Merge tag 'x86-entry-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 entry updates from Ingo Molnar:

 - Make IA32_EMULATION boot time configurable with
   the new ia32_emulation=<bool> boot option

 - Clean up fast syscall return validation code: convert
   it to C and refactor the code

 - As part of this, optimize the canonical RIP test code

* tag 'x86-entry-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/entry/32: Clean up syscall fast exit tests
  x86/entry/64: Use TASK_SIZE_MAX for canonical RIP test
  x86/entry/64: Convert SYSRET validation tests to C
  x86/entry/32: Remove SEP test for SYSEXIT
  x86/entry/32: Convert do_fast_syscall_32() to bool return type
  x86/entry/compat: Combine return value test from syscall handler
  x86/entry/64: Remove obsolete comment on tracing vs. SYSRET
  x86: Make IA32_EMULATION boot time configurable
  x86/entry: Make IA32 syscalls' availability depend on ia32_enabled()
  x86/elf: Make loading of 32bit processes depend on ia32_enabled()
  x86/entry: Compile entry_SYSCALL32_ignore() unconditionally
  x86/entry: Rename ignore_sysret()
  x86: Introduce ia32_enabled()

1 files changed, 4 insertions, 68 deletions

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d656924eefc2..de6469dffe3a 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -126,70 +126,8 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	 * 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
-
-	cmpq	%rcx, %r11	/* SYSRET requires RCX == RIP */
-	jne	swapgs_restore_regs_and_return_to_usermode
-
-	/*
-	 * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
-	 * in kernel space.  This essentially lets the user take over
-	 * the kernel, since userspace controls RSP.
-	 *
-	 * If width of "canonical tail" ever becomes variable, this will need
-	 * to be updated to remain correct on both old and new CPUs.
-	 *
-	 * Change top bits to match most significant bit (47th or 56th bit
-	 * depending on paging mode) in the address.
-	 */
-#ifdef CONFIG_X86_5LEVEL
-	ALTERNATIVE "shl $(64 - 48), %rcx; sar $(64 - 48), %rcx", \
-		"shl $(64 - 57), %rcx; sar $(64 - 57), %rcx", X86_FEATURE_LA57
-#else
-	shl	$(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
-	sar	$(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
-#endif
-
-	/* If this changed %rcx, it was not canonical */
-	cmpq	%rcx, %r11
-	jne	swapgs_restore_regs_and_return_to_usermode
-
-	cmpq	$__USER_CS, CS(%rsp)		/* CS must match SYSRET */
-	jne	swapgs_restore_regs_and_return_to_usermode
-
-	movq	R11(%rsp), %r11
-	cmpq	%r11, EFLAGS(%rsp)		/* R11 == RFLAGS */
-	jne	swapgs_restore_regs_and_return_to_usermode
-
-	/*
-	 * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot
-	 * restore RF properly. If the slowpath sets it for whatever reason, we
-	 * need to restore it correctly.
-	 *
-	 * SYSRET can restore TF, but unlike IRET, restoring TF results in a
-	 * trap from userspace immediately after SYSRET.  This would cause an
-	 * infinite loop whenever #DB happens with register state that satisfies
-	 * the opportunistic SYSRET conditions.  For example, single-stepping
-	 * this user code:
-	 *
-	 *           movq	$stuck_here, %rcx
-	 *           pushfq
-	 *           popq %r11
-	 *   stuck_here:
-	 *
-	 * would never get past 'stuck_here'.
-	 */
-	testq	$(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
-	jnz	swapgs_restore_regs_and_return_to_usermode
-
-	/* nothing to check for RSP */
-
-	cmpq	$__USER_DS, SS(%rsp)		/* SS must match SYSRET */
-	jne	swapgs_restore_regs_and_return_to_usermode
+	ALTERNATIVE "testb %al, %al; jz swapgs_restore_regs_and_return_to_usermode", \
+		"jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 
 	/*
 	 * We win! This label is here just for ease of understanding
@@ -1509,18 +1447,16 @@ nmi_restore:
 	iretq
 SYM_CODE_END(asm_exc_nmi)
 
-#ifndef CONFIG_IA32_EMULATION
 /*
  * This handles SYSCALL from 32-bit code.  There is no way to program
  * MSRs to fully disable 32-bit SYSCALL.
  */
-SYM_CODE_START(ignore_sysret)
+SYM_CODE_START(entry_SYSCALL32_ignore)
 	UNWIND_HINT_END_OF_STACK
 	ENDBR
 	mov	$-ENOSYS, %eax
 	sysretl
-SYM_CODE_END(ignore_sysret)
-#endif
+SYM_CODE_END(entry_SYSCALL32_ignore)
 
 .pushsection .text, "ax"
 	__FUNC_ALIGN