summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/9p/client.c6
-rw-r--r--net/9p/trans_common.c4
-rw-r--r--net/9p/trans_fd.c4
-rw-r--r--net/9p/trans_rdma.c2
-rw-r--r--net/9p/trans_virtio.c9
-rw-r--r--net/Kconfig2
-rw-r--r--net/Makefile1
-rw-r--r--net/appletalk/aarp.c18
-rw-r--r--net/appletalk/ddp.c7
-rw-r--r--net/atm/raw.c12
-rw-r--r--net/bridge/Kconfig11
-rw-r--r--net/bridge/Makefile2
-rw-r--r--net/bridge/br_cfm.c867
-rw-r--r--net/bridge/br_cfm_netlink.c726
-rw-r--r--net/bridge/br_device.c8
-rw-r--r--net/bridge/br_if.c1
-rw-r--r--net/bridge/br_input.c35
-rw-r--r--net/bridge/br_mdb.c30
-rw-r--r--net/bridge/br_mrp.c41
-rw-r--r--net/bridge/br_mrp_netlink.c2
-rw-r--r--net/bridge/br_multicast.c13
-rw-r--r--net/bridge/br_netlink.c117
-rw-r--r--net/bridge/br_private.h106
-rw-r--r--net/bridge/br_private_cfm.h147
-rw-r--r--net/bridge/br_private_mrp.h2
-rw-r--r--net/bridge/br_vlan.c15
-rw-r--r--net/bridge/netfilter/Kconfig2
-rw-r--r--net/bridge/netfilter/nft_reject_bridge.c255
-rw-r--r--net/core/bpf_sk_storage.c135
-rw-r--r--net/core/datagram.c2
-rw-r--r--net/core/dev.c23
-rw-r--r--net/core/dev_ioctl.c2
-rw-r--r--net/core/fib_rules.c4
-rw-r--r--net/core/flow_dissector.c2
-rw-r--r--net/core/page_pool.c70
-rw-r--r--net/core/rtnetlink.c12
-rw-r--r--net/core/skbuff.c16
-rw-r--r--net/core/xdp.c54
-rw-r--r--net/dcb/dcbnl.c16
-rw-r--r--net/dccp/ackvec.c5
-rw-r--r--net/dccp/ccid.c2
-rw-r--r--net/dccp/ccids/ccid2.c5
-rw-r--r--net/dccp/ccids/ccid3.c6
-rw-r--r--net/dccp/ccids/lib/loss_interval.c3
-rw-r--r--net/dccp/ccids/lib/packet_history.c3
-rw-r--r--net/dccp/feat.c6
-rw-r--r--net/dccp/output.c9
-rw-r--r--net/dccp/qpolicy.c6
-rw-r--r--net/dccp/timer.c12
-rw-r--r--net/decnet/dn_dev.c2
-rw-r--r--net/dsa/Kconfig11
-rw-r--r--net/dsa/Makefile4
-rw-r--r--net/dsa/dsa.c7
-rw-r--r--net/dsa/dsa_priv.h2
-rw-r--r--net/dsa/slave.c86
-rw-r--r--net/dsa/tag_ar9331.c3
-rw-r--r--net/dsa/tag_brcm.c3
-rw-r--r--net/dsa/tag_dsa.c332
-rw-r--r--net/dsa/tag_edsa.c206
-rw-r--r--net/dsa/tag_gswip.c5
-rw-r--r--net/dsa/tag_hellcreek.c66
-rw-r--r--net/dsa/tag_ksz.c73
-rw-r--r--net/dsa/tag_lan9303.c9
-rw-r--r--net/dsa/tag_mtk.c3
-rw-r--r--net/dsa/tag_ocelot.c7
-rw-r--r--net/dsa/tag_qca.c3
-rw-r--r--net/dsa/tag_trailer.c31
-rw-r--r--net/ethernet/eth.c6
-rw-r--r--net/ethtool/ioctl.c2
-rw-r--r--net/ieee802154/nl-mac.c2
-rw-r--r--net/ipv4/devinet.c5
-rw-r--r--net/ipv4/fib_semantics.c7
-rw-r--r--net/ipv4/fib_trie.c9
-rw-r--r--net/ipv4/ip_gre.c6
-rw-r--r--net/ipv4/ip_tunnel_core.c9
-rw-r--r--net/ipv4/ip_vti.c2
-rw-r--r--net/ipv4/ipconfig.c14
-rw-r--r--net/ipv4/ipip.c2
-rw-r--r--net/ipv4/metrics.c2
-rw-r--r--net/ipv4/netfilter/nf_reject_ipv4.c128
-rw-r--r--net/ipv4/nexthop.c255
-rw-r--r--net/ipv4/proc.c1
-rw-r--r--net/ipv4/route.c15
-rw-r--r--net/ipv4/tcp.c128
-rw-r--r--net/ipv4/tcp_input.c9
-rw-r--r--net/ipv4/tcp_ipv4.c14
-rw-r--r--net/ipv4/tcp_lp.c7
-rw-r--r--net/ipv4/tcp_output.c11
-rw-r--r--net/ipv4/tcp_recovery.c3
-rw-r--r--net/ipv4/udp.c10
-rw-r--r--net/ipv4/udp_diag.c2
-rw-r--r--net/ipv4/udp_offload.c5
-rw-r--r--net/ipv6/addrconf.c1
-rw-r--r--net/ipv6/calipso.c4
-rw-r--r--net/ipv6/exthdrs.c5
-rw-r--r--net/ipv6/ip6_gre.c6
-rw-r--r--net/ipv6/ip6_tunnel.c47
-rw-r--r--net/ipv6/ip6_vti.c3
-rw-r--r--net/ipv6/mcast.c2
-rw-r--r--net/ipv6/netfilter/nf_reject_ipv6.c139
-rw-r--r--net/ipv6/proc.c2
-rw-r--r--net/ipv6/route.c5
-rw-r--r--net/ipv6/rpl.c2
-rw-r--r--net/ipv6/rpl_iptunnel.c2
-rw-r--r--net/ipv6/sit.c2
-rw-r--r--net/ipv6/udp.c8
-rw-r--r--net/ipv6/udp_offload.c8
-rw-r--r--net/l3mdev/l3mdev.c1
-rw-r--r--net/llc/llc_conn.c2
-rw-r--r--net/mac80211/cfg.c11
-rw-r--r--net/mac80211/chan.c3
-rw-r--r--net/mac80211/debugfs_netdev.c11
-rw-r--r--net/mac80211/debugfs_sta.c2
-rw-r--r--net/mac80211/ieee80211_i.h10
-rw-r--r--net/mac80211/iface.c54
-rw-r--r--net/mac80211/main.c22
-rw-r--r--net/mac80211/mesh.c30
-rw-r--r--net/mac80211/pm.c15
-rw-r--r--net/mac80211/rx.c21
-rw-r--r--net/mac80211/tx.c44
-rw-r--r--net/mac80211/util.c7
-rw-r--r--net/mac80211/wme.c18
-rw-r--r--net/mac802154/main.c8
-rw-r--r--net/mpls/af_mpls.c2
-rw-r--r--net/mptcp/ctrl.c14
-rw-r--r--net/mptcp/options.c30
-rw-r--r--net/mptcp/pm.c3
-rw-r--r--net/mptcp/pm_netlink.c13
-rw-r--r--net/mptcp/protocol.c1051
-rw-r--r--net/mptcp/protocol.h73
-rw-r--r--net/mptcp/subflow.c33
-rw-r--r--net/netfilter/Kconfig10
-rw-r--r--net/netfilter/Makefile1
-rw-r--r--net/netfilter/ipset/ip_set_core.c6
-rw-r--r--net/netfilter/ipset/ip_set_hash_gen.h45
-rw-r--r--net/netfilter/ipset/ip_set_hash_ip.c7
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipmac.c6
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipmark.c7
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipport.c7
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipportip.c7
-rw-r--r--net/netfilter/ipset/ip_set_hash_ipportnet.c7
-rw-r--r--net/netfilter/ipset/ip_set_hash_mac.c6
-rw-r--r--net/netfilter/ipset/ip_set_hash_net.c7
-rw-r--r--net/netfilter/ipset/ip_set_hash_netiface.c11
-rw-r--r--net/netfilter/ipset/ip_set_hash_netnet.c7
-rw-r--r--net/netfilter/ipset/ip_set_hash_netport.c7
-rw-r--r--net/netfilter/ipset/ip_set_hash_netportnet.c7
-rw-r--r--net/netfilter/nf_tables_api.c9
-rw-r--r--net/netfilter/nfnetlink_acct.c2
-rw-r--r--net/netfilter/nfnetlink_cthelper.c4
-rw-r--r--net/netfilter/nft_ct.c2
-rw-r--r--net/netfilter/nft_log.c2
-rw-r--r--net/netfilter/nft_reject.c12
-rw-r--r--net/netfilter/nft_reject_inet.c68
-rw-r--r--net/netfilter/nft_reject_netdev.c189
-rw-r--r--net/netlabel/netlabel_calipso.c1
-rw-r--r--net/netlabel/netlabel_mgmt.c2
-rw-r--r--net/nfc/core.c10
-rw-r--r--net/nfc/digital_core.c3
-rw-r--r--net/nfc/nci/core.c2
-rw-r--r--net/nfc/nci/hci.c9
-rw-r--r--net/nfc/netlink.c2
-rw-r--r--net/openvswitch/flow.c4
-rw-r--r--net/openvswitch/meter.c2
-rw-r--r--net/openvswitch/vport-internal_dev.c29
-rw-r--r--net/openvswitch/vport.c4
-rw-r--r--net/packet/af_packet.c37
-rw-r--r--net/packet/internal.h5
-rw-r--r--net/qrtr/ns.c8
-rw-r--r--net/qrtr/qrtr.c49
-rw-r--r--net/sched/act_api.c73
-rw-r--r--net/sched/act_bpf.c2
-rw-r--r--net/sched/act_ipt.c2
-rw-r--r--net/sched/act_simple.c4
-rw-r--r--net/sched/cls_api.c18
-rw-r--r--net/sched/cls_rsvp.h2
-rw-r--r--net/sched/em_cmp.c2
-rw-r--r--net/sched/sch_api.c2
-rw-r--r--net/sched/sch_atm.c8
-rw-r--r--net/sched/sch_pie.c2
-rw-r--r--net/sctp/Kconfig1
-rw-r--r--net/sctp/associola.c4
-rw-r--r--net/sctp/ipv6.c44
-rw-r--r--net/sctp/offload.c6
-rw-r--r--net/sctp/output.c22
-rw-r--r--net/sctp/protocol.c142
-rw-r--r--net/sctp/sm_make_chunk.c21
-rw-r--r--net/sctp/sm_statefuns.c52
-rw-r--r--net/sctp/socket.c116
-rw-r--r--net/sctp/sysctl.c62
-rw-r--r--net/smc/af_smc.c61
-rw-r--r--net/smc/smc_cdc.c6
-rw-r--r--net/smc/smc_clc.h5
-rw-r--r--net/smc/smc_core.h1
-rw-r--r--net/smc/smc_wr.c14
-rw-r--r--net/socket.c25
-rw-r--r--net/sunrpc/rpc_pipe.c3
-rw-r--r--net/tipc/bearer.c5
-rw-r--r--net/tipc/core.c2
-rw-r--r--net/tipc/core.h3
-rw-r--r--net/tipc/link.c2
-rw-r--r--net/tipc/name_distr.c19
-rw-r--r--net/tipc/netlink_compat.c7
-rw-r--r--net/tipc/node.c2
-rw-r--r--net/tipc/socket.c27
-rw-r--r--net/tipc/socket.h2
-rw-r--r--net/tipc/topsrv.c4
-rw-r--r--net/vmw_vsock/af_vsock.c3
-rw-r--r--net/wimax/Kconfig40
-rw-r--r--net/wimax/Makefile13
-rw-r--r--net/wimax/debug-levels.h29
-rw-r--r--net/wimax/debugfs.c38
-rw-r--r--net/wimax/id-table.c130
-rw-r--r--net/wimax/op-msg.c391
-rw-r--r--net/wimax/op-reset.c108
-rw-r--r--net/wimax/op-rfkill.c431
-rw-r--r--net/wimax/op-state-get.c52
-rw-r--r--net/wimax/stack.c609
-rw-r--r--net/wimax/wimax-internal.h85
-rw-r--r--net/wireless/chan.c6
-rw-r--r--net/wireless/core.c8
-rw-r--r--net/wireless/nl80211.c85
-rw-r--r--net/wireless/rdev-ops.h10
-rw-r--r--net/wireless/scan.c2
-rw-r--r--net/wireless/trace.h5
-rw-r--r--net/wireless/util.c37
-rw-r--r--net/wireless/wext-compat.c51
-rw-r--r--net/xfrm/xfrm_input.c7
-rw-r--r--net/xfrm/xfrm_interface.c19
229 files changed, 5464 insertions, 4130 deletions
diff --git a/net/9p/client.c b/net/9p/client.c
index 09f1ec589b80..785a7bb6a539 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -412,8 +412,9 @@ static void p9_tag_cleanup(struct p9_client *c)
/**
* p9_client_cb - call back from transport to client
- * c: client state
- * req: request received
+ * @c: client state
+ * @req: request received
+ * @status: request status, one of REQ_STATUS_*
*
*/
void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status)
@@ -555,6 +556,7 @@ out_err:
* p9_check_zc_errors - check 9p packet for error return and process it
* @c: current client instance
* @req: request to parse and check for error conditions
+ * @uidata: external buffer containing error
* @in_hdrlen: Size of response protocol buffer.
*
* returns error code if one is discovered, otherwise returns 0
diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c
index 3dff68f05fb9..6ea5ea548cd4 100644
--- a/net/9p/trans_common.c
+++ b/net/9p/trans_common.c
@@ -17,7 +17,9 @@
#include "trans_common.h"
/**
- * p9_release_pages - Release pages after the transaction.
+ * p9_release_pages - Release pages after the transaction.
+ * @pages: array of pages to be put
+ * @nr_pages: size of array
*/
void p9_release_pages(struct page **pages, int nr_pages)
{
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 8f528e783a6c..fa158397bb63 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -45,7 +45,7 @@ static struct p9_trans_module p9_fd_trans;
* @rfd: file descriptor for reading (trans=fd)
* @wfd: file descriptor for writing (trans=fd)
* @port: port to connect to (trans=tcp)
- *
+ * @privport: port is privileged
*/
struct p9_fd_opts {
@@ -95,6 +95,8 @@ struct p9_poll_wait {
* @err: error state
* @req_list: accounting for requests which have been sent
* @unsent_req_list: accounting for requests that haven't been sent
+ * @rreq: read request
+ * @wreq: write request
* @req: current request being processed (if any)
* @tmp_buf: temporary buffer to read in header
* @rc: temporary fcall for reading current frame
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 2885ff9c76f0..af0a8a6cd3fd 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -99,6 +99,7 @@ struct p9_rdma_req;
/**
* struct p9_rdma_context - Keeps track of in-process WR
*
+ * @cqe: completion queue entry
* @busa: Bus address to unmap when the WR completes
* @req: Keeps track of requests (send)
* @rc: Keepts track of replies (receive)
@@ -115,6 +116,7 @@ struct p9_rdma_context {
/**
* struct p9_rdma_opts - Collection of mount options
* @port: port of connection
+ * @privport: Whether a privileged port may be used
* @sq_depth: The requested depth of the SQ. This really doesn't need
* to be any deeper than the number of threads used in the client
* @rq_depth: The depth of the RQ. Should be greater than or equal to SQ depth
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index a3cd90a74012..93f2f8654882 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -50,7 +50,11 @@ static atomic_t vp_pinned = ATOMIC_INIT(0);
* @client: client instance
* @vdev: virtio dev associated with this channel
* @vq: virtio queue associated with this channel
+ * @ring_bufs_avail: flag to indicate there is some available in the ring buf
+ * @vc_wq: wait queue for waiting for thing to be added to ring buf
+ * @p9_max_pages: maximum number of pinned pages
* @sg: scatter gather list which is used to pack a request (protected?)
+ * @chan_list: linked list of channels
*
* We keep all per-channel information in a structure.
* This structure is allocated within the devices dev->mem space.
@@ -74,8 +78,8 @@ struct virtio_chan {
unsigned long p9_max_pages;
/* Scatterlist: can be too big for stack. */
struct scatterlist sg[VIRTQUEUE_NUM];
- /*
- * tag name to identify a mount null terminated
+ /**
+ * @tag: name to identify a mount null terminated
*/
char *tag;
@@ -204,6 +208,7 @@ static int p9_virtio_cancelled(struct p9_client *client, struct p9_req_t *req)
* this takes a list of pages.
* @sg: scatter/gather list to pack into
* @start: which segment of the sg_list to start at
+ * @limit: maximum number of pages in sg list.
* @pdata: a list of pages to add into sg.
* @nr_pages: number of pages to pack into the scatter/gather list
* @offs: amount of data in the beginning of first page _not_ to pack
diff --git a/net/Kconfig b/net/Kconfig
index d6567162c1cf..f4c32d982af6 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -386,8 +386,6 @@ source "net/mac80211/Kconfig"
endif # WIRELESS
-source "net/wimax/Kconfig"
-
source "net/rfkill/Kconfig"
source "net/9p/Kconfig"
source "net/caif/Kconfig"
diff --git a/net/Makefile b/net/Makefile
index 5744bf1997fd..d96b0aa8f39f 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -66,7 +66,6 @@ obj-$(CONFIG_MAC802154) += mac802154/
ifeq ($(CONFIG_NET),y)
obj-$(CONFIG_SYSCTL) += sysctl_net.o
endif
-obj-$(CONFIG_WIMAX) += wimax/
obj-$(CONFIG_DNS_RESOLVER) += dns_resolver/
obj-$(CONFIG_CEPH_LIB) += ceph/
obj-$(CONFIG_BATMAN_ADV) += batman-adv/
diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c
index 45f584171de7..be18af481d7d 100644
--- a/net/appletalk/aarp.c
+++ b/net/appletalk/aarp.c
@@ -44,15 +44,15 @@ int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME;
/* Lists of aarp entries */
/**
* struct aarp_entry - AARP entry
- * @last_sent - Last time we xmitted the aarp request
- * @packet_queue - Queue of frames wait for resolution
- * @status - Used for proxy AARP
- * expires_at - Entry expiry time
- * target_addr - DDP Address
- * dev - Device to use
- * hwaddr - Physical i/f address of target/router
- * xmit_count - When this hits 10 we give up
- * next - Next entry in chain
+ * @last_sent: Last time we xmitted the aarp request
+ * @packet_queue: Queue of frames wait for resolution
+ * @status: Used for proxy AARP
+ * @expires_at: Entry expiry time
+ * @target_addr: DDP Address
+ * @dev: Device to use
+ * @hwaddr: Physical i/f address of target/router
+ * @xmit_count: When this hits 10 we give up
+ * @next: Next entry in chain
*/
struct aarp_entry {
/* These first two are only used for unresolved entries */
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 1d48708c5a2e..ca1a0d07a087 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1407,9 +1407,10 @@ drop:
/**
* atalk_rcv - Receive a packet (in skb) from device dev
- * @skb - packet received
- * @dev - network device where the packet comes from
- * @pt - packet type
+ * @skb: packet received
+ * @dev: network device where the packet comes from
+ * @pt: packet type
+ * @orig_dev: the original receive net device
*
* Receive a packet (in skb) from device dev. This has come from the SNAP
* decoder, and on entry skb->transport_header is the DDP header, skb->len
diff --git a/net/atm/raw.c b/net/atm/raw.c
index b3ba44aab0ee..2b5f78a7ec3e 100644
--- a/net/atm/raw.c
+++ b/net/atm/raw.c
@@ -54,6 +54,8 @@ static int atm_send_aal0(struct atm_vcc *vcc, struct sk_buff *skb)
kfree_skb(skb);
return -EADDRNOTAVAIL;
}
+ if (vcc->dev->ops->send_bh)
+ return vcc->dev->ops->send_bh(vcc, skb);
return vcc->dev->ops->send(vcc, skb);
}
@@ -71,7 +73,10 @@ int atm_init_aal34(struct atm_vcc *vcc)
vcc->push = atm_push_raw;
vcc->pop = atm_pop_raw;
vcc->push_oam = NULL;
- vcc->send = vcc->dev->ops->send;
+ if (vcc->dev->ops->send_bh)
+ vcc->send = vcc->dev->ops->send_bh;
+ else
+ vcc->send = vcc->dev->ops->send;
return 0;
}
@@ -80,7 +85,10 @@ int atm_init_aal5(struct atm_vcc *vcc)
vcc->push = atm_push_raw;
vcc->pop = atm_pop_raw;
vcc->push_oam = NULL;
- vcc->send = vcc->dev->ops->send;
+ if (vcc->dev->ops->send_bh)
+ vcc->send = vcc->dev->ops->send_bh;
+ else
+ vcc->send = vcc->dev->ops->send;
return 0;
}
EXPORT_SYMBOL(atm_init_aal5);
diff --git a/net/bridge/Kconfig b/net/bridge/Kconfig
index 80879196560c..3c8ded7d3e84 100644
--- a/net/bridge/Kconfig
+++ b/net/bridge/Kconfig
@@ -73,3 +73,14 @@ config BRIDGE_MRP
Say N to exclude this support and reduce the binary size.
If unsure, say N.
+
+config BRIDGE_CFM
+ bool "CFM protocol"
+ depends on BRIDGE
+ help
+ If you say Y here, then the Ethernet bridge will be able to run CFM
+ protocol according to 802.1Q section 12.14
+
+ Say N to exclude this support and reduce the binary size.
+
+ If unsure, say N.
diff --git a/net/bridge/Makefile b/net/bridge/Makefile
index ccb394236fbd..4702702a74d3 100644
--- a/net/bridge/Makefile
+++ b/net/bridge/Makefile
@@ -27,3 +27,5 @@ bridge-$(CONFIG_NET_SWITCHDEV) += br_switchdev.o
obj-$(CONFIG_NETFILTER) += netfilter/
bridge-$(CONFIG_BRIDGE_MRP) += br_mrp_switchdev.o br_mrp.o br_mrp_netlink.o
+
+bridge-$(CONFIG_BRIDGE_CFM) += br_cfm.o br_cfm_netlink.o
diff --git a/net/bridge/br_cfm.c b/net/bridge/br_cfm.c
new file mode 100644
index 000000000000..001064f7583d
--- /dev/null
+++ b/net/bridge/br_cfm.c
@@ -0,0 +1,867 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/cfm_bridge.h>
+#include <uapi/linux/cfm_bridge.h>
+#include "br_private_cfm.h"
+
+static struct br_cfm_mep *br_mep_find(struct net_bridge *br, u32 instance)
+{
+ struct br_cfm_mep *mep;
+
+ hlist_for_each_entry(mep, &br->mep_list, head)
+ if (mep->instance == instance)
+ return mep;
+
+ return NULL;
+}
+
+static struct br_cfm_mep *br_mep_find_ifindex(struct net_bridge *br,
+ u32 ifindex)
+{
+ struct br_cfm_mep *mep;
+
+ hlist_for_each_entry_rcu(mep, &br->mep_list, head,
+ lockdep_rtnl_is_held())
+ if (mep->create.ifindex == ifindex)
+ return mep;
+
+ return NULL;
+}
+
+static struct br_cfm_peer_mep *br_peer_mep_find(struct br_cfm_mep *mep,
+ u32 mepid)
+{
+ struct br_cfm_peer_mep *peer_mep;
+
+ hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head,
+ lockdep_rtnl_is_held())
+ if (peer_mep->mepid == mepid)
+ return peer_mep;
+
+ return NULL;
+}
+
+static struct net_bridge_port *br_mep_get_port(struct net_bridge *br,
+ u32 ifindex)
+{
+ struct net_bridge_port *port;
+
+ list_for_each_entry(port, &br->port_list, list)
+ if (port->dev->ifindex == ifindex)
+ return port;
+
+ return NULL;
+}
+
+/* Calculate the CCM interval in us. */
+static u32 interval_to_us(enum br_cfm_ccm_interval interval)
+{
+ switch (interval) {
+ case BR_CFM_CCM_INTERVAL_NONE:
+ return 0;
+ case BR_CFM_CCM_INTERVAL_3_3_MS:
+ return 3300;
+ case BR_CFM_CCM_INTERVAL_10_MS:
+ return 10 * 1000;
+ case BR_CFM_CCM_INTERVAL_100_MS:
+ return 100 * 1000;
+ case BR_CFM_CCM_INTERVAL_1_SEC:
+ return 1000 * 1000;
+ case BR_CFM_CCM_INTERVAL_10_SEC:
+ return 10 * 1000 * 1000;
+ case BR_CFM_CCM_INTERVAL_1_MIN:
+ return 60 * 1000 * 1000;
+ case BR_CFM_CCM_INTERVAL_10_MIN:
+ return 10 * 60 * 1000 * 1000;
+ }
+ return 0;
+}
+
+/* Convert the interface interval to CCM PDU value. */
+static u32 interval_to_pdu(enum br_cfm_ccm_interval interval)
+{
+ switch (interval) {
+ case BR_CFM_CCM_INTERVAL_NONE:
+ return 0;
+ case BR_CFM_CCM_INTERVAL_3_3_MS:
+ return 1;
+ case BR_CFM_CCM_INTERVAL_10_MS:
+ return 2;
+ case BR_CFM_CCM_INTERVAL_100_MS:
+ return 3;
+ case BR_CFM_CCM_INTERVAL_1_SEC:
+ return 4;
+ case BR_CFM_CCM_INTERVAL_10_SEC:
+ return 5;
+ case BR_CFM_CCM_INTERVAL_1_MIN:
+ return 6;
+ case BR_CFM_CCM_INTERVAL_10_MIN:
+ return 7;
+ }
+ return 0;
+}
+
+/* Convert the CCM PDU value to interval on interface. */
+static u32 pdu_to_interval(u32 value)
+{
+ switch (value) {
+ case 0:
+ return BR_CFM_CCM_INTERVAL_NONE;
+ case 1:
+ return BR_CFM_CCM_INTERVAL_3_3_MS;
+ case 2:
+ return BR_CFM_CCM_INTERVAL_10_MS;
+ case 3:
+ return BR_CFM_CCM_INTERVAL_100_MS;
+ case 4:
+ return BR_CFM_CCM_INTERVAL_1_SEC;
+ case 5:
+ return BR_CFM_CCM_INTERVAL_10_SEC;
+ case 6:
+ return BR_CFM_CCM_INTERVAL_1_MIN;
+ case 7:
+ return BR_CFM_CCM_INTERVAL_10_MIN;
+ }
+ return BR_CFM_CCM_INTERVAL_NONE;
+}
+
+static void ccm_rx_timer_start(struct br_cfm_peer_mep *peer_mep)
+{
+ u32 interval_us;
+
+ interval_us = interval_to_us(peer_mep->mep->cc_config.exp_interval);
+ /* Function ccm_rx_dwork must be called with 1/4
+ * of the configured CC 'expected_interval'
+ * in order to detect CCM defect after 3.25 interval.
+ */
+ queue_delayed_work(system_wq, &peer_mep->ccm_rx_dwork,
+ usecs_to_jiffies(interval_us / 4));
+}
+
+static void br_cfm_notify(int event, const struct net_bridge_port *port)
+{
+ u32 filter = RTEXT_FILTER_CFM_STATUS;
+
+ return br_info_notify(event, port->br, NULL, filter);
+}
+
+static void cc_peer_enable(struct br_cfm_peer_mep *peer_mep)
+{
+ memset(&peer_mep->cc_status, 0, sizeof(peer_mep->cc_status));
+ peer_mep->ccm_rx_count_miss = 0;
+
+ ccm_rx_timer_start(peer_mep);
+}
+
+static void cc_peer_disable(struct br_cfm_peer_mep *peer_mep)
+{
+ cancel_delayed_work_sync(&peer_mep->ccm_rx_dwork);
+}
+
+static struct sk_buff *ccm_frame_build(struct br_cfm_mep *mep,
+ const struct br_cfm_cc_ccm_tx_info *const tx_info)
+
+{
+ struct br_cfm_common_hdr *common_hdr;
+ struct net_bridge_port *b_port;
+ struct br_cfm_maid *maid;
+ u8 *itu_reserved, *e_tlv;
+ struct ethhdr *eth_hdr;
+ struct sk_buff *skb;
+ __be32 *status_tlv;
+ __be32 *snumber;
+ __be16 *mepid;
+
+ skb = dev_alloc_skb(CFM_CCM_MAX_FRAME_LENGTH);
+ if (!skb)
+ return NULL;
+
+ rcu_read_lock();
+ b_port = rcu_dereference(mep->b_port);
+ if (!b_port) {
+ kfree_skb(skb);
+ rcu_read_unlock();
+ return NULL;
+ }
+ skb->dev = b_port->dev;
+ rcu_read_unlock();
+ /* The device cannot be deleted until the work_queue functions has
+ * completed. This function is called from ccm_tx_work_expired()
+ * that is a work_queue functions.
+ */
+
+ skb->protocol = htons(ETH_P_CFM);
+ skb->priority = CFM_FRAME_PRIO;
+
+ /* Ethernet header */
+ eth_hdr = skb_put(skb, sizeof(*eth_hdr));
+ ether_addr_copy(eth_hdr->h_dest, tx_info->dmac.addr);
+ ether_addr_copy(eth_hdr->h_source, mep->config.unicast_mac.addr);
+ eth_hdr->h_proto = htons(ETH_P_CFM);
+
+ /* Common CFM Header */
+ common_hdr = skb_put(skb, sizeof(*common_hdr));
+ common_hdr->mdlevel_version = mep->config.mdlevel << 5;
+ common_hdr->opcode = BR_CFM_OPCODE_CCM;
+ common_hdr->flags = (mep->rdi << 7) |
+ interval_to_pdu(mep->cc_config.exp_interval);
+ common_hdr->tlv_offset = CFM_CCM_TLV_OFFSET;
+
+ /* Sequence number */
+ snumber = skb_put(skb, sizeof(*snumber));
+ if (tx_info->seq_no_update) {
+ *snumber = cpu_to_be32(mep->ccm_tx_snumber);
+ mep->ccm_tx_snumber += 1;
+ } else {
+ *snumber = 0;
+ }
+
+ mepid = skb_put(skb, sizeof(*mepid));
+ *mepid = cpu_to_be16((u16)mep->config.mepid);
+
+ maid = skb_put(skb, sizeof(*maid));
+ memcpy(maid->data, mep->cc_config.exp_maid.data, sizeof(maid->data));
+
+ /* ITU reserved (CFM_CCM_ITU_RESERVED_SIZE octets) */
+ itu_reserved = skb_put(skb, CFM_CCM_ITU_RESERVED_SIZE);
+ memset(itu_reserved, 0, CFM_CCM_ITU_RESERVED_SIZE);
+
+ /* Generel CFM TLV format:
+ * TLV type: one byte
+ * TLV value length: two bytes
+ * TLV value: 'TLV value length' bytes
+ */
+
+ /* Port status TLV. The value length is 1. Total of 4 bytes. */
+ if (tx_info->port_tlv) {
+ status_tlv = skb_put(skb, sizeof(*status_tlv));
+ *status_tlv = cpu_to_be32((CFM_PORT_STATUS_TLV_TYPE << 24) |
+ (1 << 8) | /* Value length */
+ (tx_info->port_tlv_value & 0xFF));
+ }
+
+ /* Interface status TLV. The value length is 1. Total of 4 bytes. */
+ if (tx_info->if_tlv) {
+ status_tlv = skb_put(skb, sizeof(*status_tlv));
+ *status_tlv = cpu_to_be32((CFM_IF_STATUS_TLV_TYPE << 24) |
+ (1 << 8) | /* Value length */
+ (tx_info->if_tlv_value & 0xFF));
+ }
+
+ /* End TLV */
+ e_tlv = skb_put(skb, sizeof(*e_tlv));
+ *e_tlv = CFM_ENDE_TLV_TYPE;
+
+ return skb;
+}
+
+static void ccm_frame_tx(struct sk_buff *skb)
+{
+ skb_reset_network_header(skb);
+ dev_queue_xmit(skb);
+}
+
+/* This function is called with the configured CC 'expected_interval'
+ * in order to drive CCM transmission when enabled.
+ */
+static void ccm_tx_work_expired(struct work_struct *work)
+{
+ struct delayed_work *del_work;
+ struct br_cfm_mep *mep;
+ struct sk_buff *skb;
+ u32 interval_us;
+
+ del_work = to_delayed_work(work);
+ mep = container_of(del_work, struct br_cfm_mep, ccm_tx_dwork);
+
+ if (time_before_eq(mep->ccm_tx_end, jiffies)) {
+ /* Transmission period has ended */
+ mep->cc_ccm_tx_info.period = 0;
+ return;
+ }
+
+ skb = ccm_frame_build(mep, &mep->cc_ccm_tx_info);
+ if (skb)
+ ccm_frame_tx(skb);
+
+ interval_us = interval_to_us(mep->cc_config.exp_interval);
+ queue_delayed_work(system_wq, &mep->ccm_tx_dwork,
+ usecs_to_jiffies(interval_us));
+}
+
+/* This function is called with 1/4 of the configured CC 'expected_interval'
+ * in order to detect CCM defect after 3.25 interval.
+ */
+static void ccm_rx_work_expired(struct work_struct *work)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct net_bridge_port *b_port;
+ struct delayed_work *del_work;
+
+ del_work = to_delayed_work(work);
+ peer_mep = container_of(del_work, struct br_cfm_peer_mep, ccm_rx_dwork);
+
+ /* After 13 counts (4 * 3,25) then 3.25 intervals are expired */
+ if (peer_mep->ccm_rx_count_miss < 13) {
+ /* 3.25 intervals are NOT expired without CCM reception */
+ peer_mep->ccm_rx_count_miss++;
+
+ /* Start timer again */
+ ccm_rx_timer_start(peer_mep);
+ } else {
+ /* 3.25 intervals are expired without CCM reception.
+ * CCM defect detected
+ */
+ peer_mep->cc_status.ccm_defect = true;
+
+ /* Change in CCM defect status - notify */
+ rcu_read_lock();
+ b_port = rcu_dereference(peer_mep->mep->b_port);
+ if (b_port)
+ br_cfm_notify(RTM_NEWLINK, b_port);
+ rcu_read_unlock();
+ }
+}
+
+static u32 ccm_tlv_extract(struct sk_buff *skb, u32 index,
+ struct br_cfm_peer_mep *peer_mep)
+{
+ __be32 *s_tlv;
+ __be32 _s_tlv;
+ u32 h_s_tlv;
+ u8 *e_tlv;
+ u8 _e_tlv;
+
+ e_tlv = skb_header_pointer(skb, index, sizeof(_e_tlv), &_e_tlv);
+ if (!e_tlv)
+ return 0;
+
+ /* TLV is present - get the status TLV */
+ s_tlv = skb_header_pointer(skb,
+ index,
+ sizeof(_s_tlv), &_s_tlv);
+ if (!s_tlv)
+ return 0;
+
+ h_s_tlv = ntohl(*s_tlv);
+ if ((h_s_tlv >> 24) == CFM_IF_STATUS_TLV_TYPE) {
+ /* Interface status TLV */
+ peer_mep->cc_status.tlv_seen = true;
+ peer_mep->cc_status.if_tlv_value = (h_s_tlv & 0xFF);
+ }
+
+ if ((h_s_tlv >> 24) == CFM_PORT_STATUS_TLV_TYPE) {
+ /* Port status TLV */
+ peer_mep->cc_status.tlv_seen = true;
+ peer_mep->cc_status.port_tlv_value = (h_s_tlv & 0xFF);
+ }
+
+ /* The Sender ID TLV is not handled */
+ /* The Organization-Specific TLV is not handled */
+
+ /* Return the length of this tlv.
+ * This is the length of the value field plus 3 bytes for size of type
+ * field and length field
+ */
+ return ((h_s_tlv >> 8) & 0xFFFF) + 3;
+}
+
+/* note: already called with rcu_read_lock */
+static int br_cfm_frame_rx(struct net_bridge_port *port, struct sk_buff *skb)
+{
+ u32 mdlevel, interval, size, index, max;
+ const struct br_cfm_common_hdr *hdr;
+ struct br_cfm_peer_mep *peer_mep;
+ const struct br_cfm_maid *maid;
+ struct br_cfm_common_hdr _hdr;
+ struct br_cfm_maid _maid;
+ struct br_cfm_mep *mep;
+ struct net_bridge *br;
+ __be32 *snumber;
+ __be32 _snumber;
+ __be16 *mepid;
+ __be16 _mepid;
+
+ if (port->state == BR_STATE_DISABLED)
+ return 0;
+
+ hdr = skb_header_pointer(skb, 0, sizeof(_hdr), &_hdr);
+ if (!hdr)
+ return 1;
+
+ br = port->br;
+ mep = br_mep_find_ifindex(br, port->dev->ifindex);
+ if (unlikely(!mep))
+ /* No MEP on this port - must be forwarded */
+ return 0;
+
+ mdlevel = hdr->mdlevel_version >> 5;
+ if (mdlevel > mep->config.mdlevel)
+ /* The level is above this MEP level - must be forwarded */
+ return 0;
+
+ if ((hdr->mdlevel_version & 0x1F) != 0) {
+ /* Invalid version */
+ mep->status.version_unexp_seen = true;
+ return 1;
+ }
+
+ if (mdlevel < mep->config.mdlevel) {
+ /* The level is below this MEP level */
+ mep->status.rx_level_low_seen = true;
+ return 1;
+ }
+
+ if (hdr->opcode == BR_CFM_OPCODE_CCM) {
+ /* CCM PDU received. */
+ /* MA ID is after common header + sequence number + MEP ID */
+ maid = skb_header_pointer(skb,
+ CFM_CCM_PDU_MAID_OFFSET,
+ sizeof(_maid), &_maid);
+ if (!maid)
+ return 1;
+ if (memcmp(maid->data, mep->cc_config.exp_maid.data,
+ sizeof(maid->data)))
+ /* MA ID not as expected */
+ return 1;
+
+ /* MEP ID is after common header + sequence number */
+ mepid = skb_header_pointer(skb,
+ CFM_CCM_PDU_MEPID_OFFSET,
+ sizeof(_mepid), &_mepid);
+ if (!mepid)
+ return 1;
+ peer_mep = br_peer_mep_find(mep, (u32)ntohs(*mepid));
+ if (!peer_mep)
+ return 1;
+
+ /* Interval is in common header flags */
+ interval = hdr->flags & 0x07;
+ if (mep->cc_config.exp_interval != pdu_to_interval(interval))
+ /* Interval not as expected */
+ return 1;
+
+ /* A valid CCM frame is received */
+ if (peer_mep->cc_status.ccm_defect) {
+ peer_mep->cc_status.ccm_defect = false;
+
+ /* Change in CCM defect status - notify */
+ br_cfm_notify(RTM_NEWLINK, port);
+
+ /* Start CCM RX timer */
+ ccm_rx_timer_start(peer_mep);
+ }
+
+ peer_mep->cc_status.seen = true;
+ peer_mep->ccm_rx_count_miss = 0;
+
+ /* RDI is in common header flags */
+ peer_mep->cc_status.rdi = (hdr->flags & 0x80) ? true : false;
+
+ /* Sequence number is after common header */
+ snumber = skb_header_pointer(skb,
+ CFM_CCM_PDU_SEQNR_OFFSET,
+ sizeof(_snumber), &_snumber);
+ if (!snumber)
+ return 1;
+ if (ntohl(*snumber) != (mep->ccm_rx_snumber + 1))
+ /* Unexpected sequence number */
+ peer_mep->cc_status.seq_unexp_seen = true;
+
+ mep->ccm_rx_snumber = ntohl(*snumber);
+
+ /* TLV end is after common header + sequence number + MEP ID +
+ * MA ID + ITU reserved
+ */
+ index = CFM_CCM_PDU_TLV_OFFSET;
+ max = 0;
+ do { /* Handle all TLVs */
+ size = ccm_tlv_extract(skb, index, peer_mep);
+ index += size;
+ max += 1;
+ } while (size != 0 && max < 4); /* Max four TLVs possible */
+
+ return 1;
+ }
+
+ mep->status.opcode_unexp_seen = true;
+
+ return 1;
+}
+
+static struct br_frame_type cfm_frame_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_CFM),
+ .frame_handler = br_cfm_frame_rx,
+};
+
+int br_cfm_mep_create(struct net_bridge *br,
+ const u32 instance,
+ struct br_cfm_mep_create *const create,
+ struct netlink_ext_ack *extack)
+{
+ struct net_bridge_port *p;
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ if (create->domain == BR_CFM_VLAN) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "VLAN domain not supported");
+ return -EINVAL;
+ }
+ if (create->domain != BR_CFM_PORT) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Invalid domain value");
+ return -EINVAL;
+ }
+ if (create->direction == BR_CFM_MEP_DIRECTION_UP) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Up-MEP not supported");
+ return -EINVAL;
+ }
+ if (create->direction != BR_CFM_MEP_DIRECTION_DOWN) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Invalid direction value");
+ return -EINVAL;
+ }
+ p = br_mep_get_port(br, create->ifindex);
+ if (!p) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Port is not related to bridge");
+ return -EINVAL;
+ }
+ mep = br_mep_find(br, instance);
+ if (mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance already exists");
+ return -EEXIST;
+ }
+
+ /* In PORT domain only one instance can be created per port */
+ if (create->domain == BR_CFM_PORT) {
+ mep = br_mep_find_ifindex(br, create->ifindex);
+ if (mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Only one Port MEP on a port allowed");
+ return -EINVAL;
+ }
+ }
+
+ mep = kzalloc(sizeof(*mep), GFP_KERNEL);
+ if (!mep)
+ return -ENOMEM;
+
+ mep->create = *create;
+ mep->instance = instance;
+ rcu_assign_pointer(mep->b_port, p);
+
+ INIT_HLIST_HEAD(&mep->peer_mep_list);
+ INIT_DELAYED_WORK(&mep->ccm_tx_dwork, ccm_tx_work_expired);
+
+ if (hlist_empty(&br->mep_list))
+ br_add_frame(br, &cfm_frame_type);
+
+ hlist_add_tail_rcu(&mep->head, &br->mep_list);
+
+ return 0;
+}
+
+static void mep_delete_implementation(struct net_bridge *br,
+ struct br_cfm_mep *mep)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct hlist_node *n_store;
+
+ ASSERT_RTNL();
+
+ /* Empty and free peer MEP list */
+ hlist_for_each_entry_safe(peer_mep, n_store, &mep->peer_mep_list, head) {
+ cancel_delayed_work_sync(&peer_mep->ccm_rx_dwork);
+ hlist_del_rcu(&peer_mep->head);
+ kfree_rcu(peer_mep, rcu);
+ }
+
+ cancel_delayed_work_sync(&mep->ccm_tx_dwork);
+
+ RCU_INIT_POINTER(mep->b_port, NULL);
+ hlist_del_rcu(&mep->head);
+ kfree_rcu(mep, rcu);
+
+ if (hlist_empty(&br->mep_list))
+ br_del_frame(br, &cfm_frame_type);
+}
+
+int br_cfm_mep_delete(struct net_bridge *br,
+ const u32 instance,
+ struct netlink_ext_ack *extack)
+{
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ mep = br_mep_find(br, instance);
+ if (!mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance does not exists");
+ return -ENOENT;
+ }
+
+ mep_delete_implementation(br, mep);
+
+ return 0;
+}
+
+int br_cfm_mep_config_set(struct net_bridge *br,
+ const u32 instance,
+ const struct br_cfm_mep_config *const config,
+ struct netlink_ext_ack *extack)
+{
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ mep = br_mep_find(br, instance);
+ if (!mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance does not exists");
+ return -ENOENT;
+ }
+
+ mep->config = *config;
+
+ return 0;
+}
+
+int br_cfm_cc_config_set(struct net_bridge *br,
+ const u32 instance,
+ const struct br_cfm_cc_config *const config,
+ struct netlink_ext_ack *extack)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ mep = br_mep_find(br, instance);
+ if (!mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance does not exists");
+ return -ENOENT;
+ }
+
+ /* Check for no change in configuration */
+ if (memcmp(config, &mep->cc_config, sizeof(*config)) == 0)
+ return 0;
+
+ if (config->enable && !mep->cc_config.enable)
+ /* CC is enabled */
+ hlist_for_each_entry(peer_mep, &mep->peer_mep_list, head)
+ cc_peer_enable(peer_mep);
+
+ if (!config->enable && mep->cc_config.enable)
+ /* CC is disabled */
+ hlist_for_each_entry(peer_mep, &mep->peer_mep_list, head)
+ cc_peer_disable(peer_mep);
+
+ mep->cc_config = *config;
+ mep->ccm_rx_snumber = 0;
+ mep->ccm_tx_snumber = 1;
+
+ return 0;
+}
+
+int br_cfm_cc_peer_mep_add(struct net_bridge *br, const u32 instance,
+ u32 mepid,
+ struct netlink_ext_ack *extack)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ mep = br_mep_find(br, instance);
+ if (!mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance does not exists");
+ return -ENOENT;
+ }
+
+ peer_mep = br_peer_mep_find(mep, mepid);
+ if (peer_mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Peer MEP-ID already exists");
+ return -EEXIST;
+ }
+
+ peer_mep = kzalloc(sizeof(*peer_mep), GFP_KERNEL);
+ if (!peer_mep)
+ return -ENOMEM;
+
+ peer_mep->mepid = mepid;
+ peer_mep->mep = mep;
+ INIT_DELAYED_WORK(&peer_mep->ccm_rx_dwork, ccm_rx_work_expired);
+
+ if (mep->cc_config.enable)
+ cc_peer_enable(peer_mep);
+
+ hlist_add_tail_rcu(&peer_mep->head, &mep->peer_mep_list);
+
+ return 0;
+}
+
+int br_cfm_cc_peer_mep_remove(struct net_bridge *br, const u32 instance,
+ u32 mepid,
+ struct netlink_ext_ack *extack)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ mep = br_mep_find(br, instance);
+ if (!mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance does not exists");
+ return -ENOENT;
+ }
+
+ peer_mep = br_peer_mep_find(mep, mepid);
+ if (!peer_mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Peer MEP-ID does not exists");
+ return -ENOENT;
+ }
+
+ cc_peer_disable(peer_mep);
+
+ hlist_del_rcu(&peer_mep->head);
+ kfree_rcu(peer_mep, rcu);
+
+ return 0;
+}
+
+int br_cfm_cc_rdi_set(struct net_bridge *br, const u32 instance,
+ const bool rdi, struct netlink_ext_ack *extack)
+{
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ mep = br_mep_find(br, instance);
+ if (!mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance does not exists");
+ return -ENOENT;
+ }
+
+ mep->rdi = rdi;
+
+ return 0;
+}
+
+int br_cfm_cc_ccm_tx(struct net_bridge *br, const u32 instance,
+ const struct br_cfm_cc_ccm_tx_info *const tx_info,
+ struct netlink_ext_ack *extack)
+{
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ mep = br_mep_find(br, instance);
+ if (!mep) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "MEP instance does not exists");
+ return -ENOENT;
+ }
+
+ if (memcmp(tx_info, &mep->cc_ccm_tx_info, sizeof(*tx_info)) == 0) {
+ /* No change in tx_info. */
+ if (mep->cc_ccm_tx_info.period == 0)
+ /* Transmission is not enabled - just return */
+ return 0;
+
+ /* Transmission is ongoing, the end time is recalculated */
+ mep->ccm_tx_end = jiffies +
+ usecs_to_jiffies(tx_info->period * 1000000);
+ return 0;
+ }
+
+ if (tx_info->period == 0 && mep->cc_ccm_tx_info.period == 0)
+ /* Some change in info and transmission is not ongoing */
+ goto save;
+
+ if (tx_info->period != 0 && mep->cc_ccm_tx_info.period != 0) {
+ /* Some change in info and transmission is ongoing
+ * The end time is recalculated
+ */
+ mep->ccm_tx_end = jiffies +
+ usecs_to_jiffies(tx_info->period * 1000000);
+
+ goto save;
+ }
+
+ if (tx_info->period == 0 && mep->cc_ccm_tx_info.period != 0) {
+ cancel_delayed_work_sync(&mep->ccm_tx_dwork);
+ goto save;
+ }
+
+ /* Start delayed work to transmit CCM frames. It is done with zero delay
+ * to send first frame immediately
+ */
+ mep->ccm_tx_end = jiffies + usecs_to_jiffies(tx_info->period * 1000000);
+ queue_delayed_work(system_wq, &mep->ccm_tx_dwork, 0);
+
+save:
+ mep->cc_ccm_tx_info = *tx_info;
+
+ return 0;
+}
+
+int br_cfm_mep_count(struct net_bridge *br, u32 *count)
+{
+ struct br_cfm_mep *mep;
+
+ *count = 0;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(mep, &br->mep_list, head)
+ *count += 1;
+ rcu_read_unlock();
+
+ return 0;
+}
+
+int br_cfm_peer_mep_count(struct net_bridge *br, u32 *count)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct br_cfm_mep *mep;
+
+ *count = 0;
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(mep, &br->mep_list, head)
+ hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head)
+ *count += 1;
+ rcu_read_unlock();
+
+ return 0;
+}
+
+bool br_cfm_created(struct net_bridge *br)
+{
+ return !hlist_empty(&br->mep_list);
+}
+
+/* Deletes the CFM instances on a specific bridge port
+ */
+void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *port)
+{
+ struct hlist_node *n_store;
+ struct br_cfm_mep *mep;
+
+ ASSERT_RTNL();
+
+ hlist_for_each_entry_safe(mep, n_store, &br->mep_list, head)
+ if (mep->create.ifindex == port->dev->ifindex)
+ mep_delete_implementation(br, mep);
+}
diff --git a/net/bridge/br_cfm_netlink.c b/net/bridge/br_cfm_netlink.c
new file mode 100644
index 000000000000..5c4c369f8536
--- /dev/null
+++ b/net/bridge/br_cfm_netlink.c
@@ -0,0 +1,726 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <net/genetlink.h>
+
+#include "br_private.h"
+#include "br_private_cfm.h"
+
+static const struct nla_policy
+br_cfm_mep_create_policy[IFLA_BRIDGE_CFM_MEP_CREATE_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_MEP_CREATE_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX] = { .type = NLA_U32 },
+};
+
+static const struct nla_policy
+br_cfm_mep_delete_policy[IFLA_BRIDGE_CFM_MEP_DELETE_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_MEP_DELETE_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE] = { .type = NLA_U32 },
+};
+
+static const struct nla_policy
+br_cfm_mep_config_policy[IFLA_BRIDGE_CFM_MEP_CONFIG_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_MEP_CONFIG_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC] = NLA_POLICY_ETH_ADDR,
+ [IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL] = NLA_POLICY_MAX(NLA_U32, 7),
+ [IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID] = NLA_POLICY_MAX(NLA_U32, 0x1FFF),
+};
+
+static const struct nla_policy
+br_cfm_cc_config_policy[IFLA_BRIDGE_CFM_CC_CONFIG_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_CC_CONFIG_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID] = {
+ .type = NLA_BINARY, .len = CFM_MAID_LENGTH },
+};
+
+static const struct nla_policy
+br_cfm_cc_peer_mep_policy[IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_CC_PEER_MEP_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_PEER_MEPID] = NLA_POLICY_MAX(NLA_U32, 0x1FFF),
+};
+
+static const struct nla_policy
+br_cfm_cc_rdi_policy[IFLA_BRIDGE_CFM_CC_RDI_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_CC_RDI_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_CC_RDI_INSTANCE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_RDI_RDI] = { .type = NLA_U32 },
+};
+
+static const struct nla_policy
+br_cfm_cc_ccm_tx_policy[IFLA_BRIDGE_CFM_CC_CCM_TX_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC] = NLA_POLICY_ETH_ADDR,
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE] = { .type = NLA_U8 },
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV] = { .type = NLA_U32 },
+ [IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE] = { .type = NLA_U8 },
+};
+
+static const struct nla_policy
+br_cfm_policy[IFLA_BRIDGE_CFM_MAX + 1] = {
+ [IFLA_BRIDGE_CFM_UNSPEC] = { .type = NLA_REJECT },
+ [IFLA_BRIDGE_CFM_MEP_CREATE] =
+ NLA_POLICY_NESTED(br_cfm_mep_create_policy),
+ [IFLA_BRIDGE_CFM_MEP_DELETE] =
+ NLA_POLICY_NESTED(br_cfm_mep_delete_policy),
+ [IFLA_BRIDGE_CFM_MEP_CONFIG] =
+ NLA_POLICY_NESTED(br_cfm_mep_config_policy),
+ [IFLA_BRIDGE_CFM_CC_CONFIG] =
+ NLA_POLICY_NESTED(br_cfm_cc_config_policy),
+ [IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD] =
+ NLA_POLICY_NESTED(br_cfm_cc_peer_mep_policy),
+ [IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE] =
+ NLA_POLICY_NESTED(br_cfm_cc_peer_mep_policy),
+ [IFLA_BRIDGE_CFM_CC_RDI] =
+ NLA_POLICY_NESTED(br_cfm_cc_rdi_policy),
+ [IFLA_BRIDGE_CFM_CC_CCM_TX] =
+ NLA_POLICY_NESTED(br_cfm_cc_ccm_tx_policy),
+};
+
+static int br_mep_create_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_MEP_CREATE_MAX + 1];
+ struct br_cfm_mep_create create;
+ u32 instance;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MEP_CREATE_MAX, attr,
+ br_cfm_mep_create_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing DOMAIN attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing DIRECTION attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing IFINDEX attribute");
+ return -EINVAL;
+ }
+
+ memset(&create, 0, sizeof(create));
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE]);
+ create.domain = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN]);
+ create.direction = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION]);
+ create.ifindex = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX]);
+
+ return br_cfm_mep_create(br, instance, &create, extack);
+}
+
+static int br_mep_delete_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_MEP_DELETE_MAX + 1];
+ u32 instance;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MEP_DELETE_MAX, attr,
+ br_cfm_mep_delete_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE]);
+
+ return br_cfm_mep_delete(br, instance, extack);
+}
+
+static int br_mep_config_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MAX + 1];
+ struct br_cfm_mep_config config;
+ u32 instance;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MEP_CONFIG_MAX, attr,
+ br_cfm_mep_config_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing UNICAST_MAC attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing MDLEVEL attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing MEPID attribute");
+ return -EINVAL;
+ }
+
+ memset(&config, 0, sizeof(config));
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE]);
+ nla_memcpy(&config.unicast_mac.addr,
+ tb[IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC],
+ sizeof(config.unicast_mac.addr));
+ config.mdlevel = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL]);
+ config.mepid = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID]);
+
+ return br_cfm_mep_config_set(br, instance, &config, extack);
+}
+
+static int br_cc_config_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_CC_CONFIG_MAX + 1];
+ struct br_cfm_cc_config config;
+ u32 instance;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_CONFIG_MAX, attr,
+ br_cfm_cc_config_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing ENABLE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INTERVAL attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing MAID attribute");
+ return -EINVAL;
+ }
+
+ memset(&config, 0, sizeof(config));
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE]);
+ config.enable = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE]);
+ config.exp_interval = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL]);
+ nla_memcpy(&config.exp_maid.data, tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID],
+ sizeof(config.exp_maid.data));
+
+ return br_cfm_cc_config_set(br, instance, &config, extack);
+}
+
+static int br_cc_peer_mep_add_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX + 1];
+ u32 instance, peer_mep_id;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX, attr,
+ br_cfm_cc_peer_mep_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing PEER_MEP_ID attribute");
+ return -EINVAL;
+ }
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]);
+ peer_mep_id = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]);
+
+ return br_cfm_cc_peer_mep_add(br, instance, peer_mep_id, extack);
+}
+
+static int br_cc_peer_mep_remove_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX + 1];
+ u32 instance, peer_mep_id;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX, attr,
+ br_cfm_cc_peer_mep_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing PEER_MEP_ID attribute");
+ return -EINVAL;
+ }
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]);
+ peer_mep_id = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]);
+
+ return br_cfm_cc_peer_mep_remove(br, instance, peer_mep_id, extack);
+}
+
+static int br_cc_rdi_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_CC_RDI_MAX + 1];
+ u32 instance, rdi;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_RDI_MAX, attr,
+ br_cfm_cc_rdi_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_RDI_RDI]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing RDI attribute");
+ return -EINVAL;
+ }
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]);
+ rdi = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_RDI]);
+
+ return br_cfm_cc_rdi_set(br, instance, rdi, extack);
+}
+
+static int br_cc_ccm_tx_parse(struct net_bridge *br, struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_CC_CCM_TX_MAX + 1];
+ struct br_cfm_cc_ccm_tx_info tx_info;
+ u32 instance;
+ int err;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_CCM_TX_MAX, attr,
+ br_cfm_cc_ccm_tx_policy, extack);
+ if (err)
+ return err;
+
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing DMAC attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing SEQ_NO_UPDATE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing PERIOD attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing IF_TLV attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing IF_TLV_VALUE attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing PORT_TLV attribute");
+ return -EINVAL;
+ }
+ if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE]) {
+ NL_SET_ERR_MSG_MOD(extack, "Missing PORT_TLV_VALUE attribute");
+ return -EINVAL;
+ }
+
+ memset(&tx_info, 0, sizeof(tx_info));
+
+ instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]);
+ nla_memcpy(&tx_info.dmac.addr,
+ tb[IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC],
+ sizeof(tx_info.dmac.addr));
+ tx_info.seq_no_update = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE]);
+ tx_info.period = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD]);
+ tx_info.if_tlv = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV]);
+ tx_info.if_tlv_value = nla_get_u8(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE]);
+ tx_info.port_tlv = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV]);
+ tx_info.port_tlv_value = nla_get_u8(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE]);
+
+ return br_cfm_cc_ccm_tx(br, instance, &tx_info, extack);
+}
+
+int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p,
+ struct nlattr *attr, int cmd, struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_BRIDGE_CFM_MAX + 1];
+ int err;
+
+ /* When this function is called for a port then the br pointer is
+ * invalid, therefor set the br to point correctly
+ */
+ if (p)
+ br = p->br;
+
+ err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MAX, attr,
+ br_cfm_policy, extack);
+ if (err)
+ return err;
+
+ if (tb[IFLA_BRIDGE_CFM_MEP_CREATE]) {
+ err = br_mep_create_parse(br, tb[IFLA_BRIDGE_CFM_MEP_CREATE],
+ extack);
+ if (err)
+ return err;
+ }
+
+ if (tb[IFLA_BRIDGE_CFM_MEP_DELETE]) {
+ err = br_mep_delete_parse(br, tb[IFLA_BRIDGE_CFM_MEP_DELETE],
+ extack);
+ if (err)
+ return err;
+ }
+
+ if (tb[IFLA_BRIDGE_CFM_MEP_CONFIG]) {
+ err = br_mep_config_parse(br, tb[IFLA_BRIDGE_CFM_MEP_CONFIG],
+ extack);
+ if (err)
+ return err;
+ }
+
+ if (tb[IFLA_BRIDGE_CFM_CC_CONFIG]) {
+ err = br_cc_config_parse(br, tb[IFLA_BRIDGE_CFM_CC_CONFIG],
+ extack);
+ if (err)
+ return err;
+ }
+
+ if (tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD]) {
+ err = br_cc_peer_mep_add_parse(br, tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD],
+ extack);
+ if (err)
+ return err;
+ }
+
+ if (tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE]) {
+ err = br_cc_peer_mep_remove_parse(br, tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE],
+ extack);
+ if (err)
+ return err;
+ }
+
+ if (tb[IFLA_BRIDGE_CFM_CC_RDI]) {
+ err = br_cc_rdi_parse(br, tb[IFLA_BRIDGE_CFM_CC_RDI],
+ extack);
+ if (err)
+ return err;
+ }
+
+ if (tb[IFLA_BRIDGE_CFM_CC_CCM_TX]) {
+ err = br_cc_ccm_tx_parse(br, tb[IFLA_BRIDGE_CFM_CC_CCM_TX],
+ extack);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct br_cfm_mep *mep;
+ struct nlattr *tb;
+
+ hlist_for_each_entry_rcu(mep, &br->mep_list, head) {
+ tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_MEP_CREATE_INFO);
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN,
+ mep->create.domain))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION,
+ mep->create.direction))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX,
+ mep->create.ifindex))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, tb);
+
+ tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_INFO);
+
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC,
+ sizeof(mep->config.unicast_mac.addr),
+ mep->config.unicast_mac.addr))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL,
+ mep->config.mdlevel))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID,
+ mep->config.mepid))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, tb);
+
+ tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_CC_CONFIG_INFO);
+
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE,
+ mep->cc_config.enable))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL,
+ mep->cc_config.exp_interval))
+ goto nla_put_failure;
+
+ if (nla_put(skb, IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID,
+ sizeof(mep->cc_config.exp_maid.data),
+ mep->cc_config.exp_maid.data))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, tb);
+
+ tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_CC_RDI_INFO);
+
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_RDI_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_RDI_RDI,
+ mep->rdi))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, tb);
+
+ tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_INFO);
+
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC,
+ sizeof(mep->cc_ccm_tx_info.dmac),
+ mep->cc_ccm_tx_info.dmac.addr))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE,
+ mep->cc_ccm_tx_info.seq_no_update))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD,
+ mep->cc_ccm_tx_info.period))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV,
+ mep->cc_ccm_tx_info.if_tlv))
+ goto nla_put_failure;
+
+ if (nla_put_u8(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE,
+ mep->cc_ccm_tx_info.if_tlv_value))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV,
+ mep->cc_ccm_tx_info.port_tlv))
+ goto nla_put_failure;
+
+ if (nla_put_u8(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE,
+ mep->cc_ccm_tx_info.port_tlv_value))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, tb);
+
+ hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head) {
+ tb = nla_nest_start(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_MEP_INFO);
+
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_PEER_MEPID,
+ peer_mep->mepid))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, tb);
+ }
+ }
+
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, tb);
+
+nla_info_failure:
+ return -EMSGSIZE;
+}
+
+int br_cfm_status_fill_info(struct sk_buff *skb,
+ struct net_bridge *br,
+ bool getlink)
+{
+ struct br_cfm_peer_mep *peer_mep;
+ struct br_cfm_mep *mep;
+ struct nlattr *tb;
+
+ hlist_for_each_entry_rcu(mep, &br->mep_list, head) {
+ tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_MEP_STATUS_INFO);
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN,
+ mep->status.opcode_unexp_seen))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN,
+ mep->status.version_unexp_seen))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN,
+ mep->status.rx_level_low_seen))
+ goto nla_put_failure;
+
+ /* Only clear if this is a GETLINK */
+ if (getlink) {
+ /* Clear all 'seen' indications */
+ mep->status.opcode_unexp_seen = false;
+ mep->status.version_unexp_seen = false;
+ mep->status.rx_level_low_seen = false;
+ }
+
+ nla_nest_end(skb, tb);
+
+ hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head) {
+ tb = nla_nest_start(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_INFO);
+ if (!tb)
+ goto nla_info_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE,
+ mep->instance))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID,
+ peer_mep->mepid))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT,
+ peer_mep->cc_status.ccm_defect))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI,
+ peer_mep->cc_status.rdi))
+ goto nla_put_failure;
+
+ if (nla_put_u8(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE,
+ peer_mep->cc_status.port_tlv_value))
+ goto nla_put_failure;
+
+ if (nla_put_u8(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE,
+ peer_mep->cc_status.if_tlv_value))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN,
+ peer_mep->cc_status.seen))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN,
+ peer_mep->cc_status.tlv_seen))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb,
+ IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN,
+ peer_mep->cc_status.seq_unexp_seen))
+ goto nla_put_failure;
+
+ if (getlink) { /* Only clear if this is a GETLINK */
+ /* Clear all 'seen' indications */
+ peer_mep->cc_status.seen = false;
+ peer_mep->cc_status.tlv_seen = false;
+ peer_mep->cc_status.seq_unexp_seen = false;
+ }
+
+ nla_nest_end(skb, tb);
+ }
+ }
+
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, tb);
+
+nla_info_failure:
+ return -EMSGSIZE;
+}
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 7730c8f3cb53..77bcc84875af 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -93,7 +93,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
mdst = br_mdb_get(br, skb, vid);
if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
- br_multicast_querier_exists(br, eth_hdr(skb)))
+ br_multicast_querier_exists(br, eth_hdr(skb), mdst))
br_multicast_flood(mdst, skb, false, true);
else
br_flood(br, skb, BR_PKT_MULTICAST, false, true);
@@ -455,8 +455,12 @@ void br_dev_setup(struct net_device *dev)
spin_lock_init(&br->lock);
INIT_LIST_HEAD(&br->port_list);
INIT_HLIST_HEAD(&br->fdb_list);
+ INIT_HLIST_HEAD(&br->frame_type_list);
#if IS_ENABLED(CONFIG_BRIDGE_MRP)
- INIT_LIST_HEAD(&br->mrp_list);
+ INIT_HLIST_HEAD(&br->mrp_list);
+#endif
+#if IS_ENABLED(CONFIG_BRIDGE_CFM)
+ INIT_HLIST_HEAD(&br->mep_list);
#endif
spin_lock_init(&br->hash_lock);
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index a0e9a7937412..f7d2f472ae24 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -334,6 +334,7 @@ static void del_nbp(struct net_bridge_port *p)
spin_unlock_bh(&br->lock);
br_mrp_port_del(br, p);
+ br_cfm_port_del(br, p);
br_ifinfo_notify(RTM_DELLINK, NULL, p);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 59a318b9f646..21808985f268 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -134,7 +134,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
case BR_PKT_MULTICAST:
mdst = br_mdb_get(br, skb, vid);
if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
- br_multicast_querier_exists(br, eth_hdr(skb))) {
+ br_multicast_querier_exists(br, eth_hdr(skb), mdst)) {
if ((mdst && mdst->host_joined) ||
br_multicast_is_router(br)) {
local_rcv = true;
@@ -254,6 +254,21 @@ frame_finish:
return RX_HANDLER_CONSUMED;
}
+/* Return 0 if the frame was not processed otherwise 1
+ * note: already called with rcu_read_lock
+ */
+static int br_process_frame_type(struct net_bridge_port *p,
+ struct sk_buff *skb)
+{
+ struct br_frame_type *tmp;
+
+ hlist_for_each_entry_rcu(tmp, &p->br->frame_type_list, list)
+ if (unlikely(tmp->type == skb->protocol))
+ return tmp->frame_handler(p, skb);
+
+ return 0;
+}
+
/*
* Return NULL if skb is handled
* note: already called with rcu_read_lock
@@ -343,7 +358,7 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
}
}
- if (unlikely(br_mrp_process(p, skb)))
+ if (unlikely(br_process_frame_type(p, skb)))
return RX_HANDLER_PASS;
forward:
@@ -380,3 +395,19 @@ rx_handler_func_t *br_get_rx_handler(const struct net_device *dev)
return br_handle_frame;
}
+
+void br_add_frame(struct net_bridge *br, struct br_frame_type *ft)
+{
+ hlist_add_head_rcu(&ft->list, &br->frame_type_list);
+}
+
+void br_del_frame(struct net_bridge *br, struct br_frame_type *ft)
+{
+ struct br_frame_type *tmp;
+
+ hlist_for_each_entry(tmp, &br->frame_type_list, list)
+ if (ft == tmp) {
+ hlist_del_rcu(&ft->list);
+ return;
+ }
+}
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index e15bab19a012..8846c5bcd075 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -87,6 +87,8 @@ static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip,
ip->src.ip6 = nla_get_in6_addr(mdb_attrs[MDBE_ATTR_SOURCE]);
break;
#endif
+ default:
+ ether_addr_copy(ip->dst.mac_addr, entry->addr.u.mac_addr);
}
}
@@ -174,9 +176,11 @@ static int __mdb_fill_info(struct sk_buff *skb,
if (mp->addr.proto == htons(ETH_P_IP))
e.addr.u.ip4 = mp->addr.dst.ip4;
#if IS_ENABLED(CONFIG_IPV6)
- if (mp->addr.proto == htons(ETH_P_IPV6))
+ else if (mp->addr.proto == htons(ETH_P_IPV6))
e.addr.u.ip6 = mp->addr.dst.ip6;
#endif
+ else
+ ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr);
e.addr.proto = mp->addr.proto;
nest_ent = nla_nest_start_noflag(skb,
MDBA_MDB_ENTRY_INFO);
@@ -210,6 +214,8 @@ static int __mdb_fill_info(struct sk_buff *skb,
}
break;
#endif
+ default:
+ ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr);
}
if (p) {
if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, p->rt_protocol))
@@ -562,9 +568,12 @@ void br_mdb_notify(struct net_device *dev,
if (mp->addr.proto == htons(ETH_P_IP))
ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr);
#if IS_ENABLED(CONFIG_IPV6)
- else
+ else if (mp->addr.proto == htons(ETH_P_IPV6))
ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr);
#endif
+ else
+ ether_addr_copy(mdb.addr, mp->addr.dst.mac_addr);
+
mdb.obj.orig_dev = pg->key.port->dev;
switch (type) {
case RTM_NEWMDB:
@@ -693,6 +702,12 @@ static bool is_valid_mdb_entry(struct br_mdb_entry *entry,
return false;
}
#endif
+ } else if (entry->addr.proto == 0) {
+ /* L2 mdb */
+ if (!is_multicast_ether_addr(entry->addr.u.mac_addr)) {
+ NL_SET_ERR_MSG_MOD(extack, "L2 entry group is not multicast");
+ return false;
+ }
} else {
NL_SET_ERR_MSG_MOD(extack, "Unknown entry protocol");
return false;
@@ -831,6 +846,7 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
struct net_bridge_port_group __rcu **pp;
struct br_ip group, star_group;
unsigned long now = jiffies;
+ unsigned char flags = 0;
u8 filter_mode;
int err;
@@ -849,6 +865,11 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
}
}
+ if (br_group_is_l2(&group) && entry->state != MDB_PERMANENT) {
+ NL_SET_ERR_MSG_MOD(extack, "Only permanent L2 entries allowed");
+ return -EINVAL;
+ }
+
mp = br_mdb_ip_get(br, &group);
if (!mp) {
mp = br_multicast_new_group(br, &group);
@@ -884,7 +905,10 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
filter_mode = br_multicast_is_star_g(&group) ? MCAST_EXCLUDE :
MCAST_INCLUDE;
- p = br_multicast_new_port_group(port, &group, *pp, entry->state, NULL,
+ if (entry->state == MDB_PERMANENT)
+ flags |= MDB_PG_FLAGS_PERMANENT;
+
+ p = br_multicast_new_port_group(port, &group, *pp, flags, NULL,
filter_mode, RTPROT_STATIC);
if (unlikely(!p)) {
NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new port group");
diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c
index b36689e6e7cb..bb12fbf9aaf2 100644
--- a/net/bridge/br_mrp.c
+++ b/net/bridge/br_mrp.c
@@ -6,6 +6,13 @@
static const u8 mrp_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x1 };
static const u8 mrp_in_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x3 };
+static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb);
+
+static struct br_frame_type mrp_frame_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_MRP),
+ .frame_handler = br_mrp_process,
+};
+
static bool br_mrp_is_ring_port(struct net_bridge_port *p_port,
struct net_bridge_port *s_port,
struct net_bridge_port *port)
@@ -47,8 +54,8 @@ static struct br_mrp *br_mrp_find_id(struct net_bridge *br, u32 ring_id)
struct br_mrp *res = NULL;
struct br_mrp *mrp;
- list_for_each_entry_rcu(mrp, &br->mrp_list, list,
- lockdep_rtnl_is_held()) {
+ hlist_for_each_entry_rcu(mrp, &br->mrp_list, list,
+ lockdep_rtnl_is_held()) {
if (mrp->ring_id == ring_id) {
res = mrp;
break;
@@ -63,8 +70,8 @@ static struct br_mrp *br_mrp_find_in_id(struct net_bridge *br, u32 in_id)
struct br_mrp *res = NULL;
struct br_mrp *mrp;
- list_for_each_entry_rcu(mrp, &br->mrp_list, list,
- lockdep_rtnl_is_held()) {
+ hlist_for_each_entry_rcu(mrp, &br->mrp_list, list,
+ lockdep_rtnl_is_held()) {
if (mrp->in_id == in_id) {
res = mrp;
break;
@@ -78,8 +85,8 @@ static bool br_mrp_unique_ifindex(struct net_bridge *br, u32 ifindex)
{
struct br_mrp *mrp;
- list_for_each_entry_rcu(mrp, &br->mrp_list, list,
- lockdep_rtnl_is_held()) {
+ hlist_for_each_entry_rcu(mrp, &br->mrp_list, list,
+ lockdep_rtnl_is_held()) {
struct net_bridge_port *p;
p = rtnl_dereference(mrp->p_port);
@@ -104,8 +111,8 @@ static struct br_mrp *br_mrp_find_port(struct net_bridge *br,
struct br_mrp *res = NULL;
struct br_mrp *mrp;
- list_for_each_entry_rcu(mrp, &br->mrp_list, list,
- lockdep_rtnl_is_held()) {
+ hlist_for_each_entry_rcu(mrp, &br->mrp_list, list,
+ lockdep_rtnl_is_held()) {
if (rcu_access_pointer(mrp->p_port) == p ||
rcu_access_pointer(mrp->s_port) == p ||
rcu_access_pointer(mrp->i_port) == p) {
@@ -443,8 +450,11 @@ static void br_mrp_del_impl(struct net_bridge *br, struct br_mrp *mrp)
rcu_assign_pointer(mrp->i_port, NULL);
}
- list_del_rcu(&mrp->list);
+ hlist_del_rcu(&mrp->list);
kfree_rcu(mrp, rcu);
+
+ if (hlist_empty(&br->mrp_list))
+ br_del_frame(br, &mrp_frame_type);
}
/* Adds a new MRP instance.
