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

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (21 commits)
  x86: Fix atomic64_xxx_cx8() functions
  x86: Fix and improve cmpxchg_double{,_local}()
  x86_64, asm: Optimise fls(), ffs() and fls64()
  x86, bitops: Move fls64.h inside __KERNEL__
  x86: Fix and improve percpu_cmpxchg{8,16}b_double()
  x86: Report cpb and eff_freq_ro flags correctly
  x86/i386: Use less assembly in strlen(), speed things up a bit
  x86: Use the same node_distance for 32 and 64-bit
  x86: Fix rflags in FAKE_STACK_FRAME
  x86: Clean up and extend do_int3()
  x86: Call do_notify_resume() with interrupts enabled
  x86/div64: Add a micro-optimization shortcut if base is power of two
  x86-64: Cleanup some assembly entry points
  x86-64: Slightly shorten line system call entry and exit paths
  x86-64: Reduce amount of redundant code generated for invalidate_interruptNN
  x86-64: Slightly shorten int_ret_from_sys_call
  x86, efi: Convert efi_phys_get_time() args to physical addresses
  x86: Default to vsyscall=emulate
  x86-64: Set siginfo and context on vsyscall emulation faults
  x86: consolidate xchg and xadd macros
  ...

1 files changed, 14 insertions, 8 deletions

diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h
index 9a2d644c08ef..ced283ac79df 100644
--- a/arch/x86/include/asm/div64.h
+++ b/arch/x86/include/asm/div64.h
@@ -4,6 +4,7 @@
 #ifdef CONFIG_X86_32
 
 #include <linux/types.h>
+#include <linux/log2.h>
 
 /*
  * do_div() is NOT a C function. It wants to return
@@ -21,15 +22,20 @@
 ({                                                              \
         unsigned long __upper, __low, __high, __mod, __base;    \
         __base = (base);                                        \
-        asm("":"=a" (__low), "=d" (__high) : "A" (n));          \
-        __upper = __high;                                       \
-        if (__high) {                                           \
-                __upper = __high % (__base);                    \
-                __high = __high / (__base);                     \
+        if (__builtin_constant_p(__base) && is_power_of_2(__base)) { \
+                __mod = n & (__base - 1);                       \
+                n >>= ilog2(__base);                            \
+        } else {                                                \
+                asm("" : "=a" (__low), "=d" (__high) : "A" (n));\
+                __upper = __high;                               \
+                if (__high) {                                   \
+                        __upper = __high % (__base);            \
+                        __high = __high / (__base);             \
+                }                                               \
+                asm("divl %2" : "=a" (__low), "=d" (__mod)      \
+                        : "rm" (__base), "0" (__low), "1" (__upper));   \
+                asm("" : "=A" (n) : "a" (__low), "d" (__high)); \
         }                                                       \
-        asm("divl %2":"=a" (__low), "=d" (__mod)                \
-            : "rm" (__base), "0" (__low), "1" (__upper));       \
-        asm("":"=A" (n) : "a" (__low), "d" (__high));           \
         __mod;                                                  \
 })