summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-12-16 00:22:29 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2020-12-16 00:22:29 +0300
commitd635a69dd4981cc51f90293f5f64268620ed1565 (patch)
tree5e0a758b402ea7d624c25c3a343545dd29e80f31 /net/core
parentac73e3dc8acd0a3be292755db30388c3580f5674 (diff)
parentefd5a1584537698220578227e6467638307c2a0b (diff)
downloadlinux-d635a69dd4981cc51f90293f5f64268620ed1565.tar.xz
Merge tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Core: - support "prefer busy polling" NAPI operation mode, where we defer softirq for some time expecting applications to periodically busy poll - AF_XDP: improve efficiency by more batching and hindering the adjacency cache prefetcher - af_packet: make packet_fanout.arr size configurable up to 64K - tcp: optimize TCP zero copy receive in presence of partial or unaligned reads making zero copy a performance win for much smaller messages - XDP: add bulk APIs for returning / freeing frames - sched: support fragmenting IP packets as they come out of conntrack - net: allow virtual netdevs to forward UDP L4 and fraglist GSO skbs BPF: - BPF switch from crude rlimit-based to memcg-based memory accounting - BPF type format information for kernel modules and related tracing enhancements - BPF implement task local storage for BPF LSM - allow the FENTRY/FEXIT/RAW_TP tracing programs to use bpf_sk_storage Protocols: - mptcp: improve multiple xmit streams support, memory accounting and many smaller improvements - TLS: support CHACHA20-POLY1305 cipher - seg6: add support for SRv6 End.DT4/DT6 behavior - sctp: Implement RFC 6951: UDP Encapsulation of SCTP - ppp_generic: add ability to bridge channels directly - bridge: Connectivity Fault Management (CFM) support as is defined in IEEE 802.1Q section 12.14. Drivers: - mlx5: make use of the new auxiliary bus to organize the driver internals - mlx5: more accurate port TX timestamping support - mlxsw: - improve the efficiency of offloaded next hop updates by using the new nexthop object API - support blackhole nexthops - support IEEE 802.1ad (Q-in-Q) bridging - rtw88: major bluetooth co-existance improvements - iwlwifi: support new 6 GHz frequency band - ath11k: Fast Initial Link Setup (FILS) - mt7915: dual band concurrent (DBDC) support - net: ipa: add basic support for IPA v4.5 Refactor: - a few pieces of in_interrupt() cleanup work from Sebastian Andrzej Siewior - phy: add support for shared interrupts; get rid of multiple driver APIs and have the drivers write a full IRQ handler, slight growth of driver code should be compensated by the simpler API which also allows shared IRQs - add common code for handling netdev per-cpu counters - move TX packet re-allocation from Ethernet switch tag drivers to a central place - improve efficiency and rename nla_strlcpy - number of W=1 warning cleanups as we now catch those in a patchwork build bot Old code removal: - wan: delete the DLCI / SDLA drivers - wimax: move to staging - wifi: remove old WDS wifi bridging support" * tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1922 commits) net: hns3: fix expression that is currently always true net: fix proc_fs init handling in af_packet and tls nfc: pn533: convert comma to semicolon af_vsock: Assign the vsock transport considering the vsock address flags af_vsock: Set VMADDR_FLAG_TO_HOST flag on the receive path vsock_addr: Check for supported flag values vm_sockets: Add VMADDR_FLAG_TO_HOST vsock flag vm_sockets: Add flags field in the vsock address data structure net: Disable NETIF_F_HW_TLS_TX when HW_CSUM is disabled tcp: Add logic to check for SYN w/ data in tcp_simple_retransmit net: mscc: ocelot: install MAC addresses in .ndo_set_rx_mode from process context nfc: s3fwrn5: Release the nfc firmware net: vxget: clean up sparse warnings mlxsw: spectrum_router: Use eXtended mezzanine to offload IPv4 router mlxsw: spectrum: Set KVH XLT cache mode for Spectrum2/3 mlxsw: spectrum_router_xm: Introduce basic XM cache flushing mlxsw: reg: Add Router LPM Cache Enable Register mlxsw: reg: Add Router LPM Cache ML Delete Register mlxsw: spectrum_router_xm: Implement L-value tracking for M-index mlxsw: reg: Add XM Router M Table Register ...
Diffstat (limited to 'net/core')
-rw-r--r--net/core/bpf_sk_storage.c136
-rw-r--r--net/core/datagram.c2
-rw-r--r--net/core/dev.c137
-rw-r--r--net/core/dev_ioctl.c2
-rw-r--r--net/core/devlink.c44
-rw-r--r--net/core/fib_rules.c4
-rw-r--r--net/core/filter.c25
-rw-r--r--net/core/flow_dissector.c2
-rw-r--r--net/core/netclassid_cgroup.c3
-rw-r--r--net/core/netprio_cgroup.c3
-rw-r--r--net/core/page_pool.c70
-rw-r--r--net/core/rtnetlink.c36
-rw-r--r--net/core/skbuff.c18
-rw-r--r--net/core/sock.c32
-rw-r--r--net/core/sock_map.c42
-rw-r--r--net/core/xdp.c57
16 files changed, 449 insertions, 164 deletions
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index c907f0dc7f87..4edd033e899c 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -6,6 +6,7 @@
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/bpf.h>
+#include <linux/btf.h>
#include <linux/btf_ids.h>
#include <linux/bpf_local_storage.h>
#include <net/bpf_sk_storage.h>
@@ -15,20 +16,8 @@
DEFINE_BPF_STORAGE_CACHE(sk_cache);
-static int omem_charge(struct sock *sk, unsigned int size)
-{
- /* same check as in sock_kmalloc() */
- if (size <= sysctl_optmem_max &&
- atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
- atomic_add(size, &sk->sk_omem_alloc);
- return 0;
- }
-
- return -ENOMEM;
-}
-
static struct bpf_local_storage_data *
-sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
+bpf_sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
{
struct bpf_local_storage *sk_storage;
struct bpf_local_storage_map *smap;
@@ -41,11 +30,11 @@ sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit);
}
-static int sk_storage_delete(struct sock *sk, struct bpf_map *map)
+static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map)
{
struct bpf_local_storage_data *sdata;
- sdata = sk_storage_lookup(sk, map, false);
