diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index e43ac17cb9fb51..73f17d0544dd58 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -189,11 +189,9 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
 				/* push arguments for extract_kernel: */
 	pushl	$z_output_len	/* decompressed length, end of relocs */
 
-	movl    BP_init_size(%esi), %eax
-	subl    $_end, %eax
-	movl    %ebx, %ebp
-	subl    %eax, %ebp
-	pushl	%ebp		/* output address */
+	leal	_end(%ebx), %eax
+	subl    BP_init_size(%esi), %eax
+	pushl	%eax		/* output address */
 
 	pushl	$z_input_len	/* input_len */
 	leal	input_data(%ebx), %eax
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 76942cbd95a115..f2bb91e87877c3 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1728,7 +1728,7 @@ SYM_CODE_END(nmi)
 SYM_CODE_START(ignore_sysret)
 	UNWIND_HINT_EMPTY
 	mov	$-ENOSYS, %eax
-	sysret
+	sysretl
 SYM_CODE_END(ignore_sysret)
 #endif
 
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 30416d7f19d4f8..a3aefe9b94012a 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -114,8 +114,6 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 
 	err |= fpu__restore_sig(buf, 1);
 
-	force_iret();
-
 	return err;
 }
 
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index e9b62498fe75a3..98c60fa31cedab 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -357,6 +357,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_FSRM		(18*32+ 4) /* Fast Short Rep Mov */
 #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 5057a8ed100b82..78897a8da01f7c 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -339,22 +339,6 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs,
 
 #define ARCH_HAS_USER_SINGLE_STEP_REPORT
 
-/*
- * When hitting ptrace_stop(), we cannot return using SYSRET because
- * that does not restore the full CPU state, only a minimal set.  The
- * ptracer can change arbitrary register values, which is usually okay
- * because the usual ptrace stops run off the signal delivery path which
- * forces IRET; however, ptrace_event() stops happen in arbitrary places
- * in the kernel and don't force IRET path.
- *
- * So force IRET path after a ptrace stop.
- */
-#define arch_ptrace_stop_needed(code, info)				\
-({									\
-	force_iret();							\
-	false;								\
-})
-
 struct user_desc;
 extern int do_get_thread_area(struct task_struct *p, int idx,
 			      struct user_desc __user *info);
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index d779366ce3f89f..cf4327986e98d5 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -239,15 +239,6 @@ static inline int arch_within_stack_frames(const void * const stack,
 			   current_thread_info()->status & TS_COMPAT)
 #endif
 
-/*
- * Force syscall return via IRET by making it look as if there was
- * some work pending. IRET is our most capable (but slowest) syscall
- * return path, which is able to restore modified SS, CS and certain
- * EFLAGS values that other (fast) syscall return instructions
- * are not able to restore properly.
- */
-#define force_iret() set_thread_flag(TIF_NOTIFY_RESUME)
-
 extern void arch_task_cache_init(void);
 extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 extern void arch_release_task_struct(struct task_struct *tsk);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 32ef1ee733b776..81045aabb6f459 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -245,17 +245,13 @@ NOKPROBE_SYMBOL(kvm_read_and_reset_pf_reason);
 dotraplinkage void
 do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address)
 {
-	enum ctx_state prev_state;
-
 	switch (kvm_read_and_reset_pf_reason()) {
 	default:
 		do_page_fault(regs, error_code, address);
 		break;
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
 		/* page is swapped out by the host. */
-		prev_state = exception_enter();
 		kvm_async_pf_task_wait((u32)address, !user_mode(regs));
-		exception_exit(prev_state);
 		break;
 	case KVM_PV_REASON_PAGE_READY:
 		rcu_irq_enter();
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 323499f48858b8..5052ced433734b 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -124,7 +124,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 	regs->ip		= new_ip;
 	regs->sp		= new_sp;
 	regs->flags		= X86_EFLAGS_IF;
-	force_iret();
 }
 EXPORT_SYMBOL_GPL(start_thread);
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 506d66830d4d7e..ffd497804dbc34 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -394,7 +394,6 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip,
 	regs->cs		= _cs;
 	regs->ss		= _ss;
 	regs->flags		= X86_EFLAGS_IF;
-	force_iret();
 }
 
 void
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 8eb7193e158dd8..8a29573851a327 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -151,8 +151,6 @@ static int restore_sigcontext(struct pt_regs *regs,
 
 	err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32));
 
