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:

 - Add UMIP emulation/spoofing for 64-bit processes as well, because of
   Wine based gaming.

 - Clean up symbols/labels in low level asm code

 - Add an assembly optimized mul_u64_u32_div() implementation on x86-64.

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/umip: Add emulation (spoofing) for UMIP covered instructions in 64-bit processes as well
  x86/asm: Make some functions local labels
  x86/asm/suspend: Get rid of bogus_64_magic
  x86/math64: Provide a sane mul_u64_u32_div() implementation for x86_64

arch/x86/boot/compressed/head_32.S

@@ -140,7 +140,7 @@ ENTRY(startup_32)
 /*
  * Jump to the relocated address.
  */
-	leal	relocated(%ebx), %eax
+	leal	.Lrelocated(%ebx), %eax
 	jmp	*%eax
 ENDPROC(startup_32)
 
@@ -209,7 +209,7 @@ ENDPROC(efi32_stub_entry)
 #endif
 
 	.text
-relocated:
+.Lrelocated:
 
 /*
  * Clear BSS (stack is currently empty)

arch/x86/boot/compressed/head_64.S

@@ -87,7 +87,7 @@ ENTRY(startup_32)
 
 	call	verify_cpu
 	testl	%eax, %eax
-	jnz	no_longmode
+	jnz	.Lno_longmode
 
 /*
  * Compute the delta between where we were compiled to run at
@@ -322,7 +322,7 @@ ENTRY(startup_64)
 1:	popq	%rdi
 	subq	$1b, %rdi
 
-	call	adjust_got
+	call	.Ladjust_got
 
 	/*
 	 * At this point we are in long mode with 4-level paging enabled,
@@ -421,7 +421,7 @@ trampoline_return:
 
 	/* The new adjustment is the relocation address */
 	movq	%rbx, %rdi
-	call	adjust_got
+	call	.Ladjust_got
 
 /*
  * Copy the compressed kernel to the end of our buffer
@@ -440,7 +440,7 @@ trampoline_return:
 /*
  * Jump to the relocated address.
  */
-	leaq	relocated(%rbx), %rax
+	leaq	.Lrelocated(%rbx), %rax
 	jmp	*%rax
 
 #ifdef CONFIG_EFI_STUB
@@ -511,7 +511,7 @@ ENDPROC(efi64_stub_entry)
 #endif
 
 	.text
-relocated:
+.Lrelocated:
 
 /*
  * Clear BSS (stack is currently empty)
@@ -548,7 +548,7 @@ relocated:
  * first time we touch GOT).
  * RDI is the new adjustment to apply.
  */
-adjust_got:
+.Ladjust_got:
 	/* Walk through the GOT adding the address to the entries */
 	leaq	_got(%rip), %rdx
 	leaq	_egot(%rip), %rcx
@@ -622,7 +622,7 @@ ENTRY(trampoline_32bit_src)
 	movl	%eax, %cr4
 
 	/* Calculate address of paging_enabled() once we are executing in the trampoline */
-	leal	paging_enabled - trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_OFFSET(%ecx), %eax
+	leal	.Lpaging_enabled - trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_OFFSET(%ecx), %eax
 
 	/* Prepare the stack for far return to Long Mode */
 	pushl	$__KERNEL_CS
@@ -635,7 +635,7 @@ ENTRY(trampoline_32bit_src)
 	lret
 
 	.code64
-paging_enabled:
+.Lpaging_enabled:
 	/* Return from the trampoline */
 	jmp	*%rdi
 
@@ -647,7 +647,7 @@ paging_enabled:
 	.org	trampoline_32bit_src + TRAMPOLINE_32BIT_CODE_SIZE
 
 	.code32
-no_longmode:
+.Lno_longmode:
 	/* This isn't an x86-64 CPU, so hang intentionally, we cannot continue */
 1:
 	hlt

arch/x86/entry/entry_64.S

@@ -1058,10 +1058,10 @@ ENTRY(native_load_gs_index)
 ENDPROC(native_load_gs_index)
 EXPORT_SYMBOL(native_load_gs_index)
 
