diff options
author | 2016-04-11 10:41:07 +0300 | |
---|---|---|
committer | 2016-04-13 08:17:18 +0300 | |
commit | e09b41010ba33a20a87472ee821fa407a5b8da36 (patch) | |
tree | d10dc367189862e7ca5c592f033dc3726e1df4e3 /kernel/arch/powerpc/kvm/book3s_hv.c | |
parent | f93b97fd65072de626c074dbe099a1fff05ce060 (diff) |
These changes are the raw update to linux-4.4.6-rt14. Kernel sources
are taken from kernel.org, and rt patch from the rt wiki download page.
During the rebasing, the following patch collided:
Force tick interrupt and get rid of softirq magic(I70131fb85).
Collisions have been removed because its logic was found on the
source already.
Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>
Diffstat (limited to 'kernel/arch/powerpc/kvm/book3s_hv.c')
-rw-r--r-- | kernel/arch/powerpc/kvm/book3s_hv.c | 742 |
1 files changed, 602 insertions, 140 deletions
diff --git a/kernel/arch/powerpc/kvm/book3s_hv.c b/kernel/arch/powerpc/kvm/book3s_hv.c index 3e9087f45..df34a6432 100644 --- a/kernel/arch/powerpc/kvm/book3s_hv.c +++ b/kernel/arch/powerpc/kvm/book3s_hv.c @@ -36,7 +36,6 @@ #include <asm/reg.h> #include <asm/cputable.h> -#include <asm/cache.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/uaccess.h> @@ -75,12 +74,12 @@ static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1); -#if defined(CONFIG_PPC_64K_PAGES) -#define MPP_BUFFER_ORDER 0 -#elif defined(CONFIG_PPC_4K_PAGES) -#define MPP_BUFFER_ORDER 3 -#endif - +static int dynamic_mt_modes = 6; +module_param(dynamic_mt_modes, int, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(dynamic_mt_modes, "Set of allowed dynamic micro-threading modes: 0 (= none), 2, 4, or 6 (= 2 or 4)"); +static int target_smt_mode; +module_param(target_smt_mode, int, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(target_smt_mode, "Target threads per core (0 = max)"); static void kvmppc_end_cede(struct kvm_vcpu *vcpu); static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); @@ -114,19 +113,20 @@ static bool kvmppc_ipi_thread(int cpu) static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) { - int cpu = vcpu->cpu; - struct swait_head *wqp; + int cpu; + struct swait_queue_head *wqp; wqp = kvm_arch_vcpu_wq(vcpu); - if (swaitqueue_active(wqp)) { - swait_wake_interruptible(wqp); + if (swait_active(wqp)) { + swake_up(wqp); ++vcpu->stat.halt_wakeup; } - if (kvmppc_ipi_thread(cpu + vcpu->arch.ptid)) + if (kvmppc_ipi_thread(vcpu->arch.thread_cpu)) return; /* CPU points to the first thread of the core */ + cpu = vcpu->cpu; if (cpu >= 0 && cpu < nr_cpu_ids && cpu_online(cpu)) smp_send_reschedule(cpu); } @@ -164,6 +164,27 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) * they should never fail.) */ +static void kvmppc_core_start_stolen(struct kvmppc_vcore *vc) +{ + unsigned long flags; + + spin_lock_irqsave(&vc->stoltb_lock, flags); + vc->preempt_tb = mftb(); + spin_unlock_irqrestore(&vc->stoltb_lock, flags); +} + +static void kvmppc_core_end_stolen(struct kvmppc_vcore *vc) +{ + unsigned long flags; + + spin_lock_irqsave(&vc->stoltb_lock, flags); + if (vc->preempt_tb != TB_NIL) { + vc->stolen_tb += mftb() - vc->preempt_tb; + vc->preempt_tb = TB_NIL; + } + spin_unlock_irqrestore(&vc->stoltb_lock, flags); +} + static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu) { struct kvmppc_vcore *vc = vcpu->arch.vcore; @@ -175,14 +196,9 @@ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu) * vcpu, and once it is set to this vcpu, only this task * ever sets it to NULL. */ - if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE) { - spin_lock_irqsave(&vc->stoltb_lock, flags); - if (vc->preempt_tb != TB_NIL) { - vc->stolen_tb += mftb() - vc->preempt_tb; - vc->preempt_tb = TB_NIL; - } - spin_unlock_irqrestore(&vc->stoltb_lock, flags); - } + if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING) + kvmppc_core_end_stolen(vc); + spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST && vcpu->arch.busy_preempt != TB_NIL) { @@ -197,11 +213,9 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) struct