diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-13 15:47:48 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-13 15:47:48 -0800 |
commit | 7e68dd7d07a28faa2e6574dd6b9dbd90cdeaae91 (patch) | |
tree | ae0427c5a3b905f24b3a44b510a9bcf35d9b67a3 /net/xfrm/xfrm_state.c | |
parent | 1ca06f1c1acecbe02124f14a37cce347b8c1a90c (diff) | |
parent | 7c4a6309e27f411743817fe74a832ec2d2798a4b (diff) |
Merge tag 'net-next-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Paolo Abeni:
"Core:
- Allow live renaming when an interface is up
- Add retpoline wrappers for tc, improving considerably the
performances of complex queue discipline configurations
- Add inet drop monitor support
- A few GRO performance improvements
- Add infrastructure for atomic dev stats, addressing long standing
data races
- De-duplicate common code between OVS and conntrack offloading
infrastructure
- A bunch of UBSAN_BOUNDS/FORTIFY_SOURCE improvements
- Netfilter: introduce packet parser for tunneled packets
- Replace IPVS timer-based estimators with kthreads to scale up the
workload with the number of available CPUs
- Add the helper support for connection-tracking OVS offload
BPF:
- Support for user defined BPF objects: the use case is to allocate
own objects, build own object hierarchies and use the building
blocks to build own data structures flexibly, for example, linked
lists in BPF
- Make cgroup local storage available to non-cgroup attached BPF
programs
- Avoid unnecessary deadlock detection and failures wrt BPF task
storage helpers
- A relevant bunch of BPF verifier fixes and improvements
- Veristat tool improvements to support custom filtering, sorting,
and replay of results
- Add LLVM disassembler as default library for dumping JITed code
- Lots of new BPF documentation for various BPF maps
- Add bpf_rcu_read_{,un}lock() support for sleepable programs
- Add RCU grace period chaining to BPF to wait for the completion of
access from both sleepable and non-sleepable BPF programs
- Add support storing struct task_struct objects as kptrs in maps
- Improve helper UAPI by explicitly defining BPF_FUNC_xxx integer
values
- Add libbpf *_opts API-variants for bpf_*_get_fd_by_id() functions
Protocols:
- TCP: implement Protective Load Balancing across switch links
- TCP: allow dynamically disabling TCP-MD5 static key, reverting back
to fast[er]-path
- UDP: Introduce optional per-netns hash lookup table
- IPv6: simplify and cleanup sockets disposal
- Netlink: support different type policies for each generic netlink
operation
- MPTCP: add MSG_FASTOPEN and FastOpen listener side support
- MPTCP: add netlink notification support for listener sockets events
- SCTP: add VRF support, allowing sctp sockets binding to VRF devices
- Add bridging MAC Authentication Bypass (MAB) support
- Extensions for Ethernet VPN bridging implementation to better
support multicast scenarios
- More work for Wi-Fi 7 support, comprising conversion of all the
existing drivers to internal TX queue usage
- IPSec: introduce a new offload type (packet offload) allowing
complete header processing and crypto offloading
- IPSec: extended ack support for more descriptive XFRM error
reporting
- RXRPC: increase SACK table size and move processing into a
per-local endpoint kernel thread, reducing considerably the
required locking
- IEEE 802154: synchronous send frame and extended filtering support,
initial support for scanning available 15.4 networks
- Tun: bump the link speed from 10Mbps to 10Gbps
- Tun/VirtioNet: implement UDP segmentation offload support
Driver API:
- PHY/SFP: improve power level switching between standard level 1 and
the higher power levels
- New API for netdev <-> devlink_port linkage
- PTP: convert existing drivers to new frequency adjustment
implementation
- DSA: add support for rx offloading
- Autoload DSA tagging driver when dynamically changing protocol
- Add new PCP and APPTRUST attributes to Data Center Bridging
- Add configuration support for 800Gbps link speed
- Add devlink port function attribute to enable/disable RoCE and
migratable
- Extend devlink-rate to support strict prioriry and weighted fair
queuing
- Add devlink support to directly reading from region memory
