*/
if (!context_tracking_guest_enter()) {
instrumentation_begin();
- rcu_virt_note_context_switch(smp_processor_id());
+ rcu_virt_note_context_switch();
instrumentation_end();
}
}
struct srcu_struct srcu;
struct srcu_struct irq_srcu;
pid_t userspace_pid;
+ bool override_halt_poll_ns;
unsigned int max_halt_poll_ns;
u32 dirty_ring_size;
bool vm_bugged;
void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn);
/**
- * kvm_gfn_to_pfn_cache_init - prepare a cached kernel mapping and HPA for a
- * given guest physical address.
+ * kvm_gpc_init - initialize gfn_to_pfn_cache.
+ *
+ * @gpc: struct gfn_to_pfn_cache object.
+ *
+ * This sets up a gfn_to_pfn_cache by initializing locks. Note, the cache must
+ * be zero-allocated (or zeroed by the caller before init).
+ */
+void kvm_gpc_init(struct gfn_to_pfn_cache *gpc);
+
+/**
+ * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest
+ * physical address.
*
* @kvm: pointer to kvm instance.
* @gpc: struct gfn_to_pfn_cache object.
* kvm_gfn_to_pfn_cache_check() to ensure that the cache is valid before
* accessing the target page.
*/
-int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
- struct kvm_vcpu *vcpu, enum pfn_cache_usage usage,
- gpa_t gpa, unsigned long len);
+int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
+ struct kvm_vcpu *vcpu, enum pfn_cache_usage usage,
+ gpa_t gpa, unsigned long len);
/**
* kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache.
void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc);
/**
- * kvm_gfn_to_pfn_cache_destroy - destroy and unlink a gfn_to_pfn_cache.
+ * kvm_gpc_deactivate - deactivate and unlink a gfn_to_pfn_cache.
*
* @kvm: pointer to kvm instance.
* @gpc: struct gfn_to_pfn_cache object.
* This removes a cache from the @kvm's list to be processed on MMU notifier
* invocation.
*/
-void kvm_gfn_to_pfn_cache_destroy(struct kvm *kvm, struct gfn_to_pfn_cache *gpc);
+void kvm_gpc_deactivate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc);
void kvm_sigset_activate(struct kvm_vcpu *vcpu);
void kvm_sigset_deactivate(struct kvm_vcpu *vcpu);
struct kvm_enable_cap *cap);
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg);
+long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl,
+ unsigned long arg);
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);
* rcu_read_lock before reading the address, then rcu_read_unlock after
* taking the spinlock within the structure expected at that address.
*
+ * Note that it is not possible to acquire a lock within a structure
+ * allocated with SLAB_TYPESAFE_BY_RCU without first acquiring a reference
+ * as described above. The reason is that SLAB_TYPESAFE_BY_RCU pages
+ * are not zeroed before being given to the slab, which means that any
+ * locks must be initialized after each and every kmem_struct_alloc().
+ * Alternatively, make the ctor passed to kmem_cache_create() initialize
+ * the locks at page-allocation time, as is done in __i915_request_ctor(),
+ * sighand_ctor(), and anon_vma_ctor(). Such a ctor permits readers
+ * to safely acquire those ctor-initialized locks under rcu_read_lock()
+ * protection.
+ *
* Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU.
*/
/* Defer freeing slabs to RCU */
void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment
__malloc;
-#ifdef CONFIG_TRACING
void *kmalloc_trace(struct kmem_cache *s, gfp_t flags, size_t size)
__assume_kmalloc_alignment __alloc_size(3);
void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags,
int node, size_t size) __assume_kmalloc_alignment
__alloc_size(4);
-#else /* CONFIG_TRACING */
-/* Save a function call when CONFIG_TRACING=n */
-static __always_inline __alloc_size(3)
-void *kmalloc_trace(struct kmem_cache *s, gfp_t flags, size_t size)
-{
- void *ret = kmem_cache_alloc(s, flags);
-
- ret = kasan_kmalloc(s, ret, size, flags);
- return ret;
-}
-
-static __always_inline __alloc_size(4)
-void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags,
- int node, size_t size)
-{
- void *ret = kmem_cache_alloc_node(s, gfpflags, node);
-
- ret = kasan_kmalloc(s, ret, size, gfpflags);
- return ret;
-}
-#endif /* CONFIG_TRACING */
-
void *kmalloc_large(size_t size, gfp_t flags) __assume_page_alignment
__alloc_size(1);
return !(snap & RCU_DYNTICKS_IDX);
}
- /* Return true if the specified CPU is currently idle from an RCU viewpoint. */
- bool rcu_is_idle_cpu(int cpu)
- {
- return rcu_dynticks_in_eqs(rcu_dynticks_snap(cpu));
- }
-
/*
* Return true if the CPU corresponding to the specified rcu_data
* structure has spent some time in an extended quiescent state since
// where caller does not hold the root rcu_node structure's lock.
