percpu, x86: Add arch-specific this_cpu_cmpxchg_double() support

Support this_cpu_cmpxchg_double() using the cmpxchg16b and cmpxchg8b
instructions.

-tj: s/percpu_cmpxchg16b/percpu_cmpxchg16b_double/ for consistency and
     other cosmetic changes.

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

2 files changed, 60 insertions, 0 deletions

diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index e10cf070ede0..f2479f19ddde 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -42,4 +42,5 @@ else
         lib-y += memmove_64.o memset_64.o
         lib-y += copy_user_64.o rwlock_64.o copy_user_nocache_64.o
         lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem_64.o
+        lib-y += cmpxchg16b_emu.o
 endif
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
new file mode 100644
index 000000000000..3e8b08a6de2b
--- /dev/null
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -0,0 +1,59 @@
+/*
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; version 2
+ *      of the License.
+ *
+ */
+#include <linux/linkage.h>
+#include <asm/alternative-asm.h>
+#include <asm/frame.h>
+#include <asm/dwarf2.h>
+
+.text
+
+/*
+ * Inputs:
+ * %rsi : memory location to compare
+ * %rax : low 64 bits of old value
+ * %rdx : high 64 bits of old value
+ * %rbx : low 64 bits of new value
+ * %rcx : high 64 bits of new value
+ * %al  : Operation successful
+ */
+ENTRY(this_cpu_cmpxchg16b_emu)
+CFI_STARTPROC
+
+#
+# Emulate 'cmpxchg16b %gs:(%rsi)' except we return the result in %al not
+# via the ZF.  Caller will access %al to get result.
+#
+# Note that this is only useful for a cpuops operation.  Meaning that we
+# do *not* have a fully atomic operation but just an operation that is
+# *atomic* on a single cpu (as provided by the this_cpu_xx class of
+# macros).
+#
+this_cpu_cmpxchg16b_emu:
+        pushf
+        cli
+
+        cmpq %gs:(%rsi), %rax
+        jne not_same
+        cmpq %gs:8(%rsi), %rdx
+        jne not_same
+
+        movq %rbx, %gs:(%rsi)
+        movq %rcx, %gs:8(%rsi)
+
+        popf
+        mov $1, %al
+        ret
+
+ not_same:
+        popf
+        xor %al,%al
+        ret
+
+CFI_ENDPROC
+
+ENDPROC(this_cpu_cmpxchg16b_emu)