17 files changed, 75 insertions, 389 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 5eeb808eb024..2ddf08351f0b 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -116,7 +116,6 @@ obj-$(CONFIG_VM86)		+= vm86_32.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 
 obj-$(CONFIG_HPET_TIMER) 	+= hpet.o
-obj-$(CONFIG_APB_TIMER)		+= apb_timer.o
 
 obj-$(CONFIG_AMD_NB)		+= amd_nb.o
 obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o
diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile
index f1bb57b0e41e..cf340d85946a 100644
--- a/arch/x86/kernel/acpi/Makefile
+++ b/arch/x86/kernel/acpi/Makefile
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-OBJECT_FILES_NON_STANDARD_wakeup_$(BITS).o := y
 
 obj-$(CONFIG_ACPI)		+= boot.o
 obj-$(CONFIG_ACPI_SLEEP)	+= sleep.o wakeup_$(BITS).o
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 5d3a0b8fd379..56b6865afb2a 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -1,12 +1,14 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 .text
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/segment.h>
 #include <asm/pgtable_types.h>
 #include <asm/page_types.h>
 #include <asm/msr.h>
 #include <asm/asm-offsets.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
 
 # Copyright 2003 Pavel Machek <pavel@suse.cz
 
@@ -39,6 +41,7 @@ SYM_FUNC_START(wakeup_long64)
 	movq	saved_rbp, %rbp
 
 	movq	saved_rip, %rax
+	ANNOTATE_RETPOLINE_SAFE
 	jmp	*%rax
 SYM_FUNC_END(wakeup_long64)
 
@@ -126,6 +129,7 @@ SYM_FUNC_START(do_suspend_lowlevel)
 	FRAME_END
 	jmp	restore_processor_state
 SYM_FUNC_END(do_suspend_lowlevel)
+STACK_FRAME_NON_STANDARD do_suspend_lowlevel
 
