From 2da2b32fd9346009e9acdb68c570ca8d3966aba7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 15 Oct 2019 21:18:08 +0200 Subject: sched/rt, net: Use CONFIG_PREEMPTION.patch CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT. Both PREEMPT and PREEMPT_RT require the same functionality which today depends on CONFIG_PREEMPT. Update the comment to use CONFIG_PREEMPTION. Signed-off-by: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Acked-by: David S. Miller Cc: Linus Torvalds Cc: Peter Zijlstra Cc: netdev@vger.kernel.org Link: https://lore.kernel.org/r/20191015191821.11479-22-bigeasy@linutronix.de Signed-off-by: Ingo Molnar --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 46580b290450..de5f14bc639d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -928,7 +928,7 @@ EXPORT_SYMBOL(dev_get_by_napi_id); * * The use of raw_seqcount_begin() and cond_resched() before * retrying is required as we want to give the writers a chance - * to complete when CONFIG_PREEMPT is not set. + * to complete when CONFIG_PREEMPTION is not set. */ int netdev_get_name(struct net *net, char *name, int ifindex) { -- cgit v1.2.3 From 7e6897f95935973c3253fd756135b5ea58043dc8 Mon Sep 17 00:00:00 2001 From: Björn Töpel Date: Fri, 13 Dec 2019 18:51:09 +0100 Subject: bpf, xdp: Start using the BPF dispatcher for XDP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This commit adds a BPF dispatcher for XDP. The dispatcher is updated from the XDP control-path, dev_xdp_install(), and used when an XDP program is run via bpf_prog_run_xdp(). Signed-off-by: Björn Töpel Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20191213175112.30208-4-bjorn.topel@gmail.com --- include/linux/bpf.h | 15 +++++++++++++++ include/linux/filter.h | 40 ++++++++++++++++++++++++---------------- kernel/bpf/syscall.c | 26 ++++++++++++++++++-------- net/core/dev.c | 19 ++++++++++++++++++- net/core/filter.c | 8 ++++++++ 5 files changed, 83 insertions(+), 25 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 53ae4a50abe4..5970989b99d1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -488,6 +488,14 @@ struct bpf_dispatcher { u32 image_off; }; +static __always_inline unsigned int bpf_dispatcher_nopfunc( + const void *ctx, + const struct bpf_insn *insnsi, + unsigned int (*bpf_func)(const void *, + const struct bpf_insn *)) +{ + return bpf_func(ctx, insnsi); +} #ifdef CONFIG_BPF_JIT struct bpf_trampoline *bpf_trampoline_lookup(u64 key); int bpf_trampoline_link_prog(struct bpf_prog *prog); @@ -997,6 +1005,8 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog); +struct bpf_prog *bpf_prog_by_id(u32 id); + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -1128,6 +1138,11 @@ static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, static inline void bpf_map_put(struct bpf_map *map) { } + +static inline struct bpf_prog *bpf_prog_by_id(u32 id) +{ + return ERR_PTR(-ENOTSUPP); +} #endif /* CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, diff --git a/include/linux/filter.h b/include/linux/filter.h index a141cb07e76a..37ac7025031d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -559,23 +559,26 @@ struct sk_filter { DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); -#define BPF_PROG_RUN(prog, ctx) ({ \ - u32 ret; \ - cant_sleep(); \ - if (static_branch_unlikely(&bpf_stats_enabled_key)) { \ - struct bpf_prog_stats *stats; \ - u64 start = sched_clock(); \ - ret = (*(prog)->bpf_func)(ctx, (prog)->insnsi); \ - stats = this_cpu_ptr(prog->aux->stats); \ - u64_stats_update_begin(&stats->syncp); \ - stats->cnt++; \ - stats->nsecs += sched_clock() - start; \ - u64_stats_update_end(&stats->syncp); \ - } else { \ - ret = (*(prog)->bpf_func)(ctx, (prog)->insnsi); \ - } \ +#define __BPF_PROG_RUN(prog, ctx, dfunc) ({ \ + u32 ret; \ + cant_sleep(); \ + if (static_branch_unlikely(&bpf_stats_enabled_key)) { \ + struct bpf_prog_stats *stats; \ + u64 start = sched_clock(); \ + ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ + stats = this_cpu_ptr(prog->aux->stats); \ + u64_stats_update_begin(&stats->syncp); \ + stats->cnt++; \ + stats->nsecs += sched_clock() - start; \ + u64_stats_update_end(&stats->syncp); \ + } else { \ + ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ + } \ ret; }) +#define BPF_PROG_RUN(prog, ctx) __BPF_PROG_RUN(prog, ctx, \ + bpf_dispatcher_nopfunc) + #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN struct bpf_skb_data_end { @@ -699,6 +702,8 @@ static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, return res; } +DECLARE_BPF_DISPATCHER(bpf_dispatcher_xdp) + static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) { @@ -708,9 +713,12 @@ static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, * already takes rcu_read_lock() when fetching the program, so * it's not necessary here anymore. */ - return BPF_PROG_RUN(prog, xdp); + return __BPF_PROG_RUN(prog, xdp, + BPF_DISPATCHER_FUNC(bpf_dispatcher_xdp)); } +void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog); + static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) { return prog->len * sizeof(struct bpf_insn); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 66b90eaf99fe..b08c362f4e02 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2338,17 +2338,12 @@ static int bpf_obj_get_next_id(const union bpf_attr *attr, #define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id -static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) +struct bpf_prog *bpf_prog_by_id(u32 id) { struct bpf_prog *prog; - u32 id = attr->prog_id; - int fd; - - if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID)) - return -EINVAL; - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; + if (!id) + return ERR_PTR(-ENOENT); spin_lock_bh(&prog_idr_lock); prog = idr_find(&prog_idr, id); @@ -2357,7 +2352,22 @@ static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) else prog = ERR_PTR(-ENOENT); spin_unlock_bh(&prog_idr_lock); + return prog; +} + +static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) +{ + struct bpf_prog *prog; + u32 id = attr->prog_id; + int fd; + + if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + prog = bpf_prog_by_id(id); if (IS_ERR(prog)) return PTR_ERR(prog); diff --git a/net/core/dev.c b/net/core/dev.c index 2c277b8aba38..255d3cf35360 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8542,7 +8542,17 @@ static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op, struct netlink_ext_ack *extack, u32 flags, struct bpf_prog *prog) { + bool non_hw = !(flags & XDP_FLAGS_HW_MODE); + struct bpf_prog *prev_prog = NULL; struct netdev_bpf xdp; + int err; + + if (non_hw) { + prev_prog = bpf_prog_by_id(__dev_xdp_query(dev, bpf_op, + XDP_QUERY_PROG)); + if (IS_ERR(prev_prog)) + prev_prog = NULL; + } memset(&xdp, 0, sizeof(xdp)); if (flags & XDP_FLAGS_HW_MODE) @@ -8553,7 +8563,14 @@ static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op, xdp.flags = flags; xdp.prog = prog; - return bpf_op(dev, &xdp); + err = bpf_op(dev, &xdp); + if (!err && non_hw) + bpf_prog_change_xdp(prev_prog, prog); + + if (prev_prog) + bpf_prog_put(prev_prog); + + return err; } static void dev_xdp_uninstall(struct net_device *dev) diff --git a/net/core/filter.c b/net/core/filter.c index f1e703eed3d2..a411f7835dee 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8940,3 +8940,11 @@ const struct bpf_verifier_ops sk_reuseport_verifier_ops = { const struct bpf_prog_ops sk_reuseport_prog_ops = { }; #endif /* CONFIG_INET */ + +DEFINE_BPF_DISPATCHER(bpf_dispatcher_xdp) + +void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog) +{ + bpf_dispatcher_change_prog(BPF_DISPATCHER_PTR(bpf_dispatcher_xdp), + prev_prog, prog); +} -- cgit v1.2.3 From 871185ace40df871a93866b2a7ce441276fc4ee8 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Wed, 20 Nov 2019 12:33:59 +0100 Subject: netfilter: Clean up unnecessary #ifdef If CONFIG_NETFILTER_INGRESS is not enabled, nf_ingress() becomes a no-op because it solely contains an if-clause calling nf_hook_ingress_active(), for which an empty inline stub exists in . All the symbols used in the if-clause's body are still available even if CONFIG_NETFILTER_INGRESS is not enabled. The additional "#ifdef CONFIG_NETFILTER_INGRESS" in nf_ingress() is thus unnecessary, so drop it. Signed-off-by: Lukas Wunner Cc: Daniel Borkmann Signed-off-by: Pablo Neira Ayuso --- net/core/dev.