
-
-static int sgi_timer_create(struct k_itimer *timer)
-{
-	/* Insure that a newly created timer is off */
-	timer->it.mmtimer.clock = TIMER_OFF;
-	return 0;
-}
-
-/* This does not really delete a timer. It just insures
- * that the timer is not active
- *
- * Assumption: it_lock is already held with irq's disabled
- */
-static int sgi_timer_del(struct k_itimer *timr)
-{
-	cnodeid_t nodeid = timr->it.mmtimer.node;
-	unsigned long irqflags;
-
-	spin_lock_irqsave(&timers[nodeid].lock, irqflags);
-	if (timr->it.mmtimer.clock != TIMER_OFF) {
-		unsigned long expires = timr->it.mmtimer.expires;
-		struct rb_node *n = timers[nodeid].timer_head.rb_node;
-		struct mmtimer *uninitialized_var(t);
-		int r = 0;
-
-		timr->it.mmtimer.clock = TIMER_OFF;
-		timr->it.mmtimer.expires = 0;
-
-		while (n) {
-			t = rb_entry(n, struct mmtimer, list);
-			if (t->timer == timr)
-				break;
-
-			if (expires < t->timer->it.mmtimer.expires)
-				n = n->rb_left;
-			else
-				n = n->rb_right;
-		}
-
-		if (!n) {
-			spin_unlock_irqrestore(&timers[nodeid].lock, irqflags);
-			return 0;
-		}
-
-		if (timers[nodeid].next == n) {
-			timers[nodeid].next = rb_next(n);
-			r = 1;
-		}
-
-		rb_erase(n, &timers[nodeid].timer_head);
-		kfree(t);
-
-		if (r) {
-			mmtimer_disable_int(cnodeid_to_nasid(nodeid),
-				COMPARATOR);
-			mmtimer_set_next_timer(nodeid);
-		}
-	}
-	spin_unlock_irqrestore(&timers[nodeid].lock, irqflags);
-	return 0;
-}
-
-/* Assumption: it_lock is already held with irq's disabled */
-static void sgi_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting)
-{
-
-	if (timr->it.mmtimer.clock == TIMER_OFF) {
-		cur_setting->it_interval.tv_nsec = 0;
-		cur_setting->it_interval.tv_sec = 0;
-		cur_setting->it_value.tv_nsec = 0;
-		cur_setting->it_value.tv_sec =0;
-		return;
-	}
-
-	cur_setting->it_interval = ns_to_timespec64(timr->it.mmtimer.incr * sgi_clock_period);
-	cur_setting->it_value = ns_to_timespec64((timr->it.mmtimer.expires - rtc_time()) * sgi_clock_period);
-}
-
-
-static int sgi_timer_set(struct k_itimer *timr, int flags,
-	struct itimerspec64 *new_setting,
-	struct itimerspec64 *old_setting)
-{
-	unsigned long when, period, irqflags;
-	int err = 0;
-	cnodeid_t nodeid;
-	struct mmtimer *base;
-	struct rb_node *n;
-
-	if (old_setting)
-		sgi_timer_get(timr, old_setting);
-
-	sgi_timer_del(timr);
-	when = timespec64_to_ns(&new_setting->it_value);
-	period = timespec64_to_ns(&new_setting->it_interval);
-
-	if (when == 0)
-		/* Clear timer */
-		return 0;
-
-	base = kmalloc(sizeof(struct mmtimer), GFP_KERNEL);
-	if (base == NULL)
-		return -ENOMEM;
-
-	if (flags & TIMER_ABSTIME) {
-		struct timespec64 n;
-		unsigned long now;
-
-		getnstimeofday64(&n);
-		now = timespec64_to_ns(&n);
-		if (when > now)
-			when -= now;
-		else
-			/* Fire the timer immediately */
-			when = 0;
-	}
-
-	/*
-	 * Convert to sgi clock period. Need to keep rtc_time() as near as possible
-	 * to getnstimeofday() in order to be as faithful as possible to the time
-	 * specified.
-	 */
-	when = (when + sgi_clock_period - 1) / sgi_clock_period + rtc_time();
-	period = (period + sgi_clock_period - 1)  / sgi_clock_period;
-
-	/*
-	 * We are allocating a local SHub comparator. If we would be moved to another
-	 * cpu then another SHub may be local to us. Prohibit that by switching off
-	 * preemption.
-	 */
-	preempt_disable();
-
-	nodeid =  cpu_to_node(smp_processor_id());
-
-	/* Lock the node timer structure */
-	spin_lock_irqsave(&timers[nodeid].lock, irqflags);
-
-	base->timer = timr;
-	base->cpu = smp_processor_id();
-
-	timr->it.mmtimer.clock = TIMER_SET;
-	timr->it.mmtimer.node = nodeid;
-	timr->it.mmtimer.incr = period;
-	timr->it.mmtimer.expires = when;
-
-	n = timers[nodeid].next;
-
-	/* Add the new struct mmtimer to node's timer list */
-	mmtimer_add_list(base);
-
-	if (timers[nodeid].next == n) {
-		/* No need to reprogram comparator for now */
-		spin_unlock_irqrestore(&timers[nodeid].lock, irqflags);
-		preempt_enable();
-		return err;
-	}
-
-	/* We need to reprogram the comparator */
-	if (n)
-		mmtimer_disable_int(cnodeid_to_nasid(nodeid), COMPARATOR);
-
-	mmtimer_set_next_timer(nodeid);
-
-	/* Unlock the node timer structure */
-	spin_unlock_irqrestore(&timers[nodeid].lock, irqflags);
-
-	preempt_enable();
-
-	return err;
-}
-
-static int sgi_clock_getres(const clockid_t which_clock, struct timespec64 *tp)
-{
-	tp->tv_sec = 0;
-	tp->tv_nsec = sgi_clock_period;
-	return 0;
-}
-
-static struct k_clock sgi_clock = {
-	.clock_set	= sgi_clock_set,
-	.clock_get	= sgi_clock_get,
-	.clock_getres	= sgi_clock_getres,
-	.timer_create	= sgi_timer_create,
-	.timer_set	= sgi_timer_set,
-	.timer_del	= sgi_timer_del,
-	.timer_get	= sgi_timer_get
-};
-
-/**
- * mmtimer_init - device initialization routine
- *
- * Does initial setup for the mmtimer device.
- */
-static int __init mmtimer_init(void)
-{
-	cnodeid_t node, maxn = -1;
-
-	if (!ia64_platform_is("sn2"))
-		return 0;
-
-	/*
-	 * Sanity check the cycles/sec variable
-	 */
-	if (sn_rtc_cycles_per_second < 100000) {
-		printk(KERN_ERR "%s: unable to determine clock frequency\n",
-		       MMTIMER_NAME);
-		goto out1;
-	}
-
-	mmtimer_femtoperiod = ((unsigned long)1E15 + sn_rtc_cycles_per_second /
-			       2) / sn_rtc_cycles_per_second;
-
-	if (request_irq(SGI_MMTIMER_VECTOR, mmtimer_interrupt, IRQF_PERCPU, MMTIMER_NAME, NULL)) {
-		printk(KERN_WARNING "%s: unable to allocate interrupt.",
-			MMTIMER_NAME);
-		goto out1;
-	}
-
-	if (misc_register(&mmtimer_miscdev)) {
-		printk(KERN_ERR "%s: failed to register device\n",
-		       MMTIMER_NAME);
-		goto out2;
-	}
-
-	/* Get max numbered node, calculate slots needed */
-	for_each_online_node(node) {
-		maxn = node;
-	}
-	maxn++;
-
-	/* Allocate list of node ptrs to mmtimer_t's */
-	timers = kzalloc(sizeof(struct mmtimer_node)*maxn, GFP_KERNEL);
-	if (!timers) {
-		printk(KERN_ERR "%s: failed to allocate memory for device\n",
-				MMTIMER_NAME);
-		goto out3;
-	}
-
-	/* Initialize struct mmtimer's for each online node */
-	for_each_online_node(node) {
-		spin_lock_init(&timers[node].lock);
-		tasklet_init(&timers[node].tasklet, mmtimer_tasklet,
-			(unsigned long) node);
-	}
-
-	sgi_clock_period = NSEC_PER_SEC / sn_rtc_cycles_per_second;
-	posix_timers_register_clock(CLOCK_SGI_CYCLE, &sgi_clock);
-
-	printk(KERN_INFO "%s: v%s, %ld MHz\n", MMTIMER_DESC, MMTIMER_VERSION,
-	       sn_rtc_cycles_per_second/(unsigned long)1E6);
-
-	return 0;
-
-out3:
-	misc_deregister(&mmtimer_miscdev);
-out2:
-	free_irq(SGI_MMTIMER_VECTOR, NULL);
-out1:
-	return -1;
-}
-
-module_init(mmtimer_init);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 0e3f6496524d..6001369f9aeb 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -887,7 +887,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 	struct freq_attr *fattr = to_attr(attr);
 	ssize_t ret = -EINVAL;
 
-	get_online_cpus();
+	cpus_read_lock();
 
 	if (cpu_online(policy->cpu)) {
 		down_write(&policy->rwsem);
@@ -895,7 +895,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 		up_write(&policy->rwsem);
 	}
 
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return ret;
 }
@@ -2441,7 +2441,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	pr_debug("trying to register driver %s\n", driver_data->name);
 
 	/* Protect against concurrent CPU online/offline. */
-	get_online_cpus();
+	cpus_read_lock();
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 	if (cpufreq_driver) {
@@ -2473,9 +2473,10 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 		goto err_if_unreg;
 	}
 
-	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "cpufreq:online",
-					cpuhp_cpufreq_online,
-					cpuhp_cpufreq_offline);
+	ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ONLINE_DYN,
+						   "cpufreq:online",
+						   cpuhp_cpufreq_online,
+						   cpuhp_cpufreq_offline);
 	if (ret < 0)
 		goto err_if_unreg;
 	hp_online = ret;
@@ -2493,7 +2494,7 @@ err_null_driver:
 	cpufreq_driver = NULL;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 out:
-	put_online_cpus();
+	cpus_read_unlock();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(cpufreq_register_driver);
@@ -2516,17 +2517,17 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 	pr_debug("unregistering driver %s\n", driver->name);
 
 	/* Protect against concurrent cpu hotplug */
-	get_online_cpus();
+	cpus_read_lock();
 	subsys_interface_unregister(&cpufreq_interface);
 	remove_boost_sysfs_file();
-	cpuhp_remove_state_nocalls(hp_online);
+	cpuhp_remove_state_nocalls_cpuslocked(hp_online);
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 
 	cpufreq_driver = NULL;
 
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return 0;
 }
diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c
index 35dd4d7ffee0..b257fc7d5204 100644
--- a/drivers/cpufreq/pasemi-cpufreq.c
+++ b/drivers/cpufreq/pasemi-cpufreq.c
@@ -226,7 +226,7 @@ static int pas_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 	 * We don't support CPU hotplug. Don't unmap after the system
 	 * has already made it to a running state.
 	 */
-	if (system_state != SYSTEM_BOOTING)
+	if (system_state >= SYSTEM_RUNNING)
 		return 0;
 
 	if (sdcasr_mapbase)
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 2706be7ed334..60bb64f4329d 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -220,6 +220,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	entered_state = target_state->enter(dev, drv, index);
 	start_critical_timings();
 
+	sched_clock_idle_wakeup_event();
 	time_end = ns_to_ktime(local_clock());
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
 
diff --git a/drivers/firmware/efi/efi-bgrt.c b/drivers/firmware/efi/efi-bgrt.c
index 04ca8764f0c0..8bf27323f7a3 100644
--- a/drivers/firmware/efi/efi-bgrt.c
+++ b/drivers/firmware/efi/efi-bgrt.c
@@ -36,6 +36,9 @@ void __init efi_bgrt_init(struct acpi_table_header *table)
 	if (acpi_disabled)
 		return;
 
+	if (!efi_enabled(EFI_BOOT))
+		return;
+
 	if (table->length < sizeof(bgrt_tab)) {
 		pr_notice("Ignoring BGRT: invalid length %u (expected %zu)\n",
 		       table->length, sizeof(bgrt_tab));
diff --git a/drivers/firmware/efi/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c
index 8c34d50a4d80..959777ec8a77 100644
--- a/drivers/firmware/efi/libstub/secureboot.c
+++ b/drivers/firmware/efi/libstub/secureboot.c
@@ -16,10 +16,10 @@
 
 /* BIOS variables */
 static const efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
-static const efi_char16_t const efi_SecureBoot_name[] = {
+static const efi_char16_t efi_SecureBoot_name[] = {
 	'S', 'e', 'c', 'u', 'r', 'e', 'B', 'o', 'o', 't', 0
 };
-static const efi_char16_t const efi_SetupMode_name[] = {
+static const efi_char16_t efi_SetupMode_name[] = {
 	'S', 'e', 't', 'u', 'p', 'M', 'o', 'd', 'e', 0
 };
 
diff --git a/drivers/hwtracing/coresight/coresight-etm3x.c b/drivers/hwtracing/coresight/coresight-etm3x.c
index a51b6b64ecdf..93ee8fc539be 100644
--- a/drivers/hwtracing/coresight/coresight-etm3x.c
+++ b/drivers/hwtracing/coresight/coresight-etm3x.c
@@ -587,7 +587,7 @@ static void etm_disable_sysfs(struct coresight_device *csdev)
 	 * after cpu online mask indicates the cpu is offline but before the
 	 * DYING hotplug callback is serviced by the ETM driver.
 	 */
-	get_online_cpus();
+	cpus_read_lock();
 	spin_lock(&drvdata->spinlock);
 
 	/*
@@ -597,7 +597,7 @@ static void etm_disable_sysfs(struct coresight_device *csdev)
 	smp_call_function_single(drvdata->cpu, etm_disable_hw, drvdata, 1);
 
 	spin_unlock(&drvdata->spinlock);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	dev_info(drvdata->dev, "ETM tracing disabled\n");
 }
@@ -795,7 +795,7 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id)
 
 	drvdata->cpu = pdata ? pdata->cpu : 0;
 
-	get_online_cpus();
+	cpus_read_lock();
 	etmdrvdata[drvdata->cpu] = drvdata;
 
 	if (smp_call_function_single(drvdata->cpu,
@@ -803,17 +803,17 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id)
 		dev_err(dev, "ETM arch init failed\n");
 
 	if (!etm_count++) {
-		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING,
-					  "arm/coresight:starting",
-					  etm_starting_cpu, etm_dying_cpu);
-		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-						"arm/coresight:online",
-						etm_online_cpu, NULL);
+		cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ARM_CORESIGHT_STARTING,
+						     "arm/coresight:starting",
+						     etm_starting_cpu, etm_dying_cpu);
+		ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ONLINE_DYN,
+							   "arm/coresight:online",
+							   etm_online_cpu, NULL);
 		if (ret < 0)
 			goto err_arch_supported;
 		hp_online = ret;
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 
 	if (etm_arch_supported(drvdata->arch) == false) {
 		ret = -EINVAL;
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index d1340fb4e457..532adc9dd32a 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -371,7 +371,7 @@ static void etm4_disable_sysfs(struct coresight_device *csdev)
 	 * after cpu online mask indicates the cpu is offline but before the
 	 * DYING hotplug callback is serviced by the ETM driver.
 	 */
-	get_online_cpus();
+	cpus_read_lock();
 	spin_lock(&drvdata->spinlock);
 
 	/*
@@ -381,7 +381,7 @@ static void etm4_disable_sysfs(struct coresight_device *csdev)
 	smp_call_function_single(drvdata->cpu, etm4_disable_hw, drvdata, 1);
 
 	spin_unlock(&drvdata->spinlock);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	dev_info(drvdata->dev, "ETM tracing disabled\n");
 }
@@ -982,7 +982,7 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 
 	drvdata->cpu = pdata ? pdata->cpu : 0;
 
-	get_online_cpus();
+	cpus_read_lock();
 	etmdrvdata[drvdata->cpu] = drvdata;
 
 	if (smp_call_function_single(drvdata->cpu,
@@ -990,18 +990,18 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 		dev_err(dev, "ETM arch init failed\n");
 
 	if (!etm4_count++) {
-		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING,
-					  "arm/coresight4:starting",
-					  etm4_starting_cpu, etm4_dying_cpu);
-		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-						"arm/coresight4:online",
-						etm4_online_cpu, NULL);
+		cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ARM_CORESIGHT_STARTING,
+						     "arm/coresight4:starting",
+						     etm4_starting_cpu, etm4_dying_cpu);
+		ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ONLINE_DYN,
+							   "arm/coresight4:online",
+							   etm4_online_cpu, NULL);
 		if (ret < 0)
 			goto err_arch_supported;
 		hp_online = ret;
 	}
 
-	put_online_cpus();
+	cpus_read_unlock();
 
 	if (etm4_arch_supported(drvdata->arch) == false) {
 		ret = -EINVAL;
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index fc2765ccdb57..8500deda9175 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4315,7 +4315,7 @@ int dmar_parse_one_atsr(struct acpi_dmar_header *hdr, void *arg)
 	struct acpi_dmar_atsr *atsr;
 	struct dmar_atsr_unit *atsru;
 
-	if (system_state != SYSTEM_BOOTING && !intel_iommu_enabled)
+	if (system_state >= SYSTEM_RUNNING && !intel_iommu_enabled)
 		return 0;
 
 	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
@@ -4565,7 +4565,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 	struct acpi_dmar_atsr *atsr;
 	struct acpi_dmar_reserved_memory *rmrr;
 
-	if (!intel_iommu_enabled && system_state != SYSTEM_BOOTING)
+	if (!intel_iommu_enabled && system_state >= SYSTEM_RUNNING)
 		return 0;
 
 	list_for_each_entry(rmrru, &dmar_rmrr_units, list) {
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 9f44ee8ea1bc..b8dcf44df441 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -103,7 +103,7 @@ static bool of_iommu_driver_present(struct device_node *np)
 	 * it never will be. We don't want to defer indefinitely, nor attempt
 	 * to dereference __iommu_of_table after it's been freed.
 	 */
-	if (system_state > SYSTEM_BOOTING)
+	if (system_state >= SYSTEM_RUNNING)
 		return false;
 
 	return of_match_node(&__iommu_of_table, np);
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 192e7b681b96..fe6be6382505 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -320,10 +320,19 @@ static long local_pci_probe(void *_ddi)
 	return 0;
 }
 
+static bool pci_physfn_is_probed(struct pci_dev *dev)
+{
+#ifdef CONFIG_PCI_IOV
+	return dev->is_virtfn && dev->physfn->is_probed;
+#else
+	return false;
+#endif
+}
+
 static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
 			  const struct pci_device_id *id)
 {
-	int error, node;
+	int error, node, cpu;
 	struct drv_dev_and_id ddi = { drv, dev, id };
 
 	/*
@@ -332,33 +341,27 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
 	 * on the right node.
 	 */
 	node = dev_to_node(&dev->dev);
+	dev->is_probed = 1;
+
+	cpu_hotplug_disable();
 
 	/*
-	 * On NUMA systems, we are likely to call a PF probe function using
-	 * work_on_cpu().  If that probe calls pci_enable_sriov() (which
-	 * adds the VF devices via pci_bus_add_device()), we may re-enter
-	 * this function to call the VF probe function.  Calling
-	 * work_on_cpu() again will cause a lockdep warning.  Since VFs are
-	 * always on the same node as the PF, we can work around this by
-	 * avoiding work_on_cpu() when we're already on the correct node.
-	 *
-	 * Preemption is enabled, so it's theoretically unsafe to use
-	 * numa_node_id(), but even if we run the probe function on the
-	 * wrong node, it should be functionally correct.
+	 * Prevent nesting work_on_cpu() for the case where a Virtual Function
+	 * device is probed from work_on_cpu() of the Physical device.
 	 */
-	if (node >= 0 && node != numa_node_id()) {
-		int cpu;
-
-		get_online_cpus();
+	if (node < 0 || node >= MAX_NUMNODES || !node_online(node) ||
+	    pci_physfn_is_probed(dev))
+		cpu = nr_cpu_ids;
+	else
 		cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask);
-		if (cpu < nr_cpu_ids)
-			error = work_on_cpu(cpu, local_pci_probe, &ddi);
-		else
-			error = local_pci_probe(&ddi);
-		put_online_cpus();
-	} else
+
+	if (cpu < nr_cpu_ids)
+		error = work_on_cpu(cpu, local_pci_probe, &ddi);
+	else
 		error = local_pci_probe(&ddi);
 
+	dev->is_probed = 0;
+	cpu_hotplug_enable();
 	return error;
 }
 
diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c
index 94f8038864b4..ed4c343d08c4 100644
--- a/drivers/ras/ras.c
+++ b/drivers/ras/ras.c
@@ -29,7 +29,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event);
 EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event);
 
 
-int __init parse_ras_param(char *str)
+static int __init parse_ras_param(char *str)
 {
 #ifdef CONFIG_RAS_CEC
 	parse_cec_param(str);
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index c1ec8ee80924..9e35032351a0 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -190,6 +190,7 @@ static void do_poweroff(void)
 {
 	switch (system_state) {
 	case SYSTEM_BOOTING:
+	case SYSTEM_SCHEDULING:
 		orderly_poweroff(true);
 		break;
 	case SYSTEM_RUNNING:
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index f2b10d9ebd04..81490456c242 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -96,6 +96,7 @@ struct clocksource {
 	void (*suspend)(struct clocksource *cs);
 	void (*resume)(struct clocksource *cs);
 	void (*mark_unstable)(struct clocksource *cs);
+	void (*tick_stable)(struct clocksource *cs);
 
 	/* private: */
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index f92081234afd..ca73bc1563f4 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -99,26 +99,32 @@ static inline void cpu_maps_update_done(void)
 extern struct bus_type cpu_subsys;
 
 #ifdef CONFIG_HOTPLUG_CPU
-/* Stop CPUs going up and down. */
-
-extern void cpu_hotplug_begin(void);
-extern void cpu_hotplug_done(void);
-extern void get_online_cpus(void);
-extern void put_online_cpus(void);
+extern void cpus_write_lock(void);
+extern void cpus_write_unlock(void);
+extern void cpus_read_lock(void);
+extern void cpus_read_unlock(void);
+extern void lockdep_assert_cpus_held(void);
 extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
 void clear_tasks_mm_cpumask(int cpu);
 int cpu_down(unsigned int cpu);
 
-#else		/* CONFIG_HOTPLUG_CPU */
-
-static inline void cpu_hotplug_begin(void) {}
-static inline void cpu_hotplug_done(void) {}
-#define get_online_cpus()	do { } while (0)
-#define put_online_cpus()	do { } while (0)
-#define cpu_hotplug_disable()	do { } while (0)
-#define cpu_hotplug_enable()	do { } while (0)
-#endif		/* CONFIG_HOTPLUG_CPU */
+#else /* CONFIG_HOTPLUG_CPU */
+
+static inline void cpus_write_lock(void) { }
+static inline void cpus_write_unlock(void) { }
+static inline void cpus_read_lock(void) { }
+static inline void cpus_read_unlock(void) { }
+static inline void lockdep_assert_cpus_held(void) { }
+static inline void cpu_hotplug_disable(void) { }
+static inline void cpu_hotplug_enable(void) { }
+#endif	/* !CONFIG_HOTPLUG_CPU */
+
+/* Wrappers which go away once all code is converted */
+static inline void cpu_hotplug_begin(void) { cpus_write_lock(); }
+static inline void cpu_hotplug_done(void) { cpus_write_unlock(); }
+static inline void get_online_cpus(void) { cpus_read_lock(); }
+static inline void put_online_cpus(void) { cpus_read_unlock(); }
 
 #ifdef CONFIG_PM_SLEEP_SMP
 extern int freeze_secondary_cpus(int primary);
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 0f2a80377520..df3d2719a796 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -153,6 +153,11 @@ int __cpuhp_setup_state(enum cpuhp_state state,	const char *name, bool invoke,
 			int (*startup)(unsigned int cpu),
 			int (*teardown)(unsigned int cpu), bool multi_instance);
 
+int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, const char *name,
+				   bool invoke,
+				   int (*startup)(unsigned int cpu),
+				   int (*teardown)(unsigned int cpu),
+				   bool multi_instance);
 /**
  * cpuhp_setup_state - Setup hotplug state callbacks with calling the callbacks
  * @state:	The state for which the calls are installed
@@ -171,6 +176,15 @@ static inline int cpuhp_setup_state(enum cpuhp_state state,
 	return __cpuhp_setup_state(state, name, true, startup, teardown, false);
 }
 
+static inline int cpuhp_setup_state_cpuslocked(enum cpuhp_state state,
+					       const char *name,
+					       int (*startup)(unsigned int cpu),
+					       int (*teardown)(unsigned int cpu))
+{
+	return __cpuhp_setup_state_cpuslocked(state, name, true, startup,
+					      teardown, false);
+}
+
 /**
  * cpuhp_setup_state_nocalls - Setup hotplug state callbacks without calling the
  *			       callbacks
@@ -191,6 +205,15 @@ static inline int cpuhp_setup_state_nocalls(enum cpuhp_state state,
 				   false);
 }
 
+static inline int cpuhp_setup_state_nocalls_cpuslocked(enum cpuhp_state state,
+						     const char *name,
+						     int (*startup)(unsigned int cpu),
+						     int (*teardown)(unsigned int cpu))
+{
+	return __cpuhp_setup_state_cpuslocked(state, name, false, startup,
+					    teardown, false);
+}
+
 /**
  * cpuhp_setup_state_multi - Add callbacks for multi state
  * @state:	The state for which the calls are installed
@@ -217,6 +240,8 @@ static inline int cpuhp_setup_state_multi(enum cpuhp_state state,
 
 int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
 			       bool invoke);
+int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state,
+					  struct hlist_node *node, bool invoke);
 
 /**
  * cpuhp_state_add_instance - Add an instance for a state and invoke startup
@@ -249,7 +274,15 @@ static inline int cpuhp_state_add_instance_nocalls(enum cpuhp_state state,
 	return __cpuhp_state_add_instance(state, node, false);
 }
 
+static inline int
+cpuhp_state_add_instance_nocalls_cpuslocked(enum cpuhp_state state,
+					    struct hlist_node *node)
+{
+	return __cpuhp_state_add_instance_cpuslocked(state, node, false);
+}
+
 void __cpuhp_remove_state(enum cpuhp_state state, bool invoke);
+void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke);
 
 /**
  * cpuhp_remove_state - Remove hotplug state callbacks and invoke the teardown
@@ -273,6 +306,11 @@ static inline void cpuhp_remove_state_nocalls(enum cpuhp_state state)
 	__cpuhp_remove_state(state, false);
 }
 
+static inline void cpuhp_remove_state_nocalls_cpuslocked(enum cpuhp_state state)
+{
+	__cpuhp_remove_state_cpuslocked(state, false);
+}
+
 /**
  * cpuhp_remove_multi_state - Remove hotplug multi state callback
  * @state:	The state for which the calls are removed
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 2404ad238c0b..4bf4479a3a80 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -236,6 +236,23 @@ unsigned int cpumask_local_spread(unsigned int i, int node);
 		(cpu) = cpumask_next_zero((cpu), (mask)),	\
 		(cpu) < nr_cpu_ids;)
 
+extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap);
+
+/**
+ * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask: the cpumask poiter
+ * @start: the start location
+ *
+ * The implementation does not assume any bit in @mask is set (including @start).
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu_wrap(cpu, mask, start)					\
+	for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false);	\
+	     (cpu) < nr_cpumask_bits;						\
+	     (cpu) = cpumask_next_wrap((cpu), (mask), (start), true))
+
 /**
  * for_each_cpu_and - iterate over every cpu in both masks
  * @cpu: the (optionally unsigned) integer iterator
@@ -276,6 +293,12 @@ static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
 	set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
+static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+{
+	__set_bit(cpumask_check(cpu), cpumask_bits(dstp));
+}
+
+
 /**
  * cpumask_clear_cpu - clear a cpu in a cpumask
  * @cpu: cpu number (< nr_cpu_ids)
@@ -286,6 +309,11 @@ static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp)
 	clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
+static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
+{
+	__clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
+}
+
 /**
  * cpumask_test_cpu - test for a cpu in a cpumask
  * @cpu: cpu number (< nr_cpu_ids)
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 13bc08aba704..1c91f26e2996 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -490,9 +490,13 @@ extern int root_mountflags;
 
 extern bool early_boot_irqs_disabled;
 
-/* Values used for system_state */
+/*
+ * Values used for system_state. Ordering of the states must not be changed
+ * as code checks for <, <=, >, >= STATE.
+ */
 extern enum system_states {
 	SYSTEM_BOOTING,
+	SYSTEM_SCHEDULING,
 	SYSTEM_RUNNING,
 	SYSTEM_HALT,
 	SYSTEM_POWER_OFF,
diff --git a/include/linux/llist.h b/include/linux/llist.h
index 171baa90f6f6..d11738110a7a 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -110,6 +110,25 @@ static inline void init_llist_head(struct llist_head *list)
 	for ((pos) = (node); pos; (pos) = (pos)->next)
 
 /**
+ * llist_for_each_safe - iterate over some deleted entries of a lock-less list
+ *			 safe against removal of list entry
+ * @pos:	the &struct llist_node to use as a loop cursor
+ * @n:		another &struct llist_node to use as temporary storage
+ * @node:	the first entry of deleted list entries
+ *
+ * In general, some entries of the lock-less list can be traversed
+ * safely only after being deleted from list, so start with an entry
+ * instead of list head.
+ *
+ * If being used on entries deleted from lock-less list directly, the
+ * traverse order is from the newest to the oldest added entry.  If
+ * you want to traverse from the oldest to the newest, you must
+ * reverse the order by yourself before traversing.
+ */
+#define llist_for_each_safe(pos, n, node)			\
+	for ((pos) = (node); (pos) && ((n) = (pos)->next, true); (pos) = (n))
+
+/**
  * llist_for_each_entry - iterate over some deleted entries of lock-less list of given type
  * @pos:	the type * to use as a loop cursor.
  * @node:	the fist entry of deleted list entries.
diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
index 136dfdf63ba1..fc412fbd80bd 100644
--- a/include/linux/mm_types_task.h
+++ b/include/linux/mm_types_task.h
@@ -14,6 +14,10 @@
 
 #include <asm/page.h>
 
+#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+#include <asm/tlbbatch.h>
+#endif
+
 #define USE_SPLIT_PTE_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
 #define USE_SPLIT_PMD_PTLOCKS	(USE_SPLIT_PTE_PTLOCKS && \
 		IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
@@ -67,12 +71,15 @@ struct page_frag {
 struct tlbflush_unmap_batch {
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 	/*
-	 * Each bit set is a CPU that potentially has a TLB entry for one of
-	 * the PFNs being flushed. See set_tlb_ubc_flush_pending().
+	 * The arch code makes the following promise: generic code can modify a
+	 * PTE, then call arch_tlbbatch_add_mm() (which internally provides all
+	 * needed barriers), then call arch_tlbbatch_flush(), and the entries
+	 * will be flushed on all CPUs by the time that arch_tlbbatch_flush()
+	 * returns.
 	 */
-	struct cpumask cpumask;
+	struct arch_tlbflush_unmap_batch arch;
 
-	/* True if any bit in cpumask is set */
+	/* True if a flush is needed. */
 	bool flush_required;
 
 	/*
diff --git a/include/linux/padata.h b/include/linux/padata.h
index 0f9e567d5e15..2f9c1f93b1ce 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -166,9 +166,6 @@ struct padata_instance {
 
 extern struct padata_instance *padata_alloc_possible(
 					struct workqueue_struct *wq);
-extern struct padata_instance *padata_alloc(struct workqueue_struct *wq,
-					    const struct cpumask *pcpumask,
-					    const struct cpumask *cbcpumask);
 extern void padata_free(struct padata_instance *pinst);
 extern int padata_do_parallel(struct padata_instance *pinst,
 			      struct padata_priv *padata, int cb_cpu);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 8039f9f0ca05..58f1ab06c4e8 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -376,6 +376,7 @@ struct pci_dev {
 	unsigned int	irq_managed:1;
 	unsigned int	has_secondary_link:1;
 	unsigned int	non_compliant_bars:1;	/* broken BARs; ignore them */
+	unsigned int	is_probed:1;		/* device probing in progress */
 	pci_dev_flags_t dev_flags;
 	atomic_t	enable_cnt;	/* pci_enable_device has been called */
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 24a635887f28..7d6aa29094b2 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -801,6 +801,8 @@ struct perf_cpu_context {
 
 	struct list_head		sched_cb_entry;
 	int				sched_cb_usage;
+
+	int				online;
 };
 
 struct perf_output_handle {
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 8c1e43ab14a9..34e893a75771 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -73,12 +73,6 @@ struct k_itimer {
 		} real;
 		struct cpu_timer_list cpu;
 		struct {
-			unsigned int clock;
-			unsigned int node;
-			unsigned long incr;
-			unsigned long expires;
-		} mmtimer;
-		struct {
 			struct alarm alarmtimer;
 			ktime_t interval;
 		} alarm;
@@ -105,10 +99,11 @@ struct k_clock {
 			   struct itimerspec64 *cur_setting);
 };
 
-extern struct k_clock clock_posix_cpu;
-extern struct k_clock clock_posix_dynamic;
-
-void posix_timers_register_clock(const clockid_t clock_id, struct k_clock *new_clock);
+extern const struct k_clock clock_posix_cpu;
+extern const struct k_clock clock_posix_dynamic;
+extern const struct k_clock clock_process;
+extern const struct k_clock clock_thread;
+extern const struct k_clock alarm_clock;
 
 /* function to call to trigger timer event */
 int posix_timer_event(struct k_itimer *timr, int si_private);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2b69fc650201..3dfa5f99d6ee 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1265,6 +1265,16 @@ extern struct pid *cad_pid;
 #define tsk_used_math(p)			((p)->flags & PF_USED_MATH)
 #define used_math()				tsk_used_math(current)
 
+static inline bool is_percpu_thread(void)
+{
+#ifdef CONFIG_SMP
+	return (current->flags & PF_NO_SETAFFINITY) &&
+		(current->nr_cpus_allowed  == 1);
+#else
+	return true;
+#endif
+}
+
 /* Per-process atomic flags. */
 #define PFA_NO_NEW_PRIVS		0	/* May not gain new privileges. */
 #define PFA_SPREAD_PAGE			1	/* Spread page cache over cpuset */
diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h
index 34fe92ce1ebd..a55600ffdf4b 100644
--- a/include/linux/sched/clock.h
+++ b/include/linux/sched/clock.h
@@ -23,10 +23,6 @@ extern u64 sched_clock_cpu(int cpu);
 extern void sched_clock_init(void);
 
 #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-static inline void sched_clock_init_late(void)
-{
-}
-
 static inline void sched_clock_tick(void)
 {
 }
@@ -39,7 +35,7 @@ static inline void sched_clock_idle_sleep_event(void)
 {
 }
 
-static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
+static inline void sched_clock_idle_wakeup_event(void)
 {
 }
 
@@ -53,7 +49,6 @@ static inline u64 local_clock(void)
 	return sched_clock();
 }
 #else
-extern void sched_clock_init_late(void);
 extern int sched_clock_stable(void);
 extern void clear_sched_clock_stable(void);
 
@@ -63,10 +58,10 @@ extern void clear_sched_clock_stable(void);
  */
 extern u64 __sched_clock_offset;
 
-
 extern void sched_clock_tick(void);
+extern void sched_clock_tick_stable(void);
 extern void sched_clock_idle_sleep_event(void);
-extern void sched_clock_idle_wakeup_event(u64 delta_ns);
+extern void sched_clock_idle_wakeup_event(void);
 
 /*
  * As outlined in clock.c, provides a fast, high resolution, nanosecond
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 3cc9632dcc2a..3d60275e3ba9 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -116,15 +116,29 @@ static inline int try_stop_cpus(const struct cpumask *cpumask,
  * @fn() runs.
  *
  * This can be thought of as a very heavy write lock, equivalent to
- * grabbing every spinlock in the kernel. */
+ * grabbing every spinlock in the kernel.
+ *
+ * Protects against CPU hotplug.
+ */
 int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus);
 
+/**
+ * stop_machine_cpuslocked: freeze the machine on all CPUs and run this function
+ * @fn: the function to run
+ * @data: the data ptr for the @fn()
+ * @cpus: the cpus to run the @fn() on (NULL = any online cpu)
+ *
+ * Same as above. Must be called from with in a cpus_read_lock() protected
+ * region. Avoids nested calls to cpus_read_lock().
+ */
+int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus);
+
 int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 				   const struct cpumask *cpus);
 #else	/* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
 
-static inline int stop_machine(cpu_stop_fn_t fn, void *data,
-				 const struct cpumask *cpus)
+static inline int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data,
+					  const struct cpumask *cpus)
 {
 	unsigned long flags;
 	int ret;
@@ -134,6 +148,12 @@ static inline int stop_machine(cpu_stop_fn_t fn, void *data,
 	return ret;
 }
 
+static inline int stop_machine(cpu_stop_fn_t fn, void *data,
+			       const struct cpumask *cpus)
+{
+	return stop_machine_cpuslocked(fn, data, cpus);
+}
+
 static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 						 const struct cpumask *cpus)
 {
diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h
index e75e1b6ff27f..09299fcb842a 100644
--- a/include/uapi/linux/time.h
+++ b/include/uapi/linux/time.h
@@ -54,7 +54,11 @@ struct itimerval {
 #define CLOCK_BOOTTIME			7
 #define CLOCK_REALTIME_ALARM		8
 #define CLOCK_BOOTTIME_ALARM		9
-#define CLOCK_SGI_CYCLE			10	/* Hardware specific */
+/*
+ * The driver implementing this got removed. The clock ID is kept as a
+ * place holder. Do not reuse!
+ */
+#define CLOCK_SGI_CYCLE			10
 #define CLOCK_TAI			11
 
 #define MAX_CLOCKS			16
diff --git a/init/main.c b/init/main.c
index f866510472d7..df58a416dd1d 100644
--- a/init/main.c
+++ b/init/main.c
@@ -389,6 +389,7 @@ static __initdata DECLARE_COMPLETION(kthreadd_done);
 
 static noinline void __ref rest_init(void)
 {
+	struct task_struct *tsk;
 	int pid;
 
 	rcu_scheduler_starting();
@@ -397,12 +398,32 @@ static noinline void __ref rest_init(void)
 	 * the init task will end up wanting to create kthreads, which, if
 	 * we schedule it before we create kthreadd, will OOPS.
 	 */
-	kernel_thread(kernel_init, NULL, CLONE_FS);
+	pid = kernel_thread(kernel_init, NULL, CLONE_FS);
+	/*
+	 * Pin init on the boot CPU. Task migration is not properly working
+	 * until sched_init_smp() has been run. It will set the allowed
+	 * CPUs for init to the non isolated CPUs.
+	 */
+	rcu_read_lock();
+	tsk = find_task_by_pid_ns(pid, &init_pid_ns);
+	set_cpus_allowed_ptr(tsk, cpumask_of(smp_processor_id()));
+	rcu_read_unlock();
+
 	numa_default_policy();
 	pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
 	rcu_read_lock();
 	kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
 	rcu_read_unlock();
+
+	/*
+	 * Enable might_sleep() and smp_processor_id() checks.
+	 * They cannot be enabled earlier because with CONFIG_PRREMPT=y
+	 * kernel_thread() would trigger might_sleep() splats. With
+	 * CONFIG_PREEMPT_VOLUNTARY=y the init task might have scheduled
+	 * already, but it's stuck on the kthreadd_done completion.
+	 */
+	system_state = SYSTEM_SCHEDULING;
+
 	complete(&kthreadd_done);
 
