#include <linux/page-flags.h>
#include <linux/srcu.h>
#include <linux/miscdevice.h>
+#include <linux/debugfs.h>
#include <asm/reg.h>
#include <asm/cputable.h>
#include <asm/hvcall.h>
#include <asm/switch_to.h>
#include <asm/smp.h>
+#include <asm/dbell.h>
#include <linux/gfp.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
+static bool kvmppc_ipi_thread(int cpu)
+{
+ /* On POWER8 for IPIs to threads in the same core, use msgsnd */
+ if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+ preempt_disable();
+ if (cpu_first_thread_sibling(cpu) ==
+ cpu_first_thread_sibling(smp_processor_id())) {
+ unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+ msg |= cpu_thread_in_core(cpu);
+ smp_mb();
+ __asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+ preempt_enable();
+ return true;
+ }
+ preempt_enable();
+ }
+
+#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
+ if (cpu >= 0 && cpu < nr_cpu_ids && paca[cpu].kvm_hstate.xics_phys) {
+ xics_wake_cpu(cpu);
+ return true;
+ }
+#endif
+
+ return false;
+}
+
static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
{
- int me;
int cpu = vcpu->cpu;
wait_queue_head_t *wqp;
++vcpu->stat.halt_wakeup;
}
- me = get_cpu();
+ if (kvmppc_ipi_thread(cpu + vcpu->arch.ptid))
+ return;
/* CPU points to the first thread of the core */
- if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) {
-#ifdef CONFIG_PPC_ICP_NATIVE
- int real_cpu = cpu + vcpu->arch.ptid;
- if (paca[real_cpu].kvm_hstate.xics_phys)
- xics_wake_cpu(real_cpu);
- else
-#endif
- if (cpu_online(cpu))
- smp_send_reschedule(cpu);
- }
- put_cpu();
+ if (cpu >= 0 && cpu < nr_cpu_ids && cpu_online(cpu))
+ smp_send_reschedule(cpu);
}
/*
/* Send the error out to userspace via KVM_RUN */
return rc;
+ case H_LOGICAL_CI_LOAD:
+ ret = kvmppc_h_logical_ci_load(vcpu);
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
+ case H_LOGICAL_CI_STORE:
+ ret = kvmppc_h_logical_ci_store(vcpu);
+ if (ret == H_TOO_HARD)
+ return RESUME_HOST;
+ break;
case H_SET_MODE:
ret = kvmppc_h_set_mode(vcpu, kvmppc_get_gpr(vcpu, 4),
kvmppc_get_gpr(vcpu, 5),
case H_CONFER:
case H_REGISTER_VPA:
case H_SET_MODE:
+ case H_LOGICAL_CI_LOAD:
+ case H_LOGICAL_CI_STORE:
#ifdef CONFIG_KVM_XICS
case H_XIRR:
case H_CPPR:
return vcore;
}
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+static struct debugfs_timings_element {
+ const char *name;
+ size_t offset;
+} timings[] = {
+ {"rm_entry", offsetof(struct kvm_vcpu, arch.rm_entry)},
+ {"rm_intr", offsetof(struct kvm_vcpu, arch.rm_intr)},
+ {"rm_exit", offsetof(struct kvm_vcpu, arch.rm_exit)},
+ {"guest", offsetof(struct kvm_vcpu, arch.guest_time)},
+ {"cede", offsetof(struct kvm_vcpu, arch.cede_time)},
+};
+
+#define N_TIMINGS (sizeof(timings) / sizeof(timings[0]))
+
+struct debugfs_timings_state {
+ struct kvm_vcpu *vcpu;
+ unsigned int buflen;
+ char buf[N_TIMINGS * 100];
+};
+
+static int debugfs_timings_open(struct inode *inode, struct file *file)
+{
+ struct kvm_vcpu *vcpu = inode->i_private;
+ struct debugfs_timings_state *p;
+
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (!p)
+ return -ENOMEM;
+
+ kvm_get_kvm(vcpu->kvm);
+ p->vcpu = vcpu;
+ file->private_data = p;
+
+ return nonseekable_open(inode, file);
+}
+
+static int debugfs_timings_release(struct inode *inode, struct file *file)
+{
+ struct debugfs_timings_state *p = file->private_data;
+
+ kvm_put_kvm(p->vcpu->kvm);
+ kfree(p);
+ return 0;
+}
+
+static ssize_t debugfs_timings_read(struct file *file, char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ struct debugfs_timings_state *p = file->private_data;
+ struct kvm_vcpu *vcpu = p->vcpu;