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 2c277b8aba38..1ccead4b19bf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4932,7 +4932,6 @@ static bool skb_pfmemalloc_protocol(struct sk_buff *skb) static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) { -#ifdef CONFIG_NETFILTER_INGRESS if (nf_hook_ingress_active(skb)) { int ingress_retval; @@ -4946,7 +4945,6 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, rcu_read_unlock(); return ingress_retval; } -#endif /* CONFIG_NETFILTER_INGRESS */ return 0; } -- cgit v1.2.3 From 75ccae62cb8d42a619323a85c577107b8b37d797 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Thu, 16 Jan 2020 16:14:44 +0100 Subject: xdp: Move devmap bulk queue into struct net_device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 96360004b862 ("xdp: Make devmap flush_list common for all map instances"), changed devmap flushing to be a global operation instead of a per-map operation. However, the queue structure used for bulking was still allocated as part of the containing map. This patch moves the devmap bulk queue into struct net_device. The motivation for this is reusing it for the non-map variant of XDP_REDIRECT, which will be changed in a subsequent commit. To avoid other fields of struct net_device moving to different cache lines, we also move a couple of other members around. We defer the actual allocation of the bulk queue structure until the NETDEV_REGISTER notification devmap.c. This makes it possible to check for ndo_xdp_xmit support before allocating the structure, which is not possible at the time struct net_device is allocated. However, we keep the freeing in free_netdev() to avoid adding another RCU callback on NETDEV_UNREGISTER. Because of this change, we lose the reference back to the map that originated the redirect, so change the tracepoint to always return 0 as the map ID and index. Otherwise no functional change is intended with this patch. After this patch, the relevant part of struct net_device looks like this, according to pahole: /* --- cacheline 14 boundary (896 bytes) --- */ struct netdev_queue * _tx __attribute__((__aligned__(64))); /* 896 8 */ unsigned int num_tx_queues; /* 904 4 */ unsigned int real_num_tx_queues; /* 908 4 */ struct Qdisc * qdisc; /* 912 8 */ unsigned int tx_queue_len; /* 920 4 */ spinlock_t tx_global_lock; /* 924 4 */ struct xdp_dev_bulk_queue * xdp_bulkq; /* 928 8 */ struct xps_dev_maps * xps_cpus_map; /* 936 8 */ struct xps_dev_maps * xps_rxqs_map; /* 944 8 */ struct mini_Qdisc * miniq_egress; /* 952 8 */ /* --- cacheline 15 boundary (960 bytes) --- */ struct hlist_head qdisc_hash[16]; /* 960 128 */ /* --- cacheline 17 boundary (1088 bytes) --- */ struct timer_list watchdog_timer; /* 1088 40 */ /* XXX last struct has 4 bytes of padding */ int watchdog_timeo; /* 1128 4 */ /* XXX 4 bytes hole, try to pack */ struct list_head todo_list; /* 1136 16 */ /* --- cacheline 18 boundary (1152 bytes) --- */ Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Alexei Starovoitov Acked-by: Björn Töpel Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/157918768397.1458396.12673224324627072349.stgit@toke.dk --- include/linux/netdevice.h | 13 ++++++---- include/trace/events/xdp.h | 2 +- kernel/bpf/devmap.c | 63 ++++++++++++++++++++-------------------------- net/core/dev.c | 2 ++ 4 files changed, 38 insertions(+), 42 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2741aa35bec6..5ec3537fbdb1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -876,6 +876,7 @@ enum bpf_netdev_command { struct bpf_prog_offload_ops; struct netlink_ext_ack; struct xdp_umem; +struct xdp_dev_bulk_queue; struct netdev_bpf { enum bpf_netdev_command command; @@ -1986,12 +1987,10 @@ struct net_device { unsigned int num_tx_queues; unsigned int real_num_tx_queues; struct Qdisc *qdisc; -#ifdef CONFIG_NET_SCHED - DECLARE_HASHTABLE (qdisc_hash, 4); -#endif unsigned int tx_queue_len; spinlock_t tx_global_lock; - int watchdog_timeo; + + struct xdp_dev_bulk_queue __percpu *xdp_bulkq; #ifdef CONFIG_XPS struct xps_dev_maps __rcu *xps_cpus_map; @@ -2001,11 +2000,15 @@ struct net_device { struct mini_Qdisc __rcu *miniq_egress; #endif +#ifdef CONFIG_NET_SCHED + DECLARE_HASHTABLE (qdisc_hash, 4); +#endif /* These may be needed for future network-power-down code. */ struct timer_list watchdog_timer; + int watchdog_timeo; - int __percpu *pcpu_refcnt; struct list_head todo_list; + int __percpu *pcpu_refcnt; struct list_head link_watch_list; diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index a7378bcd9928..72bad13d4a3c 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -278,7 +278,7 @@ TRACE_EVENT(xdp_devmap_xmit, ), TP_fast_assign( - __entry->map_id = map->id; + __entry->map_id = map ? map->id : 0; __entry->act = XDP_REDIRECT; __entry->map_index = map_index; __entry->drops = drops; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index da9c832fc5c8..030d125c3839 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -53,13 +53,11 @@ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) #define DEV_MAP_BULK_SIZE 16 -struct bpf_dtab_netdev; - -struct xdp_bulk_queue { +struct xdp_dev_bulk_queue { struct xdp_frame *q[DEV_MAP_BULK_SIZE]; struct list_head flush_node; + struct net_device *dev; struct net_device *dev_rx; - struct bpf_dtab_netdev *obj; unsigned int count; }; @@ -67,9 +65,8 @@ struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ struct hlist_node index_hlist; struct bpf_dtab *dtab; - struct xdp_bulk_queue __percpu *bulkq; struct rcu_head rcu; - unsigned int idx; /* keep track of map index for tracepoint */ + unsigned int idx; }; struct bpf_dtab { @@ -219,7 +216,6 @@ static void dev_map_free(struct bpf_map *map) hlist_for_each_entry_safe(dev, next, head, index_hlist) { hlist_del_rcu(&dev->index_hlist); - free_percpu(dev->bulkq); dev_put(dev->dev); kfree(dev); } @@ -234,7 +230,6 @@ static void dev_map_free(struct bpf_map *map) if (!dev) continue; - free_percpu(dev->bulkq); dev_put(dev->dev); kfree(dev); } @@ -320,10 +315,9 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, return -ENOENT; } -static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags) +static int bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) { - struct bpf_dtab_netdev *obj = bq->obj; - struct net_device *dev = obj->dev; + struct net_device *dev = bq->dev; int sent = 0, drops = 0, err = 0; int i; @@ -346,8 +340,7 @@ static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags) out: bq->count = 0; - trace_xdp_devmap_xmit(&obj->dtab->map, obj->idx, - sent, drops, bq->dev_rx, dev, err); + trace_xdp_devmap_xmit(NULL, 0, sent, drops, bq->dev_rx, dev, err); bq->dev_rx = NULL; __list_del_clearprev(&bq->flush_node); return 0; @@ -374,7 +367,7 @@ error: void __dev_map_flush(void) { struct list_head *flush_list = this_cpu_ptr(&dev_map_flush_list); - struct xdp_bulk_queue *bq, *tmp; + struct xdp_dev_bulk_queue *bq, *tmp; rcu_read_lock(); list_for_each_entry_safe(bq, tmp, flush_list, flush_node) @@ -401,12 +394,12 @@ struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key) /* Runs under RCU-read-side, plus in softirq under NAPI protection. * Thus, safe percpu variable access. */ -static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf, +static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { struct list_head *flush_list = this_cpu_ptr(&dev_map_flush_list); - struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq); + struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) bq_xmit_all(bq, 0); @@ -444,7 +437,7 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, if (unlikely(!xdpf)) return -EOVERFLOW; - return bq_enqueue(dst, xdpf, dev_rx); + return bq_enqueue(dev, xdpf, dev_rx); } int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, @@ -483,7 +476,6 @@ static void __dev_map_entry_free(struct rcu_head *rcu) struct bpf_dtab_netdev *dev; dev = container_of(rcu, struct