From 15c14a3dca421f086c187155afba3222b879472d Mon Sep 17 00:00:00 2001 From: Brian Vazquez Date: Wed, 15 Jan 2020 10:43:00 -0800 Subject: [PATCH 1/9] bpf: Add bpf_map_{value_size, update_value, map_copy_value} functions This commit moves reusable code from map_lookup_elem and map_update_elem to avoid code duplication in kernel/bpf/syscall.c. Signed-off-by: Brian Vazquez Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20200115184308.162644-2-brianvv@google.com --- kernel/bpf/syscall.c | 280 +++++++++++++++++++++++-------------------- 1 file changed, 152 insertions(+), 128 deletions(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f9db72a96ec0..08b0b6e40454 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -129,6 +129,154 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } +static u32 bpf_map_value_size(struct bpf_map *map) +{ + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) + return round_up(map->value_size, 8) * num_possible_cpus(); + else if (IS_FD_MAP(map)) + return sizeof(u32); + else + return map->value_size; +} + +static void maybe_wait_bpf_programs(struct bpf_map *map) +{ + /* Wait for any running BPF programs to complete so that + * userspace, when we return to it, knows that all programs + * that could be running use the new map value. + */ + if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS || + map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) + synchronize_rcu(); +} + +static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, + void *value, __u64 flags) +{ + int err; + + /* Need to create a kthread, thus must support schedule */ + if (bpf_map_is_dev_bound(map)) { + return bpf_map_offload_update_elem(map, key, value, flags); + } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || + map->map_type == BPF_MAP_TYPE_SOCKHASH || + map->map_type == BPF_MAP_TYPE_SOCKMAP || + map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { + return map->ops->map_update_elem(map, key, value, flags); + } else if (IS_FD_PROG_ARRAY(map)) { + return bpf_fd_array_map_update_elem(map, f.file, key, value, + flags); + } + + /* must increment bpf_prog_active to avoid kprobe+bpf triggering from + * inside bpf map update or delete otherwise deadlocks are possible + */ + preempt_disable(); + __this_cpu_inc(bpf_prog_active); + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + err = bpf_percpu_hash_update(map, key, value, flags); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { + err = bpf_percpu_array_update(map, key, value, flags); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + err = bpf_percpu_cgroup_storage_update(map, key, value, + flags); + } else if (IS_FD_ARRAY(map)) { + rcu_read_lock(); + err = bpf_fd_array_map_update_elem(map, f.file, key, value, + flags); + rcu_read_unlock(); + } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { + rcu_read_lock(); + err = bpf_fd_htab_map_update_elem(map, f.file, key, value, + flags); + rcu_read_unlock(); + } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { + /* rcu_read_lock() is not needed */ + err = bpf_fd_reuseport_array_update_elem(map, key, value, + flags); + } else if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_push_elem(map, value, flags); + } else { + rcu_read_lock(); + err = map->ops->map_update_elem(map, key, value, flags); + rcu_read_unlock(); + } + __this_cpu_dec(bpf_prog_active); + preempt_enable(); + maybe_wait_bpf_programs(map); + + return err; +} + +static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, + __u64 flags) +{ + void *ptr; + int err; + + if (bpf_map_is_dev_bound(map)) { + err = bpf_map_offload_lookup_elem(map, key, value); + return err; + } + + preempt_disable(); + this_cpu_inc(bpf_prog_active); + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + err = bpf_percpu_hash_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { + err = bpf_percpu_array_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + err = bpf_percpu_cgroup_storage_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { + err = bpf_stackmap_copy(map, key, value); + } else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) { + err = bpf_fd_array_map_lookup_elem(map, key, value); + } else if (IS_FD_HASH(map)) { + err = bpf_fd_htab_map_lookup_elem(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { + err = bpf_fd_reuseport_array_lookup_elem(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_peek_elem(map, value); + } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { + /* struct_ops map requires directly updating "value" */ + err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); + } else { + rcu_read_lock(); + if (map->ops->map_lookup_elem_sys_only) + ptr = map->ops->map_lookup_elem_sys_only(map, key); + else + ptr = map->ops->map_lookup_elem(map, key); + if (IS_ERR(ptr)) { + err = PTR_ERR(ptr); + } else if (!ptr) { + err = -ENOENT; + } else { + err = 0; + if (flags & BPF_F_LOCK) + /* lock 'ptr' and copy everything but lock */ + copy_map_value_locked(map, value, ptr, true); + else + copy_map_value(map, value, ptr); + /* mask lock, since value wasn't zero inited */ + check_and_init_map_lock(map, value); + } + rcu_read_unlock(); + } + + this_cpu_dec(bpf_prog_active); + preempt_enable(); + maybe_wait_bpf_programs(map); + + return err; +} + static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) { /* We really just want to fail instead of triggering OOM killer @@ -827,7 +975,7 @@ static int map_lookup_elem(union bpf_attr *attr) void __user *uvalue = u64_to_user_ptr(attr->value); int ufd = attr->map_fd; struct bpf_map *map; - void *key, *value, *ptr; + void *key, *value; u32 value_size; struct fd f; int err; @@ -859,75 +1007,14 @@ static int map_lookup_elem(union bpf_attr *attr) goto err_put; } - if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || - map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) - value_size = round_up(map->value_size, 8) * num_possible_cpus(); - else if (IS_FD_MAP(map)) - value_size = sizeof(u32); - else - value_size = map->value_size; + value_size = bpf_map_value_size(map); err = -ENOMEM; value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; - if (bpf_map_is_dev_bound(map)) { - err = bpf_map_offload_lookup_elem(map, key, value); - goto done; - } - - preempt_disable(); - this_cpu_inc(bpf_prog_active); - if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { - err = bpf_percpu_hash_copy(map, key, value); - } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { - err = bpf_percpu_array_copy(map, key, value); - } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { - err = bpf_percpu_cgroup_storage_copy(map, key, value); - } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { - err = bpf_stackmap_copy(map, key, value); - } else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) { - err = bpf_fd_array_map_lookup_elem(map, key, value); - } else if (IS_FD_HASH(map)) { - err = bpf_fd_htab_map_lookup_elem(map, key, value); - } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { - err = bpf_fd_reuseport_array_lookup_elem(map, key, value); - } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { - err = map->ops->map_peek_elem(map, value); - } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { - /* struct_ops map requires directly updating "value" */ - err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); - } else { - rcu_read_lock(); - if (map->ops->map_lookup_elem_sys_only) - ptr = map->ops->map_lookup_elem_sys_only(map, key); - else - ptr = map->ops->map_lookup_elem(map, key); - if (IS_ERR(ptr)) { - err = PTR_ERR(ptr); - } else if (!ptr) { - err = -ENOENT; - } else { - err = 0; - if (attr->flags & BPF_F_LOCK) - /* lock 'ptr' and copy everything but lock */ - copy_map_value_locked(map, value, ptr, true); - else - copy_map_value(map, value, ptr); - /* mask lock, since value wasn't zero inited */ - check_and_init_map_lock(map, value); - } - rcu_read_unlock(); - } - this_cpu_dec(bpf_prog_active); - preempt_enable(); - -done: + err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; @@ -946,16 +1033,6 @@ static int map_lookup_elem(union bpf_attr *attr) return err; } -static void maybe_wait_bpf_programs(struct bpf_map *map) -{ - /* Wait for any running BPF programs to complete so that - * userspace, when we return to it, knows that all programs - * that could be running use the new map value. - */ - if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS || - map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) - synchronize_rcu(); -} #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags @@ -1011,61 +1088,8 @@ static int map_update_elem(union bpf_attr *attr) if (copy_from_user(value, uvalue, value_size) != 0) goto free_value; - /* Need to create a kthread, thus must support schedule */ - if (bpf_map_is_dev_bound(map)) { - err = bpf_map_offload_update_elem(map, key, value, attr->flags); - goto out; - } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || - map->map_type == BPF_MAP_TYPE_SOCKHASH || - map->map_type == BPF_MAP_TYPE_SOCKMAP || - map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { - err = map->ops->map_update_elem(map, key, value, attr->flags); - goto out; - } else if (IS_FD_PROG_ARRAY(map)) { - err = bpf_fd_array_map_update_elem(map, f.file, key, value, - attr->flags); - goto out; - } + err = bpf_map_update_value(map, f, key, value, attr->flags); - /* must increment bpf_prog_active to avoid kprobe+bpf triggering from - * inside bpf map update or delete otherwise deadlocks are possible - */ - preempt_disable(); - __this_cpu_inc(bpf_prog_active); - if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { - err = bpf_percpu_hash_update(map, key, value, attr->flags); - } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { - err = bpf_percpu_array_update(map, key, value, attr->flags); - } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { - err = bpf_percpu_cgroup_storage_update(map, key, value, - attr->flags); - } else if (IS_FD_ARRAY(map)) { - rcu_read_lock(); - err = bpf_fd_array_map_update_elem(map, f.file, key, value, - attr->flags); - rcu_read_unlock(); - } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { - rcu_read_lock(); - err = bpf_fd_htab_map_update_elem(map, f.file, key, value, - attr->flags); - rcu_read_unlock(); - } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { - /* rcu_read_lock() is not needed */ - err = bpf_fd_reuseport_array_update_elem(map, key, value, - attr->flags); - } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { - err = map->ops->map_push_elem(map, value, attr->flags); - } else { - rcu_read_lock(); - err = map->ops->map_update_elem(map, key, value, attr->flags); - rcu_read_unlock(); - } - __this_cpu_dec(bpf_prog_active); - preempt_enable(); - maybe_wait_bpf_programs(map); -out: free_value: kfree(value); free_key: From cb4d03ab499d4c040f4ab6fd4389d2b49f42b5a5 Mon Sep 17 00:00:00 2001 From: Brian Vazquez Date: Wed, 15 Jan 2020 10:43:01 -0800 Subject: [PATCH 2/9] bpf: Add generic support for lookup batch op This commit introduces generic support for the bpf_map_lookup_batch. This implementation can be used by almost all the bpf maps since its core implementation is relying on the existing map_get_next_key and map_lookup_elem. The bpf syscall subcommand introduced is: BPF_MAP_LOOKUP_BATCH The UAPI attribute is: struct { /* struct used by BPF_MAP_*_BATCH commands */ __aligned_u64 in_batch; /* start batch, * NULL to start from beginning */ __aligned_u64 out_batch; /* output: next start batch */ __aligned_u64 keys; __aligned_u64 values; __u32 count; /* input/output: * input: # of key/value * elements * output: # of filled elements */ __u32 map_fd; __u64 elem_flags; __u64 flags; } batch; in_batch/out_batch are opaque values use to communicate between user/kernel space, in_batch/out_batch must be of key_size length. To start iterating from the beginning in_batch must be null, count is the # of key/value elements to retrieve. Note that the 'keys' buffer must be a buffer of key_size * count size and the 'values' buffer must be value_size * count, where value_size must be aligned to 8 bytes by userspace if it's dealing with percpu maps. 'count' will contain the number of keys/values successfully retrieved. Note that 'count' is an input/output variable and it can contain a lower value after a call. If there's no more entries to retrieve, ENOENT will be returned. If error is ENOENT, count might be > 0 in case it copied some values but there were no more entries to retrieve. Note that if the return code is an error and not -EFAULT, count indicates the number of elements successfully processed. Suggested-by: Stanislav Fomichev Signed-off-by: Brian Vazquez Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200115184308.162644-3-brianvv@google.com --- include/linux/bpf.h | 5 ++ include/uapi/linux/bpf.h | 18 +++++ kernel/bpf/syscall.c | 160 ++++++++++++++++++++++++++++++++++++++- 3 files changed, 179 insertions(+), 4 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index aed2bc39d72b..807744ecaa5a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -44,6 +44,8 @@ struct bpf_map_ops { int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key); void (*map_release_uref)(struct bpf_map *map); void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); + int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr); /* funcs callable from userspace and from eBPF programs */ void *(*map_lookup_elem)(struct