Automatically merging tracking-llvm into merge-linux-linaro

Conflicting files:

24 files changed, 133 insertions, 79 deletions

diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 510d46e9aba6..439615dca6e0 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -26,6 +26,10 @@ GZFLAGS		:=-9
 # Never generate .eh_frame
 KBUILD_CFLAGS	+= $(call cc-option,-fno-dwarf2-cfi-asm)
 
+ifeq ($(COMPILER),clang)
+KBUILD_CFLAGS += -Wa,-mno-warn-deprecated
+endif
+
 # Do not use arch/arm/defconfig - it's always outdated.
 # Select a platform tht is kept up-to-date
 KBUILD_DEFCONFIG := versatile_defconfig
@@ -37,15 +41,15 @@ KBUILD_CFLAGS	+= $(call cc-option,-mno-unaligned-access)
 endif
 
 ifeq ($(CONFIG_FRAME_POINTER),y)
-KBUILD_CFLAGS	+=-fno-omit-frame-pointer -mapcs -mno-sched-prolog
+KBUILD_CFLAGS	+=-fno-omit-frame-pointer $(call cc-option,-mapcs,) $(call cc-option,-mno-sched-prolog,)
 endif
 
 ifeq ($(CONFIG_CPU_BIG_ENDIAN),y)
-KBUILD_CPPFLAGS	+= -mbig-endian
+KBUILD_CPPFLAGS	+= $(call cc-option,-mbig-endian)
 AS		+= -EB
 LD		+= -EB
 else
-KBUILD_CPPFLAGS	+= -mlittle-endian
+KBUILD_CPPFLAGS	+= $(call cc-option,-mlittle-endian)
 AS		+= -EL
 LD		+= -EL
 endif
@@ -94,7 +98,7 @@ tune-$(CONFIG_CPU_V6K)		=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
 tune-y := $(tune-y)
 
 ifeq ($(CONFIG_AEABI),y)
-CFLAGS_ABI	:=-mabi=aapcs-linux -mno-thumb-interwork -mfpu=vfp
+CFLAGS_ABI	:=-mabi=aapcs-linux $(call cc-option,-mno-thumb-interwork,) -mfpu=vfp
 else
 CFLAGS_ABI	:=$(call cc-option,-mapcs-32,-mabi=apcs-gnu) $(call cc-option,-mno-thumb-interwork,)
 endif
@@ -118,7 +122,7 @@ AFLAGS_ISA	:=$(CFLAGS_ISA)
 endif
 
 # Need -Uarm for gcc < 3.x
-KBUILD_CFLAGS	+=$(CFLAGS_ABI) $(CFLAGS_ISA) $(arch-y) $(tune-y) $(call cc-option,-mshort-load-bytes,$(call cc-option,-malignment-traps,)) -msoft-float -Uarm
+KBUILD_CFLAGS	+=$(CFLAGS_ABI) $(CFLAGS_ISA) $(arch-y) $(tune-y) $(call cc-option,-mshort-load-bytes,$(call cc-option,-malignment-traps,)) -msoft-float $(call cc-option, -Uarm,)
 KBUILD_AFLAGS	+=$(CFLAGS_ABI) $(AFLAGS_ISA) $(arch-y) $(tune-y) -include asm/unified.h -msoft-float
 
 CHECKFLAGS	+= -D__arm__
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 3ea230aa94b7..b7a39fbebad7 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -123,7 +123,7 @@ ORIG_CFLAGS := $(KBUILD_CFLAGS)
 KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
 endif
 
-ccflags-y := -fpic -mno-single-pic-base -fno-builtin -I$(obj)
+ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin -I$(obj)
 asflags-y := -DZIMAGE
 