bpf_dtab_netdev, rcu); - free_percpu(dev->bulkq); dev_put(dev->dev); kfree(dev); } @@ -538,30 +530,15 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, u32 ifindex, unsigned int idx) { - gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; struct bpf_dtab_netdev *dev; - struct xdp_bulk_queue *bq; - int cpu; - dev = kmalloc_node(sizeof(*dev), gfp, dtab->map.numa_node); + dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, + dtab->map.numa_node); if (!dev) return ERR_PTR(-ENOMEM); - dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq), - sizeof(void *), gfp); - if (!dev->bulkq) { - kfree(dev); - return ERR_PTR(-ENOMEM); - } - - for_each_possible_cpu(cpu) { - bq = per_cpu_ptr(dev->bulkq, cpu); - bq->obj = dev; - } - dev->dev = dev_get_by_index(net, ifindex); if (!dev->dev) { - free_percpu(dev->bulkq); kfree(dev); return ERR_PTR(-EINVAL); } @@ -721,9 +698,23 @@ static int dev_map_notification(struct notifier_block *notifier, { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct bpf_dtab *dtab; - int i; + int i, cpu; switch (event) { + case NETDEV_REGISTER: + if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq) + break; + + /* will be freed in free_netdev() */ + netdev->xdp_bulkq = + __alloc_percpu_gfp(sizeof(struct xdp_dev_bulk_queue), + sizeof(void *), GFP_ATOMIC); + if (!netdev->xdp_bulkq) + return NOTIFY_BAD; + + for_each_possible_cpu(cpu) + per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev; + break; case NETDEV_UNREGISTER: /* This rcu_read_lock/unlock pair is needed because * dev_map_list is an RCU list AND to ensure a delete diff --git a/net/core/dev.c b/net/core/dev.c index d99f88c58636..e7802a41ae7f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9847,6 +9847,8 @@ void free_netdev(struct net_device *dev) free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL; + free_percpu(dev->xdp_bulkq); + dev->xdp_bulkq = NULL; netdev_unregister_lockdep_key(dev); -- cgit v1.2.3 From 1a3c998f3a27ab6ecf56bdbb17e27e55fd6d47cd Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Sat, 25 Jan 2020 11:26:43 +0100 Subject: net: Add a netdev software feature set that defaults to off. The previous patch added the NETIF_F_GRO_FRAGLIST feature. This is a software feature that should default to off. Current software features default to on, so add a new feature set that defaults to off. Signed-off-by: Steffen Klassert Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 3 +++ net/core/dev.c | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index b239507da2a0..34d050bb1ae6 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -230,6 +230,9 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) /* changeable features with no special hardware requirements */ #define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO) +/* Changeable features with no special hardware requirements that defaults to off. */ +#define NETIF_F_SOFT_FEATURES_OFF NETIF_F_GRO_FRAGLIST + #define NETIF_F_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_FILTER | \ NETIF_F_HW_VLAN_CTAG_RX | \ NETIF_F_HW_VLAN_CTAG_TX | \ diff --git a/net/core/dev.c b/net/core/dev.c index c806b078097b..a3b154a4b4f9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9283,7 +9283,7 @@ int register_netdevice(struct net_device *dev) /* Transfer changeable features to wanted_features and enable * software offloads (GSO and GRO). */ - dev->hw_features |= NETIF_F_SOFT_FEATURES; + dev->hw_features |= (NETIF_F_SOFT_FEATURES | NETIF_F_SOFT_FEATURES_OFF); dev->features |= NETIF_F_SOFT_FEATURES; if (dev->netdev_ops->ndo_udp_tunnel_add) { -- cgit v1.2.3 From 3a1296a38d0cf62bffb9a03c585cbd5dbf15d596 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Sat, 25 Jan 2020 11:26:44 +0100 Subject: net: Support GRO/GSO fraglist chaining. This patch adds the core functions to chain/unchain GSO skbs at the frag_list pointer. This also adds a new GSO type SKB_GSO_FRAGLIST and a is_flist flag to napi_gro_cb which indicates that this flow will be GROed by fraglist chaining. Signed-off-by: Steffen Klassert Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++- include/linux/skbuff.h | 2 ++ net/core/dev.c | 2 +- net/core/skbuff.c | 91 +++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 97 insertions(+), 2 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fcc76b890f50..20445f94eb1c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2326,7 +2326,8 @@ struct napi_gro_cb { /* Number of gro_receive callbacks this packet already went through */ u8 recursion_counter:4; - /* 1 bit hole */ + /* GRO is done by frag_list pointer chaining. */ + u8 is_flist:1; /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; @@ -2694,6 +2695,7 @@ struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); +int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb); static inline unsigned int skb_gro_offset(const struct sk_buff *skb) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 23aaaf08e1e9..3d13a4b717e9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3535,6 +3535,8 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet); bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu); bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); +struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, + unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, int write_len); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); diff --git a/net/core/dev.c b/net/core/dev.c index a3b154a4b4f9..ce8900dbd9ea 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3249,7 +3249,7 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, segs = skb_mac_gso_segment(skb, features); - if (unlikely(skb_needs_check(skb, tx_path) && !IS_ERR(segs))) + if (segs != skb && unlikely(skb_needs_check(skb, tx_path) && !IS_ERR(segs))) skb_warn_bad_offload(skb); return segs; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 48a7029529c9..864cb9e9622f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3639,6 +3639,97 @@ static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb) return head_frag; } +struct sk_buff *skb_segment_list(struct sk_buff *skb, + netdev_features_t features, + unsigned int offset) +{ + struct sk_buff *list_skb = skb_shinfo(skb)->frag_list; + unsigned int tnl_hlen = skb_tnl_header_len(skb); + unsigned int delta_truesize = 0; + unsigned int delta_len = 0; + struct sk_buff *tail = NULL; + struct sk_buff *nskb; + + skb_push(skb, -skb_network_offset(skb) + offset); + + skb_shinfo(skb)->frag_list = NULL; + + do { + nskb = list_skb; + list_skb = list_skb->next; + + if (!tail) + skb->next = nskb; + else + tail->next = nskb; + + tail = nskb; + + delta_len += nskb->len; + delta_truesize += nskb->truesize; + + skb_push(nskb, -skb_network_offset(nskb) + offset); + + __copy_skb_header(nskb, skb); + + skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb)); + skb_copy_from_linear_data_offset(skb, -tnl_hlen, + nskb->data - tnl_hlen, + offset + tnl_hlen); + + if (skb_needs_linearize(nskb, features) && + __skb_linearize(nskb)) + goto err_linearize; + + } while (list_skb); + + skb->truesize = skb->truesize - delta_truesize; + skb->data_len = skb->data_len - delta_len; + skb->len = skb->len - delta_len; + + skb_gso_reset(skb); + + skb->prev = tail; + + if (skb_needs_linearize(skb, features) && + __skb_linearize(skb)) + goto err_linearize; + + skb_get(skb); + + return skb; + +err_linearize: + kfree_skb_list(skb->next); + skb->next = NULL; + return ERR_PTR(-ENOMEM); +} +EXPORT_SYMBOL_GPL(skb_segment_list); + +int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) +{ + if (unlikely(p->len + skb->len >= 65536)) + return -E2BIG; + + if (NAPI_GRO_CB(p)->last == p) + skb_shinfo(p)->frag_list = skb; + else + NAPI_GRO_CB(p)->last->next = skb; + + skb_pull(skb, skb_gro_offset(skb)); + + NAPI_GRO_CB(p)->last = skb; + NAPI_GRO_CB(p)->count++; + p->data_len += skb->len; + p->truesize += skb->truesize; + p->len += skb->len; + + NAPI_GRO_CB(skb)->same_flow = 1; + + return 0; +} +EXPORT_SYMBOL_GPL(skb_gro_receive_list); + /** * skb_segment - Perform protocol segmentation on skb. * @head_skb: buffer to segment -- cgit v1.2.3 From 48b3a1379fc6603c1ff26893ea05322c1c41e31c Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 25 Jan 2020 12:17:06 +0100 Subject: net: call call_netdevice_unregister_net_notifiers from unregister The function does the same thing as the existing code, so rather call call_netdevice_unregister_net_notifiers() instead of code duplication. Signed-off-by: Jiri Pirko Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/core/dev.