@@ -493,9 +503,12 @@ int br_mrp_add(struct net_bridge *br, struct br_mrp_instance *instance)
spin_unlock_bh(&br->lock);
rcu_assign_pointer(mrp->s_port, p);
+ if (hlist_empty(&br->mrp_list))
+ br_add_frame(br, &mrp_frame_type);
+
INIT_DELAYED_WORK(&mrp->test_work, br_mrp_test_work_expired);
INIT_DELAYED_WORK(&mrp->in_test_work, br_mrp_in_test_work_expired);
- list_add_tail_rcu(&mrp->list, &br->mrp_list);
+ hlist_add_tail_rcu(&mrp->list, &br->mrp_list);
err = br_mrp_switchdev_add(br, mrp);
if (err)
@@ -1172,20 +1185,18 @@ no_forward:
* normal forwarding.
* note: already called with rcu_read_lock
*/
-int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb)
+static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb)
{
/* If there is no MRP instance do normal forwarding */
if (likely(!(p->flags & BR_MRP_AWARE)))
goto out;
- if (unlikely(skb->protocol == htons(ETH_P_MRP)))
- return br_mrp_rcv(p, skb, p->dev);
-
+ return br_mrp_rcv(p, skb, p->dev);
out:
return 0;
}
bool br_mrp_enabled(struct net_bridge *br)
{
- return !list_empty(&br->mrp_list);
+ return !hlist_empty(&br->mrp_list);
}
diff --git a/net/bridge/br_mrp_netlink.c b/net/bridge/br_mrp_netlink.c
index 2a2fdf3500c5..ce6f63c77cc0 100644
--- a/net/bridge/br_mrp_netlink.c
+++ b/net/bridge/br_mrp_netlink.c
@@ -453,7 +453,7 @@ int br_mrp_fill_info(struct sk_buff *skb, struct net_bridge *br)
if (!mrp_tb)
return -EMSGSIZE;
- list_for_each_entry_rcu(mrp, &br->mrp_list, list) {
+ hlist_for_each_entry_rcu(mrp, &br->mrp_list, list) {
struct net_bridge_port *p;
tb = nla_nest_start_noflag(skb, IFLA_BRIDGE_MRP_INFO);
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index eae898c3cff7..484820c223a3 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -179,7 +179,8 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
break;
#endif
default:
- return NULL;
+ ip.proto = 0;
+ ether_addr_copy(ip.dst.mac_addr, eth_hdr(skb)->h_dest);
}
return br_mdb_ip_get_rcu(br, &ip);
@@ -1203,6 +1204,10 @@ void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify)
if (notify)
br_mdb_notify(mp->br->dev, mp, NULL, RTM_NEWMDB);
}
+
+ if (br_group_is_l2(&mp->addr))
+ return;
+
mod_timer(&mp->timer, jiffies + mp->br->multicast_membership_interval);
}
@@ -1254,8 +1259,8 @@ __br_multicast_add_group(struct net_bridge *br,
break;
}
- p = br_multicast_new_port_group(port, group, *pp, 0, src, filter_mode,
- RTPROT_KERNEL);
+ p = br_multicast_new_port_group(port, group, *pp, 0, src,
+ filter_mode, RTPROT_KERNEL);
if (unlikely(!p)) {
p = ERR_PTR(-ENOMEM);
goto out;
@@ -3690,7 +3695,7 @@ bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto)
memset(&eth, 0, sizeof(eth));
eth.h_proto = htons(proto);
- ret = br_multicast_querier_exists(br, &eth);
+ ret = br_multicast_querier_exists(br, &eth, NULL);
unlock:
rcu_read_unlock();
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 92d64abffa87..49700ce0e919 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -16,6 +16,7 @@
#include "br_private.h"
#include "br_private_stp.h"
+#include "br_private_cfm.h"
#include "br_private_tunnel.h"
static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg,
@@ -93,9 +94,11 @@ static size_t br_get_link_af_size_filtered(const struct net_device *dev,
{
struct net_bridge_vlan_group *vg = NULL;
struct net_bridge_port *p = NULL;
- struct net_bridge *br;
- int num_vlan_infos;
+ struct net_bridge *br = NULL;
+ u32 num_cfm_peer_mep_infos;
+ u32 num_cfm_mep_infos;
size_t vinfo_sz = 0;
+ int num_vlan_infos;
rcu_read_lock();
if (netif_is_bridge_port(dev)) {
@@ -114,6 +117,49 @@ static size_t br_get_link_af_size_filtered(const struct net_device *dev,
/* Each VLAN is returned in bridge_vlan_info along with flags */
vinfo_sz += num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info));
+ if (!(filter_mask & RTEXT_FILTER_CFM_STATUS))
+ return vinfo_sz;
+
+ if (!br)
+ return vinfo_sz;
+
+ /* CFM status info must be added */
+ br_cfm_mep_count(br, &num_cfm_mep_infos);
+ br_cfm_peer_mep_count(br, &num_cfm_peer_mep_infos);
+
+ vinfo_sz += nla_total_size(0); /* IFLA_BRIDGE_CFM */
+ /* For each status struct the MEP instance (u32) is added */
+ /* MEP instance (u32) + br_cfm_mep_status */
+ vinfo_sz += num_cfm_mep_infos *
+ /*IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE */
+ (nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN */
+ + nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN */
+ + nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN */
+ + nla_total_size(sizeof(u32)));
+ /* MEP instance (u32) + br_cfm_cc_peer_status */
+ vinfo_sz += num_cfm_peer_mep_infos *
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE */
+ (nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID */
+ + nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT */
+ + nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI */
+ + nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE */
+ + nla_total_size(sizeof(u8))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE */
+ + nla_total_size(sizeof(u8))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN */
+ + nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN */
+ + nla_total_size(sizeof(u32))
+ /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN */
+ + nla_total_size(sizeof(u32)));
+
return vinfo_sz;
}
@@ -377,7 +423,8 @@ nla_put_failure:
static int br_fill_ifinfo(struct sk_buff *skb,
const struct net_bridge_port *port,
u32 pid, u32 seq, int event, unsigned int flags,
- u32 filter_mask, const struct net_device *dev)
+ u32 filter_mask, const struct net_device *dev,
+ bool getlink)
{
u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
struct nlattr *af = NULL;
@@ -426,7 +473,9 @@ static int br_fill_ifinfo(struct sk_buff *skb,
if (filter_mask & (RTEXT_FILTER_BRVLAN |
RTEXT_FILTER_BRVLAN_COMPRESSED |
- RTEXT_FILTER_MRP)) {
+ RTEXT_FILTER_MRP |
+ RTEXT_FILTER_CFM_CONFIG |
+ RTEXT_FILTER_CFM_STATUS)) {
af = nla_nest_start_noflag(skb, IFLA_AF_SPEC);
if (!af)
goto nla_put_failure;
@@ -475,6 +524,36 @@ static int br_fill_ifinfo(struct sk_buff *skb,
goto nla_put_failure;
}
+ if (filter_mask & (RTEXT_FILTER_CFM_CONFIG | RTEXT_FILTER_CFM_STATUS)) {
+ struct nlattr *cfm_nest = NULL;
+ int err;
+
+ if (!br_cfm_created(br) || port)
+ goto done;
+
+ cfm_nest = nla_nest_start(skb, IFLA_BRIDGE_CFM);
+ if (!cfm_nest)
+ goto nla_put_failure;
+
+ if (filter_mask & RTEXT_FILTER_CFM_CONFIG) {
+ rcu_read_lock();
+ err = br_cfm_config_fill_info(skb, br);
+ rcu_read_unlock();
+ if (err)
+ goto nla_put_failure;
+ }
+
+ if (filter_mask & RTEXT_FILTER_CFM_STATUS) {
+ rcu_read_lock();
+ err = br_cfm_status_fill_info(skb, br, getlink);
+ rcu_read_unlock();
+ if (err)
+ goto nla_put_failure;
+ }
+
+ nla_nest_end(skb, cfm_nest);
+ }
+
done:
if (af)
nla_nest_end(skb, af);
@@ -486,11 +565,9 @@ nla_put_failure:
return -EMSGSIZE;
}
-/* Notify listeners of a change in bridge or port information */
-void br_ifinfo_notify(int event, const struct net_bridge *br,
- const struct net_bridge_port *port)
+void br_info_notify(int event, const struct net_bridge *br,
+ const struct net_bridge_port *port, u32 filter)
{
- u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED;
struct net_device *dev;
struct sk_buff *skb;
int err = -ENOBUFS;
@@ -515,7 +592,7 @@ void br_ifinfo_notify(int event, const struct net_bridge *br,
if (skb == NULL)
goto errout;
- err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev);
+ err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev, false);
if (err < 0) {
/* -EMSGSIZE implies BUG in br_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
@@ -528,6 +605,15 @@ errout:
rtnl_set_sk_err(net, RTNLGRP_LINK, err);
}
+/* Notify listeners of a change in bridge or port information */
+void br_ifinfo_notify(int event, const struct net_bridge *br,
+ const struct net_bridge_port *port)
+{
+ u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED;
+
+ return br_info_notify(event, br, port, filter);
+}
+
/*
* Dump information about all ports, in response to GETLINK
*/
@@ -538,11 +624,13 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq,
if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN) &&
!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) &&
- !(filter_mask & RTEXT_FILTER_MRP))
+ !(filter_mask & RTEXT_FILTER_MRP) &&
+ !(filter_mask & RTEXT_FILTER_CFM_CONFIG) &&
+ !(filter_mask & RTEXT_FILTER_CFM_STATUS))
return 0;
return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags,
- filter_mask, dev);
+ filter_mask, dev, true);
}
static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
@@ -700,6 +788,11 @@ static int br_afspec(struct net_bridge *br,
if (err)
return err;
break;
+ case IFLA_BRIDGE_CFM:
+ err = br_cfm_parse(br, p, attr, cmd, extack);
+ if (err)
+ return err;
+ break;
}
}
@@ -1631,7 +1724,7 @@ static int br_fill_linkxstats(struct sk_buff *skb,
pvid = br_get_pvid(vg);
list_for_each_entry(v, &vg->vlan_list, vlist) {
struct bridge_vlan_xstats vxi;
- struct br_vlan_stats stats;
+ struct pcpu_sw_netstats stats;
if (++vl_idx < *prividx)
continue;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 345118e35c42..f44f46a305aa 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -89,14 +89,6 @@ struct bridge_mcast_stats {
};
#endif
-struct br_vlan_stats {
- u64 rx_bytes;
- u64 rx_packets;
- u64 tx_bytes;
- u64 tx_packets;
- struct u64_stats_sync syncp;
-};
-
struct br_tunnel_info {
__be64 tunnel_id;
struct metadata_dst *tunnel_dst;
@@ -137,7 +129,7 @@ struct net_bridge_vlan {
u16 flags;
u16 priv_flags;
u8 state;
- struct br_vlan_stats __percpu *stats;
+ struct pcpu_sw_netstats __percpu *stats;
union {
struct net_bridge *br;
struct net_bridge_port *port;
@@ -383,7 +375,7 @@ enum net_bridge_opts {
struct net_bridge {
spinlock_t lock;
spinlock_t hash_lock;
- struct list_head port_list;
+ struct hlist_head frame_type_list;
struct net_device *dev;
struct pcpu_sw_netstats __percpu *stats;
unsigned long options;
@@ -395,6 +387,7 @@ struct net_bridge {
#endif
struct rhashtable fdb_hash_tbl;
+ struct list_head port_list;
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
union {
struct rtable fake_rtable;
@@ -481,7 +474,10 @@ struct net_bridge {
struct hlist_head fdb_list;
#if IS_ENABLED(CONFIG_BRIDGE_MRP)
- struct list_head mrp_list;
+ struct hlist_head mrp_list;
+#endif
+#if IS_ENABLED(CONFIG_BRIDGE_CFM)
+ struct hlist_head mep_list;
#endif
};
@@ -755,6 +751,16 @@ int nbp_backup_change(struct net_bridge_port *p, struct net_device *backup_dev);
int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb);
rx_handler_func_t *br_get_rx_handler(const struct net_device *dev);
+struct br_frame_type {
+ __be16 type;
+ int (*frame_handler)(struct net_bridge_port *port,
+ struct sk_buff *skb);
+ struct hlist_node list;
+};
+
+void br_add_frame(struct net_bridge *br, struct br_frame_type *ft);
+void br_del_frame(struct net_bridge *br, struct br_frame_type *ft);
+
static inline bool br_rx_handler_check_rcu(const struct net_device *dev)
{
return rcu_dereference(dev->rx_handler) == br_get_rx_handler(dev);
@@ -840,6 +846,11 @@ void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg,
void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp,
struct net_bridge_port_group *sg);
+static inline bool br_group_is_l2(const struct br_ip *group)
+{
+ return group->proto == 0;
+}
+
#define mlock_dereference(X, br) \
rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
@@ -871,7 +882,8 @@ __br_multicast_querier_exists(struct net_bridge *br,
}
static inline bool br_multicast_querier_exists(struct net_bridge *br,
- struct ethhdr *eth)
+ struct ethhdr *eth,
+ const struct net_bridge_mdb_entry *mdb)
{
switch (eth->h_proto) {
case (htons(ETH_P_IP)):
@@ -883,7 +895,7 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br,
&br->ip6_other_query, true);
#endif
default:
- return false;
+ return !!mdb && br_group_is_l2(&mdb->addr);
}
}
@@ -993,7 +1005,8 @@ static inline bool br_multicast_is_router(struct net_bridge *br)
}
static inline bool br_multicast_querier_exists(struct net_bridge *br,
- struct ethhdr *eth)
+ struct ethhdr *eth,
+ const struct net_bridge_mdb_entry *mdb)
{
return false;
}
@@ -1072,7 +1085,7 @@ void nbp_vlan_flush(struct net_bridge_port *port);
int nbp_vlan_init(struct net_bridge_port *port, struct netlink_ext_ack *extack);
int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask);
void br_vlan_get_stats(const struct net_bridge_vlan *v,
- struct br_vlan_stats *stats);
+ struct pcpu_sw_netstats *stats);
void br_vlan_port_event(struct net_bridge_port *p, unsigned long event);
int br_vlan_bridge_event(struct net_device *dev, unsigned long event,
void *ptr);
@@ -1268,7 +1281,7 @@ static inline struct net_bridge_vlan_group *nbp_vlan_group_rcu(
}
static inline void br_vlan_get_stats(const struct net_bridge_vlan *v,
- struct br_vlan_stats *stats)
+ struct pcpu_sw_netstats *stats)
{
}
@@ -1417,7 +1430,6 @@ extern int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr)
#if IS_ENABLED(CONFIG_BRIDGE_MRP)
int br_mrp_parse(struct net_bridge *br, struct net_bridge_port *p,
struct nlattr *attr, int cmd, struct netlink_ext_ack *extack);
-int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb);
bool br_mrp_enabled(struct net_bridge *br);
void br_mrp_port_del(struct net_bridge *br, struct net_bridge_port *p);
int br_mrp_fill_info(struct sk_buff *skb, struct net_bridge *br);
@@ -1429,11 +1441,6 @@ static inline int br_mrp_parse(struct net_bridge *br, struct net_bridge_port *p,
return -EOPNOTSUPP;
}
-static inline int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb)
-{
- return 0;
-}
-
static inline bool br_mrp_enabled(struct net_bridge *br)
{
return false;
@@ -1451,12 +1458,67 @@ static inline int br_mrp_fill_info(struct sk_buff *skb, struct net_bridge *br)
#endif
+/* br_cfm.c */
+#if IS_ENABLED(CONFIG_BRIDGE_CFM)
+int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p,
+ struct nlattr *attr, int cmd, struct netlink_ext_ack *extack);
+bool br_cfm_created(struct net_bridge *br);
+void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *p);
+int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br);
+int br_cfm_status_fill_info(struct sk_buff *skb,
+ struct net_bridge *br,
+ bool getlink);
+int br_cfm_mep_count(struct net_bridge *br, u32 *count);
+int br_cfm_peer_mep_count(struct net_bridge *br, u32 *count);
+#else
+static inline int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p,
+ struct nlattr *attr, int cmd,
+ struct netlink_ext_ack *extack)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline bool br_cfm_created(struct net_bridge *br)
+{
+ return false;
+}
+
+static inline void br_cfm_port_del(struct net_bridge *br,
+ struct net_bridge_port *p)
+{
+}
+
+static inline int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int br_cfm_status_fill_info(struct sk_buff *skb,
+ struct net_bridge *br,
+ bool getlink)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int br_cfm_mep_count(struct net_bridge *br, u32 *count)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int br_cfm_peer_mep_count(struct net_bridge *br, u32 *count)
+{
+ return -EOPNOTSUPP;
+}
+#endif
+
/* br_netlink.c */
extern struct rtnl_link_ops br_link_ops;
int br_netlink_init(void);
void br_netlink_fini(void);
void br_ifinfo_notify(int event, const struct net_bridge *br,
const struct net_bridge_port *port);
+void br_info_notify(int event, const struct net_bridge *br,
+ const struct net_bridge_port *port, u32 filter);
int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags,
struct netlink_ext_ack *extack);
int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags);
diff --git a/net/bridge/br_private_cfm.h b/net/bridge/br_private_cfm.h
new file mode 100644
index 000000000000..a43a5e7fa2c3
--- /dev/null
+++ b/net/bridge/br_private_cfm.h
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _BR_PRIVATE_CFM_H_
+#define _BR_PRIVATE_CFM_H_
+
+#include "br_private.h"
+#include <uapi/linux/cfm_bridge.h>
+
+struct br_cfm_mep_create {
+ enum br_cfm_domain domain; /* Domain for this MEP */
+ enum br_cfm_mep_direction direction; /* Up or Down MEP direction */
+ u32 ifindex; /* Residence port */
+};
+
+int br_cfm_mep_create(struct net_bridge *br,
+ const u32 instance,
+ struct br_cfm_mep_create *const create,
+ struct netlink_ext_ack *extack);
+
+int br_cfm_mep_delete(struct net_bridge *br,
+ const u32 instance,
+ struct netlink_ext_ack *extack);
+
+struct br_cfm_mep_config {
+ u32 mdlevel;
+ u32 mepid; /* MEPID for this MEP */
+ struct mac_addr unicast_mac; /* The MEP unicast MAC */
+};
+
+int br_cfm_mep_config_set(struct net_bridge *br,
+ const u32 instance,
+ const struct br_cfm_mep_config *const config,
+ struct netlink_ext_ack *extack);
+
+struct br_cfm_maid {
+ u8 data[CFM_MAID_LENGTH];
+};
+
+struct br_cfm_cc_config {
+ /* Expected received CCM PDU MAID. */
+ struct br_cfm_maid exp_maid;
+
+ /* Expected received CCM PDU interval. */
+ /* Transmitting CCM PDU interval when CCM tx is enabled. */
+ enum br_cfm_ccm_interval exp_interval;
+
+ bool enable; /* Enable/disable CCM PDU handling */
+};
+
+int br_cfm_cc_config_set(struct net_bridge *br,
+ const u32 instance,
+ const struct br_cfm_cc_config *const config,
+ struct netlink_ext_ack *extack);
+
+int br_cfm_cc_peer_mep_add(struct net_bridge *br, const u32 instance,
+ u32 peer_mep_id,
+ struct netlink_ext_ack *extack);
+int br_cfm_cc_peer_mep_remove(struct net_bridge *br, const u32 instance,
+ u32 peer_mep_id,
+ struct netlink_ext_ack *extack);
+
+/* Transmitted CCM Remote Defect Indication status set.
+ * This RDI is inserted in transmitted CCM PDUs if CCM transmission is enabled.
+ * See br_cfm_cc_ccm_tx() with interval != BR_CFM_CCM_INTERVAL_NONE
+ */
+int br_cfm_cc_rdi_set(struct net_bridge *br, const u32 instance,
+ const bool rdi, struct netlink_ext_ack *extack);
+
+/* OAM PDU Tx information */
+struct br_cfm_cc_ccm_tx_info {
+ struct mac_addr dmac;
+ /* The CCM will be transmitted for this period in seconds.
+ * Call br_cfm_cc_ccm_tx before timeout to keep transmission alive.
+ * When period is zero any ongoing transmission will be stopped.
+ */
+ u32 period;
+
+ bool seq_no_update; /* Update Tx CCM sequence number */
+ bool if_tlv; /* Insert Interface Status TLV */
+ u8 if_tlv_value; /* Interface Status TLV value */
+ bool port_tlv; /* Insert Port Status TLV */
+ u8 port_tlv_value; /* Port Status TLV value */
+ /* Sender ID TLV ??
+ * Organization-Specific TLV ??
+ */
+};
+
+int br_cfm_cc_ccm_tx(struct net_bridge *br, const u32 instance,
+ const struct br_cfm_cc_ccm_tx_info *const tx_info,
+ struct netlink_ext_ack *extack);
+
+struct br_cfm_mep_status {
+ /* Indications that an OAM PDU has been seen. */
+ bool opcode_unexp_seen; /* RX of OAM PDU with unexpected opcode */
+ bool version_unexp_seen; /* RX of OAM PDU with unexpected version */
+ bool rx_level_low_seen; /* Rx of OAM PDU with level low */
+};
+
+struct br_cfm_cc_peer_status {
+ /* This CCM related status is based on the latest received CCM PDU. */
+ u8 port_tlv_value; /* Port Status TLV value */
+ u8 if_tlv_value; /* Interface Status TLV value */
+
+ /* CCM has not been received for 3.25 intervals */
+ u8 ccm_defect:1;
+
+ /* (RDI == 1) for last received CCM PDU */
+ u8 rdi:1;
+
+ /* Indications that a CCM PDU has been seen. */
+ u8 seen:1; /* CCM PDU received */
+ u8 tlv_seen:1; /* CCM PDU with TLV received */
+ /* CCM PDU with unexpected sequence number received */
+ u8 seq_unexp_seen:1;
+};
+
+struct br_cfm_mep {
+ /* list header of MEP instances */
+ struct hlist_node head;
+ u32 instance;
+ struct br_cfm_mep_create create;
+ struct br_cfm_mep_config config;
+ struct br_cfm_cc_config cc_config;
+ struct br_cfm_cc_ccm_tx_info cc_ccm_tx_info;
+ /* List of multiple peer MEPs */
+ struct hlist_head peer_mep_list;
+ struct net_bridge_port __rcu *b_port;
+ unsigned long ccm_tx_end;
+ struct delayed_work ccm_tx_dwork;
+ u32 ccm_tx_snumber;
+ u32 ccm_rx_snumber;
+ struct br_cfm_mep_status status;
+ bool rdi;
+ struct rcu_head rcu;
+};
+
+struct br_cfm_peer_mep {
+ struct hlist_node head;
+ struct br_cfm_mep *mep;
+ struct delayed_work ccm_rx_dwork;
+ u32 mepid;
+ struct br_cfm_cc_peer_status cc_status;
+ u32 ccm_rx_count_miss;
+ struct rcu_head rcu;
+};
+
+#endif /* _BR_PRIVATE_CFM_H_ */
diff --git a/net/bridge/br_private_mrp.h b/net/bridge/br_private_mrp.h
index af0e9eff6549..1883118aae55 100644
--- a/net/bridge/br_private_mrp.h
+++ b/net/bridge/br_private_mrp.h
@@ -8,7 +8,7 @@
struct br_mrp {
/* list of mrp instances */
- struct list_head list;
+ struct hlist_node list;
struct net_bridge_port __rcu *p_port;
struct net_bridge_port __rcu *s_port;
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 3e493eb85bb2..11f54a7c0d1d 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -270,7 +270,8 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags,
goto out_filt;
v->brvlan = masterv;
if (br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)) {
- v->stats = netdev_alloc_pcpu_stats(struct br_vlan_stats);
+ v->stats =
+ netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!v->stats) {
err = -ENOMEM;
goto out_filt;
@@ -421,7 +422,7 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br,
struct net_bridge_vlan_group *vg,
struct sk_buff *skb)
{
- struct br_vlan_stats *stats;
+ struct pcpu_sw_netstats *stats;
struct net_bridge_vlan *v;
u16 vid;
@@ -474,7 +475,7 @@ static bool __allowed_ingress(const struct net_bridge *br,
struct sk_buff *skb, u16 *vid,
u8 *state)
{
- struct br_vlan_stats *stats;
+ struct pcpu_sw_netstats *stats;
struct net_bridge_vlan *v;
bool tagged;
@@ -708,7 +709,7 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed,
if (!vlan)
return -ENOMEM;
- vlan->stats = netdev_alloc_pcpu_stats(struct br_vlan_stats);
+ vlan->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!vlan->stats) {
kfree(vlan);
return -ENOMEM;
@@ -1262,14 +1263,14 @@ void nbp_vlan_flush(struct net_bridge_port *port)
}
void br_vlan_get_stats(const struct net_bridge_vlan *v,
- struct br_vlan_stats *stats)
+ struct pcpu_sw_netstats *stats)
{
int i;
memset(stats, 0, sizeof(*stats));
for_each_possible_cpu(i) {
u64 rxpackets, rxbytes, txpackets, txbytes;
- struct br_vlan_stats *cpu_stats;
+ struct pcpu_sw_netstats *cpu_stats;
unsigned int start;
cpu_stats = per_cpu_ptr(v->stats, i);
@@ -1585,7 +1586,7 @@ void br_vlan_port_event(struct net_bridge_port *p, unsigned long event)
static bool br_vlan_stats_fill(struct sk_buff *skb,
const struct net_bridge_vlan *v)
{
- struct br_vlan_stats stats;
+ struct pcpu_sw_netstats stats;
struct nlattr *nest;
nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY_STATS);
diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig
index 5040fe43f4b4..e4d287afc2c9 100644
--- a/net/bridge/netfilter/Kconfig
+++ b/net/bridge/netfilter/Kconfig
@@ -17,7 +17,7 @@ config NFT_BRIDGE_META
config NFT_BRIDGE_REJECT
tristate "Netfilter nf_tables bridge reject support"
- depends on NFT_REJECT && NFT_REJECT_IPV4 && NFT_REJECT_IPV6
+ depends on NFT_REJECT
help
Add support to reject packets.
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index deae2c9a0f69..eba0efe64d05 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -39,30 +39,6 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb,
}
}
-static int nft_bridge_iphdr_validate(struct sk_buff *skb)
-{
- struct iphdr *iph;
- u32 len;
-
- if (!pskb_may_pull(skb, sizeof(struct iphdr)))
- return 0;
-
- iph = ip_hdr(skb);
- if (iph->ihl < 5 || iph->version != 4)
- return 0;
-
- len = ntohs(iph->tot_len);
- if (skb->len < len)
- return 0;
- else if (len < (iph->ihl*4))
- return 0;
-
- if (!pskb_may_pull(skb, iph->ihl*4))
- return 0;
-
- return 1;
-}
-
/* We cannot use oldskb->dev, it can be either bridge device (NF_BRIDGE INPUT)
* or the bridge port (NF_BRIDGE PREROUTING).
*/
@@ -72,29 +48,11 @@ static void nft_reject_br_send_v4_tcp_reset(struct net *net,
int hook)
{
struct sk_buff *nskb;
- struct iphdr *niph;
- const struct tcphdr *oth;
- struct tcphdr _oth;
- if (!nft_bridge_iphdr_validate(oldskb))
- return;
-
- oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook);
- if (!oth)
- return;
-
- nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
- LL_MAX_HEADER, GFP_ATOMIC);
+ nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, dev, hook);
if (!nskb)
return;
- skb_reserve(nskb, LL_MAX_HEADER);
- niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
- net->ipv4.sysctl_ip_default_ttl);
- nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
- niph->tot_len = htons(nskb->len);
- ip_send_check(niph);
-
nft_reject_br_push_etherhdr(oldskb, nskb);
br_forward(br_port_get_rcu(dev), nskb, false, true);
@@ -106,139 +64,32 @@ static void nft_reject_br_send_v4_unreach(struct net *net,
int hook, u8 code)
{
struct sk_buff *nskb;
- struct iphdr *niph;
- struct icmphdr *icmph;
- unsigned int len;
- __wsum csum;
- u8 proto;
-
- if (!nft_bridge_iphdr_validate(oldskb))
- return;
-
- /* IP header checks: fragment. */
- if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
- return;
-
- /* RFC says return as much as we can without exceeding 576 bytes. */
- len = min_t(unsigned int, 536, oldskb->len);
-
- if (!pskb_may_pull(oldskb, len))
- return;
-
- if (pskb_trim_rcsum(oldskb, ntohs(ip_hdr(oldskb)->tot_len)))
- return;
-
- proto = ip_hdr(oldskb)->protocol;
-
- if (!skb_csum_unnecessary(oldskb) &&
- nf_reject_verify_csum(proto) &&
- nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), proto))
- return;
- nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmphdr) +
- LL_MAX_HEADER + len, GFP_ATOMIC);
+ nskb = nf_reject_skb_v4_unreach(net, oldskb, dev, hook, code);
if (!nskb)
return;
- skb_reserve(nskb, LL_MAX_HEADER);
- niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP,
- net->ipv4.sysctl_ip_default_ttl);
-
- skb_reset_transport_header(nskb);
- icmph = skb_put_zero(nskb, sizeof(struct icmphdr));
- icmph->type = ICMP_DEST_UNREACH;
- icmph->code = code;
-
- skb_put_data(nskb, skb_network_header(oldskb), len);
-
- csum = csum_partial((void *)icmph, len + sizeof(struct icmphdr), 0);
- icmph->checksum = csum_fold(csum);
-
- niph->tot_len = htons(nskb->len);
- ip_send_check(niph);
-
nft_reject_br_push_etherhdr(oldskb, nskb);
br_forward(br_port_get_rcu(dev), nskb, false, true);
}
-static int nft_bridge_ip6hdr_validate(struct sk_buff *skb)
-{
- struct ipv6hdr *hdr;
- u32 pkt_len;
-
- if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
- return 0;
-
- hdr = ipv6_hdr(skb);
- if (hdr->version != 6)
- return 0;
-
- pkt_len = ntohs(hdr->payload_len);
- if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
- return 0;
-
- return 1;
-}
-
static void nft_reject_br_send_v6_tcp_reset(struct net *net,
struct sk_buff *oldskb,
const struct net_device *dev,
int hook)
{
struct sk_buff *nskb;
- const struct tcphdr *oth;
- struct tcphdr _oth;
- unsigned int otcplen;
- struct ipv6hdr *nip6h;
- if (!nft_bridge_ip6hdr_validate(oldskb))
- return;
-
- oth = nf_reject_ip6_tcphdr_get(oldskb, &_oth, &otcplen, hook);
- if (!oth)
- return;
-
- nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct tcphdr) +
- LL_MAX_HEADER, GFP_ATOMIC);
+ nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, dev, hook);
if (!nskb)
return;
- skb_reserve(nskb, LL_MAX_HEADER);
- nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP,
- net->ipv6.devconf_all->hop_limit);
- nf_reject_ip6_tcphdr_put(nskb, oldskb, oth, otcplen);
- nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr));
-
nft_reject_br_push_etherhdr(oldskb, nskb);
br_forward(br_port_get_rcu(dev), nskb, false, true);
}
-static bool reject6_br_csum_ok(struct sk_buff *skb, int hook)
-{
- const struct ipv6hdr *ip6h = ipv6_hdr(skb);
- int thoff;
- __be16 fo;
- u8 proto = ip6h->nexthdr;
-
- if (skb_csum_unnecessary(skb))
- return true;
-
- if (ip6h->payload_len &&
- pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h)))
- return false;
-
- ip6h = ipv6_hdr(skb);
- thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo);
- if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0)
- return false;
-
- if (!nf_reject_verify_csum(proto))
- return true;
-
- return nf_ip6_checksum(skb, hook, thoff, proto) == 0;
-}
static void nft_reject_br_send_v6_unreach(struct net *net,
struct sk_buff *oldskb,
@@ -246,49 +97,11 @@ static void nft_reject_br_send_v6_unreach(struct net *net,
int hook, u8 code)
{
struct sk_buff *nskb;
- struct ipv6hdr *nip6h;
- struct icmp6hdr *icmp6h;
- unsigned int len;
-
- if (!nft_bridge_ip6hdr_validate(oldskb))
- return;
- /* Include "As much of invoking packet as possible without the ICMPv6
- * packet exceeding the minimum IPv6 MTU" in the ICMP payload.
- */
- len = min_t(unsigned int, 1220, oldskb->len);
-
- if (!pskb_may_pull(oldskb, len))
- return;
-
- if (!reject6_br_csum_ok(oldskb, hook))
- return;
-
- nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) +
- LL_MAX_HEADER + len, GFP_ATOMIC);
+ nskb = nf_reject_skb_v6_unreach(net, oldskb, dev, hook, code);
if (!nskb)
return;
- skb_reserve(nskb, LL_MAX_HEADER);
- nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_ICMPV6,
- net->ipv6.devconf_all->hop_limit);
-
- skb_reset_transport_header(nskb);
- icmp6h = skb_put_zero(nskb, sizeof(struct icmp6hdr));
- icmp6h->icmp6_type = ICMPV6_DEST_UNREACH;
- icmp6h->icmp6_code = code;
-
- skb_put_data(nskb, skb_network_header(oldskb), len);
- nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr));
-
- icmp6h->icmp6_cksum =
- csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr,
- nskb->len - sizeof(struct ipv6hdr),
- IPPROTO_ICMPV6,
- csum_partial(icmp6h,
- nskb->len - sizeof(struct ipv6hdr),
- 0));
-
nft_reject_br_push_etherhdr(oldskb, nskb);
br_forward(br_port_get_rcu(dev), nskb, false, true);
@@ -364,69 +177,13 @@ static int nft_reject_bridge_validate(const struct nft_ctx *ctx,
(1 << NF_BR_LOCAL_IN));
}
-static int nft_reject_bridge_init(const struct nft_ctx *ctx,
- const struct nft_expr *expr,
- const struct nlattr * const tb[])
-{
- struct nft_reject *priv = nft_expr_priv(expr);
- int icmp_code;
-
- if (tb[NFTA_REJECT_TYPE] == NULL)
- return -EINVAL;
-
- priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
- switch (priv->type) {
- case NFT_REJECT_ICMP_UNREACH:
- case NFT_REJECT_ICMPX_UNREACH:
- if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
- return -EINVAL;
-
- icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
- if (priv->type == NFT_REJECT_ICMPX_UNREACH &&
- icmp_code > NFT_REJECT_ICMPX_MAX)
- return -EINVAL;
-
- priv->icmp_code = icmp_code;
- break;
- case NFT_REJECT_TCP_RST:
- break;
- default:
- return -EINVAL;
- }
- return 0;
-}
-
-static int nft_reject_bridge_dump(struct sk_buff *skb,
- const struct nft_expr *expr)
-{
- const struct nft_reject *priv = nft_expr_priv(expr);
-
- if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type)))
- goto nla_put_failure;
-
- switch (priv->type) {
- case NFT_REJECT_ICMP_UNREACH:
- case NFT_REJECT_ICMPX_UNREACH:
- if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
- goto nla_put_failure;
- break;
- default:
- break;
- }
-
- return 0;
-
-nla_put_failure:
- return -1;
-}
-
static struct nft_expr_type nft_reject_bridge_type;
static const struct nft_expr_ops nft_reject_bridge_ops = {
.type = &nft_reject_bridge_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_reject)),
.eval = nft_reject_bridge_eval,
- .init = nft_reject_bridge_init,
- .dump = nft_reject_bridge_dump,
+ .init = nft_reject_init,
+ .dump = nft_reject_dump,
.validate = nft_reject_bridge_validate,
};
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index c907f0dc7f87..359908a7d3c1 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -6,6 +6,7 @@
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/bpf.h>
+#include <linux/btf.h>
#include <linux/btf_ids.h>
#include <linux/bpf_local_storage.h>
#include <net/bpf_sk_storage.h>
@@ -15,20 +16,8 @@
DEFINE_BPF_STORAGE_CACHE(sk_cache);
-static int omem_charge(struct sock *sk, unsigned int size)
-{
- /* same check as in sock_kmalloc() */
- if (size <= sysctl_optmem_max &&
- atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
- atomic_add(size, &sk->sk_omem_alloc);
- return 0;
- }
-
- return -ENOMEM;
-}
-
static struct bpf_local_storage_data *
-sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
+bpf_sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
{
struct bpf_local_storage *sk_storage;
struct bpf_local_storage_map *smap;
@@ -41,11 +30,11 @@ sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit);
}
-static int sk_storage_delete(struct sock *sk, struct bpf_map *map)
+static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map)
{
struct bpf_local_storage_data *sdata;
- sdata = sk_storage_lookup(sk, map, false);
+ sdata = bpf_sk_storage_lookup(sk, map, false);
if (!sdata)
return -ENOENT;
@@ -94,7 +83,7 @@ void bpf_sk_storage_free(struct sock *sk)
kfree_rcu(sk_storage, rcu);
}
-static void sk_storage_map_free(struct bpf_map *map)
+static void bpf_sk_storage_map_free(struct bpf_map *map)
{
struct bpf_local_storage_map *smap;
@@ -103,7 +92,7 @@ static void sk_storage_map_free(struct bpf_map *map)
bpf_local_storage_map_free(smap);
}
-static struct bpf_map *sk_storage_map_alloc(union bpf_attr *attr)
+static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
{
struct bpf_local_storage_map *smap;
@@ -130,7 +119,7 @@ static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
fd = *(int *)key;
sock = sockfd_lookup(fd, &err);
if (sock) {
- sdata = sk_storage_lookup(sock->sk, map, true);
+ sdata = bpf_sk_storage_lookup(sock->sk, map, true);
sockfd_put(sock);
return sdata ? sdata->data : NULL;
}
@@ -166,7 +155,7 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key)
fd = *(int *)key;
sock = sockfd_lookup(fd, &err);
if (sock) {
- err = sk_storage_delete(sock->sk, map);
+ err = bpf_sk_storage_del(sock->sk, map);
sockfd_put(sock);
return err;
}
@@ -272,7 +261,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE)
return (unsigned long)NULL;
- sdata = sk_storage_lookup(sk, map, true);
+ sdata = bpf_sk_storage_lookup(sk, map, true);
if (sdata)
return (unsigned long)sdata->data;
@@ -305,7 +294,7 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
if (refcount_inc_not_zero(&sk->sk_refcnt)) {
int err;
- err = sk_storage_delete(sk, map);
+ err = bpf_sk_storage_del(sk, map);
sock_put(sk);
return err;
}
@@ -313,14 +302,23 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
return -ENOENT;
}
-static int sk_storage_charge(struct bpf_local_storage_map *smap,
- void *owner, u32 size)
+static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap,
+ void *owner, u32 size)
{
- return omem_charge(owner, size);
+ struct sock *sk = (struct sock *)owner;
+
+ /* same check as in sock_kmalloc() */
+ if (size <= sysctl_optmem_max &&
+ atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+ atomic_add(size, &sk->sk_omem_alloc);
+ return 0;
+ }
+
+ return -ENOMEM;
}
-static void sk_storage_uncharge(struct bpf_local_storage_map *smap,
- void *owner, u32 size)
+static void bpf_sk_storage_uncharge(struct bpf_local_storage_map *smap,
+ void *owner, u32 size)
{
struct sock *sk = owner;
@@ -328,7 +326,7 @@ static void sk_storage_uncharge(struct bpf_local_storage_map *smap,
}
static struct bpf_local_storage __rcu **
-sk_storage_ptr(void *owner)
+bpf_sk_storage_ptr(void *owner)
{
struct sock *sk = owner;
@@ -339,8 +337,8 @@ static int sk_storage_map_btf_id;
const struct bpf_map_ops sk_storage_map_ops = {
.map_meta_equal = bpf_map_meta_equal,
.map_alloc_check = bpf_local_storage_map_alloc_check,
- .map_alloc = sk_storage_map_alloc,
- .map_free = sk_storage_map_free,
+ .map_alloc = bpf_sk_storage_map_alloc,
+ .map_free = bpf_sk_storage_map_free,
.map_get_next_key = notsupp_get_next_key,
.map_lookup_elem = bpf_fd_sk_storage_lookup_elem,
.map_update_elem = bpf_fd_sk_storage_update_elem,
@@ -348,9 +346,9 @@ const struct bpf_map_ops sk_storage_map_ops = {
.map_check_btf = bpf_local_storage_map_check_btf,
.map_btf_name = "bpf_local_storage_map",
.map_btf_id = &sk_storage_map_btf_id,
- .map_local_storage_charge = sk_storage_charge,
- .map_local_storage_uncharge = sk_storage_uncharge,
- .map_owner_storage_ptr = sk_storage_ptr,
+ .map_local_storage_charge = bpf_sk_storage_charge,
+ .map_local_storage_uncharge = bpf_sk_storage_uncharge,
+ .map_owner_storage_ptr = bpf_sk_storage_ptr,
};
const struct bpf_func_proto bpf_sk_storage_get_proto = {
@@ -381,6 +379,79 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = {
.arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
};
+static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog)
+{
+ const struct btf *btf_vmlinux;
+ const struct btf_type *t;
+ const char *tname;
+ u32 btf_id;
+
+ if (prog->aux->dst_prog)
+ return false;
+
+ /* Ensure the tracing program is not tracing
+ * any bpf_sk_storage*() function and also
+ * use the bpf_sk_storage_(get|delete) helper.
+ */
+ switch (prog->expected_attach_type) {
+ case BPF_TRACE_RAW_TP:
+ /* bpf_sk_storage has no trace point */
+ return true;
+ case BPF_TRACE_FENTRY:
+ case BPF_TRACE_FEXIT:
+ btf_vmlinux = bpf_get_btf_vmlinux();
+ btf_id = prog->aux->attach_btf_id;
+ t = btf_type_by_id(btf_vmlinux, btf_id);
+ tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+ return !!strncmp(tname, "bpf_sk_storage",
+ strlen("bpf_sk_storage"));
+ default:
+ return false;
+ }
+
+ return false;
+}
+
+BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk,
+ void *, value, u64, flags)
+{
+ if (!in_serving_softirq() && !in_task())
+ return (unsigned long)NULL;
+
+ return (unsigned long)____bpf_sk_storage_get(map, sk, value, flags);
+}
+
+BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map,
+ struct sock *, sk)
+{
+ if (!in_serving_softirq() && !in_task())
+ return -EPERM;
+
+ return ____bpf_sk_storage_delete(map, sk);
+}
+
+const struct bpf_func_proto bpf_sk_storage_get_tracing_proto = {
+ .func = bpf_sk_storage_get_tracing,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+ .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg4_type = ARG_ANYTHING,
+ .allowed = bpf_sk_storage_tracing_allowed,
+};
+
+const struct bpf_func_proto bpf_sk_storage_delete_tracing_proto = {
+ .func = bpf_sk_storage_delete_tracing,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+ .allowed = bpf_sk_storage_tracing_allowed,
+};
+
struct bpf_sk_storage_diag {
u32 nr_maps;
struct bpf_map *maps[];
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 9fcaa544f11a..81809fa735a7 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -709,7 +709,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
EXPORT_SYMBOL(zerocopy_sg_from_iter);
/**
- * skb_copy_and_csum_datagram_iter - Copy datagram to an iovec iterator
+ * skb_copy_and_csum_datagram - Copy datagram to an iovec iterator
* and update a checksum.
* @skb: buffer to copy
* @offset: offset in the buffer to start copying from
diff --git a/net/core/dev.c b/net/core/dev.c
index 82dc6b48e45f..4bfdcd6b20e8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3206,7 +3206,7 @@ int skb_checksum_help(struct sk_buff *skb)
if (skb->ip_summed == CHECKSUM_COMPLETE)
goto out_set_summed;
- if (unlikely(skb_shinfo(skb)->gso_size)) {
+ if (unlikely(skb_is_gso(skb))) {
skb_warn_bad_offload(skb);
return -EINVAL;
}
@@ -6919,7 +6919,7 @@ bool netdev_has_upper_dev(struct net_device *dev,
EXPORT_SYMBOL(netdev_has_upper_dev);
/**
- * netdev_has_upper_dev_all - Check if device is linked to an upper device
+ * netdev_has_upper_dev_all_rcu - Check if device is linked to an upper device
* @dev: device
* @upper_dev: upper device to check
*
@@ -8157,7 +8157,7 @@ EXPORT_SYMBOL(netdev_lower_dev_get_private);
/**
- * netdev_lower_change - Dispatch event about lower device state change
+ * netdev_lower_state_changed - Dispatch event about lower device state change
* @lower_dev: device
* @lower_state_info: state to dispatch
*
@@ -8902,7 +8902,7 @@ static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode)
return dev->netdev_ops->ndo_bpf;
default:
return NULL;
- };
+ }
}
static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev,
@@ -10366,6 +10366,21 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
}
EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats);
+/**
+ * dev_get_tstats64 - ndo_get_stats64 implementation
+ * @dev: device to get statistics from
+ * @s: place to store stats
+ *
+ * Populate @s from dev->stats and dev->tstats. Can be used as
+ * ndo_get_stats64() callback.
+ */
+void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s)
+{
+ netdev_stats_to_stats64(s, &dev->stats);
+ dev_fetch_sw_netstats(s, dev->tstats);
+}
+EXPORT_SYMBOL_GPL(dev_get_tstats64);
+
struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
{
struct netdev_queue *queue = dev_ingress_queue(dev);
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 205e92e604ef..db8a0ff86f36 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -230,7 +230,7 @@ static int dev_do_ioctl(struct net_device *dev,
struct ifreq *ifr, unsigned int cmd)
{
const struct net_device_ops *ops = dev->netdev_ops;
- int err = -EOPNOTSUPP;
+ int err;
err = dsa_ndo_do_ioctl(dev, ifr, cmd);
if (err == 0 || err != -EOPNOTSUPP)
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 7bcfb16854cb..cd80ffed6d26 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -563,7 +563,7 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net_device *dev;
nlrule->iifindex = -1;
- nla_strlcpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
+ nla_strscpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
dev = __dev_get_by_name(net, nlrule->iifname);
if (dev)
nlrule->iifindex = dev->ifindex;
@@ -573,7 +573,7 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net_device *dev;
nlrule->oifindex = -1;
- nla_strlcpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
+ nla_strscpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
dev = __dev_get_by_name(net, nlrule->oifname);
if (dev)
nlrule->oifindex = dev->ifindex;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index e21950a2c897..6f1adba6695f 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -48,7 +48,7 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
memset(flow_dissector, 0, sizeof(*flow_dissector));
for (i = 0; i < key_count; i++, key++) {
- /* User should make sure that every key target offset is withing
+ /* User should make sure that every key target offset is within
* boundaries of unsigned short.
*/
BUG_ON(key->offset > USHRT_MAX);
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index ef98372facf6..f3c690b8c8e3 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -11,6 +11,8 @@
#include <linux/device.h>
#include <net/page_pool.h>
+#include <net/xdp.h>
+
#include <linux/dma-direction.h>
#include <linux/dma-mapping.h>
#include <linux/page-flags.h>
@@ -362,8 +364,9 @@ static bool pool_page_reusable(struct page_pool *pool, struct page *page)
* If the page refcnt != 1, then the page will be returned to memory
* subsystem.
*/
-void page_pool_put_page(struct page_pool *pool, struct page *page,
- unsigned int dma_sync_size, bool allow_direct)
+static __always_inline struct page *
+__page_pool_put_page(struct page_pool *pool, struct page *page,
+ unsigned int dma_sync_size, bool allow_direct)
{
/* This allocator is optimized for the XDP mode that uses
* one-frame-per-page, but have fallbacks that act like the
@@ -379,15 +382,12 @@ void page_pool_put_page(struct page_pool *pool, struct page *page,
page_pool_dma_sync_for_device(pool, page,
dma_sync_size);
- if (allow_direct && in_serving_softirq())
- if (page_pool_recycle_in_cache(page, pool))
- return;
+ if (allow_direct && in_serving_softirq() &&
+ page_pool_recycle_in_cache(page, pool))
+ return NULL;
- if (!page_pool_recycle_in_ring(pool, page)) {
- /* Cache full, fallback to free pages */
- page_pool_return_page(pool, page);
- }
- return;
+ /* Page found as candidate for recycling */
+ return page;
}
/* Fallback/non-XDP mode: API user have elevated refcnt.
*
@@ -405,9 +405,59 @@ void page_pool_put_page(struct page_pool *pool, struct page *page,
/* Do not replace this with page_pool_return_page() */
page_pool_release_page(pool, page);
put_page(page);
+
+ return NULL;
+}
+
+void page_pool_put_page(struct page_pool *pool, struct page *page,
+ unsigned int dma_sync_size, bool allow_direct)
+{
+ page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct);
+ if (page && !page_pool_recycle_in_ring(pool, page)) {
+ /* Cache full, fallback to free pages */
+ page_pool_return_page(pool, page);
+ }
}
EXPORT_SYMBOL(page_pool_put_page);
+/* Caller must not use data area after call, as this function overwrites it */
+void page_pool_put_page_bulk(struct page_pool *pool, void **data,
+ int count)
+{
+ int i, bulk_len = 0;
+
+ for (i = 0; i < count; i++) {
+ struct page *page = virt_to_head_page(data[i]);
+
+ page = __page_pool_put_page(pool, page, -1, false);
+ /* Approved for bulk recycling in ptr_ring cache */
+ if (page)
+ data[bulk_len++] = page;
+ }
+
+ if (unlikely(!bulk_len))
+ return;
+
+ /* Bulk producer into ptr_ring page_pool cache */
+ page_pool_ring_lock(pool);
+ for (i = 0; i < bulk_len; i++) {
+ if (__ptr_ring_produce(&pool->ring, data[i]))
+ break; /* ring full */
+ }
+ page_pool_ring_unlock(pool);
+
+ /* Hopefully all pages was return into ptr_ring */
+ if (likely(i == bulk_len))
+ return;
+
+ /* ptr_ring cache full, free remaining pages outside producer lock
+ * since put_page() with refcnt == 1 can be an expensive operation
+ */
+ for (; i < bulk_len; i++)
+ page_pool_return_page(pool, data[i]);
+}
+EXPORT_SYMBOL(page_pool_put_page_bulk);
+
static void page_pool_empty_ring(struct page_pool *pool)
{
struct page *page;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 7d7223691783..60917ff4a00b 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1939,7 +1939,7 @@ static const struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla
if (linfo[IFLA_INFO_KIND]) {
char kind[MODULE_NAME_LEN];
- nla_strlcpy(kind, linfo[IFLA_INFO_KIND], sizeof(kind));
+ nla_strscpy(kind, linfo[IFLA_INFO_KIND], sizeof(kind));
ops = rtnl_link_ops_get(kind);
}
@@ -2953,9 +2953,9 @@ static struct net_device *rtnl_dev_get(struct net *net,
if (!ifname) {
ifname = buffer;
if (ifname_attr)
- nla_strlcpy(ifname, ifname_attr, IFNAMSIZ);
+ nla_strscpy(ifname, ifname_attr, IFNAMSIZ);
else if (altifname_attr)
- nla_strlcpy(ifname, altifname_attr, ALTIFNAMSIZ);
+ nla_strscpy(ifname, altifname_attr, ALTIFNAMSIZ);
else
return NULL;
}
@@ -2983,7 +2983,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
goto errout;
if (tb[IFLA_IFNAME])
- nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+ nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
else
ifname[0] = '\0';
@@ -3264,7 +3264,7 @@ replay:
return err;
if (tb[IFLA_IFNAME])
- nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+ nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
else
ifname[0] = '\0';
@@ -3296,7 +3296,7 @@ replay:
memset(linkinfo, 0, sizeof(linkinfo));
if (linkinfo[IFLA_INFO_KIND]) {
- nla_strlcpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind));
+ nla_strscpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind));
ops = rtnl_link_ops_get(kind);
} else {
kind[0] = '\0';
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1ba8f0163744..ffe3dcc0ebea 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -249,6 +249,9 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
fclones->skb2.fclone = SKB_FCLONE_CLONE;
}
+
+ skb_set_kcov_handle(skb, kcov_common_handle());
+
out:
return skb;
nodata:
@@ -282,6 +285,8 @@ static struct sk_buff *__build_skb_around(struct sk_buff *skb,
memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
atomic_set(&shinfo->dataref, 1);
+ skb_set_kcov_handle(skb, kcov_common_handle());
+
return skb;
}
@@ -837,7 +842,7 @@ EXPORT_SYMBOL(consume_skb);
#endif
/**
- * consume_stateless_skb - free an skbuff, assuming it is stateless
+ * __consume_stateless_skb - free an skbuff, assuming it is stateless
* @skb: buffer to free
*
* Alike consume_skb(), but this variant assumes that this is the last
@@ -4203,6 +4208,9 @@ static const u8 skb_ext_type_len[] = {
#if IS_ENABLED(CONFIG_MPTCP)
[SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext),
#endif
+#if IS_ENABLED(CONFIG_KCOV)
+ [SKB_EXT_KCOV_HANDLE] = SKB_EXT_CHUNKSIZEOF(u64),
+#endif
};
static __always_inline unsigned int skb_ext_total_length(void)
@@ -4220,6 +4228,9 @@ static __always_inline unsigned int skb_ext_total_length(void)
#if IS_ENABLED(CONFIG_MPTCP)
skb_ext_type_len[SKB_EXT_MPTCP] +
#endif
+#if IS_ENABLED(CONFIG_KCOV)
+ skb_ext_type_len[SKB_EXT_KCOV_HANDLE] +
+#endif
0;
}
@@ -5430,7 +5441,8 @@ struct sk_buff *skb_vlan_untag(struct sk_buff *skb)
goto err_free;
skb_reset_network_header(skb);
- skb_reset_transport_header(skb);
+ if (!skb_transport_header_was_set(skb))
+ skb_reset_transport_header(skb);
skb_reset_mac_len(skb);
return skb;
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 48aba933a5a8..3d330ebda893 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -380,6 +380,60 @@ void xdp_return_frame_rx_napi(struct xdp_frame *xdpf)
}
EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi);
+/* XDP bulk APIs introduce a defer/flush mechanism to return
+ * pages belonging to the same xdp_mem_allocator object
+ * (identified via the mem.id field) in bulk to optimize
+ * I-cache and D-cache.
+ * The bulk queue size is set to 16 to be aligned to how
+ * XDP_REDIRECT bulking works. The bulk is flushed when
+ * it is full or when mem.id changes.
+ * xdp_frame_bulk is usually stored/allocated on the function
+ * call-stack to avoid locking penalties.