 # Supply kernel BSS size to the decompressor via a linker symbol.
diff --git a/arch/arm/firmware/trusted_foundations.c b/arch/arm/firmware/trusted_foundations.c
index 3fb1b5a1dce9..f319c3fa0fe5 100644
--- a/arch/arm/firmware/trusted_foundations.c
+++ b/arch/arm/firmware/trusted_foundations.c
@@ -31,14 +31,11 @@
 
 static unsigned long cpu_boot_addr;
 
-static void __naked tf_generic_smc(u32 type, u32 arg1, u32 arg2)
+static inline void tf_generic_smc(u32 type, u32 arg1, u32 arg2)
 {
 	asm volatile(
 		".arch_extension	sec\n\t"
 		"stmfd	sp!, {r4 - r11, lr}\n\t"
-		__asmeq("%0", "r0")
-		__asmeq("%1", "r1")
-		__asmeq("%2", "r2")
 		"mov	r3, #0\n\t"
 		"mov	r4, #0\n\t"
 		"smc	#0\n\t"
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 72812a1f3d1c..32a0716bdef1 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -91,6 +91,11 @@ struct thread_info {
 register unsigned long current_stack_pointer asm ("sp");
 
 /*
+ * how to get the current stack pointer in C
+ */
+register unsigned long current_stack_pointer asm ("sp");
+
+/*
  * how to get the thread information struct from C
  */
 static inline struct thread_info *current_thread_info(void) __attribute_const__;
diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c
index f73891b6b730..824809eb8775 100644
--- a/arch/arm/kernel/psci.c
+++ b/arch/arm/kernel/psci.c
@@ -78,31 +78,33 @@ static u32 psci_power_state_pack(struct psci_power_state state)
 static noinline int __invoke_psci_fn_hvc(u32 function_id, u32 arg0, u32 arg1,
 					 u32 arg2)
 {
+	register u32 function_id_r0 asm ("r0") = function_id;
+	register u32 arg0_r1 asm ("r1") = arg0;
+	register u32 arg1_r2 asm ("r2") = arg1;
+	register u32 arg2_r3 asm ("r3") = arg2;
+
 	asm volatile(
-			__asmeq("%0", "r0")
-			__asmeq("%1", "r1")
-			__asmeq("%2", "r2")
-			__asmeq("%3", "r3")
 			__HVC(0)
-		: "+r" (function_id)
-		: "r" (arg0), "r" (arg1), "r" (arg2));
+		: "+r" (function_id_r0)
+		: "r" (arg0_r1), "r" (arg1_r2), "r" (arg2_r3));
 
-	return function_id;
+	return function_id_r0;
 }
 
 static noinline int __invoke_psci_fn_smc(u32 function_id, u32 arg0, u32 arg1,
 					 u32 arg2)
 {
+	register u32 function_id_r0 asm ("r0") = function_id;
+	register u32 arg0_r1 asm ("r1") = arg0;
+	register u32 arg1_r2 asm ("r2") = arg1;
+	register u32 arg2_r3 asm ("r3") = arg2;
+
 	asm volatile(
-			__asmeq("%0", "r0")
-			__asmeq("%1", "r1")
-			__asmeq("%2", "r2")
-			__asmeq("%3", "r3")
 			__SMC(0)
-		: "+r" (function_id)
-		: "r" (arg0), "r" (arg1), "r" (arg2));
+		: "+r" (function_id_r0)
+		: "r" (arg0_r1), "r" (arg1_r2), "r" (arg2_r3));
 
-	return function_id;
+	return function_id_r0;
 }
 
 static int psci_get_version(void)
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index d8a780799506..6c7a5b715584 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -15,6 +15,10 @@ lib-y		:= backtrace.o changebit.o csumipv6.o csumpartial.o   \
 		   io-readsb.o io-writesb.o io-readsl.o io-writesl.o  \
 		   call_with_stack.o bswapsdi2.o
 
