Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 7c40ae0..ffbc7ed 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -62,6 +62,7 @@
#include <net/rtnetlink.h>
#include <net/sock.h>
#include <net/xdp.h>
+#include <net/ip_tunnels.h>
#include <linux/seq_file.h>
#include <linux/uio.h>
#include <linux/skb_array.h>
@@ -83,35 +84,6 @@
static void tun_default_link_ksettings(struct net_device *dev,
struct ethtool_link_ksettings *cmd);
-/* Uncomment to enable debugging */
-/* #define TUN_DEBUG 1 */
-
-#ifdef TUN_DEBUG
-static int debug;
-
-#define tun_debug(level, tun, fmt, args...) \
-do { \
- if (tun->debug) \
- netdev_printk(level, tun->dev, fmt, ##args); \
-} while (0)
-#define DBG1(level, fmt, args...) \
-do { \
- if (debug == 2) \
- printk(level fmt, ##args); \
-} while (0)
-#else
-#define tun_debug(level, tun, fmt, args...) \
-do { \
- if (0) \
- netdev_printk(level, tun->dev, fmt, ##args); \
-} while (0)
-#define DBG1(level, fmt, args...) \
-do { \
- if (0) \
- printk(level fmt, ##args); \
-} while (0)
-#endif
-
#define TUN_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD)
/* TUN device flags */
@@ -144,10 +116,10 @@
#define TUN_FLOW_EXPIRE (3 * HZ)
struct tun_pcpu_stats {
- u64 rx_packets;
- u64 rx_bytes;
- u64 tx_packets;
- u64 tx_bytes;
+ u64_stats_t rx_packets;
+ u64_stats_t rx_bytes;
+ u64_stats_t tx_packets;
+ u64_stats_t tx_bytes;
struct u64_stats_sync syncp;
u32 rx_dropped;
u32 tx_dropped;
@@ -233,9 +205,7 @@
struct sock_fprog fprog;
/* protected by rtnl lock */
bool filter_attached;
-#ifdef TUN_DEBUG
- int debug;
-#endif
+ u32 msg_enable;
spinlock_t lock;
struct hlist_head flows[TUN_NUM_FLOW_ENTRIES];
struct timer_list flow_gc_timer;
@@ -257,24 +227,6 @@
__be16 h_vlan_TCI;
};
-bool tun_is_xdp_frame(void *ptr)
-{
- return (unsigned long)ptr & TUN_XDP_FLAG;
-}
-EXPORT_SYMBOL(tun_is_xdp_frame);
-
-void *tun_xdp_to_ptr(void *ptr)
-{
- return (void *)((unsigned long)ptr | TUN_XDP_FLAG);
-}
-EXPORT_SYMBOL(tun_xdp_to_ptr);
-
-void *tun_ptr_to_xdp(void *ptr)
-{
- return (void *)((unsigned long)ptr & ~TUN_XDP_FLAG);
-}
-EXPORT_SYMBOL(tun_ptr_to_xdp);
-
static int tun_napi_receive(struct napi_struct *napi, int budget)
{
struct tun_file *tfile = container_of(napi, struct tun_file, napi);
@@ -431,8 +383,9 @@
struct tun_flow_entry *e = kmalloc(sizeof(*e), GFP_ATOMIC);
if (e) {
- tun_debug(KERN_INFO, tun, "create flow: hash %u index %u\n",
- rxhash, queue_index);
+ netif_info(tun, tx_queued, tun->dev,
+ "create flow: hash %u index %u\n",
+ rxhash, queue_index);
e->updated = jiffies;
e->rxhash = rxhash;
e->rps_rxhash = 0;
@@ -446,8 +399,8 @@
static void tun_flow_delete(struct tun_struct *tun, struct tun_flow_entry *e)
{
- tun_debug(KERN_INFO, tun, "delete flow: hash %u index %u\n",
- e->rxhash, e->queue_index);
+ netif_info(tun, tx_queued, tun->dev, "delete flow: hash %u index %u\n",
+ e->rxhash, e->queue_index);
hlist_del_rcu(&e->hash_link);
kfree_rcu(e, rcu);
--tun->flow_count;
@@ -493,8 +446,6 @@
unsigned long count = 0;
int i;
- tun_debug(KERN_INFO, tun, "tun_flow_cleanup\n");
-
spin_lock(&tun->lock);
for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) {
struct tun_flow_entry *e;
@@ -554,8 +505,7 @@
rcu_read_unlock();
}
-/**
- * Save the hash received in the stack receive path and update the
+/* Save the hash received in the stack receive path and update the
* flow_hash table accordingly.
