Merge tag 'x86_cleanups_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cleanups from Borislav Petkov:

 - Serious sanitization and cleanup of the whole APERF/MPERF and
   frequency invariance code along with removing the need for
   unnecessary IPIs

 - Finally remove a.out support

 - The usual trivial cleanups and fixes all over x86

* tag 'x86_cleanups_for_v5.19_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (21 commits)
  x86: Remove empty files
  x86/speculation: Add missing srbds=off to the mitigations= help text
  x86/prctl: Remove pointless task argument
  x86/aperfperf: Make it correct on 32bit and UP kernels
  x86/aperfmperf: Integrate the fallback code from show_cpuinfo()
  x86/aperfmperf: Replace arch_freq_get_on_cpu()
  x86/aperfmperf: Replace aperfmperf_get_khz()
  x86/aperfmperf: Store aperf/mperf data for cpu frequency reads
  x86/aperfmperf: Make parts of the frequency invariance code unconditional
  x86/aperfmperf: Restructure arch_scale_freq_tick()
  x86/aperfmperf: Put frequency invariance aperf/mperf data into a struct
  x86/aperfmperf: Untangle Intel and AMD frequency invariance init
  x86/aperfmperf: Separate AP/BP frequency invariance init
  x86/smp: Move APERF/MPERF code where it belongs
  x86/aperfmperf: Dont wake idle CPUs in arch_freq_get_on_cpu()
  x86/process: Fix kernel-doc warning due to a changed function name
  x86: Remove a.out support
  x86/mm: Replace nodes_weight() with nodes_empty() where appropriate
  x86: Replace cpumask_weight() with cpumask_empty() where appropriate
  x86/pkeys: Remove __arch_set_user_pkey_access() declaration
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -3147,6 +3147,7 @@
 					       mds=off [X86]
 					       tsx_async_abort=off [X86]
 					       kvm.nx_huge_pages=off [X86]
+					       srbds=off [X86,INTEL]
 					       no_entry_flush [PPC]
 					       no_uaccess_flush [PPC]
 

MAINTAINERS

@@ -7385,7 +7385,6 @@ L:	linux-mm@kvack.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve
 F:	arch/alpha/kernel/binfmt_loader.c
-F:	arch/x86/ia32/ia32_aout.c
 F:	fs/*binfmt_*.c
 F:	fs/exec.c
 F:	include/linux/binfmts.h

arch/x86/Kconfig

@@ -2842,13 +2842,6 @@ config IA32_EMULATION
 	  64-bit kernel. You should likely turn this on, unless you're
 	  100% sure that you don't have any 32-bit programs left.
 
-config IA32_AOUT
-	tristate "IA32 a.out support"
-	depends on IA32_EMULATION
-	depends on BROKEN
-	help
-	  Support old a.out binaries in the 32bit emulation.
-
 config X86_X32_ABI
 	bool "x32 ABI for 64-bit mode"
 	depends on X86_64

arch/x86/ia32/Makefile

@@ -5,7 +5,5 @@
 
 obj-$(CONFIG_IA32_EMULATION) := ia32_signal.o
 
-obj-$(CONFIG_IA32_AOUT) += ia32_aout.o
-
 audit-class-$(CONFIG_AUDIT) := audit.o
 obj-$(CONFIG_IA32_EMULATION) += $(audit-class-y)