- New device tree helper to fetch MAC address from nvmem
- New big TCP helper to simplify temporary header stripping
New hardware / drivers:
- Ethernet:
- Marvel Octeon CNF95N and CN10KB Ethernet Switches
- Marvel Prestera AC5X Ethernet Switch
- WangXun 10 Gigabit NIC
- Motorcomm yt8521 Gigabit Ethernet
- Microchip ksz9563 Gigabit Ethernet Switch
- Microsoft Azure Network Adapter
- Linux Automation 10Base-T1L adapter
- PHY:
- Aquantia AQR112 and AQR412
- Motorcomm YT8531S
- PTP:
- Orolia ART-CARD
- WiFi:
- MediaTek Wi-Fi 7 (802.11be) devices
- RealTek rtw8821cu, rtw8822bu, rtw8822cu and rtw8723du USB
devices
- Bluetooth:
- Broadcom BCM4377/4378/4387 Bluetooth chipsets
- Realtek RTL8852BE and RTL8723DS
- Cypress.CYW4373A0 WiFi + Bluetooth combo device
Drivers:
- CAN:
- gs_usb: bus error reporting support
- kvaser_usb: listen only and bus error reporting support
- Ethernet NICs:
- Intel (100G):
- extend action skbedit to RX queue mapping
- implement devlink-rate support
- support direct read from memory
- nVidia/Mellanox (mlx5):
- SW steering improvements, increasing rules update rate
- Support for enhanced events compression
- extend H/W offload packet manipulation capabilities
- implement IPSec packet offload mode
- nVidia/Mellanox (mlx4):
- better big TCP support
- Netronome Ethernet NICs (nfp):
- IPsec offload support
- add support for multicast filter
- Broadcom:
- RSS and PTP support improvements
- AMD/SolarFlare:
- netlink extened ack improvements
- add basic flower matches to offload, and related stats
- Virtual NICs:
- ibmvnic: introduce affinity hint support
- small / embedded:
- FreeScale fec: add initial XDP support
- Marvel mv643xx_eth: support MII/GMII/RGMII modes for Kirkwood
- TI am65-cpsw: add suspend/resume support
- Mediatek MT7986: add RX wireless wthernet dispatch support
- Realtek 8169: enable GRO software interrupt coalescing per
default
- Ethernet high-speed switches:
- Microchip (sparx5):
- add support for Sparx5 TC/flower H/W offload via VCAP
- Mellanox mlxsw:
- add 802.1X and MAC Authentication Bypass offload support
- add ip6gre support
- Embedded Ethernet switches:
- Mediatek (mtk_eth_soc):
- improve PCS implementation, add DSA untag support
- enable flow offload support
- Renesas:
- add rswitch R-Car Gen4 gPTP support
- Microchip (lan966x):
- add full XDP support
- add TC H/W offload via VCAP
- enable PTP on bridge interfaces
- Microchip (ksz8):
- add MTU support for KSZ8 series
- Qualcomm 802.11ax WiFi (ath11k):
- support configuring channel dwell time during scan
- MediaTek WiFi (mt76):
- enable Wireless Ethernet Dispatch (WED) offload support
- add ack signal support
- enable coredump support
- remain_on_channel support
- Intel WiFi (iwlwifi):
- enable Wi-Fi 7 Extremely High Throughput (EHT) PHY capabilities
- 320 MHz channels support
- RealTek WiFi (rtw89):
- new dynamic header firmware format support
- wake-over-WLAN support"
* tag 'net-next-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2002 commits)
ipvs: fix type warning in do_div() on 32 bit
net: lan966x: Remove a useless test in lan966x_ptp_add_trap()
net: ipa: add IPA v4.7 support
dt-bindings: net: qcom,ipa: Add SM6350 compatible
bnxt: Use generic HBH removal helper in tx path
IPv6/GRO: generic helper to remove temporary HBH/jumbo header in driver
selftests: forwarding: Add bridge MDB test
selftests: forwarding: Rename bridge_mdb test
bridge: mcast: Support replacement of MDB port group entries
bridge: mcast: Allow user space to specify MDB entry routing protocol
bridge: mcast: Allow user space to add (*, G) with a source list and filter mode
bridge: mcast: Add support for (*, G) with a source list and filter mode
bridge: mcast: Avoid arming group timer when (S, G) corresponds to a source
bridge: mcast: Add a flag for user installed source entries
bridge: mcast: Expose __br_multicast_del_group_src()
bridge: mcast: Expose br_multicast_new_group_src()
bridge: mcast: Add a centralized error path
bridge: mcast: Place netlink policy before validation functions
bridge: mcast: Split (*, G) and (S, G) addition into different functions
bridge: mcast: Do not derive entry type from its filter mode
...
