WSL2-Linux-Kernel/arch/arm64/kernel/time.c

72 строки
1.5 KiB
C
Исходник Обычный вид История

// SPDX-License-Identifier: GPL-2.0-only
/*
* Based on arch/arm/kernel/time.c
*
* Copyright (C) 1991, 1992, 1995 Linus Torvalds
* Modifications for ARM (C) 1994-2001 Russell King
* Copyright (C) 2012 ARM Ltd.
*/
arm64: kernel: initialize broadcast hrtimer based clock event device On platforms implementing CPU power management, the CPUidle subsystem can allow CPUs to enter idle states where local timers logic is lost on power down. To keep the software timers functional the kernel relies on an always-on broadcast timer to be present in the platform to relay the interrupt signalling the timer expiries. For platforms implementing CPU core gating that do not implement an always-on HW timer or implement it in a broken way, this patch adds code to initialize the kernel hrtimer based clock event device upon boot (which can be chosen as tick broadcast device by the kernel). It relies on a dynamically chosen CPU to be always powered-up. This CPU then relays the timer interrupt to CPUs in deep-idle states through its HW local timer device. Having a CPU always-on has implications on power management platform capabilities and makes CPUidle suboptimal, since at least a CPU is kept always in a shallow idle state by the kernel to relay timer interrupts, but at least leaves the kernel with a functional system with some working power management capabilities. The hrtimer based clock event device is unconditionally registered, but has the lowest possible rating such that any broadcast-capable HW clock event device present will be chosen in preference as the tick broadcast device. Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Acked-by: Will Deacon <will.deacon@arm.com> Acked-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2014-05-29 21:16:54 +04:00
#include <linux/clockchips.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/interrupt.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/timex.h>
#include <linux/errno.h>
#include <linux/profile.h>
#include <linux/syscore_ops.h>
#include <linux/timer.h>
#include <linux/irq.h>
#include <linux/delay.h>
#include <linux/clocksource.h>
#include <linux/clk-provider.h>
#include <linux/acpi.h>
#include <clocksource/arm_arch_timer.h>
#include <asm/thread_info.h>
#include <asm/stacktrace.h>
unsigned long profile_pc(struct pt_regs *regs)
{
struct stackframe frame;
if (!in_lock_functions(regs->pc))
return regs->pc;
frame.fp = regs->regs[29];
frame.pc = regs->pc;
arm64: ftrace: fix a stack tracer's output under function graph tracer Function graph tracer modifies a return address (LR) in a stack frame to hook a function return. This will result in many useless entries (return_to_handler) showing up in a) a stack tracer's output b) perf call graph (with perf record -g) c) dump_backtrace (at panic et al.) For example, in case of a), $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ echo 1 > /proc/sys/kernel/stack_trace_enabled $ cat /sys/kernel/debug/tracing/stack_trace Depth Size Location (54 entries) ----- ---- -------- 0) 4504 16 gic_raise_softirq+0x28/0x150 1) 4488 80 smp_cross_call+0x38/0xb8 2) 4408 48 return_to_handler+0x0/0x40 3) 4360 32 return_to_handler+0x0/0x40 ... In case of b), $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ perf record -e mem:XXX:x -ag -- sleep 10 $ perf report ... | | |--0.22%-- 0x550f8 | | | 0x10888 | | | el0_svc_naked | | | sys_openat | | | return_to_handler | | | return_to_handler ... In case of c), $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ echo c > /proc/sysrq-trigger ... Call trace: [<ffffffc00044d3ac>] sysrq_handle_crash+0x24/0x30 [<ffffffc000092250>] return_to_handler+0x0/0x40 [<ffffffc000092250>] return_to_handler+0x0/0x40 ... This patch replaces such entries with real addresses preserved in current->ret_stack[] at unwind_frame(). This way, we can cover all the cases. Reviewed-by: Jungseok Lee <jungseoklee85@gmail.com> Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org> [will: fixed minor context changes conflicting with irq stack bits] Signed-off-by: Will Deacon <will.deacon@arm.com>
2015-12-15 11:33:41 +03:00
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
frame.graph = 0;
arm64: ftrace: fix a stack tracer's output under function graph tracer Function graph tracer modifies a return address (LR) in a stack frame to hook a function return. This will result in many useless entries (return_to_handler) showing up in a) a stack tracer's output b) perf call graph (with perf record -g) c) dump_backtrace (at panic et al.) For example, in case of a), $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ echo 1 > /proc/sys/kernel/stack_trace_enabled $ cat /sys/kernel/debug/tracing/stack_trace Depth Size Location (54 entries) ----- ---- -------- 0) 4504 16 gic_raise_softirq+0x28/0x150 1) 4488 80 smp_cross_call+0x38/0xb8 2) 4408 48 return_to_handler+0x0/0x40 3) 4360 32 return_to_handler+0x0/0x40 ... In case of b), $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ perf record -e mem:XXX:x -ag -- sleep 10 $ perf report ... | | |--0.22%-- 0x550f8 | | | 0x10888 | | | el0_svc_naked | | | sys_openat | | | return_to_handler | | | return_to_handler ... In case of c), $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ echo c > /proc/sysrq-trigger ... Call trace: [<ffffffc00044d3ac>] sysrq_handle_crash+0x24/0x30 [<ffffffc000092250>] return_to_handler+0x0/0x40 [<ffffffc000092250>] return_to_handler+0x0/0x40 ... This patch replaces such entries with real addresses preserved in current->ret_stack[] at unwind_frame(). This way, we can cover all the cases. Reviewed-by: Jungseok Lee <jungseoklee85@gmail.com> Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org> [will: fixed minor context changes conflicting with irq stack bits] Signed-off-by: Will Deacon <will.deacon@arm.com>
2015-12-15 11:33:41 +03:00
#endif
do {
int ret = unwind_frame(NULL, &frame);
if (ret < 0)
return 0;
} while (in_lock_functions(frame.pc));
return frame.pc;
}
EXPORT_SYMBOL(profile_pc);
void __init time_init(void)
{
u32 arch_timer_rate;
of_clk_init(NULL);
timer_probe();
arm64: kernel: initialize broadcast hrtimer based clock event device On platforms implementing CPU power management, the CPUidle subsystem can allow CPUs to enter idle states where local timers logic is lost on power down. To keep the software timers functional the kernel relies on an always-on broadcast timer to be present in the platform to relay the interrupt signalling the timer expiries. For platforms implementing CPU core gating that do not implement an always-on HW timer or implement it in a broken way, this patch adds code to initialize the kernel hrtimer based clock event device upon boot (which can be chosen as tick broadcast device by the kernel). It relies on a dynamically chosen CPU to be always powered-up. This CPU then relays the timer interrupt to CPUs in deep-idle states through its HW local timer device. Having a CPU always-on has implications on power management platform capabilities and makes CPUidle suboptimal, since at least a CPU is kept always in a shallow idle state by the kernel to relay timer interrupts, but at least leaves the kernel with a functional system with some working power management capabilities. The hrtimer based clock event device is unconditionally registered, but has the lowest possible rating such that any broadcast-capable HW clock event device present will be chosen in preference as the tick broadcast device. Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Acked-by: Will Deacon <will.deacon@arm.com> Acked-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com>
2014-05-29 21:16:54 +04:00
tick_setup_hrtimer_broadcast();
arch_timer_rate = arch_timer_get_rate();
if (!arch_timer_rate)
panic("Unable to initialise architected timer.\n");
/* Calibrate the delay loop directly */
lpj_fine = arch_timer_rate / HZ;
}