16 files changed, 180 insertions, 112 deletions

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 6bd20c0de8bc..7f4c081f59f0 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -41,6 +41,7 @@
 #include <asm/perf_event.h>
 #include <asm/x86_init.h>
 #include <linux/atomic.h>
+#include <asm/barrier.h>
 #include <asm/mpspec.h>
 #include <asm/i8259.h>
 #include <asm/proto.h>
@@ -477,6 +478,9 @@ static int lapic_next_deadline(unsigned long delta,
 {
 	u64 tsc;
 
+	/* This MSR is special and need a special fence: */
+	weak_wrmsr_fence();
+
 	tsc = rdtsc();
 	wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR));
 	return 0;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index df6adc5674c9..f4da9bb69a88 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -29,7 +29,8 @@ static void x2apic_send_IPI(int cpu, int vector)
 {
 	u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu);
 
-	x2apic_wrmsr_fence();
+	/* x2apic MSRs are special and need a special fence: */
+	weak_wrmsr_fence();
 	__x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL);
 }
 
@@ -41,7 +42,8 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
 	unsigned long flags;
 	u32 dest;
 
-	x2apic_wrmsr_fence();
+	/* x2apic MSRs are special and need a special fence: */
+	weak_wrmsr_fence();
 	local_irq_save(flags);
 
 	tmpmsk = this_cpu_cpumask_var_ptr(ipi_mask);
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 0e4e81971567..6bde05a86b4e 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -43,7 +43,8 @@ static void x2apic_send_IPI(int cpu, int vector)
 {
 	u32 dest = per_cpu(x86_cpu_to_apicid, cpu);
 
-	x2apic_wrmsr_fence();
+	/* x2apic MSRs are special and need a special fence: */
+	weak_wrmsr_fence();
 	__x2apic_send_IPI_dest(dest, vector, APIC_DEST_PHYSICAL);
 }
 
@@ -54,7 +55,8 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
 	unsigned long this_cpu;
 	unsigned long flags;
 
-	x2apic_wrmsr_fence();
+	/* x2apic MSRs are special and need a special fence: */
+	weak_wrmsr_fence();
 
 	local_irq_save(flags);
 
@@ -125,7 +127,8 @@ void __x2apic_send_IPI_shorthand(int vector, u32 which)
 {
 	unsigned long cfg = __prepare_ICR(which, vector, 0);
 
-	x2apic_wrmsr_fence();
+	/* x2apic MSRs are special and need a special fence: */
+	weak_wrmsr_fence();
 	native_x2apic_icr_write(cfg, 0);
 }
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f8ca66f3d861..347a956f71ca 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -542,12 +542,12 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		u32 ecx;
 
 		ecx = cpuid_ecx(0x8000001e);
-		nodes_per_socket = ((ecx >> 8) & 7) + 1;
+		__max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1;
 	} else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
 		u64 value;
 
 		rdmsrl(MSR_FAM10H_NODE_ID, value);
-		nodes_per_socket = ((value >> 3) & 7) + 1;
+		__max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1;
 	}
 
 	if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) &&
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 59a1e3ce3f14..816fdbec795a 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -1159,6 +1159,7 @@ static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		1),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	1),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		1),
+	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		1),
 	{}
 };
 
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 13d3f1cbda17..e133ce1e562b 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1992,10 +1992,9 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
 	 * that out because it's an indirect call. Annotate it.
 	 */
 	instrumentation_begin();
-	trace_hardirqs_off_finish();
+
 	machine_check_vector(regs);
-	if (regs->flags & X86_EFLAGS_IF)
-		trace_hardirqs_on_prepare();
+
 	instrumentation_end();
 	irqentry_nmi_exit(regs, irq_state);
 }
@@ -2004,7 +2003,9 @@ static __always_inline void exc_machine_check_user(struct pt_regs *regs)
 {
 	irqentry_enter_from_user_mode(regs);
 	instrumentation_begin();
+
 	machine_check_vector(regs);
+
 	instrumentation_end();
 	irqentry_exit_to_user_mode(regs);
 }
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index f628e3dc150f..43b54bef5448 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -135,14 +135,32 @@ static void hv_machine_shutdown(void)
 {
 	if (kexec_in_progress && hv_kexec_handler)
 		hv_kexec_handler();
+
+	/*
+	 * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor
+	 * corrupts the old VP Assist Pages and can crash the kexec kernel.
+	 */
+	if (kexec_in_progress && hyperv_init_cpuhp > 0)
+		cpuhp_remove_state(hyperv_init_cpuhp);
+
+	/* The function calls stop_other_cpus(). */
 	native_machine_shutdown();
+
+	/* Disable the hypercall page when there is only 1 active CPU. */
+	if (kexec_in_progress)
+		hyperv_cleanup();
 }
 
