Merging upstream version 5.10.218.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

25 files changed, 81 insertions, 125 deletions

diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi
index ca8e78487..5a7f9a806 100644
--- a/arch/arm64/boot/dts/qcom/msm8998.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi
@@ -949,10 +949,10 @@
 			interrupts = <GIC_SPI 405 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "msi";
 			interrupt-map-mask = <0 0 0 0x7>;
-			interrupt-map =	<0 0 0 1 &intc 0 135 IRQ_TYPE_LEVEL_HIGH>,
-					<0 0 0 2 &intc 0 136 IRQ_TYPE_LEVEL_HIGH>,
-					<0 0 0 3 &intc 0 138 IRQ_TYPE_LEVEL_HIGH>,
-					<0 0 0 4 &intc 0 139 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map =	<0 0 0 1 &intc 0 0 135 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 2 &intc 0 0 136 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 3 &intc 0 0 138 IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 4 &intc 0 0 139 IRQ_TYPE_LEVEL_HIGH>;
 
 			clocks = <&gcc GCC_PCIE_0_PIPE_CLK>,
 				 <&gcc GCC_PCIE_0_MSTR_AXI_CLK>,
diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi
index e3c6b0586..b00f6d8bc 100644
--- a/arch/arm64/boot/dts/qcom/sdm845.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi
@@ -1824,10 +1824,10 @@
 			interrupt-names = "msi";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
-			interrupt-map = <0 0 0 1 &intc 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
-					<0 0 0 2 &intc 0 150 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
-					<0 0 0 3 &intc 0 151 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
-					<0 0 0 4 &intc 0 152 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
+			interrupt-map = <0 0 0 1 &intc 0 0 0 149 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
+					<0 0 0 2 &intc 0 0 0 150 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
+					<0 0 0 3 &intc 0 0 0 151 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
+					<0 0 0 4 &intc 0 0 0 152 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
 
 			clocks = <&gcc GCC_PCIE_0_PIPE_CLK>,
 				 <&gcc GCC_PCIE_0_AUX_CLK>,
@@ -1928,10 +1928,10 @@
 			interrupt-names = "msi";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
-			interrupt-map = <0 0 0 1 &intc 0 434 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
-					<0 0 0 2 &intc 0 435 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
-					<0 0 0 3 &intc 0 438 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
-					<0 0 0 4 &intc 0 439 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
+			interrupt-map = <0 0 0 1 &intc 0 0 0 434 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
+					<0 0 0 2 &intc 0 0 0 435 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
+					<0 0 0 3 &intc 0 0 0 438 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
+					<0 0 0 4 &intc 0 0 0 439 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
 
 			clocks = <&gcc GCC_PCIE_1_PIPE_CLK>,
 				 <&gcc GCC_PCIE_1_AUX_CLK>,
diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c
index 7740995de..e80b638b7 100644
--- a/arch/arm64/kvm/vgic/vgic-kvm-device.c
+++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c
@@ -284,16 +284,12 @@ int kvm_register_vgic_device(unsigned long type)
 int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr,
 		       struct vgic_reg_attr *reg_attr)
 {
-	int cpuid;
+	int cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr);
 
-	cpuid = (attr->attr & KVM_DEV_ARM_VGIC_CPUID_MASK) >>
-		 KVM_DEV_ARM_VGIC_CPUID_SHIFT;
-
-	if (cpuid >= atomic_read(&dev->kvm->online_vcpus))
-		return -EINVAL;
-
-	reg_attr->vcpu = kvm_get_vcpu(dev->kvm, cpuid);
 	reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
+	reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid);
+	if (!reg_attr->vcpu)
+		return -EINVAL;
 
 	return 0;
 }
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index 2849a9b65..ae578860f 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -157,7 +157,7 @@ static inline long regs_return_value(struct pt_regs *regs)
 #define instruction_pointer(regs) ((regs)->cp0_epc)
 #define profile_pc(regs) instruction_pointer(regs)
 
-extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall);
+extern asmlinkage long syscall_trace_enter(struct pt_regs *regs);
 extern asmlinkage void syscall_trace_leave(struct pt_regs *regs);
 
 extern void die(const char *, struct pt_regs *) __noreturn;
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index aebfda811..6c5269d3a 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -100,6 +100,7 @@ void output_thread_info_defines(void)
 	OFFSET(TI_PRE_COUNT, thread_info, preempt_count);
 	OFFSET(TI_ADDR_LIMIT, thread_info, addr_limit);
 	OFFSET(TI_REGS, thread_info, regs);
+	OFFSET(TI_SYSCALL, thread_info, syscall);
 	DEFINE(_THREAD_SIZE, THREAD_SIZE);
 	DEFINE(_THREAD_MASK, THREAD_MASK);
 	DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE);
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index db7c5be1d..dd454b429 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -1310,16 +1310,13 @@ long arch_ptrace(struct task_struct *child, long request,
  * Notification of system call entry/exit
  * - triggered by current->work.syscall_trace
  */
-asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
+asmlinkage long syscall_trace_enter(struct pt_regs *regs)
 {
 	user_exit();
 
