summaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/Makefile1
-rw-r--r--net/core/dev.c419
-rw-r--r--net/core/dev.h7
-rw-r--r--net/core/drop_monitor.c20
-rw-r--r--net/core/dst.c6
-rw-r--r--net/core/dst_cache.c4
-rw-r--r--net/core/filter.c183
-rw-r--r--net/core/gro.c40
-rw-r--r--net/core/gro_cells.c3
-rw-r--r--net/core/gso.c4
-rw-r--r--net/core/hotdata.c22
-rw-r--r--net/core/link_watch.c9
-rw-r--r--net/core/net-procfs.c55
-rw-r--r--net/core/net-sysfs.c133
-rw-r--r--net/core/net_namespace.c42
-rw-r--r--net/core/netdev-genl-gen.c12
-rw-r--r--net/core/netdev-genl-gen.h2
-rw-r--r--net/core/netdev-genl.c230
-rw-r--r--net/core/netpoll.c2
-rw-r--r--net/core/page_pool.c64
-rw-r--r--net/core/rtnetlink.c174
-rw-r--r--net/core/scm.c5
-rw-r--r--net/core/skbuff.c188
-rw-r--r--net/core/sock.c84
-rw-r--r--net/core/sock_diag.c120
-rw-r--r--net/core/sock_map.c16
-rw-r--r--net/core/sysctl_net_core.c25
-rw-r--r--net/core/xdp.c15
28 files changed, 1337 insertions, 548 deletions
diff --git a/net/core/Makefile b/net/core/Makefile
index 821aec06ab..6e6548011f 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -18,6 +18,7 @@ obj-y += dev.o dev_addr_lists.o dst.o netevent.o \
obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o
obj-y += net-sysfs.o
+obj-y += hotdata.o
obj-$(CONFIG_PAGE_POOL) += page_pool.o page_pool_user.o
obj-$(CONFIG_PROC_FS) += net-procfs.o
obj-$(CONFIG_NET_PKTGEN) += pktgen.o
diff --git a/net/core/dev.c b/net/core/dev.c
index a32811aebd..e8fb4ef8a8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -153,41 +153,21 @@
#include <linux/prandom.h>
#include <linux/once_lite.h>
#include <net/netdev_rx_queue.h>
+#include <net/page_pool/types.h>
+#include <net/page_pool/helpers.h>
+#include <net/rps.h>
#include "dev.h"
#include "net-sysfs.h"
static DEFINE_SPINLOCK(ptype_lock);
struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
-struct list_head ptype_all __read_mostly; /* Taps */
static int netif_rx_internal(struct sk_buff *skb);
static int call_netdevice_notifiers_extack(unsigned long val,
struct net_device *dev,
struct netlink_ext_ack *extack);
-/*
- * The @dev_base_head list is protected by @dev_base_lock and the rtnl
- * semaphore.
- *
- * Pure readers hold dev_base_lock for reading, or rcu_read_lock()
- *
- * Writers must hold the rtnl semaphore while they loop through the
- * dev_base_head list, and hold dev_base_lock for writing when they do the
- * actual updates. This allows pure readers to access the list even
- * while a writer is preparing to update it.
- *
- * To put it another way, dev_base_lock is held for writing only to
- * protect against pure readers; the rtnl semaphore provides the
- * protection against other writers.
- *
- * See, for example usages, register_netdevice() and
- * unregister_netdevice(), which must be called with the rtnl
- * semaphore held.
- */
-DEFINE_RWLOCK(dev_base_lock);
-EXPORT_SYMBOL(dev_base_lock);
-
static DEFINE_MUTEX(ifalias_mutex);
/* protects napi_hash addition/deletion and napi_gen_id */
@@ -200,8 +180,9 @@ static DECLARE_RWSEM(devnet_rename_sem);
static inline void dev_base_seq_inc(struct net *net)
{
- while (++net->dev_base_seq == 0)
- ;
+ unsigned int val = net->dev_base_seq + 1;
+
+ WRITE_ONCE(net->dev_base_seq, val ?: 1);
}
static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
@@ -341,13 +322,22 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name)
return 0;
}
-static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node)
+static void netdev_name_node_alt_free(struct rcu_head *head)
{
- list_del(&name_node->list);
+ struct netdev_name_node *name_node =
+ container_of(head, struct netdev_name_node, rcu);
+
kfree(name_node->name);
netdev_name_node_free(name_node);
}
+static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node)
+{
+ netdev_name_node_del(name_node);
+ list_del(&name_node->list);
+ call_rcu(&name_node->rcu, netdev_name_node_alt_free);
+}
+
int netdev_name_node_alt_destroy(struct net_device *dev, const char *name)
{
struct netdev_name_node *name_node;
@@ -362,10 +352,7 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name)
if (name_node == dev->name_node || name_node->dev != dev)
return -EINVAL;
- netdev_name_node_del(name_node);
- synchronize_rcu();
__netdev_name_node_alt_destroy(name_node);
-
return 0;
}
@@ -373,8 +360,10 @@ 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);
+ list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list) {
+ list_del(&name_node->list);
+ netdev_name_node_alt_free(&name_node->rcu);
+ }
}
/* Device list insertion */
@@ -385,12 +374,10 @@ static void list_netdevice(struct net_device *dev)
ASSERT_RTNL();
- write_lock(&dev_base_lock);
list_add_tail_rcu(&dev->dev_list, &net->dev_base_head);
netdev_name_node_add(net, dev->name_node);
hlist_add_head_rcu(&dev->index_hlist,
dev_index_hash(net, dev->ifindex));
- write_unlock(&dev_base_lock);
netdev_for_each_altname(dev, name_node)
netdev_name_node_add(net, name_node);
@@ -404,7 +391,7 @@ static void list_netdevice(struct net_device *dev)
/* Device list removal
* caller must respect a RCU grace period before freeing/reusing dev
*/
-static void unlist_netdevice(struct net_device *dev, bool lock)
+static void unlist_netdevice(struct net_device *dev)
{
struct netdev_name_node *name_node;
struct net *net = dev_net(dev);
@@ -417,13 +404,9 @@ static void unlist_netdevice(struct net_device *dev, bool lock)
netdev_name_node_del(name_node);
/* Unlink dev from the device chain */
- if (lock)
- write_lock(&dev_base_lock);
list_del_rcu(&dev->dev_list);
netdev_name_node_del(dev->name_node);
hlist_del_rcu(&dev->index_hlist);
- if (lock)
- write_unlock(&dev_base_lock);
dev_base_seq_inc(dev_net(dev));
}
@@ -442,6 +425,12 @@ static RAW_NOTIFIER_HEAD(netdev_chain);
DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
EXPORT_PER_CPU_SYMBOL(softnet_data);
+/* Page_pool has a lockless array/stack to alloc/recycle pages.
+ * PP consumers must pay attention to run APIs in the appropriate context
+ * (e.g. NAPI context).
+ */
+static DEFINE_PER_CPU(struct page_pool *, system_page_pool);
+
#ifdef CONFIG_LOCKDEP
/*
* register_netdevice() inits txq->_xmit_lock and sets lockdep class
@@ -551,7 +540,7 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
static inline struct list_head *ptype_head(const struct packet_type *pt)
{
if (pt->type == htons(ETH_P_ALL))
- return pt->dev ? &pt->dev->ptype_all : &ptype_all;
+ return pt->dev ? &pt->dev->ptype_all : &net_hotdata.ptype_all;
else
return pt->dev ? &pt->dev->ptype_specific :
&ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK];
@@ -653,7 +642,7 @@ int dev_get_iflink(const struct net_device *dev)
if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink)
return dev->netdev_ops->ndo_get_iflink(dev);
- return dev->ifindex;
+ return READ_ONCE(dev->ifindex);
}
EXPORT_SYMBOL(dev_get_iflink);
@@ -738,9 +727,9 @@ EXPORT_SYMBOL_GPL(dev_fill_forward_path);
* @net: the applicable net namespace
* @name: name to find
*
- * Find an interface by name. Must be called under RTNL semaphore
- * or @dev_base_lock. If the name is found a pointer to the device
- * is returned. If the name is not found then %NULL is returned. The
+ * Find an interface by name. Must be called under RTNL semaphore.
+ * If the name is found a pointer to the device is returned.
+ * If the name is not found then %NULL is returned. The
* reference counters are not incremented so the caller must be
* careful with locks.
*/
@@ -821,8 +810,7 @@ EXPORT_SYMBOL(netdev_get_by_name);
* Search for an interface by index. Returns %NULL if the device
* is not found or a pointer to the device. The device has not
* had its reference counter increased so the caller must be careful
- * about locking. The caller must hold either the RTNL semaphore
- * or @dev_base_lock.
+ * about locking. The caller must hold the RTNL semaphore.
*/
struct net_device *__dev_get_by_index(struct net *net, int ifindex)
@@ -1212,13 +1200,13 @@ int dev_change_name(struct net_device *dev, const char *newname)
dev->flags & IFF_UP ? " (while UP)" : "");
old_assign_type = dev->name_assign_type;
- dev->name_assign_type = NET_NAME_RENAMED;
+ WRITE_ONCE(dev->name_assign_type, NET_NAME_RENAMED);
rollback:
ret = device_rename(&dev->dev, dev->name);
if (ret) {
memcpy(dev->name, oldname, IFNAMSIZ);
- dev->name_assign_type = old_assign_type;
+ WRITE_ONCE(dev->name_assign_type, old_assign_type);
up_write(&devnet_rename_sem);
return ret;
}
@@ -1227,15 +1215,11 @@ rollback:
netdev_adjacent_rename_links(dev, oldname);
- write_lock(&dev_base_lock);
netdev_name_node_del(dev->name_node);
- write_unlock(&dev_base_lock);
- synchronize_rcu();
+ synchronize_net();
- write_lock(&dev_base_lock);
netdev_name_node_add(net, dev->name_node);
- write_unlock(&dev_base_lock);
ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev);
ret = notifier_to_errno(ret);
@@ -1247,7 +1231,7 @@ rollback:
down_write(&devnet_rename_sem);
memcpy(dev->name, oldname, IFNAMSIZ);
memcpy(oldname, newname, IFNAMSIZ);
- dev->name_assign_type = old_assign_type;
+ WRITE_ONCE(dev->name_assign_type, old_assign_type);
old_assign_type = NET_NAME_RENAMED;
goto rollback;
} else {
@@ -2242,7 +2226,8 @@ static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb)
*/
bool dev_nit_active(struct net_device *dev)
{
- return !list_empty(&ptype_all) || !list_empty(&dev->ptype_all);
+ return !list_empty(&net_hotdata.ptype_all) ||
+ !list_empty(&dev->ptype_all);
}
EXPORT_SYMBOL_GPL(dev_nit_active);
@@ -2253,10 +2238,9 @@ EXPORT_SYMBOL_GPL(dev_nit_active);
void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
{
- struct packet_type *ptype;
+ struct list_head *ptype_list = &net_hotdata.ptype_all;
+ struct packet_type *ptype, *pt_prev = NULL;
struct sk_buff *skb2 = NULL;
- struct packet_type *pt_prev = NULL;
- struct list_head *ptype_list = &ptype_all;
rcu_read_lock();
again:
@@ -2302,7 +2286,7 @@ again:
pt_prev = ptype;
}
- if (ptype_list == &ptype_all) {
+ if (ptype_list == &net_hotdata.ptype_all) {
ptype_list = &dev->ptype_all;
goto again;
}
@@ -4427,19 +4411,10 @@ EXPORT_SYMBOL(__dev_direct_xmit);
* Receiver routines
*************************************************************************/
-int netdev_max_backlog __read_mostly = 1000;
-EXPORT_SYMBOL(netdev_max_backlog);
-
-int netdev_tstamp_prequeue __read_mostly = 1;
unsigned int sysctl_skb_defer_max __read_mostly = 64;
-int netdev_budget __read_mostly = 300;
-/* 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 */
-int dev_rx_weight __read_mostly = 64;
-int dev_tx_weight __read_mostly = 64;
/* Called with irq disabled */
static inline void ____napi_schedule(struct softnet_data *sd,
@@ -4481,12 +4456,6 @@ static inline void ____napi_schedule(struct softnet_data *sd,
#ifdef CONFIG_RPS
-/* One global table that all flow-based protocols share. */
-struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly;
-EXPORT_SYMBOL(rps_sock_flow_table);
-u32 rps_cpu_mask __read_mostly;
-EXPORT_SYMBOL(rps_cpu_mask);
-
struct static_key_false rps_needed __read_mostly;
EXPORT_SYMBOL(rps_needed);
struct static_key_false rfs_needed __read_mostly;
@@ -4578,7 +4547,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
if (!hash)
goto done;
- sock_flow_table = rcu_dereference(rps_sock_flow_table);
+ sock_flow_table = rcu_dereference(net_hotdata.rps_sock_flow_table);
if (flow_table && sock_flow_table) {
struct rps_dev_flow *rflow;
u32 next_cpu;
@@ -4588,10 +4557,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
* This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow().
*/
ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]);
- if ((ident ^ hash) & ~rps_cpu_mask)
+ if ((ident ^ hash) & ~net_hotdata.rps_cpu_mask)
goto try_rps;
- next_cpu = ident & rps_cpu_mask;
+ next_cpu = ident & net_hotdata.rps_cpu_mask;
/* OK, now we know there is a match,
* we can look at the local (per receive queue) flow table
@@ -4740,7 +4709,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
struct softnet_data *sd;
unsigned int old_flow, new_flow;
- if (qlen < (READ_ONCE(netdev_max_backlog) >> 1))
+ if (qlen < (READ_ONCE(net_hotdata.max_backlog) >> 1))
return false;
sd = this_cpu_ptr(&softnet_data);
@@ -4788,7 +4757,8 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
if (!netif_running(skb->dev))
goto drop;
qlen = skb_queue_len(&sd->input_pkt_queue);
- if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) {
+ if (qlen <= READ_ONCE(net_hotdata.max_backlog) &&
+ !skb_flow_limit(skb, qlen)) {
if (qlen) {
enqueue:
__skb_queue_tail(&sd->input_pkt_queue, skb);
@@ -4864,6 +4834,12 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
xdp_init_buff(xdp, frame_sz, &rxqueue->xdp_rxq);
xdp_prepare_buff(xdp, hard_start, skb_headroom(skb) - mac_len,
skb_headlen(skb) + mac_len, true);
+ if (skb_is_nonlinear(skb)) {
+ skb_shinfo(skb)->xdp_frags_size = skb->data_len;
+ xdp_buff_set_frags_flag(xdp);
+ } else {
+ xdp_buff_clear_frags_flag(xdp);
+ }
orig_data_end = xdp->data_end;
orig_data = xdp->data;
@@ -4893,6 +4869,14 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
skb->len += off; /* positive on grow, negative on shrink */
}
+ /* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers
+ * (e.g. bpf_xdp_adjust_tail), we need to update data_len here.
+ */
+ if (xdp_buff_has_frags(xdp))
+ skb->data_len = skb_shinfo(skb)->xdp_frags_size;
+ else
+ skb->data_len = 0;
+
/* check if XDP changed eth hdr such SKB needs update */
eth = (struct ethhdr *)xdp->data;
if ((orig_eth_type != eth->h_proto) ||
@@ -4926,11 +4910,35 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
return act;
}
-static u32 netif_receive_generic_xdp(struct sk_buff *skb,
+static int
+netif_skb_check_for_xdp(struct sk_buff **pskb, struct bpf_prog *prog)
+{
+ struct sk_buff *skb = *pskb;
+ int err, hroom, troom;
+
+ if (!skb_cow_data_for_xdp(this_cpu_read(system_page_pool), pskb, prog))
+ return 0;
+
+ /* In case we have to go down the path and also linearize,
+ * then lets do the pskb_expand_head() work just once here.
+ */
+ hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
+ troom = skb->tail + skb->data_len - skb->end;
+ err = pskb_expand_head(skb,
+ hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
+ troom > 0 ? troom + 128 : 0, GFP_ATOMIC);
+ if (err)
+ return err;
+
+ return skb_linearize(skb);
+}
+
+static u32 netif_receive_generic_xdp(struct sk_buff **pskb,
struct xdp_buff *xdp,
struct bpf_prog *xdp_prog)
{
- u32 act = XDP_DROP;
+ struct sk_buff *skb = *pskb;
+ u32 mac_len, act = XDP_DROP;
/* Reinjected packets coming from act_mirred or similar should
* not get XDP generic processing.
@@ -4938,41 +4946,36 @@ static u32 netif_receive_generic_xdp(struct sk_buff *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.
+ /* XDP packets 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.
*/
+ mac_len = skb->data - skb_mac_header(skb);
+ __skb_push(skb, mac_len);
+
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;
-
- /* In case we have to go down the path and also linearize,
- * then lets do the pskb_expand_head() work just once here.