 static void hv_machine_crash_shutdown(struct pt_regs *regs)
 {
 	if (hv_crash_handler)
 		hv_crash_handler(regs);
+
+	/* The function calls crash_smp_send_stop(). */
 	native_machine_crash_shutdown(regs);
+
+	/* Disable the hypercall page when there is only 1 active CPU. */
+	hyperv_cleanup();
 }
 #endif /* CONFIG_KEXEC_CORE */
 #endif /* CONFIG_HYPERV */
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 23ad8e953dfb..a29997e6cf9e 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -167,9 +167,6 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end,
 	*repeat = 0;
 	*uniform = 1;
 
-	/* Make end inclusive instead of exclusive */
-	end--;
-
 	prev_match = MTRR_TYPE_INVALID;
 	for (i = 0; i < num_var_ranges; ++i) {
 		unsigned short start_state, end_state, inclusive;
@@ -261,6 +258,9 @@ u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform)
 	int repeat;
 	u64 partial_end;
 
+	/* Make end inclusive instead of exclusive */
+	end--;
+
 	if (!mtrr_state_set)
 		return MTRR_TYPE_INVALID;
 
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 29ffb95b25ff..460f3e0df106 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -525,89 +525,70 @@ static void rdtgroup_remove(struct rdtgroup *rdtgrp)
 	kfree(rdtgrp);
 }
 
-struct task_move_callback {
-	struct callback_head	work;
-	struct rdtgroup		*rdtgrp;
-};
-
-static void move_myself(struct callback_head *head)
+static void _update_task_closid_rmid(void *task)
 {
-	struct task_move_callback *callback;
-	struct rdtgroup *rdtgrp;
-
-	callback = container_of(head, struct task_move_callback, work);
-	rdtgrp = callback->rdtgrp;
-
 	/*
-	 * If resource group was deleted before this task work callback
-	 * was invoked, then assign the task to root group and free the
-	 * resource group.
+	 * If the task is still current on this CPU, update PQR_ASSOC MSR.
+	 * Otherwise, the MSR is updated when the task is scheduled in.
 	 */
-	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
-	    (rdtgrp->flags & RDT_DELETED)) {
-		current->closid = 0;
-		current->rmid = 0;
-		rdtgroup_remove(rdtgrp);
-	}
-
-	if (unlikely(current->flags & PF_EXITING))
-		goto out;
-
-	preempt_disable();
-	/* update PQR_ASSOC MSR to make resource group go into effect */
-	resctrl_sched_in();
-	preempt_enable();
+	if (task == current)
+		resctrl_sched_in();
+}
 
-out:
-	kfree(callback);
+static void update_task_closid_rmid(struct task_struct *t)
+{
+	if (IS_ENABLED(CONFIG_SMP) && task_curr(t))
+		smp_call_function_single(task_cpu(t), _update_task_closid_rmid, t, 1);
+	else
+		_update_task_closid_rmid(t);
 }
 
 static int __rdtgroup_move_task(struct task_struct *tsk,
 				struct rdtgroup *rdtgrp)
 {
-	struct task_move_callback *callback;
-	int ret;
-
-	callback = kzalloc(sizeof(*callback), GFP_KERNEL);
-	if (!callback)
-		return -ENOMEM;
-	callback->work.func = move_myself;
-	callback->rdtgrp = rdtgrp;
+	/* If the task is already in rdtgrp, no need to move the task. */
+	if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid &&
+	     tsk->rmid == rdtgrp->mon.rmid) ||
+	    (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid &&
+	     tsk->closid == rdtgrp->mon.parent->closid))
+		return 0;
 
