summaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm/percpu.h
diff options
context:
space:
mode:
authorChristoph Lameter <cl@linux-foundation.org>2010-01-05 07:34:50 +0100
committerTejun Heo <tj@kernel.org>2010-01-05 07:34:50 +0100
commit5917dae83cb02dfe74c9167b79e86e6d65183fa3 (patch)
treeffd3a8c0b0c27868600f2a426ad14c0885bf4d7d /arch/x86/include/asm/percpu.h
parentlocal_t: Move local.h include to ringbuffer.c and ring_buffer_benchmark.c (diff)
downloadlinux-5917dae83cb02dfe74c9167b79e86e6d65183fa3.tar.xz
linux-5917dae83cb02dfe74c9167b79e86e6d65183fa3.zip
percpu, x86: Generic inc / dec percpu instructions
Optimize code generated for percpu access by checking for increment and decrements. tj: fix incorrect usage of __builtin_constant_p() and restructure percpu_add_op() macro. Signed-off-by: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: Tejun Heo <tj@kernel.org>
Diffstat (limited to 'arch/x86/include/asm/percpu.h')
-rw-r--r--arch/x86/include/asm/percpu.h86
1 files changed, 72 insertions, 14 deletions
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 4c170ccc72ed..66a272dfd8b8 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -103,6 +103,64 @@ do { \
} \
} while (0)
+/*
+ * Generate a percpu add to memory instruction and optimize code
+ * if a one is added or subtracted.
+ */
+#define percpu_add_op(var, val) \
+do { \
+ typedef typeof(var) pao_T__; \
+ const int pao_ID__ = (__builtin_constant_p(val) && \
+ ((val) == 1 || (val) == -1)) ? (val) : 0; \
+ if (0) { \
+ pao_T__ pao_tmp__; \
+ pao_tmp__ = (val); \
+ } \
+ switch (sizeof(var)) { \
+ case 1: \
+ if (pao_ID__ == 1) \
+ asm("incb "__percpu_arg(0) : "+m" (var)); \
+ else if (pao_ID__ == -1) \
+ asm("decb "__percpu_arg(0) : "+m" (var)); \
+ else \
+ asm("addb %1, "__percpu_arg(0) \
+ : "+m" (var) \
+ : "qi" ((pao_T__)(val))); \
+ break; \
+ case 2: \
+ if (pao_ID__ == 1) \
+ asm("incw "__percpu_arg(0) : "+m" (var)); \
+ else if (pao_ID__ == -1) \
+ asm("decw "__percpu_arg(0) : "+m" (var)); \
+ else \
+ asm("addw %1, "__percpu_arg(0) \
+ : "+m" (var) \
+ : "ri" ((pao_T__)(val))); \
+ break; \
+ case 4: \
+ if (pao_ID__ == 1) \
+ asm("incl "__percpu_arg(0) : "+m" (var)); \
+ else if (pao_ID__ == -1) \
+ asm("decl "__percpu_arg(0) : "+m" (var)); \
+ else \
+ asm("addl %1, "__percpu_arg(0) \
+ : "+m" (var) \
+ : "ri" ((pao_T__)(val))); \
+ break; \
+ case 8: \
+ if (pao_ID__ == 1) \
+ asm("incq "__percpu_arg(0) : "+m" (var)); \
+ else if (pao_ID__ == -1) \
+ asm("decq "__percpu_arg(0) : "+m" (var)); \
+ else \
+ asm("addq %1, "__percpu_arg(0) \
+ : "+m" (var) \
+ : "re" ((pao_T__)(val))); \
+ break; \
+ default: __bad_percpu_size(); \
+ } \
+} while (0)
+
#define percpu_from_op(op, var, constraint) \
({ \
typeof(var) pfo_ret__; \
@@ -144,8 +202,8 @@ do { \
#define percpu_read(var) percpu_from_op("mov", var, "m" (var))
#define percpu_read_stable(var) percpu_from_op("mov", var, "p" (&(var)))
#define percpu_write(var, val) percpu_to_op("mov", var, val)
-#define percpu_add(var, val) percpu_to_op("add", var, val)
-#define percpu_sub(var, val) percpu_to_op("sub", var, val)
+#define percpu_add(var, val) percpu_add_op(var, val)
+#define percpu_sub(var, val) percpu_add_op(var, -(val))
#define percpu_and(var, val) percpu_to_op("and", var, val)
#define percpu_or(var, val) percpu_to_op("or", var, val)
#define percpu_xor(var, val) percpu_to_op("xor", var, val)
@@ -157,9 +215,9 @@ do { \
#define __this_cpu_write_1(pcp, val) percpu_to_op("mov", (pcp), val)
#define __this_cpu_write_2(pcp, val) percpu_to_op("mov", (pcp), val)