+ char *s, *buf_end;
+ struct kvmhv_tb_accumulator tb;
+ u64 count;
+ loff_t pos;
+ ssize_t n;
+ int i, loops;
+ bool ok;
+
+ if (!p->buflen) {
+ s = p->buf;
+ buf_end = s + sizeof(p->buf);
+ for (i = 0; i < N_TIMINGS; ++i) {
+ struct kvmhv_tb_accumulator *acc;
+
+ acc = (struct kvmhv_tb_accumulator *)
+ ((unsigned long)vcpu + timings[i].offset);
+ ok = false;
+ for (loops = 0; loops < 1000; ++loops) {
+ count = acc->seqcount;
+ if (!(count & 1)) {
+ smp_rmb();
+ tb = *acc;
+ smp_rmb();
+ if (count == acc->seqcount) {
+ ok = true;
+ break;
+ }
+ }
+ udelay(1);
+ }
+ if (!ok)
+ snprintf(s, buf_end - s, "%s: stuck\n",
+ timings[i].name);
+ else
+ snprintf(s, buf_end - s,
+ "%s: %llu %llu %llu %llu\n",
+ timings[i].name, count / 2,
+ tb_to_ns(tb.tb_total),
+ tb_to_ns(tb.tb_min),
+ tb_to_ns(tb.tb_max));
+ s += strlen(s);
+ }
+ p->buflen = s - p->buf;
+ }
+
+ pos = *ppos;
+ if (pos >= p->buflen)
+ return 0;
+ if (len > p->buflen - pos)
+ len = p->buflen - pos;
+ n = copy_to_user(buf, p->buf + pos, len);
+ if (n) {
+ if (n == len)
+ return -EFAULT;
+ len -= n;
+ }
+ *ppos = pos + len;
+ return len;
+}
+
+static ssize_t debugfs_timings_write(struct file *file, const char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ return -EACCES;
+}
+
+static const struct file_operations debugfs_timings_ops = {
+ .owner = THIS_MODULE,
+ .open = debugfs_timings_open,
+ .release = debugfs_timings_release,
+ .read = debugfs_timings_read,
+ .write = debugfs_timings_write,
+ .llseek = generic_file_llseek,
+};
+
+/* Create a debugfs directory for the vcpu */
+static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
+{
+ char buf[16];
+ struct kvm *kvm = vcpu->kvm;
+
+ snprintf(buf, sizeof(buf), "vcpu%u", id);
+ if (IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
+ return;
+ vcpu->arch.debugfs_dir = debugfs_create_dir(buf, kvm->arch.debugfs_dir);
+ if (IS_ERR_OR_NULL(vcpu->arch.debugfs_dir))
+ return;
+ vcpu->arch.debugfs_timings =
+ debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir,
+ vcpu, &debugfs_timings_ops);
+}
+
+#else /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
+static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
+{
+}
+#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
+
static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
unsigned int id)
{
vcpu->arch.cpu_type = KVM_CPU_3S_64;
kvmppc_sanity_check(vcpu);
+ debugfs_vcpu_init(vcpu, id);
+
return vcpu;
free_vcpu:
tpaca = &paca[cpu];
/* Ensure the thread won't go into the kernel if it wakes */
- tpaca->kvm_hstate.hwthread_req = 1;
tpaca->kvm_hstate.kvm_vcpu = NULL;
+ tpaca->kvm_hstate.napping = 0;
+ smp_wmb();
+ tpaca->kvm_hstate.hwthread_req = 1;
/*
* If the thread is already executing in the kernel (e.g. handling
}
cpu = vc->pcpu + vcpu->arch.ptid;
tpaca = &paca[cpu];
- tpaca->kvm_hstate.kvm_vcpu = vcpu;
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();
-#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
- if (cpu != smp_processor_id()) {
- xics_wake_cpu(cpu);
- if (vcpu->arch.ptid)
- ++vc->n_woken;
- }
-#endif
+ tpaca->kvm_hstate.kvm_vcpu = vcpu;
+ if (cpu != smp_processor_id())
+ kvmppc_ipi_thread(cpu);
}
-static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc)
+static void kvmppc_wait_for_nap(void)
{
- int i;
+ int cpu = smp_processor_id();
+ int i, loops;
- HMT_low();
- i = 0;
- while (vc->nap_count < vc->n_woken) {
- if (++i >= 1000000) {
- pr_err("kvmppc_wait_for_nap timeout %d %d\n",
- vc->nap_count, vc->n_woken);
- break;
+ for (loops = 0; loops < 1000000; ++loops) {
+ /*
+ * Check if all threads are finished.