bpf_map *map, void *key); @@ -982,6 +984,9 @@ void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 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); +int generic_map_lookup_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr); extern int sysctl_unprivileged_bpf_disabled; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a88837d4dd18..0721b2c6bb8c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -107,6 +107,7 @@ enum bpf_cmd { BPF_MAP_LOOKUP_AND_DELETE_ELEM, BPF_MAP_FREEZE, BPF_BTF_GET_NEXT_ID, + BPF_MAP_LOOKUP_BATCH, }; enum bpf_map_type { @@ -420,6 +421,23 @@ union bpf_attr { __u64 flags; }; + struct { /* struct used by BPF_MAP_*_BATCH commands */ + __aligned_u64 in_batch; /* start batch, + * NULL to start from beginning + */ + __aligned_u64 out_batch; /* output: next start batch */ + __aligned_u64 keys; + __aligned_u64 values; + __u32 count; /* input/output: + * input: # of key/value + * elements + * output: # of filled elements + */ + __u32 map_fd; + __u64 elem_flags; + __u64 flags; + } batch; + struct { /* anonymous struct used by BPF_PROG_LOAD command */ __u32 prog_type; /* one of enum bpf_prog_type */ __u32 insn_cnt; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 08b0b6e40454..d604ddbb1afb 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -219,10 +219,8 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, void *ptr; int err; - if (bpf_map_is_dev_bound(map)) { - err = bpf_map_offload_lookup_elem(map, key, value); - return err; - } + if (bpf_map_is_dev_bound(map)) + return bpf_map_offload_lookup_elem(map, key, value); preempt_disable(); this_cpu_inc(bpf_prog_active); @@ -1220,6 +1218,109 @@ static int map_get_next_key(union bpf_attr *attr) return err; } +#define MAP_LOOKUP_RETRIES 3 + +int generic_map_lookup_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + void __user *uobatch = u64_to_user_ptr(attr->batch.out_batch); + void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch); + void __user *values = u64_to_user_ptr(attr->batch.values); + void __user *keys = u64_to_user_ptr(attr->batch.keys); + void *buf, *buf_prevkey, *prev_key, *key, *value; + int err, retry = MAP_LOOKUP_RETRIES; + u32 value_size, cp, max_count; + bool first_key = false; + + if (attr->batch.elem_flags & ~BPF_F_LOCK) + return -EINVAL; + + if ((attr->batch.elem_flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) + return -EINVAL; + + value_size = bpf_map_value_size(map); + + max_count = attr->batch.count; + if (!max_count) + return 0; + + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + + buf_prevkey = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + if (!buf_prevkey) + return -ENOMEM; + + buf = kmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN); + if (!buf) { + kvfree(buf_prevkey); + return -ENOMEM; + } + + err = -EFAULT; + first_key = false; + prev_key = NULL; + if (ubatch && copy_from_user(buf_prevkey, ubatch, map->key_size)) + goto free_buf; + key = buf; + value = key + map->key_size; + if (ubatch) + prev_key = buf_prevkey; + + for (cp = 0; cp < max_count;) { + rcu_read_lock(); + err = map->ops->map_get_next_key(map, prev_key, key); + rcu_read_unlock(); + if (err) + break; + err = bpf_map_copy_value(map, key, value, + attr->batch.elem_flags); + + if (err == -ENOENT) { + if (retry) { + retry--; + continue; + } + err = -EINTR; + break; + } + + if (err) + goto free_buf; + + if (copy_to_user(keys + cp * map->key_size, key, + map->key_size)) { + err = -EFAULT; + goto free_buf; + } + if (copy_to_user(values + cp * value_size, value, value_size)) { + err = -EFAULT; + goto free_buf; + } + + if (!prev_key) + prev_key = buf_prevkey; + + swap(prev_key, key); + retry = MAP_LOOKUP_RETRIES; + cp++; + } + + if (err == -EFAULT) + goto free_buf; + + if ((copy_to_user(&uattr->batch.count, &cp, sizeof(cp)) || + (cp && copy_to_user(uobatch, prev_key, map->key_size)))) + err = -EFAULT; + +free_buf: + kfree(buf_prevkey); + kfree(buf); + return err; +} + #define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value static int map_lookup_and_delete_elem(union bpf_attr *attr) @@ -3076,6 +3177,54 @@ static int bpf_task_fd_query(const union bpf_attr *attr, return err; } +#define BPF_MAP_BATCH_LAST_FIELD batch.flags + +#define BPF_DO_BATCH(fn) \ + do { \ + if (!fn) { \ + err = -ENOTSUPP; \ + goto err_put; \ + } \ + err = fn(map, attr, uattr); \ + } while (0) + +static int bpf_map_do_batch(const union bpf_attr *attr, + union bpf_attr __user *uattr, + int cmd) +{ + struct bpf_map *map; + int err, ufd; + struct fd f; + + if (CHECK_ATTR(BPF_MAP_BATCH)) + return -EINVAL; + + ufd = attr->batch.map_fd; + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + if (cmd == BPF_MAP_LOOKUP_BATCH && + !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { + err = -EPERM; + goto err_put; + } + + if (cmd != BPF_MAP_LOOKUP_BATCH && + !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + + if (cmd == BPF_MAP_LOOKUP_BATCH) + BPF_DO_BATCH(map->ops->map_lookup_batch); + +err_put: + fdput(f); + return err; +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr = {}; @@ -3173,6 +3322,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_MAP_LOOKUP_AND_DELETE_ELEM: err = map_lookup_and_delete_elem(&attr); break; + case BPF_MAP_LOOKUP_BATCH: + err = bpf_map_do_batch(&attr, uattr, BPF_MAP_LOOKUP_BATCH); + break; default: err = -EINVAL; break; From aa2e93b8e58e18442edfb2427446732415bc215e Mon Sep 17 00:00:00 2001 From: Brian Vazquez Date: Wed, 15 Jan 2020 10:43:02 -0800 Subject: [PATCH 3/9] bpf: Add generic support for update and delete batch ops This commit adds generic support for update and delete batch ops that can be used for almost all the bpf maps. These commands share the same UAPI attr that lookup and lookup_and_delete batch ops use and the syscall commands are: BPF_MAP_UPDATE_BATCH BPF_MAP_DELETE_BATCH The main difference between update/delete and lookup batch ops is that for update/delete keys/values must be specified for userspace and because of that, neither in_batch nor out_batch are used. Suggested-by: Stanislav Fomichev Signed-off-by: Brian Vazquez Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200115184308.162644-4-brianvv@google.com --- include/linux/bpf.h | 10 ++++ include/uapi/linux/bpf.h | 2 + kernel/bpf/syscall.c | 115 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 127 insertions(+) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 807744ecaa5a..05466ad6cf1c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -46,6 +46,10 @@ struct bpf_map_ops { void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); + int (*map_update_batch)(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr); + int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr); /* funcs