Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 asm updates from Ingo Molnar:
 "Misc updates:

   - Remove last remaining calls to exception_enter/exception_exit() and
     simplify the entry code some more.

   - Remove force_iret()

   - Add support for "Fast Short Rep Mov", which is available starting
     with Ice Lake Intel CPUs - and make the x86 assembly version of
     memmove() use REP MOV for all sizes when FSRM is available.

   - Micro-optimize/simplify the 32-bit boot code a bit.

   - Use a more future-proof SYSRET instruction mnemonic"

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/boot: Simplify calculation of output address
  x86/entry/64: Add instruction suffix to SYSRET
  x86: Remove force_iret()
  x86/cpufeatures: Add support for fast short REP; MOVSB
  x86/context-tracking: Remove exception_enter/exit() from KVM_PV_REASON_PAGE_NOT_PRESENT async page fault
  x86/context-tracking: Remove exception_enter/exit() from do_page_fault()

Author: torvalds

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

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
 

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;
 }
 

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 */

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);

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);

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();

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);
 

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

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;
 }