summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-05-25 12:22:58 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-05-25 12:22:58 -0700
commit7e062cda7d90543ac8c7700fc7c5527d0c0f22ad (patch)
tree2f1602595d9416be41cc2e88a659ba4c145734b9 /net/core
parent5d1772b1739b085721431eef0c0400f3aff01abf (diff)
parent57d7becda9c9e612e6b00676f2eecfac3e719e88 (diff)
Merge tag 'net-next-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Core ---- - Support TCPv6 segmentation offload with super-segments larger than 64k bytes using the IPv6 Jumbogram extension header (AKA BIG TCP). - Generalize skb freeing deferral to per-cpu lists, instead of per-socket lists. - Add a netdev statistic for packets dropped due to L2 address mismatch (rx_otherhost_dropped). - Continue work annotating skb drop reasons. - Accept alternative netdev names (ALT_IFNAME) in more netlink requests. - Add VLAN support for AF_PACKET SOCK_RAW GSO. - Allow receiving skb mark from the socket as a cmsg. - Enable memcg accounting for veth queues, sysctl tables and IPv6. BPF --- - Add libbpf support for User Statically-Defined Tracing (USDTs). - Speed up symbol resolution for kprobes multi-link attachments. - Support storing typed pointers to referenced and unreferenced objects in BPF maps. - Add support for BPF link iterator. - Introduce access to remote CPU map elements in BPF per-cpu map. - Allow middle-of-the-road settings for the kernel.unprivileged_bpf_disabled sysctl. - Implement basic types of dynamic pointers e.g. to allow for dynamically sized ringbuf reservations without extra memory copies. Protocols --------- - Retire port only listening_hash table, add a second bind table hashed by port and address. Avoid linear list walk when binding to very popular ports (e.g. 443). - Add bridge FDB bulk flush filtering support allowing user space to remove all FDB entries matching a condition. - Introduce accept_unsolicited_na sysctl for IPv6 to implement router-side changes for RFC9131. - Support for MPTCP path manager in user space. - Add MPTCP support for fallback to regular TCP for connections that have never connected additional subflows or transmitted out-of-sequence data (partial support for RFC8684 fallback). - Avoid races in MPTCP-level window tracking, stabilize and improve throughput. - Support lockless operation of GRE tunnels with seq numbers enabled. - WiFi support for host based BSS color collision detection. - Add support for SO_TXTIME/SCM_TXTIME on CAN sockets. - Support transmission w/o flow control in CAN ISOTP (ISO 15765-2). - Support zero-copy Tx with TLS 1.2 crypto offload (sendfile). - Allow matching on the number of VLAN tags via tc-flower. - Add tracepoint for tcp_set_ca_state(). Driver API ---------- - Improve error reporting from classifier and action offload. - Add support for listing line cards in switches (devlink). - Add helpers for reporting page pool statistics with ethtool -S. - Add support for reading clock cycles when using PTP virtual clocks, instead of having the driver convert to time before reporting. This makes it possible to report time from different vclocks. - Support configuring low-latency Tx descriptor push via ethtool. - Separate Clause 22 and Clause 45 MDIO accesses more explicitly. New hardware / drivers ---------------------- - Ethernet: - Marvell's Octeon NIC PCI Endpoint support (octeon_ep) - Sunplus SP7021 SoC (sp7021_emac) - Add support for Renesas RZ/V2M (in ravb) - Add support for MediaTek mt7986 switches (in mtk_eth_soc) - Ethernet PHYs: - ADIN1100 industrial PHYs (w/ 10BASE-T1L and SQI reporting) - TI DP83TD510 PHY - Microchip LAN8742/LAN88xx PHYs - WiFi: - Driver for pureLiFi X, XL, XC devices (plfxlc) - Driver for Silicon Labs devices (wfx) - Support for WCN6750 (in ath11k) - Support Realtek 8852ce devices (in rtw89) - Mobile: - MediaTek T700 modems (Intel 5G 5000 M.2 cards) - CAN: - ctucanfd: add support for CTU CAN FD open-source IP core from Czech Technical University in Prague Drivers ------- - Delete a number of old drivers still using virt_to_bus(). - Ethernet NICs: - intel: support TSO on tunnels MPLS - broadcom: support multi-buffer XDP - nfp: support VF rate limiting - sfc: use hardware tx timestamps for more than PTP - mlx5: multi-port eswitch support - hyper-v: add support for XDP_REDIRECT - atlantic: XDP support (including multi-buffer) - macb: improve real-time perf by deferring Tx processing to NAPI - High-speed Ethernet switches: - mlxsw: implement basic line card information querying - prestera: add support for traffic policing on ingress and egress - Embedded Ethernet switches: - lan966x: add support for packet DMA (FDMA) - lan966x: add support for PTP programmable pins - ti: cpsw_new: enable bc/mc storm prevention - Qualcomm 802.11ax WiFi (ath11k): - Wake-on-WLAN support for QCA6390 and WCN6855 - device recovery (firmware restart) support - support setting Specific Absorption Rate (SAR) for WCN6855 - read country code from SMBIOS for WCN6855/QCA6390 - enable keep-alive during WoWLAN suspend - implement remain-on-channel support - MediaTek WiFi (mt76): - support Wireless Ethernet Dispatch offloading packet movement between the Ethernet switch and WiFi interfaces - non-standard VHT MCS10-11 support - mt7921 AP mode support - mt7921 IPv6 NS offload support - Ethernet PHYs: - micrel: ksz9031/ksz9131: cabletest support - lan87xx: SQI support for T1 PHYs - lan937x: add interrupt support for link detection" * tag 'net-next-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1809 commits) ptp: ocp: Add firmware header checks ptp: ocp: fix PPS source selector debugfs reporting ptp: ocp: add .init function for sma_op vector ptp: ocp: vectorize the sma accessor functions ptp: ocp: constify selectors ptp: ocp: parameterize input/output sma selectors ptp: ocp: revise firmware display ptp: ocp: add Celestica timecard PCI ids ptp: ocp: Remove #ifdefs around PCI IDs ptp: ocp: 32-bit fixups for pci start address Revert "net/smc: fix listen processing for SMC-Rv2" ath6kl: Use cc-disable-warning to disable -Wdangling-pointer selftests/bpf: Dynptr tests bpf: Add dynptr data slices bpf: Add bpf_dynptr_read and bpf_dynptr_write bpf: Dynptr support for ring buffers bpf: Add bpf_dynptr_from_mem for local dynptrs bpf: Add verifier support for dynptrs bpf: Suppress 'passing zero to PTR_ERR' warning bpf: Introduce bpf_arch_text_invalidate for bpf_prog_pack ...
Diffstat (limited to 'net/core')
-rw-r--r--net/core/bpf_sk_storage.c11
-rw-r--r--net/core/datagram.c7
-rw-r--r--net/core/datagram.h15
-rw-r--r--net/core/dev.c232
-rw-r--r--net/core/dev.h112
-rw-r--r--net/core/dev_addr_lists.c2
-rw-r--r--net/core/dev_ioctl.c2
-rw-r--r--net/core/devlink.c653
-rw-r--r--net/core/drop_monitor.c2
-rw-r--r--net/core/filter.c37
-rw-r--r--net/core/flow_dissector.c20
-rw-r--r--net/core/gro.c8
-rw-r--r--net/core/link_watch.c1
-rw-r--r--net/core/neighbour.c2
-rw-r--r--net/core/net-procfs.c2
-rw-r--r--net/core/net-sysfs.c22
-rw-r--r--net/core/page_pool.c83
-rw-r--r--net/core/rtnetlink.c449
-rw-r--r--net/core/skbuff.c67
-rw-r--r--net/core/skmsg.c22
-rw-r--r--net/core/sock.c126
-rw-r--r--net/core/sock_map.c10
-rw-r--r--net/core/sysctl_net_core.c29
23 files changed, 1560 insertions, 354 deletions
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index e3ac36380520..a25ec93729b9 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -40,7 +40,7 @@ static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map)
if (!sdata)
return -ENOENT;
- bpf_selem_unlink(SELEM(sdata));
+ bpf_selem_unlink(SELEM(sdata), true);
return 0;
}
@@ -75,8 +75,8 @@ void bpf_sk_storage_free(struct sock *sk)
* sk_storage.
*/
bpf_selem_unlink_map(selem);
- free_sk_storage = bpf_selem_unlink_storage_nolock(sk_storage,
- selem, true);
+ free_sk_storage = bpf_selem_unlink_storage_nolock(
+ sk_storage, selem, true, false);
}
raw_spin_unlock_bh(&sk_storage->lock);
rcu_read_unlock();
@@ -338,7 +338,7 @@ bpf_sk_storage_ptr(void *owner)
return &sk->sk_bpf_storage;
}
-static int sk_storage_map_btf_id;
+BTF_ID_LIST_SINGLE(sk_storage_map_btf_ids, struct, bpf_local_storage_map)
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,
@@ -349,8 +349,7 @@ const struct bpf_map_ops sk_storage_map_ops = {
.map_update_elem = bpf_fd_sk_storage_update_elem,
.map_delete_elem = bpf_fd_sk_storage_delete_elem,
.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_btf_id = &sk_storage_map_btf_ids[0],
.map_local_storage_charge = bpf_sk_storage_charge,
.map_local_storage_uncharge = bpf_sk_storage_uncharge,
.map_owner_storage_ptr = bpf_sk_storage_ptr,
diff --git a/net/core/datagram.c b/net/core/datagram.c
index ee290776c661..50f4faeea76c 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -62,8 +62,6 @@
#include <trace/events/skb.h>
#include <net/busy_poll.h>
-#include "datagram.h"
-
/*
* Is a socket 'connection oriented' ?
*/
@@ -310,12 +308,11 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk,
EXPORT_SYMBOL(__skb_recv_datagram);
struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags,
- int noblock, int *err)
+ int *err)
{
int off = 0;
- return __skb_recv_datagram(sk, &sk->sk_receive_queue,
- flags | (noblock ? MSG_DONTWAIT : 0),
+ return __skb_recv_datagram(sk, &sk->sk_receive_queue, flags,
&off, err);
}
EXPORT_SYMBOL(skb_recv_datagram);
diff --git a/net/core/datagram.h b/net/core/datagram.h
deleted file mode 100644
index bcfb75bfa3b2..000000000000
--- a/net/core/datagram.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-#ifndef _NET_CORE_DATAGRAM_H_
-#define _NET_CORE_DATAGRAM_H_
-
-#include <linux/types.h>
-
-struct sock;
-struct sk_buff;
-struct iov_iter;
-
-int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
- struct iov_iter *from, size_t length);
-
-#endif /* _NET_CORE_DATAGRAM_H_ */
diff --git a/net/core/dev.c b/net/core/dev.c
index 191ec76d4c3b..08ce317fcec8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -151,6 +151,7 @@
#include <linux/prandom.h>
#include <linux/once_lite.h>
+#include "dev.h"
#include "net-sysfs.h"
@@ -701,6 +702,10 @@ int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
if (WARN_ON_ONCE(last_dev == ctx.dev))
return -1;
}
+
+ if (!ctx.dev)
+ return ret;
+
path = dev_fwd_path(stack);
if (!path)
return -1;
@@ -2988,6 +2993,52 @@ undo_rx:
EXPORT_SYMBOL(netif_set_real_num_queues);
/**
+ * netif_set_tso_max_size() - set the max size of TSO frames supported
+ * @dev: netdev to update
+ * @size: max skb->len of a TSO frame
+ *
+ * Set the limit on the size of TSO super-frames the device can handle.
+ * Unless explicitly set the stack will assume the value of
+ * %GSO_LEGACY_MAX_SIZE.
+ */
+void netif_set_tso_max_size(struct net_device *dev, unsigned int size)
+{
+ dev->tso_max_size = min(GSO_MAX_SIZE, size);
+ if (size < READ_ONCE(dev->gso_max_size))
+ netif_set_gso_max_size(dev, size);
+}
+EXPORT_SYMBOL(netif_set_tso_max_size);
+
+/**
+ * netif_set_tso_max_segs() - set the max number of segs supported for TSO
+ * @dev: netdev to update
+ * @segs: max number of TCP segments
+ *
+ * Set the limit on the number of TCP segments the device can generate from
+ * a single TSO super-frame.
+ * Unless explicitly set the stack will assume the value of %GSO_MAX_SEGS.
+ */
+void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs)
+{
+ dev->tso_max_segs = segs;
+ if (segs < READ_ONCE(dev->gso_max_segs))
+ netif_set_gso_max_segs(dev, segs);
+}
+EXPORT_SYMBOL(netif_set_tso_max_segs);
+
+/**
+ * netif_inherit_tso_max() - copy all TSO limits from a lower device to an upper
+ * @to: netdev to update
+ * @from: netdev from which to copy the limits
+ */
+void netif_inherit_tso_max(struct net_device *to, const struct net_device *from)
+{
+ netif_set_tso_max_size(to, from->tso_max_size);
+ netif_set_tso_max_segs(to, from->tso_max_segs);
+}
+EXPORT_SYMBOL(netif_inherit_tso_max);
+
+/**
* netif_get_num_default_rss_queues - default number of RSS queues
*
* Default value is the number of physical cores if there are only 1 or 2, or
@@ -3215,12 +3266,18 @@ int skb_checksum_help(struct sk_buff *skb)
}
offset = skb_checksum_start_offset(skb);
- BUG_ON(offset >= skb_headlen(skb));
+ ret = -EINVAL;
+ if (WARN_ON_ONCE(offset >= skb_headlen(skb))) {
+ DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false);
+ goto out;
+ }
csum = skb_checksum(skb, offset, skb->len - offset, 0);
offset += skb->csum_offset;
- BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb));
-
+ if (WARN_ON_ONCE(offset + sizeof(__sum16) > skb_headlen(skb))) {
+ DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false);
+ goto out;
+ }
ret = skb_ensure_writable(skb, offset + sizeof(__sum16));
if (ret)
goto out;
@@ -3919,6 +3976,25 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
return skb;
}
+
+static struct netdev_queue *
+netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb)
+{
+ int qm = skb_get_queue_mapping(skb);
+
+ return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm));
+}
+
+static bool netdev_xmit_txqueue_skipped(void)
+{
+ return __this_cpu_read(softnet_data.xmit.skip_txqueue);
+}
+
+void netdev_xmit_skip_txqueue(bool skip)
+{
+ __this_cpu_write(softnet_data.xmit.skip_txqueue, skip);
+}
+EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue);
#endif /* CONFIG_NET_EGRESS */
#ifdef CONFIG_XPS
@@ -4061,35 +4137,30 @@ struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
}
/**
- * __dev_queue_xmit - transmit a buffer
- * @skb: buffer to transmit
- * @sb_dev: suboordinate device used for L2 forwarding offload
- *
- * Queue a buffer for transmission to a network device. The caller must
- * have set the device and priority and built the buffer before calling
- * this function. The function can be called from an interrupt.
