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

Pull x86 fixes from Thomas Gleixner:
 "A set of fixes and updates for x86:

   - Address a swiotlb regression which was caused by the recent DMA
     rework and made driver fail because dma_direct_supported() returned
     false

   - Fix a signedness bug in the APIC ID validation which caused invalid
     APIC IDs to be detected as valid thereby bloating the CPU possible
     space.

   - Fix inconsisten config dependcy/select magic for the MFD_CS5535
     driver.

   - Fix a corruption of the physical address space bits when encryption
     has reduced the address space and late cpuinfo updates overwrite
     the reduced bit information with the original value.

   - Dominiks syscall rework which consolidates the architecture
     specific syscall functions so all syscalls can be wrapped with the
     same macros. This allows to switch x86/64 to struct pt_regs based
     syscalls. Extend the clearing of user space controlled registers in
     the entry patch to the lower registers"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/apic: Fix signedness bug in APIC ID validity checks
  x86/cpu: Prevent cpuinfo_x86::x86_phys_bits adjustment corruption
  x86/olpc: Fix inconsistent MFD_CS5535 configuration
  swiotlb: Use dma_direct_supported() for swiotlb_ops
  syscalls/x86: Adapt syscall_wrapper.h to the new syscall stub naming convention
  syscalls/core, syscalls/x86: Rename struct pt_regs-based sys_*() to __x64_sys_*()
  syscalls/core, syscalls/x86: Clean up compat syscall stub naming convention
  syscalls/core, syscalls/x86: Clean up syscall stub naming convention
  syscalls/x86: Extend register clearing on syscall entry to lower registers
  syscalls/x86: Unconditionally enable 'struct pt_regs' based syscalls on x86_64
  syscalls/x86: Use 'struct pt_regs' based syscall calling for IA32_EMULATION and x32
  syscalls/core: Prepare CONFIG_ARCH_HAS_SYSCALL_WRAPPER=y for compat syscalls
  syscalls/x86: Use 'struct pt_regs' based syscall calling convention for 64-bit syscalls
  syscalls/core: Introduce CONFIG_ARCH_HAS_SYSCALL_WRAPPER=y
  x86/syscalls: Don't pointlessly reload the system call number
  x86/mm: Fix documentation of module mapping range with 4-level paging
  x86/cpuid: Switch to 'static const' specifier

Documentation/process/adding-syscalls.rst

@@ -360,7 +360,7 @@ First, the entry in ``arch/x86/entry/syscalls/syscall_32.tbl`` gets an extra
 column to indicate that a 32-bit userspace program running on a 64-bit kernel
 should hit the compat entry point::
 
-    380   i386     xyzzy     sys_xyzzy    compat_sys_xyzzy
+    380   i386     xyzzy     sys_xyzzy    __ia32_compat_sys_xyzzy
 
 Second, you need to figure out what should happen for the x32 ABI version of
 the new system call.  There's a choice here: the layout of the arguments
@@ -373,7 +373,7 @@ the compatibility wrapper::
 
     333   64       xyzzy     sys_xyzzy
     ...
-    555   x32      xyzzy     compat_sys_xyzzy
+    555   x32      xyzzy     __x32_compat_sys_xyzzy
 
 If no pointers are involved, then it is preferable to re-use the 64-bit system
 call for the x32 ABI (and consequently the entry in

Documentation/x86/x86_64/mm.txt

@@ -20,7 +20,7 @@ ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
 ... unused hole ...
 ffffffff80000000 - ffffffff9fffffff (=512 MB)  kernel text mapping, from phys 0
-ffffffffa0000000 - [fixmap start]   (~1526 MB) module mapping space (variable)
+ffffffffa0000000 - fffffffffeffffff (1520 MB) module mapping space
 [fixmap start]   - ffffffffff5fffff kernel-internal fixmap range
 ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI
 ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole

arch/x86/Kconfig

@@ -29,6 +29,7 @@ config X86_64
 	select HAVE_ARCH_SOFT_DIRTY
 	select MODULES_USE_ELF_RELA
 	select X86_DEV_DMA_OPS
+	select ARCH_HAS_SYSCALL_WRAPPER
 