 	/*
-	 * Take a refcount, so rdtgrp cannot be freed before the
-	 * callback has been invoked.
+	 * Set the task's closid/rmid before the PQR_ASSOC MSR can be
+	 * updated by them.
+	 *
+	 * For ctrl_mon groups, move both closid and rmid.
+	 * For monitor groups, can move the tasks only from
+	 * their parent CTRL group.
 	 */
-	atomic_inc(&rdtgrp->waitcount);
-	ret = task_work_add(tsk, &callback->work, TWA_RESUME);
-	if (ret) {
-		/*
-		 * Task is exiting. Drop the refcount and free the callback.
-		 * No need to check the refcount as the group cannot be
-		 * deleted before the write function unlocks rdtgroup_mutex.
-		 */
-		atomic_dec(&rdtgrp->waitcount);
-		kfree(callback);
-		rdt_last_cmd_puts("Task exited\n");
-	} else {
-		/*
-		 * For ctrl_mon groups move both closid and rmid.
-		 * For monitor groups, can move the tasks only from
-		 * their parent CTRL group.
-		 */
-		if (rdtgrp->type == RDTCTRL_GROUP) {
-			tsk->closid = rdtgrp->closid;
+
+	if (rdtgrp->type == RDTCTRL_GROUP) {
+		tsk->closid = rdtgrp->closid;
+		tsk->rmid = rdtgrp->mon.rmid;
+	} else if (rdtgrp->type == RDTMON_GROUP) {
+		if (rdtgrp->mon.parent->closid == tsk->closid) {
 			tsk->rmid = rdtgrp->mon.rmid;
-		} else if (rdtgrp->type == RDTMON_GROUP) {
-			if (rdtgrp->mon.parent->closid == tsk->closid) {
-				tsk->rmid = rdtgrp->mon.rmid;
-			} else {
-				rdt_last_cmd_puts("Can't move task to different control group\n");
-				ret = -EINVAL;
-			}
+		} else {
+			rdt_last_cmd_puts("Can't move task to different control group\n");
+			return -EINVAL;
 		}
 	}
-	return ret;
+
+	/*
+	 * Ensure the task's closid and rmid are written before determining if
+	 * the task is current that will decide if it will be interrupted.
+	 */
+	barrier();
+
+	/*
+	 * By now, the task's closid and rmid are set. If the task is current
+	 * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource
+	 * group go into effect. If the task is not current, the MSR will be
+	 * updated when the task is scheduled in.
+	 */
+	update_task_closid_rmid(tsk);
+
+	return 0;
 }
 
 static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 1068002c8532..8678864ce712 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -25,10 +25,10 @@
 #define BITS_SHIFT_NEXT_LEVEL(eax)	((eax) & 0x1f)
 #define LEVEL_MAX_SIBLINGS(ebx)		((ebx) & 0xffff)
 
-#ifdef CONFIG_SMP
 unsigned int __max_die_per_package __read_mostly = 1;
 EXPORT_SYMBOL(__max_die_per_package);
 
+#ifdef CONFIG_SMP
 /*
  * Check if given CPUID extended toplogy "leaf" is implemented
  */
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index eb86a2b831b1..571220ac8bea 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -121,7 +121,7 @@ int copy_fpregs_to_fpstate(struct fpu *fpu)
 }
 EXPORT_SYMBOL(copy_fpregs_to_fpstate);
 
-void kernel_fpu_begin(void)
+void kernel_fpu_begin_mask(unsigned int kfpu_mask)
 {
 	preempt_disable();
 
@@ -141,13 +141,14 @@ void kernel_fpu_begin(void)
 	}
 	__cpu_invalidate_fpregs_state();
 
-	if (boot_cpu_has(X86_FEATURE_XMM))
+	/* Put sane initial values into the control registers. */
+	if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM))
 		ldmxcsr(MXCSR_DEFAULT);
 
-	if (boot_cpu_has(X86_FEATURE_FPU))
+	if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU))
 		asm volatile ("fninit");
 }
-EXPORT_SYMBOL_GPL(kernel_fpu_begin);
+EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask);
 
 void kernel_fpu_end(void)
 {
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 03aa33b58165..668a4a6533d9 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -269,6 +269,20 @@ static inline bool within_cpu_entry(unsigned long addr, unsigned long end)
 			CPU_ENTRY_AREA_TOTAL_SIZE))
 		return true;
 