-	_ASM_EXTABLE(.Lgs_change, bad_gs)
+	_ASM_EXTABLE(.Lgs_change, .Lbad_gs)
 	.section .fixup, "ax"
 	/* running with kernelgs */
-bad_gs:
+.Lbad_gs:
 	SWAPGS					/* switch back to user gs */
 .macro ZAP_GS
 	/* This can't be a string because the preprocessor needs to see it. */

arch/x86/include/asm/div64.h

@@ -73,6 +73,19 @@ static inline u64 mul_u32_u32(u32 a, u32 b)
 
 #else
 # include <asm-generic/div64.h>
+
+static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 div)
+{
+	u64 q;
+
+	asm ("mulq %2; divq %3" : "=a" (q)
+				: "a" (a), "rm" ((u64)mul), "rm" ((u64)div)
+				: "rdx");
+
+	return q;
+}
+#define mul_u64_u32_div	mul_u64_u32_div
+
 #endif /* CONFIG_X86_32 */
 
 #endif /* _ASM_X86_DIV64_H */

arch/x86/kernel/acpi/wakeup_64.S

@@ -18,8 +18,13 @@ ENTRY(wakeup_long64)
 	movq	saved_magic, %rax
 	movq	$0x123456789abcdef0, %rdx
 	cmpq	%rdx, %rax
-	jne	bogus_64_magic
+	je	2f
 
+	/* stop here on a saved_magic mismatch */
+	movq $0xbad6d61676963, %rcx
+1:
+	jmp 1b
+2:
 	movw	$__KERNEL_DS, %ax
 	movw	%ax, %ss	
 	movw	%ax, %ds
@@ -37,9 +42,6 @@ ENTRY(wakeup_long64)
 	jmp	*%rax
 ENDPROC(wakeup_long64)
 
-bogus_64_magic:
-	jmp	bogus_64_magic
-
 ENTRY(do_suspend_lowlevel)
 	FRAME_BEGIN
 	subq	$8, %rsp

arch/x86/kernel/umip.c

@@ -19,7 +19,7 @@
 /** DOC: Emulation for User-Mode Instruction Prevention (UMIP)
  *
  * The feature User-Mode Instruction Prevention present in recent Intel
- * processor prevents a group of instructions (sgdt, sidt, sldt, smsw, and str)
+ * processor prevents a group of instructions (SGDT, SIDT, SLDT, SMSW and STR)
  * from being executed with CPL > 0. Otherwise, a general protection fault is
  * issued.
  *
@@ -36,8 +36,8 @@
  * DOSEMU2) rely on this subset of instructions to function.
  *
  * The instructions protected by UMIP can be split in two groups. Those which
- * return a kernel memory address (sgdt and sidt) and those which return a
- * value (sldt, str and smsw).
+ * return a kernel memory address (SGDT and SIDT) and those which return a
+ * value (SLDT, STR and SMSW).
  *
  * For the instructions that return a kernel memory address, applications
  * such as WineHQ rely on the result being located in the kernel memory space,
@@ -45,15 +45,13 @@
  * value that, lies close to the top of the kernel memory. The limit for the GDT
  * and the IDT are set to zero.
  *
- * Given that sldt and str are not commonly used in programs that run on WineHQ
+ * Given that SLDT and STR are not commonly used in programs that run on WineHQ
  * or DOSEMU2, they are not emulated.
  *
  * The instruction smsw is emulated to return the value that the register CR0
  * has at boot time as set in the head_32.
  *
- * Also, emulation is provided only for 32-bit processes; 64-bit processes
- * that attempt to use the instructions that UMIP protects will receive the
- * SIGSEGV signal issued as a consequence of the general protection fault.
+ * Emulation is provided for both 32-bit and 64-bit processes.
  *
  * Care is taken to appropriately emulate the results when segmentation is
  * used. That is, rather than relying on USER_DS and USER_CS, the function
@@ -63,17 +61,18 @@
  * application uses a local descriptor table.
  */
 
-#define UMIP_DUMMY_GDT_BASE 0xfffe0000
-#define UMIP_DUMMY_IDT_BASE 0xffff0000
+#define UMIP_DUMMY_GDT_BASE 0xfffffffffffe0000ULL
+#define UMIP_DUMMY_IDT_BASE 0xffffffffffff0000ULL
 
