Merge ce990f1de0 ("Merge tag 'for-linus-5.17-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip") into android-mainline

Steps on the way to 5.17-rc1

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I7734f7ad7d56bdd0b0431bd40c1b378300743f88

Documentation/devicetree/bindings/arm/xen.txt

@@ -7,15 +7,17 @@ the following properties:
 	compatible = "xen,xen-<version>", "xen,xen";
   where <version> is the version of the Xen ABI of the platform.
 
-- reg: specifies the base physical address and size of a region in
-  memory where the grant table should be mapped to, using an
-  HYPERVISOR_memory_op hypercall. The memory region is large enough to map
-  the whole grant table (it is larger or equal to gnttab_max_grant_frames()).
-  This property is unnecessary when booting Dom0 using ACPI.
+- reg: specifies the base physical address and size of the regions in memory
+  where the special resources should be mapped to, using an HYPERVISOR_memory_op
+  hypercall.
+  Region 0 is reserved for mapping grant table, it must be always present.
+  The memory region is large enough to map the whole grant table (it is larger
+  or equal to gnttab_max_grant_frames()).
+  Regions 1...N are extended regions (unused address space) for mapping foreign
+  GFNs and grants, they might be absent if there is nothing to expose.
 
 - interrupts: the interrupt used by Xen to inject event notifications.
   A GIC node is also required.
-  This property is unnecessary when booting Dom0 using ACPI.
 
 To support UEFI on Xen ARM virtual platforms, Xen populates the FDT "uefi" node
 under /hypervisor with following parameters:

Makefile

@@ -708,17 +708,6 @@ ifdef CONFIG_FUNCTION_TRACER
   CC_FLAGS_FTRACE := -pg
 endif
 
-ifdef CONFIG_CC_IS_GCC
-RETPOLINE_CFLAGS	:= $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
-RETPOLINE_VDSO_CFLAGS	:= $(call cc-option,-mindirect-branch=thunk-inline -mindirect-branch-register)
-endif
-ifdef CONFIG_CC_IS_CLANG
-RETPOLINE_CFLAGS	:= -mretpoline-external-thunk
-RETPOLINE_VDSO_CFLAGS	:= -mretpoline
-endif
-export RETPOLINE_CFLAGS
-export RETPOLINE_VDSO_CFLAGS
-
 include $(srctree)/arch/$(SRCARCH)/Makefile
 
 ifdef need-config

arch/arm/kernel/perf_callchain.c

@@ -64,11 +64,6 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 {
 	struct frame_tail __user *tail;
 
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		/* We don't support guest os callchain now */
-		return;
-	}
-
 	perf_callchain_store(entry, regs->ARM_pc);
 
 	if (!current->mm)
@@ -100,20 +95,12 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 {
 	struct stackframe fr;
 
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		/* We don't support guest os callchain now */
-		return;
-	}
-
 	arm_get_current_stackframe(regs, &fr);
 	walk_stackframe(&fr, callchain_trace, entry);
 }
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
-		return perf_guest_cbs->get_guest_ip();
-
 	return instruction_pointer(regs);
 }
 
@@ -121,17 +108,10 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
 {
 	int misc = 0;
 
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		if (perf_guest_cbs->is_user_mode())
-			misc |= PERF_RECORD_MISC_GUEST_USER;
-		else
-			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
-	} else {
-		if (user_mode(regs))
-			misc |= PERF_RECORD_MISC_USER;
-		else
-			misc |= PERF_RECORD_MISC_KERNEL;
-	}
+	if (user_mode(regs))
+		misc |= PERF_RECORD_MISC_USER;
+	else
+		misc |= PERF_RECORD_MISC_KERNEL;
 
 	return misc;
 }

arch/arm/xen/enlighten.c

@@ -59,6 +59,10 @@ unsigned long xen_released_pages;
 struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
 
 static __read_mostly unsigned int xen_events_irq;
+static __read_mostly phys_addr_t xen_grant_frames;
+
+#define GRANT_TABLE_INDEX   0
+#define EXT_REGION_INDEX    1
 
 uint32_t xen_start_flags;
 EXPORT_SYMBOL(xen_start_flags);
@@ -300,9 +304,115 @@ static void __init xen_acpi_guest_init(void)
 #endif
 }
 
+#ifdef CONFIG_XEN_UNPOPULATED_ALLOC
+/*
+ * A type-less specific Xen resource which contains extended regions
+ * (unused regions of guest physical address space provided by the hypervisor).
+ */
+static struct resource xen_resource = {
+	.name = "Xen unused space",
+};
+
+int __init arch_xen_unpopulated_init(struct resource **res)
+{
+	struct device_node *np;
+	struct resource *regs, *tmp_res;
+	uint64_t min_gpaddr = -1, max_gpaddr = 0;
+	unsigned int i, nr_reg = 0;
+	int rc;
+
+	if (!xen_domain())
+		return -ENODEV;
+
+	if (!acpi_disabled)
+		return -ENODEV;
+
+	np = of_find_compatible_node(NULL, NULL, "xen,xen");
+	if (WARN_ON(!np))
+		return -ENODEV;
+
+	/* Skip region 0 which is reserved for grant table space */
+	while (of_get_address(np, nr_reg + EXT_REGION_INDEX, NULL, NULL))
+		nr_reg++;
+
+	if (!nr_reg) {
+		pr_err("No extended regions are found\n");
+		return -EINVAL;
+	}
+
+	regs = kcalloc(nr_reg, sizeof(*regs), GFP_KERNEL);
+	if (!regs)
+		return -ENOMEM;
+
+	/*
+	 * Create resource from extended regions provided by the hypervisor to be
+	 * used as unused address space for Xen scratch pages.
+	 */
+	for (i = 0; i < nr_reg; i++) {
+		rc = of_address_to_resource(np, i + EXT_REGION_INDEX, &regs[i]);
+		if (rc)
+			goto err;
+
+		if (max_gpaddr < regs[i].end)
+			max_gpaddr = regs[i].end;
+		if (min_gpaddr > regs[i].start)
+			min_gpaddr = regs[i].start;
+	}
+
+	xen_resource.start = min_gpaddr;
+	xen_resource.end = max_gpaddr;
+
+	/*
+	 * Mark holes between extended regions as unavailable. The rest of that
+	 * address space will be available for the allocation.
+	 */
+	for (i = 1; i < nr_reg; i++) {
+		resource_size_t start, end;
+
+		/* There is an overlap between regions */
+		if (regs[i - 1].end + 1 > regs[i].start) {
+			rc = -EINVAL;
+			goto err;
+		}
+
+		/* There is no hole between regions */
+		if (regs[i - 1].end + 1 == regs[i].start)
+			continue;
+
+		start = regs[i - 1].end + 1;
+		end = regs[i].start - 1;
+
+		tmp_res = kzalloc(sizeof(*tmp_res), GFP_KERNEL);
+		if (!tmp_res) {
+			rc = -ENOMEM;
+			goto err;
+		}
+
+		tmp_res->name = "Unavailable space";
+		tmp_res->start = start;
+		tmp_res->end = end;
+
+		rc = insert_resource(&xen_resource, tmp_res);
+		if (rc) {
+			pr_err("Cannot insert resource %pR (%d)\n", tmp_res, rc);
+			kfree(tmp_res);
+			goto err;
+		}
+	}
+
+	*res = &xen_resource;
+
+err:
+	kfree(regs);
+
+	return rc;
+}
+#endif
+
 static void __init xen_dt_guest_init(void)
 {
 	struct device_node *xen_node;
+	struct resource res;
 
 	xen_node = of_find_compatible_node(NULL, NULL, "xen,xen");
 	if (!xen_node) {
@@ -311,13 +421,19 @@ static void __init xen_dt_guest_init(void)
 	}
 
 	xen_events_irq = irq_of_parse_and_map(xen_node, 0);
+
+	if (of_address_to_resource(xen_node, GRANT_TABLE_INDEX, &res)) {
+		pr_err("Xen grant table region is not found\n");
+		return;
+	}
+	xen_grant_frames = res.start;
 }
 
 static int __init xen_guest_init(void)
 {
 	struct xen_add_to_physmap xatp;
 	struct shared_info *shared_info_page = NULL;
-	int cpu;
+	int rc, cpu;
 
 	if (!xen_domain())
 		return 0;
@@ -370,12 +486,16 @@ static int __init xen_guest_init(void)
 	for_each_possible_cpu(cpu)
 		per_cpu(xen_vcpu_id, cpu) = cpu;
 
-	xen_auto_xlat_grant_frames.count = gnttab_max_grant_frames();
-	if (xen_xlate_map_ballooned_pages(&xen_auto_xlat_grant_frames.pfn,
-					  &xen_auto_xlat_grant_frames.vaddr,
-					  xen_auto_xlat_grant_frames.count)) {
+	if (!xen_grant_frames) {
+		xen_auto_xlat_grant_frames.count = gnttab_max_grant_frames();
+		rc = xen_xlate_map_ballooned_pages(&xen_auto_xlat_grant_frames.pfn,
+										   &xen_auto_xlat_grant_frames.vaddr,
+										   xen_auto_xlat_grant_frames.count);
+	} else
+		rc = gnttab_setup_auto_xlat_frames(xen_grant_frames);
+	if (rc) {
 		free_percpu(xen_vcpu_info);
-		return -ENOMEM;
+		return rc;
 	}
 	gnttab_init();
 

arch/arm64/include/asm/kvm_host.h

@@ -675,8 +675,15 @@ unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
 int kvm_handle_mmio_return(struct kvm_vcpu *vcpu);
 int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa);
 
-int kvm_perf_init(void);
-int kvm_perf_teardown(void);
+/*
+ * Returns true if a Performance Monitoring Interrupt (PMI), a.k.a. perf event,
+ * arrived in guest context.  For arm64, any event that arrives while a vCPU is
+ * loaded is considered to be "in guest".
+ */
+static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu)
+{
+	return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu;
+}
 
 long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu);
 gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);

arch/arm64/kernel/image-vars.h

@@ -102,7 +102,9 @@ KVM_NVHE_ALIAS(__stop___kvm_ex_table);
 KVM_NVHE_ALIAS(kvm_arm_hyp_percpu_base);
 
 /* PMU available static key */
+#ifdef CONFIG_HW_PERF_EVENTS
 KVM_NVHE_ALIAS(kvm_arm_pmu_available);
+#endif
 
 /* Position-independent library routines */
 KVM_NVHE_ALIAS_HYP(clear_page, __pi_clear_page);

arch/arm64/kernel/perf_callchain.c

@@ -102,7 +102,7 @@ compat_user_backtrace(struct compat_frame_tail __user *tail,
 void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 			 struct pt_regs *regs)
 {
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+	if (perf_guest_state()) {
 		/* We don't support guest os callchain now */
 		return;
 	}
@@ -141,7 +141,7 @@ static bool callchain_trace(void *data, unsigned long pc)
 void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 			   struct pt_regs *regs)
 {
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+	if (perf_guest_state()) {
 		/* We don't support guest os callchain now */
 		return;
 	}
@@ -151,18 +151,19 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
-		return perf_guest_cbs->get_guest_ip();
+	if (perf_guest_state())
+		return perf_guest_get_ip();
 
 	return instruction_pointer(regs);
 }
 
 unsigned long perf_misc_flags(struct pt_regs *regs)
 {
+	unsigned int guest_state = perf_guest_state();
 	int misc = 0;
 
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		if (perf_guest_cbs->is_user_mode())
+	if (guest_state) {
+		if (guest_state & PERF_GUEST_USER)
 			misc |= PERF_RECORD_MISC_GUEST_USER;
 		else
 			misc |= PERF_RECORD_MISC_GUEST_KERNEL;

arch/arm64/kvm/Kconfig

@@ -39,6 +39,7 @@ menuconfig KVM
 	select HAVE_KVM_IRQ_BYPASS
 	select HAVE_KVM_VCPU_RUN_PID_CHANGE
 	select SCHED_INFO
+	select GUEST_PERF_EVENTS if PERF_EVENTS
 	help
 	  Support hosting virtualized guest machines.
 

arch/arm64/kvm/Makefile

@@ -12,7 +12,7 @@ obj-$(CONFIG_KVM) += hyp/
 
 kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
 	 $(KVM)/vfio.o $(KVM)/irqchip.o $(KVM)/binary_stats.o \
-	 arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \
+	 arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \
 	 inject_fault.o va_layout.o handle_exit.o \
 	 guest.o debug.o reset.o sys_regs.o \
 	 vgic-sys-reg-v3.o fpsimd.o pmu.o \

arch/arm64/kvm/arm.c

@@ -503,6 +503,13 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 	return vcpu_mode_priv(vcpu);
 }
 
+#ifdef CONFIG_GUEST_PERF_EVENTS
+unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
+{
+	return *vcpu_pc(vcpu);
+}
+#endif
+
 /* Just ensure a guest exit from a particular CPU */
 static void exit_vm_noop(void *info)
 {
@@ -1775,7 +1782,8 @@ static int init_subsystems(void)
 	if (err)
 		goto out;
 
-	kvm_perf_init();
+	kvm_register_perf_callbacks(NULL);
+
 	kvm_sys_reg_table_init();
 
 out:
@@ -2163,7 +2171,7 @@ out_err:
 /* NOP: Compiling as a module not supported */
 void kvm_arch_exit(void)
 {
-	kvm_perf_teardown();
+	kvm_unregister_perf_callbacks();
 }
 
 static int __init early_kvm_mode_cfg(char *arg)

arch/arm64/kvm/perf.c

@@ -1,59 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Based on the x86 implementation.
- *
- * Copyright (C) 2012 ARM Ltd.
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- */
-
-#include <linux/perf_event.h>
-#include <linux/kvm_host.h>
-
-#include <asm/kvm_emulate.h>
-
-DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
-
-static int kvm_is_in_guest(void)
-{
-        return kvm_get_running_vcpu() != NULL;
-}
-
-static int kvm_is_user_mode(void)
-{
-	struct kvm_vcpu *vcpu;
-
-	vcpu = kvm_get_running_vcpu();
-
-	if (vcpu)
-		return !vcpu_mode_priv(vcpu);
-
-	return 0;
-}
-
-static unsigned long kvm_get_guest_ip(void)
-{
-	struct kvm_vcpu *vcpu;
-
-	vcpu = kvm_get_running_vcpu();
-
-	if (vcpu)
-		return *vcpu_pc(vcpu);
-
-	return 0;
-}
-
-static struct perf_guest_info_callbacks kvm_guest_cbs = {
-	.is_in_guest	= kvm_is_in_guest,
-	.is_user_mode	= kvm_is_user_mode,
-	.get_guest_ip	= kvm_get_guest_ip,
-};
-
-int kvm_perf_init(void)
-{
-	return perf_register_guest_info_callbacks(&kvm_guest_cbs);
-}
-
-int kvm_perf_teardown(void)
-{
-	return perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
-}

arch/arm64/kvm/pmu-emul.c

@@ -14,6 +14,8 @@
 #include <kvm/arm_pmu.h>
 #include <kvm/arm_vgic.h>
 
+DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
+
 static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx);
 static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx);
 static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc);

arch/csky/kernel/perf_callchain.c

@@ -88,10 +88,6 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 {
 	unsigned long fp = 0;
 