- */
- if (pskb_expand_head(skb,
- hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
- troom > 0 ? troom + 128 : 0, GFP_ATOMIC))
- goto do_drop;
- if (skb_linearize(skb))
+ if (netif_skb_check_for_xdp(pskb, xdp_prog))
goto do_drop;
}
- act = bpf_prog_run_generic_xdp(skb, xdp, xdp_prog);
+ __skb_pull(*pskb, mac_len);
+
+ act = bpf_prog_run_generic_xdp(*pskb, xdp, xdp_prog);
switch (act) {
case XDP_REDIRECT:
case XDP_TX:
case XDP_PASS:
break;
default:
- bpf_warn_invalid_xdp_action(skb->dev, xdp_prog, act);
+ bpf_warn_invalid_xdp_action((*pskb)->dev, xdp_prog, act);
fallthrough;
case XDP_ABORTED:
- trace_xdp_exception(skb->dev, xdp_prog, act);
+ trace_xdp_exception((*pskb)->dev, xdp_prog, act);
fallthrough;
case XDP_DROP:
do_drop:
- kfree_skb(skb);
+ kfree_skb(*pskb);
break;
}
@@ -5010,24 +5013,24 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog)
static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key);
-int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb)
+int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb)
{
if (xdp_prog) {
struct xdp_buff xdp;
u32 act;
int err;
- act = netif_receive_generic_xdp(skb, &xdp, xdp_prog);
+ act = netif_receive_generic_xdp(pskb, &xdp, xdp_prog);
if (act != XDP_PASS) {
switch (act) {
case XDP_REDIRECT:
- err = xdp_do_generic_redirect(skb->dev, skb,
+ err = xdp_do_generic_redirect((*pskb)->dev, *pskb,
&xdp, xdp_prog);
if (err)
goto out_redir;
break;
case XDP_TX:
- generic_xdp_tx(skb, xdp_prog);
+ generic_xdp_tx(*pskb, xdp_prog);
break;
}
return XDP_DROP;
@@ -5035,7 +5038,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb)
}
return XDP_PASS;
out_redir:
- kfree_skb_reason(skb, SKB_DROP_REASON_XDP);
+ kfree_skb_reason(*pskb, SKB_DROP_REASON_XDP);
return XDP_DROP;
}
EXPORT_SYMBOL_GPL(do_xdp_generic);
@@ -5044,7 +5047,7 @@ static int netif_rx_internal(struct sk_buff *skb)
{
int ret;
- net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
+ net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb);
trace_netif_rx(skb);
@@ -5336,7 +5339,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
int ret = NET_RX_DROP;
__be16 type;
- net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb);
+ net_timestamp_check(!READ_ONCE(net_hotdata.tstamp_prequeue), skb);
trace_netif_receive_skb(skb);
@@ -5358,7 +5361,8 @@ another_round:
int ret2;
migrate_disable();
- ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb);
+ ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog),
+ &skb);
migrate_enable();
if (ret2 != XDP_PASS) {
@@ -5379,7 +5383,7 @@ another_round:
if (pfmemalloc)
goto skip_taps;
- list_for_each_entry_rcu(ptype, &ptype_all, list) {
+ list_for_each_entry_rcu(ptype, &net_hotdata.ptype_all, list) {
if (pt_prev)
ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = ptype;
@@ -5719,7 +5723,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
{
int ret;
- net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
+ net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb);
if (skb_defer_rx_timestamp(skb))
return NET_RX_SUCCESS;
@@ -5749,7 +5753,8 @@ void netif_receive_skb_list_internal(struct list_head *head)
INIT_LIST_HEAD(&sublist);
list_for_each_entry_safe(skb, next, head, list) {
- net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb);
+ net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue),
+ skb);
skb_list_del_init(skb);
if (!skb_defer_rx_timestamp(skb))
list_add_tail(&skb->list, &sublist);
@@ -5973,7 +5978,7 @@ static int process_backlog(struct napi_struct *napi, int quota)
net_rps_action_and_irq_enable(sd);
}
- napi->weight = READ_ONCE(dev_rx_weight);
+ napi->weight = READ_ONCE(net_hotdata.dev_rx_weight);
while (again) {
struct sk_buff *skb;
@@ -6162,6 +6167,27 @@ struct napi_struct *napi_by_id(unsigned int napi_id)
return NULL;
}
+static void skb_defer_free_flush(struct softnet_data *sd)
+{
+ struct sk_buff *skb, *next;
+
+ /* Paired with WRITE_ONCE() in skb_attempt_defer_free() */
+ if (!READ_ONCE(sd->defer_list))
+ return;
+
+ spin_lock(&sd->defer_lock);
+ skb = sd->defer_list;
+ sd->defer_list = NULL;
+ sd->defer_count = 0;
+ spin_unlock(&sd->defer_lock);
+
+ while (skb != NULL) {
+ next = skb->next;
+ napi_consume_skb(skb, 1);
+ skb = next;
+ }
+}
+
#if defined(CONFIG_NET_RX_BUSY_POLL)
static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
@@ -6183,8 +6209,13 @@ static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
clear_bit(NAPI_STATE_SCHED, &napi->state);
}
-static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll,
- u16 budget)
+enum {
+ NAPI_F_PREFER_BUSY_POLL = 1,
+ NAPI_F_END_ON_RESCHED = 2,
+};
+
+static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
+ unsigned flags, u16 budget)
{
bool skip_schedule = false;
unsigned long timeout;
@@ -6204,7 +6235,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool
local_bh_disable();
- if (prefer_busy_poll) {
+ if (flags & NAPI_F_PREFER_BUSY_POLL) {
napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs);
timeout = READ_ONCE(napi->dev->gro_flush_timeout);
if (napi->defer_hard_irqs_count && timeout) {
@@ -6228,23 +6259,23 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool
local_bh_enable();
}
-void napi_busy_loop(unsigned int napi_id,
- bool (*loop_end)(void *, unsigned long),
- void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+static void __napi_busy_loop(unsigned int napi_id,
+ bool (*loop_end)(void *, unsigned long),
+ void *loop_end_arg, unsigned flags, u16 budget)
{
unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
int (*napi_poll)(struct napi_struct *napi, int budget);
void *have_poll_lock = NULL;
struct napi_struct *napi;
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
restart:
napi_poll = NULL;
- rcu_read_lock();
-
napi = napi_by_id(napi_id);
if (!napi)
- goto out;
+ return;
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
preempt_disable();
@@ -6260,14 +6291,14 @@ restart:
*/
if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
NAPIF_STATE_IN_BUSY_POLL)) {
- if (prefer_busy_poll)
+ if (flags & NAPI_F_PREFER_BUSY_POLL)
set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
goto count;
}
if (cmpxchg(&napi->state, val,
val | NAPIF_STATE_IN_BUSY_POLL |
NAPIF_STATE_SCHED) != val) {
- if (prefer_busy_poll)
+ if (flags & NAPI_F_PREFER_BUSY_POLL)
set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
goto count;
}
@@ -6281,18 +6312,22 @@ count:
if (work > 0)
__NET_ADD_STATS(dev_net(napi->dev),
LINUX_MIB_BUSYPOLLRXPACKETS, work);
+ skb_defer_free_flush(this_cpu_ptr(&softnet_data));
local_bh_enable();
if (!loop_end || loop_end(loop_end_arg, start_time))
break;
if (unlikely(need_resched())) {
+ if (flags & NAPI_F_END_ON_RESCHED)
+ break;
if (napi_poll)
- busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
+ busy_poll_stop(napi, have_poll_lock, flags, budget);
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
preempt_enable();
rcu_read_unlock();
cond_resched();
+ rcu_read_lock();
if (loop_end(loop_end_arg, start_time))
return;
goto restart;
@@ -6300,10 +6335,31 @@ count:
cpu_relax();
}
if (napi_poll)
- busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
+ busy_poll_stop(napi, have_poll_lock, flags, budget);
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
preempt_enable();
-out:
+}
+
+void napi_busy_loop_rcu(unsigned int napi_id,
+ bool (*loop_end)(void *, unsigned long),
+ void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+{
+ unsigned flags = NAPI_F_END_ON_RESCHED;
+
+ if (prefer_busy_poll)
+ flags |= NAPI_F_PREFER_BUSY_POLL;
+
+ __napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget);
+}
+
+void napi_busy_loop(unsigned int napi_id,
+ bool (*loop_end)(void *, unsigned long),
+ void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+{
+ unsigned flags = prefer_busy_poll ? NAPI_F_PREFER_BUSY_POLL : 0;
+
+ rcu_read_lock();
+ __napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget);
rcu_read_unlock();
}
EXPORT_SYMBOL(napi_busy_loop);
@@ -6686,27 +6742,6 @@ static int napi_thread_wait(struct napi_struct *napi)
return -1;
}
-static void skb_defer_free_flush(struct softnet_data *sd)
-{
- struct sk_buff *skb, *next;
-
- /* Paired with WRITE_ONCE() in skb_attempt_defer_free() */
- if (!READ_ONCE(sd->defer_list))
- return;
-
- spin_lock(&sd->defer_lock);
- skb = sd->defer_list;
- sd->defer_list = NULL;
- sd->defer_count = 0;
- spin_unlock(&sd->defer_lock);
-
- while (skb != NULL) {
- next = skb->next;
- napi_consume_skb(skb, 1);
- skb = next;
- }
-}
-
static int napi_threaded_poll(void *data)
{
struct napi_struct *napi = data;
@@ -6751,8 +6786,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
{
struct softnet_data *sd = this_cpu_ptr(&softnet_data);
unsigned long time_limit = jiffies +
- usecs_to_jiffies(READ_ONCE(netdev_budget_usecs));
- int budget = READ_ONCE(netdev_budget);
+ usecs_to_jiffies(READ_ONCE(net_hotdata.netdev_budget_usecs));
+ int budget = READ_ONCE(net_hotdata.netdev_budget);
LIST_HEAD(list);
LIST_HEAD(repoll);
@@ -8595,12 +8630,12 @@ unsigned int dev_get_flags(const struct net_device *dev)
{
unsigned int flags;
- flags = (dev->flags & ~(IFF_PROMISC |
+ flags = (READ_ONCE(dev->flags) & ~(IFF_PROMISC |
IFF_ALLMULTI |
IFF_RUNNING |
IFF_LOWER_UP |
IFF_DORMANT)) |
- (dev->gflags & (IFF_PROMISC |
+ (READ_ONCE(dev->gflags) & (IFF_PROMISC |
IFF_ALLMULTI));
if (netif_running(dev)) {
@@ -8923,7 +8958,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
}
EXPORT_SYMBOL(dev_set_mac_address);
-static DECLARE_RWSEM(dev_addr_sem);
+DECLARE_RWSEM(dev_addr_sem);
int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
struct netlink_ext_ack *extack)
@@ -9677,11 +9712,11 @@ static void dev_index_release(struct net *net, int ifindex)
/* Delayed registration/unregisteration */
LIST_HEAD(net_todo_list);
DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
+atomic_t dev_unreg_count = ATOMIC_INIT(0);
static void net_set_todo(struct net_device *dev)
{
list_add_tail(&dev->todo_list, &net_todo_list);
- atomic_inc(&dev_net(dev)->dev_unreg_count);
}
static netdev_features_t netdev_sync_upper_features(struct net_device *lower,
@@ -10246,9 +10281,9 @@ int register_netdevice(struct net_device *dev)
goto err_ifindex_release;
ret = netdev_register_kobject(dev);
- write_lock(&dev_base_lock);
- dev->reg_state = ret ? NETREG_UNREGISTERED : NETREG_REGISTERED;
- write_unlock(&dev_base_lock);
+
+ WRITE_ONCE(dev->reg_state, ret ? NETREG_UNREGISTERED : NETREG_REGISTERED);
+
if (ret)
goto err_uninit_notify;
@@ -10324,7 +10359,7 @@ EXPORT_SYMBOL(register_netdevice);
* that need to tie several hardware interfaces to a single NAPI
* poll scheduler due to HW limitations.
*/
-int init_dummy_netdev(struct net_device *dev)
+void init_dummy_netdev(struct net_device *dev)
{
/* Clear everything. Note we don't initialize spinlocks
* are they aren't supposed to be taken by any of the
@@ -10352,8 +10387,6 @@ int init_dummy_netdev(struct net_device *dev)
* because users of this 'device' dont need to change
* its refcount.
*/
-
- return 0;
}
EXPORT_SYMBOL_GPL(init_dummy_netdev);
@@ -10509,6 +10542,7 @@ void netdev_run_todo(void)
{
struct net_device *dev, *tmp;
struct list_head list;
+ int cnt;
#ifdef CONFIG_LOCKDEP
struct list_head unlink_list;
@@ -10539,12 +10573,11 @@ void netdev_run_todo(void)
continue;
}
- write_lock(&dev_base_lock);
- dev->reg_state = NETREG_UNREGISTERED;
- write_unlock(&dev_base_lock);
+ WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERED);
linkwatch_sync_dev(dev);
}
+ cnt = 0;
while (!list_empty(&list)) {
dev = netdev_wait_allrefs_any(&list);
list_del(&dev->todo_list);
@@ -10562,12 +10595,13 @@ void netdev_run_todo(void)
if (dev->needs_free_netdev)
free_netdev(dev);
- if (atomic_dec_and_test(&dev_net(dev)->dev_unreg_count))
- wake_up(&netdev_unregistering_wq);
+ cnt++;
/* Free network device */
kobject_put(&dev->dev.kobj);
}
+ if (cnt && atomic_sub_and_test(cnt, &dev_unreg_count))
+ wake_up(&netdev_unregistering_wq);
}
/* Convert net_device_stats to rtnl_link_stats64. rtnl_link_stats64 has
@@ -10644,6 +10678,8 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
ops->ndo_get_stats64(dev, storage);
} else if (ops->ndo_get_stats) {
netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev));
+ } else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_TSTATS) {
+ dev_get_tstats64(dev, storage);
} else {
netdev_stats_to_stats64(storage, &dev->stats);
}
@@ -10958,7 +10994,7 @@ void free_netdev(struct net_device *dev)
}
BUG_ON(dev->reg_state != NETREG_UNREGISTERED);
- dev->reg_state = NETREG_RELEASED;
+ WRITE_ONCE(dev->reg_state, NETREG_RELEASED);
/* will free via device release */
put_device(&dev->dev);
@@ -11014,6 +11050,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
{
struct net_device *dev, *tmp;
LIST_HEAD(close_head);
+ int cnt = 0;
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
@@ -11045,10 +11082,8 @@ void unregister_netdevice_many_notify(struct list_head *head,
list_for_each_entry(dev, head, unreg_list) {
/* And unlink it from device chain. */
- write_lock(&dev_base_lock);
- unlist_netdevice(dev, false);
- dev->reg_state = NETREG_UNREGISTERING;
- write_unlock(&dev_base_lock);
+ unlist_netdevice(dev);
+ WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERING);
}
flush_all_backlogs();
@@ -11110,7 +11145,9 @@ void unregister_netdevice_many_notify(struct list_head *head,
list_for_each_entry(dev, head, unreg_list) {
netdev_put(dev, &dev->dev_registered_tracker);
net_set_todo(dev);
+ cnt++;
}
+ atomic_add(cnt, &dev_unreg_count);
list_del(head);
}
@@ -11228,7 +11265,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
dev_close(dev);
/* And unlink it from device chain */
- unlist_netdevice(dev, true);
+ unlist_netdevice(dev);
synchronize_net();
@@ -11564,11 +11601,8 @@ static void __net_exit default_device_exit_net(struct net *net)
snprintf(fb_name, IFNAMSIZ, "dev%%d");
netdev_for_each_altname_safe(dev, name_node, tmp)
- if (netdev_name_in_use(&init_net, name_node->name)) {
- netdev_name_node_del(name_node);
- synchronize_rcu();
+ if (netdev_name_in_use(&init_net, name_node->name))
__netdev_name_node_alt_destroy(name_node);
- }
err = dev_change_net_namespace(dev, &init_net, fb_name);
if (err) {
@@ -11676,6 +11710,28 @@ static void __init net_dev_struct_check(void)
*
*/
+/* We allocate 256 pages for each CPU if PAGE_SHIFT is 12 */
+#define SYSTEM_PERCPU_PAGE_POOL_SIZE ((1 << 20) / PAGE_SIZE)
+
+static int net_page_pool_create(int cpuid)
+{
+#if IS_ENABLED(CONFIG_PAGE_POOL)
+ struct page_pool_params page_pool_params = {
+ .pool_size = SYSTEM_PERCPU_PAGE_POOL_SIZE,
+ .flags = PP_FLAG_SYSTEM_POOL,
+ .nid = NUMA_NO_NODE,
+ };
+ struct page_pool *pp_ptr;
+
+ pp_ptr = page_pool_create_percpu(&page_pool_params, cpuid);
+ if (IS_ERR(pp_ptr))
+ return -ENOMEM;
+
+ per_cpu(system_page_pool, cpuid) = pp_ptr;
+#endif
+ return 0;
+}
+
/*
* This is called single threaded during boot, so no need
* to take the rtnl semaphore.
