Merge branch 'for-next/entry' into for-next/core

The never-ending entry.S refactoring continues, putting us in a much
better place wrt compiler instrumentation whilst moving more of the code
into C.

* for-next/entry:
  arm64: idle: don't instrument idle code with KCOV
  arm64: entry: don't instrument entry code with KCOV
  arm64: entry: make NMI entry/exit functions static
  arm64: entry: split SDEI entry
  arm64: entry: split bad stack entry
  arm64: entry: fold el1_inv() into el1h_64_sync_handler()
  arm64: entry: handle all vectors with C
  arm64: entry: template the entry asm functions
  arm64: entry: improve bad_mode()
  arm64: entry: move bad_mode() to entry-common.c
  arm64: entry: consolidate EL1 exception returns
  arm64: entry: organise entry vectors consistently
  arm64: entry: organise entry handlers consistently
  arm64: entry: convert IRQ+FIQ handlers to C
  arm64: entry: add a call_on_irq_stack helper
  arm64: entry: move NMI preempt logic to C
  arm64: entry: move arm64_preempt_schedule_irq to entry-common.c
  arm64: entry: convert SError handlers to C
  arm64: entry: unmask IRQ+FIQ after EL0 handling
  arm64: remove redundant local_daif_mask() in bad_mode()

7 files changed, 388 insertions, 421 deletions

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 6cc97730790e..de434204d723 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -14,6 +14,12 @@ CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_syscall.o	 = -fstack-protector -fstack-protector-strong
 CFLAGS_syscall.o	+= -fno-stack-protector
 
+# It's not safe to invoke KCOV when portions of the kernel environment aren't
+# available or are out-of-sync with HW state. Since `noinstr` doesn't always
+# inhibit KCOV instrumentation, disable it for the entire compilation unit.
+KCOV_INSTRUMENT_entry.o := n
+KCOV_INSTRUMENT_idle.o := n
+
 # Object file lists.
 obj-y			:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   entry-common.o entry-fpsimd.o process.o ptrace.o	\
@@ -22,7 +28,7 @@ obj-y			:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   return_address.o cpuinfo.o cpu_errata.o		\
 			   cpufeature.o alternative.o cacheinfo.o		\
 			   smp.o smp_spin_table.o topology.o smccc-call.o	\
-			   syscall.o proton-pack.o idreg-override.o
+			   syscall.o proton-pack.o idreg-override.o idle.o
 
 targets			+= efi-entry.o
 
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 340d04e13617..12ce14a98b7c 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -6,7 +6,11 @@
  */
 
 #include <linux/context_tracking.h>
+#include <linux/linkage.h>
+#include <linux/lockdep.h>
 #include <linux/ptrace.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
 #include <linux/thread_info.h>
 
 #include <asm/cpufeature.h>
@@ -15,7 +19,11 @@
 #include <asm/exception.h>
 #include <asm/kprobes.h>
 #include <asm/mmu.h>
+#include <asm/processor.h>
+#include <asm/sdei.h>
+#include <asm/stacktrace.h>
 #include <asm/sysreg.h>
+#include <asm/system_misc.h>
 
 /*
  * This is intended to match the logic in irqentry_enter(), handling the kernel
@@ -67,7 +75,7 @@ static void noinstr exit_to_kernel_mode(struct pt_regs *regs)
 	}
 }
 
-void noinstr arm64_enter_nmi(struct pt_regs *regs)
+static void noinstr arm64_enter_nmi(struct pt_regs *regs)
 {
 	regs->lockdep_hardirqs = lockdep_hardirqs_enabled();
 
@@ -80,7 +88,7 @@ void noinstr arm64_enter_nmi(struct pt_regs *regs)
 	ftrace_nmi_enter();
 }
 
-void noinstr arm64_exit_nmi(struct pt_regs *regs)
+static void noinstr arm64_exit_nmi(struct pt_regs *regs)
 {
 	bool restore = regs->lockdep_hardirqs;
 
@@ -97,7 +105,7 @@ void noinstr arm64_exit_nmi(struct pt_regs *regs)
 	__nmi_exit();
 }
 
-asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs)
+static void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs)
 {
 	if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs))
 		arm64_enter_nmi(regs);
@@ -105,7 +113,7 @@ asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs)
 		enter_from_kernel_mode(regs);
 }
 
-asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs)
+static void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs)
 {
 	if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs))
 		arm64_exit_nmi(regs);
@@ -113,6 +121,65 @@ asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs)
 		exit_to_kernel_mode(regs);
 }
 