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index ce8900dbd9ea..ee4b1e64d663 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1764,7 +1764,6 @@ EXPORT_SYMBOL(register_netdevice_notifier); int unregister_netdevice_notifier(struct notifier_block *nb) { - struct net_device *dev; struct net *net; int err; @@ -1775,16 +1774,9 @@ int unregister_netdevice_notifier(struct notifier_block *nb) if (err) goto unlock; - for_each_net(net) { - for_each_netdev(net, dev) { - if (dev->flags & IFF_UP) { - call_netdevice_notifier(nb, NETDEV_GOING_DOWN, - dev); - call_netdevice_notifier(nb, NETDEV_DOWN, dev); - } - call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); - } - } + for_each_net(net) + call_netdevice_unregister_net_notifiers(nb, net); + unlock: rtnl_unlock(); up_write(&pernet_ops_rwsem); -- cgit v1.2.3 From 1f637703d8b63f1ba411b4c798e998e3f828b6cb Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 25 Jan 2020 12:17:07 +0100 Subject: net: push code from net notifier reg/unreg into helpers Push the code which is done under rtnl lock in net notifier register and unregister function into separate helpers. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/dev.c | 60 +++++++++++++++++++++++++++++++++++++--------------------- 1 file changed, 38 insertions(+), 22 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index ee4b1e64d663..b521b509a653 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1784,6 +1784,42 @@ unlock: } EXPORT_SYMBOL(unregister_netdevice_notifier); +static int __register_netdevice_notifier_net(struct net *net, + struct notifier_block *nb, + bool ignore_call_fail) +{ + int err; + + err = raw_notifier_chain_register(&net->netdev_chain, nb); + if (err) + return err; + if (dev_boot_phase) + return 0; + + err = call_netdevice_register_net_notifiers(nb, net); + if (err && !ignore_call_fail) + goto chain_unregister; + + return 0; + +chain_unregister: + raw_notifier_chain_unregister(&net->netdev_chain, nb); + return err; +} + +static int __unregister_netdevice_notifier_net(struct net *net, + struct notifier_block *nb) +{ + int err; + + err = raw_notifier_chain_unregister(&net->netdev_chain, nb); + if (err) + return err; + + call_netdevice_unregister_net_notifiers(nb, net); + return 0; +} + /** * register_netdevice_notifier_net - register a per-netns network notifier block * @net: network namespace @@ -1804,23 +1840,9 @@ int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb) int err; rtnl_lock(); - err = raw_notifier_chain_register(&net->netdev_chain, nb); - if (err) - goto unlock; - if (dev_boot_phase) - goto unlock; - - err = call_netdevice_register_net_notifiers(nb, net); - if (err) - goto chain_unregister; - -unlock: + err = __register_netdevice_notifier_net(net, nb, false); rtnl_unlock(); return err; - -chain_unregister: - raw_notifier_chain_unregister(&netdev_chain, nb); - goto unlock; } EXPORT_SYMBOL(register_netdevice_notifier_net); @@ -1846,13 +1868,7 @@ int unregister_netdevice_notifier_net(struct net *net, int err; rtnl_lock(); - err = raw_notifier_chain_unregister(&net->netdev_chain, nb); - if (err) - goto unlock; - - call_netdevice_unregister_net_notifiers(nb, net); - -unlock: + err = __unregister_netdevice_notifier_net(net, nb); rtnl_unlock(); return err; } -- cgit v1.2.3 From 93642e14bd50e59b11cf6389ce3fc243e932777a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 25 Jan 2020 12:17:08 +0100 Subject: net: introduce dev_net notifier register/unregister variants Introduce dev_net variants of netdev notifier register/unregister functions and allow per-net notifier to follow the netdevice into the namespace it is moved to. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 17 +++++++++++++++++ net/core/dev.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 63 insertions(+) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 20445f94eb1c..4626188a754b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -939,6 +939,11 @@ struct netdev_name_node { int netdev_name_node_alt_create(struct net_device *dev, const char *name); int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); +struct netdev_net_notifier { + struct list_head list; + struct notifier_block *nb; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1793,6 +1798,10 @@ enum netdev_priv_flags { * * @wol_enabled: Wake-on-LAN is enabled * + * @net_notifier_list: List of per-net netdev notifier block + * that follow this device when it is moved + * to another network namespace. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2085,6 +2094,8 @@ struct net_device { struct lock_class_key addr_list_lock_key; bool proto_down; unsigned wol_enabled:1; + + struct list_head net_notifier_list; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -2529,6 +2540,12 @@ int unregister_netdevice_notifier(struct notifier_block *nb); int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb); int unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb); +int register_netdevice_notifier_dev_net(struct net_device *dev, + struct notifier_block *nb, + struct netdev_net_notifier *nn); +int unregister_netdevice_notifier_dev_net(struct net_device *dev, + struct notifier_block *nb, + struct netdev_net_notifier *nn); struct netdev_notifier_info { struct net_device *dev; diff --git a/net/core/dev.c b/net/core/dev.c index b521b509a653..38bc35da39f7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1874,6 +1874,48 @@ int unregister_netdevice_notifier_net(struct net *net, } EXPORT_SYMBOL(unregister_netdevice_notifier_net); +int register_netdevice_notifier_dev_net(struct net_device *dev, + struct notifier_block *nb, + struct netdev_net_notifier *nn) +{ + int err; + + rtnl_lock(); + err = __register_netdevice_notifier_net(dev_net(dev), nb, false); + if (!err) { + nn->nb = nb; + list_add(&nn->list, &dev->net_notifier_list); + } + rtnl_unlock(); + return err; +} +EXPORT_SYMBOL(register_netdevice_notifier_dev_net); + +int unregister_netdevice_notifier_dev_net(struct net_device *dev, + struct notifier_block *nb, + struct netdev_net_notifier *nn) +{ + int err; + + rtnl_lock(); + list_del(&nn->list); + err = __unregister_netdevice_notifier_net(dev_net(dev), nb); + rtnl_unlock(); + return err; +} +EXPORT_SYMBOL(unregister_netdevice_notifier_dev_net); + +static void move_netdevice_notifiers_dev_net(struct net_device *dev, + struct net *net) +{ + struct netdev_net_notifier *nn; + + list_for_each_entry(nn, &dev->net_notifier_list, list) { + __unregister_netdevice_notifier_net(dev_net(dev), nn->nb); + __register_netdevice_notifier_net(net, nn->nb, true); + } +} + /** * call_netdevice_notifiers_info - call all network notifier blocks * @val: value passed unmodified to notifier function @@ -9786,6 +9828,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, INIT_LIST_HEAD(&dev->adj_list.lower); INIT_LIST_HEAD(&dev->ptype_all); INIT_LIST_HEAD(&dev->ptype_specific); + INIT_LIST_HEAD(&dev->net_notifier_list); #ifdef CONFIG_NET_SCHED hash_init(dev->qdisc_hash); #endif @@ -10049,6 +10092,9 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE); netdev_adjacent_del_links(dev); + /* Move per-net netdevice notifiers that are following the netdevice */ + move_netdevice_notifiers_dev_net(dev, net); + /* Actually switch the network namespace */ dev_net_set(dev, net); dev->ifindex = new_ifindex; -- cgit v1.2.3 From 45586c7078d42b932c5399953d21746800083691 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 3 Feb 2020 17:37:45 -0800 Subject: treewide: remove redundant IS_ERR() before error code check 'PTR_ERR(p) == -E*' is a stronger condition than IS_ERR(p). Hence, IS_ERR(p) is unneeded. The semantic patch that generates this commit is as follows: // @@ expression