@@ -11694,7 +11750,6 @@ static int __init net_dev_init(void)
if (netdev_kobject_init())
goto out;
- INIT_LIST_HEAD(&ptype_all);
for (i = 0; i < PTYPE_HASH_SIZE; i++)
INIT_LIST_HEAD(&ptype_base[i]);
@@ -11728,6 +11783,9 @@ static int __init net_dev_init(void)
init_gro_hash(&sd->backlog);
sd->backlog.poll = process_backlog;
sd->backlog.weight = weight_p;
+
+ if (net_page_pool_create(i))
+ goto out;
}
dev_boot_phase = 0;
@@ -11755,6 +11813,19 @@ static int __init net_dev_init(void)
WARN_ON(rc < 0);
rc = 0;
out:
+ if (rc < 0) {
+ for_each_possible_cpu(i) {
+ struct page_pool *pp_ptr;
+
+ pp_ptr = per_cpu(system_page_pool, i);
+ if (!pp_ptr)
+ continue;
+
+ page_pool_destroy(pp_ptr);
+ per_cpu(system_page_pool, i) = NULL;
+ }
+ }
+
return rc;
}
diff --git a/net/core/dev.h b/net/core/dev.h
index 7480b4c842..2bcaf8eee5 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -3,6 +3,7 @@
#define _NET_CORE_DEV_H
#include <linux/types.h>
+#include <linux/rwsem.h>
struct net;
struct net_device;
@@ -37,15 +38,14 @@ int dev_addr_init(struct net_device *dev);
void dev_addr_check(struct net_device *dev);
/* sysctls not referred to from outside net/core/ */
-extern int netdev_budget;
-extern unsigned int netdev_budget_usecs;
extern unsigned int sysctl_skb_defer_max;
-extern int netdev_tstamp_prequeue;
extern int netdev_unregister_timeout_secs;
extern int weight_p;
extern int dev_weight_rx_bias;
extern int dev_weight_tx_bias;
+extern struct rw_semaphore dev_addr_sem;
+
/* rtnl helpers */
extern struct list_head net_todo_list;
void netdev_run_todo(void);
@@ -56,6 +56,7 @@ struct netdev_name_node {
struct list_head list;
struct net_device *dev;
const char *name;
+ struct rcu_head rcu;
};
int netdev_get_name(struct net *net, char *name, int ifindex);
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index b0f221d658..430ed18f85 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -74,7 +74,7 @@ struct net_dm_hw_entries {
};
struct per_cpu_dm_data {
- spinlock_t lock; /* Protects 'skb', 'hw_entries' and
+ raw_spinlock_t lock; /* Protects 'skb', 'hw_entries' and
* 'send_timer'
*/
union {
@@ -168,9 +168,9 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
err:
mod_timer(&data->send_timer, jiffies + HZ / 10);
out:
- spin_lock_irqsave(&data->lock, flags);
+ raw_spin_lock_irqsave(&data->lock, flags);
swap(data->skb, skb);
- spin_unlock_irqrestore(&data->lock, flags);
+ raw_spin_unlock_irqrestore(&data->lock, flags);
if (skb) {
struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data;
@@ -225,7 +225,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
local_irq_save(flags);
data = this_cpu_ptr(&dm_cpu_data);
- spin_lock(&data->lock);
+ raw_spin_lock(&data->lock);
dskb = data->skb;
if (!dskb)
@@ -259,7 +259,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
}
out:
- spin_unlock_irqrestore(&data->lock, flags);
+ raw_spin_unlock_irqrestore(&data->lock, flags);
}
static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb,
@@ -314,9 +314,9 @@ net_dm_hw_reset_per_cpu_data(struct per_cpu_dm_data *hw_data)
mod_timer(&hw_data->send_timer, jiffies + HZ / 10);
}
- spin_lock_irqsave(&hw_data->lock, flags);
+ raw_spin_lock_irqsave(&hw_data->lock, flags);
swap(hw_data->hw_entries, hw_entries);
- spin_unlock_irqrestore(&hw_data->lock, flags);
+ raw_spin_unlock_irqrestore(&hw_data->lock, flags);
return hw_entries;
}
@@ -448,7 +448,7 @@ net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink,
return;
hw_data = this_cpu_ptr(&dm_hw_cpu_data);
- spin_lock_irqsave(&hw_data->lock, flags);
+ raw_spin_lock_irqsave(&hw_data->lock, flags);
hw_entries = hw_data->hw_entries;
if (!hw_entries)
@@ -477,7 +477,7 @@ net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink,
}
out:
- spin_unlock_irqrestore(&hw_data->lock, flags);
+ raw_spin_unlock_irqrestore(&hw_data->lock, flags);
}
static const struct net_dm_alert_ops net_dm_alert_summary_ops = {
@@ -1673,7 +1673,7 @@ static struct notifier_block dropmon_net_notifier = {
static void __net_dm_cpu_data_init(struct per_cpu_dm_data *data)
{
- spin_lock_init(&data->lock);
+ raw_spin_lock_init(&data->lock);
skb_queue_head_init(&data->drop_queue);
u64_stats_init(&data->stats.syncp);
}
diff --git a/net/core/dst.c b/net/core/dst.c
index 6838d3212c..95f533844f 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -96,7 +96,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
}
EXPORT_SYMBOL(dst_alloc);
-struct dst_entry *dst_destroy(struct dst_entry * dst)
+static void dst_destroy(struct dst_entry *dst)
{
struct dst_entry *child = NULL;
@@ -126,15 +126,13 @@ struct dst_entry *dst_destroy(struct dst_entry * dst)
dst = child;
if (dst)
dst_release_immediate(dst);
- return NULL;
}
-EXPORT_SYMBOL(dst_destroy);
static void dst_destroy_rcu(struct rcu_head *head)
{
struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head);
- dst = dst_destroy(dst);
+ dst_destroy(dst);
}
/* Operations to mark dst as DEAD and clean up the net device referenced
diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c
index 0ccfd5fa5c..0c0bdb058c 100644
--- a/net/core/dst_cache.c
+++ b/net/core/dst_cache.c
@@ -83,7 +83,7 @@ struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr)
return NULL;
*saddr = idst->in_saddr.s_addr;
- return container_of(dst, struct rtable, dst);
+ return dst_rtable(dst);
}
EXPORT_SYMBOL_GPL(dst_cache_get_ip4);
@@ -112,7 +112,7 @@ void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst,
idst = this_cpu_ptr(dst_cache->cache);
dst_cache_per_cpu_dst_set(this_cpu_ptr(dst_cache->cache), dst,
- rt6_get_cookie((struct rt6_info *)dst));
+ rt6_get_cookie(dst_rt6_info(dst)));
idst->in6_saddr = *saddr;
}
EXPORT_SYMBOL_GPL(dst_cache_set_ip6);
diff --git a/net/core/filter.c b/net/core/filter.c
index 75cdaa1604..ce255e0a2f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -88,7 +88,7 @@
#include "dev.h"
static const struct bpf_func_proto *
-bpf_sk_base_func_proto(enum bpf_func_id func_id);
+bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog);
int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len)
{
@@ -778,7 +778,7 @@ jmp_rest:
BPF_EMIT_JMP;
break;
- /* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */
+ /* ldxb 4 * ([14] & 0xf) is remapped into 6 insns. */
case BPF_LDX | BPF_MSH | BPF_B: {
struct sock_filter tmp = {
.code = BPF_LD | BPF_ABS | BPF_B,
@@ -804,7 +804,7 @@ jmp_rest:
*insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP);
break;
}
- /* RET_K is remaped into 2 insns. RET_A case doesn't need an
+ /* RET_K is remapped into 2 insns. RET_A case doesn't need an
* extra mov as BPF_REG_0 is already mapped into BPF_REG_A.
*/
case BPF_RET | BPF_A:
@@ -1662,6 +1662,11 @@ static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp);
static inline int __bpf_try_make_writable(struct sk_buff *skb,
unsigned int write_len)
{
+#ifdef CONFIG_DEBUG_NET
+ /* Avoid a splat in pskb_may_pull_reason() */
+ if (write_len > INT_MAX)
+ return -EINVAL;
+#endif
return skb_ensure_writable(skb, write_len);
}
@@ -2215,7 +2220,7 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb,
rcu_read_lock();
if (!nh) {
dst = skb_dst(skb);
- nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst),
+ nexthop = rt6_nexthop(dst_rt6_info(dst),
&ipv6_hdr(skb)->daddr);
} else {
nexthop = &nh->ipv6_nh;
@@ -2314,8 +2319,7 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb,
rcu_read_lock();
if (!nh) {
- struct dst_entry *dst = skb_dst(skb);
- struct rtable *rt = container_of(dst, struct rtable, dst);
+ struct rtable *rt = skb_rtable(skb);
neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
} else if (nh->nh_family == AF_INET6) {
@@ -2968,7 +2972,7 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
*
* Then if B is non-zero AND there is no space allocate space and
* compact A, B regions into page. If there is space shift ring to
- * the rigth free'ing the next element in ring to place B, leaving
+ * the right free'ing the next element in ring to place B, leaving
* A untouched except to reduce length.
*/
if (start != offset) {
@@ -6010,7 +6014,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
return -ENODEV;
idev = __in6_dev_get_safely(dev);
- if (unlikely(!idev || !idev->cnf.forwarding))
+ if (unlikely(!idev || !READ_ONCE(idev->cnf.forwarding)))
return BPF_FIB_LKUP_RET_FWD_DISABLED;
if (flags & BPF_FIB_LOOKUP_OUTPUT) {
@@ -7916,7 +7920,7 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_ktime_get_coarse_ns:
return &bpf_ktime_get_coarse_ns_proto;
default:
- return bpf_base_func_proto(func_id);
+ return bpf_base_func_proto(func_id, prog);
}
}
@@ -8009,7 +8013,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return NULL;
}
default:
- return bpf_sk_base_func_proto(func_id);
+ return bpf_sk_base_func_proto(func_id, prog);
}
}
@@ -8028,7 +8032,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_perf_event_output:
return &bpf_skb_event_output_proto;
default:
- return bpf_sk_base_func_proto(func_id);
+ return bpf_sk_base_func_proto(func_id, prog);
}
}
@@ -8215,7 +8219,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
#endif
#endif
default:
- return bpf_sk_base_func_proto(func_id);
+ return bpf_sk_base_func_proto(func_id, prog);
}
}
@@ -8274,13 +8278,13 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
#endif
#endif
default:
- return bpf_sk_base_func_proto(func_id);
+ return bpf_sk_base_func_proto(func_id, prog);
}
#if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)
/* The nf_conn___init type is used in the NF_CONNTRACK kfuncs. The
* kfuncs are defined in two different modules, and we want to be able
- * to use them interchangably with the same BTF type ID. Because modules
+ * to use them interchangeably with the same BTF type ID. Because modules
* can't de-duplicate BTF IDs between each other, we need the type to be
* referenced in the vmlinux BTF or the verifier will get confused about
* the different types. So we add this dummy type reference which will
@@ -8335,7 +8339,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_tcp_sock_proto;
#endif /* CONFIG_INET */
default:
- return bpf_sk_base_func_proto(func_id);
+ return bpf_sk_base_func_proto(func_id, prog);
}
}
@@ -8377,7 +8381,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_get_cgroup_classid_curr_proto;
#endif
default:
- return bpf_sk_base_func_proto(func_id);
+ return bpf_sk_base_func_proto(func_id, prog);
}
}
@@ -8421,7 +8425,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_skc_lookup_tcp_proto;
#endif
default:
- return bpf_sk_base_func_proto(func_id);
+ return bpf_sk_base_func_proto(func_id, prog);
}
}
@@ -8432,7 +8436,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_skb_load_bytes:
return &bpf_flow_dissector_load_bytes_proto;
default:
- return bpf_sk_base_func_proto(func_id);
+ return bpf_sk_base_func_proto(func_id, prog);
}
}
@@ -8459,7 +8463,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_skb_under_cgroup:
return &bpf_skb_under_cgroup_proto;
default:
- return bpf_sk_base_func_proto(func_id);
+ return bpf_sk_base_func_proto(func_id, prog);
}
}
@@ -8634,7 +8638,7 @@ static bool cg_skb_is_valid_access(int off, int size,
return false;
case bpf_ctx_range(struct __sk_buff, data):
case bpf_ctx_range(struct __sk_buff, data_end):
- if (!bpf_capable())
+ if (!bpf_token_capable(prog->aux->token, CAP_BPF))
return false;
break;
}
@@ -8646,7 +8650,7 @@ static bool cg_skb_is_valid_access(int off, int size,
case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
break;
case bpf_ctx_range(struct __sk_buff, tstamp):
- if (!bpf_capable())
+ if (!bpf_token_capable(prog->aux->token, CAP_BPF))
return false;
break;
default:
@@ -11290,7 +11294,7 @@ sk_reuseport_func_proto(enum bpf_func_id func_id,
case BPF_FUNC_ktime_get_coarse_ns:
return &bpf_ktime_get_coarse_ns_proto;
default:
- return bpf_base_func_proto(func_id);
+ return bpf_base_func_proto(func_id, prog);
}
}
@@ -11472,7 +11476,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_sk_release:
return &bpf_sk_release_proto;
default:
- return bpf_sk_base_func_proto(func_id);
+ return bpf_sk_base_func_proto(func_id, prog);
}
}
@@ -11806,7 +11810,7 @@ const struct bpf_func_proto bpf_sock_from_file_proto = {
};
static const struct bpf_func_proto *
-bpf_sk_base_func_proto(enum bpf_func_id func_id)
+bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
const struct bpf_func_proto *func;
@@ -11835,10 +11839,10 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id)
case BPF_FUNC_ktime_get_coarse_ns:
return &bpf_ktime_get_coarse_ns_proto;
default:
- return bpf_base_func_proto(func_id);
+ return bpf_base_func_proto(func_id, prog);
}
- if (!perfmon_capable())
+ if (!bpf_token_capable(prog->aux->token, CAP_PERFMON))
return NULL;
return func;
@@ -11891,6 +11895,103 @@ __bpf_kfunc int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern,
return 0;
}
+
+__bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct sk_buff *skb, struct sock *sk,
+ struct bpf_tcp_req_attrs *attrs, int attrs__sz)
+{
+#if IS_ENABLED(CONFIG_SYN_COOKIES)
+ const struct request_sock_ops *ops;