Diffstat (limited to 'net/xfrm/xfrm_state.c')
-rw-r--r-- | net/xfrm/xfrm_state.c | 212 |
1 files changed, 189 insertions, 23 deletions
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index d63a3644ee1a..89c731f4f0c7 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -84,6 +84,25 @@ static unsigned int xfrm_seq_hash(struct net *net, u32 seq) return __xfrm_seq_hash(seq, net->xfrm.state_hmask); } +#define XFRM_STATE_INSERT(by, _n, _h, _type) \ + { \ + struct xfrm_state *_x = NULL; \ + \ + if (_type != XFRM_DEV_OFFLOAD_PACKET) { \ + hlist_for_each_entry_rcu(_x, _h, by) { \ + if (_x->xso.type == XFRM_DEV_OFFLOAD_PACKET) \ + continue; \ + break; \ + } \ + } \ + \ + if (!_x || _x->xso.type == XFRM_DEV_OFFLOAD_PACKET) \ + /* SAD is empty or consist from HW SAs only */ \ + hlist_add_head_rcu(_n, _h); \ + else \ + hlist_add_before_rcu(_n, &_x->by); \ + } + static void xfrm_hash_transfer(struct hlist_head *list, struct hlist_head *ndsttable, struct hlist_head *nsrctable, @@ -100,23 +119,25 @@ static void xfrm_hash_transfer(struct hlist_head *list, h = __xfrm_dst_hash(&x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family, nhashmask); - hlist_add_head_rcu(&x->bydst, ndsttable + h); + XFRM_STATE_INSERT(bydst, &x->bydst, ndsttable + h, x->xso.type); h = __xfrm_src_hash(&x->id.daddr, &x->props.saddr, x->props.family, nhashmask); - hlist_add_head_rcu(&x->bysrc, nsrctable + h); + XFRM_STATE_INSERT(bysrc, &x->bysrc, nsrctable + h, x->xso.type); if (x->id.spi) { h = __xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, x->props.family, nhashmask); - hlist_add_head_rcu(&x->byspi, nspitable + h); + XFRM_STATE_INSERT(byspi, &x->byspi, nspitable + h, + x->xso.type); } if (x->km.seq) { h = __xfrm_seq_hash(x->km.seq, nhashmask); - hlist_add_head_rcu(&x->byseq, nseqtable + h); + XFRM_STATE_INSERT(byseq, &x->byseq, nseqtable + h, + x->xso.type); } } } @@ -549,6 +570,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) int err = 0; spin_lock(&x->lock); + xfrm_dev_state_update_curlft(x); + if (x->km.state == XFRM_STATE_DEAD) goto out; if (x->km.state == XFRM_STATE_EXPIRED) @@ -951,6 +974,49 @@ xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl, x->props.family = tmpl->encap_family; } +static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark, + const xfrm_address_t *daddr, + __be32 spi, u8 proto, + unsigned short family, + struct xfrm_dev_offload *xdo) +{ + unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family); + struct xfrm_state *x; + + hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) { +#ifdef CONFIG_XFRM_OFFLOAD + if (xdo->type == XFRM_DEV_OFFLOAD_PACKET) { + if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) + /* HW states are in the head of list, there is + * no need to iterate further. + */ + break; + + /* Packet offload: both policy and SA should + * have same device. + */ + if (xdo->dev != x->xso.dev) + continue; + } else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) + /* Skip HW policy for SW lookups */ + continue; +#endif + if (x->props.family != family || + x->id.spi != spi || + x->id.proto != proto || + !xfrm_addr_equal(&x->id.daddr, daddr, family)) + continue; + + if ((mark & x->mark.m) != x->mark.v) + continue; + if (!xfrm_state_hold_rcu(x)) + continue; + return x; + } + + return NULL; +} + static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, @@ -1092,6 +1158,23 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, rcu_read_lock(); h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) { +#ifdef CONFIG_XFRM_OFFLOAD + if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { + if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) + /* HW states are in the head of