callable from userspace and from eBPF programs */ void *(*map_lookup_elem)(struct bpf_map *map, void *key); @@ -987,6 +991,12 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); +int generic_map_update_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr); +int generic_map_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr); extern int sysctl_unprivileged_bpf_disabled; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0721b2c6bb8c..d5320b0be459 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -108,6 +108,8 @@ enum bpf_cmd { BPF_MAP_FREEZE, BPF_BTF_GET_NEXT_ID, BPF_MAP_LOOKUP_BATCH, + BPF_MAP_UPDATE_BATCH, + BPF_MAP_DELETE_BATCH, }; enum bpf_map_type { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d604ddbb1afb..ce8244d1ba99 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1218,6 +1218,111 @@ static int map_get_next_key(union bpf_attr *attr) return err; } +int generic_map_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + void __user *keys = u64_to_user_ptr(attr->batch.keys); + u32 cp, max_count; + int err = 0; + void *key; + + if (attr->batch.elem_flags & ~BPF_F_LOCK) + return -EINVAL; + + if ((attr->batch.elem_flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) { + return -EINVAL; + } + + max_count = attr->batch.count; + if (!max_count) + return 0; + + for (cp = 0; cp < max_count; cp++) { + key = __bpf_copy_key(keys + cp * map->key_size, map->key_size); + if (IS_ERR(key)) { + err = PTR_ERR(key); + break; + } + + if (bpf_map_is_dev_bound(map)) { + err = bpf_map_offload_delete_elem(map, key); + break; + } + + preempt_disable(); + __this_cpu_inc(bpf_prog_active); + rcu_read_lock(); + err = map->ops->map_delete_elem(map, key); + rcu_read_unlock(); + __this_cpu_dec(bpf_prog_active); + preempt_enable(); + maybe_wait_bpf_programs(map); + if (err) + break; + } + if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) + err = -EFAULT; + return err; +} + +int generic_map_update_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + void __user *values = u64_to_user_ptr(attr->batch.values); + void __user *keys = u64_to_user_ptr(attr->batch.keys); + u32 value_size, cp, max_count; + int ufd = attr->map_fd; + void *key, *value; + struct fd f; + int err = 0; + + f = fdget(ufd); + if (attr->batch.elem_flags & ~BPF_F_LOCK) + return -EINVAL; + + if ((attr->batch.elem_flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) { + return -EINVAL; + } + + value_size = bpf_map_value_size(map); + + max_count = attr->batch.count; + if (!max_count) + return 0; + + value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); + if (!value) + return -ENOMEM; + + for (cp = 0; cp < max_count; cp++) { + key = __bpf_copy_key(keys + cp * map->key_size, map->key_size); + if (IS_ERR(key)) { + err = PTR_ERR(key); + break; + } + err = -EFAULT; + if (copy_from_user(value, values + cp * value_size, value_size)) + break; + + err = bpf_map_update_value(map, f, key, value, + attr->batch.elem_flags); + + if (err) + break; + } + + if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) + err = -EFAULT; + + kfree(value); + kfree(key); + return err; +} + #define MAP_LOOKUP_RETRIES 3 int generic_map_lookup_batch(struct bpf_map *map, @@ -3219,6 +3324,10 @@ static int bpf_map_do_batch(const union bpf_attr *attr, if (cmd == BPF_MAP_LOOKUP_BATCH) BPF_DO_BATCH(map->ops->map_lookup_batch); + else if (cmd == BPF_MAP_UPDATE_BATCH) + BPF_DO_BATCH(map->ops->map_update_batch); + else + BPF_DO_BATCH(map->ops->map_delete_batch); err_put: fdput(f); @@ -3325,6 +3434,12 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_MAP_LOOKUP_BATCH: err = bpf_map_do_batch(&attr, uattr, BPF_MAP_LOOKUP_BATCH); break; + case BPF_MAP_UPDATE_BATCH: + err = bpf_map_do_batch(&attr, uattr, BPF_MAP_UPDATE_BATCH); + break; + case BPF_MAP_DELETE_BATCH: + err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH); + break; default: err = -EINVAL; break; From c60f2d2861778de6370a4f4ca6ab1d7d4a32efae Mon Sep 17 00:00:00 2001 From: Brian Vazquez Date: Wed, 15 Jan 2020 10:43:03 -0800 Subject: [PATCH 4/9] bpf: Add lookup and update batch ops to arraymap This adds the generic batch ops functionality to bpf arraymap, note that since deletion is not a valid operation for arraymap, only batch and lookup are added. Signed-off-by: Brian Vazquez Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20200115184308.162644-5-brianvv@google.com --- kernel/bpf/arraymap.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index f0d19bbb9211..95d77770353c 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -503,6 +503,8 @@ const struct bpf_map_ops array_map_ops = { .map_mmap = array_map_mmap, .map_seq_show_elem = array_map_seq_show_elem, .map_check_btf = array_map_check_btf, + .map_lookup_batch = generic_map_lookup_batch, + .map_update_batch = generic_map_update_batch, }; const struct bpf_map_ops percpu_array_map_ops = { From 057996380a42bb64ccc04383cfa9c0ace4ea11f0 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 15 Jan 2020 10:43:04 -0800 Subject: [PATCH 5/9] bpf: Add batch ops to all htab bpf map htab can't use generic batch support due some problematic behaviours inherent to the data structre, i.e. while iterating the bpf map a concurrent program might delete the next entry that batch was about to use, in that case there's no easy solution to retrieve the next entry, the issue has been discussed multiple times (see [1] and [2]). The only way hmap can be traversed without the problem previously exposed is by making sure that the map is traversing entire buckets. This commit implements those strict requirements for hmap, the implementation follows the same interaction that generic support with some exceptions: - If keys/values buffer are not big enough to traverse a bucket, ENOSPC will be returned. - out_batch contains the value of the next bucket in the iteration, not the next key, but this is transparent for the user since the user should never use out_batch for other than bpf batch syscalls. This commits implements BPF_MAP_LOOKUP_BATCH and adds support for new command BPF_MAP_LOOKUP_AND_DELETE_BATCH. Note that for update/delete batch ops it is possible to use the generic implementations. [1] https://lore.kernel.org/bpf/20190724165803.87470-1-brianvv@google.com/ [2] https://lore.kernel.org/bpf/20190906225434.3635421-1-yhs@fb.com/ Signed-off-by: Yonghong Song Signed-off-by: Brian Vazquez Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200115184308.162644-6-brianvv@google.com --- include/linux/bpf.h | 3 + include/uapi/linux/bpf.h | 1 + kernel/bpf/hashtab.c | 264 +++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 9 +- 4 files changed, 276 insertions(+), 1 