+ * __dev_queue_xmit() - transmit a buffer
+ * @skb: buffer to transmit
+ * @sb_dev: suboordinate device used for L2 forwarding offload
*
- * A negative errno code is returned on a failure. A success does not
- * guarantee the frame will be transmitted as it may be dropped due
- * to congestion or traffic shaping.
+ * Queue a buffer for transmission to a network device. The caller must
+ * have set the device and priority and built the buffer before calling
+ * this function. The function can be called from an interrupt.
*
- * -----------------------------------------------------------------------------------
- * I notice this method can also return errors from the queue disciplines,
- * including NET_XMIT_DROP, which is a positive value. So, errors can also
- * be positive.
+ * When calling this method, interrupts MUST be enabled. This is because
+ * the BH enable code must have IRQs enabled so that it will not deadlock.
*
- * Regardless of the return value, the skb is consumed, so it is currently
- * difficult to retry a send to this method. (You can bump the ref count
- * before sending to hold a reference for retry if you are careful.)
+ * Regardless of the return value, the skb is consumed, so it is currently
+ * difficult to retry a send to this method. (You can bump the ref count
+ * before sending to hold a reference for retry if you are careful.)
*
- * When calling this method, interrupts MUST be enabled. This is because
- * the BH enable code must have IRQs enabled so that it will not deadlock.
- * --BLG
+ * Return:
+ * * 0 - buffer successfully transmitted
+ * * positive qdisc return code - NET_XMIT_DROP etc.
+ * * negative errno - other errors
*/
-static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
+int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
{
struct net_device *dev = skb->dev;
- struct netdev_queue *txq;
+ struct netdev_queue *txq = NULL;
struct Qdisc *q;
int rc = -ENOMEM;
bool again = false;
@@ -4117,11 +4188,17 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
if (!skb)
goto out;
}
+
+ netdev_xmit_skip_txqueue(false);
+
nf_skip_egress(skb, true);
skb = sch_handle_egress(skb, &rc, dev);
if (!skb)
goto out;
nf_skip_egress(skb, false);
+
+ if (netdev_xmit_txqueue_skipped())
+ txq = netdev_tx_queue_mapping(dev, skb);
}
#endif
/* If device/qdisc don't need skb->dst, release it right now while
@@ -4132,7 +4209,9 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
else
skb_dst_force(skb);
- txq = netdev_core_pick_tx(dev, skb, sb_dev);
+ if (!txq)
+ txq = netdev_core_pick_tx(dev, skb, sb_dev);
+
q = rcu_dereference_bh(txq->qdisc);
trace_net_dev_queue(skb);
@@ -4201,18 +4280,7 @@ out:
rcu_read_unlock_bh();
return rc;
}
-
-int dev_queue_xmit(struct sk_buff *skb)
-{
- return __dev_queue_xmit(skb, NULL);
-}
-EXPORT_SYMBOL(dev_queue_xmit);
-
-int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev)
-{
- return __dev_queue_xmit(skb, sb_dev);
-}
-EXPORT_SYMBOL(dev_queue_xmit_accel);
+EXPORT_SYMBOL(__dev_queue_xmit);
int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
{
@@ -4259,6 +4327,7 @@ 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;
@@ -4510,6 +4579,15 @@ static void rps_trigger_softirq(void *data)
#endif /* CONFIG_RPS */
+/* Called from hardirq (IPI) context */
+static void trigger_rx_softirq(void *data)
+{
+ struct softnet_data *sd = data;
+
+ __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ smp_store_release(&sd->defer_ipi_scheduled, 0);
+}
+
/*
* Check if this softnet_data structure is another cpu one
* If yes, queue it to our IPI list and return 1
@@ -5367,13 +5445,11 @@ check_vlan_id:
*ppt_prev = pt_prev;
} else {
drop:
- if (!deliver_exact) {
+ if (!deliver_exact)
dev_core_stats_rx_dropped_inc(skb->dev);
- kfree_skb_reason(skb, SKB_DROP_REASON_PTYPE_ABSENT);
- } else {
+ else
dev_core_stats_rx_nohandler_inc(skb->dev);
- kfree_skb(skb);
- }
+ kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO);
/* Jamal, now you will not able to escape explaining
* me how you were going to use this. :-)
*/
@@ -6275,8 +6351,8 @@ int dev_set_threaded(struct net_device *dev, bool threaded)
}
EXPORT_SYMBOL(dev_set_threaded);
-void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
- int (*poll)(struct napi_struct *, int), int weight)
+void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
+ int (*poll)(struct napi_struct *, int), int weight)
{
if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state)))
return;
@@ -6309,7 +6385,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
if (dev->threaded && napi_kthread_create(napi))
dev->threaded = 0;
}
-EXPORT_SYMBOL(netif_napi_add);
+EXPORT_SYMBOL(netif_napi_add_weight);
void napi_disable(struct napi_struct *n)
{
@@ -6538,6 +6614,28 @@ static int napi_threaded_poll(void *data)
return 0;
}
+static void skb_defer_free_flush(struct softnet_data *sd)
+{
+ struct sk_buff *skb, *next;
+ unsigned long flags;
+
+ /* Paired with WRITE_ONCE() in skb_attempt_defer_free() */
+ if (!READ_ONCE(sd->defer_list))
+ return;
+
+ spin_lock_irqsave(&sd->defer_lock, flags);
+ skb = sd->defer_list;
+ sd->defer_list = NULL;
+ sd->defer_count = 0;
+ spin_unlock_irqrestore(&sd->defer_lock, flags);
+
+ while (skb != NULL) {
+ next = skb->next;
+ napi_consume_skb(skb, 1);
+ skb = next;
+ }
+}
+
static __latent_entropy void net_rx_action(struct softirq_action *h)
{
struct softnet_data *sd = this_cpu_ptr(&softnet_data);
@@ -6554,9 +6652,11 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
for (;;) {
struct napi_struct *n;
+ skb_defer_free_flush(sd);
+
if (list_empty(&list)) {
if (!sd_has_rps_ipi_waiting(sd) && list_empty(&repoll))
- return;
+ goto end;
break;
}
@@ -6583,6 +6683,7 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
net_rps_action_and_irq_enable(sd);
+end:;
}
struct netdev_adjacent {
@@ -8638,7 +8739,6 @@ void dev_set_group(struct net_device *dev, int new_group)
{
dev->group = new_group;
}
-EXPORT_SYMBOL(dev_set_group);
/**
* dev_pre_changeaddr_notify - Call NETDEV_PRE_CHANGEADDR.
@@ -8753,7 +8853,6 @@ int dev_change_carrier(struct net_device *dev, bool new_carrier)
return -ENODEV;
return ops->ndo_change_carrier(dev, new_carrier);
}
-EXPORT_SYMBOL(dev_change_carrier);
/**
* dev_get_phys_port_id - Get device physical port ID
@@ -8771,7 +8870,6 @@ int dev_get_phys_port_id(struct net_device *dev,
return -EOPNOTSUPP;
return ops->ndo_get_phys_port_id(dev, ppid);
}
-EXPORT_SYMBOL(dev_get_phys_port_id);
/**
* dev_get_phys_port_name - Get device physical port name
@@ -8794,7 +8892,6 @@ int dev_get_phys_port_name(struct net_device *dev,
}
return devlink_compat_phys_port_name_get(dev, name, len);
}
-EXPORT_SYMBOL(dev_get_phys_port_name);
/**
* dev_get_port_parent_id - Get the device's port parent identifier
@@ -8876,7 +8973,6 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down)
dev->proto_down = proto_down;
return 0;
}
-EXPORT_SYMBOL(dev_change_proto_down);
/**
* dev_change_proto_down_reason - proto down reason
@@ -8901,7 +8997,6 @@ void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask,
}
}
}
-EXPORT_SYMBOL(dev_change_proto_down_reason);
struct bpf_xdp_link {
struct bpf_link link;
@@ -9428,7 +9523,7 @@ static int dev_new_index(struct net *net)
}
/* Delayed registration/unregisteration */
-static LIST_HEAD(net_todo_list);
+LIST_HEAD(net_todo_list);
DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
static void net_set_todo(struct net_device *dev)
@@ -9835,22 +9930,14 @@ void netif_tx_stop_all_queues(struct net_device *dev)
EXPORT_SYMBOL(netif_tx_stop_all_queues);
/**
- * register_netdevice - register a network device
- * @dev: device to register
- *
- * Take a completed network device structure and add it to the kernel
- * interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier
- * chain. 0 is returned on success. A negative errno code is returned
- * on a failure to set up the device, or if the name is a duplicate.
+ * register_netdevice() - register a network device
+ * @dev: device to register
*
- * Callers must hold the rtnl semaphore. You may want
- * register_netdev() instead of this.
- *
- * BUGS:
- * The locking appears insufficient to guarantee two parallel registers
- * will not get the same name.
+ * Take a prepared network device structure and make it externally accessible.
+ * A %NETDEV_REGISTER message is sent to the netdev notifier chain.
+ * Callers must hold the rtnl lock - you may want register_netdev()
+ * instead of this.
*/
-
int register_netdevice(struct net_device *dev)
{
int ret;
@@ -10352,6 +10439,7 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
storage->rx_dropped += READ_ONCE(core_stats->rx_dropped);
storage->tx_dropped += READ_ONCE(core_stats->tx_dropped);
storage->rx_nohandler += READ_ONCE(core_stats->rx_nohandler);
+ storage->rx_otherhost_dropped += READ_ONCE(core_stats->rx_otherhost_dropped);
}
}
return storage;
@@ -10510,9 +10598,11 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
dev_net_set(dev, &init_net);
- dev->gso_max_size = GSO_MAX_SIZE;
+ dev->gso_max_size = GSO_LEGACY_MAX_SIZE;
dev->gso_max_segs = GSO_MAX_SEGS;
- dev->gro_max_size = GRO_MAX_SIZE;
+ dev->gro_max_size = GRO_LEGACY_MAX_SIZE;
+ dev->tso_max_size = TSO_LEGACY_MAX_SIZE;
+ dev->tso_max_segs = TSO_MAX_SEGS;
dev->upper_level = 1;
dev->lower_level = 1;
#ifdef CONFIG_LOCKDEP
@@ -11294,6 +11384,8 @@ static int __init net_dev_init(void)
INIT_CSD(&sd->csd, rps_trigger_softirq, sd);
sd->cpu = i;
#endif
+ INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd);
+ spin_lock_init(&sd->defer_lock);
init_gro_hash(&sd->backlog);
sd->backlog.poll = process_backlog;
diff --git a/net/core/dev.h b/net/core/dev.h
new file mode 100644
index 000000000000..cbb8a925175a
--- /dev/null
+++ b/net/core/dev.h
@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _NET_CORE_DEV_H
+#define _NET_CORE_DEV_H
+
+#include <linux/types.h>
+
+struct net;
+struct net_device;
+struct netdev_bpf;
+struct netdev_phys_item_id;
+struct netlink_ext_ack;
+
+/* Random bits of netdevice that don't need to be exposed */
+#define FLOW_LIMIT_HISTORY (1 << 7) /* must be ^2 and !overflow buckets */
+struct sd_flow_limit {
+ u64 count;
+ unsigned int num_buckets;
+ unsigned int history_head;
+ u16 history[FLOW_LIMIT_HISTORY];
+ u8 buckets[];
+};
+
+extern int netdev_flow_limit_table_len;
+
+#ifdef CONFIG_PROC_FS
+int __init dev_proc_init(void);
+#else
+#define dev_proc_init() 0
+#endif
+
+void linkwatch_init_dev(struct net_device *dev);
+void linkwatch_forget_dev(struct net_device *dev);
+void linkwatch_run_queue(void);
+
+void dev_addr_flush(struct net_device *dev);
+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;
+
+/* rtnl helpers */
+extern struct list_head net_todo_list;
+void netdev_run_todo(void);
+
+/* netdev management, shared between various uAPI entry points */
+struct netdev_name_node {
+ struct hlist_node hlist;
+ struct list_head list;
+ struct net_device *dev;
+ const char *name;
+};
+
+int netdev_get_name(struct net *net, char *name, int ifindex);
+int dev_change_name(struct net_device *dev, const char *newname);
+
+int netdev_name_node_alt_create(struct net_device *dev, const char *name);
+int netdev_name_node_alt_destroy(struct net_device *dev, const char *name);
+
+int dev_validate_mtu(struct net_device *dev, int mtu,
+ struct netlink_ext_ack *extack);
+int dev_set_mtu_ext(struct net_device *dev, int mtu,
+ struct netlink_ext_ack *extack);
+
+int dev_get_phys_port_id(struct net_device *dev,
+ struct netdev_phys_item_id *ppid);
+int dev_get_phys_port_name(struct net_device *dev,
+ char *name, size_t len);
+
+int dev_change_proto_down(struct net_device *dev, bool proto_down);
+void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask,
+ u32 value);
+
+typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
+int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
+ int fd, int expected_fd, u32 flags);
+
+int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len);
+void dev_set_group(struct net_device *dev, int new_group);
+int dev_change_carrier(struct net_device *dev, bool new_carrier);
+
+void __dev_set_rx_mode(struct net_device *dev);
+
+static inline void netif_set_gso_max_size(struct net_device *dev,
+ unsigned int size)
+{
+ /* dev->gso_max_size is read locklessly from sk_setup_caps() */
+ WRITE_ONCE(dev->gso_max_size, size);
+}
+
+static inline void netif_set_gso_max_segs(struct net_device *dev,
+ unsigned int segs)
+{
+ /* dev->gso_max_segs is read locklessly from sk_setup_caps() */
+ WRITE_ONCE(dev->gso_max_segs, segs);
+}
+
+static inline void netif_set_gro_max_size(struct net_device *dev,
+ unsigned int size)
+{
+ /* This pairs with the READ_ONCE() in skb_gro_receive() */
+ WRITE_ONCE(dev->gro_max_size, size);
+}
+
+#endif
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index bead38ca50bd..baa63dee2829 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -12,6 +12,8 @@
#include <linux/export.h>
#include <linux/list.h>
+#include "dev.h"
+
/*
* General list handling functions
*/
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 1b807d119da5..4f6be442ae7e 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -10,6 +10,8 @@
#include <net/dsa.h>
#include <net/wext.h>
+#include "dev.h"
+
/*
* Map an interface index to its name (SIOCGIFNAME)
*/
diff --git a/net/core/devlink.c b/net/core/devlink.c
index aeca13b6e57b..5cc88490f18f 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -54,6 +54,8 @@ struct devlink {
struct list_head trap_list;
struct list_head trap_group_list;
struct list_head trap_policer_list;
+ struct list_head linecard_list;
+ struct mutex linecards_lock; /* protects linecard_list */
const struct devlink_ops *ops;
u64 features;
struct xarray snapshot_ids;
@@ -70,6 +72,23 @@ struct devlink {
char priv[] __aligned(NETDEV_ALIGN);
};
+struct devlink_linecard_ops;
+struct devlink_linecard_type;
+
+struct devlink_linecard {
+ struct list_head list;
+ struct devlink *devlink;
+ unsigned int index;
+ refcount_t refcount;
+ const struct devlink_linecard_ops *ops;
+ void *priv;
+ enum devlink_linecard_state state;
+ struct mutex state_lock; /* Protects state */
+ const char *type;
+ struct devlink_linecard_type *types;
+ unsigned int types_count;
+};
+
/**
* struct devlink_resource - devlink resource
* @name: name of the resource
@@ -397,6 +416,58 @@ devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info)
return ERR_PTR(-EINVAL);
}
+static struct devlink_linecard *
+devlink_linecard_get_by_index(struct devlink *devlink,
+ unsigned int linecard_index)
+{
+ struct devlink_linecard *devlink_linecard;
+
+ list_for_each_entry(devlink_linecard, &devlink->linecard_list, list) {
+ if (devlink_linecard->index == linecard_index)
+ return devlink_linecard;
+ }
+ return NULL;
+}
+
+static bool devlink_linecard_index_exists(struct devlink *devlink,
+ unsigned int linecard_index)
+{
+ return devlink_linecard_get_by_index(devlink, linecard_index);
+}
+
+static struct devlink_linecard *
+devlink_linecard_get_from_attrs(struct devlink *devlink, struct nlattr **attrs)
+{
+ if (attrs[DEVLINK_ATTR_LINECARD_INDEX]) {
+ u32 linecard_index = nla_get_u32(attrs[DEVLINK_ATTR_LINECARD_INDEX]);
+ struct devlink_linecard *linecard;
+
+ mutex_lock(&devlink->linecards_lock);
+ linecard = devlink_linecard_get_by_index(devlink, linecard_index);
+ if (linecard)
+ refcount_inc(&linecard->refcount);
+ mutex_unlock(&devlink->linecards_lock);
+ if (!linecard)
+ return ERR_PTR(-ENODEV);
+ return linecard;
+ }
+ return ERR_PTR(-EINVAL);
+}
+
+static struct devlink_linecard *
+devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info)
+{
+ return devlink_linecard_get_from_attrs(devlink, info->attrs);
+}
+
+static void devlink_linecard_put(struct devlink_linecard *linecard)
+{
+ if (refcount_dec_and_test(&linecard->refcount)) {
+ mutex_destroy(&linecard->state_lock);
+ kfree(linecard);
+ }
+}
+
struct devlink_sb {
struct list_head list;
unsigned int index;
@@ -617,16 +688,18 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id)
#define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT BIT(1)
#define DEVLINK_NL_FLAG_NEED_RATE BIT(2)
#define DEVLINK_NL_FLAG_NEED_RATE_NODE BIT(3)
+#define DEVLINK_NL_FLAG_NEED_LINECARD BIT(4)
/* The per devlink instance lock is taken by default in the pre-doit
* operation, yet several commands do not require this. The global
* devlink lock is taken and protects from disruption by user-calls.