arch/x86/ia32/ia32_aout.c

-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *  a.out loader for x86-64
- *
- *  Copyright (C) 1991, 1992, 1996  Linus Torvalds
- *  Hacked together by Andi Kleen
- */
-
-#include <linux/module.h>
-
-#include <linux/time.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/mman.h>
-#include <linux/a.out.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/string.h>
-#include <linux/fs.h>
-#include <linux/file.h>
-#include <linux/stat.h>
-#include <linux/fcntl.h>
-#include <linux/ptrace.h>
-#include <linux/user.h>
-#include <linux/binfmts.h>
-#include <linux/personality.h>
-#include <linux/init.h>
-#include <linux/jiffies.h>
-#include <linux/perf_event.h>
-#include <linux/sched/task_stack.h>
-
-#include <linux/uaccess.h>
-#include <asm/cacheflush.h>
-#include <asm/user32.h>
-#include <asm/ia32.h>
-
-#undef WARN_OLD
-
-static int load_aout_binary(struct linux_binprm *);
-static int load_aout_library(struct file *);
-
-static struct linux_binfmt aout_format = {
-	.module		= THIS_MODULE,
-	.load_binary	= load_aout_binary,
-	.load_shlib	= load_aout_library,
-};
-
-static int set_brk(unsigned long start, unsigned long end)
-{
-	start = PAGE_ALIGN(start);
-	end = PAGE_ALIGN(end);
-	if (end <= start)
-		return 0;
-	return vm_brk(start, end - start);
-}
-
-
-/*
- * create_aout_tables() parses the env- and arg-strings in new user
- * memory and creates the pointer tables from them, and puts their
- * addresses on the "stack", returning the new stack pointer value.
- */
-static u32 __user *create_aout_tables(char __user *p, struct linux_binprm *bprm)
-{
-	u32 __user *argv, *envp, *sp;
-	int argc = bprm->argc, envc = bprm->envc;
-
-	sp = (u32 __user *) ((-(unsigned long)sizeof(u32)) & (unsigned long) p);
-	sp -= envc+1;
-	envp = sp;
-	sp -= argc+1;
-	argv = sp;
-	put_user((unsigned long) envp, --sp);
-	put_user((unsigned long) argv, --sp);
-	put_user(argc, --sp);
-	current->mm->arg_start = (unsigned long) p;
-	while (argc-- > 0) {
-		char c;
-
-		put_user((u32)(unsigned long)p, argv++);
-		do {
-			get_user(c, p++);
-		} while (c);
-	}
-	put_user(0, argv);
-	current->mm->arg_end = current->mm->env_start = (unsigned long) p;
-	while (envc-- > 0) {
-		char c;
-
-		put_user((u32)(unsigned long)p, envp++);
-		do {
-			get_user(c, p++);
-		} while (c);
-	}
-	put_user(0, envp);
-	current->mm->env_end = (unsigned long) p;
-	return sp;
-}
-
-/*
- * These are the functions used to load a.out style executables and shared
- * libraries.  There is no binary dependent code anywhere else.
- */
-static int load_aout_binary(struct linux_binprm *bprm)
-{
-	unsigned long error, fd_offset, rlim;
-	struct pt_regs *regs = current_pt_regs();
-	struct exec ex;
-	int retval;
-
-	ex = *((struct exec *) bprm->buf);		/* exec-header */
-	if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != OMAGIC &&
-	     N_MAGIC(ex) != QMAGIC && N_MAGIC(ex) != NMAGIC) ||
-	    N_TRSIZE(ex) || N_DRSIZE(ex) ||
-	    i_size_read(file_inode(bprm->file)) <
-	    ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
-		return -ENOEXEC;
-	}
-
-	fd_offset = N_TXTOFF(ex);
-
-	/* Check initial limits. This avoids letting people circumvent
-	 * size limits imposed on them by creating programs with large
-	 * arrays in the data or bss.
-	 */
-	rlim = rlimit(RLIMIT_DATA);
-	if (rlim >= RLIM_INFINITY)
-		rlim = ~0;
-	if (ex.a_data + ex.a_bss > rlim)
-		return -ENOMEM;
-
-	/* Flush all traces of the currently running executable */
-	retval = begin_new_exec(bprm);
-	if (retval)
-		return retval;
-
-	/* OK, This is the point of no return */
-	set_personality(PER_LINUX);
-	set_personality_ia32(false);
-
-	setup_new_exec(bprm);
-
-	regs->cs = __USER32_CS;
-	regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 =
-		regs->r13 = regs->r14 = regs->r15 = 0;
-
-	current->mm->end_code = ex.a_text +
-		(current->mm->start_code = N_TXTADDR(ex));
-	current->mm->end_data = ex.a_data +
-		(current->mm->start_data = N_DATADDR(ex));
-	current->mm->brk = ex.a_bss +
-		(current->mm->start_brk = N_BSSADDR(ex));
-
-	retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT);
-	if (retval < 0)
-		return retval;
-
-	if (N_MAGIC(ex) == OMAGIC) {
-		unsigned long text_addr, map_size;
-
-		text_addr = N_TXTADDR(ex);
-		map_size = ex.a_text+ex.a_data;
-
-		error = vm_brk(text_addr & PAGE_MASK, map_size);
-
-		if (error)
-			return error;
-
-		error = read_code(bprm->file, text_addr, 32,
-				  ex.a_text + ex.a_data);
-		if ((signed long)error < 0)
-			return error;
-	} else {
-#ifdef WARN_OLD
-		static unsigned long error_time, error_time2;
-		if ((ex.a_text & 0xfff || ex.a_data & 0xfff) &&
-		    (N_MAGIC(ex) != NMAGIC) &&
-				time_after(jiffies, error_time2 + 5*HZ)) {
-			printk(KERN_NOTICE "executable not page aligned\n");
-			error_time2 = jiffies;
-		}
-
-		if ((fd_offset & ~PAGE_MASK) != 0 &&
-			    time_after(jiffies, error_time + 5*HZ)) {
-			printk(KERN_WARNING
-			       "fd_offset is not page aligned. Please convert "
-			       "program: %pD\n",
-			       bprm->file);
-			error_time = jiffies;
-		}
-#endif
-
-		if (!bprm->file->f_op->mmap || (fd_offset & ~PAGE_MASK) != 0) {
-			error = vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
-			if (error)
-				return error;
-
-			read_code(bprm->file, N_TXTADDR(ex), fd_offset,
-					ex.a_text+ex.a_data);
-			goto beyond_if;
-		}
-
-		error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
-				PROT_READ | PROT_EXEC,
-				MAP_FIXED | MAP_PRIVATE | MAP_32BIT,
-				fd_offset);
-
-		if (error != N_TXTADDR(ex))
-			return error;
-
-		error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
-				PROT_READ | PROT_WRITE | PROT_EXEC,
-				MAP_FIXED | MAP_PRIVATE | MAP_32BIT,
-				fd_offset + ex.a_text);
-		if (error != N_DATADDR(ex))
-			return error;
-	}
-
-beyond_if:
-	error = set_brk(current->mm->start_brk, current->mm->brk);
-	if (error)
-		return error;
-
-	set_binfmt(&aout_format);
-
-	current->mm->start_stack =
-		(unsigned long)create_aout_tables((char __user *)bprm->p, bprm);
-	/* start thread */
-	loadsegment(fs, 0);
-	loadsegment(ds, __USER32_DS);
-	loadsegment(es, __USER32_DS);
-	load_gs_index(0);
-	(regs)->ip = ex.a_entry;
-	(regs)->sp = current->mm->start_stack;
-	(regs)->flags = 0x200;
-	(regs)->cs = __USER32_CS;
-	(regs)->ss = __USER32_DS;
-	regs->r8 = regs->r9 = regs->r10 = regs->r11 =
-	regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;
-	return 0;
-}
-
-static int load_aout_library(struct file *file)
-{
-	unsigned long bss, start_addr, len, error;
-	int retval;
-	struct exec ex;
-	loff_t pos = 0;
-
-	retval = -ENOEXEC;
-	error = kernel_read(file, &ex, sizeof(ex), &pos);
-	if (error != sizeof(ex))
-		goto out;
-
-	/* We come in here for the regular a.out style of shared libraries */
-	if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != QMAGIC) || N_TRSIZE(ex) ||
-	    N_DRSIZE(ex) || ((ex.a_entry & 0xfff) && N_MAGIC(ex) == ZMAGIC) ||
-	    i_size_read(file_inode(file)) <
-	    ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
-		goto out;
-	}
-
-	if (N_FLAGS(ex))
-		goto out;
-
-	/* For  QMAGIC, the starting address is 0x20 into the page.  We mask
-	   this off to get the starting address for the page */
-
-	start_addr =  ex.a_entry & 0xfffff000;
-
-	if ((N_TXTOFF(ex) & ~PAGE_MASK) != 0) {
-#ifdef WARN_OLD
-		static unsigned long error_time;
-		if (time_after(jiffies, error_time + 5*HZ)) {
-			printk(KERN_WARNING
-			       "N_TXTOFF is not page aligned. Please convert "
-			       "library: %pD\n",
-			       file);
-			error_time = jiffies;
-		}
-#endif
-		retval = vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
-		if (retval)
-			goto out;
-
-		read_code(file, start_addr, N_TXTOFF(ex),
-			  ex.a_text + ex.a_data);
-		retval = 0;
-		goto out;
-	}
-	/* Now use mmap to map the library into memory. */
-	error = vm_mmap(file, start_addr, ex.a_text + ex.a_data,
-			PROT_READ | PROT_WRITE | PROT_EXEC,
-			MAP_FIXED | MAP_PRIVATE | MAP_32BIT,
-			N_TXTOFF(ex));
-	retval = error;
-	if (error != start_addr)
-		goto out;
-
-	len = PAGE_ALIGN(ex.a_text + ex.a_data);
-	bss = ex.a_text + ex.a_data + ex.a_bss;
-	if (bss > len) {
-		retval = vm_brk(start_addr + len, bss - len);
-		if (retval)
-			goto out;
-	}
-	retval = 0;
-out:
-	return retval;
-}
-
-static int __init init_aout_binfmt(void)
-{
-	register_binfmt(&aout_format);
-	return 0;
-}
-
-static void __exit exit_aout_binfmt(void)
-{
-	unregister_binfmt(&aout_format);
-}
-
-module_init(init_aout_binfmt);
-module_exit(exit_aout_binfmt);
-MODULE_LICENSE("GPL");

arch/x86/include/asm/cpu.h

@@ -36,6 +36,8 @@ extern int _debug_hotplug_cpu(int cpu, int action);
 #endif
 #endif
 