deletion(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 05466ad6cf1c..3517e32149a4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -46,6 +46,9 @@ struct bpf_map_ops { void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); + int (*map_lookup_and_delete_batch)(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr); int (*map_update_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d5320b0be459..033d90a2282d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -108,6 +108,7 @@ enum bpf_cmd { BPF_MAP_FREEZE, BPF_BTF_GET_NEXT_ID, BPF_MAP_LOOKUP_BATCH, + BPF_MAP_LOOKUP_AND_DELETE_BATCH, BPF_MAP_UPDATE_BATCH, BPF_MAP_DELETE_BATCH, }; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 22066a62c8c9..2d182c4ee9d9 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -17,6 +17,16 @@ (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \ BPF_F_ACCESS_MASK | BPF_F_ZERO_SEED) +#define BATCH_OPS(_name) \ + .map_lookup_batch = \ + _name##_map_lookup_batch, \ + .map_lookup_and_delete_batch = \ + _name##_map_lookup_and_delete_batch, \ + .map_update_batch = \ + generic_map_update_batch, \ + .map_delete_batch = \ + generic_map_delete_batch + struct bucket { struct hlist_nulls_head head; raw_spinlock_t lock; @@ -1232,6 +1242,256 @@ static void htab_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } +static int +__htab_map_lookup_and_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr, + bool do_delete, bool is_lru_map, + bool is_percpu) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + u32 bucket_cnt, total, key_size, value_size, roundup_key_size; + void *keys = NULL, *values = NULL, *value, *dst_key, *dst_val; + void __user *uvalues = u64_to_user_ptr(attr->batch.values); + void __user *ukeys = u64_to_user_ptr(attr->batch.keys); + void *ubatch = u64_to_user_ptr(attr->batch.in_batch); + u32 batch, max_count, size, bucket_size; + u64 elem_map_flags, map_flags; + struct hlist_nulls_head *head; + struct hlist_nulls_node *n; + unsigned long flags; + struct htab_elem *l; + struct bucket *b; + int ret = 0; + + elem_map_flags = attr->batch.elem_flags; + if ((elem_map_flags & ~BPF_F_LOCK) || + ((elem_map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) + return -EINVAL; + + map_flags = attr->batch.flags; + if (map_flags) + return -EINVAL; + + max_count = attr->batch.count; + if (!max_count) + return 0; + + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + + batch = 0; + if (ubatch && copy_from_user(&batch, ubatch, sizeof(batch))) + return -EFAULT; + + if (batch >= htab->n_buckets) + return -ENOENT; + + key_size = htab->map.key_size; + roundup_key_size = round_up(htab->map.key_size, 8); + value_size = htab->map.value_size; + size = round_up(value_size, 8); + if (is_percpu) + value_size = size * num_possible_cpus(); + total = 0; + /* while experimenting with hash tables with sizes ranging from 10 to + * 1000, it was observed that a bucket can have upto 5 entries. + */ + bucket_size = 5; + +alloc: + /* We cannot do copy_from_user or copy_to_user inside + * the rcu_read_lock. Allocate enough space here. + */ + keys = kvmalloc(key_size * bucket_size, GFP_USER | __GFP_NOWARN); + values = kvmalloc(value_size * bucket_size, GFP_USER | __GFP_NOWARN); + if (!keys || !values) { + ret = -ENOMEM; + goto after_loop; + } + +again: + preempt_disable(); + this_cpu_inc(bpf_prog_active); + rcu_read_lock(); +again_nocopy: + dst_key = keys; + dst_val = values; + b = &htab->buckets[batch]; + head = &b->head; + raw_spin_lock_irqsave(&b->lock, flags); + + bucket_cnt = 0; + hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) + bucket_cnt++; + + if (bucket_cnt > (max_count - total)) { + if (total == 0) + ret = -ENOSPC; + raw_spin_unlock_irqrestore(&b->lock, flags); + rcu_read_unlock(); + this_cpu_dec(bpf_prog_active); + preempt_enable(); + goto after_loop; + } + + if (bucket_cnt > bucket_size) { + bucket_size = bucket_cnt; + raw_spin_unlock_irqrestore(&b->lock, flags); + rcu_read_unlock(); + this_cpu_dec(bpf_prog_active); + preempt_enable(); + kvfree(keys); + kvfree(values); + goto alloc; + } + + hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { + memcpy(dst_key, l->key, key_size); + + if (is_percpu) { + int off = 0, cpu; + void __percpu *pptr; + + pptr = htab_elem_get_ptr(l, map->key_size); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(dst_val + off, + per_cpu_ptr(pptr, cpu), size); + off += size; + } + } else { + value = l->key + roundup_key_size; + if (elem_map_flags & BPF_F_LOCK) + copy_map_value_locked(map, dst_val, value, + true); + else + copy_map_value(map, dst_val, value); + check_and_init_map_lock(map, dst_val); + } + if (do_delete) { + hlist_nulls_del_rcu(&l->hash_node); + if (is_lru_map) + bpf_lru_push_free(&htab->lru, &l->lru_node); + else + free_htab_elem(htab, l); + } + dst_key += key_size; + dst_val += value_size; + } + + raw_spin_unlock_irqrestore(&b->lock, flags); + /* If we are not copying data, we can go to next bucket and avoid + * unlocking the rcu. + */ + if (!bucket_cnt && (batch + 1 < htab->n_buckets)) { + batch++; + goto again_nocopy; + } + + rcu_read_unlock(); + this_cpu_dec(bpf_prog_active); + preempt_enable(); + if (bucket_cnt && (copy_to_user(ukeys + total * key_size, keys, + key_size * bucket_cnt) || + copy_to_user(uvalues + total * value_size, values, + value_size * bucket_cnt))) { + ret = -EFAULT; + goto after_loop; + } + + total += bucket_cnt; + batch++; + if (batch >= htab->n_buckets) { + ret = -ENOENT; + goto after_loop; + } + goto again; + +after_loop: + if (ret == -EFAULT) + goto out; + + /* copy # of entries and next batch */ + ubatch = u64_to_user_ptr(attr->batch.out_batch); + if (copy_to_user(ubatch, &batch, sizeof(batch)) || + put_user(total, &uattr->batch.count)) + ret = -EFAULT; + +out: + kvfree(keys); + kvfree(values); + return ret; +} + +static int +htab_percpu_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, false, + false, true); +} + +static int +htab_percpu_map_lookup_and_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, true, + false, true); +} + +static int +htab_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, false, + false, false); +} + +static int +htab_map_lookup_and_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, true, + false, false); +} + +static int +htab_lru_percpu_map_lookup_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, false, + true, true); +} + +static int +htab_lru_percpu_map_lookup_and_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, true, + true, true); +} + +static int +htab_lru_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, false, + true, false); +} + +static int +htab_lru_map_lookup_and_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, true, + true, false); +} + const struct bpf_map_ops htab_map_ops = { .