-	/* C-SKY does not support virtualization. */
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
-		return;
-
 	fp = regs->regs[4];
 	perf_callchain_store(entry, regs->pc);
 
@@ -112,12 +108,6 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 {
 	struct stackframe fr;
 
-	/* C-SKY does not support virtualization. */
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		pr_warn("C-SKY does not support perf in guest mode!");
-		return;
-	}
-
 	fr.fp = regs->regs[4];
 	fr.lr = regs->lr;
 	walk_stackframe(&fr, entry);

arch/nds32/kernel/perf_event_cpu.c

@@ -1371,11 +1371,6 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 
 	leaf_fp = 0;
 
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		/* We don't support guest os callchain now */
-		return;
-	}
-
 	perf_callchain_store(entry, regs->ipc);
 	fp = regs->fp;
 	gp = regs->gp;
@@ -1481,10 +1476,6 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 {
 	struct stackframe fr;
 
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		/* We don't support guest os callchain now */
-		return;
-	}
 	fr.fp = regs->fp;
 	fr.lp = regs->lp;
 	fr.sp = regs->sp;
@@ -1493,10 +1484,6 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
-	/* However, NDS32 does not support virtualization */
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
-		return perf_guest_cbs->get_guest_ip();
-
 	return instruction_pointer(regs);
 }
 
@@ -1504,18 +1491,10 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
 {
 	int misc = 0;
 
-	/* However, NDS32 does not support virtualization */
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		if (perf_guest_cbs->is_user_mode())
-			misc |= PERF_RECORD_MISC_GUEST_USER;
-		else
-			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
-	} else {
-		if (user_mode(regs))
-			misc |= PERF_RECORD_MISC_USER;
-		else
-			misc |= PERF_RECORD_MISC_KERNEL;
-	}
+	if (user_mode(regs))
+		misc |= PERF_RECORD_MISC_USER;
+	else
+		misc |= PERF_RECORD_MISC_KERNEL;
 
 	return misc;
 }

arch/riscv/kernel/perf_callchain.c

@@ -58,10 +58,6 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 {
 	unsigned long fp = 0;
 
-	/* RISC-V does not support perf in guest mode. */
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
-		return;
-
 	fp = regs->s0;
 	perf_callchain_store(entry, regs->epc);
 
@@ -78,11 +74,5 @@ static bool fill_callchain(void *entry, unsigned long pc)
 void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 			   struct pt_regs *regs)
 {
-	/* RISC-V does not support perf in guest mode. */
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		pr_warn("RISC-V does not support perf in guest mode!");
-		return;
-	}
-
 	walk_stackframe(NULL, regs, fill_callchain, entry);
 }

arch/x86/Kconfig

@@ -473,6 +473,18 @@ config RETPOLINE
 	  branches. Requires a compiler with -mindirect-branch=thunk-extern
 	  support for full protection. The kernel may run slower.
 
+config CC_HAS_SLS
+	def_bool $(cc-option,-mharden-sls=all)
+
+config SLS
+	bool "Mitigate Straight-Line-Speculation"
+	depends on CC_HAS_SLS && X86_64
+	default n
+	help
+	  Compile the kernel with straight-line-speculation options to guard
+	  against straight line speculation. The kernel image might be slightly
+	  larger.
+
 config X86_CPU_RESCTRL
 	bool "x86 CPU resource control support"
 	depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD)
@@ -1952,7 +1964,7 @@ config EFI
 
 config EFI_STUB
 	bool "EFI stub support"
-	depends on EFI && !X86_USE_3DNOW
+	depends on EFI
 	depends on $(cc-option,-mabi=ms) || X86_32
 	select RELOCATABLE
 	help

arch/x86/Kconfig.cpu

@@ -342,10 +342,6 @@ config X86_USE_PPRO_CHECKSUM
 	def_bool y
 	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM
 
-config X86_USE_3DNOW
-	def_bool y
-	depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML
-
 #
 # P6_NOPs are a relatively minor optimization that require a family >=
 # 6 processor, except that it is broken on certain VIA chips.

arch/x86/Makefile

@@ -12,6 +12,18 @@ else
         KBUILD_DEFCONFIG := $(ARCH)_defconfig
 endif
 
+ifdef CONFIG_CC_IS_GCC
+RETPOLINE_CFLAGS	:= $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
+RETPOLINE_CFLAGS	+= $(call cc-option,-mindirect-branch-cs-prefix)
+RETPOLINE_VDSO_CFLAGS	:= $(call cc-option,-mindirect-branch=thunk-inline -mindirect-branch-register)
+endif
+ifdef CONFIG_CC_IS_CLANG
+RETPOLINE_CFLAGS	:= -mretpoline-external-thunk
+RETPOLINE_VDSO_CFLAGS	:= -mretpoline
+endif
+export RETPOLINE_CFLAGS
+export RETPOLINE_VDSO_CFLAGS
+
 # For gcc stack alignment is specified with -mpreferred-stack-boundary,
 # clang has the option -mstack-alignment for that purpose.
 ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
@@ -179,6 +191,10 @@ ifdef CONFIG_RETPOLINE
   endif
 endif
 
+ifdef CONFIG_SLS
+  KBUILD_CFLAGS += -mharden-sls=all
+endif
+
 KBUILD_LDFLAGS += -m elf_$(UTS_MACHINE)
 
 ifdef CONFIG_LTO_CLANG

arch/x86/boot/compressed/efi_thunk_64.S

@@ -101,7 +101,7 @@ SYM_FUNC_START(__efi64_thunk)
 
 	pop	%rbx
 	pop	%rbp
-	ret
+	RET
 SYM_FUNC_END(__efi64_thunk)
 
 	.code32

arch/x86/boot/compressed/head_64.S

@@ -813,7 +813,7 @@ SYM_FUNC_START(efi32_pe_entry)
 2:	popl	%edi				// restore callee-save registers
 	popl	%ebx
 	leave
-	ret
+	RET
 SYM_FUNC_END(efi32_pe_entry)
 
 	.section ".rodata"
@@ -868,7 +868,7 @@ SYM_FUNC_START(startup32_set_idt_entry)
 
 	pop     %ecx
 	pop     %ebx
-	ret
+	RET
 SYM_FUNC_END(startup32_set_idt_entry)
 #endif
 
@@ -884,7 +884,7 @@ SYM_FUNC_START(startup32_load_idt)
 	movl	%eax, rva(boot32_idt_desc+2)(%ebp)
 	lidt    rva(boot32_idt_desc)(%ebp)
 #endif
-	ret
+	RET
 SYM_FUNC_END(startup32_load_idt)
 
 /*
@@ -954,7 +954,7 @@ SYM_FUNC_START(startup32_check_sev_cbit)
 	popl	%ebx
 	popl	%eax
 #endif
-	ret
+	RET
 SYM_FUNC_END(startup32_check_sev_cbit)
 
 /*

arch/x86/boot/compressed/mem_encrypt.S

@@ -58,7 +58,7 @@ SYM_FUNC_START(get_sev_encryption_bit)
 
 #endif	/* CONFIG_AMD_MEM_ENCRYPT */
 
-	ret
+	RET
 SYM_FUNC_END(get_sev_encryption_bit)
 
 /**
@@ -92,7 +92,7 @@ SYM_CODE_START_LOCAL(sev_es_req_cpuid)
 	/* All good - return success */
 	xorl	%eax, %eax
 1:
-	ret
+	RET
 2:
 	movl	$-1, %eax
 	jmp	1b
@@ -221,7 +221,7 @@ SYM_FUNC_START(set_sev_encryption_mask)
 #endif
 
 	xor	%rax, %rax
-	ret
+	RET
 SYM_FUNC_END(set_sev_encryption_mask)
 
 	.data

arch/x86/crypto/aegis128-aesni-asm.S

@@ -122,7 +122,7 @@ SYM_FUNC_START_LOCAL(__load_partial)
 	pxor T0, MSG
 
 .Lld_partial_8:
-	ret
+	RET
 SYM_FUNC_END(__load_partial)
 
 /*
@@ -180,7 +180,7 @@ SYM_FUNC_START_LOCAL(__store_partial)
 	mov %r10b, (%r9)
 
 .Lst_partial_1:
-	ret
+	RET
 SYM_FUNC_END(__store_partial)
 
 /*
@@ -225,7 +225,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_init)
 	movdqu STATE4, 0x40(STATEP)
 
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(crypto_aegis128_aesni_init)
 
 /*
@@ -337,7 +337,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_ad)
 	movdqu STATE3, 0x30(STATEP)
 	movdqu STATE4, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lad_out_1:
 	movdqu STATE4, 0x00(STATEP)
@@ -346,7 +346,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_ad)
 	movdqu STATE2, 0x30(STATEP)
 	movdqu STATE3, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lad_out_2:
 	movdqu STATE3, 0x00(STATEP)
@@ -355,7 +355,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_ad)
 	movdqu STATE1, 0x30(STATEP)
 	movdqu STATE2, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lad_out_3:
 	movdqu STATE2, 0x00(STATEP)
@@ -364,7 +364,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_ad)
 	movdqu STATE0, 0x30(STATEP)
 	movdqu STATE1, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lad_out_4:
 	movdqu STATE1, 0x00(STATEP)
@@ -373,11 +373,11 @@ SYM_FUNC_START(crypto_aegis128_aesni_ad)
 	movdqu STATE4, 0x30(STATEP)
 	movdqu STATE0, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lad_out:
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(crypto_aegis128_aesni_ad)
 
 .macro encrypt_block a s0 s1 s2 s3 s4 i
@@ -452,7 +452,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc)
 	movdqu STATE2, 0x30(STATEP)
 	movdqu STATE3, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lenc_out_1:
 	movdqu STATE3, 0x00(STATEP)
@@ -461,7 +461,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc)
 	movdqu STATE1, 0x30(STATEP)
 	movdqu STATE2, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lenc_out_2:
 	movdqu STATE2, 0x00(STATEP)
@@ -470,7 +470,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc)
 	movdqu STATE0, 0x30(STATEP)
 	movdqu STATE1, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lenc_out_3:
 	movdqu STATE1, 0x00(STATEP)
@@ -479,7 +479,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc)
 	movdqu STATE4, 0x30(STATEP)
 	movdqu STATE0, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lenc_out_4:
 	movdqu STATE0, 0x00(STATEP)
@@ -488,11 +488,11 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc)
 	movdqu STATE3, 0x30(STATEP)
 	movdqu STATE4, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lenc_out:
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(crypto_aegis128_aesni_enc)
 
 /*
@@ -532,7 +532,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc_tail)
 	movdqu STATE3, 0x40(STATEP)
 
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(crypto_aegis128_aesni_enc_tail)
 
 .macro decrypt_block a s0 s1 s2 s3 s4 i
@@ -606,7 +606,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec)
 	movdqu STATE2, 0x30(STATEP)
 	movdqu STATE3, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Ldec_out_1:
 	movdqu STATE3, 0x00(STATEP)
@@ -615,7 +615,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec)
 	movdqu STATE1, 0x30(STATEP)
 	movdqu STATE2, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Ldec_out_2:
 	movdqu STATE2, 0x00(STATEP)
@@ -624,7 +624,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec)
 	movdqu STATE0, 0x30(STATEP)
 	movdqu STATE1, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Ldec_out_3:
 	movdqu STATE1, 0x00(STATEP)
@@ -633,7 +633,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec)
 	movdqu STATE4, 0x30(STATEP)
 	movdqu STATE0, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Ldec_out_4:
 	movdqu STATE0, 0x00(STATEP)
@@ -642,11 +642,11 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec)
 	movdqu STATE3, 0x30(STATEP)
 	movdqu STATE4, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Ldec_out:
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(crypto_aegis128_aesni_dec)
 
 /*
@@ -696,7 +696,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec_tail)
 	movdqu STATE3, 0x40(STATEP)
 
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(crypto_aegis128_aesni_dec_tail)
 
 /*
@@ -743,5 +743,5 @@ SYM_FUNC_START(crypto_aegis128_aesni_final)
 	movdqu MSG, (%rsi)
 
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(crypto_aegis128_aesni_final)

arch/x86/crypto/aes_ctrby8_avx-x86_64.S

@@ -525,7 +525,7 @@ ddq_add_8:
 	/* return updated IV */
 	vpshufb	xbyteswap, xcounter, xcounter
 	vmovdqu	xcounter, (p_iv)
-	ret
+	RET
 .endm
 
 /*

arch/x86/crypto/aesni-intel_asm.S

@@ -1594,7 +1594,7 @@ SYM_FUNC_START(aesni_gcm_dec)
 	GCM_ENC_DEC dec
 	GCM_COMPLETE arg10, arg11
 	FUNC_RESTORE
-	ret
+	RET
 SYM_FUNC_END(aesni_gcm_dec)
 
 
@@ -1683,7 +1683,7 @@ SYM_FUNC_START(aesni_gcm_enc)
 
 	GCM_COMPLETE arg10, arg11
 	FUNC_RESTORE
-	ret
+	RET
 SYM_FUNC_END(aesni_gcm_enc)
 
 /*****************************************************************************
@@ -1701,7 +1701,7 @@ SYM_FUNC_START(aesni_gcm_init)
 	FUNC_SAVE
 	GCM_INIT %arg3, %arg4,%arg5, %arg6
 	FUNC_RESTORE
-	ret
+	RET
 SYM_FUNC_END(aesni_gcm_init)
 
 /*****************************************************************************
@@ -1716,7 +1716,7 @@ SYM_FUNC_START(aesni_gcm_enc_update)
 	FUNC_SAVE
 	GCM_ENC_DEC enc
 	FUNC_RESTORE
-	ret
+	RET
 SYM_FUNC_END(aesni_gcm_enc_update)
 
 /*****************************************************************************
@@ -1731,7 +1731,7 @@ SYM_FUNC_START(aesni_gcm_dec_update)
 	FUNC_SAVE
 	GCM_ENC_DEC dec
 	FUNC_RESTORE
-	ret
+	RET
 SYM_FUNC_END(aesni_gcm_dec_update)
 