*/
static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash)
@@ -1071,6 +1021,7 @@
{
struct tun_struct *tun = netdev_priv(dev);
int txq = skb->queue_mapping;
+ struct netdev_queue *queue;
struct tun_file *tfile;
int len = skb->len;
@@ -1084,9 +1035,7 @@
if (!rcu_dereference(tun->steering_prog))
tun_automq_xmit(tun, skb);
- tun_debug(KERN_INFO, tun, "tun_net_xmit %d\n", skb->len);
-
- BUG_ON(!tfile);
+ netif_info(tun, tx_queued, tun->dev, "%s %d\n", __func__, skb->len);
/* Drop if the filter does not like it.
* This is a noop if the filter is disabled.
@@ -1117,6 +1066,10 @@
if (ptr_ring_produce(&tfile->tx_ring, skb))
goto drop;
+ /* NETIF_F_LLTX requires to do our own update of trans_start */
+ queue = netdev_get_tx_queue(dev, txq);
+ queue->trans_start = jiffies;
+
/* Notify and wake up reader process */
if (tfile->flags & TUN_FASYNC)
kill_fasync(&tfile->fasync, SIGIO, POLL_IN);
@@ -1175,10 +1128,10 @@
p = per_cpu_ptr(tun->pcpu_stats, i);
do {
start = u64_stats_fetch_begin(&p->syncp);
- rxpackets = p->rx_packets;
- rxbytes = p->rx_bytes;
- txpackets = p->tx_packets;
- txbytes = p->tx_bytes;
+ rxpackets = u64_stats_read(&p->rx_packets);
+ rxbytes = u64_stats_read(&p->rx_bytes);
+ txpackets = u64_stats_read(&p->tx_packets);
+ txbytes = u64_stats_read(&p->tx_bytes);
} while (u64_stats_fetch_retry(&p->syncp, start));
stats->rx_packets += rxpackets;
@@ -1226,26 +1179,11 @@
return 0;
}
-static u32 tun_xdp_query(struct net_device *dev)
-{
- struct tun_struct *tun = netdev_priv(dev);
- const struct bpf_prog *xdp_prog;
-
- xdp_prog = rtnl_dereference(tun->xdp_prog);
- if (xdp_prog)
- return xdp_prog->aux->id;
-
- return 0;
-}
-
static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp)
{
switch (xdp->command) {
case XDP_SETUP_PROG:
return tun_xdp_set(dev, xdp->prog, xdp->extack);
- case XDP_QUERY_PROG:
- xdp->prog_id = tun_xdp_query(dev);
- return 0;
default:
return -EINVAL;
}
@@ -1338,7 +1276,7 @@
static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp)
{
- struct xdp_frame *frame = convert_to_xdp_frame(xdp);
+ struct xdp_frame *frame = xdp_convert_buff_to_frame(xdp);
if (unlikely(!frame))
return -EOVERFLOW;
@@ -1394,6 +1332,7 @@
switch (tun->flags & TUN_TYPE_MASK) {
case IFF_TUN:
dev->netdev_ops = &tun_netdev_ops;
+ dev->header_ops = &ip_tunnel_header_ops;
/* Point-to-Point TUN Device */
dev->hard_header_len = 0;
@@ -1443,8 +1382,6 @@
sk = tfile->socket.sk;
- tun_debug(KERN_INFO, tun, "tun_chr_poll\n");
-
poll_wait(file, sk_sleep(sk), wait);
if (!ptr_ring_empty(&tfile->tx_ring))
@@ -1648,10 +1585,10 @@
break;
default:
bpf_warn_invalid_xdp_action(act);
- /* fall through */
+ fallthrough;
case XDP_ABORTED:
trace_xdp_exception(tun->dev, xdp_prog, act);
- /* fall through */
+ fallthrough;
case XDP_DROP:
this_cpu_inc(tun->pcpu_stats->rx_dropped);
break;
@@ -1716,6 +1653,7 @@
xdp_set_data_meta_invalid(&xdp);
xdp.data_end = xdp.data + len;
xdp.rxq = &tfile->xdp_rxq;
+ xdp.frame_sz = buflen;
act = bpf_prog_run_xdp(xdp_prog, &xdp);
if (act == XDP_REDIRECT || act == XDP_TX) {