 	/*
@@ -1015,10 +1036,6 @@ static noinline void __init kernel_init_freeable(void)
 	 * init can allocate pages on any node
 	 */
 	set_mems_allowed(node_states[N_MEMORY]);
-	/*
-	 * init can run on any cpu.
-	 */
-	set_cpus_allowed_ptr(current, cpu_all_mask);
 
 	cad_pid = task_pid(current);
 
diff --git a/kernel/async.c b/kernel/async.c
index d2edd6efec56..2cbd3dd5940d 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -114,14 +114,14 @@ static void async_run_entry_fn(struct work_struct *work)
 	ktime_t uninitialized_var(calltime), delta, rettime;
 
 	/* 1) run (and print duration) */
-	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+	if (initcall_debug && system_state < SYSTEM_RUNNING) {
 		pr_debug("calling  %lli_%pF @ %i\n",
 			(long long)entry->cookie,
 			entry->func, task_pid_nr(current));
 		calltime = ktime_get();
 	}
 	entry->func(entry->data, entry->cookie);
-	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+	if (initcall_debug && system_state < SYSTEM_RUNNING) {
 		rettime = ktime_get();
 		delta = ktime_sub(rettime, calltime);
 		pr_debug("initcall %lli_%pF returned 0 after %lld usecs\n",
@@ -284,14 +284,14 @@ void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain
 {
 	ktime_t uninitialized_var(starttime), delta, endtime;
 
-	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+	if (initcall_debug && system_state < SYSTEM_RUNNING) {
 		pr_debug("async_waiting @ %i\n", task_pid_nr(current));
 		starttime = ktime_get();
 	}
 
 	wait_event(async_done, lowest_in_progress(domain) >= cookie);
 
-	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+	if (initcall_debug && system_state < SYSTEM_RUNNING) {
 		endtime = ktime_get();
 		delta = ktime_sub(endtime, starttime);
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9ae6fbe5b5cf..7435ffc6163b 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -27,6 +27,7 @@
 #include <linux/smpboot.h>
 #include <linux/relay.h>
 #include <linux/slab.h>
+#include <linux/percpu-rwsem.h>
 
 #include <trace/events/power.h>
 #define CREATE_TRACE_POINTS
@@ -65,6 +66,12 @@ struct cpuhp_cpu_state {
 
 static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state);
 
+#if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP)
+static struct lock_class_key cpuhp_state_key;
+static struct lockdep_map cpuhp_state_lock_map =
+	STATIC_LOCKDEP_MAP_INIT("cpuhp_state", &cpuhp_state_key);
+#endif
+
 /**
  * cpuhp_step - Hotplug state machine step
  * @name:	Name of the step
@@ -196,121 +203,41 @@ void cpu_maps_update_done(void)
 	mutex_unlock(&cpu_add_remove_lock);
 }
 
-/* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
+/*
+ * If set, cpu_up and cpu_down will return -EBUSY and do nothing.
  * Should always be manipulated under cpu_add_remove_lock
  */
 static int cpu_hotplug_disabled;
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static struct {
-	struct task_struct *active_writer;
-	/* wait queue to wake up the active_writer */
-	wait_queue_head_t wq;
-	/* verifies that no writer will get active while readers are active */
-	struct mutex lock;
-	/*
-	 * Also blocks the new readers during
-	 * an ongoing cpu hotplug operation.
-	 */
-	atomic_t refcount;
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map dep_map;
-#endif
-} cpu_hotplug = {
-	.active_writer = NULL,
-	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq),
-	.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	.dep_map = STATIC_LOCKDEP_MAP_INIT("cpu_hotplug.dep_map", &cpu_hotplug.dep_map),
-#endif
-};
-
-/* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */
-#define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map)
-#define cpuhp_lock_acquire_tryread() \
-				  lock_map_acquire_tryread(&cpu_hotplug.dep_map)
-#define cpuhp_lock_acquire()      lock_map_acquire(&cpu_hotplug.dep_map)
-#define cpuhp_lock_release()      lock_map_release(&cpu_hotplug.dep_map)
+DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock);
 
-
-void get_online_cpus(void)
+void cpus_read_lock(void)
 {
-	might_sleep();
-	if (cpu_hotplug.active_writer == current)
-		return;
-	cpuhp_lock_acquire_read();
-	mutex_lock(&cpu_hotplug.lock);
-	atomic_inc(&cpu_hotplug.refcount);
-	mutex_unlock(&cpu_hotplug.lock);
+	percpu_down_read(&cpu_hotplug_lock);
 }
-EXPORT_SYMBOL_GPL(get_online_cpus);
+EXPORT_SYMBOL_GPL(cpus_read_lock);
 
-void put_online_cpus(void)
+void cpus_read_unlock(void)
 {
-	int refcount;
-
-	if (cpu_hotplug.active_writer == current)
-		return;
-
-	refcount = atomic_dec_return(&cpu_hotplug.refcount);
-	if (WARN_ON(refcount < 0)) /* try to fix things up */
-		atomic_inc(&cpu_hotplug.refcount);
-
-	if (refcount <= 0 && waitqueue_active(&cpu_hotplug.wq))
-		wake_up(&cpu_hotplug.wq);
-
-	cpuhp_lock_release();
-
+	percpu_up_read(&cpu_hotplug_lock);
 }
-EXPORT_SYMBOL_GPL(put_online_cpus);
+EXPORT_SYMBOL_GPL(cpus_read_unlock);
 
-/*
- * This ensures that the hotplug operation can begin only when the
- * refcount goes to zero.
- *
- * Note that during a cpu-hotplug operation, the new readers, if any,
- * will be blocked by the cpu_hotplug.lock
- *
- * Since cpu_hotplug_begin() is always called after invoking
- * cpu_maps_update_begin(), we can be sure that only one writer is active.
- *
- * Note that theoretically, there is a possibility of a livelock:
- * - Refcount goes to zero, last reader wakes up the sleeping
- *   writer.
- * - Last reader unlocks the cpu_hotplug.lock.
- * - A new reader arrives at this moment, bumps up the refcount.
- * - The writer acquires the cpu_hotplug.lock finds the refcount
- *   non zero and goes to sleep again.
- *
- * However, this is very difficult to achieve in practice since
- * get_online_cpus() not an api which is called all that often.
- *
- */
-void cpu_hotplug_begin(void)
+void cpus_write_lock(void)
 {
-	DEFINE_WAIT(wait);
-
-	cpu_hotplug.active_writer = current;
-	cpuhp_lock_acquire();
+	percpu_down_write(&cpu_hotplug_lock);
+}
 
-	for (;;) {
-		mutex_lock(&cpu_hotplug.lock);
-		prepare_to_wait(&cpu_hotplug.wq, &wait, TASK_UNINTERRUPTIBLE);
-		if (likely(!atomic_read(&cpu_hotplug.refcount)))
-				break;
-		mutex_unlock(&cpu_hotplug.lock);
-		schedule();
-	}
-	finish_wait(&cpu_hotplug.wq, &wait);
+void cpus_write_unlock(void)
+{
+	percpu_up_write(&cpu_hotplug_lock);
 }
 
-void cpu_hotplug_done(void)
+void lockdep_assert_cpus_held(void)
 {
-	cpu_hotplug.active_writer = NULL;
-	mutex_unlock(&cpu_hotplug.lock);
-	cpuhp_lock_release();
+	percpu_rwsem_assert_held(&cpu_hotplug_lock);
 }
 
 /*
@@ -344,8 +271,6 @@ void cpu_hotplug_enable(void)
 EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 #endif	/* CONFIG_HOTPLUG_CPU */
 
-/* Notifier wrappers for transitioning to state machine */
-
 static int bringup_wait_for_ap(unsigned int cpu)
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
@@ -484,6 +409,7 @@ static void cpuhp_thread_fun(unsigned int cpu)
 
 	st->should_run = false;
 
+	lock_map_acquire(&cpuhp_state_lock_map);
 	/* Single callback invocation for [un]install ? */
 	if (st->single) {
 		if (st->cb_state < CPUHP_AP_ONLINE) {
@@ -510,6 +436,7 @@ static void cpuhp_thread_fun(unsigned int cpu)
 		else if (st->state > st->target)
 			ret = cpuhp_ap_offline(cpu, st);
 	}
+	lock_map_release(&cpuhp_state_lock_map);
 	st->result = ret;
 	complete(&st->done);
 }
@@ -524,6 +451,9 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup,
 	if (!cpu_online(cpu))
 		return 0;
 
+	lock_map_acquire(&cpuhp_state_lock_map);
+	lock_map_release(&cpuhp_state_lock_map);
+
 	/*
 	 * If we are up and running, use the hotplug thread. For early calls
 	 * we invoke the thread function directly.
@@ -567,6 +497,8 @@ static int cpuhp_kick_ap_work(unsigned int cpu)
 	enum cpuhp_state state = st->state;
 
 	trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work);
+	lock_map_acquire(&cpuhp_state_lock_map);
+	lock_map_release(&cpuhp_state_lock_map);
 	__cpuhp_kick_ap_work(st);
 	wait_for_completion(&st->done);
 	trace_cpuhp_exit(cpu, st->state, state, st->result);
@@ -701,7 +633,7 @@ static int takedown_cpu(unsigned int cpu)
 	/*
 	 * So now all preempt/rcu users must observe !cpu_active().
 	 */
-	err = stop_machine(take_cpu_down, NULL, cpumask_of(cpu));
+	err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu));
 	if (err) {
 		/* CPU refused to die */
 		irq_unlock_sparse();
@@ -773,7 +705,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 	if (!cpu_present(cpu))
 		return -EINVAL;
 
-	cpu_hotplug_begin();
+	cpus_write_lock();
 
 	cpuhp_tasks_frozen = tasks_frozen;
 
@@ -811,7 +743,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 	}
 
 out:
-	cpu_hotplug_done();
+	cpus_write_unlock();
 	return ret;
 }
 
@@ -893,7 +825,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
 	struct task_struct *idle;
 	int ret = 0;
 
-	cpu_hotplug_begin();
+	cpus_write_lock();
 
 	if (!cpu_present(cpu)) {
 		ret = -EINVAL;
@@ -941,7 +873,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
 	target = min((int)target, CPUHP_BRINGUP_CPU);
 	ret = cpuhp_up_callbacks(cpu, st, target);
 out:
-	cpu_hotplug_done();
+	cpus_write_unlock();
 	return ret;
 }
 
@@ -1413,18 +1345,20 @@ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state,
 	}
 }
 
-int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
-			       bool invoke)
+int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state,
+					  struct hlist_node *node,
+					  bool invoke)
 {
 	struct cpuhp_step *sp;
 	int cpu;
 	int ret;
 
+	lockdep_assert_cpus_held();
+
 	sp = cpuhp_get_step(state);
 	if (sp->multi_instance == false)
 		return -EINVAL;
 
-	get_online_cpus();
 	mutex_lock(&cpuhp_state_mutex);
 
 	if (!invoke || !sp->startup.multi)
@@ -1453,13 +1387,23 @@ add_node:
 	hlist_add_head(node, &sp->list);
 unlock:
 	mutex_unlock(&cpuhp_state_mutex);
-	put_online_cpus();
+	return ret;
+}
+
+int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
+			       bool invoke)
+{
+	int ret;
+
+	cpus_read_lock();
+	ret = __cpuhp_state_add_instance_cpuslocked(state, node, invoke);
+	cpus_read_unlock();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);
 
 /**
- * __cpuhp_setup_state - Setup the callbacks for an hotplug machine state
+ * __cpuhp_setup_state_cpuslocked - Setup the callbacks for an hotplug machine state
  * @state:		The state to setup
  * @invoke:		If true, the startup function is invoked for cpus where
  *			cpu state >= @state
@@ -1468,25 +1412,27 @@ EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);
  * @multi_instance:	State is set up for multiple instances which get
  *			added afterwards.
  *
+ * The caller needs to hold cpus read locked while calling this function.
  * Returns:
  *   On success:
  *      Positive state number if @state is CPUHP_AP_ONLINE_DYN
  *      0 for all other states
  *   On failure: proper (negative) error code
  */
-int __cpuhp_setup_state(enum cpuhp_state state,
-			const char *name, bool invoke,
-			int (*startup)(unsigned int cpu),
-			int (*teardown)(unsigned int cpu),
-			bool multi_instance)
+int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state,
+				   const char *name, bool invoke,
+				   int (*startup)(unsigned int cpu),
+				   int (*teardown)(unsigned int cpu),
+				   bool multi_instance)
 {
 	int cpu, ret = 0;
 	bool dynstate;
 
+	lockdep_assert_cpus_held();
+
 	if (cpuhp_cb_check(state) || !name)
 		return -EINVAL;
 
-	get_online_cpus();
 	mutex_lock(&cpuhp_state_mutex);
 
 	ret = cpuhp_store_callbacks(state, name, startup, teardown,
@@ -1522,7 +1468,6 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 	}
 out:
 	mutex_unlock(&cpuhp_state_mutex);
-	put_online_cpus();
 	/*
 	 * If the requested state is CPUHP_AP_ONLINE_DYN, return the
 	 * dynamically allocated state in case of success.
@@ -1531,6 +1476,22 @@ out:
 		return state;
 	return ret;
 }
+EXPORT_SYMBOL(__cpuhp_setup_state_cpuslocked);
+
+int __cpuhp_setup_state(enum cpuhp_state state,
+			const char *name, bool invoke,
+			int (*startup)(unsigned int cpu),
+			int (*teardown)(unsigned int cpu),
+			bool multi_instance)
+{
+	int ret;
+
+	cpus_read_lock();
+	ret = __cpuhp_setup_state_cpuslocked(state, name, invoke, startup,
+					     teardown, multi_instance);
+	cpus_read_unlock();
+	return ret;
+}
 EXPORT_SYMBOL(__cpuhp_setup_state);
 
 int __cpuhp_state_remove_instance(enum cpuhp_state state,
@@ -1544,7 +1505,7 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state,
 	if (!sp->multi_instance)
 		return -EINVAL;
 
-	get_online_cpus();
+	cpus_read_lock();
 	mutex_lock(&cpuhp_state_mutex);
 
 	if (!invoke || !cpuhp_get_teardown_cb(state))
@@ -1565,29 +1526,30 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state,
 remove:
 	hlist_del(node);
 	mutex_unlock(&cpuhp_state_mutex);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance);
 
 /**
- * __cpuhp_remove_state - Remove the callbacks for an hotplug machine state
+ * __cpuhp_remove_state_cpuslocked - Remove the callbacks for an hotplug machine state
  * @state:	The state to remove
  * @invoke:	If true, the teardown function is invoked for cpus where
  *		cpu state >= @state
  *
+ * The caller needs to hold cpus read locked while calling this function.
  * The teardown callback is currently not allowed to fail. Think
  * about module removal!
  */
-void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
+void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke)
 {
 	struct cpuhp_step *sp = cpuhp_get_step(state);
 	int cpu;
 
 	BUG_ON(cpuhp_cb_check(state));
 
-	get_online_cpus();
+	lockdep_assert_cpus_held();
 
 	mutex_lock(&cpuhp_state_mutex);
 	if (sp->multi_instance) {
@@ -1615,7 +1577,14 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
 remove:
 	cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
 	mutex_unlock(&cpuhp_state_mutex);
-	put_online_cpus();
+}
+EXPORT_SYMBOL(__cpuhp_remove_state_cpuslocked);
+
+void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
+{
+	cpus_read_lock();
+	__cpuhp_remove_state_cpuslocked(state, invoke);
+	cpus_read_unlock();
 }
 EXPORT_SYMBOL(__cpuhp_remove_state);
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6e75a5c9412d..8d6acaeeea17 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -389,6 +389,7 @@ static atomic_t nr_switch_events __read_mostly;
 static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
 static struct srcu_struct pmus_srcu;
+static cpumask_var_t perf_online_mask;
 
 /*
  * perf event paranoia level:
@@ -3812,14 +3813,6 @@ find_get_context(struct pmu *pmu, struct task_struct *task,
 		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
 			return ERR_PTR(-EACCES);
 
-		/*
-		 * We could be clever and allow to attach a event to an
-		 * offline CPU and activate it when the CPU comes up, but
-		 * that's for later.
-		 */
-		if (!cpu_online(cpu))
-			return ERR_PTR(-ENODEV);
-
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		ctx = &cpuctx->ctx;
 		get_ctx(ctx);
@@ -7703,7 +7696,8 @@ static int swevent_hlist_get_cpu(int cpu)
 	int err = 0;
 
 	mutex_lock(&swhash->hlist_mutex);
-	if (!swevent_hlist_deref(swhash) && cpu_online(cpu)) {
+	if (!swevent_hlist_deref(swhash) &&
+	    cpumask_test_cpu(cpu, perf_online_mask)) {
 		struct swevent_hlist *hlist;
 
 		hlist = kzalloc(sizeof(*hlist), GFP_KERNEL);
@@ -7724,7 +7718,7 @@ static int swevent_hlist_get(void)
 {
 	int err, cpu, failed_cpu;
 
-	get_online_cpus();
+	mutex_lock(&pmus_lock);
 	for_each_possible_cpu(cpu) {
 		err = swevent_hlist_get_cpu(cpu);
 		if (err) {
@@ -7732,8 +7726,7 @@ static int swevent_hlist_get(void)
 			goto fail;
 		}
 	}
-	put_online_cpus();
-
+	mutex_unlock(&pmus_lock);
 	return 0;
 fail:
 	for_each_possible_cpu(cpu) {
@@ -7741,8 +7734,7 @@ fail:
 			break;
 		swevent_hlist_put_cpu(cpu);
 	}
-
-	put_online_cpus();
+	mutex_unlock(&pmus_lock);
 	return err;
 }
 
@@ -8920,7 +8912,7 @@ perf_event_mux_interval_ms_store(struct device *dev,
 	pmu->hrtimer_interval_ms = timer;
 
 	/* update all cpuctx for this PMU */
-	get_online_cpus();
+	cpus_read_lock();
 	for_each_online_cpu(cpu) {
 		struct perf_cpu_context *cpuctx;
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
@@ -8929,7 +8921,7 @@ perf_event_mux_interval_ms_store(struct device *dev,
 		cpu_function_call(cpu,
 			(remote_function_f)perf_mux_hrtimer_restart, cpuctx);
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 	mutex_unlock(&mux_interval_mutex);
 
 	return count;
@@ -9059,6 +9051,7 @@ skip_type:
 		lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
 		lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
 		cpuctx->ctx.pmu = pmu;
+		cpuctx->online = cpumask_test_cpu(cpu, perf_online_mask);
 
 		__perf_mux_hrtimer_init(cpuctx, cpu);
 	}
@@ -9172,7 +9165,7 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 
 static struct pmu *perf_init_event(struct perf_event *event)
 {
-	struct pmu *pmu = NULL;
+	struct pmu *pmu;
 	int idx;
 	int ret;
 
@@ -9456,9 +9449,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	}
 
 	pmu = perf_init_event(event);
-	if (!pmu)
-		goto err_ns;
-	else if (IS_ERR(pmu)) {
+	if (IS_ERR(pmu)) {
 		err = PTR_ERR(pmu);
 		goto err_ns;
 	}
@@ -9471,8 +9462,10 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		event->addr_filters_offs = kcalloc(pmu->nr_addr_filters,
 						   sizeof(unsigned long),
 						   GFP_KERNEL);
-		if (!event->addr_filters_offs)
+		if (!event->addr_filters_offs) {
+			err = -ENOMEM;
 			goto err_per_task;
+		}
 
 		/* force hw sync on the address filters */
 		event->addr_filters_gen = 1;
@@ -9882,12 +9875,10 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_task;
 	}
 
-	get_online_cpus();
-
 	if (task) {
 		err = mutex_lock_interruptible(&task->signal->cred_guard_mutex);
 		if (err)
-			goto err_cpus;
+			goto err_cred;
 
 		/*
 		 * Reuse ptrace permission checks for now.
@@ -10073,6 +10064,23 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_locked;
 	}
 