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, @@ -1242,6 +1502,7 @@ const struct bpf_map_ops htab_map_ops = { .map_delete_elem = htab_map_delete_elem, .map_gen_lookup = htab_map_gen_lookup, .map_seq_show_elem = htab_map_seq_show_elem, + BATCH_OPS(htab), }; const struct bpf_map_ops htab_lru_map_ops = { @@ -1255,6 +1516,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_delete_elem = htab_lru_map_delete_elem, .map_gen_lookup = htab_lru_map_gen_lookup, .map_seq_show_elem = htab_map_seq_show_elem, + BATCH_OPS(htab_lru), }; /* Called from eBPF program */ @@ -1368,6 +1630,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { .map_update_elem = htab_percpu_map_update_elem, .map_delete_elem = htab_map_delete_elem, .map_seq_show_elem = htab_percpu_map_seq_show_elem, + BATCH_OPS(htab_percpu), }; const struct bpf_map_ops htab_lru_percpu_map_ops = { @@ -1379,6 +1642,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_update_elem = htab_lru_percpu_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, .map_seq_show_elem = htab_percpu_map_seq_show_elem, + BATCH_OPS(htab_lru_percpu), }; static int fd_htab_map_alloc_check(union bpf_attr *attr) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ce8244d1ba99..0d94d361379c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3310,7 +3310,8 @@ static int bpf_map_do_batch(const union bpf_attr *attr, if (IS_ERR(map)) return PTR_ERR(map); - if (cmd == BPF_MAP_LOOKUP_BATCH && + if ((cmd == BPF_MAP_LOOKUP_BATCH || + cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; @@ -3324,6 +3325,8 @@ static int bpf_map_do_batch(const union bpf_attr *attr, if (cmd == BPF_MAP_LOOKUP_BATCH) BPF_DO_BATCH(map->ops->map_lookup_batch); + else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) + BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch); else if (cmd == BPF_MAP_UPDATE_BATCH) BPF_DO_BATCH(map->ops->map_update_batch); else @@ -3434,6 +3437,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_MAP_LOOKUP_BATCH: err = bpf_map_do_batch(&attr, uattr, BPF_MAP_LOOKUP_BATCH); break; + case BPF_MAP_LOOKUP_AND_DELETE_BATCH: + err = bpf_map_do_batch(&attr, uattr, + BPF_MAP_LOOKUP_AND_DELETE_BATCH); + break; case BPF_MAP_UPDATE_BATCH: err = bpf_map_do_batch(&attr, uattr, BPF_MAP_UPDATE_BATCH); break; From a1e3a3b8ba2c381a043d0c4273837895c1d3cf9c Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 15 Jan 2020 10:43:05 -0800 Subject: [PATCH 6/9] tools/bpf: Sync uapi header bpf.h sync uapi header include/uapi/linux/bpf.h to tools/include/uapi/linux/bpf.h Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200115184308.162644-7-brianvv@google.com --- tools/include/uapi/linux/bpf.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a88837d4dd18..033d90a2282d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -107,6 +107,10 @@ enum bpf_cmd { BPF_MAP_LOOKUP_AND_DELETE_ELEM, BPF_MAP_FREEZE, BPF_BTF_GET_NEXT_ID, + BPF_MAP_LOOKUP_BATCH, + BPF_MAP_LOOKUP_AND_DELETE_BATCH, + BPF_MAP_UPDATE_BATCH, + BPF_MAP_DELETE_BATCH, }; enum bpf_map_type { @@ -420,6 +424,23 @@ union bpf_attr { __u64 flags; }; + struct { /* struct used by BPF_MAP_*_BATCH commands */ + __aligned_u64 in_batch; /* start batch, + * NULL to start from beginning + */ + __aligned_u64 out_batch; /* output: next start batch */ + __aligned_u64 keys; + __aligned_u64 values; + __u32 count; /* input/output: + * input: # of key/value + * elements + * output: # of filled elements + */ + __u32 map_fd; + __u64 elem_flags; + __u64 flags; + } batch; + struct { /* anonymous struct used by BPF_PROG_LOAD command */ __u32 prog_type; /* one of enum bpf_prog_type */ __u32 insn_cnt; From 2ab3d86ea1859d1a4b830ce3551cba725620593a Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 15 Jan 2020 10:43:06 -0800 Subject: [PATCH 7/9] libbpf: Add libbpf support to batch ops Added four libbpf API functions to support map batch operations: . int bpf_map_delete_batch( ... ) . int bpf_map_lookup_batch( ... ) . int bpf_map_lookup_and_delete_batch( ... ) . int bpf_map_update_batch( ... ) Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200115184308.162644-8-brianvv@google.com --- tools/lib/bpf/bpf.c | 58 ++++++++++++++++++++++++++++++++++++++++ tools/lib/bpf/bpf.h | 22 +++++++++++++++ tools/lib/bpf/libbpf.map | 4 +++ 3 files changed, 84 insertions(+) diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 500afe478e94..317727d61214 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -452,6 +452,64 @@ int bpf_map_freeze(int fd) return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr)); } +static int bpf_map_batch_common(int cmd, int fd, void *in_batch, + void *out_batch, void *keys, void *values, + __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + union bpf_attr attr = {}; + int ret; + + if (!OPTS_VALID(opts, bpf_map_batch_opts)) + return -EINVAL; + + memset(&attr, 0, sizeof(attr)); + attr.batch.map_fd = fd; + attr.batch.in_batch = ptr_to_u64(in_batch); + attr.batch.out_batch = ptr_to_u64(out_batch); + attr.batch.keys = ptr_to_u64(keys); + attr.batch.values = ptr_to_u64(values); + attr.batch.count = *count; + attr.batch.elem_flags = OPTS_GET(opts, elem_flags, 0); + attr.batch.flags = OPTS_GET(opts, flags, 0); + + ret = sys_bpf(cmd, &attr, sizeof(attr)); + *count = attr.batch.count; + + return ret; +} + +int bpf_map_delete_batch(int fd, void *keys, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_DELETE_BATCH, fd, NULL, + NULL, keys, NULL, count, opts); +} + +int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys, + void *values, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_LOOKUP_BATCH, fd, in_batch, + out_batch, keys, values, count, opts); +} + +int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch, + void *keys, void *values, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_LOOKUP_AND_DELETE_BATCH, + fd, in_batch, out_batch, keys, values, + count, opts); +} + +int bpf_map_update_batch(int fd, void *keys, void *values, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_UPDATE_BATCH, fd, NULL, NULL, + keys, values, count, opts); +} + int bpf_obj_pin(int fd, const char *pathname) { union bpf_attr attr; diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 56341d117e5b..b976e77316cc 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -127,6 +127,28 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key, LIBBPF_API int bpf_map_delete_elem(int fd, const void *key); LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key); LIBBPF_API int bpf_map_freeze(int fd); + +struct bpf_map_batch_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u64 elem_flags; + __u64 flags; +}; +#define bpf_map_batch_opts__last_field