struct kvm_pmc *pmc = perf_event->overflow_handler_context;
struct kvm_pmu *pmu = pmc_to_pmu(pmc);
- if (!test_and_set_bit(pmc->idx,
- (unsigned long *)&pmu->reprogram_pmi)) {
+ if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
}
struct kvm_pmc *pmc = perf_event->overflow_handler_context;
struct kvm_pmu *pmu = pmc_to_pmu(pmc);
- if (!test_and_set_bit(pmc->idx,
- (unsigned long *)&pmu->reprogram_pmi)) {
+ if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
}
pmc->perf_event = event;
- clear_bit(pmc->idx, (unsigned long*)&pmc_to_pmu(pmc)->reprogram_pmi);
+ pmc_to_pmu(pmc)->event_count++;
+ clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
+}
+
+static void pmc_pause_counter(struct kvm_pmc *pmc)
+{
+ u64 counter = pmc->counter;
+
+ if (!pmc->perf_event)
+ return;
+
+ /* update counter, reset event value to avoid redundant accumulation */
+ counter += perf_event_pause(pmc->perf_event, true);
+ pmc->counter = counter & pmc_bitmask(pmc);
+}
+
+static bool pmc_resume_counter(struct kvm_pmc *pmc)
+{
+ if (!pmc->perf_event)
+ return false;
+
+ /* recalibrate sample period and check if it's accepted by perf core */
+ if (perf_event_period(pmc->perf_event,
+ (-pmc->counter) & pmc_bitmask(pmc)))
+ return false;
+
+ /* reuse perf_event to serve as pmc_reprogram_counter() does*/
+ perf_event_enable(pmc->perf_event);
+
+ clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
+ return true;
}
void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
pmc->eventsel = eventsel;
- pmc_stop_counter(pmc);
+ pmc_pause_counter(pmc);
if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc))
return;
if (type == PERF_TYPE_RAW)
config = eventsel & X86_RAW_EVENT_MASK;
+ if (pmc->current_config == eventsel && pmc_resume_counter(pmc))
+ return;
+
+ pmc_release_perf_event(pmc);
+
+ pmc->current_config = eventsel;
pmc_reprogram_counter(pmc, type, config,
!(eventsel & ARCH_PERFMON_EVENTSEL_USR),
!(eventsel & ARCH_PERFMON_EVENTSEL_OS),
struct kvm_pmu_event_filter *filter;
struct kvm *kvm = pmc->vcpu->kvm;
- pmc_stop_counter(pmc);
+ pmc_pause_counter(pmc);
if (!en_field || !pmc_is_enabled(pmc))
return;
return;
}
+ if (pmc->current_config == (u64)ctrl && pmc_resume_counter(pmc))
+ return;
+
+ pmc_release_perf_event(pmc);
+
+ pmc->current_config = (u64)ctrl;
pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE,
kvm_x86_ops->pmu_ops->find_fixed_event(idx),
!(en_field & 0x2), /* exclude user */
void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
- u64 bitmask;
int bit;
- bitmask = pmu->reprogram_pmi;
-
- for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) {
+ for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) {
struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, bit);
if (unlikely(!pmc || !pmc->perf_event)) {
- clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi);
+ clear_bit(bit, pmu->reprogram_pmi);
continue;
}
reprogram_counter(pmu, bit);
}
+
+ /*
+ * Unused perf_events are only released if the corresponding MSRs
+ * weren't accessed during the last vCPU time slice. kvm_arch_sched_in
+ * triggers KVM_REQ_PMU if cleanup is needed.
+ */
+ if (unlikely(pmu->need_cleanup))
+ kvm_pmu_cleanup(vcpu);
}
/* check if idx is a valid index to access PMU */
-int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
+int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
{
- return kvm_x86_ops->pmu_ops->is_valid_msr_idx(vcpu, idx);
+ return kvm_x86_ops->pmu_ops->is_valid_rdpmc_ecx(vcpu, idx);
}
bool is_vmware_backdoor_pmc(u32 pmc_idx)
if (is_vmware_backdoor_pmc(idx))
return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
- pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx, &mask);
+ pmc = kvm_x86_ops->pmu_ops->rdpmc_ecx_to_pmc(vcpu, idx, &mask);
if (!pmc)
return 1;
bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
{
- return kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr);
+ return kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr) ||
+ kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr);
+}
+
+static void kvm_pmu_mark_pmc_in_use(struct kvm_vcpu *vcpu, u32 msr)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, msr);
+
+ if (pmc)
+ __set_bit(pmc->idx, pmu->pmc_in_use);
}
int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
+ kvm_pmu_mark_pmc_in_use(vcpu, msr_info->index);
return kvm_x86_ops->pmu_ops->set_msr(vcpu, msr_info);
}
memset(pmu, 0, sizeof(*pmu));
kvm_x86_ops->pmu_ops->init(vcpu);
init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn);
+ pmu->event_count = 0;
+ pmu->need_cleanup = false;
kvm_pmu_refresh(vcpu);
}
+static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc)
+{
+ struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+
+ if (pmc_is_fixed(pmc))
+ return fixed_ctrl_field(pmu->fixed_ctr_ctrl,
+ pmc->idx - INTEL_PMC_IDX_FIXED) & 0x3;
+
+ return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE;
+}
+
+/* Release perf_events for vPMCs that have been unused for a full time slice. */
+void kvm_pmu_cleanup(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ struct kvm_pmc *pmc = NULL;
+ DECLARE_BITMAP(bitmask, X86_PMC_IDX_MAX);
+ int i;
+
+ pmu->need_cleanup = false;
+
+ bitmap_andnot(bitmask, pmu->all_valid_pmc_idx,
+ pmu->pmc_in_use, X86_PMC_IDX_MAX);
+
+ for_each_set_bit(i, bitmask, X86_PMC_IDX_MAX) {
+ pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, i);
+
+ if (pmc && pmc->perf_event && !pmc_speculative_in_use(pmc))
+ pmc_stop_counter(pmc);
+ }
+
+ bitmap_zero(pmu->pmc_in_use, X86_PMC_IDX_MAX);
+}
+
void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
{
kvm_pmu_reset(vcpu);
*filter = tmp;
mutex_lock(&kvm->lock);
- rcu_swap_protected(kvm->arch.pmu_event_filter, filter,
- mutex_is_locked(&kvm->lock));
+ filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter,
+ mutex_is_locked(&kvm->lock));
mutex_unlock(&kvm->lock);
synchronize_srcu_expedited(&kvm->srcu);
free_engines(rcu_access_pointer(ctx->engines));
mutex_destroy(&ctx->engines_mutex);
+ kfree(ctx->jump_whitelist);
+
if (ctx->timeline)
intel_timeline_put(ctx->timeline);
for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
+ ctx->jump_whitelist = NULL;
+ ctx->jump_whitelist_cmds = 0;
+
return ctx;
err_free:
i915_gem_context_set_user_engines(ctx);
else
i915_gem_context_clear_user_engines(ctx);
- rcu_swap_protected(ctx->engines, set.engines, 1);
+ set.engines = rcu_replace_pointer(ctx->engines, set.engines, 1);
mutex_unlock(&ctx->engines_mutex);
call_rcu(&set.engines->rcu, free_engines_rcu);
TICK_DEP_BIT_POSIX_TIMER = 0,
TICK_DEP_BIT_PERF_EVENTS = 1,
TICK_DEP_BIT_SCHED = 2,
- TICK_DEP_BIT_CLOCK_UNSTABLE = 3
+ TICK_DEP_BIT_CLOCK_UNSTABLE = 3,
+ TICK_DEP_BIT_RCU = 4
};
#define TICK_DEP_MASK_NONE 0
#define TICK_DEP_MASK_PERF_EVENTS (1 << TICK_DEP_BIT_PERF_EVENTS)
#define TICK_DEP_MASK_SCHED (1 << TICK_DEP_BIT_SCHED)
#define TICK_DEP_MASK_CLOCK_UNSTABLE (1 << TICK_DEP_BIT_CLOCK_UNSTABLE)
+ #define TICK_DEP_MASK_RCU (1 << TICK_DEP_BIT_RCU)
#ifdef CONFIG_NO_HZ_COMMON
extern bool tick_nohz_enabled;
static inline bool tick_nohz_full_enabled(void)
{
- if (!context_tracking_is_enabled())
+ if (!context_tracking_enabled())
return false;
return tick_nohz_full_running;
static inline bool tick_nohz_full_cpu(int cpu) { return false; }
static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { }
+ static inline void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { }
+ static inline void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { }
+
static inline void tick_dep_set(enum tick_dep_bits bit) { }
static inline void tick_dep_clear(enum tick_dep_bits bit) { }
static inline void tick_dep_set_cpu(int cpu, enum tick_dep_bits bit) { }
enum bpf_attach_type type,
struct bpf_prog_array *old_array)
{
- rcu_swap_protected(cgrp->bpf.effective[type], old_array,
- lockdep_is_held(&cgroup_mutex));
+ old_array = rcu_replace_pointer(cgrp->bpf.effective[type], old_array,
+ lockdep_is_held(&cgroup_mutex));
/* free prog array after grace period, since __cgroup_bpf_run_*()
* might be still walking the array
*/
return false;
switch (off) {
- case offsetof(struct bpf_sysctl, write):
+ case bpf_ctx_range(struct bpf_sysctl, write):
if (type != BPF_READ)
return false;
bpf_ctx_record_field_size(info, size_default);
return bpf_ctx_narrow_access_ok(off, size, size_default);
- case offsetof(struct bpf_sysctl, file_pos):
+ case bpf_ctx_range(struct bpf_sysctl, file_pos):
if (type == BPF_READ) {
bpf_ctx_record_field_size(info, size_default);
return bpf_ctx_narrow_access_ok(off, size, size_default);
#ifdef CONFIG_NO_HZ_FULL
cpumask_var_t tick_nohz_full_mask;
bool tick_nohz_full_running;
+ EXPORT_SYMBOL_GPL(tick_nohz_full_running);
static atomic_t tick_dep_mask;
static bool check_tick_dependency(atomic_t *dep)
return true;
}
+ if (val & TICK_DEP_MASK_RCU) {
+ trace_tick_stop(0, TICK_DEP_MASK_RCU);
+ return true;
+ }
+
return false;
}
preempt_enable();
}
}
+ EXPORT_SYMBOL_GPL(tick_nohz_dep_set_cpu);
void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
{
atomic_andnot(BIT(bit), &ts->tick_dep_mask);
}
+ EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu);
/*
* Set a per-task tick dependency. Posix CPU timers need this in order to elapse
*/
tick_nohz_dep_set_all(&tsk->tick_dep_mask, bit);
}
+ EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task);
void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit)
{
atomic_andnot(BIT(bit), &tsk->tick_dep_mask);
}
+ EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_task);
/*
* Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse
cpumask_copy(tick_nohz_full_mask, cpumask);
tick_nohz_full_running = true;
}
+ EXPORT_SYMBOL_GPL(tick_nohz_full_setup);
static int tick_nohz_cpu_down(unsigned int cpu)
{
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
unsigned long ticks;
- if (vtime_accounting_cpu_enabled())
+ if (vtime_accounting_enabled_this_cpu())
return;
/*
* We stopped the tick in idle. Update process times would miss the
struct list_head flusher_overflow; /* WQ: flush overflow list */
struct list_head maydays; /* MD: pwqs requesting rescue */
- struct worker *rescuer; /* I: rescue worker */
+ struct worker *rescuer; /* MD: rescue worker */
int nr_drainers; /* WQ: drain in progress */
int saved_max_active; /* WQ: saved pwq max_active */
static int worker_thread(void *__worker);
static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
+static void show_pwq(struct pool_workqueue *pwq);
#define CREATE_TRACE_POINTS
#include <trace/events/workqueue.h>
!lockdep_is_held(&wq_pool_mutex), \
"RCU or wq_pool_mutex should be held")
- #define assert_rcu_or_wq_mutex(wq) \
- RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \
- !lockdep_is_held(&wq->mutex), \
- "RCU or wq->mutex should be held")
-
#define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \
RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \
!lockdep_is_held(&wq->mutex) && \
*/
#define for_each_pwq(pwq, wq) \
list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node, \
- lockdep_is_held(&wq->mutex)) \
- if (({ assert_rcu_or_wq_mutex(wq); false; })) { } \
- else
+ lockdep_is_held(&(wq->mutex)))
#ifdef CONFIG_DEBUG_OBJECTS_WORK
*/
if (need_to_create_worker(pool)) {
spin_lock(&wq_mayday_lock);
- get_pwq(pwq);
- list_move_tail(&pwq->mayday_node, &wq->maydays);
+ /*
+ * Queue iff we aren't racing destruction
+ * and somebody else hasn't queued it already.
+ */
+ if (wq->rescuer && list_empty(&pwq->mayday_node)) {
+ get_pwq(pwq);
+ list_add_tail(&pwq->mayday_node, &wq->maydays);
+ }
spin_unlock(&wq_mayday_lock);
}
}
}
EXPORT_SYMBOL_GPL(alloc_workqueue);
+static bool pwq_busy(struct pool_workqueue *pwq)
+{
+ int i;
+
+ for (i = 0; i < WORK_NR_COLORS; i++)
+ if (pwq->nr_in_flight[i])
+ return true;
+
+ if ((pwq != pwq->wq->dfl_pwq) && (pwq->refcnt > 1))
+ return true;
+ if (pwq->nr_active || !list_empty(&pwq->delayed_works))
+ return true;
+
+ return false;
+}
+
/**
* destroy_workqueue - safely terminate a workqueue
* @wq: target workqueue
struct pool_workqueue *pwq;
int node;
+ /*
+ * Remove it from sysfs first so that sanity check failure doesn't
+ * lead to sysfs name conflicts.