+ */
+void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq)
+{
+ struct xdp_mem_allocator *xa = bq->xa;
+
+ if (unlikely(!xa || !bq->count))
+ return;
+
+ page_pool_put_page_bulk(xa->page_pool, bq->q, bq->count);
+ /* bq->xa is not cleared to save lookup, if mem.id same in next bulk */
+ bq->count = 0;
+}
+EXPORT_SYMBOL_GPL(xdp_flush_frame_bulk);
+
+/* Must be called with rcu_read_lock held */
+void xdp_return_frame_bulk(struct xdp_frame *xdpf,
+ struct xdp_frame_bulk *bq)
+{
+ struct xdp_mem_info *mem = &xdpf->mem;
+ struct xdp_mem_allocator *xa;
+
+ if (mem->type != MEM_TYPE_PAGE_POOL) {
+ __xdp_return(xdpf->data, &xdpf->mem, false);
+ return;
+ }
+
+ xa = bq->xa;
+ if (unlikely(!xa)) {
+ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+ bq->count = 0;
+ bq->xa = xa;
+ }
+
+ if (bq->count == XDP_BULK_QUEUE_SIZE)
+ xdp_flush_frame_bulk(bq);
+
+ if (unlikely(mem->id != xa->mem.id)) {
+ xdp_flush_frame_bulk(bq);
+ bq->xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+ }
+
+ bq->q[bq->count++] = xdpf->data;
+}
+EXPORT_SYMBOL_GPL(xdp_return_frame_bulk);
+
void xdp_return_buff(struct xdp_buff *xdp)
{
__xdp_return(xdp->data, &xdp->rxq->mem, true);
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 16014ad19406..084e159a12ba 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1827,6 +1827,8 @@ static int dcb_app_add(const struct dcb_app *app, int ifindex)
/**
* dcb_getapp - retrieve the DCBX application user priority
+ * @dev: network interface
+ * @app: application to get user priority of
*
* On success returns a non-zero 802.1p user priority bitmap
* otherwise returns 0 as the invalid user priority bitmap to
@@ -1849,6 +1851,8 @@ EXPORT_SYMBOL(dcb_getapp);
/**
* dcb_setapp - add CEE dcb application data to app list
+ * @dev: network interface
+ * @new: application data to add
*
* Priority 0 is an invalid priority in CEE spec. This routine
* removes applications from the app list if the priority is
@@ -1890,6 +1894,8 @@ EXPORT_SYMBOL(dcb_setapp);
/**
* dcb_ieee_getapp_mask - retrieve the IEEE DCB application priority
+ * @dev: network interface
+ * @app: where to store the retrieve application data
*
* Helper routine which on success returns a non-zero 802.1Qaz user
* priority bitmap otherwise returns 0 to indicate the dcb_app was
@@ -1912,6 +1918,8 @@ EXPORT_SYMBOL(dcb_ieee_getapp_mask);
/**
* dcb_ieee_setapp - add IEEE dcb application data to app list
+ * @dev: network interface
+ * @new: application data to add
*
* This adds Application data to the list. Multiple application
* entries may exists for the same selector and protocol as long
@@ -1946,6 +1954,8 @@ EXPORT_SYMBOL(dcb_ieee_setapp);
/**
* dcb_ieee_delapp - delete IEEE dcb application data from list
+ * @dev: network interface
+ * @del: application data to delete
*
* This removes a matching APP data from the APP list
*/
@@ -1975,7 +1985,7 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del)
}
EXPORT_SYMBOL(dcb_ieee_delapp);
-/**
+/*
* dcb_ieee_getapp_prio_dscp_mask_map - For a given device, find mapping from
* priorities to the DSCP values assigned to that priority. Initialize p_map
* such that each map element holds a bit mask of DSCP values configured for
@@ -2004,7 +2014,7 @@ void dcb_ieee_getapp_prio_dscp_mask_map(const struct net_device *dev,
}
EXPORT_SYMBOL(dcb_ieee_getapp_prio_dscp_mask_map);
-/**
+/*
* dcb_ieee_getapp_dscp_prio_mask_map - For a given device, find mapping from
* DSCP values to the priorities assigned to that DSCP value. Initialize p_map
* such that each map element holds a bit mask of priorities configured for a
@@ -2031,7 +2041,7 @@ dcb_ieee_getapp_dscp_prio_mask_map(const struct net_device *dev,
}
EXPORT_SYMBOL(dcb_ieee_getapp_dscp_prio_mask_map);
-/**
+/*
* Per 802.1Q-2014, the selector value of 1 is used for matching on Ethernet
* type, with valid PID values >= 1536. A special meaning is then assigned to
* protocol value of 0: "default priority. For use when priority is not
diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c
index 8f3dd3b1d2d0..c4bbac99740d 100644
--- a/net/dccp/ackvec.c
+++ b/net/dccp/ackvec.c
@@ -242,6 +242,8 @@ static void dccp_ackvec_add_new(struct dccp_ackvec *av, u32 num_packets,
/**
* dccp_ackvec_input - Register incoming packet in the buffer
+ * @av: Ack Vector to register packet to
+ * @skb: Packet to register
*/
void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb)
{
@@ -273,6 +275,9 @@ void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb)
/**
* dccp_ackvec_clear_state - Perform house-keeping / garbage-collection
+ * @av: Ack Vector record to clean
+ * @ackno: last Ack Vector which has been acknowledged
+ *
* This routine is called when the peer acknowledges the receipt of Ack Vectors
* up to and including @ackno. While based on section A.3 of RFC 4340, here
* are additional precautions to prevent corrupted buffer state. In particular,
diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c
index 1e9bb121ba72..6beac5d348e2 100644
--- a/net/dccp/ccid.c
+++ b/net/dccp/ccid.c
@@ -76,7 +76,7 @@ int ccid_getsockopt_builtin_ccids(struct sock *sk, int len,
return err;
}
-static struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_fmt, const char *fmt,...)
+static __printf(3, 4) struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_fmt, const char *fmt,...)
{
struct kmem_cache *slab;
va_list args;
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index 3da1f77bd039..4d9823d6dced 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -181,6 +181,9 @@ MODULE_PARM_DESC(ccid2_do_cwv, "Perform RFC2861 Congestion Window Validation");
/**
* ccid2_update_used_window - Track how much of cwnd is actually used
+ * @hc: socket to update window
+ * @new_wnd: new window values to add into the filter
+ *
* This is done in addition to CWV. The sender needs to have an idea of how many
* packets may be in flight, to set the local Sequence Window value accordingly
* (RFC 4340, 7.5.2). The CWV mechanism is exploited to keep track of the
@@ -349,6 +352,8 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len)
/**
* ccid2_rtt_estimator - Sample RTT and compute RTO using RFC2988 algorithm
+ * @sk: socket to perform estimator on
+ *
* This code is almost identical with TCP's tcp_rtt_estimator(), since
* - it has a higher sampling frequency (recommended by RFC 1323),
* - the RTO does not collapse into RTT due to RTTVAR going towards zero,
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index b9ee1a4a8955..ca8670f78ac6 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -79,6 +79,8 @@ static inline u64 rfc3390_initial_rate(struct sock *sk)
/**
* ccid3_update_send_interval - Calculate new t_ipi = s / X_inst
+ * @hc: socket to have the send interval updated
+ *
* This respects the granularity of X_inst (64 * bytes/second).
*/
static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hc)
@@ -99,6 +101,7 @@ static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hc, ktime_t now)
/**
* ccid3_hc_tx_update_x - Update allowed sending rate X
+ * @sk: socket to be updated
* @stamp: most recent time if available - can be left NULL.
*
* This function tracks draft rfc3448bis, check there for latest details.
@@ -151,6 +154,7 @@ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp)
/**
* ccid3_hc_tx_update_s - Track the mean packet size `s'
+ * @hc: socket to be updated
* @len: DCCP packet payload size in bytes
*
* cf. RFC 4342, 5.3 and RFC 3448, 4.1
@@ -259,6 +263,7 @@ out:
/**
* ccid3_hc_tx_send_packet - Delay-based dequeueing of TX packets
+ * @sk: socket to send packet from
* @skb: next packet candidate to send on @sk
*
* This function uses the convention of ccid_packet_dequeue_eval() and
@@ -655,6 +660,7 @@ static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb)
/**
* ccid3_first_li - Implements [RFC 5348, 6.3.1]
+ * @sk: socket to calculate loss interval for
*
* Determine the length of the first loss interval via inverse lookup.
* Assume that X_recv can be computed by the throughput equation
diff --git a/net/dccp/ccids/lib/loss_interval.c b/net/dccp/ccids/lib/loss_interval.c
index 67abad695e66..da95319842bb 100644
--- a/net/dccp/ccids/lib/loss_interval.c
+++ b/net/dccp/ccids/lib/loss_interval.c
@@ -79,6 +79,9 @@ static void tfrc_lh_calc_i_mean(struct tfrc_loss_hist *lh)
/**
* tfrc_lh_update_i_mean - Update the `open' loss interval I_0
+ * @lh: histogram to update
+ * @skb: received socket triggering loss interval update
+ *
* For recomputing p: returns `true' if p > p_prev <=> 1/p < 1/p_prev
*/
u8 tfrc_lh_update_i_mean(struct tfrc_loss_hist *lh, struct sk_buff *skb)
diff --git a/net/dccp/ccids/lib/packet_history.c b/net/dccp/ccids/lib/packet_history.c
index af08e2df7108..0cdda3c66fb5 100644
--- a/net/dccp/ccids/lib/packet_history.c
+++ b/net/dccp/ccids/lib/packet_history.c
@@ -385,6 +385,9 @@ static inline struct tfrc_rx_hist_entry *
/**
* tfrc_rx_hist_sample_rtt - Sample RTT from timestamp / CCVal
+ * @h: receive histogram
+ * @skb: packet containing timestamp.
+ *
* Based on ideas presented in RFC 4342, 8.1. Returns 0 if it was not able
* to compute a sample with given data - calling function should check this.
*/
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index 788dd629c420..305f56804832 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -996,6 +996,8 @@ int dccp_feat_finalise_settings(struct dccp_sock *dp)
/**
* dccp_feat_server_ccid_dependencies - Resolve CCID-dependent features
+ * @dreq: server socket to resolve
+ *
* It is the server which resolves the dependencies once the CCID has been
* fully negotiated. If no CCID has been negotiated, it uses the default CCID.
*/
@@ -1033,6 +1035,10 @@ static int dccp_feat_preflist_match(u8 *servlist, u8 slen, u8 *clilist, u8 clen)
/**
* dccp_feat_prefer - Move preferred entry to the start of array
+ * @preferred_value: entry to move to start of array
+ * @array: array of preferred entries
+ * @array_len: size of the array
+ *
* Reorder the @array_len elements in @array so that @preferred_value comes
* first. Returns >0 to indicate that @preferred_value does occur in @array.
*/
diff --git a/net/dccp/output.c b/net/dccp/output.c
index 50e6d5699bb2..b8a24734385e 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -143,6 +143,8 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
/**
* dccp_determine_ccmps - Find out about CCID-specific packet-size limits
+ * @dp: socket to find packet size limits of
+ *
* We only consider the HC-sender CCID for setting the CCMPS (RFC 4340, 14.),
* since the RX CCID is restricted to feedback packets (Acks), which are small
* in comparison with the data traffic. A value of 0 means "no current CCMPS".
@@ -236,6 +238,8 @@ static int dccp_wait_for_ccid(struct sock *sk, unsigned long delay)
/**
* dccp_xmit_packet - Send data packet under control of CCID
+ * @sk: socket to send data packet on
+ *
* Transmits next-queued payload and informs CCID to account for the packet.
*/
static void dccp_xmit_packet(struct sock *sk)
@@ -296,6 +300,9 @@ static void dccp_xmit_packet(struct sock *sk)
/**
* dccp_flush_write_queue - Drain queue at end of connection
+ * @sk: socket to be drained
+ * @time_budget: time allowed to drain the queue
+ *
* Since dccp_sendmsg queues packets without waiting for them to be sent, it may
* happen that the TX queue is not empty at the end of a connection. We give the
* HC-sender CCID a grace period of up to @time_budget jiffies. If this function
@@ -367,6 +374,8 @@ void dccp_write_xmit(struct sock *sk)
/**
* dccp_retransmit_skb - Retransmit Request, Close, or CloseReq packets
+ * @sk: socket to perform retransmit on
+ *
* There are only four retransmittable packet types in DCCP:
* - Request in client-REQUEST state (sec. 8.1.1),
* - CloseReq in server-CLOSEREQ state (sec. 8.3),
diff --git a/net/dccp/qpolicy.c b/net/dccp/qpolicy.c
index db2448c33a62..5ba204ec0aca 100644
--- a/net/dccp/qpolicy.c
+++ b/net/dccp/qpolicy.c
@@ -65,14 +65,16 @@ static bool qpolicy_prio_full(struct sock *sk)
* @push: add a new @skb to the write queue
* @full: indicates that no more packets will be admitted
* @top: peeks at whatever the queueing policy defines as its `top'
+ * @params: parameter passed to policy operation
*/
-static struct dccp_qpolicy_operations {
+struct dccp_qpolicy_operations {
void (*push) (struct sock *sk, struct sk_buff *skb);
bool (*full) (struct sock *sk);
struct sk_buff* (*top) (struct sock *sk);
__be32 params;
+};
-} qpol_table[DCCPQ_POLICY_MAX] = {
+static struct dccp_qpolicy_operations qpol_table[DCCPQ_POLICY_MAX] = {
[DCCPQ_POLICY_SIMPLE] = {
.push = qpolicy_simple_push,
.full = qpolicy_simple_full,
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index a934d2932373..db768f223ef7 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -215,13 +215,14 @@ out:
/**
* dccp_write_xmitlet - Workhorse for CCID packet dequeueing interface
- * @data: Socket to act on
+ * @t: pointer to the tasklet associated with this handler
*
* See the comments above %ccid_dequeueing_decision for supported modes.
*/
-static void dccp_write_xmitlet(unsigned long data)
+static void dccp_write_xmitlet(struct tasklet_struct *t)
{
- struct sock *sk = (struct sock *)data;
+ struct dccp_sock *dp = from_tasklet(dp, t, dccps_xmitlet);
+ struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk;
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
@@ -235,16 +236,15 @@ static void dccp_write_xmitlet(unsigned long data)
static void dccp_write_xmit_timer(struct timer_list *t)
{
struct dccp_sock *dp = from_timer(dp, t, dccps_xmit_timer);
- struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk;
- dccp_write_xmitlet((unsigned long)sk);
+ dccp_write_xmitlet(&dp->dccps_xmitlet);
}
void dccp_init_xmit_timers(struct sock *sk)
{
struct dccp_sock *dp = dccp_sk(sk);
- tasklet_init(&dp->dccps_xmitlet, dccp_write_xmitlet, (unsigned long)sk);
+ tasklet_setup(&dp->dccps_xmitlet, dccp_write_xmitlet);
timer_setup(&dp->dccps_xmit_timer, dccp_write_xmit_timer, 0);
inet_csk_init_xmit_timers(sk, &dccp_write_timer, &dccp_delack_timer,
&dccp_keepalive_timer);
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index 15d42353f1a3..d1c50a48614b 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -658,7 +658,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
ifa->ifa_dev = dn_db;
if (tb[IFA_LABEL])
- nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
+ nla_strscpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
else
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index 1f9b9b11008c..dfecd7b22fd7 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -56,20 +56,31 @@ config NET_DSA_TAG_BRCM_PREPEND
Broadcom switches which places the tag before the Ethernet header
(prepended).
+config NET_DSA_TAG_HELLCREEK
+ tristate "Tag driver for Hirschmann Hellcreek TSN switches"
+ help
+ Say Y or M if you want to enable support for tagging frames
+ for the Hirschmann Hellcreek TSN switches.
+
config NET_DSA_TAG_GSWIP
tristate "Tag driver for Lantiq / Intel GSWIP switches"
help
Say Y or M if you want to enable support for tagging frames for the
Lantiq / Intel GSWIP switches.
+config NET_DSA_TAG_DSA_COMMON
+ tristate
+
config NET_DSA_TAG_DSA
tristate "Tag driver for Marvell switches using DSA headers"
+ select NET_DSA_TAG_DSA_COMMON
help
Say Y or M if you want to enable support for tagging frames for the
Marvell switches which use DSA headers.
config NET_DSA_TAG_EDSA
tristate "Tag driver for Marvell switches using EtherType DSA headers"
+ select NET_DSA_TAG_DSA_COMMON
help
Say Y or M if you want to enable support for tagging frames for the
Marvell switches which use EtherType DSA headers.
diff --git a/net/dsa/Makefile b/net/dsa/Makefile
index 4f47b2025ff5..0fb2b75a7ae3 100644
--- a/net/dsa/Makefile
+++ b/net/dsa/Makefile
@@ -7,9 +7,9 @@ dsa_core-y += dsa.o dsa2.o master.o port.o slave.o switch.o
obj-$(CONFIG_NET_DSA_TAG_8021Q) += tag_8021q.o
obj-$(CONFIG_NET_DSA_TAG_AR9331) += tag_ar9331.o
obj-$(CONFIG_NET_DSA_TAG_BRCM_COMMON) += tag_brcm.o
-obj-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o
-obj-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o
+obj-$(CONFIG_NET_DSA_TAG_DSA_COMMON) += tag_dsa.o
obj-$(CONFIG_NET_DSA_TAG_GSWIP) += tag_gswip.o
+obj-$(CONFIG_NET_DSA_TAG_HELLCREEK) += tag_hellcreek.o
obj-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o
obj-$(CONFIG_NET_DSA_TAG_RTL4_A) += tag_rtl4_a.o
obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 2131bf2b3a67..a1b1dc8a4d87 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -201,7 +201,6 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
struct sk_buff *nskb = NULL;
- struct pcpu_sw_netstats *s;
struct dsa_slave_priv *p;
if (unlikely(!cpu_dp)) {
@@ -234,11 +233,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
skb = nskb;
}
- s = this_cpu_ptr(p->stats64);
- u64_stats_update_begin(&s->syncp);
- s->rx_packets++;
- s->rx_bytes += skb->len;
- u64_stats_update_end(&s->syncp);
+ dev_sw_netstats_rx_add(skb->dev, skb->len);
if (dsa_skb_defer_rx_timestamp(p, skb))
return 0;
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 12998bf04e55..7c96aae9062c 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -78,8 +78,6 @@ struct dsa_slave_priv {
struct sk_buff * (*xmit)(struct sk_buff *skb,
struct net_device *dev);
- struct pcpu_sw_netstats __percpu *stats64;
-
struct gro_cells gcells;
/* DSA port data, such as switch, port index, etc. */
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 3bc5ca40c9fb..ff2266d2b998 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -548,17 +548,36 @@ netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev)
}
EXPORT_SYMBOL_GPL(dsa_enqueue_skb);
+static int dsa_realloc_skb(struct sk_buff *skb, struct net_device *dev)
+{
+ int needed_headroom = dev->needed_headroom;
+ int needed_tailroom = dev->needed_tailroom;
+
+ /* For tail taggers, we need to pad short frames ourselves, to ensure
+ * that the tail tag does not fail at its role of being at the end of
+ * the packet, once the master interface pads the frame. Account for
+ * that pad length here, and pad later.
+ */
+ if (unlikely(needed_tailroom && skb->len < ETH_ZLEN))
+ needed_tailroom += ETH_ZLEN - skb->len;
+ /* skb_headroom() returns unsigned int... */
+ needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0);
+ needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0);
+
+ if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb)))
+ /* No reallocation needed, yay! */
+ return 0;
+
+ return pskb_expand_head(skb, needed_headroom, needed_tailroom,
+ GFP_ATOMIC);
+}
+
static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct dsa_slave_priv *p = netdev_priv(dev);
- struct pcpu_sw_netstats *s;
struct sk_buff *nskb;
- s = this_cpu_ptr(p->stats64);
- u64_stats_update_begin(&s->syncp);
- s->tx_packets++;
- s->tx_bytes += skb->len;
- u64_stats_update_end(&s->syncp);
+ dev_sw_netstats_tx_add(dev, 1, skb->len);
DSA_SKB_CB(skb)->clone = NULL;
@@ -567,6 +586,17 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
*/
dsa_skb_tx_timestamp(p, skb);
+ if (dsa_realloc_skb(skb, dev)) {
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+ }
+
+ /* needed_tailroom should still be 'warm' in the cache line from
+ * dsa_realloc_skb(), which has also ensured that padding is safe.
+ */
+ if (dev->needed_tailroom)
+ eth_skb_pad(skb);
+
/* Transmit function may have to reallocate the original SKB,
* in which case it must have freed it. Only free it here on error.
*/
@@ -679,7 +709,6 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev,
uint64_t *data)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
- struct dsa_slave_priv *p = netdev_priv(dev);
struct dsa_switch *ds = dp->ds;
struct pcpu_sw_netstats *s;
unsigned int start;
@@ -688,7 +717,7 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev,
for_each_possible_cpu(i) {
u64 tx_packets, tx_bytes, rx_packets, rx_bytes;
- s = per_cpu_ptr(p->stats64, i);
+ s = per_cpu_ptr(dev->tstats, i);
do {
start = u64_stats_fetch_begin_irq(&s->syncp);
tx_packets = s->tx_packets;
@@ -1217,15 +1246,6 @@ static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type,
return ds->ops->port_setup_tc(ds, dp->index, type, type_data);
}
-static void dsa_slave_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *stats)
-{
- struct dsa_slave_priv *p = netdev_priv(dev);
-
- netdev_stats_to_stats64(stats, &dev->stats);
- dev_fetch_sw_netstats(stats, p->stats64);
-}
-
static int dsa_slave_get_rxnfc(struct net_device *dev,
struct ethtool_rxnfc *nfc, u32 *rule_locs)
{
@@ -1601,7 +1621,7 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
#endif
.ndo_get_phys_port_name = dsa_slave_get_phys_port_name,
.ndo_setup_tc = dsa_slave_setup_tc,
- .ndo_get_stats64 = dsa_slave_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_port_parent_id = dsa_slave_get_port_parent_id,
.ndo_vlan_rx_add_vid = dsa_slave_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = dsa_slave_vlan_rx_kill_vid,
@@ -1791,6 +1811,16 @@ int dsa_slave_create(struct dsa_port *port)
slave_dev->netdev_ops = &dsa_slave_netdev_ops;
if (ds->ops->port_max_mtu)
slave_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index);
+ if (cpu_dp->tag_ops->tail_tag)
+ slave_dev->needed_tailroom = cpu_dp->tag_ops->overhead;
+ else
+ slave_dev->needed_headroom = cpu_dp->tag_ops->overhead;
+ /* Try to save one extra realloc later in the TX path (in the master)
+ * by also inheriting the master's needed headroom and tailroom.
+ * The 8021q driver also does this.
+ */
+ slave_dev->needed_headroom += master->needed_headroom;
+ slave_dev->needed_tailroom += master->needed_tailroom;
SET_NETDEV_DEVTYPE(slave_dev, &dsa_type);
netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one,
@@ -1801,8 +1831,8 @@ int dsa_slave_create(struct dsa_port *port)
slave_dev->vlan_features = master->vlan_features;
p = netdev_priv(slave_dev);
- p->stats64 = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
- if (!p->stats64) {
+ slave_dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+ if (!slave_dev->tstats) {
free_netdev(slave_dev);
return -ENOMEM;
}
@@ -1864,7 +1894,7 @@ out_phy:
out_gcells:
gro_cells_destroy(&p->gcells);
out_free:
- free_percpu(p->stats64);
+ free_percpu(slave_dev->tstats);
free_netdev(slave_dev);
port->slave = NULL;
return ret;
@@ -1886,7 +1916,7 @@ void dsa_slave_destroy(struct net_device *slave_dev)
dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER);
phylink_destroy(dp->pl);
gro_cells_destroy(&p->gcells);
- free_percpu(p->stats64);
+ free_percpu(slave_dev->tstats);
free_netdev(slave_dev);
}
@@ -1987,10 +2017,22 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb,
switch (event) {
case NETDEV_PRECHANGEUPPER: {
struct netdev_notifier_changeupper_info *info = ptr;
+ struct dsa_switch *ds;
+ struct dsa_port *dp;
+ int err;
if (!dsa_slave_dev_check(dev))
return dsa_prevent_bridging_8021q_upper(dev, ptr);
+ dp = dsa_slave_to_port(dev);
+ ds = dp->ds;
+
+ if (ds->ops->port_prechangeupper) {
+ err = ds->ops->port_prechangeupper(ds, dp->index, info);
+ if (err)
+ return notifier_from_errno(err);
+ }
+
if (is_vlan_dev(info->upper_dev))
return dsa_slave_check_8021q_upper(dev, ptr);
break;
diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c
index 55b00694cdba..002cf7f952e2 100644
--- a/net/dsa/tag_ar9331.c
+++ b/net/dsa/tag_ar9331.c
@@ -31,9 +31,6 @@ static struct sk_buff *ar9331_tag_xmit(struct sk_buff *skb,
__le16 *phdr;
u16 hdr;
- if (skb_cow_head(skb, AR9331_HDR_LEN) < 0)
- return NULL;
-
phdr = skb_push(skb, AR9331_HDR_LEN);
hdr = FIELD_PREP(AR9331_HDR_VERSION_MASK, AR9331_HDR_VERSION);
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index ad72dff8d524..e934dace3922 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -66,9 +66,6 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb,
u16 queue = skb_get_queue_mapping(skb);
u8 *brcm_tag;
- if (skb_cow_head(skb, BRCM_TAG_LEN) < 0)
- return NULL;
-
/* The Ethernet switch we are interfaced with needs packets to be at
* least 64 bytes (including FCS) otherwise they will be discarded when
* they enter the switch port logic. When Broadcom tags are enabled, we
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index 0b756fae68a5..112c7c6dd568 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -1,7 +1,48 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * net/dsa/tag_dsa.c - (Non-ethertype) DSA tagging
+ * Regular and Ethertype DSA tagging
* Copyright (c) 2008-2009 Marvell Semiconductor
+ *
+ * Regular DSA
+ * -----------
+
+ * For untagged (in 802.1Q terms) packets, the switch will splice in
+ * the tag between the SA and the ethertype of the original
+ * packet. Tagged frames will instead have their outermost .1Q tag
+ * converted to a DSA tag. It expects the same layout when receiving
+ * packets from the CPU.
+ *
+ * Example:
+ *
+ * .----.----.----.---------
+ * Pu: | DA | SA | ET | Payload ...
+ * '----'----'----'---------
+ * 6 6 2 N
+ * .----.----.--------.-----.----.---------
+ * Pt: | DA | SA | 0x8100 | TCI | ET | Payload ...
+ * '----'----'--------'-----'----'---------
+ * 6 6 2 2 2 N
+ * .----.----.-----.----.---------
+ * Pd: | DA | SA | DSA | ET | Payload ...
+ * '----'----'-----'----'---------
+ * 6 6 4 2 N
+ *
+ * No matter if a packet is received untagged (Pu) or tagged (Pt),
+ * they will both have the same layout (Pd) when they are sent to the
+ * CPU. This is done by ignoring 802.3, replacing the ethertype field
+ * with more metadata, among which is a bit to signal if the original
+ * packet was tagged or not.
+ *
+ * Ethertype DSA
+ * -------------
+ * Uses the exact same tag format as regular DSA, but also includes a
+ * proper ethertype field (which the mv88e6xxx driver sets to
+ * ETH_P_EDSA/0xdada) followed by two zero bytes:
+ *
+ * .----.----.--------.--------.-----.----.---------
+ * | DA | SA | 0xdada | 0x0000 | DSA | ET | Payload ...
+ * '----'----'--------'--------'-----'----'---------
+ * 6 6 2 2 4 2 N
*/
#include <linux/etherdevice.h>
@@ -12,46 +53,104 @@
#define DSA_HLEN 4
-static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
+/**
+ * enum dsa_cmd - DSA Command
+ * @DSA_CMD_TO_CPU: Set on packets that were trapped or mirrored to
+ * the CPU port. This is needed to implement control protocols,
+ * e.g. STP and LLDP, that must not allow those control packets to
+ * be switched according to the normal rules.
+ * @DSA_CMD_FROM_CPU: Used by the CPU to send a packet to a specific
+ * port, ignoring all the barriers that the switch normally
+ * enforces (VLANs, STP port states etc.). No source address
+ * learning takes place. "sudo send packet"
+ * @DSA_CMD_TO_SNIFFER: Set on the copies of packets that matched some
+ * user configured ingress or egress monitor criteria. These are
+ * forwarded by the switch tree to the user configured ingress or
+ * egress monitor port, which can be set to the CPU port or a
+ * regular port. If the destination is a regular port, the tag
+ * will be removed before egressing the port. If the destination
+ * is the CPU port, the tag will not be removed.
+ * @DSA_CMD_FORWARD: This tag is used on all bulk traffic passing
+ * through the switch tree, including the flows that are directed
+ * towards the CPU. Its device/port tuple encodes the original
+ * source port on which the packet ingressed. It can also be used
+ * on transmit by the CPU to defer the forwarding decision to the
+ * hardware, based on the current config of PVT/VTU/ATU
+ * etc. Source address learning takes places if enabled on the
+ * receiving DSA/CPU port.
+ */
+enum dsa_cmd {
+ DSA_CMD_TO_CPU = 0,
+ DSA_CMD_FROM_CPU = 1,
+ DSA_CMD_TO_SNIFFER = 2,
+ DSA_CMD_FORWARD = 3
+};
+
+/**
+ * enum dsa_code - TO_CPU Code
+ *
+ * @DSA_CODE_MGMT_TRAP: DA was classified as a management
+ * address. Typical examples include STP BPDUs and LLDP.
+ * @DSA_CODE_FRAME2REG: Response to a "remote management" request.
+ * @DSA_CODE_IGMP_MLD_TRAP: IGMP/MLD signaling.
+ * @DSA_CODE_POLICY_TRAP: Frame matched some policy configuration on
+ * the device. Typical examples are matching on DA/SA/VID and DHCP
+ * snooping.
+ * @DSA_CODE_ARP_MIRROR: The name says it all really.
+ * @DSA_CODE_POLICY_MIRROR: Same as @DSA_CODE_POLICY_TRAP, but the
+ * particular policy was set to trigger a mirror instead of a
+ * trap.
+ * @DSA_CODE_RESERVED_6: Unused on all devices up to at least 6393X.
+ * @DSA_CODE_RESERVED_7: Unused on all devices up to at least 6393X.
+ *
+ * A 3-bit code is used to relay why a particular frame was sent to
+ * the CPU. We only use this to determine if the packet was mirrored
+ * or trapped, i.e. whether the packet has been forwarded by hardware
+ * or not.
+ *
+ * This is the superset of all possible codes. Any particular device
+ * may only implement a subset.
+ */
+enum dsa_code {
+ DSA_CODE_MGMT_TRAP = 0,
+ DSA_CODE_FRAME2REG = 1,
+ DSA_CODE_IGMP_MLD_TRAP = 2,
+ DSA_CODE_POLICY_TRAP = 3,
+ DSA_CODE_ARP_MIRROR = 4,
+ DSA_CODE_POLICY_MIRROR = 5,
+ DSA_CODE_RESERVED_6 = 6,
+ DSA_CODE_RESERVED_7 = 7
+};
+
+static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev,
+ u8 extra)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
u8 *dsa_header;
- /*
- * Convert the outermost 802.1q tag to a DSA tag for tagged
- * packets, or insert a DSA tag between the addresses and
- * the ethertype field for untagged packets.
- */
if (skb->protocol == htons(ETH_P_8021Q)) {
- if (skb_cow_head(skb, 0) < 0)
- return NULL;
+ if (extra) {
+ skb_push(skb, extra);
+ memmove(skb->data, skb->data + extra, 2 * ETH_ALEN);
+ }
- /*
- * Construct tagged FROM_CPU DSA tag from 802.1q tag.
- */
- dsa_header = skb->data + 2 * ETH_ALEN;
- dsa_header[0] = 0x60 | dp->ds->index;
+ /* Construct tagged FROM_CPU DSA tag from 802.1Q tag. */
+ dsa_header = skb->data + 2 * ETH_ALEN + extra;
+ dsa_header[0] = (DSA_CMD_FROM_CPU << 6) | 0x20 | dp->ds->index;
dsa_header[1] = dp->index << 3;
- /*
- * Move CFI field from byte 2 to byte 1.
- */
+ /* Move CFI field from byte 2 to byte 1. */
if (dsa_header[2] & 0x10) {
dsa_header[1] |= 0x01;
dsa_header[2] &= ~0x10;
}
} else {
- if (skb_cow_head(skb, DSA_HLEN) < 0)
- return NULL;
- skb_push(skb, DSA_HLEN);
+ skb_push(skb, DSA_HLEN + extra);
+ memmove(skb->data, skb->data + DSA_HLEN + extra, 2 * ETH_ALEN);
- memmove(skb->data, skb->data + DSA_HLEN, 2 * ETH_ALEN);
-
- /*
- * Construct untagged FROM_CPU DSA tag.
- */
- dsa_header = skb->data + 2 * ETH_ALEN;
- dsa_header[0] = 0x40 | dp->ds->index;
+ /* Construct untagged FROM_CPU DSA tag. */
+ dsa_header = skb->data + 2 * ETH_ALEN + extra;
+ dsa_header[0] = (DSA_CMD_FROM_CPU << 6) | dp->ds->index;
dsa_header[1] = dp->index << 3;
dsa_header[2] = 0x00;
dsa_header[3] = 0x00;
@@ -60,30 +159,60 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
return skb;
}
-static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
- struct packet_type *pt)
+static struct sk_buff *dsa_rcv_ll(struct sk_buff *skb, struct net_device *dev,
+ u8 extra)
{
+ int source_device, source_port;
+ enum dsa_code code;
+ enum dsa_cmd cmd;
u8 *dsa_header;
- int source_device;
- int source_port;
- if (unlikely(!pskb_may_pull(skb, DSA_HLEN)))
- return NULL;
-
- /*
- * The ethertype field is part of the DSA header.
- */
+ /* The ethertype field is part of the DSA header. */
dsa_header = skb->data - 2;
- /*
- * Check that frame type is either TO_CPU or FORWARD.
- */
- if ((dsa_header[0] & 0xc0) != 0x00 && (dsa_header[0] & 0xc0) != 0xc0)
+ cmd = dsa_header[0] >> 6;
+ switch (cmd) {
+ case DSA_CMD_FORWARD:
+ skb->offload_fwd_mark = 1;
+ break;
+
+ case DSA_CMD_TO_CPU:
+ code = (dsa_header[1] & 0x6) | ((dsa_header[2] >> 4) & 1);
+
+ switch (code) {
+ case DSA_CODE_FRAME2REG:
+ /* Remote management is not implemented yet,
+ * drop.
+ */
+ return NULL;
+ case DSA_CODE_ARP_MIRROR:
+ case DSA_CODE_POLICY_MIRROR:
+ /* Mark mirrored packets to notify any upper
+ * device (like a bridge) that forwarding has
+ * already been done by hardware.
+ */
+ skb->offload_fwd_mark = 1;
+ break;
+ case DSA_CODE_MGMT_TRAP:
+ case DSA_CODE_IGMP_MLD_TRAP:
+ case DSA_CODE_POLICY_TRAP:
+ /* Traps have, by definition, not been
+ * forwarded by hardware, so don't mark them.
+ */
+ break;
+ default:
+ /* Reserved code, this could be anything. Drop
+ * seems like the safest option.
+ */
+ return NULL;
+ }
+
+ break;
+
+ default:
return NULL;
+ }
- /*
- * Determine source device and port.
- */
source_device = dsa_header[0] & 0x1f;
source_port = (dsa_header[1] >> 3) & 0x1f;
@@ -91,16 +220,15 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
if (!skb->dev)
return NULL;
- /*
- * Convert the DSA header to an 802.1q header if the 'tagged'
- * bit in the DSA header is set. If the 'tagged' bit is clear,
- * delete the DSA header entirely.
+ /* If the 'tagged' bit is set; convert the DSA tag to a 802.1Q
+ * tag, and delete the ethertype (extra) if applicable. If the
+ * 'tagged' bit is cleared; delete the DSA tag, and ethertype
+ * if applicable.
*/
if (dsa_header[0] & 0x20) {
u8 new_header[4];
- /*
- * Insert 802.1q ethertype and copy the VLAN-related
+ /* Insert 802.1Q ethertype and copy the VLAN-related
* fields, but clear the bit that will hold CFI (since
* DSA uses that bit location for another purpose).
*/
@@ -109,16 +237,13 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
new_header[2] = dsa_header[2] & ~0x10;
new_header[3] = dsa_header[3];
- /*
- * Move CFI bit from its place in the DSA header to
- * its 802.1q-designated place.
+ /* Move CFI bit from its place in the DSA header to
+ * its 802.1Q-designated place.
*/
if (dsa_header[1] & 0x01)
new_header[2] |= 0x10;
- /*
- * Update packet checksum if skb is CHECKSUM_COMPLETE.
- */
+ /* Update packet checksum if skb is CHECKSUM_COMPLETE. */
if (skb->ip_summed == CHECKSUM_COMPLETE) {
__wsum c = skb->csum;
c = csum_add(c, csum_partial(new_header + 2, 2, 0));
@@ -127,30 +252,101 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
}
memcpy(dsa_header, new_header, DSA_HLEN);
+
+ if (extra)
+ memmove(skb->data - ETH_HLEN,
+ skb->data - ETH_HLEN - extra,
+ 2 * ETH_ALEN);
} else {
- /*
- * Remove DSA tag and update checksum.
- */
skb_pull_rcsum(skb, DSA_HLEN);
memmove(skb->data - ETH_HLEN,
- skb->data - ETH_HLEN - DSA_HLEN,
+ skb->data - ETH_HLEN - DSA_HLEN - extra,
2 * ETH_ALEN);
}
- skb->offload_fwd_mark = 1;
-
return skb;
}
+#if IS_ENABLED(CONFIG_NET_DSA_TAG_DSA)
+
+static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ return dsa_xmit_ll(skb, dev, 0);
+}
+
+static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt)
+{
+ if (unlikely(!pskb_may_pull(skb, DSA_HLEN)))
+ return NULL;
+
+ return dsa_rcv_ll(skb, dev, 0);
+}
+
static const struct dsa_device_ops dsa_netdev_ops = {
- .name = "dsa",
- .proto = DSA_TAG_PROTO_DSA,
- .xmit = dsa_xmit,
- .rcv = dsa_rcv,
+ .name = "dsa",
+ .proto = DSA_TAG_PROTO_DSA,
+ .xmit = dsa_xmit,
+ .rcv = dsa_rcv,
.overhead = DSA_HLEN,
};
-MODULE_LICENSE("GPL");
+DSA_TAG_DRIVER(dsa_netdev_ops);
MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_DSA);
+#endif /* CONFIG_NET_DSA_TAG_DSA */
+
+#if IS_ENABLED(CONFIG_NET_DSA_TAG_EDSA)
+
+#define EDSA_HLEN 8
+
+static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ u8 *edsa_header;
-module_dsa_tag_driver(dsa_netdev_ops);
+ skb = dsa_xmit_ll(skb, dev, EDSA_HLEN - DSA_HLEN);
+ if (!skb)
+ return NULL;
+
+ edsa_header = skb->data + 2 * ETH_ALEN;
+ edsa_header[0] = (ETH_P_EDSA >> 8) & 0xff;
+ edsa_header[1] = ETH_P_EDSA & 0xff;
+ edsa_header[2] = 0x00;
+ edsa_header[3] = 0x00;
+ return skb;
+}
+
+static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt)
+{
+ if (unlikely(!pskb_may_pull(skb, EDSA_HLEN)))
+ return NULL;
+
+ skb_pull_rcsum(skb, EDSA_HLEN - DSA_HLEN);
+
+ return dsa_rcv_ll(skb, dev, EDSA_HLEN - DSA_HLEN);
+}
+
+static const struct dsa_device_ops edsa_netdev_ops = {
+ .name = "edsa",
+ .proto = DSA_TAG_PROTO_EDSA,
+ .xmit = edsa_xmit,
+ .rcv = edsa_rcv,
+ .overhead = EDSA_HLEN,
+};
+
+DSA_TAG_DRIVER(edsa_netdev_ops);
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_EDSA);
+#endif /* CONFIG_NET_DSA_TAG_EDSA */
+
+static struct dsa_tag_driver *dsa_tag_drivers[] = {
+#if IS_ENABLED(CONFIG_NET_DSA_TAG_DSA)
+ &DSA_TAG_DRIVER_NAME(dsa_netdev_ops),
+#endif
+#if IS_ENABLED(CONFIG_NET_DSA_TAG_EDSA)
+ &DSA_TAG_DRIVER_NAME(edsa_netdev_ops),
+#endif
+};
+
+module_dsa_tag_drivers(dsa_tag_drivers);
+
+MODULE_LICENSE("GPL");
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
deleted file mode 100644
index 120614240319..000000000000
--- a/net/dsa/tag_edsa.c
+++ /dev/null
@@ -1,206 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * net/dsa/tag_edsa.c - Ethertype DSA tagging
- * Copyright (c) 2008-2009 Marvell Semiconductor
- */
-
-#include <linux/etherdevice.h>
-#include <linux/list.h>
-#include <linux/slab.h>
-
-#include "dsa_priv.h"
-
-#define DSA_HLEN 4
-#define EDSA_HLEN 8
-
-#define FRAME_TYPE_TO_CPU 0x00
-#define FRAME_TYPE_FORWARD 0x03
-
-#define TO_CPU_CODE_MGMT_TRAP 0x00
-#define TO_CPU_CODE_FRAME2REG 0x01
-#define TO_CPU_CODE_IGMP_MLD_TRAP 0x02
-#define TO_CPU_CODE_POLICY_TRAP 0x03
-#define TO_CPU_CODE_ARP_MIRROR 0x04
-#define TO_CPU_CODE_POLICY_MIRROR 0x05
-
-static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev)
-{
- struct dsa_port *dp = dsa_slave_to_port(dev);
- u8 *edsa_header;
-
- /*
- * Convert the outermost 802.1q tag to a DSA tag and prepend
- * a DSA ethertype field is the packet is tagged, or insert
- * a DSA ethertype plus DSA tag between the addresses and the
- * current ethertype field if the packet is untagged.
- */
- if (skb->protocol == htons(ETH_P_8021Q)) {
- if (skb_cow_head(skb, DSA_HLEN) < 0)
- return NULL;
- skb_push(skb, DSA_HLEN);
-
- memmove(skb->data, skb->data + DSA_HLEN, 2 * ETH_ALEN);
-
- /*
- * Construct tagged FROM_CPU DSA tag from 802.1q tag.
- */
- edsa_header = skb->data + 2 * ETH_ALEN;
- edsa_header[0] = (ETH_P_EDSA >> 8) & 0xff;
- edsa_header[1] = ETH_P_EDSA & 0xff;
- edsa_header[2] = 0x00;
- edsa_header[3] = 0x00;
- edsa_header[4] = 0x60 | dp->ds->index;
- edsa_header[5] = dp->index << 3;
-
- /*
- * Move CFI field from byte 6 to byte 5.
- */
- if (edsa_header[6] & 0x10) {
- edsa_header[5] |= 0x01;
- edsa_header[6] &= ~0x10;
- }
- } else {
- if (skb_cow_head(skb, EDSA_HLEN) < 0)
- return NULL;
- skb_push(skb, EDSA_HLEN);
-
- memmove(skb->data, skb->data + EDSA_HLEN, 2 * ETH_ALEN);
-
- /*
- * Construct untagged FROM_CPU DSA tag.
- */
- edsa_header = skb->data + 2 * ETH_ALEN;
- edsa_header[0] = (ETH_P_EDSA >> 8) & 0xff;
- edsa_header[1] = ETH_P_EDSA & 0xff;
- edsa_header[2] = 0x00;
- edsa_header[3] = 0x00;
- edsa_header[4] = 0x40 | dp->ds->index;
- edsa_header[5] = dp->index << 3;
- edsa_header[6] = 0x00;
- edsa_header[7] = 0x00;
- }
-
- return skb;
-}
-
-static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
- struct packet_type *pt)
-{
- u8 *edsa_header;
- int frame_type;
- int code;
- int source_device;
- int source_port;
-
- if (unlikely(!pskb_may_pull(skb, EDSA_HLEN)))
- return NULL;
-
- /*
- * Skip the two null bytes after the ethertype.
- */
- edsa_header = skb->data + 2;
-
- /*
- * Check that frame type is either TO_CPU or FORWARD.
- */
- frame_type = edsa_header[0] >> 6;
-
- switch (frame_type) {
- case FRAME_TYPE_TO_CPU:
- code = (edsa_header[1] & 0x6) | ((edsa_header[2] >> 4) & 1);
-
- /*
- * Mark the frame to never egress on any port of the same switch
- * unless it's a trapped IGMP/MLD packet, in which case the
- * bridge might want to forward it.
- */
- if (code != TO_CPU_CODE_IGMP_MLD_TRAP)
- skb->offload_fwd_mark = 1;
-
- break;
-
- case FRAME_TYPE_FORWARD:
- skb->offload_fwd_mark = 1;
- break;
-
- default:
- return NULL;
- }
-
- /*
- * Determine source device and port.
- */
- source_device = edsa_header[0] & 0x1f;
- source_port = (edsa_header[1] >> 3) & 0x1f;
-
- skb->dev = dsa_master_find_slave(dev, source_device, source_port);
- if (!skb->dev)
- return NULL;
-
- /*
- * If the 'tagged' bit is set, convert the DSA tag to a 802.1q
- * tag and delete the ethertype part. If the 'tagged' bit is
- * clear, delete the ethertype and the DSA tag parts.
- */
- if (edsa_header[0] & 0x20) {
- u8 new_header[4];
-
- /*
- * Insert 802.1q ethertype and copy the VLAN-related
- * fields, but clear the bit that will hold CFI (since
- * DSA uses that bit location for another purpose).
- */
- new_header[0] = (ETH_P_8021Q >> 8) & 0xff;
- new_header[1] = ETH_P_8021Q & 0xff;
- new_header[2] = edsa_header[2] & ~0x10;
- new_header[3] = edsa_header[3];
-
- /*
- * Move CFI bit from its place in the DSA header to
- * its 802.1q-designated place.
- */
- if (edsa_header[1] & 0x01)
- new_header[2] |= 0x10;
-
- skb_pull_rcsum(skb, DSA_HLEN);
-
- /*
- * Update packet checksum if skb is CHECKSUM_COMPLETE.
- */
- if (skb->ip_summed == CHECKSUM_COMPLETE) {
- __wsum c = skb->csum;
- c = csum_add(c, csum_partial(new_header + 2, 2, 0));
- c = csum_sub(c, csum_partial(edsa_header + 2, 2, 0));
- skb->csum = c;
- }
-
- memcpy(edsa_header, new_header, DSA_HLEN);
-
- memmove(skb->data - ETH_HLEN,
- skb->data - ETH_HLEN - DSA_HLEN,
- 2 * ETH_ALEN);
- } else {
- /*
- * Remove DSA tag and update checksum.
- */
- skb_pull_rcsum(skb, EDSA_HLEN);
- memmove(skb->data - ETH_HLEN,
- skb->data - ETH_HLEN - EDSA_HLEN,
- 2 * ETH_ALEN);
- }
-
- return skb;
-}
-
-static const struct dsa_device_ops edsa_netdev_ops = {
- .name = "edsa",
- .proto = DSA_TAG_PROTO_EDSA,
- .xmit = edsa_xmit,
- .rcv = edsa_rcv,
- .overhead = EDSA_HLEN,
-};
-
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_EDSA);
-
-module_dsa_tag_driver(edsa_netdev_ops);
diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c
index 408d4af390a0..2f5bd5e338ab 100644
--- a/net/dsa/tag_gswip.c
+++ b/net/dsa/tag_gswip.c
@@ -60,13 +60,8 @@ static struct sk_buff *gswip_tag_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
- int err;
u8 *gswip_tag;
- err = skb_cow_head(skb, GSWIP_TX_HEADER_LEN);
- if (err)
- return NULL;
-
skb_push(skb, GSWIP_TX_HEADER_LEN);
gswip_tag = skb->data;
diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c
new file mode 100644
index 000000000000..2061de06eafb
--- /dev/null
+++ b/net/dsa/tag_hellcreek.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * net/dsa/tag_hellcreek.c - Hirschmann Hellcreek switch tag format handling
+ *
+ * Copyright (C) 2019,2020 Linutronix GmbH
+ * Author Kurt Kanzenbach <kurt@linutronix.de>
+ *
+ * Based on tag_ksz.c.
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <net/dsa.h>
+
+#include "dsa_priv.h"
+
+#define HELLCREEK_TAG_LEN 1
+
+static struct sk_buff *hellcreek_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ u8 *tag;
+
+ /* Tag encoding */
+ tag = skb_put(skb, HELLCREEK_TAG_LEN);
+ *tag = BIT(dp->index);
+
+ return skb;
+}
+
+static struct sk_buff *hellcreek_rcv(struct sk_buff *skb,
+ struct net_device *dev,
+ struct packet_type *pt)
+{
+ /* Tag decoding */
+ u8 *tag = skb_tail_pointer(skb) - HELLCREEK_TAG_LEN;
+ unsigned int port = tag[0] & 0x03;
+
+ skb->dev = dsa_master_find_slave(dev, 0, port);
+ if (!skb->dev) {
+ netdev_warn(dev, "Failed to get source port: %d\n", port);
+ return NULL;
+ }
+
+ pskb_trim_rcsum(skb, skb->len - HELLCREEK_TAG_LEN);
+
+ skb->offload_fwd_mark = true;
+
+ return skb;
+}
+
+static const struct dsa_device_ops hellcreek_netdev_ops = {
+ .name = "hellcreek",
+ .proto = DSA_TAG_PROTO_HELLCREEK,
+ .xmit = hellcreek_xmit,
+ .rcv = hellcreek_rcv,
+ .overhead = HELLCREEK_TAG_LEN,
+ .tail_tag = true,
+};
+
+MODULE_LICENSE("Dual MIT/GPL");
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_HELLCREEK);
+
+module_dsa_tag_driver(hellcreek_netdev_ops);
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 0a5aa982c60d..4820dbcedfa2 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -14,46 +14,6 @@
#define KSZ_EGRESS_TAG_LEN 1
#define KSZ_INGRESS_TAG_LEN 1
-static struct sk_buff *ksz_common_xmit(struct sk_buff *skb,
- struct net_device *dev, int len)
-{
- struct sk_buff *nskb;
- int padlen;
-
- padlen = (skb->len >= ETH_ZLEN) ? 0 : ETH_ZLEN - skb->len;
-
- if (skb_tailroom(skb) >= padlen + len) {
- /* Let dsa_slave_xmit() free skb */
- if (__skb_put_padto(skb, skb->len + padlen, false))
- return NULL;
-
- nskb = skb;
- } else {
- nskb = alloc_skb(NET_IP_ALIGN + skb->len +
- padlen + len, GFP_ATOMIC);
- if (!nskb)
- return NULL;
- skb_reserve(nskb, NET_IP_ALIGN);
-
- skb_reset_mac_header(nskb);
- skb_set_network_header(nskb,
- skb_network_header(skb) - skb->head);
- skb_set_transport_header(nskb,
- skb_transport_header(skb) - skb->head);
- skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len));
-
- /* Let skb_put_padto() free nskb, and let dsa_slave_xmit() free
- * skb
- */
- if (skb_put_padto(nskb, nskb->len + padlen))
- return NULL;
-
- consume_skb(skb);
- }
-
- return nskb;
-}
-
static struct sk_buff *ksz_common_rcv(struct sk_buff *skb,
struct net_device *dev,
unsigned int port, unsigned int len)
@@ -90,23 +50,18 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb,
static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
- struct sk_buff *nskb;
u8 *tag;
u8 *addr;
- nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN);
- if (!nskb)
- return NULL;
-
/* Tag encoding */
- tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN);
- addr = skb_mac_header(nskb);
+ tag = skb_put(skb, KSZ_INGRESS_TAG_LEN);
+ addr = skb_mac_header(skb);
*tag = 1 << dp->index;
if (is_link_local_ether_addr(addr))
*tag |= KSZ8795_TAIL_TAG_OVERRIDE;
- return nskb;
+ return skb;
}
static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev,
@@ -156,18 +111,13 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
- struct sk_buff *nskb;
__be16 *tag;
u8 *addr;
u16 val;
- nskb = ksz_common_xmit(skb, dev, KSZ9477_INGRESS_TAG_LEN);
- if (!nskb)
- return NULL;
-
/* Tag encoding */
- tag = skb_put(nskb, KSZ9477_INGRESS_TAG_LEN);
- addr = skb_mac_header(nskb);
+ tag = skb_put(skb, KSZ9477_INGRESS_TAG_LEN);
+ addr = skb_mac_header(skb);
val = BIT(dp->index);
@@ -176,7 +126,7 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb,
*tag = cpu_to_be16(val);
- return nskb;
+ return skb;
}
static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev,
@@ -213,24 +163,19 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
- struct sk_buff *nskb;
u8 *addr;
u8 *tag;
- nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN);
- if (!nskb)
- return NULL;
-
/* Tag encoding */
- tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN);
- addr = skb_mac_header(nskb);
+ tag = skb_put(skb, KSZ_INGRESS_TAG_LEN);
+ addr = skb_mac_header(skb);
*tag = BIT(dp->index);
if (is_link_local_ether_addr(addr))
*tag |= KSZ9893_TAIL_TAG_OVERRIDE;
- return nskb;
+ return skb;
}
static const struct dsa_device_ops ksz9893_netdev_ops = {
diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c
index ccfb6f641bbf..aa1318dccaf0 100644
--- a/net/dsa/tag_lan9303.c
+++ b/net/dsa/tag_lan9303.c
@@ -58,15 +58,6 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev)
__be16 *lan9303_tag;
u16 tag;
- /* insert a special VLAN tag between the MAC addresses
- * and the current ethertype field.
- */
- if (skb_cow_head(skb, LAN9303_TAG_LEN) < 0) {
- dev_dbg(&dev->dev,
- "Cannot make room for the special tag. Dropping packet\n");
- return NULL;
- }
-
/* provide 'LAN9303_TAG_LEN' bytes additional space */
skb_push(skb, LAN9303_TAG_LEN);
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index 4cdd9cf428fb..38dcdded74c0 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -34,9 +34,6 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
* table with VID.
*/
if (!skb_vlan_tagged(skb)) {
- if (skb_cow_head(skb, MTK_HDR_LEN) < 0)
- return NULL;
-
skb_push(skb, MTK_HDR_LEN);
memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN);
is_vlan_skb = false;
diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c
index 3b468aca5c53..16a1afd5b8e1 100644
--- a/net/dsa/tag_ocelot.c
+++ b/net/dsa/tag_ocelot.c
@@ -143,13 +143,6 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb,
struct ocelot_port *ocelot_port;
u8 *prefix, *injection;
u64 qos_class, rew_op;
- int err;
-
- err = skb_cow_head(skb, OCELOT_TOTAL_TAG_LEN);
- if (unlikely(err < 0)) {
- netdev_err(netdev, "Cannot make room for tag.\n");
- return NULL;
- }
ocelot_port = ocelot->ports[dp->index];
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index 1b9e8507112b..88181b52f480 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -34,9 +34,6 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
__be16 *phdr;
u16 hdr;
- if (skb_cow_head(skb, QCA_HDR_LEN) < 0)
- return NULL;
-
skb_push(skb, QCA_HDR_LEN);
memmove(skb->data, skb->data + QCA_HDR_LEN, 2 * ETH_ALEN);
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 3a1cc24a4f0a..5b97ede56a0f 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -13,42 +13,15 @@
static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
- struct sk_buff *nskb;
- int padlen;
u8 *trailer;
- /*
- * We have to make sure that the trailer ends up as the very
- * last 4 bytes of the packet. This means that we have to pad
- * the packet to the minimum ethernet frame size, if necessary,
- * before adding the trailer.
- */
- padlen = 0;
- if (skb->len < 60)
- padlen = 60 - skb->len;
-
- nskb = alloc_skb(NET_IP_ALIGN + skb->len + padlen + 4, GFP_ATOMIC);
- if (!nskb)
- return NULL;
- skb_reserve(nskb, NET_IP_ALIGN);
-
- skb_reset_mac_header(nskb);
- skb_set_network_header(nskb, skb_network_header(skb) - skb->head);
- skb_set_transport_header(nskb, skb_transport_header(skb) - skb->head);
- skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len));
- consume_skb(skb);
-
- if (padlen) {
- skb_put_zero(nskb, padlen);
- }
-
- trailer = skb_put(nskb, 4);
+ trailer = skb_put(skb, 4);
trailer[0] = 0x80;
trailer[1] = 1 << dp->index;
trailer[2] = 0x10;
trailer[3] = 0x00;
- return nskb;
+ return skb;
}
static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev,
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index dac65180c4ef..4106373180c6 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -272,7 +272,7 @@ void eth_header_cache_update(struct hh_cache *hh,
EXPORT_SYMBOL(eth_header_cache_update);
/**
- * eth_header_parser_protocol - extract protocol from L2 header
+ * eth_header_parse_protocol - extract protocol from L2 header
* @skb: packet to extract protocol from
*/
__be16 eth_header_parse_protocol(const struct sk_buff *skb)
@@ -523,8 +523,8 @@ int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr)
EXPORT_SYMBOL(eth_platform_get_mac_address);
/**
- * Obtain the MAC address from an nvmem cell named 'mac-address' associated
- * with given device.
+ * nvmem_get_mac_address - Obtain the MAC address from an nvmem cell named
+ * 'mac-address' associated with given device.
*
* @dev: Device with which the mac-address cell is associated.
* @addrbuf: Buffer to which the MAC address will be copied on success.