*/
-#define DEVLINK_NL_FLAG_NO_LOCK BIT(4)
+#define DEVLINK_NL_FLAG_NO_LOCK BIT(5)
static int devlink_nl_pre_doit(const struct genl_ops *ops,
struct sk_buff *skb, struct genl_info *info)
{
+ struct devlink_linecard *linecard;
struct devlink_port *devlink_port;
struct devlink *devlink;
int err;
@@ -669,6 +742,13 @@ static int devlink_nl_pre_doit(const struct genl_ops *ops,
goto unlock;
}
info->user_ptr[1] = rate_node;
+ } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_LINECARD) {
+ linecard = devlink_linecard_get_from_info(devlink, info);
+ if (IS_ERR(linecard)) {
+ err = PTR_ERR(linecard);
+ goto unlock;
+ }
+ info->user_ptr[1] = linecard;
}
return 0;
@@ -683,9 +763,14 @@ unlock:
static void devlink_nl_post_doit(const struct genl_ops *ops,
struct sk_buff *skb, struct genl_info *info)
{
+ struct devlink_linecard *linecard;
struct devlink *devlink;
devlink = info->user_ptr[0];
+ if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_LINECARD) {
+ linecard = info->user_ptr[1];
+ devlink_linecard_put(linecard);
+ }
if (~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK)
mutex_unlock(&devlink->lock);
devlink_put(devlink);
@@ -1158,6 +1243,10 @@ static int devlink_nl_port_fill(struct sk_buff *msg,
goto nla_put_failure;
if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack))
goto nla_put_failure;
+ if (devlink_port->linecard &&
+ nla_put_u32(msg, DEVLINK_ATTR_LINECARD_INDEX,
+ devlink_port->linecard->index))
+ goto nla_put_failure;
genlmsg_end(msg, hdr);
return 0;
@@ -1964,6 +2053,322 @@ static int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb,
return err;
}
+struct devlink_linecard_type {
+ const char *type;
+ const void *priv;
+};
+
+static int devlink_nl_linecard_fill(struct sk_buff *msg,
+ struct devlink *devlink,
+ struct devlink_linecard *linecard,
+ enum devlink_command cmd, u32 portid,
+ u32 seq, int flags,
+ struct netlink_ext_ack *extack)
+{
+ struct devlink_linecard_type *linecard_type;
+ struct nlattr *attr;
+ void *hdr;
+ int i;
+
+ hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ if (devlink_nl_put_handle(msg, devlink))
+ goto nla_put_failure;
+ if (nla_put_u32(msg, DEVLINK_ATTR_LINECARD_INDEX, linecard->index))
+ goto nla_put_failure;
+ if (nla_put_u8(msg, DEVLINK_ATTR_LINECARD_STATE, linecard->state))
+ goto nla_put_failure;
+ if (linecard->type &&
+ nla_put_string(msg, DEVLINK_ATTR_LINECARD_TYPE, linecard->type))
+ goto nla_put_failure;
+
+ if (linecard->types_count) {
+ attr = nla_nest_start(msg,
+ DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES);
+ if (!attr)
+ goto nla_put_failure;
+ for (i = 0; i < linecard->types_count; i++) {
+ linecard_type = &linecard->types[i];
+ if (nla_put_string(msg, DEVLINK_ATTR_LINECARD_TYPE,
+ linecard_type->type)) {
+ nla_nest_cancel(msg, attr);
+ goto nla_put_failure;
+ }
+ }
+ nla_nest_end(msg, attr);
+ }
+
+ genlmsg_end(msg, hdr);
+ return 0;
+
+nla_put_failure:
+ genlmsg_cancel(msg, hdr);
+ return -EMSGSIZE;
+}
+
+static void devlink_linecard_notify(struct devlink_linecard *linecard,
+ enum devlink_command cmd)
+{
+ struct devlink *devlink = linecard->devlink;
+ struct sk_buff *msg;
+ int err;
+
+ WARN_ON(cmd != DEVLINK_CMD_LINECARD_NEW &&
+ cmd != DEVLINK_CMD_LINECARD_DEL);
+
+ if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+ return;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return;
+
+ err = devlink_nl_linecard_fill(msg, devlink, linecard, cmd, 0, 0, 0,
+ NULL);
+ if (err) {
+ nlmsg_free(msg);
+ return;
+ }
+
+ genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+ msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+static int devlink_nl_cmd_linecard_get_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink_linecard *linecard = info->user_ptr[1];
+ struct devlink *devlink = linecard->devlink;
+ struct sk_buff *msg;
+ int err;
+
+ msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
+
+ mutex_lock(&linecard->state_lock);
+ err = devlink_nl_linecard_fill(msg, devlink, linecard,
+ DEVLINK_CMD_LINECARD_NEW,
+ info->snd_portid, info->snd_seq, 0,
+ info->extack);
+ mutex_unlock(&linecard->state_lock);
+ if (err) {
+ nlmsg_free(msg);
+ return err;
+ }
+
+ return genlmsg_reply(msg, info);
+}
+
+static int devlink_nl_cmd_linecard_get_dumpit(struct sk_buff *msg,
+ struct netlink_callback *cb)
+{
+ struct devlink_linecard *linecard;
+ struct devlink *devlink;
+ int start = cb->args[0];
+ unsigned long index;
+ int idx = 0;
+ int err;
+
+ mutex_lock(&devlink_mutex);
+ xa_for_each_marked(&devlinks, index, devlink, DEVLINK_REGISTERED) {
+ if (!devlink_try_get(devlink))
+ continue;
+
+ if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
+ goto retry;
+
+ mutex_lock(&devlink->linecards_lock);
+ list_for_each_entry(linecard, &devlink->linecard_list, list) {
+ if (idx < start) {
+ idx++;
+ continue;
+ }
+ mutex_lock(&linecard->state_lock);
+ err = devlink_nl_linecard_fill(msg, devlink, linecard,
+ DEVLINK_CMD_LINECARD_NEW,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NLM_F_MULTI,
+ cb->extack);
+ mutex_unlock(&linecard->state_lock);
+ if (err) {
+ mutex_unlock(&devlink->linecards_lock);
+ devlink_put(devlink);
+ goto out;
+ }
+ idx++;
+ }
+ mutex_unlock(&devlink->linecards_lock);
+retry:
+ devlink_put(devlink);
+ }
+out:
+ mutex_unlock(&devlink_mutex);
+
+ cb->args[0] = idx;
+ return msg->len;
+}
+
+static struct devlink_linecard_type *
+devlink_linecard_type_lookup(struct devlink_linecard *linecard,
+ const char *type)
+{
+ struct devlink_linecard_type *linecard_type;
+ int i;
+
+ for (i = 0; i < linecard->types_count; i++) {
+ linecard_type = &linecard->types[i];
+ if (!strcmp(type, linecard_type->type))
+ return linecard_type;
+ }
+ return NULL;
+}
+
+static int devlink_linecard_type_set(struct devlink_linecard *linecard,
+ const char *type,
+ struct netlink_ext_ack *extack)
+{
+ const struct devlink_linecard_ops *ops = linecard->ops;
+ struct devlink_linecard_type *linecard_type;
+ int err;
+
+ mutex_lock(&linecard->state_lock);
+ if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) {
+ NL_SET_ERR_MSG_MOD(extack, "Line card is currently being provisioned");
+ err = -EBUSY;
+ goto out;
+ }
+ if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) {
+ NL_SET_ERR_MSG_MOD(extack, "Line card is currently being unprovisioned");
+ err = -EBUSY;
+ goto out;
+ }
+
+ linecard_type = devlink_linecard_type_lookup(linecard, type);
+ if (!linecard_type) {
+ NL_SET_ERR_MSG_MOD(extack, "Unsupported line card type provided");
+ err = -EINVAL;
+ goto out;
+ }
+
+ if (linecard->state != DEVLINK_LINECARD_STATE_UNPROVISIONED &&
+ linecard->state != DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) {
+ NL_SET_ERR_MSG_MOD(extack, "Line card already provisioned");
+ err = -EBUSY;
+ /* Check if the line card is provisioned in the same
+ * way the user asks. In case it is, make the operation
+ * to return success.
+ */
+ if (ops->same_provision &&
+ ops->same_provision(linecard, linecard->priv,
+ linecard_type->type,
+ linecard_type->priv))
+ err = 0;
+ goto out;
+ }
+
+ linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING;
+ linecard->type = linecard_type->type;
+ devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+ mutex_unlock(&linecard->state_lock);
+ err = ops->provision(linecard, linecard->priv, linecard_type->type,
+ linecard_type->priv, extack);
+ if (err) {
+ /* Provisioning failed. Assume the linecard is unprovisioned
+ * for future operations.
+ */
+ mutex_lock(&linecard->state_lock);
+ linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+ linecard->type = NULL;
+ devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+ mutex_unlock(&linecard->state_lock);
+ }
+ return err;
+
+out:
+ mutex_unlock(&linecard->state_lock);
+ return err;
+}
+
+static int devlink_linecard_type_unset(struct devlink_linecard *linecard,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ mutex_lock(&linecard->state_lock);
+ if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING) {
+ NL_SET_ERR_MSG_MOD(extack, "Line card is currently being provisioned");
+ err = -EBUSY;
+ goto out;
+ }
+ if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONING) {
+ NL_SET_ERR_MSG_MOD(extack, "Line card is currently being unprovisioned");
+ err = -EBUSY;
+ goto out;
+ }
+ if (linecard->state == DEVLINK_LINECARD_STATE_PROVISIONING_FAILED) {
+ linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+ linecard->type = NULL;
+ devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+ err = 0;
+ goto out;
+ }
+
+ if (linecard->state == DEVLINK_LINECARD_STATE_UNPROVISIONED) {
+ NL_SET_ERR_MSG_MOD(extack, "Line card is not provisioned");
+ err = 0;
+ goto out;
+ }
+ linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONING;
+ devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+ mutex_unlock(&linecard->state_lock);
+ err = linecard->ops->unprovision(linecard, linecard->priv,
+ extack);
+ if (err) {
+ /* Unprovisioning failed. Assume the linecard is unprovisioned
+ * for future operations.