 /*
  * The SGDT and SIDT instructions store the contents of the global descriptor
  * table and interrupt table registers, respectively. The destination is a
  * memory operand of X+2 bytes. X bytes are used to store the base address of
- * the table and 2 bytes are used to store the limit. In 32-bit processes, the
- * only processes for which emulation is provided, X has a value of 4.
+ * the table and 2 bytes are used to store the limit. In 32-bit processes X
+ * has a value of 4, in 64-bit processes X has a value of 8.
  */
-#define UMIP_GDT_IDT_BASE_SIZE 4
+#define UMIP_GDT_IDT_BASE_SIZE_64BIT 8
+#define UMIP_GDT_IDT_BASE_SIZE_32BIT 4
 #define UMIP_GDT_IDT_LIMIT_SIZE 2
 
 #define	UMIP_INST_SGDT	0	/* 0F 01 /0 */
@@ -189,6 +188,7 @@ static int identify_insn(struct insn *insn)
  * @umip_inst:	A constant indicating the instruction to emulate
  * @data:	Buffer into which the dummy result is stored
  * @data_size:	Size of the emulated result
+ * @x86_64:	true if process is 64-bit, false otherwise
  *
  * Emulate an instruction protected by UMIP and provide a dummy result. The
  * result of the emulation is saved in @data. The size of the results depends
@@ -202,11 +202,8 @@ static int identify_insn(struct insn *insn)
  * 0 on success, -EINVAL on error while emulating.
  */
 static int emulate_umip_insn(struct insn *insn, int umip_inst,
-			     unsigned char *data, int *data_size)
+			     unsigned char *data, int *data_size, bool x86_64)
 {
-	unsigned long dummy_base_addr, dummy_value;
-	unsigned short dummy_limit = 0;
-
 	if (!data || !data_size || !insn)
 		return -EINVAL;
 	/*
@@ -219,6 +216,9 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst,
 	 * is always returned irrespective of the operand size.
 	 */
 	if (umip_inst == UMIP_INST_SGDT || umip_inst == UMIP_INST_SIDT) {
+		u64 dummy_base_addr;
+		u16 dummy_limit = 0;
+
 		/* SGDT and SIDT do not use registers operands. */
 		if (X86_MODRM_MOD(insn->modrm.value) == 3)
 			return -EINVAL;
@@ -228,13 +228,24 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst,
 		else
 			dummy_base_addr = UMIP_DUMMY_IDT_BASE;
 
-		*data_size = UMIP_GDT_IDT_LIMIT_SIZE + UMIP_GDT_IDT_BASE_SIZE;
+		/*
+		 * 64-bit processes use the entire dummy base address.
+		 * 32-bit processes use the lower 32 bits of the base address.
+		 * dummy_base_addr is always 64 bits, but we memcpy the correct
+		 * number of bytes from it to the destination.
+		 */
+		if (x86_64)
+			*data_size = UMIP_GDT_IDT_BASE_SIZE_64BIT;
+		else
+			*data_size = UMIP_GDT_IDT_BASE_SIZE_32BIT;
+
+		memcpy(data + 2, &dummy_base_addr, *data_size);
 
-		memcpy(data + 2, &dummy_base_addr, UMIP_GDT_IDT_BASE_SIZE);
+		*data_size += UMIP_GDT_IDT_LIMIT_SIZE;
 		memcpy(data, &dummy_limit, UMIP_GDT_IDT_LIMIT_SIZE);
 
 	} else if (umip_inst == UMIP_INST_SMSW) {
-		dummy_value = CR0_STATE;
+		unsigned long dummy_value = CR0_STATE;
 
