aboutsummaryrefslogtreecommitdiffstats
path: root/net/core/dev.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/dev.c')
-rw-r--r--net/core/dev.c480
1 files changed, 352 insertions, 128 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 828ecca03c07..50ae8a2db946 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -79,6 +79,7 @@
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/mutex.h>
+#include <linux/rwsem.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
@@ -194,7 +195,7 @@ static DEFINE_SPINLOCK(napi_hash_lock);
static unsigned int napi_gen_id = NR_CPUS;
static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8);
-static seqcount_t devnet_rename_seq;
+static DECLARE_RWSEM(devnet_rename_sem);
static inline void dev_base_seq_inc(struct net *net)
{
@@ -217,14 +218,14 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex)
static inline void rps_lock(struct softnet_data *sd)
{
#ifdef CONFIG_RPS
- spin_lock(&sd->input_pkt_queue.lock);
+ raw_spin_lock(&sd->input_pkt_queue.raw_lock);
#endif
}
static inline void rps_unlock(struct softnet_data *sd)
{
#ifdef CONFIG_RPS
- spin_unlock(&sd->input_pkt_queue.lock);
+ raw_spin_unlock(&sd->input_pkt_queue.raw_lock);
#endif
}
@@ -898,33 +899,28 @@ EXPORT_SYMBOL(dev_get_by_napi_id);
* @net: network namespace
* @name: a pointer to the buffer where the name will be stored.
* @ifindex: the ifindex of the interface to get the name from.
- *
- * The use of raw_seqcount_begin() and cond_resched() before
- * retrying is required as we want to give the writers a chance
- * to complete when CONFIG_PREEMPT is not set.
*/
int netdev_get_name(struct net *net, char *name, int ifindex)
{
struct net_device *dev;
- unsigned int seq;
+ int ret;
-retry:
- seq = raw_seqcount_begin(&devnet_rename_seq);
+ down_read(&devnet_rename_sem);
rcu_read_lock();
+
dev = dev_get_by_index_rcu(net, ifindex);
if (!dev) {
- rcu_read_unlock();
- return -ENODEV;
+ ret = -ENODEV;
+ goto out;
}
strcpy(name, dev->name);
- rcu_read_unlock();
- if (read_seqcount_retry(&devnet_rename_seq, seq)) {
- cond_resched();
- goto retry;
- }
- return 0;
+ ret = 0;
+out:
+ rcu_read_unlock();
+ up_read(&devnet_rename_sem);
+ return ret;
}
/**
@@ -1197,10 +1193,10 @@ int dev_change_name(struct net_device *dev, const char *newname)
likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK)))
return -EBUSY;
- write_seqcount_begin(&devnet_rename_seq);
+ down_write(&devnet_rename_sem);
if (strncmp(newname, dev->name, IFNAMSIZ) == 0) {
- write_seqcount_end(&devnet_rename_seq);
+ up_write(&devnet_rename_sem);
return 0;
}
@@ -1208,7 +1204,7 @@ int dev_change_name(struct net_device *dev, const char *newname)
err = dev_get_valid_name(net, dev, newname);
if (err < 0) {
- write_seqcount_end(&devnet_rename_seq);
+ up_write(&devnet_rename_sem);
return err;
}
@@ -1223,11 +1219,11 @@ rollback:
if (ret) {
memcpy(dev->name, oldname, IFNAMSIZ);
dev->name_assign_type = old_assign_type;
- write_seqcount_end(&devnet_rename_seq);
+ up_write(&devnet_rename_sem);
return ret;
}
- write_seqcount_end(&devnet_rename_seq);
+ up_write(&devnet_rename_sem);
netdev_adjacent_rename_links(dev, oldname);
@@ -1248,7 +1244,7 @@ rollback:
/* err >= 0 after dev_alloc_name() or stores the first errno */
if (err >= 0) {
err = ret;
- write_seqcount_begin(&devnet_rename_seq);
+ down_write(&devnet_rename_sem);