+ struct inet_request_sock *ireq;
+ struct tcp_request_sock *treq;
+ struct request_sock *req;
+ struct net *net;
+ __u16 min_mss;
+ u32 tsoff = 0;
+
+ if (attrs__sz != sizeof(*attrs) ||
+ attrs->reserved[0] || attrs->reserved[1] || attrs->reserved[2])
+ return -EINVAL;
+
+ if (!skb_at_tc_ingress(skb))
+ return -EINVAL;
+
+ net = dev_net(skb->dev);
+ if (net != sock_net(sk))
+ return -ENETUNREACH;
+
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ ops = &tcp_request_sock_ops;
+ min_mss = 536;
+ break;
+#if IS_BUILTIN(CONFIG_IPV6)
+ case htons(ETH_P_IPV6):
+ ops = &tcp6_request_sock_ops;
+ min_mss = IPV6_MIN_MTU - 60;
+ break;
+#endif
+ default:
+ return -EINVAL;
+ }
+
+ if (sk->sk_type != SOCK_STREAM || sk->sk_state != TCP_LISTEN ||
+ sk_is_mptcp(sk))
+ return -EINVAL;
+
+ if (attrs->mss < min_mss)
+ return -EINVAL;
+
+ if (attrs->wscale_ok) {
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_window_scaling))
+ return -EINVAL;
+
+ if (attrs->snd_wscale > TCP_MAX_WSCALE ||
+ attrs->rcv_wscale > TCP_MAX_WSCALE)
+ return -EINVAL;
+ }
+
+ if (attrs->sack_ok && !READ_ONCE(net->ipv4.sysctl_tcp_sack))
+ return -EINVAL;
+
+ if (attrs->tstamp_ok) {
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_timestamps))
+ return -EINVAL;
+
+ tsoff = attrs->rcv_tsecr - tcp_ns_to_ts(attrs->usec_ts_ok, tcp_clock_ns());
+ }
+
+ req = inet_reqsk_alloc(ops, sk, false);
+ if (!req)
+ return -ENOMEM;
+
+ ireq = inet_rsk(req);
+ treq = tcp_rsk(req);
+
+ req->rsk_listener = sk;
+ req->syncookie = 1;
+ req->mss = attrs->mss;
+ req->ts_recent = attrs->rcv_tsval;
+
+ ireq->snd_wscale = attrs->snd_wscale;
+ ireq->rcv_wscale = attrs->rcv_wscale;
+ ireq->tstamp_ok = !!attrs->tstamp_ok;
+ ireq->sack_ok = !!attrs->sack_ok;
+ ireq->wscale_ok = !!attrs->wscale_ok;
+ ireq->ecn_ok = !!attrs->ecn_ok;
+
+ treq->req_usec_ts = !!attrs->usec_ts_ok;
+ treq->ts_off = tsoff;
+
+ skb_orphan(skb);
+ skb->sk = req_to_sk(req);
+ skb->destructor = sock_pfree;
+
+ return 0;
+#else
+ return -EOPNOTSUPP;
+#endif
+}
+
__bpf_kfunc_end_defs();
int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
@@ -11907,17 +12008,21 @@ int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
return 0;
}
-BTF_SET8_START(bpf_kfunc_check_set_skb)
+BTF_KFUNCS_START(bpf_kfunc_check_set_skb)
BTF_ID_FLAGS(func, bpf_dynptr_from_skb)
-BTF_SET8_END(bpf_kfunc_check_set_skb)
+BTF_KFUNCS_END(bpf_kfunc_check_set_skb)
-BTF_SET8_START(bpf_kfunc_check_set_xdp)
+BTF_KFUNCS_START(bpf_kfunc_check_set_xdp)
BTF_ID_FLAGS(func, bpf_dynptr_from_xdp)
-BTF_SET8_END(bpf_kfunc_check_set_xdp)
+BTF_KFUNCS_END(bpf_kfunc_check_set_xdp)
-BTF_SET8_START(bpf_kfunc_check_set_sock_addr)
+BTF_KFUNCS_START(bpf_kfunc_check_set_sock_addr)
BTF_ID_FLAGS(func, bpf_sock_addr_set_sun_path)
-BTF_SET8_END(bpf_kfunc_check_set_sock_addr)
+BTF_KFUNCS_END(bpf_kfunc_check_set_sock_addr)
+
+BTF_KFUNCS_START(bpf_kfunc_check_set_tcp_reqsk)
+BTF_ID_FLAGS(func, bpf_sk_assign_tcp_reqsk, KF_TRUSTED_ARGS)
+BTF_KFUNCS_END(bpf_kfunc_check_set_tcp_reqsk)
static const struct btf_kfunc_id_set bpf_kfunc_set_skb = {
.owner = THIS_MODULE,
@@ -11934,6 +12039,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_sock_addr = {
.set = &bpf_kfunc_check_set_sock_addr,
};
+static const struct btf_kfunc_id_set bpf_kfunc_set_tcp_reqsk = {
+ .owner = THIS_MODULE,
+ .set = &bpf_kfunc_check_set_tcp_reqsk,
+};
+
static int __init bpf_kfunc_init(void)
{
int ret;
@@ -11949,8 +12059,9 @@ static int __init bpf_kfunc_init(void)
ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb);
ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_NETFILTER, &bpf_kfunc_set_skb);
ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp);
- return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
- &bpf_kfunc_set_sock_addr);
+ ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ &bpf_kfunc_set_sock_addr);
+ return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk);
}
late_initcall(bpf_kfunc_init);
@@ -11990,9 +12101,9 @@ __bpf_kfunc int bpf_sock_destroy(struct sock_common *sock)
__bpf_kfunc_end_defs();
-BTF_SET8_START(bpf_sk_iter_kfunc_ids)
+BTF_KFUNCS_START(bpf_sk_iter_kfunc_ids)
BTF_ID_FLAGS(func, bpf_sock_destroy, KF_TRUSTED_ARGS)
-BTF_SET8_END(bpf_sk_iter_kfunc_ids)
+BTF_KFUNCS_END(bpf_sk_iter_kfunc_ids)
static int tracing_iter_filter(const struct bpf_prog *prog, u32 kfunc_id)
{
diff --git a/net/core/gro.c b/net/core/gro.c
index 31e40f25fd..c7901253a1 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -10,9 +10,6 @@
#define GRO_MAX_HEAD (MAX_HEADER + 128)
static DEFINE_SPINLOCK(offload_lock);
-struct list_head offload_base __read_mostly = LIST_HEAD_INIT(offload_base);
-/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */
-int gro_normal_batch __read_mostly = 8;
/**
* dev_add_offload - register offload handlers
@@ -31,7 +28,7 @@ void dev_add_offload(struct packet_offload *po)
struct packet_offload *elem;
spin_lock(&offload_lock);
- list_for_each_entry(elem, &offload_base, list) {
+ list_for_each_entry(elem, &net_hotdata.offload_base, list) {
if (po->priority < elem->priority)
break;
}
@@ -55,7 +52,7 @@ EXPORT_SYMBOL(dev_add_offload);
*/
static void __dev_remove_offload(struct packet_offload *po)
{
- struct list_head *head = &offload_base;
+ struct list_head *head = &net_hotdata.offload_base;
struct packet_offload *po1;
spin_lock(&offload_lock);
@@ -236,9 +233,9 @@ done:
static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb)
{
+ struct list_head *head = &net_hotdata.offload_base;
struct packet_offload *ptype;
__be16 type = skb->protocol;
- struct list_head *head = &offload_base;
int err = -ENOENT;
BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb));
@@ -370,16 +367,22 @@ static void gro_list_prepare(const struct list_head *head,
static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff)
{
- const struct skb_shared_info *pinfo = skb_shinfo(skb);
- const skb_frag_t *frag0 = &pinfo->frags[0];
+ const struct skb_shared_info *pinfo;
+ const skb_frag_t *frag0;
+ unsigned int headlen;
NAPI_GRO_CB(skb)->network_offset = 0;
NAPI_GRO_CB(skb)->data_offset = 0;
- NAPI_GRO_CB(skb)->frag0 = NULL;
- NAPI_GRO_CB(skb)->frag0_len = 0;
+ headlen = skb_headlen(skb);
+ NAPI_GRO_CB(skb)->frag0 = skb->data;
+ NAPI_GRO_CB(skb)->frag0_len = headlen;
+ if (headlen)
+ return;
+
+ pinfo = skb_shinfo(skb);
+ frag0 = &pinfo->frags[0];
- if (!skb_headlen(skb) && pinfo->nr_frags &&
- !PageHighMem(skb_frag_page(frag0)) &&
+ if (pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0)) &&
(!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) {
NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int,
@@ -440,7 +443,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
{
u32 bucket = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1);
struct gro_list *gro_list = &napi->gro_hash[bucket];
- struct list_head *head = &offload_base;
+ struct list_head *head = &net_hotdata.offload_base;
struct packet_offload *ptype;
__be16 type = skb->protocol;
struct sk_buff *pp = NULL;
@@ -546,7 +549,7 @@ normal:
struct packet_offload *gro_find_receive_by_type(__be16 type)
{
- struct list_head *offload_head = &offload_base;
+ struct list_head *offload_head = &net_hotdata.offload_base;
struct packet_offload *ptype;
list_for_each_entry_rcu(ptype, offload_head, list) {
@@ -560,7 +563,7 @@ EXPORT_SYMBOL(gro_find_receive_by_type);
struct packet_offload *gro_find_complete_by_type(__be16 type)
{
- struct list_head *offload_head = &offload_base;
+ struct list_head *offload_head = &net_hotdata.offload_base;
struct packet_offload *ptype;
list_for_each_entry_rcu(ptype, offload_head, list) {
@@ -702,7 +705,7 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
skb_reset_mac_header(skb);
skb_gro_reset_offset(skb, hlen);
- if (unlikely(skb_gro_header_hard(skb, hlen))) {
+ if (unlikely(!skb_gro_may_pull(skb, hlen))) {
eth = skb_gro_header_slow(skb, hlen, 0);
if (unlikely(!eth)) {
net_warn_ratelimited("%s: dropping impossible skb from %s\n",
@@ -712,7 +715,10 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
}
} else {
eth = (const struct ethhdr *)skb->data;
- gro_pull_from_frag0(skb, hlen);
+
+ if (NAPI_GRO_CB(skb)->frag0 != skb->data)
+ gro_pull_from_frag0(skb, hlen);
+
NAPI_GRO_CB(skb)->frag0 += hlen;
NAPI_GRO_CB(skb)->frag0_len -= hlen;
}
diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c
index ed5ec5de47..ff8e5b64bf 100644
--- a/net/core/gro_cells.c
+++ b/net/core/gro_cells.c
@@ -3,6 +3,7 @@
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <net/gro_cells.h>
+#include <net/hotdata.h>
struct gro_cell {
struct sk_buff_head napi_skbs;
@@ -26,7 +27,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
cell = this_cpu_ptr(gcells->cells);
- if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(netdev_max_backlog)) {
+ if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(net_hotdata.max_backlog)) {
drop:
dev_core_stats_rx_dropped_inc(dev);
kfree_skb(skb);
diff --git a/net/core/gso.c b/net/core/gso.c
index 9e1803bfc9..bcd156372f 100644
--- a/net/core/gso.c
+++ b/net/core/gso.c
@@ -17,7 +17,7 @@ struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb,
struct packet_offload *ptype;
rcu_read_lock();
- list_for_each_entry_rcu(ptype, &offload_base, list) {
+ list_for_each_entry_rcu(ptype, &net_hotdata.offload_base, list) {
if (ptype->type == type && ptype->callbacks.gso_segment) {
segs = ptype->callbacks.gso_segment(skb, features);
break;
@@ -48,7 +48,7 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
__skb_pull(skb, vlan_depth);
rcu_read_lock();
- list_for_each_entry_rcu(ptype, &offload_base, list) {
+ list_for_each_entry_rcu(ptype, &net_hotdata.offload_base, list) {
if (ptype->type == type && ptype->callbacks.gso_segment) {
segs = ptype->callbacks.gso_segment(skb, features);
break;
diff --git a/net/core/hotdata.c b/net/core/hotdata.c
new file mode 100644
index 0000000000..c8a7a451c1
--- /dev/null
+++ b/net/core/hotdata.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <net/hotdata.h>
+#include <linux/cache.h>
+#include <linux/jiffies.h>
+#include <linux/list.h>
+
+
+struct net_hotdata net_hotdata __cacheline_aligned = {
+ .offload_base = LIST_HEAD_INIT(net_hotdata.offload_base),
+ .ptype_all = LIST_HEAD_INIT(net_hotdata.ptype_all),
+ .gro_normal_batch = 8,
+
+ .netdev_budget = 300,
+ /* Must be at least 2 jiffes to guarantee 1 jiffy timeout */
+ .netdev_budget_usecs = 2 * USEC_PER_SEC / HZ,
+
+ .tstamp_prequeue = 1,
+ .max_backlog = 1000,
+ .dev_tx_weight = 64,
+ .dev_rx_weight = 64,
+};
+EXPORT_SYMBOL(net_hotdata);
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index 1b93e054c9..8ec35194bf 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -33,7 +33,7 @@ static DECLARE_DELAYED_WORK(linkwatch_work, linkwatch_event);
static LIST_HEAD(lweventlist);
static DEFINE_SPINLOCK(lweventlist_lock);
-static unsigned char default_operstate(const struct net_device *dev)
+static unsigned int default_operstate(const struct net_device *dev)
{
if (netif_testing(dev))
return IF_OPER_TESTING;
@@ -62,16 +62,13 @@ static unsigned char default_operstate(const struct net_device *dev)
return IF_OPER_UP;
}
-
static void rfc2863_policy(struct net_device *dev)
{
- unsigned char operstate = default_operstate(dev);
+ unsigned int operstate = default_operstate(dev);
if (operstate == READ_ONCE(dev->operstate))
return;
- write_lock(&dev_base_lock);
-
switch(dev->link_mode) {
case IF_LINK_MODE_TESTING:
if (operstate == IF_OPER_UP)
@@ -88,8 +85,6 @@ static void rfc2863_policy(struct net_device *dev)
}
WRITE_ONCE(dev->operstate, operstate);
-
- write_unlock(&dev_base_lock);
}
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index 09f7ed1a04..a97eceb84e 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -3,52 +3,22 @@
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <net/wext.h>
+#include <net/hotdata.h>
#include "dev.h"
-#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1)
-
-#define get_bucket(x) ((x) >> BUCKET_SPACE)
-#define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1))
-#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o))
-
-static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos)
+static void *dev_seq_from_index(struct seq_file *seq, loff_t *pos)
{
- struct net *net = seq_file_net(seq);
+ unsigned long ifindex = *pos;
struct net_device *dev;
- struct hlist_head *h;
- unsigned int count = 0, offset = get_offset(*pos);
- h = &net->dev_index_head[get_bucket(*pos)];
- hlist_for_each_entry_rcu(dev, h, index_hlist) {
- if (++count == offset)
- return dev;
+ for_each_netdev_dump(seq_file_net(seq), dev, ifindex) {
+ *pos = dev->ifindex;
+ return dev;
}
-
- return NULL;
-}
-
-static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos)
-{
- struct net_device *dev;
- unsigned int bucket;
-
- do {
- dev = dev_from_same_bucket(seq, pos);
- if (dev)
- return dev;
-
- bucket = get_bucket(*pos) + 1;
- *pos = set_bucket_offset(bucket, 1);
- } while (bucket < NETDEV_HASHENTRIES);
-
return NULL;
}
-/*
- * This is invoked by the /proc filesystem handler to display a device
- * in detail.