-	current_thread_info()->syscall = syscall;
-
 	if (test_thread_flag(TIF_SYSCALL_TRACE)) {
 		if (tracehook_report_syscall_entry(regs))
 			return -1;
-		syscall = current_thread_info()->syscall;
 	}
 
 #ifdef CONFIG_SECCOMP
@@ -1328,7 +1325,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
 		struct seccomp_data sd;
 		unsigned long args[6];
 
-		sd.nr = syscall;
+		sd.nr = current_thread_info()->syscall;
 		sd.arch = syscall_get_arch(current);
 		syscall_get_arguments(current, regs, args);
 		for (i = 0; i < 6; i++)
@@ -1338,23 +1335,23 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
 		ret = __secure_computing(&sd);
 		if (ret == -1)
 			return ret;
-		syscall = current_thread_info()->syscall;
 	}
 #endif
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->regs[2]);
 
-	audit_syscall_entry(syscall, regs->regs[4], regs->regs[5],
+	audit_syscall_entry(current_thread_info()->syscall,
+			    regs->regs[4], regs->regs[5],
 			    regs->regs[6], regs->regs[7]);
 
 	/*
 	 * Negative syscall numbers are mistaken for rejected syscalls, but
 	 * won't have had the return value set appropriately, so we do so now.
 	 */
-	if (syscall < 0)
+	if (current_thread_info()->syscall < 0)
 		syscall_set_return_value(current, regs, -ENOSYS, 0);
-	return syscall;
+	return current_thread_info()->syscall;
 }
 
 /*
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index b449b6866..80747719a 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -80,6 +80,18 @@ loads_done:
 	PTR	load_a7, bad_stack_a7
 	.previous
 
+	/*
+	 * syscall number is in v0 unless we called syscall(__NR_###)
+	 * where the real syscall number is in a0
+	 */
+	subu	t2, v0,  __NR_O32_Linux
+	bnez	t2, 1f /* __NR_syscall at offset 0 */
+	LONG_S	a0, TI_SYSCALL($28)	# Save a0 as syscall number
+	b	2f
+1:
+	LONG_S	v0, TI_SYSCALL($28)	# Save v0 as syscall number
+2:
+
 	lw	t0, TI_FLAGS($28)	# syscall tracing enabled?
 	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	and	t0, t1
@@ -117,16 +129,7 @@ syscall_trace_entry:
 	SAVE_STATIC
 	move	a0, sp
 
-	/*
-	 * syscall number is in v0 unless we called syscall(__NR_###)
-	 * where the real syscall number is in a0
-	 */
-	move	a1, v0
-	subu	t2, v0,  __NR_O32_Linux
-	bnez	t2, 1f /* __NR_syscall at offset 0 */
-	lw	a1, PT_R4(sp)
-
-1:	jal	syscall_trace_enter
+	jal	syscall_trace_enter
 
 	bltz	v0, 1f			# seccomp failed? Skip syscall
 
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 35d8c86b1..a8679e34c 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -44,6 +44,8 @@ NESTED(handle_sysn32, PT_SIZE, sp)
 
 	sd	a3, PT_R26(sp)		# save a3 for syscall restarting
 
+	LONG_S	v0, TI_SYSCALL($28)     # Store syscall number
+
 	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
 	and	t0, t1, t0
@@ -72,7 +74,6 @@ syscall_common:
 n32_syscall_trace_entry:
 	SAVE_STATIC
 	move	a0, sp
-	move	a1, v0
 	jal	syscall_trace_enter
 
 	bltz	v0, 1f			# seccomp failed? Skip syscall
diff --git a/arch/mips/kernel/scall64-n64.S b/arch/mips/kernel/scall64-n64.S
index 23b2e2b16..a3b5ab509 100644
--- a/arch/mips/kernel/scall64-n64.S
+++ b/arch/mips/kernel/scall64-n64.S
@@ -47,6 +47,8 @@ NESTED(handle_sys64, PT_SIZE, sp)
 
 	sd	a3, PT_R26(sp)		# save a3 for syscall restarting
 
+	LONG_S	v0, TI_SYSCALL($28)     # Store syscall number
+
 	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
 	and	t0, t1, t0
@@ -83,7 +85,6 @@ n64_syscall_exit:
 syscall_trace_entry:
 	SAVE_STATIC
 	move	a0, sp
-	move	a1, v0
 	jal	syscall_trace_enter
 
 	bltz	v0, 1f			# seccomp failed? Skip syscall
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 50c9a57e0..6757368e9 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -79,6 +79,22 @@ loads_done:
 	PTR	load_a7, bad_stack_a7
 	.previous
 
