[PATCH v3 4/9] s390/percpu: Use new percpu code section for arch_this_cpu_add()

[Heiko Carstens <hca@linux.ibm.com>]

Convert arch_this_cpu_add() to make use of the new percpu code section
infrastructure.

With this the text size of the kernel image is reduced by ~76kb
(defconfig). Also more than 5300 generated preempt_schedule_notrace()
function calls within the kernel image (modules not counted) are removed.

With:

DEFINE_PER_CPU(long, foo);
void bar(long a) { this_cpu_add(foo, a); }

Old arch_this_cpu_add() looks like this:

00000000000000c0 <bar>:
  c0:   c0 04 00 00 00 00       jgnop   c0 <bar>
  c6:   eb 01 03 a8 00 6a       asi     936,1
  cc:   c4 18 00 00 00 00       lgrl    %r1,cc <bar+0xc>
                        ce: R_390_GOTENT        foo+0x2
  d2:   e3 10 03 b8 00 08       ag      %r1,952
  d8:   eb 22 10 00 00 e8       laag    %r2,%r2,0(%r1)
  de:   eb ff 03 a8 00 6e       alsi    936,-1
  e4:   a7 a4 00 05             jhe     ee <bar+0x2e>
  e8:   c0 f4 00 00 00 00       jg      e8 <bar+0x28>
                        ea: R_390_PC32DBL       __s390_indirect_jump_r14+0x2
  ee:   c0 f4 00 00 00 00       jg      ee <bar+0x2e>
                        f0: R_390_PLT32DBL      preempt_schedule_notrace+0x2

New arch_this_cpu_add() looks like this:

00000000000000c0 <bar>:
  c0:   c0 04 00 00 00 00       jgnop   c0 <bar>
  c6:   c4 38 00 00 00 00       lgrl    %r3,c6 <bar+0x6>
                        c8: R_390_GOTENT        foo+0x2
  cc:   b9 04 00 43             lgr     %r4,%r3
  d0:   eb 00 43 c0 00 52       mviy    960(%r0),4
  d6:   e3 40 03 b8 00 08       ag      %r4,952
  dc:   eb 52 40 00 00 e8       laag    %r5,%r2,0(%r4)
  e2:   eb 00 03 c0 00 52       mviy    960,0
  e8:   c0 f4 00 00 00 00       jg      e8 <bar+0x28>
                        ea: R_390_PC32DBL       __s390_indirect_jump_r14+0x2

Note that the conditional function call is removed.

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
 arch/s390/include/asm/percpu.h | 65 ++++++++++++++++++++++------------
 1 file changed, 43 insertions(+), 22 deletions(-)

diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index c8fc8b320a86..459603c7305a 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -127,28 +127,49 @@
 
 #else /* MARCH_HAS_Z196_FEATURES */
 
-#define arch_this_cpu_add(pcp, val, op1, op2, szcast)			\
-do {									\
-	typedef typeof(pcp) pcp_op_T__; 				\
-	pcp_op_T__ val__ = (val);					\
-	pcp_op_T__ old__, *ptr__;					\
-	preempt_disable_notrace();					\
-	ptr__ = raw_cpu_ptr(&(pcp)); 				\
-	if (__builtin_constant_p(val__) &&				\
-	    ((szcast)val__ > -129) && ((szcast)val__ < 128)) {		\
-		asm volatile(						\
-			op2 "   %[ptr__],%[val__]"			\
-			: [ptr__] "+Q" (*ptr__) 			\
-			: [val__] "i" ((szcast)val__)			\
-			: "cc");					\
-	} else {							\
-		asm volatile(						\
-			op1 "   %[old__],%[val__],%[ptr__]"		\
-			: [old__] "=d" (old__), [ptr__] "+Q" (*ptr__)	\
-			: [val__] "d" (val__)				\
-			: "cc");					\
-	}								\
-	preempt_enable_notrace();					\
+#define arch_this_cpu_add(pcp, val, op1, op2, szcast)				\
+do {										\
+	unsigned long lc_pcpr, lc_pcpo;						\
+	typedef typeof(pcp) pcp_op_T__;						\
+	pcp_op_T__ val__ = (val);						\
+	pcp_op_T__ old__, *ptr__;						\
+										\
+	lc_pcpr = offsetof(struct lowcore, percpu_register);			\
+	lc_pcpo = offsetof(struct lowcore, percpu_offset);			\
+	ptr__ = PERCPU_PTR(&(pcp));						\
+	if (__builtin_constant_p(val__) &&					\
+	    ((szcast)val__ > -129) && ((szcast)val__ < 128)) {			\
+		asm volatile(							\
+			MVIY_PERCPU("%[disppcpr]", "%[dispaltpcpr]", "%[ptr__]")\
+			AG_ALT("%[disppcpo]", "%[dispaltpcpo]", "%[ptr__]")	\
+			op2 "   0(%[ptr__]),%[val__]\n"				\
+			MVIY_ALT("%[disppcpr]", "%[dispaltpcpr]", "%%r0")	\
+			: [ptr__] "+&a" (ptr__), "+m" (*ptr__),			\
+			  "=m" (((struct lowcore *)0)->percpu_register)		\
+			: [val__] "i" ((szcast)val__),				\
+			  [disppcpr] "i" (lc_pcpr),				\
+			  [disppcpo] "i" (lc_pcpo),				\
+			  [dispaltpcpr] "i" (lc_pcpr + LOWCORE_ALT_ADDRESS),	\
+			  [dispaltpcpo] "i" (lc_pcpo + LOWCORE_ALT_ADDRESS),	\
+			  "m" (((struct lowcore *)0)->percpu_offset)		\
+			: "cc");						\
+	} else {								\
+		asm volatile(							\
+			MVIY_PERCPU("%[disppcpr]", "%[dispaltpcpr]", "%[ptr__]")\
+			AG_ALT("%[disppcpo]", "%[dispaltpcpo]", "%[ptr__]")	\
+			op1 "   %[old__],%[val__],0(%[ptr__])\n"		\
+			MVIY_ALT("%[disppcpr]", "%[dispaltpcpr]", "%%r0")	\
+			: [old__] "=&d" (old__),				\
+			  [ptr__] "+&a" (ptr__),  "+m" (*ptr__),		\
+			  "=m" (((struct lowcore *)0)->percpu_register)		\
+			: [val__] "d" (val__),					\
+			  [disppcpr] "i" (lc_pcpr),				\
+			  [disppcpo] "i" (lc_pcpo),				\
+			  [dispaltpcpr] "i" (lc_pcpr + LOWCORE_ALT_ADDRESS),	\
+			  [dispaltpcpo] "i" (lc_pcpo + LOWCORE_ALT_ADDRESS),	\
+			  "m" (((struct lowcore *)0)->percpu_offset)		\
+			: "cc");						\
+	}									\
 } while (0)
 
 #define this_cpu_add_4(pcp, val) arch_this_cpu_add(pcp, val, "laa", "asi", int)
-- 
2.51.0