diff options
author | David S. Miller <davem@davemloft.net> | 2019-06-01 06:21:18 +0200 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2019-06-01 06:21:18 +0200 |
commit | 0462eaacee493f7e2d87551a35d38be93ca723f8 (patch) | |
tree | c2d454ff64156281c9b4ce071194cb9a47e5dd1a /kernel | |
parent | Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirshe... (diff) | |
parent | selftests/bpf: measure RTT from xdp using xdping (diff) | |
download | linux-0462eaacee493f7e2d87551a35d38be93ca723f8.tar.xz linux-0462eaacee493f7e2d87551a35d38be93ca723f8.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says:
====================
pull-request: bpf-next 2019-05-31
The following pull-request contains BPF updates for your *net-next* tree.
Lots of exciting new features in the first PR of this developement cycle!
The main changes are:
1) misc verifier improvements, from Alexei.
2) bpftool can now convert btf to valid C, from Andrii.
3) verifier can insert explicit ZEXT insn when requested by 32-bit JITs.
This feature greatly improves BPF speed on 32-bit architectures. From Jiong.
4) cgroups will now auto-detach bpf programs. This fixes issue of thousands
bpf programs got stuck in dying cgroups. From Roman.
5) new bpf_send_signal() helper, from Yonghong.
6) cgroup inet skb programs can signal CN to the stack, from Lawrence.
7) miscellaneous cleanups, from many developers.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/arraymap.c | 18 | ||||
-rw-r--r-- | kernel/bpf/cgroup.c | 94 | ||||
-rw-r--r-- | kernel/bpf/core.c | 46 | ||||
-rw-r--r-- | kernel/bpf/cpumap.c | 9 | ||||
-rw-r--r-- | kernel/bpf/devmap.c | 14 | ||||
-rw-r--r-- | kernel/bpf/hashtab.c | 14 | ||||
-rw-r--r-- | kernel/bpf/local_storage.c | 13 | ||||
-rw-r--r-- | kernel/bpf/lpm_trie.c | 8 | ||||
-rw-r--r-- | kernel/bpf/queue_stack_maps.c | 13 | ||||
-rw-r--r-- | kernel/bpf/reuseport_array.c | 17 | ||||
-rw-r--r-- | kernel/bpf/stackmap.c | 28 | ||||
-rw-r--r-- | kernel/bpf/syscall.c | 103 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 397 | ||||
-rw-r--r-- | kernel/bpf/xskmap.c | 10 | ||||
-rw-r--r-- | kernel/cgroup/cgroup.c | 11 | ||||
-rw-r--r-- | kernel/trace/bpf_trace.c | 96 |
16 files changed, 661 insertions, 230 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 584636c9e2eb..0349cbf23cdb 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -83,6 +83,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) u32 elem_size, index_mask, max_entries; bool unpriv = !capable(CAP_SYS_ADMIN); u64 cost, array_size, mask64; + struct bpf_map_memory mem; struct bpf_array *array; elem_size = round_up(attr->value_size, 8); @@ -116,32 +117,29 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) /* make sure there is no u32 overflow later in round_up() */ cost = array_size; - if (cost >= U32_MAX - PAGE_SIZE) - return ERR_PTR(-ENOMEM); - if (percpu) { + if (percpu) cost += (u64)attr->max_entries * elem_size * num_possible_cpus(); - if (cost >= U32_MAX - PAGE_SIZE) - return ERR_PTR(-ENOMEM); - } - cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; - ret = bpf_map_precharge_memlock(cost); + ret = bpf_map_charge_init(&mem, cost); if (ret < 0) return ERR_PTR(ret); /* allocate all map elements and zero-initialize them */ array = bpf_map_area_alloc(array_size, numa_node); - if (!array) + if (!array) { + bpf_map_charge_finish(&mem); return ERR_PTR(-ENOMEM); + } array->index_mask = index_mask; array->map.unpriv_array = unpriv; /* copy mandatory map attributes */ bpf_map_init_from_attr(&array->map, attr); - array->map.pages = cost; + bpf_map_charge_move(&array->map.memory, &mem); array->elem_size = elem_size; if (percpu && bpf_array_alloc_percpu(array)) { + bpf_map_charge_finish(&array->map.memory); bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index fcde0f7b2585..1b65ab0df457 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -22,13 +22,23 @@ DEFINE_STATIC_KEY_FALSE(cgroup_bpf_enabled_key); EXPORT_SYMBOL(cgroup_bpf_enabled_key); +void cgroup_bpf_offline(struct cgroup *cgrp) +{ + cgroup_get(cgrp); + percpu_ref_kill(&cgrp->bpf.refcnt); +} + /** - * cgroup_bpf_put() - put references of all bpf programs - * @cgrp: the cgroup to modify + * cgroup_bpf_release() - put references of all bpf programs and + * release all cgroup bpf data + * @work: work structure embedded into the cgroup to modify */ -void cgroup_bpf_put(struct cgroup *cgrp) +static void cgroup_bpf_release(struct work_struct *work) { + struct cgroup *cgrp = container_of(work, struct cgroup, + bpf.release_work); enum bpf_cgroup_storage_type stype; + struct bpf_prog_array *old_array; unsigned int type; for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) { @@ -45,8 +55,27 @@ void cgroup_bpf_put(struct cgroup *cgrp) kfree(pl); static_branch_dec(&cgroup_bpf_enabled_key); } - bpf_prog_array_free(cgrp->bpf.effective[type]); + old_array = rcu_dereference_protected( + cgrp->bpf.effective[type], + percpu_ref_is_dying(&cgrp->bpf.refcnt)); + bpf_prog_array_free(old_array); } + + percpu_ref_exit(&cgrp->bpf.refcnt); + cgroup_put(cgrp); +} + +/** + * cgroup_bpf_release_fn() - callback used to schedule releasing + * of bpf cgroup data + * @ref: percpu ref counter structure + */ +static void cgroup_bpf_release_fn(struct percpu_ref *ref) +{ + struct cgroup *cgrp = container_of(ref, struct cgroup, bpf.refcnt); + + INIT_WORK(&cgrp->bpf.release_work, cgroup_bpf_release); + queue_work(system_wq, &cgrp->bpf.release_work); } /* count number of elements in the list. @@ -101,7 +130,7 @@ static bool hierarchy_allows_attach(struct cgroup *cgrp, */ static int compute_effective_progs(struct cgroup *cgrp, enum bpf_attach_type type, - struct bpf_prog_array __rcu **array) + struct bpf_prog_array **array) { enum bpf_cgroup_storage_type stype; struct bpf_prog_array *progs; @@ -139,17 +168,16 @@ static int compute_effective_progs(struct cgroup *cgrp, } } while ((p = cgroup_parent(p))); - rcu_assign_pointer(*array, progs); + *array = progs; return 0; } static void activate_effective_progs(struct cgroup *cgrp, enum bpf_attach_type type, - struct bpf_prog_array __rcu *array) + struct bpf_prog_array *old_array) { - struct bpf_prog_array __rcu *old_array; - - old_array = xchg(&cgrp->bpf.effective[type], array); + rcu_swap_protected(cgrp->bpf.effective[type], old_array, + lockdep_is_held(&cgroup_mutex)); /* free prog array after grace period, since __cgroup_bpf_run_*() * might be still walking the array */ @@ -166,8 +194,13 @@ int cgroup_bpf_inherit(struct cgroup *cgrp) * that array below is variable length */ #define NR ARRAY_SIZE(cgrp->bpf.effective) - struct bpf_prog_array __rcu *arrays[NR] = {}; - int i; + struct bpf_prog_array *arrays[NR] = {}; + int ret, i; + + ret = percpu_ref_init(&cgrp->bpf.refcnt, cgroup_bpf_release_fn, 0, + GFP_KERNEL); + if (ret) + return ret; for (i = 0; i < NR; i++) INIT_LIST_HEAD(&cgrp->bpf.progs[i]); @@ -183,6 +216,9 @@ int cgroup_bpf_inherit(struct cgroup *cgrp) cleanup: for (i = 0; i < NR; i++) bpf_prog_array_free(arrays[i]); + + percpu_ref_exit(&cgrp->bpf.refcnt); + return -ENOMEM; } @@ -444,10 +480,14 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, enum bpf_attach_type type = attr->query.attach_type; struct list_head *progs = &cgrp->bpf.progs[type]; u32 flags = cgrp->bpf.flags[type]; + struct bpf_prog_array *effective; int cnt, ret = 0, i; + effective = rcu_dereference_protected(cgrp->bpf.effective[type], + lockdep_is_held(&cgroup_mutex)); + if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) - cnt = bpf_prog_array_length(cgrp->bpf.effective[type]); + cnt = bpf_prog_array_length(effective); else cnt = prog_list_length(progs); @@ -464,8 +504,7 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, } if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) { - return bpf_prog_array_copy_to_user(cgrp->bpf.effective[type], - prog_ids, cnt); + return bpf_prog_array_copy_to_user(effective, prog_ids, cnt); } else { struct bpf_prog_list *pl; u32 id; @@ -548,8 +587,16 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, * The program type passed in via @type must be suitable for network * filtering. No further check is performed to assert that. * - * This function will return %-EPERM if any if an attached program was found - * and if it returned != 1 during execution. In all other cases, 0 is returned. + * For egress packets, this function can return: + * NET_XMIT_SUCCESS (0) - continue with packet output + * NET_XMIT_DROP (1) - drop packet and notify TCP to call cwr + * NET_XMIT_CN (2) - continue with packet output and notify TCP + * to call cwr + * -EPERM - drop packet + * + * For ingress packets, this function will return -EPERM if any + * attached program was found and if it returned != 1 during execution. + * Otherwise 0 is returned. */ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, @@ -575,12 +622,19 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, /* compute pointers for the bpf prog */ bpf_compute_and_save_data_end(skb, &saved_data_end); - ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb, - __bpf_prog_run_save_cb); + if (type == BPF_CGROUP_INET_EGRESS) { + ret = BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY( + cgrp->bpf.effective[type], skb, __bpf_prog_run_save_cb); + } else { + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb, + __bpf_prog_run_save_cb); + ret = (ret == 1 ? 0 : -EPERM); + } bpf_restore_data_end(skb, saved_data_end); __skb_pull(skb, offset); skb->sk = save_sk; - return ret == 1 ? 0 : -EPERM; + + return ret; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 242a643af82f..33fb292f2e30 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1795,38 +1795,33 @@ struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) return &empty_prog_array.hdr; } -void bpf_prog_array_free(struct bpf_prog_array __rcu *progs) +void bpf_prog_array_free(struct bpf_prog_array *progs) { - if (!progs || - progs == (struct bpf_prog_array __rcu *)&empty_prog_array.hdr) + if (!progs || progs == &empty_prog_array.hdr) return; kfree_rcu(progs, rcu); } -int bpf_prog_array_length(struct bpf_prog_array __rcu *array) +int bpf_prog_array_length(struct bpf_prog_array *array) { struct bpf_prog_array_item *item; u32 cnt = 0; - rcu_read_lock(); - item = rcu_dereference(array)->items; - for (; item->prog; item++) + for (item = array->items; item->prog; item++) if (item->prog != &dummy_bpf_prog.prog) cnt++; - rcu_read_unlock(); return cnt; } -static bool bpf_prog_array_copy_core(struct bpf_prog_array __rcu *array, +static bool bpf_prog_array_copy_core(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt) { struct bpf_prog_array_item *item; int i = 0; - item = rcu_dereference_check(array, 1)->items; - for (; item->prog; item++) { + for (item = array->items; item->prog; item++) { if (item->prog == &dummy_bpf_prog.prog) continue; prog_ids[i] = item->prog->aux->id; @@ -1839,7 +1834,7 @@ static bool bpf_prog_array_copy_core(struct bpf_prog_array __rcu *array, return !!(item->prog); } -int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *array, +int bpf_prog_array_copy_to_user(struct bpf_prog_array *array, __u32 __user *prog_ids, u32 cnt) { unsigned long err = 0; @@ -1850,18 +1845,12 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *array, * cnt = bpf_prog_array_length(); * if (cnt > 0) * bpf_prog_array_copy_to_user(..., cnt); - * so below kcalloc doesn't need extra cnt > 0 check, but - * bpf_prog_array_length() releases rcu lock and - * prog array could have been swapped with empty or larger array, - * so always copy 'cnt' prog_ids to the user. - * In a rare race the user will see zero prog_ids + * so below kcalloc doesn't need extra cnt > 0 check. */ ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN); if (!ids) return -ENOMEM; - rcu_read_lock(); nospc = bpf_prog_array_copy_core(array, ids, cnt); - rcu_read_unlock(); err = copy_to_user(prog_ids, ids, cnt * sizeof(u32)); kfree(ids); if (err) @@ -1871,19 +1860,19 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *array, return 0; } -void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *array, +void bpf_prog_array_delete_safe(struct bpf_prog_array *array, struct bpf_prog *old_prog) { - struct bpf_prog_array_item *item = array->items; + struct bpf_prog_array_item *item; - for (; item->prog; item++) + for (item = array->items; item->prog; item++) if (item->prog == old_prog) { WRITE_ONCE(item->prog, &dummy_bpf_prog.prog); break; } } -int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, +int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, struct bpf_prog_array **new_array) @@ -1947,7 +1936,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, return 0; } -int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array, +int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt) { @@ -2090,6 +2079,15 @@ bool __weak bpf_helper_changes_pkt_data(void *func) return false; } +/* Return TRUE if the JIT backend wants verifier to enable sub-register usage + * analysis code and wants explicit zero extension inserted by verifier. + * Otherwise, return FALSE. + */ +bool __weak bpf_jit_needs_zext(void) +{ + return false; +} + /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. */ diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index cf727d77c6c6..b31a71909307 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -106,12 +106,9 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) /* make sure page count doesn't overflow */ cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *); cost += cpu_map_bitmap_size(attr) * num_possible_cpus(); - if (cost >= U32_MAX - PAGE_SIZE) - goto free_cmap; - cmap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; /* Notice returns -EPERM on if map size is larger than memlock limit */ - ret = bpf_map_precharge_memlock(cmap->map.pages); + ret = bpf_map_charge_init(&cmap->map.memory, cost); if (ret) { err = ret; goto free_cmap; @@ -121,7 +118,7 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) cmap->flush_needed = __alloc_percpu(cpu_map_bitmap_size(attr), __alignof__(unsigned long)); if (!cmap->flush_needed) - goto free_cmap; + goto free_charge; /* Alloc array for possible remote "destination" CPUs */ cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries * @@ -133,6 +130,8 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) return &cmap->map; free_percpu: free_percpu(cmap->flush_needed); +free_charge: + bpf_map_charge_finish(&cmap->map.memory); free_cmap: kfree(cmap); return ERR_PTR(err); diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 1e525d70f833..5ae7cce5ef16 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -108,13 +108,9 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) /* make sure page count doesn't overflow */ cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); cost += dev_map_bitmap_size(attr) * num_possible_cpus(); - if (cost >= U32_MAX - PAGE_SIZE) - goto free_dtab; - - dtab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; - /* if map size is larger than memlock limit, reject it early */ - err = bpf_map_precharge_memlock(dtab->map.pages); + /* if map size is larger than memlock limit, reject it */ + err = bpf_map_charge_init(&dtab->map.memory, cost); if (err) goto free_dtab; @@ -125,19 +121,21 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) __alignof__(unsigned long), GFP_KERNEL | __GFP_NOWARN); if (!dtab->flush_needed) - goto free_dtab; + goto free_charge; dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *), dtab->map.numa_node); if (!dtab->netdev_map) - goto free_dtab; + goto free_charge; spin_lock(&dev_map_lock); list_add_tail_rcu(&dtab->list, &dev_map_list); spin_unlock(&dev_map_lock); return &dtab->map; +free_charge: + bpf_map_charge_finish(&dtab->map.memory); free_dtab: free_percpu(dtab->flush_needed); kfree(dtab); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 0f2708fde5f7..d92e05d9979b 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -360,14 +360,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) else cost += (u64) htab->elem_size * num_possible_cpus(); - if (cost >= U32_MAX - PAGE_SIZE) - /* make sure page count doesn't overflow */ - goto free_htab; - - htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; - - /* if map size is larger than memlock limit, reject it early */ - err = bpf_map_precharge_memlock(htab->map.pages); + /* if map size is larger than memlock limit, reject it */ + err = bpf_map_charge_init(&htab->map.memory, cost); if (err) goto free_htab; @@ -376,7 +370,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) sizeof(struct bucket), htab->map.numa_node); if (!htab->buckets) - goto free_htab; + goto free_charge; if (htab->map.map_flags & BPF_F_ZERO_SEED) htab->hashrnd = 0; @@ -409,6 +403,8 @@ free_prealloc: prealloc_destroy(htab); free_buckets: bpf_map_area_free(htab->buckets); +free_charge: + bpf_map_charge_finish(&htab->map.memory); free_htab: kfree(htab); return ERR_PTR(err); diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 980e8f1f6cb5..addd6fdceec8 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -272,6 +272,8 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); struct bpf_cgroup_storage_map *map; + struct bpf_map_memory mem; + int ret; if (attr->key_size != sizeof(struct bpf_cgroup_storage_key)) return ERR_PTR(-EINVAL); @@ -290,13 +292,18 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) /* max_entries is not used and enforced to be 0 */ return ERR_PTR(-EINVAL); + ret = bpf_map_charge_init(&mem, sizeof(struct bpf_cgroup_storage_map)); + if (ret < 0) + return ERR_PTR(ret); + map = kmalloc_node(sizeof(struct bpf_cgroup_storage_map), __GFP_ZERO | GFP_USER, numa_node); - if (!map) + if (!map) { + bpf_map_charge_finish(&mem); return ERR_PTR(-ENOMEM); + } - map->map.pages = round_up(sizeof(struct bpf_cgroup_storage_map), - PAGE_SIZE) >> PAGE_SHIFT; + bpf_map_charge_move(&map->map.memory, &mem); /* copy mandatory map attributes */ bpf_map_init_from_attr(&map->map, attr); diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index e61630c2e50b..09334f13a8a0 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -573,14 +573,8 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) cost_per_node = sizeof(struct lpm_trie_node) + attr->value_size + trie->data_size; cost += (u64) attr->max_entries * cost_per_node; - if (cost >= U32_MAX - PAGE_SIZE) { - ret = -E2BIG; - goto out_err; - } - - trie->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; - ret = bpf_map_precharge_memlock(trie->map.pages); + ret = bpf_map_charge_init(&trie->map.memory, cost); if (ret) goto out_err; diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 0b140d236889..f697647ceb54 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -67,29 +67,28 @@ static int queue_stack_map_alloc_check(union bpf_attr *attr) static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr) { int ret, numa_node = bpf_map_attr_numa_node(attr); + struct bpf_map_memory mem = {0}; struct bpf_queue_stack *qs; u64 size, queue_size, cost; size = (u64) attr->max_entries + 1; cost = queue_size = sizeof(*qs) + size * attr->value_size; - if (cost >= U32_MAX - PAGE_SIZE) - return ERR_PTR(-E2BIG); - cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; - - ret = bpf_map_precharge_memlock(cost); + ret = bpf_map_charge_init(&mem, cost); if (ret < 0) return ERR_PTR(ret); qs = bpf_map_area_alloc(queue_size, numa_node); - if (!qs) + if (!qs) { + bpf_map_charge_finish(&mem); return ERR_PTR(-ENOMEM); + } memset(qs, 0, sizeof(*qs)); bpf_map_init_from_attr(&qs->map, attr); - qs->map.pages = cost; + bpf_map_charge_move(&qs->map.memory, &mem); qs->size = size; raw_spin_lock_init(&qs->lock); diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index 18e225de80ff..50c083ba978c 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -151,7 +151,8 @@ static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr) { int err, numa_node = bpf_map_attr_numa_node(attr); struct reuseport_array *array; - u64 cost, array_size; + struct bpf_map_memory mem; + u64 array_size; if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); @@ -159,24 +160,20 @@ static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr) array_size = sizeof(*array); array_size += (u64)attr->max_entries * sizeof(struct sock *); - /* make sure there is no u32 overflow later in round_up() */ - cost = array_size; - if (cost >= U32_MAX - PAGE_SIZE) - return ERR_PTR(-ENOMEM); - cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; - - err = bpf_map_precharge_memlock(cost); + err = bpf_map_charge_init(&mem, array_size); if (err) return ERR_PTR(err); /* allocate all map elements and zero-initialize them */ array = bpf_map_area_alloc(array_size, numa_node); - if (!array) + if (!array) { + bpf_map_charge_finish(&mem); return ERR_PTR(-ENOMEM); + } /* copy mandatory map attributes */ bpf_map_init_from_attr(&array->map, attr); - array->map.pages = cost; + bpf_map_charge_move(&array->map.memory, &mem); return &array->map; } diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 