memcpy(dev->name, oldname, IFNAMSIZ);
memcpy(oldname, newname, IFNAMSIZ);
dev->name_assign_type = old_assign_type;
@@ -2750,6 +2746,7 @@ static void __netif_reschedule(struct Qdisc *q)
sd->output_queue_tailp = &q->next_sched;
raise_softirq_irqoff(NET_TX_SOFTIRQ);
local_irq_restore(flags);
+ preempt_check_resched_rt();
}
void __netif_schedule(struct Qdisc *q)
@@ -2812,6 +2809,7 @@ void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
__this_cpu_write(softnet_data.completion_queue, skb);
raise_softirq_irqoff(NET_TX_SOFTIRQ);
local_irq_restore(flags);
+ preempt_check_resched_rt();
}
EXPORT_SYMBOL(__dev_kfree_skb_irq);
@@ -2877,6 +2875,8 @@ static u16 skb_tx_hash(const struct net_device *dev,
if (skb_rx_queue_recorded(skb)) {
hash = skb_get_rx_queue(skb);
+ if (hash >= qoffset)
+ hash -= qoffset;
while (unlikely(hash >= qcount))
hash -= qcount;
return hash + qoffset;
@@ -3475,26 +3475,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
qdisc_calculate_pkt_len(skb, q);
if (q->flags & TCQ_F_NOLOCK) {
- if ((q->flags & TCQ_F_CAN_BYPASS) && q->empty &&
- qdisc_run_begin(q)) {
- if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED,
- &q->state))) {
- __qdisc_drop(skb, &to_free);
- rc = NET_XMIT_DROP;
- goto end_run;
- }
- qdisc_bstats_cpu_update(q, skb);
-
- rc = NET_XMIT_SUCCESS;
- if (sch_direct_xmit(skb, q, dev, txq, NULL, true))
- __qdisc_run(q);
-
-end_run:
- qdisc_run_end(q);
- } else {
- rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
- qdisc_run(q);
- }
+ rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+ qdisc_run(q);
if (unlikely(to_free))
kfree_skb_list(to_free);
@@ -3507,7 +3489,11 @@ end_run:
* This permits qdisc->running owner to get the lock more
* often and dequeue packets faster.
*/
+#ifdef CONFIG_PREEMPT_RT_FULL
+ contended = true;
+#else
contended = qdisc_is_running(q);
+#endif
if (unlikely(contended))
spin_lock(&q->busylock);
@@ -3942,10 +3928,12 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
local_bh_disable();
+ dev_xmit_recursion_inc();
HARD_TX_LOCK(dev, txq, smp_processor_id());
if (!netif_xmit_frozen_or_drv_stopped(txq))
ret = netdev_start_xmit(skb, dev, txq, false);
HARD_TX_UNLOCK(dev, txq);
+ dev_xmit_recursion_dec();
local_bh_enable();
@@ -3969,7 +3957,8 @@ EXPORT_SYMBOL(netdev_max_backlog);
int netdev_tstamp_prequeue __read_mostly = 1;
int netdev_budget __read_mostly = 300;
-unsigned int __read_mostly netdev_budget_usecs = 2000;
+/* Must be at least 2 jiffes to guarantee 1 jiffy timeout */
+unsigned int __read_mostly netdev_budget_usecs = 2 * USEC_PER_SEC / HZ;
int weight_p __read_mostly = 64; /* old backlog weight */
int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */
int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */
@@ -4298,6 +4287,7 @@ drop:
rps_unlock(sd);
local_irq_restore(flags);
+ preempt_check_resched_rt();
atomic_long_inc(&skb->dev->rx_dropped);
kfree_skb(skb);
@@ -4343,14 +4333,14 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
/* Reinjected packets coming from act_mirred or similar should
* not get XDP generic processing.
*/
- if (skb_cloned(skb) || skb_is_tc_redirected(skb))
+ if (skb_is_redirected(skb))
return XDP_PASS;
/* XDP packets must be linear and must have sufficient headroom
* of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
* native XDP provides, thus we need to do it here as well.