+ */
+ workqueue_sysfs_unregister(wq);
+
/* drain it before proceeding with destruction */
drain_workqueue(wq);
- /* sanity checks */
- mutex_lock(&wq->mutex);
- for_each_pwq(pwq, wq) {
- int i;
+ /* kill rescuer, if sanity checks fail, leave it w/o rescuer */
+ if (wq->rescuer) {
+ struct worker *rescuer = wq->rescuer;
- for (i = 0; i < WORK_NR_COLORS; i++) {
- if (WARN_ON(pwq->nr_in_flight[i])) {
- mutex_unlock(&wq->mutex);
- show_workqueue_state();
- return;
- }
- }
+ /* this prevents new queueing */
+ spin_lock_irq(&wq_mayday_lock);
+ wq->rescuer = NULL;
+ spin_unlock_irq(&wq_mayday_lock);
- if (WARN_ON((pwq != wq->dfl_pwq) && (pwq->refcnt > 1)) ||
- WARN_ON(pwq->nr_active) ||
- WARN_ON(!list_empty(&pwq->delayed_works))) {
+ /* rescuer will empty maydays list before exiting */
+ kthread_stop(rescuer->task);
+ kfree(rescuer);
+ }
+
+ /*
+ * Sanity checks - grab all the locks so that we wait for all
+ * in-flight operations which may do put_pwq().
+ */
+ mutex_lock(&wq_pool_mutex);
+ mutex_lock(&wq->mutex);
+ for_each_pwq(pwq, wq) {
+ spin_lock_irq(&pwq->pool->lock);
+ if (WARN_ON(pwq_busy(pwq))) {
+ pr_warning("%s: %s has the following busy pwq\n",
+ __func__, wq->name);
+ show_pwq(pwq);
+ spin_unlock_irq(&pwq->pool->lock);
mutex_unlock(&wq->mutex);
+ mutex_unlock(&wq_pool_mutex);
show_workqueue_state();
return;
}
+ spin_unlock_irq(&pwq->pool->lock);
}
mutex_unlock(&wq->mutex);
+ mutex_unlock(&wq_pool_mutex);
/*
* wq list is used to freeze wq, remove from list after
list_del_rcu(&wq->list);
mutex_unlock(&wq_pool_mutex);
- workqueue_sysfs_unregister(wq);
-
- if (wq->rescuer)
- kthread_stop(wq->rescuer->task);
-
if (!(wq->flags & WQ_UNBOUND)) {
wq_unregister_lockdep(wq);
/*
pr_info(" pwq %d:", pool->id);
pr_cont_pool_info(pool);
- pr_cont(" active=%d/%d%s\n", pwq->nr_active, pwq->max_active,
+ pr_cont(" active=%d/%d refcnt=%d%s\n",
+ pwq->nr_active, pwq->max_active, pwq->refcnt,
!list_empty(&pwq->mayday_node) ? " MAYDAY" : "");
hash_for_each(pool->busy_hash, bkt, worker, hentry) {
pr_cont("%s %d%s:%ps", comma ? "," : "",
task_pid_nr(worker->task),
- worker == pwq->wq->rescuer ? "(RESCUER)" : "",
+ worker->rescue_wq ? "(RESCUER)" : "",
worker->current_func);
list_for_each_entry(work, &worker->scheduled, entry)
pr_cont_work(false, work);
#include "net-sysfs.h"
#define MAX_GRO_SKBS 8
+#define MAX_NEST_DEV 8
/* This should be increased if a protocol with a bigger head is added. */
#define GRO_MAX_HEAD (MAX_HEADER + 128)
#endif
}
+static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev,
+ const char *name)
+{
+ struct netdev_name_node *name_node;
+
+ name_node = kmalloc(sizeof(*name_node), GFP_KERNEL);
+ if (!name_node)
+ return NULL;
+ INIT_HLIST_NODE(&name_node->hlist);
+ name_node->dev = dev;
+ name_node->name = name;
+ return name_node;
+}
+
+static struct netdev_name_node *
+netdev_name_node_head_alloc(struct net_device *dev)
+{
+ struct netdev_name_node *name_node;
+
+ name_node = netdev_name_node_alloc(dev, dev->name);
+ if (!name_node)
+ return NULL;
+ INIT_LIST_HEAD(&name_node->list);
+ return name_node;
+}
+
+static void netdev_name_node_free(struct netdev_name_node *name_node)
+{
+ kfree(name_node);
+}
+
+static void netdev_name_node_add(struct net *net,
+ struct netdev_name_node *name_node)
+{
+ hlist_add_head_rcu(&name_node->hlist,
+ dev_name_hash(net, name_node->name));
+}
+
+static void netdev_name_node_del(struct netdev_name_node *name_node)
+{
+ hlist_del_rcu(&name_node->hlist);
+}
+
+static struct netdev_name_node *netdev_name_node_lookup(struct net *net,
+ const char *name)
+{
+ struct hlist_head *head = dev_name_hash(net, name);
+ struct netdev_name_node *name_node;
+
+ hlist_for_each_entry(name_node, head, hlist)
+ if (!strcmp(name_node->name, name))
+ return name_node;
+ return NULL;
+}
+
+static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net,
+ const char *name)
+{
+ struct hlist_head *head = dev_name_hash(net, name);
+ struct netdev_name_node *name_node;
+
+ hlist_for_each_entry_rcu(name_node, head, hlist)
+ if (!strcmp(name_node->name, name))
+ return name_node;
+ return NULL;
+}
+
+int netdev_name_node_alt_create(struct net_device *dev, const char *name)
+{
+ struct netdev_name_node *name_node;
+ struct net *net = dev_net(dev);
+
+ name_node = netdev_name_node_lookup(net, name);
+ if (name_node)
+ return -EEXIST;
+ name_node = netdev_name_node_alloc(dev, name);
+ if (!name_node)
+ return -ENOMEM;
+ netdev_name_node_add(net, name_node);
+ /* The node that holds dev->name acts as a head of per-device list. */
+ list_add_tail(&name_node->list, &dev->name_node->list);
+
+ return 0;
+}
+EXPORT_SYMBOL(netdev_name_node_alt_create);
+
+static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node)
+{
+ list_del(&name_node->list);
+ netdev_name_node_del(name_node);
+ kfree(name_node->name);
+ netdev_name_node_free(name_node);
+}
+
+int netdev_name_node_alt_destroy(struct net_device *dev, const char *name)
+{
+ struct netdev_name_node *name_node;
+ struct net *net = dev_net(dev);
+
+ name_node = netdev_name_node_lookup(net, name);
+ if (!name_node)
+ return -ENOENT;
+ __netdev_name_node_alt_destroy(name_node);
+
+ return 0;
+}
+EXPORT_SYMBOL(netdev_name_node_alt_destroy);
+
+static void netdev_name_node_alt_flush(struct net_device *dev)
+{
+ struct netdev_name_node *name_node, *tmp;
+
+ list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list)
+ __netdev_name_node_alt_destroy(name_node);
+}
+
/* Device list insertion */
static void list_netdevice(struct net_device *dev)
{
write_lock_bh(&dev_base_lock);
list_add_tail_rcu(&dev->dev_list, &net->dev_base_head);
- hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
+ netdev_name_node_add(net, dev->name_node);
hlist_add_head_rcu(&dev->index_hlist,
dev_index_hash(net, dev->ifindex));
write_unlock_bh(&dev_base_lock);
/* Unlink dev from the device chain */
write_lock_bh(&dev_base_lock);
list_del_rcu(&dev->dev_list);
- hlist_del_rcu(&dev->name_hlist);
+ netdev_name_node_del(dev->name_node);
hlist_del_rcu(&dev->index_hlist);
write_unlock_bh(&dev_base_lock);
DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
EXPORT_PER_CPU_SYMBOL(softnet_data);
-#ifdef CONFIG_LOCKDEP
-/*
- * register_netdevice() inits txq->_xmit_lock and sets lockdep class
- * according to dev->type
- */
-static const unsigned short netdev_lock_type[] = {
- ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25,
- ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET,
- ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM,
- ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP,
- ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD,
- ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25,
- ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP,
- ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD,
- ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI,
- ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE,
- ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,
- ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
- ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM,
- ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE,
- ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE};
-
-static const char *const netdev_lock_name[] = {
- "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
- "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",
- "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",
- "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP",
- "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD",
- "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25",
- "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP",
- "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD",
- "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI",
- "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",
- "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
- "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
- "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM",
- "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE",
- "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"};
-
-static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
-static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];
-
-static inline unsigned short netdev_lock_pos(unsigned short dev_type)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++)
- if (netdev_lock_type[i] == dev_type)
- return i;
- /* the last key is used by default */
- return ARRAY_SIZE(netdev_lock_type) - 1;
-}
-
-static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
- unsigned short dev_type)
-{
- int i;
-
- i = netdev_lock_pos(dev_type);
- lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i],
- netdev_lock_name[i]);
-}
-
-static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
-{
- int i;
-
- i = netdev_lock_pos(dev->type);
- lockdep_set_class_and_name(&dev->addr_list_lock,
- &netdev_addr_lock_key[i],
- netdev_lock_name[i]);
-}
-#else
-static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
- unsigned short dev_type)
-{
-}
-static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
-{
-}
-#endif
-
/*******************************************************************************
*
* Protocol management and registration routines
struct net_device *__dev_get_by_name(struct net *net, const char *name)
{
- struct net_device *dev;
- struct hlist_head *head = dev_name_hash(net, name);
-
- hlist_for_each_entry(dev, head, name_hlist)
- if (!strncmp(dev->name, name, IFNAMSIZ))
- return dev;
+ struct netdev_name_node *node_name;
- return NULL;
+ node_name = netdev_name_node_lookup(net, name);
+ return node_name ? node_name->dev : NULL;
}
EXPORT_SYMBOL(__dev_get_by_name);
struct net_device *dev_get_by_name_rcu(struct net *net, const char *name)
{
- struct net_device *dev;
- struct hlist_head *head = dev_name_hash(net, name);
+ struct netdev_name_node *node_name;
- hlist_for_each_entry_rcu(dev, head, name_hlist)
- if (!strncmp(dev->name, name, IFNAMSIZ))
- return dev;
-
- return NULL;
+ node_name = netdev_name_node_lookup_rcu(net, name);
+ return node_name ? node_name->dev : NULL;
}
EXPORT_SYMBOL(dev_get_by_name_rcu);
}
EXPORT_SYMBOL(dev_alloc_name);
-int dev_get_valid_name(struct net *net, struct net_device *dev,
- const char *name)
+static int dev_get_valid_name(struct net *net, struct net_device *dev,
+ const char *name)
{
BUG_ON(!net);
return 0;
}
-EXPORT_SYMBOL(dev_get_valid_name);
/**
* dev_change_name - change name of a device
netdev_adjacent_rename_links(dev, oldname);
write_lock_bh(&dev_base_lock);
- hlist_del_rcu(&dev->name_hlist);
+ netdev_name_node_del(dev->name_node);
write_unlock_bh(&dev_base_lock);
synchronize_rcu();
write_lock_bh(&dev_base_lock);
- hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
+ netdev_name_node_add(net, dev->name_node);
write_unlock_bh(&dev_base_lock);
ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev);
}
mutex_lock(&ifalias_mutex);
- rcu_swap_protected(dev->ifalias, new_alias,
- mutex_is_locked(&ifalias_mutex));
+ new_alias = rcu_replace_pointer(dev->ifalias, new_alias,
+ mutex_is_locked(&ifalias_mutex));
mutex_unlock(&ifalias_mutex);
if (new_alias)
return nb->notifier_call(nb, val, &info);
}
+static int call_netdevice_register_notifiers(struct notifier_block *nb,
+ struct net_device *dev)
+{
+ int err;
+
+ err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev);
+ err = notifier_to_errno(err);
+ if (err)
+ return err;
+
+ if (!(dev->flags & IFF_UP))
+ return 0;
+
+ call_netdevice_notifier(nb, NETDEV_UP, dev);
+ return 0;
+}
+
+static void call_netdevice_unregister_notifiers(struct notifier_block *nb,
+ struct net_device *dev)
+{
+ if (dev->flags & IFF_UP) {
+ call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
+ dev);
+ call_netdevice_notifier(nb, NETDEV_DOWN, dev);
+ }
+ call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
+}
+
+static int call_netdevice_register_net_notifiers(struct notifier_block *nb,
+ struct net *net)
+{
+ struct net_device *dev;
+ int err;
+
+ for_each_netdev(net, dev) {
+ err = call_netdevice_register_notifiers(nb, dev);
+ if (err)
+ goto rollback;
+ }
+ return 0;
+
+rollback:
+ for_each_netdev_continue_reverse(net, dev)
+ call_netdevice_unregister_notifiers(nb, dev);
+ return err;
+}
+
+static void call_netdevice_unregister_net_notifiers(struct notifier_block *nb,
+ struct net *net)
+{
+ struct net_device *dev;
+
+ for_each_netdev(net, dev)
+ call_netdevice_unregister_notifiers(nb, dev);
+}
+
static int dev_boot_phase = 1;
/**
int register_netdevice_notifier(struct notifier_block *nb)
{
- struct net_device *dev;
- struct net_device *last;
struct net *net;
int err;
if (dev_boot_phase)
goto unlock;
for_each_net(net) {
- for_each_netdev(net, dev) {
- err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev);
- err = notifier_to_errno(err);
- if (err)
- goto rollback;
-
- if (!(dev->flags & IFF_UP))
- continue;
-
- call_netdevice_notifier(nb, NETDEV_UP, dev);
- }
+ err = call_netdevice_register_net_notifiers(nb, net);
+ if (err)
+ goto rollback;
}
unlock:
return err;
rollback:
- last = dev;
- for_each_net(net) {
- for_each_netdev(net, dev) {
- if (dev == last)
- goto outroll;
-
- if (dev->flags & IFF_UP) {
- call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
- dev);
- call_netdevice_notifier(nb, NETDEV_DOWN, dev);
- }
- call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
- }
- }
+ for_each_net_continue_reverse(net)
+ call_netdevice_unregister_net_notifiers(nb, net);
-outroll:
raw_notifier_chain_unregister(&netdev_chain, nb);
goto unlock;
}
}
EXPORT_SYMBOL(unregister_netdevice_notifier);
+/**
+ * register_netdevice_notifier_net - register a per-netns network notifier block
+ * @net: network namespace
+ * @nb: notifier
+ *
+ * Register a notifier to be called when network device events occur.