+	/*
+	 * When FSGSBASE is enabled, paranoid_entry() fetches the per-CPU
+	 * GSBASE value via __per_cpu_offset or pcpu_unit_offsets.
+	 */
+#ifdef CONFIG_SMP
+	if (within_area(addr, end, (unsigned long)__per_cpu_offset,
+			sizeof(unsigned long) * nr_cpu_ids))
+		return true;
+#else
+	if (within_area(addr, end, (unsigned long)&pcpu_unit_offsets,
+			sizeof(pcpu_unit_offsets)))
+		return true;
+#endif
+
 	for_each_possible_cpu(cpu) {
 		/* The original rw GDT is being used after load_direct_gdt() */
 		if (within_area(addr, end, (unsigned long)get_cpu_gdt_rw(cpu),
@@ -293,6 +307,14 @@ static inline bool within_cpu_entry(unsigned long addr, unsigned long end)
 				(unsigned long)&per_cpu(cpu_tlbstate, cpu),
 				sizeof(struct tlb_state)))
 			return true;
+
+		/*
+		 * When in guest (X86_FEATURE_HYPERVISOR), local_db_save()
+		 * will read per-cpu cpu_dr7 before clear dr7 register.
+		 */
+		if (within_area(addr, end, (unsigned long)&per_cpu(cpu_dr7, cpu),
+				sizeof(cpu_dr7)))
+			return true;
 	}
 
 	return false;
@@ -491,15 +513,12 @@ static int hw_breakpoint_handler(struct die_args *args)
 	struct perf_event *bp;
 	unsigned long *dr6_p;
 	unsigned long dr6;
+	bool bpx;
 
 	/* The DR6 value is pointed by args->err */
 	dr6_p = (unsigned long *)ERR_PTR(args->err);
 	dr6 = *dr6_p;
 
-	/* If it's a single step, TRAP bits are random */
-	if (dr6 & DR_STEP)
-		return NOTIFY_DONE;
-
 	/* Do an early return if no trap bits are set in DR6 */
 	if ((dr6 & DR_TRAP_BITS) == 0)
 		return NOTIFY_DONE;
@@ -509,28 +528,29 @@ static int hw_breakpoint_handler(struct die_args *args)
 		if (likely(!(dr6 & (DR_TRAP0 << i))))
 			continue;
 
+		bp = this_cpu_read(bp_per_reg[i]);
+		if (!bp)
+			continue;
+
+		bpx = bp->hw.info.type == X86_BREAKPOINT_EXECUTE;
+
 		/*
-		 * The counter may be concurrently released but that can only
-		 * occur from a call_rcu() path. We can then safely fetch
-		 * the breakpoint, use its callback, touch its counter
-		 * while we are in an rcu_read_lock() path.
+		 * TF and data breakpoints are traps and can be merged, however
+		 * instruction breakpoints are faults and will be raised
+		 * separately.
+		 *
+		 * However DR6 can indicate both TF and instruction
+		 * breakpoints. In that case take TF as that has precedence and
+		 * delay the instruction breakpoint for the next exception.
 		 */
-		rcu_read_lock();
+		if (bpx && (dr6 & DR_STEP))
+			continue;
 
-		bp = this_cpu_read(bp_per_reg[i]);
 		/*
 		 * Reset the 'i'th TRAP bit in dr6 to denote completion of
 		 * exception handling
 		 */
 		(*dr6_p) &= ~(DR_TRAP0 << i);
-		/*
-		 * bp can be NULL due to lazy debug register switching
-		 * or due to concurrent perf counter removing.
-		 */
-		if (!bp) {
-			rcu_read_unlock();
-			break;
-		}
 
 		perf_bp_event(bp, args->regs);
 
