x86, bitops: Change bitops to be native operand size

Change the bitops operation to be naturally "long", i.e. 63 bits on
the 64-bit kernel.  Additional bugs are likely to crop up in the
future.

We already have bugs which machines with > 16 TiB of memory in a
single node, as can happen if memory is interleaved.  The x86 bitop
operations take a signed index, so using an unsigned type is not an
option.

Jim Kukunas measured the effect of this patch on kernel size: it adds
2779 bytes to the allyesconfig kernel.  Some of that probably could be
elided by replacing the inline functions with macros which select the
32-bit type if the index is a 32-bit value, something like:

In that case we could also use "Jr" constraints for the 64-bit
version.

However, this would more than double the amount of code for a
relatively small gain.

Note that we can't use ilog2() for _BITOPS_LONG_SHIFT, as that causes
a recursive header inclusion problem.

The change to constant_test_bit() should both generate better code and
give correct result for negative bit indicies.  As previously written
the compiler had to generate extra code to create the proper wrong
result for negative values.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Jim Kukunas <james.t.kukunas@intel.com>
Link: http://lkml.kernel.org/n/tip-z61ofiwe90xeyb461o72h8ya@git.kernel.org

1 files changed, 12 insertions, 12 deletions

diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h
index 9d09b4073b60..05af3b31d522 100644
--- a/arch/x86/include/asm/sync_bitops.h
+++ b/arch/x86/include/asm/sync_bitops.h
@@ -26,9 +26,9 @@
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void sync_set_bit(int nr, volatile unsigned long *addr)
+static inline void sync_set_bit(long nr, volatile unsigned long *addr)
 {
-        asm volatile("lock; btsl %1,%0"
+        asm volatile("lock; bts %1,%0"
                      : "+m" (ADDR)
                      : "Ir" (nr)
                      : "memory");
@@ -44,9 +44,9 @@ static inline void sync_set_bit(int nr, volatile unsigned long *addr)
  * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
  * in order to ensure changes are visible on other processors.
  */
-static inline void sync_clear_bit(int nr, volatile unsigned long *addr)
+static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
 {
-        asm volatile("lock; btrl %1,%0"
+        asm volatile("lock; btr %1,%0"
                      : "+m" (ADDR)
                      : "Ir" (nr)
                      : "memory");
@@ -61,9 +61,9 @@ static inline void sync_clear_bit(int nr, volatile unsigned long *addr)
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void sync_change_bit(int nr, volatile unsigned long *addr)
+static inline void sync_change_bit(long nr, volatile unsigned long *addr)
 {
-        asm volatile("lock; btcl %1,%0"
+        asm volatile("lock; btc %1,%0"
                      : "+m" (ADDR)
                      : "Ir" (nr)
                      : "memory");
@@ -77,11 +77,11 @@ static inline void sync_change_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int sync_test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
 {
         int oldbit;
 
-        asm volatile("lock; btsl %2,%1\n\tsbbl %0,%0"
+        asm volatile("lock; bts %2,%1\n\tsbbl %0,%0"
                      : "=r" (oldbit), "+m" (ADDR)
                      : "Ir" (nr) : "memory");
         return oldbit;
@@ -95,11 +95,11 @@ static inline int sync_test_and_set_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int sync_test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
         int oldbit;
 
-        asm volatile("lock; btrl %2,%1\n\tsbbl %0,%0"
+        asm volatile("lock; btr %2,%1\n\tsbbl %0,%0"
                      : "=r" (oldbit), "+m" (ADDR)
                      : "Ir" (nr) : "memory");
         return oldbit;
@@ -113,11 +113,11 @@ static inline int sync_test_and_clear_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int sync_test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr)
 {
         int oldbit;
 
-        asm volatile("lock; btcl %2,%1\n\tsbbl %0,%0"
+        asm volatile("lock; btc %2,%1\n\tsbbl %0,%0"
                      : "=r" (oldbit), "+m" (ADDR)
                      : "Ir" (nr) : "memory");
         return oldbit;