+static void __sched arm64_preempt_schedule_irq(void)
+{
+	lockdep_assert_irqs_disabled();
+
+	/*
+	 * DAIF.DA are cleared at the start of IRQ/FIQ handling, and when GIC
+	 * priority masking is used the GIC irqchip driver will clear DAIF.IF
+	 * using gic_arch_enable_irqs() for normal IRQs. If anything is set in
+	 * DAIF we must have handled an NMI, so skip preemption.
+	 */
+	if (system_uses_irq_prio_masking() && read_sysreg(daif))
+		return;
+
+	/*
+	 * Preempting a task from an IRQ means we leave copies of PSTATE
+	 * on the stack. cpufeature's enable calls may modify PSTATE, but
+	 * resuming one of these preempted tasks would undo those changes.
+	 *
+	 * Only allow a task to be preempted once cpufeatures have been
+	 * enabled.
+	 */
+	if (system_capabilities_finalized())
+		preempt_schedule_irq();
+}
+
+static void do_interrupt_handler(struct pt_regs *regs,
+				 void (*handler)(struct pt_regs *))
+{
+	if (on_thread_stack())
+		call_on_irq_stack(regs, handler);
+	else
+		handler(regs);
+}
+
+extern void (*handle_arch_irq)(struct pt_regs *);
+extern void (*handle_arch_fiq)(struct pt_regs *);
+
+static void noinstr __panic_unhandled(struct pt_regs *regs, const char *vector,
+				      unsigned int esr)
+{
+	arm64_enter_nmi(regs);
+
+	console_verbose();
+
+	pr_crit("Unhandled %s exception on CPU%d, ESR 0x%08x -- %s\n",
+		vector, smp_processor_id(), esr,
+		esr_get_class_string(esr));
+
+	__show_regs(regs);
+	panic("Unhandled exception");
+}
+
+#define UNHANDLED(el, regsize, vector)							\
+asmlinkage void noinstr el##_##regsize##_##vector##_handler(struct pt_regs *regs)	\
+{											\
+	const char *desc = #regsize "-bit " #el " " #vector;				\
+	__panic_unhandled(regs, desc, read_sysreg(esr_el1));				\
+}
+
 #ifdef CONFIG_ARM64_ERRATUM_1463225
 static DEFINE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
 
@@ -162,6 +229,11 @@ static bool cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
 }
 #endif /* CONFIG_ARM64_ERRATUM_1463225 */
 
+UNHANDLED(el1t, 64, sync)
+UNHANDLED(el1t, 64, irq)
+UNHANDLED(el1t, 64, fiq)
+UNHANDLED(el1t, 64, error)
+
 static void noinstr el1_abort(struct pt_regs *regs, unsigned long esr)
 {
 	unsigned long far = read_sysreg(far_el1);
@@ -193,15 +265,6 @@ static void noinstr el1_undef(struct pt_regs *regs)
 	exit_to_kernel_mode(regs);
 }
 
-static void noinstr el1_inv(struct pt_regs *regs, unsigned long esr)
-{
-	enter_from_kernel_mode(regs);
-	local_daif_inherit(regs);
-	bad_mode(regs, 0, esr);
-	local_daif_mask();
-	exit_to_kernel_mode(regs);
-}
-
 static void noinstr arm64_enter_el1_dbg(struct pt_regs *regs)
 {
 	regs->lockdep_hardirqs = lockdep_hardirqs_enabled();
@@ -245,7 +308,7 @@ static void noinstr el1_fpac(struct pt_regs *regs, unsigned long esr)
 	exit_to_kernel_mode(regs);
 }
 
-asmlinkage void noinstr el1_sync_handler(struct pt_regs *regs)
+asmlinkage void noinstr el1h_64_sync_handler(struct pt_regs *regs)
 {
 	unsigned long esr = read_sysreg(esr_el1);
 
@@ -275,10 +338,50 @@ asmlinkage void noinstr el1_sync_handler(struct pt_regs *regs)
 		el1_fpac(regs, esr);
 		break;
 	default:
-		el1_inv(regs, esr);
+		__panic_unhandled(regs, "64-bit el1h sync", esr);
 	}
 }
 
+static void noinstr el1_interrupt(struct pt_regs *regs,
+				  void (*handler)(struct pt_regs *))
+{
+	write_sysreg(DAIF_PROCCTX_NOIRQ, daif);
+
+	enter_el1_irq_or_nmi(regs);
+	do_interrupt_handler(regs, handler);
+
+	/*
+	 * Note: thread_info::preempt_count includes both thread_info::count
+	 * and thread_info::need_resched, and is not equivalent to
+	 * preempt_count().
+	 */
+	if (IS_ENABLED(CONFIG_PREEMPTION) &&
+	    READ_ONCE(current_thread_info()->preempt_count) == 0)
+		arm64_preempt_schedule_irq();
+
+	exit_el1_irq_or_nmi(regs);
+}
+
+asmlinkage void noinstr el1h_64_irq_handler(struct pt_regs *regs)
+{
+	el1_interrupt(regs, handle_arch_irq);
+}
+
+asmlinkage void noinstr el1h_64_fiq_handler(struct pt_regs *regs)
+{
+	el1_interrupt(regs, handle_arch_fiq);
+}
+
+asmlinkage void noinstr el1h_64_error_handler(struct pt_regs *regs)
+{
+	unsigned long esr = read_sysreg(esr_el1);
+
+	local_daif_restore(DAIF_ERRCTX);
+	arm64_enter_nmi(regs);
+	do_serror(regs, esr);
+	arm64_exit_nmi(regs);
+}
+
 asmlinkage void noinstr enter_from_user_mode(void)
 {
 	lockdep_hardirqs_off(CALLER_ADDR0);
@@ -398,7 +501,7 @@ static void noinstr el0_dbg(struct pt_regs *regs, unsigned long esr)
 
 	enter_from_user_mode();
 	do_debug_exception(far, esr, regs);
-	local_daif_restore(DAIF_PROCCTX_NOIRQ);
+	local_daif_restore(DAIF_PROCCTX);
 }
 
 static void noinstr el0_svc(struct pt_regs *regs)
@@ -415,7 +518,7 @@ static void noinstr el0_fpac(struct pt_regs *regs, unsigned long esr)
 	do_ptrauth_fault(regs, esr);
 }
 