*/
- if (skb_is_nonlinear(skb) ||
+ if (skb_cloned(skb) || skb_is_nonlinear(skb) ||
skb_headroom(skb) < XDP_PACKET_HEADROOM) {
int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
int troom = skb->tail + skb->data_len - skb->end;
@@ -4512,7 +4502,7 @@ static int netif_rx_internal(struct sk_buff *skb)
struct rps_dev_flow voidflow, *rflow = &voidflow;
int cpu;
- preempt_disable();
+ migrate_disable();
rcu_read_lock();
cpu = get_rps_cpu(skb->dev, skb, &rflow);
@@ -4522,14 +4512,14 @@ static int netif_rx_internal(struct sk_buff *skb)
ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
rcu_read_unlock();
- preempt_enable();
+ migrate_enable();
} else
#endif
{
unsigned int qtail;
- ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
- put_cpu();
+ ret = enqueue_to_backlog(skb, get_cpu_light(), &qtail);
+ put_cpu_light();
}
return ret;
}
@@ -4568,11 +4558,9 @@ int netif_rx_ni(struct sk_buff *skb)
trace_netif_rx_ni_entry(skb);
- preempt_disable();
+ local_bh_disable();
err = netif_rx_internal(skb);
- if (local_softirq_pending())
- do_softirq();
- preempt_enable();
+ local_bh_enable();
trace_netif_rx_ni_exit(err);
return err;
@@ -4818,11 +4806,12 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev,
return 0;
}
-static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc,
+static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
struct packet_type **ppt_prev)
{
struct packet_type *ptype, *pt_prev;
rx_handler_func_t *rx_handler;
+ struct sk_buff *skb = *pskb;
struct net_device *orig_dev;
bool deliver_exact = false;
int ret = NET_RX_DROP;
@@ -4853,8 +4842,10 @@ another_round:
ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb);
preempt_enable();
- if (ret2 != XDP_PASS)
- return NET_RX_DROP;
+ if (ret2 != XDP_PASS) {
+ ret = NET_RX_DROP;
+ goto out;
+ }
skb_reset_mac_len(skb);
}
@@ -4894,7 +4885,7 @@ skip_taps:
goto out;
}
#endif
- skb_reset_tc(skb);
+ skb_reset_redirect(skb);
skip_classify:
if (pfmemalloc && !skb_pfmemalloc_protocol(skb))
goto drop;
@@ -5004,6 +4995,13 @@ drop:
}
out:
+ /* The invariant here is that if *ppt_prev is not NULL
+ * then skb should also be non-NULL.
+ *
+ * Apparently *ppt_prev assignment above holds this invariant due to
+ * skb dereferencing near it.
+ */
+ *pskb = skb;
return ret;
}
@@ -5013,7 +5011,7 @@ static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc)
struct packet_type *pt_prev = NULL;
int ret;
- ret = __netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+ ret = __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev);
if (pt_prev)
ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb,
skb->dev, pt_prev, orig_dev);
@@ -5091,7 +5089,7 @@ static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemallo
struct packet_type *pt_prev = NULL;
skb_list_del_init(skb);
- __netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+ __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev);
if (!pt_prev)
continue;
if (pt_curr != pt_prev || od_curr != orig_dev) {
@@ -5326,7 +5324,7 @@ static void flush_backlog(struct work_struct *work)
skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
if (skb->dev->reg_state == NETREG_UNREGISTERING) {
__skb_unlink(skb, &sd->input_pkt_queue);
- kfree_skb(skb);
+ __skb_queue_tail(&sd->tofree_queue, skb);
input_queue_head_incr(sd);
}
}
@@ -5336,11 +5334,14 @@ static void flush_backlog(struct work_struct *work)
skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
if (skb->dev->reg_state == NETREG_UNREGISTERING) {
__skb_unlink(skb, &sd->process_queue);
- kfree_skb(skb);
+ __skb_queue_tail(&sd->tofree_queue, skb);
input_queue_head_incr(sd);
}
}
+ if (!skb_queue_empty(&sd->tofree_queue))
+ raise_softirq_irqoff(NET_RX_SOFTIRQ);
local_bh_enable();
+
}
static void flush_all_backlogs(void)
@@ -5903,12 +5904,14 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd)
sd->rps_ipi_list = NULL;
local_irq_enable();
+ preempt_check_resched_rt();