 		/*
 		 * Even though the CR0 register has 4 bytes, the number
@@ -290,11 +301,10 @@ static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs)
  * fixup_umip_exception() - Fixup a general protection fault caused by UMIP
  * @regs:	Registers as saved when entering the #GP handler
  *
- * The instructions sgdt, sidt, str, smsw, sldt cause a general protection
- * fault if executed with CPL > 0 (i.e., from user space). If the offending
- * user-space process is not in long mode, this function fixes the exception
- * up and provides dummy results for sgdt, sidt and smsw; str and sldt are not
- * fixed up. Also long mode user-space processes are not fixed up.
+ * The instructions SGDT, SIDT, STR, SMSW and SLDT cause a general protection
+ * fault if executed with CPL > 0 (i.e., from user space). This function fixes
+ * the exception up and provides dummy results for SGDT, SIDT and SMSW; STR
+ * and SLDT are not fixed up.
  *
  * If operands are memory addresses, results are copied to user-space memory as
  * indicated by the instruction pointed by eIP using the registers indicated in
@@ -373,13 +383,14 @@ bool fixup_umip_exception(struct pt_regs *regs)
 	umip_pr_warning(regs, "%s instruction cannot be used by applications.\n",
 			umip_insns[umip_inst]);
 
-	/* Do not emulate SLDT, STR or user long mode processes. */
-	if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT || user_64bit_mode(regs))
+	/* Do not emulate (spoof) SLDT or STR. */
+	if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT)
 		return false;
 
 	umip_pr_warning(regs, "For now, expensive software emulation returns the result.\n");
 
-	if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size))
+	if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size,
+			      user_64bit_mode(regs)))
 		return false;
 
 	/*

arch/x86/lib/copy_user_64.S

@@ -33,7 +33,7 @@
 102:
 	.section .fixup,"ax"
 103:	addl %ecx,%edx			/* ecx is zerorest also */
-	jmp copy_user_handle_tail
+	jmp .Lcopy_user_handle_tail
 	.previous
 
 	_ASM_EXTABLE_UA(100b, 103b)
@@ -113,7 +113,7 @@ ENTRY(copy_user_generic_unrolled)
 40:	leal (%rdx,%rcx,8),%edx
 	jmp 60f
 50:	movl %ecx,%edx
-60:	jmp copy_user_handle_tail /* ecx is zerorest also */
+60:	jmp .Lcopy_user_handle_tail /* ecx is zerorest also */
 	.previous
 
 	_ASM_EXTABLE_UA(1b, 30b)
@@ -177,7 +177,7 @@ ENTRY(copy_user_generic_string)
 	.section .fixup,"ax"
 11:	leal (%rdx,%rcx,8),%ecx
 12:	movl %ecx,%edx		/* ecx is zerorest also */
-	jmp copy_user_handle_tail
+	jmp .Lcopy_user_handle_tail
 	.previous
 
 	_ASM_EXTABLE_UA(1b, 11b)
@@ -210,7 +210,7 @@ ENTRY(copy_user_enhanced_fast_string)
 
 	.section .fixup,"ax"
 12:	movl %ecx,%edx		/* ecx is zerorest also */
-	jmp copy_user_handle_tail
+	jmp .Lcopy_user_handle_tail
 	.previous
 
 	_ASM_EXTABLE_UA(1b, 12b)
@@ -231,7 +231,7 @@ EXPORT_SYMBOL(copy_user_enhanced_fast_string)
  * eax uncopied bytes or 0 if successful.
  */
 ALIGN;
-copy_user_handle_tail:
+.Lcopy_user_handle_tail:
 	movl %edx,%ecx
 1:	rep movsb
 2:	mov %ecx,%eax
@@ -239,7 +239,7 @@ copy_user_handle_tail:
 	ret
 
 	_ASM_EXTABLE_UA(1b, 2b)
-END(copy_user_handle_tail)
+END(.Lcopy_user_handle_tail)
 
 /*
  * copy_user_nocache - Uncached memory copy with exception handling
@@ -364,7 +364,7 @@ ENTRY(__copy_user_nocache)
 	movl %ecx,%edx
 .L_fixup_handle_tail:
 	sfence
-	jmp copy_user_handle_tail
+	jmp .Lcopy_user_handle_tail
 	.previous
 
 	_ASM_EXTABLE_UA(1b, .L_fixup_4x8b_copy)

arch/x86/lib/getuser.S

@@ -115,7 +115,7 @@ ENDPROC(__get_user_8)
 EXPORT_SYMBOL(__get_user_8)
 
 
-bad_get_user_clac:
+.Lbad_get_user_clac:
 	ASM_CLAC
 bad_get_user:
 	xor %edx,%edx
@@ -123,7 +123,7 @@ bad_get_user:
 	ret
 