 /*****************************************************************************
@@ -1746,7 +1746,7 @@ SYM_FUNC_START(aesni_gcm_finalize)
 	FUNC_SAVE
 	GCM_COMPLETE %arg3 %arg4
 	FUNC_RESTORE
-	ret
+	RET
 SYM_FUNC_END(aesni_gcm_finalize)
 
 #endif
@@ -1762,7 +1762,7 @@ SYM_FUNC_START_LOCAL(_key_expansion_256a)
 	pxor %xmm1, %xmm0
 	movaps %xmm0, (TKEYP)
 	add $0x10, TKEYP
-	ret
+	RET
 SYM_FUNC_END(_key_expansion_256a)
 SYM_FUNC_END_ALIAS(_key_expansion_128)
 
@@ -1787,7 +1787,7 @@ SYM_FUNC_START_LOCAL(_key_expansion_192a)
 	shufps $0b01001110, %xmm2, %xmm1
 	movaps %xmm1, 0x10(TKEYP)
 	add $0x20, TKEYP
-	ret
+	RET
 SYM_FUNC_END(_key_expansion_192a)
 
 SYM_FUNC_START_LOCAL(_key_expansion_192b)
@@ -1806,7 +1806,7 @@ SYM_FUNC_START_LOCAL(_key_expansion_192b)
 
 	movaps %xmm0, (TKEYP)
 	add $0x10, TKEYP
-	ret
+	RET
 SYM_FUNC_END(_key_expansion_192b)
 
 SYM_FUNC_START_LOCAL(_key_expansion_256b)
@@ -1818,7 +1818,7 @@ SYM_FUNC_START_LOCAL(_key_expansion_256b)
 	pxor %xmm1, %xmm2
 	movaps %xmm2, (TKEYP)
 	add $0x10, TKEYP
-	ret
+	RET
 SYM_FUNC_END(_key_expansion_256b)
 
 /*
@@ -1933,7 +1933,7 @@ SYM_FUNC_START(aesni_set_key)
 	popl KEYP
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_set_key)
 
 /*
@@ -1957,7 +1957,7 @@ SYM_FUNC_START(aesni_enc)
 	popl KEYP
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_enc)
 
 /*
@@ -2014,7 +2014,7 @@ SYM_FUNC_START_LOCAL(_aesni_enc1)
 	aesenc KEY, STATE
 	movaps 0x70(TKEYP), KEY
 	aesenclast KEY, STATE
-	ret
+	RET
 SYM_FUNC_END(_aesni_enc1)
 
 /*
@@ -2122,7 +2122,7 @@ SYM_FUNC_START_LOCAL(_aesni_enc4)
 	aesenclast KEY, STATE2
 	aesenclast KEY, STATE3
 	aesenclast KEY, STATE4
-	ret
+	RET
 SYM_FUNC_END(_aesni_enc4)
 
 /*
@@ -2147,7 +2147,7 @@ SYM_FUNC_START(aesni_dec)
 	popl KEYP
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_dec)
 
 /*
@@ -2204,7 +2204,7 @@ SYM_FUNC_START_LOCAL(_aesni_dec1)
 	aesdec KEY, STATE
 	movaps 0x70(TKEYP), KEY
 	aesdeclast KEY, STATE
-	ret
+	RET
 SYM_FUNC_END(_aesni_dec1)
 
 /*
@@ -2312,7 +2312,7 @@ SYM_FUNC_START_LOCAL(_aesni_dec4)
 	aesdeclast KEY, STATE2
 	aesdeclast KEY, STATE3
 	aesdeclast KEY, STATE4
-	ret
+	RET
 SYM_FUNC_END(_aesni_dec4)
 
 /*
@@ -2372,7 +2372,7 @@ SYM_FUNC_START(aesni_ecb_enc)
 	popl LEN
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_ecb_enc)
 
 /*
@@ -2433,7 +2433,7 @@ SYM_FUNC_START(aesni_ecb_dec)
 	popl LEN
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_ecb_dec)
 
 /*
@@ -2477,7 +2477,7 @@ SYM_FUNC_START(aesni_cbc_enc)
 	popl IVP
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_cbc_enc)
 
 /*
@@ -2570,7 +2570,7 @@ SYM_FUNC_START(aesni_cbc_dec)
 	popl IVP
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_cbc_dec)
 
 /*
@@ -2627,7 +2627,7 @@ SYM_FUNC_START(aesni_cts_cbc_enc)
 	popl IVP
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_cts_cbc_enc)
 
 /*
@@ -2688,7 +2688,7 @@ SYM_FUNC_START(aesni_cts_cbc_dec)
 	popl IVP
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_cts_cbc_dec)
 
 .pushsection .rodata
@@ -2725,7 +2725,7 @@ SYM_FUNC_START_LOCAL(_aesni_inc_init)
 	mov $1, TCTR_LOW
 	movq TCTR_LOW, INC
 	movq CTR, TCTR_LOW
-	ret
+	RET
 SYM_FUNC_END(_aesni_inc_init)
 
 /*
@@ -2753,7 +2753,7 @@ SYM_FUNC_START_LOCAL(_aesni_inc)
 .Linc_low:
 	movaps CTR, IV
 	pshufb BSWAP_MASK, IV
-	ret
+	RET
 SYM_FUNC_END(_aesni_inc)
 
 /*
@@ -2816,7 +2816,7 @@ SYM_FUNC_START(aesni_ctr_enc)
 	movups IV, (IVP)
 .Lctr_enc_just_ret:
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_ctr_enc)
 
 #endif
@@ -2932,7 +2932,7 @@ SYM_FUNC_START(aesni_xts_encrypt)
 	popl IVP
 #endif
 	FRAME_END
-	ret
+	RET
 
 .Lxts_enc_1x:
 	add $64, LEN
@@ -3092,7 +3092,7 @@ SYM_FUNC_START(aesni_xts_decrypt)
 	popl IVP
 #endif
 	FRAME_END
-	ret
+	RET
 
 .Lxts_dec_1x:
 	add $64, LEN

arch/x86/crypto/aesni-intel_avx-x86_64.S

@@ -1767,7 +1767,7 @@ SYM_FUNC_START(aesni_gcm_init_avx_gen2)
         FUNC_SAVE
         INIT GHASH_MUL_AVX, PRECOMPUTE_AVX
         FUNC_RESTORE
-        ret
+        RET
 SYM_FUNC_END(aesni_gcm_init_avx_gen2)
 
 ###############################################################################
@@ -1788,15 +1788,15 @@ SYM_FUNC_START(aesni_gcm_enc_update_avx_gen2)
         # must be 192
         GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 11
         FUNC_RESTORE
-        ret
+        RET
 key_128_enc_update:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 9
         FUNC_RESTORE
-        ret
+        RET
 key_256_enc_update:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 13
         FUNC_RESTORE
-        ret
+        RET
 SYM_FUNC_END(aesni_gcm_enc_update_avx_gen2)
 
 ###############################################################################
@@ -1817,15 +1817,15 @@ SYM_FUNC_START(aesni_gcm_dec_update_avx_gen2)
         # must be 192
         GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 11
         FUNC_RESTORE
-        ret
+        RET
 key_128_dec_update:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 9
         FUNC_RESTORE
-        ret
+        RET
 key_256_dec_update:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 13
         FUNC_RESTORE
-        ret
+        RET
 SYM_FUNC_END(aesni_gcm_dec_update_avx_gen2)
 
 ###############################################################################
@@ -1846,15 +1846,15 @@ SYM_FUNC_START(aesni_gcm_finalize_avx_gen2)
         # must be 192
         GCM_COMPLETE GHASH_MUL_AVX, 11, arg3, arg4
         FUNC_RESTORE
-        ret
+        RET
 key_128_finalize:
         GCM_COMPLETE GHASH_MUL_AVX, 9, arg3, arg4
         FUNC_RESTORE
-        ret
+        RET
 key_256_finalize:
         GCM_COMPLETE GHASH_MUL_AVX, 13, arg3, arg4
         FUNC_RESTORE
-        ret
+        RET
 SYM_FUNC_END(aesni_gcm_finalize_avx_gen2)
 
 ###############################################################################
@@ -2735,7 +2735,7 @@ SYM_FUNC_START(aesni_gcm_init_avx_gen4)
         FUNC_SAVE
         INIT GHASH_MUL_AVX2, PRECOMPUTE_AVX2
         FUNC_RESTORE
-        ret
+        RET
 SYM_FUNC_END(aesni_gcm_init_avx_gen4)
 
 ###############################################################################
@@ -2756,15 +2756,15 @@ SYM_FUNC_START(aesni_gcm_enc_update_avx_gen4)
         # must be 192
         GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 11
         FUNC_RESTORE
-	ret
+	RET
 key_128_enc_update4:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 9
         FUNC_RESTORE
-	ret
+	RET
 key_256_enc_update4:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 13
         FUNC_RESTORE
-	ret
+	RET
 SYM_FUNC_END(aesni_gcm_enc_update_avx_gen4)
 
 ###############################################################################
@@ -2785,15 +2785,15 @@ SYM_FUNC_START(aesni_gcm_dec_update_avx_gen4)
         # must be 192
         GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 11
         FUNC_RESTORE
-        ret
+        RET
 key_128_dec_update4:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 9
         FUNC_RESTORE
-        ret
+        RET
 key_256_dec_update4:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 13
         FUNC_RESTORE
-        ret
+        RET
 SYM_FUNC_END(aesni_gcm_dec_update_avx_gen4)
 
 ###############################################################################
@@ -2814,13 +2814,13 @@ SYM_FUNC_START(aesni_gcm_finalize_avx_gen4)
         # must be 192
         GCM_COMPLETE GHASH_MUL_AVX2, 11, arg3, arg4
         FUNC_RESTORE
-        ret
+        RET
 key_128_finalize4:
         GCM_COMPLETE GHASH_MUL_AVX2, 9, arg3, arg4
         FUNC_RESTORE
-        ret
+        RET
 key_256_finalize4:
         GCM_COMPLETE GHASH_MUL_AVX2, 13, arg3, arg4
         FUNC_RESTORE
-        ret
+        RET
 SYM_FUNC_END(aesni_gcm_finalize_avx_gen4)

arch/x86/crypto/blake2s-core.S

@@ -171,7 +171,7 @@ SYM_FUNC_START(blake2s_compress_ssse3)
 	movdqu		%xmm1,0x10(%rdi)
 	movdqu		%xmm14,0x20(%rdi)
 .Lendofloop:
-	ret
+	RET
 SYM_FUNC_END(blake2s_compress_ssse3)
 
 #ifdef CONFIG_AS_AVX512
@@ -251,6 +251,6 @@ SYM_FUNC_START(blake2s_compress_avx512)
 	vmovdqu		%xmm1,0x10(%rdi)
 	vmovdqu		%xmm4,0x20(%rdi)
 	vzeroupper
-	retq
+	RET
 SYM_FUNC_END(blake2s_compress_avx512)
 #endif /* CONFIG_AS_AVX512 */

arch/x86/crypto/blowfish-x86_64-asm_64.S

@@ -135,10 +135,10 @@ SYM_FUNC_START(__blowfish_enc_blk)
 	jnz .L__enc_xor;
 
 	write_block();
-	ret;
+	RET;
 .L__enc_xor:
 	xor_block();
-	ret;
+	RET;
 SYM_FUNC_END(__blowfish_enc_blk)
 
 SYM_FUNC_START(blowfish_dec_blk)
@@ -170,7 +170,7 @@ SYM_FUNC_START(blowfish_dec_blk)
 
 	movq %r11, %r12;
 
-	ret;
+	RET;
 SYM_FUNC_END(blowfish_dec_blk)
 
 /**********************************************************************
@@ -322,14 +322,14 @@ SYM_FUNC_START(__blowfish_enc_blk_4way)
 
 	popq %rbx;
 	popq %r12;
-	ret;
+	RET;
 
 .L__enc_xor4:
 	xor_block4();
 
 	popq %rbx;
 	popq %r12;
-	ret;
+	RET;
 SYM_FUNC_END(__blowfish_enc_blk_4way)
 
 SYM_FUNC_START(blowfish_dec_blk_4way)
@@ -364,5 +364,5 @@ SYM_FUNC_START(blowfish_dec_blk_4way)
 	popq %rbx;
 	popq %r12;
 
-	ret;
+	RET;
 SYM_FUNC_END(blowfish_dec_blk_4way)

arch/x86/crypto/camellia-aesni-avx-asm_64.S

@@ -192,7 +192,7 @@ SYM_FUNC_START_LOCAL(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_c
 	roundsm16(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7,
 		  %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15,
 		  %rcx, (%r9));
-	ret;
+	RET;
 SYM_FUNC_END(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 
 .align 8
@@ -200,7 +200,7 @@ SYM_FUNC_START_LOCAL(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_a
 	roundsm16(%xmm4, %xmm5, %xmm6, %xmm7, %xmm0, %xmm1, %xmm2, %xmm3,
 		  %xmm12, %xmm13, %xmm14, %xmm15, %xmm8, %xmm9, %xmm10, %xmm11,
 		  %rax, (%r9));
-	ret;
+	RET;
 SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 
 /*
@@ -778,7 +778,7 @@ SYM_FUNC_START_LOCAL(__camellia_enc_blk16)
 		    %xmm15, (key_table)(CTX, %r8, 8), (%rax), 1 * 16(%rax));
 
 	FRAME_END
-	ret;
+	RET;
 
 .align 8
 .Lenc_max32:
@@ -865,7 +865,7 @@ SYM_FUNC_START_LOCAL(__camellia_dec_blk16)
 		    %xmm15, (key_table)(CTX), (%rax), 1 * 16(%rax));
 
 	FRAME_END
-	ret;
+	RET;
 
 .align 8
 .Ldec_max32:
@@ -906,7 +906,7 @@ SYM_FUNC_START(camellia_ecb_enc_16way)
 		     %xmm8, %rsi);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(camellia_ecb_enc_16way)
 
 SYM_FUNC_START(camellia_ecb_dec_16way)
@@ -936,7 +936,7 @@ SYM_FUNC_START(camellia_ecb_dec_16way)
 		     %xmm8, %rsi);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(camellia_ecb_dec_16way)
 