kvmppc_vcore *vc = vcpu->arch.vcore; unsigned long flags; - if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE) { - spin_lock_irqsave(&vc->stoltb_lock, flags); - vc->preempt_tb = mftb(); - spin_unlock_irqrestore(&vc->stoltb_lock, flags); - } + if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING) + kvmppc_core_start_stolen(vc); + spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags); if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST) vcpu->arch.busy_preempt = mftb(); @@ -210,16 +224,22 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr) { + /* + * Check for illegal transactional state bit combination + * and if we find it, force the TS field to a safe state. + */ + if ((msr & MSR_TS_MASK) == MSR_TS_MASK) + msr &= ~MSR_TS_MASK; vcpu->arch.shregs.msr = msr; kvmppc_end_cede(vcpu); } -void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr) +static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr) { vcpu->arch.pvr = pvr; } -int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) +static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) { unsigned long pcr = 0; struct kvmppc_vcore *vc = vcpu->arch.vcore; @@ -259,7 +279,7 @@ int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) return 0; } -void kvmppc_dump_regs(struct kvm_vcpu *vcpu) +static void kvmppc_dump_regs(struct kvm_vcpu *vcpu) { int r; @@ -292,7 +312,7 @@ void kvmppc_dump_regs(struct kvm_vcpu *vcpu) vcpu->arch.last_inst); } -struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id) +static struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id) { int r; struct kvm_vcpu *v, *ret = NULL; @@ -641,7 +661,8 @@ static int kvm_arch_vcpu_yield_to(struct kvm_vcpu *target) spin_lock(&vcore->lock); if (target->arch.state == KVMPPC_VCPU_RUNNABLE && - vcore->vcore_state != VCORE_INACTIVE) + vcore->vcore_state != VCORE_INACTIVE && + vcore->runner) target = vcore->runner; spin_unlock(&vcore->lock); @@ -686,8 +707,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) tvcpu->arch.prodded = 1; smp_mb(); if (vcpu->arch.ceded) { - if (swaitqueue_active(&vcpu->wq)) { - swait_wake_interruptible(&vcpu->wq); + if (swait_active(&vcpu->wq)) { + swake_up(&vcpu->wq); vcpu->stat.halt_wakeup++; } } @@ -1426,18 +1447,12 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core) INIT_LIST_HEAD(&vcore->runnable_threads); spin_lock_init(&vcore->lock); spin_lock_init(&vcore->stoltb_lock); - init_swait_head(&vcore->wq); + init_swait_queue_head(&vcore->wq); vcore->preempt_tb = TB_NIL; vcore->lpcr = kvm->arch.lpcr; vcore->first_vcpuid = core * threads_per_subcore; vcore->kvm = kvm; - - vcore->mpp_buffer_is_valid = false; - - if (cpu_has_feature(CPU_FTR_ARCH_207S)) - vcore->mpp_buffer = (void *)__get_free_pages( - GFP_KERNEL|__GFP_ZERO, - MPP_BUFFER_ORDER); + INIT_LIST_HEAD(&vcore->preempt_list); return vcore; } @@ -1655,6 +1670,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, spin_unlock(&vcore->lock); vcpu->arch.vcore = vcore; vcpu->arch.ptid = vcpu->vcpu_id - vcore->first_vcpuid; + vcpu->arch.thread_cpu = -1; vcpu->arch.cpu_type = KVM_CPU_3S_64; kvmppc_sanity_check(vcpu); @@ -1749,6 +1765,7 @@ static int kvmppc_grab_hwthread(int cpu) /* Ensure the thread won't go into the kernel if it wakes */ tpaca->kvm_hstate.kvm_vcpu = NULL; + tpaca->kvm_hstate.kvm_vcore = NULL; tpaca->kvm_hstate.napping = 0; smp_wmb(); tpaca->kvm_hstate.hwthread_req = 1; @@ -1780,26 +1797,32 @@ static void kvmppc_release_hwthread(int cpu) tpaca = &paca[cpu]; tpaca->kvm_hstate.hwthread_req = 0; tpaca->kvm_hstate.kvm_vcpu = NULL; + tpaca->kvm_hstate.kvm_vcore = NULL; + tpaca->kvm_hstate.kvm_split_mode = NULL; } -static void kvmppc_start_thread(struct kvm_vcpu *vcpu) +static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc) { int cpu; struct paca_struct *tpaca; - struct kvmppc_vcore *vc = vcpu->arch.vcore; + struct kvmppc_vcore *mvc = vc->master_vcore; - if (vcpu->arch.timer_running) { - hrtimer_try_to_cancel(&vcpu->arch.dec_timer); - vcpu->arch.timer_running = 0; + cpu = vc->pcpu; + if (vcpu) { + if (vcpu->arch.timer_running) { + hrtimer_try_to_cancel(&vcpu->arch.dec_timer); + vcpu->arch.timer_running = 0; + } + cpu += vcpu->arch.ptid; + vcpu->cpu = mvc->pcpu; + vcpu->arch.thread_cpu = cpu; } - cpu = vc->pcpu + vcpu->arch.ptid; tpaca = &paca[cpu]; - tpaca->kvm_hstate.kvm_vcore = vc; - tpaca->kvm_hstate.ptid = vcpu->arch.ptid; - vcpu->cpu = vc->pcpu; - /* Order stores to hstate.kvm_vcore etc. before store to kvm_vcpu */ - smp_wmb(); tpaca->kvm_hstate.kvm_vcpu = vcpu; + tpaca->kvm_hstate.ptid = cpu - mvc->pcpu; + /* Order stores to hstate.kvm_vcpu etc. before store to kvm_vcore */ + smp_wmb(); + tpaca->kvm_hstate.kvm_vcore = mvc; if (cpu != smp_processor_id()) kvmppc_ipi_thread(cpu); } @@ -1812,12 +1835,12 @@ static void kvmppc_wait_for_nap(void) for (loops = 0; loops < 1000000; ++loops) { /* * Check if all threads are finished. - * We set the vcpu pointer when starting a thread + * We set the vcore pointer when starting a thread * and the thread clears it when finished, so we look - * for any threads that still have a non-NULL vcpu ptr. + * for any threads that still have a non-NULL vcore ptr. */ for (i = 1; i < threads_per_subcore; ++i) - if (paca[cpu + i].kvm_hstate.kvm_vcpu) + if (paca[cpu + i].kvm_hstate.kvm_vcore) break; if (i == threads_per_subcore) { HMT_medium(); @@ -1827,7 +1850,7 @@ static void kvmppc_wait_for_nap(void) } HMT_medium(); for (i = 1; i < threads_per_subcore; ++i) - if (paca[cpu + i].kvm_hstate.kvm_vcpu) + if (paca[cpu + i].kvm_hstate.kvm_vcore) pr_err("KVM: CPU %d seems to be stuck\n", cpu + i); } @@ -1863,31 +1886,276 @@ static int on_primary_thread(void) return 1; } -static void kvmppc_start_saving_l2_cache(struct kvmppc_vcore *vc) +/* + * A list of virtual cores for each physical CPU. + * These are vcores that could run but their runner VCPU tasks are + * (or may be) preempted. + */ +struct preempted_vcore_list { + struct list_head list; + spinlock_t lock; +}; + +static DEFINE_PER_CPU(struct preempted_vcore_list, preempted_vcores); + +static void init_vcore_lists(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct preempted_vcore_list *lp = &per_cpu(preempted_vcores, cpu); + spin_lock_init(&lp->lock); + INIT_LIST_HEAD(&lp->list); + } +} + +static void kvmppc_vcore_preempt(struct kvmppc_vcore *vc) +{ + struct preempted_vcore_list *lp = this_cpu_ptr(&preempted_vcores); + + vc->vcore_state = VCORE_PREEMPT; + vc->pcpu = smp_processor_id(); + if (vc->num_threads < threads_per_subcore) { + spin_lock(&lp->lock); + list_add_tail(&vc->preempt_list, &lp->list); + spin_unlock(&lp->lock); + } + + /* Start accumulating stolen time */ + kvmppc_core_start_stolen(vc); +} + +static void kvmppc_vcore_end_preempt(struct kvmppc_vcore *vc) +{ + struct preempted_vcore_list *lp; + + kvmppc_core_end_stolen(vc); + if (!list_empty(&vc->preempt_list)) { + lp = &per_cpu(preempted_vcores, vc->pcpu); + spin_lock(&lp->lock); + list_del_init(&vc->preempt_list); + spin_unlock(&lp->lock); + } + vc->vcore_state = VCORE_INACTIVE; +} + +/* + * This stores information about the virtual cores currently + * assigned to a physical core. + */ +struct core_info { + int n_subcores; + int max_subcore_threads; + int total_threads; + int subcore_threads[MAX_SUBCORES]; + struct kvm *subcore_vm[MAX_SUBCORES]; + struct list_head vcs[MAX_SUBCORES]; +}; + +/* + * This mapping means subcores 0 and 1 can use threads 0-3 and 4-7 + * respectively in 2-way micro-threading (split-core) mode. + */ +static int subcore_thread_map[MAX_SUBCORES] = { 0, 4, 2, 6 }; + +static void init_core_info(struct core_info *cip, struct kvmppc_vcore *vc) +{ + int sub; + + memset(cip, 0, sizeof(*cip)); + cip->n_subcores = 1; + cip->max_subcore_threads = vc->num_threads; + cip->total_threads = vc->num_threads; + cip->subcore_threads[0] = vc->num_threads; + cip->subcore_vm[0] = vc->kvm; + for (sub = 0; sub < MAX_SUBCORES; ++sub) + INIT_LIST_HEAD(&cip->vcs[sub]); + list_add_tail(&vc->preempt_list, &cip->vcs[0]); +} + +static bool subcore_config_ok(int n_subcores, int n_threads) +{ + /* Can only dynamically split if unsplit to begin with */ + if (n_subcores > 1 && threads_per_subcore < MAX_SMT_THREADS) + return false; + if (n_subcores > MAX_SUBCORES) + return false; + if (n_subcores > 1) { + if (!