static void rcu_poll_gp_seq_start_unlocked(unsigned long *snap)
{
+ unsigned long flags;
struct rcu_node *rnp = rcu_get_root();
if (rcu_init_invoked()) {
lockdep_assert_irqs_enabled();
- raw_spin_lock_irq_rcu_node(rnp);
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
}
rcu_poll_gp_seq_start(snap);
if (rcu_init_invoked())
- raw_spin_unlock_irq_rcu_node(rnp);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
// Make the polled API aware of the end of a grace period, but where
// caller does not hold the root rcu_node structure's lock.
static void rcu_poll_gp_seq_end_unlocked(unsigned long *snap)
{
+ unsigned long flags;
struct rcu_node *rnp = rcu_get_root();
if (rcu_init_invoked()) {
lockdep_assert_irqs_enabled();
- raw_spin_lock_irq_rcu_node(rnp);
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
}
rcu_poll_gp_seq_end(snap);
if (rcu_init_invoked())
- raw_spin_unlock_irq_rcu_node(rnp);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
/*
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return 0;
- blkd = !!(rnp->qsmask & rdp->grpmask);
+ blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask);
trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
blkd ? TPS("cpuofl-bgp") : TPS("cpuofl"));
return 0;
struct rcu_node *rnp_old = NULL;
/* Funnel through hierarchy to reduce memory contention. */
- rnp = __this_cpu_read(rcu_data.mynode);
+ rnp = raw_cpu_read(rcu_data.mynode);
for (; rnp != NULL; rnp = rnp->parent) {
ret = (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) ||
!raw_spin_trylock(&rnp->fqslock);
raw_spin_unlock_rcu_node(rnp);
}
- /**
- * call_rcu() - Queue an RCU callback for invocation after a grace period.
- * @head: structure to be used for queueing the RCU updates.
- * @func: actual callback function to be invoked after the grace period
- *
- * The callback function will be invoked some time after a full grace
- * period elapses, in other words after all pre-existing RCU read-side
- * critical sections have completed. However, the callback function
- * might well execute concurrently with RCU read-side critical sections
- * that started after call_rcu() was invoked.
- *
- * RCU read-side critical sections are delimited by rcu_read_lock()
- * and rcu_read_unlock(), and may be nested. In addition, but only in
- * v5.0 and later, regions of code across which interrupts, preemption,
- * or softirqs have been disabled also serve as RCU read-side critical
- * sections. This includes hardware interrupt handlers, softirq handlers,
- * and NMI handlers.
- *
- * Note that all CPUs must agree that the grace period extended beyond
- * all pre-existing RCU read-side critical section. On systems with more
- * than one CPU, this means that when "func()" is invoked, each CPU is
- * guaranteed to have executed a full memory barrier since the end of its
- * last RCU read-side critical section whose beginning preceded the call
- * to call_rcu(). It also means that each CPU executing an RCU read-side
- * critical section that continues beyond the start of "func()" must have
- * executed a memory barrier after the call_rcu() but before the beginning
- * of that RCU read-side critical section. Note that these guarantees
- * include CPUs that are offline, idle, or executing in user mode, as
- * well as CPUs that are executing in the kernel.
- *
- * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
- * resulting RCU callback function "func()", then both CPU A and CPU B are
- * guaranteed to execute a full memory barrier during the time interval
- * between the call to call_rcu() and the invocation of "func()" -- even
- * if CPU A and CPU B are the same CPU (but again only if the system has
- * more than one CPU).
- *
- * Implementation of these memory-ordering guarantees is described here:
- * Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst.
- */
- void call_rcu(struct rcu_head *head, rcu_callback_t func)
+ static void
+ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy)
{
static atomic_t doublefrees;
unsigned long flags;
}
check_cb_ovld(rdp);
- if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags))
+ if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags, lazy))
return; // Enqueued onto ->nocb_bypass, so just leave.
// If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock.
rcu_segcblist_enqueue(&rdp->cblist, head);
local_irq_restore(flags);
}
}
- EXPORT_SYMBOL_GPL(call_rcu);
+ #ifdef CONFIG_RCU_LAZY
+ /**
+ * call_rcu_hurry() - Queue RCU callback for invocation after grace period, and
+ * flush all lazy callbacks (including the new one) to the main ->cblist while
+ * doing so.
+ *
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all pre-existing RCU read-side
+ * critical sections have completed.
+ *
+ * Use this API instead of call_rcu() if you don't want the callback to be
+ * invoked after very long periods of time, which can happen on systems without
+ * memory pressure and on systems which are lightly loaded or mostly idle.
+ * This function will cause callbacks to be invoked sooner than later at the
+ * expense of extra power. Other than that, this function is identical to, and
+ * reuses call_rcu()'s logic. Refer to call_rcu() for more details about memory
+ * ordering and other functionality.