+ sdata = bpf_sk_storage_lookup(sk, map, false);
if (!sdata)
return -ENOENT;
@@ -94,7 +83,7 @@ void bpf_sk_storage_free(struct sock *sk)
kfree_rcu(sk_storage, rcu);
}
-static void sk_storage_map_free(struct bpf_map *map)
+static void bpf_sk_storage_map_free(struct bpf_map *map)
{
struct bpf_local_storage_map *smap;
@@ -103,7 +92,7 @@ static void sk_storage_map_free(struct bpf_map *map)
bpf_local_storage_map_free(smap);
}
-static struct bpf_map *sk_storage_map_alloc(union bpf_attr *attr)
+static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
{
struct bpf_local_storage_map *smap;
@@ -130,7 +119,7 @@ static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
fd = *(int *)key;
sock = sockfd_lookup(fd, &err);
if (sock) {
- sdata = sk_storage_lookup(sock->sk, map, true);
+ sdata = bpf_sk_storage_lookup(sock->sk, map, true);
sockfd_put(sock);
return sdata ? sdata->data : NULL;
}
@@ -166,7 +155,7 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key)
fd = *(int *)key;
sock = sockfd_lookup(fd, &err);
if (sock) {
- err = sk_storage_delete(sock->sk, map);
+ err = bpf_sk_storage_del(sock->sk, map);
sockfd_put(sock);
return err;
}
@@ -272,7 +261,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE)
return (unsigned long)NULL;
- sdata = sk_storage_lookup(sk, map, true);
+ sdata = bpf_sk_storage_lookup(sk, map, true);
if (sdata)
return (unsigned long)sdata->data;
@@ -305,7 +294,7 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
if (refcount_inc_not_zero(&sk->sk_refcnt)) {
int err;
- err = sk_storage_delete(sk, map);
+ err = bpf_sk_storage_del(sk, map);
sock_put(sk);
return err;
}
@@ -313,14 +302,23 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
return -ENOENT;
}
-static int sk_storage_charge(struct bpf_local_storage_map *smap,
- void *owner, u32 size)
+static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap,
+ void *owner, u32 size)
{
- return omem_charge(owner, size);
+ struct sock *sk = (struct sock *)owner;
+
+ /* same check as in sock_kmalloc() */
+ if (size <= sysctl_optmem_max &&
+ atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+ atomic_add(size, &sk->sk_omem_alloc);
+ return 0;
+ }
+
+ return -ENOMEM;
}
-static void sk_storage_uncharge(struct bpf_local_storage_map *smap,
- void *owner, u32 size)
+static void bpf_sk_storage_uncharge(struct bpf_local_storage_map *smap,
+ void *owner, u32 size)
{
struct sock *sk = owner;
@@ -328,7 +326,7 @@ static void sk_storage_uncharge(struct bpf_local_storage_map *smap,
}
static struct bpf_local_storage __rcu **
-sk_storage_ptr(void *owner)
+bpf_sk_storage_ptr(void *owner)
{
struct sock *sk = owner;
@@ -339,8 +337,8 @@ static int sk_storage_map_btf_id;
const struct bpf_map_ops sk_storage_map_ops = {
.map_meta_equal = bpf_map_meta_equal,
.map_alloc_check = bpf_local_storage_map_alloc_check,
- .map_alloc = sk_storage_map_alloc,
- .map_free = sk_storage_map_free,
+ .map_alloc = bpf_sk_storage_map_alloc,
+ .map_free = bpf_sk_storage_map_free,
.map_get_next_key = notsupp_get_next_key,
.map_lookup_elem = bpf_fd_sk_storage_lookup_elem,
.map_update_elem = bpf_fd_sk_storage_update_elem,
@@ -348,9 +346,9 @@ const struct bpf_map_ops sk_storage_map_ops = {
.map_check_btf = bpf_local_storage_map_check_btf,
.map_btf_name = "bpf_local_storage_map",
.map_btf_id = &sk_storage_map_btf_id,
- .map_local_storage_charge = sk_storage_charge,
- .map_local_storage_uncharge = sk_storage_uncharge,
- .map_owner_storage_ptr = sk_storage_ptr,
+ .map_local_storage_charge = bpf_sk_storage_charge,
+ .map_local_storage_uncharge = bpf_sk_storage_uncharge,
+ .map_owner_storage_ptr = bpf_sk_storage_ptr,
};
const struct bpf_func_proto bpf_sk_storage_get_proto = {
@@ -381,6 +379,80 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = {
.arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
};
+static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog)
+{
+ const struct btf *btf_vmlinux;
+ const struct btf_type *t;
+ const char *tname;
+ u32 btf_id;
+
+ if (prog->aux->dst_prog)
+ return false;
+
+ /* Ensure the tracing program is not tracing
+ * any bpf_sk_storage*() function and also
+ * use the bpf_sk_storage_(get|delete) helper.
+ */
+ switch (prog->expected_attach_type) {
+ case BPF_TRACE_ITER:
+ case BPF_TRACE_RAW_TP:
+ /* bpf_sk_storage has no trace point */
+ return true;
+ case BPF_TRACE_FENTRY:
+ case BPF_TRACE_FEXIT:
+ btf_vmlinux = bpf_get_btf_vmlinux();
+ btf_id = prog->aux->attach_btf_id;
+ t = btf_type_by_id(btf_vmlinux, btf_id);
+ tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+ return !!strncmp(tname, "bpf_sk_storage",
+ strlen("bpf_sk_storage"));
+ default:
+ return false;
+ }
+
+ return false;
+}
+
+BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk,
+ void *, value, u64, flags)
+{
+ if (in_irq() || in_nmi())
+ return (unsigned long)NULL;
+
+ return (unsigned long)____bpf_sk_storage_get(map, sk, value, flags);
+}
+
+BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map,
+ struct sock *, sk)
+{
+ if (in_irq() || in_nmi())
+ return -EPERM;
+
+ return ____bpf_sk_storage_delete(map, sk);
+}
+
+const struct bpf_func_proto bpf_sk_storage_get_tracing_proto = {
+ .func = bpf_sk_storage_get_tracing,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+ .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg4_type = ARG_ANYTHING,
+ .allowed = bpf_sk_storage_tracing_allowed,
+};
+
+const struct bpf_func_proto bpf_sk_storage_delete_tracing_proto = {
+ .func = bpf_sk_storage_delete_tracing,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+ .allowed = bpf_sk_storage_tracing_allowed,
+};
+
struct bpf_sk_storage_diag {
u32 nr_maps;
struct bpf_map *maps[];
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 9fcaa544f11a..81809fa735a7 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -709,7 +709,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
EXPORT_SYMBOL(zerocopy_sg_from_iter);
/**
- * skb_copy_and_csum_datagram_iter - Copy datagram to an iovec iterator
+ * skb_copy_and_csum_datagram - Copy datagram to an iovec iterator
* and update a checksum.