+ * The notifier passed is linked into the kernel structures and must
+ * not be reused until it has been unregistered. A negative errno code
+ * is returned on a failure.
+ *
+ * When registered all registration and up events are replayed
+ * to the new notifier to allow device to have a race free
+ * view of the network device list.
+ */
+
+int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb)
+{
+ int err;
+
+ rtnl_lock();
+ err = raw_notifier_chain_register(&net->netdev_chain, nb);
+ if (err)
+ goto unlock;
+ if (dev_boot_phase)
+ goto unlock;
+
+ err = call_netdevice_register_net_notifiers(nb, net);
+ if (err)
+ goto chain_unregister;
+
+unlock:
+ rtnl_unlock();
+ return err;
+
+chain_unregister:
+ raw_notifier_chain_unregister(&netdev_chain, nb);
+ goto unlock;
+}
+EXPORT_SYMBOL(register_netdevice_notifier_net);
+
+/**
+ * unregister_netdevice_notifier_net - unregister a per-netns
+ * network notifier block
+ * @net: network namespace
+ * @nb: notifier
+ *
+ * Unregister a notifier previously registered by
+ * register_netdevice_notifier(). The notifier is unlinked into the
+ * kernel structures and may then be reused. A negative errno code
+ * is returned on a failure.
+ *
+ * After unregistering unregister and down device events are synthesized
+ * for all devices on the device list to the removed notifier to remove
+ * the need for special case cleanup code.
+ */
+
+int unregister_netdevice_notifier_net(struct net *net,
+ struct notifier_block *nb)
+{
+ int err;
+
+ rtnl_lock();
+ err = raw_notifier_chain_unregister(&net->netdev_chain, nb);
+ if (err)
+ goto unlock;
+
+ call_netdevice_unregister_net_notifiers(nb, net);
+
+unlock:
+ rtnl_unlock();
+ return err;
+}
+EXPORT_SYMBOL(unregister_netdevice_notifier_net);
+
/**
* call_netdevice_notifiers_info - call all network notifier blocks
* @val: value passed unmodified to notifier function
static int call_netdevice_notifiers_info(unsigned long val,
struct netdev_notifier_info *info)
{
+ struct net *net = dev_net(info->dev);
+ int ret;
+
ASSERT_RTNL();
+
+ /* Run per-netns notifier block chain first, then run the global one.
+ * Hopefully, one day, the global one is going to be removed after
+ * all notifier block registrators get converted to be per-netns.
+ */
+ ret = raw_notifier_call_chain(&net->netdev_chain, val, info);
+ if (ret & NOTIFY_STOP_MASK)
+ return ret;
return raw_notifier_call_chain(&netdev_chain, val, info);
}
void netif_schedule_queue(struct netdev_queue *txq)
{
rcu_read_lock();
- if (!(txq->state & QUEUE_STATE_ANY_XOFF)) {
+ if (!netif_xmit_stopped(txq)) {
struct Qdisc *q = rcu_dereference(txq->qdisc);
__netif_schedule(q);
offset += skb->csum_offset;
BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb));
- if (skb_cloned(skb) &&
- !skb_clone_writable(skb, offset + sizeof(__sum16))) {
- ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
- if (ret)
- goto out;
- }
+ ret = skb_ensure_writable(skb, offset + sizeof(__sum16));
+ if (ret)
+ goto out;
*(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0;
out_set_summed:
ret = -EINVAL;
goto out;
}
- if (skb_cloned(skb) &&
- !skb_clone_writable(skb, offset + sizeof(__le32))) {
- ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
- if (ret)
- goto out;
- }
+
+ ret = skb_ensure_writable(skb, offset + sizeof(__le32));
+ if (ret)
+ goto out;
+
crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start,
skb->len - start, ~(__u32)0,
crc32c_csum_stub));
qdisc_calculate_pkt_len(skb, q);
if (q->flags & TCQ_F_NOLOCK) {
- if ((q->flags & TCQ_F_CAN_BYPASS) && q->empty &&
+ if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) &&
qdisc_run_begin(q)) {
if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
&q->state))) {
diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb);
if (skb_vlan_tag_present(p))
- diffs |= p->vlan_tci ^ skb->vlan_tci;
+ diffs |= skb_vlan_tag_get(p) ^ skb_vlan_tag_get(skb);
diffs |= skb_metadata_dst_cmp(p, skb);
diffs |= skb_metadata_differs(p, skb);
if (maclen == ETH_HLEN)
NAPI_GRO_CB(skb)->frag0 = NULL;
NAPI_GRO_CB(skb)->frag0_len = 0;
- if (skb_mac_header(skb) == skb_tail_pointer(skb) &&
- pinfo->nr_frags &&
+ if (!skb_headlen(skb) && pinfo->nr_frags &&
!PageHighMem(skb_frag_page(frag0))) {
NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int,
}
EXPORT_SYMBOL(gro_find_complete_by_type);
+/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
+static void gro_normal_list(struct napi_struct *napi)
+{
+ if (!napi->rx_count)
+ return;
+ netif_receive_skb_list_internal(&napi->rx_list);
+ INIT_LIST_HEAD(&napi->rx_list);
+ napi->rx_count = 0;
+}
+
+/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
+ * pass the whole batch up to the stack.
+ */
+static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb)
+{
+ list_add_tail(&skb->list, &napi->rx_list);
+ if (++napi->rx_count >= gro_normal_batch)
+ gro_normal_list(napi);
+}
+
static void napi_skb_free_stolen_head(struct sk_buff *skb)
{
skb_dst_drop(skb);
kmem_cache_free(skbuff_head_cache, skb);
}
-static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
+static gro_result_t napi_skb_finish(struct napi_struct *napi,
+ struct sk_buff *skb,
+ gro_result_t ret)
{
switch (ret) {
case GRO_NORMAL:
- if (netif_receive_skb_internal(skb))
- ret = GRO_DROP;
+ gro_normal_one(napi, skb);
break;
case GRO_DROP:
skb_gro_reset_offset(skb);
- ret = napi_skb_finish(dev_gro_receive(napi, skb), skb);
+ ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb));
trace_napi_gro_receive_exit(ret);
return ret;
}
EXPORT_SYMBOL(napi_get_frags);
-/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
-static void gro_normal_list(struct napi_struct *napi)
-{
- if (!napi->rx_count)
- return;
- netif_receive_skb_list_internal(&napi->rx_list);
- INIT_LIST_HEAD(&napi->rx_list);
- napi->rx_count = 0;
-}
-
-/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
- * pass the whole batch up to the stack.
- */
-static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb)
-{
- list_add_tail(&skb->list, &napi->rx_list);
- if (++napi->rx_count >= gro_normal_batch)
- gro_normal_list(napi);
-}
-
static gro_result_t napi_frags_finish(struct napi_struct *napi,
struct sk_buff *skb,
gro_result_t ret)
/* upper master flag, there can only be one master device per list */
bool master;
+ /* lookup ignore flag */
+ bool ignore;
+
/* counter for the number of times this device was added to us */
u16 ref_nr;
return NULL;
}
-static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data)
+static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data)
{
struct net_device *dev = data;
{
ASSERT_RTNL();
- return netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev,
+ return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
upper_dev);
}
EXPORT_SYMBOL(netdev_has_upper_dev);
bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
struct net_device *upper_dev)
{
- return !!netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev,
+ return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
upper_dev);
}
EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu);
}
EXPORT_SYMBOL(netdev_master_upper_dev_get);
+static struct net_device *__netdev_master_upper_dev_get(struct net_device *dev)
+{
+ struct netdev_adjacent *upper;
+
+ ASSERT_RTNL();
+
+ if (list_empty(&dev->adj_list.upper))
+ return NULL;
+
+ upper = list_first_entry(&dev->adj_list.upper,
+ struct netdev_adjacent, list);
+ if (likely(upper->master) && !upper->ignore)
+ return upper->dev;
+ return NULL;
+}
+
/**
* netdev_has_any_lower_dev - Check if device is linked to some device
* @dev: device
}
EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
+static struct net_device *__netdev_next_upper_dev(struct net_device *dev,
+ struct list_head **iter,
+ bool *ignore)
+{
+ struct netdev_adjacent *upper;
+
+ upper = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+ if (&upper->list == &dev->adj_list.upper)
+ return NULL;
+
+ *iter = &upper->list;
+ *ignore = upper->ignore;
+
+ return upper->dev;
+}
+
static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
struct list_head **iter)
{
return upper->dev;
}
+static int __netdev_walk_all_upper_dev(struct net_device *dev,
+ int (*fn)(struct net_device *dev,
+ void *data),
+ void *data)
+{
+ struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int ret, cur = 0;
+ bool ignore;
+
+ now = dev;
+ iter = &dev->adj_list.upper;
+
+ while (1) {
+ if (now != dev) {
+ ret = fn(now, data);
+ if (ret)
+ return ret;
+ }
+
+ next = NULL;
+ while (1) {
+ udev = __netdev_next_upper_dev(now, &iter, &ignore);
+ if (!udev)
+ break;
+ if (ignore)
+ continue;
+
+ next = udev;
+ niter = &udev->adj_list.upper;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return 0;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
+ }
+
+ return 0;
+}
+
int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *dev,
void *data),
void *data)
{
- struct net_device *udev;
- struct list_head *iter;
- int ret;
+ struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int ret, cur = 0;
- for (iter = &dev->adj_list.upper,
- udev = netdev_next_upper_dev_rcu(dev, &iter);
- udev;
- udev = netdev_next_upper_dev_rcu(dev, &iter)) {
- /* first is the upper device itself */
- ret = fn(udev, data);
- if (ret)
- return ret;
+ now = dev;
+ iter = &dev->adj_list.upper;
- /* then look at all of its upper devices */
- ret = netdev_walk_all_upper_dev_rcu(udev, fn, data);
- if (ret)
- return ret;
+ while (1) {
+ if (now != dev) {
+ ret = fn(now, data);
+ if (ret)
+ return ret;
+ }
+
+ next = NULL;
+ while (1) {
+ udev = netdev_next_upper_dev_rcu(now, &iter);
+ if (!udev)
+ break;
+
+ next = udev;
+ niter = &udev->adj_list.upper;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return 0;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
}
return 0;
}
EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu);
+static bool __netdev_has_upper_dev(struct net_device *dev,
+ struct net_device *upper_dev)
+{
+ ASSERT_RTNL();
+
+ return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev,
+ upper_dev);
+}
+
/**
* netdev_lower_get_next_private - Get the next ->private from the
* lower neighbour list
return lower->dev;
}
+static struct net_device *__netdev_next_lower_dev(struct net_device *dev,
+ struct list_head **iter,
+ bool *ignore)
+{
+ struct netdev_adjacent *lower;
+
+ lower = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+ if (&lower->list == &dev->adj_list.lower)
+ return NULL;
+
+ *iter = &lower->list;
+ *ignore = lower->ignore;
+
+ return lower->dev;
+}
+
int netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *dev,
void *data),
void *data)
{
- struct net_device *ldev;
- struct list_head *iter;
- int ret;
+ struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int ret, cur = 0;
- for (iter = &dev->adj_list.lower,
- ldev = netdev_next_lower_dev(dev, &iter);
- ldev;
- ldev = netdev_next_lower_dev(dev, &iter)) {
- /* first is the lower device itself */
- ret = fn(ldev, data);
- if (ret)
- return ret;
+ now = dev;
+ iter = &dev->adj_list.lower;
- /* then look at all of its lower devices */
- ret = netdev_walk_all_lower_dev(ldev, fn, data);
- if (ret)
- return ret;
+ while (1) {
+ if (now != dev) {
+ ret = fn(now, data);
+ if (ret)
+ return ret;
+ }
+
+ next = NULL;
+ while (1) {
+ ldev = netdev_next_lower_dev(now, &iter);
+ if (!ldev)
+ break;
+
+ next = ldev;