-asmlinkage void noinstr el0_sync_handler(struct pt_regs *regs)
+asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs)
 {
 	unsigned long esr = read_sysreg(esr_el1);
 
@@ -468,6 +571,56 @@ asmlinkage void noinstr el0_sync_handler(struct pt_regs *regs)
 	}
 }
 
+static void noinstr el0_interrupt(struct pt_regs *regs,
+				  void (*handler)(struct pt_regs *))
+{
+	enter_from_user_mode();
+
+	write_sysreg(DAIF_PROCCTX_NOIRQ, daif);
+
+	if (regs->pc & BIT(55))
+		arm64_apply_bp_hardening();
+
+	do_interrupt_handler(regs, handler);
+}
+
+static void noinstr __el0_irq_handler_common(struct pt_regs *regs)
+{
+	el0_interrupt(regs, handle_arch_irq);
+}
+
+asmlinkage void noinstr el0t_64_irq_handler(struct pt_regs *regs)
+{
+	__el0_irq_handler_common(regs);
+}
+
+static void noinstr __el0_fiq_handler_common(struct pt_regs *regs)
+{
+	el0_interrupt(regs, handle_arch_fiq);
+}
+
+asmlinkage void noinstr el0t_64_fiq_handler(struct pt_regs *regs)
+{
+	__el0_fiq_handler_common(regs);
+}
+
+static void __el0_error_handler_common(struct pt_regs *regs)
+{
+	unsigned long esr = read_sysreg(esr_el1);
+
+	enter_from_user_mode();
+	local_daif_restore(DAIF_ERRCTX);
+	arm64_enter_nmi(regs);
+	do_serror(regs, esr);
+	arm64_exit_nmi(regs);
+	local_daif_restore(DAIF_PROCCTX);
+}
+
+asmlinkage void noinstr el0t_64_error_handler(struct pt_regs *regs)
+{
+	__el0_error_handler_common(regs);
+}
+
 #ifdef CONFIG_COMPAT
 static void noinstr el0_cp15(struct pt_regs *regs, unsigned long esr)
 {
@@ -483,7 +636,7 @@ static void noinstr el0_svc_compat(struct pt_regs *regs)
 	do_el0_svc_compat(regs);
 }
 
-asmlinkage void noinstr el0_sync_compat_handler(struct pt_regs *regs)
+asmlinkage void noinstr el0t_32_sync_handler(struct pt_regs *regs)
 {
 	unsigned long esr = read_sysreg(esr_el1);
 
@@ -526,4 +679,71 @@ asmlinkage void noinstr el0_sync_compat_handler(struct pt_regs *regs)
 		el0_inv(regs, esr);
 	}
 }
+
+asmlinkage void noinstr el0t_32_irq_handler(struct pt_regs *regs)
+{
+	__el0_irq_handler_common(regs);
+}
+
+asmlinkage void noinstr el0t_32_fiq_handler(struct pt_regs *regs)
+{
+	__el0_fiq_handler_common(regs);
+}
+
+asmlinkage void noinstr el0t_32_error_handler(struct pt_regs *regs)
+{
+	__el0_error_handler_common(regs);
+}
+#else /* CONFIG_COMPAT */
+UNHANDLED(el0t, 32, sync)
+UNHANDLED(el0t, 32, irq)
+UNHANDLED(el0t, 32, fiq)
+UNHANDLED(el0t, 32, error)
 #endif /* CONFIG_COMPAT */
+
+#ifdef CONFIG_VMAP_STACK
+asmlinkage void noinstr handle_bad_stack(struct pt_regs *regs)
+{
+	unsigned int esr = read_sysreg(esr_el1);
+	unsigned long far = read_sysreg(far_el1);
+
+	arm64_enter_nmi(regs);
+	panic_bad_stack(regs, esr, far);
+}
+#endif /* CONFIG_VMAP_STACK */
+
+#ifdef CONFIG_ARM_SDE_INTERFACE
+asmlinkage noinstr unsigned long
+__sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg)
+{
+	unsigned long ret;
+
+	/*
+	 * We didn't take an exception to get here, so the HW hasn't
+	 * set/cleared bits in PSTATE that we may rely on.
+	 *
+	 * The original SDEI spec (ARM DEN 0054A) can be read ambiguously as to
+	 * whether PSTATE bits are inherited unchanged or generated from
+	 * scratch, and the TF-A implementation always clears PAN and always
+	 * clears UAO. There are no other known implementations.
+	 *
+	 * Subsequent revisions (ARM DEN 0054B) follow the usual rules for how
+	 * PSTATE is modified upon architectural exceptions, and so PAN is
+	 * either inherited or set per SCTLR_ELx.SPAN, and UAO is always
+	 * cleared.
+	 *
+	 * We must explicitly reset PAN to the expected state, including
+	 * clearing it when the host isn't using it, in case a VM had it set.
+	 */
+	if (system_uses_hw_pan())
+		set_pstate_pan(1);
+	else if (cpu_has_pan())
+		set_pstate_pan(0);
+
+	arm64_enter_nmi(regs);
+	ret = do_sdei_event(regs, arg);
+	arm64_exit_nmi(regs);
+
+	return ret;
+}
+#endif /* CONFIG_ARM_SDE_INTERFACE */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 3153f1448cdb..863d44f73028 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -33,12 +33,6 @@
  * Context tracking and irqflag tracing need to instrument transitions between
  * user and kernel mode.
  */
-	.macro user_exit_irqoff
-#if defined(CONFIG_CONTEXT_TRACKING) || defined(CONFIG_TRACE_IRQFLAGS)
-	bl	enter_from_user_mode
-#endif
-	.endm
-
 	.macro user_enter_irqoff
 #if defined(CONFIG_CONTEXT_TRACKING) || defined(CONFIG_TRACE_IRQFLAGS)
 	bl	exit_to_user_mode
@@ -51,16 +45,7 @@
 	.endr
 	.endm
 