+extern void ap_init_aperfmperf(void);
+
 int mwait_usable(const struct cpuinfo_x86 *);
 
 unsigned int x86_family(unsigned int sig);

arch/x86/include/asm/fpu/api.h

@@ -162,7 +162,6 @@ static inline bool fpstate_is_confidential(struct fpu_guest *gfpu)
 }
 
 /* prctl */
-struct task_struct;
-extern long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2);
+extern long fpu_xstate_prctl(int option, unsigned long arg2);
 
 #endif /* _ASM_X86_FPU_API_H */

arch/x86/include/asm/pkeys.h

@@ -41,9 +41,6 @@ static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma,
 	return __arch_override_mprotect_pkey(vma, prot, pkey);
 }
 
-extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
-		unsigned long init_val);
-
 #define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3)
 
 #define mm_pkey_allocation_map(mm)	(mm->context.pkey_allocation_map)
@@ -118,11 +115,6 @@ int mm_pkey_free(struct mm_struct *mm, int pkey)
 	return 0;
 }
 
-extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
-		unsigned long init_val);
-extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
-		unsigned long init_val);
-
 static inline int vma_pkey(struct vm_area_struct *vma)
 {
 	unsigned long vma_pkey_mask = VM_PKEY_BIT0 | VM_PKEY_BIT1 |

arch/x86/include/asm/proto.h

@@ -42,7 +42,6 @@ void x86_configure_nx(void);
 
 extern int reboot_force;
 
-long do_arch_prctl_common(struct task_struct *task, int option,
-			  unsigned long arg2);
+long do_arch_prctl_common(int option, unsigned long arg2);
 
 #endif /* _ASM_X86_PROTO_H */

arch/x86/include/asm/topology.h

@@ -212,30 +212,19 @@ static inline long arch_scale_freq_capacity(int cpu)
 }
 #define arch_scale_freq_capacity arch_scale_freq_capacity
 
-extern void arch_scale_freq_tick(void);
-#define arch_scale_freq_tick arch_scale_freq_tick
-
 extern void arch_set_max_freq_ratio(bool turbo_disabled);
-void init_freq_invariance(bool secondary, bool cppc_ready);
+extern void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled);
 #else
-static inline void arch_set_max_freq_ratio(bool turbo_disabled)
-{
-}
-static inline void init_freq_invariance(bool secondary, bool cppc_ready)
-{
-}
+static inline void arch_set_max_freq_ratio(bool turbo_disabled) { }
+static inline void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { }
 #endif
 
+extern void arch_scale_freq_tick(void);
+#define arch_scale_freq_tick arch_scale_freq_tick
+
 #ifdef CONFIG_ACPI_CPPC_LIB
 void init_freq_invariance_cppc(void);
 #define arch_init_invariance_cppc init_freq_invariance_cppc
-
-bool amd_set_max_freq_ratio(u64 *ratio);
-#else
-static inline bool amd_set_max_freq_ratio(u64 *ratio)
-{
-	return false;
-}
 #endif
 
 #endif /* _ASM_X86_TOPOLOGY_H */

arch/x86/kernel/acpi/cppc.c

@@ -50,20 +50,17 @@ int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
 	return err;
 }
 
-bool amd_set_max_freq_ratio(u64 *ratio)
+static void amd_set_max_freq_ratio(void)
 {
 	struct cppc_perf_caps perf_caps;
 	u64 highest_perf, nominal_perf;
 	u64 perf_ratio;
 	int rc;
 
-	if (!ratio)
-		return false;
-
 	rc = cppc_get_perf_caps(0, &perf_caps);
 	if (rc) {
 		pr_debug("Could not retrieve perf counters (%d)\n", rc);
-		return false;
+		return;
 	}
 
 	highest_perf = amd_get_highest_perf();
@@ -71,7 +68,7 @@ bool amd_set_max_freq_ratio(u64 *ratio)
 
 	if (!highest_perf || !nominal_perf) {
 		pr_debug("Could not retrieve highest or nominal performance\n");
-		return false;
+		return;
 	}
 
 	perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf);
@@ -79,25 +76,27 @@ bool amd_set_max_freq_ratio(u64 *ratio)
 	perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1;
 	if (!perf_ratio) {
 		pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n");
-		return false;
+		return;
 	}
 
-	*ratio = perf_ratio;
-	arch_set_max_freq_ratio(false);
-
-	return true;
+	freq_invariance_set_perf_ratio(perf_ratio, false);
 }
 
 static DEFINE_MUTEX(freq_invariance_lock);
 
 void init_freq_invariance_cppc(void)
 {
-	static bool secondary;
+	static bool init_done;
 
-	mutex_lock(&freq_invariance_lock);
+	if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
+		return;
 
-	init_freq_invariance(secondary, true);
-	secondary = true;
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+		return;
 
+	mutex_lock(&freq_invariance_lock);
+	if (!init_done)
+		amd_set_max_freq_ratio();
+	init_done = true;
 	mutex_unlock(&freq_invariance_lock);
 }

arch/x86/kernel/cpu/aperfmperf.c

@@ -6,146 +6,446 @@
  * Copyright (C) 2017 Intel Corp.
  * Author: Len Brown <len.brown@intel.com>
  */
-
+#include <linux/cpufreq.h>
 #include <linux/delay.h>
 #include <linux/ktime.h>
 #include <linux/math64.h>
 #include <linux/percpu.h>
-#include <linux/cpufreq.h>
-#include <linux/smp.h>
-#include <linux/sched/isolation.h>
 #include <linux/rcupdate.h>
+#include <linux/sched/isolation.h>
+#include <linux/sched/topology.h>
+#include <linux/smp.h>
+#include <linux/syscore_ops.h>
+
+#include <asm/cpu.h>
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
 
 #include "cpu.h"
 
-struct aperfmperf_sample {
-	unsigned int	khz;
-	atomic_t	scfpending;
-	ktime_t	time;
-	u64	aperf;
-	u64	mperf;
+struct aperfmperf {
+	seqcount_t	seq;
+	unsigned long	last_update;
+	u64		acnt;
+	u64		mcnt;
+	u64		aperf;
+	u64		mperf;
 };
 
-static DEFINE_PER_CPU(struct aperfmperf_sample, samples);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct aperfmperf, cpu_samples) = {
+	.seq = SEQCNT_ZERO(cpu_samples.seq)
+};
 
-#define APERFMPERF_CACHE_THRESHOLD_MS	10
-#define APERFMPERF_REFRESH_DELAY_MS	10
-#define APERFMPERF_STALE_THRESHOLD_MS	1000
+static void init_counter_refs(void)
+{
+	u64 aperf, mperf;
+
+	rdmsrl(MSR_IA32_APERF, aperf);
+	rdmsrl(MSR_IA32_MPERF, mperf);
 
