summaryrefslogtreecommitdiff
path: root/net/sched/cls_flower.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-07-16 19:28:34 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2024-07-16 19:28:34 -0700
commit51835949dda3783d4639cfa74ce13a3c9829de00 (patch)
tree2b593de5eba6ecc73f7c58fc65fdaffae45c7323 /net/sched/cls_flower.c
parent0434dbe32053d07d658165be681505120c6b1abc (diff)
parent77ae5e5b00720372af2860efdc4bc652ac682696 (diff)
Merge tag 'net-next-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextHEADmaster
Pull networking updates from Jakub Kicinski: "Not much excitement - a handful of large patchsets (devmem among them) did not make it in time. Core & protocols: - Use local_lock in addition to local_bh_disable() to protect per-CPU resources in networking, a step closer for local_bh_disable() not to act as a big lock on PREEMPT_RT - Use flex array for netdevice priv area, ensure its cache alignment - Add a sysctl knob to allow user to specify a default rto_min at socket init time. Bit of a big hammer but multiple companies were independently carrying such patch downstream so clearly it's useful - Support scheduling transmission of packets based on CLOCK_TAI - Un-pin TCP TIMEWAIT timer to avoid it firing on CPUs later cordoned off using cpusets - Support multiple L2TPv3 UDP tunnels using the same 5-tuple address - Allow configuration of multipath hash seed, to both allow synchronizing hashing of two routers, and preventing partial accidental sync - Improve TCP compliance with RFC 9293 for simultaneous connect() - Support sending NAT keepalives in IPsec ESP in UDP states. Userspace IKE daemon had to do this before, but the kernel can better keep track of it - Support sending supervision HSR frames with MAC addresses stored in ProxyNodeTable when RedBox (i.e. HSR-SAN) is enabled - Introduce IPPROTO_SMC for selecting SMC when socket is created - Allow UDP GSO transmit from devices with no checksum offload - openvswitch: add packet sampling via psample, separating the sampled traffic from "upcall" packets sent to user space for forwarding - nf_tables: shrink memory consumption for transaction objects Things we sprinkled into general kernel code: - Power Sequencing subsystem (used by Qualcomm Bluetooth driver for QCA6390) [ Already merged separately - Linus ] - Add IRQ information in sysfs for auxiliary bus - Introduce guard definition for local_lock - Add aligned flavor of __cacheline_group_{begin, end}() markings for grouping fields in structures BPF: - Notify user space (via epoll) when a struct_ops object is getting detached/unregistered - Add new kfuncs for a generic, open-coded bits iterator - Enable BPF programs to declare arrays of kptr, bpf_rb_root, and bpf_list_head - Support resilient split BTF which cuts down on duplication and makes BTF as compact as possible WRT BTF from modules - Add support for dumping kfunc prototypes from BTF which enables both detecting as well as dumping compilable prototypes for kfuncs - riscv64 BPF JIT improvements in particular to add 12-argument support for BPF trampolines and to utilize bpf_prog_pack for the latter - Add the capability to offload the netfilter flowtable in XDP layer through kfuncs Driver API: - Allow users to configure IRQ tresholds between which automatic IRQ moderation can choose - Expand Power Sourcing (PoE) status with power, class and failure reason. Support setting power limits - Track additional RSS contexts in the core, make sure configuration changes don't break them - Support IPsec crypto offload for IPv6 ESP and IPv4 UDP-encapsulated ESP data paths - Support updating firmware on SFP modules Tests and tooling: - mptcp: use net/lib.sh to manage netns - TCP-AO and TCP-MD5: replace debug prints used by tests with tracepoints - openvswitch: make test self-contained (don't depend on OvS CLI tools) Drivers: - Ethernet high-speed NICs: - Broadcom (bnxt): - increase the max total outstanding PTP TX packets to 4 - add timestamping statistics support - implement netdev_queue_mgmt_ops - support new RSS context API - Intel (100G, ice, idpf): - implement FEC statistics and dumping signal quality indicators - support E825C products (with 56Gbps PHYs) - nVidia/Mellanox: - support HW-GRO - mlx4/mlx5: support per-queue statistics via netlink - obey the max number of EQs setting in sub-functions - AMD/Solarflare: - support new RSS context API - AMD/Pensando: - ionic: rework fix for doorbell miss to lower overhead and skip it on new HW - Wangxun: - txgbe: support Flow Director perfect filters - Ethernet NICs consumer, embedded and virtual: - Add driver for Tehuti Networks TN40xx chips - Add driver for Meta's internal NIC chips - Add driver for