linux/arch/powerpc/include/asm/time.h

125 lines
3 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Common time prototypes and such for all ppc machines.
*
* Written by Cort Dougan (cort@cs.nmt.edu) to merge
* Paul Mackerras' version and mine for PReP and Pmac.
*/
#ifndef __POWERPC_TIME_H
#define __POWERPC_TIME_H
#ifdef __KERNEL__
#include <linux/types.h>
#include <linux/percpu.h>
#include <asm/processor.h>
#include <asm/cpu_has_feature.h>
#include <asm/vdso/timebase.h>
/* time.c */
extern u64 decrementer_max;
extern unsigned long tb_ticks_per_jiffy;
extern unsigned long tb_ticks_per_usec;
extern unsigned long tb_ticks_per_sec;
extern struct clock_event_device decrementer_clockevent;
extern u64 decrementer_max;
extern void generic_calibrate_decr(void);
/* Some sane defaults: 125 MHz timebase, 1GHz processor */
extern unsigned long ppc_proc_freq;
#define DEFAULT_PROC_FREQ (DEFAULT_TB_FREQ * 8)
extern unsigned long ppc_tb_freq;
#define DEFAULT_TB_FREQ 125000000UL
extern bool tb_invalid;
struct div_result {
u64 result_high;
u64 result_low;
};
static inline u64 get_vtb(void)
{
if (cpu_has_feature(CPU_FTR_ARCH_207S))
return mfspr(SPRN_VTB);
return 0;
}
/* Accessor functions for the decrementer register.
* The 4xx doesn't even have a decrementer. I tried to use the
* generic timer interrupt code, which seems OK, with the 4xx PIT
* in auto-reload mode. The problem is PIT stops counting when it
* hits zero. If it would wrap, we could use it just like a decrementer.
*/
powerpc/timer: Large Decrementer support Power ISAv3 adds a large decrementer (LD) mode which increases the size of the decrementer register. The size of the enlarged decrementer register is between 32 and 64 bits with the exact size being dependent on the implementation. When in LD mode, reads are sign extended to 64 bits and a decrementer exception is raised when the high bit is set (i.e the value goes below zero). Writes however are truncated to the physical register width so some care needs to be taken to ensure that the high bit is not set when reloading the decrementer. This patch adds support for using the LD inside the host kernel on processors that support it. When LD mode is supported firmware will supply the ibm,dec-bits property for CPU nodes to allow the kernel to determine the maximum decrementer value. Enabling LD mode is a hypervisor privileged operation so the kernel can only enable it manually when running in hypervisor mode. Guests that support LD mode can request it using the "ibm,client-architecture-support" firmware call (not implemented in this patch) or some other platform specific method. If this property is not supplied then the traditional decrementer width of 32 bit is assumed and LD mode will not be enabled. This patch was based on initial work by Jack Miller. Signed-off-by: Oliver O'Halloran <oohall@gmail.com> Signed-off-by: Balbir Singh <bsingharora@gmail.com> Acked-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-07-01 16:20:39 +10:00
static inline u64 get_dec(void)
{
if (IS_ENABLED(CONFIG_40x))
return mfspr(SPRN_PIT);
return mfspr(SPRN_DEC);
}
/*
* Note: Book E and 4xx processors differ from other PowerPC processors
* in when the decrementer generates its interrupt: on the 1 to 0
* transition for Book E/4xx, but on the 0 to -1 transition for others.
