From 16f07c551e3ac433874031433231140d38e69ccd Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 4 Jan 2018 13:55:03 -0800 Subject: bpf: implement syscall command BPF_MAP_GET_NEXT_KEY for stacktrace map Currently, bpf syscall command BPF_MAP_GET_NEXT_KEY is not supported for stacktrace map. However, there are use cases where user space wants to enumerate all stacktrace map entries where BPF_MAP_GET_NEXT_KEY command will be really helpful. In addition, if user space wants to delete all map entries in order to save memory and does not want to close the map file descriptor, BPF_MAP_GET_NEXT_KEY may help improve performance if map entries are sparsely populated. The implementation has similar behavior for BPF_MAP_GET_NEXT_KEY implementation in hashtab. If user provides a NULL key pointer or an invalid key, the first key is returned. Otherwise, the first valid key after the input parameter "key" is returned, or -ENOENT if no valid key can be found. Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- kernel/bpf/stackmap.c | 28 ++++++++++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-) (limited to 'kernel/bpf/stackmap.c') diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index a15bc636cc98..6c63c2222ea8 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -226,9 +226,33 @@ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) return 0; } -static int stack_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +static int stack_map_get_next_key(struct bpf_map *map, void *key, + void *next_key) { - return -EINVAL; + struct bpf_stack_map *smap = container_of(map, + struct bpf_stack_map, map); + u32 id; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (!key) { + id = 0; + } else { + id = *(u32 *)key; + if (id >= smap->n_buckets || !smap->buckets[id]) + id = 0; + else + id++; + } + + while (id < smap->n_buckets && !smap->buckets[id]) + id++; + + if (id >= smap->n_buckets) + return -ENOENT; + + *(u32 *)next_key = id; + return 0; } static int stack_map_update_elem(struct bpf_map *map, void *key, void *value, -- cgit v1.2.3 From bd475643d74e8ed78bfd36d941053b0e45974e8e Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 11 Jan 2018 20:29:06 -0800 Subject: bpf: add helper for copying attrs to struct bpf_map All map types reimplement the field-by-field copy of union bpf_attr members into struct bpf_map. Add a helper to perform this operation. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 1 + kernel/bpf/cpumap.c | 8 +------- kernel/bpf/devmap.c | 8 +------- kernel/bpf/hashtab.c | 9 +-------- kernel/bpf/lpm_trie.c | 7 +------ kernel/bpf/sockmap.c | 8 +------- kernel/bpf/stackmap.c | 6 +----- kernel/bpf/syscall.c | 10 ++++++++++ 8 files changed, 17 insertions(+), 40 deletions(-) (limited to 'kernel/bpf/stackmap.c') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 263598619f90..c60ddfb34d41 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -378,6 +378,7 @@ void bpf_map_put(struct bpf_map *map); int bpf_map_precharge_memlock(u32 pages); void *bpf_map_area_alloc(size_t size, int numa_node); void bpf_map_area_free(void *base); +void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); extern int sysctl_unprivileged_bpf_disabled; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index ce5b669003b2..192151ec9d12 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -94,13 +94,7 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) if (!cmap) return ERR_PTR(-ENOMEM); - /* mandatory map attributes */ - cmap->map.map_type = attr->map_type; - cmap->map.key_size = attr->key_size; - cmap->map.value_size = attr->value_size; - cmap->map.max_entries = attr->max_entries; - cmap->map.map_flags = attr->map_flags; - cmap->map.numa_node = bpf_map_attr_numa_node(attr); + bpf_map_init_from_attr(&cmap->map, attr); /* Pre-limit array size based on NR_CPUS, not final CPU check */ if (cmap->map.max_entries > NR_CPUS) { diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index ebdef54bf7df..565f9ece9115 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -93,13 +93,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) if (!dtab) return ERR_PTR(-ENOMEM); - /* mandatory map attributes */ - dtab->map.map_type = attr->map_type; - dtab->map.key_size = attr->key_size; - dtab->map.value_size = attr->value_size; - dtab->map.max_entries = attr->max_entries; - dtab->map.map_flags = attr->map_flags; - dtab->map.numa_node = bpf_map_attr_numa_node(attr); + bpf_map_init_from_attr(&dtab->map, attr); /* make sure page count doesn't overflow */ cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 7fd6519444d3..b76828f23b49 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -304,7 +304,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) */ bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU); bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); - int numa_node = bpf_map_attr_numa_node(attr); struct bpf_htab *htab; int err, i; u64 cost; @@ -313,13 +312,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (!htab) return ERR_PTR(-ENOMEM); - /* mandatory map attributes */ - htab->map.map_type = attr->map_type; - htab->map.key_size = attr->key_size; - htab->map.value_size = attr->value_size; - htab->map.max_entries = attr->max_entries; - htab->map.map_flags = attr->map_flags; - htab->map.numa_node = numa_node; + bpf_map_init_from_attr(&htab->map, attr); if (percpu_lru) { /* ensure each CPU's lru list has >=1 elements. diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 885e45479680..584e02227671 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -522,12 +522,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) return ERR_PTR(-ENOMEM); /* copy mandatory map attributes */ - trie->map.map_type = attr->map_type; - trie->map.key_size = attr->key_size; - trie->map.value_size = attr->value_size; - trie->map.max_entries = attr->max_entries; - trie->map.map_flags = attr->map_flags; - trie->map.numa_node = bpf_map_attr_numa_node(attr); + bpf_map_init_from_attr(&trie->map, attr); trie->data_size = attr->key_size - offsetof(struct bpf_lpm_trie_key, data); trie->max_prefixlen = trie->data_size * 8; diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 079968680bc3..0314d1783d77 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -513,13 +513,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) if (!stab) return ERR_PTR(-ENOMEM); - /* mandatory map attributes */ - stab->map.map_type = attr->map_type; - stab->map.key_size = attr->key_size; - stab->map.value_size = attr->value_size; - stab->map.max_entries = attr->max_entries; - stab->map.map_flags = attr->map_flags; - stab->map.numa_node = bpf_map_attr_numa_node(attr); + bpf_map_init_from_attr(&stab->map, attr); /* make sure page count doesn't overflow */ cost = (u64) stab->map.max_entries * sizeof(struct sock *); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 6c63c2222ea8..b0ecf43f5894 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -88,14 +88,10 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (cost >= U32_MAX - PAGE_SIZE) goto free_smap; - smap->map.map_type = attr->map_type; - smap->map.key_size = attr->key_size; + bpf_map_init_from_attr(&smap->map, attr); smap->map.value_size = value_size; - smap->map.max_entries = attr->max_entries; - smap->map.map_flags = attr->map_flags; smap->n_buckets = n_buckets; smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; - smap->map.numa_node = bpf_map_attr_numa_node(attr); err = bpf_map_precharge_memlock(smap->map.pages); if (err) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c0ac03a04880..a3f726bb42ea 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -143,6 +143,16 @@ void bpf_map_area_free(void *area) kvfree(area); } +void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) +{ + map->map_type = attr->map_type; + map->key_size = attr->key_size; + map->value_size = attr->value_size; + map->max_entries = attr->max_entries; + map->map_flags = attr->map_flags; + map->numa_node = bpf_map_attr_numa_node(attr); +} + int bpf_map_precharge_memlock(u32 pages) { struct user_struct *user = get_current_user(); -- cgit v1.2.3