950ab2f28922..3d86072d8e32 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -89,6 +89,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) { u32 value_size = attr->value_size; struct bpf_stack_map *smap; + struct bpf_map_memory mem; u64 cost, n_buckets; int err; @@ -116,40 +117,37 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) n_buckets = roundup_pow_of_two(attr->max_entries); cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); - if (cost >= U32_MAX - PAGE_SIZE) - return ERR_PTR(-E2BIG); + cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); + err = bpf_map_charge_init(&mem, cost); + if (err) + return ERR_PTR(err); smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr)); - if (!smap) + if (!smap) { + bpf_map_charge_finish(&mem); return ERR_PTR(-ENOMEM); - - err = -E2BIG; - cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); - if (cost >= U32_MAX - PAGE_SIZE) - goto free_smap; + } bpf_map_init_from_attr(&smap->map, attr); smap->map.value_size = value_size; smap->n_buckets = n_buckets; - smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; - - err = bpf_map_precharge_memlock(smap->map.pages); - if (err) - goto free_smap; err = get_callchain_buffers(sysctl_perf_event_max_stack); if (err) - goto free_smap; + goto free_charge; err = prealloc_elems_and_freelist(smap); if (err) goto put_buffers; + bpf_map_charge_move(&smap->map.memory, &mem); + return &smap->map; put_buffers: put_callchain_buffers(); -free_smap: +free_charge: + bpf_map_charge_finish(&mem); bpf_map_area_free(smap); return ERR_PTR(err); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index cb5440b02e82..4c53cbd3329d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -188,19 +188,6 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) map->numa_node = bpf_map_attr_numa_node(attr); } -int bpf_map_precharge_memlock(u32 pages) -{ - struct user_struct *user = get_current_user(); - unsigned long memlock_limit, cur; - - memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - cur = atomic_long_read(&user->locked_vm); - free_uid(user); - if (cur + pages > memlock_limit) - return -EPERM; - return 0; -} - static int bpf_charge_memlock(struct user_struct *user, u32 pages) { unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; @@ -214,45 +201,62 @@ static int bpf_charge_memlock(struct user_struct *user, u32 pages) static void bpf_uncharge_memlock(struct user_struct *user, u32 pages) { - atomic_long_sub(pages, &user->locked_vm); + if (user) + atomic_long_sub(pages, &user->locked_vm); } -static int bpf_map_init_memlock(struct bpf_map *map) +int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size) { - struct user_struct *user = get_current_user(); + u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT; + struct user_struct *user; int ret; - ret = bpf_charge_memlock(user, map->pages); + if (size >= U32_MAX - PAGE_SIZE) + return -E2BIG; + + user = get_current_user(); + ret = bpf_charge_memlock(user, pages); if (ret) { free_uid(user); return ret; } - map->user = user; - return ret; + + mem->pages = pages; + mem->user = user; + + return 0; } -static void bpf_map_release_memlock(struct bpf_map *map) +void bpf_map_charge_finish(struct bpf_map_memory *mem) { - struct user_struct *user = map->user; - bpf_uncharge_memlock(user, map->pages); - free_uid(user); + bpf_uncharge_memlock(mem->user, mem->pages); + free_uid(mem->user); +} + +void bpf_map_charge_move(struct bpf_map_memory *dst, + struct bpf_map_memory *src) +{ + *dst = *src; + + /* Make sure src will not be used for the redundant uncharging. */ + memset(src, 0, sizeof(struct bpf_map_memory)); } int bpf_map_charge_memlock(struct bpf_map *map, u32 pages) { int ret; - ret = bpf_charge_memlock(map->user, pages); + ret = bpf_charge_memlock(map->memory.user, pages); if (ret) return ret; - map->pages += pages; + map->memory.pages += pages; return ret; } void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages) { - bpf_uncharge_memlock(map->user, pages); - map->pages -= pages; + bpf_uncharge_memlock(map->memory.user, pages); + map->memory.pages -= pages; } static int bpf_map_alloc_id(struct bpf_map *map) @@ -303,11 +307,13 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); + struct bpf_map_memory mem; - bpf_map_release_memlock(map); + bpf_map_charge_move(&mem, &map->memory); security_bpf_map_free(map); /* implementation dependent freeing */ map->ops->map_free(map); + bpf_map_charge_finish(&mem); } static void bpf_map_put_uref(struct bpf_map *map) @@ -395,7 +401,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->value_size, map->max_entries, map->map_flags, - map->pages * 1ULL << PAGE_SHIFT, + map->memory.pages * 1ULL << PAGE_SHIFT, map->id, READ_ONCE(map->frozen)); @@ -549,6 +555,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, static int map_create(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); + struct bpf_map_memory mem; struct bpf_map *map; int f_flags; int err; @@ -573,7 +580,7 @@ static int map_create(union bpf_attr *attr) err = bpf_obj_name_cpy(map->name, attr->map_name); if (err) - goto free_map_nouncharge; + goto free_map; atomic_set(&map->refcnt, 1); atomic_set(&map->usercnt, 1); @@ -583,20 +590,20 @@ static int map_create(union bpf_attr *attr) if (!attr->btf_value_type_id) { err = -EINVAL; - goto free_map_nouncharge; + goto free_map; } btf = btf_get_by_fd(attr->btf_fd); if (IS_ERR(btf)) { err = PTR_ERR(btf); - goto free_map_nouncharge; + goto free_map; } err = map_check_btf(map, btf, attr->btf_key_type_id, attr->btf_value_type_id); if (err) { btf_put(btf); - goto free_map_nouncharge; + goto free_map; } map->btf = btf; @@ -608,15 +615,11 @@ static int map_create(union bpf_attr *attr) err = security_bpf_map_alloc(map); if (err) - goto free_map_nouncharge; - - err = bpf_map_init_memlock(map); - if (err) - goto free_map_sec; + goto free_map; err = bpf_map_alloc_id(map); if (err) - goto free_map; + goto free_map_sec; err = bpf_map_new_fd(map, f_flags); if (err < 0) { @@ -632,13 +635,13 @@ static int map_create(union bpf_attr *attr) return err; -free_map: - bpf_map_release_memlock(map); free_map_sec: security_bpf_map_free(map); -free_map_nouncharge: +free_map: btf_put(map->btf); + bpf_map_charge_move(&mem, &map->memory); map->ops->map_free(map); + bpf_map_charge_finish(&mem); return err; } @@ -1585,6 +1588,14 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type, default: return -EINVAL; } + case BPF_PROG_TYPE_CGROUP_SKB: + switch (expected_attach_type) { + case BPF_CGROUP_INET_INGRESS: + case BPF_CGROUP_INET_EGRESS: + return 0; + default: + return -EINVAL; + } default: return 0; } @@ -1604,7 +1615,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (CHECK_ATTR(BPF_PROG_LOAD)) return -EINVAL; - if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT)) + if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | + BPF_F_ANY_ALIGNMENT | + BPF_F_TEST_RND_HI32)) return -EINVAL; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && @@ -1834,6 +1847,10 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; + case BPF_PROG_TYPE_CGROUP_SKB: + return prog->enforce_expected_attach_type && + prog->expected_attach_type != attach_type ? + -EINVAL : 0; default: return 0; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 95f9354495ad..5c2cb5bd84ce 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -176,7 +176,7 @@ struct bpf_verifier_stack_elem { struct bpf_verifier_stack_elem *next; }; -#define BPF_COMPLEXITY_LIMIT_STACK 1024 +#define BPF_COMPLEXITY_LIMIT_JMP_SEQ 8192 #define BPF_COMPLEXITY_LIMIT_STATES 64 #define BPF_MAP_PTR_UNPRIV 1UL @@ -782,8 +782,9 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, if (err) goto err; elem->st.speculative |= speculative; - if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) { - verbose(env, "BPF program is too complex\n"); + if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) { + verbose(env, "The sequence of %d jumps is too complex.