+	/*
+	 * absolute syscall number is in v0 unless we called syscall(__NR_###)
+	 * where the real syscall number is in a0
+	 * note: NR_syscall is the first O32 syscall but the macro is
+	 * only defined when compiling with -mabi=32 (CONFIG_32BIT)
+	 * therefore __NR_O32_Linux is used (4000)
+	 */
+
+	subu	t2, v0,  __NR_O32_Linux
+	bnez	t2, 1f /* __NR_syscall at offset 0 */
+	LONG_S	a0, TI_SYSCALL($28)	# Save a0 as syscall number
+	b	2f
+1:
+	LONG_S	v0, TI_SYSCALL($28)	# Save v0 as syscall number
+2:
+
 	li	t1, _TIF_WORK_SYSCALL_ENTRY
 	LONG_L	t0, TI_FLAGS($28)	# syscall tracing enabled?
 	and	t0, t1, t0
@@ -113,22 +129,7 @@ trace_a_syscall:
 	sd	a7, PT_R11(sp)		# For indirect syscalls
 
 	move	a0, sp
-	/*
-	 * absolute syscall number is in v0 unless we called syscall(__NR_###)
-	 * where the real syscall number is in a0
-	 * note: NR_syscall is the first O32 syscall but the macro is
-	 * only defined when compiling with -mabi=32 (CONFIG_32BIT)
-	 * therefore __NR_O32_Linux is used (4000)
-	 */
-	.set	push
-	.set	reorder
-	subu	t1, v0,  __NR_O32_Linux
-	move	a1, v0
-	bnez	t1, 1f /* __NR_syscall at offset 0 */
-	ld	a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
-	.set	pop
-
-1:	jal	syscall_trace_enter
+	jal	syscall_trace_enter
 
 	bltz	v0, 1f			# seccomp failed? Skip syscall
 
diff --git a/arch/s390/include/asm/dwarf.h b/arch/s390/include/asm/dwarf.h
index 4f21ae561..390906b8e 100644
--- a/arch/s390/include/asm/dwarf.h
+++ b/arch/s390/include/asm/dwarf.h
@@ -9,6 +9,7 @@
 #define CFI_DEF_CFA_OFFSET	.cfi_def_cfa_offset
 #define CFI_ADJUST_CFA_OFFSET	.cfi_adjust_cfa_offset
 #define CFI_RESTORE		.cfi_restore
+#define CFI_REL_OFFSET		.cfi_rel_offset
 
 #ifdef CONFIG_AS_CFI_VAL_OFFSET
 #define CFI_VAL_OFFSET		.cfi_val_offset
diff --git a/arch/s390/kernel/vdso64/vdso_user_wrapper.S b/arch/s390/kernel/vdso64/vdso_user_wrapper.S
index a775d7e52..2183b8f64 100644
--- a/arch/s390/kernel/vdso64/vdso_user_wrapper.S
+++ b/arch/s390/kernel/vdso64/vdso_user_wrapper.S
@@ -23,8 +23,10 @@ __kernel_\func:
 	CFI_DEF_CFA_OFFSET (STACK_FRAME_OVERHEAD + WRAPPER_FRAME_SIZE)
 	CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
 	stg	%r14,STACK_FRAME_OVERHEAD(%r15)
+	CFI_REL_OFFSET 14, STACK_FRAME_OVERHEAD
 	brasl	%r14,__s390_vdso_\func
 	lg	%r14,STACK_FRAME_OVERHEAD(%r15)
+	CFI_RESTORE 14
 	aghi	%r15,WRAPPER_FRAME_SIZE
 	CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
 	CFI_RESTORE 15
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index b5a60fbb9..ad4bae246 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2627,7 +2627,7 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr,
 		return 0;
 
 	start = pmd_val(*pmd) & HPAGE_MASK;
-	end = start + HPAGE_SIZE - 1;
+	end = start + HPAGE_SIZE;
 	__storage_key_init_range(start, end);
 	set_bit(PG_arch_1, &page->flags);
 	cond_resched();
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 3b5a4d25c..0ca46f5d9 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -146,7 +146,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste)
 	}
 
 	if (!test_and_set_bit(PG_arch_1, &page->flags))
-		__storage_key_init_range(paddr, paddr + size - 1);
+		__storage_key_init_range(paddr, paddr + size);
 }
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 1631a9a15..bd785386d 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -46,14 +46,6 @@
 .code64
 .section .entry.text, "ax"
 