* @skb: buffer to copy
* @offset: offset in the buffer to start copying from
diff --git a/net/core/dev.c b/net/core/dev.c
index ac7a7ae4614a..a46334906c94 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1069,19 +1069,6 @@ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
}
EXPORT_SYMBOL(dev_getbyhwaddr_rcu);
-struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type)
-{
- struct net_device *dev;
-
- ASSERT_RTNL();
- for_each_netdev(net, dev)
- if (dev->type == type)
- return dev;
-
- return NULL;
-}
-EXPORT_SYMBOL(__dev_getfirstbyhwtype);
-
struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
{
struct net_device *dev, *ret = NULL;
@@ -3206,7 +3193,7 @@ int skb_checksum_help(struct sk_buff *skb)
if (skb->ip_summed == CHECKSUM_COMPLETE)
goto out_set_summed;
- if (unlikely(skb_shinfo(skb)->gso_size)) {
+ if (unlikely(skb_is_gso(skb))) {
skb_warn_bad_offload(skb);
return -EINVAL;
}
@@ -3495,6 +3482,11 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
if (gso_segs > dev->gso_max_segs)
return features & ~NETIF_F_GSO_MASK;
+ if (!skb_shinfo(skb)->gso_type) {
+ skb_warn_bad_offload(skb);
+ return features & ~NETIF_F_GSO_MASK;
+ }
+
/* Support for GSO partial features requires software
* intervention before we can actually process the packets
* so we need to strip support for any partial features now
@@ -3867,6 +3859,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
return skb;
/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
+ qdisc_skb_cb(skb)->mru = 0;
mini_qdisc_bstats_cpu_update(miniq, skb);
switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) {
@@ -4950,6 +4943,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
}
qdisc_skb_cb(skb)->pkt_len = skb->len;
+ qdisc_skb_cb(skb)->mru = 0;
skb->tc_at_ingress = 1;
mini_qdisc_bstats_cpu_update(miniq, skb);
@@ -6454,7 +6448,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
- new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED);
+ new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED |
+ NAPIF_STATE_PREFER_BUSY_POLL);
/* If STATE_MISSED was set, leave STATE_SCHED set,
* because we will call napi->poll() one more time.
@@ -6491,10 +6486,30 @@ static struct napi_struct *napi_by_id(unsigned int napi_id)
#if defined(CONFIG_NET_RX_BUSY_POLL)
-#define BUSY_POLL_BUDGET 8
+static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
+{
+ if (!skip_schedule) {
+ gro_normal_list(napi);
+ __napi_schedule(napi);
+ return;
+ }
-static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
+ if (napi->gro_bitmask) {
+ /* flush too old packets
+ * If HZ < 1000, flush all packets.
+ */
+ napi_gro_flush(napi, HZ >= 1000);
+ }
+
+ gro_normal_list(napi);
+ 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)
{
+ bool skip_schedule = false;
+ unsigned long timeout;
int rc;
/* Busy polling means there is a high chance device driver hard irq
@@ -6511,29 +6526,33 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
local_bh_disable();
+ if (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) {
+ hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED);
+ skip_schedule = true;
+ }
+ }
+
/* All we really want here is to re-enable device interrupts.
* Ideally, a new ndo_busy_poll_stop() could avoid another round.
*/
- rc = napi->poll(napi, BUSY_POLL_BUDGET);
+ rc = napi->poll(napi, budget);
/* We can't gro_normal_list() here, because napi->poll() might have
* rearmed the napi (napi_complete_done()) in which case it could
* already be running on another CPU.
*/
- trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
+ trace_napi_poll(napi, rc, budget);
netpoll_poll_unlock(have_poll_lock);
- if (rc == BUSY_POLL_BUDGET) {
- /* As the whole budget was spent, we still own the napi so can
- * safely handle the rx_list.
- */
- gro_normal_list(napi);
- __napi_schedule(napi);
- }
+ if (rc == budget)
+ __busy_poll_stop(napi, skip_schedule);
local_bh_enable();
}
void napi_busy_loop(unsigned int napi_id,
bool (*loop_end)(void *, unsigned long),
- void *loop_end_arg)
+ void *loop_end_arg, bool prefer_busy_poll, u16 budget)
{
unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
int (*napi_poll)(struct napi_struct *napi, int budget);
@@ -6561,17 +6580,23 @@ restart:
* we avoid dirtying napi->state as much as we can.
*/
if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
- NAPIF_STATE_IN_BUSY_POLL))
+ NAPIF_STATE_IN_BUSY_POLL)) {
+ if (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)
+ NAPIF_STATE_SCHED) != val) {
+ if (prefer_busy_poll)
+ set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
goto count;
+ }
have_poll_lock = netpoll_poll_lock(napi);
napi_poll = napi->poll;
}
- work = napi_poll(napi, BUSY_POLL_BUDGET);
- trace_napi_poll(napi, work, BUSY_POLL_BUDGET);
+ work = napi_poll(napi, budget);
+ trace_napi_poll(napi, work, budget);
gro_normal_list(napi);
count:
if (work > 0)
@@ -6584,7 +6609,7 @@ count:
if (unlikely(need_resched())) {
if (napi_poll)
- busy_poll_stop(napi, have_poll_lock);
+ busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
preempt_enable();
rcu_read_unlock();
cond_resched();
@@ -6595,7 +6620,7 @@ count:
cpu_relax();
}
if (napi_poll)
- busy_poll_stop(napi, have_poll_lock);
+ busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
preempt_enable();
out:
rcu_read_unlock();
@@ -6646,8 +6671,10 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
* NAPI_STATE_MISSED, since we do not react to a device IRQ.