\n", + env->stack_size); goto err; } return &elem->st; @@ -981,6 +982,7 @@ static void mark_reg_not_init(struct bpf_verifier_env *env, __mark_reg_not_init(regs + regno); } +#define DEF_NOT_SUBREG (0) static void init_reg_state(struct bpf_verifier_env *env, struct bpf_func_state *state) { @@ -991,6 +993,7 @@ static void init_reg_state(struct bpf_verifier_env *env, mark_reg_not_init(env, regs, i); regs[i].live = REG_LIVE_NONE; regs[i].parent = NULL; + regs[i].subreg_def = DEF_NOT_SUBREG; } /* frame pointer */ @@ -1136,7 +1139,7 @@ next: */ static int mark_reg_read(struct bpf_verifier_env *env, const struct bpf_reg_state *state, - struct bpf_reg_state *parent) + struct bpf_reg_state *parent, u8 flag) { bool writes = parent == state->parent; /* Observe write marks */ int cnt = 0; @@ -1151,17 +1154,26 @@ static int mark_reg_read(struct bpf_verifier_env *env, parent->var_off.value, parent->off); return -EFAULT; } - if (parent->live & REG_LIVE_READ) + /* The first condition is more likely to be true than the + * second, checked it first. + */ + if ((parent->live & REG_LIVE_READ) == flag || + parent->live & REG_LIVE_READ64) /* The parentage chain never changes and * this parent was already marked as LIVE_READ. * There is no need to keep walking the chain again and * keep re-marking all parents as LIVE_READ. * This case happens when the same register is read * multiple times without writes into it in-between. + * Also, if parent has the stronger REG_LIVE_READ64 set, + * then no need to set the weak REG_LIVE_READ32. */ break; /* ... then we depend on parent's value */ - parent->live |= REG_LIVE_READ; + parent->live |= flag; + /* REG_LIVE_READ64 overrides REG_LIVE_READ32. */ + if (flag == REG_LIVE_READ64) + parent->live &= ~REG_LIVE_READ32; state = parent; parent = state->parent; writes = true; @@ -1173,12 +1185,129 @@ static int mark_reg_read(struct bpf_verifier_env *env, return 0; } +/* This function is supposed to be used by the following 32-bit optimization + * code only. It returns TRUE if the source or destination register operates + * on 64-bit, otherwise return FALSE. + */ +static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn, + u32 regno, struct bpf_reg_state *reg, enum reg_arg_type t) +{ + u8 code, class, op; + + code = insn->code; + class = BPF_CLASS(code); + op = BPF_OP(code); + if (class == BPF_JMP) { + /* BPF_EXIT for "main" will reach here. Return TRUE + * conservatively. + */ + if (op == BPF_EXIT) + return true; + if (op == BPF_CALL) { + /* BPF to BPF call will reach here because of marking + * caller saved clobber with DST_OP_NO_MARK for which we + * don't care the register def because they are anyway + * marked as NOT_INIT already. + */ + if (insn->src_reg == BPF_PSEUDO_CALL) + return false; + /* Helper call will reach here because of arg type + * check, conservatively return TRUE. + */ + if (t == SRC_OP) + return true; + + return false; + } + } + + if (class == BPF_ALU64 || class == BPF_JMP || + /* BPF_END always use BPF_ALU class. */ + (class == BPF_ALU && op == BPF_END && insn->imm == 64)) + return true; + + if (class == BPF_ALU || class == BPF_JMP32) + return false; + + if (class == BPF_LDX) { + if (t != SRC_OP) + return BPF_SIZE(code) == BPF_DW; + /* LDX source must be ptr. */ + return true; + } + + if (class == BPF_STX) { + if (reg->type != SCALAR_VALUE) + return true; + return BPF_SIZE(code) == BPF_DW; + } + + if (class == BPF_LD) { + u8 mode = BPF_MODE(code); + + /* LD_IMM64 */ + if (mode == BPF_IMM) + return true; + + /* Both LD_IND and LD_ABS return 32-bit data. */ + if (t != SRC_OP) + return false; + + /* Implicit ctx ptr. */ + if (regno == BPF_REG_6) + return true; + + /* Explicit source could be any width. */ + return true; + } + + if (class == BPF_ST) + /* The only source register for BPF_ST is a ptr. */ + return true; + + /* Conservatively return true at default. */ + return true; +} + +/* Return TRUE if INSN doesn't have explicit value define. */ +static bool insn_no_def(struct bpf_insn *insn) +{ + u8 class = BPF_CLASS(insn->code); + + return (class == BPF_JMP || class == BPF_JMP32 || + class == BPF_STX || class == BPF_ST); +} + +/* Return TRUE if INSN has defined any 32-bit value explicitly. */ +static bool insn_has_def32(struct bpf_verifier_env *env, struct bpf_insn *insn) +{ + if (insn_no_def(insn)) + return false; + + return !is_reg64(env, insn, insn->dst_reg, NULL, DST_OP); +} + +static void mark_insn_zext(struct bpf_verifier_env *env, + struct bpf_reg_state *reg) +{ + s32 def_idx = reg->subreg_def; + + if (def_idx == DEF_NOT_SUBREG) + return; + + env->insn_aux_data[def_idx - 1].zext_dst = true; + /* The dst will be zero extended, so won't be sub-register anymore. */ + reg->subreg_def = DEF_NOT_SUBREG; +} + static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, enum reg_arg_type t) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; + struct bpf_insn *insn = env->prog->insnsi + env->insn_idx; struct bpf_reg_state *reg, *regs = state->regs; + bool rw64; if (regno >= MAX_BPF_REG) { verbose(env, "R%d is invalid\n", regno); @@ -1186,6 +1315,7 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, } reg = ®s[regno]; + rw64 = is_reg64(env, insn, regno, reg, t); if (t == SRC_OP) { /* check whether register used as source operand can be read */ if (reg->type == NOT_INIT) { @@ -1196,7 +1326,11 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, if (regno == BPF_REG_FP) return 0; - return mark_reg_read(env, reg, reg->parent); + if (rw64) + mark_insn_zext(env, reg); + + return mark_reg_read(env, reg, reg->parent, + rw64 ? REG_LIVE_READ64 : REG_LIVE_READ32); } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { @@ -1204,6 +1338,7 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, return -EACCES; } reg->live |= REG_LIVE_WRITTEN; + reg->subreg_def = rw64 ? DEF_NOT_SUBREG : env->insn_idx + 1; if (t == DST_OP) mark_reg_unknown(env, regs, regno); } @@ -1383,7 +1518,8 @@ static int check_stack_read(struct bpf_verifier_env *env, state->regs[value_regno].live |= REG_LIVE_WRITTEN; } mark_reg_read(env, ®_state->stack[spi].spilled_ptr, - reg_state->stack[spi].spilled_ptr.parent); + reg_state->stack[spi].spilled_ptr.parent, + REG_LIVE_READ64); return 0; } else { int zeros = 0; @@ -1400,7 +1536,8 @@ static int check_stack_read(struct bpf_verifier_env *env, return -EACCES; } mark_reg_read(env, ®_state->stack[spi].spilled_ptr, - reg_state->stack[spi].spilled_ptr.parent); + reg_state->stack[spi].spilled_ptr.parent, + REG_LIVE_READ64); if (value_regno >= 0) { if (zeros == size) { /* any size read into register is zero extended, @@ -2109,6 +2246,12 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn value_regno); if (reg_type_may_be_null(reg_type)) regs[value_regno].id = ++env->id_gen; + /* A load of ctx field could have different + * actual load size with the one encoded in the + * insn. When the dst is PTR, it is for sure not + * a sub-register. + */ + regs[value_regno].subreg_def = DEF_NOT_SUBREG; } regs[value_regno].type = reg_type; } @@ -2368,7 +2511,8 @@ mark: * the whole slot to be marked as 'read' */ mark_reg_read(env, &state->stack[spi].spilled_ptr, - state->stack[spi].spilled_ptr.parent); + state->stack[spi].spilled_ptr.parent, + REG_LIVE_READ64); } return update_stack_depth(env, state, min_off); } @@ -3332,6 +3476,9 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } + /* helper call returns 64-bit value. */ + regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; + /* update return register (already marked as written above) */ if (fn->ret_type == RET_INTEGER) { /* sets type to SCALAR_VALUE */ @@ -4263,6 +4410,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) */ *dst_reg = *src_reg; dst_reg->live |= REG_LIVE_WRITTEN; + dst_reg->subreg_def = DEF_NOT_SUBREG; } else { /* R1 = (u32) R2 */ if (is_pointer_value(env, insn->src_reg)) { @@ -4273,6 +4421,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } else if (src_reg->type == SCALAR_VALUE) { *dst_reg = *src_reg; dst_reg->live |= REG_LIVE_WRITTEN; + dst_reg->subreg_def = env->insn_idx + 1; } else { mark_reg_unknown(env, regs, insn->dst_reg); @@ -5352,16 +5501,23 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) * Already marked as written above. */ mark_reg_unknown(env, regs, BPF_REG_0); + /* ld_abs load up to 32-bit skb data. */ + regs[BPF_REG_0].subreg_def = env->insn_idx + 1; return 0; } static int check_return_code(struct bpf_verifier_env *env) { + struct tnum enforce_attach_type_range = tnum_unknown; struct bpf_reg_state *reg; struct tnum range = tnum_range(0, 1); switch (env->prog->type) { case BPF_PROG_TYPE_CGROUP_SKB: + if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) { + range = tnum_range(0, 3); + enforce_attach_type_range = tnum_range(2, 3); + } case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_SOCK_OPS: @@ -5380,18 +5536,23 @@ static int check_return_code(struct bpf_verifier_env *env) } if (!tnum_in(range, reg->var_off)) { + char tn_buf[48]; + verbose(env, "At program exit the register R0 "); if (!tnum_is_unknown(reg->var_off)) { - char tn_buf[48]; - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "has value %s", tn_buf); } else { verbose(env, "has unknown scalar value"); } - verbose(env, " should have been 0 or 1\n"); + tnum_strn(tn_buf, sizeof(tn_buf), range); + verbose(env, " should have been %s\n", tn_buf); return -EINVAL; } + + if (!tnum_is_unknown(enforce_attach_type_range) && + tnum_in(enforce_attach_type_range, reg->var_off)) + env->prog->enforce_expected_attach_type = 1; return 0; } @@ -5435,7 +5596,25 @@ enum { BRANCH = 2, }; -#define STATE_LIST_MARK ((struct bpf_verifier_state_list *) -1L) +static u32 state_htab_size(struct bpf_verifier_env *env) +{ + return env->prog->len; +} + +static struct bpf_verifier_state_list **explored_state( + struct bpf_verifier_env *env, + int idx) +{ + struct bpf_verifier_state *cur = env->cur_state; + struct bpf_func_state *state = cur->frame[cur->curframe]; + + return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)]; +} + +static void init_explored_state(struct bpf_verifier_env *env, int idx) +{ + env->insn_aux_data[idx].prune_point = true; +} /* t, w, e - match pseudo-code above: * t - index of current instruction @@ -5461,7 +5640,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) if (e == BRANCH) /* mark branch target for state pruning */ - env->explored_states[w] = STATE_LIST_MARK; + init_explored_state(env, w); if (insn_state[w] == 0) { /* tree-edge */ @@ -5529,9 +5708,9 @@ peek_stack: else if (ret < 0) goto err_free; if (t + 1 < insn_cnt) - env->explored_states[t + 1] = STATE_LIST_MARK; + init_explored_state(env, t + 1); if (insns[t].src_reg == BPF_PSEUDO_CALL) { - env->explored_states[t] = STATE_LIST_MARK; + init_explored_state(env, t); ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env); if (ret == 1) goto peek_stack; @@ -5554,10 +5733,10 @@ peek_stack: * after every call and jump */ if (t + 1 < insn_cnt) - env->explored_states[t + 1] = STATE_LIST_MARK; + init_explored_state(env, t + 1); } else { /* conditional jump with two edges */ - env->explored_states[t] = STATE_LIST_MARK; + init_explored_state(env, t); ret = push_insn(t, t + 1, FALLTHROUGH, env); if (ret == 1) goto peek_stack; @@ -6005,12 +6184,10 @@ static void clean_live_states(struct bpf_verifier_env *env, int insn, struct bpf_verifier_state_list *sl; int i; - sl = env->explored_states[insn]; - if (!sl) - return; - - while (sl != STATE_LIST_MARK) { - if (sl->state.curframe != cur->curframe) + sl = *explored_state(env, insn); + while (sl) { + if (sl->state.insn_idx != insn || + sl->state.curframe != cur->curframe) goto next; for (i = 0; i <= cur->curframe; i++) if (sl->state.frame[i]->callsite != cur->frame[i]->callsite) @@ -6292,20 +6469,33 @@ static bool states_equal(struct bpf_verifier_env *env, return true; } +/* Return 0 if no propagation happened. Return negative error code if error + * happened. Otherwise, return the propagated bit. + */ static int propagate_liveness_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, struct bpf_reg_state *parent_reg) { + u8 parent_flag = parent_reg->live & REG_LIVE_READ; + u8 flag = reg->live & REG_LIVE_READ; int err; - if (parent_reg->live & REG_LIVE_READ || !