Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm…

…/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - membarrier updates (Mathieu Desnoyers)

 - SMP balancing optimizations (Mel Gorman)

 - stats update optimizations (Peter Zijlstra)

 - RT scheduler race fixes (Steven Rostedt)

 - misc fixes and updates

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Use a recently used CPU as an idle candidate and the basis for SIS
  sched/fair: Do not migrate if the prev_cpu is idle
  sched/fair: Restructure wake_affine*() to return a CPU id
  sched/fair: Remove unnecessary parameters from wake_affine_idle()
  sched/rt: Make update_curr_rt() more accurate
  sched/rt: Up the root domain ref count when passing it around via IPIs
  sched/rt: Use container_of() to get root domain in rto_push_irq_work_func()
  sched/core: Optimize update_stats_*()
  sched/core: Optimize ttwu_stat()
  membarrier/selftest: Test private expedited sync core command
  membarrier/arm64: Provide core serializing command
  membarrier/x86: Provide core serializing command
  membarrier: Provide core serializing command, *_SYNC_CORE
  lockin/x86: Implement sync_core_before_usermode()
  locking: Introduce sync_core_before_usermode()
  membarrier/selftest: Test global expedited command
  membarrier: Provide GLOBAL_EXPEDITED command
  membarrier: Document scheduler barrier requirements
  powerpc, membarrier: Skip memory barrier in switch_mm()
  membarrier/selftest: Test private expedited command

MAINTAINERS

@@ -9025,6 +9025,7 @@ L:	linux-kernel@vger.kernel.org
 S:	Supported
 F:	kernel/sched/membarrier.c
 F:	include/uapi/linux/membarrier.h
+F:	arch/powerpc/include/asm/membarrier.h
 
 MEMORY MANAGEMENT
 L:	linux-mm@kvack.org

arch/arm64/Kconfig

@@ -16,6 +16,7 @@ config ARM64
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX

arch/arm64/kernel/entry.S

@@ -324,6 +324,10 @@ alternative_else_nop_endif
 	ldp	x28, x29, [sp, #16 * 14]
 	ldr	lr, [sp, #S_LR]
 	add	sp, sp, #S_FRAME_SIZE		// restore sp
+	/*
+	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on eret context synchronization
+	 * when returning from IPI handler, and when returning to user-space.
+	 */
 
 	.if	\el == 0
 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0

arch/powerpc/Kconfig

@@ -141,6 +141,7 @@ config PPC
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PMEM_API                if PPC64
+	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX	if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION)

arch/powerpc/include/asm/membarrier.h

@@ -0,0 +1,27 @@
+#ifndef _ASM_POWERPC_MEMBARRIER_H
+#define _ASM_POWERPC_MEMBARRIER_H
+
+static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
+					     struct mm_struct *next,
+					     struct task_struct *tsk)
+{
+	/*
+	 * Only need the full barrier when switching between processes.
+	 * Barrier when switching from kernel to userspace is not
+	 * required here, given that it is implied by mmdrop(). Barrier
+	 * when switching from userspace to kernel is not needed after
+	 * store to rq->curr.
+	 */
+	if (likely(!(atomic_read(&next->membarrier_state) &
+		     (MEMBARRIER_STATE_PRIVATE_EXPEDITED |
+		      MEMBARRIER_STATE_GLOBAL_EXPEDITED)) || !prev))
+		return;
+
+	/*
+	 * The membarrier system call requires a full memory barrier
+	 * after storing to rq->curr, before going back to user-space.
+	 */
+	smp_mb();
+}
+
+#endif /* _ASM_POWERPC_MEMBARRIER_H */

arch/powerpc/mm/mmu_context.c

@@ -12,6 +12,7 @@
 
 #include <linux/mm.h>
 #include <linux/cpu.h>
+#include <linux/sched/mm.h>
 
 #include <asm/mmu_context.h>
 
@@ -58,6 +59,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		 *
 		 * On the read side the barrier is in pte_xchg(), which orders
 		 * the store to the PTE vs the load of mm_cpumask.
+		 *
+		 * This full barrier is needed by membarrier when switching
+		 * between processes after store to rq->curr, before user-space
+		 * memory accesses.
 		 */
 		smp_mb();
 