ptr; constant error_code; @@ -IS_ERR(ptr) && (PTR_ERR(ptr) == - error_code) +PTR_ERR(ptr) == - error_code // Link: http://lkml.kernel.org/r/20200106045833.1725-1-masahiroy@kernel.org Signed-off-by: Masahiro Yamada Cc: Julia Lawall Acked-by: Stephen Boyd [drivers/clk/clk.c] Acked-by: Bartosz Golaszewski [GPIO] Acked-by: Wolfram Sang [drivers/i2c] Acked-by: Rafael J. Wysocki [acpi/scan.c] Acked-by: Rob Herring Cc: Eric Biggers Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- crypto/af_alg.c | 2 +- drivers/acpi/scan.c | 2 +- drivers/char/hw_random/bcm2835-rng.c | 2 +- drivers/char/hw_random/omap-rng.c | 4 ++-- drivers/clk/clk.c | 2 +- drivers/dma/mv_xor_v2.c | 2 +- drivers/gpio/gpiolib-devres.c | 2 +- drivers/gpio/gpiolib-of.c | 8 ++++---- drivers/gpio/gpiolib.c | 2 +- drivers/i2c/busses/i2c-mv64xxx.c | 5 ++--- drivers/i2c/busses/i2c-synquacer.c | 2 +- drivers/mtd/ubi/build.c | 2 +- drivers/of/device.c | 2 +- drivers/pci/controller/pci-tegra.c | 2 +- drivers/phy/phy-core.c | 4 ++-- drivers/spi/spi-orion.c | 3 +-- drivers/video/fbdev/imxfb.c | 2 +- fs/ext4/super.c | 2 +- fs/f2fs/node.c | 2 +- fs/ocfs2/suballoc.c | 2 +- fs/sysfs/group.c | 2 +- net/core/dev.c | 2 +- net/core/filter.c | 2 +- net/xfrm/xfrm_policy.c | 2 +- sound/soc/codecs/ak4104.c | 3 +-- sound/soc/codecs/cs4270.c | 3 +-- sound/soc/codecs/tlv320aic32x4.c | 6 ++---- sound/soc/sunxi/sun4i-spdif.c | 2 +- 28 files changed, 35 insertions(+), 41 deletions(-) (limited to 'net/core/dev.c') diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 3d8e53010cda..439367a8e95c 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -171,7 +171,7 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) sa->salg_name[sizeof(sa->salg_name) + addr_len - sizeof(*sa) - 1] = 0; type = alg_get_type(sa->salg_type); - if (IS_ERR(type) && PTR_ERR(type) == -ENOENT) { + if (PTR_ERR(type) == -ENOENT) { request_module("algif-%s", sa->salg_type); type = alg_get_type(sa->salg_type); } diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 915650bf519f..6d3448895382 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1462,7 +1462,7 @@ int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr) iort_dma_setup(dev, &dma_addr, &size); iommu = iort_iommu_configure(dev); - if (IS_ERR(iommu) && PTR_ERR(iommu) == -EPROBE_DEFER) + if (PTR_ERR(iommu) == -EPROBE_DEFER) return -EPROBE_DEFER; arch_setup_dma_ops(dev, dma_addr, size, diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c index d2a5791eb49f..cbf5eaea662c 100644 --- a/drivers/char/hw_random/bcm2835-rng.c +++ b/drivers/char/hw_random/bcm2835-rng.c @@ -157,7 +157,7 @@ static int bcm2835_rng_probe(struct platform_device *pdev) /* Clock is optional on most platforms */ priv->clk = devm_clk_get(dev, NULL); - if (IS_ERR(priv->clk) && PTR_ERR(priv->clk) == -EPROBE_DEFER) + if (PTR_ERR(priv->clk) == -EPROBE_DEFER) return -EPROBE_DEFER; priv->rng.name = pdev->name; diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c index 0ed07d16ec8e..65952393e1bb 100644 --- a/drivers/char/hw_random/omap-rng.c +++ b/drivers/char/hw_random/omap-rng.c @@ -476,7 +476,7 @@ static int omap_rng_probe(struct platform_device *pdev) } priv->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(priv->clk) && PTR_ERR(priv->clk) == -EPROBE_DEFER) + if (PTR_ERR(priv->clk) == -EPROBE_DEFER) return -EPROBE_DEFER; if (!IS_ERR(priv->clk)) { ret = clk_prepare_enable(priv->clk); @@ -488,7 +488,7 @@ static int omap_rng_probe(struct platform_device *pdev) } priv->clk_reg = devm_clk_get(&pdev->dev, "reg"); - if (IS_ERR(priv->clk_reg) && PTR_ERR(priv->clk_reg) == -EPROBE_DEFER) + if (PTR_ERR(priv->clk_reg) == -EPROBE_DEFER) return -EPROBE_DEFER; if (!IS_ERR(priv->clk_reg)) { ret = clk_prepare_enable(priv->clk_reg); diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 772258de2d1f..39eda7fd3830 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -429,7 +429,7 @@ static void clk_core_fill_parent_index(struct clk_core *core, u8 index) parent = ERR_PTR(-EPROBE_DEFER); } else { parent = clk_core_get(core, index); - if (IS_ERR(parent) && PTR_ERR(parent) == -ENOENT && entry->name) + if (PTR_ERR(parent) == -ENOENT && entry->name) parent = clk_core_lookup(entry->name); } diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c index e3850f04f676..157c959311ea 100644 --- a/drivers/dma/mv_xor_v2.c +++ b/drivers/dma/mv_xor_v2.c @@ -750,7 +750,7 @@ static int mv_xor_v2_probe(struct platform_device *pdev) } xor_dev->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(xor_dev->clk) && PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) { + if (PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) { ret = EPROBE_DEFER; goto disable_reg_clk; } diff --git a/drivers/gpio/gpiolib-devres.c b/drivers/gpio/gpiolib-devres.c index 4421be09b960..72b6001c56ef 100644 --- a/drivers/gpio/gpiolib-devres.c +++ b/drivers/gpio/gpiolib-devres.c @@ -308,7 +308,7 @@ devm_gpiod_get_array_optional(struct device *dev, const char *con_id, struct gpio_descs *descs; descs = devm_gpiod_get_array(dev, con_id, flags); - if (IS_ERR(descs) && (PTR_ERR(descs) == -ENOENT)) + if (PTR_ERR(descs) == -ENOENT) return NULL; return descs; diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 1b3f217a35e2..c6d30f73df07 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -484,24 +484,24 @@ struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id, break; } - if (IS_ERR(desc) && PTR_ERR(desc) == -ENOENT) { + if (PTR_ERR(desc) == -ENOENT) { /* Special handling for SPI GPIOs if used */ desc = of_find_spi_gpio(dev, con_id, &of_flags); } - if (IS_ERR(desc) && PTR_ERR(desc) == -ENOENT) { + if (PTR_ERR(desc) == -ENOENT) { /* This quirk looks up flags and all */ desc = of_find_spi_cs_gpio(dev, con_id, idx, flags); if (!IS_ERR(desc)) return desc; } - if (IS_ERR(desc) && PTR_ERR(desc) == -ENOENT) { + if (PTR_ERR(desc) == -ENOENT) { /* Special handling for regulator GPIOs if used */ desc = of_find_regulator_gpio(dev, con_id, &of_flags); } - if (IS_ERR(desc) && PTR_ERR(desc) == -ENOENT) + if (PTR_ERR(desc) == -ENOENT) desc = of_find_arizona_gpio(dev, con_id, &of_flags); if (IS_ERR(desc)) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 99ac27a72e28..753283486037 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -5039,7 +5039,7 @@ struct gpio_descs *__must_check gpiod_get_array_optional(struct device *dev, struct gpio_descs *descs; descs = gpiod_get_array(dev, con_id, flags); - if (IS_ERR(descs) && (PTR_ERR(descs) == -ENOENT)) + if (PTR_ERR(descs) == -ENOENT) return NULL; return descs; diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c index a5a95ea5b81a..febb7c7ea72b 100644 --- a/drivers/i2c/busses/i2c-mv64xxx.c +++ b/drivers/i2c/busses/i2c-mv64xxx.c @@ -901,14 +901,13 @@ mv64xxx_i2c_probe(struct platform_device *pd) /* Not all platforms have clocks */ drv_data->clk = devm_clk_get(&pd->dev, NULL); - if (IS_ERR(drv_data->clk) && PTR_ERR(drv_data->clk) == -EPROBE_DEFER) + if (PTR_ERR(drv_data->clk) == -EPROBE_DEFER) return -EPROBE_DEFER; if (!IS_ERR(drv_data->clk)) clk_prepare_enable(drv_data->clk); drv_data->reg_clk = devm_clk_get(&pd->dev, "reg"); - if (IS_ERR(drv_data->reg_clk) && - PTR_ERR(drv_data->reg_clk) == -EPROBE_DEFER) + if (PTR_ERR(drv_data->reg_clk) == -EPROBE_DEFER) return -EPROBE_DEFER; if (!IS_ERR(drv_data->reg_clk)) clk_prepare_enable(drv_data->reg_clk); diff --git a/drivers/i2c/busses/i2c-synquacer.c b/drivers/i2c/busses/i2c-synquacer.c index 39762f0611b1..86026798b4f7 100644 --- a/drivers/i2c/busses/i2c-synquacer.c +++ b/drivers/i2c/busses/i2c-synquacer.c @@ -553,7 +553,7 @@ static int synquacer_i2c_probe(struct platform_device *pdev) &i2c->pclkrate); i2c->pclk = devm_clk_get(&pdev->dev, "pclk"); - if (IS_ERR(i2c->pclk) && PTR_ERR(i2c->pclk) == -EPROBE_DEFER) + if (PTR_ERR(i2c->pclk) == -EPROBE_DEFER) return -EPROBE_DEFER; if (!IS_ERR_OR_NULL(i2c->pclk)) { dev_dbg(&pdev->dev, "clock source %p\n", i2c->pclk); diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 25fb72b2efa0..2f93c25bbaee 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -1180,7 +1180,7 @@ static struct mtd_info * __init open_mtd_device(const char *mtd_dev) * MTD