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index ec2cd7aab5ad..771688e1b0da 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -2433,7 +2433,7 @@ static int noinline_for_stack ethtool_set_per_queue(struct net_device *dev,
return ethtool_set_per_queue_coalesce(dev, useraddr, &per_queue_opt);
default:
return -EOPNOTSUPP;
- };
+ }
}
static int ethtool_phy_tunable_valid(const struct ethtool_tunable *tuna)
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index 6d091e419d3e..9c640d670ffe 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -149,7 +149,7 @@ static struct net_device *ieee802154_nl_get_dev(struct genl_info *info)
if (info->attrs[IEEE802154_ATTR_DEV_NAME]) {
char name[IFNAMSIZ + 1];
- nla_strlcpy(name, info->attrs[IEEE802154_ATTR_DEV_NAME],
+ nla_strscpy(name, info->attrs[IEEE802154_ATTR_DEV_NAME],
sizeof(name));
dev = dev_get_by_name(&init_net, name);
} else if (info->attrs[IEEE802154_ATTR_DEV_INDEX]) {
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 123a6d39438f..75f67994fc85 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -650,8 +650,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
struct in_device *in_dev;
struct ifaddrmsg *ifm;
struct in_ifaddr *ifa;
-
- int err = -EINVAL;
+ int err;
ASSERT_RTNL();
@@ -881,7 +880,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
ifa->ifa_broadcast = nla_get_in_addr(tb[IFA_BROADCAST]);
if (tb[IFA_LABEL])
- nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
+ nla_strscpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
else
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 1f75dc686b6b..b5400cec4f69 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -973,7 +973,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
char tmp[TCP_CA_NAME_MAX];
bool ecn_ca = false;
- nla_strlcpy(tmp, nla, sizeof(tmp));
+ nla_strscpy(tmp, nla, sizeof(tmp));
val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
} else {
if (nla_len(nla) != sizeof(u32))
@@ -1641,9 +1641,8 @@ int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc,
break;
}
- *flags |= (nhc->nhc_flags & RTNH_F_ONLINK);
- if (nhc->nhc_flags & RTNH_F_OFFLOAD)
- *flags |= RTNH_F_OFFLOAD;
+ *flags |= (nhc->nhc_flags &
+ (RTNH_F_ONLINK | RTNH_F_OFFLOAD | RTNH_F_TRAP));
if (!skip_oif && nhc->nhc_dev &&
nla_put_u32(skb, RTA_OIF, nhc->nhc_dev->ifindex))
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index ffc5332f1390..28117c05dc35 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2100,15 +2100,6 @@ static void __fib_info_notify_update(struct net *net, struct fib_table *tb,
rtmsg_fib(RTM_NEWROUTE, htonl(n->key), fa,
KEYLENGTH - fa->fa_slen, tb->tb_id,
info, NLM_F_REPLACE);
-
- /* call_fib_entry_notifiers will be removed when
- * in-kernel notifier is implemented and supported
- * for nexthop objects
- */
- call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE,
- n->key,
- KEYLENGTH - fa->fa_slen, fa,
- NULL);
}
}
}
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index e70291748889..a68bf4c6fe9b 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -920,7 +920,7 @@ static const struct net_device_ops ipgre_netdev_ops = {
.ndo_start_xmit = ipgre_xmit,
.ndo_do_ioctl = ip_tunnel_ioctl,
.ndo_change_mtu = ip_tunnel_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
.ndo_tunnel_ctl = ipgre_tunnel_ctl,
};
@@ -1275,7 +1275,7 @@ static const struct net_device_ops gre_tap_netdev_ops = {
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = ip_tunnel_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
.ndo_fill_metadata_dst = gre_fill_metadata_dst,
};
@@ -1308,7 +1308,7 @@ static const struct net_device_ops erspan_netdev_ops = {
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = ip_tunnel_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
.ndo_fill_metadata_dst = gre_fill_metadata_dst,
};
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index e25be2d01a7a..7ca338fbe8ba 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -429,15 +429,6 @@ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
}
EXPORT_SYMBOL(skb_tunnel_check_pmtu);
-/* Often modified stats are per cpu, other are shared (netdev->stats) */
-void ip_tunnel_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *tot)
-{
- netdev_stats_to_stats64(tot, &dev->stats);
- dev_fetch_sw_netstats(tot, dev->tstats);
-}
-EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
-
static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = {
[LWTUNNEL_IP_UNSPEC] = { .strict_start_type = LWTUNNEL_IP_OPTS },
[LWTUNNEL_IP_ID] = { .type = NLA_U64 },
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index b957cbee2cf7..abc171e79d3e 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -404,7 +404,7 @@ static const struct net_device_ops vti_netdev_ops = {
.ndo_start_xmit = vti_tunnel_xmit,
.ndo_do_ioctl = ip_tunnel_ioctl,
.ndo_change_mtu = ip_tunnel_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
.ndo_tunnel_ctl = vti_tunnel_ctl,
};
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 561f15b5a944..3cd13e1bc6a7 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1441,7 +1441,7 @@ static int __init ip_auto_config(void)
int retries = CONF_OPEN_RETRIES;
#endif
int err;
- unsigned int i;
+ unsigned int i, count;
/* Initialise all name servers and NTP servers to NONE (but only if the
* "ip=" or "nfsaddrs=" kernel command line parameters weren't decoded,
@@ -1575,7 +1575,7 @@ static int __init ip_auto_config(void)
if (ic_dev_mtu)
pr_cont(", mtu=%d", ic_dev_mtu);
/* Name servers (if any): */
- for (i = 0; i < CONF_NAMESERVERS_MAX; i++) {
+ for (i = 0, count = 0; i < CONF_NAMESERVERS_MAX; i++) {
if (ic_nameservers[i] != NONE) {
if (i == 0)
pr_info(" nameserver%u=%pI4",
@@ -1583,12 +1583,14 @@ static int __init ip_auto_config(void)
else
pr_cont(", nameserver%u=%pI4",
i, &ic_nameservers[i]);
+
+ count++;
}
- if (i + 1 == CONF_NAMESERVERS_MAX)
+ if ((i + 1 == CONF_NAMESERVERS_MAX) && count > 0)
pr_cont("\n");
}
/* NTP servers (if any): */
- for (i = 0; i < CONF_NTP_SERVERS_MAX; i++) {
+ for (i = 0, count = 0; i < CONF_NTP_SERVERS_MAX; i++) {
if (ic_ntp_servers[i] != NONE) {
if (i == 0)
pr_info(" ntpserver%u=%pI4",
@@ -1596,8 +1598,10 @@ static int __init ip_auto_config(void)
else
pr_cont(", ntpserver%u=%pI4",
i, &ic_ntp_servers[i]);
+
+ count++;
}
- if (i + 1 == CONF_NTP_SERVERS_MAX)
+ if ((i + 1 == CONF_NTP_SERVERS_MAX) && count > 0)
pr_cont("\n");
}
#endif /* !SILENT */
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 75d35e76bec2..d5bfa087c23a 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -347,7 +347,7 @@ static const struct net_device_ops ipip_netdev_ops = {
.ndo_start_xmit = ipip_tunnel_xmit,
.ndo_do_ioctl = ip_tunnel_ioctl,
.ndo_change_mtu = ip_tunnel_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
.ndo_tunnel_ctl = ipip_tunnel_ctl,
};
diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c
index 3205d5f7c8c9..25ea6ac44db9 100644
--- a/net/ipv4/metrics.c
+++ b/net/ipv4/metrics.c
@@ -31,7 +31,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
if (type == RTAX_CC_ALGO) {
char tmp[TCP_CA_NAME_MAX];
- nla_strlcpy(tmp, nla, sizeof(tmp));
+ nla_strscpy(tmp, nla, sizeof(tmp));
val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca);
if (val == TCP_CA_UNSPEC) {
NL_SET_ERR_MSG(extack, "Unknown tcp congestion algorithm");
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 93b07739807b..4109055cdea6 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -12,6 +12,128 @@
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_bridge.h>
+static int nf_reject_iphdr_validate(struct sk_buff *skb)
+{
+ struct iphdr *iph;
+ u32 len;
+
+ if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+ return 0;
+
+ iph = ip_hdr(skb);
+ if (iph->ihl < 5 || iph->version != 4)
+ return 0;
+
+ len = ntohs(iph->tot_len);
+ if (skb->len < len)
+ return 0;
+ else if (len < (iph->ihl*4))
+ return 0;
+
+ if (!pskb_may_pull(skb, iph->ihl*4))
+ return 0;
+
+ return 1;
+}
+
+struct sk_buff *nf_reject_skb_v4_tcp_reset(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook)
+{
+ const struct tcphdr *oth;
+ struct sk_buff *nskb;
+ struct iphdr *niph;
+ struct tcphdr _oth;
+
+ if (!nf_reject_iphdr_validate(oldskb))
+ return NULL;
+
+ oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook);
+ if (!oth)
+ return NULL;
+
+ nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
+ LL_MAX_HEADER, GFP_ATOMIC);
+ if (!nskb)
+ return NULL;
+
+ nskb->dev = (struct net_device *)dev;
+
+ skb_reserve(nskb, LL_MAX_HEADER);
+ niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
+ net->ipv4.sysctl_ip_default_ttl);
+ nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
+ niph->tot_len = htons(nskb->len);
+ ip_send_check(niph);
+
+ return nskb;
+}
+EXPORT_SYMBOL_GPL(nf_reject_skb_v4_tcp_reset);
+
+struct sk_buff *nf_reject_skb_v4_unreach(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook, u8 code)
+{
+ struct sk_buff *nskb;
+ struct iphdr *niph;
+ struct icmphdr *icmph;
+ unsigned int len;
+ __wsum csum;
+ u8 proto;
+
+ if (!nf_reject_iphdr_validate(oldskb))
+ return NULL;
+
+ /* IP header checks: fragment. */
+ if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
+ return NULL;
+
+ /* RFC says return as much as we can without exceeding 576 bytes. */
+ len = min_t(unsigned int, 536, oldskb->len);
+
+ if (!pskb_may_pull(oldskb, len))
+ return NULL;
+
+ if (pskb_trim_rcsum(oldskb, ntohs(ip_hdr(oldskb)->tot_len)))
+ return NULL;
+
+ proto = ip_hdr(oldskb)->protocol;
+
+ if (!skb_csum_unnecessary(oldskb) &&
+ nf_reject_verify_csum(proto) &&
+ nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), proto))
+ return NULL;
+
+ nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmphdr) +
+ LL_MAX_HEADER + len, GFP_ATOMIC);
+ if (!nskb)
+ return NULL;
+
+ nskb->dev = (struct net_device *)dev;
+
+ skb_reserve(nskb, LL_MAX_HEADER);
+ niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP,
+ net->ipv4.sysctl_ip_default_ttl);
+
+ skb_reset_transport_header(nskb);
+ icmph = skb_put_zero(nskb, sizeof(struct icmphdr));
+ icmph->type = ICMP_DEST_UNREACH;
+ icmph->code = code;
+
+ skb_put_data(nskb, skb_network_header(oldskb), len);
+
+ csum = csum_partial((void *)icmph, len + sizeof(struct icmphdr), 0);
+ icmph->checksum = csum_fold(csum);
+
+ niph->tot_len = htons(nskb->len);
+ ip_send_check(niph);
+
+ return nskb;
+}
+EXPORT_SYMBOL_GPL(nf_reject_skb_v4_unreach);
+
const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb,
struct tcphdr *_oth, int hook)
{
@@ -124,7 +246,8 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
if (!oth)
return;
- if (hook == NF_INET_PRE_ROUTING && nf_reject_fill_skb_dst(oldskb))
+ if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) &&
+ nf_reject_fill_skb_dst(oldskb) < 0)
return;
if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
@@ -193,7 +316,8 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook)
if (iph->frag_off & htons(IP_OFFSET))
return;
- if (hook == NF_INET_PRE_ROUTING && nf_reject_fill_skb_dst(skb_in))
+ if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) &&
+ nf_reject_fill_skb_dst(skb_in) < 0)
return;
if (skb_csum_unnecessary(skb_in) || !nf_reject_verify_csum(proto)) {
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 0dc43ad28eb9..5e1b22d4f939 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -36,14 +36,145 @@ static const struct nla_policy rtm_nh_policy[NHA_MAX + 1] = {
[NHA_FDB] = { .type = NLA_FLAG },
};
+static bool nexthop_notifiers_is_empty(struct net *net)
+{
+ return !net->nexthop.notifier_chain.head;
+}
+
+static void
+__nh_notifier_single_info_init(struct nh_notifier_single_info *nh_info,
+ const struct nexthop *nh)
+{
+ struct nh_info *nhi = rtnl_dereference(nh->nh_info);
+
+ nh_info->dev = nhi->fib_nhc.nhc_dev;
+ nh_info->gw_family = nhi->fib_nhc.nhc_gw_family;
+ if (nh_info->gw_family == AF_INET)
+ nh_info->ipv4 = nhi->fib_nhc.nhc_gw.ipv4;
+ else if (nh_info->gw_family == AF_INET6)
+ nh_info->ipv6 = nhi->fib_nhc.nhc_gw.ipv6;
+
+ nh_info->is_reject = nhi->reject_nh;
+ nh_info->is_fdb = nhi->fdb_nh;
+ nh_info->has_encap = !!nhi->fib_nhc.nhc_lwtstate;
+}
+
+static int nh_notifier_single_info_init(struct nh_notifier_info *info,
+ const struct nexthop *nh)
+{
+ info->nh = kzalloc(sizeof(*info->nh), GFP_KERNEL);
+ if (!info->nh)
+ return -ENOMEM;
+
+ __nh_notifier_single_info_init(info->nh, nh);
+
+ return 0;
+}
+
+static void nh_notifier_single_info_fini(struct nh_notifier_info *info)
+{
+ kfree(info->nh);
+}
+
+static int nh_notifier_grp_info_init(struct nh_notifier_info *info,
+ const struct nexthop *nh)
+{
+ struct nh_group *nhg = rtnl_dereference(nh->nh_grp);
+ u16 num_nh = nhg->num_nh;
+ int i;
+
+ info->nh_grp = kzalloc(struct_size(info->nh_grp, nh_entries, num_nh),
+ GFP_KERNEL);
+ if (!info->nh_grp)
+ return -ENOMEM;
+
+ info->nh_grp->num_nh = num_nh;
+ info->nh_grp->is_fdb = nhg->fdb_nh;
+
+ for (i = 0; i < num_nh; i++) {
+ struct nh_grp_entry *nhge = &nhg->nh_entries[i];
+
+ info->nh_grp->nh_entries[i].id = nhge->nh->id;
+ info->nh_grp->nh_entries[i].weight = nhge->weight;
+ __nh_notifier_single_info_init(&info->nh_grp->nh_entries[i].nh,
+ nhge->nh);
+ }
+
+ return 0;
+}
+
+static void nh_notifier_grp_info_fini(struct nh_notifier_info *info)
+{
+ kfree(info->nh_grp);
+}
+
+static int nh_notifier_info_init(struct nh_notifier_info *info,
+ const struct nexthop *nh)
+{
+ info->id = nh->id;
+ info->is_grp = nh->is_group;
+
+ if (info->is_grp)
+ return nh_notifier_grp_info_init(info, nh);
+ else
+ return nh_notifier_single_info_init(info, nh);
+}
+
+static void nh_notifier_info_fini(struct nh_notifier_info *info)
+{
+ if (info->is_grp)
+ nh_notifier_grp_info_fini(info);
+ else
+ nh_notifier_single_info_fini(info);
+}
+
static int call_nexthop_notifiers(struct net *net,
enum nexthop_event_type event_type,
- struct nexthop *nh)
+ struct nexthop *nh,
+ struct netlink_ext_ack *extack)
{
+ struct nh_notifier_info info = {
+ .net = net,
+ .extack = extack,
+ };
int err;
+ ASSERT_RTNL();
+
+ if (nexthop_notifiers_is_empty(net))
+ return 0;
+
+ err = nh_notifier_info_init(&info, nh);
+ if (err) {
+ NL_SET_ERR_MSG(extack, "Failed to initialize nexthop notifier info");
+ return err;
+ }
+
err = blocking_notifier_call_chain(&net->nexthop.notifier_chain,
- event_type, nh);
+ event_type, &info);
+ nh_notifier_info_fini(&info);
+
+ return notifier_to_errno(err);
+}
+
+static int call_nexthop_notifier(struct notifier_block *nb, struct net *net,
+ enum nexthop_event_type event_type,
+ struct nexthop *nh,
+ struct netlink_ext_ack *extack)
+{
+ struct nh_notifier_info info = {
+ .net = net,
+ .extack = extack,
+ };
+ int err;
+
+ err = nh_notifier_info_init(&info, nh);
+ if (err)
+ return err;
+
+ err = nb->notifier_call(nb, event_type, &info);
+ nh_notifier_info_fini(&info);
+
return notifier_to_errno(err);
}
@@ -782,9 +913,10 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
{
struct nh_grp_entry *nhges, *new_nhges;
struct nexthop *nhp = nhge->nh_parent;
+ struct netlink_ext_ack extack;
struct nexthop *nh = nhge->nh;
struct nh_group *nhg, *newg;
- int i, j;
+ int i, j, err;
WARN_ON(!nh);
@@ -832,6 +964,10 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
list_del(&nhge->nh_list);
nexthop_put(nhge->nh);
+ err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, &extack);
+ if (err)
+ pr_err("%s\n", extack._msg);
+
if (nlinfo)
nexthop_notify(RTM_NEWNEXTHOP, nhp, nlinfo);
}
@@ -907,7 +1043,7 @@ static void __remove_nexthop(struct net *net, struct nexthop *nh,
static void remove_nexthop(struct net *net, struct nexthop *nh,
struct nl_info *nlinfo)
{
- call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh);
+ call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh, NULL);
/* remove from the tree */
rb_erase(&nh->rb_node, &net->nexthop.rb_root);
@@ -940,13 +1076,17 @@ static int replace_nexthop_grp(struct net *net, struct nexthop *old,
struct netlink_ext_ack *extack)
{
struct nh_group *oldg, *newg;
- int i;
+ int i, err;
if (!new->is_group) {
NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with a nexthop.");
return -EINVAL;
}
+ err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack);
+ if (err)
+ return err;
+
oldg = rtnl_dereference(old->nh_grp);
newg = rtnl_dereference(new->nh_grp);
@@ -985,31 +1125,54 @@ static int replace_nexthop_single(struct net *net, struct nexthop *old,
struct nexthop *new,
struct netlink_ext_ack *extack)
{
+ u8 old_protocol, old_nh_flags;
struct nh_info *oldi, *newi;
+ struct nh_grp_entry *nhge;
+ int err;
if (new->is_group) {
NL_SET_ERR_MSG(extack, "Can not replace a nexthop with a nexthop group.");
return -EINVAL;
}
+ err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack);
+ if (err)
+ return err;
+
+ /* Hardware flags were set on 'old' as 'new' is not in the red-black
+ * tree. Therefore, inherit the flags from 'old' to 'new'.
+ */
+ new->nh_flags |= old->nh_flags & (RTNH_F_OFFLOAD | RTNH_F_TRAP);
+
oldi = rtnl_dereference(old->nh_info);
newi = rtnl_dereference(new->nh_info);
newi->nh_parent = old;
oldi->nh_parent = new;
+ old_protocol = old->protocol;
+ old_nh_flags = old->nh_flags;
+
old->protocol = new->protocol;
old->nh_flags = new->nh_flags;
rcu_assign_pointer(old->nh_info, newi);
rcu_assign_pointer(new->nh_info, oldi);
+ /* Send a replace notification for all the groups using the nexthop. */
+ list_for_each_entry(nhge, &old->grp_list, nh_list) {
+ struct nexthop *nhp = nhge->nh_parent;
+
+ err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp,
+ extack);
+ if (err)
+ goto err_notify;
+ }
+
/* When replacing an IPv4 nexthop with an IPv6 nexthop, potentially
* update IPv4 indication in all the groups using the nexthop.
*/
if (oldi->family == AF_INET && newi->family == AF_INET6) {
- struct nh_grp_entry *nhge;
-
list_for_each_entry(nhge, &old->grp_list, nh_list) {
struct nexthop *nhp = nhge->nh_parent;
struct nh_group *nhg;
@@ -1020,6 +1183,21 @@ static int replace_nexthop_single(struct net *net, struct nexthop *old,
}
return 0;
+
+err_notify:
+ rcu_assign_pointer(new->nh_info, newi);
+ rcu_assign_pointer(old->nh_info, oldi);
+ old->nh_flags = old_nh_flags;
+ old->protocol = old_protocol;
+ oldi->nh_parent = old;
+ newi->nh_parent = new;
+ list_for_each_entry_continue_reverse(nhge, &old->grp_list, nh_list) {
+ struct nexthop *nhp = nhge->nh_parent;
+
+ call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, extack);
+ }
+ call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, old, extack);
+ return err;
}
static void __nexthop_replace_notify(struct net *net, struct nexthop *nh,
@@ -1168,7 +1346,11 @@ static int insert_nexthop(struct net *net, struct nexthop *new_nh,
rb_link_node_rcu(&new_nh->rb_node, parent, pp);
rb_insert_color(&new_nh->rb_node, root);
- rc = 0;
+
+ rc = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new_nh, extack);
+ if (rc)
+ rb_erase(&new_nh->rb_node, &net->nexthop.rb_root);
+
out:
if (!rc) {
nh_base_seq_inc(net);
@@ -1957,10 +2139,40 @@ static struct notifier_block nh_netdev_notifier = {
.notifier_call = nh_netdev_event,
};
-int register_nexthop_notifier(struct net *net, struct notifier_block *nb)
+static int nexthops_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
+{
+ struct rb_root *root = &net->nexthop.rb_root;
+ struct rb_node *node;
+ int err = 0;
+
+ for (node = rb_first(root); node; node = rb_next(node)) {
+ struct nexthop *nh;
+
+ nh = rb_entry(node, struct nexthop, rb_node);
+ err = call_nexthop_notifier(nb, net, NEXTHOP_EVENT_REPLACE, nh,
+ extack);
+ if (err)
+ break;
+ }
+
+ return err;
+}
+
+int register_nexthop_notifier(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
- return blocking_notifier_chain_register(&net->nexthop.notifier_chain,
- nb);
+ int err;
+
+ rtnl_lock();
+ err = nexthops_dump(net, nb, extack);
+ if (err)
+ goto unlock;
+ err = blocking_notifier_chain_register(&net->nexthop.notifier_chain,
+ nb);
+unlock:
+ rtnl_unlock();
+ return err;
}
EXPORT_SYMBOL(register_nexthop_notifier);
@@ -1971,6 +2183,27 @@ int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb)
}
EXPORT_SYMBOL(unregister_nexthop_notifier);
+void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap)
+{
+ struct nexthop *nexthop;
+
+ rcu_read_lock();
+
+ nexthop = nexthop_find_by_id(net, id);
+ if (!nexthop)
+ goto out;
+
+ nexthop->nh_flags &= ~(RTNH_F_OFFLOAD | RTNH_F_TRAP);
+ if (offload)
+ nexthop->nh_flags |= RTNH_F_OFFLOAD;
+ if (trap)
+ nexthop->nh_flags |= RTNH_F_TRAP;
+
+out:
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL(nexthop_set_hw_flags);
+
static void __net_exit nexthop_net_exit(struct net *net)
{
rtnl_lock();
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 8d5e1695b9aa..63cd370ea29d 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -167,6 +167,7 @@ static const struct snmp_mib snmp4_udp_list[] = {
SNMP_MIB_ITEM("SndbufErrors", UDP_MIB_SNDBUFERRORS),
SNMP_MIB_ITEM("InCsumErrors", UDP_MIB_CSUMERRORS),
SNMP_MIB_ITEM("IgnoredMulti", UDP_MIB_IGNOREDMULTI),
+ SNMP_MIB_ITEM("MemErrors", UDP_MIB_MEMERRORS),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index dc2a399cd9f4..c962f0d96d8d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1741,7 +1741,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
flags |= RTCF_LOCAL;
rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
- IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+ IN_DEV_ORCONF(in_dev, NOPOLICY), false);
if (!rth)
return -ENOBUFS;
@@ -1857,8 +1857,8 @@ static int __mkroute_input(struct sk_buff *skb,
}
rth = rt_dst_alloc(out_dev->dev, 0, res->type,
- IN_DEV_CONF_GET(in_dev, NOPOLICY),
- IN_DEV_CONF_GET(out_dev, NOXFRM));
+ IN_DEV_ORCONF(in_dev, NOPOLICY),
+ IN_DEV_ORCONF(out_dev, NOXFRM));
if (!rth) {
err = -ENOBUFS;
goto cleanup;
@@ -2227,7 +2227,7 @@ local_input:
rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev,
flags | RTCF_LOCAL, res->type,
- IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+ IN_DEV_ORCONF(in_dev, NOPOLICY), false);
if (!rth)
goto e_nobufs;
@@ -2450,8 +2450,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
add:
rth = rt_dst_alloc(dev_out, flags, type,
- IN_DEV_CONF_GET(in_dev, NOPOLICY),
- IN_DEV_CONF_GET(in_dev, NOXFRM));
+ IN_DEV_ORCONF(in_dev, NOPOLICY),
+ IN_DEV_ORCONF(in_dev, NOXFRM));
if (!rth)
return ERR_PTR(-ENOBUFS);
@@ -2872,6 +2872,9 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
if (rt->dst.dev &&
nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
goto nla_put_failure;
+ if (rt->dst.lwtstate &&
+ lwtunnel_fill_encap(skb, rt->dst.lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
+ goto nla_put_failure;
#ifdef CONFIG_IP_ROUTE_CLASSID
if (rt->dst.tclassid &&
nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid))
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b2bc3d7fe9e8..b285b338a019 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -954,7 +954,7 @@ int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
* importantly be able to generate EPOLLOUT for Edge Trigger epoll()
* users.
*/
-static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
+void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
{
if (skb && !skb->len) {
tcp_unlink_write_queue(skb, sk);
@@ -964,6 +964,68 @@ static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
}
}
+struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags,
+ struct page *page, int offset, size_t *size)
+{
+ struct sk_buff *skb = tcp_write_queue_tail(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+ bool can_coalesce;
+ int copy, i;
+
+ if (!skb || (copy = size_goal - skb->len) <= 0 ||
+ !tcp_skb_can_collapse_to(skb)) {
+new_segment:
+ if (!sk_stream_memory_free(sk))
+ return NULL;
+
+ skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
+ tcp_rtx_and_write_queues_empty(sk));
+ if (!skb)
+ return NULL;
+
+#ifdef CONFIG_TLS_DEVICE
+ skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
+#endif
+ skb_entail(sk, skb);
+ copy = size_goal;
+ }
+
+ if (copy > *size)
+ copy = *size;
+
+ i = skb_shinfo(skb)->nr_frags;
+ can_coalesce = skb_can_coalesce(skb, i, page, offset);
+ if (!can_coalesce && i >= sysctl_max_skb_frags) {
+ tcp_mark_push(tp, skb);
+ goto new_segment;
+ }
+ if (!sk_wmem_schedule(sk, copy))
+ return NULL;
+
+ if (can_coalesce) {
+ skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+ } else {
+ get_page(page);
+ skb_fill_page_desc(skb, i, page, offset, copy);
+ }
+
+ if (!(flags & MSG_NO_SHARED_FRAGS))
+ skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
+
+ skb->len += copy;
+ skb->data_len += copy;
+ skb->truesize += copy;
+ sk_wmem_queued_add(sk, copy);
+ sk_mem_charge(sk, copy);
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
+ TCP_SKB_CB(skb)->end_seq += copy;
+ tcp_skb_pcount_set(skb, 0);
+
+ *size = copy;
+ return skb;
+}
+
ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
size_t size, int flags)
{
@@ -999,60 +1061,13 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
goto out_err;
while (size > 0) {
- struct sk_buff *skb = tcp_write_queue_tail(sk);
- int copy, i;
- bool can_coalesce;
+ struct sk_buff *skb;
+ size_t copy = size;
- if (!skb || (copy = size_goal - skb->len) <= 0 ||
- !tcp_skb_can_collapse_to(skb)) {
-new_segment:
- if (!sk_stream_memory_free(sk))
- goto wait_for_space;
-
- skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
- tcp_rtx_and_write_queues_empty(sk));
- if (!skb)
- goto wait_for_space;
-
-#ifdef CONFIG_TLS_DEVICE
- skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
-#endif
- skb_entail(sk, skb);
- copy = size_goal;
- }
-
- if (copy > size)
- copy = size;
-
- i = skb_shinfo(skb)->nr_frags;
- can_coalesce = skb_can_coalesce(skb, i, page, offset);
- if (!can_coalesce && i >= sysctl_max_skb_frags) {
- tcp_mark_push(tp, skb);
- goto new_segment;
- }
- if (!sk_wmem_schedule(sk, copy))
+ skb = tcp_build_frag(sk, size_goal, flags, page, offset, &copy);
+ if (!skb)
goto wait_for_space;
- if (can_coalesce) {
- skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
- } else {
- get_page(page);
- skb_fill_page_desc(skb, i, page, offset, copy);
- }
-
- if (!(flags & MSG_NO_SHARED_FRAGS))
- skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
-
- skb->len += copy;
- skb->data_len += copy;
- skb->truesize += copy;
- sk_wmem_queued_add(sk, copy);
- sk_mem_charge(sk, copy);
- skb->ip_summed = CHECKSUM_PARTIAL;
- WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
- TCP_SKB_CB(skb)->end_seq += copy;
- tcp_skb_pcount_set(skb, 0);
-
if (!copied)
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
@@ -2405,13 +2420,12 @@ bool tcp_check_oom(struct sock *sk, int shift)
return too_many_orphans || out_of_socket_memory;
}
-void tcp_close(struct sock *sk, long timeout)
+void __tcp_close(struct sock *sk, long timeout)
{
struct sk_buff *skb;
int data_was_unread = 0;
int state;
- lock_sock(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
if (sk->sk_state == TCP_LISTEN) {
@@ -2575,6 +2589,12 @@ adjudge_to_death:
out:
bh_unlock_sock(sk);
local_bh_enable();
+}
+
+void tcp_close(struct sock *sk, long timeout)
+{
+ lock_sock(sk);
+ __tcp_close(sk, timeout);
release_sock(sk);
sock_put(sk);
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 389d1b340248..fb3a7750f623 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2546,7 +2546,7 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
* 1) If the packets in flight is larger than ssthresh, PRR spreads the
* cwnd reductions across a full RTT.
* 2) Otherwise PRR uses packet conservation to send as much as delivered.
- * But when the retransmits are acked without further losses, PRR
+ * But when SND_UNA is acked without further losses,
* slow starts cwnd up to ssthresh to speed up the recovery.
*/
static void tcp_init_cwnd_reduction(struct sock *sk)
@@ -2563,7 +2563,7 @@ static void tcp_init_cwnd_reduction(struct sock *sk)
tcp_ecn_queue_cwr(tp);
}
-void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag)
+void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
int sndcnt = 0;
@@ -2577,8 +2577,7 @@ void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag)
u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered +
tp->prior_cwnd - 1;
sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out;
- } else if ((flag & (FLAG_RETRANS_DATA_ACKED | FLAG_LOST_RETRANS)) ==
- FLAG_RETRANS_DATA_ACKED) {
+ } else if (flag & FLAG_SND_UNA_ADVANCED && !newly_lost) {
sndcnt = min_t(int, delta,
max_t(int, tp->prr_delivered - tp->prr_out,
newly_acked_sacked) + 1);
@@ -3419,7 +3418,7 @@ static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked,
if (tcp_in_cwnd_reduction(sk)) {
/* Reduce cwnd if state mandates */
- tcp_cwnd_reduction(sk, acked_sacked, flag);
+ tcp_cwnd_reduction(sk, acked_sacked, rs->losses, flag);
} else if (tcp_may_raise_cwnd(sk, flag)) {
/* Advance cwnd if state allows */
tcp_cong_avoid(sk, ack, acked_sacked);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7352c097ae48..c2d5132c523c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2740,6 +2740,20 @@ void tcp4_proc_exit(void)
}
#endif /* CONFIG_PROC_FS */
+/* @wake is one when sk_stream_write_space() calls us.
+ * This sends EPOLLOUT only if notsent_bytes is half the limit.
+ * This mimics the strategy used in sock_def_write_space().
+ */
+bool tcp_stream_memory_free(const struct sock *sk, int wake)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ u32 notsent_bytes = READ_ONCE(tp->write_seq) -
+ READ_ONCE(tp->snd_nxt);
+
+ return (notsent_bytes << wake) < tcp_notsent_lowat(tp);
+}
+EXPORT_SYMBOL(tcp_stream_memory_free);
+
struct proto tcp_prot = {
.name = "TCP",
.owner = THIS_MODULE,
diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c
index 8c643a4ffad1..e6459537d4d2 100644
--- a/net/ipv4/tcp_lp.c
+++ b/net/ipv4/tcp_lp.c
@@ -89,6 +89,7 @@ struct lp {
/**
* tcp_lp_init
+ * @sk: socket to initialize congestion control algorithm for
*
* Init all required variables.
* Clone the handling from Vegas module implementation.
@@ -111,6 +112,7 @@ static void tcp_lp_init(struct sock *sk)
/**
* tcp_lp_cong_avoid
+ * @sk: socket to avoid congesting
*
* Implementation of cong_avoid.
* Will only call newReno CA when away from inference.
@@ -126,6 +128,7 @@ static void tcp_lp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
/**
* tcp_lp_remote_hz_estimator
+ * @sk: socket which needs an estimate for the remote HZs
*
* Estimate remote HZ.
* We keep on updating the estimated value, where original TCP-LP
@@ -176,6 +179,7 @@ static u32 tcp_lp_remote_hz_estimator(struct sock *sk)
/**
* tcp_lp_owd_calculator
+ * @sk: socket to calculate one way delay for
*
* Calculate one way delay (in relative format).
* Original implement OWD as minus of remote time difference to local time
@@ -210,6 +214,8 @@ static u32 tcp_lp_owd_calculator(struct sock *sk)
/**
* tcp_lp_rtt_sample
+ * @sk: socket to add a rtt sample to
+ * @rtt: round trip time, which is ignored!
*
* Implementation or rtt_sample.
* Will take the following action,
@@ -254,6 +260,7 @@ static void tcp_lp_rtt_sample(struct sock *sk, u32 rtt)
/**
* tcp_lp_pkts_acked
+ * @sk: socket requiring congestion avoidance calculations
*
* Implementation of pkts_acked.
* Deal with active drop under Early Congestion Indication.
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bf48cd73e967..99905bc01d40 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1038,9 +1038,9 @@ static void tcp_tsq_handler(struct sock *sk)
* transferring tsq->head because tcp_wfree() might
* interrupt us (non NAPI drivers)
*/
-static void tcp_tasklet_func(unsigned long data)
+static void tcp_tasklet_func(struct tasklet_struct *t)
{
- struct tsq_tasklet *tsq = (struct tsq_tasklet *)data;
+ struct tsq_tasklet *tsq = from_tasklet(tsq, t, tasklet);
LIST_HEAD(list);
unsigned long flags;
struct list_head *q, *n;
@@ -1125,9 +1125,7 @@ void __init tcp_tasklet_init(void)
struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i);
INIT_LIST_HEAD(&tsq->head);
- tasklet_init(&tsq->tasklet,
- tcp_tasklet_func,
- (unsigned long)tsq);
+ tasklet_setup(&tsq->tasklet, tcp_tasklet_func);
}
}
@@ -1569,6 +1567,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
if (!buff)
return -ENOMEM; /* We'll just try again later. */
skb_copy_decrypted(buff, skb);
+ mptcp_skb_ext_copy(buff, skb);
sk_wmem_queued_add(sk, buff->truesize);
sk_mem_charge(sk, buff->truesize);
@@ -2123,6 +2122,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
if (unlikely(!buff))
return -ENOMEM;
skb_copy_decrypted(buff, skb);
+ mptcp_skb_ext_copy(buff, skb);
sk_wmem_queued_add(sk, buff->truesize);
sk_mem_charge(sk, buff->truesize);
@@ -2393,6 +2393,7 @@ static int tcp_mtu_probe(struct sock *sk)
skb = tcp_send_head(sk);
skb_copy_decrypted(nskb, skb);
+ mptcp_skb_ext_copy(nskb, skb);
TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index f65a3ddd0d58..177307a3081f 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -153,6 +153,7 @@ void tcp_rack_reo_timeout(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 timeout, prior_inflight;
+ u32 lost = tp->lost;
prior_inflight = tcp_packets_in_flight(tp);
tcp_rack_detect_loss(sk, &timeout);
@@ -160,7 +161,7 @@ void tcp_rack_reo_timeout(struct sock *sk)
if (inet_csk(sk)->icsk_ca_state != TCP_CA_Recovery) {
tcp_enter_recovery(sk, false);
if (!inet_csk(sk)->icsk_ca_ops->cong_control)
- tcp_cwnd_reduction(sk, 1, 0);
+ tcp_cwnd_reduction(sk, 1, tp->lost - lost, 0);
}
tcp_xmit_retransmit_queue(sk);
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 09f0a23d1a01..a3f105227ccc 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -541,7 +541,7 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
inet_sdif(skb), udptable, skb);
}
-struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
+struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport)
{
const struct iphdr *iph = ip_hdr(skb);
@@ -550,7 +550,6 @@ struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
iph->daddr, dport, inet_iif(skb),
inet_sdif(skb), &udp_table, NULL);
}
-EXPORT_SYMBOL_GPL(udp4_lib_lookup_skb);
/* Must be called under rcu_read_lock().
* Does increment socket refcount.
@@ -702,7 +701,7 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,
iph->saddr, uh->source, skb->dev->ifindex,
inet_sdif(skb), udptable, NULL);
- if (!sk) {
+ if (!sk || udp_sk(sk)->encap_type) {
/* No socket for error: try tunnels before discarding */
sk = ERR_PTR(-ENOENT);
if (static_branch_unlikely(&udp_encap_needed_key)) {
@@ -874,7 +873,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
struct sock *sk = skb->sk;
struct inet_sock *inet = inet_sk(sk);
struct udphdr *uh;
- int err = 0;
+ int err;
int is_udplite = IS_UDPLITE(sk);
int offset = skb_transport_offset(skb);
int len = skb->len - offset;
@@ -2038,6 +2037,9 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
if (rc == -ENOMEM)
UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS,
is_udplite);
+ else
+ UDP_INC_STATS(sock_net(sk), UDP_MIB_MEMERRORS,
+ is_udplite);
UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
kfree_skb(skb);
trace_udp_fail_queue_rcv_skb(rc, sk);
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 1dbece34496e..b2cee9a307d4 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -30,7 +30,7 @@ static int udp_dump_one(struct udp_table *tbl,
const struct inet_diag_req_v2 *req)
{
struct sk_buff *in_skb = cb->skb;
- int err = -EINVAL;
+ int err;
struct sock *sk = NULL;
struct sk_buff *rep;
struct net *net = sock_net(in_skb->sk);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index c62805cd3131..ff39e94781bf 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -49,6 +49,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
__skb_pull(skb, tnl_hlen);
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb_inner_network_offset(skb));
+ skb_set_transport_header(skb, skb_inner_transport_offset(skb));
skb->mac_len = skb_inner_network_offset(skb);
skb->protocol = new_protocol;
@@ -67,6 +68,8 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
(NETIF_F_HW_CSUM | NETIF_F_IP_CSUM))));
features &= skb->dev->hw_enc_features;
+ /* CRC checksum can't be handled by HW when it's a UDP tunneling packet. */
+ features &= ~NETIF_F_SCTP_CRC;
/* The only checksum offload we care about from here on out is the
* outer one so strip the existing checksum feature flags and
@@ -564,8 +567,8 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff,
{
__be16 newlen = htons(skb->len - nhoff);
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
- int err = -ENOSYS;
struct sock *sk;
+ int err;
uh->len = newlen;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 8b6eb384bac7..eff2cacd5209 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1997,6 +1997,7 @@ EXPORT_SYMBOL(ipv6_chk_prefix);
* ipv6_dev_find - find the first device with a given source address.
* @net: the net namespace
* @addr: the source address
+ * @dev: used to find the L3 domain of interest
*
* The caller should be protected by RCU, or RTNL.
*/
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 78f766019b7e..51184a70ac7e 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -423,7 +423,7 @@ static void calipso_doi_free_rcu(struct rcu_head *entry)
/**
* calipso_doi_remove - Remove an existing DOI from the CALIPSO protocol engine
* @doi: the DOI value
- * @audit_secid: the LSM secid to use in the audit message
+ * @audit_info: NetLabel audit information
*
* Description:
* Removes a DOI definition from the CALIPSO engine. The NetLabel routines will
@@ -1226,7 +1226,7 @@ static int calipso_req_setattr(struct request_sock *req,
/**
* calipso_req_delattr - Delete the CALIPSO option from a request socket
- * @reg: the request socket
+ * @req: the request socket
*
* Description:
* Removes the CALIPSO option from a request socket, if present.
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 374105e4394f..6126f8bf94b3 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -906,11 +906,6 @@ void ipv6_exthdrs_exit(void)
/*
* Note: we cannot rely on skb_dst(skb) before we assign it in ip6_route_input().
*/
-static inline struct inet6_dev *ipv6_skb_idev(struct sk_buff *skb)
-{
- return skb_dst(skb) ? ip6_dst_idev(skb_dst(skb)) : __in6_dev_get(skb->dev);
-}
-
static inline struct net *ipv6_skb_net(struct sk_buff *skb)
{
return skb_dst(skb) ? dev_net(skb_dst(skb)->dev) : dev_net(skb->dev);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 931b186d2e48..8cf659994412 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1391,7 +1391,7 @@ static const struct net_device_ops ip6gre_netdev_ops = {
.ndo_start_xmit = ip6gre_tunnel_xmit,
.ndo_do_ioctl = ip6gre_tunnel_ioctl,
.ndo_change_mtu = ip6_tnl_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip6_tnl_get_iflink,
};
@@ -1828,7 +1828,7 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = {
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = ip6_tnl_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip6_tnl_get_iflink,
};
@@ -1896,7 +1896,7 @@ static const struct net_device_ops ip6erspan_netdev_ops = {
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = ip6_tnl_change_mtu,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip6_tnl_get_iflink,
};
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 648db3fe508f..a7950baa05e5 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -94,36 +94,6 @@ static inline int ip6_tnl_mpls_supported(void)
return IS_ENABLED(CONFIG_MPLS);
}
-static struct net_device_stats *ip6_get_stats(struct net_device *dev)
-{
- struct pcpu_sw_netstats tmp, sum = { 0 };
- int i;
-
- for_each_possible_cpu(i) {
- unsigned int start;
- const struct pcpu_sw_netstats *tstats =
- per_cpu_ptr(dev->tstats, i);
-
- do {
- start = u64_stats_fetch_begin_irq(&tstats->syncp);
- tmp.rx_packets = tstats->rx_packets;
- tmp.rx_bytes = tstats->rx_bytes;
- tmp.tx_packets = tstats->tx_packets;
- tmp.tx_bytes = tstats->tx_bytes;
- } while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
-
- sum.rx_packets += tmp.rx_packets;
- sum.rx_bytes += tmp.rx_bytes;
- sum.tx_packets += tmp.tx_packets;
- sum.tx_bytes += tmp.tx_bytes;
- }
- dev->stats.rx_packets = sum.rx_packets;
- dev->stats.rx_bytes = sum.rx_bytes;
- dev->stats.tx_packets = sum.tx_packets;
- dev->stats.tx_bytes = sum.tx_bytes;
- return &dev->stats;
-}
-
#define for_each_ip6_tunnel_rcu(start) \
for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
@@ -204,6 +174,7 @@ ip6_tnl_lookup(struct net *net, int link,
/**
* ip6_tnl_bucket - get head of list matching given tunnel parameters
+ * @ip6n: the private data for ip6_vti in the netns
* @p: parameters containing tunnel end-points
*
* Description:
@@ -230,6 +201,7 @@ ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct __ip6_tnl_parm *p)
/**
* ip6_tnl_link - add tunnel to hash table
+ * @ip6n: the private data for ip6_vti in the netns
* @t: tunnel to be added
**/
@@ -246,6 +218,7 @@ ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
/**
* ip6_tnl_unlink - remove tunnel from hash table
+ * @ip6n: the private data for ip6_vti in the netns
* @t: tunnel to be removed
**/
@@ -417,6 +390,7 @@ ip6_tnl_dev_uninit(struct net_device *dev)
/**
* parse_tvl_tnl_enc_lim - handle encapsulation limit option
* @skb: received socket buffer
+ * @raw: the ICMPv6 error message data
*
* Return:
* 0 if none was found,
@@ -485,14 +459,9 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
}
EXPORT_SYMBOL(ip6_tnl_parse_tlv_enc_lim);
-/**
- * ip6_tnl_err - tunnel error handler
- *
- * Description:
- * ip6_tnl_err() should handle errors in the tunnel according
- * to the specifications in RFC 2473.
- **/
-
+/* ip6_tnl_err() should handle errors in the tunnel according to the
+ * specifications in RFC 2473.
+ */
static int
ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
u8 *type, u8 *code, int *msg, __u32 *info, int offset)
@@ -1835,7 +1804,7 @@ static const struct net_device_ops ip6_tnl_netdev_ops = {
.ndo_start_xmit = ip6_tnl_start_xmit,
.ndo_do_ioctl = ip6_tnl_ioctl,
.ndo_change_mtu = ip6_tnl_change_mtu,
- .ndo_get_stats = ip6_get_stats,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip6_tnl_get_iflink,
};
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 5f9c4fdc120d..0225fd694192 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -125,6 +125,7 @@ vti6_tnl_lookup(struct net *net, const struct in6_addr *remote,
/**
* vti6_tnl_bucket - get head of list matching given tunnel parameters
+ * @ip6n: the private data for ip6_vti in the netns
* @p: parameters containing tunnel end-points
*
* Description:
@@ -889,7 +890,7 @@ static const struct net_device_ops vti6_netdev_ops = {
.ndo_uninit = vti6_dev_uninit,
.ndo_start_xmit = vti6_tnl_xmit,
.ndo_do_ioctl = vti6_ioctl,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip6_tnl_get_iflink,
};
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 8cd2782a31e4..6c8604390266 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -548,7 +548,7 @@ done:
}
int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
- struct sockaddr_storage *p)
+ struct sockaddr_storage __user *p)
{
int err, i, count, copycount;
const struct in6_addr *group;
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 4aef6baaa55e..aa35e6e37c1f 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -12,6 +12,140 @@
#include <linux/netfilter_ipv6.h>
#include <linux/netfilter_bridge.h>
+static bool nf_reject_v6_csum_ok(struct sk_buff *skb, int hook)
+{
+ const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+ int thoff;
+ __be16 fo;
+ u8 proto = ip6h->nexthdr;
+
+ if (skb_csum_unnecessary(skb))
+ return true;
+
+ if (ip6h->payload_len &&
+ pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h)))
+ return false;
+
+ ip6h = ipv6_hdr(skb);
+ thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo);
+ if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0)
+ return false;
+
+ if (!nf_reject_verify_csum(proto))
+ return true;
+
+ return nf_ip6_checksum(skb, hook, thoff, proto) == 0;
+}
+
+static int nf_reject_ip6hdr_validate(struct sk_buff *skb)
+{
+ struct ipv6hdr *hdr;
+ u32 pkt_len;
+
+ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+ return 0;
+
+ hdr = ipv6_hdr(skb);
+ if (hdr->version != 6)
+ return 0;
+
+ pkt_len = ntohs(hdr->payload_len);
+ if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
+ return 0;
+
+ return 1;
+}
+
+struct sk_buff *nf_reject_skb_v6_tcp_reset(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook)
+{
+ struct sk_buff *nskb;
+ const struct tcphdr *oth;
+ struct tcphdr _oth;
+ unsigned int otcplen;
+ struct ipv6hdr *nip6h;
+
+ if (!nf_reject_ip6hdr_validate(oldskb))
+ return NULL;
+
+ oth = nf_reject_ip6_tcphdr_get(oldskb, &_oth, &otcplen, hook);
+ if (!oth)
+ return NULL;
+
+ nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct tcphdr) +
+ LL_MAX_HEADER, GFP_ATOMIC);
+ if (!nskb)
+ return NULL;
+
+ nskb->dev = (struct net_device *)dev;
+
+ skb_reserve(nskb, LL_MAX_HEADER);
+ nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP,
+ net->ipv6.devconf_all->hop_limit);
+ nf_reject_ip6_tcphdr_put(nskb, oldskb, oth, otcplen);
+ nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr));
+
+ return nskb;
+}
+EXPORT_SYMBOL_GPL(nf_reject_skb_v6_tcp_reset);
+
+struct sk_buff *nf_reject_skb_v6_unreach(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook, u8 code)
+{
+ struct sk_buff *nskb;
+ struct ipv6hdr *nip6h;
+ struct icmp6hdr *icmp6h;
+ unsigned int len;
+
+ if (!nf_reject_ip6hdr_validate(oldskb))
+ return NULL;
+
+ /* Include "As much of invoking packet as possible without the ICMPv6
+ * packet exceeding the minimum IPv6 MTU" in the ICMP payload.
+ */
+ len = min_t(unsigned int, 1220, oldskb->len);
+
+ if (!pskb_may_pull(oldskb, len))
+ return NULL;
+
+ if (!nf_reject_v6_csum_ok(oldskb, hook))
+ return NULL;
+
+ nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) +
+ LL_MAX_HEADER + len, GFP_ATOMIC);
+ if (!nskb)
+ return NULL;
+
+ nskb->dev = (struct net_device *)dev;
+
+ skb_reserve(nskb, LL_MAX_HEADER);
+ nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_ICMPV6,
+ net->ipv6.devconf_all->hop_limit);
+
+ skb_reset_transport_header(nskb);
+ icmp6h = skb_put_zero(nskb, sizeof(struct icmp6hdr));
+ icmp6h->icmp6_type = ICMPV6_DEST_UNREACH;
+ icmp6h->icmp6_code = code;
+
+ skb_put_data(nskb, skb_network_header(oldskb), len);
+ nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr));
+
+ icmp6h->icmp6_cksum =
+ csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr,
+ nskb->len - sizeof(struct ipv6hdr),
+ IPPROTO_ICMPV6,
+ csum_partial(icmp6h,
+ nskb->len - sizeof(struct ipv6hdr),
+ 0));
+
+ return nskb;
+}
+EXPORT_SYMBOL_GPL(nf_reject_skb_v6_unreach);
+
const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb,
struct tcphdr *otcph,
unsigned int *otcplen, int hook)
@@ -170,7 +304,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
fl6.fl6_sport = otcph->dest;
fl6.fl6_dport = otcph->source;
- if (hook == NF_INET_PRE_ROUTING) {
+ if (hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) {
nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false);
if (!dst)
return;
@@ -268,7 +402,8 @@ void nf_send_unreach6(struct net *net, struct sk_buff *skb_in,
if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL)
skb_in->dev = net->loopback_dev;
- if (hooknum == NF_INET_PRE_ROUTING && nf_reject6_fill_skb_dst(skb_in))
+ if ((hooknum == NF_INET_PRE_ROUTING || hooknum == NF_INET_INGRESS) &&
+ nf_reject6_fill_skb_dst(skb_in) < 0)
return;
icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0);
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index bbff3e02e302..d6306aa46bb1 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -126,6 +126,7 @@ static const struct snmp_mib snmp6_udp6_list[] = {
SNMP_MIB_ITEM("Udp6SndbufErrors", UDP_MIB_SNDBUFERRORS),
SNMP_MIB_ITEM("Udp6InCsumErrors", UDP_MIB_CSUMERRORS),
SNMP_MIB_ITEM("Udp6IgnoredMulti", UDP_MIB_IGNOREDMULTI),
+ SNMP_MIB_ITEM("Udp6MemErrors", UDP_MIB_MEMERRORS),
SNMP_MIB_SENTINEL
};
@@ -137,6 +138,7 @@ static const struct snmp_mib snmp6_udplite6_list[] = {
SNMP_MIB_ITEM("UdpLite6RcvbufErrors", UDP_MIB_RCVBUFERRORS),
SNMP_MIB_ITEM("UdpLite6SndbufErrors", UDP_MIB_SNDBUFERRORS),
SNMP_MIB_ITEM("UdpLite6InCsumErrors", UDP_MIB_CSUMERRORS),
+ SNMP_MIB_ITEM("UdpLite6MemErrors", UDP_MIB_MEMERRORS),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7e0ce7af8234..f91a689edafd 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -6039,11 +6039,6 @@ void fib6_rt_update(struct net *net, struct fib6_info *rt,
struct sk_buff *skb;
int err = -ENOBUFS;
- /* call_fib6_entry_notifiers will be removed when in-kernel notifier
- * is implemented and supported for nexthop objects
- */
- call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, rt, NULL);
-
skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any());
if (!skb)
goto errout;
diff --git a/net/ipv6/rpl.c b/net/ipv6/rpl.c
index 307f336b5353..488aec9e1a74 100644
--- a/net/ipv6/rpl.c
+++ b/net/ipv6/rpl.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* Authors:
* (C) 2020 Alexander Aring <alex.aring@gmail.com>
*/
diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index 5fdf3ebb953f..233da43dd8d7 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* Authors:
* (C) 2020 Alexander Aring <alex.aring@gmail.com>
*/
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 5e7983cb6154..2da0ee703779 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1395,7 +1395,7 @@ static const struct net_device_ops ipip6_netdev_ops = {
.ndo_uninit = ipip6_tunnel_uninit,
.ndo_start_xmit = sit_tunnel_xmit,
.ndo_do_ioctl = ipip6_tunnel_ioctl,
- .ndo_get_stats64 = ip_tunnel_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
.ndo_tunnel_ctl = ipip6_tunnel_ctl,
};
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 29d9691359b9..9008f5796ad4 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -276,7 +276,7 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
inet6_sdif(skb), udptable, skb);
}
-struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
+struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
@@ -285,7 +285,6 @@ struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
&iph->daddr, dport, inet6_iif(skb),
inet6_sdif(skb), &udp_table, NULL);
}
-EXPORT_SYMBOL_GPL(udp6_lib_lookup_skb);
/* Must be called under rcu_read_lock().
* Does increment socket refcount.
@@ -560,7 +559,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
inet6_iif(skb), inet6_sdif(skb), udptable, NULL);
- if (!sk) {
+ if (!sk || udp_sk(sk)->encap_type) {
/* No socket for error: try tunnels before discarding */
sk = ERR_PTR(-ENOENT);
if (static_branch_unlikely(&udpv6_encap_needed_key)) {
@@ -637,6 +636,9 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
if (rc == -ENOMEM)
UDP6_INC_STATS(sock_net(sk),
UDP_MIB_RCVBUFERRORS, is_udplite);
+ else
+ UDP6_INC_STATS(sock_net(sk),
+ UDP_MIB_MEMERRORS, is_udplite);
UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
kfree_skb(skb);
return -1;
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index f9e888d1b9af..c7bd7b1a04c1 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -28,10 +28,6 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
int tnl_hlen;
int err;
- mss = skb_shinfo(skb)->gso_size;
- if (unlikely(skb->len <= mss))
- goto out;
-
if (skb->encapsulation && skb_shinfo(skb)->gso_type &
(SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))
segs = skb_udp_tunnel_segment(skb, features, true);
@@ -48,6 +44,10 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
return __udp_gso_segment(skb, features);
+ mss = skb_shinfo(skb)->gso_size;
+ if (unlikely(skb->len <= mss))
+ goto out;
+
/* Do software UFO. Complete and fill in the UDP checksum as HW cannot
* do checksum of UDP packets sent as multiple IP fragments.
*/
diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c
index 864326f150e2..ad7730b68772 100644
--- a/net/l3mdev/l3mdev.c
+++ b/net/l3mdev/l3mdev.c
@@ -241,6 +241,7 @@ EXPORT_SYMBOL_GPL(l3mdev_link_scope_lookup);
* L3 master device
* @net: network namespace for device index lookup
* @fl: flow struct
+ * @arg: store the table the rule matched with here
*/
int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 1144cda2a0fc..912aa9bd5e29 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -909,6 +909,8 @@ static void llc_sk_init(struct sock *sk)
* @net: network namespace
* @family: upper layer protocol family
* @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
+ * @prot: struct proto associated with this new sock instance
+ * @kern: is this to be a kernel socket?
*
* Allocates a LLC sock and initializes it. Returns the new LLC sock
* or %NULL if there's no memory available for one
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 7276e66ae435..454432ced0c9 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2708,16 +2708,6 @@ static int ieee80211_get_tx_power(struct wiphy *wiphy,
return 0;
}
-static int ieee80211_set_wds_peer(struct wiphy *wiphy, struct net_device *dev,
- const u8 *addr)
-{
- struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-
- memcpy(&sdata->u.wds.remote_addr, addr, ETH_ALEN);
-
- return 0;
-}
-
static void ieee80211_rfkill_poll(struct wiphy *wiphy)
{
struct ieee80211_local *local = wiphy_priv(wiphy);
@@ -4138,7 +4128,6 @@ const struct cfg80211_ops mac80211_config_ops = {
.set_wiphy_params = ieee80211_set_wiphy_params,
.set_tx_power = ieee80211_set_tx_power,
.get_tx_power = ieee80211_get_tx_power,
- .set_wds_peer = ieee80211_set_wds_peer,
.rfkill_poll = ieee80211_rfkill_poll,
CFG80211_TESTMODE_CMD(ieee80211_testmode_cmd)
CFG80211_TESTMODE_DUMP(ieee80211_testmode_dump)
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 8f48aff74c7b..b6c80a45b9f5 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -275,11 +275,11 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local,
case NL80211_IFTYPE_NAN:
continue;
case NL80211_IFTYPE_ADHOC:
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_MESH_POINT:
case NL80211_IFTYPE_OCB:
width = vif->bss_conf.chandef.width;
break;
+ case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_UNSPECIFIED:
case NUM_NL80211_IFTYPES:
case NL80211_IFTYPE_MONITOR:
@@ -743,7 +743,6 @@ void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local,
continue;
case NL80211_IFTYPE_AP:
case NL80211_IFTYPE_ADHOC:
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_MESH_POINT:
case NL80211_IFTYPE_OCB:
break;
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index fe8a7a87e513..9fc8ce214322 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -574,9 +574,6 @@ static ssize_t ieee80211_if_parse_tsf(
IEEE80211_IF_FILE_RW(tsf);
-/* WDS attributes */
-IEEE80211_IF_FILE(peer, u.wds.remote_addr, MAC);
-
#ifdef CONFIG_MAC80211_MESH
IEEE80211_IF_FILE(estab_plinks, u.mesh.estab_plinks, ATOMIC);
@@ -701,11 +698,6 @@ static void add_ibss_files(struct ieee80211_sub_if_data *sdata)
DEBUGFS_ADD_MODE(tsf, 0600);
}
-static void add_wds_files(struct ieee80211_sub_if_data *sdata)
-{
- DEBUGFS_ADD(peer);
-}
-
#ifdef CONFIG_MAC80211_MESH
static void add_mesh_files(struct ieee80211_sub_if_data *sdata)
@@ -805,9 +797,6 @@ static void add_files(struct ieee80211_sub_if_data *sdata)
case NL80211_IFTYPE_AP_VLAN:
add_vlan_files(sdata);
break;
- case NL80211_IFTYPE_WDS:
- add_wds_files(sdata);
- break;
default:
break;
}
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 829dcad69c2c..6a51b8b58f9e 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -274,7 +274,7 @@ static ssize_t sta_aql_read(struct file *file, char __user *userbuf,
"Q limit[low/high]: VO: %u/%u VI: %u/%u BE: %u/%u BK: %u/%u\n",
q_depth[0], q_depth[1], q_depth[2], q_depth[3],
q_limit_l[0], q_limit_h[0], q_limit_l[1], q_limit_h[1],
- q_limit_l[2], q_limit_h[2], q_limit_l[3], q_limit_h[3]),
+ q_limit_l[2], q_limit_h[2], q_limit_l[3], q_limit_h[3]);
rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf);
kfree(buf);
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 2a21226fb518..cde2e3f4fbcd 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -311,11 +311,6 @@ struct ieee80211_if_ap {
bool multicast_to_unicast;
};
-struct ieee80211_if_wds {
- struct sta_info *sta;
- u8 remote_addr[ETH_ALEN];
-};
-
struct ieee80211_if_vlan {
struct list_head list; /* write-protected with RTNL and local->mtx */
@@ -985,7 +980,6 @@ struct ieee80211_sub_if_data {
union {
struct ieee80211_if_ap ap;
- struct ieee80211_if_wds wds;
struct ieee80211_if_vlan vlan;
struct ieee80211_if_managed mgd;
struct ieee80211_if_ibss ibss;
@@ -1795,7 +1789,7 @@ static inline bool ieee80211_sdata_running(struct ieee80211_sub_if_data *sdata)
/* tx handling */
void ieee80211_clear_tx_pending(struct ieee80211_local *local);
-void ieee80211_tx_pending(unsigned long data);
+void ieee80211_tx_pending(struct tasklet_struct *t);
netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
struct net_device *dev);
netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
@@ -2146,7 +2140,7 @@ void ieee80211_txq_remove_vlan(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata);
void ieee80211_fill_txq_stats(struct cfg80211_txq_stats *txqstats,
struct txq_info *txqi);
-void ieee80211_wake_txqs(unsigned long data);
+void ieee80211_wake_txqs(struct tasklet_struct *t);
void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata,
u16 transaction, u16 auth_alg, u16 status,
const u8 *extra, size_t extra_len, const u8 *bssid,
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 1be775979132..f5d4ceb72882 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -230,10 +230,6 @@ static inline int identical_mac_addr_allowed(int type1, int type2)
type2 == NL80211_IFTYPE_MONITOR ||
type1 == NL80211_IFTYPE_P2P_DEVICE ||
type2 == NL80211_IFTYPE_P2P_DEVICE ||
- (type1 == NL80211_IFTYPE_AP && type2 == NL80211_IFTYPE_WDS) ||
- (type1 == NL80211_IFTYPE_WDS &&
- (type2 == NL80211_IFTYPE_WDS ||
- type2 == NL80211_IFTYPE_AP)) ||
(type1 == NL80211_IFTYPE_AP && type2 == NL80211_IFTYPE_AP_VLAN) ||
(type1 == NL80211_IFTYPE_AP_VLAN &&
(type2 == NL80211_IFTYPE_AP ||
@@ -417,15 +413,12 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
* (because if we remove a STA after ops->remove_interface()
* the driver will have removed the vif info already!)
*
- * In WDS mode a station must exist here and be flushed, for
- * AP_VLANs stations may exist since there's nothing else that
+ * For AP_VLANs stations may exist since there's nothing else that
* would have removed them, but in other modes there shouldn't
* be any stations.
*/
flushed = sta_info_flush(sdata);
- WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_AP_VLAN &&
- ((sdata->vif.type != NL80211_IFTYPE_WDS && flushed > 0) ||
- (sdata->vif.type == NL80211_IFTYPE_WDS && flushed != 1)));
+ WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_AP_VLAN && flushed > 0);
/* don't count this interface for allmulti while it is down */
if (sdata->flags & IEEE80211_SDATA_ALLMULTI)
@@ -552,8 +545,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
* When we get here, the interface is marked down.
* Free the remaining keys, if there are any
* (which can happen in AP mode if userspace sets
- * keys before the interface is operating, and maybe
- * also in WDS mode)
+ * keys before the interface is operating)
*
* Force the key freeing to always synchronize_net()
* to wait for the RX path in case it is using this
@@ -1020,16 +1012,11 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
struct net_device *dev = wdev->netdev;
struct ieee80211_local *local = sdata->local;
- struct sta_info *sta;
u32 changed = 0;
int res;
u32 hw_reconf_flags = 0;
switch (sdata->vif.type) {
- case NL80211_IFTYPE_WDS:
- if (!is_valid_ether_addr(sdata->u.wds.remote_addr))
- return -ENOLINK;
- break;
case NL80211_IFTYPE_AP_VLAN: {
struct ieee80211_sub_if_data *master;
@@ -1078,6 +1065,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
case NUM_NL80211_IFTYPES:
case NL80211_IFTYPE_P2P_CLIENT:
case NL80211_IFTYPE_P2P_GO:
+ case NL80211_IFTYPE_WDS:
/* cannot happen */
WARN_ON(1);
break;
@@ -1196,7 +1184,6 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
case NL80211_IFTYPE_OCB:
netif_carrier_off(dev);
break;
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_P2P_DEVICE:
case NL80211_IFTYPE_NAN:
break;
@@ -1218,28 +1205,6 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
set_bit(SDATA_STATE_RUNNING, &sdata->state);
switch (sdata->vif.type) {
- case NL80211_IFTYPE_WDS:
- /* Create STA entry for the WDS peer */
- sta = sta_info_alloc(sdata, sdata->u.wds.remote_addr,
- GFP_KERNEL);
- if (!sta) {
- res = -ENOMEM;
- goto err_del_interface;
- }
-
- sta_info_pre_move_state(sta, IEEE80211_STA_AUTH);
- sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC);
- sta_info_pre_move_state(sta, IEEE80211_STA_AUTHORIZED);
-
- res = sta_info_insert(sta);
- if (res) {
- /* STA has been freed */
- goto err_del_interface;
- }
-
- rate_control_rate_init(sta);
- netif_carrier_on(dev);
- break;
case NL80211_IFTYPE_P2P_DEVICE:
rcu_assign_pointer(local->p2p_sdata, sdata);
break;
@@ -1356,6 +1321,7 @@ static void ieee80211_iface_work(struct work_struct *work)
while ((skb = skb_dequeue(&sdata->skb_queue))) {
struct ieee80211_mgmt *mgmt = (void *)skb->data;
+ kcov_remote_start_common(skb_get_kcov_handle(skb));
if (ieee80211_is_action(mgmt->frame_control) &&
mgmt->u.action.category == WLAN_CATEGORY_BACK) {
int len = skb->len;
@@ -1465,6 +1431,7 @@ static void ieee80211_iface_work(struct work_struct *work)
}
kfree_skb(skb);
+ kcov_remote_stop();
}
/* then other type-dependent work */
@@ -1574,9 +1541,6 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
sdata->u.mntr.flags = MONITOR_FLAG_CONTROL |
MONITOR_FLAG_OTHER_BSS;
break;
- case NL80211_IFTYPE_WDS:
- sdata->vif.bss_conf.bssid = NULL;
- break;
case NL80211_IFTYPE_NAN:
idr_init(&sdata->u.nan.function_inst_ids);
spin_lock_init(&sdata->u.nan.func_lock);
@@ -1587,6 +1551,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
sdata->vif.bss_conf.bssid = sdata->vif.addr;
break;
case NL80211_IFTYPE_UNSPECIFIED:
+ case NL80211_IFTYPE_WDS:
case NUM_NL80211_IFTYPES:
WARN_ON(1);
break;
@@ -1631,9 +1596,7 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata,
case NL80211_IFTYPE_OCB:
/*
* Could probably support everything
- * but WDS here (WDS do_open can fail
- * under memory pressure, which this
- * code isn't prepared to handle).
+ * but here.
*/
break;
case NL80211_IFTYPE_P2P_CLIENT:
@@ -1726,7 +1689,6 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local,
case NL80211_IFTYPE_MONITOR:
/* doesn't matter */
break;
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_AP_VLAN:
/* match up with an AP interface */
list_for_each_entry(sdata, &local->interfaces, list) {
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 523380aed92e..dee88ec566ad 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -220,9 +220,9 @@ u32 ieee80211_reset_erp_info(struct ieee80211_sub_if_data *sdata)
BSS_CHANGED_ERP_SLOT;
}
-static void ieee80211_tasklet_handler(unsigned long data)
+static void ieee80211_tasklet_handler(struct tasklet_struct *t)
{
- struct ieee80211_local *local = (struct ieee80211_local *) data;
+ struct ieee80211_local *local = from_tasklet(local, t, tasklet);
struct sk_buff *skb;
while ((skb = skb_dequeue(&local->skb_queue)) ||
@@ -733,16 +733,12 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
skb_queue_head_init(&local->pending[i]);
atomic_set(&local->agg_queue_stop[i], 0);
}
- tasklet_init(&local->tx_pending_tasklet, ieee80211_tx_pending,
- (unsigned long)local);
+ tasklet_setup(&local->tx_pending_tasklet, ieee80211_tx_pending);
if (ops->wake_tx_queue)
- tasklet_init(&local->wake_txqs_tasklet, ieee80211_wake_txqs,
- (unsigned long)local);
+ tasklet_setup(&local->wake_txqs_tasklet, ieee80211_wake_txqs);
- tasklet_init(&local->tasklet,
- ieee80211_tasklet_handler,
- (unsigned long) local);
+ tasklet_setup(&local->tasklet, ieee80211_tasklet_handler);
skb_queue_head_init(&local->skb_queue);
skb_queue_head_init(&local->skb_queue_unreliable);
@@ -935,14 +931,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
return -EINVAL;
}
} else {
- /*
- * WDS is currently prohibited when channel contexts are used
- * because there's no clear definition of which channel WDS
- * type interfaces use
- */
- if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_WDS))
- return -EINVAL;
-
/* DFS is not supported with multi-channel combinations yet */
for (i = 0; i < local->hw.wiphy->n_iface_combinations; i++) {
const struct ieee80211_iface_combination *comb;
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index ce5825d6f1d1..97095b7c9c64 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -667,6 +667,35 @@ void ieee80211_mesh_root_setup(struct ieee80211_if_mesh *ifmsh)
}
}
+static void
+ieee80211_mesh_update_bss_params(struct ieee80211_sub_if_data *sdata,
+ u8 *ie, u8 ie_len)
+{
+ struct ieee80211_supported_band *sband;
+ const u8 *cap;
+ const struct ieee80211_he_operation *he_oper = NULL;
+
+ sband = ieee80211_get_sband(sdata);
+ if (!sband)
+ return;
+
+ if (!ieee80211_get_he_iftype_cap(sband, NL80211_IFTYPE_MESH_POINT) ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 ||
+ sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10)
+ return;
+
+ sdata->vif.bss_conf.he_support = true;
+
+ cap = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION, ie, ie_len);
+ if (cap && cap[1] >= ieee80211_he_oper_size(&cap[3]))
+ he_oper = (void *)(cap + 3);
+
+ if (he_oper)
+ sdata->vif.bss_conf.he_oper.params =
+ __le32_to_cpu(he_oper->he_oper_params);
+}
+
/**
* ieee80211_fill_mesh_addresses - fill addresses of a locally originated mesh frame
* @hdr: 802.11 frame header
@@ -943,6 +972,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh)
bcn->tail_len = skb->len;
memcpy(bcn->tail, skb->data, bcn->tail_len);
+ ieee80211_mesh_update_bss_params(sdata, bcn->tail, bcn->tail_len);
bcn->meshconf = (struct ieee80211_meshconf_ie *)
(bcn->tail + ifmsh->meshconf_offset);
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index 38c45e1dafd8..ae378a41c927 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -150,21 +150,6 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
case NL80211_IFTYPE_STATION:
ieee80211_mgd_quiesce(sdata);
break;
- case NL80211_IFTYPE_WDS:
- /* tear down aggregation sessions and remove STAs */
- mutex_lock(&local->sta_mtx);
- sta = sdata->u.wds.sta;
- if (sta && sta->uploaded) {
- enum ieee80211_sta_state state;
-
- state = sta->sta_state;
- for (; state > IEEE80211_STA_NOTEXIST; state--)
- WARN_ON(drv_sta_state(local, sta->sdata,
- sta, state,
- state - 1));
- }
- mutex_unlock(&local->sta_mtx);
- break;
default:
break;
}
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 1e2e5a406d58..062c2b45584e 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1477,7 +1477,6 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx)
if (unlikely((ieee80211_is_data(hdr->frame_control) ||
ieee80211_is_pspoll(hdr->frame_control)) &&
rx->sdata->vif.type != NL80211_IFTYPE_ADHOC &&
- rx->sdata->vif.type != NL80211_IFTYPE_WDS &&
rx->sdata->vif.type != NL80211_IFTYPE_OCB &&
(!rx->sta || !test_sta_flag(rx->sta, WLAN_STA_ASSOC)))) {
/*
@@ -4080,10 +4079,6 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx)
return false;
return true;
- case NL80211_IFTYPE_WDS:
- if (bssid || !ieee80211_is_data(hdr->frame_control))
- return false;
- return ether_addr_equal(sdata->u.wds.remote_addr, hdr->addr2);
case NL80211_IFTYPE_P2P_DEVICE:
return ieee80211_is_public_action(hdr, skb->len) ||
ieee80211_is_probe_req(hdr->frame_control) ||
@@ -4742,6 +4737,8 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
status->rx_flags = 0;
+ kcov_remote_start_common(skb_get_kcov_handle(skb));
+
/*
* Frames with failed FCS/PLCP checksum are not returned,
* all other frames are returned without radiotap header
@@ -4749,15 +4746,15 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
* Also, frames with less than 16 bytes are dropped.
*/
skb = ieee80211_rx_monitor(local, skb, rate);
- if (!skb)
- return;
-
- ieee80211_tpt_led_trig_rx(local,
- ((struct ieee80211_hdr *)skb->data)->frame_control,
- skb->len);
+ if (skb) {
+ ieee80211_tpt_led_trig_rx(local,
+ ((struct ieee80211_hdr *)skb->data)->frame_control,
+ skb->len);
- __ieee80211_rx_handle_packet(hw, pubsta, skb, list);
+ __ieee80211_rx_handle_packet(hw, pubsta, skb, list);
+ }
+ kcov_remote_stop();
return;
drop:
kfree_skb(skb);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 56a4d0d20a26..01eb08527817 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -319,9 +319,6 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx)
if (tx->sdata->vif.type == NL80211_IFTYPE_OCB)
return TX_CONTINUE;
- if (tx->sdata->vif.type == NL80211_IFTYPE_WDS)
- return TX_CONTINUE;
-
if (tx->flags & IEEE80211_TX_PS_BUFFERED)
return TX_CONTINUE;
@@ -2113,6 +2110,9 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb,
info->flags |= IEEE80211_TX_CTL_NO_ACK;
if (txflags & IEEE80211_RADIOTAP_F_TX_NOSEQNO)
info->control.flags |= IEEE80211_TX_CTRL_NO_SEQNO;
+ if (txflags & IEEE80211_RADIOTAP_F_TX_ORDER)
+ info->control.flags |=
+ IEEE80211_TX_CTRL_DONT_REORDER;
break;
case IEEE80211_RADIOTAP_RATE:
@@ -2279,11 +2279,13 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
payload[7]);
}
- /*
- * Initialize skb->priority for QoS frames. This is put in the TID field
- * of the frame before passing it to the driver.