(dynamic_mt_modes & 2)) + n_subcores = 4; + if (n_subcores > 2 && !(dynamic_mt_modes & 4)) + return false; + } + + return n_subcores * roundup_pow_of_two(n_threads) <= MAX_SMT_THREADS; +} + +static void init_master_vcore(struct kvmppc_vcore *vc) +{ + vc->master_vcore = vc; + vc->entry_exit_map = 0; + vc->in_guest = 0; + vc->napping_threads = 0; + vc->conferring_threads = 0; +} + +/* + * See if the existing subcores can be split into 3 (or fewer) subcores + * of at most two threads each, so we can fit in another vcore. This + * assumes there are at most two subcores and at most 6 threads in total. + */ +static bool can_split_piggybacked_subcores(struct core_info *cip) +{ + int sub, new_sub; + int large_sub = -1; + int thr; + int n_subcores = cip->n_subcores; + struct kvmppc_vcore *vc, *vcnext; + struct kvmppc_vcore *master_vc = NULL; + + for (sub = 0; sub < cip->n_subcores; ++sub) { + if (cip->subcore_threads[sub] <= 2) + continue; + if (large_sub >= 0) + return false; + large_sub = sub; + vc = list_first_entry(&cip->vcs[sub], struct kvmppc_vcore, + preempt_list); + if (vc->num_threads > 2) + return false; + n_subcores += (cip->subcore_threads[sub] - 1) >> 1; + } + if (large_sub < 0 || !subcore_config_ok(n_subcores + 1, 2)) + return false; + + /* + * Seems feasible, so go through and move vcores to new subcores. + * Note that when we have two or more vcores in one subcore, + * all those vcores must have only one thread each. + */ + new_sub = cip->n_subcores; + thr = 0; + sub = large_sub; + list_for_each_entry_safe(vc, vcnext, &cip->vcs[sub], preempt_list) { + if (thr >= 2) { + list_del(&vc->preempt_list); + list_add_tail(&vc->preempt_list, &cip->vcs[new_sub]); + /* vc->num_threads must be 1 */ + if (++cip->subcore_threads[new_sub] == 1) { + cip->subcore_vm[new_sub] = vc->kvm; + init_master_vcore(vc); + master_vc = vc; + ++cip->n_subcores; + } else { + vc->master_vcore = master_vc; + ++new_sub; + } + } + thr += vc->num_threads; + } + cip->subcore_threads[large_sub] = 2; + cip->max_subcore_threads = 2; + + return true; +} + +static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip) +{ + int n_threads = vc->num_threads; + int sub; + + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return false; + + if (n_threads < cip->max_subcore_threads) + n_threads = cip->max_subcore_threads; + if (subcore_config_ok(cip->n_subcores + 1, n_threads)) { + cip->max_subcore_threads = n_threads; + } else if (cip->n_subcores <= 2 && cip->total_threads <= 6 && + vc->num_threads <= 2) { + /* + * We may be able to fit another subcore in by + * splitting an existing subcore with 3 or 4 + * threads into two 2-thread subcores, or one + * with 5 or 6 threads into three subcores. + * We can only do this if those subcores have + * piggybacked virtual cores. + */ + if (!can_split_piggybacked_subcores(cip)) + return false; + } else { + return false; + } + + sub = cip->n_subcores; + ++cip->n_subcores; + cip->total_threads += vc->num_threads; + cip->subcore_threads[sub] = vc->num_threads; + cip->subcore_vm[sub] = vc->kvm; + init_master_vcore(vc); + list_del(&vc->preempt_list); + list_add_tail(&vc->preempt_list, &cip->vcs[sub]); + + return true; +} + +static bool can_piggyback_subcore(struct kvmppc_vcore *pvc, + struct core_info *cip, int sub) { - phys_addr_t phy_addr, mpp_addr; + struct kvmppc_vcore *vc; + int n_thr; - phy_addr = (phys_addr_t)virt_to_phys(vc->mpp_buffer); - mpp_addr = phy_addr & PPC_MPPE_ADDRESS_MASK; + vc = list_first_entry(&cip->vcs[sub], struct kvmppc_vcore, + preempt_list); - mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_ABORT); - logmpp(mpp_addr | PPC_LOGMPP_LOG_L2); + /* require same VM and same per-core reg values */ + if (pvc->kvm != vc->kvm || + pvc->tb_offset != vc->tb_offset || + pvc->pcr != vc->pcr || + pvc->lpcr != vc->lpcr) + return false; - vc->mpp_buffer_is_valid = true; + /* P8 guest with > 1 thread per core would see wrong TIR value */ + if (cpu_has_feature(CPU_FTR_ARCH_207S) && + (vc->num_threads > 1 || pvc->num_threads > 1)) + return false; + + n_thr = cip->subcore_threads[sub] + pvc->num_threads; + if (n_thr > cip->max_subcore_threads) { + if (!subcore_config_ok(cip->n_subcores, n_thr)) + return false; + cip->max_subcore_threads = n_thr; + } + + cip->total_threads += pvc->num_threads; + cip->subcore_threads[sub] = n_thr; + pvc->master_vcore = vc; + list_del(&pvc->preempt_list); + list_add_tail(&pvc->preempt_list, &cip->vcs[sub]); + + return true; } -static void kvmppc_start_restoring_l2_cache(const struct kvmppc_vcore *vc) +/* + * Work out whether it is possible to piggyback the execution of + * vcore *pvc onto the execution of the other vcores described in *cip. + */ +static bool can_piggyback(struct kvmppc_vcore *pvc, struct core_info *cip, + int target_threads) { - phys_addr_t phy_addr, mpp_addr; + int sub; - phy_addr = virt_to_phys(vc->mpp_buffer); - mpp_addr = phy_addr & PPC_MPPE_ADDRESS_MASK; + if (cip->total_threads + pvc->num_threads > target_threads) + return false; + for (sub = 0; sub < cip->n_subcores; ++sub) + if (cip->subcore_threads[sub] && + can_piggyback_subcore(pvc, cip, sub)) + return true; + + if (can_dynamic_split(pvc, cip)) + return true; - /* We must abort any in-progress save operations to ensure - * the table is valid so that prefetch engine knows when to - * stop prefetching. */ - logmpp(mpp_addr | PPC_LOGMPP_LOG_ABORT); - mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_WHOLE_TABLE); + return false; } static void prepare_threads(struct kvmppc_vcore *vc) @@ -1909,12 +2177,45 @@ static void prepare_threads(struct kvmppc_vcore *vc) } } -static void post_guest_process(struct kvmppc_vcore *vc) +static void collect_piggybacks(struct core_info *cip, int target_threads) +{ + struct preempted_vcore_list *lp = this_cpu_ptr(&preempted_vcores); + struct kvmppc_vcore *pvc, *vcnext; + + spin_lock(&lp->lock); + list_for_each_entry_safe(pvc, vcnext, &lp->list, preempt_list) { + if (!spin_trylock(&pvc->lock)) + continue; + prepare_threads(pvc); + if (!pvc->n_runnable) { + list_del_init(&pvc->preempt_list); + if (pvc->runner == NULL) { + pvc->vcore_state = VCORE_INACTIVE; + kvmppc_core_end_stolen(pvc); + } + spin_unlock(&pvc->lock); + continue; + } + if (!can_piggyback(pvc, cip, target_threads)) { + spin_unlock(&pvc->lock); + continue; + } + kvmppc_core_end_stolen(pvc); + pvc->vcore_state = VCORE_PIGGYBACK; + if (cip->total_threads >= target_threads) + break; + } + spin_unlock(&lp->lock); +} + +static void post_guest_process(struct kvmppc_vcore *vc, bool is_master) { + int still_running = 0; u64 now; long ret; struct kvm_vcpu *vcpu, *vnext; + spin_lock(&vc->lock); now = get_tb(); list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads, arch.run_list) { @@ -1933,17 +2234,36 @@ static void post_guest_process(struct kvmppc_vcore *vc) vcpu->arch.ret = ret; vcpu->arch.trap = 0; - if (vcpu->arch.ceded) { - if (!is_kvmppc_resume_guest(ret)) - kvmppc_end_cede(vcpu); - else + if (is_kvmppc_resume_guest(vcpu->arch.ret)) { + if (vcpu->arch.pending_exceptions) + kvmppc_core_prepare_to_enter(vcpu); + if (vcpu->arch.ceded) kvmppc_set_timer(vcpu); - } - if (!is_kvmppc_resume_guest(vcpu->arch.ret)) { + else + ++still_running; + } else { kvmppc_remove_runnable(vc, vcpu); wake_up(&vcpu->arch.cpu_run); } } + list_del_init(&vc->preempt_list); + if (!is_master) { + if (still_running > 0) { + kvmppc_vcore_preempt(vc); + } else if (vc->runner) { + vc->vcore_state = VCORE_PREEMPT; + kvmppc_core_start_stolen(vc); + } else { + vc->vcore_state = VCORE_INACTIVE; + } + if (vc->n_runnable > 0 && vc->runner == NULL) { + /* make sure there's a candidate runner awake */ + vcpu = list_first_entry(&vc->runnable_threads, + struct kvm_vcpu, arch.run_list); + wake_up(&vcpu->arch.cpu_run); + } + } + spin_unlock(&vc->lock); } /* @@ -1955,6 +2275,15 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) struct kvm_vcpu *vcpu, *vnext; int