-/*
- * Bad Abort numbers
- *-----------------
- */
-#define BAD_SYNC	0
-#define BAD_IRQ		1
-#define BAD_FIQ		2
-#define BAD_ERROR	3
-
-	.macro kernel_ventry, el, label, regsize = 64
+	.macro kernel_ventry, el:req, ht:req, regsize:req, label:req
 	.align 7
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	.if	\el == 0
@@ -87,7 +72,7 @@ alternative_else_nop_endif
 	tbnz	x0, #THREAD_SHIFT, 0f
 	sub	x0, sp, x0			// x0'' = sp' - x0' = (sp + x0) - sp = x0
 	sub	sp, sp, x0			// sp'' = sp' - x0 = (sp + x0) - x0 = sp
-	b	el\()\el\()_\label
+	b	el\el\ht\()_\regsize\()_\label
 
 0:
 	/*
@@ -119,7 +104,7 @@ alternative_else_nop_endif
 	sub	sp, sp, x0
 	mrs	x0, tpidrro_el0
 #endif
-	b	el\()\el\()_\label
+	b	el\el\ht\()_\regsize\()_\label
 	.endm
 
 	.macro tramp_alias, dst, sym
@@ -486,63 +471,12 @@ SYM_CODE_START_LOCAL(__swpan_exit_el0)
 SYM_CODE_END(__swpan_exit_el0)
 #endif
 
-	.macro	irq_stack_entry
-	mov	x19, sp			// preserve the original sp
-#ifdef CONFIG_SHADOW_CALL_STACK
-	mov	x24, scs_sp		// preserve the original shadow stack
-#endif
-
-	/*
-	 * Compare sp with the base of the task stack.
-	 * If the top ~(THREAD_SIZE - 1) bits match, we are on a task stack,
-	 * and should switch to the irq stack.
-	 */
-	ldr	x25, [tsk, TSK_STACK]
-	eor	x25, x25, x19
-	and	x25, x25, #~(THREAD_SIZE - 1)
-	cbnz	x25, 9998f
-
-	ldr_this_cpu x25, irq_stack_ptr, x26
-	mov	x26, #IRQ_STACK_SIZE
-	add	x26, x25, x26
-
-	/* switch to the irq stack */
-	mov	sp, x26
-
-#ifdef CONFIG_SHADOW_CALL_STACK
-	/* also switch to the irq shadow stack */
-	ldr_this_cpu scs_sp, irq_shadow_call_stack_ptr, x26
-#endif
-
-9998:
-	.endm
-
-	/*
-	 * The callee-saved regs (x19-x29) should be preserved between
-	 * irq_stack_entry and irq_stack_exit, but note that kernel_entry
-	 * uses x20-x23 to store data for later use.
-	 */
-	.macro	irq_stack_exit
-	mov	sp, x19
-#ifdef CONFIG_SHADOW_CALL_STACK
-	mov	scs_sp, x24
-#endif
-	.endm
-
 /* GPRs used by entry code */
 tsk	.req	x28		// current thread_info
 
 /*
  * Interrupt handling.
  */
-	.macro	irq_handler, handler:req
-	ldr_l	x1, \handler
-	mov	x0, sp
-	irq_stack_entry
-	blr	x1
-	irq_stack_exit
-	.endm
-
 	.macro	gic_prio_kentry_setup, tmp:req
 #ifdef CONFIG_ARM64_PSEUDO_NMI
 	alternative_if ARM64_HAS_IRQ_PRIO_MASKING
@@ -552,45 +486,6 @@ tsk	.req	x28		// current thread_info
 #endif
 	.endm
 