 #
 # Arch settings
@@ -2763,11 +2764,9 @@ config OLPC_XO1_RTC
 
 config OLPC_XO1_SCI
 	bool "OLPC XO-1 SCI extras"
-	depends on OLPC && OLPC_XO1_PM
+	depends on OLPC && OLPC_XO1_PM && GPIO_CS5535=y
 	depends on INPUT=y
 	select POWER_SUPPLY
-	select GPIO_CS5535
-	select MFD_CORE
 	---help---
 	  Add support for SCI-based features of the OLPC XO-1 laptop:
 	   - EC-driven system wakeups

arch/x86/entry/calling.h

@@ -114,7 +114,9 @@ For 32-bit we have the following conventions - kernel is built with
 	pushq   %rsi		/* pt_regs->si */
 	.endif
 	pushq	\rdx		/* pt_regs->dx */
+	xorl	%edx, %edx	/* nospec   dx */
 	pushq   %rcx		/* pt_regs->cx */
+	xorl	%ecx, %ecx	/* nospec   cx */
 	pushq   \rax		/* pt_regs->ax */
 	pushq   %r8		/* pt_regs->r8 */
 	xorl	%r8d, %r8d	/* nospec   r8 */

arch/x86/entry/common.c

@@ -266,14 +266,13 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs)
 }
 
 #ifdef CONFIG_X86_64
-__visible void do_syscall_64(struct pt_regs *regs)
+__visible void do_syscall_64(unsigned long nr, struct pt_regs *regs)
 {
-	struct thread_info *ti = current_thread_info();
-	unsigned long nr = regs->orig_ax;
+	struct thread_info *ti;
 
 	enter_from_user_mode();
 	local_irq_enable();
-
+	ti = current_thread_info();
 	if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY)
 		nr = syscall_trace_enter(regs);
 
@@ -282,11 +281,10 @@ __visible void do_syscall_64(struct pt_regs *regs)
 	 * table.  The only functional difference is the x32 bit in
 	 * regs->orig_ax, which changes the behavior of some syscalls.
 	 */
-	if (likely((nr & __SYSCALL_MASK) < NR_syscalls)) {
-		nr = array_index_nospec(nr & __SYSCALL_MASK, NR_syscalls);
-		regs->ax = sys_call_table[nr](
-			regs->di, regs->si, regs->dx,
-			regs->r10, regs->r8, regs->r9);
+	nr &= __SYSCALL_MASK;
+	if (likely(nr < NR_syscalls)) {
+		nr = array_index_nospec(nr, NR_syscalls);
+		regs->ax = sys_call_table[nr](regs);
 	}
 
 	syscall_return_slowpath(regs);
@@ -321,6 +319,9 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
 
 	if (likely(nr < IA32_NR_syscalls)) {
 		nr = array_index_nospec(nr, IA32_NR_syscalls);
+#ifdef CONFIG_IA32_EMULATION
+		regs->ax = ia32_sys_call_table[nr](regs);
+#else
 		/*
 		 * It's possible that a 32-bit syscall implementation
 		 * takes a 64-bit parameter but nonetheless assumes that
@@ -331,6 +332,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
 			(unsigned int)regs->bx, (unsigned int)regs->cx,
 			(unsigned int)regs->dx, (unsigned int)regs->si,
 			(unsigned int)regs->di, (unsigned int)regs->bp);
+#endif /* CONFIG_IA32_EMULATION */
 	}
 
 	syscall_return_slowpath(regs);

arch/x86/entry/entry_64.S

@@ -233,7 +233,8 @@ GLOBAL(entry_SYSCALL_64_after_hwframe)
 	TRACE_IRQS_OFF
 
 	/* IRQs are off. */
-	movq	%rsp, %rdi
+	movq	%rax, %rdi
+	movq	%rsp, %rsi
 	call	do_syscall_64		/* returns with IRQs disabled */
 
 	TRACE_IRQS_IRETQ		/* we're about to change IF */

arch/x86/entry/entry_64_compat.S

@@ -220,8 +220,11 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe)
 	pushq	%rax			/* pt_regs->orig_ax */
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
+	xorl	%esi, %esi		/* nospec   si */
 	pushq	%rdx			/* pt_regs->dx */
+	xorl	%edx, %edx		/* nospec   dx */
 	pushq	%rbp			/* pt_regs->cx (stashed in bp) */
+	xorl	%ecx, %ecx		/* nospec   cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
 	xorl	%r8d, %r8d		/* nospec   r8 */
@@ -365,8 +368,11 @@ ENTRY(entry_INT80_compat)
 
 	pushq	(%rdi)			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
+	xorl	%esi, %esi		/* nospec   si */
 	pushq	%rdx			/* pt_regs->dx */
+	xorl	%edx, %edx		/* nospec   dx */
 	pushq	%rcx			/* pt_regs->cx */
+	xorl	%ecx, %ecx		/* nospec   cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
 	xorl	%r8d, %r8d		/* nospec   r8 */