device name. */ mtd = get_mtd_device_nm(mtd_dev); - if (IS_ERR(mtd) && PTR_ERR(mtd) == -ENODEV) + if (PTR_ERR(mtd) == -ENODEV) /* Probably this is an MTD character device node path */ mtd = open_mtd_by_chdev(mtd_dev); } else diff --git a/drivers/of/device.c b/drivers/of/device.c index e9127db7b067..27203bfd0b22 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -161,7 +161,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma) coherent ? " " : " not "); iommu = of_iommu_configure(dev, np); - if (IS_ERR(iommu) && PTR_ERR(iommu) == -EPROBE_DEFER) + if (PTR_ERR(iommu) == -EPROBE_DEFER) return -EPROBE_DEFER; dev_dbg(dev, "device is%sbehind an iommu\n", diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c index ac93f5a0398e..0e03cef72840 100644 --- a/drivers/pci/controller/pci-tegra.c +++ b/drivers/pci/controller/pci-tegra.c @@ -1406,7 +1406,7 @@ static struct phy *devm_of_phy_optional_get_index(struct device *dev, phy = devm_of_phy_get(dev, np, name); kfree(name); - if (IS_ERR(phy) && PTR_ERR(phy) == -ENODEV) + if (PTR_ERR(phy) == -ENODEV) phy = NULL; return phy; diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 2eb28cc2d2dc..cd5a6c95dbdc 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -712,7 +712,7 @@ struct phy *phy_optional_get(struct device *dev, const char *string) { struct phy *phy = phy_get(dev, string); - if (IS_ERR(phy) && (PTR_ERR(phy) == -ENODEV)) + if (PTR_ERR(phy) == -ENODEV) phy = NULL; return phy; @@ -766,7 +766,7 @@ struct phy *devm_phy_optional_get(struct device *dev, const char *string) { struct phy *phy = devm_phy_get(dev, string); - if (IS_ERR(phy) && (PTR_ERR(phy) == -ENODEV)) + if (PTR_ERR(phy) == -ENODEV) phy = NULL; return phy; diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c index c7266ef295fd..1f59beb7d27e 100644 --- a/drivers/spi/spi-orion.c +++ b/drivers/spi/spi-orion.c @@ -646,8 +646,7 @@ static int orion_spi_probe(struct platform_device *pdev) /* The following clock is only used by some SoCs */ spi->axi_clk = devm_clk_get(&pdev->dev, "axi"); - if (IS_ERR(spi->axi_clk) && - PTR_ERR(spi->axi_clk) == -EPROBE_DEFER) { + if (PTR_ERR(spi->axi_clk) == -EPROBE_DEFER) { status = -EPROBE_DEFER; goto out_rel_clk; } diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c index 08a17eb2a5c7..370bf2553d43 100644 --- a/drivers/video/fbdev/imxfb.c +++ b/drivers/video/fbdev/imxfb.c @@ -1017,7 +1017,7 @@ static int imxfb_probe(struct platform_device *pdev) } fbi->lcd_pwr = devm_regulator_get(&pdev->dev, "lcd"); - if (IS_ERR(fbi->lcd_pwr) && (PTR_ERR(fbi->lcd_pwr) == -EPROBE_DEFER)) { + if (PTR_ERR(fbi->lcd_pwr) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; goto failed_lcd; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 88b213bd32bc..8434217549b3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -6043,7 +6043,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, bh = ext4_bread(handle, inode, blk, EXT4_GET_BLOCKS_CREATE | EXT4_GET_BLOCKS_METADATA_NOFAIL); - } while (IS_ERR(bh) && (PTR_ERR(bh) == -ENOSPC) && + } while (PTR_ERR(bh) == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); if (IS_ERR(bh)) return PTR_ERR(bh); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 3314a0f3405e..9d02cdcdbb07 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -875,7 +875,7 @@ static int truncate_dnode(struct dnode_of_data *dn) /* get direct node */ page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid); - if (IS_ERR(page) && PTR_ERR(page) == -ENOENT) + if (PTR_ERR(page) == -ENOENT) return 1; else if (IS_ERR(page)) return PTR_ERR(page); diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 4180c3ef0a68..939df99d2dec 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -696,7 +696,7 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb, bg_bh = ocfs2_block_group_alloc_contig(osb, handle, alloc_inode, ac, cl); - if (IS_ERR(bg_bh) && (PTR_ERR(bg_bh) == -ENOSPC)) + if (PTR_ERR(bg_bh) == -ENOSPC) bg_bh = ocfs2_block_group_alloc_discontig(handle, alloc_inode, ac, cl); diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index d41c21fef138..c4ab045926b7 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -449,7 +449,7 @@ int __compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj, } link = kernfs_create_link(kobj->sd, target_name, entry); - if (IS_ERR(link) && PTR_ERR(link) == -EEXIST) + if (PTR_ERR(link) == -EEXIST) sysfs_warn_dup(kobj->sd, target_name); kernfs_put(entry); diff --git a/net/core/dev.c b/net/core/dev.c index 17529d49faec..a69e8bd7ed74 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5792,7 +5792,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (&ptype->list == head) goto normal; - if (IS_ERR(pp) && PTR_ERR(pp) == -EINPROGRESS) { + if (PTR_ERR(pp) == -EINPROGRESS) { ret = GRO_CONSUMED; goto ok; } diff --git a/net/core/filter.c b/net/core/filter.c index 792e3744b915..c180871e606d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1573,7 +1573,7 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) return -EPERM; prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER); - if (IS_ERR(prog) && PTR_ERR(prog) == -EINVAL) + if (PTR_ERR(prog) == -EINVAL) prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SK_REUSEPORT); if (IS_ERR(prog)) return PTR_ERR(prog); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 297d1eb79e5c..dbda08ec566e 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3189,7 +3189,7 @@ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, flags | XFRM_LOOKUP_QUEUE | XFRM_LOOKUP_KEEP_DST_REF); - if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE) + if (PTR_ERR(dst) == -EREMOTE) return make_blackhole(net, dst_orig->ops->family, dst_orig); if (IS_ERR(dst)) diff --git a/sound/soc/codecs/ak4104.c b/sound/soc/codecs/ak4104.c index e8c5fda82e08..979cfb165eed 100644 --- a/sound/soc/codecs/ak4104.c +++ b/sound/soc/codecs/ak4104.c @@ -295,8 +295,7 @@ static int ak4104_spi_probe(struct spi_device *spi) reset_gpiod = devm_gpiod_get_optional(&spi->dev, "reset", GPIOD_OUT_HIGH); - if (IS_ERR(reset_gpiod) && - PTR_ERR(reset_gpiod) == -EPROBE_DEFER) + if (PTR_ERR(reset_gpiod) == -EPROBE_DEFER) return -EPROBE_DEFER; /* read the 'reserved' register - according to the datasheet, it diff --git a/sound/soc/codecs/cs4270.c b/sound/soc/codecs/cs4270.c index 793a14d58667..5f25b9f872bd 100644 --- a/sound/soc/codecs/cs4270.c +++ b/sound/soc/codecs/cs4270.c @@ -681,8 +681,7 @@ static int cs4270_i2c_probe(struct i2c_client *i2c_client, reset_gpiod = devm_gpiod_get_optional(&i2c_client->dev, "reset", GPIOD_OUT_HIGH); - if (IS_ERR(reset_gpiod) && - PTR_ERR(reset_gpiod) == -EPROBE_DEFER) + if (PTR_ERR(reset_gpiod) == -EPROBE_DEFER) return -EPROBE_DEFER; cs4270->regmap = devm_regmap_init_i2c(i2c_client, &cs4270_regmap); diff --git a/sound/soc/codecs/tlv320aic32x4.c b/sound/soc/codecs/tlv320aic32x4.c index b4e9a6c73f90..d087f3b20b1d 100644 --- a/sound/soc/codecs/tlv320aic32x4.c +++ b/sound/soc/codecs/tlv320aic32x4.c @@ -1098,11 +1098,9 @@ static int aic32x4_setup_regulators(struct device *dev, return PTR_ERR(aic32x4->supply_av); } } else { - if (IS_ERR(aic32x4->supply_dv) && - PTR_ERR(aic32x4->supply_dv) == -EPROBE_DEFER) + if (PTR_ERR(aic32x4->supply_dv) == -EPROBE_DEFER) return -EPROBE_DEFER; - if (IS_ERR(aic32x4->supply_av) && - PTR_ERR(aic32x4->supply_av) == -EPROBE_DEFER) + if (PTR_ERR(aic32x4->supply_av) == -EPROBE_DEFER) return -EPROBE_DEFER; } diff --git a/sound/soc/sunxi/sun4i-spdif.c b/sound/soc/sunxi/sun4i-spdif.c index cbe598b0fb10..98a9fe645521 100644 --- a/sound/soc/sunxi/sun4i-spdif.c +++ b/sound/soc/sunxi/sun4i-spdif.c @@ -555,7 +555,7 @@ static int sun4i_spdif_probe(struct platform_device *pdev) if (quirks->has_reset) { host->rst = devm_reset_control_get_optional_exclusive(&pdev->dev, NULL); - if (IS_ERR(host->rst) && PTR_ERR(host->rst) == -EPROBE_DEFER) { + if (PTR_ERR(host->rst) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; dev_err(&pdev->dev, "Failed to get reset: %d\n", ret); return ret; -- cgit v1.2.3 From ad1e03b2b3d4430baaa109b77bc308dc73050de3 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Mon, 10 Feb 2020 17:10:46 +0100 Subject: core: Don't skip generic XDP program execution for cloned SKBs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current generic XDP handler skips execution of XDP programs entirely if an SKB is marked as cloned. This leads to some surprising behaviour, as packets can end up being cloned in various ways, which will make an XDP program not see all the traffic on an interface. This was discovered by a simple test case where an XDP program that always returns XDP_DROP is installed on a veth device. When combining this with the Scapy packet sniffer (which uses an AF_PACKET) socket on the sending side, SKBs reliably end up in the cloned state, causing them to be passed through to the receiving interface instead of being dropped. A minimal reproducer script for this is included below. This patch fixed the issue by simply triggering the existing linearisation code for cloned SKBs instead of skipping the XDP program execution. This behaviour is in line with the behaviour of the native XDP implementation for the veth driver, which will reallocate and copy the SKB data if the SKB is marked as shared. Reproducer Python script (requires BCC and Scapy): from scapy.all import TCP, IP, Ether, sendp, sniff, AsyncSniffer, Raw, UDP from bcc import BPF import time, sys, subprocess, shlex SKB_MODE = (1 << 1) DRV_MODE = (1 << 2) PYTHON=sys.executable def client(): time.sleep(2) # Sniffing on the sender causes skb_cloned() to be set s = AsyncSniffer() s.start() for p in range(10): sendp(Ether(dst="aa:aa:aa:aa:aa:aa", src="cc:cc:cc:cc:cc:cc")/IP()/UDP()/Raw("Test"), verbose=False) time.sleep(0.1) s.stop() return 0 def server(mode): prog = BPF(text="int dummy_drop(struct xdp_md *ctx) {return XDP_DROP;}") func = prog.load_func("dummy_drop", BPF.XDP) prog.attach_xdp("a_to_b", func, mode) time.sleep(1) s = sniff(iface="a_to_b", count=10, timeout=15) if len(s): print(f"Got {len(s)} packets - should have gotten 0") return 1 else: print("Got no packets - as expected") return 0 if len(sys.argv) < 2: print(f"Usage: {sys.argv[0]} ") sys.exit(1) if sys.argv[1] == "client": sys.exit(client()) elif sys.argv[1] == "server": mode = SKB_MODE if sys.argv[2] == 'skb' else DRV_MODE sys.exit(server(mode)) else: try: mode = sys.argv[1] if mode not in ('skb', 'drv'): print(f"Usage: {sys.argv[0]} ") sys.exit(1) print(f"Running in {mode} mode") for cmd in [ 'ip netns add netns_a', 'ip netns add netns_b', 'ip -n netns_a link add a_to_b type veth peer name b_to_a netns netns_b', # Disable ipv6 to make sure there's no address autoconf traffic 'ip netns exec netns_a sysctl -qw net.ipv6.conf.a_to_b.disable_ipv6=1', 'ip netns exec netns_b sysctl -qw net.ipv6.conf.b_to_a.disable_ipv6=1', 'ip -n netns_a link set dev a_to_b address aa:aa:aa:aa:aa:aa', 'ip -n netns_b link set dev b_to_a address cc:cc:cc:cc:cc:cc', 'ip -n netns_a link set dev a_to_b up', 'ip -n netns_b link set dev b_to_a up']: subprocess.check_call(shlex.split(cmd)) server = subprocess.Popen(shlex.split(f"ip netns exec netns_a {PYTHON} {sys.argv[0]} server {mode}")) client = subprocess.Popen(shlex.split(f"ip netns exec netns_b {PYTHON} {sys.argv[0]} client")) client.wait() server.wait() sys.exit(server.returncode) finally: subprocess.run(shlex.split("ip netns delete netns_a")) subprocess.run(shlex.split("ip netns delete netns_b")) Fixes: d445516966dc ("net: xdp: support xdp generic on virtual devices") Reported-by: Stepan Horacek Suggested-by: Paolo Abeni Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- net/core/dev.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index a69e8bd7ed74..a6316b336128 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4527,14 +4527,14 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. */ - if (skb_cloned(skb) || skb_is_tc_redirected(skb)) + if (skb_is_tc_redirected(skb)) return XDP_PASS; /* XDP packets must be linear and must have sufficient headroom * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also * native XDP provides, thus we need to do it here as well. */ - if (skb_is_nonlinear(skb) || + if (skb_cloned(skb) || skb_is_nonlinear(skb) || skb_headroom(skb) < XDP_PACKET_HEADROOM) { int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); int troom = skb->tail + skb->data_len - skb->end; -- cgit v1.2.3 From e08ad80551b4b33c02f2fce1522f6c227d3976cf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 14 Feb 2020 07:53:53 -0800 Subject: net: add strict checks in netdev_name_node_alt_destroy() netdev_name_node_alt_destroy() does a lookup over all device names of a namespace. We need to make sure the name belongs to the device of interest, and that we do not destroy its primary name, since we rely on it being not deleted : dev->name_node would indeed point to freed memory. syzbot report was the following : BUG: KASAN: use-after-free in dev_net include/linux/netdevice.h:2206 [inline] BUG: KASAN: use-after-free in mld_force_mld_version net/ipv6/mcast.c:1172 [inline] BUG: KASAN: use-after-free in mld_in_v2_mode_only net/ipv6/mcast.c:1180 [inline] BUG: KASAN: use-after-free in mld_in_v1_mode+0x203/0x230 net/ipv6/mcast.c:1190 Read of size 8 at addr ffff88809886c588 by task swapper/1/0 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 5.6.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x197/0x210 lib/dump_stack.c:118 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374 __kasan_report.cold+0x1b/0x32 mm/kasan/report.c:506 kasan_report+0x12/0x20 mm/kasan/common.c:641 __asan_report_load8_noabort+0x14/0x20 mm/kasan/generic_report.c:135 dev_net include/linux/netdevice.h:2206 [inline] mld_force_mld_version net/ipv6/mcast.c:1172 [inline] mld_in_v2_mode_only net/ipv6/mcast.c:1180 [inline] mld_in_v1_mode+0x203/0x230 net/ipv6/mcast.c:1190 mld_send_initial_cr net/ipv6/mcast.c:2083 [inline] mld_dad_timer_expire+0x24/0x230 net/ipv6/mcast.c:2118 call_timer_fn+0x1ac/0x780 kernel/time/timer.c:1404 expire_timers kernel/time/timer.c:1449 [inline] __run_timers kernel/time/timer.c:1773 [inline] __run_timers kernel/time/timer.c:1740 [inline] run_timer_softirq+0x6c3/0x1790 kernel/time/timer.c:1786 __do_softirq+0x262/0x98c kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0x19b/0x1e0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:546 [inline] smp_apic_timer_interrupt+0x1a3/0x610 arch/x86/kernel/apic/apic.c:1146 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:829 RIP: 0010:native_safe_halt+0xe/0x10 arch/x86/include/asm/irqflags.h:61 Code: 68 73 c5 f9 eb 8a cc cc cc cc cc cc e9 07 00 00 00 0f 00 2d 94 be 59 00 f4 c3 66 90 e9 07 00 00 00 0f 00 2d 84 be 59 00 fb f4 cc 55 48 89 e5 41 57 41 56 41 55 41 54 53 e8 de 2a 74 f9 e8 09 RSP: 0018:ffffc90000d3fd68 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13 RAX: 1ffffffff136761a RBX: ffff8880a99fc340 RCX: 0000000000000000 RDX: dffffc0000000000 RSI: 0000000000000006 RDI: ffff8880a99fcbd4 RBP: ffffc90000d3fd98 R08: ffff8880a99fc340 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: dffffc0000000000 R13: ffffffff8aa5a1c0 R14: 0000000000000000 R15: 0000000000000001 arch_cpu_idle+0xa/0x10 arch/x86/kernel/process.c:686 default_idle_call+0x84/0xb0 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x3c8/0x6e0 kernel/sched/idle.c:269 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:361 start_secondary+0x2f4/0x410 arch/x86/kernel/smpboot.c:264 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:242 Allocated by task 10229: save_stack+0x23/0x90 mm/kasan/common.c:72 set_track mm/kasan/common.c:80 [inline] __kasan_kmalloc mm/kasan/common.c:515 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:488 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:529 __do_kmalloc_node mm/slab.c:3616 [inline] __kmalloc_node+0x4e/0x70 mm/slab.c:3623 kmalloc_node include/linux/slab.h:578 [inline] kvmalloc_node+0x68/0x100 mm/util.c:574 kvmalloc include/linux/mm.h:645 [inline] kvzalloc include/linux/mm.h:653 [inline] alloc_netdev_mqs+0x98/0xe40 net/core/dev.c:9797 rtnl_create_link+0x22d/0xaf0 net/core/rtnetlink.c:3047 __rtnl_newlink+0xf9f/0x1790 net/core/rtnetlink.c:3309 rtnl_newlink+0x69/0xa0 net/core/rtnetlink.c:3377 rtnetlink_rcv_msg+0x45e/0xaf0 