*/
if (!napi_disable_pending(napi) &&
- !test_and_set_bit(NAPI_STATE_SCHED, &napi->state))
+ !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) {
+ clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
__napi_schedule_irqoff(napi);
+ }
return HRTIMER_NORESTART;
}
@@ -6705,6 +6732,7 @@ void napi_disable(struct napi_struct *n)
hrtimer_cancel(&n->timer);
+ clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state);
clear_bit(NAPI_STATE_DISABLE, &n->state);
}
EXPORT_SYMBOL(napi_disable);
@@ -6777,6 +6805,19 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
goto out_unlock;
}
+ /* The NAPI context has more processing work, but busy-polling
+ * is preferred. Exit early.
+ */
+ if (napi_prefer_busy_poll(n)) {
+ if (napi_complete_done(n, work)) {
+ /* If timeout is not set, we need to make sure
+ * that the NAPI is re-scheduled.
+ */
+ napi_schedule(n);
+ }
+ goto out_unlock;
+ }
+
if (n->gro_bitmask) {
/* flush too old packets
* If HZ < 1000, flush all packets.
@@ -6915,7 +6956,7 @@ bool netdev_has_upper_dev(struct net_device *dev,
EXPORT_SYMBOL(netdev_has_upper_dev);
/**
- * netdev_has_upper_dev_all - Check if device is linked to an upper device
+ * netdev_has_upper_dev_all_rcu - Check if device is linked to an upper device
* @dev: device
* @upper_dev: upper device to check
*
@@ -8153,7 +8194,7 @@ EXPORT_SYMBOL(netdev_lower_dev_get_private);
/**
- * netdev_lower_change - Dispatch event about lower device state change
+ * netdev_lower_state_changed - Dispatch event about lower device state change
* @lower_dev: device
* @lower_state_info: state to dispatch
*
@@ -8898,7 +8939,7 @@ static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode)
return dev->netdev_ops->ndo_bpf;
default:
return NULL;
- };
+ }
}
static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev,
@@ -9602,6 +9643,11 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
}
}
+ if ((features & NETIF_F_HW_TLS_TX) && !(features & NETIF_F_HW_CSUM)) {
+ netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
+ features &= ~NETIF_F_HW_TLS_TX;
+ }
+
return features;
}
@@ -9777,7 +9823,7 @@ static int netif_alloc_rx_queues(struct net_device *dev)
rx[i].dev = dev;
/* XDP RX-queue setup */
- err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i);
+ err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i, 0);
if (err < 0)
goto err_rxq_info;
}
@@ -10380,6 +10426,21 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
}
EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats);
+/**
+ * dev_get_tstats64 - ndo_get_stats64 implementation
+ * @dev: device to get statistics from
+ * @s: place to store stats
+ *
+ * Populate @s from dev->stats and dev->tstats. Can be used as
+ * ndo_get_stats64() callback.
+ */
+void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s)
+{
+ netdev_stats_to_stats64(s, &dev->stats);
+ dev_fetch_sw_netstats(s, dev->tstats);
+}
+EXPORT_SYMBOL_GPL(dev_get_tstats64);
+
struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
{
struct netdev_queue *queue = dev_ingress_queue(dev);
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 205e92e604ef..db8a0ff86f36 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -230,7 +230,7 @@ static int dev_do_ioctl(struct net_device *dev,
struct ifreq *ifr, unsigned int cmd)
{
const struct net_device_ops *ops = dev->netdev_ops;
- int err = -EOPNOTSUPP;
+ int err;
err = dsa_ndo_do_ioctl(dev, ifr, cmd);
if (err == 0 || err != -EOPNOTSUPP)
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 8c5ddffd707d..ee828e4b1007 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3394,7 +3394,7 @@ out_free_msg:
nlmsg_free(msg);
}
-void devlink_flash_update_begin_notify(struct devlink *devlink)
+static void devlink_flash_update_begin_notify(struct devlink *devlink)
{
struct devlink_flash_notify params = { 0 };
@@ -3402,9 +3402,8 @@ void devlink_flash_update_begin_notify(struct devlink *devlink)
DEVLINK_CMD_FLASH_UPDATE,
&params);
}
-EXPORT_SYMBOL_GPL(devlink_flash_update_begin_notify);
-void devlink_flash_update_end_notify(struct devlink *devlink)
+static void devlink_flash_update_end_notify(struct devlink *devlink)
{
struct devlink_flash_notify params = { 0 };
@@ -3412,7 +3411,6 @@ void devlink_flash_update_end_notify(struct devlink *devlink)
DEVLINK_CMD_FLASH_UPDATE_END,
&params);
}
-EXPORT_SYMBOL_GPL(devlink_flash_update_end_notify);
void devlink_flash_update_status_notify(struct devlink *devlink,
const char *status_msg,
@@ -3453,10 +3451,12 @@ EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify);
static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
struct genl_info *info)
{
- struct nlattr *nla_component, *nla_overwrite_mask;
+ struct nlattr *nla_component, *nla_overwrite_mask, *nla_file_name;
struct devlink_flash_update_params params = {};
struct devlink *devlink = info->user_ptr[0];
+ const char *file_name;
u32 supported_params;
+ int ret;
if (!devlink->ops->flash_update)
return -EOPNOTSUPP;
@@ -3466,8 +3466,6 @@ static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
supported_params = devlink->ops->supported_flash_update_params;
- params.file_name = nla_data(info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]);
-
nla_component = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT];
if (nla_component) {
if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT)) {
@@ -3491,7 +3489,21 @@ static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
params.overwrite_mask = sections.value & sections.selector;
}
- return devlink->ops->flash_update(devlink, &params, info->extack);
+ nla_file_name = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME];
+ file_name = nla_data(nla_file_name);
+ ret = request_firmware(&params.fw, file_name, devlink->dev);
+ if (ret) {
+ NL_SET_ERR_MSG_ATTR(info->extack, nla_file_name, "failed to locate the requested firmware file");
+ return ret;
+ }
+
+ devlink_flash_update_begin_notify(devlink);