- */
static void *dev_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(RCU)
{
@@ -56,16 +26,13 @@ static void *dev_seq_start(struct seq_file *seq, loff_t *pos)
if (!*pos)
return SEQ_START_TOKEN;
- if (get_bucket(*pos) >= NETDEV_HASHENTRIES)
- return NULL;
-
- return dev_from_bucket(seq, pos);
+ return dev_seq_from_index(seq, pos);
}
static void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
++*pos;
- return dev_from_bucket(seq, pos);
+ return dev_seq_from_index(seq, pos);
}
static void dev_seq_stop(struct seq_file *seq, void *v)
@@ -217,7 +184,7 @@ static void *ptype_get_idx(struct seq_file *seq, loff_t pos)
}
}
- list_for_each_entry_rcu(pt, &ptype_all, list) {
+ list_for_each_entry_rcu(pt, &net_hotdata.ptype_all, list) {
if (i == pos)
return pt;
++i;
@@ -265,13 +232,13 @@ static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos)
}
}
- nxt = ptype_all.next;
+ nxt = net_hotdata.ptype_all.next;
goto ptype_all;
}
if (pt->type == htons(ETH_P_ALL)) {
ptype_all:
- if (nxt != &ptype_all)
+ if (nxt != &net_hotdata.ptype_all)
goto found;
hash = 0;
nxt = ptype_base[0].next;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 676048ae11..e3d7a8cfa2 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -24,6 +24,7 @@
#include <linux/of_net.h>
#include <linux/cpu.h>
#include <net/netdev_rx_queue.h>
+#include <net/rps.h>
#include "dev.h"
#include "net-sysfs.h"
@@ -34,10 +35,10 @@ static const char fmt_dec[] = "%d\n";
static const char fmt_ulong[] = "%lu\n";
static const char fmt_u64[] = "%llu\n";
-/* Caller holds RTNL or dev_base_lock */
+/* Caller holds RTNL or RCU */
static inline int dev_isalive(const struct net_device *dev)
{
- return dev->reg_state <= NETREG_REGISTERED;
+ return READ_ONCE(dev->reg_state) <= NETREG_REGISTERED;
}
/* use same locking rules as GIF* ioctl's */
@@ -48,10 +49,10 @@ static ssize_t netdev_show(const struct device *dev,
struct net_device *ndev = to_net_dev(dev);
ssize_t ret = -EINVAL;
- read_lock(&dev_base_lock);
+ rcu_read_lock();
if (dev_isalive(ndev))
ret = (*format)(ndev, buf);
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
return ret;
}
@@ -60,7 +61,7 @@ static ssize_t netdev_show(const struct device *dev,
#define NETDEVICE_SHOW(field, format_string) \
static ssize_t format_##field(const struct net_device *dev, char *buf) \
{ \
- return sysfs_emit(buf, format_string, dev->field); \
+ return sysfs_emit(buf, format_string, READ_ONCE(dev->field)); \
} \
static ssize_t field##_show(struct device *dev, \
struct device_attribute *attr, char *buf) \
@@ -125,7 +126,7 @@ static DEVICE_ATTR_RO(iflink);
static ssize_t format_name_assign_type(const struct net_device *dev, char *buf)
{
- return sysfs_emit(buf, fmt_dec, dev->name_assign_type);
+ return sysfs_emit(buf, fmt_dec, READ_ONCE(dev->name_assign_type));
}
static ssize_t name_assign_type_show(struct device *dev,
@@ -135,24 +136,28 @@ static ssize_t name_assign_type_show(struct device *dev,
struct net_device *ndev = to_net_dev(dev);
ssize_t ret = -EINVAL;
- if (ndev->name_assign_type != NET_NAME_UNKNOWN)
+ if (READ_ONCE(ndev->name_assign_type) != NET_NAME_UNKNOWN)
ret = netdev_show(dev, attr, buf, format_name_assign_type);
return ret;
}
static DEVICE_ATTR_RO(name_assign_type);
-/* use same locking rules as GIFHWADDR ioctl's */
+/* use same locking rules as GIFHWADDR ioctl's (dev_get_mac_address()) */
static ssize_t address_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct net_device *ndev = to_net_dev(dev);
ssize_t ret = -EINVAL;
- read_lock(&dev_base_lock);
+ down_read(&dev_addr_sem);
+
+ rcu_read_lock();
if (dev_isalive(ndev))
ret = sysfs_format_mac(buf, ndev->dev_addr, ndev->addr_len);
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
+
+ up_read(&dev_addr_sem);
return ret;
}
static DEVICE_ATTR_RO(address);
@@ -161,10 +166,13 @@ static ssize_t broadcast_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct net_device *ndev = to_net_dev(dev);
+ int ret = -EINVAL;
+ rcu_read_lock();
if (dev_isalive(ndev))
- return sysfs_format_mac(buf, ndev->broadcast, ndev->addr_len);
- return -EINVAL;
+ ret = sysfs_format_mac(buf, ndev->broadcast, ndev->addr_len);
+ rcu_read_unlock();
+ return ret;
}
static DEVICE_ATTR_RO(broadcast);
@@ -678,14 +686,14 @@ static ssize_t netstat_show(const struct device *d,
WARN_ON(offset > sizeof(struct rtnl_link_stats64) ||
offset % sizeof(u64) != 0);
- read_lock(&dev_base_lock);
+ rcu_read_lock();
if (dev_isalive(dev)) {
struct rtnl_link_stats64 temp;
const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp);
ret = sysfs_emit(buf, fmt_u64, *(u64 *)(((u8 *)stats) + offset));
}
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
return ret;
}
@@ -1407,6 +1415,65 @@ static struct netdev_queue_attribute bql_hold_time_attribute __ro_after_init
= __ATTR(hold_time, 0644,
bql_show_hold_time, bql_set_hold_time);
+static ssize_t bql_show_stall_thrs(struct netdev_queue *queue, char *buf)
+{
+ struct dql *dql = &queue->dql;
+
+ return sprintf(buf, "%u\n", jiffies_to_msecs(dql->stall_thrs));
+}
+
+static ssize_t bql_set_stall_thrs(struct netdev_queue *queue,
+ const char *buf, size_t len)
+{
+ struct dql *dql = &queue->dql;
+ unsigned int value;
+ int err;
+
+ err = kstrtouint(buf, 10, &value);
+ if (err < 0)
+ return err;
+
+ value = msecs_to_jiffies(value);
+ if (value && (value < 4 || value > 4 / 2 * BITS_PER_LONG))
+ return -ERANGE;
+
+ if (!dql->stall_thrs && value)
+ dql->last_reap = jiffies;
+ /* Force last_reap to be live */
+ smp_wmb();
+ dql->stall_thrs = value;
+
+ return len;
+}
+
+static struct netdev_queue_attribute bql_stall_thrs_attribute __ro_after_init =
+ __ATTR(stall_thrs, 0644, bql_show_stall_thrs, bql_set_stall_thrs);
+
+static ssize_t bql_show_stall_max(struct netdev_queue *queue, char *buf)
+{
+ return sprintf(buf, "%u\n", READ_ONCE(queue->dql.stall_max));
+}
+
+static ssize_t bql_set_stall_max(struct netdev_queue *queue,
+ const char *buf, size_t len)
+{
+ WRITE_ONCE(queue->dql.stall_max, 0);
+ return len;
+}
+
+static struct netdev_queue_attribute bql_stall_max_attribute __ro_after_init =
+ __ATTR(stall_max, 0644, bql_show_stall_max, bql_set_stall_max);
+
+static ssize_t bql_show_stall_cnt(struct netdev_queue *queue, char *buf)
+{
+ struct dql *dql = &queue->dql;
+
+ return sprintf(buf, "%lu\n", dql->stall_cnt);
+}
+
+static struct netdev_queue_attribute bql_stall_cnt_attribute __ro_after_init =
+ __ATTR(stall_cnt, 0444, bql_show_stall_cnt, NULL);
+
static ssize_t bql_show_inflight(struct netdev_queue *queue,
char *buf)
{
@@ -1445,6 +1512,9 @@ static struct attribute *dql_attrs[] __ro_after_init = {
&bql_limit_min_attribute.attr,
&bql_hold_time_attribute.attr,
&bql_inflight_attribute.attr,
+ &bql_stall_thrs_attribute.attr,
+ &bql_stall_cnt_attribute.attr,
+ &bql_stall_max_attribute.attr,
NULL
};
@@ -1452,6 +1522,9 @@ static const struct attribute_group dql_group = {
.name = "byte_queue_limits",
.attrs = dql_attrs,
};
+#else
+/* Fake declaration, all the code using it should be dead */
+extern const struct attribute_group dql_group;
#endif /* CONFIG_BQL */
#ifdef CONFIG_XPS
@@ -1689,6 +1762,15 @@ static const struct kobj_type netdev_queue_ktype = {
.get_ownership = netdev_queue_get_ownership,
};
+static bool netdev_uses_bql(const struct net_device *dev)
+{
+ if (dev->features & NETIF_F_LLTX ||
+ dev->priv_flags & IFF_NO_QUEUE)
+ return false;
+
+ return IS_ENABLED(CONFIG_BQL);
+}
+
static int netdev_queue_add_kobject(struct net_device *dev, int index)
{
struct netdev_queue *queue = dev->_tx + index;
@@ -1706,11 +1788,11 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
if (error)
goto err;
-#ifdef CONFIG_BQL
- error = sysfs_create_group(kobj, &dql_group);
- if (error)
- goto err;
-#endif
+ if (netdev_uses_bql(dev)) {
+ error = sysfs_create_group(kobj, &dql_group);
+ if (error)
+ goto err;
+ }
kobject_uevent(kobj, KOBJ_ADD);
return 0;
@@ -1731,9 +1813,9 @@ static int tx_queue_change_owner(struct net_device *ndev, int index,
if (error)
return error;
-#ifdef CONFIG_BQL
- error = sysfs_group_change_owner(kobj, &dql_group, kuid, kgid);
-#endif
+ if (netdev_uses_bql(ndev))
+ error = sysfs_group_change_owner(kobj, &dql_group, kuid, kgid);
+
return error;
}
#endif /* CONFIG_SYSFS */
@@ -1765,9 +1847,10 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
if (!refcount_read(&dev_net(dev)->ns.count))
queue->kobj.uevent_suppress = 1;
-#ifdef CONFIG_BQL
- sysfs_remove_group(&queue->kobj, &dql_group);
-#endif
+
+ if (netdev_uses_bql(dev))
+ sysfs_remove_group(&queue->kobj, &dql_group);
+
kobject_put(&queue->kobj);
}
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index b36444e381..b1dc84c4fd 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -321,8 +321,9 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
{
/* Must be called with pernet_ops_rwsem held */
const struct pernet_operations *ops, *saved_ops;
- int error = 0;
LIST_HEAD(net_exit_list);
+ LIST_HEAD(dev_kill_list);
+ int error = 0;
refcount_set(&net->ns.count, 1);
ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt");
@@ -361,6 +362,15 @@ out_undo:
synchronize_rcu();
ops = saved_ops;
+ rtnl_lock();
+ list_for_each_entry_continue_reverse(ops, &pernet_list, list) {
+ if (ops->exit_batch_rtnl)
+ ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list);
+ }
+ unregister_netdevice_many(&dev_kill_list);
+ rtnl_unlock();
+
+ ops = saved_ops;
list_for_each_entry_continue_reverse(ops, &pernet_list, list)
ops_exit_list(ops, &net_exit_list);
@@ -576,6 +586,7 @@ static void cleanup_net(struct work_struct *work)
struct net *net, *tmp, *last;
struct llist_node *net_kill_list;
LIST_HEAD(net_exit_list);
+ LIST_HEAD(dev_kill_list);
/* Atomically snapshot the list of namespaces to cleanup */
net_kill_list = llist_del_all(&cleanup_list);
@@ -614,7 +625,15 @@ static void cleanup_net(struct work_struct *work)
* the rcu_barrier() below isn't sufficient alone.
* Also the pre_exit() and exit() methods need this barrier.
*/
- synchronize_rcu();
+ synchronize_rcu_expedited();
+
+ rtnl_lock();
+ list_for_each_entry_reverse(ops, &pernet_list, list) {
+ if (ops->exit_batch_rtnl)
+ ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list);
+ }
+ unregister_netdevice_many(&dev_kill_list);
+ rtnl_unlock();
/* Run all of the network namespace exit methods */
list_for_each_entry_reverse(ops, &pernet_list, list)
@@ -674,11 +693,16 @@ EXPORT_SYMBOL_GPL(__put_net);
* get_net_ns - increment the refcount of the network namespace
* @ns: common namespace (net)
*
- * Returns the net's common namespace.
+ * Returns the net's common namespace or ERR_PTR() if ref is zero.
*/
struct ns_common *get_net_ns(struct ns_common *ns)
{
- return &get_net(container_of(ns, struct net, ns))->ns;
+ struct net *net;
+
+ net = maybe_get_net(container_of(ns, struct net, ns));
+ if (net)
+ return &net->ns;
+ return ERR_PTR(-EINVAL);
}
EXPORT_SYMBOL_GPL(get_net_ns);
@@ -1196,7 +1220,17 @@ static void free_exit_list(struct pernet_operations *ops, struct list_head *net_
{
ops_pre_exit_list(ops, net_exit_list);
synchronize_rcu();
+
+ if (ops->exit_batch_rtnl) {
+ LIST_HEAD(dev_kill_list);
+
+ rtnl_lock();
+ ops->exit_batch_rtnl(net_exit_list, &dev_kill_list);
+ unregister_netdevice_many(&dev_kill_list);
+ rtnl_unlock();
+ }
ops_exit_list(ops, net_exit_list);
+
ops_free_list(ops, net_exit_list);
}
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index be7f2ebd61..8d8ace9ef8 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -68,6 +68,11 @@ static const struct nla_policy netdev_napi_get_dump_nl_policy[NETDEV_A_NAPI_IFIN
[NETDEV_A_NAPI_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
};
+/* NETDEV_CMD_QSTATS_GET - dump */
+static const struct nla_policy netdev_qstats_get_nl_policy[NETDEV_A_QSTATS_SCOPE + 1] = {
+ [NETDEV_A_QSTATS_SCOPE] = NLA_POLICY_MASK(NLA_UINT, 0x1),
+};
+
/* Ops table for netdev */
static const struct genl_split_ops netdev_nl_ops[] = {
{
@@ -138,6 +143,13 @@ static const struct genl_split_ops netdev_nl_ops[] = {
.maxattr = NETDEV_A_NAPI_IFINDEX,
.flags = GENL_CMD_CAP_DUMP,
},
+ {
+ .cmd = NETDEV_CMD_QSTATS_GET,
+ .dumpit = netdev_nl_qstats_get_dumpit,
+ .policy = netdev_qstats_get_nl_policy,
+ .maxattr = NETDEV_A_QSTATS_SCOPE,
+ .flags = GENL_CMD_CAP_DUMP,
+ },
};
static const struct genl_multicast_group netdev_nl_mcgrps[] = {
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index a47f2bcbe4..4db40fd5b4 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -28,6 +28,8 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb,
struct netlink_callback *cb);
int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info);
int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int netdev_nl_qstats_get_dumpit(struct sk_buff *skb,
+ struct netlink_callback *cb);
enum {
NETDEV_NLGRP_MGMT,
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 918b109e0c..8c2d5a0bc2 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -8,6 +8,7 @@
#include <net/xdp.h>
#include <net/xdp_sock.h>
#include <net/netdev_rx_queue.h>
+#include <net/netdev_queues.h>
#include <net/busy_poll.h>
#include "netdev-genl-gen.h"
@@ -58,22 +59,22 @@ XDP_METADATA_KFUNC_xxx
nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
xdp_rx_meta, NETDEV_A_DEV_PAD) ||
nla_put_u64_64bit(rsp, NETDEV_A_DEV_XSK_FEATURES,
- xsk_features, NETDEV_A_DEV_PAD)) {
- genlmsg_cancel(rsp, hdr);
- return -EINVAL;
- }
+ xsk_features, NETDEV_A_DEV_PAD))
+ goto err_cancel_msg;
if (netdev->xdp_features & NETDEV_XDP_ACT_XSK_ZEROCOPY) {
if (nla_put_u32(rsp, NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
- netdev->xdp_zc_max_segs)) {
- genlmsg_cancel(rsp, hdr);
- return -EINVAL;
- }
+ netdev->xdp_zc_max_segs))
+ goto err_cancel_msg;
}
genlmsg_end(rsp, hdr);
return 0;
+
+err_cancel_msg:
+ genlmsg_cancel(rsp, hdr);
+ return -EMSGSIZE;
}
static void
@@ -460,6 +461,219 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
return err;
}
+#define NETDEV_STAT_NOT_SET (~0ULL)
+
+static void netdev_nl_stats_add(void *_sum, const void *_add, size_t size)
+{
+ const u64 *add = _add;
+ u64 *sum = _sum;
+
+ while (size) {
+ if (*add != NETDEV_STAT_NOT_SET && *sum != NETDEV_STAT_NOT_SET)
+ *sum += *add;
+ sum++;
+ add++;
+ size -= 8;
+ }
+}
+
+static int netdev_stat_put(struct sk_buff *rsp, unsigned int attr_id, u64 value)
+{
+ if (value == NETDEV_STAT_NOT_SET)
+ return 0;
+ return nla_put_uint(rsp, attr_id, value);
+}
+
+static int
+netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx)
+{
+ if (netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_PACKETS, rx->packets) ||
+ netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_BYTES, rx->bytes) ||
+ netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail))
+ return -EMSGSIZE;
+ return 0;
+}
+
+static int
+netdev_nl_stats_write_tx(struct sk_buff *rsp, struct netdev_queue_stats_tx *tx)
+{
+ if (netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_PACKETS, tx->packets) ||
+ netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes))
+ return -EMSGSIZE;
+ return 0;
+}
+
+static int
+netdev_nl_stats_queue(struct net_device *netdev, struct sk_buff *rsp,
+ u32 q_type, int i, const struct genl_info *info)
+{
+ const struct netdev_stat_ops *ops = netdev->stat_ops;
+ struct netdev_queue_stats_rx rx;
+ struct netdev_queue_stats_tx tx;
+ void *hdr;
+
+ hdr = genlmsg_iput(rsp, info);
+ if (!hdr)
+ return -EMSGSIZE;
+ if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex) ||
+ nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_TYPE, q_type) ||
+ nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_ID, i))
+ goto nla_put_failure;
+
+ switch (q_type) {
+ case NETDEV_QUEUE_TYPE_RX:
+ memset(&rx, 0xff, sizeof(rx));
+ ops->get_queue_stats_rx(netdev, i, &rx);
+ if (!memchr_inv(&rx, 0xff, sizeof(rx)))
+ goto nla_cancel;
+ if (netdev_nl_stats_write_rx(rsp, &rx))
+ goto nla_put_failure;
+ break;
+ case NETDEV_QUEUE_TYPE_TX:
+ memset(&tx, 0xff, sizeof(tx));
+ ops->get_queue_stats_tx(netdev, i, &tx);
+ if (!memchr_inv(&tx, 0xff, sizeof(tx)))
+ goto nla_cancel;
+ if (netdev_nl_stats_write_tx(rsp, &tx))
+ goto nla_put_failure;
+ break;
+ }
+
+ genlmsg_end(rsp, hdr);
+ return 0;
+
+nla_cancel:
+ genlmsg_cancel(rsp, hdr);
+ return 0;
+nla_put_failure:
+ genlmsg_cancel(rsp, hdr);
+ return -EMSGSIZE;
+}
+
+static int
+netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp,
+ const struct genl_info *info,
+ struct netdev_nl_dump_ctx *ctx)
+{
+ const struct netdev_stat_ops *ops = netdev->stat_ops;
+ int i, err;
+
+ if (!(netdev->flags & IFF_UP))
+ return 0;
+
+ i = ctx->rxq_idx;
+ while (ops->get_queue_stats_rx && i < netdev->real_num_rx_queues) {
+ err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_RX,
+ i, info);
+ if (err)
+ return err;
+ ctx->rxq_idx = i++;
+ }
+ i = ctx->txq_idx;
+ while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) {
+ err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_TX,
+ i, info);
+ if (err)
+ return err;
+ ctx->txq_idx = i++;
+ }
+
+ ctx->rxq_idx = 0;
+ ctx->txq_idx = 0;
+ return 0;
+}
+
+static int
+netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp,
+ const struct genl_info *info)
+{
+ struct netdev_queue_stats_rx rx_sum, rx;
+ struct netdev_queue_stats_tx tx_sum, tx;
+ const struct netdev_stat_ops *ops;
+ void *hdr;
+ int i;
+
+ ops = netdev->stat_ops;
+ /* Netdev can't guarantee any complete counters */
+ if (!ops->get_base_stats)
+ return 0;
+
+ memset(&rx_sum, 0xff, sizeof(rx_sum));
+ memset(&tx_sum, 0xff, sizeof(tx_sum));
+
+ ops->get_base_stats(netdev, &rx_sum, &tx_sum);
+
+ /* The op was there, but nothing reported, don't bother */
+ if (!memchr_inv(&rx_sum, 0xff, sizeof(rx_sum)) &&
+ !memchr_inv(&tx_sum, 0xff, sizeof(tx_sum)))
+ return 0;
+
+ hdr = genlmsg_iput(rsp, info);
+ if (!hdr)
+ return -EMSGSIZE;
+ if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex))
+ goto nla_put_failure;
+
+ for (i = 0; i < netdev->real_num_rx_queues; i++) {
+ memset(&rx, 0xff, sizeof(rx));
+ if (ops->get_queue_stats_rx)
+ ops->get_queue_stats_rx(netdev, i, &rx);
+ netdev_nl_stats_add(&rx_sum, &rx, sizeof(rx));
+ }
+ for (i = 0; i < netdev->real_num_tx_queues; i++) {
+ memset(&tx, 0xff, sizeof(tx));
+ if (ops->get_queue_stats_tx)
+ ops->get_queue_stats_tx(netdev, i, &tx);
+ netdev_nl_stats_add(&tx_sum, &tx, sizeof(tx));
+ }
+
+ if (netdev_nl_stats_write_rx(rsp, &rx_sum) ||
+ netdev_nl_stats_write_tx(rsp, &tx_sum))
+ goto nla_put_failure;
+
+ genlmsg_end(rsp, hdr);
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(rsp, hdr);
+ return -EMSGSIZE;
+}
+
+int netdev_nl_qstats_get_dumpit(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb);
+ const struct genl_info *info = genl_info_dump(cb);
+ struct net *net = sock_net(skb->sk);
+ struct net_device *netdev;
+ unsigned int scope;
+ int err = 0;
+
+ scope = 0;
+ if (info->attrs[NETDEV_A_QSTATS_SCOPE])
+ scope = nla_get_uint(info->attrs[NETDEV_A_QSTATS_SCOPE]);
+
+ rtnl_lock();
+ for_each_netdev_dump(net, netdev, ctx->ifindex) {
+ if (!netdev->stat_ops)
+ continue;
+
+ switch (scope) {
+ case 0:
+ err = netdev_nl_stats_by_netdev(netdev, skb, info);
+ break;
+ case NETDEV_QSTATS_SCOPE_QUEUE:
+ err = netdev_nl_stats_by_queue(netdev, skb, info, ctx);
+ break;
+ }
+ if (err < 0)
+ break;
+ }
+ rtnl_unlock();
+
+ return err;
+}
+
static int netdev_genl_netdevice_event(struct notifier_block *nb,
unsigned long event, void *ptr)
{
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 543007f159..55bcacf67d 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -316,7 +316,7 @@ static int netpoll_owner_active(struct net_device *dev)
struct napi_struct *napi;
list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) {
- if (napi->poll_owner == smp_processor_id())
+ if (READ_ONCE(napi->poll_owner) == smp_processor_id())
return 1;
}
return 0;
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 4933762e5a..dd364d738c 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -31,6 +31,8 @@
#define BIAS_MAX (LONG_MAX >> 1)
#ifdef CONFIG_PAGE_POOL_STATS
+static DEFINE_PER_CPU(struct page_pool_recycle_stats, pp_system_recycle_stats);
+
/* alloc_stat_inc is intended to be used in softirq context */
#define alloc_stat_inc(pool, __stat) (pool->alloc_stats.__stat++)
/* recycle_stat_inc is safe to use when preemption is possible. */
@@ -171,13 +173,16 @@ static void page_pool_producer_unlock(struct page_pool *pool,
}
static int page_pool_init(struct page_pool *pool,
- const struct page_pool_params *params)
+ const struct page_pool_params *params,
+ int cpuid)
{
unsigned int ring_qsize = 1024; /* Default */
memcpy(&pool->p, &params->fast, sizeof(pool->p));
memcpy(&pool->slow, &params->slow, sizeof(pool->slow));
+ pool->cpuid = cpuid;
+
/* Validate only known flags were used */
if (pool->p.flags & ~(PP_FLAG_ALL))
return -EINVAL;
@@ -217,14 +222,23 @@ static int page_pool_init(struct page_pool *pool,
pool->has_init_callback = !!pool->slow.init_callback;
#ifdef CONFIG_PAGE_POOL_STATS
- pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats);
- if (!pool->recycle_stats)
- return -ENOMEM;
+ if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL)) {
+ pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats);
+ if (!pool->recycle_stats)
+ return -ENOMEM;
+ } else {
+ /* For system page pool instance we use a singular stats object
+ * instead of allocating a separate percpu variable for each
+ * (also percpu) page pool instance.
