aboutsummaryrefslogtreecommitdiff
path: root/net/sched/cls_api.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-11-21 08:28:08 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2024-11-21 08:28:08 -0800
commitfcc79e1714e8c2b8e216dc3149812edd37884eef (patch)
tree17a51d29db810b81412be040aaf380936b3261b4 /net/sched/cls_api.c
parent6e95ef0258ff4ee23ae3b06bf6b00b33dbbd5ef7 (diff)
parentdd7207838d38780b51e4690ee508ab2d5057e099 (diff)
downloadlinux-fcc79e1714e8c2b8e216dc3149812edd37884eef.tar.gz
linux-fcc79e1714e8c2b8e216dc3149812edd37884eef.tar.bz2
linux-fcc79e1714e8c2b8e216dc3149812edd37884eef.zip
Merge tag 'net-next-6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Paolo Abeni: "The most significant set of changes is the per netns RTNL. The new behavior is disabled by default, regression risk should be contained. Notably the new config knob PTP_1588_CLOCK_VMCLOCK will inherit its default value from PTP_1588_CLOCK_KVM, as the first is intended to be a more reliable replacement for the latter. Core: - Started a very large, in-progress, effort to make the RTNL lock scope per network-namespace, thus reducing the lock contention significantly in the containerized use-case, comprising: - RCU-ified some relevant slices of the FIB control path - introduce basic per netns locking helpers - namespacified the IPv4 address hash table - remove rtnl_register{,_module}() in favour of rtnl_register_many() - refactor rtnl_{new,del,set}link() moving as much validation as possible out of RTNL lock - convert all phonet doit() and dumpit() handlers to RCU - convert IPv4 addresses manipulation to per-netns RTNL - convert virtual interface creation to per-netns RTNL the per-netns lock infrastructure is guarded by the CONFIG_DEBUG_NET_SMALL_RTNL knob, disabled by default ad interim. - Introduce NAPI suspension, to efficiently switching between busy polling (NAPI processing suspended) and normal processing. - Migrate the IPv4 routing input, output and control path from direct ToS usage to DSCP macros. This is a work in progress to make ECN handling consistent and reliable. - Add drop reasons support to the IPv4 rotue input path, allowing better introspection in case of packets drop. - Make FIB seqnum lockless, dropping RTNL protection for read access. - Make inet{,v6} addresses hashing less predicable. - Allow providing timestamp OPT_ID via cmsg, to correlate TX packets and timestamps Things we sprinkled into general kernel code: - Add small file operations for debugfs, to reduce the struct ops size. - Refactoring and optimization for the implementation of page_frag API, This is a preparatory work to consolidate the page_frag implementation. Netfilter: - Optimize set element transactions to reduce memory consumption - Extended netlink error reporting for attribute parser failure. - Make legacy xtables configs user selectable, giving users the option to configure iptables without enabling any other config. - Address a lot of false-positive RCU issues, pointed by recent CI improvements. BPF: - Put xsk sockets on a struct diet and add various cleanups. Overall, this helps to bump performance by 12% for some workloads. - Extend BPF selftests to increase coverage of XDP features in combination with BPF cpumap. - Optimize and homogenize bpf_csum_diff helper for all archs and also add a batch of new BPF selftests for it. - Extend netkit with an option to delegate skb->{mark,priority} scrubbing to its BPF program. - Make the bpf_get_netns_cookie() helper available also to tc(x) BPF programs. Protocols: - Introduces 4-tuple hash for connected udp sockets, speeding-up significantly connected sockets lookup. - Add a fastpath for some TCP timers that usually expires after close, the socket lock contention. - Add inbound and outbound