diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-06-30 15:51:09 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-06-30 15:51:09 -0700 |
commit | dbe69e43372212527abf48609aba7fc39a6daa27 (patch) | |
tree | 96cfafdf70f5325ceeac1054daf7deca339c9730 /net/xdp | |
parent | a6eaf3850cb171c328a8b0db6d3c79286a1eba9d (diff) | |
parent | b6df00789e2831fff7a2c65aa7164b2a4dcbe599 (diff) | |
download | linux-next-dbe69e43372212527abf48609aba7fc39a6daa27.tar.gz |
Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:
"Core:
- BPF:
- add syscall program type and libbpf support for generating
instructions and bindings for in-kernel BPF loaders (BPF loaders
for BPF), this is a stepping stone for signed BPF programs
- infrastructure to migrate TCP child sockets from one listener to
another in the same reuseport group/map to improve flexibility
of service hand-off/restart
- add broadcast support to XDP redirect
- allow bypass of the lockless qdisc to improving performance (for
pktgen: +23% with one thread, +44% with 2 threads)
- add a simpler version of "DO_ONCE()" which does not require jump
labels, intended for slow-path usage
- virtio/vsock: introduce SOCK_SEQPACKET support
- add getsocketopt to retrieve netns cookie
- ip: treat lowest address of a IPv4 subnet as ordinary unicast
address allowing reclaiming of precious IPv4 addresses
- ipv6: use prandom_u32() for ID generation
- ip: add support for more flexible field selection for hashing
across multi-path routes (w/ offload to mlxsw)
- icmp: add support for extended RFC 8335 PROBE (ping)
- seg6: add support for SRv6 End.DT46 behavior
- mptcp:
- DSS checksum support (RFC 8684) to detect middlebox meddling
- support Connection-time 'C' flag
- time stamping support
- sctp: packetization Layer Path MTU Discovery (RFC 8899)
- xfrm: speed up state addition with seq set
- WiFi:
- hidden AP discovery on 6 GHz and other HE 6 GHz improvements
- aggregation handling improvements for some drivers
- minstrel improvements for no-ack frames
- deferred rate control for TXQs to improve reaction times
- switch from round robin to virtual time-based airtime scheduler
- add trace points:
- tcp checksum errors
- openvswitch - action execution, upcalls
- socket errors via sk_error_report
Device APIs:
- devlink: add rate API for hierarchical control of max egress rate
of virtual devices (VFs, SFs etc.)
- don't require RCU read lock to be held around BPF hooks in NAPI
context
- page_pool: generic buffer recycling
New hardware/drivers:
- mobile:
- iosm: PCIe Driver for Intel M.2 Modem
- support for Qualcomm MSM8998 (ipa)
- WiFi: Qualcomm QCN9074 and WCN6855 PCI devices
- sparx5: Microchip SparX-5 family of Enterprise Ethernet switches
- Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)
- NXP SJA1110 Automotive Ethernet 10-port switch
- Qualcomm QCA8327 switch support (qca8k)
- Mikrotik 10/25G NIC (atl1c)
Driver changes:
- ACPI support for some MDIO, MAC and PHY devices from Marvell and
NXP (our first foray into MAC/PHY description via ACPI)
- HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx
- Mellanox/Nvidia NIC (mlx5)
- NIC VF offload of L2 bridging
- support IRQ distribution to Sub-functions
- Marvell (prestera):
- add flower and match all
- devlink trap
- link aggregation
- Netronome (nfp): connection tracking offload
- Intel 1GE (igc): add AF_XDP support
- Marvell DPU (octeontx2): ingress ratelimit offload
- Google vNIC (gve): new ring/descriptor format support
- Qualcomm mobile (rmnet & ipa): inline checksum offload support
- MediaTek WiFi (mt76)
- mt7915 MSI support
- mt7915 Tx status reporting
- mt7915 thermal sensors support
- mt7921 decapsulation offload
- mt7921 enable runtime pm and deep sleep
- Realtek WiFi (rtw88)
- beacon filter support
- Tx antenna path diversity support
- firmware crash information via devcoredump
- Qualcomm WiFi (wcn36xx)
- Wake-on-WLAN support with magic packets and GTK rekeying
- Micrel PHY (ksz886x/ksz8081): add cable test support"
* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
tcp: change ICSK_CA_PRIV_SIZE definition
tcp_yeah: check struct yeah size at compile time
gve: DQO: Fix off by one in gve_rx_dqo()
stmmac: intel: set PCI_D3hot in suspend
stmmac: intel: Enable PHY WOL option in EHL
net: stmmac: option to enable PHY WOL with PMT enabled
net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
net: use netdev_info in ndo_dflt_fdb_{add,del}
ptp: Set lookup cookie when creating a PTP PPS source.