/* Send pending IPI's to kick RPS processing on remote cpus. */
net_rps_send_ipi(remsd);
} else
#endif
local_irq_enable();
+ preempt_check_resched_rt();
}
static bool sd_has_rps_ipi_waiting(struct softnet_data *sd)
@@ -5938,7 +5941,9 @@ static int process_backlog(struct napi_struct *napi, int quota)
while (again) {
struct sk_buff *skb;
+ local_irq_disable();
while ((skb = __skb_dequeue(&sd->process_queue))) {
+ local_irq_enable();
rcu_read_lock();
__netif_receive_skb(skb);
rcu_read_unlock();
@@ -5946,9 +5951,9 @@ static int process_backlog(struct napi_struct *napi, int quota)
if (++work >= quota)
return work;
+ local_irq_disable();
}
- local_irq_disable();
rps_lock(sd);
if (skb_queue_empty(&sd->input_pkt_queue)) {
/*
@@ -5986,6 +5991,7 @@ void __napi_schedule(struct napi_struct *n)
local_irq_save(flags);
____napi_schedule(this_cpu_ptr(&softnet_data), n);
local_irq_restore(flags);
+ preempt_check_resched_rt();
}
EXPORT_SYMBOL(__napi_schedule);
@@ -6022,6 +6028,7 @@ bool napi_schedule_prep(struct napi_struct *n)
}
EXPORT_SYMBOL(napi_schedule_prep);
+#ifndef CONFIG_PREEMPT_RT_FULL
/**
* __napi_schedule_irqoff - schedule for receive
* @n: entry to schedule
@@ -6033,6 +6040,7 @@ void __napi_schedule_irqoff(struct napi_struct *n)
____napi_schedule(this_cpu_ptr(&softnet_data), n);
}
EXPORT_SYMBOL(__napi_schedule_irqoff);
+#endif
bool napi_complete_done(struct napi_struct *n, int work_done)
{
@@ -6412,13 +6420,21 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
unsigned long time_limit = jiffies +
usecs_to_jiffies(netdev_budget_usecs);
int budget = netdev_budget;
+ struct sk_buff_head tofree_q;
+ struct sk_buff *skb;
LIST_HEAD(list);
LIST_HEAD(repoll);
+ __skb_queue_head_init(&tofree_q);
+
local_irq_disable();
+ skb_queue_splice_init(&sd->tofree_queue, &tofree_q);
list_splice_init(&sd->poll_list, &list);
local_irq_enable();
+ while ((skb = __skb_dequeue(&tofree_q)))
+ kfree_skb(skb);
+
for (;;) {
struct napi_struct *n;
@@ -6616,6 +6632,21 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
}
EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
+static struct net_device *netdev_next_upper_dev(struct net_device *dev,
+ struct list_head **iter)
+{
+ 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;
+
+ return upper->dev;
+}
+
static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
struct list_head **iter)
{
@@ -6633,28 +6664,93 @@ static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
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;
+
+ 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);
+ 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;
+}
+
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;
@@ -6762,31 +6858,50 @@ int netdev_walk_all_lower_dev(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 struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
- struct list_head **iter)
+struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
+ struct list_head **iter)
{
struct netdev_adjacent *lower;
@@ -6798,29 +6913,95 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
return lower->dev;
}
+EXPORT_SYMBOL(netdev_next_lower_dev_rcu);
-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;
+
+ for (iter = &dev->adj_list.upper,
+ udev = netdev_next_upper_dev(dev, &iter);
+ udev;
+ udev = netdev_next_upper_dev(dev, &iter)) {
+ 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;
for (iter = &dev->adj_list.lower,
- ldev = netdev_next_lower_dev_rcu(dev, &iter);
+ ldev = netdev_next_lower_dev(dev, &iter);
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)) {
+ 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;
@@ -7077,6 +7258,9 @@ static int __netdev_upper_dev_link(struct net_device *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))
return -EEXIST;
@@ -7103,6 +7287,12 @@ static int __netdev_upper_dev_link(struct net_device *dev,
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:
@@ -7185,6 +7375,12 @@ void netdev_upper_dev_unlink(struct net_device *dev,
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);
@@ -7672,11 +7868,28 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu)
if (ops->ndo_change_mtu)
return ops->ndo_change_mtu(dev, new_mtu);
- dev->mtu = new_mtu;
+ /* Pairs with all the lockless reads of dev->mtu in the stack */
+ WRITE_ONCE(dev->mtu, new_mtu);
return 0;
}
EXPORT_SYMBOL(__dev_set_mtu);
+int dev_validate_mtu(struct net_device *dev, int new_mtu,
+ struct netlink_ext_ack *extack)
+{
+ /* MTU must be positive, and in range */
+ if (new_mtu < 0 || new_mtu < dev->min_mtu) {
+ NL_SET_ERR_MSG(extack, "mtu less than device minimum");
+ return -EINVAL;
+ }
+
+ if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) {
+ NL_SET_ERR_MSG(extack, "mtu greater than device maximum");
+ return -EINVAL;
+ }
+ return 0;
+}
+
/**
* dev_set_mtu_ext - Change maximum transfer unit
* @dev: device
@@ -7693,16 +7906,9 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu,
if (new_mtu == dev->mtu)
return 0;
- /* MTU must be positive, and in range */
- if (new_mtu < 0 || new_mtu < dev->min_mtu) {
- NL_SET_ERR_MSG(extack, "mtu less than device minimum");
- return -EINVAL;
- }
-
- if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) {
- NL_SET_ERR_MSG(extack, "mtu greater than device maximum");
- return -EINVAL;
- }
+ err = dev_validate_mtu(dev, new_mtu, extack);
+ if (err)
+ return err;
if (!netif_device_present(dev))
return -ENODEV;
@@ -8291,11 +8497,13 @@ static void netdev_sync_lower_features(struct net_device *upper,
netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n",
&feature, lower->name);
lower->wanted_features &= ~feature;
- netdev_update_features(lower);
+ __netdev_update_features(lower);
if (unlikely(lower->features & feature))
netdev_WARN(upper, "failed to disable %pNF on %s!\n",
&feature, lower->name);
+ else
+ netdev_features_change(lower);
}
}
}
@@ -8740,8 +8948,10 @@ int register_netdevice(struct net_device *dev)
goto err_uninit;
ret = netdev_register_kobject(dev);
- if (ret)
+ if (ret) {
+ dev->reg_state = NETREG_UNREGISTERED;
goto err_uninit;
+ }
dev->reg_state = NETREG_REGISTERED;
__netdev_update_features(dev);
@@ -8775,6 +8985,13 @@ int register_netdevice(struct net_device *dev)
rcu_barrier();
dev->reg_state = NETREG_UNREGISTERED;
+ /* We should put the kobject that hold in
+ * netdev_unregister_kobject(), otherwise
+ * the net device cannot be freed when
+ * driver calls free_netdev(), because the
+ * kobject is being hold.
+ */
+ kobject_put(&dev->dev.kobj);
}
/*
* Prevent userspace races by waiting until the network
@@ -9173,6 +9390,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
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);
@@ -9421,7 +9640,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
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);
@@ -9517,6 +9736,7 @@ static int dev_cpu_dead(unsigned int oldcpu)
raise_softirq_irqoff(NET_TX_SOFTIRQ);
local_irq_enable();
+ preempt_check_resched_rt();
#ifdef CONFIG_RPS
remsd = oldsd->rps_ipi_list;
@@ -9530,10 +9750,13 @@ static int dev_cpu_dead(unsigned int oldcpu)
netif_rx_ni(skb);
input_queue_head_incr(oldsd);
}
- while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) {
+ while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
netif_rx_ni(skb);
input_queue_head_incr(oldsd);
}
+ while ((skb = __skb_dequeue(&oldsd->tofree_queue))) {
+ kfree_skb(skb);
+ }
return 0;
}
@@ -9844,8 +10067,9 @@ static int __init net_dev_init(void)
INIT_WORK(flush, flush_backlog);
- skb_queue_head_init(&sd->input_pkt_queue);
- skb_queue_head_init(&sd->process_queue);
+ skb_queue_head_init_raw(&sd->input_pkt_queue);
+ skb_queue_head_init_raw(&sd->process_queue);
+ skb_queue_head_init_raw(&sd->tofree_queue);
#ifdef CONFIG_XFRM_OFFLOAD
skb_queue_head_init(&sd->xfrm_backlog);
#endif
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-04-18 21:13:38 +0000