i; int srcu_idx; + struct core_info core_info; + struct kvmppc_vcore *pvc, *vcnext; + struct kvm_split_mode split_info, *sip; + int split, subcore_size, active; + int sub; + bool thr0_done; + unsigned long cmd_bit, stat_bit; + int pcpu, thr; + int target_threads; /* * Remove from the list any threads that have a signal pending @@ -1969,11 +2298,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) /* * Initialize *vc. */ - vc->entry_exit_map = 0; + init_master_vcore(vc); vc->preempt_tb = TB_NIL; - vc->in_guest = 0; - vc->napping_threads = 0; - vc->conferring_threads = 0; /* * Make sure we are running on primary threads, and that secondary @@ -1991,60 +2317,176 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) goto out; } + /* + * See if we could run any other vcores on the physical core + * along with this one. + */ + init_core_info(&core_info, vc); + pcpu = smp_processor_id(); + target_threads = threads_per_subcore; + if (target_smt_mode && target_smt_mode < target_threads) + target_threads = target_smt_mode; + if (vc->num_threads < target_threads) + collect_piggybacks(&core_info, target_threads); + + /* Decide on micro-threading (split-core) mode */ + subcore_size = threads_per_subcore; + cmd_bit = stat_bit = 0; + split = core_info.n_subcores; + sip = NULL; + if (split > 1) { + /* threads_per_subcore must be MAX_SMT_THREADS (8) here */ + if (split == 2 && (dynamic_mt_modes & 2)) { + cmd_bit = HID0_POWER8_1TO2LPAR; + stat_bit = HID0_POWER8_2LPARMODE; + } else { + split = 4; + cmd_bit = HID0_POWER8_1TO4LPAR; + stat_bit = HID0_POWER8_4LPARMODE; + } + subcore_size = MAX_SMT_THREADS / split; + sip = &split_info; + memset(&split_info, 0, sizeof(split_info)); + split_info.rpr = mfspr(SPRN_RPR); + split_info.pmmar = mfspr(SPRN_PMMAR); + split_info.ldbar = mfspr(SPRN_LDBAR); + split_info.subcore_size = subcore_size; + for (sub = 0; sub < core_info.n_subcores; ++sub) + split_info.master_vcs[sub] = + list_first_entry(&core_info.vcs[sub], + struct kvmppc_vcore, preempt_list); + /* order writes to split_info before kvm_split_mode pointer */ + smp_wmb(); + } + pcpu = smp_processor_id(); + for (thr = 0; thr < threads_per_subcore; ++thr) + paca[pcpu + thr].kvm_hstate.kvm_split_mode = sip; + + /* Initiate micro-threading (split-core) if required */ + if (cmd_bit) { + unsigned long hid0 = mfspr(SPRN_HID0); + + hid0 |= cmd_bit | HID0_POWER8_DYNLPARDIS; + mb(); + mtspr(SPRN_HID0, hid0); + isync(); + for (;;) { + hid0 = mfspr(SPRN_HID0); + if (hid0 & stat_bit) + break; + cpu_relax(); + } + } - vc->pcpu = smp_processor_id(); - list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) { - kvmppc_start_thread(vcpu); - kvmppc_create_dtl_entry(vcpu, vc); - trace_kvm_guest_enter(vcpu); + /* Start all the threads */ + active = 0; + for (sub = 0; sub < core_info.n_subcores; ++sub) { + thr = subcore_thread_map[sub]; + thr0_done = false; + active |= 1 << thr; + list_for_each_entry(pvc, &core_info.vcs[sub], preempt_list) { + pvc->pcpu = pcpu + thr; + list_for_each_entry(vcpu, &pvc->runnable_threads, + arch.run_list) { + kvmppc_start_thread(vcpu, pvc); + kvmppc_create_dtl_entry(vcpu, pvc); + trace_kvm_guest_enter(vcpu); + if (!vcpu->arch.ptid) + thr0_done = true; + active |= 1 << (thr + vcpu->arch.ptid); + } + /* + * We need to start the first thread of each subcore + * even if it doesn't have a vcpu. + */ + if (pvc->master_vcore == pvc && !thr0_done) + kvmppc_start_thread(NULL, pvc); + thr += pvc->num_threads; + } } - /* Set this explicitly in case thread 0 doesn't have a vcpu */ - get_paca()->kvm_hstate.kvm_vcore = vc; - get_paca()->kvm_hstate.ptid = 0; + /* + * Ensure that split_info.do_nap is set after setting + * the vcore pointer in the PACA of the secondaries. + */ + smp_mb(); + if (cmd_bit) + split_info.do_nap = 1; /* ask secondaries to nap when done */ + + /* + * When doing micro-threading, poke the inactive threads as well. + * This gets them to the nap instruction after kvm_do_nap, + * which reduces the time taken to unsplit later. + */ + if (split > 1) + for (thr = 1; thr < threads_per_subcore; ++thr) + if (!