@@ -80,6 +85,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 
 	if (new_on_cpu)
 		radix_kvm_prefetch_workaround(next);
+	else
+		membarrier_arch_switch_mm(prev, next, tsk);
 
 	/*
 	 * The actual HW switching method differs between the various

arch/x86/Kconfig

@@ -55,13 +55,15 @@ config X86
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_KCOV			if X86_64
 	select ARCH_HAS_PHYS_TO_DMA
+	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_PMEM_API		if X86_64
 	select ARCH_HAS_REFCOUNT
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
+	select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_HAS_ZONE_DEVICE		if X86_64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG

arch/x86/entry/entry_32.S

@@ -566,6 +566,11 @@ restore_all:
 .Lrestore_nocheck:
 	RESTORE_REGS 4				# skip orig_eax/error_code
 .Lirq_return:
+	/*
+	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
+	 * when returning from IPI handler and when returning from
+	 * scheduler to user-space.
+	 */
 	INTERRUPT_RETURN
 
 .section .fixup, "ax"

arch/x86/entry/entry_64.S

@@ -691,6 +691,10 @@ GLOBAL(restore_regs_and_return_to_kernel)
 	POP_EXTRA_REGS
 	POP_C_REGS
 	addq	$8, %rsp	/* skip regs->orig_ax */
+	/*
+	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
+	 * when returning from IPI handler.
+	 */
 	INTERRUPT_RETURN
 
 ENTRY(native_iret)

arch/x86/include/asm/sync_core.h

@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_SYNC_CORE_H
+#define _ASM_X86_SYNC_CORE_H
+
+#include <linux/preempt.h>
+#include <asm/processor.h>
+#include <asm/cpufeature.h>
+
+/*
+ * Ensure that a core serializing instruction is issued before returning
+ * to user-mode. x86 implements return to user-space through sysexit,
+ * sysrel, and sysretq, which are not core serializing.
+ */
+static inline void sync_core_before_usermode(void)
+{
+	/* With PTI, we unconditionally serialize before running user code. */
+	if (static_cpu_has(X86_FEATURE_PTI))
+		return;
+	/*
+	 * Return from interrupt and NMI is done through iret, which is core
+	 * serializing.
+	 */
+	if (in_irq() || in_nmi())
+		return;
+	sync_core();
+}
+
+#endif /* _ASM_X86_SYNC_CORE_H */

arch/x86/mm/tlb.c

@@ -229,6 +229,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 #endif
 	this_cpu_write(cpu_tlbstate.is_lazy, false);
 
+	/*
+	 * The membarrier system call requires a full memory barrier and
+	 * core serialization before returning to user-space, after
+	 * storing to rq->curr. Writing to CR3 provides that full
+	 * memory barrier and core serializing instruction.
+	 */
 	if (real_prev == next) {
 		VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
 			   next->context.ctx_id);

include/linux/sched.h

@@ -555,6 +555,14 @@ struct task_struct {
 	unsigned long			wakee_flip_decay_ts;
 	struct task_struct		*last_wakee;
 
+	/*
+	 * recent_used_cpu is initially set as the last CPU used by a task
+	 * that wakes affine another task. Waker/wakee relationships can
+	 * push tasks around a CPU where each wakeup moves to the next one.
+	 * Tracking a recently used CPU allows a quick search for a recently
+	 * used CPU that may be idle.
+	 */
+	int				recent_used_cpu;
 	int				wake_cpu;
 #endif
 	int				on_rq;

include/linux/sched/mm.h

@@ -7,6 +7,7 @@
 #include <linux/sched.h>
 #include <linux/mm_types.h>
 #include <linux/gfp.h>
+#include <linux/sync_core.h>
 