 SYM_FUNC_START(camellia_cbc_dec_16way)
@@ -987,5 +987,5 @@ SYM_FUNC_START(camellia_cbc_dec_16way)
 		     %xmm8, %rsi);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(camellia_cbc_dec_16way)

arch/x86/crypto/camellia-aesni-avx2-asm_64.S

@@ -226,7 +226,7 @@ SYM_FUNC_START_LOCAL(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_c
 	roundsm32(%ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7,
 		  %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15,
 		  %rcx, (%r9));
-	ret;
+	RET;
 SYM_FUNC_END(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 
 .align 8
@@ -234,7 +234,7 @@ SYM_FUNC_START_LOCAL(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_a
 	roundsm32(%ymm4, %ymm5, %ymm6, %ymm7, %ymm0, %ymm1, %ymm2, %ymm3,
 		  %ymm12, %ymm13, %ymm14, %ymm15, %ymm8, %ymm9, %ymm10, %ymm11,
 		  %rax, (%r9));
-	ret;
+	RET;
 SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 
 /*
@@ -814,7 +814,7 @@ SYM_FUNC_START_LOCAL(__camellia_enc_blk32)
 		    %ymm15, (key_table)(CTX, %r8, 8), (%rax), 1 * 32(%rax));
 
 	FRAME_END
-	ret;
+	RET;
 
 .align 8
 .Lenc_max32:
@@ -901,7 +901,7 @@ SYM_FUNC_START_LOCAL(__camellia_dec_blk32)
 		    %ymm15, (key_table)(CTX), (%rax), 1 * 32(%rax));
 
 	FRAME_END
-	ret;
+	RET;
 
 .align 8
 .Ldec_max32:
@@ -946,7 +946,7 @@ SYM_FUNC_START(camellia_ecb_enc_32way)
 	vzeroupper;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(camellia_ecb_enc_32way)
 
 SYM_FUNC_START(camellia_ecb_dec_32way)
@@ -980,7 +980,7 @@ SYM_FUNC_START(camellia_ecb_dec_32way)
 	vzeroupper;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(camellia_ecb_dec_32way)
 
 SYM_FUNC_START(camellia_cbc_dec_32way)
@@ -1047,5 +1047,5 @@ SYM_FUNC_START(camellia_cbc_dec_32way)
 
 	addq $(16 * 32), %rsp;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(camellia_cbc_dec_32way)

arch/x86/crypto/camellia-x86_64-asm_64.S

@@ -213,13 +213,13 @@ SYM_FUNC_START(__camellia_enc_blk)
 	enc_outunpack(mov, RT1);
 
 	movq RR12, %r12;
-	ret;
+	RET;
 
 .L__enc_xor:
 	enc_outunpack(xor, RT1);
 
 	movq RR12, %r12;
-	ret;
+	RET;
 SYM_FUNC_END(__camellia_enc_blk)
 
 SYM_FUNC_START(camellia_dec_blk)
@@ -257,7 +257,7 @@ SYM_FUNC_START(camellia_dec_blk)
 	dec_outunpack();
 
 	movq RR12, %r12;
-	ret;
+	RET;
 SYM_FUNC_END(camellia_dec_blk)
 
 /**********************************************************************
@@ -448,14 +448,14 @@ SYM_FUNC_START(__camellia_enc_blk_2way)
 
 	movq RR12, %r12;
 	popq %rbx;
-	ret;
+	RET;
 
 .L__enc2_xor:
 	enc_outunpack2(xor, RT2);
 
 	movq RR12, %r12;
 	popq %rbx;
-	ret;
+	RET;
 SYM_FUNC_END(__camellia_enc_blk_2way)
 
 SYM_FUNC_START(camellia_dec_blk_2way)
@@ -495,5 +495,5 @@ SYM_FUNC_START(camellia_dec_blk_2way)
 
 	movq RR12, %r12;
 	movq RXOR, %rbx;
-	ret;
+	RET;
 SYM_FUNC_END(camellia_dec_blk_2way)

arch/x86/crypto/cast5-avx-x86_64-asm_64.S

@@ -279,7 +279,7 @@ SYM_FUNC_START_LOCAL(__cast5_enc_blk16)
 	outunpack_blocks(RR3, RL3, RTMP, RX, RKM);
 	outunpack_blocks(RR4, RL4, RTMP, RX, RKM);
 
-	ret;
+	RET;
 SYM_FUNC_END(__cast5_enc_blk16)
 
 .align 16
@@ -352,7 +352,7 @@ SYM_FUNC_START_LOCAL(__cast5_dec_blk16)
 	outunpack_blocks(RR3, RL3, RTMP, RX, RKM);
 	outunpack_blocks(RR4, RL4, RTMP, RX, RKM);
 
-	ret;
+	RET;
 
 .L__skip_dec:
 	vpsrldq $4, RKR, RKR;
@@ -393,7 +393,7 @@ SYM_FUNC_START(cast5_ecb_enc_16way)
 
 	popq %r15;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(cast5_ecb_enc_16way)
 
 SYM_FUNC_START(cast5_ecb_dec_16way)
@@ -431,7 +431,7 @@ SYM_FUNC_START(cast5_ecb_dec_16way)
 
 	popq %r15;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(cast5_ecb_dec_16way)
 
 SYM_FUNC_START(cast5_cbc_dec_16way)
@@ -483,7 +483,7 @@ SYM_FUNC_START(cast5_cbc_dec_16way)
 	popq %r15;
 	popq %r12;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(cast5_cbc_dec_16way)
 
 SYM_FUNC_START(cast5_ctr_16way)
@@ -559,5 +559,5 @@ SYM_FUNC_START(cast5_ctr_16way)
 	popq %r15;
 	popq %r12;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(cast5_ctr_16way)

arch/x86/crypto/cast6-avx-x86_64-asm_64.S

@@ -289,7 +289,7 @@ SYM_FUNC_START_LOCAL(__cast6_enc_blk8)
 	outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
 	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
 
-	ret;
+	RET;
 SYM_FUNC_END(__cast6_enc_blk8)
 
 .align 8
@@ -336,7 +336,7 @@ SYM_FUNC_START_LOCAL(__cast6_dec_blk8)
 	outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
 	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
 
-	ret;
+	RET;
 SYM_FUNC_END(__cast6_dec_blk8)
 
 SYM_FUNC_START(cast6_ecb_enc_8way)
@@ -359,7 +359,7 @@ SYM_FUNC_START(cast6_ecb_enc_8way)
 
 	popq %r15;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(cast6_ecb_enc_8way)
 
 SYM_FUNC_START(cast6_ecb_dec_8way)
@@ -382,7 +382,7 @@ SYM_FUNC_START(cast6_ecb_dec_8way)
 
 	popq %r15;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(cast6_ecb_dec_8way)
 
 SYM_FUNC_START(cast6_cbc_dec_8way)
@@ -408,5 +408,5 @@ SYM_FUNC_START(cast6_cbc_dec_8way)
 	popq %r15;
 	popq %r12;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(cast6_cbc_dec_8way)

arch/x86/crypto/chacha-avx2-x86_64.S

@@ -193,7 +193,7 @@ SYM_FUNC_START(chacha_2block_xor_avx2)
 
 .Ldone2:
 	vzeroupper
-	ret
+	RET
 
 .Lxorpart2:
 	# xor remaining bytes from partial register into output
@@ -498,7 +498,7 @@ SYM_FUNC_START(chacha_4block_xor_avx2)
 
 .Ldone4:
 	vzeroupper
-	ret
+	RET
 
 .Lxorpart4:
 	# xor remaining bytes from partial register into output
@@ -992,7 +992,7 @@ SYM_FUNC_START(chacha_8block_xor_avx2)
 .Ldone8:
 	vzeroupper
 	lea		-8(%r10),%rsp
-	ret
+	RET
 
 .Lxorpart8:
 	# xor remaining bytes from partial register into output

arch/x86/crypto/chacha-avx512vl-x86_64.S

@@ -166,7 +166,7 @@ SYM_FUNC_START(chacha_2block_xor_avx512vl)
 
 .Ldone2:
 	vzeroupper
-	ret
+	RET
 
 .Lxorpart2:
 	# xor remaining bytes from partial register into output
@@ -432,7 +432,7 @@ SYM_FUNC_START(chacha_4block_xor_avx512vl)
 
 .Ldone4:
 	vzeroupper
-	ret
+	RET
 
 .Lxorpart4:
 	# xor remaining bytes from partial register into output
@@ -812,7 +812,7 @@ SYM_FUNC_START(chacha_8block_xor_avx512vl)
 
 .Ldone8:
 	vzeroupper
-	ret
+	RET
 
 .Lxorpart8:
 	# xor remaining bytes from partial register into output

arch/x86/crypto/chacha-ssse3-x86_64.S

@@ -108,7 +108,7 @@ SYM_FUNC_START_LOCAL(chacha_permute)
 	sub		$2,%r8d
 	jnz		.Ldoubleround
 
-	ret
+	RET
 SYM_FUNC_END(chacha_permute)
 
 SYM_FUNC_START(chacha_block_xor_ssse3)
@@ -166,7 +166,7 @@ SYM_FUNC_START(chacha_block_xor_ssse3)
 
 .Ldone:
 	FRAME_END
-	ret
+	RET
 
 .Lxorpart:
 	# xor remaining bytes from partial register into output
@@ -217,7 +217,7 @@ SYM_FUNC_START(hchacha_block_ssse3)
 	movdqu		%xmm3,0x10(%rsi)
 
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(hchacha_block_ssse3)
 
 SYM_FUNC_START(chacha_4block_xor_ssse3)
@@ -762,7 +762,7 @@ SYM_FUNC_START(chacha_4block_xor_ssse3)
 
 .Ldone4:
 	lea		-8(%r10),%rsp
-	ret
+	RET
 
 .Lxorpart4:
 	# xor remaining bytes from partial register into output

arch/x86/crypto/crc32-pclmul_asm.S

@@ -236,5 +236,5 @@ fold_64:
 	pxor    %xmm2, %xmm1
 	pextrd  $0x01, %xmm1, %eax
 
-	ret
+	RET
 SYM_FUNC_END(crc32_pclmul_le_16)

arch/x86/crypto/crc32c-pcl-intel-asm_64.S

@@ -306,7 +306,7 @@ do_return:
 	popq    %rsi
 	popq    %rdi
 	popq    %rbx
-        ret
+        RET
 SYM_FUNC_END(crc_pcl)
 
 .section	.rodata, "a", @progbits

arch/x86/crypto/crct10dif-pcl-asm_64.S

@@ -257,7 +257,7 @@ SYM_FUNC_START(crc_t10dif_pcl)
 	# Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of xmm0.
 
 	pextrw	$0, %xmm0, %eax
-	ret
+	RET
 
 .align 16
 .Lless_than_256_bytes:

arch/x86/crypto/des3_ede-asm_64.S

@@ -243,7 +243,7 @@ SYM_FUNC_START(des3_ede_x86_64_crypt_blk)
 	popq %r12;
 	popq %rbx;
 
-	ret;
+	RET;
 SYM_FUNC_END(des3_ede_x86_64_crypt_blk)
 
 /***********************************************************************
@@ -528,7 +528,7 @@ SYM_FUNC_START(des3_ede_x86_64_crypt_blk_3way)
 	popq %r12;
 	popq %rbx;
 
-	ret;
+	RET;
 SYM_FUNC_END(des3_ede_x86_64_crypt_blk_3way)
 
 .section	.rodata, "a", @progbits

arch/x86/crypto/ghash-clmulni-intel_asm.S

@@ -85,7 +85,7 @@ SYM_FUNC_START_LOCAL(__clmul_gf128mul_ble)
 	psrlq $1, T2
 	pxor T2, T1
 	pxor T1, DATA
-	ret
+	RET
 SYM_FUNC_END(__clmul_gf128mul_ble)
 
 /* void clmul_ghash_mul(char *dst, const u128 *shash) */
@@ -99,7 +99,7 @@ SYM_FUNC_START(clmul_ghash_mul)
 	pshufb BSWAP, DATA
 	movups DATA, (%rdi)
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(clmul_ghash_mul)
 
 /*
@@ -128,5 +128,5 @@ SYM_FUNC_START(clmul_ghash_update)
 	movups DATA, (%rdi)
 .Lupdate_just_ret:
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(clmul_ghash_update)

arch/x86/crypto/nh-avx2-x86_64.S

@@ -153,5 +153,5 @@ SYM_FUNC_START(nh_avx2)
 	vpaddq		T1, T0, T0
 	vpaddq		T4, T0, T0
 	vmovdqu		T0, (HASH)
-	ret
+	RET
 SYM_FUNC_END(nh_avx2)

arch/x86/crypto/nh-sse2-x86_64.S

@@ -119,5 +119,5 @@ SYM_FUNC_START(nh_sse2)
 	paddq		PASS2_SUMS, T1
 	movdqu		T0, 0x00(HASH)
 	movdqu		T1, 0x10(HASH)
-	ret
+	RET
 SYM_FUNC_END(nh_sse2)

arch/x86/crypto/serpent-avx-x86_64-asm_64.S

@@ -601,7 +601,7 @@ SYM_FUNC_START_LOCAL(__serpent_enc_blk8_avx)
 	write_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
 	write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(__serpent_enc_blk8_avx)
 
 .align 8
@@ -655,7 +655,7 @@ SYM_FUNC_START_LOCAL(__serpent_dec_blk8_avx)
 	write_blocks(RC1, RD1, RB1, RE1, RK0, RK1, RK2);
 	write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(__serpent_dec_blk8_avx)
 
 SYM_FUNC_START(serpent_ecb_enc_8way_avx)
@@ -673,7 +673,7 @@ SYM_FUNC_START(serpent_ecb_enc_8way_avx)
 	store_8way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(serpent_ecb_enc_8way_avx)
 
 SYM_FUNC_START(serpent_ecb_dec_8way_avx)
@@ -691,7 +691,7 @@ SYM_FUNC_START(serpent_ecb_dec_8way_avx)
 	store_8way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(serpent_ecb_dec_8way_avx)
 
 SYM_FUNC_START(serpent_cbc_dec_8way_avx)
@@ -709,5 +709,5 @@ SYM_FUNC_START(serpent_cbc_dec_8way_avx)
 	store_cbc_8way(%rdx, %rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(serpent_cbc_dec_8way_avx)

arch/x86/crypto/serpent-avx2-asm_64.S

@@ -601,7 +601,7 @@ SYM_FUNC_START_LOCAL(__serpent_enc_blk16)
 	write_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
 	write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(__serpent_enc_blk16)
 
 .align 8
@@ -655,7 +655,7 @@ SYM_FUNC_START_LOCAL(__serpent_dec_blk16)
 	write_blocks(RC1, RD1, RB1, RE1, RK0, RK1, RK2);
 	write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(__serpent_dec_blk16)
 
 SYM_FUNC_START(serpent_ecb_enc_16way)
@@ -677,7 +677,7 @@ SYM_FUNC_START(serpent_ecb_enc_16way)
 	vzeroupper;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(serpent_ecb_enc_16way)
 