+ */
+ pool->recycle_stats = &pp_system_recycle_stats;
+ }
#endif
if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) {
#ifdef CONFIG_PAGE_POOL_STATS
- free_percpu(pool->recycle_stats);
+ if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL))
+ free_percpu(pool->recycle_stats);
#endif
return -ENOMEM;
}
@@ -248,15 +262,18 @@ static void page_pool_uninit(struct page_pool *pool)
put_device(pool->p.dev);
#ifdef CONFIG_PAGE_POOL_STATS
- free_percpu(pool->recycle_stats);
+ if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL))
+ free_percpu(pool->recycle_stats);
#endif
}
/**
- * page_pool_create() - create a page pool.
+ * page_pool_create_percpu() - create a page pool for a given cpu.
* @params: parameters, see struct page_pool_params
+ * @cpuid: cpu identifier
*/
-struct page_pool *page_pool_create(const struct page_pool_params *params)
+struct page_pool *
+page_pool_create_percpu(const struct page_pool_params *params, int cpuid)
{
struct page_pool *pool;
int err;
@@ -265,7 +282,7 @@ struct page_pool *page_pool_create(const struct page_pool_params *params)
if (!pool)
return ERR_PTR(-ENOMEM);
- err = page_pool_init(pool, params);
+ err = page_pool_init(pool, params, cpuid);
if (err < 0)
goto err_free;
@@ -282,6 +299,16 @@ err_free:
kfree(pool);
return ERR_PTR(err);
}
+EXPORT_SYMBOL(page_pool_create_percpu);
+
+/**
+ * page_pool_create() - create a page pool
+ * @params: parameters, see struct page_pool_params
+ */
+struct page_pool *page_pool_create(const struct page_pool_params *params)
+{
+ return page_pool_create_percpu(params, -1);
+}
EXPORT_SYMBOL(page_pool_create);
static void page_pool_return_page(struct page_pool *pool, struct page *page);
@@ -630,6 +657,11 @@ static bool page_pool_recycle_in_cache(struct page *page,
return true;
}
+static bool __page_pool_page_can_be_recycled(const struct page *page)
+{
+ return page_ref_count(page) == 1 && !page_is_pfmemalloc(page);
+}
+
/* If the page refcnt == 1, this will try to recycle the page.
* if PP_FLAG_DMA_SYNC_DEV is set, we'll try to sync the DMA area for
* the configured size min(dma_sync_size, pool->max_len).
@@ -651,7 +683,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
* page is NOT reusable when allocated when system is under
* some pressure. (page_is_pfmemalloc)
*/
- if (likely(page_ref_count(page) == 1 && !page_is_pfmemalloc(page))) {
+ if (likely(__page_pool_page_can_be_recycled(page))) {
/* Read barrier done in page_ref_count / READ_ONCE */
if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
@@ -766,7 +798,7 @@ static struct page *page_pool_drain_frag(struct page_pool *pool,
if (likely(page_pool_unref_page(page, drain_count)))
return NULL;
- if (page_ref_count(page) == 1 && !page_is_pfmemalloc(page)) {
+ if (__page_pool_page_can_be_recycled(page)) {
if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
page_pool_dma_sync_for_device(pool, page, -1);
@@ -934,8 +966,13 @@ void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
pool->xdp_mem_id = mem->id;
}
-void page_pool_unlink_napi(struct page_pool *pool)
+static void page_pool_disable_direct_recycling(struct page_pool *pool)
{
+ /* Disable direct recycling based on pool->cpuid.
+ * Paired with READ_ONCE() in napi_pp_put_page().
+ */
+ WRITE_ONCE(pool->cpuid, -1);
+
if (!pool->p.napi)
return;
@@ -947,7 +984,6 @@ void page_pool_unlink_napi(struct page_pool *pool)
WRITE_ONCE(pool->p.napi, NULL);
}
-EXPORT_SYMBOL(page_pool_unlink_napi);
void page_pool_destroy(struct page_pool *pool)
{
@@ -957,7 +993,7 @@ void page_pool_destroy(struct page_pool *pool)
if (!page_pool_put(pool))
return;
- page_pool_unlink_napi(pool);
+ page_pool_disable_direct_recycling(pool);
page_pool_free_frag(pool);
if (!page_pool_release(pool))
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 95e62235b5..74e6f9746f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -483,24 +483,15 @@ EXPORT_SYMBOL_GPL(__rtnl_link_unregister);
*/
static void rtnl_lock_unregistering_all(void)
{
- struct net *net;
- bool unregistering;
DEFINE_WAIT_FUNC(wait, woken_wake_function);
add_wait_queue(&netdev_unregistering_wq, &wait);
for (;;) {
- unregistering = false;
rtnl_lock();
/* We held write locked pernet_ops_rwsem, and parallel
* setup_net() and cleanup_net() are not possible.
*/
- for_each_net(net) {
- if (atomic_read(&net->dev_unreg_count) > 0) {
- unregistering = true;
- break;
- }
- }
- if (!unregistering)
+ if (!atomic_read(&dev_unreg_count))
break;
__rtnl_unlock();
@@ -851,9 +842,22 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
}
EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);
+void netdev_set_operstate(struct net_device *dev, int newstate)
+{
+ unsigned int old = READ_ONCE(dev->operstate);
+
+ do {
+ if (old == newstate)
+ return;
+ } while (!try_cmpxchg(&dev->operstate, &old, newstate));
+
+ netdev_state_change(dev);
+}
+EXPORT_SYMBOL(netdev_set_operstate);
+
static void set_operstate(struct net_device *dev, unsigned char transition)
{
- unsigned char operstate = dev->operstate;
+ unsigned char operstate = READ_ONCE(dev->operstate);
switch (transition) {
case IF_OPER_UP:
@@ -875,12 +879,7 @@ static void set_operstate(struct net_device *dev, unsigned char transition)
break;
}
- if (READ_ONCE(dev->operstate) != operstate) {
- write_lock(&dev_base_lock);
- WRITE_ONCE(dev->operstate, operstate);
- write_unlock(&dev_base_lock);
- netdev_state_change(dev);
- }
+ netdev_set_operstate(dev, operstate);
}
static unsigned int rtnl_dev_get_flags(const struct net_device *dev)
@@ -1456,17 +1455,18 @@ static noinline_for_stack int rtnl_fill_vf(struct sk_buff *skb,
return 0;
}
-static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
+static int rtnl_fill_link_ifmap(struct sk_buff *skb,
+ const struct net_device *dev)
{
struct rtnl_link_ifmap map;
memset(&map, 0, sizeof(map));
- map.mem_start = dev->mem_start;
- map.mem_end = dev->mem_end;
- map.base_addr = dev->base_addr;
- map.irq = dev->irq;
- map.dma = dev->dma;
- map.port = dev->if_port;
+ map.mem_start = READ_ONCE(dev->mem_start);
+ map.mem_end = READ_ONCE(dev->mem_end);
+ map.base_addr = READ_ONCE(dev->base_addr);
+ map.irq = READ_ONCE(dev->irq);
+ map.dma = READ_ONCE(dev->dma);
+ map.port = READ_ONCE(dev->if_port);
if (nla_put_64bit(skb, IFLA_MAP, sizeof(map), &map, IFLA_PAD))
return -EMSGSIZE;
@@ -1612,10 +1612,10 @@ static int put_master_ifindex(struct sk_buff *skb, struct net_device *dev)
static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev,
bool force)
{
- int ifindex = dev_get_iflink(dev);
+ int iflink = dev_get_iflink(dev);
- if (force || dev->ifindex != ifindex)
- return nla_put_u32(skb, IFLA_LINK, ifindex);
+ if (force || READ_ONCE(dev->ifindex) != iflink)
+ return nla_put_u32(skb, IFLA_LINK, iflink);
return 0;
}
@@ -1699,7 +1699,7 @@ static int rtnl_fill_alt_ifnames(struct sk_buff *skb,
struct netdev_name_node *name_node;
int count = 0;
- list_for_each_entry(name_node, &dev->name_node->list, list) {
+ list_for_each_entry_rcu(name_node, &dev->name_node->list, list) {
if (nla_put_string(skb, IFLA_ALT_IFNAME, name_node->name))
return -EMSGSIZE;
count++;
@@ -1707,6 +1707,7 @@ static int rtnl_fill_alt_ifnames(struct sk_buff *skb,
return count;
}
+/* RCU protected. */
static int rtnl_fill_prop_list(struct sk_buff *skb,
const struct net_device *dev)
{
@@ -1876,9 +1877,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
goto nla_put_failure;
}
- if (rtnl_fill_link_ifmap(skb, dev))
- goto nla_put_failure;
-
if (dev->addr_len) {
if (nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr) ||
nla_put(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast))
@@ -1928,10 +1926,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
rcu_read_lock();
if (rtnl_fill_link_af(skb, dev, ext_filter_mask))
goto nla_put_failure_rcu;
- rcu_read_unlock();
-
+ if (rtnl_fill_link_ifmap(skb, dev))
+ goto nla_put_failure_rcu;
if (rtnl_fill_prop_list(skb, dev))
- goto nla_put_failure;
+ goto nla_put_failure_rcu;
+ rcu_read_unlock();
if (dev->dev.parent &&
nla_put_string(skb, IFLA_PARENT_DEV_NAME,
@@ -2200,25 +2199,22 @@ static int rtnl_valid_dump_ifinfo_req(const struct nlmsghdr *nlh,
static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
{
+ const struct rtnl_link_ops *kind_ops = NULL;
struct netlink_ext_ack *extack = cb->extack;
const struct nlmsghdr *nlh = cb->nlh;
struct net *net = sock_net(skb->sk);
- struct net *tgt_net = net;
- int h, s_h;
- int idx = 0, s_idx;
- struct net_device *dev;
- struct hlist_head *head;
+ unsigned int flags = NLM_F_MULTI;
struct nlattr *tb[IFLA_MAX+1];
+ struct {
+ unsigned long ifindex;
+ } *ctx = (void *)cb->ctx;
+ struct net *tgt_net = net;
u32 ext_filter_mask = 0;
- const struct rtnl_link_ops *kind_ops = NULL;
- unsigned int flags = NLM_F_MULTI;
+ struct net_device *dev;
int master_idx = 0;
int netnsid = -1;
int err, i;
- s_h = cb->args[0];
- s_idx = cb->args[1];
-
err = rtnl_valid_dump_ifinfo_req(nlh, cb->strict_check, tb, extack);
if (err < 0) {
if (cb->strict_check)
@@ -2262,36 +2258,18 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
flags |= NLM_F_DUMP_FILTERED;
walk_entries:
- for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
- idx = 0;
- head = &tgt_net->dev_index_head[h];
- hlist_for_each_entry(dev, head, index_hlist) {
- if (link_dump_filtered(dev, master_idx, kind_ops))
- goto cont;
- if (idx < s_idx)
- goto cont;
- err = rtnl_fill_ifinfo(skb, dev, net,
- RTM_NEWLINK,
- NETLINK_CB(cb->skb).portid,
- nlh->nlmsg_seq, 0, flags,
- ext_filter_mask, 0, NULL, 0,
- netnsid, GFP_KERNEL);
-
- if (err < 0) {
- if (likely(skb->len))
- goto out;
-
- goto out_err;
- }
-cont:
- idx++;
- }
+ err = 0;
+ for_each_netdev_dump(tgt_net, dev, ctx->ifindex) {
+ if (link_dump_filtered(dev, master_idx, kind_ops))
+ continue;
+ err = rtnl_fill_ifinfo(skb, dev, net, RTM_NEWLINK,
+ NETLINK_CB(cb->skb).portid,
+ nlh->nlmsg_seq, 0, flags,
+ ext_filter_mask, 0, NULL, 0,
+ netnsid, GFP_KERNEL);
+ if (err < 0)
+ break;
}
-out:
- err = skb->len;
-out_err:
- cb->args[1] = idx;
- cb->args[0] = h;
cb->seq = tgt_net->dev_base_seq;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
if (netnsid >= 0)
@@ -2983,11 +2961,9 @@ static int do_setlink(const struct sk_buff *skb,
if (tb[IFLA_LINKMODE]) {
unsigned char value = nla_get_u8(tb[IFLA_LINKMODE]);
- write_lock(&dev_base_lock);
if (dev->link_mode ^ value)
status |= DO_SETLINK_NOTIFY;
- dev->link_mode = value;
- write_unlock(&dev_base_lock);
+ WRITE_ONCE(dev->link_mode, value);
}
if (tb[IFLA_VFINFO_LIST]) {
@@ -6508,6 +6484,46 @@ static int rtnl_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
/* Process one rtnetlink message. */
+static int rtnl_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ rtnl_dumpit_func dumpit = cb->data;
+ int err;
+
+ /* Previous iteration have already finished, avoid calling->dumpit()
+ * again, it may not expect to be called after it reached the end.
+ */
+ if (!dumpit)
+ return 0;
+
+ err = dumpit(skb, cb);
+
+ /* Old dump handlers used to send NLM_DONE as in a separate recvmsg().
+ * Some applications which parse netlink manually depend on this.