+ niter = &ldev->adj_list.lower;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return 0;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
}
return 0;
}
EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev);
+static int __netdev_walk_all_lower_dev(struct net_device *dev,
+ int (*fn)(struct net_device *dev,
+ void *data),
+ void *data)
+{
+ struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int ret, cur = 0;
+ bool ignore;
+
+ now = dev;
+ iter = &dev->adj_list.lower;
+
+ while (1) {
+ if (now != dev) {
+ ret = fn(now, data);
+ if (ret)
+ return ret;
+ }
+
+ next = NULL;
+ while (1) {
+ ldev = __netdev_next_lower_dev(now, &iter, &ignore);
+ if (!ldev)
+ break;
+ if (ignore)
+ continue;
+
+ next = ldev;
+ niter = &ldev->adj_list.lower;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return 0;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
+ }
+
+ return 0;
+}
+
static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
struct list_head **iter)
{
return lower->dev;
}
-int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
- int (*fn)(struct net_device *dev,
- void *data),
- void *data)
+static u8 __netdev_upper_depth(struct net_device *dev)
+{
+ struct net_device *udev;
+ struct list_head *iter;
+ u8 max_depth = 0;
+ bool ignore;
+
+ for (iter = &dev->adj_list.upper,
+ udev = __netdev_next_upper_dev(dev, &iter, &ignore);
+ udev;
+ udev = __netdev_next_upper_dev(dev, &iter, &ignore)) {
+ if (ignore)
+ continue;
+ if (max_depth < udev->upper_level)
+ max_depth = udev->upper_level;
+ }
+
+ return max_depth;
+}
+
+static u8 __netdev_lower_depth(struct net_device *dev)
{
struct net_device *ldev;
struct list_head *iter;
- int ret;
+ u8 max_depth = 0;
+ bool ignore;
for (iter = &dev->adj_list.lower,
- ldev = netdev_next_lower_dev_rcu(dev, &iter);
+ ldev = __netdev_next_lower_dev(dev, &iter, &ignore);
ldev;
- ldev = netdev_next_lower_dev_rcu(dev, &iter)) {
- /* first is the lower device itself */
- ret = fn(ldev, data);
- if (ret)
- return ret;
+ ldev = __netdev_next_lower_dev(dev, &iter, &ignore)) {
+ if (ignore)
+ continue;
+ if (max_depth < ldev->lower_level)
+ max_depth = ldev->lower_level;
+ }
- /* then look at all of its lower devices */
- ret = netdev_walk_all_lower_dev_rcu(ldev, fn, data);
- if (ret)
- return ret;
+ return max_depth;
+}
+
+static int __netdev_update_upper_level(struct net_device *dev, void *data)
+{
+ dev->upper_level = __netdev_upper_depth(dev) + 1;
+ return 0;
+}
+
+static int __netdev_update_lower_level(struct net_device *dev, void *data)
+{
+ dev->lower_level = __netdev_lower_depth(dev) + 1;
+ return 0;
+}
+
+int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
+ int (*fn)(struct net_device *dev,
+ void *data),
+ void *data)
+{
+ struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+ struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+ int ret, cur = 0;
+
+ now = dev;
+ iter = &dev->adj_list.lower;
+
+ while (1) {
+ if (now != dev) {
+ ret = fn(now, data);
+ if (ret)
+ return ret;
+ }
+
+ next = NULL;
+ while (1) {
+ ldev = netdev_next_lower_dev_rcu(now, &iter);
+ if (!ldev)
+ break;
+
+ next = ldev;
+ niter = &ldev->adj_list.lower;
+ dev_stack[cur] = now;
+ iter_stack[cur++] = iter;
+ break;
+ }
+
+ if (!next) {
+ if (!cur)
+ return 0;
+ next = dev_stack[--cur];
+ niter = iter_stack[cur];
+ }
+
+ now = next;
+ iter = niter;
}
return 0;
adj->master = master;
adj->ref_nr = 1;
adj->private = private;
+ adj->ignore = false;
dev_hold(adj_dev);
pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n",
return -EBUSY;
/* To prevent loops, check if dev is not upper device to upper_dev. */
- if (netdev_has_upper_dev(upper_dev, dev))
+ if (__netdev_has_upper_dev(upper_dev, dev))
return -EBUSY;
+ if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV)
+ return -EMLINK;
+
if (!master) {
- if (netdev_has_upper_dev(dev, upper_dev))
+ if (__netdev_has_upper_dev(dev, upper_dev))
return -EEXIST;
} else {
- master_dev = netdev_master_upper_dev_get(dev);
+ master_dev = __netdev_master_upper_dev_get(dev);
if (master_dev)
return master_dev == upper_dev ? -EEXIST : -EBUSY;
}
if (ret)
goto rollback;
+ __netdev_update_upper_level(dev, NULL);
+ __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
+
+ __netdev_update_lower_level(upper_dev, NULL);
+ __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
+ NULL);
+
return 0;
rollback:
call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
&changeupper_info.info);
+
+ __netdev_update_upper_level(dev, NULL);
+ __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
+
+ __netdev_update_lower_level(upper_dev, NULL);
+ __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
+ NULL);
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
+static void __netdev_adjacent_dev_set(struct net_device *upper_dev,
+ struct net_device *lower_dev,
+ bool val)
+{
+ struct netdev_adjacent *adj;
+
+ adj = __netdev_find_adj(lower_dev, &upper_dev->adj_list.lower);
+ if (adj)
+ adj->ignore = val;
+
+ adj = __netdev_find_adj(upper_dev, &lower_dev->adj_list.upper);
+ if (adj)
+ adj->ignore = val;
+}
+
+static void netdev_adjacent_dev_disable(struct net_device *upper_dev,
+ struct net_device *lower_dev)
+{
+ __netdev_adjacent_dev_set(upper_dev, lower_dev, true);
+}
+
+static void netdev_adjacent_dev_enable(struct net_device *upper_dev,
+ struct net_device *lower_dev)
+{
+ __netdev_adjacent_dev_set(upper_dev, lower_dev, false);
+}
+
+int netdev_adjacent_change_prepare(struct net_device *old_dev,
+ struct net_device *new_dev,
+ struct net_device *dev,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ if (!new_dev)
+ return 0;
+
+ if (old_dev && new_dev != old_dev)
+ netdev_adjacent_dev_disable(dev, old_dev);
+
+ err = netdev_upper_dev_link(new_dev, dev, extack);
+ if (err) {
+ if (old_dev && new_dev != old_dev)
+ netdev_adjacent_dev_enable(dev, old_dev);
+ return err;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(netdev_adjacent_change_prepare);
+
+void netdev_adjacent_change_commit(struct net_device *old_dev,
+ struct net_device *new_dev,
+ struct net_device *dev)
+{
+ if (!new_dev || !old_dev)
+ return;
+
+ if (new_dev == old_dev)
+ return;
+
+ netdev_adjacent_dev_enable(dev, old_dev);
+ netdev_upper_dev_unlink(old_dev, dev);
+}
+EXPORT_SYMBOL(netdev_adjacent_change_commit);
+
+void netdev_adjacent_change_abort(struct net_device *old_dev,
+ struct net_device *new_dev,
+ struct net_device *dev)
+{
+ if (!new_dev)
+ return;
+
+ if (old_dev && new_dev != old_dev)
+ netdev_adjacent_dev_enable(dev, old_dev);
+
+ netdev_upper_dev_unlink(new_dev, dev);
+}
+EXPORT_SYMBOL(netdev_adjacent_change_abort);
+
/**
* netdev_bonding_info_change - Dispatch event about slave change
* @dev: device
EXPORT_SYMBOL(netdev_lower_dev_get_private);
-int dev_get_nest_level(struct net_device *dev)
-{
- struct net_device *lower = NULL;
- struct list_head *iter;
- int max_nest = -1;
- int nest;
-
- ASSERT_RTNL();
-
- netdev_for_each_lower_dev(dev, lower, iter) {
- nest = dev_get_nest_level(lower);
- if (max_nest < nest)
- max_nest = nest;
- }
-
- return max_nest + 1;
-}
-EXPORT_SYMBOL(dev_get_nest_level);
-
/**
* netdev_lower_change - Dispatch event about lower device state change
* @lower_dev: device
return -EINVAL;
}
- if (prog->aux->id == prog_id) {
+ /* prog->aux->id may be 0 for orphaned device-bound progs */
+ if (prog->aux->id && prog->aux->id == prog_id) {
bpf_prog_put(prog);
return 0;
}
dev_uc_flush(dev);
dev_mc_flush(dev);
+ netdev_name_node_alt_flush(dev);
+ netdev_name_node_free(dev->name_node);
+
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
{
/* Initialize queue lock */
spin_lock_init(&queue->_xmit_lock);
- netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type);
+ lockdep_set_class(&queue->_xmit_lock, &dev->qdisc_xmit_lock_key);
queue->xmit_lock_owner = -1;
netdev_queue_numa_node_write(queue, NUMA_NO_NODE);
queue->dev = dev;
}
EXPORT_SYMBOL(netif_tx_stop_all_queues);
+static void netdev_register_lockdep_key(struct net_device *dev)
+{
+ lockdep_register_key(&dev->qdisc_tx_busylock_key);
+ lockdep_register_key(&dev->qdisc_running_key);
+ lockdep_register_key(&dev->qdisc_xmit_lock_key);
+ lockdep_register_key(&dev->addr_list_lock_key);
+}
+
+static void netdev_unregister_lockdep_key(struct net_device *dev)
+{
+ lockdep_unregister_key(&dev->qdisc_tx_busylock_key);
+ lockdep_unregister_key(&dev->qdisc_running_key);
+ lockdep_unregister_key(&dev->qdisc_xmit_lock_key);
+ lockdep_unregister_key(&dev->addr_list_lock_key);
+}
+
+void netdev_update_lockdep_key(struct net_device *dev)
+{
+ struct netdev_queue *queue;
+ int i;
+
+ lockdep_unregister_key(&dev->qdisc_xmit_lock_key);
+ lockdep_unregister_key(&dev->addr_list_lock_key);
+
+ lockdep_register_key(&dev->qdisc_xmit_lock_key);
+ lockdep_register_key(&dev->addr_list_lock_key);
+
+ lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key);
+ for (i = 0; i < dev->num_tx_queues; i++) {
+ queue = netdev_get_tx_queue(dev, i);
+
+ lockdep_set_class(&queue->_xmit_lock,
+ &dev->qdisc_xmit_lock_key);
+ }
+}
+EXPORT_SYMBOL(netdev_update_lockdep_key);
+
/**
* register_netdevice - register a network device
* @dev: device to register
BUG_ON(!net);
spin_lock_init(&dev->addr_list_lock);
- netdev_set_addr_lockdep_class(dev);
+ lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key);
ret = dev_get_valid_name(net, dev, dev->name);
if (ret < 0)
goto out;
+ ret = -ENOMEM;
+ dev->name_node = netdev_name_node_head_alloc(dev);
+ if (!dev->name_node)
+ goto out;
+
/* Init, if this function is available */
if (dev->netdev_ops->ndo_init) {
ret = dev->netdev_ops->ndo_init(dev);
return ret;
err_uninit:
+ if (dev->name_node)
+ netdev_name_node_free(dev->name_node);
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
if (dev->priv_destructor)
dev_net_set(dev, &init_net);
+ netdev_register_lockdep_key(dev);
+
dev->gso_max_size = GSO_MAX_SIZE;
dev->gso_max_segs = GSO_MAX_SEGS;
+ dev->upper_level = 1;
+ dev->lower_level = 1;
INIT_LIST_HEAD(&dev->napi_list);
INIT_LIST_HEAD(&dev->unreg_list);
free_percpu(dev->pcpu_refcnt);
dev->pcpu_refcnt = NULL;
+ netdev_unregister_lockdep_key(dev);
+
/* Compatibility with error handling in drivers */
if (dev->reg_state == NETREG_UNINITIALIZED) {
netdev_freemem(dev);
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
rcu_barrier();
- new_nsid = peernet2id_alloc(dev_net(dev), net);
+ new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL);
/* If there is an ifindex conflict assign a new one */
if (__dev_get_by_index(net, dev->ifindex))
new_ifindex = dev_new_index(net);
if (net->dev_index_head == NULL)
goto err_idx;
+ RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain);
+
return 0;
err_idx:
}
}
+static int nft_netdev_register_hooks(struct net *net,
+ struct list_head *hook_list)
+{
+ struct nft_hook *hook;
+ int err, j;
+
+ j = 0;
+ list_for_each_entry(hook, hook_list, list) {
+ err = nf_register_net_hook(net, &hook->ops);
+ if (err < 0)
+ goto err_register;
+
+ j++;
+ }
+ return 0;
+
+err_register:
+ list_for_each_entry(hook, hook_list, list) {
+ if (j-- <= 0)
+ break;
+
+ nf_unregister_net_hook(net, &hook->ops);
+ }
+ return err;
+}
+
+static void nft_netdev_unregister_hooks(struct net *net,
+ struct list_head *hook_list)
+{
+ struct nft_hook *hook;
+
+ list_for_each_entry(hook, hook_list, list)
+ nf_unregister_net_hook(net, &hook->ops);
+}
+
+static int nft_register_basechain_hooks(struct net *net, int family,
+ struct nft_base_chain *basechain)