(reg->live & REG_LIVE_READ)) + /* When comes here, read flags of PARENT_REG or REG could be any of + * REG_LIVE_READ64, REG_LIVE_READ32, REG_LIVE_NONE. There is no need + * of propagation if PARENT_REG has strongest REG_LIVE_READ64. + */ + if (parent_flag == REG_LIVE_READ64 || + /* Or if there is no read flag from REG. */ + !flag || + /* Or if the read flag from REG is the same as PARENT_REG. */ + parent_flag == flag) return 0; - err = mark_reg_read(env, reg, parent_reg); + err = mark_reg_read(env, reg, parent_reg, flag); if (err) return err; - return 0; + return flag; } /* A write screens off any subsequent reads; but write marks come from the @@ -6339,8 +6529,10 @@ static int propagate_liveness(struct bpf_verifier_env *env, for (i = frame < vstate->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) { err = propagate_liveness_reg(env, &state_reg[i], &parent_reg[i]); - if (err) + if (err < 0) return err; + if (err == REG_LIVE_READ64) + mark_insn_zext(env, &parent_reg[i]); } /* Propagate stack slots. */ @@ -6350,11 +6542,11 @@ static int propagate_liveness(struct bpf_verifier_env *env, state_reg = &state->stack[i].spilled_ptr; err = propagate_liveness_reg(env, state_reg, parent_reg); - if (err) + if (err < 0) return err; } } - return err; + return 0; } static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) @@ -6364,18 +6556,21 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err, states_cnt = 0; - pprev = &env->explored_states[insn_idx]; - sl = *pprev; - - if (!sl) + if (!env->insn_aux_data[insn_idx].prune_point) /* this 'insn_idx' instruction wasn't marked, so we will not * be doing state search here */ return 0; + pprev = explored_state(env, insn_idx); + sl = *pprev; + clean_live_states(env, insn_idx, cur); - while (sl != STATE_LIST_MARK) { + while (sl) { + states_cnt++; + if (sl->state.insn_idx != insn_idx) + goto next; if (states_equal(env, &sl->state, cur)) { sl->hit_cnt++; /* reached equivalent register/stack state, @@ -6393,7 +6588,6 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return err; return 1; } - states_cnt++; sl->miss_cnt++; /* heuristic to determine whether this state is beneficial * to keep checking from state equivalence point of view. @@ -6420,6 +6614,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) sl = *pprev; continue; } +next: pprev = &sl->next; sl = *pprev; } @@ -6451,8 +6646,9 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) kfree(new_sl); return err; } - new_sl->next = env->explored_states[insn_idx]; - env->explored_states[insn_idx] = new_sl; + new->insn_idx = insn_idx; + new_sl->next = *explored_state(env, insn_idx); + *explored_state(env, insn_idx) = new_sl; /* connect new state to parentage chain. Current frame needs all * registers connected. Only r6 - r9 of the callers are alive (pushed * to the stack implicitly by JITs) so in callers' frames connect just @@ -7130,14 +7326,23 @@ static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env) * insni[off, off + cnt). Adjust corresponding insn_aux_data by copying * [0, off) and [off, end) to new locations, so the patched range stays zero */ -static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len, - u32 off, u32 cnt) +static int adjust_insn_aux_data(struct bpf_verifier_env *env, + struct bpf_prog *new_prog, u32 off, u32 cnt) { struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data; + struct bpf_insn *insn = new_prog->insnsi; + u32 prog_len; int i; + /* aux info at OFF always needs adjustment, no matter fast path + * (cnt == 1) is taken or not. There is no guarantee INSN at OFF is the + * original insn at old prog. + */ + old_data[off].zext_dst = insn_has_def32(env, insn + off + cnt - 1); + if (cnt == 1) return 0; + prog_len = new_prog->len; new_data = vzalloc(array_size(prog_len, sizeof(struct bpf_insn_aux_data))); if (!new_data) @@ -7145,8 +7350,10 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len, memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off); memcpy(new_data + off + cnt - 1, old_data + off, sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); - for (i = off; i < off + cnt - 1; i++) + for (i = off; i < off + cnt - 1; i++) { new_data[i].seen = true; + new_data[i].zext_dst = insn_has_def32(env, insn + i); + } env->insn_aux_data = new_data; vfree(old_data); return 0; @@ -7179,7 +7386,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of env->insn_aux_data[off].orig_idx); return NULL; } - if (adjust_insn_aux_data(env, new_prog->len, off, len)) + if (adjust_insn_aux_data(env, new_prog, off, len)) return NULL; adjust_subprog_starts(env, off, len); return new_prog; @@ -7443,6 +7650,84 @@ static int opt_remove_nops(struct bpf_verifier_env *env) return 0; } +static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env, + const union bpf_attr *attr) +{ + struct bpf_insn *patch, zext_patch[2], rnd_hi32_patch[4]; + struct bpf_insn_aux_data *aux = env->insn_aux_data; + int i, patch_len, delta = 0, len = env->prog->len; + struct bpf_insn *insns = env->prog->insnsi; + struct bpf_prog *new_prog; + bool rnd_hi32; + + rnd_hi32 = attr->prog_flags & BPF_F_TEST_RND_HI32; + zext_patch[1] = BPF_ZEXT_REG(0); + rnd_hi32_patch[1] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, 0); + rnd_hi32_patch[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32); + rnd_hi32_patch[3] = BPF_ALU64_REG(BPF_OR, 0, BPF_REG_AX); + for (i = 0; i < len; i++) { + int adj_idx = i + delta; + struct bpf_insn insn; + + insn = insns[adj_idx]; + if (!aux[adj_idx].zext_dst) { + u8 code, class; + u32 imm_rnd; + + if (!rnd_hi32) + continue; + + code = insn.code; + class = BPF_CLASS(code); + if (insn_no_def(&insn)) + continue; + + /* NOTE: arg "reg" (the fourth one) is only used for + * BPF_STX which has been ruled out in above + * check, it is safe to pass NULL here. + */ + if (is_reg64(env, &insn, insn.dst_reg, NULL, DST_OP)) { + if (class == BPF_LD && + BPF_MODE(code) == BPF_IMM) + i++; + continue; + } + + /* ctx load could be transformed into wider load. */ + if (class == BPF_LDX && + aux[adj_idx].ptr_type == PTR_TO_CTX) + continue; + + imm_rnd = get_random_int(); + rnd_hi32_patch[0] = insn; + rnd_hi32_patch[1].imm = imm_rnd; + rnd_hi32_patch[3].dst_reg = insn.dst_reg; + patch = rnd_hi32_patch; + patch_len = 4; + goto apply_patch_buffer; + } + + if (!bpf_jit_needs_zext()) + continue; + + zext_patch[0] = insn; + zext_patch[1].dst_reg = insn.dst_reg; + zext_patch[1].src_reg = insn.dst_reg; + patch = zext_patch; + patch_len = 2; +apply_patch_buffer: + new_prog = bpf_patch_insn_data(env, adj_idx, patch, patch_len); + if (!new_prog) + return -ENOMEM; + env->prog = new_prog; + insns = new_prog->insnsi; + aux = env->insn_aux_data; + delta += patch_len - 1; + } + + return 0; +} + /* convert load instructions that access fields of a context type into a * sequence of instructions that access fields of the underlying structure: * struct __sk_buff -> struct sk_buff @@ -8130,16 +8415,15 @@ static void free_states(struct bpf_verifier_env *env) if (!env->explored_states) return; - for (i = 0; i < env->prog->len; i++) { + for (i = 0; i < state_htab_size(env); i++) { sl = env->explored_states[i]; - if (sl) - while (sl != STATE_LIST_MARK) { - sln = sl->next; - free_verifier_state(&sl->state, false); - kfree(sl); - sl = sln; - } + while (sl) { + sln = sl->next; + free_verifier_state(&sl->state, false); + kfree(sl); + sl = sln; + } } kvfree(env->explored_states); @@ -8239,7 +8523,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, goto skip_full_check; } - env->explored_states = kvcalloc(env->prog->len, + env->explored_states = kvcalloc(state_htab_size(env), sizeof(struct bpf_verifier_state_list *), GFP_USER); ret = -ENOMEM; @@ -8294,6 +8578,15 @@ skip_full_check: if (ret == 0) ret = fixup_bpf_calls(env); + /* do 32-bit optimization after insn patching has done so those