-	.macro el1_interrupt_handler, handler:req
-	enable_da
-
-	mov	x0, sp
-	bl	enter_el1_irq_or_nmi
-
-	irq_handler	\handler
-
-#ifdef CONFIG_PREEMPTION
-	ldr	x24, [tsk, #TSK_TI_PREEMPT]	// get preempt count
-alternative_if ARM64_HAS_IRQ_PRIO_MASKING
-	/*
-	 * DA were cleared at start of handling, and IF are cleared by
-	 * the GIC irqchip driver using gic_arch_enable_irqs() for
-	 * normal IRQs. If anything is set, it means we come back from
-	 * an NMI instead of a normal IRQ, so skip preemption
-	 */
-	mrs	x0, daif
-	orr	x24, x24, x0
-alternative_else_nop_endif
-	cbnz	x24, 1f				// preempt count != 0 || NMI return path
-	bl	arm64_preempt_schedule_irq	// irq en/disable is done inside
-1:
-#endif
-
-	mov	x0, sp
-	bl	exit_el1_irq_or_nmi
-	.endm
-
-	.macro el0_interrupt_handler, handler:req
-	user_exit_irqoff
-	enable_da
-
-	tbz	x22, #55, 1f
-	bl	do_el0_irq_bp_hardening
-1:
-	irq_handler	\handler
-	.endm
-
 	.text
 
 /*
@@ -600,32 +495,25 @@ alternative_else_nop_endif
 
 	.align	11
 SYM_CODE_START(vectors)
-	kernel_ventry	1, sync_invalid			// Synchronous EL1t
-	kernel_ventry	1, irq_invalid			// IRQ EL1t
-	kernel_ventry	1, fiq_invalid			// FIQ EL1t
-	kernel_ventry	1, error_invalid		// Error EL1t
-
-	kernel_ventry	1, sync				// Synchronous EL1h
-	kernel_ventry	1, irq				// IRQ EL1h
-	kernel_ventry	1, fiq				// FIQ EL1h
-	kernel_ventry	1, error			// Error EL1h
-
-	kernel_ventry	0, sync				// Synchronous 64-bit EL0
-	kernel_ventry	0, irq				// IRQ 64-bit EL0
-	kernel_ventry	0, fiq				// FIQ 64-bit EL0
-	kernel_ventry	0, error			// Error 64-bit EL0
-
-#ifdef CONFIG_COMPAT
-	kernel_ventry	0, sync_compat, 32		// Synchronous 32-bit EL0
-	kernel_ventry	0, irq_compat, 32		// IRQ 32-bit EL0
-	kernel_ventry	0, fiq_compat, 32		// FIQ 32-bit EL0
-	kernel_ventry	0, error_compat, 32		// Error 32-bit EL0
-#else
-	kernel_ventry	0, sync_invalid, 32		// Synchronous 32-bit EL0
-	kernel_ventry	0, irq_invalid, 32		// IRQ 32-bit EL0
-	kernel_ventry	0, fiq_invalid, 32		// FIQ 32-bit EL0
-	kernel_ventry	0, error_invalid, 32		// Error 32-bit EL0
-#endif
+	kernel_ventry	1, t, 64, sync		// Synchronous EL1t
+	kernel_ventry	1, t, 64, irq		// IRQ EL1t
+	kernel_ventry	1, t, 64, fiq		// FIQ EL1h
+	kernel_ventry	1, t, 64, error		// Error EL1t
+
+	kernel_ventry	1, h, 64, sync		// Synchronous EL1h
+	kernel_ventry	1, h, 64, irq		// IRQ EL1h
+	kernel_ventry	1, h, 64, fiq		// FIQ EL1h
+	kernel_ventry	1, h, 64, error		// Error EL1h
+
+	kernel_ventry	0, t, 64, sync		// Synchronous 64-bit EL0
+	kernel_ventry	0, t, 64, irq		// IRQ 64-bit EL0
+	kernel_ventry	0, t, 64, fiq		// FIQ 64-bit EL0
+	kernel_ventry	0, t, 64, error		// Error 64-bit EL0
+
+	kernel_ventry	0, t, 32, sync		// Synchronous 32-bit EL0
+	kernel_ventry	0, t, 32, irq		// IRQ 32-bit EL0
+	kernel_ventry	0, t, 32, fiq		// FIQ 32-bit EL0
+	kernel_ventry	0, t, 32, error		// Error 32-bit EL0
 SYM_CODE_END(vectors)
 
 #ifdef CONFIG_VMAP_STACK
@@ -656,147 +544,46 @@ __bad_stack:
 	ASM_BUG()
 #endif /* CONFIG_VMAP_STACK */
 
-/*
- * Invalid mode handlers
- */
-	.macro	inv_entry, el, reason, regsize = 64
+
+	.macro entry_handler el:req, ht:req, regsize:req, label:req
+SYM_CODE_START_LOCAL(el\el\ht\()_\regsize\()_\label)
 	kernel_entry \el, \regsize
 	mov	x0, sp
-	mov	x1, #\reason
-	mrs	x2, esr_el1
-	bl	bad_mode
-	ASM_BUG()
+	bl	el\el\ht\()_\regsize\()_\label\()_handler
+	.if \el == 0
+	b	ret_to_user
+	.else
+	b	ret_to_kernel
+	.endif
+SYM_CODE_END(el\el\ht\()_\regsize\()_\label)
 	.endm
 