+ /* Initialize skb->priority for QoS frames. If the DONT_REORDER flag
+ * is set, stick to the default value for skb->priority to assure
+ * frames injected with this flag are not reordered relative to each
+ * other.
*/
- if (ieee80211_is_data_qos(hdr->frame_control)) {
+ if (ieee80211_is_data_qos(hdr->frame_control) &&
+ !(info->control.flags & IEEE80211_TX_CTRL_DONT_REORDER)) {
u8 *p = ieee80211_get_qos_ctl(hdr);
skb->priority = *p & IEEE80211_QOS_CTL_TAG1D_MASK;
}
@@ -2295,8 +2297,7 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
* we handle as though they are non-injected frames.
* This code here isn't entirely correct, the local MAC address
* isn't always enough to find the interface to use; for proper
- * VLAN/WDS support we will need a different mechanism (which
- * likely isn't going to be monitor interfaces).
+ * VLAN support we have an nl80211-based mechanism.
*
* This is necessary, for example, for old hostapd versions that
* don't use nl80211-based management TX/RX.
@@ -2307,8 +2308,7 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
if (!ieee80211_sdata_running(tmp_sdata))
continue;
if (tmp_sdata->vif.type == NL80211_IFTYPE_MONITOR ||
- tmp_sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
- tmp_sdata->vif.type == NL80211_IFTYPE_WDS)
+ tmp_sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
continue;
if (ether_addr_equal(tmp_sdata->vif.addr, hdr->addr2)) {
sdata = tmp_sdata;
@@ -2402,9 +2402,6 @@ int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata,
}
sta = sta_info_get_bss(sdata, skb->data);
break;
- case NL80211_IFTYPE_WDS:
- sta = sta_info_get(sdata, sdata->u.wds.remote_addr);
- break;
#ifdef CONFIG_MAC80211_MESH
case NL80211_IFTYPE_MESH_POINT:
/* determined much later */
@@ -2580,20 +2577,6 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
hdrlen = 24;
band = chanctx_conf->def.chan->band;
break;
- case NL80211_IFTYPE_WDS:
- fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS);
- /* RA TA DA SA */
- memcpy(hdr.addr1, sdata->u.wds.remote_addr, ETH_ALEN);
- memcpy(hdr.addr2, sdata->vif.addr, ETH_ALEN);
- memcpy(hdr.addr3, skb->data, ETH_ALEN);
- memcpy(hdr.addr4, skb->data + ETH_ALEN, ETH_ALEN);
- hdrlen = 30;
- /*
- * This is the exception! WDS style interfaces are prohibited
- * when channel contexts are in used so this must be valid
- */
- band = local->hw.conf.chandef.chan->band;
- break;
#ifdef CONFIG_MAC80211_MESH
case NL80211_IFTYPE_MESH_POINT:
if (!is_multicast_ether_addr(skb->data)) {
@@ -4418,9 +4401,10 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
/*
* Transmit all pending packets. Called from tasklet.
*/
-void ieee80211_tx_pending(unsigned long data)
+void ieee80211_tx_pending(struct tasklet_struct *t)
{
- struct ieee80211_local *local = (struct ieee80211_local *)data;
+ struct ieee80211_local *local = from_tasklet(local, t,
+ tx_pending_tasklet);
unsigned long flags;
int i;
bool txok;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 49342060490f..8c3c01a1b923 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -386,9 +386,10 @@ _ieee80211_wake_txqs(struct ieee80211_local *local, unsigned long *flags)
rcu_read_unlock();
}
-void ieee80211_wake_txqs(unsigned long data)
+void ieee80211_wake_txqs(struct tasklet_struct *t)
{
- struct ieee80211_local *local = (struct ieee80211_local *)data;
+ struct ieee80211_local *local = from_tasklet(local, t,
+ wake_txqs_tasklet);
unsigned long flags;
spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
@@ -2513,7 +2514,6 @@ int ieee80211_reconfig(struct ieee80211_local *local)
return res;
}
break;
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_AP_VLAN:
case NL80211_IFTYPE_MONITOR:
case NL80211_IFTYPE_P2P_DEVICE:
@@ -2523,6 +2523,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
case NUM_NL80211_IFTYPES:
case NL80211_IFTYPE_P2P_CLIENT:
case NL80211_IFTYPE_P2P_GO:
+ case NL80211_IFTYPE_WDS:
WARN_ON(1);
break;
}
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index 2fb99325135a..9ea6004abe1b 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -118,9 +118,11 @@ u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata,
struct ieee80211_hdr *hdr)
{
struct ieee80211_local *local = sdata->local;
+ struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
u8 *p;
- if (local->hw.queues < IEEE80211_NUM_ACS)
+ if ((info->control.flags & IEEE80211_TX_CTRL_DONT_REORDER) ||
+ local->hw.queues < IEEE80211_NUM_ACS)
return 0;
if (!ieee80211_is_data(hdr->frame_control)) {
@@ -141,6 +143,7 @@ u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata,
u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
struct sta_info *sta, struct sk_buff *skb)
{
+ struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
struct mac80211_qos_map *qos_map;
bool qos;
@@ -153,7 +156,7 @@ u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
else
qos = false;
- if (!qos) {
+ if (!qos || (info->control.flags & IEEE80211_TX_CTRL_DONT_REORDER)) {
skb->priority = 0; /* required for correct WPA/11i MIC */
return IEEE80211_AC_BE;
}
@@ -202,9 +205,6 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
case NL80211_IFTYPE_AP:
ra = skb->data;
break;
- case NL80211_IFTYPE_WDS:
- ra = sdata->u.wds.remote_addr;
- break;
case NL80211_IFTYPE_STATION:
/* might be a TDLS station */
sta = sta_info_get(sdata, skb->data);
@@ -249,6 +249,14 @@ void ieee80211_set_qos_hdr(struct ieee80211_sub_if_data *sdata,
p = ieee80211_get_qos_ctl(hdr);
+ /* don't overwrite the QoS field of injected frames */
+ if (info->flags & IEEE80211_TX_CTL_INJECTED) {
+ /* do take into account Ack policy of injected frames */
+ if (*p & IEEE80211_QOS_CTL_ACK_POLICY_NOACK)
+ info->flags |= IEEE80211_TX_CTL_NO_ACK;
+ return;
+ }
+
/* set up the first byte */
/*
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 06ea0f8bfd5c..520cedc594e1 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -20,9 +20,9 @@
#include "ieee802154_i.h"
#include "cfg.h"
-static void ieee802154_tasklet_handler(unsigned long data)
+static void ieee802154_tasklet_handler(struct tasklet_struct *t)
{
- struct ieee802154_local *local = (struct ieee802154_local *)data;
+ struct ieee802154_local *local = from_tasklet(local, t, tasklet);
struct sk_buff *skb;
while ((skb = skb_dequeue(&local->skb_queue))) {
@@ -91,9 +91,7 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops)
INIT_LIST_HEAD(&local->interfaces);
mutex_init(&local->iflist_mtx);
- tasklet_init(&local->tasklet,
- ieee802154_tasklet_handler,
- (unsigned long)local);
+ tasklet_setup(&local->tasklet, ieee802154_tasklet_handler);
skb_queue_head_init(&local->skb_queue);
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index f2868a8a50c3..47bab701555f 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -377,6 +377,8 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
if (!pskb_may_pull(skb, sizeof(*hdr)))
goto err;
+ skb_dst_drop(skb);
+
/* Read and decode the label */
hdr = mpls_hdr(skb);
dec = mpls_entry_decode(hdr);
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 54b888f94009..96ba616f59bf 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -18,6 +18,7 @@ struct mptcp_pernet {
struct ctl_table_header *ctl_table_hdr;
int mptcp_enabled;
+ unsigned int add_addr_timeout;
};
static struct mptcp_pernet *mptcp_get_pernet(struct net *net)
@@ -30,6 +31,11 @@ int mptcp_is_enabled(struct net *net)
return mptcp_get_pernet(net)->mptcp_enabled;
}
+unsigned int mptcp_get_add_addr_timeout(struct net *net)
+{
+ return mptcp_get_pernet(net)->add_addr_timeout;
+}
+
static struct ctl_table mptcp_sysctl_table[] = {
{
.procname = "enabled",
@@ -40,12 +46,19 @@ static struct ctl_table mptcp_sysctl_table[] = {
*/
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "add_addr_timeout",
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
{}
};
static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
{
pernet->mptcp_enabled = 1;
+ pernet->add_addr_timeout = TCP_RTO_MAX;
}
static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
@@ -61,6 +74,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
}
table[0].data = &pernet->mptcp_enabled;
+ table[1].data = &pernet->add_addr_timeout;
hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table);
if (!hdr)
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index a044dd43411d..f2d1e27a2bc1 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -492,7 +492,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
bool ret = false;
mpext = skb ? mptcp_get_ext(skb) : NULL;
- snd_data_fin_enable = READ_ONCE(msk->snd_data_fin_enable);
+ snd_data_fin_enable = mptcp_data_fin_enabled(msk);
if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) {
unsigned int map_size;
@@ -809,11 +809,14 @@ static u64 expand_ack(u64 old_ack, u64 cur_ack, bool use_64bit)
return cur_ack;
}
-static void update_una(struct mptcp_sock *msk,
- struct mptcp_options_received *mp_opt)
+static void ack_update_msk(struct mptcp_sock *msk,
+ const struct sock *ssk,
+ struct mptcp_options_received *mp_opt)
{
u64 new_snd_una, snd_una, old_snd_una = atomic64_read(&msk->snd_una);
- u64 write_seq = READ_ONCE(msk->write_seq);
+ u64 new_wnd_end, wnd_end, old_wnd_end = atomic64_read(&msk->wnd_end);
+ u64 snd_nxt = READ_ONCE(msk->snd_nxt);
+ struct sock *sk = (struct sock *)msk;
/* avoid ack expansion on update conflict, to reduce the risk of
* wrongly expanding to a future ack sequence number, which is way
@@ -822,15 +825,28 @@ static void update_una(struct mptcp_sock *msk,
new_snd_una = expand_ack(old_snd_una, mp_opt->data_ack, mp_opt->ack64);
/* ACK for data not even sent yet? Ignore. */
- if (after64(new_snd_una, write_seq))
+ if (after64(new_snd_una, snd_nxt))
new_snd_una = old_snd_una;
+ new_wnd_end = new_snd_una + tcp_sk(ssk)->snd_wnd;
+
+ while (after64(new_wnd_end, old_wnd_end)) {
+ wnd_end = old_wnd_end;
+ old_wnd_end = atomic64_cmpxchg(&msk->wnd_end, wnd_end,
+ new_wnd_end);
+ if (old_wnd_end == wnd_end) {
+ if (mptcp_send_head(sk))
+ mptcp_schedule_work(sk);
+ break;
+ }
+ }
+
while (after64(new_snd_una, old_snd_una)) {
snd_una = old_snd_una;
old_snd_una = atomic64_cmpxchg(&msk->snd_una, snd_una,
new_snd_una);
if (old_snd_una == snd_una) {
- mptcp_data_acked((struct sock *)msk);
+ mptcp_data_acked(sk);
break;
}
}
@@ -930,7 +946,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
* monodirectional flows will stuck
*/
if (mp_opt.use_ack)
- update_una(msk, &mp_opt);
+ ack_update_msk(msk, sk, &mp_opt);
/* Zero-data-length packets are dropped by the caller and not
* propagated to the MPTCP layer, so the skb extension does not
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index e19e1525ecbb..f9c88e2abb8e 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -89,8 +89,7 @@ static bool mptcp_pm_schedule_work(struct mptcp_sock *msk,
return false;
msk->pm.status |= BIT(new_status);
- if (schedule_work(&msk->work))
- sock_hold((struct sock *)msk);
+ mptcp_schedule_work((struct sock *)msk);
return true;
}
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 0d6f3d912891..f8a9d82a0ea8 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -232,7 +232,8 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
}
if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
- sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX);
+ sk_reset_timer(sk, timer,
+ jiffies + mptcp_get_add_addr_timeout(sock_net(sk)));
spin_unlock_bh(&msk->pm.lock);
@@ -264,6 +265,7 @@ static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
{
struct mptcp_pm_add_entry *add_entry = NULL;
struct sock *sk = (struct sock *)msk;
+ struct net *net = sock_net(sk);
if (lookup_anno_list_by_saddr(msk, &entry->addr))
return false;
@@ -279,7 +281,8 @@ static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
add_entry->retrans_times = 0;
timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
- sk_reset_timer(sk, &add_entry->add_timer, jiffies + TCP_RTO_MAX);
+ sk_reset_timer(sk, &add_entry->add_timer,
+ jiffies + mptcp_get_add_addr_timeout(net));
return true;
}
@@ -413,14 +416,13 @@ void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk)
list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
- long timeout = 0;
if (msk->pm.rm_id != subflow->remote_id)
continue;
spin_unlock_bh(&msk->pm.lock);
mptcp_subflow_shutdown(sk, ssk, how);
- __mptcp_close_ssk(sk, ssk, subflow, timeout);
+ __mptcp_close_ssk(sk, ssk, subflow);
spin_lock_bh(&msk->pm.lock);
msk->pm.add_addr_accepted--;
@@ -449,14 +451,13 @@ void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id)
list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
- long timeout = 0;
if (rm_id != subflow->local_id)
continue;
spin_unlock_bh(&msk->pm.lock);
mptcp_subflow_shutdown(sk, ssk, how);
- __mptcp_close_ssk(sk, ssk, subflow, timeout);
+ __mptcp_close_ssk(sk, ssk, subflow);
spin_lock_bh(&msk->pm.lock);
msk->pm.local_addr_used--;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 88f2a7a0ccb8..8df013daea88 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -21,6 +21,7 @@
#include <net/transp_v6.h>
#endif
#include <net/mptcp.h>
+#include <net/xfrm.h>
#include "protocol.h"
#include "mib.h"
@@ -41,6 +42,9 @@ struct mptcp_skb_cb {
static struct percpu_counter mptcp_sockets_allocated;
+static void __mptcp_destroy_sock(struct sock *sk);
+static void __mptcp_check_send_data_fin(struct sock *sk);
+
/* If msk has an initial subflow socket, and the MP_CAPABLE handshake has not
* completed yet or has failed, return the subflow socket.
* Otherwise return NULL.
@@ -53,6 +57,12 @@ static struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk)
return msk->subflow;
}
+/* Returns end sequence number of the receiver's advertised window */
+static u64 mptcp_wnd_end(const struct mptcp_sock *msk)
+{
+ return atomic64_read(&msk->wnd_end);
+}
+
static bool mptcp_is_tcpsk(struct sock *sk)
{
struct socket *sock = sk->sk_socket;
@@ -102,6 +112,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
msk->subflow = ssock;
subflow = mptcp_subflow_ctx(ssock->sk);
list_add(&subflow->node, &msk->conn_list);
+ sock_hold(ssock->sk);
subflow->request_mptcp = 1;
/* accept() will wait on first subflow sk_wq, and we always wakes up
@@ -169,6 +180,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
if (after64(seq, max_seq)) {
/* out of window */
mptcp_drop(sk, skb);
+ pr_debug("oow by %ld", (unsigned long)seq - (unsigned long)max_seq);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_NODSSWINDOW);
return;
}
@@ -323,6 +335,19 @@ static void mptcp_stop_timer(struct sock *sk)
mptcp_sk(sk)->timer_ival = 0;
}
+static void mptcp_close_wake_up(struct sock *sk)
+{
+ if (sock_flag(sk, SOCK_DEAD))
+ return;
+
+ sk->sk_state_change(sk);
+ if (sk->sk_shutdown == SHUTDOWN_MASK ||
+ sk->sk_state == TCP_CLOSE)
+ sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
+ else
+ sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+}
+
static void mptcp_check_data_fin_ack(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
@@ -341,20 +366,14 @@ static void mptcp_check_data_fin_ack(struct sock *sk)
switch (sk->sk_state) {
case TCP_FIN_WAIT1:
inet_sk_state_store(sk, TCP_FIN_WAIT2);
- sk->sk_state_change(sk);
break;
case TCP_CLOSING:
case TCP_LAST_ACK:
inet_sk_state_store(sk, TCP_CLOSE);
- sk->sk_state_change(sk);
break;
}
- if (sk->sk_shutdown == SHUTDOWN_MASK ||
- sk->sk_state == TCP_CLOSE)
- sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
- else
- sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+ mptcp_close_wake_up(sk);
}
}
@@ -388,13 +407,27 @@ static void mptcp_set_timeout(const struct sock *sk, const struct sock *ssk)
mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN;
}
-static void mptcp_check_data_fin(struct sock *sk)
+static void mptcp_send_ack(struct mptcp_sock *msk)
+{
+ struct mptcp_subflow_context *subflow;
+
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+ lock_sock(ssk);
+ tcp_send_ack(ssk);
+ release_sock(ssk);
+ }
+}
+
+static bool mptcp_check_data_fin(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
u64 rcv_data_fin_seq;
+ bool ret = false;
if (__mptcp_check_fallback(msk) || !msk->first)
- return;
+ return ret;
/* Need to ack a DATA_FIN received from a peer while this side
* of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2.
@@ -410,8 +443,6 @@ static void mptcp_check_data_fin(struct sock *sk)
*/
if (mptcp_pending_data_fin(sk, &rcv_data_fin_seq)) {
- struct mptcp_subflow_context *subflow;
-
WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1);
WRITE_ONCE(msk->rcv_data_fin, 0);
@@ -428,7 +459,6 @@ static void mptcp_check_data_fin(struct sock *sk)
break;
case TCP_FIN_WAIT2:
inet_sk_state_store(sk, TCP_CLOSE);
- // @@ Close subflows now?
break;
default:
/* Other states not expected */
@@ -436,23 +466,12 @@ static void mptcp_check_data_fin(struct sock *sk)
break;
}
+ ret = true;
mptcp_set_timeout(sk, NULL);
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
- lock_sock(ssk);
- tcp_send_ack(ssk);
- release_sock(ssk);
- }
-
- sk->sk_state_change(sk);
-
- if (sk->sk_shutdown == SHUTDOWN_MASK ||
- sk->sk_state == TCP_CLOSE)
- sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
- else
- sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+ mptcp_send_ack(msk);
+ mptcp_close_wake_up(sk);
}
+ return ret;
}
static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
@@ -466,6 +485,18 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
struct tcp_sock *tp;
u32 old_copied_seq;
bool done = false;
+ int sk_rbuf;
+
+ sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
+
+ if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
+ int ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
+
+ if (unlikely(ssk_rbuf > sk_rbuf)) {
+ WRITE_ONCE(sk->sk_rcvbuf, ssk_rbuf);
+ sk_rbuf = ssk_rbuf;
+ }
+ }
pr_debug("msk=%p ssk=%p", msk, ssk);
tp = tcp_sk(ssk);
@@ -528,7 +559,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
WRITE_ONCE(tp->copied_seq, seq);
more_data_avail = mptcp_subflow_data_available(ssk);
- if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) {
+ if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) {
done = true;
break;
}
@@ -608,9 +639,8 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
* this is not a good place to change state. Let the workqueue
* do it.
*/
- if (mptcp_pending_data_fin(sk, NULL) &&
- schedule_work(&msk->work))
- sock_hold(sk);
+ if (mptcp_pending_data_fin(sk, NULL))
+ mptcp_schedule_work(sk);
}
spin_unlock_bh(&sk->sk_lock.slock);
@@ -622,6 +652,7 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct mptcp_sock *msk = mptcp_sk(sk);
+ int sk_rbuf, ssk_rbuf;
bool wake;
/* move_skbs_to_msk below can legitly clear the data_avail flag,
@@ -632,12 +663,16 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
if (wake)
set_bit(MPTCP_DATA_READY, &msk->flags);
- if (atomic_read(&sk->sk_rmem_alloc) < READ_ONCE(sk->sk_rcvbuf) &&
- move_skbs_to_msk(msk, ssk))
+ ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
+ sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
+ if (unlikely(ssk_rbuf > sk_rbuf))
+ sk_rbuf = ssk_rbuf;
+
+ /* over limit? can't append more skbs to msk */
+ if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf)
goto wake;
- /* don't schedule if mptcp sk is (still) over limit */
- if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf))
+ if (move_skbs_to_msk(msk, ssk))
goto wake;
/* mptcp socket is owned, release_cb should retry */
@@ -675,6 +710,10 @@ static void mptcp_reset_timer(struct sock *sk)
struct inet_connection_sock *icsk = inet_csk(sk);
unsigned long tout;
+ /* prevent rescheduling on close */
+ if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE))
+ return;
+
/* should never be called with mptcp level timer cleared */
tout = READ_ONCE(mptcp_sk(sk)->timer_ival);
if (WARN_ON_ONCE(!tout))
@@ -682,23 +721,33 @@ static void mptcp_reset_timer(struct sock *sk)
sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + tout);
}
+bool mptcp_schedule_work(struct sock *sk)
+{
+ if (inet_sk_state_load(sk) != TCP_CLOSE &&
+ schedule_work(&mptcp_sk(sk)->work)) {
+ /* each subflow already holds a reference to the sk, and the
+ * workqueue is invoked by a subflow, so sk can't go away here.
+ */
+ sock_hold(sk);
+ return true;
+ }
+ return false;
+}
+
void mptcp_data_acked(struct sock *sk)
{
mptcp_reset_timer(sk);
- if ((!test_bit(MPTCP_SEND_SPACE, &mptcp_sk(sk)->flags) ||
- (inet_sk_state_load(sk) != TCP_ESTABLISHED)) &&
- schedule_work(&mptcp_sk(sk)->work))
- sock_hold(sk);
+ if ((test_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags) ||
+ mptcp_send_head(sk) ||
+ (inet_sk_state_load(sk) != TCP_ESTABLISHED)))
+ mptcp_schedule_work(sk);
}
void mptcp_subflow_eof(struct sock *sk)
{
- struct mptcp_sock *msk = mptcp_sk(sk);
-
- if (!test_and_set_bit(MPTCP_WORK_EOF, &msk->flags) &&
- schedule_work(&msk->work))
- sock_hold(sk);
+ if (!test_and_set_bit(MPTCP_WORK_EOF, &mptcp_sk(sk)->flags))
+ mptcp_schedule_work(sk);
}
static void mptcp_check_for_eof(struct mptcp_sock *msk)
@@ -709,8 +758,10 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk)
mptcp_for_each_subflow(msk, subflow)
receivers += !subflow->rx_eof;
+ if (receivers)
+ return;
- if (!receivers && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
+ if (!(sk->sk_shutdown & RCV_SHUTDOWN)) {
/* hopefully temporary hack: propagate shutdown status
* to msk, when all subflows agree on it
*/
@@ -720,6 +771,19 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk)
set_bit(MPTCP_DATA_READY, &msk->flags);
sk->sk_data_ready(sk);
}
+
+ switch (sk->sk_state) {
+ case TCP_ESTABLISHED:
+ inet_sk_state_store(sk, TCP_CLOSE_WAIT);
+ break;
+ case TCP_FIN_WAIT1:
+ /* fallback sockets skip TCP_CLOSING - TCP will take care */
+ inet_sk_state_store(sk, TCP_CLOSE);
+ break;
+ default:
+ return;
+ }
+ mptcp_close_wake_up(sk);
}
static bool mptcp_ext_cache_refill(struct mptcp_sock *msk)
@@ -754,8 +818,11 @@ static bool mptcp_skb_can_collapse_to(u64 write_seq,
if (!tcp_skb_can_collapse_to(skb))
return false;
- /* can collapse only if MPTCP level sequence is in order */
- return mpext && mpext->data_seq + mpext->data_len == write_seq;
+ /* can collapse only if MPTCP level sequence is in order and this
+ * mapping has not been xmitted yet
+ */
+ return mpext && mpext->data_seq + mpext->data_len == write_seq &&
+ !mpext->frozen;
}
static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
@@ -763,6 +830,7 @@ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
const struct mptcp_data_frag *df)
{
return df && pfrag->page == df->page &&
+ pfrag->size - pfrag->offset > 0 &&
df->data_seq + df->data_len == msk->write_seq;
}
@@ -781,20 +849,6 @@ static void dfrag_clear(struct sock *sk, struct mptcp_data_frag *dfrag)
put_page(dfrag->page);
}
-static bool mptcp_is_writeable(struct mptcp_sock *msk)
-{
- struct mptcp_subflow_context *subflow;
-
- if (!sk_stream_is_writeable((struct sock *)msk))
- return false;
-
- mptcp_for_each_subflow(msk, subflow) {
- if (sk_stream_is_writeable(subflow->tcp_sock))
- return true;
- }
- return false;
-}
-
static void mptcp_clean_una(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
@@ -806,13 +860,16 @@ static void mptcp_clean_una(struct sock *sk)
* plain TCP
*/
if (__mptcp_check_fallback(msk))
- atomic64_set(&msk->snd_una, msk->write_seq);
+ atomic64_set(&msk->snd_una, msk->snd_nxt);
+
snd_una = atomic64_read(&msk->snd_una);
list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) {
if (after64(dfrag->data_seq + dfrag->data_len, snd_una))
break;
+ if (WARN_ON_ONCE(dfrag == msk->first_pending))
+ break;
dfrag_clear(sk, dfrag);
cleaned = true;
}
@@ -821,31 +878,33 @@ static void mptcp_clean_una(struct sock *sk)
if (dfrag && after64(snd_una, dfrag->data_seq)) {
u64 delta = snd_una - dfrag->data_seq;
- if (WARN_ON_ONCE(delta > dfrag->data_len))
+ if (WARN_ON_ONCE(delta > dfrag->already_sent))
goto out;
dfrag->data_seq += delta;
dfrag->offset += delta;
dfrag->data_len -= delta;
+ dfrag->already_sent -= delta;
dfrag_uncharge(sk, delta);
cleaned = true;
}
out:
- if (cleaned) {
+ if (cleaned)
sk_mem_reclaim_partial(sk);
+}
- /* Only wake up writers if a subflow is ready */
- if (mptcp_is_writeable(msk)) {
- set_bit(MPTCP_SEND_SPACE, &mptcp_sk(sk)->flags);
- smp_mb__after_atomic();
+static void mptcp_clean_una_wakeup(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
- /* set SEND_SPACE before sk_stream_write_space clears
- * NOSPACE
- */
- sk_stream_write_space(sk);
- }
+ mptcp_clean_una(sk);
+
+ /* Only wake up writers if a subflow is ready */
+ if (sk_stream_is_writeable(sk)) {
+ clear_bit(MPTCP_NOSPACE, &msk->flags);
+ sk_stream_write_space(sk);
}
}
@@ -854,12 +913,23 @@ out:
*/
static bool mptcp_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
{
+ struct mptcp_subflow_context *subflow;
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ bool first = true;
+
if (likely(skb_page_frag_refill(32U + sizeof(struct mptcp_data_frag),
pfrag, sk->sk_allocation)))
return true;
- sk->sk_prot->enter_memory_pressure(sk);
sk_stream_moderate_sndbuf(sk);
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+ if (first)
+ tcp_enter_memory_pressure(ssk);
+ sk_stream_moderate_sndbuf(ssk);
+ first = false;
+ }
return false;
}
@@ -875,149 +945,109 @@ mptcp_carve_data_frag(const struct mptcp_sock *msk, struct page_frag *pfrag,
dfrag->data_seq = msk->write_seq;
dfrag->overhead = offset - orig_offset + sizeof(struct mptcp_data_frag);
dfrag->offset = offset + sizeof(struct mptcp_data_frag);
+ dfrag->already_sent = 0;
dfrag->page = pfrag->page;
return dfrag;
}
+struct mptcp_sendmsg_info {
+ int mss_now;
+ int size_goal;
+ u16 limit;
+ u16 sent;
+ unsigned int flags;
+};
+
+static int mptcp_check_allowed_size(struct mptcp_sock *msk, u64 data_seq,
+ int avail_size)
+{
+ u64 window_end = mptcp_wnd_end(msk);
+
+ if (__mptcp_check_fallback(msk))
+ return avail_size;
+
+ if (!before64(data_seq + avail_size, window_end)) {
+ u64 allowed_size = window_end - data_seq;
+
+ return min_t(unsigned int, allowed_size, avail_size);
+ }
+
+ return avail_size;
+}
+
static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
- struct msghdr *msg, struct mptcp_data_frag *dfrag,
- long *timeo, int *pmss_now,
- int *ps_goal)
+ struct mptcp_data_frag *dfrag,
+ struct mptcp_sendmsg_info *info)
{
- int mss_now, avail_size, size_goal, offset, ret, frag_truesize = 0;
- bool dfrag_collapsed, can_collapse = false;
+ u64 data_seq = dfrag->data_seq + info->sent;
struct mptcp_sock *msk = mptcp_sk(sk);
+ bool zero_window_probe = false;
struct mptcp_ext *mpext = NULL;
- bool retransmission = !!dfrag;
struct sk_buff *skb, *tail;
- struct page_frag *pfrag;
- struct page *page;
- u64 *write_seq;
- size_t psize;
-
- /* use the mptcp page cache so that we can easily move the data
- * from one substream to another, but do per subflow memory accounting
- * Note: pfrag is used only !retransmission, but the compiler if
- * fooled into a warning if we don't init here
- */
- pfrag = sk_page_frag(sk);
- if (!retransmission) {
- write_seq = &msk->write_seq;
- page = pfrag->page;
- } else {
- write_seq = &dfrag->data_seq;
- page = dfrag->page;
- }
+ bool can_collapse = false;
+ int avail_size;
+ size_t ret;
- /* compute copy limit */
- mss_now = tcp_send_mss(ssk, &size_goal, msg->msg_flags);
- *pmss_now = mss_now;
- *ps_goal = size_goal;
- avail_size = size_goal;
+ pr_debug("msk=%p ssk=%p sending dfrag at seq=%lld len=%d already sent=%d",
+ msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent);
+
+ /* compute send limit */
+ info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags);
+ avail_size = info->size_goal;
skb = tcp_write_queue_tail(ssk);
if (skb) {
- mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
-
/* Limit the write to the size available in the
* current skb, if any, so that we create at most a new skb.
* Explicitly tells TCP internals to avoid collapsing on later
* queue management operation, to avoid breaking the ext <->
* SSN association set here
*/
- can_collapse = (size_goal - skb->len > 0) &&
- mptcp_skb_can_collapse_to(*write_seq, skb, mpext);
+ mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
+ can_collapse = (info->size_goal - skb->len > 0) &&
+ mptcp_skb_can_collapse_to(data_seq, skb, mpext);
if (!can_collapse)
TCP_SKB_CB(skb)->eor = 1;
else
- avail_size = size_goal - skb->len;
+ avail_size = info->size_goal - skb->len;
}
- if (!retransmission) {
- /* reuse tail pfrag, if possible, or carve a new one from the
- * page allocator
- */
- dfrag = mptcp_rtx_tail(sk);
- offset = pfrag->offset;
- dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag);
- if (!dfrag_collapsed) {
- dfrag = mptcp_carve_data_frag(msk, pfrag, offset);
- offset = dfrag->offset;
- frag_truesize = dfrag->overhead;
- }
- psize = min_t(size_t, pfrag->size - offset, avail_size);
-
- /* Copy to page */
- pr_debug("left=%zu", msg_data_left(msg));
- psize = copy_page_from_iter(pfrag->page, offset,
- min_t(size_t, msg_data_left(msg),
- psize),
- &msg->msg_iter);
- pr_debug("left=%zu", msg_data_left(msg));
- if (!psize)
- return -EINVAL;
-
- if (!sk_wmem_schedule(sk, psize + dfrag->overhead)) {
- iov_iter_revert(&msg->msg_iter, psize);
- return -ENOMEM;
- }
- } else {
- offset = dfrag->offset;
- psize = min_t(size_t, dfrag->data_len, avail_size);
+ /* Zero window and all data acked? Probe. */
+ avail_size = mptcp_check_allowed_size(msk, data_seq, avail_size);
+ if (avail_size == 0) {
+ if (skb || atomic64_read(&msk->snd_una) != msk->snd_nxt)
+ return 0;
+ zero_window_probe = true;
+ data_seq = atomic64_read(&msk->snd_una) - 1;
+ avail_size = 1;
}
- /* tell the TCP stack to delay the push so that we can safely
- * access the skb after the sendpages call
- */
- ret = do_tcp_sendpages(ssk, page, offset, psize,
- msg->msg_flags | MSG_SENDPAGE_NOTLAST | MSG_DONTWAIT);
- if (ret <= 0) {
- if (!retransmission)
- iov_iter_revert(&msg->msg_iter, psize);
- return ret;
- }
+ if (WARN_ON_ONCE(info->sent > info->limit ||
+ info->limit > dfrag->data_len))
+ return 0;
- frag_truesize += ret;
- if (!retransmission) {
- if (unlikely(ret < psize))
- iov_iter_revert(&msg->msg_iter, psize - ret);
-
- /* send successful, keep track of sent data for mptcp-level
- * retransmission
- */
- dfrag->data_len += ret;
- if (!dfrag_collapsed) {
- get_page(dfrag->page);
- list_add_tail(&dfrag->list, &msk->rtx_queue);
- sk_wmem_queued_add(sk, frag_truesize);
- } else {
- sk_wmem_queued_add(sk, ret);
- }
-
- /* charge data on mptcp rtx queue to the master socket
- * Note: we charge such data both to sk and ssk
- */
- sk->sk_forward_alloc -= frag_truesize;
+ ret = info->limit - info->sent;
+ tail = tcp_build_frag(ssk, avail_size, info->flags, dfrag->page,
+ dfrag->offset + info->sent, &ret);
+ if (!tail) {
+ tcp_remove_empty_skb(sk, tcp_write_queue_tail(ssk));
+ return -ENOMEM;
}
- /* if the tail skb extension is still the cached one, collapsing
- * really happened. Note: we can't check for 'same skb' as the sk_buff
- * hdr on tail can be transmitted, freed and re-allocated by the
- * do_tcp_sendpages() call
+ /* if the tail skb is still the cached one, collapsing really happened.
*/
- tail = tcp_write_queue_tail(ssk);
- if (mpext && tail && mpext == skb_ext_find(tail, SKB_EXT_MPTCP)) {
+ if (skb == tail) {
WARN_ON_ONCE(!can_collapse);
mpext->data_len += ret;
+ WARN_ON_ONCE(zero_window_probe);
goto out;
}
- skb = tcp_write_queue_tail(ssk);
- mpext = __skb_ext_set(skb, SKB_EXT_MPTCP, msk->cached_ext);
+ mpext = __skb_ext_set(tail, SKB_EXT_MPTCP, msk->cached_ext);
msk->cached_ext = NULL;
memset(mpext, 0, sizeof(*mpext));
- mpext->data_seq = *write_seq;
+ mpext->data_seq = data_seq;
mpext->subflow_seq = mptcp_subflow_ctx(ssk)->rel_write_seq;
mpext->data_len = ret;
mpext->use_map = 1;
@@ -1027,12 +1057,14 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
mpext->data_seq, mpext->subflow_seq, mpext->data_len,
mpext->dsn64);
+ if (zero_window_probe) {
+ mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
+ mpext->frozen = 1;
+ ret = 0;
+ tcp_push_pending_frames(ssk);
+ }
out:
- if (!retransmission)
- pfrag->offset += frag_truesize;
- WRITE_ONCE(*write_seq, *write_seq + ret);
mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
-
return ret;
}
@@ -1040,17 +1072,25 @@ static void mptcp_nospace(struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow;
- clear_bit(MPTCP_SEND_SPACE, &msk->flags);
+ set_bit(MPTCP_NOSPACE, &msk->flags);
smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ bool ssk_writeable = sk_stream_is_writeable(ssk);
struct socket *sock = READ_ONCE(ssk->sk_socket);
+ if (ssk_writeable || !sock)
+ continue;
+
/* enables ssk->write_space() callbacks */
- if (sock)
- set_bit(SOCK_NOSPACE, &sock->flags);
+ set_bit(SOCK_NOSPACE, &sock->flags);
}
+
+ /* mptcp_data_acked() could run just before we set the NOSPACE bit,
+ * so explicitly check for snd_una value
+ */
+ mptcp_clean_una((struct sock *)msk);
}
static bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
@@ -1154,21 +1194,86 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk,
return NULL;
}
-static void ssk_check_wmem(struct mptcp_sock *msk)
+static void mptcp_push_release(struct sock *sk, struct sock *ssk,
+ struct mptcp_sendmsg_info *info)
{
- if (unlikely(!mptcp_is_writeable(msk)))
- mptcp_nospace(msk);
+ mptcp_set_timeout(sk, ssk);
+ tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle, info->size_goal);
+ release_sock(ssk);
+}
+
+static void mptcp_push_pending(struct sock *sk, unsigned int flags)
+{
+ struct sock *prev_ssk = NULL, *ssk = NULL;
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct mptcp_sendmsg_info info = {
+ .flags = flags,
+ };
+ struct mptcp_data_frag *dfrag;
+ int len, copied = 0;
+ u32 sndbuf;
+
+ while ((dfrag = mptcp_send_head(sk))) {
+ info.sent = dfrag->already_sent;
+ info.limit = dfrag->data_len;
+ len = dfrag->data_len - dfrag->already_sent;
+ while (len > 0) {
+ int ret = 0;
+
+ prev_ssk = ssk;
+ __mptcp_flush_join_list(msk);
+ ssk = mptcp_subflow_get_send(msk, &sndbuf);
+
+ /* do auto tuning */
+ if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK) &&
+ sndbuf > READ_ONCE(sk->sk_sndbuf))
+ WRITE_ONCE(sk->sk_sndbuf, sndbuf);
+
+ /* try to keep the subflow socket lock across
+ * consecutive xmit on the same socket
+ */
+ if (ssk != prev_ssk && prev_ssk)
+ mptcp_push_release(sk, prev_ssk, &info);
+ if (!ssk)
+ goto out;
+
+ if (ssk != prev_ssk || !prev_ssk)
+ lock_sock(ssk);
+
+ ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+ if (ret <= 0) {
+ mptcp_push_release(sk, ssk, &info);
+ goto out;
+ }
+
+ info.sent += ret;
+ dfrag->already_sent += ret;
+ msk->snd_nxt += ret;
+ msk->snd_burst -= ret;
+ copied += ret;
+ len -= ret;
+ }
+ WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+ }
+
+ /* at this point we held the socket lock for the last subflow we used */
+ if (ssk)
+ mptcp_push_release(sk, ssk, &info);
+
+out:
+ /* start the timer, if it's not pending */
+ if (!mptcp_timer_pending(sk))
+ mptcp_reset_timer(sk);
+ if (copied)
+ __mptcp_check_send_data_fin(sk);
}
static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
- int mss_now = 0, size_goal = 0, ret = 0;
struct mptcp_sock *msk = mptcp_sk(sk);
struct page_frag *pfrag;
size_t copied = 0;
- struct sock *ssk;
- u32 sndbuf;
- bool tx_ok;
+ int ret = 0;
long timeo;
if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
@@ -1185,130 +1290,92 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}
pfrag = sk_page_frag(sk);
-restart:
mptcp_clean_una(sk);
- if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) {
- ret = -EPIPE;
- goto out;
- }
-
- __mptcp_flush_join_list(msk);
- ssk = mptcp_subflow_get_send(msk, &sndbuf);
- while (!sk_stream_memory_free(sk) ||
- !ssk ||
- !mptcp_page_frag_refill(ssk, pfrag)) {
- if (ssk) {
- /* make sure retransmit timer is
- * running before we wait for memory.
- *
- * The retransmit timer might be needed
- * to make the peer send an up-to-date
- * MPTCP Ack.
- */
- mptcp_set_timeout(sk, ssk);
- if (!mptcp_timer_pending(sk))
- mptcp_reset_timer(sk);
- }
+ while (msg_data_left(msg)) {
+ struct mptcp_data_frag *dfrag;
+ int frag_truesize = 0;
+ bool dfrag_collapsed;
+ size_t psize, offset;
- mptcp_nospace(msk);
- ret = sk_stream_wait_memory(sk, &timeo);
- if (ret)
- goto out;
-
- mptcp_clean_una(sk);
-
- ssk = mptcp_subflow_get_send(msk, &sndbuf);
- if (list_empty(&msk->conn_list)) {
- ret = -ENOTCONN;
+ if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) {
+ ret = -EPIPE;
goto out;
}
- }
-
- /* do auto tuning */
- if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK) &&
- sndbuf > READ_ONCE(sk->sk_sndbuf))
- WRITE_ONCE(sk->sk_sndbuf, sndbuf);
- pr_debug("conn_list->subflow=%p", ssk);
-
- lock_sock(ssk);
- tx_ok = msg_data_left(msg);
- while (tx_ok) {
- ret = mptcp_sendmsg_frag(sk, ssk, msg, NULL, &timeo, &mss_now,
- &size_goal);
- if (ret < 0) {
- if (ret == -EAGAIN && timeo > 0) {
- mptcp_set_timeout(sk, ssk);
- release_sock(ssk);
- goto restart;
+ /* reuse tail pfrag, if possible, or carve a new one from the
+ * page allocator
+ */
+ dfrag = mptcp_pending_tail(sk);
+ dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag);
+ if (!dfrag_collapsed) {
+ if (!sk_stream_memory_free(sk)) {
+ mptcp_push_pending(sk, msg->msg_flags);
+ if (!sk_stream_memory_free(sk))
+ goto wait_for_memory;
}
- break;
+ if (!mptcp_page_frag_refill(sk, pfrag))
+ goto wait_for_memory;
+
+ dfrag = mptcp_carve_data_frag(msk, pfrag, pfrag->offset);
+ frag_truesize = dfrag->overhead;
}
- /* burst can be negative, we will try move to the next subflow
- * at selection time, if possible.
+ /* we do not bound vs wspace, to allow a single packet.
+ * memory accounting will prevent execessive memory usage
+ * anyway
*/
- msk->snd_burst -= ret;
- copied += ret;
-
- tx_ok = msg_data_left(msg);
- if (!tx_ok)
- break;
-
- if (!sk_stream_memory_free(ssk) ||
- !mptcp_page_frag_refill(ssk, pfrag) ||
- !mptcp_ext_cache_refill(msk)) {
- tcp_push(ssk, msg->msg_flags, mss_now,
- tcp_sk(ssk)->nonagle, size_goal);
- mptcp_set_timeout(sk, ssk);
- release_sock(ssk);
- goto restart;
+ offset = dfrag->offset + dfrag->data_len;
+ psize = pfrag->size - offset;
+ psize = min_t(size_t, psize, msg_data_left(msg));
+ if (!sk_wmem_schedule(sk, psize + frag_truesize))
+ goto wait_for_memory;
+
+ if (copy_page_from_iter(dfrag->page, offset, psize,
+ &msg->msg_iter) != psize) {
+ ret = -EFAULT;
+ goto out;
}
- /* memory is charged to mptcp level socket as well, i.e.
- * if msg is very large, mptcp socket may run out of buffer
- * space. mptcp_clean_una() will release data that has
- * been acked at mptcp level in the mean time, so there is
- * a good chance we can continue sending data right away.
- *
- * Normally, when the tcp subflow can accept more data, then
- * so can the MPTCP socket. However, we need to cope with
- * peers that might lag behind in their MPTCP-level
- * acknowledgements, i.e. data might have been acked at
- * tcp level only. So, we must also check the MPTCP socket
- * limits before we send more data.
+ /* data successfully copied into the write queue */
+ copied += psize;
+ dfrag->data_len += psize;
+ frag_truesize += psize;
+ pfrag->offset += frag_truesize;
+ WRITE_ONCE(msk->write_seq, msk->write_seq + psize);
+
+ /* charge data on mptcp pending queue to the msk socket
+ * Note: we charge such data both to sk and ssk
*/
- if (unlikely(!sk_stream_memory_free(sk))) {
- tcp_push(ssk, msg->msg_flags, mss_now,
- tcp_sk(ssk)->nonagle, size_goal);
- mptcp_clean_una(sk);
- if (!sk_stream_memory_free(sk)) {
- /* can't send more for now, need to wait for
- * MPTCP-level ACKs from peer.
- *
- * Wakeup will happen via mptcp_clean_una().
- */
- mptcp_set_timeout(sk, ssk);
- release_sock(ssk);
- goto restart;
- }
+ sk_wmem_queued_add(sk, frag_truesize);
+ sk->sk_forward_alloc -= frag_truesize;
+ if (!dfrag_collapsed) {
+ get_page(dfrag->page);
+ list_add_tail(&dfrag->list, &msk->rtx_queue);
+ if (!msk->first_pending)
+ WRITE_ONCE(msk->first_pending, dfrag);
}
- }
+ pr_debug("msk=%p dfrag at seq=%lld len=%d sent=%d new=%d", msk,
+ dfrag->data_seq, dfrag->data_len, dfrag->already_sent,
+ !dfrag_collapsed);
- mptcp_set_timeout(sk, ssk);
- if (copied) {
- tcp_push(ssk, msg->msg_flags, mss_now, tcp_sk(ssk)->nonagle,
- size_goal);
+ if (!mptcp_ext_cache_refill(msk))
+ goto wait_for_memory;
+ continue;
- /* start the timer, if it's not pending */
- if (!mptcp_timer_pending(sk))
+wait_for_memory:
+ mptcp_nospace(msk);
+ if (mptcp_timer_pending(sk))
mptcp_reset_timer(sk);
+ ret = sk_stream_wait_memory(sk, &timeo);
+ if (ret)
+ goto out;
}
- release_sock(ssk);
+ if (copied)
+ mptcp_push_pending(sk, msg->msg_flags);
+
out:
- ssk_check_wmem(msk);
release_sock(sk);
return copied ? : ret;
}
@@ -1476,17 +1543,19 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)
__mptcp_flush_join_list(msk);
do {
struct sock *ssk = mptcp_subflow_recv_lookup(msk);
+ bool slowpath;
if (!ssk)
break;
- lock_sock(ssk);
+ slowpath = lock_sock_fast(ssk);
done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
- release_sock(ssk);
+ unlock_sock_fast(ssk, slowpath);
} while (!done);
if (mptcp_ofo_queue(msk) || moved > 0) {
- mptcp_check_data_fin((struct sock *)msk);
+ if (!mptcp_check_data_fin((struct sock *)msk))
+ mptcp_send_ack(msk);
return true;
}
return false;
@@ -1598,12 +1667,11 @@ static void mptcp_retransmit_handler(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- if (atomic64_read(&msk->snd_una) == READ_ONCE(msk->write_seq)) {
+ if (atomic64_read(&msk->snd_una) == READ_ONCE(msk->snd_nxt)) {
mptcp_stop_timer(sk);
} else {
set_bit(MPTCP_WORK_RTX, &msk->flags);
- if (schedule_work(&msk->work))
- sock_hold(sk);
+ mptcp_schedule_work(sk);
}
}
@@ -1626,6 +1694,13 @@ static void mptcp_retransmit_timer(struct timer_list *t)
sock_put(sk);
}
+static void mptcp_timeout_timer(struct timer_list *t)
+{
+ struct sock *sk = from_timer(sk, t, sk_timer);
+
+ mptcp_schedule_work(sk);
+}
+
/* Find an idle subflow. Return NULL if there is unacked data at tcp
* level.
*
@@ -1639,7 +1714,7 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk)
sock_owned_by_me((const struct sock *)msk);
if (__mptcp_check_fallback(msk))
- return msk->first;
+ return NULL;
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
@@ -1672,20 +1747,43 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk)
* parent socket.
*/
void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
- struct mptcp_subflow_context *subflow,
- long timeout)
+ struct mptcp_subflow_context *subflow)
{
- struct socket *sock = READ_ONCE(ssk->sk_socket);
+ bool dispose_socket = false;
+ struct socket *sock;
list_del(&subflow->node);
- if (sock && sock != sk->sk_socket) {
- /* outgoing subflow */
- sock_release(sock);
+ lock_sock(ssk);
+
+ /* if we are invoked by the msk cleanup code, the subflow is
+ * already orphaned
+ */
+ sock = ssk->sk_socket;
+ if (sock) {
+ dispose_socket = sock != sk->sk_socket;
+ sock_orphan(ssk);
+ }
+
+ /* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops
+ * the ssk has been already destroyed, we just need to release the
+ * reference owned by msk;
+ */
+ if (!inet_csk(ssk)->icsk_ulp_ops) {
+ kfree_rcu(subflow, rcu);
} else {
- /* incoming subflow */
- tcp_close(ssk, timeout);
+ /* otherwise ask tcp do dispose of ssk and subflow ctx */
+ subflow->disposable = 1;
+ __tcp_close(ssk, 0);
+
+ /* close acquired an extra ref */
+ __sock_put(ssk);
}
+ release_sock(ssk);
+ if (dispose_socket)
+ iput(SOCK_INODE(sock));
+
+ sock_put(ssk);
}
static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu)
@@ -1730,31 +1828,53 @@ static void __mptcp_close_subflow(struct mptcp_sock *msk)
if (inet_sk_state_load(ssk) != TCP_CLOSE)
continue;
- __mptcp_close_ssk((struct sock *)msk, ssk, subflow, 0);
+ __mptcp_close_ssk((struct sock *)msk, ssk, subflow);
+ }
+}
+
+static bool mptcp_check_close_timeout(const struct sock *sk)
+{
+ s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp;
+ struct mptcp_subflow_context *subflow;
+
+ if (delta >= TCP_TIMEWAIT_LEN)
+ return true;
+
+ /* if all subflows are in closed status don't bother with additional
+ * timeout
+ */
+ mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
+ if (inet_sk_state_load(mptcp_subflow_tcp_sock(subflow)) !=
+ TCP_CLOSE)
+ return false;
}
+ return true;
}
static void mptcp_worker(struct work_struct *work)
{
struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
struct sock *ssk, *sk = &msk->sk.icsk_inet.sk;
- int orig_len, orig_offset, mss_now = 0, size_goal = 0;
+ struct mptcp_sendmsg_info info = {};
struct mptcp_data_frag *dfrag;
- u64 orig_write_seq;
size_t copied = 0;
- struct msghdr msg = {
- .msg_flags = MSG_DONTWAIT,
- };
- long timeo = 0;
+ int state, ret;
lock_sock(sk);
- mptcp_clean_una(sk);
+ set_bit(MPTCP_WORKER_RUNNING, &msk->flags);
+ state = sk->sk_state;
+ if (unlikely(state == TCP_CLOSE))
+ goto unlock;
+
+ mptcp_clean_una_wakeup(sk);
mptcp_check_data_fin_ack(sk);
__mptcp_flush_join_list(msk);
if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
__mptcp_close_subflow(msk);
__mptcp_move_skbs(msk);
+ if (mptcp_send_head(sk))
+ mptcp_push_pending(sk, 0);
if (msk->pm.status)
pm_work(msk);
@@ -1764,6 +1884,18 @@ static void mptcp_worker(struct work_struct *work)
mptcp_check_data_fin(sk);
+ /* if the msk data is completely acked, or the socket timedout,
+ * there is no point in keeping around an orphaned sk
+ */
+ if (sock_flag(sk, SOCK_DEAD) &&
+ (mptcp_check_close_timeout(sk) ||
+ (state != sk->sk_state &&
+ ((1 << inet_sk_state_load(sk)) & (TCPF_CLOSE | TCPF_FIN_WAIT2))))) {
+ inet_sk_state_store(sk, TCP_CLOSE);
+ __mptcp_destroy_sock(sk);
+ goto unlock;
+ }
+
if (!test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
goto unlock;
@@ -1780,30 +1912,24 @@ static void mptcp_worker(struct work_struct *work)
lock_sock(ssk);
- orig_len = dfrag->data_len;
- orig_offset = dfrag->offset;
- orig_write_seq = dfrag->data_seq;
- while (dfrag->data_len > 0) {
- int ret = mptcp_sendmsg_frag(sk, ssk, &msg, dfrag, &timeo,
- &mss_now, &size_goal);
- if (ret < 0)
+ /* limit retransmission to the bytes already sent on some subflows */
+ info.sent = 0;
+ info.limit = dfrag->already_sent;
+ while (info.sent < dfrag->already_sent) {
+ ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+ if (ret <= 0)
break;
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
copied += ret;
- dfrag->data_len -= ret;
- dfrag->offset += ret;
+ info.sent += ret;
if (!mptcp_ext_cache_refill(msk))
break;
}
if (copied)
- tcp_push(ssk, msg.msg_flags, mss_now, tcp_sk(ssk)->nonagle,
- size_goal);
-
- dfrag->data_seq = orig_write_seq;
- dfrag->offset = orig_offset;
- dfrag->data_len = orig_len;
+ tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+ info.size_goal);
mptcp_set_timeout(sk, ssk);
release_sock(ssk);
@@ -1813,6 +1939,7 @@ reset_unlock:
mptcp_reset_timer(sk);
unlock:
+ clear_bit(MPTCP_WORKER_RUNNING, &msk->flags);
release_sock(sk);
sock_put(sk);
}
@@ -1826,9 +1953,9 @@ static int __mptcp_init_sock(struct sock *sk)
INIT_LIST_HEAD(&msk->conn_list);
INIT_LIST_HEAD(&msk->join_list);
INIT_LIST_HEAD(&msk->rtx_queue);
- __set_bit(MPTCP_SEND_SPACE, &msk->flags);
INIT_WORK(&msk->work, mptcp_worker);
msk->out_of_order_queue = RB_ROOT;
+ msk->first_pending = NULL;
msk->first = NULL;
inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
@@ -1837,7 +1964,7 @@ static int __mptcp_init_sock(struct sock *sk)
/* re-use the csk retrans timer for MPTCP-level retrans */
timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
-
+ timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0);
return 0;
}
@@ -1874,6 +2001,7 @@ static void __mptcp_clear_xmit(struct sock *sk)
sk_stop_timer(sk, &msk->sk.icsk_retransmit_timer);
+ WRITE_ONCE(msk->first_pending, NULL);
list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list)
dfrag_clear(sk, dfrag);
}
@@ -1882,8 +2010,12 @@ static void mptcp_cancel_work(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- if (cancel_work_sync(&msk->work))
- sock_put(sk);
+ /* if called by the work itself, do not try to cancel the work, or
+ * we will hang.
+ */
+ if (!test_bit(MPTCP_WORKER_RUNNING, &msk->flags) &&
+ cancel_work_sync(&msk->work))
+ __sock_put(sk);
}
void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
@@ -1941,42 +2073,61 @@ static int mptcp_close_state(struct sock *sk)
return next & TCP_ACTION_FIN;
}
-static void mptcp_close(struct sock *sk, long timeout)
+static void __mptcp_check_send_data_fin(struct sock *sk)
{
- struct mptcp_subflow_context *subflow, *tmp;
+ struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk = mptcp_sk(sk);
- LIST_HEAD(conn_list);
- lock_sock(sk);
- sk->sk_shutdown = SHUTDOWN_MASK;
+ pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu",
+ msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk),
+ msk->snd_nxt, msk->write_seq);
- if (sk->sk_state == TCP_LISTEN) {
+ /* we still need to enqueue subflows or not really shutting down,
+ * skip this
+ */
+ if (!msk->snd_data_fin_enable || msk->snd_nxt + 1 != msk->write_seq ||
+ mptcp_send_head(sk))
+ return;
+
+ WRITE_ONCE(msk->snd_nxt, msk->write_seq);
+
+ /* fallback socket will not get data_fin/ack, can move to close now */
+ if (__mptcp_check_fallback(msk) && sk->sk_state == TCP_LAST_ACK) {
inet_sk_state_store(sk, TCP_CLOSE);
- goto cleanup;
- } else if (sk->sk_state == TCP_CLOSE) {
- goto cleanup;
+ mptcp_close_wake_up(sk);
}
- if (__mptcp_check_fallback(msk)) {
- goto update_state;
- } else if (mptcp_close_state(sk)) {
- pr_debug("Sending DATA_FIN sk=%p", sk);
- WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
- WRITE_ONCE(msk->snd_data_fin_enable, 1);
-
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
+ __mptcp_flush_join_list(msk);
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
- mptcp_subflow_shutdown(sk, tcp_sk, SHUTDOWN_MASK);
- }
+ mptcp_subflow_shutdown(sk, tcp_sk, SEND_SHUTDOWN);
}
+}
- sk_stream_wait_close(sk, timeout);
+static void __mptcp_wr_shutdown(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
-update_state:
- inet_sk_state_store(sk, TCP_CLOSE);
+ pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d",
+ msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state,
+ !!mptcp_send_head(sk));
+
+ /* will be ignored by fallback sockets */
+ WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
+ WRITE_ONCE(msk->snd_data_fin_enable, 1);
+
+ __mptcp_check_send_data_fin(sk);
+}
+
+static void __mptcp_destroy_sock(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow, *tmp;
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ LIST_HEAD(conn_list);
+
+ pr_debug("msk=%p", msk);
-cleanup:
/* be sure to always acquire the join list lock, to sync vs
* mptcp_finish_join().
*/
@@ -1986,19 +2137,74 @@ cleanup:
list_splice_init(&msk->conn_list, &conn_list);
__mptcp_clear_xmit(sk);
-
- release_sock(sk);
+ sk_stop_timer(sk, &sk->sk_timer);
+ msk->pm.status = 0;
list_for_each_entry_safe(subflow, tmp, &conn_list, node) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
- __mptcp_close_ssk(sk, ssk, subflow, timeout);
+ __mptcp_close_ssk(sk, ssk, subflow);
}
- mptcp_cancel_work(sk);
+ sk->sk_prot->destroy(sk);
- __skb_queue_purge(&sk->sk_receive_queue);
+ sk_stream_kill_queues(sk);
+ xfrm_sk_free_policy(sk);
+ sk_refcnt_debug_release(sk);
+ sock_put(sk);
+}
- sk_common_release(sk);
+static void mptcp_close(struct sock *sk, long timeout)
+{
+ struct mptcp_subflow_context *subflow;
+ bool do_cancel_work = false;
+
+ lock_sock(sk);
+ sk->sk_shutdown = SHUTDOWN_MASK;
+
+ if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
+ inet_sk_state_store(sk, TCP_CLOSE);
+ goto cleanup;
+ }
+
+ if (mptcp_close_state(sk))
+ __mptcp_wr_shutdown(sk);
+
+ sk_stream_wait_close(sk, timeout);
+
+cleanup:
+ /* orphan all the subflows */
+ inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
+ list_for_each_entry(subflow, &mptcp_sk(sk)->conn_list, node) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ bool slow, dispose_socket;
+ struct socket *sock;
+
+ slow = lock_sock_fast(ssk);
+ sock = ssk->sk_socket;
+ dispose_socket = sock && sock != sk->sk_socket;
+ sock_orphan(ssk);
+ unlock_sock_fast(ssk, slow);
+
+ /* for the outgoing subflows we additionally need to free
+ * the associated socket
+ */
+ if (dispose_socket)
+ iput(SOCK_INODE(sock));
+ }
+ sock_orphan(sk);
+
+ sock_hold(sk);
+ pr_debug("msk=%p state=%d", sk, sk->sk_state);
+ if (sk->sk_state == TCP_CLOSE) {
+ __mptcp_destroy_sock(sk);
+ do_cancel_work = true;
+ } else {
+ sk_reset_timer(sk, &sk->sk_timer, jiffies + TCP_TIMEWAIT_LEN);
+ }
+ release_sock(sk);
+ if (do_cancel_work)
+ mptcp_cancel_work(sk);
+ sock_put(sk);
}
static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
@@ -2069,7 +2275,10 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
WRITE_ONCE(msk->fully_established, false);
msk->write_seq = subflow_req->idsn + 1;
+ msk->snd_nxt = msk->write_seq;
atomic64_set(&msk->snd_una, msk->write_seq);
+ atomic64_set(&msk->wnd_end, msk->snd_nxt + req->rsk_rcv_wnd);
+
if (mp_opt->mp_capable) {
msk->can_ack = true;
msk->remote_key = mp_opt->sndr_key;
@@ -2102,6 +2311,8 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
TCP_INIT_CWND * tp->advmss);
if (msk->rcvq_space.space == 0)
msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT;
+
+ atomic64_set(&msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
}
static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
@@ -2150,6 +2361,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
newsk = new_mptcp_sock;
mptcp_copy_inaddrs(newsk, ssk);
list_add(&subflow->node, &msk->conn_list);
+ sock_hold(ssk);
mptcp_rcv_space_init(msk, ssk);
bh_unlock_sock(new_mptcp_sock);
@@ -2316,7 +2528,8 @@ static void mptcp_release_cb(struct sock *sk)
struct sock *ssk;
ssk = mptcp_subflow_recv_lookup(msk);
- if (!ssk || !schedule_work(&msk->work))
+ if (!ssk || sk->sk_state == TCP_CLOSE ||
+ !schedule_work(&msk->work))
__sock_put(sk);
}
@@ -2377,6 +2590,7 @@ void mptcp_finish_connect(struct sock *ssk)
WRITE_ONCE(msk->remote_key, subflow->remote_key);
WRITE_ONCE(msk->local_key, subflow->local_key);
WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
+ WRITE_ONCE(msk->snd_nxt, msk->write_seq);
WRITE_ONCE(msk->ack_seq, ack_seq);
WRITE_ONCE(msk->can_ack, 1);
atomic64_set(&msk->snd_una, msk->write_seq);
@@ -2395,9 +2609,9 @@ static void mptcp_sock_graft(struct sock *sk, struct socket *parent)
write_unlock_bh(&sk->sk_callback_lock);
}
-bool mptcp_finish_join(struct sock *sk)
+bool mptcp_finish_join(struct sock *ssk)
{
- struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
struct sock *parent = (void *)msk;
struct socket *parent_sock;
@@ -2418,12 +2632,14 @@ bool mptcp_finish_join(struct sock *sk)
/* active connections are already on conn_list, and we can't acquire
* msk lock here.