-#ifdef CONFIG_PARAVIRT_XXL
-SYM_CODE_START(native_usergs_sysret64)
-	UNWIND_HINT_EMPTY
-	swapgs
-	sysretq
-SYM_CODE_END(native_usergs_sysret64)
-#endif /* CONFIG_PARAVIRT_XXL */
-
 /*
  * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers.
  *
@@ -128,7 +120,12 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	 * Try to use SYSRET instead of IRET if we're returning to
 	 * a completely clean 64-bit userspace context.  If we're not,
 	 * go to the slow exit path.
+	 * In the Xen PV case we must use iret anyway.
 	 */
+
+	ALTERNATIVE "", "jmp	swapgs_restore_regs_and_return_to_usermode", \
+		X86_FEATURE_XENPV
+
 	movq	RCX(%rsp), %rcx
 	movq	RIP(%rsp), %r11
 
@@ -220,7 +217,9 @@ syscall_return_via_sysret:
 
 	popq	%rdi
 	popq	%rsp
-	USERGS_SYSRET64
+	swapgs
+	CLEAR_CPU_BUFFERS
+	sysretq
 SYM_CODE_END(entry_SYSCALL_64)
 
 /*
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index f40dea50d..e585a4705 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -132,13 +132,6 @@ static __always_inline unsigned long arch_local_irq_save(void)
 #endif
 
 #define INTERRUPT_RETURN	jmp native_iret
-#define USERGS_SYSRET64				\
-	swapgs;					\
-	CLEAR_CPU_BUFFERS;			\
-	sysretq;
-#define USERGS_SYSRET32				\
-	swapgs;					\
-	sysretl
 
 #else
 #define INTERRUPT_RETURN		iret
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 4a32b0d34..3c89c1f64 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -776,11 +776,6 @@ extern void default_banner(void);
 
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT_XXL
-#define USERGS_SYSRET64							\
-	PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64),			\
-		  ANNOTATE_RETPOLINE_SAFE;				\
-		  jmp PARA_INDIRECT(pv_ops+PV_CPU_usergs_sysret64);)
-
 #ifdef CONFIG_DEBUG_ENTRY
 #define SAVE_FLAGS(clobbers)                                        \
 	PARA_SITE(PARA_PATCH(PV_IRQ_save_fl),			    \
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 903d71884..55d8b7950 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -157,14 +157,6 @@ struct pv_cpu_ops {
 
 	u64 (*read_pmc)(int counter);
 
-	/*
-	 * Switch to usermode gs and return to 64-bit usermode using
-	 * sysret.  Only used in 64-bit kernels to return to 64-bit
-	 * processes.  Usermode register state, including %rsp, must
-	 * already be restored.
-	 */
-	void (*usergs_sysret64)(void);
-
 	/* Normal iret.  Jump to this with the standard iret stack
 	   frame set up. */
 	void (*iret)(void);
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 1354bc306..b14533af7 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -13,8 +13,6 @@ int main(void)
 {
 #ifdef CONFIG_PARAVIRT
 #ifdef CONFIG_PARAVIRT_XXL
-	OFFSET(PV_CPU_usergs_sysret64, paravirt_patch_template,
-	       cpu.usergs_sysret64);
 #ifdef CONFIG_DEBUG_ENTRY
 	OFFSET(PV_IRQ_save_fl, paravirt_patch_template, irq.save_fl);
 #endif
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index f0e4ad859..9d91061b8 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -124,8 +124,7 @@ unsigned paravirt_patch_default(u8 type, void *insn_buff,
 	else if (opfunc == _paravirt_ident_64)
 		ret = paravirt_patch_ident_64(insn_buff, len);
 
-	else if (type == PARAVIRT_PATCH(cpu.iret) ||
-		 type == PARAVIRT_PATCH(cpu.usergs_sysret64))
+	else if (type == PARAVIRT_PATCH(cpu.iret))
 		/* If operation requires a jmp, then jmp */
 		ret = paravirt_patch_jmp(insn_buff, opfunc, addr, len);
 #endif
@@ -159,7 +158,6 @@ static u64 native_steal_clock(int cpu)
 