patched + * insns could be handled correctly. + */ + if (ret == 0 && !bpf_prog_is_dev_bound(env->prog->aux)) { + ret = opt_subreg_zext_lo32_rnd_hi32(env, attr); + env->prog->aux->verifier_zext = bpf_jit_needs_zext() ? !ret + : false; + } + if (ret == 0) ret = fixup_call_args(env); diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c index 686d244e798d..22066c28ba61 100644 --- a/kernel/bpf/xskmap.c +++ b/kernel/bpf/xskmap.c @@ -37,13 +37,9 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *); cost += sizeof(struct list_head) * num_possible_cpus(); - if (cost >= U32_MAX - PAGE_SIZE) - goto free_m; - - m->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; /* Notice returns -EPERM on if map size is larger than memlock limit */ - err = bpf_map_precharge_memlock(m->map.pages); + err = bpf_map_charge_init(&m->map.memory, cost); if (err) goto free_m; @@ -51,7 +47,7 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) m->flush_list = alloc_percpu(struct list_head); if (!m->flush_list) - goto free_m; + goto free_charge; for_each_possible_cpu(cpu) INIT_LIST_HEAD(per_cpu_ptr(m->flush_list, cpu)); @@ -65,6 +61,8 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) free_percpu: free_percpu(m->flush_list); +free_charge: + bpf_map_charge_finish(&m->map.memory); free_m: kfree(m); return ERR_PTR(err); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 217cec4e22c6..ef9cfbfc82a9 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4955,8 +4955,6 @@ static void css_release_work_fn(struct work_struct *work) if (cgrp->kn) RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL); - - cgroup_bpf_put(cgrp); } mutex_unlock(&cgroup_mutex); @@ -5482,6 +5480,8 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) cgroup1_check_for_release(parent); + cgroup_bpf_offline(cgrp); + /* put the base reference */ percpu_ref_kill(&cgrp->self.refcnt); @@ -6221,6 +6221,7 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd) * Don't use cgroup_get_live(). */ cgroup_get(sock_cgroup_ptr(skcd)); + cgroup_bpf_get(sock_cgroup_ptr(skcd)); return; } @@ -6232,6 +6233,7 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd) cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { skcd->val = (unsigned long)cset->dfl_cgrp; + cgroup_bpf_get(cset->dfl_cgrp); break; } cpu_relax(); @@ -6242,7 +6244,10 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd) void cgroup_sk_free(struct sock_cgroup_data *skcd) { - cgroup_put(sock_cgroup_ptr(skcd)); + struct cgroup *cgrp = sock_cgroup_ptr(skcd); + + cgroup_bpf_put(cgrp); + cgroup_put(cgrp); } #endif /* CONFIG_SOCK_CGROUP_DATA */ diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f92d6ad5e080..3994a231eb92 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -19,6 +19,9 @@ #include "trace_probe.h" #include "trace.h" +#define bpf_event_rcu_dereference(p) \ + rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex)) + #ifdef CONFIG_MODULES struct bpf_trace_module { struct module *module; @@ -567,6 +570,69 @@ static const struct bpf_func_proto bpf_probe_read_str_proto = { .arg3_type = ARG_ANYTHING, }; +struct send_signal_irq_work { + struct irq_work irq_work; + struct task_struct *task; + u32 sig; +}; + +static DEFINE_PER_CPU(struct send_signal_irq_work, send_signal_work); + +static void do_bpf_send_signal(struct irq_work *entry) +{ + struct send_signal_irq_work *work; + + work = container_of(entry, struct send_signal_irq_work, irq_work); + group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, PIDTYPE_TGID); +} + +BPF_CALL_1(bpf_send_signal, u32, sig) +{ + struct send_signal_irq_work *work = NULL; + + /* Similar to bpf_probe_write_user, task needs to be + * in a sound condition and kernel memory access be + * permitted in order to send signal to the current + * task. + */ + if (unlikely(current->flags & (PF_KTHREAD | PF_EXITING))) + return -EPERM; + if (unlikely(uaccess_kernel())) + return -EPERM; + if (unlikely(!nmi_uaccess_okay())) + return -EPERM; + + if (in_nmi()) { + /* Do an early check on signal validity. Otherwise, + * the error is lost in deferred irq_work. + */ + if (unlikely(!valid_signal(sig))) + return -EINVAL; + + work = this_cpu_ptr(&send_signal_work); + if (work->irq_work.flags & IRQ_WORK_BUSY) + return -EBUSY; + + /* Add the current task, which is the target of sending signal, + * to the irq_work. The current task may change when queued + * irq works get executed. + */ + work->task = current; + work->sig = sig; + irq_work_queue(&work->irq_work); + return 0; + } + + return group_send_sig_info(sig, SEND_SIG_PRIV, current, PIDTYPE_TGID); +} + +static const struct bpf_func_proto bpf_send_signal_proto = { + .func = bpf_send_signal, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -617,6 +683,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; #endif + case BPF_FUNC_send_signal: + return &bpf_send_signal_proto; default: return NULL; } @@ -1034,7 +1102,7 @@ static DEFINE_MUTEX(bpf_event_mutex); int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog) { - struct bpf_prog_array __rcu *old_array; + struct bpf_prog_array *old_array; struct bpf_prog_array *new_array; int ret = -EEXIST; @@ -1052,7 +1120,7 @@ int perf_event_attach_bpf_prog(struct perf_event *event, if (event->prog) goto unlock; - old_array = event->tp_event->prog_array; + old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); if (old_array && bpf_prog_array_length(old_array) >= BPF_TRACE_MAX_PROGS) { ret = -E2BIG; @@ -1075,7 +1143,7 @@ unlock: void perf_event_detach_bpf_prog(struct perf_event *event) { - struct bpf_prog_array __rcu *old_array; + struct bpf_prog_array *old_array; struct bpf_prog_array *new_array; int ret; @@ -1084,7 +1152,7 @@ void perf_event_detach_bpf_prog(struct perf_event *event) if (!event->prog) goto unlock; - old_array = event->tp_event->prog_array; + old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array); if (ret == -ENOENT) goto unlock; @@ -1106,6 +1174,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) { struct perf_event_query_bpf __user *uquery = info; struct perf_event_query_bpf query = {}; + struct bpf_prog_array *progs; u32 *ids, prog_cnt, ids_len; int ret; @@ -1130,10 +1199,8 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) */ mutex_lock(&bpf_event_mutex); - ret = bpf_prog_array_copy_info(event->tp_event->prog_array, - ids, - ids_len, - &prog_cnt); + progs = bpf_event_rcu_dereference(event->tp_event->prog_array); + ret = bpf_prog_array_copy_info(progs, ids, ids_len, &prog_cnt); mutex_unlock(&bpf_event_mutex); if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) || @@ -1343,5 +1410,18 @@ static int __init bpf_event_init(void) return 0; } +static int __init send_signal_irq_work_init(void) +{ + int cpu; + struct send_signal_irq_work *work; + + for_each_possible_cpu(cpu) { + work = per_cpu_ptr(&send_signal_work, cpu); + init_irq_work(&work->irq_work, do_bpf_send_signal); + } + return 0; +} + fs_initcall(bpf_event_init); +subsys_initcall(send_signal_irq_work_init); #endif /* CONFIG_MODULES */ |