From 8978cc921fc7fad3f4d6f91f1da01352aeeeff25 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Tue, 9 Jan 2018 11:41:10 +0200 Subject: {net,ib}/mlx5: Don't disable local loopback multicast traffic when needed There are systems platform information management interfaces (such as HOST2BMC) for which we cannot disable local loopback multicast traffic. Separate disable_local_lb_mc and disable_local_lb_uc capability bits so driver will not disable multicast loopback traffic if not supported. (It is expected that Firmware will not set disable_local_lb_mc if HOST2BMC is running for example.) Function mlx5_nic_vport_update_local_lb will do best effort to disable/enable UC/MC loopback traffic and return success only in case it succeeded to changed all allowed by Firmware. Adapt mlx5_ib and mlx5e to support the new cap bits. Fixes: 2c43c5a036be ("net/mlx5e: Enable local loopback in loopback selftest") Fixes: c85023e153e3 ("IB/mlx5: Add raw ethernet local loopback support") Fixes: bded747bb432 ("net/mlx5: Add raw ethernet local loopback firmware command") Signed-off-by: Eran Ben Elisha Cc: kernel-team@fb.com Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index d44ec5f41d4a..1391a82da98e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1027,8 +1027,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_wq_sz[0x5]; u8 nic_vport_change_event[0x1]; - u8 disable_local_lb[0x1]; - u8 reserved_at_3e2[0x9]; + u8 disable_local_lb_uc[0x1]; + u8 disable_local_lb_mc[0x1]; + u8 reserved_at_3e3[0x8]; u8 log_max_vlan_list[0x5]; u8 reserved_at_3f0[0x3]; u8 log_max_current_mc_list[0x5]; -- cgit v1.2.3 From 05e0cc84e00c54fb152d1f4b86bc211823a83d0c Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Thu, 4 Jan 2018 04:35:51 +0200 Subject: net/mlx5: Fix get vector affinity helper function mlx5_get_vector_affinity used to call pci_irq_get_affinity and after reverting the patch that sets the device affinity via PCI_IRQ_AFFINITY API, calling pci_irq_get_affinity becomes useless and it breaks RDMA mlx5 users. To fix this, this patch provides an alternative way to retrieve IRQ vector affinity using legacy IRQ API, following smp_affinity read procfs implementation. Fixes: 231243c82793 ("Revert mlx5: move affinity hints assignments to generic code") Fixes: a435393acafb ("mlx5: move affinity hints assignments to generic code") Cc: Sagi Grimberg Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1f509d072026..a0610427e168 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include @@ -1231,7 +1232,23 @@ enum { static inline const struct cpumask * mlx5_get_vector_affinity(struct mlx5_core_dev *dev, int vector) { - return pci_irq_get_affinity(dev->pdev, MLX5_EQ_VEC_COMP_BASE + vector); + const struct cpumask *mask; + struct irq_desc *desc; + unsigned int irq; + int eqn; + int err; + + err = mlx5_vector2eqn(dev, vector, &eqn, &irq); + if (err) + return NULL; + + desc = irq_to_desc(irq); +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + mask = irq_data_get_effective_affinity_mask(&desc->irq_data); +#else + mask = desc->irq_common_data.affinity; +#endif + return mask; } #endif /* MLX5_DRIVER_H */ -- cgit v1.2.3 From 51a1aaa631c90223888d8beac4d649dc11d2ca55 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 15 Jan 2018 09:32:36 +0100 Subject: mac80211_hwsim: validate number of different channels When creating a new radio on the fly, hwsim allows this to be done with an arbitrary number of channels, but cfg80211 only supports a limited number of simultaneous channels, leading to a warning. Fix this by validating the number - this requires moving the define for the maximum out to a visible header file. Reported-by: syzbot+8dd9051ff19940290931@syzkaller.appspotmail.com Fixes: b59ec8dd4394 ("mac80211_hwsim: fix number of channels in interface combinations") Signed-off-by: Johannes Berg --- drivers/net/wireless/mac80211_hwsim.c | 5 +++++ include/net/cfg80211.h | 2 ++ net/wireless/core.h | 2 -- 3 