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

10 files changed, 85 insertions, 0 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 53612879fe56..7381eeb7ef8e 100644
--- a/arch/arm64/Kconfig
+++ b/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
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index b34e717d7597..cccd2788e631 100644
--- a/arch/arm64/kernel/entry.S
+++ b/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
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 9d3329811cc1..73ce5dd07642 100644
--- a/arch/powerpc/Kconfig
+++ b/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)
diff --git a/arch/powerpc/include/asm/membarrier.h b/arch/powerpc/include/asm/membarrier.h
new file mode 100644
index 000000000000..6e20bb5c74ea
--- /dev/null
+++ b/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 */
diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c
index d60a62bf4fc7..0ab297c4cfad 100644
--- a/arch/powerpc/mm/mmu_context.c
+++ b/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
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b0771ceabb4b..cefa6dbe80ae 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -55,6 +55,7 @@ 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
@@ -62,6 +63,7 @@ config X86
 	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
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 2a35b1e0fb90..abee6d2b9311 100644
--- a/arch/x86/entry/entry_32.S
+++ b/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"
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index c752abe89d80..4a9bef6aca34 100644
--- a/arch/x86/entry/entry_64.S
+++ b/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)
diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h
new file mode 100644
index 000000000000..c67caafd3381
--- /dev/null
+++ b/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 */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 012d02624848..8dcc0607f805 100644
--- a/arch/x86/mm/tlb.c
+++ b/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);