+{
+ if (family == NFPROTO_NETDEV)
+ return nft_netdev_register_hooks(net, &basechain->hook_list);
+
+ return nf_register_net_hook(net, &basechain->ops);
+}
+
+static void nft_unregister_basechain_hooks(struct net *net, int family,
+ struct nft_base_chain *basechain)
+{
+ if (family == NFPROTO_NETDEV)
+ nft_netdev_unregister_hooks(net, &basechain->hook_list);
+ else
+ nf_unregister_net_hook(net, &basechain->ops);
+}
+
static int nf_tables_register_hook(struct net *net,
const struct nft_table *table,
struct nft_chain *chain)
{
- const struct nft_base_chain *basechain;
+ struct nft_base_chain *basechain;
const struct nf_hook_ops *ops;
if (table->flags & NFT_TABLE_F_DORMANT ||
if (basechain->type->ops_register)
return basechain->type->ops_register(net, ops);
- return nf_register_net_hook(net, ops);
+ return nft_register_basechain_hooks(net, table->family, basechain);
}
static void nf_tables_unregister_hook(struct net *net,
const struct nft_table *table,
struct nft_chain *chain)
{
- const struct nft_base_chain *basechain;
+ struct nft_base_chain *basechain;
const struct nf_hook_ops *ops;
if (table->flags & NFT_TABLE_F_DORMANT ||
if (basechain->type->ops_unregister)
return basechain->type->ops_unregister(net, ops);
- nf_unregister_net_hook(net, ops);
+ nft_unregister_basechain_hooks(net, table->family, basechain);
}
static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type)
static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule)
{
+ struct nft_flow_rule *flow;
struct nft_trans *trans;
int err;
if (trans == NULL)
return -ENOMEM;
+ if (ctx->chain->flags & NFT_CHAIN_HW_OFFLOAD) {
+ flow = nft_flow_rule_create(ctx->net, rule);
+ if (IS_ERR(flow)) {
+ nft_trans_destroy(trans);
+ return PTR_ERR(flow);
+ }
+
+ nft_trans_flow_rule(trans) = flow;
+ }
+
err = nf_tables_delrule_deactivate(ctx, rule);
if (err < 0) {
nft_trans_destroy(trans);
if (cnt && i++ == cnt)
break;
- nf_unregister_net_hook(net, &nft_base_chain(chain)->ops);
+ nft_unregister_basechain_hooks(net, table->family,
+ nft_base_chain(chain));
}
}
if (!nft_is_base_chain(chain))
continue;
- err = nf_register_net_hook(net, &nft_base_chain(chain)->ops);
+ err = nft_register_basechain_hooks(net, table->family,
+ nft_base_chain(chain));
if (err < 0)
- goto err;
+ goto err_register_hooks;
i++;
}
return 0;
-err:
+
+err_register_hooks:
if (i)
nft_table_disable(net, table, i);
return err;
return -ENOSPC;
}
+static int nft_dump_basechain_hook(struct sk_buff *skb, int family,
+ const struct nft_base_chain *basechain)
+{
+ const struct nf_hook_ops *ops = &basechain->ops;
+ struct nft_hook *hook, *first = NULL;
+ struct nlattr *nest, *nest_devs;
+ int n = 0;
+
+ nest = nla_nest_start_noflag(skb, NFTA_CHAIN_HOOK);
+ if (nest == NULL)
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_HOOK_HOOKNUM, htonl(ops->hooknum)))
+ goto nla_put_failure;
+ if (nla_put_be32(skb, NFTA_HOOK_PRIORITY, htonl(ops->priority)))
+ goto nla_put_failure;
+
+ if (family == NFPROTO_NETDEV) {
+ nest_devs = nla_nest_start_noflag(skb, NFTA_HOOK_DEVS);
+ list_for_each_entry(hook, &basechain->hook_list, list) {
+ if (!first)
+ first = hook;
+
+ if (nla_put_string(skb, NFTA_DEVICE_NAME,
+ hook->ops.dev->name))
+ goto nla_put_failure;
+ n++;
+ }
+ nla_nest_end(skb, nest_devs);
+
+ if (n == 1 &&
+ nla_put_string(skb, NFTA_HOOK_DEV, first->ops.dev->name))
+ goto nla_put_failure;
+ }
+ nla_nest_end(skb, nest);
+
+ return 0;
+nla_put_failure:
+ return -1;
+}
+
static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
u32 portid, u32 seq, int event, u32 flags,
int family, const struct nft_table *table,
if (nft_is_base_chain(chain)) {
const struct nft_base_chain *basechain = nft_base_chain(chain);
- const struct nf_hook_ops *ops = &basechain->ops;
struct nft_stats __percpu *stats;
- struct nlattr *nest;
- nest = nla_nest_start_noflag(skb, NFTA_CHAIN_HOOK);
- if (nest == NULL)
- goto nla_put_failure;
- if (nla_put_be32(skb, NFTA_HOOK_HOOKNUM, htonl(ops->hooknum)))
- goto nla_put_failure;
- if (nla_put_be32(skb, NFTA_HOOK_PRIORITY, htonl(ops->priority)))
- goto nla_put_failure;
- if (basechain->dev_name[0] &&
- nla_put_string(skb, NFTA_HOOK_DEV, basechain->dev_name))
+ if (nft_dump_basechain_hook(skb, family, basechain))
goto nla_put_failure;
- nla_nest_end(skb, nest);
if (nla_put_be32(skb, NFTA_CHAIN_POLICY,
htonl(basechain->policy)))
if (!nft_trans_chain_stats(trans))
return;
- rcu_swap_protected(chain->stats, nft_trans_chain_stats(trans),
- lockdep_commit_lock_is_held(trans->ctx.net));
+ nft_trans_chain_stats(trans) =
+ rcu_replace_pointer(chain->stats, nft_trans_chain_stats(trans),
+ lockdep_commit_lock_is_held(trans->ctx.net));
if (!nft_trans_chain_stats(trans))
static_branch_inc(&nft_counters_enabled);
static void nf_tables_chain_destroy(struct nft_ctx *ctx)
{
struct nft_chain *chain = ctx->chain;
+ struct nft_hook *hook, *next;
if (WARN_ON(chain->use > 0))
return;
if (nft_is_base_chain(chain)) {
struct nft_base_chain *basechain = nft_base_chain(chain);
+ if (ctx->family == NFPROTO_NETDEV) {
+ list_for_each_entry_safe(hook, next,
+ &basechain->hook_list, list) {
+ list_del_rcu(&hook->list);
+ kfree_rcu(hook, rcu);
+ }
+ }
module_put(basechain->type->owner);
if (rcu_access_pointer(basechain->stats)) {
static_branch_dec(&nft_counters_enabled);
}
}
+static struct nft_hook *nft_netdev_hook_alloc(struct net *net,
+ const struct nlattr *attr)
+{
+ struct net_device *dev;
+ char ifname[IFNAMSIZ];
+ struct nft_hook *hook;
+ int err;
+
+ hook = kmalloc(sizeof(struct nft_hook), GFP_KERNEL);
+ if (!hook) {
+ err = -ENOMEM;
+ goto err_hook_alloc;
+ }
+
+ nla_strlcpy(ifname, attr, IFNAMSIZ);
+ dev = __dev_get_by_name(net, ifname);
+ if (!dev) {
+ err = -ENOENT;
+ goto err_hook_dev;
+ }
+ hook->ops.dev = dev;
+
+ return hook;
+
+err_hook_dev:
+ kfree(hook);
+err_hook_alloc:
+ return ERR_PTR(err);
+}
+
+static bool nft_hook_list_find(struct list_head *hook_list,
+ const struct nft_hook *this)
+{
+ struct nft_hook *hook;
+
+ list_for_each_entry(hook, hook_list, list) {
+ if (this->ops.dev == hook->ops.dev)
+ return true;
+ }
+
+ return false;
+}
+
+static int nf_tables_parse_netdev_hooks(struct net *net,
+ const struct nlattr *attr,
+ struct list_head *hook_list)
+{
+ struct nft_hook *hook, *next;
+ const struct nlattr *tmp;
+ int rem, n = 0, err;
+
+ nla_for_each_nested(tmp, attr, rem) {
+ if (nla_type(tmp) != NFTA_DEVICE_NAME) {
+ err = -EINVAL;
+ goto err_hook;
+ }
+
+ hook = nft_netdev_hook_alloc(net, tmp);
+ if (IS_ERR(hook)) {
+ err = PTR_ERR(hook);
+ goto err_hook;
+ }
+ if (nft_hook_list_find(hook_list, hook)) {
+ err = -EEXIST;
+ goto err_hook;
+ }
+ list_add_tail(&hook->list, hook_list);
+ n++;
+
+ if (n == NFT_NETDEVICE_MAX) {
+ err = -EFBIG;
+ goto err_hook;
+ }
+ }
+ if (!n)
+ return -EINVAL;
+
+ return 0;
+
+err_hook:
+ list_for_each_entry_safe(hook, next, hook_list, list) {
+ list_del(&hook->list);
+ kfree(hook);
+ }
+ return err;
+}
+
struct nft_chain_hook {
u32 num;
s32 priority;
const struct nft_chain_type *type;
- struct net_device *dev;
+ struct list_head list;
};
+static int nft_chain_parse_netdev(struct net *net,
+ struct nlattr *tb[],
+ struct list_head *hook_list)
+{
+ struct nft_hook *hook;
+ int err;
+
+ if (tb[NFTA_HOOK_DEV]) {
+ hook = nft_netdev_hook_alloc(net, tb[NFTA_HOOK_DEV]);
+ if (IS_ERR(hook))
+ return PTR_ERR(hook);
+
+ list_add_tail(&hook->list, hook_list);
+ } else if (tb[NFTA_HOOK_DEVS]) {
+ err = nf_tables_parse_netdev_hooks(net, tb[NFTA_HOOK_DEVS],
+ hook_list);
+ if (err < 0)
+ return err;
+ } else {
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int nft_chain_parse_hook(struct net *net,
const struct nlattr * const nla[],
struct nft_chain_hook *hook, u8 family,
{
struct nlattr *ha[NFTA_HOOK_MAX + 1];
const struct nft_chain_type *type;
- struct net_device *dev;
int err;
lockdep_assert_held(&net->nft.commit_mutex);
hook->type = type;
- hook->dev = NULL;
+ INIT_LIST_HEAD(&hook->list);
if (family == NFPROTO_NETDEV) {
- char ifname[IFNAMSIZ];
-
- if (!ha[NFTA_HOOK_DEV]) {
- module_put(type->owner);
- return -EOPNOTSUPP;
- }
-
- nla_strlcpy(ifname, ha[NFTA_HOOK_DEV], IFNAMSIZ);
- dev = __dev_get_by_name(net, ifname);
- if (!dev) {
+ err = nft_chain_parse_netdev(net, ha, &hook->list);
+ if (err < 0) {
module_put(type->owner);
- return -ENOENT;
+ return err;
}
- hook->dev = dev;
- } else if (ha[NFTA_HOOK_DEV]) {
+ } else if (ha[NFTA_HOOK_DEV] || ha[NFTA_HOOK_DEVS]) {
module_put(type->owner);
return -EOPNOTSUPP;
}
static void nft_chain_release_hook(struct nft_chain_hook *hook)
{
+ struct nft_hook *h, *next;
+
+ list_for_each_entry_safe(h, next, &hook->list, list) {
+ list_del(&h->list);
+ kfree(h);
+ }
module_put(hook->type->owner);
}
return kvmalloc(alloc, GFP_KERNEL);
}
+static void nft_basechain_hook_init(struct nf_hook_ops *ops, u8 family,
+ const struct nft_chain_hook *hook,
+ struct nft_chain *chain)
+{
+ ops->pf = family;
+ ops->hooknum = hook->num;
+ ops->priority = hook->priority;
+ ops->priv = chain;
+ ops->hook = hook->type->hooks[ops->hooknum];
+}
+
+static int nft_basechain_init(struct nft_base_chain *basechain, u8 family,
+ struct nft_chain_hook *hook, u32 flags)
+{
+ struct nft_chain *chain;
+ struct nft_hook *h;
+
+ basechain->type = hook->type;
+ INIT_LIST_HEAD(&basechain->hook_list);
+ chain = &basechain->chain;
+
+ if (family == NFPROTO_NETDEV) {
+ list_splice_init(&hook->list, &basechain->hook_list);
+ list_for_each_entry(h, &basechain->hook_list, list)
+ nft_basechain_hook_init(&h->ops, family, hook, chain);
+
+ basechain->ops.hooknum = hook->num;
+ basechain->ops.priority = hook->priority;
+ } else {
+ nft_basechain_hook_init(&basechain->ops, family, hook, chain);
+ }
+
+ chain->flags |= NFT_BASE_CHAIN | flags;
+ basechain->policy = NF_ACCEPT;
+ if (chain->flags & NFT_CHAIN_HW_OFFLOAD &&
+ nft_chain_offload_priority(basechain) < 0)
+ return -EOPNOTSUPP;
+
+ flow_block_init(&basechain->flow_block);
+
+ return 0;
+}
+
static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
u8 policy, u32 flags)
{
if (nla[NFTA_CHAIN_HOOK]) {
struct nft_chain_hook hook;
- struct nf_hook_ops *ops;
err = nft_chain_parse_hook(net, nla, &hook, family, true);
if (err < 0)
nft_chain_release_hook(&hook);
return -ENOMEM;
}
-
- if (hook.dev != NULL)
- strncpy(basechain->dev_name, hook.dev->name, IFNAMSIZ);
+ chain = &basechain->chain;
if (nla[NFTA_CHAIN_COUNTERS]) {
stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]);
static_branch_inc(&nft_counters_enabled);
}
- basechain->type = hook.type;
- chain = &basechain->chain;
-
- ops = &basechain->ops;
- ops->pf = family;
- ops->hooknum = hook.num;
- ops->priority = hook.priority;
- ops->priv = chain;
- ops->hook = hook.type->hooks[ops->hooknum];
- ops->dev = hook.dev;
-
- chain->flags |= NFT_BASE_CHAIN | flags;
- basechain->policy = NF_ACCEPT;
- if (chain->flags & NFT_CHAIN_HW_OFFLOAD &&
- nft_chain_offload_priority(basechain) < 0)
- return -EOPNOTSUPP;
-
- flow_block_init(&basechain->flow_block);
+ err = nft_basechain_init(basechain, family, &hook, flags);
+ if (err < 0) {
+ nft_chain_release_hook(&hook);
+ kfree(basechain);
+ return err;
+ }
} else {
chain = kzalloc(sizeof(*chain), GFP_KERNEL);
if (chain == NULL)
return err;
}
+static bool nft_hook_list_equal(struct list_head *hook_list1,
+ struct list_head *hook_list2)
+{
+ struct nft_hook *hook;
+ int n = 0, m = 0;
+
+ n = 0;
+ list_for_each_entry(hook, hook_list2, list) {
+ if (!nft_hook_list_find(hook_list1, hook))