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index ccd573e53c92..f6d4a50f1bdb 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3121,6 +3121,11 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) if (info->attrs[HWSIM_ATTR_CHANNELS]) param.channels = nla_get_u32(info->attrs[HWSIM_ATTR_CHANNELS]); + if (param.channels > CFG80211_MAX_NUM_DIFFERENT_CHANNELS) { + GENL_SET_ERR_MSG(info, "too many channels specified"); + return -EINVAL; + } + if (info->attrs[HWSIM_ATTR_NO_VIF]) param.no_vif = true; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index cb4d92b79cd9..fb94a8bd8ab5 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -815,6 +815,8 @@ struct cfg80211_csa_settings { u8 count; }; +#define CFG80211_MAX_NUM_DIFFERENT_CHANNELS 10 + /** * struct iface_combination_params - input parameters for interface combinations * diff --git a/net/wireless/core.h b/net/wireless/core.h index d2f7e8b8a097..eaff636169c2 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -507,8 +507,6 @@ void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev, void cfg80211_stop_nan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); -#define CFG80211_MAX_NUM_DIFFERENT_CHANNELS 10 - #ifdef CONFIG_CFG80211_DEVELOPER_WARNINGS #define CFG80211_DEV_WARN_ON(cond) WARN_ON(cond) #else -- cgit v1.2.3 From 66940f35d5a81d5969bb5543171c70a434fc5110 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 10 Jan 2018 16:03:05 +0200 Subject: ptr_ring: document usage around __ptr_ring_peek This explains why is the net usage of __ptr_ring_peek actually ok without locks. Signed-off-by: Michael S. Tsirkin Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/ptr_ring.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 6866df4f31b5..d72b2e7dd500 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -174,6 +174,15 @@ static inline int ptr_ring_produce_bh(struct ptr_ring *r, void *ptr) * if they dereference the pointer - see e.g. PTR_RING_PEEK_CALL. * If ring is never resized, and if the pointer is merely * tested, there's no need to take the lock - see e.g. __ptr_ring_empty. + * However, if called outside the lock, and if some other CPU + * consumes ring entries at the same time, the value returned + * is not guaranteed to be correct. + * In this case - to avoid incorrectly detecting the ring + * as empty - the CPU consuming the ring entries is responsible + * for either consuming all ring entries until the ring is empty, + * or synchronizing with some other CPU and causing it to + * execute __ptr_ring_peek and/or consume the ring enteries + * after the synchronization point. */ static inline void *__ptr_ring_peek(struct ptr_ring *r) { @@ -182,10 +191,7 @@ static inline void *__ptr_ring_peek(struct ptr_ring *r) return NULL; } -/* Note: callers invoking this in a loop must use a compiler barrier, - * for example cpu_relax(). Callers must take consumer_lock - * if the ring is ever resized - see e.g. ptr_ring_empty. - */ +/* See __ptr_ring_peek above for locking rules. */ static inline bool __ptr_ring_empty(struct ptr_ring *r) { return !__ptr_ring_peek(r); -- cgit v1.2.3 From 30be8f8dba1bd2aff73e8447d59228471233a3d4 Mon Sep 17 00:00:00 2001 From: "r.hering@avm.de" Date: Fri, 12 Jan 2018 15:42:06 +0100 Subject: net/tls: Fix inverted error codes to avoid endless loop sendfile() calls can hang endless with using Kernel TLS if a socket error occurs. Socket error codes must be inverted by Kernel TLS before returning because they are stored with positive sign. If returned non-inverted they are interpreted as number of bytes sent, causing endless looping of the splice mechanic behind sendfile(). Signed-off-by: Robert Hering Signed-off-by: David S. Miller --- include/net/tls.h | 2 +- net/tls/tls_sw.