+ */
+ mutex_lock(&linecard->state_lock);
+ linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+ linecard->type = NULL;
+ devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+ mutex_unlock(&linecard->state_lock);
+ }
+ return err;
+
+out:
+ mutex_unlock(&linecard->state_lock);
+ return err;
+}
+
+static int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb,
+ struct genl_info *info)
+{
+ struct devlink_linecard *linecard = info->user_ptr[1];
+ struct netlink_ext_ack *extack = info->extack;
+ int err;
+
+ if (info->attrs[DEVLINK_ATTR_LINECARD_TYPE]) {
+ const char *type;
+
+ type = nla_data(info->attrs[DEVLINK_ATTR_LINECARD_TYPE]);
+ if (strcmp(type, "")) {
+ err = devlink_linecard_type_set(linecard, type, extack);
+ if (err)
+ return err;
+ } else {
+ err = devlink_linecard_type_unset(linecard, extack);
+ if (err)
+ return err;
+ }
+ }
+
+ return 0;
+}
+
static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink,
struct devlink_sb *devlink_sb,
enum devlink_command cmd, u32 portid,
@@ -8589,6 +8994,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
[DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64 },
[DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING },
[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING },
+ [DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32 },
+ [DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING },
};
static const struct genl_small_ops devlink_nl_ops[] = {
@@ -8665,6 +9072,19 @@ static const struct genl_small_ops devlink_nl_ops[] = {
.internal_flags = DEVLINK_NL_FLAG_NO_LOCK,
},
{
+ .cmd = DEVLINK_CMD_LINECARD_GET,
+ .doit = devlink_nl_cmd_linecard_get_doit,
+ .dumpit = devlink_nl_cmd_linecard_get_dumpit,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_LINECARD,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = DEVLINK_CMD_LINECARD_SET,
+ .doit = devlink_nl_cmd_linecard_set_doit,
+ .flags = GENL_ADMIN_PERM,
+ .internal_flags = DEVLINK_NL_FLAG_NEED_LINECARD,
+ },
+ {
.cmd = DEVLINK_CMD_SB_GET,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = devlink_nl_cmd_sb_get_doit,
@@ -9043,6 +9463,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops,
write_pnet(&devlink->_net, net);
INIT_LIST_HEAD(&devlink->port_list);
INIT_LIST_HEAD(&devlink->rate_list);
+ INIT_LIST_HEAD(&devlink->linecard_list);
INIT_LIST_HEAD(&devlink->sb_list);
INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
INIT_LIST_HEAD(&devlink->resource_list);
@@ -9054,6 +9475,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops,
INIT_LIST_HEAD(&devlink->trap_policer_list);
mutex_init(&devlink->lock);
mutex_init(&devlink->reporters_lock);
+ mutex_init(&devlink->linecards_lock);
refcount_set(&devlink->refcount, 1);
init_completion(&devlink->comp);
@@ -9080,10 +9502,14 @@ static void devlink_notify_register(struct devlink *devlink)
struct devlink_param_item *param_item;
struct devlink_trap_item *trap_item;
struct devlink_port *devlink_port;
+ struct devlink_linecard *linecard;
struct devlink_rate *rate_node;
struct devlink_region *region;
devlink_notify(devlink, DEVLINK_CMD_NEW);
+ list_for_each_entry(linecard, &devlink->linecard_list, list)
+ devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+
list_for_each_entry(devlink_port, &devlink->port_list, list)
devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
@@ -9191,6 +9617,7 @@ void devlink_free(struct devlink *devlink)
{
ASSERT_DEVLINK_NOT_REGISTERED(devlink);
+ mutex_destroy(&devlink->linecards_lock);
mutex_destroy(&devlink->reporters_lock);
mutex_destroy(&devlink->lock);
WARN_ON(!list_empty(&devlink->trap_policer_list));
@@ -9203,6 +9630,7 @@ void devlink_free(struct devlink *devlink)
WARN_ON(!list_empty(&devlink->dpipe_table_list));
WARN_ON(!list_empty(&devlink->sb_list));
WARN_ON(!list_empty(&devlink->rate_list));
+ WARN_ON(!list_empty(&devlink->linecard_list));
WARN_ON(!list_empty(&devlink->port_list));
xa_destroy(&devlink->snapshot_ids);
@@ -9681,6 +10109,21 @@ void devlink_rate_nodes_destroy(struct devlink *devlink)
}
EXPORT_SYMBOL_GPL(devlink_rate_nodes_destroy);
+/**
+ * devlink_port_linecard_set - Link port with a linecard
+ *
+ * @devlink_port: devlink port
+ * @linecard: devlink linecard
+ */
+void devlink_port_linecard_set(struct devlink_port *devlink_port,
+ struct devlink_linecard *linecard)
+{
+ if (WARN_ON(devlink_port->devlink))
+ return;
+ devlink_port->linecard = linecard;
+}
+EXPORT_SYMBOL_GPL(devlink_port_linecard_set);
+
static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
char *name, size_t len)
{
@@ -9692,7 +10135,12 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
switch (attrs->flavour) {
case DEVLINK_PORT_FLAVOUR_PHYSICAL:
- n = snprintf(name, len, "p%u", attrs->phys.port_number);
+ if (devlink_port->linecard)
+ n = snprintf(name, len, "l%u",
+ devlink_port->linecard->index);
+ if (n < len)
+ n += snprintf(name + n, len - n, "p%u",
+ attrs->phys.port_number);
if (n < len && attrs->split)
n += snprintf(name + n, len - n, "s%u",
attrs->phys.split_subport_number);
@@ -9747,6 +10195,207 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
return 0;
}
+static int devlink_linecard_types_init(struct devlink_linecard *linecard)
+{
+ struct devlink_linecard_type *linecard_type;
+ unsigned int count;
+ int i;
+
+ count = linecard->ops->types_count(linecard, linecard->priv);
+ linecard->types = kmalloc_array(count, sizeof(*linecard_type),
+ GFP_KERNEL);
+ if (!linecard->types)
+ return -ENOMEM;
+ linecard->types_count = count;
+
+ for (i = 0; i < count; i++) {
+ linecard_type = &linecard->types[i];
+ linecard->ops->types_get(linecard, linecard->priv, i,
+ &linecard_type->type,
+ &linecard_type->priv);
+ }
+ return 0;
+}
+
+static void devlink_linecard_types_fini(struct devlink_linecard *linecard)
+{
+ kfree(linecard->types);
+}
+
+/**
+ * devlink_linecard_create - Create devlink linecard
+ *
+ * @devlink: devlink
+ * @linecard_index: driver-specific numerical identifier of the linecard
+ * @ops: linecards ops
+ * @priv: user priv pointer
+ *
+ * Create devlink linecard instance with provided linecard index.
+ * Caller can use any indexing, even hw-related one.
+ *
+ * Return: Line card structure or an ERR_PTR() encoded error code.
+ */
+struct devlink_linecard *
+devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index,
+ const struct devlink_linecard_ops *ops, void *priv)
+{
+ struct devlink_linecard *linecard;
+ int err;
+
+ if (WARN_ON(!ops || !ops->provision || !ops->unprovision ||
+ !ops->types_count || !ops->types_get))
+ return ERR_PTR(-EINVAL);
+
+ mutex_lock(&devlink->linecards_lock);
+ if (devlink_linecard_index_exists(devlink, linecard_index)) {
+ mutex_unlock(&devlink->linecards_lock);
+ return ERR_PTR(-EEXIST);
+ }
+
+ linecard = kzalloc(sizeof(*linecard), GFP_KERNEL);
+ if (!linecard) {
+ mutex_unlock(&devlink->linecards_lock);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ linecard->devlink = devlink;
+ linecard->index = linecard_index;
+ linecard->ops = ops;
+ linecard->priv = priv;
+ linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+ mutex_init(&linecard->state_lock);
+
+ err = devlink_linecard_types_init(linecard);
+ if (err) {
+ mutex_destroy(&linecard->state_lock);
+ kfree(linecard);
+ mutex_unlock(&devlink->linecards_lock);
+ return ERR_PTR(err);
+ }
+
+ list_add_tail(&linecard->list, &devlink->linecard_list);
+ refcount_set(&linecard->refcount, 1);
+ mutex_unlock(&devlink->linecards_lock);
+ devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+ return linecard;
+}
+EXPORT_SYMBOL_GPL(devlink_linecard_create);
+
+/**
+ * devlink_linecard_destroy - Destroy devlink linecard
+ *
+ * @linecard: devlink linecard
+ */
+void devlink_linecard_destroy(struct devlink_linecard *linecard)
+{
+ struct devlink *devlink = linecard->devlink;
+
+ devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_DEL);
+ mutex_lock(&devlink->linecards_lock);
+ list_del(&linecard->list);
+ devlink_linecard_types_fini(linecard);
+ mutex_unlock(&devlink->linecards_lock);
+ devlink_linecard_put(linecard);
+}
+EXPORT_SYMBOL_GPL(devlink_linecard_destroy);
+
+/**
+ * devlink_linecard_provision_set - Set provisioning on linecard
+ *
+ * @linecard: devlink linecard
+ * @type: linecard type
+ *
+ * This is either called directly from the provision() op call or
+ * as a result of the provision() op call asynchronously.
+ */
+void devlink_linecard_provision_set(struct devlink_linecard *linecard,
+ const char *type)
+{
+ mutex_lock(&linecard->state_lock);
+ WARN_ON(linecard->type && strcmp(linecard->type, type));
+ linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED;
+ linecard->type = type;
+ devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+ mutex_unlock(&linecard->state_lock);
+}
+EXPORT_SYMBOL_GPL(devlink_linecard_provision_set);
+
+/**
+ * devlink_linecard_provision_clear - Clear provisioning on linecard
+ *
+ * @linecard: devlink linecard
+ *
+ * This is either called directly from the unprovision() op call or
+ * as a result of the unprovision() op call asynchronously.
+ */
+void devlink_linecard_provision_clear(struct devlink_linecard *linecard)
+{
+ mutex_lock(&linecard->state_lock);
+ linecard->state = DEVLINK_LINECARD_STATE_UNPROVISIONED;
+ linecard->type = NULL;
+ devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+ mutex_unlock(&linecard->state_lock);
+}
+EXPORT_SYMBOL_GPL(devlink_linecard_provision_clear);
+
+/**
+ * devlink_linecard_provision_fail - Fail provisioning on linecard
+ *
+ * @linecard: devlink linecard
+ *
+ * This is either called directly from the provision() op call or
+ * as a result of the provision() op call asynchronously.
+ */
+void devlink_linecard_provision_fail(struct devlink_linecard *linecard)
+{
+ mutex_lock(&linecard->state_lock);
+ linecard->state = DEVLINK_LINECARD_STATE_PROVISIONING_FAILED;
+ devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+ mutex_unlock(&linecard->state_lock);
+}
+EXPORT_SYMBOL_GPL(devlink_linecard_provision_fail);
+
+/**
+ * devlink_linecard_activate - Set linecard active
+ *
+ * @linecard: devlink linecard
+ */
+void devlink_linecard_activate(struct devlink_linecard *linecard)
+{
+ mutex_lock(&linecard->state_lock);
+ WARN_ON(linecard->state != DEVLINK_LINECARD_STATE_PROVISIONED);
+ linecard->state = DEVLINK_LINECARD_STATE_ACTIVE;
+ devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+ mutex_unlock(&linecard->state_lock);
+}
+EXPORT_SYMBOL_GPL(devlink_linecard_activate);
+
+/**
+ * devlink_linecard_deactivate - Set linecard inactive
+ *
+ * @linecard: devlink linecard
+ */
+void devlink_linecard_deactivate(struct devlink_linecard *linecard)
+{
+ mutex_lock(&linecard->state_lock);
+ switch (linecard->state) {
+ case DEVLINK_LINECARD_STATE_ACTIVE:
+ linecard->state = DEVLINK_LINECARD_STATE_PROVISIONED;
+ devlink_linecard_notify(linecard, DEVLINK_CMD_LINECARD_NEW);
+ break;
+ case DEVLINK_LINECARD_STATE_UNPROVISIONING:
+ /* Line card is being deactivated as part
+ * of unprovisioning flow.
