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

Pull x86/asm changes from Ingo Molnar:
 "The one change that stands out is the alternatives patching change
  that prevents us from ever patching back instructions from SMP to UP:
  this simplifies things and speeds up CPU hotplug.

  Other than that it's smaller fixes, cleanups and improvements."

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86: Unspaghettize do_trap()
  x86_64: Work around old GAS bug
  x86: Use REP BSF unconditionally
  x86: Prefer TZCNT over BFS
  x86/64: Adjust types of temporaries used by ffs()/fls()/fls64()
  x86: Drop unnecessary kernel_eflags variable on 64-bit
  x86/smp: Don't ever patch back to UP if we unplug cpus

4 files changed, 31 insertions, 36 deletions

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 70780689599a..444704c8e186 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -60,7 +60,7 @@ extern void alternatives_smp_module_add(struct module *mod, char *name,
 					void *locks, void *locks_end,
 					void *text, void *text_end);
 extern void alternatives_smp_module_del(struct module *mod);
-extern void alternatives_smp_switch(int smp);
+extern void alternatives_enable_smp(void);
 extern int alternatives_text_reserved(void *start, void *end);
 extern bool skip_smp_alternatives;
 #else
@@ -68,7 +68,7 @@ static inline void alternatives_smp_module_add(struct module *mod, char *name,
 					       void *locks, void *locks_end,
 					       void *text, void *text_end) {}
 static inline void alternatives_smp_module_del(struct module *mod) {}
-static inline void alternatives_smp_switch(int smp) {}
+static inline void alternatives_enable_smp(void) {}
 static inline int alternatives_text_reserved(void *start, void *end)
 {
 	return 0;
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 72f5009deb5a..6dfd0195bb55 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -355,7 +355,7 @@ static int test_bit(int nr, const volatile unsigned long *addr);
  */
 static inline unsigned long __ffs(unsigned long word)
 {
-	asm("bsf %1,%0"
+	asm("rep; bsf %1,%0"
 		: "=r" (word)
 		: "rm" (word));
 	return word;
@@ -369,7 +369,7 @@ static inline unsigned long __ffs(unsigned long word)
  */
 static inline unsigned long ffz(unsigned long word)
 {
-	asm("bsf %1,%0"
+	asm("rep; bsf %1,%0"
 		: "=r" (word)
 		: "r" (~word));
 	return word;
@@ -417,10 +417,9 @@ static inline int ffs(int x)
 	 * We cannot do this on 32 bits because at the very least some
 	 * 486 CPUs did not behave this way.
 	 */
-	long tmp = -1;
 	asm("bsfl %1,%0"
 	    : "=r" (r)
-	    : "rm" (x), "0" (tmp));
+	    : "rm" (x), "0" (-1));
 #elif defined(CONFIG_X86_CMOV)
 	asm("bsfl %1,%0\n\t"
 	    "cmovzl %2,%0"
@@ -459,10 +458,9 @@ static inline int fls(int x)
 	 * We cannot do this on 32 bits because at the very least some
 	 * 486 CPUs did not behave this way.
 	 */
-	long tmp = -1;
 	asm("bsrl %1,%0"
 	    : "=r" (r)
-	    : "rm" (x), "0" (tmp));
+	    : "rm" (x), "0" (-1));
 #elif defined(CONFIG_X86_CMOV)
 	asm("bsrl %1,%0\n\t"
 	    "cmovzl %2,%0"
@@ -490,13 +488,13 @@ static inline int fls(int x)
 #ifdef CONFIG_X86_64
 static __always_inline int fls64(__u64 x)
 {
-	long bitpos = -1;
+	int bitpos = -1;
 	/*
 	 * AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the
 	 * dest reg is undefined if x==0, but their CPU architect says its
 	 * value is written to set it to the same as before.
 	 */
-	asm("bsrq %1,%0"
+	asm("bsrq %1,%q0"
 	    : "+r" (bitpos)
 	    : "rm" (x));
 	return bitpos + 1;
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index a9e3a740f697..7f8422a28a46 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -49,38 +49,36 @@ For 32-bit we have the following conventions - kernel is built with
 #include "dwarf2.h"
 
 /*
- * 64-bit system call stack frame layout defines and helpers, for
- * assembly code (note that the seemingly unnecessary parentheses
- * are to prevent cpp from inserting spaces in expressions that get
- * passed to macros):
+ * 64-bit system call stack frame layout defines and helpers,
+ * for assembly code:
  */
 
-#define R15		  (0)
-#define R14		  (8)
-#define R13		 (16)
-#define R12		 (24)
-#define RBP		 (32)
-#define RBX		 (40)
+#define R15		  0
+#define R14		  8
+#define R13		 16
+#define R12		 24
+#define RBP		 32
+#define RBX		 40
 
 /* arguments: interrupts/non tracing syscalls only save up to here: */
-#define R11		 (48)
-#define R10		 (56)
-#define R9		 (64)
-#define R8		 (72)
-#define RAX		 (80)
-#define RCX		 (88)
-#define RDX		 (96)
-#define RSI		(104)
-#define RDI		(112)
-#define ORIG_RAX	(120)       /* + error_code */
+#define R11		 48
+#define R10		 56
+#define R9		 64
+#define R8		 72
+#define RAX		 80
+#define RCX		 88
+#define RDX		 96
+#define RSI		104
+#define RDI		112
+#define ORIG_RAX	120       /* + error_code */
 /* end of arguments */
 
 /* cpu exception frame or undefined in case of fast syscall: */
-#define RIP		(128)
-#define CS		(136)
-#define EFLAGS		(144)
-#define RSP		(152)
-#define SS		(160)
+#define RIP		128
+#define CS		136
+#define EFLAGS		144
+#define RSP		152
+#define SS		160
 
 #define ARGOFFSET	R11
 #define SWFRAME		ORIG_RAX
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 433d2e5c98a7..b98c0d958ebb 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -423,7 +423,6 @@ DECLARE_INIT_PER_CPU(irq_stack_union);
 
 DECLARE_PER_CPU(char *, irq_stack_ptr);
 DECLARE_PER_CPU(unsigned int, irq_count);
-extern unsigned long kernel_eflags;
 extern asmlinkage void ignore_sysret(void);
 #else	/* X86_64 */
 #ifdef CONFIG_CC_STACKPROTECTOR