Ethernet MAC on Airoha EN7581 SoCs - Add driver for Renesas Ethernet-TSN devices - Google cloud vNIC: - flow steering support - Microsoft vNIC: - support page sizes other than 4KB on ARM64 - vmware vNIC: - support latency measurement (update to version 9) - VirtIO net: - support for Byte Queue Limits - support configuring thresholds for automatic IRQ moderation - support for AF_XDP Rx zero-copy - Synopsys (stmmac): - support for STM32MP13 SoC - let platforms select the right PCS implementation - TI: - icssg-prueth: add multicast filtering support - icssg-prueth: enable PTP timestamping and PPS - Renesas: - ravb: improve Rx performance 30-400% by using page pool, theaded NAPI and timer-based IRQ coalescing - ravb: add MII support for R-Car V4M - Cadence (macb): - macb: add ARP support to Wake-On-LAN - Cortina: - use phylib for RX and TX pause configuration - Ethernet switches: - nVidia/Mellanox: - support configuration of multipath hash seed - report more accurate max MTU - use page_pool to improve Rx performance - MediaTek: - mt7530: add support for bridge port isolation - Qualcomm: - qca8k: add support for bridge port isolation - Microchip: - lan9371/2: add 100BaseTX PHY support - NXP: - vsc73xx: implement VLAN operations - Ethernet PHYs: - aquantia: enable support for aqr115c - aquantia: add support for PHY LEDs - realtek: add support for rtl8224 2.5Gbps PHY - xpcs: add memory-mapped device support - add BroadR-Reach link mode and support in Broadcom's PHY driver - CAN: - add document for ISO 15765-2 protocol support - mcp251xfd: workaround for erratum DS80000789E, use timestamps to catch when device returns incorrect FIFO status - WiFi: - mac80211/cfg80211: - parse Transmit Power Envelope (TPE) data in mac80211 instead of in drivers - improvements for 6 GHz regulatory flexibility - multi-link improvements - support multiple radios per wiphy - remove DEAUTH_NEED_MGD_TX_PREP flag - Intel (iwlwifi): - bump FW API to 91 for BZ/SC devices - report 64-bit radiotap timestamp - enable P2P low latency by default - handle Transmit Power Envelope (TPE) advertised by AP - remove support for older FW for new devices - fast resume (keeping the device configured) - mvm: re-enable Multi-Link Operation (MLO) - aggregation (A-MSDU) optimizations - MediaTek (mt76): - mt7925 Multi-Link Operation (MLO) support - Qualcomm (ath10k): - LED support for various chipsets - Qualcomm (ath12k): - remove unsupported Tx monitor handling - support channel 2 in 6 GHz band - support Spatial Multiplexing Power Save (SMPS) in 6 GHz band - supprt multiple BSSID (MBSSID) and Enhanced Multi-BSSID Advertisements (EMA) - support dynamic VLAN - add panic handler for resetting the firmware state - DebugFS support for datapath statistics - WCN7850: support for Wake on WLAN - Microchip (wilc1000): - read MAC address during probe to make it visible to user space - suspend/resume improvements - TI (wl18xx): - support newer firmware versions - RealTek (rtw89): - preparation for RTL8852BE-VT support - Wake on WLAN support for WiFi 6 chips - 36-bit PCI DMA support - RealTek (rtlwifi): - RTL8192DU support - Broadcom (brcmfmac): - Management Frame Protection support (to enable WPA3) - Bluetooth: - qualcomm: use the power sequencer for QCA6390 - btusb: mediatek: add ISO data transmission functions - hci_bcm4377: add BCM4388 support - btintel: add support for BlazarU core - btintel: add support for Whale Peak2 - btnxpuart: add support for AW693 A1 chipset - btnxpuart: add support for IW615 chipset - btusb: add Realtek RTL8852BE support ID 0x13d3:0x3591" * tag 'net-next-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1589 commits) eth: fbnic: Fix spelling mistake "tiggerring" -> "triggering" tcp: Replace strncpy() with strscpy() wifi: ath12k: fix build vs old compiler tcp: Don't access uninit tcp_rsk(req)->ao_keyid in tcp_create_openreq_child(). eth: fbnic: Write the TCAM tables used for RSS control and Rx to host eth: fbnic: Add L2 address programming eth: fbnic: Add basic Rx handling eth: fbnic: Add basic Tx handling eth: fbnic: Add link detection eth: fbnic: Add initial messaging to notify FW of our presence eth: fbnic: Implement Rx queue alloc/start/stop/free eth: fbnic: Implement Tx queue alloc/start/stop/free eth: fbnic: Allocate a netdevice and napi vectors with queues eth: fbnic: Add FW communication mechanism eth: fbnic: Add message parsing for FW messages eth: fbnic: Add register init to set PCIe/Ethernet device config eth: fbnic: Allocate core device specific structures and devlink interface eth: fbnic: Add scaffolding for Meta's NIC driver PCI: Add Meta Platforms vendor ID net/sched: cls_flower: propagate tca[TCA_OPTIONS] to NL_REQ_ATTR_CHECK ...