 .data
 saved_rbp:		.quad	0
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
deleted file mode 100644
index 263eeaddb0aa..000000000000
--- a/arch/x86/kernel/apb_timer.c
+++ /dev/null
@@ -1,347 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * apb_timer.c: Driver for Langwell APB timers
- *
- * (C) Copyright 2009 Intel Corporation
- * Author: Jacob Pan (jacob.jun.pan@intel.com)
- *
- * Note:
- * Langwell is the south complex of Intel Moorestown MID platform. There are
- * eight external timers in total that can be used by the operating system.
- * The timer information, such as frequency and addresses, is provided to the
- * OS via SFI tables.
- * Timer interrupts are routed via FW/HW emulated IOAPIC independently via
- * individual redirection table entries (RTE).
- * Unlike HPET, there is no master counter, therefore one of the timers are
- * used as clocksource. The overall allocation looks like:
- *  - timer 0 - NR_CPUs for per cpu timer
- *  - one timer for clocksource
- *  - one timer for watchdog driver.
- * It is also worth notice that APB timer does not support true one-shot mode,
- * free-running mode will be used here to emulate one-shot mode.
- * APB timer can also be used as broadcast timer along with per cpu local APIC
- * timer, but by default APB timer has higher rating than local APIC timers.
- */
-
-#include <linux/delay.h>
-#include <linux/dw_apb_timer.h>
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/pm.h>
-#include <linux/sfi.h>
-#include <linux/interrupt.h>
-#include <linux/cpu.h>
-#include <linux/irq.h>
-
-#include <asm/fixmap.h>
-#include <asm/apb_timer.h>
-#include <asm/intel-mid.h>
-#include <asm/time.h>
-
-#define APBT_CLOCKEVENT_RATING		110
-#define APBT_CLOCKSOURCE_RATING		250
-
-#define APBT_CLOCKEVENT0_NUM   (0)
-#define APBT_CLOCKSOURCE_NUM   (2)
-
-static phys_addr_t apbt_address;
-static int apb_timer_block_enabled;
-static void __iomem *apbt_virt_address;
-
-/*
- * Common DW APB timer info
- */
-static unsigned long apbt_freq;
-
-struct apbt_dev {
-	struct dw_apb_clock_event_device	*timer;
-	unsigned int				num;
-	int					cpu;
-	unsigned int				irq;
-	char					name[10];
-};
-
-static struct dw_apb_clocksource *clocksource_apbt;
-
-static inline void __iomem *adev_virt_addr(struct apbt_dev *adev)
-{
-	return apbt_virt_address + adev->num * APBTMRS_REG_SIZE;
-}
-
-static DEFINE_PER_CPU(struct apbt_dev, cpu_apbt_dev);
-
-#ifdef CONFIG_SMP
-static unsigned int apbt_num_timers_used;
-#endif
-
-static inline void apbt_set_mapping(void)
-{
-	struct sfi_timer_table_entry *mtmr;
-	int phy_cs_timer_id = 0;
-
-	if (apbt_virt_address) {
-		pr_debug("APBT base already mapped\n");
-		return;
-	}
-	mtmr = sfi_get_mtmr(APBT_CLOCKEVENT0_NUM);
-	if (mtmr == NULL) {
-		printk(KERN_ERR "Failed to get MTMR %d from SFI\n",
-		       APBT_CLOCKEVENT0_NUM);
-		return;
-	}
-	apbt_address = (phys_addr_t)mtmr->phys_addr;
-	if (!apbt_address) {
-		printk(KERN_WARNING "No timer base from SFI, use default\n");
-		apbt_address = APBT_DEFAULT_BASE;
-	}
-	apbt_virt_address = ioremap(apbt_address, APBT_MMAP_SIZE);
-	if (!apbt_virt_address) {
-		pr_debug("Failed mapping APBT phy address at %lu\n",\
-			 (unsigned long)apbt_address);
-		goto panic_noapbt;
-	}
-	apbt_freq = mtmr->freq_hz;
-	sfi_free_mtmr(mtmr);
-
-	/* Now figure out the physical timer id for clocksource device */
-	mtmr = sfi_get_mtmr(APBT_CLOCKSOURCE_NUM);
-	if (mtmr == NULL)
-		goto panic_noapbt;
-
-	/* Now figure out the physical timer id */
-	pr_debug("Use timer %d for clocksource\n",
-		 (int)(mtmr->phys_addr & 0xff) / APBTMRS_REG_SIZE);
-	phy_cs_timer_id = (unsigned int)(mtmr->phys_addr & 0xff) /
-		APBTMRS_REG_SIZE;
-
-	clocksource_apbt = dw_apb_clocksource_init(APBT_CLOCKSOURCE_RATING,
-		"apbt0", apbt_virt_address + phy_cs_timer_id *
-		APBTMRS_REG_SIZE, apbt_freq);
-	return;
-
-panic_noapbt:
-	panic("Failed to setup APB system timer\n");
-
-}
-
-static inline void apbt_clear_mapping(void)
-{
-	iounmap(apbt_virt_address);
-	apbt_virt_address = NULL;
-}
-
-static int __init apbt_clockevent_register(void)
-{
-	struct sfi_timer_table_entry *mtmr;
-	struct apbt_dev *adev = this_cpu_ptr(&cpu_apbt_dev);
-
-	mtmr = sfi_get_mtmr(APBT_CLOCKEVENT0_NUM);
-	if (mtmr == NULL) {
-		printk(KERN_ERR "Failed to get MTMR %d from SFI\n",
-		       APBT_CLOCKEVENT0_NUM);
-		return -ENODEV;
-	}
-
-	adev->num = smp_processor_id();
-	adev->timer = dw_apb_clockevent_init(smp_processor_id(), "apbt0",
-		intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT ?
-		APBT_CLOCKEVENT_RATING - 100 : APBT_CLOCKEVENT_RATING,
-		adev_virt_addr(adev), 0, apbt_freq);
-	/* Firmware does EOI handling for us. */
-	adev->timer->eoi = NULL;
-
-	if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT) {
-		global_clock_event = &adev->timer->ced;
-		printk(KERN_DEBUG "%s clockevent registered as global\n",
-		       global_clock_event->name);
-	}
-
-	dw_apb_clockevent_register(adev->timer);
-
-	sfi_free_mtmr(mtmr);
-	return 0;
-}
-
-#ifdef CONFIG_SMP
-
-static void apbt_setup_irq(struct apbt_dev *adev)
-{
-	irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
