[PATCH 2/3] x86/asm/entry/32: Remove most of SYSCALL32 code, part 1

[Denys Vlasenko]

SYSCALL32 code is nearly identical to SYSCALL32, except for initial
section. Merge them.

The removal is split into two parts, to make review eaiser. This is part 1.

auditsys_entry_common and auditsys_exit macros are indented one more tab without
any changes. This prevents diff from becoming unreadable.
They will be removed in part 2.

Signed-off-by: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
CC: Ingo Molnar <mingo@xxxxxxxxxx>
CC: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
CC: Krzysztof A. Sobiecki <sobkas@xxxxxxxxx>
CC: Steven Rostedt <rostedt@xxxxxxxxxxx>
CC: Borislav Petkov <bp@xxxxxxxxx>
CC: "H. Peter Anvin" <hpa@xxxxxxxxx>
CC: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
CC: Oleg Nesterov <oleg@xxxxxxxxxx>
CC: Frederic Weisbecker <fweisbec@xxxxxxxxx>
CC: Alexei Starovoitov <ast@xxxxxxxxxxxx>
CC: Will Drewry <wad@xxxxxxxxxxxx>
CC: Kees Cook <keescook@xxxxxxxxxxxx>
CC: x86@xxxxxxxxxx
CC: linux-kernel@xxxxxxxxxxxxxxx
---
 arch/x86/entry/entry_64_compat.S | 237 +++++++++++----------------------------
 1 file changed, 63 insertions(+), 174 deletions(-)

diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 9f9dfa5..2d0a2f0 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -16,13 +16,7 @@
 #include <linux/linkage.h>
 #include <linux/err.h>
 
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_I386		(EM_386|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_LE		0x40000000
-
 #ifndef CONFIG_AUDITSYSCALL
-# define sysexit_audit		ia32_ret_from_sys_call_irqs_off
 # define sysretl_audit		ia32_ret_from_sys_call_irqs_off
 #endif
 
@@ -93,188 +87,82 @@ ENTRY(entry_SYSENTER_compat)
 	 * 32-bit zero extended
 	 */
 	ASM_STAC
-1:	movl	(%rbp), %ebp
+1:	movl	(%rbp), %r9d
 	_ASM_EXTABLE(1b, ia32_badarg)
 	ASM_CLAC
 