(active & (1 << thr))) + kvmppc_ipi_thread(pcpu + thr); vc->vcore_state = VCORE_RUNNING; preempt_disable(); trace_kvmppc_run_core(vc, 0); - spin_unlock(&vc->lock); + for (sub = 0; sub < core_info.n_subcores; ++sub) + list_for_each_entry(pvc, &core_info.vcs[sub], preempt_list) + spin_unlock(&pvc->lock); kvm_guest_enter(); srcu_idx = srcu_read_lock(&vc->kvm->srcu); - if (vc->mpp_buffer_is_valid) - kvmppc_start_restoring_l2_cache(vc); - __kvmppc_vcore_entry(); - spin_lock(&vc->lock); + srcu_read_unlock(&vc->kvm->srcu, srcu_idx); - if (vc->mpp_buffer) - kvmppc_start_saving_l2_cache(vc); + spin_lock(&vc->lock); + /* prevent other vcpu threads from doing kvmppc_start_thread() now */ + vc->vcore_state = VCORE_EXITING; - /* disable sending of IPIs on virtual external irqs */ - list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) - vcpu->cpu = -1; /* wait for secondary threads to finish writing their state to memory */ kvmppc_wait_for_nap(); - for (i = 0; i < threads_per_subcore; ++i) - kvmppc_release_hwthread(vc->pcpu + i); - /* prevent other vcpu threads from doing kvmppc_start_thread() now */ - vc->vcore_state = VCORE_EXITING; - spin_unlock(&vc->lock); - srcu_read_unlock(&vc->kvm->srcu, srcu_idx); + /* Return to whole-core mode if we split the core earlier */ + if (split > 1) { + unsigned long hid0 = mfspr(SPRN_HID0); + unsigned long loops = 0; + + hid0 &= ~HID0_POWER8_DYNLPARDIS; + stat_bit = HID0_POWER8_2LPARMODE | HID0_POWER8_4LPARMODE; + mb(); + mtspr(SPRN_HID0, hid0); + isync(); + for (;;) { + hid0 = mfspr(SPRN_HID0); + if (!(hid0 & stat_bit)) + break; + cpu_relax(); + ++loops; + } + split_info.do_nap = 0; + } + + /* Let secondaries go back to the offline loop */ + for (i = 0; i < threads_per_subcore; ++i) { + kvmppc_release_hwthread(pcpu + i); + if (sip && sip->napped[i]) + kvmppc_ipi_thread(pcpu + i); + } + + spin_unlock(&vc->lock); /* make sure updates to secondary vcpu structs are visible now */ smp_mb(); kvm_guest_exit(); - preempt_enable(); + for (sub = 0; sub < core_info.n_subcores; ++sub) + list_for_each_entry_safe(pvc, vcnext, &core_info.vcs[sub], + preempt_list) + post_guest_process(pvc, pvc == vc); spin_lock(&vc->lock); - post_guest_process(vc); + preempt_enable(); out: vc->vcore_state = VCORE_INACTIVE; @@ -2055,13 +2497,17 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) * Wait for some other vcpu thread to execute us, and * wake us up when we need to handle something in the host. */ -static void kvmppc_wait_for_exec(struct kvm_vcpu *vcpu, int wait_state) +static void kvmppc_wait_for_exec(struct kvmppc_vcore *vc, + struct kvm_vcpu *vcpu, int wait_state) { DEFINE_WAIT(wait); prepare_to_wait(&vcpu->arch.cpu_run, &wait, wait_state); - if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) + if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) { + spin_unlock(&vc->lock); schedule(); + spin_lock(&vc->lock); + } finish_wait(&vcpu->arch.cpu_run, &wait); } @@ -2073,9 +2519,9 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) { struct kvm_vcpu *vcpu; int do_sleep = 1; - DEFINE_SWAITER(wait); + DECLARE_SWAITQUEUE(wait); - swait_prepare(&vc->wq, &wait, TASK_INTERRUPTIBLE); + prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE); /* * Check one last time for pending exceptions and ceded state after @@ -2089,7 +2535,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) } if (!do_sleep) { - swait_finish(&vc->wq, &wait); + finish_swait(&vc->wq, &wait); return; } @@ -2097,7 +2543,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) trace_kvmppc_vcore_blocked(vc, 0); spin_unlock(&vc->lock); schedule(); - swait_finish(&vc->wq, &wait); + finish_swait(&vc->wq, &wait); spin_lock(&vc->lock); vc->vcore_state = VCORE_INACTIVE; trace_kvmppc_vcore_blocked(vc, 1); @@ -2136,22 +2582,35 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) * this thread straight away and have it join in. */ if (!signal_pending(current)) { - if (vc->vcore_state == VCORE_RUNNING && !VCORE_IS_EXITING(vc)) { + if (vc->vcore_state == VCORE_PIGGYBACK) { + struct kvmppc_vcore *mvc = vc->master_vcore; + if (spin_trylock(&mvc->lock)) { + if (mvc->vcore_state == VCORE_RUNNING && + !VCORE_IS_EXITING(mvc)) { + kvmppc_create_dtl_entry(vcpu, vc); + kvmppc_start_thread(vcpu, vc); + trace_kvm_guest_enter(vcpu); + } + spin_unlock(&mvc->lock); + } + } else if (vc->vcore_state == VCORE_RUNNING && + !VCORE_IS_EXITING(vc)) { kvmppc_create_dtl_entry(vcpu, vc); - kvmppc_start_thread(vcpu); + kvmppc_start_thread(vcpu, vc); trace_kvm_guest_enter(vcpu); } else if (vc->vcore_state == VCORE_SLEEPING) { - swait_wake(&vc->wq); + swake_up(&vc->wq); } } while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE && !signal_pending(current)) { + if (vc->vcore_state == VCORE_PREEMPT && vc->runner == NULL) + kvmppc_vcore_end_preempt(vc); + if (vc->vcore_state != VCORE_INACTIVE) { - spin_unlock(&vc->lock); - kvmppc_wait_for_exec(vcpu, TASK_INTERRUPTIBLE); - spin_lock(&vc->lock); + kvmppc_wait_for_exec(vc, vcpu, TASK_INTERRUPTIBLE); continue; } list_for_each_entry_safe(v, vn, &vc->runnable_threads, @@ -2177,11 +2636,12 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) vc->runner = vcpu; if (n_ceded == vc->n_runnable) { kvmppc_vcore_blocked(vc); - } else if (should_resched()) { - vc->vcore_state = VCORE_PREEMPT; + } else if (need_resched()) { + kvmppc_vcore_preempt(vc); /* Let something else run */ cond_resched_lock(&vc->lock); - vc->vcore_state = VCORE_INACTIVE; + if (vc->vcore_state == VCORE_PREEMPT) + kvmppc_vcore_end_preempt(vc); } else { kvmppc_run_core(vc); } @@ -2190,11 +2650,12 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE && (vc->vcore_state == VCORE_RUNNING || - vc->vcore_state == VCORE_EXITING)) { - spin_unlock(&vc->lock); - kvmppc_wait_for_exec(vcpu, TASK_UNINTERRUPTIBLE); - spin_lock(&vc->lock); - } + vc->vcore_state == VCORE_EXITING || + vc->vcore_state == VCORE_PIGGYBACK)) + kvmppc_wait_for_exec(vc, vcpu, TASK_UNINTERRUPTIBLE); + + if (vc->vcore_state == VCORE_PREEMPT && vc->runner == NULL) + kvmppc_vcore_end_preempt(vc); if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) { kvmppc_remove_runnable(vc, vcpu); @@ -2320,6 +2781,7 @@ static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm, static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm, struct kvm_dirty_log *log) { + struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int r; unsigned long n; @@ -2330,7 +2792,8 @@ static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm, if (log->slot >= KVM_USER_MEM_SLOTS) goto out; - memslot = id_to_memslot(kvm->memslots, log->slot); + slots = kvm_memslots(kvm); + memslot = id_to_memslot(slots, log->slot); r = -ENOENT; if (!memslot->dirty_bitmap) goto out; @@ -2373,16 +2836,18 @@ static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot, static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region *mem) { return 0; } static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old) + const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new) { unsigned long npages = mem->memory_size >> PAGE_SHIFT; + struct kvm_memslots *slots; struct kvm_memory_slot *memslot; if (npages && old->npages) { @@ -2392,7 +2857,8 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, * since the rmap array starts out as all zeroes, * i.e. no pages are dirty. */ - memslot = id_to_memslot(kvm->memslots, mem->slot); + slots = kvm_memslots(kvm); + memslot = id_to_memslot(slots, mem->slot); kvmppc_hv_get_dirty_log(kvm, memslot, NULL); } } @@ -2565,14 +3031,8 @@ static void kvmppc_free_vcores(struct kvm *kvm) { long int i; - for (i = 0; i < KVM_MAX_VCORES; ++i) { - if (kvm->arch.vcores[i] && kvm->arch.vcores[i]->mpp_buffer) { - struct kvmppc_vcore *vc = kvm->arch.vcores[i]; - free_pages((unsigned long)vc->mpp_buffer, - MPP_BUFFER_ORDER); - } + for (i = 0; i < KVM_MAX_VCORES; ++i) kfree(kvm->arch.vcores[i]); - } kvm->arch.online_vcores = 0; } @@ -2749,6 +3209,8 @@ static int kvmppc_book3s_init_hv(void) init_default_hcalls(); + init_vcore_lists(); + r = kvmppc_mmu_hv_init(); return r; } |