arch/x86/entry/syscall_32.c

@@ -7,14 +7,23 @@
 #include <asm/asm-offsets.h>
 #include <asm/syscall.h>
 
-#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
+#ifdef CONFIG_IA32_EMULATION
+/* On X86_64, we use struct pt_regs * to pass parameters to syscalls */
+#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *);
+
+/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */
+extern asmlinkage long sys_ni_syscall(const struct pt_regs *);
+
+#else /* CONFIG_IA32_EMULATION */
+#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
+extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
+#endif /* CONFIG_IA32_EMULATION */
+
 #include <asm/syscalls_32.h>
 #undef __SYSCALL_I386
 
 #define __SYSCALL_I386(nr, sym, qual) [nr] = sym,
 
-extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
-
 __visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = {
 	/*
 	 * Smells like a compiler bug -- it doesn't work

arch/x86/entry/syscall_64.c

@@ -7,14 +7,14 @@
 #include <asm/asm-offsets.h>
 #include <asm/syscall.h>
 
-#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
+/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */
+extern asmlinkage long sys_ni_syscall(const struct pt_regs *);
+#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *);
 #include <asm/syscalls_64.h>
 #undef __SYSCALL_64
 
 #define __SYSCALL_64(nr, sym, qual) [nr] = sym,
 
-extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
-
 asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
 	/*
 	 * Smells like a compiler bug -- it doesn't work

arch/x86/entry/syscalls/syscalltbl.sh

@@ -25,15 +25,27 @@ emit() {
     nr="$2"
     entry="$3"
     compat="$4"
+    umlentry=""
 
     if [ "$abi" = "64" -a -n "$compat" ]; then
 	echo "a compat entry for a 64-bit syscall makes no sense" >&2
 	exit 1
     fi
 
+    # For CONFIG_UML, we need to strip the __x64_sys prefix
+    if [ "$abi" = "64" -a "${entry}" != "${entry#__x64_sys}" ]; then
+	    umlentry="sys${entry#__x64_sys}"
+    fi
+
     if [ -z "$compat" ]; then
-	if [ -n "$entry" ]; then
+	if [ -n "$entry" -a -z "$umlentry" ]; then
 	    syscall_macro "$abi" "$nr" "$entry"
+	elif [ -n "$umlentry" ]; then # implies -n "$entry"
+	    echo "#ifdef CONFIG_X86"
+	    syscall_macro "$abi" "$nr" "$entry"
+	    echo "#else /* CONFIG_UML */"
+	    syscall_macro "$abi" "$nr" "$umlentry"
+	    echo "#endif"
 	fi
     else
 	echo "#ifdef CONFIG_X86_32"

arch/x86/entry/vsyscall/vsyscall_64.c

@@ -127,6 +127,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 	int vsyscall_nr, syscall_nr, tmp;
 	int prev_sig_on_uaccess_err;
 	long ret;
+	unsigned long orig_dx;
 
 	/*
 	 * No point in checking CS -- the only way to get here is a user mode
@@ -227,19 +228,22 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 	ret = -EFAULT;
 	switch (vsyscall_nr) {
 	case 0:
-		ret = sys_gettimeofday(
-			(struct timeval __user *)regs->di,
-			(struct timezone __user *)regs->si);
+		/* this decodes regs->di and regs->si on its own */
+		ret = __x64_sys_gettimeofday(regs);
 		break;
 
 	case 1:
-		ret = sys_time((time_t __user *)regs->di);
+		/* this decodes regs->di on its own */
+		ret = __x64_sys_time(regs);
 		break;
 
 	case 2:
-		ret = sys_getcpu((unsigned __user *)regs->di,
-				 (unsigned __user *)regs->si,
-				 NULL);
+		/* while we could clobber regs->dx, we didn't in the past... */
+		orig_dx = regs->dx;
+		regs->dx = 0;
+		/* this decodes regs->di, regs->si and regs->dx on its own */
+		ret = __x64_sys_getcpu(regs);
+		regs->dx = orig_dx;
 		break;
 	}
 

arch/x86/include/asm/apic.h

@@ -313,7 +313,7 @@ struct apic {
 	/* Probe, setup and smpboot functions */
 	int	(*probe)(void);
 	int	(*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
-	int	(*apic_id_valid)(int apicid);
+	int	(*apic_id_valid)(u32 apicid);
 	int	(*apic_id_registered)(void);
 
 	bool	(*check_apicid_used)(physid_mask_t *map, int apicid);
@@ -486,7 +486,7 @@ static inline unsigned int read_apic_id(void)
 	return apic->get_apic_id(reg);
 }
 