+ * We set the vcpu 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 (i = 1; i < threads_per_subcore; ++i)
+ if (paca[cpu + i].kvm_hstate.kvm_vcpu)
+ break;
+ if (i == threads_per_subcore) {
+ HMT_medium();
+ return;
}
- cpu_relax();
+ HMT_low();
}
HMT_medium();
+ for (i = 1; i < threads_per_subcore; ++i)
+ if (paca[cpu + i].kvm_hstate.kvm_vcpu)
+ pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
}
/*
mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_WHOLE_TABLE);
}
+static void prepare_threads(struct kvmppc_vcore *vc)
+{
+ struct kvm_vcpu *vcpu, *vnext;
+
+ list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
+ arch.run_list) {
+ if (signal_pending(vcpu->arch.run_task))
+ vcpu->arch.ret = -EINTR;
+ else if (vcpu->arch.vpa.update_pending ||
+ vcpu->arch.slb_shadow.update_pending ||
+ vcpu->arch.dtl.update_pending)
+ vcpu->arch.ret = RESUME_GUEST;
+ else
+ continue;
+ kvmppc_remove_runnable(vc, vcpu);
+ wake_up(&vcpu->arch.cpu_run);
+ }
+}
+
+static void post_guest_process(struct kvmppc_vcore *vc)
+{
+ u64 now;
+ long ret;
+ struct kvm_vcpu *vcpu, *vnext;
+
+ now = get_tb();
+ list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
+ arch.run_list) {
+ /* cancel pending dec exception if dec is positive */
+ if (now < vcpu->arch.dec_expires &&
+ kvmppc_core_pending_dec(vcpu))
+ kvmppc_core_dequeue_dec(vcpu);
+
+ trace_kvm_guest_exit(vcpu);
+
+ ret = RESUME_GUEST;
+ if (vcpu->arch.trap)
+ ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu,
+ vcpu->arch.run_task);
+
+ vcpu->arch.ret = ret;
+ vcpu->arch.trap = 0;
+
+ if (vcpu->arch.ceded) {
+ if (!is_kvmppc_resume_guest(ret))
+ kvmppc_end_cede(vcpu);
+ else
+ kvmppc_set_timer(vcpu);
+ }
+ if (!is_kvmppc_resume_guest(vcpu->arch.ret)) {
+ kvmppc_remove_runnable(vc, vcpu);
+ wake_up(&vcpu->arch.cpu_run);
+ }
+ }
+}
+
/*
* Run a set of guest threads on a physical core.
* Called with vc->lock held.
*/
-static void kvmppc_run_core(struct kvmppc_vcore *vc)
+static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
{
- struct kvm_vcpu *vcpu, *vnext;
- long ret;
- u64 now;
- int i, need_vpa_update;
+ struct kvm_vcpu *vcpu;
+ int i;
int srcu_idx;
- struct kvm_vcpu *vcpus_to_update[threads_per_core];
- /* don't start if any threads have a signal pending */
- need_vpa_update = 0;
- list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
- if (signal_pending(vcpu->arch.run_task))
- return;
- if (vcpu->arch.vpa.update_pending ||
- vcpu->arch.slb_shadow.update_pending ||
- vcpu->arch.dtl.update_pending)
- vcpus_to_update[need_vpa_update++] = vcpu;
- }
+ /*
+ * Remove from the list any threads that have a signal pending
+ * or need a VPA update done
+ */
+ prepare_threads(vc);
+
+ /* if the runner is no longer runnable, let the caller pick a new one */
+ if (vc->runner->arch.state != KVMPPC_VCPU_RUNNABLE)
+ return;
/*
- * Initialize *vc, in particular vc->vcore_state, so we can
- * drop the vcore lock if necessary.
+ * Initialize *vc.
*/
- vc->n_woken = 0;
- vc->nap_count = 0;
- vc->entry_exit_count = 0;
+ vc->entry_exit_map = 0;
vc->preempt_tb = TB_NIL;
- vc->vcore_state = VCORE_STARTING;
vc->in_guest = 0;
vc->napping_threads = 0;
vc->conferring_threads = 0;
- /*
- * Updating any of the vpas requires calling kvmppc_pin_guest_page,
- * which can't be called with any spinlocks held.