+	this_cpu_write(cpu_samples.aperf, aperf);
+	this_cpu_write(cpu_samples.mperf, mperf);
+}
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
 /*
- * aperfmperf_snapshot_khz()
- * On the current CPU, snapshot APERF, MPERF, and jiffies
- * unless we already did it within 10ms
- * calculate kHz, save snapshot
+ * APERF/MPERF frequency ratio computation.
+ *
+ * The scheduler wants to do frequency invariant accounting and needs a <1
+ * ratio to account for the 'current' frequency, corresponding to
+ * freq_curr / freq_max.
+ *
+ * Since the frequency freq_curr on x86 is controlled by micro-controller and
+ * our P-state setting is little more than a request/hint, we need to observe
+ * the effective frequency 'BusyMHz', i.e. the average frequency over a time
+ * interval after discarding idle time. This is given by:
+ *
+ *   BusyMHz = delta_APERF / delta_MPERF * freq_base
+ *
+ * where freq_base is the max non-turbo P-state.
+ *
+ * The freq_max term has to be set to a somewhat arbitrary value, because we
+ * can't know which turbo states will be available at a given point in time:
+ * it all depends on the thermal headroom of the entire package. We set it to
+ * the turbo level with 4 cores active.
+ *
+ * Benchmarks show that's a good compromise between the 1C turbo ratio
+ * (freq_curr/freq_max would rarely reach 1) and something close to freq_base,
+ * which would ignore the entire turbo range (a conspicuous part, making
+ * freq_curr/freq_max always maxed out).
+ *
+ * An exception to the heuristic above is the Atom uarch, where we choose the
+ * highest turbo level for freq_max since Atom's are generally oriented towards
+ * power efficiency.
+ *
+ * Setting freq_max to anything less than the 1C turbo ratio makes the ratio
+ * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1.
  */
-static void aperfmperf_snapshot_khz(void *dummy)
+
+DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key);
+
+static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE;
+static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE;
+
+void arch_set_max_freq_ratio(bool turbo_disabled)
 {
-	u64 aperf, aperf_delta;
-	u64 mperf, mperf_delta;
-	struct aperfmperf_sample *s = this_cpu_ptr(&samples);
-	unsigned long flags;
+	arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE :
+					arch_turbo_freq_ratio;
+}
+EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio);
 
-	local_irq_save(flags);
-	rdmsrl(MSR_IA32_APERF, aperf);
-	rdmsrl(MSR_IA32_MPERF, mperf);
-	local_irq_restore(flags);
+static bool __init turbo_disabled(void)
+{
+	u64 misc_en;
+	int err;
+
+	err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en);
+	if (err)
+		return false;
+
+	return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
+}
+
+static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
+{
+	int err;
+
+	err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq);
+	if (err)
+		return false;
+
+	err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq);
+	if (err)
+		return false;
+
+	*base_freq = (*base_freq >> 16) & 0x3F;     /* max P state */
+	*turbo_freq = *turbo_freq & 0x3F;           /* 1C turbo    */
+
+	return true;
+}
+
+#define X86_MATCH(model)					\
+	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6,		\
+		INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL)
+
+static const struct x86_cpu_id has_knl_turbo_ratio_limits[] __initconst = {
+	X86_MATCH(XEON_PHI_KNL),
+	X86_MATCH(XEON_PHI_KNM),
+	{}
+};
+
+static const struct x86_cpu_id has_skx_turbo_ratio_limits[] __initconst = {
+	X86_MATCH(SKYLAKE_X),
+	{}
+};
+
+static const struct x86_cpu_id has_glm_turbo_ratio_limits[] __initconst = {
+	X86_MATCH(ATOM_GOLDMONT),
+	X86_MATCH(ATOM_GOLDMONT_D),
+	X86_MATCH(ATOM_GOLDMONT_PLUS),
+	{}
+};
+
+static bool __init knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
+					  int num_delta_fratio)
+{
+	int fratio, delta_fratio, found;
+	int err, i;
+	u64 msr;
+
+	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+	if (err)
+		return false;
+
+	*base_freq = (*base_freq >> 8) & 0xFF;	    /* max P state */
+
+	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
+	if (err)
+		return false;
+
+	fratio = (msr >> 8) & 0xFF;
+	i = 16;
+	found = 0;
+	do {
+		if (found >= num_delta_fratio) {
+			*turbo_freq = fratio;
+			return true;
+		}
+
+		delta_fratio = (msr >> (i + 5)) & 0x7;
+
+		if (delta_fratio) {
+			found += 1;
+			fratio -= delta_fratio;
+		}
+
+		i += 8;
+	} while (i < 64);
+
+	return true;
+}
+
+static bool __init skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
+{
+	u64 ratios, counts;
+	u32 group_size;
+	int err, i;
+
+	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+	if (err)
+		return false;
+
+	*base_freq = (*base_freq >> 8) & 0xFF;      /* max P state */
+
+	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios);
+	if (err)
+		return false;
+
+	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts);
+	if (err)
+		return false;
+
+	for (i = 0; i < 64; i += 8) {
+		group_size = (counts >> i) & 0xFF;
+		if (group_size >= size) {
+			*turbo_freq = (ratios >> i) & 0xFF;
+			return true;
+		}
+	}
+
+	return false;
+}
 
-	aperf_delta = aperf - s->aperf;
-	mperf_delta = mperf - s->mperf;
+static bool __init core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
+{
+	u64 msr;
+	int err;
+
+	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+	if (err)
+		return false;
+
+	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
+	if (err)
+		return false;
+
+	*base_freq = (*base_freq >> 8) & 0xFF;    /* max P state */
+	*turbo_freq = (msr >> 24) & 0xFF;         /* 4C turbo    */
+
+	/* The CPU may have less than 4 cores */
+	if (!*turbo_freq)
+		*turbo_freq = msr & 0xFF;         /* 1C turbo    */
+
+	return true;
+}
+
+static bool __init intel_set_max_freq_ratio(void)
+{
+	u64 base_freq, turbo_freq;
+	u64 turbo_ratio;
 
+	if (slv_set_max_freq_ratio(&base_freq, &turbo_freq))
+		goto out;
+
+	if (x86_match_cpu(has_glm_turbo_ratio_limits) &&
+	    skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
+		goto out;
+
+	if (x86_match_cpu(has_knl_turbo_ratio_limits) &&
+	    knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
+		goto out;
+
+	if (x86_match_cpu(has_skx_turbo_ratio_limits) &&
+	    skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4))
+		goto out;
+
+	if (core_set_max_freq_ratio(&base_freq, &turbo_freq))
+		goto out;
+
+	return false;
+
+out:
 	/*
-	 * There is no architectural guarantee that MPERF
-	 * increments faster than we can read it.
+	 * Some hypervisors advertise X86_FEATURE_APERFMPERF
+	 * but then fill all MSR's with zeroes.
+	 * Some CPUs have turbo boost but don't declare any turbo ratio
+	 * in MSR_TURBO_RATIO_LIMIT.
 	 */
-	if (mperf_delta == 0)
-		return;
+	if (!base_freq || !turbo_freq) {
+		pr_debug("Couldn't determine cpu base or turbo frequency, necessary for scale-invariant accounting.\n");
+		return false;
+	}
 