 	/*
-	 * Sysenter doesn't filter flags, so we need to clear NT
-	 * ourselves.  To save a few cycles, we can check whether
-	 * NT was set instead of doing an unconditional popfq.
+	 * Sysenter doesn't filter flags, so we need to clear NT ourselves.
 	 */
 	testl	$X86_EFLAGS_NT, EFLAGS(%rsp)
 	jnz	sysenter_fix_flags
 sysenter_flags_fixed:
-
-	orl	$TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	testl	$_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	sysenter_tracesys
-
-sysenter_do_call:
-	/* 32-bit syscall -> 64-bit C ABI argument conversion */
-	movl	%edi, %r8d		/* arg5 */
-	movl	%ebp, %r9d		/* arg6 */
-	xchg	%ecx, %esi		/* rsi:arg2, rcx:arg4 */
-	movl	%ebx, %edi		/* arg1 */
-	movl	%edx, %edx		/* arg3 (zero extension) */
-
-sysenter_dispatch:
-	cmpq	$(IA32_NR_syscalls-1), %rax
-	ja	1f
-	call	*ia32_sys_call_table(, %rax, 8)
-	movq	%rax, RAX(%rsp)
-1:
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	TRACE_IRQS_OFF
-	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	sysexit_audit
-
-sysexit_from_sys_call:
-	/*
-	 * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an
-	 * NMI between STI and SYSEXIT has poorly specified behavior,
-	 * and and NMI followed by an IRQ with usergs is fatal.  So
-	 * we just pretend we're using SYSEXIT but we really use
-	 * SYSRETL instead.
-	 *
-	 * This code path is still called 'sysexit' because it pairs
-	 * with 'sysenter' and it uses the SYSENTER calling convention.
-	 */
-	andl	$~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	movl	RSI(%rsp), %esi
-	movl	RDI(%rsp), %edi
-	movl	RIP(%rsp), %ecx		/* User %eip */
-	movl	EFLAGS(%rsp), %r11d	/* User eflags */
-	xorl	%edx, %edx		/* Do not leak kernel information */
-	xorq	%r10, %r10
-	xorq	%r9, %r9
-	xorq	%r8, %r8
-	TRACE_IRQS_ON
-
-	/*
-	 * SYSRETL works even on Intel CPUs.  Use it in preference to SYSEXIT,
-	 * since it avoids a dicey window with interrupts enabled.
-	 */
-	movl	RSP(%rsp), %esp
-
-	/*
-	 * USERGS_SYSRET32 does:
-	 *  gsbase = user's gs base
-	 *  eip = ecx
-	 *  rflags = r11
-	 *  cs = __USER32_CS
-	 *  ss = __USER_DS
-	 *
-	 * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does:
-	 *
-	 *  pop %ebp
-	 *  pop %edx
-	 *  pop %ecx
-	 *
-	 * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to
-	 * avoid info leaks.  R11 ends up with VDSO32_SYSENTER_RETURN's
-	 * address (already known to user code), and R12-R15 are
-	 * callee-saved and therefore don't contain any interesting
-	 * kernel data.
-	 */
-	USERGS_SYSRET32
-
-#ifdef CONFIG_AUDITSYSCALL
-	.macro auditsys_entry_common
-	/*
-	 * At this point, registers hold syscall args in the 32-bit syscall ABI:
-	 * EAX is syscall number, the 6 args are in EBX,ECX,EDX,ESI,EDI,EBP.
-	 *
-	 * We want to pass them to __audit_syscall_entry(), which is a 64-bit
-	 * C function with 5 parameters, so shuffle them to match what
-	 * the function expects: RDI,RSI,RDX,RCX,R8.
-	 */
-	movl	%esi, %r8d		/* arg5 (R8 ) <= 4th syscall arg (ESI) */
-	xchg	%ecx, %edx		/* arg4 (RCX) <= 3rd syscall arg (EDX) */
-					/* arg3 (RDX) <= 2nd syscall arg (ECX) */
-	movl	%ebx, %esi		/* arg2 (RSI) <= 1st syscall arg (EBX) */
-	movl	%eax, %edi		/* arg1 (RDI) <= syscall number  (EAX) */
-	call	__audit_syscall_entry
-
-	/*
-	 * We are going to jump back to the syscall dispatch code.
-	 * Prepare syscall args as required by the 64-bit C ABI.
-	 * Registers clobbered by __audit_syscall_entry() are
-	 * loaded from pt_regs on stack:
-	 */
-	movl	ORIG_RAX(%rsp), %eax	/* syscall number */
-	movl	%ebx, %edi		/* arg1 */
-	movl	RCX(%rsp), %esi		/* arg2 */
-	movl	RDX(%rsp), %edx		/* arg3 */
-	movl	RSI(%rsp), %ecx		/* arg4 */
-	movl	RDI(%rsp), %r8d		/* arg5 */
-	.endm
-
-	.macro auditsys_exit exit
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
-	testl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	ia32_ret_from_sys_call
-	movl	%eax, %esi		/* second arg, syscall return value */
-	cmpl	$-MAX_ERRNO, %eax	/* is it an error ? */
-	jbe	1f
-	movslq	%eax, %rsi		/* if error sign extend to 64 bits */
-1:	setbe	%al			/* 1 if error, 0 if not */
-	movzbl	%al, %edi		/* zero-extend that into %edi */
-	call	__audit_syscall_exit
-	movq	RAX(%rsp), %rax		/* reload syscall return value */
-	movl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	TRACE_IRQS_OFF
-	testl	%edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jz	\exit
-	xorl	%eax, %eax		/* Do not leak kernel information */
-	movq	%rax, R11(%rsp)
-	movq	%rax, R10(%rsp)
-	movq	%rax, R9(%rsp)
-	movq	%rax, R8(%rsp)
-	jmp	int_ret_from_sys_call_irqs_off
-	.endm
-
-sysenter_auditsys:
-	auditsys_entry_common
-	movl	%ebp, %r9d		/* reload 6th syscall arg */
-	jmp	sysenter_dispatch
-
-sysexit_audit:
-	auditsys_exit sysexit_from_sys_call
-#endif
+	jmp	sysenter_jumps_here
 