net/core/rtnetlink.c:5438 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5456 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline] netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328 netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:672 __sys_sendto+0x262/0x380 net/socket.c:1998 __do_compat_sys_socketcall net/compat.c:771 [inline] __se_compat_sys_socketcall net/compat.c:719 [inline] __ia32_compat_sys_socketcall+0x530/0x710 net/compat.c:719 do_syscall_32_irqs_on arch/x86/entry/common.c:337 [inline] do_fast_syscall_32+0x27b/0xe16 arch/x86/entry/common.c:408 entry_SYSENTER_compat+0x70/0x7f arch/x86/entry/entry_64_compat.S:139 Freed by task 10229: save_stack+0x23/0x90 mm/kasan/common.c:72 set_track mm/kasan/common.c:80 [inline] kasan_set_free_info mm/kasan/common.c:337 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:476 kasan_slab_free+0xe/0x10 mm/kasan/common.c:485 __cache_free mm/slab.c:3426 [inline] kfree+0x10a/0x2c0 mm/slab.c:3757 __netdev_name_node_alt_destroy+0x1ff/0x2a0 net/core/dev.c:322 netdev_name_node_alt_destroy+0x57/0x80 net/core/dev.c:334 rtnl_alt_ifname net/core/rtnetlink.c:3518 [inline] rtnl_linkprop.isra.0+0x575/0x6f0 net/core/rtnetlink.c:3567 rtnl_dellinkprop+0x46/0x60 net/core/rtnetlink.c:3588 rtnetlink_rcv_msg+0x45e/0xaf0 net/core/rtnetlink.c:5438 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5456 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline] netlink_unicast+0x59e/0x7e0 net/netlink/af_netlink.c:1328 netlink_sendmsg+0x91c/0xea0 net/netlink/af_netlink.c:1917 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:672 ____sys_sendmsg+0x753/0x880 net/socket.c:2343 ___sys_sendmsg+0x100/0x170 net/socket.c:2397 __sys_sendmsg+0x105/0x1d0 net/socket.c:2430 __compat_sys_sendmsg net/compat.c:642 [inline] __do_compat_sys_sendmsg net/compat.c:649 [inline] __se_compat_sys_sendmsg net/compat.c:646 [inline] __ia32_compat_sys_sendmsg+0x7a/0xb0 net/compat.c:646 do_syscall_32_irqs_on arch/x86/entry/common.c:337 [inline] do_fast_syscall_32+0x27b/0xe16 arch/x86/entry/common.c:408 entry_SYSENTER_compat+0x70/0x7f arch/x86/entry/entry_64_compat.S:139 The buggy address belongs to the object at ffff88809886c000 which belongs to the cache kmalloc-4k of size 4096 The buggy address is located 1416 bytes inside of 4096-byte region [ffff88809886c000, ffff88809886d000) The buggy address belongs to the page: page:ffffea0002621b00 refcount:1 mapcount:0 mapping:ffff8880aa402000 index:0x0 compound_mapcount: 0 flags: 0xfffe0000010200(slab|head) raw: 00fffe0000010200 ffffea0002610d08 ffffea0002607608 ffff8880aa402000 raw: 0000000000000000 ffff88809886c000 0000000100000001 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88809886c480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88809886c500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff88809886c580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88809886c600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88809886c680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: 36fbf1e52bd3 ("net: rtnetlink: add linkprop commands to add and delete alternative ifnames") Signed-off-by: Eric Dumazet Reported-by: syzbot Cc: Jiri Pirko Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/dev.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index a6316b336128..b6d13f3f1e5a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -331,6 +331,12 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) name_node = netdev_name_node_lookup(net, name); if (!name_node) return -ENOENT; + /* lookup might have found our primary name or a name belonging + * to another device. + */ + if (name_node == dev->name_node || name_node->dev != dev) + return -EINVAL; + __netdev_name_node_alt_destroy(name_node); return 0; -- cgit v1.2.3 From 7151affeef8d527f50b4b68a871fd28bd660023f Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Sat, 15 Feb 2020 10:50:21 +0000 Subject: net: export netdev_next_lower_dev_rcu() netdev_next_lower_dev_rcu() will be used to implement a function, which is to walk all lower interfaces. There are already functions that they walk their lower interface. (netdev_walk_all_lower_dev_rcu, netdev_walk_all_lower_dev()). But, there would be cases that couldn't be covered by given netdev_walk_all_lower_dev_{rcu}() function. So, some modules would want to implement own function, which is to walk all lower interfaces. In the next patch, netdev_next_lower_dev_rcu() will be used. In addition, this patch removes two unused prototypes in netdevice.h. Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++---- net/core/dev.c | 6 +++--- 2 files changed, 6 insertions(+), 7 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9f1f633235f6..6c3f7032e8d9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -72,6 +72,8 @@ void netdev_set_default_ethtool_ops(struct net_device *dev, #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ #define NET_RX_DROP 1 /* packet dropped */ +#define MAX_NEST_DEV 8 + /* * Transmit return codes: transmit return codes originate from three different * namespaces: @@ -4389,11 +4391,8 @@ void *netdev_lower_get_next(struct net_device *dev, ldev; \ ldev = netdev_lower_get_next(dev, &(iter))) -struct net_device *netdev_all_lower_get_next(struct net_device *dev, +struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter); -struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev, - struct list_head **iter); - int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *lower_dev, void *data), diff --git a/net/core/dev.c b/net/core/dev.c index b6d13f3f1e5a..2577ebfed293 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -146,7 +146,6 @@ #include "net-sysfs.h" #define MAX_GRO_SKBS 8 -#define MAX_NEST_DEV 8 /* This should be increased if a protocol with a bigger head is added. */ #define GRO_MAX_HEAD (MAX_HEADER + 128) @@ -7207,8 +7206,8 @@ static int __netdev_walk_all_lower_dev(struct net_device *dev, return 0; } -static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, - struct list_head **iter) +struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, + struct list_head **iter) { struct netdev_adjacent *lower; @@ -7220,6 +7219,7 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, return lower->dev; } +EXPORT_SYMBOL(netdev_next_lower_dev_rcu); static u8 __netdev_upper_depth(struct net_device *dev) { -- cgit v1.2.3 From 379349e9bc3b42b8b2f8f7a03f64a97623fff323 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 18 Feb 2020 18:15:44 +0100 Subject: Revert "net: dev: introduce support for sch BYPASS for lockless qdisc" This reverts commit ba27b4cdaaa66561aaedb2101876e563738d36fe Ahmed reported ouf-of-order issues bisected to commit ba27b4cdaaa6 ("net: dev: introduce support for sch BYPASS for lockless qdisc"). I can't find any working solution other than a plain revert. This will introduce some minor performance regressions for pfifo_fast qdisc. I plan to address them in net-next with more indirect call wrapper boilerplate for qdiscs. Reported-by: Ahmad Fatoum Fixes: ba27b4cdaaa6 ("net: dev: introduce support for sch BYPASS for lockless qdisc") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- net/core/dev.c | 22 ++-------------------- 1 file changed, 2 insertions(+), 20 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 2577ebfed293..e10bd680dc03 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3662,26 +3662,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_calculate_pkt_len(skb, q); if (q->flags & TCQ_F_NOLOCK) { - if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) && - qdisc_run_begin(q)) { - if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, - &q->state))) { - __qdisc_drop(skb, &to_free); - rc = NET_XMIT_DROP; - goto end_run; - } - qdisc_bstats_cpu_update(q, skb); - - rc = NET_XMIT_SUCCESS; - if (sch_direct_xmit(skb, q, dev, txq, NULL, true)) - __qdisc_run(q); - -end_run: - qdisc_run_end(q); - } else { - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; - qdisc_run(q); - } + rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + qdisc_run(q); if (unlikely(to_free)) kfree_skb_list(to_free); -- cgit v1.2.3