@@ -538,11 +558,10 @@ static int hw_breakpoint_handler(struct die_args *args)
 		 * Set up resume flag to avoid breakpoint recursion when
 		 * returning back to origin.
 		 */
-		if (bp->hw.info.type == X86_BREAKPOINT_EXECUTE)
+		if (bpx)
 			args->regs->flags |= X86_EFLAGS_RF;
-
-		rcu_read_unlock();
 	}
+
 	/*
 	 * Further processing in do_debug() is needed for a) user-space
 	 * breakpoints (to generate signals) and b) when the system has
diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c
index 7d04b356d44d..cdc04d091242 100644
--- a/arch/x86/kernel/sev-es-shared.c
+++ b/arch/x86/kernel/sev-es-shared.c
@@ -305,14 +305,14 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
 	case 0xe4:
 	case 0xe5:
 		*exitinfo |= IOIO_TYPE_IN;
-		*exitinfo |= (u64)insn->immediate.value << 16;
+		*exitinfo |= (u8)insn->immediate.value << 16;
 		break;
 
 	/* OUT immediate opcodes */
 	case 0xe6:
 	case 0xe7:
 		*exitinfo |= IOIO_TYPE_OUT;
-		*exitinfo |= (u64)insn->immediate.value << 16;
+		*exitinfo |= (u8)insn->immediate.value << 16;
 		break;
 
 	/* IN register opcodes */
diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c
index 0bd1a0fc587e..84c1821819af 100644
--- a/arch/x86/kernel/sev-es.c
+++ b/arch/x86/kernel/sev-es.c
@@ -225,7 +225,7 @@ static inline u64 sev_es_rd_ghcb_msr(void)
 	return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
 }
 
-static inline void sev_es_wr_ghcb_msr(u64 val)
+static __always_inline void sev_es_wr_ghcb_msr(u64 val)
 {
 	u32 low, high;
 
@@ -286,6 +286,12 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
 	u16 d2;
 	u8  d1;
 
+	/* If instruction ran in kernel mode and the I/O buffer is in kernel space */
+	if (!user_mode(ctxt->regs) && !access_ok(target, size)) {
+		memcpy(dst, buf, size);
+		return ES_OK;
+	}
+
 	switch (size) {
 	case 1:
 		memcpy(&d1, buf, 1);
@@ -335,6 +341,12 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 	u16 d2;
 	u8  d1;
 
+	/* If instruction ran in kernel mode and the I/O buffer is in kernel space */
+	if (!user_mode(ctxt->regs) && !access_ok(s, size)) {
+		memcpy(buf, src, size);
+		return ES_OK;
+	}
+
 	switch (size) {
 	case 1:
 		if (get_user(d1, s))
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8ca66af96a54..02813a7f3a7c 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -56,6 +56,7 @@
 #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>
@@ -1832,6 +1833,7 @@ 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)
 {
@@ -2083,6 +2085,23 @@ static void init_counter_refs(void)
 	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
+
 static void init_freq_invariance(bool secondary, bool cppc_ready)
 {
 	bool ret = false;
@@ -2109,6 +2128,7 @@ static void init_freq_invariance(bool secondary, bool cppc_ready)
 	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");
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 60d2c3798ba2..0f3c307b37b3 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -127,12 +127,17 @@ static int enable_single_step(struct task_struct *child)
 		regs->flags |= X86_EFLAGS_TF;
 
 	/*
-	 * Always set TIF_SINGLESTEP - this guarantees that
-	 * we single-step system calls etc..  This will also
+	 * Always set TIF_SINGLESTEP.  This will also
 	 * cause us to set TF when returning to user mode.
 	 */
 	set_tsk_thread_flag(child, TIF_SINGLESTEP);
 
+	/*
+	 * Ensure that a trap is triggered once stepping out of a system
+	 * call prior to executing any user instruction.
+	 */
+	set_task_syscall_work(child, SYSCALL_EXIT_TRAP);
+
 	oflags = regs->flags;
 
 	/* Set TF on the kernel stack.. */
@@ -230,6 +235,7 @@ void user_disable_single_step(struct task_struct *child)
 
 	/* Always clear TIF_SINGLESTEP... */
 	clear_tsk_thread_flag(child, TIF_SINGLESTEP);
+	clear_task_syscall_work(child, SYSCALL_EXIT_TRAP);
 
 	/* But touch TF only if it was set by us.. */
 	if (test_and_clear_tsk_thread_flag(child, TIF_FORCED_TF))