 #ifdef CONFIG_X86_32
-bad_get_user_8_clac:
+.Lbad_get_user_8_clac:
 	ASM_CLAC
 bad_get_user_8:
 	xor %edx,%edx
@@ -132,12 +132,12 @@ bad_get_user_8:
 	ret
 #endif
 
-	_ASM_EXTABLE_UA(1b, bad_get_user_clac)
-	_ASM_EXTABLE_UA(2b, bad_get_user_clac)
-	_ASM_EXTABLE_UA(3b, bad_get_user_clac)
+	_ASM_EXTABLE_UA(1b, .Lbad_get_user_clac)
+	_ASM_EXTABLE_UA(2b, .Lbad_get_user_clac)
+	_ASM_EXTABLE_UA(3b, .Lbad_get_user_clac)
 #ifdef CONFIG_X86_64
-	_ASM_EXTABLE_UA(4b, bad_get_user_clac)
+	_ASM_EXTABLE_UA(4b, .Lbad_get_user_clac)
 #else
-	_ASM_EXTABLE_UA(4b, bad_get_user_8_clac)
-	_ASM_EXTABLE_UA(5b, bad_get_user_8_clac)
+	_ASM_EXTABLE_UA(4b, .Lbad_get_user_8_clac)
+	_ASM_EXTABLE_UA(5b, .Lbad_get_user_8_clac)
 #endif

arch/x86/lib/putuser.S

@@ -37,7 +37,7 @@
 ENTRY(__put_user_1)
 	ENTER
 	cmp TASK_addr_limit(%_ASM_BX),%_ASM_CX
-	jae bad_put_user
+	jae .Lbad_put_user
 	ASM_STAC
 1:	movb %al,(%_ASM_CX)
 	xor %eax,%eax
@@ -51,7 +51,7 @@ ENTRY(__put_user_2)
 	mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
 	sub $1,%_ASM_BX
 	cmp %_ASM_BX,%_ASM_CX
-	jae bad_put_user
+	jae .Lbad_put_user
 	ASM_STAC
 2:	movw %ax,(%_ASM_CX)
 	xor %eax,%eax
@@ -65,7 +65,7 @@ ENTRY(__put_user_4)
 	mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
 	sub $3,%_ASM_BX
 	cmp %_ASM_BX,%_ASM_CX
-	jae bad_put_user
+	jae .Lbad_put_user
 	ASM_STAC
 3:	movl %eax,(%_ASM_CX)
 	xor %eax,%eax
@@ -79,7 +79,7 @@ ENTRY(__put_user_8)
 	mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
 	sub $7,%_ASM_BX
 	cmp %_ASM_BX,%_ASM_CX
-	jae bad_put_user
+	jae .Lbad_put_user
 	ASM_STAC
 4:	mov %_ASM_AX,(%_ASM_CX)
 #ifdef CONFIG_X86_32
@@ -91,16 +91,16 @@ ENTRY(__put_user_8)
 ENDPROC(__put_user_8)
 EXPORT_SYMBOL(__put_user_8)
 
-bad_put_user_clac:
+.Lbad_put_user_clac:
 	ASM_CLAC
-bad_put_user:
+.Lbad_put_user:
 	movl $-EFAULT,%eax
 	RET
 
-	_ASM_EXTABLE_UA(1b, bad_put_user_clac)
-	_ASM_EXTABLE_UA(2b, bad_put_user_clac)
-	_ASM_EXTABLE_UA(3b, bad_put_user_clac)
-	_ASM_EXTABLE_UA(4b, bad_put_user_clac)
+	_ASM_EXTABLE_UA(1b, .Lbad_put_user_clac)
+	_ASM_EXTABLE_UA(2b, .Lbad_put_user_clac)
+	_ASM_EXTABLE_UA(3b, .Lbad_put_user_clac)
+	_ASM_EXTABLE_UA(4b, .Lbad_put_user_clac)
 #ifdef CONFIG_X86_32
-	_ASM_EXTABLE_UA(5b, bad_put_user_clac)
+	_ASM_EXTABLE_UA(5b, .Lbad_put_user_clac)
 #endif