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 936cfc5cab7d..9185e53a743c 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -170,7 +170,7 @@ static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx) static inline void tls_err_abort(struct sock *sk) { - sk->sk_err = -EBADMSG; + sk->sk_err = EBADMSG; sk->sk_error_report(sk); } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 73d19210dd49..9773571b6a34 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -391,7 +391,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) while (msg_data_left(msg)) { if (sk->sk_err) { - ret = sk->sk_err; + ret = -sk->sk_err; goto send_end; } @@ -544,7 +544,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, size_t copy, required_size; if (sk->sk_err) { - ret = sk->sk_err; + ret = -sk->sk_err; goto sendpage_end; } -- cgit v1.2.3 From 95a332088ecb113c2e8753fa3f1df9b0dda9beec Mon Sep 17 00:00:00 2001 From: William Tu Date: Fri, 12 Jan 2018 12:29:22 -0800 Subject: Revert "openvswitch: Add erspan tunnel support." This reverts commit ceaa001a170e43608854d5290a48064f57b565ed. The OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS attr should be designed as a nested attribute to support all ERSPAN v1 and v2's fields. The current attr is a be32 supporting only one field. Thus, this patch reverts it and later patch will redo it using nested attr. Signed-off-by: William Tu Cc: Jiri Benc Cc: Pravin Shelar Acked-by: Jiri Benc Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 1 - net/openvswitch/flow_netlink.c | 51 +--------------------------------------- 2 files changed, 1 insertion(+), 51 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 4265d7f9e1f2..dcfab5e3b55c 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -363,7 +363,6 @@ enum ovs_tunnel_key_attr { OVS_TUNNEL_KEY_ATTR_IPV6_SRC, /* struct in6_addr src IPv6 address. */ OVS_TUNNEL_KEY_ATTR_IPV6_DST, /* struct in6_addr dst IPv6 address. */ OVS_TUNNEL_KEY_ATTR_PAD, - OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, /* be32 ERSPAN index. */ __OVS_TUNNEL_KEY_ATTR_MAX }; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 624ea74353dd..f143908b651d 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -49,7 +49,6 @@ #include #include #include -#include #include "flow_netlink.h" @@ -334,8 +333,7 @@ size_t ovs_tun_key_attr_size(void) * OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS and covered by it. */ + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_SRC */ - + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_DST */ - + nla_total_size(4); /* OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS */ + + nla_total_size(2); /* OVS_TUNNEL_KEY_ATTR_TP_DST */ } static size_t ovs_nsh_key_attr_size(void) @@ -402,7 +400,6 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] .next = ovs_vxlan_ext_key_lens }, [OVS_TUNNEL_KEY_ATTR_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, [OVS_TUNNEL_KEY_ATTR_IPV6_DST] = { .len = sizeof(struct in6_addr) }, - [OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS] = { .len = sizeof(u32) }, }; static const struct ovs_len_tbl @@ -634,33 +631,6 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr, return 0; } -static int erspan_tun_opt_from_nlattr(const struct nlattr *attr, - struct sw_flow_match *match, bool is_mask, - bool log) -{ - unsigned long opt_key_offset; - struct erspan_metadata opts; - - BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts)); - - memset(&opts, 0, sizeof(opts)); - opts.index = nla_get_be32(attr); - - /* Index has only 20-bit */ - if (ntohl(opts.index) & ~INDEX_MASK) { - OVS_NLERR(log, "ERSPAN index number %x too large.", - ntohl(opts.index)); - return -EINVAL; - } - - SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), is_mask); - opt_key_offset = TUN_METADATA_OFFSET(sizeof(opts)); - SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, &opts, sizeof(opts), - is_mask); - - return 0; -} - static int ip_tun_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool log) @@ -768,19 +738,6 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, break; case OVS_TUNNEL_KEY_ATTR_PAD: break; - case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: - if (opts_type) { - OVS_NLERR(log, "Multiple metadata blocks