+	if (!task) {
+		/*
+		 * Check if the @cpu we're creating an event for is online.
+		 *
+		 * We use the perf_cpu_context::ctx::mutex to serialize against
+		 * the hotplug notifiers. See perf_event_{init,exit}_cpu().
+		 */
+		struct perf_cpu_context *cpuctx =
+			container_of(ctx, struct perf_cpu_context, ctx);
+
+		if (!cpuctx->online) {
+			err = -ENODEV;
+			goto err_locked;
+		}
+	}
+
+
 	/*
 	 * Must be under the same ctx::mutex as perf_install_in_context(),
 	 * because we need to serialize with concurrent event creation.
@@ -10162,8 +10170,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		put_task_struct(task);
 	}
 
-	put_online_cpus();
-
 	mutex_lock(&current->perf_event_mutex);
 	list_add_tail(&event->owner_entry, &current->perf_event_list);
 	mutex_unlock(&current->perf_event_mutex);
@@ -10197,8 +10203,6 @@ err_alloc:
 err_cred:
 	if (task)
 		mutex_unlock(&task->signal->cred_guard_mutex);
-err_cpus:
-	put_online_cpus();
 err_task:
 	if (task)
 		put_task_struct(task);
@@ -10253,6 +10257,21 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 		goto err_unlock;
 	}
 
+	if (!task) {
+		/*
+		 * Check if the @cpu we're creating an event for is online.
+		 *
+		 * We use the perf_cpu_context::ctx::mutex to serialize against
+		 * the hotplug notifiers. See perf_event_{init,exit}_cpu().
+		 */
+		struct perf_cpu_context *cpuctx =
+			container_of(ctx, struct perf_cpu_context, ctx);
+		if (!cpuctx->online) {
+			err = -ENODEV;
+			goto err_unlock;
+		}
+	}
+
 	if (!exclusive_event_installable(event, ctx)) {
 		err = -EBUSY;
 		goto err_unlock;
@@ -10920,6 +10939,8 @@ static void __init perf_event_init_all_cpus(void)
 	struct swevent_htable *swhash;
 	int cpu;
 
+	zalloc_cpumask_var(&perf_online_mask, GFP_KERNEL);
+
 	for_each_possible_cpu(cpu) {
 		swhash = &per_cpu(swevent_htable, cpu);
 		mutex_init(&swhash->hlist_mutex);
@@ -10935,7 +10956,7 @@ static void __init perf_event_init_all_cpus(void)
 	}
 }
 
-int perf_event_init_cpu(unsigned int cpu)
+void perf_swevent_init_cpu(unsigned int cpu)
 {
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
@@ -10948,7 +10969,6 @@ int perf_event_init_cpu(unsigned int cpu)
 		rcu_assign_pointer(swhash->swevent_hlist, hlist);
 	}
 	mutex_unlock(&swhash->hlist_mutex);
-	return 0;
 }
 
 #if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC_CORE
@@ -10966,19 +10986,22 @@ static void __perf_event_exit_context(void *__info)
 
 static void perf_event_exit_cpu_context(int cpu)
 {
+	struct perf_cpu_context *cpuctx;
 	struct perf_event_context *ctx;
 	struct pmu *pmu;
-	int idx;
 
-	idx = srcu_read_lock(&pmus_srcu);
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		ctx = &per_cpu_ptr(pmu->pmu_cpu_context, cpu)->ctx;
+	mutex_lock(&pmus_lock);
+	list_for_each_entry(pmu, &pmus, entry) {
+		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
+		ctx = &cpuctx->ctx;
 
 		mutex_lock(&ctx->mutex);
 		smp_call_function_single(cpu, __perf_event_exit_context, ctx, 1);
+		cpuctx->online = 0;
 		mutex_unlock(&ctx->mutex);
 	}
-	srcu_read_unlock(&pmus_srcu, idx);
+	cpumask_clear_cpu(cpu, perf_online_mask);
+	mutex_unlock(&pmus_lock);
 }
 #else
 
@@ -10986,6 +11009,29 @@ static void perf_event_exit_cpu_context(int cpu) { }
 
 #endif
 
+int perf_event_init_cpu(unsigned int cpu)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_event_context *ctx;
+	struct pmu *pmu;
+
+	perf_swevent_init_cpu(cpu);
+
+	mutex_lock(&pmus_lock);
+	cpumask_set_cpu(cpu, perf_online_mask);
+	list_for_each_entry(pmu, &pmus, entry) {
+		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
+		ctx = &cpuctx->ctx;
+
+		mutex_lock(&ctx->mutex);
+		cpuctx->online = 1;
+		mutex_unlock(&ctx->mutex);
+	}
+	mutex_unlock(&pmus_lock);
+
+	return 0;
+}
+
 int perf_event_exit_cpu(unsigned int cpu)
 {
 	perf_event_exit_cpu_context(cpu);
diff --git a/kernel/extable.c b/kernel/extable.c
index 2676d7f8baf6..0fbdd8582f08 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -75,7 +75,7 @@ int core_kernel_text(unsigned long addr)
 	    addr < (unsigned long)_etext)
 		return 1;
 
-	if (system_state == SYSTEM_BOOTING &&
+	if (system_state < SYSTEM_RUNNING &&
 	    init_kernel_text(addr))
 		return 1;
 	return 0;
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 22e443133987..c5bbaed5a5e6 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -480,7 +480,8 @@ int __init early_irq_init(void)
 
 	/* Let arch update nr_irqs and return the nr of preallocated irqs */
 	initcnt = arch_probe_nr_irqs();
-	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt);
+	printk(KERN_INFO "NR_IRQS: %d, nr_irqs: %d, preallocated irqs: %d\n",
+	       NR_IRQS, nr_irqs, initcnt);
 
 	if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS))
 		nr_irqs = IRQ_BITMAP_BITS;
@@ -516,7 +517,7 @@ int __init early_irq_init(void)
 
 	init_irq_default_affinity();
 
-	printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS);
+	printk(KERN_INFO "NR_IRQS: %d\n", NR_IRQS);
 
 	desc = irq_desc;
 	count = ARRAY_SIZE(irq_desc);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 31805f237396..70b9da72018b 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -746,13 +746,54 @@ unsigned int irq_find_mapping(struct irq_domain *domain,
 EXPORT_SYMBOL_GPL(irq_find_mapping);
 
 #ifdef CONFIG_IRQ_DOMAIN_DEBUG
+static void virq_debug_show_one(struct seq_file *m, struct irq_desc *desc)
+{
+	struct irq_domain *domain;
+	struct irq_data *data;
+
+	domain = desc->irq_data.domain;
+	data = &desc->irq_data;
+
+	while (domain) {
+		unsigned int irq = data->irq;
+		unsigned long hwirq = data->hwirq;
+		struct irq_chip *chip;
+		bool direct;
+
+		if (data == &desc->irq_data)
+			seq_printf(m, "%5d  ", irq);
+		else
+			seq_printf(m, "%5d+ ", irq);
+		seq_printf(m, "0x%05lx  ", hwirq);
+
+		chip = irq_data_get_irq_chip(data);
+		seq_printf(m, "%-15s  ", (chip && chip->name) ? chip->name : "none");
+
+		seq_printf(m, data ? "0x%p  " : "  %p  ",
+			   irq_data_get_irq_chip_data(data));
+
+		seq_printf(m, "   %c    ", (desc->action && desc->action->handler) ? '*' : ' ');
+		direct = (irq == hwirq) && (irq < domain->revmap_direct_max_irq);
+		seq_printf(m, "%6s%-8s  ",
+			   (hwirq < domain->revmap_size) ? "LINEAR" : "RADIX",
+			   direct ? "(DIRECT)" : "");
+		seq_printf(m, "%s\n", domain->name);
+#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
+		domain = domain->parent;
+		data = data->parent_data;
+#else
+		domain = NULL;
+#endif
+	}
+}
+
 static int virq_debug_show(struct seq_file *m, void *private)
 {
 	unsigned long flags;
 	struct irq_desc *desc;
 	struct irq_domain *domain;
 	struct radix_tree_iter iter;
-	void *data, **slot;
+	void **slot;
 	int i;
 
 	seq_printf(m, " %-16s  %-6s  %-10s  %-10s  %s\n",
@@ -760,15 +801,26 @@ static int virq_debug_show(struct seq_file *m, void *private)
 	mutex_lock(&irq_domain_mutex);
 	list_for_each_entry(domain, &irq_domain_list, link) {
 		struct device_node *of_node;
+		const char *name;
+
 		int count = 0;
+
 		of_node = irq_domain_get_of_node(domain);
+		if (of_node)
+			name = of_node_full_name(of_node);
+		else if (is_fwnode_irqchip(domain->fwnode))
+			name = container_of(domain->fwnode, struct irqchip_fwid,
+					    fwnode)->name;
+		else
+			name = "";
+
 		radix_tree_for_each_slot(slot, &domain->revmap_tree, &iter, 0)
 			count++;
 		seq_printf(m, "%c%-16s  %6u  %10u  %10u  %s\n",
 			   domain == irq_default_domain ? '*' : ' ', domain->name,
 			   domain->revmap_size + count, domain->revmap_size,
 			   domain->revmap_direct_max_irq,
-			   of_node ? of_node_full_name(of_node) : "");
+			   name);
 	}
 	mutex_unlock(&irq_domain_mutex);
 
@@ -782,30 +834,7 @@ static int virq_debug_show(struct seq_file *m, void *private)
 			continue;
 
 		raw_spin_lock_irqsave(&desc->lock, flags);
-		domain = desc->irq_data.domain;
-
-		if (domain) {
-			struct irq_chip *chip;
-			int hwirq = desc->irq_data.hwirq;
-			bool direct;
-
-			seq_printf(m, "%5d  ", i);
-			seq_printf(m, "0x%05x  ", hwirq);
-
-			chip = irq_desc_get_chip(desc);
-			seq_printf(m, "%-15s  ", (chip && chip->name) ? chip->name : "none");
-
-			data = irq_desc_get_chip_data(desc);
-			seq_printf(m, data ? "0x%p  " : "  %p  ", data);
-
-			seq_printf(m, "   %c    ", (desc->action && desc->action->handler) ? '*' : ' ');
-			direct = (i == hwirq) && (i < domain->revmap_direct_max_irq);
-			seq_printf(m, "%6s%-8s  ",
-				   (hwirq < domain->revmap_size) ? "LINEAR" : "RADIX",
-				   direct ? "(DIRECT)" : "");
-			seq_printf(m, "%s\n", desc->irq_data.domain->name);
-		}
-
+		virq_debug_show_one(m, desc);
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	}
 
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index ddc2f5427f75..fe4d48ec5bc4 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -265,13 +265,19 @@ struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode,
 					 struct msi_domain_info *info,
 					 struct irq_domain *parent)
 {
+	struct irq_domain *domain;
+
 	if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS)
 		msi_domain_update_dom_ops(info);
 	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
 		msi_domain_update_chip_ops(info);
 
-	return irq_domain_create_hierarchy(parent, IRQ_DOMAIN_FLAG_MSI, 0,
-					   fwnode, &msi_domain_ops, info);
+	domain = irq_domain_create_hierarchy(parent, IRQ_DOMAIN_FLAG_MSI, 0,
+					     fwnode, &msi_domain_ops, info);
+	if (domain && info->chip && info->chip->name)
+		domain->name = info->chip->name;
+
+	return domain;
 }
 
 int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev,
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 6c9cb208ac48..d11c506a6ac3 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -15,6 +15,7 @@
 #include <linux/static_key.h>
 #include <linux/jump_label_ratelimit.h>
 #include <linux/bug.h>
+#include <linux/cpu.h>
 
 #ifdef HAVE_JUMP_LABEL
 
@@ -124,6 +125,7 @@ void static_key_slow_inc(struct static_key *key)
 			return;
 	}
 
+	cpus_read_lock();
 	jump_label_lock();
 	if (atomic_read(&key->enabled) == 0) {
 		atomic_set(&key->enabled, -1);
@@ -133,12 +135,14 @@ void static_key_slow_inc(struct static_key *key)
 		atomic_inc(&key->enabled);
 	}
 	jump_label_unlock();
+	cpus_read_unlock();
 }
 EXPORT_SYMBOL_GPL(static_key_slow_inc);
 
 static void __static_key_slow_dec(struct static_key *key,
 		unsigned long rate_limit, struct delayed_work *work)
 {
+	cpus_read_lock();
 	/*
 	 * The negative count check is valid even when a negative
 	 * key->enabled is in use by static_key_slow_inc(); a
@@ -149,6 +153,7 @@ static void __static_key_slow_dec(struct static_key *key,
 	if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
 		WARN(atomic_read(&key->enabled) < 0,
 		     "jump label: negative count!\n");
+		cpus_read_unlock();
 		return;
 	}
 
@@ -159,6 +164,7 @@ static void __static_key_slow_dec(struct static_key *key,
 		jump_label_update(key);
 	}
 	jump_label_unlock();
+	cpus_read_unlock();
 }
 
 static void jump_label_update_timeout(struct work_struct *work)
@@ -334,6 +340,7 @@ void __init jump_label_init(void)
 	if (static_key_initialized)
 		return;
 
+	cpus_read_lock();
 	jump_label_lock();
 	jump_label_sort_entries(iter_start, iter_stop);
 
@@ -353,6 +360,7 @@ void __init jump_label_init(void)
 	}
 	static_key_initialized = true;
 	jump_label_unlock();
+	cpus_read_unlock();
 }
 
 #ifdef CONFIG_MODULES
@@ -590,28 +598,28 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val,
 	struct module *mod = data;
 	int ret = 0;
 
+	cpus_read_lock();
+	jump_label_lock();
+
 	switch (val) {
 	case MODULE_STATE_COMING:
-		jump_label_lock();
 		ret = jump_label_add_module(mod);
 		if (ret) {
 			WARN(1, "Failed to allocatote memory: jump_label may not work properly.\n");
 			jump_label_del_module(mod);
 		}
-		jump_label_unlock();
 		break;
 	case MODULE_STATE_GOING:
-		jump_label_lock();
 		jump_label_del_module(mod);
-		jump_label_unlock();
 		break;
 	case MODULE_STATE_LIVE:
-		jump_label_lock();
 		jump_label_invalidate_module_init(mod);
-		jump_label_unlock();
 		break;
 	}
 
+	jump_label_unlock();
+	cpus_read_unlock();
+
 	return notifier_from_errno(ret);
 }
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index adfe3b4cfe05..6756d750b31b 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -483,11 +483,6 @@ static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
  */
 static void do_optimize_kprobes(void)
 {
-	/* Optimization never be done when disarmed */
-	if (kprobes_all_disarmed || !kprobes_allow_optimization ||
-	    list_empty(&optimizing_list))
-		return;
-
 	/*
 	 * The optimization/unoptimization refers online_cpus via
 	 * stop_machine() and cpu-hotplug modifies online_cpus.
@@ -495,14 +490,19 @@ static void do_optimize_kprobes(void)
 	 * This combination can cause a deadlock (cpu-hotplug try to lock
 	 * text_mutex but stop_machine can not be done because online_cpus
 	 * has been changed)
-	 * To avoid this deadlock, we need to call get_online_cpus()
+	 * To avoid this deadlock, caller must have locked cpu hotplug
 	 * for preventing cpu-hotplug outside of text_mutex locking.
 	 */
-	get_online_cpus();
+	lockdep_assert_cpus_held();
+
+	/* Optimization never be done when disarmed */
+	if (kprobes_all_disarmed || !kprobes_allow_optimization ||
+	    list_empty(&optimizing_list))
+		return;
+
 	mutex_lock(&text_mutex);
 	arch_optimize_kprobes(&optimizing_list);
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 /*
@@ -513,12 +513,13 @@ static void do_unoptimize_kprobes(void)
 {
 	struct optimized_kprobe *op, *tmp;
 
+	/* See comment in do_optimize_kprobes() */
+	lockdep_assert_cpus_held();
+
 	/* Unoptimization must be done anytime */
 	if (list_empty(&unoptimizing_list))
 		return;
 
-	/* Ditto to do_optimize_kprobes */
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 	arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list);
 	/* Loop free_list for disarming */
@@ -537,7 +538,6 @@ static void do_unoptimize_kprobes(void)
 			list_del_init(&op->list);
 	}
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 /* Reclaim all kprobes on the free_list */
@@ -562,6 +562,7 @@ static void kick_kprobe_optimizer(void)
 static void kprobe_optimizer(struct work_struct *work)
 {
 	mutex_lock(&kprobe_mutex);
+	cpus_read_lock();
 	/* Lock modules while optimizing kprobes */
 	mutex_lock(&module_mutex);
 
@@ -587,6 +588,7 @@ static void kprobe_optimizer(struct work_struct *work)
 	do_free_cleaned_kprobes();
 
 	mutex_unlock(&module_mutex);
+	cpus_read_unlock();
 	mutex_unlock(&kprobe_mutex);
 
 	/* Step 5: Kick optimizer again if needed */
@@ -650,9 +652,8 @@ static void optimize_kprobe(struct kprobe *p)
 /* Short cut to direct unoptimizing */
 static void force_unoptimize_kprobe(struct optimized_kprobe *op)
 {
-	get_online_cpus();
+	lockdep_assert_cpus_held();
 	arch_unoptimize_kprobe(op);
-	put_online_cpus();
 	if (kprobe_disabled(&op->kp))
 		arch_disarm_kprobe(&op->kp);
 }
@@ -791,6 +792,7 @@ static void try_to_optimize_kprobe(struct kprobe *p)
 		return;
 
 	/* For preparing optimization, jump_label_text_reserved() is called */
+	cpus_read_lock();
 	jump_label_lock();
 	mutex_lock(&text_mutex);
 
@@ -812,6 +814,7 @@ static void try_to_optimize_kprobe(struct kprobe *p)
 out:
 	mutex_unlock(&text_mutex);
 	jump_label_unlock();
+	cpus_read_unlock();
 }
 
 #ifdef CONFIG_SYSCTL
@@ -826,6 +829,7 @@ static void optimize_all_kprobes(void)
 	if (kprobes_allow_optimization)
 		goto out;
 
+	cpus_read_lock();
 	kprobes_allow_optimization = true;
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
@@ -833,6 +837,7 @@ static void optimize_all_kprobes(void)
 			if (!kprobe_disabled(p))
 				optimize_kprobe(p);
 	}
+	cpus_read_unlock();
 	printk(KERN_INFO "Kprobes globally optimized\n");
 out:
 	mutex_unlock(&kprobe_mutex);
@@ -851,6 +856,7 @@ static void unoptimize_all_kprobes(void)
 		return;
 	}
 
+	cpus_read_lock();
 	kprobes_allow_optimization = false;
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
@@ -859,6 +865,7 @@ static void unoptimize_all_kprobes(void)
 				unoptimize_kprobe(p, false);
 		}
 	}
+	cpus_read_unlock();
 	mutex_unlock(&kprobe_mutex);
 
 	/* Wait for unoptimizing completion */
@@ -1010,14 +1017,11 @@ static void arm_kprobe(struct kprobe *kp)
 		arm_kprobe_ftrace(kp);
 		return;
 	}
-	/*
-	 * Here, since __arm_kprobe() doesn't use stop_machine(),
-	 * this doesn't cause deadlock on text_mutex. So, we don't
-	 * need get_online_cpus().
-	 */
+	cpus_read_lock();
 	mutex_lock(&text_mutex);
 	__arm_kprobe(kp);
 	mutex_unlock(&text_mutex);
+	cpus_read_unlock();
 }
 
 /* Disarm a kprobe with text_mutex */
@@ -1027,10 +1031,12 @@ static void disarm_kprobe(struct kprobe *kp, bool reopt)
 		disarm_kprobe_ftrace(kp);
 		return;
 	}
-	/* Ditto */
+
+	cpus_read_lock();
 	mutex_lock(&text_mutex);
 	__disarm_kprobe(kp, reopt);
 	mutex_unlock(&text_mutex);
+	cpus_read_unlock();
 }
 
 /*
@@ -1298,13 +1304,10 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p)
 	int ret = 0;
 	struct kprobe *ap = orig_p;
 