-SYM_CODE_START_LOCAL(el0_sync_invalid)
-	inv_entry 0, BAD_SYNC
-SYM_CODE_END(el0_sync_invalid)
-
-SYM_CODE_START_LOCAL(el0_irq_invalid)
-	inv_entry 0, BAD_IRQ
-SYM_CODE_END(el0_irq_invalid)
-
-SYM_CODE_START_LOCAL(el0_fiq_invalid)
-	inv_entry 0, BAD_FIQ
-SYM_CODE_END(el0_fiq_invalid)
-
-SYM_CODE_START_LOCAL(el0_error_invalid)
-	inv_entry 0, BAD_ERROR
-SYM_CODE_END(el0_error_invalid)
-
-SYM_CODE_START_LOCAL(el1_sync_invalid)
-	inv_entry 1, BAD_SYNC
-SYM_CODE_END(el1_sync_invalid)
-
-SYM_CODE_START_LOCAL(el1_irq_invalid)
-	inv_entry 1, BAD_IRQ
-SYM_CODE_END(el1_irq_invalid)
-
-SYM_CODE_START_LOCAL(el1_fiq_invalid)
-	inv_entry 1, BAD_FIQ
-SYM_CODE_END(el1_fiq_invalid)
-
-SYM_CODE_START_LOCAL(el1_error_invalid)
-	inv_entry 1, BAD_ERROR
-SYM_CODE_END(el1_error_invalid)
-
 /*
- * EL1 mode handlers.
+ * Early exception handlers
  */
-	.align	6
-SYM_CODE_START_LOCAL_NOALIGN(el1_sync)
-	kernel_entry 1
-	mov	x0, sp
-	bl	el1_sync_handler
-	kernel_exit 1
-SYM_CODE_END(el1_sync)
-
-	.align	6
-SYM_CODE_START_LOCAL_NOALIGN(el1_irq)
-	kernel_entry 1
-	el1_interrupt_handler handle_arch_irq
-	kernel_exit 1
-SYM_CODE_END(el1_irq)
-
-SYM_CODE_START_LOCAL_NOALIGN(el1_fiq)
-	kernel_entry 1
-	el1_interrupt_handler handle_arch_fiq
-	kernel_exit 1
-SYM_CODE_END(el1_fiq)
-
-/*
- * EL0 mode handlers.
- */
-	.align	6
-SYM_CODE_START_LOCAL_NOALIGN(el0_sync)
-	kernel_entry 0
-	mov	x0, sp
-	bl	el0_sync_handler
-	b	ret_to_user
-SYM_CODE_END(el0_sync)
-
-#ifdef CONFIG_COMPAT
-	.align	6
-SYM_CODE_START_LOCAL_NOALIGN(el0_sync_compat)
-	kernel_entry 0, 32
-	mov	x0, sp
-	bl	el0_sync_compat_handler
-	b	ret_to_user
-SYM_CODE_END(el0_sync_compat)
-
-	.align	6
-SYM_CODE_START_LOCAL_NOALIGN(el0_irq_compat)
-	kernel_entry 0, 32
-	b	el0_irq_naked
-SYM_CODE_END(el0_irq_compat)
-
-SYM_CODE_START_LOCAL_NOALIGN(el0_fiq_compat)
-	kernel_entry 0, 32
-	b	el0_fiq_naked
-SYM_CODE_END(el0_fiq_compat)
-
-SYM_CODE_START_LOCAL_NOALIGN(el0_error_compat)
-	kernel_entry 0, 32
-	b	el0_error_naked
-SYM_CODE_END(el0_error_compat)
-#endif
-
-	.align	6
-SYM_CODE_START_LOCAL_NOALIGN(el0_irq)
-	kernel_entry 0
-el0_irq_naked:
-	el0_interrupt_handler handle_arch_irq
-	b	ret_to_user
-SYM_CODE_END(el0_irq)
-
-SYM_CODE_START_LOCAL_NOALIGN(el0_fiq)
-	kernel_entry 0
-el0_fiq_naked:
-	el0_interrupt_handler handle_arch_fiq
-	b	ret_to_user
-SYM_CODE_END(el0_fiq)
-
-SYM_CODE_START_LOCAL(el1_error)
-	kernel_entry 1
-	mrs	x1, esr_el1
-	enable_dbg
-	mov	x0, sp
-	bl	do_serror
+	entry_handler	1, t, 64, sync
+	entry_handler	1, t, 64, irq
+	entry_handler	1, t, 64, fiq
+	entry_handler	1, t, 64, error
+
+	entry_handler	1, h, 64, sync
+	entry_handler	1, h, 64, irq
+	entry_handler	1, h, 64, fiq
+	entry_handler	1, h, 64, error
+
+	entry_handler	0, t, 64, sync
+	entry_handler	0, t, 64, irq
+	entry_handler	0, t, 64, fiq
+	entry_handler	0, t, 64, error
+
+	entry_handler	0, t, 32, sync
+	entry_handler	0, t, 32, irq
+	entry_handler	0, t, 32, fiq
+	entry_handler	0, t, 32, error
+
+SYM_CODE_START_LOCAL(ret_to_kernel)
 	kernel_exit 1
-SYM_CODE_END(el1_error)
-
-SYM_CODE_START_LOCAL(el0_error)
-	kernel_entry 0
-el0_error_naked:
-	mrs	x25, esr_el1
-	user_exit_irqoff
-	enable_dbg
-	mov	x0, sp
-	mov	x1, x25
-	bl	do_serror
-	enable_da
-	b	ret_to_user
-SYM_CODE_END(el0_error)
+SYM_CODE_END(ret_to_kernel)
 
