Message ID | 1464986428-6739-11-git-send-email-alex.bennee@linaro.org (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
On 03/06/16 23:40, Alex Bennée wrote: > In preparation for multi-threaded TCG we remove tcg_exec_all and move > all the CPU cycling into the main thread function. When MTTCG is enabled > we shall use a separate thread function which only handles one vCPU. > > Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Sergey Fedorov <sergey.fedorov@linaro.org> > > --- > v2 > - update timer calls to new API on rebase > v3 > - move tcg_cpu_exec above thread function, drop static fwd declaration > --- > cpus.c | 185 +++++++++++++++++++++++++++++++---------------------------------- > 1 file changed, 89 insertions(+), 96 deletions(-) > > diff --git a/cpus.c b/cpus.c > index c404dd7..4cc2ce6 100644 > --- a/cpus.c > +++ b/cpus.c > @@ -69,7 +69,6 @@ > > #endif /* CONFIG_LINUX */ > > -static CPUState *next_cpu; > int64_t max_delay; > int64_t max_advance; > > @@ -1119,7 +1118,67 @@ static void *qemu_dummy_cpu_thread_fn(void *arg) > #endif > } > > -static void tcg_exec_all(void); > +static int64_t tcg_get_icount_limit(void) > +{ > + int64_t deadline; > + > + if (replay_mode != REPLAY_MODE_PLAY) { > + deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL); > + > + /* Maintain prior (possibly buggy) behaviour where if no deadline > + * was set (as there is no QEMU_CLOCK_VIRTUAL timer) or it is more than > + * INT32_MAX nanoseconds ahead, we still use INT32_MAX > + * nanoseconds. > + */ > + if ((deadline < 0) || (deadline > INT32_MAX)) { > + deadline = INT32_MAX; > + } > + > + return qemu_icount_round(deadline); > + } else { > + return replay_get_instructions(); > + } > +} > + > +static int tcg_cpu_exec(CPUState *cpu) > +{ > + int ret; > +#ifdef CONFIG_PROFILER > + int64_t ti; > +#endif > + > +#ifdef CONFIG_PROFILER > + ti = profile_getclock(); > +#endif > + if (use_icount) { > + int64_t count; > + int decr; > + timers_state.qemu_icount -= (cpu->icount_decr.u16.low > + + cpu->icount_extra); > + cpu->icount_decr.u16.low = 0; > + cpu->icount_extra = 0; > + count = tcg_get_icount_limit(); > + timers_state.qemu_icount += count; > + decr = (count > 0xffff) ? 0xffff : count; > + count -= decr; > + cpu->icount_decr.u16.low = decr; > + cpu->icount_extra = count; > + } > + ret = cpu_exec(cpu); > +#ifdef CONFIG_PROFILER > + tcg_time += profile_getclock() - ti; > +#endif > + if (use_icount) { > + /* Fold pending instructions back into the > + instruction counter, and clear the interrupt flag. */ > + timers_state.qemu_icount -= (cpu->icount_decr.u16.low > + + cpu->icount_extra); > + cpu->icount_decr.u32 = 0; > + cpu->icount_extra = 0; > + replay_account_executed_instructions(); > + } > + return ret; > +} > > static void *qemu_tcg_cpu_thread_fn(void *arg) > { > @@ -1150,8 +1209,35 @@ static void *qemu_tcg_cpu_thread_fn(void *arg) > /* process any pending work */ > atomic_mb_set(&exit_request, 1); > > + cpu = first_cpu; > + > while (1) { > - tcg_exec_all(); > + /* Account partial waits to QEMU_CLOCK_VIRTUAL. */ > + qemu_account_warp_timer(); > + > + if (!cpu) { > + cpu = first_cpu; > + } > + > + for (; cpu != NULL && !exit_request; cpu = CPU_NEXT(cpu)) { > + > + qemu_clock_enable(QEMU_CLOCK_VIRTUAL, > + (cpu->singlestep_enabled & SSTEP_NOTIMER) == 0); > + > + if (cpu_can_run(cpu)) { > + int r = tcg_cpu_exec(cpu); > + if (r == EXCP_DEBUG) { > + cpu_handle_guest_debug(cpu); > + break; > + } > + } else if (cpu->stop || cpu->stopped) { > + break; > + } > + > + } /* for cpu.. */ > + > + /* Pairs with smp_wmb in qemu_cpu_kick. */ > + atomic_mb_set(&exit_request, 0); > > if (use_icount) { > int64_t deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL); > @@ -1448,99 +1534,6 @@ int vm_stop_force_state(RunState state) > } > } > > -static int64_t tcg_get_icount_limit(void) > -{ > - int64_t deadline; > - > - if (replay_mode != REPLAY_MODE_PLAY) { > - deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL); > - > - /* Maintain prior (possibly buggy) behaviour where if no deadline > - * was set (as there is no QEMU_CLOCK_VIRTUAL