 SYM_FUNC_START(serpent_ecb_dec_16way)
@@ -699,7 +699,7 @@ SYM_FUNC_START(serpent_ecb_dec_16way)
 	vzeroupper;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(serpent_ecb_dec_16way)
 
 SYM_FUNC_START(serpent_cbc_dec_16way)
@@ -722,5 +722,5 @@ SYM_FUNC_START(serpent_cbc_dec_16way)
 	vzeroupper;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(serpent_cbc_dec_16way)

arch/x86/crypto/serpent-sse2-i586-asm_32.S

@@ -553,12 +553,12 @@ SYM_FUNC_START(__serpent_enc_blk_4way)
 
 	write_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
 
-	ret;
+	RET;
 
 .L__enc_xor4:
 	xor_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
 
-	ret;
+	RET;
 SYM_FUNC_END(__serpent_enc_blk_4way)
 
 SYM_FUNC_START(serpent_dec_blk_4way)
@@ -612,5 +612,5 @@ SYM_FUNC_START(serpent_dec_blk_4way)
 	movl arg_dst(%esp), %eax;
 	write_blocks(%eax, RC, RD, RB, RE, RT0, RT1, RA);
 
-	ret;
+	RET;
 SYM_FUNC_END(serpent_dec_blk_4way)

arch/x86/crypto/serpent-sse2-x86_64-asm_64.S

@@ -675,13 +675,13 @@ SYM_FUNC_START(__serpent_enc_blk_8way)
 	write_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
 	write_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
-	ret;
+	RET;
 
 .L__enc_xor8:
 	xor_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
 	xor_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(__serpent_enc_blk_8way)
 
 SYM_FUNC_START(serpent_dec_blk_8way)
@@ -735,5 +735,5 @@ SYM_FUNC_START(serpent_dec_blk_8way)
 	write_blocks(%rsi, RC1, RD1, RB1, RE1, RK0, RK1, RK2);
 	write_blocks(%rax, RC2, RD2, RB2, RE2, RK0, RK1, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(serpent_dec_blk_8way)

arch/x86/crypto/sha1_avx2_x86_64_asm.S

@@ -674,7 +674,7 @@ _loop3:
 	pop	%r12
 	pop	%rbx
 
-	ret
+	RET
 
 	SYM_FUNC_END(\name)
 .endm

arch/x86/crypto/sha1_ni_asm.S

@@ -290,7 +290,7 @@ SYM_FUNC_START(sha1_ni_transform)
 	mov		%rbp, %rsp
 	pop		%rbp
 
-	ret
+	RET
 SYM_FUNC_END(sha1_ni_transform)
 
 .section	.rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16

arch/x86/crypto/sha1_ssse3_asm.S

@@ -99,7 +99,7 @@
 	pop	%rbp
 	pop	%r12
 	pop	%rbx
-	ret
+	RET
 
 	SYM_FUNC_END(\name)
 .endm

arch/x86/crypto/sha256-avx-asm.S

@@ -458,7 +458,7 @@ done_hash:
 	popq    %r13
 	popq	%r12
 	popq    %rbx
-	ret
+	RET
 SYM_FUNC_END(sha256_transform_avx)
 
 .section	.rodata.cst256.K256, "aM", @progbits, 256

arch/x86/crypto/sha256-avx2-asm.S

@@ -710,7 +710,7 @@ done_hash:
 	popq	%r13
 	popq	%r12
 	popq	%rbx
-	ret
+	RET
 SYM_FUNC_END(sha256_transform_rorx)
 
 .section	.rodata.cst512.K256, "aM", @progbits, 512

arch/x86/crypto/sha256-ssse3-asm.S

@@ -472,7 +472,7 @@ done_hash:
 	popq    %r12
 	popq    %rbx
 
-	ret
+	RET
 SYM_FUNC_END(sha256_transform_ssse3)
 
 .section	.rodata.cst256.K256, "aM", @progbits, 256

arch/x86/crypto/sha256_ni_asm.S

@@ -326,7 +326,7 @@ SYM_FUNC_START(sha256_ni_transform)
 
 .Ldone_hash:
 
-	ret
+	RET
 SYM_FUNC_END(sha256_ni_transform)
 
 .section	.rodata.cst256.K256, "aM", @progbits, 256

arch/x86/crypto/sha512-avx-asm.S

@@ -361,7 +361,7 @@ updateblock:
 	pop	%rbx
 
 nowork:
-	ret
+	RET
 SYM_FUNC_END(sha512_transform_avx)
 
 ########################################################################

arch/x86/crypto/sha512-avx2-asm.S

@@ -679,7 +679,7 @@ done_hash:
 	pop	%r12
 	pop	%rbx
 
-	ret
+	RET
 SYM_FUNC_END(sha512_transform_rorx)
 
 ########################################################################

arch/x86/crypto/sha512-ssse3-asm.S

@@ -363,7 +363,7 @@ updateblock:
 	pop	%rbx
 
 nowork:
-	ret
+	RET
 SYM_FUNC_END(sha512_transform_ssse3)
 
 ########################################################################

arch/x86/crypto/sm4-aesni-avx-asm_64.S

@@ -246,7 +246,7 @@ SYM_FUNC_START(sm4_aesni_avx_crypt4)
 .Lblk4_store_output_done:
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx_crypt4)
 
 .align 8
@@ -356,7 +356,7 @@ SYM_FUNC_START_LOCAL(__sm4_crypt_blk8)
 	vpshufb RTMP2, RB3, RB3;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(__sm4_crypt_blk8)
 
 /*
@@ -412,7 +412,7 @@ SYM_FUNC_START(sm4_aesni_avx_crypt8)
 .Lblk8_store_output_done:
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx_crypt8)
 
 /*
@@ -487,7 +487,7 @@ SYM_FUNC_START(sm4_aesni_avx_ctr_enc_blk8)
 
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx_ctr_enc_blk8)
 
 /*
@@ -537,7 +537,7 @@ SYM_FUNC_START(sm4_aesni_avx_cbc_dec_blk8)
 
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx_cbc_dec_blk8)
 
 /*
@@ -590,5 +590,5 @@ SYM_FUNC_START(sm4_aesni_avx_cfb_dec_blk8)
 
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx_cfb_dec_blk8)

arch/x86/crypto/sm4-aesni-avx2-asm_64.S

@@ -268,7 +268,7 @@ SYM_FUNC_START_LOCAL(__sm4_crypt_blk16)
 	vpshufb RTMP2, RB3, RB3;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(__sm4_crypt_blk16)
 
 #define inc_le128(x, minus_one, tmp) \
@@ -387,7 +387,7 @@ SYM_FUNC_START(sm4_aesni_avx2_ctr_enc_blk16)
 
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx2_ctr_enc_blk16)
 
 /*
@@ -441,7 +441,7 @@ SYM_FUNC_START(sm4_aesni_avx2_cbc_dec_blk16)
 
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx2_cbc_dec_blk16)
 
 /*
@@ -497,5 +497,5 @@ SYM_FUNC_START(sm4_aesni_avx2_cfb_dec_blk16)
 
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx2_cfb_dec_blk16)

arch/x86/crypto/twofish-avx-x86_64-asm_64.S

@@ -267,7 +267,7 @@ SYM_FUNC_START_LOCAL(__twofish_enc_blk8)
 	outunpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
 	outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(__twofish_enc_blk8)
 
 .align 8
@@ -307,7 +307,7 @@ SYM_FUNC_START_LOCAL(__twofish_dec_blk8)
 	outunpack_blocks(RA1, RB1, RC1, RD1, RK1, RX0, RY0, RK2);
 	outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(__twofish_dec_blk8)
 
 SYM_FUNC_START(twofish_ecb_enc_8way)
@@ -327,7 +327,7 @@ SYM_FUNC_START(twofish_ecb_enc_8way)
 	store_8way(%r11, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(twofish_ecb_enc_8way)
 
 SYM_FUNC_START(twofish_ecb_dec_8way)
@@ -347,7 +347,7 @@ SYM_FUNC_START(twofish_ecb_dec_8way)
 	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(twofish_ecb_dec_8way)
 
 SYM_FUNC_START(twofish_cbc_dec_8way)
@@ -372,5 +372,5 @@ SYM_FUNC_START(twofish_cbc_dec_8way)
 	popq %r12;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(twofish_cbc_dec_8way)

arch/x86/crypto/twofish-i586-asm_32.S

@@ -260,7 +260,7 @@ SYM_FUNC_START(twofish_enc_blk)
 	pop	%ebx
 	pop	%ebp
 	mov	$1,	%eax
-	ret
+	RET
 SYM_FUNC_END(twofish_enc_blk)
 
 SYM_FUNC_START(twofish_dec_blk)
@@ -317,5 +317,5 @@ SYM_FUNC_START(twofish_dec_blk)
 	pop	%ebx
 	pop	%ebp
 	mov	$1,	%eax
-	ret
+	RET
 SYM_FUNC_END(twofish_dec_blk)

arch/x86/crypto/twofish-x86_64-asm_64-3way.S

@@ -258,7 +258,7 @@ SYM_FUNC_START(__twofish_enc_blk_3way)
 	popq %rbx;
 	popq %r12;
 	popq %r13;
-	ret;
+	RET;
 
 .L__enc_xor3:
 	outunpack_enc3(xor);
@@ -266,7 +266,7 @@ SYM_FUNC_START(__twofish_enc_blk_3way)
 	popq %rbx;
 	popq %r12;
 	popq %r13;
-	ret;
+	RET;
 SYM_FUNC_END(__twofish_enc_blk_3way)
 
 SYM_FUNC_START(twofish_dec_blk_3way)
@@ -301,5 +301,5 @@ SYM_FUNC_START(twofish_dec_blk_3way)
 	popq %rbx;
 	popq %r12;
 	popq %r13;
-	ret;
+	RET;
 SYM_FUNC_END(twofish_dec_blk_3way)

arch/x86/crypto/twofish-x86_64-asm_64.S

@@ -252,7 +252,7 @@ SYM_FUNC_START(twofish_enc_blk)
 
 	popq	R1
 	movl	$1,%eax
-	ret
+	RET
 SYM_FUNC_END(twofish_enc_blk)
 
 SYM_FUNC_START(twofish_dec_blk)
@@ -304,5 +304,5 @@ SYM_FUNC_START(twofish_dec_blk)
 
 	popq	R1
 	movl	$1,%eax
-	ret
+	RET
 SYM_FUNC_END(twofish_dec_blk)

arch/x86/entry/entry_32.S

@@ -268,19 +268,16 @@
 1:	popl	%ds
 2:	popl	%es
 3:	popl	%fs
-	addl	$(4 + \pop), %esp	/* pop the unused "gs" slot */
+4:	addl	$(4 + \pop), %esp	/* pop the unused "gs" slot */
 	IRET_FRAME
-.pushsection .fixup, "ax"
-4:	movl	$0, (%esp)
-	jmp	1b
-5:	movl	$0, (%esp)
-	jmp	2b
-6:	movl	$0, (%esp)
-	jmp	3b
-.popsection
-	_ASM_EXTABLE(1b, 4b)
-	_ASM_EXTABLE(2b, 5b)
-	_ASM_EXTABLE(3b, 6b)
+
+	/*
+	 * There is no _ASM_EXTABLE_TYPE_REG() for ASM, however since this is
+	 * ASM the registers are known and we can trivially hard-code them.
+	 */
+	_ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_POP_ZERO|EX_REG_DS)
+	_ASM_EXTABLE_TYPE(2b, 3b, EX_TYPE_POP_ZERO|EX_REG_ES)
+	_ASM_EXTABLE_TYPE(3b, 4b, EX_TYPE_POP_ZERO|EX_REG_FS)
 .endm
 
 .macro RESTORE_ALL_NMI cr3_reg:req pop=0
@@ -740,7 +737,7 @@ SYM_FUNC_START(schedule_tail_wrapper)
 	popl	%eax
 
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(schedule_tail_wrapper)
 .popsection
 
@@ -925,10 +922,8 @@ SYM_FUNC_START(entry_SYSENTER_32)
 	sti
 	sysexit
 
-.pushsection .fixup, "ax"
-2:	movl	$0, PT_FS(%esp)
-	jmp	1b
-.popsection
+2:	movl    $0, PT_FS(%esp)
+	jmp     1b
 	_ASM_EXTABLE(1b, 2b)
 
 .Lsysenter_fix_flags:
@@ -996,8 +991,7 @@ restore_all_switch_stack:
 	 */
 	iret
 
-.section .fixup, "ax"
-SYM_CODE_START(asm_iret_error)
+.Lasm_iret_error:
 	pushl	$0				# no error code
 	pushl	$iret_error
 
@@ -1014,9 +1008,8 @@ SYM_CODE_START(asm_iret_error)
 #endif
 
 	jmp	handle_exception
-SYM_CODE_END(asm_iret_error)
-.previous
-	_ASM_EXTABLE(.Lirq_return, asm_iret_error)
+
+	_ASM_EXTABLE(.Lirq_return, .Lasm_iret_error)
 SYM_FUNC_END(entry_INT80_32)
 
 .macro FIXUP_ESPFIX_STACK

arch/x86/entry/entry_64.S

@@ -738,14 +738,10 @@ SYM_FUNC_START(asm_load_gs_index)
 2:	ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
 	swapgs
 	FRAME_END
-	ret
-SYM_FUNC_END(asm_load_gs_index)
-EXPORT_SYMBOL(asm_load_gs_index)
+	RET
 
-	_ASM_EXTABLE(.Lgs_change, .Lbad_gs)
-	.section .fixup, "ax"
 	/* running with kernelgs */
-SYM_CODE_START_LOCAL_NOALIGN(.Lbad_gs)
+.Lbad_gs:
 	swapgs					/* switch back to user gs */
 .macro ZAP_GS
 	/* This can't be a string because the preprocessor needs to see it. */
@@ -756,8 +752,11 @@ SYM_CODE_START_LOCAL_NOALIGN(.Lbad_gs)
 	xorl	%eax, %eax
 	movl	%eax, %gs
 	jmp	2b
-SYM_CODE_END(.Lbad_gs)
-	.previous
+
+	_ASM_EXTABLE(.Lgs_change, .Lbad_gs)
+
+SYM_FUNC_END(asm_load_gs_index)
+EXPORT_SYMBOL(asm_load_gs_index)
 
 #ifdef CONFIG_XEN_PV
 /*
@@ -889,7 +888,7 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 	 * is needed here.
 	 */
 	SAVE_AND_SET_GSBASE scratch_reg=%rax save_reg=%rbx
-	ret
+	RET
 
 .Lparanoid_entry_checkgs:
 	/* EBX = 1 -> kernel GSBASE active, no restore required */
@@ -910,7 +909,7 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 .Lparanoid_kernel_gsbase:
 
