summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorHeiko Carstens <hca@linux.ibm.com>2026-03-17 22:54:28 +0300
committerVasily Gorbik <gor@linux.ibm.com>2026-03-24 23:00:41 +0300
commitfa8be59ce23df05d3e1190ce4238f6f875d3868d (patch)
treea1892fd141250193b0e5dd278ba7b9e177f1368b
parent7bbf70131f937ee5871e22d159ed2fc66795722f (diff)
downloadlinux-fa8be59ce23df05d3e1190ce4238f6f875d3868d.tar.xz
s390/percpu: Provide arch_raw_cpu_ptr()
Provide an s390 specific arch_raw_cpu_ptr() implementation which avoids the detour over get_lowcore() to get the lowcore pointer. The inline assembly is implemented with an alternative so that relocated lowcore (percpu offset is at a different address) is handled correctly. This turns code like this 102f78: a7 39 00 00 lghi %r3,0 102f7c: e3 20 33 b8 00 08 ag %r2,952(%r3) which adds the percpu offset to register r2 into a single instruction 102f7c: e3 20 33 b8 00 08 ag %r2,952(%r0) and also avoids the need of a base register, thus reducing register pressure. With defconfig bloat-o-meter -t provides this result: add/remove: 12/26 grow/shrink: 183/3391 up/down: 14880/-41950 (-27070) Signed-off-by: Heiko Carstens <hca@linux.ibm.com> Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
-rw-r--r--arch/s390/include/asm/percpu.h18
1 files changed, 18 insertions, 0 deletions
diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index 5899f57f17d1..b18a96f3a334 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -12,6 +12,24 @@
*/
#define __my_cpu_offset get_lowcore()->percpu_offset
+#define arch_raw_cpu_ptr(_ptr) \
+({ \
+ unsigned long lc_percpu, tcp_ptr__; \
+ \
+ tcp_ptr__ = (__force unsigned long)(_ptr); \
+ lc_percpu = offsetof(struct lowcore, percpu_offset); \
+ asm_inline volatile( \
+ ALTERNATIVE("ag %[__ptr__],%[offzero](%%r0)\n", \
+ "ag %[__ptr__],%[offalt](%%r0)\n", \
+ ALT_FEATURE(MFEATURE_LOWCORE)) \
+ : [__ptr__] "+d" (tcp_ptr__) \
+ : [offzero] "i" (lc_percpu), \
+ [offalt] "i" (lc_percpu + LOWCORE_ALT_ADDRESS), \
+ "m" (((struct lowcore *)0)->percpu_offset) \
+ : "cc"); \
+ (TYPEOF_UNQUAL(*(_ptr)) __force __kernel *)tcp_ptr__; \
+})
+
/*
* We use a compare-and-swap loop since that uses less cpu cycles than
* disabling and enabling interrupts like the generic variant would do.