-	irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
-}
-
-/* Should be called with per cpu */
-void apbt_setup_secondary_clock(void)
-{
-	struct apbt_dev *adev;
-	int cpu;
-
-	/* Don't register boot CPU clockevent */
-	cpu = smp_processor_id();
-	if (!cpu)
-		return;
-
-	adev = this_cpu_ptr(&cpu_apbt_dev);
-	if (!adev->timer) {
-		adev->timer = dw_apb_clockevent_init(cpu, adev->name,
-			APBT_CLOCKEVENT_RATING, adev_virt_addr(adev),
-			adev->irq, apbt_freq);
-		adev->timer->eoi = NULL;
-	} else {
-		dw_apb_clockevent_resume(adev->timer);
-	}
-
-	printk(KERN_INFO "Registering CPU %d clockevent device %s, cpu %08x\n",
-	       cpu, adev->name, adev->cpu);
-
-	apbt_setup_irq(adev);
-	dw_apb_clockevent_register(adev->timer);
-
-	return;
-}
-
-/*
- * this notify handler process CPU hotplug events. in case of S0i3, nonboot
- * cpus are disabled/enabled frequently, for performance reasons, we keep the
- * per cpu timer irq registered so that we do need to do free_irq/request_irq.
- *
- * TODO: it might be more reliable to directly disable percpu clockevent device
- * without the notifier chain. currently, cpu 0 may get interrupts from other
- * cpu timers during the offline process due to the ordering of notification.
- * the extra interrupt is harmless.
- */
-static int apbt_cpu_dead(unsigned int cpu)
-{
-	struct apbt_dev *adev = &per_cpu(cpu_apbt_dev, cpu);
-
-	dw_apb_clockevent_pause(adev->timer);
-	if (system_state == SYSTEM_RUNNING) {
-		pr_debug("skipping APBT CPU %u offline\n", cpu);
-	} else {
-		pr_debug("APBT clockevent for cpu %u offline\n", cpu);
-		dw_apb_clockevent_stop(adev->timer);
-	}
-	return 0;
-}
-
-static __init int apbt_late_init(void)
-{
-	if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT ||
-		!apb_timer_block_enabled)
-		return 0;
-	return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "x86/apb:dead", NULL,
-				 apbt_cpu_dead);
-}
-fs_initcall(apbt_late_init);
-#else
-
-void apbt_setup_secondary_clock(void) {}
-
-#endif /* CONFIG_SMP */
-
-static int apbt_clocksource_register(void)
-{
-	u64 start, now;
-	u64 t1;
-
-	/* Start the counter, use timer 2 as source, timer 0/1 for event */
-	dw_apb_clocksource_start(clocksource_apbt);
-
-	/* Verify whether apbt counter works */
-	t1 = dw_apb_clocksource_read(clocksource_apbt);
-	start = rdtsc();
-
-	/*
-	 * We don't know the TSC frequency yet, but waiting for
-	 * 200000 TSC cycles is safe:
-	 * 4 GHz == 50us
-	 * 1 GHz == 200us
-	 */
-	do {
-		rep_nop();
-		now = rdtsc();
-	} while ((now - start) < 200000UL);
-
-	/* APBT is the only always on clocksource, it has to work! */
-	if (t1 == dw_apb_clocksource_read(clocksource_apbt))
-		panic("APBT counter not counting. APBT disabled\n");
-
-	dw_apb_clocksource_register(clocksource_apbt);
-
-	return 0;
-}
-
-/*
- * Early setup the APBT timer, only use timer 0 for booting then switch to
- * per CPU timer if possible.
- * returns 1 if per cpu apbt is setup
- * returns 0 if no per cpu apbt is chosen
- * panic if set up failed, this is the only platform timer on Moorestown.
- */
-void __init apbt_time_init(void)
-{
-#ifdef CONFIG_SMP
-	int i;
-	struct sfi_timer_table_entry *p_mtmr;
-	struct apbt_dev *adev;
-#endif
-
-	if (apb_timer_block_enabled)
-		return;
-	apbt_set_mapping();
-	if (!apbt_virt_address)
-		goto out_noapbt;
-	/*
-	 * Read the frequency and check for a sane value, for ESL model
-	 * we extend the possible clock range to allow time scaling.
-	 */
-
-	if (apbt_freq < APBT_MIN_FREQ || apbt_freq > APBT_MAX_FREQ) {
-		pr_debug("APBT has invalid freq 0x%lx\n", apbt_freq);
-		goto out_noapbt;
-	}
-	if (apbt_clocksource_register()) {
-		pr_debug("APBT has failed to register clocksource\n");
-		goto out_noapbt;
-	}
-	if (!apbt_clockevent_register())
-		apb_timer_block_enabled = 1;
-	else {
-		pr_debug("APBT has failed to register clockevent\n");
-		goto out_noapbt;
-	}
-#ifdef CONFIG_SMP
-	/* kernel cmdline disable apb timer, so we will use lapic timers */
-	if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT) {
-		printk(KERN_INFO "apbt: disabled per cpu timer\n");
-		return;
-	}
-	pr_debug("%s: %d CPUs online\n", __func__, num_online_cpus());
-	if (num_possible_cpus() <= sfi_mtimer_num)
-		apbt_num_timers_used = num_possible_cpus();
-	else
-		apbt_num_timers_used = 1;
-	pr_debug("%s: %d APB timers used\n", __func__, apbt_num_timers_used);
-
-	/* here we set up per CPU timer data structure */
-	for (i = 0; i < apbt_num_timers_used; i++) {
-		adev = &per_cpu(cpu_apbt_dev, i);
-		adev->num = i;
-		adev->cpu = i;
-		p_mtmr = sfi_get_mtmr(i);
-		if (p_mtmr)
-			adev->irq = p_mtmr->irq;
-		else
-			printk(KERN_ERR "Failed to get timer for cpu %d\n", i);
-		snprintf(adev->name, sizeof(adev->name) - 1, "apbt%d", i);
-	}
-#endif
-
-	return;
-
-out_noapbt:
-	apbt_clear_mapping();
-	apb_timer_block_enabled = 0;
-	panic("failed to enable APB timer\n");
-}
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 819db00c9388..bda4f2a36868 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2138,18 +2138,11 @@ void __init register_lapic_address(unsigned long address)
  * Local APIC interrupts
  */
 