provided"); - return -EINVAL; - } - - err = erspan_tun_opt_from_nlattr(a, match, is_mask, log); - if (err) - return err; - - tun_flags |= TUNNEL_ERSPAN_OPT; - opts_type = type; - break; default: OVS_NLERR(log, "Unknown IP tunnel attribute %d", type); @@ -905,10 +862,6 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, else if (output->tun_flags & TUNNEL_VXLAN_OPT && vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len)) return -EMSGSIZE; - else if (output->tun_flags & TUNNEL_ERSPAN_OPT && - nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, - ((struct erspan_metadata *)tun_opts)->index)) - return -EMSGSIZE; } return 0; @@ -2533,8 +2486,6 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: break; - case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: - break; } }; -- cgit v1.2.3 From cd9ff4de0107c65d69d02253bb25d6db93c3dbc1 Mon Sep 17 00:00:00 2001 From: Jim Westfall Date: Sun, 14 Jan 2018 04:18:51 -0800 Subject: ipv4: Make neigh lookup keys for loopback/point-to-point devices be INADDR_ANY Map all lookup neigh keys to INADDR_ANY for loopback/point-to-point devices to avoid making an entry for every remote ip the device needs to talk to. This used the be the old behavior but became broken in a263b3093641f (ipv4: Make neigh lookups directly in output packet path) and later removed in 0bb4087cbec0 (ipv4: Fix neigh lookup keying over loopback/point-to-point devices) because it was broken. Signed-off-by: Jim Westfall Signed-off-by: David S. Miller --- include/net/arp.h | 3 +++ net/ipv4/arp.c | 7 ++++++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/arp.h b/include/net/arp.h index dc8cd47f883b..977aabfcdc03 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -20,6 +20,9 @@ static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) + key = INADDR_ANY; + return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev); } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index a8d7c5a9fb05..6c231b43974d 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -223,11 +223,16 @@ static bool arp_key_eq(const struct neighbour *neigh, const void *pkey) static int arp_constructor(struct neighbour *neigh) { - __be32 addr = *(__be32 *)neigh->primary_key; + __be32 addr; struct net_device *dev = neigh->dev; struct in_device *in_dev; struct neigh_parms *parms; + u32 inaddr_any = INADDR_ANY; + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) + memcpy(neigh->primary_key, &inaddr_any, arp_tbl.key_len); + + addr = *(__be32 *)neigh->primary_key; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) { -- cgit v1.2.3 From 6311b7ce42e0c1d6d944bc099dc47e936c20cf11 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 15 Jan 2018 12:42:25 +0100 Subject: netlink: extack: avoid parenthesized string constant warning NL_SET_ERR_MSG() and NL_SET_ERR_MSG_ATTR() lead to the following warning in newer versions of gcc: warning: array initialized from parenthesized string constant Just remove the parentheses, they're not needed in this context since anyway since there can be no operator precendence issues or similar. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/netlink.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 49b4257ce1ea..f3075d6c7e82 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -85,7 +85,7 @@ struct netlink_ext_ack { * to the lack of an output buffer.) */ #define NL_SET_ERR_MSG(extack, msg) do { \ - static const char __msg[] = (msg); \ + static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ if (__extack) \ @@ -101,7 +101,7 @@ struct netlink_ext_ack { } while (0) #define NL_SET_ERR_MSG_ATTR(extack, attr, msg) do { \ - static const char __msg[] = (msg); \ + static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ if (__extack) { \ -- cgit v1.2.3 From 81d947e2b8dd2394586c3eaffdd2357797d3bf59 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 15 Jan 2018 23:12:09 +0100 Subject: net, sched: fix panic when updating miniq {b,q}stats While working on fixing another bug, I