+ifeq ($(COMPILER),clang)
+lib-y += eabi.o
+endif
+
 mmu-y		:= clear_user.o copy_page.o getuser.o putuser.o       \
 		   copy_from_user.o copy_to_user.o
 
diff --git a/arch/arm/lib/eabi.c b/arch/arm/lib/eabi.c
new file mode 100644
index 000000000000..636a403c9579
--- /dev/null
+++ b/arch/arm/lib/eabi.c
@@ -0,0 +1,28 @@
+/*
+ * EABI routines
+ *
+ *  Copyright (C) 2012  Mark Charlebois
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/export.h>
+
+void __aeabi_memcpy(void *dest, const void *src, size_t n)
+{
+	(void)memcpy(dest, src, n);
+}
+EXPORT_SYMBOL(__aeabi_memcpy);
+
+void __aeabi_memmove(void *dest, const void *src, size_t n)
+{
+	(void)memmove(dest, src, n);
+}
+EXPORT_SYMBOL(__aeabi_memmove);
+
+void __aeabi_memset(void *s, size_t n, int c)
+{
+	(void)memset(s, c, n);
+}
+EXPORT_SYMBOL(__aeabi_memset);
diff --git a/arch/arm/mach-bcm/bcm_kona_smc.c b/arch/arm/mach-bcm/bcm_kona_smc.c
index a55a7ecf146a..3937bd5d452f 100644
--- a/arch/arm/mach-bcm/bcm_kona_smc.c
+++ b/arch/arm/mach-bcm/bcm_kona_smc.c
@@ -106,9 +106,14 @@ int __init bcm_kona_smc_init(void)
  * request result appropriately.  This result value is found in r0
  * when the "smc" request completes.
  */
+#ifdef __clang__
+#define R12	"r12"
+#else  /* !__clang__ */
+#define R12	"ip"	/* gcc calls r12 "ip" */
+#endif /* !__clang__ */
 static int bcm_kona_do_smc(u32 service_id, u32 buffer_phys)
 {
-	register u32 ip asm("ip");	/* Also called r12 */
+	register u32 ip asm(R12);	/* Also called r12 */
 	register u32 r0 asm("r0");
 	register u32 r4 asm("r4");
 	register u32 r5 asm("r5");
@@ -120,7 +125,7 @@ static int bcm_kona_do_smc(u32 service_id, u32 buffer_phys)
 
 	asm volatile (
 		/* Make sure we got the registers we want */
-		__asmeq("%0", "ip")
+		__asmeq("%0", R12)
 		__asmeq("%1", "r0")
 		__asmeq("%2", "r4")
 		__asmeq("%3", "r5")
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 9b4f29e595a4..da44697a4b06 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -697,7 +697,7 @@ config SWP_EMULATE
 
 config CPU_BIG_ENDIAN
 	bool "Build big-endian kernel"
-	depends on ARCH_SUPPORTS_BIG_ENDIAN
+	depends on ARCH_SUPPORTS_BIG_ENDIAN && BROKEN
 	help
 	  Say Y if you plan on running a kernel in big-endian mode.
 	  Note that your board must be properly built and your board
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index abb79b3cfcfe..574851096072 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -18,7 +18,7 @@ obj-$(CONFIG_CRYPTO_GHASH_ARM64_CE) += ghash-ce.o
 ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o
 
 obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
-CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto
+CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto -Wa,-march=armv8-a+crypto
 
 obj-$(CONFIG_CRYPTO_AES_ARM64_CE_CCM) += aes-ce-ccm.o
 aes-ce-ccm-y := aes-ce-ccm-glue.o aes-ce-ccm-core.o
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 5f750dc96e0f..9e5ed17447ca 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -108,7 +108,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	int ret = 0;
 	u32 val, tmp;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+	/* compiler may optimize uaddr to xzr if all uses are 0 which fails */
+	if (uaddr == 0 || !access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 20e9591a60cf..42ca271b6c60 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -146,13 +146,13 @@ extern struct task_struct *cpu_switch_to(struct task_struct *prev,
 #define ARCH_HAS_PREFETCH
 static inline void prefetch(const void *ptr)
 {
-	asm volatile("prfm pldl1keep, %a0\n" : : "p" (ptr));
+	asm volatile("prfm pldl1keep, [%x0]\n" : : "r" (ptr));
 }
 