+ ret = devlink->ops->flash_update(devlink, &params, info->extack);
+ devlink_flash_update_end_notify(devlink);
+
+ release_firmware(params.fw);
+
+ return ret;
}
static const struct devlink_param devlink_param_generic[] = {
@@ -6981,7 +6993,6 @@ static int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb,
struct netlink_ext_ack *extack = info->extack;
struct devlink *devlink = info->user_ptr[0];
struct devlink_trap_item *trap_item;
- int err;
if (list_empty(&devlink->trap_list))
return -EOPNOTSUPP;
@@ -6992,11 +7003,7 @@ static int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb,
return -ENOENT;
}
- err = devlink_trap_action_set(devlink, trap_item, info);
- if (err)
- return err;
-
- return 0;
+ return devlink_trap_action_set(devlink, trap_item, info);
}
static struct devlink_trap_group_item *
@@ -9500,6 +9507,7 @@ static const struct devlink_trap devlink_trap_generic[] = {
DEVLINK_TRAP(DCCP_PARSING, DROP),
DEVLINK_TRAP(GTP_PARSING, DROP),
DEVLINK_TRAP(ESP_PARSING, DROP),
+ DEVLINK_TRAP(BLACKHOLE_NEXTHOP, DROP),
};
#define DEVLINK_TRAP_GROUP(_id) \
@@ -10249,12 +10257,18 @@ int devlink_compat_flash_update(struct net_device *dev, const char *file_name)
goto out;
}
- params.file_name = file_name;
+ ret = request_firmware(&params.fw, file_name, devlink->dev);
+ if (ret)
+ goto out;
mutex_lock(&devlink->lock);
+ devlink_flash_update_begin_notify(devlink);
ret = devlink->ops->flash_update(devlink, &params, NULL);
+ devlink_flash_update_end_notify(devlink);
mutex_unlock(&devlink->lock);
+ release_firmware(params.fw);
+
out:
rtnl_lock();
dev_put(dev);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 7bcfb16854cb..cd80ffed6d26 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -563,7 +563,7 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net_device *dev;
nlrule->iifindex = -1;
- nla_strlcpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
+ nla_strscpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
dev = __dev_get_by_name(net, nlrule->iifname);
if (dev)
nlrule->iifindex = dev->ifindex;
@@ -573,7 +573,7 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net_device *dev;
nlrule->oifindex = -1;
- nla_strlcpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
+ nla_strscpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
dev = __dev_get_by_name(net, nlrule->oifname);
if (dev)
nlrule->oifindex = dev->ifindex;
diff --git a/net/core/filter.c b/net/core/filter.c
index 2ca5eecebacf..255aeee72402 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4910,6 +4910,9 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
tp->notsent_lowat = val;
sk->sk_write_space(sk);
break;
+ case TCP_WINDOW_CLAMP:
+ ret = tcp_set_window_clamp(sk, val);
+ break;
default:
ret = -EINVAL;
}
@@ -6995,6 +6998,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_sk_storage_delete_proto;
case BPF_FUNC_setsockopt:
switch (prog->expected_attach_type) {
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
return &bpf_sock_addr_setsockopt_proto;
@@ -7003,6 +7008,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
}
case BPF_FUNC_getsockopt:
switch (prog->expected_attach_type) {
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
return &bpf_sock_addr_getsockopt_proto;
@@ -10406,6 +10413,24 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = {
.ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UDP6],
};
+BPF_CALL_1(bpf_sock_from_file, struct file *, file)
+{
+ return (unsigned long)sock_from_file(file);
+}
+
+BTF_ID_LIST(bpf_sock_from_file_btf_ids)
+BTF_ID(struct, socket)
+BTF_ID(struct, file)
+
+const struct bpf_func_proto bpf_sock_from_file_proto = {
+ .func = bpf_sock_from_file,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_BTF_ID_OR_NULL,
+ .ret_btf_id = &bpf_sock_from_file_btf_ids[0],
+ .arg1_type = ARG_PTR_TO_BTF_ID,
+ .arg1_btf_id = &bpf_sock_from_file_btf_ids[1],
+};
+
static const struct bpf_func_proto *
bpf_sk_base_func_proto(enum bpf_func_id func_id)
{
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index e21950a2c897..6f1adba6695f 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -48,7 +48,7 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
memset(flow_dissector, 0, sizeof(*flow_dissector));
for (i = 0; i < key_count; i++, key++) {
- /* User should make sure that every key target offset is withing
+ /* User should make sure that every key target offset is within
* boundaries of unsigned short.
*/
BUG_ON(key->offset > USHRT_MAX);
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 41b24cd31562..b49c57d35a88 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -68,9 +68,8 @@ struct update_classid_context {
static int update_classid_sock(const void *v, struct file *file, unsigned n)
{
- int err;
struct update_classid_context *ctx = (void *)v;
- struct socket *sock = sock_from_file(file, &err);
+ struct socket *sock = sock_from_file(file);
if (sock) {
spin_lock(&cgroup_sk_update_lock);
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 9bd4cab7d510..99a431c56f23 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -220,8 +220,7 @@ static ssize_t write_priomap(struct kernfs_open_file *of,
static int update_netprio(const void *v, struct file *file, unsigned n)
{
- int err;
- struct socket *sock = sock_from_file(file, &err);
+ struct socket *sock = sock_from_file(file);
if (sock) {
spin_lock(&cgroup_sk_update_lock);
sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data,
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index ef98372facf6..f3c690b8c8e3 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -11,6 +11,8 @@
#include <linux/device.h>
#include <net/page_pool.h>
+#include <net/xdp.h>
+
#include <linux/dma-direction.h>
#include <linux/dma-mapping.h>
#include <linux/page-flags.h>
@@ -362,8 +364,9 @@ static bool pool_page_reusable(struct page_pool *pool, struct page *page)
* If the page refcnt != 1, then the page will be returned to memory
* subsystem.