-extern int default_apic_id_valid(int apicid);
+extern int default_apic_id_valid(u32 apicid);
 extern int default_acpi_madt_oem_check(char *, char *);
 extern void default_setup_apic_routing(void);
 

arch/x86/include/asm/syscall.h

@@ -20,9 +20,13 @@
 #include <asm/thread_info.h>	/* for TS_COMPAT */
 #include <asm/unistd.h>
 
+#ifdef CONFIG_X86_64
+typedef asmlinkage long (*sys_call_ptr_t)(const struct pt_regs *);
+#else
 typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long,
 					  unsigned long, unsigned long,
 					  unsigned long, unsigned long);
+#endif /* CONFIG_X86_64 */
 extern const sys_call_ptr_t sys_call_table[];
 
 #if defined(CONFIG_X86_32)

arch/x86/include/asm/syscall_wrapper.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * syscall_wrapper.h - x86 specific wrappers to syscall definitions
+ */
+
+#ifndef _ASM_X86_SYSCALL_WRAPPER_H
+#define _ASM_X86_SYSCALL_WRAPPER_H
+
+/* Mapping of registers to parameters for syscalls on x86-64 and x32 */
+#define SC_X86_64_REGS_TO_ARGS(x, ...)					\
+	__MAP(x,__SC_ARGS						\
+		,,regs->di,,regs->si,,regs->dx				\
+		,,regs->r10,,regs->r8,,regs->r9)			\
+
+/* Mapping of registers to parameters for syscalls on i386 */
+#define SC_IA32_REGS_TO_ARGS(x, ...)					\
+	__MAP(x,__SC_ARGS						\
+	      ,,(unsigned int)regs->bx,,(unsigned int)regs->cx		\
+	      ,,(unsigned int)regs->dx,,(unsigned int)regs->si		\
+	      ,,(unsigned int)regs->di,,(unsigned int)regs->bp)
+
+#ifdef CONFIG_IA32_EMULATION
+/*
+ * For IA32 emulation, we need to handle "compat" syscalls *and* create
+ * additional wrappers (aptly named __ia32_sys_xyzzy) which decode the
+ * ia32 regs in the proper order for shared or "common" syscalls. As some
+ * syscalls may not be implemented, we need to expand COND_SYSCALL in
+ * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this
+ * case as well.
+ */
+#define __IA32_COMPAT_SYS_STUBx(x, name, ...)				\
+	asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs);\
+	ALLOW_ERROR_INJECTION(__ia32_compat_sys##name, ERRNO);		\
+	asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs)\
+	{								\
+		return __se_compat_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\
+	}								\
+
+#define __IA32_SYS_STUBx(x, name, ...)					\
+	asmlinkage long __ia32_sys##name(const struct pt_regs *regs);	\
+	ALLOW_ERROR_INJECTION(__ia32_sys##name, ERRNO);			\
+	asmlinkage long __ia32_sys##name(const struct pt_regs *regs)	\
+	{								\
+		return __se_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\
+	}
+
+/*
+ * To keep the naming coherent, re-define SYSCALL_DEFINE0 to create an alias
+ * named __ia32_sys_*()
+ */
+#define SYSCALL_DEFINE0(sname)					\
+	SYSCALL_METADATA(_##sname, 0);				\
+	asmlinkage long __x64_sys_##sname(void);		\
+	ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO);	\
+	SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname);	\
+	asmlinkage long __x64_sys_##sname(void)
+
+#define COND_SYSCALL(name)						\
+	cond_syscall(__x64_sys_##name);					\
+	cond_syscall(__ia32_sys_##name)
+
+#define SYS_NI(name)							\
+	SYSCALL_ALIAS(__x64_sys_##name, sys_ni_posix_timers);		\
+	SYSCALL_ALIAS(__ia32_sys_##name, sys_ni_posix_timers)
+
+#else /* CONFIG_IA32_EMULATION */
+#define __IA32_COMPAT_SYS_STUBx(x, name, ...)
+#define __IA32_SYS_STUBx(x, fullname, name, ...)
+#endif /* CONFIG_IA32_EMULATION */
+
+
+#ifdef CONFIG_X86_X32
+/*
+ * For the x32 ABI, we need to create a stub for compat_sys_*() which is aware
+ * of the x86-64-style parameter ordering of x32 syscalls. The syscalls common
+ * with x86_64 obviously do not need such care.
+ */
+#define __X32_COMPAT_SYS_STUBx(x, name, ...)				\
+	asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs);\
+	ALLOW_ERROR_INJECTION(__x32_compat_sys##name, ERRNO);		\
+	asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs)\
+	{								\
+		return __se_compat_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\
+	}								\
+
+#else /* CONFIG_X86_X32 */
+#define __X32_COMPAT_SYS_STUBx(x, name, ...)
+#endif /* CONFIG_X86_X32 */
+
+
+#ifdef CONFIG_COMPAT
+/*
+ * Compat means IA32_EMULATION and/or X86_X32. As they use a different
+ * mapping of registers to parameters, we need to generate stubs for each
+ * of them.
+ */
+#define COMPAT_SYSCALL_DEFINEx(x, name, ...)					\
