From 171526f6fee84de0c39e2b7aa7e666ba0bbfd173 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Sun, 31 May 2020 10:28:35 +0200 Subject: flow_dissector: Pull locking up from prog attach callback Split out the part of attach callback that happens with attach/detach lock acquired. This structures the prog attach callback in a way that opens up doors for moving the locking out of flow_dissector and into generic callbacks for attaching/detaching progs to netns in subsequent patches. Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Reviewed-by: Stanislav Fomichev Link: https://lore.kernel.org/bpf/20200531082846.2117903-2-jakub@cloudflare.com --- net/core/flow_dissector.c | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) (limited to 'net') diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 0aeb33572feb..b64a44a083fd 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -109,15 +109,10 @@ int skb_flow_dissector_prog_query(const union bpf_attr *attr, return 0; } -int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, - struct bpf_prog *prog) +static int flow_dissector_bpf_prog_attach(struct net *net, + struct bpf_prog *prog) { struct bpf_prog *attached; - struct net *net; - int ret = 0; - - net = current->nsproxy->net_ns; - mutex_lock(&flow_dissector_mutex); if (net == &init_net) { /* BPF flow dissector in the root namespace overrides @@ -130,33 +125,38 @@ int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, for_each_net(ns) { if (ns == &init_net) continue; - if (rcu_access_pointer(ns->flow_dissector_prog)) { - ret = -EEXIST; - goto out; - } + if (rcu_access_pointer(ns->flow_dissector_prog)) + return -EEXIST; } } else { /* Make sure root flow dissector is not attached * when attaching to the non-root namespace. */ - if (rcu_access_pointer(init_net.flow_dissector_prog)) { - ret = -EEXIST; - goto out; - } + if (rcu_access_pointer(init_net.flow_dissector_prog)) + return -EEXIST; } attached = rcu_dereference_protected(net->flow_dissector_prog, lockdep_is_held(&flow_dissector_mutex)); - if (attached == prog) { + if (attached == prog) /* The same program cannot be attached twice */ - ret = -EINVAL; - goto out; - } + return -EINVAL; + rcu_assign_pointer(net->flow_dissector_prog, prog); if (attached) bpf_prog_put(attached); -out: + return 0; +} + +int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + int ret; + + mutex_lock(&flow_dissector_mutex); + ret = flow_dissector_bpf_prog_attach(current->nsproxy->net_ns, prog); mutex_unlock(&flow_dissector_mutex); + return ret; } -- cgit v1.2.3 From a3fd7ceee05431d2c51ed86c6cae015d236a51f0 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Sun, 31 May 2020 10:28:36 +0200 Subject: net: Introduce netns_bpf for BPF programs attached to netns In order to: (1) attach more than one BPF program type to netns, or (2) support attaching BPF programs to netns with bpf_link, or (3) support multi-prog attach points for netns we will need to keep more state per netns than a single pointer like we have now for BPF flow dissector program. Prepare for the above by extracting netns_bpf that is part of struct net, for storing all state related to BPF programs attached to netns. Turn flow dissector callbacks for querying/attaching/detaching a program into generic ones that operate on netns_bpf. Next patch will move the generic callbacks into their own module. This is similar to how it is organized for cgroup with cgroup_bpf. Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Cc: Stanislav Fomichev Link: https://lore.kernel.org/bpf/20200531082846.2117903-3-jakub@cloudflare.com --- net/core/flow_dissector.c | 105 ++++++++++++++++++++++++++++++---------------- 1 file changed, 69 insertions(+), 36 deletions(-) (limited to 'net') diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index b64a44a083fd..6c1b8e43d611 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -31,8 +31,10 @@ #include #include #endif +#include -static DEFINE_MUTEX(flow_dissector_mutex); +/* Protects updates to netns_bpf */ +DEFINE_MUTEX(netns_bpf_mutex); static void dissector_set_key(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) @@ -70,23 +72,28 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, } EXPORT_SYMBOL(skb_flow_dissector_init); -int skb_flow_dissector_prog_query(const union bpf_attr *attr, - union bpf_attr __user *uattr) +int netns_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) { __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); u32 prog_id, prog_cnt = 0, flags = 0; + enum netns_bpf_attach_type type; struct bpf_prog *attached; struct net *net; if (attr->query.query_flags) return -EINVAL; + type = to_netns_bpf_attach_type(attr->query.attach_type); + if (type < 0) + return -EINVAL; + net = get_net_ns_by_fd(attr->query.target_fd); if (IS_ERR(net)) return PTR_ERR(net); rcu_read_lock(); - attached = rcu_dereference(net->flow_dissector_prog); + attached = rcu_dereference(net->bpf.progs[type]); if (attached) { prog_cnt = 1; prog_id = attached->aux->id; @@ -112,6 +119,7 @@ int skb_flow_dissector_prog_query(const union bpf_attr *attr, static int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog) { + enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; struct bpf_prog *attached; if (net == &init_net) { @@ -125,74 +133,97 @@ static int flow_dissector_bpf_prog_attach(struct net *net, for_each_net(ns) { if (ns == &init_net) continue; - if (rcu_access_pointer(ns->flow_dissector_prog)) + if (rcu_access_pointer(ns->bpf.progs[type])) return -EEXIST; } } else { /* Make sure root flow dissector is not attached * when attaching to the non-root namespace. */ - if (rcu_access_pointer(init_net.flow_dissector_prog)) + if (rcu_access_pointer(init_net.bpf.progs[type])) return -EEXIST; } - attached = rcu_dereference_protected(net->flow_dissector_prog, - lockdep_is_held(&flow_dissector_mutex)); + attached = rcu_dereference_protected(net->bpf.progs[type], + lockdep_is_held(&netns_bpf_mutex)); if (attached == prog) /* The same program cannot be attached twice */ return -EINVAL; - rcu_assign_pointer(net->flow_dissector_prog, prog); + rcu_assign_pointer(net->bpf.progs[type], prog); if (attached) bpf_prog_put(attached); return 0; } -int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, - struct bpf_prog *prog) +int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { + enum netns_bpf_attach_type type; + struct net *net; int ret; - mutex_lock(&flow_dissector_mutex); - ret = flow_dissector_bpf_prog_attach(current->nsproxy->net_ns, prog); - mutex_unlock(&flow_dissector_mutex); + type = to_netns_bpf_attach_type(attr->attach_type); + if (type < 0) + return -EINVAL; + + net = current->nsproxy->net_ns; + mutex_lock(&netns_bpf_mutex); + switch (type) { + case NETNS_BPF_FLOW_DISSECTOR: + ret = flow_dissector_bpf_prog_attach(net, prog); + break; + default: + ret = -EINVAL; + break; + } + mutex_unlock(&netns_bpf_mutex); return ret; } -static int flow_dissector_bpf_prog_detach(struct net *net) +/* Must be called with netns_bpf_mutex held. */ +static int __netns_bpf_prog_detach(struct net *net, + enum netns_bpf_attach_type type) { struct bpf_prog *attached; - mutex_lock(&flow_dissector_mutex); - attached = rcu_dereference_protected(net->flow_dissector_prog, - lockdep_is_held(&flow_dissector_mutex)); - if (!attached) { - mutex_unlock(&flow_dissector_mutex); + attached = rcu_dereference_protected(net->bpf.progs[type], + lockdep_is_held(&netns_bpf_mutex)); + if (!attached) return -ENOENT; - } - RCU_INIT_POINTER(net->flow_dissector_prog, NULL); + RCU_INIT_POINTER(net->bpf.progs[type], NULL); bpf_prog_put(attached); - mutex_unlock(&flow_dissector_mutex); return 0; } -int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) +int netns_bpf_prog_detach(const union bpf_attr *attr) { - return flow_dissector_bpf_prog_detach(current->nsproxy->net_ns); + enum netns_bpf_attach_type type; + int ret; + + type = to_netns_bpf_attach_type(attr->attach_type); + if (type < 0) + return -EINVAL; + + mutex_lock(&netns_bpf_mutex); + ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type); + mutex_unlock(&netns_bpf_mutex); + + return ret; } -static void __net_exit flow_dissector_pernet_pre_exit(struct net *net) +static void __net_exit netns_bpf_pernet_pre_exit(struct net *net) { - /* We're not racing with attach/detach because there are no - * references to netns left when pre_exit gets called. - */ - if (rcu_access_pointer(net->flow_dissector_prog)) - flow_dissector_bpf_prog_detach(net); + enum netns_bpf_attach_type type; + + mutex_lock(&netns_bpf_mutex); + for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) + __netns_bpf_prog_detach(net, type); + mutex_unlock(&netns_bpf_mutex); } -static struct pernet_operations flow_dissector_pernet_ops __net_initdata = { - .pre_exit = flow_dissector_pernet_pre_exit, +static struct pernet_operations netns_bpf_pernet_ops __net_initdata = { + .pre_exit = netns_bpf_pernet_pre_exit, }; /** @@ -1044,11 +1075,13 @@ bool __skb_flow_dissect(const struct net *net, WARN_ON_ONCE(!net); if (net) { + enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; + rcu_read_lock(); - attached = rcu_dereference(init_net.flow_dissector_prog); + attached = rcu_dereference(init_net.bpf.progs[type]); if (!attached) - attached = rcu_dereference(net->flow_dissector_prog); + attached = rcu_dereference(net->bpf.progs[type]); if (attached) { struct bpf_flow_keys flow_keys; @@ -1870,6 +1903,6 @@ static int __init init_default_flow_dissectors(void) flow_keys_basic_dissector_keys, ARRAY_SIZE(flow_keys_basic_dissector_keys)); - return register_pernet_subsys(&flow_dissector_pernet_ops); + return register_pernet_subsys(&netns_bpf_pernet_ops); } core_initcall(init_default_flow_dissectors); -- cgit v1.2.3 From b27f7bb590ba835b32ef122389db158e44cfda1e Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Sun, 31 May 2020 10:28:37 +0200 Subject: flow_dissector: Move out netns_bpf prog callbacks Move functions to manage BPF programs attached to netns that are not specific to flow dissector to a dedicated module named bpf/net_namespace.c. The set of functions will grow with the addition of bpf_link support for netns attached programs. This patch prepares ground by creating a place for it. This is a code move with no functional changes intended. Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200531082846.2117903-4-jakub@cloudflare.com --- net/core/flow_dissector.c | 125 ++-------------------------------------------- 1 file changed, 4 insertions(+), 121 deletions(-) (limited to 'net') diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 6c1b8e43d611..d02df0b6d0d9 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -33,9 +33,6 @@ #endif #include -/* Protects updates to netns_bpf */ -DEFINE_MUTEX(netns_bpf_mutex); - static void dissector_set_key(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) { @@ -72,52 +69,8 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, } EXPORT_SYMBOL(skb_flow_dissector_init); -int netns_bpf_prog_query(const union bpf_attr *attr, - union bpf_attr __user *uattr) -{ - __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); - u32 prog_id, prog_cnt = 0, flags = 0; - enum netns_bpf_attach_type type; - struct bpf_prog *attached; - struct net *net; - - if (attr->query.query_flags) - return -EINVAL; - - type = to_netns_bpf_attach_type(attr->query.attach_type); - if (type < 0) - return -EINVAL; - - net = get_net_ns_by_fd(attr->query.target_fd); - if (IS_ERR(net)) - return PTR_ERR(net); - - rcu_read_lock(); - attached = rcu_dereference(net->bpf.progs[type]); - if (attached) { - prog_cnt = 1; - prog_id = attached->aux->id; - } - rcu_read_unlock(); - - put_net(net); - - if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) - return -EFAULT; - if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) - return -EFAULT; - - if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) - return 0; - - if (copy_to_user(prog_ids, &prog_id, sizeof(u32))) - return -EFAULT; - - return 0; -} - -static int flow_dissector_bpf_prog_attach(struct net *net, - struct bpf_prog *prog) +#ifdef CONFIG_BPF_SYSCALL +int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; struct bpf_prog *attached; @@ -155,76 +108,7 @@ static int flow_dissector_bpf_prog_attach(struct net *net, bpf_prog_put(attached); return 0; } - -int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) -{ - enum netns_bpf_attach_type type; - struct net *net; - int ret; - - type = to_netns_bpf_attach_type(attr->attach_type); - if (type < 0) - return -EINVAL; - - net = current->nsproxy->net_ns; - mutex_lock(&netns_bpf_mutex); - switch (type) { - case NETNS_BPF_FLOW_DISSECTOR: - ret = flow_dissector_bpf_prog_attach(net, prog); - break; - default: - ret = -EINVAL; - break; - } - mutex_unlock(&netns_bpf_mutex); - - return ret; -} - -/* Must be called with netns_bpf_mutex held. */ -static int __netns_bpf_prog_detach(struct net *net, - enum netns_bpf_attach_type type) -{ - struct bpf_prog *attached; - - attached = rcu_dereference_protected(net->bpf.progs[type], - lockdep_is_held(&netns_bpf_mutex)); - if (!attached) - return -ENOENT; - RCU_INIT_POINTER(net->bpf.progs[type], NULL); - bpf_prog_put(attached); - return 0; -} - -int netns_bpf_prog_detach(const union bpf_attr *attr) -{ - enum netns_bpf_attach_type type; - int ret; - - type = to_netns_bpf_attach_type(attr->attach_type); - if (type < 0) - return -EINVAL; - - mutex_lock(&netns_bpf_mutex); - ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type); - mutex_unlock(&netns_bpf_mutex); - - return ret; -} - -static void __net_exit netns_bpf_pernet_pre_exit(struct net *net) -{ - enum netns_bpf_attach_type type; - - mutex_lock(&netns_bpf_mutex); - for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) - __netns_bpf_prog_detach(net, type); - mutex_unlock(&netns_bpf_mutex); -} - -static struct pernet_operations netns_bpf_pernet_ops __net_initdata = { - .pre_exit = netns_bpf_pernet_pre_exit, -}; +#endif /* CONFIG_BPF_SYSCALL */ /** * __skb_flow_get_ports - extract the upper layer ports and return them @@ -1902,7 +1786,6 @@ static int __init init_default_flow_dissectors(void) skb_flow_dissector_init(&flow_keys_basic_dissector, flow_keys_basic_dissector_keys, ARRAY_SIZE(flow_keys_basic_dissector_keys)); - - return register_pernet_subsys(&netns_bpf_pernet_ops); + return 0; } core_initcall(init_default_flow_dissectors); -- cgit v1.2.3