kernel/linux.git/arch/s390/include/asm/preempt.h, branch linux-7.0.y

s390/preempt: Optimize __preempt_count_dec_and_test()

2026-01-17T14:52:49+00:00

Provide an inline assembly using alternatives to avoid the need of a base register due to relocatable lowcore when adding or subtracting small constants from preempt_count. Main user is preempt_enable(), which subtracts one from preempt_count and tests if the result is zero. With this the generated code changes from 1000b8: a7 19 00 00 lghi %r1,0 1000bc: eb ff 13 a8 00 6e alsi 936(%r1),-1 1000c2: a7 54 00 05 jnhe 1000cc <__rcu_read_unlock+0x14> to something like this: 1000b8: eb ff 03 a8 00 6e alsi 936,-1 1000be: a7 54 00 05 jnhe 1000c8 <__rcu_read_unlock+0x10> Kernel image size is reduced by 45kb (bloat-o-meter -t, defconfig, gcc15). Reviewed-by: Sven Schnelle Signed-off-by: Heiko Carstens

s390/preempt: Optimize __preemp_count_add()/__preempt_count_sub()

2026-01-17T14:52:49+00:00

Provide an inline assembly using alternatives to avoid the need of a base register due to relocatable lowcore when adding or subtracting small constants from preempt_count. Main user is preempt_disable(), which subtracts one from preempt_count. With this the generated code changes from 10012c: a7 b9 00 00 lghi %r11,0 100130: eb 01 b3 a8 00 6a asi 936(%r11),1 to something like this: 10012c: eb 01 03 a8 00 6a asi 936,1 Kernel image size is reduced by 13kb (bloat-o-meter -t, defconfig, gcc15). Reviewed-by: Sven Schnelle Signed-off-by: Heiko Carstens

s390/preempt: Optimize preempt_count()

2026-01-17T14:52:49+00:00

Provide an inline assembly using alternatives to avoid the need of a base register when reading preempt_count() from lowcore. Use the LLGT instruction, which reads only the least significant 31 bits of preempt_count. This masks out the encoded PREEMPT_NEED_RESCHED bit. Generated code is changed from 000000000046e5d0 : 46e5d0: c0 04 00 00 00 00 jgnop 46e5d0 46e5d6: a7 39 00 00 lghi %r3,0 46e5da: 58 10 33 a8 l %r1,936(%r3) 46e5de: c0 1b 00 ff ff 00 nilf %r1,16776960 46e5e4: a7 74 00 11 jne 46e606 to something like this: 000000000046e5d0 : 46e5d0: c0 04 00 00 00 00 jgnop 46e5d0 46e5d6: e3 10 03 a8 00 17 llgt %r1,936 46e5dc: ec 41 28 b7 00 55 risbgz %r4,%r1,40,55 46e5e2: a7 74 00 0f jne 46e600 Overall savings are only 82 bytes according to bloat-o-meter. This is because of different inlining decisions, and there aren't many preempt_count() users in the kernel. Reviewed-by: Sven Schnelle Signed-off-by: Heiko Carstens

s390/preempt: Optimize __preempt_count_dec_and_test()

2024-12-15T15:19:03+00:00

Use __atomic_add_const_and_test() within __preempt_count_dec_and_test(). With this it is possible to decrease preempt_count by one and test if need_resched is set with one instruction, if the compiler has support for flag output operand constraints. Reviewed-by: Juergen Christ Signed-off-by: Heiko Carstens Signed-off-by: Alexander Gordeev

s390/preempt: Adjust coding style

2024-12-15T14:13:43+00:00

Just remove a line break which reduces readability. Reviewed-by: Alexander Gordeev Signed-off-by: Heiko Carstens Signed-off-by: Alexander Gordeev

s390/preempt: Remove special pre MARCH_HAS_Z196_FEATURES implementation

2024-12-15T14:13:43+00:00

Remove the preempt count implementation for pre MARCH_HAS_Z196_FEATURES builds. If the kernel is compiled with PREEMPT=n, which is the default for all distributions, this has close to zero impact in the generated code. Therefore remove the alternative implementation to keep things simple. Acked-by: Alexander Gordeev Signed-off-by: Heiko Carstens Signed-off-by: Alexander Gordeev

s390/preempt: Add comments

2024-12-15T14:13:43+00:00

The s390 preempt_count implementation is more or less a copy of the x86 implementation using different instructions. For clarification how this works also add all comments from x86 with some minor modifications. Acked-by: Alexander Gordeev Signed-off-by: Heiko Carstens Signed-off-by: Alexander Gordeev

s390: Support PREEMPT_DYNAMIC

2024-11-28T13:12:04+00:00

Select HAVE_PREEMPT_DYNAMIC_KEY and add the pieces which are required to support PREEMPT_DYNAMIC. See commit 99cf983cc8bc ("sched/preempt: Add PREEMPT_DYNAMIC using static keys") and commit 1b2d3451ee50 ("arm64: Support PREEMPT_DYNAMIC") for more details. Signed-off-by: Heiko Carstens

s390/preempt: Use arch_try_cmpxchg() instead of __atomic_cmpxchg()

2024-11-12T13:01:29+00:00

Use arch_try_cmpxchg() instead of __atomic_cmpxchg() in preempt_count_set() to generate similar or better code, depending in compiler features. Reviewed-by: Juergen Christ Signed-off-by: Heiko Carstens

s390: Use MARCH_HAS_*_FEATURES defines

2024-09-07T15:12:42+00:00

Replace CONFIG_HAVE_MARCH_*_FEATURES with MARCH_HAS_*_FEATURES everywhere so code gets compiled correctly depending on if the target is the kernel or the decompressor. Reviewed-by: Sven Schnelle Signed-off-by: Heiko Carstens