x86: A fast way to check capabilities of the current cpu

Add this_cpu_has() which determines if the current cpu has a certain
ability using a segment prefix and a bit test operation.

For that we need to add bit operations to x86s percpu.h.

Many uses of cpu_has use a pointer passed to a function to determine
the current flags. That is no longer necessary after this patch.

However, this patch only converts the straightforward cases where
cpu_has is used with this_cpu_ptr. The rest is work for later.

-tj: Rolled up patch to add x86_ prefix and use percpu_read() instead
     of percpu_read_stable().

Signed-off-by: Christoph Lameter <cl@linux.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 27 insertions, 0 deletions

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index d475b4398d8b..76042d981596 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -542,6 +542,33 @@ do {									\
         old__;                                                          \
 })
 
+static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
+                        const unsigned long __percpu *addr)
+{
+        unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG;
+
+        return ((1UL << (nr % BITS_PER_LONG)) & percpu_read(*a)) != 0;
+}
+
+static inline int x86_this_cpu_variable_test_bit(int nr,
+                        const unsigned long __percpu *addr)
+{
+        int oldbit;
+
+        asm volatile("bt "__percpu_arg(2)",%1\n\t"
+                        "sbb %0,%0"
+                        : "=r" (oldbit)
+                        : "m" (*(unsigned long *)addr), "Ir" (nr));
+
+        return oldbit;
+}
+
+#define x86_this_cpu_test_bit(nr, addr)                 \
+        (__builtin_constant_p((nr))                     \
+         ? x86_this_cpu_constant_test_bit((nr), (addr)) \
+         : x86_this_cpu_variable_test_bit((nr), (addr)))
+
+
 #include <asm-generic/percpu.h>
 
 /* We can use this directly for local CPU (faster). */