 /* These are in entry.S */
 extern void native_iret(void);
-extern void native_usergs_sysret64(void);
 
 static struct resource reserve_ioports = {
 	.start = 0,
@@ -299,7 +297,6 @@ struct paravirt_patch_template pv_ops = {
 
 	.cpu.load_sp0		= native_load_sp0,
 
-	.cpu.usergs_sysret64	= native_usergs_sysret64,
 	.cpu.iret		= native_iret,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c
index 7c518b08a..2fada2c34 100644
--- a/arch/x86/kernel/paravirt_patch.c
+++ b/arch/x86/kernel/paravirt_patch.c
@@ -27,7 +27,6 @@ struct patch_xxl {
 	const unsigned char	mmu_write_cr3[3];
 	const unsigned char	irq_restore_fl[2];
 	const unsigned char	cpu_wbinvd[2];
-	const unsigned char	cpu_usergs_sysret64[6];
 	const unsigned char	mov64[3];
 };
 
@@ -40,8 +39,6 @@ static const struct patch_xxl patch_data_xxl = {
 	.mmu_write_cr3		= { 0x0f, 0x22, 0xdf },	// mov %rdi, %cr3
 	.irq_restore_fl		= { 0x57, 0x9d },	// push %rdi; popfq
 	.cpu_wbinvd		= { 0x0f, 0x09 },	// wbinvd
-	.cpu_usergs_sysret64	= { 0x0f, 0x01, 0xf8,
-				    0x48, 0x0f, 0x07 },	// swapgs; sysretq
 	.mov64			= { 0x48, 0x89, 0xf8 },	// mov %rdi, %rax
 };
 
@@ -83,7 +80,6 @@ unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
 	PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len);
 	PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len);
 
-	PATCH_CASE(cpu, usergs_sysret64, xxl, insn_buff, len);
 	PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len);
 #endif
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8e0b957c6..bc2954393 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8501,13 +8501,20 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 
 static void kvm_inject_exception(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * Suppress the error code if the vCPU is in Real Mode, as Real Mode
+	 * exceptions don't report error codes.  The presence of an error code
+	 * is carried with the exception and only stripped when the exception
+	 * is injected as intercepted #PF VM-Exits for AMD's Paged Real Mode do
+	 * report an error code despite the CPU being in Real Mode.
+	 */
+	vcpu->arch.exception.has_error_code &= is_protmode(vcpu);
+
 	trace_kvm_inj_exception(vcpu->arch.exception.nr,
 				vcpu->arch.exception.has_error_code,
 				vcpu->arch.exception.error_code,
 				vcpu->arch.exception.injected);
 
-	if (vcpu->arch.exception.error_code && !is_protmode(vcpu))
-		vcpu->arch.exception.error_code = false;
 	kvm_x86_ops.queue_exception(vcpu);
 }
 
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 94804670c..b1efc4b4f 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1059,7 +1059,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.read_pmc = xen_read_pmc,
 
 	.iret = xen_iret,
-	.usergs_sysret64 = xen_sysret64,
 
 	.load_tr_desc = paravirt_nop,
 	.set_ldt = xen_set_ldt,
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index e3031afcb..3a33713cf 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -220,27 +220,6 @@ SYM_CODE_START(xen_iret)
 	jmp hypercall_iret
 SYM_CODE_END(xen_iret)
 
-SYM_CODE_START(xen_sysret64)
-	UNWIND_HINT_EMPTY
-	/*
-	 * We're already on the usermode stack at this point, but
-	 * still with the kernel gs, so we can easily switch back.
-	 *
-	 * tss.sp2 is scratch space.
-	 */
-	movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
-	movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
-
-	pushq $__USER_DS
-	pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
-	pushq %r11
-	pushq $__USER_CS
-	pushq %rcx
-
-	pushq $VGCF_in_syscall
-	jmp hypercall_iret
-SYM_CODE_END(xen_sysret64)
-
 /*
  * XEN pv doesn't use trampoline stack, PER_CPU_VAR(cpu_tss_rw + TSS_sp0) is
  * also the kernel stack.  Reusing swapgs_restore_regs_and_return_to_usermode()
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 8695809b8..98242430d 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -138,8 +138,6 @@ __visible unsigned long xen_read_cr2_direct(void);
 
 /* These are not functions, and cannot be called normally */
 __visible void xen_iret(void);
-__visible void xen_sysret32(void);
-__visible void xen_sysret64(void);
 
 extern int xen_panic_handler_init(void);