+	static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
+	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
+	__IA32_COMPAT_SYS_STUBx(x, name, __VA_ARGS__)				\
+	__X32_COMPAT_SYS_STUBx(x, name, __VA_ARGS__)				\
+	static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))	\
+	{									\
+		return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\
+	}									\
+	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+
+/*
+ * As some compat syscalls may not be implemented, we need to expand
+ * COND_SYSCALL_COMPAT in kernel/sys_ni.c and COMPAT_SYS_NI in
+ * kernel/time/posix-stubs.c to cover this case as well.
+ */
+#define COND_SYSCALL_COMPAT(name) 					\
+	cond_syscall(__ia32_compat_sys_##name);				\
+	cond_syscall(__x32_compat_sys_##name)
+
+#define COMPAT_SYS_NI(name)						\
+	SYSCALL_ALIAS(__ia32_compat_sys_##name, sys_ni_posix_timers);	\
+	SYSCALL_ALIAS(__x32_compat_sys_##name, sys_ni_posix_timers)
+
+#endif /* CONFIG_COMPAT */
+
+
+/*
+ * Instead of the generic __SYSCALL_DEFINEx() definition, this macro takes
+ * struct pt_regs *regs as the only argument of the syscall stub named
+ * __x64_sys_*(). It decodes just the registers it needs and passes them on to
+ * the __se_sys_*() wrapper performing sign extension and then to the
+ * __do_sys_*() function doing the actual job. These wrappers and functions
+ * are inlined (at least in very most cases), meaning that the assembly looks
+ * as follows (slightly re-ordered for better readability):
+ *
+ * <__x64_sys_recv>:		<-- syscall with 4 parameters
+ *	callq	<__fentry__>
+ *
+ *	mov	0x70(%rdi),%rdi	<-- decode regs->di
+ *	mov	0x68(%rdi),%rsi	<-- decode regs->si
+ *	mov	0x60(%rdi),%rdx	<-- decode regs->dx
+ *	mov	0x38(%rdi),%rcx	<-- decode regs->r10
+ *
+ *	xor	%r9d,%r9d	<-- clear %r9
+ *	xor	%r8d,%r8d	<-- clear %r8
+ *
+ *	callq	__sys_recvfrom	<-- do the actual work in __sys_recvfrom()
+ *				    which takes 6 arguments
+ *
+ *	cltq			<-- extend return value to 64-bit
+ *	retq			<-- return
+ *
+ * This approach avoids leaking random user-provided register content down
+ * the call chain.
+ *
+ * If IA32_EMULATION is enabled, this macro generates an additional wrapper
+ * named __ia32_sys_*() which decodes the struct pt_regs *regs according
+ * to the i386 calling convention (bx, cx, dx, si, di, bp).
+ */
+#define __SYSCALL_DEFINEx(x, name, ...)					\
+	asmlinkage long __x64_sys##name(const struct pt_regs *regs);	\
+	ALLOW_ERROR_INJECTION(__x64_sys##name, ERRNO);			\
+	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
+	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
+	asmlinkage long __x64_sys##name(const struct pt_regs *regs)	\
+	{								\
+		return __se_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\
+	}								\
+	__IA32_SYS_STUBx(x, name, __VA_ARGS__)				\
+	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))	\
+	{								\
+		long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));\
+		__MAP(x,__SC_TEST,__VA_ARGS__);				\
+		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));	\
+		return ret;						\
+	}								\
+	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+
+/*
+ * As the generic SYSCALL_DEFINE0() macro does not decode any parameters for
+ * obvious reasons, and passing struct pt_regs *regs to it in %rdi does not
+ * hurt, we only need to re-define it here to keep the naming congruent to
+ * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() and SYS_NI()
+ * macros to work correctly.
+ */
+#ifndef SYSCALL_DEFINE0
+#define SYSCALL_DEFINE0(sname)					\
+	SYSCALL_METADATA(_##sname, 0);				\
+	asmlinkage long __x64_sys_##sname(void);		\
+	ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO);	\
+	asmlinkage long __x64_sys_##sname(void)
+#endif
+
+#ifndef COND_SYSCALL
+#define COND_SYSCALL(name) cond_syscall(__x64_sys_##name)
+#endif
+
+#ifndef SYS_NI
+#define SYS_NI(name) SYSCALL_ALIAS(__x64_sys_##name, sys_ni_posix_timers);
+#endif
+
+
+/*
+ * For VSYSCALLS, we need to declare these three syscalls with the new
+ * pt_regs-based calling convention for in-kernel use.
+ */
+struct pt_regs;
+asmlinkage long __x64_sys_getcpu(const struct pt_regs *regs);
+asmlinkage long __x64_sys_gettimeofday(const struct pt_regs *regs);
+asmlinkage long __x64_sys_time(const struct pt_regs *regs);
+
+#endif /* _ASM_X86_SYSCALL_WRAPPER_H */