+ */
+ break;
+ default:
+ WARN_ON(1);
+ break;
+ }
+ mutex_unlock(&linecard->state_lock);
+}
+EXPORT_SYMBOL_GPL(devlink_linecard_deactivate);
+
int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
u32 size, u16 ingress_pools_count,
u16 egress_pools_count, u16 ingress_tc_count,
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index b89e3e95bffc..41cac0e4834e 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -517,7 +517,7 @@ static void net_dm_packet_trace_kfree_skb_hit(void *ignore,
if (!nskb)
return;
- if ((unsigned int)reason >= SKB_DROP_REASON_MAX)
+ if (unlikely(reason >= SKB_DROP_REASON_MAX || reason <= 0))
reason = SKB_DROP_REASON_NOT_SPECIFIED;
cb = NET_DM_SKB_CB(nskb);
cb->reason = reason;
diff --git a/net/core/filter.c b/net/core/filter.c
index 64470a727ef7..5af58eb48587 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -78,6 +78,7 @@
#include <linux/btf_ids.h>
#include <net/tls.h>
#include <net/xdp.h>
+#include <net/mptcp.h>
static const struct bpf_func_proto *
bpf_sk_base_func_proto(enum bpf_func_id func_id);
@@ -1687,7 +1688,7 @@ BPF_CALL_5(bpf_skb_store_bytes, struct sk_buff *, skb, u32, offset,
if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH)))
return -EINVAL;
- if (unlikely(offset > 0xffff))
+ if (unlikely(offset > INT_MAX))
return -EFAULT;
if (unlikely(bpf_try_make_writable(skb, offset + len)))
return -EFAULT;
@@ -1722,7 +1723,7 @@ BPF_CALL_4(bpf_skb_load_bytes, const struct sk_buff *, skb, u32, offset,
{
void *ptr;
- if (unlikely(offset > 0xffff))
+ if (unlikely(offset > INT_MAX))
goto err_clear;
ptr = skb_header_pointer(skb, offset, len, to);
@@ -4498,6 +4499,7 @@ BPF_CALL_4(bpf_skb_get_tunnel_key, struct sk_buff *, skb, struct bpf_tunnel_key
if (unlikely(size != sizeof(struct bpf_tunnel_key))) {
err = -EINVAL;
switch (size) {
+ case offsetof(struct bpf_tunnel_key, local_ipv6[0]):
case offsetof(struct bpf_tunnel_key, tunnel_label):
case offsetof(struct bpf_tunnel_key, tunnel_ext):
goto set_compat;
@@ -4523,10 +4525,14 @@ set_compat:
if (flags & BPF_F_TUNINFO_IPV6) {
memcpy(to->remote_ipv6, &info->key.u.ipv6.src,
sizeof(to->remote_ipv6));
+ memcpy(to->local_ipv6, &info->key.u.ipv6.dst,
+ sizeof(to->local_ipv6));
to->tunnel_label = be32_to_cpu(info->key.label);
} else {
to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src);
memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3);
+ to->local_ipv4 = be32_to_cpu(info->key.u.ipv4.dst);
+ memset(&to->local_ipv6[1], 0, sizeof(__u32) * 3);
to->tunnel_label = 0;
}
@@ -4597,6 +4603,7 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb,
return -EINVAL;
if (unlikely(size != sizeof(struct bpf_tunnel_key))) {
switch (size) {
+ case offsetof(struct bpf_tunnel_key, local_ipv6[0]):
case offsetof(struct bpf_tunnel_key, tunnel_label):
case offsetof(struct bpf_tunnel_key, tunnel_ext):
case offsetof(struct bpf_tunnel_key, remote_ipv6[1]):
@@ -4639,10 +4646,13 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb,
info->mode |= IP_TUNNEL_INFO_IPV6;
memcpy(&info->key.u.ipv6.dst, from->remote_ipv6,
sizeof(from->remote_ipv6));
+ memcpy(&info->key.u.ipv6.src, from->local_ipv6,
+ sizeof(from->local_ipv6));
info->key.label = cpu_to_be32(from->tunnel_label) &
IPV6_FLOWLABEL_MASK;
} else {
info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4);
+ info->key.u.ipv4.src = cpu_to_be32(from->local_ipv4);
}
return 0;
@@ -5173,7 +5183,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
if (val <= 0 || tp->data_segs_out > tp->syn_data)
ret = -EINVAL;
else
- tp->snd_cwnd = val;
+ tcp_snd_cwnd_set(tp, val);
break;
case TCP_BPF_SNDCWND_CLAMP:
if (val <= 0) {
@@ -6621,7 +6631,7 @@ static const struct bpf_func_proto bpf_sk_release_proto = {
.func = bpf_sk_release,
.gpl_only = false,
.ret_type = RET_INTEGER,
- .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
+ .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON | OBJ_RELEASE,
};
BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
@@ -7099,7 +7109,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len,
*/
switch (((struct iphdr *)iph)->version) {
case 4:
- if (sk->sk_family == AF_INET6 && sk->sk_ipv6only)
+ if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk))
return -EINVAL;
mss = tcp_v4_get_syncookie(sk, iph, th, &cookie);
@@ -11272,6 +11282,20 @@ const struct bpf_func_proto bpf_skc_to_unix_sock_proto = {
.ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UNIX],
};
+BPF_CALL_1(bpf_skc_to_mptcp_sock, struct sock *, sk)
+{
+ BTF_TYPE_EMIT(struct mptcp_sock);
+ return (unsigned long)bpf_mptcp_sock_from_subflow(sk);
+}
+
+const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto = {
+ .func = bpf_skc_to_mptcp_sock,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_BTF_ID_OR_NULL,
+ .arg1_type = ARG_PTR_TO_SOCK_COMMON,
+ .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_MPTCP],
+};
+
BPF_CALL_1(bpf_sock_from_file, struct file *, file)
{
return (unsigned long)sock_from_file(file);
@@ -11314,6 +11338,9 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id)
case BPF_FUNC_skc_to_unix_sock:
func = &bpf_skc_to_unix_sock_proto;
break;
+ case BPF_FUNC_skc_to_mptcp_sock:
+ func = &bpf_skc_to_mptcp_sock_proto;
+ break;
case BPF_FUNC_ktime_get_coarse_ns:
return &bpf_ktime_get_coarse_ns_proto;
default:
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 6f7ec72016dc..6aee04f75e3e 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1035,6 +1035,16 @@ bool __skb_flow_dissect(const struct net *net,
memcpy(key_eth_addrs, eth, sizeof(*key_eth_addrs));
}
+ if (dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_NUM_OF_VLANS)) {
+ struct flow_dissector_key_num_of_vlans *key_num_of_vlans;
+
+ key_num_of_vlans = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_NUM_OF_VLANS,
+ target_container);
+ key_num_of_vlans->num_of_vlans = 0;
+ }
+
proto_again:
fdret = FLOW_DISSECT_RET_CONTINUE;
@@ -1158,6 +1168,16 @@ proto_again:
nhoff += sizeof(*vlan);
}
+ if (dissector_uses_key(flow_dissector,
+ FLOW_DISSECTOR_KEY_NUM_OF_VLANS)) {
+ struct flow_dissector_key_num_of_vlans *key_nvs;
+
+ key_nvs = skb_flow_dissector_target(flow_dissector,
+ FLOW_DISSECTOR_KEY_NUM_OF_VLANS,
+ target_container);
+ key_nvs->num_of_vlans++;
+ }
+
if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX) {
dissector_vlan = FLOW_DISSECTOR_KEY_VLAN;
} else if (dissector_vlan == FLOW_DISSECTOR_KEY_VLAN) {
diff --git a/net/core/gro.c b/net/core/gro.c
index 78110edf5d4b..b4190eb08467 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -167,6 +167,14 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush))
return -E2BIG;
+ if (unlikely(p->len + len >= GRO_LEGACY_MAX_SIZE)) {
+ if (p->protocol != htons(ETH_P_IPV6) ||
+ skb_headroom(p) < sizeof(struct hop_jumbo_hdr) ||
+ ipv6_hdr(p)->nexthdr != IPPROTO_TCP ||
+ p->encapsulation)
+ return -E2BIG;
+ }
+
lp = NAPI_GRO_CB(p)->last;
pinfo = skb_shinfo(lp);
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index 95098d1a49bd..a244d3bade7d 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -18,6 +18,7 @@
#include <linux/bitops.h>
#include <linux/types.h>
+#include "dev.h"
enum lw_bits {
LW_URGENT = 0,
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index f64ebd050f6c..47b6c1f0fdbb 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -3728,7 +3728,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
char neigh_path[ sizeof("net//neigh/") + IFNAMSIZ + IFNAMSIZ ];
char *p_name;
- t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL);
+ t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL_ACCOUNT);
if (!t)
goto err;
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index 88cc0ad7d386..1ec23bf8b05c 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -4,6 +4,8 @@
#include <linux/seq_file.h>
#include <net/wext.h>
+#include "dev.h"
+
#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1)
#define get_bucket(x) ((x) >> BUCKET_SPACE)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 9cbc1c8289bc..e319e242dddf 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 "dev.h"
#include "net-sysfs.h"
#ifdef CONFIG_SYSFS
@@ -745,7 +746,6 @@ static const struct attribute_group netstat_group = {
.attrs = netstat_attrs,
};
-#if IS_ENABLED(CONFIG_WIRELESS_EXT) || IS_ENABLED(CONFIG_CFG80211)
static struct attribute *wireless_attrs[] = {
NULL
};
@@ -754,7 +754,19 @@ static const struct attribute_group wireless_group = {
.name = "wireless",
.attrs = wireless_attrs,
};
+
+static bool wireless_group_needed(struct net_device *ndev)
+{
+#if IS_ENABLED(CONFIG_CFG80211)
+ if (ndev->ieee80211_ptr)
+ return true;
#endif
+#if IS_ENABLED(CONFIG_WIRELESS_EXT)
+ if (ndev->wireless_handlers)
+ return true;
+#endif
+ return false;
+}
#else /* CONFIG_SYSFS */
#define net_class_groups NULL
@@ -1995,14 +2007,8 @@ int netdev_register_kobject(struct net_device *ndev)
*groups++ = &netstat_group;
-#if IS_ENABLED(CONFIG_WIRELESS_EXT) || IS_ENABLED(CONFIG_CFG80211)
- if (ndev->ieee80211_ptr)
- *groups++ = &wireless_group;
-#if IS_ENABLED(CONFIG_WIRELESS_EXT)
- else if (ndev->wireless_handlers)
+ if (wireless_group_needed(ndev))
*groups++ = &wireless_group;
-#endif
-#endif
#endif /* CONFIG_SYSFS */
error = device_add(dev);
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 1943c0f0307d..f18e6e771993 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -18,6 +18,7 @@
#include <linux/page-flags.h>
#include <linux/mm.h> /* for __put_page() */
#include <linux/poison.h>
+#include <linux/ethtool.h>
#include <trace/events/page_pool.h>
@@ -36,6 +37,26 @@
this_cpu_inc(s->__stat); \
} while (0)
+#define recycle_stat_add(pool, __stat, val) \
+ do { \
+ struct page_pool_recycle_stats __percpu *s = pool->recycle_stats; \
+ this_cpu_add(s->__stat, val); \
+ } while (0)
+
+static const char pp_stats[][ETH_GSTRING_LEN] = {
+ "rx_pp_alloc_fast",
+ "rx_pp_alloc_slow",
+ "rx_pp_alloc_slow_ho",
+ "rx_pp_alloc_empty",
+ "rx_pp_alloc_refill",
+ "rx_pp_alloc_waive",
+ "rx_pp_recycle_cached",
+ "rx_pp_recycle_cache_full",
+ "rx_pp_recycle_ring",
+ "rx_pp_recycle_ring_full",
+ "rx_pp_recycle_released_ref",
+};
+
bool page_pool_get_stats(struct page_pool *pool,
struct page_pool_stats *stats)
{
@@ -44,7 +65,13 @@ bool page_pool_get_stats(struct page_pool *pool,
if (!stats)
return false;
- memcpy(&stats->alloc_stats, &pool->alloc_stats, sizeof(pool->alloc_stats));
+ /* The caller is responsible to initialize stats. */
+ stats->alloc_stats.fast += pool->alloc_stats.fast;
+ stats->alloc_stats.slow += pool->alloc_stats.slow;
+ stats->alloc_stats.slow_high_order += pool->alloc_stats.slow_high_order;
+ stats->alloc_stats.empty += pool->alloc_stats.empty;
+ stats->alloc_stats.refill += pool->alloc_stats.refill;
+ stats->alloc_stats.waive += pool->alloc_stats.waive;
for_each_possible_cpu(cpu) {
const struct page_pool_recycle_stats *pcpu =
@@ -60,9 +87,50 @@ bool page_pool_get_stats(struct page_pool *pool,
return true;
}
EXPORT_SYMBOL(page_pool_get_stats);
+
+u8 *page_pool_ethtool_stats_get_strings(u8 *data)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(pp_stats); i++) {
+ memcpy(data, pp_stats[i], ETH_GSTRING_LEN);
+ data += ETH_GSTRING_LEN;
+ }
+
+ return data;
+}
+EXPORT_SYMBOL(page_pool_ethtool_stats_get_strings);
+
+int page_pool_ethtool_stats_get_count(void)
+{
+ return ARRAY_SIZE(pp_stats);
+}
+EXPORT_SYMBOL(page_pool_ethtool_stats_get_count);
+
+u64 *page_pool_ethtool_stats_get(u64 *data, void *stats)
+{
+ struct page_pool_stats *pool_stats = stats;
+
+ *data++ = pool_stats->alloc_stats.fast;
+ *data++ = pool_stats->alloc_stats.slow;
+ *data++ = pool_stats->alloc_stats.slow_high_order;
+ *data++ = pool_stats->alloc_stats.empty;
+ *data++ = pool_stats->alloc_stats.refill;
+ *data++ = pool_stats->alloc_stats.waive;
+ *data++ = pool_stats->recycle_stats.cached;
+ *data++ = pool_stats->recycle_stats.cache_full;
+ *data++ = pool_stats->recycle_stats.ring;
+ *data++ = pool_stats->recycle_stats.ring_full;
+ *data++ = pool_stats->recycle_stats.released_refcnt;
+
+ return data;
+}
+EXPORT_SYMBOL(page_pool_ethtool_stats_get);
+
#else
#define alloc_stat_inc(pool, __stat)
#define recycle_stat_inc(pool, __stat)
+#define recycle_stat_add(pool, __stat, val)
#endif
static int page_pool_init(struct page_pool *pool,
@@ -566,9 +634,13 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data,
/* 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 */
+ if (__ptr_ring_produce(&pool->ring, data[i])) {
+ /* ring full */
+ recycle_stat_inc(pool, ring_full);
+ break;
+ }
}
+ recycle_stat_add(pool, ring, i);
page_pool_ring_unlock(pool);
/* Hopefully all pages was return into ptr_ring */
@@ -632,8 +704,10 @@ struct page *page_pool_alloc_frag(struct page_pool *pool,
if (page && *offset + size > max_size) {
page = page_pool_drain_frag(pool, page);
- if (page)
+ if (page) {
+ alloc_stat_inc(pool, fast);
goto frag_reset;
+ }
}
if (!page) {
@@ -655,6 +729,7 @@ frag_reset:
pool->frag_users++;
pool->frag_offset = *offset + size;
+ alloc_stat_inc(pool, fast);
return page;
}
EXPORT_SYMBOL(page_pool_alloc_frag);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d1381ea6d52e..ac45328607f7 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -54,6 +54,8 @@
#include <net/rtnetlink.h>
#include <net/net_namespace.h>
+#include "dev.h"
+
#define RTNL_MAX_TYPE 50
#define RTNL_SLAVE_MAX_TYPE 40
@@ -95,6 +97,39 @@ void __rtnl_unlock(void)
defer_kfree_skb_list = NULL;
+ /* Ensure that we didn't actually add any TODO item when __rtnl_unlock()
+ * is used. In some places, e.g. in cfg80211, we have code that will do
+ * something like
+ * rtnl_lock()
+ * wiphy_lock()
+ * ...
