x86-64: support native xadd rwsem implementation

This one is much faster than the spinlock based fallback rwsem code,
with certain artifical benchmarks having shown 300%+ improvement on
threaded page faults etc.

Again, note the 32767-thread limit here. So this really does need that
whole "make rwsem_count_t be 64-bit and fix the BIAS values to match"
extension on top of it, but that is conceptually a totally independent
issue.

NOT TESTED! The original patch that this all was based on were tested by
KAMEZAWA Hiroyuki, but maybe I screwed up something when I created the
cleaned-up series, so caveat emptor..

Also note that it _may_ be a good idea to mark some more registers
clobbered on x86-64 in the inline asms instead of saving/restoring them.
They are inline functions, but they are only used in places where there
are not a lot of live registers _anyway_, so doing for example the
clobbers of %r8-%r11 in the asm wouldn't make the fast-path code any
worse, and would make the slow-path code smaller.

(Not that the slow-path really matters to that degree. Saving a few
unnecessary registers is the _least_ of our problems when we hit the slow
path. The instruction/cycle counting really only matters in the fast
path).

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
LKML-Reference: <alpine.LFD.2.00.1001121810410.17145@localhost.localdomain>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

2 files changed, 82 insertions, 0 deletions

diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index cffd754f..c802451 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -39,4 +39,5 @@ else
         lib-y += thunk_64.o clear_page_64.o copy_page_64.o
         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
 endif
diff --git a/arch/x86/lib/rwsem_64.S b/arch/x86/lib/rwsem_64.S
new file mode 100644
index 0000000..15acecf
--- /dev/null
+++ b/arch/x86/lib/rwsem_64.S
@@ -0,0 +1,81 @@
+/*
+ * x86-64 rwsem wrappers
+ *
+ * This interfaces the inline asm code to the slow-path
+ * C routines. We need to save the call-clobbered regs
+ * that the asm does not mark as clobbered, and move the
+ * argument from %rax to %rdi.
+ *
+ * NOTE! We don't need to save %rax, because the functions
+ * will always return the semaphore pointer in %rax (which
+ * is also the input argument to these helpers)
+ *
+ * The following can clobber %rdx because the asm clobbers it:
+ *   call_rwsem_down_write_failed
+ *   call_rwsem_wake
+ * but %rdi, %rsi, %rcx, %r8-r11 always need saving.
+ */
+
+#include <linux/linkage.h>
+#include <asm/rwlock.h>
+#include <asm/alternative-asm.h>
+#include <asm/frame.h>
+#include <asm/dwarf2.h>
+
+#define save_common_regs \
+	pushq %rdi; \
+	pushq %rsi; \
+	pushq %rcx; \
+	pushq %r8; \
+	pushq %r9; \
+	pushq %r10; \
+	pushq %r11
+
+#define restore_common_regs \
+	popq %r11; \
+	popq %r10; \
+	popq %r9; \
+	popq %r8; \
+	popq %rcx; \
+	popq %rsi; \
+	popq %rdi
+
+/* Fix up special calling conventions */
+ENTRY(call_rwsem_down_read_failed)
+	save_common_regs
+	pushq %rdx
+	movq %rax,%rdi
+	call rwsem_down_read_failed
+	popq %rdx
+	restore_common_regs
+	ret
+	ENDPROC(call_rwsem_down_read_failed)
+
+ENTRY(call_rwsem_down_write_failed)
+	save_common_regs
+	movq %rax,%rdi
+	call rwsem_down_write_failed
+	restore_common_regs
+	ret
+	ENDPROC(call_rwsem_down_write_failed)
+
+ENTRY(call_rwsem_wake)
+	decw %dx    /* do nothing if still outstanding active readers */
+	jnz 1f
+	save_common_regs
+	movq %rax,%rdi
+	call rwsem_wake
+	restore_common_regs
+1:	ret
+	ENDPROC(call_rwsem_wake)
+
+/* Fix up special calling conventions */
+ENTRY(call_rwsem_downgrade_wake)
+	save_common_regs
+	pushq %rdx
+	movq %rax,%rdi
+	call rwsem_downgrade_wake
+	popq %rdx
+	restore_common_regs
+	ret
+	ENDPROC(call_rwsem_downgrade_wake)