+	cpus_read_lock();
+
 	/* For preparing optimization, jump_label_text_reserved() is called */
 	jump_label_lock();
-	/*
-	 * Get online CPUs to avoid text_mutex deadlock.with stop machine,
-	 * which is invoked by unoptimize_kprobe() in add_new_kprobe()
-	 */
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 
 	if (!kprobe_aggrprobe(orig_p)) {
@@ -1352,8 +1355,8 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p)
 
 out:
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 	jump_label_unlock();
+	cpus_read_unlock();
 
 	if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) {
 		ap->flags &= ~KPROBE_FLAG_DISABLED;
@@ -1555,9 +1558,12 @@ int register_kprobe(struct kprobe *p)
 		goto out;
 	}
 
-	mutex_lock(&text_mutex);	/* Avoiding text modification */
+	cpus_read_lock();
+	/* Prevent text modification */
+	mutex_lock(&text_mutex);
 	ret = prepare_kprobe(p);
 	mutex_unlock(&text_mutex);
+	cpus_read_unlock();
 	if (ret)
 		goto out;
 
@@ -1570,7 +1576,6 @@ int register_kprobe(struct kprobe *p)
 
 	/* Try to optimize kprobe */
 	try_to_optimize_kprobe(p);
-
 out:
 	mutex_unlock(&kprobe_mutex);
 
diff --git a/kernel/padata.c b/kernel/padata.c
index ac8f1e524836..868f947166d7 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -934,29 +934,18 @@ static struct kobj_type padata_attr_type = {
 };
 
 /**
- * padata_alloc_possible - Allocate and initialize padata instance.
- *                         Use the cpu_possible_mask for serial and
- *                         parallel workers.
- *
- * @wq: workqueue to use for the allocated padata instance
- */
-struct padata_instance *padata_alloc_possible(struct workqueue_struct *wq)
-{
-	return padata_alloc(wq, cpu_possible_mask, cpu_possible_mask);
-}
-EXPORT_SYMBOL(padata_alloc_possible);
-
-/**
  * padata_alloc - allocate and initialize a padata instance and specify
  *                cpumasks for serial and parallel workers.
  *
  * @wq: workqueue to use for the allocated padata instance
  * @pcpumask: cpumask that will be used for padata parallelization
  * @cbcpumask: cpumask that will be used for padata serialization
+ *
+ * Must be called from a cpus_read_lock() protected region
  */
-struct padata_instance *padata_alloc(struct workqueue_struct *wq,
-				     const struct cpumask *pcpumask,
-				     const struct cpumask *cbcpumask)
+static struct padata_instance *padata_alloc(struct workqueue_struct *wq,
+					    const struct cpumask *pcpumask,
+					    const struct cpumask *cbcpumask)
 {
 	struct padata_instance *pinst;
 	struct parallel_data *pd = NULL;
@@ -965,7 +954,6 @@ struct padata_instance *padata_alloc(struct workqueue_struct *wq,
 	if (!pinst)
 		goto err;
 
-	get_online_cpus();
 	if (!alloc_cpumask_var(&pinst->cpumask.pcpu, GFP_KERNEL))
 		goto err_free_inst;
 	if (!alloc_cpumask_var(&pinst->cpumask.cbcpu, GFP_KERNEL)) {
@@ -989,14 +977,12 @@ struct padata_instance *padata_alloc(struct workqueue_struct *wq,
 
 	pinst->flags = 0;
 
-	put_online_cpus();
-
 	BLOCKING_INIT_NOTIFIER_HEAD(&pinst->cpumask_change_notifier);
 	kobject_init(&pinst->kobj, &padata_attr_type);
 	mutex_init(&pinst->lock);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	cpuhp_state_add_instance_nocalls(hp_online, &pinst->node);
+	cpuhp_state_add_instance_nocalls_cpuslocked(hp_online, &pinst->node);
 #endif
 	return pinst;
 
@@ -1005,12 +991,27 @@ err_free_masks:
 	free_cpumask_var(pinst->cpumask.cbcpu);
 err_free_inst:
 	kfree(pinst);
-	put_online_cpus();
 err:
 	return NULL;
 }
 
 /**
+ * padata_alloc_possible - Allocate and initialize padata instance.
+ *                         Use the cpu_possible_mask for serial and
+ *                         parallel workers.
+ *
+ * @wq: workqueue to use for the allocated padata instance
+ *
+ * Must be called from a cpus_read_lock() protected region
+ */
+struct padata_instance *padata_alloc_possible(struct workqueue_struct *wq)
+{
+	lockdep_assert_cpus_held();
+	return padata_alloc(wq, cpu_possible_mask, cpu_possible_mask);
+}
+EXPORT_SYMBOL(padata_alloc_possible);
+
+/**
  * padata_free - free a padata instance
  *
  * @padata_inst: padata instance to free
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 9995b2dfaaff..e782e9049e73 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1176,7 +1176,7 @@ static void boot_delay_msec(int level)
 	unsigned long long k;
 	unsigned long timeout;
 
-	if ((boot_delay == 0 || system_state != SYSTEM_BOOTING)
+	if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING)
 		|| suppress_message_printing(level)) {
 		return;
 	}
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 00a45c45beca..ca0f8fc945c6 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -64,6 +64,7 @@
 #include <linux/workqueue.h>
 #include <linux/compiler.h>
 #include <linux/tick.h>
+#include <linux/init.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.
@@ -124,14 +125,27 @@ int sched_clock_stable(void)
 	return static_branch_likely(&__sched_clock_stable);
 }
 
+static void __scd_stamp(struct sched_clock_data *scd)
+{
+	scd->tick_gtod = ktime_get_ns();
+	scd->tick_raw = sched_clock();
+}
+
 static void __set_sched_clock_stable(void)
 {
-	struct sched_clock_data *scd = this_scd();
+	struct sched_clock_data *scd;
 
 	/*
+	 * Since we're still unstable and the tick is already running, we have
+	 * to disable IRQs in order to get a consistent scd->tick* reading.
+	 */
+	local_irq_disable();
+	scd = this_scd();
+	/*
 	 * Attempt to make the (initial) unstable->stable transition continuous.
 	 */
 	__sched_clock_offset = (scd->tick_gtod + __gtod_offset) - (scd->tick_raw);
+	local_irq_enable();
 
 	printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n",
 			scd->tick_gtod, __gtod_offset,
@@ -141,8 +155,38 @@ static void __set_sched_clock_stable(void)
 	tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
 }
 
+/*
+ * If we ever get here, we're screwed, because we found out -- typically after
+ * the fact -- that TSC wasn't good. This means all our clocksources (including
+ * ktime) could have reported wrong values.
+ *
+ * What we do here is an attempt to fix up and continue sort of where we left
+ * off in a coherent manner.
+ *
+ * The only way to fully avoid random clock jumps is to boot with:
+ * "tsc=unstable".
+ */
 static void __sched_clock_work(struct work_struct *work)
 {
+	struct sched_clock_data *scd;
+	int cpu;
+
+	/* take a current timestamp and set 'now' */
+	preempt_disable();
+	scd = this_scd();
+	__scd_stamp(scd);
+	scd->clock = scd->tick_gtod + __gtod_offset;
+	preempt_enable();
+
+	/* clone to all CPUs */
+	for_each_possible_cpu(cpu)
+		per_cpu(sched_clock_data, cpu) = *scd;
+
+	printk(KERN_WARNING "TSC found unstable after boot, most likely due to broken BIOS. Use 'tsc=unstable'.\n");
+	printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
+			scd->tick_gtod, __gtod_offset,
+			scd->tick_raw,  __sched_clock_offset);
+
 	static_branch_disable(&__sched_clock_stable);
 }
 
@@ -150,27 +194,11 @@ static DECLARE_WORK(sched_clock_work, __sched_clock_work);
 
 static void __clear_sched_clock_stable(void)
 {
-	struct sched_clock_data *scd = this_scd();
-
-	/*
-	 * Attempt to make the stable->unstable transition continuous.
-	 *
-	 * Trouble is, this is typically called from the TSC watchdog
-	 * timer, which is late per definition. This means the tick
-	 * values can already be screwy.
-	 *
-	 * Still do what we can.
-	 */
-	__gtod_offset = (scd->tick_raw + __sched_clock_offset) - (scd->tick_gtod);
-
-	printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
-			scd->tick_gtod, __gtod_offset,
-			scd->tick_raw,  __sched_clock_offset);
+	if (!sched_clock_stable())
+		return;
 
 	tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
-
-	if (sched_clock_stable())
-		schedule_work(&sched_clock_work);
+	schedule_work(&sched_clock_work);
 }
 
 void clear_sched_clock_stable(void)
@@ -183,7 +211,11 @@ void clear_sched_clock_stable(void)
 		__clear_sched_clock_stable();
 }
 
-void sched_clock_init_late(void)
+/*
+ * We run this as late_initcall() such that it runs after all built-in drivers,
+ * notably: acpi_processor and intel_idle, which can mark the TSC as unstable.
+ */
+static int __init sched_clock_init_late(void)
 {
 	sched_clock_running = 2;
 	/*
@@ -197,7 +229,10 @@ void sched_clock_init_late(void)
 
 	if (__sched_clock_stable_early)
 		__set_sched_clock_stable();
+
+	return 0;
 }
+late_initcall(sched_clock_init_late);
 
 /*
  * min, max except they take wrapping into account
@@ -347,21 +382,38 @@ void sched_clock_tick(void)
 {
 	struct sched_clock_data *scd;
 
+	if (sched_clock_stable())
+		return;
+
+	if (unlikely(!sched_clock_running))
+		return;
+
 	WARN_ON_ONCE(!irqs_disabled());
 
+	scd = this_scd();
+	__scd_stamp(scd);
+	sched_clock_local(scd);
+}
+
+void sched_clock_tick_stable(void)
+{
+	u64 gtod, clock;
+
+	if (!sched_clock_stable())
+		return;
+
 	/*
-	 * Update these values even if sched_clock_stable(), because it can
-	 * become unstable at any point in time at which point we need some
-	 * values to fall back on.
+	 * Called under watchdog_lock.
 	 *
-	 * XXX arguably we can skip this if we expose tsc_clocksource_reliable
+	 * The watchdog just found this TSC to (still) be stable, so now is a
+	 * good moment to update our __gtod_offset. Because once we find the
+	 * TSC to be unstable, any computation will be computing crap.
 	 */
-	scd = this_scd();
-	scd->tick_raw  = sched_clock();
-	scd->tick_gtod = ktime_get_ns();
-
-	if (!sched_clock_stable() && likely(sched_clock_running))
-		sched_clock_local(scd);
+	local_irq_disable();
+	gtod = ktime_get_ns();
+	clock = sched_clock();
+	__gtod_offset = (clock + __sched_clock_offset) - gtod;
+	local_irq_enable();
 }
 
 /*
@@ -374,15 +426,21 @@ void sched_clock_idle_sleep_event(void)
 EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
 
 /*
- * We just idled delta nanoseconds (called with irqs disabled):
+ * We just idled; resync with ktime.
  */
-void sched_clock_idle_wakeup_event(u64 delta_ns)
+void sched_clock_idle_wakeup_event(void)
 {
-	if (timekeeping_suspended)
+	unsigned long flags;
+
+	if (sched_clock_stable())
+		return;
+
+	if (unlikely(timekeeping_suspended))
 		return;
 
+	local_irq_save(flags);
 	sched_clock_tick();
-	touch_softlockup_watchdog_sched();
+	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 803c3bc274c4..c3e50cada84d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1731,7 +1731,7 @@ void sched_ttwu_pending(void)
 {
 	struct rq *rq = this_rq();
 	struct llist_node *llist = llist_del_all(&rq->wake_list);
-	struct task_struct *p;
+	struct task_struct *p, *t;
 	struct rq_flags rf;
 
 	if (!llist)
@@ -1740,17 +1740,8 @@ void sched_ttwu_pending(void)
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 
-	while (llist) {
-		int wake_flags = 0;
-
-		p = llist_entry(llist, struct task_struct, wake_entry);
-		llist = llist_next(llist);
-
-		if (p->sched_remote_wakeup)
-			wake_flags = WF_MIGRATED;
-
-		ttwu_do_activate(rq, p, wake_flags, &rf);
-	}
+	llist_for_each_entry_safe(p, t, llist, wake_entry)
+		ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);
 
 	rq_unlock_irqrestore(rq, &rf);
 }
@@ -4197,8 +4188,8 @@ static int __sched_setscheduler(struct task_struct *p,
 	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 	struct rq *rq;
 
-	/* May grab non-irq protected spin_locks: */
-	BUG_ON(in_interrupt());
+	/* The pi code expects interrupts enabled */
+	BUG_ON(pi && in_interrupt());
 recheck:
 	/* Double check policy once rq lock held: */
 	if (policy < 0) {
@@ -5958,7 +5949,6 @@ void __init sched_init_smp(void)
 	cpumask_var_t non_isolated_cpus;
 
 	alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
-	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
 
 	sched_init_numa();
 
@@ -5968,7 +5958,7 @@ void __init sched_init_smp(void)
 	 * happen.
 	 */
 	mutex_lock(&sched_domains_mutex);
-	init_sched_domains(cpu_active_mask);
+	sched_init_domains(cpu_active_mask);
 	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
 	if (cpumask_empty(non_isolated_cpus))
 		cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
@@ -5984,7 +5974,6 @@ void __init sched_init_smp(void)
 	init_sched_dl_class();
 
 	sched_init_smt();
-	sched_clock_init_late();
 
 	sched_smp_initialized = true;
 }
@@ -6000,7 +5989,6 @@ early_initcall(migration_init);
 void __init sched_init_smp(void)
 {
 	sched_init_granularity();
-	sched_clock_init_late();
 }
 #endif /* CONFIG_SMP */
 
@@ -6199,7 +6187,6 @@ void __init sched_init(void)
 	calc_load_update = jiffies + LOAD_FREQ;
 
 #ifdef CONFIG_SMP
-	zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT);
 	/* May be allocated at isolcpus cmdline parse time */
 	if (cpu_isolated_map == NULL)
 		zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
@@ -6251,8 +6238,10 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
 
 	if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
 	     !is_idle_task(current)) ||
-	    system_state != SYSTEM_RUNNING || oops_in_progress)
+	    system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING ||
+	    oops_in_progress)
 		return;
+
 	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
 		return;
 	prev_jiffy = jiffies;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index a2ce59015642..df6c2912bd60 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1533,7 +1533,7 @@ retry:
 		 * then possible that next_task has migrated.
 		 */
 		task = pick_next_pushable_dl_task(rq);
-		if (task_cpu(next_task) == rq->cpu && task == next_task) {
+		if (task == next_task) {
 			/*
 			 * The task is still there. We don't try
 			 * again, some other cpu will pull it when ready.
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d71109321841..47a0c552c77b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -369,8 +369,9 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 }
 
 /* Iterate thr' all leaf cfs_rq's on a runqueue */
-#define for_each_leaf_cfs_rq(rq, cfs_rq) \
-	list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
+#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)			\
+	list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list,	\
+				 leaf_cfs_rq_list)
 
 /* Do the two (enqueued) entities belong to the same group ? */
 static inline struct cfs_rq *
@@ -463,8 +464,8 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 {
 }
 
-#define for_each_leaf_cfs_rq(rq, cfs_rq) \
-		for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
+#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)	\
+		for (cfs_rq = &rq->cfs, pos = NULL; cfs_rq; cfs_rq = pos)
 
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
 {
@@ -2469,7 +2470,8 @@ void task_numa_work(struct callback_head *work)
 		return;
 
 
-	down_read(&mm->mmap_sem);
+	if (!down_read_trylock(&mm->mmap_sem))
+		return;
 	vma = find_vma(mm, start);
 	if (!vma) {
 		reset_ptenuma_scan(p);
@@ -2916,12 +2918,12 @@ ___update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 	/*
 	 * Step 2: update *_avg.
 	 */
-	sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX);
+	sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib);
 	if (cfs_rq) {
 		cfs_rq->runnable_load_avg =
-			div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
+			div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib);
 	}
-	sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
+	sa->util_avg = sa->util_sum / (LOAD_AVG_MAX - 1024 + sa->period_contrib);
 
 	return 1;
 }
@@ -4642,24 +4644,43 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	hrtimer_cancel(&cfs_b->slack_timer);
 }
 
+/*
+ * Both these cpu hotplug callbacks race against unregister_fair_sched_group()
+ *
+ * The race is harmless, since modifying bandwidth settings of unhooked group
+ * bits doesn't do much.
+ */
+
+/* cpu online calback */
 static void __maybe_unused update_runtime_enabled(struct rq *rq)
 {
-	struct cfs_rq *cfs_rq;
+	struct task_group *tg;
 
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
-		struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth;
+	lockdep_assert_held(&rq->lock);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(tg, &task_groups, list) {
+		struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
+		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
 
 		raw_spin_lock(&cfs_b->lock);
 		cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF;
 		raw_spin_unlock(&cfs_b->lock);
 	}
+	rcu_read_unlock();
 }
 
+/* cpu offline callback */
 static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 {
-	struct cfs_rq *cfs_rq;
+	struct task_group *tg;
+
+	lockdep_assert_held(&rq->lock);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(tg, &task_groups, list) {
+		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
 
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
 		if (!cfs_rq->runtime_enabled)
 			continue;
 
@@ -4677,6 +4698,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 		if (cfs_rq_throttled(cfs_rq))
 			unthrottle_cfs_rq(cfs_rq);
 	}
+	rcu_read_unlock();
 }
 
 #else /* CONFIG_CFS_BANDWIDTH */
@@ -5484,12 +5506,12 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		int i;
 
 		/* Skip over this group if it has no CPUs allowed */
-		if (!cpumask_intersects(sched_group_cpus(group),
+		if (!cpumask_intersects(sched_group_span(group),
 					&p->cpus_allowed))
 			continue;
 
 		local_group = cpumask_test_cpu(this_cpu,
-					       sched_group_cpus(group));
+					       sched_group_span(group));
 
 		/*
 		 * Tally up the load of all CPUs in the group and find
@@ -5499,7 +5521,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		runnable_load = 0;
 		max_spare_cap = 0;
 
-		for_each_cpu(i, sched_group_cpus(group)) {
+		for_each_cpu(i, sched_group_span(group)) {
 			/* Bias balancing toward cpus of our domain */
 			if (local_group)
 				load = source_load(i, load_idx);
@@ -5602,10 +5624,10 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 
 	/* Check if we have any choice: */
 	if (group->group_weight == 1)
-		return cpumask_first(sched_group_cpus(group));
+		return cpumask_first(sched_group_span(group));
 
 	/* Traverse only the allowed CPUs */
-	for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) {
+	for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) {
 		if (idle_cpu(i)) {
 			struct rq *rq = cpu_rq(i);
 			struct cpuidle_state *idle = idle_get_state(rq);
@@ -5640,43 +5662,6 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
 }
 
-/*
- * Implement a for_each_cpu() variant that starts the scan at a given cpu
- * (@start), and wraps around.
- *
- * This is used to scan for idle CPUs; such that not all CPUs looking for an
- * idle CPU find the same CPU. The down-side is that tasks tend to cycle
- * through the LLC domain.
- *
- * Especially tbench is found sensitive to this.
- */
-
-static int cpumask_next_wrap(int n, const struct cpumask *mask, int start, int *wrapped)
-{
-	int next;
-
-again:
-	next = find_next_bit(cpumask_bits(mask), nr_cpumask_bits, n+1);
-
-	if (*wrapped) {
-		if (next >= start)
-			return nr_cpumask_bits;
-	} else {
-		if (next >= nr_cpumask_bits) {
-			*wrapped = 1;
-			n = -1;
-			goto again;
-		}
-	}
-
-	return next;
-}
-
-#define for_each_cpu_wrap(cpu, mask, start, wrap)				\
-	for ((wrap) = 0, (cpu) = (start)-1;					\
-		(cpu) = cpumask_next_wrap((cpu), (mask), (start), &(wrap)),	\
-		(cpu) < nr_cpumask_bits; )
-
 #ifdef CONFIG_SCHED_SMT
 
 static inline void set_idle_cores(int cpu, int val)
@@ -5736,7 +5721,7 @@ unlock:
 static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
-	int core, cpu, wrap;
+	int core, cpu;
 
 	if (!static_branch_likely(&sched_smt_present))
 		return -1;
@@ -5746,7 +5731,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
 
 	cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed);
 