+ * rtnl_unlock()
+ *
+ * and because netdev_run_todo() acquires the RTNL for items on the list
+ * we could cause a situation such as this:
+ * Thread 1 Thread 2
+ * rtnl_lock()
+ * unregister_netdevice()
+ * __rtnl_unlock()
+ * rtnl_lock()
+ * wiphy_lock()
+ * rtnl_unlock()
+ * netdev_run_todo()
+ * __rtnl_unlock()
+ *
+ * // list not empty now
+ * // because of thread 2
+ * rtnl_lock()
+ * while (!list_empty(...))
+ * rtnl_lock()
+ * wiphy_lock()
+ * **** DEADLOCK ****
+ *
+ * However, usage of __rtnl_unlock() is rare, and so we can ensure that
+ * it's not used in cases where something is added to do the list.
+ */
+ WARN_ON(!list_empty(&net_todo_list));
+
mutex_unlock(&rtnl_mutex);
while (head) {
@@ -214,6 +249,8 @@ static int rtnl_register_internal(struct module *owner,
if (dumpit)
link->dumpit = dumpit;
+ WARN_ON(rtnl_msgtype_kind(msgtype) != RTNL_KIND_DEL &&
+ (flags & RTNL_FLAG_BULK_DEL_SUPPORTED));
link->flags |= flags;
/* publish protocol:msgtype */
@@ -1027,6 +1064,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(4) /* IFLA_GSO_MAX_SEGS */
+ nla_total_size(4) /* IFLA_GSO_MAX_SIZE */
+ nla_total_size(4) /* IFLA_GRO_MAX_SIZE */
+ + nla_total_size(4) /* IFLA_TSO_MAX_SIZE */
+ + nla_total_size(4) /* IFLA_TSO_MAX_SEGS */
+ nla_total_size(1) /* IFLA_OPERSTATE */
+ nla_total_size(1) /* IFLA_LINKMODE */
+ nla_total_size(4) /* IFLA_CARRIER_CHANGES */
@@ -1732,6 +1771,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
nla_put_u32(skb, IFLA_GSO_MAX_SEGS, dev->gso_max_segs) ||
nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) ||
nla_put_u32(skb, IFLA_GRO_MAX_SIZE, dev->gro_max_size) ||
+ nla_put_u32(skb, IFLA_TSO_MAX_SIZE, dev->tso_max_size) ||
+ nla_put_u32(skb, IFLA_TSO_MAX_SEGS, dev->tso_max_segs) ||
#ifdef CONFIG_RPS
nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||
#endif
@@ -1885,6 +1926,8 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_NEW_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1),
[IFLA_PARENT_DEV_NAME] = { .type = NLA_NUL_STRING },
[IFLA_GRO_MAX_SIZE] = { .type = NLA_U32 },
+ [IFLA_TSO_MAX_SIZE] = { .type = NLA_REJECT },
+ [IFLA_TSO_MAX_SEGS] = { .type = NLA_REJECT },
};
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2269,6 +2312,19 @@ invalid_attr:
return -EINVAL;
}
+static int rtnl_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate,
+ int max_tx_rate)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (!ops->ndo_set_vf_rate)
+ return -EOPNOTSUPP;
+ if (max_tx_rate && max_tx_rate < min_tx_rate)
+ return -EINVAL;
+
+ return ops->ndo_set_vf_rate(dev, vf, min_tx_rate, max_tx_rate);
+}
+
static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[],
struct netlink_ext_ack *extack)
{
@@ -2304,14 +2360,6 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[],
}
}
- if (tb[IFLA_GRO_MAX_SIZE]) {
- u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_MAX_SIZE]);
-
- if (gro_max_size > GRO_MAX_SIZE) {
- NL_SET_ERR_MSG(extack, "too big gro_max_size");
- return -EINVAL;
- }
- }
return 0;
}
@@ -2406,11 +2454,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (err < 0)
return err;
- err = -EOPNOTSUPP;
- if (ops->ndo_set_vf_rate)
- err = ops->ndo_set_vf_rate(dev, ivt->vf,
- ivf.min_tx_rate,
- ivt->rate);
+ err = rtnl_set_vf_rate(dev, ivt->vf,
+ ivf.min_tx_rate, ivt->rate);
if (err < 0)
return err;
}
@@ -2420,11 +2465,9 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
if (ivt->vf >= INT_MAX)
return -EINVAL;
- err = -EOPNOTSUPP;
- if (ops->ndo_set_vf_rate)
- err = ops->ndo_set_vf_rate(dev, ivt->vf,
- ivt->min_tx_rate,
- ivt->max_tx_rate);
+
+ err = rtnl_set_vf_rate(dev, ivt->vf,
+ ivt->min_tx_rate, ivt->max_tx_rate);
if (err < 0)
return err;
}
@@ -2607,17 +2650,23 @@ static int do_set_proto_down(struct net_device *dev,
static int do_setlink(const struct sk_buff *skb,
struct net_device *dev, struct ifinfomsg *ifm,
struct netlink_ext_ack *extack,
- struct nlattr **tb, char *ifname, int status)
+ struct nlattr **tb, int status)
{
const struct net_device_ops *ops = dev->netdev_ops;
+ char ifname[IFNAMSIZ];
int err;
err = validate_linkmsg(dev, tb, extack);
if (err < 0)
return err;
+ if (tb[IFLA_IFNAME])
+ nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+ else
+ ifname[0] = '\0';
+
if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_TARGET_NETNSID]) {
- const char *pat = ifname && ifname[0] ? ifname : NULL;
+ const char *pat = ifname[0] ? ifname : NULL;
struct net *net;
int new_ifindex;
@@ -2760,7 +2809,7 @@ static int do_setlink(const struct sk_buff *skb,
if (tb[IFLA_GSO_MAX_SIZE]) {
u32 max_size = nla_get_u32(tb[IFLA_GSO_MAX_SIZE]);
- if (max_size > GSO_MAX_SIZE) {
+ if (max_size > dev->tso_max_size) {
err = -EINVAL;
goto errout;
}
@@ -2774,7 +2823,7 @@ static int do_setlink(const struct sk_buff *skb,
if (tb[IFLA_GSO_MAX_SEGS]) {
u32 max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]);
- if (max_segs > GSO_MAX_SEGS) {
+ if (max_segs > GSO_MAX_SEGS || max_segs > dev->tso_max_segs) {
err = -EINVAL;
goto errout;
}
@@ -2973,21 +3022,16 @@ errout:
}
static struct net_device *rtnl_dev_get(struct net *net,
- struct nlattr *ifname_attr,
- struct nlattr *altifname_attr,
- char *ifname)
-{
- char buffer[ALTIFNAMSIZ];
-
- if (!ifname) {
- ifname = buffer;
- if (ifname_attr)
- nla_strscpy(ifname, ifname_attr, IFNAMSIZ);
- else if (altifname_attr)
- nla_strscpy(ifname, altifname_attr, ALTIFNAMSIZ);
- else
- return NULL;
- }
+ struct nlattr *tb[])
+{
+ char ifname[ALTIFNAMSIZ];
+
+ if (tb[IFLA_IFNAME])
+ nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+ else if (tb[IFLA_ALT_IFNAME])
+ nla_strscpy(ifname, tb[IFLA_ALT_IFNAME], ALTIFNAMSIZ);
+ else
+ return NULL;
return __dev_get_by_name(net, ifname);
}
@@ -3000,7 +3044,6 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net_device *dev;
int err;
struct nlattr *tb[IFLA_MAX+1];
- char ifname[IFNAMSIZ];
err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFLA_MAX,
ifla_policy, extack);
@@ -3011,17 +3054,12 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err < 0)
goto errout;
- if (tb[IFLA_IFNAME])
- nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
- else
- ifname[0] = '\0';
-
err = -EINVAL;
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(net, ifm->ifi_index);
else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
- dev = rtnl_dev_get(net, NULL, tb[IFLA_ALT_IFNAME], ifname);
+ dev = rtnl_dev_get(net, tb);
else
goto errout;
@@ -3030,7 +3068,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
goto errout;
}
- err = do_setlink(skb, dev, ifm, extack, tb, ifname, 0);
+ err = do_setlink(skb, dev, ifm, extack, tb, 0);
errout:
return err;
}
@@ -3119,15 +3157,14 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
- dev = rtnl_dev_get(net, tb[IFLA_IFNAME],
- tb[IFLA_ALT_IFNAME], NULL);
+ dev = rtnl_dev_get(net, tb);
else if (tb[IFLA_GROUP])
err = rtnl_group_dellink(tgt_net, nla_get_u32(tb[IFLA_GROUP]));
else
goto out;
if (!dev) {
- if (tb[IFLA_IFNAME] || ifm->ifi_index > 0)
+ if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME] || ifm->ifi_index > 0)
err = -ENODEV;
goto out;
@@ -3262,7 +3299,7 @@ static int rtnl_group_changelink(const struct sk_buff *skb,
for_each_netdev_safe(net, dev, aux) {
if (dev->group == group) {
- err = do_setlink(skb, dev, ifm, extack, tb, NULL, 0);
+ err = do_setlink(skb, dev, ifm, extack, tb, 0);
if (err < 0)
return err;
}
@@ -3271,24 +3308,118 @@ static int rtnl_group_changelink(const struct sk_buff *skb,
return 0;
}
-static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
- struct nlattr **attr, struct netlink_ext_ack *extack)
+static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
+ const struct rtnl_link_ops *ops,
+ struct nlattr **tb, struct nlattr **data,
+ struct netlink_ext_ack *extack)
{
- struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1];
unsigned char name_assign_type = NET_NAME_USER;
+ struct net *net = sock_net(skb->sk);
+ struct net *dest_net, *link_net;
+ struct net_device *dev;
+ char ifname[IFNAMSIZ];
+ int err;
+
+ if (!ops->alloc && !ops->setup)
+ return -EOPNOTSUPP;
+
+ if (tb[IFLA_IFNAME]) {
+ nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+ } else {
+ snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind);
+ name_assign_type = NET_NAME_ENUM;
+ }
+
+ dest_net = rtnl_link_get_net_capable(skb, net, tb, CAP_NET_ADMIN);
+ if (IS_ERR(dest_net))
+ return PTR_ERR(dest_net);
+
+ if (tb[IFLA_LINK_NETNSID]) {
+ int id = nla_get_s32(tb[IFLA_LINK_NETNSID]);
+
+ link_net = get_net_ns_by_id(dest_net, id);
+ if (!link_net) {
+ NL_SET_ERR_MSG(extack, "Unknown network namespace id");
+ err = -EINVAL;
+ goto out;
+ }
+ err = -EPERM;
+ if (!netlink_ns_capable(skb, link_net->user_ns, CAP_NET_ADMIN))
+ goto out;
+ } else {
+ link_net = NULL;
+ }
+
+ dev = rtnl_create_link(link_net ? : dest_net, ifname,
+ name_assign_type, ops, tb, extack);
+ if (IS_ERR(dev)) {
+ err = PTR_ERR(dev);
+ goto out;
+ }
+
+ dev->ifindex = ifm->ifi_index;
+
+ if (ops->newlink)
+ err = ops->newlink(link_net ? : net, dev, tb, data, extack);
+ else
+ err = register_netdevice(dev);
+ if (err < 0) {
+ free_netdev(dev);
+ goto out;
+ }
+
+ err = rtnl_configure_link(dev, ifm);
+ if (err < 0)
+ goto out_unregister;
+ if (link_net) {
+ err = dev_change_net_namespace(dev, dest_net, ifname);
+ if (err < 0)
+ goto out_unregister;
+ }
+ if (tb[IFLA_MASTER]) {
+ err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
+ if (err)
+ goto out_unregister;
+ }
+out:
+ if (link_net)
+ put_net(link_net);
+ put_net(dest_net);
+ return err;
+out_unregister:
+ if (ops->newlink) {
+ LIST_HEAD(list_kill);
+
+ ops->dellink(dev, &list_kill);
+ unregister_netdevice_many(&list_kill);
+ } else {
+ unregister_netdevice(dev);
+ }
+ goto out;
+}
+
+struct rtnl_newlink_tbs {
+ struct nlattr *tb[IFLA_MAX + 1];
+ struct nlattr *attr[RTNL_MAX_TYPE + 1];
+ struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1];
+};
+
+static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
+ struct rtnl_newlink_tbs *tbs,
+ struct netlink_ext_ack *extack)
+{
struct nlattr *linkinfo[IFLA_INFO_MAX + 1];
+ struct nlattr ** const tb = tbs->tb;
const struct rtnl_link_ops *m_ops;
struct net_device *master_dev;
struct net *net = sock_net(skb->sk);
const struct rtnl_link_ops *ops;
- struct nlattr *tb[IFLA_MAX + 1];
- struct net *dest_net, *link_net;
struct nlattr **slave_data;
char kind[MODULE_NAME_LEN];
struct net_device *dev;
struct ifinfomsg *ifm;
- char ifname[IFNAMSIZ];
struct nlattr **data;
+ bool link_specified;
int err;
#ifdef CONFIG_MODULES
@@ -3303,18 +3434,17 @@ replay:
if (err < 0)
return err;
- if (tb[IFLA_IFNAME])
- nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
- else
- ifname[0] = '\0';
-
ifm = nlmsg_data(nlh);
- if (ifm->ifi_index > 0)
+ if (ifm->ifi_index > 0) {
+ link_specified = true;
dev = __dev_get_by_index(net, ifm->ifi_index);
- else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
- dev = rtnl_dev_get(net, NULL, tb[IFLA_ALT_IFNAME], ifname);
- else
+ } else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) {
+ link_specified = true;
+ dev = rtnl_dev_get(net, tb);
+ } else {
+ link_specified = false;
dev = NULL;
+ }
master_dev = NULL;
m_ops = NULL;
@@ -3351,12 +3481,12 @@ replay:
return -EINVAL;
if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) {
- err = nla_parse_nested_deprecated(attr, ops->maxtype,
+ err = nla_parse_nested_deprecated(tbs->attr, ops->maxtype,
linkinfo[IFLA_INFO_DATA],
ops->policy, extack);
if (err < 0)
return err;
- data = attr;
+ data = tbs->attr;
}
if (ops->validate) {
err = ops->validate(tb, data, extack);
@@ -3372,14 +3502,14 @@ replay:
if (m_ops->slave_maxtype &&
linkinfo[IFLA_INFO_SLAVE_DATA]) {
- err = nla_parse_nested_deprecated(slave_attr,
+ err = nla_parse_nested_deprecated(tbs->slave_attr,
m_ops->slave_maxtype,
linkinfo[IFLA_INFO_SLAVE_DATA],
m_ops->slave_policy,
extack);
if (err < 0)
return err;
- slave_data = slave_attr;
+ slave_data = tbs->slave_attr;
}
}
@@ -3413,11 +3543,16 @@ replay:
status |= DO_SETLINK_NOTIFY;
}
- return do_setlink(skb, dev, ifm, extack, tb, ifname, status);
+ return do_setlink(skb, dev, ifm, extack, tb, status);
}
if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