@@ -1730,7 +1668,7 @@
}
if (err == XDP_REDIRECT)
- xdp_do_flush_map();
+ xdp_do_flush();
if (err != XDP_PASS)
goto out;
@@ -2019,8 +1957,8 @@
stats = get_cpu_ptr(tun->pcpu_stats);
u64_stats_update_begin(&stats->syncp);
- stats->rx_packets++;
- stats->rx_bytes += len;
+ u64_stats_inc(&stats->rx_packets);
+ u64_stats_add(&stats->rx_bytes, len);
u64_stats_update_end(&stats->syncp);
put_cpu_ptr(stats);
@@ -2076,8 +2014,8 @@
stats = get_cpu_ptr(tun->pcpu_stats);
u64_stats_update_begin(&stats->syncp);
- stats->tx_packets++;
- stats->tx_bytes += ret;
+ u64_stats_inc(&stats->tx_packets);
+ u64_stats_add(&stats->tx_bytes, ret);
u64_stats_update_end(&stats->syncp);
put_cpu_ptr(tun->pcpu_stats);
@@ -2171,8 +2109,8 @@
/* caller is in process context, */
stats = get_cpu_ptr(tun->pcpu_stats);
u64_stats_update_begin(&stats->syncp);
- stats->tx_packets++;
- stats->tx_bytes += skb->len + vlan_hlen;
+ u64_stats_inc(&stats->tx_packets);
+ u64_stats_add(&stats->tx_bytes, skb->len + vlan_hlen);
u64_stats_update_end(&stats->syncp);
put_cpu_ptr(tun->pcpu_stats);
@@ -2227,8 +2165,6 @@
ssize_t ret;
int err;
- tun_debug(KERN_INFO, tun, "tun_do_read\n");
-
if (!iov_iter_count(to)) {
tun_ptr_free(ptr);
return 0;
@@ -2319,7 +2255,13 @@
struct tun_struct *tun = netdev_priv(dev);
BUG_ON(!(list_empty(&tun->disabled)));
+
free_percpu(tun->pcpu_stats);
+ /* We clear pcpu_stats so that tun_set_iff() can tell if
+ * tun_free_netdev() has been called from register_netdevice().
+ */
+ tun->pcpu_stats = NULL;
+
tun_flow_uninit(tun);
security_tun_dev_free_security(tun->security);
__tun_set_ebpf(tun, &tun->steering_prog, NULL);
@@ -2466,6 +2408,7 @@
}
xdp_set_data_meta_invalid(xdp);
xdp->rxq = &tfile->xdp_rxq;
+ xdp->frame_sz = buflen;
act = bpf_prog_run_xdp(xdp_prog, xdp);
err = tun_xdp_act(tun, xdp_prog, xdp, act);
@@ -2477,7 +2420,7 @@
switch (err) {
case XDP_REDIRECT:
*flush = true;
- /* fall through */
+ fallthrough;
case XDP_TX:
return 0;
case XDP_PASS:
@@ -2534,8 +2477,8 @@
*/
stats = this_cpu_ptr(tun->pcpu_stats);
u64_stats_update_begin(&stats->syncp);
- stats->rx_packets++;
- stats->rx_bytes += datasize;
+ u64_stats_inc(&stats->rx_packets);
+ u64_stats_add(&stats->rx_bytes, datasize);
u64_stats_update_end(&stats->syncp);
if (rxhash)
@@ -2572,7 +2515,7 @@
}
if (flush)
- xdp_do_flush_map();
+ xdp_do_flush();
rcu_read_unlock();
local_bh_enable();
@@ -2811,9 +2754,6 @@
if (!dev)
return -ENOMEM;
- err = dev_get_valid_name(net, dev, name);
- if (err < 0)
- goto err_free_dev;
dev_net_set(dev, net);
dev->rtnl_link_ops = &tun_link_ops;
@@ -2875,8 +2815,6 @@
netif_carrier_on(tun->dev);
- tun_debug(KERN_INFO, tun, "tun_set_iff\n");
-
/* Make sure persistent devices do not get stuck in
* xoff state.
*/
@@ -2888,8 +2826,12 @@
err_detach:
tun_detach_all(dev);
- /* register_netdevice() already called tun_free_netdev() */
- goto err_free_dev;
+ /* We are here because register_netdevice() has failed.
+ * If register_netdevice() already called tun_free_netdev()
+ * while dealing with the error, tun->pcpu_stats has been cleared.