xfrm state caches to speed up state lookups. - Avoid sending MPTCP advertisements on stale subflows, reducing risks on loosing them. - Make neighbours table flushing more scalable, maintaining per device neigh lists. Driver API: - Introduce a unified interface to configure transmission H/W shaping, and expose it to user-space via generic-netlink. - Add support for per-NAPI config via netlink. This makes napi configuration persistent across queues removal and re-creation. Requires driver updates, currently supported drivers are: nVidia/Mellanox mlx4 and mlx5, Broadcom brcm and Intel ice. - Add ethtool support for writing SFP / PHY firmware blocks. - Track RSS context allocation from ethtool core. - Implement support for mirroring to DSA CPU port, via TC mirror offload. - Consolidate FDB updates notification, to avoid duplicates on device-specific entries. - Expose DPLL clock quality level to the user-space. - Support master-slave PHY config via device tree. Tests and tooling: - forwarding: introduce deferred commands, to simplify the cleanup phase Drivers: - Updated several drivers - Amazon vNic, Google vNic, Microsoft vNic, Intel e1000e and Broadcom Tigon3 - to use netdev-genl to link the IRQs and queues to NAPI IDs, allowing busy polling and better introspection. - Ethernet high-speed NICs: - nVidia/Mellanox: - mlx5: - a large refactor to implement support for cross E-Switch scheduling - refactor H/W conter management to let it scale better - H/W GRO cleanups - Intel (100G, ice):: - add support for ethtool reset - implement support for per TX queue H/W shaping - AMD/Solarflare: - implement per device queue stats support - Broadcom (bnxt): - improve wildcard l4proto on IPv4/IPv6 ntuple rules - Marvell Octeon: - Add representor support for each Resource Virtualization Unit (RVU) device. - Hisilicon: - add support for the BMC Gigabit Ethernet - IBM (EMAC): - driver cleanup and modernization - Cisco (VIC): - raise the queues number limit to 256 - Ethernet virtual: - Google vNIC: - implement page pool support - macsec: - inherit lower device's features and TSO limits when offloading - virtio_net: - enable premapped mode by default - support for XDP socket(AF_XDP) zerocopy TX - wireguard: - set the TSO max size to be GSO_MAX_SIZE, to aggregate larger packets. - Ethernet NICs embedded and virtual: - Broadcom ASP: - enable software timestamping - Freescale: - add enetc4 PF driver - MediaTek: Airoha SoC: - implement BQL support - RealTek r8169: - enable TSO by default on r8168/r8125 - implement extended ethtool stats - Renesas AVB: - enable TX checksum offload - Synopsys (stmmac): - support header splitting for vlan tagged packets - move common code for DWMAC4 and DWXGMAC into a separate FPE module. - add dwmac driver support for T-HEAD TH1520 SoC - Synopsys (xpcs): - driver refactor and cleanup - TI: - icssg_prueth: add VLAN offload support - Xilinx emaclite: - add clock support - Ethernet switches: - Microchip: - implement support for the lan969x Ethernet switch family - add LAN9646 switch support to KSZ DSA driver - Ethernet PHYs: - Marvel: 88q2x: enable auto negotiation - Microchip: add support for LAN865X Rev B1 and LAN867X Rev C1/C2 - PTP: - Add support for the Amazon virtual clock device - Add PtP driver for s390 clocks - WiFi: - mac80211 - EHT 1024 aggregation size for transmissions - new operation to indicate that a new interface is to be added - support radio separation of multi-band devices - move wireless extension spy implementation to libiw - Broadcom: - brcmfmac: optional LPO clock support - Microchip: - add support for Atmel WILC3000 - Qualcomm (ath12k): - firmware coredump collection support - add debugfs support for a multitude of statistics - Qualcomm (ath5k): - Arcadyan ARV45XX AR2417 & Gigaset