 	FENCE_SWAPGS_KERNEL_ENTRY
-	ret
+	RET
 SYM_CODE_END(paranoid_entry)
 
 /*
@@ -989,7 +988,7 @@ SYM_CODE_START_LOCAL(error_entry)
 	movq	%rax, %rsp			/* switch stack */
 	ENCODE_FRAME_POINTER
 	pushq	%r12
-	ret
+	RET
 
 	/*
 	 * There are two places in the kernel that can potentially fault with
@@ -1020,7 +1019,7 @@ SYM_CODE_START_LOCAL(error_entry)
 	 */
 .Lerror_entry_done_lfence:
 	FENCE_SWAPGS_KERNEL_ENTRY
-	ret
+	RET
 
 .Lbstep_iret:
 	/* Fix truncated RIP */

arch/x86/entry/thunk_32.S

@@ -24,7 +24,7 @@ SYM_CODE_START_NOALIGN(\name)
 	popl %edx
 	popl %ecx
 	popl %eax
-	ret
+	RET
 	_ASM_NOKPROBE(\name)
 SYM_CODE_END(\name)
 	.endm

arch/x86/entry/thunk_64.S

@@ -50,7 +50,7 @@ SYM_CODE_START_LOCAL_NOALIGN(__thunk_restore)
 	popq %rsi
 	popq %rdi
 	popq %rbp
-	ret
+	RET
 	_ASM_NOKPROBE(__thunk_restore)
 SYM_CODE_END(__thunk_restore)
 #endif

arch/x86/entry/vdso/vdso-layout.lds.S

@@ -77,7 +77,6 @@ SECTIONS
 
 	.text		: {
 		*(.text*)
-		*(.fixup)
 	}						:text	=0x90909090,
 
 

arch/x86/entry/vdso/vdso32/system_call.S

@@ -78,7 +78,7 @@ SYM_INNER_LABEL(int80_landing_pad, SYM_L_GLOBAL)
 	popl	%ecx
 	CFI_RESTORE		ecx
 	CFI_ADJUST_CFA_OFFSET	-4
-	ret
+	RET
 	CFI_ENDPROC
 
 	.size __kernel_vsyscall,.-__kernel_vsyscall

arch/x86/entry/vdso/vsgx.S

@@ -81,7 +81,7 @@ SYM_FUNC_START(__vdso_sgx_enter_enclave)
 	pop	%rbx
 	leave
 	.cfi_def_cfa		%rsp, 8
-	ret
+	RET
 
 	/* The out-of-line code runs with the pre-leave stack frame. */
 	.cfi_def_cfa		%rbp, 16

arch/x86/entry/vsyscall/vsyscall_emu_64.S

@@ -19,17 +19,17 @@ __vsyscall_page:
 
 	mov $__NR_gettimeofday, %rax
 	syscall
-	ret
+	RET
 
 	.balign 1024, 0xcc
 	mov $__NR_time, %rax
 	syscall
-	ret
+	RET
 
 	.balign 1024, 0xcc
 	mov $__NR_getcpu, %rax
 	syscall
-	ret
+	RET
 
 	.balign 4096, 0xcc
 

arch/x86/events/core.c

@@ -2771,7 +2771,7 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 	struct unwind_state state;
 	unsigned long addr;
 
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+	if (perf_guest_state()) {
 		/* TODO: We don't support guest os callchain now */
 		return;
 	}
@@ -2874,7 +2874,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 	struct stack_frame frame;
 	const struct stack_frame __user *fp;
 
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+	if (perf_guest_state()) {
 		/* TODO: We don't support guest os callchain now */
 		return;
 	}
@@ -2951,18 +2951,19 @@ static unsigned long code_segment_base(struct pt_regs *regs)
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
-		return perf_guest_cbs->get_guest_ip();
+	if (perf_guest_state())
+		return perf_guest_get_ip();
 
 	return regs->ip + code_segment_base(regs);
 }
 
 unsigned long perf_misc_flags(struct pt_regs *regs)
 {
+	unsigned int guest_state = perf_guest_state();
 	int misc = 0;
 
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		if (perf_guest_cbs->is_user_mode())
+	if (guest_state) {
+		if (guest_state & PERF_GUEST_USER)
 			misc |= PERF_RECORD_MISC_GUEST_USER;
 		else
 			misc |= PERF_RECORD_MISC_GUEST_KERNEL;

arch/x86/events/intel/core.c

@@ -2901,10 +2901,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	 */
 	if (__test_and_clear_bit(GLOBAL_STATUS_TRACE_TOPAPMI_BIT, (unsigned long *)&status)) {
 		handled++;
-		if (unlikely(perf_guest_cbs && perf_guest_cbs->is_in_guest() &&
-			perf_guest_cbs->handle_intel_pt_intr))
-			perf_guest_cbs->handle_intel_pt_intr();
-		else
+		if (!perf_guest_handle_intel_pt_intr())
 			intel_pt_interrupt();
 	}
 

arch/x86/include/asm/asm.h

@@ -152,6 +152,33 @@
 
 #else /* ! __ASSEMBLY__ */
 
+# define DEFINE_EXTABLE_TYPE_REG \
+	".macro extable_type_reg type:req reg:req\n"						\
+	".set found, 0\n"									\
+	".set regnr, 0\n"									\
+	".irp rs,rax,rcx,rdx,rbx,rsp,rbp,rsi,rdi,r8,r9,r10,r11,r12,r13,r14,r15\n"		\
+	".ifc \\reg, %%\\rs\n"									\
+	".set found, found+1\n"									\
+	".long \\type + (regnr << 8)\n"								\
+	".endif\n"										\
+	".set regnr, regnr+1\n"									\
+	".endr\n"										\
+	".set regnr, 0\n"									\
+	".irp rs,eax,ecx,edx,ebx,esp,ebp,esi,edi,r8d,r9d,r10d,r11d,r12d,r13d,r14d,r15d\n"	\
+	".ifc \\reg, %%\\rs\n"									\
+	".set found, found+1\n"									\
+	".long \\type + (regnr << 8)\n"								\
+	".endif\n"										\
+	".set regnr, regnr+1\n"									\
+	".endr\n"										\
+	".if (found != 1)\n"									\
+	".error \"extable_type_reg: bad register argument\"\n"					\
+	".endif\n"										\
+	".endm\n"
+
+# define UNDEFINE_EXTABLE_TYPE_REG \
+	".purgem extable_type_reg\n"
+
 # define _ASM_EXTABLE_TYPE(from, to, type)			\
 	" .pushsection \"__ex_table\",\"a\"\n"			\
 	" .balign 4\n"						\
@@ -160,6 +187,16 @@
 	" .long " __stringify(type) " \n"			\
 	" .popsection\n"
 
+# define _ASM_EXTABLE_TYPE_REG(from, to, type, reg)				\
+	" .pushsection \"__ex_table\",\"a\"\n"					\
+	" .balign 4\n"								\
+	" .long (" #from ") - .\n"						\
+	" .long (" #to ") - .\n"						\
+	DEFINE_EXTABLE_TYPE_REG							\
+	"extable_type_reg reg=" __stringify(reg) ", type=" __stringify(type) " \n"\
+	UNDEFINE_EXTABLE_TYPE_REG						\
+	" .popsection\n"
+
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 
 /*

arch/x86/include/asm/extable.h

@@ -21,7 +21,7 @@
  */
 
 struct exception_table_entry {
-	int insn, fixup, type;
+	int insn, fixup, data;
 };
 struct pt_regs;
 
@@ -31,8 +31,8 @@ struct pt_regs;
 	do {							\
 		(a)->fixup = (b)->fixup + (delta);		\
 		(b)->fixup = (tmp).fixup - (delta);		\
-		(a)->type = (b)->type;				\
-		(b)->type = (tmp).type;				\
+		(a)->data = (b)->data;				\
+		(b)->data = (tmp).data;				\
 	} while (0)
 
 extern int fixup_exception(struct pt_regs *regs, int trapnr,

arch/x86/include/asm/extable_fixup_types.h

@@ -2,6 +2,36 @@
 #ifndef _ASM_X86_EXTABLE_FIXUP_TYPES_H
 #define _ASM_X86_EXTABLE_FIXUP_TYPES_H
 
+/*
+ * Our IMM is signed, as such it must live at the top end of the word. Also,
+ * since C99 hex constants are of ambigious type, force cast the mask to 'int'
+ * so that FIELD_GET() will DTRT and sign extend the value when it extracts it.
+ */
+#define EX_DATA_TYPE_MASK		((int)0x000000FF)
+#define EX_DATA_REG_MASK		((int)0x00000F00)
+#define EX_DATA_FLAG_MASK		((int)0x0000F000)
+#define EX_DATA_IMM_MASK		((int)0xFFFF0000)
+
+#define EX_DATA_REG_SHIFT		8
+#define EX_DATA_FLAG_SHIFT		12
+#define EX_DATA_IMM_SHIFT		16
+
+#define EX_DATA_REG(reg)		((reg) << EX_DATA_REG_SHIFT)
+#define EX_DATA_FLAG(flag)		((flag) << EX_DATA_FLAG_SHIFT)
+#define EX_DATA_IMM(imm)		((imm) << EX_DATA_IMM_SHIFT)
+
+/* segment regs */
+#define EX_REG_DS			EX_DATA_REG(8)
+#define EX_REG_ES			EX_DATA_REG(9)
+#define EX_REG_FS			EX_DATA_REG(10)
+#define EX_REG_GS			EX_DATA_REG(11)
+
+/* flags */
+#define EX_FLAG_CLEAR_AX		EX_DATA_FLAG(1)
+#define EX_FLAG_CLEAR_DX		EX_DATA_FLAG(2)
+#define EX_FLAG_CLEAR_AX_DX		EX_DATA_FLAG(3)
+
+/* types */
 #define	EX_TYPE_NONE			 0
 #define	EX_TYPE_DEFAULT			 1
 #define	EX_TYPE_FAULT			 2
@@ -9,14 +39,29 @@
 #define	EX_TYPE_COPY			 4
 #define	EX_TYPE_CLEAR_FS		 5
 #define	EX_TYPE_FPU_RESTORE		 6
-#define	EX_TYPE_WRMSR			 7
-#define	EX_TYPE_RDMSR			 8
-#define	EX_TYPE_BPF			 9
+#define	EX_TYPE_BPF			 7
+#define	EX_TYPE_WRMSR			 8
+#define	EX_TYPE_RDMSR			 9
+#define	EX_TYPE_WRMSR_SAFE		10 /* reg := -EIO */
+#define	EX_TYPE_RDMSR_SAFE		11 /* reg := -EIO */
+#define	EX_TYPE_WRMSR_IN_MCE		12
+#define	EX_TYPE_RDMSR_IN_MCE		13
+#define	EX_TYPE_DEFAULT_MCE_SAFE	14
+#define	EX_TYPE_FAULT_MCE_SAFE		15
 
-#define	EX_TYPE_WRMSR_IN_MCE		10
-#define	EX_TYPE_RDMSR_IN_MCE		11
+#define	EX_TYPE_POP_REG			16 /* sp += sizeof(long) */
+#define EX_TYPE_POP_ZERO		(EX_TYPE_POP_REG | EX_DATA_IMM(0))
 
-#define	EX_TYPE_DEFAULT_MCE_SAFE	12
-#define	EX_TYPE_FAULT_MCE_SAFE		13
+#define	EX_TYPE_IMM_REG			17 /* reg := (long)imm */
+#define	EX_TYPE_EFAULT_REG		(EX_TYPE_IMM_REG | EX_DATA_IMM(-EFAULT))
+#define	EX_TYPE_ZERO_REG		(EX_TYPE_IMM_REG | EX_DATA_IMM(0))
+#define	EX_TYPE_ONE_REG			(EX_TYPE_IMM_REG | EX_DATA_IMM(1))
+
+#define	EX_TYPE_FAULT_SGX		18
+
+#define	EX_TYPE_UCOPY_LEN		19 /* cx := reg + imm*cx */
+#define	EX_TYPE_UCOPY_LEN1		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(1))
+#define	EX_TYPE_UCOPY_LEN4		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(4))
+#define	EX_TYPE_UCOPY_LEN8		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(8))
 
 #endif

arch/x86/include/asm/futex.h

@@ -17,13 +17,9 @@ do {								\
 	int oldval = 0, ret;					\
 	asm volatile("1:\t" insn "\n"				\
 		     "2:\n"					\
-		     "\t.section .fixup,\"ax\"\n"		\
-		     "3:\tmov\t%3, %1\n"			\
-		     "\tjmp\t2b\n"				\
-		     "\t.previous\n"				\
-		     _ASM_EXTABLE_UA(1b, 3b)			\
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %1) \
 		     : "=r" (oldval), "=r" (ret), "+m" (*uaddr)	\
-		     : "i" (-EFAULT), "0" (oparg), "1" (0));	\
+		     : "0" (oparg), "1" (0));	\
 	if (ret)						\
 		goto label;					\
 	*oval = oldval;						\
@@ -39,15 +35,11 @@ do {								\
 		     "3:\t" LOCK_PREFIX "cmpxchgl %3, %2\n"	\
 		     "\tjnz\t2b\n"				\
 		     "4:\n"					\
-		     "\t.section .fixup,\"ax\"\n"		\
-		     "5:\tmov\t%5, %1\n"			\
-		     "\tjmp\t4b\n"				\
-		     "\t.previous\n"				\
-		     _ASM_EXTABLE_UA(1b, 5b)			\
-		     _ASM_EXTABLE_UA(3b, 5b)			\
+		     _ASM_EXTABLE_TYPE_REG(1b, 4b, EX_TYPE_EFAULT_REG, %1) \
+		     _ASM_EXTABLE_TYPE_REG(3b, 4b, EX_TYPE_EFAULT_REG, %1) \
 		     : "=&a" (oldval), "=&r" (ret),		\
 		       "+m" (*uaddr), "=&r" (tem)		\
-		     : "r" (oparg), "i" (-EFAULT), "1" (0));	\
+		     : "r" (oparg), "1" (0));			\
 	if (ret)						\
 		goto label;					\
 	*oval = oldval;						\
@@ -95,15 +87,11 @@ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!user_access_begin(uaddr, sizeof(u32)))
 		return -EFAULT;
 	asm volatile("\n"
-		"1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"
+		"1:\t" LOCK_PREFIX "cmpxchgl %3, %2\n"
 		"2:\n"
-		"\t.section .fixup, \"ax\"\n"
-		"3:\tmov     %3, %0\n"
-		"\tjmp     2b\n"
-		"\t.previous\n"
-		_ASM_EXTABLE_UA(1b, 3b)
+		_ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %0) \
 		: "+r" (ret), "=a" (oldval), "+m" (*uaddr)
-		: "i" (-EFAULT), "r" (newval), "1" (oldval)
+		: "r" (newval), "1" (oldval)
 		: "memory"
 	);
 	user_access_end();

arch/x86/include/asm/insn-eval.h

@@ -15,6 +15,8 @@
 #define INSN_CODE_SEG_OPND_SZ(params) (params & 0xf)
 #define INSN_CODE_SEG_PARAMS(oper_sz, addr_sz) (oper_sz | (addr_sz << 4))
 