-	for_each_cpu_wrap(core, cpus, target, wrap) {
+	for_each_cpu_wrap(core, cpus, target) {
 		bool idle = true;
 
 		for_each_cpu(cpu, cpu_smt_mask(core)) {
@@ -5812,7 +5797,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 	u64 avg_cost, avg_idle = this_rq()->avg_idle;
 	u64 time, cost;
 	s64 delta;
-	int cpu, wrap;
+	int cpu;
 
 	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
 	if (!this_sd)
@@ -5829,7 +5814,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 
 	time = local_clock();
 
-	for_each_cpu_wrap(cpu, sched_domain_span(sd), target, wrap) {
+	for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
 		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
 			continue;
 		if (idle_cpu(cpu))
@@ -6970,10 +6955,28 @@ static void attach_tasks(struct lb_env *env)
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+
+static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
+{
+	if (cfs_rq->load.weight)
+		return false;
+
+	if (cfs_rq->avg.load_sum)
+		return false;
+
+	if (cfs_rq->avg.util_sum)
+		return false;
+
+	if (cfs_rq->runnable_load_sum)
+		return false;
+
+	return true;
+}
+
 static void update_blocked_averages(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	struct cfs_rq *cfs_rq;
+	struct cfs_rq *cfs_rq, *pos;
 	struct rq_flags rf;
 
 	rq_lock_irqsave(rq, &rf);
@@ -6983,7 +6986,7 @@ static void update_blocked_averages(int cpu)
 	 * Iterates the task_group tree in a bottom up fashion, see
 	 * list_add_leaf_cfs_rq() for details.
 	 */
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
+	for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) {
 		struct sched_entity *se;
 
 		/* throttled entities do not contribute to load */
@@ -6997,6 +7000,13 @@ static void update_blocked_averages(int cpu)
 		se = cfs_rq->tg->se[cpu];
 		if (se && !skip_blocked_update(se))
 			update_load_avg(se, 0);
+
+		/*
+		 * There can be a lot of idle CPU cgroups.  Don't let fully
+		 * decayed cfs_rqs linger on the list.
+		 */
+		if (cfs_rq_is_decayed(cfs_rq))
+			list_del_leaf_cfs_rq(cfs_rq);
 	}
 	rq_unlock_irqrestore(rq, &rf);
 }
@@ -7229,7 +7239,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 		 * span the current group.
 		 */
 
-		for_each_cpu(cpu, sched_group_cpus(sdg)) {
+		for_each_cpu(cpu, sched_group_span(sdg)) {
 			struct sched_group_capacity *sgc;
 			struct rq *rq = cpu_rq(cpu);
 
@@ -7408,7 +7418,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
 	memset(sgs, 0, sizeof(*sgs));
 
-	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
+	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
 		struct rq *rq = cpu_rq(i);
 
 		/* Bias balancing toward cpus of our domain */
@@ -7572,7 +7582,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 		struct sg_lb_stats *sgs = &tmp_sgs;
 		int local_group;
 
-		local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
+		local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(sg));
 		if (local_group) {
 			sds->local = sg;
 			sgs = local;
@@ -7927,7 +7937,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 	unsigned long busiest_load = 0, busiest_capacity = 1;
 	int i;
 
-	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
+	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
 		unsigned long capacity, wl;
 		enum fbq_type rt;
 
@@ -8033,7 +8043,6 @@ static int active_load_balance_cpu_stop(void *data);
 static int should_we_balance(struct lb_env *env)
 {
 	struct sched_group *sg = env->sd->groups;
-	struct cpumask *sg_cpus, *sg_mask;
 	int cpu, balance_cpu = -1;
 
 	/*
@@ -8043,11 +8052,9 @@ static int should_we_balance(struct lb_env *env)
 	if (env->idle == CPU_NEWLY_IDLE)
 		return 1;
 
-	sg_cpus = sched_group_cpus(sg);
-	sg_mask = sched_group_mask(sg);
 	/* Try to find first idle cpu */
-	for_each_cpu_and(cpu, sg_cpus, env->cpus) {
-		if (!cpumask_test_cpu(cpu, sg_mask) || !idle_cpu(cpu))
+	for_each_cpu_and(cpu, group_balance_mask(sg), env->cpus) {
+		if (!idle_cpu(cpu))
 			continue;
 
 		balance_cpu = cpu;
@@ -8083,7 +8090,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		.sd		= sd,
 		.dst_cpu	= this_cpu,
 		.dst_rq		= this_rq,
-		.dst_grpmask    = sched_group_cpus(sd->groups),
+		.dst_grpmask    = sched_group_span(sd->groups),
 		.idle		= idle,
 		.loop_break	= sched_nr_migrate_break,
 		.cpus		= cpus,
@@ -9523,10 +9530,10 @@ const struct sched_class fair_sched_class = {
 #ifdef CONFIG_SCHED_DEBUG
 void print_cfs_stats(struct seq_file *m, int cpu)
 {
-	struct cfs_rq *cfs_rq;
+	struct cfs_rq *cfs_rq, *pos;
 
 	rcu_read_lock();
-	for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
+	for_each_leaf_cfs_rq_safe(cpu_rq(cpu), cfs_rq, pos)
 		print_cfs_rq(m, cpu, cfs_rq);
 	rcu_read_unlock();
 }
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 11192e0cb122..dc4d1483b038 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -76,7 +76,6 @@ SCHED_FEAT(WARN_DOUBLE_CLOCK, false)
 SCHED_FEAT(RT_PUSH_IPI, true)
 #endif
 
-SCHED_FEAT(FORCE_SD_OVERLAP, false)
 SCHED_FEAT(RT_RUNTIME_SHARE, true)
 SCHED_FEAT(LB_MIN, false)
 SCHED_FEAT(ATTACH_AGE_LOAD, true)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 979b7341008a..581d5c7a5264 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -840,6 +840,17 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 		int enqueue = 0;
 		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
 		struct rq *rq = rq_of_rt_rq(rt_rq);
+		int skip;
+
+		/*
+		 * When span == cpu_online_mask, taking each rq->lock
+		 * can be time-consuming. Try to avoid it when possible.
+		 */
+		raw_spin_lock(&rt_rq->rt_runtime_lock);
+		skip = !rt_rq->rt_time && !rt_rq->rt_nr_running;
+		raw_spin_unlock(&rt_rq->rt_runtime_lock);
+		if (skip)
+			continue;
 
 		raw_spin_lock(&rq->lock);
 		if (rt_rq->rt_time) {
@@ -1819,7 +1830,7 @@ retry:
 		 * pushing.
 		 */
 		task = pick_next_pushable_task(rq);
-		if (task_cpu(next_task) == rq->cpu && task == next_task) {
+		if (task == next_task) {
 			/*
 			 * The task hasn't migrated, and is still the next
 			 * eligible task, but we failed to find a run-queue
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6dda2aab731e..f8cf1d87f065 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -606,11 +606,9 @@ struct root_domain {
 
 extern struct root_domain def_root_domain;
 extern struct mutex sched_domains_mutex;
-extern cpumask_var_t fallback_doms;
-extern cpumask_var_t sched_domains_tmpmask;
 
 extern void init_defrootdomain(void);
-extern int init_sched_domains(const struct cpumask *cpu_map);
+extern int sched_init_domains(const struct cpumask *cpu_map);
 extern void rq_attach_root(struct rq *rq, struct root_domain *rd);
 
 #endif /* CONFIG_SMP */
@@ -1025,7 +1023,11 @@ struct sched_group_capacity {
 	unsigned long next_update;
 	int imbalance; /* XXX unrelated to capacity but shared group state */
 
-	unsigned long cpumask[0]; /* iteration mask */
+#ifdef CONFIG_SCHED_DEBUG
+	int id;
+#endif
+
+	unsigned long cpumask[0]; /* balance mask */
 };
 
 struct sched_group {
@@ -1046,16 +1048,15 @@ struct sched_group {
 	unsigned long cpumask[0];
 };
 
-static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
+static inline struct cpumask *sched_group_span(struct sched_group *sg)
 {
 	return to_cpumask(sg->cpumask);
 }
 
 /*
- * cpumask masking which cpus in the group are allowed to iterate up the domain
- * tree.
+ * See build_balance_mask().
  */
-static inline struct cpumask *sched_group_mask(struct sched_group *sg)
+static inline struct cpumask *group_balance_mask(struct sched_group *sg)
 {
 	return to_cpumask(sg->sgc->cpumask);
 }
@@ -1066,7 +1067,7 @@ static inline struct cpumask *sched_group_mask(struct sched_group *sg)
  */
 static inline unsigned int group_first_cpu(struct sched_group *group)
 {
-	return cpumask_first(sched_group_cpus(group));
+	return cpumask_first(sched_group_span(group));
 }
 
 extern int group_balance_cpu(struct sched_group *sg);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 1b0b4fb12837..79895aec281e 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -10,6 +10,7 @@ DEFINE_MUTEX(sched_domains_mutex);
 
 /* Protected by sched_domains_mutex: */
 cpumask_var_t sched_domains_tmpmask;
+cpumask_var_t sched_domains_tmpmask2;
 
 #ifdef CONFIG_SCHED_DEBUG
 
@@ -35,7 +36,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 
 	cpumask_clear(groupmask);
 
-	printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
+	printk(KERN_DEBUG "%*s domain-%d: ", level, "", level);
 
 	if (!(sd->flags & SD_LOAD_BALANCE)) {
 		printk("does not load-balance\n");
@@ -45,14 +46,14 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		return -1;
 	}
 
-	printk(KERN_CONT "span %*pbl level %s\n",
+	printk(KERN_CONT "span=%*pbl level=%s\n",
 	       cpumask_pr_args(sched_domain_span(sd)), sd->name);
 
 	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
 		printk(KERN_ERR "ERROR: domain->span does not contain "
 				"CPU%d\n", cpu);
 	}
-	if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
+	if (!cpumask_test_cpu(cpu, sched_group_span(group))) {
 		printk(KERN_ERR "ERROR: domain->groups does not contain"
 				" CPU%d\n", cpu);
 	}
@@ -65,29 +66,47 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		if (!cpumask_weight(sched_group_cpus(group))) {
+		if (!cpumask_weight(sched_group_span(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: empty group\n");
 			break;
 		}
 
 		if (!(sd->flags & SD_OVERLAP) &&
-		    cpumask_intersects(groupmask, sched_group_cpus(group))) {
+		    cpumask_intersects(groupmask, sched_group_span(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: repeated CPUs\n");
 			break;
 		}
 
-		cpumask_or(groupmask, groupmask, sched_group_cpus(group));
+		cpumask_or(groupmask, groupmask, sched_group_span(group));
 
-		printk(KERN_CONT " %*pbl",
-		       cpumask_pr_args(sched_group_cpus(group)));
-		if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
-			printk(KERN_CONT " (cpu_capacity = %lu)",
-				group->sgc->capacity);
+		printk(KERN_CONT " %d:{ span=%*pbl",
+				group->sgc->id,
+				cpumask_pr_args(sched_group_span(group)));
+
+		if ((sd->flags & SD_OVERLAP) &&
+		    !cpumask_equal(group_balance_mask(group), sched_group_span(group))) {
+			printk(KERN_CONT " mask=%*pbl",
+				cpumask_pr_args(group_balance_mask(group)));
+		}
+
+		if (group->sgc->capacity != SCHED_CAPACITY_SCALE)
+			printk(KERN_CONT " cap=%lu", group->sgc->capacity);
+
+		if (group == sd->groups && sd->child &&
+		    !cpumask_equal(sched_domain_span(sd->child),
+				   sched_group_span(group))) {
+			printk(KERN_ERR "ERROR: domain->groups does not match domain->child\n");
 		}
 
+		printk(KERN_CONT " }");
+
 		group = group->next;
+
+		if (group != sd->groups)
+			printk(KERN_CONT ",");
+
 	} while (group != sd->groups);
 	printk(KERN_CONT "\n");
 
@@ -113,7 +132,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 		return;
 	}
 
-	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
+	printk(KERN_DEBUG "CPU%d attaching sched-domain(s):\n", cpu);
 
 	for (;;) {
 		if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
@@ -477,46 +496,214 @@ enum s_alloc {
 };
 
 /*
- * Build an iteration mask that can exclude certain CPUs from the upwards
- * domain traversal.
+ * Return the canonical balance CPU for this group, this is the first CPU
+ * of this group that's also in the balance mask.
  *
- * Asymmetric node setups can result in situations where the domain tree is of
- * unequal depth, make sure to skip domains that already cover the entire
- * range.
+ * The balance mask are all those CPUs that could actually end up at this
+ * group. See build_balance_mask().
  *
- * In that case build_sched_domains() will have terminated the iteration early
- * and our sibling sd spans will be empty. Domains should always include the
- * CPU they're built on, so check that.
+ * Also see should_we_balance().
  */
-static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
+int group_balance_cpu(struct sched_group *sg)
 {
-	const struct cpumask *span = sched_domain_span(sd);
+	return cpumask_first(group_balance_mask(sg));
+}
+
+
+/*
+ * NUMA topology (first read the regular topology blurb below)
+ *
+ * Given a node-distance table, for example:
+ *
+ *   node   0   1   2   3
+ *     0:  10  20  30  20
+ *     1:  20  10  20  30
+ *     2:  30  20  10  20
+ *     3:  20  30  20  10
+ *
+ * which represents a 4 node ring topology like:
+ *
+ *   0 ----- 1
+ *   |       |
+ *   |       |
+ *   |       |
+ *   3 ----- 2
+ *
+ * We want to construct domains and groups to represent this. The way we go
+ * about doing this is to build the domains on 'hops'. For each NUMA level we
+ * construct the mask of all nodes reachable in @level hops.
+ *
+ * For the above NUMA topology that gives 3 levels:
+ *
+ * NUMA-2	0-3		0-3		0-3		0-3
+ *  groups:	{0-1,3},{1-3}	{0-2},{0,2-3}	{1-3},{0-1,3}	{0,2-3},{0-2}
+ *
+ * NUMA-1	0-1,3		0-2		1-3		0,2-3
+ *  groups:	{0},{1},{3}	{0},{1},{2}	{1},{2},{3}	{0},{2},{3}
+ *
+ * NUMA-0	0		1		2		3
+ *
+ *
+ * As can be seen; things don't nicely line up as with the regular topology.
+ * When we iterate a domain in child domain chunks some nodes can be
+ * represented multiple times -- hence the "overlap" naming for this part of
+ * the topology.
+ *
+ * In order to minimize this overlap, we only build enough groups to cover the
+ * domain. For instance Node-0 NUMA-2 would only get groups: 0-1,3 and 1-3.
+ *
+ * Because:
+ *
+ *  - the first group of each domain is its child domain; this
+ *    gets us the first 0-1,3
+ *  - the only uncovered node is 2, who's child domain is 1-3.
+ *
+ * However, because of the overlap, computing a unique CPU for each group is
+ * more complicated. Consider for instance the groups of NODE-1 NUMA-2, both
+ * groups include the CPUs of Node-0, while those CPUs would not in fact ever
+ * end up at those groups (they would end up in group: 0-1,3).
+ *
+ * To correct this we have to introduce the group balance mask. This mask
+ * will contain those CPUs in the group that can reach this group given the
+ * (child) domain tree.
+ *
+ * With this we can once again compute balance_cpu and sched_group_capacity
+ * relations.
+ *
+ * XXX include words on how balance_cpu is unique and therefore can be
+ * used for sched_group_capacity links.
+ *
+ *
+ * Another 'interesting' topology is:
+ *
+ *   node   0   1   2   3
+ *     0:  10  20  20  30
+ *     1:  20  10  20  20
+ *     2:  20  20  10  20
+ *     3:  30  20  20  10
+ *
+ * Which looks a little like:
+ *
+ *   0 ----- 1
+ *   |     / |
+ *   |   /   |
+ *   | /     |
+ *   2 ----- 3
+ *
+ * This topology is asymmetric, nodes 1,2 are fully connected, but nodes 0,3
+ * are not.
+ *
+ * This leads to a few particularly weird cases where the sched_domain's are
+ * not of the same number for each cpu. Consider:
+ *
+ * NUMA-2	0-3						0-3
+ *  groups:	{0-2},{1-3}					{1-3},{0-2}
+ *
+ * NUMA-1	0-2		0-3		0-3		1-3
+ *
+ * NUMA-0	0		1		2		3
+ *
+ */
+
+
+/*
+ * Build the balance mask; it contains only those CPUs that can arrive at this
+ * group and should be considered to continue balancing.
+ *
+ * We do this during the group creation pass, therefore the group information
+ * isn't complete yet, however since each group represents a (child) domain we
+ * can fully construct this using the sched_domain bits (which are already
+ * complete).
+ */
+static void
+build_balance_mask(struct sched_domain *sd, struct sched_group *sg, struct cpumask *mask)
+{
+	const struct cpumask *sg_span = sched_group_span(sg);
 	struct sd_data *sdd = sd->private;
 	struct sched_domain *sibling;
 	int i;
 
-	for_each_cpu(i, span) {
+	cpumask_clear(mask);
+
+	for_each_cpu(i, sg_span) {
 		sibling = *per_cpu_ptr(sdd->sd, i);
-		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+
+		/*
+		 * Can happen in the asymmetric case, where these siblings are
+		 * unused. The mask will not be empty because those CPUs that
+		 * do have the top domain _should_ span the domain.
+		 */
+		if (!sibling->child)
 			continue;
 
-		cpumask_set_cpu(i, sched_group_mask(sg));
+		/* If we would not end up here, we can't continue from here */
+		if (!cpumask_equal(sg_span, sched_domain_span(sibling->child)))
+			continue;
+
+		cpumask_set_cpu(i, mask);
 	}
+
+	/* We must not have empty masks here */
+	WARN_ON_ONCE(cpumask_empty(mask));
 }
 
 /*
- * Return the canonical balance CPU for this group, this is the first CPU
- * of this group that's also in the iteration mask.
+ * XXX: This creates per-node group entries; since the load-balancer will
+ * immediately access remote memory to construct this group's load-balance
+ * statistics having the groups node local is of dubious benefit.
  */
-int group_balance_cpu(struct sched_group *sg)
+static struct sched_group *
+build_group_from_child_sched_domain(struct sched_domain *sd, int cpu)
 {
-	return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg));
+	struct sched_group *sg;
+	struct cpumask *sg_span;
+
+	sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
+			GFP_KERNEL, cpu_to_node(cpu));
+
+	if (!sg)
+		return NULL;
+
+	sg_span = sched_group_span(sg);
+	if (sd->child)
+		cpumask_copy(sg_span, sched_domain_span(sd->child));
+	else
+		cpumask_copy(sg_span, sched_domain_span(sd));
+
+	return sg;
+}
+
+static void init_overlap_sched_group(struct sched_domain *sd,
+				     struct sched_group *sg)
+{
+	struct cpumask *mask = sched_domains_tmpmask2;
+	struct sd_data *sdd = sd->private;
+	struct cpumask *sg_span;
+	int cpu;
+
+	build_balance_mask(sd, sg, mask);
+	cpu = cpumask_first_and(sched_group_span(sg), mask);
+
+	sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
+	if (atomic_inc_return(&sg->sgc->ref) == 1)
+		cpumask_copy(group_balance_mask(sg), mask);
+	else
+		WARN_ON_ONCE(!cpumask_equal(group_balance_mask(sg), mask));
+
+	/*
+	 * Initialize sgc->capacity such that even if we mess up the
+	 * domains and no possible iteration will get us here, we won't
+	 * die on a /0 trap.
+	 */
+	sg_span = sched_group_span(sg);
+	sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
+	sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
 }
 
 static int
 build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 {
-	struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg;
+	struct sched_group *first = NULL, *last = NULL, *sg;
 	const struct cpumask *span = sched_domain_span(sd);
 	struct cpumask *covered = sched_domains_tmpmask;
 	struct sd_data *sdd = sd->private;
@@ -525,7 +712,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 
 	cpumask_clear(covered);
 