list, there is + * no need to iterate further. + */ + break; + + /* Packet offload: both policy and SA should + * have same device. + */ + if (pol->xdo.dev != x->xso.dev) + continue; + } else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) + /* Skip HW policy for SW lookups */ + continue; +#endif if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && @@ -1109,6 +1192,23 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family); hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h_wildcard, bydst) { +#ifdef CONFIG_XFRM_OFFLOAD + if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { + if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) + /* HW states are in the head of list, there is + * no need to iterate further. + */ + break; + + /* Packet offload: both policy and SA should + * have same device. + */ + if (pol->xdo.dev != x->xso.dev) + continue; + } else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) + /* Skip HW policy for SW lookups */ + continue; +#endif if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && @@ -1126,8 +1226,10 @@ found: x = best; if (!x && !error && !acquire_in_progress) { if (tmpl->id.spi && - (x0 = __xfrm_state_lookup(net, mark, daddr, tmpl->id.spi, - tmpl->id.proto, encap_family)) != NULL) { + (x0 = __xfrm_state_lookup_all(net, mark, daddr, + tmpl->id.spi, tmpl->id.proto, + encap_family, + &pol->xdo)) != NULL) { to_put = x0; error = -EEXIST; goto out; @@ -1161,21 +1263,53 @@ found: x = NULL; goto out; } - +#ifdef CONFIG_XFRM_OFFLOAD + if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { + struct xfrm_dev_offload *xdo = &pol->xdo; + struct xfrm_dev_offload *xso = &x->xso; + + xso->type = XFRM_DEV_OFFLOAD_PACKET; + xso->dir = xdo->dir; + xso->dev = xdo->dev; + xso->real_dev = xdo->real_dev; + netdev_tracker_alloc(xso->dev, &xso->dev_tracker, + GFP_ATOMIC); + error = xso->dev->xfrmdev_ops->xdo_dev_state_add(x); + if (error) { + xso->dir = 0; + netdev_put(xso->dev, &xso->dev_tracker); + xso->dev = NULL; + xso->real_dev = NULL; + xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; + x->km.state = XFRM_STATE_DEAD; + to_put = x; + x = NULL; + goto out; + } + } +#endif if (km_query(x, tmpl, pol) == 0) { spin_lock_bh(&net->xfrm.xfrm_state_lock); x->km.state = XFRM_STATE_ACQ; list_add(&x->km.all, &net->xfrm.state_all); - hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h); + XFRM_STATE_INSERT(bydst, &x->bydst, + net->xfrm.state_bydst + h, + x->xso.type); h = xfrm_src_hash(net, daddr, saddr, encap_family); - hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h); + XFRM_STATE_INSERT(bysrc, &x->bysrc, + net->xfrm.state_bysrc + h, + x->xso.type); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family); - hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); + XFRM_STATE_INSERT(byspi, &x->byspi, + net->xfrm.state_byspi + h, + x->xso.type); } if (x->km.seq) { h = xfrm_seq_hash(net, x->km.seq); - hlist_add_head_rcu(&x->byseq, net->xfrm.state_byseq + h); + XFRM_STATE_INSERT(byseq, &x->byseq, + net->xfrm.state_byseq + h, + x->xso.type); } x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; hrtimer_start(&x->mtimer, @@ -1185,6 +1319,18 @@ found: xfrm_hash_grow_check(net, x->bydst.next != NULL); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } else { +#ifdef CONFIG_XFRM_OFFLOAD + struct xfrm_dev_offload *xso = &x->xso; + + if (xso->type == XFRM_DEV_OFFLOAD_PACKET) { + xso->dev->xfrmdev_ops->xdo_dev_state_delete(x); + xso->dir = 0; + netdev_put(xso->dev, &xso->dev_tracker); + xso->dev = NULL; + xso->real_dev = NULL; + xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; + } +#endif x->km.state = XFRM_STATE_DEAD; to_put = x; x = NULL; @@ -1280,22 +1426,26 @@ static void __xfrm_state_insert(struct xfrm_state *x) h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family); - hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h); + XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, + x->xso.type); h = xfrm_src_hash(net, &x->id.daddr, &x->props.saddr, x->props.family); - hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h); + XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h, + x->xso.type); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); - hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); + XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, + x->xso.type); } if (x->km.seq) { h = xfrm_seq_hash(net, x->km.seq); - hlist_add_head_rcu(&x->byseq, net->xfrm.state_byseq + h); + XFRM_STATE_INSERT(byseq, &x->byseq, net->xfrm.state_byseq + h, + x->xso.type); } hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); @@ -1409,9 +1559,11 @@ static struct xfrm_state *__find_acq_core(struct net *net, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL_SOFT); list_add(&x->km.all, &net->xfrm.state_all); - hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h); + XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, + x->xso.type); h = xfrm_src_hash(net, daddr, saddr, family); - hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h); + XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h, + x->xso.type); net->xfrm.state_num++; @@ -1786,6 +1938,8 @@ EXPORT_SYMBOL(xfrm_state_update); int xfrm_state_check_expire(struct xfrm_state *x) { + xfrm_dev_state_update_curlft(x); + if (!x->curlft.use_time) x->curlft.use_time = ktime_get_real_seconds(); @@ -2017,7 +2171,7 @@ u32 xfrm_get_acqseq(void) } EXPORT_SYMBOL(xfrm_get_acqseq); -int verify_spi_info(u8 proto, u32 min, u32 max) +int verify_spi_info(u8 proto, u32 min, u32 max, struct netlink_ext_ack *extack) { switch (proto) { case IPPROTO_AH: @@ -2026,22 +2180,28 @@ int verify_spi_info(u8 proto, u32 min, u32 max) case IPPROTO_COMP: /* IPCOMP spi is 16-bits. */ - if (max >= 0x10000) + if (max >= 0x10000) { + NL_SET_ERR_MSG(extack, "IPCOMP SPI must be <= 65535"); return -EINVAL; + } break; default: + NL_SET_ERR_MSG(extack, "Invalid protocol, must be one of AH, ESP, IPCOMP"); return -EINVAL; } - if (min > max) + if (min > max) { + NL_SET_ERR_MSG(extack, "Invalid SPI range: min > max"); return -EINVAL; + } return 0; } EXPORT_SYMBOL(verify_spi_info); -int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) +int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high, + struct netlink_ext_ack *extack) { struct net *net = xs_net(x); unsigned int h; @@ -2053,8 +2213,10 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) u32 mark = x->mark.v & x->mark.m; spin_lock_bh(&x->lock); - if (x->km.state == XFRM_STATE_DEAD) + if (x->km.state == XFRM_STATE_DEAD) { + NL_SET_ERR_MSG(extack, "Target ACQUIRE is in DEAD state"); goto unlock; + } err = 0; if (x->id.spi) @@ -2065,6 +2227,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) if (minspi == maxspi) { x0 = xfrm_state_lookup(net, mark, &x->id.daddr, minspi, x->id.proto, x->props.family); if (x0) { + NL_SET_ERR_MSG(extack, "Requested SPI is already in use"); xfrm_state_put(x0); goto unlock; } @@ -2085,10 +2248,13 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) spin_lock_bh(&net->xfrm.xfrm_state_lock); x->id.spi = newspi; h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); - hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); + XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, + x->xso.type); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = 0; + } else { + NL_SET_ERR_MSG(extack, "No SPI available in the requested range"); } unlock: |