- if (ifm->ifi_index == 0 && tb[IFLA_GROUP])
+ /* No dev found and NLM_F_CREATE not set. Requested dev does not exist,
+ * or it's for a group
+ */
+ if (link_specified)
+ return -ENODEV;
+ if (tb[IFLA_GROUP])
return rtnl_group_changelink(skb, net,
nla_get_u32(tb[IFLA_GROUP]),
ifm, extack, tb);
@@ -3442,94 +3577,21 @@ replay:
return -EOPNOTSUPP;
}
- if (!ops->alloc && !ops->setup)
- return -EOPNOTSUPP;
-
- if (!ifname[0]) {
- snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind);
- name_assign_type = NET_NAME_ENUM;
- }
-
- dest_net = rtnl_link_get_net_capable(skb, net, tb, CAP_NET_ADMIN);
- if (IS_ERR(dest_net))
- return PTR_ERR(dest_net);
-
- if (tb[IFLA_LINK_NETNSID]) {
- int id = nla_get_s32(tb[IFLA_LINK_NETNSID]);
-
- link_net = get_net_ns_by_id(dest_net, id);
- if (!link_net) {
- NL_SET_ERR_MSG(extack, "Unknown network namespace id");
- err = -EINVAL;
- goto out;
- }
- err = -EPERM;
- if (!netlink_ns_capable(skb, link_net->user_ns, CAP_NET_ADMIN))
- goto out;
- } else {
- link_net = NULL;
- }
-
- dev = rtnl_create_link(link_net ? : dest_net, ifname,
- name_assign_type, ops, tb, extack);
- if (IS_ERR(dev)) {
- err = PTR_ERR(dev);
- goto out;
- }
-
- dev->ifindex = ifm->ifi_index;
-
- if (ops->newlink)
- err = ops->newlink(link_net ? : net, dev, tb, data, extack);
- else
- err = register_netdevice(dev);
- if (err < 0) {
- free_netdev(dev);
- goto out;
- }
-
- err = rtnl_configure_link(dev, ifm);
- if (err < 0)
- goto out_unregister;
- if (link_net) {
- err = dev_change_net_namespace(dev, dest_net, ifname);
- if (err < 0)
- goto out_unregister;
- }
- if (tb[IFLA_MASTER]) {
- err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
- if (err)
- goto out_unregister;
- }
-out:
- if (link_net)
- put_net(link_net);
- put_net(dest_net);
- return err;
-out_unregister:
- if (ops->newlink) {
- LIST_HEAD(list_kill);
-
- ops->dellink(dev, &list_kill);
- unregister_netdevice_many(&list_kill);
- } else {
- unregister_netdevice(dev);
- }
- goto out;
+ return rtnl_newlink_create(skb, ifm, ops, tb, data, extack);
}
static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
- struct nlattr **attr;
+ struct rtnl_newlink_tbs *tbs;
int ret;
- attr = kmalloc_array(RTNL_MAX_TYPE + 1, sizeof(*attr), GFP_KERNEL);
- if (!attr)
+ tbs = kmalloc(sizeof(*tbs), GFP_KERNEL);
+ if (!tbs)
return -ENOMEM;
- ret = __rtnl_newlink(skb, nlh, attr, extack);
- kfree(attr);
+ ret = __rtnl_newlink(skb, nlh, tbs, extack);
+ kfree(tbs);
return ret;
}
@@ -3617,8 +3679,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
- dev = rtnl_dev_get(tgt_net, tb[IFLA_IFNAME],
- tb[IFLA_ALT_IFNAME], NULL);
+ dev = rtnl_dev_get(tgt_net, tb);
else
goto out;
@@ -3713,8 +3774,7 @@ static int rtnl_linkprop(int cmd, struct sk_buff *skb, struct nlmsghdr *nlh,
if (ifm->ifi_index > 0)
dev = __dev_get_by_index(net, ifm->ifi_index);
else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
- dev = rtnl_dev_get(net, tb[IFLA_IFNAME],
- tb[IFLA_ALT_IFNAME], NULL);
+ dev = rtnl_dev_get(net, tb);
else
return -EINVAL;
@@ -4132,22 +4192,36 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm,
}
EXPORT_SYMBOL(ndo_dflt_fdb_del);
+static const struct nla_policy fdb_del_bulk_policy[NDA_MAX + 1] = {
+ [NDA_VLAN] = { .type = NLA_U16 },
+ [NDA_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1),
+ [NDA_NDM_STATE_MASK] = { .type = NLA_U16 },
+ [NDA_NDM_FLAGS_MASK] = { .type = NLA_U8 },
+};
+
static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
+ bool del_bulk = !!(nlh->nlmsg_flags & NLM_F_BULK);
struct net *net = sock_net(skb->sk);
+ const struct net_device_ops *ops;
struct ndmsg *ndm;
struct nlattr *tb[NDA_MAX+1];
struct net_device *dev;
- __u8 *addr;
+ __u8 *addr = NULL;
int err;
u16 vid;
if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
- err = nlmsg_parse_deprecated(nlh, sizeof(*ndm), tb, NDA_MAX, NULL,
- extack);
+ if (!del_bulk) {
+ err = nlmsg_parse_deprecated(nlh, sizeof(*ndm), tb, NDA_MAX,
+ NULL, extack);
+ } else {
+ err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX,
+ fdb_del_bulk_policy, extack);
+ }
if (err < 0)
return err;
@@ -4163,9 +4237,12 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
return -ENODEV;
}
- if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
- NL_SET_ERR_MSG(extack, "invalid address");
- return -EINVAL;
+ if (!del_bulk) {
+ if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
+ NL_SET_ERR_MSG(extack, "invalid address");
+ return -EINVAL;
+ }
+ addr = nla_data(tb[NDA_LLADDR]);
}
if (dev->type != ARPHRD_ETHER) {
@@ -4173,8 +4250,6 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
return -EINVAL;
}
- addr = nla_data(tb[NDA_LLADDR]);
-
err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
if (err)
return err;
@@ -4185,10 +4260,16 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) &&
netif_is_bridge_port(dev)) {
struct net_device *br_dev = netdev_master_upper_dev_get(dev);
- const struct net_device_ops *ops = br_dev->netdev_ops;
- if (ops->ndo_fdb_del)
- err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid);
+ ops = br_dev->netdev_ops;
+ if (!del_bulk) {
+ if (ops->ndo_fdb_del)
+ err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid, extack);
+ } else {
+ if (ops->ndo_fdb_del_bulk)
+ err = ops->ndo_fdb_del_bulk(ndm, tb, dev, vid,
+ extack);
+ }
if (err)
goto out;
@@ -4198,15 +4279,24 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
/* Embedded bridge, macvlan, and any other device support */
if (ndm->ndm_flags & NTF_SELF) {
- if (dev->netdev_ops->ndo_fdb_del)
- err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr,
- vid);
- else
- err = ndo_dflt_fdb_del(ndm, tb, dev, addr, vid);
+ ops = dev->netdev_ops;
+ if (!del_bulk) {
+ if (ops->ndo_fdb_del)
+ err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid, extack);
+ else
+ err = ndo_dflt_fdb_del(ndm, tb, dev, addr, vid);
+ } else {
+ /* in case err was cleared by NTF_MASTER call */
+ err = -EOPNOTSUPP;
+ if (ops->ndo_fdb_del_bulk)
+ err = ops->ndo_fdb_del_bulk(ndm, tb, dev, vid,
+ extack);
+ }
if (!err) {
- rtnl_fdb_notify(dev, addr, vid, RTM_DELNEIGH,
- ndm->ndm_state);
+ if (!del_bulk)
+ rtnl_fdb_notify(dev, addr, vid, RTM_DELNEIGH,
+ ndm->ndm_state);
ndm->ndm_flags &= ~NTF_SELF;
}
}
@@ -5896,11 +5986,11 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
{
struct net *net = sock_net(skb->sk);
struct rtnl_link *link;
+ enum rtnl_kinds kind;
struct module *owner;
int err = -EOPNOTSUPP;
rtnl_doit_func doit;
unsigned int flags;
- int kind;
int family;
int type;
@@ -5915,13 +6005,13 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
return 0;
family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family;
- kind = type&3;
+ kind = rtnl_msgtype_kind(type);
- if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN))
+ if (kind != RTNL_KIND_GET && !netlink_net_capable(skb, CAP_NET_ADMIN))
return -EPERM;
rcu_read_lock();
- if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
+ if (kind == RTNL_KIND_GET && (nlh->nlmsg_flags & NLM_F_DUMP)) {
struct sock *rtnl;
rtnl_dumpit_func dumpit;
u32 min_dump_alloc = 0;
@@ -5977,6 +6067,12 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
}
flags = link->flags;
+ if (kind == RTNL_KIND_DEL && (nlh->nlmsg_flags & NLM_F_BULK) &&
+ !(flags & RTNL_FLAG_BULK_DEL_SUPPORTED)) {
+ NL_SET_ERR_MSG(extack, "Bulk delete is not supported");
+ goto err_unlock;
+ }
+
if (flags & RTNL_FLAG_DOIT_UNLOCKED) {
doit = link->doit;
rcu_read_unlock();
@@ -6105,7 +6201,8 @@ void __init rtnetlink_init(void)
rtnl_register(PF_UNSPEC, RTM_DELLINKPROP, rtnl_dellinkprop, NULL, 0);
rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, 0);
- rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, 0);
+ rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL,
+ RTNL_FLAG_BULK_DEL_SUPPORTED);
rtnl_register(PF_BRIDGE, RTM_GETNEIGH, rtnl_fdb_get, rtnl_fdb_dump, 0);
rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, 0);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c90c74de90d5..5b3559cb1d82 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -80,7 +80,7 @@
#include <linux/user_namespace.h>
#include <linux/indirect_call_wrapper.h>
-#include "datagram.h"
+#include "dev.h"
#include "sock_destructor.h"
struct kmem_cache *skbuff_head_cache __ro_after_init;
@@ -204,7 +204,7 @@ static void __build_skb_around(struct sk_buff *skb, void *data,
skb_set_end_offset(skb, size);
skb->mac_header = (typeof(skb->mac_header))~0U;
skb->transport_header = (typeof(skb->transport_header))~0U;
-
+ skb->alloc_cpu = raw_smp_processor_id();
/* make sure we initialize shinfo sequentially */
shinfo = skb_shinfo(skb);
memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
@@ -772,6 +772,8 @@ void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason)
if (!skb_unref(skb))
return;
+ DEBUG_NET_WARN_ON_ONCE(reason <= 0 || reason >= SKB_DROP_REASON_MAX);
+
trace_kfree_skb(skb, __builtin_return_address(0), reason);
__kfree_skb(skb);
}
@@ -1037,6 +1039,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
#ifdef CONFIG_NET_RX_BUSY_POLL
CHECK_SKB_FIELD(napi_id);
#endif
+ CHECK_SKB_FIELD(alloc_cpu);
#ifdef CONFIG_XPS
CHECK_SKB_FIELD(sender_cpu);
#endif
@@ -1165,7 +1168,7 @@ void mm_unaccount_pinned_pages(struct mmpin *mmp)
}
EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages);
-struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size)
+static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size)
{
struct ubuf_info *uarg;
struct sk_buff *skb;
@@ -1196,7 +1199,6 @@ struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size)
return uarg;
}
-EXPORT_SYMBOL_GPL(msg_zerocopy_alloc);
static inline struct sk_buff *skb_from_uarg(struct ubuf_info *uarg)
{
@@ -1339,18 +1341,11 @@ void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref)
}
EXPORT_SYMBOL_GPL(msg_zerocopy_put_abort);
-int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len)
-{
- return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len);
-}
-EXPORT_SYMBOL_GPL(skb_zerocopy_iter_dgram);
-
int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
struct msghdr *msg, int len,
struct ubuf_info *uarg)
{
struct ubuf_info *orig_uarg = skb_zcopy(skb);
- struct iov_iter orig_iter = msg->msg_iter;
int err, orig_len = skb->len;
/* An skb can only point to one uarg. This edge case happens when
@@ -1364,7 +1359,7 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
struct sock *save_sk = skb->sk;
/* Streams do not free skb on error. Reset to prev state. */
- msg->msg_iter = orig_iter;
+ iov_iter_revert(&msg->msg_iter, skb->len - orig_len);
skb->sk = sk;
___pskb_trim(skb, orig_len);
skb->sk = save_sk;
@@ -5603,7 +5598,7 @@ err_free:
}
EXPORT_SYMBOL(skb_vlan_untag);
-int skb_ensure_writable(struct sk_buff *skb, int write_len)
+int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len)
{
if (!pskb_may_pull(skb, write_len))
return -ENOMEM;
@@ -6488,3 +6483,49 @@ free_now:
}
EXPORT_SYMBOL(__skb_ext_put);
#endif /* CONFIG_SKB_EXTENSIONS */
+
+/**
+ * skb_attempt_defer_free - queue skb for remote freeing
+ * @skb: buffer
+ *
+ * Put @skb in a per-cpu list, using the cpu which
+ * allocated the skb/pages to reduce false sharing
+ * and memory zone spinlock contention.
+ */
+void skb_attempt_defer_free(struct sk_buff *skb)
+{
+ int cpu = skb->alloc_cpu;
+ struct softnet_data *sd;
+ unsigned long flags;
+ unsigned int defer_max;
+ bool kick;
+
+ if (WARN_ON_ONCE(cpu >= nr_cpu_ids) ||
+ !cpu_online(cpu) ||
+ cpu == raw_smp_processor_id()) {
+nodefer: __kfree_skb(skb);
+ return;
+ }
+
+ sd = &per_cpu(softnet_data, cpu);
+ defer_max = READ_ONCE(sysctl_skb_defer_max);
+ if (READ_ONCE(sd->defer_count) >= defer_max)
+ goto nodefer;
+
+ spin_lock_irqsave(&sd->defer_lock, flags);
+ /* Send an IPI every time queue reaches half capacity. */
+ kick = sd->defer_count == (defer_max >> 1);
+ /* Paired with the READ_ONCE() few lines above */
+ WRITE_ONCE(sd->defer_count, sd->defer_count + 1);
+
+ skb->next = sd->defer_list;
+ /* Paired with READ_ONCE() in skb_defer_free_flush() */
+ WRITE_ONCE(sd->defer_list, skb);
+ spin_unlock_irqrestore(&sd->defer_lock, flags);
+
+ /* Make sure to trigger NET_RX_SOFTIRQ on the remote CPU
+ * if we are unlucky enough (this seems very unlikely).