+ */
+ if (cb->flags & RTNL_FLAG_DUMP_SPLIT_NLM_DONE) {
+ if (err < 0 && err != -EMSGSIZE)
+ return err;
+ if (!err)
+ cb->data = NULL;
+
+ return skb->len;
+ }
+ return err;
+}
+
+static int rtnetlink_dump_start(struct sock *ssk, struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ struct netlink_dump_control *control)
+{
+ if (control->flags & RTNL_FLAG_DUMP_SPLIT_NLM_DONE) {
+ WARN_ON(control->data);
+ control->data = control->dump;
+ control->dump = rtnl_dumpit;
+ }
+
+ return netlink_dump_start(ssk, skb, nlh, control);
+}
+
static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
@@ -6552,6 +6568,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
}
owner = link->owner;
dumpit = link->dumpit;
+ flags = link->flags;
if (type == RTM_GETLINK - RTM_BASE)
min_dump_alloc = rtnl_calcit(skb, nlh);
@@ -6569,8 +6586,9 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
.dump = dumpit,
.min_dump_alloc = min_dump_alloc,
.module = owner,
+ .flags = flags,
};
- err = netlink_dump_start(rtnl, skb, nlh, &c);
+ err = rtnetlink_dump_start(rtnl, skb, nlh, &c);
/* netlink_dump_start() will keep a reference on
* module if dump is still in progress.
*/
@@ -6716,7 +6734,7 @@ void __init rtnetlink_init(void)
register_netdevice_notifier(&rtnetlink_dev_notifier);
rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink,
- rtnl_dump_ifinfo, 0);
+ rtnl_dump_ifinfo, RTNL_FLAG_DUMP_SPLIT_NLM_DONE);
rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, 0);
rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, 0);
rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, 0);
diff --git a/net/core/scm.c b/net/core/scm.c
index d0e0852a24..9cd4b0a01c 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -36,6 +36,7 @@
#include <net/compat.h>
#include <net/scm.h>
#include <net/cls_cgroup.h>
+#include <net/af_unix.h>
/*
@@ -85,6 +86,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
return -ENOMEM;
*fplp = fpl;
fpl->count = 0;
+ fpl->count_unix = 0;
fpl->max = SCM_MAX_FD;
fpl->user = NULL;
}
@@ -109,6 +111,9 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
fput(file);
return -EINVAL;
}
+ if (unix_get_socket(file))
+ fpl->count_unix++;
+
*fpp++ = file;
fpl->count++;
}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 570269c477..4096e679f6 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -69,6 +69,7 @@
#include <net/sock.h>
#include <net/checksum.h>
#include <net/gso.h>
+#include <net/hotdata.h>
#include <net/ip6_checksum.h>
#include <net/xfrm.h>
#include <net/mpls.h>
@@ -88,15 +89,10 @@
#include "dev.h"
#include "sock_destructor.h"
-struct kmem_cache *skbuff_cache __ro_after_init;
-static struct kmem_cache *skbuff_fclone_cache __ro_after_init;
#ifdef CONFIG_SKB_EXTENSIONS
static struct kmem_cache *skbuff_ext_cache __ro_after_init;
#endif
-
-static struct kmem_cache *skb_small_head_cache __ro_after_init;
-
#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER)
/* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two.
@@ -115,6 +111,24 @@ static struct kmem_cache *skb_small_head_cache __ro_after_init;
int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
EXPORT_SYMBOL(sysctl_max_skb_frags);
+/* kcm_write_msgs() relies on casting paged frags to bio_vec to use
+ * iov_iter_bvec(). These static asserts ensure the cast is valid is long as the
+ * netmem is a page.
+ */
+static_assert(offsetof(struct bio_vec, bv_page) ==
+ offsetof(skb_frag_t, netmem));
+static_assert(sizeof_field(struct bio_vec, bv_page) ==
+ sizeof_field(skb_frag_t, netmem));
+
+static_assert(offsetof(struct bio_vec, bv_len) == offsetof(skb_frag_t, len));
+static_assert(sizeof_field(struct bio_vec, bv_len) ==
+ sizeof_field(skb_frag_t, len));
+
+static_assert(offsetof(struct bio_vec, bv_offset) ==
+ offsetof(skb_frag_t, offset));
+static_assert(sizeof_field(struct bio_vec, bv_offset) ==
+ sizeof_field(skb_frag_t, offset));
+
#undef FN
#define FN(reason) [SKB_DROP_REASON_##reason] = #reason,
static const char * const drop_reasons[] = {
@@ -297,7 +311,8 @@ void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
fragsz = SKB_DATA_ALIGN(fragsz);
- return page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask);
+ return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
+ align_mask);
}
EXPORT_SYMBOL(__napi_alloc_frag_align);
@@ -309,13 +324,15 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
if (in_hardirq() || irqs_disabled()) {
struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache);
- data = page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align_mask);
+ data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC,
+ align_mask);
} else {
struct napi_alloc_cache *nc;
local_bh_disable();
nc = this_cpu_ptr(&napi_alloc_cache);
- data = page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask);
+ data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
+ align_mask);
local_bh_enable();
}
return data;
@@ -328,7 +345,7 @@ static struct sk_buff *napi_skb_cache_get(void)
struct sk_buff *skb;
if (unlikely(!nc->skb_count)) {
- nc->skb_count = kmem_cache_alloc_bulk(skbuff_cache,
+ nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache,
GFP_ATOMIC,
NAPI_SKB_CACHE_BULK,
nc->skb_cache);
@@ -337,7 +354,7 @@ static struct sk_buff *napi_skb_cache_get(void)
}
skb = nc->skb_cache[--nc->skb_count];
- kasan_mempool_unpoison_object(skb, kmem_cache_size(skbuff_cache));
+ kasan_mempool_unpoison_object(skb, kmem_cache_size(net_hotdata.skbuff_cache));
return skb;
}
@@ -395,7 +412,7 @@ struct sk_buff *slab_build_skb(void *data)
struct sk_buff *skb;
unsigned int size;
- skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC);
+ skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC);
if (unlikely(!skb))
return NULL;
@@ -446,7 +463,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size)
{
struct sk_buff *skb;
- skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC);
+ skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC);
if (unlikely(!skb))
return NULL;
@@ -557,7 +574,7 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
obj_size = SKB_HEAD_ALIGN(*size);
if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE &&
!(flags & KMALLOC_NOT_NORMAL_BITS)) {
- obj = kmem_cache_alloc_node(skb_small_head_cache,
+ obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache,
flags | __GFP_NOMEMALLOC | __GFP_NOWARN,
node);
*size = SKB_SMALL_HEAD_CACHE_SIZE;
@@ -565,7 +582,7 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
goto out;
/* Try again but now we are using pfmemalloc reserves */
ret_pfmemalloc = true;
- obj = kmem_cache_alloc_node(skb_small_head_cache, flags, node);
+ obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags, node);
goto out;
}
@@ -628,7 +645,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
u8 *data;
cache = (flags & SKB_ALLOC_FCLONE)
- ? skbuff_fclone_cache : skbuff_cache;
+ ? net_hotdata.skbuff_fclone_cache : net_hotdata.skbuff_cache;
if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX))
gfp_mask |= __GFP_MEMALLOC;
@@ -845,17 +862,17 @@ skb_fail:
}
EXPORT_SYMBOL(__napi_alloc_skb);
-void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
- int size, unsigned int truesize)
+void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem,
+ int off, int size, unsigned int truesize)
{
DEBUG_NET_WARN_ON_ONCE(size > truesize);
- skb_fill_page_desc(skb, i, page, off, size);
+ skb_fill_netmem_desc(skb, i, netmem, off, size);
skb->len += size;
skb->data_len += size;
skb->truesize += truesize;
}
-EXPORT_SYMBOL(skb_add_rx_frag);
+EXPORT_SYMBOL(skb_add_rx_frag_netmem);
void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size,
unsigned int truesize)
@@ -895,6 +912,98 @@ static bool is_pp_page(struct page *page)
return (page->pp_magic & ~0x3UL) == PP_SIGNATURE;
}
+int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
+ unsigned int headroom)
+{
+#if IS_ENABLED(CONFIG_PAGE_POOL)
+ u32 size, truesize, len, max_head_size, off;
+ struct sk_buff *skb = *pskb, *nskb;
+ int err, i, head_off;
+ void *data;
+
+ /* XDP does not support fraglist so we need to linearize
+ * the skb.
+ */
+ if (skb_has_frag_list(skb))
+ return -EOPNOTSUPP;
+
+ max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE - headroom);
+ if (skb->len > max_head_size + MAX_SKB_FRAGS * PAGE_SIZE)
+ return -ENOMEM;
+
+ size = min_t(u32, skb->len, max_head_size);
+ truesize = SKB_HEAD_ALIGN(size) + headroom;
+ data = page_pool_dev_alloc_va(pool, &truesize);
+ if (!data)
+ return -ENOMEM;
+
+ nskb = napi_build_skb(data, truesize);
+ if (!nskb) {
+ page_pool_free_va(pool, data, true);
+ return -ENOMEM;
+ }
+
+ skb_reserve(nskb, headroom);
+ skb_copy_header(nskb, skb);
+ skb_mark_for_recycle(nskb);
+
+ err = skb_copy_bits(skb, 0, nskb->data, size);
+ if (err) {
+ consume_skb(nskb);
+ return err;
+ }
+ skb_put(nskb, size);
+
+ head_off = skb_headroom(nskb) - skb_headroom(skb);
+ skb_headers_offset_update(nskb, head_off);
+
+ off = size;
+ len = skb->len - off;
+ for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) {
+ struct page *page;
+ u32 page_off;
+
+ size = min_t(u32, len, PAGE_SIZE);
+ truesize = size;
+
+ page = page_pool_dev_alloc(pool, &page_off, &truesize);
+ if (!page) {
+ consume_skb(nskb);
+ return -ENOMEM;
+ }
+
+ skb_add_rx_frag(nskb, i, page, page_off, size, truesize);
+ err = skb_copy_bits(skb, off, page_address(page) + page_off,
+ size);
+ if (err) {
+ consume_skb(nskb);
+ return err;
+ }
+
+ len -= size;
+ off += size;
+ }
+
+ consume_skb(skb);
+ *pskb = nskb;
+
+ return 0;
+#else
+ return -EOPNOTSUPP;
+#endif
+}
+EXPORT_SYMBOL(skb_pp_cow_data);
+
+int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
+ struct bpf_prog *prog)
+{
+ if (!prog->aux->xdp_has_frags)
+ return -EINVAL;
+
+ return skb_pp_cow_data(pool, pskb, XDP_PACKET_HEADROOM);
+}
+EXPORT_SYMBOL(skb_cow_data_for_xdp);
+
#if IS_ENABLED(CONFIG_PAGE_POOL)
bool napi_pp_put_page(struct page *page, bool napi_safe)
{
@@ -923,9 +1032,10 @@ bool napi_pp_put_page(struct page *page, bool napi_safe)
*/
if (napi_safe || in_softirq()) {
const struct napi_struct *napi = READ_ONCE(pp->p.napi);
+ unsigned int cpuid = smp_processor_id();
- allow_direct = napi &&
- READ_ONCE(napi->list_owner) == smp_processor_id();
+ allow_direct = napi && READ_ONCE(napi->list_owner) == cpuid;
+ allow_direct |= READ_ONCE(pp->cpuid) == cpuid;
}
/* Driver set this to memory recycling info. Reset it on recycle.
@@ -981,7 +1091,7 @@ static int skb_pp_frag_ref(struct sk_buff *skb)
static void skb_kfree_head(void *head, unsigned int end_offset)
{
if (end_offset == SKB_SMALL_HEAD_HEADROOM)
- kmem_cache_free(skb_small_head_cache, head);
+ kmem_cache_free(net_hotdata.skb_small_head_cache, head);
else
kfree(head);
}
@@ -1005,9 +1115,7 @@ static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason,
struct skb_shared_info *shinfo = skb_shinfo(skb);
int i;
- if (skb->cloned &&
- atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
- &shinfo->dataref))
+ if (!skb_data_unref(skb, shinfo))
goto exit;
if (skb_zcopy(skb)) {
@@ -1048,7 +1156,7 @@ static void kfree_skbmem(struct sk_buff *skb)
switch (skb->fclone) {
case SKB_FCLONE_UNAVAILABLE:
- kmem_cache_free(skbuff_cache, skb);
+ kmem_cache_free(net_hotdata.skbuff_cache, skb);
return;
case SKB_FCLONE_ORIG:
@@ -1069,7 +1177,7 @@ static void kfree_skbmem(struct sk_buff *skb)
if (!refcount_dec_and_test(&fclones->fclone_ref))
return;
fastpath:
- kmem_cache_free(skbuff_fclone_cache, fclones);
+ kmem_cache_free(net_hotdata.skbuff_fclone_cache, fclones);
}
void skb_release_head_state(struct sk_buff *skb)
@@ -1166,7 +1274,7 @@ static void kfree_skb_add_bulk(struct sk_buff *skb,
sa->skb_array[sa->skb_count++] = skb;
if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) {
- kmem_cache_free_bulk(skbuff_cache, KFREE_SKB_BULK_SIZE,
+ kmem_cache_free_bulk(net_hotdata.skbuff_cache, KFREE_SKB_BULK_SIZE,
sa->skb_array);
sa->skb_count = 0;
}
@@ -1191,7 +1299,7 @@ kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason)
}
if (sa.skb_count)
- kmem_cache_free_bulk(skbuff_cache, sa.skb_count, sa.skb_array);
+ kmem_cache_free_bulk(net_hotdata.skbuff_cache, sa.skb_count, sa.skb_array);
}
EXPORT_SYMBOL(kfree_skb_list_reason);
@@ -1353,9 +1461,9 @@ static void napi_skb_cache_put(struct sk_buff *skb)
if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) {
for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++)
kasan_mempool_unpoison_object(nc->skb_cache[i],
- kmem_cache_size(skbuff_cache));
+ kmem_cache_size(net_hotdata.skbuff_cache));
- kmem_cache_free_bulk(skbuff_cache, NAPI_SKB_CACHE_HALF,
+ kmem_cache_free_bulk(net_hotdata.skbuff_cache, NAPI_SKB_CACHE_HALF,
nc->skb_cache + NAPI_SKB_CACHE_HALF);
nc->skb_count = NAPI_SKB_CACHE_HALF;
}
@@ -1906,10 +2014,11 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
/* skb frags point to kernel buffers */
for (i = 0; i < new_frags - 1; i++) {
- __skb_fill_page_desc(skb, i, head, 0, psize);
+ __skb_fill_netmem_desc(skb, i, page_to_netmem(head), 0, psize);
head = (struct page *)page_private(head);
}
- __skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off);
+ __skb_fill_netmem_desc(skb, new_frags - 1, page_to_netmem(head), 0,
+ d_off);
skb_shinfo(skb)->nr_frags = new_frags;
release:
@@ -1951,7 +2060,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
if (skb_pfmemalloc(skb))
gfp_mask |= __GFP_MEMALLOC;
- n = kmem_cache_alloc(skbuff_cache, gfp_mask);
+ n = kmem_cache_alloc(net_hotdata.skbuff_cache, gfp_mask);
if (!n)
return NULL;
@@ -3658,7 +3767,8 @@ skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen)
if (plen) {
page = virt_to_head_page(from->head);
offset = from->data - (unsigned char *)page_address(page);
- __skb_fill_page_desc(to, 0, page, offset, plen);
+ __skb_fill_netmem_desc(to, 0, page_to_netmem(page),
+ offset, plen);
get_page(page);
j = 1;
len -= plen;
@@ -4900,7 +5010,7 @@ static void skb_extensions_init(void) {}
void __init skb_init(void)
{
- skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache",
+ net_hotdata.skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache",
sizeof(struct sk_buff),
0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|
@@ -4908,7 +5018,7 @@ void __init skb_init(void)
offsetof(struct sk_buff, cb),
sizeof_field(struct sk_buff, cb),
NULL);
- skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache",
+ net_hotdata.skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache",
sizeof(struct sk_buff_fclones),
0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC,
@@ -4917,7 +5027,7 @@ void __init skb_init(void)
* struct skb_shared_info is located at the end of skb->head,
* and should not be copied to/from user.