+ return false;
+
+ n++;
+ }
+ list_for_each_entry(hook, hook_list1, list)
+ m++;
+
+ return n == m;
+}
+
static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
u32 flags)
{
return -EBUSY;
}
- ops = &basechain->ops;
- if (ops->hooknum != hook.num ||
- ops->priority != hook.priority ||
- ops->dev != hook.dev) {
- nft_chain_release_hook(&hook);
- return -EBUSY;
+ if (ctx->family == NFPROTO_NETDEV) {
+ if (!nft_hook_list_equal(&basechain->hook_list,
+ &hook.list)) {
+ nft_chain_release_hook(&hook);
+ return -EBUSY;
+ }
+ } else {
+ ops = &basechain->ops;
+ if (ops->hooknum != hook.num ||
+ ops->priority != hook.priority) {
+ nft_chain_release_hook(&hook);
+ return -EBUSY;
+ }
}
nft_chain_release_hook(&hook);
}
if (nlh->nlmsg_flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
+ flags |= chain->flags & NFT_BASE_CHAIN;
return nf_tables_updchain(&ctx, genmask, policy, flags);
}
struct nft_trans *trans;
int err;
- if (!obj->ops->update)
- return -EOPNOTSUPP;
-
trans = nft_trans_alloc(ctx, NFT_MSG_NEWOBJ,
sizeof(struct nft_trans_obj));
if (!trans)
.len = NFT_NAME_MAXLEN - 1 },
[NFTA_FLOWTABLE_HOOK] = { .type = NLA_NESTED },
[NFTA_FLOWTABLE_HANDLE] = { .type = NLA_U64 },
+ [NFTA_FLOWTABLE_FLAGS] = { .type = NLA_U32 },
};
struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table,
return ERR_PTR(-ENOENT);
}
-static int nf_tables_parse_devices(const struct nft_ctx *ctx,
- const struct nlattr *attr,
- struct net_device *dev_array[], int *len)
-{
- const struct nlattr *tmp;
- struct net_device *dev;
- char ifname[IFNAMSIZ];
- int rem, n = 0, err;
-
- nla_for_each_nested(tmp, attr, rem) {
- if (nla_type(tmp) != NFTA_DEVICE_NAME) {
- err = -EINVAL;
- goto err1;
- }
-
- nla_strlcpy(ifname, tmp, IFNAMSIZ);
- dev = __dev_get_by_name(ctx->net, ifname);
- if (!dev) {
- err = -ENOENT;
- goto err1;
- }
-
- dev_array[n++] = dev;
- if (n == NFT_FLOWTABLE_DEVICE_MAX) {
- err = -EFBIG;
- goto err1;
- }
- }
- if (!len)
- return -EINVAL;
-
- err = 0;
-err1:
- *len = n;
- return err;
-}
-
static const struct nla_policy nft_flowtable_hook_policy[NFTA_FLOWTABLE_HOOK_MAX + 1] = {
[NFTA_FLOWTABLE_HOOK_NUM] = { .type = NLA_U32 },
[NFTA_FLOWTABLE_HOOK_PRIORITY] = { .type = NLA_U32 },
const struct nlattr *attr,
struct nft_flowtable *flowtable)
{
- struct net_device *dev_array[NFT_FLOWTABLE_DEVICE_MAX];
struct nlattr *tb[NFTA_FLOWTABLE_HOOK_MAX + 1];
- struct nf_hook_ops *ops;
+ struct nft_hook *hook;
int hooknum, priority;
- int err, n = 0, i;
+ int err;
err = nla_parse_nested_deprecated(tb, NFTA_FLOWTABLE_HOOK_MAX, attr,
nft_flowtable_hook_policy, NULL);
priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY]));
- err = nf_tables_parse_devices(ctx, tb[NFTA_FLOWTABLE_HOOK_DEVS],
- dev_array, &n);
+ err = nf_tables_parse_netdev_hooks(ctx->net,
+ tb[NFTA_FLOWTABLE_HOOK_DEVS],
+ &flowtable->hook_list);
if (err < 0)
return err;
- ops = kcalloc(n, sizeof(struct nf_hook_ops), GFP_KERNEL);
- if (!ops)
- return -ENOMEM;
-
- flowtable->hooknum = hooknum;
- flowtable->priority = priority;
- flowtable->ops = ops;
- flowtable->ops_len = n;
+ flowtable->hooknum = hooknum;
+ flowtable->data.priority = priority;
- for (i = 0; i < n; i++) {
- flowtable->ops[i].pf = NFPROTO_NETDEV;
- flowtable->ops[i].hooknum = hooknum;
- flowtable->ops[i].priority = priority;
- flowtable->ops[i].priv = &flowtable->data;
- flowtable->ops[i].hook = flowtable->data.type->hook;
- flowtable->ops[i].dev = dev_array[i];
+ list_for_each_entry(hook, &flowtable->hook_list, list) {
+ hook->ops.pf = NFPROTO_NETDEV;
+ hook->ops.hooknum = hooknum;
+ hook->ops.priority = priority;
+ hook->ops.priv = &flowtable->data;
+ hook->ops.hook = flowtable->data.type->hook;
}
return err;
return ERR_PTR(-ENOENT);
}
+static void nft_unregister_flowtable_hook(struct net *net,
+ struct nft_flowtable *flowtable,
+ struct nft_hook *hook)
+{
+ nf_unregister_net_hook(net, &hook->ops);
+ flowtable->data.type->setup(&flowtable->data, hook->ops.dev,
+ FLOW_BLOCK_UNBIND);
+}
+
static void nft_unregister_flowtable_net_hooks(struct net *net,
struct nft_flowtable *flowtable)
{
- int i;
+ struct nft_hook *hook;
- for (i = 0; i < flowtable->ops_len; i++) {
- if (!flowtable->ops[i].dev)
- continue;
+ list_for_each_entry(hook, &flowtable->hook_list, list)
+ nft_unregister_flowtable_hook(net, flowtable, hook);
+}
+
+static int nft_register_flowtable_net_hooks(struct net *net,
+ struct nft_table *table,
+ struct nft_flowtable *flowtable)
+{
+ struct nft_hook *hook, *hook2, *next;
+ struct nft_flowtable *ft;
+ int err, i = 0;
+
+ list_for_each_entry(hook, &flowtable->hook_list, list) {
+ list_for_each_entry(ft, &table->flowtables, list) {
+ list_for_each_entry(hook2, &ft->hook_list, list) {
+ if (hook->ops.dev == hook2->ops.dev &&
+ hook->ops.pf == hook2->ops.pf) {
+ err = -EBUSY;
+ goto err_unregister_net_hooks;
+ }
+ }
+ }
+
+ err = flowtable->data.type->setup(&flowtable->data,
+ hook->ops.dev,
+ FLOW_BLOCK_BIND);
+ if (err < 0)
+ goto err_unregister_net_hooks;
+
+ err = nf_register_net_hook(net, &hook->ops);
+ if (err < 0) {
+ flowtable->data.type->setup(&flowtable->data,
+ hook->ops.dev,
+ FLOW_BLOCK_UNBIND);
+ goto err_unregister_net_hooks;
+ }
+
+ i++;
+ }
+
+ return 0;
- nf_unregister_net_hook(net, &flowtable->ops[i]);
+err_unregister_net_hooks:
+ list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) {
+ if (i-- <= 0)
+ break;
+
+ nft_unregister_flowtable_hook(net, flowtable, hook);
+ list_del_rcu(&hook->list);
+ kfree_rcu(hook, rcu);
}
+
+ return err;
}
static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
const struct nf_flowtable_type *type;
- struct nft_flowtable *flowtable, *ft;
u8 genmask = nft_genmask_next(net);
int family = nfmsg->nfgen_family;
+ struct nft_flowtable *flowtable;
+ struct nft_hook *hook, *next;
struct nft_table *table;
struct nft_ctx ctx;
- int err, i, k;
+ int err;
if (!nla[NFTA_FLOWTABLE_TABLE] ||
!nla[NFTA_FLOWTABLE_NAME] ||
flowtable->table = table;
flowtable->handle = nf_tables_alloc_handle(table);
+ INIT_LIST_HEAD(&flowtable->hook_list);
flowtable->name = nla_strdup(nla[NFTA_FLOWTABLE_NAME], GFP_KERNEL);
if (!flowtable->name) {
goto err2;
}
+ if (nla[NFTA_FLOWTABLE_FLAGS]) {
+ flowtable->data.flags =
+ ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS]));
+ if (flowtable->data.flags & ~NF_FLOWTABLE_HW_OFFLOAD)
+ goto err3;
+ }
+
+ write_pnet(&flowtable->data.net, net);
flowtable->data.type = type;
err = type->init(&flowtable->data);
if (err < 0)
if (err < 0)
goto err4;
- for (i = 0; i < flowtable->ops_len; i++) {
- if (!flowtable->ops[i].dev)
- continue;
-
- list_for_each_entry(ft, &table->flowtables, list) {
- for (k = 0; k < ft->ops_len; k++) {
- if (!ft->ops[k].dev)
- continue;
-
- if (flowtable->ops[i].dev == ft->ops[k].dev &&
- flowtable->ops[i].pf == ft->ops[k].pf) {
- err = -EBUSY;
- goto err5;
- }
- }
- }
-
- err = nf_register_net_hook(net, &flowtable->ops[i]);
- if (err < 0)
- goto err5;
- }
+ err = nft_register_flowtable_net_hooks(ctx.net, table, flowtable);
+ if (err < 0)
+ goto err4;
err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable);
if (err < 0)
- goto err6;
+ goto err5;
list_add_tail_rcu(&flowtable->list, &table->flowtables);
table->use++;
return 0;
-err6:
- i = flowtable->ops_len;
err5:
- for (k = i - 1; k >= 0; k--)
- nf_unregister_net_hook(net, &flowtable->ops[k]);
-
- kfree(flowtable->ops);
+ list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) {
+ nft_unregister_flowtable_hook(net, flowtable, hook);
+ list_del_rcu(&hook->list);
+ kfree_rcu(hook, rcu);
+ }
err4:
flowtable->data.type->free(&flowtable->data);
err3:
{
struct nlattr *nest, *nest_devs;
struct nfgenmsg *nfmsg;
+ struct nft_hook *hook;
struct nlmsghdr *nlh;
- int i;
event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags);
nla_put_string(skb, NFTA_FLOWTABLE_NAME, flowtable->name) ||
nla_put_be32(skb, NFTA_FLOWTABLE_USE, htonl(flowtable->use)) ||
nla_put_be64(skb, NFTA_FLOWTABLE_HANDLE, cpu_to_be64(flowtable->handle),
- NFTA_FLOWTABLE_PAD))
+ NFTA_FLOWTABLE_PAD) ||
+ nla_put_be32(skb, NFTA_FLOWTABLE_FLAGS, htonl(flowtable->data.flags)))
goto nla_put_failure;
nest = nla_nest_start_noflag(skb, NFTA_FLOWTABLE_HOOK);
if (!nest)
goto nla_put_failure;
if (nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_NUM, htonl(flowtable->hooknum)) ||
- nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_PRIORITY, htonl(flowtable->priority)))
+ nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_PRIORITY, htonl(flowtable->data.priority)))
goto nla_put_failure;
nest_devs = nla_nest_start_noflag(skb, NFTA_FLOWTABLE_HOOK_DEVS);
if (!nest_devs)
goto nla_put_failure;
- for (i = 0; i < flowtable->ops_len; i++) {
- const struct net_device *dev = READ_ONCE(flowtable->ops[i].dev);
-
- if (dev &&
- nla_put_string(skb, NFTA_DEVICE_NAME, dev->name))
+ list_for_each_entry_rcu(hook, &flowtable->hook_list, list) {
+ if (nla_put_string(skb, NFTA_DEVICE_NAME, hook->ops.dev->name))
goto nla_put_failure;
}
nla_nest_end(skb, nest_devs);
static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
{
- kfree(flowtable->ops);
+ struct nft_hook *hook, *next;
+
+ list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) {
+ list_del_rcu(&hook->list);
+ kfree(hook);
+ }
kfree(flowtable->name);
flowtable->data.type->free(&flowtable->data);
module_put(flowtable->data.type->owner);
static void nft_flowtable_event(unsigned long event, struct net_device *dev,
struct nft_flowtable *flowtable)
{
- int i;
+ struct nft_hook *hook;
- for (i = 0; i < flowtable->ops_len; i++) {
- if (flowtable->ops[i].dev != dev)
+ list_for_each_entry(hook, &flowtable->hook_list, list) {
+ if (hook->ops.dev != dev)
continue;
- nf_unregister_net_hook(dev_net(dev), &flowtable->ops[i]);
- flowtable->ops[i].dev = NULL;
+ nft_unregister_flowtable_hook(dev_net(dev), flowtable, hook);
+ list_del_rcu(&hook->list);
+ kfree_rcu(hook, rcu);
break;
}
}
obj = nft_trans_obj(trans);
newobj = nft_trans_obj_newobj(trans);
- obj->ops->update(obj, newobj);
+ if (obj->ops->update)
+ obj->ops->update(obj, newobj);
kfree(newobj);
}
struct tcf_chain *goto_chain)
{
a->tcfa_action = action;
- rcu_swap_protected(a->goto_chain, goto_chain, 1);
+ goto_chain = rcu_replace_pointer(a->goto_chain, goto_chain, 1);
return goto_chain;
}
EXPORT_SYMBOL(tcf_action_set_ctrlact);
+ nla_total_size(0) /* TCA_ACT_STATS nested */
/* TCA_STATS_BASIC */
+ nla_total_size_64bit(sizeof(struct gnet_stats_basic))
+ /* TCA_STATS_PKT64 */
+ + nla_total_size_64bit(sizeof(u64))
/* TCA_STATS_QUEUE */
+ nla_total_size_64bit(sizeof(struct gnet_stats_queue))
+ nla_total_size(0) /* TCA_OPTIONS nested */
int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
struct tc_action **a, const struct tc_action_ops *ops,
- int bind, bool cpustats)
+ int bind, bool cpustats, u32 flags)
{
struct tc_action *p = kzalloc(ops->size, GFP_KERNEL);
struct tcf_idrinfo *idrinfo = tn->idrinfo;
p->tcfa_tm.install = jiffies;
p->tcfa_tm.lastuse = jiffies;
p->tcfa_tm.firstuse = 0;
+ p->tcfa_flags = flags;
if (est) {
err = gen_new_estimator(&p->tcfa_bstats, p->cpu_bstats,
&p->tcfa_rate_est,
}
EXPORT_SYMBOL(tcf_idr_create);
+int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index,
+ struct nlattr *est, struct tc_action **a,
+ const struct tc_action_ops *ops, int bind,
+ u32 flags)
+{
+ /* Set cpustats according to actions flags. */
+ return tcf_idr_create(tn, index, est, a, ops, bind,