 /*
  * "slow" syscall return path.
@@ -998,6 +785,42 @@ SYM_CODE_START(ret_from_fork)
 SYM_CODE_END(ret_from_fork)
 NOKPROBE(ret_from_fork)
 
+/*
+ * void call_on_irq_stack(struct pt_regs *regs,
+ * 		          void (*func)(struct pt_regs *));
+ *
+ * Calls func(regs) using this CPU's irq stack and shadow irq stack.
+ */
+SYM_FUNC_START(call_on_irq_stack)
+#ifdef CONFIG_SHADOW_CALL_STACK
+	stp	scs_sp, xzr, [sp, #-16]!
+	ldr_this_cpu scs_sp, irq_shadow_call_stack_ptr, x17
+#endif
+	/* Create a frame record to save our LR and SP (implicit in FP) */
+	stp	x29, x30, [sp, #-16]!
+	mov	x29, sp
+
+	ldr_this_cpu x16, irq_stack_ptr, x17
+	mov	x15, #IRQ_STACK_SIZE
+	add	x16, x16, x15
+
+	/* Move to the new stack and call the function there */
+	mov	sp, x16
+	blr	x1
+
+	/*
+	 * Restore the SP from the FP, and restore the FP and LR from the frame
+	 * record.
+	 */
+	mov	sp, x29
+	ldp	x29, x30, [sp], #16
+#ifdef CONFIG_SHADOW_CALL_STACK
+	ldp	scs_sp, xzr, [sp], #16
+#endif
+	ret
+SYM_FUNC_END(call_on_irq_stack)
+NOKPROBE(call_on_irq_stack)
+
 #ifdef CONFIG_ARM_SDE_INTERFACE
 
 #include <asm/sdei.h>
diff --git a/arch/arm64/kernel/idle.c b/arch/arm64/kernel/idle.c
new file mode 100644
index 000000000000..a2cfbacec2bb
--- /dev/null
+++ b/arch/arm64/kernel/idle.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Low-level idle sequences
+ */
+
+#include <linux/cpu.h>
+#include <linux/irqflags.h>
+
+#include <asm/barrier.h>
+#include <asm/cpuidle.h>
+#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
+
+/*
+ *	cpu_do_idle()
+ *
+ *	Idle the processor (wait for interrupt).
+ *
+ *	If the CPU supports priority masking we must do additional work to
+ *	ensure that interrupts are not masked at the PMR (because the core will
+ *	not wake up if we block the wake up signal in the interrupt controller).
+ */
+void noinstr cpu_do_idle(void)
+{
+	struct arm_cpuidle_irq_context context;
+
+	arm_cpuidle_save_irq_context(&context);
+
+	dsb(sy);
+	wfi();
+
+	arm_cpuidle_restore_irq_context(&context);
+}
+
+/*
+ * This is our default idle handler.
+ */
+void noinstr arch_cpu_idle(void)
+{
+	/*
+	 * This should do all the clock switching and wait for interrupt
+	 * tricks
+	 */
+	cpu_do_idle();
+	raw_local_irq_enable();
+}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 3925ec3128ec..6b8b4b3e357a 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -18,7 +18,6 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
-#include <linux/lockdep.h>
 #include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/nospec.h>
@@ -48,7 +47,6 @@
 #include <asm/alternative.h>
 #include <asm/compat.h>
 #include <asm/cpufeature.h>
-#include <asm/cpuidle.h>
 #include <asm/cacheflush.h>
 #include <asm/exec.h>
 #include <asm/fpsimd.h>
@@ -74,40 +72,6 @@ EXPORT_SYMBOL_GPL(pm_power_off);
 
 void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
 
-/*
- *	cpu_do_idle()
- *
- *	Idle the processor (wait for interrupt).
- *
- *	If the CPU supports priority masking we must do additional work to
- *	ensure that interrupts are not masked at the PMR (because the core will
- *	not wake up if we block the wake up signal in the interrupt controller).
- */
-void noinstr cpu_do_idle(void)
-{
-	struct arm_cpuidle_irq_context context;
-
-	arm_cpuidle_save_irq_context(&context);
-
-	dsb(sy);
-	wfi();
-
-	arm_cpuidle_restore_irq_context(&context);
-}
-
-/*
- * This is our default idle handler.
- */
-void noinstr arch_cpu_idle(void)
-{
-	/*
-	 * This should do all the clock switching and wait for interrupt
-	 * tricks
-	 */
-	cpu_do_idle();
-	raw_local_irq_enable();
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 void arch_cpu_idle_dead(void)
 {
@@ -723,22 +687,6 @@ static int __init tagged_addr_init(void)
 core_initcall(tagged_addr_init);
 #endif	/* CONFIG_ARM64_TAGGED_ADDR_ABI */
 