+ */
+ void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func)
+ {
+ return __call_rcu_common(head, func, false);
+ }
+ EXPORT_SYMBOL_GPL(call_rcu_hurry);
+ #endif
+
+ /**
+ * call_rcu() - Queue an RCU callback for invocation after a grace period.
+ * By default the callbacks are 'lazy' and are kept hidden from the main
+ * ->cblist to prevent starting of grace periods too soon.
+ * If you desire grace periods to start very soon, use call_rcu_hurry().
+ *
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all pre-existing RCU read-side
+ * critical sections have completed. However, the callback function
+ * might well execute concurrently with RCU read-side critical sections
+ * that started after call_rcu() was invoked.
+ *
+ * RCU read-side critical sections are delimited by rcu_read_lock()
+ * and rcu_read_unlock(), and may be nested. In addition, but only in
+ * v5.0 and later, regions of code across which interrupts, preemption,
+ * or softirqs have been disabled also serve as RCU read-side critical
+ * sections. This includes hardware interrupt handlers, softirq handlers,
+ * and NMI handlers.
+ *
+ * Note that all CPUs must agree that the grace period extended beyond
+ * all pre-existing RCU read-side critical section. On systems with more
+ * than one CPU, this means that when "func()" is invoked, each CPU is
+ * guaranteed to have executed a full memory barrier since the end of its
+ * last RCU read-side critical section whose beginning preceded the call
+ * to call_rcu(). It also means that each CPU executing an RCU read-side
+ * critical section that continues beyond the start of "func()" must have
+ * executed a memory barrier after the call_rcu() but before the beginning
+ * of that RCU read-side critical section. Note that these guarantees
+ * include CPUs that are offline, idle, or executing in user mode, as
+ * well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * resulting RCU callback function "func()", then both CPU A and CPU B are
+ * guaranteed to execute a full memory barrier during the time interval
+ * between the call to call_rcu() and the invocation of "func()" -- even
+ * if CPU A and CPU B are the same CPU (but again only if the system has
+ * more than one CPU).
+ *
+ * Implementation of these memory-ordering guarantees is described here:
+ * Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst.
+ */
+ void call_rcu(struct rcu_head *head, rcu_callback_t func)
+ {
+ return __call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY));
+ }
+ EXPORT_SYMBOL_GPL(call_rcu);
/* Maximum number of jiffies to wait before draining a batch. */
#define KFREE_DRAIN_JIFFIES (5 * HZ)
if (rcu_gp_is_expedited())
synchronize_rcu_expedited();
else
- wait_rcu_gp(call_rcu);
+ wait_rcu_gp(call_rcu_hurry);
return;
}
{
unsigned long gseq = READ_ONCE(rcu_state.barrier_sequence);
unsigned long lseq = READ_ONCE(rdp->barrier_seq_snap);
+ bool wake_nocb = false;
+ bool was_alldone = false;
lockdep_assert_held(&rcu_state.barrier_lock);
if (rcu_seq_state(lseq) || !rcu_seq_state(gseq) || rcu_seq_ctr(lseq) != rcu_seq_ctr(gseq))
rdp->barrier_head.func = rcu_barrier_callback;
debug_rcu_head_queue(&rdp->barrier_head);
rcu_nocb_lock(rdp);
- WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies));
+ /*
+ * Flush bypass and wakeup rcuog if we add callbacks to an empty regular
+ * queue. This way we don't wait for bypass timer that can reach seconds
+ * if it's fully lazy.
+ */
+ was_alldone = rcu_rdp_is_offloaded(rdp) && !rcu_segcblist_pend_cbs(&rdp->cblist);
+ WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies, false));
+ wake_nocb = was_alldone && rcu_segcblist_pend_cbs(&rdp->cblist);
if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head)) {
atomic_inc(&rcu_state.barrier_cpu_count);
} else {
rcu_barrier_trace(TPS("IRQNQ"), -1, rcu_state.barrier_sequence);
}
rcu_nocb_unlock(rdp);
+ if (wake_nocb)
+ wake_nocb_gp(rdp, false);
smp_store_release(&rdp->barrier_seq_snap, gseq);
}
// Do any dangling deferred wakeups.
do_nocb_deferred_wakeup(rdp);
- /* QS for any half-done expedited grace period. */
- rcu_report_exp_rdp(rdp);
rcu_preempt_deferred_qs(current);
/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
my_rdp = this_cpu_ptr(&rcu_data);
my_rnp = my_rdp->mynode;
rcu_nocb_lock(my_rdp); /* irqs already disabled. */
- WARN_ON_ONCE(!rcu_nocb_flush_bypass(my_rdp, NULL, jiffies));
+ WARN_ON_ONCE(!rcu_nocb_flush_bypass(my_rdp, NULL, jiffies, false));
raw_spin_lock_rcu_node(my_rnp); /* irqs already disabled. */
/* Leverage recent GPs and set GP for new callbacks. */
needwake = rcu_advance_cbs(my_rnp, rdp) ||
projects / linux.git / commitdiff