+ */
+ if (!tun->pcpu_stats)
+ goto err_free_dev;
err_free_flow:
tun_flow_uninit(tun);
@@ -2903,8 +2845,6 @@
static void tun_get_iff(struct tun_struct *tun, struct ifreq *ifr)
{
- tun_debug(KERN_INFO, tun, "tun_get_iff\n");
-
strcpy(ifr->ifr_name, tun->dev->name);
ifr->ifr_flags = tun_flags(tun);
@@ -3031,7 +2971,7 @@
return ret;
}
-static int tun_set_ebpf(struct tun_struct *tun, struct tun_prog **prog_p,
+static int tun_set_ebpf(struct tun_struct *tun, struct tun_prog __rcu **prog_p,
void __user *data)
{
struct bpf_prog *prog;
@@ -3167,7 +3107,7 @@
if (!tun)
goto unlock;
- tun_debug(KERN_INFO, tun, "tun_chr_ioctl cmd %u\n", cmd);
+ netif_info(tun, drv, tun->dev, "tun_chr_ioctl cmd %u\n", cmd);
net = dev_net(tun->dev);
ret = 0;
@@ -3188,8 +3128,8 @@
/* Disable/Enable checksum */
/* [unimplemented] */
- tun_debug(KERN_INFO, tun, "ignored: set checksum %s\n",
- arg ? "disabled" : "enabled");
+ netif_info(tun, drv, tun->dev, "ignored: set checksum %s\n",
+ arg ? "disabled" : "enabled");
break;
case TUNSETPERSIST:
@@ -3207,8 +3147,8 @@
do_notify = true;
}
- tun_debug(KERN_INFO, tun, "persist %s\n",
- arg ? "enabled" : "disabled");
+ netif_info(tun, drv, tun->dev, "persist %s\n",
+ arg ? "enabled" : "disabled");
break;
case TUNSETOWNER:
@@ -3220,8 +3160,8 @@
}
tun->owner = owner;
do_notify = true;
- tun_debug(KERN_INFO, tun, "owner set to %u\n",
- from_kuid(&init_user_ns, tun->owner));
+ netif_info(tun, drv, tun->dev, "owner set to %u\n",
+ from_kuid(&init_user_ns, tun->owner));
break;
case TUNSETGROUP:
@@ -3233,30 +3173,29 @@
}
tun->group = group;
do_notify = true;
- tun_debug(KERN_INFO, tun, "group set to %u\n",
- from_kgid(&init_user_ns, tun->group));
+ netif_info(tun, drv, tun->dev, "group set to %u\n",
+ from_kgid(&init_user_ns, tun->group));
break;
case TUNSETLINK:
/* Only allow setting the type when the interface is down */
if (tun->dev->flags & IFF_UP) {
- tun_debug(KERN_INFO, tun,
- "Linktype set failed because interface is up\n");
+ netif_info(tun, drv, tun->dev,
+ "Linktype set failed because interface is up\n");
ret = -EBUSY;
} else {
tun->dev->type = (int) arg;
tun->dev->addr_len = tun_get_addr_len(tun->dev->type);
- tun_debug(KERN_INFO, tun, "linktype set to %d\n",
- tun->dev->type);
+ netif_info(tun, drv, tun->dev, "linktype set to %d\n",
+ tun->dev->type);
ret = 0;
}
break;
-#ifdef TUN_DEBUG
case TUNSETDEBUG:
- tun->debug = arg;
+ tun->msg_enable = (u32)arg;
break;
-#endif
+
case TUNSETOFFLOAD:
ret = set_offload(tun, arg);
break;
@@ -3271,7 +3210,6 @@
case SIOCGIFHWADDR:
/* Get hw address */
- memcpy(ifr.ifr_hwaddr.sa_data, tun->dev->dev_addr, ETH_ALEN);
dev_get_mac_address(&ifr.ifr_hwaddr, net, tun->dev->name);
if (copy_to_user(argp, &ifr, ifreq_len))
ret = -EFAULT;
@@ -3279,9 +3217,6 @@
case SIOCSIFHWADDR:
/* Set hw address */
- tun_debug(KERN_DEBUG, tun, "set hw address: %pM\n",
- ifr.ifr_hwaddr.sa_data);
-
ret = dev_set_mac_address_user(tun->dev, &ifr.ifr_hwaddr, NULL);
break;
@@ -3476,8 +3411,6 @@
struct net *net = current->nsproxy->net_ns;
struct tun_file *tfile;
- DBG1(KERN_INFO, "tunX: tun_chr_open\n");
-
tfile = (struct tun_file *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL,
&tun_proto, 0);
if (!tfile)
@@ -3617,20 +3550,16 @@
static u32 tun_get_msglevel(struct net_device *dev)
{
-#ifdef TUN_DEBUG
struct tun_struct *tun = netdev_priv(dev);
- return tun->debug;
-#else
- return -EOPNOTSUPP;
-#endif
+
+ return tun->msg_enable;
}
static void tun_set_msglevel(struct net_device *dev, u32 value)
{
-#ifdef TUN_DEBUG
struct tun_struct *tun = netdev_priv(dev);
- tun->debug = value;
-#endif
+
+ tun->msg_enable = value;
}
static int tun_get_coalesce(struct net_device *dev,
@@ -3657,6 +3586,7 @@
}
static const struct ethtool_ops tun_ethtool_ops = {
+ .supported_coalesce_params = ETHTOOL_COALESCE_RX_MAX_FRAMES,
.get_drvinfo = tun_get_drvinfo,
.get_msglevel = tun_get_msglevel,
.set_msglevel = tun_set_msglevel,