*/
- skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head",
+ net_hotdata.skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head",
SKB_SMALL_HEAD_CACHE_SIZE,
0,
SLAB_HWCACHE_ALIGN | SLAB_PANIC,
@@ -5790,7 +5900,7 @@ void kfree_skb_partial(struct sk_buff *skb, bool head_stolen)
{
if (head_stolen) {
skb_release_head_state(skb);
- kmem_cache_free(skbuff_cache, skb);
+ kmem_cache_free(net_hotdata.skbuff_cache, skb);
} else {
__kfree_skb(skb);
}
diff --git a/net/core/sock.c b/net/core/sock.c
index 599f186fe3..09eccc9c50 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2053,8 +2053,9 @@ static void sock_copy(struct sock *nsk, const struct sock *osk)
memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin));
- memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end,
- prot->obj_size - offsetof(struct sock, sk_dontcopy_end));
+ unsafe_memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end,
+ prot->obj_size - offsetof(struct sock, sk_dontcopy_end),
+ /* alloc is larger than struct, see sk_prot_alloc() */);
#ifdef CONFIG_SECURITY_NETWORK
nsk->sk_security = sptr;
@@ -2583,8 +2584,18 @@ EXPORT_SYMBOL(sock_efree);
#ifdef CONFIG_INET
void sock_pfree(struct sk_buff *skb)
{
- if (sk_is_refcounted(skb->sk))
- sock_gen_put(skb->sk);
+ struct sock *sk = skb->sk;
+
+ if (!sk_is_refcounted(sk))
+ return;
+
+ if (sk->sk_state == TCP_NEW_SYN_RECV && inet_reqsk(sk)->syncookie) {
+ inet_reqsk(sk)->rsk_listener = NULL;
+ reqsk_free(inet_reqsk(sk));
+ return;
+ }
+
+ sock_gen_put(sk);
}
EXPORT_SYMBOL(sock_pfree);
#endif /* CONFIG_INET */
@@ -3732,6 +3743,9 @@ void sk_common_release(struct sock *sk)
sk->sk_prot->unhash(sk);
+ if (sk->sk_socket)
+ sk->sk_socket->sk = NULL;
+
/*
* In this point socket cannot receive new packets, but it is possible
* that some packets are in flight because some CPU runs receiver and
@@ -4224,3 +4238,65 @@ int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
return sock_ioctl_out(sk, cmd, arg);
}
EXPORT_SYMBOL(sk_ioctl);
+
+static int __init sock_struct_check(void)
+{
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_drops);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_peek_off);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_error_queue);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_receive_queue);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_backlog);
+
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst_ifindex);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst_cookie);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvbuf);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_filter);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_wq);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_data_ready);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvtimeo);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvlowat);
+
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_err);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_socket);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_memcg);
+
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_lock);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_reserved_mem);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_forward_alloc);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_tsflags);
+
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_omem_alloc);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_omem_alloc);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_sndbuf);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_wmem_queued);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_wmem_alloc);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_tsq_flags);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_send_head);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_queue);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_pending);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_dst_pending_confirm);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_pacing_status);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_frag);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_timer);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_pacing_rate);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_zckey);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_tskey);
+
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_max_pacing_rate);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_sndtimeo);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_priority);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_mark);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_dst_cache);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_route_caps);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_type);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_max_size);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_allocation);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_txhash);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_max_segs);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_pacing_shift);
+ CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_use_task_frag);
+ return 0;
+}
+
+core_initcall(sock_struct_check);
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index c53b731f2d..6541228380 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -16,9 +16,10 @@
#include <linux/inet_diag.h>
#include <linux/sock_diag.h>
-static const struct sock_diag_handler *sock_diag_handlers[AF_MAX];
-static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
-static DEFINE_MUTEX(sock_diag_table_mutex);
+static const struct sock_diag_handler __rcu *sock_diag_handlers[AF_MAX];
+
+static struct sock_diag_inet_compat __rcu *inet_rcv_compat;
+
static struct workqueue_struct *broadcast_wq;
DEFINE_COOKIE(sock_cookie);
@@ -122,6 +123,24 @@ static size_t sock_diag_nlmsg_size(void)
+ nla_total_size_64bit(sizeof(struct tcp_info))); /* INET_DIAG_INFO */
}
+static const struct sock_diag_handler *sock_diag_lock_handler(int family)
+{
+ const struct sock_diag_handler *handler;
+
+ rcu_read_lock();
+ handler = rcu_dereference(sock_diag_handlers[family]);
+ if (handler && !try_module_get(handler->owner))
+ handler = NULL;
+ rcu_read_unlock();
+
+ return handler;
+}
+
+static void sock_diag_unlock_handler(const struct sock_diag_handler *handler)
+{
+ module_put(handler->owner);
+}
+
static void sock_diag_broadcast_destroy_work(struct work_struct *work)
{
struct broadcast_sk *bsk =
@@ -138,12 +157,12 @@ static void sock_diag_broadcast_destroy_work(struct work_struct *work)
if (!skb)
goto out;
- mutex_lock(&sock_diag_table_mutex);
- hndl = sock_diag_handlers[sk->sk_family];
- if (hndl && hndl->get_info)
- err = hndl->get_info(skb, sk);
- mutex_unlock(&sock_diag_table_mutex);
-
+ hndl = sock_diag_lock_handler(sk->sk_family);
+ if (hndl) {
+ if (hndl->get_info)
+ err = hndl->get_info(skb, sk);
+ sock_diag_unlock_handler(hndl);
+ }
if (!err)
nlmsg_multicast(sock_net(sk)->diag_nlsk, skb, 0, group,
GFP_KERNEL);
@@ -166,51 +185,45 @@ void sock_diag_broadcast_destroy(struct sock *sk)
queue_work(broadcast_wq, &bsk->work);
}
-void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh))
+void sock_diag_register_inet_compat(const struct sock_diag_inet_compat *ptr)
{
- mutex_lock(&sock_diag_table_mutex);
- inet_rcv_compat = fn;
- mutex_unlock(&sock_diag_table_mutex);
+ xchg((__force const struct sock_diag_inet_compat **)&inet_rcv_compat,
+ ptr);
}
EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat);
-void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh))
+void sock_diag_unregister_inet_compat(const struct sock_diag_inet_compat *ptr)
{
- mutex_lock(&sock_diag_table_mutex);
- inet_rcv_compat = NULL;
- mutex_unlock(&sock_diag_table_mutex);
+ const struct sock_diag_inet_compat *old;
+
+ old = xchg((__force const struct sock_diag_inet_compat **)&inet_rcv_compat,
+ NULL);
+ WARN_ON_ONCE(old != ptr);
}
EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat);
int sock_diag_register(const struct sock_diag_handler *hndl)
{
- int err = 0;
+ int family = hndl->family;
- if (hndl->family >= AF_MAX)
+ if (family >= AF_MAX)
return -EINVAL;
- mutex_lock(&sock_diag_table_mutex);
- if (sock_diag_handlers[hndl->family])
- err = -EBUSY;
- else
- WRITE_ONCE(sock_diag_handlers[hndl->family], hndl);
- mutex_unlock(&sock_diag_table_mutex);
-
- return err;
+ return !cmpxchg((const struct sock_diag_handler **)
+ &sock_diag_handlers[family],
+ NULL, hndl) ? 0 : -EBUSY;
}
EXPORT_SYMBOL_GPL(sock_diag_register);
-void sock_diag_unregister(const struct sock_diag_handler *hnld)
+void sock_diag_unregister(const struct sock_diag_handler *hndl)
{
- int family = hnld->family;
+ int family = hndl->family;
if (family >= AF_MAX)
return;
- mutex_lock(&sock_diag_table_mutex);
- BUG_ON(sock_diag_handlers[family] != hnld);
- WRITE_ONCE(sock_diag_handlers[family], NULL);
- mutex_unlock(&sock_diag_table_mutex);
+ xchg((const struct sock_diag_handler **)&sock_diag_handlers[family],
+ NULL);
}
EXPORT_SYMBOL_GPL(sock_diag_unregister);
@@ -227,20 +240,20 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh)
return -EINVAL;
req->sdiag_family = array_index_nospec(req->sdiag_family, AF_MAX);
- if (READ_ONCE(sock_diag_handlers[req->sdiag_family]) == NULL)
+ if (!rcu_access_pointer(sock_diag_handlers[req->sdiag_family]))
sock_load_diag_module(req->sdiag_family, 0);
- mutex_lock(&sock_diag_table_mutex);
- hndl = sock_diag_handlers[req->sdiag_family];
+ hndl = sock_diag_lock_handler(req->sdiag_family);
if (hndl == NULL)
- err = -ENOENT;
- else if (nlh->nlmsg_type == SOCK_DIAG_BY_FAMILY)
+ return -ENOENT;
+
+ if (nlh->nlmsg_type == SOCK_DIAG_BY_FAMILY)
err = hndl->dump(skb, nlh);
else if (nlh->nlmsg_type == SOCK_DESTROY && hndl->destroy)
err = hndl->destroy(skb, nlh);
else
err = -EOPNOTSUPP;
- mutex_unlock(&sock_diag_table_mutex);
+ sock_diag_unlock_handler(hndl);
return err;
}
@@ -248,20 +261,27 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh)
static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
+ const struct sock_diag_inet_compat *ptr;
int ret;
switch (nlh->nlmsg_type) {
case TCPDIAG_GETSOCK:
case DCCPDIAG_GETSOCK:
- if (inet_rcv_compat == NULL)
+
+ if (!rcu_access_pointer(inet_rcv_compat))
sock_load_diag_module(AF_INET, 0);
- mutex_lock(&sock_diag_table_mutex);
- if (inet_rcv_compat != NULL)
- ret = inet_rcv_compat(skb, nlh);
- else
- ret = -EOPNOTSUPP;
- mutex_unlock(&sock_diag_table_mutex);
+ rcu_read_lock();
+ ptr = rcu_dereference(inet_rcv_compat);
+ if (ptr && !try_module_get(ptr->owner))
+ ptr = NULL;
+ rcu_read_unlock();
+
+ ret = -EOPNOTSUPP;
+ if (ptr) {
+ ret = ptr->fn(skb, nlh);
+ module_put(ptr->owner);
+ }
return ret;
case SOCK_DIAG_BY_FAMILY:
@@ -272,13 +292,9 @@ static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
}
}
-static DEFINE_MUTEX(sock_diag_mutex);
-
static void sock_diag_rcv(struct sk_buff *skb)
{
- mutex_lock(&sock_diag_mutex);
netlink_rcv_skb(skb, &sock_diag_rcv_msg);
- mutex_unlock(&sock_diag_mutex);
}
static int sock_diag_bind(struct net *net, int group)
@@ -286,12 +302,12 @@ static int sock_diag_bind(struct net *net, int group)
switch (group) {
case SKNLGRP_INET_TCP_DESTROY:
case SKNLGRP_INET_UDP_DESTROY:
- if (!READ_ONCE(sock_diag_handlers[AF_INET]))
+ if (!rcu_access_pointer(sock_diag_handlers[AF_INET]))
sock_load_diag_module(AF_INET, 0);
break;
case SKNLGRP_INET6_TCP_DESTROY:
case SKNLGRP_INET6_UDP_DESTROY:
- if (!READ_ONCE(sock_diag_handlers[AF_INET6]))
+ if (!rcu_access_pointer(sock_diag_handlers[AF_INET6]))
sock_load_diag_module(AF_INET6, 0);
break;
}
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 8598466a38..01be07b485 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1639,19 +1639,23 @@ void sock_map_close(struct sock *sk, long timeout)
lock_sock(sk);
rcu_read_lock();
- psock = sk_psock_get(sk);
- if (unlikely(!psock)) {
- rcu_read_unlock();
- release_sock(sk);
- saved_close = READ_ONCE(sk->sk_prot)->close;
- } else {
+ psock = sk_psock(sk);
+ if (likely(psock)) {
saved_close = psock->saved_close;
sock_map_remove_links(sk, psock);
+ psock = sk_psock_get(sk);
+ if (unlikely(!psock))
+ goto no_psock;
rcu_read_unlock();
sk_psock_stop(psock);
release_sock(sk);
cancel_delayed_work_sync(&psock->work);
sk_psock_put(sk, psock);
+ } else {
+ saved_close = READ_ONCE(sk->sk_prot)->close;
+no_psock:
+ rcu_read_unlock();
+ release_sock(sk);
}
/* Make sure we do not recurse. This is a bug.
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 986f15e5d6..6973dda3ab 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -23,6 +23,8 @@
#include <net/net_ratelimit.h>
#include <net/busy_poll.h>
#include <net/pkt_sched.h>
+#include <net/hotdata.h>
+#include <net/rps.h>
#include "dev.h"
@@ -138,7 +140,8 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
mutex_lock(&sock_flow_mutex);
- orig_sock_table = rcu_dereference_protected(rps_sock_flow_table,
+ orig_sock_table = rcu_dereference_protected(
+ net_hotdata.rps_sock_flow_table,
lockdep_is_held(&sock_flow_mutex));
size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0;
@@ -159,7 +162,8 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
mutex_unlock(&sock_flow_mutex);
return -ENOMEM;
}
- rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1;
+ net_hotdata.rps_cpu_mask =
+ roundup_pow_of_two(nr_cpu_ids) - 1;
sock_table->mask = size - 1;
} else
sock_table = orig_sock_table;
@@ -170,7 +174,8 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
sock_table = NULL;
if (sock_table != orig_sock_table) {
- rcu_assign_pointer(rps_sock_flow_table, sock_table);
+ rcu_assign_pointer(net_hotdata.rps_sock_flow_table,
+ sock_table);
if (sock_table) {
static_branch_inc(&rps_needed);
static_branch_inc(&rfs_needed);
@@ -300,8 +305,8 @@ static int proc_do_dev_weight(struct ctl_table *table, int write,
ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (!ret && write) {
weight = READ_ONCE(weight_p);
- WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias);
- WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias);
+ WRITE_ONCE(net_hotdata.dev_rx_weight, weight * dev_weight_rx_bias);
+ WRITE_ONCE(net_hotdata.dev_tx_weight, weight * dev_weight_tx_bias);
}
mutex_unlock(&dev_weight_mutex);
@@ -439,7 +444,7 @@ static struct ctl_table net_core_table[] = {
},
{
.procname = "netdev_max_backlog",
- .data = &netdev_max_backlog,
+ .data = &net_hotdata.max_backlog,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
@@ -498,7 +503,7 @@ static struct ctl_table net_core_table[] = {
#endif
{
.procname = "netdev_tstamp_prequeue",
- .data = &netdev_tstamp_prequeue,
+ .data = &net_hotdata.tstamp_prequeue,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
@@ -576,7 +581,7 @@ static struct ctl_table net_core_table[] = {
#endif
{
.procname = "netdev_budget",
- .data = &netdev_budget,
+ .data = &net_hotdata.netdev_budget,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
@@ -599,7 +604,7 @@ static struct ctl_table net_core_table[] = {
},
{
.procname = "netdev_budget_usecs",
- .data = &netdev_budget_usecs,
+ .data = &net_hotdata.netdev_budget_usecs,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
@@ -632,7 +637,7 @@ static struct ctl_table net_core_table[] = {
},
{
.procname = "gro_normal_batch",
- .data = &gro_normal_batch,
+ .data = &net_hotdata.gro_normal_batch,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 4869c1c2d8..41693154e4 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -16,6 +16,7 @@
#include <linux/bug.h>
#include <net/page_pool/helpers.h>
+#include <net/hotdata.h>
#include <net/xdp.h>
#include <net/xdp_priv.h> /* struct xdp_mem_allocator */
#include <trace/events/xdp.h>
@@ -75,7 +76,7 @@ static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu)
xa = container_of(rcu, struct xdp_mem_allocator, rcu);
/* Allow this ID to be reused */
- ida_simple_remove(&mem_id_pool, xa->mem.id);
+ ida_free(&mem_id_pool, xa->mem.id);
kfree(xa);
}
@@ -242,7 +243,7 @@ static int __mem_id_cyclic_get(gfp_t gfp)
int id;
again:
- id = ida_simple_get(&mem_id_pool, mem_id_next, MEM_ID_MAX, gfp);
+ id = ida_alloc_range(&mem_id_pool, mem_id_next, MEM_ID_MAX - 1, gfp);
if (id < 0) {
if (id == -ENOSPC) {
/* Cyclic allocator, reset next id */
@@ -317,7 +318,7 @@ static struct xdp_mem_allocator *__xdp_reg_mem_model(struct xdp_mem_info *mem,
/* Insert allocator into ID lookup table */
ptr = rhashtable_insert_slow(mem_id_ht, &id, &xdp_alloc->node);
if (IS_ERR(ptr)) {
- ida_simple_remove(&mem_id_pool, mem->id);
+ ida_free(&mem_id_pool, mem->id);
mem->id = 0;
errno = PTR_ERR(ptr);
goto err;
@@ -589,7 +590,7 @@ EXPORT_SYMBOL_GPL(xdp_warn);
int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp)
{
- n_skb = kmem_cache_alloc_bulk(skbuff_cache, gfp, n_skb, skbs);
+ n_skb = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, gfp, n_skb, skbs);
if (unlikely(!n_skb))
return -ENOMEM;
@@ -658,7 +659,7 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
{
struct sk_buff *skb;
- skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC);
+ skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC);
if (unlikely(!skb))
return NULL;
@@ -771,11 +772,11 @@ __bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
__bpf_kfunc_end_defs();
-BTF_SET8_START(xdp_metadata_kfunc_ids)
+BTF_KFUNCS_START(xdp_metadata_kfunc_ids)
#define XDP_METADATA_KFUNC(_, __, name, ___) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS)
XDP_METADATA_KFUNC_xxx
#undef XDP_METADATA_KFUNC
-BTF_SET8_END(xdp_metadata_kfunc_ids)
+BTF_KFUNCS_END(xdp_metadata_kfunc_ids)
static const struct btf_kfunc_id_set xdp_metadata_kfunc_set = {
.owner = THIS_MODULE,