-	for_each_cpu(i, span) {
+	for_each_cpu_wrap(i, span, cpu) {
 		struct cpumask *sg_span;
 
 		if (cpumask_test_cpu(i, covered))
@@ -533,44 +720,27 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 
 		sibling = *per_cpu_ptr(sdd->sd, i);
 
-		/* See the comment near build_group_mask(). */
+		/*
+		 * Asymmetric node setups can result in situations where the
+		 * domain tree is of unequal depth, make sure to skip domains
+		 * that already cover the entire range.
+		 *
+		 * In that case build_sched_domains() will have terminated the
+		 * iteration early and our sibling sd spans will be empty.
+		 * Domains should always include the CPU they're built on, so
+		 * check that.
+		 */
 		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
 			continue;
 
-		sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
-				GFP_KERNEL, cpu_to_node(cpu));
-
+		sg = build_group_from_child_sched_domain(sibling, cpu);
 		if (!sg)
 			goto fail;
 
-		sg_span = sched_group_cpus(sg);
-		if (sibling->child)
-			cpumask_copy(sg_span, sched_domain_span(sibling->child));
-		else
-			cpumask_set_cpu(i, sg_span);
-
+		sg_span = sched_group_span(sg);
 		cpumask_or(covered, covered, sg_span);
 
-		sg->sgc = *per_cpu_ptr(sdd->sgc, i);
-		if (atomic_inc_return(&sg->sgc->ref) == 1)
-			build_group_mask(sd, sg);
-
-		/*
-		 * Initialize sgc->capacity such that even if we mess up the
-		 * domains and no possible iteration will get us here, we won't
-		 * die on a /0 trap.
-		 */
-		sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
-		sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
-
-		/*
-		 * Make sure the first group of this domain contains the
-		 * canonical balance CPU. Otherwise the sched_domain iteration
-		 * breaks. See update_sg_lb_stats().
-		 */
-		if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
-		    group_balance_cpu(sg) == cpu)
-			groups = sg;
+		init_overlap_sched_group(sd, sg);
 
 		if (!first)
 			first = sg;
@@ -579,7 +749,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 		last = sg;
 		last->next = first;
 	}
-	sd->groups = groups;
+	sd->groups = first;
 
 	return 0;
 
@@ -589,23 +759,106 @@ fail:
 	return -ENOMEM;
 }
 
-static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
+
+/*
+ * Package topology (also see the load-balance blurb in fair.c)
+ *
+ * The scheduler builds a tree structure to represent a number of important
+ * topology features. By default (default_topology[]) these include:
+ *
+ *  - Simultaneous multithreading (SMT)
+ *  - Multi-Core Cache (MC)
+ *  - Package (DIE)
+ *
+ * Where the last one more or less denotes everything up to a NUMA node.
+ *
+ * The tree consists of 3 primary data structures:
+ *
+ *	sched_domain -> sched_group -> sched_group_capacity
+ *	    ^ ^             ^ ^
+ *          `-'             `-'
+ *
+ * The sched_domains are per-cpu and have a two way link (parent & child) and
+ * denote the ever growing mask of CPUs belonging to that level of topology.
+ *
+ * Each sched_domain has a circular (double) linked list of sched_group's, each
+ * denoting the domains of the level below (or individual CPUs in case of the
+ * first domain level). The sched_group linked by a sched_domain includes the
+ * CPU of that sched_domain [*].
+ *
+ * Take for instance a 2 threaded, 2 core, 2 cache cluster part:
+ *
+ * CPU   0   1   2   3   4   5   6   7
+ *
+ * DIE  [                             ]
+ * MC   [             ] [             ]
+ * SMT  [     ] [     ] [     ] [     ]
+ *
+ *  - or -
+ *
+ * DIE  0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7
+ * MC	0-3 0-3 0-3 0-3 4-7 4-7 4-7 4-7
+ * SMT  0-1 0-1 2-3 2-3 4-5 4-5 6-7 6-7
+ *
+ * CPU   0   1   2   3   4   5   6   7
+ *
+ * One way to think about it is: sched_domain moves you up and down among these
+ * topology levels, while sched_group moves you sideways through it, at child
+ * domain granularity.
+ *
+ * sched_group_capacity ensures each unique sched_group has shared storage.
+ *
+ * There are two related construction problems, both require a CPU that
+ * uniquely identify each group (for a given domain):
+ *
+ *  - The first is the balance_cpu (see should_we_balance() and the
+ *    load-balance blub in fair.c); for each group we only want 1 CPU to
+ *    continue balancing at a higher domain.
+ *
+ *  - The second is the sched_group_capacity; we want all identical groups
+ *    to share a single sched_group_capacity.
+ *
+ * Since these topologies are exclusive by construction. That is, its
+ * impossible for an SMT thread to belong to multiple cores, and cores to
+ * be part of multiple caches. There is a very clear and unique location
+ * for each CPU in the hierarchy.
+ *
+ * Therefore computing a unique CPU for each group is trivial (the iteration
+ * mask is redundant and set all 1s; all CPUs in a group will end up at _that_
+ * group), we can simply pick the first CPU in each group.
+ *
+ *
+ * [*] in other words, the first group of each domain is its child domain.
+ */
+
+static struct sched_group *get_group(int cpu, struct sd_data *sdd)
 {
 	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
 	struct sched_domain *child = sd->child;
+	struct sched_group *sg;
 
 	if (child)
 		cpu = cpumask_first(sched_domain_span(child));
 
-	if (sg) {
-		*sg = *per_cpu_ptr(sdd->sg, cpu);
-		(*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu);
+	sg = *per_cpu_ptr(sdd->sg, cpu);
+	sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
+
+	/* For claim_allocations: */
+	atomic_inc(&sg->ref);
+	atomic_inc(&sg->sgc->ref);
 
-		/* For claim_allocations: */
-		atomic_set(&(*sg)->sgc->ref, 1);
+	if (child) {
+		cpumask_copy(sched_group_span(sg), sched_domain_span(child));
+		cpumask_copy(group_balance_mask(sg), sched_group_span(sg));
+	} else {
+		cpumask_set_cpu(cpu, sched_group_span(sg));
+		cpumask_set_cpu(cpu, group_balance_mask(sg));
 	}
 
-	return cpu;
+	sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sched_group_span(sg));
+	sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
+
+	return sg;
 }
 
 /*
@@ -624,34 +877,20 @@ build_sched_groups(struct sched_domain *sd, int cpu)
 	struct cpumask *covered;
 	int i;
 
-	get_group(cpu, sdd, &sd->groups);
-	atomic_inc(&sd->groups->ref);
-
-	if (cpu != cpumask_first(span))
-		return 0;
-
 	lockdep_assert_held(&sched_domains_mutex);
 	covered = sched_domains_tmpmask;
 
 	cpumask_clear(covered);
 
-	for_each_cpu(i, span) {
+	for_each_cpu_wrap(i, span, cpu) {
 		struct sched_group *sg;
-		int group, j;
 
 		if (cpumask_test_cpu(i, covered))
 			continue;
 
-		group = get_group(i, sdd, &sg);
-		cpumask_setall(sched_group_mask(sg));
+		sg = get_group(i, sdd);
 
-		for_each_cpu(j, span) {
-			if (get_group(j, sdd, NULL) != group)
-				continue;
-
-			cpumask_set_cpu(j, covered);
-			cpumask_set_cpu(j, sched_group_cpus(sg));
-		}
+		cpumask_or(covered, covered, sched_group_span(sg));
 
 		if (!first)
 			first = sg;
@@ -660,6 +899,7 @@ build_sched_groups(struct sched_domain *sd, int cpu)
 		last = sg;
 	}
 	last->next = first;
+	sd->groups = first;
 
 	return 0;
 }
@@ -683,12 +923,12 @@ static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
 	do {
 		int cpu, max_cpu = -1;
 
-		sg->group_weight = cpumask_weight(sched_group_cpus(sg));
+		sg->group_weight = cpumask_weight(sched_group_span(sg));
 
 		if (!(sd->flags & SD_ASYM_PACKING))
 			goto next;
 
-		for_each_cpu(cpu, sched_group_cpus(sg)) {
+		for_each_cpu(cpu, sched_group_span(sg)) {
 			if (max_cpu < 0)
 				max_cpu = cpu;
 			else if (sched_asym_prefer(cpu, max_cpu))
@@ -1308,6 +1548,10 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 			if (!sgc)
 				return -ENOMEM;
 
+#ifdef CONFIG_SCHED_DEBUG
+			sgc->id = j;
+#endif
+
 			*per_cpu_ptr(sdd->sgc, j) = sgc;
 		}
 	}
@@ -1407,7 +1651,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
 			if (tl == sched_domain_topology)
 				*per_cpu_ptr(d.sd, i) = sd;
-			if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
+			if (tl->flags & SDTL_OVERLAP)
 				sd->flags |= SD_OVERLAP;
 			if (cpumask_equal(cpu_map, sched_domain_span(sd)))
 				break;
@@ -1478,7 +1722,7 @@ static struct sched_domain_attr		*dattr_cur;
  * cpumask) fails, then fallback to a single sched domain,
  * as determined by the single cpumask fallback_doms.
  */
-cpumask_var_t				fallback_doms;
+static cpumask_var_t			fallback_doms;
 
 /*
  * arch_update_cpu_topology lets virtualized architectures update the
@@ -1520,10 +1764,14 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
  * For now this just excludes isolated CPUs, but could be used to
  * exclude other special cases in the future.
  */
-int init_sched_domains(const struct cpumask *cpu_map)
+int sched_init_domains(const struct cpumask *cpu_map)
 {
 	int err;
 
+	zalloc_cpumask_var(&sched_domains_tmpmask, GFP_KERNEL);
+	zalloc_cpumask_var(&sched_domains_tmpmask2, GFP_KERNEL);
+	zalloc_cpumask_var(&fallback_doms, GFP_KERNEL);
+
 	arch_update_cpu_topology();
 	ndoms_cur = 1;
 	doms_cur = alloc_sched_domains(ndoms_cur);
diff --git a/kernel/smp.c b/kernel/smp.c
index a817769b53c0..3061483cb3ad 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -30,6 +30,7 @@ enum {
 struct call_function_data {
 	struct call_single_data	__percpu *csd;
 	cpumask_var_t		cpumask;
+	cpumask_var_t		cpumask_ipi;
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
@@ -45,9 +46,15 @@ int smpcfd_prepare_cpu(unsigned int cpu)
 	if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
 				     cpu_to_node(cpu)))
 		return -ENOMEM;
+	if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL,
+				     cpu_to_node(cpu))) {
+		free_cpumask_var(cfd->cpumask);
+		return -ENOMEM;
+	}
 	cfd->csd = alloc_percpu(struct call_single_data);
 	if (!cfd->csd) {
 		free_cpumask_var(cfd->cpumask);
+		free_cpumask_var(cfd->cpumask_ipi);
 		return -ENOMEM;
 	}
 
@@ -59,6 +66,7 @@ int smpcfd_dead_cpu(unsigned int cpu)
 	struct call_function_data *cfd = &per_cpu(cfd_data, cpu);
 
 	free_cpumask_var(cfd->cpumask);
+	free_cpumask_var(cfd->cpumask_ipi);
 	free_percpu(cfd->csd);
 	return 0;
 }
@@ -428,12 +436,13 @@ void smp_call_function_many(const struct cpumask *mask,
 	cfd = this_cpu_ptr(&cfd_data);
 
 	cpumask_and(cfd->cpumask, mask, cpu_online_mask);
-	cpumask_clear_cpu(this_cpu, cfd->cpumask);
+	__cpumask_clear_cpu(this_cpu, cfd->cpumask);
 
 	/* Some callers race with other cpus changing the passed mask */
 	if (unlikely(!cpumask_weight(cfd->cpumask)))
 		return;
 
+	cpumask_clear(cfd->cpumask_ipi);
 	for_each_cpu(cpu, cfd->cpumask) {
 		struct call_single_data *csd = per_cpu_ptr(cfd->csd, cpu);
 
@@ -442,11 +451,12 @@ void smp_call_function_many(const struct cpumask *mask,
 			csd->flags |= CSD_FLAG_SYNCHRONOUS;
 		csd->func = func;
 		csd->info = info;
-		llist_add(&csd->llist, &per_cpu(call_single_queue, cpu));
+		if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
+			__cpumask_set_cpu(cpu, cfd->cpumask_ipi);
 	}
 
 	/* Send a message to all CPUs in the map */
-	arch_send_call_function_ipi_mask(cfd->cpumask);
+	arch_send_call_function_ipi_mask(cfd->cpumask_ipi);
 
 	if (wait) {
 		for_each_cpu(cpu, cfd->cpumask) {
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 1eb82661ecdb..b7591261652d 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -552,7 +552,8 @@ static int __init cpu_stop_init(void)
 }
 early_initcall(cpu_stop_init);
 
-static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
+int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data,
+			    const struct cpumask *cpus)
 {
 	struct multi_stop_data msdata = {
 		.fn = fn,
@@ -561,6 +562,8 @@ static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cp
 		.active_cpus = cpus,
 	};
 
+	lockdep_assert_cpus_held();
+
 	if (!stop_machine_initialized) {
 		/*
 		 * Handle the case where stop_machine() is called
@@ -590,9 +593,9 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
 	int ret;
 
 	/* No CPUs can come up or down during this. */
-	get_online_cpus();
-	ret = __stop_machine(fn, data, cpus);
-	put_online_cpus();
+	cpus_read_lock();
+	ret = stop_machine_cpuslocked(fn, data, cpus);
+	cpus_read_unlock();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(stop_machine);
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 5cb5b0008d97..4cfebfff848d 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -45,11 +45,13 @@ static struct alarm_base {
 	clockid_t		base_clockid;
 } alarm_bases[ALARM_NUMTYPE];
 
+#if defined(CONFIG_POSIX_TIMERS) || defined(CONFIG_RTC_CLASS)
 /* freezer information to handle clock_nanosleep triggered wakeups */
 static enum alarmtimer_type freezer_alarmtype;
 static ktime_t freezer_expires;
 static ktime_t freezer_delta;
 static DEFINE_SPINLOCK(freezer_delta_lock);
+#endif
 
 static struct wakeup_source *ws;
 
@@ -307,38 +309,6 @@ static int alarmtimer_resume(struct device *dev)
 }
 #endif
 
-static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type)
-{
-	struct alarm_base *base;
-	unsigned long flags;
-	ktime_t delta;
-
-	switch(type) {
-	case ALARM_REALTIME:
-		base = &alarm_bases[ALARM_REALTIME];
-		type = ALARM_REALTIME_FREEZER;
-		break;
-	case ALARM_BOOTTIME:
-		base = &alarm_bases[ALARM_BOOTTIME];
-		type = ALARM_BOOTTIME_FREEZER;
-		break;
-	default:
-		WARN_ONCE(1, "Invalid alarm type: %d\n", type);
-		return;
-	}
-
-	delta = ktime_sub(absexp, base->gettime());
-
-	spin_lock_irqsave(&freezer_delta_lock, flags);
-	if (!freezer_delta || (delta < freezer_delta)) {
-		freezer_delta = delta;
-		freezer_expires = absexp;
-		freezer_alarmtype = type;
-	}
-	spin_unlock_irqrestore(&freezer_delta_lock, flags);
-}
-
-
 /**
  * alarm_init - Initialize an alarm structure
  * @alarm: ptr to alarm to be initialized
@@ -488,6 +458,38 @@ u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
 }
 EXPORT_SYMBOL_GPL(alarm_forward_now);
 
+#ifdef CONFIG_POSIX_TIMERS
+
+static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type)
+{
+	struct alarm_base *base;
+	unsigned long flags;
+	ktime_t delta;
+
+	switch(type) {
+	case ALARM_REALTIME:
+		base = &alarm_bases[ALARM_REALTIME];
+		type = ALARM_REALTIME_FREEZER;
+		break;
+	case ALARM_BOOTTIME:
+		base = &alarm_bases[ALARM_BOOTTIME];
+		type = ALARM_BOOTTIME_FREEZER;
+		break;
+	default:
+		WARN_ONCE(1, "Invalid alarm type: %d\n", type);
+		return;
+	}
+
+	delta = ktime_sub(absexp, base->gettime());
+
+	spin_lock_irqsave(&freezer_delta_lock, flags);
+	if (!freezer_delta || (delta < freezer_delta)) {
+		freezer_delta = delta;
+		freezer_expires = absexp;
+		freezer_alarmtype = type;
+	}
+	spin_unlock_irqrestore(&freezer_delta_lock, flags);
+}
 
 /**
  * clock2alarm - helper that converts from clockid to alarmtypes
@@ -846,6 +848,17 @@ out:
 	return ret;
 }
 
+const struct k_clock alarm_clock = {
+	.clock_getres	= alarm_clock_getres,
+	.clock_get	= alarm_clock_get,
+	.timer_create	= alarm_timer_create,
+	.timer_set	= alarm_timer_set,
+	.timer_del	= alarm_timer_del,
+	.timer_get	= alarm_timer_get,
+	.nsleep		= alarm_timer_nsleep,
+};
+#endif /* CONFIG_POSIX_TIMERS */
+
 
 /* Suspend hook structures */
 static const struct dev_pm_ops alarmtimer_pm_ops = {
@@ -871,23 +884,9 @@ static int __init alarmtimer_init(void)
 	struct platform_device *pdev;
 	int error = 0;
 	int i;
-	struct k_clock alarm_clock = {
-		.clock_getres	= alarm_clock_getres,
-		.clock_get	= alarm_clock_get,
-		.timer_create	= alarm_timer_create,
-		.timer_set	= alarm_timer_set,
-		.timer_del	= alarm_timer_del,
-		.timer_get	= alarm_timer_get,
-		.nsleep		= alarm_timer_nsleep,
-	};
 
 	alarmtimer_rtc_timer_init();
 
-	if (IS_ENABLED(CONFIG_POSIX_TIMERS)) {
-		posix_timers_register_clock(CLOCK_REALTIME_ALARM, &alarm_clock);
-		posix_timers_register_clock(CLOCK_BOOTTIME_ALARM, &alarm_clock);
-	}
-
 	/* Initialize alarm bases */
 	alarm_bases[ALARM_REALTIME].base_clockid = CLOCK_REALTIME;
 	alarm_bases[ALARM_REALTIME].gettime = &ktime_get_real;
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 93621ae718d3..03918a19cf2d 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -233,6 +233,9 @@ static void clocksource_watchdog(unsigned long data)
 			continue;
 		}
 
+		if (cs == curr_clocksource && cs->tick_stable)
+			cs->tick_stable(cs);
+
 		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
 		    (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) &&
 		    (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) {
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 31d588d37a17..7e453005e078 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -434,7 +434,7 @@ static int pc_timer_settime(struct k_itimer *kit, int flags,
 	return err;
 }
 
-struct k_clock clock_posix_dynamic = {
+const struct k_clock clock_posix_dynamic = {
 	.clock_getres	= pc_clock_getres,
 	.clock_set	= pc_clock_settime,
 	.clock_get	= pc_clock_gettime,
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index d2a1e6dd0291..c99434739fd5 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1421,7 +1421,7 @@ static int thread_cpu_timer_create(struct k_itimer *timer)
 	return posix_cpu_timer_create(timer);
 }
 
-struct k_clock clock_posix_cpu = {
+const struct k_clock clock_posix_cpu = {
 	.clock_getres	= posix_cpu_clock_getres,
 	.clock_set	= posix_cpu_clock_set,
 	.clock_get	= posix_cpu_clock_get,
@@ -1433,24 +1433,16 @@ struct k_clock clock_posix_cpu = {
 	.timer_get	= posix_cpu_timer_get,
 };
 