* use the join list lock as synchronization point and double-check
- * msk status to avoid racing with mptcp_close()
+ * msk status to avoid racing with __mptcp_destroy_sock()
*/
spin_lock_bh(&msk->join_list_lock);
ret = inet_sk_state_load(parent) == TCP_ESTABLISHED;
- if (ret && !WARN_ON_ONCE(!list_empty(&subflow->node)))
+ if (ret && !WARN_ON_ONCE(!list_empty(&subflow->node))) {
list_add_tail(&subflow->node, &msk->join_list);
+ sock_hold(ssk);
+ }
spin_unlock_bh(&msk->join_list_lock);
if (!ret)
return false;
@@ -2432,19 +2648,12 @@ bool mptcp_finish_join(struct sock *sk)
* at close time
*/
parent_sock = READ_ONCE(parent->sk_socket);
- if (parent_sock && !sk->sk_socket)
- mptcp_sock_graft(sk, parent_sock);
+ if (parent_sock && !ssk->sk_socket)
+ mptcp_sock_graft(ssk, parent_sock);
subflow->map_seq = READ_ONCE(msk->ack_seq);
return true;
}
-static bool mptcp_memory_free(const struct sock *sk, int wake)
-{
- struct mptcp_sock *msk = mptcp_sk(sk);
-
- return wake ? test_bit(MPTCP_SEND_SPACE, &msk->flags) : true;
-}
-
static struct proto mptcp_prot = {
.name = "MPTCP",
.owner = THIS_MODULE,
@@ -2465,7 +2674,6 @@ static struct proto mptcp_prot = {
.sockets_allocated = &mptcp_sockets_allocated,
.memory_allocated = &tcp_memory_allocated,
.memory_pressure = &tcp_memory_pressure,
- .stream_memory_free = mptcp_memory_free,
.sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem),
.sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem),
.sysctl_mem = sysctl_tcp_mem,
@@ -2639,6 +2847,39 @@ static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
0;
}
+static bool __mptcp_check_writeable(struct mptcp_sock *msk)
+{
+ struct sock *sk = (struct sock *)msk;
+ bool mptcp_writable;
+
+ mptcp_clean_una(sk);
+ mptcp_writable = sk_stream_is_writeable(sk);
+ if (!mptcp_writable)
+ mptcp_nospace(msk);
+
+ return mptcp_writable;
+}
+
+static __poll_t mptcp_check_writeable(struct mptcp_sock *msk)
+{
+ struct sock *sk = (struct sock *)msk;
+ __poll_t ret = 0;
+ bool slow;
+
+ if (unlikely(sk->sk_shutdown & SEND_SHUTDOWN))
+ return 0;
+
+ if (sk_stream_is_writeable(sk))
+ return EPOLLOUT | EPOLLWRNORM;
+
+ slow = lock_sock_fast(sk);
+ if (__mptcp_check_writeable(msk))
+ ret = EPOLLOUT | EPOLLWRNORM;
+
+ unlock_sock_fast(sk, slow);
+ return ret;
+}
+
static __poll_t mptcp_poll(struct file *file, struct socket *sock,
struct poll_table_struct *wait)
{
@@ -2657,8 +2898,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) {
mask |= mptcp_check_readable(msk);
- if (test_bit(MPTCP_SEND_SPACE, &msk->flags))
- mask |= EPOLLOUT | EPOLLWRNORM;
+ mask |= mptcp_check_writeable(msk);
}
if (sk->sk_shutdown & RCV_SHUTDOWN)
mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
@@ -2669,12 +2909,12 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
static int mptcp_shutdown(struct socket *sock, int how)
{
struct mptcp_sock *msk = mptcp_sk(sock->sk);
- struct mptcp_subflow_context *subflow;
+ struct sock *sk = sock->sk;
int ret = 0;
pr_debug("sk=%p, how=%d", msk, how);
- lock_sock(sock->sk);
+ lock_sock(sk);
how++;
if ((how & ~SHUTDOWN_MASK) || !how) {
@@ -2683,45 +2923,22 @@ static int mptcp_shutdown(struct socket *sock, int how)
}
if (sock->state == SS_CONNECTING) {
- if ((1 << sock->sk->sk_state) &
+ if ((1 << sk->sk_state) &
(TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))
sock->state = SS_DISCONNECTING;
else
sock->state = SS_CONNECTED;
}
- /* If we've already sent a FIN, or it's a closed state, skip this. */
- if (__mptcp_check_fallback(msk)) {
- if (how == SHUT_WR || how == SHUT_RDWR)
- inet_sk_state_store(sock->sk, TCP_FIN_WAIT1);
-
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
-
- mptcp_subflow_shutdown(sock->sk, tcp_sk, how);
- }
- } else if ((how & SEND_SHUTDOWN) &&
- ((1 << sock->sk->sk_state) &
- (TCPF_ESTABLISHED | TCPF_SYN_SENT |
- TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) &&
- mptcp_close_state(sock->sk)) {
- __mptcp_flush_join_list(msk);
-
- WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
- WRITE_ONCE(msk->snd_data_fin_enable, 1);
-
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
-
- mptcp_subflow_shutdown(sock->sk, tcp_sk, how);
- }
- }
+ sk->sk_shutdown |= how;
+ if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
+ __mptcp_wr_shutdown(sk);
/* Wake up anyone sleeping in poll. */
- sock->sk->sk_state_change(sock->sk);
+ sk->sk_state_change(sk);
out_unlock:
- release_sock(sock->sk);
+ release_sock(sk);
return ret;
}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 13ab89dc1914..b4c8dbe9236b 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -86,11 +86,19 @@
/* MPTCP socket flags */
#define MPTCP_DATA_READY 0
-#define MPTCP_SEND_SPACE 1
+#define MPTCP_NOSPACE 1
#define MPTCP_WORK_RTX 2
#define MPTCP_WORK_EOF 3
#define MPTCP_FALLBACK_DONE 4
#define MPTCP_WORK_CLOSE_SUBFLOW 5
+#define MPTCP_WORKER_RUNNING 6
+
+static inline bool before64(__u64 seq1, __u64 seq2)
+{
+ return (__s64)(seq1 - seq2) < 0;
+}
+
+#define after64(seq2, seq1) before64(seq1, seq2)
struct mptcp_options_received {
u64 sndr_key;
@@ -187,9 +195,10 @@ struct mptcp_pm_data {
struct mptcp_data_frag {
struct list_head list;
u64 data_seq;
- int data_len;
- int offset;
- int overhead;
+ u16 data_len;
+ u16 offset;
+ u16 overhead;
+ u16 already_sent;
struct page *page;
};
@@ -200,11 +209,13 @@ struct mptcp_sock {
u64 local_key;
u64 remote_key;
u64 write_seq;
+ u64 snd_nxt;
u64 ack_seq;
u64 rcv_data_fin_seq;
struct sock *last_snd;
int snd_burst;
atomic64_t snd_una;
+ atomic64_t wnd_end;
unsigned long timer_ival;
u32 token;
unsigned long flags;
@@ -219,6 +230,7 @@ struct mptcp_sock {
struct rb_root out_of_order_queue;
struct list_head conn_list;
struct list_head rtx_queue;
+ struct mptcp_data_frag *first_pending;
struct list_head join_list;
struct skb_ext *cached_ext; /* for the next sendmsg */
struct socket *subflow; /* outgoing connect/listener/!mp_capable */
@@ -240,11 +252,41 @@ static inline struct mptcp_sock *mptcp_sk(const struct sock *sk)
return (struct mptcp_sock *)sk;
}
+static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
+{
+ const struct mptcp_sock *msk = mptcp_sk(sk);
+
+ return READ_ONCE(msk->first_pending);
+}
+
+static inline struct mptcp_data_frag *mptcp_send_next(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct mptcp_data_frag *cur;
+
+ cur = msk->first_pending;
+ return list_is_last(&cur->list, &msk->rtx_queue) ? NULL :
+ list_next_entry(cur, list);
+}
+
+static inline struct mptcp_data_frag *mptcp_pending_tail(const struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ if (!msk->first_pending)
+ return NULL;
+
+ if (WARN_ON_ONCE(list_empty(&msk->rtx_queue)))
+ return NULL;
+
+ return list_last_entry(&msk->rtx_queue, struct mptcp_data_frag, list);
+}
+
static inline struct mptcp_data_frag *mptcp_rtx_tail(const struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- if (list_empty(&msk->rtx_queue))
+ if (!before64(msk->snd_nxt, atomic64_read(&msk->snd_una)))
return NULL;
return list_last_entry(&msk->rtx_queue, struct mptcp_data_frag, list);
@@ -312,7 +354,8 @@ struct mptcp_subflow_context {
mpc_map : 1,
backup : 1,
rx_eof : 1,
- can_ack : 1; /* only after processing the remote a key */
+ can_ack : 1, /* only after processing the remote a key */
+ disposable : 1; /* ctx can be free at ulp release time */
enum mptcp_data_avail data_avail;
u32 remote_nonce;
u64 thmac;
@@ -362,14 +405,14 @@ mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow)
}
int mptcp_is_enabled(struct net *net);
+unsigned int mptcp_get_add_addr_timeout(struct net *net);
void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
struct mptcp_options_received *mp_opt);
bool mptcp_subflow_data_available(struct sock *sk);
void __init mptcp_subflow_init(void);
void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how);
void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
- struct mptcp_subflow_context *subflow,
- long timeout);
+ struct mptcp_subflow_context *subflow);
void mptcp_subflow_reset(struct sock *ssk);
/* called with sk socket lock held */
@@ -407,9 +450,16 @@ static inline bool mptcp_is_fully_established(struct sock *sk)
void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk);
void mptcp_data_ready(struct sock *sk, struct sock *ssk);
bool mptcp_finish_join(struct sock *sk);
+bool mptcp_schedule_work(struct sock *sk);
void mptcp_data_acked(struct sock *sk);
void mptcp_subflow_eof(struct sock *sk);
bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit);
+static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk)
+{
+ return READ_ONCE(msk->snd_data_fin_enable) &&
+ READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt);
+}
+
void mptcp_destroy_common(struct mptcp_sock *msk);
void __init mptcp_token_init(void);
@@ -494,13 +544,6 @@ static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb)
return (struct mptcp_ext *)skb_ext_find(skb, SKB_EXT_MPTCP);
}
-static inline bool before64(__u64 seq1, __u64 seq2)
-{
- return (__s64)(seq1 - seq2) < 0;
-}
-
-#define after64(seq2, seq1) before64(seq1, seq2)
-
void mptcp_diag_subflow_init(struct tcp_ulp_ops *ops);
static inline bool __mptcp_check_fallback(const struct mptcp_sock *msk)
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index ac4a1fe3550b..794259789194 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -997,17 +997,16 @@ static void subflow_data_ready(struct sock *sk)
static void subflow_write_space(struct sock *sk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct socket *sock = READ_ONCE(sk->sk_socket);
struct sock *parent = subflow->conn;
if (!sk_stream_is_writeable(sk))
return;
- if (sk_stream_is_writeable(parent)) {
- set_bit(MPTCP_SEND_SPACE, &mptcp_sk(parent)->flags);
- smp_mb__after_atomic();
- /* set SEND_SPACE before sk_stream_write_space clears NOSPACE */
- sk_stream_write_space(parent);
- }
+ if (sock && sk_stream_is_writeable(parent))
+ clear_bit(SOCK_NOSPACE, &sock->flags);
+
+ sk_stream_write_space(parent);
}
static struct inet_connection_sock_af_ops *
@@ -1125,6 +1124,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
if (err && err != -EINPROGRESS)
goto failed;
+ sock_hold(ssk);
spin_lock_bh(&msk->join_list_lock);
list_add_tail(&subflow->node, &msk->join_list);
spin_unlock_bh(&msk->join_list_lock);
@@ -1132,6 +1132,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
return err;
failed:
+ subflow->disposable = 1;
sock_release(sf);
return err;
}
@@ -1254,7 +1255,6 @@ static void subflow_state_change(struct sock *sk)
mptcp_data_ready(parent, sk);
if (__mptcp_check_fallback(mptcp_sk(parent)) &&
- !(parent->sk_shutdown & RCV_SHUTDOWN) &&
!subflow->rx_eof && subflow_is_done(sk)) {
subflow->rx_eof = 1;
mptcp_subflow_eof(parent);
@@ -1297,17 +1297,26 @@ out:
return err;
}
-static void subflow_ulp_release(struct sock *sk)
+static void subflow_ulp_release(struct sock *ssk)
{
- struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(sk);
+ struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk);
+ bool release = true;
+ struct sock *sk;
if (!ctx)
return;
- if (ctx->conn)
- sock_put(ctx->conn);
+ sk = ctx->conn;
+ if (sk) {
+ /* if the msk has been orphaned, keep the ctx
+ * alive, will be freed by mptcp_done()
+ */
+ release = ctx->disposable;
+ sock_put(sk);
+ }
- kfree_rcu(ctx, rcu);
+ if (release)
+ kfree_rcu(ctx, rcu);
}
static void subflow_ulp_clone(const struct request_sock *req,
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 52370211e46b..49fbef0d99be 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -682,6 +682,16 @@ config NFT_FIB_NETDEV
The lookup will be delegated to the IPv4 or IPv6 FIB depending
on the protocol of the packet.
+config NFT_REJECT_NETDEV
+ depends on NFT_REJECT_IPV4
+ depends on NFT_REJECT_IPV6
+ tristate "Netfilter nf_tables netdev REJECT support"
+ help
+ This option enables the REJECT support from the netdev table.
+ The return packet generation will be delegated to the IPv4
+ or IPv6 ICMP or TCP RST implementation depending on the
+ protocol of the packet.
+
endif # NF_TABLES_NETDEV
endif # NF_TABLES
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 0e0ded87e27b..33da7bf1b68e 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -101,6 +101,7 @@ obj-$(CONFIG_NFT_QUEUE) += nft_queue.o
obj-$(CONFIG_NFT_QUOTA) += nft_quota.o
obj-$(CONFIG_NFT_REJECT) += nft_reject.o
obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o
+obj-$(CONFIG_NFT_REJECT_NETDEV) += nft_reject_netdev.o
obj-$(CONFIG_NFT_TUNNEL) += nft_tunnel.o
obj-$(CONFIG_NFT_COUNTER) += nft_counter.o
obj-$(CONFIG_NFT_LOG) += nft_log.o
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 7cff6e5e7445..c7eaa3776238 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1110,6 +1110,8 @@ static int ip_set_create(struct net *net, struct sock *ctnl,
ret = -IPSET_ERR_PROTOCOL;
goto put_out;
}
+ /* Set create flags depending on the type revision */
+ set->flags |= set->type->create_flags[revision];
ret = set->type->create(net, set, tb, flags);
if (ret != 0)
@@ -1240,10 +1242,12 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl,
/* Modified by ip_set_destroy() only, which is serialized */
inst->is_destroyed = false;
} else {
+ u32 flags = flag_exist(nlh);
s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]),
&i);
if (!s) {
- ret = -ENOENT;
+ if (!(flags & IPSET_FLAG_EXIST))
+ ret = -ENOENT;
goto out;
} else if (s->ref || s->ref_netlink) {
ret = -IPSET_ERR_BUSY;
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 521e970be402..5f1208ad049e 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -37,18 +37,18 @@
*/
/* Number of elements to store in an initial array block */
-#define AHASH_INIT_SIZE 4
+#define AHASH_INIT_SIZE 2
/* Max number of elements to store in an array block */
-#define AHASH_MAX_SIZE (3 * AHASH_INIT_SIZE)
+#define AHASH_MAX_SIZE (6 * AHASH_INIT_SIZE)
/* Max muber of elements in the array block when tuned */
#define AHASH_MAX_TUNED 64
+#define AHASH_MAX(h) ((h)->bucketsize)
+
/* Max number of elements can be tuned */
#ifdef IP_SET_HASH_WITH_MULTI
-#define AHASH_MAX(h) ((h)->ahash_max)
-
static u8
-tune_ahash_max(u8 curr, u32 multi)
+tune_bucketsize(u8 curr, u32 multi)
{
u32 n;
@@ -61,12 +61,10 @@ tune_ahash_max(u8 curr, u32 multi)
*/
return n > curr && n <= AHASH_MAX_TUNED ? n : curr;
}
-
-#define TUNE_AHASH_MAX(h, multi) \
- ((h)->ahash_max = tune_ahash_max((h)->ahash_max, multi))
+#define TUNE_BUCKETSIZE(h, multi) \
+ ((h)->bucketsize = tune_bucketsize((h)->bucketsize, multi))
#else
-#define AHASH_MAX(h) AHASH_MAX_SIZE
-#define TUNE_AHASH_MAX(h, multi)
+#define TUNE_BUCKETSIZE(h, multi)
#endif
/* A hash bucket */
@@ -321,9 +319,7 @@ struct htype {
#ifdef IP_SET_HASH_WITH_MARKMASK
u32 markmask; /* markmask value for mark mask to store */
#endif
-#ifdef IP_SET_HASH_WITH_MULTI
- u8 ahash_max; /* max elements in an array block */
-#endif
+ u8 bucketsize; /* max elements in an array block */
#ifdef IP_SET_HASH_WITH_NETMASK
u8 netmask; /* netmask value for subnets to store */
#endif
@@ -950,7 +946,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
goto set_full;
/* Create a new slot */
if (n->pos >= n->size) {
- TUNE_AHASH_MAX(h, multi);
+ TUNE_BUCKETSIZE(h, multi);
if (n->size >= AHASH_MAX(h)) {
/* Trigger rehashing */
mtype_data_next(&h->next, d);
@@ -1305,6 +1301,11 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask))
goto nla_put_failure;
#endif
+ if (set->flags & IPSET_CREATE_FLAG_BUCKETSIZE) {
+ if (nla_put_u8(skb, IPSET_ATTR_BUCKETSIZE, h->bucketsize) ||
+ nla_put_net32(skb, IPSET_ATTR_INITVAL, htonl(h->initval)))
+ goto nla_put_failure;
+ }
if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) ||
nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) ||
nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements)))
@@ -1547,8 +1548,20 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
#ifdef IP_SET_HASH_WITH_MARKMASK
h->markmask = markmask;
#endif
- get_random_bytes(&h->initval, sizeof(h->initval));
-
+ if (tb[IPSET_ATTR_INITVAL])
+ h->initval = ntohl(nla_get_be32(tb[IPSET_ATTR_INITVAL]));
+ else
+ get_random_bytes(&h->initval, sizeof(h->initval));
+ h->bucketsize = AHASH_MAX_SIZE;
+ if (tb[IPSET_ATTR_BUCKETSIZE]) {
+ h->bucketsize = nla_get_u8(tb[IPSET_ATTR_BUCKETSIZE]);
+ if (h->bucketsize < AHASH_INIT_SIZE)
+ h->bucketsize = AHASH_INIT_SIZE;
+ else if (h->bucketsize > AHASH_MAX_SIZE)
+ h->bucketsize = AHASH_MAX_SIZE;
+ else if (h->bucketsize % 2)
+ h->bucketsize += 1;
+ }
t->htable_bits = hbits;
t->maxelem = h->maxelem / ahash_numof_locks(hbits);
RCU_INIT_POINTER(h->table, t);
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index 5d6d68eaf6a9..d1bef23fd4f5 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -23,7 +23,8 @@
/* 1 Counters support */
/* 2 Comments support */
/* 3 Forceadd support */
-#define IPSET_TYPE_REV_MAX 4 /* skbinfo support */
+/* 4 skbinfo support */
+#define IPSET_TYPE_REV_MAX 5 /* bucketsize, initval support */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -277,11 +278,13 @@ static struct ip_set_type hash_ip_type __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_ip_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_NETMASK] = { .type = NLA_U8 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c
index eceb7bc4a93a..467c59a83c0a 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmac.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmac.c
@@ -23,7 +23,7 @@
#include <linux/netfilter/ipset/ip_set_hash.h>
#define IPSET_TYPE_REV_MIN 0
-#define IPSET_TYPE_REV_MAX 0
+#define IPSET_TYPE_REV_MAX 1 /* bucketsize, initval support */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Tomasz Chilinski <tomasz.chilinski@chilan.com>");
@@ -268,11 +268,13 @@ static struct ip_set_type hash_ipmac_type __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_ipmac_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c
index aba1df617d6e..18346d18aa16 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmark.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmark.c
@@ -21,7 +21,8 @@
#define IPSET_TYPE_REV_MIN 0
/* 1 Forceadd support */
-#define IPSET_TYPE_REV_MAX 2 /* skbinfo support */
+/* 2 skbinfo support */
+#define IPSET_TYPE_REV_MAX 3 /* bucketsize, initval support */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Vytas Dauksa <vytas.dauksa@smoothwall.net>");
@@ -274,12 +275,14 @@ static struct ip_set_type hash_ipmark_type __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_ipmark_create,
.create_policy = {
[IPSET_ATTR_MARKMASK] = { .type = NLA_U32 },
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index 1ff228717e29..e1ca11196515 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -25,7 +25,8 @@
/* 2 Counters support added */
/* 3 Comments support added */
/* 4 Forceadd support added */
-#define IPSET_TYPE_REV_MAX 5 /* skbinfo support added */
+/* 5 skbinfo support added */
+#define IPSET_TYPE_REV_MAX 6 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -341,11 +342,13 @@ static struct ip_set_type hash_ipport_type __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_ipport_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_PROTO] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index fa88afd812fa..ab179e064597 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -25,7 +25,8 @@
/* 2 Counters support added */
/* 3 Comments support added */
/* 4 Forceadd support added */
-#define IPSET_TYPE_REV_MAX 5 /* skbinfo support added */
+/* 5 skbinfo support added */
+#define IPSET_TYPE_REV_MAX 6 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -356,11 +357,13 @@ static struct ip_set_type hash_ipportip_type __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_ipportip_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index eef6ecfcb409..8f075b44cf64 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -27,7 +27,8 @@
/* 4 Counters support added */
/* 5 Comments support added */
/* 6 Forceadd support added */
-#define IPSET_TYPE_REV_MAX 7 /* skbinfo support added */
+/* 7 skbinfo support added */
+#define IPSET_TYPE_REV_MAX 8 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -513,11 +514,13 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_ipportnet_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_mac.c b/net/netfilter/ipset/ip_set_hash_mac.c
index 0b61593165ef..718814730acf 100644
--- a/net/netfilter/ipset/ip_set_hash_mac.c
+++ b/net/netfilter/ipset/ip_set_hash_mac.c
@@ -16,7 +16,7 @@
#include <linux/netfilter/ipset/ip_set_hash.h>
#define IPSET_TYPE_REV_MIN 0
-#define IPSET_TYPE_REV_MAX 0
+#define IPSET_TYPE_REV_MAX 1 /* bucketsize, initval support */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -125,11 +125,13 @@ static struct ip_set_type hash_mac_type __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_mac_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 136cf0781d3a..c1a11f041ac6 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -24,7 +24,8 @@
/* 3 Counters support added */
/* 4 Comments support added */
/* 5 Forceadd support added */
-#define IPSET_TYPE_REV_MAX 6 /* skbinfo mapping support added */
+/* 6 skbinfo support added */
+#define IPSET_TYPE_REV_MAX 7 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -354,11 +355,13 @@ static struct ip_set_type hash_net_type __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_net_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index be5e95a0d876..ddd51c2e1cb3 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -26,7 +26,8 @@
/* 4 Comments support added */
/* 5 Forceadd support added */
/* 6 skbinfo support added */
-#define IPSET_TYPE_REV_MAX 7 /* interface wildcard support added */
+/* 7 interface wildcard support added */
+#define IPSET_TYPE_REV_MAX 8 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -225,7 +226,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
if (e.cidr > HOST_MASK)
return -IPSET_ERR_INVALID_CIDR;
}
- nla_strlcpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
+ nla_strscpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
if (tb[IPSET_ATTR_CADT_FLAGS]) {
u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
@@ -442,7 +443,7 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[],
ip6_netmask(&e.ip, e.cidr);
- nla_strlcpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
+ nla_strscpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
if (tb[IPSET_ATTR_CADT_FLAGS]) {
u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
@@ -470,11 +471,13 @@ static struct ip_set_type hash_netiface_type __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_netiface_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_PROTO] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
index da4ef910b12d..6532f0505e66 100644
--- a/net/netfilter/ipset/ip_set_hash_netnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -22,7 +22,8 @@
#define IPSET_TYPE_REV_MIN 0
/* 1 Forceadd support added */
-#define IPSET_TYPE_REV_MAX 2 /* skbinfo support added */
+/* 2 skbinfo support added */
+#define IPSET_TYPE_REV_MAX 3 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
@@ -459,11 +460,13 @@ static struct ip_set_type hash_netnet_type __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_netnet_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index 34448df80fb9..ec1564a1cb5a 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -26,7 +26,8 @@
/* 4 Counters support added */
/* 5 Comments support added */
/* 6 Forceadd support added */
-#define IPSET_TYPE_REV_MAX 7 /* skbinfo support added */
+/* 7 skbinfo support added */
+#define IPSET_TYPE_REV_MAX 8 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -460,11 +461,13 @@ static struct ip_set_type hash_netport_type __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_netport_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_PROTO] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index 934c1712cba8..0e91d1e82f1c 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -23,7 +23,8 @@
#define IPSET_TYPE_REV_MIN 0
/* 0 Comments support added */
/* 1 Forceadd support added */
-#define IPSET_TYPE_REV_MAX 2 /* skbinfo support added */
+/* 2 skbinfo support added */
+#define IPSET_TYPE_REV_MAX 3 /* bucketsize, initval support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
@@ -558,11 +559,13 @@ static struct ip_set_type hash_netportnet_type __read_mostly = {
.family = NFPROTO_UNSPEC,
.revision_min = IPSET_TYPE_REV_MIN,
.revision_max = IPSET_TYPE_REV_MAX,
+ .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
.create = hash_netportnet_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
[IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
- [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_INITVAL] = { .type = NLA_U32 },
+ [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 0f58e98542be..65aa98fc5eb6 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -581,7 +581,8 @@ struct nft_module_request {
};
#ifdef CONFIG_MODULES
-static int nft_request_module(struct net *net, const char *fmt, ...)
+static __printf(2, 3) int nft_request_module(struct net *net, const char *fmt,
+ ...)
{
char module_name[MODULE_NAME_LEN];
struct nft_module_request *req;
@@ -1281,7 +1282,7 @@ static struct nft_chain *nft_chain_lookup(struct net *net,
if (nla == NULL)
return ERR_PTR(-EINVAL);
- nla_strlcpy(search, nla, sizeof(search));
+ nla_strscpy(search, nla, sizeof(search));
WARN_ON(!rcu_read_lock_held() &&
!lockdep_commit_lock_is_held(net));
@@ -1721,7 +1722,7 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net,
goto err_hook_alloc;
}
- nla_strlcpy(ifname, attr, IFNAMSIZ);
+ nla_strscpy(ifname, attr, IFNAMSIZ);
dev = __dev_get_by_name(net, ifname);
if (!dev) {
err = -ENOENT;
@@ -5734,7 +5735,7 @@ struct nft_object *nft_obj_lookup(const struct net *net,
struct rhlist_head *tmp, *list;
struct nft_object *obj;
- nla_strlcpy(search, nla, sizeof(search));
+ nla_strscpy(search, nla, sizeof(search));
k.name = search;
WARN_ON_ONCE(!rcu_read_lock_held() &&
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index 5bfec829c12f..5e511df8d709 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -112,7 +112,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl,
nfacct->flags = flags;
}
- nla_strlcpy(nfacct->name, tb[NFACCT_NAME], NFACCT_NAME_MAX);
+ nla_strscpy(nfacct->name, tb[NFACCT_NAME], NFACCT_NAME_MAX);
if (tb[NFACCT_BYTES]) {
atomic64_set(&nfacct->bytes,
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 5b0d0a77379c..0f94fce1d3ed 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -146,7 +146,7 @@ nfnl_cthelper_expect_policy(struct nf_conntrack_expect_policy *expect_policy,
!tb[NFCTH_POLICY_EXPECT_TIMEOUT])
return -EINVAL;
- nla_strlcpy(expect_policy->name,
+ nla_strscpy(expect_policy->name,
tb[NFCTH_POLICY_NAME], NF_CT_HELPER_NAME_LEN);
expect_policy->max_expected =
ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
@@ -233,7 +233,7 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
if (ret < 0)
goto err1;
- nla_strlcpy(helper->name,
+ nla_strscpy(helper->name,
tb[NFCTH_NAME], NF_CT_HELPER_NAME_LEN);
size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
if (size > sizeof_field(struct nf_conn_help, data)) {
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 322bd674963e..a8c4d442231c 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -990,7 +990,7 @@ static int nft_ct_helper_obj_init(const struct nft_ctx *ctx,
if (!priv->l4proto)
return -ENOENT;
- nla_strlcpy(name, tb[NFTA_CT_HELPER_NAME], sizeof(name));
+ nla_strscpy(name, tb[NFTA_CT_HELPER_NAME], sizeof(name));
if (tb[NFTA_CT_HELPER_L3PROTO])
family = ntohs(nla_get_be16(tb[NFTA_CT_HELPER_L3PROTO]));
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index 57899454a530..a06a46b039c5 100644
--- a/net/netfilter/nft_log.c
+++ b/net/netfilter/nft_log.c
@@ -152,7 +152,7 @@ static int nft_log_init(const struct nft_ctx *ctx,
priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL);
if (priv->prefix == NULL)
return -ENOMEM;
- nla_strlcpy(priv->prefix, nla, nla_len(nla) + 1);
+ nla_strscpy(priv->prefix, nla, nla_len(nla) + 1);
} else {
priv->prefix = (char *)nft_log_null_prefix;
}
diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c
index 61fb7e8afbf0..927ff8459bd9 100644
--- a/net/netfilter/nft_reject.c
+++ b/net/netfilter/nft_reject.c
@@ -40,6 +40,7 @@ int nft_reject_init(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
struct nft_reject *priv = nft_expr_priv(expr);
+ int icmp_code;
if (tb[NFTA_REJECT_TYPE] == NULL)
return -EINVAL;
@@ -47,9 +48,17 @@ int nft_reject_init(const struct nft_ctx *ctx,
priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
switch (priv->type) {
case NFT_REJECT_ICMP_UNREACH:
+ case NFT_REJECT_ICMPX_UNREACH:
if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
return -EINVAL;
- priv->icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
+
+ icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
+ if (priv->type == NFT_REJECT_ICMPX_UNREACH &&
+ icmp_code > NFT_REJECT_ICMPX_MAX)
+ return -EINVAL;
+
+ priv->icmp_code = icmp_code;
+ break;
case NFT_REJECT_TCP_RST:
break;
default:
@@ -69,6 +78,7 @@ int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
switch (priv->type) {
case NFT_REJECT_ICMP_UNREACH:
+ case NFT_REJECT_ICMPX_UNREACH:
if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
goto nla_put_failure;
break;
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
index cf8f2646e93c..32f3ea398ddf 100644
--- a/net/netfilter/nft_reject_inet.c
+++ b/net/netfilter/nft_reject_inet.c
@@ -58,60 +58,16 @@ static void nft_reject_inet_eval(const struct nft_expr *expr,
regs->verdict.code = NF_DROP;
}
-static int nft_reject_inet_init(const struct nft_ctx *ctx,
- const struct nft_expr *expr,
- const struct nlattr * const tb[])
+static int nft_reject_inet_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data)
{
- struct nft_reject *priv = nft_expr_priv(expr);
- int icmp_code;
-
- if (tb[NFTA_REJECT_TYPE] == NULL)
- return -EINVAL;
-
- priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
- switch (priv->type) {
- case NFT_REJECT_ICMP_UNREACH:
- case NFT_REJECT_ICMPX_UNREACH:
- if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
- return -EINVAL;
-
- icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
- if (priv->type == NFT_REJECT_ICMPX_UNREACH &&
- icmp_code > NFT_REJECT_ICMPX_MAX)
- return -EINVAL;
-
- priv->icmp_code = icmp_code;
- break;
- case NFT_REJECT_TCP_RST:
- break;
- default:
- return -EINVAL;
- }
- return 0;
-}
-
-static int nft_reject_inet_dump(struct sk_buff *skb,
- const struct nft_expr *expr)
-{
- const struct nft_reject *priv = nft_expr_priv(expr);
-
- if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type)))
- goto nla_put_failure;
-
- switch (priv->type) {
- case NFT_REJECT_ICMP_UNREACH:
- case NFT_REJECT_ICMPX_UNREACH:
- if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
- goto nla_put_failure;
- break;
- default:
- break;
- }
-
- return 0;
-
-nla_put_failure:
- return -1;
+ return nft_chain_validate_hooks(ctx->chain,
+ (1 << NF_INET_LOCAL_IN) |
+ (1 << NF_INET_FORWARD) |
+ (1 << NF_INET_LOCAL_OUT) |
+ (1 << NF_INET_PRE_ROUTING) |
+ (1 << NF_INET_INGRESS));
}
static struct nft_expr_type nft_reject_inet_type;
@@ -119,9 +75,9 @@ static const struct nft_expr_ops nft_reject_inet_ops = {
.type = &nft_reject_inet_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_reject)),
.eval = nft_reject_inet_eval,
- .init = nft_reject_inet_init,
- .dump = nft_reject_inet_dump,
- .validate = nft_reject_validate,
+ .init = nft_reject_init,
+ .dump = nft_reject_dump,
+ .validate = nft_reject_inet_validate,
};
static struct nft_expr_type nft_reject_inet_type __read_mostly = {
diff --git a/net/netfilter/nft_reject_netdev.c b/net/netfilter/nft_reject_netdev.c
new file mode 100644
index 000000000000..d89f68754f42
--- /dev/null
+++ b/net/netfilter/nft_reject_netdev.c
@@ -0,0 +1,189 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Laura Garcia Liebana <nevola@gmail.com>
+ * Copyright (c) 2020 Jose M. Guisado <guigom@riseup.net>
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_reject.h>
+#include <net/netfilter/ipv4/nf_reject.h>
+#include <net/netfilter/ipv6/nf_reject.h>
+
+static void nft_reject_queue_xmit(struct sk_buff *nskb, struct sk_buff *oldskb)
+{
+ dev_hard_header(nskb, nskb->dev, ntohs(oldskb->protocol),
+ eth_hdr(oldskb)->h_source, eth_hdr(oldskb)->h_dest,
+ nskb->len);
+ dev_queue_xmit(nskb);
+}
+
+static void nft_reject_netdev_send_v4_tcp_reset(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook)
+{
+ struct sk_buff *nskb;
+
+ nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, dev, hook);
+ if (!nskb)
+ return;
+
+ nft_reject_queue_xmit(nskb, oldskb);
+}
+
+static void nft_reject_netdev_send_v4_unreach(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook, u8 code)
+{
+ struct sk_buff *nskb;
+
+ nskb = nf_reject_skb_v4_unreach(net, oldskb, dev, hook, code);
+ if (!nskb)
+ return;
+
+ nft_reject_queue_xmit(nskb, oldskb);
+}
+
+static void nft_reject_netdev_send_v6_tcp_reset(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook)
+{
+ struct sk_buff *nskb;
+
+ nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, dev, hook);
+ if (!nskb)
+ return;
+
+ nft_reject_queue_xmit(nskb, oldskb);
+}
+
+
+static void nft_reject_netdev_send_v6_unreach(struct net *net,
+ struct sk_buff *oldskb,
+ const struct net_device *dev,
+ int hook, u8 code)
+{
+ struct sk_buff *nskb;
+
+ nskb = nf_reject_skb_v6_unreach(net, oldskb, dev, hook, code);
+ if (!nskb)
+ return;
+
+ nft_reject_queue_xmit(nskb, oldskb);
+}
+
+static void nft_reject_netdev_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ struct ethhdr *eth = eth_hdr(pkt->skb);
+ struct nft_reject *priv = nft_expr_priv(expr);
+ const unsigned char *dest = eth->h_dest;
+
+ if (is_broadcast_ether_addr(dest) ||
+ is_multicast_ether_addr(dest))
+ goto out;
+
+ switch (eth->h_proto) {
+ case htons(ETH_P_IP):
+ switch (priv->type) {
+ case NFT_REJECT_ICMP_UNREACH:
+ nft_reject_netdev_send_v4_unreach(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt),
+ priv->icmp_code);
+ break;
+ case NFT_REJECT_TCP_RST:
+ nft_reject_netdev_send_v4_tcp_reset(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt));
+ break;
+ case NFT_REJECT_ICMPX_UNREACH:
+ nft_reject_netdev_send_v4_unreach(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt),
+ nft_reject_icmp_code(priv->icmp_code));
+ break;
+ }
+ break;
+ case htons(ETH_P_IPV6):
+ switch (priv->type) {
+ case NFT_REJECT_ICMP_UNREACH:
+ nft_reject_netdev_send_v6_unreach(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt),
+ priv->icmp_code);
+ break;
+ case NFT_REJECT_TCP_RST:
+ nft_reject_netdev_send_v6_tcp_reset(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt));
+ break;
+ case NFT_REJECT_ICMPX_UNREACH:
+ nft_reject_netdev_send_v6_unreach(nft_net(pkt), pkt->skb,
+ nft_in(pkt),
+ nft_hook(pkt),
+ nft_reject_icmpv6_code(priv->icmp_code));
+ break;
+ }
+ break;
+ default:
+ /* No explicit way to reject this protocol, drop it. */
+ break;
+ }
+out:
+ regs->verdict.code = NF_DROP;
+}
+
+static int nft_reject_netdev_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data)
+{
+ return nft_chain_validate_hooks(ctx->chain, (1 << NF_NETDEV_INGRESS));
+}
+
+static struct nft_expr_type nft_reject_netdev_type;
+static const struct nft_expr_ops nft_reject_netdev_ops = {
+ .type = &nft_reject_netdev_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+ .eval = nft_reject_netdev_eval,
+ .init = nft_reject_init,
+ .dump = nft_reject_dump,
+ .validate = nft_reject_netdev_validate,
+};
+
+static struct nft_expr_type nft_reject_netdev_type __read_mostly = {
+ .family = NFPROTO_NETDEV,
+ .name = "reject",
+ .ops = &nft_reject_netdev_ops,
+ .policy = nft_reject_policy,
+ .maxattr = NFTA_REJECT_MAX,
+ .owner = THIS_MODULE,
+};
+
+static int __init nft_reject_netdev_module_init(void)
+{
+ return nft_register_expr(&nft_reject_netdev_type);
+}
+
+static void __exit nft_reject_netdev_module_exit(void)
+{
+ nft_unregister_expr(&nft_reject_netdev_type);
+}
+
+module_init(nft_reject_netdev_module_init);
+module_exit(nft_reject_netdev_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Laura Garcia Liebana <nevola@gmail.com>");
+MODULE_AUTHOR("Jose M. Guisado <guigom@riseup.net>");
+MODULE_DESCRIPTION("Reject packets from netdev via nftables");
+MODULE_ALIAS_NFT_AF_EXPR(5, "reject");
diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c
index 4e62f2ad3575..f28c8947c730 100644
--- a/net/netlabel/netlabel_calipso.c
+++ b/net/netlabel/netlabel_calipso.c
@@ -366,6 +366,7 @@ static const struct netlbl_calipso_ops *calipso_ops;
/**
* netlbl_calipso_ops_register - Register the CALIPSO operations
+ * @ops: ops to register
*
* Description:
* Register the CALIPSO packet engine operations.
diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c
index eb1d66d20afb..df1b41ed73fd 100644
--- a/net/netlabel/netlabel_mgmt.c
+++ b/net/netlabel/netlabel_mgmt.c
@@ -95,7 +95,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
ret_val = -ENOMEM;
goto add_free_entry;
}
- nla_strlcpy(entry->domain,
+ nla_strscpy(entry->domain,
info->attrs[NLBL_MGMT_A_DOMAIN], tmp_size);
}
diff --git a/net/nfc/core.c b/net/nfc/core.c
index eb377f87bcae..573c80c6ff7a 100644
--- a/net/nfc/core.c
+++ b/net/nfc/core.c
@@ -189,7 +189,8 @@ static const struct rfkill_ops nfc_rfkill_ops = {
* nfc_start_poll - start polling for nfc targets
*
* @dev: The nfc device that must start polling
- * @protocols: bitset of nfc protocols that must be used for polling
+ * @im_protocols: bitset of nfc initiator protocols to be used for polling
+ * @tm_protocols: bitset of nfc transport protocols to be used for polling
*
* The device remains polling for targets until a target is found or
* the nfc_stop_poll function is called.
@@ -436,6 +437,7 @@ error:
*
* @dev: The nfc device that found the target
* @target_idx: index of the target that must be deactivated
+ * @mode: idle or sleep?
*/
int nfc_deactivate_target(struct nfc_dev *dev, u32 target_idx, u8 mode)
{
@@ -703,7 +705,11 @@ EXPORT_SYMBOL(nfc_tm_deactivated);
/**
* nfc_alloc_send_skb - allocate a skb for data exchange responses
*
+ * @dev: device sending the response
+ * @sk: socket sending the response
+ * @flags: MSG_DONTWAIT flag
* @size: size to allocate
+ * @err: pointer to memory to store the error code
*/
struct sk_buff *nfc_alloc_send_skb(struct nfc_dev *dev, struct sock *sk,
unsigned int flags, unsigned int size,
@@ -1039,6 +1045,8 @@ struct nfc_dev *nfc_get_device(unsigned int idx)
*
* @ops: device operations
* @supported_protocols: NFC protocols supported by the device
+ * @tx_headroom: reserved space at beginning of skb
+ * @tx_tailroom: reserved space at end of skb
*/
struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops,
u32 supported_protocols,
diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c
index e3599ed4a7a8..da7e2112771f 100644
--- a/net/nfc/digital_core.c
+++ b/net/nfc/digital_core.c
@@ -458,6 +458,9 @@ static void digital_add_poll_tech(struct nfc_digital_dev *ddev, u8 rf_tech,
/**
* start_poll operation
+ * @nfc_dev: device to be polled
+ * @im_protocols: bitset of nfc initiator protocols to be used for polling
+ * @tm_protocols: bitset of nfc transport protocols to be used for polling
*
* For every supported protocol, the corresponding polling function is added
* to the table of polling technologies (ddev->poll_techs[]) using
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 741da8f81c2b..4953ee5146e1 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -1112,6 +1112,8 @@ static struct nfc_ops nci_nfc_ops = {
*
* @ops: device operations
* @supported_protocols: NFC protocols supported by the device
+ * @tx_headroom: Reserved space at beginning of skb
+ * @tx_tailroom: Reserved space at end of skb
*/
struct nci_dev *nci_allocate_device(struct nci_ops *ops,
__u32 supported_protocols,
diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c
index c18e76d6d8ba..6b275a387a92 100644
--- a/net/nfc/nci/hci.c
+++ b/net/nfc/nci/hci.c
@@ -363,16 +363,13 @@ exit:
}
static void nci_hci_resp_received(struct nci_dev *ndev, u8 pipe,
- u8 result, struct sk_buff *skb)
+ struct sk_buff *skb)
{
struct nci_conn_info *conn_info;
- u8 status = result;
conn_info = ndev->hci_dev->conn_info;
- if (!conn_info) {
- status = NCI_STATUS_REJECTED;
+ if (!conn_info)
goto exit;
- }
conn_info->rx_skb = skb;
@@ -388,7 +385,7 @@ static void nci_hci_hcp_message_rx(struct nci_dev *ndev, u8 pipe,
{
switch (type) {
case NCI_HCI_HCP_RESPONSE:
- nci_hci_resp_received(ndev, pipe, instruction, skb);
+ nci_hci_resp_received(ndev, pipe, skb);
break;
case NCI_HCI_HCP_COMMAND:
nci_hci_cmd_received(ndev, pipe, instruction, skb);
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 8709f3d4e7c4..573b38ad2f8e 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -1226,7 +1226,7 @@ static int nfc_genl_fw_download(struct sk_buff *skb, struct genl_info *info)
if (!dev)
return -ENODEV;
- nla_strlcpy(firmware_name, info->attrs[NFC_ATTR_FIRMWARE_NAME],
+ nla_strscpy(firmware_name, info->attrs[NFC_ATTR_FIRMWARE_NAME],
sizeof(firmware_name));
rc = nfc_fw_download(dev, firmware_name);
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index b03d142ec82e..c7f34d6a9934 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -294,6 +294,10 @@ static bool icmp6hdr_ok(struct sk_buff *skb)
/**
* Parse vlan tag from vlan header.
+ * @skb: skb containing frame to parse
+ * @key_vh: pointer to parsed vlan tag
+ * @untag_vlan: should the vlan header be removed from the frame
+ *
* Returns ERROR on memory error.
* Returns 0 if it encounters a non-vlan or incomplete packet.
* Returns 1 after successfully parsing vlan tag.
diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index 8fbefd52af7f..15424d26e85d 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c
@@ -423,7 +423,7 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info)
return -EINVAL;
meter = dp_meter_create(a);
- if (IS_ERR_OR_NULL(meter))
+ if (IS_ERR(meter))
return PTR_ERR(meter);
reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_SET,
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 1e30d8df3ba5..5b2ee9c1c00b 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -35,21 +35,18 @@ internal_dev_xmit(struct sk_buff *skb, struct net_device *netdev)
{
int len, err;
+ /* store len value because skb can be freed inside ovs_vport_receive() */
len = skb->len;
+
rcu_read_lock();
err = ovs_vport_receive(internal_dev_priv(netdev)->vport, skb, NULL);
rcu_read_unlock();
- if (likely(!err)) {
- struct pcpu_sw_netstats *tstats = this_cpu_ptr(netdev->tstats);
-
- u64_stats_update_begin(&tstats->syncp);
- tstats->tx_bytes += len;
- tstats->tx_packets++;
- u64_stats_update_end(&tstats->syncp);
- } else {
+ if (likely(!err))
+ dev_sw_netstats_tx_add(netdev, 1, len);
+ else
netdev->stats.tx_errors++;
- }
+
return NETDEV_TX_OK;
}
@@ -83,24 +80,12 @@ static void internal_dev_destructor(struct net_device *dev)
ovs_vport_free(vport);
}
-static void
-internal_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
-{
- memset(stats, 0, sizeof(*stats));
- stats->rx_errors = dev->stats.rx_errors;
- stats->tx_errors = dev->stats.tx_errors;
- stats->tx_dropped = dev->stats.tx_dropped;
- stats->rx_dropped = dev->stats.rx_dropped;
-
- dev_fetch_sw_netstats(stats, dev->tstats);
-}
-
static const struct net_device_ops internal_dev_netdev_ops = {
.ndo_open = internal_dev_open,
.ndo_stop = internal_dev_stop,
.ndo_start_xmit = internal_dev_xmit,
.ndo_set_mac_address = eth_mac_addr,
- .ndo_get_stats64 = internal_get_stats,
+ .ndo_get_stats64 = dev_get_tstats64,
};
static struct rtnl_link_ops internal_dev_link_ops __read_mostly = {
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 82d801f063b7..4ed7e52c7012 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -111,10 +111,12 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name)
*
* @priv_size: Size of private data area to allocate.
* @ops: vport device ops
+ * @parms: information about new vport.
*
* Allocate and initialize a new vport defined by @ops. The vport will contain
* a private data area of size @priv_size that can be accessed using
- * vport_priv(). vports that are no longer needed should be released with
+ * vport_priv(). Some parameters of the vport will be initialized from @parms.
+ * @vports that are no longer needed should be released with
* vport_free().
*/
struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index cefbd50c1090..62ebfaa7adcb 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1636,13 +1636,15 @@ static bool fanout_find_new_id(struct sock *sk, u16 *new_id)
return false;
}
-static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
+static int fanout_add(struct sock *sk, struct fanout_args *args)
{
struct packet_rollover *rollover = NULL;
struct packet_sock *po = pkt_sk(sk);
+ u16 type_flags = args->type_flags;
struct packet_fanout *f, *match;
u8 type = type_flags & 0xff;
u8 flags = type_flags >> 8;
+ u16 id = args->id;
int err;
switch (type) {
@@ -1700,11 +1702,21 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
}
}
err = -EINVAL;
- if (match && match->flags != flags)
- goto out;
- if (!match) {
+ if (match) {
+ if (match->flags != flags)
+ goto out;
+ if (args->max_num_members &&
+ args->max_num_members != match->max_num_members)
+ goto out;
+ } else {
+ if (args->max_num_members > PACKET_FANOUT_MAX)
+ goto out;
+ if (!args->max_num_members)
+ /* legacy PACKET_FANOUT_MAX */
+ args->max_num_members = 256;
err = -ENOMEM;
- match = kzalloc(sizeof(*match), GFP_KERNEL);
+ match = kvzalloc(struct_size(match, arr, args->max_num_members),
+ GFP_KERNEL);
if (!match)
goto out;
write_pnet(&match->net, sock_net(sk));
@@ -1720,6 +1732,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
match->prot_hook.func = packet_rcv_fanout;
match->prot_hook.af_packet_priv = match;
match->prot_hook.id_match = match_fanout_group;
+ match->max_num_members = args->max_num_members;
list_add(&match->list, &fanout_list);
}
err = -EINVAL;
@@ -1730,7 +1743,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
match->prot_hook.type == po->prot_hook.type &&
match->prot_hook.dev == po->prot_hook.dev) {
err = -ENOSPC;
- if (refcount_read(&match->sk_ref) < PACKET_FANOUT_MAX) {
+ if (refcount_read(&match->sk_ref) < match->max_num_members) {
__dev_remove_pack(&po->prot_hook);
po->fanout = match;
po->rollover = rollover;
@@ -1744,7 +1757,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
if (err && !refcount_read(&match->sk_ref)) {
list_del(&match->list);
- kfree(match);
+ kvfree(match);
}
out:
@@ -3075,7 +3088,7 @@ static int packet_release(struct socket *sock)
kfree(po->rollover);
if (f) {
fanout_release_data(f);
- kfree(f);
+ kvfree(f);
}
/*
* Now the socket is dead. No more input will appear.
@@ -3866,14 +3879,14 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval,
}
case PACKET_FANOUT:
{
- int val;
+ struct fanout_args args = { 0 };
- if (optlen != sizeof(val))
+ if (optlen != sizeof(int) && optlen != sizeof(args))
return -EINVAL;
- if (copy_from_sockptr(&val, optval, sizeof(val)))
+ if (copy_from_sockptr(&args, optval, optlen))
return -EFAULT;
- return fanout_add(sk, val & 0xffff, val >> 16);
+ return fanout_add(sk, &args);
}
case PACKET_FANOUT_DATA:
{
diff --git a/net/packet/internal.h b/net/packet/internal.h
index fd41ecb7f605..baafc3f3fa25 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -77,11 +77,12 @@ struct packet_ring_buffer {
};
extern struct mutex fanout_mutex;
-#define PACKET_FANOUT_MAX 256
+#define PACKET_FANOUT_MAX (1 << 16)
struct packet_fanout {
possible_net_t net;
unsigned int num_members;
+ u32 max_num_members;
u16 id;
u8 type;
u8 flags;
@@ -90,10 +91,10 @@ struct packet_fanout {
struct bpf_prog __rcu *bpf_prog;
};
struct list_head list;
- struct sock *arr[PACKET_FANOUT_MAX];
spinlock_t lock;
refcount_t sk_ref;
struct packet_type prot_hook ____cacheline_aligned_in_smp;
+ struct sock *arr[];
};
struct packet_rollover {
diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c
index b8559c882431..56aaf8cb6527 100644
--- a/net/qrtr/ns.c
+++ b/net/qrtr/ns.c
@@ -517,10 +517,6 @@ static int ctrl_cmd_new_server(struct sockaddr_qrtr *from,
port = from->sq_port;
}
- /* Don't accept spoofed messages */
- if (from->sq_node != node_id)
- return -EINVAL;
-
srv = server_add(service, instance, node_id, port);
if (!srv)
return -EINVAL;
@@ -559,10 +555,6 @@ static int ctrl_cmd_del_server(struct sockaddr_qrtr *from,
port = from->sq_port;
}
- /* Don't accept spoofed messages */
- if (from->sq_node != node_id)
- return -EINVAL;
-
/* Local servers may only unregister themselves */
if (from->sq_node == qrtr_ns.local_node && from->sq_port != port)
return -EINVAL;
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 957aa9263ba4..f4ab3ca6d73b 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -171,8 +171,13 @@ static void __qrtr_node_release(struct kref *kref)
void __rcu **slot;
spin_lock_irqsave(&qrtr_nodes_lock, flags);
- if (node->nid != QRTR_EP_NID_AUTO)
- radix_tree_delete(&qrtr_nodes, node->nid);
+ /* If the node is a bridge for other nodes, there are possibly
+ * multiple entries pointing to our released node, delete them all.
+ */
+ radix_tree_for_each_slot(slot, &qrtr_nodes, &iter, 0) {
+ if (*slot == node)
+ radix_tree_iter_delete(&qrtr_nodes, &iter, slot);
+ }
spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
list_del(&node->item);
@@ -347,7 +352,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
hdr->src_port_id = cpu_to_le32(from->sq_port);
if (to->sq_port == QRTR_PORT_CTRL) {
hdr->dst_node_id = cpu_to_le32(node->nid);
- hdr->dst_port_id = cpu_to_le32(QRTR_NODE_BCAST);
+ hdr->dst_port_id = cpu_to_le32(QRTR_PORT_CTRL);
} else {
hdr->dst_node_id = cpu_to_le32(to->sq_node);
hdr->dst_port_id = cpu_to_le32(to->sq_port);
@@ -401,12 +406,13 @@ static void qrtr_node_assign(struct qrtr_node *node, unsigned int nid)
{
unsigned long flags;
- if (node->nid != QRTR_EP_NID_AUTO || nid == QRTR_EP_NID_AUTO)
+ if (nid == QRTR_EP_NID_AUTO)
return;
spin_lock_irqsave(&qrtr_nodes_lock, flags);
radix_tree_insert(&qrtr_nodes, nid, node);
- node->nid = nid;
+ if (node->nid == QRTR_EP_NID_AUTO)
+ node->nid = nid;
spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
}
@@ -494,6 +500,13 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
qrtr_node_assign(node, cb->src_node);
+ if (cb->type == QRTR_TYPE_NEW_SERVER) {
+ /* Remote node endpoint can bridge other distant nodes */
+ const struct qrtr_ctrl_pkt *pkt = data + hdrlen;
+
+ qrtr_node_assign(node, le32_to_cpu(pkt->server.node));
+ }
+
if (cb->type == QRTR_TYPE_RESUME_TX) {
qrtr_tx_resume(node, skb);
} else {
@@ -519,18 +532,20 @@ EXPORT_SYMBOL_GPL(qrtr_endpoint_post);
/**
* qrtr_alloc_ctrl_packet() - allocate control packet skb
* @pkt: reference to qrtr_ctrl_pkt pointer
+ * @flags: the type of memory to allocate
*
* Returns newly allocated sk_buff, or NULL on failure
*
* This function allocates a sk_buff large enough to carry a qrtr_ctrl_pkt and
* on success returns a reference to the control packet in @pkt.
*/
-static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt)
+static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt,
+ gfp_t flags)
{
const int pkt_len = sizeof(struct qrtr_ctrl_pkt);
struct sk_buff *skb;
- skb = alloc_skb(QRTR_HDR_MAX_SIZE + pkt_len, GFP_KERNEL);
+ skb = alloc_skb(QRTR_HDR_MAX_SIZE + pkt_len, flags);
if (!skb)
return NULL;
@@ -592,6 +607,7 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep)
struct qrtr_ctrl_pkt *pkt;
struct qrtr_tx_flow *flow;
struct sk_buff *skb;
+ unsigned long flags;
void __rcu **slot;
mutex_lock(&node->ep_lock);
@@ -599,11 +615,18 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep)
mutex_unlock(&node->ep_lock);
/* Notify the local controller about the event */
- skb = qrtr_alloc_ctrl_packet(&pkt);
- if (skb) {
- pkt->cmd = cpu_to_le32(QRTR_TYPE_BYE);
- qrtr_local_enqueue(NULL, skb, QRTR_TYPE_BYE, &src, &dst);
+ spin_lock_irqsave(&qrtr_nodes_lock, flags);
+ radix_tree_for_each_slot(slot, &qrtr_nodes, &iter, 0) {
+ if (*slot != node)
+ continue;
+ src.sq_node = iter.index;
+ skb = qrtr_alloc_ctrl_packet(&pkt, GFP_ATOMIC);
+ if (skb) {
+ pkt->cmd = cpu_to_le32(QRTR_TYPE_BYE);
+ qrtr_local_enqueue(NULL, skb, QRTR_TYPE_BYE, &src, &dst);
+ }
}
+ spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
/* Wake up any transmitters waiting for resume-tx from the node */
mutex_lock(&node->qrtr_tx_lock);
@@ -656,7 +679,7 @@ static void qrtr_port_remove(struct qrtr_sock *ipc)
to.sq_node = QRTR_NODE_BCAST;
to.sq_port = QRTR_PORT_CTRL;
- skb = qrtr_alloc_ctrl_packet(&pkt);
+ skb = qrtr_alloc_ctrl_packet(&pkt, GFP_KERNEL);
if (skb) {
pkt->cmd = cpu_to_le32(QRTR_TYPE_DEL_CLIENT);
pkt->client.node = cpu_to_le32(ipc->us.sq_node);
@@ -982,7 +1005,7 @@ static int qrtr_send_resume_tx(struct qrtr_cb *cb)
if (!node)
return -EINVAL;
- skb = qrtr_alloc_ctrl_packet(&pkt);
+ skb = qrtr_alloc_ctrl_packet(&pkt, GFP_KERNEL);
if (!skb)
return -ENOMEM;
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index f66417d5d2c3..fc23f46a315c 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -215,6 +215,36 @@ static size_t tcf_action_fill_size(const struct tc_action *act)
return sz;
}
+static int
+tcf_action_dump_terse(struct sk_buff *skb, struct tc_action *a, bool from_act)
+{
+ unsigned char *b = skb_tail_pointer(skb);
+ struct tc_cookie *cookie;
+
+ if (nla_put_string(skb, TCA_KIND, a->ops->kind))
+ goto nla_put_failure;
+ if (tcf_action_copy_stats(skb, a, 0))
+ goto nla_put_failure;
+ if (from_act && nla_put_u32(skb, TCA_ACT_INDEX, a->tcfa_index))
+ goto nla_put_failure;
+
+ rcu_read_lock();
+ cookie = rcu_dereference(a->act_cookie);
+ if (cookie) {
+ if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) {
+ rcu_read_unlock();
+ goto nla_put_failure;
+ }
+ }
+ rcu_read_unlock();
+
+ return 0;
+
+nla_put_failure:
+ nlmsg_trim(skb, b);
+ return -1;
+}
+
static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
struct netlink_callback *cb)
{
@@ -248,7 +278,9 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
index--;
goto nla_put_failure;
}
- err = tcf_action_dump_1(skb, p, 0, 0);
+ err = (act_flags & TCA_FLAG_TERSE_DUMP) ?
+ tcf_action_dump_terse(skb, p, true) :
+ tcf_action_dump_1(skb, p, 0, 0);
if (err < 0) {
index--;
nlmsg_trim(skb, nest);
@@ -651,7 +683,7 @@ static struct tc_action_ops *tc_lookup_action(struct nlattr *kind)
return res;
}
-/*TCA_ACT_MAX_PRIO is 32, there count upto 32 */
+/*TCA_ACT_MAX_PRIO is 32, there count up to 32 */
#define TCA_ACT_MAX_PRIO_MASK 0x1FF
int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
int nr_actions, struct tcf_result *res)
@@ -752,34 +784,6 @@ tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
return a->ops->dump(skb, a, bind, ref);
}
-static int
-tcf_action_dump_terse(struct sk_buff *skb, struct tc_action *a)
-{
- unsigned char *b = skb_tail_pointer(skb);
- struct tc_cookie *cookie;
-
- if (nla_put_string(skb, TCA_KIND, a->ops->kind))
- goto nla_put_failure;
- if (tcf_action_copy_stats(skb, a, 0))
- goto nla_put_failure;
-
- rcu_read_lock();
- cookie = rcu_dereference(a->act_cookie);
- if (cookie) {
- if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) {
- rcu_read_unlock();
- goto nla_put_failure;
- }
- }
- rcu_read_unlock();
-
- return 0;
-
-nla_put_failure:
- nlmsg_trim(skb, b);
- return -1;
-}
-
int
tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
{
@@ -787,7 +791,7 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
unsigned char *b = skb_tail_pointer(skb);
struct nlattr *nest;
- if (tcf_action_dump_terse(skb, a))
+ if (tcf_action_dump_terse(skb, a, false))
goto nla_put_failure;
if (a->hw_stats != TCA_ACT_HW_STATS_ANY &&
@@ -832,7 +836,7 @@ int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[],
nest = nla_nest_start_noflag(skb, i + 1);
if (nest == NULL)
goto nla_put_failure;
- err = terse ? tcf_action_dump_terse(skb, a) :
+ err = terse ? tcf_action_dump_terse(skb, a, false) :
tcf_action_dump_1(skb, a, bind, ref);
if (err < 0)
goto errout;
@@ -935,7 +939,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
NL_SET_ERR_MSG(extack, "TC action kind must be specified");
goto err_out;
}
- if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) {
+ if (nla_strscpy(act_name, kind, IFNAMSIZ) < 0) {
NL_SET_ERR_MSG(extack, "TC action name too long");
goto err_out;
}
@@ -1469,7 +1473,8 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
}
static const struct nla_policy tcaa_policy[TCA_ROOT_MAX + 1] = {
- [TCA_ROOT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_FLAG_LARGE_DUMP_ON),
+ [TCA_ROOT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_FLAG_LARGE_DUMP_ON |
+ TCA_FLAG_TERSE_DUMP),
[TCA_ROOT_TIME_DELTA] = { .type = NLA_U32 },
};
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index a4c7ba35a343..e48e980c3b93 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -65,7 +65,7 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act,
* In case a different well-known TC_ACT opcode has been
* returned, it will overwrite the default one.
*
- * For everything else that is unkown, TC_ACT_UNSPEC is
+ * For everything else that is unknown, TC_ACT_UNSPEC is
* returned.
*/
switch (filter_res) {
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 8dc3bec0d325..ac7297f42355 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -166,7 +166,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
if (unlikely(!tname))
goto err1;
if (tb[TCA_IPT_TABLE] == NULL ||
- nla_strlcpy(tname, tb[TCA_IPT_TABLE], IFNAMSIZ) >= IFNAMSIZ)
+ nla_strscpy(tname, tb[TCA_IPT_TABLE], IFNAMSIZ) >= IFNAMSIZ)
strcpy(tname, "mangle");
t = kmemdup(td, td->u.target_size, GFP_KERNEL);
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index a4f3d0f0daa9..726cc956d06f 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -52,7 +52,7 @@ static int alloc_defdata(struct tcf_defact *d, const struct nlattr *defdata)
d->tcfd_defdata = kzalloc(SIMP_MAX_DATA, GFP_KERNEL);
if (unlikely(!d->tcfd_defdata))
return -ENOMEM;
- nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
+ nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
return 0;
}
@@ -71,7 +71,7 @@ static int reset_policy(struct tc_action *a, const struct nlattr *defdata,
spin_lock_bh(&d->tcf_lock);
goto_ch = tcf_action_set_ctrlact(a, p->action, goto_ch);
memset(d->tcfd_defdata, 0, SIMP_MAX_DATA);
- nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
+ nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
spin_unlock_bh(&d->tcf_lock);
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 838b3fd94d77..ff3e943febaa 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -223,7 +223,7 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp)
static bool tcf_proto_check_kind(struct nlattr *kind, char *name)
{
if (kind)
- return nla_strlcpy(name, kind, IFNAMSIZ) >= IFNAMSIZ;
+ return nla_strscpy(name, kind, IFNAMSIZ) < 0;
memset(name, 0, IFNAMSIZ);
return false;
}
@@ -2940,7 +2940,6 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
struct tcf_chain *chain;
long index_start;
long index;
- u32 parent;
int err;
if (nlmsg_len(cb->nlh) < sizeof(*tcm))
@@ -2955,13 +2954,6 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
block = tcf_block_refcnt_get(net, tcm->tcm_block_index);
if (!block)
goto out;
- /* If we work with block index, q is NULL and parent value
- * will never be used in the following code. The check
- * in tcf_fill_node prevents it. However, compiler does not
- * see that far, so set parent to zero to silence the warning
- * about parent being uninitialized.
- */
- parent = 0;
} else {
const struct Qdisc_class_ops *cops;
struct net_device *dev;
@@ -2971,13 +2963,11 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
if (!dev)
return skb->len;
- parent = tcm->tcm_parent;
- if (!parent) {
+ if (!tcm->tcm_parent)
q = dev->qdisc;
- parent = q->handle;
- } else {
+ else
q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
- }
+
if (!q)
goto out;
cops = q->ops->cl_ops;
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index d36949d9382c..2e288f88ff02 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -238,7 +238,7 @@ static void rsvp_replace(struct tcf_proto *tp, struct rsvp_filter *n, u32 h)
}
}
- /* Something went wrong if we are trying to replace a non-existant
+ /* Something went wrong if we are trying to replace a non-existent
* node. Mind as well halt instead of silently failing.
*/
BUG_ON(1);
diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c
index a4d09b1fb66a..f17b049ea530 100644
--- a/net/sched/em_cmp.c
+++ b/net/sched/em_cmp.c
@@ -41,7 +41,7 @@ static int em_cmp_match(struct sk_buff *skb, struct tcf_ematch *em,
break;
case TCF_EM_ALIGN_U32:
- /* Worth checking boundries? The branching seems
+ /* Worth checking boundaries? The branching seems
* to get worse. Visit again.
*/
val = get_unaligned_be32(ptr);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 2a76a2f5ed88..1a2d2471b078 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1170,7 +1170,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
#ifdef CONFIG_MODULES
if (ops == NULL && kind != NULL) {
char name[IFNAMSIZ];
- if (nla_strlcpy(name, kind, IFNAMSIZ) < IFNAMSIZ) {
+ if (nla_strscpy(name, kind, IFNAMSIZ) >= 0) {
/* We dropped the RTNL semaphore in order to
* perform the module load. So, even if we
* succeeded in loading the module we have to
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 1c281cc81f57..007bd2d9f1ff 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -466,10 +466,10 @@ drop: __maybe_unused
* non-ATM interfaces.