- */
- if (need_vpa_update) {
- spin_unlock(&vc->lock);
- for (i = 0; i < need_vpa_update; ++i)
- kvmppc_update_vpas(vcpus_to_update[i]);
- spin_lock(&vc->lock);
- }
-
/*
* Make sure we are running on primary threads, and that secondary
* threads are offline. Also check if the number of threads in this
*/
if ((threads_per_core > 1) &&
((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
- list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
+ list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
vcpu->arch.ret = -EBUSY;
+ kvmppc_remove_runnable(vc, vcpu);
+ wake_up(&vcpu->arch.cpu_run);
+ }
goto out;
}
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 */
- if (vc->nap_count < vc->n_woken)
- kvmppc_wait_for_nap(vc);
+ 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 */
kvm_guest_exit();
preempt_enable();
- cond_resched();
spin_lock(&vc->lock);
- now = get_tb();
- list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
- /* cancel pending dec exception if dec is positive */
- if (now < vcpu->arch.dec_expires &&
- kvmppc_core_pending_dec(vcpu))
- kvmppc_core_dequeue_dec(vcpu);
-
- trace_kvm_guest_exit(vcpu);
-
- ret = RESUME_GUEST;
- if (vcpu->arch.trap)
- ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu,
- vcpu->arch.run_task);
-
- vcpu->arch.ret = ret;
- vcpu->arch.trap = 0;
-
- if (vcpu->arch.ceded) {
- if (!is_kvmppc_resume_guest(ret))
- kvmppc_end_cede(vcpu);
- else
- kvmppc_set_timer(vcpu);
- }
- }
+ post_guest_process(vc);
out:
vc->vcore_state = VCORE_INACTIVE;
- list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
- arch.run_list) {
- if (!is_kvmppc_resume_guest(vcpu->arch.ret)) {
- kvmppc_remove_runnable(vc, vcpu);
- wake_up(&vcpu->arch.cpu_run);
- }
- }
-
trace_kvmppc_run_core(vc, 1);
}
* this thread straight away and have it join in.
*/
if (!signal_pending(current)) {
- if (vc->vcore_state == VCORE_RUNNING &&
- VCORE_EXIT_COUNT(vc) == 0) {
+ if (vc->vcore_state == VCORE_RUNNING && !VCORE_IS_EXITING(vc)) {
kvmppc_create_dtl_entry(vcpu, vc);
kvmppc_start_thread(vcpu);
trace_kvm_guest_enter(vcpu);
}
if (!vc->n_runnable || vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
break;
- vc->runner = vcpu;
n_ceded = 0;
list_for_each_entry(v, &vc->runnable_threads, arch.run_list) {
if (!v->arch.pending_exceptions)
else
v->arch.ceded = 0;
}
- if (n_ceded == vc->n_runnable)
+ vc->runner = vcpu;
+ if (n_ceded == vc->n_runnable) {
kvmppc_vcore_blocked(vc);
- else
+ } else if (should_resched()) {
+ vc->vcore_state = VCORE_PREEMPT;
+ /* Let something else run */
+ cond_resched_lock(&vc->lock);
+ vc->vcore_state = VCORE_INACTIVE;
+ } else {
kvmppc_run_core(vc);
+ }
vc->runner = NULL;
}
}
atomic_inc(&vcpu->kvm->arch.vcpus_running);
- /* Order vcpus_running vs. rma_setup_done, see kvmppc_alloc_reset_hpt */
+ /* Order vcpus_running vs. hpte_setup_done, see kvmppc_alloc_reset_hpt */
smp_mb();
/* On the first time here, set up HTAB and VRMA */
- if (!vcpu->kvm->arch.rma_setup_done) {
+ if (!vcpu->kvm->arch.hpte_setup_done) {
r = kvmppc_hv_setup_htab_rma(vcpu);
if (r)
goto out;
int srcu_idx;
mutex_lock(&kvm->lock);
- if (kvm->arch.rma_setup_done)
+ if (kvm->arch.hpte_setup_done)
goto out; /* another vcpu beat us to it */
/* Allocate hashed page table (if not done already) and reset it */
kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
- /* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */
+ /* Order updates to kvm->arch.lpcr etc. vs. hpte_setup_done */
smp_wmb();
- kvm->arch.rma_setup_done = 1;
+ kvm->arch.hpte_setup_done = 1;
err = 0;
out_srcu:
srcu_read_unlock(&kvm->srcu, srcu_idx);
static int kvmppc_core_init_vm_hv(struct kvm *kvm)
{
unsigned long lpcr, lpid;
+ char buf[32];
/* Allocate the guest's logical partition ID */
*/
kvm_hv_vm_activated();
+ /*
+ * Create a debugfs directory for the VM
+ */
+ snprintf(buf, sizeof(buf), "vm%d", current->pid);
+ kvm->arch.debugfs_dir = debugfs_create_dir(buf, kvm_debugfs_dir);
+ if (!IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
+ kvmppc_mmu_debugfs_init(kvm);
+
return 0;
}
static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
{
+ debugfs_remove_recursive(kvm->arch.debugfs_dir);
+
kvm_hv_vm_deactivated();
kvmppc_free_vcores(kvm);
projects / firefly-linux-kernel-4.4.55.git / blobdiff