-/**
- * spurious_interrupt - Catch all for interrupts raised on unused vectors
- * @regs:	Pointer to pt_regs on stack
- * @vector:	The vector number
- *
- * This is invoked from ASM entry code to catch all interrupts which
- * trigger on an entry which is routed to the common_spurious idtentry
- * point.
- *
- * Also called from sysvec_spurious_apic_interrupt().
+/*
+ * Common handling code for spurious_interrupt and spurious_vector entry
+ * points below. No point in allowing the compiler to inline it twice.
  */
-DEFINE_IDTENTRY_IRQ(spurious_interrupt)
+static noinline void handle_spurious_interrupt(u8 vector)
 {
 	u32 v;
 
@@ -2184,9 +2177,23 @@ out:
 	trace_spurious_apic_exit(vector);
 }
 
+/**
+ * spurious_interrupt - Catch all for interrupts raised on unused vectors
+ * @regs:	Pointer to pt_regs on stack
+ * @vector:	The vector number
+ *
+ * This is invoked from ASM entry code to catch all interrupts which
+ * trigger on an entry which is routed to the common_spurious idtentry
+ * point.
+ */
+DEFINE_IDTENTRY_IRQ(spurious_interrupt)
+{
+	handle_spurious_interrupt(vector);
+}
+
 DEFINE_IDTENTRY_SYSVEC(sysvec_spurious_apic_interrupt)
 {
-	__spurious_interrupt(regs, SPURIOUS_APIC_VECTOR);
+	handle_spurious_interrupt(SPURIOUS_APIC_VECTOR);
 }
 
 /*
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index e4ab4804b20d..c3b60c37c728 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -198,7 +198,7 @@ static int __init parse_noapic(char *str)
 }
 early_param("noapic", parse_noapic);
 
-/* Will be called in mpparse/acpi/sfi codes for saving IRQ info */
+/* Will be called in mpparse/ACPI codes for saving IRQ info */
 void mp_save_irq(struct mpc_intsrc *m)
 {
 	int i;
@@ -2863,7 +2863,7 @@ int mp_register_ioapic(int id, u32 address, u32 gsi_base,
 