*/
powerpc/timer: Large Decrementer support Power ISAv3 adds a large decrementer (LD) mode which increases the size of the decrementer register. The size of the enlarged decrementer register is between 32 and 64 bits with the exact size being dependent on the implementation. When in LD mode, reads are sign extended to 64 bits and a decrementer exception is raised when the high bit is set (i.e the value goes below zero). Writes however are truncated to the physical register width so some care needs to be taken to ensure that the high bit is not set when reloading the decrementer. This patch adds support for using the LD inside the host kernel on processors that support it. When LD mode is supported firmware will supply the ibm,dec-bits property for CPU nodes to allow the kernel to determine the maximum decrementer value. Enabling LD mode is a hypervisor privileged operation so the kernel can only enable it manually when running in hypervisor mode. Guests that support LD mode can request it using the "ibm,client-architecture-support" firmware call (not implemented in this patch) or some other platform specific method. If this property is not supplied then the traditional decrementer width of 32 bit is assumed and LD mode will not be enabled. This patch was based on initial work by Jack Miller. Signed-off-by: Oliver O'Halloran <oohall@gmail.com> Signed-off-by: Balbir Singh <bsingharora@gmail.com> Acked-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-07-01 16:20:39 +10:00
static inline void set_dec(u64 val)
{
if (IS_ENABLED(CONFIG_40x))
mtspr(SPRN_PIT, (u32)val);
else if (IS_ENABLED(CONFIG_BOOKE))
mtspr(SPRN_DEC, val);
else
mtspr(SPRN_DEC, val - 1);
}
static inline unsigned long tb_ticks_since(unsigned long tstamp)
{
return mftb() - tstamp;
}
#define mulhwu(x,y) \
({unsigned z; asm ("mulhwu %0,%1,%2" : "=r" (z) : "r" (x), "r" (y)); z;})
#ifdef CONFIG_PPC64
#define mulhdu(x,y) \
({unsigned long z; asm ("mulhdu %0,%1,%2" : "=r" (z) : "r" (x), "r" (y)); z;})
#else
extern u64 mulhdu(u64, u64);
#endif
extern void div128_by_32(u64 dividend_high, u64 dividend_low,
unsigned divisor, struct div_result *dr);
extern void secondary_cpu_time_init(void);
extern void __init time_init(void);
DECLARE_PER_CPU(u64, decrementers_next_tb);
static inline u64 timer_get_next_tb(void)
{
return __this_cpu_read(decrementers_next_tb);
}
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
void timer_rearm_host_dec(u64 now);
#endif
KVM: PPC: Book3S HV: Accumulate timing information for real-mode code This reads the timebase at various points in the real-mode guest entry/exit code and uses that to accumulate total, minimum and maximum time spent in those parts of the code. Currently these times are accumulated per vcpu in 5 parts of the code: * rm_entry - time taken from the start of kvmppc_hv_entry() until just before entering the guest. * rm_intr - time from when we take a hypervisor interrupt in the guest until we either re-enter the guest or decide to exit to the host. This includes time spent handling hcalls in real mode. * rm_exit - time from when we decide to exit the guest until the return from kvmppc_hv_entry(). * guest - time spend in the guest * cede - time spent napping in real mode due to an H_CEDE hcall while other threads in the same vcore are active. These times are exposed in debugfs in a directory per vcpu that contains a file called "timings". This file contains one line for each of the 5 timings above, with the name followed by a colon and 4 numbers, which are the count (number of times the code has been executed), the total time, the minimum time, and the maximum time, all in nanoseconds. The overhead of the extra code amounts to about 30ns for an hcall that is handled in real mode (e.g. H_SET_DABR), which is about 25%. Since production environments may not wish to incur this overhead, the new code is conditional on a new config symbol, CONFIG_KVM_BOOK3S_HV_EXIT_TIMING. Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Alexander Graf <agraf@suse.de>
2015-03-28 14:21:02 +11:00
/* Convert timebase ticks to nanoseconds */
unsigned long long tb_to_ns(unsigned long long tb_ticks);
void timer_broadcast_interrupt(void);
/* SPLPAR and VIRT_CPU_ACCOUNTING_NATIVE */
void pseries_accumulate_stolen_time(void);
u64 pseries_calculate_stolen_time(u64 stop_tb);
powerpc/64/sycall: Implement syscall entry/exit logic in C System call entry and particularly exit code is beyond the limit of what is reasonable to implement in asm. This conversion moves all conditional branches out of the asm code, except for the case that all GPRs should be restored at exit. Null syscall test is about 5% faster after this patch, because the exit work is handled under local_irq_disable, and the hard mask and pending interrupt replay is handled after that, which avoids games with MSR. mpe: Includes subsequent fixes from Nick: This fixes 4 issues caught by TM selftests. First was a tm-syscall bug that hit due to tabort_syscall being called after interrupts were reconciled (in a subsequent patch), which led to interrupts being enabled before tabort_syscall was called. Rather than going through an un-reconciling interrupts for the return, I just go back to putting the test early in asm, the C-ification of that wasn't a big win anyway. Second is the syscall return _TIF_USER_WORK_MASK check would go into an infinite loop if _TIF_RESTORE_TM became set. The asm code uses _TIF_USER_WORK_MASK to brach to slowpath which includes restore_tm_state. Third is system call return was not calling restore_tm_state, I missed this completely (alhtough it's in the return from interrupt C conversion because when the asm syscall code encountered problems it would branch to the interrupt return code. Fourth is MSR_VEC missing from restore_math, which was caught by tm-unavailable selftest taking an unexpected facility unavailable interrupt when testing VSX unavailble exception with MSR.FP=1 MSR.VEC=1. Fourth case also has a fixup in a subsequent patch. Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michal Suchanek <msuchanek@suse.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200225173541.1549955-26-npiggin@gmail.com
2020-02-26 03:35:34 +10:00
#endif /* __KERNEL__ */
#endif /* __POWERPC_TIME_H */