 sysenter_fix_flags:
 	pushq	$(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
 	popfq
 	jmp	sysenter_flags_fixed
-
-sysenter_tracesys:
-#ifdef CONFIG_AUDITSYSCALL
-	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jz	sysenter_auditsys
-#endif
-	SAVE_EXTRA_REGS
-	xorl	%eax, %eax		/* Do not leak kernel information */
-	movq	%rax, R11(%rsp)
-	movq	%rax, R10(%rsp)
-	movq	%rax, R9(%rsp)
-	movq	%rax, R8(%rsp)
-	movq	%rsp, %rdi		/* &pt_regs -> arg1 */
-	call	syscall_trace_enter
-
-	/* Reload arg registers from stack. (see sysenter_tracesys) */
-	movl	RCX(%rsp), %ecx
-	movl	RDX(%rsp), %edx
-	movl	RSI(%rsp), %esi
-	movl	RDI(%rsp), %edi
-	movl	%eax, %eax		/* zero extension */
-
-	RESTORE_EXTRA_REGS
-	jmp	sysenter_do_call
 ENDPROC(entry_SYSENTER_compat)
 
+
+	#ifdef CONFIG_AUDITSYSCALL
+		.macro auditsys_entry_common
+		/*
+		 * At this point, registers hold syscall args in the 32-bit syscall ABI:
+		 * EAX is syscall number, the 6 args are in EBX,ECX,EDX,ESI,EDI,EBP.
+		 *
+		 * We want to pass them to __audit_syscall_entry(), which is a 64-bit
+		 * C function with 5 parameters, so shuffle them to match what
+		 * the function expects: RDI,RSI,RDX,RCX,R8.
+		 */
+		movl	%esi, %r8d		/* arg5 (R8 ) <= 4th syscall arg (ESI) */
+		xchg	%ecx, %edx		/* arg4 (RCX) <= 3rd syscall arg (EDX) */
+						/* arg3 (RDX) <= 2nd syscall arg (ECX) */
+		movl	%ebx, %esi		/* arg2 (RSI) <= 1st syscall arg (EBX) */
+		movl	%eax, %edi		/* arg1 (RDI) <= syscall number  (EAX) */
+		call	__audit_syscall_entry
+
+		/*
+		 * We are going to jump back to the syscall dispatch code.
+		 * Prepare syscall args as required by the 64-bit C ABI.
+		 * Registers clobbered by __audit_syscall_entry() are
+		 * loaded from pt_regs on stack:
+		 */
+		movl	ORIG_RAX(%rsp), %eax	/* syscall number */
+		movl	%ebx, %edi		/* arg1 */
+		movl	RCX(%rsp), %esi		/* arg2 */
+		movl	RDX(%rsp), %edx		/* arg3 */
+		movl	RSI(%rsp), %ecx		/* arg4 */
+		movl	RDI(%rsp), %r8d		/* arg5 */
+		.endm
+
+		.macro auditsys_exit exit
+		TRACE_IRQS_ON
+		ENABLE_INTERRUPTS(CLBR_NONE)
+		testl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+		jnz	ia32_ret_from_sys_call
+		movl	%eax, %esi		/* second arg, syscall return value */
+		cmpl	$-MAX_ERRNO, %eax	/* is it an error ? */
+		jbe	1f
+		movslq	%eax, %rsi		/* if error sign extend to 64 bits */
+	1:	setbe	%al			/* 1 if error, 0 if not */
+		movzbl	%al, %edi		/* zero-extend that into %edi */
+		call	__audit_syscall_exit
+		movq	RAX(%rsp), %rax		/* reload syscall return value */
+		movl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi
+		DISABLE_INTERRUPTS(CLBR_NONE)
+		TRACE_IRQS_OFF
+		testl	%edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+		jz	\exit
+		xorl	%eax, %eax		/* Do not leak kernel information */
+		movq	%rax, R11(%rsp)
+		movq	%rax, R10(%rsp)
+		movq	%rax, R9(%rsp)
+		movq	%rax, R8(%rsp)
+		jmp	int_ret_from_sys_call_irqs_off
+		.endm
+	#endif
 /*
  * 32-bit SYSCALL instruction entry.
  *
@@ -343,6 +231,7 @@ ENTRY(entry_SYSCALL_compat)
 	_ASM_EXTABLE(1b, ia32_badarg)
 	ASM_CLAC
 
+sysenter_jumps_here:
 	orl	$TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
 	testl	$_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
 	jnz	cstar_tracesys
@@ -421,7 +310,7 @@ cstar_tracesys:
 	call	syscall_trace_enter
 	movl	R9(%rsp), %r9d
 
-	/* Reload arg registers from stack. (see sysenter_tracesys) */
+	/* Reload arg registers from stack. */
 	movl	RCX(%rsp), %ecx
 	movl	RDX(%rsp), %edx
 	movl	RSI(%rsp), %esi
-- 
1.8.1.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/