Diffstat (limited to 'net/sched/cls_flower.c')
-rw-r--r--net/sched/cls_flower.c132
1 files changed, 108 insertions, 24 deletions
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index fd9a6f20b60b..e280c27cb9f9 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -41,6 +41,16 @@
#define TCA_FLOWER_KEY_CT_FLAGS_MASK \
(TCA_FLOWER_KEY_CT_FLAGS_MAX - 1)
+#define TCA_FLOWER_KEY_FLAGS_POLICY_MASK \
+ (TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT | \
+ TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST)
+
+#define TCA_FLOWER_KEY_ENC_FLAGS_POLICY_MASK \
+ (TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM | \
+ TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT | \
+ TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM | \
+ TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT)
+
struct fl_flow_key {
struct flow_dissector_key_meta meta;
struct flow_dissector_key_control control;
@@ -669,8 +679,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
[TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_ENC_UDP_DST_PORT] = { .type = NLA_U16 },
[TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK] = { .type = NLA_U16 },
- [TCA_FLOWER_KEY_FLAGS] = { .type = NLA_U32 },
- [TCA_FLOWER_KEY_FLAGS_MASK] = { .type = NLA_U32 },
+ [TCA_FLOWER_KEY_FLAGS] = NLA_POLICY_MASK(NLA_BE32,
+ TCA_FLOWER_KEY_FLAGS_POLICY_MASK),
+ [TCA_FLOWER_KEY_FLAGS_MASK] = NLA_POLICY_MASK(NLA_BE32,
+ TCA_FLOWER_KEY_FLAGS_POLICY_MASK),
[TCA_FLOWER_KEY_ICMPV4_TYPE] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_ICMPV4_TYPE_MASK] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_ICMPV4_CODE] = { .type = NLA_U8 },
@@ -732,6 +744,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
[TCA_FLOWER_KEY_SPI_MASK] = { .type = NLA_U32 },
[TCA_FLOWER_L2_MISS] = NLA_POLICY_MAX(NLA_U8, 1),
[TCA_FLOWER_KEY_CFM] = { .type = NLA_NESTED },
+ [TCA_FLOWER_KEY_ENC_FLAGS] = NLA_POLICY_MASK(NLA_BE32,
+ TCA_FLOWER_KEY_ENC_FLAGS_POLICY_MASK),
+ [TCA_FLOWER_KEY_ENC_FLAGS_MASK] = NLA_POLICY_MASK(NLA_BE32,
+ TCA_FLOWER_KEY_ENC_FLAGS_POLICY_MASK),
};
static const struct nla_policy
@@ -1155,19 +1171,29 @@ static void fl_set_key_flag(u32 flower_key, u32 flower_mask,
}
}
-static int fl_set_key_flags(struct nlattr **tb, u32 *flags_key,
- u32 *flags_mask, struct netlink_ext_ack *extack)
+static int fl_set_key_flags(struct nlattr *tca_opts, struct nlattr **tb,
+ bool encap, u32 *flags_key, u32 *flags_mask,
+ struct netlink_ext_ack *extack)
{
+ int fl_key, fl_mask;
u32 key, mask;
+ if (encap) {
+ fl_key = TCA_FLOWER_KEY_ENC_FLAGS;
+ fl_mask = TCA_FLOWER_KEY_ENC_FLAGS_MASK;
+ } else {
+ fl_key = TCA_FLOWER_KEY_FLAGS;
+ fl_mask = TCA_FLOWER_KEY_FLAGS_MASK;
+ }
+
/* mask is mandatory for flags */
- if (!tb[TCA_FLOWER_KEY_FLAGS_MASK]) {
+ if (NL_REQ_ATTR_CHECK(extack, tca_opts, tb, fl_mask)) {
NL_SET_ERR_MSG(extack, "Missing flags mask");
return -EINVAL;
}
- key = be32_to_cpu(nla_get_be32(tb[TCA_FLOWER_KEY_FLAGS]));
- mask = be32_to_cpu(nla_get_be32(tb[TCA_FLOWER_KEY_FLAGS_MASK]));
+ key = be32_to_cpu(nla_get_be32(tb[fl_key]));
+ mask = be32_to_cpu(nla_get_be32(tb[fl_mask]));
*flags_key = 0;
*flags_mask = 0;