+ */
+ if (unlikely(kick) && !cmpxchg(&sd->defer_ipi_scheduled, 0, 1))
+ smp_call_function_single_async(cpu, &sd->defer_csd);
+}
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index cc381165ea08..22b983ade0e7 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -524,16 +524,20 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
{
int num_sge, copied;
- /* skb linearize may fail with ENOMEM, but lets simply try again
- * later if this happens. Under memory pressure we don't want to
- * drop the skb. We need to linearize the skb so that the mapping
- * in skb_to_sgvec can not error.
- */
- if (skb_linearize(skb))
- return -EAGAIN;
num_sge = skb_to_sgvec(skb, msg->sg.data, off, len);
- if (unlikely(num_sge < 0))
- return num_sge;
+ if (num_sge < 0) {
+ /* skb linearize may fail with ENOMEM, but lets simply try again
+ * later if this happens. Under memory pressure we don't want to
+ * drop the skb. We need to linearize the skb so that the mapping
+ * in skb_to_sgvec can not error.
+ */
+ if (skb_linearize(skb))
+ return -EAGAIN;
+
+ num_sge = skb_to_sgvec(skb, msg->sg.data, off, len);
+ if (unlikely(num_sge < 0))
+ return num_sge;
+ }
copied = len;
msg->sg.start = 0;
diff --git a/net/core/sock.c b/net/core/sock.c
index 1180a0cb0110..2ff40dd0a7a6 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -141,9 +141,14 @@
#include <linux/ethtool.h>
+#include "dev.h"
+
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
+static void sock_def_write_space_wfree(struct sock *sk);
+static void sock_def_write_space(struct sock *sk);
+
/**
* sk_ns_capable - General socket capability test
* @sk: Socket to use a capability on or through
@@ -503,17 +508,35 @@ int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(__sock_queue_rcv_skb);
-int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb,
+ enum skb_drop_reason *reason)
{
+ enum skb_drop_reason drop_reason;
int err;
err = sk_filter(sk, skb);
- if (err)
- return err;
-
- return __sock_queue_rcv_skb(sk, skb);
+ if (err) {
+ drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
+ goto out;
+ }
+ err = __sock_queue_rcv_skb(sk, skb);
+ switch (err) {
+ case -ENOMEM:
+ drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF;
+ break;
+ case -ENOBUFS:
+ drop_reason = SKB_DROP_REASON_PROTO_MEM;
+ break;
+ default:
+ drop_reason = SKB_NOT_DROPPED_YET;
+ break;
+ }
+out:
+ if (reason)
+ *reason = drop_reason;
+ return err;
}
-EXPORT_SYMBOL(sock_queue_rcv_skb);
+EXPORT_SYMBOL(sock_queue_rcv_skb_reason);
int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
const int nested, unsigned int trim_cap, bool refcounted)
@@ -612,7 +635,9 @@ static int sock_bindtoindex_locked(struct sock *sk, int ifindex)
if (ifindex < 0)
goto out;
- sk->sk_bound_dev_if = ifindex;
+ /* Paired with all READ_ONCE() done locklessly. */
+ WRITE_ONCE(sk->sk_bound_dev_if, ifindex);
+
if (sk->sk_prot->rehash)
sk->sk_prot->rehash(sk);
sk_dst_reset(sk);
@@ -690,10 +715,11 @@ static int sock_getbindtodevice(struct sock *sk, char __user *optval,
{
int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
+ int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
struct net *net = sock_net(sk);
char devname[IFNAMSIZ];
- if (sk->sk_bound_dev_if == 0) {
+ if (bound_dev_if == 0) {
len = 0;
goto zero;
}
@@ -702,7 +728,7 @@ static int sock_getbindtodevice(struct sock *sk, char __user *optval,
if (len < IFNAMSIZ)
goto out;
- ret = netdev_get_name(net, devname, sk->sk_bound_dev_if);
+ ret = netdev_get_name(net, devname, bound_dev_if);
if (ret)
goto out;
@@ -1291,6 +1317,15 @@ set_sndbuf:
__sock_set_mark(sk, val);
break;
+ case SO_RCVMARK:
+ if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
+ !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+ ret = -EPERM;
+ break;
+ }
+
+ sock_valbool_flag(sk, SOCK_RCVMARK, valbool);
+ break;
case SO_RXQ_OVFL:
sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool);
@@ -1717,6 +1752,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = sk->sk_mark;
break;
+ case SO_RCVMARK:
+ v.val = sock_flag(sk, SOCK_RCVMARK);
+ break;
+
case SO_RXQ_OVFL:
v.val = sock_flag(sk, SOCK_RXQ_OVFL);
break;
@@ -1825,7 +1864,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_BINDTOIFINDEX:
- v.val = sk->sk_bound_dev_if;
+ v.val = READ_ONCE(sk->sk_bound_dev_if);
break;
case SO_NETNS_COOKIE:
@@ -2062,9 +2101,6 @@ void sk_destruct(struct sock *sk)
{
bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE);
- WARN_ON_ONCE(!llist_empty(&sk->defer_list));
- sk_defer_free_flush(sk);
-
if (rcu_access_pointer(sk->sk_reuseport_cb)) {
reuseport_detach_sock(sk);
use_call_rcu = true;
@@ -2260,6 +2296,19 @@ void sk_free_unlock_clone(struct sock *sk)
}
EXPORT_SYMBOL_GPL(sk_free_unlock_clone);
+static void sk_trim_gso_size(struct sock *sk)
+{
+ if (sk->sk_gso_max_size <= GSO_LEGACY_MAX_SIZE)
+ return;
+#if IS_ENABLED(CONFIG_IPV6)
+ if (sk->sk_family == AF_INET6 &&
+ sk_is_tcp(sk) &&
+ !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+ return;
+#endif
+ sk->sk_gso_max_size = GSO_LEGACY_MAX_SIZE;
+}
+
void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
{
u32 max_segs = 1;
@@ -2279,6 +2328,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
/* pairs with the WRITE_ONCE() in netif_set_gso_max_size() */
sk->sk_gso_max_size = READ_ONCE(dst->dev->gso_max_size);
+ sk_trim_gso_size(sk);
sk->sk_gso_max_size -= (MAX_TCP_HEADER + 1);
/* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */
max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1);
@@ -2300,8 +2350,20 @@ void sock_wfree(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
unsigned int len = skb->truesize;
+ bool free;
if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) {
+ if (sock_flag(sk, SOCK_RCU_FREE) &&
+ sk->sk_write_space == sock_def_write_space) {
+ rcu_read_lock();
+ free = refcount_sub_and_test(len, &sk->sk_wmem_alloc);
+ sock_def_write_space_wfree(sk);
+ rcu_read_unlock();
+ if (unlikely(free))
+ __sk_free(sk);
+ return;
+ }
+
/*
* Keep a reference on sk_wmem_alloc, this will be released
* after sk_write_space() call
@@ -2611,13 +2673,6 @@ failure:
}
EXPORT_SYMBOL(sock_alloc_send_pskb);
-struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
- int noblock, int *errcode)
-{
- return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0);
-}
-EXPORT_SYMBOL(sock_alloc_send_skb);
-
int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
struct sockcm_cookie *sockc)
{
@@ -3174,20 +3229,42 @@ static void sock_def_write_space(struct sock *sk)
/* Do not wake up a writer until he can make "significant"
* progress. --DaveM
*/
- if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) {
+ if (sock_writeable(sk)) {
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
EPOLLWRNORM | EPOLLWRBAND);
/* Should agree with poll, otherwise some programs break */
- if (sock_writeable(sk))
- sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
+ sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
}
rcu_read_unlock();
}
+/* An optimised version of sock_def_write_space(), should only be called
+ * for SOCK_RCU_FREE sockets under RCU read section and after putting
+ * ->sk_wmem_alloc.
+ */
+static void sock_def_write_space_wfree(struct sock *sk)
+{
+ /* Do not wake up a writer until he can make "significant"
+ * progress. --DaveM
+ */
+ if (sock_writeable(sk)) {
+ struct socket_wq *wq = rcu_dereference(sk->sk_wq);
+
+ /* rely on refcount_sub from sock_wfree() */
+ smp_mb__after_atomic();
+ if (wq && waitqueue_active(&wq->wait))
+ wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
+ EPOLLWRNORM | EPOLLWRBAND);
+
+ /* Should agree with poll, otherwise some programs break */
+ sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
+ }
+}
+
static void sock_def_destruct(struct sock *sk)
{
}
@@ -3486,8 +3563,7 @@ int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int addr_len = 0;
int err;
- err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
- flags & ~MSG_DONTWAIT, &addr_len);
+ err = sk->sk_prot->recvmsg(sk, msg, size, flags, &addr_len);
if (err >= 0)
msg->msg_namelen = addr_len;
return err;
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 2d213c4011db..81d4b4756a02 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -793,7 +793,7 @@ static const struct bpf_iter_seq_info sock_map_iter_seq_info = {
.seq_priv_size = sizeof(struct sock_map_seq_info),
};
-static int sock_map_btf_id;
+BTF_ID_LIST_SINGLE(sock_map_btf_ids, struct, bpf_stab)
const struct bpf_map_ops sock_map_ops = {
.map_meta_equal = bpf_map_meta_equal,
.map_alloc = sock_map_alloc,
@@ -805,8 +805,7 @@ const struct bpf_map_ops sock_map_ops = {
.map_lookup_elem = sock_map_lookup,
.map_release_uref = sock_map_release_progs,
.map_check_btf = map_check_no_btf,
- .map_btf_name = "bpf_stab",
- .map_btf_id = &sock_map_btf_id,
+ .map_btf_id = &sock_map_btf_ids[0],
.iter_seq_info = &sock_map_iter_seq_info,
};
@@ -1385,7 +1384,7 @@ static const struct bpf_iter_seq_info sock_hash_iter_seq_info = {
.seq_priv_size = sizeof(struct sock_hash_seq_info),
};
-static int sock_hash_map_btf_id;
+BTF_ID_LIST_SINGLE(sock_hash_map_btf_ids, struct, bpf_shtab)
const struct bpf_map_ops sock_hash_ops = {
.map_meta_equal = bpf_map_meta_equal,
.map_alloc = sock_hash_alloc,
@@ -1397,8 +1396,7 @@ const struct bpf_map_ops sock_hash_ops = {
.map_lookup_elem_sys_only = sock_hash_lookup_sys,
.map_release_uref = sock_hash_release_progs,
.map_check_btf = map_check_no_btf,
- .map_btf_name = "bpf_shtab",
- .map_btf_id = &sock_hash_map_btf_id,
+ .map_btf_id = &sock_hash_map_btf_ids[0],
.iter_seq_info = &sock_hash_iter_seq_info,
};
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 7123fe7feeac..71a13596ea2b 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -23,13 +23,12 @@
#include <net/busy_poll.h>
#include <net/pkt_sched.h>
-static int two = 2;
-static int three = 3;
+#include "dev.h"
+
static int int_3600 = 3600;
static int min_sndbuf = SOCK_MIN_SNDBUF;
static int min_rcvbuf = SOCK_MIN_RCVBUF;
static int max_skb_frags = MAX_SKB_FRAGS;
-static long long_one __maybe_unused = 1;
static long long_max __maybe_unused = LONG_MAX;
static int net_msg_warn; /* Unused, but still a sysctl */
@@ -265,6 +264,8 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
loff_t *ppos)
{
int ret, jit_enable = *(int *)table->data;
+ int min = *(int *)table->extra1;
+ int max = *(int *)table->extra2;
struct ctl_table tmp = *table;
if (write && !capable(CAP_SYS_ADMIN))
@@ -282,6 +283,10 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
ret = -EPERM;
}
}
+
+ if (write && ret && min == max)
+ pr_info_once("CONFIG_BPF_JIT_ALWAYS_ON is enabled, bpf_jit_enable is permanently set to 1.\n");
+
return ret;
}
@@ -388,7 +393,7 @@ static struct ctl_table net_core_table[] = {
.extra2 = SYSCTL_ONE,
# else
.extra1 = SYSCTL_ZERO,
- .extra2 = &two,
+ .extra2 = SYSCTL_TWO,
# endif
},
# ifdef CONFIG_HAVE_EBPF_JIT
@@ -399,7 +404,7 @@ static struct ctl_table net_core_table[] = {
.mode = 0600,
.proc_handler = proc_dointvec_minmax_bpf_restricted,
.extra1 = SYSCTL_ZERO,
- .extra2 = &two,
+ .extra2 = SYSCTL_TWO,
},
{
.procname = "bpf_jit_kallsyms",
@@ -417,7 +422,7 @@ static struct ctl_table net_core_table[] = {
.maxlen = sizeof(long),
.mode = 0600,
.proc_handler = proc_dolongvec_minmax_bpf_restricted,
- .extra1 = &long_one,
+ .extra1 = SYSCTL_LONG_ONE,
.extra2 = &bpf_jit_limit_max,
},
#endif
@@ -544,7 +549,7 @@ static struct ctl_table net_core_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
- .extra2 = &two,
+ .extra2 = SYSCTL_TWO,
},
{
.procname = "devconf_inherit_init_net",
@@ -553,7 +558,7 @@ static struct ctl_table net_core_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
- .extra2 = &three,
+ .extra2 = SYSCTL_THREE,
},
{
.procname = "high_order_alloc_disable",
@@ -579,6 +584,14 @@ static struct ctl_table net_core_table[] = {
.extra1 = SYSCTL_ONE,
.extra2 = &int_3600,
},
+ {
+ .procname = "skb_defer_max",
+ .data = &sysctl_skb_defer_max,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ },
{ }
};