 	/*
 	 * If mp_register_ioapic() is called during early boot stage when
-	 * walking ACPI/SFI/DT tables, it's too early to create irqdomain,
+	 * walking ACPI/DT tables, it's too early to create irqdomain,
 	 * we are still using bootmem allocator. So delay it to setup_IO_APIC().
 	 */
 	if (hotplug) {
diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c
index 0b2c03943ac6..23f5f27b5a02 100644
--- a/arch/x86/kernel/cpu/acrn.c
+++ b/arch/x86/kernel/cpu/acrn.c
@@ -10,6 +10,8 @@
  */
 
 #include <linux/interrupt.h>
+
+#include <asm/acrn.h>
 #include <asm/apic.h>
 #include <asm/cpufeatures.h>
 #include <asm/desc.h>
@@ -19,7 +21,7 @@
 
 static u32 __init acrn_detect(void)
 {
-	return hypervisor_cpuid_base("ACRNACRNACRN", 0);
+	return acrn_cpuid_base();
 }
 
 static void __init acrn_init_platform(void)
@@ -55,6 +57,18 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_acrn_hv_callback)
 	set_irq_regs(old_regs);
 }
 
+void acrn_setup_intr_handler(void (*handler)(void))
+{
+	acrn_intr_handler = handler;
+}
+EXPORT_SYMBOL_GPL(acrn_setup_intr_handler);
+
+void acrn_remove_intr_handler(void)
+{
+	acrn_intr_handler = NULL;
+}
+EXPORT_SYMBOL_GPL(acrn_remove_intr_handler);
+
 const __initconst struct hypervisor_x86 x86_hyper_acrn = {
 	.name                   = "ACRN",
 	.detect                 = acrn_detect,
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9215b91bc044..ab640abe26b6 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1742,8 +1742,8 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
 	&init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 
-DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
-DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
+DEFINE_PER_CPU(void *, hardirq_stack_ptr);
+DEFINE_PER_CPU(bool, hardirq_stack_inuse);
 
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 1dd851397bd9..5601b95944fa 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -128,12 +128,21 @@ static __always_inline bool in_exception_stack(unsigned long *stack, struct stac
 
 static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *end   = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
-	unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long));
+	unsigned long *end = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
+	unsigned long *begin;
 
 	/*
-	 * This is a software stack, so 'end' can be a valid stack pointer.
-	 * It just means the stack is empty.
+	 * @end points directly to the top most stack entry to avoid a -8
+	 * adjustment in the stack switch hotpath. Adjust it back before
+	 * calculating @begin.
+	 */
+	end++;
+	begin = end - (IRQ_STACK_SIZE / sizeof(long));
+
+	/*
+	 * Due to the switching logic RSP can never be == @end because the
+	 * final operation is 'popq %rsp' which means after that RSP points
+	 * to the original stack and not to @end.
 	 */
 	if (stack < begin || stack >= end)
 		return false;
@@ -143,8 +152,9 @@ static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info
 	info->end	= end;
 
 	/*
-	 * The next stack pointer is the first thing pushed by the entry code
-	 * after switching to the irq stack.
+	 * The next stack pointer is stored at the top of the irq stack
+	 * before switching to the irq stack. Actual stack entries are all
+	 * below that.
 	 */
 	info->next_sp = (unsigned long *)*(end - 1);
 
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 0d54099c2a3a..7c273846c687 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -184,6 +184,7 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
  * It is also used to copy the retq for trampolines.
  */
 SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK)
+	UNWIND_HINT_FUNC
 	retq
 SYM_FUNC_END(ftrace_epilogue)
 
@@ -276,7 +277,7 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
 	restore_mcount_regs 8
 	/* Restore flags */
 	popfq
-	UNWIND_HINT_RET_OFFSET
+	UNWIND_HINT_FUNC
 	jmp	ftrace_epilogue
 
 SYM_FUNC_END(ftrace_regs_caller)
@@ -333,8 +334,7 @@ SYM_FUNC_START(ftrace_graph_caller)
 	retq
 SYM_FUNC_END(ftrace_graph_caller)
 
-SYM_CODE_START(return_to_handler)
-	UNWIND_HINT_EMPTY
+SYM_FUNC_START(return_to_handler)
 	subq  $24, %rsp
 