flags + +LIBBPF_API int bpf_map_delete_batch(int fd, void *keys, + __u32 *count, + const struct bpf_map_batch_opts *opts); +LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, + void *keys, void *values, __u32 *count, + const struct bpf_map_batch_opts *opts); +LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, + void *out_batch, void *keys, + void *values, __u32 *count, + const struct bpf_map_batch_opts *opts); +LIBBPF_API int bpf_map_update_batch(int fd, void *keys, void *values, + __u32 *count, + const struct bpf_map_batch_opts *opts); + LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); LIBBPF_API int bpf_obj_get(const char *pathname); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index a19f04e6e3d9..1902a0fc6afc 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -214,6 +214,10 @@ LIBBPF_0.0.7 { btf_dump__emit_type_decl; bpf_link__disconnect; bpf_map__attach_struct_ops; + bpf_map_delete_batch; + bpf_map_lookup_and_delete_batch; + bpf_map_lookup_batch; + bpf_map_update_batch; bpf_object__find_program_by_name; bpf_object__attach_skeleton; bpf_object__destroy_skeleton; From 30ff3c59137d00e083f68437665e00895cc271c7 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 15 Jan 2020 10:43:07 -0800 Subject: [PATCH 8/9] selftests/bpf: Add batch ops testing for htab and htab_percpu map Tested bpf_map_lookup_batch(), bpf_map_lookup_and_delete_batch(), bpf_map_update_batch(), and bpf_map_delete_batch() functionality. $ ./test_maps ... test_htab_map_batch_ops:PASS test_htab_percpu_map_batch_ops:PASS ... Signed-off-by: Yonghong Song Signed-off-by: Brian Vazquez Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200115184308.162644-9-brianvv@google.com --- .../bpf/map_tests/htab_map_batch_ops.c | 283 ++++++++++++++++++ 1 file changed, 283 insertions(+) create mode 100644 tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c diff --git a/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c new file mode 100644 index 000000000000..976bf415fbdd --- /dev/null +++ b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c @@ -0,0 +1,283 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include +#include +#include + +#include +#include + +#include +#include + +static void map_batch_update(int map_fd, __u32 max_entries, int *keys, + void *values, bool is_pcpu) +{ + typedef BPF_DECLARE_PERCPU(int, value); + value *v = NULL; + int i, j, err; + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + if (is_pcpu) + v = (value *)values; + + for (i = 0; i < max_entries; i++) { + keys[i] = i + 1; + if (is_pcpu) + for (j = 0; j < bpf_num_possible_cpus(); j++) + bpf_percpu(v[i], j) = i + 2 + j; + else + ((int *)values)[i] = i + 2; + } + + err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts); + CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno)); +} + +static void map_batch_verify(int *visited, __u32 max_entries, + int *keys, void *values, bool is_pcpu) +{ + typedef BPF_DECLARE_PERCPU(int, value); + value *v = NULL; + int i, j; + + if (is_pcpu) + v = (value *)values; + + memset(visited, 0, max_entries * sizeof(*visited)); + for (i = 0; i < max_entries; i++) { + + if (is_pcpu) { + for (j = 0; j < bpf_num_possible_cpus(); j++) { + CHECK(keys[i] + 1 + j != bpf_percpu(v[i], j), + "key/value checking", + "error: i %d j %d key %d value %d\n", + i, j, keys[i], bpf_percpu(v[i], j)); + } + } else { + CHECK(keys[i] + 1 != ((int *)values)[i], + "key/value checking", + "error: i %d key %d value %d\n", i, keys[i], + ((int *)values)[i]); + } + + visited[i] = 1; + + } + for (i = 0; i < max_entries; i++) { + CHECK(visited[i] != 1, "visited checking", + "error: keys array at index %d missing\n", i); + } +} + +void __test_map_lookup_and_delete_batch(bool is_pcpu) +{ + __u32 batch, count, total, total_success; + typedef BPF_DECLARE_PERCPU(int, value); + int map_fd, *keys, *visited, key; + const __u32 max_entries = 10; + value pcpu_values[max_entries]; + int err, step, value_size; + bool nospace_err; + void *values; + struct bpf_create_map_attr xattr = { + .name = "hash_map", + .map_type = is_pcpu ? BPF_MAP_TYPE_PERCPU_HASH : + BPF_MAP_TYPE_HASH, + .key_size = sizeof(int), + .value_size = sizeof(int), + }; + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + xattr.max_entries = max_entries; + map_fd = bpf_create_map_xattr(&xattr); + CHECK(map_fd == -1, + "bpf_create_map_xattr()", "error:%s\n", strerror(errno)); + + value_size = is_pcpu ? sizeof(value) : sizeof(int); + keys = malloc(max_entries * sizeof(int)); + if (is_pcpu) + values = pcpu_values; + else + values = malloc(max_entries * sizeof(int)); + visited = malloc(max_entries * sizeof(int)); + CHECK(!keys || !values || !visited, "malloc()", + "error:%s\n", strerror(errno)); + + /* test 1: lookup/delete an empty hash table, -ENOENT */ + count = max_entries; + err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys, + values, &count, &opts); + CHECK((err && errno != ENOENT), "empty map", + "error: %s\n", strerror(errno)); + + /* populate elements to the map */ + map_batch_update(map_fd, max_entries, keys, values, is_pcpu); + + /* test 2: lookup/delete with count = 0, success */ + count = 0; + err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys, + values, &count, &opts); + CHECK(err, "count = 0", "error: %s\n", strerror(errno)); + + /* test 3: lookup/delete with count = max_entries, success */ + memset(keys, 0, max_entries * sizeof(*keys)); + memset(values, 0, max_entries * value_size); + count = max_entries; + err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys, + values, &count, &opts); + CHECK((err && errno != ENOENT), "count = max_entries", + "error: %s\n", strerror(errno)); + CHECK(count != max_entries, "count = max_entries", + "count = %u, max_entries = %u\n", count, max_entries); + map_batch_verify(visited, max_entries, keys, values, is_pcpu); + + /* bpf_map_get_next_key() should return -ENOENT for an empty map. */ + err = bpf_map_get_next_key(map_fd, NULL, &key); + CHECK(!err, "bpf_map_get_next_key()", "error: %s\n", strerror(errno)); + + /* test 4: lookup/delete in a loop with various steps. */ + total_success = 0; + for (step = 1; step < max_entries; step++) { + map_batch_update(map_fd, max_entries, keys, values, is_pcpu); + memset(keys, 0, max_entries * sizeof(*keys)); + memset(values, 0, max_entries * value_size); + total = 0; + /* iteratively lookup/delete elements with 'step' + * elements each + */ + count = step; + nospace_err = false; + while (true) { + err = bpf_map_lookup_batch(map_fd, + total ? &batch : NULL, + &batch, keys + total, + values + + total * value_size, + &count, &opts); + /* It is possible that we are failing due to buffer size + * not big enough. In such cases, let