SX76[23] AR241[34]A support - Realtek: - rtw88: 8821au and 8812au USB adapters support - rtw89: add thermal protection - rtw89: fine tune BT-coexsitence to improve user experience - rtw89: firmware secure boot for WiFi 6 chip - Bluetooth - add Qualcomm WCN785x support for ids Foxconn 0xe0fc/0xe0f3 and 0x13d3:0x3623 - add Realtek RTL8852BE support for id Foxconn 0xe123 - add MediaTek MT7920 support for wireless module ids - btintel_pcie: add handshake between driver and firmware - btintel_pcie: add recovery mechanism - btnxpuart: add GPIO support to power save feature" * tag 'net-next-6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1475 commits) mm: page_frag: fix a compile error when kernel is not compiled Documentation: tipc: fix formatting issue in tipc.rst selftests: nic_performance: Add selftest for performance of NIC driver selftests: nic_link_layer: Add selftest case for speed and duplex states selftests: nic_link_layer: Add link layer selftest for NIC driver bnxt_en: Add FW trace coredump segments to the coredump bnxt_en: Add a new ethtool -W dump flag bnxt_en: Add 2 parameters to bnxt_fill_coredump_seg_hdr() bnxt_en: Add functions to copy host context memory bnxt_en: Do not free FW log context memory bnxt_en: Manage the FW trace context memory bnxt_en: Allocate backing store memory for FW trace logs bnxt_en: Add a 'force' parameter to bnxt_free_ctx_mem() bnxt_en: Refactor bnxt_free_ctx_mem() bnxt_en: Add mem_valid bit to struct bnxt_ctx_mem_type bnxt_en: Update firmware interface spec to 1.10.3.85 selftests/bpf: Add some tests with sockmap SK_PASS bpf: fix recursive lock when verdict program return SK_PASS wireguard: device: support big tcp GSO wireguard: selftests: load nf_conntrack if not present ...
Diffstat (limited to 'net/sched/cls_api.c')
-rw-r--r--net/sched/cls_api.c72
1 files changed, 43 insertions, 29 deletions
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index bbc778c233c8..7578e27260c9 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1933,7 +1933,8 @@ static void tcf_chain_tp_remove(struct tcf_chain *chain,
static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain,
struct tcf_chain_info *chain_info,
u32 protocol, u32 prio,
- bool prio_allocate);
+ bool prio_allocate,
+ struct netlink_ext_ack *extack);
/* Try to insert new proto.
* If proto with specified priority already exists, free new proto
@@ -1957,8 +1958,7 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain,
return ERR_PTR(-EAGAIN);
}
- tp = tcf_chain_tp_find(chain, &chain_info,
- protocol, prio, false);
+ tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, false, NULL);
if (!tp)
err = tcf_chain_tp_insert(chain, &chain_info, tp_new);
mutex_unlock(&chain->filter_chain_lock);
@@ -2018,7 +2018,8 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain,
static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain,
struct tcf_chain_info *chain_info,
u32 protocol, u32 prio,
- bool prio_allocate)
+ bool prio_allocate,
+ struct netlink_ext_ack *extack)
{
struct tcf_proto **pprev;
struct tcf_proto *tp;
@@ -2029,9 +2030,14 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain,
pprev = &tp->next) {
if (tp->prio >= prio) {
if (tp->prio == prio) {
- if (prio_allocate ||
- (tp->protocol != protocol && protocol))
+ if (prio_allocate) {
+ NL_SET_ERR_MSG(extack, "Lowest ID from auto-alloc range already in use");
+ return ERR_PTR(-ENOSPC);
+ }
+ if (tp->protocol != protocol && protocol) {
+ NL_SET_ERR_MSG(extack, "Protocol mismatch for filter with specified priority");
return ERR_PTR(-EINVAL);
+ }
} else {
tp = NULL;
}
@@ -2297,7 +2303,7 @@ replay:
}
block->classid = parent;
- chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
+ chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0);