*/
-void page_pool_put_page(struct page_pool *pool, struct page *page,
- unsigned int dma_sync_size, bool allow_direct)
+static __always_inline struct page *
+__page_pool_put_page(struct page_pool *pool, struct page *page,
+ unsigned int dma_sync_size, bool allow_direct)
{
/* This allocator is optimized for the XDP mode that uses
* one-frame-per-page, but have fallbacks that act like the
@@ -379,15 +382,12 @@ void page_pool_put_page(struct page_pool *pool, struct page *page,
page_pool_dma_sync_for_device(pool, page,
dma_sync_size);
- if (allow_direct && in_serving_softirq())
- if (page_pool_recycle_in_cache(page, pool))
- return;
+ if (allow_direct && in_serving_softirq() &&
+ page_pool_recycle_in_cache(page, pool))
+ return NULL;
- if (!page_pool_recycle_in_ring(pool, page)) {
- /* Cache full, fallback to free pages */
- page_pool_return_page(pool, page);
- }
- return;
+ /* Page found as candidate for recycling */
+ return page;
}
/* Fallback/non-XDP mode: API user have elevated refcnt.
*
@@ -405,9 +405,59 @@ void page_pool_put_page(struct page_pool *pool, struct page *page,
/* Do not replace this with page_pool_return_page() */
page_pool_release_page(pool, page);
put_page(page);
+
+ return NULL;
+}
+
+void page_pool_put_page(struct page_pool *pool, struct page *page,
+ unsigned int dma_sync_size, bool allow_direct)
+{
+ page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct);
+ if (page && !page_pool_recycle_in_ring(pool, page)) {
+ /* Cache full, fallback to free pages */
+ page_pool_return_page(pool, page);
+ }
}
EXPORT_SYMBOL(page_pool_put_page);
+/* Caller must not use data area after call, as this function overwrites it */
+void page_pool_put_page_bulk(struct page_pool *pool, void **data,
+ int count)
+{
+ int i, bulk_len = 0;
+
+ for (i = 0; i < count; i++) {
+ struct page *page = virt_to_head_page(data[i]);
+
+ page = __page_pool_put_page(pool, page, -1, false);
+ /* Approved for bulk recycling in ptr_ring cache */
+ if (page)
+ data[bulk_len++] = page;
+ }
+
+ if (unlikely(!bulk_len))
+ return;
+
+ /* Bulk producer into ptr_ring page_pool cache */
+ page_pool_ring_lock(pool);
+ for (i = 0; i < bulk_len; i++) {
+ if (__ptr_ring_produce(&pool->ring, data[i]))
+ break; /* ring full */
+ }
+ page_pool_ring_unlock(pool);
+
+ /* Hopefully all pages was return into ptr_ring */
+ if (likely(i == bulk_len))
+ return;
+
+ /* ptr_ring cache full, free remaining pages outside producer lock
+ * since put_page() with refcnt == 1 can be an expensive operation
+ */
+ for (; i < bulk_len; i++)
+ page_pool_return_page(pool, data[i]);
+}
+EXPORT_SYMBOL(page_pool_put_page_bulk);
+
static void page_pool_empty_ring(struct page_pool *pool)
{
struct page *page;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 7d7223691783..bb0596c41b3e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -139,7 +139,7 @@ bool lockdep_rtnl_is_held(void)
EXPORT_SYMBOL(lockdep_rtnl_is_held);
#endif /* #ifdef CONFIG_PROVE_LOCKING */
-static struct rtnl_link *__rcu *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1];
+static struct rtnl_link __rcu *__rcu *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1];
static inline int rtm_msgindex(int msgtype)
{
@@ -157,7 +157,7 @@ static inline int rtm_msgindex(int msgtype)
static struct rtnl_link *rtnl_get_link(int protocol, int msgtype)
{
- struct rtnl_link **tab;
+ struct rtnl_link __rcu **tab;
if (protocol >= ARRAY_SIZE(rtnl_msg_handlers))
protocol = PF_UNSPEC;
@@ -166,7 +166,7 @@ static struct rtnl_link *rtnl_get_link(int protocol, int msgtype)
if (!tab)
tab = rcu_dereference_rtnl(rtnl_msg_handlers[PF_UNSPEC]);
- return tab[msgtype];
+ return rcu_dereference_rtnl(tab[msgtype]);
}
static int rtnl_register_internal(struct module *owner,
@@ -183,7 +183,7 @@ static int rtnl_register_internal(struct module *owner,
msgindex = rtm_msgindex(msgtype);
rtnl_lock();
- tab = rtnl_msg_handlers[protocol];
+ tab = rtnl_dereference(rtnl_msg_handlers[protocol]);
if (tab == NULL) {
tab = kcalloc(RTM_NR_MSGTYPES, sizeof(void *), GFP_KERNEL);
if (!tab)
@@ -286,7 +286,8 @@ void rtnl_register(int protocol, int msgtype,
*/
int rtnl_unregister(int protocol, int msgtype)
{
- struct rtnl_link **tab, *link;
+ struct rtnl_link __rcu **tab;
+ struct rtnl_link *link;
int msgindex;
BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
@@ -299,7 +300,7 @@ int rtnl_unregister(int protocol, int msgtype)
return -ENOENT;
}
- link = tab[msgindex];
+ link = rtnl_dereference(tab[msgindex]);
rcu_assign_pointer(tab[msgindex], NULL);
rtnl_unlock();
@@ -318,20 +319,21 @@ EXPORT_SYMBOL_GPL(rtnl_unregister);
*/
void rtnl_unregister_all(int protocol)
{
- struct rtnl_link **tab, *link;
+ struct rtnl_link __rcu **tab;
+ struct rtnl_link *link;
int msgindex;
BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
rtnl_lock();
- tab = rtnl_msg_handlers[protocol];
+ tab = rtnl_dereference(rtnl_msg_handlers[protocol]);
if (!tab) {
rtnl_unlock();
return;
}
RCU_INIT_POINTER(rtnl_msg_handlers[protocol], NULL);
for (msgindex = 0; msgindex < RTM_NR_MSGTYPES; msgindex++) {