us just exit and + * go with large steps. Not that a buffer size with + * max_entries should always work. + */ + if (err && errno == ENOSPC) { + nospace_err = true; + break; + } + + CHECK((err && errno != ENOENT), "lookup with steps", + "error: %s\n", strerror(errno)); + + total += count; + if (err) + break; + + } + if (nospace_err == true) + continue; + + CHECK(total != max_entries, "lookup with steps", + "total = %u, max_entries = %u\n", total, max_entries); + map_batch_verify(visited, max_entries, keys, values, is_pcpu); + + total = 0; + count = step; + while (total < max_entries) { + if (max_entries - total < step) + count = max_entries - total; + err = bpf_map_delete_batch(map_fd, + keys + total, + &count, &opts); + CHECK((err && errno != ENOENT), "delete batch", + "error: %s\n", strerror(errno)); + total += count; + if (err) + break; + } + CHECK(total != max_entries, "delete with steps", + "total = %u, max_entries = %u\n", total, max_entries); + + /* check map is empty, errono == ENOENT */ + err = bpf_map_get_next_key(map_fd, NULL, &key); + CHECK(!err || errno != ENOENT, "bpf_map_get_next_key()", + "error: %s\n", strerror(errno)); + + /* iteratively lookup/delete elements with 'step' + * elements each + */ + map_batch_update(map_fd, max_entries, keys, values, is_pcpu); + memset(keys, 0, max_entries * sizeof(*keys)); + memset(values, 0, max_entries * value_size); + total = 0; + count = step; + nospace_err = false; + while (true) { + err = bpf_map_lookup_and_delete_batch(map_fd, + total ? &batch : NULL, + &batch, keys + total, + values + + total * value_size, + &count, &opts); + /* It is possible that we are failing due to buffer size + * not big enough. In such cases, let us just exit and + * go with large steps. Not that a buffer size with + * max_entries should always work. + */ + if (err && errno == ENOSPC) { + nospace_err = true; + break; + } + + CHECK((err && errno != ENOENT), "lookup with steps", + "error: %s\n", strerror(errno)); + + total += count; + if (err) + break; + } + + if (nospace_err == true) + continue; + + CHECK(total != max_entries, "lookup/delete with steps", + "total = %u, max_entries = %u\n", total, max_entries); + + map_batch_verify(visited, max_entries, keys, values, is_pcpu); + err = bpf_map_get_next_key(map_fd, NULL, &key); + CHECK(!err, "bpf_map_get_next_key()", "error: %s\n", + strerror(errno)); + + total_success++; + } + + CHECK(total_success == 0, "check total_success", + "unexpected failure\n"); + free(keys); + free(visited); + if (!is_pcpu) + free(values); +} + +void htab_map_batch_ops(void) +{ + __test_map_lookup_and_delete_batch(false); + printf("test_%s:PASS\n", __func__); +} + +void htab_percpu_map_batch_ops(void) +{ + __test_map_lookup_and_delete_batch(true); + printf("test_%s:PASS\n", __func__); +} + +void test_htab_map_batch_ops(void) +{ + htab_map_batch_ops(); + htab_percpu_map_batch_ops(); +} From f0fac2cec2861abc6fc0c094fb2584d9a33f868d Mon Sep 17 00:00:00 2001 From: Brian Vazquez Date: Wed, 15 Jan 2020 10:43:08 -0800 Subject: [PATCH 9/9] selftests/bpf: Add batch ops testing to array bpf map Tested bpf_map_lookup_batch() and bpf_map_update_batch() functionality. $ ./test_maps ... test_array_map_batch_ops:PASS ... Signed-off-by: Brian Vazquez Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200115184308.162644-10-brianvv@google.com --- .../bpf/map_tests/array_map_batch_ops.c | 129 ++++++++++++++++++ 1 file changed, 129 insertions(+) create mode 100644 tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c diff --git a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c new file mode 100644 index 000000000000..f0a64d8ac59a --- /dev/null +++ b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c @@ -0,0 +1,129 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include + +#include +#include + +#include + +static void map_batch_update(int map_fd, __u32 max_entries, int *keys, + int *values) +{ + int i, err; + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + for (i = 0; i < max_entries; i++) { + keys[i] = i; + values[i] = i + 1; + } + + err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts); + CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno)); +} + +static void map_batch_verify(int *visited, __u32 max_entries, + int *keys, int *values) +{ + int i; + + memset(visited, 0, max_entries * sizeof(*visited)); + for (i = 0; i < max_entries; i++) { + CHECK(keys[i] + 1 != values[i], "key/value checking", + "error: i %d key %d value %d\n", i, keys[i], values[i]); + visited[i] = 1; + } + for (i = 0; i < max_entries; i++) { + CHECK(visited[i] != 1, "visited checking", + "error: keys array at index %d missing\n", i); + } +} + +void test_array_map_batch_ops(void) +{ + struct bpf_create_map_attr xattr = { + .name = "array_map", + .map_type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + }; + int map_fd, *keys, *values, *visited; + __u32 count, total, total_success; + const __u32 max_entries = 10; + bool nospace_err; + __u64 batch = 0; + int err, step; + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + xattr.max_entries = max_entries; + map_fd = bpf_create_map_xattr(&xattr); + CHECK(map_fd == -1, + "bpf_create_map_xattr()", "error:%s\n", strerror(errno)); + + keys = malloc(max_entries * sizeof(int)); + values = malloc(max_entries * sizeof(int)); + visited = malloc(max_entries * sizeof(int)); + CHECK(!keys || !values || !visited, "malloc()", "error:%s\n", + strerror(errno)); + + /* populate elements to the map */ + map_batch_update(map_fd, max_entries, keys, values); + + /* test 1: lookup in a loop with various steps. */ + total_success = 0; + for (step = 1; step < max_entries; step++) { + map_batch_update(map_fd, max_entries, keys, values); + map_batch_verify(visited, max_entries, keys, values); + memset(keys, 0, max_entries * sizeof(*keys)); + memset(values, 0, max_entries * sizeof(*values)); + batch = 0; + total = 0; + /* iteratively lookup/delete elements with 'step' + * elements each. + */ + count = step; + nospace_err = false; + while (true) { + err = bpf_map_lookup_batch(map_fd, + total ? &batch : NULL, &batch, + keys + total, + values + total, + &count, &opts); + + CHECK((err && errno != ENOENT), "lookup with steps", + "error: %s\n", strerror(errno)); + + total += count; + if (err) + break; + + } + + if (nospace_err == true) + continue; + + CHECK(total != max_entries, "lookup with steps", + "total = %u, max_entries = %u\n", total, max_entries); + + map_batch_verify(visited, max_entries, keys, values); + + total_success++; + } + + CHECK(total_success == 0, "check total_success", + "unexpected failure\n"); + + printf("%s:PASS\n", __func__); + + free(keys); + free(values); + free(visited); +}