net: sock: add trace for socket errors
net: sock: introduce sk_error_report
net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
net: dsa: include fdb entries pointing to bridge in the host fdb list
net: dsa: include bridge addresses which are local in the host fdb list
net: dsa: sync static FDB entries on foreign interfaces to hardware
net: dsa: install the host MDB and FDB entries in the master's RX filter
net: dsa: reference count the FDB addresses at the cross-chip notifier level
net: dsa: introduce a separate cross-chip notifier type for host FDBs
net: dsa: reference count the MDB entries at the cross-chip notifier level
...
Diffstat (limited to 'net/xdp')
-rw-r--r-- | net/xdp/xdp_umem.c | 7 | ||||
-rw-r--r-- | net/xdp/xsk.c | 6 | ||||
-rw-r--r-- | net/xdp/xsk.h | 4 | ||||
-rw-r--r-- | net/xdp/xsk_queue.h | 11 | ||||
-rw-r--r-- | net/xdp/xskmap.c | 32 |
5 files changed, 34 insertions, 26 deletions
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 56a28a686988..f01ef6bda390 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -27,7 +27,7 @@ static void xdp_umem_unpin_pages(struct xdp_umem *umem) { unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true); - kfree(umem->pgs); + kvfree(umem->pgs); umem->pgs = NULL; } @@ -99,8 +99,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) long npgs; int err; - umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs), - GFP_KERNEL | __GFP_NOWARN); + umem->pgs = kvcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL | __GFP_NOWARN); if (!umem->pgs) return -ENOMEM; @@ -123,7 +122,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) out_pin: xdp_umem_unpin_pages(umem); out_pgs: - kfree(umem->pgs); + kvfree(umem->pgs); umem->pgs = NULL; return err; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index cd62d4ba87a9..d6b500dc4208 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -749,7 +749,7 @@ static void xsk_unbind_dev(struct xdp_sock *xs) } static struct xsk_map *xsk_get_map_list_entry(struct xdp_sock *xs, - struct xdp_sock ***map_entry) + struct xdp_sock __rcu ***map_entry) { struct xsk_map *map = NULL; struct xsk_map_node *node; @@ -785,7 +785,7 @@ static void xsk_delete_from_maps(struct xdp_sock *xs) * might be updates to the map between * xsk_get_map_list_entry() and xsk_map_try_sock_delete(). */ - struct xdp_sock **map_entry = NULL; + struct xdp_sock __rcu **map_entry = NULL; struct xsk_map *map; while ((map = xsk_get_map_list_entry(xs, &map_entry))) { @@ -1313,7 +1313,7 @@ static int xsk_notifier(struct notifier_block *this, if (xs->dev == dev) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); xsk_unbind_dev(xs); diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h index edcf249ad1f1..a4bc4749faac 100644 --- a/net/xdp/xsk.h +++ b/net/xdp/xsk.h @@ -31,7 +31,7 @@ struct xdp_mmap_offsets_v1 { struct xsk_map_node { struct list_head node; struct xsk_map *map; - struct xdp_sock **map_entry; + struct xdp_sock __rcu **map_entry; }; static inline struct xdp_sock *xdp_sk(struct sock *sk) @@ -40,7 +40,7 @@ static inline struct xdp_sock *xdp_sk(struct sock *sk) } void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, - struct xdp_sock **map_entry); + struct xdp_sock __rcu **map_entry); void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id); int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, u16 queue_id); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 9d2a89d793c0..9ae13cccfb28 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -128,12 +128,15 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr) static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { - u64 chunk; - - if (desc->len > pool->chunk_size) - return false; + u64 chunk, chunk_end; chunk = xp_aligned_extract_addr(pool, desc->addr); + if (likely(desc->len)) { + chunk_end = xp_aligned_extract_addr(pool, desc->addr + desc->len - 1); + if (chunk != chunk_end) + return false; + } + if (chunk >= pool->addrs_cnt) return false; diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index 67b4ce504852..2e48d0e094d9 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -12,7 +12,7 @@ #include "xsk.h" static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map, - struct xdp_sock **map_entry) + struct xdp_sock __rcu **map_entry) { struct xsk_map_node *node; @@ -42,7 +42,7 @@ static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node) } static void xsk_map_sock_delete(struct xdp_sock *xs, - struct xdp_sock **map_entry) + struct xdp_sock __rcu **map_entry) { struct xsk_map_node *n, *tmp; @@ -124,6 +124,10 @@ static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) return insn - insn_buf; } +/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or + * by local_bh_disable() (from XDP calls inside NAPI). The + * rcu_read_lock_bh_held() below makes lockdep accept both. + */ static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key) { struct xsk_map *m = container_of(map, struct xsk_map, map); @@ -131,12 +135,11 @@ static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key) if (key >= map->max_entries) return NULL; - return READ_ONCE(m->xsk_map[key]); + return rcu_dereference_check(m->xsk_map[key], rcu_read_lock_bh_held()); } static void *xsk_map_lookup_elem(struct bpf_map *map, void *key) { - WARN_ON_ONCE(!rcu_read_lock_held()); return __xsk_map_lookup_elem(map, *(u32 *)key); } @@ -149,7 +152,8 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct xsk_map *m = container_of(map, struct xsk_map, map); - struct xdp_sock *xs, *old_xs, **map_entry; + struct xdp_sock __rcu **map_entry; + struct xdp_sock *xs, *old_xs; u32 i = *(u32 *)key, fd = *(u32 *)value; struct xsk_map_node *node; struct socket *sock; @@ -179,7 +183,7 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, } spin_lock_bh(&m->lock); - old_xs = READ_ONCE(*map_entry); + old_xs = rcu_dereference_protected(*map_entry, lockdep_is_held(&m->lock)); if (old_xs == xs) { err = 0; goto out; @@ -191,7 +195,7 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, goto out; } xsk_map_sock_add(xs, node); - WRITE_ONCE(*map_entry, xs); + rcu_assign_pointer(*map_entry, xs); if (old_xs) xsk_map_sock_delete(old_xs, map_entry); spin_unlock_bh(&m->lock); @@ -208,7 +212,8 @@ out: static int xsk_map_delete_elem(struct bpf_map *map, void *key) { struct xsk_map *m = container_of(map, struct xsk_map, map); - struct xdp_sock *old_xs, **map_entry; + struct xdp_sock __rcu **map_entry; + struct xdp_sock *old_xs; int k = *(u32 *)key; if (k >= map->max_entries) @@ -216,7 +221,7 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) spin_lock_bh(&m->lock); map_entry = &m->xsk_map[k]; - old_xs = xchg(map_entry, NULL); + old_xs = unrcu_pointer(xchg(map_entry, NULL)); if (old_xs) xsk_map_sock_delete(old_xs, map_entry); spin_unlock_bh(&m->lock); @@ -226,15 +231,16 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem); + return __bpf_xdp_redirect_map(map, ifindex, flags, 0, + __xsk_map_lookup_elem); } void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, - struct xdp_sock **map_entry) + struct xdp_sock __rcu **map_entry) { spin_lock_bh(&map->lock); - if (READ_ONCE(*map_entry) == xs) { - WRITE_ONCE(*map_entry, NULL); + if (rcu_access_pointer(*map_entry) == xs) { + rcu_assign_pointer(*map_entry, NULL); xsk_map_sock_delete(xs, map_entry); } spin_unlock_bh(&map->lock); |