 /*
  * Routines for handling mm_structs
@@ -194,18 +195,48 @@ static inline void memalloc_noreclaim_restore(unsigned int flags)
 
 #ifdef CONFIG_MEMBARRIER
 enum {
-	MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY	= (1U << 0),
-	MEMBARRIER_STATE_SWITCH_MM			= (1U << 1),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY		= (1U << 0),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED			= (1U << 1),
+	MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY			= (1U << 2),
+	MEMBARRIER_STATE_GLOBAL_EXPEDITED			= (1U << 3),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY	= (1U << 4),
+	MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE		= (1U << 5),
 };
 
+enum {
+	MEMBARRIER_FLAG_SYNC_CORE	= (1U << 0),
+};
+
+#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
+#include <asm/membarrier.h>
+#endif
+
+static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
+{
+	if (likely(!(atomic_read(&mm->membarrier_state) &
+		     MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE)))
+		return;
+	sync_core_before_usermode();
+}
+
 static inline void membarrier_execve(struct task_struct *t)
 {
 	atomic_set(&t->mm->membarrier_state, 0);
 }
 #else
+#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
+static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
+					     struct mm_struct *next,
+					     struct task_struct *tsk)
+{
+}
+#endif
 static inline void membarrier_execve(struct task_struct *t)
 {
 }
+static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
+{
+}
 #endif
 
 #endif /* _LINUX_SCHED_MM_H */

include/linux/sync_core.h

@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SYNC_CORE_H
+#define _LINUX_SYNC_CORE_H
+
+#ifdef CONFIG_ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
+#include <asm/sync_core.h>
+#else
+/*
+ * This is a dummy sync_core_before_usermode() implementation that can be used
+ * on all architectures which return to user-space through core serializing
+ * instructions.
+ * If your architecture returns to user-space through non-core-serializing
+ * instructions, you need to write your own functions.
+ */
+static inline void sync_core_before_usermode(void)
+{
+}
+#endif
+
+#endif /* _LINUX_SYNC_CORE_H */
+