timer) or it is more than > - * INT32_MAX nanoseconds ahead, we still use INT32_MAX > - * nanoseconds. > - */ > - if ((deadline < 0) || (deadline > INT32_MAX)) { > - deadline = INT32_MAX; > - } > - > - return qemu_icount_round(deadline); > - } else { > - return replay_get_instructions(); > - } > -} > - > -static int tcg_cpu_exec(CPUState *cpu) > -{ > - int ret; > -#ifdef CONFIG_PROFILER > - int64_t ti; > -#endif > - > -#ifdef CONFIG_PROFILER > - ti = profile_getclock(); > -#endif > - if (use_icount) { > - int64_t count; > - int decr; > - timers_state.qemu_icount -= (cpu->icount_decr.u16.low > - + cpu->icount_extra); > - cpu->icount_decr.u16.low = 0; > - cpu->icount_extra = 0; > - count = tcg_get_icount_limit(); > - timers_state.qemu_icount += count; > - decr = (count > 0xffff) ? 0xffff : count; > - count -= decr; > - cpu->icount_decr.u16.low = decr; > - cpu->icount_extra = count; > - } > - ret = cpu_exec(cpu); > -#ifdef CONFIG_PROFILER > - tcg_time += profile_getclock() - ti; > -#endif > - if (use_icount) { > - /* Fold pending instructions back into the > - instruction counter, and clear the interrupt flag. */ > - timers_state.qemu_icount -= (cpu->icount_decr.u16.low > - + cpu->icount_extra); > - cpu->icount_decr.u32 = 0; > - cpu->icount_extra = 0; > - replay_account_executed_instructions(); > - } > - return ret; > -} > - > -static void tcg_exec_all(void) > -{ > - int r; > - > - /* Account partial waits to QEMU_CLOCK_VIRTUAL. */ > - qemu_account_warp_timer(); > - > - if (next_cpu == NULL) { > - next_cpu = first_cpu; > - } > - for (; next_cpu != NULL && !exit_request; next_cpu = CPU_NEXT(next_cpu)) { > - CPUState *cpu = next_cpu; > - > - qemu_clock_enable(QEMU_CLOCK_VIRTUAL, > - (cpu->singlestep_enabled & SSTEP_NOTIMER) == 0); > - > - if (cpu_can_run(cpu)) { > - r = tcg_cpu_exec(cpu); > - if (r == EXCP_DEBUG) { > - cpu_handle_guest_debug(cpu); > - break; > - } > - } else if (cpu->stop || cpu->stopped) { > - break; > - } > - } > - > - /* Pairs with smp_wmb in qemu_cpu_kick. */ > - atomic_mb_set(&exit_request, 0); > -} > - > void list_cpus(FILE *f, fprintf_function cpu_fprintf, const char *optarg) > { > /* XXX: implement xxx_cpu_list for targets that still miss it */
On 06/03/2016 01:40 PM, Alex Bennée wrote: > In preparation for multi-threaded TCG we remove tcg_exec_all and move > all the CPU cycling into the main thread function. When MTTCG is enabled > we shall use a separate thread function which only handles one vCPU. > > Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <rth@twiddle.net> r~
diff --git a/cpus.c b/cpus.c index c404dd7..4cc2ce6 100644 --- a/cpus.c +++ b/cpus.c @@ -69,7 +69,6 @@ #endif /* CONFIG_LINUX */ -static CPUState *next_cpu; int64_t max_delay; int64_t max_advance; @@ -1119,7 +1118,67 @@ static void *qemu_dummy_cpu_thread_fn(void *arg) #endif } -static void tcg_exec_all(void); +static int64_t tcg_get_icount_limit(void) +{ + int64_t deadline; + + if (replay_mode != REPLAY_MODE_PLAY) { + deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL); + + /* Maintain prior (possibly buggy) behaviour where if no deadline + * was set (as there is no QEMU_CLOCK_VIRTUAL timer) or it is more than + * INT32_MAX nanoseconds ahead, we still use INT32_MAX + * nanoseconds. + */ + if ((deadline < 0) || (deadline > INT32_MAX)) { + deadline = INT32_MAX; + } + + return qemu_icount_round(deadline); + } else { + return replay_get_instructions(); + } +} + +static int tcg_cpu_exec(CPUState *cpu) +{ + int ret; +#ifdef CONFIG_PROFILER + int64_t ti; +#endif + +#ifdef CONFIG_PROFILER + ti = profile_getclock(); +#endif + if (use_icount) { + int64_t count; + int decr; + timers_state.qemu_icount -= (cpu->icount_decr.u16.low + + cpu->icount_extra); + cpu->icount_decr.u16.low = 0; + cpu->icount_extra = 0; + count = tcg_get_icount_limit(); + timers_state.qemu_icount += count; + decr = (count > 0xffff) ? 