+int pt_regs_offset(struct pt_regs *regs, int regno);
+
 bool insn_has_rep_prefix(struct insn *insn);
 void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs);
 int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs);

arch/x86/include/asm/kvm_host.h

@@ -774,6 +774,7 @@ struct kvm_vcpu_arch {
 	unsigned nmi_pending; /* NMI queued after currently running handler */
 	bool nmi_injected;    /* Trying to inject an NMI this entry */
 	bool smi_pending;    /* SMI queued after currently running handler */
+	u8 handling_intr_from_guest;
 
 	struct kvm_mtrr mtrr_state;
 	u64 pat;
@@ -1519,6 +1520,7 @@ struct kvm_x86_init_ops {
 	int (*disabled_by_bios)(void);
 	int (*check_processor_compatibility)(void);
 	int (*hardware_setup)(void);
+	unsigned int (*handle_intel_pt_intr)(void);
 
 	struct kvm_x86_ops *runtime_ops;
 };
@@ -1568,6 +1570,9 @@ static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
 		return -ENOTSUPP;
 }
 
+#define kvm_arch_pmi_in_guest(vcpu) \
+	((vcpu) && (vcpu)->arch.handling_intr_from_guest)
+
 int kvm_mmu_module_init(void);
 void kvm_mmu_module_exit(void);
 
@@ -1897,8 +1902,6 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu);
 int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
 void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);
 
-int kvm_is_in_guest(void);
-
 void __user *__x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
 				     u32 size);
 bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);

arch/x86/include/asm/linkage.h

@@ -18,6 +18,20 @@
 #define __ALIGN_STR	__stringify(__ALIGN)
 #endif
 
+#ifdef CONFIG_SLS
+#define RET	ret; int3
+#else
+#define RET	ret
+#endif
+
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_SLS
+#define ASM_RET	"ret; int3\n\t"
+#else
+#define ASM_RET	"ret\n\t"
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_LINKAGE_H */

arch/x86/include/asm/mmx.h

@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_MMX_H
-#define _ASM_X86_MMX_H
-
-/*
- *	MMX 3Dnow! helper operations
- */
-
-#include <linux/types.h>
-
-extern void *_mmx_memcpy(void *to, const void *from, size_t size);
-extern void mmx_clear_page(void *page);
-extern void mmx_copy_page(void *to, void *from);
-
-#endif /* _ASM_X86_MMX_H */

arch/x86/include/asm/msr.h

@@ -137,17 +137,11 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 {
 	DECLARE_ARGS(val, low, high);
 
-	asm volatile("2: rdmsr ; xor %[err],%[err]\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3: mov %[fault],%[err]\n\t"
-		     "xorl %%eax, %%eax\n\t"
-		     "xorl %%edx, %%edx\n\t"
-		     "jmp 1b\n\t"
-		     ".previous\n\t"
-		     _ASM_EXTABLE(2b, 3b)
+	asm volatile("1: rdmsr ; xor %[err],%[err]\n"
+		     "2:\n\t"
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_RDMSR_SAFE, %[err])
 		     : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
-		     : "c" (msr), [fault] "i" (-EIO));
+		     : "c" (msr));
 	if (tracepoint_enabled(read_msr))
 		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err);
 	return EAX_EDX_VAL(val, low, high);
@@ -169,15 +163,11 @@ native_write_msr_safe(unsigned int msr, u32 low, u32 high)
 {
 	int err;
 
-	asm volatile("2: wrmsr ; xor %[err],%[err]\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3:  mov %[fault],%[err] ; jmp 1b\n\t"
-		     ".previous\n\t"
-		     _ASM_EXTABLE(2b, 3b)
+	asm volatile("1: wrmsr ; xor %[err],%[err]\n"
+		     "2:\n\t"
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_WRMSR_SAFE, %[err])
 		     : [err] "=a" (err)
-		     : "c" (msr), "0" (low), "d" (high),
-		       [fault] "i" (-EIO)
+		     : "c" (msr), "0" (low), "d" (high)
 		     : "memory");
 	if (tracepoint_enabled(write_msr))
 		do_trace_write_msr(msr, ((u64)high << 32 | low), err);

arch/x86/include/asm/page_32.h

@@ -19,19 +19,6 @@ extern unsigned long __phys_addr(unsigned long);
 #define pfn_valid(pfn)		((pfn) < max_mapnr)
 #endif /* CONFIG_FLATMEM */
 
-#ifdef CONFIG_X86_USE_3DNOW
-#include <asm/mmx.h>
-
-static inline void clear_page(void *page)
-{
-	mmx_clear_page(page);
-}
-
-static inline void copy_page(void *to, void *from)
-{
-	mmx_copy_page(to, from);
-}
-#else  /* !CONFIG_X86_USE_3DNOW */
 #include <linux/string.h>
 
 static inline void clear_page(void *page)
@@ -43,7 +30,6 @@ static inline void copy_page(void *to, void *from)
 {
 	memcpy(to, from, PAGE_SIZE);
 }
-#endif	/* CONFIG_X86_USE_3DNOW */
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PAGE_32_H */

arch/x86/include/asm/paravirt.h

@@ -671,7 +671,7 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 	    "call " #func ";"						\
 	    PV_RESTORE_ALL_CALLER_REGS					\
 	    FRAME_END							\
-	    "ret;"							\
+	    ASM_RET							\
 	    ".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";"	\
 	    ".popsection")
 

arch/x86/include/asm/qspinlock_paravirt.h

@@ -48,7 +48,7 @@ asm    (".pushsection .text;"
 	"jne   .slowpath;"
 	"pop   %rdx;"
 	FRAME_END
-	"ret;"
+	ASM_RET
 	".slowpath: "
 	"push   %rsi;"
 	"movzbl %al,%esi;"
@@ -56,7 +56,7 @@ asm    (".pushsection .text;"
 	"pop    %rsi;"
 	"pop    %rdx;"
 	FRAME_END
-	"ret;"
+	ASM_RET
 	".size " PV_UNLOCK ", .-" PV_UNLOCK ";"
 	".popsection");
 

arch/x86/include/asm/required-features.h

@@ -35,11 +35,7 @@
 # define NEED_CMOV	0
 #endif
 
-#ifdef CONFIG_X86_USE_3DNOW
-# define NEED_3DNOW	(1<<(X86_FEATURE_3DNOW & 31))
-#else
 # define NEED_3DNOW	0
-#endif
 
 #if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
 # define NEED_NOPL	(1<<(X86_FEATURE_NOPL & 31))

arch/x86/include/asm/segment.h

@@ -307,14 +307,7 @@ do {									\
 									\
 	asm volatile("						\n"	\
 		     "1:	movl %k0,%%" #seg "		\n"	\
-									\
-		     ".section .fixup,\"ax\"			\n"	\
-		     "2:	xorl %k0,%k0			\n"	\
-		     "		jmp 1b				\n"	\
-		     ".previous					\n"	\
-									\
-		     _ASM_EXTABLE(1b, 2b)				\
-									\
+		     _ASM_EXTABLE_TYPE_REG(1b, 1b, EX_TYPE_ZERO_REG, %k0)\
 		     : "+r" (__val) : : "memory");			\
 } while (0)
 

arch/x86/include/asm/sgx.h

@@ -45,6 +45,24 @@ enum sgx_encls_function {
 	EMODT	= 0x0F,
 };
 
+/**
+ * SGX_ENCLS_FAULT_FLAG - flag signifying an ENCLS return code is a trapnr
+ *
+ * ENCLS has its own (positive value) error codes and also generates
+ * ENCLS specific #GP and #PF faults.  And the ENCLS values get munged
+ * with system error codes as everything percolates back up the stack.
+ * Unfortunately (for us), we need to precisely identify each unique
+ * error code, e.g. the action taken if EWB fails varies based on the
+ * type of fault and on the exact SGX error code, i.e. we can't simply
+ * convert all faults to -EFAULT.
+ *
+ * To make all three error types coexist, we set bit 30 to identify an
+ * ENCLS fault.  Bit 31 (technically bits N:31) is used to differentiate
+ * between positive (faults and SGX error codes) and negative (system
+ * error codes) values.
+ */
+#define SGX_ENCLS_FAULT_FLAG 0x40000000
+
 /**
  * enum sgx_return_code - The return code type for ENCLS, ENCLU and ENCLV
  * %SGX_NOT_TRACKED:		Previous ETRACK's shootdown sequence has not

arch/x86/include/asm/static_call.h

@@ -36,7 +36,7 @@
 	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)")
 
 #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
-	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; nop; nop; nop; nop")
+	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop")
 
 
 #define ARCH_ADD_TRAMP_KEY(name)					\

arch/x86/include/asm/string_32.h

@@ -146,42 +146,9 @@ static __always_inline void *__constant_memcpy(void *to, const void *from,
 extern void *memcpy(void *, const void *, size_t);
 
 #ifndef CONFIG_FORTIFY_SOURCE
-#ifdef CONFIG_X86_USE_3DNOW
-
-#include <asm/mmx.h>
-
-/*
- *	This CPU favours 3DNow strongly (eg AMD Athlon)
- */
-
-static inline void *__constant_memcpy3d(void *to, const void *from, size_t len)
-{
-	if (len < 512)
-		return __constant_memcpy(to, from, len);
-	return _mmx_memcpy(to, from, len);
-}
-
-static inline void *__memcpy3d(void *to, const void *from, size_t len)
-{
-	if (len < 512)
-		return __memcpy(to, from, len);
-	return _mmx_memcpy(to, from, len);
-}
-
-#define memcpy(t, f, n)				\
-	(__builtin_constant_p((n))		\
-	 ? __constant_memcpy3d((t), (f), (n))	\
-	 : __memcpy3d((t), (f), (n)))
-
-#else
-
-/*
- *	No 3D Now!
- */
 
 #define memcpy(t, f, n) __builtin_memcpy(t, f, n)
 
-#endif
 #endif /* !CONFIG_FORTIFY_SOURCE */
 
 #define __HAVE_ARCH_MEMMOVE

arch/x86/include/asm/uaccess.h

@@ -352,24 +352,22 @@ do {									\
 		     "1:	movl %[lowbits],%%eax\n"		\
 		     "2:	movl %[highbits],%%edx\n"		\
 		     "3:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "4:	mov %[efault],%[errout]\n"		\
-		     "	xorl %%eax,%%eax\n"				\
-		     "	xorl %%edx,%%edx\n"				\
-		     "	jmp 3b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE_UA(1b, 4b)				\
-		     _ASM_EXTABLE_UA(2b, 4b)				\
+		     _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG |	\
+					   EX_FLAG_CLEAR_AX_DX,		\
+					   %[errout])			\
+		     _ASM_EXTABLE_TYPE_REG(2b, 3b, EX_TYPE_EFAULT_REG |	\
+					   EX_FLAG_CLEAR_AX_DX,		\
+					   %[errout])			\
 		     : [errout] "=r" (retval),				\
 		       [output] "=&A"(x)				\
 		     : [lowbits] "m" (__m(__ptr)),			\
 		       [highbits] "m" __m(((u32 __user *)(__ptr)) + 1),	\
-		       [efault] "i" (-EFAULT), "0" (retval));		\
+		       "0" (retval));					\
 })
 
 #else
 #define __get_user_asm_u64(x, ptr, retval) \
-	 __get_user_asm(x, ptr, retval, "q", "=r")
+	 __get_user_asm(x, ptr, retval, "q")
 #endif
 
 #define __get_user_size(x, ptr, size, retval)				\
@@ -380,14 +378,14 @@ do {									\
 	__chk_user_ptr(ptr);						\
 	switch (size) {							\
 	case 1:								\
-		__get_user_asm(x_u8__, ptr, retval, "b", "=q");		\
+		__get_user_asm(x_u8__, ptr, retval, "b");		\
 		(x) = x_u8__;						\
 		break;							\
 	case 2:								\
-		__get_user_asm(x, ptr, retval, "w", "=r");		\
+		__get_user_asm(x, ptr, retval, "w");			\
 		break;							\
 	case 4:								\
-		__get_user_asm(x, ptr, retval, "l", "=r");		\
+		__get_user_asm(x, ptr, retval, "l");			\
 		break;							\
 	case 8:								\
 		__get_user_asm_u64(x, ptr, retval);			\
@@ -397,20 +395,17 @@ do {									\
 	}								\
 } while (0)
 
-#define __get_user_asm(x, addr, err, itype, ltype)			\
+#define __get_user_asm(x, addr, err, itype)				\
 	asm volatile("\n"						\
 		     "1:	mov"itype" %[umem],%[output]\n"		\
 		     "2:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:	mov %[efault],%[errout]\n"		\
-		     "	xorl %k[output],%k[output]\n"			\
-		     "	jmp 2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE_UA(1b, 3b)				\
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG | \
+					   EX_FLAG_CLEAR_AX,		\
+					   %[errout])			\
 		     : [errout] "=r" (err),				\
-		       [output] ltype(x)				\
+		       [output] "=a" (x)				\
 		     : [umem] "m" (__m(addr)),				\
-		       [efault] "i" (-EFAULT), "0" (err))
+		       "0" (err))
 
 #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT
 

arch/x86/include/asm/word-at-a-time.h

@@ -77,30 +77,58 @@ static inline unsigned long find_zero(unsigned long mask)
  * and the next page not being mapped, take the exception and
  * return zeroes in the non-existing part.
  */
+#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
+
 static inline unsigned long load_unaligned_zeropad(const void *addr)
 {
-	unsigned long ret, dummy;
+	unsigned long offset, data;
+	unsigned long ret;
+
+	asm_volatile_goto(
+		"1:	mov %[mem], %[ret]\n"
+
+		_ASM_EXTABLE(1b, %l[do_exception])
+
+		: [ret] "=r" (ret)
+		: [mem] "m" (*(unsigned long *)addr)
+		: : do_exception);
+
+	return ret;
+
+do_exception:
+	offset = (unsigned long)addr & (sizeof(long) - 1);
+	addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
+	data = *(unsigned long *)addr;
+	ret = data >> offset * 8;
 