 #define ARCH_HAS_PREFETCHW
 static inline void prefetchw(const void *ptr)
 {
-	asm volatile("prfm pstl1keep, %a0\n" : : "p" (ptr));
+	asm volatile("prfm pstl1keep, [%x0]\n" : : "r" (ptr));
 }
 
 #define ARCH_HAS_SPINLOCK_PREFETCH
diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index 0cae4595e985..68acc034a901 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -202,12 +202,12 @@
 	.word	0x41600021 | (\reg << 16)
 	.endm
 
-	.macro	MFTR	rt=0, rd=0, u=0, sel=0
-	 .word	0x41000000 | (\rt << 16) | (\rd << 11) | (\u << 5) | (\sel)
+	.macro	MFTR	rt=0, rd=0, _u=0, sel=0
+	 .word	0x41000000 | (\rt << 16) | (\rd << 11) | (\_u << 5) | (\sel)
 	.endm
 
-	.macro	MTTR	rt=0, rd=0, u=0, sel=0
-	 .word	0x41800000 | (\rt << 16) | (\rd << 11) | (\u << 5) | (\sel)
+	.macro	MTTR	rt=0, rd=0, _u=0, sel=0
+	 .word	0x41800000 | (\rt << 16) | (\rd << 11) | (\_u << 5) | (\sel)
 	.endm
 
 #ifdef TOOLCHAIN_SUPPORTS_MSA
diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index 5c585c5c1c3e..966c36a9391b 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -215,7 +215,7 @@ static inline __sum16 ip_compute_csum(const void *buff, int len)
 #define _HAVE_ARCH_IPV6_CSUM
 static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 					  const struct in6_addr *daddr,
-					  __u32 len, unsigned short proto,
+					  __u32 len, __u32 proto,
 					  __wsum sum)
 {
 	__asm__(
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 55ed6602204c..397ae940bcee 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -55,11 +55,11 @@ struct thread_info {
 #define init_stack		(init_thread_union.stack)
 
 /* How to get the thread information struct from C.  */
+register struct thread_info *current_gp_register asm("$28");
+
 static inline struct thread_info *current_thread_info(void)
 {
-	register struct thread_info *__current_thread_info __asm__("$28");
-
-	return __current_thread_info;
+	return current_gp_register;
 }
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h
index fc0cf5ac0cf7..368dad88dbbc 100644
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@@ -915,7 +915,7 @@ union mips_instruction {
 };
 
 union mips16e_instruction {
-	unsigned int full : 16;
+	unsigned short full;
 	struct m16e_rr rr;
 	struct m16e_jal jal;
 	struct m16e_i64 i64;
diff --git a/arch/mips/math-emu/dp_add.c b/arch/mips/math-emu/dp_add.c
index 7f64577df984..31d31de1f6cb 100644
--- a/arch/mips/math-emu/dp_add.c
+++ b/arch/mips/math-emu/dp_add.c
@@ -150,8 +150,8 @@ union ieee754dp ieee754dp_add(union ieee754dp x, union ieee754dp y)
 		 * leaving result in xm, xs and xe.
 		 */
 		xm = xm + ym;
-		xe = xe;
-		xs = xs;
+		/* xe does not change */
+		/* xs does not change */
 