- link = tab[msgindex];
+ link = rtnl_dereference(tab[msgindex]);
if (!link)
continue;
@@ -1939,7 +1941,7 @@ static const struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla
if (linfo[IFLA_INFO_KIND]) {
char kind[MODULE_NAME_LEN];
- nla_strlcpy(kind, linfo[IFLA_INFO_KIND], sizeof(kind));
+ nla_strscpy(kind, linfo[IFLA_INFO_KIND], sizeof(kind));
ops = rtnl_link_ops_get(kind);
}
@@ -2953,9 +2955,9 @@ static struct net_device *rtnl_dev_get(struct net *net,
if (!ifname) {
ifname = buffer;
if (ifname_attr)
- nla_strlcpy(ifname, ifname_attr, IFNAMSIZ);
+ nla_strscpy(ifname, ifname_attr, IFNAMSIZ);
else if (altifname_attr)
- nla_strlcpy(ifname, altifname_attr, ALTIFNAMSIZ);
+ nla_strscpy(ifname, altifname_attr, ALTIFNAMSIZ);
else
return NULL;
}
@@ -2983,7 +2985,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
goto errout;
if (tb[IFLA_IFNAME])
- nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+ nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
else
ifname[0] = '\0';
@@ -3264,7 +3266,7 @@ replay:
return err;
if (tb[IFLA_IFNAME])
- nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+ nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
else
ifname[0] = '\0';
@@ -3296,7 +3298,7 @@ replay:
memset(linkinfo, 0, sizeof(linkinfo));
if (linkinfo[IFLA_INFO_KIND]) {
- nla_strlcpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind));
+ nla_strscpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind));
ops = rtnl_link_ops_get(kind);
} else {
kind[0] = '\0';
@@ -3754,7 +3756,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
s_idx = 1;
for (idx = 1; idx <= RTNL_FAMILY_MAX; idx++) {
- struct rtnl_link **tab;
+ struct rtnl_link __rcu **tab;
struct rtnl_link *link;
rtnl_dumpit_func dumpit;
@@ -3768,7 +3770,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
if (!tab)
continue;
- link = tab[type];
+ link = rcu_dereference_rtnl(tab[type]);
if (!link)
continue;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e578544b2cc7..f62cae3f75d8 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -249,6 +249,9 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
fclones->skb2.fclone = SKB_FCLONE_CLONE;
}
+
+ skb_set_kcov_handle(skb, kcov_common_handle());
+
out:
return skb;
nodata:
@@ -282,6 +285,8 @@ static struct sk_buff *__build_skb_around(struct sk_buff *skb,
memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
atomic_set(&shinfo->dataref, 1);
+ skb_set_kcov_handle(skb, kcov_common_handle());
+
return skb;
}
@@ -837,7 +842,7 @@ EXPORT_SYMBOL(consume_skb);
#endif
/**
- * consume_stateless_skb - free an skbuff, assuming it is stateless
+ * __consume_stateless_skb - free an skbuff, assuming it is stateless
* @skb: buffer to free
*
* Alike consume_skb(), but this variant assumes that this is the last
@@ -897,6 +902,8 @@ void napi_consume_skb(struct sk_buff *skb, int budget)
return;
}
+ lockdep_assert_in_softirq();
+
if (!skb_unref(skb))
return;
@@ -2011,6 +2018,12 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len)
skb->csum = csum_block_sub(skb->csum,
skb_checksum(skb, len, delta, 0),
len);
+ } else if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ int hdlen = (len > skb_headlen(skb)) ? skb_headlen(skb) : len;
+ int offset = skb_checksum_start_offset(skb) + skb->csum_offset;
+
+ if (offset + sizeof(__sum16) > hdlen)
+ return -EINVAL;
}
return __pskb_trim(skb, len);
}
@@ -5430,7 +5443,8 @@ struct sk_buff *skb_vlan_untag(struct sk_buff *skb)
goto err_free;
skb_reset_network_header(skb);
- skb_reset_transport_header(skb);
+ if (!skb_transport_header_was_set(skb))
+ skb_reset_transport_header(skb);
skb_reset_mac_len(skb);
return skb;
diff --git a/net/core/sock.c b/net/core/sock.c
index 727ea1cc633c..bbcd4b97eddd 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1159,6 +1159,22 @@ set_sndbuf:
sk->sk_ll_usec = val;
}
break;
+ case SO_PREFER_BUSY_POLL:
+ if (valbool && !capable(CAP_NET_ADMIN))
+ ret = -EPERM;
+ else
+ WRITE_ONCE(sk->sk_prefer_busy_poll, valbool);
+ break;
+ case SO_BUSY_POLL_BUDGET:
+ if (val > READ_ONCE(sk->sk_busy_poll_budget) && !capable(CAP_NET_ADMIN)) {
+ ret = -EPERM;
+ } else {
+ if (val < 0 || val > U16_MAX)
+ ret = -EINVAL;
+ else
+ WRITE_ONCE(sk->sk_busy_poll_budget, val);
+ }
+ break;
#endif
case SO_MAX_PACING_RATE:
@@ -1523,6 +1539,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
case SO_BUSY_POLL:
v.val = sk->sk_ll_usec;
break;
+ case SO_PREFER_BUSY_POLL:
+ v.val = READ_ONCE(sk->sk_prefer_busy_poll);
+ break;
#endif
case SO_MAX_PACING_RATE:
@@ -2486,7 +2505,7 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
}
EXPORT_SYMBOL(sk_page_frag_refill);
-static void __lock_sock(struct sock *sk)
+void __lock_sock(struct sock *sk)
__releases(&sk->sk_lock.slock)
__acquires(&sk->sk_lock.slock)
{
@@ -2808,14 +2827,8 @@ EXPORT_SYMBOL(sock_no_mmap);
void __receive_sock(struct file *file)
{
struct socket *sock;
- int error;
- /*
- * The resulting value of "error" is ignored here since we only
- * need to take action when the file is a socket and testing
- * "sock" for NULL is sufficient.