+ !(flags & TCA_ACT_FLAGS_NO_PERCPU_STATS), flags);
+}
+EXPORT_SYMBOL(tcf_idr_create_from_flags);
+
void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a)
{
struct tcf_idrinfo *idrinfo = tn->idrinfo;
}
rcu_read_unlock();
+ if (a->tcfa_flags) {
+ struct nla_bitfield32 flags = { a->tcfa_flags,
+ a->tcfa_flags, };
+
+ if (nla_put(skb, TCA_ACT_FLAGS, sizeof(flags), &flags))
+ goto nla_put_failure;
+ }
+
nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
return c;
}
+static const u32 tca_act_flags_allowed = TCA_ACT_FLAGS_NO_PERCPU_STATS;
static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = {
[TCA_ACT_KIND] = { .type = NLA_STRING },
[TCA_ACT_INDEX] = { .type = NLA_U32 },
[TCA_ACT_COOKIE] = { .type = NLA_BINARY,
.len = TC_COOKIE_MAX_SIZE },
[TCA_ACT_OPTIONS] = { .type = NLA_NESTED },
+ [TCA_ACT_FLAGS] = { .type = NLA_BITFIELD32,
+ .validation_data = &tca_act_flags_allowed },
};
struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
bool rtnl_held,
struct netlink_ext_ack *extack)
{
+ struct nla_bitfield32 flags = { 0, 0 };
struct tc_action *a;
struct tc_action_ops *a_o;
struct tc_cookie *cookie = NULL;
goto err_out;
}
}
+ if (tb[TCA_ACT_FLAGS])
+ flags = nla_get_bitfield32(tb[TCA_ACT_FLAGS]);
} else {
if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ) {
NL_SET_ERR_MSG(extack, "TC action name too long");
/* backward compatibility for policer */
if (name == NULL)
err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind,
- rtnl_held, tp, extack);
+ rtnl_held, tp, flags.value, extack);
else
err = a_o->init(net, nla, est, &a, ovr, bind, rtnl_held,
- tp, extack);
+ tp, flags.value, extack);
if (err < 0)
goto err_mod;
err = PTR_ERR(act);
goto err;
}
- act->order = i;
sz += tcf_action_fill_size(act);
/* Start from index 0 */
actions[i - 1] = act;
return err;
}
+void tcf_action_update_stats(struct tc_action *a, u64 bytes, u32 packets,
+ bool drop, bool hw)
+{
+ if (a->cpu_bstats) {
+ _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
+
+ if (drop)
+ this_cpu_ptr(a->cpu_qstats)->drops += packets;
+
+ if (hw)
+ _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
+ bytes, packets);
+ return;
+ }
+
+ _bstats_update(&a->tcfa_bstats, bytes, packets);
+ if (drop)
+ a->tcfa_qstats.drops += packets;
+ if (hw)
+ _bstats_update(&a->tcfa_bstats_hw, bytes, packets);
+}
+EXPORT_SYMBOL(tcf_action_update_stats);
+
int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p,
int compat_mode)
{
static int tcf_csum_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a, int ovr,
int bind, bool rtnl_held, struct tcf_proto *tp,
- struct netlink_ext_ack *extack)
+ u32 flags, struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, csum_net_id);
struct tcf_csum_params *params_new;
index = parm->index;
err = tcf_idr_check_alloc(tn, &index, a, bind);
if (!err) {
- ret = tcf_idr_create(tn, index, est, a,
- &act_csum_ops, bind, true);
+ ret = tcf_idr_create_from_flags(tn, index, est, a,
+ &act_csum_ops, bind, flags);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
spin_lock_bh(&p->tcf_lock);
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
- rcu_swap_protected(p->params, params_new,
- lockdep_is_held(&p->tcf_lock));
+ params_new = rcu_replace_pointer(p->params, params_new,
+ lockdep_is_held(&p->tcf_lock));
spin_unlock_bh(&p->tcf_lock);
if (goto_ch)
params = rcu_dereference_bh(p->params);
tcf_lastuse_update(&p->tcf_tm);
- bstats_cpu_update(this_cpu_ptr(p->common.cpu_bstats), skb);
+ tcf_action_update_bstats(&p->common, skb);
action = READ_ONCE(p->tcf_action);
if (unlikely(action == TC_ACT_SHOT))
return action;
drop:
- qstats_drop_inc(this_cpu_ptr(p->common.cpu_qstats));
+ tcf_action_inc_drop_qstats(&p->common);
action = TC_ACT_SHOT;
goto out;
}
skb_push_rcsum(skb, nh_ofs);
out:
- bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), skb);
+ tcf_action_update_bstats(&c->common, skb);
return retval;
drop:
- qstats_drop_inc(this_cpu_ptr(a->cpu_qstats));
+ tcf_action_inc_drop_qstats(&c->common);
return TC_ACT_SHOT;
}
static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = {
- [TCA_CT_UNSPEC] = { .strict_start_type = TCA_CT_UNSPEC + 1 },
[TCA_CT_ACTION] = { .type = NLA_U16 },
[TCA_CT_PARMS] = { .type = NLA_EXACT_LEN, .len = sizeof(struct tc_ct) },
[TCA_CT_ZONE] = { .type = NLA_U16 },
static int tcf_ct_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int replace, int bind, bool rtnl_held,
- struct tcf_proto *tp,
+ struct tcf_proto *tp, u32 flags,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, ct_net_id);
return err;
if (!err) {
- err = tcf_idr_create(tn, index, est, a,
- &act_ct_ops, bind, true);
+ err = tcf_idr_create_from_flags(tn, index, est, a,
+ &act_ct_ops, bind, flags);
if (err) {
tcf_idr_cleanup(tn, index);
return err;
spin_lock_bh(&c->tcf_lock);
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
- rcu_swap_protected(c->params, params, lockdep_is_held(&c->tcf_lock));
+ params = rcu_replace_pointer(c->params, params,
+ lockdep_is_held(&c->tcf_lock));
spin_unlock_bh(&c->tcf_lock);
if (goto_ch)
{
struct tcf_ct *c = to_ct(a);
- _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
-
- if (hw)
- _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
- bytes, packets);
+ tcf_action_update_stats(a, bytes, packets, false, hw);
c->tcf_tm.lastuse = max_t(u64, c->tcf_tm.lastuse, lastuse);
}
static int tcf_ctinfo_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
- struct tcf_proto *tp,
+ struct tcf_proto *tp, u32 flags,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, ctinfo_net_id);
err = tcf_idr_check_alloc(tn, &index, a, bind);
if (!err) {
ret = tcf_idr_create(tn, index, est, a,
- &act_ctinfo_ops, bind, false);
+ &act_ctinfo_ops, bind, false, 0);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
spin_lock_bh(&ci->tcf_lock);
goto_ch = tcf_action_set_ctrlact(*a, actparm->action, goto_ch);
- rcu_swap_protected(ci->params, cp_new,
- lockdep_is_held(&ci->tcf_lock));
+ cp_new = rcu_replace_pointer(ci->params, cp_new,
+ lockdep_is_held(&ci->tcf_lock));
spin_unlock_bh(&ci->tcf_lock);
if (goto_ch)
static int tcf_ife_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
- struct tcf_proto *tp, struct netlink_ext_ack *extack)
+ struct tcf_proto *tp, u32 flags,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, ife_net_id);
struct nlattr *tb[TCA_IFE_MAX + 1];
if (!exists) {
ret = tcf_idr_create(tn, index, est, a, &act_ife_ops,
- bind, true);
+ bind, true, 0);
if (ret) {
tcf_idr_cleanup(tn, index);
kfree(p);
spin_lock_bh(&ife->tcf_lock);
/* protected by tcf_lock when modifying existing action */
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
- rcu_swap_protected(ife->params, p, 1);
+ p = rcu_replace_pointer(ife->params, p, 1);
if (exists)
spin_unlock_bh(&ife->tcf_lock);
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
struct tcf_proto *tp,
- struct netlink_ext_ack *extack)
+ u32 flags, struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, mirred_net_id);
struct nlattr *tb[TCA_MIRRED_MAX + 1];
NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist");
return -EINVAL;
}
- ret = tcf_idr_create(tn, index, est, a,
- &act_mirred_ops, bind, true);
+ ret = tcf_idr_create_from_flags(tn, index, est, a,
+ &act_mirred_ops, bind, flags);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
goto put_chain;
}
mac_header_xmit = dev_is_mac_header_xmit(dev);
- rcu_swap_protected(m->tcfm_dev, dev,
- lockdep_is_held(&m->tcf_lock));
+ dev = rcu_replace_pointer(m->tcfm_dev, dev,
+ lockdep_is_held(&m->tcf_lock));
if (dev)
dev_put(dev);
m->tcfm_mac_header_xmit = mac_header_xmit;
}
tcf_lastuse_update(&m->tcf_tm);
- bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb);
+ tcf_action_update_bstats(&m->common, skb);
m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit);
m_eaction = READ_ONCE(m->tcfm_eaction);
/* let's the caller reinsert the packet, if possible */
if (use_reinsert) {
res->ingress = want_ingress;
- res->qstats = this_cpu_ptr(m->common.cpu_qstats);
- skb_tc_reinsert(skb, res);
+ if (skb_tc_reinsert(skb, res))
+ tcf_action_inc_overlimit_qstats(&m->common);
__this_cpu_dec(mirred_rec_level);
return TC_ACT_CONSUMED;
}
if (err) {
out:
- qstats_overlimit_inc(this_cpu_ptr(m->common.cpu_qstats));
+ tcf_action_inc_overlimit_qstats(&m->common);
if (tcf_mirred_is_act_redirect(m_eaction))
retval = TC_ACT_SHOT;
}
struct tcf_mirred *m = to_mirred(a);
struct tcf_t *tm = &m->tcf_tm;
- _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
- if (hw)
- _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
- bytes, packets);
+ tcf_action_update_stats(a, bytes, packets, false, hw);
tm->lastuse = max_t(u64, tm->lastuse, lastuse);
}
}
static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = {
- [TCA_MPLS_UNSPEC] = { .strict_start_type = TCA_MPLS_UNSPEC + 1 },
[TCA_MPLS_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_mpls)),
[TCA_MPLS_PROTO] = { .type = NLA_U16 },
[TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_U32, valid_label),
static int tcf_mpls_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
- struct tcf_proto *tp, struct netlink_ext_ack *extack)
+ struct tcf_proto *tp, u32 flags,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, mpls_net_id);
struct nlattr *tb[TCA_MPLS_MAX + 1];
if (!exists) {
ret = tcf_idr_create(tn, index, est, a,
- &act_mpls_ops, bind, true);
+ &act_mpls_ops, bind, true, 0);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
spin_lock_bh(&m->tcf_lock);
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
- rcu_swap_protected(m->mpls_p, p, lockdep_is_held(&m->tcf_lock));
+ p = rcu_replace_pointer(m->mpls_p, p, lockdep_is_held(&m->tcf_lock));
spin_unlock_bh(&m->tcf_lock);
if (goto_ch)
static int tcf_police_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
- struct tcf_proto *tp,
+ struct tcf_proto *tp, u32 flags,
struct netlink_ext_ack *extack)
{
int ret = 0, tcfp_result = TC_ACT_OK, err, size;
if (!exists) {
ret = tcf_idr_create(tn, index, NULL, a,
- &act_police_ops, bind, true);
+ &act_police_ops, bind, true, 0);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
police->tcfp_ptoks = new->tcfp_mtu_ptoks;
spin_unlock_bh(&police->tcfp_lock);
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
- rcu_swap_protected(police->params,
- new,
- lockdep_is_held(&police->tcf_lock));
+ new = rcu_replace_pointer(police->params,
+ new,
+ lockdep_is_held(&police->tcf_lock));
spin_unlock_bh(&police->tcf_lock);
if (goto_ch)
struct tcf_police *police = to_police(a);
struct tcf_t *tm = &police->tcf_tm;
- _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
- if (hw)
- _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
- bytes, packets);
+ tcf_action_update_stats(a, bytes, packets, false, hw);
tm->lastuse = max_t(u64, tm->lastuse, lastuse);
}
nla_put_u32(skb, TCA_POLICE_AVRATE, p->tcfp_ewma_rate))
goto nla_put_failure;
- t.install = jiffies_to_clock_t(jiffies - police->tcf_tm.install);
- t.lastuse = jiffies_to_clock_t(jiffies - police->tcf_tm.lastuse);
- t.firstuse = jiffies_to_clock_t(jiffies - police->tcf_tm.firstuse);
- t.expires = jiffies_to_clock_t(police->tcf_tm.expires);
+ tcf_tm_dump(&t, &police->tcf_tm);
if (nla_put_64bit(skb, TCA_POLICE_TM, sizeof(t), &t, TCA_POLICE_PAD))
goto nla_put_failure;
spin_unlock_bh(&police->tcf_lock);
static int tcf_sample_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a, int ovr,
int bind, bool rtnl_held, struct tcf_proto *tp,
- struct netlink_ext_ack *extack)
