mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 12:05:10 +07:00
68b34588e2
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
202 lines
4.4 KiB
C
202 lines
4.4 KiB
C
/* 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>
|
|
|
|
/* time.c */
|
|
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 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;
|
|
};
|
|
|
|
/* Accessor functions for the timebase (RTC on 601) registers. */
|
|
/* If one day CONFIG_POWER is added just define __USE_RTC as 1 */
|
|
#define __USE_RTC() (IS_ENABLED(CONFIG_PPC_BOOK3S_601))
|
|
|
|
#ifdef CONFIG_PPC64
|
|
|
|
/* For compatibility, get_tbl() is defined as get_tb() on ppc64 */
|
|
#define get_tbl get_tb
|
|
|
|
#else
|
|
|
|
static inline unsigned long get_tbl(void)
|
|
{
|
|
#if defined(CONFIG_403GCX)
|
|
unsigned long tbl;
|
|
asm volatile("mfspr %0, 0x3dd" : "=r" (tbl));
|
|
return tbl;
|
|
#else
|
|
return mftbl();
|
|
#endif
|
|
}
|
|
|
|
static inline unsigned int get_tbu(void)
|
|
{
|
|
#ifdef CONFIG_403GCX
|
|
unsigned int tbu;
|
|
asm volatile("mfspr %0, 0x3dc" : "=r" (tbu));
|
|
return tbu;
|
|
#else
|
|
return mftbu();
|
|
#endif
|
|
}
|
|
#endif /* !CONFIG_PPC64 */
|
|
|
|
static inline unsigned int get_rtcl(void)
|
|
{
|
|
unsigned int rtcl;
|
|
|
|
asm volatile("mfrtcl %0" : "=r" (rtcl));
|
|
return rtcl;
|
|
}
|
|
|
|
static inline u64 get_rtc(void)
|
|
{
|
|
unsigned int hi, lo, hi2;
|
|
|
|
do {
|
|
asm volatile("mfrtcu %0; mfrtcl %1; mfrtcu %2"
|
|
: "=r" (hi), "=r" (lo), "=r" (hi2));
|
|
} while (hi2 != hi);
|
|
return (u64)hi * 1000000000 + lo;
|
|
}
|
|
|
|
static inline u64 get_vtb(void)
|
|
{
|
|
#ifdef CONFIG_PPC_BOOK3S_64
|
|
if (cpu_has_feature(CPU_FTR_ARCH_207S))
|
|
return mfspr(SPRN_VTB);
|
|
#endif
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_PPC64
|
|
static inline u64 get_tb(void)
|
|
{
|
|
return mftb();
|
|
}
|
|
#else /* CONFIG_PPC64 */
|
|
static inline u64 get_tb(void)
|
|
{
|
|
unsigned int tbhi, tblo, tbhi2;
|
|
|
|
do {
|
|
tbhi = get_tbu();
|
|
tblo = get_tbl();
|
|
tbhi2 = get_tbu();
|
|
} while (tbhi != tbhi2);
|
|
|
|
return ((u64)tbhi << 32) | tblo;
|
|
}
|
|
#endif /* !CONFIG_PPC64 */
|
|
|
|
static inline u64 get_tb_or_rtc(void)
|
|
{
|
|
return __USE_RTC() ? get_rtc() : get_tb();
|
|
}
|
|
|
|
static inline void set_tb(unsigned int upper, unsigned int lower)
|
|
{
|
|
mtspr(SPRN_TBWL, 0);
|
|
mtspr(SPRN_TBWU, upper);
|
|
mtspr(SPRN_TBWL, lower);
|
|
}
|
|
|
|
/* 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.
|
|
*/
|
|
static inline u64 get_dec(void)
|
|
{
|
|
#if defined(CONFIG_40x)
|
|
return (mfspr(SPRN_PIT));
|
|
#else
|
|
return (mfspr(SPRN_DEC));
|
|
#endif
|
|
}
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
static inline void set_dec(u64 val)
|
|
{
|
|
#if defined(CONFIG_40x)
|
|
mtspr(SPRN_PIT, (u32) val);
|
|
#else
|
|
#ifndef CONFIG_BOOKE
|
|
--val;
|
|
#endif
|
|
mtspr(SPRN_DEC, val);
|
|
#endif /* not 40x */
|
|
}
|
|
|
|
static inline unsigned long tb_ticks_since(unsigned long tstamp)
|
|
{
|
|
if (__USE_RTC()) {
|
|
int delta = get_rtcl() - (unsigned int) tstamp;
|
|
return delta < 0 ? delta + 1000000000 : delta;
|
|
}
|
|
return get_tbl() - 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);
|
|
|
|
/* Convert timebase ticks to nanoseconds */
|
|
unsigned long long tb_to_ns(unsigned long long tb_ticks);
|
|
|
|
/* SPLPAR */
|
|
void accumulate_stolen_time(void);
|
|
|
|
#endif /* __KERNEL__ */
|
|
#endif /* __POWERPC_TIME_H */
|