*/
-static void sch_atm_dequeue(unsigned long data)
+static void sch_atm_dequeue(struct tasklet_struct *t)
{
- struct Qdisc *sch = (struct Qdisc *)data;
- struct atm_qdisc_data *p = qdisc_priv(sch);
+ struct atm_qdisc_data *p = from_tasklet(p, t, task);
+ struct Qdisc *sch = qdisc_from_priv(p);
struct atm_flow_data *flow;
struct sk_buff *skb;
@@ -563,7 +563,7 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt,
if (err)
return err;
- tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch);
+ tasklet_setup(&p->task, sch_atm_dequeue);
return 0;
}
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index c65077f0c0f3..5a457ff61acd 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -405,7 +405,7 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars,
/* We restart the measurement cycle if the following conditions are met
* 1. If the delay has been low for 2 consecutive Tupdate periods
* 2. Calculated drop probability is zero
- * 3. If average dq_rate_estimator is enabled, we have atleast one
+ * 3. If average dq_rate_estimator is enabled, we have at least one
* estimate for the avg_dq_rate ie., is a non-zero value
*/
if ((vars->qdelay < params->target / 2) &&
diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig
index 39d7fa9569f8..5da599ff84a9 100644
--- a/net/sctp/Kconfig
+++ b/net/sctp/Kconfig
@@ -11,6 +11,7 @@ menuconfig IP_SCTP
select CRYPTO_HMAC
select CRYPTO_SHA1
select LIBCRC32C
+ select NET_UDP_TUNNEL
help
Stream Control Transmission Protocol
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index fdb69d46276d..336df4b36655 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -99,6 +99,8 @@ static struct sctp_association *sctp_association_init(
*/
asoc->hbinterval = msecs_to_jiffies(sp->hbinterval);
+ asoc->encap_port = sp->encap_port;
+
/* Initialize path max retrans value. */
asoc->pathmaxrxt = sp->pathmaxrxt;
@@ -624,6 +626,8 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
*/
peer->hbinterval = asoc->hbinterval;
+ peer->encap_port = asoc->encap_port;
+
/* Set the path max_retrans. */
peer->pathmaxrxt = asoc->pathmaxrxt;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 8a58f42d6d19..c3e89c776e66 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -55,6 +55,7 @@
#include <net/inet_common.h>
#include <net/inet_ecn.h>
#include <net/sctp/sctp.h>
+#include <net/udp_tunnel.h>
#include <linux/uaccess.h>
@@ -191,33 +192,53 @@ out:
return ret;
}
-static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
+static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *t)
{
+ struct dst_entry *dst = dst_clone(t->dst);
+ struct flowi6 *fl6 = &t->fl.u.ip6;
struct sock *sk = skb->sk;
struct ipv6_pinfo *np = inet6_sk(sk);
- struct flowi6 *fl6 = &transport->fl.u.ip6;
__u8 tclass = np->tclass;
- int res;
+ __be32 label;
pr_debug("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb,
skb->len, &fl6->saddr, &fl6->daddr);
- if (transport->dscp & SCTP_DSCP_SET_MASK)
- tclass = transport->dscp & SCTP_DSCP_VAL_MASK;
+ if (t->dscp & SCTP_DSCP_SET_MASK)
+ tclass = t->dscp & SCTP_DSCP_VAL_MASK;
if (INET_ECN_is_capable(tclass))
IP6_ECN_flow_xmit(sk, fl6->flowlabel);
- if (!(transport->param_flags & SPP_PMTUD_ENABLE))
+ if (!(t->param_flags & SPP_PMTUD_ENABLE))
skb->ignore_df = 1;
SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
- rcu_read_lock();
- res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt),
- tclass, sk->sk_priority);
- rcu_read_unlock();
- return res;
+ if (!t->encap_port || !sctp_sk(sk)->udp_port) {
+ int res;
+
+ skb_dst_set(skb, dst);
+ rcu_read_lock();
+ res = ip6_xmit(sk, skb, fl6, sk->sk_mark,
+ rcu_dereference(np->opt),
+ tclass, sk->sk_priority);
+ rcu_read_unlock();
+ return res;
+ }
+
+ if (skb_is_gso(skb))
+ skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+
+ skb->encapsulation = 1;
+ skb_reset_inner_mac_header(skb);
+ skb_reset_inner_transport_header(skb);
+ skb_set_inner_ipproto(skb, IPPROTO_SCTP);
+ label = ip6_make_flowlabel(sock_net(sk), skb, fl6->flowlabel, true, fl6);
+
+ return udp_tunnel6_xmit_skb(dst, sk, skb, NULL, &fl6->saddr,
+ &fl6->daddr, tclass, ip6_dst_hoplimit(dst),
+ label, sctp_sk(sk)->udp_port, t->encap_port, false);
}
/* Returns the dst cache entry for the given source and destination ip
@@ -1053,6 +1074,7 @@ static struct inet_protosw sctpv6_stream_protosw = {
static int sctp6_rcv(struct sk_buff *skb)
{
+ SCTP_INPUT_CB(skb)->encap_port = 0;
return sctp_rcv(skb) ? -1 : 0;
}
diff --git a/net/sctp/offload.c b/net/sctp/offload.c
index 74847d613835..ce281a9a2875 100644
--- a/net/sctp/offload.c
+++ b/net/sctp/offload.c
@@ -27,7 +27,11 @@ static __le32 sctp_gso_make_checksum(struct sk_buff *skb)
{
skb->ip_summed = CHECKSUM_NONE;
skb->csum_not_inet = 0;
- gso_reset_checksum(skb, ~0);
+ /* csum and csum_start in GSO CB may be needed to do the UDP
+ * checksum when it's a UDP tunneling packet.
+ */
+ SKB_GSO_CB(skb)->csum = (__force __wsum)~0;
+ SKB_GSO_CB(skb)->csum_start = skb_headroom(skb) + skb->len;
return sctp_compute_cksum(skb, skb_transport_offset(skb));
}
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 1441eaf460bb..6614c9fdc51e 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -508,20 +508,14 @@ merge:
sizeof(struct inet6_skb_parm)));
skb_shinfo(head)->gso_segs = pkt_count;
skb_shinfo(head)->gso_size = GSO_BY_FRAGS;
- rcu_read_lock();
- if (skb_dst(head) != tp->dst) {
- dst_hold(tp->dst);
- sk_setup_caps(sk, tp->dst);
- }
- rcu_read_unlock();
goto chksum;
}
if (sctp_checksum_disable)
return 1;
- if (!(skb_dst(head)->dev->features & NETIF_F_SCTP_CRC) ||
- dst_xfrm(skb_dst(head)) || packet->ipfragok) {
+ if (!(tp->dst->dev->features & NETIF_F_SCTP_CRC) ||
+ dst_xfrm(tp->dst) || packet->ipfragok || tp->encap_port) {
struct sctphdr *sh =
(struct sctphdr *)skb_transport_header(head);
@@ -548,7 +542,6 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
struct sctp_association *asoc = tp->asoc;
struct sctp_chunk *chunk, *tmp;
int pkt_count, gso = 0;
- struct dst_entry *dst;
struct sk_buff *head;
struct sctphdr *sh;
struct sock *sk;
@@ -585,13 +578,18 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
sh->checksum = 0;
/* drop packet if no dst */
- dst = dst_clone(tp->dst);
- if (!dst) {
+ if (!tp->dst) {
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
kfree_skb(head);
goto out;
}
- skb_dst_set(head, dst);
+
+ rcu_read_lock();
+ if (__sk_dst_get(sk) != tp->dst) {
+ dst_hold(tp->dst);
+ sk_setup_caps(sk, tp->dst);
+ }
+ rcu_read_unlock();
/* pack up chunks */
pkt_count = sctp_packet_pack(packet, head, gso, gfp);
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 25833238fe93..6f2bbfeec3a4 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -44,6 +44,7 @@
#include <net/addrconf.h>
#include <net/inet_common.h>
#include <net/inet_ecn.h>
+#include <net/udp_tunnel.h>
#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024)
@@ -840,6 +841,92 @@ static int sctp_ctl_sock_init(struct net *net)
return 0;
}
+static int sctp_udp_rcv(struct sock *sk, struct sk_buff *skb)
+{
+ SCTP_INPUT_CB(skb)->encap_port = udp_hdr(skb)->source;
+
+ skb_set_transport_header(skb, sizeof(struct udphdr));
+ sctp_rcv(skb);
+ return 0;
+}
+
+static int sctp_udp_err_lookup(struct sock *sk, struct sk_buff *skb)
+{
+ struct sctp_association *asoc;
+ struct sctp_transport *t;
+ int family;
+
+ skb->transport_header += sizeof(struct udphdr);
+ family = (ip_hdr(skb)->version == 4) ? AF_INET : AF_INET6;
+ sk = sctp_err_lookup(dev_net(skb->dev), family, skb, sctp_hdr(skb),
+ &asoc, &t);
+ if (!sk)
+ return -ENOENT;
+
+ sctp_err_finish(sk, t);
+ return 0;
+}
+
+int sctp_udp_sock_start(struct net *net)
+{
+ struct udp_tunnel_sock_cfg tuncfg = {NULL};
+ struct udp_port_cfg udp_conf = {0};
+ struct socket *sock;
+ int err;
+
+ udp_conf.family = AF_INET;
+ udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
+ udp_conf.local_udp_port = htons(net->sctp.udp_port);
+ err = udp_sock_create(net, &udp_conf, &sock);
+ if (err) {
+ pr_err("Failed to create the SCTP UDP tunneling v4 sock\n");
+ return err;
+ }
+
+ tuncfg.encap_type = 1;
+ tuncfg.encap_rcv = sctp_udp_rcv;
+ tuncfg.encap_err_lookup = sctp_udp_err_lookup;
+ setup_udp_tunnel_sock(net, sock, &tuncfg);
+ net->sctp.udp4_sock = sock->sk;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ memset(&udp_conf, 0, sizeof(udp_conf));
+
+ udp_conf.family = AF_INET6;
+ udp_conf.local_ip6 = in6addr_any;
+ udp_conf.local_udp_port = htons(net->sctp.udp_port);
+ udp_conf.use_udp6_rx_checksums = true;
+ udp_conf.ipv6_v6only = true;
+ err = udp_sock_create(net, &udp_conf, &sock);
+ if (err) {
+ pr_err("Failed to create the SCTP UDP tunneling v6 sock\n");
+ udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
+ net->sctp.udp4_sock = NULL;
+ return err;
+ }
+
+ tuncfg.encap_type = 1;
+ tuncfg.encap_rcv = sctp_udp_rcv;
+ tuncfg.encap_err_lookup = sctp_udp_err_lookup;
+ setup_udp_tunnel_sock(net, sock, &tuncfg);
+ net->sctp.udp6_sock = sock->sk;
+#endif
+
+ return 0;
+}
+
+void sctp_udp_sock_stop(struct net *net)
+{
+ if (net->sctp.udp4_sock) {
+ udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
+ net->sctp.udp4_sock = NULL;
+ }
+ if (net->sctp.udp6_sock) {
+ udp_tunnel_sock_release(net->sctp.udp6_sock->sk_socket);
+ net->sctp.udp6_sock = NULL;
+ }
+}
+
/* Register address family specific functions. */
int sctp_register_af(struct sctp_af *af)
{
@@ -971,25 +1058,44 @@ static int sctp_inet_supported_addrs(const struct sctp_sock *opt,
}
/* Wrapper routine that calls the ip transmit routine. */
-static inline int sctp_v4_xmit(struct sk_buff *skb,
- struct sctp_transport *transport)
+static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *t)
{
- struct inet_sock *inet = inet_sk(skb->sk);
+ struct dst_entry *dst = dst_clone(t->dst);
+ struct flowi4 *fl4 = &t->fl.u.ip4;
+ struct sock *sk = skb->sk;
+ struct inet_sock *inet = inet_sk(sk);
__u8 dscp = inet->tos;
+ __be16 df = 0;
pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb,
- skb->len, &transport->fl.u.ip4.saddr,
- &transport->fl.u.ip4.daddr);
+ skb->len, &fl4->saddr, &fl4->daddr);
- if (transport->dscp & SCTP_DSCP_SET_MASK)
- dscp = transport->dscp & SCTP_DSCP_VAL_MASK;
+ if (t->dscp & SCTP_DSCP_SET_MASK)
+ dscp = t->dscp & SCTP_DSCP_VAL_MASK;
+
+ inet->pmtudisc = t->param_flags & SPP_PMTUD_ENABLE ? IP_PMTUDISC_DO
+ : IP_PMTUDISC_DONT;
+ SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
- inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ?
- IP_PMTUDISC_DO : IP_PMTUDISC_DONT;
+ if (!t->encap_port || !sctp_sk(sk)->udp_port) {
+ skb_dst_set(skb, dst);
+ return __ip_queue_xmit(sk, skb, &t->fl, dscp);
+ }
- SCTP_INC_STATS(sock_net(&inet->sk), SCTP_MIB_OUTSCTPPACKS);
+ if (skb_is_gso(skb))
+ skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
- return __ip_queue_xmit(&inet->sk, skb, &transport->fl, dscp);
+ if (ip_dont_fragment(sk, dst) && !skb->ignore_df)
+ df = htons(IP_DF);
+
+ skb->encapsulation = 1;
+ skb_reset_inner_mac_header(skb);
+ skb_reset_inner_transport_header(skb);
+ skb_set_inner_ipproto(skb, IPPROTO_SCTP);
+ udp_tunnel_xmit_skb((struct rtable *)dst, sk, skb, fl4->saddr,
+ fl4->daddr, dscp, ip4_dst_hoplimit(dst), df,
+ sctp_sk(sk)->udp_port, t->encap_port, false, false);
+ return 0;
}
static struct sctp_af sctp_af_inet;
@@ -1054,9 +1160,15 @@ static struct inet_protosw sctp_stream_protosw = {
.flags = SCTP_PROTOSW_FLAG
};
+static int sctp4_rcv(struct sk_buff *skb)
+{
+ SCTP_INPUT_CB(skb)->encap_port = 0;
+ return sctp_rcv(skb);
+}
+
/* Register with IP layer. */
static const struct net_protocol sctp_protocol = {
- .handler = sctp_rcv,
+ .handler = sctp4_rcv,
.err_handler = sctp_v4_err,
.no_policy = 1,
.netns_ok = 1,
@@ -1271,6 +1383,12 @@ static int __net_init sctp_defaults_init(struct net *net)
/* Enable ECN by default. */
net->sctp.ecn_enable = 1;
+ /* Set UDP tunneling listening port to 0 by default */
+ net->sctp.udp_port = 0;
+
+ /* Set remote encap port to 0 by default */
+ net->sctp.encap_port = 0;
+
/* Set SCOPE policy to enabled */
net->sctp.scope_policy = SCTP_SCOPE_POLICY_ENABLE;
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 9a56ae2f3651..f77484df097b 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1142,6 +1142,26 @@ nodata:
return retval;
}
+struct sctp_chunk *sctp_make_new_encap_port(const struct sctp_association *asoc,
+ const struct sctp_chunk *chunk)
+{
+ struct sctp_new_encap_port_hdr nep;
+ struct sctp_chunk *retval;
+
+ retval = sctp_make_abort(asoc, chunk,
+ sizeof(struct sctp_errhdr) + sizeof(nep));
+ if (!retval)
+ goto nodata;
+
+ sctp_init_cause(retval, SCTP_ERROR_NEW_ENCAP_PORT, sizeof(nep));
+ nep.cur_port = SCTP_INPUT_CB(chunk->skb)->encap_port;
+ nep.new_port = chunk->transport->encap_port;
+ sctp_addto_chunk(retval, sizeof(nep), &nep);
+
+nodata:
+ return retval;
+}
+
/* Make a HEARTBEAT chunk. */
struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc,
const struct sctp_transport *transport)
@@ -2321,6 +2341,7 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk,
* added as the primary transport. The source address seems to
* be a better choice than any of the embedded addresses.
*/
+ asoc->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port;
if (!sctp_assoc_add_peer(asoc, peer_addr, gfp, SCTP_ACTIVE))
goto nomem;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index c669f8bd1eab..af2b7041fa4e 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -87,6 +87,13 @@ static enum sctp_disposition sctp_sf_tabort_8_4_8(
const union sctp_subtype type,
void *arg,
struct sctp_cmd_seq *commands);
+static enum sctp_disposition sctp_sf_new_encap_port(
+ struct net *net,
+ const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const union sctp_subtype type,
+ void *arg,
+ struct sctp_cmd_seq *commands);
static struct sctp_sackhdr *sctp_sm_pull_sack(struct sctp_chunk *chunk);
static enum sctp_disposition sctp_stop_t1_and_abort(
@@ -1493,6 +1500,10 @@ static enum sctp_disposition sctp_sf_do_unexpected_init(
if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
commands);
+
+ if (SCTP_INPUT_CB(chunk->skb)->encap_port != chunk->transport->encap_port)
+ return sctp_sf_new_encap_port(net, ep, asoc, type, arg, commands);
+
/* Grab the INIT header. */
chunk->subh.init_hdr = (struct sctp_inithdr *)chunk->skb->data;
@@ -3392,6 +3403,45 @@ static enum sctp_disposition sctp_sf_tabort_8_4_8(
sctp_packet_append_chunk(packet, abort);
+ sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, SCTP_PACKET(packet));
+
+ SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS);
+
+ sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+ return SCTP_DISPOSITION_CONSUME;
+}
+
+/* Handling of SCTP Packets Containing an INIT Chunk Matching an
+ * Existing Associations when the UDP encap port is incorrect.
+ *
+ * From Section 4 at draft-tuexen-tsvwg-sctp-udp-encaps-cons-03.
+ */
+static enum sctp_disposition sctp_sf_new_encap_port(
+ struct net *net,
+ const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const union sctp_subtype type,
+ void *arg,
+ struct sctp_cmd_seq *commands)
+{
+ struct sctp_packet *packet = NULL;
+ struct sctp_chunk *chunk = arg;
+ struct sctp_chunk *abort;
+
+ packet = sctp_ootb_pkt_new(net, asoc, chunk);
+ if (!packet)
+ return SCTP_DISPOSITION_NOMEM;
+
+ abort = sctp_make_new_encap_port(asoc, chunk);
+ if (!abort) {
+ sctp_ootb_pkt_free(packet);
+ return SCTP_DISPOSITION_NOMEM;
+ }
+
+ abort->skb->sk = ep->base.sk;
+
+ sctp_packet_append_chunk(packet, abort);
+
sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT,
SCTP_PACKET(packet));
@@ -6268,6 +6318,8 @@ static struct sctp_packet *sctp_ootb_pkt_new(
if (!transport)
goto nomem;
+ transport->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port;
+
/* Cache a route for the transport with the chunk's destination as
* the source address.
*/
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 53d0a4161df3..a710917c5ac7 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4417,6 +4417,55 @@ out:
return retval;
}
+static int sctp_setsockopt_encap_port(struct sock *sk,
+ struct sctp_udpencaps *encap,
+ unsigned int optlen)
+{
+ struct sctp_association *asoc;
+ struct sctp_transport *t;
+ __be16 encap_port;
+
+ if (optlen != sizeof(*encap))
+ return -EINVAL;
+
+ /* If an address other than INADDR_ANY is specified, and
+ * no transport is found, then the request is invalid.
+ */
+ encap_port = (__force __be16)encap->sue_port;
+ if (!sctp_is_any(sk, (union sctp_addr *)&encap->sue_address)) {
+ t = sctp_addr_id2transport(sk, &encap->sue_address,
+ encap->sue_assoc_id);
+ if (!t)
+ return -EINVAL;
+
+ t->encap_port = encap_port;
+ return 0;
+ }
+
+ /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the
+ * socket is a one to many style socket, and an association
+ * was not found, then the id was invalid.
+ */
+ asoc = sctp_id2assoc(sk, encap->sue_assoc_id);
+ if (!asoc && encap->sue_assoc_id != SCTP_FUTURE_ASSOC &&
+ sctp_style(sk, UDP))
+ return -EINVAL;
+
+ /* If changes are for association, also apply encap_port to
+ * each transport.
+ */
+ if (asoc) {
+ list_for_each_entry(t, &asoc->peer.transport_addr_list,
+ transports)
+ t->encap_port = encap_port;
+
+ return 0;
+ }
+
+ sctp_sk(sk)->encap_port = encap_port;
+ return 0;
+}
+
/* API 6.2 setsockopt(), getsockopt()
*
* Applications use setsockopt() and getsockopt() to set or retrieve
@@ -4636,6 +4685,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE:
retval = sctp_setsockopt_pf_expose(sk, kopt, optlen);
break;
+ case SCTP_REMOTE_UDP_ENCAPS_PORT:
+ retval = sctp_setsockopt_encap_port(sk, kopt, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
@@ -4876,6 +4928,8 @@ static int sctp_init_sock(struct sock *sk)
* be modified via SCTP_PEER_ADDR_PARAMS
*/
sp->hbinterval = net->sctp.hb_interval;
+ sp->udp_port = htons(net->sctp.udp_port);
+ sp->encap_port = htons(net->sctp.encap_port);
sp->pathmaxrxt = net->sctp.max_retrans_path;
sp->pf_retrans = net->sctp.pf_retrans;
sp->ps_retrans = net->sctp.ps_retrans;
@@ -7790,6 +7844,65 @@ out:
return retval;
}
+static int sctp_getsockopt_encap_port(struct sock *sk, int len,
+ char __user *optval, int __user *optlen)
+{
+ struct sctp_association *asoc;
+ struct sctp_udpencaps encap;
+ struct sctp_transport *t;
+ __be16 encap_port;
+
+ if (len < sizeof(encap))
+ return -EINVAL;
+
+ len = sizeof(encap);
+ if (copy_from_user(&encap, optval, len))
+ return -EFAULT;
+
+ /* If an address other than INADDR_ANY is specified, and
+ * no transport is found, then the request is invalid.
+ */
+ if (!sctp_is_any(sk, (union sctp_addr *)&encap.sue_address)) {
+ t = sctp_addr_id2transport(sk, &encap.sue_address,
+ encap.sue_assoc_id);
+ if (!t) {
+ pr_debug("%s: failed no transport\n", __func__);
+ return -EINVAL;
+ }
+
+ encap_port = t->encap_port;
+ goto out;
+ }
+
+ /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the
+ * socket is a one to many style socket, and an association
+ * was not found, then the id was invalid.
+ */
+ asoc = sctp_id2assoc(sk, encap.sue_assoc_id);
+ if (!asoc && encap.sue_assoc_id != SCTP_FUTURE_ASSOC &&
+ sctp_style(sk, UDP)) {
+ pr_debug("%s: failed no association\n", __func__);
+ return -EINVAL;
+ }
+
+ if (asoc) {
+ encap_port = asoc->encap_port;
+ goto out;
+ }
+
+ encap_port = sctp_sk(sk)->encap_port;
+
+out:
+ encap.sue_port = (__force uint16_t)encap_port;
+ if (copy_to_user(optval, &encap, len))
+ return -EFAULT;
+
+ if (put_user(len, optlen))
+ return -EFAULT;
+
+ return 0;
+}
+
static int sctp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
@@ -8010,6 +8123,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE:
retval = sctp_getsockopt_pf_expose(sk, len, optval, optlen);
break;
+ case SCTP_REMOTE_UDP_ENCAPS_PORT:
+ retval = sctp_getsockopt_encap_port(sk, len, optval, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index c16c80963e55..e92df779af73 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -36,6 +36,7 @@ static int rto_alpha_max = 1000;
static int rto_beta_max = 1000;
static int pf_expose_max = SCTP_PF_EXPOSE_MAX;
static int ps_retrans_max = SCTP_PS_RETRANS_MAX;
+static int udp_port_max = 65535;
static unsigned long max_autoclose_min = 0;
static unsigned long max_autoclose_max =
@@ -48,6 +49,8 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
void *buffer, size_t *lenp, loff_t *ppos);
static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, void *buffer,
size_t *lenp, loff_t *ppos);
+static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, void *buffer,
+ size_t *lenp, loff_t *ppos);
static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
void *buffer, size_t *lenp, loff_t *ppos);
static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
@@ -291,6 +294,24 @@ static struct ctl_table sctp_net_table[] = {
.proc_handler = proc_dointvec,
},
{
+ .procname = "udp_port",
+ .data = &init_net.sctp.udp_port,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_sctp_do_udp_port,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = &udp_port_max,
+ },
+ {
+ .procname = "encap_port",
+ .data = &init_net.sctp.encap_port,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = &udp_port_max,
+ },
+ {
.procname = "addr_scope_policy",
.data = &init_net.sctp.scope_policy,
.maxlen = sizeof(int),
@@ -477,6 +498,47 @@ static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
return ret;
}
+static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct net *net = current->nsproxy->net_ns;
+ unsigned int min = *(unsigned int *)ctl->extra1;
+ unsigned int max = *(unsigned int *)ctl->extra2;
+ struct ctl_table tbl;
+ int ret, new_value;
+
+ memset(&tbl, 0, sizeof(struct ctl_table));
+ tbl.maxlen = sizeof(unsigned int);
+
+ if (write)
+ tbl.data = &new_value;
+ else
+ tbl.data = &net->sctp.udp_port;
+
+ ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+ if (write && ret == 0) {
+ struct sock *sk = net->sctp.ctl_sock;
+
+ if (new_value > max || new_value < min)
+ return -EINVAL;
+
+ net->sctp.udp_port = new_value;
+ sctp_udp_sock_stop(net);
+ if (new_value) {
+ ret = sctp_udp_sock_start(net);
+ if (ret)
+ net->sctp.udp_port = 0;
+ }
+
+ /* Update the value in the control socket */
+ lock_sock(sk);
+ sctp_sk(sk)->udp_port = htons(net->sctp.udp_port);
+ release_sock(sk);
+ }
+
+ return ret;
+}
+
int sctp_sysctl_net_register(struct net *net)
{
struct ctl_table *table;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 5dd4faaf7d6e..811819c849da 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1347,6 +1347,7 @@ static int smc_listen_v2_check(struct smc_sock *new_smc,
{
struct smc_clc_smcd_v2_extension *pclc_smcd_v2_ext;
struct smc_clc_v2_extension *pclc_v2_ext;
+ int rc = SMC_CLC_DECL_PEERNOSMC;
ini->smc_type_v1 = pclc->hdr.typev1;
ini->smc_type_v2 = pclc->hdr.typev2;
@@ -1354,29 +1355,30 @@ static int smc_listen_v2_check(struct smc_sock *new_smc,
if (pclc->hdr.version > SMC_V1)
ini->smcd_version |=
ini->smc_type_v2 != SMC_TYPE_N ? SMC_V2 : 0;
+ if (!(ini->smcd_version & SMC_V2)) {
+ rc = SMC_CLC_DECL_PEERNOSMC;
+ goto out;
+ }
if (!smc_ism_v2_capable) {
ini->smcd_version &= ~SMC_V2;
+ rc = SMC_CLC_DECL_NOISM2SUPP;
goto out;
}
pclc_v2_ext = smc_get_clc_v2_ext(pclc);
if (!pclc_v2_ext) {
ini->smcd_version &= ~SMC_V2;
+ rc = SMC_CLC_DECL_NOV2EXT;
goto out;
}
pclc_smcd_v2_ext = smc_get_clc_smcd_v2_ext(pclc_v2_ext);
- if (!pclc_smcd_v2_ext)
+ if (!pclc_smcd_v2_ext) {
ini->smcd_version &= ~SMC_V2;
+ rc = SMC_CLC_DECL_NOV2DEXT;
+ }
out:
- if (!ini->smcd_version) {
- if (pclc->hdr.typev1 == SMC_TYPE_B ||
- pclc->hdr.typev2 == SMC_TYPE_B)
- return SMC_CLC_DECL_NOSMCDEV;
- if (pclc->hdr.typev1 == SMC_TYPE_D ||
- pclc->hdr.typev2 == SMC_TYPE_D)
- return SMC_CLC_DECL_NOSMCDDEV;
- return SMC_CLC_DECL_NOSMCRDEV;
- }
+ if (!ini->smcd_version)
+ return rc;
return 0;
}
@@ -1474,6 +1476,12 @@ static void smc_check_ism_v2_match(struct smc_init_info *ini,
}
}
+static void smc_find_ism_store_rc(u32 rc, struct smc_init_info *ini)
+{
+ if (!ini->rc)
+ ini->rc = rc;
+}
+
static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc,
struct smc_clc_msg_proposal *pclc,
struct smc_init_info *ini)
@@ -1484,7 +1492,7 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc,
unsigned int matches = 0;
u8 smcd_version;
u8 *eid = NULL;
- int i;
+ int i, rc;
if (!(ini->smcd_version & SMC_V2) || !smcd_indicated(ini->smc_type_v2))
goto not_found;
@@ -1493,8 +1501,10 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc,
smc_v2_ext = smc_get_clc_v2_ext(pclc);
smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext);
if (!smcd_v2_ext ||
- !smc_v2_ext->hdr.flag.seid) /* no system EID support for SMCD */
+ !smc_v2_ext->hdr.flag.seid) { /* no system EID support for SMCD */
+ smc_find_ism_store_rc(SMC_CLC_DECL_NOSEID, ini);
goto not_found;
+ }
mutex_lock(&smcd_dev_list.mutex);
if (pclc_smcd->ism.chid)
@@ -1526,9 +1536,12 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc,
ini->smcd_version = SMC_V2;
ini->is_smcd = true;
ini->ism_selected = i;
- if (smc_listen_ism_init(new_smc, ini))
+ rc = smc_listen_ism_init(new_smc, ini);
+ if (rc) {
+ smc_find_ism_store_rc(rc, ini);
/* try next active ISM device */
continue;
+ }
return; /* matching and usable V2 ISM device found */
}
/* no V2 ISM device could be initialized */
@@ -1545,19 +1558,23 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc,
struct smc_init_info *ini)
{
struct smc_clc_msg_smcd *pclc_smcd = smc_get_clc_msg_smcd(pclc);
+ int rc = 0;
/* check if ISM V1 is available */
if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1))
goto not_found;
ini->is_smcd = true; /* prepare ISM check */
ini->ism_peer_gid[0] = ntohll(pclc_smcd->ism.gid);
- if (smc_find_ism_device(new_smc, ini))
+ rc = smc_find_ism_device(new_smc, ini);
+ if (rc)
goto not_found;
ini->ism_selected = 0;
- if (!smc_listen_ism_init(new_smc, ini))
+ rc = smc_listen_ism_init(new_smc, ini);
+ if (!rc)
return; /* V1 ISM device found */
not_found:
+ smc_find_ism_store_rc(rc, ini);
ini->ism_dev[0] = NULL;
ini->is_smcd = false;
}
@@ -1614,16 +1631,16 @@ static int smc_listen_find_device(struct smc_sock *new_smc,
return 0;
if (!(ini->smcd_version & SMC_V1))
- return SMC_CLC_DECL_NOSMCDEV;
+ return ini->rc ?: SMC_CLC_DECL_NOSMCD2DEV;
/* check for matching IP prefix and subnet length */
rc = smc_listen_prfx_check(new_smc, pclc);
if (rc)
- return rc;
+ return ini->rc ?: rc;
/* get vlan id from IP device */
if (smc_vlan_by_tcpsk(new_smc->clcsock, ini))
- return SMC_CLC_DECL_GETVLANERR;
+ return ini->rc ?: SMC_CLC_DECL_GETVLANERR;
/* check for ISM device matching V1 proposed device */
smc_find_ism_v1_device_serv(new_smc, pclc, ini);
@@ -1631,10 +1648,14 @@ static int smc_listen_find_device(struct smc_sock *new_smc,
return 0;
if (pclc->hdr.typev1 == SMC_TYPE_D)
- return SMC_CLC_DECL_NOSMCDDEV; /* skip RDMA and decline */
+ /* skip RDMA and decline */
+ return ini->rc ?: SMC_CLC_DECL_NOSMCDDEV;
/* check if RDMA is available */
- return smc_find_rdma_v1_device_serv(new_smc, pclc, ini);
+ rc = smc_find_rdma_v1_device_serv(new_smc, pclc, ini);
+ smc_find_ism_store_rc(rc, ini);
+
+ return (!rc) ? 0 : ini->rc;
}
/* listen worker: finish RDMA setup */
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index b1ce6ccbfaec..f23f558054a7 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -389,9 +389,9 @@ static void smc_cdc_msg_recv(struct smc_sock *smc, struct smc_cdc_msg *cdc)
* Context:
* - tasklet context
*/
-static void smcd_cdc_rx_tsklet(unsigned long data)
+static void smcd_cdc_rx_tsklet(struct tasklet_struct *t)
{
- struct smc_connection *conn = (struct smc_connection *)data;
+ struct smc_connection *conn = from_tasklet(conn, t, rx_tsklet);
struct smcd_cdc_msg *data_cdc;
struct smcd_cdc_msg cdc;
struct smc_sock *smc;
@@ -411,7 +411,7 @@ static void smcd_cdc_rx_tsklet(unsigned long data)
*/
void smcd_cdc_rx_init(struct smc_connection *conn)
{
- tasklet_init(&conn->rx_tsklet, smcd_cdc_rx_tsklet, (unsigned long)conn);
+ tasklet_setup(&conn->rx_tsklet, smcd_cdc_rx_tsklet);
}
/***************************** init, exit, misc ******************************/
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index c579d1d5995a..49752c997c51 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -37,6 +37,11 @@
#define SMC_CLC_DECL_NOSMCDEV 0x03030000 /* no SMC device found (R or D) */
#define SMC_CLC_DECL_NOSMCDDEV 0x03030001 /* no SMC-D device found */
#define SMC_CLC_DECL_NOSMCRDEV 0x03030002 /* no SMC-R device found */
+#define SMC_CLC_DECL_NOISM2SUPP 0x03030003 /* hardware has no ISMv2 support */
+#define SMC_CLC_DECL_NOV2EXT 0x03030004 /* peer sent no clc v2 extension */
+#define SMC_CLC_DECL_NOV2DEXT 0x03030005 /* peer sent no clc SMC-Dv2 ext. */
+#define SMC_CLC_DECL_NOSEID 0x03030006 /* peer sent no SEID */
+#define SMC_CLC_DECL_NOSMCD2DEV 0x03030007 /* no SMC-Dv2 device found */
#define SMC_CLC_DECL_MODEUNSUPP 0x03040000 /* smc modes do not match (R or D)*/
#define SMC_CLC_DECL_RMBE_EC 0x03050000 /* peer has eyecatcher in RMBE */
#define SMC_CLC_DECL_OPTUNSUPP 0x03060000 /* fastopen sockopt not supported */
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index f1e867ce2e63..9aee54a6bcba 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -301,6 +301,7 @@ struct smc_init_info {
u8 first_contact_peer;
u8 first_contact_local;
unsigned short vlan_id;
+ u32 rc;
/* SMC-R */
struct smc_clc_msg_local *ib_lcl;
struct smc_ib_device *ib_dev;
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 1e23cdd41eb1..cbc73a7e4d59 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -131,9 +131,9 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
wake_up(&link->wr_tx_wait);
}
-static void smc_wr_tx_tasklet_fn(unsigned long data)
+static void smc_wr_tx_tasklet_fn(struct tasklet_struct *t)
{
- struct smc_ib_device *dev = (struct smc_ib_device *)data;
+ struct smc_ib_device *dev = from_tasklet(dev, t, send_tasklet);
struct ib_wc wc[SMC_WR_MAX_POLL_CQE];
int i = 0, rc;
int polled = 0;
@@ -435,9 +435,9 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
}
}
-static void smc_wr_rx_tasklet_fn(unsigned long data)
+static void smc_wr_rx_tasklet_fn(struct tasklet_struct *t)
{
- struct smc_ib_device *dev = (struct smc_ib_device *)data;
+ struct smc_ib_device *dev = from_tasklet(dev, t, recv_tasklet);
struct ib_wc wc[SMC_WR_MAX_POLL_CQE];
int polled = 0;
int rc;
@@ -698,10 +698,8 @@ void smc_wr_remove_dev(struct smc_ib_device *smcibdev)
void smc_wr_add_dev(struct smc_ib_device *smcibdev)
{
- tasklet_init(&smcibdev->recv_tasklet, smc_wr_rx_tasklet_fn,
- (unsigned long)smcibdev);
- tasklet_init(&smcibdev->send_tasklet, smc_wr_tx_tasklet_fn,
- (unsigned long)smcibdev);
+ tasklet_setup(&smcibdev->recv_tasklet, smc_wr_rx_tasklet_fn);
+ tasklet_setup(&smcibdev->send_tasklet, smc_wr_tx_tasklet_fn);
}
int smc_wr_create_link(struct smc_link *lnk)
diff --git a/net/socket.c b/net/socket.c
index 6e6cccc2104f..152b1dcf93c6 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -64,7 +64,6 @@
#include <linux/seq_file.h>
#include <linux/mutex.h>
#include <linux/if_bridge.h>
-#include <linux/if_frad.h>
#include <linux/if_vlan.h>
#include <linux/ptp_classify.h>
#include <linux/init.h>
@@ -1027,17 +1026,6 @@ void vlan_ioctl_set(int (*hook) (struct net *, void __user *))
}
EXPORT_SYMBOL(vlan_ioctl_set);
-static DEFINE_MUTEX(dlci_ioctl_mutex);
-static int (*dlci_ioctl_hook) (unsigned int, void __user *);
-
-void dlci_ioctl_set(int (*hook) (unsigned int, void __user *))
-{
- mutex_lock(&dlci_ioctl_mutex);
- dlci_ioctl_hook = hook;
- mutex_unlock(&dlci_ioctl_mutex);
-}
-EXPORT_SYMBOL(dlci_ioctl_set);
-
static long sock_do_ioctl(struct net *net, struct socket *sock,
unsigned int cmd, unsigned long arg)
{
@@ -1156,17 +1144,6 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
err = vlan_ioctl_hook(net, argp);
mutex_unlock(&vlan_ioctl_mutex);
break;
- case SIOCADDDLCI:
- case SIOCDELDLCI:
- err = -ENOPKG;
- if (!dlci_ioctl_hook)
- request_module("dlci");
-
- mutex_lock(&dlci_ioctl_mutex);
- if (dlci_ioctl_hook)
- err = dlci_ioctl_hook(cmd, argp);
- mutex_unlock(&dlci_ioctl_mutex);
- break;
case SIOCGSKNS:
err = -EPERM;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
@@ -3427,8 +3404,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
case SIOCBRDELBR:
case SIOCGIFVLAN:
case SIOCSIFVLAN:
- case SIOCADDDLCI:
- case SIOCDELDLCI:
case SIOCGSKNS:
case SIOCGSTAMP_NEW:
case SIOCGSTAMPNS_NEW:
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index eadc0ede928c..8241f5a4a01c 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -781,7 +781,8 @@ static int rpc_rmdir_depopulate(struct dentry *dentry,
}
/**
- * rpc_mkpipe - make an rpc_pipefs file for kernel<->userspace communication
+ * rpc_mkpipe_dentry - make an rpc_pipefs file for kernel<->userspace
+ * communication
* @parent: dentry of directory to create new "pipe" in
* @name: name of pipe
* @private: private data to associate with the pipe, for the caller's use
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 650414110452..2241d5a38f7b 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -139,10 +139,7 @@ static int bearer_name_validate(const char *name,
u32 if_len;
/* copy bearer name & ensure length is OK */
- name_copy[TIPC_MAX_BEARER_NAME - 1] = 0;
- /* need above in case non-Posix strncpy() doesn't pad with nulls */
- strncpy(name_copy, name, TIPC_MAX_BEARER_NAME);
- if (name_copy[TIPC_MAX_BEARER_NAME - 1] != 0)
+ if (strscpy(name_copy, name, TIPC_MAX_BEARER_NAME) < 0)
return 0;
/* ensure all component parts of bearer name are present */
diff --git a/net/tipc/core.c b/net/tipc/core.c
index c2ff42900b53..5cc1f0307215 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -81,8 +81,6 @@ static int __net_init tipc_init_net(struct net *net)
if (err)
goto out_nametbl;
- INIT_LIST_HEAD(&tn->dist_queue);
-
err = tipc_bcast_init(net);
if (err)
goto out_bclink;
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 1d57a4d3b05e..df34dcdd0607 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -132,9 +132,6 @@ struct tipc_net {
spinlock_t nametbl_lock;
struct name_table *nametbl;
- /* Name dist queue */
- struct list_head dist_queue;
-
/* Topology subscription server */
struct tipc_topsrv *topsrv;
atomic_t subscription_count;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 06b880da2a8e..97b1c6bd45dc 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1260,7 +1260,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
pr_warn("Dropping received illegal msg type\n");
kfree_skb(skb);
return true;
- };
+ }
}
/* tipc_link_input - process packet that has passed link protocol check
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index fe4edce459ad..4cd90d5c84c8 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -244,24 +244,6 @@ static void tipc_publ_purge(struct net *net, struct publication *publ, u32 addr)
kfree_rcu(p, rcu);
}
-/**
- * tipc_dist_queue_purge - remove deferred updates from a node that went down
- */
-static void tipc_dist_queue_purge(struct net *net, u32 addr)
-{
- struct tipc_net *tn = net_generic(net, tipc_net_id);
- struct distr_queue_item *e, *tmp;
-
- spin_lock_bh(&tn->nametbl_lock);
- list_for_each_entry_safe(e, tmp, &tn->dist_queue, next) {
- if (e->node != addr)
- continue;
- list_del(&e->next);
- kfree(e);
- }
- spin_unlock_bh(&tn->nametbl_lock);
-}
-
void tipc_publ_notify(struct net *net, struct list_head *nsub_list,
u32 addr, u16 capabilities)
{
@@ -272,7 +254,6 @@ void tipc_publ_notify(struct net *net, struct list_head *nsub_list,
list_for_each_entry_safe(publ, tmp, nsub_list, binding_node)
tipc_publ_purge(net, publ, addr);
- tipc_dist_queue_purge(net, addr);
spin_lock_bh(&tn->nametbl_lock);
if (!(capabilities & TIPC_NAMED_BCAST))
nt->rc_dests--;
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 1c7aa51cc2a3..82f154989418 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -118,7 +118,8 @@ static void tipc_tlv_init(struct sk_buff *skb, u16 type)
skb_put(skb, sizeof(struct tlv_desc));
}
-static int tipc_tlv_sprintf(struct sk_buff *skb, const char *fmt, ...)
+static __printf(2, 3) int tipc_tlv_sprintf(struct sk_buff *skb,
+ const char *fmt, ...)
{
int n;
u16 len;
@@ -588,7 +589,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
return 0;
tipc_tlv_sprintf(msg->rep, "\nLink <%s>\n",
- nla_data(link[TIPC_NLA_LINK_NAME]));
+ (char *)nla_data(link[TIPC_NLA_LINK_NAME]));
if (link[TIPC_NLA_LINK_BROADCAST]) {
__fill_bc_link_stat(msg, prop, stats);
@@ -695,7 +696,7 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg,
link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]);
link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP]));
- nla_strlcpy(link_info.str, link[TIPC_NLA_LINK_NAME],
+ nla_strscpy(link_info.str, link[TIPC_NLA_LINK_NAME],
TIPC_MAX_LINK_NAME);
return tipc_add_tlv(msg->rep, TIPC_TLV_LINK_INFO,
diff --git a/net/tipc/node.c b/net/tipc/node.c
index d269ebe382e1..cd67b7d5169f 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1638,7 +1638,7 @@ static void tipc_lxc_xmit(struct net *peer_net, struct sk_buff_head *list)
return;
default:
return;
- };
+ }
}
/**
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index e795a8a2955b..69c4b16e8184 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -658,8 +658,8 @@ static int tipc_release(struct socket *sock)
* NOTE: This routine doesn't need to take the socket lock since it doesn't
* access any non-constant socket information.
*/
-static int tipc_bind(struct socket *sock, struct sockaddr *uaddr,
- int uaddr_len)
+
+int tipc_sk_bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len)
{
struct sock *sk = sock->sk;
struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
@@ -691,13 +691,6 @@ static int tipc_bind(struct socket *sock, struct sockaddr *uaddr,
goto exit;
}
- if ((addr->addr.nameseq.type < TIPC_RESERVED_TYPES) &&
- (addr->addr.nameseq.type != TIPC_TOP_SRV) &&
- (addr->addr.nameseq.type != TIPC_CFG_SRV)) {
- res = -EACCES;
- goto exit;
- }
-
res = (addr->scope >= 0) ?
tipc_sk_publish(tsk, addr->scope, &addr->addr.nameseq) :
tipc_sk_withdraw(tsk, -addr->scope, &addr->addr.nameseq);
@@ -706,6 +699,22 @@ exit:
return res;
}
+static int tipc_bind(struct socket *sock, struct sockaddr *skaddr, int alen)
+{
+ struct sockaddr_tipc *addr = (struct sockaddr_tipc *)skaddr;
+
+ if (alen) {
+ if (alen < sizeof(struct sockaddr_tipc))
+ return -EINVAL;
+ if (addr->addr.nameseq.type < TIPC_RESERVED_TYPES) {
+ pr_warn_once("Can't bind to reserved service type %u\n",
+ addr->addr.nameseq.type);
+ return -EACCES;
+ }
+ }
+ return tipc_sk_bind(sock, skaddr, alen);
+}
+
/**
* tipc_getname - get port ID of socket or peer socket
* @sock: socket structure
diff --git a/net/tipc/socket.h b/net/tipc/socket.h
index b11575afc66f..02cdf166807d 100644
--- a/net/tipc/socket.h
+++ b/net/tipc/socket.h
@@ -74,7 +74,7 @@ int tipc_dump_done(struct netlink_callback *cb);
u32 tipc_sock_get_portid(struct sock *sk);
bool tipc_sk_overlimit1(struct sock *sk, struct sk_buff *skb);
bool tipc_sk_overlimit2(struct sock *sk, struct sk_buff *skb);
-
+int tipc_sk_bind(struct socket *sock, struct sockaddr *skaddr, int alen);
int tsk_set_importance(struct sock *sk, int imp);
#endif
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index 13f3143609f9..88ad39e47a98 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -520,12 +520,12 @@ static int tipc_topsrv_create_listener(struct tipc_topsrv *srv)
saddr.family = AF_TIPC;
saddr.addrtype = TIPC_ADDR_NAMESEQ;
- saddr.addr.nameseq.type = TIPC_TOP_SRV;
+ saddr.addr.nameseq.type = TIPC_TOP_SRV;
saddr.addr.nameseq.lower = TIPC_TOP_SRV;
saddr.addr.nameseq.upper = TIPC_TOP_SRV;
saddr.scope = TIPC_NODE_SCOPE;
- rc = kernel_bind(lsock, (struct sockaddr *)&saddr, sizeof(saddr));
+ rc = tipc_sk_bind(lsock, (struct sockaddr *)&saddr, sizeof(saddr));
if (rc < 0)
goto err;
rc = kernel_listen(lsock, 0);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index d10916ab4526..d2834047c6db 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -2072,8 +2072,7 @@ static long vsock_dev_do_ioctl(struct file *filp,
break;
default:
- pr_err("Unknown ioctl %d\n", cmd);
- retval = -EINVAL;
+ retval = -ENOIOCTLCMD;
}
return retval;
diff --git a/net/wimax/Kconfig b/net/wimax/Kconfig
deleted file mode 100644
index d13762bc4abc..000000000000
--- a/net/wimax/Kconfig
+++ /dev/null
@@ -1,40 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# WiMAX LAN device configuration
-#
-
-menuconfig WIMAX
- tristate "WiMAX Wireless Broadband support"
- depends on RFKILL || !RFKILL
- help
-
- Select to configure support for devices that provide
- wireless broadband connectivity using the WiMAX protocol
- (IEEE 802.16).
-
- Please note that most of these devices require signing up
- for a service plan with a provider.
-
- The different WiMAX drivers can be enabled in the menu entry
-
- Device Drivers > Network device support > WiMAX Wireless
- Broadband devices
-
- If unsure, it is safe to select M (module).
-
-config WIMAX_DEBUG_LEVEL
- int "WiMAX debug level"
- depends on WIMAX
- default 8
- help
-
- Select the maximum debug verbosity level to be compiled into
- the WiMAX stack code.
-
- By default, debug messages are disabled at runtime and can
- be selectively enabled for different parts of the code using
- the sysfs debug-levels file.
-
- If set at zero, this will compile out all the debug code.
-
- It is recommended that it is left at 8.
diff --git a/net/wimax/Makefile b/net/wimax/Makefile
deleted file mode 100644
index c2a71ae487ac..000000000000
--- a/net/wimax/Makefile
+++ /dev/null
@@ -1,13 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-
-obj-$(CONFIG_WIMAX) += wimax.o
-
-wimax-y := \
- id-table.o \
- op-msg.o \
- op-reset.o \
- op-rfkill.o \
- op-state-get.o \
- stack.o
-
-wimax-$(CONFIG_DEBUG_FS) += debugfs.o
diff --git a/net/wimax/debug-levels.h b/net/wimax/debug-levels.h
deleted file mode 100644
index ebc287cde336..000000000000
--- a/net/wimax/debug-levels.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Linux WiMAX Stack
- * Debug levels control file for the wimax module
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-#ifndef __debug_levels__h__
-#define __debug_levels__h__
-
-/* Maximum compile and run time debug level for all submodules */
-#define D_MODULENAME wimax
-#define D_MASTER CONFIG_WIMAX_DEBUG_LEVEL
-
-#include <linux/wimax/debug.h>
-
-/* List of all the enabled modules */
-enum d_module {
- D_SUBMODULE_DECLARE(debugfs),
- D_SUBMODULE_DECLARE(id_table),
- D_SUBMODULE_DECLARE(op_msg),
- D_SUBMODULE_DECLARE(op_reset),
- D_SUBMODULE_DECLARE(op_rfkill),
- D_SUBMODULE_DECLARE(op_state_get),
- D_SUBMODULE_DECLARE(stack),
-};
-
-#endif /* #ifndef __debug_levels__h__ */
diff --git a/net/wimax/debugfs.c b/net/wimax/debugfs.c
deleted file mode 100644
index 3c54bb6b925a..000000000000
--- a/net/wimax/debugfs.c
+++ /dev/null
@@ -1,38 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Debugfs support
- *
- * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-#include <linux/debugfs.h>
-#include <linux/wimax.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE debugfs
-#include "debug-levels.h"
-
-void wimax_debugfs_add(struct wimax_dev *wimax_dev)
-{
- struct net_device *net_dev = wimax_dev->net_dev;
- struct dentry *dentry;
- char buf[128];
-
- snprintf(buf, sizeof(buf), "wimax:%s", net_dev->name);
- dentry = debugfs_create_dir(buf, NULL);
- wimax_dev->debugfs_dentry = dentry;
-
- d_level_register_debugfs("wimax_dl_", debugfs, dentry);
- d_level_register_debugfs("wimax_dl_", id_table, dentry);
- d_level_register_debugfs("wimax_dl_", op_msg, dentry);
- d_level_register_debugfs("wimax_dl_", op_reset, dentry);
- d_level_register_debugfs("wimax_dl_", op_rfkill, dentry);
- d_level_register_debugfs("wimax_dl_", op_state_get, dentry);
- d_level_register_debugfs("wimax_dl_", stack, dentry);
-}
-
-void wimax_debugfs_rm(struct wimax_dev *wimax_dev)
-{
- debugfs_remove_recursive(wimax_dev->debugfs_dentry);
-}
diff --git a/net/wimax/id-table.c b/net/wimax/id-table.c
deleted file mode 100644
index 02eee37b7e31..000000000000
--- a/net/wimax/id-table.c
+++ /dev/null
@@ -1,130 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Mappping of generic netlink family IDs to net devices
- *
- * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * We assign a single generic netlink family ID to each device (to
- * simplify lookup).
- *
- * We need a way to map family ID to a wimax_dev pointer.
- *
- * The idea is to use a very simple lookup. Using a netlink attribute
- * with (for example) the interface name implies a heavier search over
- * all the network devices; seemed kind of a waste given that we know
- * we are looking for a WiMAX device and that most systems will have
- * just a single WiMAX adapter.
- *
- * We put all the WiMAX devices in the system in a linked list and
- * match the generic link family ID against the list.
- *
- * By using a linked list, the case of a single adapter in the system
- * becomes (almost) no overhead, while still working for many more. If
- * it ever goes beyond two, I'll be surprised.
- */
-#include <linux/device.h>
-#include <net/genetlink.h>
-#include <linux/netdevice.h>
-#include <linux/list.h>
-#include <linux/wimax.h>
-#include "wimax-internal.h"
-
-
-#define D_SUBMODULE id_table
-#include "debug-levels.h"
-
-
-static DEFINE_SPINLOCK(wimax_id_table_lock);
-static struct list_head wimax_id_table = LIST_HEAD_INIT(wimax_id_table);
-
-
-/*
- * wimax_id_table_add - add a gennetlink familiy ID / wimax_dev mapping
- *
- * @wimax_dev: WiMAX device descriptor to associate to the Generic
- * Netlink family ID.
- *
- * Look for an empty spot in the ID table; if none found, double the
- * table's size and get the first spot.
- */
-void wimax_id_table_add(struct wimax_dev *wimax_dev)
-{
- d_fnstart(3, NULL, "(wimax_dev %p)\n", wimax_dev);
- spin_lock(&wimax_id_table_lock);
- list_add(&wimax_dev->id_table_node, &wimax_id_table);
- spin_unlock(&wimax_id_table_lock);
- d_fnend(3, NULL, "(wimax_dev %p)\n", wimax_dev);
-}
-
-
-/*
- * wimax_get_netdev_by_info - lookup a wimax_dev from the gennetlink info
- *
- * The generic netlink family ID has been filled out in the
- * nlmsghdr->nlmsg_type field, so we pull it from there, look it up in
- * the mapping table and reference the wimax_dev.
- *
- * When done, the reference should be dropped with
- * 'dev_put(wimax_dev->net_dev)'.
- */
-struct wimax_dev *wimax_dev_get_by_genl_info(
- struct genl_info *info, int ifindex)
-{
- struct wimax_dev *wimax_dev = NULL;
-
- d_fnstart(3, NULL, "(info %p ifindex %d)\n", info, ifindex);
- spin_lock(&wimax_id_table_lock);
- list_for_each_entry(wimax_dev, &wimax_id_table, id_table_node) {
- if (wimax_dev->net_dev->ifindex == ifindex) {
- dev_hold(wimax_dev->net_dev);
- goto found;
- }
- }
- wimax_dev = NULL;
- d_printf(1, NULL, "wimax: no devices found with ifindex %d\n",
- ifindex);
-found:
- spin_unlock(&wimax_id_table_lock);
- d_fnend(3, NULL, "(info %p ifindex %d) = %p\n",
- info, ifindex, wimax_dev);
- return wimax_dev;
-}
-
-
-/*
- * wimax_id_table_rm - Remove a gennetlink familiy ID / wimax_dev mapping
- *
- * @id: family ID to remove from the table
- */
-void wimax_id_table_rm(struct wimax_dev *wimax_dev)
-{
- spin_lock(&wimax_id_table_lock);
- list_del_init(&wimax_dev->id_table_node);
- spin_unlock(&wimax_id_table_lock);
-}
-
-
-/*
- * Release the gennetlink family id / mapping table
- *
- * On debug, verify that the table is empty upon removal. We want the
- * code always compiled, to ensure it doesn't bit rot. It will be
- * compiled out if CONFIG_BUG is disabled.
- */
-void wimax_id_table_release(void)
-{
- struct wimax_dev *wimax_dev;
-
-#ifndef CONFIG_BUG
- return;
-#endif
- spin_lock(&wimax_id_table_lock);
- list_for_each_entry(wimax_dev, &wimax_id_table, id_table_node) {
- pr_err("BUG: %s wimax_dev %p ifindex %d not cleared\n",
- __func__, wimax_dev, wimax_dev->net_dev->ifindex);
- WARN_ON(1);
- }
- spin_unlock(&wimax_id_table_lock);
-}
diff --git a/net/wimax/op-msg.c b/net/wimax/op-msg.c
deleted file mode 100644
index 6460b5785758..000000000000
--- a/net/wimax/op-msg.c
+++ /dev/null
@@ -1,391 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Generic messaging interface between userspace and driver/device
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This implements a direct communication channel between user space and
- * the driver/device, by which free form messages can be sent back and
- * forth.
- *
- * This is intended for device-specific features, vendor quirks, etc.
- *
- * See include/net/wimax.h
- *
- * GENERIC NETLINK ENCODING AND CAPACITY
- *
- * A destination "pipe name" is added to each message; it is up to the
- * drivers to assign or use those names (if using them at all).
- *
- * Messages are encoded as a binary netlink attribute using nla_put()
- * using type NLA_UNSPEC (as some versions of libnl still in
- * deployment don't yet understand NLA_BINARY).
- *
- * The maximum capacity of this transport is PAGESIZE per message (so
- * the actual payload will be bit smaller depending on the
- * netlink/generic netlink attributes and headers).
- *
- * RECEPTION OF MESSAGES
- *
- * When a message is received from user space, it is passed verbatim
- * to the driver calling wimax_dev->op_msg_from_user(). The return
- * value from this function is passed back to user space as an ack
- * over the generic netlink protocol.
- *
- * The stack doesn't do any processing or interpretation of these
- * messages.
- *
- * SENDING MESSAGES
- *
- * Messages can be sent with wimax_msg().
- *
- * If the message delivery needs to happen on a different context to
- * that of its creation, wimax_msg_alloc() can be used to get a
- * pointer to the message that can be delivered later on with
- * wimax_msg_send().
- *
- * ROADMAP
- *
- * wimax_gnl_doit_msg_from_user() Process a message from user space
- * wimax_dev_get_by_genl_info()
- * wimax_dev->op_msg_from_user() Delivery of message to the driver
- *
- * wimax_msg() Send a message to user space
- * wimax_msg_alloc()
- * wimax_msg_send()
- */
-#include <linux/device.h>
-#include <linux/slab.h>
-#include <net/genetlink.h>
-#include <linux/netdevice.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include <linux/export.h>
-#include "wimax-internal.h"
-
-
-#define D_SUBMODULE op_msg
-#include "debug-levels.h"
-
-
-/**
- * wimax_msg_alloc - Create a new skb for sending a message to userspace
- *
- * @wimax_dev: WiMAX device descriptor
- * @pipe_name: "named pipe" the message will be sent to
- * @msg: pointer to the message data to send
- * @size: size of the message to send (in bytes), including the header.
- * @gfp_flags: flags for memory allocation.
- *
- * Returns: %0 if ok, negative errno code on error
- *
- * Description:
- *
- * Allocates an skb that will contain the message to send to user
- * space over the messaging pipe and initializes it, copying the
- * payload.
- *
- * Once this call is done, you can deliver it with
- * wimax_msg_send().
- *
- * IMPORTANT:
- *
- * Don't use skb_push()/skb_pull()/skb_reserve() on the skb, as
- * wimax_msg_send() depends on skb->data being placed at the
- * beginning of the user message.
- *
- * Unlike other WiMAX stack calls, this call can be used way early,
- * even before wimax_dev_add() is called, as long as the
- * wimax_dev->net_dev pointer is set to point to a proper
- * net_dev. This is so that drivers can use it early in case they need
- * to send stuff around or communicate with user space.
- */
-struct sk_buff *wimax_msg_alloc(struct wimax_dev *wimax_dev,
- const char *pipe_name,
- const void *msg, size_t size,
- gfp_t gfp_flags)
-{
- int result;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- size_t msg_size;
- void *genl_msg;
- struct sk_buff *skb;
-
- msg_size = nla_total_size(size)
- + nla_total_size(sizeof(u32))
- + (pipe_name ? nla_total_size(strlen(pipe_name)) : 0);
- result = -ENOMEM;
- skb = genlmsg_new(msg_size, gfp_flags);
- if (skb == NULL)
- goto error_new;
- genl_msg = genlmsg_put(skb, 0, 0, &wimax_gnl_family,
- 0, WIMAX_GNL_OP_MSG_TO_USER);
- if (genl_msg == NULL) {
- dev_err(dev, "no memory to create generic netlink message\n");
- goto error_genlmsg_put;
- }
- result = nla_put_u32(skb, WIMAX_GNL_MSG_IFIDX,
- wimax_dev->net_dev->ifindex);
- if (result < 0) {
- dev_err(dev, "no memory to add ifindex attribute\n");
- goto error_nla_put;
- }
- if (pipe_name) {
- result = nla_put_string(skb, WIMAX_GNL_MSG_PIPE_NAME,
- pipe_name);
- if (result < 0) {
- dev_err(dev, "no memory to add pipe_name attribute\n");
- goto error_nla_put;
- }
- }
- result = nla_put(skb, WIMAX_GNL_MSG_DATA, size, msg);
- if (result < 0) {
- dev_err(dev, "no memory to add payload (msg %p size %zu) in "
- "attribute: %d\n", msg, size, result);
- goto error_nla_put;
- }
- genlmsg_end(skb, genl_msg);
- return skb;
-
-error_nla_put:
-error_genlmsg_put:
-error_new:
- nlmsg_free(skb);
- return ERR_PTR(result);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_alloc);
-
-
-/**
- * wimax_msg_data_len - Return a pointer and size of a message's payload
- *
- * @msg: Pointer to a message created with wimax_msg_alloc()
- * @size: Pointer to where to store the message's size
- *
- * Returns the pointer to the message data.
- */
-const void *wimax_msg_data_len(struct sk_buff *msg, size_t *size)
-{
- struct nlmsghdr *nlh = (void *) msg->head;
- struct nlattr *nla;
-
- nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
- WIMAX_GNL_MSG_DATA);
- if (nla == NULL) {
- pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
- return NULL;
- }
- *size = nla_len(nla);
- return nla_data(nla);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_data_len);
-
-
-/**
- * wimax_msg_data - Return a pointer to a message's payload
- *
- * @msg: Pointer to a message created with wimax_msg_alloc()
- */
-const void *wimax_msg_data(struct sk_buff *msg)
-{
- struct nlmsghdr *nlh = (void *) msg->head;
- struct nlattr *nla;
-
- nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
- WIMAX_GNL_MSG_DATA);
- if (nla == NULL) {
- pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
- return NULL;
- }
- return nla_data(nla);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_data);
-
-
-/**
- * wimax_msg_len - Return a message's payload length
- *
- * @msg: Pointer to a message created with wimax_msg_alloc()
- */
-ssize_t wimax_msg_len(struct sk_buff *msg)
-{
- struct nlmsghdr *nlh = (void *) msg->head;
- struct nlattr *nla;
-
- nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
- WIMAX_GNL_MSG_DATA);
- if (nla == NULL) {
- pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
- return -EINVAL;
- }
- return nla_len(nla);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_len);
-
-
-/**
- * wimax_msg_send - Send a pre-allocated message to user space
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @skb: &struct sk_buff returned by wimax_msg_alloc(). Note the
- * ownership of @skb is transferred to this function.
- *
- * Returns: 0 if ok, < 0 errno code on error
- *
- * Description:
- *
- * Sends a free-form message that was preallocated with
- * wimax_msg_alloc() and filled up.
- *
- * Assumes that once you pass an skb to this function for sending, it
- * owns it and will release it when done (on success).
- *
- * IMPORTANT:
- *
- * Don't use skb_push()/skb_pull()/skb_reserve() on the skb, as
- * wimax_msg_send() depends on skb->data being placed at the
- * beginning of the user message.
- *
- * Unlike other WiMAX stack calls, this call can be used way early,
- * even before wimax_dev_add() is called, as long as the
- * wimax_dev->net_dev pointer is set to point to a proper
- * net_dev. This is so that drivers can use it early in case they need
- * to send stuff around or communicate with user space.
- */
-int wimax_msg_send(struct wimax_dev *wimax_dev, struct sk_buff *skb)
-{
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- void *msg = skb->data;
- size_t size = skb->len;
- might_sleep();
-
- d_printf(1, dev, "CTX: wimax msg, %zu bytes\n", size);
- d_dump(2, dev, msg, size);
- genlmsg_multicast(&wimax_gnl_family, skb, 0, 0, GFP_KERNEL);
- d_printf(1, dev, "CTX: genl multicast done\n");
- return 0;
-}
-EXPORT_SYMBOL_GPL(wimax_msg_send);
-
-
-/**
- * wimax_msg - Send a message to user space
- *
- * @wimax_dev: WiMAX device descriptor (properly referenced)
- * @pipe_name: "named pipe" the message will be sent to
- * @buf: pointer to the message to send.
- * @size: size of the buffer pointed to by @buf (in bytes).
- * @gfp_flags: flags for memory allocation.
- *
- * Returns: %0 if ok, negative errno code on error.
- *
- * Description:
- *
- * Sends a free-form message to user space on the device @wimax_dev.
- *
- * NOTES:
- *
- * Once the @skb is given to this function, who will own it and will
- * release it when done (unless it returns error).
- */
-int wimax_msg(struct wimax_dev *wimax_dev, const char *pipe_name,
- const void *buf, size_t size, gfp_t gfp_flags)
-{
- int result = -ENOMEM;
- struct sk_buff *skb;
-
- skb = wimax_msg_alloc(wimax_dev, pipe_name, buf, size, gfp_flags);
- if (IS_ERR(skb))
- result = PTR_ERR(skb);
- else
- result = wimax_msg_send(wimax_dev, skb);
- return result;
-}
-EXPORT_SYMBOL_GPL(wimax_msg);
-
-/*
- * Relays a message from user space to the driver
- *
- * The skb is passed to the driver-specific function with the netlink
- * and generic netlink headers already stripped.
- *
- * This call will block while handling/relaying the message.