0xffff : count; + count -= decr; + cpu->icount_decr.u16.low = decr; + cpu->icount_extra = count; + } + ret = cpu_exec(cpu); +#ifdef CONFIG_PROFILER + tcg_time += profile_getclock() - ti; +#endif + if (use_icount) { + /* Fold pending instructions back into the + instruction counter, and clear the interrupt flag. */ + timers_state.qemu_icount -= (cpu->icount_decr.u16.low + + cpu->icount_extra); + cpu->icount_decr.u32 = 0; + cpu->icount_extra = 0; + replay_account_executed_instructions(); + } + return ret; +} static void *qemu_tcg_cpu_thread_fn(void *arg) { @@ -1150,8 +1209,35 @@ static void *qemu_tcg_cpu_thread_fn(void *arg) /* process any pending work */ atomic_mb_set(&exit_request, 1); + cpu = first_cpu; + while (1) { - tcg_exec_all(); + /* Account partial waits to QEMU_CLOCK_VIRTUAL. */ + qemu_account_warp_timer(); + + if (!cpu) { + cpu = first_cpu; + } + + for (; cpu != NULL && !exit_request; cpu = CPU_NEXT(cpu)) { + + qemu_clock_enable(QEMU_CLOCK_VIRTUAL, + (cpu->singlestep_enabled & SSTEP_NOTIMER) == 0); + + if (cpu_can_run(cpu)) { + int r = tcg_cpu_exec(cpu); + if (r == EXCP_DEBUG) { + cpu_handle_guest_debug(cpu); + break; + } + } else if (cpu->stop || cpu->stopped) { + break; + } + + } /* for cpu.. */ + + /* Pairs with smp_wmb in qemu_cpu_kick. */ + atomic_mb_set(&exit_request, 0); if (use_icount) { int64_t deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL); @@ -1448,99 +1534,6 @@ int vm_stop_force_state(RunState state) } } -static int64_t tcg_get_icount_limit(void) -{ - int64_t deadline; - - if (replay_mode != REPLAY_MODE_PLAY) { - deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL); - - /* Maintain prior (possibly buggy) behaviour where if no deadline - * was set (as there is no QEMU_CLOCK_VIRTUAL timer) or it is more than - * INT32_MAX nanoseconds ahead, we still use INT32_MAX - * nanoseconds. - */ - if ((deadline < 0) || (deadline > INT32_MAX)) { - deadline = INT32_MAX; - } - - return qemu_icount_round(deadline); - } else { - return replay_get_instructions(); - } -} - -static int tcg_cpu_exec(CPUState *cpu) -{ - int ret; -#ifdef CONFIG_PROFILER - int64_t ti; -#endif - -#ifdef CONFIG_PROFILER - ti = profile_getclock(); -#endif - if (use_icount) { - int64_t count; - int decr; - timers_state.qemu_icount -= (cpu->icount_decr.u16.low - + cpu->icount_extra); - cpu->icount_decr.u16.low = 0; - cpu->icount_extra = 0; - count = tcg_get_icount_limit(); - timers_state.qemu_icount += count; - decr = (count > 0xffff) ? 0xffff : count; - count -= decr; - cpu->icount_decr.u16.low = decr; - cpu->icount_extra = count; - } - ret = cpu_exec(cpu); -#ifdef CONFIG_PROFILER - tcg_time += profile_getclock() - ti; -#endif - if (use_icount) { - /* Fold pending instructions back into the - instruction counter, and clear the interrupt flag. */ - timers_state.qemu_icount -= (cpu->icount_decr.u16.low - + cpu->icount_extra); - cpu->icount_decr.u32 = 0; - cpu->icount_extra = 0; - replay_account_executed_instructions(); - } - return ret; -} - -static void tcg_exec_all(void) -{ - int r; - - /* Account partial waits to QEMU_CLOCK_VIRTUAL. */ - qemu_account_warp_timer(); - - if (next_cpu == NULL) { - next_cpu = first_cpu; - } - for (; next_cpu != NULL && !exit_request; next_cpu = CPU_NEXT(next_cpu)) { - CPUState *cpu = next_cpu; - - qemu_clock_enable(QEMU_CLOCK_VIRTUAL, - (cpu->singlestep_enabled & SSTEP_NOTIMER) == 0); - - if (cpu_can_run(cpu)) { - r = tcg_cpu_exec(cpu); - if (r == EXCP_DEBUG) { - cpu_handle_guest_debug(cpu); - break; - } - } else if (cpu->stop || cpu->stopped) { - break; - } - } - - /* Pairs with smp_wmb in qemu_cpu_kick. */ - atomic_mb_set(&exit_request, 0); -} - void list_cpus(FILE *f, fprintf_function cpu_fprintf, const char *optarg) { /* XXX: implement xxx_cpu_list for targets that still miss it */
In preparation for multi-threaded TCG we remove tcg_exec_all and move all the CPU cycling into the main thread function. When MTTCG is enabled we shall use a separate thread function which only handles one vCPU. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> --- v2 - update timer calls to new API on rebase v3 - move tcg_cpu_exec above thread function, drop static fwd declaration --- cpus.c | 185 +++++++++++++++++++++++++++++++---------------------------------- 1 file changed, 89 insertions(+), 96 deletions(-)