- */
- sock = sock_from_file(file, &error);
+ sock = sock_from_file(file);
if (sock) {
sock_update_netprioidx(&sock->sk->sk_cgrp_data);
sock_update_classid(&sock->sk->sk_cgrp_data);
@@ -3078,7 +3091,7 @@ EXPORT_SYMBOL(release_sock);
*
* sk_lock.slock unlocked, owned = 1, BH enabled
*/
-bool lock_sock_fast(struct sock *sk)
+bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock)
{
might_sleep();
spin_lock_bh(&sk->sk_lock.slock);
@@ -3096,6 +3109,7 @@ bool lock_sock_fast(struct sock *sk)
* The sk_lock has mutex_lock() semantics here:
*/
mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_);
+ __acquire(&sk->sk_lock.slock);
local_bh_enable();
return true;
}
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index ddc899e83313..64b5ec14ff50 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -27,8 +27,6 @@ struct bpf_stab {
static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
{
struct bpf_stab *stab;
- u64 cost;
- int err;
if (!capable(CAP_NET_ADMIN))
return ERR_PTR(-EPERM);
@@ -39,29 +37,22 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
return ERR_PTR(-EINVAL);
- stab = kzalloc(sizeof(*stab), GFP_USER);
+ stab = kzalloc(sizeof(*stab), GFP_USER | __GFP_ACCOUNT);
if (!stab)
return ERR_PTR(-ENOMEM);
bpf_map_init_from_attr(&stab->map, attr);
raw_spin_lock_init(&stab->lock);
- /* Make sure page count doesn't overflow. */
- cost = (u64) stab->map.max_entries * sizeof(struct sock *);
- err = bpf_map_charge_init(&stab->map.memory, cost);
- if (err)
- goto free_stab;
-
stab->sks = bpf_map_area_alloc(stab->map.max_entries *
sizeof(struct sock *),
stab->map.numa_node);
- if (stab->sks)
- return &stab->map;
- err = -ENOMEM;
- bpf_map_charge_finish(&stab->map.memory);
-free_stab:
- kfree(stab);
- return ERR_PTR(err);
+ if (!stab->sks) {
+ kfree(stab);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ return &stab->map;
}
int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog)
@@ -975,8 +966,9 @@ static struct bpf_shtab_elem *sock_hash_alloc_elem(struct bpf_shtab *htab,
}
}
- new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
- htab->map.numa_node);
+ new = bpf_map_kmalloc_node(&htab->map, htab->elem_size,
+ GFP_ATOMIC | __GFP_NOWARN,
+ htab->map.numa_node);
if (!new) {
atomic_dec(&htab->count);
return ERR_PTR(-ENOMEM);
@@ -1103,7 +1095,6 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
{
struct bpf_shtab *htab;
int i, err;
- u64 cost;
if (!capable(CAP_NET_ADMIN))
return ERR_PTR(-EPERM);
@@ -1116,7 +1107,7 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
if (attr->key_size > MAX_BPF_STACK)
return ERR_PTR(-E2BIG);
- htab = kzalloc(sizeof(*htab), GFP_USER);
+ htab = kzalloc(sizeof(*htab), GFP_USER | __GFP_ACCOUNT);
if (!htab)
return ERR_PTR(-ENOMEM);
@@ -1131,21 +1122,10 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
goto free_htab;
}
- cost = (u64) htab->buckets_num * sizeof(struct bpf_shtab_bucket) +
- (u64) htab->elem_size * htab->map.max_entries;
- if (cost >= U32_MAX - PAGE_SIZE) {
- err = -EINVAL;
- goto free_htab;
- }
- err = bpf_map_charge_init(&htab->map.memory, cost);
- if (err)
- goto free_htab;
-
htab->buckets = bpf_map_area_alloc(htab->buckets_num *
sizeof(struct bpf_shtab_bucket),
htab->map.numa_node);
if (!htab->buckets) {
- bpf_map_charge_finish(&htab->map.memory);
err = -ENOMEM;
goto free_htab;
}
diff --git a/net/core/xdp.c b/net/core/xdp.c
index d900cebc0acd..3a8c9ab4ecbe 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -158,7 +158,7 @@ static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq)
/* Returns 0 on success, negative on failure */
int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
- struct net_device *dev, u32 queue_index)
+ struct net_device *dev, u32 queue_index, unsigned int napi_id)
{
if (xdp_rxq->reg_state == REG_STATE_UNUSED) {
WARN(1, "Driver promised not to register this");
@@ -179,6 +179,7 @@ int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
xdp_rxq_info_init(xdp_rxq);
xdp_rxq->dev = dev;
xdp_rxq->queue_index = queue_index;
+ xdp_rxq->napi_id = napi_id;
xdp_rxq->reg_state = REG_STATE_REGISTERED;
return 0;
@@ -383,6 +384,60 @@ void xdp_return_frame_rx_napi(struct xdp_frame *xdpf)
}
EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi);
+/* XDP bulk APIs introduce a defer/flush mechanism to return
+ * pages belonging to the same xdp_mem_allocator object
+ * (identified via the mem.id field) in bulk to optimize
+ * I-cache and D-cache.
+ * The bulk queue size is set to 16 to be aligned to how
+ * XDP_REDIRECT bulking works. The bulk is flushed when
+ * it is full or when mem.id changes.
+ * xdp_frame_bulk is usually stored/allocated on the function
+ * call-stack to avoid locking penalties.
+ */
+void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq)
+{
+ struct xdp_mem_allocator *xa = bq->xa;
+
+ if (unlikely(!xa || !bq->count))
+ return;
+
+ page_pool_put_page_bulk(xa->page_pool, bq->q, bq->count);
+ /* bq->xa is not cleared to save lookup, if mem.id same in next bulk */
+ bq->count = 0;
+}
+EXPORT_SYMBOL_GPL(xdp_flush_frame_bulk);
+
+/* Must be called with rcu_read_lock held */
+void xdp_return_frame_bulk(struct xdp_frame *xdpf,
+ struct xdp_frame_bulk *bq)
+{
+ struct xdp_mem_info *mem = &xdpf->mem;
+ struct xdp_mem_allocator *xa;
+
+ if (mem->type != MEM_TYPE_PAGE_POOL) {
+ __xdp_return(xdpf->data, &xdpf->mem, false, NULL);
+ return;
+ }
+
+ xa = bq->xa;
+ if (unlikely(!xa)) {
+ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+ bq->count = 0;
+ bq->xa = xa;
+ }
+
+ if (bq->count == XDP_BULK_QUEUE_SIZE)
+ xdp_flush_frame_bulk(bq);
+
+ if (unlikely(mem->id != xa->mem.id)) {
+ xdp_flush_frame_bulk(bq);
+ bq->xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+ }
+
+ bq->q[bq->count++] = xdpf->data;
+}
+EXPORT_SYMBOL_GPL(xdp_return_frame_bulk);
+
void xdp_return_buff(struct xdp_buff *xdp)
{
__xdp_return(xdp->data, &xdp->rxq->mem, true, xdp);