 	/* Save the return values */
@@ -349,5 +349,5 @@ SYM_CODE_START(return_to_handler)
 	movq (%rsp), %rax
 	addq $24, %rsp
 	JMP_NOSPEC rdi
-SYM_CODE_END(return_to_handler)
+SYM_FUNC_END(return_to_handler)
 #endif
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index d4ad344e80bf..58aa712973ac 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -228,7 +228,7 @@ static __always_inline void handle_irq(struct irq_desc *desc,
 				       struct pt_regs *regs)
 {
 	if (IS_ENABLED(CONFIG_X86_64))
-		run_irq_on_irqstack_cond(desc->handle_irq, desc, regs);
+		generic_handle_irq_desc(desc);
 	else
 		__handle_irq(desc, regs);
 }
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 0b79efc87be5..044902d5a3c4 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -22,6 +22,7 @@
 
 #include <asm/apic.h>
 #include <asm/nospec-branch.h>
+#include <asm/softirq_stack.h>
 
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
 
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 440eed558558..1c0fb96b9e39 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -20,6 +20,7 @@
 #include <linux/sched/task_stack.h>
 
 #include <asm/cpu_entry_area.h>
+#include <asm/softirq_stack.h>
 #include <asm/irq_stack.h>
 #include <asm/io_apic.h>
 #include <asm/apic.h>
@@ -48,7 +49,8 @@ static int map_irq_stack(unsigned int cpu)
 	if (!va)
 		return -ENOMEM;
 
-	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE;
+	/* Store actual TOS to avoid adjustment in the hotpath */
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
 	return 0;
 }
 #else
@@ -60,7 +62,8 @@ static int map_irq_stack(unsigned int cpu)
 {
 	void *va = per_cpu_ptr(&irq_stack_backing_store, cpu);
 
-	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE;
+	/* Store actual TOS to avoid adjustment in the hotpath */
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
 	return 0;
 }
 #endif
@@ -71,8 +74,3 @@ int irq_init_percpu_irqstack(unsigned int cpu)
 		return 0;
 	return map_irq_stack(cpu);
 }
-
-void do_softirq_own_stack(void)
-{
-	run_on_irqstack_cond(__do_softirq, NULL);
-}
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 145a7ac0c19a..9c214d7085a4 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -161,7 +161,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 #endif
 
 	/* Kernel thread ? */
-	if (unlikely(p->flags & PF_KTHREAD)) {
+	if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) {
 		memset(childregs, 0, sizeof(struct pt_regs));
 		kthread_frame_init(frame, sp, arg);
 		return 0;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ad582f9ac5a6..d08307df69ad 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -539,7 +539,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	int cpu = smp_processor_id();
 
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
-		     this_cpu_read(irq_count) != -1);
+		     this_cpu_read(hardirq_stack_inuse));
 
 	if (!test_thread_flag(TIF_NEED_FPU_LOAD))
 		switch_fpu_prepare(prev_fpu, cpu);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 740f3bdb3f61..d883176ef2ce 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -16,7 +16,6 @@
 #include <linux/memblock.h>
 #include <linux/pci.h>
 #include <linux/root_dev.h>
-#include <linux/sfi.h>
 #include <linux/hugetlb.h>
 #include <linux/tboot.h>
 #include <linux/usb/xhci-dbgp.h>
@@ -1185,7 +1184,6 @@ void __init setup_arch(char **cmdline_p)
 	 * Read APIC and some other early information from ACPI tables.
 	 */
 	acpi_boot_init();
-	sfi_init();
 	x86_dtb_init();
 
 	/*
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 73f800100066..2a1d47f47eee 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -471,7 +471,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	case ORC_REG_SP_INDIRECT:
-		sp = state->sp + orc->sp_offset;
+		sp = state->sp;
 		indirect = true;
 		break;
 
@@ -521,6 +521,9 @@ bool unwind_next_frame(struct unwind_state *state)
 	if (indirect) {
 		if (!deref_stack_reg(state, sp, &sp))
 			goto err;
+
+		if (orc->sp_reg == ORC_REG_SP_INDIRECT)
+			sp += orc->sp_offset;
 	}
 
 	/* Find IP, SP and possibly regs: */