-asmlinkage void __sched arm64_preempt_schedule_irq(void)
-{
-	lockdep_assert_irqs_disabled();
-
-	/*
-	 * Preempting a task from an IRQ means we leave copies of PSTATE
-	 * on the stack. cpufeature's enable calls may modify PSTATE, but
-	 * resuming one of these preempted tasks would undo those changes.
-	 *
-	 * Only allow a task to be preempted once cpufeatures have been
-	 * enabled.
-	 */
-	if (system_capabilities_finalized())
-		preempt_schedule_irq();
-}
-
 #ifdef CONFIG_BINFMT_ELF
 int arch_elf_adjust_prot(int prot, const struct arch_elf_state *state,
 			 bool has_interp, bool is_interp)
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index c524f96f97c4..47f77d1234cb 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -233,13 +233,13 @@ out_err:
 }
 
 /*
- * __sdei_handler() returns one of:
+ * do_sdei_event() returns one of:
  *  SDEI_EV_HANDLED -  success, return to the interrupted context.
  *  SDEI_EV_FAILED  -  failure, return this error code to firmare.
  *  virtual-address -  success, return to this address.
  */
-static __kprobes unsigned long _sdei_handler(struct pt_regs *regs,
-					     struct sdei_registered_event *arg)
+unsigned long __kprobes do_sdei_event(struct pt_regs *regs,
+				      struct sdei_registered_event *arg)
 {
 	u32 mode;
 	int i, err = 0;
@@ -294,45 +294,3 @@ static __kprobes unsigned long _sdei_handler(struct pt_regs *regs,
 
 	return vbar + 0x480;
 }
-
-static void __kprobes notrace __sdei_pstate_entry(void)
-{
-	/*
-	 * The original SDEI spec (ARM DEN 0054A) can be read ambiguously as to
-	 * whether PSTATE bits are inherited unchanged or generated from
-	 * scratch, and the TF-A implementation always clears PAN and always
-	 * clears UAO. There are no other known implementations.
-	 *
-	 * Subsequent revisions (ARM DEN 0054B) follow the usual rules for how
-	 * PSTATE is modified upon architectural exceptions, and so PAN is
-	 * either inherited or set per SCTLR_ELx.SPAN, and UAO is always
-	 * cleared.
-	 *
-	 * We must explicitly reset PAN to the expected state, including
-	 * clearing it when the host isn't using it, in case a VM had it set.
-	 */
-	if (system_uses_hw_pan())
-		set_pstate_pan(1);
-	else if (cpu_has_pan())
-		set_pstate_pan(0);
-}
-
-asmlinkage noinstr unsigned long
-__sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg)
-{
-	unsigned long ret;
-
-	/*
-	 * We didn't take an exception to get here, so the HW hasn't
-	 * set/cleared bits in PSTATE that we may rely on. Initialize PAN.
-	 */
-	__sdei_pstate_entry();
-
-	arm64_enter_nmi(regs);
-
-	ret = _sdei_handler(regs, arg);
-
-	arm64_exit_nmi(regs);
-
-	return ret;
-}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index a05d34f0e82a..af941996eb5f 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -45,13 +45,6 @@
 #include <asm/system_misc.h>
 #include <asm/sysreg.h>
 
-static const char *handler[] = {
-	"Synchronous Abort",
-	"IRQ",
-	"FIQ",
-	"Error"
-};
-
 int show_unhandled_signals = 0;
 
 static void dump_kernel_instr(const char *lvl, struct pt_regs *regs)
@@ -751,27 +744,8 @@ const char *esr_get_class_string(u32 esr)
 }
 
 /*
- * bad_mode handles the impossible case in the exception vector. This is always
- * fatal.
- */
-asmlinkage void notrace bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
-{
-	arm64_enter_nmi(regs);
-
-	console_verbose();
-
-	pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n",
-		handler[reason], smp_processor_id(), esr,
-		esr_get_class_string(esr));
-
-	__show_regs(regs);
-	local_daif_mask();
-	panic("bad mode");
-}
-
-/*
  * bad_el0_sync handles unexpected, but potentially recoverable synchronous
- * exceptions taken from EL0. Unlike bad_mode, this returns.
+ * exceptions taken from EL0.
  */
 void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
 {
@@ -789,15 +763,11 @@ void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
 DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack)
 	__aligned(16);
 
-asmlinkage void noinstr handle_bad_stack(struct pt_regs *regs)
+void panic_bad_stack(struct pt_regs *regs, unsigned int esr, unsigned long far)
 {
 	unsigned long tsk_stk = (unsigned long)current->stack;
 	unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr);
 	unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack);
-	unsigned int esr = read_sysreg(esr_el1);
-	unsigned long far = read_sysreg(far_el1);
-
-	arm64_enter_nmi(regs);
 
 	console_verbose();
 	pr_emerg("Insufficient stack space to handle exception!");
@@ -870,15 +840,11 @@ bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr)
 	}
 }
 
-asmlinkage void noinstr do_serror(struct pt_regs *regs, unsigned int esr)
+void do_serror(struct pt_regs *regs, unsigned int esr)
 {
-	arm64_enter_nmi(regs);
-
 	/* non-RAS errors are not containable */
 	if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr))
 		arm64_serror_panic(regs, esr);
-
-	arm64_exit_nmi(regs);
 }
 
 /* GENERIC_BUG traps */