include/uapi/linux/membarrier.h

@@ -31,7 +31,7 @@
  * enum membarrier_cmd - membarrier system call command
  * @MEMBARRIER_CMD_QUERY:   Query the set of supported commands. It returns
  *                          a bitmask of valid commands.
- * @MEMBARRIER_CMD_SHARED:  Execute a memory barrier on all running threads.
+ * @MEMBARRIER_CMD_GLOBAL:  Execute a memory barrier on all running threads.
  *                          Upon return from system call, the caller thread
  *                          is ensured that all running threads have passed
  *                          through a state where all memory accesses to
@@ -40,6 +40,28 @@
  *                          (non-running threads are de facto in such a
  *                          state). This covers threads from all processes
  *                          running on the system. This command returns 0.
+ * @MEMBARRIER_CMD_GLOBAL_EXPEDITED:
+ *                          Execute a memory barrier on all running threads
+ *                          of all processes which previously registered
+ *                          with MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED.
+ *                          Upon return from system call, the caller thread
+ *                          is ensured that all running threads have passed
+ *                          through a state where all memory accesses to
+ *                          user-space addresses match program order between
+ *                          entry to and return from the system call
+ *                          (non-running threads are de facto in such a
+ *                          state). This only covers threads from processes
+ *                          which registered with
+ *                          MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED.
+ *                          This command returns 0. Given that
+ *                          registration is about the intent to receive
+ *                          the barriers, it is valid to invoke
+ *                          MEMBARRIER_CMD_GLOBAL_EXPEDITED from a
+ *                          non-registered process.
+ * @MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED:
+ *                          Register the process intent to receive
+ *                          MEMBARRIER_CMD_GLOBAL_EXPEDITED memory
+ *                          barriers. Always returns 0.
  * @MEMBARRIER_CMD_PRIVATE_EXPEDITED:
  *                          Execute a memory barrier on each running
  *                          thread belonging to the same process as the current
@@ -51,7 +73,7 @@
  *                          to and return from the system call
  *                          (non-running threads are de facto in such a
  *                          state). This only covers threads from the
- *                          same processes as the caller thread. This
+ *                          same process as the caller thread. This
  *                          command returns 0 on success. The
  *                          "expedited" commands complete faster than
  *                          the non-expedited ones, they never block,
@@ -64,18 +86,54 @@
  *                          Register the process intent to use
  *                          MEMBARRIER_CMD_PRIVATE_EXPEDITED. Always
  *                          returns 0.
+ * @MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE:
+ *                          In addition to provide memory ordering
+ *                          guarantees described in
+ *                          MEMBARRIER_CMD_PRIVATE_EXPEDITED, ensure
+ *                          the caller thread, upon return from system
+ *                          call, that all its running threads siblings
+ *                          have executed a core serializing
+ *                          instruction. (architectures are required to
+ *                          guarantee that non-running threads issue
+ *                          core serializing instructions before they
+ *                          resume user-space execution). This only
+ *                          covers threads from the same process as the
+ *                          caller thread. This command returns 0 on
+ *                          success. The "expedited" commands complete
+ *                          faster than the non-expedited ones, they
+ *                          never block, but have the downside of
+ *                          causing extra overhead. If this command is
+ *                          not implemented by an architecture, -EINVAL
+ *                          is returned. A process needs to register its
+ *                          intent to use the private expedited sync
+ *                          core command prior to using it, otherwise
+ *                          this command returns -EPERM.
+ * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE:
+ *                          Register the process intent to use
+ *                          MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE.
+ *                          If this command is not implemented by an
+ *                          architecture, -EINVAL is returned.
+ *                          Returns 0 on success.
+ * @MEMBARRIER_CMD_SHARED:
+ *                          Alias to MEMBARRIER_CMD_GLOBAL. Provided for
+ *                          header backward compatibility.
  *
  * Command to be passed to the membarrier system call. The commands need to
  * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to
  * the value 0.
  */
 enum membarrier_cmd {
-	MEMBARRIER_CMD_QUERY				= 0,
-	MEMBARRIER_CMD_SHARED				= (1 << 0),
-	/* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */
-	/* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */
-	MEMBARRIER_CMD_PRIVATE_EXPEDITED		= (1 << 3),
-	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED	= (1 << 4),
+	MEMBARRIER_CMD_QUERY					= 0,
+	MEMBARRIER_CMD_GLOBAL					= (1 << 0),
+	MEMBARRIER_CMD_GLOBAL_EXPEDITED				= (1 << 1),
+	MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED		= (1 << 2),
+	MEMBARRIER_CMD_PRIVATE_EXPEDITED			= (1 << 3),
+	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED		= (1 << 4),
+	MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE		= (1 << 5),
+	MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE	= (1 << 6),
+
+	/* Alias for header backward compatibility. */
+	MEMBARRIER_CMD_SHARED			= MEMBARRIER_CMD_GLOBAL,
 };
 
 #endif /* _UAPI_LINUX_MEMBARRIER_H */

init/Kconfig

@@ -1412,6 +1412,12 @@ config USERFAULTFD
 	  Enable the userfaultfd() system call that allows to intercept and
 	  handle page faults in userland.
 
+config ARCH_HAS_MEMBARRIER_CALLBACKS
+	bool
+
+config ARCH_HAS_MEMBARRIER_SYNC_CORE
+	bool
+
 config EMBEDDED
 	bool "Embedded system"
 	option allnoconfig_y
@@ -1915,3 +1921,6 @@ config ASN1
 	  functions to call on what tags.
 
 source "kernel/Kconfig.locks"
+
+config ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
+	bool