-	s->time = ktime_get();
-	s->aperf = aperf;
-	s->mperf = mperf;
-	s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
-	atomic_set_release(&s->scfpending, 0);
+	turbo_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq);
+	if (!turbo_ratio) {
+		pr_debug("Non-zero turbo and base frequencies led to a 0 ratio.\n");
+		return false;
+	}
+
+	arch_turbo_freq_ratio = turbo_ratio;
+	arch_set_max_freq_ratio(turbo_disabled());
+
+	return true;
 }
 
-static bool aperfmperf_snapshot_cpu(int cpu, ktime_t now, bool wait)
+#ifdef CONFIG_PM_SLEEP
+static struct syscore_ops freq_invariance_syscore_ops = {
+	.resume = init_counter_refs,
+};
+
+static void register_freq_invariance_syscore_ops(void)
 {
-	s64 time_delta = ktime_ms_delta(now, per_cpu(samples.time, cpu));
-	struct aperfmperf_sample *s = per_cpu_ptr(&samples, cpu);
+	register_syscore_ops(&freq_invariance_syscore_ops);
+}
+#else
+static inline void register_freq_invariance_syscore_ops(void) {}
+#endif
 
-	/* Don't bother re-computing within the cache threshold time. */
-	if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
-		return true;
+static void freq_invariance_enable(void)
+{
+	if (static_branch_unlikely(&arch_scale_freq_key)) {
+		WARN_ON_ONCE(1);
+		return;
+	}
+	static_branch_enable(&arch_scale_freq_key);
+	register_freq_invariance_syscore_ops();
+	pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio);
+}
+
+void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled)
+{
+	arch_turbo_freq_ratio = ratio;
+	arch_set_max_freq_ratio(turbo_disabled);
+	freq_invariance_enable();
+}
+
+static void __init bp_init_freq_invariance(void)
+{
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return;
 
-	if (!atomic_xchg(&s->scfpending, 1) || wait)
-		smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, wait);
+	if (intel_set_max_freq_ratio())
+		freq_invariance_enable();
+}
 
-	/* Return false if the previous iteration was too long ago. */
-	return time_delta <= APERFMPERF_STALE_THRESHOLD_MS;
+static void disable_freq_invariance_workfn(struct work_struct *work)
+{
+	static_branch_disable(&arch_scale_freq_key);
 }
 
-unsigned int aperfmperf_get_khz(int cpu)
+static DECLARE_WORK(disable_freq_invariance_work,
+		    disable_freq_invariance_workfn);
+
+DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;
+
+static void scale_freq_tick(u64 acnt, u64 mcnt)
 {
-	if (!cpu_khz)
-		return 0;
+	u64 freq_scale;
 
-	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
-		return 0;
+	if (!arch_scale_freq_invariant())
+		return;
 
-	if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
-		return 0;
+	if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt))
+		goto error;
 
-	if (rcu_is_idle_cpu(cpu))
-		return 0; /* Idle CPUs are completely uninteresting. */
+	if (check_mul_overflow(mcnt, arch_max_freq_ratio, &mcnt) || !mcnt)
+		goto error;
 
-	aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
-	return per_cpu(samples.khz, cpu);
+	freq_scale = div64_u64(acnt, mcnt);
+	if (!freq_scale)
+		goto error;
+
+	if (freq_scale > SCHED_CAPACITY_SCALE)
+		freq_scale = SCHED_CAPACITY_SCALE;
+
+	this_cpu_write(arch_freq_scale, freq_scale);
+	return;
+
+error:
+	pr_warn("Scheduler frequency invariance went wobbly, disabling!\n");
+	schedule_work(&disable_freq_invariance_work);
 }
+#else
+static inline void bp_init_freq_invariance(void) { }
+static inline void scale_freq_tick(u64 acnt, u64 mcnt) { }
+#endif /* CONFIG_X86_64 && CONFIG_SMP */
 
-void arch_freq_prepare_all(void)
+void arch_scale_freq_tick(void)
 {
-	ktime_t now = ktime_get();
-	bool wait = false;
-	int cpu;
+	struct aperfmperf *s = this_cpu_ptr(&cpu_samples);
+	u64 acnt, mcnt, aperf, mperf;
 
-	if (!cpu_khz)
+	if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
 		return;
 
-	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
-		return;
+	rdmsrl(MSR_IA32_APERF, aperf);
+	rdmsrl(MSR_IA32_MPERF, mperf);
+	acnt = aperf - s->aperf;
+	mcnt = mperf - s->mperf;
 
-	for_each_online_cpu(cpu) {
-		if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
-			continue;
-		if (rcu_is_idle_cpu(cpu))
-			continue; /* Idle CPUs are completely uninteresting. */
-		if (!aperfmperf_snapshot_cpu(cpu, now, false))
-			wait = true;
-	}
+	s->aperf = aperf;
+	s->mperf = mperf;
+
+	raw_write_seqcount_begin(&s->seq);
+	s->last_update = jiffies;
+	s->acnt = acnt;
+	s->mcnt = mcnt;
+	raw_write_seqcount_end(&s->seq);
 
-	if (wait)
-		msleep(APERFMPERF_REFRESH_DELAY_MS);
+	scale_freq_tick(acnt, mcnt);
 }
 
+/*
+ * Discard samples older than the define maximum sample age of 20ms. There
+ * is no point in sending IPIs in such a case. If the scheduler tick was
+ * not running then the CPU is either idle or isolated.
+ */
+#define MAX_SAMPLE_AGE	((unsigned long)HZ / 50)
+
 unsigned int arch_freq_get_on_cpu(int cpu)
 {
-	struct aperfmperf_sample *s = per_cpu_ptr(&samples, cpu);
+	struct aperfmperf *s = per_cpu_ptr(&cpu_samples, cpu);
+	unsigned int seq, freq;
+	unsigned long last;
+	u64 acnt, mcnt;
 
-	if (!cpu_khz)
-		return 0;
+	if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
+		goto fallback;
 
-	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
-		return 0;
+	do {
+		seq = raw_read_seqcount_begin(&s->seq);
+		last = s->last_update;
+		acnt = s->acnt;
+		mcnt = s->mcnt;
+	} while (read_seqcount_retry(&s->seq, seq));
 
-	if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
-		return 0;
+	/*
+	 * Bail on invalid count and when the last update was too long ago,
+	 * which covers idle and NOHZ full CPUs.
+	 */
+	if (!mcnt || (jiffies - last) > MAX_SAMPLE_AGE)
+		goto fallback;
+
+	return div64_u64((cpu_khz * acnt), mcnt);
+
+fallback:
+	freq = cpufreq_quick_get(cpu);
+	return freq ? freq : cpu_khz;
+}
 
-	if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
-		return per_cpu(samples.khz, cpu);
+static int __init bp_init_aperfmperf(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
+		return 0;
 
-	msleep(APERFMPERF_REFRESH_DELAY_MS);
-	atomic_set(&s->scfpending, 1);
-	smp_mb(); /* ->scfpending before smp_call_function_single(). */
-	smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
+	init_counter_refs();
+	bp_init_freq_invariance();
+	return 0;
+}
+early_initcall(bp_init_aperfmperf);
 
-	return per_cpu(samples.khz, cpu);
+void ap_init_aperfmperf(void)
+{
+	if (cpu_feature_enabled(X86_FEATURE_APERFMPERF))
+		init_counter_refs();
 }

arch/x86/kernel/cpu/proc.c

@@ -84,14 +84,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		seq_printf(m, "microcode\t: 0x%x\n", c->microcode);
 
 	if (cpu_has(c, X86_FEATURE_TSC)) {
-		unsigned int freq = aperfmperf_get_khz(cpu);
-
-		if (!freq)
-			freq = cpufreq_quick_get(cpu);
-		if (!freq)
-			freq = cpu_khz;
-		seq_printf(m, "cpu MHz\t\t: %u.%03u\n",
-			   freq / 1000, (freq % 1000));
+		unsigned int freq = arch_freq_get_on_cpu(cpu);
+
+		seq_printf(m, "cpu MHz\t\t: %u.%03u\n", freq / 1000, (freq % 1000));
 	}
 
 	/* Cache size */

arch/x86/kernel/cpu/resctrl/rdtgroup.c

@@ -341,14 +341,14 @@ static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
 
 	/* Check whether cpus belong to parent ctrl group */
 	cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask);
-	if (cpumask_weight(tmpmask)) {
+	if (!cpumask_empty(tmpmask)) {
 		rdt_last_cmd_puts("Can only add CPUs to mongroup that belong to parent\n");
 		return -EINVAL;
 	}
 
 	/* Check whether cpus are dropped from this group */
 	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
-	if (cpumask_weight(tmpmask)) {
+	if (!cpumask_empty(tmpmask)) {
 		/* Give any dropped cpus to parent rdtgroup */
 		cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask);
 		update_closid_rmid(tmpmask, prgrp);
@@ -359,7 +359,7 @@ static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
 	 * and update per-cpu rmid
 	 */
 	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
-	if (cpumask_weight(tmpmask)) {
+	if (!cpumask_empty(tmpmask)) {
 		head = &prgrp->mon.crdtgrp_list;
 		list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
 			if (crgrp == rdtgrp)
@@ -394,7 +394,7 @@ static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
 
 	/* Check whether cpus are dropped from this group */
 	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
-	if (cpumask_weight(tmpmask)) {
+	if (!cpumask_empty(tmpmask)) {
 		/* Can't drop from default group */
 		if (rdtgrp == &rdtgroup_default) {
 			rdt_last_cmd_puts("Can't drop CPUs from default group\n");
@@ -413,12 +413,12 @@ static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
 	 * and update per-cpu closid/rmid.
 	 */
 	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
-	if (cpumask_weight(tmpmask)) {
+	if (!cpumask_empty(tmpmask)) {
 		list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) {
 			if (r == rdtgrp)
 				continue;
 			cpumask_and(tmpmask1, &r->cpu_mask, tmpmask);
-			if (cpumask_weight(tmpmask1))
+			if (!cpumask_empty(tmpmask1))
 				cpumask_rdtgrp_clear(r, tmpmask1);
 		}
 		update_closid_rmid(tmpmask, rdtgrp);
@@ -488,7 +488,7 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 
 	/* check that user didn't specify any offline cpus */
 	cpumask_andnot(tmpmask, newmask, cpu_online_mask);
-	if (cpumask_weight(tmpmask)) {
+	if (!cpumask_empty(tmpmask)) {
 		ret = -EINVAL;
 		rdt_last_cmd_puts("Can only assign online CPUs\n");
 		goto unlock;

arch/x86/kernel/fpu/xstate.c

@@ -1687,16 +1687,13 @@ EXPORT_SYMBOL_GPL(xstate_get_guest_group_perm);
  * e.g. for AMX which requires XFEATURE_XTILE_CFG(17) and
  * XFEATURE_XTILE_DATA(18) this would be XFEATURE_XTILE_DATA(18).
  */
-long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2)
+long fpu_xstate_prctl(int option, unsigned long arg2)
 {
 	u64 __user *uptr = (u64 __user *)arg2;
 	u64 permitted, supported;
 	unsigned long idx = arg2;
 	bool guest = false;
 
-	if (tsk != current)
-		return -EPERM;
-
 	switch (option) {
 	case ARCH_GET_XCOMP_SUPP:
 		supported = fpu_user_cfg.max_features |	fpu_user_cfg.legacy_features;

arch/x86/kernel/process.c

@@ -335,7 +335,7 @@ static int get_cpuid_mode(void)
 	return !test_thread_flag(TIF_NOCPUID);
 }
 
-static int set_cpuid_mode(struct task_struct *task, unsigned long cpuid_enabled)
+static int set_cpuid_mode(unsigned long cpuid_enabled)
 {
 	if (!boot_cpu_has(X86_FEATURE_CPUID_FAULT))
 		return -ENODEV;
@@ -406,7 +406,7 @@ static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm)
 }
 
 /**
- * tss_update_io_bitmap - Update I/O bitmap before exiting to usermode
+ * native_tss_update_io_bitmap - Update I/O bitmap before exiting to user mode
  */
 void native_tss_update_io_bitmap(void)
 {
@@ -989,20 +989,19 @@ unsigned long __get_wchan(struct task_struct *p)
 	return addr;
 }
 
-long do_arch_prctl_common(struct task_struct *task, int option,
-			  unsigned long arg2)
+long do_arch_prctl_common(int option, unsigned long arg2)
 {
 	switch (option) {
 	case ARCH_GET_CPUID:
 		return get_cpuid_mode();
 	case ARCH_SET_CPUID:
-		return set_cpuid_mode(task, arg2);
+		return set_cpuid_mode(arg2);
 	case ARCH_GET_XCOMP_SUPP:
 	case ARCH_GET_XCOMP_PERM:
 	case ARCH_REQ_XCOMP_PERM:
 	case ARCH_GET_XCOMP_GUEST_PERM:
 	case ARCH_REQ_XCOMP_GUEST_PERM:
-		return fpu_xstate_prctl(task, option, arg2);
+		return fpu_xstate_prctl(option, arg2);
 	}
 
 	return -EINVAL;

arch/x86/kernel/process_32.c

@@ -222,5 +222,5 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
 {
-	return do_arch_prctl_common(current, option, arg2);
+	return do_arch_prctl_common(option, arg2);
 }

arch/x86/kernel/process_64.c

@@ -844,7 +844,7 @@ SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
 
 	ret = do_arch_prctl_64(current, option, arg2);
 	if (ret == -EINVAL)
-		ret = do_arch_prctl_common(current, option, arg2);
+		ret = do_arch_prctl_common(option, arg2);
 
 	return ret;
 }
@@ -852,7 +852,7 @@ SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
 #ifdef CONFIG_IA32_EMULATION
 COMPAT_SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
 {
-	return do_arch_prctl_common(current, option, arg2);
+	return do_arch_prctl_common(option, arg2);
 }
 #endif
 

arch/x86/kernel/smpboot.c

@@ -56,7 +56,6 @@
 #include <linux/numa.h>
 #include <linux/pgtable.h>
 #include <linux/overflow.h>
-#include <linux/syscore_ops.h>
 