- */
-int wimax_gnl_doit_msg_from_user(struct sk_buff *skb, struct genl_info *info)
-{
- int result, ifindex;
- struct wimax_dev *wimax_dev;
- struct device *dev;
- struct nlmsghdr *nlh = info->nlhdr;
- char *pipe_name;
- void *msg_buf;
- size_t msg_len;
-
- might_sleep();
- d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
- result = -ENODEV;
- if (info->attrs[WIMAX_GNL_MSG_IFIDX] == NULL) {
- pr_err("WIMAX_GNL_MSG_FROM_USER: can't find IFIDX attribute\n");
- goto error_no_wimax_dev;
- }
- ifindex = nla_get_u32(info->attrs[WIMAX_GNL_MSG_IFIDX]);
- wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
- if (wimax_dev == NULL)
- goto error_no_wimax_dev;
- dev = wimax_dev_to_dev(wimax_dev);
-
- /* Unpack arguments */
- result = -EINVAL;
- if (info->attrs[WIMAX_GNL_MSG_DATA] == NULL) {
- dev_err(dev, "WIMAX_GNL_MSG_FROM_USER: can't find MSG_DATA "
- "attribute\n");
- goto error_no_data;
- }
- msg_buf = nla_data(info->attrs[WIMAX_GNL_MSG_DATA]);
- msg_len = nla_len(info->attrs[WIMAX_GNL_MSG_DATA]);
-
- if (info->attrs[WIMAX_GNL_MSG_PIPE_NAME] == NULL)
- pipe_name = NULL;
- else {
- struct nlattr *attr = info->attrs[WIMAX_GNL_MSG_PIPE_NAME];
- size_t attr_len = nla_len(attr);
- /* libnl-1.1 does not yet support NLA_NUL_STRING */
- result = -ENOMEM;
- pipe_name = kstrndup(nla_data(attr), attr_len + 1, GFP_KERNEL);
- if (pipe_name == NULL)
- goto error_alloc;
- pipe_name[attr_len] = 0;
- }
- mutex_lock(&wimax_dev->mutex);
- result = wimax_dev_is_ready(wimax_dev);
- if (result == -ENOMEDIUM)
- result = 0;
- if (result < 0)
- goto error_not_ready;
- result = -ENOSYS;
- if (wimax_dev->op_msg_from_user == NULL)
- goto error_noop;
-
- d_printf(1, dev,
- "CRX: nlmsghdr len %u type %u flags 0x%04x seq 0x%x pid %u\n",
- nlh->nlmsg_len, nlh->nlmsg_type, nlh->nlmsg_flags,
- nlh->nlmsg_seq, nlh->nlmsg_pid);
- d_printf(1, dev, "CRX: wimax message %zu bytes\n", msg_len);
- d_dump(2, dev, msg_buf, msg_len);
-
- result = wimax_dev->op_msg_from_user(wimax_dev, pipe_name,
- msg_buf, msg_len, info);
-error_noop:
-error_not_ready:
- mutex_unlock(&wimax_dev->mutex);
-error_alloc:
- kfree(pipe_name);
-error_no_data:
- dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
- d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
- return result;
-}
diff --git a/net/wimax/op-reset.c b/net/wimax/op-reset.c
deleted file mode 100644
index 9899b2e56721..000000000000
--- a/net/wimax/op-reset.c
+++ /dev/null
@@ -1,108 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Implement and export a method for resetting a WiMAX device
- *
- * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This implements a simple synchronous call to reset a WiMAX device.
- *
- * Resets aim at being warm, keeping the device handles active;
- * however, when that fails, it falls back to a cold reset (that will
- * disconnect and reconnect the device).
- */
-
-#include <net/wimax.h>
-#include <net/genetlink.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include <linux/export.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE op_reset
-#include "debug-levels.h"
-
-
-/**
- * wimax_reset - Reset a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * Returns:
- *
- * %0 if ok and a warm reset was done (the device still exists in
- * the system).
- *
- * -%ENODEV if a cold/bus reset had to be done (device has
- * disconnected and reconnected, so current handle is not valid
- * any more).
- *
- * -%EINVAL if the device is not even registered.
- *
- * Any other negative error code shall be considered as
- * non-recoverable.
- *
- * Description:
- *
- * Called when wanting to reset the device for any reason. Device is
- * taken back to power on status.
- *
- * This call blocks; on successful return, the device has completed the
- * reset process and is ready to operate.
- */
-int wimax_reset(struct wimax_dev *wimax_dev)
-{
- int result = -EINVAL;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- enum wimax_st state;
-
- might_sleep();
- d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
- mutex_lock(&wimax_dev->mutex);
- dev_hold(wimax_dev->net_dev);
- state = wimax_dev->state;
- mutex_unlock(&wimax_dev->mutex);
-
- if (state >= WIMAX_ST_DOWN) {
- mutex_lock(&wimax_dev->mutex_reset);
- result = wimax_dev->op_reset(wimax_dev);
- mutex_unlock(&wimax_dev->mutex_reset);
- }
- dev_put(wimax_dev->net_dev);
-
- d_fnend(3, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
- return result;
-}
-EXPORT_SYMBOL(wimax_reset);
-
-
-/*
- * Exporting to user space over generic netlink
- *
- * Parse the reset command from user space, return error code.
- *
- * No attributes.
- */
-int wimax_gnl_doit_reset(struct sk_buff *skb, struct genl_info *info)
-{
- int result, ifindex;
- struct wimax_dev *wimax_dev;
-
- d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
- result = -ENODEV;
- if (info->attrs[WIMAX_GNL_RESET_IFIDX] == NULL) {
- pr_err("WIMAX_GNL_OP_RFKILL: can't find IFIDX attribute\n");
- goto error_no_wimax_dev;
- }
- ifindex = nla_get_u32(info->attrs[WIMAX_GNL_RESET_IFIDX]);
- wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
- if (wimax_dev == NULL)
- goto error_no_wimax_dev;
- /* Execute the operation and send the result back to user space */
- result = wimax_reset(wimax_dev);
- dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
- d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
- return result;
-}
diff --git a/net/wimax/op-rfkill.c b/net/wimax/op-rfkill.c
deleted file mode 100644
index 248d10b60b05..000000000000
--- a/net/wimax/op-rfkill.c
+++ /dev/null
@@ -1,431 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * RF-kill framework integration
- *
- * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This integrates into the Linux Kernel rfkill susbystem so that the
- * drivers just have to do the bare minimal work, which is providing a
- * method to set the software RF-Kill switch and to report changes in
- * the software and hardware switch status.
- *
- * A non-polled generic rfkill device is embedded into the WiMAX
- * subsystem's representation of a device.
- *
- * FIXME: Need polled support? Let drivers provide a poll routine
- * and hand it to rfkill ops then?
- *
- * All device drivers have to do is after wimax_dev_init(), call
- * wimax_report_rfkill_hw() and wimax_report_rfkill_sw() to update
- * initial state and then every time it changes. See wimax.h:struct
- * wimax_dev for more information.
- *
- * ROADMAP
- *
- * wimax_gnl_doit_rfkill() User space calling wimax_rfkill()
- * wimax_rfkill() Kernel calling wimax_rfkill()
- * __wimax_rf_toggle_radio()
- *
- * wimax_rfkill_set_radio_block() RF-Kill subsystem calling
- * __wimax_rf_toggle_radio()
- *
- * __wimax_rf_toggle_radio()
- * wimax_dev->op_rfkill_sw_toggle() Driver backend
- * __wimax_state_change()
- *
- * wimax_report_rfkill_sw() Driver reports state change
- * __wimax_state_change()
- *
- * wimax_report_rfkill_hw() Driver reports state change
- * __wimax_state_change()
- *
- * wimax_rfkill_add() Initialize/shutdown rfkill support
- * wimax_rfkill_rm() [called by wimax_dev_add/rm()]
- */
-
-#include <net/wimax.h>
-#include <net/genetlink.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include <linux/rfkill.h>
-#include <linux/export.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE op_rfkill
-#include "debug-levels.h"
-
-/**
- * wimax_report_rfkill_hw - Reports changes in the hardware RF switch
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @state: New state of the RF Kill switch. %WIMAX_RF_ON radio on,
- * %WIMAX_RF_OFF radio off.
- *
- * When the device detects a change in the state of thehardware RF
- * switch, it must call this function to let the WiMAX kernel stack
- * know that the state has changed so it can be properly propagated.
- *
- * The WiMAX stack caches the state (the driver doesn't need to). As
- * well, as the change is propagated it will come back as a request to
- * change the software state to mirror the hardware state.
- *
- * If the device doesn't have a hardware kill switch, just report
- * it on initialization as always on (%WIMAX_RF_ON, radio on).
- */
-void wimax_report_rfkill_hw(struct wimax_dev *wimax_dev,
- enum wimax_rf_state state)
-{
- int result;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- enum wimax_st wimax_state;
-
- d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
- BUG_ON(state == WIMAX_RF_QUERY);
- BUG_ON(state != WIMAX_RF_ON && state != WIMAX_RF_OFF);
-
- mutex_lock(&wimax_dev->mutex);
- result = wimax_dev_is_ready(wimax_dev);
- if (result < 0)
- goto error_not_ready;
-
- if (state != wimax_dev->rf_hw) {
- wimax_dev->rf_hw = state;
- if (wimax_dev->rf_hw == WIMAX_RF_ON &&
- wimax_dev->rf_sw == WIMAX_RF_ON)
- wimax_state = WIMAX_ST_READY;
- else
- wimax_state = WIMAX_ST_RADIO_OFF;
-
- result = rfkill_set_hw_state(wimax_dev->rfkill,
- state == WIMAX_RF_OFF);
-
- __wimax_state_change(wimax_dev, wimax_state);
- }
-error_not_ready:
- mutex_unlock(&wimax_dev->mutex);
- d_fnend(3, dev, "(wimax_dev %p state %u) = void [%d]\n",
- wimax_dev, state, result);
-}
-EXPORT_SYMBOL_GPL(wimax_report_rfkill_hw);
-
-
-/**
- * wimax_report_rfkill_sw - Reports changes in the software RF switch
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @state: New state of the RF kill switch. %WIMAX_RF_ON radio on,
- * %WIMAX_RF_OFF radio off.
- *
- * Reports changes in the software RF switch state to the WiMAX stack.
- *
- * The main use is during initialization, so the driver can query the
- * device for its current software radio kill switch state and feed it
- * to the system.
- *
- * On the side, the device does not change the software state by
- * itself. In practice, this can happen, as the device might decide to
- * switch (in software) the radio off for different reasons.
- */
-void wimax_report_rfkill_sw(struct wimax_dev *wimax_dev,
- enum wimax_rf_state state)
-{
- int result;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- enum wimax_st wimax_state;
-
- d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
- BUG_ON(state == WIMAX_RF_QUERY);
- BUG_ON(state != WIMAX_RF_ON && state != WIMAX_RF_OFF);
-
- mutex_lock(&wimax_dev->mutex);
- result = wimax_dev_is_ready(wimax_dev);
- if (result < 0)
- goto error_not_ready;
-
- if (state != wimax_dev->rf_sw) {
- wimax_dev->rf_sw = state;
- if (wimax_dev->rf_hw == WIMAX_RF_ON &&
- wimax_dev->rf_sw == WIMAX_RF_ON)
- wimax_state = WIMAX_ST_READY;
- else
- wimax_state = WIMAX_ST_RADIO_OFF;
- __wimax_state_change(wimax_dev, wimax_state);
- rfkill_set_sw_state(wimax_dev->rfkill, state == WIMAX_RF_OFF);
- }
-error_not_ready:
- mutex_unlock(&wimax_dev->mutex);
- d_fnend(3, dev, "(wimax_dev %p state %u) = void [%d]\n",
- wimax_dev, state, result);
-}
-EXPORT_SYMBOL_GPL(wimax_report_rfkill_sw);
-
-
-/*
- * Callback for the RF Kill toggle operation
- *
- * This function is called by:
- *
- * - The rfkill subsystem when the RF-Kill key is pressed in the
- * hardware and the driver notifies through
- * wimax_report_rfkill_hw(). The rfkill subsystem ends up calling back
- * here so the software RF Kill switch state is changed to reflect
- * the hardware switch state.
- *
- * - When the user sets the state through sysfs' rfkill/state file
- *
- * - When the user calls wimax_rfkill().
- *
- * This call blocks!
- *
- * WARNING! When we call rfkill_unregister(), this will be called with
- * state 0!
- *
- * WARNING: wimax_dev must be locked
- */
-static
-int __wimax_rf_toggle_radio(struct wimax_dev *wimax_dev,
- enum wimax_rf_state state)
-{
- int result = 0;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- enum wimax_st wimax_state;
-
- might_sleep();
- d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
- if (wimax_dev->rf_sw == state)
- goto out_no_change;
- if (wimax_dev->op_rfkill_sw_toggle != NULL)
- result = wimax_dev->op_rfkill_sw_toggle(wimax_dev, state);
- else if (state == WIMAX_RF_OFF) /* No op? can't turn off */
- result = -ENXIO;
- else /* No op? can turn on */
- result = 0; /* should never happen tho */
- if (result >= 0) {
- result = 0;
- wimax_dev->rf_sw = state;
- wimax_state = state == WIMAX_RF_ON ?
- WIMAX_ST_READY : WIMAX_ST_RADIO_OFF;
- __wimax_state_change(wimax_dev, wimax_state);
- }
-out_no_change:
- d_fnend(3, dev, "(wimax_dev %p state %u) = %d\n",
- wimax_dev, state, result);
- return result;
-}
-
-
-/*
- * Translate from rfkill state to wimax state
- *
- * NOTE: Special state handling rules here
- *
- * Just pretend the call didn't happen if we are in a state where
- * we know for sure it cannot be handled (WIMAX_ST_DOWN or
- * __WIMAX_ST_QUIESCING). rfkill() needs it to register and
- * unregister, as it will run this path.
- *
- * NOTE: This call will block until the operation is completed.
- */
-static int wimax_rfkill_set_radio_block(void *data, bool blocked)
-{
- int result;
- struct wimax_dev *wimax_dev = data;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- enum wimax_rf_state rf_state;
-
- d_fnstart(3, dev, "(wimax_dev %p blocked %u)\n", wimax_dev, blocked);
- rf_state = WIMAX_RF_ON;
- if (blocked)
- rf_state = WIMAX_RF_OFF;
- mutex_lock(&wimax_dev->mutex);
- if (wimax_dev->state <= __WIMAX_ST_QUIESCING)
- result = 0;
- else
- result = __wimax_rf_toggle_radio(wimax_dev, rf_state);
- mutex_unlock(&wimax_dev->mutex);
- d_fnend(3, dev, "(wimax_dev %p blocked %u) = %d\n",
- wimax_dev, blocked, result);
- return result;
-}
-
-static const struct rfkill_ops wimax_rfkill_ops = {
- .set_block = wimax_rfkill_set_radio_block,
-};
-
-/**
- * wimax_rfkill - Set the software RF switch state for a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @state: New RF state.
- *
- * Returns:
- *
- * >= 0 toggle state if ok, < 0 errno code on error. The toggle state
- * is returned as a bitmap, bit 0 being the hardware RF state, bit 1
- * the software RF state.
- *
- * 0 means disabled (%WIMAX_RF_ON, radio on), 1 means enabled radio
- * off (%WIMAX_RF_OFF).
- *
- * Description:
- *
- * Called by the user when he wants to request the WiMAX radio to be
- * switched on (%WIMAX_RF_ON) or off (%WIMAX_RF_OFF). With
- * %WIMAX_RF_QUERY, just the current state is returned.
- *
- * NOTE:
- *
- * This call will block until the operation is complete.
- */
-int wimax_rfkill(struct wimax_dev *wimax_dev, enum wimax_rf_state state)
-{
- int result;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
-
- d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
- mutex_lock(&wimax_dev->mutex);
- result = wimax_dev_is_ready(wimax_dev);
- if (result < 0) {
- /* While initializing, < 1.4.3 wimax-tools versions use
- * this call to check if the device is a valid WiMAX
- * device; so we allow it to proceed always,
- * considering the radios are all off. */
- if (result == -ENOMEDIUM && state == WIMAX_RF_QUERY)
- result = WIMAX_RF_OFF << 1 | WIMAX_RF_OFF;
- goto error_not_ready;
- }
- switch (state) {
- case WIMAX_RF_ON:
- case WIMAX_RF_OFF:
- result = __wimax_rf_toggle_radio(wimax_dev, state);
- if (result < 0)
- goto error;
- rfkill_set_sw_state(wimax_dev->rfkill, state == WIMAX_RF_OFF);
- break;
- case WIMAX_RF_QUERY:
- break;
- default:
- result = -EINVAL;
- goto error;
- }
- result = wimax_dev->rf_sw << 1 | wimax_dev->rf_hw;
-error:
-error_not_ready:
- mutex_unlock(&wimax_dev->mutex);
- d_fnend(3, dev, "(wimax_dev %p state %u) = %d\n",
- wimax_dev, state, result);
- return result;
-}
-EXPORT_SYMBOL(wimax_rfkill);
-
-
-/*
- * Register a new WiMAX device's RF Kill support
- *
- * WARNING: wimax_dev->mutex must be unlocked
- */
-int wimax_rfkill_add(struct wimax_dev *wimax_dev)
-{
- int result;
- struct rfkill *rfkill;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
-
- d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
- /* Initialize RF Kill */
- result = -ENOMEM;
- rfkill = rfkill_alloc(wimax_dev->name, dev, RFKILL_TYPE_WIMAX,
- &wimax_rfkill_ops, wimax_dev);
- if (rfkill == NULL)
- goto error_rfkill_allocate;
-
- d_printf(1, dev, "rfkill %p\n", rfkill);
-
- wimax_dev->rfkill = rfkill;
-
- rfkill_init_sw_state(rfkill, 1);
- result = rfkill_register(wimax_dev->rfkill);
- if (result < 0)
- goto error_rfkill_register;
-
- /* If there is no SW toggle op, SW RFKill is always on */
- if (wimax_dev->op_rfkill_sw_toggle == NULL)
- wimax_dev->rf_sw = WIMAX_RF_ON;
-
- d_fnend(3, dev, "(wimax_dev %p) = 0\n", wimax_dev);
- return 0;
-
-error_rfkill_register:
- rfkill_destroy(wimax_dev->rfkill);
-error_rfkill_allocate:
- d_fnend(3, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
- return result;
-}
-
-
-/*
- * Deregister a WiMAX device's RF Kill support
- *
- * Ick, we can't call rfkill_free() after rfkill_unregister()...oh
- * well.
- *
- * WARNING: wimax_dev->mutex must be unlocked
- */
-void wimax_rfkill_rm(struct wimax_dev *wimax_dev)
-{
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
- rfkill_unregister(wimax_dev->rfkill);
- rfkill_destroy(wimax_dev->rfkill);
- d_fnend(3, dev, "(wimax_dev %p)\n", wimax_dev);
-}
-
-
-/*
- * Exporting to user space over generic netlink
- *
- * Parse the rfkill command from user space, return a combination
- * value that describe the states of the different toggles.
- *
- * Only one attribute: the new state requested (on, off or no change,
- * just query).
- */
-
-int wimax_gnl_doit_rfkill(struct sk_buff *skb, struct genl_info *info)
-{
- int result, ifindex;
- struct wimax_dev *wimax_dev;
- struct device *dev;
- enum wimax_rf_state new_state;
-
- d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
- result = -ENODEV;
- if (info->attrs[WIMAX_GNL_RFKILL_IFIDX] == NULL) {
- pr_err("WIMAX_GNL_OP_RFKILL: can't find IFIDX attribute\n");
- goto error_no_wimax_dev;
- }
- ifindex = nla_get_u32(info->attrs[WIMAX_GNL_RFKILL_IFIDX]);
- wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
- if (wimax_dev == NULL)
- goto error_no_wimax_dev;
- dev = wimax_dev_to_dev(wimax_dev);
- result = -EINVAL;
- if (info->attrs[WIMAX_GNL_RFKILL_STATE] == NULL) {
- dev_err(dev, "WIMAX_GNL_RFKILL: can't find RFKILL_STATE "
- "attribute\n");
- goto error_no_pid;
- }
- new_state = nla_get_u32(info->attrs[WIMAX_GNL_RFKILL_STATE]);
-
- /* Execute the operation and send the result back to user space */
- result = wimax_rfkill(wimax_dev, new_state);
-error_no_pid:
- dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
- d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
- return result;
-}
diff --git a/net/wimax/op-state-get.c b/net/wimax/op-state-get.c
deleted file mode 100644
index 5bc712de1563..000000000000
--- a/net/wimax/op-state-get.c
+++ /dev/null
@@ -1,52 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Implement and export a method for getting a WiMAX device current state
- *
- * Copyright (C) 2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
- *
- * Based on previous WiMAX core work by:
- * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-
-#include <net/wimax.h>
-#include <net/genetlink.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE op_state_get
-#include "debug-levels.h"
-
-
-/*
- * Exporting to user space over generic netlink
- *
- * Parse the state get command from user space, return a combination
- * value that describe the current state.
- *
- * No attributes.
- */
-int wimax_gnl_doit_state_get(struct sk_buff *skb, struct genl_info *info)
-{
- int result, ifindex;
- struct wimax_dev *wimax_dev;
-
- d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
- result = -ENODEV;
- if (info->attrs[WIMAX_GNL_STGET_IFIDX] == NULL) {
- pr_err("WIMAX_GNL_OP_STATE_GET: can't find IFIDX attribute\n");
- goto error_no_wimax_dev;
- }
- ifindex = nla_get_u32(info->attrs[WIMAX_GNL_STGET_IFIDX]);
- wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
- if (wimax_dev == NULL)
- goto error_no_wimax_dev;
- /* Execute the operation and send the result back to user space */
- result = wimax_state_get(wimax_dev);
- dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
- d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
- return result;
-}
diff --git a/net/wimax/stack.c b/net/wimax/stack.c
deleted file mode 100644
index b6dd9d956ed8..000000000000
--- a/net/wimax/stack.c
+++ /dev/null
@@ -1,609 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Initialization, addition and removal of wimax devices
- *
- * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This implements:
- *
- * - basic life cycle of 'struct wimax_dev' [wimax_dev_*()]; on
- * addition/registration initialize all subfields and allocate
- * generic netlink resources for user space communication. On
- * removal/unregistration, undo all that.
- *
- * - device state machine [wimax_state_change()] and support to send
- * reports to user space when the state changes
- * [wimax_gnl_re_state_change*()].
- *
- * See include/net/wimax.h for rationales and design.
- *
- * ROADMAP
- *
- * [__]wimax_state_change() Called by drivers to update device's state
- * wimax_gnl_re_state_change_alloc()
- * wimax_gnl_re_state_change_send()
- *
- * wimax_dev_init() Init a device
- * wimax_dev_add() Register
- * wimax_rfkill_add()
- * wimax_gnl_add() Register all the generic netlink resources.
- * wimax_id_table_add()
- * wimax_dev_rm() Unregister
- * wimax_id_table_rm()
- * wimax_gnl_rm()
- * wimax_rfkill_rm()
- */
-#include <linux/device.h>
-#include <linux/gfp.h>
-#include <net/genetlink.h>
-#include <linux/netdevice.h>
-#include <linux/wimax.h>
-#include <linux/module.h>
-#include "wimax-internal.h"
-
-
-#define D_SUBMODULE stack
-#include "debug-levels.h"
-
-static char wimax_debug_params[128];
-module_param_string(debug, wimax_debug_params, sizeof(wimax_debug_params),
- 0644);
-MODULE_PARM_DESC(debug,
- "String of space-separated NAME:VALUE pairs, where NAMEs "
- "are the different debug submodules and VALUE are the "
- "initial debug value to set.");
-
-/*
- * Authoritative source for the RE_STATE_CHANGE attribute policy
- *
- * We don't really use it here, but /me likes to keep the definition
- * close to where the data is generated.
- */
-/*
-static const struct nla_policy wimax_gnl_re_status_change[WIMAX_GNL_ATTR_MAX + 1] = {
- [WIMAX_GNL_STCH_STATE_OLD] = { .type = NLA_U8 },
- [WIMAX_GNL_STCH_STATE_NEW] = { .type = NLA_U8 },
-};
-*/
-
-
-/*
- * Allocate a Report State Change message
- *
- * @header: save it, you need it for _send()
- *
- * Creates and fills a basic state change message; different code
- * paths can then add more attributes to the message as needed.
- *
- * Use wimax_gnl_re_state_change_send() to send the returned skb.
- *
- * Returns: skb with the genl message if ok, IS_ERR() ptr on error
- * with an errno code.
- */
-static
-struct sk_buff *wimax_gnl_re_state_change_alloc(
- struct wimax_dev *wimax_dev,
- enum wimax_st new_state, enum wimax_st old_state,
- void **header)
-{
- int result;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- void *data;
- struct sk_buff *report_skb;
-
- d_fnstart(3, dev, "(wimax_dev %p new_state %u old_state %u)\n",
- wimax_dev, new_state, old_state);
- result = -ENOMEM;
- report_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (report_skb == NULL) {
- dev_err(dev, "RE_STCH: can't create message\n");
- goto error_new;
- }
- /* FIXME: sending a group ID as the seq is wrong */
- data = genlmsg_put(report_skb, 0, wimax_gnl_family.mcgrp_offset,
- &wimax_gnl_family, 0, WIMAX_GNL_RE_STATE_CHANGE);
- if (data == NULL) {
- dev_err(dev, "RE_STCH: can't put data into message\n");
- goto error_put;
- }
- *header = data;
-
- result = nla_put_u8(report_skb, WIMAX_GNL_STCH_STATE_OLD, old_state);
- if (result < 0) {
- dev_err(dev, "RE_STCH: Error adding OLD attr: %d\n", result);
- goto error_put;
- }
- result = nla_put_u8(report_skb, WIMAX_GNL_STCH_STATE_NEW, new_state);
- if (result < 0) {
- dev_err(dev, "RE_STCH: Error adding NEW attr: %d\n", result);
- goto error_put;
- }
- result = nla_put_u32(report_skb, WIMAX_GNL_STCH_IFIDX,
- wimax_dev->net_dev->ifindex);
- if (result < 0) {
- dev_err(dev, "RE_STCH: Error adding IFINDEX attribute\n");
- goto error_put;
- }
- d_fnend(3, dev, "(wimax_dev %p new_state %u old_state %u) = %p\n",
- wimax_dev, new_state, old_state, report_skb);
- return report_skb;
-
-error_put:
- nlmsg_free(report_skb);
-error_new:
- d_fnend(3, dev, "(wimax_dev %p new_state %u old_state %u) = %d\n",
- wimax_dev, new_state, old_state, result);
- return ERR_PTR(result);
-}
-
-
-/*
- * Send a Report State Change message (as created with _alloc).
- *
- * @report_skb: as returned by wimax_gnl_re_state_change_alloc()
- * @header: as returned by wimax_gnl_re_state_change_alloc()
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * If the message is NULL, pretend it didn't happen.
- */
-static
-int wimax_gnl_re_state_change_send(
- struct wimax_dev *wimax_dev, struct sk_buff *report_skb,
- void *header)
-{
- int result = 0;
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- d_fnstart(3, dev, "(wimax_dev %p report_skb %p)\n",
- wimax_dev, report_skb);
- if (report_skb == NULL) {
- result = -ENOMEM;
- goto out;
- }
- genlmsg_end(report_skb, header);
- genlmsg_multicast(&wimax_gnl_family, report_skb, 0, 0, GFP_KERNEL);
-out:
- d_fnend(3, dev, "(wimax_dev %p report_skb %p) = %d\n",
- wimax_dev, report_skb, result);
- return result;
-}
-
-
-static
-void __check_new_state(enum wimax_st old_state, enum wimax_st new_state,
- unsigned int allowed_states_bm)
-{
- if (WARN_ON(((1 << new_state) & allowed_states_bm) == 0)) {
- pr_err("SW BUG! Forbidden state change %u -> %u\n",
- old_state, new_state);
- }
-}
-
-
-/*
- * Set the current state of a WiMAX device [unlocking version of
- * wimax_state_change().
- */
-void __wimax_state_change(struct wimax_dev *wimax_dev, enum wimax_st new_state)
-{
- struct device *dev = wimax_dev_to_dev(wimax_dev);
- enum wimax_st old_state = wimax_dev->state;
- struct sk_buff *stch_skb;
- void *header;
-
- d_fnstart(3, dev, "(wimax_dev %p new_state %u [old %u])\n",
- wimax_dev, new_state, old_state);
-
- if (WARN_ON(new_state >= __WIMAX_ST_INVALID)) {
- dev_err(dev, "SW BUG: requesting invalid state %u\n",
- new_state);
- goto out;
- }
- if (old_state == new_state)
- goto out;
- header = NULL; /* gcc complains? can't grok why */
- stch_skb = wimax_gnl_re_state_change_alloc(
- wimax_dev, new_state, old_state, &header);
-
- /* Verify the state transition and do exit-from-state actions */
- switch (old_state) {
- case __WIMAX_ST_NULL:
- __check_new_state(old_state, new_state,
- 1 << WIMAX_ST_DOWN);
- break;
- case WIMAX_ST_DOWN:
- __check_new_state(old_state, new_state,
- 1 << __WIMAX_ST_QUIESCING
- | 1 << WIMAX_ST_UNINITIALIZED
- | 1 << WIMAX_ST_RADIO_OFF);
- break;
- case __WIMAX_ST_QUIESCING:
- __check_new_state(old_state, new_state, 1 << WIMAX_ST_DOWN);
- break;
- case WIMAX_ST_UNINITIALIZED:
- __check_new_state(old_state, new_state,
- 1 << __WIMAX_ST_QUIESCING
- | 1 << WIMAX_ST_RADIO_OFF);
- break;
- case WIMAX_ST_RADIO_OFF:
- __check_new_state(old_state, new_state,
- 1 << __WIMAX_ST_QUIESCING
- | 1 << WIMAX_ST_READY);
- break;
- case WIMAX_ST_READY:
- __check_new_state(old_state, new_state,
- 1 << __WIMAX_ST_QUIESCING
- | 1 << WIMAX_ST_RADIO_OFF
- | 1 << WIMAX_ST_SCANNING
- | 1 << WIMAX_ST_CONNECTING
- | 1 << WIMAX_ST_CONNECTED);
- break;
- case WIMAX_ST_SCANNING:
- __check_new_state(old_state, new_state,
- 1 << __WIMAX_ST_QUIESCING
- | 1 << WIMAX_ST_RADIO_OFF
- | 1 << WIMAX_ST_READY
- | 1 << WIMAX_ST_CONNECTING
- | 1 << WIMAX_ST_CONNECTED);
- break;
- case WIMAX_ST_CONNECTING:
- __check_new_state(old_state, new_state,
- 1 << __WIMAX_ST_QUIESCING
- | 1 << WIMAX_ST_RADIO_OFF
- | 1 << WIMAX_ST_READY
- | 1 << WIMAX_ST_SCANNING
- | 1 << WIMAX_ST_CONNECTED);
- break;
- case WIMAX_ST_CONNECTED:
- __check_new_state(old_state, new_state,
- 1 << __WIMAX_ST_QUIESCING
- | 1 << WIMAX_ST_RADIO_OFF
- | 1 << WIMAX_ST_READY);
- netif_tx_disable(wimax_dev->net_dev);
- netif_carrier_off(wimax_dev->net_dev);
- break;
- case __WIMAX_ST_INVALID:
- default:
- dev_err(dev, "SW BUG: wimax_dev %p is in unknown state %u\n",
- wimax_dev, wimax_dev->state);
- WARN_ON(1);
- goto out;
- }
-
- /* Execute the actions of entry to the new state */
- switch (new_state) {
- case __WIMAX_ST_NULL:
- dev_err(dev, "SW BUG: wimax_dev %p entering NULL state "
- "from %u\n", wimax_dev, wimax_dev->state);
- WARN_ON(1); /* Nobody can enter this state */
- break;
- case WIMAX_ST_DOWN:
- break;
- case __WIMAX_ST_QUIESCING:
- break;
- case WIMAX_ST_UNINITIALIZED:
- break;
- case WIMAX_ST_RADIO_OFF:
- break;
- case WIMAX_ST_READY:
- break;
- case WIMAX_ST_SCANNING:
- break;
- case WIMAX_ST_CONNECTING:
- break;
- case WIMAX_ST_CONNECTED:
- netif_carrier_on(wimax_dev->net_dev);
- netif_wake_queue(wimax_dev->net_dev);
- break;
- case __WIMAX_ST_INVALID:
- default:
- BUG();
- }
- __wimax_state_set(wimax_dev, new_state);
- if (!IS_ERR(stch_skb))
- wimax_gnl_re_state_change_send(wimax_dev, stch_skb, header);
-out:
- d_fnend(3, dev, "(wimax_dev %p new_state %u [old %u]) = void\n",
- wimax_dev, new_state, old_state);
-}
-
-
-/**
- * wimax_state_change - Set the current state of a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor (properly referenced)
- * @new_state: New state to switch to
- *
- * This implements the state changes for the wimax devices. It will
- *
- * - verify that the state transition is legal (for now it'll just
- * print a warning if not) according to the table in
- * linux/wimax.h's documentation for 'enum wimax_st'.
- *
- * - perform the actions needed for leaving the current state and
- * whichever are needed for entering the new state.
- *
- * - issue a report to user space indicating the new state (and an
- * optional payload with information about the new state).
- *
- * NOTE: @wimax_dev must be locked
- */
-void wimax_state_change(struct wimax_dev *wimax_dev, enum wimax_st new_state)
-{
- /*
- * A driver cannot take the wimax_dev out of the
- * __WIMAX_ST_NULL state unless by calling wimax_dev_add(). If
- * the wimax_dev's state is still NULL, we ignore any request
- * to change its state because it means it hasn't been yet
- * registered.
- *
- * There is no need to complain about it, as routines that
- * call this might be shared from different code paths that
- * are called before or after wimax_dev_add() has done its
- * job.
- */
- mutex_lock(&wimax_dev->mutex);
- if (wimax_dev->state > __WIMAX_ST_NULL)
- __wimax_state_change(wimax_dev, new_state);
- mutex_unlock(&wimax_dev->mutex);
-}
-EXPORT_SYMBOL_GPL(wimax_state_change);
-
-
-/**
- * wimax_state_get() - Return the current state of a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * Returns: Current state of the device according to its driver.
- */
-enum wimax_st wimax_state_get(struct wimax_dev *wimax_dev)
-{
- enum wimax_st state;
- mutex_lock(&wimax_dev->mutex);
- state = wimax_dev->state;
- mutex_unlock(&wimax_dev->mutex);
- return state;
-}
-EXPORT_SYMBOL_GPL(wimax_state_get);
-
-
-/**
- * wimax_dev_init - initialize a newly allocated instance
- *
- * @wimax_dev: WiMAX device descriptor to initialize.
- *
- * Initializes fields of a freshly allocated @wimax_dev instance. This
- * function assumes that after allocation, the memory occupied by
- * @wimax_dev was zeroed.
- */
-void wimax_dev_init(struct wimax_dev *wimax_dev)
-{
- INIT_LIST_HEAD(&wimax_dev->id_table_node);
- __wimax_state_set(wimax_dev, __WIMAX_ST_NULL);
- mutex_init(&wimax_dev->mutex);
- mutex_init(&wimax_dev->mutex_reset);
-}
-EXPORT_SYMBOL_GPL(wimax_dev_init);
-
-static const struct nla_policy wimax_gnl_policy[WIMAX_GNL_ATTR_MAX + 1] = {
- [WIMAX_GNL_RESET_IFIDX] = { .type = NLA_U32, },
- [WIMAX_GNL_RFKILL_IFIDX] = { .type = NLA_U32, },
- [WIMAX_GNL_RFKILL_STATE] = {
- .type = NLA_U32 /* enum wimax_rf_state */
- },
- [WIMAX_GNL_STGET_IFIDX] = { .type = NLA_U32, },
- [WIMAX_GNL_MSG_IFIDX] = { .type = NLA_U32, },
- [WIMAX_GNL_MSG_DATA] = {
- .type = NLA_UNSPEC, /* libnl doesn't grok BINARY yet */
- },
-};
-
-static const struct genl_small_ops wimax_gnl_ops[] = {
- {
- .cmd = WIMAX_GNL_OP_MSG_FROM_USER,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
- .flags = GENL_ADMIN_PERM,
- .doit = wimax_gnl_doit_msg_from_user,
- },
- {
- .cmd = WIMAX_GNL_OP_RESET,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
- .flags = GENL_ADMIN_PERM,
- .doit = wimax_gnl_doit_reset,
- },
- {
- .cmd = WIMAX_GNL_OP_RFKILL,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
- .flags = GENL_ADMIN_PERM,
- .doit = wimax_gnl_doit_rfkill,
- },
- {
- .cmd = WIMAX_GNL_OP_STATE_GET,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
- .flags = GENL_ADMIN_PERM,
- .doit = wimax_gnl_doit_state_get,
- },
-};
-
-
-static
-size_t wimax_addr_scnprint(char *addr_str, size_t addr_str_size,
- unsigned char *addr, size_t addr_len)
-{
- unsigned int cnt, total;
-
- for (total = cnt = 0; cnt < addr_len; cnt++)
- total += scnprintf(addr_str + total, addr_str_size - total,
- "%02x%c", addr[cnt],
- cnt == addr_len - 1 ? '\0' : ':');
- return total;
-}
-
-
-/**
- * wimax_dev_add - Register a new WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor (as embedded in your @net_dev's
- * priv data). You must have called wimax_dev_init() on it before.
- *
- * @net_dev: net device the @wimax_dev is associated with. The
- * function expects SET_NETDEV_DEV() and register_netdev() were
- * already called on it.
- *
- * Registers the new WiMAX device, sets up the user-kernel control
- * interface (generic netlink) and common WiMAX infrastructure.
- *
- * Note that the parts that will allow interaction with user space are
- * setup at the very end, when the rest is in place, as once that
- * happens, the driver might get user space control requests via
- * netlink or from debugfs that might translate into calls into
- * wimax_dev->op_*().
- */
-int wimax_dev_add(struct wimax_dev *wimax_dev, struct net_device *net_dev)
-{
- int result;
- struct device *dev = net_dev->dev.parent;
- char addr_str[32];
-
- d_fnstart(3, dev, "(wimax_dev %p net_dev %p)\n", wimax_dev, net_dev);
-
- /* Do the RFKILL setup before locking, as RFKILL will call
- * into our functions.
- */
- wimax_dev->net_dev = net_dev;
- result = wimax_rfkill_add(wimax_dev);
- if (result < 0)
- goto error_rfkill_add;
-
- /* Set up user-space interaction */
- mutex_lock(&wimax_dev->mutex);
- wimax_id_table_add(wimax_dev);
- wimax_debugfs_add(wimax_dev);
-
- __wimax_state_set(wimax_dev, WIMAX_ST_DOWN);
- mutex_unlock(&wimax_dev->mutex);
-
- wimax_addr_scnprint(addr_str, sizeof(addr_str),
- net_dev->dev_addr, net_dev->addr_len);
- dev_err(dev, "WiMAX interface %s (%s) ready\n",
- net_dev->name, addr_str);
- d_fnend(3, dev, "(wimax_dev %p net_dev %p) = 0\n", wimax_dev, net_dev);
- return 0;
-
-error_rfkill_add:
- d_fnend(3, dev, "(wimax_dev %p net_dev %p) = %d\n",
- wimax_dev, net_dev, result);
- return result;
-}
-EXPORT_SYMBOL_GPL(wimax_dev_add);
-
-
-/**
- * wimax_dev_rm - Unregister an existing WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * Unregisters a WiMAX device previously registered for use with
- * wimax_add_rm().
- *
- * IMPORTANT! Must call before calling unregister_netdev().
- *
- * After this function returns, you will not get any more user space
- * control requests (via netlink or debugfs) and thus to wimax_dev->ops.
- *
- * Reentrancy control is ensured by setting the state to
- * %__WIMAX_ST_QUIESCING. rfkill operations coming through
- * wimax_*rfkill*() will be stopped by the quiescing state; ops coming
- * from the rfkill subsystem will be stopped by the support being
- * removed by wimax_rfkill_rm().
- */
-void wimax_dev_rm(struct wimax_dev *wimax_dev)
-{
- d_fnstart(3, NULL, "(wimax_dev %p)\n", wimax_dev);
-
- mutex_lock(&wimax_dev->mutex);
- __wimax_state_change(wimax_dev, __WIMAX_ST_QUIESCING);
- wimax_debugfs_rm(wimax_dev);
- wimax_id_table_rm(wimax_dev);
- __wimax_state_change(wimax_dev, WIMAX_ST_DOWN);
- mutex_unlock(&wimax_dev->mutex);
- wimax_rfkill_rm(wimax_dev);
- d_fnend(3, NULL, "(wimax_dev %p) = void\n", wimax_dev);
-}
-EXPORT_SYMBOL_GPL(wimax_dev_rm);
-
-
-/* Debug framework control of debug levels */
-struct d_level D_LEVEL[] = {
- D_SUBMODULE_DEFINE(debugfs),
- D_SUBMODULE_DEFINE(id_table),
- D_SUBMODULE_DEFINE(op_msg),
- D_SUBMODULE_DEFINE(op_reset),
- D_SUBMODULE_DEFINE(op_rfkill),
- D_SUBMODULE_DEFINE(op_state_get),
- D_SUBMODULE_DEFINE(stack),
-};
-size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
-
-
-static const struct genl_multicast_group wimax_gnl_mcgrps[] = {
- { .name = "msg", },
-};
-
-struct genl_family wimax_gnl_family __ro_after_init = {
- .name = "WiMAX",
- .version = WIMAX_GNL_VERSION,
- .hdrsize = 0,
- .maxattr = WIMAX_GNL_ATTR_MAX,
- .policy = wimax_gnl_policy,
- .module = THIS_MODULE,
- .small_ops = wimax_gnl_ops,
- .n_small_ops = ARRAY_SIZE(wimax_gnl_ops),
- .mcgrps = wimax_gnl_mcgrps,
- .n_mcgrps = ARRAY_SIZE(wimax_gnl_mcgrps),
-};
-
-
-
-/* Shutdown the wimax stack */
-static
-int __init wimax_subsys_init(void)
-{
- int result;
-
- d_fnstart(4, NULL, "()\n");
- d_parse_params(D_LEVEL, D_LEVEL_SIZE, wimax_debug_params,
- "wimax.debug");
-
- result = genl_register_family(&wimax_gnl_family);
- if (unlikely(result < 0)) {
- pr_err("cannot register generic netlink family: %d\n", result);
- goto error_register_family;
- }
-
- d_fnend(4, NULL, "() = 0\n");
- return 0;
-
-error_register_family:
- d_fnend(4, NULL, "() = %d\n", result);
- return result;
-
-}
-module_init(wimax_subsys_init);
-
-
-/* Shutdown the wimax stack */
-static
-void __exit wimax_subsys_exit(void)
-{
- wimax_id_table_release();
- genl_unregister_family(&wimax_gnl_family);
-}
-module_exit(wimax_subsys_exit);
-
-MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
-MODULE_DESCRIPTION("Linux WiMAX stack");
-MODULE_LICENSE("GPL");
diff --git a/net/wimax/wimax-internal.h b/net/wimax/wimax-internal.h
deleted file mode 100644
index 40751207296c..000000000000
--- a/net/wimax/wimax-internal.h
+++ /dev/null
@@ -1,85 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Linux WiMAX
- * Internal API for kernel space WiMAX stack
- *
- * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This header file is for declarations and definitions internal to
- * the WiMAX stack. For public APIs and documentation, see
- * include/net/wimax.h and include/linux/wimax.h.
- */
-
-#ifndef __WIMAX_INTERNAL_H__
-#define __WIMAX_INTERNAL_H__
-#ifdef __KERNEL__
-
-#ifdef pr_fmt
-#undef pr_fmt
-#endif
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/device.h>
-#include <net/wimax.h>
-
-
-/*
- * Decide if a (locked) device is ready for use
- *
- * Before using the device structure, it must be locked
- * (wimax_dev->mutex). As well, most operations need to call this
- * function to check if the state is the right one.
- *
- * An error value will be returned if the state is not the right
- * one. In that case, the caller should not attempt to use the device
- * and just unlock it.
- */
-static inline __must_check
-int wimax_dev_is_ready(struct wimax_dev *wimax_dev)
-{
- if (wimax_dev->state == __WIMAX_ST_NULL)
- return -EINVAL; /* Device is not even registered! */
- if (wimax_dev->state == WIMAX_ST_DOWN)
- return -ENOMEDIUM;
- if (wimax_dev->state == __WIMAX_ST_QUIESCING)
- return -ESHUTDOWN;
- return 0;
-}
-
-
-static inline
-void __wimax_state_set(struct wimax_dev *wimax_dev, enum wimax_st state)
-{
- wimax_dev->state = state;
-}
-void __wimax_state_change(struct wimax_dev *, enum wimax_st);
-
-#ifdef CONFIG_DEBUG_FS
-void wimax_debugfs_add(struct wimax_dev *);
-void wimax_debugfs_rm(struct wimax_dev *);
-#else
-static inline void wimax_debugfs_add(struct wimax_dev *wimax_dev) {}
-static inline void wimax_debugfs_rm(struct wimax_dev *wimax_dev) {}
-#endif
-
-void wimax_id_table_add(struct wimax_dev *);
-struct wimax_dev *wimax_dev_get_by_genl_info(struct genl_info *, int);
-void wimax_id_table_rm(struct wimax_dev *);
-void wimax_id_table_release(void);
-
-int wimax_rfkill_add(struct wimax_dev *);
-void wimax_rfkill_rm(struct wimax_dev *);
-
-/* generic netlink */
-extern struct genl_family wimax_gnl_family;
-
-/* ops */
-int wimax_gnl_doit_msg_from_user(struct sk_buff *skb, struct genl_info *info);
-int wimax_gnl_doit_reset(struct sk_buff *skb, struct genl_info *info);
-int wimax_gnl_doit_rfkill(struct sk_buff *skb, struct genl_info *info);
-int wimax_gnl_doit_state_get(struct sk_buff *skb, struct genl_info *info);
-
-#endif /* #ifdef __KERNEL__ */
-#endif /* #ifndef __WIMAX_INTERNAL_H__ */
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 22d1779ab2b1..e4030f1fbc60 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -530,10 +530,10 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy,
case NL80211_IFTYPE_P2P_CLIENT:
case NL80211_IFTYPE_MONITOR:
case NL80211_IFTYPE_AP_VLAN:
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_P2P_DEVICE:
case NL80211_IFTYPE_NAN:
break;
+ case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_UNSPECIFIED:
case NUM_NL80211_IFTYPES:
WARN_ON(1);
@@ -677,12 +677,12 @@ bool cfg80211_beaconing_iface_active(struct wireless_dev *wdev)
case NL80211_IFTYPE_P2P_CLIENT:
case NL80211_IFTYPE_MONITOR:
case NL80211_IFTYPE_AP_VLAN:
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_P2P_DEVICE:
/* Can NAN type be considered as beaconing interface? */
case NL80211_IFTYPE_NAN:
break;
case NL80211_IFTYPE_UNSPECIFIED:
+ case NL80211_IFTYPE_WDS:
case NUM_NL80211_IFTYPES:
WARN_ON(1);
}
@@ -1324,12 +1324,12 @@ cfg80211_get_chan_state(struct wireless_dev *wdev,
break;
case NL80211_IFTYPE_MONITOR:
case NL80211_IFTYPE_AP_VLAN:
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_P2P_DEVICE:
case NL80211_IFTYPE_NAN:
/* these interface types don't really have a channel */
return;
case NL80211_IFTYPE_UNSPECIFIED:
+ case NL80211_IFTYPE_WDS:
case NUM_NL80211_IFTYPES:
WARN_ON(1);
}
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 240282c083aa..4b1f35e976e7 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -631,10 +631,8 @@ static int wiphy_verify_combinations(struct wiphy *wiphy)
return -EINVAL;
}
-#ifndef CONFIG_WIRELESS_WDS
if (WARN_ON(all_iftypes & BIT(NL80211_IFTYPE_WDS)))
return -EINVAL;
-#endif
/* You can't even choose that many! */
if (WARN_ON(cnt < c->max_interfaces))
@@ -675,10 +673,8 @@ int wiphy_register(struct wiphy *wiphy)
!(wiphy->nan_supported_bands & BIT(NL80211_BAND_2GHZ)))))
return -EINVAL;
-#ifndef CONFIG_WIRELESS_WDS
if (WARN_ON(wiphy->interface_modes & BIT(NL80211_IFTYPE_WDS)))
return -EINVAL;
-#endif
if (WARN_ON(wiphy->pmsr_capa && !wiphy->pmsr_capa->ftm.supported))
return -EINVAL;
@@ -1202,9 +1198,6 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev,
case NL80211_IFTYPE_OCB:
__cfg80211_leave_ocb(rdev, dev);
break;
- case NL80211_IFTYPE_WDS:
- /* must be handled by mac80211/driver, has no APIs */
- break;
case NL80211_IFTYPE_P2P_DEVICE:
case NL80211_IFTYPE_NAN:
/* cannot happen, has no netdev */
@@ -1214,6 +1207,7 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev,
/* nothing to do */
break;
case NL80211_IFTYPE_UNSPECIFIED:
+ case NL80211_IFTYPE_WDS:
case NUM_NL80211_IFTYPES:
/* invalid */
break;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index a77174b99b07..8811a4b69f21 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -715,6 +715,9 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN),
[NL80211_ATTR_S1G_CAPABILITY_MASK] =
NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN),
+ [NL80211_ATTR_SAE_PWE] =
+ NLA_POLICY_RANGE(NLA_U8, NL80211_SAE_PWE_HUNT_AND_PECK,
+ NL80211_SAE_PWE_BOTH),
};
/* policy for the key attributes */
@@ -1882,7 +1885,6 @@ static int nl80211_add_commands_unsplit(struct cfg80211_registered_device *rdev,
if (nla_put_u32(msg, i, NL80211_CMD_SET_CHANNEL))
goto nla_put_failure;
}
- CMD(set_wds_peer, SET_WDS_PEER);
if (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) {
CMD(tdls_mgmt, TDLS_MGMT);
CMD(tdls_oper, TDLS_OPER);
@@ -2860,8 +2862,8 @@ static int parse_txq_params(struct nlattr *tb[],
static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev)
{
/*
- * You can only set the channel explicitly for WDS interfaces,
- * all others have their channel managed via their respective
+ * You can only set the channel explicitly for some interfaces,
+ * most have their channel managed via their respective
* "establish a connection" command (connect, join, ...)
*
* For AP/GO and mesh mode, the channel can be set with the
@@ -3066,29 +3068,6 @@ static int nl80211_set_channel(struct sk_buff *skb, struct genl_info *info)
return __nl80211_set_channel(rdev, netdev, info);
}
-static int nl80211_set_wds_peer(struct sk_buff *skb, struct genl_info *info)
-{
- struct cfg80211_registered_device *rdev = info->user_ptr[0];
- struct net_device *dev = info->user_ptr[1];
- struct wireless_dev *wdev = dev->ieee80211_ptr;
- const u8 *bssid;
-
- if (!info->attrs[NL80211_ATTR_MAC])
- return -EINVAL;
-
- if (netif_running(dev))
- return -EBUSY;
-
- if (!rdev->ops->set_wds_peer)
- return -EOPNOTSUPP;
-
- if (wdev->iftype != NL80211_IFTYPE_WDS)
- return -EOPNOTSUPP;
-
- bssid = nla_data(info->attrs[NL80211_ATTR_MAC]);
- return rdev_set_wds_peer(rdev, dev, bssid);
-}
-
static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
{
struct cfg80211_registered_device *rdev;
@@ -4595,7 +4574,8 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
struct nlattr *attrs[],
enum nl80211_attrs attr,
struct cfg80211_bitrate_mask *mask,
- struct net_device *dev)
+ struct net_device *dev,
+ bool default_all_enabled)
{
struct nlattr *tb[NL80211_TXRATE_MAX + 1];
struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -4610,6 +4590,9 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
for (i = 0; i < NUM_NL80211_BANDS; i++) {
const struct ieee80211_sta_he_cap *he_cap;
+ if (!default_all_enabled)
+ break;
+
sband = rdev->wiphy.bands[i];
if (!sband)
@@ -4677,6 +4660,7 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
mask->control[band].ht_mcs))
return -EINVAL;
}
+
if (tb[NL80211_TXRATE_VHT]) {
if (!vht_set_mcs_mask(
sband,
@@ -4684,6 +4668,7 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
mask->control[band].vht_mcs))
return -EINVAL;
}
+
if (tb[NL80211_TXRATE_GI]) {
mask->control[band].gi =
nla_get_u8(tb[NL80211_TXRATE_GI]);
@@ -4695,6 +4680,7 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
nla_data(tb[NL80211_TXRATE_HE]),
mask->control[band].he_mcs))
return -EINVAL;
+
if (tb[NL80211_TXRATE_HE_GI])
mask->control[band].he_gi =
nla_get_u8(tb[NL80211_TXRATE_HE_GI]);
@@ -4736,7 +4722,7 @@ static int validate_beacon_tx_rate(struct cfg80211_registered_device *rdev,
enum nl80211_band band,
struct cfg80211_bitrate_mask *beacon_rate)
{
- u32 count_ht, count_vht, i;
+ u32 count_ht, count_vht, count_he, i;
u32 rate = beacon_rate->control[band].legacy;
/* Allow only one rate */
@@ -4769,7 +4755,21 @@ static int validate_beacon_tx_rate(struct cfg80211_registered_device *rdev,
return -EINVAL;
}
- if ((count_ht && count_vht) || (!rate && !count_ht && !count_vht))
+ count_he = 0;
+ for (i = 0; i < NL80211_HE_NSS_MAX; i++) {
+ if (hweight16(beacon_rate->control[band].he_mcs[i]) > 1) {
+ return -EINVAL;
+ } else if (beacon_rate->control[band].he_mcs[i]) {
+ count_he++;
+ if (count_he > 1)
+ return -EINVAL;
+ }
+ if (count_he && rate)
+ return -EINVAL;
+ }
+
+ if ((count_ht && count_vht && count_he) ||
+ (!rate && !count_ht && !count_vht && !count_he))
return -EINVAL;
if (rate &&
@@ -4784,6 +4784,10 @@ static int validate_beacon_tx_rate(struct cfg80211_registered_device *rdev,
!wiphy_ext_feature_isset(&rdev->wiphy,
NL80211_EXT_FEATURE_BEACON_RATE_VHT))
return -EINVAL;
+ if (count_he &&
+ !wiphy_ext_feature_isset(&rdev->wiphy,
+ NL80211_EXT_FEATURE_BEACON_RATE_HE))
+ return -EINVAL;
return 0;
}
@@ -5244,7 +5248,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
err = nl80211_parse_tx_bitrate_mask(info, info->attrs,
NL80211_ATTR_TX_RATES,
&params.beacon_rate,
- dev);
+ dev, false);
if (err)
return err;
@@ -9732,6 +9736,12 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev,
nla_len(info->attrs[NL80211_ATTR_SAE_PASSWORD]);
}
+ if (info->attrs[NL80211_ATTR_SAE_PWE])
+ settings->sae_pwe =
+ nla_get_u8(info->attrs[NL80211_ATTR_SAE_PWE]);
+ else
+ settings->sae_pwe = NL80211_SAE_PWE_UNSPECIFIED;
+
return 0;
}
@@ -11088,7 +11098,7 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb,
err = nl80211_parse_tx_bitrate_mask(info, info->attrs,
NL80211_ATTR_TX_RATES, &mask,
- dev);
+ dev, true);
if (err)
return err;
@@ -11697,7 +11707,7 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info)
err = nl80211_parse_tx_bitrate_mask(info, info->attrs,
NL80211_ATTR_TX_RATES,
&setup.beacon_rate,
- dev);
+ dev, false);
if (err)
return err;
@@ -14477,7 +14487,8 @@ static int parse_tid_conf(struct cfg80211_registered_device *rdev,
if (tid_conf->txrate_type != NL80211_TX_RATE_AUTOMATIC) {
attr = NL80211_TID_CONFIG_ATTR_TX_RATE;
err = nl80211_parse_tx_bitrate_mask(info, attrs, attr,
- &tid_conf->txrate_mask, dev);
+ &tid_conf->txrate_mask, dev,
+ true);
if (err)
return err;
@@ -15140,14 +15151,6 @@ static const struct genl_small_ops nl80211_small_ops[] = {
NL80211_FLAG_NEED_RTNL,
},
{
- .cmd = NL80211_CMD_SET_WDS_PEER,
- .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
- .doit = nl80211_set_wds_peer,
- .flags = GENL_UNS_ADMIN_PERM,
- .internal_flags = NL80211_FLAG_NEED_NETDEV |
- NL80211_FLAG_NEED_RTNL,
- },
- {
.cmd = NL80211_CMD_JOIN_MESH,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = nl80211_join_mesh,
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 950d57494168..5e2f349c92a8 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -582,16 +582,6 @@ static inline int rdev_get_tx_power(struct cfg80211_registered_device *rdev,
return ret;
}
-static inline int rdev_set_wds_peer(struct cfg80211_registered_device *rdev,
- struct net_device *dev, const u8 *addr)
-{
- int ret;
- trace_rdev_set_wds_peer(&rdev->wiphy, dev, addr);
- ret = rdev->ops->set_wds_peer(&rdev->wiphy, dev, addr);
- trace_rdev_return_int(&rdev->wiphy, ret);
- return ret;
-}
-
static inline int
rdev_set_multicast_to_unicast(struct cfg80211_registered_device *rdev,
struct net_device *dev,
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 8d0e49c46db3..3409f37d838b 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -694,7 +694,7 @@ static void cfg80211_scan_req_add_chan(struct cfg80211_scan_request *request,
static bool cfg80211_find_ssid_match(struct cfg80211_colocated_ap *ap,
struct cfg80211_scan_request *request)
{
- u8 i;
+ int i;
u32 s_ssid;
for (i = 0; i < request->n_ssids; i++) {
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 6e218a0acd4e..817c6fef13be 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -838,11 +838,6 @@ DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_del_mpath,
TP_ARGS(wiphy, netdev, mac)
);
-DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_set_wds_peer,
- TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, const u8 *mac),
- TP_ARGS(wiphy, netdev, mac)
-);
-
TRACE_EVENT(rdev_dump_station,
TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int _idx,
u8 *mac),
diff --git a/net/wireless/util.c b/net/wireless/util.c
index f01746894a4e..5af88037f1fb 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -550,8 +550,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
return -1;
break;
case cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS):
- if (unlikely(iftype != NL80211_IFTYPE_WDS &&
- iftype != NL80211_IFTYPE_MESH_POINT &&
+ if (unlikely(iftype != NL80211_IFTYPE_MESH_POINT &&
iftype != NL80211_IFTYPE_AP_VLAN &&
iftype != NL80211_IFTYPE_STATION))
return -1;
@@ -1051,7 +1050,6 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
case NL80211_IFTYPE_P2P_GO:
case NL80211_IFTYPE_AP:
case NL80211_IFTYPE_AP_VLAN:
- case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_MESH_POINT:
/* bridging OK */
break;
@@ -1063,6 +1061,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
/* not happening */
break;
case NL80211_IFTYPE_P2P_DEVICE:
+ case NL80211_IFTYPE_WDS:
case NL80211_IFTYPE_NAN:
WARN_ON(1);
break;
@@ -1276,20 +1275,22 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate)
static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate)
{
-#define SCALE 2048
- u16 mcs_divisors[12] = {
- 34133, /* 16.666666... */
- 17067, /* 8.333333... */
- 11378, /* 5.555555... */
- 8533, /* 4.166666... */
- 5689, /* 2.777777... */
- 4267, /* 2.083333... */
- 3923, /* 1.851851... */
- 3413, /* 1.666666... */
- 2844, /* 1.388888... */
- 2560, /* 1.250000... */
- 2276, /* 1.111111... */
- 2048, /* 1.000000... */
+#define SCALE 6144
+ u32 mcs_divisors[14] = {
+ 102399, /* 16.666666... */
+ 51201, /* 8.333333... */
+ 34134, /* 5.555555... */
+ 25599, /* 4.166666... */
+ 17067, /* 2.777777... */
+ 12801, /* 2.083333... */
+ 11769, /* 1.851851... */
+ 10239, /* 1.666666... */
+ 8532, /* 1.388888... */
+ 7680, /* 1.250000... */
+ 6828, /* 1.111111... */
+ 6144, /* 1.000000... */
+ 5690, /* 0.926106... */
+ 5120, /* 0.833333... */
};
u32 rates_160M[3] = { 960777777, 907400000, 816666666 };
u32 rates_969[3] = { 480388888, 453700000, 408333333 };
@@ -1301,7 +1302,7 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate)
u64 tmp;
u32 result;
- if (WARN_ON_ONCE(rate->mcs > 11))
+ if (WARN_ON_ONCE(rate->mcs > 13))
return 0;
if (WARN_ON_ONCE(rate->he_gi > NL80211_RATE_INFO_HE_GI_3_2))
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index 78f2927ead7f..b84a345b2653 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -49,9 +49,6 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info,
case IW_MODE_ADHOC:
type = NL80211_IFTYPE_ADHOC;
break;
- case IW_MODE_REPEAT:
- type = NL80211_IFTYPE_WDS;
- break;
case IW_MODE_MONITOR:
type = NL80211_IFTYPE_MONITOR;
break;
@@ -1150,50 +1147,6 @@ static int cfg80211_wext_giwpower(struct net_device *dev,
return 0;
}
-static int cfg80211_wds_wext_siwap(struct net_device *dev,
- struct iw_request_info *info,
- struct sockaddr *addr, char *extra)
-{
- struct wireless_dev *wdev = dev->ieee80211_ptr;
- struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
- int err;
-
- if (WARN_ON(wdev->iftype != NL80211_IFTYPE_WDS))
- return -EINVAL;
-
- if (addr->sa_family != ARPHRD_ETHER)
- return -EINVAL;
-
- if (netif_running(dev))
- return -EBUSY;
-
- if (!rdev->ops->set_wds_peer)
- return -EOPNOTSUPP;
-
- err = rdev_set_wds_peer(rdev, dev, (u8 *)&addr->sa_data);
- if (err)
- return err;
-
- memcpy(&wdev->wext.bssid, (u8 *) &addr->sa_data, ETH_ALEN);
-
- return 0;
-}
-
-static int cfg80211_wds_wext_giwap(struct net_device *dev,
- struct iw_request_info *info,
- struct sockaddr *addr, char *extra)
-{
- struct wireless_dev *wdev = dev->ieee80211_ptr;
-
- if (WARN_ON(wdev->iftype != NL80211_IFTYPE_WDS))
- return -EINVAL;
-
- addr->sa_family = ARPHRD_ETHER;
- memcpy(&addr->sa_data, wdev->wext.bssid, ETH_ALEN);
-
- return 0;
-}
-
static int cfg80211_wext_siwrate(struct net_device *dev,
struct iw_request_info *info,
struct iw_param *rate, char *extra)
@@ -1371,8 +1324,6 @@ static int cfg80211_wext_siwap(struct net_device *dev,
return cfg80211_ibss_wext_siwap(dev, info, ap_addr, extra);
case NL80211_IFTYPE_STATION:
return cfg80211_mgd_wext_siwap(dev, info, ap_addr, extra);
- case NL80211_IFTYPE_WDS:
- return cfg80211_wds_wext_siwap(dev, info, ap_addr, extra);
default:
return -EOPNOTSUPP;
}
@@ -1389,8 +1340,6 @@ static int cfg80211_wext_giwap(struct net_device *dev,
return cfg80211_ibss_wext_giwap(dev, info, ap_addr, extra);
case NL80211_IFTYPE_STATION:
return cfg80211_mgd_wext_giwap(dev, info, ap_addr, extra);
- case NL80211_IFTYPE_WDS:
- return cfg80211_wds_wext_giwap(dev, info, ap_addr, extra);
default:
return -EOPNOTSUPP;
}
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 37456d022cfa..be6351e3f3cd 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -760,9 +760,9 @@ int xfrm_input_resume(struct sk_buff *skb, int nexthdr)
}
EXPORT_SYMBOL(xfrm_input_resume);
-static void xfrm_trans_reinject(unsigned long data)
+static void xfrm_trans_reinject(struct tasklet_struct *t)
{
- struct xfrm_trans_tasklet *trans = (void *)data;
+ struct xfrm_trans_tasklet *trans = from_tasklet(trans, t, tasklet);
struct sk_buff_head queue;
struct sk_buff *skb;
@@ -818,7 +818,6 @@ void __init xfrm_input_init(void)
trans = &per_cpu(xfrm_trans_tasklet, i);
__skb_queue_head_init(&trans->queue);
- tasklet_init(&trans->tasklet, xfrm_trans_reinject,
- (unsigned long)trans);
+ tasklet_setup(&trans->tasklet, xfrm_trans_reinject);
}
}
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 9b8e292a7c6a..697cdcfbb5e1 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -319,12 +319,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
err = dst_output(xi->net, skb->sk, skb);
if (net_xmit_eval(err) == 0) {
- struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
-
- u64_stats_update_begin(&tstats->syncp);
- tstats->tx_bytes += length;
- tstats->tx_packets++;
- u64_stats_update_end(&tstats->syncp);
+ dev_sw_netstats_tx_add(dev, 1, length);
} else {
stats->tx_errors++;
stats->tx_aborted_errors++;
@@ -538,15 +533,6 @@ static int xfrmi_update(struct xfrm_if *xi, struct xfrm_if_parms *p)
return err;
}
-static void xfrmi_get_stats64(struct net_device *dev,
- struct rtnl_link_stats64 *s)
-{
- dev_fetch_sw_netstats(s, dev->tstats);
-
- s->rx_dropped = dev->stats.rx_dropped;
- s->tx_dropped = dev->stats.tx_dropped;
-}
-
static int xfrmi_get_iflink(const struct net_device *dev)
{
struct xfrm_if *xi = netdev_priv(dev);
@@ -554,12 +540,11 @@ static int xfrmi_get_iflink(const struct net_device *dev)
return xi->p.link;
}
-
static const struct net_device_ops xfrmi_netdev_ops = {
.ndo_init = xfrmi_dev_init,
.ndo_uninit = xfrmi_dev_uninit,
.ndo_start_xmit = xfrmi_xmit,
- .ndo_get_stats64 = xfrmi_get_stats64,
+ .ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = xfrmi_get_iflink,
};