if (chain_index > TC_ACT_EXT_VAL_MASK) {
NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
err = -EINVAL;
@@ -2312,9 +2318,8 @@ replay:
mutex_lock(&chain->filter_chain_lock);
tp = tcf_chain_tp_find(chain, &chain_info, protocol,
- prio, prio_allocate);
+ prio, prio_allocate, extack);
if (IS_ERR(tp)) {
- NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
err = PTR_ERR(tp);
goto errout_locked;
}
@@ -2509,7 +2514,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
goto errout;
}
- chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
+ chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0);
if (chain_index > TC_ACT_EXT_VAL_MASK) {
NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
err = -EINVAL;
@@ -2539,10 +2544,13 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
mutex_lock(&chain->filter_chain_lock);
tp = tcf_chain_tp_find(chain, &chain_info, protocol,
- prio, false);
- if (!tp || IS_ERR(tp)) {
+ prio, false, extack);
+ if (!tp) {
+ err = -ENOENT;
NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
- err = tp ? PTR_ERR(tp) : -ENOENT;
+ goto errout_locked;
+ } else if (IS_ERR(tp)) {
+ err = PTR_ERR(tp);
goto errout_locked;
} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
@@ -2664,7 +2672,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
goto errout;
}
- chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
+ chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0);
if (chain_index > TC_ACT_EXT_VAL_MASK) {
NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
err = -EINVAL;
@@ -2679,11 +2687,14 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
mutex_lock(&chain->filter_chain_lock);
tp = tcf_chain_tp_find(chain, &chain_info, protocol,
- prio, false);
+ prio, false, extack);
mutex_unlock(&chain->filter_chain_lock);
- if (!tp || IS_ERR(tp)) {
+ if (!tp) {
+ err = -ENOENT;
NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
- err = tp ? PTR_ERR(tp) : -ENOENT;
+ goto errout;
+ } else if (IS_ERR(tp)) {
+ err = PTR_ERR(tp);
goto errout;
} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
@@ -3104,7 +3115,7 @@ replay:
if (IS_ERR(block))
return PTR_ERR(block);
- chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
+ chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0);
if (chain_index > TC_ACT_EXT_VAL_MASK) {
NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
err = -EINVAL;
@@ -4056,6 +4067,19 @@ static struct pernet_operations tcf_net_ops = {
.size = sizeof(struct tcf_net),
};
+static const struct rtnl_msg_handler tc_filter_rtnl_msg_handlers[] __initconst = {
+ {.msgtype = RTM_NEWTFILTER, .doit = tc_new_tfilter,
+ .flags = RTNL_FLAG_DOIT_UNLOCKED},
+ {.msgtype = RTM_DELTFILTER, .doit = tc_del_tfilter,
+ .flags = RTNL_FLAG_DOIT_UNLOCKED},
+ {.msgtype = RTM_GETTFILTER, .doit = tc_get_tfilter,
+ .dumpit = tc_dump_tfilter, .flags = RTNL_FLAG_DOIT_UNLOCKED},
+ {.msgtype = RTM_NEWCHAIN, .doit = tc_ctl_chain},
+ {.msgtype = RTM_DELCHAIN, .doit = tc_ctl_chain},
+ {.msgtype = RTM_GETCHAIN, .doit = tc_ctl_chain,
+ .dumpit = tc_dump_chain},
+};
+
static int __init tc_filter_init(void)
{
int err;
@@ -4069,17 +4093,7 @@ static int __init tc_filter_init(void)
goto err_register_pernet_subsys;
xa_init_flags(&tcf_exts_miss_cookies_xa, XA_FLAGS_ALLOC1);
-
- rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL,
- RTNL_FLAG_DOIT_UNLOCKED);
- rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL,
- RTNL_FLAG_DOIT_UNLOCKED);
- rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter,
- tc_dump_tfilter, RTNL_FLAG_DOIT_UNLOCKED);
- rtnl_register(PF_UNSPEC, RTM_NEWCHAIN, tc_ctl_chain, NULL, 0);
- rtnl_register(PF_UNSPEC, RTM_DELCHAIN, tc_ctl_chain, NULL, 0);
- rtnl_register(PF_UNSPEC, RTM_GETCHAIN, tc_ctl_chain,
- tc_dump_chain, 0);
+ rtnl_register_many(tc_filter_rtnl_msg_handlers);
return 0;