 #include <asm/acpi.h>
 #include <asm/desc.h>
@@ -188,7 +187,7 @@ static void smp_callin(void)
 	 */
 	set_cpu_sibling_map(raw_smp_processor_id());
 
-	init_freq_invariance(true, false);
+	ap_init_aperfmperf();
 
 	/*
 	 * Get our bogomips.
@@ -1406,7 +1405,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 {
 	smp_prepare_cpus_common();
 
-	init_freq_invariance(false, false);
 	smp_sanity_check();
 
 	switch (apic_intr_mode) {
@@ -1858,357 +1856,3 @@ void native_play_dead(void)
 }
 
 #endif
-
-#ifdef CONFIG_X86_64
-/*
- * APERF/MPERF frequency ratio computation.
- *
- * The scheduler wants to do frequency invariant accounting and needs a <1
- * ratio to account for the 'current' frequency, corresponding to
- * freq_curr / freq_max.
- *
- * Since the frequency freq_curr on x86 is controlled by micro-controller and
- * our P-state setting is little more than a request/hint, we need to observe
- * the effective frequency 'BusyMHz', i.e. the average frequency over a time
- * interval after discarding idle time. This is given by:
- *
- *   BusyMHz = delta_APERF / delta_MPERF * freq_base
- *
- * where freq_base is the max non-turbo P-state.
- *
- * The freq_max term has to be set to a somewhat arbitrary value, because we
- * can't know which turbo states will be available at a given point in time:
- * it all depends on the thermal headroom of the entire package. We set it to
- * the turbo level with 4 cores active.
- *
- * Benchmarks show that's a good compromise between the 1C turbo ratio
- * (freq_curr/freq_max would rarely reach 1) and something close to freq_base,
- * which would ignore the entire turbo range (a conspicuous part, making
- * freq_curr/freq_max always maxed out).
- *
- * An exception to the heuristic above is the Atom uarch, where we choose the
- * highest turbo level for freq_max since Atom's are generally oriented towards
- * power efficiency.
- *
- * Setting freq_max to anything less than the 1C turbo ratio makes the ratio
- * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1.
- */
-
-DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key);
-
-static DEFINE_PER_CPU(u64, arch_prev_aperf);
-static DEFINE_PER_CPU(u64, arch_prev_mperf);
-static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE;
-static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE;
-
-void arch_set_max_freq_ratio(bool turbo_disabled)
-{
-	arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE :
-					arch_turbo_freq_ratio;
-}
-EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio);
-
-static bool turbo_disabled(void)
-{
-	u64 misc_en;
-	int err;
-
-	err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en);
-	if (err)
-		return false;
-
-	return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
-}
-
-static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
-{
-	int err;
-
-	err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq);
-	if (err)
-		return false;
-
-	err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq);
-	if (err)
-		return false;
-
-	*base_freq = (*base_freq >> 16) & 0x3F;     /* max P state */
-	*turbo_freq = *turbo_freq & 0x3F;           /* 1C turbo    */
-
-	return true;
-}
-
-#define X86_MATCH(model)					\
-	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6,		\
-		INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL)
-
-static const struct x86_cpu_id has_knl_turbo_ratio_limits[] = {
-	X86_MATCH(XEON_PHI_KNL),
-	X86_MATCH(XEON_PHI_KNM),
-	{}
-};
-
-static const struct x86_cpu_id has_skx_turbo_ratio_limits[] = {
-	X86_MATCH(SKYLAKE_X),
-	{}
-};
-
-static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = {
-	X86_MATCH(ATOM_GOLDMONT),
-	X86_MATCH(ATOM_GOLDMONT_D),
-	X86_MATCH(ATOM_GOLDMONT_PLUS),
-	{}
-};
-
-static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
-				int num_delta_fratio)
-{
-	int fratio, delta_fratio, found;
-	int err, i;
-	u64 msr;
-
-	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
-	if (err)
-		return false;
-
-	*base_freq = (*base_freq >> 8) & 0xFF;	    /* max P state */
-
-	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
-	if (err)
-		return false;
-
-	fratio = (msr >> 8) & 0xFF;
-	i = 16;
-	found = 0;
-	do {
-		if (found >= num_delta_fratio) {
-			*turbo_freq = fratio;
-			return true;
-		}
-
-		delta_fratio = (msr >> (i + 5)) & 0x7;
-
-		if (delta_fratio) {
-			found += 1;
-			fratio -= delta_fratio;
-		}
-
-		i += 8;
-	} while (i < 64);
-
-	return true;
-}
-
-static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
-{
-	u64 ratios, counts;
-	u32 group_size;
-	int err, i;
-
-	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
-	if (err)
-		return false;
-
-	*base_freq = (*base_freq >> 8) & 0xFF;      /* max P state */
-
-	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios);
-	if (err)
-		return false;
-
-	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts);
-	if (err)
-		return false;
-
-	for (i = 0; i < 64; i += 8) {
-		group_size = (counts >> i) & 0xFF;
-		if (group_size >= size) {
-			*turbo_freq = (ratios >> i) & 0xFF;
-			return true;
-		}
-	}
-
-	return false;
-}
-
-static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
-{
-	u64 msr;
-	int err;
-
-	err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
-	if (err)
-		return false;
-
-	err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
-	if (err)
-		return false;
-
-	*base_freq = (*base_freq >> 8) & 0xFF;    /* max P state */
-	*turbo_freq = (msr >> 24) & 0xFF;         /* 4C turbo    */
-
-	/* The CPU may have less than 4 cores */
-	if (!*turbo_freq)
-		*turbo_freq = msr & 0xFF;         /* 1C turbo    */
-
-	return true;
-}
-
-static bool intel_set_max_freq_ratio(void)
-{
-	u64 base_freq, turbo_freq;
-	u64 turbo_ratio;
-
-	if (slv_set_max_freq_ratio(&base_freq, &turbo_freq))
-		goto out;
-
-	if (x86_match_cpu(has_glm_turbo_ratio_limits) &&
-	    skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
-		goto out;
-
-	if (x86_match_cpu(has_knl_turbo_ratio_limits) &&
-	    knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1))
-		goto out;
-
-	if (x86_match_cpu(has_skx_turbo_ratio_limits) &&
-	    skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4))
-		goto out;
-
-	if (core_set_max_freq_ratio(&base_freq, &turbo_freq))
-		goto out;
-
-	return false;
-
-out:
-	/*
-	 * Some hypervisors advertise X86_FEATURE_APERFMPERF
-	 * but then fill all MSR's with zeroes.
-	 * Some CPUs have turbo boost but don't declare any turbo ratio
-	 * in MSR_TURBO_RATIO_LIMIT.
-	 */
-	if (!base_freq || !turbo_freq) {
-		pr_debug("Couldn't determine cpu base or turbo frequency, necessary for scale-invariant accounting.\n");
-		return false;
-	}
-
-	turbo_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq);
-	if (!turbo_ratio) {
-		pr_debug("Non-zero turbo and base frequencies led to a 0 ratio.\n");
-		return false;
-	}
-
-	arch_turbo_freq_ratio = turbo_ratio;
-	arch_set_max_freq_ratio(turbo_disabled());
-
-	return true;
-}
-
-static void init_counter_refs(void)
-{
-	u64 aperf, mperf;
-
-	rdmsrl(MSR_IA32_APERF, aperf);
-	rdmsrl(MSR_IA32_MPERF, mperf);
-
-	this_cpu_write(arch_prev_aperf, aperf);
-	this_cpu_write(arch_prev_mperf, mperf);
-}
-
-#ifdef CONFIG_PM_SLEEP
-static struct syscore_ops freq_invariance_syscore_ops = {
-	.resume = init_counter_refs,
-};
-
-static void register_freq_invariance_syscore_ops(void)
-{
-	/* Bail out if registered already. */
-	if (freq_invariance_syscore_ops.node.prev)
-		return;
-
-	register_syscore_ops(&freq_invariance_syscore_ops);
-}
-#else
-static inline void register_freq_invariance_syscore_ops(void) {}
-#endif
-
-void init_freq_invariance(bool secondary, bool cppc_ready)
-{
-	bool ret = false;
-
-	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
-		return;
-
-	if (secondary) {
-		if (static_branch_likely(&arch_scale_freq_key)) {
-			init_counter_refs();
-		}
-		return;
-	}
-
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
-		ret = intel_set_max_freq_ratio();
-	else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
-		if (!cppc_ready) {
-			return;
-		}
-		ret = amd_set_max_freq_ratio(&arch_turbo_freq_ratio);
-	}
-
-	if (ret) {
-		init_counter_refs();
-		static_branch_enable(&arch_scale_freq_key);
-		register_freq_invariance_syscore_ops();
-		pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio);
-	} else {
-		pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n");
-	}
-}
-
-static void disable_freq_invariance_workfn(struct work_struct *work)
-{
-	static_branch_disable(&arch_scale_freq_key);
-}
-
-static DECLARE_WORK(disable_freq_invariance_work,
-		    disable_freq_invariance_workfn);
-
-DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;
-
-void arch_scale_freq_tick(void)
-{
-	u64 freq_scale;
-	u64 aperf, mperf;
-	u64 acnt, mcnt;
-
-	if (!arch_scale_freq_invariant())
-		return;
-
-	rdmsrl(MSR_IA32_APERF, aperf);
-	rdmsrl(MSR_IA32_MPERF, mperf);
-
-	acnt = aperf - this_cpu_read(arch_prev_aperf);
-	mcnt = mperf - this_cpu_read(arch_prev_mperf);
-
-	this_cpu_write(arch_prev_aperf, aperf);
-	this_cpu_write(arch_prev_mperf, mperf);
-
-	if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt))
-		goto error;
-
-	if (check_mul_overflow(mcnt, arch_max_freq_ratio, &mcnt) || !mcnt)
-		goto error;
-
-	freq_scale = div64_u64(acnt, mcnt);
-	if (!freq_scale)
-		goto error;
-
-	if (freq_scale > SCHED_CAPACITY_SCALE)
-		freq_scale = SCHED_CAPACITY_SCALE;
-
-	this_cpu_write(arch_freq_scale, freq_scale);
-	return;
-
-error:
-	pr_warn("Scheduler frequency invariance went wobbly, disabling!\n");
-	schedule_work(&disable_freq_invariance_work);
-}
-#endif /* CONFIG_X86_64 */