 		if (xm >> (DP_FBITS + 1 + 3)) { /* carry out */
 			xm = XDPSRS1(xm);
@@ -160,11 +160,11 @@ union ieee754dp ieee754dp_add(union ieee754dp x, union ieee754dp y)
 	} else {
 		if (xm >= ym) {
 			xm = xm - ym;
-			xe = xe;
-			xs = xs;
+			/* xe does not change */
+			/* xs does not change */
 		} else {
 			xm = ym - xm;
-			xe = xe;
+			/* xe does not change */
 			xs = ys;
 		}
 		if (xm == 0)
diff --git a/arch/mips/math-emu/dp_sub.c b/arch/mips/math-emu/dp_sub.c
index 7a174029043a..5a109735cb50 100644
--- a/arch/mips/math-emu/dp_sub.c
+++ b/arch/mips/math-emu/dp_sub.c
@@ -153,8 +153,8 @@ union ieee754dp ieee754dp_sub(union ieee754dp x, union ieee754dp y)
 		/* generate 28 bit result of adding two 27 bit numbers
 		 */
 		xm = xm + ym;
-		xe = xe;
-		xs = xs;
+		/* xe does not change */
+		/* xs does not change */
 
 		if (xm >> (DP_FBITS + 1 + 3)) { /* carry out */
 			xm = XDPSRS1(xm);	/* shift preserving sticky */
@@ -163,11 +163,11 @@ union ieee754dp ieee754dp_sub(union ieee754dp x, union ieee754dp y)
 	} else {
 		if (xm >= ym) {
 			xm = xm - ym;
-			xe = xe;
-			xs = xs;
+			/* xe does not change */
+			/* xs does not change */
 		} else {
 			xm = ym - xm;
-			xe = xe;
+			/* xe does not change */
 			xs = ys;
 		}
 		if (xm == 0) {
diff --git a/arch/mips/math-emu/sp_add.c b/arch/mips/math-emu/sp_add.c
index 2d84d460cb67..18e71f517a1c 100644
--- a/arch/mips/math-emu/sp_add.c
+++ b/arch/mips/math-emu/sp_add.c
@@ -148,8 +148,8 @@ union ieee754sp ieee754sp_add(union ieee754sp x, union ieee754sp y)
 		 * leaving result in xm, xs and xe.
 		 */
 		xm = xm + ym;
-		xe = xe;
-		xs = xs;
+		/* xe does not change */
+		/* xs does not change */
 
 		if (xm >> (SP_FBITS + 1 + 3)) { /* carry out */
 			SPXSRSX1();
@@ -157,11 +157,11 @@ union ieee754sp ieee754sp_add(union ieee754sp x, union ieee754sp y)
 	} else {
 		if (xm >= ym) {
 			xm = xm - ym;
-			xe = xe;
-			xs = xs;
+			/* xe does not change */
+			/* xs does not change */
 		} else {
 			xm = ym - xm;
-			xe = xe;
+			/* xe does not change */
 			xs = ys;
 		}
 		if (xm == 0)
diff --git a/arch/mips/math-emu/sp_sub.c b/arch/mips/math-emu/sp_sub.c
index 8592e49032b8..b3443f5438a7 100644
--- a/arch/mips/math-emu/sp_sub.c
+++ b/arch/mips/math-emu/sp_sub.c
@@ -148,8 +148,8 @@ union ieee754sp ieee754sp_sub(union ieee754sp x, union ieee754sp y)
 		/* generate 28 bit result of adding two 27 bit numbers
 		 */
 		xm = xm + ym;
-		xe = xe;
-		xs = xs;
+		/* xe does not change */
+		/* xs does not change */
 
 		if (xm >> (SP_FBITS + 1 + 3)) { /* carry out */
 			SPXSRSX1();	/* shift preserving sticky */
@@ -157,11 +157,11 @@ union ieee754sp ieee754sp_sub(union ieee754sp x, union ieee754sp y)
 	} else {
 		if (xm >= ym) {
 			xm = xm - ym;
-			xe = xe;
-			xs = xs;
+			/* xe does not change */
+			/* xs does not change */
 		} else {
 			xm = ym - xm;
-			xe = xe;
+			/* xe does not change */
 			xs = ys;
 		}
 		if (xm == 0) {
diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c
index db75d07c3645..7af65046dfad 100644
--- a/arch/x86/boot/memory.c
+++ b/arch/x86/boot/memory.c
@@ -63,8 +63,13 @@ static int detect_memory_e820(void)
 			count = 0;
 			break;
 		}
-
+#ifdef __clang__
+		/* PR18415 */
+		memcpy(desc, &buf, sizeof(*desc));
+		desc++;
+#else
 		*desc++ = buf;
+#endif
 		count++;
 	} while (ireg.ebx && count < ARRAY_SIZE(boot_params.e820_map));
 
diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h
index 725e820602b1..3e07af1d80e3 100644
--- a/arch/x86/boot/string.h
+++ b/arch/x86/boot/string.h
@@ -14,8 +14,10 @@ int memcmp(const void *s1, const void *s2, size_t len);
  * Access builtin version by default. If one needs to use optimized version,
  * do "undef memcpy" in .c file and link against right string.c
  */
+#ifndef __clang__ /* PR18415 */
 #define memcpy(d,s,l) __builtin_memcpy(d,s,l)
 #define memset(d,c,l) __builtin_memset(d,c,l)
 #define memcmp	__builtin_memcmp
+#endif
 
 #endif /* BOOT_STRING_H */
diff --git a/arch/x86/um/ksyms.c b/arch/x86/um/ksyms.c
index 2e8f43ec6214..04aedcecd887 100644
--- a/arch/x86/um/ksyms.c
+++ b/arch/x86/um/ksyms.c
@@ -4,7 +4,7 @@
 
 #ifndef CONFIG_X86_32
 /*XXX: we need them because they would be exported by x86_64 */
-#if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4
+#if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4 || defined(__clang__)
 EXPORT_SYMBOL(memcpy);
 #else
 EXPORT_SYMBOL(__memcpy);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index adca9e2b6553..09e3b5c0e632 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1271,36 +1271,37 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 				 struct mm_struct *mm, unsigned long start,
 				 unsigned long end)
 {
-	struct {
-		struct mmuext_op op;
-#ifdef CONFIG_SMP
-		DECLARE_BITMAP(mask, num_processors);
-#else
-		DECLARE_BITMAP(mask, NR_CPUS);
-#endif
-	} *args;
 	struct multicall_space mcs;
+	struct mmuext_op *op;
+	struct cpumask *mask;
 
 	trace_xen_mmu_flush_tlb_others(cpus, mm, start, end);
 
 	if (cpumask_empty(cpus))
 		return;		/* nothing to do */
 
-	mcs = xen_mc_entry(sizeof(*args));
-	args = mcs.args;
-	args->op.arg2.vcpumask = to_cpumask(args->mask);
+#ifdef CONFIG_SMP
+	mcs = xen_mc_entry(sizeof(struct mmuext_op) + BITS_TO_LONGS(num_processors)*sizeof(unsigned long));
+#else
+	mcs = xen_mc_entry(sizeof(struct mmuext_op) + BITS_TO_LONGS(NR_CPUS)*sizeof(unsigned long));
+#endif
+	/* Extract fields */
+	op = mcs.args;
+	mask = to_cpumask(mcs.args + sizeof(struct mmuext_op));
+
+	op->arg2.vcpumask = mask;
 
 	/* Remove us, and any offline CPUS. */
-	cpumask_and(to_cpumask(args->mask), cpus, cpu_online_mask);
-	cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
+	cpumask_and(mask, cpus, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), mask);
 
-	args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
+	op->cmd = MMUEXT_TLB_FLUSH_MULTI;
 	if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
-		args->op.cmd = MMUEXT_INVLPG_MULTI;
-		args->op.arg1.linear_addr = start;
+		op->cmd = MMUEXT_INVLPG_MULTI;
+		op->arg1.linear_addr = start;
 	}
 
-	MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
+	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
 	xen_mc_issue(PARAVIRT_LAZY_MMU);
 }