ran into the following panic on arm64 by simply attaching clsact qdisc, adding a filter and running traffic on ingress to it: [...] [ 178.188591] Unable to handle kernel read from unreadable memory at virtual address 810fb501f000 [ 178.197314] Mem abort info: [ 178.200121] ESR = 0x96000004 [ 178.203168] Exception class = DABT (current EL), IL = 32 bits [ 178.209095] SET = 0, FnV = 0 [ 178.212157] EA = 0, S1PTW = 0 [ 178.215288] Data abort info: [ 178.218175] ISV = 0, ISS = 0x00000004 [ 178.222019] CM = 0, WnR = 0 [ 178.224997] user pgtable: 4k pages, 48-bit VAs, pgd = 0000000023cb3f33 [ 178.231531] [0000810fb501f000] *pgd=0000000000000000 [ 178.236508] Internal error: Oops: 96000004 [#1] SMP [...] [ 178.311855] CPU: 73 PID: 2497 Comm: ping Tainted: G W 4.15.0-rc7+ #5 [ 178.319413] Hardware name: FOXCONN R2-1221R-A4/C2U4N_MB, BIOS G31FB18A 03/31/2017 [ 178.326887] pstate: 60400005 (nZCv daif +PAN -UAO) [ 178.331685] pc : __netif_receive_skb_core+0x49c/0xac8 [ 178.336728] lr : __netif_receive_skb+0x28/0x78 [ 178.341161] sp : ffff00002344b750 [ 178.344465] x29: ffff00002344b750 x28: ffff810fbdfd0580 [ 178.349769] x27: 0000000000000000 x26: ffff000009378000 [...] [ 178.418715] x1 : 0000000000000054 x0 : 0000000000000000 [ 178.424020] Process ping (pid: 2497, stack limit = 0x000000009f0a3ff4) [ 178.430537] Call trace: [ 178.432976] __netif_receive_skb_core+0x49c/0xac8 [ 178.437670] __netif_receive_skb+0x28/0x78 [ 178.441757] process_backlog+0x9c/0x160 [ 178.445584] net_rx_action+0x2f8/0x3f0 [...] Reason is that sch_ingress and sch_clsact are doing mini_qdisc_pair_init() which sets up miniq pointers to cpu_{b,q}stats from the underlying qdisc. Problem is that this cannot work since they are actually set up right after the qdisc ->init() callback in qdisc_create(), so first packet going into sch_handle_ingress() tries to call mini_qdisc_bstats_cpu_update() and we therefore panic. In order to fix this, allocation of {b,q}stats needs to happen before we call into ->init(). In net-next, there's already such option through commit d59f5ffa59d8 ("net: sched: a dflt qdisc may be used with per cpu stats"). However, the bug needs to be fixed in net still for 4.15. Thus, include these bits to reduce any merge churn and reuse the static_flags field to set TCQ_F_CPUSTATS, and remove the allocation from qdisc_create() since there is no other user left. Prashant Bhole ran into the same issue but for net-next, thus adding him below as well as co-author. Same issue was also reported by Sandipan Das when using bcc. Fixes: 46209401f8f6 ("net: core: introduce mini_Qdisc and eliminate usage of tp->q for clsact fastpath") Reference: https://lists.iovisor.org/pipermail/iovisor-dev/2018-January/001190.html Reported-by: Sandipan Das Co-authored-by: Prashant Bhole Co-authored-by: John Fastabend Signed-off-by: Daniel Borkmann Cc: Jiri Pirko Signed-off-by: David S. Miller --- include/net/sch_generic.h | 2 ++ net/sched/sch_api.c | 15 +-------------- net/sched/sch_generic.c | 18 +++++++++++++++++- net/sched/sch_ingress.c | 19 ++++--------------- 4 files changed, 24 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 83a3e47d5845..becf86aa4ac6 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -179,6 +179,7 @@ struct Qdisc_ops { const struct Qdisc_class_ops *cl_ops; char id[IFNAMSIZ]; int priv_size; + unsigned int static_flags; int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, @@ -444,6 +445,7 @@ void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n, unsigned int len); struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops); +void qdisc_free(struct Qdisc *qdisc); struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, u32 parentid); void __qdisc_calculate_pkt_len(struct sk_buff *skb, diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 0f1eab99ff4e..52529b7f8d96 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1063,17 +1063,6 @@ static struct Qdisc *qdisc_create(struct net_device *dev, } if (!ops->init || (err = ops->init(sch, tca[TCA_OPTIONS])) == 0) { - if (qdisc_is_percpu_stats(sch)) { - sch->cpu_bstats = - netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); - if (!sch->cpu_bstats) - goto err_out4; - - sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue); - if (!sch->cpu_qstats) - goto err_out4; - } - if (tca[TCA_STAB]) { stab = qdisc_get_stab(tca[TCA_STAB]); if (IS_ERR(stab)) { @@ -1115,7 +1104,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, ops->destroy(sch); err_out3: dev_put(dev); - kfree((char *) sch - sch->padded); + qdisc_free(sch); err_out2: module_put(ops->owner); err_out: @@ -1123,8 +1112,6 @@ err_out: return NULL; err_out4: - free_percpu(sch->cpu_bstats); - free_percpu(sch->cpu_qstats); /* * Any broken qdiscs that would require a ops->reset() here? * The qdisc was never in action so it shouldn't be necessary. diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 661c7144b53a..cac003fddf3e 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -633,6 +633,19 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, qdisc_skb_head_init(&sch->q); spin_lock_init(&sch->q.lock); + if (ops->static_flags & TCQ_F_CPUSTATS) { + sch->cpu_bstats = + netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); + if (!sch->cpu_bstats) + goto errout1; + + sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue); + if (!sch->cpu_qstats) { + free_percpu(sch->cpu_bstats); + goto errout1; + } + } + spin_lock_init(&sch->busylock); lockdep_set_class(&sch->busylock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); @@ -642,6 +655,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, dev->qdisc_running_key ?: &qdisc_running_key); sch->ops = ops; + sch->flags = ops->static_flags; sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; @@ -649,6 +663,8 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, refcount_set(&sch->refcnt, 1); return sch; +errout1: + kfree(p); errout: return ERR_PTR(err); } @@ -698,7 +714,7 @@ void qdisc_reset(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_reset); -static void qdisc_free(struct Qdisc *qdisc) +void qdisc_free(struct Qdisc *qdisc) { if (qdisc_is_percpu_stats(qdisc)) { free_percpu(qdisc->cpu_bstats); diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index fc1286f499c1..003e1b063447 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -66,7 +66,6 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) { struct ingress_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); - int err; net_inc_ingress_queue(); @@ -76,13 +75,7 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) q->block_info.chain_head_change = clsact_chain_head_change; q->block_info.chain_head_change_priv = &q->miniqp; - err = tcf_block_get_ext(&q->block, sch, &q->block_info); - if (err) - return err; - - sch->flags |= TCQ_F_CPUSTATS; - - return 0; + return tcf_block_get_ext(&q->block, sch, &q->block_info); } static void ingress_destroy(struct Qdisc *sch) @@ -121,6 +114,7 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { .cl_ops = &ingress_class_ops, .id = "ingress", .priv_size = sizeof(struct ingress_sched_data), + .static_flags = TCQ_F_CPUSTATS, .init = ingress_init, .destroy = ingress_destroy, .dump = ingress_dump, @@ -192,13 +186,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) q->egress_block_info.chain_head_change = clsact_chain_head_change; q->egress_block_info.chain_head_change_priv = &q->miniqp_egress; - err = tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info); - if (err) - return err; - - sch->flags |= TCQ_F_CPUSTATS; - - return 0; + return tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info); } static void clsact_destroy(struct Qdisc *sch) @@ -225,6 +213,7 @@ static struct Qdisc_ops clsact_qdisc_ops __read_mostly = { .cl_ops = &clsact_class_ops, .id = "clsact", .priv_size = sizeof(struct clsact_sched_data), + .static_flags = TCQ_F_CPUSTATS, .init = clsact_init, .destroy = clsact_destroy, .dump = ingress_dump, -- cgit v1.2.3