arch/x86/mm/amdtopology.c

@@ -154,7 +154,7 @@ int __init amd_numa_init(void)
 		node_set(nodeid, numa_nodes_parsed);
 	}
 
-	if (!nodes_weight(numa_nodes_parsed))
+	if (nodes_empty(numa_nodes_parsed))
 		return -ENOENT;
 
 	/*

arch/x86/mm/mmio-mod.c

@@ -400,7 +400,7 @@ static void leave_uniprocessor(void)
 	int cpu;
 	int err;
 
-	if (!cpumask_available(downed_cpus) || cpumask_weight(downed_cpus) == 0)
+	if (!cpumask_available(downed_cpus) || cpumask_empty(downed_cpus))
 		return;
 	pr_notice("Re-enabling CPUs...\n");
 	for_each_cpu(cpu, downed_cpus) {

arch/x86/mm/numa_emulation.c

@@ -123,7 +123,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei,
 	 * Continue to fill physical nodes with fake nodes until there is no
 	 * memory left on any of them.
 	 */
-	while (nodes_weight(physnode_mask)) {
+	while (!nodes_empty(physnode_mask)) {
 		for_each_node_mask(i, physnode_mask) {
 			u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN);
 			u64 start, limit, end;
@@ -270,7 +270,7 @@ static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei,
 	 * Fill physical nodes with fake nodes of size until there is no memory
 	 * left on any of them.
 	 */
-	while (nodes_weight(physnode_mask)) {
+	while (!nodes_empty(physnode_mask)) {
 		for_each_node_mask(i, physnode_mask) {
 			u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN);
 			u64 start, limit, end;

arch/x86/platform/uv/uv_nmi.c

@@ -985,7 +985,7 @@ static int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 
 	/* Clear global flags */
 	if (master) {
-		if (cpumask_weight(uv_nmi_cpu_mask))
+		if (!cpumask_empty(uv_nmi_cpu_mask))
 			uv_nmi_cleanup_mask();
 		atomic_set(&uv_nmi_cpus_in_nmi, -1);
 		atomic_set(&uv_nmi_cpu, -1);

fs/proc/cpuinfo.c

@@ -5,14 +5,10 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 
-__weak void arch_freq_prepare_all(void)
-{
-}
-
 extern const struct seq_operations cpuinfo_op;
+
 static int cpuinfo_open(struct inode *inode, struct file *file)
 {
-	arch_freq_prepare_all();
 	return seq_open(file, &cpuinfo_op);
 }
 

include/linux/cpufreq.h

@@ -1199,7 +1199,6 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
 			struct cpufreq_governor *old_gov) { }
 #endif
 
-extern void arch_freq_prepare_all(void);
 extern unsigned int arch_freq_get_on_cpu(int cpu);
 
 #ifndef arch_set_freq_scale