-	force_iret();
-
 	return err;
 }
 
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index a76c12b38e925a..91d55454e7022a 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -381,7 +381,6 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 		mark_screen_rdonly(tsk->mm);
 
 	memcpy((struct kernel_vm86_regs *)regs, &vm86regs, sizeof(vm86regs));
-	force_iret();
 	return regs->ax;
 }
 
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 337830d7a59c75..7ff00ea64e4fe5 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -29,10 +29,7 @@
 SYM_FUNC_START_ALIAS(memmove)
 SYM_FUNC_START(__memmove)
 
-	/* Handle more 32 bytes in loop */
 	mov %rdi, %rax
-	cmp $0x20, %rdx
-	jb	1f
 
 	/* Decide forward/backward copy mode */
 	cmp %rdi, %rsi
@@ -42,7 +39,9 @@ SYM_FUNC_START(__memmove)
 	cmp %rdi, %r8
 	jg 2f
 
+	/* FSRM implies ERMS => no length checks, do the copy directly */
 .Lmemmove_begin_forward:
+	ALTERNATIVE "cmp $0x20, %rdx; jb 1f", "", X86_FEATURE_FSRM
 	ALTERNATIVE "", "movq %rdx, %rcx; rep movsb; retq", X86_FEATURE_ERMS
 
 	/*
@@ -114,6 +113,8 @@ SYM_FUNC_START(__memmove)
 	 */
 	.p2align 4
 2:
+	cmp $0x20, %rdx
+	jb 1f
 	cmp $680, %rdx
 	jb 6f
 	cmp %dil, %sil
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index c9c8523a3a480d..fa4ea09593abb0 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1487,27 +1487,6 @@ void do_user_addr_fault(struct pt_regs *regs,
 }
 NOKPROBE_SYMBOL(do_user_addr_fault);
 
-/*
- * Explicitly marked noinline such that the function tracer sees this as the
- * page_fault entry point.
- */
-static noinline void
-__do_page_fault(struct pt_regs *regs, unsigned long hw_error_code,
-		unsigned long address)
-{
-	prefetchw(&current->mm->mmap_sem);
-
-	if (unlikely(kmmio_fault(regs, address)))
-		return;
-
-	/* Was the fault on kernel-controlled part of the address space? */
-	if (unlikely(fault_in_kernel_space(address)))
-		do_kern_addr_fault(regs, hw_error_code, address);
-	else
-		do_user_addr_fault(regs, hw_error_code, address);
-}
-NOKPROBE_SYMBOL(__do_page_fault);
-
 static __always_inline void
 trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code,
 			 unsigned long address)
@@ -1522,13 +1501,19 @@ trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code,
 }
 
 dotraplinkage void
-do_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address)
+do_page_fault(struct pt_regs *regs, unsigned long hw_error_code,
+		unsigned long address)
 {
-	enum ctx_state prev_state;
+	prefetchw(&current->mm->mmap_sem);
+	trace_page_fault_entries(regs, hw_error_code, address);
 
-	prev_state = exception_enter();
-	trace_page_fault_entries(regs, error_code, address);
-	__do_page_fault(regs, error_code, address);
-	exception_exit(prev_state);
+	if (unlikely(kmmio_fault(regs, address)))
+		return;
+
+	/* Was the fault on kernel-controlled part of the address space? */
+	if (unlikely(fault_in_kernel_space(address)))
+		do_kern_addr_fault(regs, hw_error_code, address);
+	else
+		do_user_addr_fault(regs, hw_error_code, address);
 }
 NOKPROBE_SYMBOL(do_page_fault);