@@ -1178,6 +1204,21 @@ static int fl_set_key_flags(struct nlattr **tb, u32 *flags_key,
TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST,
FLOW_DIS_FIRST_FRAG);
+ fl_set_key_flag(key, mask, flags_key, flags_mask,
+ TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM,
+ FLOW_DIS_F_TUNNEL_CSUM);
+
+ fl_set_key_flag(key, mask, flags_key, flags_mask,
+ TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT,
+ FLOW_DIS_F_TUNNEL_DONT_FRAGMENT);
+
+ fl_set_key_flag(key, mask, flags_key, flags_mask,
+ TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM, FLOW_DIS_F_TUNNEL_OAM);
+
+ fl_set_key_flag(key, mask, flags_key, flags_mask,
+ TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT,
+ FLOW_DIS_F_TUNNEL_CRIT_OPT);
+
return 0;
}
@@ -1825,9 +1866,9 @@ static int fl_set_key_cfm(struct nlattr **tb,
return 0;
}
-static int fl_set_key(struct net *net, struct nlattr **tb,
- struct fl_flow_key *key, struct fl_flow_key *mask,
- struct netlink_ext_ack *extack)
+static int fl_set_key(struct net *net, struct nlattr *tca_opts,
+ struct nlattr **tb, struct fl_flow_key *key,
+ struct fl_flow_key *mask, struct netlink_ext_ack *extack)
{
__be16 ethertype;
int ret = 0;
@@ -2059,9 +2100,18 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
if (ret)
return ret;
- if (tb[TCA_FLOWER_KEY_FLAGS])
- ret = fl_set_key_flags(tb, &key->control.flags,
+ if (tb[TCA_FLOWER_KEY_FLAGS]) {
+ ret = fl_set_key_flags(tca_opts, tb, false,
+ &key->control.flags,
&mask->control.flags, extack);
+ if (ret)
+ return ret;
+ }
+
+ if (tb[TCA_FLOWER_KEY_ENC_FLAGS])
+ ret = fl_set_key_flags(tca_opts, tb, true,
+ &key->enc_control.flags,
+ &mask->enc_control.flags, extack);
return ret;
}
@@ -2152,7 +2202,8 @@ static void fl_init_dissector(struct flow_dissector *dissector,
FL_KEY_SET_IF_MASKED(mask, keys, cnt,
FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, enc_ipv6);
if (FL_KEY_IS_MASKED(mask, enc_ipv4) ||
- FL_KEY_IS_MASKED(mask, enc_ipv6))
+ FL_KEY_IS_MASKED(mask, enc_ipv6) ||
+ FL_KEY_IS_MASKED(mask, enc_control))
FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_ENC_CONTROL,
enc_control);
FL_KEY_SET_IF_MASKED(mask, keys, cnt,
@@ -2310,6 +2361,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
{
struct cls_fl_head *head = fl_head_dereference(tp);
bool rtnl_held = !(flags & TCA_ACT_FLAGS_NO_RTNL);
+ struct nlattr *tca_opts = tca[TCA_OPTIONS];
struct cls_fl_filter *fold = *arg;
bool bound_to_filter = false;
struct cls_fl_filter *fnew;
@@ -2318,7 +2370,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
bool in_ht;
int err;
- if (!tca[TCA_OPTIONS]) {
+ if (!tca_opts) {
err = -EINVAL;
goto errout_fold;
}
@@ -2336,7 +2388,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
}
err = nla_parse_nested_deprecated(tb, TCA_FLOWER_MAX,
- tca[TCA_OPTIONS], fl_policy, NULL);
+ tca_opts, fl_policy, NULL);
if (err < 0)
goto errout_tb;
@@ -2412,7 +2464,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
bound_to_filter = true;
}
- err = fl_set_key(net, tb, &fnew->key, &mask->key, extack);
+ err = fl_set_key(net, tca_opts, tb, &fnew->key, &mask->key, extack);
if (err)
goto unbind_filter;