#define __this_cpu_write_4(pcp, val) percpu_to_op("mov", (pcp), val)
-#define __this_cpu_add_1(pcp, val) percpu_to_op("add", (pcp), val)
-#define __this_cpu_add_2(pcp, val) percpu_to_op("add", (pcp), val)
-#define __this_cpu_add_4(pcp, val) percpu_to_op("add", (pcp), val)
+#define __this_cpu_add_1(pcp, val) percpu_add_op((pcp), val)
+#define __this_cpu_add_2(pcp, val) percpu_add_op((pcp), val)
+#define __this_cpu_add_4(pcp, val) percpu_add_op((pcp), val)
#define __this_cpu_and_1(pcp, val) percpu_to_op("and", (pcp), val)
#define __this_cpu_and_2(pcp, val) percpu_to_op("and", (pcp), val)
#define __this_cpu_and_4(pcp, val) percpu_to_op("and", (pcp), val)
@@ -176,9 +234,9 @@ do { \
#define this_cpu_write_1(pcp, val) percpu_to_op("mov", (pcp), val)
#define this_cpu_write_2(pcp, val) percpu_to_op("mov", (pcp), val)
#define this_cpu_write_4(pcp, val) percpu_to_op("mov", (pcp), val)
-#define this_cpu_add_1(pcp, val) percpu_to_op("add", (pcp), val)
-#define this_cpu_add_2(pcp, val) percpu_to_op("add", (pcp), val)
-#define this_cpu_add_4(pcp, val) percpu_to_op("add", (pcp), val)
+#define this_cpu_add_1(pcp, val) percpu_add_op((pcp), val)
+#define this_cpu_add_2(pcp, val) percpu_add_op((pcp), val)
+#define this_cpu_add_4(pcp, val) percpu_add_op((pcp), val)
#define this_cpu_and_1(pcp, val) percpu_to_op("and", (pcp), val)
#define this_cpu_and_2(pcp, val) percpu_to_op("and", (pcp), val)
#define this_cpu_and_4(pcp, val) percpu_to_op("and", (pcp), val)
@@ -189,9 +247,9 @@ do { \
#define this_cpu_xor_2(pcp, val) percpu_to_op("xor", (pcp), val)
#define this_cpu_xor_4(pcp, val) percpu_to_op("xor", (pcp), val)
-#define irqsafe_cpu_add_1(pcp, val) percpu_to_op("add", (pcp), val)
-#define irqsafe_cpu_add_2(pcp, val) percpu_to_op("add", (pcp), val)
-#define irqsafe_cpu_add_4(pcp, val) percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_add_1(pcp, val) percpu_add_op((pcp), val)
+#define irqsafe_cpu_add_2(pcp, val) percpu_add_op((pcp), val)
+#define irqsafe_cpu_add_4(pcp, val) percpu_add_op((pcp), val)
#define irqsafe_cpu_and_1(pcp, val) percpu_to_op("and", (pcp), val)
#define irqsafe_cpu_and_2(pcp, val) percpu_to_op("and", (pcp), val)
#define irqsafe_cpu_and_4(pcp, val) percpu_to_op("and", (pcp), val)
@@ -209,19 +267,19 @@ do { \
#ifdef CONFIG_X86_64
#define __this_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
#define __this_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val)
-#define __this_cpu_add_8(pcp, val) percpu_to_op("add", (pcp), val)
+#define __this_cpu_add_8(pcp, val) percpu_add_op((pcp), val)
#define __this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val)
#define __this_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val)
#define __this_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val)
#define this_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
#define this_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val)
-#define this_cpu_add_8(pcp, val) percpu_to_op("add", (pcp), val)
+#define this_cpu_add_8(pcp, val) percpu_add_op((pcp), val)
#define this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val)
#define this_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val)
#define this_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val)
-#define irqsafe_cpu_add_8(pcp, val) percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_add_8(pcp, val) percpu_add_op((pcp), val)
#define irqsafe_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val)
#define irqsafe_cpu_or_8(pcp, val) percpu_to_op("or", (pcp), val)
#define irqsafe_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val)