diff options
author | Puranjay Mohan <puranjay@kernel.org> | 2024-05-03 19:18:47 +0200 |
---|---|---|
committer | Catalin Marinas <catalin.marinas@arm.com> | 2024-06-12 16:44:19 +0200 |
commit | bf0baa5bbdc9b99ea081d360f245e5f96e835612 (patch) | |
tree | 4acac0c94439b1e1feb92caca8521f1d012aabe6 | |
parent | arm64/arch_timer: include <linux/percpu.h> (diff) | |
download | linux-bf0baa5bbdc9b99ea081d360f245e5f96e835612.tar.xz linux-bf0baa5bbdc9b99ea081d360f245e5f96e835612.zip |
arm64: implement raw_smp_processor_id() using thread_info
Historically, arm64 implemented raw_smp_processor_id() as a read of
current_thread_info()->cpu. This changed when arm64 moved thread_info into
task struct, as at the time CONFIG_THREAD_INFO_IN_TASK made core code use
thread_struct::cpu for the cpu number, and due to header dependencies
prevented using this in raw_smp_processor_id(). As a workaround, we moved to
using a percpu variable in commit:
57c82954e77fa12c ("arm64: make cpu number a percpu variable")
Since then, thread_info::cpu was reintroduced, and core code was made to use
this in commits:
001430c1910df65a ("arm64: add CPU field to struct thread_info")
bcf9033e5449bdca ("sched: move CPU field back into thread_info if THREAD_INFO_IN_TASK=y")
Consequently it is possible to use current_thread_info()->cpu again.
This decreases the number of emitted instructions like in the following
example:
Dump of assembler code for function bpf_get_smp_processor_id:
0xffff8000802cd608 <+0>: nop
0xffff8000802cd60c <+4>: nop
0xffff8000802cd610 <+8>: adrp x0, 0xffff800082138000
0xffff8000802cd614 <+12>: mrs x1, tpidr_el1
0xffff8000802cd618 <+16>: add x0, x0, #0x8
0xffff8000802cd61c <+20>: ldrsw x0, [x0, x1]
0xffff8000802cd620 <+24>: ret
After this patch:
Dump of assembler code for function bpf_get_smp_processor_id:
0xffff8000802c9130 <+0>: nop
0xffff8000802c9134 <+4>: nop
0xffff8000802c9138 <+8>: mrs x0, sp_el0
0xffff8000802c913c <+12>: ldr w0, [x0, #24]
0xffff8000802c9140 <+16>: ret
A microbenchmark[1] was built to measure the performance improvement
provided by this change. It calls the following function given number of
times and finds the runtime overhead:
static noinline int get_cpu_id(void)
{
return smp_processor_id();
}
Run the benchmark like:
modprobe smp_processor_id nr_function_calls=1000000000
+--------------------------+------------------------+
| | Number of Calls | Time taken |
+--------+-----------------+------------------------+
| Before | 1000000000 | 1602888401ns |
+--------+-----------------+------------------------+
| After | 1000000000 | 1206212658ns |
+--------+-----------------+------------------------+
| Difference (decrease) | 396675743ns (24.74%) |
+---------------------------------------------------+
Remove the percpu variable cpu_number as it is used only in
set_smp_ipi_range() as a dummy variable to be passed to ipi_handler().
Use irq_stat in place of cpu_number here like arm32.
[1] https://github.com/puranjaymohan/linux/commit/77d3fdd
Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Link: https://lore.kernel.org/r/20240503171847.68267-2-puranjay@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
-rw-r--r-- | arch/arm64/include/asm/smp.h | 13 | ||||
-rw-r--r-- | arch/arm64/kernel/smp.c | 9 |
2 files changed, 3 insertions, 19 deletions
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index efb13112b408..2510eec026f7 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -25,22 +25,11 @@ #ifndef __ASSEMBLY__ -#include <asm/percpu.h> - #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/thread_info.h> -DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); - -/* - * We don't use this_cpu_read(cpu_number) as that has implicit writes to - * preempt_count, and associated (compiler) barriers, that we'd like to avoid - * the expense of. If we're preemptible, the value can be stale at use anyway. - * And we can't use this_cpu_ptr() either, as that winds up recursing back - * here under CONFIG_DEBUG_PREEMPT=y. - */ -#define raw_smp_processor_id() (*raw_cpu_ptr(&cpu_number)) +#define raw_smp_processor_id() (current_thread_info()->cpu) /* * Logical CPU mapping. diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 31c8b3094dd7..753360ce72f6 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -55,9 +55,6 @@ #include <trace/events/ipi.h> -DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number); -EXPORT_PER_CPU_SYMBOL(cpu_number); - /* * as from 2.5, kernels no longer have an init_tasks structure * so we need some other way of telling a new secondary core @@ -749,8 +746,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus) */ for_each_possible_cpu(cpu) { - per_cpu(cpu_number, cpu) = cpu; - if (cpu == smp_processor_id()) continue; @@ -1028,12 +1023,12 @@ void __init set_smp_ipi_range(int ipi_base, int n) if (ipi_should_be_nmi(i)) { err = request_percpu_nmi(ipi_base + i, ipi_handler, - "IPI", &cpu_number); + "IPI", &irq_stat); WARN(err, "Could not request IPI %d as NMI, err=%d\n", i, err); } else { err = request_percpu_irq(ipi_base + i, ipi_handler, - "IPI", &cpu_number); + "IPI", &irq_stat); WARN(err, "Could not request IPI %d as IRQ, err=%d\n", i, err); } |