+ u32 flags, struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, sample_net_id);
struct nlattr *tb[TCA_SAMPLE_MAX + 1];
if (!exists) {
ret = tcf_idr_create(tn, index, est, a,
- &act_sample_ops, bind, true);
+ &act_sample_ops, bind, true, 0);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
s->rate = rate;
s->psample_group_num = psample_group_num;
- rcu_swap_protected(s->psample_group, psample_group,
- lockdep_is_held(&s->tcf_lock));
+ psample_group = rcu_replace_pointer(s->psample_group, psample_group,
+ lockdep_is_held(&s->tcf_lock));
if (tb[TCA_SAMPLE_TRUNC_SIZE]) {
s->truncate = true;
static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
- struct tcf_proto *tp,
+ struct tcf_proto *tp, u32 act_flags,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, skbedit_net_id);
if (!exists) {
ret = tcf_idr_create(tn, index, est, a,
- &act_skbedit_ops, bind, true);
+ &act_skbedit_ops, bind, true, 0);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
spin_lock_bh(&d->tcf_lock);
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
- rcu_swap_protected(d->params, params_new,
- lockdep_is_held(&d->tcf_lock));
+ params_new = rcu_replace_pointer(d->params, params_new,
+ lockdep_is_held(&d->tcf_lock));
spin_unlock_bh(&d->tcf_lock);
if (params_new)
kfree_rcu(params_new, rcu);
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <net/geneve.h>
+#include <net/vxlan.h>
+#include <net/erspan.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/dst.h>
params = rcu_dereference_bh(t->params);
tcf_lastuse_update(&t->tcf_tm);
- bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb);
+ tcf_action_update_bstats(&t->common, skb);
action = READ_ONCE(t->tcf_action);
switch (params->tcft_action) {
static const struct nla_policy
enc_opts_policy[TCA_TUNNEL_KEY_ENC_OPTS_MAX + 1] = {
+ [TCA_TUNNEL_KEY_ENC_OPTS_UNSPEC] = {
+ .strict_start_type = TCA_TUNNEL_KEY_ENC_OPTS_VXLAN },
[TCA_TUNNEL_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED },
+ [TCA_TUNNEL_KEY_ENC_OPTS_VXLAN] = { .type = NLA_NESTED },
+ [TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN] = { .type = NLA_NESTED },
};
static const struct nla_policy
.len = 128 },
};
+static const struct nla_policy
+vxlan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1] = {
+ [TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP] = { .type = NLA_U32 },
+};
+
+static const struct nla_policy
+erspan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1] = {
+ [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER] = { .type = NLA_U8 },
+ [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX] = { .type = NLA_U32 },
+ [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR] = { .type = NLA_U8 },
+ [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID] = { .type = NLA_U8 },
+};
+
static int
tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len,
struct netlink_ext_ack *extack)
return opt_len;
}
+static int
+tunnel_key_copy_vxlan_opt(const struct nlattr *nla, void *dst, int dst_len,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1];
+ int err;
+
+ err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX, nla,
+ vxlan_opt_policy, extack);
+ if (err < 0)
+ return err;
+
+ if (!tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]) {
+ NL_SET_ERR_MSG(extack, "Missing tunnel key vxlan option gbp");
+ return -EINVAL;
+ }
+
+ if (dst) {
+ struct vxlan_metadata *md = dst;
+
+ md->gbp = nla_get_u32(tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]);
+ }
+
+ return sizeof(struct vxlan_metadata);
+}
+
+static int
+tunnel_key_copy_erspan_opt(const struct nlattr *nla, void *dst, int dst_len,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1];
+ int err;
+ u8 ver;
+
+ err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX, nla,
+ erspan_opt_policy, extack);
+ if (err < 0)
+ return err;
+
+ if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]) {
+ NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option ver");
+ return -EINVAL;
+ }
+
+ ver = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]);
+ if (ver == 1) {
+ if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX]) {
+ NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option index");
+ return -EINVAL;
+ }
+ } else if (ver == 2) {
+ if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR] ||
+ !tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID]) {
+ NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option dir or hwid");
+ return -EINVAL;
+ }
+ } else {
+ NL_SET_ERR_MSG(extack, "Tunnel key erspan option ver is incorrect");
+ return -EINVAL;
+ }
+
+ if (dst) {
+ struct erspan_metadata *md = dst;
+
+ md->version = ver;
+ if (ver == 1) {
+ nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX];
+ md->u.index = nla_get_be32(nla);
+ } else {
+ nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR];
+ md->u.md2.dir = nla_get_u8(nla);
+ nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID];
+ set_hwid(&md->u.md2, nla_get_u8(nla));
+ }
+ }
+
+ return sizeof(struct erspan_metadata);
+}
+
static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst,
int dst_len, struct netlink_ext_ack *extack)
{
- int err, rem, opt_len, len = nla_len(nla), opts_len = 0;
+ int err, rem, opt_len, len = nla_len(nla), opts_len = 0, type = 0;
const struct nlattr *attr, *head = nla_data(nla);
err = nla_validate_deprecated(head, len, TCA_TUNNEL_KEY_ENC_OPTS_MAX,
nla_for_each_attr(attr, head, len, rem) {
switch (nla_type(attr)) {
case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE:
+ if (type && type != TUNNEL_GENEVE_OPT) {
+ NL_SET_ERR_MSG(extack, "Duplicate type for geneve options");
+ return -EINVAL;
+ }
opt_len = tunnel_key_copy_geneve_opt(attr, dst,
dst_len, extack);
if (opt_len < 0)
return opt_len;
opts_len += opt_len;
+ if (opts_len > IP_TUNNEL_OPTS_MAX) {
+ NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size");
+ return -EINVAL;
+ }
if (dst) {
dst_len -= opt_len;
dst += opt_len;
}
+ type = TUNNEL_GENEVE_OPT;
+ break;
+ case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN:
+ if (type) {
+ NL_SET_ERR_MSG(extack, "Duplicate type for vxlan options");
+ return -EINVAL;
+ }
+ opt_len = tunnel_key_copy_vxlan_opt(attr, dst,
+ dst_len, extack);
+ if (opt_len < 0)
+ return opt_len;
+ opts_len += opt_len;
+ type = TUNNEL_VXLAN_OPT;
+ break;
+ case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN:
+ if (type) {
+ NL_SET_ERR_MSG(extack, "Duplicate type for erspan options");
+ return -EINVAL;
+ }
+ opt_len = tunnel_key_copy_erspan_opt(attr, dst,
+ dst_len, extack);
+ if (opt_len < 0)
+ return opt_len;
+ opts_len += opt_len;
+ type = TUNNEL_ERSPAN_OPT;
break;
}
}
opts_len, extack);
#else
return -EAFNOSUPPORT;
+#endif
+ case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN:
+#if IS_ENABLED(CONFIG_INET)
+ info->key.tun_flags |= TUNNEL_VXLAN_OPT;
+ return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info),
+ opts_len, extack);
+#else
+ return -EAFNOSUPPORT;
+#endif
+ case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN:
+#if IS_ENABLED(CONFIG_INET)
+ info->key.tun_flags |= TUNNEL_ERSPAN_OPT;
+ return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info),
+ opts_len, extack);
+#else
+ return -EAFNOSUPPORT;
#endif
default:
NL_SET_ERR_MSG(extack, "Cannot set tunnel options for unknown tunnel type");
static int tunnel_key_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
- struct tcf_proto *tp,
+ struct tcf_proto *tp, u32 act_flags,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
}
if (!exists) {
- ret = tcf_idr_create(tn, index, est, a,
- &act_tunnel_key_ops, bind, true);
+ ret = tcf_idr_create_from_flags(tn, index, est, a,
+ &act_tunnel_key_ops, bind,
+ act_flags);
if (ret) {
NL_SET_ERR_MSG(extack, "Cannot create TC IDR");
goto release_tun_meta;
spin_lock_bh(&t->tcf_lock);
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
- rcu_swap_protected(t->params, params_new,
- lockdep_is_held(&t->tcf_lock));
+ params_new = rcu_replace_pointer(t->params, params_new,
+ lockdep_is_held(&t->tcf_lock));
spin_unlock_bh(&t->tcf_lock);
tunnel_key_release_params(params_new);
if (goto_ch)
return 0;
}
+static int tunnel_key_vxlan_opts_dump(struct sk_buff *skb,
+ const struct ip_tunnel_info *info)
+{
+ struct vxlan_metadata *md = (struct vxlan_metadata *)(info + 1);
+ struct nlattr *start;
+
+ start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_VXLAN);
+ if (!start)
+ return -EMSGSIZE;
+
+ if (nla_put_u32(skb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP, md->gbp)) {
+ nla_nest_cancel(skb, start);
+ return -EMSGSIZE;
+ }
+
+ nla_nest_end(skb, start);
+ return 0;
+}
+
+static int tunnel_key_erspan_opts_dump(struct sk_buff *skb,
+ const struct ip_tunnel_info *info)
+{
+ struct erspan_metadata *md = (struct erspan_metadata *)(info + 1);
+ struct nlattr *start;
+
+ start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN);
+ if (!start)
+ return -EMSGSIZE;
+
+ if (nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER, md->version))
+ goto err;
+
+ if (md->version == 1 &&
+ nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX, md->u.index))
+ goto err;
+
+ if (md->version == 2 &&
+ (nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR,
+ md->u.md2.dir) ||
+ nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID,
+ get_hwid(&md->u.md2))))
+ goto err;
+
+ nla_nest_end(skb, start);
+ return 0;
+err:
+ nla_nest_cancel(skb, start);
+ return -EMSGSIZE;
+}
+
static int tunnel_key_opts_dump(struct sk_buff *skb,
const struct ip_tunnel_info *info)
{
err = tunnel_key_geneve_opts_dump(skb, info);
if (err)
goto err_out;
+ } else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) {
+ err = tunnel_key_vxlan_opts_dump(skb, info);
+ if (err)
+ goto err_out;
+ } else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) {
+ err = tunnel_key_erspan_opts_dump(skb, info);
+ if (err)
+ goto err_out;
} else {
err_out:
nla_nest_cancel(skb, start);
u16 tci;
tcf_lastuse_update(&v->tcf_tm);
- bstats_cpu_update(this_cpu_ptr(v->common.cpu_bstats), skb);
+ tcf_action_update_bstats(&v->common, skb);
/* Ensure 'data' points at mac_header prior calling vlan manipulating
* functions.
return action;
drop:
- qstats_drop_inc(this_cpu_ptr(v->common.cpu_qstats));
+ tcf_action_inc_drop_qstats(&v->common);
return TC_ACT_SHOT;
}
static int tcf_vlan_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
- struct tcf_proto *tp, struct netlink_ext_ack *extack)
+ struct tcf_proto *tp, u32 flags,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, vlan_net_id);
struct nlattr *tb[TCA_VLAN_MAX + 1];
action = parm->v_action;
if (!exists) {
- ret = tcf_idr_create(tn, index, est, a,
- &act_vlan_ops, bind, true);
+ ret = tcf_idr_create_from_flags(tn, index, est, a,
+ &act_vlan_ops, bind, flags);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
spin_lock_bh(&v->tcf_lock);
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
- rcu_swap_protected(v->vlan_p, p, lockdep_is_held(&v->tcf_lock));
+ p = rcu_replace_pointer(v->vlan_p, p, lockdep_is_held(&v->tcf_lock));
spin_unlock_bh(&v->tcf_lock);
if (goto_ch)
struct tcf_vlan *v = to_vlan(a);
struct tcf_t *tm = &v->tcf_tm;
- _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
- if (hw)
- _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
- bytes, packets);
+ tcf_action_update_stats(a, bytes, packets, false, hw);
tm->lastuse = max_t(u64, tm->lastuse, lastuse);
}