arch/x86/include/asm/syscalls.h

@@ -18,6 +18,12 @@
 /* Common in X86_32 and X86_64 */
 /* kernel/ioport.c */
 long ksys_ioperm(unsigned long from, unsigned long num, int turn_on);
+
+#ifdef CONFIG_X86_32
+/*
+ * These definitions are only valid on pure 32-bit systems; x86-64 uses a
+ * different syscall calling convention
+ */
 asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
 asmlinkage long sys_iopl(unsigned int);
 
@@ -32,7 +38,6 @@ asmlinkage long sys_set_thread_area(struct user_desc __user *);
 asmlinkage long sys_get_thread_area(struct user_desc __user *);
 
 /* X86_32 only */
-#ifdef CONFIG_X86_32
 
 /* kernel/signal.c */
 asmlinkage long sys_sigreturn(void);
@@ -42,15 +47,5 @@ struct vm86_struct;
 asmlinkage long sys_vm86old(struct vm86_struct __user *);
 asmlinkage long sys_vm86(unsigned long, unsigned long);
 
-#else /* CONFIG_X86_32 */
-
-/* X86_64 only */
-/* kernel/process_64.c */
-asmlinkage long sys_arch_prctl(int, unsigned long);
-
-/* kernel/sys_x86_64.c */
-asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long,
-			 unsigned long, unsigned long, unsigned long);
-
 #endif /* CONFIG_X86_32 */
 #endif /* _ASM_X86_SYSCALLS_H */

arch/x86/kernel/acpi/boot.c

@@ -200,7 +200,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
 {
 	struct acpi_madt_local_x2apic *processor = NULL;
 #ifdef CONFIG_X86_X2APIC
-	int apic_id;
+	u32 apic_id;
 	u8 enabled;
 #endif
 
@@ -222,10 +222,13 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end)
 	 * to not preallocating memory for all NR_CPUS
 	 * when we use CPU hotplug.
 	 */
-	if (!apic->apic_id_valid(apic_id) && enabled)
-		printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
-	else
-		acpi_register_lapic(apic_id, processor->uid, enabled);
+	if (!apic->apic_id_valid(apic_id)) {
+		if (enabled)
+			pr_warn(PREFIX "x2apic entry ignored\n");
+		return 0;
+	}
+
+	acpi_register_lapic(apic_id, processor->uid, enabled);
 #else
 	printk(KERN_WARNING PREFIX "x2apic entry ignored\n");
 #endif

arch/x86/kernel/apic/apic_common.c

@@ -40,7 +40,7 @@ int default_check_phys_apicid_present(int phys_apicid)
 	return physid_isset(phys_apicid, phys_cpu_present_map);
 }
 
-int default_apic_id_valid(int apicid)
+int default_apic_id_valid(u32 apicid)
 {
 	return (apicid < 255);
 }

arch/x86/kernel/apic/apic_numachip.c

@@ -56,7 +56,7 @@ static u32 numachip2_set_apic_id(unsigned int id)
 	return id << 24;
 }
 
-static int numachip_apic_id_valid(int apicid)
+static int numachip_apic_id_valid(u32 apicid)
 {
 	/* Trust what bootloader passes in MADT */
 	return 1;