-static __init int init_posix_cpu_timers(void)
-{
-	struct k_clock process = {
-		.clock_getres	= process_cpu_clock_getres,
-		.clock_get	= process_cpu_clock_get,
-		.timer_create	= process_cpu_timer_create,
-		.nsleep		= process_cpu_nsleep,
-		.nsleep_restart	= process_cpu_nsleep_restart,
-	};
-	struct k_clock thread = {
-		.clock_getres	= thread_cpu_clock_getres,
-		.clock_get	= thread_cpu_clock_get,
-		.timer_create	= thread_cpu_timer_create,
-	};
-
-	posix_timers_register_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
-	posix_timers_register_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
+const struct k_clock clock_process = {
+	.clock_getres	= process_cpu_clock_getres,
+	.clock_get	= process_cpu_clock_get,
+	.timer_create	= process_cpu_timer_create,
+	.nsleep		= process_cpu_nsleep,
+	.nsleep_restart	= process_cpu_nsleep_restart,
+};
 
-	return 0;
-}
-__initcall(init_posix_cpu_timers);
+const struct k_clock clock_thread = {
+	.clock_getres	= thread_cpu_clock_getres,
+	.clock_get	= thread_cpu_clock_get,
+	.timer_create	= thread_cpu_timer_create,
+};
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 4d7b2ce09c27..0c0cccfa3586 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -125,8 +125,6 @@ static DEFINE_SPINLOCK(hash_lock);
  *	    which we beg off on and pass to do_sys_settimeofday().
  */
 
-static struct k_clock posix_clocks[MAX_CLOCKS];
-
 /*
  * These ones are defined below.
  */
@@ -280,74 +278,87 @@ static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec64 *tp)
 	return 0;
 }
 
+
+static const struct k_clock clock_realtime = {
+	.clock_getres	= posix_get_hrtimer_res,
+	.clock_get	= posix_clock_realtime_get,
+	.clock_set	= posix_clock_realtime_set,
+	.clock_adj	= posix_clock_realtime_adj,
+	.nsleep		= common_nsleep,
+	.nsleep_restart	= hrtimer_nanosleep_restart,
+	.timer_create	= common_timer_create,
+	.timer_set	= common_timer_set,
+	.timer_get	= common_timer_get,
+	.timer_del	= common_timer_del,
+};
+
+static const struct k_clock clock_monotonic = {
+	.clock_getres	= posix_get_hrtimer_res,
+	.clock_get	= posix_ktime_get_ts,
+	.nsleep		= common_nsleep,
+	.nsleep_restart	= hrtimer_nanosleep_restart,
+	.timer_create	= common_timer_create,
+	.timer_set	= common_timer_set,
+	.timer_get	= common_timer_get,
+	.timer_del	= common_timer_del,
+};
+
+static const struct k_clock clock_monotonic_raw = {
+	.clock_getres	= posix_get_hrtimer_res,
+	.clock_get	= posix_get_monotonic_raw,
+};
+
+static const struct k_clock clock_realtime_coarse = {
+	.clock_getres	= posix_get_coarse_res,
+	.clock_get	= posix_get_realtime_coarse,
+};
+
+static const struct k_clock clock_monotonic_coarse = {
+	.clock_getres	= posix_get_coarse_res,
+	.clock_get	= posix_get_monotonic_coarse,
+};
+
+static const struct k_clock clock_tai = {
+	.clock_getres	= posix_get_hrtimer_res,
+	.clock_get	= posix_get_tai,
+	.nsleep		= common_nsleep,
+	.nsleep_restart	= hrtimer_nanosleep_restart,
+	.timer_create	= common_timer_create,
+	.timer_set	= common_timer_set,
+	.timer_get	= common_timer_get,
+	.timer_del	= common_timer_del,
+};
+
+static const struct k_clock clock_boottime = {
+	.clock_getres	= posix_get_hrtimer_res,
+	.clock_get	= posix_get_boottime,
+	.nsleep		= common_nsleep,
+	.nsleep_restart	= hrtimer_nanosleep_restart,
+	.timer_create	= common_timer_create,
+	.timer_set	= common_timer_set,
+	.timer_get	= common_timer_get,
+	.timer_del	= common_timer_del,
+};
+
+static const struct k_clock * const posix_clocks[] = {
+	[CLOCK_REALTIME]		= &clock_realtime,
+	[CLOCK_MONOTONIC]		= &clock_monotonic,
+	[CLOCK_PROCESS_CPUTIME_ID]	= &clock_process,
+	[CLOCK_THREAD_CPUTIME_ID]	= &clock_thread,
+	[CLOCK_MONOTONIC_RAW]		= &clock_monotonic_raw,
+	[CLOCK_REALTIME_COARSE]		= &clock_realtime_coarse,
+	[CLOCK_MONOTONIC_COARSE]	= &clock_monotonic_coarse,
+	[CLOCK_BOOTTIME]		= &clock_boottime,
+	[CLOCK_REALTIME_ALARM]		= &alarm_clock,
+	[CLOCK_BOOTTIME_ALARM]		= &alarm_clock,
+	[CLOCK_TAI]			= &clock_tai,
+};
+
 /*
  * Initialize everything, well, just everything in Posix clocks/timers ;)
  */
 static __init int init_posix_timers(void)
 {
-	struct k_clock clock_realtime = {
-		.clock_getres	= posix_get_hrtimer_res,
-		.clock_get	= posix_clock_realtime_get,
-		.clock_set	= posix_clock_realtime_set,
-		.clock_adj	= posix_clock_realtime_adj,
-		.nsleep		= common_nsleep,
-		.nsleep_restart	= hrtimer_nanosleep_restart,
-		.timer_create	= common_timer_create,
-		.timer_set	= common_timer_set,
-		.timer_get	= common_timer_get,
-		.timer_del	= common_timer_del,
-	};
-	struct k_clock clock_monotonic = {
-		.clock_getres	= posix_get_hrtimer_res,
-		.clock_get	= posix_ktime_get_ts,
-		.nsleep		= common_nsleep,
-		.nsleep_restart	= hrtimer_nanosleep_restart,
-		.timer_create	= common_timer_create,
-		.timer_set	= common_timer_set,
-		.timer_get	= common_timer_get,
-		.timer_del	= common_timer_del,
-	};
-	struct k_clock clock_monotonic_raw = {
-		.clock_getres	= posix_get_hrtimer_res,
-		.clock_get	= posix_get_monotonic_raw,
-	};
-	struct k_clock clock_realtime_coarse = {
-		.clock_getres	= posix_get_coarse_res,
-		.clock_get	= posix_get_realtime_coarse,
-	};
-	struct k_clock clock_monotonic_coarse = {
-		.clock_getres	= posix_get_coarse_res,
-		.clock_get	= posix_get_monotonic_coarse,
-	};
-	struct k_clock clock_tai = {
-		.clock_getres	= posix_get_hrtimer_res,
-		.clock_get	= posix_get_tai,
-		.nsleep		= common_nsleep,
-		.nsleep_restart	= hrtimer_nanosleep_restart,
-		.timer_create	= common_timer_create,
-		.timer_set	= common_timer_set,
-		.timer_get	= common_timer_get,
-		.timer_del	= common_timer_del,
-	};
-	struct k_clock clock_boottime = {
-		.clock_getres	= posix_get_hrtimer_res,
-		.clock_get	= posix_get_boottime,
-		.nsleep		= common_nsleep,
-		.nsleep_restart	= hrtimer_nanosleep_restart,
-		.timer_create	= common_timer_create,
-		.timer_set	= common_timer_set,
-		.timer_get	= common_timer_get,
-		.timer_del	= common_timer_del,
-	};
-
-	posix_timers_register_clock(CLOCK_REALTIME, &clock_realtime);
-	posix_timers_register_clock(CLOCK_MONOTONIC, &clock_monotonic);
-	posix_timers_register_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
-	posix_timers_register_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
-	posix_timers_register_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
-	posix_timers_register_clock(CLOCK_BOOTTIME, &clock_boottime);
-	posix_timers_register_clock(CLOCK_TAI, &clock_tai);
-
 	posix_timers_cache = kmem_cache_create("posix_timers_cache",
 					sizeof (struct k_itimer), 0, SLAB_PANIC,
 					NULL);
@@ -521,30 +532,6 @@ static struct pid *good_sigevent(sigevent_t * event)
 	return task_pid(rtn);
 }
 
-void posix_timers_register_clock(const clockid_t clock_id,
-				 struct k_clock *new_clock)
-{
-	if ((unsigned) clock_id >= MAX_CLOCKS) {
-		printk(KERN_WARNING "POSIX clock register failed for clock_id %d\n",
-		       clock_id);
-		return;
-	}
-
-	if (!new_clock->clock_get) {
-		printk(KERN_WARNING "POSIX clock id %d lacks clock_get()\n",
-		       clock_id);
-		return;
-	}
-	if (!new_clock->clock_getres) {
-		printk(KERN_WARNING "POSIX clock id %d lacks clock_getres()\n",
-		       clock_id);
-		return;
-	}
-
-	posix_clocks[clock_id] = *new_clock;
-}
-EXPORT_SYMBOL_GPL(posix_timers_register_clock);
-
 static struct k_itimer * alloc_posix_timer(void)
 {
 	struct k_itimer *tmr;
@@ -581,15 +568,15 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
 	call_rcu(&tmr->it.rcu, k_itimer_rcu_free);
 }
 
-static struct k_clock *clockid_to_kclock(const clockid_t id)
+static const struct k_clock *clockid_to_kclock(const clockid_t id)
 {
 	if (id < 0)
 		return (id & CLOCKFD_MASK) == CLOCKFD ?
 			&clock_posix_dynamic : &clock_posix_cpu;
 
-	if (id >= MAX_CLOCKS || !posix_clocks[id].clock_getres)
+	if (id >= ARRAY_SIZE(posix_clocks) || !posix_clocks[id])
 		return NULL;
-	return &posix_clocks[id];
+	return posix_clocks[id];
 }
 
 static int common_timer_create(struct k_itimer *new_timer)
@@ -604,7 +591,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
 		struct sigevent __user *, timer_event_spec,
 		timer_t __user *, created_timer_id)
 {
-	struct k_clock *kc = clockid_to_kclock(which_clock);
+	const struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct k_itimer *new_timer;
 	int error, new_timer_id;
 	sigevent_t event;
@@ -781,7 +768,7 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
 	struct itimerspec64 cur_setting64;
 	struct itimerspec cur_setting;
 	struct k_itimer *timr;
-	struct k_clock *kc;
+	const struct k_clock *kc;
 	unsigned long flags;
 	int ret = 0;
 
@@ -890,7 +877,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
 	struct itimerspec new_spec, old_spec;
 	struct k_itimer *timr;
 	unsigned long flag;
-	struct k_clock *kc;
+	const struct k_clock *kc;
 	int error = 0;
 
 	if (!new_setting)
@@ -939,7 +926,7 @@ static int common_timer_del(struct k_itimer *timer)
 
 static inline int timer_delete_hook(struct k_itimer *timer)
 {
-	struct k_clock *kc = clockid_to_kclock(timer->it_clock);
+	const struct k_clock *kc = clockid_to_kclock(timer->it_clock);
 
 	if (WARN_ON_ONCE(!kc || !kc->timer_del))
 		return -EINVAL;
@@ -1018,7 +1005,7 @@ void exit_itimers(struct signal_struct *sig)
 SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
 		const struct timespec __user *, tp)
 {
-	struct k_clock *kc = clockid_to_kclock(which_clock);
+	const struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec64 new_tp64;
 	struct timespec new_tp;
 
@@ -1035,7 +1022,7 @@ SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
 SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
 		struct timespec __user *,tp)
 {
-	struct k_clock *kc = clockid_to_kclock(which_clock);
+	const struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec64 kernel_tp64;
 	struct timespec kernel_tp;
 	int error;
@@ -1055,7 +1042,7 @@ SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
 SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
 		struct timex __user *, utx)
 {
-	struct k_clock *kc = clockid_to_kclock(which_clock);
+	const struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timex ktx;
 	int err;
 
@@ -1078,7 +1065,7 @@ SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
 SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
 		struct timespec __user *, tp)
 {
-	struct k_clock *kc = clockid_to_kclock(which_clock);
+	const struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec64 rtn_tp64;
 	struct timespec rtn_tp;
 	int error;
@@ -1110,7 +1097,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 		const struct timespec __user *, rqtp,
 		struct timespec __user *, rmtp)
 {
-	struct k_clock *kc = clockid_to_kclock(which_clock);
+	const struct k_clock *kc = clockid_to_kclock(which_clock);
 	struct timespec64 t64;
 	struct timespec t;
 
@@ -1136,7 +1123,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 long clock_nanosleep_restart(struct restart_block *restart_block)
 {
 	clockid_t which_clock = restart_block->nanosleep.clockid;
-	struct k_clock *kc = clockid_to_kclock(which_clock);
+	const struct k_clock *kc = clockid_to_kclock(which_clock);
 
 	if (WARN_ON_ONCE(!kc || !kc->nsleep_restart))
 		return -EINVAL;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 64c97fc130c4..2de9c553682f 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -150,6 +150,12 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 		touch_softlockup_watchdog_sched();
 		if (is_idle_task(current))
 			ts->idle_jiffies++;
+		/*
+		 * In case the current tick fired too early past its expected
+		 * expiration, make sure we don't bypass the next clock reprogramming
+		 * to the same deadline.
+		 */
+		ts->next_tick = 0;
 	}
 #endif
 	update_process_times(user_mode(regs));
@@ -554,7 +560,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
 	update_ts_time_stats(smp_processor_id(), ts, now, NULL);
 	ts->idle_active = 0;
 
-	sched_clock_idle_wakeup_event(0);
+	sched_clock_idle_wakeup_event();
 }
 
 static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
@@ -660,6 +666,12 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 		hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
 	else
 		tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
+
+	/*
+	 * Reset to make sure next tick stop doesn't get fooled by past
+	 * cached clock deadline.
+	 */
+	ts->next_tick = 0;
 }
 
 static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
@@ -771,8 +783,16 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	tick = expires;
 
 	/* Skip reprogram of event if its not changed */
-	if (ts->tick_stopped && (expires == dev->next_event))
-		goto out;
+	if (ts->tick_stopped && (expires == ts->next_tick)) {
+		/* Sanity check: make sure clockevent is actually programmed */
+		if (likely(dev->next_event <= ts->next_tick))
+			goto out;
+
+		WARN_ON_ONCE(1);
+		printk_once("basemono: %llu ts->next_tick: %llu dev->next_event: %llu timer->active: %d timer->expires: %llu\n",
+			    basemono, ts->next_tick, dev->next_event,
+			    hrtimer_active(&ts->sched_timer), hrtimer_get_expires(&ts->sched_timer));
+	}
 
 	/*
 	 * nohz_stop_sched_tick can be called several times before
@@ -791,6 +811,8 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 		trace_tick_stop(1, TICK_DEP_MASK_NONE);
 	}
 
+	ts->next_tick = tick;
+
 	/*
 	 * If the expiration time == KTIME_MAX, then we simply stop
 	 * the tick timer.
@@ -806,7 +828,10 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	else
 		tick_program_event(tick, 1);
 out:
-	/* Update the estimated sleep length */
+	/*
+	 * Update the estimated sleep length until the next timer
+	 * (not only the tick).
+	 */
 	ts->sleep_length = ktime_sub(dev->next_event, now);
 	return tick;
 }
@@ -864,6 +889,11 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 	if (unlikely(!cpu_online(cpu))) {
 		if (cpu == tick_do_timer_cpu)
 			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+		/*
+		 * Make sure the CPU doesn't get fooled by obsolete tick
+		 * deadline if it comes back online later.
+		 */
+		ts->next_tick = 0;
 		return false;
 	}
 
@@ -1172,6 +1202,8 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
 	 */
 	if (regs)
 		tick_sched_handle(ts, regs);
+	else
+		ts->next_tick = 0;
 
 	/* No need to reprogram if we are in idle or full dynticks mode */
 	if (unlikely(ts->tick_stopped))
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index bf38226e5c17..075444e3d48e 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -27,6 +27,7 @@ enum tick_nohz_mode {
  *			timer is modified for nohz sleeps. This is necessary
  *			to resume the tick timer operation in the timeline
  *			when the CPU returns from nohz sleep.
+ * @next_tick:		Next tick to be fired when in dynticks mode.
  * @tick_stopped:	Indicator that the idle tick has been stopped
  * @idle_jiffies:	jiffies at the entry to idle for idle time accounting
  * @idle_calls:		Total number of idle calls
@@ -44,6 +45,7 @@ struct tick_sched {
 	unsigned long			check_clocks;
 	enum tick_nohz_mode		nohz_mode;
 	ktime_t				last_tick;
+	ktime_t				next_tick;
 	int				inidle;
 	int				tick_stopped;
 	unsigned long			idle_jiffies;
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 81dedaab36cc..4731a0895760 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -43,6 +43,38 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
 }
 EXPORT_SYMBOL(cpumask_any_but);
 
+/**
+ * cpumask_next_wrap - helper to implement for_each_cpu_wrap
+ * @n: the cpu prior to the place to search
+ * @mask: the cpumask pointer
+ * @start: the start point of the iteration
+ * @wrap: assume @n crossing @start terminates the iteration
+ *
+ * Returns >= nr_cpu_ids on completion
+ *
+ * Note: the @wrap argument is required for the start condition when
+ * we cannot assume @start is set in @mask.
+ */
+int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
+{
+	int next;
+
+again:
+	next = cpumask_next(n, mask);
+
+	if (wrap && n < start && next >= start) {
+		return nr_cpumask_bits;
+
+	} else if (next >= nr_cpumask_bits) {
+		wrap = true;
+		n = -1;
+		goto again;
+	}
+
+	return next;
+}
+EXPORT_SYMBOL(cpumask_next_wrap);
+
 /* These are not inline because of header tangles. */
 #ifdef CONFIG_CPUMASK_OFFSTACK
 /**
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 690d75b132fa..2fb007be0212 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -28,7 +28,7 @@ notrace static unsigned int check_preemption_disabled(const char *what1,
 	/*
 	 * It is valid to assume CPU-locality during early bootup:
 	 */
-	if (system_state != SYSTEM_RUNNING)
+	if (system_state < SYSTEM_SCHEDULING)
 		goto out;
 
 	/*
diff --git a/mm/rmap.c b/mm/rmap.c
index d405f0e0ee96..130c238fe384 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -579,25 +579,13 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma)
 void try_to_unmap_flush(void)
 {
 	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
-	int cpu;
 
 	if (!tlb_ubc->flush_required)
 		return;
 
-	cpu = get_cpu();
-
-	if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) {
-		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-		local_flush_tlb();
-		trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL);
-	}
-
-	if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids)
-		flush_tlb_others(&tlb_ubc->cpumask, NULL, 0, TLB_FLUSH_ALL);
-	cpumask_clear(&tlb_ubc->cpumask);
+	arch_tlbbatch_flush(&tlb_ubc->arch);
 	tlb_ubc->flush_required = false;
 	tlb_ubc->writable = false;
-	put_cpu();
 }
 
 /* Flush iff there are potentially writable TLB entries that can race with IO */
@@ -613,7 +601,7 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
 {
 	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
 
-	cpumask_or(&tlb_ubc->cpumask, &tlb_ubc->cpumask, mm_cpumask(mm));
+	arch_tlbbatch_add_mm(&tlb_ubc->arch, mm);
 	tlb_ubc->flush_required = true;
 
 	/*
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8ad39bbc79e6..c3c1c6ac62da 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3652,7 +3652,7 @@ int kswapd_run(int nid)
 	pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
 	if (IS_ERR(pgdat->kswapd)) {
 		/* failure at boot is fatal */
-		BUG_ON(system_state == SYSTEM_BOOTING);
+		BUG_ON(system_state < SYSTEM_RUNNING);
 		pr_err("Failed to start kswapd on node %d\n", nid);
 		ret = PTR_ERR(pgdat->kswapd);
 		pgdat->kswapd = NULL;