-	asm(
-		"1:\tmov %2,%0\n"
-		"2:\n"
-		".section .fixup,\"ax\"\n"
-		"3:\t"
-		"lea %2,%1\n\t"
-		"and %3,%1\n\t"
-		"mov (%1),%0\n\t"
-		"leal %2,%%ecx\n\t"
-		"andl %4,%%ecx\n\t"
-		"shll $3,%%ecx\n\t"
-		"shr %%cl,%0\n\t"
-		"jmp 2b\n"
-		".previous\n"
-		_ASM_EXTABLE(1b, 3b)
-		:"=&r" (ret),"=&c" (dummy)
-		:"m" (*(unsigned long *)addr),
-		 "i" (-sizeof(unsigned long)),
-		 "i" (sizeof(unsigned long)-1));
 	return ret;
 }
 
+#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
+
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+	unsigned long offset, data;
+	unsigned long ret, err = 0;
+
+	asm(	"1:	mov %[mem], %[ret]\n"
+		"2:\n"
+
+		_ASM_EXTABLE_FAULT(1b, 2b)
+
+		: [ret] "=&r" (ret), "+a" (err)
+		: [mem] "m" (*(unsigned long *)addr));
+
+	if (unlikely(err)) {
+		offset = (unsigned long)addr & (sizeof(long) - 1);
+		addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
+		data = *(unsigned long *)addr;
+		ret = data >> offset * 8;
+	}
+
+	return ret;
+}
+
+#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
+
 #endif /* _ASM_WORD_AT_A_TIME_H */

arch/x86/include/asm/xen/page.h

@@ -96,11 +96,7 @@ static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val)
 
 	asm volatile("1: mov %[val], %[ptr]\n"
 		     "2:\n"
-		     ".section .fixup, \"ax\"\n"
-		     "3: sub $1, %[ret]\n"
-		     "   jmp 2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %[ret])
 		     : [ret] "+r" (ret), [ptr] "=m" (*addr)
 		     : [val] "r" (val));
 
@@ -110,16 +106,12 @@ static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val)
 static inline int xen_safe_read_ulong(const unsigned long *addr,
 				      unsigned long *val)
 {
-	int ret = 0;
 	unsigned long rval = ~0ul;
+	int ret = 0;
 
 	asm volatile("1: mov %[ptr], %[rval]\n"
 		     "2:\n"
-		     ".section .fixup, \"ax\"\n"
-		     "3: sub $1, %[ret]\n"
-		     "   jmp 2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %[ret])
 		     : [ret] "+r" (ret), [rval] "+r" (rval)
 		     : [ptr] "m" (*addr));
 	*val = rval;

arch/x86/kernel/acpi/wakeup_32.S

@@ -60,7 +60,7 @@ save_registers:
 	popl	saved_context_eflags
 
 	movl	$ret_point, saved_eip
-	ret
+	RET
 
 
 restore_registers:
@@ -70,7 +70,7 @@ restore_registers:
 	movl	saved_context_edi, %edi
 	pushl	saved_context_eflags
 	popfl
-	ret
+	RET
 
 SYM_CODE_START(do_suspend_lowlevel)
 	call	save_processor_state
@@ -86,7 +86,7 @@ SYM_CODE_START(do_suspend_lowlevel)
 ret_point:
 	call	restore_registers
 	call	restore_processor_state
-	ret
+	RET
 SYM_CODE_END(do_suspend_lowlevel)
 
 .data

arch/x86/kernel/alternative.c

@@ -714,7 +714,7 @@ asm (
 "	.type		int3_magic, @function\n"
 "int3_magic:\n"
 "	movl	$1, (%" _ASM_ARG1 ")\n"
-"	ret\n"
+	ASM_RET
 "	.size		int3_magic, .-int3_magic\n"
 "	.popsection\n"
 );
@@ -1113,10 +1113,13 @@ void text_poke_sync(void)
 }
 
 struct text_poke_loc {
-	s32 rel_addr; /* addr := _stext + rel_addr */
-	s32 rel32;
+	/* addr := _stext + rel_addr */
+	s32 rel_addr;
+	s32 disp;
+	u8 len;
 	u8 opcode;
 	const u8 text[POKE_MAX_OPCODE_SIZE];
+	/* see text_poke_bp_batch() */
 	u8 old;
 };
 
@@ -1131,7 +1134,8 @@ static struct bp_patching_desc *bp_desc;
 static __always_inline
 struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp)
 {
-	struct bp_patching_desc *desc = __READ_ONCE(*descp); /* rcu_dereference */
+	/* rcu_dereference */
+	struct bp_patching_desc *desc = __READ_ONCE(*descp);
 
 	if (!desc || !arch_atomic_inc_not_zero(&desc->refs))
 		return NULL;
@@ -1165,7 +1169,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 {
 	struct bp_patching_desc *desc;
 	struct text_poke_loc *tp;
-	int len, ret = 0;
+	int ret = 0;
 	void *ip;
 
 	if (user_mode(regs))
@@ -1205,8 +1209,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 			goto out_put;
 	}
 
-	len = text_opcode_size(tp->opcode);
-	ip += len;
+	ip += tp->len;
 
 	switch (tp->opcode) {
 	case INT3_INSN_OPCODE:
@@ -1221,12 +1224,12 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 		break;
 
 	case CALL_INSN_OPCODE:
-		int3_emulate_call(regs, (long)ip + tp->rel32);
+		int3_emulate_call(regs, (long)ip + tp->disp);
 		break;
 
 	case JMP32_INSN_OPCODE:
 	case JMP8_INSN_OPCODE:
-		int3_emulate_jmp(regs, (long)ip + tp->rel32);
+		int3_emulate_jmp(regs, (long)ip + tp->disp);
 		break;
 
 	default:
@@ -1301,7 +1304,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	 */
 	for (do_sync = 0, i = 0; i < nr_entries; i++) {
 		u8 old[POKE_MAX_OPCODE_SIZE] = { tp[i].old, };
-		int len = text_opcode_size(tp[i].opcode);
+		int len = tp[i].len;
 
 		if (len - INT3_INSN_SIZE > 0) {
 			memcpy(old + INT3_INSN_SIZE,
@@ -1378,20 +1381,36 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 			       const void *opcode, size_t len, const void *emulate)
 {
 	struct insn insn;
-	int ret;
+	int ret, i;
 
 	memcpy((void *)tp->text, opcode, len);
 	if (!emulate)
 		emulate = opcode;
 
 	ret = insn_decode_kernel(&insn, emulate);
-
 	BUG_ON(ret < 0);
-	BUG_ON(len != insn.length);
 
 	tp->rel_addr = addr - (void *)_stext;
+	tp->len = len;
 	tp->opcode = insn.opcode.bytes[0];
 
+	switch (tp->opcode) {
+	case RET_INSN_OPCODE:
+	case JMP32_INSN_OPCODE:
+	case JMP8_INSN_OPCODE:
+		/*
+		 * Control flow instructions without implied execution of the
+		 * next instruction can be padded with INT3.
+		 */
+		for (i = insn.length; i < len; i++)
+			BUG_ON(tp->text[i] != INT3_INSN_OPCODE);
+		break;
+
+	default:
+		BUG_ON(len != insn.length);
+	};
+
+
 	switch (tp->opcode) {
 	case INT3_INSN_OPCODE:
 	case RET_INSN_OPCODE:
@@ -1400,7 +1419,7 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 	case CALL_INSN_OPCODE:
 	case JMP32_INSN_OPCODE:
 	case JMP8_INSN_OPCODE:
-		tp->rel32 = insn.immediate.value;
+		tp->disp = insn.immediate.value;
 		break;
 
 	default: /* assume NOP */
@@ -1408,13 +1427,13 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 		case 2: /* NOP2 -- emulate as JMP8+0 */
 			BUG_ON(memcmp(emulate, x86_nops[len], len));
 			tp->opcode = JMP8_INSN_OPCODE;
-			tp->rel32 = 0;
+			tp->disp = 0;
 			break;
 
 		case 5: /* NOP5 -- emulate as JMP32+0 */
 			BUG_ON(memcmp(emulate, x86_nops[len], len));
 			tp->opcode = JMP32_INSN_OPCODE;
-			tp->rel32 = 0;
+			tp->disp = 0;
 			break;
 
 		default: /* unknown instruction */

arch/x86/kernel/cpu/sgx/encls.h

@@ -11,26 +11,8 @@
 #include <asm/traps.h>
 #include "sgx.h"
 
-/**
- * ENCLS_FAULT_FLAG - flag signifying an ENCLS return code is a trapnr
- *
- * ENCLS has its own (positive value) error codes and also generates
- * ENCLS specific #GP and #PF faults.  And the ENCLS values get munged
- * with system error codes as everything percolates back up the stack.
- * Unfortunately (for us), we need to precisely identify each unique
- * error code, e.g. the action taken if EWB fails varies based on the
- * type of fault and on the exact SGX error code, i.e. we can't simply
- * convert all faults to -EFAULT.
- *
- * To make all three error types coexist, we set bit 30 to identify an
- * ENCLS fault.  Bit 31 (technically bits N:31) is used to differentiate
- * between positive (faults and SGX error codes) and negative (system
- * error codes) values.
- */
-#define ENCLS_FAULT_FLAG 0x40000000
-
 /* Retrieve the encoded trapnr from the specified return code. */
-#define ENCLS_TRAPNR(r) ((r) & ~ENCLS_FAULT_FLAG)
+#define ENCLS_TRAPNR(r) ((r) & ~SGX_ENCLS_FAULT_FLAG)
 
 /* Issue a WARN() about an ENCLS function. */
 #define ENCLS_WARN(r, name) {						  \
@@ -50,7 +32,7 @@
  */
 static inline bool encls_faulted(int ret)
 {
-	return ret & ENCLS_FAULT_FLAG;
+	return ret & SGX_ENCLS_FAULT_FLAG;
 }
 
 /**
@@ -88,11 +70,7 @@ static inline bool encls_failed(int ret)
 	asm volatile(						\
 	"1: .byte 0x0f, 0x01, 0xcf;\n\t"			\
 	"2:\n"							\
-	".section .fixup,\"ax\"\n"				\
-	"3: orl $"__stringify(ENCLS_FAULT_FLAG)",%%eax\n"	\
-	"   jmp 2b\n"						\
-	".previous\n"						\
-	_ASM_EXTABLE_FAULT(1b, 3b)				\
+	_ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_SGX)		\
 	: "=a"(ret)						\
 	: "a"(rax), inputs					\
 	: "memory", "cc");					\
@@ -127,7 +105,7 @@ static inline bool encls_failed(int ret)
  *
  * Return:
  *   0 on success,
- *   trapnr with ENCLS_FAULT_FLAG set on fault
+ *   trapnr with SGX_ENCLS_FAULT_FLAG set on fault
  */
 #define __encls_N(rax, rbx_out, inputs...)			\
 	({							\
@@ -136,11 +114,7 @@ static inline bool encls_failed(int ret)
 	"1: .byte 0x0f, 0x01, 0xcf;\n\t"			\
 	"   xor %%eax,%%eax;\n"					\
 	"2:\n"							\
-	".section .fixup,\"ax\"\n"				\
-	"3: orl $"__stringify(ENCLS_FAULT_FLAG)",%%eax\n"	\
-	"   jmp 2b\n"						\
-	".previous\n"						\
-	_ASM_EXTABLE_FAULT(1b, 3b)				\
+	_ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_SGX)		\
 	: "=a"(ret), "=b"(rbx_out)				\
 	: "a"(rax), inputs					\
 	: "memory");						\

arch/x86/kernel/fpu/legacy.h

@@ -35,11 +35,7 @@ static inline void ldmxcsr(u32 mxcsr)
 	int err;							\
 	asm volatile("1:" #insn "\n\t"					\
 		     "2:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:  movl $-1,%[err]\n"				\
-		     "    jmp  2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %[err]) \
 		     : [err] "=r" (err), output				\
 		     : "0"(0), input);					\
 	err;								\

arch/x86/kernel/fpu/xstate.h

@@ -108,11 +108,7 @@ static inline u64 xfeatures_mask_independent(void)
 		     "\n"						\
 		     "xor %[err], %[err]\n"				\
 		     "3:\n"						\
-		     ".pushsection .fixup,\"ax\"\n"			\
-		     "4: movl $-2, %[err]\n"				\
-		     "jmp 3b\n"						\
-		     ".popsection\n"					\
-		     _ASM_EXTABLE(661b, 4b)				\
+		     _ASM_EXTABLE_TYPE_REG(661b, 3b, EX_TYPE_EFAULT_REG, %[err]) \
 		     : [err] "=r" (err)					\
 		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
 		     : "memory")

arch/x86/kernel/ftrace.c

@@ -303,7 +303,7 @@ union ftrace_op_code_union {
 	} __attribute__((packed));
 };
 
-#define RET_SIZE		1
+#define RET_SIZE		1 + IS_ENABLED(CONFIG_SLS)
 
 static unsigned long
 create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)

arch/x86/kernel/ftrace_32.S

@@ -19,7 +19,7 @@
 #endif
 
 SYM_FUNC_START(__fentry__)
-	ret
+	RET
 SYM_FUNC_END(__fentry__)
 EXPORT_SYMBOL(__fentry__)
 
@@ -84,7 +84,7 @@ ftrace_graph_call:
 
 /* This is weak to keep gas from relaxing the jumps */
 SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK)
-	ret
+	RET
 SYM_CODE_END(ftrace_caller)
 
 SYM_CODE_START(ftrace_regs_caller)
@@ -177,7 +177,7 @@ SYM_CODE_START(ftrace_graph_caller)
 	popl	%edx
 	popl	%ecx
 	popl	%eax
-	ret
+	RET
 SYM_CODE_END(ftrace_graph_caller)
 
 .globl return_to_handler

arch/x86/kernel/ftrace_64.S

@@ -132,7 +132,7 @@
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 SYM_FUNC_START(__fentry__)
-	retq
+	RET
 SYM_FUNC_END(__fentry__)
 EXPORT_SYMBOL(__fentry__)
 
@@ -176,11 +176,11 @@ SYM_FUNC_END(ftrace_caller);
 SYM_FUNC_START(ftrace_epilogue)
 /*
  * This is weak to keep gas from relaxing the jumps.
- * It is also used to copy the retq for trampolines.
+ * It is also used to copy the RET for trampolines.
  */
 SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK)
 	UNWIND_HINT_FUNC
-	retq
+	RET
 SYM_FUNC_END(ftrace_epilogue)
 
 SYM_FUNC_START(ftrace_regs_caller)
@@ -284,7 +284,7 @@ SYM_FUNC_START(__fentry__)
 	jnz trace
 
 SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL)
-	retq
+	RET
 
 trace:
 	/* save_mcount_regs fills in first two parameters */