@@ -2752,18 +2804,19 @@ static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain,
struct nlattr **tca,
struct netlink_ext_ack *extack)
{
+ struct nlattr *tca_opts = tca[TCA_OPTIONS];
struct fl_flow_tmplt *tmplt;
struct nlattr **tb;
int err;
- if (!tca[TCA_OPTIONS])
+ if (!tca_opts)
return ERR_PTR(-EINVAL);
tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL);
if (!tb)
return ERR_PTR(-ENOBUFS);
err = nla_parse_nested_deprecated(tb, TCA_FLOWER_MAX,
- tca[TCA_OPTIONS], fl_policy, NULL);
+ tca_opts, fl_policy, NULL);
if (err)
goto errout_tb;
@@ -2773,7 +2826,8 @@ static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain,
goto errout_tb;
}
tmplt->chain = chain;
- err = fl_set_key(net, tb, &tmplt->dummy_key, &tmplt->mask, extack);
+ err = fl_set_key(net, tca_opts, tb, &tmplt->dummy_key,
+ &tmplt->mask, extack);
if (err)
goto errout_tmplt;
@@ -3049,12 +3103,22 @@ static void fl_get_key_flag(u32 dissector_key, u32 dissector_mask,
}
}
-static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask)
+static int fl_dump_key_flags(struct sk_buff *skb, bool encap,
+ u32 flags_key, u32 flags_mask)
{
- u32 key, mask;
+ int fl_key, fl_mask;
__be32 _key, _mask;
+ u32 key, mask;
int err;
+ if (encap) {
+ fl_key = TCA_FLOWER_KEY_ENC_FLAGS;
+ fl_mask = TCA_FLOWER_KEY_ENC_FLAGS_MASK;
+ } else {
+ fl_key = TCA_FLOWER_KEY_FLAGS;
+ fl_mask = TCA_FLOWER_KEY_FLAGS_MASK;
+ }
+
if (!memchr_inv(&flags_mask, 0, sizeof(flags_mask)))
return 0;
@@ -3067,14 +3131,29 @@ static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask)
TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST,
FLOW_DIS_FIRST_FRAG);
+ fl_get_key_flag(flags_key, flags_mask, &key, &mask,
+ TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM,
+ FLOW_DIS_F_TUNNEL_CSUM);
+
+ fl_get_key_flag(flags_key, flags_mask, &key, &mask,
+ TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT,
+ FLOW_DIS_F_TUNNEL_DONT_FRAGMENT);
+
+ fl_get_key_flag(flags_key, flags_mask, &key, &mask,
+ TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM, FLOW_DIS_F_TUNNEL_OAM);
+
+ fl_get_key_flag(flags_key, flags_mask, &key, &mask,
+ TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT,
+ FLOW_DIS_F_TUNNEL_CRIT_OPT);
+
_key = cpu_to_be32(key);
_mask = cpu_to_be32(mask);
- err = nla_put(skb, TCA_FLOWER_KEY_FLAGS, 4, &_key);
+ err = nla_put(skb, fl_key, 4, &_key);
if (err)
return err;
- return nla_put(skb, TCA_FLOWER_KEY_FLAGS_MASK, 4, &_mask);
+ return nla_put(skb, fl_mask, 4, &_mask);
}
static int fl_dump_key_geneve_opt(struct sk_buff *skb,
@@ -3581,7 +3660,8 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
if (fl_dump_key_ct(skb, &key->ct, &mask->ct))
goto nla_put_failure;
- if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags))
+ if (fl_dump_key_flags(skb, false, key->control.flags,
+ mask->control.flags))
goto nla_put_failure;
if (fl_dump_key_val(skb, &key->hash.hash, TCA_FLOWER_KEY_HASH,
@@ -3592,6 +3672,10 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
if (fl_dump_key_cfm(skb, &key->cfm, &mask->cfm))
goto nla_put_failure;
+ if (fl_dump_key_flags(skb, true, key->enc_control.flags,
+ mask->enc_control.flags))
+ goto nla_put_failure;
+
return 0;
nla_put_failure: